view hgext/convert/p4.py @ 16719:e7bf09acd410

localrepo: add branchtip() method for faster single-branch lookups For the PyPy repo with 744 branches and 843 branch heads, this brings hg log -r default over NFS from: CallCount Recursive Total(ms) Inline(ms) module:lineno(function) 3249 0 1.3222 1.3222 <open> 3244 0 0.6211 0.6211 <method 'close' of 'file' objects> 3243 0 0.0800 0.0800 <method 'read' of 'file' objects> 3241 0 0.0660 0.0660 <method 'seek' of 'file' objects> 3905 0 0.0476 0.0476 <zlib.decompress> 3281 0 2.6756 0.0472 mercurial.changelog:182(read) +3281 0 2.5256 0.0453 +mercurial.revlog:881(revision) +3276 0 0.0389 0.0196 +mercurial.changelog:28(decodeextra) +6562 0 0.0123 0.0123 +<method 'split' of 'str' objects> +6562 0 0.0408 0.0073 +mercurial.encoding:61(tolocal) +3281 0 0.0054 0.0054 +<method 'index' of 'str' objects> 3241 0 2.2464 0.0456 mercurial.revlog:818(_loadchunk) +3241 0 0.6205 0.6205 +<method 'close' of 'file' objects> +3241 0 0.0765 0.0765 +<method 'read' of 'file' objects> +3241 0 0.0660 0.0660 +<method 'seek' of 'file' objects> +3241 0 1.4209 0.0135 +mercurial.store:374(__call__) +3241 0 0.0122 0.0107 +mercurial.revlog:810(_addchunk) 3281 0 2.5256 0.0453 mercurial.revlog:881(revision) +3280 0 0.0175 0.0175 +mercurial.revlog:305(rev) +3281 0 2.2819 0.0119 +mercurial.revlog:847(_chunkraw) +3281 0 0.0603 0.0083 +mercurial.revlog:945(_checkhash) +3281 0 0.0051 0.0051 +mercurial.revlog:349(flags) +3281 0 0.0040 0.0040 +<mercurial.mpatch.patches> 13682 0 0.0479 0.0248 <method 'decode' of 'str' objects> +7418 0 0.0228 0.0076 +encodings.utf_8:15(decode) +1 0 0.0003 0.0000 +encodings:71(search_function) 3248 0 1.3995 0.0246 mercurial.scmutil:218(__call__) +3248 0 1.3222 1.3222 +<open> +3248 0 0.0235 0.0184 +os.path:80(split) +3248 0 0.0084 0.0068 +mercurial.scmutil:92(__call__) Time: real 2.750 secs (user 0.680+0.000 sys 0.360+0.000) down to: CallCount Recursive Total(ms) Inline(ms) module:lineno(function) 55 31 0.0197 0.0163 <__import__> +1 0 0.0006 0.0002 +mercurial.context:8(<module>) +1 0 0.0042 0.0001 +mercurial.revlog:12(<module>) +1 0 0.0002 0.0001 +mercurial.match:8(<module>) +1 0 0.0003 0.0001 +mercurial.dirstate:7(<module>) +1 0 0.0057 0.0001 +mercurial.changelog:8(<module>) 1 0 0.0117 0.0032 mercurial.localrepo:525(_readbranchcache) +844 0 0.0015 0.0015 +<binascii.unhexlify> +845 0 0.0010 0.0010 +<method 'split' of 'str' objects> +843 0 0.0045 0.0009 +mercurial.encoding:61(tolocal) +843 0 0.0004 0.0004 +<method 'setdefault' of 'dict' objects> +1 0 0.0003 0.0003 +<method 'close' of 'file' objects> 3 0 0.0029 0.0029 <method 'read' of 'file' objects> 9 0 0.0018 0.0018 <open> 990 0 0.0017 0.0017 <binascii.unhexlify> 53 0 0.0016 0.0016 mercurial.demandimport:43(__init__) 862 0 0.0015 0.0015 <_codecs.utf_8_decode> 862 0 0.0037 0.0014 <method 'decode' of 'str' objects> +862 0 0.0023 0.0008 +encodings.utf_8:15(decode) 981 0 0.0011 0.0011 <method 'split' of 'str' objects> 861 0 0.0046 0.0009 mercurial.encoding:61(tolocal) +861 0 0.0037 0.0014 +<method 'decode' of 'str' objects> 862 0 0.0023 0.0008 encodings.utf_8:15(decode) +862 0 0.0015 0.0015 +<_codecs.utf_8_decode> 4 0 0.0008 0.0008 <method 'close' of 'file' objects> 179 154 0.0202 0.0004 mercurial.demandimport:83(__getattribute__) +36 11 0.0199 0.0003 +mercurial.demandimport:55(_load) +72 0 0.0001 0.0001 +mercurial.demandimport:83(__getattribute__) +36 0 0.0000 0.0000 +<getattr> 1 0 0.0015 0.0004 mercurial.tags:148(_readtagcache) Time: real 0.060 secs (user 0.030+0.000 sys 0.010+0.000)
author Brodie Rao <brodie@sf.io>
date Sun, 13 May 2012 14:04:04 +0200
parents 363e808de349
children c27a37678508
line wrap: on
line source

# Perforce source for convert extension.
#
# Copyright 2009, Frank Kingswood <frank@kingswood-consulting.co.uk>
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.

from mercurial import util
from mercurial.i18n import _

from common import commit, converter_source, checktool, NoRepo
import marshal
import re

def loaditer(f):
    "Yield the dictionary objects generated by p4"
    try:
        while True:
            d = marshal.load(f)
            if not d:
                break
            yield d
    except EOFError:
        pass

class p4_source(converter_source):
    def __init__(self, ui, path, rev=None):
        super(p4_source, self).__init__(ui, path, rev=rev)

        if "/" in path and not path.startswith('//'):
            raise NoRepo(_('%s does not look like a P4 repository') % path)

        checktool('p4', abort=False)

        self.p4changes = {}
        self.heads = {}
        self.changeset = {}
        self.files = {}
        self.tags = {}
        self.lastbranch = {}
        self.parent = {}
        self.encoding = "latin_1"
        self.depotname = {}           # mapping from local name to depot name
        self.re_type = re.compile(
            "([a-z]+)?(text|binary|symlink|apple|resource|unicode|utf\d+)"
            "(\+\w+)?$")
        self.re_keywords = re.compile(
            r"\$(Id|Header|Date|DateTime|Change|File|Revision|Author)"
            r":[^$\n]*\$")
        self.re_keywords_old = re.compile("\$(Id|Header):[^$\n]*\$")

        self._parse(ui, path)

    def _parse_view(self, path):
        "Read changes affecting the path"
        cmd = 'p4 -G changes -s submitted %s' % util.shellquote(path)
        stdout = util.popen(cmd, mode='rb')
        for d in loaditer(stdout):
            c = d.get("change", None)
            if c:
                self.p4changes[c] = True

    def _parse(self, ui, path):
        "Prepare list of P4 filenames and revisions to import"
        ui.status(_('reading p4 views\n'))

        # read client spec or view
        if "/" in path:
            self._parse_view(path)
            if path.startswith("//") and path.endswith("/..."):
                views = {path[:-3]:""}
            else:
                views = {"//": ""}
        else:
            cmd = 'p4 -G client -o %s' % util.shellquote(path)
            clientspec = marshal.load(util.popen(cmd, mode='rb'))

            views = {}
            for client in clientspec:
                if client.startswith("View"):
                    sview, cview = clientspec[client].split()
                    self._parse_view(sview)
                    if sview.endswith("...") and cview.endswith("..."):
                        sview = sview[:-3]
                        cview = cview[:-3]
                    cview = cview[2:]
                    cview = cview[cview.find("/") + 1:]
                    views[sview] = cview

        # list of changes that affect our source files
        self.p4changes = self.p4changes.keys()
        self.p4changes.sort(key=int)

        # list with depot pathnames, longest first
        vieworder = views.keys()
        vieworder.sort(key=len, reverse=True)

        # handle revision limiting
        startrev = self.ui.config('convert', 'p4.startrev', default=0)
        self.p4changes = [x for x in self.p4changes
                          if ((not startrev or int(x) >= int(startrev)) and
                              (not self.rev or int(x) <= int(self.rev)))]

        # now read the full changelists to get the list of file revisions
        ui.status(_('collecting p4 changelists\n'))
        lastid = None
        for change in self.p4changes:
            cmd = "p4 -G describe -s %s" % change
            stdout = util.popen(cmd, mode='rb')
            d = marshal.load(stdout)
            desc = self.recode(d["desc"])
            shortdesc = desc.split("\n", 1)[0]
            t = '%s %s' % (d["change"], repr(shortdesc)[1:-1])
            ui.status(util.ellipsis(t, 80) + '\n')

            if lastid:
                parents = [lastid]
            else:
                parents = []

            date = (int(d["time"]), 0)     # timezone not set
            c = commit(author=self.recode(d["user"]),
                       date=util.datestr(date, '%Y-%m-%d %H:%M:%S %1%2'),
                       parents=parents, desc=desc, branch='',
                       extra={"p4": change})

            files = []
            i = 0
            while ("depotFile%d" % i) in d and ("rev%d" % i) in d:
                oldname = d["depotFile%d" % i]
                filename = None
                for v in vieworder:
                    if oldname.startswith(v):
                        filename = views[v] + oldname[len(v):]
                        break
                if filename:
                    files.append((filename, d["rev%d" % i]))
                    self.depotname[filename] = oldname
                i += 1
            self.changeset[change] = c
            self.files[change] = files
            lastid = change

        if lastid:
            self.heads = [lastid]

    def getheads(self):
        return self.heads

    def getfile(self, name, rev):
        cmd = 'p4 -G print %s' \
            % util.shellquote("%s#%s" % (self.depotname[name], rev))
        stdout = util.popen(cmd, mode='rb')

        mode = None
        contents = ""
        keywords = None

        for d in loaditer(stdout):
            code = d["code"]
            data = d.get("data")

            if code == "error":
                raise IOError(d["generic"], data)

            elif code == "stat":
                p4type = self.re_type.match(d["type"])
                if p4type:
                    mode = ""
                    flags = (p4type.group(1) or "") + (p4type.group(3) or "")
                    if "x" in flags:
                        mode = "x"
                    if p4type.group(2) == "symlink":
                        mode = "l"
                    if "ko" in flags:
                        keywords = self.re_keywords_old
                    elif "k" in flags:
                        keywords = self.re_keywords

            elif code == "text" or code == "binary":
                contents += data

        if mode is None:
            raise IOError(0, "bad stat")

        if keywords:
            contents = keywords.sub("$\\1$", contents)
        if mode == "l" and contents.endswith("\n"):
            contents = contents[:-1]

        return contents, mode

    def getchanges(self, rev):
        return self.files[rev], {}

    def getcommit(self, rev):
        return self.changeset[rev]

    def gettags(self):
        return self.tags

    def getchangedfiles(self, rev, i):
        return sorted([x[0] for x in self.files[rev]])