| indygreg | |
| Alphare |
| hg-reviewers |
We drop two unused entry. This is mostly a proof of concept before starting to
actually rework the format.
| Automatic diff as part of commit; lint not applicable. |
| Automatic diff as part of commit; unit tests not applicable. |
| Path | Packages | |||
|---|---|---|---|---|
| M | mercurial/configitems.py (1 line) | |||
| M | mercurial/pure/parsers.py (24 lines) | |||
| M | mercurial/revlog.py (11 lines) | |||
| M | mercurial/revlogutils/constants.py (14 lines) |
| b'format', | b'format', | ||||
| b'revlog-compression', | b'revlog-compression', | ||||
| default=lambda: [b'zstd', b'zlib'], | default=lambda: [b'zstd', b'zlib'], | ||||
| alias=[(b'experimental', b'format.compression')], | alias=[(b'experimental', b'format.compression')], | ||||
| ) | ) | ||||
| # Experimental TODOs: | # Experimental TODOs: | ||||
| # | # | ||||
| # * Same as for evlogv2 (but for the reduction of the number of files) | # * Same as for evlogv2 (but for the reduction of the number of files) | ||||
| # * drop the storage of the base | |||||
| # * Improvement to investigate | # * Improvement to investigate | ||||
| # - storing .hgtags fnode | # - storing .hgtags fnode | ||||
| # - storing `rank` of changesets | # - storing `rank` of changesets | ||||
| # - storing branch related identifier | # - storing branch related identifier | ||||
| coreconfigitem( | coreconfigitem( | ||||
| b'format', | b'format', | ||||
| b'exp-use-changelog-v2', | b'exp-use-changelog-v2', | ||||
| def parse_index2(data, inline, revlogv2=False): | def parse_index2(data, inline, revlogv2=False): | ||||
| if not inline: | if not inline: | ||||
| cls = IndexObject2 if revlogv2 else IndexObject | cls = IndexObject2 if revlogv2 else IndexObject | ||||
| return cls(data), None | return cls(data), None | ||||
| cls = InlinedIndexObject | cls = InlinedIndexObject | ||||
| return cls(data, inline), (0, data) | return cls(data, inline), (0, data) | ||||
| def parse_index_cl_v2(data): | |||||
| return IndexChangelogV2(data), None | |||||
| class IndexObject2(IndexObject): | class IndexObject2(IndexObject): | ||||
| index_format = revlog_constants.INDEX_ENTRY_V2 | index_format = revlog_constants.INDEX_ENTRY_V2 | ||||
| def replace_sidedata_info( | def replace_sidedata_info( | ||||
| self, | self, | ||||
| rev, | rev, | ||||
| sidedata_offset, | sidedata_offset, | ||||
| sidedata_length, | sidedata_length, | ||||
| def pack_header(self, header): | def pack_header(self, header): | ||||
| """pack header information as binary""" | """pack header information as binary""" | ||||
| msg = 'version header should go in the docket, not the index: %d' | msg = 'version header should go in the docket, not the index: %d' | ||||
| msg %= header | msg %= header | ||||
| raise error.ProgrammingError(msg) | raise error.ProgrammingError(msg) | ||||
| class IndexChangelogV2(IndexObject2): | |||||
| index_format = revlog_constants.INDEX_ENTRY_CL_V2 | |||||
| def _unpack_entry(self, rev, data, r=True): | |||||
| items = self.index_format.unpack(data) | |||||
| entry = items[:3] + (rev, rev) + items[3:8] | |||||
| data_comp = items[8] & 3 | |||||
| sidedata_comp = (items[8] >> 2) & 3 | |||||
| return entry + (data_comp, sidedata_comp) | |||||
| def _pack_entry(self, rev, entry): | |||||
| assert entry[3] == rev, entry[3] | |||||
| assert entry[4] == rev, entry[4] | |||||
| data = entry[:3] + entry[5:10] | |||||
| data_comp = entry[10] & 3 | |||||
| sidedata_comp = (entry[11] & 3) << 2 | |||||
| data += (data_comp | sidedata_comp,) | |||||
| return self.index_format.pack(*data) | |||||
| def parse_index_devel_nodemap(data, inline): | def parse_index_devel_nodemap(data, inline): | ||||
| """like parse_index2, but alway return a PersistentNodeMapIndexObject""" | """like parse_index2, but alway return a PersistentNodeMapIndexObject""" | ||||
| return PersistentNodeMapIndexObject(data), None | return PersistentNodeMapIndexObject(data), None | ||||
| def parse_dirstate(dmap, copymap, st): | def parse_dirstate(dmap, copymap, st): | ||||
| parents = [st[:20], st[20:40]] | parents = [st[:20], st[20:40]] | ||||
| # dereference fields so they will be local in loop | # dereference fields so they will be local in loop | ||||
| def parse_index_v2(data, inline): | def parse_index_v2(data, inline): | ||||
| # call the C implementation to parse the index data | # call the C implementation to parse the index data | ||||
| index, cache = parsers.parse_index2(data, inline, revlogv2=True) | index, cache = parsers.parse_index2(data, inline, revlogv2=True) | ||||
| return index, cache | return index, cache | ||||
| def parse_index_cl_v2(data, inline): | |||||
| # call the C implementation to parse the index data | |||||
| assert not inline | |||||
| from .pure.parsers import parse_index_cl_v2 | |||||
| index, cache = parse_index_cl_v2(data) | |||||
| return index, cache | |||||
| if util.safehasattr(parsers, 'parse_index_devel_nodemap'): | if util.safehasattr(parsers, 'parse_index_devel_nodemap'): | ||||
| def parse_index_v1_nodemap(data, inline): | def parse_index_v1_nodemap(data, inline): | ||||
| index, cache = parsers.parse_index_devel_nodemap(data, inline) | index, cache = parsers.parse_index_devel_nodemap(data, inline) | ||||
| return index, cache | return index, cache | ||||
| else: | else: | ||||
| use_rust_index = self.opener.options.get(b'rust.index') | use_rust_index = self.opener.options.get(b'rust.index') | ||||
| self._parse_index = parse_index_v1 | self._parse_index = parse_index_v1 | ||||
| if self._format_version == REVLOGV0: | if self._format_version == REVLOGV0: | ||||
| self._parse_index = revlogv0.parse_index_v0 | self._parse_index = revlogv0.parse_index_v0 | ||||
| elif self._format_version == REVLOGV2: | elif self._format_version == REVLOGV2: | ||||
| self._parse_index = parse_index_v2 | self._parse_index = parse_index_v2 | ||||
| elif self._format_version == CHANGELOGV2: | elif self._format_version == CHANGELOGV2: | ||||
| self._parse_index = parse_index_v2 | self._parse_index = parse_index_cl_v2 | ||||
| elif devel_nodemap: | elif devel_nodemap: | ||||
| self._parse_index = parse_index_v1_nodemap | self._parse_index = parse_index_v1_nodemap | ||||
| elif use_rust_index: | elif use_rust_index: | ||||
| self._parse_index = parse_index_v1_mixed | self._parse_index = parse_index_v1_mixed | ||||
| try: | try: | ||||
| d = self._parse_index(index_data, self._inline) | d = self._parse_index(index_data, self._inline) | ||||
| index, _chunkcache = d | index, _chunkcache = d | ||||
| use_nodemap = ( | use_nodemap = ( | ||||
| # 32 bytes: nodeid | # 32 bytes: nodeid | ||||
| # 8 bytes: sidedata offset | # 8 bytes: sidedata offset | ||||
| # 4 bytes: sidedata compressed length | # 4 bytes: sidedata compressed length | ||||
| # 1 bytes: compression mode (2 lower bit are data_compression_mode) | # 1 bytes: compression mode (2 lower bit are data_compression_mode) | ||||
| # 19 bytes: Padding to align to 96 bytes (see RevlogV2Plan wiki page) | # 19 bytes: Padding to align to 96 bytes (see RevlogV2Plan wiki page) | ||||
| INDEX_ENTRY_V2 = struct.Struct(b">Qiiiiii20s12xQiB19x") | INDEX_ENTRY_V2 = struct.Struct(b">Qiiiiii20s12xQiB19x") | ||||
| assert INDEX_ENTRY_V2.size == 32 * 3, INDEX_ENTRY_V2.size | assert INDEX_ENTRY_V2.size == 32 * 3, INDEX_ENTRY_V2.size | ||||
| # 6 bytes: offset | |||||
| # 2 bytes: flags | |||||
| # 4 bytes: compressed length | |||||
| # 4 bytes: uncompressed length | |||||
| # 4 bytes: parent 1 rev | |||||
| # 4 bytes: parent 2 rev | |||||
| # 32 bytes: nodeid | |||||
| # 8 bytes: sidedata offset | |||||
| # 4 bytes: sidedata compressed length | |||||
| # 1 bytes: compression mode (2 lower bit are data_compression_mode) | |||||
| # 27 bytes: Padding to align to 96 bytes (see RevlogV2Plan wiki page) | |||||
| INDEX_ENTRY_CL_V2 = struct.Struct(b">Qiiii20s12xQiB27x") | |||||
| assert INDEX_ENTRY_CL_V2.size == 32 * 3, INDEX_ENTRY_V2.size | |||||
| # revlog index flags | # revlog index flags | ||||
| # For historical reasons, revlog's internal flags were exposed via the | # For historical reasons, revlog's internal flags were exposed via the | ||||
| # wire protocol and are even exposed in parts of the storage APIs. | # wire protocol and are even exposed in parts of the storage APIs. | ||||
| # revision has censor metadata, must be verified | # revision has censor metadata, must be verified | ||||
| REVIDX_ISCENSORED = repository.REVISION_FLAG_CENSORED | REVIDX_ISCENSORED = repository.REVISION_FLAG_CENSORED | ||||
| # revision hash does not match data (narrowhg) | # revision hash does not match data (narrowhg) | ||||