comparison mercurial/manifest.py @ 24572:b83679eb5f86

manifestv2: add support for reading new manifest format

The new manifest format is designed to be smaller, in particular to
produce smaller deltas. It stores hashes in binary and puts the hash
on a new line (for smaller deltas). It also uses stem compression to
save space for long paths. The format has room for metadata, but
that's there only for future-proofing. The parser thus accepts any
metadata and throws it away. For more information, see
http://mercurial.selenic.com/wiki/ManifestV2Plan.

The current manifest format doesn't allow an empty filename, so we use
an empty filename on the first line to tell a manifest of the new
format from the old. Since we still never write manifests in the new
format, the added code is unused, but it is tested by
test-manifest.py.

24571:919f8ce040be

import mdiff, parsers, error, revlog, util, scmutil
import array, struct

propertycache = util.propertycache

def _parse(data):
    """Generates (path, node, flags) tuples from a manifest text"""
    # This method does a little bit of excessive-looking
    # precondition checking. This is so that the behavior of this
    # class exactly matches its C counterpart to try and help
    # prevent surprise breakage for anyone that develops against
    # the pure version.

        if len(n) > 40:
            yield f, revlog.bin(n[:40]), n[40:]
        else:
            yield f, revlog.bin(n), ''

def _text(it):
    """Given an iterator over (path, node, flags) tuples, returns a manifest
    text"""
    files = []
    lines = []

except AttributeError:
    pass

class manifestdict(object):
    def __init__(self, data=''):
        self._lm = _lazymanifest(data)

    def __getitem__(self, key):
        return self._lm[key][0]

    def find(self, key):

24572:b83679eb5f86

import mdiff, parsers, error, revlog, util, scmutil
import array, struct

propertycache = util.propertycache

def _parsev1(data):
    # This method does a little bit of excessive-looking
    # precondition checking. This is so that the behavior of this
    # class exactly matches its C counterpart to try and help
    # prevent surprise breakage for anyone that develops against
    # the pure version.

        if len(n) > 40:
            yield f, revlog.bin(n[:40]), n[40:]
        else:
            yield f, revlog.bin(n), ''

def _parsev2(data):
    metadataend = data.find('\n')
    # Just ignore metadata for now
    pos = metadataend + 1
    prevf = ''
    while pos < len(data):
        end = data.find('\n', pos + 1) # +1 to skip stem length byte
        if end == -1:
            raise ValueError('Manifest ended with incomplete file entry.')
        stemlen = ord(data[pos])
        items = data[pos + 1:end].split('\0')
        f = prevf[:stemlen] + items[0]
        if prevf > f:
            raise ValueError('Manifest entries not in sorted order.')
        fl = items[1]
        # Just ignore metadata (items[2:] for now)
        n = data[end + 1:end + 21]
        yield f, n, fl
        pos = end + 22
        prevf = f

def _parse(data):
    """Generates (path, node, flags) tuples from a manifest text"""
    if data.startswith('\0'):
        return iter(_parsev2(data))
    else:
        return iter(_parsev1(data))

def _text(it):
    """Given an iterator over (path, node, flags) tuples, returns a manifest
    text"""
    files = []
    lines = []

except AttributeError:
    pass

class manifestdict(object):
    def __init__(self, data=''):
        if data.startswith('\0'):
            #_lazymanifest can not parse v2
            self._lm = _lazymanifest('')
            for f, n, fl in _parsev2(data):
                self._lm[f] = n, fl
        else:
            self._lm = _lazymanifest(data)

    def __getitem__(self, key):
        return self._lm[key][0]

    def find(self, key):