annotate mercurial/utils/storageutil.py @ 39878:3e896b51aa5d

storageutil: move metadata parsing and packing from revlog (API)

Parsing and writing of revision text metadata is likely identical
across storage backends. Let's move the code out of revlog so we
don't need to import the revlog module in order to use it.

Differential Revision: https://phab.mercurial-scm.org/D4754

# storageutil.py - Storage functionality agnostic of backend implementation.
#
# Copyright 2018 Gregory Szorc <[e-mail]>
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.

from __future__ import absolute_import

import hashlib
import re

from ..node import (
    nullid,
)

_nullhash = hashlib.sha1(nullid)

def hashrevisionsha1(text, p1, p2):
    """Compute the SHA-1 for revision data and its parents.

    This hash combines both the current file contents and its history
    in a manner that makes it easy to distinguish nodes with the same
    content in the revision graph.
    """
    # As of now, if one of the parent node is null, p2 is null
    if p2 == nullid:
        # deep copy of a hash is faster than creating one
        s = _nullhash.copy()
        s.update(p1)
    else:
        # none of the parent nodes are nullid
        if p1 < p2:
            a = p1
            b = p2
        else:
            a = p2
            b = p1
        s = hashlib.sha1(a)
        s.update(b)
    s.update(text)
    return s.digest()

METADATA_RE = re.compile(b'\x01\n')

def parsemeta(text):
    """Parse metadata header from revision data.

    Returns a 2-tuple of (metadata, offset), where both can be None if there
    is no metadata.
    """
    # text can be buffer, so we can't use .startswith or .index
    if text[:2] != b'\x01\n':
        return None, None
    s = METADATA_RE.search(text, 2).start()
    mtext = text[2:s]
    meta = {}
    for l in mtext.splitlines():
        k, v = l.split(b': ', 1)
        meta[k] = v
    return meta, s + 2

def packmeta(meta, text):
    """Add metadata to fulltext to produce revision text."""
    keys = sorted(meta)
    metatext = b''.join(b'%s: %s\n' % (k, meta[k]) for k in keys)
    return b'\x01\n%s\x01\n%s' % (metatext, text)