Mercurial > public > mercurial-scm > hg
annotate mercurial/utils/compression.py @ 42098:5753e5949b51
py3: add b'' prefixes to new doctests in match.py
# skip-blame as just b'' prefixes
Differential Revision: https://phab.mercurial-scm.org/D6221
author | Pulkit Goyal <pulkit@yandex-team.ru> |
---|---|
date | Wed, 10 Apr 2019 03:10:53 +0530 |
parents | bb271ec2fbfb |
children | 2372284d9457 |
rev | line source |
---|---|
42041
3e47d1ec9da5
util: extract compression code in `mercurial.utils.compression`
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
41834
diff
changeset
|
1 # compression.py - Mercurial utility functions for compression |
8226
8b2cd04a6e97
put license and copyright info into comment blocks
Martin Geisler <mg@lazybytes.net>
parents:
8225
diff
changeset
|
2 # |
8b2cd04a6e97
put license and copyright info into comment blocks
Martin Geisler <mg@lazybytes.net>
parents:
8225
diff
changeset
|
3 # This software may be used and distributed according to the terms of the |
10263 | 4 # GNU General Public License version 2 or any later version. |
1082 | 5 |
419
28511fc21073
[PATCH] file seperator handling for the other 'OS'
mpm@selenic.com
parents:
diff
changeset
|
6 |
34137
a8994d08e4a2
doctest: use print_function and convert bytes to unicode where needed
Yuya Nishihara <yuya@tcha.org>
parents:
34134
diff
changeset
|
7 from __future__ import absolute_import, print_function |
27358
ac839ee45b6a
util: use absolute_import
Gregory Szorc <gregory.szorc@gmail.com>
parents:
27357
diff
changeset
|
8 |
ac839ee45b6a
util: use absolute_import
Gregory Szorc <gregory.szorc@gmail.com>
parents:
27357
diff
changeset
|
9 import bz2 |
ac839ee45b6a
util: use absolute_import
Gregory Szorc <gregory.szorc@gmail.com>
parents:
27357
diff
changeset
|
10 import collections |
26266
1e042e31bd0c
changegroup: move all compressions utilities in util
Pierre-Yves David <pierre-yves.david@fb.com>
parents:
26201
diff
changeset
|
11 import zlib |
3769 | 12 |
42041
3e47d1ec9da5
util: extract compression code in `mercurial.utils.compression`
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
41834
diff
changeset
|
13 from .. import ( |
27358
ac839ee45b6a
util: use absolute_import
Gregory Szorc <gregory.szorc@gmail.com>
parents:
27357
diff
changeset
|
14 error, |
ac839ee45b6a
util: use absolute_import
Gregory Szorc <gregory.szorc@gmail.com>
parents:
27357
diff
changeset
|
15 i18n, |
28818
6041fb8f2da8
pycompat: add empty and queue to handle py3 divergence
timeless <timeless@mozdev.org>
parents:
28497
diff
changeset
|
16 pycompat, |
27358
ac839ee45b6a
util: use absolute_import
Gregory Szorc <gregory.szorc@gmail.com>
parents:
27357
diff
changeset
|
17 ) |
42041
3e47d1ec9da5
util: extract compression code in `mercurial.utils.compression`
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
41834
diff
changeset
|
18 from . import ( |
37083
f99d64e8a4e4
stringutil: move generic string helpers to new module
Yuya Nishihara <yuya@tcha.org>
parents:
37082
diff
changeset
|
19 stringutil, |
f99d64e8a4e4
stringutil: move generic string helpers to new module
Yuya Nishihara <yuya@tcha.org>
parents:
37082
diff
changeset
|
20 ) |
3769 | 21 |
42041
3e47d1ec9da5
util: extract compression code in `mercurial.utils.compression`
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
41834
diff
changeset
|
22 safehasattr = pycompat.safehasattr |
32201
4462a981e8df
base85: proxy through util module
Yuya Nishihara <yuya@tcha.org>
parents:
32154
diff
changeset
|
23 |
14926
4e7e63fc685a
util: eliminate wildcard imports
Adrian Buehlmann <adrian@cadifra.com>
parents:
14918
diff
changeset
|
24 |
27358
ac839ee45b6a
util: use absolute_import
Gregory Szorc <gregory.szorc@gmail.com>
parents:
27357
diff
changeset
|
25 _ = i18n._ |
14926
4e7e63fc685a
util: eliminate wildcard imports
Adrian Buehlmann <adrian@cadifra.com>
parents:
14918
diff
changeset
|
26 |
42041
3e47d1ec9da5
util: extract compression code in `mercurial.utils.compression`
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
41834
diff
changeset
|
27 # compression code |
36524
bfe38f787d5b
util: add a file object proxy that can notify observers
Gregory Szorc <gregory.szorc@gmail.com>
parents:
36432
diff
changeset
|
28 |
42041
3e47d1ec9da5
util: extract compression code in `mercurial.utils.compression`
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
41834
diff
changeset
|
29 SERVERROLE = 'server' |
3e47d1ec9da5
util: extract compression code in `mercurial.utils.compression`
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
41834
diff
changeset
|
30 CLIENTROLE = 'client' |
33793
bbbbd3c30bfc
util: add base class for transactional context managers
Martin von Zweigbergk <martinvonz@google.com>
parents:
33737
diff
changeset
|
31 |
42041
3e47d1ec9da5
util: extract compression code in `mercurial.utils.compression`
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
41834
diff
changeset
|
32 compewireprotosupport = collections.namedtuple(r'compenginewireprotosupport', |
3e47d1ec9da5
util: extract compression code in `mercurial.utils.compression`
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
41834
diff
changeset
|
33 (r'name', r'serverpriority', |
3e47d1ec9da5
util: extract compression code in `mercurial.utils.compression`
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
41834
diff
changeset
|
34 r'clientpriority')) |
9097
431462bd8478
fix memory usage of revlog caches by limiting cache size [issue1639]
Matt Mackall <mpm@selenic.com>
parents:
9089
diff
changeset
|
35 |
8207
dd8d5be57d65
util: take propertycache from context.py
Matt Mackall <mpm@selenic.com>
parents:
8181
diff
changeset
|
36 class propertycache(object): |
dd8d5be57d65
util: take propertycache from context.py
Matt Mackall <mpm@selenic.com>
parents:
8181
diff
changeset
|
37 def __init__(self, func): |
dd8d5be57d65
util: take propertycache from context.py
Matt Mackall <mpm@selenic.com>
parents:
8181
diff
changeset
|
38 self.func = func |
dd8d5be57d65
util: take propertycache from context.py
Matt Mackall <mpm@selenic.com>
parents:
8181
diff
changeset
|
39 self.name = func.__name__ |
dd8d5be57d65
util: take propertycache from context.py
Matt Mackall <mpm@selenic.com>
parents:
8181
diff
changeset
|
40 def __get__(self, obj, type=None): |
dd8d5be57d65
util: take propertycache from context.py
Matt Mackall <mpm@selenic.com>
parents:
8181
diff
changeset
|
41 result = self.func(obj) |
18013
98c867ac1330
clfilter: add a propertycache that must be unfiltered
Pierre-Yves David <pierre-yves.david@logilab.fr>
parents:
17962
diff
changeset
|
42 self.cachevalue(obj, result) |
8207
dd8d5be57d65
util: take propertycache from context.py
Matt Mackall <mpm@selenic.com>
parents:
8181
diff
changeset
|
43 return result |
dd8d5be57d65
util: take propertycache from context.py
Matt Mackall <mpm@selenic.com>
parents:
8181
diff
changeset
|
44 |
18013
98c867ac1330
clfilter: add a propertycache that must be unfiltered
Pierre-Yves David <pierre-yves.david@logilab.fr>
parents:
17962
diff
changeset
|
45 def cachevalue(self, obj, value): |
19951
d51c4d85ec23
spelling: random spell checker fixes
Mads Kiilerich <madski@unity3d.com>
parents:
19852
diff
changeset
|
46 # __dict__ assignment required to bypass __setattr__ (eg: repoview) |
19845
a1237a4b437d
repoview: make propertycache.setcache compatible with repoview
Pierre-Yves David <pierre-yves.david@ens-lyon.org>
parents:
19461
diff
changeset
|
47 obj.__dict__[self.name] = value |
18013
98c867ac1330
clfilter: add a propertycache that must be unfiltered
Pierre-Yves David <pierre-yves.david@logilab.fr>
parents:
17962
diff
changeset
|
48 |
30350
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
49 class compressormanager(object): |
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
50 """Holds registrations of various compression engines. |
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
51 |
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
52 This class essentially abstracts the differences between compression |
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
53 engines to allow new compression formats to be added easily, possibly from |
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
54 extensions. |
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
55 |
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
56 Compressors are registered against the global instance by calling its |
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
57 ``register()`` method. |
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
58 """ |
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
59 def __init__(self): |
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
60 self._engines = {} |
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
61 # Bundle spec human name to engine name. |
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
62 self._bundlenames = {} |
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
63 # Internal bundle identifier to engine name. |
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
64 self._bundletypes = {} |
30798
f50c0db50025
util: compression APIs to support revlog decompression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30794
diff
changeset
|
65 # Revlog header to engine name. |
f50c0db50025
util: compression APIs to support revlog decompression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30794
diff
changeset
|
66 self._revlogheaders = {} |
30761
7283719e2bfd
util: declare wire protocol support of compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30745
diff
changeset
|
67 # Wire proto identifier to engine name. |
7283719e2bfd
util: declare wire protocol support of compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30745
diff
changeset
|
68 self._wiretypes = {} |
30350
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
69 |
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
70 def __getitem__(self, key): |
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
71 return self._engines[key] |
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
72 |
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
73 def __contains__(self, key): |
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
74 return key in self._engines |
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
75 |
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
76 def __iter__(self): |
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
77 return iter(self._engines.keys()) |
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
78 |
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
79 def register(self, engine): |
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
80 """Register a compression engine with the manager. |
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
81 |
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
82 The argument must be a ``compressionengine`` instance. |
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
83 """ |
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
84 if not isinstance(engine, compressionengine): |
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
85 raise ValueError(_('argument must be a compressionengine')) |
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
86 |
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
87 name = engine.name() |
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
88 |
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
89 if name in self._engines: |
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
90 raise error.Abort(_('compression engine %s already registered') % |
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
91 name) |
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
92 |
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
93 bundleinfo = engine.bundletype() |
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
94 if bundleinfo: |
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
95 bundlename, bundletype = bundleinfo |
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
96 |
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
97 if bundlename in self._bundlenames: |
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
98 raise error.Abort(_('bundle name %s already registered') % |
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
99 bundlename) |
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
100 if bundletype in self._bundletypes: |
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
101 raise error.Abort(_('bundle type %s already registered by %s') % |
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
102 (bundletype, self._bundletypes[bundletype])) |
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
103 |
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
104 # No external facing name declared. |
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
105 if bundlename: |
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
106 self._bundlenames[bundlename] = name |
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
107 |
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
108 self._bundletypes[bundletype] = name |
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
109 |
30761
7283719e2bfd
util: declare wire protocol support of compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30745
diff
changeset
|
110 wiresupport = engine.wireprotosupport() |
7283719e2bfd
util: declare wire protocol support of compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30745
diff
changeset
|
111 if wiresupport: |
7283719e2bfd
util: declare wire protocol support of compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30745
diff
changeset
|
112 wiretype = wiresupport.name |
7283719e2bfd
util: declare wire protocol support of compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30745
diff
changeset
|
113 if wiretype in self._wiretypes: |
7283719e2bfd
util: declare wire protocol support of compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30745
diff
changeset
|
114 raise error.Abort(_('wire protocol compression %s already ' |
7283719e2bfd
util: declare wire protocol support of compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30745
diff
changeset
|
115 'registered by %s') % |
7283719e2bfd
util: declare wire protocol support of compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30745
diff
changeset
|
116 (wiretype, self._wiretypes[wiretype])) |
7283719e2bfd
util: declare wire protocol support of compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30745
diff
changeset
|
117 |
7283719e2bfd
util: declare wire protocol support of compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30745
diff
changeset
|
118 self._wiretypes[wiretype] = name |
7283719e2bfd
util: declare wire protocol support of compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30745
diff
changeset
|
119 |
30798
f50c0db50025
util: compression APIs to support revlog decompression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30794
diff
changeset
|
120 revlogheader = engine.revlogheader() |
f50c0db50025
util: compression APIs to support revlog decompression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30794
diff
changeset
|
121 if revlogheader and revlogheader in self._revlogheaders: |
f50c0db50025
util: compression APIs to support revlog decompression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30794
diff
changeset
|
122 raise error.Abort(_('revlog header %s already registered by %s') % |
f50c0db50025
util: compression APIs to support revlog decompression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30794
diff
changeset
|
123 (revlogheader, self._revlogheaders[revlogheader])) |
f50c0db50025
util: compression APIs to support revlog decompression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30794
diff
changeset
|
124 |
f50c0db50025
util: compression APIs to support revlog decompression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30794
diff
changeset
|
125 if revlogheader: |
f50c0db50025
util: compression APIs to support revlog decompression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30794
diff
changeset
|
126 self._revlogheaders[revlogheader] = name |
f50c0db50025
util: compression APIs to support revlog decompression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30794
diff
changeset
|
127 |
30350
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
128 self._engines[name] = engine |
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
129 |
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
130 @property |
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
131 def supportedbundlenames(self): |
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
132 return set(self._bundlenames.keys()) |
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
133 |
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
134 @property |
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
135 def supportedbundletypes(self): |
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
136 return set(self._bundletypes.keys()) |
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
137 |
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
138 def forbundlename(self, bundlename): |
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
139 """Obtain a compression engine registered to a bundle name. |
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
140 |
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
141 Will raise KeyError if the bundle type isn't registered. |
30438
90933e4e44fd
util: check for compression engine availability before returning
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30437
diff
changeset
|
142 |
90933e4e44fd
util: check for compression engine availability before returning
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30437
diff
changeset
|
143 Will abort if the engine is known but not available. |
30350
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
144 """ |
30438
90933e4e44fd
util: check for compression engine availability before returning
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30437
diff
changeset
|
145 engine = self._engines[self._bundlenames[bundlename]] |
90933e4e44fd
util: check for compression engine availability before returning
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30437
diff
changeset
|
146 if not engine.available(): |
90933e4e44fd
util: check for compression engine availability before returning
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30437
diff
changeset
|
147 raise error.Abort(_('compression engine %s could not be loaded') % |
90933e4e44fd
util: check for compression engine availability before returning
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30437
diff
changeset
|
148 engine.name()) |
90933e4e44fd
util: check for compression engine availability before returning
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30437
diff
changeset
|
149 return engine |
30350
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
150 |
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
151 def forbundletype(self, bundletype): |
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
152 """Obtain a compression engine registered to a bundle type. |
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
153 |
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
154 Will raise KeyError if the bundle type isn't registered. |
30438
90933e4e44fd
util: check for compression engine availability before returning
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30437
diff
changeset
|
155 |
90933e4e44fd
util: check for compression engine availability before returning
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30437
diff
changeset
|
156 Will abort if the engine is known but not available. |
30350
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
157 """ |
30438
90933e4e44fd
util: check for compression engine availability before returning
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30437
diff
changeset
|
158 engine = self._engines[self._bundletypes[bundletype]] |
90933e4e44fd
util: check for compression engine availability before returning
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30437
diff
changeset
|
159 if not engine.available(): |
90933e4e44fd
util: check for compression engine availability before returning
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30437
diff
changeset
|
160 raise error.Abort(_('compression engine %s could not be loaded') % |
90933e4e44fd
util: check for compression engine availability before returning
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30437
diff
changeset
|
161 engine.name()) |
90933e4e44fd
util: check for compression engine availability before returning
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30437
diff
changeset
|
162 return engine |
30350
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
163 |
30761
7283719e2bfd
util: declare wire protocol support of compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30745
diff
changeset
|
164 def supportedwireengines(self, role, onlyavailable=True): |
7283719e2bfd
util: declare wire protocol support of compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30745
diff
changeset
|
165 """Obtain compression engines that support the wire protocol. |
7283719e2bfd
util: declare wire protocol support of compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30745
diff
changeset
|
166 |
7283719e2bfd
util: declare wire protocol support of compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30745
diff
changeset
|
167 Returns a list of engines in prioritized order, most desired first. |
7283719e2bfd
util: declare wire protocol support of compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30745
diff
changeset
|
168 |
7283719e2bfd
util: declare wire protocol support of compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30745
diff
changeset
|
169 If ``onlyavailable`` is set, filter out engines that can't be |
7283719e2bfd
util: declare wire protocol support of compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30745
diff
changeset
|
170 loaded. |
7283719e2bfd
util: declare wire protocol support of compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30745
diff
changeset
|
171 """ |
7283719e2bfd
util: declare wire protocol support of compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30745
diff
changeset
|
172 assert role in (SERVERROLE, CLIENTROLE) |
7283719e2bfd
util: declare wire protocol support of compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30745
diff
changeset
|
173 |
7283719e2bfd
util: declare wire protocol support of compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30745
diff
changeset
|
174 attr = 'serverpriority' if role == SERVERROLE else 'clientpriority' |
7283719e2bfd
util: declare wire protocol support of compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30745
diff
changeset
|
175 |
7283719e2bfd
util: declare wire protocol support of compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30745
diff
changeset
|
176 engines = [self._engines[e] for e in self._wiretypes.values()] |
7283719e2bfd
util: declare wire protocol support of compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30745
diff
changeset
|
177 if onlyavailable: |
7283719e2bfd
util: declare wire protocol support of compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30745
diff
changeset
|
178 engines = [e for e in engines if e.available()] |
7283719e2bfd
util: declare wire protocol support of compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30745
diff
changeset
|
179 |
7283719e2bfd
util: declare wire protocol support of compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30745
diff
changeset
|
180 def getkey(e): |
7283719e2bfd
util: declare wire protocol support of compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30745
diff
changeset
|
181 # Sort first by priority, highest first. In case of tie, sort |
7283719e2bfd
util: declare wire protocol support of compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30745
diff
changeset
|
182 # alphabetically. This is arbitrary, but ensures output is |
7283719e2bfd
util: declare wire protocol support of compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30745
diff
changeset
|
183 # stable. |
7283719e2bfd
util: declare wire protocol support of compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30745
diff
changeset
|
184 w = e.wireprotosupport() |
7283719e2bfd
util: declare wire protocol support of compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30745
diff
changeset
|
185 return -1 * getattr(w, attr), w.name |
7283719e2bfd
util: declare wire protocol support of compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30745
diff
changeset
|
186 |
7283719e2bfd
util: declare wire protocol support of compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30745
diff
changeset
|
187 return list(sorted(engines, key=getkey)) |
7283719e2bfd
util: declare wire protocol support of compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30745
diff
changeset
|
188 |
7283719e2bfd
util: declare wire protocol support of compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30745
diff
changeset
|
189 def forwiretype(self, wiretype): |
7283719e2bfd
util: declare wire protocol support of compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30745
diff
changeset
|
190 engine = self._engines[self._wiretypes[wiretype]] |
7283719e2bfd
util: declare wire protocol support of compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30745
diff
changeset
|
191 if not engine.available(): |
7283719e2bfd
util: declare wire protocol support of compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30745
diff
changeset
|
192 raise error.Abort(_('compression engine %s could not be loaded') % |
7283719e2bfd
util: declare wire protocol support of compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30745
diff
changeset
|
193 engine.name()) |
7283719e2bfd
util: declare wire protocol support of compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30745
diff
changeset
|
194 return engine |
7283719e2bfd
util: declare wire protocol support of compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30745
diff
changeset
|
195 |
30798
f50c0db50025
util: compression APIs to support revlog decompression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30794
diff
changeset
|
196 def forrevlogheader(self, header): |
f50c0db50025
util: compression APIs to support revlog decompression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30794
diff
changeset
|
197 """Obtain a compression engine registered to a revlog header. |
f50c0db50025
util: compression APIs to support revlog decompression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30794
diff
changeset
|
198 |
f50c0db50025
util: compression APIs to support revlog decompression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30794
diff
changeset
|
199 Will raise KeyError if the revlog header value isn't registered. |
f50c0db50025
util: compression APIs to support revlog decompression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30794
diff
changeset
|
200 """ |
f50c0db50025
util: compression APIs to support revlog decompression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30794
diff
changeset
|
201 return self._engines[self._revlogheaders[header]] |
f50c0db50025
util: compression APIs to support revlog decompression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30794
diff
changeset
|
202 |
30350
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
203 compengines = compressormanager() |
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
204 |
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
205 class compressionengine(object): |
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
206 """Base class for compression engines. |
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
207 |
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
208 Compression engines must implement the interface defined by this class. |
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
209 """ |
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
210 def name(self): |
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
211 """Returns the name of the compression engine. |
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
212 |
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
213 This is the key the engine is registered under. |
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
214 |
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
215 This method must be implemented. |
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
216 """ |
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
217 raise NotImplementedError() |
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
218 |
30437
64d7275445d0
util: expose an "available" API on compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30418
diff
changeset
|
219 def available(self): |
64d7275445d0
util: expose an "available" API on compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30418
diff
changeset
|
220 """Whether the compression engine is available. |
64d7275445d0
util: expose an "available" API on compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30418
diff
changeset
|
221 |
64d7275445d0
util: expose an "available" API on compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30418
diff
changeset
|
222 The intent of this method is to allow optional compression engines |
64d7275445d0
util: expose an "available" API on compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30418
diff
changeset
|
223 that may not be available in all installations (such as engines relying |
64d7275445d0
util: expose an "available" API on compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30418
diff
changeset
|
224 on C extensions that may not be present). |
64d7275445d0
util: expose an "available" API on compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30418
diff
changeset
|
225 """ |
64d7275445d0
util: expose an "available" API on compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30418
diff
changeset
|
226 return True |
64d7275445d0
util: expose an "available" API on compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30418
diff
changeset
|
227 |
30350
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
228 def bundletype(self): |
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
229 """Describes bundle identifiers for this engine. |
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
230 |
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
231 If this compression engine isn't supported for bundles, returns None. |
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
232 |
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
233 If this engine can be used for bundles, returns a 2-tuple of strings of |
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
234 the user-facing "bundle spec" compression name and an internal |
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
235 identifier used to denote the compression format within bundles. To |
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
236 exclude the name from external usage, set the first element to ``None``. |
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
237 |
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
238 If bundle compression is supported, the class must also implement |
30359
673f0fdc1046
util: remove compressorobj API from compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30356
diff
changeset
|
239 ``compressstream`` and `decompressorreader``. |
31792
55c0c91f55e6
util: document bundle compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
31777
diff
changeset
|
240 |
55c0c91f55e6
util: document bundle compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
31777
diff
changeset
|
241 The docstring of this method is used in the help system to tell users |
55c0c91f55e6
util: document bundle compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
31777
diff
changeset
|
242 about this engine. |
30350
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
243 """ |
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
244 return None |
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
245 |
30761
7283719e2bfd
util: declare wire protocol support of compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30745
diff
changeset
|
246 def wireprotosupport(self): |
7283719e2bfd
util: declare wire protocol support of compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30745
diff
changeset
|
247 """Declare support for this compression format on the wire protocol. |
7283719e2bfd
util: declare wire protocol support of compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30745
diff
changeset
|
248 |
7283719e2bfd
util: declare wire protocol support of compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30745
diff
changeset
|
249 If this compression engine isn't supported for compressing wire |
7283719e2bfd
util: declare wire protocol support of compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30745
diff
changeset
|
250 protocol payloads, returns None. |
7283719e2bfd
util: declare wire protocol support of compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30745
diff
changeset
|
251 |
7283719e2bfd
util: declare wire protocol support of compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30745
diff
changeset
|
252 Otherwise, returns ``compenginewireprotosupport`` with the following |
7283719e2bfd
util: declare wire protocol support of compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30745
diff
changeset
|
253 fields: |
7283719e2bfd
util: declare wire protocol support of compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30745
diff
changeset
|
254 |
7283719e2bfd
util: declare wire protocol support of compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30745
diff
changeset
|
255 * String format identifier |
7283719e2bfd
util: declare wire protocol support of compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30745
diff
changeset
|
256 * Integer priority for the server |
7283719e2bfd
util: declare wire protocol support of compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30745
diff
changeset
|
257 * Integer priority for the client |
7283719e2bfd
util: declare wire protocol support of compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30745
diff
changeset
|
258 |
7283719e2bfd
util: declare wire protocol support of compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30745
diff
changeset
|
259 The integer priorities are used to order the advertisement of format |
7283719e2bfd
util: declare wire protocol support of compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30745
diff
changeset
|
260 support by server and client. The highest integer is advertised |
7283719e2bfd
util: declare wire protocol support of compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30745
diff
changeset
|
261 first. Integers with non-positive values aren't advertised. |
7283719e2bfd
util: declare wire protocol support of compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30745
diff
changeset
|
262 |
7283719e2bfd
util: declare wire protocol support of compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30745
diff
changeset
|
263 The priority values are somewhat arbitrary and only used for default |
7283719e2bfd
util: declare wire protocol support of compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30745
diff
changeset
|
264 ordering. The relative order can be changed via config options. |
7283719e2bfd
util: declare wire protocol support of compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30745
diff
changeset
|
265 |
7283719e2bfd
util: declare wire protocol support of compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30745
diff
changeset
|
266 If wire protocol compression is supported, the class must also implement |
7283719e2bfd
util: declare wire protocol support of compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30745
diff
changeset
|
267 ``compressstream`` and ``decompressorreader``. |
7283719e2bfd
util: declare wire protocol support of compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30745
diff
changeset
|
268 """ |
7283719e2bfd
util: declare wire protocol support of compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30745
diff
changeset
|
269 return None |
7283719e2bfd
util: declare wire protocol support of compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30745
diff
changeset
|
270 |
30798
f50c0db50025
util: compression APIs to support revlog decompression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30794
diff
changeset
|
271 def revlogheader(self): |
f50c0db50025
util: compression APIs to support revlog decompression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30794
diff
changeset
|
272 """Header added to revlog chunks that identifies this engine. |
f50c0db50025
util: compression APIs to support revlog decompression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30794
diff
changeset
|
273 |
f50c0db50025
util: compression APIs to support revlog decompression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30794
diff
changeset
|
274 If this engine can be used to compress revlogs, this method should |
f50c0db50025
util: compression APIs to support revlog decompression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30794
diff
changeset
|
275 return the bytes used to identify chunks compressed with this engine. |
f50c0db50025
util: compression APIs to support revlog decompression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30794
diff
changeset
|
276 Else, the method should return ``None`` to indicate it does not |
f50c0db50025
util: compression APIs to support revlog decompression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30794
diff
changeset
|
277 participate in revlog compression. |
f50c0db50025
util: compression APIs to support revlog decompression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30794
diff
changeset
|
278 """ |
f50c0db50025
util: compression APIs to support revlog decompression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30794
diff
changeset
|
279 return None |
f50c0db50025
util: compression APIs to support revlog decompression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30794
diff
changeset
|
280 |
30356
c86109eface7
util: add a stream compression API to compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30355
diff
changeset
|
281 def compressstream(self, it, opts=None): |
c86109eface7
util: add a stream compression API to compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30355
diff
changeset
|
282 """Compress an iterator of chunks. |
c86109eface7
util: add a stream compression API to compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30355
diff
changeset
|
283 |
c86109eface7
util: add a stream compression API to compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30355
diff
changeset
|
284 The method receives an iterator (ideally a generator) of chunks of |
c86109eface7
util: add a stream compression API to compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30355
diff
changeset
|
285 bytes to be compressed. It returns an iterator (ideally a generator) |
c86109eface7
util: add a stream compression API to compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30355
diff
changeset
|
286 of bytes of chunks representing the compressed output. |
c86109eface7
util: add a stream compression API to compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30355
diff
changeset
|
287 |
c86109eface7
util: add a stream compression API to compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30355
diff
changeset
|
288 Optionally accepts an argument defining how to perform compression. |
c86109eface7
util: add a stream compression API to compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30355
diff
changeset
|
289 Each engine treats this argument differently. |
c86109eface7
util: add a stream compression API to compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30355
diff
changeset
|
290 """ |
c86109eface7
util: add a stream compression API to compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30355
diff
changeset
|
291 raise NotImplementedError() |
c86109eface7
util: add a stream compression API to compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30355
diff
changeset
|
292 |
30350
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
293 def decompressorreader(self, fh): |
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
294 """Perform decompression on a file object. |
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
295 |
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
296 Argument is an object with a ``read(size)`` method that returns |
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
297 compressed data. Return value is an object with a ``read(size)`` that |
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
298 returns uncompressed data. |
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
299 """ |
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
300 raise NotImplementedError() |
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
301 |
30794
31e1f0d4ab44
util: compression APIs to support revlog compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30773
diff
changeset
|
302 def revlogcompressor(self, opts=None): |
31e1f0d4ab44
util: compression APIs to support revlog compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30773
diff
changeset
|
303 """Obtain an object that can be used to compress revlog entries. |
31e1f0d4ab44
util: compression APIs to support revlog compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30773
diff
changeset
|
304 |
31e1f0d4ab44
util: compression APIs to support revlog compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30773
diff
changeset
|
305 The object has a ``compress(data)`` method that compresses binary |
31e1f0d4ab44
util: compression APIs to support revlog compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30773
diff
changeset
|
306 data. This method returns compressed binary data or ``None`` if |
31e1f0d4ab44
util: compression APIs to support revlog compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30773
diff
changeset
|
307 the data could not be compressed (too small, not compressible, etc). |
31e1f0d4ab44
util: compression APIs to support revlog compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30773
diff
changeset
|
308 The returned data should have a header uniquely identifying this |
31e1f0d4ab44
util: compression APIs to support revlog compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30773
diff
changeset
|
309 compression format so decompression can be routed to this engine. |
30798
f50c0db50025
util: compression APIs to support revlog decompression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30794
diff
changeset
|
310 This header should be identified by the ``revlogheader()`` return |
f50c0db50025
util: compression APIs to support revlog decompression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30794
diff
changeset
|
311 value. |
f50c0db50025
util: compression APIs to support revlog decompression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30794
diff
changeset
|
312 |
f50c0db50025
util: compression APIs to support revlog decompression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30794
diff
changeset
|
313 The object has a ``decompress(data)`` method that decompresses |
f50c0db50025
util: compression APIs to support revlog decompression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30794
diff
changeset
|
314 data. The method will only be called if ``data`` begins with |
f50c0db50025
util: compression APIs to support revlog decompression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30794
diff
changeset
|
315 ``revlogheader()``. The method should return the raw, uncompressed |
39777
b63dee7bd0d9
global: replace most uses of RevlogError with StorageError (API)
Gregory Szorc <gregory.szorc@gmail.com>
parents:
39571
diff
changeset
|
316 data or raise a ``StorageError``. |
30794
31e1f0d4ab44
util: compression APIs to support revlog compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30773
diff
changeset
|
317 |
31e1f0d4ab44
util: compression APIs to support revlog compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30773
diff
changeset
|
318 The object is reusable but is not thread safe. |
31e1f0d4ab44
util: compression APIs to support revlog compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30773
diff
changeset
|
319 """ |
31e1f0d4ab44
util: compression APIs to support revlog compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30773
diff
changeset
|
320 raise NotImplementedError() |
31e1f0d4ab44
util: compression APIs to support revlog compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30773
diff
changeset
|
321 |
38713
27391d74aaa2
ssh: avoid reading beyond the end of stream when using compression
Joerg Sonnenberger <joerg@bec.de>
parents:
38575
diff
changeset
|
322 class _CompressedStreamReader(object): |
27391d74aaa2
ssh: avoid reading beyond the end of stream when using compression
Joerg Sonnenberger <joerg@bec.de>
parents:
38575
diff
changeset
|
323 def __init__(self, fh): |
27391d74aaa2
ssh: avoid reading beyond the end of stream when using compression
Joerg Sonnenberger <joerg@bec.de>
parents:
38575
diff
changeset
|
324 if safehasattr(fh, 'unbufferedread'): |
27391d74aaa2
ssh: avoid reading beyond the end of stream when using compression
Joerg Sonnenberger <joerg@bec.de>
parents:
38575
diff
changeset
|
325 self._reader = fh.unbufferedread |
27391d74aaa2
ssh: avoid reading beyond the end of stream when using compression
Joerg Sonnenberger <joerg@bec.de>
parents:
38575
diff
changeset
|
326 else: |
27391d74aaa2
ssh: avoid reading beyond the end of stream when using compression
Joerg Sonnenberger <joerg@bec.de>
parents:
38575
diff
changeset
|
327 self._reader = fh.read |
27391d74aaa2
ssh: avoid reading beyond the end of stream when using compression
Joerg Sonnenberger <joerg@bec.de>
parents:
38575
diff
changeset
|
328 self._pending = [] |
27391d74aaa2
ssh: avoid reading beyond the end of stream when using compression
Joerg Sonnenberger <joerg@bec.de>
parents:
38575
diff
changeset
|
329 self._pos = 0 |
27391d74aaa2
ssh: avoid reading beyond the end of stream when using compression
Joerg Sonnenberger <joerg@bec.de>
parents:
38575
diff
changeset
|
330 self._eof = False |
27391d74aaa2
ssh: avoid reading beyond the end of stream when using compression
Joerg Sonnenberger <joerg@bec.de>
parents:
38575
diff
changeset
|
331 |
27391d74aaa2
ssh: avoid reading beyond the end of stream when using compression
Joerg Sonnenberger <joerg@bec.de>
parents:
38575
diff
changeset
|
332 def _decompress(self, chunk): |
27391d74aaa2
ssh: avoid reading beyond the end of stream when using compression
Joerg Sonnenberger <joerg@bec.de>
parents:
38575
diff
changeset
|
333 raise NotImplementedError() |
27391d74aaa2
ssh: avoid reading beyond the end of stream when using compression
Joerg Sonnenberger <joerg@bec.de>
parents:
38575
diff
changeset
|
334 |
27391d74aaa2
ssh: avoid reading beyond the end of stream when using compression
Joerg Sonnenberger <joerg@bec.de>
parents:
38575
diff
changeset
|
335 def read(self, l): |
27391d74aaa2
ssh: avoid reading beyond the end of stream when using compression
Joerg Sonnenberger <joerg@bec.de>
parents:
38575
diff
changeset
|
336 buf = [] |
27391d74aaa2
ssh: avoid reading beyond the end of stream when using compression
Joerg Sonnenberger <joerg@bec.de>
parents:
38575
diff
changeset
|
337 while True: |
27391d74aaa2
ssh: avoid reading beyond the end of stream when using compression
Joerg Sonnenberger <joerg@bec.de>
parents:
38575
diff
changeset
|
338 while self._pending: |
27391d74aaa2
ssh: avoid reading beyond the end of stream when using compression
Joerg Sonnenberger <joerg@bec.de>
parents:
38575
diff
changeset
|
339 if len(self._pending[0]) > l + self._pos: |
27391d74aaa2
ssh: avoid reading beyond the end of stream when using compression
Joerg Sonnenberger <joerg@bec.de>
parents:
38575
diff
changeset
|
340 newbuf = self._pending[0] |
27391d74aaa2
ssh: avoid reading beyond the end of stream when using compression
Joerg Sonnenberger <joerg@bec.de>
parents:
38575
diff
changeset
|
341 buf.append(newbuf[self._pos:self._pos + l]) |
27391d74aaa2
ssh: avoid reading beyond the end of stream when using compression
Joerg Sonnenberger <joerg@bec.de>
parents:
38575
diff
changeset
|
342 self._pos += l |
27391d74aaa2
ssh: avoid reading beyond the end of stream when using compression
Joerg Sonnenberger <joerg@bec.de>
parents:
38575
diff
changeset
|
343 return ''.join(buf) |
27391d74aaa2
ssh: avoid reading beyond the end of stream when using compression
Joerg Sonnenberger <joerg@bec.de>
parents:
38575
diff
changeset
|
344 |
27391d74aaa2
ssh: avoid reading beyond the end of stream when using compression
Joerg Sonnenberger <joerg@bec.de>
parents:
38575
diff
changeset
|
345 newbuf = self._pending.pop(0) |
27391d74aaa2
ssh: avoid reading beyond the end of stream when using compression
Joerg Sonnenberger <joerg@bec.de>
parents:
38575
diff
changeset
|
346 if self._pos: |
27391d74aaa2
ssh: avoid reading beyond the end of stream when using compression
Joerg Sonnenberger <joerg@bec.de>
parents:
38575
diff
changeset
|
347 buf.append(newbuf[self._pos:]) |
27391d74aaa2
ssh: avoid reading beyond the end of stream when using compression
Joerg Sonnenberger <joerg@bec.de>
parents:
38575
diff
changeset
|
348 l -= len(newbuf) - self._pos |
27391d74aaa2
ssh: avoid reading beyond the end of stream when using compression
Joerg Sonnenberger <joerg@bec.de>
parents:
38575
diff
changeset
|
349 else: |
27391d74aaa2
ssh: avoid reading beyond the end of stream when using compression
Joerg Sonnenberger <joerg@bec.de>
parents:
38575
diff
changeset
|
350 buf.append(newbuf) |
27391d74aaa2
ssh: avoid reading beyond the end of stream when using compression
Joerg Sonnenberger <joerg@bec.de>
parents:
38575
diff
changeset
|
351 l -= len(newbuf) |
27391d74aaa2
ssh: avoid reading beyond the end of stream when using compression
Joerg Sonnenberger <joerg@bec.de>
parents:
38575
diff
changeset
|
352 self._pos = 0 |
27391d74aaa2
ssh: avoid reading beyond the end of stream when using compression
Joerg Sonnenberger <joerg@bec.de>
parents:
38575
diff
changeset
|
353 |
27391d74aaa2
ssh: avoid reading beyond the end of stream when using compression
Joerg Sonnenberger <joerg@bec.de>
parents:
38575
diff
changeset
|
354 if self._eof: |
27391d74aaa2
ssh: avoid reading beyond the end of stream when using compression
Joerg Sonnenberger <joerg@bec.de>
parents:
38575
diff
changeset
|
355 return ''.join(buf) |
27391d74aaa2
ssh: avoid reading beyond the end of stream when using compression
Joerg Sonnenberger <joerg@bec.de>
parents:
38575
diff
changeset
|
356 chunk = self._reader(65536) |
27391d74aaa2
ssh: avoid reading beyond the end of stream when using compression
Joerg Sonnenberger <joerg@bec.de>
parents:
38575
diff
changeset
|
357 self._decompress(chunk) |
39209
1af95139e5ec
util: improve handling of truncated compressed streams
Joerg Sonnenberger <joerg@bec.de>
parents:
39060
diff
changeset
|
358 if not chunk and not self._pending and not self._eof: |
1af95139e5ec
util: improve handling of truncated compressed streams
Joerg Sonnenberger <joerg@bec.de>
parents:
39060
diff
changeset
|
359 # No progress and no new data, bail out |
1af95139e5ec
util: improve handling of truncated compressed streams
Joerg Sonnenberger <joerg@bec.de>
parents:
39060
diff
changeset
|
360 return ''.join(buf) |
38713
27391d74aaa2
ssh: avoid reading beyond the end of stream when using compression
Joerg Sonnenberger <joerg@bec.de>
parents:
38575
diff
changeset
|
361 |
27391d74aaa2
ssh: avoid reading beyond the end of stream when using compression
Joerg Sonnenberger <joerg@bec.de>
parents:
38575
diff
changeset
|
362 class _GzipCompressedStreamReader(_CompressedStreamReader): |
27391d74aaa2
ssh: avoid reading beyond the end of stream when using compression
Joerg Sonnenberger <joerg@bec.de>
parents:
38575
diff
changeset
|
363 def __init__(self, fh): |
27391d74aaa2
ssh: avoid reading beyond the end of stream when using compression
Joerg Sonnenberger <joerg@bec.de>
parents:
38575
diff
changeset
|
364 super(_GzipCompressedStreamReader, self).__init__(fh) |
27391d74aaa2
ssh: avoid reading beyond the end of stream when using compression
Joerg Sonnenberger <joerg@bec.de>
parents:
38575
diff
changeset
|
365 self._decompobj = zlib.decompressobj() |
27391d74aaa2
ssh: avoid reading beyond the end of stream when using compression
Joerg Sonnenberger <joerg@bec.de>
parents:
38575
diff
changeset
|
366 def _decompress(self, chunk): |
27391d74aaa2
ssh: avoid reading beyond the end of stream when using compression
Joerg Sonnenberger <joerg@bec.de>
parents:
38575
diff
changeset
|
367 newbuf = self._decompobj.decompress(chunk) |
27391d74aaa2
ssh: avoid reading beyond the end of stream when using compression
Joerg Sonnenberger <joerg@bec.de>
parents:
38575
diff
changeset
|
368 if newbuf: |
27391d74aaa2
ssh: avoid reading beyond the end of stream when using compression
Joerg Sonnenberger <joerg@bec.de>
parents:
38575
diff
changeset
|
369 self._pending.append(newbuf) |
27391d74aaa2
ssh: avoid reading beyond the end of stream when using compression
Joerg Sonnenberger <joerg@bec.de>
parents:
38575
diff
changeset
|
370 d = self._decompobj.copy() |
27391d74aaa2
ssh: avoid reading beyond the end of stream when using compression
Joerg Sonnenberger <joerg@bec.de>
parents:
38575
diff
changeset
|
371 try: |
27391d74aaa2
ssh: avoid reading beyond the end of stream when using compression
Joerg Sonnenberger <joerg@bec.de>
parents:
38575
diff
changeset
|
372 d.decompress('x') |
27391d74aaa2
ssh: avoid reading beyond the end of stream when using compression
Joerg Sonnenberger <joerg@bec.de>
parents:
38575
diff
changeset
|
373 d.flush() |
27391d74aaa2
ssh: avoid reading beyond the end of stream when using compression
Joerg Sonnenberger <joerg@bec.de>
parents:
38575
diff
changeset
|
374 if d.unused_data == 'x': |
27391d74aaa2
ssh: avoid reading beyond the end of stream when using compression
Joerg Sonnenberger <joerg@bec.de>
parents:
38575
diff
changeset
|
375 self._eof = True |
27391d74aaa2
ssh: avoid reading beyond the end of stream when using compression
Joerg Sonnenberger <joerg@bec.de>
parents:
38575
diff
changeset
|
376 except zlib.error: |
27391d74aaa2
ssh: avoid reading beyond the end of stream when using compression
Joerg Sonnenberger <joerg@bec.de>
parents:
38575
diff
changeset
|
377 pass |
27391d74aaa2
ssh: avoid reading beyond the end of stream when using compression
Joerg Sonnenberger <joerg@bec.de>
parents:
38575
diff
changeset
|
378 |
27391d74aaa2
ssh: avoid reading beyond the end of stream when using compression
Joerg Sonnenberger <joerg@bec.de>
parents:
38575
diff
changeset
|
379 class _BZ2CompressedStreamReader(_CompressedStreamReader): |
27391d74aaa2
ssh: avoid reading beyond the end of stream when using compression
Joerg Sonnenberger <joerg@bec.de>
parents:
38575
diff
changeset
|
380 def __init__(self, fh): |
27391d74aaa2
ssh: avoid reading beyond the end of stream when using compression
Joerg Sonnenberger <joerg@bec.de>
parents:
38575
diff
changeset
|
381 super(_BZ2CompressedStreamReader, self).__init__(fh) |
27391d74aaa2
ssh: avoid reading beyond the end of stream when using compression
Joerg Sonnenberger <joerg@bec.de>
parents:
38575
diff
changeset
|
382 self._decompobj = bz2.BZ2Decompressor() |
27391d74aaa2
ssh: avoid reading beyond the end of stream when using compression
Joerg Sonnenberger <joerg@bec.de>
parents:
38575
diff
changeset
|
383 def _decompress(self, chunk): |
27391d74aaa2
ssh: avoid reading beyond the end of stream when using compression
Joerg Sonnenberger <joerg@bec.de>
parents:
38575
diff
changeset
|
384 newbuf = self._decompobj.decompress(chunk) |
27391d74aaa2
ssh: avoid reading beyond the end of stream when using compression
Joerg Sonnenberger <joerg@bec.de>
parents:
38575
diff
changeset
|
385 if newbuf: |
27391d74aaa2
ssh: avoid reading beyond the end of stream when using compression
Joerg Sonnenberger <joerg@bec.de>
parents:
38575
diff
changeset
|
386 self._pending.append(newbuf) |
27391d74aaa2
ssh: avoid reading beyond the end of stream when using compression
Joerg Sonnenberger <joerg@bec.de>
parents:
38575
diff
changeset
|
387 try: |
27391d74aaa2
ssh: avoid reading beyond the end of stream when using compression
Joerg Sonnenberger <joerg@bec.de>
parents:
38575
diff
changeset
|
388 while True: |
27391d74aaa2
ssh: avoid reading beyond the end of stream when using compression
Joerg Sonnenberger <joerg@bec.de>
parents:
38575
diff
changeset
|
389 newbuf = self._decompobj.decompress('') |
27391d74aaa2
ssh: avoid reading beyond the end of stream when using compression
Joerg Sonnenberger <joerg@bec.de>
parents:
38575
diff
changeset
|
390 if newbuf: |
27391d74aaa2
ssh: avoid reading beyond the end of stream when using compression
Joerg Sonnenberger <joerg@bec.de>
parents:
38575
diff
changeset
|
391 self._pending.append(newbuf) |
27391d74aaa2
ssh: avoid reading beyond the end of stream when using compression
Joerg Sonnenberger <joerg@bec.de>
parents:
38575
diff
changeset
|
392 else: |
27391d74aaa2
ssh: avoid reading beyond the end of stream when using compression
Joerg Sonnenberger <joerg@bec.de>
parents:
38575
diff
changeset
|
393 break |
27391d74aaa2
ssh: avoid reading beyond the end of stream when using compression
Joerg Sonnenberger <joerg@bec.de>
parents:
38575
diff
changeset
|
394 except EOFError: |
27391d74aaa2
ssh: avoid reading beyond the end of stream when using compression
Joerg Sonnenberger <joerg@bec.de>
parents:
38575
diff
changeset
|
395 self._eof = True |
27391d74aaa2
ssh: avoid reading beyond the end of stream when using compression
Joerg Sonnenberger <joerg@bec.de>
parents:
38575
diff
changeset
|
396 |
27391d74aaa2
ssh: avoid reading beyond the end of stream when using compression
Joerg Sonnenberger <joerg@bec.de>
parents:
38575
diff
changeset
|
397 class _TruncatedBZ2CompressedStreamReader(_BZ2CompressedStreamReader): |
27391d74aaa2
ssh: avoid reading beyond the end of stream when using compression
Joerg Sonnenberger <joerg@bec.de>
parents:
38575
diff
changeset
|
398 def __init__(self, fh): |
27391d74aaa2
ssh: avoid reading beyond the end of stream when using compression
Joerg Sonnenberger <joerg@bec.de>
parents:
38575
diff
changeset
|
399 super(_TruncatedBZ2CompressedStreamReader, self).__init__(fh) |
27391d74aaa2
ssh: avoid reading beyond the end of stream when using compression
Joerg Sonnenberger <joerg@bec.de>
parents:
38575
diff
changeset
|
400 newbuf = self._decompobj.decompress('BZ') |
27391d74aaa2
ssh: avoid reading beyond the end of stream when using compression
Joerg Sonnenberger <joerg@bec.de>
parents:
38575
diff
changeset
|
401 if newbuf: |
27391d74aaa2
ssh: avoid reading beyond the end of stream when using compression
Joerg Sonnenberger <joerg@bec.de>
parents:
38575
diff
changeset
|
402 self._pending.append(newbuf) |
27391d74aaa2
ssh: avoid reading beyond the end of stream when using compression
Joerg Sonnenberger <joerg@bec.de>
parents:
38575
diff
changeset
|
403 |
27391d74aaa2
ssh: avoid reading beyond the end of stream when using compression
Joerg Sonnenberger <joerg@bec.de>
parents:
38575
diff
changeset
|
404 class _ZstdCompressedStreamReader(_CompressedStreamReader): |
27391d74aaa2
ssh: avoid reading beyond the end of stream when using compression
Joerg Sonnenberger <joerg@bec.de>
parents:
38575
diff
changeset
|
405 def __init__(self, fh, zstd): |
27391d74aaa2
ssh: avoid reading beyond the end of stream when using compression
Joerg Sonnenberger <joerg@bec.de>
parents:
38575
diff
changeset
|
406 super(_ZstdCompressedStreamReader, self).__init__(fh) |
27391d74aaa2
ssh: avoid reading beyond the end of stream when using compression
Joerg Sonnenberger <joerg@bec.de>
parents:
38575
diff
changeset
|
407 self._zstd = zstd |
27391d74aaa2
ssh: avoid reading beyond the end of stream when using compression
Joerg Sonnenberger <joerg@bec.de>
parents:
38575
diff
changeset
|
408 self._decompobj = zstd.ZstdDecompressor().decompressobj() |
27391d74aaa2
ssh: avoid reading beyond the end of stream when using compression
Joerg Sonnenberger <joerg@bec.de>
parents:
38575
diff
changeset
|
409 def _decompress(self, chunk): |
27391d74aaa2
ssh: avoid reading beyond the end of stream when using compression
Joerg Sonnenberger <joerg@bec.de>
parents:
38575
diff
changeset
|
410 newbuf = self._decompobj.decompress(chunk) |
27391d74aaa2
ssh: avoid reading beyond the end of stream when using compression
Joerg Sonnenberger <joerg@bec.de>
parents:
38575
diff
changeset
|
411 if newbuf: |
27391d74aaa2
ssh: avoid reading beyond the end of stream when using compression
Joerg Sonnenberger <joerg@bec.de>
parents:
38575
diff
changeset
|
412 self._pending.append(newbuf) |
27391d74aaa2
ssh: avoid reading beyond the end of stream when using compression
Joerg Sonnenberger <joerg@bec.de>
parents:
38575
diff
changeset
|
413 try: |
27391d74aaa2
ssh: avoid reading beyond the end of stream when using compression
Joerg Sonnenberger <joerg@bec.de>
parents:
38575
diff
changeset
|
414 while True: |
27391d74aaa2
ssh: avoid reading beyond the end of stream when using compression
Joerg Sonnenberger <joerg@bec.de>
parents:
38575
diff
changeset
|
415 newbuf = self._decompobj.decompress('') |
27391d74aaa2
ssh: avoid reading beyond the end of stream when using compression
Joerg Sonnenberger <joerg@bec.de>
parents:
38575
diff
changeset
|
416 if newbuf: |
27391d74aaa2
ssh: avoid reading beyond the end of stream when using compression
Joerg Sonnenberger <joerg@bec.de>
parents:
38575
diff
changeset
|
417 self._pending.append(newbuf) |
27391d74aaa2
ssh: avoid reading beyond the end of stream when using compression
Joerg Sonnenberger <joerg@bec.de>
parents:
38575
diff
changeset
|
418 else: |
27391d74aaa2
ssh: avoid reading beyond the end of stream when using compression
Joerg Sonnenberger <joerg@bec.de>
parents:
38575
diff
changeset
|
419 break |
27391d74aaa2
ssh: avoid reading beyond the end of stream when using compression
Joerg Sonnenberger <joerg@bec.de>
parents:
38575
diff
changeset
|
420 except self._zstd.ZstdError: |
27391d74aaa2
ssh: avoid reading beyond the end of stream when using compression
Joerg Sonnenberger <joerg@bec.de>
parents:
38575
diff
changeset
|
421 self._eof = True |
27391d74aaa2
ssh: avoid reading beyond the end of stream when using compression
Joerg Sonnenberger <joerg@bec.de>
parents:
38575
diff
changeset
|
422 |
30350
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
423 class _zlibengine(compressionengine): |
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
424 def name(self): |
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
425 return 'zlib' |
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
426 |
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
427 def bundletype(self): |
31792
55c0c91f55e6
util: document bundle compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
31777
diff
changeset
|
428 """zlib compression using the DEFLATE algorithm. |
55c0c91f55e6
util: document bundle compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
31777
diff
changeset
|
429 |
55c0c91f55e6
util: document bundle compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
31777
diff
changeset
|
430 All Mercurial clients should support this format. The compression |
55c0c91f55e6
util: document bundle compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
31777
diff
changeset
|
431 algorithm strikes a reasonable balance between compression ratio |
55c0c91f55e6
util: document bundle compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
31777
diff
changeset
|
432 and size. |
55c0c91f55e6
util: document bundle compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
31777
diff
changeset
|
433 """ |
30350
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
434 return 'gzip', 'GZ' |
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
435 |
30761
7283719e2bfd
util: declare wire protocol support of compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30745
diff
changeset
|
436 def wireprotosupport(self): |
7283719e2bfd
util: declare wire protocol support of compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30745
diff
changeset
|
437 return compewireprotosupport('zlib', 20, 20) |
7283719e2bfd
util: declare wire protocol support of compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30745
diff
changeset
|
438 |
30798
f50c0db50025
util: compression APIs to support revlog decompression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30794
diff
changeset
|
439 def revlogheader(self): |
f50c0db50025
util: compression APIs to support revlog decompression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30794
diff
changeset
|
440 return 'x' |
f50c0db50025
util: compression APIs to support revlog decompression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30794
diff
changeset
|
441 |
30356
c86109eface7
util: add a stream compression API to compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30355
diff
changeset
|
442 def compressstream(self, it, opts=None): |
c86109eface7
util: add a stream compression API to compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30355
diff
changeset
|
443 opts = opts or {} |
c86109eface7
util: add a stream compression API to compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30355
diff
changeset
|
444 |
c86109eface7
util: add a stream compression API to compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30355
diff
changeset
|
445 z = zlib.compressobj(opts.get('level', -1)) |
c86109eface7
util: add a stream compression API to compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30355
diff
changeset
|
446 for chunk in it: |
c86109eface7
util: add a stream compression API to compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30355
diff
changeset
|
447 data = z.compress(chunk) |
c86109eface7
util: add a stream compression API to compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30355
diff
changeset
|
448 # Not all calls to compress emit data. It is cheaper to inspect |
c86109eface7
util: add a stream compression API to compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30355
diff
changeset
|
449 # here than to feed empty chunks through generator. |
c86109eface7
util: add a stream compression API to compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30355
diff
changeset
|
450 if data: |
c86109eface7
util: add a stream compression API to compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30355
diff
changeset
|
451 yield data |
c86109eface7
util: add a stream compression API to compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30355
diff
changeset
|
452 |
c86109eface7
util: add a stream compression API to compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30355
diff
changeset
|
453 yield z.flush() |
c86109eface7
util: add a stream compression API to compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30355
diff
changeset
|
454 |
30350
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
455 def decompressorreader(self, fh): |
38713
27391d74aaa2
ssh: avoid reading beyond the end of stream when using compression
Joerg Sonnenberger <joerg@bec.de>
parents:
38575
diff
changeset
|
456 return _GzipCompressedStreamReader(fh) |
30350
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
457 |
30794
31e1f0d4ab44
util: compression APIs to support revlog compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30773
diff
changeset
|
458 class zlibrevlogcompressor(object): |
42042
aaececb4b066
compression: accept level management for zlib compression
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
42041
diff
changeset
|
459 |
aaececb4b066
compression: accept level management for zlib compression
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
42041
diff
changeset
|
460 def __init__(self, level=None): |
aaececb4b066
compression: accept level management for zlib compression
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
42041
diff
changeset
|
461 self._level = level |
aaececb4b066
compression: accept level management for zlib compression
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
42041
diff
changeset
|
462 |
30794
31e1f0d4ab44
util: compression APIs to support revlog compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30773
diff
changeset
|
463 def compress(self, data): |
31e1f0d4ab44
util: compression APIs to support revlog compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30773
diff
changeset
|
464 insize = len(data) |
31e1f0d4ab44
util: compression APIs to support revlog compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30773
diff
changeset
|
465 # Caller handles empty input case. |
31e1f0d4ab44
util: compression APIs to support revlog compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30773
diff
changeset
|
466 assert insize > 0 |
31e1f0d4ab44
util: compression APIs to support revlog compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30773
diff
changeset
|
467 |
31e1f0d4ab44
util: compression APIs to support revlog compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30773
diff
changeset
|
468 if insize < 44: |
31e1f0d4ab44
util: compression APIs to support revlog compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30773
diff
changeset
|
469 return None |
31e1f0d4ab44
util: compression APIs to support revlog compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30773
diff
changeset
|
470 |
31e1f0d4ab44
util: compression APIs to support revlog compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30773
diff
changeset
|
471 elif insize <= 1000000: |
42042
aaececb4b066
compression: accept level management for zlib compression
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
42041
diff
changeset
|
472 if self._level is None: |
aaececb4b066
compression: accept level management for zlib compression
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
42041
diff
changeset
|
473 compressed = zlib.compress(data) |
aaececb4b066
compression: accept level management for zlib compression
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
42041
diff
changeset
|
474 else: |
aaececb4b066
compression: accept level management for zlib compression
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
42041
diff
changeset
|
475 compressed = zlib.compress(data, self._level) |
30794
31e1f0d4ab44
util: compression APIs to support revlog compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30773
diff
changeset
|
476 if len(compressed) < insize: |
31e1f0d4ab44
util: compression APIs to support revlog compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30773
diff
changeset
|
477 return compressed |
31e1f0d4ab44
util: compression APIs to support revlog compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30773
diff
changeset
|
478 return None |
31e1f0d4ab44
util: compression APIs to support revlog compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30773
diff
changeset
|
479 |
31e1f0d4ab44
util: compression APIs to support revlog compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30773
diff
changeset
|
480 # zlib makes an internal copy of the input buffer, doubling |
31e1f0d4ab44
util: compression APIs to support revlog compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30773
diff
changeset
|
481 # memory usage for large inputs. So do streaming compression |
31e1f0d4ab44
util: compression APIs to support revlog compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30773
diff
changeset
|
482 # on large inputs. |
31e1f0d4ab44
util: compression APIs to support revlog compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30773
diff
changeset
|
483 else: |
42042
aaececb4b066
compression: accept level management for zlib compression
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
42041
diff
changeset
|
484 if self._level is None: |
aaececb4b066
compression: accept level management for zlib compression
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
42041
diff
changeset
|
485 z = zlib.compressobj() |
aaececb4b066
compression: accept level management for zlib compression
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
42041
diff
changeset
|
486 else: |
aaececb4b066
compression: accept level management for zlib compression
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
42041
diff
changeset
|
487 z = zlib.compressobj(level=self._level) |
30794
31e1f0d4ab44
util: compression APIs to support revlog compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30773
diff
changeset
|
488 parts = [] |
31e1f0d4ab44
util: compression APIs to support revlog compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30773
diff
changeset
|
489 pos = 0 |
31e1f0d4ab44
util: compression APIs to support revlog compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30773
diff
changeset
|
490 while pos < insize: |
31e1f0d4ab44
util: compression APIs to support revlog compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30773
diff
changeset
|
491 pos2 = pos + 2**20 |
31e1f0d4ab44
util: compression APIs to support revlog compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30773
diff
changeset
|
492 parts.append(z.compress(data[pos:pos2])) |
31e1f0d4ab44
util: compression APIs to support revlog compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30773
diff
changeset
|
493 pos = pos2 |
31e1f0d4ab44
util: compression APIs to support revlog compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30773
diff
changeset
|
494 parts.append(z.flush()) |
31e1f0d4ab44
util: compression APIs to support revlog compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30773
diff
changeset
|
495 |
31e1f0d4ab44
util: compression APIs to support revlog compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30773
diff
changeset
|
496 if sum(map(len, parts)) < insize: |
31e1f0d4ab44
util: compression APIs to support revlog compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30773
diff
changeset
|
497 return ''.join(parts) |
31e1f0d4ab44
util: compression APIs to support revlog compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30773
diff
changeset
|
498 return None |
31e1f0d4ab44
util: compression APIs to support revlog compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30773
diff
changeset
|
499 |
30798
f50c0db50025
util: compression APIs to support revlog decompression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30794
diff
changeset
|
500 def decompress(self, data): |
f50c0db50025
util: compression APIs to support revlog decompression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30794
diff
changeset
|
501 try: |
f50c0db50025
util: compression APIs to support revlog decompression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30794
diff
changeset
|
502 return zlib.decompress(data) |
f50c0db50025
util: compression APIs to support revlog decompression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30794
diff
changeset
|
503 except zlib.error as e: |
39777
b63dee7bd0d9
global: replace most uses of RevlogError with StorageError (API)
Gregory Szorc <gregory.szorc@gmail.com>
parents:
39571
diff
changeset
|
504 raise error.StorageError(_('revlog decompress error: %s') % |
b63dee7bd0d9
global: replace most uses of RevlogError with StorageError (API)
Gregory Szorc <gregory.szorc@gmail.com>
parents:
39571
diff
changeset
|
505 stringutil.forcebytestr(e)) |
30798
f50c0db50025
util: compression APIs to support revlog decompression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30794
diff
changeset
|
506 |
30794
31e1f0d4ab44
util: compression APIs to support revlog compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30773
diff
changeset
|
507 def revlogcompressor(self, opts=None): |
42043
1fac9b931d46
compression: introduce a `storage.revlog.zlib.level` configuration
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
42042
diff
changeset
|
508 level = None |
1fac9b931d46
compression: introduce a `storage.revlog.zlib.level` configuration
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
42042
diff
changeset
|
509 if opts is not None: |
1fac9b931d46
compression: introduce a `storage.revlog.zlib.level` configuration
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
42042
diff
changeset
|
510 level = opts.get('zlib.level') |
1fac9b931d46
compression: introduce a `storage.revlog.zlib.level` configuration
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
42042
diff
changeset
|
511 return self.zlibrevlogcompressor(level) |
30794
31e1f0d4ab44
util: compression APIs to support revlog compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30773
diff
changeset
|
512 |
30350
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
513 compengines.register(_zlibengine()) |
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
514 |
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
515 class _bz2engine(compressionengine): |
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
516 def name(self): |
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
517 return 'bz2' |
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
518 |
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
519 def bundletype(self): |
31792
55c0c91f55e6
util: document bundle compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
31777
diff
changeset
|
520 """An algorithm that produces smaller bundles than ``gzip``. |
55c0c91f55e6
util: document bundle compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
31777
diff
changeset
|
521 |
55c0c91f55e6
util: document bundle compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
31777
diff
changeset
|
522 All Mercurial clients should support this format. |
55c0c91f55e6
util: document bundle compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
31777
diff
changeset
|
523 |
55c0c91f55e6
util: document bundle compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
31777
diff
changeset
|
524 This engine will likely produce smaller bundles than ``gzip`` but |
55c0c91f55e6
util: document bundle compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
31777
diff
changeset
|
525 will be significantly slower, both during compression and |
55c0c91f55e6
util: document bundle compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
31777
diff
changeset
|
526 decompression. |
55c0c91f55e6
util: document bundle compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
31777
diff
changeset
|
527 |
55c0c91f55e6
util: document bundle compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
31777
diff
changeset
|
528 If available, the ``zstd`` engine can yield similar or better |
55c0c91f55e6
util: document bundle compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
31777
diff
changeset
|
529 compression at much higher speeds. |
55c0c91f55e6
util: document bundle compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
31777
diff
changeset
|
530 """ |
30350
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
531 return 'bzip2', 'BZ' |
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
532 |
30761
7283719e2bfd
util: declare wire protocol support of compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30745
diff
changeset
|
533 # We declare a protocol name but don't advertise by default because |
7283719e2bfd
util: declare wire protocol support of compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30745
diff
changeset
|
534 # it is slow. |
7283719e2bfd
util: declare wire protocol support of compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30745
diff
changeset
|
535 def wireprotosupport(self): |
7283719e2bfd
util: declare wire protocol support of compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30745
diff
changeset
|
536 return compewireprotosupport('bzip2', 0, 0) |
7283719e2bfd
util: declare wire protocol support of compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30745
diff
changeset
|
537 |
30356
c86109eface7
util: add a stream compression API to compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30355
diff
changeset
|
538 def compressstream(self, it, opts=None): |
c86109eface7
util: add a stream compression API to compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30355
diff
changeset
|
539 opts = opts or {} |
c86109eface7
util: add a stream compression API to compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30355
diff
changeset
|
540 z = bz2.BZ2Compressor(opts.get('level', 9)) |
c86109eface7
util: add a stream compression API to compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30355
diff
changeset
|
541 for chunk in it: |
c86109eface7
util: add a stream compression API to compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30355
diff
changeset
|
542 data = z.compress(chunk) |
c86109eface7
util: add a stream compression API to compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30355
diff
changeset
|
543 if data: |
c86109eface7
util: add a stream compression API to compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30355
diff
changeset
|
544 yield data |
c86109eface7
util: add a stream compression API to compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30355
diff
changeset
|
545 |
c86109eface7
util: add a stream compression API to compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30355
diff
changeset
|
546 yield z.flush() |
c86109eface7
util: add a stream compression API to compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30355
diff
changeset
|
547 |
30350
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
548 def decompressorreader(self, fh): |
38713
27391d74aaa2
ssh: avoid reading beyond the end of stream when using compression
Joerg Sonnenberger <joerg@bec.de>
parents:
38575
diff
changeset
|
549 return _BZ2CompressedStreamReader(fh) |
30350
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
550 |
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
551 compengines.register(_bz2engine()) |
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
552 |
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
553 class _truncatedbz2engine(compressionengine): |
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
554 def name(self): |
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
555 return 'bz2truncated' |
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
556 |
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
557 def bundletype(self): |
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
558 return None, '_truncatedBZ' |
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
559 |
30359
673f0fdc1046
util: remove compressorobj API from compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30356
diff
changeset
|
560 # We don't implement compressstream because it is hackily handled elsewhere. |
30350
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
561 |
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
562 def decompressorreader(self, fh): |
38713
27391d74aaa2
ssh: avoid reading beyond the end of stream when using compression
Joerg Sonnenberger <joerg@bec.de>
parents:
38575
diff
changeset
|
563 return _TruncatedBZ2CompressedStreamReader(fh) |
30350
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
564 |
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
565 compengines.register(_truncatedbz2engine()) |
30265
6a8aff737a17
util: put compression code next to each other
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30181
diff
changeset
|
566 |
30350
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
567 class _noopengine(compressionengine): |
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
568 def name(self): |
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
569 return 'none' |
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
570 |
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
571 def bundletype(self): |
31792
55c0c91f55e6
util: document bundle compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
31777
diff
changeset
|
572 """No compression is performed. |
55c0c91f55e6
util: document bundle compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
31777
diff
changeset
|
573 |
55c0c91f55e6
util: document bundle compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
31777
diff
changeset
|
574 Use this compression engine to explicitly disable compression. |
55c0c91f55e6
util: document bundle compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
31777
diff
changeset
|
575 """ |
30350
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
576 return 'none', 'UN' |
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
577 |
30761
7283719e2bfd
util: declare wire protocol support of compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30745
diff
changeset
|
578 # Clients always support uncompressed payloads. Servers don't because |
7283719e2bfd
util: declare wire protocol support of compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30745
diff
changeset
|
579 # unless you are on a fast network, uncompressed payloads can easily |
7283719e2bfd
util: declare wire protocol support of compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30745
diff
changeset
|
580 # saturate your network pipe. |
7283719e2bfd
util: declare wire protocol support of compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30745
diff
changeset
|
581 def wireprotosupport(self): |
7283719e2bfd
util: declare wire protocol support of compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30745
diff
changeset
|
582 return compewireprotosupport('none', 0, 10) |
7283719e2bfd
util: declare wire protocol support of compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30745
diff
changeset
|
583 |
30798
f50c0db50025
util: compression APIs to support revlog decompression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30794
diff
changeset
|
584 # We don't implement revlogheader because it is handled specially |
f50c0db50025
util: compression APIs to support revlog decompression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30794
diff
changeset
|
585 # in the revlog class. |
f50c0db50025
util: compression APIs to support revlog decompression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30794
diff
changeset
|
586 |
30356
c86109eface7
util: add a stream compression API to compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30355
diff
changeset
|
587 def compressstream(self, it, opts=None): |
c86109eface7
util: add a stream compression API to compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30355
diff
changeset
|
588 return it |
c86109eface7
util: add a stream compression API to compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30355
diff
changeset
|
589 |
30350
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
590 def decompressorreader(self, fh): |
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
591 return fh |
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
592 |
30794
31e1f0d4ab44
util: compression APIs to support revlog compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30773
diff
changeset
|
593 class nooprevlogcompressor(object): |
31e1f0d4ab44
util: compression APIs to support revlog compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30773
diff
changeset
|
594 def compress(self, data): |
31e1f0d4ab44
util: compression APIs to support revlog compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30773
diff
changeset
|
595 return None |
31e1f0d4ab44
util: compression APIs to support revlog compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30773
diff
changeset
|
596 |
31e1f0d4ab44
util: compression APIs to support revlog compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30773
diff
changeset
|
597 def revlogcompressor(self, opts=None): |
31e1f0d4ab44
util: compression APIs to support revlog compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30773
diff
changeset
|
598 return self.nooprevlogcompressor() |
31e1f0d4ab44
util: compression APIs to support revlog compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30773
diff
changeset
|
599 |
30350
358cda0af6ee
util: create new abstraction for compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30332
diff
changeset
|
600 compengines.register(_noopengine()) |
26266
1e042e31bd0c
changegroup: move all compressions utilities in util
Pierre-Yves David <pierre-yves.david@fb.com>
parents:
26201
diff
changeset
|
601 |
30442
41a8106789ca
util: implement zstd compression engine
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30438
diff
changeset
|
602 class _zstdengine(compressionengine): |
41a8106789ca
util: implement zstd compression engine
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30438
diff
changeset
|
603 def name(self): |
41a8106789ca
util: implement zstd compression engine
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30438
diff
changeset
|
604 return 'zstd' |
41a8106789ca
util: implement zstd compression engine
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30438
diff
changeset
|
605 |
41a8106789ca
util: implement zstd compression engine
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30438
diff
changeset
|
606 @propertycache |
41a8106789ca
util: implement zstd compression engine
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30438
diff
changeset
|
607 def _module(self): |
41a8106789ca
util: implement zstd compression engine
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30438
diff
changeset
|
608 # Not all installs have the zstd module available. So defer importing |
41a8106789ca
util: implement zstd compression engine
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30438
diff
changeset
|
609 # until first access. |
41a8106789ca
util: implement zstd compression engine
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30438
diff
changeset
|
610 try: |
42041
3e47d1ec9da5
util: extract compression code in `mercurial.utils.compression`
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
41834
diff
changeset
|
611 from .. import zstd |
30442
41a8106789ca
util: implement zstd compression engine
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30438
diff
changeset
|
612 # Force delayed import. |
41a8106789ca
util: implement zstd compression engine
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30438
diff
changeset
|
613 zstd.__version__ |
41a8106789ca
util: implement zstd compression engine
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30438
diff
changeset
|
614 return zstd |
41a8106789ca
util: implement zstd compression engine
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30438
diff
changeset
|
615 except ImportError: |
41a8106789ca
util: implement zstd compression engine
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30438
diff
changeset
|
616 return None |
41a8106789ca
util: implement zstd compression engine
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30438
diff
changeset
|
617 |
41a8106789ca
util: implement zstd compression engine
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30438
diff
changeset
|
618 def available(self): |
41a8106789ca
util: implement zstd compression engine
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30438
diff
changeset
|
619 return bool(self._module) |
41a8106789ca
util: implement zstd compression engine
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30438
diff
changeset
|
620 |
41a8106789ca
util: implement zstd compression engine
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30438
diff
changeset
|
621 def bundletype(self): |
31792
55c0c91f55e6
util: document bundle compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
31777
diff
changeset
|
622 """A modern compression algorithm that is fast and highly flexible. |
55c0c91f55e6
util: document bundle compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
31777
diff
changeset
|
623 |
55c0c91f55e6
util: document bundle compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
31777
diff
changeset
|
624 Only supported by Mercurial 4.1 and newer clients. |
55c0c91f55e6
util: document bundle compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
31777
diff
changeset
|
625 |
55c0c91f55e6
util: document bundle compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
31777
diff
changeset
|
626 With the default settings, zstd compression is both faster and yields |
55c0c91f55e6
util: document bundle compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
31777
diff
changeset
|
627 better compression than ``gzip``. It also frequently yields better |
55c0c91f55e6
util: document bundle compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
31777
diff
changeset
|
628 compression than ``bzip2`` while operating at much higher speeds. |
55c0c91f55e6
util: document bundle compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
31777
diff
changeset
|
629 |
55c0c91f55e6
util: document bundle compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
31777
diff
changeset
|
630 If this engine is available and backwards compatibility is not a |
55c0c91f55e6
util: document bundle compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
31777
diff
changeset
|
631 concern, it is likely the best available engine. |
55c0c91f55e6
util: document bundle compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
31777
diff
changeset
|
632 """ |
30442
41a8106789ca
util: implement zstd compression engine
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30438
diff
changeset
|
633 return 'zstd', 'ZS' |
41a8106789ca
util: implement zstd compression engine
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30438
diff
changeset
|
634 |
30761
7283719e2bfd
util: declare wire protocol support of compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30745
diff
changeset
|
635 def wireprotosupport(self): |
7283719e2bfd
util: declare wire protocol support of compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30745
diff
changeset
|
636 return compewireprotosupport('zstd', 50, 50) |
7283719e2bfd
util: declare wire protocol support of compression engines
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30745
diff
changeset
|
637 |
30798
f50c0db50025
util: compression APIs to support revlog decompression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30794
diff
changeset
|
638 def revlogheader(self): |
f50c0db50025
util: compression APIs to support revlog decompression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30794
diff
changeset
|
639 return '\x28' |
f50c0db50025
util: compression APIs to support revlog decompression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30794
diff
changeset
|
640 |
30442
41a8106789ca
util: implement zstd compression engine
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30438
diff
changeset
|
641 def compressstream(self, it, opts=None): |
41a8106789ca
util: implement zstd compression engine
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30438
diff
changeset
|
642 opts = opts or {} |
41a8106789ca
util: implement zstd compression engine
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30438
diff
changeset
|
643 # zstd level 3 is almost always significantly faster than zlib |
41a8106789ca
util: implement zstd compression engine
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30438
diff
changeset
|
644 # while providing no worse compression. It strikes a good balance |
41a8106789ca
util: implement zstd compression engine
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30438
diff
changeset
|
645 # between speed and compression. |
41a8106789ca
util: implement zstd compression engine
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30438
diff
changeset
|
646 level = opts.get('level', 3) |
41a8106789ca
util: implement zstd compression engine
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30438
diff
changeset
|
647 |
41a8106789ca
util: implement zstd compression engine
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30438
diff
changeset
|
648 zstd = self._module |
41a8106789ca
util: implement zstd compression engine
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30438
diff
changeset
|
649 z = zstd.ZstdCompressor(level=level).compressobj() |
41a8106789ca
util: implement zstd compression engine
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30438
diff
changeset
|
650 for chunk in it: |
41a8106789ca
util: implement zstd compression engine
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30438
diff
changeset
|
651 data = z.compress(chunk) |
41a8106789ca
util: implement zstd compression engine
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30438
diff
changeset
|
652 if data: |
41a8106789ca
util: implement zstd compression engine
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30438
diff
changeset
|
653 yield data |
41a8106789ca
util: implement zstd compression engine
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30438
diff
changeset
|
654 |
41a8106789ca
util: implement zstd compression engine
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30438
diff
changeset
|
655 yield z.flush() |
41a8106789ca
util: implement zstd compression engine
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30438
diff
changeset
|
656 |
41a8106789ca
util: implement zstd compression engine
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30438
diff
changeset
|
657 def decompressorreader(self, fh): |
38713
27391d74aaa2
ssh: avoid reading beyond the end of stream when using compression
Joerg Sonnenberger <joerg@bec.de>
parents:
38575
diff
changeset
|
658 return _ZstdCompressedStreamReader(fh, self._module) |
30442
41a8106789ca
util: implement zstd compression engine
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30438
diff
changeset
|
659 |
30794
31e1f0d4ab44
util: compression APIs to support revlog compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30773
diff
changeset
|
660 class zstdrevlogcompressor(object): |
31e1f0d4ab44
util: compression APIs to support revlog compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30773
diff
changeset
|
661 def __init__(self, zstd, level=3): |
37496
1765ed63db40
util: drop write_content_size=True
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37455
diff
changeset
|
662 # TODO consider omitting frame magic to save 4 bytes. |
1765ed63db40
util: drop write_content_size=True
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37455
diff
changeset
|
663 # This writes content sizes into the frame header. That is |
1765ed63db40
util: drop write_content_size=True
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37455
diff
changeset
|
664 # extra storage. But it allows a correct size memory allocation |
1765ed63db40
util: drop write_content_size=True
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37455
diff
changeset
|
665 # to hold the result. |
1765ed63db40
util: drop write_content_size=True
Gregory Szorc <gregory.szorc@gmail.com>
parents:
37455
diff
changeset
|
666 self._cctx = zstd.ZstdCompressor(level=level) |
30798
f50c0db50025
util: compression APIs to support revlog decompression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30794
diff
changeset
|
667 self._dctx = zstd.ZstdDecompressor() |
30794
31e1f0d4ab44
util: compression APIs to support revlog compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30773
diff
changeset
|
668 self._compinsize = zstd.COMPRESSION_RECOMMENDED_INPUT_SIZE |
30798
f50c0db50025
util: compression APIs to support revlog decompression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30794
diff
changeset
|
669 self._decompinsize = zstd.DECOMPRESSION_RECOMMENDED_INPUT_SIZE |
30794
31e1f0d4ab44
util: compression APIs to support revlog compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30773
diff
changeset
|
670 |
31e1f0d4ab44
util: compression APIs to support revlog compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30773
diff
changeset
|
671 def compress(self, data): |
31e1f0d4ab44
util: compression APIs to support revlog compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30773
diff
changeset
|
672 insize = len(data) |
31e1f0d4ab44
util: compression APIs to support revlog compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30773
diff
changeset
|
673 # Caller handles empty input case. |
31e1f0d4ab44
util: compression APIs to support revlog compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30773
diff
changeset
|
674 assert insize > 0 |
31e1f0d4ab44
util: compression APIs to support revlog compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30773
diff
changeset
|
675 |
31e1f0d4ab44
util: compression APIs to support revlog compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30773
diff
changeset
|
676 if insize < 50: |
31e1f0d4ab44
util: compression APIs to support revlog compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30773
diff
changeset
|
677 return None |
31e1f0d4ab44
util: compression APIs to support revlog compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30773
diff
changeset
|
678 |
31e1f0d4ab44
util: compression APIs to support revlog compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30773
diff
changeset
|
679 elif insize <= 1000000: |
31e1f0d4ab44
util: compression APIs to support revlog compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30773
diff
changeset
|
680 compressed = self._cctx.compress(data) |
31e1f0d4ab44
util: compression APIs to support revlog compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30773
diff
changeset
|
681 if len(compressed) < insize: |
31e1f0d4ab44
util: compression APIs to support revlog compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30773
diff
changeset
|
682 return compressed |
31e1f0d4ab44
util: compression APIs to support revlog compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30773
diff
changeset
|
683 return None |
31e1f0d4ab44
util: compression APIs to support revlog compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30773
diff
changeset
|
684 else: |
31e1f0d4ab44
util: compression APIs to support revlog compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30773
diff
changeset
|
685 z = self._cctx.compressobj() |
31e1f0d4ab44
util: compression APIs to support revlog compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30773
diff
changeset
|
686 chunks = [] |
31e1f0d4ab44
util: compression APIs to support revlog compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30773
diff
changeset
|
687 pos = 0 |
31e1f0d4ab44
util: compression APIs to support revlog compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30773
diff
changeset
|
688 while pos < insize: |
31e1f0d4ab44
util: compression APIs to support revlog compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30773
diff
changeset
|
689 pos2 = pos + self._compinsize |
31e1f0d4ab44
util: compression APIs to support revlog compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30773
diff
changeset
|
690 chunk = z.compress(data[pos:pos2]) |
31e1f0d4ab44
util: compression APIs to support revlog compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30773
diff
changeset
|
691 if chunk: |
31e1f0d4ab44
util: compression APIs to support revlog compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30773
diff
changeset
|
692 chunks.append(chunk) |
31e1f0d4ab44
util: compression APIs to support revlog compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30773
diff
changeset
|
693 pos = pos2 |
31e1f0d4ab44
util: compression APIs to support revlog compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30773
diff
changeset
|
694 chunks.append(z.flush()) |
31e1f0d4ab44
util: compression APIs to support revlog compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30773
diff
changeset
|
695 |
31e1f0d4ab44
util: compression APIs to support revlog compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30773
diff
changeset
|
696 if sum(map(len, chunks)) < insize: |
31e1f0d4ab44
util: compression APIs to support revlog compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30773
diff
changeset
|
697 return ''.join(chunks) |
31e1f0d4ab44
util: compression APIs to support revlog compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30773
diff
changeset
|
698 return None |
31e1f0d4ab44
util: compression APIs to support revlog compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30773
diff
changeset
|
699 |
30798
f50c0db50025
util: compression APIs to support revlog decompression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30794
diff
changeset
|
700 def decompress(self, data): |
f50c0db50025
util: compression APIs to support revlog decompression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30794
diff
changeset
|
701 insize = len(data) |
f50c0db50025
util: compression APIs to support revlog decompression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30794
diff
changeset
|
702 |
f50c0db50025
util: compression APIs to support revlog decompression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30794
diff
changeset
|
703 try: |
f50c0db50025
util: compression APIs to support revlog decompression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30794
diff
changeset
|
704 # This was measured to be faster than other streaming |
f50c0db50025
util: compression APIs to support revlog decompression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30794
diff
changeset
|
705 # decompressors. |
f50c0db50025
util: compression APIs to support revlog decompression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30794
diff
changeset
|
706 dobj = self._dctx.decompressobj() |
f50c0db50025
util: compression APIs to support revlog decompression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30794
diff
changeset
|
707 chunks = [] |
f50c0db50025
util: compression APIs to support revlog decompression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30794
diff
changeset
|
708 pos = 0 |
f50c0db50025
util: compression APIs to support revlog decompression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30794
diff
changeset
|
709 while pos < insize: |
f50c0db50025
util: compression APIs to support revlog decompression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30794
diff
changeset
|
710 pos2 = pos + self._decompinsize |
f50c0db50025
util: compression APIs to support revlog decompression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30794
diff
changeset
|
711 chunk = dobj.decompress(data[pos:pos2]) |
f50c0db50025
util: compression APIs to support revlog decompression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30794
diff
changeset
|
712 if chunk: |
f50c0db50025
util: compression APIs to support revlog decompression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30794
diff
changeset
|
713 chunks.append(chunk) |
f50c0db50025
util: compression APIs to support revlog decompression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30794
diff
changeset
|
714 pos = pos2 |
f50c0db50025
util: compression APIs to support revlog decompression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30794
diff
changeset
|
715 # Frame should be exhausted, so no finish() API. |
f50c0db50025
util: compression APIs to support revlog decompression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30794
diff
changeset
|
716 |
f50c0db50025
util: compression APIs to support revlog decompression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30794
diff
changeset
|
717 return ''.join(chunks) |
f50c0db50025
util: compression APIs to support revlog decompression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30794
diff
changeset
|
718 except Exception as e: |
39777
b63dee7bd0d9
global: replace most uses of RevlogError with StorageError (API)
Gregory Szorc <gregory.szorc@gmail.com>
parents:
39571
diff
changeset
|
719 raise error.StorageError(_('revlog decompress error: %s') % |
b63dee7bd0d9
global: replace most uses of RevlogError with StorageError (API)
Gregory Szorc <gregory.szorc@gmail.com>
parents:
39571
diff
changeset
|
720 stringutil.forcebytestr(e)) |
30798
f50c0db50025
util: compression APIs to support revlog decompression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30794
diff
changeset
|
721 |
30794
31e1f0d4ab44
util: compression APIs to support revlog compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30773
diff
changeset
|
722 def revlogcompressor(self, opts=None): |
31e1f0d4ab44
util: compression APIs to support revlog compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30773
diff
changeset
|
723 opts = opts or {} |
42044
bb271ec2fbfb
compression: introduce a `storage.revlog.zstd.level` configuration
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
42043
diff
changeset
|
724 level = opts.get('zstd.level') |
bb271ec2fbfb
compression: introduce a `storage.revlog.zstd.level` configuration
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
42043
diff
changeset
|
725 if level is None: |
bb271ec2fbfb
compression: introduce a `storage.revlog.zstd.level` configuration
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
42043
diff
changeset
|
726 level = opts.get('level') |
bb271ec2fbfb
compression: introduce a `storage.revlog.zstd.level` configuration
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
42043
diff
changeset
|
727 if level is None: |
bb271ec2fbfb
compression: introduce a `storage.revlog.zstd.level` configuration
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
42043
diff
changeset
|
728 level = 3 |
bb271ec2fbfb
compression: introduce a `storage.revlog.zstd.level` configuration
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
42043
diff
changeset
|
729 return self.zstdrevlogcompressor(self._module, level=level) |
30794
31e1f0d4ab44
util: compression APIs to support revlog compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30773
diff
changeset
|
730 |
30442
41a8106789ca
util: implement zstd compression engine
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30438
diff
changeset
|
731 compengines.register(_zstdengine()) |
41a8106789ca
util: implement zstd compression engine
Gregory Szorc <gregory.szorc@gmail.com>
parents:
30438
diff
changeset
|
732 |
31792
55c0c91f55e6
util: document bundle compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
31777
diff
changeset
|
733 def bundlecompressiontopics(): |
55c0c91f55e6
util: document bundle compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
31777
diff
changeset
|
734 """Obtains a list of available bundle compressions for use in help.""" |
55c0c91f55e6
util: document bundle compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
31777
diff
changeset
|
735 # help.makeitemsdocs() expects a dict of names to items with a .__doc__. |
55c0c91f55e6
util: document bundle compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
31777
diff
changeset
|
736 items = {} |
55c0c91f55e6
util: document bundle compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
31777
diff
changeset
|
737 |
55c0c91f55e6
util: document bundle compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
31777
diff
changeset
|
738 # We need to format the docstring. So use a dummy object/type to hold it |
55c0c91f55e6
util: document bundle compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
31777
diff
changeset
|
739 # rather than mutating the original. |
55c0c91f55e6
util: document bundle compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
31777
diff
changeset
|
740 class docobject(object): |
55c0c91f55e6
util: document bundle compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
31777
diff
changeset
|
741 pass |
55c0c91f55e6
util: document bundle compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
31777
diff
changeset
|
742 |
55c0c91f55e6
util: document bundle compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
31777
diff
changeset
|
743 for name in compengines: |
55c0c91f55e6
util: document bundle compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
31777
diff
changeset
|
744 engine = compengines[name] |
55c0c91f55e6
util: document bundle compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
31777
diff
changeset
|
745 |
55c0c91f55e6
util: document bundle compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
31777
diff
changeset
|
746 if not engine.available(): |
55c0c91f55e6
util: document bundle compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
31777
diff
changeset
|
747 continue |
55c0c91f55e6
util: document bundle compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
31777
diff
changeset
|
748 |
55c0c91f55e6
util: document bundle compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
31777
diff
changeset
|
749 bt = engine.bundletype() |
55c0c91f55e6
util: document bundle compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
31777
diff
changeset
|
750 if not bt or not bt[0]: |
55c0c91f55e6
util: document bundle compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
31777
diff
changeset
|
751 continue |
55c0c91f55e6
util: document bundle compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
31777
diff
changeset
|
752 |
40251
3c89227788a2
py3: build help of compression engines in bytes
Yuya Nishihara <yuya@tcha.org>
parents:
40029
diff
changeset
|
753 doc = b'``%s``\n %s' % (bt[0], pycompat.getdoc(engine.bundletype)) |
31792
55c0c91f55e6
util: document bundle compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
31777
diff
changeset
|
754 |
55c0c91f55e6
util: document bundle compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
31777
diff
changeset
|
755 value = docobject() |
40251
3c89227788a2
py3: build help of compression engines in bytes
Yuya Nishihara <yuya@tcha.org>
parents:
40029
diff
changeset
|
756 value.__doc__ = pycompat.sysstr(doc) |
33818
ed04d7254a91
i18n: use saved object to get actual function information if available
FUJIWARA Katsunori <foozy@lares.dti.ne.jp>
parents:
33799
diff
changeset
|
757 value._origdoc = engine.bundletype.__doc__ |
ed04d7254a91
i18n: use saved object to get actual function information if available
FUJIWARA Katsunori <foozy@lares.dti.ne.jp>
parents:
33799
diff
changeset
|
758 value._origfunc = engine.bundletype |
31792
55c0c91f55e6
util: document bundle compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
31777
diff
changeset
|
759 |
55c0c91f55e6
util: document bundle compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
31777
diff
changeset
|
760 items[bt[0]] = value |
55c0c91f55e6
util: document bundle compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
31777
diff
changeset
|
761 |
55c0c91f55e6
util: document bundle compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
31777
diff
changeset
|
762 return items |
55c0c91f55e6
util: document bundle compression
Gregory Szorc <gregory.szorc@gmail.com>
parents:
31777
diff
changeset
|
763 |
33820
fa7e30efe05a
i18n: get translation entries for description of each compression engines
FUJIWARA Katsunori <foozy@lares.dti.ne.jp>
parents:
33818
diff
changeset
|
764 i18nfunctions = bundlecompressiontopics().values() |