cleanup: "not x in y" -> "x not in y"

doc/hgmanpage.py

@@ -1,1110 +1,1110 b''
 # -*- coding: utf-8 -*-
 # $Id: manpage.py 6110 2009-08-31 14:40:33Z grubert $
 # Author: Engelbert Gruber <[e-mail]>
 # Copyright: This module is put into the public domain.
 
 """
 Simple man page writer for reStructuredText.
 
 Man pages (short for "manual pages") contain system documentation on unix-like
 systems. The pages are grouped in numbered sections:
 
  1 executable programs and shell commands
  2 system calls
  3 library functions
  4 special files
  5 file formats
  6 games
  7 miscellaneous
  8 system administration
 
 Man pages are written *troff*, a text file formatting system.
 
 See http://www.tldp.org/HOWTO/Man-Page for a start.
 
 Man pages have no subsection only parts.
 Standard parts
 
   NAME ,
   SYNOPSIS ,
   DESCRIPTION ,
   OPTIONS ,
   FILES ,
   SEE ALSO ,
   BUGS ,
 
 and
 
   AUTHOR .
 
 A unix-like system keeps an index of the DESCRIPTIONs, which is accesable
 by the command whatis or apropos.
 
 """
 
 __docformat__ = 'reStructuredText'
 
 import re
 
 from docutils import nodes, writers, languages
 try:
     import roman
 except ImportError:
     from docutils.utils import roman
 import inspect
 
 FIELD_LIST_INDENT = 7
 DEFINITION_LIST_INDENT = 7
 OPTION_LIST_INDENT = 7
 BLOCKQOUTE_INDENT = 3.5
 
 # Define two macros so man/roff can calculate the
 # indent/unindent margins by itself
 MACRO_DEF = (r""".
 .nr rst2man-indent-level 0
 .
 .de1 rstReportMargin
 \\$1 \\n[an-margin]
 level \\n[rst2man-indent-level]
 level margin: \\n[rst2man-indent\\n[rst2man-indent-level]]
 -
 \\n[rst2man-indent0]
 \\n[rst2man-indent1]
 \\n[rst2man-indent2]
 ..
 .de1 INDENT
 .\" .rstReportMargin pre:
 . RS \\$1
 . nr rst2man-indent\\n[rst2man-indent-level] \\n[an-margin]
 . nr rst2man-indent-level +1
 .\" .rstReportMargin post:
 ..
 .de UNINDENT
 . RE
 .\" indent \\n[an-margin]
 .\" old: \\n[rst2man-indent\\n[rst2man-indent-level]]
 .nr rst2man-indent-level -1
 .\" new: \\n[rst2man-indent\\n[rst2man-indent-level]]
 .in \\n[rst2man-indent\\n[rst2man-indent-level]]u
 ..
 """)
 
 class Writer(writers.Writer):
 
     supported = ('manpage')
     """Formats this writer supports."""
 
     output = None
     """Final translated form of `document`."""
 
     def __init__(self):
         writers.Writer.__init__(self)
         self.translator_class = Translator
 
     def translate(self):
         visitor = self.translator_class(self.document)
         self.document.walkabout(visitor)
         self.output = visitor.astext()
 
 
 class Table(object):
     def __init__(self):
         self._rows = []
         self._options = ['center']
         self._tab_char = '\t'
         self._coldefs = []
     def new_row(self):
         self._rows.append([])
     def append_separator(self, separator):
         """Append the separator for table head."""
         self._rows.append([separator])
     def append_cell(self, cell_lines):
         """cell_lines is an array of lines"""
         start = 0
         if len(cell_lines) > 0 and cell_lines[0] == '.sp\n':
             start = 1
         self._rows[-1].append(cell_lines[start:])
         if len(self._coldefs) < len(self._rows[-1]):
             self._coldefs.append('l')
     def _minimize_cell(self, cell_lines):
         """Remove leading and trailing blank and ``.sp`` lines"""
         while (cell_lines and cell_lines[0] in ('\n', '.sp\n')):
             del cell_lines[0]
         while (cell_lines and cell_lines[-1] in ('\n', '.sp\n')):
             del cell_lines[-1]
     def as_list(self):
         text = ['.TS\n']
         text.append(' '.join(self._options) + ';\n')
         text.append('|%s|.\n' % ('|'.join(self._coldefs)))
         for row in self._rows:
             # row = array of cells. cell = array of lines.
             text.append('_\n')       # line above
             text.append('T{\n')
             for i in range(len(row)):
                 cell = row[i]
                 self._minimize_cell(cell)
                 text.extend(cell)
                 if not text[-1].endswith('\n'):
                     text[-1] += '\n'
                 if i < len(row)-1:
                     text.append('T}'+self._tab_char+'T{\n')
                 else:
                     text.append('T}\n')
         text.append('_\n')
         text.append('.TE\n')
         return text
 
 class Translator(nodes.NodeVisitor):
     """"""
 
     words_and_spaces = re.compile(r'\S+| +|\n')
     document_start = """Man page generated from reStructeredText."""
 
     def __init__(self, document):
         nodes.NodeVisitor.__init__(self, document)
         self.settings = settings = document.settings
         lcode = settings.language_code
         arglen = len(inspect.getargspec(languages.get_language)[0])
         if arglen == 2:
             self.language = languages.get_language(lcode,
                                                    self.document.reporter)
         else:
             self.language = languages.get_language(lcode)
         self.head = []
         self.body = []
         self.foot = []
         self.section_level = 0
         self.context = []
         self.topic_class = ''
         self.colspecs = []
         self.compact_p = 1
         self.compact_simple = None
         # the list style "*" bullet or "#" numbered
         self._list_char = []
         # writing the header .TH and .SH NAME is postboned after
         # docinfo.
         self._docinfo = {
                 "title" : "", "title_upper": "",
                 "subtitle" : "",
                 "manual_section" : "", "manual_group" : "",
                 "author" : [],
                 "date" : "",
                 "copyright" : "",
                 "version" : "",
                     }
         self._docinfo_keys = []     # a list to keep the sequence as in source.
         self._docinfo_names = {}    # to get name from text not normalized.
         self._in_docinfo = None
         self._active_table = None
         self._in_literal = False
         self.header_written = 0
         self._line_block = 0
         self.authors = []
         self.section_level = 0
         self._indent = [0]
         # central definition of simple processing rules
         # what to output on : visit, depart
         # Do not use paragraph requests ``.PP`` because these set indentation.
         # use ``.sp``. Remove superfluous ``.sp`` in ``astext``.
         #
         # Fonts are put on a stack, the top one is used.
         # ``.ft P`` or ``\\fP`` pop from stack.
         # ``B`` bold, ``I`` italic, ``R`` roman should be available.
         # Hopefully ``C`` courier too.
         self.defs = {
                 'indent' : ('.INDENT %.1f\n', '.UNINDENT\n'),
                 'definition_list_item' : ('.TP', ''),
                 'field_name' : ('.TP\n.B ', '\n'),
                 'literal' : ('\\fB', '\\fP'),
                 'literal_block' : ('.sp\n.nf\n.ft C\n', '\n.ft P\n.fi\n'),
 
                 'option_list_item' : ('.TP\n', ''),
 
                 'reference' : (r'\%', r'\:'),
                 'emphasis': ('\\fI', '\\fP'),
                 'strong' : ('\\fB', '\\fP'),
                 'term' : ('\n.B ', '\n'),
                 'title_reference' : ('\\fI', '\\fP'),
 
                 'topic-title' : ('.SS ',),
                 'sidebar-title' : ('.SS ',),
 
                 'problematic' : ('\n.nf\n', '\n.fi\n'),
                     }
         # NOTE don't specify the newline before a dot-command, but ensure
         # it is there.
 
     def comment_begin(self, text):
         """Return commented version of the passed text WITHOUT end of
         line/comment."""
         prefix = '.\\" '
         out_text = ''.join(
             [(prefix + in_line + '\n')
             for in_line in text.split('\n')])
         return out_text
 
     def comment(self, text):
         """Return commented version of the passed text."""
         return self.comment_begin(text)+'.\n'
 
     def ensure_eol(self):
         """Ensure the last line in body is terminated by new line."""
         if self.body[-1][-1] != '\n':
             self.body.append('\n')
 
     def astext(self):
         """Return the final formatted document as a string."""
         if not self.header_written:
             # ensure we get a ".TH" as viewers require it.
             self.head.append(self.header())
         # filter body
         for i in xrange(len(self.body)-1, 0, -1):
             # remove superfluous vertical gaps.
             if self.body[i] == '.sp\n':
                 if self.body[i - 1][:4] in ('.BI ','.IP '):
                     self.body[i] = '.\n'
                 elif (self.body[i - 1][:3] == '.B ' and
                     self.body[i - 2][:4] == '.TP\n'):
                     self.body[i] = '.\n'
                 elif (self.body[i - 1] == '\n' and
                     self.body[i - 2][0] != '.' and
                     (self.body[i - 3][:7] == '.TP\n.B '
                         or self.body[i - 3][:4] == '\n.B ')
                      ):
                     self.body[i] = '.\n'
         return ''.join(self.head + self.body + self.foot)
 
     def deunicode(self, text):
         text = text.replace(u'\xa0', '\\ ')
         text = text.replace(u'\u2020', '\\(dg')
         return text
 
     def visit_Text(self, node):
         text = node.astext()
         text = text.replace('\\','\\e')
         replace_pairs = [
             (u'-', ur'\-'),
             (u'\'', ur'\(aq'),
             (u'´', ur'\''),
             (u'`', ur'\(ga'),
             ]
         for (in_char, out_markup) in replace_pairs:
             text = text.replace(in_char, out_markup)
         # unicode
         text = self.deunicode(text)
         if self._in_literal:
             # prevent interpretation of "." at line start
             if text[0] == '.':
                 text = '\\&' + text
             text = text.replace('\n.', '\n\\&.')
         self.body.append(text)
 
     def depart_Text(self, node):
         pass
 
     def list_start(self, node):
         class enum_char(object):
             enum_style = {
                     'bullet'     : '\\(bu',
                     'emdash'     : '\\(em',
                      }
 
             def __init__(self, style):
                 self._style = style
                 if 'start' in node:
                     self._cnt = node['start'] - 1
                 else:
                     self._cnt = 0
                 self._indent = 2
                 if style == 'arabic':
                     # indentation depends on number of childrens
                     # and start value.
                     self._indent = len(str(len(node.children)))
                     self._indent += len(str(self._cnt)) + 1
                 elif style == 'loweralpha':
                     self._cnt += ord('a') - 1
                     self._indent = 3
                 elif style == 'upperalpha':
                     self._cnt += ord('A') - 1
                     self._indent = 3
                 elif style.endswith('roman'):
                     self._indent = 5
 
             def next(self):
                 if self._style == 'bullet':
                     return self.enum_style[self._style]
                 elif self._style == 'emdash':
                     return self.enum_style[self._style]
                 self._cnt += 1
                 # TODO add prefix postfix
                 if self._style == 'arabic':
                     return "%d." % self._cnt
                 elif self._style in ('loweralpha', 'upperalpha'):
                     return "%c." % self._cnt
                 elif self._style.endswith('roman'):
                     res = roman.toRoman(self._cnt) + '.'
                     if self._style.startswith('upper'):
                         return res.upper()
                     return res.lower()
                 else:
                     return "%d." % self._cnt
             def get_width(self):
                 return self._indent
             def __repr__(self):
                 return 'enum_style-%s' % list(self._style)
 
         if 'enumtype' in node:
             self._list_char.append(enum_char(node['enumtype']))
         else:
             self._list_char.append(enum_char('bullet'))
         if len(self._list_char) > 1:
             # indent nested lists
             self.indent(self._list_char[-2].get_width())
         else:
             self.indent(self._list_char[-1].get_width())
 
     def list_end(self):
         self.dedent()
         self._list_char.pop()
 
     def header(self):
         tmpl = (".TH %(title_upper)s %(manual_section)s"
                 " \"%(date)s\" \"%(version)s\" \"%(manual_group)s\"\n"
                 ".SH NAME\n"
                 "%(title)s \- %(subtitle)s\n")
         return tmpl % self._docinfo
 
     def append_header(self):
         """append header with .TH and .SH NAME"""
         # NOTE before everything
         # .TH title_upper section date source manual
         if self.header_written:
             return
         self.body.append(self.header())
         self.body.append(MACRO_DEF)
         self.header_written = 1
 
     def visit_address(self, node):
         self.visit_docinfo_item(node, 'address')
 
     def depart_address(self, node):
         pass
 
     def visit_admonition(self, node, name=None):
         if name:
             self.body.append('.IP %s\n' %
                         self.language.labels.get(name, name))
 
     def depart_admonition(self, node):
         self.body.append('.RE\n')
 
     def visit_attention(self, node):
         self.visit_admonition(node, 'attention')
 
     depart_attention = depart_admonition
 
     def visit_docinfo_item(self, node, name):
         if name == 'author':
             self._docinfo[name].append(node.astext())
         else:
             self._docinfo[name] = node.astext()
         self._docinfo_keys.append(name)
         raise nodes.SkipNode
 
     def depart_docinfo_item(self, node):
         pass
 
     def visit_author(self, node):
         self.visit_docinfo_item(node, 'author')
 
     depart_author = depart_docinfo_item
 
     def visit_authors(self, node):
         # _author is called anyway.
         pass
 
     def depart_authors(self, node):
         pass
 
     def visit_block_quote(self, node):
         # BUG/HACK: indent alway uses the _last_ indention,
         # thus we need two of them.
         self.indent(BLOCKQOUTE_INDENT)
         self.indent(0)
 
     def depart_block_quote(self, node):
         self.dedent()
         self.dedent()
 
     def visit_bullet_list(self, node):
         self.list_start(node)
 
     def depart_bullet_list(self, node):
         self.list_end()
 
     def visit_caption(self, node):
         pass
 
     def depart_caption(self, node):
         pass
 
     def visit_caution(self, node):
         self.visit_admonition(node, 'caution')
 
     depart_caution = depart_admonition
 
     def visit_citation(self, node):
         num, text = node.astext().split(None, 1)
         num = num.strip()
         self.body.append('.IP [%s] 5\n' % num)
 
     def depart_citation(self, node):
         pass
 
     def visit_citation_reference(self, node):
         self.body.append('['+node.astext()+']')
         raise nodes.SkipNode
 
     def visit_classifier(self, node):
         pass
 
     def depart_classifier(self, node):
         pass
 
     def visit_colspec(self, node):
         self.colspecs.append(node)
 
     def depart_colspec(self, node):
         pass
 
     def write_colspecs(self):
         self.body.append("%s.\n" % ('L '*len(self.colspecs)))
 
     def visit_comment(self, node,
                       sub=re.compile('-(?=-)').sub):
         self.body.append(self.comment(node.astext()))
         raise nodes.SkipNode
 
     def visit_contact(self, node):
         self.visit_docinfo_item(node, 'contact')
 
     depart_contact = depart_docinfo_item
 
     def visit_container(self, node):
         pass
 
     def depart_container(self, node):
         pass
 
     def visit_compound(self, node):
         pass
 
     def depart_compound(self, node):
         pass
 
     def visit_copyright(self, node):
         self.visit_docinfo_item(node, 'copyright')
 
     def visit_danger(self, node):
         self.visit_admonition(node, 'danger')
 
     depart_danger = depart_admonition
 
     def visit_date(self, node):
         self.visit_docinfo_item(node, 'date')
 
     def visit_decoration(self, node):
         pass
 
     def depart_decoration(self, node):
         pass
 
     def visit_definition(self, node):
         pass
 
     def depart_definition(self, node):
         pass
 
     def visit_definition_list(self, node):
         self.indent(DEFINITION_LIST_INDENT)
 
     def depart_definition_list(self, node):
         self.dedent()
 
     def visit_definition_list_item(self, node):
         self.body.append(self.defs['definition_list_item'][0])
 
     def depart_definition_list_item(self, node):
         self.body.append(self.defs['definition_list_item'][1])
 
     def visit_description(self, node):
         pass
 
     def depart_description(self, node):
         pass
 
     def visit_docinfo(self, node):
         self._in_docinfo = 1
 
     def depart_docinfo(self, node):
         self._in_docinfo = None
         # NOTE nothing should be written before this
         self.append_header()
 
     def visit_doctest_block(self, node):
         self.body.append(self.defs['literal_block'][0])
         self._in_literal = True
 
     def depart_doctest_block(self, node):
         self._in_literal = False
         self.body.append(self.defs['literal_block'][1])
 
     def visit_document(self, node):
         # no blank line between comment and header.
         self.body.append(self.comment(self.document_start).rstrip()+'\n')
         # writing header is postboned
         self.header_written = 0
 
     def depart_document(self, node):
         if self._docinfo['author']:
             self.body.append('.SH AUTHOR\n%s\n'
                     % ', '.join(self._docinfo['author']))
         skip = ('author', 'copyright', 'date',
                 'manual_group', 'manual_section',
                 'subtitle',
                 'title', 'title_upper', 'version')
         for name in self._docinfo_keys:
             if name == 'address':
                 self.body.append("\n%s:\n%s%s.nf\n%s\n.fi\n%s%s" % (
                                     self.language.labels.get(name, name),
                                     self.defs['indent'][0] % 0,
                                     self.defs['indent'][0] % BLOCKQOUTE_INDENT,
                                     self._docinfo[name],
                                     self.defs['indent'][1],
                                     self.defs['indent'][1]))
-            elif not name in skip:
+            elif name not in skip:
                 if name in self._docinfo_names:
                     label = self._docinfo_names[name]
                 else:
                     label = self.language.labels.get(name, name)
                 self.body.append("\n%s: %s\n" % (label, self._docinfo[name]))
         if self._docinfo['copyright']:
             self.body.append('.SH COPYRIGHT\n%s\n'
                     % self._docinfo['copyright'])
         self.body.append(self.comment(
                         'Generated by docutils manpage writer.\n'))
 
     def visit_emphasis(self, node):
         self.body.append(self.defs['emphasis'][0])
 
     def depart_emphasis(self, node):
         self.body.append(self.defs['emphasis'][1])
 
     def visit_entry(self, node):
         # a cell in a table row
         if 'morerows' in node:
             self.document.reporter.warning('"table row spanning" not supported',
                     base_node=node)
         if 'morecols' in node:
             self.document.reporter.warning(
                     '"table cell spanning" not supported', base_node=node)
         self.context.append(len(self.body))
 
     def depart_entry(self, node):
         start = self.context.pop()
         self._active_table.append_cell(self.body[start:])
         del self.body[start:]
 
     def visit_enumerated_list(self, node):
         self.list_start(node)
 
     def depart_enumerated_list(self, node):
         self.list_end()
 
     def visit_error(self, node):
         self.visit_admonition(node, 'error')
 
     depart_error = depart_admonition
 
     def visit_field(self, node):
         pass
 
     def depart_field(self, node):
         pass
 
     def visit_field_body(self, node):
         if self._in_docinfo:
             name_normalized = self._field_name.lower().replace(" ","_")
             self._docinfo_names[name_normalized] = self._field_name
             self.visit_docinfo_item(node, name_normalized)
             raise nodes.SkipNode
 
     def depart_field_body(self, node):
         pass
 
     def visit_field_list(self, node):
         self.indent(FIELD_LIST_INDENT)
 
     def depart_field_list(self, node):
         self.dedent()
 
     def visit_field_name(self, node):
         if self._in_docinfo:
             self._field_name = node.astext()
             raise nodes.SkipNode
         else:
             self.body.append(self.defs['field_name'][0])
 
     def depart_field_name(self, node):
         self.body.append(self.defs['field_name'][1])
 
     def visit_figure(self, node):
         self.indent(2.5)
         self.indent(0)
 
     def depart_figure(self, node):
         self.dedent()
         self.dedent()
 
     def visit_footer(self, node):
         self.document.reporter.warning('"footer" not supported',
                 base_node=node)
 
     def depart_footer(self, node):
         pass
 
     def visit_footnote(self, node):
         num, text = node.astext().split(None, 1)
         num = num.strip()
         self.body.append('.IP [%s] 5\n' % self.deunicode(num))
 
     def depart_footnote(self, node):
         pass
 
     def footnote_backrefs(self, node):
         self.document.reporter.warning('"footnote_backrefs" not supported',
                 base_node=node)
 
     def visit_footnote_reference(self, node):
         self.body.append('['+self.deunicode(node.astext())+']')
         raise nodes.SkipNode
 
     def depart_footnote_reference(self, node):
         pass
 
     def visit_generated(self, node):
         pass
 
     def depart_generated(self, node):
         pass
 
     def visit_header(self, node):
         raise NotImplementedError, node.astext()
 
     def depart_header(self, node):
         pass
 
     def visit_hint(self, node):
         self.visit_admonition(node, 'hint')
 
     depart_hint = depart_admonition
 
     def visit_subscript(self, node):
         self.body.append('\\s-2\\d')
 
     def depart_subscript(self, node):
         self.body.append('\\u\\s0')
 
     def visit_superscript(self, node):
         self.body.append('\\s-2\\u')
 
     def depart_superscript(self, node):
         self.body.append('\\d\\s0')
 
     def visit_attribution(self, node):
         self.body.append('\\(em ')
 
     def depart_attribution(self, node):
         self.body.append('\n')
 
     def visit_image(self, node):
         self.document.reporter.warning('"image" not supported',
                 base_node=node)
         text = []
         if 'alt' in node.attributes:
             text.append(node.attributes['alt'])
         if 'uri' in node.attributes:
             text.append(node.attributes['uri'])
         self.body.append('[image: %s]\n' % ('/'.join(text)))
         raise nodes.SkipNode
 
     def visit_important(self, node):
         self.visit_admonition(node, 'important')
 
     depart_important = depart_admonition
 
     def visit_label(self, node):
         # footnote and citation
         if (isinstance(node.parent, nodes.footnote)
             or isinstance(node.parent, nodes.citation)):
             raise nodes.SkipNode
         self.document.reporter.warning('"unsupported "label"',
                 base_node=node)
         self.body.append('[')
 
     def depart_label(self, node):
         self.body.append(']\n')
 
     def visit_legend(self, node):
         pass
 
     def depart_legend(self, node):
         pass
 
     # WHAT should we use .INDENT, .UNINDENT ?
     def visit_line_block(self, node):
         self._line_block += 1
         if self._line_block == 1:
             self.body.append('.sp\n')
             self.body.append('.nf\n')
         else:
             self.body.append('.in +2\n')
 
     def depart_line_block(self, node):
         self._line_block -= 1
         if self._line_block == 0:
             self.body.append('.fi\n')
             self.body.append('.sp\n')
         else:
             self.body.append('.in -2\n')
 
     def visit_line(self, node):
         pass
 
     def depart_line(self, node):
         self.body.append('\n')
 
     def visit_list_item(self, node):
         # man 7 man argues to use ".IP" instead of ".TP"
         self.body.append('.IP %s %d\n' % (
                 self._list_char[-1].next(),
                 self._list_char[-1].get_width(),))
 
     def depart_list_item(self, node):
         pass
 
     def visit_literal(self, node):
         self.body.append(self.defs['literal'][0])
 
     def depart_literal(self, node):
         self.body.append(self.defs['literal'][1])
 
     def visit_literal_block(self, node):
         self.body.append(self.defs['literal_block'][0])
         self._in_literal = True
 
     def depart_literal_block(self, node):
         self._in_literal = False
         self.body.append(self.defs['literal_block'][1])
 
     def visit_meta(self, node):
         raise NotImplementedError, node.astext()
 
     def depart_meta(self, node):
         pass
 
     def visit_note(self, node):
         self.visit_admonition(node, 'note')
 
     depart_note = depart_admonition
 
     def indent(self, by=0.5):
         # if we are in a section ".SH" there already is a .RS
         step = self._indent[-1]
         self._indent.append(by)
         self.body.append(self.defs['indent'][0] % step)
 
     def dedent(self):
         self._indent.pop()
         self.body.append(self.defs['indent'][1])
 
     def visit_option_list(self, node):
         self.indent(OPTION_LIST_INDENT)
 
     def depart_option_list(self, node):
         self.dedent()
 
     def visit_option_list_item(self, node):
         # one item of the list
         self.body.append(self.defs['option_list_item'][0])
 
     def depart_option_list_item(self, node):
         self.body.append(self.defs['option_list_item'][1])
 
     def visit_option_group(self, node):
         # as one option could have several forms it is a group
         # options without parameter bold only, .B, -v
         # options with parameter bold italic, .BI, -f file
         #
         # we do not know if .B or .BI
         self.context.append('.B')           # blind guess
         self.context.append(len(self.body)) # to be able to insert later
         self.context.append(0)              # option counter
 
     def depart_option_group(self, node):
         self.context.pop()  # the counter
         start_position = self.context.pop()
         text = self.body[start_position:]
         del self.body[start_position:]
         self.body.append('%s%s\n' % (self.context.pop(), ''.join(text)))
 
     def visit_option(self, node):
         # each form of the option will be presented separately
         if self.context[-1] > 0:
             self.body.append(', ')
         if self.context[-3] == '.BI':
             self.body.append('\\')
         self.body.append(' ')
 
     def depart_option(self, node):
         self.context[-1] += 1
 
     def visit_option_string(self, node):
         # do not know if .B or .BI
         pass
 
     def depart_option_string(self, node):
         pass
 
     def visit_option_argument(self, node):
         self.context[-3] = '.BI' # bold/italic alternate
         if node['delimiter'] != ' ':
             self.body.append('\\fB%s ' % node['delimiter'])
         elif self.body[len(self.body)-1].endswith('='):
             # a blank only means no blank in output, just changing font
             self.body.append(' ')
         else:
             # blank backslash blank, switch font then a blank
             self.body.append(' \\ ')
 
     def depart_option_argument(self, node):
         pass
 
     def visit_organization(self, node):
         self.visit_docinfo_item(node, 'organization')
 
     def depart_organization(self, node):
         pass
 
     def visit_paragraph(self, node):
         # ``.PP`` : Start standard indented paragraph.
         # ``.LP`` : Start block paragraph, all except the first.
         # ``.P [type]``  : Start paragraph type.
         # NOTE dont use paragraph starts because they reset indentation.
         # ``.sp`` is only vertical space
         self.ensure_eol()
         self.body.append('.sp\n')
 
     def depart_paragraph(self, node):
         self.body.append('\n')
 
     def visit_problematic(self, node):
         self.body.append(self.defs['problematic'][0])
 
     def depart_problematic(self, node):
         self.body.append(self.defs['problematic'][1])
 
     def visit_raw(self, node):
         if node.get('format') == 'manpage':
             self.body.append(node.astext() + "\n")
         # Keep non-manpage raw text out of output:
         raise nodes.SkipNode
 
     def visit_reference(self, node):
         """E.g. link or email address."""
         self.body.append(self.defs['reference'][0])
 
     def depart_reference(self, node):
         self.body.append(self.defs['reference'][1])
 
     def visit_revision(self, node):
         self.visit_docinfo_item(node, 'revision')
 
     depart_revision = depart_docinfo_item
 
     def visit_row(self, node):
         self._active_table.new_row()
 
     def depart_row(self, node):
         pass
 
     def visit_section(self, node):
         self.section_level += 1
 
     def depart_section(self, node):
         self.section_level -= 1
 
     def visit_status(self, node):
         self.visit_docinfo_item(node, 'status')
 
     depart_status = depart_docinfo_item
 
     def visit_strong(self, node):
         self.body.append(self.defs['strong'][0])
 
     def depart_strong(self, node):
         self.body.append(self.defs['strong'][1])
 
     def visit_substitution_definition(self, node):
         """Internal only."""
         raise nodes.SkipNode
 
     def visit_substitution_reference(self, node):
         self.document.reporter.warning('"substitution_reference" not supported',
                 base_node=node)
 
     def visit_subtitle(self, node):
         if isinstance(node.parent, nodes.sidebar):
             self.body.append(self.defs['strong'][0])
         elif isinstance(node.parent, nodes.document):
             self.visit_docinfo_item(node, 'subtitle')
         elif isinstance(node.parent, nodes.section):
             self.body.append(self.defs['strong'][0])
 
     def depart_subtitle(self, node):
         # document subtitle calls SkipNode
         self.body.append(self.defs['strong'][1]+'\n.PP\n')
 
     def visit_system_message(self, node):
         # TODO add report_level
         #if node['level'] < self.document.reporter['writer'].report_level:
         #    Level is too low to display:
         #    raise nodes.SkipNode
         attr = {}
         backref_text = ''
         if node.hasattr('id'):
             attr['name'] = node['id']
         if node.hasattr('line'):
             line = ', line %s' % node['line']
         else:
             line = ''
         self.body.append('.IP "System Message: %s/%s (%s:%s)"\n'
                          % (node['type'], node['level'], node['source'], line))
 
     def depart_system_message(self, node):
         pass
 
     def visit_table(self, node):
         self._active_table = Table()
 
     def depart_table(self, node):
         self.ensure_eol()
         self.body.extend(self._active_table.as_list())
         self._active_table = None
 
     def visit_target(self, node):
         # targets are in-document hyper targets, without any use for man-pages.
         raise nodes.SkipNode
 
     def visit_tbody(self, node):
         pass
 
     def depart_tbody(self, node):
         pass
 
     def visit_term(self, node):
         self.body.append(self.defs['term'][0])
 
     def depart_term(self, node):
         self.body.append(self.defs['term'][1])
 
     def visit_tgroup(self, node):
         pass
 
     def depart_tgroup(self, node):
         pass
 
     def visit_thead(self, node):
         # MAYBE double line '='
         pass
 
     def depart_thead(self, node):
         # MAYBE double line '='
         pass
 
     def visit_tip(self, node):
         self.visit_admonition(node, 'tip')
 
     depart_tip = depart_admonition
 
     def visit_title(self, node):
         if isinstance(node.parent, nodes.topic):
             self.body.append(self.defs['topic-title'][0])
         elif isinstance(node.parent, nodes.sidebar):
             self.body.append(self.defs['sidebar-title'][0])
         elif isinstance(node.parent, nodes.admonition):
             self.body.append('.IP "')
         elif self.section_level == 0:
             self._docinfo['title'] = node.astext()
             # document title for .TH
             self._docinfo['title_upper'] = node.astext().upper()
             raise nodes.SkipNode
         elif self.section_level == 1:
             self.body.append('.SH ')
             for n in node.traverse(nodes.Text):
                 n.parent.replace(n, nodes.Text(n.astext().upper()))
         else:
             self.body.append('.SS ')
 
     def depart_title(self, node):
         if isinstance(node.parent, nodes.admonition):
             self.body.append('"')
         self.body.append('\n')
 
     def visit_title_reference(self, node):
         """inline citation reference"""
         self.body.append(self.defs['title_reference'][0])
 
     def depart_title_reference(self, node):
         self.body.append(self.defs['title_reference'][1])
 
     def visit_topic(self, node):
         pass
 
     def depart_topic(self, node):
         pass
 
     def visit_sidebar(self, node):
         pass
 
     def depart_sidebar(self, node):
         pass
 
     def visit_rubric(self, node):
         pass
 
     def depart_rubric(self, node):
         pass
 
     def visit_transition(self, node):
         # .PP      Begin a new paragraph and reset prevailing indent.
         # .sp N    leaves N lines of blank space.
         # .ce      centers the next line
         self.body.append('\n.sp\n.ce\n----\n')
 
     def depart_transition(self, node):
         self.body.append('\n.ce 0\n.sp\n')
 
     def visit_version(self, node):
         self.visit_docinfo_item(node, 'version')
 
     def visit_warning(self, node):
         self.visit_admonition(node, 'warning')
 
     depart_warning = depart_admonition
 
     def unimplemented_visit(self, node):
         raise NotImplementedError('visiting unimplemented node type: %s'
                                   % node.__class__.__name__)
 
 # vim: set fileencoding=utf-8 et ts=4 ai :

hgext/convert/convcmd.py

@@ -1,470 +1,470 b''
 # convcmd - convert extension commands definition
 #
 # Copyright 2005-2007 Matt Mackall <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 from common import NoRepo, MissingTool, SKIPREV, mapfile
 from cvs import convert_cvs
 from darcs import darcs_source
 from git import convert_git
 from hg import mercurial_source, mercurial_sink
 from subversion import svn_source, svn_sink
 from monotone import monotone_source
 from gnuarch import gnuarch_source
 from bzr import bzr_source
 from p4 import p4_source
 import filemap, common
 
 import os, shutil
 from mercurial import hg, util, encoding
 from mercurial.i18n import _
 
 orig_encoding = 'ascii'
 
 def recode(s):
     if isinstance(s, unicode):
         return s.encode(orig_encoding, 'replace')
     else:
         return s.decode('utf-8').encode(orig_encoding, 'replace')
 
 source_converters = [
     ('cvs', convert_cvs, 'branchsort'),
     ('git', convert_git, 'branchsort'),
     ('svn', svn_source, 'branchsort'),
     ('hg', mercurial_source, 'sourcesort'),
     ('darcs', darcs_source, 'branchsort'),
     ('mtn', monotone_source, 'branchsort'),
     ('gnuarch', gnuarch_source, 'branchsort'),
     ('bzr', bzr_source, 'branchsort'),
     ('p4', p4_source, 'branchsort'),
     ]
 
 sink_converters = [
     ('hg', mercurial_sink),
     ('svn', svn_sink),
     ]
 
 def convertsource(ui, path, type, rev):
     exceptions = []
     if type and type not in [s[0] for s in source_converters]:
         raise util.Abort(_('%s: invalid source repository type') % type)
     for name, source, sortmode in source_converters:
         try:
             if not type or name == type:
                 return source(ui, path, rev), sortmode
         except (NoRepo, MissingTool), inst:
             exceptions.append(inst)
     if not ui.quiet:
         for inst in exceptions:
             ui.write("%s\n" % inst)
     raise util.Abort(_('%s: missing or unsupported repository') % path)
 
 def convertsink(ui, path, type):
     if type and type not in [s[0] for s in sink_converters]:
         raise util.Abort(_('%s: invalid destination repository type') % type)
     for name, sink in sink_converters:
         try:
             if not type or name == type:
                 return sink(ui, path)
         except NoRepo, inst:
             ui.note(_("convert: %s\n") % inst)
         except MissingTool, inst:
             raise util.Abort('%s\n' % inst)
     raise util.Abort(_('%s: unknown repository type') % path)
 
 class progresssource(object):
     def __init__(self, ui, source, filecount):
         self.ui = ui
         self.source = source
         self.filecount = filecount
         self.retrieved = 0
 
     def getfile(self, file, rev):
         self.retrieved += 1
         self.ui.progress(_('getting files'), self.retrieved,
                          item=file, total=self.filecount)
         return self.source.getfile(file, rev)
 
     def lookuprev(self, rev):
         return self.source.lookuprev(rev)
 
     def close(self):
         self.ui.progress(_('getting files'), None)
 
 class converter(object):
     def __init__(self, ui, source, dest, revmapfile, opts):
 
         self.source = source
         self.dest = dest
         self.ui = ui
         self.opts = opts
         self.commitcache = {}
         self.authors = {}
         self.authorfile = None
 
         # Record converted revisions persistently: maps source revision
         # ID to target revision ID (both strings).  (This is how
         # incremental conversions work.)
         self.map = mapfile(ui, revmapfile)
 
         # Read first the dst author map if any
         authorfile = self.dest.authorfile()
         if authorfile and os.path.exists(authorfile):
             self.readauthormap(authorfile)
         # Extend/Override with new author map if necessary
         if opts.get('authormap'):
             self.readauthormap(opts.get('authormap'))
             self.authorfile = self.dest.authorfile()
 
         self.splicemap = common.parsesplicemap(opts.get('splicemap'))
         self.branchmap = mapfile(ui, opts.get('branchmap'))
 
     def walktree(self, heads):
         '''Return a mapping that identifies the uncommitted parents of every
         uncommitted changeset.'''
         visit = heads
         known = set()
         parents = {}
         while visit:
             n = visit.pop(0)
             if n in known or n in self.map:
                 continue
             known.add(n)
             self.ui.progress(_('scanning'), len(known), unit=_('revisions'))
             commit = self.cachecommit(n)
             parents[n] = []
             for p in commit.parents:
                 parents[n].append(p)
                 visit.append(p)
         self.ui.progress(_('scanning'), None)
 
         return parents
 
     def mergesplicemap(self, parents, splicemap):
         """A splicemap redefines child/parent relationships. Check the
         map contains valid revision identifiers and merge the new
         links in the source graph.
         """
         for c in splicemap:
             if c not in parents:
                 if not self.dest.hascommit(self.map.get(c, c)):
                     # Could be in source but not converted during this run
                     self.ui.warn(_('splice map revision %s is not being '
                                    'converted, ignoring\n') % c)
                 continue
             pc = []
             for p in splicemap[c]:
                 # We do not have to wait for nodes already in dest.
                 if self.dest.hascommit(self.map.get(p, p)):
                     continue
                 # Parent is not in dest and not being converted, not good
                 if p not in parents:
                     raise util.Abort(_('unknown splice map parent: %s') % p)
                 pc.append(p)
             parents[c] = pc
 
     def toposort(self, parents, sortmode):
         '''Return an ordering such that every uncommitted changeset is
         preceeded by all its uncommitted ancestors.'''
 
         def mapchildren(parents):
             """Return a (children, roots) tuple where 'children' maps parent
             revision identifiers to children ones, and 'roots' is the list of
             revisions without parents. 'parents' must be a mapping of revision
             identifier to its parents ones.
             """
             visit = parents.keys()
             seen = set()
             children = {}
             roots = []
 
             while visit:
                 n = visit.pop(0)
                 if n in seen:
                     continue
                 seen.add(n)
                 # Ensure that nodes without parents are present in the
                 # 'children' mapping.
                 children.setdefault(n, [])
                 hasparent = False
                 for p in parents[n]:
-                    if not p in self.map:
+                    if p not in self.map:
                         visit.append(p)
                         hasparent = True
                     children.setdefault(p, []).append(n)
                 if not hasparent:
                     roots.append(n)
 
             return children, roots
 
         # Sort functions are supposed to take a list of revisions which
         # can be converted immediately and pick one
 
         def makebranchsorter():
             """If the previously converted revision has a child in the
             eligible revisions list, pick it. Return the list head
             otherwise. Branch sort attempts to minimize branch
             switching, which is harmful for Mercurial backend
             compression.
             """
             prev = [None]
             def picknext(nodes):
                 next = nodes[0]
                 for n in nodes:
                     if prev[0] in parents[n]:
                         next = n
                         break
                 prev[0] = next
                 return next
             return picknext
 
         def makesourcesorter():
             """Source specific sort."""
             keyfn = lambda n: self.commitcache[n].sortkey
             def picknext(nodes):
                 return sorted(nodes, key=keyfn)[0]
             return picknext
 
         def makedatesorter():
             """Sort revisions by date."""
             dates = {}
             def getdate(n):
                 if n not in dates:
                     dates[n] = util.parsedate(self.commitcache[n].date)
                 return dates[n]
 
             def picknext(nodes):
                 return min([(getdate(n), n) for n in nodes])[1]
 
             return picknext
 
         if sortmode == 'branchsort':
             picknext = makebranchsorter()
         elif sortmode == 'datesort':
             picknext = makedatesorter()
         elif sortmode == 'sourcesort':
             picknext = makesourcesorter()
         else:
             raise util.Abort(_('unknown sort mode: %s') % sortmode)
 
         children, actives = mapchildren(parents)
 
         s = []
         pendings = {}
         while actives:
             n = picknext(actives)
             actives.remove(n)
             s.append(n)
 
             # Update dependents list
             for c in children.get(n, []):
                 if c not in pendings:
                     pendings[c] = [p for p in parents[c] if p not in self.map]
                 try:
                     pendings[c].remove(n)
                 except ValueError:
                     raise util.Abort(_('cycle detected between %s and %s')
                                        % (recode(c), recode(n)))
                 if not pendings[c]:
                     # Parents are converted, node is eligible
                     actives.insert(0, c)
                     pendings[c] = None
 
         if len(s) != len(parents):
             raise util.Abort(_("not all revisions were sorted"))
 
         return s
 
     def writeauthormap(self):
         authorfile = self.authorfile
         if authorfile:
             self.ui.status(_('Writing author map file %s\n') % authorfile)
             ofile = open(authorfile, 'w+')
             for author in self.authors:
                 ofile.write("%s=%s\n" % (author, self.authors[author]))
             ofile.close()
 
     def readauthormap(self, authorfile):
         afile = open(authorfile, 'r')
         for line in afile:
 
             line = line.strip()
             if not line or line.startswith('#'):
                 continue
 
             try:
                 srcauthor, dstauthor = line.split('=', 1)
             except ValueError:
                 msg = _('Ignoring bad line in author map file %s: %s\n')
                 self.ui.warn(msg % (authorfile, line.rstrip()))
                 continue
 
             srcauthor = srcauthor.strip()
             dstauthor = dstauthor.strip()
             if self.authors.get(srcauthor) in (None, dstauthor):
                 msg = _('mapping author %s to %s\n')
                 self.ui.debug(msg % (srcauthor, dstauthor))
                 self.authors[srcauthor] = dstauthor
                 continue
 
             m = _('overriding mapping for author %s, was %s, will be %s\n')
             self.ui.status(m % (srcauthor, self.authors[srcauthor], dstauthor))
 
         afile.close()
 
     def cachecommit(self, rev):
         commit = self.source.getcommit(rev)
         commit.author = self.authors.get(commit.author, commit.author)
         commit.branch = self.branchmap.get(commit.branch, commit.branch)
         self.commitcache[rev] = commit
         return commit
 
     def copy(self, rev):
         commit = self.commitcache[rev]
 
         changes = self.source.getchanges(rev)
         if isinstance(changes, basestring):
             if changes == SKIPREV:
                 dest = SKIPREV
             else:
                 dest = self.map[changes]
             self.map[rev] = dest
             return
         files, copies = changes
         pbranches = []
         if commit.parents:
             for prev in commit.parents:
                 if prev not in self.commitcache:
                     self.cachecommit(prev)
                 pbranches.append((self.map[prev],
                                   self.commitcache[prev].branch))
         self.dest.setbranch(commit.branch, pbranches)
         try:
             parents = self.splicemap[rev]
             self.ui.status(_('spliced in %s as parents of %s\n') %
                            (parents, rev))
             parents = [self.map.get(p, p) for p in parents]
         except KeyError:
             parents = [b[0] for b in pbranches]
         source = progresssource(self.ui, self.source, len(files))
         newnode = self.dest.putcommit(files, copies, parents, commit,
                                       source, self.map)
         source.close()
         self.source.converted(rev, newnode)
         self.map[rev] = newnode
 
     def convert(self, sortmode):
         try:
             self.source.before()
             self.dest.before()
             self.source.setrevmap(self.map)
             self.ui.status(_("scanning source...\n"))
             heads = self.source.getheads()
             parents = self.walktree(heads)
             self.mergesplicemap(parents, self.splicemap)
             self.ui.status(_("sorting...\n"))
             t = self.toposort(parents, sortmode)
             num = len(t)
             c = None
 
             self.ui.status(_("converting...\n"))
             for i, c in enumerate(t):
                 num -= 1
                 desc = self.commitcache[c].desc
                 if "\n" in desc:
                     desc = desc.splitlines()[0]
                 # convert log message to local encoding without using
                 # tolocal() because the encoding.encoding convert()
                 # uses is 'utf-8'
                 self.ui.status("%d %s\n" % (num, recode(desc)))
                 self.ui.note(_("source: %s\n") % recode(c))
                 self.ui.progress(_('converting'), i, unit=_('revisions'),
                                  total=len(t))
                 self.copy(c)
             self.ui.progress(_('converting'), None)
 
             tags = self.source.gettags()
             ctags = {}
             for k in tags:
                 v = tags[k]
                 if self.map.get(v, SKIPREV) != SKIPREV:
                     ctags[k] = self.map[v]
 
             if c and ctags:
                 nrev, tagsparent = self.dest.puttags(ctags)
                 if nrev and tagsparent:
                     # write another hash correspondence to override the previous
                     # one so we don't end up with extra tag heads
                     tagsparents = [e for e in self.map.iteritems()
                                    if e[1] == tagsparent]
                     if tagsparents:
                         self.map[tagsparents[0][0]] = nrev
 
             bookmarks = self.source.getbookmarks()
             cbookmarks = {}
             for k in bookmarks:
                 v = bookmarks[k]
                 if self.map.get(v, SKIPREV) != SKIPREV:
                     cbookmarks[k] = self.map[v]
 
             if c and cbookmarks:
                 self.dest.putbookmarks(cbookmarks)
 
             self.writeauthormap()
         finally:
             self.cleanup()
 
     def cleanup(self):
         try:
             self.dest.after()
         finally:
             self.source.after()
         self.map.close()
 
 def convert(ui, src, dest=None, revmapfile=None, **opts):
     global orig_encoding
     orig_encoding = encoding.encoding
     encoding.encoding = 'UTF-8'
 
     # support --authors as an alias for --authormap
     if not opts.get('authormap'):
         opts['authormap'] = opts.get('authors')
 
     if not dest:
         dest = hg.defaultdest(src) + "-hg"
         ui.status(_("assuming destination %s\n") % dest)
 
     destc = convertsink(ui, dest, opts.get('dest_type'))
 
     try:
         srcc, defaultsort = convertsource(ui, src, opts.get('source_type'),
                                           opts.get('rev'))
     except Exception:
         for path in destc.created:
             shutil.rmtree(path, True)
         raise
 
     sortmodes = ('branchsort', 'datesort', 'sourcesort')
     sortmode = [m for m in sortmodes if opts.get(m)]
     if len(sortmode) > 1:
         raise util.Abort(_('more than one sort mode specified'))
     sortmode = sortmode and sortmode[0] or defaultsort
     if sortmode == 'sourcesort' and not srcc.hasnativeorder():
         raise util.Abort(_('--sourcesort is not supported by this data source'))
 
     fmap = opts.get('filemap')
     if fmap:
         srcc = filemap.filemap_source(ui, srcc, fmap)
         destc.setfilemapmode(True)
 
     if not revmapfile:
         try:
             revmapfile = destc.revmapfile()
         except:
             revmapfile = os.path.join(destc, "map")
 
     c = converter(ui, srcc, destc, revmapfile, opts)
     c.convert(sortmode)
 

hgext/convert/hg.py

@@ -1,395 +1,395 b''
 # hg.py - hg backend for convert extension
 #
 #  Copyright 2005-2009 Matt Mackall <[e-mail]> and others
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 # Notes for hg->hg conversion:
 #
 # * Old versions of Mercurial didn't trim the whitespace from the ends
 #   of commit messages, but new versions do.  Changesets created by
 #   those older versions, then converted, may thus have different
 #   hashes for changesets that are otherwise identical.
 #
 # * Using "--config convert.hg.saverev=true" will make the source
 #   identifier to be stored in the converted revision. This will cause
 #   the converted revision to have a different identity than the
 #   source.
 
 
 import os, time, cStringIO
 from mercurial.i18n import _
 from mercurial.node import bin, hex, nullid
 from mercurial import hg, util, context, bookmarks, error
 
 from common import NoRepo, commit, converter_source, converter_sink
 
 class mercurial_sink(converter_sink):
     def __init__(self, ui, path):
         converter_sink.__init__(self, ui, path)
         self.branchnames = ui.configbool('convert', 'hg.usebranchnames', True)
         self.clonebranches = ui.configbool('convert', 'hg.clonebranches', False)
         self.tagsbranch = ui.config('convert', 'hg.tagsbranch', 'default')
         self.lastbranch = None
         if os.path.isdir(path) and len(os.listdir(path)) > 0:
             try:
                 self.repo = hg.repository(self.ui, path)
                 if not self.repo.local():
                     raise NoRepo(_('%s is not a local Mercurial repository')
                                  % path)
             except error.RepoError, err:
                 ui.traceback()
                 raise NoRepo(err.args[0])
         else:
             try:
                 ui.status(_('initializing destination %s repository\n') % path)
                 self.repo = hg.repository(self.ui, path, create=True)
                 if not self.repo.local():
                     raise NoRepo(_('%s is not a local Mercurial repository')
                                  % path)
                 self.created.append(path)
             except error.RepoError:
                 ui.traceback()
                 raise NoRepo(_("could not create hg repository %s as sink")
                              % path)
         self.lock = None
         self.wlock = None
         self.filemapmode = False
 
     def before(self):
         self.ui.debug('run hg sink pre-conversion action\n')
         self.wlock = self.repo.wlock()
         self.lock = self.repo.lock()
 
     def after(self):
         self.ui.debug('run hg sink post-conversion action\n')
         if self.lock:
             self.lock.release()
         if self.wlock:
             self.wlock.release()
 
     def revmapfile(self):
         return self.repo.join("shamap")
 
     def authorfile(self):
         return self.repo.join("authormap")
 
     def getheads(self):
         h = self.repo.changelog.heads()
         return [hex(x) for x in h]
 
     def setbranch(self, branch, pbranches):
         if not self.clonebranches:
             return
 
         setbranch = (branch != self.lastbranch)
         self.lastbranch = branch
         if not branch:
             branch = 'default'
         pbranches = [(b[0], b[1] and b[1] or 'default') for b in pbranches]
         pbranch = pbranches and pbranches[0][1] or 'default'
 
         branchpath = os.path.join(self.path, branch)
         if setbranch:
             self.after()
             try:
                 self.repo = hg.repository(self.ui, branchpath)
             except:
                 self.repo = hg.repository(self.ui, branchpath, create=True)
             self.before()
 
         # pbranches may bring revisions from other branches (merge parents)
         # Make sure we have them, or pull them.
         missings = {}
         for b in pbranches:
             try:
                 self.repo.lookup(b[0])
             except:
                 missings.setdefault(b[1], []).append(b[0])
 
         if missings:
             self.after()
             for pbranch, heads in missings.iteritems():
                 pbranchpath = os.path.join(self.path, pbranch)
                 prepo = hg.peer(self.ui, {}, pbranchpath)
                 self.ui.note(_('pulling from %s into %s\n') % (pbranch, branch))
                 self.repo.pull(prepo, [prepo.lookup(h) for h in heads])
             self.before()
 
     def _rewritetags(self, source, revmap, data):
         fp = cStringIO.StringIO()
         for line in data.splitlines():
             s = line.split(' ', 1)
             if len(s) != 2:
                 continue
             revid = revmap.get(source.lookuprev(s[0]))
             if not revid:
                 continue
             fp.write('%s %s\n' % (revid, s[1]))
         return fp.getvalue()
 
     def putcommit(self, files, copies, parents, commit, source, revmap):
 
         files = dict(files)
         def getfilectx(repo, memctx, f):
             v = files[f]
             data, mode = source.getfile(f, v)
             if f == '.hgtags':
                 data = self._rewritetags(source, revmap, data)
             return context.memfilectx(f, data, 'l' in mode, 'x' in mode,
                                       copies.get(f))
 
         pl = []
         for p in parents:
             if p not in pl:
                 pl.append(p)
         parents = pl
         nparents = len(parents)
         if self.filemapmode and nparents == 1:
             m1node = self.repo.changelog.read(bin(parents[0]))[0]
             parent = parents[0]
 
         if len(parents) < 2:
             parents.append(nullid)
         if len(parents) < 2:
             parents.append(nullid)
         p2 = parents.pop(0)
 
         text = commit.desc
         extra = commit.extra.copy()
         if self.branchnames and commit.branch:
             extra['branch'] = commit.branch
         if commit.rev:
             extra['convert_revision'] = commit.rev
 
         while parents:
             p1 = p2
             p2 = parents.pop(0)
             ctx = context.memctx(self.repo, (p1, p2), text, files.keys(),
                                  getfilectx, commit.author, commit.date, extra)
             self.repo.commitctx(ctx)
             text = "(octopus merge fixup)\n"
             p2 = hex(self.repo.changelog.tip())
 
         if self.filemapmode and nparents == 1:
             man = self.repo.manifest
             mnode = self.repo.changelog.read(bin(p2))[0]
             closed = 'close' in commit.extra
             if not closed and not man.cmp(m1node, man.revision(mnode)):
                 self.ui.status(_("filtering out empty revision\n"))
                 self.repo.rollback(force=True)
                 return parent
         return p2
 
     def puttags(self, tags):
         try:
             parentctx = self.repo[self.tagsbranch]
             tagparent = parentctx.node()
         except error.RepoError:
             parentctx = None
             tagparent = nullid
 
         try:
             oldlines = sorted(parentctx['.hgtags'].data().splitlines(True))
         except:
             oldlines = []
 
         newlines = sorted([("%s %s\n" % (tags[tag], tag)) for tag in tags])
         if newlines == oldlines:
             return None, None
         data = "".join(newlines)
         def getfilectx(repo, memctx, f):
             return context.memfilectx(f, data, False, False, None)
 
         self.ui.status(_("updating tags\n"))
         date = "%s 0" % int(time.mktime(time.gmtime()))
         extra = {'branch': self.tagsbranch}
         ctx = context.memctx(self.repo, (tagparent, None), "update tags",
                              [".hgtags"], getfilectx, "convert-repo", date,
                              extra)
         self.repo.commitctx(ctx)
         return hex(self.repo.changelog.tip()), hex(tagparent)
 
     def setfilemapmode(self, active):
         self.filemapmode = active
 
     def putbookmarks(self, updatedbookmark):
         if not len(updatedbookmark):
             return
 
         self.ui.status(_("updating bookmarks\n"))
         for bookmark in updatedbookmark:
             self.repo._bookmarks[bookmark] = bin(updatedbookmark[bookmark])
             bookmarks.write(self.repo)
 
     def hascommit(self, rev):
-        if not rev in self.repo and self.clonebranches:
+        if rev not in self.repo and self.clonebranches:
             raise util.Abort(_('revision %s not found in destination '
                                'repository (lookups with clonebranches=true '
                                'are not implemented)') % rev)
         return rev in self.repo
 
 class mercurial_source(converter_source):
     def __init__(self, ui, path, rev=None):
         converter_source.__init__(self, ui, path, rev)
         self.ignoreerrors = ui.configbool('convert', 'hg.ignoreerrors', False)
         self.ignored = set()
         self.saverev = ui.configbool('convert', 'hg.saverev', False)
         try:
             self.repo = hg.repository(self.ui, path)
             # try to provoke an exception if this isn't really a hg
             # repo, but some other bogus compatible-looking url
             if not self.repo.local():
                 raise error.RepoError()
         except error.RepoError:
             ui.traceback()
             raise NoRepo(_("%s is not a local Mercurial repository") % path)
         self.lastrev = None
         self.lastctx = None
         self._changescache = None
         self.convertfp = None
         # Restrict converted revisions to startrev descendants
         startnode = ui.config('convert', 'hg.startrev')
         if startnode is not None:
             try:
                 startnode = self.repo.lookup(startnode)
             except error.RepoError:
                 raise util.Abort(_('%s is not a valid start revision')
                                  % startnode)
             startrev = self.repo.changelog.rev(startnode)
             children = {startnode: 1}
             for rev in self.repo.changelog.descendants(startrev):
                 children[self.repo.changelog.node(rev)] = 1
             self.keep = children.__contains__
         else:
             self.keep = util.always
 
     def changectx(self, rev):
         if self.lastrev != rev:
             self.lastctx = self.repo[rev]
             self.lastrev = rev
         return self.lastctx
 
     def parents(self, ctx):
         return [p for p in ctx.parents() if p and self.keep(p.node())]
 
     def getheads(self):
         if self.rev:
             heads = [self.repo[self.rev].node()]
         else:
             heads = self.repo.heads()
         return [hex(h) for h in heads if self.keep(h)]
 
     def getfile(self, name, rev):
         try:
             fctx = self.changectx(rev)[name]
             return fctx.data(), fctx.flags()
         except error.LookupError, err:
             raise IOError(err)
 
     def getchanges(self, rev):
         ctx = self.changectx(rev)
         parents = self.parents(ctx)
         if not parents:
             files = sorted(ctx.manifest())
             # getcopies() is not needed for roots, but it is a simple way to
             # detect missing revlogs and abort on errors or populate
             # self.ignored
             self.getcopies(ctx, parents, files)
             return [(f, rev) for f in files if f not in self.ignored], {}
         if self._changescache and self._changescache[0] == rev:
             m, a, r = self._changescache[1]
         else:
             m, a, r = self.repo.status(parents[0].node(), ctx.node())[:3]
         # getcopies() detects missing revlogs early, run it before
         # filtering the changes.
         copies = self.getcopies(ctx, parents, m + a)
         changes = [(name, rev) for name in m + a + r
                    if name not in self.ignored]
         return sorted(changes), copies
 
     def getcopies(self, ctx, parents, files):
         copies = {}
         for name in files:
             if name in self.ignored:
                 continue
             try:
                 copysource, copynode = ctx.filectx(name).renamed()
                 if copysource in self.ignored or not self.keep(copynode):
                     continue
                 # Ignore copy sources not in parent revisions
                 found = False
                 for p in parents:
                     if copysource in p:
                         found = True
                         break
                 if not found:
                     continue
                 copies[name] = copysource
             except TypeError:
                 pass
             except error.LookupError, e:
                 if not self.ignoreerrors:
                     raise
                 self.ignored.add(name)
                 self.ui.warn(_('ignoring: %s\n') % e)
         return copies
 
     def getcommit(self, rev):
         ctx = self.changectx(rev)
         parents = [p.hex() for p in self.parents(ctx)]
         if self.saverev:
             crev = rev
         else:
             crev = None
         return commit(author=ctx.user(),
                       date=util.datestr(ctx.date(), '%Y-%m-%d %H:%M:%S %1%2'),
                       desc=ctx.description(), rev=crev, parents=parents,
                       branch=ctx.branch(), extra=ctx.extra(),
                       sortkey=ctx.rev())
 
     def gettags(self):
         tags = [t for t in self.repo.tagslist() if t[0] != 'tip']
         return dict([(name, hex(node)) for name, node in tags
                      if self.keep(node)])
 
     def getchangedfiles(self, rev, i):
         ctx = self.changectx(rev)
         parents = self.parents(ctx)
         if not parents and i is None:
             i = 0
             changes = [], ctx.manifest().keys(), []
         else:
             i = i or 0
             changes = self.repo.status(parents[i].node(), ctx.node())[:3]
         changes = [[f for f in l if f not in self.ignored] for l in changes]
 
         if i == 0:
             self._changescache = (rev, changes)
 
         return changes[0] + changes[1] + changes[2]
 
     def converted(self, rev, destrev):
         if self.convertfp is None:
             self.convertfp = open(self.repo.join('shamap'), 'a')
         self.convertfp.write('%s %s\n' % (destrev, rev))
         self.convertfp.flush()
 
     def before(self):
         self.ui.debug('run hg source pre-conversion action\n')
 
     def after(self):
         self.ui.debug('run hg source post-conversion action\n')
 
     def hasnativeorder(self):
         return True
 
     def lookuprev(self, rev):
         try:
             return hex(self.repo.lookup(rev))
         except error.RepoError:
             return None
 
     def getbookmarks(self):
         return bookmarks.listbookmarks(self.repo)

hgext/extdiff.py

@@ -1,329 +1,329 b''
 # extdiff.py - external diff program support for mercurial
 #
 # Copyright 2006 Vadim Gelfer <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 '''command to allow external programs to compare revisions
 
 The extdiff Mercurial extension allows you to use external programs
 to compare revisions, or revision with working directory. The external
 diff programs are called with a configurable set of options and two
 non-option arguments: paths to directories containing snapshots of
 files to compare.
 
 The extdiff extension also allows you to configure new diff commands, so
 you do not need to type :hg:`extdiff -p kdiff3` always. ::
 
   [extdiff]
   # add new command that runs GNU diff(1) in 'context diff' mode
   cdiff = gdiff -Nprc5
   ## or the old way:
   #cmd.cdiff = gdiff
   #opts.cdiff = -Nprc5
 
   # add new command called vdiff, runs kdiff3
   vdiff = kdiff3
 
   # add new command called meld, runs meld (no need to name twice)
   meld =
 
   # add new command called vimdiff, runs gvimdiff with DirDiff plugin
   # (see http://www.vim.org/scripts/script.php?script_id=102) Non
   # English user, be sure to put "let g:DirDiffDynamicDiffText = 1" in
   # your .vimrc
   vimdiff = gvim -f "+next" \\
             "+execute 'DirDiff' fnameescape(argv(0)) fnameescape(argv(1))"
 
 Tool arguments can include variables that are expanded at runtime::
 
   $parent1, $plabel1 - filename, descriptive label of first parent
   $child,   $clabel  - filename, descriptive label of child revision
   $parent2, $plabel2 - filename, descriptive label of second parent
   $root              - repository root
   $parent is an alias for $parent1.
 
 The extdiff extension will look in your [diff-tools] and [merge-tools]
 sections for diff tool arguments, when none are specified in [extdiff].
 
 ::
 
   [extdiff]
   kdiff3 =
 
   [diff-tools]
   kdiff3.diffargs=--L1 '$plabel1' --L2 '$clabel' $parent $child
 
 You can use -I/-X and list of file or directory names like normal
 :hg:`diff` command. The extdiff extension makes snapshots of only
 needed files, so running the external diff program will actually be
 pretty fast (at least faster than having to compare the entire tree).
 '''
 
 from mercurial.i18n import _
 from mercurial.node import short, nullid
 from mercurial import scmutil, scmutil, util, commands, encoding
 import os, shlex, shutil, tempfile, re
 
 def snapshot(ui, repo, files, node, tmproot):
     '''snapshot files as of some revision
     if not using snapshot, -I/-X does not work and recursive diff
     in tools like kdiff3 and meld displays too many files.'''
     dirname = os.path.basename(repo.root)
     if dirname == "":
         dirname = "root"
     if node is not None:
         dirname = '%s.%s' % (dirname, short(node))
     base = os.path.join(tmproot, dirname)
     os.mkdir(base)
     if node is not None:
         ui.note(_('making snapshot of %d files from rev %s\n') %
                 (len(files), short(node)))
     else:
         ui.note(_('making snapshot of %d files from working directory\n') %
             (len(files)))
     wopener = scmutil.opener(base)
     fns_and_mtime = []
     ctx = repo[node]
     for fn in files:
         wfn = util.pconvert(fn)
-        if not wfn in ctx:
+        if wfn not in ctx:
             # File doesn't exist; could be a bogus modify
             continue
         ui.note('  %s\n' % wfn)
         dest = os.path.join(base, wfn)
         fctx = ctx[wfn]
         data = repo.wwritedata(wfn, fctx.data())
         if 'l' in fctx.flags():
             wopener.symlink(data, wfn)
         else:
             wopener.write(wfn, data)
             if 'x' in fctx.flags():
                 util.setflags(dest, False, True)
         if node is None:
             fns_and_mtime.append((dest, repo.wjoin(fn),
                                   os.lstat(dest).st_mtime))
     return dirname, fns_and_mtime
 
 def dodiff(ui, repo, diffcmd, diffopts, pats, opts):
     '''Do the actuall diff:
 
     - copy to a temp structure if diffing 2 internal revisions
     - copy to a temp structure if diffing working revision with
       another one and more than 1 file is changed
     - just invoke the diff for a single file in the working dir
     '''
 
     revs = opts.get('rev')
     change = opts.get('change')
     args = ' '.join(diffopts)
     do3way = '$parent2' in args
 
     if revs and change:
         msg = _('cannot specify --rev and --change at the same time')
         raise util.Abort(msg)
     elif change:
         node2 = scmutil.revsingle(repo, change, None).node()
         node1a, node1b = repo.changelog.parents(node2)
     else:
         node1a, node2 = scmutil.revpair(repo, revs)
         if not revs:
             node1b = repo.dirstate.p2()
         else:
             node1b = nullid
 
     # Disable 3-way merge if there is only one parent
     if do3way:
         if node1b == nullid:
             do3way = False
 
     matcher = scmutil.match(repo[node2], pats, opts)
     mod_a, add_a, rem_a = map(set, repo.status(node1a, node2, matcher)[:3])
     if do3way:
         mod_b, add_b, rem_b = map(set, repo.status(node1b, node2, matcher)[:3])
     else:
         mod_b, add_b, rem_b = set(), set(), set()
     modadd = mod_a | add_a | mod_b | add_b
     common = modadd | rem_a | rem_b
     if not common:
         return 0
 
     tmproot = tempfile.mkdtemp(prefix='extdiff.')
     try:
         # Always make a copy of node1a (and node1b, if applicable)
         dir1a_files = mod_a | rem_a | ((mod_b | add_b) - add_a)
         dir1a = snapshot(ui, repo, dir1a_files, node1a, tmproot)[0]
         rev1a = '@%d' % repo[node1a].rev()
         if do3way:
             dir1b_files = mod_b | rem_b | ((mod_a | add_a) - add_b)
             dir1b = snapshot(ui, repo, dir1b_files, node1b, tmproot)[0]
             rev1b = '@%d' % repo[node1b].rev()
         else:
             dir1b = None
             rev1b = ''
 
         fns_and_mtime = []
 
         # If node2 in not the wc or there is >1 change, copy it
         dir2root = ''
         rev2 = ''
         if node2:
             dir2 = snapshot(ui, repo, modadd, node2, tmproot)[0]
             rev2 = '@%d' % repo[node2].rev()
         elif len(common) > 1:
             #we only actually need to get the files to copy back to
             #the working dir in this case (because the other cases
             #are: diffing 2 revisions or single file -- in which case
             #the file is already directly passed to the diff tool).
             dir2, fns_and_mtime = snapshot(ui, repo, modadd, None, tmproot)
         else:
             # This lets the diff tool open the changed file directly
             dir2 = ''
             dir2root = repo.root
 
         label1a = rev1a
         label1b = rev1b
         label2 = rev2
 
         # If only one change, diff the files instead of the directories
         # Handle bogus modifies correctly by checking if the files exist
         if len(common) == 1:
             common_file = util.localpath(common.pop())
             dir1a = os.path.join(tmproot, dir1a, common_file)
             label1a = common_file + rev1a
             if not os.path.isfile(dir1a):
                 dir1a = os.devnull
             if do3way:
                 dir1b = os.path.join(tmproot, dir1b, common_file)
                 label1b = common_file + rev1b
                 if not os.path.isfile(dir1b):
                     dir1b = os.devnull
             dir2 = os.path.join(dir2root, dir2, common_file)
             label2 = common_file + rev2
 
         # Function to quote file/dir names in the argument string.
         # When not operating in 3-way mode, an empty string is
         # returned for parent2
         replace = dict(parent=dir1a, parent1=dir1a, parent2=dir1b,
                        plabel1=label1a, plabel2=label1b,
                        clabel=label2, child=dir2,
                        root=repo.root)
         def quote(match):
             key = match.group()[1:]
             if not do3way and key == 'parent2':
                 return ''
             return util.shellquote(replace[key])
 
         # Match parent2 first, so 'parent1?' will match both parent1 and parent
         regex = '\$(parent2|parent1?|child|plabel1|plabel2|clabel|root)'
         if not do3way and not re.search(regex, args):
             args += ' $parent1 $child'
         args = re.sub(regex, quote, args)
         cmdline = util.shellquote(diffcmd) + ' ' + args
 
         ui.debug('running %r in %s\n' % (cmdline, tmproot))
         util.system(cmdline, cwd=tmproot, out=ui.fout)
 
         for copy_fn, working_fn, mtime in fns_and_mtime:
             if os.lstat(copy_fn).st_mtime != mtime:
                 ui.debug('file changed while diffing. '
                          'Overwriting: %s (src: %s)\n' % (working_fn, copy_fn))
                 util.copyfile(copy_fn, working_fn)
 
         return 1
     finally:
         ui.note(_('cleaning up temp directory\n'))
         shutil.rmtree(tmproot)
 
 def extdiff(ui, repo, *pats, **opts):
     '''use external program to diff repository (or selected files)
 
     Show differences between revisions for the specified files, using
     an external program. The default program used is diff, with
     default options "-Npru".
 
     To select a different program, use the -p/--program option. The
     program will be passed the names of two directories to compare. To
     pass additional options to the program, use -o/--option. These
     will be passed before the names of the directories to compare.
 
     When two revision arguments are given, then changes are shown
     between those revisions. If only one revision is specified then
     that revision is compared to the working directory, and, when no
     revisions are specified, the working directory files are compared
     to its parent.'''
     program = opts.get('program')
     option = opts.get('option')
     if not program:
         program = 'diff'
         option = option or ['-Npru']
     return dodiff(ui, repo, program, option, pats, opts)
 
 cmdtable = {
     "extdiff":
     (extdiff,
      [('p', 'program', '',
        _('comparison program to run'), _('CMD')),
       ('o', 'option', [],
        _('pass option to comparison program'), _('OPT')),
       ('r', 'rev', [],
        _('revision'), _('REV')),
       ('c', 'change', '',
        _('change made by revision'), _('REV')),
      ] + commands.walkopts,
      _('hg extdiff [OPT]... [FILE]...')),
     }
 
 def uisetup(ui):
     for cmd, path in ui.configitems('extdiff'):
         if cmd.startswith('cmd.'):
             cmd = cmd[4:]
             if not path:
                 path = cmd
             diffopts = ui.config('extdiff', 'opts.' + cmd, '')
             diffopts = diffopts and [diffopts] or []
         elif cmd.startswith('opts.'):
             continue
         else:
             # command = path opts
             if path:
                 diffopts = shlex.split(path)
                 path = diffopts.pop(0)
             else:
                 path, diffopts = cmd, []
         # look for diff arguments in [diff-tools] then [merge-tools]
         if diffopts == []:
             args = ui.config('diff-tools', cmd+'.diffargs') or \
                    ui.config('merge-tools', cmd+'.diffargs')
             if args:
                 diffopts = shlex.split(args)
         def save(cmd, path, diffopts):
             '''use closure to save diff command to use'''
             def mydiff(ui, repo, *pats, **opts):
                 return dodiff(ui, repo, path, diffopts + opts['option'],
                               pats, opts)
             doc = _('''\
 use %(path)s to diff repository (or selected files)
 
     Show differences between revisions for the specified files, using
     the %(path)s program.
 
     When two revision arguments are given, then changes are shown
     between those revisions. If only one revision is specified then
     that revision is compared to the working directory, and, when no
     revisions are specified, the working directory files are compared
     to its parent.\
 ''') % dict(path=util.uirepr(path))
 
             # We must translate the docstring right away since it is
             # used as a format string. The string will unfortunately
             # be translated again in commands.helpcmd and this will
             # fail when the docstring contains non-ASCII characters.
             # Decoding the string to a Unicode string here (using the
             # right encoding) prevents that.
             mydiff.__doc__ = doc.decode(encoding.encoding)
             return mydiff
         cmdtable[cmd] = (save(cmd, path, diffopts),
                          cmdtable['extdiff'][1][1:],
                          _('hg %s [OPTION]... [FILE]...') % cmd)

hgext/keyword.py

@@ -1,702 +1,702 b''
 # keyword.py - $Keyword$ expansion for Mercurial
 #
 # Copyright 2007-2010 Christian Ebert <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 #
 # $Id$
 #
 # Keyword expansion hack against the grain of a DSCM
 #
 # There are many good reasons why this is not needed in a distributed
 # SCM, still it may be useful in very small projects based on single
 # files (like LaTeX packages), that are mostly addressed to an
 # audience not running a version control system.
 #
 # For in-depth discussion refer to
 # <http://mercurial.selenic.com/wiki/KeywordPlan>.
 #
 # Keyword expansion is based on Mercurial's changeset template mappings.
 #
 # Binary files are not touched.
 #
 # Files to act upon/ignore are specified in the [keyword] section.
 # Customized keyword template mappings in the [keywordmaps] section.
 #
 # Run "hg help keyword" and "hg kwdemo" to get info on configuration.
 
 '''expand keywords in tracked files
 
 This extension expands RCS/CVS-like or self-customized $Keywords$ in
 tracked text files selected by your configuration.
 
 Keywords are only expanded in local repositories and not stored in the
 change history. The mechanism can be regarded as a convenience for the
 current user or for archive distribution.
 
 Keywords expand to the changeset data pertaining to the latest change
 relative to the working directory parent of each file.
 
 Configuration is done in the [keyword], [keywordset] and [keywordmaps]
 sections of hgrc files.
 
 Example::
 
     [keyword]
     # expand keywords in every python file except those matching "x*"
     **.py =
     x*    = ignore
 
     [keywordset]
     # prefer svn- over cvs-like default keywordmaps
     svn = True
 
 .. note::
    The more specific you are in your filename patterns the less you
    lose speed in huge repositories.
 
 For [keywordmaps] template mapping and expansion demonstration and
 control run :hg:`kwdemo`. See :hg:`help templates` for a list of
 available templates and filters.
 
 Three additional date template filters are provided:
 
 :``utcdate``:    "2006/09/18 15:13:13"
 :``svnutcdate``: "2006-09-18 15:13:13Z"
 :``svnisodate``: "2006-09-18 08:13:13 -700 (Mon, 18 Sep 2006)"
 
 The default template mappings (view with :hg:`kwdemo -d`) can be
 replaced with customized keywords and templates. Again, run
 :hg:`kwdemo` to control the results of your configuration changes.
 
 Before changing/disabling active keywords, you must run :hg:`kwshrink`
 to avoid storing expanded keywords in the change history.
 
 To force expansion after enabling it, or a configuration change, run
 :hg:`kwexpand`.
 
 Expansions spanning more than one line and incremental expansions,
 like CVS' $Log$, are not supported. A keyword template map "Log =
 {desc}" expands to the first line of the changeset description.
 '''
 
 from mercurial import commands, context, cmdutil, dispatch, filelog, extensions
 from mercurial import localrepo, match, patch, templatefilters, templater, util
 from mercurial import scmutil
 from mercurial.hgweb import webcommands
 from mercurial.i18n import _
 import os, re, shutil, tempfile
 
 commands.optionalrepo += ' kwdemo'
 
 cmdtable = {}
 command = cmdutil.command(cmdtable)
 
 # hg commands that do not act on keywords
 nokwcommands = ('add addremove annotate bundle export grep incoming init log'
                 ' outgoing push tip verify convert email glog')
 
 # hg commands that trigger expansion only when writing to working dir,
 # not when reading filelog, and unexpand when reading from working dir
 restricted = 'merge kwexpand kwshrink record qrecord resolve transplant'
 
 # names of extensions using dorecord
 recordextensions = 'record'
 
 colortable = {
     'kwfiles.enabled': 'green bold',
     'kwfiles.deleted': 'cyan bold underline',
     'kwfiles.enabledunknown': 'green',
     'kwfiles.ignored': 'bold',
     'kwfiles.ignoredunknown': 'none'
 }
 
 # date like in cvs' $Date
 def utcdate(text):
     ''':utcdate: Date. Returns a UTC-date in this format: "2009/08/18 11:00:13".
     '''
     return util.datestr((text[0], 0), '%Y/%m/%d %H:%M:%S')
 # date like in svn's $Date
 def svnisodate(text):
     ''':svnisodate: Date. Returns a date in this format: "2009-08-18 13:00:13
     +0200 (Tue, 18 Aug 2009)".
     '''
     return util.datestr(text, '%Y-%m-%d %H:%M:%S %1%2 (%a, %d %b %Y)')
 # date like in svn's $Id
 def svnutcdate(text):
     ''':svnutcdate: Date. Returns a UTC-date in this format: "2009-08-18
     11:00:13Z".
     '''
     return util.datestr((text[0], 0), '%Y-%m-%d %H:%M:%SZ')
 
 templatefilters.filters.update({'utcdate': utcdate,
                                 'svnisodate': svnisodate,
                                 'svnutcdate': svnutcdate})
 
 # make keyword tools accessible
 kwtools = {'templater': None, 'hgcmd': ''}
 
 def _defaultkwmaps(ui):
     '''Returns default keywordmaps according to keywordset configuration.'''
     templates = {
         'Revision': '{node|short}',
         'Author': '{author|user}',
     }
     kwsets = ({
         'Date': '{date|utcdate}',
         'RCSfile': '{file|basename},v',
         'RCSFile': '{file|basename},v', # kept for backwards compatibility
                                         # with hg-keyword
         'Source': '{root}/{file},v',
         'Id': '{file|basename},v {node|short} {date|utcdate} {author|user}',
         'Header': '{root}/{file},v {node|short} {date|utcdate} {author|user}',
     }, {
         'Date': '{date|svnisodate}',
         'Id': '{file|basename},v {node|short} {date|svnutcdate} {author|user}',
         'LastChangedRevision': '{node|short}',
         'LastChangedBy': '{author|user}',
         'LastChangedDate': '{date|svnisodate}',
     })
     templates.update(kwsets[ui.configbool('keywordset', 'svn')])
     return templates
 
 def _shrinktext(text, subfunc):
     '''Helper for keyword expansion removal in text.
     Depending on subfunc also returns number of substitutions.'''
     return subfunc(r'$\1$', text)
 
 def _preselect(wstatus, changed):
     '''Retrieves modfied and added files from a working directory state
     and returns the subset of each contained in given changed files
     retrieved from a change context.'''
     modified, added = wstatus[:2]
     modified = [f for f in modified if f in changed]
     added = [f for f in added if f in changed]
     return modified, added
 
 
 class kwtemplater(object):
     '''
     Sets up keyword templates, corresponding keyword regex, and
     provides keyword substitution functions.
     '''
 
     def __init__(self, ui, repo, inc, exc):
         self.ui = ui
         self.repo = repo
         self.match = match.match(repo.root, '', [], inc, exc)
         self.restrict = kwtools['hgcmd'] in restricted.split()
         self.record = False
 
         kwmaps = self.ui.configitems('keywordmaps')
         if kwmaps: # override default templates
             self.templates = dict((k, templater.parsestring(v, False))
                                   for k, v in kwmaps)
         else:
             self.templates = _defaultkwmaps(self.ui)
 
     @util.propertycache
     def escape(self):
         '''Returns bar-separated and escaped keywords.'''
         return '|'.join(map(re.escape, self.templates.keys()))
 
     @util.propertycache
     def rekw(self):
         '''Returns regex for unexpanded keywords.'''
         return re.compile(r'\$(%s)\$' % self.escape)
 
     @util.propertycache
     def rekwexp(self):
         '''Returns regex for expanded keywords.'''
         return re.compile(r'\$(%s): [^$\n\r]*? \$' % self.escape)
 
     def substitute(self, data, path, ctx, subfunc):
         '''Replaces keywords in data with expanded template.'''
         def kwsub(mobj):
             kw = mobj.group(1)
             ct = cmdutil.changeset_templater(self.ui, self.repo,
                                              False, None, '', False)
             ct.use_template(self.templates[kw])
             self.ui.pushbuffer()
             ct.show(ctx, root=self.repo.root, file=path)
             ekw = templatefilters.firstline(self.ui.popbuffer())
             return '$%s: %s $' % (kw, ekw)
         return subfunc(kwsub, data)
 
     def linkctx(self, path, fileid):
         '''Similar to filelog.linkrev, but returns a changectx.'''
         return self.repo.filectx(path, fileid=fileid).changectx()
 
     def expand(self, path, node, data):
         '''Returns data with keywords expanded.'''
         if not self.restrict and self.match(path) and not util.binary(data):
             ctx = self.linkctx(path, node)
             return self.substitute(data, path, ctx, self.rekw.sub)
         return data
 
     def iskwfile(self, cand, ctx):
         '''Returns subset of candidates which are configured for keyword
         expansion but are not symbolic links.'''
-        return [f for f in cand if self.match(f) and not 'l' in ctx.flags(f)]
+        return [f for f in cand if self.match(f) and 'l' not in ctx.flags(f)]
 
     def overwrite(self, ctx, candidates, lookup, expand, rekw=False):
         '''Overwrites selected files expanding/shrinking keywords.'''
         if self.restrict or lookup or self.record: # exclude kw_copy
             candidates = self.iskwfile(candidates, ctx)
         if not candidates:
             return
         kwcmd = self.restrict and lookup # kwexpand/kwshrink
         if self.restrict or expand and lookup:
             mf = ctx.manifest()
         if self.restrict or rekw:
             re_kw = self.rekw
         else:
             re_kw = self.rekwexp
         if expand:
             msg = _('overwriting %s expanding keywords\n')
         else:
             msg = _('overwriting %s shrinking keywords\n')
         for f in candidates:
             if self.restrict:
                 data = self.repo.file(f).read(mf[f])
             else:
                 data = self.repo.wread(f)
             if util.binary(data):
                 continue
             if expand:
                 if lookup:
                     ctx = self.linkctx(f, mf[f])
                 data, found = self.substitute(data, f, ctx, re_kw.subn)
             elif self.restrict:
                 found = re_kw.search(data)
             else:
                 data, found = _shrinktext(data, re_kw.subn)
             if found:
                 self.ui.note(msg % f)
                 fp = self.repo.wopener(f, "wb", atomictemp=True)
                 fp.write(data)
                 fp.close()
                 if kwcmd:
                     self.repo.dirstate.normal(f)
                 elif self.record:
                     self.repo.dirstate.normallookup(f)
 
     def shrink(self, fname, text):
         '''Returns text with all keyword substitutions removed.'''
         if self.match(fname) and not util.binary(text):
             return _shrinktext(text, self.rekwexp.sub)
         return text
 
     def shrinklines(self, fname, lines):
         '''Returns lines with keyword substitutions removed.'''
         if self.match(fname):
             text = ''.join(lines)
             if not util.binary(text):
                 return _shrinktext(text, self.rekwexp.sub).splitlines(True)
         return lines
 
     def wread(self, fname, data):
         '''If in restricted mode returns data read from wdir with
         keyword substitutions removed.'''
         if self.restrict:
             return self.shrink(fname, data)
         return data
 
 class kwfilelog(filelog.filelog):
     '''
     Subclass of filelog to hook into its read, add, cmp methods.
     Keywords are "stored" unexpanded, and processed on reading.
     '''
     def __init__(self, opener, kwt, path):
         super(kwfilelog, self).__init__(opener, path)
         self.kwt = kwt
         self.path = path
 
     def read(self, node):
         '''Expands keywords when reading filelog.'''
         data = super(kwfilelog, self).read(node)
         if self.renamed(node):
             return data
         return self.kwt.expand(self.path, node, data)
 
     def add(self, text, meta, tr, link, p1=None, p2=None):
         '''Removes keyword substitutions when adding to filelog.'''
         text = self.kwt.shrink(self.path, text)
         return super(kwfilelog, self).add(text, meta, tr, link, p1, p2)
 
     def cmp(self, node, text):
         '''Removes keyword substitutions for comparison.'''
         text = self.kwt.shrink(self.path, text)
         return super(kwfilelog, self).cmp(node, text)
 
 def _status(ui, repo, wctx, kwt, *pats, **opts):
     '''Bails out if [keyword] configuration is not active.
     Returns status of working directory.'''
     if kwt:
         return repo.status(match=scmutil.match(wctx, pats, opts), clean=True,
                            unknown=opts.get('unknown') or opts.get('all'))
     if ui.configitems('keyword'):
         raise util.Abort(_('[keyword] patterns cannot match'))
     raise util.Abort(_('no [keyword] patterns configured'))
 
 def _kwfwrite(ui, repo, expand, *pats, **opts):
     '''Selects files and passes them to kwtemplater.overwrite.'''
     wctx = repo[None]
     if len(wctx.parents()) > 1:
         raise util.Abort(_('outstanding uncommitted merge'))
     kwt = kwtools['templater']
     wlock = repo.wlock()
     try:
         status = _status(ui, repo, wctx, kwt, *pats, **opts)
         modified, added, removed, deleted, unknown, ignored, clean = status
         if modified or added or removed or deleted:
             raise util.Abort(_('outstanding uncommitted changes'))
         kwt.overwrite(wctx, clean, True, expand)
     finally:
         wlock.release()
 
 @command('kwdemo',
          [('d', 'default', None, _('show default keyword template maps')),
           ('f', 'rcfile', '',
            _('read maps from rcfile'), _('FILE'))],
          _('hg kwdemo [-d] [-f RCFILE] [TEMPLATEMAP]...'))
 def demo(ui, repo, *args, **opts):
     '''print [keywordmaps] configuration and an expansion example
 
     Show current, custom, or default keyword template maps and their
     expansions.
 
     Extend the current configuration by specifying maps as arguments
     and using -f/--rcfile to source an external hgrc file.
 
     Use -d/--default to disable current configuration.
 
     See :hg:`help templates` for information on templates and filters.
     '''
     def demoitems(section, items):
         ui.write('[%s]\n' % section)
         for k, v in sorted(items):
             ui.write('%s = %s\n' % (k, v))
 
     fn = 'demo.txt'
     tmpdir = tempfile.mkdtemp('', 'kwdemo.')
     ui.note(_('creating temporary repository at %s\n') % tmpdir)
     repo = localrepo.localrepository(ui, tmpdir, True)
     ui.setconfig('keyword', fn, '')
     svn = ui.configbool('keywordset', 'svn')
     # explicitly set keywordset for demo output
     ui.setconfig('keywordset', 'svn', svn)
 
     uikwmaps = ui.configitems('keywordmaps')
     if args or opts.get('rcfile'):
         ui.status(_('\n\tconfiguration using custom keyword template maps\n'))
         if uikwmaps:
             ui.status(_('\textending current template maps\n'))
         if opts.get('default') or not uikwmaps:
             if svn:
                 ui.status(_('\toverriding default svn keywordset\n'))
             else:
                 ui.status(_('\toverriding default cvs keywordset\n'))
         if opts.get('rcfile'):
             ui.readconfig(opts.get('rcfile'))
         if args:
             # simulate hgrc parsing
             rcmaps = ['[keywordmaps]\n'] + [a + '\n' for a in args]
             fp = repo.opener('hgrc', 'w')
             fp.writelines(rcmaps)
             fp.close()
             ui.readconfig(repo.join('hgrc'))
         kwmaps = dict(ui.configitems('keywordmaps'))
     elif opts.get('default'):
         if svn:
             ui.status(_('\n\tconfiguration using default svn keywordset\n'))
         else:
             ui.status(_('\n\tconfiguration using default cvs keywordset\n'))
         kwmaps = _defaultkwmaps(ui)
         if uikwmaps:
             ui.status(_('\tdisabling current template maps\n'))
             for k, v in kwmaps.iteritems():
                 ui.setconfig('keywordmaps', k, v)
     else:
         ui.status(_('\n\tconfiguration using current keyword template maps\n'))
         if uikwmaps:
             kwmaps = dict(uikwmaps)
         else:
             kwmaps = _defaultkwmaps(ui)
 
     uisetup(ui)
     reposetup(ui, repo)
     ui.write('[extensions]\nkeyword =\n')
     demoitems('keyword', ui.configitems('keyword'))
     demoitems('keywordset', ui.configitems('keywordset'))
     demoitems('keywordmaps', kwmaps.iteritems())
     keywords = '$' + '$\n$'.join(sorted(kwmaps.keys())) + '$\n'
     repo.wopener.write(fn, keywords)
     repo[None].add([fn])
     ui.note(_('\nkeywords written to %s:\n') % fn)
     ui.note(keywords)
     repo.dirstate.setbranch('demobranch')
     for name, cmd in ui.configitems('hooks'):
         if name.split('.', 1)[0].find('commit') > -1:
             repo.ui.setconfig('hooks', name, '')
     msg = _('hg keyword configuration and expansion example')
     ui.note("hg ci -m '%s'\n" % msg)
     repo.commit(text=msg)
     ui.status(_('\n\tkeywords expanded\n'))
     ui.write(repo.wread(fn))
     shutil.rmtree(tmpdir, ignore_errors=True)
 
 @command('kwexpand', commands.walkopts, _('hg kwexpand [OPTION]... [FILE]...'))
 def expand(ui, repo, *pats, **opts):
     '''expand keywords in the working directory
 
     Run after (re)enabling keyword expansion.
 
     kwexpand refuses to run if given files contain local changes.
     '''
     # 3rd argument sets expansion to True
     _kwfwrite(ui, repo, True, *pats, **opts)
 
 @command('kwfiles',
          [('A', 'all', None, _('show keyword status flags of all files')),
           ('i', 'ignore', None, _('show files excluded from expansion')),
           ('u', 'unknown', None, _('only show unknown (not tracked) files')),
          ] + commands.walkopts,
          _('hg kwfiles [OPTION]... [FILE]...'))
 def files(ui, repo, *pats, **opts):
     '''show files configured for keyword expansion
 
     List which files in the working directory are matched by the
     [keyword] configuration patterns.
 
     Useful to prevent inadvertent keyword expansion and to speed up
     execution by including only files that are actual candidates for
     expansion.
 
     See :hg:`help keyword` on how to construct patterns both for
     inclusion and exclusion of files.
 
     With -A/--all and -v/--verbose the codes used to show the status
     of files are::
 
       K = keyword expansion candidate
       k = keyword expansion candidate (not tracked)
       I = ignored
       i = ignored (not tracked)
     '''
     kwt = kwtools['templater']
     wctx = repo[None]
     status = _status(ui, repo, wctx, kwt, *pats, **opts)
     cwd = pats and repo.getcwd() or ''
     modified, added, removed, deleted, unknown, ignored, clean = status
     files = []
     if not opts.get('unknown') or opts.get('all'):
         files = sorted(modified + added + clean)
     kwfiles = kwt.iskwfile(files, wctx)
     kwdeleted = kwt.iskwfile(deleted, wctx)
     kwunknown = kwt.iskwfile(unknown, wctx)
     if not opts.get('ignore') or opts.get('all'):
         showfiles = kwfiles, kwdeleted, kwunknown
     else:
         showfiles = [], [], []
     if opts.get('all') or opts.get('ignore'):
         showfiles += ([f for f in files if f not in kwfiles],
                       [f for f in unknown if f not in kwunknown])
     kwlabels = 'enabled deleted enabledunknown ignored ignoredunknown'.split()
     kwstates = zip('K!kIi', showfiles, kwlabels)
     for char, filenames, kwstate in kwstates:
         fmt = (opts.get('all') or ui.verbose) and '%s %%s\n' % char or '%s\n'
         for f in filenames:
             ui.write(fmt % repo.pathto(f, cwd), label='kwfiles.' + kwstate)
 
 @command('kwshrink', commands.walkopts, _('hg kwshrink [OPTION]... [FILE]...'))
 def shrink(ui, repo, *pats, **opts):
     '''revert expanded keywords in the working directory
 
     Must be run before changing/disabling active keywords.
 
     kwshrink refuses to run if given files contain local changes.
     '''
     # 3rd argument sets expansion to False
     _kwfwrite(ui, repo, False, *pats, **opts)
 
 
 def uisetup(ui):
     ''' Monkeypatches dispatch._parse to retrieve user command.'''
 
     def kwdispatch_parse(orig, ui, args):
         '''Monkeypatch dispatch._parse to obtain running hg command.'''
         cmd, func, args, options, cmdoptions = orig(ui, args)
         kwtools['hgcmd'] = cmd
         return cmd, func, args, options, cmdoptions
 
     extensions.wrapfunction(dispatch, '_parse', kwdispatch_parse)
 
 def reposetup(ui, repo):
     '''Sets up repo as kwrepo for keyword substitution.
     Overrides file method to return kwfilelog instead of filelog
     if file matches user configuration.
     Wraps commit to overwrite configured files with updated
     keyword substitutions.
     Monkeypatches patch and webcommands.'''
 
     try:
         if (not repo.local() or kwtools['hgcmd'] in nokwcommands.split()
             or '.hg' in util.splitpath(repo.root)
             or repo._url.startswith('bundle:')):
             return
     except AttributeError:
         pass
 
     inc, exc = [], ['.hg*']
     for pat, opt in ui.configitems('keyword'):
         if opt != 'ignore':
             inc.append(pat)
         else:
             exc.append(pat)
     if not inc:
         return
 
     kwtools['templater'] = kwt = kwtemplater(ui, repo, inc, exc)
 
     class kwrepo(repo.__class__):
         def file(self, f):
             if f[0] == '/':
                 f = f[1:]
             return kwfilelog(self.sopener, kwt, f)
 
         def wread(self, filename):
             data = super(kwrepo, self).wread(filename)
             return kwt.wread(filename, data)
 
         def commit(self, *args, **opts):
             # use custom commitctx for user commands
             # other extensions can still wrap repo.commitctx directly
             self.commitctx = self.kwcommitctx
             try:
                 return super(kwrepo, self).commit(*args, **opts)
             finally:
                 del self.commitctx
 
         def kwcommitctx(self, ctx, error=False):
             n = super(kwrepo, self).commitctx(ctx, error)
             # no lock needed, only called from repo.commit() which already locks
             if not kwt.record:
                 restrict = kwt.restrict
                 kwt.restrict = True
                 kwt.overwrite(self[n], sorted(ctx.added() + ctx.modified()),
                               False, True)
                 kwt.restrict = restrict
             return n
 
         def rollback(self, dryrun=False, force=False):
             wlock = self.wlock()
             try:
                 if not dryrun:
                     changed = self['.'].files()
                 ret = super(kwrepo, self).rollback(dryrun, force)
                 if not dryrun:
                     ctx = self['.']
                     modified, added = _preselect(self[None].status(), changed)
                     kwt.overwrite(ctx, modified, True, True)
                     kwt.overwrite(ctx, added, True, False)
                 return ret
             finally:
                 wlock.release()
 
     # monkeypatches
     def kwpatchfile_init(orig, self, ui, gp, backend, store, eolmode=None):
         '''Monkeypatch/wrap patch.patchfile.__init__ to avoid
         rejects or conflicts due to expanded keywords in working dir.'''
         orig(self, ui, gp, backend, store, eolmode)
         # shrink keywords read from working dir
         self.lines = kwt.shrinklines(self.fname, self.lines)
 
     def kw_diff(orig, repo, node1=None, node2=None, match=None, changes=None,
                 opts=None, prefix=''):
         '''Monkeypatch patch.diff to avoid expansion.'''
         kwt.restrict = True
         return orig(repo, node1, node2, match, changes, opts, prefix)
 
     def kwweb_skip(orig, web, req, tmpl):
         '''Wraps webcommands.x turning off keyword expansion.'''
         kwt.match = util.never
         return orig(web, req, tmpl)
 
     def kw_copy(orig, ui, repo, pats, opts, rename=False):
         '''Wraps cmdutil.copy so that copy/rename destinations do not
         contain expanded keywords.
         Note that the source of a regular file destination may also be a
         symlink:
         hg cp sym x                -> x is symlink
         cp sym x; hg cp -A sym x   -> x is file (maybe expanded keywords)
         For the latter we have to follow the symlink to find out whether its
         target is configured for expansion and we therefore must unexpand the
         keywords in the destination.'''
         orig(ui, repo, pats, opts, rename)
         if opts.get('dry_run'):
             return
         wctx = repo[None]
         cwd = repo.getcwd()
 
         def haskwsource(dest):
             '''Returns true if dest is a regular file and configured for
             expansion or a symlink which points to a file configured for
             expansion. '''
             source = repo.dirstate.copied(dest)
             if 'l' in wctx.flags(source):
                 source = scmutil.canonpath(repo.root, cwd,
                                            os.path.realpath(source))
             return kwt.match(source)
 
         candidates = [f for f in repo.dirstate.copies() if
-                      not 'l' in wctx.flags(f) and haskwsource(f)]
+                      'l' not in wctx.flags(f) and haskwsource(f)]
         kwt.overwrite(wctx, candidates, False, False)
 
     def kw_dorecord(orig, ui, repo, commitfunc, *pats, **opts):
         '''Wraps record.dorecord expanding keywords after recording.'''
         wlock = repo.wlock()
         try:
             # record returns 0 even when nothing has changed
             # therefore compare nodes before and after
             kwt.record = True
             ctx = repo['.']
             wstatus = repo[None].status()
             ret = orig(ui, repo, commitfunc, *pats, **opts)
             recctx = repo['.']
             if ctx != recctx:
                 modified, added = _preselect(wstatus, recctx.files())
                 kwt.restrict = False
                 kwt.overwrite(recctx, modified, False, True)
                 kwt.overwrite(recctx, added, False, True, True)
                 kwt.restrict = True
             return ret
         finally:
             wlock.release()
 
     def kwfilectx_cmp(orig, self, fctx):
         # keyword affects data size, comparing wdir and filelog size does
         # not make sense
         if (fctx._filerev is None and
             (self._repo._encodefilterpats or
-             kwt.match(fctx.path()) and not 'l' in fctx.flags() or
+             kwt.match(fctx.path()) and 'l' not in fctx.flags() or
              self.size() - 4 == fctx.size()) or
             self.size() == fctx.size()):
             return self._filelog.cmp(self._filenode, fctx.data())
         return True
 
     extensions.wrapfunction(context.filectx, 'cmp', kwfilectx_cmp)
     extensions.wrapfunction(patch.patchfile, '__init__', kwpatchfile_init)
     extensions.wrapfunction(patch, 'diff', kw_diff)
     extensions.wrapfunction(cmdutil, 'copy', kw_copy)
     for c in 'annotate changeset rev filediff diff'.split():
         extensions.wrapfunction(webcommands, c, kwweb_skip)
     for name in recordextensions.split():
         try:
             record = extensions.find(name)
             extensions.wrapfunction(record, 'dorecord', kw_dorecord)
         except KeyError:
             pass
 
     repo.__class__ = kwrepo

hgext/largefiles/wirestore.py

@@ -1,29 +1,29 b''
 # Copyright 2010-2011 Fog Creek Software
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 '''largefile store working over Mercurial's wire protocol'''
 
 import lfutil
 import remotestore
 
 class wirestore(remotestore.remotestore):
     def __init__(self, ui, repo, remote):
         cap = remote.capable('largefiles')
         if not cap:
             raise lfutil.storeprotonotcapable([])
         storetypes = cap.split(',')
-        if not 'serve' in storetypes:
+        if 'serve' not in storetypes:
             raise lfutil.storeprotonotcapable(storetypes)
         self.remote = remote
         super(wirestore, self).__init__(ui, repo, remote.url())
 
     def _put(self, hash, fd):
         return self.remote.putlfile(hash, fd)
 
     def _get(self, hash):
         return self.remote.getlfile(hash)
 
     def _stat(self, hash):
         return self.remote.statlfile(hash)

hgext/relink.py

@@ -1,184 +1,184 b''
 # Mercurial extension to provide 'hg relink' command
 #
 # Copyright (C) 2007 Brendan Cully <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 """recreates hardlinks between repository clones"""
 
 from mercurial import hg, util
 from mercurial.i18n import _
 import os, stat
 
 def relink(ui, repo, origin=None, **opts):
     """recreate hardlinks between two repositories
 
     When repositories are cloned locally, their data files will be
     hardlinked so that they only use the space of a single repository.
 
     Unfortunately, subsequent pulls into either repository will break
     hardlinks for any files touched by the new changesets, even if
     both repositories end up pulling the same changes.
 
     Similarly, passing --rev to "hg clone" will fail to use any
     hardlinks, falling back to a complete copy of the source
     repository.
 
     This command lets you recreate those hardlinks and reclaim that
     wasted space.
 
     This repository will be relinked to share space with ORIGIN, which
     must be on the same local disk. If ORIGIN is omitted, looks for
     "default-relink", then "default", in [paths].
 
     Do not attempt any read operations on this repository while the
     command is running. (Both repositories will be locked against
     writes.)
     """
     if (not util.safehasattr(util, 'samefile') or
         not util.safehasattr(util, 'samedevice')):
         raise util.Abort(_('hardlinks are not supported on this system'))
     src = hg.repository(ui, ui.expandpath(origin or 'default-relink',
                                           origin or 'default'))
     if not src.local():
         raise util.Abort(_('must specify local origin repository'))
     ui.status(_('relinking %s to %s\n') % (src.store.path, repo.store.path))
     if repo.root == src.root:
         ui.status(_('there is nothing to relink\n'))
         return
 
     locallock = repo.lock()
     try:
         remotelock = src.lock()
         try:
             candidates = sorted(collect(src, ui))
             targets = prune(candidates, src.store.path, repo.store.path, ui)
             do_relink(src.store.path, repo.store.path, targets, ui)
         finally:
             remotelock.release()
     finally:
         locallock.release()
 
 def collect(src, ui):
     seplen = len(os.path.sep)
     candidates = []
     live = len(src['tip'].manifest())
     # Your average repository has some files which were deleted before
     # the tip revision. We account for that by assuming that there are
     # 3 tracked files for every 2 live files as of the tip version of
     # the repository.
     #
     # mozilla-central as of 2010-06-10 had a ratio of just over 7:5.
     total = live * 3 // 2
     src = src.store.path
     pos = 0
     ui.status(_("tip has %d files, estimated total number of files: %s\n")
               % (live, total))
     for dirpath, dirnames, filenames in os.walk(src):
         dirnames.sort()
         relpath = dirpath[len(src) + seplen:]
         for filename in sorted(filenames):
-            if not filename[-2:] in ('.d', '.i'):
+            if filename[-2:] not in ('.d', '.i'):
                 continue
             st = os.stat(os.path.join(dirpath, filename))
             if not stat.S_ISREG(st.st_mode):
                 continue
             pos += 1
             candidates.append((os.path.join(relpath, filename), st))
             ui.progress(_('collecting'), pos, filename, _('files'), total)
 
     ui.progress(_('collecting'), None)
     ui.status(_('collected %d candidate storage files\n') % len(candidates))
     return candidates
 
 def prune(candidates, src, dst, ui):
     def linkfilter(src, dst, st):
         try:
             ts = os.stat(dst)
         except OSError:
             # Destination doesn't have this file?
             return False
         if util.samefile(src, dst):
             return False
         if not util.samedevice(src, dst):
             # No point in continuing
             raise util.Abort(
                 _('source and destination are on different devices'))
         if st.st_size != ts.st_size:
             return False
         return st
 
     targets = []
     total = len(candidates)
     pos = 0
     for fn, st in candidates:
         pos += 1
         srcpath = os.path.join(src, fn)
         tgt = os.path.join(dst, fn)
         ts = linkfilter(srcpath, tgt, st)
         if not ts:
             ui.debug('not linkable: %s\n' % fn)
             continue
         targets.append((fn, ts.st_size))
         ui.progress(_('pruning'), pos, fn, _('files'), total)
 
     ui.progress(_('pruning'), None)
     ui.status(_('pruned down to %d probably relinkable files\n') % len(targets))
     return targets
 
 def do_relink(src, dst, files, ui):
     def relinkfile(src, dst):
         bak = dst + '.bak'
         os.rename(dst, bak)
         try:
             util.oslink(src, dst)
         except OSError:
             os.rename(bak, dst)
             raise
         os.remove(bak)
 
     CHUNKLEN = 65536
     relinked = 0
     savedbytes = 0
 
     pos = 0
     total = len(files)
     for f, sz in files:
         pos += 1
         source = os.path.join(src, f)
         tgt = os.path.join(dst, f)
         # Binary mode, so that read() works correctly, especially on Windows
         sfp = file(source, 'rb')
         dfp = file(tgt, 'rb')
         sin = sfp.read(CHUNKLEN)
         while sin:
             din = dfp.read(CHUNKLEN)
             if sin != din:
                 break
             sin = sfp.read(CHUNKLEN)
         sfp.close()
         dfp.close()
         if sin:
             ui.debug('not linkable: %s\n' % f)
             continue
         try:
             relinkfile(source, tgt)
             ui.progress(_('relinking'), pos, f, _('files'), total)
             relinked += 1
             savedbytes += sz
         except OSError, inst:
             ui.warn('%s: %s\n' % (tgt, str(inst)))
 
     ui.progress(_('relinking'), None)
 
     ui.status(_('relinked %d files (%s reclaimed)\n') %
               (relinked, util.bytecount(savedbytes)))
 
 cmdtable = {
     'relink': (
         relink,
         [],
         _('[ORIGIN]')
     )
 }

mercurial/bundlerepo.py

@@ -1,380 +1,380 b''
 # bundlerepo.py - repository class for viewing uncompressed bundles
 #
 # Copyright 2006, 2007 Benoit Boissinot <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 """Repository class for viewing uncompressed bundles.
 
 This provides a read-only repository interface to bundles as if they
 were part of the actual repository.
 """
 
 from node import nullid
 from i18n import _
 import os, tempfile, shutil
 import changegroup, util, mdiff, discovery, cmdutil
 import localrepo, changelog, manifest, filelog, revlog, error
 
 class bundlerevlog(revlog.revlog):
     def __init__(self, opener, indexfile, bundle, linkmapper):
         # How it works:
         # to retrieve a revision, we need to know the offset of
         # the revision in the bundle (an unbundle object).
         #
         # We store this offset in the index (start), to differentiate a
         # rev in the bundle and from a rev in the revlog, we check
         # len(index[r]). If the tuple is bigger than 7, it is a bundle
         # (it is bigger since we store the node to which the delta is)
         #
         revlog.revlog.__init__(self, opener, indexfile)
         self.bundle = bundle
         self.basemap = {}
         n = len(self)
         chain = None
         while True:
             chunkdata = bundle.deltachunk(chain)
             if not chunkdata:
                 break
             node = chunkdata['node']
             p1 = chunkdata['p1']
             p2 = chunkdata['p2']
             cs = chunkdata['cs']
             deltabase = chunkdata['deltabase']
             delta = chunkdata['delta']
 
             size = len(delta)
             start = bundle.tell() - size
 
             link = linkmapper(cs)
             if node in self.nodemap:
                 # this can happen if two branches make the same change
                 chain = node
                 continue
 
             for p in (p1, p2):
-                if not p in self.nodemap:
+                if p not in self.nodemap:
                     raise error.LookupError(p, self.indexfile,
                                             _("unknown parent"))
             # start, size, full unc. size, base (unused), link, p1, p2, node
             e = (revlog.offset_type(start, 0), size, -1, -1, link,
                  self.rev(p1), self.rev(p2), node)
             self.basemap[n] = deltabase
             self.index.insert(-1, e)
             self.nodemap[node] = n
             chain = node
             n += 1
 
     def inbundle(self, rev):
         """is rev from the bundle"""
         if rev < 0:
             return False
         return rev in self.basemap
     def bundlebase(self, rev):
         return self.basemap[rev]
     def _chunk(self, rev):
         # Warning: in case of bundle, the diff is against bundlebase,
         # not against rev - 1
         # XXX: could use some caching
         if not self.inbundle(rev):
             return revlog.revlog._chunk(self, rev)
         self.bundle.seek(self.start(rev))
         return self.bundle.read(self.length(rev))
 
     def revdiff(self, rev1, rev2):
         """return or calculate a delta between two revisions"""
         if self.inbundle(rev1) and self.inbundle(rev2):
             # hot path for bundle
             revb = self.rev(self.bundlebase(rev2))
             if revb == rev1:
                 return self._chunk(rev2)
         elif not self.inbundle(rev1) and not self.inbundle(rev2):
             return revlog.revlog.revdiff(self, rev1, rev2)
 
         return mdiff.textdiff(self.revision(self.node(rev1)),
                          self.revision(self.node(rev2)))
 
     def revision(self, nodeorrev):
         """return an uncompressed revision of a given node or revision
         number.
         """
         if isinstance(nodeorrev, int):
             rev = nodeorrev
             node = self.node(rev)
         else:
             node = nodeorrev
             rev = self.rev(node)
 
         if node == nullid:
             return ""
 
         text = None
         chain = []
         iter_node = node
         # reconstruct the revision if it is from a changegroup
         while self.inbundle(rev):
             if self._cache and self._cache[0] == iter_node:
                 text = self._cache[2]
                 break
             chain.append(rev)
             iter_node = self.bundlebase(rev)
             rev = self.rev(iter_node)
         if text is None:
             text = revlog.revlog.revision(self, iter_node)
 
         while chain:
             delta = self._chunk(chain.pop())
             text = mdiff.patches(text, [delta])
 
         p1, p2 = self.parents(node)
         if node != revlog.hash(text, p1, p2):
             raise error.RevlogError(_("integrity check failed on %s:%d")
                                      % (self.datafile, self.rev(node)))
 
         self._cache = (node, self.rev(node), text)
         return text
 
     def addrevision(self, text, transaction, link, p1=None, p2=None, d=None):
         raise NotImplementedError
     def addgroup(self, revs, linkmapper, transaction):
         raise NotImplementedError
     def strip(self, rev, minlink):
         raise NotImplementedError
     def checksize(self):
         raise NotImplementedError
 
 class bundlechangelog(bundlerevlog, changelog.changelog):
     def __init__(self, opener, bundle):
         changelog.changelog.__init__(self, opener)
         linkmapper = lambda x: x
         bundlerevlog.__init__(self, opener, self.indexfile, bundle,
                               linkmapper)
 
 class bundlemanifest(bundlerevlog, manifest.manifest):
     def __init__(self, opener, bundle, linkmapper):
         manifest.manifest.__init__(self, opener)
         bundlerevlog.__init__(self, opener, self.indexfile, bundle,
                               linkmapper)
 
 class bundlefilelog(bundlerevlog, filelog.filelog):
     def __init__(self, opener, path, bundle, linkmapper, repo):
         filelog.filelog.__init__(self, opener, path)
         bundlerevlog.__init__(self, opener, self.indexfile, bundle,
                               linkmapper)
         self._repo = repo
 
     def _file(self, f):
         self._repo.file(f)
 
 class bundlerepository(localrepo.localrepository):
     def __init__(self, ui, path, bundlename):
         self._tempparent = None
         try:
             localrepo.localrepository.__init__(self, ui, path)
         except error.RepoError:
             self._tempparent = tempfile.mkdtemp()
             localrepo.instance(ui, self._tempparent, 1)
             localrepo.localrepository.__init__(self, ui, self._tempparent)
         self.ui.setconfig('phases', 'publish', False)
 
         if path:
             self._url = 'bundle:' + util.expandpath(path) + '+' + bundlename
         else:
             self._url = 'bundle:' + bundlename
 
         self.tempfile = None
         f = util.posixfile(bundlename, "rb")
         self.bundle = changegroup.readbundle(f, bundlename)
         if self.bundle.compressed():
             fdtemp, temp = tempfile.mkstemp(prefix="hg-bundle-",
                                             suffix=".hg10un", dir=self.path)
             self.tempfile = temp
             fptemp = os.fdopen(fdtemp, 'wb')
 
             try:
                 fptemp.write("HG10UN")
                 while True:
                     chunk = self.bundle.read(2**18)
                     if not chunk:
                         break
                     fptemp.write(chunk)
             finally:
                 fptemp.close()
 
             f = util.posixfile(self.tempfile, "rb")
             self.bundle = changegroup.readbundle(f, bundlename)
 
         # dict with the mapping 'filename' -> position in the bundle
         self.bundlefilespos = {}
 
     @util.propertycache
     def changelog(self):
         # consume the header if it exists
         self.bundle.changelogheader()
         c = bundlechangelog(self.sopener, self.bundle)
         self.manstart = self.bundle.tell()
         return c
 
     @util.propertycache
     def manifest(self):
         self.bundle.seek(self.manstart)
         # consume the header if it exists
         self.bundle.manifestheader()
         m = bundlemanifest(self.sopener, self.bundle, self.changelog.rev)
         self.filestart = self.bundle.tell()
         return m
 
     @util.propertycache
     def manstart(self):
         self.changelog
         return self.manstart
 
     @util.propertycache
     def filestart(self):
         self.manifest
         return self.filestart
 
     def url(self):
         return self._url
 
     def file(self, f):
         if not self.bundlefilespos:
             self.bundle.seek(self.filestart)
             while True:
                 chunkdata = self.bundle.filelogheader()
                 if not chunkdata:
                     break
                 fname = chunkdata['filename']
                 self.bundlefilespos[fname] = self.bundle.tell()
                 while True:
                     c = self.bundle.deltachunk(None)
                     if not c:
                         break
 
         if f[0] == '/':
             f = f[1:]
         if f in self.bundlefilespos:
             self.bundle.seek(self.bundlefilespos[f])
             return bundlefilelog(self.sopener, f, self.bundle,
                                  self.changelog.rev, self)
         else:
             return filelog.filelog(self.sopener, f)
 
     def close(self):
         """Close assigned bundle file immediately."""
         self.bundle.close()
         if self.tempfile is not None:
             os.unlink(self.tempfile)
         if self._tempparent:
             shutil.rmtree(self._tempparent, True)
 
     def cancopy(self):
         return False
 
     def getcwd(self):
         return os.getcwd() # always outside the repo
 
     def _writebranchcache(self, branches, tip, tiprev):
         # don't overwrite the disk cache with bundle-augmented data
         pass
 
 def instance(ui, path, create):
     if create:
         raise util.Abort(_('cannot create new bundle repository'))
     parentpath = ui.config("bundle", "mainreporoot", "")
     if not parentpath:
         # try to find the correct path to the working directory repo
         parentpath = cmdutil.findrepo(os.getcwd())
         if parentpath is None:
             parentpath = ''
     if parentpath:
         # Try to make the full path relative so we get a nice, short URL.
         # In particular, we don't want temp dir names in test outputs.
         cwd = os.getcwd()
         if parentpath == cwd:
             parentpath = ''
         else:
             cwd = os.path.join(cwd,'')
             if parentpath.startswith(cwd):
                 parentpath = parentpath[len(cwd):]
     u = util.url(path)
     path = u.localpath()
     if u.scheme == 'bundle':
         s = path.split("+", 1)
         if len(s) == 1:
             repopath, bundlename = parentpath, s[0]
         else:
             repopath, bundlename = s
     else:
         repopath, bundlename = parentpath, path
     return bundlerepository(ui, repopath, bundlename)
 
 def getremotechanges(ui, repo, other, onlyheads=None, bundlename=None,
                      force=False):
     '''obtains a bundle of changes incoming from other
 
     "onlyheads" restricts the returned changes to those reachable from the
       specified heads.
     "bundlename", if given, stores the bundle to this file path permanently;
       otherwise it's stored to a temp file and gets deleted again when you call
       the returned "cleanupfn".
     "force" indicates whether to proceed on unrelated repos.
 
     Returns a tuple (local, csets, cleanupfn):
 
     "local" is a local repo from which to obtain the actual incoming
       changesets; it is a bundlerepo for the obtained bundle when the
       original "other" is remote.
     "csets" lists the incoming changeset node ids.
     "cleanupfn" must be called without arguments when you're done processing
       the changes; it closes both the original "other" and the one returned
       here.
     '''
     tmp = discovery.findcommonincoming(repo, other, heads=onlyheads,
                                        force=force)
     common, incoming, rheads = tmp
     if not incoming:
         try:
             if bundlename:
                 os.unlink(bundlename)
         except OSError:
             pass
         return other, [], other.close
 
     bundle = None
     bundlerepo = None
     localrepo = other
     if bundlename or not other.local():
         # create a bundle (uncompressed if other repo is not local)
 
         if other.capable('getbundle'):
             cg = other.getbundle('incoming', common=common, heads=rheads)
         elif onlyheads is None and not other.capable('changegroupsubset'):
             # compat with older servers when pulling all remote heads
             cg = other.changegroup(incoming, "incoming")
             rheads = None
         else:
             cg = other.changegroupsubset(incoming, rheads, 'incoming')
         bundletype = other.local() and "HG10BZ" or "HG10UN"
         fname = bundle = changegroup.writebundle(cg, bundlename, bundletype)
         # keep written bundle?
         if bundlename:
             bundle = None
         if not other.local():
             # use the created uncompressed bundlerepo
             localrepo = bundlerepo = bundlerepository(ui, repo.root, fname)
             # this repo contains local and other now, so filter out local again
             common = repo.heads()
 
     csets = localrepo.changelog.findmissing(common, rheads)
 
     def cleanup():
         if bundlerepo:
             bundlerepo.close()
         if bundle:
             os.unlink(bundle)
         other.close()
 
     return (localrepo, csets, cleanup)
 

mercurial/dirstate.py

@@ -1,796 +1,796 b''
 # dirstate.py - working directory tracking for mercurial
 #
 # Copyright 2005-2007 Matt Mackall <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 import errno
 
 from node import nullid
 from i18n import _
 import scmutil, util, ignore, osutil, parsers, encoding
 import struct, os, stat, errno
 import cStringIO
 
 _format = ">cllll"
 propertycache = util.propertycache
 filecache = scmutil.filecache
 
 class repocache(filecache):
     """filecache for files in .hg/"""
     def join(self, obj, fname):
         return obj._opener.join(fname)
 
 class rootcache(filecache):
     """filecache for files in the repository root"""
     def join(self, obj, fname):
         return obj._join(fname)
 
 def _finddirs(path):
     pos = path.rfind('/')
     while pos != -1:
         yield path[:pos]
         pos = path.rfind('/', 0, pos)
 
 def _incdirs(dirs, path):
     for base in _finddirs(path):
         if base in dirs:
             dirs[base] += 1
             return
         dirs[base] = 1
 
 def _decdirs(dirs, path):
     for base in _finddirs(path):
         if dirs[base] > 1:
             dirs[base] -= 1
             return
         del dirs[base]
 
 class dirstate(object):
 
     def __init__(self, opener, ui, root, validate):
         '''Create a new dirstate object.
 
         opener is an open()-like callable that can be used to open the
         dirstate file; root is the root of the directory tracked by
         the dirstate.
         '''
         self._opener = opener
         self._validate = validate
         self._root = root
         self._rootdir = os.path.join(root, '')
         self._dirty = False
         self._dirtypl = False
         self._lastnormaltime = 0
         self._ui = ui
         self._filecache = {}
 
     @propertycache
     def _map(self):
         '''Return the dirstate contents as a map from filename to
         (state, mode, size, time).'''
         self._read()
         return self._map
 
     @propertycache
     def _copymap(self):
         self._read()
         return self._copymap
 
     @propertycache
     def _foldmap(self):
         f = {}
         for name in self._map:
             f[util.normcase(name)] = name
         for name in self._dirs:
             f[util.normcase(name)] = name
         f['.'] = '.' # prevents useless util.fspath() invocation
         return f
 
     @repocache('branch')
     def _branch(self):
         try:
             return self._opener.read("branch").strip() or "default"
         except IOError, inst:
             if inst.errno != errno.ENOENT:
                 raise
             return "default"
 
     @propertycache
     def _pl(self):
         try:
             fp = self._opener("dirstate")
             st = fp.read(40)
             fp.close()
             l = len(st)
             if l == 40:
                 return st[:20], st[20:40]
             elif l > 0 and l < 40:
                 raise util.Abort(_('working directory state appears damaged!'))
         except IOError, err:
             if err.errno != errno.ENOENT:
                 raise
         return [nullid, nullid]
 
     @propertycache
     def _dirs(self):
         dirs = {}
         for f, s in self._map.iteritems():
             if s[0] != 'r':
                 _incdirs(dirs, f)
         return dirs
 
     def dirs(self):
         return self._dirs
 
     @rootcache('.hgignore')
     def _ignore(self):
         files = [self._join('.hgignore')]
         for name, path in self._ui.configitems("ui"):
             if name == 'ignore' or name.startswith('ignore.'):
                 files.append(util.expandpath(path))
         return ignore.ignore(self._root, files, self._ui.warn)
 
     @propertycache
     def _slash(self):
         return self._ui.configbool('ui', 'slash') and os.sep != '/'
 
     @propertycache
     def _checklink(self):
         return util.checklink(self._root)
 
     @propertycache
     def _checkexec(self):
         return util.checkexec(self._root)
 
     @propertycache
     def _checkcase(self):
         return not util.checkcase(self._join('.hg'))
 
     def _join(self, f):
         # much faster than os.path.join()
         # it's safe because f is always a relative path
         return self._rootdir + f
 
     def flagfunc(self, buildfallback):
         if self._checklink and self._checkexec:
             def f(x):
                 p = self._join(x)
                 if os.path.islink(p):
                     return 'l'
                 if util.isexec(p):
                     return 'x'
                 return ''
             return f
 
         fallback = buildfallback()
         if self._checklink:
             def f(x):
                 if os.path.islink(self._join(x)):
                     return 'l'
                 if 'x' in fallback(x):
                     return 'x'
                 return ''
             return f
         if self._checkexec:
             def f(x):
                 if 'l' in fallback(x):
                     return 'l'
                 if util.isexec(self._join(x)):
                     return 'x'
                 return ''
             return f
         else:
             return fallback
 
     def getcwd(self):
         cwd = os.getcwd()
         if cwd == self._root:
             return ''
         # self._root ends with a path separator if self._root is '/' or 'C:\'
         rootsep = self._root
         if not util.endswithsep(rootsep):
             rootsep += os.sep
         if cwd.startswith(rootsep):
             return cwd[len(rootsep):]
         else:
             # we're outside the repo. return an absolute path.
             return cwd
 
     def pathto(self, f, cwd=None):
         if cwd is None:
             cwd = self.getcwd()
         path = util.pathto(self._root, cwd, f)
         if self._slash:
             return util.normpath(path)
         return path
 
     def __getitem__(self, key):
         '''Return the current state of key (a filename) in the dirstate.
 
         States are:
           n  normal
           m  needs merging
           r  marked for removal
           a  marked for addition
           ?  not tracked
         '''
         return self._map.get(key, ("?",))[0]
 
     def __contains__(self, key):
         return key in self._map
 
     def __iter__(self):
         for x in sorted(self._map):
             yield x
 
     def parents(self):
         return [self._validate(p) for p in self._pl]
 
     def p1(self):
         return self._validate(self._pl[0])
 
     def p2(self):
         return self._validate(self._pl[1])
 
     def branch(self):
         return encoding.tolocal(self._branch)
 
     def setparents(self, p1, p2=nullid):
         """Set dirstate parents to p1 and p2.
 
         When moving from two parents to one, 'm' merged entries a
         adjusted to normal and previous copy records discarded and
         returned by the call.
 
         See localrepo.setparents()
         """
         self._dirty = self._dirtypl = True
         oldp2 = self._pl[1]
         self._pl = p1, p2
         copies = {}
         if oldp2 != nullid and p2 == nullid:
             # Discard 'm' markers when moving away from a merge state
             for f, s in self._map.iteritems():
                 if s[0] == 'm':
                     if f in self._copymap:
                         copies[f] = self._copymap[f]
                     self.normallookup(f)
         return copies
 
     def setbranch(self, branch):
         if branch in ['tip', '.', 'null']:
             raise util.Abort(_('the name \'%s\' is reserved') % branch)
         self._branch = encoding.fromlocal(branch)
         f = self._opener('branch', 'w', atomictemp=True)
         try:
             f.write(self._branch + '\n')
         finally:
             f.close()
 
     def _read(self):
         self._map = {}
         self._copymap = {}
         try:
             st = self._opener.read("dirstate")
         except IOError, err:
             if err.errno != errno.ENOENT:
                 raise
             return
         if not st:
             return
 
         p = parsers.parse_dirstate(self._map, self._copymap, st)
         if not self._dirtypl:
             self._pl = p
 
     def invalidate(self):
         for a in ("_map", "_copymap", "_foldmap", "_branch", "_pl", "_dirs",
                 "_ignore"):
             if a in self.__dict__:
                 delattr(self, a)
         self._lastnormaltime = 0
         self._dirty = False
 
     def copy(self, source, dest):
         """Mark dest as a copy of source. Unmark dest if source is None."""
         if source == dest:
             return
         self._dirty = True
         if source is not None:
             self._copymap[dest] = source
         elif dest in self._copymap:
             del self._copymap[dest]
 
     def copied(self, file):
         return self._copymap.get(file, None)
 
     def copies(self):
         return self._copymap
 
     def _droppath(self, f):
         if self[f] not in "?r" and "_dirs" in self.__dict__:
             _decdirs(self._dirs, f)
 
     def _addpath(self, f, check=False):
         oldstate = self[f]
         if check or oldstate == "r":
             scmutil.checkfilename(f)
             if f in self._dirs:
                 raise util.Abort(_('directory %r already in dirstate') % f)
             # shadows
             for d in _finddirs(f):
                 if d in self._dirs:
                     break
                 if d in self._map and self[d] != 'r':
                     raise util.Abort(
                         _('file %r in dirstate clashes with %r') % (d, f))
         if oldstate in "?r" and "_dirs" in self.__dict__:
             _incdirs(self._dirs, f)
 
     def normal(self, f):
         '''Mark a file normal and clean.'''
         self._dirty = True
         self._addpath(f)
         s = os.lstat(self._join(f))
         mtime = int(s.st_mtime)
         self._map[f] = ('n', s.st_mode, s.st_size, mtime)
         if f in self._copymap:
             del self._copymap[f]
         if mtime > self._lastnormaltime:
             # Remember the most recent modification timeslot for status(),
             # to make sure we won't miss future size-preserving file content
             # modifications that happen within the same timeslot.
             self._lastnormaltime = mtime
 
     def normallookup(self, f):
         '''Mark a file normal, but possibly dirty.'''
         if self._pl[1] != nullid and f in self._map:
             # if there is a merge going on and the file was either
             # in state 'm' (-1) or coming from other parent (-2) before
             # being removed, restore that state.
             entry = self._map[f]
             if entry[0] == 'r' and entry[2] in (-1, -2):
                 source = self._copymap.get(f)
                 if entry[2] == -1:
                     self.merge(f)
                 elif entry[2] == -2:
                     self.otherparent(f)
                 if source:
                     self.copy(source, f)
                 return
             if entry[0] == 'm' or entry[0] == 'n' and entry[2] == -2:
                 return
         self._dirty = True
         self._addpath(f)
         self._map[f] = ('n', 0, -1, -1)
         if f in self._copymap:
             del self._copymap[f]
 
     def otherparent(self, f):
         '''Mark as coming from the other parent, always dirty.'''
         if self._pl[1] == nullid:
             raise util.Abort(_("setting %r to other parent "
                                "only allowed in merges") % f)
         self._dirty = True
         self._addpath(f)
         self._map[f] = ('n', 0, -2, -1)
         if f in self._copymap:
             del self._copymap[f]
 
     def add(self, f):
         '''Mark a file added.'''
         self._dirty = True
         self._addpath(f, True)
         self._map[f] = ('a', 0, -1, -1)
         if f in self._copymap:
             del self._copymap[f]
 
     def remove(self, f):
         '''Mark a file removed.'''
         self._dirty = True
         self._droppath(f)
         size = 0
         if self._pl[1] != nullid and f in self._map:
             # backup the previous state
             entry = self._map[f]
             if entry[0] == 'm': # merge
                 size = -1
             elif entry[0] == 'n' and entry[2] == -2: # other parent
                 size = -2
         self._map[f] = ('r', 0, size, 0)
         if size == 0 and f in self._copymap:
             del self._copymap[f]
 
     def merge(self, f):
         '''Mark a file merged.'''
         if self._pl[1] == nullid:
             return self.normallookup(f)
         self._dirty = True
         s = os.lstat(self._join(f))
         self._addpath(f)
         self._map[f] = ('m', s.st_mode, s.st_size, int(s.st_mtime))
         if f in self._copymap:
             del self._copymap[f]
 
     def drop(self, f):
         '''Drop a file from the dirstate'''
         if f in self._map:
             self._dirty = True
             self._droppath(f)
             del self._map[f]
 
     def _normalize(self, path, isknown, ignoremissing=False, exists=None):
         normed = util.normcase(path)
         folded = self._foldmap.get(normed, None)
         if folded is None:
             if isknown:
                 folded = path
             else:
                 if exists is None:
                     exists = os.path.lexists(os.path.join(self._root, path))
                 if not exists:
                     # Maybe a path component exists
                     if not ignoremissing and '/' in path:
                         d, f = path.rsplit('/', 1)
                         d = self._normalize(d, isknown, ignoremissing, None)
                         folded = d + "/" + f
                     else:
                         # No path components, preserve original case
                         folded = path
                 else:
                     # recursively normalize leading directory components
                     # against dirstate
                     if '/' in normed:
                         d, f = normed.rsplit('/', 1)
                         d = self._normalize(d, isknown, ignoremissing, True)
                         r = self._root + "/" + d
                         folded = d + "/" + util.fspath(f, r)
                     else:
                         folded = util.fspath(normed, self._root)
                     self._foldmap[normed] = folded
 
         return folded
 
     def normalize(self, path, isknown=False, ignoremissing=False):
         '''
         normalize the case of a pathname when on a casefolding filesystem
 
         isknown specifies whether the filename came from walking the
         disk, to avoid extra filesystem access.
 
         If ignoremissing is True, missing path are returned
         unchanged. Otherwise, we try harder to normalize possibly
         existing path components.
 
         The normalized case is determined based on the following precedence:
 
         - version of name already stored in the dirstate
         - version of name stored on disk
         - version provided via command arguments
         '''
 
         if self._checkcase:
             return self._normalize(path, isknown, ignoremissing)
         return path
 
     def clear(self):
         self._map = {}
         if "_dirs" in self.__dict__:
             delattr(self, "_dirs")
         self._copymap = {}
         self._pl = [nullid, nullid]
         self._lastnormaltime = 0
         self._dirty = True
 
     def rebuild(self, parent, files):
         self.clear()
         for f in files:
             if 'x' in files.flags(f):
                 self._map[f] = ('n', 0777, -1, 0)
             else:
                 self._map[f] = ('n', 0666, -1, 0)
         self._pl = (parent, nullid)
         self._dirty = True
 
     def write(self):
         if not self._dirty:
             return
         st = self._opener("dirstate", "w", atomictemp=True)
 
         # use the modification time of the newly created temporary file as the
         # filesystem's notion of 'now'
         now = int(util.fstat(st).st_mtime)
 
         cs = cStringIO.StringIO()
         copymap = self._copymap
         pack = struct.pack
         write = cs.write
         write("".join(self._pl))
         for f, e in self._map.iteritems():
             if e[0] == 'n' and e[3] == now:
                 # The file was last modified "simultaneously" with the current
                 # write to dirstate (i.e. within the same second for file-
                 # systems with a granularity of 1 sec). This commonly happens
                 # for at least a couple of files on 'update'.
                 # The user could change the file without changing its size
                 # within the same second. Invalidate the file's stat data in
                 # dirstate, forcing future 'status' calls to compare the
                 # contents of the file. This prevents mistakenly treating such
                 # files as clean.
                 e = (e[0], 0, -1, -1)   # mark entry as 'unset'
                 self._map[f] = e
 
             if f in copymap:
                 f = "%s\0%s" % (f, copymap[f])
             e = pack(_format, e[0], e[1], e[2], e[3], len(f))
             write(e)
             write(f)
         st.write(cs.getvalue())
         st.close()
         self._lastnormaltime = 0
         self._dirty = self._dirtypl = False
 
     def _dirignore(self, f):
         if f == '.':
             return False
         if self._ignore(f):
             return True
         for p in _finddirs(f):
             if self._ignore(p):
                 return True
         return False
 
     def walk(self, match, subrepos, unknown, ignored):
         '''
         Walk recursively through the directory tree, finding all files
         matched by match.
 
         Return a dict mapping filename to stat-like object (either
         mercurial.osutil.stat instance or return value of os.stat()).
         '''
 
         def fwarn(f, msg):
             self._ui.warn('%s: %s\n' % (self.pathto(f), msg))
             return False
 
         def badtype(mode):
             kind = _('unknown')
             if stat.S_ISCHR(mode):
                 kind = _('character device')
             elif stat.S_ISBLK(mode):
                 kind = _('block device')
             elif stat.S_ISFIFO(mode):
                 kind = _('fifo')
             elif stat.S_ISSOCK(mode):
                 kind = _('socket')
             elif stat.S_ISDIR(mode):
                 kind = _('directory')
             return _('unsupported file type (type is %s)') % kind
 
         ignore = self._ignore
         dirignore = self._dirignore
         if ignored:
             ignore = util.never
             dirignore = util.never
         elif not unknown:
             # if unknown and ignored are False, skip step 2
             ignore = util.always
             dirignore = util.always
 
         matchfn = match.matchfn
         badfn = match.bad
         dmap = self._map
         normpath = util.normpath
         listdir = osutil.listdir
         lstat = os.lstat
         getkind = stat.S_IFMT
         dirkind = stat.S_IFDIR
         regkind = stat.S_IFREG
         lnkkind = stat.S_IFLNK
         join = self._join
         work = []
         wadd = work.append
 
         exact = skipstep3 = False
         if matchfn == match.exact: # match.exact
             exact = True
             dirignore = util.always # skip step 2
         elif match.files() and not match.anypats(): # match.match, no patterns
             skipstep3 = True
 
         if not exact and self._checkcase:
             normalize = self._normalize
             skipstep3 = False
         else:
             normalize = lambda x, y, z: x
 
         files = sorted(match.files())
         subrepos.sort()
         i, j = 0, 0
         while i < len(files) and j < len(subrepos):
             subpath = subrepos[j] + "/"
             if files[i] < subpath:
                 i += 1
                 continue
             while i < len(files) and files[i].startswith(subpath):
                 del files[i]
             j += 1
 
         if not files or '.' in files:
             files = ['']
         results = dict.fromkeys(subrepos)
         results['.hg'] = None
 
         # step 1: find all explicit files
         for ff in files:
             nf = normalize(normpath(ff), False, True)
             if nf in results:
                 continue
 
             try:
                 st = lstat(join(nf))
                 kind = getkind(st.st_mode)
                 if kind == dirkind:
                     skipstep3 = False
                     if nf in dmap:
                         #file deleted on disk but still in dirstate
                         results[nf] = None
                     match.dir(nf)
                     if not dirignore(nf):
                         wadd(nf)
                 elif kind == regkind or kind == lnkkind:
                     results[nf] = st
                 else:
                     badfn(ff, badtype(kind))
                     if nf in dmap:
                         results[nf] = None
             except OSError, inst:
                 if nf in dmap: # does it exactly match a file?
                     results[nf] = None
                 else: # does it match a directory?
                     prefix = nf + "/"
                     for fn in dmap:
                         if fn.startswith(prefix):
                             match.dir(nf)
                             skipstep3 = False
                             break
                     else:
                         badfn(ff, inst.strerror)
 
         # step 2: visit subdirectories
         while work:
             nd = work.pop()
             skip = None
             if nd == '.':
                 nd = ''
             else:
                 skip = '.hg'
             try:
                 entries = listdir(join(nd), stat=True, skip=skip)
             except OSError, inst:
                 if inst.errno == errno.EACCES:
                     fwarn(nd, inst.strerror)
                     continue
                 raise
             for f, kind, st in entries:
                 nf = normalize(nd and (nd + "/" + f) or f, True, True)
                 if nf not in results:
                     if kind == dirkind:
                         if not ignore(nf):
                             match.dir(nf)
                             wadd(nf)
                         if nf in dmap and matchfn(nf):
                             results[nf] = None
                     elif kind == regkind or kind == lnkkind:
                         if nf in dmap:
                             if matchfn(nf):
                                 results[nf] = st
                         elif matchfn(nf) and not ignore(nf):
                             results[nf] = st
                     elif nf in dmap and matchfn(nf):
                         results[nf] = None
 
         # step 3: report unseen items in the dmap hash
         if not skipstep3 and not exact:
             visit = sorted([f for f in dmap if f not in results and matchfn(f)])
             for nf, st in zip(visit, util.statfiles([join(i) for i in visit])):
                 if (not st is None and
-                    not getkind(st.st_mode) in (regkind, lnkkind)):
+                    getkind(st.st_mode) not in (regkind, lnkkind)):
                     st = None
                 results[nf] = st
         for s in subrepos:
             del results[s]
         del results['.hg']
         return results
 
     def status(self, match, subrepos, ignored, clean, unknown):
         '''Determine the status of the working copy relative to the
         dirstate and return a tuple of lists (unsure, modified, added,
         removed, deleted, unknown, ignored, clean), where:
 
           unsure:
             files that might have been modified since the dirstate was
             written, but need to be read to be sure (size is the same
             but mtime differs)
           modified:
             files that have definitely been modified since the dirstate
             was written (different size or mode)
           added:
             files that have been explicitly added with hg add
           removed:
             files that have been explicitly removed with hg remove
           deleted:
             files that have been deleted through other means ("missing")
           unknown:
             files not in the dirstate that are not ignored
           ignored:
             files not in the dirstate that are ignored
             (by _dirignore())
           clean:
             files that have definitely not been modified since the
             dirstate was written
         '''
         listignored, listclean, listunknown = ignored, clean, unknown
         lookup, modified, added, unknown, ignored = [], [], [], [], []
         removed, deleted, clean = [], [], []
 
         dmap = self._map
         ladd = lookup.append            # aka "unsure"
         madd = modified.append
         aadd = added.append
         uadd = unknown.append
         iadd = ignored.append
         radd = removed.append
         dadd = deleted.append
         cadd = clean.append
 
         lnkkind = stat.S_IFLNK
 
         for fn, st in self.walk(match, subrepos, listunknown,
                                 listignored).iteritems():
             if fn not in dmap:
                 if (listignored or match.exact(fn)) and self._dirignore(fn):
                     if listignored:
                         iadd(fn)
                 elif listunknown:
                     uadd(fn)
                 continue
 
             state, mode, size, time = dmap[fn]
 
             if not st and state in "nma":
                 dadd(fn)
             elif state == 'n':
                 # The "mode & lnkkind != lnkkind or self._checklink"
                 # lines are an expansion of "islink => checklink"
                 # where islink means "is this a link?" and checklink
                 # means "can we check links?".
                 mtime = int(st.st_mtime)
                 if (size >= 0 and
                     (size != st.st_size
                      or ((mode ^ st.st_mode) & 0100 and self._checkexec))
                     and (mode & lnkkind != lnkkind or self._checklink)
                     or size == -2 # other parent
                     or fn in self._copymap):
                     madd(fn)
                 elif (mtime != time
                       and (mode & lnkkind != lnkkind or self._checklink)):
                     ladd(fn)
                 elif mtime == self._lastnormaltime:
                     # fn may have been changed in the same timeslot without
                     # changing its size. This can happen if we quickly do
                     # multiple commits in a single transaction.
                     # Force lookup, so we don't miss such a racy file change.
                     ladd(fn)
                 elif listclean:
                     cadd(fn)
             elif state == 'm':
                 madd(fn)
             elif state == 'a':
                 aadd(fn)
             elif state == 'r':
                 radd(fn)
 
         return (lookup, modified, added, removed, deleted, unknown, ignored,
                 clean)

mercurial/dispatch.py

@@ -1,789 +1,789 b''
 # dispatch.py - command dispatching for mercurial
 #
 # Copyright 2005-2007 Matt Mackall <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 from i18n import _
 import os, sys, atexit, signal, pdb, socket, errno, shlex, time, traceback, re
 import util, commands, hg, fancyopts, extensions, hook, error
 import cmdutil, encoding
 import ui as uimod
 
 class request(object):
     def __init__(self, args, ui=None, repo=None, fin=None, fout=None,
                  ferr=None):
         self.args = args
         self.ui = ui
         self.repo = repo
 
         # input/output/error streams
         self.fin = fin
         self.fout = fout
         self.ferr = ferr
 
 def run():
     "run the command in sys.argv"
     sys.exit((dispatch(request(sys.argv[1:])) or 0) & 255)
 
 def dispatch(req):
     "run the command specified in req.args"
     if req.ferr:
         ferr = req.ferr
     elif req.ui:
         ferr = req.ui.ferr
     else:
         ferr = sys.stderr
 
     try:
         if not req.ui:
             req.ui = uimod.ui()
         if '--traceback' in req.args:
             req.ui.setconfig('ui', 'traceback', 'on')
 
         # set ui streams from the request
         if req.fin:
             req.ui.fin = req.fin
         if req.fout:
             req.ui.fout = req.fout
         if req.ferr:
             req.ui.ferr = req.ferr
     except util.Abort, inst:
         ferr.write(_("abort: %s\n") % inst)
         if inst.hint:
             ferr.write(_("(%s)\n") % inst.hint)
         return -1
     except error.ParseError, inst:
         if len(inst.args) > 1:
             ferr.write(_("hg: parse error at %s: %s\n") %
                              (inst.args[1], inst.args[0]))
         else:
             ferr.write(_("hg: parse error: %s\n") % inst.args[0])
         return -1
 
     return _runcatch(req)
 
 def _runcatch(req):
     def catchterm(*args):
         raise error.SignalInterrupt
 
     ui = req.ui
     try:
         for name in 'SIGBREAK', 'SIGHUP', 'SIGTERM':
             num = getattr(signal, name, None)
             if num:
                 signal.signal(num, catchterm)
     except ValueError:
         pass # happens if called in a thread
 
     try:
         try:
             # enter the debugger before command execution
             if '--debugger' in req.args:
                 ui.warn(_("entering debugger - "
                         "type c to continue starting hg or h for help\n"))
                 pdb.set_trace()
             try:
                 return _dispatch(req)
             finally:
                 ui.flush()
         except:
             # enter the debugger when we hit an exception
             if '--debugger' in req.args:
                 traceback.print_exc()
                 pdb.post_mortem(sys.exc_info()[2])
             ui.traceback()
             raise
 
     # Global exception handling, alphabetically
     # Mercurial-specific first, followed by built-in and library exceptions
     except error.AmbiguousCommand, inst:
         ui.warn(_("hg: command '%s' is ambiguous:\n    %s\n") %
                 (inst.args[0], " ".join(inst.args[1])))
     except error.ParseError, inst:
         if len(inst.args) > 1:
             ui.warn(_("hg: parse error at %s: %s\n") %
                              (inst.args[1], inst.args[0]))
         else:
             ui.warn(_("hg: parse error: %s\n") % inst.args[0])
         return -1
     except error.LockHeld, inst:
         if inst.errno == errno.ETIMEDOUT:
             reason = _('timed out waiting for lock held by %s') % inst.locker
         else:
             reason = _('lock held by %s') % inst.locker
         ui.warn(_("abort: %s: %s\n") % (inst.desc or inst.filename, reason))
     except error.LockUnavailable, inst:
         ui.warn(_("abort: could not lock %s: %s\n") %
                (inst.desc or inst.filename, inst.strerror))
     except error.CommandError, inst:
         if inst.args[0]:
             ui.warn(_("hg %s: %s\n") % (inst.args[0], inst.args[1]))
             commands.help_(ui, inst.args[0], full=False, command=True)
         else:
             ui.warn(_("hg: %s\n") % inst.args[1])
             commands.help_(ui, 'shortlist')
     except error.OutOfBandError, inst:
         ui.warn(_("abort: remote error:\n"))
         ui.warn(''.join(inst.args))
     except error.RepoError, inst:
         ui.warn(_("abort: %s!\n") % inst)
         if inst.hint:
             ui.warn(_("(%s)\n") % inst.hint)
     except error.ResponseError, inst:
         ui.warn(_("abort: %s") % inst.args[0])
         if not isinstance(inst.args[1], basestring):
             ui.warn(" %r\n" % (inst.args[1],))
         elif not inst.args[1]:
             ui.warn(_(" empty string\n"))
         else:
             ui.warn("\n%r\n" % util.ellipsis(inst.args[1]))
     except error.RevlogError, inst:
         ui.warn(_("abort: %s!\n") % inst)
     except error.SignalInterrupt:
         ui.warn(_("killed!\n"))
     except error.UnknownCommand, inst:
         ui.warn(_("hg: unknown command '%s'\n") % inst.args[0])
         try:
             # check if the command is in a disabled extension
             # (but don't check for extensions themselves)
             commands.help_(ui, inst.args[0], unknowncmd=True)
         except error.UnknownCommand:
             commands.help_(ui, 'shortlist')
     except util.Abort, inst:
         ui.warn(_("abort: %s\n") % inst)
         if inst.hint:
             ui.warn(_("(%s)\n") % inst.hint)
     except ImportError, inst:
         ui.warn(_("abort: %s!\n") % inst)
         m = str(inst).split()[-1]
         if m in "mpatch bdiff".split():
             ui.warn(_("(did you forget to compile extensions?)\n"))
         elif m in "zlib".split():
             ui.warn(_("(is your Python install correct?)\n"))
     except IOError, inst:
         if util.safehasattr(inst, "code"):
             ui.warn(_("abort: %s\n") % inst)
         elif util.safehasattr(inst, "reason"):
             try: # usually it is in the form (errno, strerror)
                 reason = inst.reason.args[1]
             except (AttributeError, IndexError):
                  # it might be anything, for example a string
                 reason = inst.reason
             ui.warn(_("abort: error: %s\n") % reason)
         elif util.safehasattr(inst, "args") and inst.args[0] == errno.EPIPE:
             if ui.debugflag:
                 ui.warn(_("broken pipe\n"))
         elif getattr(inst, "strerror", None):
             if getattr(inst, "filename", None):
                 ui.warn(_("abort: %s: %s\n") % (inst.strerror, inst.filename))
             else:
                 ui.warn(_("abort: %s\n") % inst.strerror)
         else:
             raise
     except OSError, inst:
         if getattr(inst, "filename", None):
             ui.warn(_("abort: %s: %s\n") % (inst.strerror, inst.filename))
         else:
             ui.warn(_("abort: %s\n") % inst.strerror)
     except KeyboardInterrupt:
         try:
             ui.warn(_("interrupted!\n"))
         except IOError, inst:
             if inst.errno == errno.EPIPE:
                 if ui.debugflag:
                     ui.warn(_("\nbroken pipe\n"))
             else:
                 raise
     except MemoryError:
         ui.warn(_("abort: out of memory\n"))
     except SystemExit, inst:
         # Commands shouldn't sys.exit directly, but give a return code.
         # Just in case catch this and and pass exit code to caller.
         return inst.code
     except socket.error, inst:
         ui.warn(_("abort: %s\n") % inst.args[-1])
     except:
         ui.warn(_("** unknown exception encountered,"
                   " please report by visiting\n"))
         ui.warn(_("**  http://mercurial.selenic.com/wiki/BugTracker\n"))
         ui.warn(_("** Python %s\n") % sys.version.replace('\n', ''))
         ui.warn(_("** Mercurial Distributed SCM (version %s)\n")
                % util.version())
         ui.warn(_("** Extensions loaded: %s\n")
                % ", ".join([x[0] for x in extensions.extensions()]))
         raise
 
     return -1
 
 def aliasargs(fn, givenargs):
     args = getattr(fn, 'args', [])
     if args:
         cmd = ' '.join(map(util.shellquote, args))
 
         nums = []
         def replacer(m):
             num = int(m.group(1)) - 1
             nums.append(num)
             if num < len(givenargs):
                 return givenargs[num]
             raise util.Abort(_('too few arguments for command alias'))
         cmd = re.sub(r'\$(\d+|\$)', replacer, cmd)
         givenargs = [x for i, x in enumerate(givenargs)
                      if i not in nums]
         args = shlex.split(cmd)
     return args + givenargs
 
 class cmdalias(object):
     def __init__(self, name, definition, cmdtable):
         self.name = self.cmd = name
         self.cmdname = ''
         self.definition = definition
         self.args = []
         self.opts = []
         self.help = ''
         self.norepo = True
         self.optionalrepo = False
         self.badalias = False
 
         try:
             aliases, entry = cmdutil.findcmd(self.name, cmdtable)
             for alias, e in cmdtable.iteritems():
                 if e is entry:
                     self.cmd = alias
                     break
             self.shadows = True
         except error.UnknownCommand:
             self.shadows = False
 
         if not self.definition:
             def fn(ui, *args):
                 ui.warn(_("no definition for alias '%s'\n") % self.name)
                 return 1
             self.fn = fn
             self.badalias = True
             return
 
         if self.definition.startswith('!'):
             self.shell = True
             def fn(ui, *args):
                 env = {'HG_ARGS': ' '.join((self.name,) + args)}
                 def _checkvar(m):
                     if m.groups()[0] == '$':
                         return m.group()
                     elif int(m.groups()[0]) <= len(args):
                         return m.group()
                     else:
                         ui.debug("No argument found for substitution "
                                  "of %i variable in alias '%s' definition."
                                  % (int(m.groups()[0]), self.name))
                         return ''
                 cmd = re.sub(r'\$(\d+|\$)', _checkvar, self.definition[1:])
                 replace = dict((str(i + 1), arg) for i, arg in enumerate(args))
                 replace['0'] = self.name
                 replace['@'] = ' '.join(args)
                 cmd = util.interpolate(r'\$', replace, cmd, escape_prefix=True)
                 return util.system(cmd, environ=env, out=ui.fout)
             self.fn = fn
             return
 
         args = shlex.split(self.definition)
         self.cmdname = cmd = args.pop(0)
         args = map(util.expandpath, args)
 
         for invalidarg in ("--cwd", "-R", "--repository", "--repo"):
             if _earlygetopt([invalidarg], args):
                 def fn(ui, *args):
                     ui.warn(_("error in definition for alias '%s': %s may only "
                               "be given on the command line\n")
                             % (self.name, invalidarg))
                     return 1
 
                 self.fn = fn
                 self.badalias = True
                 return
 
         try:
             tableentry = cmdutil.findcmd(cmd, cmdtable, False)[1]
             if len(tableentry) > 2:
                 self.fn, self.opts, self.help = tableentry
             else:
                 self.fn, self.opts = tableentry
 
             self.args = aliasargs(self.fn, args)
             if cmd not in commands.norepo.split(' '):
                 self.norepo = False
             if cmd in commands.optionalrepo.split(' '):
                 self.optionalrepo = True
             if self.help.startswith("hg " + cmd):
                 # drop prefix in old-style help lines so hg shows the alias
                 self.help = self.help[4 + len(cmd):]
             self.__doc__ = self.fn.__doc__
 
         except error.UnknownCommand:
             def fn(ui, *args):
                 ui.warn(_("alias '%s' resolves to unknown command '%s'\n") \
                             % (self.name, cmd))
                 try:
                     # check if the command is in a disabled extension
                     commands.help_(ui, cmd, unknowncmd=True)
                 except error.UnknownCommand:
                     pass
                 return 1
             self.fn = fn
             self.badalias = True
         except error.AmbiguousCommand:
             def fn(ui, *args):
                 ui.warn(_("alias '%s' resolves to ambiguous command '%s'\n") \
                             % (self.name, cmd))
                 return 1
             self.fn = fn
             self.badalias = True
 
     def __call__(self, ui, *args, **opts):
         if self.shadows:
             ui.debug("alias '%s' shadows command '%s'\n" %
                      (self.name, self.cmdname))
 
         if util.safehasattr(self, 'shell'):
             return self.fn(ui, *args, **opts)
         else:
             try:
                 util.checksignature(self.fn)(ui, *args, **opts)
             except error.SignatureError:
                 args = ' '.join([self.cmdname] + self.args)
                 ui.debug("alias '%s' expands to '%s'\n" % (self.name, args))
                 raise
 
 def addaliases(ui, cmdtable):
     # aliases are processed after extensions have been loaded, so they
     # may use extension commands. Aliases can also use other alias definitions,
     # but only if they have been defined prior to the current definition.
     for alias, definition in ui.configitems('alias'):
         aliasdef = cmdalias(alias, definition, cmdtable)
 
         try:
             olddef = cmdtable[aliasdef.cmd][0]
             if olddef.definition == aliasdef.definition:
                 continue
         except (KeyError, AttributeError):
             # definition might not exist or it might not be a cmdalias
             pass
 
         cmdtable[aliasdef.name] = (aliasdef, aliasdef.opts, aliasdef.help)
         if aliasdef.norepo:
             commands.norepo += ' %s' % alias
         if aliasdef.optionalrepo:
             commands.optionalrepo += ' %s' % alias
 
 def _parse(ui, args):
     options = {}
     cmdoptions = {}
 
     try:
         args = fancyopts.fancyopts(args, commands.globalopts, options)
     except fancyopts.getopt.GetoptError, inst:
         raise error.CommandError(None, inst)
 
     if args:
         cmd, args = args[0], args[1:]
         aliases, entry = cmdutil.findcmd(cmd, commands.table,
                                          ui.configbool("ui", "strict"))
         cmd = aliases[0]
         args = aliasargs(entry[0], args)
         defaults = ui.config("defaults", cmd)
         if defaults:
             args = map(util.expandpath, shlex.split(defaults)) + args
         c = list(entry[1])
     else:
         cmd = None
         c = []
 
     # combine global options into local
     for o in commands.globalopts:
         c.append((o[0], o[1], options[o[1]], o[3]))
 
     try:
         args = fancyopts.fancyopts(args, c, cmdoptions, True)
     except fancyopts.getopt.GetoptError, inst:
         raise error.CommandError(cmd, inst)
 
     # separate global options back out
     for o in commands.globalopts:
         n = o[1]
         options[n] = cmdoptions[n]
         del cmdoptions[n]
 
     return (cmd, cmd and entry[0] or None, args, options, cmdoptions)
 
 def _parseconfig(ui, config):
     """parse the --config options from the command line"""
     configs = []
 
     for cfg in config:
         try:
             name, value = cfg.split('=', 1)
             section, name = name.split('.', 1)
             if not section or not name:
                 raise IndexError
             ui.setconfig(section, name, value)
             configs.append((section, name, value))
         except (IndexError, ValueError):
             raise util.Abort(_('malformed --config option: %r '
                                '(use --config section.name=value)') % cfg)
 
     return configs
 
 def _earlygetopt(aliases, args):
     """Return list of values for an option (or aliases).
 
     The values are listed in the order they appear in args.
     The options and values are removed from args.
     """
     try:
         argcount = args.index("--")
     except ValueError:
         argcount = len(args)
     shortopts = [opt for opt in aliases if len(opt) == 2]
     values = []
     pos = 0
     while pos < argcount:
         if args[pos] in aliases:
             if pos + 1 >= argcount:
                 # ignore and let getopt report an error if there is no value
                 break
             del args[pos]
             values.append(args.pop(pos))
             argcount -= 2
         elif args[pos][:2] in shortopts:
             # short option can have no following space, e.g. hg log -Rfoo
             values.append(args.pop(pos)[2:])
             argcount -= 1
         else:
             pos += 1
     return values
 
 def runcommand(lui, repo, cmd, fullargs, ui, options, d, cmdpats, cmdoptions):
     # run pre-hook, and abort if it fails
     ret = hook.hook(lui, repo, "pre-%s" % cmd, False, args=" ".join(fullargs),
                     pats=cmdpats, opts=cmdoptions)
     if ret:
         return ret
     ret = _runcommand(ui, options, cmd, d)
     # run post-hook, passing command result
     hook.hook(lui, repo, "post-%s" % cmd, False, args=" ".join(fullargs),
               result=ret, pats=cmdpats, opts=cmdoptions)
     return ret
 
 def _getlocal(ui, rpath):
     """Return (path, local ui object) for the given target path.
 
     Takes paths in [cwd]/.hg/hgrc into account."
     """
     try:
         wd = os.getcwd()
     except OSError, e:
         raise util.Abort(_("error getting current working directory: %s") %
                          e.strerror)
     path = cmdutil.findrepo(wd) or ""
     if not path:
         lui = ui
     else:
         lui = ui.copy()
         lui.readconfig(os.path.join(path, ".hg", "hgrc"), path)
 
     if rpath and rpath[-1]:
         path = lui.expandpath(rpath[-1])
         lui = ui.copy()
         lui.readconfig(os.path.join(path, ".hg", "hgrc"), path)
 
     return path, lui
 
 def _checkshellalias(lui, ui, args):
     options = {}
 
     try:
         args = fancyopts.fancyopts(args, commands.globalopts, options)
     except fancyopts.getopt.GetoptError:
         return
 
     if not args:
         return
 
     norepo = commands.norepo
     optionalrepo = commands.optionalrepo
     def restorecommands():
         commands.norepo = norepo
         commands.optionalrepo = optionalrepo
 
     cmdtable = commands.table.copy()
     addaliases(lui, cmdtable)
 
     cmd = args[0]
     try:
         aliases, entry = cmdutil.findcmd(cmd, cmdtable,
                                          lui.configbool("ui", "strict"))
     except (error.AmbiguousCommand, error.UnknownCommand):
         restorecommands()
         return
 
     cmd = aliases[0]
     fn = entry[0]
 
     if cmd and util.safehasattr(fn, 'shell'):
         d = lambda: fn(ui, *args[1:])
         return lambda: runcommand(lui, None, cmd, args[:1], ui, options, d,
                                   [], {})
 
     restorecommands()
 
 _loaded = set()
 def _dispatch(req):
     args = req.args
     ui = req.ui
 
     # read --config before doing anything else
     # (e.g. to change trust settings for reading .hg/hgrc)
     cfgs = _parseconfig(ui, _earlygetopt(['--config'], args))
 
     # check for cwd
     cwd = _earlygetopt(['--cwd'], args)
     if cwd:
         os.chdir(cwd[-1])
 
     rpath = _earlygetopt(["-R", "--repository", "--repo"], args)
     path, lui = _getlocal(ui, rpath)
 
     # Now that we're operating in the right directory/repository with
     # the right config settings, check for shell aliases
     shellaliasfn = _checkshellalias(lui, ui, args)
     if shellaliasfn:
         return shellaliasfn()
 
     # Configure extensions in phases: uisetup, extsetup, cmdtable, and
     # reposetup. Programs like TortoiseHg will call _dispatch several
     # times so we keep track of configured extensions in _loaded.
     extensions.loadall(lui)
     exts = [ext for ext in extensions.extensions() if ext[0] not in _loaded]
     # Propagate any changes to lui.__class__ by extensions
     ui.__class__ = lui.__class__
 
     # (uisetup and extsetup are handled in extensions.loadall)
 
     for name, module in exts:
         cmdtable = getattr(module, 'cmdtable', {})
         overrides = [cmd for cmd in cmdtable if cmd in commands.table]
         if overrides:
             ui.warn(_("extension '%s' overrides commands: %s\n")
                     % (name, " ".join(overrides)))
         commands.table.update(cmdtable)
         _loaded.add(name)
 
     # (reposetup is handled in hg.repository)
 
     addaliases(lui, commands.table)
 
     # check for fallback encoding
     fallback = lui.config('ui', 'fallbackencoding')
     if fallback:
         encoding.fallbackencoding = fallback
 
     fullargs = args
     cmd, func, args, options, cmdoptions = _parse(lui, args)
 
     if options["config"]:
         raise util.Abort(_("option --config may not be abbreviated!"))
     if options["cwd"]:
         raise util.Abort(_("option --cwd may not be abbreviated!"))
     if options["repository"]:
         raise util.Abort(_(
             "option -R has to be separated from other options (e.g. not -qR) "
             "and --repository may only be abbreviated as --repo!"))
 
     if options["encoding"]:
         encoding.encoding = options["encoding"]
     if options["encodingmode"]:
         encoding.encodingmode = options["encodingmode"]
     if options["time"]:
         def get_times():
             t = os.times()
             if t[4] == 0.0: # Windows leaves this as zero, so use time.clock()
                 t = (t[0], t[1], t[2], t[3], time.clock())
             return t
         s = get_times()
         def print_time():
             t = get_times()
             ui.warn(_("Time: real %.3f secs (user %.3f+%.3f sys %.3f+%.3f)\n") %
                 (t[4]-s[4], t[0]-s[0], t[2]-s[2], t[1]-s[1], t[3]-s[3]))
         atexit.register(print_time)
 
     uis = set([ui, lui])
 
     if req.repo:
         uis.add(req.repo.ui)
 
         # copy configs that were passed on the cmdline (--config) to the repo ui
         for cfg in cfgs:
             req.repo.ui.setconfig(*cfg)
 
     if options['verbose'] or options['debug'] or options['quiet']:
         for opt in ('verbose', 'debug', 'quiet'):
             val = str(bool(options[opt]))
             for ui_ in uis:
                 ui_.setconfig('ui', opt, val)
 
     if options['traceback']:
         for ui_ in uis:
             ui_.setconfig('ui', 'traceback', 'on')
 
     if options['noninteractive']:
         for ui_ in uis:
             ui_.setconfig('ui', 'interactive', 'off')
 
     if cmdoptions.get('insecure', False):
         for ui_ in uis:
             ui_.setconfig('web', 'cacerts', '')
 
     if options['version']:
         return commands.version_(ui)
     if options['help']:
         return commands.help_(ui, cmd)
     elif not cmd:
         return commands.help_(ui, 'shortlist')
 
     repo = None
     cmdpats = args[:]
     if cmd not in commands.norepo.split():
         # use the repo from the request only if we don't have -R
         if not rpath and not cwd:
             repo = req.repo
 
         if repo:
             # set the descriptors of the repo ui to those of ui
             repo.ui.fin = ui.fin
             repo.ui.fout = ui.fout
             repo.ui.ferr = ui.ferr
         else:
             try:
                 repo = hg.repository(ui, path=path)
                 if not repo.local():
                     raise util.Abort(_("repository '%s' is not local") % path)
                 repo.ui.setconfig("bundle", "mainreporoot", repo.root)
             except error.RequirementError:
                 raise
             except error.RepoError:
                 if cmd not in commands.optionalrepo.split():
                     if args and not path: # try to infer -R from command args
                         repos = map(cmdutil.findrepo, args)
                         guess = repos[0]
                         if guess and repos.count(guess) == len(repos):
                             req.args = ['--repository', guess] + fullargs
                             return _dispatch(req)
                     if not path:
                         raise error.RepoError(_("no repository found in '%s'"
                                                 " (.hg not found)")
                                               % os.getcwd())
                     raise
         if repo:
             ui = repo.ui
         args.insert(0, repo)
     elif rpath:
         ui.warn(_("warning: --repository ignored\n"))
 
     msg = ' '.join(' ' in a and repr(a) or a for a in fullargs)
     ui.log("command", msg + "\n")
     d = lambda: util.checksignature(func)(ui, *args, **cmdoptions)
     try:
         return runcommand(lui, repo, cmd, fullargs, ui, options, d,
                           cmdpats, cmdoptions)
     finally:
         if repo and repo != req.repo:
             repo.close()
 
 def lsprofile(ui, func, fp):
     format = ui.config('profiling', 'format', default='text')
     field = ui.config('profiling', 'sort', default='inlinetime')
     climit = ui.configint('profiling', 'nested', default=5)
 
-    if not format in ['text', 'kcachegrind']:
+    if format not in ['text', 'kcachegrind']:
         ui.warn(_("unrecognized profiling format '%s'"
                     " - Ignored\n") % format)
         format = 'text'
 
     try:
         from mercurial import lsprof
     except ImportError:
         raise util.Abort(_(
             'lsprof not available - install from '
             'http://codespeak.net/svn/user/arigo/hack/misc/lsprof/'))
     p = lsprof.Profiler()
     p.enable(subcalls=True)
     try:
         return func()
     finally:
         p.disable()
 
         if format == 'kcachegrind':
             import lsprofcalltree
             calltree = lsprofcalltree.KCacheGrind(p)
             calltree.output(fp)
         else:
             # format == 'text'
             stats = lsprof.Stats(p.getstats())
             stats.sort(field)
             stats.pprint(limit=30, file=fp, climit=climit)
 
 def statprofile(ui, func, fp):
     try:
         import statprof
     except ImportError:
         raise util.Abort(_(
             'statprof not available - install using "easy_install statprof"'))
 
     freq = ui.configint('profiling', 'freq', default=1000)
     if freq > 0:
         statprof.reset(freq)
     else:
         ui.warn(_("invalid sampling frequency '%s' - ignoring\n") % freq)
 
     statprof.start()
     try:
         return func()
     finally:
         statprof.stop()
         statprof.display(fp)
 
 def _runcommand(ui, options, cmd, cmdfunc):
     def checkargs():
         try:
             return cmdfunc()
         except error.SignatureError:
             raise error.CommandError(cmd, _("invalid arguments"))
 
     if options['profile']:
         profiler = os.getenv('HGPROF')
         if profiler is None:
             profiler = ui.config('profiling', 'type', default='ls')
         if profiler not in ('ls', 'stat'):
             ui.warn(_("unrecognized profiler '%s' - ignored\n") % profiler)
             profiler = 'ls'
 
         output = ui.config('profiling', 'output')
 
         if output:
             path = ui.expandpath(output)
             fp = open(path, 'wb')
         else:
             fp = sys.stderr
 
         try:
             if profiler == 'ls':
                 return lsprofile(ui, checkargs, fp)
             else:
                 return statprofile(ui, checkargs, fp)
         finally:
             if output:
                 fp.close()
     else:
         return checkargs()

mercurial/keepalive.py

@@ -1,764 +1,764 b''
 #   This library is free software; you can redistribute it and/or
 #   modify it under the terms of the GNU Lesser General Public
 #   License as published by the Free Software Foundation; either
 #   version 2.1 of the License, or (at your option) any later version.
 #
 #   This library is distributed in the hope that it will be useful,
 #   but WITHOUT ANY WARRANTY; without even the implied warranty of
 #   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
 #   Lesser General Public License for more details.
 #
 #   You should have received a copy of the GNU Lesser General Public
 #   License along with this library; if not, see
 #   <http://www.gnu.org/licenses/>.
 
 # This file is part of urlgrabber, a high-level cross-protocol url-grabber
 # Copyright 2002-2004 Michael D. Stenner, Ryan Tomayko
 
 # Modified by Benoit Boissinot:
 #  - fix for digest auth (inspired from urllib2.py @ Python v2.4)
 # Modified by Dirkjan Ochtman:
 #  - import md5 function from a local util module
 # Modified by Martin Geisler:
 #  - moved md5 function from local util module to this module
 # Modified by Augie Fackler:
 #  - add safesend method and use it to prevent broken pipe errors
 #    on large POST requests
 
 """An HTTP handler for urllib2 that supports HTTP 1.1 and keepalive.
 
 >>> import urllib2
 >>> from keepalive import HTTPHandler
 >>> keepalive_handler = HTTPHandler()
 >>> opener = urllib2.build_opener(keepalive_handler)
 >>> urllib2.install_opener(opener)
 >>>
 >>> fo = urllib2.urlopen('http://www.python.org')
 
 If a connection to a given host is requested, and all of the existing
 connections are still in use, another connection will be opened.  If
 the handler tries to use an existing connection but it fails in some
 way, it will be closed and removed from the pool.
 
 To remove the handler, simply re-run build_opener with no arguments, and
 install that opener.
 
 You can explicitly close connections by using the close_connection()
 method of the returned file-like object (described below) or you can
 use the handler methods:
 
   close_connection(host)
   close_all()
   open_connections()
 
 NOTE: using the close_connection and close_all methods of the handler
 should be done with care when using multiple threads.
   * there is nothing that prevents another thread from creating new
     connections immediately after connections are closed
   * no checks are done to prevent in-use connections from being closed
 
 >>> keepalive_handler.close_all()
 
 EXTRA ATTRIBUTES AND METHODS
 
   Upon a status of 200, the object returned has a few additional
   attributes and methods, which should not be used if you want to
   remain consistent with the normal urllib2-returned objects:
 
     close_connection()  -  close the connection to the host
     readlines()         -  you know, readlines()
     status              -  the return status (ie 404)
     reason              -  english translation of status (ie 'File not found')
 
   If you want the best of both worlds, use this inside an
   AttributeError-catching try:
 
   >>> try: status = fo.status
   >>> except AttributeError: status = None
 
   Unfortunately, these are ONLY there if status == 200, so it's not
   easy to distinguish between non-200 responses.  The reason is that
   urllib2 tries to do clever things with error codes 301, 302, 401,
   and 407, and it wraps the object upon return.
 
   For python versions earlier than 2.4, you can avoid this fancy error
   handling by setting the module-level global HANDLE_ERRORS to zero.
   You see, prior to 2.4, it's the HTTP Handler's job to determine what
   to handle specially, and what to just pass up.  HANDLE_ERRORS == 0
   means "pass everything up".  In python 2.4, however, this job no
   longer belongs to the HTTP Handler and is now done by a NEW handler,
   HTTPErrorProcessor.  Here's the bottom line:
 
     python version < 2.4
         HANDLE_ERRORS == 1  (default) pass up 200, treat the rest as
                             errors
         HANDLE_ERRORS == 0  pass everything up, error processing is
                             left to the calling code
     python version >= 2.4
         HANDLE_ERRORS == 1  pass up 200, treat the rest as errors
         HANDLE_ERRORS == 0  (default) pass everything up, let the
                             other handlers (specifically,
                             HTTPErrorProcessor) decide what to do
 
   In practice, setting the variable either way makes little difference
   in python 2.4, so for the most consistent behavior across versions,
   you probably just want to use the defaults, which will give you
   exceptions on errors.
 
 """
 
 # $Id: keepalive.py,v 1.14 2006/04/04 21:00:32 mstenner Exp $
 
 import errno
 import httplib
 import socket
 import thread
 import urllib2
 
 DEBUG = None
 
 import sys
 if sys.version_info < (2, 4):
     HANDLE_ERRORS = 1
 else: HANDLE_ERRORS = 0
 
 class ConnectionManager(object):
     """
     The connection manager must be able to:
       * keep track of all existing
       """
     def __init__(self):
         self._lock = thread.allocate_lock()
         self._hostmap = {} # map hosts to a list of connections
         self._connmap = {} # map connections to host
         self._readymap = {} # map connection to ready state
 
     def add(self, host, connection, ready):
         self._lock.acquire()
         try:
-            if not host in self._hostmap:
+            if host not in self._hostmap:
                 self._hostmap[host] = []
             self._hostmap[host].append(connection)
             self._connmap[connection] = host
             self._readymap[connection] = ready
         finally:
             self._lock.release()
 
     def remove(self, connection):
         self._lock.acquire()
         try:
             try:
                 host = self._connmap[connection]
             except KeyError:
                 pass
             else:
                 del self._connmap[connection]
                 del self._readymap[connection]
                 self._hostmap[host].remove(connection)
                 if not self._hostmap[host]: del self._hostmap[host]
         finally:
             self._lock.release()
 
     def set_ready(self, connection, ready):
         try:
             self._readymap[connection] = ready
         except KeyError:
             pass
 
     def get_ready_conn(self, host):
         conn = None
         self._lock.acquire()
         try:
             if host in self._hostmap:
                 for c in self._hostmap[host]:
                     if self._readymap[c]:
                         self._readymap[c] = 0
                         conn = c
                         break
         finally:
             self._lock.release()
         return conn
 
     def get_all(self, host=None):
         if host:
             return list(self._hostmap.get(host, []))
         else:
             return dict(self._hostmap)
 
 class KeepAliveHandler(object):
     def __init__(self):
         self._cm = ConnectionManager()
 
     #### Connection Management
     def open_connections(self):
         """return a list of connected hosts and the number of connections
         to each.  [('foo.com:80', 2), ('bar.org', 1)]"""
         return [(host, len(li)) for (host, li) in self._cm.get_all().items()]
 
     def close_connection(self, host):
         """close connection(s) to <host>
         host is the host:port spec, as in 'www.cnn.com:8080' as passed in.
         no error occurs if there is no connection to that host."""
         for h in self._cm.get_all(host):
             self._cm.remove(h)
             h.close()
 
     def close_all(self):
         """close all open connections"""
         for host, conns in self._cm.get_all().iteritems():
             for h in conns:
                 self._cm.remove(h)
                 h.close()
 
     def _request_closed(self, request, host, connection):
         """tells us that this request is now closed and the the
         connection is ready for another request"""
         self._cm.set_ready(connection, 1)
 
     def _remove_connection(self, host, connection, close=0):
         if close:
             connection.close()
         self._cm.remove(connection)
 
     #### Transaction Execution
     def http_open(self, req):
         return self.do_open(HTTPConnection, req)
 
     def do_open(self, http_class, req):
         host = req.get_host()
         if not host:
             raise urllib2.URLError('no host given')
 
         try:
             h = self._cm.get_ready_conn(host)
             while h:
                 r = self._reuse_connection(h, req, host)
 
                 # if this response is non-None, then it worked and we're
                 # done.  Break out, skipping the else block.
                 if r:
                     break
 
                 # connection is bad - possibly closed by server
                 # discard it and ask for the next free connection
                 h.close()
                 self._cm.remove(h)
                 h = self._cm.get_ready_conn(host)
             else:
                 # no (working) free connections were found.  Create a new one.
                 h = http_class(host)
                 if DEBUG:
                     DEBUG.info("creating new connection to %s (%d)",
                                host, id(h))
                 self._cm.add(host, h, 0)
                 self._start_transaction(h, req)
                 r = h.getresponse()
         except (socket.error, httplib.HTTPException), err:
             raise urllib2.URLError(err)
 
         # if not a persistent connection, don't try to reuse it
         if r.will_close:
             self._cm.remove(h)
 
         if DEBUG:
             DEBUG.info("STATUS: %s, %s", r.status, r.reason)
         r._handler = self
         r._host = host
         r._url = req.get_full_url()
         r._connection = h
         r.code = r.status
         r.headers = r.msg
         r.msg = r.reason
 
         if r.status == 200 or not HANDLE_ERRORS:
             return r
         else:
             return self.parent.error('http', req, r,
                                      r.status, r.msg, r.headers)
 
     def _reuse_connection(self, h, req, host):
         """start the transaction with a re-used connection
         return a response object (r) upon success or None on failure.
         This DOES not close or remove bad connections in cases where
         it returns.  However, if an unexpected exception occurs, it
         will close and remove the connection before re-raising.
         """
         try:
             self._start_transaction(h, req)
             r = h.getresponse()
             # note: just because we got something back doesn't mean it
             # worked.  We'll check the version below, too.
         except (socket.error, httplib.HTTPException):
             r = None
         except:
             # adding this block just in case we've missed
             # something we will still raise the exception, but
             # lets try and close the connection and remove it
             # first.  We previously got into a nasty loop
             # where an exception was uncaught, and so the
             # connection stayed open.  On the next try, the
             # same exception was raised, etc.  The tradeoff is
             # that it's now possible this call will raise
             # a DIFFERENT exception
             if DEBUG:
                 DEBUG.error("unexpected exception - closing "
                             "connection to %s (%d)", host, id(h))
             self._cm.remove(h)
             h.close()
             raise
 
         if r is None or r.version == 9:
             # httplib falls back to assuming HTTP 0.9 if it gets a
             # bad header back.  This is most likely to happen if
             # the socket has been closed by the server since we
             # last used the connection.
             if DEBUG:
                 DEBUG.info("failed to re-use connection to %s (%d)",
                            host, id(h))
             r = None
         else:
             if DEBUG:
                 DEBUG.info("re-using connection to %s (%d)", host, id(h))
 
         return r
 
     def _start_transaction(self, h, req):
         # What follows mostly reimplements HTTPConnection.request()
         # except it adds self.parent.addheaders in the mix.
         headers = req.headers.copy()
         if sys.version_info >= (2, 4):
             headers.update(req.unredirected_hdrs)
         headers.update(self.parent.addheaders)
         headers = dict((n.lower(), v) for n, v in headers.items())
         skipheaders = {}
         for n in ('host', 'accept-encoding'):
             if n in headers:
                 skipheaders['skip_' + n.replace('-', '_')] = 1
         try:
             if req.has_data():
                 data = req.get_data()
                 h.putrequest('POST', req.get_selector(), **skipheaders)
                 if 'content-type' not in headers:
                     h.putheader('Content-type',
                                 'application/x-www-form-urlencoded')
                 if 'content-length' not in headers:
                     h.putheader('Content-length', '%d' % len(data))
             else:
                 h.putrequest('GET', req.get_selector(), **skipheaders)
         except (socket.error), err:
             raise urllib2.URLError(err)
         for k, v in headers.items():
             h.putheader(k, v)
         h.endheaders()
         if req.has_data():
             h.send(data)
 
 class HTTPHandler(KeepAliveHandler, urllib2.HTTPHandler):
     pass
 
 class HTTPResponse(httplib.HTTPResponse):
     # we need to subclass HTTPResponse in order to
     # 1) add readline() and readlines() methods
     # 2) add close_connection() methods
     # 3) add info() and geturl() methods
 
     # in order to add readline(), read must be modified to deal with a
     # buffer.  example: readline must read a buffer and then spit back
     # one line at a time.  The only real alternative is to read one
     # BYTE at a time (ick).  Once something has been read, it can't be
     # put back (ok, maybe it can, but that's even uglier than this),
     # so if you THEN do a normal read, you must first take stuff from
     # the buffer.
 
     # the read method wraps the original to accomodate buffering,
     # although read() never adds to the buffer.
     # Both readline and readlines have been stolen with almost no
     # modification from socket.py
 
 
     def __init__(self, sock, debuglevel=0, strict=0, method=None):
         if method: # the httplib in python 2.3 uses the method arg
             httplib.HTTPResponse.__init__(self, sock, debuglevel, method)
         else: # 2.2 doesn't
             httplib.HTTPResponse.__init__(self, sock, debuglevel)
         self.fileno = sock.fileno
         self.code = None
         self._rbuf = ''
         self._rbufsize = 8096
         self._handler = None # inserted by the handler later
         self._host = None    # (same)
         self._url = None     # (same)
         self._connection = None # (same)
 
     _raw_read = httplib.HTTPResponse.read
 
     def close(self):
         if self.fp:
             self.fp.close()
             self.fp = None
             if self._handler:
                 self._handler._request_closed(self, self._host,
                                               self._connection)
 
     def close_connection(self):
         self._handler._remove_connection(self._host, self._connection, close=1)
         self.close()
 
     def info(self):
         return self.headers
 
     def geturl(self):
         return self._url
 
     def read(self, amt=None):
         # the _rbuf test is only in this first if for speed.  It's not
         # logically necessary
         if self._rbuf and not amt is None:
             L = len(self._rbuf)
             if amt > L:
                 amt -= L
             else:
                 s = self._rbuf[:amt]
                 self._rbuf = self._rbuf[amt:]
                 return s
 
         s = self._rbuf + self._raw_read(amt)
         self._rbuf = ''
         return s
 
     # stolen from Python SVN #68532 to fix issue1088
     def _read_chunked(self, amt):
         chunk_left = self.chunk_left
         value = ''
 
         # XXX This accumulates chunks by repeated string concatenation,
         # which is not efficient as the number or size of chunks gets big.
         while True:
             if chunk_left is None:
                 line = self.fp.readline()
                 i = line.find(';')
                 if i >= 0:
                     line = line[:i] # strip chunk-extensions
                 try:
                     chunk_left = int(line, 16)
                 except ValueError:
                     # close the connection as protocol synchronisation is
                     # probably lost
                     self.close()
                     raise httplib.IncompleteRead(value)
                 if chunk_left == 0:
                     break
             if amt is None:
                 value += self._safe_read(chunk_left)
             elif amt < chunk_left:
                 value += self._safe_read(amt)
                 self.chunk_left = chunk_left - amt
                 return value
             elif amt == chunk_left:
                 value += self._safe_read(amt)
                 self._safe_read(2)  # toss the CRLF at the end of the chunk
                 self.chunk_left = None
                 return value
             else:
                 value += self._safe_read(chunk_left)
                 amt -= chunk_left
 
             # we read the whole chunk, get another
             self._safe_read(2)      # toss the CRLF at the end of the chunk
             chunk_left = None
 
         # read and discard trailer up to the CRLF terminator
         ### note: we shouldn't have any trailers!
         while True:
             line = self.fp.readline()
             if not line:
                 # a vanishingly small number of sites EOF without
                 # sending the trailer
                 break
             if line == '\r\n':
                 break
 
         # we read everything; close the "file"
         self.close()
 
         return value
 
     def readline(self, limit=-1):
         i = self._rbuf.find('\n')
         while i < 0 and not (0 < limit <= len(self._rbuf)):
             new = self._raw_read(self._rbufsize)
             if not new:
                 break
             i = new.find('\n')
             if i >= 0:
                 i = i + len(self._rbuf)
             self._rbuf = self._rbuf + new
         if i < 0:
             i = len(self._rbuf)
         else:
             i = i + 1
         if 0 <= limit < len(self._rbuf):
             i = limit
         data, self._rbuf = self._rbuf[:i], self._rbuf[i:]
         return data
 
     def readlines(self, sizehint = 0):
         total = 0
         list = []
         while True:
             line = self.readline()
             if not line:
                 break
             list.append(line)
             total += len(line)
             if sizehint and total >= sizehint:
                 break
         return list
 
 def safesend(self, str):
     """Send `str' to the server.
 
     Shamelessly ripped off from httplib to patch a bad behavior.
     """
     # _broken_pipe_resp is an attribute we set in this function
     # if the socket is closed while we're sending data but
     # the server sent us a response before hanging up.
     # In that case, we want to pretend to send the rest of the
     # outgoing data, and then let the user use getresponse()
     # (which we wrap) to get this last response before
     # opening a new socket.
     if getattr(self, '_broken_pipe_resp', None) is not None:
         return
 
     if self.sock is None:
         if self.auto_open:
             self.connect()
         else:
             raise httplib.NotConnected()
 
     # send the data to the server. if we get a broken pipe, then close
     # the socket. we want to reconnect when somebody tries to send again.
     #
     # NOTE: we DO propagate the error, though, because we cannot simply
     #       ignore the error... the caller will know if they can retry.
     if self.debuglevel > 0:
         print "send:", repr(str)
     try:
         blocksize = 8192
         read = getattr(str, 'read', None)
         if read is not None:
             if self.debuglevel > 0:
                 print "sendIng a read()able"
             data = read(blocksize)
             while data:
                 self.sock.sendall(data)
                 data = read(blocksize)
         else:
             self.sock.sendall(str)
     except socket.error, v:
         reraise = True
         if v[0] == errno.EPIPE:      # Broken pipe
             if self._HTTPConnection__state == httplib._CS_REQ_SENT:
                 self._broken_pipe_resp = None
                 self._broken_pipe_resp = self.getresponse()
                 reraise = False
             self.close()
         if reraise:
             raise
 
 def wrapgetresponse(cls):
     """Wraps getresponse in cls with a broken-pipe sane version.
     """
     def safegetresponse(self):
         # In safesend() we might set the _broken_pipe_resp
         # attribute, in which case the socket has already
         # been closed and we just need to give them the response
         # back. Otherwise, we use the normal response path.
         r = getattr(self, '_broken_pipe_resp', None)
         if r is not None:
             return r
         return cls.getresponse(self)
     safegetresponse.__doc__ = cls.getresponse.__doc__
     return safegetresponse
 
 class HTTPConnection(httplib.HTTPConnection):
     # use the modified response class
     response_class = HTTPResponse
     send = safesend
     getresponse = wrapgetresponse(httplib.HTTPConnection)
 
 
 #########################################################################
 #####   TEST FUNCTIONS
 #########################################################################
 
 def error_handler(url):
     global HANDLE_ERRORS
     orig = HANDLE_ERRORS
     keepalive_handler = HTTPHandler()
     opener = urllib2.build_opener(keepalive_handler)
     urllib2.install_opener(opener)
     pos = {0: 'off', 1: 'on'}
     for i in (0, 1):
         print "  fancy error handling %s (HANDLE_ERRORS = %i)" % (pos[i], i)
         HANDLE_ERRORS = i
         try:
             fo = urllib2.urlopen(url)
             fo.read()
             fo.close()
             try:
                 status, reason = fo.status, fo.reason
             except AttributeError:
                 status, reason = None, None
         except IOError, e:
             print "  EXCEPTION: %s" % e
             raise
         else:
             print "  status = %s, reason = %s" % (status, reason)
     HANDLE_ERRORS = orig
     hosts = keepalive_handler.open_connections()
     print "open connections:", hosts
     keepalive_handler.close_all()
 
 def md5(s):
     try:
         from hashlib import md5 as _md5
     except ImportError:
         from md5 import md5 as _md5
     global md5
     md5 = _md5
     return _md5(s)
 
 def continuity(url):
     format = '%25s: %s'
 
     # first fetch the file with the normal http handler
     opener = urllib2.build_opener()
     urllib2.install_opener(opener)
     fo = urllib2.urlopen(url)
     foo = fo.read()
     fo.close()
     m = md5.new(foo)
     print format % ('normal urllib', m.hexdigest())
 
     # now install the keepalive handler and try again
     opener = urllib2.build_opener(HTTPHandler())
     urllib2.install_opener(opener)
 
     fo = urllib2.urlopen(url)
     foo = fo.read()
     fo.close()
     m = md5.new(foo)
     print format % ('keepalive read', m.hexdigest())
 
     fo = urllib2.urlopen(url)
     foo = ''
     while True:
         f = fo.readline()
         if f:
             foo = foo + f
         else: break
     fo.close()
     m = md5.new(foo)
     print format % ('keepalive readline', m.hexdigest())
 
 def comp(N, url):
     print '  making %i connections to:\n  %s' % (N, url)
 
     sys.stdout.write('  first using the normal urllib handlers')
     # first use normal opener
     opener = urllib2.build_opener()
     urllib2.install_opener(opener)
     t1 = fetch(N, url)
     print '  TIME: %.3f s' % t1
 
     sys.stdout.write('  now using the keepalive handler       ')
     # now install the keepalive handler and try again
     opener = urllib2.build_opener(HTTPHandler())
     urllib2.install_opener(opener)
     t2 = fetch(N, url)
     print '  TIME: %.3f s' % t2
     print '  improvement factor: %.2f' % (t1 / t2)
 
 def fetch(N, url, delay=0):
     import time
     lens = []
     starttime = time.time()
     for i in range(N):
         if delay and i > 0:
             time.sleep(delay)
         fo = urllib2.urlopen(url)
         foo = fo.read()
         fo.close()
         lens.append(len(foo))
     diff = time.time() - starttime
 
     j = 0
     for i in lens[1:]:
         j = j + 1
         if not i == lens[0]:
             print "WARNING: inconsistent length on read %i: %i" % (j, i)
 
     return diff
 
 def test_timeout(url):
     global DEBUG
     dbbackup = DEBUG
     class FakeLogger(object):
         def debug(self, msg, *args):
             print msg % args
         info = warning = error = debug
     DEBUG = FakeLogger()
     print "  fetching the file to establish a connection"
     fo = urllib2.urlopen(url)
     data1 = fo.read()
     fo.close()
 
     i = 20
     print "  waiting %i seconds for the server to close the connection" % i
     while i > 0:
         sys.stdout.write('\r  %2i' % i)
         sys.stdout.flush()
         time.sleep(1)
         i -= 1
     sys.stderr.write('\r')
 
     print "  fetching the file a second time"
     fo = urllib2.urlopen(url)
     data2 = fo.read()
     fo.close()
 
     if data1 == data2:
         print '  data are identical'
     else:
         print '  ERROR: DATA DIFFER'
 
     DEBUG = dbbackup
 
 
 def test(url, N=10):
     print "checking error hander (do this on a non-200)"
     try: error_handler(url)
     except IOError:
         print "exiting - exception will prevent further tests"
         sys.exit()
     print
     print "performing continuity test (making sure stuff isn't corrupted)"
     continuity(url)
     print
     print "performing speed comparison"
     comp(N, url)
     print
     print "performing dropped-connection check"
     test_timeout(url)
 
 if __name__ == '__main__':
     import time
     import sys
     try:
         N = int(sys.argv[1])
         url = sys.argv[2]
     except:
         print "%s <integer> <url>" % sys.argv[0]
     else:
         test(url, N)

mercurial/patch.py

@@ -1,1890 +1,1890 b''
 # patch.py - patch file parsing routines
 #
 # Copyright 2006 Brendan Cully <[e-mail]>
 # Copyright 2007 Chris Mason <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 import cStringIO, email.Parser, os, errno, re
 import tempfile, zlib, shutil
 
 from i18n import _
 from node import hex, nullid, short
 import base85, mdiff, scmutil, util, diffhelpers, copies, encoding, error
 import context
 
 gitre = re.compile('diff --git a/(.*) b/(.*)')
 
 class PatchError(Exception):
     pass
 
 
 # public functions
 
 def split(stream):
     '''return an iterator of individual patches from a stream'''
     def isheader(line, inheader):
         if inheader and line[0] in (' ', '\t'):
             # continuation
             return True
         if line[0] in (' ', '-', '+'):
             # diff line - don't check for header pattern in there
             return False
         l = line.split(': ', 1)
         return len(l) == 2 and ' ' not in l[0]
 
     def chunk(lines):
         return cStringIO.StringIO(''.join(lines))
 
     def hgsplit(stream, cur):
         inheader = True
 
         for line in stream:
             if not line.strip():
                 inheader = False
             if not inheader and line.startswith('# HG changeset patch'):
                 yield chunk(cur)
                 cur = []
                 inheader = True
 
             cur.append(line)
 
         if cur:
             yield chunk(cur)
 
     def mboxsplit(stream, cur):
         for line in stream:
             if line.startswith('From '):
                 for c in split(chunk(cur[1:])):
                     yield c
                 cur = []
 
             cur.append(line)
 
         if cur:
             for c in split(chunk(cur[1:])):
                 yield c
 
     def mimesplit(stream, cur):
         def msgfp(m):
             fp = cStringIO.StringIO()
             g = email.Generator.Generator(fp, mangle_from_=False)
             g.flatten(m)
             fp.seek(0)
             return fp
 
         for line in stream:
             cur.append(line)
         c = chunk(cur)
 
         m = email.Parser.Parser().parse(c)
         if not m.is_multipart():
             yield msgfp(m)
         else:
             ok_types = ('text/plain', 'text/x-diff', 'text/x-patch')
             for part in m.walk():
                 ct = part.get_content_type()
                 if ct not in ok_types:
                     continue
                 yield msgfp(part)
 
     def headersplit(stream, cur):
         inheader = False
 
         for line in stream:
             if not inheader and isheader(line, inheader):
                 yield chunk(cur)
                 cur = []
                 inheader = True
             if inheader and not isheader(line, inheader):
                 inheader = False
 
             cur.append(line)
 
         if cur:
             yield chunk(cur)
 
     def remainder(cur):
         yield chunk(cur)
 
     class fiter(object):
         def __init__(self, fp):
             self.fp = fp
 
         def __iter__(self):
             return self
 
         def next(self):
             l = self.fp.readline()
             if not l:
                 raise StopIteration
             return l
 
     inheader = False
     cur = []
 
     mimeheaders = ['content-type']
 
     if not util.safehasattr(stream, 'next'):
         # http responses, for example, have readline but not next
         stream = fiter(stream)
 
     for line in stream:
         cur.append(line)
         if line.startswith('# HG changeset patch'):
             return hgsplit(stream, cur)
         elif line.startswith('From '):
             return mboxsplit(stream, cur)
         elif isheader(line, inheader):
             inheader = True
             if line.split(':', 1)[0].lower() in mimeheaders:
                 # let email parser handle this
                 return mimesplit(stream, cur)
         elif line.startswith('--- ') and inheader:
             # No evil headers seen by diff start, split by hand
             return headersplit(stream, cur)
         # Not enough info, keep reading
 
     # if we are here, we have a very plain patch
     return remainder(cur)
 
 def extract(ui, fileobj):
     '''extract patch from data read from fileobj.
 
     patch can be a normal patch or contained in an email message.
 
     return tuple (filename, message, user, date, branch, node, p1, p2).
     Any item in the returned tuple can be None. If filename is None,
     fileobj did not contain a patch. Caller must unlink filename when done.'''
 
     # attempt to detect the start of a patch
     # (this heuristic is borrowed from quilt)
     diffre = re.compile(r'^(?:Index:[ \t]|diff[ \t]|RCS file: |'
                         r'retrieving revision [0-9]+(\.[0-9]+)*$|'
                         r'---[ \t].*?^\+\+\+[ \t]|'
                         r'\*\*\*[ \t].*?^---[ \t])', re.MULTILINE|re.DOTALL)
 
     fd, tmpname = tempfile.mkstemp(prefix='hg-patch-')
     tmpfp = os.fdopen(fd, 'w')
     try:
         msg = email.Parser.Parser().parse(fileobj)
 
         subject = msg['Subject']
         user = msg['From']
         if not subject and not user:
             # Not an email, restore parsed headers if any
             subject = '\n'.join(': '.join(h) for h in msg.items()) + '\n'
 
         gitsendmail = 'git-send-email' in msg.get('X-Mailer', '')
         # should try to parse msg['Date']
         date = None
         nodeid = None
         branch = None
         parents = []
 
         if subject:
             if subject.startswith('[PATCH'):
                 pend = subject.find(']')
                 if pend >= 0:
                     subject = subject[pend + 1:].lstrip()
             subject = re.sub(r'\n[ \t]+', ' ', subject)
             ui.debug('Subject: %s\n' % subject)
         if user:
             ui.debug('From: %s\n' % user)
         diffs_seen = 0
         ok_types = ('text/plain', 'text/x-diff', 'text/x-patch')
         message = ''
         for part in msg.walk():
             content_type = part.get_content_type()
             ui.debug('Content-Type: %s\n' % content_type)
             if content_type not in ok_types:
                 continue
             payload = part.get_payload(decode=True)
             m = diffre.search(payload)
             if m:
                 hgpatch = False
                 hgpatchheader = False
                 ignoretext = False
 
                 ui.debug('found patch at byte %d\n' % m.start(0))
                 diffs_seen += 1
                 cfp = cStringIO.StringIO()
                 for line in payload[:m.start(0)].splitlines():
                     if line.startswith('# HG changeset patch') and not hgpatch:
                         ui.debug('patch generated by hg export\n')
                         hgpatch = True
                         hgpatchheader = True
                         # drop earlier commit message content
                         cfp.seek(0)
                         cfp.truncate()
                         subject = None
                     elif hgpatchheader:
                         if line.startswith('# User '):
                             user = line[7:]
                             ui.debug('From: %s\n' % user)
                         elif line.startswith("# Date "):
                             date = line[7:]
                         elif line.startswith("# Branch "):
                             branch = line[9:]
                         elif line.startswith("# Node ID "):
                             nodeid = line[10:]
                         elif line.startswith("# Parent "):
                             parents.append(line[9:].lstrip())
                         elif not line.startswith("# "):
                             hgpatchheader = False
                     elif line == '---' and gitsendmail:
                         ignoretext = True
                     if not hgpatchheader and not ignoretext:
                         cfp.write(line)
                         cfp.write('\n')
                 message = cfp.getvalue()
                 if tmpfp:
                     tmpfp.write(payload)
                     if not payload.endswith('\n'):
                         tmpfp.write('\n')
             elif not diffs_seen and message and content_type == 'text/plain':
                 message += '\n' + payload
     except:
         tmpfp.close()
         os.unlink(tmpname)
         raise
 
     if subject and not message.startswith(subject):
         message = '%s\n%s' % (subject, message)
     tmpfp.close()
     if not diffs_seen:
         os.unlink(tmpname)
         return None, message, user, date, branch, None, None, None
     p1 = parents and parents.pop(0) or None
     p2 = parents and parents.pop(0) or None
     return tmpname, message, user, date, branch, nodeid, p1, p2
 
 class patchmeta(object):
     """Patched file metadata
 
     'op' is the performed operation within ADD, DELETE, RENAME, MODIFY
     or COPY.  'path' is patched file path. 'oldpath' is set to the
     origin file when 'op' is either COPY or RENAME, None otherwise. If
     file mode is changed, 'mode' is a tuple (islink, isexec) where
     'islink' is True if the file is a symlink and 'isexec' is True if
     the file is executable. Otherwise, 'mode' is None.
     """
     def __init__(self, path):
         self.path = path
         self.oldpath = None
         self.mode = None
         self.op = 'MODIFY'
         self.binary = False
 
     def setmode(self, mode):
         islink = mode & 020000
         isexec = mode & 0100
         self.mode = (islink, isexec)
 
     def copy(self):
         other = patchmeta(self.path)
         other.oldpath = self.oldpath
         other.mode = self.mode
         other.op = self.op
         other.binary = self.binary
         return other
 
     def _ispatchinga(self, afile):
         if afile == '/dev/null':
             return self.op == 'ADD'
         return afile == 'a/' + (self.oldpath or self.path)
 
     def _ispatchingb(self, bfile):
         if bfile == '/dev/null':
             return self.op == 'DELETE'
         return bfile == 'b/' + self.path
 
     def ispatching(self, afile, bfile):
         return self._ispatchinga(afile) and self._ispatchingb(bfile)
 
     def __repr__(self):
         return "<patchmeta %s %r>" % (self.op, self.path)
 
 def readgitpatch(lr):
     """extract git-style metadata about patches from <patchname>"""
 
     # Filter patch for git information
     gp = None
     gitpatches = []
     for line in lr:
         line = line.rstrip(' \r\n')
         if line.startswith('diff --git'):
             m = gitre.match(line)
             if m:
                 if gp:
                     gitpatches.append(gp)
                 dst = m.group(2)
                 gp = patchmeta(dst)
         elif gp:
             if line.startswith('--- '):
                 gitpatches.append(gp)
                 gp = None
                 continue
             if line.startswith('rename from '):
                 gp.op = 'RENAME'
                 gp.oldpath = line[12:]
             elif line.startswith('rename to '):
                 gp.path = line[10:]
             elif line.startswith('copy from '):
                 gp.op = 'COPY'
                 gp.oldpath = line[10:]
             elif line.startswith('copy to '):
                 gp.path = line[8:]
             elif line.startswith('deleted file'):
                 gp.op = 'DELETE'
             elif line.startswith('new file mode '):
                 gp.op = 'ADD'
                 gp.setmode(int(line[-6:], 8))
             elif line.startswith('new mode '):
                 gp.setmode(int(line[-6:], 8))
             elif line.startswith('GIT binary patch'):
                 gp.binary = True
     if gp:
         gitpatches.append(gp)
 
     return gitpatches
 
 class linereader(object):
     # simple class to allow pushing lines back into the input stream
     def __init__(self, fp):
         self.fp = fp
         self.buf = []
 
     def push(self, line):
         if line is not None:
             self.buf.append(line)
 
     def readline(self):
         if self.buf:
             l = self.buf[0]
             del self.buf[0]
             return l
         return self.fp.readline()
 
     def __iter__(self):
         while True:
             l = self.readline()
             if not l:
                 break
             yield l
 
 class abstractbackend(object):
     def __init__(self, ui):
         self.ui = ui
 
     def getfile(self, fname):
         """Return target file data and flags as a (data, (islink,
         isexec)) tuple.
         """
         raise NotImplementedError
 
     def setfile(self, fname, data, mode, copysource):
         """Write data to target file fname and set its mode. mode is a
         (islink, isexec) tuple. If data is None, the file content should
         be left unchanged. If the file is modified after being copied,
         copysource is set to the original file name.
         """
         raise NotImplementedError
 
     def unlink(self, fname):
         """Unlink target file."""
         raise NotImplementedError
 
     def writerej(self, fname, failed, total, lines):
         """Write rejected lines for fname. total is the number of hunks
         which failed to apply and total the total number of hunks for this
         files.
         """
         pass
 
     def exists(self, fname):
         raise NotImplementedError
 
 class fsbackend(abstractbackend):
     def __init__(self, ui, basedir):
         super(fsbackend, self).__init__(ui)
         self.opener = scmutil.opener(basedir)
 
     def _join(self, f):
         return os.path.join(self.opener.base, f)
 
     def getfile(self, fname):
         path = self._join(fname)
         if os.path.islink(path):
             return (os.readlink(path), (True, False))
         isexec = False
         try:
             isexec = os.lstat(path).st_mode & 0100 != 0
         except OSError, e:
             if e.errno != errno.ENOENT:
                 raise
         return (self.opener.read(fname), (False, isexec))
 
     def setfile(self, fname, data, mode, copysource):
         islink, isexec = mode
         if data is None:
             util.setflags(self._join(fname), islink, isexec)
             return
         if islink:
             self.opener.symlink(data, fname)
         else:
             self.opener.write(fname, data)
             if isexec:
                 util.setflags(self._join(fname), False, True)
 
     def unlink(self, fname):
         try:
             util.unlinkpath(self._join(fname))
         except OSError, inst:
             if inst.errno != errno.ENOENT:
                 raise
 
     def writerej(self, fname, failed, total, lines):
         fname = fname + ".rej"
         self.ui.warn(
             _("%d out of %d hunks FAILED -- saving rejects to file %s\n") %
             (failed, total, fname))
         fp = self.opener(fname, 'w')
         fp.writelines(lines)
         fp.close()
 
     def exists(self, fname):
         return os.path.lexists(self._join(fname))
 
 class workingbackend(fsbackend):
     def __init__(self, ui, repo, similarity):
         super(workingbackend, self).__init__(ui, repo.root)
         self.repo = repo
         self.similarity = similarity
         self.removed = set()
         self.changed = set()
         self.copied = []
 
     def _checkknown(self, fname):
         if self.repo.dirstate[fname] == '?' and self.exists(fname):
             raise PatchError(_('cannot patch %s: file is not tracked') % fname)
 
     def setfile(self, fname, data, mode, copysource):
         self._checkknown(fname)
         super(workingbackend, self).setfile(fname, data, mode, copysource)
         if copysource is not None:
             self.copied.append((copysource, fname))
         self.changed.add(fname)
 
     def unlink(self, fname):
         self._checkknown(fname)
         super(workingbackend, self).unlink(fname)
         self.removed.add(fname)
         self.changed.add(fname)
 
     def close(self):
         wctx = self.repo[None]
         addremoved = set(self.changed)
         for src, dst in self.copied:
             scmutil.dirstatecopy(self.ui, self.repo, wctx, src, dst)
         if self.removed:
             wctx.forget(sorted(self.removed))
             for f in self.removed:
                 if f not in self.repo.dirstate:
                     # File was deleted and no longer belongs to the
                     # dirstate, it was probably marked added then
                     # deleted, and should not be considered by
                     # addremove().
                     addremoved.discard(f)
         if addremoved:
             cwd = self.repo.getcwd()
             if cwd:
                 addremoved = [util.pathto(self.repo.root, cwd, f)
                               for f in addremoved]
             scmutil.addremove(self.repo, addremoved, similarity=self.similarity)
         return sorted(self.changed)
 
 class filestore(object):
     def __init__(self, maxsize=None):
         self.opener = None
         self.files = {}
         self.created = 0
         self.maxsize = maxsize
         if self.maxsize is None:
             self.maxsize = 4*(2**20)
         self.size = 0
         self.data = {}
 
     def setfile(self, fname, data, mode, copied=None):
         if self.maxsize < 0 or (len(data) + self.size) <= self.maxsize:
             self.data[fname] = (data, mode, copied)
             self.size += len(data)
         else:
             if self.opener is None:
                 root = tempfile.mkdtemp(prefix='hg-patch-')
                 self.opener = scmutil.opener(root)
             # Avoid filename issues with these simple names
             fn = str(self.created)
             self.opener.write(fn, data)
             self.created += 1
             self.files[fname] = (fn, mode, copied)
 
     def getfile(self, fname):
         if fname in self.data:
             return self.data[fname]
         if not self.opener or fname not in self.files:
             raise IOError()
         fn, mode, copied = self.files[fname]
         return self.opener.read(fn), mode, copied
 
     def close(self):
         if self.opener:
             shutil.rmtree(self.opener.base)
 
 class repobackend(abstractbackend):
     def __init__(self, ui, repo, ctx, store):
         super(repobackend, self).__init__(ui)
         self.repo = repo
         self.ctx = ctx
         self.store = store
         self.changed = set()
         self.removed = set()
         self.copied = {}
 
     def _checkknown(self, fname):
         if fname not in self.ctx:
             raise PatchError(_('cannot patch %s: file is not tracked') % fname)
 
     def getfile(self, fname):
         try:
             fctx = self.ctx[fname]
         except error.LookupError:
             raise IOError()
         flags = fctx.flags()
         return fctx.data(), ('l' in flags, 'x' in flags)
 
     def setfile(self, fname, data, mode, copysource):
         if copysource:
             self._checkknown(copysource)
         if data is None:
             data = self.ctx[fname].data()
         self.store.setfile(fname, data, mode, copysource)
         self.changed.add(fname)
         if copysource:
             self.copied[fname] = copysource
 
     def unlink(self, fname):
         self._checkknown(fname)
         self.removed.add(fname)
 
     def exists(self, fname):
         return fname in self.ctx
 
     def close(self):
         return self.changed | self.removed
 
 # @@ -start,len +start,len @@ or @@ -start +start @@ if len is 1
 unidesc = re.compile('@@ -(\d+)(?:,(\d+))? \+(\d+)(?:,(\d+))? @@')
 contextdesc = re.compile('(?:---|\*\*\*) (\d+)(?:,(\d+))? (?:---|\*\*\*)')
 eolmodes = ['strict', 'crlf', 'lf', 'auto']
 
 class patchfile(object):
     def __init__(self, ui, gp, backend, store, eolmode='strict'):
         self.fname = gp.path
         self.eolmode = eolmode
         self.eol = None
         self.backend = backend
         self.ui = ui
         self.lines = []
         self.exists = False
         self.missing = True
         self.mode = gp.mode
         self.copysource = gp.oldpath
         self.create = gp.op in ('ADD', 'COPY', 'RENAME')
         self.remove = gp.op == 'DELETE'
         try:
             if self.copysource is None:
                 data, mode = backend.getfile(self.fname)
                 self.exists = True
             else:
                 data, mode = store.getfile(self.copysource)[:2]
                 self.exists = backend.exists(self.fname)
             self.missing = False
             if data:
                 self.lines = mdiff.splitnewlines(data)
             if self.mode is None:
                 self.mode = mode
             if self.lines:
                 # Normalize line endings
                 if self.lines[0].endswith('\r\n'):
                     self.eol = '\r\n'
                 elif self.lines[0].endswith('\n'):
                     self.eol = '\n'
                 if eolmode != 'strict':
                     nlines = []
                     for l in self.lines:
                         if l.endswith('\r\n'):
                             l = l[:-2] + '\n'
                         nlines.append(l)
                     self.lines = nlines
         except IOError:
             if self.create:
                 self.missing = False
             if self.mode is None:
                 self.mode = (False, False)
         if self.missing:
              self.ui.warn(_("unable to find '%s' for patching\n") % self.fname)
 
         self.hash = {}
         self.dirty = 0
         self.offset = 0
         self.skew = 0
         self.rej = []
         self.fileprinted = False
         self.printfile(False)
         self.hunks = 0
 
     def writelines(self, fname, lines, mode):
         if self.eolmode == 'auto':
             eol = self.eol
         elif self.eolmode == 'crlf':
             eol = '\r\n'
         else:
             eol = '\n'
 
         if self.eolmode != 'strict' and eol and eol != '\n':
             rawlines = []
             for l in lines:
                 if l and l[-1] == '\n':
                     l = l[:-1] + eol
                 rawlines.append(l)
             lines = rawlines
 
         self.backend.setfile(fname, ''.join(lines), mode, self.copysource)
 
     def printfile(self, warn):
         if self.fileprinted:
             return
         if warn or self.ui.verbose:
             self.fileprinted = True
         s = _("patching file %s\n") % self.fname
         if warn:
             self.ui.warn(s)
         else:
             self.ui.note(s)
 
 
     def findlines(self, l, linenum):
         # looks through the hash and finds candidate lines.  The
         # result is a list of line numbers sorted based on distance
         # from linenum
 
         cand = self.hash.get(l, [])
         if len(cand) > 1:
             # resort our list of potentials forward then back.
             cand.sort(key=lambda x: abs(x - linenum))
         return cand
 
     def write_rej(self):
         # our rejects are a little different from patch(1).  This always
         # creates rejects in the same form as the original patch.  A file
         # header is inserted so that you can run the reject through patch again
         # without having to type the filename.
         if not self.rej:
             return
         base = os.path.basename(self.fname)
         lines = ["--- %s\n+++ %s\n" % (base, base)]
         for x in self.rej:
             for l in x.hunk:
                 lines.append(l)
                 if l[-1] != '\n':
                     lines.append("\n\ No newline at end of file\n")
         self.backend.writerej(self.fname, len(self.rej), self.hunks, lines)
 
     def apply(self, h):
         if not h.complete():
             raise PatchError(_("bad hunk #%d %s (%d %d %d %d)") %
                             (h.number, h.desc, len(h.a), h.lena, len(h.b),
                             h.lenb))
 
         self.hunks += 1
 
         if self.missing:
             self.rej.append(h)
             return -1
 
         if self.exists and self.create:
             if self.copysource:
                 self.ui.warn(_("cannot create %s: destination already "
                                "exists\n" % self.fname))
             else:
                 self.ui.warn(_("file %s already exists\n") % self.fname)
             self.rej.append(h)
             return -1
 
         if isinstance(h, binhunk):
             if self.remove:
                 self.backend.unlink(self.fname)
             else:
                 self.lines[:] = h.new()
                 self.offset += len(h.new())
                 self.dirty = True
             return 0
 
         horig = h
         if (self.eolmode in ('crlf', 'lf')
             or self.eolmode == 'auto' and self.eol):
             # If new eols are going to be normalized, then normalize
             # hunk data before patching. Otherwise, preserve input
             # line-endings.
             h = h.getnormalized()
 
         # fast case first, no offsets, no fuzz
         old, oldstart, new, newstart = h.fuzzit(0, False)
         oldstart += self.offset
         orig_start = oldstart
         # if there's skew we want to emit the "(offset %d lines)" even
         # when the hunk cleanly applies at start + skew, so skip the
         # fast case code
         if (self.skew == 0 and
             diffhelpers.testhunk(old, self.lines, oldstart) == 0):
             if self.remove:
                 self.backend.unlink(self.fname)
             else:
                 self.lines[oldstart:oldstart + len(old)] = new
                 self.offset += len(new) - len(old)
                 self.dirty = True
             return 0
 
         # ok, we couldn't match the hunk. Lets look for offsets and fuzz it
         self.hash = {}
         for x, s in enumerate(self.lines):
             self.hash.setdefault(s, []).append(x)
 
         for fuzzlen in xrange(3):
             for toponly in [True, False]:
                 old, oldstart, new, newstart = h.fuzzit(fuzzlen, toponly)
                 oldstart = oldstart + self.offset + self.skew
                 oldstart = min(oldstart, len(self.lines))
                 if old:
                     cand = self.findlines(old[0][1:], oldstart)
                 else:
                     # Only adding lines with no or fuzzed context, just
                     # take the skew in account
                     cand = [oldstart]
 
                 for l in cand:
                     if not old or diffhelpers.testhunk(old, self.lines, l) == 0:
                         self.lines[l : l + len(old)] = new
                         self.offset += len(new) - len(old)
                         self.skew = l - orig_start
                         self.dirty = True
                         offset = l - orig_start - fuzzlen
                         if fuzzlen:
                             msg = _("Hunk #%d succeeded at %d "
                                     "with fuzz %d "
                                     "(offset %d lines).\n")
                             self.printfile(True)
                             self.ui.warn(msg %
                                 (h.number, l + 1, fuzzlen, offset))
                         else:
                             msg = _("Hunk #%d succeeded at %d "
                                     "(offset %d lines).\n")
                             self.ui.note(msg % (h.number, l + 1, offset))
                         return fuzzlen
         self.printfile(True)
         self.ui.warn(_("Hunk #%d FAILED at %d\n") % (h.number, orig_start))
         self.rej.append(horig)
         return -1
 
     def close(self):
         if self.dirty:
             self.writelines(self.fname, self.lines, self.mode)
         self.write_rej()
         return len(self.rej)
 
 class hunk(object):
     def __init__(self, desc, num, lr, context):
         self.number = num
         self.desc = desc
         self.hunk = [desc]
         self.a = []
         self.b = []
         self.starta = self.lena = None
         self.startb = self.lenb = None
         if lr is not None:
             if context:
                 self.read_context_hunk(lr)
             else:
                 self.read_unified_hunk(lr)
 
     def getnormalized(self):
         """Return a copy with line endings normalized to LF."""
 
         def normalize(lines):
             nlines = []
             for line in lines:
                 if line.endswith('\r\n'):
                     line = line[:-2] + '\n'
                 nlines.append(line)
             return nlines
 
         # Dummy object, it is rebuilt manually
         nh = hunk(self.desc, self.number, None, None)
         nh.number = self.number
         nh.desc = self.desc
         nh.hunk = self.hunk
         nh.a = normalize(self.a)
         nh.b = normalize(self.b)
         nh.starta = self.starta
         nh.startb = self.startb
         nh.lena = self.lena
         nh.lenb = self.lenb
         return nh
 
     def read_unified_hunk(self, lr):
         m = unidesc.match(self.desc)
         if not m:
             raise PatchError(_("bad hunk #%d") % self.number)
         self.starta, self.lena, self.startb, self.lenb = m.groups()
         if self.lena is None:
             self.lena = 1
         else:
             self.lena = int(self.lena)
         if self.lenb is None:
             self.lenb = 1
         else:
             self.lenb = int(self.lenb)
         self.starta = int(self.starta)
         self.startb = int(self.startb)
         diffhelpers.addlines(lr, self.hunk, self.lena, self.lenb, self.a,
                              self.b)
         # if we hit eof before finishing out the hunk, the last line will
         # be zero length.  Lets try to fix it up.
         while len(self.hunk[-1]) == 0:
             del self.hunk[-1]
             del self.a[-1]
             del self.b[-1]
             self.lena -= 1
             self.lenb -= 1
         self._fixnewline(lr)
 
     def read_context_hunk(self, lr):
         self.desc = lr.readline()
         m = contextdesc.match(self.desc)
         if not m:
             raise PatchError(_("bad hunk #%d") % self.number)
         self.starta, aend = m.groups()
         self.starta = int(self.starta)
         if aend is None:
             aend = self.starta
         self.lena = int(aend) - self.starta
         if self.starta:
             self.lena += 1
         for x in xrange(self.lena):
             l = lr.readline()
             if l.startswith('---'):
                 # lines addition, old block is empty
                 lr.push(l)
                 break
             s = l[2:]
             if l.startswith('- ') or l.startswith('! '):
                 u = '-' + s
             elif l.startswith('  '):
                 u = ' ' + s
             else:
                 raise PatchError(_("bad hunk #%d old text line %d") %
                                  (self.number, x))
             self.a.append(u)
             self.hunk.append(u)
 
         l = lr.readline()
         if l.startswith('\ '):
             s = self.a[-1][:-1]
             self.a[-1] = s
             self.hunk[-1] = s
             l = lr.readline()
         m = contextdesc.match(l)
         if not m:
             raise PatchError(_("bad hunk #%d") % self.number)
         self.startb, bend = m.groups()
         self.startb = int(self.startb)
         if bend is None:
             bend = self.startb
         self.lenb = int(bend) - self.startb
         if self.startb:
             self.lenb += 1
         hunki = 1
         for x in xrange(self.lenb):
             l = lr.readline()
             if l.startswith('\ '):
                 # XXX: the only way to hit this is with an invalid line range.
                 # The no-eol marker is not counted in the line range, but I
                 # guess there are diff(1) out there which behave differently.
                 s = self.b[-1][:-1]
                 self.b[-1] = s
                 self.hunk[hunki - 1] = s
                 continue
             if not l:
                 # line deletions, new block is empty and we hit EOF
                 lr.push(l)
                 break
             s = l[2:]
             if l.startswith('+ ') or l.startswith('! '):
                 u = '+' + s
             elif l.startswith('  '):
                 u = ' ' + s
             elif len(self.b) == 0:
                 # line deletions, new block is empty
                 lr.push(l)
                 break
             else:
                 raise PatchError(_("bad hunk #%d old text line %d") %
                                  (self.number, x))
             self.b.append(s)
             while True:
                 if hunki >= len(self.hunk):
                     h = ""
                 else:
                     h = self.hunk[hunki]
                 hunki += 1
                 if h == u:
                     break
                 elif h.startswith('-'):
                     continue
                 else:
                     self.hunk.insert(hunki - 1, u)
                     break
 
         if not self.a:
             # this happens when lines were only added to the hunk
             for x in self.hunk:
                 if x.startswith('-') or x.startswith(' '):
                     self.a.append(x)
         if not self.b:
             # this happens when lines were only deleted from the hunk
             for x in self.hunk:
                 if x.startswith('+') or x.startswith(' '):
                     self.b.append(x[1:])
         # @@ -start,len +start,len @@
         self.desc = "@@ -%d,%d +%d,%d @@\n" % (self.starta, self.lena,
                                              self.startb, self.lenb)
         self.hunk[0] = self.desc
         self._fixnewline(lr)
 
     def _fixnewline(self, lr):
         l = lr.readline()
         if l.startswith('\ '):
             diffhelpers.fix_newline(self.hunk, self.a, self.b)
         else:
             lr.push(l)
 
     def complete(self):
         return len(self.a) == self.lena and len(self.b) == self.lenb
 
     def _fuzzit(self, old, new, fuzz, toponly):
         # this removes context lines from the top and bottom of list 'l'.  It
         # checks the hunk to make sure only context lines are removed, and then
         # returns a new shortened list of lines.
         fuzz = min(fuzz, len(old))
         if fuzz:
             top = 0
             bot = 0
             hlen = len(self.hunk)
             for x in xrange(hlen - 1):
                 # the hunk starts with the @@ line, so use x+1
                 if self.hunk[x + 1][0] == ' ':
                     top += 1
                 else:
                     break
             if not toponly:
                 for x in xrange(hlen - 1):
                     if self.hunk[hlen - bot - 1][0] == ' ':
                         bot += 1
                     else:
                         break
 
             bot = min(fuzz, bot)
             top = min(fuzz, top)
             return old[top:len(old)-bot], new[top:len(new)-bot], top
         return old, new, 0
 
     def fuzzit(self, fuzz, toponly):
         old, new, top = self._fuzzit(self.a, self.b, fuzz, toponly)
         oldstart = self.starta + top
         newstart = self.startb + top
         # zero length hunk ranges already have their start decremented
         if self.lena and oldstart > 0:
             oldstart -= 1
         if self.lenb and newstart > 0:
             newstart -= 1
         return old, oldstart, new, newstart
 
 class binhunk(object):
     'A binary patch file. Only understands literals so far.'
     def __init__(self, lr, fname):
         self.text = None
         self.hunk = ['GIT binary patch\n']
         self._fname = fname
         self._read(lr)
 
     def complete(self):
         return self.text is not None
 
     def new(self):
         return [self.text]
 
     def _read(self, lr):
         def getline(lr, hunk):
             l = lr.readline()
             hunk.append(l)
             return l.rstrip('\r\n')
 
         while True:
             line = getline(lr, self.hunk)
             if not line:
                 raise PatchError(_('could not extract "%s" binary data')
                                  % self._fname)
             if line.startswith('literal '):
                 break
         size = int(line[8:].rstrip())
         dec = []
         line = getline(lr, self.hunk)
         while len(line) > 1:
             l = line[0]
             if l <= 'Z' and l >= 'A':
                 l = ord(l) - ord('A') + 1
             else:
                 l = ord(l) - ord('a') + 27
             try:
                 dec.append(base85.b85decode(line[1:])[:l])
             except ValueError, e:
                 raise PatchError(_('could not decode "%s" binary patch: %s')
                                  % (self._fname, str(e)))
             line = getline(lr, self.hunk)
         text = zlib.decompress(''.join(dec))
         if len(text) != size:
             raise PatchError(_('"%s" length is %d bytes, should be %d')
                              % (self._fname, len(text), size))
         self.text = text
 
 def parsefilename(str):
     # --- filename \t|space stuff
     s = str[4:].rstrip('\r\n')
     i = s.find('\t')
     if i < 0:
         i = s.find(' ')
         if i < 0:
             return s
     return s[:i]
 
 def pathstrip(path, strip):
     pathlen = len(path)
     i = 0
     if strip == 0:
         return '', path.rstrip()
     count = strip
     while count > 0:
         i = path.find('/', i)
         if i == -1:
             raise PatchError(_("unable to strip away %d of %d dirs from %s") %
                              (count, strip, path))
         i += 1
         # consume '//' in the path
         while i < pathlen - 1 and path[i] == '/':
             i += 1
         count -= 1
     return path[:i].lstrip(), path[i:].rstrip()
 
 def makepatchmeta(backend, afile_orig, bfile_orig, hunk, strip):
     nulla = afile_orig == "/dev/null"
     nullb = bfile_orig == "/dev/null"
     create = nulla and hunk.starta == 0 and hunk.lena == 0
     remove = nullb and hunk.startb == 0 and hunk.lenb == 0
     abase, afile = pathstrip(afile_orig, strip)
     gooda = not nulla and backend.exists(afile)
     bbase, bfile = pathstrip(bfile_orig, strip)
     if afile == bfile:
         goodb = gooda
     else:
         goodb = not nullb and backend.exists(bfile)
     missing = not goodb and not gooda and not create
 
     # some diff programs apparently produce patches where the afile is
     # not /dev/null, but afile starts with bfile
     abasedir = afile[:afile.rfind('/') + 1]
     bbasedir = bfile[:bfile.rfind('/') + 1]
     if (missing and abasedir == bbasedir and afile.startswith(bfile)
         and hunk.starta == 0 and hunk.lena == 0):
         create = True
         missing = False
 
     # If afile is "a/b/foo" and bfile is "a/b/foo.orig" we assume the
     # diff is between a file and its backup. In this case, the original
     # file should be patched (see original mpatch code).
     isbackup = (abase == bbase and bfile.startswith(afile))
     fname = None
     if not missing:
         if gooda and goodb:
             fname = isbackup and afile or bfile
         elif gooda:
             fname = afile
 
     if not fname:
         if not nullb:
             fname = isbackup and afile or bfile
         elif not nulla:
             fname = afile
         else:
             raise PatchError(_("undefined source and destination files"))
 
     gp = patchmeta(fname)
     if create:
         gp.op = 'ADD'
     elif remove:
         gp.op = 'DELETE'
     return gp
 
 def scangitpatch(lr, firstline):
     """
     Git patches can emit:
     - rename a to b
     - change b
     - copy a to c
     - change c
 
     We cannot apply this sequence as-is, the renamed 'a' could not be
     found for it would have been renamed already. And we cannot copy
     from 'b' instead because 'b' would have been changed already. So
     we scan the git patch for copy and rename commands so we can
     perform the copies ahead of time.
     """
     pos = 0
     try:
         pos = lr.fp.tell()
         fp = lr.fp
     except IOError:
         fp = cStringIO.StringIO(lr.fp.read())
     gitlr = linereader(fp)
     gitlr.push(firstline)
     gitpatches = readgitpatch(gitlr)
     fp.seek(pos)
     return gitpatches
 
 def iterhunks(fp):
     """Read a patch and yield the following events:
     - ("file", afile, bfile, firsthunk): select a new target file.
     - ("hunk", hunk): a new hunk is ready to be applied, follows a
     "file" event.
     - ("git", gitchanges): current diff is in git format, gitchanges
     maps filenames to gitpatch records. Unique event.
     """
     afile = ""
     bfile = ""
     state = None
     hunknum = 0
     emitfile = newfile = False
     gitpatches = None
 
     # our states
     BFILE = 1
     context = None
     lr = linereader(fp)
 
     while True:
         x = lr.readline()
         if not x:
             break
         if state == BFILE and (
             (not context and x[0] == '@')
             or (context is not False and x.startswith('***************'))
             or x.startswith('GIT binary patch')):
             gp = None
             if (gitpatches and
                 gitpatches[-1].ispatching(afile, bfile)):
                 gp = gitpatches.pop()
             if x.startswith('GIT binary patch'):
                 h = binhunk(lr, gp.path)
             else:
                 if context is None and x.startswith('***************'):
                     context = True
                 h = hunk(x, hunknum + 1, lr, context)
             hunknum += 1
             if emitfile:
                 emitfile = False
                 yield 'file', (afile, bfile, h, gp and gp.copy() or None)
             yield 'hunk', h
         elif x.startswith('diff --git'):
             m = gitre.match(x.rstrip(' \r\n'))
             if not m:
                 continue
             if gitpatches is None:
                 # scan whole input for git metadata
                 gitpatches = scangitpatch(lr, x)
                 yield 'git', [g.copy() for g in gitpatches
                               if g.op in ('COPY', 'RENAME')]
                 gitpatches.reverse()
             afile = 'a/' + m.group(1)
             bfile = 'b/' + m.group(2)
             while gitpatches and not gitpatches[-1].ispatching(afile, bfile):
                 gp = gitpatches.pop()
                 yield 'file', ('a/' + gp.path, 'b/' + gp.path, None, gp.copy())
             if not gitpatches:
                 raise PatchError(_('failed to synchronize metadata for "%s"')
                                  % afile[2:])
             gp = gitpatches[-1]
             newfile = True
         elif x.startswith('---'):
             # check for a unified diff
             l2 = lr.readline()
             if not l2.startswith('+++'):
                 lr.push(l2)
                 continue
             newfile = True
             context = False
             afile = parsefilename(x)
             bfile = parsefilename(l2)
         elif x.startswith('***'):
             # check for a context diff
             l2 = lr.readline()
             if not l2.startswith('---'):
                 lr.push(l2)
                 continue
             l3 = lr.readline()
             lr.push(l3)
             if not l3.startswith("***************"):
                 lr.push(l2)
                 continue
             newfile = True
             context = True
             afile = parsefilename(x)
             bfile = parsefilename(l2)
 
         if newfile:
             newfile = False
             emitfile = True
             state = BFILE
             hunknum = 0
 
     while gitpatches:
         gp = gitpatches.pop()
         yield 'file', ('a/' + gp.path, 'b/' + gp.path, None, gp.copy())
 
 def applydiff(ui, fp, backend, store, strip=1, eolmode='strict'):
     """Reads a patch from fp and tries to apply it.
 
     Returns 0 for a clean patch, -1 if any rejects were found and 1 if
     there was any fuzz.
 
     If 'eolmode' is 'strict', the patch content and patched file are
     read in binary mode. Otherwise, line endings are ignored when
     patching then normalized according to 'eolmode'.
     """
     return _applydiff(ui, fp, patchfile, backend, store, strip=strip,
                       eolmode=eolmode)
 
 def _applydiff(ui, fp, patcher, backend, store, strip=1,
                eolmode='strict'):
 
     def pstrip(p):
         return pathstrip(p, strip - 1)[1]
 
     rejects = 0
     err = 0
     current_file = None
 
     for state, values in iterhunks(fp):
         if state == 'hunk':
             if not current_file:
                 continue
             ret = current_file.apply(values)
             if ret > 0:
                 err = 1
         elif state == 'file':
             if current_file:
                 rejects += current_file.close()
                 current_file = None
             afile, bfile, first_hunk, gp = values
             if gp:
                 gp.path = pstrip(gp.path)
                 if gp.oldpath:
                     gp.oldpath = pstrip(gp.oldpath)
             else:
                 gp = makepatchmeta(backend, afile, bfile, first_hunk, strip)
             if gp.op == 'RENAME':
                 backend.unlink(gp.oldpath)
             if not first_hunk:
                 if gp.op == 'DELETE':
                     backend.unlink(gp.path)
                     continue
                 data, mode = None, None
                 if gp.op in ('RENAME', 'COPY'):
                     data, mode = store.getfile(gp.oldpath)[:2]
                 if gp.mode:
                     mode = gp.mode
                     if gp.op == 'ADD':
                         # Added files without content have no hunk and
                         # must be created
                         data = ''
                 if data or mode:
                     if (gp.op in ('ADD', 'RENAME', 'COPY')
                         and backend.exists(gp.path)):
                         raise PatchError(_("cannot create %s: destination "
                                            "already exists") % gp.path)
                     backend.setfile(gp.path, data, mode, gp.oldpath)
                 continue
             try:
                 current_file = patcher(ui, gp, backend, store,
                                        eolmode=eolmode)
             except PatchError, inst:
                 ui.warn(str(inst) + '\n')
                 current_file = None
                 rejects += 1
                 continue
         elif state == 'git':
             for gp in values:
                 path = pstrip(gp.oldpath)
                 data, mode = backend.getfile(path)
                 store.setfile(path, data, mode)
         else:
             raise util.Abort(_('unsupported parser state: %s') % state)
 
     if current_file:
         rejects += current_file.close()
 
     if rejects:
         return -1
     return err
 
 def _externalpatch(ui, repo, patcher, patchname, strip, files,
                    similarity):
     """use <patcher> to apply <patchname> to the working directory.
     returns whether patch was applied with fuzz factor."""
 
     fuzz = False
     args = []
     cwd = repo.root
     if cwd:
         args.append('-d %s' % util.shellquote(cwd))
     fp = util.popen('%s %s -p%d < %s' % (patcher, ' '.join(args), strip,
                                        util.shellquote(patchname)))
     try:
         for line in fp:
             line = line.rstrip()
             ui.note(line + '\n')
             if line.startswith('patching file '):
                 pf = util.parsepatchoutput(line)
                 printed_file = False
                 files.add(pf)
             elif line.find('with fuzz') >= 0:
                 fuzz = True
                 if not printed_file:
                     ui.warn(pf + '\n')
                     printed_file = True
                 ui.warn(line + '\n')
             elif line.find('saving rejects to file') >= 0:
                 ui.warn(line + '\n')
             elif line.find('FAILED') >= 0:
                 if not printed_file:
                     ui.warn(pf + '\n')
                     printed_file = True
                 ui.warn(line + '\n')
     finally:
         if files:
             cfiles = list(files)
             cwd = repo.getcwd()
             if cwd:
                 cfiles = [util.pathto(repo.root, cwd, f)
                           for f in cfiles]
             scmutil.addremove(repo, cfiles, similarity=similarity)
     code = fp.close()
     if code:
         raise PatchError(_("patch command failed: %s") %
                          util.explainexit(code)[0])
     return fuzz
 
 def patchbackend(ui, backend, patchobj, strip, files=None, eolmode='strict'):
     if files is None:
         files = set()
     if eolmode is None:
         eolmode = ui.config('patch', 'eol', 'strict')
     if eolmode.lower() not in eolmodes:
         raise util.Abort(_('unsupported line endings type: %s') % eolmode)
     eolmode = eolmode.lower()
 
     store = filestore()
     try:
         fp = open(patchobj, 'rb')
     except TypeError:
         fp = patchobj
     try:
         ret = applydiff(ui, fp, backend, store, strip=strip,
                         eolmode=eolmode)
     finally:
         if fp != patchobj:
             fp.close()
         files.update(backend.close())
         store.close()
     if ret < 0:
         raise PatchError(_('patch failed to apply'))
     return ret > 0
 
 def internalpatch(ui, repo, patchobj, strip, files=None, eolmode='strict',
                   similarity=0):
     """use builtin patch to apply <patchobj> to the working directory.
     returns whether patch was applied with fuzz factor."""
     backend = workingbackend(ui, repo, similarity)
     return patchbackend(ui, backend, patchobj, strip, files, eolmode)
 
 def patchrepo(ui, repo, ctx, store, patchobj, strip, files=None,
               eolmode='strict'):
     backend = repobackend(ui, repo, ctx, store)
     return patchbackend(ui, backend, patchobj, strip, files, eolmode)
 
 def makememctx(repo, parents, text, user, date, branch, files, store,
                editor=None):
     def getfilectx(repo, memctx, path):
         data, (islink, isexec), copied = store.getfile(path)
         return context.memfilectx(path, data, islink=islink, isexec=isexec,
                                   copied=copied)
     extra = {}
     if branch:
         extra['branch'] = encoding.fromlocal(branch)
     ctx =  context.memctx(repo, parents, text, files, getfilectx, user,
                           date, extra)
     if editor:
         ctx._text = editor(repo, ctx, [])
     return ctx
 
 def patch(ui, repo, patchname, strip=1, files=None, eolmode='strict',
           similarity=0):
     """Apply <patchname> to the working directory.
 
     'eolmode' specifies how end of lines should be handled. It can be:
     - 'strict': inputs are read in binary mode, EOLs are preserved
     - 'crlf': EOLs are ignored when patching and reset to CRLF
     - 'lf': EOLs are ignored when patching and reset to LF
     - None: get it from user settings, default to 'strict'
     'eolmode' is ignored when using an external patcher program.
 
     Returns whether patch was applied with fuzz factor.
     """
     patcher = ui.config('ui', 'patch')
     if files is None:
         files = set()
     try:
         if patcher:
             return _externalpatch(ui, repo, patcher, patchname, strip,
                                   files, similarity)
         return internalpatch(ui, repo, patchname, strip, files, eolmode,
                              similarity)
     except PatchError, err:
         raise util.Abort(str(err))
 
 def changedfiles(ui, repo, patchpath, strip=1):
     backend = fsbackend(ui, repo.root)
     fp = open(patchpath, 'rb')
     try:
         changed = set()
         for state, values in iterhunks(fp):
             if state == 'file':
                 afile, bfile, first_hunk, gp = values
                 if gp:
                     gp.path = pathstrip(gp.path, strip - 1)[1]
                     if gp.oldpath:
                         gp.oldpath = pathstrip(gp.oldpath, strip - 1)[1]
                 else:
                     gp = makepatchmeta(backend, afile, bfile, first_hunk, strip)
                 changed.add(gp.path)
                 if gp.op == 'RENAME':
                     changed.add(gp.oldpath)
             elif state not in ('hunk', 'git'):
                 raise util.Abort(_('unsupported parser state: %s') % state)
         return changed
     finally:
         fp.close()
 
 def b85diff(to, tn):
     '''print base85-encoded binary diff'''
     def gitindex(text):
         if not text:
             return hex(nullid)
         l = len(text)
         s = util.sha1('blob %d\0' % l)
         s.update(text)
         return s.hexdigest()
 
     def fmtline(line):
         l = len(line)
         if l <= 26:
             l = chr(ord('A') + l - 1)
         else:
             l = chr(l - 26 + ord('a') - 1)
         return '%c%s\n' % (l, base85.b85encode(line, True))
 
     def chunk(text, csize=52):
         l = len(text)
         i = 0
         while i < l:
             yield text[i:i + csize]
             i += csize
 
     tohash = gitindex(to)
     tnhash = gitindex(tn)
     if tohash == tnhash:
         return ""
 
     # TODO: deltas
     ret = ['index %s..%s\nGIT binary patch\nliteral %s\n' %
            (tohash, tnhash, len(tn))]
     for l in chunk(zlib.compress(tn)):
         ret.append(fmtline(l))
     ret.append('\n')
     return ''.join(ret)
 
 class GitDiffRequired(Exception):
     pass
 
 def diffopts(ui, opts=None, untrusted=False, section='diff'):
     def get(key, name=None, getter=ui.configbool):
         return ((opts and opts.get(key)) or
                 getter(section, name or key, None, untrusted=untrusted))
     return mdiff.diffopts(
         text=opts and opts.get('text'),
         git=get('git'),
         nodates=get('nodates'),
         showfunc=get('show_function', 'showfunc'),
         ignorews=get('ignore_all_space', 'ignorews'),
         ignorewsamount=get('ignore_space_change', 'ignorewsamount'),
         ignoreblanklines=get('ignore_blank_lines', 'ignoreblanklines'),
         context=get('unified', getter=ui.config))
 
 def diff(repo, node1=None, node2=None, match=None, changes=None, opts=None,
          losedatafn=None, prefix=''):
     '''yields diff of changes to files between two nodes, or node and
     working directory.
 
     if node1 is None, use first dirstate parent instead.
     if node2 is None, compare node1 with working directory.
 
     losedatafn(**kwarg) is a callable run when opts.upgrade=True and
     every time some change cannot be represented with the current
     patch format. Return False to upgrade to git patch format, True to
     accept the loss or raise an exception to abort the diff. It is
     called with the name of current file being diffed as 'fn'. If set
     to None, patches will always be upgraded to git format when
     necessary.
 
     prefix is a filename prefix that is prepended to all filenames on
     display (used for subrepos).
     '''
 
     if opts is None:
         opts = mdiff.defaultopts
 
     if not node1 and not node2:
         node1 = repo.dirstate.p1()
 
     def lrugetfilectx():
         cache = {}
         order = []
         def getfilectx(f, ctx):
             fctx = ctx.filectx(f, filelog=cache.get(f))
             if f not in cache:
                 if len(cache) > 20:
                     del cache[order.pop(0)]
                 cache[f] = fctx.filelog()
             else:
                 order.remove(f)
             order.append(f)
             return fctx
         return getfilectx
     getfilectx = lrugetfilectx()
 
     ctx1 = repo[node1]
     ctx2 = repo[node2]
 
     if not changes:
         changes = repo.status(ctx1, ctx2, match=match)
     modified, added, removed = changes[:3]
 
     if not modified and not added and not removed:
         return []
 
     revs = None
     if not repo.ui.quiet:
         hexfunc = repo.ui.debugflag and hex or short
         revs = [hexfunc(node) for node in [node1, node2] if node]
 
     copy = {}
     if opts.git or opts.upgrade:
         copy = copies.pathcopies(ctx1, ctx2)
 
     difffn = (lambda opts, losedata:
                   trydiff(repo, revs, ctx1, ctx2, modified, added, removed,
                           copy, getfilectx, opts, losedata, prefix))
     if opts.upgrade and not opts.git:
         try:
             def losedata(fn):
                 if not losedatafn or not losedatafn(fn=fn):
                     raise GitDiffRequired()
             # Buffer the whole output until we are sure it can be generated
             return list(difffn(opts.copy(git=False), losedata))
         except GitDiffRequired:
             return difffn(opts.copy(git=True), None)
     else:
         return difffn(opts, None)
 
 def difflabel(func, *args, **kw):
     '''yields 2-tuples of (output, label) based on the output of func()'''
     headprefixes = [('diff', 'diff.diffline'),
                     ('copy', 'diff.extended'),
                     ('rename', 'diff.extended'),
                     ('old', 'diff.extended'),
                     ('new', 'diff.extended'),
                     ('deleted', 'diff.extended'),
                     ('---', 'diff.file_a'),
                     ('+++', 'diff.file_b')]
     textprefixes = [('@', 'diff.hunk'),
                     ('-', 'diff.deleted'),
                     ('+', 'diff.inserted')]
     head = False
     for chunk in func(*args, **kw):
         lines = chunk.split('\n')
         for i, line in enumerate(lines):
             if i != 0:
                 yield ('\n', '')
             if head:
                 if line.startswith('@'):
                     head = False
             else:
-                if line and not line[0] in ' +-@\\':
+                if line and line[0] not in ' +-@\\':
                     head = True
             stripline = line
             if not head and line and line[0] in '+-':
                 # highlight trailing whitespace, but only in changed lines
                 stripline = line.rstrip()
             prefixes = textprefixes
             if head:
                 prefixes = headprefixes
             for prefix, label in prefixes:
                 if stripline.startswith(prefix):
                     yield (stripline, label)
                     break
             else:
                 yield (line, '')
             if line != stripline:
                 yield (line[len(stripline):], 'diff.trailingwhitespace')
 
 def diffui(*args, **kw):
     '''like diff(), but yields 2-tuples of (output, label) for ui.write()'''
     return difflabel(diff, *args, **kw)
 
 
 def _addmodehdr(header, omode, nmode):
     if omode != nmode:
         header.append('old mode %s\n' % omode)
         header.append('new mode %s\n' % nmode)
 
 def trydiff(repo, revs, ctx1, ctx2, modified, added, removed,
             copy, getfilectx, opts, losedatafn, prefix):
 
     def join(f):
         return os.path.join(prefix, f)
 
     date1 = util.datestr(ctx1.date())
     man1 = ctx1.manifest()
 
     gone = set()
     gitmode = {'l': '120000', 'x': '100755', '': '100644'}
 
     copyto = dict([(v, k) for k, v in copy.items()])
 
     if opts.git:
         revs = None
 
     for f in sorted(modified + added + removed):
         to = None
         tn = None
         dodiff = True
         header = []
         if f in man1:
             to = getfilectx(f, ctx1).data()
         if f not in removed:
             tn = getfilectx(f, ctx2).data()
         a, b = f, f
         if opts.git or losedatafn:
             if f in added:
                 mode = gitmode[ctx2.flags(f)]
                 if f in copy or f in copyto:
                     if opts.git:
                         if f in copy:
                             a = copy[f]
                         else:
                             a = copyto[f]
                         omode = gitmode[man1.flags(a)]
                         _addmodehdr(header, omode, mode)
                         if a in removed and a not in gone:
                             op = 'rename'
                             gone.add(a)
                         else:
                             op = 'copy'
                         header.append('%s from %s\n' % (op, join(a)))
                         header.append('%s to %s\n' % (op, join(f)))
                         to = getfilectx(a, ctx1).data()
                     else:
                         losedatafn(f)
                 else:
                     if opts.git:
                         header.append('new file mode %s\n' % mode)
                     elif ctx2.flags(f):
                         losedatafn(f)
                 # In theory, if tn was copied or renamed we should check
                 # if the source is binary too but the copy record already
                 # forces git mode.
                 if util.binary(tn):
                     if opts.git:
                         dodiff = 'binary'
                     else:
                         losedatafn(f)
                 if not opts.git and not tn:
                     # regular diffs cannot represent new empty file
                     losedatafn(f)
             elif f in removed:
                 if opts.git:
                     # have we already reported a copy above?
                     if ((f in copy and copy[f] in added
                          and copyto[copy[f]] == f) or
                         (f in copyto and copyto[f] in added
                          and copy[copyto[f]] == f)):
                         dodiff = False
                     else:
                         header.append('deleted file mode %s\n' %
                                       gitmode[man1.flags(f)])
                 elif not to or util.binary(to):
                     # regular diffs cannot represent empty file deletion
                     losedatafn(f)
             else:
                 oflag = man1.flags(f)
                 nflag = ctx2.flags(f)
                 binary = util.binary(to) or util.binary(tn)
                 if opts.git:
                     _addmodehdr(header, gitmode[oflag], gitmode[nflag])
                     if binary:
                         dodiff = 'binary'
                 elif binary or nflag != oflag:
                     losedatafn(f)
             if opts.git:
                 header.insert(0, mdiff.diffline(revs, join(a), join(b), opts))
 
         if dodiff:
             if dodiff == 'binary':
                 text = b85diff(to, tn)
             else:
                 text = mdiff.unidiff(to, date1,
                                     # ctx2 date may be dynamic
                                     tn, util.datestr(ctx2.date()),
                                     join(a), join(b), revs, opts=opts)
             if header and (text or len(header) > 1):
                 yield ''.join(header)
             if text:
                 yield text
 
 def diffstatsum(stats):
     maxfile, maxtotal, addtotal, removetotal, binary = 0, 0, 0, 0, False
     for f, a, r, b in stats:
         maxfile = max(maxfile, encoding.colwidth(f))
         maxtotal = max(maxtotal, a + r)
         addtotal += a
         removetotal += r
         binary = binary or b
 
     return maxfile, maxtotal, addtotal, removetotal, binary
 
 def diffstatdata(lines):
     diffre = re.compile('^diff .*-r [a-z0-9]+\s(.*)$')
 
     results = []
     filename, adds, removes, isbinary = None, 0, 0, False
 
     def addresult():
         if filename:
             results.append((filename, adds, removes, isbinary))
 
     for line in lines:
         if line.startswith('diff'):
             addresult()
             # set numbers to 0 anyway when starting new file
             adds, removes, isbinary = 0, 0, False
             if line.startswith('diff --git'):
                 filename = gitre.search(line).group(1)
             elif line.startswith('diff -r'):
                 # format: "diff -r ... -r ... filename"
                 filename = diffre.search(line).group(1)
         elif line.startswith('+') and not line.startswith('+++ '):
             adds += 1
         elif line.startswith('-') and not line.startswith('--- '):
             removes += 1
         elif (line.startswith('GIT binary patch') or
               line.startswith('Binary file')):
             isbinary = True
     addresult()
     return results
 
 def diffstat(lines, width=80, git=False):
     output = []
     stats = diffstatdata(lines)
     maxname, maxtotal, totaladds, totalremoves, hasbinary = diffstatsum(stats)
 
     countwidth = len(str(maxtotal))
     if hasbinary and countwidth < 3:
         countwidth = 3
     graphwidth = width - countwidth - maxname - 6
     if graphwidth < 10:
         graphwidth = 10
 
     def scale(i):
         if maxtotal <= graphwidth:
             return i
         # If diffstat runs out of room it doesn't print anything,
         # which isn't very useful, so always print at least one + or -
         # if there were at least some changes.
         return max(i * graphwidth // maxtotal, int(bool(i)))
 
     for filename, adds, removes, isbinary in stats:
         if isbinary:
             count = 'Bin'
         else:
             count = adds + removes
         pluses = '+' * scale(adds)
         minuses = '-' * scale(removes)
         output.append(' %s%s |  %*s %s%s\n' %
                       (filename, ' ' * (maxname - encoding.colwidth(filename)),
                        countwidth, count, pluses, minuses))
 
     if stats:
         output.append(_(' %d files changed, %d insertions(+), '
                         '%d deletions(-)\n')
                       % (len(stats), totaladds, totalremoves))
 
     return ''.join(output)
 
 def diffstatui(*args, **kw):
     '''like diffstat(), but yields 2-tuples of (output, label) for
     ui.write()
     '''
 
     for line in diffstat(*args, **kw).splitlines():
         if line and line[-1] in '+-':
             name, graph = line.rsplit(' ', 1)
             yield (name + ' ', '')
             m = re.search(r'\++', graph)
             if m:
                 yield (m.group(0), 'diffstat.inserted')
             m = re.search(r'-+', graph)
             if m:
                 yield (m.group(0), 'diffstat.deleted')
         else:
             yield (line, '')
         yield ('\n', '')

mercurial/pure/osutil.py

@@ -1,170 +1,170 b''
 # osutil.py - pure Python version of osutil.c
 #
 #  Copyright 2009 Matt Mackall <[e-mail]> and others
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 import os
 import stat as statmod
 
 def _mode_to_kind(mode):
     if statmod.S_ISREG(mode):
         return statmod.S_IFREG
     if statmod.S_ISDIR(mode):
         return statmod.S_IFDIR
     if statmod.S_ISLNK(mode):
         return statmod.S_IFLNK
     if statmod.S_ISBLK(mode):
         return statmod.S_IFBLK
     if statmod.S_ISCHR(mode):
         return statmod.S_IFCHR
     if statmod.S_ISFIFO(mode):
         return statmod.S_IFIFO
     if statmod.S_ISSOCK(mode):
         return statmod.S_IFSOCK
     return mode
 
 def listdir(path, stat=False, skip=None):
     '''listdir(path, stat=False) -> list_of_tuples
 
     Return a sorted list containing information about the entries
     in the directory.
 
     If stat is True, each element is a 3-tuple:
 
       (name, type, stat object)
 
     Otherwise, each element is a 2-tuple:
 
       (name, type)
     '''
     result = []
     prefix = path
     if not prefix.endswith(os.sep):
         prefix += os.sep
     names = os.listdir(path)
     names.sort()
     for fn in names:
         st = os.lstat(prefix + fn)
         if fn == skip and statmod.S_ISDIR(st.st_mode):
             return []
         if stat:
             result.append((fn, _mode_to_kind(st.st_mode), st))
         else:
             result.append((fn, _mode_to_kind(st.st_mode)))
     return result
 
 if os.name != 'nt':
     posixfile = open
 else:
     import ctypes, msvcrt
 
     _kernel32 = ctypes.windll.kernel32
 
     _DWORD = ctypes.c_ulong
     _LPCSTR = _LPSTR = ctypes.c_char_p
     _HANDLE = ctypes.c_void_p
 
     _INVALID_HANDLE_VALUE = _HANDLE(-1).value
 
     # CreateFile 
     _FILE_SHARE_READ = 0x00000001
     _FILE_SHARE_WRITE = 0x00000002
     _FILE_SHARE_DELETE = 0x00000004
 
     _CREATE_ALWAYS = 2
     _OPEN_EXISTING = 3
     _OPEN_ALWAYS = 4
 
     _GENERIC_READ = 0x80000000
     _GENERIC_WRITE = 0x40000000
 
     _FILE_ATTRIBUTE_NORMAL = 0x80
 
     # _open_osfhandle
     _O_RDONLY = 0x0000
     _O_RDWR = 0x0002
     _O_APPEND = 0x0008
 
     _O_TEXT = 0x4000
     _O_BINARY = 0x8000
 
     # types of parameters of C functions used (required by pypy)
 
     _kernel32.CreateFileA.argtypes = [_LPCSTR, _DWORD, _DWORD, ctypes.c_void_p,
         _DWORD, _DWORD, _HANDLE]
     _kernel32.CreateFileA.restype = _HANDLE
 
     def _raiseioerror(name):
         err = ctypes.WinError()
         raise IOError(err.errno, '%s: %s' % (name, err.strerror))
 
     class posixfile(object):
         '''a file object aiming for POSIX-like semantics
 
         CPython's open() returns a file that was opened *without* setting the
         _FILE_SHARE_DELETE flag, which causes rename and unlink to abort.
         This even happens if any hardlinked copy of the file is in open state.
         We set _FILE_SHARE_DELETE here, so files opened with posixfile can be
         renamed and deleted while they are held open.
         Note that if a file opened with posixfile is unlinked, the file
         remains but cannot be opened again or be recreated under the same name,
         until all reading processes have closed the file.'''
 
         def __init__(self, name, mode='r', bufsize=-1):
             if 'b' in mode:
                 flags = _O_BINARY
             else:
                 flags = _O_TEXT
 
             m0 = mode[0]
-            if m0 == 'r' and not '+' in mode:
+            if m0 == 'r' and '+' not in mode:
                 flags |= _O_RDONLY
                 access = _GENERIC_READ
             else:
                 # work around http://support.microsoft.com/kb/899149 and
                 # set _O_RDWR for 'w' and 'a', even if mode has no '+'
                 flags |= _O_RDWR
                 access = _GENERIC_READ | _GENERIC_WRITE
 
             if m0 == 'r':
                 creation = _OPEN_EXISTING
             elif m0 == 'w':
                 creation = _CREATE_ALWAYS
             elif m0 == 'a':
                 creation = _OPEN_ALWAYS
                 flags |= _O_APPEND
             else:
                 raise ValueError("invalid mode: %s" % mode)
 
             fh = _kernel32.CreateFileA(name, access,
                     _FILE_SHARE_READ | _FILE_SHARE_WRITE | _FILE_SHARE_DELETE,
                     None, creation, _FILE_ATTRIBUTE_NORMAL, None)
             if fh == _INVALID_HANDLE_VALUE:
                 _raiseioerror(name)
 
             fd = msvcrt.open_osfhandle(fh, flags)
             if fd == -1:
                 _kernel32.CloseHandle(fh)
                 _raiseioerror(name)
 
             f = os.fdopen(fd, mode, bufsize)
             # unfortunately, f.name is '<fdopen>' at this point -- so we store
             # the name on this wrapper. We cannot just assign to f.name,
             # because that attribute is read-only.
             object.__setattr__(self, 'name', name)
             object.__setattr__(self, '_file', f)
 
         def __iter__(self):
             return self._file
 
         def __getattr__(self, name):
             return getattr(self._file, name)
 
         def __setattr__(self, name, value):
             '''mimics the read-only attributes of Python file objects
             by raising 'TypeError: readonly attribute' if someone tries:
               f = posixfile('foo.txt')
               f.name = 'bla'  '''
             return self._file.__setattr__(name, value)

mercurial/revlog.py

@@ -1,1317 +1,1317 b''
 # revlog.py - storage back-end for mercurial
 #
 # Copyright 2005-2007 Matt Mackall <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 """Storage back-end for Mercurial.
 
 This provides efficient delta storage with O(1) retrieve and append
 and O(changes) merge between branches.
 """
 
 # import stuff from node for others to import from revlog
 from node import bin, hex, nullid, nullrev
 from i18n import _
 import ancestor, mdiff, parsers, error, util, dagutil
 import struct, zlib, errno
 
 _pack = struct.pack
 _unpack = struct.unpack
 _compress = zlib.compress
 _decompress = zlib.decompress
 _sha = util.sha1
 
 # revlog header flags
 REVLOGV0 = 0
 REVLOGNG = 1
 REVLOGNGINLINEDATA = (1 << 16)
 REVLOGGENERALDELTA = (1 << 17)
 REVLOG_DEFAULT_FLAGS = REVLOGNGINLINEDATA
 REVLOG_DEFAULT_FORMAT = REVLOGNG
 REVLOG_DEFAULT_VERSION = REVLOG_DEFAULT_FORMAT | REVLOG_DEFAULT_FLAGS
 REVLOGNG_FLAGS = REVLOGNGINLINEDATA | REVLOGGENERALDELTA
 
 # revlog index flags
 REVIDX_KNOWN_FLAGS = 0
 
 # max size of revlog with inline data
 _maxinline = 131072
 _chunksize = 1048576
 
 RevlogError = error.RevlogError
 LookupError = error.LookupError
 
 def getoffset(q):
     return int(q >> 16)
 
 def gettype(q):
     return int(q & 0xFFFF)
 
 def offset_type(offset, type):
     return long(long(offset) << 16 | type)
 
 nullhash = _sha(nullid)
 
 def hash(text, p1, p2):
     """generate a hash from the given text and its parent hashes
 
     This hash combines both the current file contents and its history
     in a manner that makes it easy to distinguish nodes with the same
     content in the revision graph.
     """
     # As of now, if one of the parent node is null, p2 is null
     if p2 == nullid:
         # deep copy of a hash is faster than creating one
         s = nullhash.copy()
         s.update(p1)
     else:
         # none of the parent nodes are nullid
         l = [p1, p2]
         l.sort()
         s = _sha(l[0])
         s.update(l[1])
     s.update(text)
     return s.digest()
 
 def compress(text):
     """ generate a possibly-compressed representation of text """
     if not text:
         return ("", text)
     l = len(text)
     bin = None
     if l < 44:
         pass
     elif l > 1000000:
         # zlib makes an internal copy, thus doubling memory usage for
         # large files, so lets do this in pieces
         z = zlib.compressobj()
         p = []
         pos = 0
         while pos < l:
             pos2 = pos + 2**20
             p.append(z.compress(text[pos:pos2]))
             pos = pos2
         p.append(z.flush())
         if sum(map(len, p)) < l:
             bin = "".join(p)
     else:
         bin = _compress(text)
     if bin is None or len(bin) > l:
         if text[0] == '\0':
             return ("", text)
         return ('u', text)
     return ("", bin)
 
 def decompress(bin):
     """ decompress the given input """
     if not bin:
         return bin
     t = bin[0]
     if t == '\0':
         return bin
     if t == 'x':
         return _decompress(bin)
     if t == 'u':
         return bin[1:]
     raise RevlogError(_("unknown compression type %r") % t)
 
 indexformatv0 = ">4l20s20s20s"
 v0shaoffset = 56
 
 class revlogoldio(object):
     def __init__(self):
         self.size = struct.calcsize(indexformatv0)
 
     def parseindex(self, data, inline):
         s = self.size
         index = []
         nodemap =  {nullid: nullrev}
         n = off = 0
         l = len(data)
         while off + s <= l:
             cur = data[off:off + s]
             off += s
             e = _unpack(indexformatv0, cur)
             # transform to revlogv1 format
             e2 = (offset_type(e[0], 0), e[1], -1, e[2], e[3],
                   nodemap.get(e[4], nullrev), nodemap.get(e[5], nullrev), e[6])
             index.append(e2)
             nodemap[e[6]] = n
             n += 1
 
         # add the magic null revision at -1
         index.append((0, 0, 0, -1, -1, -1, -1, nullid))
 
         return index, nodemap, None
 
     def packentry(self, entry, node, version, rev):
         if gettype(entry[0]):
             raise RevlogError(_("index entry flags need RevlogNG"))
         e2 = (getoffset(entry[0]), entry[1], entry[3], entry[4],
               node(entry[5]), node(entry[6]), entry[7])
         return _pack(indexformatv0, *e2)
 
 # index ng:
 #  6 bytes: offset
 #  2 bytes: flags
 #  4 bytes: compressed length
 #  4 bytes: uncompressed length
 #  4 bytes: base rev
 #  4 bytes: link rev
 #  4 bytes: parent 1 rev
 #  4 bytes: parent 2 rev
 # 32 bytes: nodeid
 indexformatng = ">Qiiiiii20s12x"
 ngshaoffset = 32
 versionformat = ">I"
 
 class revlogio(object):
     def __init__(self):
         self.size = struct.calcsize(indexformatng)
 
     def parseindex(self, data, inline):
         # call the C implementation to parse the index data
         index, cache = parsers.parse_index2(data, inline)
         return index, getattr(index, 'nodemap', None), cache
 
     def packentry(self, entry, node, version, rev):
         p = _pack(indexformatng, *entry)
         if rev == 0:
             p = _pack(versionformat, version) + p[4:]
         return p
 
 class revlog(object):
     """
     the underlying revision storage object
 
     A revlog consists of two parts, an index and the revision data.
 
     The index is a file with a fixed record size containing
     information on each revision, including its nodeid (hash), the
     nodeids of its parents, the position and offset of its data within
     the data file, and the revision it's based on. Finally, each entry
     contains a linkrev entry that can serve as a pointer to external
     data.
 
     The revision data itself is a linear collection of data chunks.
     Each chunk represents a revision and is usually represented as a
     delta against the previous chunk. To bound lookup time, runs of
     deltas are limited to about 2 times the length of the original
     version data. This makes retrieval of a version proportional to
     its size, or O(1) relative to the number of revisions.
 
     Both pieces of the revlog are written to in an append-only
     fashion, which means we never need to rewrite a file to insert or
     remove data, and can use some simple techniques to avoid the need
     for locking while reading.
     """
     def __init__(self, opener, indexfile):
         """
         create a revlog object
 
         opener is a function that abstracts the file opening operation
         and can be used to implement COW semantics or the like.
         """
         self.indexfile = indexfile
         self.datafile = indexfile[:-2] + ".d"
         self.opener = opener
         self._cache = None
         self._basecache = (0, 0)
         self._chunkcache = (0, '')
         self.index = []
         self._pcache = {}
         self._nodecache = {nullid: nullrev}
         self._nodepos = None
 
         v = REVLOG_DEFAULT_VERSION
         opts = getattr(opener, 'options', None)
         if opts is not None:
             if 'revlogv1' in opts:
                 if 'generaldelta' in opts:
                     v |= REVLOGGENERALDELTA
             else:
                 v = 0
 
         i = ''
         self._initempty = True
         try:
             f = self.opener(self.indexfile)
             i = f.read()
             f.close()
             if len(i) > 0:
                 v = struct.unpack(versionformat, i[:4])[0]
                 self._initempty = False
         except IOError, inst:
             if inst.errno != errno.ENOENT:
                 raise
 
         self.version = v
         self._inline = v & REVLOGNGINLINEDATA
         self._generaldelta = v & REVLOGGENERALDELTA
         flags = v & ~0xFFFF
         fmt = v & 0xFFFF
         if fmt == REVLOGV0 and flags:
             raise RevlogError(_("index %s unknown flags %#04x for format v0")
                               % (self.indexfile, flags >> 16))
         elif fmt == REVLOGNG and flags & ~REVLOGNG_FLAGS:
             raise RevlogError(_("index %s unknown flags %#04x for revlogng")
                               % (self.indexfile, flags >> 16))
         elif fmt > REVLOGNG:
             raise RevlogError(_("index %s unknown format %d")
                               % (self.indexfile, fmt))
 
         self._io = revlogio()
         if self.version == REVLOGV0:
             self._io = revlogoldio()
         try:
             d = self._io.parseindex(i, self._inline)
         except (ValueError, IndexError):
             raise RevlogError(_("index %s is corrupted") % (self.indexfile))
         self.index, nodemap, self._chunkcache = d
         if nodemap is not None:
             self.nodemap = self._nodecache = nodemap
         if not self._chunkcache:
             self._chunkclear()
 
     def tip(self):
         return self.node(len(self.index) - 2)
     def __len__(self):
         return len(self.index) - 1
     def __iter__(self):
         for i in xrange(len(self)):
             yield i
 
     @util.propertycache
     def nodemap(self):
         self.rev(self.node(0))
         return self._nodecache
 
     def hasnode(self, node):
         try:
             self.rev(node)
             return True
         except KeyError:
             return False
 
     def clearcaches(self):
         try:
             self._nodecache.clearcaches()
         except AttributeError:
             self._nodecache = {nullid: nullrev}
             self._nodepos = None
 
     def rev(self, node):
         try:
             return self._nodecache[node]
         except RevlogError:
             # parsers.c radix tree lookup failed
             raise LookupError(node, self.indexfile, _('no node'))
         except KeyError:
             # pure python cache lookup failed
             n = self._nodecache
             i = self.index
             p = self._nodepos
             if p is None:
                 p = len(i) - 2
             for r in xrange(p, -1, -1):
                 v = i[r][7]
                 n[v] = r
                 if v == node:
                     self._nodepos = r - 1
                     return r
             raise LookupError(node, self.indexfile, _('no node'))
 
     def node(self, rev):
         return self.index[rev][7]
     def linkrev(self, rev):
         return self.index[rev][4]
     def parents(self, node):
         i = self.index
         d = i[self.rev(node)]
         return i[d[5]][7], i[d[6]][7] # map revisions to nodes inline
     def parentrevs(self, rev):
         return self.index[rev][5:7]
     def start(self, rev):
         return int(self.index[rev][0] >> 16)
     def end(self, rev):
         return self.start(rev) + self.length(rev)
     def length(self, rev):
         return self.index[rev][1]
     def chainbase(self, rev):
         index = self.index
         base = index[rev][3]
         while base != rev:
             rev = base
             base = index[rev][3]
         return base
     def flags(self, rev):
         return self.index[rev][0] & 0xFFFF
     def rawsize(self, rev):
         """return the length of the uncompressed text for a given revision"""
         l = self.index[rev][2]
         if l >= 0:
             return l
 
         t = self.revision(self.node(rev))
         return len(t)
     size = rawsize
 
     def reachable(self, node, stop=None):
         """return the set of all nodes ancestral to a given node, including
          the node itself, stopping when stop is matched"""
         reachable = set((node,))
         visit = [node]
         if stop:
             stopn = self.rev(stop)
         else:
             stopn = 0
         while visit:
             n = visit.pop(0)
             if n == stop:
                 continue
             if n == nullid:
                 continue
             for p in self.parents(n):
                 if self.rev(p) < stopn:
                     continue
                 if p not in reachable:
                     reachable.add(p)
                     visit.append(p)
         return reachable
 
     def ancestors(self, *revs):
         """Generate the ancestors of 'revs' in reverse topological order.
 
         Yield a sequence of revision numbers starting with the parents
         of each revision in revs, i.e., each revision is *not* considered
         an ancestor of itself.  Results are in breadth-first order:
         parents of each rev in revs, then parents of those, etc.  Result
         does not include the null revision."""
         visit = list(revs)
         seen = set([nullrev])
         while visit:
             for parent in self.parentrevs(visit.pop(0)):
                 if parent not in seen:
                     visit.append(parent)
                     seen.add(parent)
                     yield parent
 
     def descendants(self, *revs):
         """Generate the descendants of 'revs' in revision order.
 
         Yield a sequence of revision numbers starting with a child of
         some rev in revs, i.e., each revision is *not* considered a
         descendant of itself.  Results are ordered by revision number (a
         topological sort)."""
         first = min(revs)
         if first == nullrev:
             for i in self:
                 yield i
             return
 
         seen = set(revs)
         for i in xrange(first + 1, len(self)):
             for x in self.parentrevs(i):
                 if x != nullrev and x in seen:
                     seen.add(i)
                     yield i
                     break
 
     def findcommonmissing(self, common=None, heads=None):
         """Return a tuple of the ancestors of common and the ancestors of heads
         that are not ancestors of common. In revset terminology, we return the
         tuple:
 
           ::common, (::heads) - (::common)
 
         The list is sorted by revision number, meaning it is
         topologically sorted.
 
         'heads' and 'common' are both lists of node IDs.  If heads is
         not supplied, uses all of the revlog's heads.  If common is not
         supplied, uses nullid."""
         if common is None:
             common = [nullid]
         if heads is None:
             heads = self.heads()
 
         common = [self.rev(n) for n in common]
         heads = [self.rev(n) for n in heads]
 
         # we want the ancestors, but inclusive
         has = set(self.ancestors(*common))
         has.add(nullrev)
         has.update(common)
 
         # take all ancestors from heads that aren't in has
         missing = set()
         visit = [r for r in heads if r not in has]
         while visit:
             r = visit.pop(0)
             if r in missing:
                 continue
             else:
                 missing.add(r)
                 for p in self.parentrevs(r):
                     if p not in has:
                         visit.append(p)
         missing = list(missing)
         missing.sort()
         return has, [self.node(r) for r in missing]
 
     def findmissing(self, common=None, heads=None):
         """Return the ancestors of heads that are not ancestors of common.
 
         More specifically, return a list of nodes N such that every N
         satisfies the following constraints:
 
           1. N is an ancestor of some node in 'heads'
           2. N is not an ancestor of any node in 'common'
 
         The list is sorted by revision number, meaning it is
         topologically sorted.
 
         'heads' and 'common' are both lists of node IDs.  If heads is
         not supplied, uses all of the revlog's heads.  If common is not
         supplied, uses nullid."""
         _common, missing = self.findcommonmissing(common, heads)
         return missing
 
     def nodesbetween(self, roots=None, heads=None):
         """Return a topological path from 'roots' to 'heads'.
 
         Return a tuple (nodes, outroots, outheads) where 'nodes' is a
         topologically sorted list of all nodes N that satisfy both of
         these constraints:
 
           1. N is a descendant of some node in 'roots'
           2. N is an ancestor of some node in 'heads'
 
         Every node is considered to be both a descendant and an ancestor
         of itself, so every reachable node in 'roots' and 'heads' will be
         included in 'nodes'.
 
         'outroots' is the list of reachable nodes in 'roots', i.e., the
         subset of 'roots' that is returned in 'nodes'.  Likewise,
         'outheads' is the subset of 'heads' that is also in 'nodes'.
 
         'roots' and 'heads' are both lists of node IDs.  If 'roots' is
         unspecified, uses nullid as the only root.  If 'heads' is
         unspecified, uses list of all of the revlog's heads."""
         nonodes = ([], [], [])
         if roots is not None:
             roots = list(roots)
             if not roots:
                 return nonodes
             lowestrev = min([self.rev(n) for n in roots])
         else:
             roots = [nullid] # Everybody's a descendant of nullid
             lowestrev = nullrev
         if (lowestrev == nullrev) and (heads is None):
             # We want _all_ the nodes!
             return ([self.node(r) for r in self], [nullid], list(self.heads()))
         if heads is None:
             # All nodes are ancestors, so the latest ancestor is the last
             # node.
             highestrev = len(self) - 1
             # Set ancestors to None to signal that every node is an ancestor.
             ancestors = None
             # Set heads to an empty dictionary for later discovery of heads
             heads = {}
         else:
             heads = list(heads)
             if not heads:
                 return nonodes
             ancestors = set()
             # Turn heads into a dictionary so we can remove 'fake' heads.
             # Also, later we will be using it to filter out the heads we can't
             # find from roots.
             heads = dict.fromkeys(heads, False)
             # Start at the top and keep marking parents until we're done.
             nodestotag = set(heads)
             # Remember where the top was so we can use it as a limit later.
             highestrev = max([self.rev(n) for n in nodestotag])
             while nodestotag:
                 # grab a node to tag
                 n = nodestotag.pop()
                 # Never tag nullid
                 if n == nullid:
                     continue
                 # A node's revision number represents its place in a
                 # topologically sorted list of nodes.
                 r = self.rev(n)
                 if r >= lowestrev:
                     if n not in ancestors:
                         # If we are possibly a descendant of one of the roots
                         # and we haven't already been marked as an ancestor
                         ancestors.add(n) # Mark as ancestor
                         # Add non-nullid parents to list of nodes to tag.
                         nodestotag.update([p for p in self.parents(n) if
                                            p != nullid])
                     elif n in heads: # We've seen it before, is it a fake head?
                         # So it is, real heads should not be the ancestors of
                         # any other heads.
                         heads.pop(n)
             if not ancestors:
                 return nonodes
             # Now that we have our set of ancestors, we want to remove any
             # roots that are not ancestors.
 
             # If one of the roots was nullid, everything is included anyway.
             if lowestrev > nullrev:
                 # But, since we weren't, let's recompute the lowest rev to not
                 # include roots that aren't ancestors.
 
                 # Filter out roots that aren't ancestors of heads
                 roots = [n for n in roots if n in ancestors]
                 # Recompute the lowest revision
                 if roots:
                     lowestrev = min([self.rev(n) for n in roots])
                 else:
                     # No more roots?  Return empty list
                     return nonodes
             else:
                 # We are descending from nullid, and don't need to care about
                 # any other roots.
                 lowestrev = nullrev
                 roots = [nullid]
         # Transform our roots list into a set.
         descendants = set(roots)
         # Also, keep the original roots so we can filter out roots that aren't
         # 'real' roots (i.e. are descended from other roots).
         roots = descendants.copy()
         # Our topologically sorted list of output nodes.
         orderedout = []
         # Don't start at nullid since we don't want nullid in our output list,
         # and if nullid shows up in descedents, empty parents will look like
         # they're descendants.
         for r in xrange(max(lowestrev, 0), highestrev + 1):
             n = self.node(r)
             isdescendant = False
             if lowestrev == nullrev:  # Everybody is a descendant of nullid
                 isdescendant = True
             elif n in descendants:
                 # n is already a descendant
                 isdescendant = True
                 # This check only needs to be done here because all the roots
                 # will start being marked is descendants before the loop.
                 if n in roots:
                     # If n was a root, check if it's a 'real' root.
                     p = tuple(self.parents(n))
                     # If any of its parents are descendants, it's not a root.
                     if (p[0] in descendants) or (p[1] in descendants):
                         roots.remove(n)
             else:
                 p = tuple(self.parents(n))
                 # A node is a descendant if either of its parents are
                 # descendants.  (We seeded the dependents list with the roots
                 # up there, remember?)
                 if (p[0] in descendants) or (p[1] in descendants):
                     descendants.add(n)
                     isdescendant = True
             if isdescendant and ((ancestors is None) or (n in ancestors)):
                 # Only include nodes that are both descendants and ancestors.
                 orderedout.append(n)
                 if (ancestors is not None) and (n in heads):
                     # We're trying to figure out which heads are reachable
                     # from roots.
                     # Mark this head as having been reached
                     heads[n] = True
                 elif ancestors is None:
                     # Otherwise, we're trying to discover the heads.
                     # Assume this is a head because if it isn't, the next step
                     # will eventually remove it.
                     heads[n] = True
                     # But, obviously its parents aren't.
                     for p in self.parents(n):
                         heads.pop(p, None)
         heads = [n for n, flag in heads.iteritems() if flag]
         roots = list(roots)
         assert orderedout
         assert roots
         assert heads
         return (orderedout, roots, heads)
 
     def headrevs(self):
         count = len(self)
         if not count:
             return [nullrev]
         ishead = [1] * (count + 1)
         index = self.index
         for r in xrange(count):
             e = index[r]
             ishead[e[5]] = ishead[e[6]] = 0
         return [r for r in xrange(count) if ishead[r]]
 
     def heads(self, start=None, stop=None):
         """return the list of all nodes that have no children
 
         if start is specified, only heads that are descendants of
         start will be returned
         if stop is specified, it will consider all the revs from stop
         as if they had no children
         """
         if start is None and stop is None:
             if not len(self):
                 return [nullid]
             return [self.node(r) for r in self.headrevs()]
 
         if start is None:
             start = nullid
         if stop is None:
             stop = []
         stoprevs = set([self.rev(n) for n in stop])
         startrev = self.rev(start)
         reachable = set((startrev,))
         heads = set((startrev,))
 
         parentrevs = self.parentrevs
         for r in xrange(startrev + 1, len(self)):
             for p in parentrevs(r):
                 if p in reachable:
                     if r not in stoprevs:
                         reachable.add(r)
                     heads.add(r)
                 if p in heads and p not in stoprevs:
                     heads.remove(p)
 
         return [self.node(r) for r in heads]
 
     def children(self, node):
         """find the children of a given node"""
         c = []
         p = self.rev(node)
         for r in range(p + 1, len(self)):
             prevs = [pr for pr in self.parentrevs(r) if pr != nullrev]
             if prevs:
                 for pr in prevs:
                     if pr == p:
                         c.append(self.node(r))
             elif p == nullrev:
                 c.append(self.node(r))
         return c
 
     def descendant(self, start, end):
         if start == nullrev:
             return True
         for i in self.descendants(start):
             if i == end:
                 return True
             elif i > end:
                 break
         return False
 
     def ancestor(self, a, b):
         """calculate the least common ancestor of nodes a and b"""
 
         # fast path, check if it is a descendant
         a, b = self.rev(a), self.rev(b)
         start, end = sorted((a, b))
         if self.descendant(start, end):
             return self.node(start)
 
         def parents(rev):
             return [p for p in self.parentrevs(rev) if p != nullrev]
 
         c = ancestor.ancestor(a, b, parents)
         if c is None:
             return nullid
 
         return self.node(c)
 
     def _match(self, id):
         if isinstance(id, (long, int)):
             # rev
             return self.node(id)
         if len(id) == 20:
             # possibly a binary node
             # odds of a binary node being all hex in ASCII are 1 in 10**25
             try:
                 node = id
                 self.rev(node) # quick search the index
                 return node
             except LookupError:
                 pass # may be partial hex id
         try:
             # str(rev)
             rev = int(id)
             if str(rev) != id:
                 raise ValueError
             if rev < 0:
                 rev = len(self) + rev
             if rev < 0 or rev >= len(self):
                 raise ValueError
             return self.node(rev)
         except (ValueError, OverflowError):
             pass
         if len(id) == 40:
             try:
                 # a full hex nodeid?
                 node = bin(id)
                 self.rev(node)
                 return node
             except (TypeError, LookupError):
                 pass
 
     def _partialmatch(self, id):
         try:
             return self.index.partialmatch(id)
         except RevlogError:
             # parsers.c radix tree lookup gave multiple matches
             raise LookupError(id, self.indexfile, _("ambiguous identifier"))
         except (AttributeError, ValueError):
             # we are pure python, or key was too short to search radix tree
             pass
 
         if id in self._pcache:
             return self._pcache[id]
 
         if len(id) < 40:
             try:
                 # hex(node)[:...]
                 l = len(id) // 2  # grab an even number of digits
                 prefix = bin(id[:l * 2])
                 nl = [e[7] for e in self.index if e[7].startswith(prefix)]
                 nl = [n for n in nl if hex(n).startswith(id)]
                 if len(nl) > 0:
                     if len(nl) == 1:
                         self._pcache[id] = nl[0]
                         return nl[0]
                     raise LookupError(id, self.indexfile,
                                       _('ambiguous identifier'))
                 return None
             except TypeError:
                 pass
 
     def lookup(self, id):
         """locate a node based on:
             - revision number or str(revision number)
             - nodeid or subset of hex nodeid
         """
         n = self._match(id)
         if n is not None:
             return n
         n = self._partialmatch(id)
         if n:
             return n
 
         raise LookupError(id, self.indexfile, _('no match found'))
 
     def cmp(self, node, text):
         """compare text with a given file revision
 
         returns True if text is different than what is stored.
         """
         p1, p2 = self.parents(node)
         return hash(text, p1, p2) != node
 
     def _addchunk(self, offset, data):
         o, d = self._chunkcache
         # try to add to existing cache
         if o + len(d) == offset and len(d) + len(data) < _chunksize:
             self._chunkcache = o, d + data
         else:
             self._chunkcache = offset, data
 
     def _loadchunk(self, offset, length):
         if self._inline:
             df = self.opener(self.indexfile)
         else:
             df = self.opener(self.datafile)
 
         readahead = max(65536, length)
         df.seek(offset)
         d = df.read(readahead)
         df.close()
         self._addchunk(offset, d)
         if readahead > length:
             return util.buffer(d, 0, length)
         return d
 
     def _getchunk(self, offset, length):
         o, d = self._chunkcache
         l = len(d)
 
         # is it in the cache?
         cachestart = offset - o
         cacheend = cachestart + length
         if cachestart >= 0 and cacheend <= l:
             if cachestart == 0 and cacheend == l:
                 return d # avoid a copy
             return util.buffer(d, cachestart, cacheend - cachestart)
 
         return self._loadchunk(offset, length)
 
     def _chunkraw(self, startrev, endrev):
         start = self.start(startrev)
         length = self.end(endrev) - start
         if self._inline:
             start += (startrev + 1) * self._io.size
         return self._getchunk(start, length)
 
     def _chunk(self, rev):
         return decompress(self._chunkraw(rev, rev))
 
     def _chunkbase(self, rev):
         return self._chunk(rev)
 
     def _chunkclear(self):
         self._chunkcache = (0, '')
 
     def deltaparent(self, rev):
         """return deltaparent of the given revision"""
         base = self.index[rev][3]
         if base == rev:
             return nullrev
         elif self._generaldelta:
             return base
         else:
             return rev - 1
 
     def revdiff(self, rev1, rev2):
         """return or calculate a delta between two revisions"""
         if rev1 != nullrev and self.deltaparent(rev2) == rev1:
             return str(self._chunk(rev2))
 
         return mdiff.textdiff(self.revision(rev1),
                               self.revision(rev2))
 
     def revision(self, nodeorrev):
         """return an uncompressed revision of a given node or revision
         number.
         """
         if isinstance(nodeorrev, int):
             rev = nodeorrev
             node = self.node(rev)
         else:
             node = nodeorrev
             rev = None
 
         cachedrev = None
         if node == nullid:
             return ""
         if self._cache:
             if self._cache[0] == node:
                 return self._cache[2]
             cachedrev = self._cache[1]
 
         # look up what we need to read
         text = None
         if rev is None:
             rev = self.rev(node)
 
         # check rev flags
         if self.flags(rev) & ~REVIDX_KNOWN_FLAGS:
             raise RevlogError(_('incompatible revision flag %x') %
                               (self.flags(rev) & ~REVIDX_KNOWN_FLAGS))
 
         # build delta chain
         chain = []
         index = self.index # for performance
         generaldelta = self._generaldelta
         iterrev = rev
         e = index[iterrev]
         while iterrev != e[3] and iterrev != cachedrev:
             chain.append(iterrev)
             if generaldelta:
                 iterrev = e[3]
             else:
                 iterrev -= 1
             e = index[iterrev]
         chain.reverse()
         base = iterrev
 
         if iterrev == cachedrev:
             # cache hit
             text = self._cache[2]
 
         # drop cache to save memory
         self._cache = None
 
         self._chunkraw(base, rev)
         if text is None:
             text = str(self._chunkbase(base))
 
         bins = [self._chunk(r) for r in chain]
         text = mdiff.patches(text, bins)
 
         text = self._checkhash(text, node, rev)
 
         self._cache = (node, rev, text)
         return text
 
     def _checkhash(self, text, node, rev):
         p1, p2 = self.parents(node)
         if node != hash(text, p1, p2):
             raise RevlogError(_("integrity check failed on %s:%d")
                               % (self.indexfile, rev))
         return text
 
     def checkinlinesize(self, tr, fp=None):
         if not self._inline or (self.start(-2) + self.length(-2)) < _maxinline:
             return
 
         trinfo = tr.find(self.indexfile)
         if trinfo is None:
             raise RevlogError(_("%s not found in the transaction")
                               % self.indexfile)
 
         trindex = trinfo[2]
         dataoff = self.start(trindex)
 
         tr.add(self.datafile, dataoff)
 
         if fp:
             fp.flush()
             fp.close()
 
         df = self.opener(self.datafile, 'w')
         try:
             for r in self:
                 df.write(self._chunkraw(r, r))
         finally:
             df.close()
 
         fp = self.opener(self.indexfile, 'w', atomictemp=True)
         self.version &= ~(REVLOGNGINLINEDATA)
         self._inline = False
         for i in self:
             e = self._io.packentry(self.index[i], self.node, self.version, i)
             fp.write(e)
 
         # if we don't call close, the temp file will never replace the
         # real index
         fp.close()
 
         tr.replace(self.indexfile, trindex * self._io.size)
         self._chunkclear()
 
     def addrevision(self, text, transaction, link, p1, p2, cachedelta=None):
         """add a revision to the log
 
         text - the revision data to add
         transaction - the transaction object used for rollback
         link - the linkrev data to add
         p1, p2 - the parent nodeids of the revision
         cachedelta - an optional precomputed delta
         """
         node = hash(text, p1, p2)
         if node in self.nodemap:
             return node
 
         dfh = None
         if not self._inline:
             dfh = self.opener(self.datafile, "a")
         ifh = self.opener(self.indexfile, "a+")
         try:
             return self._addrevision(node, text, transaction, link, p1, p2,
                                      cachedelta, ifh, dfh)
         finally:
             if dfh:
                 dfh.close()
             ifh.close()
 
     def _addrevision(self, node, text, transaction, link, p1, p2,
                      cachedelta, ifh, dfh):
         """internal function to add revisions to the log
 
         see addrevision for argument descriptions.
         invariants:
         - text is optional (can be None); if not set, cachedelta must be set.
           if both are set, they must correspond to eachother.
         """
         btext = [text]
         def buildtext():
             if btext[0] is not None:
                 return btext[0]
             # flush any pending writes here so we can read it in revision
             if dfh:
                 dfh.flush()
             ifh.flush()
             basetext = self.revision(self.node(cachedelta[0]))
             btext[0] = mdiff.patch(basetext, cachedelta[1])
             chk = hash(btext[0], p1, p2)
             if chk != node:
                 raise RevlogError(_("consistency error in delta"))
             return btext[0]
 
         def builddelta(rev):
             # can we use the cached delta?
             if cachedelta and cachedelta[0] == rev:
                 delta = cachedelta[1]
             else:
                 t = buildtext()
                 ptext = self.revision(self.node(rev))
                 delta = mdiff.textdiff(ptext, t)
             data = compress(delta)
             l = len(data[1]) + len(data[0])
             if basecache[0] == rev:
                 chainbase = basecache[1]
             else:
                 chainbase = self.chainbase(rev)
             dist = l + offset - self.start(chainbase)
             if self._generaldelta:
                 base = rev
             else:
                 base = chainbase
             return dist, l, data, base, chainbase
 
         curr = len(self)
         prev = curr - 1
         base = chainbase = curr
         offset = self.end(prev)
         flags = 0
         d = None
         basecache = self._basecache
         p1r, p2r = self.rev(p1), self.rev(p2)
 
         # should we try to build a delta?
         if prev != nullrev:
             if self._generaldelta:
                 if p1r >= basecache[1]:
                     d = builddelta(p1r)
                 elif p2r >= basecache[1]:
                     d = builddelta(p2r)
                 else:
                     d = builddelta(prev)
             else:
                 d = builddelta(prev)
             dist, l, data, base, chainbase = d
 
         # full versions are inserted when the needed deltas
         # become comparable to the uncompressed text
         if text is None:
             textlen = mdiff.patchedsize(self.rawsize(cachedelta[0]),
                                         cachedelta[1])
         else:
             textlen = len(text)
         if d is None or dist > textlen * 2:
             text = buildtext()
             data = compress(text)
             l = len(data[1]) + len(data[0])
             base = chainbase = curr
 
         e = (offset_type(offset, flags), l, textlen,
              base, link, p1r, p2r, node)
         self.index.insert(-1, e)
         self.nodemap[node] = curr
 
         entry = self._io.packentry(e, self.node, self.version, curr)
         if not self._inline:
             transaction.add(self.datafile, offset)
             transaction.add(self.indexfile, curr * len(entry))
             if data[0]:
                 dfh.write(data[0])
             dfh.write(data[1])
             dfh.flush()
             ifh.write(entry)
         else:
             offset += curr * self._io.size
             transaction.add(self.indexfile, offset, curr)
             ifh.write(entry)
             ifh.write(data[0])
             ifh.write(data[1])
             self.checkinlinesize(transaction, ifh)
 
         if type(text) == str: # only accept immutable objects
             self._cache = (node, curr, text)
         self._basecache = (curr, chainbase)
         return node
 
     def group(self, nodelist, bundler, reorder=None):
         """Calculate a delta group, yielding a sequence of changegroup chunks
         (strings).
 
         Given a list of changeset revs, return a set of deltas and
         metadata corresponding to nodes. The first delta is
         first parent(nodelist[0]) -> nodelist[0], the receiver is
         guaranteed to have this parent as it has all history before
         these changesets. In the case firstparent is nullrev the
         changegroup starts with a full revision.
         """
 
         # if we don't have any revisions touched by these changesets, bail
         if len(nodelist) == 0:
             yield bundler.close()
             return
 
         # for generaldelta revlogs, we linearize the revs; this will both be
         # much quicker and generate a much smaller bundle
         if (self._generaldelta and reorder is not False) or reorder:
             dag = dagutil.revlogdag(self)
             revs = set(self.rev(n) for n in nodelist)
             revs = dag.linearize(revs)
         else:
             revs = sorted([self.rev(n) for n in nodelist])
 
         # add the parent of the first rev
         p = self.parentrevs(revs[0])[0]
         revs.insert(0, p)
 
         # build deltas
         for r in xrange(len(revs) - 1):
             prev, curr = revs[r], revs[r + 1]
             for c in bundler.revchunk(self, curr, prev):
                 yield c
 
         yield bundler.close()
 
     def addgroup(self, bundle, linkmapper, transaction):
         """
         add a delta group
 
         given a set of deltas, add them to the revision log. the
         first delta is against its parent, which should be in our
         log, the rest are against the previous delta.
         """
 
         # track the base of the current delta log
         content = []
         node = None
 
         r = len(self)
         end = 0
         if r:
             end = self.end(r - 1)
         ifh = self.opener(self.indexfile, "a+")
         isize = r * self._io.size
         if self._inline:
             transaction.add(self.indexfile, end + isize, r)
             dfh = None
         else:
             transaction.add(self.indexfile, isize, r)
             transaction.add(self.datafile, end)
             dfh = self.opener(self.datafile, "a")
 
         try:
             # loop through our set of deltas
             chain = None
             while True:
                 chunkdata = bundle.deltachunk(chain)
                 if not chunkdata:
                     break
                 node = chunkdata['node']
                 p1 = chunkdata['p1']
                 p2 = chunkdata['p2']
                 cs = chunkdata['cs']
                 deltabase = chunkdata['deltabase']
                 delta = chunkdata['delta']
 
                 content.append(node)
 
                 link = linkmapper(cs)
                 if node in self.nodemap:
                     # this can happen if two branches make the same change
                     chain = node
                     continue
 
                 for p in (p1, p2):
-                    if not p in self.nodemap:
+                    if p not in self.nodemap:
                         raise LookupError(p, self.indexfile,
                                           _('unknown parent'))
 
                 if deltabase not in self.nodemap:
                     raise LookupError(deltabase, self.indexfile,
                                       _('unknown delta base'))
 
                 baserev = self.rev(deltabase)
                 chain = self._addrevision(node, None, transaction, link,
                                           p1, p2, (baserev, delta), ifh, dfh)
                 if not dfh and not self._inline:
                     # addrevision switched from inline to conventional
                     # reopen the index
                     ifh.close()
                     dfh = self.opener(self.datafile, "a")
                     ifh = self.opener(self.indexfile, "a")
         finally:
             if dfh:
                 dfh.close()
             ifh.close()
 
         return content
 
     def strip(self, minlink, transaction):
         """truncate the revlog on the first revision with a linkrev >= minlink
 
         This function is called when we're stripping revision minlink and
         its descendants from the repository.
 
         We have to remove all revisions with linkrev >= minlink, because
         the equivalent changelog revisions will be renumbered after the
         strip.
 
         So we truncate the revlog on the first of these revisions, and
         trust that the caller has saved the revisions that shouldn't be
         removed and that it'll re-add them after this truncation.
         """
         if len(self) == 0:
             return
 
         for rev in self:
             if self.index[rev][4] >= minlink:
                 break
         else:
             return
 
         # first truncate the files on disk
         end = self.start(rev)
         if not self._inline:
             transaction.add(self.datafile, end)
             end = rev * self._io.size
         else:
             end += rev * self._io.size
 
         transaction.add(self.indexfile, end)
 
         # then reset internal state in memory to forget those revisions
         self._cache = None
         self._chunkclear()
         for x in xrange(rev, len(self)):
             del self.nodemap[self.node(x)]
 
         del self.index[rev:-1]
 
     def checksize(self):
         expected = 0
         if len(self):
             expected = max(0, self.end(len(self) - 1))
 
         try:
             f = self.opener(self.datafile)
             f.seek(0, 2)
             actual = f.tell()
             f.close()
             dd = actual - expected
         except IOError, inst:
             if inst.errno != errno.ENOENT:
                 raise
             dd = 0
 
         try:
             f = self.opener(self.indexfile)
             f.seek(0, 2)
             actual = f.tell()
             f.close()
             s = self._io.size
             i = max(0, actual // s)
             di = actual - (i * s)
             if self._inline:
                 databytes = 0
                 for r in self:
                     databytes += max(0, self.length(r))
                 dd = 0
                 di = actual - len(self) * s - databytes
         except IOError, inst:
             if inst.errno != errno.ENOENT:
                 raise
             di = 0
 
         return (dd, di)
 
     def files(self):
         res = [self.indexfile]
         if not self._inline:
             res.append(self.datafile)
         return res

mercurial/templatefilters.py

@@ -1,395 +1,395 b''
 # template-filters.py - common template expansion filters
 #
 # Copyright 2005-2008 Matt Mackall <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 import cgi, re, os, time, urllib
 import encoding, node, util
 import hbisect
 
 def addbreaks(text):
     """:addbreaks: Any text. Add an XHTML "<br />" tag before the end of
     every line except the last.
     """
     return text.replace('\n', '<br/>\n')
 
 agescales = [("year", 3600 * 24 * 365),
              ("month", 3600 * 24 * 30),
              ("week", 3600 * 24 * 7),
              ("day", 3600 * 24),
              ("hour", 3600),
              ("minute", 60),
              ("second", 1)]
 
 def age(date):
     """:age: Date. Returns a human-readable date/time difference between the
     given date/time and the current date/time.
     """
 
     def plural(t, c):
         if c == 1:
             return t
         return t + "s"
     def fmt(t, c):
         return "%d %s" % (c, plural(t, c))
 
     now = time.time()
     then = date[0]
     future = False
     if then > now:
         future = True
         delta = max(1, int(then - now))
         if delta > agescales[0][1] * 30:
             return 'in the distant future'
     else:
         delta = max(1, int(now - then))
         if delta > agescales[0][1] * 2:
             return util.shortdate(date)
 
     for t, s in agescales:
         n = delta // s
         if n >= 2 or s == 1:
             if future:
                 return '%s from now' % fmt(t, n)
             return '%s ago' % fmt(t, n)
 
 def basename(path):
     """:basename: Any text. Treats the text as a path, and returns the last
     component of the path after splitting by the path separator
     (ignoring trailing separators). For example, "foo/bar/baz" becomes
     "baz" and "foo/bar//" becomes "bar".
     """
     return os.path.basename(path)
 
 def datefilter(text):
     """:date: Date. Returns a date in a Unix date format, including the
     timezone: "Mon Sep 04 15:13:13 2006 0700".
     """
     return util.datestr(text)
 
 def domain(author):
     """:domain: Any text. Finds the first string that looks like an email
     address, and extracts just the domain component. Example: ``User
     <[e-mail]>`` becomes ``example.com``.
     """
     f = author.find('@')
     if f == -1:
         return ''
     author = author[f + 1:]
     f = author.find('>')
     if f >= 0:
         author = author[:f]
     return author
 
 def email(text):
     """:email: Any text. Extracts the first string that looks like an email
     address. Example: ``User <[e-mail]>`` becomes
     ``[e-mail]``.
     """
     return util.email(text)
 
 def escape(text):
     """:escape: Any text. Replaces the special XML/XHTML characters "&", "<"
     and ">" with XML entities.
     """
     return cgi.escape(text, True)
 
 para_re = None
 space_re = None
 
 def fill(text, width):
     '''fill many paragraphs.'''
     global para_re, space_re
     if para_re is None:
         para_re = re.compile('(\n\n|\n\\s*[-*]\\s*)', re.M)
         space_re = re.compile(r'  +')
 
     def findparas():
         start = 0
         while True:
             m = para_re.search(text, start)
             if not m:
                 uctext = unicode(text[start:], encoding.encoding)
                 w = len(uctext)
                 while 0 < w and uctext[w - 1].isspace():
                     w -= 1
                 yield (uctext[:w].encode(encoding.encoding),
                        uctext[w:].encode(encoding.encoding))
                 break
             yield text[start:m.start(0)], m.group(1)
             start = m.end(1)
 
     return "".join([space_re.sub(' ', util.wrap(para, width=width)) + rest
                     for para, rest in findparas()])
 
 def fill68(text):
     """:fill68: Any text. Wraps the text to fit in 68 columns."""
     return fill(text, 68)
 
 def fill76(text):
     """:fill76: Any text. Wraps the text to fit in 76 columns."""
     return fill(text, 76)
 
 def firstline(text):
     """:firstline: Any text. Returns the first line of text."""
     try:
         return text.splitlines(True)[0].rstrip('\r\n')
     except IndexError:
         return ''
 
 def hexfilter(text):
     """:hex: Any text. Convert a binary Mercurial node identifier into
     its long hexadecimal representation.
     """
     return node.hex(text)
 
 def hgdate(text):
     """:hgdate: Date. Returns the date as a pair of numbers: "1157407993
     25200" (Unix timestamp, timezone offset).
     """
     return "%d %d" % text
 
 def isodate(text):
     """:isodate: Date. Returns the date in ISO 8601 format: "2009-08-18 13:00
     +0200".
     """
     return util.datestr(text, '%Y-%m-%d %H:%M %1%2')
 
 def isodatesec(text):
     """:isodatesec: Date. Returns the date in ISO 8601 format, including
     seconds: "2009-08-18 13:00:13 +0200". See also the rfc3339date
     filter.
     """
     return util.datestr(text, '%Y-%m-%d %H:%M:%S %1%2')
 
 def indent(text, prefix):
     '''indent each non-empty line of text after first with prefix.'''
     lines = text.splitlines()
     num_lines = len(lines)
     endswithnewline = text[-1:] == '\n'
     def indenter():
         for i in xrange(num_lines):
             l = lines[i]
             if i and l.strip():
                 yield prefix
             yield l
             if i < num_lines - 1 or endswithnewline:
                 yield '\n'
     return "".join(indenter())
 
 def json(obj):
     if obj is None or obj is False or obj is True:
         return {None: 'null', False: 'false', True: 'true'}[obj]
     elif isinstance(obj, int) or isinstance(obj, float):
         return str(obj)
     elif isinstance(obj, str):
         u = unicode(obj, encoding.encoding, 'replace')
         return '"%s"' % jsonescape(u)
     elif isinstance(obj, unicode):
         return '"%s"' % jsonescape(obj)
     elif util.safehasattr(obj, 'keys'):
         out = []
         for k, v in obj.iteritems():
             s = '%s: %s' % (json(k), json(v))
             out.append(s)
         return '{' + ', '.join(out) + '}'
     elif util.safehasattr(obj, '__iter__'):
         out = []
         for i in obj:
             out.append(json(i))
         return '[' + ', '.join(out) + ']'
     else:
         raise TypeError('cannot encode type %s' % obj.__class__.__name__)
 
 def _uescape(c):
     if ord(c) < 0x80:
         return c
     else:
         return '\\u%04x' % ord(c)
 
 _escapes = [
     ('\\', '\\\\'), ('"', '\\"'), ('\t', '\\t'), ('\n', '\\n'),
     ('\r', '\\r'), ('\f', '\\f'), ('\b', '\\b'),
 ]
 
 def jsonescape(s):
     for k, v in _escapes:
         s = s.replace(k, v)
     return ''.join(_uescape(c) for c in s)
 
 def localdate(text):
     """:localdate: Date. Converts a date to local date."""
     return (text[0], util.makedate()[1])
 
 def nonempty(str):
     """:nonempty: Any text. Returns '(none)' if the string is empty."""
     return str or "(none)"
 
 def obfuscate(text):
     """:obfuscate: Any text. Returns the input text rendered as a sequence of
     XML entities.
     """
     text = unicode(text, encoding.encoding, 'replace')
     return ''.join(['&#%d;' % ord(c) for c in text])
 
 def permissions(flags):
     if "l" in flags:
         return "lrwxrwxrwx"
     if "x" in flags:
         return "-rwxr-xr-x"
     return "-rw-r--r--"
 
 def person(author):
     """:person: Any text. Returns the name before an email address,
     interpreting it as per RFC 5322.
 
     >>> person('foo@bar')
     'foo'
     >>> person('Foo Bar <foo@bar>')
     'Foo Bar'
     >>> person('"Foo Bar" <foo@bar>')
     'Foo Bar'
     >>> person('"Foo \"buz\" Bar" <foo@bar>')
     'Foo "buz" Bar'
     >>> # The following are invalid, but do exist in real-life
     ...
     >>> person('Foo "buz" Bar <foo@bar>')
     'Foo "buz" Bar'
     >>> person('"Foo Bar <foo@bar>')
     'Foo Bar'
     """
-    if not '@' in author:
+    if '@' not in author:
         return author
     f = author.find('<')
     if f != -1:
         return author[:f].strip(' "').replace('\\"', '"')
     f = author.find('@')
     return author[:f].replace('.', ' ')
 
 def rfc3339date(text):
     """:rfc3339date: Date. Returns a date using the Internet date format
     specified in RFC 3339: "2009-08-18T13:00:13+02:00".
     """
     return util.datestr(text, "%Y-%m-%dT%H:%M:%S%1:%2")
 
 def rfc822date(text):
     """:rfc822date: Date. Returns a date using the same format used in email
     headers: "Tue, 18 Aug 2009 13:00:13 +0200".
     """
     return util.datestr(text, "%a, %d %b %Y %H:%M:%S %1%2")
 
 def short(text):
     """:short: Changeset hash. Returns the short form of a changeset hash,
     i.e. a 12 hexadecimal digit string.
     """
     return text[:12]
 
 def shortbisect(text):
     """:shortbisect: Any text. Treats `text` as a bisection status, and
     returns a single-character representing the status (G: good, B: bad,
     S: skipped, U: untested, I: ignored). Returns single space if `text`
     is not a valid bisection status.
     """
     return hbisect.shortlabel(text) or ' '
 
 def shortdate(text):
     """:shortdate: Date. Returns a date like "2006-09-18"."""
     return util.shortdate(text)
 
 def stringescape(text):
     return text.encode('string_escape')
 
 def stringify(thing):
     """:stringify: Any type. Turns the value into text by converting values into
     text and concatenating them.
     """
     if util.safehasattr(thing, '__iter__') and not isinstance(thing, str):
         return "".join([stringify(t) for t in thing if t is not None])
     return str(thing)
 
 def strip(text):
     """:strip: Any text. Strips all leading and trailing whitespace."""
     return text.strip()
 
 def stripdir(text):
     """:stripdir: Treat the text as path and strip a directory level, if
     possible. For example, "foo" and "foo/bar" becomes "foo".
     """
     dir = os.path.dirname(text)
     if dir == "":
         return os.path.basename(text)
     else:
         return dir
 
 def tabindent(text):
     """:tabindent: Any text. Returns the text, with every line except the
     first starting with a tab character.
     """
     return indent(text, '\t')
 
 def urlescape(text):
     """:urlescape: Any text. Escapes all "special" characters. For example,
     "foo bar" becomes "foo%20bar".
     """
     return urllib.quote(text)
 
 def userfilter(text):
     """:user: Any text. Returns a short representation of a user name or email
     address."""
     return util.shortuser(text)
 
 def emailuser(text):
     """:emailuser: Any text. Returns the user portion of an email address."""
     return util.emailuser(text)
 
 def xmlescape(text):
     text = (text
             .replace('&', '&amp;')
             .replace('<', '&lt;')
             .replace('>', '&gt;')
             .replace('"', '&quot;')
             .replace("'", '&#39;')) # &apos; invalid in HTML
     return re.sub('[\x00-\x08\x0B\x0C\x0E-\x1F]', ' ', text)
 
 filters = {
     "addbreaks": addbreaks,
     "age": age,
     "basename": basename,
     "date": datefilter,
     "domain": domain,
     "email": email,
     "escape": escape,
     "fill68": fill68,
     "fill76": fill76,
     "firstline": firstline,
     "hex": hexfilter,
     "hgdate": hgdate,
     "isodate": isodate,
     "isodatesec": isodatesec,
     "json": json,
     "jsonescape": jsonescape,
     "localdate": localdate,
     "nonempty": nonempty,
     "obfuscate": obfuscate,
     "permissions": permissions,
     "person": person,
     "rfc3339date": rfc3339date,
     "rfc822date": rfc822date,
     "short": short,
     "shortbisect": shortbisect,
     "shortdate": shortdate,
     "stringescape": stringescape,
     "stringify": stringify,
     "strip": strip,
     "stripdir": stripdir,
     "tabindent": tabindent,
     "urlescape": urlescape,
     "user": userfilter,
     "emailuser": emailuser,
     "xmlescape": xmlescape,
 }
 
 # tell hggettext to extract docstrings from these functions:
 i18nfunctions = filters.values()

mercurial/templater.py

@@ -1,392 +1,392 b''
 # templater.py - template expansion for output
 #
 # Copyright 2005, 2006 Matt Mackall <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 from i18n import _
 import sys, os
 import util, config, templatefilters, parser, error
 
 # template parsing
 
 elements = {
     "(": (20, ("group", 1, ")"), ("func", 1, ")")),
     ",": (2, None, ("list", 2)),
     "|": (5, None, ("|", 5)),
     "%": (6, None, ("%", 6)),
     ")": (0, None, None),
     "symbol": (0, ("symbol",), None),
     "string": (0, ("string",), None),
     "end": (0, None, None),
 }
 
 def tokenizer(data):
     program, start, end = data
     pos = start
     while pos < end:
         c = program[pos]
         if c.isspace(): # skip inter-token whitespace
             pass
         elif c in "(,)%|": # handle simple operators
             yield (c, None, pos)
         elif (c in '"\'' or c == 'r' and
               program[pos:pos + 2] in ("r'", 'r"')): # handle quoted strings
             if c == 'r':
                 pos += 1
                 c = program[pos]
                 decode = lambda x: x
             else:
                 decode = lambda x: x.decode('string-escape')
             pos += 1
             s = pos
             while pos < end: # find closing quote
                 d = program[pos]
                 if d == '\\': # skip over escaped characters
                     pos += 2
                     continue
                 if d == c:
                     yield ('string', decode(program[s:pos]), s)
                     break
                 pos += 1
             else:
                 raise error.ParseError(_("unterminated string"), s)
         elif c.isalnum() or c in '_':
             s = pos
             pos += 1
             while pos < end: # find end of symbol
                 d = program[pos]
                 if not (d.isalnum() or d == "_"):
                     break
                 pos += 1
             sym = program[s:pos]
             yield ('symbol', sym, s)
             pos -= 1
         elif c == '}':
             pos += 1
             break
         else:
             raise error.ParseError(_("syntax error"), pos)
         pos += 1
     yield ('end', None, pos)
 
 def compiletemplate(tmpl, context):
     parsed = []
     pos, stop = 0, len(tmpl)
     p = parser.parser(tokenizer, elements)
 
     while pos < stop:
         n = tmpl.find('{', pos)
         if n < 0:
             parsed.append(("string", tmpl[pos:]))
             break
         if n > 0 and tmpl[n - 1] == '\\':
             # escaped
             parsed.append(("string", tmpl[pos:n - 1] + "{"))
             pos = n + 1
             continue
         if n > pos:
             parsed.append(("string", tmpl[pos:n]))
 
         pd = [tmpl, n + 1, stop]
         parseres, pos = p.parse(pd)
         parsed.append(parseres)
 
     return [compileexp(e, context) for e in parsed]
 
 def compileexp(exp, context):
     t = exp[0]
     if t in methods:
         return methods[t](exp, context)
     raise error.ParseError(_("unknown method '%s'") % t)
 
 # template evaluation
 
 def getsymbol(exp):
     if exp[0] == 'symbol':
         return exp[1]
     raise error.ParseError(_("expected a symbol"))
 
 def getlist(x):
     if not x:
         return []
     if x[0] == 'list':
         return getlist(x[1]) + [x[2]]
     return [x]
 
 def getfilter(exp, context):
     f = getsymbol(exp)
     if f not in context._filters:
         raise error.ParseError(_("unknown function '%s'") % f)
     return context._filters[f]
 
 def gettemplate(exp, context):
     if exp[0] == 'string':
         return compiletemplate(exp[1], context)
     if exp[0] == 'symbol':
         return context._load(exp[1])
     raise error.ParseError(_("expected template specifier"))
 
 def runstring(context, mapping, data):
     return data
 
 def runsymbol(context, mapping, key):
     v = mapping.get(key)
     if v is None:
         v = context._defaults.get(key, '')
     if util.safehasattr(v, '__call__'):
         return v(**mapping)
     return v
 
 def buildfilter(exp, context):
     func, data = compileexp(exp[1], context)
     filt = getfilter(exp[2], context)
     return (runfilter, (func, data, filt))
 
 def runfilter(context, mapping, data):
     func, data, filt = data
     return filt(func(context, mapping, data))
 
 def buildmap(exp, context):
     func, data = compileexp(exp[1], context)
     ctmpl = gettemplate(exp[2], context)
     return (runmap, (func, data, ctmpl))
 
 def runmap(context, mapping, data):
     func, data, ctmpl = data
     d = func(context, mapping, data)
     lm = mapping.copy()
 
     for i in d:
         if isinstance(i, dict):
             lm.update(i)
             for f, d in ctmpl:
                 yield f(context, lm, d)
         else:
             # v is not an iterable of dicts, this happen when 'key'
             # has been fully expanded already and format is useless.
             # If so, return the expanded value.
             yield i
 
 def buildfunc(exp, context):
     n = getsymbol(exp[1])
     args = [compileexp(x, context) for x in getlist(exp[2])]
     if n in funcs:
         f = funcs[n]
         return (f, args)
     if n in context._filters:
         if len(args) != 1:
             raise error.ParseError(_("filter %s expects one argument") % n)
         f = context._filters[n]
         return (runfilter, (args[0][0], args[0][1], f))
 
 methods = {
     "string": lambda e, c: (runstring, e[1]),
     "symbol": lambda e, c: (runsymbol, e[1]),
     "group": lambda e, c: compileexp(e[1], c),
 #    ".": buildmember,
     "|": buildfilter,
     "%": buildmap,
     "func": buildfunc,
     }
 
 funcs = {
 }
 
 # template engine
 
 path = ['templates', '../templates']
 stringify = templatefilters.stringify
 
 def _flatten(thing):
     '''yield a single stream from a possibly nested set of iterators'''
     if isinstance(thing, str):
         yield thing
     elif not util.safehasattr(thing, '__iter__'):
         if thing is not None:
             yield str(thing)
     else:
         for i in thing:
             if isinstance(i, str):
                 yield i
             elif not util.safehasattr(i, '__iter__'):
                 if i is not None:
                     yield str(i)
             elif i is not None:
                 for j in _flatten(i):
                     yield j
 
 def parsestring(s, quoted=True):
     '''parse a string using simple c-like syntax.
     string must be in quotes if quoted is True.'''
     if quoted:
         if len(s) < 2 or s[0] != s[-1]:
             raise SyntaxError(_('unmatched quotes'))
         return s[1:-1].decode('string_escape')
 
     return s.decode('string_escape')
 
 class engine(object):
     '''template expansion engine.
 
     template expansion works like this. a map file contains key=value
     pairs. if value is quoted, it is treated as string. otherwise, it
     is treated as name of template file.
 
     templater is asked to expand a key in map. it looks up key, and
     looks for strings like this: {foo}. it expands {foo} by looking up
     foo in map, and substituting it. expansion is recursive: it stops
     when there is no more {foo} to replace.
 
     expansion also allows formatting and filtering.
 
     format uses key to expand each item in list. syntax is
     {key%format}.
 
     filter uses function to transform value. syntax is
     {key|filter1|filter2|...}.'''
 
     def __init__(self, loader, filters={}, defaults={}):
         self._loader = loader
         self._filters = filters
         self._defaults = defaults
         self._cache = {}
 
     def _load(self, t):
         '''load, parse, and cache a template'''
         if t not in self._cache:
             self._cache[t] = compiletemplate(self._loader(t), self)
         return self._cache[t]
 
     def process(self, t, mapping):
         '''Perform expansion. t is name of map element to expand.
         mapping contains added elements for use during expansion. Is a
         generator.'''
         return _flatten(func(self, mapping, data) for func, data in
                          self._load(t))
 
 engines = {'default': engine}
 
 class templater(object):
 
     def __init__(self, mapfile, filters={}, defaults={}, cache={},
                  minchunk=1024, maxchunk=65536):
         '''set up template engine.
         mapfile is name of file to read map definitions from.
         filters is dict of functions. each transforms a value into another.
         defaults is dict of default map definitions.'''
         self.mapfile = mapfile or 'template'
         self.cache = cache.copy()
         self.map = {}
         self.base = (mapfile and os.path.dirname(mapfile)) or ''
         self.filters = templatefilters.filters.copy()
         self.filters.update(filters)
         self.defaults = defaults
         self.minchunk, self.maxchunk = minchunk, maxchunk
         self.ecache = {}
 
         if not mapfile:
             return
         if not os.path.exists(mapfile):
             raise util.Abort(_('style not found: %s') % mapfile)
 
         conf = config.config()
         conf.read(mapfile)
 
         for key, val in conf[''].items():
             if val[0] in "'\"":
                 try:
                     self.cache[key] = parsestring(val)
                 except SyntaxError, inst:
                     raise SyntaxError('%s: %s' %
                                       (conf.source('', key), inst.args[0]))
             else:
                 val = 'default', val
                 if ':' in val[1]:
                     val = val[1].split(':', 1)
                 self.map[key] = val[0], os.path.join(self.base, val[1])
 
     def __contains__(self, key):
         return key in self.cache or key in self.map
 
     def load(self, t):
         '''Get the template for the given template name. Use a local cache.'''
-        if not t in self.cache:
+        if t not in self.cache:
             try:
                 self.cache[t] = util.readfile(self.map[t][1])
             except KeyError, inst:
                 raise util.Abort(_('"%s" not in template map') % inst.args[0])
             except IOError, inst:
                 raise IOError(inst.args[0], _('template file %s: %s') %
                               (self.map[t][1], inst.args[1]))
         return self.cache[t]
 
     def __call__(self, t, **mapping):
         ttype = t in self.map and self.map[t][0] or 'default'
         if ttype not in self.ecache:
             self.ecache[ttype] = engines[ttype](self.load,
                                                  self.filters, self.defaults)
         proc = self.ecache[ttype]
 
         stream = proc.process(t, mapping)
         if self.minchunk:
             stream = util.increasingchunks(stream, min=self.minchunk,
                                            max=self.maxchunk)
         return stream
 
 def templatepath(name=None):
     '''return location of template file or directory (if no name).
     returns None if not found.'''
     normpaths = []
 
     # executable version (py2exe) doesn't support __file__
     if util.mainfrozen():
         module = sys.executable
     else:
         module = __file__
     for f in path:
         if f.startswith('/'):
             p = f
         else:
             fl = f.split('/')
             p = os.path.join(os.path.dirname(module), *fl)
         if name:
             p = os.path.join(p, name)
         if name and os.path.exists(p):
             return os.path.normpath(p)
         elif os.path.isdir(p):
             normpaths.append(os.path.normpath(p))
 
     return normpaths
 
 def stylemap(styles, paths=None):
     """Return path to mapfile for a given style.
 
     Searches mapfile in the following locations:
     1. templatepath/style/map
     2. templatepath/map-style
     3. templatepath/map
     """
 
     if paths is None:
         paths = templatepath()
     elif isinstance(paths, str):
         paths = [paths]
 
     if isinstance(styles, str):
         styles = [styles]
 
     for style in styles:
         if not style:
             continue
         locations = [os.path.join(style, 'map'), 'map-' + style]
         locations.append('map')
 
         for path in paths:
             for location in locations:
                 mapfile = os.path.join(path, location)
                 if os.path.isfile(mapfile):
                     return style, mapfile
 
     raise RuntimeError("No hgweb templates found in %r" % paths)

tests/test-walkrepo.py

@@ -1,55 +1,55 b''
 import os
 from mercurial import hg, ui
 from mercurial.scmutil import walkrepos
 from mercurial.util import checklink
 from os import mkdir, chdir
 from os.path import join as pjoin
 
 u = ui.ui()
 sym = checklink('.')
 
 hg.repository(u, 'top1', create=1)
 mkdir('subdir')
 chdir('subdir')
 hg.repository(u, 'sub1', create=1)
 mkdir('subsubdir')
 chdir('subsubdir')
 hg.repository(u, 'subsub1', create=1)
 chdir(os.path.pardir)
 if sym:
     os.symlink(os.path.pardir, 'circle')
     os.symlink(pjoin('subsubdir', 'subsub1'), 'subsub1')
 
 def runtest():
     reposet = frozenset(walkrepos('.', followsym=True))
     if sym and (len(reposet) != 3):
         print "reposet = %r" % (reposet,)
         print ("Found %d repositories when I should have found 3"
                % (len(reposet),))
     if (not sym) and (len(reposet) != 2):
         print "reposet = %r" % (reposet,)
         print ("Found %d repositories when I should have found 2"
                % (len(reposet),))
     sub1set = frozenset((pjoin('.', 'sub1'),
                          pjoin('.', 'circle', 'subdir', 'sub1')))
     if len(sub1set & reposet) != 1:
         print "sub1set = %r" % (sub1set,)
         print "reposet = %r" % (reposet,)
         print "sub1set and reposet should have exactly one path in common."
     sub2set = frozenset((pjoin('.', 'subsub1'),
                          pjoin('.', 'subsubdir', 'subsub1')))
     if len(sub2set & reposet) != 1:
         print "sub2set = %r" % (sub2set,)
         print "reposet = %r" % (reposet,)
         print "sub1set and reposet should have exactly one path in common."
     sub3 = pjoin('.', 'circle', 'top1')
-    if sym and not (sub3 in reposet):
+    if sym and sub3 not in reposet:
         print "reposet = %r" % (reposet,)
         print "Symbolic links are supported and %s is not in reposet" % (sub3,)
 
 runtest()
 if sym:
     # Simulate not having symlinks.
     del os.path.samestat
     sym = False
     runtest()