patch: move diff parsing in iterhunks generator

mercurial/patch.py

@@ -1,1360 +1,1377 b''
 # patch.py - patch file parsing routines
 #
 # Copyright 2006 Brendan Cully <[e-mail]>
 # Copyright 2007 Chris Mason <[e-mail]>
 #
 # This software may be used and distributed according to the terms
 # of the GNU General Public License, incorporated herein by reference.
 
 from i18n import _
 from node import *
 import base85, cmdutil, mdiff, util, context, revlog, diffhelpers
 import cStringIO, email.Parser, os, popen2, re, sha, errno
 import sys, tempfile, zlib
 
 class PatchError(Exception):
     pass
 
 class NoHunks(PatchError):
     pass
 
 # helper functions
 
 def copyfile(src, dst, basedir=None):
     if not basedir:
         basedir = os.getcwd()
 
     abssrc, absdst = [os.path.join(basedir, n) for n in (src, dst)]
     if os.path.exists(absdst):
         raise util.Abort(_("cannot create %s: destination already exists") %
                          dst)
 
     targetdir = os.path.dirname(absdst)
     if not os.path.isdir(targetdir):
         os.makedirs(targetdir)
 
     util.copyfile(abssrc, absdst)
 
 # public functions
 
 def extract(ui, fileobj):
     '''extract patch from data read from fileobj.
 
     patch can be a normal patch or contained in an email message.
 
     return tuple (filename, message, user, date, node, p1, p2).
     Any item in the returned tuple can be None. If filename is None,
     fileobj did not contain a patch. Caller must unlink filename when done.'''
 
     # attempt to detect the start of a patch
     # (this heuristic is borrowed from quilt)
     diffre = re.compile(r'^(?:Index:[ \t]|diff[ \t]|RCS file: |' +
                         'retrieving revision [0-9]+(\.[0-9]+)*$|' +
                         '(---|\*\*\*)[ \t])', re.MULTILINE)
 
     fd, tmpname = tempfile.mkstemp(prefix='hg-patch-')
     tmpfp = os.fdopen(fd, 'w')
     try:
         msg = email.Parser.Parser().parse(fileobj)
 
         subject = msg['Subject']
         user = msg['From']
         gitsendmail = 'git-send-email' in msg.get('X-Mailer', '')
         # should try to parse msg['Date']
         date = None
         nodeid = None
         branch = None
         parents = []
 
         if subject:
             if subject.startswith('[PATCH'):
                 pend = subject.find(']')
                 if pend >= 0:
                     subject = subject[pend+1:].lstrip()
             subject = subject.replace('\n\t', ' ')
             ui.debug('Subject: %s\n' % subject)
         if user:
             ui.debug('From: %s\n' % user)
         diffs_seen = 0
         ok_types = ('text/plain', 'text/x-diff', 'text/x-patch')
         message = ''
         for part in msg.walk():
             content_type = part.get_content_type()
             ui.debug('Content-Type: %s\n' % content_type)
             if content_type not in ok_types:
                 continue
             payload = part.get_payload(decode=True)
             m = diffre.search(payload)
             if m:
                 hgpatch = False
                 ignoretext = False
 
                 ui.debug(_('found patch at byte %d\n') % m.start(0))
                 diffs_seen += 1
                 cfp = cStringIO.StringIO()
                 for line in payload[:m.start(0)].splitlines():
                     if line.startswith('# HG changeset patch'):
                         ui.debug(_('patch generated by hg export\n'))
                         hgpatch = True
                         # drop earlier commit message content
                         cfp.seek(0)
                         cfp.truncate()
                         subject = None
                     elif hgpatch:
                         if line.startswith('# User '):
                             user = line[7:]
                             ui.debug('From: %s\n' % user)
                         elif line.startswith("# Date "):
                             date = line[7:]
                         elif line.startswith("# Branch "):
                             branch = line[9:]
                         elif line.startswith("# Node ID "):
                             nodeid = line[10:]
                         elif line.startswith("# Parent "):
                             parents.append(line[10:])
                     elif line == '---' and gitsendmail:
                         ignoretext = True
                     if not line.startswith('# ') and not ignoretext:
                         cfp.write(line)
                         cfp.write('\n')
                 message = cfp.getvalue()
                 if tmpfp:
                     tmpfp.write(payload)
                     if not payload.endswith('\n'):
                         tmpfp.write('\n')
             elif not diffs_seen and message and content_type == 'text/plain':
                 message += '\n' + payload
     except:
         tmpfp.close()
         os.unlink(tmpname)
         raise
 
     if subject and not message.startswith(subject):
         message = '%s\n%s' % (subject, message)
     tmpfp.close()
     if not diffs_seen:
         os.unlink(tmpname)
         return None, message, user, date, branch, None, None, None
     p1 = parents and parents.pop(0) or None
     p2 = parents and parents.pop(0) or None
     return tmpname, message, user, date, branch, nodeid, p1, p2
 
 GP_PATCH  = 1 << 0  # we have to run patch
 GP_FILTER = 1 << 1  # there's some copy/rename operation
 GP_BINARY = 1 << 2  # there's a binary patch
 
 def readgitpatch(fp, firstline=None):
     """extract git-style metadata about patches from <patchname>"""
     class gitpatch:
         "op is one of ADD, DELETE, RENAME, MODIFY or COPY"
         def __init__(self, path):
             self.path = path
             self.oldpath = None
             self.mode = None
             self.op = 'MODIFY'
             self.lineno = 0
             self.binary = False
 
     def reader(fp, firstline):
         if firstline is not None:
             yield firstline
         for line in fp:
             yield line
 
     # Filter patch for git information
     gitre = re.compile('diff --git a/(.*) b/(.*)')
     gp = None
     gitpatches = []
     # Can have a git patch with only metadata, causing patch to complain
     dopatch = 0
 
     lineno = 0
     for line in reader(fp, firstline):
         lineno += 1
         if line.startswith('diff --git'):
             m = gitre.match(line)
             if m:
                 if gp:
                     gitpatches.append(gp)
                 src, dst = m.group(1, 2)
                 gp = gitpatch(dst)
                 gp.lineno = lineno
         elif gp:
             if line.startswith('--- '):
                 if gp.op in ('COPY', 'RENAME'):
                     dopatch |= GP_FILTER
                 gitpatches.append(gp)
                 gp = None
                 dopatch |= GP_PATCH
                 continue
             if line.startswith('rename from '):
                 gp.op = 'RENAME'
                 gp.oldpath = line[12:].rstrip()
             elif line.startswith('rename to '):
                 gp.path = line[10:].rstrip()
             elif line.startswith('copy from '):
                 gp.op = 'COPY'
                 gp.oldpath = line[10:].rstrip()
             elif line.startswith('copy to '):
                 gp.path = line[8:].rstrip()
             elif line.startswith('deleted file'):
                 gp.op = 'DELETE'
             elif line.startswith('new file mode '):
                 gp.op = 'ADD'
                 gp.mode = int(line.rstrip()[-6:], 8)
             elif line.startswith('new mode '):
                 gp.mode = int(line.rstrip()[-6:], 8)
             elif line.startswith('GIT binary patch'):
                 dopatch |= GP_BINARY
                 gp.binary = True
     if gp:
         gitpatches.append(gp)
 
     if not gitpatches:
         dopatch = GP_PATCH
 
     return (dopatch, gitpatches)
 
 def patch(patchname, ui, strip=1, cwd=None, files={}):
     """apply <patchname> to the working directory.
     returns whether patch was applied with fuzz factor."""
     patcher = ui.config('ui', 'patch')
     args = []
     try:
         if patcher:
             return externalpatch(patcher, args, patchname, ui, strip, cwd,
                                  files)
         else:
             try:
                 return internalpatch(patchname, ui, strip, cwd, files)
             except NoHunks:
                 patcher = util.find_exe('gpatch') or util.find_exe('patch')
                 ui.debug('no valid hunks found; trying with %r instead\n' %
                          patcher)
                 if util.needbinarypatch():
                     args.append('--binary')
                 return externalpatch(patcher, args, patchname, ui, strip, cwd,
                                      files)
     except PatchError, err:
         s = str(err)
         if s:
             raise util.Abort(s)
         else:
             raise util.Abort(_('patch failed to apply'))
 
 def externalpatch(patcher, args, patchname, ui, strip, cwd, files):
     """use <patcher> to apply <patchname> to the working directory.
     returns whether patch was applied with fuzz factor."""
 
     fuzz = False
     if cwd:
         args.append('-d %s' % util.shellquote(cwd))
     fp = util.popen('%s %s -p%d < %s' % (patcher, ' '.join(args), strip,
                                        util.shellquote(patchname)))
 
     for line in fp:
         line = line.rstrip()
         ui.note(line + '\n')
         if line.startswith('patching file '):
             pf = util.parse_patch_output(line)
             printed_file = False
             files.setdefault(pf, (None, None))
         elif line.find('with fuzz') >= 0:
             fuzz = True
             if not printed_file:
                 ui.warn(pf + '\n')
                 printed_file = True
             ui.warn(line + '\n')
         elif line.find('saving rejects to file') >= 0:
             ui.warn(line + '\n')
         elif line.find('FAILED') >= 0:
             if not printed_file:
                 ui.warn(pf + '\n')
                 printed_file = True
             ui.warn(line + '\n')
     code = fp.close()
     if code:
         raise PatchError(_("patch command failed: %s") %
                          util.explain_exit(code)[0])
     return fuzz
 
 def internalpatch(patchobj, ui, strip, cwd, files={}):
     """use builtin patch to apply <patchobj> to the working directory.
     returns whether patch was applied with fuzz factor."""
     try:
         fp = file(patchobj, 'rb')
     except TypeError:
         fp = patchobj
     if cwd:
         curdir = os.getcwd()
         os.chdir(cwd)
     try:
         ret = applydiff(ui, fp, files, strip=strip)
     finally:
         if cwd:
             os.chdir(curdir)
     if ret < 0:
         raise PatchError
     return ret > 0
 
 # @@ -start,len +start,len @@ or @@ -start +start @@ if len is 1
 unidesc = re.compile('@@ -(\d+)(,(\d+))? \+(\d+)(,(\d+))? @@')
 contextdesc = re.compile('(---|\*\*\*) (\d+)(,(\d+))? (---|\*\*\*)')
 
 class patchfile:
     def __init__(self, ui, fname):
         self.fname = fname
         self.ui = ui
         try:
             fp = file(fname, 'rb')
             self.lines = fp.readlines()
             self.exists = True
         except IOError:
             dirname = os.path.dirname(fname)
             if dirname and not os.path.isdir(dirname):
                 dirs = dirname.split(os.path.sep)
                 d = ""
                 for x in dirs:
                     d = os.path.join(d, x)
                     if not os.path.isdir(d):
                         os.mkdir(d)
             self.lines = []
             self.exists = False
 
         self.hash = {}
         self.dirty = 0
         self.offset = 0
         self.rej = []
         self.fileprinted = False
         self.printfile(False)
         self.hunks = 0
 
     def printfile(self, warn):
         if self.fileprinted:
             return
         if warn or self.ui.verbose:
             self.fileprinted = True
         s = _("patching file %s\n") % self.fname
         if warn:
             self.ui.warn(s)
         else:
             self.ui.note(s)
 
 
     def findlines(self, l, linenum):
         # looks through the hash and finds candidate lines.  The
         # result is a list of line numbers sorted based on distance
         # from linenum
         def sorter(a, b):
             vala = abs(a - linenum)
             valb = abs(b - linenum)
             return cmp(vala, valb)
 
         try:
             cand = self.hash[l]
         except:
             return []
 
         if len(cand) > 1:
             # resort our list of potentials forward then back.
             cand.sort(sorter)
         return cand
 
     def hashlines(self):
         self.hash = {}
         for x in xrange(len(self.lines)):
             s = self.lines[x]
             self.hash.setdefault(s, []).append(x)
 
     def write_rej(self):
         # our rejects are a little different from patch(1).  This always
         # creates rejects in the same form as the original patch.  A file
         # header is inserted so that you can run the reject through patch again
         # without having to type the filename.
 
         if not self.rej:
             return
         if self.hunks != 1:
             hunkstr = "s"
         else:
             hunkstr = ""
 
         fname = self.fname + ".rej"
         self.ui.warn(
             _("%d out of %d hunk%s FAILED -- saving rejects to file %s\n") %
             (len(self.rej), self.hunks, hunkstr, fname))
         try: os.unlink(fname)
         except:
             pass
         fp = file(fname, 'wb')
         base = os.path.basename(self.fname)
         fp.write("--- %s\n+++ %s\n" % (base, base))
         for x in self.rej:
             for l in x.hunk:
                 fp.write(l)
                 if l[-1] != '\n':
                     fp.write("\n\ No newline at end of file\n")
 
     def write(self, dest=None):
         if self.dirty:
             if not dest:
                 dest = self.fname
             st = None
             try:
                 st = os.lstat(dest)
             except OSError, inst:
                 if inst.errno != errno.ENOENT:
                     raise
             if st and st.st_nlink > 1:
                 os.unlink(dest)
             fp = file(dest, 'wb')
             if st and st.st_nlink > 1:
                 os.chmod(dest, st.st_mode)
             fp.writelines(self.lines)
             fp.close()
 
     def close(self):
         self.write()
         self.write_rej()
 
     def apply(self, h, reverse):
         if not h.complete():
             raise PatchError(_("bad hunk #%d %s (%d %d %d %d)") %
                             (h.number, h.desc, len(h.a), h.lena, len(h.b),
                             h.lenb))
 
         self.hunks += 1
         if reverse:
             h.reverse()
 
         if self.exists and h.createfile():
             self.ui.warn(_("file %s already exists\n") % self.fname)
             self.rej.append(h)
             return -1
 
         if isinstance(h, binhunk):
             if h.rmfile():
                 os.unlink(self.fname)
             else:
                 self.lines[:] = h.new()
                 self.offset += len(h.new())
                 self.dirty = 1
             return 0
 
         # fast case first, no offsets, no fuzz
         old = h.old()
         # patch starts counting at 1 unless we are adding the file
         if h.starta == 0:
             start = 0
         else:
             start = h.starta + self.offset - 1
         orig_start = start
         if diffhelpers.testhunk(old, self.lines, start) == 0:
             if h.rmfile():
                 os.unlink(self.fname)
             else:
                 self.lines[start : start + h.lena] = h.new()
                 self.offset += h.lenb - h.lena
                 self.dirty = 1
             return 0
 
         # ok, we couldn't match the hunk.  Lets look for offsets and fuzz it
         self.hashlines()
         if h.hunk[-1][0] != ' ':
             # if the hunk tried to put something at the bottom of the file
             # override the start line and use eof here
             search_start = len(self.lines)
         else:
             search_start = orig_start
 
         for fuzzlen in xrange(3):
             for toponly in [ True, False ]:
                 old = h.old(fuzzlen, toponly)
 
                 cand = self.findlines(old[0][1:], search_start)
                 for l in cand:
                     if diffhelpers.testhunk(old, self.lines, l) == 0:
                         newlines = h.new(fuzzlen, toponly)
                         self.lines[l : l + len(old)] = newlines
                         self.offset += len(newlines) - len(old)
                         self.dirty = 1
                         if fuzzlen:
                             fuzzstr = "with fuzz %d " % fuzzlen
                             f = self.ui.warn
                             self.printfile(True)
                         else:
                             fuzzstr = ""
                             f = self.ui.note
                         offset = l - orig_start - fuzzlen
                         if offset == 1:
                             linestr = "line"
                         else:
                             linestr = "lines"
                         f(_("Hunk #%d succeeded at %d %s(offset %d %s).\n") %
                           (h.number, l+1, fuzzstr, offset, linestr))
                         return fuzzlen
         self.printfile(True)
         self.ui.warn(_("Hunk #%d FAILED at %d\n") % (h.number, orig_start))
         self.rej.append(h)
         return -1
 
 class hunk:
     def __init__(self, desc, num, lr, context):
         self.number = num
         self.desc = desc
         self.hunk = [ desc ]
         self.a = []
         self.b = []
         if context:
             self.read_context_hunk(lr)
         else:
             self.read_unified_hunk(lr)
 
     def read_unified_hunk(self, lr):
         m = unidesc.match(self.desc)
         if not m:
             raise PatchError(_("bad hunk #%d") % self.number)
         self.starta, foo, self.lena, self.startb, foo2, self.lenb = m.groups()
         if self.lena == None:
             self.lena = 1
         else:
             self.lena = int(self.lena)
         if self.lenb == None:
             self.lenb = 1
         else:
             self.lenb = int(self.lenb)
         self.starta = int(self.starta)
         self.startb = int(self.startb)
         diffhelpers.addlines(lr.fp, self.hunk, self.lena, self.lenb, self.a, self.b)
         # if we hit eof before finishing out the hunk, the last line will
         # be zero length.  Lets try to fix it up.
         while len(self.hunk[-1]) == 0:
                 del self.hunk[-1]
                 del self.a[-1]
                 del self.b[-1]
                 self.lena -= 1
                 self.lenb -= 1
 
     def read_context_hunk(self, lr):
         self.desc = lr.readline()
         m = contextdesc.match(self.desc)
         if not m:
             raise PatchError(_("bad hunk #%d") % self.number)
         foo, self.starta, foo2, aend, foo3 = m.groups()
         self.starta = int(self.starta)
         if aend == None:
             aend = self.starta
         self.lena = int(aend) - self.starta
         if self.starta:
             self.lena += 1
         for x in xrange(self.lena):
             l = lr.readline()
             if l.startswith('---'):
                 lr.push(l)
                 break
             s = l[2:]
             if l.startswith('- ') or l.startswith('! '):
                 u = '-' + s
             elif l.startswith('  '):
                 u = ' ' + s
             else:
                 raise PatchError(_("bad hunk #%d old text line %d") %
                                  (self.number, x))
             self.a.append(u)
             self.hunk.append(u)
 
         l = lr.readline()
         if l.startswith('\ '):
             s = self.a[-1][:-1]
             self.a[-1] = s
             self.hunk[-1] = s
             l = lr.readline()
         m = contextdesc.match(l)
         if not m:
             raise PatchError(_("bad hunk #%d") % self.number)
         foo, self.startb, foo2, bend, foo3 = m.groups()
         self.startb = int(self.startb)
         if bend == None:
             bend = self.startb
         self.lenb = int(bend) - self.startb
         if self.startb:
             self.lenb += 1
         hunki = 1
         for x in xrange(self.lenb):
             l = lr.readline()
             if l.startswith('\ '):
                 s = self.b[-1][:-1]
                 self.b[-1] = s
                 self.hunk[hunki-1] = s
                 continue
             if not l:
                 lr.push(l)
                 break
             s = l[2:]
             if l.startswith('+ ') or l.startswith('! '):
                 u = '+' + s
             elif l.startswith('  '):
                 u = ' ' + s
             elif len(self.b) == 0:
                 # this can happen when the hunk does not add any lines
                 lr.push(l)
                 break
             else:
                 raise PatchError(_("bad hunk #%d old text line %d") %
                                  (self.number, x))
             self.b.append(s)
             while True:
                 if hunki >= len(self.hunk):
                     h = ""
                 else:
                     h = self.hunk[hunki]
                 hunki += 1
                 if h == u:
                     break
                 elif h.startswith('-'):
                     continue
                 else:
                     self.hunk.insert(hunki-1, u)
                     break
 
         if not self.a:
             # this happens when lines were only added to the hunk
             for x in self.hunk:
                 if x.startswith('-') or x.startswith(' '):
                     self.a.append(x)
         if not self.b:
             # this happens when lines were only deleted from the hunk
             for x in self.hunk:
                 if x.startswith('+') or x.startswith(' '):
                     self.b.append(x[1:])
         # @@ -start,len +start,len @@
         self.desc = "@@ -%d,%d +%d,%d @@\n" % (self.starta, self.lena,
                                              self.startb, self.lenb)
         self.hunk[0] = self.desc
 
     def reverse(self):
         origlena = self.lena
         origstarta = self.starta
         self.lena = self.lenb
         self.starta = self.startb
         self.lenb = origlena
         self.startb = origstarta
         self.a = []
         self.b = []
         # self.hunk[0] is the @@ description
         for x in xrange(1, len(self.hunk)):
             o = self.hunk[x]
             if o.startswith('-'):
                 n = '+' + o[1:]
                 self.b.append(o[1:])
             elif o.startswith('+'):
                 n = '-' + o[1:]
                 self.a.append(n)
             else:
                 n = o
                 self.b.append(o[1:])
                 self.a.append(o)
             self.hunk[x] = o
 
     def fix_newline(self):
         diffhelpers.fix_newline(self.hunk, self.a, self.b)
 
     def complete(self):
         return len(self.a) == self.lena and len(self.b) == self.lenb
 
     def createfile(self):
         return self.starta == 0 and self.lena == 0
 
     def rmfile(self):
         return self.startb == 0 and self.lenb == 0
 
     def fuzzit(self, l, fuzz, toponly):
         # this removes context lines from the top and bottom of list 'l'.  It
         # checks the hunk to make sure only context lines are removed, and then
         # returns a new shortened list of lines.
         fuzz = min(fuzz, len(l)-1)
         if fuzz:
             top = 0
             bot = 0
             hlen = len(self.hunk)
             for x in xrange(hlen-1):
                 # the hunk starts with the @@ line, so use x+1
                 if self.hunk[x+1][0] == ' ':
                     top += 1
                 else:
                     break
             if not toponly:
                 for x in xrange(hlen-1):
                     if self.hunk[hlen-bot-1][0] == ' ':
                         bot += 1
                     else:
                         break
 
             # top and bot now count context in the hunk
             # adjust them if either one is short
             context = max(top, bot, 3)
             if bot < context:
                 bot = max(0, fuzz - (context - bot))
             else:
                 bot = min(fuzz, bot)
             if top < context:
                 top = max(0, fuzz - (context - top))
             else:
                 top = min(fuzz, top)
 
             return l[top:len(l)-bot]
         return l
 
     def old(self, fuzz=0, toponly=False):
         return self.fuzzit(self.a, fuzz, toponly)
 
     def newctrl(self):
         res = []
         for x in self.hunk:
             c = x[0]
             if c == ' ' or c == '+':
                 res.append(x)
         return res
 
     def new(self, fuzz=0, toponly=False):
         return self.fuzzit(self.b, fuzz, toponly)
 
 class binhunk:
     'A binary patch file. Only understands literals so far.'
     def __init__(self, gitpatch):
         self.gitpatch = gitpatch
         self.text = None
         self.hunk = ['GIT binary patch\n']
 
     def createfile(self):
         return self.gitpatch.op in ('ADD', 'RENAME', 'COPY')
 
     def rmfile(self):
         return self.gitpatch.op == 'DELETE'
 
     def complete(self):
         return self.text is not None
 
     def new(self):
         return [self.text]
 
     def extract(self, fp):
         line = fp.readline()
         self.hunk.append(line)
         while line and not line.startswith('literal '):
             line = fp.readline()
             self.hunk.append(line)
         if not line:
             raise PatchError(_('could not extract binary patch'))
         size = int(line[8:].rstrip())
         dec = []
         line = fp.readline()
         self.hunk.append(line)
         while len(line) > 1:
             l = line[0]
             if l <= 'Z' and l >= 'A':
                 l = ord(l) - ord('A') + 1
             else:
                 l = ord(l) - ord('a') + 27
             dec.append(base85.b85decode(line[1:-1])[:l])
             line = fp.readline()
             self.hunk.append(line)
         text = zlib.decompress(''.join(dec))
         if len(text) != size:
             raise PatchError(_('binary patch is %d bytes, not %d') %
                              len(text), size)
         self.text = text
 
 def parsefilename(str):
     # --- filename \t|space stuff
     s = str[4:]
     i = s.find('\t')
     if i < 0:
         i = s.find(' ')
         if i < 0:
             return s
     return s[:i]
 
 def selectfile(afile_orig, bfile_orig, hunk, strip, reverse):
     def pathstrip(path, count=1):
         pathlen = len(path)
         i = 0
         if count == 0:
             return path.rstrip()
         while count > 0:
             i = path.find('/', i)
             if i == -1:
                 raise PatchError(_("unable to strip away %d dirs from %s") %
                                  (count, path))
             i += 1
             # consume '//' in the path
             while i < pathlen - 1 and path[i] == '/':
                 i += 1
             count -= 1
         return path[i:].rstrip()
 
     nulla = afile_orig == "/dev/null"
     nullb = bfile_orig == "/dev/null"
     afile = pathstrip(afile_orig, strip)
     gooda = os.path.exists(afile) and not nulla
     bfile = pathstrip(bfile_orig, strip)
     if afile == bfile:
         goodb = gooda
     else:
         goodb = os.path.exists(bfile) and not nullb
     createfunc = hunk.createfile
     if reverse:
         createfunc = hunk.rmfile
     if not goodb and not gooda and not createfunc():
         raise PatchError(_("unable to find %s or %s for patching") %
                          (afile, bfile))
     if gooda and goodb:
         fname = bfile
         if afile in bfile:
             fname = afile
     elif gooda:
         fname = afile
     elif not nullb:
         fname = bfile
         if afile in bfile:
             fname = afile
     elif not nulla:
         fname = afile
     return fname
 
 class linereader:
     # simple class to allow pushing lines back into the input stream
     def __init__(self, fp):
         self.fp = fp
         self.buf = []
 
     def push(self, line):
         self.buf.append(line)
 
     def readline(self):
         if self.buf:
             l = self.buf[0]
             del self.buf[0]
             return l
         return self.fp.readline()
 
-def applydiff(ui, fp, changed, strip=1, sourcefile=None, reverse=False,
-              rejmerge=None, updatedir=None):
-    """reads a patch from fp and tries to apply it.  The dict 'changed' is
-       filled in with all of the filenames changed by the patch.  Returns 0
-       for a clean patch, -1 if any rejects were found and 1 if there was
-       any fuzz."""
+def iterhunks(ui, fp, sourcefile=None):
+    """Read a patch and yield the following events:
+    - ("file", afile, bfile, firsthunk): select a new target file.
+    - ("hunk", hunk): a new hunk is ready to be applied, follows a
+    "file" event.
+    - ("git", gitchanges): current diff is in git format, gitchanges
+    maps filenames to gitpatch records. Unique event.
+    """
 
-    def scangitpatch(fp, firstline, cwd=None):
+    def scangitpatch(fp, firstline):
         '''git patches can modify a file, then copy that file to
         a new file, but expect the source to be the unmodified form.
         So we scan the patch looking for that case so we can do
         the copies ahead of time.'''
 
         pos = 0
         try:
             pos = fp.tell()
         except IOError:
             fp = cStringIO.StringIO(fp.read())
 
         (dopatch, gitpatches) = readgitpatch(fp, firstline)
-        for gp in gitpatches:
-            if gp.op in ('COPY', 'RENAME'):
-                copyfile(gp.oldpath, gp.path, basedir=cwd)
-
         fp.seek(pos)
 
         return fp, dopatch, gitpatches
 
+    changed = {}
     current_hunk = None
-    current_file = None
     afile = ""
     bfile = ""
     state = None
     hunknum = 0
-    rejects = 0
+    emitfile = False
 
     git = False
     gitre = re.compile('diff --git (a/.*) (b/.*)')
 
     # our states
     BFILE = 1
-    err = 0
     context = None
     lr = linereader(fp)
     dopatch = True
     gitworkdone = False
 
-    def getpatchfile(afile, bfile, hunk):
-         try:
-             if sourcefile:
-                 targetfile = patchfile(ui, sourcefile)
-             else:
-                 targetfile = selectfile(afile, bfile, hunk,
-                                         strip, reverse)
-                 targetfile = patchfile(ui, targetfile)
-             return targetfile
-         except PatchError, err:
-             ui.warn(str(err) + '\n')
-             return None
-
     while True:
         newfile = False
         x = lr.readline()
         if not x:
             break
         if current_hunk:
             if x.startswith('\ '):
                 current_hunk.fix_newline()
-            ret = current_file.apply(current_hunk, reverse)
-            if ret >= 0:
-                changed.setdefault(current_file.fname, (None, None))
-                if ret > 0:
-                    err = 1
+            yield 'hunk', current_hunk
             current_hunk = None
             gitworkdone = False
         if ((sourcefile or state == BFILE) and ((not context and x[0] == '@') or
             ((context or context == None) and x.startswith('***************')))):
             try:
                 if context == None and x.startswith('***************'):
                     context = True
                 current_hunk = hunk(x, hunknum + 1, lr, context)
             except PatchError, err:
                 ui.debug(err)
                 current_hunk = None
                 continue
             hunknum += 1
-            if not current_file:
-                current_file = getpatchfile(afile, bfile, current_hunk)
-                if not current_file:
-                    current_file, current_hunk = None, None
-                    rejects += 1
-                    continue
+            if emitfile:
+                emitfile = False
+                yield 'file', (afile, bfile, current_hunk)
         elif state == BFILE and x.startswith('GIT binary patch'):
             current_hunk = binhunk(changed[bfile[2:]][1])
             hunknum += 1
-            if not current_file:
-                current_file = getpatchfile(afile, bfile, current_hunk)
-                if not current_file:
-                    current_file, current_hunk = None, None
-                    rejects += 1
-                    continue
+            if emitfile:
+                emitfile = False
+                yield 'file', (afile, bfile, current_hunk)
             current_hunk.extract(fp)
         elif x.startswith('diff --git'):
             # check for git diff, scanning the whole patch file if needed
             m = gitre.match(x)
             if m:
                 afile, bfile = m.group(1, 2)
                 if not git:
                     git = True
                     fp, dopatch, gitpatches = scangitpatch(fp, x)
+                    yield 'git', gitpatches
                     for gp in gitpatches:
                         changed[gp.path] = (gp.op, gp)
                 # else error?
                 # copy/rename + modify should modify target, not source
                 if changed.get(bfile[2:], (None, None))[0] in ('COPY',
                                                                'RENAME'):
                     afile = bfile
                     gitworkdone = True
             newfile = True
         elif x.startswith('---'):
             # check for a unified diff
             l2 = lr.readline()
             if not l2.startswith('+++'):
                 lr.push(l2)
                 continue
             newfile = True
             context = False
             afile = parsefilename(x)
             bfile = parsefilename(l2)
         elif x.startswith('***'):
             # check for a context diff
             l2 = lr.readline()
             if not l2.startswith('---'):
                 lr.push(l2)
                 continue
             l3 = lr.readline()
             lr.push(l3)
             if not l3.startswith("***************"):
                 lr.push(l2)
                 continue
             newfile = True
             context = True
             afile = parsefilename(x)
             bfile = parsefilename(l2)
 
         if newfile:
-            if current_file:
-                current_file.close()
-                if rejmerge:
-                    rejmerge(current_file)
-                rejects += len(current_file.rej)
+            emitfile = True
             state = BFILE
-            current_file = None
             hunknum = 0
     if current_hunk:
         if current_hunk.complete():
+            yield 'hunk', current_hunk
+        else:
+            raise PatchError(_("malformed patch %s %s") % (afile,
+                             current_hunk.desc))
+
+    if hunknum == 0 and dopatch and not gitworkdone:
+        raise NoHunks
+
+def applydiff(ui, fp, changed, strip=1, sourcefile=None, reverse=False,
+              rejmerge=None, updatedir=None):
+    """reads a patch from fp and tries to apply it.  The dict 'changed' is
+       filled in with all of the filenames changed by the patch.  Returns 0
+       for a clean patch, -1 if any rejects were found and 1 if there was
+       any fuzz."""
+
+    rejects = 0
+    err = 0
+    current_file = None
+    gitpatches = None
+
+    def closefile():
+        if not current_file:
+            return 0
+        current_file.close()
+        if rejmerge:
+            rejmerge(current_file)
+        return len(current_file.rej)
+
+    for state, values in iterhunks(ui, fp, sourcefile):
+        if state == 'hunk':
+            if not current_file:
+                continue
+            current_hunk = values
             ret = current_file.apply(current_hunk, reverse)
             if ret >= 0:
                 changed.setdefault(current_file.fname, (None, None))
                 if ret > 0:
                     err = 1
+        elif state == 'file':
+            rejects += closefile()
+            afile, bfile, first_hunk = values
+            try:
+                if sourcefile:
+                    current_file = patchfile(ui, sourcefile)
+                else:
+                    current_file = selectfile(afile, bfile, first_hunk,
+                                            strip, reverse)
+                    current_file = patchfile(ui, current_file)
+            except PatchError, err:
+                ui.warn(str(err) + '\n')
+                current_file, current_hunk = None, None
+                rejects += 1
+                continue
+        elif state == 'git':
+            gitpatches = values
+            for gp in gitpatches:
+                if gp.op in ('COPY', 'RENAME'):
+                    copyfile(gp.oldpath, gp.path)
+                changed[gp.path] = (gp.op, gp)                
         else:
-            fname = current_file and current_file.fname or None
-            raise PatchError(_("malformed patch %s %s") % (fname,
-                             current_hunk.desc))
-    if current_file:
-        current_file.close()
-        if rejmerge:
-            rejmerge(current_file)
-        rejects += len(current_file.rej)
+            raise util.Abort(_('unsupported parser state: %s') % state)
 
-    if not rejects and hunknum == 0 and dopatch and not gitworkdone:
-        raise NoHunks
-    if updatedir and git:
+    rejects += closefile()
+
+    if updatedir and gitpatches:
         updatedir(gitpatches)
     if rejects:
         return -1
     return err
 
 def diffopts(ui, opts={}, untrusted=False):
     def get(key, name=None):
         return (opts.get(key) or
                 ui.configbool('diff', name or key, None, untrusted=untrusted))
     return mdiff.diffopts(
         text=opts.get('text'),
         git=get('git'),
         nodates=get('nodates'),
         showfunc=get('show_function', 'showfunc'),
         ignorews=get('ignore_all_space', 'ignorews'),
         ignorewsamount=get('ignore_space_change', 'ignorewsamount'),
         ignoreblanklines=get('ignore_blank_lines', 'ignoreblanklines'))
 
 def updatedir(ui, repo, patches):
     '''Update dirstate after patch application according to metadata'''
     if not patches:
         return
     copies = []
     removes = {}
     cfiles = patches.keys()
     cwd = repo.getcwd()
     if cwd:
         cfiles = [util.pathto(repo.root, cwd, f) for f in patches.keys()]
     for f in patches:
         ctype, gp = patches[f]
         if ctype == 'RENAME':
             copies.append((gp.oldpath, gp.path))
             removes[gp.oldpath] = 1
         elif ctype == 'COPY':
             copies.append((gp.oldpath, gp.path))
         elif ctype == 'DELETE':
             removes[gp.path] = 1
     for src, dst in copies:
         repo.copy(src, dst)
     removes = removes.keys()
     if removes:
         removes.sort()
         repo.remove(removes, True)
     for f in patches:
         ctype, gp = patches[f]
         if gp and gp.mode:
             x = gp.mode & 0100 != 0
             l = gp.mode & 020000 != 0
             dst = os.path.join(repo.root, gp.path)
             # patch won't create empty files
             if ctype == 'ADD' and not os.path.exists(dst):
                 repo.wwrite(gp.path, '', x and 'x' or '')
             else:
                 util.set_link(dst, l)
                 if not l:
                     util.set_exec(dst, x)
     cmdutil.addremove(repo, cfiles)
     files = patches.keys()
     files.extend([r for r in removes if r not in files])
     files.sort()
 
     return files
 
 def b85diff(to, tn):
     '''print base85-encoded binary diff'''
     def gitindex(text):
         if not text:
             return '0' * 40
         l = len(text)
         s = sha.new('blob %d\0' % l)
         s.update(text)
         return s.hexdigest()
 
     def fmtline(line):
         l = len(line)
         if l <= 26:
             l = chr(ord('A') + l - 1)
         else:
             l = chr(l - 26 + ord('a') - 1)
         return '%c%s\n' % (l, base85.b85encode(line, True))
 
     def chunk(text, csize=52):
         l = len(text)
         i = 0
         while i < l:
             yield text[i:i+csize]
             i += csize
 
     tohash = gitindex(to)
     tnhash = gitindex(tn)
     if tohash == tnhash:
         return ""
 
     # TODO: deltas
     ret = ['index %s..%s\nGIT binary patch\nliteral %s\n' %
            (tohash, tnhash, len(tn))]
     for l in chunk(zlib.compress(tn)):
         ret.append(fmtline(l))
     ret.append('\n')
     return ''.join(ret)
 
 def diff(repo, node1=None, node2=None, files=None, match=util.always,
          fp=None, changes=None, opts=None):
     '''print diff of changes to files between two nodes, or node and
     working directory.
 
     if node1 is None, use first dirstate parent instead.
     if node2 is None, compare node1 with working directory.'''
 
     if opts is None:
         opts = mdiff.defaultopts
     if fp is None:
         fp = repo.ui
 
     if not node1:
         node1 = repo.dirstate.parents()[0]
 
     ccache = {}
     def getctx(r):
         if r not in ccache:
             ccache[r] = context.changectx(repo, r)
         return ccache[r]
 
     flcache = {}
     def getfilectx(f, ctx):
         flctx = ctx.filectx(f, filelog=flcache.get(f))
         if f not in flcache:
             flcache[f] = flctx._filelog
         return flctx
 
     # reading the data for node1 early allows it to play nicely
     # with repo.status and the revlog cache.
     ctx1 = context.changectx(repo, node1)
     # force manifest reading
     man1 = ctx1.manifest()
     date1 = util.datestr(ctx1.date())
 
     if not changes:
         changes = repo.status(node1, node2, files, match=match)[:5]
     modified, added, removed, deleted, unknown = changes
 
     if not modified and not added and not removed:
         return
 
     if node2:
         ctx2 = context.changectx(repo, node2)
         execf2 = ctx2.manifest().execf
         linkf2 = ctx2.manifest().linkf
     else:
         ctx2 = context.workingctx(repo)
         execf2 = util.execfunc(repo.root, None)
         linkf2 = util.linkfunc(repo.root, None)
         if execf2 is None:
             mc = ctx2.parents()[0].manifest().copy()
             execf2 = mc.execf
             linkf2 = mc.linkf
 
     # returns False if there was no rename between ctx1 and ctx2
     # returns None if the file was created between ctx1 and ctx2
     # returns the (file, node) present in ctx1 that was renamed to f in ctx2
     # This will only really work if c1 is the Nth 1st parent of c2.
     def renamed(c1, c2, man, f):
         startrev = c1.rev()
         c = c2
         crev = c.rev()
         if crev is None:
             crev = repo.changelog.count()
         orig = f
         files = (f,)
         while crev > startrev:
             if f in files:
                 try:
                     src = getfilectx(f, c).renamed()
                 except revlog.LookupError:
                     return None
                 if src:
                     f = src[0]
             crev = c.parents()[0].rev()
             # try to reuse
             c = getctx(crev)
             files = c.files()
         if f not in man:
             return None
         if f == orig:
             return False
         return f
 
     if repo.ui.quiet:
         r = None
     else:
         hexfunc = repo.ui.debugflag and hex or short
         r = [hexfunc(node) for node in [node1, node2] if node]
 
     if opts.git:
         copied = {}
         c1, c2 = ctx1, ctx2
         files = added
         man = man1
         if node2 and ctx1.rev() >= ctx2.rev():
             # renamed() starts at c2 and walks back in history until c1.
             # Since ctx1.rev() >= ctx2.rev(), invert ctx2 and ctx1 to
             # detect (inverted) copies.
             c1, c2 = ctx2, ctx1
             files = removed
             man = ctx2.manifest()
         for f in files:
             src = renamed(c1, c2, man, f)
             if src:
                 copied[f] = src
         if ctx1 == c2:
             # invert the copied dict
             copied = dict([(v, k) for (k, v) in copied.iteritems()])
         # If we've renamed file foo to bar (copied['bar'] = 'foo'),
         # avoid showing a diff for foo if we're going to show
         # the rename to bar.
         srcs = [x[1] for x in copied.iteritems() if x[0] in added]
 
     all = modified + added + removed
     all.sort()
     gone = {}
 
     for f in all:
         to = None
         tn = None
         dodiff = True
         header = []
         if f in man1:
             to = getfilectx(f, ctx1).data()
         if f not in removed:
             tn = getfilectx(f, ctx2).data()
         a, b = f, f
         if opts.git:
             def gitmode(x, l):
                 return l and '120000' or (x and '100755' or '100644')
             def addmodehdr(header, omode, nmode):
                 if omode != nmode:
                     header.append('old mode %s\n' % omode)
                     header.append('new mode %s\n' % nmode)
 
             if f in added:
                 mode = gitmode(execf2(f), linkf2(f))
                 if f in copied:
                     a = copied[f]
                     omode = gitmode(man1.execf(a), man1.linkf(a))
                     addmodehdr(header, omode, mode)
                     if a in removed and a not in gone:
                         op = 'rename'
                         gone[a] = 1
                     else:
                         op = 'copy'
                     header.append('%s from %s\n' % (op, a))
                     header.append('%s to %s\n' % (op, f))
                     to = getfilectx(a, ctx1).data()
                 else:
                     header.append('new file mode %s\n' % mode)
                 if util.binary(tn):
                     dodiff = 'binary'
             elif f in removed:
                 if f in srcs:
                     dodiff = False
                 else:
                     mode = gitmode(man1.execf(f), man1.linkf(f))
                     header.append('deleted file mode %s\n' % mode)
             else:
                 omode = gitmode(man1.execf(f), man1.linkf(f))
                 nmode = gitmode(execf2(f), linkf2(f))
                 addmodehdr(header, omode, nmode)
                 if util.binary(to) or util.binary(tn):
                     dodiff = 'binary'
             r = None
             header.insert(0, 'diff --git a/%s b/%s\n' % (a, b))
         if dodiff:
             if dodiff == 'binary':
                 text = b85diff(to, tn)
             else:
                 text = mdiff.unidiff(to, date1,
                                     # ctx2 date may be dynamic
                                     tn, util.datestr(ctx2.date()),
                                     a, b, r, opts=opts)
             if text or len(header) > 1:
                 fp.write(''.join(header))
             fp.write(text)
 
 def export(repo, revs, template='hg-%h.patch', fp=None, switch_parent=False,
            opts=None):
     '''export changesets as hg patches.'''
 
     total = len(revs)
     revwidth = max([len(str(rev)) for rev in revs])
 
     def single(rev, seqno, fp):
         ctx = repo.changectx(rev)
         node = ctx.node()
         parents = [p.node() for p in ctx.parents() if p]
         branch = ctx.branch()
         if switch_parent:
             parents.reverse()
         prev = (parents and parents[0]) or nullid
 
         if not fp:
             fp = cmdutil.make_file(repo, template, node, total=total,
                                    seqno=seqno, revwidth=revwidth)
         if fp != sys.stdout and hasattr(fp, 'name'):
             repo.ui.note("%s\n" % fp.name)
 
         fp.write("# HG changeset patch\n")
         fp.write("# User %s\n" % ctx.user())
         fp.write("# Date %d %d\n" % ctx.date())
         if branch and (branch != 'default'):
             fp.write("# Branch %s\n" % branch)
         fp.write("# Node ID %s\n" % hex(node))
         fp.write("# Parent  %s\n" % hex(prev))
         if len(parents) > 1:
             fp.write("# Parent  %s\n" % hex(parents[1]))
         fp.write(ctx.description().rstrip())
         fp.write("\n\n")
 
         diff(repo, prev, node, fp=fp, opts=opts)
         if fp not in (sys.stdout, repo.ui):
             fp.close()
 
     for seqno, rev in enumerate(revs):
         single(rev, seqno+1, fp)
 
 def diffstat(patchlines):
     if not util.find_exe('diffstat'):
         return
     fd, name = tempfile.mkstemp(prefix="hg-patchbomb-", suffix=".txt")
     try:
         p = popen2.Popen3('diffstat -p1 -w79 2>/dev/null > ' + name)
         try:
             for line in patchlines: print >> p.tochild, line
             p.tochild.close()
             if p.wait(): return
             fp = os.fdopen(fd, 'r')
             stat = []
             for line in fp: stat.append(line.lstrip())
             last = stat.pop()
             stat.insert(0, last)
             stat = ''.join(stat)
             if stat.startswith('0 files'): raise ValueError
             return stat
         except: raise
     finally:
         try: os.unlink(name)
         except: pass

tests/test-mq-missingfiles.out

@@ -1,25 +1,24 b''
 adding b
 Patch queue now empty
 % push patch with missing target
 applying changeb
 unable to find b or b for patching
-unable to find b or b for patching
 patch failed, unable to continue (try -v)
 patch failed, rejects left in working dir
 Errors during apply, please fix and refresh changeb
 % display added files
 a
 c
 adding b
 Patch queue now empty
 % push git patch with missing target
 applying changeb
 unable to find b or b for patching
 patch failed, unable to continue (try -v)
 b: No such file or directory
 b not tracked!
 patch failed, rejects left in working dir
 Errors during apply, please fix and refresh changeb
 % display added files
 a
 c