classes: fix class style problems found by b071cd58af50

This makes test-wireprotocol.py work on Python 2.4

doc/hgmanpage.py

@@ -1,1107 +1,1107 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
 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:
+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:
+        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:
                 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 :

mercurial/byterange.py

@@ -1,466 +1,466 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, write to the
 #      Free Software Foundation, Inc.,
 #      59 Temple Place, Suite 330,
 #      Boston, MA  02111-1307  USA
 
 # This file is part of urlgrabber, a high-level cross-protocol url-grabber
 # Copyright 2002-2004 Michael D. Stenner, Ryan Tomayko
 
 # $Id: byterange.py,v 1.9 2005/02/14 21:55:07 mstenner Exp $
 
 import os
 import stat
 import urllib
 import urllib2
 import email.Utils
 
 class RangeError(IOError):
     """Error raised when an unsatisfiable range is requested."""
     pass
 
 class HTTPRangeHandler(urllib2.BaseHandler):
     """Handler that enables HTTP Range headers.
 
     This was extremely simple. The Range header is a HTTP feature to
     begin with so all this class does is tell urllib2 that the
     "206 Partial Content" reponse from the HTTP server is what we
     expected.
 
     Example:
         import urllib2
         import byterange
 
         range_handler = range.HTTPRangeHandler()
         opener = urllib2.build_opener(range_handler)
 
         # install it
         urllib2.install_opener(opener)
 
         # create Request and set Range header
         req = urllib2.Request('http://www.python.org/')
         req.header['Range'] = 'bytes=30-50'
         f = urllib2.urlopen(req)
     """
 
     def http_error_206(self, req, fp, code, msg, hdrs):
         # 206 Partial Content Response
         r = urllib.addinfourl(fp, hdrs, req.get_full_url())
         r.code = code
         r.msg = msg
         return r
 
     def http_error_416(self, req, fp, code, msg, hdrs):
         # HTTP's Range Not Satisfiable error
         raise RangeError('Requested Range Not Satisfiable')
 
-class RangeableFileObject:
+class RangeableFileObject(object):
     """File object wrapper to enable raw range handling.
     This was implemented primarilary for handling range
     specifications for file:// urls. This object effectively makes
     a file object look like it consists only of a range of bytes in
     the stream.
 
     Examples:
         # expose 10 bytes, starting at byte position 20, from
         # /etc/aliases.
         >>> fo = RangeableFileObject(file('/etc/passwd', 'r'), (20,30))
         # seek seeks within the range (to position 23 in this case)
         >>> fo.seek(3)
         # tell tells where your at _within the range_ (position 3 in
         # this case)
         >>> fo.tell()
         # read EOFs if an attempt is made to read past the last
         # byte in the range. the following will return only 7 bytes.
         >>> fo.read(30)
     """
 
     def __init__(self, fo, rangetup):
         """Create a RangeableFileObject.
         fo       -- a file like object. only the read() method need be
                     supported but supporting an optimized seek() is
                     preferable.
         rangetup -- a (firstbyte,lastbyte) tuple specifying the range
                     to work over.
         The file object provided is assumed to be at byte offset 0.
         """
         self.fo = fo
         (self.firstbyte, self.lastbyte) = range_tuple_normalize(rangetup)
         self.realpos = 0
         self._do_seek(self.firstbyte)
 
     def __getattr__(self, name):
         """This effectively allows us to wrap at the instance level.
         Any attribute not found in _this_ object will be searched for
         in self.fo.  This includes methods."""
         if hasattr(self.fo, name):
             return getattr(self.fo, name)
         raise AttributeError(name)
 
     def tell(self):
         """Return the position within the range.
         This is different from fo.seek in that position 0 is the
         first byte position of the range tuple. For example, if
         this object was created with a range tuple of (500,899),
         tell() will return 0 when at byte position 500 of the file.
         """
         return (self.realpos - self.firstbyte)
 
     def seek(self, offset, whence=0):
         """Seek within the byte range.
         Positioning is identical to that described under tell().
         """
         assert whence in (0, 1, 2)
         if whence == 0:   # absolute seek
             realoffset = self.firstbyte + offset
         elif whence == 1: # relative seek
             realoffset = self.realpos + offset
         elif whence == 2: # absolute from end of file
             # XXX: are we raising the right Error here?
             raise IOError('seek from end of file not supported.')
 
         # do not allow seek past lastbyte in range
         if self.lastbyte and (realoffset >= self.lastbyte):
             realoffset = self.lastbyte
 
         self._do_seek(realoffset - self.realpos)
 
     def read(self, size=-1):
         """Read within the range.
         This method will limit the size read based on the range.
         """
         size = self._calc_read_size(size)
         rslt = self.fo.read(size)
         self.realpos += len(rslt)
         return rslt
 
     def readline(self, size=-1):
         """Read lines within the range.
         This method will limit the size read based on the range.
         """
         size = self._calc_read_size(size)
         rslt = self.fo.readline(size)
         self.realpos += len(rslt)
         return rslt
 
     def _calc_read_size(self, size):
         """Handles calculating the amount of data to read based on
         the range.
         """
         if self.lastbyte:
             if size > -1:
                 if ((self.realpos + size) >= self.lastbyte):
                     size = (self.lastbyte - self.realpos)
             else:
                 size = (self.lastbyte - self.realpos)
         return size
 
     def _do_seek(self, offset):
         """Seek based on whether wrapped object supports seek().
         offset is relative to the current position (self.realpos).
         """
         assert offset >= 0
         if not hasattr(self.fo, 'seek'):
             self._poor_mans_seek(offset)
         else:
             self.fo.seek(self.realpos + offset)
         self.realpos += offset
 
     def _poor_mans_seek(self, offset):
         """Seek by calling the wrapped file objects read() method.
         This is used for file like objects that do not have native
         seek support. The wrapped objects read() method is called
         to manually seek to the desired position.
         offset -- read this number of bytes from the wrapped
                   file object.
         raise RangeError if we encounter EOF before reaching the
         specified offset.
         """
         pos = 0
         bufsize = 1024
         while pos < offset:
             if (pos + bufsize) > offset:
                 bufsize = offset - pos
             buf = self.fo.read(bufsize)
             if len(buf) != bufsize:
                 raise RangeError('Requested Range Not Satisfiable')
             pos += bufsize
 
 class FileRangeHandler(urllib2.FileHandler):
     """FileHandler subclass that adds Range support.
     This class handles Range headers exactly like an HTTP
     server would.
     """
     def open_local_file(self, req):
         import mimetypes
         import email
         host = req.get_host()
         file = req.get_selector()
         localfile = urllib.url2pathname(file)
         stats = os.stat(localfile)
         size = stats[stat.ST_SIZE]
         modified = email.Utils.formatdate(stats[stat.ST_MTIME])
         mtype = mimetypes.guess_type(file)[0]
         if host:
             host, port = urllib.splitport(host)
             if port or socket.gethostbyname(host) not in self.get_names():
                 raise urllib2.URLError('file not on local host')
         fo = open(localfile,'rb')
         brange = req.headers.get('Range', None)
         brange = range_header_to_tuple(brange)
         assert brange != ()
         if brange:
             (fb, lb) = brange
             if lb == '':
                 lb = size
             if fb < 0 or fb > size or lb > size:
                 raise RangeError('Requested Range Not Satisfiable')
             size = (lb - fb)
             fo = RangeableFileObject(fo, (fb, lb))
         headers = email.message_from_string(
             'Content-Type: %s\nContent-Length: %d\nLast-Modified: %s\n' %
             (mtype or 'text/plain', size, modified))
         return urllib.addinfourl(fo, headers, 'file:'+file)
 
 
 # FTP Range Support
 # Unfortunately, a large amount of base FTP code had to be copied
 # from urllib and urllib2 in order to insert the FTP REST command.
 # Code modifications for range support have been commented as
 # follows:
 # -- range support modifications start/end here
 
 from urllib import splitport, splituser, splitpasswd, splitattr, \
                    unquote, addclosehook, addinfourl
 import ftplib
 import socket
 import sys
 import mimetypes
 import email
 
 class FTPRangeHandler(urllib2.FTPHandler):
     def ftp_open(self, req):
         host = req.get_host()
         if not host:
             raise IOError('ftp error', 'no host given')
         host, port = splitport(host)
         if port is None:
             port = ftplib.FTP_PORT
         else:
             port = int(port)
 
         # username/password handling
         user, host = splituser(host)
         if user:
             user, passwd = splitpasswd(user)
         else:
             passwd = None
         host = unquote(host)
         user = unquote(user or '')
         passwd = unquote(passwd or '')
 
         try:
             host = socket.gethostbyname(host)
         except socket.error, msg:
             raise urllib2.URLError(msg)
         path, attrs = splitattr(req.get_selector())
         dirs = path.split('/')
         dirs = map(unquote, dirs)
         dirs, file = dirs[:-1], dirs[-1]
         if dirs and not dirs[0]:
             dirs = dirs[1:]
         try:
             fw = self.connect_ftp(user, passwd, host, port, dirs)
             type = file and 'I' or 'D'
             for attr in attrs:
                 attr, value = splitattr(attr)
                 if attr.lower() == 'type' and \
                    value in ('a', 'A', 'i', 'I', 'd', 'D'):
                     type = value.upper()
 
             # -- range support modifications start here
             rest = None
             range_tup = range_header_to_tuple(req.headers.get('Range', None))
             assert range_tup != ()
             if range_tup:
                 (fb, lb) = range_tup
                 if fb > 0:
                     rest = fb
             # -- range support modifications end here
 
             fp, retrlen = fw.retrfile(file, type, rest)
 
             # -- range support modifications start here
             if range_tup:
                 (fb, lb) = range_tup
                 if lb == '':
                     if retrlen is None or retrlen == 0:
                         raise RangeError('Requested Range Not Satisfiable due'
                                          ' to unobtainable file length.')
                     lb = retrlen
                     retrlen = lb - fb
                     if retrlen < 0:
                         # beginning of range is larger than file
                         raise RangeError('Requested Range Not Satisfiable')
                 else:
                     retrlen = lb - fb
                     fp = RangeableFileObject(fp, (0, retrlen))
             # -- range support modifications end here
 
             headers = ""
             mtype = mimetypes.guess_type(req.get_full_url())[0]
             if mtype:
                 headers += "Content-Type: %s\n" % mtype
             if retrlen is not None and retrlen >= 0:
                 headers += "Content-Length: %d\n" % retrlen
             headers = email.message_from_string(headers)
             return addinfourl(fp, headers, req.get_full_url())
         except ftplib.all_errors, msg:
             raise IOError('ftp error', msg), sys.exc_info()[2]
 
     def connect_ftp(self, user, passwd, host, port, dirs):
         fw = ftpwrapper(user, passwd, host, port, dirs)
         return fw
 
 class ftpwrapper(urllib.ftpwrapper):
     # range support note:
     # this ftpwrapper code is copied directly from
     # urllib. The only enhancement is to add the rest
     # argument and pass it on to ftp.ntransfercmd
     def retrfile(self, file, type, rest=None):
         self.endtransfer()
         if type in ('d', 'D'):
             cmd = 'TYPE A'
             isdir = 1
         else:
             cmd = 'TYPE ' + type
             isdir = 0
         try:
             self.ftp.voidcmd(cmd)
         except ftplib.all_errors:
             self.init()
             self.ftp.voidcmd(cmd)
         conn = None
         if file and not isdir:
             # Use nlst to see if the file exists at all
             try:
                 self.ftp.nlst(file)
             except ftplib.error_perm, reason:
                 raise IOError('ftp error', reason), sys.exc_info()[2]
             # Restore the transfer mode!
             self.ftp.voidcmd(cmd)
             # Try to retrieve as a file
             try:
                 cmd = 'RETR ' + file
                 conn = self.ftp.ntransfercmd(cmd, rest)
             except ftplib.error_perm, reason:
                 if str(reason).startswith('501'):
                     # workaround for REST not supported error
                     fp, retrlen = self.retrfile(file, type)
                     fp = RangeableFileObject(fp, (rest,''))
                     return (fp, retrlen)
                 elif not str(reason).startswith('550'):
                     raise IOError('ftp error', reason), sys.exc_info()[2]
         if not conn:
             # Set transfer mode to ASCII!
             self.ftp.voidcmd('TYPE A')
             # Try a directory listing
             if file:
                 cmd = 'LIST ' + file
             else:
                 cmd = 'LIST'
             conn = self.ftp.ntransfercmd(cmd)
         self.busy = 1
         # Pass back both a suitably decorated object and a retrieval length
         return (addclosehook(conn[0].makefile('rb'),
                             self.endtransfer), conn[1])
 
 
 ####################################################################
 # Range Tuple Functions
 # XXX: These range tuple functions might go better in a class.
 
 _rangere = None
 def range_header_to_tuple(range_header):
     """Get a (firstbyte,lastbyte) tuple from a Range header value.
 
     Range headers have the form "bytes=<firstbyte>-<lastbyte>". This
     function pulls the firstbyte and lastbyte values and returns
     a (firstbyte,lastbyte) tuple. If lastbyte is not specified in
     the header value, it is returned as an empty string in the
     tuple.
 
     Return None if range_header is None
     Return () if range_header does not conform to the range spec
     pattern.
 
     """
     global _rangere
     if range_header is None:
         return None
     if _rangere is None:
         import re
         _rangere = re.compile(r'^bytes=(\d{1,})-(\d*)')
     match = _rangere.match(range_header)
     if match:
         tup = range_tuple_normalize(match.group(1, 2))
         if tup and tup[1]:
             tup = (tup[0], tup[1]+1)
         return tup
     return ()
 
 def range_tuple_to_header(range_tup):
     """Convert a range tuple to a Range header value.
     Return a string of the form "bytes=<firstbyte>-<lastbyte>" or None
     if no range is needed.
     """
     if range_tup is None:
         return None
     range_tup = range_tuple_normalize(range_tup)
     if range_tup:
         if range_tup[1]:
             range_tup = (range_tup[0], range_tup[1] - 1)
         return 'bytes=%s-%s' % range_tup
 
 def range_tuple_normalize(range_tup):
     """Normalize a (first_byte,last_byte) range tuple.
     Return a tuple whose first element is guaranteed to be an int
     and whose second element will be '' (meaning: the last byte) or
     an int. Finally, return None if the normalized tuple == (0,'')
     as that is equivelant to retrieving the entire file.
     """
     if range_tup is None:
         return None
     # handle first byte
     fb = range_tup[0]
     if fb in (None, ''):
         fb = 0
     else:
         fb = int(fb)
     # handle last byte
     try:
         lb = range_tup[1]
     except IndexError:
         lb = ''
     else:
         if lb is None:
             lb = ''
         elif lb != '':
             lb = int(lb)
     # check if range is over the entire file
     if (fb, lb) == (0, ''):
         return None
     # check that the range is valid
     if lb < fb:
         raise RangeError('Invalid byte range: %s-%s' % (fb, lb))
     return (fb, lb)

mercurial/hgweb/server.py

@@ -1,319 +1,319 b''
 # hgweb/server.py - The standalone hg web server.
 #
 # Copyright 21 May 2005 - (c) 2005 Jake Edge <[e-mail]>
 # 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 os, sys, errno, urllib, BaseHTTPServer, socket, SocketServer, traceback
 from mercurial import util, error
 from mercurial.hgweb import common
 from mercurial.i18n import _
 
 def _splitURI(uri):
     """ Return path and query splited from uri
 
     Just like CGI environment, the path is unquoted, the query is
     not.
     """
     if '?' in uri:
         path, query = uri.split('?', 1)
     else:
         path, query = uri, ''
     return urllib.unquote(path), query
 
 class _error_logger(object):
     def __init__(self, handler):
         self.handler = handler
     def flush(self):
         pass
     def write(self, str):
         self.writelines(str.split('\n'))
     def writelines(self, seq):
         for msg in seq:
             self.handler.log_error("HG error:  %s", msg)
 
 class _httprequesthandler(BaseHTTPServer.BaseHTTPRequestHandler):
 
     url_scheme = 'http'
 
     @staticmethod
     def preparehttpserver(httpserver, ssl_cert):
         """Prepare .socket of new HTTPServer instance"""
         pass
 
     def __init__(self, *args, **kargs):
         self.protocol_version = 'HTTP/1.1'
         BaseHTTPServer.BaseHTTPRequestHandler.__init__(self, *args, **kargs)
 
     def _log_any(self, fp, format, *args):
         fp.write("%s - - [%s] %s\n" % (self.client_address[0],
                                        self.log_date_time_string(),
                                        format % args))
         fp.flush()
 
     def log_error(self, format, *args):
         self._log_any(self.server.errorlog, format, *args)
 
     def log_message(self, format, *args):
         self._log_any(self.server.accesslog, format, *args)
 
     def log_request(self, code='-', size='-'):
         xheaders = [h for h in self.headers.items() if h[0].startswith('x-')]
         self.log_message('"%s" %s %s%s',
                          self.requestline, str(code), str(size),
                          ''.join([' %s:%s' % h for h in sorted(xheaders)]))
 
     def do_write(self):
         try:
             self.do_hgweb()
         except socket.error, inst:
             if inst[0] != errno.EPIPE:
                 raise
 
     def do_POST(self):
         try:
             self.do_write()
         except Exception:
             self._start_response("500 Internal Server Error", [])
             self._write("Internal Server Error")
             tb = "".join(traceback.format_exception(*sys.exc_info()))
             self.log_error("Exception happened during processing "
                            "request '%s':\n%s", self.path, tb)
 
     def do_GET(self):
         self.do_POST()
 
     def do_hgweb(self):
         path, query = _splitURI(self.path)
 
         env = {}
         env['GATEWAY_INTERFACE'] = 'CGI/1.1'
         env['REQUEST_METHOD'] = self.command
         env['SERVER_NAME'] = self.server.server_name
         env['SERVER_PORT'] = str(self.server.server_port)
         env['REQUEST_URI'] = self.path
         env['SCRIPT_NAME'] = self.server.prefix
         env['PATH_INFO'] = path[len(self.server.prefix):]
         env['REMOTE_HOST'] = self.client_address[0]
         env['REMOTE_ADDR'] = self.client_address[0]
         if query:
             env['QUERY_STRING'] = query
 
         if self.headers.typeheader is None:
             env['CONTENT_TYPE'] = self.headers.type
         else:
             env['CONTENT_TYPE'] = self.headers.typeheader
         length = self.headers.getheader('content-length')
         if length:
             env['CONTENT_LENGTH'] = length
         for header in [h for h in self.headers.keys()
                        if h not in ('content-type', 'content-length')]:
             hkey = 'HTTP_' + header.replace('-', '_').upper()
             hval = self.headers.getheader(header)
             hval = hval.replace('\n', '').strip()
             if hval:
                 env[hkey] = hval
         env['SERVER_PROTOCOL'] = self.request_version
         env['wsgi.version'] = (1, 0)
         env['wsgi.url_scheme'] = self.url_scheme
         if env.get('HTTP_EXPECT', '').lower() == '100-continue':
             self.rfile = common.continuereader(self.rfile, self.wfile.write)
 
         env['wsgi.input'] = self.rfile
         env['wsgi.errors'] = _error_logger(self)
         env['wsgi.multithread'] = isinstance(self.server,
                                              SocketServer.ThreadingMixIn)
         env['wsgi.multiprocess'] = isinstance(self.server,
                                               SocketServer.ForkingMixIn)
         env['wsgi.run_once'] = 0
 
         self.close_connection = True
         self.saved_status = None
         self.saved_headers = []
         self.sent_headers = False
         self.length = None
         for chunk in self.server.application(env, self._start_response):
             self._write(chunk)
 
     def send_headers(self):
         if not self.saved_status:
             raise AssertionError("Sending headers before "
                                  "start_response() called")
         saved_status = self.saved_status.split(None, 1)
         saved_status[0] = int(saved_status[0])
         self.send_response(*saved_status)
         should_close = True
         for h in self.saved_headers:
             self.send_header(*h)
             if h[0].lower() == 'content-length':
                 should_close = False
                 self.length = int(h[1])
         # The value of the Connection header is a list of case-insensitive
         # tokens separated by commas and optional whitespace.
         if 'close' in [token.strip().lower() for token in
                        self.headers.get('connection', '').split(',')]:
             should_close = True
         if should_close:
             self.send_header('Connection', 'close')
         self.close_connection = should_close
         self.end_headers()
         self.sent_headers = True
 
     def _start_response(self, http_status, headers, exc_info=None):
         code, msg = http_status.split(None, 1)
         code = int(code)
         self.saved_status = http_status
         bad_headers = ('connection', 'transfer-encoding')
         self.saved_headers = [h for h in headers
                               if h[0].lower() not in bad_headers]
         return self._write
 
     def _write(self, data):
         if not self.saved_status:
             raise AssertionError("data written before start_response() called")
         elif not self.sent_headers:
             self.send_headers()
         if self.length is not None:
             if len(data) > self.length:
                 raise AssertionError("Content-length header sent, but more "
                                      "bytes than specified are being written.")
             self.length = self.length - len(data)
         self.wfile.write(data)
         self.wfile.flush()
 
 class _httprequesthandleropenssl(_httprequesthandler):
     """HTTPS handler based on pyOpenSSL"""
 
     url_scheme = 'https'
 
     @staticmethod
     def preparehttpserver(httpserver, ssl_cert):
         try:
             import OpenSSL
             OpenSSL.SSL.Context
         except ImportError:
             raise util.Abort(_("SSL support is unavailable"))
         ctx = OpenSSL.SSL.Context(OpenSSL.SSL.SSLv23_METHOD)
         ctx.use_privatekey_file(ssl_cert)
         ctx.use_certificate_file(ssl_cert)
         sock = socket.socket(httpserver.address_family, httpserver.socket_type)
         httpserver.socket = OpenSSL.SSL.Connection(ctx, sock)
         httpserver.server_bind()
         httpserver.server_activate()
 
     def setup(self):
         self.connection = self.request
         self.rfile = socket._fileobject(self.request, "rb", self.rbufsize)
         self.wfile = socket._fileobject(self.request, "wb", self.wbufsize)
 
     def do_write(self):
         import OpenSSL
         try:
             _httprequesthandler.do_write(self)
         except OpenSSL.SSL.SysCallError, inst:
             if inst.args[0] != errno.EPIPE:
                 raise
 
     def handle_one_request(self):
         import OpenSSL
         try:
             _httprequesthandler.handle_one_request(self)
         except (OpenSSL.SSL.SysCallError, OpenSSL.SSL.ZeroReturnError):
             self.close_connection = True
             pass
 
 class _httprequesthandlerssl(_httprequesthandler):
     """HTTPS handler based on Pythons ssl module (introduced in 2.6)"""
 
     url_scheme = 'https'
 
     @staticmethod
     def preparehttpserver(httpserver, ssl_cert):
         try:
             import ssl
             ssl.wrap_socket
         except ImportError:
             raise util.Abort(_("SSL support is unavailable"))
         httpserver.socket = ssl.wrap_socket(httpserver.socket, server_side=True,
             certfile=ssl_cert, ssl_version=ssl.PROTOCOL_SSLv23)
 
     def setup(self):
         self.connection = self.request
         self.rfile = socket._fileobject(self.request, "rb", self.rbufsize)
         self.wfile = socket._fileobject(self.request, "wb", self.wbufsize)
 
 try:
     from threading import activeCount
     _mixin = SocketServer.ThreadingMixIn
 except ImportError:
     if hasattr(os, "fork"):
         _mixin = SocketServer.ForkingMixIn
     else:
-        class _mixin:
+        class _mixin(object):
             pass
 
 def openlog(opt, default):
     if opt and opt != '-':
         return open(opt, 'a')
     return default
 
 class MercurialHTTPServer(object, _mixin, BaseHTTPServer.HTTPServer):
 
     # SO_REUSEADDR has broken semantics on windows
     if os.name == 'nt':
         allow_reuse_address = 0
 
     def __init__(self, ui, app, addr, handler, **kwargs):
         BaseHTTPServer.HTTPServer.__init__(self, addr, handler, **kwargs)
         self.daemon_threads = True
         self.application = app
 
         handler.preparehttpserver(self, ui.config('web', 'certificate'))
 
         prefix = ui.config('web', 'prefix', '')
         if prefix:
             prefix = '/' + prefix.strip('/')
         self.prefix = prefix
 
         alog = openlog(ui.config('web', 'accesslog', '-'), sys.stdout)
         elog = openlog(ui.config('web', 'errorlog', '-'), sys.stderr)
         self.accesslog = alog
         self.errorlog = elog
 
         self.addr, self.port = self.socket.getsockname()[0:2]
         self.fqaddr = socket.getfqdn(addr[0])
 
 class IPv6HTTPServer(MercurialHTTPServer):
     address_family = getattr(socket, 'AF_INET6', None)
     def __init__(self, *args, **kwargs):
         if self.address_family is None:
             raise error.RepoError(_('IPv6 is not available on this system'))
         super(IPv6HTTPServer, self).__init__(*args, **kwargs)
 
 def create_server(ui, app):
 
     if ui.config('web', 'certificate'):
         if sys.version_info >= (2, 6):
             handler = _httprequesthandlerssl
         else:
             handler = _httprequesthandleropenssl
     else:
         handler = _httprequesthandler
 
     if ui.configbool('web', 'ipv6'):
         cls = IPv6HTTPServer
     else:
         cls = MercurialHTTPServer
 
     # ugly hack due to python issue5853 (for threaded use)
     import mimetypes; mimetypes.init()
 
     address = ui.config('web', 'address', '')
     port = util.getport(ui.config('web', 'port', 8000))
     try:
         return cls(ui, app, (address, port), handler)
     except socket.error, inst:
         raise util.Abort(_("cannot start server at '%s:%d': %s")
                          % (address, port, inst.args[1]))

mercurial/keepalive.py

@@ -1,765 +1,765 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, write to the
 #      Free Software Foundation, Inc.,
 #      59 Temple Place, Suite 330,
 #      Boston, MA  02111-1307  USA
 
 # 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:
+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:
                 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:
+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
         if hasattr(str,'read') :
             if self.debuglevel > 0:
                 print "sendIng a read()able"
             data = str.read(blocksize)
             while data:
                 self.sock.sendall(data)
                 data = str.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:
+    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

@@ -1,1859 +1,1859 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 hasattr(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 = subject.replace('\n\t', ' ')
             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[10:])
                         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 __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)
             addremoved.discard(src)
         if (not self.similarity) and self.removed:
             wctx.forget(sorted(self.removed))
         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 = data.splitlines(True)
             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 = h.old()
         # patch starts counting at 1 unless we are adding the file
         if h.starta == 0:
             start = 0
         else:
             start = h.starta + self.offset - 1
         orig_start = start
         # 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, start) == 0:
             if self.remove:
                 self.backend.unlink(self.fname)
             else:
                 self.lines[start : start + h.lena] = h.new()
                 self.offset += h.lenb - h.lena
                 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)
         if h.hunk[-1][0] != ' ':
             # if the hunk tried to put something at the bottom of the file
             # override the start line and use eof here
             search_start = len(self.lines)
         else:
             search_start = orig_start + self.skew
 
         for fuzzlen in xrange(3):
             for toponly in [True, False]:
                 old = h.old(fuzzlen, toponly)
 
                 cand = self.findlines(old[0][1:], search_start)
                 for l in cand:
                     if diffhelpers.testhunk(old, self.lines, l) == 0:
                         newlines = h.new(fuzzlen, toponly)
                         self.lines[l : l + len(old)] = newlines
                         self.offset += len(newlines) - 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, foo, self.lena, self.startb, foo2, 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)
         foo, self.starta, foo2, aend, foo3 = 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)
         foo, self.startb, foo2, bend, foo3 = 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, l, 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(l)-1)
         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
 
             # top and bot now count context in the hunk
             # adjust them if either one is short
             context = max(top, bot, 3)
             if bot < context:
                 bot = max(0, fuzz - (context - bot))
             else:
                 bot = min(fuzz, bot)
             if top < context:
                 top = max(0, fuzz - (context - top))
             else:
                 top = min(fuzz, top)
 
             return l[top:len(l)-bot]
         return l
 
     def old(self, fuzz=0, toponly=False):
         return self.fuzzit(self.a, fuzz, toponly)
 
     def new(self, fuzz=0, toponly=False):
         return self.fuzzit(self.b, fuzz, toponly)
 
-class binhunk:
+class binhunk(object):
     'A binary patch file. Only understands literals so far.'
     def __init__(self, lr):
         self.text = None
         self.hunk = ['GIT binary patch\n']
         self._read(lr)
 
     def complete(self):
         return self.text is not None
 
     def new(self):
         return [self.text]
 
     def _read(self, lr):
         line = lr.readline()
         self.hunk.append(line)
         while line and not line.startswith('literal '):
             line = lr.readline()
             self.hunk.append(line)
         if not line:
             raise PatchError(_('could not extract binary patch'))
         size = int(line[8:].rstrip())
         dec = []
         line = lr.readline()
         self.hunk.append(line)
         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
             dec.append(base85.b85decode(line[1:-1])[:l])
             line = lr.readline()
             self.hunk.append(line)
         text = zlib.decompress(''.join(dec))
         if len(text) != size:
             raise PatchError(_('binary patch is %d bytes, not %d') %
                              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][0] == afile or gitpatches[-1][1] == bfile)):
                 gp = gitpatches.pop()[2]
             if x.startswith('GIT binary patch'):
                 h = binhunk(lr)
             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)
             if not m:
                 continue
             if gitpatches is None:
                 # scan whole input for git metadata
                 gitpatches = [('a/' + gp.path, 'b/' + gp.path, gp) for gp
                               in scangitpatch(lr, x)]
                 yield 'git', [g[2].copy() for g in gitpatches
                               if g[2].op in ('COPY', 'RENAME')]
                 gitpatches.reverse()
             afile = 'a/' + m.group(1)
             bfile = 'b/' + m.group(2)
             while afile != gitpatches[-1][0] and bfile != gitpatches[-1][1]:
                 gp = gitpatches.pop()[2]
                 yield 'file', ('a/' + gp.path, 'b/' + gp.path, None, gp.copy())
             gp = gitpatches[-1][2]
             # copy/rename + modify should modify target, not source
             if gp.op in ('COPY', 'DELETE', 'RENAME', 'ADD') or gp.mode:
                 afile = bfile
             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()[2]
         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:
                 path = pstrip(gp.path)
                 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):
     def get(key, name=None, getter=ui.configbool):
         return ((opts and opts.get(key)) or
                 getter('diff', 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.copies(repo, ctx1, ctx2, repo[nullid])[0]
 
     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()'''
     prefixes = [('diff', 'diff.diffline'),
                 ('copy', 'diff.extended'),
                 ('rename', 'diff.extended'),
                 ('old', 'diff.extended'),
                 ('new', 'diff.extended'),
                 ('deleted', 'diff.extended'),
                 ('---', 'diff.file_a'),
                 ('+++', 'diff.file_b'),
                 ('@@', 'diff.hunk'),
                 ('-', 'diff.deleted'),
                 ('+', 'diff.inserted')]
 
     for chunk in func(*args, **kw):
         lines = chunk.split('\n')
         for i, line in enumerate(lines):
             if i != 0:
                 yield ('\n', '')
             stripline = line
             if line and line[0] in '+-':
                 # highlight trailing whitespace, but only in changed lines
                 stripline = line.rstrip()
             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 = None, 0, 0
 
     def addresult():
         if filename:
             isbinary = adds == 0 and removes == 0
             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 = 0, 0
             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
     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 git and 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', '')

tests/test-batching.py

@@ -1,175 +1,175 b''
 # test-batching.py - tests for transparent command batching
 #
 # Copyright 2011 Peter Arrenbrecht <[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 mercurial.wireproto import localbatch, remotebatch, batchable, future
 
 # equivalent of repo.repository
 class thing(object):
     def hello(self):
         return "Ready."
 
 # equivalent of localrepo.localrepository
 class localthing(thing):
     def foo(self, one, two=None):
         if one:
             return "%s and %s" % (one, two,)
         return "Nope"
     def bar(self, b, a):
         return "%s und %s" % (b, a,)
     def greet(self, name=None):
         return "Hello, %s" % name
     def batch(self):
         '''Support for local batching.'''
         return localbatch(self)
 
 # usage of "thing" interface
 def use(it):
 
     # Direct call to base method shared between client and server.
     print it.hello()
 
     # Direct calls to proxied methods. They cause individual roundtrips.
     print it.foo("Un", two="Deux")
     print it.bar("Eins", "Zwei")
 
     # Batched call to a couple of (possibly proxied) methods.
     batch = it.batch()
     # The calls return futures to eventually hold results.
     foo = batch.foo(one="One", two="Two")
     foo2 = batch.foo(None)
     bar = batch.bar("Eins", "Zwei")
     # We can call non-batchable proxy methods, but the break the current batch
     # request and cause additional roundtrips.
     greet = batch.greet(name="John Smith")
     # We can also add local methods into the mix, but they break the batch too.
     hello = batch.hello()
     bar2 = batch.bar(b="Uno", a="Due")
     # Only now are all the calls executed in sequence, with as few roundtrips
     # as possible.
     batch.submit()
     # After the call to submit, the futures actually contain values.
     print foo.value
     print foo2.value
     print bar.value
     print greet.value
     print hello.value
     print bar2.value
 
 # local usage
 mylocal = localthing()
 print
 print "== Local"
 use(mylocal)
 
 # demo remoting; mimicks what wireproto and HTTP/SSH do
 
 # shared
 
 def escapearg(plain):
     return (plain
             .replace(':', '::')
             .replace(',', ':,')
             .replace(';', ':;')
             .replace('=', ':='))
 def unescapearg(escaped):
     return (escaped
             .replace(':=', '=')
             .replace(':;', ';')
             .replace(':,', ',')
             .replace('::', ':'))
 
 # server side
 
 # equivalent of wireproto's global functions
-class server:
+class server(object):
     def __init__(self, local):
         self.local = local
     def _call(self, name, args):
         args = dict(arg.split('=', 1) for arg in args)
         return getattr(self, name)(**args)
     def perform(self, req):
         print "REQ:", req
         name, args = req.split('?', 1)
         args = args.split('&')
         vals = dict(arg.split('=', 1) for arg in args)
         res = getattr(self, name)(**vals)
         print "  ->", res
         return res
     def batch(self, cmds):
         res = []
         for pair in cmds.split(';'):
             name, args = pair.split(':', 1)
             vals = {}
             for a in args.split(','):
                 if a:
                     n, v = a.split('=')
                     vals[n] = unescapearg(v)
             res.append(escapearg(getattr(self, name)(**vals)))
         return ';'.join(res)
     def foo(self, one, two):
         return mangle(self.local.foo(unmangle(one), unmangle(two)))
     def bar(self, b, a):
         return mangle(self.local.bar(unmangle(b), unmangle(a)))
     def greet(self, name):
         return mangle(self.local.greet(unmangle(name)))
 myserver = server(mylocal)
 
 # local side
 
 # equivalent of wireproto.encode/decodelist, that is, type-specific marshalling
 # here we just transform the strings a bit to check we're properly en-/decoding
 def mangle(s):
     return ''.join(chr(ord(c) + 1) for c in s)
 def unmangle(s):
     return ''.join(chr(ord(c) - 1) for c in s)
 
 # equivalent of wireproto.wirerepository and something like http's wire format
 class remotething(thing):
     def __init__(self, server):
         self.server = server
     def _submitone(self, name, args):
         req = name + '?' + '&'.join(['%s=%s' % (n, v) for n, v in args])
         return self.server.perform(req)
     def _submitbatch(self, cmds):
         req = []
         for name, args in cmds:
             args = ','.join(n + '=' + escapearg(v) for n, v in args)
             req.append(name + ':' + args)
         req = ';'.join(req)
         res = self._submitone('batch', [('cmds', req,)])
         return res.split(';')
 
     def batch(self):
         return remotebatch(self)
 
     @batchable
     def foo(self, one, two=None):
         if not one:
             yield "Nope", None
         encargs = [('one', mangle(one),), ('two', mangle(two),)]
         encresref = future()
         yield encargs, encresref
         yield unmangle(encresref.value)
 
     @batchable
     def bar(self, b, a):
         encresref = future()
         yield [('b', mangle(b),), ('a', mangle(a),)], encresref
         yield unmangle(encresref.value)
 
     # greet is coded directly. It therefore does not support batching. If it
     # does appear in a batch, the batch is split around greet, and the call to
     # greet is done in its own roundtrip.
     def greet(self, name=None):
         return unmangle(self._submitone('greet', [('name', mangle(name),)]))
 
 # demo remote usage
 
 myproxy = remotething(myserver)
 print
 print "== Remote"
 use(myproxy)

tests/test-wireprotocol.py

@@ -1,45 +1,45 b''
 from mercurial import wireproto
 
-class proto():
+class proto(object):
     def __init__(self, args):
         self.args = args
     def getargs(self, spec):
         args = self.args
         args.setdefault('*', {})
         names = spec.split()
         return [args[n] for n in names]
 
 class clientrepo(wireproto.wirerepository):
     def __init__(self, serverrepo):
         self.serverrepo = serverrepo
     def _call(self, cmd, **args):
         return wireproto.dispatch(self.serverrepo, proto(args), cmd)
 
     @wireproto.batchable
     def greet(self, name):
         f = wireproto.future()
         yield wireproto.todict(name=mangle(name)), f
         yield unmangle(f.value)
 
-class serverrepo():
+class serverrepo(object):
     def greet(self, name):
         return "Hello, " + name
 
 def mangle(s):
     return ''.join(chr(ord(c) + 1) for c in s)
 def unmangle(s):
     return ''.join(chr(ord(c) - 1) for c in s)
 
 def greet(repo, proto, name):
     return mangle(repo.greet(unmangle(name)))
 
 wireproto.commands['greet'] = (greet, 'name',)
 
 srv = serverrepo()
 clt = clientrepo(srv)
 
 print clt.greet("Foobar")
 b = clt.batch()
 fs = [b.greet(s) for s in ["Fo, =;o", "Bar"]]
 b.submit()
 print [f.value for f in fs]