mercurial/config.py
author Gregory Szorc <gregory.szorc@gmail.com>
Mon, 25 May 2015 17:14:11 -0700
changeset 25402 0c2ded041d10
parent 25095 3182965b3971
child 25660 328739ea70c3
permissions -rw-r--r--
exchange: support transferring .hgtags fnodes mapping On Mozilla's mozilla-beta repository .hgtags fnodes resolution takes ~18s from a clean cache on my machine. This means that the first time a user runs `hg tags`, `hg log`, or any other command that displays or accesses tags data, a ~18s pause will occur. There is no output during this pause. This results in a poor user experience and perception that Mercurial is slow. The .hgtags changeset to filenode mapping is deterministic. This patch takes advantage of that property by implementing support for transferring .hgtags filenodes mappings in a dedicated bundle2 part. When a client advertising support for the "hgtagsfnodes" capability requests a bundle, a mapping of changesets to .hgtags filenodes will be sent to the client. Only mappings of head changesets included in the bundle will be sent. The transfer of this mapping effectively eliminates one time tags cache related pauses after initial clone. The mappings are sent as binary data. So, 40 bytes per pair of SHA-1s. On the aforementioned mozilla-beta repository, 659 * 40 = 26,360 raw bytes of mappings are sent over the wire (in addition to the bundle part headers). Assuming 18s to populate the cache, we only need to transfer this extra data faster than 1.5 KB/s for overall clone + tags cache population time to be shorter. Put into perspective, the mozilla-beta repository is ~1 GB in size. So, this additional data constitutes <0.01% of the cloned data. The marginal overhead for a multi-second performance win on clones in my opinion justifies an on-by-default behavior.

# config.py - configuration parsing for Mercurial
#
#  Copyright 2009 Matt Mackall <mpm@selenic.com> 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 i18n import _
import error, util
import os, errno

class config(object):
    def __init__(self, data=None, includepaths=[]):
        self._data = {}
        self._source = {}
        self._unset = []
        self._includepaths = includepaths
        if data:
            for k in data._data:
                self._data[k] = data[k].copy()
            self._source = data._source.copy()
    def copy(self):
        return config(self)
    def __contains__(self, section):
        return section in self._data
    def __getitem__(self, section):
        return self._data.get(section, {})
    def __iter__(self):
        for d in self.sections():
            yield d
    def update(self, src):
        for s, n in src._unset:
            if s in self and n in self._data[s]:
                del self._data[s][n]
                del self._source[(s, n)]
        for s in src:
            if s not in self:
                self._data[s] = util.sortdict()
            self._data[s].update(src._data[s])
        self._source.update(src._source)
    def get(self, section, item, default=None):
        return self._data.get(section, {}).get(item, default)

    def backup(self, section, item):
        """return a tuple allowing restore to reinstall a previous value

        The main reason we need it is because it handles the "no data" case.
        """
        try:
            value = self._data[section][item]
            source = self.source(section, item)
            return (section, item, value, source)
        except KeyError:
            return (section, item)

    def source(self, section, item):
        return self._source.get((section, item), "")
    def sections(self):
        return sorted(self._data.keys())
    def items(self, section):
        return self._data.get(section, {}).items()
    def set(self, section, item, value, source=""):
        if section not in self:
            self._data[section] = util.sortdict()
        self._data[section][item] = value
        if source:
            self._source[(section, item)] = source

    def restore(self, data):
        """restore data returned by self.backup"""
        if len(data) == 4:
            # restore old data
            section, item, value, source = data
            self._data[section][item] = value
            self._source[(section, item)] = source
        else:
            # no data before, remove everything
            section, item = data
            if section in self._data:
                self._data[section].pop(item, None)
            self._source.pop((section, item), None)

    def parse(self, src, data, sections=None, remap=None, include=None):
        sectionre = util.re.compile(r'\[([^\[]+)\]')
        itemre = util.re.compile(r'([^=\s][^=]*?)\s*=\s*(.*\S|)')
        contre = util.re.compile(r'\s+(\S|\S.*\S)\s*$')
        emptyre = util.re.compile(r'(;|#|\s*$)')
        commentre = util.re.compile(r'(;|#)')
        unsetre = util.re.compile(r'%unset\s+(\S+)')
        includere = util.re.compile(r'%include\s+(\S|\S.*\S)\s*$')
        section = ""
        item = None
        line = 0
        cont = False

        for l in data.splitlines(True):
            line += 1
            if line == 1 and l.startswith('\xef\xbb\xbf'):
                # Someone set us up the BOM
                l = l[3:]
            if cont:
                if commentre.match(l):
                    continue
                m = contre.match(l)
                if m:
                    if sections and section not in sections:
                        continue
                    v = self.get(section, item) + "\n" + m.group(1)
                    self.set(section, item, v, "%s:%d" % (src, line))
                    continue
                item = None
                cont = False
            m = includere.match(l)

            if m and include:
                expanded = util.expandpath(m.group(1))
                includepaths = [os.path.dirname(src)] + self._includepaths

                for base in includepaths:
                    inc = os.path.normpath(os.path.join(base, expanded))

                    try:
                        include(inc, remap=remap, sections=sections)
                        break
                    except IOError, inst:
                        if inst.errno != errno.ENOENT:
                            raise error.ParseError(_("cannot include %s (%s)")
                                                   % (inc, inst.strerror),
                                                   "%s:%s" % (src, line))
                continue
            if emptyre.match(l):
                continue
            m = sectionre.match(l)
            if m:
                section = m.group(1)
                if remap:
                    section = remap.get(section, section)
                if section not in self:
                    self._data[section] = util.sortdict()
                continue
            m = itemre.match(l)
            if m:
                item = m.group(1)
                cont = True
                if sections and section not in sections:
                    continue
                self.set(section, item, m.group(2), "%s:%d" % (src, line))
                continue
            m = unsetre.match(l)
            if m:
                name = m.group(1)
                if sections and section not in sections:
                    continue
                if self.get(section, name) is not None:
                    del self._data[section][name]
                self._unset.append((section, name))
                continue

            raise error.ParseError(l.rstrip(), ("%s:%s" % (src, line)))

    def read(self, path, fp=None, sections=None, remap=None):
        if not fp:
            fp = util.posixfile(path)
        self.parse(path, fp.read(), sections, remap, self.read)