mercurial/patch.py

commands.import: refactor patch parsing into patch.extract.

# patch.py - patch file parsing routines
#
# Copyright 2006 Brendan Cully <[e-mail]>
#
# This software may be used and distributed according to the terms
# of the GNU General Public License, incorporated herein by reference.

from demandload import demandload
from i18n import gettext as _
demandload(globals(), "util")
demandload(globals(), "cStringIO email.Parser os re shutil tempfile")

def extract(ui, fileobj):
    '''extract patch from data read from fileobj.

    patch can be normal patch or contained in email message.

    return tuple (filename, message, user, date). any item in returned
    tuple can be None.  if filename is None, fileobj did not contain
    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:
        hgpatch = False

        msg = email.Parser.Parser().parse(fileobj)

        message = msg['Subject']
        user = msg['From']
        # should try to parse msg['Date']
        date = None

        if message:
            message = message.replace('\n\t', ' ')
            ui.debug('Subject: %s\n' % message)
        if user:
            ui.debug('From: %s\n' % user)
        diffs_seen = 0
        ok_types = ('text/plain', 'text/x-diff', 'text/x-patch')

        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:
                ui.debug(_('found patch at byte %d\n') % m.start(0))
                diffs_seen += 1
                cfp = cStringIO.StringIO()
                if message:
                    cfp.write(message)
                    cfp.write('\n')
                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()
                    elif hgpatch:
                        if line.startswith('# User '):
                            user = line[7:]
                            ui.debug('From: %s\n' % user)
                        elif line.startswith("# Date "):
                            date = line[7:]
                    if not line.startswith('# '):
                        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

    tmpfp.close()
    if not diffs_seen:
        os.unlink(tmpname)
        return None, message, user, date
    return tmpname, message, user, date

def readgitpatch(patchname):
    """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.copymod = False
            self.lineno = 0
    
    # Filter patch for git information
    gitre = re.compile('diff --git a/(.*) b/(.*)')
    pf = file(patchname)
    gp = None
    gitpatches = []
    # Can have a git patch with only metadata, causing patch to complain
    dopatch = False

    lineno = 0
    for line in pf:
        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'):
                    gp.copymod = True
                    dopatch = 'filter'
                gitpatches.append(gp)
                gp = None
                if not dopatch:
                    dopatch = True
                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()[-3:], 8)
            elif line.startswith('new mode '):
                gp.mode = int(line.rstrip()[-3:], 8)
    if gp:
        gitpatches.append(gp)

    if not gitpatches:
        dopatch = True

    return (dopatch, gitpatches)

def dogitpatch(patchname, gitpatches):
    """Preprocess git patch so that vanilla patch can handle it"""
    pf = file(patchname)
    pfline = 1

    fd, patchname = tempfile.mkstemp(prefix='hg-patch-')
    tmpfp = os.fdopen(fd, 'w')

    try:
        for i in range(len(gitpatches)):
            p = gitpatches[i]
            if not p.copymod:
                continue

            if os.path.exists(p.path):
                raise util.Abort(_("cannot create %s: destination already exists") %
                            p.path)

            (src, dst) = [os.path.join(os.getcwd(), n)
                          for n in (p.oldpath, p.path)]

            targetdir = os.path.dirname(dst)
            if not os.path.isdir(targetdir):
                os.makedirs(targetdir)
            try:
                shutil.copyfile(src, dst)
                shutil.copymode(src, dst)
            except shutil.Error, inst:
                raise util.Abort(str(inst))

            # rewrite patch hunk
            while pfline < p.lineno:
                tmpfp.write(pf.readline())
                pfline += 1
            tmpfp.write('diff --git a/%s b/%s\n' % (p.path, p.path))
            line = pf.readline()
            pfline += 1
            while not line.startswith('--- a/'):
                tmpfp.write(line)
                line = pf.readline()
                pfline += 1
            tmpfp.write('--- a/%s\n' % p.path)

        line = pf.readline()
        while line:
            tmpfp.write(line)
            line = pf.readline()
    except:
        tmpfp.close()
        os.unlink(patchname)
        raise

    tmpfp.close()
    return patchname

def patch(strip, patchname, ui, cwd=None):
    """apply the patch <patchname> to the working directory.
    a list of patched files is returned"""

    (dopatch, gitpatches) = readgitpatch(patchname)

    files = {}
    if dopatch:
        if dopatch == 'filter':
            patchname = dogitpatch(patchname, gitpatches)
        patcher = util.find_in_path('gpatch', os.environ.get('PATH', ''), 'patch')
        args = []
        if cwd:
            args.append('-d %s' % util.shellquote(cwd))
        fp = os.popen('%s %s -p%d < %s' % (patcher, ' '.join(args), strip,
                                           util.shellquote(patchname)))

        if dopatch == 'filter':
            False and os.unlink(patchname)

        for line in fp:
            line = line.rstrip()
            ui.status("%s\n" % line)
            if line.startswith('patching file '):
                pf = util.parse_patch_output(line)
                files.setdefault(pf, (None, None))
        code = fp.close()
        if code:
            raise util.Abort(_("patch command failed: %s") % explain_exit(code)[0])

    for gp in gitpatches:
        files[gp.path] = (gp.op, gp)

    return files