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
|
import difflib
from test.support import run_unittest, findfile
import unittest
import doctest
import sys
class TestWithAscii(unittest.TestCase):
def test_one_insert(self):
sm = difflib.SequenceMatcher(None, 'b' * 100, 'a' + 'b' * 100)
self.assertAlmostEqual(sm.ratio(), 0.995, places=3)
self.assertEqual(list(sm.get_opcodes()),
[ ('insert', 0, 0, 0, 1),
('equal', 0, 100, 1, 101)])
self.assertEqual(sm.bpopular, set())
sm = difflib.SequenceMatcher(None, 'b' * 100, 'b' * 50 + 'a' + 'b' * 50)
self.assertAlmostEqual(sm.ratio(), 0.995, places=3)
self.assertEqual(list(sm.get_opcodes()),
[ ('equal', 0, 50, 0, 50),
('insert', 50, 50, 50, 51),
('equal', 50, 100, 51, 101)])
self.assertEqual(sm.bpopular, set())
def test_one_delete(self):
sm = difflib.SequenceMatcher(None, 'a' * 40 + 'c' + 'b' * 40, 'a' * 40 + 'b' * 40)
self.assertAlmostEqual(sm.ratio(), 0.994, places=3)
self.assertEqual(list(sm.get_opcodes()),
[ ('equal', 0, 40, 0, 40),
('delete', 40, 41, 40, 40),
('equal', 41, 81, 40, 80)])
def test_bjunk(self):
sm = difflib.SequenceMatcher(isjunk=lambda x: x == ' ',
a='a' * 40 + 'b' * 40, b='a' * 44 + 'b' * 40)
self.assertEqual(sm.bjunk, set())
sm = difflib.SequenceMatcher(isjunk=lambda x: x == ' ',
a='a' * 40 + 'b' * 40, b='a' * 44 + 'b' * 40 + ' ' * 20)
self.assertEqual(sm.bjunk, {' '})
sm = difflib.SequenceMatcher(isjunk=lambda x: x in [' ', 'b'],
a='a' * 40 + 'b' * 40, b='a' * 44 + 'b' * 40 + ' ' * 20)
self.assertEqual(sm.bjunk, {' ', 'b'})
class TestAutojunk(unittest.TestCase):
"""Tests for the autojunk parameter added in 2.7"""
def test_one_insert_homogenous_sequence(self):
# By default autojunk=True and the heuristic kicks in for a sequence
# of length 200+
seq1 = 'b' * 200
seq2 = 'a' + 'b' * 200
sm = difflib.SequenceMatcher(None, seq1, seq2)
self.assertAlmostEqual(sm.ratio(), 0, places=3)
self.assertEqual(sm.bpopular, {'b'})
# Now turn the heuristic off
sm = difflib.SequenceMatcher(None, seq1, seq2, autojunk=False)
self.assertAlmostEqual(sm.ratio(), 0.9975, places=3)
self.assertEqual(sm.bpopular, set())
class TestSFbugs(unittest.TestCase):
def test_ratio_for_null_seqn(self):
# Check clearing of SF bug 763023
s = difflib.SequenceMatcher(None, [], [])
self.assertEqual(s.ratio(), 1)
self.assertEqual(s.quick_ratio(), 1)
self.assertEqual(s.real_quick_ratio(), 1)
def test_comparing_empty_lists(self):
# Check fix for bug #979794
group_gen = difflib.SequenceMatcher(None, [], []).get_grouped_opcodes()
self.assertRaises(StopIteration, next, group_gen)
diff_gen = difflib.unified_diff([], [])
self.assertRaises(StopIteration, next, diff_gen)
def test_added_tab_hint(self):
# Check fix for bug #1488943
diff = list(difflib.Differ().compare(["\tI am a buggy"],["\t\tI am a bug"]))
self.assertEqual("- \tI am a buggy", diff[0])
self.assertEqual("? --\n", diff[1])
self.assertEqual("+ \t\tI am a bug", diff[2])
self.assertEqual("? +\n", diff[3])
patch914575_from1 = """
1. Beautiful is beTTer than ugly.
2. Explicit is better than implicit.
3. Simple is better than complex.
4. Complex is better than complicated.
"""
patch914575_to1 = """
1. Beautiful is better than ugly.
3. Simple is better than complex.
4. Complicated is better than complex.
5. Flat is better than nested.
"""
patch914575_from2 = """
\t\tLine 1: preceeded by from:[tt] to:[ssss]
\t\tLine 2: preceeded by from:[sstt] to:[sssst]
\t \tLine 3: preceeded by from:[sstst] to:[ssssss]
Line 4: \thas from:[sst] to:[sss] after :
Line 5: has from:[t] to:[ss] at end\t
"""
patch914575_to2 = """
Line 1: preceeded by from:[tt] to:[ssss]
\tLine 2: preceeded by from:[sstt] to:[sssst]
Line 3: preceeded by from:[sstst] to:[ssssss]
Line 4: has from:[sst] to:[sss] after :
Line 5: has from:[t] to:[ss] at end
"""
patch914575_from3 = """line 0
1234567890123456789012345689012345
line 1
line 2
line 3
line 4 changed
line 5 changed
line 6 changed
line 7
line 8 subtracted
line 9
1234567890123456789012345689012345
short line
just fits in!!
just fits in two lines yup!!
the end"""
patch914575_to3 = """line 0
1234567890123456789012345689012345
line 1
line 2 added
line 3
line 4 chanGEd
line 5a chanGed
line 6a changEd
line 7
line 8
line 9
1234567890
another long line that needs to be wrapped
just fitS in!!
just fits in two lineS yup!!
the end"""
class TestSFpatches(unittest.TestCase):
def test_html_diff(self):
# Check SF patch 914575 for generating HTML differences
f1a = ((patch914575_from1 + '123\n'*10)*3)
t1a = (patch914575_to1 + '123\n'*10)*3
f1b = '456\n'*10 + f1a
t1b = '456\n'*10 + t1a
f1a = f1a.splitlines()
t1a = t1a.splitlines()
f1b = f1b.splitlines()
t1b = t1b.splitlines()
f2 = patch914575_from2.splitlines()
t2 = patch914575_to2.splitlines()
f3 = patch914575_from3
t3 = patch914575_to3
i = difflib.HtmlDiff()
j = difflib.HtmlDiff(tabsize=2)
k = difflib.HtmlDiff(wrapcolumn=14)
full = i.make_file(f1a,t1a,'from','to',context=False,numlines=5)
tables = '\n'.join(
[
'<h2>Context (first diff within numlines=5(default))</h2>',
i.make_table(f1a,t1a,'from','to',context=True),
'<h2>Context (first diff after numlines=5(default))</h2>',
i.make_table(f1b,t1b,'from','to',context=True),
'<h2>Context (numlines=6)</h2>',
i.make_table(f1a,t1a,'from','to',context=True,numlines=6),
'<h2>Context (numlines=0)</h2>',
i.make_table(f1a,t1a,'from','to',context=True,numlines=0),
'<h2>Same Context</h2>',
i.make_table(f1a,f1a,'from','to',context=True),
'<h2>Same Full</h2>',
i.make_table(f1a,f1a,'from','to',context=False),
'<h2>Empty Context</h2>',
i.make_table([],[],'from','to',context=True),
'<h2>Empty Full</h2>',
i.make_table([],[],'from','to',context=False),
'<h2>tabsize=2</h2>',
j.make_table(f2,t2),
'<h2>tabsize=default</h2>',
i.make_table(f2,t2),
'<h2>Context (wrapcolumn=14,numlines=0)</h2>',
k.make_table(f3.splitlines(),t3.splitlines(),context=True,numlines=0),
'<h2>wrapcolumn=14,splitlines()</h2>',
k.make_table(f3.splitlines(),t3.splitlines()),
'<h2>wrapcolumn=14,splitlines(True)</h2>',
k.make_table(f3.splitlines(True),t3.splitlines(True)),
])
actual = full.replace('</body>','\n%s\n</body>' % tables)
# temporarily uncomment next two lines to baseline this test
#with open('test_difflib_expect.html','w') as fp:
# fp.write(actual)
with open(findfile('test_difflib_expect.html')) as fp:
self.assertEqual(actual, fp.read())
def test_recursion_limit(self):
# Check if the problem described in patch #1413711 exists.
limit = sys.getrecursionlimit()
old = [(i%2 and "K:%d" or "V:A:%d") % i for i in range(limit*2)]
new = [(i%2 and "K:%d" or "V:B:%d") % i for i in range(limit*2)]
difflib.SequenceMatcher(None, old, new).get_opcodes()
class TestOutputFormat(unittest.TestCase):
def test_tab_delimiter(self):
args = ['one', 'two', 'Original', 'Current',
'2005-01-26 23:30:50', '2010-04-02 10:20:52']
ud = difflib.unified_diff(*args, lineterm='')
self.assertEqual(list(ud)[0:2], [
"--- Original\t2005-01-26 23:30:50",
"+++ Current\t2010-04-02 10:20:52"])
cd = difflib.context_diff(*args, lineterm='')
self.assertEqual(list(cd)[0:2], [
"*** Original\t2005-01-26 23:30:50",
"--- Current\t2010-04-02 10:20:52"])
def test_no_trailing_tab_on_empty_filedate(self):
args = ['one', 'two', 'Original', 'Current']
ud = difflib.unified_diff(*args, lineterm='')
self.assertEqual(list(ud)[0:2], ["--- Original", "+++ Current"])
cd = difflib.context_diff(*args, lineterm='')
self.assertEqual(list(cd)[0:2], ["*** Original", "--- Current"])
def test_range_format_unified(self):
# Per the diff spec at http://www.unix.org/single_unix_specification/
spec = '''\
Each <range> field shall be of the form:
%1d", <beginning line number> if the range contains exactly one line,
and:
"%1d,%1d", <beginning line number>, <number of lines> otherwise.
If a range is empty, its beginning line number shall be the number of
the line just before the range, or 0 if the empty range starts the file.
'''
fmt = difflib._format_range_unified
self.assertEqual(fmt(3,3), '3,0')
self.assertEqual(fmt(3,4), '4')
self.assertEqual(fmt(3,5), '4,2')
self.assertEqual(fmt(3,6), '4,3')
self.assertEqual(fmt(0,0), '0,0')
def test_range_format_context(self):
# Per the diff spec at http://www.unix.org/single_unix_specification/
spec = '''\
The range of lines in file1 shall be written in the following format
if the range contains two or more lines:
"*** %d,%d ****\n", <beginning line number>, <ending line number>
and the following format otherwise:
"*** %d ****\n", <ending line number>
The ending line number of an empty range shall be the number of the preceding line,
or 0 if the range is at the start of the file.
Next, the range of lines in file2 shall be written in the following format
if the range contains two or more lines:
"--- %d,%d ----\n", <beginning line number>, <ending line number>
and the following format otherwise:
"--- %d ----\n", <ending line number>
'''
fmt = difflib._format_range_context
self.assertEqual(fmt(3,3), '3')
self.assertEqual(fmt(3,4), '4')
self.assertEqual(fmt(3,5), '4,5')
self.assertEqual(fmt(3,6), '4,6')
self.assertEqual(fmt(0,0), '0')
def test_main():
difflib.HtmlDiff._default_prefix = 0
Doctests = doctest.DocTestSuite(difflib)
run_unittest(
TestWithAscii, TestAutojunk, TestSFpatches, TestSFbugs,
TestOutputFormat, Doctests)
if __name__ == '__main__':
test_main()
|
