# HG changeset patch # User Pierre-Yves David # Date 1567551555 -7200 # Node ID 294afb982a8834db6d97cd2cefea5d643024285b # Parent 21025a4107d4fa77e7079204e42cedcf590344ce sidedata: add a function to read sidedata from revlog raw text This implement the "reading" part of a `sidedata` flag processor. Differential Revision: https://phab.mercurial-scm.org/D6890 diff -r 21025a4107d4 -r 294afb982a88 mercurial/error.py --- a/mercurial/error.py Mon Sep 09 14:03:12 2019 +0200 +++ b/mercurial/error.py Wed Sep 04 00:59:15 2019 +0200 @@ -44,6 +44,13 @@ class RevlogError(StorageError): __bytes__ = _tobytes +class SidedataHashError(RevlogError): + + def __init__(self, key, expected, got): + self.sidedatakey = key + self.expecteddigest = expected + self.actualdigest = got + class FilteredIndexError(IndexError): __bytes__ = _tobytes diff -r 21025a4107d4 -r 294afb982a88 mercurial/revlog.py --- a/mercurial/revlog.py Mon Sep 09 14:03:12 2019 +0200 +++ b/mercurial/revlog.py Wed Sep 04 00:59:15 2019 +0200 @@ -1675,7 +1675,13 @@ validatehash = flagutil.processflagsraw(self, rawtext, flags) text = rawtext else: - r = flagutil.processflagsread(self, rawtext, flags) + try: + r = flagutil.processflagsread(self, rawtext, flags) + except error.SidedataHashError as exc: + msg = _("integrity check failed on %s:%s sidedata key %d") + msg %= (self.indexfile, pycompat.bytestr(rev), + exc.sidedatakey) + raise error.RevlogError(msg) text, validatehash, sidedata = r if validatehash: self.checkhash(text, node, rev=rev) diff -r 21025a4107d4 -r 294afb982a88 mercurial/revlogutils/sidedata.py --- a/mercurial/revlogutils/sidedata.py Mon Sep 09 14:03:12 2019 +0200 +++ b/mercurial/revlogutils/sidedata.py Wed Sep 04 00:59:15 2019 +0200 @@ -32,3 +32,32 @@ """ from __future__ import absolute_import + +import hashlib +import struct + +from .. import error + +SIDEDATA_HEADER = struct.Struct('>H') +SIDEDATA_ENTRY = struct.Struct('>HL20s') + +def sidedatareadprocessor(rl, text): + sidedata = {} + offset = 0 + nbentry, = SIDEDATA_HEADER.unpack(text[:SIDEDATA_HEADER.size]) + offset += SIDEDATA_HEADER.size + dataoffset = SIDEDATA_HEADER.size + (SIDEDATA_ENTRY.size * nbentry) + for i in range(nbentry): + nextoffset = offset + SIDEDATA_ENTRY.size + key, size, storeddigest = SIDEDATA_ENTRY.unpack(text[offset:nextoffset]) + offset = nextoffset + # read the data associated with that entry + nextdataoffset = dataoffset + size + entrytext = text[dataoffset:nextdataoffset] + readdigest = hashlib.sha1(entrytext).digest() + if storeddigest != readdigest: + raise error.SidedataHashError(key, storeddigest, readdigest) + sidedata[key] = entrytext + dataoffset = nextdataoffset + text = text[dataoffset:] + return text, True, sidedata