Show More
@@ -1,768 +1,770 b'' | |||||
1 | # -*- coding: utf-8 -*- |
|
1 | # -*- coding: utf-8 -*- | |
2 | """ |
|
2 | """ | |
3 | rhodecode.lib.diffs |
|
3 | rhodecode.lib.diffs | |
4 | ~~~~~~~~~~~~~~~~~~~ |
|
4 | ~~~~~~~~~~~~~~~~~~~ | |
5 |
|
5 | |||
6 | Set of diffing helpers, previously part of vcs |
|
6 | Set of diffing helpers, previously part of vcs | |
7 |
|
7 | |||
8 |
|
8 | |||
9 | :created_on: Dec 4, 2011 |
|
9 | :created_on: Dec 4, 2011 | |
10 | :author: marcink |
|
10 | :author: marcink | |
11 | :copyright: (C) 2010-2012 Marcin Kuzminski <marcin@python-works.com> |
|
11 | :copyright: (C) 2010-2012 Marcin Kuzminski <marcin@python-works.com> | |
12 | :original copyright: 2007-2008 by Armin Ronacher |
|
12 | :original copyright: 2007-2008 by Armin Ronacher | |
13 | :license: GPLv3, see COPYING for more details. |
|
13 | :license: GPLv3, see COPYING for more details. | |
14 | """ |
|
14 | """ | |
15 | # This program is free software: you can redistribute it and/or modify |
|
15 | # This program is free software: you can redistribute it and/or modify | |
16 | # it under the terms of the GNU General Public License as published by |
|
16 | # it under the terms of the GNU General Public License as published by | |
17 | # the Free Software Foundation, either version 3 of the License, or |
|
17 | # the Free Software Foundation, either version 3 of the License, or | |
18 | # (at your option) any later version. |
|
18 | # (at your option) any later version. | |
19 | # |
|
19 | # | |
20 | # This program is distributed in the hope that it will be useful, |
|
20 | # This program is distributed in the hope that it will be useful, | |
21 | # but WITHOUT ANY WARRANTY; without even the implied warranty of |
|
21 | # but WITHOUT ANY WARRANTY; without even the implied warranty of | |
22 | # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the |
|
22 | # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the | |
23 | # GNU General Public License for more details. |
|
23 | # GNU General Public License for more details. | |
24 | # |
|
24 | # | |
25 | # You should have received a copy of the GNU General Public License |
|
25 | # You should have received a copy of the GNU General Public License | |
26 | # along with this program. If not, see <http://www.gnu.org/licenses/>. |
|
26 | # along with this program. If not, see <http://www.gnu.org/licenses/>. | |
27 |
|
27 | |||
28 | import re |
|
28 | import re | |
29 | import difflib |
|
29 | import difflib | |
30 | import logging |
|
30 | import logging | |
31 | import traceback |
|
31 | import traceback | |
32 |
|
32 | |||
33 | from itertools import tee, imap |
|
33 | from itertools import tee, imap | |
34 |
|
34 | |||
35 | from mercurial import patch |
|
35 | from mercurial import patch | |
36 | from mercurial.mdiff import diffopts |
|
36 | from mercurial.mdiff import diffopts | |
37 | from mercurial.bundlerepo import bundlerepository |
|
37 | from mercurial.bundlerepo import bundlerepository | |
38 |
|
38 | |||
39 | from pylons.i18n.translation import _ |
|
39 | from pylons.i18n.translation import _ | |
40 |
|
40 | |||
41 | from rhodecode.lib.compat import BytesIO |
|
41 | from rhodecode.lib.compat import BytesIO | |
42 | from rhodecode.lib.vcs.utils.hgcompat import localrepo |
|
42 | from rhodecode.lib.vcs.utils.hgcompat import localrepo | |
43 | from rhodecode.lib.vcs.exceptions import VCSError |
|
43 | from rhodecode.lib.vcs.exceptions import VCSError | |
44 | from rhodecode.lib.vcs.nodes import FileNode, SubModuleNode |
|
44 | from rhodecode.lib.vcs.nodes import FileNode, SubModuleNode | |
45 | from rhodecode.lib.vcs.backends.base import EmptyChangeset |
|
45 | from rhodecode.lib.vcs.backends.base import EmptyChangeset | |
46 | from rhodecode.lib.helpers import escape |
|
46 | from rhodecode.lib.helpers import escape | |
47 | from rhodecode.lib.utils import make_ui |
|
47 | from rhodecode.lib.utils import make_ui | |
48 | from rhodecode.lib.utils2 import safe_unicode |
|
48 | from rhodecode.lib.utils2 import safe_unicode | |
49 |
|
49 | |||
50 | log = logging.getLogger(__name__) |
|
50 | log = logging.getLogger(__name__) | |
51 |
|
51 | |||
52 |
|
52 | |||
53 | def wrap_to_table(str_): |
|
53 | def wrap_to_table(str_): | |
54 | return '''<table class="code-difftable"> |
|
54 | return '''<table class="code-difftable"> | |
55 | <tr class="line no-comment"> |
|
55 | <tr class="line no-comment"> | |
56 | <td class="lineno new"></td> |
|
56 | <td class="lineno new"></td> | |
57 | <td class="code no-comment"><pre>%s</pre></td> |
|
57 | <td class="code no-comment"><pre>%s</pre></td> | |
58 | </tr> |
|
58 | </tr> | |
59 | </table>''' % str_ |
|
59 | </table>''' % str_ | |
60 |
|
60 | |||
61 |
|
61 | |||
62 | def wrapped_diff(filenode_old, filenode_new, cut_off_limit=None, |
|
62 | def wrapped_diff(filenode_old, filenode_new, cut_off_limit=None, | |
63 | ignore_whitespace=True, line_context=3, |
|
63 | ignore_whitespace=True, line_context=3, | |
64 | enable_comments=False): |
|
64 | enable_comments=False): | |
65 | """ |
|
65 | """ | |
66 | returns a wrapped diff into a table, checks for cut_off_limit and presents |
|
66 | returns a wrapped diff into a table, checks for cut_off_limit and presents | |
67 | proper message |
|
67 | proper message | |
68 | """ |
|
68 | """ | |
69 |
|
69 | |||
70 | if filenode_old is None: |
|
70 | if filenode_old is None: | |
71 | filenode_old = FileNode(filenode_new.path, '', EmptyChangeset()) |
|
71 | filenode_old = FileNode(filenode_new.path, '', EmptyChangeset()) | |
72 |
|
72 | |||
73 | if filenode_old.is_binary or filenode_new.is_binary: |
|
73 | if filenode_old.is_binary or filenode_new.is_binary: | |
74 | diff = wrap_to_table(_('binary file')) |
|
74 | diff = wrap_to_table(_('binary file')) | |
75 | stats = (0, 0) |
|
75 | stats = (0, 0) | |
76 | size = 0 |
|
76 | size = 0 | |
77 |
|
77 | |||
78 | elif cut_off_limit != -1 and (cut_off_limit is None or |
|
78 | elif cut_off_limit != -1 and (cut_off_limit is None or | |
79 | (filenode_old.size < cut_off_limit and filenode_new.size < cut_off_limit)): |
|
79 | (filenode_old.size < cut_off_limit and filenode_new.size < cut_off_limit)): | |
80 |
|
80 | |||
81 | f_gitdiff = get_gitdiff(filenode_old, filenode_new, |
|
81 | f_gitdiff = get_gitdiff(filenode_old, filenode_new, | |
82 | ignore_whitespace=ignore_whitespace, |
|
82 | ignore_whitespace=ignore_whitespace, | |
83 | context=line_context) |
|
83 | context=line_context) | |
84 | diff_processor = DiffProcessor(f_gitdiff, format='gitdiff') |
|
84 | diff_processor = DiffProcessor(f_gitdiff, format='gitdiff') | |
85 |
|
85 | |||
86 | diff = diff_processor.as_html(enable_comments=enable_comments) |
|
86 | diff = diff_processor.as_html(enable_comments=enable_comments) | |
87 | stats = diff_processor.stat() |
|
87 | stats = diff_processor.stat() | |
88 | size = len(diff or '') |
|
88 | size = len(diff or '') | |
89 | else: |
|
89 | else: | |
90 | diff = wrap_to_table(_('Changeset was too big and was cut off, use ' |
|
90 | diff = wrap_to_table(_('Changeset was too big and was cut off, use ' | |
91 | 'diff menu to display this diff')) |
|
91 | 'diff menu to display this diff')) | |
92 | stats = (0, 0) |
|
92 | stats = (0, 0) | |
93 | size = 0 |
|
93 | size = 0 | |
94 | if not diff: |
|
94 | if not diff: | |
95 | submodules = filter(lambda o: isinstance(o, SubModuleNode), |
|
95 | submodules = filter(lambda o: isinstance(o, SubModuleNode), | |
96 | [filenode_new, filenode_old]) |
|
96 | [filenode_new, filenode_old]) | |
97 | if submodules: |
|
97 | if submodules: | |
98 | diff = wrap_to_table(escape('Submodule %r' % submodules[0])) |
|
98 | diff = wrap_to_table(escape('Submodule %r' % submodules[0])) | |
99 | else: |
|
99 | else: | |
100 | diff = wrap_to_table(_('No changes detected')) |
|
100 | diff = wrap_to_table(_('No changes detected')) | |
101 |
|
101 | |||
102 | cs1 = filenode_old.changeset.raw_id |
|
102 | cs1 = filenode_old.changeset.raw_id | |
103 | cs2 = filenode_new.changeset.raw_id |
|
103 | cs2 = filenode_new.changeset.raw_id | |
104 |
|
104 | |||
105 | return size, cs1, cs2, diff, stats |
|
105 | return size, cs1, cs2, diff, stats | |
106 |
|
106 | |||
107 |
|
107 | |||
108 | def get_gitdiff(filenode_old, filenode_new, ignore_whitespace=True, context=3): |
|
108 | def get_gitdiff(filenode_old, filenode_new, ignore_whitespace=True, context=3): | |
109 | """ |
|
109 | """ | |
110 | Returns git style diff between given ``filenode_old`` and ``filenode_new``. |
|
110 | Returns git style diff between given ``filenode_old`` and ``filenode_new``. | |
111 |
|
111 | |||
112 | :param ignore_whitespace: ignore whitespaces in diff |
|
112 | :param ignore_whitespace: ignore whitespaces in diff | |
113 | """ |
|
113 | """ | |
114 | # make sure we pass in default context |
|
114 | # make sure we pass in default context | |
115 | context = context or 3 |
|
115 | context = context or 3 | |
116 | submodules = filter(lambda o: isinstance(o, SubModuleNode), |
|
116 | submodules = filter(lambda o: isinstance(o, SubModuleNode), | |
117 | [filenode_new, filenode_old]) |
|
117 | [filenode_new, filenode_old]) | |
118 | if submodules: |
|
118 | if submodules: | |
119 | return '' |
|
119 | return '' | |
120 |
|
120 | |||
121 | for filenode in (filenode_old, filenode_new): |
|
121 | for filenode in (filenode_old, filenode_new): | |
122 | if not isinstance(filenode, FileNode): |
|
122 | if not isinstance(filenode, FileNode): | |
123 | raise VCSError("Given object should be FileNode object, not %s" |
|
123 | raise VCSError("Given object should be FileNode object, not %s" | |
124 | % filenode.__class__) |
|
124 | % filenode.__class__) | |
125 |
|
125 | |||
126 | repo = filenode_new.changeset.repository |
|
126 | repo = filenode_new.changeset.repository | |
127 | old_raw_id = getattr(filenode_old.changeset, 'raw_id', repo.EMPTY_CHANGESET) |
|
127 | old_raw_id = getattr(filenode_old.changeset, 'raw_id', repo.EMPTY_CHANGESET) | |
128 | new_raw_id = getattr(filenode_new.changeset, 'raw_id', repo.EMPTY_CHANGESET) |
|
128 | new_raw_id = getattr(filenode_new.changeset, 'raw_id', repo.EMPTY_CHANGESET) | |
129 |
|
129 | |||
130 | vcs_gitdiff = repo.get_diff(old_raw_id, new_raw_id, filenode_new.path, |
|
130 | vcs_gitdiff = repo.get_diff(old_raw_id, new_raw_id, filenode_new.path, | |
131 | ignore_whitespace, context) |
|
131 | ignore_whitespace, context) | |
132 | return vcs_gitdiff |
|
132 | return vcs_gitdiff | |
133 |
|
133 | |||
134 | NEW_FILENODE = 1 |
|
134 | NEW_FILENODE = 1 | |
135 | DEL_FILENODE = 2 |
|
135 | DEL_FILENODE = 2 | |
136 | MOD_FILENODE = 3 |
|
136 | MOD_FILENODE = 3 | |
137 | RENAMED_FILENODE = 4 |
|
137 | RENAMED_FILENODE = 4 | |
138 | CHMOD_FILENODE = 5 |
|
138 | CHMOD_FILENODE = 5 | |
139 |
|
139 | |||
140 |
|
140 | |||
141 | class DiffLimitExceeded(Exception): |
|
141 | class DiffLimitExceeded(Exception): | |
142 | pass |
|
142 | pass | |
143 |
|
143 | |||
144 |
|
144 | |||
145 | class LimitedDiffContainer(object): |
|
145 | class LimitedDiffContainer(object): | |
146 |
|
146 | |||
147 | def __init__(self, diff_limit, cur_diff_size, diff): |
|
147 | def __init__(self, diff_limit, cur_diff_size, diff): | |
148 | self.diff = diff |
|
148 | self.diff = diff | |
149 | self.diff_limit = diff_limit |
|
149 | self.diff_limit = diff_limit | |
150 | self.cur_diff_size = cur_diff_size |
|
150 | self.cur_diff_size = cur_diff_size | |
151 |
|
151 | |||
152 | def __iter__(self): |
|
152 | def __iter__(self): | |
153 | for l in self.diff: |
|
153 | for l in self.diff: | |
154 | yield l |
|
154 | yield l | |
155 |
|
155 | |||
156 |
|
156 | |||
157 | class DiffProcessor(object): |
|
157 | class DiffProcessor(object): | |
158 | """ |
|
158 | """ | |
159 | Give it a unified or git diff and it returns a list of the files that were |
|
159 | Give it a unified or git diff and it returns a list of the files that were | |
160 | mentioned in the diff together with a dict of meta information that |
|
160 | mentioned in the diff together with a dict of meta information that | |
161 | can be used to render it in a HTML template. |
|
161 | can be used to render it in a HTML template. | |
162 | """ |
|
162 | """ | |
163 | _chunk_re = re.compile(r'^@@ -(\d+)(?:,(\d+))? \+(\d+)(?:,(\d+))? @@(.*)') |
|
163 | _chunk_re = re.compile(r'^@@ -(\d+)(?:,(\d+))? \+(\d+)(?:,(\d+))? @@(.*)') | |
164 | _newline_marker = re.compile(r'^\\ No newline at end of file') |
|
164 | _newline_marker = re.compile(r'^\\ No newline at end of file') | |
165 | _git_header_re = re.compile(r""" |
|
165 | _git_header_re = re.compile(r""" | |
166 | #^diff[ ]--git |
|
166 | #^diff[ ]--git | |
167 | [ ]a/(?P<a_path>.+?)[ ]b/(?P<b_path>.+?)\n |
|
167 | [ ]a/(?P<a_path>.+?)[ ]b/(?P<b_path>.+?)\n | |
168 | (?:^similarity[ ]index[ ](?P<similarity_index>\d+)%\n |
|
168 | (?:^similarity[ ]index[ ](?P<similarity_index>\d+)%\n | |
169 | ^rename[ ]from[ ](?P<rename_from>\S+)\n |
|
169 | ^rename[ ]from[ ](?P<rename_from>\S+)\n | |
170 | ^rename[ ]to[ ](?P<rename_to>\S+)(?:\n|$))? |
|
170 | ^rename[ ]to[ ](?P<rename_to>\S+)(?:\n|$))? | |
171 | (?:^old[ ]mode[ ](?P<old_mode>\d+)\n |
|
171 | (?:^old[ ]mode[ ](?P<old_mode>\d+)\n | |
172 | ^new[ ]mode[ ](?P<new_mode>\d+)(?:\n|$))? |
|
172 | ^new[ ]mode[ ](?P<new_mode>\d+)(?:\n|$))? | |
173 | (?:^new[ ]file[ ]mode[ ](?P<new_file_mode>.+)(?:\n|$))? |
|
173 | (?:^new[ ]file[ ]mode[ ](?P<new_file_mode>.+)(?:\n|$))? | |
174 | (?:^deleted[ ]file[ ]mode[ ](?P<deleted_file_mode>.+)(?:\n|$))? |
|
174 | (?:^deleted[ ]file[ ]mode[ ](?P<deleted_file_mode>.+)(?:\n|$))? | |
175 | (?:^index[ ](?P<a_blob_id>[0-9A-Fa-f]+) |
|
175 | (?:^index[ ](?P<a_blob_id>[0-9A-Fa-f]+) | |
176 | \.\.(?P<b_blob_id>[0-9A-Fa-f]+)[ ]?(?P<b_mode>.+)?(?:\n|$))? |
|
176 | \.\.(?P<b_blob_id>[0-9A-Fa-f]+)[ ]?(?P<b_mode>.+)?(?:\n|$))? | |
177 | (?:^---[ ](a/(?P<a_file>.+)|/dev/null)(?:\n|$))? |
|
177 | (?:^---[ ](a/(?P<a_file>.+)|/dev/null)(?:\n|$))? | |
178 | (?:^\+\+\+[ ](b/(?P<b_file>.+)|/dev/null)(?:\n|$))? |
|
178 | (?:^\+\+\+[ ](b/(?P<b_file>.+)|/dev/null)(?:\n|$))? | |
179 | """, re.VERBOSE | re.MULTILINE) |
|
179 | """, re.VERBOSE | re.MULTILINE) | |
180 | _hg_header_re = re.compile(r""" |
|
180 | _hg_header_re = re.compile(r""" | |
181 | #^diff[ ]--git |
|
181 | #^diff[ ]--git | |
182 | [ ]a/(?P<a_path>.+?)[ ]b/(?P<b_path>.+?)\n |
|
182 | [ ]a/(?P<a_path>.+?)[ ]b/(?P<b_path>.+?)\n | |
183 | (?:^similarity[ ]index[ ](?P<similarity_index>\d+)%(?:\n|$))? |
|
183 | (?:^similarity[ ]index[ ](?P<similarity_index>\d+)%(?:\n|$))? | |
184 | (?:^rename[ ]from[ ](?P<rename_from>\S+)\n |
|
184 | (?:^rename[ ]from[ ](?P<rename_from>\S+)\n | |
185 | ^rename[ ]to[ ](?P<rename_to>\S+)(?:\n|$))? |
|
185 | ^rename[ ]to[ ](?P<rename_to>\S+)(?:\n|$))? | |
186 | (?:^old[ ]mode[ ](?P<old_mode>\d+)\n |
|
186 | (?:^old[ ]mode[ ](?P<old_mode>\d+)\n | |
187 | ^new[ ]mode[ ](?P<new_mode>\d+)(?:\n|$))? |
|
187 | ^new[ ]mode[ ](?P<new_mode>\d+)(?:\n|$))? | |
188 | (?:^new[ ]file[ ]mode[ ](?P<new_file_mode>.+)(?:\n|$))? |
|
188 | (?:^new[ ]file[ ]mode[ ](?P<new_file_mode>.+)(?:\n|$))? | |
189 | (?:^deleted[ ]file[ ]mode[ ](?P<deleted_file_mode>.+)(?:\n|$))? |
|
189 | (?:^deleted[ ]file[ ]mode[ ](?P<deleted_file_mode>.+)(?:\n|$))? | |
190 | (?:^index[ ](?P<a_blob_id>[0-9A-Fa-f]+) |
|
190 | (?:^index[ ](?P<a_blob_id>[0-9A-Fa-f]+) | |
191 | \.\.(?P<b_blob_id>[0-9A-Fa-f]+)[ ]?(?P<b_mode>.+)?(?:\n|$))? |
|
191 | \.\.(?P<b_blob_id>[0-9A-Fa-f]+)[ ]?(?P<b_mode>.+)?(?:\n|$))? | |
192 | (?:^---[ ](a/(?P<a_file>.+)|/dev/null)(?:\n|$))? |
|
192 | (?:^---[ ](a/(?P<a_file>.+)|/dev/null)(?:\n|$))? | |
193 | (?:^\+\+\+[ ](b/(?P<b_file>.+)|/dev/null)(?:\n|$))? |
|
193 | (?:^\+\+\+[ ](b/(?P<b_file>.+)|/dev/null)(?:\n|$))? | |
194 | """, re.VERBOSE | re.MULTILINE) |
|
194 | """, re.VERBOSE | re.MULTILINE) | |
195 |
|
195 | |||
|
196 | #used for inline highlighter word split | |||
|
197 | _token_re = re.compile(r'()(>|<|&|\W+?)') | |||
|
198 | ||||
196 | def __init__(self, diff, vcs='hg', format='gitdiff', diff_limit=None): |
|
199 | def __init__(self, diff, vcs='hg', format='gitdiff', diff_limit=None): | |
197 | """ |
|
200 | """ | |
198 | :param diff: a text in diff format |
|
201 | :param diff: a text in diff format | |
199 | :param vcs: type of version controll hg or git |
|
202 | :param vcs: type of version controll hg or git | |
200 | :param format: format of diff passed, `udiff` or `gitdiff` |
|
203 | :param format: format of diff passed, `udiff` or `gitdiff` | |
201 | :param diff_limit: define the size of diff that is considered "big" |
|
204 | :param diff_limit: define the size of diff that is considered "big" | |
202 | based on that parameter cut off will be triggered, set to None |
|
205 | based on that parameter cut off will be triggered, set to None | |
203 | to show full diff |
|
206 | to show full diff | |
204 | """ |
|
207 | """ | |
205 | if not isinstance(diff, basestring): |
|
208 | if not isinstance(diff, basestring): | |
206 | raise Exception('Diff must be a basestring got %s instead' % type(diff)) |
|
209 | raise Exception('Diff must be a basestring got %s instead' % type(diff)) | |
207 |
|
210 | |||
208 | self._diff = diff |
|
211 | self._diff = diff | |
209 | self._format = format |
|
212 | self._format = format | |
210 | self.adds = 0 |
|
213 | self.adds = 0 | |
211 | self.removes = 0 |
|
214 | self.removes = 0 | |
212 | # calculate diff size |
|
215 | # calculate diff size | |
213 | self.diff_size = len(diff) |
|
216 | self.diff_size = len(diff) | |
214 | self.diff_limit = diff_limit |
|
217 | self.diff_limit = diff_limit | |
215 | self.cur_diff_size = 0 |
|
218 | self.cur_diff_size = 0 | |
216 | self.parsed = False |
|
219 | self.parsed = False | |
217 | self.parsed_diff = [] |
|
220 | self.parsed_diff = [] | |
218 | self.vcs = vcs |
|
221 | self.vcs = vcs | |
219 |
|
222 | |||
220 | if format == 'gitdiff': |
|
223 | if format == 'gitdiff': | |
221 | self.differ = self._highlight_line_difflib |
|
224 | self.differ = self._highlight_line_difflib | |
222 | self._parser = self._parse_gitdiff |
|
225 | self._parser = self._parse_gitdiff | |
223 | else: |
|
226 | else: | |
224 | self.differ = self._highlight_line_udiff |
|
227 | self.differ = self._highlight_line_udiff | |
225 | self._parser = self._parse_udiff |
|
228 | self._parser = self._parse_udiff | |
226 |
|
229 | |||
227 | def _copy_iterator(self): |
|
230 | def _copy_iterator(self): | |
228 | """ |
|
231 | """ | |
229 | make a fresh copy of generator, we should not iterate thru |
|
232 | make a fresh copy of generator, we should not iterate thru | |
230 | an original as it's needed for repeating operations on |
|
233 | an original as it's needed for repeating operations on | |
231 | this instance of DiffProcessor |
|
234 | this instance of DiffProcessor | |
232 | """ |
|
235 | """ | |
233 | self.__udiff, iterator_copy = tee(self.__udiff) |
|
236 | self.__udiff, iterator_copy = tee(self.__udiff) | |
234 | return iterator_copy |
|
237 | return iterator_copy | |
235 |
|
238 | |||
236 | def _escaper(self, string): |
|
239 | def _escaper(self, string): | |
237 | """ |
|
240 | """ | |
238 | Escaper for diff escapes special chars and checks the diff limit |
|
241 | Escaper for diff escapes special chars and checks the diff limit | |
239 |
|
242 | |||
240 | :param string: |
|
243 | :param string: | |
241 | :type string: |
|
244 | :type string: | |
242 | """ |
|
245 | """ | |
243 |
|
246 | |||
244 | self.cur_diff_size += len(string) |
|
247 | self.cur_diff_size += len(string) | |
245 |
|
248 | |||
246 | # escaper get's iterated on each .next() call and it checks if each |
|
249 | # escaper get's iterated on each .next() call and it checks if each | |
247 | # parsed line doesn't exceed the diff limit |
|
250 | # parsed line doesn't exceed the diff limit | |
248 | if self.diff_limit is not None and self.cur_diff_size > self.diff_limit: |
|
251 | if self.diff_limit is not None and self.cur_diff_size > self.diff_limit: | |
249 | raise DiffLimitExceeded('Diff Limit Exceeded') |
|
252 | raise DiffLimitExceeded('Diff Limit Exceeded') | |
250 |
|
253 | |||
251 | return safe_unicode(string).replace('&', '&')\ |
|
254 | return safe_unicode(string).replace('&', '&')\ | |
252 | .replace('<', '<')\ |
|
255 | .replace('<', '<')\ | |
253 | .replace('>', '>') |
|
256 | .replace('>', '>') | |
254 |
|
257 | |||
255 | def _line_counter(self, l): |
|
258 | def _line_counter(self, l): | |
256 | """ |
|
259 | """ | |
257 | Checks each line and bumps total adds/removes for this diff |
|
260 | Checks each line and bumps total adds/removes for this diff | |
258 |
|
261 | |||
259 | :param l: |
|
262 | :param l: | |
260 | """ |
|
263 | """ | |
261 | if l.startswith('+') and not l.startswith('+++'): |
|
264 | if l.startswith('+') and not l.startswith('+++'): | |
262 | self.adds += 1 |
|
265 | self.adds += 1 | |
263 | elif l.startswith('-') and not l.startswith('---'): |
|
266 | elif l.startswith('-') and not l.startswith('---'): | |
264 | self.removes += 1 |
|
267 | self.removes += 1 | |
265 | return safe_unicode(l) |
|
268 | return safe_unicode(l) | |
266 |
|
269 | |||
267 | def _highlight_line_difflib(self, line, next_): |
|
270 | def _highlight_line_difflib(self, line, next_): | |
268 | """ |
|
271 | """ | |
269 | Highlight inline changes in both lines. |
|
272 | Highlight inline changes in both lines. | |
270 | """ |
|
273 | """ | |
271 |
|
274 | |||
272 | if line['action'] == 'del': |
|
275 | if line['action'] == 'del': | |
273 | old, new = line, next_ |
|
276 | old, new = line, next_ | |
274 | else: |
|
277 | else: | |
275 | old, new = next_, line |
|
278 | old, new = next_, line | |
276 |
|
279 | |||
277 |
oldwords = re.split( |
|
280 | oldwords = self._token_re.split(old['line']) | |
278 |
newwords = re.split( |
|
281 | newwords = self._token_re.split(new['line']) | |
279 |
|
||||
280 | sequence = difflib.SequenceMatcher(None, oldwords, newwords) |
|
282 | sequence = difflib.SequenceMatcher(None, oldwords, newwords) | |
281 |
|
283 | |||
282 | oldfragments, newfragments = [], [] |
|
284 | oldfragments, newfragments = [], [] | |
283 | for tag, i1, i2, j1, j2 in sequence.get_opcodes(): |
|
285 | for tag, i1, i2, j1, j2 in sequence.get_opcodes(): | |
284 | oldfrag = ''.join(oldwords[i1:i2]) |
|
286 | oldfrag = ''.join(oldwords[i1:i2]) | |
285 | newfrag = ''.join(newwords[j1:j2]) |
|
287 | newfrag = ''.join(newwords[j1:j2]) | |
286 | if tag != 'equal': |
|
288 | if tag != 'equal': | |
287 | if oldfrag: |
|
289 | if oldfrag: | |
288 | oldfrag = '<del>%s</del>' % oldfrag |
|
290 | oldfrag = '<del>%s</del>' % oldfrag | |
289 | if newfrag: |
|
291 | if newfrag: | |
290 | newfrag = '<ins>%s</ins>' % newfrag |
|
292 | newfrag = '<ins>%s</ins>' % newfrag | |
291 | oldfragments.append(oldfrag) |
|
293 | oldfragments.append(oldfrag) | |
292 | newfragments.append(newfrag) |
|
294 | newfragments.append(newfrag) | |
293 |
|
295 | |||
294 | old['line'] = "".join(oldfragments) |
|
296 | old['line'] = "".join(oldfragments) | |
295 | new['line'] = "".join(newfragments) |
|
297 | new['line'] = "".join(newfragments) | |
296 |
|
298 | |||
297 | def _highlight_line_udiff(self, line, next_): |
|
299 | def _highlight_line_udiff(self, line, next_): | |
298 | """ |
|
300 | """ | |
299 | Highlight inline changes in both lines. |
|
301 | Highlight inline changes in both lines. | |
300 | """ |
|
302 | """ | |
301 | start = 0 |
|
303 | start = 0 | |
302 | limit = min(len(line['line']), len(next_['line'])) |
|
304 | limit = min(len(line['line']), len(next_['line'])) | |
303 | while start < limit and line['line'][start] == next_['line'][start]: |
|
305 | while start < limit and line['line'][start] == next_['line'][start]: | |
304 | start += 1 |
|
306 | start += 1 | |
305 | end = -1 |
|
307 | end = -1 | |
306 | limit -= start |
|
308 | limit -= start | |
307 | while -end <= limit and line['line'][end] == next_['line'][end]: |
|
309 | while -end <= limit and line['line'][end] == next_['line'][end]: | |
308 | end -= 1 |
|
310 | end -= 1 | |
309 | end += 1 |
|
311 | end += 1 | |
310 | if start or end: |
|
312 | if start or end: | |
311 | def do(l): |
|
313 | def do(l): | |
312 | last = end + len(l['line']) |
|
314 | last = end + len(l['line']) | |
313 | if l['action'] == 'add': |
|
315 | if l['action'] == 'add': | |
314 | tag = 'ins' |
|
316 | tag = 'ins' | |
315 | else: |
|
317 | else: | |
316 | tag = 'del' |
|
318 | tag = 'del' | |
317 | l['line'] = '%s<%s>%s</%s>%s' % ( |
|
319 | l['line'] = '%s<%s>%s</%s>%s' % ( | |
318 | l['line'][:start], |
|
320 | l['line'][:start], | |
319 | tag, |
|
321 | tag, | |
320 | l['line'][start:last], |
|
322 | l['line'][start:last], | |
321 | tag, |
|
323 | tag, | |
322 | l['line'][last:] |
|
324 | l['line'][last:] | |
323 | ) |
|
325 | ) | |
324 | do(line) |
|
326 | do(line) | |
325 | do(next_) |
|
327 | do(next_) | |
326 |
|
328 | |||
327 | def _get_header(self, diff_chunk): |
|
329 | def _get_header(self, diff_chunk): | |
328 | """ |
|
330 | """ | |
329 | parses the diff header, and returns parts, and leftover diff |
|
331 | parses the diff header, and returns parts, and leftover diff | |
330 | parts consists of 14 elements:: |
|
332 | parts consists of 14 elements:: | |
331 |
|
333 | |||
332 | a_path, b_path, similarity_index, rename_from, rename_to, |
|
334 | a_path, b_path, similarity_index, rename_from, rename_to, | |
333 | old_mode, new_mode, new_file_mode, deleted_file_mode, |
|
335 | old_mode, new_mode, new_file_mode, deleted_file_mode, | |
334 | a_blob_id, b_blob_id, b_mode, a_file, b_file |
|
336 | a_blob_id, b_blob_id, b_mode, a_file, b_file | |
335 |
|
337 | |||
336 | :param diff_chunk: |
|
338 | :param diff_chunk: | |
337 | :type diff_chunk: |
|
339 | :type diff_chunk: | |
338 | """ |
|
340 | """ | |
339 |
|
341 | |||
340 | if self.vcs == 'git': |
|
342 | if self.vcs == 'git': | |
341 | match = self._git_header_re.match(diff_chunk) |
|
343 | match = self._git_header_re.match(diff_chunk) | |
342 | diff = diff_chunk[match.end():] |
|
344 | diff = diff_chunk[match.end():] | |
343 | return match.groupdict(), imap(self._escaper, diff.splitlines(1)) |
|
345 | return match.groupdict(), imap(self._escaper, diff.splitlines(1)) | |
344 | elif self.vcs == 'hg': |
|
346 | elif self.vcs == 'hg': | |
345 | match = self._hg_header_re.match(diff_chunk) |
|
347 | match = self._hg_header_re.match(diff_chunk) | |
346 | diff = diff_chunk[match.end():] |
|
348 | diff = diff_chunk[match.end():] | |
347 | return match.groupdict(), imap(self._escaper, diff.splitlines(1)) |
|
349 | return match.groupdict(), imap(self._escaper, diff.splitlines(1)) | |
348 | else: |
|
350 | else: | |
349 | raise Exception('VCS type %s is not supported' % self.vcs) |
|
351 | raise Exception('VCS type %s is not supported' % self.vcs) | |
350 |
|
352 | |||
351 | def _clean_line(self, line, command): |
|
353 | def _clean_line(self, line, command): | |
352 | if command in ['+', '-', ' ']: |
|
354 | if command in ['+', '-', ' ']: | |
353 | #only modify the line if it's actually a diff thing |
|
355 | #only modify the line if it's actually a diff thing | |
354 | line = line[1:] |
|
356 | line = line[1:] | |
355 | return line |
|
357 | return line | |
356 |
|
358 | |||
357 | def _parse_gitdiff(self, inline_diff=True): |
|
359 | def _parse_gitdiff(self, inline_diff=True): | |
358 | _files = [] |
|
360 | _files = [] | |
359 | diff_container = lambda arg: arg |
|
361 | diff_container = lambda arg: arg | |
360 |
|
362 | |||
361 | ##split the diff in chunks of separate --git a/file b/file chunks |
|
363 | ##split the diff in chunks of separate --git a/file b/file chunks | |
362 | for raw_diff in ('\n' + self._diff).split('\ndiff --git')[1:]: |
|
364 | for raw_diff in ('\n' + self._diff).split('\ndiff --git')[1:]: | |
363 | binary = False |
|
365 | binary = False | |
364 | binary_msg = 'unknown binary' |
|
366 | binary_msg = 'unknown binary' | |
365 | head, diff = self._get_header(raw_diff) |
|
367 | head, diff = self._get_header(raw_diff) | |
366 |
|
368 | |||
367 | if not head['a_file'] and head['b_file']: |
|
369 | if not head['a_file'] and head['b_file']: | |
368 | op = 'A' |
|
370 | op = 'A' | |
369 | elif head['a_file'] and head['b_file']: |
|
371 | elif head['a_file'] and head['b_file']: | |
370 | op = 'M' |
|
372 | op = 'M' | |
371 | elif head['a_file'] and not head['b_file']: |
|
373 | elif head['a_file'] and not head['b_file']: | |
372 | op = 'D' |
|
374 | op = 'D' | |
373 | else: |
|
375 | else: | |
374 | #probably we're dealing with a binary file 1 |
|
376 | #probably we're dealing with a binary file 1 | |
375 | binary = True |
|
377 | binary = True | |
376 | if head['deleted_file_mode']: |
|
378 | if head['deleted_file_mode']: | |
377 | op = 'D' |
|
379 | op = 'D' | |
378 | stats = ['b', DEL_FILENODE] |
|
380 | stats = ['b', DEL_FILENODE] | |
379 | binary_msg = 'deleted binary file' |
|
381 | binary_msg = 'deleted binary file' | |
380 | elif head['new_file_mode']: |
|
382 | elif head['new_file_mode']: | |
381 | op = 'A' |
|
383 | op = 'A' | |
382 | stats = ['b', NEW_FILENODE] |
|
384 | stats = ['b', NEW_FILENODE] | |
383 | binary_msg = 'new binary file %s' % head['new_file_mode'] |
|
385 | binary_msg = 'new binary file %s' % head['new_file_mode'] | |
384 | else: |
|
386 | else: | |
385 | if head['new_mode'] and head['old_mode']: |
|
387 | if head['new_mode'] and head['old_mode']: | |
386 | stats = ['b', CHMOD_FILENODE] |
|
388 | stats = ['b', CHMOD_FILENODE] | |
387 | op = 'M' |
|
389 | op = 'M' | |
388 | binary_msg = ('modified binary file chmod %s => %s' |
|
390 | binary_msg = ('modified binary file chmod %s => %s' | |
389 | % (head['old_mode'], head['new_mode'])) |
|
391 | % (head['old_mode'], head['new_mode'])) | |
390 | elif (head['rename_from'] and head['rename_to'] |
|
392 | elif (head['rename_from'] and head['rename_to'] | |
391 | and head['rename_from'] != head['rename_to']): |
|
393 | and head['rename_from'] != head['rename_to']): | |
392 | stats = ['b', RENAMED_FILENODE] |
|
394 | stats = ['b', RENAMED_FILENODE] | |
393 | op = 'M' |
|
395 | op = 'M' | |
394 | binary_msg = ('file renamed from %s to %s' |
|
396 | binary_msg = ('file renamed from %s to %s' | |
395 | % (head['rename_from'], head['rename_to'])) |
|
397 | % (head['rename_from'], head['rename_to'])) | |
396 | else: |
|
398 | else: | |
397 | stats = ['b', MOD_FILENODE] |
|
399 | stats = ['b', MOD_FILENODE] | |
398 | op = 'M' |
|
400 | op = 'M' | |
399 | binary_msg = 'modified binary file' |
|
401 | binary_msg = 'modified binary file' | |
400 |
|
402 | |||
401 | if not binary: |
|
403 | if not binary: | |
402 | try: |
|
404 | try: | |
403 | chunks, stats = self._parse_lines(diff) |
|
405 | chunks, stats = self._parse_lines(diff) | |
404 | except DiffLimitExceeded: |
|
406 | except DiffLimitExceeded: | |
405 | diff_container = lambda _diff: LimitedDiffContainer( |
|
407 | diff_container = lambda _diff: LimitedDiffContainer( | |
406 | self.diff_limit, |
|
408 | self.diff_limit, | |
407 | self.cur_diff_size, |
|
409 | self.cur_diff_size, | |
408 | _diff) |
|
410 | _diff) | |
409 | break |
|
411 | break | |
410 | else: |
|
412 | else: | |
411 | chunks = [] |
|
413 | chunks = [] | |
412 | chunks.append([{ |
|
414 | chunks.append([{ | |
413 | 'old_lineno': '', |
|
415 | 'old_lineno': '', | |
414 | 'new_lineno': '', |
|
416 | 'new_lineno': '', | |
415 | 'action': 'binary', |
|
417 | 'action': 'binary', | |
416 | 'line': binary_msg, |
|
418 | 'line': binary_msg, | |
417 | }]) |
|
419 | }]) | |
418 |
|
420 | |||
419 | _files.append({ |
|
421 | _files.append({ | |
420 | 'filename': head['b_path'], |
|
422 | 'filename': head['b_path'], | |
421 | 'old_revision': head['a_blob_id'], |
|
423 | 'old_revision': head['a_blob_id'], | |
422 | 'new_revision': head['b_blob_id'], |
|
424 | 'new_revision': head['b_blob_id'], | |
423 | 'chunks': chunks, |
|
425 | 'chunks': chunks, | |
424 | 'operation': op, |
|
426 | 'operation': op, | |
425 | 'stats': stats, |
|
427 | 'stats': stats, | |
426 | }) |
|
428 | }) | |
427 |
|
429 | |||
428 | sorter = lambda info: {'A': 0, 'M': 1, 'D': 2}.get(info['operation']) |
|
430 | sorter = lambda info: {'A': 0, 'M': 1, 'D': 2}.get(info['operation']) | |
429 |
|
431 | |||
430 | if inline_diff is False: |
|
432 | if inline_diff is False: | |
431 | return diff_container(sorted(_files, key=sorter)) |
|
433 | return diff_container(sorted(_files, key=sorter)) | |
432 |
|
434 | |||
433 | # highlight inline changes |
|
435 | # highlight inline changes | |
434 | for diff_data in _files: |
|
436 | for diff_data in _files: | |
435 | for chunk in diff_data['chunks']: |
|
437 | for chunk in diff_data['chunks']: | |
436 | lineiter = iter(chunk) |
|
438 | lineiter = iter(chunk) | |
437 | try: |
|
439 | try: | |
438 | while 1: |
|
440 | while 1: | |
439 | line = lineiter.next() |
|
441 | line = lineiter.next() | |
440 | if line['action'] not in ['unmod', 'context']: |
|
442 | if line['action'] not in ['unmod', 'context']: | |
441 | nextline = lineiter.next() |
|
443 | nextline = lineiter.next() | |
442 | if nextline['action'] in ['unmod', 'context'] or \ |
|
444 | if nextline['action'] in ['unmod', 'context'] or \ | |
443 | nextline['action'] == line['action']: |
|
445 | nextline['action'] == line['action']: | |
444 | continue |
|
446 | continue | |
445 | self.differ(line, nextline) |
|
447 | self.differ(line, nextline) | |
446 | except StopIteration: |
|
448 | except StopIteration: | |
447 | pass |
|
449 | pass | |
448 |
|
450 | |||
449 | return diff_container(sorted(_files, key=sorter)) |
|
451 | return diff_container(sorted(_files, key=sorter)) | |
450 |
|
452 | |||
451 | def _parse_udiff(self, inline_diff=True): |
|
453 | def _parse_udiff(self, inline_diff=True): | |
452 | raise NotImplementedError() |
|
454 | raise NotImplementedError() | |
453 |
|
455 | |||
454 | def _parse_lines(self, diff): |
|
456 | def _parse_lines(self, diff): | |
455 | """ |
|
457 | """ | |
456 | Parse the diff an return data for the template. |
|
458 | Parse the diff an return data for the template. | |
457 | """ |
|
459 | """ | |
458 |
|
460 | |||
459 | lineiter = iter(diff) |
|
461 | lineiter = iter(diff) | |
460 | stats = [0, 0] |
|
462 | stats = [0, 0] | |
461 |
|
463 | |||
462 | try: |
|
464 | try: | |
463 | chunks = [] |
|
465 | chunks = [] | |
464 | line = lineiter.next() |
|
466 | line = lineiter.next() | |
465 |
|
467 | |||
466 | while line: |
|
468 | while line: | |
467 | lines = [] |
|
469 | lines = [] | |
468 | chunks.append(lines) |
|
470 | chunks.append(lines) | |
469 |
|
471 | |||
470 | match = self._chunk_re.match(line) |
|
472 | match = self._chunk_re.match(line) | |
471 |
|
473 | |||
472 | if not match: |
|
474 | if not match: | |
473 | break |
|
475 | break | |
474 |
|
476 | |||
475 | gr = match.groups() |
|
477 | gr = match.groups() | |
476 | (old_line, old_end, |
|
478 | (old_line, old_end, | |
477 | new_line, new_end) = [int(x or 1) for x in gr[:-1]] |
|
479 | new_line, new_end) = [int(x or 1) for x in gr[:-1]] | |
478 | old_line -= 1 |
|
480 | old_line -= 1 | |
479 | new_line -= 1 |
|
481 | new_line -= 1 | |
480 |
|
482 | |||
481 | context = len(gr) == 5 |
|
483 | context = len(gr) == 5 | |
482 | old_end += old_line |
|
484 | old_end += old_line | |
483 | new_end += new_line |
|
485 | new_end += new_line | |
484 |
|
486 | |||
485 | if context: |
|
487 | if context: | |
486 | # skip context only if it's first line |
|
488 | # skip context only if it's first line | |
487 | if int(gr[0]) > 1: |
|
489 | if int(gr[0]) > 1: | |
488 | lines.append({ |
|
490 | lines.append({ | |
489 | 'old_lineno': '...', |
|
491 | 'old_lineno': '...', | |
490 | 'new_lineno': '...', |
|
492 | 'new_lineno': '...', | |
491 | 'action': 'context', |
|
493 | 'action': 'context', | |
492 | 'line': line, |
|
494 | 'line': line, | |
493 | }) |
|
495 | }) | |
494 |
|
496 | |||
495 | line = lineiter.next() |
|
497 | line = lineiter.next() | |
496 |
|
498 | |||
497 | while old_line < old_end or new_line < new_end: |
|
499 | while old_line < old_end or new_line < new_end: | |
498 | command = ' ' |
|
500 | command = ' ' | |
499 | if line: |
|
501 | if line: | |
500 | command = line[0] |
|
502 | command = line[0] | |
501 |
|
503 | |||
502 | affects_old = affects_new = False |
|
504 | affects_old = affects_new = False | |
503 |
|
505 | |||
504 | # ignore those if we don't expect them |
|
506 | # ignore those if we don't expect them | |
505 | if command in '#@': |
|
507 | if command in '#@': | |
506 | continue |
|
508 | continue | |
507 | elif command == '+': |
|
509 | elif command == '+': | |
508 | affects_new = True |
|
510 | affects_new = True | |
509 | action = 'add' |
|
511 | action = 'add' | |
510 | stats[0] += 1 |
|
512 | stats[0] += 1 | |
511 | elif command == '-': |
|
513 | elif command == '-': | |
512 | affects_old = True |
|
514 | affects_old = True | |
513 | action = 'del' |
|
515 | action = 'del' | |
514 | stats[1] += 1 |
|
516 | stats[1] += 1 | |
515 | else: |
|
517 | else: | |
516 | affects_old = affects_new = True |
|
518 | affects_old = affects_new = True | |
517 | action = 'unmod' |
|
519 | action = 'unmod' | |
518 |
|
520 | |||
519 | if not self._newline_marker.match(line): |
|
521 | if not self._newline_marker.match(line): | |
520 | old_line += affects_old |
|
522 | old_line += affects_old | |
521 | new_line += affects_new |
|
523 | new_line += affects_new | |
522 | lines.append({ |
|
524 | lines.append({ | |
523 | 'old_lineno': affects_old and old_line or '', |
|
525 | 'old_lineno': affects_old and old_line or '', | |
524 | 'new_lineno': affects_new and new_line or '', |
|
526 | 'new_lineno': affects_new and new_line or '', | |
525 | 'action': action, |
|
527 | 'action': action, | |
526 | 'line': self._clean_line(line, command) |
|
528 | 'line': self._clean_line(line, command) | |
527 | }) |
|
529 | }) | |
528 |
|
530 | |||
529 | line = lineiter.next() |
|
531 | line = lineiter.next() | |
530 |
|
532 | |||
531 | if self._newline_marker.match(line): |
|
533 | if self._newline_marker.match(line): | |
532 | # we need to append to lines, since this is not |
|
534 | # we need to append to lines, since this is not | |
533 | # counted in the line specs of diff |
|
535 | # counted in the line specs of diff | |
534 | lines.append({ |
|
536 | lines.append({ | |
535 | 'old_lineno': '...', |
|
537 | 'old_lineno': '...', | |
536 | 'new_lineno': '...', |
|
538 | 'new_lineno': '...', | |
537 | 'action': 'context', |
|
539 | 'action': 'context', | |
538 | 'line': self._clean_line(line, command) |
|
540 | 'line': self._clean_line(line, command) | |
539 | }) |
|
541 | }) | |
540 |
|
542 | |||
541 | except StopIteration: |
|
543 | except StopIteration: | |
542 | pass |
|
544 | pass | |
543 | return chunks, stats |
|
545 | return chunks, stats | |
544 |
|
546 | |||
545 | def _safe_id(self, idstring): |
|
547 | def _safe_id(self, idstring): | |
546 | """Make a string safe for including in an id attribute. |
|
548 | """Make a string safe for including in an id attribute. | |
547 |
|
549 | |||
548 | The HTML spec says that id attributes 'must begin with |
|
550 | The HTML spec says that id attributes 'must begin with | |
549 | a letter ([A-Za-z]) and may be followed by any number |
|
551 | a letter ([A-Za-z]) and may be followed by any number | |
550 | of letters, digits ([0-9]), hyphens ("-"), underscores |
|
552 | of letters, digits ([0-9]), hyphens ("-"), underscores | |
551 | ("_"), colons (":"), and periods (".")'. These regexps |
|
553 | ("_"), colons (":"), and periods (".")'. These regexps | |
552 | are slightly over-zealous, in that they remove colons |
|
554 | are slightly over-zealous, in that they remove colons | |
553 | and periods unnecessarily. |
|
555 | and periods unnecessarily. | |
554 |
|
556 | |||
555 | Whitespace is transformed into underscores, and then |
|
557 | Whitespace is transformed into underscores, and then | |
556 | anything which is not a hyphen or a character that |
|
558 | anything which is not a hyphen or a character that | |
557 | matches \w (alphanumerics and underscore) is removed. |
|
559 | matches \w (alphanumerics and underscore) is removed. | |
558 |
|
560 | |||
559 | """ |
|
561 | """ | |
560 | # Transform all whitespace to underscore |
|
562 | # Transform all whitespace to underscore | |
561 | idstring = re.sub(r'\s', "_", '%s' % idstring) |
|
563 | idstring = re.sub(r'\s', "_", '%s' % idstring) | |
562 | # Remove everything that is not a hyphen or a member of \w |
|
564 | # Remove everything that is not a hyphen or a member of \w | |
563 | idstring = re.sub(r'(?!-)\W', "", idstring).lower() |
|
565 | idstring = re.sub(r'(?!-)\W', "", idstring).lower() | |
564 | return idstring |
|
566 | return idstring | |
565 |
|
567 | |||
566 | def prepare(self, inline_diff=True): |
|
568 | def prepare(self, inline_diff=True): | |
567 | """ |
|
569 | """ | |
568 | Prepare the passed udiff for HTML rendering. It'l return a list |
|
570 | Prepare the passed udiff for HTML rendering. It'l return a list | |
569 | of dicts with diff information |
|
571 | of dicts with diff information | |
570 | """ |
|
572 | """ | |
571 | parsed = self._parser(inline_diff=inline_diff) |
|
573 | parsed = self._parser(inline_diff=inline_diff) | |
572 | self.parsed = True |
|
574 | self.parsed = True | |
573 | self.parsed_diff = parsed |
|
575 | self.parsed_diff = parsed | |
574 | return parsed |
|
576 | return parsed | |
575 |
|
577 | |||
576 | def as_raw(self, diff_lines=None): |
|
578 | def as_raw(self, diff_lines=None): | |
577 | """ |
|
579 | """ | |
578 | Returns raw string diff |
|
580 | Returns raw string diff | |
579 | """ |
|
581 | """ | |
580 | return self._diff |
|
582 | return self._diff | |
581 | #return u''.join(imap(self._line_counter, self._diff.splitlines(1))) |
|
583 | #return u''.join(imap(self._line_counter, self._diff.splitlines(1))) | |
582 |
|
584 | |||
583 | def as_html(self, table_class='code-difftable', line_class='line', |
|
585 | def as_html(self, table_class='code-difftable', line_class='line', | |
584 | new_lineno_class='lineno old', old_lineno_class='lineno new', |
|
586 | new_lineno_class='lineno old', old_lineno_class='lineno new', | |
585 | code_class='code', enable_comments=False, parsed_lines=None): |
|
587 | code_class='code', enable_comments=False, parsed_lines=None): | |
586 | """ |
|
588 | """ | |
587 | Return given diff as html table with customized css classes |
|
589 | Return given diff as html table with customized css classes | |
588 | """ |
|
590 | """ | |
589 | def _link_to_if(condition, label, url): |
|
591 | def _link_to_if(condition, label, url): | |
590 | """ |
|
592 | """ | |
591 | Generates a link if condition is meet or just the label if not. |
|
593 | Generates a link if condition is meet or just the label if not. | |
592 | """ |
|
594 | """ | |
593 |
|
595 | |||
594 | if condition: |
|
596 | if condition: | |
595 | return '''<a href="%(url)s">%(label)s</a>''' % { |
|
597 | return '''<a href="%(url)s">%(label)s</a>''' % { | |
596 | 'url': url, |
|
598 | 'url': url, | |
597 | 'label': label |
|
599 | 'label': label | |
598 | } |
|
600 | } | |
599 | else: |
|
601 | else: | |
600 | return label |
|
602 | return label | |
601 | if not self.parsed: |
|
603 | if not self.parsed: | |
602 | self.prepare() |
|
604 | self.prepare() | |
603 |
|
605 | |||
604 | diff_lines = self.parsed_diff |
|
606 | diff_lines = self.parsed_diff | |
605 | if parsed_lines: |
|
607 | if parsed_lines: | |
606 | diff_lines = parsed_lines |
|
608 | diff_lines = parsed_lines | |
607 |
|
609 | |||
608 | _html_empty = True |
|
610 | _html_empty = True | |
609 | _html = [] |
|
611 | _html = [] | |
610 | _html.append('''<table class="%(table_class)s">\n''' % { |
|
612 | _html.append('''<table class="%(table_class)s">\n''' % { | |
611 | 'table_class': table_class |
|
613 | 'table_class': table_class | |
612 | }) |
|
614 | }) | |
613 |
|
615 | |||
614 | for diff in diff_lines: |
|
616 | for diff in diff_lines: | |
615 | for line in diff['chunks']: |
|
617 | for line in diff['chunks']: | |
616 | _html_empty = False |
|
618 | _html_empty = False | |
617 | for change in line: |
|
619 | for change in line: | |
618 | _html.append('''<tr class="%(lc)s %(action)s">\n''' % { |
|
620 | _html.append('''<tr class="%(lc)s %(action)s">\n''' % { | |
619 | 'lc': line_class, |
|
621 | 'lc': line_class, | |
620 | 'action': change['action'] |
|
622 | 'action': change['action'] | |
621 | }) |
|
623 | }) | |
622 | anchor_old_id = '' |
|
624 | anchor_old_id = '' | |
623 | anchor_new_id = '' |
|
625 | anchor_new_id = '' | |
624 | anchor_old = "%(filename)s_o%(oldline_no)s" % { |
|
626 | anchor_old = "%(filename)s_o%(oldline_no)s" % { | |
625 | 'filename': self._safe_id(diff['filename']), |
|
627 | 'filename': self._safe_id(diff['filename']), | |
626 | 'oldline_no': change['old_lineno'] |
|
628 | 'oldline_no': change['old_lineno'] | |
627 | } |
|
629 | } | |
628 | anchor_new = "%(filename)s_n%(oldline_no)s" % { |
|
630 | anchor_new = "%(filename)s_n%(oldline_no)s" % { | |
629 | 'filename': self._safe_id(diff['filename']), |
|
631 | 'filename': self._safe_id(diff['filename']), | |
630 | 'oldline_no': change['new_lineno'] |
|
632 | 'oldline_no': change['new_lineno'] | |
631 | } |
|
633 | } | |
632 | cond_old = (change['old_lineno'] != '...' and |
|
634 | cond_old = (change['old_lineno'] != '...' and | |
633 | change['old_lineno']) |
|
635 | change['old_lineno']) | |
634 | cond_new = (change['new_lineno'] != '...' and |
|
636 | cond_new = (change['new_lineno'] != '...' and | |
635 | change['new_lineno']) |
|
637 | change['new_lineno']) | |
636 | if cond_old: |
|
638 | if cond_old: | |
637 | anchor_old_id = 'id="%s"' % anchor_old |
|
639 | anchor_old_id = 'id="%s"' % anchor_old | |
638 | if cond_new: |
|
640 | if cond_new: | |
639 | anchor_new_id = 'id="%s"' % anchor_new |
|
641 | anchor_new_id = 'id="%s"' % anchor_new | |
640 | ########################################################### |
|
642 | ########################################################### | |
641 | # OLD LINE NUMBER |
|
643 | # OLD LINE NUMBER | |
642 | ########################################################### |
|
644 | ########################################################### | |
643 | _html.append('''\t<td %(a_id)s class="%(olc)s">''' % { |
|
645 | _html.append('''\t<td %(a_id)s class="%(olc)s">''' % { | |
644 | 'a_id': anchor_old_id, |
|
646 | 'a_id': anchor_old_id, | |
645 | 'olc': old_lineno_class |
|
647 | 'olc': old_lineno_class | |
646 | }) |
|
648 | }) | |
647 |
|
649 | |||
648 | _html.append('''%(link)s''' % { |
|
650 | _html.append('''%(link)s''' % { | |
649 | 'link': _link_to_if(True, change['old_lineno'], |
|
651 | 'link': _link_to_if(True, change['old_lineno'], | |
650 | '#%s' % anchor_old) |
|
652 | '#%s' % anchor_old) | |
651 | }) |
|
653 | }) | |
652 | _html.append('''</td>\n''') |
|
654 | _html.append('''</td>\n''') | |
653 | ########################################################### |
|
655 | ########################################################### | |
654 | # NEW LINE NUMBER |
|
656 | # NEW LINE NUMBER | |
655 | ########################################################### |
|
657 | ########################################################### | |
656 |
|
658 | |||
657 | _html.append('''\t<td %(a_id)s class="%(nlc)s">''' % { |
|
659 | _html.append('''\t<td %(a_id)s class="%(nlc)s">''' % { | |
658 | 'a_id': anchor_new_id, |
|
660 | 'a_id': anchor_new_id, | |
659 | 'nlc': new_lineno_class |
|
661 | 'nlc': new_lineno_class | |
660 | }) |
|
662 | }) | |
661 |
|
663 | |||
662 | _html.append('''%(link)s''' % { |
|
664 | _html.append('''%(link)s''' % { | |
663 | 'link': _link_to_if(True, change['new_lineno'], |
|
665 | 'link': _link_to_if(True, change['new_lineno'], | |
664 | '#%s' % anchor_new) |
|
666 | '#%s' % anchor_new) | |
665 | }) |
|
667 | }) | |
666 | _html.append('''</td>\n''') |
|
668 | _html.append('''</td>\n''') | |
667 | ########################################################### |
|
669 | ########################################################### | |
668 | # CODE |
|
670 | # CODE | |
669 | ########################################################### |
|
671 | ########################################################### | |
670 | comments = '' if enable_comments else 'no-comment' |
|
672 | comments = '' if enable_comments else 'no-comment' | |
671 | _html.append('''\t<td class="%(cc)s %(inc)s">''' % { |
|
673 | _html.append('''\t<td class="%(cc)s %(inc)s">''' % { | |
672 | 'cc': code_class, |
|
674 | 'cc': code_class, | |
673 | 'inc': comments |
|
675 | 'inc': comments | |
674 | }) |
|
676 | }) | |
675 | _html.append('''\n\t\t<pre>%(code)s</pre>\n''' % { |
|
677 | _html.append('''\n\t\t<pre>%(code)s</pre>\n''' % { | |
676 | 'code': change['line'] |
|
678 | 'code': change['line'] | |
677 | }) |
|
679 | }) | |
678 |
|
680 | |||
679 | _html.append('''\t</td>''') |
|
681 | _html.append('''\t</td>''') | |
680 | _html.append('''\n</tr>\n''') |
|
682 | _html.append('''\n</tr>\n''') | |
681 | _html.append('''</table>''') |
|
683 | _html.append('''</table>''') | |
682 | if _html_empty: |
|
684 | if _html_empty: | |
683 | return None |
|
685 | return None | |
684 | return ''.join(_html) |
|
686 | return ''.join(_html) | |
685 |
|
687 | |||
686 | def stat(self): |
|
688 | def stat(self): | |
687 | """ |
|
689 | """ | |
688 | Returns tuple of added, and removed lines for this instance |
|
690 | Returns tuple of added, and removed lines for this instance | |
689 | """ |
|
691 | """ | |
690 | return self.adds, self.removes |
|
692 | return self.adds, self.removes | |
691 |
|
693 | |||
692 |
|
694 | |||
693 | class InMemoryBundleRepo(bundlerepository): |
|
695 | class InMemoryBundleRepo(bundlerepository): | |
694 | def __init__(self, ui, path, bundlestream): |
|
696 | def __init__(self, ui, path, bundlestream): | |
695 | self._tempparent = None |
|
697 | self._tempparent = None | |
696 | localrepo.localrepository.__init__(self, ui, path) |
|
698 | localrepo.localrepository.__init__(self, ui, path) | |
697 | self.ui.setconfig('phases', 'publish', False) |
|
699 | self.ui.setconfig('phases', 'publish', False) | |
698 |
|
700 | |||
699 | self.bundle = bundlestream |
|
701 | self.bundle = bundlestream | |
700 |
|
702 | |||
701 | # dict with the mapping 'filename' -> position in the bundle |
|
703 | # dict with the mapping 'filename' -> position in the bundle | |
702 | self.bundlefilespos = {} |
|
704 | self.bundlefilespos = {} | |
703 |
|
705 | |||
704 |
|
706 | |||
705 | def differ(org_repo, org_ref, other_repo, other_ref, discovery_data=None, |
|
707 | def differ(org_repo, org_ref, other_repo, other_ref, discovery_data=None, | |
706 | remote_compare=False, context=3, ignore_whitespace=False): |
|
708 | remote_compare=False, context=3, ignore_whitespace=False): | |
707 | """ |
|
709 | """ | |
708 | General differ between branches, bookmarks, revisions of two remote or |
|
710 | General differ between branches, bookmarks, revisions of two remote or | |
709 | local but related repositories |
|
711 | local but related repositories | |
710 |
|
712 | |||
711 | :param org_repo: |
|
713 | :param org_repo: | |
712 | :param org_ref: |
|
714 | :param org_ref: | |
713 | :param other_repo: |
|
715 | :param other_repo: | |
714 | :type other_repo: |
|
716 | :type other_repo: | |
715 | :type other_ref: |
|
717 | :type other_ref: | |
716 | """ |
|
718 | """ | |
717 |
|
719 | |||
718 | org_repo_scm = org_repo.scm_instance |
|
720 | org_repo_scm = org_repo.scm_instance | |
719 | other_repo_scm = other_repo.scm_instance |
|
721 | other_repo_scm = other_repo.scm_instance | |
720 |
|
722 | |||
721 | org_repo = org_repo_scm._repo |
|
723 | org_repo = org_repo_scm._repo | |
722 | other_repo = other_repo_scm._repo |
|
724 | other_repo = other_repo_scm._repo | |
723 |
|
725 | |||
724 | org_ref = org_ref[1] |
|
726 | org_ref = org_ref[1] | |
725 | other_ref = other_ref[1] |
|
727 | other_ref = other_ref[1] | |
726 |
|
728 | |||
727 | if org_repo_scm == other_repo_scm: |
|
729 | if org_repo_scm == other_repo_scm: | |
728 | log.debug('running diff between %s@%s and %s@%s' |
|
730 | log.debug('running diff between %s@%s and %s@%s' | |
729 | % (org_repo.path, org_ref, other_repo.path, other_ref)) |
|
731 | % (org_repo.path, org_ref, other_repo.path, other_ref)) | |
730 | _diff = org_repo_scm.get_diff(rev1=org_ref, rev2=other_ref, |
|
732 | _diff = org_repo_scm.get_diff(rev1=org_ref, rev2=other_ref, | |
731 | ignore_whitespace=ignore_whitespace, context=context) |
|
733 | ignore_whitespace=ignore_whitespace, context=context) | |
732 | return _diff |
|
734 | return _diff | |
733 |
|
735 | |||
734 | elif remote_compare: |
|
736 | elif remote_compare: | |
735 | opts = diffopts(git=True, ignorews=ignore_whitespace, context=context) |
|
737 | opts = diffopts(git=True, ignorews=ignore_whitespace, context=context) | |
736 | common, incoming, rheads = discovery_data |
|
738 | common, incoming, rheads = discovery_data | |
737 | org_repo_peer = localrepo.locallegacypeer(org_repo.local()) |
|
739 | org_repo_peer = localrepo.locallegacypeer(org_repo.local()) | |
738 | # create a bundle (uncompressed if other repo is not local) |
|
740 | # create a bundle (uncompressed if other repo is not local) | |
739 | if org_repo_peer.capable('getbundle'): |
|
741 | if org_repo_peer.capable('getbundle'): | |
740 | # disable repo hooks here since it's just bundle ! |
|
742 | # disable repo hooks here since it's just bundle ! | |
741 | # patch and reset hooks section of UI config to not run any |
|
743 | # patch and reset hooks section of UI config to not run any | |
742 | # hooks on fetching archives with subrepos |
|
744 | # hooks on fetching archives with subrepos | |
743 | for k, _ in org_repo.ui.configitems('hooks'): |
|
745 | for k, _ in org_repo.ui.configitems('hooks'): | |
744 | org_repo.ui.setconfig('hooks', k, None) |
|
746 | org_repo.ui.setconfig('hooks', k, None) | |
745 | unbundle = org_repo.getbundle('incoming', common=None, |
|
747 | unbundle = org_repo.getbundle('incoming', common=None, | |
746 | heads=None) |
|
748 | heads=None) | |
747 |
|
749 | |||
748 | buf = BytesIO() |
|
750 | buf = BytesIO() | |
749 | while True: |
|
751 | while True: | |
750 | chunk = unbundle._stream.read(1024 * 4) |
|
752 | chunk = unbundle._stream.read(1024 * 4) | |
751 | if not chunk: |
|
753 | if not chunk: | |
752 | break |
|
754 | break | |
753 | buf.write(chunk) |
|
755 | buf.write(chunk) | |
754 |
|
756 | |||
755 | buf.seek(0) |
|
757 | buf.seek(0) | |
756 | # replace chunked _stream with data that can do tell() and seek() |
|
758 | # replace chunked _stream with data that can do tell() and seek() | |
757 | unbundle._stream = buf |
|
759 | unbundle._stream = buf | |
758 |
|
760 | |||
759 | ui = make_ui('db') |
|
761 | ui = make_ui('db') | |
760 | bundlerepo = InMemoryBundleRepo(ui, path=org_repo.root, |
|
762 | bundlerepo = InMemoryBundleRepo(ui, path=org_repo.root, | |
761 | bundlestream=unbundle) |
|
763 | bundlestream=unbundle) | |
762 |
|
764 | |||
763 | return ''.join(patch.diff(bundlerepo, |
|
765 | return ''.join(patch.diff(bundlerepo, | |
764 | node1=other_repo[other_ref].node(), |
|
766 | node1=other_repo[other_ref].node(), | |
765 | node2=org_repo[org_ref].node(), |
|
767 | node2=org_repo[org_ref].node(), | |
766 | opts=opts)) |
|
768 | opts=opts)) | |
767 |
|
769 | |||
768 | return '' |
|
770 | return '' |
General Comments 0
You need to be logged in to leave comments.
Login now