py3: replace os.environ with encoding.environ (part 3 of 5)

mercurial/filemerge.py

@@ -1,714 +1,715
 # filemerge.py - file-level merge handling for Mercurial
 #
 # Copyright 2006, 2007, 2008 Matt Mackall <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 from __future__ import absolute_import
 
 import filecmp
 import os
 import re
 import tempfile
 
 from .i18n import _
 from .node import nullid, short
 
 from . import (
+    encoding,
     error,
     formatter,
     match,
     pycompat,
     scmutil,
     simplemerge,
     tagmerge,
     templatekw,
     templater,
     util,
 )
 
 def _toolstr(ui, tool, part, default=""):
     return ui.config("merge-tools", tool + "." + part, default)
 
 def _toolbool(ui, tool, part, default=False):
     return ui.configbool("merge-tools", tool + "." + part, default)
 
 def _toollist(ui, tool, part, default=[]):
     return ui.configlist("merge-tools", tool + "." + part, default)
 
 internals = {}
 # Merge tools to document.
 internalsdoc = {}
 
 # internal tool merge types
 nomerge = None
 mergeonly = 'mergeonly'  # just the full merge, no premerge
 fullmerge = 'fullmerge'  # both premerge and merge
 
 class absentfilectx(object):
     """Represents a file that's ostensibly in a context but is actually not
     present in it.
 
     This is here because it's very specific to the filemerge code for now --
     other code is likely going to break with the values this returns."""
     def __init__(self, ctx, f):
         self._ctx = ctx
         self._f = f
 
     def path(self):
         return self._f
 
     def size(self):
         return None
 
     def data(self):
         return None
 
     def filenode(self):
         return nullid
 
     _customcmp = True
     def cmp(self, fctx):
         """compare with other file context
 
         returns True if different from fctx.
         """
         return not (fctx.isabsent() and
                     fctx.ctx() == self.ctx() and
                     fctx.path() == self.path())
 
     def flags(self):
         return ''
 
     def changectx(self):
         return self._ctx
 
     def isbinary(self):
         return False
 
     def isabsent(self):
         return True
 
 def internaltool(name, mergetype, onfailure=None, precheck=None):
     '''return a decorator for populating internal merge tool table'''
     def decorator(func):
         fullname = ':' + name
         func.__doc__ = (pycompat.sysstr("``%s``\n" % fullname)
                         + func.__doc__.strip())
         internals[fullname] = func
         internals['internal:' + name] = func
         internalsdoc[fullname] = func
         func.mergetype = mergetype
         func.onfailure = onfailure
         func.precheck = precheck
         return func
     return decorator
 
 def _findtool(ui, tool):
     if tool in internals:
         return tool
     return findexternaltool(ui, tool)
 
 def findexternaltool(ui, tool):
     for kn in ("regkey", "regkeyalt"):
         k = _toolstr(ui, tool, kn)
         if not k:
             continue
         p = util.lookupreg(k, _toolstr(ui, tool, "regname"))
         if p:
             p = util.findexe(p + _toolstr(ui, tool, "regappend"))
             if p:
                 return p
     exe = _toolstr(ui, tool, "executable", tool)
     return util.findexe(util.expandpath(exe))
 
 def _picktool(repo, ui, path, binary, symlink, changedelete):
     def supportscd(tool):
         return tool in internals and internals[tool].mergetype == nomerge
 
     def check(tool, pat, symlink, binary, changedelete):
         tmsg = tool
         if pat:
             tmsg += " specified for " + pat
         if not _findtool(ui, tool):
             if pat: # explicitly requested tool deserves a warning
                 ui.warn(_("couldn't find merge tool %s\n") % tmsg)
             else: # configured but non-existing tools are more silent
                 ui.note(_("couldn't find merge tool %s\n") % tmsg)
         elif symlink and not _toolbool(ui, tool, "symlink"):
             ui.warn(_("tool %s can't handle symlinks\n") % tmsg)
         elif binary and not _toolbool(ui, tool, "binary"):
             ui.warn(_("tool %s can't handle binary\n") % tmsg)
         elif changedelete and not supportscd(tool):
             # the nomerge tools are the only tools that support change/delete
             # conflicts
             pass
         elif not util.gui() and _toolbool(ui, tool, "gui"):
             ui.warn(_("tool %s requires a GUI\n") % tmsg)
         else:
             return True
         return False
 
     # internal config: ui.forcemerge
     # forcemerge comes from command line arguments, highest priority
     force = ui.config('ui', 'forcemerge')
     if force:
         toolpath = _findtool(ui, force)
         if changedelete and not supportscd(toolpath):
             return ":prompt", None
         else:
             if toolpath:
                 return (force, util.shellquote(toolpath))
             else:
                 # mimic HGMERGE if given tool not found
                 return (force, force)
 
     # HGMERGE takes next precedence
-    hgmerge = os.environ.get("HGMERGE")
+    hgmerge = encoding.environ.get("HGMERGE")
     if hgmerge:
         if changedelete and not supportscd(hgmerge):
             return ":prompt", None
         else:
             return (hgmerge, hgmerge)
 
     # then patterns
     for pat, tool in ui.configitems("merge-patterns"):
         mf = match.match(repo.root, '', [pat])
         if mf(path) and check(tool, pat, symlink, False, changedelete):
             toolpath = _findtool(ui, tool)
             return (tool, util.shellquote(toolpath))
 
     # then merge tools
     tools = {}
     disabled = set()
     for k, v in ui.configitems("merge-tools"):
         t = k.split('.')[0]
         if t not in tools:
             tools[t] = int(_toolstr(ui, t, "priority", "0"))
         if _toolbool(ui, t, "disabled", False):
             disabled.add(t)
     names = tools.keys()
     tools = sorted([(-p, tool) for tool, p in tools.items()
                     if tool not in disabled])
     uimerge = ui.config("ui", "merge")
     if uimerge:
         # external tools defined in uimerge won't be able to handle
         # change/delete conflicts
         if uimerge not in names and not changedelete:
             return (uimerge, uimerge)
         tools.insert(0, (None, uimerge)) # highest priority
     tools.append((None, "hgmerge")) # the old default, if found
     for p, t in tools:
         if check(t, None, symlink, binary, changedelete):
             toolpath = _findtool(ui, t)
             return (t, util.shellquote(toolpath))
 
     # internal merge or prompt as last resort
     if symlink or binary or changedelete:
         return ":prompt", None
     return ":merge", None
 
 def _eoltype(data):
     "Guess the EOL type of a file"
     if '\0' in data: # binary
         return None
     if '\r\n' in data: # Windows
         return '\r\n'
     if '\r' in data: # Old Mac
         return '\r'
     if '\n' in data: # UNIX
         return '\n'
     return None # unknown
 
 def _matcheol(file, origfile):
     "Convert EOL markers in a file to match origfile"
     tostyle = _eoltype(util.readfile(origfile))
     if tostyle:
         data = util.readfile(file)
         style = _eoltype(data)
         if style:
             newdata = data.replace(style, tostyle)
             if newdata != data:
                 util.writefile(file, newdata)
 
 @internaltool('prompt', nomerge)
 def _iprompt(repo, mynode, orig, fcd, fco, fca, toolconf, labels=None):
     """Asks the user which of the local `p1()` or the other `p2()` version to
     keep as the merged version."""
     ui = repo.ui
     fd = fcd.path()
 
     prompts = partextras(labels)
     prompts['fd'] = fd
     try:
         if fco.isabsent():
             index = ui.promptchoice(
                 _("local%(l)s changed %(fd)s which other%(o)s deleted\n"
                   "use (c)hanged version, (d)elete, or leave (u)nresolved?"
                   "$$ &Changed $$ &Delete $$ &Unresolved") % prompts, 2)
             choice = ['local', 'other', 'unresolved'][index]
         elif fcd.isabsent():
             index = ui.promptchoice(
                 _("other%(o)s changed %(fd)s which local%(l)s deleted\n"
                   "use (c)hanged version, leave (d)eleted, or "
                   "leave (u)nresolved?"
                   "$$ &Changed $$ &Deleted $$ &Unresolved") % prompts, 2)
             choice = ['other', 'local', 'unresolved'][index]
         else:
             index = ui.promptchoice(
                 _("no tool found to merge %(fd)s\n"
                   "keep (l)ocal%(l)s, take (o)ther%(o)s, or leave (u)nresolved?"
                   "$$ &Local $$ &Other $$ &Unresolved") % prompts, 2)
             choice = ['local', 'other', 'unresolved'][index]
 
         if choice == 'other':
             return _iother(repo, mynode, orig, fcd, fco, fca, toolconf,
                            labels)
         elif choice == 'local':
             return _ilocal(repo, mynode, orig, fcd, fco, fca, toolconf,
                            labels)
         elif choice == 'unresolved':
             return _ifail(repo, mynode, orig, fcd, fco, fca, toolconf,
                           labels)
     except error.ResponseExpected:
         ui.write("\n")
         return _ifail(repo, mynode, orig, fcd, fco, fca, toolconf,
                       labels)
 
 @internaltool('local', nomerge)
 def _ilocal(repo, mynode, orig, fcd, fco, fca, toolconf, labels=None):
     """Uses the local `p1()` version of files as the merged version."""
     return 0, fcd.isabsent()
 
 @internaltool('other', nomerge)
 def _iother(repo, mynode, orig, fcd, fco, fca, toolconf, labels=None):
     """Uses the other `p2()` version of files as the merged version."""
     if fco.isabsent():
         # local changed, remote deleted -- 'deleted' picked
         repo.wvfs.unlinkpath(fcd.path())
         deleted = True
     else:
         repo.wwrite(fcd.path(), fco.data(), fco.flags())
         deleted = False
     return 0, deleted
 
 @internaltool('fail', nomerge)
 def _ifail(repo, mynode, orig, fcd, fco, fca, toolconf, labels=None):
     """
     Rather than attempting to merge files that were modified on both
     branches, it marks them as unresolved. The resolve command must be
     used to resolve these conflicts."""
     # for change/delete conflicts write out the changed version, then fail
     if fcd.isabsent():
         repo.wwrite(fcd.path(), fco.data(), fco.flags())
     return 1, False
 
 def _premerge(repo, fcd, fco, fca, toolconf, files, labels=None):
     tool, toolpath, binary, symlink = toolconf
     if symlink or fcd.isabsent() or fco.isabsent():
         return 1
     a, b, c, back = files
 
     ui = repo.ui
 
     validkeep = ['keep', 'keep-merge3']
 
     # do we attempt to simplemerge first?
     try:
         premerge = _toolbool(ui, tool, "premerge", not binary)
     except error.ConfigError:
         premerge = _toolstr(ui, tool, "premerge").lower()
         if premerge not in validkeep:
             _valid = ', '.join(["'" + v + "'" for v in validkeep])
             raise error.ConfigError(_("%s.premerge not valid "
                                       "('%s' is neither boolean nor %s)") %
                                     (tool, premerge, _valid))
 
     if premerge:
         if premerge == 'keep-merge3':
             if not labels:
                 labels = _defaultconflictlabels
             if len(labels) < 3:
                 labels.append('base')
         r = simplemerge.simplemerge(ui, a, b, c, quiet=True, label=labels)
         if not r:
             ui.debug(" premerge successful\n")
             return 0
         if premerge not in validkeep:
             util.copyfile(back, a) # restore from backup and try again
     return 1 # continue merging
 
 def _mergecheck(repo, mynode, orig, fcd, fco, fca, toolconf):
     tool, toolpath, binary, symlink = toolconf
     if symlink:
         repo.ui.warn(_('warning: internal %s cannot merge symlinks '
                        'for %s\n') % (tool, fcd.path()))
         return False
     if fcd.isabsent() or fco.isabsent():
         repo.ui.warn(_('warning: internal %s cannot merge change/delete '
                        'conflict for %s\n') % (tool, fcd.path()))
         return False
     return True
 
 def _merge(repo, mynode, orig, fcd, fco, fca, toolconf, files, labels, mode):
     """
     Uses the internal non-interactive simple merge algorithm for merging
     files. It will fail if there are any conflicts and leave markers in
     the partially merged file. Markers will have two sections, one for each side
     of merge, unless mode equals 'union' which suppresses the markers."""
     a, b, c, back = files
 
     ui = repo.ui
 
     r = simplemerge.simplemerge(ui, a, b, c, label=labels, mode=mode)
     return True, r, False
 
 @internaltool('union', fullmerge,
               _("warning: conflicts while merging %s! "
                 "(edit, then use 'hg resolve --mark')\n"),
               precheck=_mergecheck)
 def _iunion(repo, mynode, orig, fcd, fco, fca, toolconf, files, labels=None):
     """
     Uses the internal non-interactive simple merge algorithm for merging
     files. It will use both left and right sides for conflict regions.
     No markers are inserted."""
     return _merge(repo, mynode, orig, fcd, fco, fca, toolconf,
                   files, labels, 'union')
 
 @internaltool('merge', fullmerge,
               _("warning: conflicts while merging %s! "
                 "(edit, then use 'hg resolve --mark')\n"),
               precheck=_mergecheck)
 def _imerge(repo, mynode, orig, fcd, fco, fca, toolconf, files, labels=None):
     """
     Uses the internal non-interactive simple merge algorithm for merging
     files. It will fail if there are any conflicts and leave markers in
     the partially merged file. Markers will have two sections, one for each side
     of merge."""
     return _merge(repo, mynode, orig, fcd, fco, fca, toolconf,
                   files, labels, 'merge')
 
 @internaltool('merge3', fullmerge,
               _("warning: conflicts while merging %s! "
                 "(edit, then use 'hg resolve --mark')\n"),
               precheck=_mergecheck)
 def _imerge3(repo, mynode, orig, fcd, fco, fca, toolconf, files, labels=None):
     """
     Uses the internal non-interactive simple merge algorithm for merging
     files. It will fail if there are any conflicts and leave markers in
     the partially merged file. Marker will have three sections, one from each
     side of the merge and one for the base content."""
     if not labels:
         labels = _defaultconflictlabels
     if len(labels) < 3:
         labels.append('base')
     return _imerge(repo, mynode, orig, fcd, fco, fca, toolconf, files, labels)
 
 def _imergeauto(repo, mynode, orig, fcd, fco, fca, toolconf, files,
                 labels=None, localorother=None):
     """
     Generic driver for _imergelocal and _imergeother
     """
     assert localorother is not None
     tool, toolpath, binary, symlink = toolconf
     a, b, c, back = files
     r = simplemerge.simplemerge(repo.ui, a, b, c, label=labels,
                                 localorother=localorother)
     return True, r
 
 @internaltool('merge-local', mergeonly, precheck=_mergecheck)
 def _imergelocal(*args, **kwargs):
     """
     Like :merge, but resolve all conflicts non-interactively in favor
     of the local `p1()` changes."""
     success, status = _imergeauto(localorother='local', *args, **kwargs)
     return success, status, False
 
 @internaltool('merge-other', mergeonly, precheck=_mergecheck)
 def _imergeother(*args, **kwargs):
     """
     Like :merge, but resolve all conflicts non-interactively in favor
     of the other `p2()` changes."""
     success, status = _imergeauto(localorother='other', *args, **kwargs)
     return success, status, False
 
 @internaltool('tagmerge', mergeonly,
               _("automatic tag merging of %s failed! "
                 "(use 'hg resolve --tool :merge' or another merge "
                 "tool of your choice)\n"))
 def _itagmerge(repo, mynode, orig, fcd, fco, fca, toolconf, files, labels=None):
     """
     Uses the internal tag merge algorithm (experimental).
     """
     success, status = tagmerge.merge(repo, fcd, fco, fca)
     return success, status, False
 
 @internaltool('dump', fullmerge)
 def _idump(repo, mynode, orig, fcd, fco, fca, toolconf, files, labels=None):
     """
     Creates three versions of the files to merge, containing the
     contents of local, other and base. These files can then be used to
     perform a merge manually. If the file to be merged is named
     ``a.txt``, these files will accordingly be named ``a.txt.local``,
     ``a.txt.other`` and ``a.txt.base`` and they will be placed in the
     same directory as ``a.txt``."""
     a, b, c, back = files
 
     fd = fcd.path()
 
     util.copyfile(a, a + ".local")
     repo.wwrite(fd + ".other", fco.data(), fco.flags())
     repo.wwrite(fd + ".base", fca.data(), fca.flags())
     return False, 1, False
 
 def _xmerge(repo, mynode, orig, fcd, fco, fca, toolconf, files, labels=None):
     tool, toolpath, binary, symlink = toolconf
     if fcd.isabsent() or fco.isabsent():
         repo.ui.warn(_('warning: %s cannot merge change/delete conflict '
                        'for %s\n') % (tool, fcd.path()))
         return False, 1, None
     a, b, c, back = files
     out = ""
     env = {'HG_FILE': fcd.path(),
            'HG_MY_NODE': short(mynode),
            'HG_OTHER_NODE': str(fco.changectx()),
            'HG_BASE_NODE': str(fca.changectx()),
            'HG_MY_ISLINK': 'l' in fcd.flags(),
            'HG_OTHER_ISLINK': 'l' in fco.flags(),
            'HG_BASE_ISLINK': 'l' in fca.flags(),
            }
 
     ui = repo.ui
 
     args = _toolstr(ui, tool, "args", '$local $base $other')
     if "$output" in args:
         out, a = a, back # read input from backup, write to original
     replace = {'local': a, 'base': b, 'other': c, 'output': out}
     args = util.interpolate(r'\$', replace, args,
                             lambda s: util.shellquote(util.localpath(s)))
     cmd = toolpath + ' ' + args
     repo.ui.debug('launching merge tool: %s\n' % cmd)
     r = ui.system(cmd, cwd=repo.root, environ=env)
     repo.ui.debug('merge tool returned: %s\n' % r)
     return True, r, False
 
 def _formatconflictmarker(repo, ctx, template, label, pad):
     """Applies the given template to the ctx, prefixed by the label.
 
     Pad is the minimum width of the label prefix, so that multiple markers
     can have aligned templated parts.
     """
     if ctx.node() is None:
         ctx = ctx.p1()
 
     props = templatekw.keywords.copy()
     props['templ'] = template
     props['ctx'] = ctx
     props['repo'] = repo
     templateresult = template('conflictmarker', **props)
 
     label = ('%s:' % label).ljust(pad + 1)
     mark = '%s %s' % (label, templater.stringify(templateresult))
 
     if mark:
         mark = mark.splitlines()[0] # split for safety
 
     # 8 for the prefix of conflict marker lines (e.g. '<<<<<<< ')
     return util.ellipsis(mark, 80 - 8)
 
 _defaultconflictmarker = ('{node|short} '
                           '{ifeq(tags, "tip", "", '
                            'ifeq(tags, "", "", "{tags} "))}'
                           '{if(bookmarks, "{bookmarks} ")}'
                           '{ifeq(branch, "default", "", "{branch} ")}'
                           '- {author|user}: {desc|firstline}')
 
 _defaultconflictlabels = ['local', 'other']
 
 def _formatlabels(repo, fcd, fco, fca, labels):
     """Formats the given labels using the conflict marker template.
 
     Returns a list of formatted labels.
     """
     cd = fcd.changectx()
     co = fco.changectx()
     ca = fca.changectx()
 
     ui = repo.ui
     template = ui.config('ui', 'mergemarkertemplate', _defaultconflictmarker)
     tmpl = formatter.maketemplater(ui, 'conflictmarker', template)
 
     pad = max(len(l) for l in labels)
 
     newlabels = [_formatconflictmarker(repo, cd, tmpl, labels[0], pad),
                  _formatconflictmarker(repo, co, tmpl, labels[1], pad)]
     if len(labels) > 2:
         newlabels.append(_formatconflictmarker(repo, ca, tmpl, labels[2], pad))
     return newlabels
 
 def partextras(labels):
     """Return a dictionary of extra labels for use in prompts to the user
 
     Intended use is in strings of the form "(l)ocal%(l)s".
     """
     if labels is None:
         return {
             "l": "",
             "o": "",
         }
 
     return {
         "l": " [%s]" % labels[0],
         "o": " [%s]" % labels[1],
     }
 
 def _filemerge(premerge, repo, mynode, orig, fcd, fco, fca, labels=None):
     """perform a 3-way merge in the working directory
 
     premerge = whether this is a premerge
     mynode = parent node before merge
     orig = original local filename before merge
     fco = other file context
     fca = ancestor file context
     fcd = local file context for current/destination file
 
     Returns whether the merge is complete, the return value of the merge, and
     a boolean indicating whether the file was deleted from disk."""
 
     def temp(prefix, ctx):
         fullbase, ext = os.path.splitext(ctx.path())
         pre = "%s~%s." % (os.path.basename(fullbase), prefix)
         (fd, name) = tempfile.mkstemp(prefix=pre, suffix=ext)
         data = repo.wwritedata(ctx.path(), ctx.data())
         f = os.fdopen(fd, "wb")
         f.write(data)
         f.close()
         return name
 
     if not fco.cmp(fcd): # files identical?
         return True, None, False
 
     ui = repo.ui
     fd = fcd.path()
     binary = fcd.isbinary() or fco.isbinary() or fca.isbinary()
     symlink = 'l' in fcd.flags() + fco.flags()
     changedelete = fcd.isabsent() or fco.isabsent()
     tool, toolpath = _picktool(repo, ui, fd, binary, symlink, changedelete)
     if tool in internals and tool.startswith('internal:'):
         # normalize to new-style names (':merge' etc)
         tool = tool[len('internal'):]
     ui.debug("picked tool '%s' for %s (binary %s symlink %s changedelete %s)\n"
              % (tool, fd, binary, symlink, changedelete))
 
     if tool in internals:
         func = internals[tool]
         mergetype = func.mergetype
         onfailure = func.onfailure
         precheck = func.precheck
     else:
         func = _xmerge
         mergetype = fullmerge
         onfailure = _("merging %s failed!\n")
         precheck = None
 
     toolconf = tool, toolpath, binary, symlink
 
     if mergetype == nomerge:
         r, deleted = func(repo, mynode, orig, fcd, fco, fca, toolconf, labels)
         return True, r, deleted
 
     if premerge:
         if orig != fco.path():
             ui.status(_("merging %s and %s to %s\n") % (orig, fco.path(), fd))
         else:
             ui.status(_("merging %s\n") % fd)
 
     ui.debug("my %s other %s ancestor %s\n" % (fcd, fco, fca))
 
     if precheck and not precheck(repo, mynode, orig, fcd, fco, fca,
                                  toolconf):
         if onfailure:
             ui.warn(onfailure % fd)
         return True, 1, False
 
     a = repo.wjoin(fd)
     b = temp("base", fca)
     c = temp("other", fco)
     if not fcd.isabsent():
         back = scmutil.origpath(ui, repo, a)
         if premerge:
             util.copyfile(a, back)
     else:
         back = None
     files = (a, b, c, back)
 
     r = 1
     try:
         markerstyle = ui.config('ui', 'mergemarkers', 'basic')
         if not labels:
             labels = _defaultconflictlabels
         if markerstyle != 'basic':
             labels = _formatlabels(repo, fcd, fco, fca, labels)
 
         if premerge and mergetype == fullmerge:
             r = _premerge(repo, fcd, fco, fca, toolconf, files, labels=labels)
             # complete if premerge successful (r is 0)
             return not r, r, False
 
         needcheck, r, deleted = func(repo, mynode, orig, fcd, fco, fca,
                                      toolconf, files, labels=labels)
 
         if needcheck:
             r = _check(r, ui, tool, fcd, files)
 
         if r:
             if onfailure:
                 ui.warn(onfailure % fd)
 
         return True, r, deleted
     finally:
         if not r and back is not None:
             util.unlink(back)
         util.unlink(b)
         util.unlink(c)
 
 def _check(r, ui, tool, fcd, files):
     fd = fcd.path()
     a, b, c, back = files
 
     if not r and (_toolbool(ui, tool, "checkconflicts") or
                   'conflicts' in _toollist(ui, tool, "check")):
         if re.search("^(<<<<<<< .*|=======|>>>>>>> .*)$", fcd.data(),
                      re.MULTILINE):
             r = 1
 
     checked = False
     if 'prompt' in _toollist(ui, tool, "check"):
         checked = True
         if ui.promptchoice(_("was merge of '%s' successful (yn)?"
                              "$$ &Yes $$ &No") % fd, 1):
             r = 1
 
     if not r and not checked and (_toolbool(ui, tool, "checkchanged") or
                                   'changed' in
                                   _toollist(ui, tool, "check")):
         if back is not None and filecmp.cmp(a, back):
             if ui.promptchoice(_(" output file %s appears unchanged\n"
                                  "was merge successful (yn)?"
                                  "$$ &Yes $$ &No") % fd, 1):
                 r = 1
 
     if back is not None and _toolbool(ui, tool, "fixeol"):
         _matcheol(a, back)
 
     return r
 
 def premerge(repo, mynode, orig, fcd, fco, fca, labels=None):
     return _filemerge(True, repo, mynode, orig, fcd, fco, fca, labels=labels)
 
 def filemerge(repo, mynode, orig, fcd, fco, fca, labels=None):
     return _filemerge(False, repo, mynode, orig, fcd, fco, fca, labels=labels)
 
 # tell hggettext to extract docstrings from these functions:
 i18nfunctions = internals.values()

mercurial/hgweb/common.py

@@ -1,200 +1,201
 # hgweb/common.py - Utility functions needed by hgweb_mod and hgwebdir_mod
 #
 # Copyright 21 May 2005 - (c) 2005 Jake Edge <[e-mail]>
 # Copyright 2005, 2006 Matt Mackall <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 from __future__ import absolute_import
 
 import errno
 import mimetypes
 import os
 
 from .. import (
+    encoding,
     pycompat,
     util,
 )
 
 httpserver = util.httpserver
 
 HTTP_OK = 200
 HTTP_NOT_MODIFIED = 304
 HTTP_BAD_REQUEST = 400
 HTTP_UNAUTHORIZED = 401
 HTTP_FORBIDDEN = 403
 HTTP_NOT_FOUND = 404
 HTTP_METHOD_NOT_ALLOWED = 405
 HTTP_SERVER_ERROR = 500
 
 
 def ismember(ui, username, userlist):
     """Check if username is a member of userlist.
 
     If userlist has a single '*' member, all users are considered members.
     Can be overridden by extensions to provide more complex authorization
     schemes.
     """
     return userlist == ['*'] or username in userlist
 
 def checkauthz(hgweb, req, op):
     '''Check permission for operation based on request data (including
     authentication info). Return if op allowed, else raise an ErrorResponse
     exception.'''
 
     user = req.env.get('REMOTE_USER')
 
     deny_read = hgweb.configlist('web', 'deny_read')
     if deny_read and (not user or ismember(hgweb.repo.ui, user, deny_read)):
         raise ErrorResponse(HTTP_UNAUTHORIZED, 'read not authorized')
 
     allow_read = hgweb.configlist('web', 'allow_read')
     if allow_read and (not ismember(hgweb.repo.ui, user, allow_read)):
         raise ErrorResponse(HTTP_UNAUTHORIZED, 'read not authorized')
 
     if op == 'pull' and not hgweb.allowpull:
         raise ErrorResponse(HTTP_UNAUTHORIZED, 'pull not authorized')
     elif op == 'pull' or op is None: # op is None for interface requests
         return
 
     # enforce that you can only push using POST requests
     if req.env['REQUEST_METHOD'] != 'POST':
         msg = 'push requires POST request'
         raise ErrorResponse(HTTP_METHOD_NOT_ALLOWED, msg)
 
     # require ssl by default for pushing, auth info cannot be sniffed
     # and replayed
     scheme = req.env.get('wsgi.url_scheme')
     if hgweb.configbool('web', 'push_ssl', True) and scheme != 'https':
         raise ErrorResponse(HTTP_FORBIDDEN, 'ssl required')
 
     deny = hgweb.configlist('web', 'deny_push')
     if deny and (not user or ismember(hgweb.repo.ui, user, deny)):
         raise ErrorResponse(HTTP_UNAUTHORIZED, 'push not authorized')
 
     allow = hgweb.configlist('web', 'allow_push')
     if not (allow and ismember(hgweb.repo.ui, user, allow)):
         raise ErrorResponse(HTTP_UNAUTHORIZED, 'push not authorized')
 
 # Hooks for hgweb permission checks; extensions can add hooks here.
 # Each hook is invoked like this: hook(hgweb, request, operation),
 # where operation is either read, pull or push. Hooks should either
 # raise an ErrorResponse exception, or just return.
 #
 # It is possible to do both authentication and authorization through
 # this.
 permhooks = [checkauthz]
 
 
 class ErrorResponse(Exception):
     def __init__(self, code, message=None, headers=[]):
         if message is None:
             message = _statusmessage(code)
         Exception.__init__(self, message)
         self.code = code
         self.headers = headers
 
 class continuereader(object):
     def __init__(self, f, write):
         self.f = f
         self._write = write
         self.continued = False
 
     def read(self, amt=-1):
         if not self.continued:
             self.continued = True
             self._write('HTTP/1.1 100 Continue\r\n\r\n')
         return self.f.read(amt)
 
     def __getattr__(self, attr):
         if attr in ('close', 'readline', 'readlines', '__iter__'):
             return getattr(self.f, attr)
         raise AttributeError
 
 def _statusmessage(code):
     responses = httpserver.basehttprequesthandler.responses
     return responses.get(code, ('Error', 'Unknown error'))[0]
 
 def statusmessage(code, message=None):
     return '%d %s' % (code, message or _statusmessage(code))
 
 def get_stat(spath, fn):
     """stat fn if it exists, spath otherwise"""
     cl_path = os.path.join(spath, fn)
     if os.path.exists(cl_path):
         return os.stat(cl_path)
     else:
         return os.stat(spath)
 
 def get_mtime(spath):
     return get_stat(spath, "00changelog.i").st_mtime
 
 def staticfile(directory, fname, req):
     """return a file inside directory with guessed Content-Type header
 
     fname always uses '/' as directory separator and isn't allowed to
     contain unusual path components.
     Content-Type is guessed using the mimetypes module.
     Return an empty string if fname is illegal or file not found.
 
     """
     parts = fname.split('/')
     for part in parts:
         if (part in ('', os.curdir, os.pardir) or
             pycompat.ossep in part or
             pycompat.osaltsep is not None and pycompat.osaltsep in part):
             return
     fpath = os.path.join(*parts)
     if isinstance(directory, str):
         directory = [directory]
     for d in directory:
         path = os.path.join(d, fpath)
         if os.path.exists(path):
             break
     try:
         os.stat(path)
         ct = mimetypes.guess_type(path)[0] or "text/plain"
         fp = open(path, 'rb')
         data = fp.read()
         fp.close()
         req.respond(HTTP_OK, ct, body=data)
     except TypeError:
         raise ErrorResponse(HTTP_SERVER_ERROR, 'illegal filename')
     except OSError as err:
         if err.errno == errno.ENOENT:
             raise ErrorResponse(HTTP_NOT_FOUND)
         else:
             raise ErrorResponse(HTTP_SERVER_ERROR, err.strerror)
 
 def paritygen(stripecount, offset=0):
     """count parity of horizontal stripes for easier reading"""
     if stripecount and offset:
         # account for offset, e.g. due to building the list in reverse
         count = (stripecount + offset) % stripecount
         parity = (stripecount + offset) / stripecount & 1
     else:
         count = 0
         parity = 0
     while True:
         yield parity
         count += 1
         if stripecount and count >= stripecount:
             parity = 1 - parity
             count = 0
 
 def get_contact(config):
     """Return repo contact information or empty string.
 
     web.contact is the primary source, but if that is not set, try
     ui.username or $EMAIL as a fallback to display something useful.
     """
     return (config("web", "contact") or
             config("ui", "username") or
-            os.environ.get("EMAIL") or "")
+            encoding.environ.get("EMAIL") or "")
 
 def caching(web, req):
     tag = 'W/"%s"' % web.mtime
     if req.env.get('HTTP_IF_NONE_MATCH') == tag:
         raise ErrorResponse(HTTP_NOT_MODIFIED)
     req.headers.append(('ETag', tag))

mercurial/hgweb/hgweb_mod.py

@@ -1,469 +1,470
 # 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.
 
 from __future__ import absolute_import
 
 import contextlib
 import os
 
 from .common import (
     ErrorResponse,
     HTTP_BAD_REQUEST,
     HTTP_NOT_FOUND,
     HTTP_NOT_MODIFIED,
     HTTP_OK,
     HTTP_SERVER_ERROR,
     caching,
     permhooks,
 )
 from .request import wsgirequest
 
 from .. import (
     encoding,
     error,
     hg,
     hook,
     profiling,
     repoview,
     templatefilters,
     templater,
     ui as uimod,
     util,
 )
 
 from . import (
     protocol,
     webcommands,
     webutil,
     wsgicgi,
 )
 
 perms = {
     'changegroup': 'pull',
     'changegroupsubset': 'pull',
     'getbundle': 'pull',
     'stream_out': 'pull',
     'listkeys': 'pull',
     'unbundle': 'push',
     'pushkey': 'push',
 }
 
 def makebreadcrumb(url, prefix=''):
     '''Return a 'URL breadcrumb' list
 
     A 'URL breadcrumb' is a list of URL-name pairs,
     corresponding to each of the path items on a URL.
     This can be used to create path navigation entries.
     '''
     if url.endswith('/'):
         url = url[:-1]
     if prefix:
         url = '/' + prefix + url
     relpath = url
     if relpath.startswith('/'):
         relpath = relpath[1:]
 
     breadcrumb = []
     urlel = url
     pathitems = [''] + relpath.split('/')
     for pathel in reversed(pathitems):
         if not pathel or not urlel:
             break
         breadcrumb.append({'url': urlel, 'name': pathel})
         urlel = os.path.dirname(urlel)
     return reversed(breadcrumb)
 
 class requestcontext(object):
     """Holds state/context for an individual request.
 
     Servers can be multi-threaded. Holding state on the WSGI application
     is prone to race conditions. Instances of this class exist to hold
     mutable and race-free state for requests.
     """
     def __init__(self, app, repo):
         self.repo = repo
         self.reponame = app.reponame
 
         self.archives = ('zip', 'gz', 'bz2')
 
         self.maxchanges = self.configint('web', 'maxchanges', 10)
         self.stripecount = self.configint('web', 'stripes', 1)
         self.maxshortchanges = self.configint('web', 'maxshortchanges', 60)
         self.maxfiles = self.configint('web', 'maxfiles', 10)
         self.allowpull = self.configbool('web', 'allowpull', True)
 
         # we use untrusted=False to prevent a repo owner from using
         # web.templates in .hg/hgrc to get access to any file readable
         # by the user running the CGI script
         self.templatepath = self.config('web', 'templates', untrusted=False)
 
         # This object is more expensive to build than simple config values.
         # It is shared across requests. The app will replace the object
         # if it is updated. Since this is a reference and nothing should
         # modify the underlying object, it should be constant for the lifetime
         # of the request.
         self.websubtable = app.websubtable
 
     # 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 configint(self, section, name, default=None, untrusted=True):
         return self.repo.ui.configint(section, name, default,
                                       untrusted=untrusted)
 
     def configlist(self, section, name, default=None, untrusted=True):
         return self.repo.ui.configlist(section, name, default,
                                        untrusted=untrusted)
 
     archivespecs = {
         'bz2': ('application/x-bzip2', 'tbz2', '.tar.bz2', None),
         'gz': ('application/x-gzip', 'tgz', '.tar.gz', None),
         'zip': ('application/zip', 'zip', '.zip', None),
     }
 
     def archivelist(self, nodeid):
         allowed = self.configlist('web', 'allow_archive')
         for typ, spec in self.archivespecs.iteritems():
             if typ in allowed or self.configbool('web', 'allow%s' % typ):
                 yield {'type': typ, 'extension': spec[2], 'node': nodeid}
 
     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)
         logourl = self.config('web', 'logourl', 'https://mercurial-scm.org/')
         logoimg = self.config('web', 'logoimg', 'hglogo.png')
         staticurl = self.config('web', 'staticurl') or req.url + 'static/'
         if not staticurl.endswith('/'):
             staticurl += '/'
 
         # some functions for the templater
 
         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)
 
         def websubfilter(text):
             return templatefilters.websub(text, self.websubtable)
 
         # create the templater
 
         defaults = {
             'url': req.url,
             'logourl': logourl,
             'logoimg': logoimg,
             'staticurl': staticurl,
             'urlbase': urlbase,
             'repo': self.reponame,
             'encoding': encoding.encoding,
             'motd': motd,
             'sessionvars': sessionvars,
             'pathdef': makebreadcrumb(req.url),
             'style': style,
         }
         tmpl = templater.templater.frommapfile(mapfile,
                                                filters={'websub': websubfilter},
                                                defaults=defaults)
         return tmpl
 
 
 class hgweb(object):
     """HTTP server for individual repositories.
 
     Instances of this class serve HTTP responses for a particular
     repository.
 
     Instances are typically used as WSGI applications.
 
     Some servers are multi-threaded. On these servers, there may
     be multiple active threads inside __call__.
     """
     def __init__(self, repo, name=None, baseui=None):
         if isinstance(repo, str):
             if baseui:
                 u = baseui.copy()
             else:
                 u = uimod.ui.load()
             r = hg.repository(u, repo)
         else:
             # we trust caller to give us a private copy
             r = repo
 
         r.ui.setconfig('ui', 'report_untrusted', 'off', 'hgweb')
         r.baseui.setconfig('ui', 'report_untrusted', 'off', 'hgweb')
         r.ui.setconfig('ui', 'nontty', 'true', 'hgweb')
         r.baseui.setconfig('ui', 'nontty', 'true', 'hgweb')
         # resolve file patterns relative to repo root
         r.ui.setconfig('ui', 'forcecwd', r.root, 'hgweb')
         r.baseui.setconfig('ui', 'forcecwd', r.root, 'hgweb')
         # displaying bundling progress bar while serving feel wrong and may
         # break some wsgi implementation.
         r.ui.setconfig('progress', 'disable', 'true', 'hgweb')
         r.baseui.setconfig('progress', 'disable', 'true', 'hgweb')
         self._repos = [hg.cachedlocalrepo(self._webifyrepo(r))]
         self._lastrepo = self._repos[0]
         hook.redirect(True)
         self.reponame = name
 
     def _webifyrepo(self, repo):
         repo = getwebview(repo)
         self.websubtable = webutil.getwebsubs(repo)
         return repo
 
     @contextlib.contextmanager
     def _obtainrepo(self):
         """Obtain a repo unique to the caller.
 
         Internally we maintain a stack of cachedlocalrepo instances
         to be handed out. If one is available, we pop it and return it,
         ensuring it is up to date in the process. If one is not available,
         we clone the most recently used repo instance and return it.
 
         It is currently possible for the stack to grow without bounds
         if the server allows infinite threads. However, servers should
         have a thread limit, thus establishing our limit.
         """
         if self._repos:
             cached = self._repos.pop()
             r, created = cached.fetch()
         else:
             cached = self._lastrepo.copy()
             r, created = cached.fetch()
         if created:
             r = self._webifyrepo(r)
 
         self._lastrepo = cached
         self.mtime = cached.mtime
         try:
             yield r
         finally:
             self._repos.append(cached)
 
     def run(self):
         """Start a server from CGI environment.
 
         Modern servers should be using WSGI and should avoid this
         method, if possible.
         """
-        if not os.environ.get('GATEWAY_INTERFACE', '').startswith("CGI/1."):
+        if not encoding.environ.get('GATEWAY_INTERFACE',
+                                    '').startswith("CGI/1."):
             raise RuntimeError("This function is only intended to be "
                                "called while running as a CGI script.")
         wsgicgi.launch(self)
 
     def __call__(self, env, respond):
         """Run the WSGI application.
 
         This may be called by multiple threads.
         """
         req = wsgirequest(env, respond)
         return self.run_wsgi(req)
 
     def run_wsgi(self, req):
         """Internal method to run the WSGI application.
 
         This is typically only called by Mercurial. External consumers
         should be using instances of this class as the WSGI application.
         """
         with self._obtainrepo() as repo:
             with profiling.maybeprofile(repo.ui):
                 for r in self._runwsgi(req, repo):
                     yield r
 
     def _runwsgi(self, req, repo):
         rctx = requestcontext(self, repo)
 
         # This state is global across all threads.
         encoding.encoding = rctx.config('web', 'encoding', encoding.encoding)
         rctx.repo.ui.environ = req.env
 
         # 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'].partition('&')[0]
             query = query.partition(';')[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 protocol.iscmd(cmd):
             try:
                 if query:
                     raise ErrorResponse(HTTP_NOT_FOUND)
                 if cmd in perms:
                     self.check_perm(rctx, req, perms[cmd])
                 return protocol.call(rctx.repo, req, cmd)
             except ErrorResponse as inst:
                 # A client that sends unbundle without 100-continue will
                 # break if we respond early.
                 if (cmd == 'unbundle' and
                     (req.env.get('HTTP_EXPECT',
                                  '').lower() != '100-continue') or
                     req.env.get('X-HgHttp2', '')):
                     req.drain()
                 else:
                     req.headers.append(('Connection', 'Close'))
                 req.respond(inst, protocol.HGTYPE,
                             body='0\n%s\n' % inst)
                 return ''
 
         # 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 util.safehasattr(webcommands, cmd):
                 req.form['cmd'] = [cmd]
 
             if cmd == 'static':
                 req.form['file'] = ['/'.join(args)]
             else:
                 if args and args[0]:
                     node = args.pop(0).replace('%2F', '/')
                     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 rctx.archivespecs.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 = rctx.templater(req)
             ctype = tmpl('mimetype', encoding=encoding.encoding)
             ctype = templater.stringify(ctype)
 
             # check read permissions non-static content
             if cmd != 'static':
                 self.check_perm(rctx, req, None)
 
             if cmd == '':
                 req.form['cmd'] = [tmpl.cache['default']]
                 cmd = req.form['cmd'][0]
 
             if rctx.configbool('web', 'cache', True):
                 caching(self, req) # sets ETag header or raises NOT_MODIFIED
             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', []):
                 rctx.ctype = ctype
                 content = webcommands.rawfile(rctx, req, tmpl)
             else:
                 content = getattr(webcommands, cmd)(rctx, req, tmpl)
                 req.respond(HTTP_OK, ctype)
 
             return content
 
         except (error.LookupError, error.RepoLookupError) as err:
             req.respond(HTTP_NOT_FOUND, ctype)
             msg = str(err)
             if (util.safehasattr(err, 'name') and
                 not isinstance(err,  error.ManifestLookupError)):
                 msg = 'revision not found: %s' % err.name
             return tmpl('error', error=msg)
         except (error.RepoError, error.RevlogError) as inst:
             req.respond(HTTP_SERVER_ERROR, ctype)
             return tmpl('error', error=str(inst))
         except ErrorResponse as inst:
             req.respond(inst, ctype)
             if inst.code == HTTP_NOT_MODIFIED:
                 # Not allowed to return a body on a 304
                 return ['']
             return tmpl('error', error=str(inst))
 
     def check_perm(self, rctx, req, op):
         for permhook in permhooks:
             permhook(rctx, req, op)
 
 def getwebview(repo):
     """The 'web.view' config controls changeset filter to hgweb. Possible
     values are ``served``, ``visible`` and ``all``. Default is ``served``.
     The ``served`` filter only shows changesets that can be pulled from the
     hgweb instance.  The``visible`` filter includes secret changesets but
     still excludes "hidden" one.
 
     See the repoview module for details.
 
     The option has been around undocumented since Mercurial 2.5, but no
     user ever asked about it. So we better keep it undocumented for now."""
     viewconfig = repo.ui.config('web', 'view', 'served',
                                 untrusted=True)
     if viewconfig == 'all':
         return repo.unfiltered()
     elif viewconfig in repoview.filtertable:
         return repo.filtered(viewconfig)
     else:
         return repo.filtered('served')

mercurial/hgweb/hgwebdir_mod.py

@@ -1,521 +1,522
 # hgweb/hgwebdir_mod.py - Web interface for a directory of repositories.
 #
 # Copyright 21 May 2005 - (c) 2005 Jake Edge <[e-mail]>
 # Copyright 2005, 2006 Matt Mackall <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 from __future__ import absolute_import
 
 import os
 import re
 import time
 
 from ..i18n import _
 
 from .common import (
     ErrorResponse,
     HTTP_NOT_FOUND,
     HTTP_OK,
     HTTP_SERVER_ERROR,
     get_contact,
     get_mtime,
     ismember,
     paritygen,
     staticfile,
 )
 from .request import wsgirequest
 
 from .. import (
     encoding,
     error,
     hg,
     profiling,
     scmutil,
     templater,
     ui as uimod,
     util,
 )
 
 from . import (
     hgweb_mod,
     webutil,
     wsgicgi,
 )
 
 def cleannames(items):
     return [(util.pconvert(name).strip('/'), path) for name, path in items]
 
 def findrepos(paths):
     repos = []
     for prefix, root in cleannames(paths):
         roothead, roottail = os.path.split(root)
         # "foo = /bar/*" or "foo = /bar/**" lets every repo /bar/N in or below
         # /bar/ be served as as foo/N .
         # '*' will not search inside dirs with .hg (except .hg/patches),
         # '**' will search inside dirs with .hg (and thus also find subrepos).
         try:
             recurse = {'*': False, '**': True}[roottail]
         except KeyError:
             repos.append((prefix, root))
             continue
         roothead = os.path.normpath(os.path.abspath(roothead))
         paths = scmutil.walkrepos(roothead, followsym=True, recurse=recurse)
         repos.extend(urlrepos(prefix, roothead, paths))
     return repos
 
 def urlrepos(prefix, roothead, paths):
     """yield url paths and filesystem paths from a list of repo paths
 
     >>> conv = lambda seq: [(v, util.pconvert(p)) for v,p in seq]
     >>> conv(urlrepos('hg', '/opt', ['/opt/r', '/opt/r/r', '/opt']))
     [('hg/r', '/opt/r'), ('hg/r/r', '/opt/r/r'), ('hg', '/opt')]
     >>> conv(urlrepos('', '/opt', ['/opt/r', '/opt/r/r', '/opt']))
     [('r', '/opt/r'), ('r/r', '/opt/r/r'), ('', '/opt')]
     """
     for path in paths:
         path = os.path.normpath(path)
         yield (prefix + '/' +
                util.pconvert(path[len(roothead):]).lstrip('/')).strip('/'), path
 
 def geturlcgivars(baseurl, port):
     """
     Extract CGI variables from baseurl
 
     >>> geturlcgivars("http://host.org/base", "80")
     ('host.org', '80', '/base')
     >>> geturlcgivars("http://host.org:8000/base", "80")
     ('host.org', '8000', '/base')
     >>> geturlcgivars('/base', 8000)
     ('', '8000', '/base')
     >>> geturlcgivars("base", '8000')
     ('', '8000', '/base')
     >>> geturlcgivars("http://host", '8000')
     ('host', '8000', '/')
     >>> geturlcgivars("http://host/", '8000')
     ('host', '8000', '/')
     """
     u = util.url(baseurl)
     name = u.host or ''
     if u.port:
         port = u.port
     path = u.path or ""
     if not path.startswith('/'):
         path = '/' + path
 
     return name, str(port), path
 
 class hgwebdir(object):
     """HTTP server for multiple repositories.
 
     Given a configuration, different repositories will be served depending
     on the request path.
 
     Instances are typically used as WSGI applications.
     """
     def __init__(self, conf, baseui=None):
         self.conf = conf
         self.baseui = baseui
         self.ui = None
         self.lastrefresh = 0
         self.motd = None
         self.refresh()
 
     def refresh(self):
         refreshinterval = 20
         if self.ui:
             refreshinterval = self.ui.configint('web', 'refreshinterval',
                                                 refreshinterval)
 
         # refreshinterval <= 0 means to always refresh.
         if (refreshinterval > 0 and
             self.lastrefresh + refreshinterval > time.time()):
             return
 
         if self.baseui:
             u = self.baseui.copy()
         else:
             u = uimod.ui.load()
             u.setconfig('ui', 'report_untrusted', 'off', 'hgwebdir')
             u.setconfig('ui', 'nontty', 'true', 'hgwebdir')
             # displaying bundling progress bar while serving feels wrong and may
             # break some wsgi implementations.
             u.setconfig('progress', 'disable', 'true', 'hgweb')
 
         if not isinstance(self.conf, (dict, list, tuple)):
             map = {'paths': 'hgweb-paths'}
             if not os.path.exists(self.conf):
                 raise error.Abort(_('config file %s not found!') % self.conf)
             u.readconfig(self.conf, remap=map, trust=True)
             paths = []
             for name, ignored in u.configitems('hgweb-paths'):
                 for path in u.configlist('hgweb-paths', name):
                     paths.append((name, path))
         elif isinstance(self.conf, (list, tuple)):
             paths = self.conf
         elif isinstance(self.conf, dict):
             paths = self.conf.items()
 
         repos = findrepos(paths)
         for prefix, root in u.configitems('collections'):
             prefix = util.pconvert(prefix)
             for path in scmutil.walkrepos(root, followsym=True):
                 repo = os.path.normpath(path)
                 name = util.pconvert(repo)
                 if name.startswith(prefix):
                     name = name[len(prefix):]
                 repos.append((name.lstrip('/'), repo))
 
         self.repos = repos
         self.ui = u
         encoding.encoding = self.ui.config('web', 'encoding',
                                            encoding.encoding)
         self.style = self.ui.config('web', 'style', 'paper')
         self.templatepath = self.ui.config('web', 'templates', None)
         self.stripecount = self.ui.config('web', 'stripes', 1)
         if self.stripecount:
             self.stripecount = int(self.stripecount)
         self._baseurl = self.ui.config('web', 'baseurl')
         prefix = self.ui.config('web', 'prefix', '')
         if prefix.startswith('/'):
             prefix = prefix[1:]
         if prefix.endswith('/'):
             prefix = prefix[:-1]
         self.prefix = prefix
         self.lastrefresh = time.time()
 
     def run(self):
-        if not os.environ.get('GATEWAY_INTERFACE', '').startswith("CGI/1."):
+        if not encoding.environ.get('GATEWAY_INTERFACE',
+                                    '').startswith("CGI/1."):
             raise RuntimeError("This function is only intended to be "
                                "called while running as a CGI script.")
         wsgicgi.launch(self)
 
     def __call__(self, env, respond):
         req = wsgirequest(env, respond)
         return self.run_wsgi(req)
 
     def read_allowed(self, ui, req):
         """Check allow_read and deny_read config options of a repo's ui object
         to determine user permissions.  By default, with neither option set (or
         both empty), allow all users to read the repo.  There are two ways a
         user can be denied read access:  (1) deny_read is not empty, and the
         user is unauthenticated or deny_read contains user (or *), and (2)
         allow_read is not empty and the user is not in allow_read.  Return True
         if user is allowed to read the repo, else return False."""
 
         user = req.env.get('REMOTE_USER')
 
         deny_read = ui.configlist('web', 'deny_read', untrusted=True)
         if deny_read and (not user or ismember(ui, user, deny_read)):
             return False
 
         allow_read = ui.configlist('web', 'allow_read', untrusted=True)
         # by default, allow reading if no allow_read option has been set
         if (not allow_read) or ismember(ui, user, allow_read):
             return True
 
         return False
 
     def run_wsgi(self, req):
         with profiling.maybeprofile(self.ui):
             for r in self._runwsgi(req):
                 yield r
 
     def _runwsgi(self, req):
         try:
             self.refresh()
 
             virtual = req.env.get("PATH_INFO", "").strip('/')
             tmpl = self.templater(req)
             ctype = tmpl('mimetype', encoding=encoding.encoding)
             ctype = templater.stringify(ctype)
 
             # a static file
             if virtual.startswith('static/') or 'static' in req.form:
                 if virtual.startswith('static/'):
                     fname = virtual[7:]
                 else:
                     fname = req.form['static'][0]
                 static = self.ui.config("web", "static", None,
                                         untrusted=False)
                 if not static:
                     tp = self.templatepath or templater.templatepaths()
                     if isinstance(tp, str):
                         tp = [tp]
                     static = [os.path.join(p, 'static') for p in tp]
                 staticfile(static, fname, req)
                 return []
 
             # top-level index
             elif not virtual:
                 req.respond(HTTP_OK, ctype)
                 return self.makeindex(req, tmpl)
 
             # nested indexes and hgwebs
 
             repos = dict(self.repos)
             virtualrepo = virtual
             while virtualrepo:
                 real = repos.get(virtualrepo)
                 if real:
                     req.env['REPO_NAME'] = virtualrepo
                     try:
                         # ensure caller gets private copy of ui
                         repo = hg.repository(self.ui.copy(), real)
                         return hgweb_mod.hgweb(repo).run_wsgi(req)
                     except IOError as inst:
                         msg = inst.strerror
                         raise ErrorResponse(HTTP_SERVER_ERROR, msg)
                     except error.RepoError as inst:
                         raise ErrorResponse(HTTP_SERVER_ERROR, str(inst))
 
                 up = virtualrepo.rfind('/')
                 if up < 0:
                     break
                 virtualrepo = virtualrepo[:up]
 
             # browse subdirectories
             subdir = virtual + '/'
             if [r for r in repos if r.startswith(subdir)]:
                 req.respond(HTTP_OK, ctype)
                 return self.makeindex(req, tmpl, subdir)
 
             # prefixes not found
             req.respond(HTTP_NOT_FOUND, ctype)
             return tmpl("notfound", repo=virtual)
 
         except ErrorResponse as err:
             req.respond(err, ctype)
             return tmpl('error', error=err.message or '')
         finally:
             tmpl = None
 
     def makeindex(self, req, tmpl, subdir=""):
 
         def archivelist(ui, nodeid, url):
             allowed = ui.configlist("web", "allow_archive", untrusted=True)
             archives = []
             for i in [('zip', '.zip'), ('gz', '.tar.gz'), ('bz2', '.tar.bz2')]:
                 if i[0] in allowed or ui.configbool("web", "allow" + i[0],
                                                     untrusted=True):
                     archives.append({"type" : i[0], "extension": i[1],
                                      "node": nodeid, "url": url})
             return archives
 
         def rawentries(subdir="", **map):
 
             descend = self.ui.configbool('web', 'descend', True)
             collapse = self.ui.configbool('web', 'collapse', False)
             seenrepos = set()
             seendirs = set()
             for name, path in self.repos:
 
                 if not name.startswith(subdir):
                     continue
                 name = name[len(subdir):]
                 directory = False
 
                 if '/' in name:
                     if not descend:
                         continue
 
                     nameparts = name.split('/')
                     rootname = nameparts[0]
 
                     if not collapse:
                         pass
                     elif rootname in seendirs:
                         continue
                     elif rootname in seenrepos:
                         pass
                     else:
                         directory = True
                         name = rootname
 
                         # redefine the path to refer to the directory
                         discarded = '/'.join(nameparts[1:])
 
                         # remove name parts plus accompanying slash
                         path = path[:-len(discarded) - 1]
 
                         try:
                             r = hg.repository(self.ui, path)
                             directory = False
                         except (IOError, error.RepoError):
                             pass
 
                 parts = [name]
                 if 'PATH_INFO' in req.env:
                     parts.insert(0, req.env['PATH_INFO'].rstrip('/'))
                 if req.env['SCRIPT_NAME']:
                     parts.insert(0, req.env['SCRIPT_NAME'])
                 url = re.sub(r'/+', '/', '/'.join(parts) + '/')
 
                 # show either a directory entry or a repository
                 if directory:
                     # get the directory's time information
                     try:
                         d = (get_mtime(path), util.makedate()[1])
                     except OSError:
                         continue
 
                     # add '/' to the name to make it obvious that
                     # the entry is a directory, not a regular repository
                     row = {'contact': "",
                            'contact_sort': "",
                            'name': name + '/',
                            'name_sort': name,
                            'url': url,
                            'description': "",
                            'description_sort': "",
                            'lastchange': d,
                            'lastchange_sort': d[1]-d[0],
                            'archives': [],
                            'isdirectory': True,
                            'labels': [],
                            }
 
                     seendirs.add(name)
                     yield row
                     continue
 
                 u = self.ui.copy()
                 try:
                     u.readconfig(os.path.join(path, '.hg', 'hgrc'))
                 except Exception as e:
                     u.warn(_('error reading %s/.hg/hgrc: %s\n') % (path, e))
                     continue
                 def get(section, name, default=None):
                     return u.config(section, name, default, untrusted=True)
 
                 if u.configbool("web", "hidden", untrusted=True):
                     continue
 
                 if not self.read_allowed(u, req):
                     continue
 
                 # update time with local timezone
                 try:
                     r = hg.repository(self.ui, path)
                 except IOError:
                     u.warn(_('error accessing repository at %s\n') % path)
                     continue
                 except error.RepoError:
                     u.warn(_('error accessing repository at %s\n') % path)
                     continue
                 try:
                     d = (get_mtime(r.spath), util.makedate()[1])
                 except OSError:
                     continue
 
                 contact = get_contact(get)
                 description = get("web", "description", "")
                 seenrepos.add(name)
                 name = get("web", "name", name)
                 row = {'contact': contact or "unknown",
                        'contact_sort': contact.upper() or "unknown",
                        'name': name,
                        'name_sort': name,
                        'url': url,
                        'description': description or "unknown",
                        'description_sort': description.upper() or "unknown",
                        'lastchange': d,
                        'lastchange_sort': d[1]-d[0],
                        'archives': archivelist(u, "tip", url),
                        'isdirectory': None,
                        'labels': u.configlist('web', 'labels', untrusted=True),
                        }
 
                 yield row
 
         sortdefault = None, False
         def entries(sortcolumn="", descending=False, subdir="", **map):
             rows = rawentries(subdir=subdir, **map)
 
             if sortcolumn and sortdefault != (sortcolumn, descending):
                 sortkey = '%s_sort' % sortcolumn
                 rows = sorted(rows, key=lambda x: x[sortkey],
                               reverse=descending)
             for row, parity in zip(rows, paritygen(self.stripecount)):
                 row['parity'] = parity
                 yield row
 
         self.refresh()
         sortable = ["name", "description", "contact", "lastchange"]
         sortcolumn, descending = sortdefault
         if 'sort' in req.form:
             sortcolumn = req.form['sort'][0]
             descending = sortcolumn.startswith('-')
             if descending:
                 sortcolumn = sortcolumn[1:]
             if sortcolumn not in sortable:
                 sortcolumn = ""
 
         sort = [("sort_%s" % column,
                  "%s%s" % ((not descending and column == sortcolumn)
                             and "-" or "", column))
                 for column in sortable]
 
         self.refresh()
         self.updatereqenv(req.env)
 
         return tmpl("index", entries=entries, subdir=subdir,
                     pathdef=hgweb_mod.makebreadcrumb('/' + subdir, self.prefix),
                     sortcolumn=sortcolumn, descending=descending,
                     **dict(sort))
 
     def templater(self, req):
 
         def motd(**map):
             if self.motd is not None:
                 yield self.motd
             else:
                 yield config('web', 'motd', '')
 
         def config(section, name, default=None, untrusted=True):
             return self.ui.config(section, name, default, untrusted)
 
         self.updatereqenv(req.env)
 
         url = req.env.get('SCRIPT_NAME', '')
         if not url.endswith('/'):
             url += '/'
 
         vars = {}
         styles = (
             req.form.get('style', [None])[0],
             config('web', 'style'),
             'paper'
         )
         style, mapfile = templater.stylemap(styles, self.templatepath)
         if style == styles[0]:
             vars['style'] = style
 
         start = url[-1] == '?' and '&' or '?'
         sessionvars = webutil.sessionvars(vars, start)
         logourl = config('web', 'logourl', 'https://mercurial-scm.org/')
         logoimg = config('web', 'logoimg', 'hglogo.png')
         staticurl = config('web', 'staticurl') or url + 'static/'
         if not staticurl.endswith('/'):
             staticurl += '/'
 
         defaults = {
             "encoding": encoding.encoding,
             "motd": motd,
             "url": url,
             "logourl": logourl,
             "logoimg": logoimg,
             "staticurl": staticurl,
             "sessionvars": sessionvars,
             "style": style,
         }
         tmpl = templater.templater.frommapfile(mapfile, defaults=defaults)
         return tmpl
 
     def updatereqenv(self, env):
         if self._baseurl is not None:
             name, port, path = geturlcgivars(self._baseurl, env['SERVER_PORT'])
             env['SERVER_NAME'] = name
             env['SERVER_PORT'] = port
             env['SCRIPT_NAME'] = path

mercurial/hgweb/wsgicgi.py

@@ -1,91 +1,90
 # hgweb/wsgicgi.py - CGI->WSGI translator
 #
 # Copyright 2006 Eric Hopper <[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.
 #
 # This was originally copied from the public domain code at
 # http://www.python.org/dev/peps/pep-0333/#the-server-gateway-side
 
 from __future__ import absolute_import
 
-import os
-
 from .. import (
+    encoding,
     util,
 )
 
 from . import (
     common,
 )
 
 def launch(application):
     util.setbinary(util.stdin)
     util.setbinary(util.stdout)
 
-    environ = dict(os.environ.iteritems())
+    environ = dict(encoding.environ.iteritems())
     environ.setdefault('PATH_INFO', '')
     if environ.get('SERVER_SOFTWARE', '').startswith('Microsoft-IIS'):
         # IIS includes script_name in PATH_INFO
         scriptname = environ['SCRIPT_NAME']
         if environ['PATH_INFO'].startswith(scriptname):
             environ['PATH_INFO'] = environ['PATH_INFO'][len(scriptname):]
 
     stdin = util.stdin
     if environ.get('HTTP_EXPECT', '').lower() == '100-continue':
         stdin = common.continuereader(stdin, util.stdout.write)
 
     environ['wsgi.input'] = stdin
     environ['wsgi.errors'] = util.stderr
     environ['wsgi.version'] = (1, 0)
     environ['wsgi.multithread'] = False
     environ['wsgi.multiprocess'] = True
     environ['wsgi.run_once'] = True
 
     if environ.get('HTTPS', 'off').lower() in ('on', '1', 'yes'):
         environ['wsgi.url_scheme'] = 'https'
     else:
         environ['wsgi.url_scheme'] = 'http'
 
     headers_set = []
     headers_sent = []
     out = util.stdout
 
     def write(data):
         if not headers_set:
             raise AssertionError("write() before start_response()")
 
         elif not headers_sent:
             # Before the first output, send the stored headers
             status, response_headers = headers_sent[:] = headers_set
             out.write('Status: %s\r\n' % status)
             for header in response_headers:
                 out.write('%s: %s\r\n' % header)
             out.write('\r\n')
 
         out.write(data)
         out.flush()
 
     def start_response(status, response_headers, exc_info=None):
         if exc_info:
             try:
                 if headers_sent:
                     # Re-raise original exception if headers sent
                     raise exc_info[0](exc_info[1], exc_info[2])
             finally:
                 exc_info = None     # avoid dangling circular ref
         elif headers_set:
             raise AssertionError("Headers already set!")
 
         headers_set[:] = [status, response_headers]
         return write
 
     content = application(environ, start_response)
     try:
         for chunk in content:
             write(chunk)
         if not headers_sent:
             write('')   # send headers now if body was empty
     finally:
         getattr(content, 'close', lambda : None)()

mercurial/url.py

@@ -1,490 +1,491
 # url.py - HTTP handling for mercurial
 #
 # Copyright 2005, 2006, 2007, 2008 Matt Mackall <[e-mail]>
 # Copyright 2006, 2007 Alexis S. L. Carvalho <[e-mail]>
 # 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.
 
 from __future__ import absolute_import
 
 import base64
 import os
 import socket
 
 from .i18n import _
 from . import (
+    encoding,
     error,
     httpconnection as httpconnectionmod,
     keepalive,
     sslutil,
     util,
 )
 
 httplib = util.httplib
 stringio = util.stringio
 urlerr = util.urlerr
 urlreq = util.urlreq
 
 class passwordmgr(object):
     def __init__(self, ui, passwddb):
         self.ui = ui
         self.passwddb = passwddb
 
     def add_password(self, realm, uri, user, passwd):
         return self.passwddb.add_password(realm, uri, user, passwd)
 
     def find_user_password(self, realm, authuri):
         authinfo = self.passwddb.find_user_password(realm, authuri)
         user, passwd = authinfo
         if user and passwd:
             self._writedebug(user, passwd)
             return (user, passwd)
 
         if not user or not passwd:
             res = httpconnectionmod.readauthforuri(self.ui, authuri, user)
             if res:
                 group, auth = res
                 user, passwd = auth.get('username'), auth.get('password')
                 self.ui.debug("using auth.%s.* for authentication\n" % group)
         if not user or not passwd:
             u = util.url(authuri)
             u.query = None
             if not self.ui.interactive():
                 raise error.Abort(_('http authorization required for %s') %
                                  util.hidepassword(str(u)))
 
             self.ui.write(_("http authorization required for %s\n") %
                           util.hidepassword(str(u)))
             self.ui.write(_("realm: %s\n") % realm)
             if user:
                 self.ui.write(_("user: %s\n") % user)
             else:
                 user = self.ui.prompt(_("user:"), default=None)
 
             if not passwd:
                 passwd = self.ui.getpass()
 
         self.passwddb.add_password(realm, authuri, user, passwd)
         self._writedebug(user, passwd)
         return (user, passwd)
 
     def _writedebug(self, user, passwd):
         msg = _('http auth: user %s, password %s\n')
         self.ui.debug(msg % (user, passwd and '*' * len(passwd) or 'not set'))
 
     def find_stored_password(self, authuri):
         return self.passwddb.find_user_password(None, authuri)
 
 class proxyhandler(urlreq.proxyhandler):
     def __init__(self, ui):
         proxyurl = ui.config("http_proxy", "host") or os.getenv('http_proxy')
         # XXX proxyauthinfo = None
 
         if proxyurl:
             # proxy can be proper url or host[:port]
             if not (proxyurl.startswith('http:') or
                     proxyurl.startswith('https:')):
                 proxyurl = 'http://' + proxyurl + '/'
             proxy = util.url(proxyurl)
             if not proxy.user:
                 proxy.user = ui.config("http_proxy", "user")
                 proxy.passwd = ui.config("http_proxy", "passwd")
 
             # see if we should use a proxy for this url
             no_list = ["localhost", "127.0.0.1"]
             no_list.extend([p.lower() for
                             p in ui.configlist("http_proxy", "no")])
             no_list.extend([p.strip().lower() for
                             p in os.getenv("no_proxy", '').split(',')
                             if p.strip()])
             # "http_proxy.always" config is for running tests on localhost
             if ui.configbool("http_proxy", "always"):
                 self.no_list = []
             else:
                 self.no_list = no_list
 
             proxyurl = str(proxy)
             proxies = {'http': proxyurl, 'https': proxyurl}
             ui.debug('proxying through http://%s:%s\n' %
                       (proxy.host, proxy.port))
         else:
             proxies = {}
 
         # urllib2 takes proxy values from the environment and those
         # will take precedence if found. So, if there's a config entry
         # defining a proxy, drop the environment ones
         if ui.config("http_proxy", "host"):
             for env in ["HTTP_PROXY", "http_proxy", "no_proxy"]:
                 try:
-                    if env in os.environ:
-                        del os.environ[env]
+                    if env in encoding.environ:
+                        del encoding.environ[env]
                 except OSError:
                     pass
 
         urlreq.proxyhandler.__init__(self, proxies)
         self.ui = ui
 
     def proxy_open(self, req, proxy, type_):
         host = req.get_host().split(':')[0]
         for e in self.no_list:
             if host == e:
                 return None
             if e.startswith('*.') and host.endswith(e[2:]):
                 return None
             if e.startswith('.') and host.endswith(e[1:]):
                 return None
 
         return urlreq.proxyhandler.proxy_open(self, req, proxy, type_)
 
 def _gen_sendfile(orgsend):
     def _sendfile(self, data):
         # send a file
         if isinstance(data, httpconnectionmod.httpsendfile):
             # if auth required, some data sent twice, so rewind here
             data.seek(0)
             for chunk in util.filechunkiter(data):
                 orgsend(self, chunk)
         else:
             orgsend(self, data)
     return _sendfile
 
 has_https = util.safehasattr(urlreq, 'httpshandler')
 
 class httpconnection(keepalive.HTTPConnection):
     # must be able to send big bundle as stream.
     send = _gen_sendfile(keepalive.HTTPConnection.send)
 
     def getresponse(self):
         proxyres = getattr(self, 'proxyres', None)
         if proxyres:
             if proxyres.will_close:
                 self.close()
             self.proxyres = None
             return proxyres
         return keepalive.HTTPConnection.getresponse(self)
 
 # general transaction handler to support different ways to handle
 # HTTPS proxying before and after Python 2.6.3.
 def _generic_start_transaction(handler, h, req):
     tunnel_host = getattr(req, '_tunnel_host', None)
     if tunnel_host:
         if tunnel_host[:7] not in ['http://', 'https:/']:
             tunnel_host = 'https://' + tunnel_host
         new_tunnel = True
     else:
         tunnel_host = req.get_selector()
         new_tunnel = False
 
     if new_tunnel or tunnel_host == req.get_full_url(): # has proxy
         u = util.url(tunnel_host)
         if new_tunnel or u.scheme == 'https': # only use CONNECT for HTTPS
             h.realhostport = ':'.join([u.host, (u.port or '443')])
             h.headers = req.headers.copy()
             h.headers.update(handler.parent.addheaders)
             return
 
     h.realhostport = None
     h.headers = None
 
 def _generic_proxytunnel(self):
     proxyheaders = dict(
             [(x, self.headers[x]) for x in self.headers
              if x.lower().startswith('proxy-')])
     self.send('CONNECT %s HTTP/1.0\r\n' % self.realhostport)
     for header in proxyheaders.iteritems():
         self.send('%s: %s\r\n' % header)
     self.send('\r\n')
 
     # majority of the following code is duplicated from
     # httplib.HTTPConnection as there are no adequate places to
     # override functions to provide the needed functionality
     res = self.response_class(self.sock,
                               strict=self.strict,
                               method=self._method)
 
     while True:
         version, status, reason = res._read_status()
         if status != httplib.CONTINUE:
             break
         # skip lines that are all whitespace
         list(iter(lambda: res.fp.readline().strip(), ''))
     res.status = status
     res.reason = reason.strip()
 
     if res.status == 200:
         # skip lines until we find a blank line
         list(iter(res.fp.readline, '\r\n'))
         return True
 
     if version == 'HTTP/1.0':
         res.version = 10
     elif version.startswith('HTTP/1.'):
         res.version = 11
     elif version == 'HTTP/0.9':
         res.version = 9
     else:
         raise httplib.UnknownProtocol(version)
 
     if res.version == 9:
         res.length = None
         res.chunked = 0
         res.will_close = 1
         res.msg = httplib.HTTPMessage(stringio())
         return False
 
     res.msg = httplib.HTTPMessage(res.fp)
     res.msg.fp = None
 
     # are we using the chunked-style of transfer encoding?
     trenc = res.msg.getheader('transfer-encoding')
     if trenc and trenc.lower() == "chunked":
         res.chunked = 1
         res.chunk_left = None
     else:
         res.chunked = 0
 
     # will the connection close at the end of the response?
     res.will_close = res._check_close()
 
     # do we have a Content-Length?
     # NOTE: RFC 2616, section 4.4, #3 says we ignore this if
     # transfer-encoding is "chunked"
     length = res.msg.getheader('content-length')
     if length and not res.chunked:
         try:
             res.length = int(length)
         except ValueError:
             res.length = None
         else:
             if res.length < 0:  # ignore nonsensical negative lengths
                 res.length = None
     else:
         res.length = None
 
     # does the body have a fixed length? (of zero)
     if (status == httplib.NO_CONTENT or status == httplib.NOT_MODIFIED or
         100 <= status < 200 or # 1xx codes
         res._method == 'HEAD'):
         res.length = 0
 
     # if the connection remains open, and we aren't using chunked, and
     # a content-length was not provided, then assume that the connection
     # WILL close.
     if (not res.will_close and
        not res.chunked and
        res.length is None):
         res.will_close = 1
 
     self.proxyres = res
 
     return False
 
 class httphandler(keepalive.HTTPHandler):
     def http_open(self, req):
         return self.do_open(httpconnection, req)
 
     def _start_transaction(self, h, req):
         _generic_start_transaction(self, h, req)
         return keepalive.HTTPHandler._start_transaction(self, h, req)
 
 if has_https:
     class httpsconnection(httplib.HTTPConnection):
         response_class = keepalive.HTTPResponse
         default_port = httplib.HTTPS_PORT
         # must be able to send big bundle as stream.
         send = _gen_sendfile(keepalive.safesend)
         getresponse = keepalive.wrapgetresponse(httplib.HTTPConnection)
 
         def __init__(self, host, port=None, key_file=None, cert_file=None,
                      *args, **kwargs):
             httplib.HTTPConnection.__init__(self, host, port, *args, **kwargs)
             self.key_file = key_file
             self.cert_file = cert_file
 
         def connect(self):
             self.sock = socket.create_connection((self.host, self.port))
 
             host = self.host
             if self.realhostport: # use CONNECT proxy
                 _generic_proxytunnel(self)
                 host = self.realhostport.rsplit(':', 1)[0]
             self.sock = sslutil.wrapsocket(
                 self.sock, self.key_file, self.cert_file, ui=self.ui,
                 serverhostname=host)
             sslutil.validatesocket(self.sock)
 
     class httpshandler(keepalive.KeepAliveHandler, urlreq.httpshandler):
         def __init__(self, ui):
             keepalive.KeepAliveHandler.__init__(self)
             urlreq.httpshandler.__init__(self)
             self.ui = ui
             self.pwmgr = passwordmgr(self.ui,
                                      self.ui.httppasswordmgrdb)
 
         def _start_transaction(self, h, req):
             _generic_start_transaction(self, h, req)
             return keepalive.KeepAliveHandler._start_transaction(self, h, req)
 
         def https_open(self, req):
             # req.get_full_url() does not contain credentials and we may
             # need them to match the certificates.
             url = req.get_full_url()
             user, password = self.pwmgr.find_stored_password(url)
             res = httpconnectionmod.readauthforuri(self.ui, url, user)
             if res:
                 group, auth = res
                 self.auth = auth
                 self.ui.debug("using auth.%s.* for authentication\n" % group)
             else:
                 self.auth = None
             return self.do_open(self._makeconnection, req)
 
         def _makeconnection(self, host, port=None, *args, **kwargs):
             keyfile = None
             certfile = None
 
             if len(args) >= 1: # key_file
                 keyfile = args[0]
             if len(args) >= 2: # cert_file
                 certfile = args[1]
             args = args[2:]
 
             # if the user has specified different key/cert files in
             # hgrc, we prefer these
             if self.auth and 'key' in self.auth and 'cert' in self.auth:
                 keyfile = self.auth['key']
                 certfile = self.auth['cert']
 
             conn = httpsconnection(host, port, keyfile, certfile, *args,
                                    **kwargs)
             conn.ui = self.ui
             return conn
 
 class httpdigestauthhandler(urlreq.httpdigestauthhandler):
     def __init__(self, *args, **kwargs):
         urlreq.httpdigestauthhandler.__init__(self, *args, **kwargs)
         self.retried_req = None
 
     def reset_retry_count(self):
         # Python 2.6.5 will call this on 401 or 407 errors and thus loop
         # forever. We disable reset_retry_count completely and reset in
         # http_error_auth_reqed instead.
         pass
 
     def http_error_auth_reqed(self, auth_header, host, req, headers):
         # Reset the retry counter once for each request.
         if req is not self.retried_req:
             self.retried_req = req
             self.retried = 0
         return urlreq.httpdigestauthhandler.http_error_auth_reqed(
                     self, auth_header, host, req, headers)
 
 class httpbasicauthhandler(urlreq.httpbasicauthhandler):
     def __init__(self, *args, **kwargs):
         self.auth = None
         urlreq.httpbasicauthhandler.__init__(self, *args, **kwargs)
         self.retried_req = None
 
     def http_request(self, request):
         if self.auth:
             request.add_unredirected_header(self.auth_header, self.auth)
 
         return request
 
     def https_request(self, request):
         if self.auth:
             request.add_unredirected_header(self.auth_header, self.auth)
 
         return request
 
     def reset_retry_count(self):
         # Python 2.6.5 will call this on 401 or 407 errors and thus loop
         # forever. We disable reset_retry_count completely and reset in
         # http_error_auth_reqed instead.
         pass
 
     def http_error_auth_reqed(self, auth_header, host, req, headers):
         # Reset the retry counter once for each request.
         if req is not self.retried_req:
             self.retried_req = req
             self.retried = 0
         return urlreq.httpbasicauthhandler.http_error_auth_reqed(
                         self, auth_header, host, req, headers)
 
     def retry_http_basic_auth(self, host, req, realm):
         user, pw = self.passwd.find_user_password(realm, req.get_full_url())
         if pw is not None:
             raw = "%s:%s" % (user, pw)
             auth = 'Basic %s' % base64.b64encode(raw).strip()
             if req.get_header(self.auth_header, None) == auth:
                 return None
             self.auth = auth
             req.add_unredirected_header(self.auth_header, auth)
             return self.parent.open(req)
         else:
             return None
 
 handlerfuncs = []
 
 def opener(ui, authinfo=None):
     '''
     construct an opener suitable for urllib2
     authinfo will be added to the password manager
     '''
     # experimental config: ui.usehttp2
     if ui.configbool('ui', 'usehttp2', False):
         handlers = [
             httpconnectionmod.http2handler(
                 ui,
                 passwordmgr(ui, ui.httppasswordmgrdb))
         ]
     else:
         handlers = [httphandler()]
         if has_https:
             handlers.append(httpshandler(ui))
 
     handlers.append(proxyhandler(ui))
 
     passmgr = passwordmgr(ui, ui.httppasswordmgrdb)
     if authinfo is not None:
         realm, uris, user, passwd = authinfo
         saveduser, savedpass = passmgr.find_stored_password(uris[0])
         if user != saveduser or passwd:
             passmgr.add_password(realm, uris, user, passwd)
         ui.debug('http auth: user %s, password %s\n' %
                  (user, passwd and '*' * len(passwd) or 'not set'))
 
     handlers.extend((httpbasicauthhandler(passmgr),
                      httpdigestauthhandler(passmgr)))
     handlers.extend([h(ui, passmgr) for h in handlerfuncs])
     opener = urlreq.buildopener(*handlers)
 
     # The user agent should should *NOT* be used by servers for e.g.
     # protocol detection or feature negotiation: there are other
     # facilities for that.
     #
     # "mercurial/proto-1.0" was the original user agent string and
     # exists for backwards compatibility reasons.
     #
     # The "(Mercurial %s)" string contains the distribution
     # name and version. Other client implementations should choose their
     # own distribution name. Since servers should not be using the user
     # agent string for anything, clients should be able to define whatever
     # user agent they deem appropriate.
     agent = 'mercurial/proto-1.0 (Mercurial %s)' % util.version()
     opener.addheaders = [('User-agent', agent)]
     opener.addheaders.append(('Accept', 'application/mercurial-0.1'))
     return opener
 
 def open(ui, url_, data=None):
     u = util.url(url_)
     if u.scheme:
         u.scheme = u.scheme.lower()
         url_, authinfo = u.authinfo()
     else:
         path = util.normpath(os.path.abspath(url_))
         url_ = 'file://' + urlreq.pathname2url(path)
         authinfo = None
     return opener(ui, authinfo).open(url_, data)

mercurial/windows.py

@@ -1,479 +1,479
 # windows.py - Windows utility function implementations for Mercurial
 #
 #  Copyright 2005-2009 Matt Mackall <[e-mail]> and others
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 from __future__ import absolute_import
 
 import errno
 import msvcrt
 import os
 import re
 import stat
 import sys
 
 from .i18n import _
 from . import (
     encoding,
     osutil,
     pycompat,
     win32,
 )
 
 try:
     import _winreg as winreg
     winreg.CloseKey
 except ImportError:
     import winreg
 
 executablepath = win32.executablepath
 getuser = win32.getuser
 hidewindow = win32.hidewindow
 makedir = win32.makedir
 nlinks = win32.nlinks
 oslink = win32.oslink
 samedevice = win32.samedevice
 samefile = win32.samefile
 setsignalhandler = win32.setsignalhandler
 spawndetached = win32.spawndetached
 split = os.path.split
 testpid = win32.testpid
 unlink = win32.unlink
 
 umask = 0o022
 
 class mixedfilemodewrapper(object):
     """Wraps a file handle when it is opened in read/write mode.
 
     fopen() and fdopen() on Windows have a specific-to-Windows requirement
     that files opened with mode r+, w+, or a+ make a call to a file positioning
     function when switching between reads and writes. Without this extra call,
     Python will raise a not very intuitive "IOError: [Errno 0] Error."
 
     This class wraps posixfile instances when the file is opened in read/write
     mode and automatically adds checks or inserts appropriate file positioning
     calls when necessary.
     """
     OPNONE = 0
     OPREAD = 1
     OPWRITE = 2
 
     def __init__(self, fp):
         object.__setattr__(self, '_fp', fp)
         object.__setattr__(self, '_lastop', 0)
 
     def __getattr__(self, name):
         return getattr(self._fp, name)
 
     def __setattr__(self, name, value):
         return self._fp.__setattr__(name, value)
 
     def _noopseek(self):
         self._fp.seek(0, os.SEEK_CUR)
 
     def seek(self, *args, **kwargs):
         object.__setattr__(self, '_lastop', self.OPNONE)
         return self._fp.seek(*args, **kwargs)
 
     def write(self, d):
         if self._lastop == self.OPREAD:
             self._noopseek()
 
         object.__setattr__(self, '_lastop', self.OPWRITE)
         return self._fp.write(d)
 
     def writelines(self, *args, **kwargs):
         if self._lastop == self.OPREAD:
             self._noopeseek()
 
         object.__setattr__(self, '_lastop', self.OPWRITE)
         return self._fp.writelines(*args, **kwargs)
 
     def read(self, *args, **kwargs):
         if self._lastop == self.OPWRITE:
             self._noopseek()
 
         object.__setattr__(self, '_lastop', self.OPREAD)
         return self._fp.read(*args, **kwargs)
 
     def readline(self, *args, **kwargs):
         if self._lastop == self.OPWRITE:
             self._noopseek()
 
         object.__setattr__(self, '_lastop', self.OPREAD)
         return self._fp.readline(*args, **kwargs)
 
     def readlines(self, *args, **kwargs):
         if self._lastop == self.OPWRITE:
             self._noopseek()
 
         object.__setattr__(self, '_lastop', self.OPREAD)
         return self._fp.readlines(*args, **kwargs)
 
 def posixfile(name, mode='r', buffering=-1):
     '''Open a file with even more POSIX-like semantics'''
     try:
         fp = osutil.posixfile(name, mode, buffering) # may raise WindowsError
 
         # The position when opening in append mode is implementation defined, so
         # make it consistent with other platforms, which position at EOF.
         if 'a' in mode:
             fp.seek(0, os.SEEK_END)
 
         if '+' in mode:
             return mixedfilemodewrapper(fp)
 
         return fp
     except WindowsError as err:
         # convert to a friendlier exception
         raise IOError(err.errno, '%s: %s' % (name, err.strerror))
 
 class winstdout(object):
     '''stdout on windows misbehaves if sent through a pipe'''
 
     def __init__(self, fp):
         self.fp = fp
 
     def __getattr__(self, key):
         return getattr(self.fp, key)
 
     def close(self):
         try:
             self.fp.close()
         except IOError:
             pass
 
     def write(self, s):
         try:
             # This is workaround for "Not enough space" error on
             # writing large size of data to console.
             limit = 16000
             l = len(s)
             start = 0
             self.softspace = 0
             while start < l:
                 end = start + limit
                 self.fp.write(s[start:end])
                 start = end
         except IOError as inst:
             if inst.errno != 0:
                 raise
             self.close()
             raise IOError(errno.EPIPE, 'Broken pipe')
 
     def flush(self):
         try:
             return self.fp.flush()
         except IOError as inst:
             if inst.errno != errno.EINVAL:
                 raise
             self.close()
             raise IOError(errno.EPIPE, 'Broken pipe')
 
 def _is_win_9x():
     '''return true if run on windows 95, 98 or me.'''
     try:
         return sys.getwindowsversion()[3] == 1
     except AttributeError:
-        return 'command' in os.environ.get('comspec', '')
+        return 'command' in encoding.environ.get('comspec', '')
 
 def openhardlinks():
     return not _is_win_9x()
 
 def parsepatchoutput(output_line):
     """parses the output produced by patch and returns the filename"""
     pf = output_line[14:]
     if pf[0] == '`':
         pf = pf[1:-1] # Remove the quotes
     return pf
 
 def sshargs(sshcmd, host, user, port):
     '''Build argument list for ssh or Plink'''
     pflag = 'plink' in sshcmd.lower() and '-P' or '-p'
     args = user and ("%s@%s" % (user, host)) or host
     return port and ("%s %s %s" % (args, pflag, port)) or args
 
 def setflags(f, l, x):
     pass
 
 def copymode(src, dst, mode=None):
     pass
 
 def checkexec(path):
     return False
 
 def checklink(path):
     return False
 
 def setbinary(fd):
     # When run without console, pipes may expose invalid
     # fileno(), usually set to -1.
     fno = getattr(fd, 'fileno', None)
     if fno is not None and fno() >= 0:
         msvcrt.setmode(fno(), os.O_BINARY)
 
 def pconvert(path):
     return path.replace(pycompat.ossep, '/')
 
 def localpath(path):
     return path.replace('/', '\\')
 
 def normpath(path):
     return pconvert(os.path.normpath(path))
 
 def normcase(path):
     return encoding.upper(path) # NTFS compares via upper()
 
 # see posix.py for definitions
 normcasespec = encoding.normcasespecs.upper
 normcasefallback = encoding.upperfallback
 
 def samestat(s1, s2):
     return False
 
 # A sequence of backslashes is special iff it precedes a double quote:
 # - if there's an even number of backslashes, the double quote is not
 #   quoted (i.e. it ends the quoted region)
 # - if there's an odd number of backslashes, the double quote is quoted
 # - in both cases, every pair of backslashes is unquoted into a single
 #   backslash
 # (See http://msdn2.microsoft.com/en-us/library/a1y7w461.aspx )
 # So, to quote a string, we must surround it in double quotes, double
 # the number of backslashes that precede double quotes and add another
 # backslash before every double quote (being careful with the double
 # quote we've appended to the end)
 _quotere = None
 _needsshellquote = None
 def shellquote(s):
     r"""
     >>> shellquote(r'C:\Users\xyz')
     '"C:\\Users\\xyz"'
     >>> shellquote(r'C:\Users\xyz/mixed')
     '"C:\\Users\\xyz/mixed"'
     >>> # Would be safe not to quote too, since it is all double backslashes
     >>> shellquote(r'C:\\Users\\xyz')
     '"C:\\\\Users\\\\xyz"'
     >>> # But this must be quoted
     >>> shellquote(r'C:\\Users\\xyz/abc')
     '"C:\\\\Users\\\\xyz/abc"'
     """
     global _quotere
     if _quotere is None:
         _quotere = re.compile(r'(\\*)("|\\$)')
     global _needsshellquote
     if _needsshellquote is None:
         # ":" is also treated as "safe character", because it is used as a part
         # of path name on Windows.  "\" is also part of a path name, but isn't
         # safe because shlex.split() (kind of) treats it as an escape char and
         # drops it.  It will leave the next character, even if it is another
         # "\".
         _needsshellquote = re.compile(r'[^a-zA-Z0-9._:/-]').search
     if s and not _needsshellquote(s) and not _quotere.search(s):
         # "s" shouldn't have to be quoted
         return s
     return '"%s"' % _quotere.sub(r'\1\1\\\2', s)
 
 def quotecommand(cmd):
     """Build a command string suitable for os.popen* calls."""
     if sys.version_info < (2, 7, 1):
         # Python versions since 2.7.1 do this extra quoting themselves
         return '"' + cmd + '"'
     return cmd
 
 def popen(command, mode='r'):
     # Work around "popen spawned process may not write to stdout
     # under windows"
     # http://bugs.python.org/issue1366
     command += " 2> %s" % os.devnull
     return os.popen(quotecommand(command), mode)
 
 def explainexit(code):
     return _("exited with status %d") % code, code
 
 # if you change this stub into a real check, please try to implement the
 # username and groupname functions above, too.
 def isowner(st):
     return True
 
 def findexe(command):
     '''Find executable for command searching like cmd.exe does.
     If command is a basename then PATH is searched for command.
     PATH isn't searched if command is an absolute or relative path.
     An extension from PATHEXT is found and added if not present.
     If command isn't found None is returned.'''
-    pathext = os.environ.get('PATHEXT', '.COM;.EXE;.BAT;.CMD')
+    pathext = encoding.environ.get('PATHEXT', '.COM;.EXE;.BAT;.CMD')
     pathexts = [ext for ext in pathext.lower().split(pycompat.ospathsep)]
     if os.path.splitext(command)[1].lower() in pathexts:
         pathexts = ['']
 
     def findexisting(pathcommand):
         'Will append extension (if needed) and return existing file'
         for ext in pathexts:
             executable = pathcommand + ext
             if os.path.exists(executable):
                 return executable
         return None
 
     if pycompat.ossep in command:
         return findexisting(command)
 
-    for path in os.environ.get('PATH', '').split(pycompat.ospathsep):
+    for path in encoding.environ.get('PATH', '').split(pycompat.ospathsep):
         executable = findexisting(os.path.join(path, command))
         if executable is not None:
             return executable
     return findexisting(os.path.expanduser(os.path.expandvars(command)))
 
 _wantedkinds = set([stat.S_IFREG, stat.S_IFLNK])
 
 def statfiles(files):
     '''Stat each file in files. Yield each stat, or None if a file
     does not exist or has a type we don't care about.
 
     Cluster and cache stat per directory to minimize number of OS stat calls.'''
     dircache = {} # dirname -> filename -> status | None if file does not exist
     getkind = stat.S_IFMT
     for nf in files:
         nf  = normcase(nf)
         dir, base = os.path.split(nf)
         if not dir:
             dir = '.'
         cache = dircache.get(dir, None)
         if cache is None:
             try:
                 dmap = dict([(normcase(n), s)
                              for n, k, s in osutil.listdir(dir, True)
                              if getkind(s.st_mode) in _wantedkinds])
             except OSError as err:
                 # Python >= 2.5 returns ENOENT and adds winerror field
                 # EINVAL is raised if dir is not a directory.
                 if err.errno not in (errno.ENOENT, errno.EINVAL,
                                      errno.ENOTDIR):
                     raise
                 dmap = {}
             cache = dircache.setdefault(dir, dmap)
         yield cache.get(base, None)
 
 def username(uid=None):
     """Return the name of the user with the given uid.
 
     If uid is None, return the name of the current user."""
     return None
 
 def groupname(gid=None):
     """Return the name of the group with the given gid.
 
     If gid is None, return the name of the current group."""
     return None
 
 def removedirs(name):
     """special version of os.removedirs that does not remove symlinked
     directories or junction points if they actually contain files"""
     if osutil.listdir(name):
         return
     os.rmdir(name)
     head, tail = os.path.split(name)
     if not tail:
         head, tail = os.path.split(head)
     while head and tail:
         try:
             if osutil.listdir(head):
                 return
             os.rmdir(head)
         except (ValueError, OSError):
             break
         head, tail = os.path.split(head)
 
 def unlinkpath(f, ignoremissing=False):
     """unlink and remove the directory if it is empty"""
     try:
         unlink(f)
     except OSError as e:
         if not (ignoremissing and e.errno == errno.ENOENT):
             raise
     # try removing directories that might now be empty
     try:
         removedirs(os.path.dirname(f))
     except OSError:
         pass
 
 def rename(src, dst):
     '''atomically rename file src to dst, replacing dst if it exists'''
     try:
         os.rename(src, dst)
     except OSError as e:
         if e.errno != errno.EEXIST:
             raise
         unlink(dst)
         os.rename(src, dst)
 
 def gethgcmd():
     return [sys.executable] + sys.argv[:1]
 
 def groupmembers(name):
     # Don't support groups on Windows for now
     raise KeyError
 
 def isexec(f):
     return False
 
 class cachestat(object):
     def __init__(self, path):
         pass
 
     def cacheable(self):
         return False
 
 def lookupreg(key, valname=None, scope=None):
     ''' Look up a key/value name in the Windows registry.
 
     valname: value name. If unspecified, the default value for the key
     is used.
     scope: optionally specify scope for registry lookup, this can be
     a sequence of scopes to look up in order. Default (CURRENT_USER,
     LOCAL_MACHINE).
     '''
     if scope is None:
         scope = (winreg.HKEY_CURRENT_USER, winreg.HKEY_LOCAL_MACHINE)
     elif not isinstance(scope, (list, tuple)):
         scope = (scope,)
     for s in scope:
         try:
             val = winreg.QueryValueEx(winreg.OpenKey(s, key), valname)[0]
             # never let a Unicode string escape into the wild
             return encoding.tolocal(val.encode('UTF-8'))
         except EnvironmentError:
             pass
 
 expandglobs = True
 
 def statislink(st):
     '''check whether a stat result is a symlink'''
     return False
 
 def statisexec(st):
     '''check whether a stat result is an executable file'''
     return False
 
 def poll(fds):
     # see posix.py for description
     raise NotImplementedError()
 
 def readpipe(pipe):
     """Read all available data from a pipe."""
     chunks = []
     while True:
         size = win32.peekpipe(pipe)
         if not size:
             break
 
         s = pipe.read(size)
         if not s:
             break
         chunks.append(s)
 
     return ''.join(chunks)
 
 def bindunixsocket(sock, path):
     raise NotImplementedError('unsupported platform')