Source

RhodeCode / rhodecode / lib / vcs / utils / diffs.py

Full commit
  1
  2
  3
  4
  5
  6
  7
  8
  9
 10
 11
 12
 13
 14
 15
 16
 17
 18
 19
 20
 21
 22
 23
 24
 25
 26
 27
 28
 29
 30
 31
 32
 33
 34
 35
 36
 37
 38
 39
 40
 41
 42
 43
 44
 45
 46
 47
 48
 49
 50
 51
 52
 53
 54
 55
 56
 57
 58
 59
 60
 61
 62
 63
 64
 65
 66
 67
 68
 69
 70
 71
 72
 73
 74
 75
 76
 77
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
# -*- coding: utf-8 -*-
# original copyright: 2007-2008 by Armin Ronacher
# licensed under the BSD license.

import re
import difflib
import logging

from difflib import unified_diff
from itertools import tee, imap

from mercurial.match import match

from rhodecode.lib.vcs.exceptions import VCSError
from rhodecode.lib.vcs.nodes import FileNode, NodeError


def get_udiff(filenode_old, filenode_new, show_whitespace=True):
    """
    Returns unified diff between given ``filenode_old`` and ``filenode_new``.
    """
    try:
        filenode_old_date = filenode_old.changeset.date
    except NodeError:
        filenode_old_date = None

    try:
        filenode_new_date = filenode_new.changeset.date
    except NodeError:
        filenode_new_date = None

    for filenode in (filenode_old, filenode_new):
        if not isinstance(filenode, FileNode):
            raise VCSError("Given object should be FileNode object, not %s"
                % filenode.__class__)

    if filenode_old_date and filenode_new_date:
        if not filenode_old_date < filenode_new_date:
            logging.debug("Generating udiff for filenodes with not increasing "
                "dates")

    vcs_udiff = unified_diff(filenode_old.content.splitlines(True),
                               filenode_new.content.splitlines(True),
                               filenode_old.name,
                               filenode_new.name,
                               filenode_old_date,
                               filenode_old_date)
    return vcs_udiff


def get_gitdiff(filenode_old, filenode_new, ignore_whitespace=True):
    """
    Returns git style diff between given ``filenode_old`` and ``filenode_new``.

    :param ignore_whitespace: ignore whitespaces in diff
    """

    for filenode in (filenode_old, filenode_new):
        if not isinstance(filenode, FileNode):
            raise VCSError("Given object should be FileNode object, not %s"
                % filenode.__class__)

    old_raw_id = getattr(filenode_old.changeset, 'raw_id', '0' * 40)
    new_raw_id = getattr(filenode_new.changeset, 'raw_id', '0' * 40)

    repo = filenode_new.changeset.repository
    vcs_gitdiff = repo._get_diff(old_raw_id, new_raw_id, filenode_new.path,
                                 ignore_whitespace)

    return vcs_gitdiff


class DiffProcessor(object):
    """
    Give it a unified diff and it returns a list of the files that were
    mentioned in the diff together with a dict of meta information that
    can be used to render it in a HTML template.
    """
    _chunk_re = re.compile(r'@@ -(\d+)(?:,(\d+))? \+(\d+)(?:,(\d+))? @@(.*)')

    def __init__(self, diff, differ='diff', format='udiff'):
        """
        :param diff:   a text in diff format or generator
        :param format: format of diff passed, `udiff` or `gitdiff`
        """
        if isinstance(diff, basestring):
            diff = [diff]

        self.__udiff = diff
        self.__format = format
        self.adds = 0
        self.removes = 0

        if isinstance(self.__udiff, basestring):
            self.lines = iter(self.__udiff.splitlines(1))

        elif self.__format == 'gitdiff':
            udiff_copy = self.copy_iterator()
            self.lines = imap(self.escaper, self._parse_gitdiff(udiff_copy))
        else:
            udiff_copy = self.copy_iterator()
            self.lines = imap(self.escaper, udiff_copy)

        # Select a differ.
        if differ == 'difflib':
            self.differ = self._highlight_line_difflib
        else:
            self.differ = self._highlight_line_udiff

    def escaper(self, string):
        return string.replace('<', '&lt;').replace('>', '&gt;')

    def copy_iterator(self):
        """
        make a fresh copy of generator, we should not iterate thru
        an original as it's needed for repeating operations on
        this instance of DiffProcessor
        """
        self.__udiff, iterator_copy = tee(self.__udiff)
        return iterator_copy

    def _extract_rev(self, line1, line2):
        """
        Extract the filename and revision hint from a line.
        """

        try:
            if line1.startswith('--- ') and line2.startswith('+++ '):
                l1 = line1[4:].split(None, 1)
                old_filename = l1[0].lstrip('a/') if len(l1) >= 1 else None
                old_rev = l1[1] if len(l1) == 2 else 'old'

                l2 = line2[4:].split(None, 1)
                new_filename = l2[0].lstrip('b/') if len(l1) >= 1 else None
                new_rev = l2[1] if len(l2) == 2 else 'new'

                filename = old_filename if (old_filename !=
                                            'dev/null') else new_filename

                return filename, new_rev, old_rev
        except (ValueError, IndexError):
            pass

        return None, None, None

    def _parse_gitdiff(self, diffiterator):
        def line_decoder(l):
            if l.startswith('+') and not l.startswith('+++'):
                self.adds += 1
            elif l.startswith('-') and not l.startswith('---'):
                self.removes += 1
            return l.decode('utf8', 'replace')

        output = list(diffiterator)
        size = len(output)

        if size == 2:
            l = []
            l.extend([output[0]])
            l.extend(output[1].splitlines(1))
            return map(line_decoder, l)
        elif size == 1:
            return  map(line_decoder, output[0].splitlines(1))
        elif size == 0:
            return []

        raise Exception('wrong size of diff %s' % size)

    def _highlight_line_difflib(self, line, next):
        """
        Highlight inline changes in both lines.
        """

        if line['action'] == 'del':
            old, new = line, next
        else:
            old, new = next, line

        oldwords = re.split(r'(\W)', old['line'])
        newwords = re.split(r'(\W)', new['line'])

        sequence = difflib.SequenceMatcher(None, oldwords, newwords)

        oldfragments, newfragments = [], []
        for tag, i1, i2, j1, j2 in sequence.get_opcodes():
            oldfrag = ''.join(oldwords[i1:i2])
            newfrag = ''.join(newwords[j1:j2])
            if tag != 'equal':
                if oldfrag:
                    oldfrag = '<del>%s</del>' % oldfrag
                if newfrag:
                    newfrag = '<ins>%s</ins>' % newfrag
            oldfragments.append(oldfrag)
            newfragments.append(newfrag)

        old['line'] = "".join(oldfragments)
        new['line'] = "".join(newfragments)

    def _highlight_line_udiff(self, line, next):
        """
        Highlight inline changes in both lines.
        """
        start = 0
        limit = min(len(line['line']), len(next['line']))
        while start < limit and line['line'][start] == next['line'][start]:
            start += 1
        end = -1
        limit -= start
        while -end <= limit and line['line'][end] == next['line'][end]:
            end -= 1
        end += 1
        if start or end:
            def do(l):
                last = end + len(l['line'])
                if l['action'] == 'add':
                    tag = 'ins'
                else:
                    tag = 'del'
                l['line'] = '%s<%s>%s</%s>%s' % (
                    l['line'][:start],
                    tag,
                    l['line'][start:last],
                    tag,
                    l['line'][last:]
                )
            do(line)
            do(next)

    def _parse_udiff(self):
        """
        Parse the diff an return data for the template.
        """
        lineiter = self.lines
        files = []
        try:
            line = lineiter.next()
            # skip first context
            skipfirst = True
            while 1:
                # continue until we found the old file
                if not line.startswith('--- '):
                    line = lineiter.next()
                    continue

                chunks = []
                filename, old_rev, new_rev = \
                    self._extract_rev(line, lineiter.next())
                files.append({
                    'filename':         filename,
                    'old_revision':     old_rev,
                    'new_revision':     new_rev,
                    'chunks':           chunks
                })

                line = lineiter.next()
                while line:
                    match = self._chunk_re.match(line)
                    if not match:
                        break

                    lines = []
                    chunks.append(lines)

                    old_line, old_end, new_line, new_end = \
                        [int(x or 1) for x in match.groups()[:-1]]
                    old_line -= 1
                    new_line -= 1
                    context = len(match.groups()) == 5
                    old_end += old_line
                    new_end += new_line

                    if context:
                        if not skipfirst:
                            lines.append({
                                'old_lineno': '...',
                                'new_lineno': '...',
                                'action': 'context',
                                'line': line,
                            })
                        else:
                            skipfirst = False

                    line = lineiter.next()
                    while old_line < old_end or new_line < new_end:
                        if line:
                            command, line = line[0], line[1:]
                        else:
                            command = ' '
                        affects_old = affects_new = False

                        # ignore those if we don't expect them
                        if command in '#@':
                            continue
                        elif command == '+':
                            affects_new = True
                            action = 'add'
                        elif command == '-':
                            affects_old = True
                            action = 'del'
                        else:
                            affects_old = affects_new = True
                            action = 'unmod'

                        old_line += affects_old
                        new_line += affects_new
                        lines.append({
                            'old_lineno':   affects_old and old_line or '',
                            'new_lineno':   affects_new and new_line or '',
                            'action':       action,
                            'line':         line
                        })
                        line = lineiter.next()

        except StopIteration:
            pass

        # highlight inline changes
        for file in files:
            for chunk in chunks:
                lineiter = iter(chunk)
                #first = True
                try:
                    while 1:
                        line = lineiter.next()
                        if line['action'] != 'unmod':
                            nextline = lineiter.next()
                            if nextline['action'] == 'unmod' or \
                               nextline['action'] == line['action']:
                                continue
                            self.differ(line, nextline)
                except StopIteration:
                    pass

        return files

    def prepare(self):
        """
        Prepare the passed udiff for HTML rendering. It'l return a list
        of dicts
        """
        return self._parse_udiff()

    def _safe_id(self, idstring):
        """Make a string safe for including in an id attribute.

        The HTML spec says that id attributes 'must begin with
        a letter ([A-Za-z]) and may be followed by any number
        of letters, digits ([0-9]), hyphens ("-"), underscores
        ("_"), colons (":"), and periods (".")'. These regexps
        are slightly over-zealous, in that they remove colons
        and periods unnecessarily.

        Whitespace is transformed into underscores, and then
        anything which is not a hyphen or a character that
        matches \w (alphanumerics and underscore) is removed.

        """
        # Transform all whitespace to underscore
        idstring = re.sub(r'\s', "_", '%s' % idstring)
        # Remove everything that is not a hyphen or a member of \w
        idstring = re.sub(r'(?!-)\W', "", idstring).lower()
        return idstring

    def raw_diff(self):
        """
        Returns raw string as udiff
        """
        udiff_copy = self.copy_iterator()
        if self.__format == 'gitdiff':
            udiff_copy = self._parse_gitdiff(udiff_copy)
        return u''.join(udiff_copy)

    def as_html(self, table_class='code-difftable', line_class='line',
                new_lineno_class='lineno old', old_lineno_class='lineno new',
                code_class='code'):
        """
        Return udiff as html table with customized css classes
        """
        def _link_to_if(condition, label, url):
            """
            Generates a link if condition is meet or just the label if not.
            """

            if condition:
                return '''<a href="%(url)s">%(label)s</a>''' % {'url': url,
                                                                'label': label}
            else:
                return label
        diff_lines = self.prepare()
        _html_empty = True
        _html = []
        _html.append('''<table class="%(table_class)s">\n''' \
                                            % {'table_class': table_class})
        for diff in diff_lines:
            for line in diff['chunks']:
                _html_empty = False
                for change in line:
                    _html.append('''<tr class="%(line_class)s %(action)s">\n''' \
                        % {'line_class': line_class,
                           'action': change['action']})
                    anchor_old_id = ''
                    anchor_new_id = ''
                    anchor_old = "%(filename)s_o%(oldline_no)s" % \
                                {'filename': self._safe_id(diff['filename']),
                                 'oldline_no': change['old_lineno']}
                    anchor_new = "%(filename)s_n%(oldline_no)s" % \
                                {'filename': self._safe_id(diff['filename']),
                                 'oldline_no': change['new_lineno']}
                    cond_old = change['old_lineno'] != '...' and \
                                                        change['old_lineno']
                    cond_new = change['new_lineno'] != '...' and \
                                                        change['new_lineno']
                    if cond_old:
                        anchor_old_id = 'id="%s"' % anchor_old
                    if cond_new:
                        anchor_new_id = 'id="%s"' % anchor_new
                    ###########################################################
                    # OLD LINE NUMBER
                    ###########################################################
                    _html.append('''\t<td %(a_id)s class="%(old_lineno_cls)s">''' \
                                    % {'a_id': anchor_old_id,
                                       'old_lineno_cls': old_lineno_class})

                    _html.append('''<pre>%(link)s</pre>''' \
                        % {'link':
                        _link_to_if(cond_old, change['old_lineno'], '#%s' \
                                                                % anchor_old)})
                    _html.append('''</td>\n''')
                    ###########################################################
                    # NEW LINE NUMBER
                    ###########################################################

                    _html.append('''\t<td %(a_id)s class="%(new_lineno_cls)s">''' \
                                    % {'a_id': anchor_new_id,
                                       'new_lineno_cls': new_lineno_class})

                    _html.append('''<pre>%(link)s</pre>''' \
                        % {'link':
                        _link_to_if(cond_new, change['new_lineno'], '#%s' \
                                                                % anchor_new)})
                    _html.append('''</td>\n''')
                    ###########################################################
                    # CODE
                    ###########################################################
                    _html.append('''\t<td class="%(code_class)s">''' \
                                                % {'code_class': code_class})
                    _html.append('''\n\t\t<pre>%(code)s</pre>\n''' \
                                                % {'code': change['line']})
                    _html.append('''\t</td>''')
                    _html.append('''\n</tr>\n''')
        _html.append('''</table>''')
        if _html_empty:
            return None
        return ''.join(_html)

    def stat(self):
        """
        Returns tuple of adde,and removed lines for this instance
        """
        return self.adds, self.removes