cpython/Lib/test/test_re.py

199 lines
5.3 KiB
Python
Raw Normal View History

#!/usr/local/bin/python
# -*- mode: python -*-
# $Id$
1997-07-17 22:36:14 +00:00
from test_support import verbose, TestFailed
1997-07-11 19:34:44 +00:00
import re
import reop
1997-07-15 18:47:48 +00:00
import sys, os, string, traceback
1997-07-11 19:34:44 +00:00
1997-07-17 22:36:14 +00:00
# Misc tests from Tim Peters' re.doc
1997-07-18 04:26:25 +00:00
if verbose:
print 'Running tests on re.sub'
1997-07-17 22:36:14 +00:00
1997-07-18 04:26:25 +00:00
try:
1997-07-17 22:36:14 +00:00
assert re.sub("(?i)b+", "x", "bbbb BBBB") == 'x x'
1997-07-18 04:26:25 +00:00
1997-07-17 22:36:14 +00:00
def bump_num(matchobj):
int_value = int(matchobj.group(0))
return str(int_value + 1)
1997-07-18 04:26:25 +00:00
assert re.sub(r'\d+', bump_num, '08.2 -2 23x99y') == '9.3 -3 24x100y'
1997-07-17 22:36:14 +00:00
assert re.sub('.', lambda m: r"\n", 'x') == '\\n'
assert re.sub('.', r"\n", 'x') == '\n'
1997-07-18 04:26:25 +00:00
1997-07-17 22:36:14 +00:00
s = r"\1\1"
assert re.sub('(.)', s, 'x') == 'xx'
assert re.sub('(.)', re.escape(s), 'x') == s
assert re.sub('(.)', lambda m: s, 'x') == s
1997-07-18 04:26:25 +00:00
assert re.sub('(?P<a>x)', '\g<a>\g<a>', 'xx') == 'xxxx'
1997-08-13 22:34:14 +00:00
assert re.sub('a', r'\t\n\v\r\f\a\b\B\Z\a\A\w\W\s\S\d\D', 'a') == '\t\n\v\r\f\a\bBZ\aAwWsSdD'
assert re.sub('a', '\t\n\v\r\f\a', 'a') == '\t\n\v\r\f\a'
assert re.sub('a', '\t\n\v\r\f\a', 'a') == (chr(9)+chr(10)+chr(11)+chr(13)+chr(12)+chr(7))
1997-07-17 22:36:14 +00:00
except AssertionError:
raise TestFailed, "re.sub"
1997-07-18 04:26:25 +00:00
if verbose:
print 'Running tests on symbolic references'
try:
re.sub('(?P<a>x)', '\g<a', 'xx')
except re.error, reason:
pass
else:
raise TestFailed, "symbolic reference"
try:
re.sub('(?P<a>x)', '\g<', 'xx')
except re.error, reason:
pass
else:
raise TestFailed, "symbolic reference"
try:
re.sub('(?P<a>x)', '\g', 'xx')
except re.error, reason:
pass
else:
raise TestFailed, "symbolic reference"
try:
re.sub('(?P<a>x)', '\g<a a>', 'xx')
except re.error, reason:
pass
else:
raise TestFailed, "symbolic reference"
try:
re.sub('(?P<a>x)', '\g<ab>', 'xx')
except IndexError, reason:
pass
else:
raise TestFailed, "symbolic reference"
try:
re.sub('(?P<a>x)|(?P<b>y)', '\g<b>', 'xx')
except re.error, reason:
pass
else:
raise TestFailed, "symbolic reference"
try:
re.sub('(?P<a>x)|(?P<b>y)', '\\2', 'xx')
except re.error, reason:
pass
else:
raise TestFailed, "symbolic reference"
if verbose:
print 'Running tests on re.subn'
1997-07-17 22:36:14 +00:00
try:
assert re.subn("(?i)b+", "x", "bbbb BBBB") == ('x x', 2)
assert re.subn("b+", "x", "bbbb BBBB") == ('x BBBB', 1)
assert re.subn("b+", "x", "xyz") == ('xyz', 0)
assert re.subn("b*", "x", "xyz") == ('xxxyxzx', 4)
1997-07-18 04:26:25 +00:00
1997-07-17 22:36:14 +00:00
except AssertionError:
raise TestFailed, "re.subn"
1997-07-18 04:26:25 +00:00
if verbose:
print 'Running tests on re.split'
1997-07-17 22:36:14 +00:00
try:
assert re.split(":", ":a:b::c") == ['', 'a', 'b', '', 'c']
assert re.split(":*", ":a:b::c") == ['', 'a', 'b', 'c']
assert re.split("(:*)", ":a:b::c") == ['', ':', 'a', ':', 'b', '::', 'c']
assert re.split("(?::*)", ":a:b::c") == ['', 'a', 'b', 'c']
assert re.split("(:)*", ":a:b::c") == ['', ':', 'a', ':', 'b', ':', 'c']
assert re.split("([b:]+)", ":a:b::c") == ['', ':', 'a', ':b::', 'c']
assert re.split("(b)|(:+)", ":a:b::c") == \
1997-07-18 04:26:25 +00:00
['', None, ':', 'a', None, ':', '', 'b', None, '', None, '::', 'c']
1997-07-17 22:36:14 +00:00
assert re.split("(?:b)|(?::+)", ":a:b::c") == ['', 'a', '', '', 'c']
1997-07-18 04:26:25 +00:00
1997-07-17 22:36:14 +00:00
except AssertionError:
raise TestFailed, "re.split"
1997-07-11 19:34:44 +00:00
from re_tests import *
1997-07-18 04:26:25 +00:00
if verbose:
print 'Running re_tests test suite'
else:
# To save time, only run the first and last 10 tests
tests = tests[:10] + tests[-10:]
1997-07-11 19:34:44 +00:00
for t in tests:
sys.stdout.flush()
1997-07-11 19:34:44 +00:00
pattern=s=outcome=repl=expected=None
if len(t)==5:
pattern, s, outcome, repl, expected = t
elif len(t)==3:
pattern, s, outcome = t
else:
raise ValueError, ('Test tuples should have 3 or 5 fields',t)
try:
obj=re.compile(pattern)
except re.error:
if outcome==SYNTAX_ERROR: pass # Expected a syntax error
else:
print '=== Syntax error:', t
1997-08-13 22:34:14 +00:00
except KeyboardInterrupt: raise KeyboardInterrupt
1997-07-11 19:34:44 +00:00
except:
print '*** Unexpected error ***'
if verbose:
traceback.print_exc(file=sys.stdout)
1997-07-11 19:34:44 +00:00
else:
try:
result=obj.search(s)
except (re.error, reop.error), msg:
1997-07-11 19:34:44 +00:00
print '=== Unexpected exception', t, repr(msg)
if outcome==SYNTAX_ERROR:
# This should have been a syntax error; forget it.
pass
elif outcome==FAIL:
if result is None: pass # No match, as expected
else: print '=== Succeeded incorrectly', t
elif outcome==SUCCEED:
if result is not None:
# Matched, as expected, so now we compute the
# result string and compare it to our expected result.
start, end = result.span(0)
vardict={'found': result.group(0),
'groups': result.group(),
'flags': result.re.flags}
1997-07-11 19:34:44 +00:00
for i in range(1, 100):
try:
gi = result.group(i)
1997-07-11 20:47:58 +00:00
# Special hack because else the string concat fails:
if gi is None:
gi = "None"
1997-07-11 19:34:44 +00:00
except IndexError:
gi = "Error"
1997-07-15 15:40:57 +00:00
vardict['g%d' % i] = gi
1997-07-15 18:47:48 +00:00
for i in result.re.groupindex.keys():
try:
gi = result.group(i)
if gi is None:
gi = "None"
1997-07-15 18:47:48 +00:00
except IndexError:
gi = "Error"
vardict[i] = gi
1997-07-11 19:34:44 +00:00
repl=eval(repl, vardict)
if repl!=expected:
print '=== grouping error', t,
print repr(repl)+' should be '+repr(expected)
else:
print '=== Failed incorrectly', t
1997-08-13 22:34:14 +00:00
# Try the match with IGNORECASE enabled, and check that it
# still succeeds.
obj=re.compile(pattern, re.IGNORECASE)
result=obj.search(s)
if result==None:
print '=== Fails on case-insensitive match', t