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_matching_blocks_cache(self): # Issue #21635 s = difflib.SequenceMatcher(None, "abxcd", "abcd") first = s.get_matching_blocks() second = s.get_matching_blocks() self.assertEqual(second[0].size, 2) self.assertEqual(second[1].size, 2) self.assertEqual(second[2].size, 0) 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("? \t --\n", diff[1]) self.assertEqual("+ \t\tI am a bug", diff[2]) self.assertEqual("? +\n", diff[3]) def test_hint_indented_properly_with_tabs(self): diff = list(difflib.Differ().compare(["\t \t \t^"], ["\t \t \t^\n"])) self.assertEqual("- \t \t \t^", diff[0]) self.assertEqual("+ \t \t \t^\n", diff[1]) self.assertEqual("? \t \t \t +\n", diff[2]) def test_mdiff_catch_stop_iteration(self): # Issue #33224 self.assertEqual( list(difflib._mdiff(["2"], ["3"], 1)), [((1, '\x00-2\x01'), (1, '\x00+3\x01'), True)], ) 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_nonascii_from1 = """ 1. Beautiful is beTTer than ugly. 2. Explicit is better than ımplıcıt. 3. Simple is better than complex. 4. Complex is better than complicated. """ patch914575_nonascii_to1 = """ 1. Beautiful is better than ügly. 3. Sımple is better than complex. 4. Complicated is better than cömplex. 5. Flat is better than nested. """ patch914575_from2 = """ \t\tLine 1: preceded by from:[tt] to:[ssss] \t\tLine 2: preceded by from:[sstt] to:[sssst] \t \tLine 3: preceded 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: preceded by from:[tt] to:[ssss] \tLine 2: preceded by from:[sstt] to:[sssst] Line 3: preceded 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( [ '