pylint, pyflakes: remove unused or duplicate imports

contrib/check-code.py

@@ -1,225 +1,225 b''
 #!/usr/bin/env python
 #
 # check-code - a style and portability checker for Mercurial
 #
 # Copyright 2010 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 sys, re, glob
+import re, glob
 import optparse
 
 def repquote(m):
     t = re.sub(r"\w", "x", m.group('text'))
     t = re.sub(r"[^\sx]", "o", t)
     return m.group('quote') + t + m.group('quote')
 
 def reppython(m):
     comment = m.group('comment')
     if comment:
         return "#" * len(comment)
     return repquote(m)
 
 def repcomment(m):
     return m.group(1) + "#" * len(m.group(2))
 
 def repccomment(m):
     t = re.sub(r"((?<=\n) )|\S", "x", m.group(2))
     return m.group(1) + t + "*/"
 
 def repcallspaces(m):
     t = re.sub(r"\n\s+", "\n", m.group(2))
     return m.group(1) + t
 
 def repinclude(m):
     return m.group(1) + "<foo>"
 
 def rephere(m):
     t = re.sub(r"\S", "x", m.group(2))
     return m.group(1) + t
 
 
 testpats = [
     (r'(pushd|popd)', "don't use 'pushd' or 'popd', use 'cd'"),
     (r'\W\$?\(\([^\)]*\)\)', "don't use (()) or $(()), use 'expr'"),
     (r'^function', "don't use 'function', use old style"),
     (r'grep.*-q', "don't use 'grep -q', redirect to /dev/null"),
     (r'echo.*\\n', "don't use 'echo \\n', use printf"),
     (r'^diff.*-\w*N', "don't use 'diff -N'"),
     (r'(^| )wc[^|]*$', "filter wc output"),
     (r'head -c', "don't use 'head -c', use 'dd'"),
     (r'ls.*-\w*R', "don't use 'ls -R', use 'find'"),
     (r'printf.*\\\d\d\d', "don't use 'printf \NNN', use Python"),
     (r'printf.*\\x', "don't use printf \\x, use Python"),
     (r'\$\(.*\)', "don't use $(expr), use `expr`"),
     (r'rm -rf \*', "don't use naked rm -rf, target a directory"),
     (r'(^|\|\s*)grep (-\w\s+)*[^|]*[(|]\w',
      "use egrep for extended grep syntax"),
     (r'/bin/', "don't use explicit paths for tools"),
     (r'\$PWD', "don't use $PWD, use `pwd`"),
     (r'[^\n]\Z', "no trailing newline"),
     (r'export.*=', "don't export and assign at once"),
     ('^([^"\']|("[^"]*")|(\'[^\']*\'))*\\^', "^ must be quoted"),
 ]
 
 testfilters = [
     (r"( *)(#([^\n]*\S)?)", repcomment),
     (r"<<(\S+)((.|\n)*?\n\1)", rephere),
 ]
 
 pypats = [
     (r'^\s*\t', "don't use tabs"),
     (r'\S;\s*\n', "semicolon"),
     (r'\w,\w', "missing whitespace after ,"),
     (r'\w[+/*\-<>]\w', "missing whitespace in expression"),
     (r'^\s+\w+=\w+[^,)]$', "missing whitespace in assignment"),
     (r'.{85}', "line too long"),
     (r'[^\n]\Z', "no trailing newline"),
 #    (r'^\s+[^_ ][^_. ]+_[^_]+\s*=', "don't use underbars in identifiers"),
 #    (r'\w*[a-z][A-Z]\w*\s*=', "don't use camelcase in identifiers"),
     (r'^\s*(if|while|def|class|except|try)\s[^[]*:\s*[^\]#\s]+',
      "linebreak after :"),
     (r'class\s[^(]:', "old-style class, use class foo(object)"),
     (r'^\s+del\(', "del isn't a function"),
     (r'^\s+except\(', "except isn't a function"),
     (r',]', "unneeded trailing ',' in list"),
 #    (r'class\s[A-Z][^\(]*\((?!Exception)',
 #     "don't capitalize non-exception classes"),
 #    (r'in range\(', "use xrange"),
 #    (r'^\s*print\s+', "avoid using print in core and extensions"),
     (r'[\x80-\xff]', "non-ASCII character literal"),
     (r'("\')\.format\(', "str.format() not available in Python 2.4"),
     (r'^\s*with\s+', "with not available in Python 2.4"),
     (r'^\s*(any|all)\(', "any/all not available in Python 2.4"),
     (r'if\s.*\selse', "if ... else form not available in Python 2.4"),
     (r'([\(\[]\s\S)|(\S\s[\)\]])', "gratuitous whitespace in () or []"),
 #    (r'\s\s=', "gratuitous whitespace before ="),
     (r'[^>< ](\+=|-=|!=|<>|<=|>=|<<=|>>=)\S', "missing whitespace around operator"),
     (r'[^>< ](\+=|-=|!=|<>|<=|>=|<<=|>>=)\s', "missing whitespace around operator"),
     (r'\s(\+=|-=|!=|<>|<=|>=|<<=|>>=)\S', "missing whitespace around operator"),
     (r'[^+=*!<>&| -](\s=|=\s)[^= ]', "wrong whitespace around ="),
     (r'raise Exception', "don't raise generic exceptions"),
     (r'ui\.(status|progress|write|note)\([\'\"]x',
      "warning: unwrapped ui message"),
 ]
 
 pyfilters = [
     (r"""(?msx)(?P<comment>\#.*?$)|
          ((?P<quote>('''|\"\"\"|(?<!')'(?!')|(?<!")"(?!")))
           (?P<text>(([^\\]|\\.)*?))
           (?P=quote))""", reppython),
 ]
 
 cpats = [
     (r'//', "don't use //-style comments"),
     (r'^  ', "don't use spaces to indent"),
     (r'\S\t', "don't use tabs except for indent"),
     (r'(\S\s+|^\s+)\n', "trailing whitespace"),
     (r'.{85}', "line too long"),
     (r'(while|if|do|for)\(', "use space after while/if/do/for"),
     (r'return\(', "return is not a function"),
     (r' ;', "no space before ;"),
     (r'\w+\* \w+', "use int *foo, not int* foo"),
     (r'\([^\)]+\) \w+', "use (int)foo, not (int) foo"),
     (r'\S+ (\+\+|--)', "use foo++, not foo ++"),
     (r'\w,\w', "missing whitespace after ,"),
     (r'\w[+/*]\w', "missing whitespace in expression"),
     (r'^#\s+\w', "use #foo, not # foo"),
     (r'[^\n]\Z', "no trailing newline"),
 ]
 
 cfilters = [
     (r'(/\*)(((\*(?!/))|[^*])*)\*/', repccomment),
     (r'''(?P<quote>(?<!")")(?P<text>([^"]|\\")+)"(?!")''', repquote),
     (r'''(#\s*include\s+<)([^>]+)>''', repinclude),
     (r'(\()([^)]+\))', repcallspaces),
 ]
 
 checks = [
     ('python', r'.*\.(py|cgi)$', pyfilters, pypats),
     ('test script', r'(.*/)?test-[^.~]*$', testfilters, testpats),
     ('c', r'.*\.c$', cfilters, cpats),
 ]
 
 class norepeatlogger(object):
     def __init__(self):
         self._lastseen = None
 
     def log(self, fname, lineno, line, msg):
         """print error related a to given line of a given file.
 
         The faulty line will also be printed but only once in the case
         of multiple errors.
 
         :fname: filename
         :lineno: line number
         :line: actual content of the line
         :msg: error message
         """
         msgid = fname, lineno, line
         if msgid != self._lastseen:
             print "%s:%d:" % (fname, lineno)
             print " > %s" % line
             self._lastseen = msgid
         print " " + msg
 
 _defaultlogger = norepeatlogger()
 
 def checkfile(f, logfunc=_defaultlogger.log, maxerr=None, warnings=False):
     """checks style and portability of a given file
 
     :f: filepath
     :logfunc: function used to report error
               logfunc(filename, linenumber, linecontent, errormessage)
     :maxerr: number of error to display before arborting.
              Set to None (default) to report all errors
 
     return True if no error is found, False otherwise.
     """
     result = True
     for name, match, filters, pats in checks:
         fc = 0
         if not re.match(match, f):
             continue
         pre = post = open(f).read()
         if "no-" + "check-code" in pre:
             break
         for p, r in filters:
             post = re.sub(p, r, post)
         # print post # uncomment to show filtered version
         z = enumerate(zip(pre.splitlines(), post.splitlines(True)))
         for n, l in z:
             if "check-code" + "-ignore" in l[0]:
                 continue
             for p, msg in pats:
                 if not warnings and msg.startswith("warning"):
                     continue
                 if re.search(p, l[1]):
                     logfunc(f, n + 1, l[0], msg)
                     fc += 1
                     result = False
             if maxerr is not None and fc >= maxerr:
                 print " (too many errors, giving up)"
                 break
         break
     return result
 
 
 if __name__ == "__main__":
     parser = optparse.OptionParser("%prog [options] [files]")
     parser.add_option("-w", "--warnings", action="store_true",
                       help="include warning-level checks")
     parser.add_option("-p", "--per-file", type="int",
                       help="max warnings per file")
 
     parser.set_defaults(per_file=15, warnings=False)
     (options, args) = parser.parse_args()
 
     if len(args) == 0:
         check = glob.glob("*")
     else:
         check = args
 
     for f in check:
         checkfile(f, maxerr=options.per_file, warnings=options.warnings)

doc/rst2man.py

@@ -1,1114 +1,1109 b''
 #!/usr/bin/env python
 # -*- 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 sys
-import os
-import time
 import re
-from types import ListType
 
-import docutils
-from docutils import nodes, utils, writers, languages
+from docutils import nodes, writers, languages
 import roman
 
 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:
     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
         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:
             enum_style = {
                     'bullet'     : '\\(bu',
                     'emdash'     : '\\(em',
                      }
 
             def __init__(self, style):
                 self._style = style
                 if node.has_key('start'):
                     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 node.has_key('enumtype'):
             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__)
 
 # The following part is taken from the Docutils rst2man.py script:
 if __name__ == "__main__":
     from docutils.core import publish_cmdline, default_description
     description = ("Generates plain unix manual documents.  " +
                    default_description)
     publish_cmdline(writer=Writer(), description=description)
 
 # vim: set fileencoding=utf-8 et ts=4 ai :

hgext/churn.py

@@ -1,188 +1,188 b''
 # churn.py - create a graph of revisions count grouped by template
 #
 # Copyright 2006 Josef "Jeff" Sipek <[e-mail]>
 # Copyright 2008 Alexander Solovyov <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 '''command to display statistics about repository history'''
 
 from mercurial.i18n import _
 from mercurial import patch, cmdutil, util, templater
-import sys, os
+import os
 import time, datetime
 
 def maketemplater(ui, repo, tmpl):
     tmpl = templater.parsestring(tmpl, quoted=False)
     try:
         t = cmdutil.changeset_templater(ui, repo, False, None, None, False)
     except SyntaxError, inst:
         raise util.Abort(inst.args[0])
     t.use_template(tmpl)
     return t
 
 def changedlines(ui, repo, ctx1, ctx2, fns):
     added, removed = 0, 0
     fmatch = cmdutil.matchfiles(repo, fns)
     diff = ''.join(patch.diff(repo, ctx1.node(), ctx2.node(), fmatch))
     for l in diff.split('\n'):
         if l.startswith("+") and not l.startswith("+++ "):
             added += 1
         elif l.startswith("-") and not l.startswith("--- "):
             removed += 1
     return (added, removed)
 
 def countrate(ui, repo, amap, *pats, **opts):
     """Calculate stats"""
     if opts.get('dateformat'):
         def getkey(ctx):
             t, tz = ctx.date()
             date = datetime.datetime(*time.gmtime(float(t) - tz)[:6])
             return date.strftime(opts['dateformat'])
     else:
         tmpl = opts.get('template', '{author|email}')
         tmpl = maketemplater(ui, repo, tmpl)
         def getkey(ctx):
             ui.pushbuffer()
             tmpl.show(ctx)
             return ui.popbuffer()
 
     state = {'count': 0}
     rate = {}
     df = False
     if opts.get('date'):
         df = util.matchdate(opts['date'])
 
     m = cmdutil.match(repo, pats, opts)
     def prep(ctx, fns):
         rev = ctx.rev()
         if df and not df(ctx.date()[0]): # doesn't match date format
             return
 
         key = getkey(ctx)
         key = amap.get(key, key) # alias remap
         if opts.get('changesets'):
             rate[key] = (rate.get(key, (0,))[0] + 1, 0)
         else:
             parents = ctx.parents()
             if len(parents) > 1:
                 ui.note(_('Revision %d is a merge, ignoring...\n') % (rev,))
                 return
 
             ctx1 = parents[0]
             lines = changedlines(ui, repo, ctx1, ctx, fns)
             rate[key] = [r + l for r, l in zip(rate.get(key, (0, 0)), lines)]
 
         state['count'] += 1
         ui.progress(_('analyzing'), state['count'], total=len(repo))
 
     for ctx in cmdutil.walkchangerevs(repo, m, opts, prep):
         continue
 
     ui.progress(_('analyzing'), None)
 
     return rate
 
 
 def churn(ui, repo, *pats, **opts):
     '''histogram of changes to the repository
 
     This command will display a histogram representing the number
     of changed lines or revisions, grouped according to the given
     template. The default template will group changes by author.
     The --dateformat option may be used to group the results by
     date instead.
 
     Statistics are based on the number of changed lines, or
     alternatively the number of matching revisions if the
     --changesets option is specified.
 
     Examples::
 
       # display count of changed lines for every committer
       hg churn -t '{author|email}'
 
       # display daily activity graph
       hg churn -f '%H' -s -c
 
       # display activity of developers by month
       hg churn -f '%Y-%m' -s -c
 
       # display count of lines changed in every year
       hg churn -f '%Y' -s
 
     It is possible to map alternate email addresses to a main address
     by providing a file using the following format::
 
       <alias email> <actual email>
 
     Such a file may be specified with the --aliases option, otherwise
     a .hgchurn file will be looked for in the working directory root.
     '''
     def pad(s, l):
         return (s + " " * l)[:l]
 
     amap = {}
     aliases = opts.get('aliases')
     if not aliases and os.path.exists(repo.wjoin('.hgchurn')):
         aliases = repo.wjoin('.hgchurn')
     if aliases:
         for l in open(aliases, "r"):
             l = l.strip()
             alias, actual = l.split()
             amap[alias] = actual
 
     rate = countrate(ui, repo, amap, *pats, **opts).items()
     if not rate:
         return
 
     sortkey = ((not opts.get('sort')) and (lambda x: -sum(x[1])) or None)
     rate.sort(key=sortkey)
 
     # Be careful not to have a zero maxcount (issue833)
     maxcount = float(max(sum(v) for k, v in rate)) or 1.0
     maxname = max(len(k) for k, v in rate)
 
     ttywidth = util.termwidth()
     ui.debug("assuming %i character terminal\n" % ttywidth)
     width = ttywidth - maxname - 2 - 2 - 2
 
     if opts.get('diffstat'):
         width -= 15
         def format(name, (added, removed)):
             return "%s %15s %s%s\n" % (pad(name, maxname),
                                        '+%d/-%d' % (added, removed),
                                        ui.label('+' * charnum(added),
                                                 'diffstat.inserted'),
                                        ui.label('-' * charnum(removed),
                                                 'diffstat.deleted'))
     else:
         width -= 6
         def format(name, count):
             return "%s %6d %s\n" % (pad(name, maxname), sum(count),
                                     '*' * charnum(sum(count)))
 
     def charnum(count):
         return int(round(count * width / maxcount))
 
     for name, count in rate:
         ui.write(format(name, count))
 
 
 cmdtable = {
     "churn":
         (churn,
          [('r', 'rev', [], _('count rate for the specified revision or range')),
           ('d', 'date', '', _('count rate for revisions matching date spec')),
           ('t', 'template', '{author|email}',
            _('template to group changesets')),
           ('f', 'dateformat', '',
               _('strftime-compatible format for grouping by date')),
           ('c', 'changesets', False, _('count rate by number of changesets')),
           ('s', 'sort', False, _('sort by key (default: sort by count)')),
           ('', 'diffstat', False, _('display added/removed lines separately')),
           ('', 'aliases', '', _('file with email aliases')),
           ],
          _("hg churn [-d DATE] [-r REV] [--aliases FILE] [FILE]")),
 }

mercurial/byterange.py

@@ -1,471 +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
 
-try:
-    from cStringIO import StringIO
-except ImportError, msg:
-    from StringIO import StringIO
-
 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:
     """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/hgweb_mod.py

@@ -1,287 +1,286 b''
 # hgweb/hgweb_mod.py - Web interface for a repository.
 #
 # 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
 from mercurial import ui, hg, hook, error, encoding, templater
 from common import get_mtime, ErrorResponse, permhooks
 from common import HTTP_OK, HTTP_BAD_REQUEST, HTTP_NOT_FOUND, HTTP_SERVER_ERROR
-from common import HTTP_UNAUTHORIZED, HTTP_METHOD_NOT_ALLOWED
 from request import wsgirequest
 import webcommands, protocol, webutil
 
 perms = {
     'changegroup': 'pull',
     'changegroupsubset': 'pull',
     'unbundle': 'push',
     'stream_out': 'pull',
 }
 
 class hgweb(object):
     def __init__(self, repo, name=None):
         if isinstance(repo, str):
             u = ui.ui()
             u.setconfig('ui', 'report_untrusted', 'off')
             u.setconfig('ui', 'interactive', 'off')
             self.repo = hg.repository(u, repo)
         else:
             self.repo = repo
 
         hook.redirect(True)
         self.mtime = -1
         self.reponame = name
         self.archives = 'zip', 'gz', 'bz2'
         self.stripecount = 1
         # a repo owner may set web.templates in .hg/hgrc to get any file
         # readable by the user running the CGI script
         self.templatepath = self.config('web', 'templates')
 
     # The CGI scripts are often run by a user different from the repo owner.
     # Trust the settings from the .hg/hgrc files by default.
     def config(self, section, name, default=None, untrusted=True):
         return self.repo.ui.config(section, name, default,
                                    untrusted=untrusted)
 
     def configbool(self, section, name, default=False, untrusted=True):
         return self.repo.ui.configbool(section, name, default,
                                        untrusted=untrusted)
 
     def configlist(self, section, name, default=None, untrusted=True):
         return self.repo.ui.configlist(section, name, default,
                                        untrusted=untrusted)
 
     def refresh(self, request=None):
         if request:
             self.repo.ui.environ = request.env
         mtime = get_mtime(self.repo.spath)
         if mtime != self.mtime:
             self.mtime = mtime
             self.repo = hg.repository(self.repo.ui, self.repo.root)
             self.maxchanges = int(self.config("web", "maxchanges", 10))
             self.stripecount = int(self.config("web", "stripes", 1))
             self.maxshortchanges = int(self.config("web", "maxshortchanges", 60))
             self.maxfiles = int(self.config("web", "maxfiles", 10))
             self.allowpull = self.configbool("web", "allowpull", True)
             encoding.encoding = self.config("web", "encoding",
                                             encoding.encoding)
 
     def run(self):
         if not os.environ.get('GATEWAY_INTERFACE', '').startswith("CGI/1."):
             raise RuntimeError("This function is only intended to be "
                                "called while running as a CGI script.")
         import mercurial.hgweb.wsgicgi as wsgicgi
         wsgicgi.launch(self)
 
     def __call__(self, env, respond):
         req = wsgirequest(env, respond)
         return self.run_wsgi(req)
 
     def run_wsgi(self, req):
 
         self.refresh(req)
 
         # work with CGI variables to create coherent structure
         # use SCRIPT_NAME, PATH_INFO and QUERY_STRING as well as our REPO_NAME
 
         req.url = req.env['SCRIPT_NAME']
         if not req.url.endswith('/'):
             req.url += '/'
         if 'REPO_NAME' in req.env:
             req.url += req.env['REPO_NAME'] + '/'
 
         if 'PATH_INFO' in req.env:
             parts = req.env['PATH_INFO'].strip('/').split('/')
             repo_parts = req.env.get('REPO_NAME', '').split('/')
             if parts[:len(repo_parts)] == repo_parts:
                 parts = parts[len(repo_parts):]
             query = '/'.join(parts)
         else:
             query = req.env['QUERY_STRING'].split('&', 1)[0]
             query = query.split(';', 1)[0]
 
         # process this if it's a protocol request
         # protocol bits don't need to create any URLs
         # and the clients always use the old URL structure
 
         cmd = req.form.get('cmd', [''])[0]
         if cmd and cmd in protocol.__all__:
             if query:
                 raise ErrorResponse(HTTP_NOT_FOUND)
             try:
                 if cmd in perms:
                     try:
                         self.check_perm(req, perms[cmd])
                     except ErrorResponse, inst:
                         if cmd == 'unbundle':
                             req.drain()
                         raise
                 method = getattr(protocol, cmd)
                 return method(self.repo, req)
             except ErrorResponse, inst:
                 req.respond(inst, protocol.HGTYPE)
                 if not inst.message:
                     return []
                 return '0\n%s\n' % inst.message,
 
         # translate user-visible url structure to internal structure
 
         args = query.split('/', 2)
         if 'cmd' not in req.form and args and args[0]:
 
             cmd = args.pop(0)
             style = cmd.rfind('-')
             if style != -1:
                 req.form['style'] = [cmd[:style]]
                 cmd = cmd[style + 1:]
 
             # avoid accepting e.g. style parameter as command
             if hasattr(webcommands, cmd):
                 req.form['cmd'] = [cmd]
             else:
                 cmd = ''
 
             if cmd == 'static':
                 req.form['file'] = ['/'.join(args)]
             else:
                 if args and args[0]:
                     node = args.pop(0)
                     req.form['node'] = [node]
                 if args:
                     req.form['file'] = args
 
             ua = req.env.get('HTTP_USER_AGENT', '')
             if cmd == 'rev' and 'mercurial' in ua:
                 req.form['style'] = ['raw']
 
             if cmd == 'archive':
                 fn = req.form['node'][0]
                 for type_, spec in self.archive_specs.iteritems():
                     ext = spec[2]
                     if fn.endswith(ext):
                         req.form['node'] = [fn[:-len(ext)]]
                         req.form['type'] = [type_]
 
         # process the web interface request
 
         try:
             tmpl = self.templater(req)
             ctype = tmpl('mimetype', encoding=encoding.encoding)
             ctype = templater.stringify(ctype)
 
             # check read permissions non-static content
             if cmd != 'static':
                 self.check_perm(req, None)
 
             if cmd == '':
                 req.form['cmd'] = [tmpl.cache['default']]
                 cmd = req.form['cmd'][0]
 
             if cmd not in webcommands.__all__:
                 msg = 'no such method: %s' % cmd
                 raise ErrorResponse(HTTP_BAD_REQUEST, msg)
             elif cmd == 'file' and 'raw' in req.form.get('style', []):
                 self.ctype = ctype
                 content = webcommands.rawfile(self, req, tmpl)
             else:
                 content = getattr(webcommands, cmd)(self, req, tmpl)
                 req.respond(HTTP_OK, ctype)
 
             return content
 
         except error.LookupError, err:
             req.respond(HTTP_NOT_FOUND, ctype)
             msg = str(err)
             if 'manifest' not in msg:
                 msg = 'revision not found: %s' % err.name
             return tmpl('error', error=msg)
         except (error.RepoError, error.RevlogError), inst:
             req.respond(HTTP_SERVER_ERROR, ctype)
             return tmpl('error', error=str(inst))
         except ErrorResponse, inst:
             req.respond(inst, ctype)
             return tmpl('error', error=inst.message)
 
     def templater(self, req):
 
         # determine scheme, port and server name
         # this is needed to create absolute urls
 
         proto = req.env.get('wsgi.url_scheme')
         if proto == 'https':
             proto = 'https'
             default_port = "443"
         else:
             proto = 'http'
             default_port = "80"
 
         port = req.env["SERVER_PORT"]
         port = port != default_port and (":" + port) or ""
         urlbase = '%s://%s%s' % (proto, req.env['SERVER_NAME'], port)
         staticurl = self.config("web", "staticurl") or req.url + 'static/'
         if not staticurl.endswith('/'):
             staticurl += '/'
 
         # some functions for the templater
 
         def header(**map):
             yield tmpl('header', encoding=encoding.encoding, **map)
 
         def footer(**map):
             yield tmpl("footer", **map)
 
         def motd(**map):
             yield self.config("web", "motd", "")
 
         # figure out which style to use
 
         vars = {}
         styles = (
             req.form.get('style', [None])[0],
             self.config('web', 'style'),
             'paper',
         )
         style, mapfile = templater.stylemap(styles, self.templatepath)
         if style == styles[0]:
             vars['style'] = style
 
         start = req.url[-1] == '?' and '&' or '?'
         sessionvars = webutil.sessionvars(vars, start)
 
         if not self.reponame:
             self.reponame = (self.config("web", "name")
                              or req.env.get('REPO_NAME')
                              or req.url.strip('/') or self.repo.root)
 
         # create the templater
 
         tmpl = templater.templater(mapfile,
                                    defaults={"url": req.url,
                                              "staticurl": staticurl,
                                              "urlbase": urlbase,
                                              "repo": self.reponame,
                                              "header": header,
                                              "footer": footer,
                                              "motd": motd,
                                              "sessionvars": sessionvars
                                             })
         return tmpl
 
     def archivelist(self, nodeid):
         allowed = self.configlist("web", "allow_archive")
         for i, spec in self.archive_specs.iteritems():
             if i in allowed or self.configbool("web", "allow" + i):
                 yield {"type" : i, "extension" : spec[2], "node" : nodeid}
 
     archive_specs = {
         'bz2': ('application/x-tar', 'tbz2', '.tar.bz2', None),
         'gz': ('application/x-tar', 'tgz', '.tar.gz', None),
         'zip': ('application/zip', 'zip', '.zip', None),
         }
 
     def check_perm(self, req, op):
         for hook in permhooks:
             hook(self, req, op)

mercurial/hgweb/server.py

@@ -1,277 +1,277 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 hg, util, error
+from mercurial import util, error
 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 _hgwebhandler(BaseHTTPServer.BaseHTTPRequestHandler):
 
     url_scheme = 'http'
 
     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 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 StandardError:
             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
         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 _shgwebhandler(_hgwebhandler):
 
     url_scheme = 'https'
 
     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):
         from OpenSSL.SSL import SysCallError
         try:
             super(_shgwebhandler, self).do_write()
         except SysCallError, inst:
             if inst.args[0] != errno.EPIPE:
                 raise
 
     def handle_one_request(self):
         from OpenSSL.SSL import SysCallError, ZeroReturnError
         try:
             super(_shgwebhandler, self).handle_one_request()
         except (SysCallError, ZeroReturnError):
             self.close_connection = True
             pass
 
 try:
     from threading import activeCount
     _mixin = SocketServer.ThreadingMixIn
 except ImportError:
     if hasattr(os, "fork"):
         _mixin = SocketServer.ForkingMixIn
     else:
         class _mixin:
             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
 
         ssl_cert = ui.config('web', 'certificate')
         if ssl_cert:
             try:
                 from OpenSSL import SSL
                 ctx = SSL.Context(SSL.SSLv23_METHOD)
             except ImportError:
                 raise util.Abort(_("SSL support is unavailable"))
             ctx.use_privatekey_file(ssl_cert)
             ctx.use_certificate_file(ssl_cert)
             sock = socket.socket(self.address_family, self.socket_type)
             self.socket = SSL.Connection(ctx, sock)
             self.server_bind()
             self.server_activate()
 
         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'):
         handler = _shgwebhandler
     else:
         handler = _hgwebhandler
 
     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 = int(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/patch.py

@@ -1,1697 +1,1697 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.
 
 from i18n import _
 from node import hex, nullid, short
 import base85, cmdutil, mdiff, util, diffhelpers, copies
 import cStringIO, email.Parser, os, re
-import sys, tempfile, zlib
+import tempfile, zlib
 
 gitre = re.compile('diff --git a/(.*) b/(.*)')
 
 class PatchError(Exception):
     pass
 
 class NoHunks(PatchError):
     pass
 
 # helper functions
 
 def copyfile(src, dst, basedir):
     abssrc, absdst = [util.canonpath(basedir, basedir, x) for x in [src, dst]]
     if os.path.exists(absdst):
         raise util.Abort(_("cannot create %s: destination already exists") %
                          dst)
 
     dstdir = os.path.dirname(absdst)
     if dstdir and not os.path.isdir(dstdir):
         try:
             os.makedirs(dstdir)
         except IOError:
             raise util.Abort(
                 _("cannot create %s: unable to create destination directory")
                 % dst)
 
     util.copyfile(abssrc, absdst)
 
 # 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, 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
                 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'):
                         ui.debug('patch generated by hg export\n')
                         hgpatch = True
                         # drop earlier commit message content
                         cfp.seek(0)
                         cfp.truncate()
                         subject = None
                     elif hgpatch:
                         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 line == '---' and gitsendmail:
                         ignoretext = True
                     if not line.startswith('# ') 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
 
 GP_PATCH  = 1 << 0  # we have to run patch
 GP_FILTER = 1 << 1  # there's some copy/rename operation
 GP_BINARY = 1 << 2  # there's a binary patch
 
 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.lineno = 0
         self.binary = False
 
     def setmode(self, mode):
         islink = mode & 020000
         isexec = mode & 0100
         self.mode = (islink, isexec)
 
 def readgitpatch(lr):
     """extract git-style metadata about patches from <patchname>"""
 
     # Filter patch for git information
     gp = None
     gitpatches = []
     # Can have a git patch with only metadata, causing patch to complain
     dopatch = 0
 
     lineno = 0
     for line in lr:
         lineno += 1
         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)
                 gp.lineno = lineno
         elif gp:
             if line.startswith('--- '):
                 if gp.op in ('COPY', 'RENAME'):
                     dopatch |= GP_FILTER
                 gitpatches.append(gp)
                 gp = None
                 dopatch |= GP_PATCH
                 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'
                 # is the deleted file a symlink?
                 gp.setmode(int(line[-6:], 8))
             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'):
                 dopatch |= GP_BINARY
                 gp.binary = True
     if gp:
         gitpatches.append(gp)
 
     if not gitpatches:
         dopatch = GP_PATCH
 
     return (dopatch, gitpatches)
 
 class linereader(object):
     # simple class to allow pushing lines back into the input stream
     def __init__(self, fp, textmode=False):
         self.fp = fp
         self.buf = []
         self.textmode = textmode
         self.eol = None
 
     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
         l = self.fp.readline()
         if not self.eol:
             if l.endswith('\r\n'):
                 self.eol = '\r\n'
             elif l.endswith('\n'):
                 self.eol = '\n'
         if self.textmode and l.endswith('\r\n'):
             l = l[:-2] + '\n'
         return l
 
     def __iter__(self):
         while 1:
             l = self.readline()
             if not l:
                 break
             yield l
 
 # @@ -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, fname, opener, missing=False, eolmode='strict'):
         self.fname = fname
         self.eolmode = eolmode
         self.eol = None
         self.opener = opener
         self.ui = ui
         self.lines = []
         self.exists = False
         self.missing = missing
         if not missing:
             try:
                 self.lines = self.readlines(fname)
                 self.exists = True
             except IOError:
                 pass
         else:
             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 readlines(self, fname):
         if os.path.islink(fname):
             return [os.readlink(fname)]
         fp = self.opener(fname, 'r')
         try:
             lr = linereader(fp, self.eolmode != 'strict')
             lines = list(lr)
             self.eol = lr.eol
             return lines
         finally:
             fp.close()
 
     def writelines(self, fname, lines):
         # Ensure supplied data ends in fname, being a regular file or
         # a symlink. updatedir() will -too magically- take care of
         # setting it to the proper type afterwards.
         islink = os.path.islink(fname)
         if islink:
             fp = cStringIO.StringIO()
         else:
             fp = self.opener(fname, 'w')
         try:
             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':
                 for l in lines:
                     if l and l[-1] == '\n':
                         l = l[:-1] + eol
                     fp.write(l)
             else:
                 fp.writelines(lines)
             if islink:
                 self.opener.symlink(fp.getvalue(), fname)
         finally:
             fp.close()
 
     def unlink(self, fname):
         os.unlink(fname)
 
     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 hashlines(self):
         self.hash = {}
         for x, s in enumerate(self.lines):
             self.hash.setdefault(s, []).append(x)
 
     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
 
         fname = self.fname + ".rej"
         self.ui.warn(
             _("%d out of %d hunks FAILED -- saving rejects to file %s\n") %
             (len(self.rej), self.hunks, fname))
 
         def rejlines():
             base = os.path.basename(self.fname)
             yield "--- %s\n+++ %s\n" % (base, base)
             for x in self.rej:
                 for l in x.hunk:
                     yield l
                     if l[-1] != '\n':
                         yield "\n\ No newline at end of file\n"
 
         self.writelines(fname, rejlines())
 
     def write(self, dest=None):
         if not self.dirty:
             return
         if not dest:
             dest = self.fname
         self.writelines(dest, self.lines)
 
     def close(self):
         self.write()
         self.write_rej()
 
     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 h.createfile():
             self.ui.warn(_("file %s already exists\n") % self.fname)
             self.rej.append(h)
             return -1
 
         if isinstance(h, binhunk):
             if h.rmfile():
                 self.unlink(self.fname)
             else:
                 self.lines[:] = h.new()
                 self.offset += len(h.new())
                 self.dirty = 1
             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 h.rmfile():
                 self.unlink(self.fname)
             else:
                 self.lines[start : start + h.lena] = h.new()
                 self.offset += h.lenb - h.lena
                 self.dirty = 1
             return 0
 
         # ok, we couldn't match the hunk.  Lets look for offsets and fuzz it
         self.hashlines()
         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 = 1
                         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
 
 class hunk(object):
     def __init__(self, desc, num, lr, context, create=False, remove=False):
         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)
         self.create = create
         self.remove = remove and not create
 
     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, False, False)
         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
         nh.create = self.create
         nh.remove = self.remove
         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
 
     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('---'):
                 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('\ '):
                 s = self.b[-1][:-1]
                 self.b[-1] = s
                 self.hunk[hunki - 1] = s
                 continue
             if not l:
                 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:
                 # this can happen when the hunk does not add any lines
                 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
 
     def fix_newline(self):
         diffhelpers.fix_newline(self.hunk, self.a, self.b)
 
     def complete(self):
         return len(self.a) == self.lena and len(self.b) == self.lenb
 
     def createfile(self):
         return self.starta == 0 and self.lena == 0 and self.create
 
     def rmfile(self):
         return self.startb == 0 and self.lenb == 0 and self.remove
 
     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:
     'A binary patch file. Only understands literals so far.'
     def __init__(self, gitpatch):
         self.gitpatch = gitpatch
         self.text = None
         self.hunk = ['GIT binary patch\n']
 
     def createfile(self):
         return self.gitpatch.op in ('ADD', 'RENAME', 'COPY')
 
     def rmfile(self):
         return self.gitpatch.op == 'DELETE'
 
     def complete(self):
         return self.text is not None
 
     def new(self):
         return [self.text]
 
     def extract(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 selectfile(afile_orig, bfile_orig, hunk, strip):
     def pathstrip(path, count=1):
         pathlen = len(path)
         i = 0
         if count == 0:
             return '', path.rstrip()
         while count > 0:
             i = path.find('/', i)
             if i == -1:
                 raise PatchError(_("unable to strip away %d dirs from %s") %
                                  (count, 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()
 
     nulla = afile_orig == "/dev/null"
     nullb = bfile_orig == "/dev/null"
     abase, afile = pathstrip(afile_orig, strip)
     gooda = not nulla and util.lexists(afile)
     bbase, bfile = pathstrip(bfile_orig, strip)
     if afile == bfile:
         goodb = gooda
     else:
         goodb = not nullb and os.path.exists(bfile)
     createfunc = hunk.createfile
     missing = not goodb and not gooda and not createfunc()
 
     # some diff programs apparently produce create 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):
         # this isn't very pretty
         hunk.create = True
         if createfunc():
             missing = False
         else:
             hunk.create = 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"))
 
     return fname, missing
 
 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, lr.textmode)
     gitlr.push(firstline)
     (dopatch, gitpatches) = readgitpatch(gitlr)
     fp.seek(pos)
     return dopatch, gitpatches
 
 def iterhunks(ui, fp, sourcefile=None):
     """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.
     """
     changed = {}
     current_hunk = None
     afile = ""
     bfile = ""
     state = None
     hunknum = 0
     emitfile = False
     git = False
 
     # our states
     BFILE = 1
     context = None
     lr = linereader(fp)
     # gitworkdone is True if a git operation (copy, rename, ...) was
     # performed already for the current file. Useful when the file
     # section may have no hunk.
     gitworkdone = False
     empty = None
 
     while True:
         newfile = newgitfile = False
         x = lr.readline()
         if not x:
             break
         if current_hunk:
             if x.startswith('\ '):
                 current_hunk.fix_newline()
             yield 'hunk', current_hunk
             current_hunk = None
             empty = False
         if ((sourcefile or state == BFILE) and ((not context and x[0] == '@') or
             ((context is not False) and x.startswith('***************')))):
             try:
                 if context is None and x.startswith('***************'):
                     context = True
                 gpatch = changed.get(bfile)
                 create = afile == '/dev/null' or gpatch and gpatch.op == 'ADD'
                 remove = bfile == '/dev/null' or gpatch and gpatch.op == 'DELETE'
                 current_hunk = hunk(x, hunknum + 1, lr, context, create, remove)
             except PatchError, err:
                 ui.debug(err)
                 current_hunk = None
                 continue
             hunknum += 1
             if emitfile:
                 emitfile = False
                 yield 'file', (afile, bfile, current_hunk)
                 empty = False
         elif state == BFILE and x.startswith('GIT binary patch'):
             current_hunk = binhunk(changed[bfile])
             hunknum += 1
             if emitfile:
                 emitfile = False
                 yield 'file', ('a/' + afile, 'b/' + bfile, current_hunk)
                 empty = False
             current_hunk.extract(lr)
         elif x.startswith('diff --git'):
             # check for git diff, scanning the whole patch file if needed
             m = gitre.match(x)
             gitworkdone = False
             if m:
                 afile, bfile = m.group(1, 2)
                 if not git:
                     git = True
                     gitpatches = scangitpatch(lr, x)[1]
                     yield 'git', gitpatches
                     for gp in gitpatches:
                         changed[gp.path] = gp
                 # else error?
                 # copy/rename + modify should modify target, not source
                 gp = changed.get(bfile)
                 if gp and (gp.op in ('COPY', 'DELETE', 'RENAME', 'ADD')
                            or gp.mode):
                     afile = bfile
                     gitworkdone = True
                 newgitfile = 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:
             if empty:
                 raise NoHunks
             empty = not gitworkdone
             gitworkdone = False
 
         if newgitfile or newfile:
             emitfile = True
             state = BFILE
             hunknum = 0
     if current_hunk:
         if current_hunk.complete():
             yield 'hunk', current_hunk
             empty = False
         else:
             raise PatchError(_("malformed patch %s %s") % (afile,
                              current_hunk.desc))
 
     if (empty is None and not gitworkdone) or empty:
         raise NoHunks
 
 def applydiff(ui, fp, changed, strip=1, sourcefile=None, eolmode='strict'):
     """
     Reads a patch from fp and tries to apply it.
 
     The dict 'changed' is filled in with all of the filenames changed
     by the patch. 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'.
     """
     rejects = 0
     err = 0
     current_file = None
     gitpatches = None
     opener = util.opener(os.getcwd())
 
     def closefile():
         if not current_file:
             return 0
         current_file.close()
         return len(current_file.rej)
 
     for state, values in iterhunks(ui, fp, sourcefile):
         if state == 'hunk':
             if not current_file:
                 continue
             current_hunk = values
             ret = current_file.apply(current_hunk)
             if ret >= 0:
                 changed.setdefault(current_file.fname, None)
                 if ret > 0:
                     err = 1
         elif state == 'file':
             rejects += closefile()
             afile, bfile, first_hunk = values
             try:
                 if sourcefile:
                     current_file = patchfile(ui, sourcefile, opener,
                                              eolmode=eolmode)
                 else:
                     current_file, missing = selectfile(afile, bfile,
                                                        first_hunk, strip)
                     current_file = patchfile(ui, current_file, opener,
                                              missing, eolmode)
             except PatchError, err:
                 ui.warn(str(err) + '\n')
                 current_file, current_hunk = None, None
                 rejects += 1
                 continue
         elif state == 'git':
             gitpatches = values
             cwd = os.getcwd()
             for gp in gitpatches:
                 if gp.op in ('COPY', 'RENAME'):
                     copyfile(gp.oldpath, gp.path, cwd)
                 changed[gp.path] = gp
         else:
             raise util.Abort(_('unsupported parser state: %s') % state)
 
     rejects += closefile()
 
     if rejects:
         return -1
     return err
 
 def updatedir(ui, repo, patches, similarity=0):
     '''Update dirstate after patch application according to metadata'''
     if not patches:
         return
     copies = []
     removes = set()
     cfiles = patches.keys()
     cwd = repo.getcwd()
     if cwd:
         cfiles = [util.pathto(repo.root, cwd, f) for f in patches.keys()]
     for f in patches:
         gp = patches[f]
         if not gp:
             continue
         if gp.op == 'RENAME':
             copies.append((gp.oldpath, gp.path))
             removes.add(gp.oldpath)
         elif gp.op == 'COPY':
             copies.append((gp.oldpath, gp.path))
         elif gp.op == 'DELETE':
             removes.add(gp.path)
     for src, dst in copies:
         repo.copy(src, dst)
     if (not similarity) and removes:
         repo.remove(sorted(removes), True)
     for f in patches:
         gp = patches[f]
         if gp and gp.mode:
             islink, isexec = gp.mode
             dst = repo.wjoin(gp.path)
             # patch won't create empty files
             if gp.op == 'ADD' and not os.path.exists(dst):
                 flags = (isexec and 'x' or '') + (islink and 'l' or '')
                 repo.wwrite(gp.path, '', flags)
             elif gp.op != 'DELETE':
                 util.set_flags(dst, islink, isexec)
     cmdutil.addremove(repo, cfiles, similarity=similarity)
     files = patches.keys()
     files.extend([r for r in removes if r not in files])
     return sorted(files)
 
 def externalpatch(patcher, args, patchname, ui, strip, cwd, files):
     """use <patcher> to apply <patchname> to the working directory.
     returns whether patch was applied with fuzz factor."""
 
     fuzz = False
     if cwd:
         args.append('-d %s' % util.shellquote(cwd))
     fp = util.popen('%s %s -p%d < %s' % (patcher, ' '.join(args), strip,
                                        util.shellquote(patchname)))
 
     for line in fp:
         line = line.rstrip()
         ui.note(line + '\n')
         if line.startswith('patching file '):
             pf = util.parse_patch_output(line)
             printed_file = False
             files.setdefault(pf, None)
         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')
     code = fp.close()
     if code:
         raise PatchError(_("patch command failed: %s") %
                          util.explain_exit(code)[0])
     return fuzz
 
 def internalpatch(patchobj, ui, strip, cwd, files=None, eolmode='strict'):
     """use builtin patch to apply <patchobj> to the working directory.
     returns whether patch was applied with fuzz factor."""
 
     if files is None:
         files = {}
     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()
 
     try:
         fp = open(patchobj, 'rb')
     except TypeError:
         fp = patchobj
     if cwd:
         curdir = os.getcwd()
         os.chdir(cwd)
     try:
         ret = applydiff(ui, fp, files, strip=strip, eolmode=eolmode)
     finally:
         if cwd:
             os.chdir(curdir)
         if fp != patchobj:
             fp.close()
     if ret < 0:
         raise PatchError
     return ret > 0
 
 def patch(patchname, ui, strip=1, cwd=None, files=None, eolmode='strict'):
     """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')
     args = []
     if files is None:
         files = {}
     try:
         if patcher:
             return externalpatch(patcher, args, patchname, ui, strip, cwd,
                                  files)
         else:
             try:
                 return internalpatch(patchname, ui, strip, cwd, files, eolmode)
             except NoHunks:
                 ui.warn(_('internal patcher failed\n'
                           'please report details to '
                           'http://mercurial.selenic.com/bts/\n'
                           'or [e-mail]\n'))
                 patcher = (util.find_exe('gpatch') or util.find_exe('patch')
                            or 'patch')
                 ui.debug('no valid hunks found; trying with %r instead\n' %
                          patcher)
                 if util.needbinarypatch():
                     args.append('--binary')
                 return externalpatch(patcher, args, patchname, ui, strip, cwd,
                                      files)
     except PatchError, err:
         s = str(err)
         if s:
             raise util.Abort(s)
         else:
             raise util.Abort(_('patch failed to apply'))
 
 def b85diff(to, tn):
     '''print base85-encoded binary diff'''
     def gitindex(text):
         if not text:
             return '0' * 40
         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):
     '''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.
     '''
 
     if opts is None:
         opts = mdiff.defaultopts
 
     if not node1 and not node2:
         node1 = repo.dirstate.parents()[0]
 
     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)
     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):
 
     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, a))
                         header.append('%s to %s\n' % (op, 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)
                 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:
                     # 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, a, 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()),
                                     a, b, revs, opts=opts)
             if header and (text or len(header) > 1):
                 yield ''.join(header)
             if text:
                 yield text
 
 def diffstatdata(lines):
     filename, adds, removes = None, 0, 0
     for line in lines:
         if line.startswith('diff'):
             if filename:
                 isbinary = adds == 0 and removes == 0
                 yield (filename, adds, removes, isbinary)
             # set numbers to 0 anyway when starting new file
             adds, removes = 0, 0
             if line.startswith('diff --git'):
                 filename = gitre.search(line).group(1)
             else:
                 # format: "diff -r ... -r ... filename"
                 filename = line.split(None, 5)[-1]
         elif line.startswith('+') and not line.startswith('+++'):
             adds += 1
         elif line.startswith('-') and not line.startswith('---'):
             removes += 1
     if filename:
         isbinary = adds == 0 and removes == 0
         yield (filename, adds, removes, isbinary)
 
 def diffstat(lines, width=80, git=False):
     output = []
     stats = list(diffstatdata(lines))
 
     maxtotal, maxname = 0, 0
     totaladds, totalremoves = 0, 0
     hasbinary = False
     for filename, adds, removes, isbinary in stats:
         totaladds += adds
         totalremoves += removes
         maxname = max(maxname, len(filename))
         maxtotal = max(maxtotal, adds + removes)
         if isbinary:
             hasbinary = True
 
     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\n' % (maxname, filename, countwidth,
                                                count, pluses, minuses))
 
     if stats:
         output.append(_(' %d files changed, %d insertions(+), %d deletions(-)\n')
                       % (len(stats), totaladds, totalremoves))
 
     return ''.join(output)
 
 def diffstatui(*args, **kw):
     '''like diffstat(), but yields 2-tuples of (output, label) for
     ui.write()
     '''
 
     for line in diffstat(*args, **kw).splitlines():
         if line and line[-1] in '+-':
             name, graph = line.rsplit(' ', 1)
             yield (name + ' ', '')
             m = re.search(r'\++', graph)
             if m:
                 yield (m.group(0), 'diffstat.inserted')
             m = re.search(r'-+', graph)
             if m:
                 yield (m.group(0), 'diffstat.deleted')
         else:
             yield (line, '')
         yield ('\n', '')

mercurial/streamclone.py

@@ -1,70 +1,69 b''
 # streamclone.py - streaming clone server support for mercurial
 #
 # Copyright 2006 Vadim Gelfer <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 import util, error
-from i18n import _
 
 from mercurial import store
 
 class StreamException(Exception):
     def __init__(self, code):
         Exception.__init__(self)
         self.code = code
     def __str__(self):
         return '%i\n' % self.code
 
 # if server supports streaming clone, it advertises "stream"
 # capability with value that is version+flags of repo it is serving.
 # client only streams if it can read that repo format.
 
 # stream file format is simple.
 #
 # server writes out line that says how many files, how many total
 # bytes.  separator is ascii space, byte counts are strings.
 #
 # then for each file:
 #
 #   server writes out line that says filename, how many bytes in
 #   file.  separator is ascii nul, byte count is string.
 #
 #   server writes out raw file data.
 
 def allowed(ui):
     return ui.configbool('server', 'uncompressed', True, untrusted=True)
 
 def stream_out(repo):
     '''stream out all metadata files in repository.
     writes to file-like object, must support write() and optional flush().'''
 
     if not allowed(repo.ui):
         raise StreamException(1)
 
     entries = []
     total_bytes = 0
     try:
         # get consistent snapshot of repo, lock during scan
         lock = repo.lock()
         try:
             repo.ui.debug('scanning\n')
             for name, ename, size in repo.store.walk():
                 entries.append((name, size))
                 total_bytes += size
         finally:
             lock.release()
     except error.LockError:
         raise StreamException(2)
 
     yield '0\n'
     repo.ui.debug('%d files, %d bytes to transfer\n' %
                   (len(entries), total_bytes))
     yield '%d %d\n' % (len(entries), total_bytes)
     for name, size in entries:
         repo.ui.debug('sending %s (%d bytes)\n' % (name, size))
         # partially encode name over the wire for backwards compat
         yield '%s\0%d\n' % (store.encodedir(name), size)
         for chunk in util.filechunkiter(repo.sopener(name), limit=size):
             yield chunk

setup.py

@@ -1,314 +1,313 b''
 #!/usr/bin/env python
 #
 # This is the mercurial setup script.
 #
 # 'python setup.py install', or
 # 'python setup.py --help' for more options
 
 import sys
 if not hasattr(sys, 'version_info') or sys.version_info < (2, 4, 0, 'final'):
     raise SystemExit("Mercurial requires Python 2.4 or later.")
 
 # Solaris Python packaging brain damage
 try:
     import hashlib
     sha = hashlib.sha1()
 except:
     try:
         import sha
     except:
         raise SystemExit(
             "Couldn't import standard hashlib (incomplete Python install).")
 
 try:
     import zlib
 except:
     raise SystemExit(
         "Couldn't import standard zlib (incomplete Python install).")
 
 try:
     import bz2
 except:
     raise SystemExit(
         "Couldn't import standard bz2 (incomplete Python install).")
 
 import os, subprocess, time
 import shutil
 import tempfile
 from distutils.core import setup, Extension
 from distutils.dist import Distribution
-from distutils.command.install_data import install_data
 from distutils.command.build import build
 from distutils.command.build_py import build_py
 from distutils.spawn import spawn, find_executable
 from distutils.ccompiler import new_compiler
 
 scripts = ['hg']
 if os.name == 'nt':
     scripts.append('contrib/win32/hg.bat')
 
 # simplified version of distutils.ccompiler.CCompiler.has_function
 # that actually removes its temporary files.
 def hasfunction(cc, funcname):
     tmpdir = tempfile.mkdtemp(prefix='hg-install-')
     devnull = oldstderr = None
     try:
         try:
             fname = os.path.join(tmpdir, 'funcname.c')
             f = open(fname, 'w')
             f.write('int main(void) {\n')
             f.write('    %s();\n' % funcname)
             f.write('}\n')
             f.close()
             # Redirect stderr to /dev/null to hide any error messages
             # from the compiler.
             # This will have to be changed if we ever have to check
             # for a function on Windows.
             devnull = open('/dev/null', 'w')
             oldstderr = os.dup(sys.stderr.fileno())
             os.dup2(devnull.fileno(), sys.stderr.fileno())
             objects = cc.compile([fname], output_dir=tmpdir)
             cc.link_executable(objects, os.path.join(tmpdir, "a.out"))
         except:
             return False
         return True
     finally:
         if oldstderr is not None:
             os.dup2(oldstderr, sys.stderr.fileno())
         if devnull is not None:
             devnull.close()
         shutil.rmtree(tmpdir)
 
 # py2exe needs to be installed to work
 try:
     import py2exe
     py2exeloaded = True
 
     # Help py2exe to find win32com.shell
     try:
         import modulefinder
         import win32com
         for p in win32com.__path__[1:]: # Take the path to win32comext
             modulefinder.AddPackagePath("win32com", p)
         pn = "win32com.shell"
         __import__(pn)
         m = sys.modules[pn]
         for p in m.__path__[1:]:
             modulefinder.AddPackagePath(pn, p)
     except ImportError:
         pass
 
 except ImportError:
     py2exeloaded = False
     pass
 
 def runcmd(cmd, env):
     p = subprocess.Popen(cmd, stdout=subprocess.PIPE,
                          stderr=subprocess.PIPE, env=env)
     out, err = p.communicate()
     # If root is executing setup.py, but the repository is owned by
     # another user (as in "sudo python setup.py install") we will get
     # trust warnings since the .hg/hgrc file is untrusted. That is
     # fine, we don't want to load it anyway.  Python may warn about
     # a missing __init__.py in mercurial/locale, we also ignore that.
     err = [e for e in err.splitlines()
            if not e.startswith('Not trusting file') \
               and not e.startswith('warning: Not importing')]
     if err:
         return ''
     return out
 
 version = ''
 
 if os.path.isdir('.hg'):
     # Execute hg out of this directory with a custom environment which
     # includes the pure Python modules in mercurial/pure. We also take
     # care to not use any hgrc files and do no localization.
     pypath = ['mercurial', os.path.join('mercurial', 'pure')]
     env = {'PYTHONPATH': os.pathsep.join(pypath),
            'HGRCPATH': '',
            'LANGUAGE': 'C'}
     if 'LD_LIBRARY_PATH' in os.environ:
         env['LD_LIBRARY_PATH'] = os.environ['LD_LIBRARY_PATH']
     if 'SystemRoot' in os.environ:
         # Copy SystemRoot into the custom environment for Python 2.6
         # under Windows. Otherwise, the subprocess will fail with
         # error 0xc0150004. See: http://bugs.python.org/issue3440
         env['SystemRoot'] = os.environ['SystemRoot']
     cmd = [sys.executable, 'hg', 'id', '-i', '-t']
     l = runcmd(cmd, env).split()
     while len(l) > 1 and l[-1][0].isalpha(): # remove non-numbered tags
         l.pop()
     if len(l) > 1: # tag found
         version = l[-1]
         if l[0].endswith('+'): # propagate the dirty status to the tag
             version += '+'
     elif len(l) == 1: # no tag found
         cmd = [sys.executable, 'hg', 'parents', '--template',
                '{latesttag}+{latesttagdistance}-']
         version = runcmd(cmd, env) + l[0]
     if version.endswith('+'):
         version += time.strftime('%Y%m%d')
 elif os.path.exists('.hg_archival.txt'):
     kw = dict([[t.strip() for t in l.split(':', 1)]
                for l in open('.hg_archival.txt')])
     if 'tag' in kw:
         version =  kw['tag']
     elif 'latesttag' in kw:
         version = '%(latesttag)s+%(latesttagdistance)s-%(node).12s' % kw
     else:
         version = kw.get('node', '')[:12]
 
 if version:
     f = open("mercurial/__version__.py", "w")
     f.write('# this file is autogenerated by setup.py\n')
     f.write('version = "%s"\n' % version)
     f.close()
 
 
 try:
     from mercurial import __version__
     version = __version__.version
 except ImportError:
     version = 'unknown'
 
 class hgbuildmo(build):
 
     description = "build translations (.mo files)"
 
     def run(self):
         if not find_executable('msgfmt'):
             self.warn("could not find msgfmt executable, no translations "
                      "will be built")
             return
 
         podir = 'i18n'
         if not os.path.isdir(podir):
             self.warn("could not find %s/ directory" % podir)
             return
 
         join = os.path.join
         for po in os.listdir(podir):
             if not po.endswith('.po'):
                 continue
             pofile = join(podir, po)
             modir = join('locale', po[:-3], 'LC_MESSAGES')
             mofile = join(modir, 'hg.mo')
             mobuildfile = join('mercurial', mofile)
             cmd = ['msgfmt', '-v', '-o', mobuildfile, pofile]
             if sys.platform != 'sunos5':
                 # msgfmt on Solaris does not know about -c
                 cmd.append('-c')
             self.mkpath(join('mercurial', modir))
             self.make_file([pofile], mobuildfile, spawn, (cmd,))
 
 # Insert hgbuildmo first so that files in mercurial/locale/ are found
 # when build_py is run next.
 build.sub_commands.insert(0, ('build_mo', None))
 
 Distribution.pure = 0
 Distribution.global_options.append(('pure', None, "use pure (slow) Python "
                                     "code instead of C extensions"))
 
 class hgbuildpy(build_py):
 
     def finalize_options(self):
         build_py.finalize_options(self)
 
         if self.distribution.pure:
             if self.py_modules is None:
                 self.py_modules = []
             for ext in self.distribution.ext_modules:
                 if ext.name.startswith("mercurial."):
                     self.py_modules.append("mercurial.pure.%s" % ext.name[10:])
             self.distribution.ext_modules = []
 
     def find_modules(self):
         modules = build_py.find_modules(self)
         for module in modules:
             if module[0] == "mercurial.pure":
                 if module[1] != "__init__":
                     yield ("mercurial", module[1], module[2])
             else:
                 yield module
 
 cmdclass = {'build_mo': hgbuildmo,
             'build_py': hgbuildpy}
 
 packages = ['mercurial', 'mercurial.hgweb', 'hgext', 'hgext.convert',
             'hgext.highlight', 'hgext.zeroconf']
 
 pymodules = []
 
 extmodules = [
     Extension('mercurial.base85', ['mercurial/base85.c']),
     Extension('mercurial.bdiff', ['mercurial/bdiff.c']),
     Extension('mercurial.diffhelpers', ['mercurial/diffhelpers.c']),
     Extension('mercurial.mpatch', ['mercurial/mpatch.c']),
     Extension('mercurial.parsers', ['mercurial/parsers.c']),
     ]
 
 # disable osutil.c under windows + python 2.4 (issue1364)
 if sys.platform == 'win32' and sys.version_info < (2, 5, 0, 'final'):
     pymodules.append('mercurial.pure.osutil')
 else:
     extmodules.append(Extension('mercurial.osutil', ['mercurial/osutil.c']))
 
 if sys.platform == 'linux2' and os.uname()[2] > '2.6':
     # The inotify extension is only usable with Linux 2.6 kernels.
     # You also need a reasonably recent C library.
     cc = new_compiler()
     if hasfunction(cc, 'inotify_add_watch'):
         extmodules.append(Extension('hgext.inotify.linux._inotify',
                                      ['hgext/inotify/linux/_inotify.c']))
         packages.extend(['hgext.inotify', 'hgext.inotify.linux'])
 
 packagedata = {'mercurial': ['locale/*/LC_MESSAGES/hg.mo',
                              'help/*.txt']}
 
 def ordinarypath(p):
     return p and p[0] != '.' and p[-1] != '~'
 
 for root in ('templates',):
     for curdir, dirs, files in os.walk(os.path.join('mercurial', root)):
         curdir = curdir.split(os.sep, 1)[1]
         dirs[:] = filter(ordinarypath, dirs)
         for f in filter(ordinarypath, files):
             f = os.path.join(curdir, f)
             packagedata['mercurial'].append(f)
 
 datafiles = []
 setupversion = version
 extra = {}
 
 if py2exeloaded:
     extra['console'] = [
         {'script':'hg',
          'copyright':'Copyright (C) 2005-2010 Matt Mackall and others',
          'product_version':version}]
 
 if os.name == 'nt':
     # Windows binary file versions for exe/dll files must have the
     # form W.X.Y.Z, where W,X,Y,Z are numbers in the range 0..65535
     setupversion = version.split('+', 1)[0]
 
 setup(name='mercurial',
       version=setupversion,
       author='Matt Mackall',
       author_email='[e-mail]',
       url='http://mercurial.selenic.com/',
       description='Scalable distributed SCM',
       license='GNU GPLv2+',
       scripts=scripts,
       packages=packages,
       py_modules=pymodules,
       ext_modules=extmodules,
       data_files=datafiles,
       package_data=packagedata,
       cmdclass=cmdclass,
       options=dict(py2exe=dict(packages=['hgext', 'email']),
                    bdist_mpkg=dict(zipdist=True,
                                    license='COPYING',
                                    readme='contrib/macosx/Readme.html',
                                    welcome='contrib/macosx/Welcome.html')),
       **extra)

tests/get-with-headers.py

@@ -1,29 +1,29 b''
 #!/usr/bin/env python
 
 """This does HTTP GET requests given a host:port and path and returns
 a subset of the headers plus the body of the result."""
 
-import httplib, sys, re
+import httplib, sys
 
 try:
     import msvcrt, os
     msvcrt.setmode(sys.stdout.fileno(), os.O_BINARY)
     msvcrt.setmode(sys.stderr.fileno(), os.O_BINARY)
 except ImportError:
     pass
 
 headers = [h.lower() for h in sys.argv[3:]]
 conn = httplib.HTTPConnection(sys.argv[1])
 conn.request("GET", sys.argv[2])
 response = conn.getresponse()
 print response.status, response.reason
 for h in headers:
     if response.getheader(h, None) is not None:
         print "%s: %s" % (h, response.getheader(h))
 print
 data = response.read()
 sys.stdout.write(data)
 
 if 200 <= response.status <= 299:
     sys.exit(0)
 sys.exit(1)

tests/killdaemons.py

@@ -1,25 +1,25 b''
 #!/usr/bin/env python
 
-import os, sys, time, errno, signal
+import os, time, errno, signal
 
 # Kill off any leftover daemon processes
 try:
     fp = open(os.environ['DAEMON_PIDS'])
     for line in fp:
         try:
             pid = int(line)
         except ValueError:
             continue
         try:
             os.kill(pid, 0)
             os.kill(pid, signal.SIGTERM)
             for i in range(10):
                 time.sleep(0.05)
                 os.kill(pid, 0)
             os.kill(pid, signal.SIGKILL)
         except OSError, err:
             if err.errno != errno.ESRCH:
                 raise
     fp.close()
 except IOError:
     pass

tests/run-tests.py

@@ -1,957 +1,956 b''
 #!/usr/bin/env python
 #
 # run-tests.py - Run a set of tests on Mercurial
 #
 # Copyright 2006 Matt Mackall <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 # Modifying this script is tricky because it has many modes:
 #   - serial (default) vs parallel (-jN, N > 1)
 #   - no coverage (default) vs coverage (-c, -C, -s)
 #   - temp install (default) vs specific hg script (--with-hg, --local)
 #   - tests are a mix of shell scripts and Python scripts
 #
 # If you change this script, it is recommended that you ensure you
 # haven't broken it by running it in various modes with a representative
 # sample of test scripts.  For example:
 #
 #  1) serial, no coverage, temp install:
 #      ./run-tests.py test-s*
 #  2) serial, no coverage, local hg:
 #      ./run-tests.py --local test-s*
 #  3) serial, coverage, temp install:
 #      ./run-tests.py -c test-s*
 #  4) serial, coverage, local hg:
 #      ./run-tests.py -c --local test-s*      # unsupported
 #  5) parallel, no coverage, temp install:
 #      ./run-tests.py -j2 test-s*
 #  6) parallel, no coverage, local hg:
 #      ./run-tests.py -j2 --local test-s*
 #  7) parallel, coverage, temp install:
 #      ./run-tests.py -j2 -c test-s*          # currently broken
 #  8) parallel, coverage, local install:
 #      ./run-tests.py -j2 -c --local test-s*  # unsupported (and broken)
 #  9) parallel, custom tmp dir:
 #      ./run-tests.py -j2 --tmpdir /tmp/myhgtests
 #
 # (You could use any subset of the tests: test-s* happens to match
 # enough that it's worth doing parallel runs, few enough that it
 # completes fairly quickly, includes both shell and Python scripts, and
 # includes some scripts that run daemon processes.)
 
 from distutils import version
 import difflib
 import errno
 import optparse
 import os
-import signal
+import shutil
 import subprocess
-import shutil
 import signal
 import sys
 import tempfile
 import time
 
 closefds = os.name == 'posix'
 def Popen4(cmd, bufsize=-1):
     p = subprocess.Popen(cmd, shell=True, bufsize=bufsize,
                          close_fds=closefds,
                          stdin=subprocess.PIPE, stdout=subprocess.PIPE,
                          stderr=subprocess.STDOUT)
     p.fromchild = p.stdout
     p.tochild = p.stdin
     p.childerr = p.stderr
     return p
 
 # reserved exit code to skip test (used by hghave)
 SKIPPED_STATUS = 80
 SKIPPED_PREFIX = 'skipped: '
 FAILED_PREFIX  = 'hghave check failed: '
 PYTHON = sys.executable
 IMPL_PATH = 'PYTHONPATH'
 if 'java' in sys.platform:
     IMPL_PATH = 'JYTHONPATH'
 
 requiredtools = ["python", "diff", "grep", "unzip", "gunzip", "bunzip2", "sed"]
 
 defaults = {
     'jobs': ('HGTEST_JOBS', 1),
     'timeout': ('HGTEST_TIMEOUT', 180),
     'port': ('HGTEST_PORT', 20059),
 }
 
 def parseargs():
     parser = optparse.OptionParser("%prog [options] [tests]")
     parser.add_option("-C", "--annotate", action="store_true",
         help="output files annotated with coverage")
     parser.add_option("--child", type="int",
         help="run as child process, summary to given fd")
     parser.add_option("-c", "--cover", action="store_true",
         help="print a test coverage report")
     parser.add_option("-f", "--first", action="store_true",
         help="exit on the first test failure")
     parser.add_option("-i", "--interactive", action="store_true",
         help="prompt to accept changed output")
     parser.add_option("-j", "--jobs", type="int",
         help="number of jobs to run in parallel"
              " (default: $%s or %d)" % defaults['jobs'])
     parser.add_option("-k", "--keywords",
         help="run tests matching keywords")
     parser.add_option("--keep-tmpdir", action="store_true",
         help="keep temporary directory after running tests")
     parser.add_option("--tmpdir", type="string",
         help="run tests in the given temporary directory"
              " (implies --keep-tmpdir)")
     parser.add_option("-d", "--debug", action="store_true",
         help="debug mode: write output of test scripts to console"
              " rather than capturing and diff'ing it (disables timeout)")
     parser.add_option("-R", "--restart", action="store_true",
         help="restart at last error")
     parser.add_option("-p", "--port", type="int",
         help="port on which servers should listen"
              " (default: $%s or %d)" % defaults['port'])
     parser.add_option("-r", "--retest", action="store_true",
         help="retest failed tests")
     parser.add_option("-S", "--noskips", action="store_true",
         help="don't report skip tests verbosely")
     parser.add_option("-t", "--timeout", type="int",
         help="kill errant tests after TIMEOUT seconds"
              " (default: $%s or %d)" % defaults['timeout'])
     parser.add_option("-v", "--verbose", action="store_true",
         help="output verbose messages")
     parser.add_option("-n", "--nodiff", action="store_true",
         help="skip showing test changes")
     parser.add_option("--with-hg", type="string",
         metavar="HG",
         help="test using specified hg script rather than a "
              "temporary installation")
     parser.add_option("--local", action="store_true",
         help="shortcut for --with-hg=<testdir>/../hg")
     parser.add_option("--pure", action="store_true",
         help="use pure Python code instead of C extensions")
     parser.add_option("-3", "--py3k-warnings", action="store_true",
         help="enable Py3k warnings on Python 2.6+")
     parser.add_option("--inotify", action="store_true",
         help="enable inotify extension when running tests")
     parser.add_option("--blacklist", action="append",
         help="skip tests listed in the specified blacklist file")
 
     for option, default in defaults.items():
         defaults[option] = int(os.environ.get(*default))
     parser.set_defaults(**defaults)
     (options, args) = parser.parse_args()
 
     # jython is always pure
     if 'java' in sys.platform or '__pypy__' in sys.modules:
         options.pure = True
 
     if options.with_hg:
         if not (os.path.isfile(options.with_hg) and
                 os.access(options.with_hg, os.X_OK)):
             parser.error('--with-hg must specify an executable hg script')
         if not os.path.basename(options.with_hg) == 'hg':
             sys.stderr.write('warning: --with-hg should specify an hg script')
     if options.local:
         testdir = os.path.dirname(os.path.realpath(sys.argv[0]))
         hgbin = os.path.join(os.path.dirname(testdir), 'hg')
         if not os.access(hgbin, os.X_OK):
             parser.error('--local specified, but %r not found or not executable'
                          % hgbin)
         options.with_hg = hgbin
 
     options.anycoverage = options.cover or options.annotate
     if options.anycoverage:
         try:
             import coverage
             covver = version.StrictVersion(coverage.__version__).version
             if covver < (3, 3):
                 parser.error('coverage options require coverage 3.3 or later')
         except ImportError:
             parser.error('coverage options now require the coverage package')
 
     if options.anycoverage and options.local:
         # this needs some path mangling somewhere, I guess
         parser.error("sorry, coverage options do not work when --local "
                      "is specified")
 
     global vlog
     if options.verbose:
         if options.jobs > 1 or options.child is not None:
             pid = "[%d]" % os.getpid()
         else:
             pid = None
         def vlog(*msg):
             if pid:
                 print pid,
             for m in msg:
                 print m,
             print
             sys.stdout.flush()
     else:
         vlog = lambda *msg: None
 
     if options.tmpdir:
         options.tmpdir = os.path.expanduser(options.tmpdir)
 
     if options.jobs < 1:
         parser.error('--jobs must be positive')
     if options.interactive and options.jobs > 1:
         print '(--interactive overrides --jobs)'
         options.jobs = 1
     if options.interactive and options.debug:
         parser.error("-i/--interactive and -d/--debug are incompatible")
     if options.debug:
         if options.timeout != defaults['timeout']:
             sys.stderr.write(
                 'warning: --timeout option ignored with --debug\n')
         options.timeout = 0
     if options.py3k_warnings:
         if sys.version_info[:2] < (2, 6) or sys.version_info[:2] >= (3, 0):
             parser.error('--py3k-warnings can only be used on Python 2.6+')
     if options.blacklist:
         blacklist = dict()
         for filename in options.blacklist:
             try:
                 path = os.path.expanduser(os.path.expandvars(filename))
                 f = open(path, "r")
             except IOError, err:
                 if err.errno != errno.ENOENT:
                     raise
                 print "warning: no such blacklist file: %s" % filename
                 continue
 
             for line in f.readlines():
                 line = line.strip()
                 if line and not line.startswith('#'):
                     blacklist[line] = filename
 
         options.blacklist = blacklist
 
     return (options, args)
 
 def rename(src, dst):
     """Like os.rename(), trade atomicity and opened files friendliness
     for existing destination support.
     """
     shutil.copy(src, dst)
     os.remove(src)
 
 def splitnewlines(text):
     '''like str.splitlines, but only split on newlines.
     keep line endings.'''
     i = 0
     lines = []
     while True:
         n = text.find('\n', i)
         if n == -1:
             last = text[i:]
             if last:
                 lines.append(last)
             return lines
         lines.append(text[i:n + 1])
         i = n + 1
 
 def parsehghaveoutput(lines):
     '''Parse hghave log lines.
     Return tuple of lists (missing, failed):
       * the missing/unknown features
       * the features for which existence check failed'''
     missing = []
     failed = []
     for line in lines:
         if line.startswith(SKIPPED_PREFIX):
             line = line.splitlines()[0]
             missing.append(line[len(SKIPPED_PREFIX):])
         elif line.startswith(FAILED_PREFIX):
             line = line.splitlines()[0]
             failed.append(line[len(FAILED_PREFIX):])
 
     return missing, failed
 
 def showdiff(expected, output, ref, err):
     for line in difflib.unified_diff(expected, output, ref, err):
         sys.stdout.write(line)
 
 def findprogram(program):
     """Search PATH for a executable program"""
     for p in os.environ.get('PATH', os.defpath).split(os.pathsep):
         name = os.path.join(p, program)
         if os.access(name, os.X_OK):
             return name
     return None
 
 def checktools():
     # Before we go any further, check for pre-requisite tools
     # stuff from coreutils (cat, rm, etc) are not tested
     for p in requiredtools:
         if os.name == 'nt':
             p += '.exe'
         found = findprogram(p)
         if found:
             vlog("# Found prerequisite", p, "at", found)
         else:
             print "WARNING: Did not find prerequisite tool: "+p
 
 def killdaemons():
     # Kill off any leftover daemon processes
     try:
         fp = open(DAEMON_PIDS)
         for line in fp:
             try:
                 pid = int(line)
             except ValueError:
                 continue
             try:
                 os.kill(pid, 0)
                 vlog('# Killing daemon process %d' % pid)
                 os.kill(pid, signal.SIGTERM)
                 time.sleep(0.25)
                 os.kill(pid, 0)
                 vlog('# Daemon process %d is stuck - really killing it' % pid)
                 os.kill(pid, signal.SIGKILL)
             except OSError, err:
                 if err.errno != errno.ESRCH:
                     raise
         fp.close()
         os.unlink(DAEMON_PIDS)
     except IOError:
         pass
 
 def cleanup(options):
     if not options.keep_tmpdir:
         vlog("# Cleaning up HGTMP", HGTMP)
         shutil.rmtree(HGTMP, True)
 
 def usecorrectpython():
     # some tests run python interpreter. they must use same
     # interpreter we use or bad things will happen.
     exedir, exename = os.path.split(sys.executable)
     if exename == 'python':
         path = findprogram('python')
         if os.path.dirname(path) == exedir:
             return
     vlog('# Making python executable in test path use correct Python')
     mypython = os.path.join(BINDIR, 'python')
     try:
         os.symlink(sys.executable, mypython)
     except AttributeError:
         # windows fallback
         shutil.copyfile(sys.executable, mypython)
         shutil.copymode(sys.executable, mypython)
 
 def installhg(options):
     vlog("# Performing temporary installation of HG")
     installerrs = os.path.join("tests", "install.err")
     pure = options.pure and "--pure" or ""
 
     # Run installer in hg root
     script = os.path.realpath(sys.argv[0])
     hgroot = os.path.dirname(os.path.dirname(script))
     os.chdir(hgroot)
     nohome = '--home=""'
     if os.name == 'nt':
         # The --home="" trick works only on OS where os.sep == '/'
         # because of a distutils convert_path() fast-path. Avoid it at
         # least on Windows for now, deal with .pydistutils.cfg bugs
         # when they happen.
         nohome = ''
     cmd = ('%s setup.py %s clean --all'
            ' install --force --prefix="%s" --install-lib="%s"'
            ' --install-scripts="%s" %s >%s 2>&1'
            % (sys.executable, pure, INST, PYTHONDIR, BINDIR, nohome,
               installerrs))
     vlog("# Running", cmd)
     if os.system(cmd) == 0:
         if not options.verbose:
             os.remove(installerrs)
     else:
         f = open(installerrs)
         for line in f:
             print line,
         f.close()
         sys.exit(1)
     os.chdir(TESTDIR)
 
     usecorrectpython()
 
     vlog("# Installing dummy diffstat")
     f = open(os.path.join(BINDIR, 'diffstat'), 'w')
     f.write('#!' + sys.executable + '\n'
             'import sys\n'
             'files = 0\n'
             'for line in sys.stdin:\n'
             '    if line.startswith("diff "):\n'
             '        files += 1\n'
             'sys.stdout.write("files patched: %d\\n" % files)\n')
     f.close()
     os.chmod(os.path.join(BINDIR, 'diffstat'), 0700)
 
     if options.py3k_warnings and not options.anycoverage:
         vlog("# Updating hg command to enable Py3k Warnings switch")
         f = open(os.path.join(BINDIR, 'hg'), 'r')
         lines = [line.rstrip() for line in f]
         lines[0] += ' -3'
         f.close()
         f = open(os.path.join(BINDIR, 'hg'), 'w')
         for line in lines:
             f.write(line + '\n')
         f.close()
 
     if options.anycoverage:
         custom = os.path.join(TESTDIR, 'sitecustomize.py')
         target = os.path.join(PYTHONDIR, 'sitecustomize.py')
         vlog('# Installing coverage trigger to %s' % target)
         shutil.copyfile(custom, target)
         rc = os.path.join(TESTDIR, '.coveragerc')
         vlog('# Installing coverage rc to %s' % rc)
         os.environ['COVERAGE_PROCESS_START'] = rc
         fn = os.path.join(INST, '..', '.coverage')
         os.environ['COVERAGE_FILE'] = fn
 
 def outputcoverage(options):
 
     vlog('# Producing coverage report')
     os.chdir(PYTHONDIR)
 
     def covrun(*args):
         cmd = 'coverage %s' % ' '.join(args)
         vlog('# Running: %s' % cmd)
         os.system(cmd)
 
     if options.child:
         return
 
     covrun('-c')
     omit = ','.join([BINDIR, TESTDIR])
     covrun('-i', '-r', '"--omit=%s"' % omit) # report
     if options.annotate:
         adir = os.path.join(TESTDIR, 'annotated')
         if not os.path.isdir(adir):
             os.mkdir(adir)
         covrun('-i', '-a', '"--directory=%s"' % adir, '"--omit=%s"' % omit)
 
 class Timeout(Exception):
     pass
 
 def alarmed(signum, frame):
     raise Timeout
 
 def run(cmd, options):
     """Run command in a sub-process, capturing the output (stdout and stderr).
     Return a tuple (exitcode, output).  output is None in debug mode."""
     # TODO: Use subprocess.Popen if we're running on Python 2.4
     if options.debug:
         proc = subprocess.Popen(cmd, shell=True)
         ret = proc.wait()
         return (ret, None)
 
     if os.name == 'nt' or sys.platform.startswith('java'):
         tochild, fromchild = os.popen4(cmd)
         tochild.close()
         output = fromchild.read()
         ret = fromchild.close()
         if ret == None:
             ret = 0
     else:
         proc = Popen4(cmd)
         def cleanup():
             os.kill(proc.pid, signal.SIGTERM)
             ret = proc.wait()
             if ret == 0:
                 ret = signal.SIGTERM << 8
             killdaemons()
             return ret
 
         try:
             output = ''
             proc.tochild.close()
             output = proc.fromchild.read()
             ret = proc.wait()
             if os.WIFEXITED(ret):
                 ret = os.WEXITSTATUS(ret)
         except Timeout:
             vlog('# Process %d timed out - killing it' % proc.pid)
             ret = cleanup()
             output += ("\n### Abort: timeout after %d seconds.\n"
                        % options.timeout)
         except KeyboardInterrupt:
             vlog('# Handling keyboard interrupt')
             cleanup()
             raise
 
     return ret, splitnewlines(output)
 
 def runone(options, test, skips, fails):
     '''tristate output:
     None -> skipped
     True -> passed
     False -> failed'''
 
     def skip(msg):
         if not options.verbose:
             skips.append((test, msg))
         else:
             print "\nSkipping %s: %s" % (testpath, msg)
         return None
 
     def fail(msg):
         fails.append((test, msg))
         if not options.nodiff:
             print "\nERROR: %s %s" % (testpath, msg)
         return None
 
     vlog("# Test", test)
 
     # create a fresh hgrc
     hgrc = open(HGRCPATH, 'w+')
     hgrc.write('[ui]\n')
     hgrc.write('slash = True\n')
     hgrc.write('[defaults]\n')
     hgrc.write('backout = -d "0 0"\n')
     hgrc.write('commit = -d "0 0"\n')
     hgrc.write('tag = -d "0 0"\n')
     if options.inotify:
         hgrc.write('[extensions]\n')
         hgrc.write('inotify=\n')
         hgrc.write('[inotify]\n')
         hgrc.write('pidfile=%s\n' % DAEMON_PIDS)
         hgrc.write('appendpid=True\n')
     hgrc.close()
 
     testpath = os.path.join(TESTDIR, test)
     ref = os.path.join(TESTDIR, test+".out")
     err = os.path.join(TESTDIR, test+".err")
     if os.path.exists(err):
         os.remove(err)       # Remove any previous output files
     try:
         tf = open(testpath)
         firstline = tf.readline().rstrip()
         tf.close()
     except:
         firstline = ''
     lctest = test.lower()
 
     if lctest.endswith('.py') or firstline == '#!/usr/bin/env python':
         py3kswitch = options.py3k_warnings and ' -3' or ''
         cmd = '%s%s "%s"' % (PYTHON, py3kswitch, testpath)
     elif lctest.endswith('.bat'):
         # do not run batch scripts on non-windows
         if os.name != 'nt':
             return skip("batch script")
         # To reliably get the error code from batch files on WinXP,
         # the "cmd /c call" prefix is needed. Grrr
         cmd = 'cmd /c call "%s"' % testpath
     else:
         # do not run shell scripts on windows
         if os.name == 'nt':
             return skip("shell script")
         # do not try to run non-executable programs
         if not os.path.exists(testpath):
             return fail("does not exist")
         elif not os.access(testpath, os.X_OK):
             return skip("not executable")
         cmd = '"%s"' % testpath
 
     # Make a tmp subdirectory to work in
     tmpd = os.path.join(HGTMP, test)
     os.mkdir(tmpd)
     os.chdir(tmpd)
 
     if options.timeout > 0:
         signal.alarm(options.timeout)
 
     vlog("# Running", cmd)
     ret, out = run(cmd, options)
     vlog("# Ret was:", ret)
 
     if options.timeout > 0:
         signal.alarm(0)
 
     mark = '.'
 
     skipped = (ret == SKIPPED_STATUS)
     # If we're not in --debug mode and reference output file exists,
     # check test output against it.
     if options.debug:
         refout = None                   # to match out == None
     elif os.path.exists(ref):
         f = open(ref, "r")
         refout = splitnewlines(f.read())
         f.close()
     else:
         refout = []
 
     if skipped:
         mark = 's'
         if out is None:                 # debug mode: nothing to parse
             missing = ['unknown']
             failed = None
         else:
             missing, failed = parsehghaveoutput(out)
         if not missing:
             missing = ['irrelevant']
         if failed:
             fail("hghave failed checking for %s" % failed[-1])
             skipped = False
         else:
             skip(missing[-1])
     elif out != refout:
         mark = '!'
         if ret:
             fail("output changed and returned error code %d" % ret)
         else:
             fail("output changed")
         if not options.nodiff:
             showdiff(refout, out, ref, err)
         ret = 1
     elif ret:
         mark = '!'
         fail("returned error code %d" % ret)
 
     if not options.verbose:
         sys.stdout.write(mark)
         sys.stdout.flush()
 
     if ret != 0 and not skipped and not options.debug:
         # Save errors to a file for diagnosis
         f = open(err, "wb")
         for line in out:
             f.write(line)
         f.close()
 
     killdaemons()
 
     os.chdir(TESTDIR)
     if not options.keep_tmpdir:
         shutil.rmtree(tmpd, True)
     if skipped:
         return None
     return ret == 0
 
 _hgpath = None
 
 def _gethgpath():
     """Return the path to the mercurial package that is actually found by
     the current Python interpreter."""
     global _hgpath
     if _hgpath is not None:
         return _hgpath
 
     cmd = '%s -c "import mercurial; print mercurial.__path__[0]"'
     pipe = os.popen(cmd % PYTHON)
     try:
         _hgpath = pipe.read().strip()
     finally:
         pipe.close()
     return _hgpath
 
 def _checkhglib(verb):
     """Ensure that the 'mercurial' package imported by python is
     the one we expect it to be.  If not, print a warning to stderr."""
     expecthg = os.path.join(PYTHONDIR, 'mercurial')
     actualhg = _gethgpath()
     if actualhg != expecthg:
         sys.stderr.write('warning: %s with unexpected mercurial lib: %s\n'
                          '         (expected %s)\n'
                          % (verb, actualhg, expecthg))
 
 def runchildren(options, tests):
     if INST:
         installhg(options)
         _checkhglib("Testing")
 
     optcopy = dict(options.__dict__)
     optcopy['jobs'] = 1
     if optcopy['with_hg'] is None:
         optcopy['with_hg'] = os.path.join(BINDIR, "hg")
     optcopy.pop('anycoverage', None)
 
     opts = []
     for opt, value in optcopy.iteritems():
         name = '--' + opt.replace('_', '-')
         if value is True:
             opts.append(name)
         elif value is not None:
             opts.append(name + '=' + str(value))
 
     tests.reverse()
     jobs = [[] for j in xrange(options.jobs)]
     while tests:
         for job in jobs:
             if not tests:
                 break
             job.append(tests.pop())
     fps = {}
 
     for j, job in enumerate(jobs):
         if not job:
             continue
         rfd, wfd = os.pipe()
         childopts = ['--child=%d' % wfd, '--port=%d' % (options.port + j * 3)]
         childtmp = os.path.join(HGTMP, 'child%d' % j)
         childopts += ['--tmpdir', childtmp]
         cmdline = [PYTHON, sys.argv[0]] + opts + childopts + job
         vlog(' '.join(cmdline))
         fps[os.spawnvp(os.P_NOWAIT, cmdline[0], cmdline)] = os.fdopen(rfd, 'r')
         os.close(wfd)
     signal.signal(signal.SIGINT, signal.SIG_IGN)
     failures = 0
     tested, skipped, failed = 0, 0, 0
     skips = []
     fails = []
     while fps:
         pid, status = os.wait()
         fp = fps.pop(pid)
         l = fp.read().splitlines()
         try:
             test, skip, fail = map(int, l[:3])
         except ValueError:
             test, skip, fail = 0, 0, 0
         split = -fail or len(l)
         for s in l[3:split]:
             skips.append(s.split(" ", 1))
         for s in l[split:]:
             fails.append(s.split(" ", 1))
         tested += test
         skipped += skip
         failed += fail
         vlog('pid %d exited, status %d' % (pid, status))
         failures |= status
     print
     if not options.noskips:
         for s in skips:
             print "Skipped %s: %s" % (s[0], s[1])
     for s in fails:
         print "Failed %s: %s" % (s[0], s[1])
 
     _checkhglib("Tested")
     print "# Ran %d tests, %d skipped, %d failed." % (
         tested, skipped, failed)
 
     if options.anycoverage:
         outputcoverage(options)
     sys.exit(failures != 0)
 
 def runtests(options, tests):
     global DAEMON_PIDS, HGRCPATH
     DAEMON_PIDS = os.environ["DAEMON_PIDS"] = os.path.join(HGTMP, 'daemon.pids')
     HGRCPATH = os.environ["HGRCPATH"] = os.path.join(HGTMP, '.hgrc')
 
     try:
         if INST:
             installhg(options)
             _checkhglib("Testing")
 
         if options.timeout > 0:
             try:
                 signal.signal(signal.SIGALRM, alarmed)
                 vlog('# Running each test with %d second timeout' %
                      options.timeout)
             except AttributeError:
                 print 'WARNING: cannot run tests with timeouts'
                 options.timeout = 0
 
         tested = 0
         failed = 0
         skipped = 0
 
         if options.restart:
             orig = list(tests)
             while tests:
                 if os.path.exists(tests[0] + ".err"):
                     break
                 tests.pop(0)
             if not tests:
                 print "running all tests"
                 tests = orig
 
         skips = []
         fails = []
 
         for test in tests:
             if options.blacklist:
                 filename = options.blacklist.get(test)
                 if filename is not None:
                     skips.append((test, "blacklisted (%s)" % filename))
                     skipped += 1
                     continue
 
             if options.retest and not os.path.exists(test + ".err"):
                 skipped += 1
                 continue
 
             if options.keywords:
                 t = open(test).read().lower() + test.lower()
                 for k in options.keywords.lower().split():
                     if k in t:
                         break
                 else:
                     skipped += 1
                     continue
 
             ret = runone(options, test, skips, fails)
             if ret is None:
                 skipped += 1
             elif not ret:
                 if options.interactive:
                     print "Accept this change? [n] ",
                     answer = sys.stdin.readline().strip()
                     if answer.lower() in "y yes".split():
                         rename(test + ".err", test + ".out")
                         tested += 1
                         fails.pop()
                         continue
                 failed += 1
                 if options.first:
                     break
             tested += 1
 
         if options.child:
             fp = os.fdopen(options.child, 'w')
             fp.write('%d\n%d\n%d\n' % (tested, skipped, failed))
             for s in skips:
                 fp.write("%s %s\n" % s)
             for s in fails:
                 fp.write("%s %s\n" % s)
             fp.close()
         else:
             print
             for s in skips:
                 print "Skipped %s: %s" % s
             for s in fails:
                 print "Failed %s: %s" % s
             _checkhglib("Tested")
             print "# Ran %d tests, %d skipped, %d failed." % (
                 tested, skipped, failed)
 
         if options.anycoverage:
             outputcoverage(options)
     except KeyboardInterrupt:
         failed = True
         print "\ninterrupted!"
 
     if failed:
         sys.exit(1)
 
 def main():
     (options, args) = parseargs()
     if not options.child:
         os.umask(022)
 
         checktools()
 
     # Reset some environment variables to well-known values so that
     # the tests produce repeatable output.
     os.environ['LANG'] = os.environ['LC_ALL'] = os.environ['LANGUAGE'] = 'C'
     os.environ['TZ'] = 'GMT'
     os.environ["EMAIL"] = "Foo Bar <[e-mail]>"
     os.environ['CDPATH'] = ''
     os.environ['COLUMNS'] = '80'
     os.environ['GREP_OPTIONS'] = ''
     os.environ['http_proxy'] = ''
 
     # unset env related to hooks
     for k in os.environ.keys():
         if k.startswith('HG_'):
             del os.environ[k]
 
     global TESTDIR, HGTMP, INST, BINDIR, PYTHONDIR, COVERAGE_FILE
     TESTDIR = os.environ["TESTDIR"] = os.getcwd()
     if options.tmpdir:
         options.keep_tmpdir = True
         tmpdir = options.tmpdir
         if os.path.exists(tmpdir):
             # Meaning of tmpdir has changed since 1.3: we used to create
             # HGTMP inside tmpdir; now HGTMP is tmpdir.  So fail if
             # tmpdir already exists.
             sys.exit("error: temp dir %r already exists" % tmpdir)
 
             # Automatically removing tmpdir sounds convenient, but could
             # really annoy anyone in the habit of using "--tmpdir=/tmp"
             # or "--tmpdir=$HOME".
             #vlog("# Removing temp dir", tmpdir)
             #shutil.rmtree(tmpdir)
         os.makedirs(tmpdir)
     else:
         tmpdir = tempfile.mkdtemp('', 'hgtests.')
     HGTMP = os.environ['HGTMP'] = os.path.realpath(tmpdir)
     DAEMON_PIDS = None
     HGRCPATH = None
 
     os.environ["HGEDITOR"] = sys.executable + ' -c "import sys; sys.exit(0)"'
     os.environ["HGMERGE"] = "internal:merge"
     os.environ["HGUSER"]   = "test"
     os.environ["HGENCODING"] = "ascii"
     os.environ["HGENCODINGMODE"] = "strict"
     os.environ["HGPORT"] = str(options.port)
     os.environ["HGPORT1"] = str(options.port + 1)
     os.environ["HGPORT2"] = str(options.port + 2)
 
     if options.with_hg:
         INST = None
         BINDIR = os.path.dirname(os.path.realpath(options.with_hg))
 
         # This looks redundant with how Python initializes sys.path from
         # the location of the script being executed.  Needed because the
         # "hg" specified by --with-hg is not the only Python script
         # executed in the test suite that needs to import 'mercurial'
         # ... which means it's not really redundant at all.
         PYTHONDIR = BINDIR
     else:
         INST = os.path.join(HGTMP, "install")
         BINDIR = os.environ["BINDIR"] = os.path.join(INST, "bin")
         PYTHONDIR = os.path.join(INST, "lib", "python")
 
     os.environ["BINDIR"] = BINDIR
     os.environ["PYTHON"] = PYTHON
 
     if not options.child:
         path = [BINDIR] + os.environ["PATH"].split(os.pathsep)
         os.environ["PATH"] = os.pathsep.join(path)
 
         # Include TESTDIR in PYTHONPATH so that out-of-tree extensions
         # can run .../tests/run-tests.py test-foo where test-foo
         # adds an extension to HGRC
         pypath = [PYTHONDIR, TESTDIR]
         # We have to augment PYTHONPATH, rather than simply replacing
         # it, in case external libraries are only available via current
         # PYTHONPATH.  (In particular, the Subversion bindings on OS X
         # are in /opt/subversion.)
         oldpypath = os.environ.get(IMPL_PATH)
         if oldpypath:
             pypath.append(oldpypath)
         os.environ[IMPL_PATH] = os.pathsep.join(pypath)
 
     COVERAGE_FILE = os.path.join(TESTDIR, ".coverage")
 
     if len(args) == 0:
         args = os.listdir(".")
         args.sort()
 
     tests = []
     for test in args:
         if (test.startswith("test-") and '~' not in test and
             ('.' not in test or test.endswith('.py') or
              test.endswith('.bat'))):
             tests.append(test)
     if not tests:
         print "# Ran 0 tests, 0 skipped, 0 failed."
         return
 
     vlog("# Using TESTDIR", TESTDIR)
     vlog("# Using HGTMP", HGTMP)
     vlog("# Using PATH", os.environ["PATH"])
     vlog("# Using", IMPL_PATH, os.environ[IMPL_PATH])
 
     try:
         if len(tests) > 1 and options.jobs > 1:
             runchildren(options, tests)
         else:
             runtests(options, tests)
     finally:
         time.sleep(1)
         cleanup(options)
 
 main()

tests/test-status-inprocess.py

@@ -1,32 +1,31 b''
 #!/usr/bin/python
-import os
 from mercurial.ui import ui
 from mercurial.localrepo import localrepository
 from mercurial.commands import add, commit, status
 
 u = ui()
 
 print '% creating repo'
 repo = localrepository(u, '.', create=True)
 
 f = open('test.py', 'w')
 try:
     f.write('foo\n')
 finally:
     f.close
 
 print '% add and commit'
 add(u, repo, 'test.py')
 commit(u, repo, message='*')
 status(u, repo, clean=True)
 
 
 print '% change'
 f = open('test.py', 'w')
 try:
     f.write('bar\n')
 finally:
     f.close()
 
 # this would return clean instead of changed before the fix
 status(u, repo, clean=True, modified=True)