Show More
@@ -1,837 +1,841 b'' | |||||
1 | # -*- coding: utf-8 -*- |
|
1 | # -*- coding: utf-8 -*- | |
2 |
|
2 | |||
3 | # Copyright (C) 2014-2019 RhodeCode GmbH |
|
3 | # Copyright (C) 2014-2019 RhodeCode GmbH | |
4 | # |
|
4 | # | |
5 | # This program is free software: you can redistribute it and/or modify |
|
5 | # This program is free software: you can redistribute it and/or modify | |
6 | # it under the terms of the GNU Affero General Public License, version 3 |
|
6 | # it under the terms of the GNU Affero General Public License, version 3 | |
7 | # (only), as published by the Free Software Foundation. |
|
7 | # (only), as published by the Free Software Foundation. | |
8 | # |
|
8 | # | |
9 | # This program is distributed in the hope that it will be useful, |
|
9 | # This program is distributed in the hope that it will be useful, | |
10 | # but WITHOUT ANY WARRANTY; without even the implied warranty of |
|
10 | # but WITHOUT ANY WARRANTY; without even the implied warranty of | |
11 | # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the |
|
11 | # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the | |
12 | # GNU General Public License for more details. |
|
12 | # GNU General Public License for more details. | |
13 | # |
|
13 | # | |
14 | # You should have received a copy of the GNU Affero General Public License |
|
14 | # You should have received a copy of the GNU Affero General Public License | |
15 | # along with this program. If not, see <http://www.gnu.org/licenses/>. |
|
15 | # along with this program. If not, see <http://www.gnu.org/licenses/>. | |
16 | # |
|
16 | # | |
17 | # This program is dual-licensed. If you wish to learn more about the |
|
17 | # This program is dual-licensed. If you wish to learn more about the | |
18 | # RhodeCode Enterprise Edition, including its added features, Support services, |
|
18 | # RhodeCode Enterprise Edition, including its added features, Support services, | |
19 | # and proprietary license terms, please see https://rhodecode.com/licenses/ |
|
19 | # and proprietary license terms, please see https://rhodecode.com/licenses/ | |
20 |
|
20 | |||
21 | """ |
|
21 | """ | |
22 | Module holding everything related to vcs nodes, with vcs2 architecture. |
|
22 | Module holding everything related to vcs nodes, with vcs2 architecture. | |
23 | """ |
|
23 | """ | |
24 |
|
24 | |||
25 | import os |
|
25 | import os | |
26 | import stat |
|
26 | import stat | |
27 |
|
27 | |||
28 | from zope.cachedescriptors.property import Lazy as LazyProperty |
|
28 | from zope.cachedescriptors.property import Lazy as LazyProperty | |
29 |
|
29 | |||
30 | from rhodecode.config.conf import LANGUAGES_EXTENSIONS_MAP |
|
30 | from rhodecode.config.conf import LANGUAGES_EXTENSIONS_MAP | |
31 | from rhodecode.lib.utils import safe_unicode, safe_str |
|
31 | from rhodecode.lib.utils import safe_unicode, safe_str | |
32 | from rhodecode.lib.utils2 import md5 |
|
32 | from rhodecode.lib.utils2 import md5 | |
33 | from rhodecode.lib.vcs import path as vcspath |
|
33 | from rhodecode.lib.vcs import path as vcspath | |
34 | from rhodecode.lib.vcs.backends.base import EmptyCommit, FILEMODE_DEFAULT |
|
34 | from rhodecode.lib.vcs.backends.base import EmptyCommit, FILEMODE_DEFAULT | |
35 | from rhodecode.lib.vcs.conf.mtypes import get_mimetypes_db |
|
35 | from rhodecode.lib.vcs.conf.mtypes import get_mimetypes_db | |
36 | from rhodecode.lib.vcs.exceptions import NodeError, RemovedFileNodeError |
|
36 | from rhodecode.lib.vcs.exceptions import NodeError, RemovedFileNodeError | |
37 |
|
37 | |||
38 | LARGEFILE_PREFIX = '.hglf' |
|
38 | LARGEFILE_PREFIX = '.hglf' | |
39 |
|
39 | |||
40 |
|
40 | |||
41 | class NodeKind: |
|
41 | class NodeKind: | |
42 | SUBMODULE = -1 |
|
42 | SUBMODULE = -1 | |
43 | DIR = 1 |
|
43 | DIR = 1 | |
44 | FILE = 2 |
|
44 | FILE = 2 | |
45 | LARGEFILE = 3 |
|
45 | LARGEFILE = 3 | |
46 |
|
46 | |||
47 |
|
47 | |||
48 | class NodeState: |
|
48 | class NodeState: | |
49 | ADDED = u'added' |
|
49 | ADDED = u'added' | |
50 | CHANGED = u'changed' |
|
50 | CHANGED = u'changed' | |
51 | NOT_CHANGED = u'not changed' |
|
51 | NOT_CHANGED = u'not changed' | |
52 | REMOVED = u'removed' |
|
52 | REMOVED = u'removed' | |
53 |
|
53 | |||
54 |
|
54 | |||
55 | class NodeGeneratorBase(object): |
|
55 | class NodeGeneratorBase(object): | |
56 | """ |
|
56 | """ | |
57 | Base class for removed added and changed filenodes, it's a lazy generator |
|
57 | Base class for removed added and changed filenodes, it's a lazy generator | |
58 | class that will create filenodes only on iteration or call |
|
58 | class that will create filenodes only on iteration or call | |
59 |
|
59 | |||
60 | The len method doesn't need to create filenodes at all |
|
60 | The len method doesn't need to create filenodes at all | |
61 | """ |
|
61 | """ | |
62 |
|
62 | |||
63 | def __init__(self, current_paths, cs): |
|
63 | def __init__(self, current_paths, cs): | |
64 | self.cs = cs |
|
64 | self.cs = cs | |
65 | self.current_paths = current_paths |
|
65 | self.current_paths = current_paths | |
66 |
|
66 | |||
67 | def __call__(self): |
|
67 | def __call__(self): | |
68 | return [n for n in self] |
|
68 | return [n for n in self] | |
69 |
|
69 | |||
70 | def __getslice__(self, i, j): |
|
70 | def __getslice__(self, i, j): | |
71 | for p in self.current_paths[i:j]: |
|
71 | for p in self.current_paths[i:j]: | |
72 | yield self.cs.get_node(p) |
|
72 | yield self.cs.get_node(p) | |
73 |
|
73 | |||
74 | def __len__(self): |
|
74 | def __len__(self): | |
75 | return len(self.current_paths) |
|
75 | return len(self.current_paths) | |
76 |
|
76 | |||
77 | def __iter__(self): |
|
77 | def __iter__(self): | |
78 | for p in self.current_paths: |
|
78 | for p in self.current_paths: | |
79 | yield self.cs.get_node(p) |
|
79 | yield self.cs.get_node(p) | |
80 |
|
80 | |||
81 |
|
81 | |||
82 | class AddedFileNodesGenerator(NodeGeneratorBase): |
|
82 | class AddedFileNodesGenerator(NodeGeneratorBase): | |
83 | """ |
|
83 | """ | |
84 | Class holding added files for current commit |
|
84 | Class holding added files for current commit | |
85 | """ |
|
85 | """ | |
86 |
|
86 | |||
87 |
|
87 | |||
88 | class ChangedFileNodesGenerator(NodeGeneratorBase): |
|
88 | class ChangedFileNodesGenerator(NodeGeneratorBase): | |
89 | """ |
|
89 | """ | |
90 | Class holding changed files for current commit |
|
90 | Class holding changed files for current commit | |
91 | """ |
|
91 | """ | |
92 |
|
92 | |||
93 |
|
93 | |||
94 | class RemovedFileNodesGenerator(NodeGeneratorBase): |
|
94 | class RemovedFileNodesGenerator(NodeGeneratorBase): | |
95 | """ |
|
95 | """ | |
96 | Class holding removed files for current commit |
|
96 | Class holding removed files for current commit | |
97 | """ |
|
97 | """ | |
98 | def __iter__(self): |
|
98 | def __iter__(self): | |
99 | for p in self.current_paths: |
|
99 | for p in self.current_paths: | |
100 | yield RemovedFileNode(path=p) |
|
100 | yield RemovedFileNode(path=p) | |
101 |
|
101 | |||
102 | def __getslice__(self, i, j): |
|
102 | def __getslice__(self, i, j): | |
103 | for p in self.current_paths[i:j]: |
|
103 | for p in self.current_paths[i:j]: | |
104 | yield RemovedFileNode(path=p) |
|
104 | yield RemovedFileNode(path=p) | |
105 |
|
105 | |||
106 |
|
106 | |||
107 | class Node(object): |
|
107 | class Node(object): | |
108 | """ |
|
108 | """ | |
109 | Simplest class representing file or directory on repository. SCM backends |
|
109 | Simplest class representing file or directory on repository. SCM backends | |
110 | should use ``FileNode`` and ``DirNode`` subclasses rather than ``Node`` |
|
110 | should use ``FileNode`` and ``DirNode`` subclasses rather than ``Node`` | |
111 | directly. |
|
111 | directly. | |
112 |
|
112 | |||
113 | Node's ``path`` cannot start with slash as we operate on *relative* paths |
|
113 | Node's ``path`` cannot start with slash as we operate on *relative* paths | |
114 | only. Moreover, every single node is identified by the ``path`` attribute, |
|
114 | only. Moreover, every single node is identified by the ``path`` attribute, | |
115 | so it cannot end with slash, too. Otherwise, path could lead to mistakes. |
|
115 | so it cannot end with slash, too. Otherwise, path could lead to mistakes. | |
116 | """ |
|
116 | """ | |
117 | RTLO_MARKER = u"\u202E" # RTLO marker allows swapping text, and certain |
|
117 | RTLO_MARKER = u"\u202E" # RTLO marker allows swapping text, and certain | |
118 | # security attacks could be used with this |
|
118 | # security attacks could be used with this | |
119 | commit = None |
|
119 | commit = None | |
120 |
|
120 | |||
121 | def __init__(self, path, kind): |
|
121 | def __init__(self, path, kind): | |
122 | self._validate_path(path) # can throw exception if path is invalid |
|
122 | self._validate_path(path) # can throw exception if path is invalid | |
123 | self.path = safe_str(path.rstrip('/')) # we store paths as str |
|
123 | self.path = safe_str(path.rstrip('/')) # we store paths as str | |
124 | if path == '' and kind != NodeKind.DIR: |
|
124 | if path == '' and kind != NodeKind.DIR: | |
125 | raise NodeError("Only DirNode and its subclasses may be " |
|
125 | raise NodeError("Only DirNode and its subclasses may be " | |
126 | "initialized with empty path") |
|
126 | "initialized with empty path") | |
127 | self.kind = kind |
|
127 | self.kind = kind | |
128 |
|
128 | |||
129 | if self.is_root() and not self.is_dir(): |
|
129 | if self.is_root() and not self.is_dir(): | |
130 | raise NodeError("Root node cannot be FILE kind") |
|
130 | raise NodeError("Root node cannot be FILE kind") | |
131 |
|
131 | |||
132 | def _validate_path(self, path): |
|
132 | def _validate_path(self, path): | |
133 | if path.startswith('/'): |
|
133 | if path.startswith('/'): | |
134 | raise NodeError( |
|
134 | raise NodeError( | |
135 | "Cannot initialize Node objects with slash at " |
|
135 | "Cannot initialize Node objects with slash at " | |
136 | "the beginning as only relative paths are supported. " |
|
136 | "the beginning as only relative paths are supported. " | |
137 | "Got %s" % (path,)) |
|
137 | "Got %s" % (path,)) | |
138 |
|
138 | |||
139 | @LazyProperty |
|
139 | @LazyProperty | |
140 | def parent(self): |
|
140 | def parent(self): | |
141 | parent_path = self.get_parent_path() |
|
141 | parent_path = self.get_parent_path() | |
142 | if parent_path: |
|
142 | if parent_path: | |
143 | if self.commit: |
|
143 | if self.commit: | |
144 | return self.commit.get_node(parent_path) |
|
144 | return self.commit.get_node(parent_path) | |
145 | return DirNode(parent_path) |
|
145 | return DirNode(parent_path) | |
146 | return None |
|
146 | return None | |
147 |
|
147 | |||
148 | @LazyProperty |
|
148 | @LazyProperty | |
149 | def unicode_path(self): |
|
149 | def unicode_path(self): | |
150 | return safe_unicode(self.path) |
|
150 | return safe_unicode(self.path) | |
151 |
|
151 | |||
152 | @LazyProperty |
|
152 | @LazyProperty | |
153 | def has_rtlo(self): |
|
153 | def has_rtlo(self): | |
154 | """Detects if a path has right-to-left-override marker""" |
|
154 | """Detects if a path has right-to-left-override marker""" | |
155 | return self.RTLO_MARKER in self.unicode_path |
|
155 | return self.RTLO_MARKER in self.unicode_path | |
156 |
|
156 | |||
157 | @LazyProperty |
|
157 | @LazyProperty | |
158 | def unicode_path_safe(self): |
|
158 | def unicode_path_safe(self): | |
159 | """ |
|
159 | """ | |
160 | Special SAFE representation of path without the right-to-left-override. |
|
160 | Special SAFE representation of path without the right-to-left-override. | |
161 | This should be only used for "showing" the file, cannot be used for any |
|
161 | This should be only used for "showing" the file, cannot be used for any | |
162 | urls etc. |
|
162 | urls etc. | |
163 | """ |
|
163 | """ | |
164 | return safe_unicode(self.path).replace(self.RTLO_MARKER, '') |
|
164 | return safe_unicode(self.path).replace(self.RTLO_MARKER, '') | |
165 |
|
165 | |||
166 | @LazyProperty |
|
166 | @LazyProperty | |
167 | def dir_path(self): |
|
167 | def dir_path(self): | |
168 | """ |
|
168 | """ | |
169 | Returns name of the directory from full path of this vcs node. Empty |
|
169 | Returns name of the directory from full path of this vcs node. Empty | |
170 | string is returned if there's no directory in the path |
|
170 | string is returned if there's no directory in the path | |
171 | """ |
|
171 | """ | |
172 | _parts = self.path.rstrip('/').rsplit('/', 1) |
|
172 | _parts = self.path.rstrip('/').rsplit('/', 1) | |
173 | if len(_parts) == 2: |
|
173 | if len(_parts) == 2: | |
174 | return safe_unicode(_parts[0]) |
|
174 | return safe_unicode(_parts[0]) | |
175 | return u'' |
|
175 | return u'' | |
176 |
|
176 | |||
177 | @LazyProperty |
|
177 | @LazyProperty | |
178 | def name(self): |
|
178 | def name(self): | |
179 | """ |
|
179 | """ | |
180 | Returns name of the node so if its path |
|
180 | Returns name of the node so if its path | |
181 | then only last part is returned. |
|
181 | then only last part is returned. | |
182 | """ |
|
182 | """ | |
183 | return safe_unicode(self.path.rstrip('/').split('/')[-1]) |
|
183 | return safe_unicode(self.path.rstrip('/').split('/')[-1]) | |
184 |
|
184 | |||
185 | @property |
|
185 | @property | |
186 | def kind(self): |
|
186 | def kind(self): | |
187 | return self._kind |
|
187 | return self._kind | |
188 |
|
188 | |||
189 | @kind.setter |
|
189 | @kind.setter | |
190 | def kind(self, kind): |
|
190 | def kind(self, kind): | |
191 | if hasattr(self, '_kind'): |
|
191 | if hasattr(self, '_kind'): | |
192 | raise NodeError("Cannot change node's kind") |
|
192 | raise NodeError("Cannot change node's kind") | |
193 | else: |
|
193 | else: | |
194 | self._kind = kind |
|
194 | self._kind = kind | |
195 | # Post setter check (path's trailing slash) |
|
195 | # Post setter check (path's trailing slash) | |
196 | if self.path.endswith('/'): |
|
196 | if self.path.endswith('/'): | |
197 | raise NodeError("Node's path cannot end with slash") |
|
197 | raise NodeError("Node's path cannot end with slash") | |
198 |
|
198 | |||
199 | def __cmp__(self, other): |
|
199 | def __cmp__(self, other): | |
200 | """ |
|
200 | """ | |
201 | Comparator using name of the node, needed for quick list sorting. |
|
201 | Comparator using name of the node, needed for quick list sorting. | |
202 | """ |
|
202 | """ | |
|
203 | ||||
203 | kind_cmp = cmp(self.kind, other.kind) |
|
204 | kind_cmp = cmp(self.kind, other.kind) | |
204 | if kind_cmp: |
|
205 | if kind_cmp: | |
|
206 | if isinstance(self, SubModuleNode): | |||
|
207 | # we make submodules equal to dirnode for "sorting" purposes | |||
|
208 | return NodeKind.DIR | |||
205 | return kind_cmp |
|
209 | return kind_cmp | |
206 | return cmp(self.name, other.name) |
|
210 | return cmp(self.name, other.name) | |
207 |
|
211 | |||
208 | def __eq__(self, other): |
|
212 | def __eq__(self, other): | |
209 | for attr in ['name', 'path', 'kind']: |
|
213 | for attr in ['name', 'path', 'kind']: | |
210 | if getattr(self, attr) != getattr(other, attr): |
|
214 | if getattr(self, attr) != getattr(other, attr): | |
211 | return False |
|
215 | return False | |
212 | if self.is_file(): |
|
216 | if self.is_file(): | |
213 | if self.content != other.content: |
|
217 | if self.content != other.content: | |
214 | return False |
|
218 | return False | |
215 | else: |
|
219 | else: | |
216 | # For DirNode's check without entering each dir |
|
220 | # For DirNode's check without entering each dir | |
217 | self_nodes_paths = list(sorted(n.path for n in self.nodes)) |
|
221 | self_nodes_paths = list(sorted(n.path for n in self.nodes)) | |
218 | other_nodes_paths = list(sorted(n.path for n in self.nodes)) |
|
222 | other_nodes_paths = list(sorted(n.path for n in self.nodes)) | |
219 | if self_nodes_paths != other_nodes_paths: |
|
223 | if self_nodes_paths != other_nodes_paths: | |
220 | return False |
|
224 | return False | |
221 | return True |
|
225 | return True | |
222 |
|
226 | |||
223 | def __ne__(self, other): |
|
227 | def __ne__(self, other): | |
224 | return not self.__eq__(other) |
|
228 | return not self.__eq__(other) | |
225 |
|
229 | |||
226 | def __repr__(self): |
|
230 | def __repr__(self): | |
227 | return '<%s %r>' % (self.__class__.__name__, self.path) |
|
231 | return '<%s %r>' % (self.__class__.__name__, self.path) | |
228 |
|
232 | |||
229 | def __str__(self): |
|
233 | def __str__(self): | |
230 | return self.__repr__() |
|
234 | return self.__repr__() | |
231 |
|
235 | |||
232 | def __unicode__(self): |
|
236 | def __unicode__(self): | |
233 | return self.name |
|
237 | return self.name | |
234 |
|
238 | |||
235 | def get_parent_path(self): |
|
239 | def get_parent_path(self): | |
236 | """ |
|
240 | """ | |
237 | Returns node's parent path or empty string if node is root. |
|
241 | Returns node's parent path or empty string if node is root. | |
238 | """ |
|
242 | """ | |
239 | if self.is_root(): |
|
243 | if self.is_root(): | |
240 | return '' |
|
244 | return '' | |
241 | return vcspath.dirname(self.path.rstrip('/')) + '/' |
|
245 | return vcspath.dirname(self.path.rstrip('/')) + '/' | |
242 |
|
246 | |||
243 | def is_file(self): |
|
247 | def is_file(self): | |
244 | """ |
|
248 | """ | |
245 | Returns ``True`` if node's kind is ``NodeKind.FILE``, ``False`` |
|
249 | Returns ``True`` if node's kind is ``NodeKind.FILE``, ``False`` | |
246 | otherwise. |
|
250 | otherwise. | |
247 | """ |
|
251 | """ | |
248 | return self.kind == NodeKind.FILE |
|
252 | return self.kind == NodeKind.FILE | |
249 |
|
253 | |||
250 | def is_dir(self): |
|
254 | def is_dir(self): | |
251 | """ |
|
255 | """ | |
252 | Returns ``True`` if node's kind is ``NodeKind.DIR``, ``False`` |
|
256 | Returns ``True`` if node's kind is ``NodeKind.DIR``, ``False`` | |
253 | otherwise. |
|
257 | otherwise. | |
254 | """ |
|
258 | """ | |
255 | return self.kind == NodeKind.DIR |
|
259 | return self.kind == NodeKind.DIR | |
256 |
|
260 | |||
257 | def is_root(self): |
|
261 | def is_root(self): | |
258 | """ |
|
262 | """ | |
259 | Returns ``True`` if node is a root node and ``False`` otherwise. |
|
263 | Returns ``True`` if node is a root node and ``False`` otherwise. | |
260 | """ |
|
264 | """ | |
261 | return self.kind == NodeKind.DIR and self.path == '' |
|
265 | return self.kind == NodeKind.DIR and self.path == '' | |
262 |
|
266 | |||
263 | def is_submodule(self): |
|
267 | def is_submodule(self): | |
264 | """ |
|
268 | """ | |
265 | Returns ``True`` if node's kind is ``NodeKind.SUBMODULE``, ``False`` |
|
269 | Returns ``True`` if node's kind is ``NodeKind.SUBMODULE``, ``False`` | |
266 | otherwise. |
|
270 | otherwise. | |
267 | """ |
|
271 | """ | |
268 | return self.kind == NodeKind.SUBMODULE |
|
272 | return self.kind == NodeKind.SUBMODULE | |
269 |
|
273 | |||
270 | def is_largefile(self): |
|
274 | def is_largefile(self): | |
271 | """ |
|
275 | """ | |
272 | Returns ``True`` if node's kind is ``NodeKind.LARGEFILE``, ``False`` |
|
276 | Returns ``True`` if node's kind is ``NodeKind.LARGEFILE``, ``False`` | |
273 | otherwise |
|
277 | otherwise | |
274 | """ |
|
278 | """ | |
275 | return self.kind == NodeKind.LARGEFILE |
|
279 | return self.kind == NodeKind.LARGEFILE | |
276 |
|
280 | |||
277 | def is_link(self): |
|
281 | def is_link(self): | |
278 | if self.commit: |
|
282 | if self.commit: | |
279 | return self.commit.is_link(self.path) |
|
283 | return self.commit.is_link(self.path) | |
280 | return False |
|
284 | return False | |
281 |
|
285 | |||
282 | @LazyProperty |
|
286 | @LazyProperty | |
283 | def added(self): |
|
287 | def added(self): | |
284 | return self.state is NodeState.ADDED |
|
288 | return self.state is NodeState.ADDED | |
285 |
|
289 | |||
286 | @LazyProperty |
|
290 | @LazyProperty | |
287 | def changed(self): |
|
291 | def changed(self): | |
288 | return self.state is NodeState.CHANGED |
|
292 | return self.state is NodeState.CHANGED | |
289 |
|
293 | |||
290 | @LazyProperty |
|
294 | @LazyProperty | |
291 | def not_changed(self): |
|
295 | def not_changed(self): | |
292 | return self.state is NodeState.NOT_CHANGED |
|
296 | return self.state is NodeState.NOT_CHANGED | |
293 |
|
297 | |||
294 | @LazyProperty |
|
298 | @LazyProperty | |
295 | def removed(self): |
|
299 | def removed(self): | |
296 | return self.state is NodeState.REMOVED |
|
300 | return self.state is NodeState.REMOVED | |
297 |
|
301 | |||
298 |
|
302 | |||
299 | class FileNode(Node): |
|
303 | class FileNode(Node): | |
300 | """ |
|
304 | """ | |
301 | Class representing file nodes. |
|
305 | Class representing file nodes. | |
302 |
|
306 | |||
303 | :attribute: path: path to the node, relative to repository's root |
|
307 | :attribute: path: path to the node, relative to repository's root | |
304 | :attribute: content: if given arbitrary sets content of the file |
|
308 | :attribute: content: if given arbitrary sets content of the file | |
305 | :attribute: commit: if given, first time content is accessed, callback |
|
309 | :attribute: commit: if given, first time content is accessed, callback | |
306 | :attribute: mode: stat mode for a node. Default is `FILEMODE_DEFAULT`. |
|
310 | :attribute: mode: stat mode for a node. Default is `FILEMODE_DEFAULT`. | |
307 | """ |
|
311 | """ | |
308 | _filter_pre_load = [] |
|
312 | _filter_pre_load = [] | |
309 |
|
313 | |||
310 | def __init__(self, path, content=None, commit=None, mode=None, pre_load=None): |
|
314 | def __init__(self, path, content=None, commit=None, mode=None, pre_load=None): | |
311 | """ |
|
315 | """ | |
312 | Only one of ``content`` and ``commit`` may be given. Passing both |
|
316 | Only one of ``content`` and ``commit`` may be given. Passing both | |
313 | would raise ``NodeError`` exception. |
|
317 | would raise ``NodeError`` exception. | |
314 |
|
318 | |||
315 | :param path: relative path to the node |
|
319 | :param path: relative path to the node | |
316 | :param content: content may be passed to constructor |
|
320 | :param content: content may be passed to constructor | |
317 | :param commit: if given, will use it to lazily fetch content |
|
321 | :param commit: if given, will use it to lazily fetch content | |
318 | :param mode: ST_MODE (i.e. 0100644) |
|
322 | :param mode: ST_MODE (i.e. 0100644) | |
319 | """ |
|
323 | """ | |
320 | if content and commit: |
|
324 | if content and commit: | |
321 | raise NodeError("Cannot use both content and commit") |
|
325 | raise NodeError("Cannot use both content and commit") | |
322 | super(FileNode, self).__init__(path, kind=NodeKind.FILE) |
|
326 | super(FileNode, self).__init__(path, kind=NodeKind.FILE) | |
323 | self.commit = commit |
|
327 | self.commit = commit | |
324 | self._content = content |
|
328 | self._content = content | |
325 | self._mode = mode or FILEMODE_DEFAULT |
|
329 | self._mode = mode or FILEMODE_DEFAULT | |
326 |
|
330 | |||
327 | self._set_bulk_properties(pre_load) |
|
331 | self._set_bulk_properties(pre_load) | |
328 |
|
332 | |||
329 | def _set_bulk_properties(self, pre_load): |
|
333 | def _set_bulk_properties(self, pre_load): | |
330 | if not pre_load: |
|
334 | if not pre_load: | |
331 | return |
|
335 | return | |
332 | pre_load = [entry for entry in pre_load |
|
336 | pre_load = [entry for entry in pre_load | |
333 | if entry not in self._filter_pre_load] |
|
337 | if entry not in self._filter_pre_load] | |
334 | if not pre_load: |
|
338 | if not pre_load: | |
335 | return |
|
339 | return | |
336 |
|
340 | |||
337 | for attr_name in pre_load: |
|
341 | for attr_name in pre_load: | |
338 | result = getattr(self, attr_name) |
|
342 | result = getattr(self, attr_name) | |
339 | if callable(result): |
|
343 | if callable(result): | |
340 | result = result() |
|
344 | result = result() | |
341 | self.__dict__[attr_name] = result |
|
345 | self.__dict__[attr_name] = result | |
342 |
|
346 | |||
343 | @LazyProperty |
|
347 | @LazyProperty | |
344 | def mode(self): |
|
348 | def mode(self): | |
345 | """ |
|
349 | """ | |
346 | Returns lazily mode of the FileNode. If `commit` is not set, would |
|
350 | Returns lazily mode of the FileNode. If `commit` is not set, would | |
347 | use value given at initialization or `FILEMODE_DEFAULT` (default). |
|
351 | use value given at initialization or `FILEMODE_DEFAULT` (default). | |
348 | """ |
|
352 | """ | |
349 | if self.commit: |
|
353 | if self.commit: | |
350 | mode = self.commit.get_file_mode(self.path) |
|
354 | mode = self.commit.get_file_mode(self.path) | |
351 | else: |
|
355 | else: | |
352 | mode = self._mode |
|
356 | mode = self._mode | |
353 | return mode |
|
357 | return mode | |
354 |
|
358 | |||
355 | @LazyProperty |
|
359 | @LazyProperty | |
356 | def raw_bytes(self): |
|
360 | def raw_bytes(self): | |
357 | """ |
|
361 | """ | |
358 | Returns lazily the raw bytes of the FileNode. |
|
362 | Returns lazily the raw bytes of the FileNode. | |
359 | """ |
|
363 | """ | |
360 | if self.commit: |
|
364 | if self.commit: | |
361 | if self._content is None: |
|
365 | if self._content is None: | |
362 | self._content = self.commit.get_file_content(self.path) |
|
366 | self._content = self.commit.get_file_content(self.path) | |
363 | content = self._content |
|
367 | content = self._content | |
364 | else: |
|
368 | else: | |
365 | content = self._content |
|
369 | content = self._content | |
366 | return content |
|
370 | return content | |
367 |
|
371 | |||
368 | @LazyProperty |
|
372 | @LazyProperty | |
369 | def md5(self): |
|
373 | def md5(self): | |
370 | """ |
|
374 | """ | |
371 | Returns md5 of the file node. |
|
375 | Returns md5 of the file node. | |
372 | """ |
|
376 | """ | |
373 | return md5(self.raw_bytes) |
|
377 | return md5(self.raw_bytes) | |
374 |
|
378 | |||
375 | def metadata_uncached(self): |
|
379 | def metadata_uncached(self): | |
376 | """ |
|
380 | """ | |
377 | Returns md5, binary flag of the file node, without any cache usage. |
|
381 | Returns md5, binary flag of the file node, without any cache usage. | |
378 | """ |
|
382 | """ | |
379 |
|
383 | |||
380 | if self.commit: |
|
384 | if self.commit: | |
381 | content = self.commit.get_file_content(self.path) |
|
385 | content = self.commit.get_file_content(self.path) | |
382 | else: |
|
386 | else: | |
383 | content = self._content |
|
387 | content = self._content | |
384 |
|
388 | |||
385 | is_binary = content and '\0' in content |
|
389 | is_binary = content and '\0' in content | |
386 | size = 0 |
|
390 | size = 0 | |
387 | if content: |
|
391 | if content: | |
388 | size = len(content) |
|
392 | size = len(content) | |
389 | return is_binary, md5(content), size |
|
393 | return is_binary, md5(content), size | |
390 |
|
394 | |||
391 | @LazyProperty |
|
395 | @LazyProperty | |
392 | def content(self): |
|
396 | def content(self): | |
393 | """ |
|
397 | """ | |
394 | Returns lazily content of the FileNode. If possible, would try to |
|
398 | Returns lazily content of the FileNode. If possible, would try to | |
395 | decode content from UTF-8. |
|
399 | decode content from UTF-8. | |
396 | """ |
|
400 | """ | |
397 | content = self.raw_bytes |
|
401 | content = self.raw_bytes | |
398 |
|
402 | |||
399 | if self.is_binary: |
|
403 | if self.is_binary: | |
400 | return content |
|
404 | return content | |
401 | return safe_unicode(content) |
|
405 | return safe_unicode(content) | |
402 |
|
406 | |||
403 | @LazyProperty |
|
407 | @LazyProperty | |
404 | def size(self): |
|
408 | def size(self): | |
405 | if self.commit: |
|
409 | if self.commit: | |
406 | return self.commit.get_file_size(self.path) |
|
410 | return self.commit.get_file_size(self.path) | |
407 | raise NodeError( |
|
411 | raise NodeError( | |
408 | "Cannot retrieve size of the file without related " |
|
412 | "Cannot retrieve size of the file without related " | |
409 | "commit attribute") |
|
413 | "commit attribute") | |
410 |
|
414 | |||
411 | @LazyProperty |
|
415 | @LazyProperty | |
412 | def message(self): |
|
416 | def message(self): | |
413 | if self.commit: |
|
417 | if self.commit: | |
414 | return self.last_commit.message |
|
418 | return self.last_commit.message | |
415 | raise NodeError( |
|
419 | raise NodeError( | |
416 | "Cannot retrieve message of the file without related " |
|
420 | "Cannot retrieve message of the file without related " | |
417 | "commit attribute") |
|
421 | "commit attribute") | |
418 |
|
422 | |||
419 | @LazyProperty |
|
423 | @LazyProperty | |
420 | def last_commit(self): |
|
424 | def last_commit(self): | |
421 | if self.commit: |
|
425 | if self.commit: | |
422 | pre_load = ["author", "date", "message"] |
|
426 | pre_load = ["author", "date", "message"] | |
423 | return self.commit.get_path_commit(self.path, pre_load=pre_load) |
|
427 | return self.commit.get_path_commit(self.path, pre_load=pre_load) | |
424 | raise NodeError( |
|
428 | raise NodeError( | |
425 | "Cannot retrieve last commit of the file without " |
|
429 | "Cannot retrieve last commit of the file without " | |
426 | "related commit attribute") |
|
430 | "related commit attribute") | |
427 |
|
431 | |||
428 | def get_mimetype(self): |
|
432 | def get_mimetype(self): | |
429 | """ |
|
433 | """ | |
430 | Mimetype is calculated based on the file's content. If ``_mimetype`` |
|
434 | Mimetype is calculated based on the file's content. If ``_mimetype`` | |
431 | attribute is available, it will be returned (backends which store |
|
435 | attribute is available, it will be returned (backends which store | |
432 | mimetypes or can easily recognize them, should set this private |
|
436 | mimetypes or can easily recognize them, should set this private | |
433 | attribute to indicate that type should *NOT* be calculated). |
|
437 | attribute to indicate that type should *NOT* be calculated). | |
434 | """ |
|
438 | """ | |
435 |
|
439 | |||
436 | if hasattr(self, '_mimetype'): |
|
440 | if hasattr(self, '_mimetype'): | |
437 | if (isinstance(self._mimetype, (tuple, list,)) and |
|
441 | if (isinstance(self._mimetype, (tuple, list,)) and | |
438 | len(self._mimetype) == 2): |
|
442 | len(self._mimetype) == 2): | |
439 | return self._mimetype |
|
443 | return self._mimetype | |
440 | else: |
|
444 | else: | |
441 | raise NodeError('given _mimetype attribute must be an 2 ' |
|
445 | raise NodeError('given _mimetype attribute must be an 2 ' | |
442 | 'element list or tuple') |
|
446 | 'element list or tuple') | |
443 |
|
447 | |||
444 | db = get_mimetypes_db() |
|
448 | db = get_mimetypes_db() | |
445 | mtype, encoding = db.guess_type(self.name) |
|
449 | mtype, encoding = db.guess_type(self.name) | |
446 |
|
450 | |||
447 | if mtype is None: |
|
451 | if mtype is None: | |
448 | if self.is_binary: |
|
452 | if self.is_binary: | |
449 | mtype = 'application/octet-stream' |
|
453 | mtype = 'application/octet-stream' | |
450 | encoding = None |
|
454 | encoding = None | |
451 | else: |
|
455 | else: | |
452 | mtype = 'text/plain' |
|
456 | mtype = 'text/plain' | |
453 | encoding = None |
|
457 | encoding = None | |
454 |
|
458 | |||
455 | # try with pygments |
|
459 | # try with pygments | |
456 | try: |
|
460 | try: | |
457 | from pygments.lexers import get_lexer_for_filename |
|
461 | from pygments.lexers import get_lexer_for_filename | |
458 | mt = get_lexer_for_filename(self.name).mimetypes |
|
462 | mt = get_lexer_for_filename(self.name).mimetypes | |
459 | except Exception: |
|
463 | except Exception: | |
460 | mt = None |
|
464 | mt = None | |
461 |
|
465 | |||
462 | if mt: |
|
466 | if mt: | |
463 | mtype = mt[0] |
|
467 | mtype = mt[0] | |
464 |
|
468 | |||
465 | return mtype, encoding |
|
469 | return mtype, encoding | |
466 |
|
470 | |||
467 | @LazyProperty |
|
471 | @LazyProperty | |
468 | def mimetype(self): |
|
472 | def mimetype(self): | |
469 | """ |
|
473 | """ | |
470 | Wrapper around full mimetype info. It returns only type of fetched |
|
474 | Wrapper around full mimetype info. It returns only type of fetched | |
471 | mimetype without the encoding part. use get_mimetype function to fetch |
|
475 | mimetype without the encoding part. use get_mimetype function to fetch | |
472 | full set of (type,encoding) |
|
476 | full set of (type,encoding) | |
473 | """ |
|
477 | """ | |
474 | return self.get_mimetype()[0] |
|
478 | return self.get_mimetype()[0] | |
475 |
|
479 | |||
476 | @LazyProperty |
|
480 | @LazyProperty | |
477 | def mimetype_main(self): |
|
481 | def mimetype_main(self): | |
478 | return self.mimetype.split('/')[0] |
|
482 | return self.mimetype.split('/')[0] | |
479 |
|
483 | |||
480 | @classmethod |
|
484 | @classmethod | |
481 | def get_lexer(cls, filename, content=None): |
|
485 | def get_lexer(cls, filename, content=None): | |
482 | from pygments import lexers |
|
486 | from pygments import lexers | |
483 |
|
487 | |||
484 | extension = filename.split('.')[-1] |
|
488 | extension = filename.split('.')[-1] | |
485 | lexer = None |
|
489 | lexer = None | |
486 |
|
490 | |||
487 | try: |
|
491 | try: | |
488 | lexer = lexers.guess_lexer_for_filename( |
|
492 | lexer = lexers.guess_lexer_for_filename( | |
489 | filename, content, stripnl=False) |
|
493 | filename, content, stripnl=False) | |
490 | except lexers.ClassNotFound: |
|
494 | except lexers.ClassNotFound: | |
491 | lexer = None |
|
495 | lexer = None | |
492 |
|
496 | |||
493 | # try our EXTENSION_MAP |
|
497 | # try our EXTENSION_MAP | |
494 | if not lexer: |
|
498 | if not lexer: | |
495 | try: |
|
499 | try: | |
496 | lexer_class = LANGUAGES_EXTENSIONS_MAP.get(extension) |
|
500 | lexer_class = LANGUAGES_EXTENSIONS_MAP.get(extension) | |
497 | if lexer_class: |
|
501 | if lexer_class: | |
498 | lexer = lexers.get_lexer_by_name(lexer_class[0]) |
|
502 | lexer = lexers.get_lexer_by_name(lexer_class[0]) | |
499 | except lexers.ClassNotFound: |
|
503 | except lexers.ClassNotFound: | |
500 | lexer = None |
|
504 | lexer = None | |
501 |
|
505 | |||
502 | if not lexer: |
|
506 | if not lexer: | |
503 | lexer = lexers.TextLexer(stripnl=False) |
|
507 | lexer = lexers.TextLexer(stripnl=False) | |
504 |
|
508 | |||
505 | return lexer |
|
509 | return lexer | |
506 |
|
510 | |||
507 | @LazyProperty |
|
511 | @LazyProperty | |
508 | def lexer(self): |
|
512 | def lexer(self): | |
509 | """ |
|
513 | """ | |
510 | Returns pygment's lexer class. Would try to guess lexer taking file's |
|
514 | Returns pygment's lexer class. Would try to guess lexer taking file's | |
511 | content, name and mimetype. |
|
515 | content, name and mimetype. | |
512 | """ |
|
516 | """ | |
513 | return self.get_lexer(self.name, self.content) |
|
517 | return self.get_lexer(self.name, self.content) | |
514 |
|
518 | |||
515 | @LazyProperty |
|
519 | @LazyProperty | |
516 | def lexer_alias(self): |
|
520 | def lexer_alias(self): | |
517 | """ |
|
521 | """ | |
518 | Returns first alias of the lexer guessed for this file. |
|
522 | Returns first alias of the lexer guessed for this file. | |
519 | """ |
|
523 | """ | |
520 | return self.lexer.aliases[0] |
|
524 | return self.lexer.aliases[0] | |
521 |
|
525 | |||
522 | @LazyProperty |
|
526 | @LazyProperty | |
523 | def history(self): |
|
527 | def history(self): | |
524 | """ |
|
528 | """ | |
525 | Returns a list of commit for this file in which the file was changed |
|
529 | Returns a list of commit for this file in which the file was changed | |
526 | """ |
|
530 | """ | |
527 | if self.commit is None: |
|
531 | if self.commit is None: | |
528 | raise NodeError('Unable to get commit for this FileNode') |
|
532 | raise NodeError('Unable to get commit for this FileNode') | |
529 | return self.commit.get_path_history(self.path) |
|
533 | return self.commit.get_path_history(self.path) | |
530 |
|
534 | |||
531 | @LazyProperty |
|
535 | @LazyProperty | |
532 | def annotate(self): |
|
536 | def annotate(self): | |
533 | """ |
|
537 | """ | |
534 | Returns a list of three element tuples with lineno, commit and line |
|
538 | Returns a list of three element tuples with lineno, commit and line | |
535 | """ |
|
539 | """ | |
536 | if self.commit is None: |
|
540 | if self.commit is None: | |
537 | raise NodeError('Unable to get commit for this FileNode') |
|
541 | raise NodeError('Unable to get commit for this FileNode') | |
538 | pre_load = ["author", "date", "message"] |
|
542 | pre_load = ["author", "date", "message"] | |
539 | return self.commit.get_file_annotate(self.path, pre_load=pre_load) |
|
543 | return self.commit.get_file_annotate(self.path, pre_load=pre_load) | |
540 |
|
544 | |||
541 | @LazyProperty |
|
545 | @LazyProperty | |
542 | def state(self): |
|
546 | def state(self): | |
543 | if not self.commit: |
|
547 | if not self.commit: | |
544 | raise NodeError( |
|
548 | raise NodeError( | |
545 | "Cannot check state of the node if it's not " |
|
549 | "Cannot check state of the node if it's not " | |
546 | "linked with commit") |
|
550 | "linked with commit") | |
547 | elif self.path in (node.path for node in self.commit.added): |
|
551 | elif self.path in (node.path for node in self.commit.added): | |
548 | return NodeState.ADDED |
|
552 | return NodeState.ADDED | |
549 | elif self.path in (node.path for node in self.commit.changed): |
|
553 | elif self.path in (node.path for node in self.commit.changed): | |
550 | return NodeState.CHANGED |
|
554 | return NodeState.CHANGED | |
551 | else: |
|
555 | else: | |
552 | return NodeState.NOT_CHANGED |
|
556 | return NodeState.NOT_CHANGED | |
553 |
|
557 | |||
554 | @LazyProperty |
|
558 | @LazyProperty | |
555 | def is_binary(self): |
|
559 | def is_binary(self): | |
556 | """ |
|
560 | """ | |
557 | Returns True if file has binary content. |
|
561 | Returns True if file has binary content. | |
558 | """ |
|
562 | """ | |
559 | _bin = self.raw_bytes and '\0' in self.raw_bytes |
|
563 | _bin = self.raw_bytes and '\0' in self.raw_bytes | |
560 | return _bin |
|
564 | return _bin | |
561 |
|
565 | |||
562 | @LazyProperty |
|
566 | @LazyProperty | |
563 | def extension(self): |
|
567 | def extension(self): | |
564 | """Returns filenode extension""" |
|
568 | """Returns filenode extension""" | |
565 | return self.name.split('.')[-1] |
|
569 | return self.name.split('.')[-1] | |
566 |
|
570 | |||
567 | @property |
|
571 | @property | |
568 | def is_executable(self): |
|
572 | def is_executable(self): | |
569 | """ |
|
573 | """ | |
570 | Returns ``True`` if file has executable flag turned on. |
|
574 | Returns ``True`` if file has executable flag turned on. | |
571 | """ |
|
575 | """ | |
572 | return bool(self.mode & stat.S_IXUSR) |
|
576 | return bool(self.mode & stat.S_IXUSR) | |
573 |
|
577 | |||
574 | def get_largefile_node(self): |
|
578 | def get_largefile_node(self): | |
575 | """ |
|
579 | """ | |
576 | Try to return a Mercurial FileNode from this node. It does internal |
|
580 | Try to return a Mercurial FileNode from this node. It does internal | |
577 | checks inside largefile store, if that file exist there it will |
|
581 | checks inside largefile store, if that file exist there it will | |
578 | create special instance of LargeFileNode which can get content from |
|
582 | create special instance of LargeFileNode which can get content from | |
579 | LF store. |
|
583 | LF store. | |
580 | """ |
|
584 | """ | |
581 | if self.commit: |
|
585 | if self.commit: | |
582 | return self.commit.get_largefile_node(self.path) |
|
586 | return self.commit.get_largefile_node(self.path) | |
583 |
|
587 | |||
584 | def lines(self, count_empty=False): |
|
588 | def lines(self, count_empty=False): | |
585 | all_lines, empty_lines = 0, 0 |
|
589 | all_lines, empty_lines = 0, 0 | |
586 |
|
590 | |||
587 | if not self.is_binary: |
|
591 | if not self.is_binary: | |
588 | content = self.content |
|
592 | content = self.content | |
589 | if count_empty: |
|
593 | if count_empty: | |
590 | all_lines = 0 |
|
594 | all_lines = 0 | |
591 | empty_lines = 0 |
|
595 | empty_lines = 0 | |
592 | for line in content.splitlines(True): |
|
596 | for line in content.splitlines(True): | |
593 | if line == '\n': |
|
597 | if line == '\n': | |
594 | empty_lines += 1 |
|
598 | empty_lines += 1 | |
595 | all_lines += 1 |
|
599 | all_lines += 1 | |
596 |
|
600 | |||
597 | return all_lines, all_lines - empty_lines |
|
601 | return all_lines, all_lines - empty_lines | |
598 | else: |
|
602 | else: | |
599 | # fast method |
|
603 | # fast method | |
600 | empty_lines = all_lines = content.count('\n') |
|
604 | empty_lines = all_lines = content.count('\n') | |
601 | if all_lines == 0 and content: |
|
605 | if all_lines == 0 and content: | |
602 | # one-line without a newline |
|
606 | # one-line without a newline | |
603 | empty_lines = all_lines = 1 |
|
607 | empty_lines = all_lines = 1 | |
604 |
|
608 | |||
605 | return all_lines, empty_lines |
|
609 | return all_lines, empty_lines | |
606 |
|
610 | |||
607 | def __repr__(self): |
|
611 | def __repr__(self): | |
608 | return '<%s %r @ %s>' % (self.__class__.__name__, self.path, |
|
612 | return '<%s %r @ %s>' % (self.__class__.__name__, self.path, | |
609 | getattr(self.commit, 'short_id', '')) |
|
613 | getattr(self.commit, 'short_id', '')) | |
610 |
|
614 | |||
611 |
|
615 | |||
612 | class RemovedFileNode(FileNode): |
|
616 | class RemovedFileNode(FileNode): | |
613 | """ |
|
617 | """ | |
614 | Dummy FileNode class - trying to access any public attribute except path, |
|
618 | Dummy FileNode class - trying to access any public attribute except path, | |
615 | name, kind or state (or methods/attributes checking those two) would raise |
|
619 | name, kind or state (or methods/attributes checking those two) would raise | |
616 | RemovedFileNodeError. |
|
620 | RemovedFileNodeError. | |
617 | """ |
|
621 | """ | |
618 | ALLOWED_ATTRIBUTES = [ |
|
622 | ALLOWED_ATTRIBUTES = [ | |
619 | 'name', 'path', 'state', 'is_root', 'is_file', 'is_dir', 'kind', |
|
623 | 'name', 'path', 'state', 'is_root', 'is_file', 'is_dir', 'kind', | |
620 | 'added', 'changed', 'not_changed', 'removed' |
|
624 | 'added', 'changed', 'not_changed', 'removed' | |
621 | ] |
|
625 | ] | |
622 |
|
626 | |||
623 | def __init__(self, path): |
|
627 | def __init__(self, path): | |
624 | """ |
|
628 | """ | |
625 | :param path: relative path to the node |
|
629 | :param path: relative path to the node | |
626 | """ |
|
630 | """ | |
627 | super(RemovedFileNode, self).__init__(path=path) |
|
631 | super(RemovedFileNode, self).__init__(path=path) | |
628 |
|
632 | |||
629 | def __getattribute__(self, attr): |
|
633 | def __getattribute__(self, attr): | |
630 | if attr.startswith('_') or attr in RemovedFileNode.ALLOWED_ATTRIBUTES: |
|
634 | if attr.startswith('_') or attr in RemovedFileNode.ALLOWED_ATTRIBUTES: | |
631 | return super(RemovedFileNode, self).__getattribute__(attr) |
|
635 | return super(RemovedFileNode, self).__getattribute__(attr) | |
632 | raise RemovedFileNodeError( |
|
636 | raise RemovedFileNodeError( | |
633 | "Cannot access attribute %s on RemovedFileNode" % attr) |
|
637 | "Cannot access attribute %s on RemovedFileNode" % attr) | |
634 |
|
638 | |||
635 | @LazyProperty |
|
639 | @LazyProperty | |
636 | def state(self): |
|
640 | def state(self): | |
637 | return NodeState.REMOVED |
|
641 | return NodeState.REMOVED | |
638 |
|
642 | |||
639 |
|
643 | |||
640 | class DirNode(Node): |
|
644 | class DirNode(Node): | |
641 | """ |
|
645 | """ | |
642 | DirNode stores list of files and directories within this node. |
|
646 | DirNode stores list of files and directories within this node. | |
643 | Nodes may be used standalone but within repository context they |
|
647 | Nodes may be used standalone but within repository context they | |
644 | lazily fetch data within same repositorty's commit. |
|
648 | lazily fetch data within same repositorty's commit. | |
645 | """ |
|
649 | """ | |
646 |
|
650 | |||
647 | def __init__(self, path, nodes=(), commit=None): |
|
651 | def __init__(self, path, nodes=(), commit=None): | |
648 | """ |
|
652 | """ | |
649 | Only one of ``nodes`` and ``commit`` may be given. Passing both |
|
653 | Only one of ``nodes`` and ``commit`` may be given. Passing both | |
650 | would raise ``NodeError`` exception. |
|
654 | would raise ``NodeError`` exception. | |
651 |
|
655 | |||
652 | :param path: relative path to the node |
|
656 | :param path: relative path to the node | |
653 | :param nodes: content may be passed to constructor |
|
657 | :param nodes: content may be passed to constructor | |
654 | :param commit: if given, will use it to lazily fetch content |
|
658 | :param commit: if given, will use it to lazily fetch content | |
655 | """ |
|
659 | """ | |
656 | if nodes and commit: |
|
660 | if nodes and commit: | |
657 | raise NodeError("Cannot use both nodes and commit") |
|
661 | raise NodeError("Cannot use both nodes and commit") | |
658 | super(DirNode, self).__init__(path, NodeKind.DIR) |
|
662 | super(DirNode, self).__init__(path, NodeKind.DIR) | |
659 | self.commit = commit |
|
663 | self.commit = commit | |
660 | self._nodes = nodes |
|
664 | self._nodes = nodes | |
661 |
|
665 | |||
662 | @LazyProperty |
|
666 | @LazyProperty | |
663 | def content(self): |
|
667 | def content(self): | |
664 | raise NodeError( |
|
668 | raise NodeError( | |
665 | "%s represents a dir and has no `content` attribute" % self) |
|
669 | "%s represents a dir and has no `content` attribute" % self) | |
666 |
|
670 | |||
667 | @LazyProperty |
|
671 | @LazyProperty | |
668 | def nodes(self): |
|
672 | def nodes(self): | |
669 | if self.commit: |
|
673 | if self.commit: | |
670 | nodes = self.commit.get_nodes(self.path) |
|
674 | nodes = self.commit.get_nodes(self.path) | |
671 | else: |
|
675 | else: | |
672 | nodes = self._nodes |
|
676 | nodes = self._nodes | |
673 | self._nodes_dict = dict((node.path, node) for node in nodes) |
|
677 | self._nodes_dict = dict((node.path, node) for node in nodes) | |
674 | return sorted(nodes) |
|
678 | return sorted(nodes) | |
675 |
|
679 | |||
676 | @LazyProperty |
|
680 | @LazyProperty | |
677 | def files(self): |
|
681 | def files(self): | |
678 | return sorted((node for node in self.nodes if node.is_file())) |
|
682 | return sorted((node for node in self.nodes if node.is_file())) | |
679 |
|
683 | |||
680 | @LazyProperty |
|
684 | @LazyProperty | |
681 | def dirs(self): |
|
685 | def dirs(self): | |
682 | return sorted((node for node in self.nodes if node.is_dir())) |
|
686 | return sorted((node for node in self.nodes if node.is_dir())) | |
683 |
|
687 | |||
684 | def __iter__(self): |
|
688 | def __iter__(self): | |
685 | for node in self.nodes: |
|
689 | for node in self.nodes: | |
686 | yield node |
|
690 | yield node | |
687 |
|
691 | |||
688 | def get_node(self, path): |
|
692 | def get_node(self, path): | |
689 | """ |
|
693 | """ | |
690 | Returns node from within this particular ``DirNode``, so it is now |
|
694 | Returns node from within this particular ``DirNode``, so it is now | |
691 | allowed to fetch, i.e. node located at 'docs/api/index.rst' from node |
|
695 | allowed to fetch, i.e. node located at 'docs/api/index.rst' from node | |
692 | 'docs'. In order to access deeper nodes one must fetch nodes between |
|
696 | 'docs'. In order to access deeper nodes one must fetch nodes between | |
693 | them first - this would work:: |
|
697 | them first - this would work:: | |
694 |
|
698 | |||
695 | docs = root.get_node('docs') |
|
699 | docs = root.get_node('docs') | |
696 | docs.get_node('api').get_node('index.rst') |
|
700 | docs.get_node('api').get_node('index.rst') | |
697 |
|
701 | |||
698 | :param: path - relative to the current node |
|
702 | :param: path - relative to the current node | |
699 |
|
703 | |||
700 | .. note:: |
|
704 | .. note:: | |
701 | To access lazily (as in example above) node have to be initialized |
|
705 | To access lazily (as in example above) node have to be initialized | |
702 | with related commit object - without it node is out of |
|
706 | with related commit object - without it node is out of | |
703 | context and may know nothing about anything else than nearest |
|
707 | context and may know nothing about anything else than nearest | |
704 | (located at same level) nodes. |
|
708 | (located at same level) nodes. | |
705 | """ |
|
709 | """ | |
706 | try: |
|
710 | try: | |
707 | path = path.rstrip('/') |
|
711 | path = path.rstrip('/') | |
708 | if path == '': |
|
712 | if path == '': | |
709 | raise NodeError("Cannot retrieve node without path") |
|
713 | raise NodeError("Cannot retrieve node without path") | |
710 | self.nodes # access nodes first in order to set _nodes_dict |
|
714 | self.nodes # access nodes first in order to set _nodes_dict | |
711 | paths = path.split('/') |
|
715 | paths = path.split('/') | |
712 | if len(paths) == 1: |
|
716 | if len(paths) == 1: | |
713 | if not self.is_root(): |
|
717 | if not self.is_root(): | |
714 | path = '/'.join((self.path, paths[0])) |
|
718 | path = '/'.join((self.path, paths[0])) | |
715 | else: |
|
719 | else: | |
716 | path = paths[0] |
|
720 | path = paths[0] | |
717 | return self._nodes_dict[path] |
|
721 | return self._nodes_dict[path] | |
718 | elif len(paths) > 1: |
|
722 | elif len(paths) > 1: | |
719 | if self.commit is None: |
|
723 | if self.commit is None: | |
720 | raise NodeError( |
|
724 | raise NodeError( | |
721 | "Cannot access deeper nodes without commit") |
|
725 | "Cannot access deeper nodes without commit") | |
722 | else: |
|
726 | else: | |
723 | path1, path2 = paths[0], '/'.join(paths[1:]) |
|
727 | path1, path2 = paths[0], '/'.join(paths[1:]) | |
724 | return self.get_node(path1).get_node(path2) |
|
728 | return self.get_node(path1).get_node(path2) | |
725 | else: |
|
729 | else: | |
726 | raise KeyError |
|
730 | raise KeyError | |
727 | except KeyError: |
|
731 | except KeyError: | |
728 | raise NodeError("Node does not exist at %s" % path) |
|
732 | raise NodeError("Node does not exist at %s" % path) | |
729 |
|
733 | |||
730 | @LazyProperty |
|
734 | @LazyProperty | |
731 | def state(self): |
|
735 | def state(self): | |
732 | raise NodeError("Cannot access state of DirNode") |
|
736 | raise NodeError("Cannot access state of DirNode") | |
733 |
|
737 | |||
734 | @LazyProperty |
|
738 | @LazyProperty | |
735 | def size(self): |
|
739 | def size(self): | |
736 | size = 0 |
|
740 | size = 0 | |
737 | for root, dirs, files in self.commit.walk(self.path): |
|
741 | for root, dirs, files in self.commit.walk(self.path): | |
738 | for f in files: |
|
742 | for f in files: | |
739 | size += f.size |
|
743 | size += f.size | |
740 |
|
744 | |||
741 | return size |
|
745 | return size | |
742 |
|
746 | |||
743 | @LazyProperty |
|
747 | @LazyProperty | |
744 | def last_commit(self): |
|
748 | def last_commit(self): | |
745 | if self.commit: |
|
749 | if self.commit: | |
746 | pre_load = ["author", "date", "message"] |
|
750 | pre_load = ["author", "date", "message"] | |
747 | return self.commit.get_path_commit(self.path, pre_load=pre_load) |
|
751 | return self.commit.get_path_commit(self.path, pre_load=pre_load) | |
748 | raise NodeError( |
|
752 | raise NodeError( | |
749 | "Cannot retrieve last commit of the file without " |
|
753 | "Cannot retrieve last commit of the file without " | |
750 | "related commit attribute") |
|
754 | "related commit attribute") | |
751 |
|
755 | |||
752 | def __repr__(self): |
|
756 | def __repr__(self): | |
753 | return '<%s %r @ %s>' % (self.__class__.__name__, self.path, |
|
757 | return '<%s %r @ %s>' % (self.__class__.__name__, self.path, | |
754 | getattr(self.commit, 'short_id', '')) |
|
758 | getattr(self.commit, 'short_id', '')) | |
755 |
|
759 | |||
756 |
|
760 | |||
757 | class RootNode(DirNode): |
|
761 | class RootNode(DirNode): | |
758 | """ |
|
762 | """ | |
759 | DirNode being the root node of the repository. |
|
763 | DirNode being the root node of the repository. | |
760 | """ |
|
764 | """ | |
761 |
|
765 | |||
762 | def __init__(self, nodes=(), commit=None): |
|
766 | def __init__(self, nodes=(), commit=None): | |
763 | super(RootNode, self).__init__(path='', nodes=nodes, commit=commit) |
|
767 | super(RootNode, self).__init__(path='', nodes=nodes, commit=commit) | |
764 |
|
768 | |||
765 | def __repr__(self): |
|
769 | def __repr__(self): | |
766 | return '<%s>' % self.__class__.__name__ |
|
770 | return '<%s>' % self.__class__.__name__ | |
767 |
|
771 | |||
768 |
|
772 | |||
769 | class SubModuleNode(Node): |
|
773 | class SubModuleNode(Node): | |
770 | """ |
|
774 | """ | |
771 | represents a SubModule of Git or SubRepo of Mercurial |
|
775 | represents a SubModule of Git or SubRepo of Mercurial | |
772 | """ |
|
776 | """ | |
773 | is_binary = False |
|
777 | is_binary = False | |
774 | size = 0 |
|
778 | size = 0 | |
775 |
|
779 | |||
776 | def __init__(self, name, url=None, commit=None, alias=None): |
|
780 | def __init__(self, name, url=None, commit=None, alias=None): | |
777 | self.path = name |
|
781 | self.path = name | |
778 | self.kind = NodeKind.SUBMODULE |
|
782 | self.kind = NodeKind.SUBMODULE | |
779 | self.alias = alias |
|
783 | self.alias = alias | |
780 |
|
784 | |||
781 | # we have to use EmptyCommit here since this can point to svn/git/hg |
|
785 | # we have to use EmptyCommit here since this can point to svn/git/hg | |
782 | # submodules we cannot get from repository |
|
786 | # submodules we cannot get from repository | |
783 | self.commit = EmptyCommit(str(commit), alias=alias) |
|
787 | self.commit = EmptyCommit(str(commit), alias=alias) | |
784 | self.url = url or self._extract_submodule_url() |
|
788 | self.url = url or self._extract_submodule_url() | |
785 |
|
789 | |||
786 | def __repr__(self): |
|
790 | def __repr__(self): | |
787 | return '<%s %r @ %s>' % (self.__class__.__name__, self.path, |
|
791 | return '<%s %r @ %s>' % (self.__class__.__name__, self.path, | |
788 | getattr(self.commit, 'short_id', '')) |
|
792 | getattr(self.commit, 'short_id', '')) | |
789 |
|
793 | |||
790 | def _extract_submodule_url(self): |
|
794 | def _extract_submodule_url(self): | |
791 | # TODO: find a way to parse gits submodule file and extract the |
|
795 | # TODO: find a way to parse gits submodule file and extract the | |
792 | # linking URL |
|
796 | # linking URL | |
793 | return self.path |
|
797 | return self.path | |
794 |
|
798 | |||
795 | @LazyProperty |
|
799 | @LazyProperty | |
796 | def name(self): |
|
800 | def name(self): | |
797 | """ |
|
801 | """ | |
798 | Returns name of the node so if its path |
|
802 | Returns name of the node so if its path | |
799 | then only last part is returned. |
|
803 | then only last part is returned. | |
800 | """ |
|
804 | """ | |
801 | org = safe_unicode(self.path.rstrip('/').split('/')[-1]) |
|
805 | org = safe_unicode(self.path.rstrip('/').split('/')[-1]) | |
802 | return u'%s @ %s' % (org, self.commit.short_id) |
|
806 | return u'%s @ %s' % (org, self.commit.short_id) | |
803 |
|
807 | |||
804 |
|
808 | |||
805 | class LargeFileNode(FileNode): |
|
809 | class LargeFileNode(FileNode): | |
806 |
|
810 | |||
807 | def __init__(self, path, url=None, commit=None, alias=None, org_path=None): |
|
811 | def __init__(self, path, url=None, commit=None, alias=None, org_path=None): | |
808 | self.path = path |
|
812 | self.path = path | |
809 | self.org_path = org_path |
|
813 | self.org_path = org_path | |
810 | self.kind = NodeKind.LARGEFILE |
|
814 | self.kind = NodeKind.LARGEFILE | |
811 | self.alias = alias |
|
815 | self.alias = alias | |
812 |
|
816 | |||
813 | def _validate_path(self, path): |
|
817 | def _validate_path(self, path): | |
814 | """ |
|
818 | """ | |
815 | we override check since the LargeFileNode path is system absolute |
|
819 | we override check since the LargeFileNode path is system absolute | |
816 | """ |
|
820 | """ | |
817 | pass |
|
821 | pass | |
818 |
|
822 | |||
819 | def __repr__(self): |
|
823 | def __repr__(self): | |
820 | return '<%s %r>' % (self.__class__.__name__, self.path) |
|
824 | return '<%s %r>' % (self.__class__.__name__, self.path) | |
821 |
|
825 | |||
822 | @LazyProperty |
|
826 | @LazyProperty | |
823 | def size(self): |
|
827 | def size(self): | |
824 | return os.stat(self.path).st_size |
|
828 | return os.stat(self.path).st_size | |
825 |
|
829 | |||
826 | @LazyProperty |
|
830 | @LazyProperty | |
827 | def raw_bytes(self): |
|
831 | def raw_bytes(self): | |
828 | with open(self.path, 'rb') as f: |
|
832 | with open(self.path, 'rb') as f: | |
829 | content = f.read() |
|
833 | content = f.read() | |
830 | return content |
|
834 | return content | |
831 |
|
835 | |||
832 | @LazyProperty |
|
836 | @LazyProperty | |
833 | def name(self): |
|
837 | def name(self): | |
834 | """ |
|
838 | """ | |
835 | Overwrites name to be the org lf path |
|
839 | Overwrites name to be the org lf path | |
836 | """ |
|
840 | """ | |
837 | return self.org_path |
|
841 | return self.org_path |
General Comments 0
You need to be logged in to leave comments.
Login now