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
|
from cStringIO import StringIO
from bzrlib.diff import internal_diff
from bzrlib.errors import BinaryFile
from bzrlib.patiencediff import (recurse_matches, SequenceMatcher, unique_lcs,
unified_diff, unified_diff_files)
from bzrlib.tests import TestCase, TestCaseInTempDir
def udiff_lines(old, new, allow_binary=False):
output = StringIO()
internal_diff('old', old, 'new', new, output, allow_binary)
output.seek(0, 0)
return output.readlines()
class TestDiff(TestCase):
def test_add_nl(self):
"""diff generates a valid diff for patches that add a newline"""
lines = udiff_lines(['boo'], ['boo\n'])
self.check_patch(lines)
self.assertEquals(lines[4], '\\ No newline at end of file\n')
## "expected no-nl, got %r" % lines[4]
def test_add_nl_2(self):
"""diff generates a valid diff for patches that change last line and
add a newline.
"""
lines = udiff_lines(['boo'], ['goo\n'])
self.check_patch(lines)
self.assertEquals(lines[4], '\\ No newline at end of file\n')
## "expected no-nl, got %r" % lines[4]
def test_remove_nl(self):
"""diff generates a valid diff for patches that change last line and
add a newline.
"""
lines = udiff_lines(['boo\n'], ['boo'])
self.check_patch(lines)
self.assertEquals(lines[5], '\\ No newline at end of file\n')
## "expected no-nl, got %r" % lines[5]
def check_patch(self, lines):
self.assert_(len(lines) > 1)
## "Not enough lines for a file header for patch:\n%s" % "".join(lines)
self.assert_(lines[0].startswith ('---'))
## 'No orig line for patch:\n%s' % "".join(lines)
self.assert_(lines[1].startswith ('+++'))
## 'No mod line for patch:\n%s' % "".join(lines)
self.assert_(len(lines) > 2)
## "No hunks for patch:\n%s" % "".join(lines)
self.assert_(lines[2].startswith('@@'))
## "No hunk header for patch:\n%s" % "".join(lines)
self.assert_('@@' in lines[2][2:])
## "Unterminated hunk header for patch:\n%s" % "".join(lines)
def test_binary_lines(self):
self.assertRaises(BinaryFile, udiff_lines, [1023 * 'a' + '\x00'], [])
self.assertRaises(BinaryFile, udiff_lines, [], [1023 * 'a' + '\x00'])
udiff_lines([1023 * 'a' + '\x00'], [], allow_binary=True)
udiff_lines([], [1023 * 'a' + '\x00'], allow_binary=True)
class TestCDVDiffLib(TestCase):
def test_unique_lcs(self):
self.assertEquals(unique_lcs('', ''), [])
self.assertEquals(unique_lcs('a', 'a'), [(0,0)])
self.assertEquals(unique_lcs('a', 'b'), [])
self.assertEquals(unique_lcs('ab', 'ab'), [(0,0), (1,1)])
self.assertEquals(unique_lcs('abcde', 'cdeab'), [(2,0), (3,1), (4,2)])
self.assertEquals(unique_lcs('cdeab', 'abcde'), [(0,2), (1,3), (2,4)])
self.assertEquals(unique_lcs('abXde', 'abYde'), [(0,0), (1,1),
(3,3), (4,4)])
self.assertEquals(unique_lcs('acbac', 'abc'), [(2,1)])
def test_recurse_matches(self):
def test_one(a, b, matches):
test_matches = []
recurse_matches(a, b, len(a), len(b), test_matches, 10)
self.assertEquals(test_matches, matches)
test_one(['a', None, 'b', None, 'c'], ['a', 'a', 'b', 'c', 'c'],
[(0, 0), (2, 2), (4, 4)])
test_one(['a', 'c', 'b', 'a', 'c'], ['a', 'b', 'c'],
[(0, 0), (2, 1), (4, 2)])
# recurse_matches doesn't match non-unique
# lines surrounded by bogus text.
# The update has been done in patiencediff.SequenceMatcher instead
# This is what it could be
#test_one('aBccDe', 'abccde', [(0,0), (2,2), (3,3), (5,5)])
# This is what it currently gives:
test_one('aBccDe', 'abccde', [(0,0), (5,5)])
def test_matching_blocks(self):
def chk_blocks(a, b, matching):
# difflib always adds a signature of the total
# length, with no matching entries at the end
s = SequenceMatcher(None, a, b)
blocks = s.get_matching_blocks()
x = blocks.pop()
self.assertEquals(x, (len(a), len(b), 0))
self.assertEquals(matching, blocks)
# Some basic matching tests
chk_blocks('', '', [])
chk_blocks([], [], [])
chk_blocks('abcd', 'abcd', [(0, 0, 4)])
chk_blocks('abcd', 'abce', [(0, 0, 3)])
chk_blocks('eabc', 'abce', [(1, 0, 3)])
chk_blocks('eabce', 'abce', [(1, 0, 4)])
chk_blocks('abcde', 'abXde', [(0, 0, 2), (3, 3, 2)])
chk_blocks('abcde', 'abXYZde', [(0, 0, 2), (3, 5, 2)])
chk_blocks('abde', 'abXYZde', [(0, 0, 2), (2, 5, 2)])
# This may check too much, but it checks to see that
# a copied block stays attached to the previous section,
# not the later one.
# difflib would tend to grab the trailing longest match
# which would make the diff not look right
chk_blocks('abcdefghijklmnop', 'abcdefxydefghijklmnop',
[(0, 0, 6), (6, 11, 10)])
# make sure it supports passing in lists
chk_blocks(
['hello there\n',
'world\n',
'how are you today?\n'],
['hello there\n',
'how are you today?\n'],
[(0, 0, 1), (2, 1, 1)])
chk_blocks('aBccDe', 'abccde', [(0,0,1), (2,2,2), (5,5,1)])
chk_blocks('aBcdEcdFg', 'abcdecdfg', [(0,0,1), (2,2,2),
(5,5,2), (8,8,1)])
chk_blocks('abbabbXd', 'cabbabxd', [(0,1,5), (7,7,1)])
chk_blocks('abbabbbb', 'cabbabbc', [(0,1,6)])
chk_blocks('bbbbbbbb', 'cbbbbbbc', [(0,1,6)])
def test_opcodes(self):
def chk_ops(a, b, codes):
s = SequenceMatcher(None, a, b)
self.assertEquals(codes, s.get_opcodes())
chk_ops('', '', [])
chk_ops([], [], [])
chk_ops('abcd', 'abcd', [('equal', 0,4, 0,4)])
chk_ops('abcd', 'abce', [('equal', 0,3, 0,3),
('replace', 3,4, 3,4)
])
chk_ops('eabc', 'abce', [('delete', 0,1, 0,0),
('equal', 1,4, 0,3),
('insert', 4,4, 3,4)
])
chk_ops('eabce', 'abce', [('delete', 0,1, 0,0),
('equal', 1,5, 0,4)
])
chk_ops('abcde', 'abXde', [('equal', 0,2, 0,2),
('replace', 2,3, 2,3),
('equal', 3,5, 3,5)
])
chk_ops('abcde', 'abXYZde', [('equal', 0,2, 0,2),
('replace', 2,3, 2,5),
('equal', 3,5, 5,7)
])
chk_ops('abde', 'abXYZde', [('equal', 0,2, 0,2),
('insert', 2,2, 2,5),
('equal', 2,4, 5,7)
])
chk_ops('abcdefghijklmnop', 'abcdefxydefghijklmnop',
[('equal', 0,6, 0,6),
('insert', 6,6, 6,11),
('equal', 6,16, 11,21)
])
chk_ops(
[ 'hello there\n'
, 'world\n'
, 'how are you today?\n'],
[ 'hello there\n'
, 'how are you today?\n'],
[('equal', 0,1, 0,1),
('delete', 1,2, 1,1),
('equal', 2,3, 1,2)
])
chk_ops('aBccDe', 'abccde',
[('equal', 0,1, 0,1),
('replace', 1,2, 1,2),
('equal', 2,4, 2,4),
('replace', 4,5, 4,5),
('equal', 5,6, 5,6)
])
chk_ops('aBcdEcdFg', 'abcdecdfg',
[('equal', 0,1, 0,1),
('replace', 1,2, 1,2),
('equal', 2,4, 2,4),
('replace', 4,5, 4,5),
('equal', 5,7, 5,7),
('replace', 7,8, 7,8),
('equal', 8,9, 8,9)
])
def test_multiple_ranges(self):
# There was an earlier bug where we used a bad set of ranges,
# this triggers that specific bug, to make sure it doesn't regress
def chk_blocks(a, b, matching):
# difflib always adds a signature of the total
# length, with no matching entries at the end
s = SequenceMatcher(None, a, b)
blocks = s.get_matching_blocks()
x = blocks.pop()
self.assertEquals(x, (len(a), len(b), 0))
self.assertEquals(matching, blocks)
chk_blocks('abcdefghijklmnop'
, 'abcXghiYZQRSTUVWXYZijklmnop'
, [(0, 0, 3), (6, 4, 3), (9, 20, 7)])
chk_blocks('ABCd efghIjk L'
, 'AxyzBCn mo pqrstuvwI1 2 L'
, [(0,0,1), (1, 4, 2), (4, 7, 1), (9, 19, 1), (12, 23, 3)])
chk_blocks('''\
get added when you add a file in the directory.
"""
takes_args = ['file*']
takes_options = ['no-recurse']
def run(self, file_list, no_recurse=False):
from bzrlib.add import smart_add, add_reporter_print, add_reporter_null
if is_quiet():
reporter = add_reporter_null
else:
reporter = add_reporter_print
smart_add(file_list, not no_recurse, reporter)
class cmd_mkdir(Command):
'''.splitlines(True)
, '''\
get added when you add a file in the directory.
--dry-run will show which files would be added, but not actually
add them.
"""
takes_args = ['file*']
takes_options = ['no-recurse', 'dry-run']
def run(self, file_list, no_recurse=False, dry_run=False):
import bzrlib.add
if dry_run:
if is_quiet():
# This is pointless, but I'd rather not raise an error
action = bzrlib.add.add_action_null
else:
action = bzrlib.add.add_action_print
elif is_quiet():
action = bzrlib.add.add_action_add
else:
action = bzrlib.add.add_action_add_and_print
bzrlib.add.smart_add(file_list, not no_recurse, action)
class cmd_mkdir(Command):
'''.splitlines(True)
, [(0,0,1), (1, 4, 2), (9, 19, 1), (12, 23, 3)])
def test_cdv_unified_diff(self):
txt_a = ['hello there\n',
'world\n',
'how are you today?\n']
txt_b = ['hello there\n',
'how are you today?\n']
self.assertEquals([ '--- \n',
'+++ \n',
'@@ -1,3 +1,2 @@\n',
' hello there\n',
'-world\n',
' how are you today?\n'
]
, list(unified_diff(txt_a, txt_b
, sequencematcher=SequenceMatcher)))
txt_a = map(lambda x: x+'\n', 'abcdefghijklmnop')
txt_b = map(lambda x: x+'\n', 'abcdefxydefghijklmnop')
# This is the result with LongestCommonSubstring matching
self.assertEquals(['--- \n',
'+++ \n',
'@@ -1,6 +1,11 @@\n',
' a\n',
' b\n',
' c\n',
'+d\n',
'+e\n',
'+f\n',
'+x\n',
'+y\n',
' d\n',
' e\n',
' f\n']
, list(unified_diff(txt_a, txt_b)))
# And the cdv diff
self.assertEquals(['--- \n',
'+++ \n',
'@@ -4,6 +4,11 @@\n',
' d\n',
' e\n',
' f\n',
'+x\n',
'+y\n',
'+d\n',
'+e\n',
'+f\n',
' g\n',
' h\n',
' i\n',
]
, list(unified_diff(txt_a, txt_b,
sequencematcher=SequenceMatcher)))
class TestCDVDiffLibFiles(TestCaseInTempDir):
def test_cdv_unified_diff_files(self):
txt_a = ['hello there\n',
'world\n',
'how are you today?\n']
txt_b = ['hello there\n',
'how are you today?\n']
open('a1', 'wb').writelines(txt_a)
open('b1', 'wb').writelines(txt_b)
self.assertEquals(['--- a1 \n',
'+++ b1 \n',
'@@ -1,3 +1,2 @@\n',
' hello there\n',
'-world\n',
' how are you today?\n',
]
, list(unified_diff_files('a1', 'b1',
sequencematcher=SequenceMatcher)))
txt_a = map(lambda x: x+'\n', 'abcdefghijklmnop')
txt_b = map(lambda x: x+'\n', 'abcdefxydefghijklmnop')
open('a2', 'wb').writelines(txt_a)
open('b2', 'wb').writelines(txt_b)
# This is the result with LongestCommonSubstring matching
self.assertEquals(['--- a2 \n',
'+++ b2 \n',
'@@ -1,6 +1,11 @@\n',
' a\n',
' b\n',
' c\n',
'+d\n',
'+e\n',
'+f\n',
'+x\n',
'+y\n',
' d\n',
' e\n',
' f\n']
, list(unified_diff_files('a2', 'b2')))
# And the cdv diff
self.assertEquals(['--- a2 \n',
'+++ b2 \n',
'@@ -4,6 +4,11 @@\n',
' d\n',
' e\n',
' f\n',
'+x\n',
'+y\n',
'+d\n',
'+e\n',
'+f\n',
' g\n',
' h\n',
' i\n',
]
, list(unified_diff_files('a2', 'b2',
sequencematcher=SequenceMatcher)))
|