Show More
@@ -1,713 +1,713 b'' | |||||
1 | # -*- coding: utf-8 -*- |
|
1 | # -*- coding: utf-8 -*- | |
2 | # This program is free software: you can redistribute it and/or modify |
|
2 | # This program is free software: you can redistribute it and/or modify | |
3 | # it under the terms of the GNU General Public License as published by |
|
3 | # it under the terms of the GNU General Public License as published by | |
4 | # the Free Software Foundation, either version 3 of the License, or |
|
4 | # the Free Software Foundation, either version 3 of the License, or | |
5 | # (at your option) any later version. |
|
5 | # (at your option) any later version. | |
6 | # |
|
6 | # | |
7 | # This program is distributed in the hope that it will be useful, |
|
7 | # This program is distributed in the hope that it will be useful, | |
8 | # but WITHOUT ANY WARRANTY; without even the implied warranty of |
|
8 | # but WITHOUT ANY WARRANTY; without even the implied warranty of | |
9 | # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the |
|
9 | # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the | |
10 | # GNU General Public License for more details. |
|
10 | # GNU General Public License for more details. | |
11 | # |
|
11 | # | |
12 | # You should have received a copy of the GNU General Public License |
|
12 | # You should have received a copy of the GNU General Public License | |
13 | # along with this program. If not, see <http://www.gnu.org/licenses/>. |
|
13 | # along with this program. If not, see <http://www.gnu.org/licenses/>. | |
14 | """ |
|
14 | """ | |
15 | kallithea.lib.diffs |
|
15 | kallithea.lib.diffs | |
16 | ~~~~~~~~~~~~~~~~~~~ |
|
16 | ~~~~~~~~~~~~~~~~~~~ | |
17 |
|
17 | |||
18 | Set of diffing helpers, previously part of vcs |
|
18 | Set of diffing helpers, previously part of vcs | |
19 |
|
19 | |||
20 |
|
20 | |||
21 | This file was forked by the Kallithea project in July 2014. |
|
21 | This file was forked by the Kallithea project in July 2014. | |
22 | Original author and date, and relevant copyright and licensing information is below: |
|
22 | Original author and date, and relevant copyright and licensing information is below: | |
23 | :created_on: Dec 4, 2011 |
|
23 | :created_on: Dec 4, 2011 | |
24 | :author: marcink |
|
24 | :author: marcink | |
25 | :copyright: (c) 2013 RhodeCode GmbH, and others. |
|
25 | :copyright: (c) 2013 RhodeCode GmbH, and others. | |
26 | :license: GPLv3, see LICENSE.md for more details. |
|
26 | :license: GPLv3, see LICENSE.md for more details. | |
27 | """ |
|
27 | """ | |
28 | import difflib |
|
28 | import difflib | |
29 | import logging |
|
29 | import logging | |
30 | import re |
|
30 | import re | |
31 |
|
31 | |||
32 | from tg.i18n import ugettext as _ |
|
32 | from tg.i18n import ugettext as _ | |
33 |
|
33 | |||
34 | from kallithea.lib import webutils |
|
34 | from kallithea.lib import webutils | |
35 | from kallithea.lib.utils2 import safe_str |
|
35 | from kallithea.lib.utils2 import safe_str | |
36 | from kallithea.lib.vcs.backends.base import EmptyChangeset |
|
36 | from kallithea.lib.vcs.backends.base import EmptyChangeset | |
37 | from kallithea.lib.vcs.exceptions import VCSError |
|
37 | from kallithea.lib.vcs.exceptions import VCSError | |
38 | from kallithea.lib.vcs.nodes import FileNode, SubModuleNode |
|
38 | from kallithea.lib.vcs.nodes import FileNode, SubModuleNode | |
39 |
|
39 | |||
40 |
|
40 | |||
41 | log = logging.getLogger(__name__) |
|
41 | log = logging.getLogger(__name__) | |
42 |
|
42 | |||
43 |
|
43 | |||
44 | def _safe_id(idstring): |
|
44 | def _safe_id(idstring): | |
45 | r"""Make a string safe for including in an id attribute. |
|
45 | r"""Make a string safe for including in an id attribute. | |
46 |
|
46 | |||
47 | The HTML spec says that id attributes 'must begin with |
|
47 | The HTML spec says that id attributes 'must begin with | |
48 | a letter ([A-Za-z]) and may be followed by any number |
|
48 | a letter ([A-Za-z]) and may be followed by any number | |
49 | of letters, digits ([0-9]), hyphens ("-"), underscores |
|
49 | of letters, digits ([0-9]), hyphens ("-"), underscores | |
50 | ("_"), colons (":"), and periods (".")'. These regexps |
|
50 | ("_"), colons (":"), and periods (".")'. These regexps | |
51 | are slightly over-zealous, in that they remove colons |
|
51 | are slightly over-zealous, in that they remove colons | |
52 | and periods unnecessarily. |
|
52 | and periods unnecessarily. | |
53 |
|
53 | |||
54 | Whitespace is transformed into underscores, and then |
|
54 | Whitespace is transformed into underscores, and then | |
55 | anything which is not a hyphen or a character that |
|
55 | anything which is not a hyphen or a character that | |
56 | matches \w (alphanumerics and underscore) is removed. |
|
56 | matches \w (alphanumerics and underscore) is removed. | |
57 |
|
57 | |||
58 | """ |
|
58 | """ | |
59 | # Transform all whitespace to underscore |
|
59 | # Transform all whitespace to underscore | |
60 | idstring = re.sub(r'\s', "_", idstring) |
|
60 | idstring = re.sub(r'\s', "_", idstring) | |
61 | # Remove everything that is not a hyphen or a member of \w |
|
61 | # Remove everything that is not a hyphen or a member of \w | |
62 | idstring = re.sub(r'(?!-)\W', "", idstring).lower() |
|
62 | idstring = re.sub(r'(?!-)\W', "", idstring).lower() | |
63 | return idstring |
|
63 | return idstring | |
64 |
|
64 | |||
65 |
|
65 | |||
66 | def as_html(table_class='code-difftable', line_class='line', |
|
66 | def as_html(table_class='code-difftable', line_class='line', | |
67 | old_lineno_class='lineno old', new_lineno_class='lineno new', |
|
67 | old_lineno_class='lineno old', new_lineno_class='lineno new', | |
68 | no_lineno_class='lineno', |
|
68 | no_lineno_class='lineno', | |
69 | code_class='code', parsed_lines=None): |
|
69 | code_class='code', parsed_lines=None): | |
70 | """ |
|
70 | """ | |
71 | Return given diff as html table with customized css classes |
|
71 | Return given diff as html table with customized css classes | |
72 | """ |
|
72 | """ | |
73 | _html_empty = True |
|
73 | _html_empty = True | |
74 | _html = [] |
|
74 | _html = [] | |
75 | _html.append('''<table class="%(table_class)s">\n''' % { |
|
75 | _html.append('''<table class="%(table_class)s">\n''' % { | |
76 | 'table_class': table_class |
|
76 | 'table_class': table_class | |
77 | }) |
|
77 | }) | |
78 |
|
78 | |||
79 | for file_info in parsed_lines: |
|
79 | for file_info in parsed_lines: | |
80 | count_no_lineno = 0 # counter to allow comments on lines without new/old line numbers |
|
80 | count_no_lineno = 0 # counter to allow comments on lines without new/old line numbers | |
81 | for chunk in file_info['chunks']: |
|
81 | for chunk in file_info['chunks']: | |
82 | _html_empty = False |
|
82 | _html_empty = False | |
83 | for change in chunk: |
|
83 | for change in chunk: | |
84 | _html.append('''<tr class="%(lc)s %(action)s">\n''' % { |
|
84 | _html.append('''<tr class="%(lc)s %(action)s">\n''' % { | |
85 | 'lc': line_class, |
|
85 | 'lc': line_class, | |
86 | 'action': change['action'] |
|
86 | 'action': change['action'] | |
87 | }) |
|
87 | }) | |
88 | if change['old_lineno'] or change['new_lineno']: |
|
88 | if change['old_lineno'] or change['new_lineno']: | |
89 | ########################################################### |
|
89 | ########################################################### | |
90 | # OLD LINE NUMBER |
|
90 | # OLD LINE NUMBER | |
91 | ########################################################### |
|
91 | ########################################################### | |
92 | anchor_old = "%(filename)s_o%(oldline_no)s" % { |
|
92 | anchor_old = "%(filename)s_o%(oldline_no)s" % { | |
93 | 'filename': _safe_id(file_info['filename']), |
|
93 | 'filename': _safe_id(file_info['filename']), | |
94 | 'oldline_no': change['old_lineno'] |
|
94 | 'oldline_no': change['old_lineno'] | |
95 | } |
|
95 | } | |
96 | anchor_old_id = '' |
|
96 | anchor_old_id = '' | |
97 | if change['old_lineno']: |
|
97 | if change['old_lineno']: | |
98 | anchor_old_id = 'id="%s"' % anchor_old |
|
98 | anchor_old_id = 'id="%s"' % anchor_old | |
99 | _html.append('''\t<td %(a_id)s class="%(olc)s">''' % { |
|
99 | _html.append('''\t<td %(a_id)s class="%(olc)s">''' % { | |
100 | 'a_id': anchor_old_id, |
|
100 | 'a_id': anchor_old_id, | |
101 | 'olc': old_lineno_class, |
|
101 | 'olc': old_lineno_class, | |
102 | }) |
|
102 | }) | |
103 | _html.append('''<a href="%(url)s" data-pseudo-content="%(label)s"></a>''' % { |
|
103 | _html.append('''<a href="%(url)s" data-pseudo-content="%(label)s"></a>''' % { | |
104 | 'label': change['old_lineno'], |
|
104 | 'label': change['old_lineno'], | |
105 | 'url': '#%s' % anchor_old, |
|
105 | 'url': '#%s' % anchor_old, | |
106 | }) |
|
106 | }) | |
107 | _html.append('''</td>\n''') |
|
107 | _html.append('''</td>\n''') | |
108 | ########################################################### |
|
108 | ########################################################### | |
109 | # NEW LINE NUMBER |
|
109 | # NEW LINE NUMBER | |
110 | ########################################################### |
|
110 | ########################################################### | |
111 | anchor_new = "%(filename)s_n%(newline_no)s" % { |
|
111 | anchor_new = "%(filename)s_n%(newline_no)s" % { | |
112 | 'filename': _safe_id(file_info['filename']), |
|
112 | 'filename': _safe_id(file_info['filename']), | |
113 | 'newline_no': change['new_lineno'] |
|
113 | 'newline_no': change['new_lineno'] | |
114 | } |
|
114 | } | |
115 | anchor_new_id = '' |
|
115 | anchor_new_id = '' | |
116 | if change['new_lineno']: |
|
116 | if change['new_lineno']: | |
117 | anchor_new_id = 'id="%s"' % anchor_new |
|
117 | anchor_new_id = 'id="%s"' % anchor_new | |
118 | _html.append('''\t<td %(a_id)s class="%(nlc)s">''' % { |
|
118 | _html.append('''\t<td %(a_id)s class="%(nlc)s">''' % { | |
119 | 'a_id': anchor_new_id, |
|
119 | 'a_id': anchor_new_id, | |
120 | 'nlc': new_lineno_class |
|
120 | 'nlc': new_lineno_class | |
121 | }) |
|
121 | }) | |
122 | _html.append('''<a href="%(url)s" data-pseudo-content="%(label)s"></a>''' % { |
|
122 | _html.append('''<a href="%(url)s" data-pseudo-content="%(label)s"></a>''' % { | |
123 | 'label': change['new_lineno'], |
|
123 | 'label': change['new_lineno'], | |
124 | 'url': '#%s' % anchor_new, |
|
124 | 'url': '#%s' % anchor_new, | |
125 | }) |
|
125 | }) | |
126 | _html.append('''</td>\n''') |
|
126 | _html.append('''</td>\n''') | |
127 | else: |
|
127 | else: | |
128 | ########################################################### |
|
128 | ########################################################### | |
129 | # NO LINE NUMBER |
|
129 | # NO LINE NUMBER | |
130 | ########################################################### |
|
130 | ########################################################### | |
131 | anchor = "%(filename)s_%(count_no_lineno)s" % { |
|
131 | anchor = "%(filename)s_%(count_no_lineno)s" % { | |
132 | 'filename': _safe_id(file_info['filename']), |
|
132 | 'filename': _safe_id(file_info['filename']), | |
133 | 'count_no_lineno': count_no_lineno, |
|
133 | 'count_no_lineno': count_no_lineno, | |
134 | } |
|
134 | } | |
135 | count_no_lineno += 1 |
|
135 | count_no_lineno += 1 | |
136 | _html.append('''\t<td id="%(anchor)s" class="%(olc)s" colspan="2">''' % { |
|
136 | _html.append('''\t<td id="%(anchor)s" class="%(olc)s" colspan="2">''' % { | |
137 | 'anchor': anchor, |
|
137 | 'anchor': anchor, | |
138 | 'olc': no_lineno_class, |
|
138 | 'olc': no_lineno_class, | |
139 | }) |
|
139 | }) | |
140 | _html.append('''</td>\n''') |
|
140 | _html.append('''</td>\n''') | |
141 | ########################################################### |
|
141 | ########################################################### | |
142 | # CODE |
|
142 | # CODE | |
143 | ########################################################### |
|
143 | ########################################################### | |
144 | _html.append('''\t<td class="%(cc)s">''' % { |
|
144 | _html.append('''\t<td class="%(cc)s">''' % { | |
145 | 'cc': code_class, |
|
145 | 'cc': code_class, | |
146 | }) |
|
146 | }) | |
147 | _html.append('''\n\t\t<div class="add-bubble"><div> </div></div><pre>%(code)s</pre>\n''' % { |
|
147 | _html.append('''\n\t\t<div class="add-bubble"><div> </div></div><pre>%(code)s</pre>\n''' % { | |
148 | 'code': change['line'] |
|
148 | 'code': change['line'] | |
149 | }) |
|
149 | }) | |
150 |
|
150 | |||
151 | _html.append('''\t</td>''') |
|
151 | _html.append('''\t</td>''') | |
152 | _html.append('''\n</tr>\n''') |
|
152 | _html.append('''\n</tr>\n''') | |
153 | _html.append('''</table>''') |
|
153 | _html.append('''</table>''') | |
154 | if _html_empty: |
|
154 | if _html_empty: | |
155 | return None |
|
155 | return None | |
156 | return ''.join(_html) |
|
156 | return ''.join(_html) | |
157 |
|
157 | |||
158 |
|
158 | |||
159 | def wrap_to_table(html): |
|
159 | def wrap_to_table(html): | |
160 | """Given a string with html, return it wrapped in a table, similar to what |
|
160 | """Given a string with html, return it wrapped in a table, similar to what | |
161 |
|
|
161 | as_html returns.""" | |
162 | return '''\ |
|
162 | return '''\ | |
163 | <table class="code-difftable"> |
|
163 | <table class="code-difftable"> | |
164 | <tr class="line"> |
|
164 | <tr class="line"> | |
165 | <td class="lineno new"></td> |
|
165 | <td class="lineno new"></td> | |
166 | <td class="code"><pre>%s</pre></td> |
|
166 | <td class="code"><pre>%s</pre></td> | |
167 | </tr> |
|
167 | </tr> | |
168 | </table>''' % html |
|
168 | </table>''' % html | |
169 |
|
169 | |||
170 |
|
170 | |||
171 | def wrapped_diff(filenode_old, filenode_new, diff_limit=None, |
|
171 | def wrapped_diff(filenode_old, filenode_new, diff_limit=None, | |
172 | ignore_whitespace=True, line_context=3): |
|
172 | ignore_whitespace=True, line_context=3): | |
173 | """ |
|
173 | """ | |
174 | Returns a file diff wrapped into a table. |
|
174 | Returns a file diff wrapped into a table. | |
175 | Checks for diff_limit and presents a message if the diff is too big. |
|
175 | Checks for diff_limit and presents a message if the diff is too big. | |
176 | """ |
|
176 | """ | |
177 | if filenode_old is None: |
|
177 | if filenode_old is None: | |
178 | filenode_old = FileNode(filenode_new.path, '', EmptyChangeset()) |
|
178 | filenode_old = FileNode(filenode_new.path, '', EmptyChangeset()) | |
179 |
|
179 | |||
180 | op = None |
|
180 | op = None | |
181 | a_path = filenode_old.path # default, might be overriden by actual rename in diff |
|
181 | a_path = filenode_old.path # default, might be overriden by actual rename in diff | |
182 | if filenode_old.is_binary or filenode_new.is_binary: |
|
182 | if filenode_old.is_binary or filenode_new.is_binary: | |
183 | html_diff = wrap_to_table(_('Binary file')) |
|
183 | html_diff = wrap_to_table(_('Binary file')) | |
184 | stats = (0, 0) |
|
184 | stats = (0, 0) | |
185 |
|
185 | |||
186 | elif diff_limit != -1 and ( |
|
186 | elif diff_limit != -1 and ( | |
187 | diff_limit is None or |
|
187 | diff_limit is None or | |
188 | (filenode_old.size < diff_limit and filenode_new.size < diff_limit)): |
|
188 | (filenode_old.size < diff_limit and filenode_new.size < diff_limit)): | |
189 |
|
189 | |||
190 | raw_diff = get_gitdiff(filenode_old, filenode_new, |
|
190 | raw_diff = get_gitdiff(filenode_old, filenode_new, | |
191 | ignore_whitespace=ignore_whitespace, |
|
191 | ignore_whitespace=ignore_whitespace, | |
192 | context=line_context) |
|
192 | context=line_context) | |
193 | diff_processor = DiffProcessor(raw_diff) |
|
193 | diff_processor = DiffProcessor(raw_diff) | |
194 | if diff_processor.parsed: # there should be exactly one element, for the specified file |
|
194 | if diff_processor.parsed: # there should be exactly one element, for the specified file | |
195 | f = diff_processor.parsed[0] |
|
195 | f = diff_processor.parsed[0] | |
196 | op = f['operation'] |
|
196 | op = f['operation'] | |
197 | a_path = f['old_filename'] |
|
197 | a_path = f['old_filename'] | |
198 |
|
198 | |||
199 | html_diff = as_html(parsed_lines=diff_processor.parsed) |
|
199 | html_diff = as_html(parsed_lines=diff_processor.parsed) | |
200 | stats = diff_processor.stat() |
|
200 | stats = diff_processor.stat() | |
201 |
|
201 | |||
202 | else: |
|
202 | else: | |
203 | html_diff = wrap_to_table(_('Changeset was too big and was cut off, use ' |
|
203 | html_diff = wrap_to_table(_('Changeset was too big and was cut off, use ' | |
204 | 'diff menu to display this diff')) |
|
204 | 'diff menu to display this diff')) | |
205 | stats = (0, 0) |
|
205 | stats = (0, 0) | |
206 |
|
206 | |||
207 | if not html_diff: |
|
207 | if not html_diff: | |
208 | submodules = [o for o in [filenode_new, filenode_old] if isinstance(o, SubModuleNode)] |
|
208 | submodules = [o for o in [filenode_new, filenode_old] if isinstance(o, SubModuleNode)] | |
209 | if submodules: |
|
209 | if submodules: | |
210 | html_diff = wrap_to_table(webutils.escape('Submodule %r' % submodules[0])) |
|
210 | html_diff = wrap_to_table(webutils.escape('Submodule %r' % submodules[0])) | |
211 | else: |
|
211 | else: | |
212 | html_diff = wrap_to_table(_('No changes detected')) |
|
212 | html_diff = wrap_to_table(_('No changes detected')) | |
213 |
|
213 | |||
214 | cs1 = filenode_old.changeset.raw_id |
|
214 | cs1 = filenode_old.changeset.raw_id | |
215 | cs2 = filenode_new.changeset.raw_id |
|
215 | cs2 = filenode_new.changeset.raw_id | |
216 |
|
216 | |||
217 | return cs1, cs2, a_path, html_diff, stats, op |
|
217 | return cs1, cs2, a_path, html_diff, stats, op | |
218 |
|
218 | |||
219 |
|
219 | |||
220 | def get_gitdiff(filenode_old, filenode_new, ignore_whitespace=True, context=3): |
|
220 | def get_gitdiff(filenode_old, filenode_new, ignore_whitespace=True, context=3): | |
221 | """ |
|
221 | """ | |
222 | Returns git style diff between given ``filenode_old`` and ``filenode_new``. |
|
222 | Returns git style diff between given ``filenode_old`` and ``filenode_new``. | |
223 | """ |
|
223 | """ | |
224 | # make sure we pass in default context |
|
224 | # make sure we pass in default context | |
225 | context = context or 3 |
|
225 | context = context or 3 | |
226 | submodules = [o for o in [filenode_new, filenode_old] if isinstance(o, SubModuleNode)] |
|
226 | submodules = [o for o in [filenode_new, filenode_old] if isinstance(o, SubModuleNode)] | |
227 | if submodules: |
|
227 | if submodules: | |
228 | return b'' |
|
228 | return b'' | |
229 |
|
229 | |||
230 | for filenode in (filenode_old, filenode_new): |
|
230 | for filenode in (filenode_old, filenode_new): | |
231 | if not isinstance(filenode, FileNode): |
|
231 | if not isinstance(filenode, FileNode): | |
232 | raise VCSError("Given object should be FileNode object, not %s" |
|
232 | raise VCSError("Given object should be FileNode object, not %s" | |
233 | % filenode.__class__) |
|
233 | % filenode.__class__) | |
234 |
|
234 | |||
235 | repo = filenode_new.changeset.repository |
|
235 | repo = filenode_new.changeset.repository | |
236 | old_raw_id = getattr(filenode_old.changeset, 'raw_id', repo.EMPTY_CHANGESET) |
|
236 | old_raw_id = getattr(filenode_old.changeset, 'raw_id', repo.EMPTY_CHANGESET) | |
237 | new_raw_id = getattr(filenode_new.changeset, 'raw_id', repo.EMPTY_CHANGESET) |
|
237 | new_raw_id = getattr(filenode_new.changeset, 'raw_id', repo.EMPTY_CHANGESET) | |
238 |
|
238 | |||
239 | vcs_gitdiff = get_diff(repo, old_raw_id, new_raw_id, filenode_new.path, |
|
239 | vcs_gitdiff = get_diff(repo, old_raw_id, new_raw_id, filenode_new.path, | |
240 | ignore_whitespace, context) |
|
240 | ignore_whitespace, context) | |
241 | return vcs_gitdiff |
|
241 | return vcs_gitdiff | |
242 |
|
242 | |||
243 |
|
243 | |||
244 | def get_diff(scm_instance, rev1, rev2, path=None, ignore_whitespace=False, context=3): |
|
244 | def get_diff(scm_instance, rev1, rev2, path=None, ignore_whitespace=False, context=3): | |
245 | """ |
|
245 | """ | |
246 | A thin wrapper around vcs lib get_diff. |
|
246 | A thin wrapper around vcs lib get_diff. | |
247 | """ |
|
247 | """ | |
248 | try: |
|
248 | try: | |
249 | return scm_instance.get_diff(rev1, rev2, path=path, |
|
249 | return scm_instance.get_diff(rev1, rev2, path=path, | |
250 | ignore_whitespace=ignore_whitespace, context=context) |
|
250 | ignore_whitespace=ignore_whitespace, context=context) | |
251 | except MemoryError: |
|
251 | except MemoryError: | |
252 | webutils.flash('MemoryError: Diff is too big', category='error') |
|
252 | webutils.flash('MemoryError: Diff is too big', category='error') | |
253 | return b'' |
|
253 | return b'' | |
254 |
|
254 | |||
255 |
|
255 | |||
256 | NEW_FILENODE = 1 |
|
256 | NEW_FILENODE = 1 | |
257 | DEL_FILENODE = 2 |
|
257 | DEL_FILENODE = 2 | |
258 | MOD_FILENODE = 3 |
|
258 | MOD_FILENODE = 3 | |
259 | RENAMED_FILENODE = 4 |
|
259 | RENAMED_FILENODE = 4 | |
260 | COPIED_FILENODE = 5 |
|
260 | COPIED_FILENODE = 5 | |
261 | CHMOD_FILENODE = 6 |
|
261 | CHMOD_FILENODE = 6 | |
262 | BIN_FILENODE = 7 |
|
262 | BIN_FILENODE = 7 | |
263 |
|
263 | |||
264 |
|
264 | |||
265 | class DiffProcessor(object): |
|
265 | class DiffProcessor(object): | |
266 | """ |
|
266 | """ | |
267 | Give it a unified or git diff and it returns a list of the files that were |
|
267 | Give it a unified or git diff and it returns a list of the files that were | |
268 | mentioned in the diff together with a dict of meta information that |
|
268 | mentioned in the diff together with a dict of meta information that | |
269 | can be used to render it in a HTML template. |
|
269 | can be used to render it in a HTML template. | |
270 | """ |
|
270 | """ | |
271 | _diff_git_re = re.compile(b'^diff --git', re.MULTILINE) |
|
271 | _diff_git_re = re.compile(b'^diff --git', re.MULTILINE) | |
272 |
|
272 | |||
273 | def __init__(self, diff, vcs='hg', diff_limit=None, inline_diff=True): |
|
273 | def __init__(self, diff, vcs='hg', diff_limit=None, inline_diff=True): | |
274 | """ |
|
274 | """ | |
275 | :param diff: a text in diff format |
|
275 | :param diff: a text in diff format | |
276 | :param vcs: type of version control hg or git |
|
276 | :param vcs: type of version control hg or git | |
277 | :param diff_limit: define the size of diff that is considered "big" |
|
277 | :param diff_limit: define the size of diff that is considered "big" | |
278 | based on that parameter cut off will be triggered, set to None |
|
278 | based on that parameter cut off will be triggered, set to None | |
279 | to show full diff |
|
279 | to show full diff | |
280 | """ |
|
280 | """ | |
281 | if not isinstance(diff, bytes): |
|
281 | if not isinstance(diff, bytes): | |
282 | raise Exception('Diff must be bytes - got %s' % type(diff)) |
|
282 | raise Exception('Diff must be bytes - got %s' % type(diff)) | |
283 |
|
283 | |||
284 | self._diff = memoryview(diff) |
|
284 | self._diff = memoryview(diff) | |
285 | self.adds = 0 |
|
285 | self.adds = 0 | |
286 | self.removes = 0 |
|
286 | self.removes = 0 | |
287 | self.diff_limit = diff_limit |
|
287 | self.diff_limit = diff_limit | |
288 | self.limited_diff = False |
|
288 | self.limited_diff = False | |
289 | self.vcs = vcs |
|
289 | self.vcs = vcs | |
290 | self.parsed = self._parse_gitdiff(inline_diff=inline_diff) |
|
290 | self.parsed = self._parse_gitdiff(inline_diff=inline_diff) | |
291 |
|
291 | |||
292 | def _parse_gitdiff(self, inline_diff): |
|
292 | def _parse_gitdiff(self, inline_diff): | |
293 | """Parse self._diff and return a list of dicts with meta info and chunks for each file. |
|
293 | """Parse self._diff and return a list of dicts with meta info and chunks for each file. | |
294 | Might set limited_diff. |
|
294 | Might set limited_diff. | |
295 | Optionally, do an extra pass and to extra markup of one-liner changes. |
|
295 | Optionally, do an extra pass and to extra markup of one-liner changes. | |
296 | """ |
|
296 | """ | |
297 | _files = [] # list of dicts with meta info and chunks |
|
297 | _files = [] # list of dicts with meta info and chunks | |
298 |
|
298 | |||
299 | starts = [m.start() for m in self._diff_git_re.finditer(self._diff)] |
|
299 | starts = [m.start() for m in self._diff_git_re.finditer(self._diff)] | |
300 | starts.append(len(self._diff)) |
|
300 | starts.append(len(self._diff)) | |
301 |
|
301 | |||
302 | for start, end in zip(starts, starts[1:]): |
|
302 | for start, end in zip(starts, starts[1:]): | |
303 | if self.diff_limit and end > self.diff_limit: |
|
303 | if self.diff_limit and end > self.diff_limit: | |
304 | self.limited_diff = True |
|
304 | self.limited_diff = True | |
305 | continue |
|
305 | continue | |
306 |
|
306 | |||
307 | head, diff_lines = _get_header(self.vcs, self._diff[start:end]) |
|
307 | head, diff_lines = _get_header(self.vcs, self._diff[start:end]) | |
308 |
|
308 | |||
309 | op = None |
|
309 | op = None | |
310 | stats = { |
|
310 | stats = { | |
311 | 'added': 0, |
|
311 | 'added': 0, | |
312 | 'deleted': 0, |
|
312 | 'deleted': 0, | |
313 | 'binary': False, |
|
313 | 'binary': False, | |
314 | 'ops': {}, |
|
314 | 'ops': {}, | |
315 | } |
|
315 | } | |
316 |
|
316 | |||
317 | if head['deleted_file_mode']: |
|
317 | if head['deleted_file_mode']: | |
318 | op = 'removed' |
|
318 | op = 'removed' | |
319 | stats['binary'] = True |
|
319 | stats['binary'] = True | |
320 | stats['ops'][DEL_FILENODE] = 'deleted file' |
|
320 | stats['ops'][DEL_FILENODE] = 'deleted file' | |
321 |
|
321 | |||
322 | elif head['new_file_mode']: |
|
322 | elif head['new_file_mode']: | |
323 | op = 'added' |
|
323 | op = 'added' | |
324 | stats['binary'] = True |
|
324 | stats['binary'] = True | |
325 | stats['ops'][NEW_FILENODE] = 'new file %s' % head['new_file_mode'] |
|
325 | stats['ops'][NEW_FILENODE] = 'new file %s' % head['new_file_mode'] | |
326 | else: # modify operation, can be cp, rename, chmod |
|
326 | else: # modify operation, can be cp, rename, chmod | |
327 | # CHMOD |
|
327 | # CHMOD | |
328 | if head['new_mode'] and head['old_mode']: |
|
328 | if head['new_mode'] and head['old_mode']: | |
329 | op = 'modified' |
|
329 | op = 'modified' | |
330 | stats['binary'] = True |
|
330 | stats['binary'] = True | |
331 | stats['ops'][CHMOD_FILENODE] = ('modified file chmod %s => %s' |
|
331 | stats['ops'][CHMOD_FILENODE] = ('modified file chmod %s => %s' | |
332 | % (head['old_mode'], head['new_mode'])) |
|
332 | % (head['old_mode'], head['new_mode'])) | |
333 | # RENAME |
|
333 | # RENAME | |
334 | if (head['rename_from'] and head['rename_to'] |
|
334 | if (head['rename_from'] and head['rename_to'] | |
335 | and head['rename_from'] != head['rename_to']): |
|
335 | and head['rename_from'] != head['rename_to']): | |
336 | op = 'renamed' |
|
336 | op = 'renamed' | |
337 | stats['binary'] = True |
|
337 | stats['binary'] = True | |
338 | stats['ops'][RENAMED_FILENODE] = ('file renamed from %s to %s' |
|
338 | stats['ops'][RENAMED_FILENODE] = ('file renamed from %s to %s' | |
339 | % (head['rename_from'], head['rename_to'])) |
|
339 | % (head['rename_from'], head['rename_to'])) | |
340 | # COPY |
|
340 | # COPY | |
341 | if head.get('copy_from') and head.get('copy_to'): |
|
341 | if head.get('copy_from') and head.get('copy_to'): | |
342 | op = 'modified' |
|
342 | op = 'modified' | |
343 | stats['binary'] = True |
|
343 | stats['binary'] = True | |
344 | stats['ops'][COPIED_FILENODE] = ('file copied from %s to %s' |
|
344 | stats['ops'][COPIED_FILENODE] = ('file copied from %s to %s' | |
345 | % (head['copy_from'], head['copy_to'])) |
|
345 | % (head['copy_from'], head['copy_to'])) | |
346 | # FALL BACK: detect missed old style add or remove |
|
346 | # FALL BACK: detect missed old style add or remove | |
347 | if op is None: |
|
347 | if op is None: | |
348 | if not head['a_file'] and head['b_file']: |
|
348 | if not head['a_file'] and head['b_file']: | |
349 | op = 'added' |
|
349 | op = 'added' | |
350 | stats['binary'] = True |
|
350 | stats['binary'] = True | |
351 | stats['ops'][NEW_FILENODE] = 'new file' |
|
351 | stats['ops'][NEW_FILENODE] = 'new file' | |
352 |
|
352 | |||
353 | elif head['a_file'] and not head['b_file']: |
|
353 | elif head['a_file'] and not head['b_file']: | |
354 | op = 'removed' |
|
354 | op = 'removed' | |
355 | stats['binary'] = True |
|
355 | stats['binary'] = True | |
356 | stats['ops'][DEL_FILENODE] = 'deleted file' |
|
356 | stats['ops'][DEL_FILENODE] = 'deleted file' | |
357 |
|
357 | |||
358 | # it's not ADD not DELETE |
|
358 | # it's not ADD not DELETE | |
359 | if op is None: |
|
359 | if op is None: | |
360 | op = 'modified' |
|
360 | op = 'modified' | |
361 | stats['binary'] = True |
|
361 | stats['binary'] = True | |
362 | stats['ops'][MOD_FILENODE] = 'modified file' |
|
362 | stats['ops'][MOD_FILENODE] = 'modified file' | |
363 |
|
363 | |||
364 | # a real non-binary diff |
|
364 | # a real non-binary diff | |
365 | if head['a_file'] or head['b_file']: |
|
365 | if head['a_file'] or head['b_file']: | |
366 | chunks, added, deleted = _parse_lines(diff_lines) |
|
366 | chunks, added, deleted = _parse_lines(diff_lines) | |
367 | stats['binary'] = False |
|
367 | stats['binary'] = False | |
368 | stats['added'] = added |
|
368 | stats['added'] = added | |
369 | stats['deleted'] = deleted |
|
369 | stats['deleted'] = deleted | |
370 | # explicit mark that it's a modified file |
|
370 | # explicit mark that it's a modified file | |
371 | if op == 'modified': |
|
371 | if op == 'modified': | |
372 | stats['ops'][MOD_FILENODE] = 'modified file' |
|
372 | stats['ops'][MOD_FILENODE] = 'modified file' | |
373 | else: # Git binary patch (or empty diff) |
|
373 | else: # Git binary patch (or empty diff) | |
374 | # Git binary patch |
|
374 | # Git binary patch | |
375 | if head['bin_patch']: |
|
375 | if head['bin_patch']: | |
376 | stats['ops'][BIN_FILENODE] = 'binary diff not shown' |
|
376 | stats['ops'][BIN_FILENODE] = 'binary diff not shown' | |
377 | chunks = [] |
|
377 | chunks = [] | |
378 |
|
378 | |||
379 | if op == 'removed' and chunks: |
|
379 | if op == 'removed' and chunks: | |
380 | # a way of seeing deleted content could perhaps be nice - but |
|
380 | # a way of seeing deleted content could perhaps be nice - but | |
381 | # not with the current UI |
|
381 | # not with the current UI | |
382 | chunks = [] |
|
382 | chunks = [] | |
383 |
|
383 | |||
384 | chunks.insert(0, [{ |
|
384 | chunks.insert(0, [{ | |
385 | 'old_lineno': '', |
|
385 | 'old_lineno': '', | |
386 | 'new_lineno': '', |
|
386 | 'new_lineno': '', | |
387 | 'action': 'context', |
|
387 | 'action': 'context', | |
388 | 'line': msg, |
|
388 | 'line': msg, | |
389 | } for _op, msg in stats['ops'].items() |
|
389 | } for _op, msg in stats['ops'].items() | |
390 | if _op not in [MOD_FILENODE]]) |
|
390 | if _op not in [MOD_FILENODE]]) | |
391 |
|
391 | |||
392 | _files.append({ |
|
392 | _files.append({ | |
393 | 'old_filename': head['a_path'], |
|
393 | 'old_filename': head['a_path'], | |
394 | 'filename': head['b_path'], |
|
394 | 'filename': head['b_path'], | |
395 | 'old_revision': head['a_blob_id'], |
|
395 | 'old_revision': head['a_blob_id'], | |
396 | 'new_revision': head['b_blob_id'], |
|
396 | 'new_revision': head['b_blob_id'], | |
397 | 'chunks': chunks, |
|
397 | 'chunks': chunks, | |
398 | 'operation': op, |
|
398 | 'operation': op, | |
399 | 'stats': stats, |
|
399 | 'stats': stats, | |
400 | }) |
|
400 | }) | |
401 |
|
401 | |||
402 | if not inline_diff: |
|
402 | if not inline_diff: | |
403 | return _files |
|
403 | return _files | |
404 |
|
404 | |||
405 | # highlight inline changes when one del is followed by one add |
|
405 | # highlight inline changes when one del is followed by one add | |
406 | for diff_data in _files: |
|
406 | for diff_data in _files: | |
407 | for chunk in diff_data['chunks']: |
|
407 | for chunk in diff_data['chunks']: | |
408 | lineiter = iter(chunk) |
|
408 | lineiter = iter(chunk) | |
409 | try: |
|
409 | try: | |
410 | peekline = next(lineiter) |
|
410 | peekline = next(lineiter) | |
411 | while True: |
|
411 | while True: | |
412 | # find a first del line |
|
412 | # find a first del line | |
413 | while peekline['action'] != 'del': |
|
413 | while peekline['action'] != 'del': | |
414 | peekline = next(lineiter) |
|
414 | peekline = next(lineiter) | |
415 | delline = peekline |
|
415 | delline = peekline | |
416 | peekline = next(lineiter) |
|
416 | peekline = next(lineiter) | |
417 | # if not followed by add, eat all following del lines |
|
417 | # if not followed by add, eat all following del lines | |
418 | if peekline['action'] != 'add': |
|
418 | if peekline['action'] != 'add': | |
419 | while peekline['action'] == 'del': |
|
419 | while peekline['action'] == 'del': | |
420 | peekline = next(lineiter) |
|
420 | peekline = next(lineiter) | |
421 | continue |
|
421 | continue | |
422 | # found an add - make sure it is the only one |
|
422 | # found an add - make sure it is the only one | |
423 | addline = peekline |
|
423 | addline = peekline | |
424 | try: |
|
424 | try: | |
425 | peekline = next(lineiter) |
|
425 | peekline = next(lineiter) | |
426 | except StopIteration: |
|
426 | except StopIteration: | |
427 | # add was last line - ok |
|
427 | # add was last line - ok | |
428 | _highlight_inline_diff(delline, addline) |
|
428 | _highlight_inline_diff(delline, addline) | |
429 | raise |
|
429 | raise | |
430 | if peekline['action'] != 'add': |
|
430 | if peekline['action'] != 'add': | |
431 | # there was only one add line - ok |
|
431 | # there was only one add line - ok | |
432 | _highlight_inline_diff(delline, addline) |
|
432 | _highlight_inline_diff(delline, addline) | |
433 | except StopIteration: |
|
433 | except StopIteration: | |
434 | pass |
|
434 | pass | |
435 |
|
435 | |||
436 | return _files |
|
436 | return _files | |
437 |
|
437 | |||
438 | def stat(self): |
|
438 | def stat(self): | |
439 | """ |
|
439 | """ | |
440 | Returns tuple of added, and removed lines for this instance |
|
440 | Returns tuple of added, and removed lines for this instance | |
441 | """ |
|
441 | """ | |
442 | return self.adds, self.removes |
|
442 | return self.adds, self.removes | |
443 |
|
443 | |||
444 |
|
444 | |||
445 | _escape_re = re.compile(r'(&)|(<)|(>)|(\t)($)?|(\r)|( $)') |
|
445 | _escape_re = re.compile(r'(&)|(<)|(>)|(\t)($)?|(\r)|( $)') | |
446 |
|
446 | |||
447 |
|
447 | |||
448 | def _escaper(diff_line): |
|
448 | def _escaper(diff_line): | |
449 | r""" |
|
449 | r""" | |
450 | Do HTML escaping/markup of a single diff line (including first +/- column) |
|
450 | Do HTML escaping/markup of a single diff line (including first +/- column) | |
451 |
|
451 | |||
452 | >>> _escaper('foobar') |
|
452 | >>> _escaper('foobar') | |
453 | 'foobar' |
|
453 | 'foobar' | |
454 | >>> _escaper('@foo & bar') |
|
454 | >>> _escaper('@foo & bar') | |
455 | '@foo & bar' |
|
455 | '@foo & bar' | |
456 | >>> _escaper('+foo < bar') |
|
456 | >>> _escaper('+foo < bar') | |
457 | '+foo < bar' |
|
457 | '+foo < bar' | |
458 | >>> _escaper('-foo > bar') |
|
458 | >>> _escaper('-foo > bar') | |
459 | '-foo > bar' |
|
459 | '-foo > bar' | |
460 | >>> _escaper(' <foo>') |
|
460 | >>> _escaper(' <foo>') | |
461 | ' <foo>' |
|
461 | ' <foo>' | |
462 | >>> _escaper(' foo\tbar') |
|
462 | >>> _escaper(' foo\tbar') | |
463 | ' foo<u>\t</u>bar' |
|
463 | ' foo<u>\t</u>bar' | |
464 | >>> _escaper(' foo\rbar\r') |
|
464 | >>> _escaper(' foo\rbar\r') | |
465 | ' foo<u class="cr"></u>bar<u class="cr"></u>' |
|
465 | ' foo<u class="cr"></u>bar<u class="cr"></u>' | |
466 | >>> _escaper(' foo\t') |
|
466 | >>> _escaper(' foo\t') | |
467 | ' foo<u>\t</u><i></i>' |
|
467 | ' foo<u>\t</u><i></i>' | |
468 | >>> _escaper(' foo ') |
|
468 | >>> _escaper(' foo ') | |
469 | ' foo <i></i>' |
|
469 | ' foo <i></i>' | |
470 | >>> _escaper(' foo ') |
|
470 | >>> _escaper(' foo ') | |
471 | ' foo <i></i>' |
|
471 | ' foo <i></i>' | |
472 | >>> _escaper(' ') |
|
472 | >>> _escaper(' ') | |
473 | ' ' |
|
473 | ' ' | |
474 | >>> _escaper(' ') |
|
474 | >>> _escaper(' ') | |
475 | ' <i></i>' |
|
475 | ' <i></i>' | |
476 | >>> _escaper(' \t') |
|
476 | >>> _escaper(' \t') | |
477 | ' <u>\t</u><i></i>' |
|
477 | ' <u>\t</u><i></i>' | |
478 | >>> _escaper(' \t ') |
|
478 | >>> _escaper(' \t ') | |
479 | ' <u>\t</u> <i></i>' |
|
479 | ' <u>\t</u> <i></i>' | |
480 | >>> _escaper(' \t') |
|
480 | >>> _escaper(' \t') | |
481 | ' <u>\t</u><i></i>' |
|
481 | ' <u>\t</u><i></i>' | |
482 | >>> _escaper(' \t\t ') |
|
482 | >>> _escaper(' \t\t ') | |
483 | ' <u>\t</u><u>\t</u> <i></i>' |
|
483 | ' <u>\t</u><u>\t</u> <i></i>' | |
484 | >>> _escaper(' \t\t') |
|
484 | >>> _escaper(' \t\t') | |
485 | ' <u>\t</u><u>\t</u><i></i>' |
|
485 | ' <u>\t</u><u>\t</u><i></i>' | |
486 | >>> _escaper(' foo&bar<baz> ') |
|
486 | >>> _escaper(' foo&bar<baz> ') | |
487 | ' foo&bar<baz> <i></i>' |
|
487 | ' foo&bar<baz> <i></i>' | |
488 | """ |
|
488 | """ | |
489 |
|
489 | |||
490 | def substitute(m): |
|
490 | def substitute(m): | |
491 | groups = m.groups() |
|
491 | groups = m.groups() | |
492 | if groups[0]: |
|
492 | if groups[0]: | |
493 | return '&' |
|
493 | return '&' | |
494 | if groups[1]: |
|
494 | if groups[1]: | |
495 | return '<' |
|
495 | return '<' | |
496 | if groups[2]: |
|
496 | if groups[2]: | |
497 | return '>' |
|
497 | return '>' | |
498 | if groups[3]: |
|
498 | if groups[3]: | |
499 | if groups[4] is not None: # end of line |
|
499 | if groups[4] is not None: # end of line | |
500 | return '<u>\t</u><i></i>' |
|
500 | return '<u>\t</u><i></i>' | |
501 | return '<u>\t</u>' |
|
501 | return '<u>\t</u>' | |
502 | if groups[5]: |
|
502 | if groups[5]: | |
503 | return '<u class="cr"></u>' |
|
503 | return '<u class="cr"></u>' | |
504 | if groups[6]: |
|
504 | if groups[6]: | |
505 | if m.start() == 0: |
|
505 | if m.start() == 0: | |
506 | return ' ' # first column space shouldn't make empty lines show up as trailing space |
|
506 | return ' ' # first column space shouldn't make empty lines show up as trailing space | |
507 | return ' <i></i>' |
|
507 | return ' <i></i>' | |
508 | assert False |
|
508 | assert False | |
509 |
|
509 | |||
510 | return _escape_re.sub(substitute, diff_line) |
|
510 | return _escape_re.sub(substitute, diff_line) | |
511 |
|
511 | |||
512 |
|
512 | |||
513 | _git_header_re = re.compile(br""" |
|
513 | _git_header_re = re.compile(br""" | |
514 | ^diff[ ]--git[ ]a/(?P<a_path>.+?)[ ]b/(?P<b_path>.+?)\n |
|
514 | ^diff[ ]--git[ ]a/(?P<a_path>.+?)[ ]b/(?P<b_path>.+?)\n | |
515 | (?:^old[ ]mode[ ](?P<old_mode>\d+)\n |
|
515 | (?:^old[ ]mode[ ](?P<old_mode>\d+)\n | |
516 | ^new[ ]mode[ ](?P<new_mode>\d+)(?:\n|$))? |
|
516 | ^new[ ]mode[ ](?P<new_mode>\d+)(?:\n|$))? | |
517 | (?:^similarity[ ]index[ ](?P<similarity_index>\d+)%\n |
|
517 | (?:^similarity[ ]index[ ](?P<similarity_index>\d+)%\n | |
518 | ^rename[ ]from[ ](?P<rename_from>.+)\n |
|
518 | ^rename[ ]from[ ](?P<rename_from>.+)\n | |
519 | ^rename[ ]to[ ](?P<rename_to>.+)(?:\n|$))? |
|
519 | ^rename[ ]to[ ](?P<rename_to>.+)(?:\n|$))? | |
520 | (?:^new[ ]file[ ]mode[ ](?P<new_file_mode>.+)(?:\n|$))? |
|
520 | (?:^new[ ]file[ ]mode[ ](?P<new_file_mode>.+)(?:\n|$))? | |
521 | (?:^deleted[ ]file[ ]mode[ ](?P<deleted_file_mode>.+)(?:\n|$))? |
|
521 | (?:^deleted[ ]file[ ]mode[ ](?P<deleted_file_mode>.+)(?:\n|$))? | |
522 | (?:^index[ ](?P<a_blob_id>[0-9A-Fa-f]+) |
|
522 | (?:^index[ ](?P<a_blob_id>[0-9A-Fa-f]+) | |
523 | \.\.(?P<b_blob_id>[0-9A-Fa-f]+)[ ]?(?P<b_mode>.+)?(?:\n|$))? |
|
523 | \.\.(?P<b_blob_id>[0-9A-Fa-f]+)[ ]?(?P<b_mode>.+)?(?:\n|$))? | |
524 | (?:^(?P<bin_patch>GIT[ ]binary[ ]patch)(?:\n|$))? |
|
524 | (?:^(?P<bin_patch>GIT[ ]binary[ ]patch)(?:\n|$))? | |
525 | (?:^---[ ](a/(?P<a_file>.+?)|/dev/null)\t?(?:\n|$))? |
|
525 | (?:^---[ ](a/(?P<a_file>.+?)|/dev/null)\t?(?:\n|$))? | |
526 | (?:^\+\+\+[ ](b/(?P<b_file>.+?)|/dev/null)\t?(?:\n|$))? |
|
526 | (?:^\+\+\+[ ](b/(?P<b_file>.+?)|/dev/null)\t?(?:\n|$))? | |
527 | """, re.VERBOSE | re.MULTILINE) |
|
527 | """, re.VERBOSE | re.MULTILINE) | |
528 |
|
528 | |||
529 |
|
529 | |||
530 | _hg_header_re = re.compile(br""" |
|
530 | _hg_header_re = re.compile(br""" | |
531 | ^diff[ ]--git[ ]a/(?P<a_path>.+?)[ ]b/(?P<b_path>.+?)\n |
|
531 | ^diff[ ]--git[ ]a/(?P<a_path>.+?)[ ]b/(?P<b_path>.+?)\n | |
532 | (?:^old[ ]mode[ ](?P<old_mode>\d+)\n |
|
532 | (?:^old[ ]mode[ ](?P<old_mode>\d+)\n | |
533 | ^new[ ]mode[ ](?P<new_mode>\d+)(?:\n|$))? |
|
533 | ^new[ ]mode[ ](?P<new_mode>\d+)(?:\n|$))? | |
534 | (?:^similarity[ ]index[ ](?P<similarity_index>\d+)%(?:\n|$))? |
|
534 | (?:^similarity[ ]index[ ](?P<similarity_index>\d+)%(?:\n|$))? | |
535 | (?:^rename[ ]from[ ](?P<rename_from>.+)\n |
|
535 | (?:^rename[ ]from[ ](?P<rename_from>.+)\n | |
536 | ^rename[ ]to[ ](?P<rename_to>.+)(?:\n|$))? |
|
536 | ^rename[ ]to[ ](?P<rename_to>.+)(?:\n|$))? | |
537 | (?:^copy[ ]from[ ](?P<copy_from>.+)\n |
|
537 | (?:^copy[ ]from[ ](?P<copy_from>.+)\n | |
538 | ^copy[ ]to[ ](?P<copy_to>.+)(?:\n|$))? |
|
538 | ^copy[ ]to[ ](?P<copy_to>.+)(?:\n|$))? | |
539 | (?:^new[ ]file[ ]mode[ ](?P<new_file_mode>.+)(?:\n|$))? |
|
539 | (?:^new[ ]file[ ]mode[ ](?P<new_file_mode>.+)(?:\n|$))? | |
540 | (?:^deleted[ ]file[ ]mode[ ](?P<deleted_file_mode>.+)(?:\n|$))? |
|
540 | (?:^deleted[ ]file[ ]mode[ ](?P<deleted_file_mode>.+)(?:\n|$))? | |
541 | (?:^index[ ](?P<a_blob_id>[0-9A-Fa-f]+) |
|
541 | (?:^index[ ](?P<a_blob_id>[0-9A-Fa-f]+) | |
542 | \.\.(?P<b_blob_id>[0-9A-Fa-f]+)[ ]?(?P<b_mode>.+)?(?:\n|$))? |
|
542 | \.\.(?P<b_blob_id>[0-9A-Fa-f]+)[ ]?(?P<b_mode>.+)?(?:\n|$))? | |
543 | (?:^(?P<bin_patch>GIT[ ]binary[ ]patch)(?:\n|$))? |
|
543 | (?:^(?P<bin_patch>GIT[ ]binary[ ]patch)(?:\n|$))? | |
544 | (?:^---[ ](a/(?P<a_file>.+?)|/dev/null)\t?(?:\n|$))? |
|
544 | (?:^---[ ](a/(?P<a_file>.+?)|/dev/null)\t?(?:\n|$))? | |
545 | (?:^\+\+\+[ ](b/(?P<b_file>.+?)|/dev/null)\t?(?:\n|$))? |
|
545 | (?:^\+\+\+[ ](b/(?P<b_file>.+?)|/dev/null)\t?(?:\n|$))? | |
546 | """, re.VERBOSE | re.MULTILINE) |
|
546 | """, re.VERBOSE | re.MULTILINE) | |
547 |
|
547 | |||
548 |
|
548 | |||
549 | _header_next_check = re.compile(br'''(?!@)(?!literal )(?!delta )''') |
|
549 | _header_next_check = re.compile(br'''(?!@)(?!literal )(?!delta )''') | |
550 |
|
550 | |||
551 |
|
551 | |||
552 | def _get_header(vcs, diff_chunk): |
|
552 | def _get_header(vcs, diff_chunk): | |
553 | """ |
|
553 | """ | |
554 | Parses a Git diff for a single file (header and chunks) and returns a tuple with: |
|
554 | Parses a Git diff for a single file (header and chunks) and returns a tuple with: | |
555 |
|
555 | |||
556 | 1. A dict with meta info: |
|
556 | 1. A dict with meta info: | |
557 |
|
557 | |||
558 | a_path, b_path, similarity_index, rename_from, rename_to, |
|
558 | a_path, b_path, similarity_index, rename_from, rename_to, | |
559 | old_mode, new_mode, new_file_mode, deleted_file_mode, |
|
559 | old_mode, new_mode, new_file_mode, deleted_file_mode, | |
560 | a_blob_id, b_blob_id, b_mode, a_file, b_file |
|
560 | a_blob_id, b_blob_id, b_mode, a_file, b_file | |
561 |
|
561 | |||
562 | 2. An iterator yielding lines with simple HTML markup. |
|
562 | 2. An iterator yielding lines with simple HTML markup. | |
563 | """ |
|
563 | """ | |
564 | match = None |
|
564 | match = None | |
565 | if vcs == 'git': |
|
565 | if vcs == 'git': | |
566 | match = _git_header_re.match(diff_chunk) |
|
566 | match = _git_header_re.match(diff_chunk) | |
567 | elif vcs == 'hg': |
|
567 | elif vcs == 'hg': | |
568 | match = _hg_header_re.match(diff_chunk) |
|
568 | match = _hg_header_re.match(diff_chunk) | |
569 | if match is None: |
|
569 | if match is None: | |
570 | raise Exception('diff not recognized as valid %s diff' % vcs) |
|
570 | raise Exception('diff not recognized as valid %s diff' % vcs) | |
571 | meta_info = {k: None if v is None else safe_str(v) for k, v in match.groupdict().items()} |
|
571 | meta_info = {k: None if v is None else safe_str(v) for k, v in match.groupdict().items()} | |
572 | rest = diff_chunk[match.end():] |
|
572 | rest = diff_chunk[match.end():] | |
573 | if rest: |
|
573 | if rest: | |
574 | if _header_next_check.match(rest): |
|
574 | if _header_next_check.match(rest): | |
575 | raise Exception('cannot parse %s diff header: %r followed by %r' % (vcs, safe_str(bytes(diff_chunk[:match.end()])), safe_str(bytes(rest[:1000])))) |
|
575 | raise Exception('cannot parse %s diff header: %r followed by %r' % (vcs, safe_str(bytes(diff_chunk[:match.end()])), safe_str(bytes(rest[:1000])))) | |
576 | if rest[-1:] != b'\n': |
|
576 | if rest[-1:] != b'\n': | |
577 | # The diff will generally already have trailing \n (and be a memoryview). It might also be huge so we don't want to allocate it twice. But in this very rare case, we don't care. |
|
577 | # The diff will generally already have trailing \n (and be a memoryview). It might also be huge so we don't want to allocate it twice. But in this very rare case, we don't care. | |
578 | rest = bytes(rest) + b'\n' |
|
578 | rest = bytes(rest) + b'\n' | |
579 | diff_lines = (_escaper(safe_str(m.group(1))) for m in re.finditer(br'(.*)\n', rest)) |
|
579 | diff_lines = (_escaper(safe_str(m.group(1))) for m in re.finditer(br'(.*)\n', rest)) | |
580 | return meta_info, diff_lines |
|
580 | return meta_info, diff_lines | |
581 |
|
581 | |||
582 |
|
582 | |||
583 | _chunk_re = re.compile(r'^@@ -(\d+)(?:,(\d+))? \+(\d+)(?:,(\d+))? @@(.*)') |
|
583 | _chunk_re = re.compile(r'^@@ -(\d+)(?:,(\d+))? \+(\d+)(?:,(\d+))? @@(.*)') | |
584 | _newline_marker = re.compile(r'^\\ No newline at end of file') |
|
584 | _newline_marker = re.compile(r'^\\ No newline at end of file') | |
585 |
|
585 | |||
586 |
|
586 | |||
587 | def _parse_lines(diff_lines): |
|
587 | def _parse_lines(diff_lines): | |
588 | """ |
|
588 | """ | |
589 | Given an iterator of diff body lines, parse them and return a dict per |
|
589 | Given an iterator of diff body lines, parse them and return a dict per | |
590 | line and added/removed totals. |
|
590 | line and added/removed totals. | |
591 | """ |
|
591 | """ | |
592 | added = deleted = 0 |
|
592 | added = deleted = 0 | |
593 | old_line = old_end = new_line = new_end = None |
|
593 | old_line = old_end = new_line = new_end = None | |
594 |
|
594 | |||
595 | chunks = [] |
|
595 | chunks = [] | |
596 | try: |
|
596 | try: | |
597 | line = next(diff_lines) |
|
597 | line = next(diff_lines) | |
598 |
|
598 | |||
599 | while True: |
|
599 | while True: | |
600 | lines = [] |
|
600 | lines = [] | |
601 | chunks.append(lines) |
|
601 | chunks.append(lines) | |
602 |
|
602 | |||
603 | match = _chunk_re.match(line) |
|
603 | match = _chunk_re.match(line) | |
604 |
|
604 | |||
605 | if not match: |
|
605 | if not match: | |
606 | raise Exception('error parsing diff @@ line %r' % line) |
|
606 | raise Exception('error parsing diff @@ line %r' % line) | |
607 |
|
607 | |||
608 | gr = match.groups() |
|
608 | gr = match.groups() | |
609 | (old_line, old_end, |
|
609 | (old_line, old_end, | |
610 | new_line, new_end) = [int(x or 1) for x in gr[:-1]] |
|
610 | new_line, new_end) = [int(x or 1) for x in gr[:-1]] | |
611 | old_line -= 1 |
|
611 | old_line -= 1 | |
612 | new_line -= 1 |
|
612 | new_line -= 1 | |
613 |
|
613 | |||
614 | context = len(gr) == 5 |
|
614 | context = len(gr) == 5 | |
615 | old_end += old_line |
|
615 | old_end += old_line | |
616 | new_end += new_line |
|
616 | new_end += new_line | |
617 |
|
617 | |||
618 | if context: |
|
618 | if context: | |
619 | # skip context only if it's first line |
|
619 | # skip context only if it's first line | |
620 | if int(gr[0]) > 1: |
|
620 | if int(gr[0]) > 1: | |
621 | lines.append({ |
|
621 | lines.append({ | |
622 | 'old_lineno': '', |
|
622 | 'old_lineno': '', | |
623 | 'new_lineno': '', |
|
623 | 'new_lineno': '', | |
624 | 'action': 'context', |
|
624 | 'action': 'context', | |
625 | 'line': line, |
|
625 | 'line': line, | |
626 | }) |
|
626 | }) | |
627 |
|
627 | |||
628 | line = next(diff_lines) |
|
628 | line = next(diff_lines) | |
629 |
|
629 | |||
630 | while old_line < old_end or new_line < new_end: |
|
630 | while old_line < old_end or new_line < new_end: | |
631 | if not line: |
|
631 | if not line: | |
632 | raise Exception('error parsing diff - empty line at -%s+%s' % (old_line, new_line)) |
|
632 | raise Exception('error parsing diff - empty line at -%s+%s' % (old_line, new_line)) | |
633 |
|
633 | |||
634 | affects_old = affects_new = False |
|
634 | affects_old = affects_new = False | |
635 |
|
635 | |||
636 | command = line[0] |
|
636 | command = line[0] | |
637 | if command == '+': |
|
637 | if command == '+': | |
638 | affects_new = True |
|
638 | affects_new = True | |
639 | action = 'add' |
|
639 | action = 'add' | |
640 | added += 1 |
|
640 | added += 1 | |
641 | elif command == '-': |
|
641 | elif command == '-': | |
642 | affects_old = True |
|
642 | affects_old = True | |
643 | action = 'del' |
|
643 | action = 'del' | |
644 | deleted += 1 |
|
644 | deleted += 1 | |
645 | elif command == ' ': |
|
645 | elif command == ' ': | |
646 | affects_old = affects_new = True |
|
646 | affects_old = affects_new = True | |
647 | action = 'unmod' |
|
647 | action = 'unmod' | |
648 | else: |
|
648 | else: | |
649 | raise Exception('error parsing diff - unknown command in line %r at -%s+%s' % (line, old_line, new_line)) |
|
649 | raise Exception('error parsing diff - unknown command in line %r at -%s+%s' % (line, old_line, new_line)) | |
650 |
|
650 | |||
651 | if not _newline_marker.match(line): |
|
651 | if not _newline_marker.match(line): | |
652 | old_line += affects_old |
|
652 | old_line += affects_old | |
653 | new_line += affects_new |
|
653 | new_line += affects_new | |
654 | lines.append({ |
|
654 | lines.append({ | |
655 | 'old_lineno': affects_old and old_line or '', |
|
655 | 'old_lineno': affects_old and old_line or '', | |
656 | 'new_lineno': affects_new and new_line or '', |
|
656 | 'new_lineno': affects_new and new_line or '', | |
657 | 'action': action, |
|
657 | 'action': action, | |
658 | 'line': line[1:], |
|
658 | 'line': line[1:], | |
659 | }) |
|
659 | }) | |
660 |
|
660 | |||
661 | line = next(diff_lines) |
|
661 | line = next(diff_lines) | |
662 |
|
662 | |||
663 | if _newline_marker.match(line): |
|
663 | if _newline_marker.match(line): | |
664 | # we need to append to lines, since this is not |
|
664 | # we need to append to lines, since this is not | |
665 | # counted in the line specs of diff |
|
665 | # counted in the line specs of diff | |
666 | lines.append({ |
|
666 | lines.append({ | |
667 | 'old_lineno': '', |
|
667 | 'old_lineno': '', | |
668 | 'new_lineno': '', |
|
668 | 'new_lineno': '', | |
669 | 'action': 'context', |
|
669 | 'action': 'context', | |
670 | 'line': line, |
|
670 | 'line': line, | |
671 | }) |
|
671 | }) | |
672 | line = next(diff_lines) |
|
672 | line = next(diff_lines) | |
673 | if old_line > old_end: |
|
673 | if old_line > old_end: | |
674 | raise Exception('error parsing diff - more than %s "-" lines at -%s+%s' % (old_end, old_line, new_line)) |
|
674 | raise Exception('error parsing diff - more than %s "-" lines at -%s+%s' % (old_end, old_line, new_line)) | |
675 | if new_line > new_end: |
|
675 | if new_line > new_end: | |
676 | raise Exception('error parsing diff - more than %s "+" lines at -%s+%s' % (new_end, old_line, new_line)) |
|
676 | raise Exception('error parsing diff - more than %s "+" lines at -%s+%s' % (new_end, old_line, new_line)) | |
677 | except StopIteration: |
|
677 | except StopIteration: | |
678 | pass |
|
678 | pass | |
679 | if old_line != old_end or new_line != new_end: |
|
679 | if old_line != old_end or new_line != new_end: | |
680 | raise Exception('diff processing broken when old %s<>%s or new %s<>%s line %r' % (old_line, old_end, new_line, new_end, line)) |
|
680 | raise Exception('diff processing broken when old %s<>%s or new %s<>%s line %r' % (old_line, old_end, new_line, new_end, line)) | |
681 |
|
681 | |||
682 | return chunks, added, deleted |
|
682 | return chunks, added, deleted | |
683 |
|
683 | |||
684 | # Used for inline highlighter word split, must match the substitutions in _escaper |
|
684 | # Used for inline highlighter word split, must match the substitutions in _escaper | |
685 | _token_re = re.compile(r'()(&|<|>|<u>\t</u>|<u class="cr"></u>| <i></i>|\W+?)') |
|
685 | _token_re = re.compile(r'()(&|<|>|<u>\t</u>|<u class="cr"></u>| <i></i>|\W+?)') | |
686 |
|
686 | |||
687 |
|
687 | |||
688 | def _highlight_inline_diff(old, new): |
|
688 | def _highlight_inline_diff(old, new): | |
689 | """ |
|
689 | """ | |
690 | Highlight simple add/remove in two lines given as info dicts. They are |
|
690 | Highlight simple add/remove in two lines given as info dicts. They are | |
691 | modified in place and given markup with <del>/<ins>. |
|
691 | modified in place and given markup with <del>/<ins>. | |
692 | """ |
|
692 | """ | |
693 | assert old['action'] == 'del' |
|
693 | assert old['action'] == 'del' | |
694 | assert new['action'] == 'add' |
|
694 | assert new['action'] == 'add' | |
695 |
|
695 | |||
696 | oldwords = _token_re.split(old['line']) |
|
696 | oldwords = _token_re.split(old['line']) | |
697 | newwords = _token_re.split(new['line']) |
|
697 | newwords = _token_re.split(new['line']) | |
698 | sequence = difflib.SequenceMatcher(None, oldwords, newwords) |
|
698 | sequence = difflib.SequenceMatcher(None, oldwords, newwords) | |
699 |
|
699 | |||
700 | oldfragments, newfragments = [], [] |
|
700 | oldfragments, newfragments = [], [] | |
701 | for tag, i1, i2, j1, j2 in sequence.get_opcodes(): |
|
701 | for tag, i1, i2, j1, j2 in sequence.get_opcodes(): | |
702 | oldfrag = ''.join(oldwords[i1:i2]) |
|
702 | oldfrag = ''.join(oldwords[i1:i2]) | |
703 | newfrag = ''.join(newwords[j1:j2]) |
|
703 | newfrag = ''.join(newwords[j1:j2]) | |
704 | if tag != 'equal': |
|
704 | if tag != 'equal': | |
705 | if oldfrag: |
|
705 | if oldfrag: | |
706 | oldfrag = '<del>%s</del>' % oldfrag |
|
706 | oldfrag = '<del>%s</del>' % oldfrag | |
707 | if newfrag: |
|
707 | if newfrag: | |
708 | newfrag = '<ins>%s</ins>' % newfrag |
|
708 | newfrag = '<ins>%s</ins>' % newfrag | |
709 | oldfragments.append(oldfrag) |
|
709 | oldfragments.append(oldfrag) | |
710 | newfragments.append(newfrag) |
|
710 | newfragments.append(newfrag) | |
711 |
|
711 | |||
712 | old['line'] = "".join(oldfragments) |
|
712 | old['line'] = "".join(oldfragments) | |
713 | new['line'] = "".join(newfragments) |
|
713 | new['line'] = "".join(newfragments) |
General Comments 0
You need to be logged in to leave comments.
Login now