Skip to content
Projeler
Gruplar
Parçacıklar
Yardım
Yükleniyor...
Oturum aç / Kaydol
Gezinmeyi değiştir
C
cpython
Proje
Proje
Ayrıntılar
Etkinlik
Cycle Analytics
Depo (repository)
Depo (repository)
Dosyalar
Kayıtlar (commit)
Dallar (branch)
Etiketler
Katkıda bulunanlar
Grafik
Karşılaştır
Grafikler
Konular (issue)
0
Konular (issue)
0
Liste
Pano
Etiketler
Kilometre Taşları
Birleştirme (merge) Talepleri
0
Birleştirme (merge) Talepleri
0
CI / CD
CI / CD
İş akışları (pipeline)
İşler
Zamanlamalar
Grafikler
Paketler
Paketler
Wiki
Wiki
Parçacıklar
Parçacıklar
Üyeler
Üyeler
Collapse sidebar
Close sidebar
Etkinlik
Grafik
Grafikler
Yeni bir konu (issue) oluştur
İşler
Kayıtlar (commit)
Konu (issue) Panoları
Kenar çubuğunu aç
Batuhan Osman TASKAYA
cpython
Commits
876736cd
Kaydet (Commit)
876736cd
authored
Haz 03, 1997
tarafından
Guido van Rossum
Dosyalara gözat
Seçenekler
Dosyalara Gözat
İndir
Eposta Yamaları
Sade Fark
AMK's regex test suite
üst
71160aaf
Hide whitespace changes
Inline
Side-by-side
Showing
2 changed files
with
331 additions
and
0 deletions
+331
-0
regex_tests.py
Lib/test/regex_tests.py
+283
-0
test_regex.py
Lib/test/test_regex.py
+48
-0
No files found.
Lib/test/regex_tests.py
0 → 100644
Dosyayı görüntüle @
876736cd
# Regex test suite and benchmark suite v1.5a2
# Due to the use of r"aw" strings, this file will
# only work with Python 1.5 or higher.
# The 3 possible outcomes for each pattern
[
SUCCEED
,
FAIL
,
SYNTAX_ERROR
]
=
range
(
3
)
# Benchmark suite (needs expansion)
#
# The benchmark suite does not test correctness, just speed. The
# first element of each tuple is the regex pattern; the second is a
# string to match it against. The benchmarking code will embed the
# second string inside several sizes of padding, to test how regex
# matching performs on large strings.
benchmarks
=
[
(
'Python'
,
'Python'
),
# Simple text literal
(
'.*Python'
,
'Python'
),
# Bad text literal
(
'.*Python.*'
,
'Python'
),
# Worse text literal
(
'.*
\\
(Python
\\
)'
,
'Python'
),
# Bad text literal with grouping
(
'(Python
\\
|Perl
\\
|Tcl'
,
'Perl'
),
# Alternation
(
'
\\
(Python
\\
|Perl
\\
|Tcl
\\
)'
,
'Perl'
),
# Grouped alternation
(
'
\\
(Python
\\
)
\\
1'
,
'PythonPython'
),
# Backreference
# ('\\([0a-z][a-z]*,\\)+', 'a5,b7,c9,'), # Disable the fastmap optimization
(
'
\\
([a-z][a-z0-9]*,
\\
)+'
,
'a5,b7,c9,'
)
# A few sets
]
# Test suite (for verifying correctness)
#
# The test suite is a list of 5- or 3-tuples. The 5 parts of a
# complete tuple are:
# element 0: a string containing the pattern
# 1: the string to match against the pattern
# 2: the expected result (SUCCEED, FAIL, SYNTAX_ERROR)
# 3: a string that will be eval()'ed to produce a test string.
# This is an arbitrary Python expression; the available
# variables are "found" (the whole match), and "g1", "g2", ...
# up to "g10" contain the contents of each group, or the
# string 'None' if the group wasn't given a value.
# 4: The expected result of evaluating the expression.
# If the two don't match, an error is reported.
#
# If the regex isn't expected to work, the latter two elements can be omitted.
tests
=
[
(
'abc'
,
'abc'
,
SUCCEED
,
'found'
,
'abc'
),
(
'abc'
,
'xbc'
,
FAIL
),
(
'abc'
,
'axc'
,
FAIL
),
(
'abc'
,
'abx'
,
FAIL
),
(
'abc'
,
'xabcy'
,
SUCCEED
,
'found'
,
'abc'
),
(
'abc'
,
'ababc'
,
SUCCEED
,
'found'
,
'abc'
),
(
'ab*c'
,
'abc'
,
SUCCEED
,
'found'
,
'abc'
),
(
'ab*bc'
,
'abc'
,
SUCCEED
,
'found'
,
'abc'
),
(
'ab*bc'
,
'abbc'
,
SUCCEED
,
'found'
,
'abbc'
),
(
'ab*bc'
,
'abbbbc'
,
SUCCEED
,
'found'
,
'abbbbc'
),
(
'ab+bc'
,
'abbc'
,
SUCCEED
,
'found'
,
'abbc'
),
(
'ab+bc'
,
'abc'
,
FAIL
),
(
'ab+bc'
,
'abq'
,
FAIL
),
(
'ab+bc'
,
'abbbbc'
,
SUCCEED
,
'found'
,
'abbbbc'
),
(
'ab?bc'
,
'abbc'
,
SUCCEED
,
'found'
,
'abbc'
),
(
'ab?bc'
,
'abc'
,
SUCCEED
,
'found'
,
'abc'
),
(
'ab?bc'
,
'abbbbc'
,
FAIL
),
(
'ab?c'
,
'abc'
,
SUCCEED
,
'found'
,
'abc'
),
(
'^abc$'
,
'abc'
,
SUCCEED
,
'found'
,
'abc'
),
(
'^abc$'
,
'abcc'
,
FAIL
),
(
'^abc'
,
'abcc'
,
SUCCEED
,
'found'
,
'abc'
),
(
'^abc$'
,
'aabc'
,
FAIL
),
(
'abc$'
,
'aabc'
,
SUCCEED
,
'found'
,
'abc'
),
(
'^'
,
'abc'
,
SUCCEED
,
'found+"-"'
,
'-'
),
(
'$'
,
'abc'
,
SUCCEED
,
'found+"-"'
,
'-'
),
(
'a.c'
,
'abc'
,
SUCCEED
,
'found'
,
'abc'
),
(
'a.c'
,
'axc'
,
SUCCEED
,
'found'
,
'axc'
),
(
'a.*c'
,
'axyzc'
,
SUCCEED
,
'found'
,
'axyzc'
),
(
'a.*c'
,
'axyzd'
,
FAIL
),
(
'a[bc]d'
,
'abc'
,
FAIL
),
(
'a[bc]d'
,
'abd'
,
SUCCEED
,
'found'
,
'abd'
),
(
'a[b-d]e'
,
'abd'
,
FAIL
),
(
'a[b-d]e'
,
'ace'
,
SUCCEED
,
'found'
,
'ace'
),
(
'a[b-d]'
,
'aac'
,
SUCCEED
,
'found'
,
'ac'
),
(
'a[-b]'
,
'a-'
,
SUCCEED
,
'found'
,
'a-'
),
(
'a[b-]'
,
'a-'
,
SUCCEED
,
'found'
,
'a-'
),
(
'a[]b'
,
'-'
,
SYNTAX_ERROR
),
(
'a['
,
'-'
,
SYNTAX_ERROR
),
(
'a
\\
'
,
'-'
,
SYNTAX_ERROR
),
(
'abc
\\
)'
,
'-'
,
SYNTAX_ERROR
),
(
'
\\
(abc'
,
'-'
,
SYNTAX_ERROR
),
(
'a]'
,
'a]'
,
SUCCEED
,
'found'
,
'a]'
),
(
'a[]]b'
,
'a]b'
,
SUCCEED
,
'found'
,
'a]b'
),
(
'a[^bc]d'
,
'aed'
,
SUCCEED
,
'found'
,
'aed'
),
(
'a[^bc]d'
,
'abd'
,
FAIL
),
(
'a[^-b]c'
,
'adc'
,
SUCCEED
,
'found'
,
'adc'
),
(
'a[^-b]c'
,
'a-c'
,
FAIL
),
(
'a[^]b]c'
,
'a]c'
,
FAIL
),
(
'a[^]b]c'
,
'adc'
,
SUCCEED
,
'found'
,
'adc'
),
(
'
\\
ba
\\
b'
,
'a-'
,
SUCCEED
,
'"-"'
,
'-'
),
(
'
\\
ba
\\
b'
,
'-a'
,
SUCCEED
,
'"-"'
,
'-'
),
(
'
\\
ba
\\
b'
,
'-a-'
,
SUCCEED
,
'"-"'
,
'-'
),
(
'
\\
by
\\
b'
,
'xy'
,
FAIL
),
(
'
\\
by
\\
b'
,
'yz'
,
FAIL
),
(
'
\\
by
\\
b'
,
'xyz'
,
FAIL
),
(
'ab
\\
|cd'
,
'abc'
,
SUCCEED
,
'found'
,
'ab'
),
(
'ab
\\
|cd'
,
'abcd'
,
SUCCEED
,
'found'
,
'ab'
),
(
'
\\
(
\\
)ef'
,
'def'
,
SUCCEED
,
'found+"-"+g1'
,
'ef-'
),
(
'$b'
,
'b'
,
FAIL
),
(
'a(b'
,
'a(b'
,
SUCCEED
,
'found+"-"+g1'
,
'a(b-None'
),
(
'a(*b'
,
'ab'
,
SUCCEED
,
'found'
,
'ab'
),
(
'a(*b'
,
'a((b'
,
SUCCEED
,
'found'
,
'a((b'
),
(
'a
\\\\
b'
,
'a
\\
b'
,
SUCCEED
,
'found'
,
'a
\\
b'
),
(
'
\\
(
\\
(a
\\
)
\\
)'
,
'abc'
,
SUCCEED
,
'found+"-"+g1+"-"+g2'
,
'a-a-a'
),
(
'
\\
(a
\\
)b
\\
(c
\\
)'
,
'abc'
,
SUCCEED
,
'found+"-"+g1+"-"+g2'
,
'abc-a-c'
),
(
'a+b+c'
,
'aabbabc'
,
SUCCEED
,
'found'
,
'abc'
),
(
'
\\
(a+
\\
|b
\\
)*'
,
'ab'
,
SUCCEED
,
'found+"-"+g1'
,
'ab-b'
),
(
'
\\
(a+
\\
|b
\\
)+'
,
'ab'
,
SUCCEED
,
'found+"-"+g1'
,
'ab-b'
),
(
'
\\
(a+
\\
|b
\\
)?'
,
'ab'
,
SUCCEED
,
'found+"-"+g1'
,
'a-a'
),
(
'
\\
)
\\
('
,
'-'
,
SYNTAX_ERROR
),
(
'[^ab]*'
,
'cde'
,
SUCCEED
,
'found'
,
'cde'
),
(
'abc'
,
''
,
FAIL
),
(
'a*'
,
''
,
SUCCEED
,
'found'
,
''
),
(
'a
\\
|b
\\
|c
\\
|d
\\
|e'
,
'e'
,
SUCCEED
,
'found'
,
'e'
),
(
'
\\
(a
\\
|b
\\
|c
\\
|d
\\
|e
\\
)f'
,
'ef'
,
SUCCEED
,
'found+"-"+g1'
,
'ef-e'
),
(
'abcd*efg'
,
'abcdefg'
,
SUCCEED
,
'found'
,
'abcdefg'
),
(
'ab*'
,
'xabyabbbz'
,
SUCCEED
,
'found'
,
'ab'
),
(
'ab*'
,
'xayabbbz'
,
SUCCEED
,
'found'
,
'a'
),
(
'
\\
(ab
\\
|cd
\\
)e'
,
'abcde'
,
SUCCEED
,
'found+"-"+g1'
,
'cde-cd'
),
(
'[abhgefdc]ij'
,
'hij'
,
SUCCEED
,
'found'
,
'hij'
),
(
'^
\\
(ab
\\
|cd
\\
)e'
,
'abcde'
,
FAIL
,
'xg1y'
,
'xy'
),
(
'
\\
(abc
\\
|
\\
)ef'
,
'abcdef'
,
SUCCEED
,
'found+"-"+g1'
,
'ef-'
),
(
'
\\
(a
\\
|b
\\
)c*d'
,
'abcd'
,
SUCCEED
,
'found+"-"+g1'
,
'bcd-b'
),
(
'
\\
(ab
\\
|ab*
\\
)bc'
,
'abc'
,
SUCCEED
,
'found+"-"+g1'
,
'abc-a'
),
(
'a
\\
([bc]*
\\
)c*'
,
'abc'
,
SUCCEED
,
'found+"-"+g1'
,
'abc-bc'
),
(
'a
\\
([bc]*
\\
)
\\
(c*d
\\
)'
,
'abcd'
,
SUCCEED
,
'found+"-"+g1+"-"+g2'
,
'abcd-bc-d'
),
(
'a
\\
([bc]+
\\
)
\\
(c*d
\\
)'
,
'abcd'
,
SUCCEED
,
'found+"-"+g1+"-"+g2'
,
'abcd-bc-d'
),
(
'a
\\
([bc]*
\\
)
\\
(c+d
\\
)'
,
'abcd'
,
SUCCEED
,
'found+"-"+g1+"-"+g2'
,
'abcd-b-cd'
),
(
'a[bcd]*dcdcde'
,
'adcdcde'
,
SUCCEED
,
'found'
,
'adcdcde'
),
(
'a[bcd]+dcdcde'
,
'adcdcde'
,
FAIL
),
(
'
\\
(ab
\\
|a
\\
)b*c'
,
'abc'
,
SUCCEED
,
'found+"-"+g1'
,
'abc-ab'
),
(
'
\\
(
\\
(a
\\
)
\\
(b
\\
)c
\\
)
\\
(d
\\
)'
,
'abcd'
,
SUCCEED
,
'g1+"-"+g2+"-"+g3+"-"+g4'
,
'abc-a-b-d'
),
(
'[a-zA-Z_][a-zA-Z0-9_]*'
,
'alpha'
,
SUCCEED
,
'found'
,
'alpha'
),
(
'^a
\\
(bc+
\\
|b[eh]
\\
)g
\\
|.h$'
,
'abh'
,
SUCCEED
,
'found+"-"+g1'
,
'bh-None'
),
(
'
\\
(bc+d$
\\
|ef*g.
\\
|h?i
\\
(j
\\
|k
\\
)
\\
)'
,
'effgz'
,
SUCCEED
,
'found+"-"+g1+"-"+g2'
,
'effgz-effgz-None'
),
(
'
\\
(bc+d$
\\
|ef*g.
\\
|h?i
\\
(j
\\
|k
\\
)
\\
)'
,
'ij'
,
SUCCEED
,
'found+"-"+g1+"-"+g2'
,
'ij-ij-j'
),
(
'
\\
(bc+d$
\\
|ef*g.
\\
|h?i
\\
(j
\\
|k
\\
)
\\
)'
,
'effg'
,
FAIL
),
(
'
\\
(bc+d$
\\
|ef*g.
\\
|h?i
\\
(j
\\
|k
\\
)
\\
)'
,
'bcdd'
,
FAIL
),
(
'
\\
(bc+d$
\\
|ef*g.
\\
|h?i
\\
(j
\\
|k
\\
)
\\
)'
,
'reffgz'
,
SUCCEED
,
'found+"-"+g1+"-"+g2'
,
'effgz-effgz-None'
),
(
'
\\
(
\\
(
\\
(
\\
(
\\
(
\\
(
\\
(
\\
(
\\
(a
\\
)
\\
)
\\
)
\\
)
\\
)
\\
)
\\
)
\\
)
\\
)'
,
'a'
,
SUCCEED
,
'found'
,
'a'
),
(
'multiple words of text'
,
'uh-uh'
,
FAIL
),
(
'multiple words'
,
'multiple words, yeah'
,
SUCCEED
,
'found'
,
'multiple words'
),
(
'
\\
(.*
\\
)c
\\
(.*
\\
)'
,
'abcde'
,
SUCCEED
,
'found+"-"+g1+"-"+g2'
,
'abcde-ab-de'
),
(
'(
\\
(.*
\\
),
\\
(.*
\\
))'
,
'(a, b)'
,
SUCCEED
,
'g2+"-"+g1'
,
'b-a'
),
(
'[k]'
,
'ab'
,
FAIL
),
(
'a[-]?c'
,
'ac'
,
SUCCEED
,
'found'
,
'ac'
),
(
'
\\
(abc
\\
)
\\
1'
,
'abcabc'
,
SUCCEED
,
'g1'
,
'abc'
),
(
'
\\
([a-c]*
\\
)
\\
1'
,
'abcabc'
,
SUCCEED
,
'g1'
,
'abc'
),
(
'^
\\
(.+
\\
)?B'
,
'AB'
,
SUCCEED
,
'g1'
,
'A'
),
(
'
\\
(a+
\\
).
\\
1$'
,
'aaaaa'
,
SUCCEED
,
'found+"-"+g1'
,
'aaaaa-aa'
),
(
'^
\\
(a+
\\
).
\\
1$'
,
'aaaa'
,
FAIL
),
(
'
\\
(abc
\\
)
\\
1'
,
'abcabc'
,
SUCCEED
,
'found+"-"+g1'
,
'abcabc-abc'
),
(
'
\\
([a-c]+
\\
)
\\
1'
,
'abcabc'
,
SUCCEED
,
'found+"-"+g1'
,
'abcabc-abc'
),
(
'
\\
(a
\\
)
\\
1'
,
'aa'
,
SUCCEED
,
'found+"-"+g1'
,
'aa-a'
),
(
'
\\
(a+
\\
)
\\
1'
,
'aa'
,
SUCCEED
,
'found+"-"+g1'
,
'aa-a'
),
(
'
\\
(a+
\\
)+
\\
1'
,
'aa'
,
SUCCEED
,
'found+"-"+g1'
,
'aa-a'
),
(
'
\\
(a
\\
).+
\\
1'
,
'aba'
,
SUCCEED
,
'found+"-"+g1'
,
'aba-a'
),
(
'
\\
(a
\\
)ba*
\\
1'
,
'aba'
,
SUCCEED
,
'found+"-"+g1'
,
'aba-a'
),
(
'
\\
(aa
\\
|a
\\
)a
\\
1$'
,
'aaa'
,
SUCCEED
,
'found+"-"+g1'
,
'aaa-a'
),
(
'
\\
(a
\\
|aa
\\
)a
\\
1$'
,
'aaa'
,
SUCCEED
,
'found+"-"+g1'
,
'aaa-a'
),
(
'
\\
(a+
\\
)a
\\
1$'
,
'aaa'
,
SUCCEED
,
'found+"-"+g1'
,
'aaa-a'
),
(
'
\\
([abc]*
\\
)
\\
1'
,
'abcabc'
,
SUCCEED
,
'found+"-"+g1'
,
'abcabc-abc'
),
(
'
\\
(a
\\
)
\\
(b
\\
)c
\\
|ab'
,
'ab'
,
SUCCEED
,
'found+"-"+g1+"-"+g2'
,
'ab-None-None'
),
(
'
\\
(a
\\
)+x'
,
'aaax'
,
SUCCEED
,
'found+"-"+g1'
,
'aaax-a'
),
(
'
\\
([ac]
\\
)+x'
,
'aacx'
,
SUCCEED
,
'found+"-"+g1'
,
'aacx-c'
),
(
'
\\
([^/]*/
\\
)*sub1/'
,
'd:msgs/tdir/sub1/trial/away.cpp'
,
SUCCEED
,
'found+"-"+g1'
,
'd:msgs/tdir/sub1/-tdir/'
),
(
'
\\
([^.]*
\\
)
\\
.
\\
([^:]*
\\
):[T ]+
\\
(.*
\\
)'
,
'track1.title:TBlah blah blah'
,
SUCCEED
,
'found+"-"+g1+"-"+g2+"-"+g3'
,
'track1.title:TBlah blah blah-track1-title-Blah blah blah'
),
(
'
\\
([^N]*N
\\
)+'
,
'abNNxyzN'
,
SUCCEED
,
'found+"-"+g1'
,
'abNNxyzN-xyzN'
),
(
'
\\
([^N]*N
\\
)+'
,
'abNNxyz'
,
SUCCEED
,
'found+"-"+g1'
,
'abNN-N'
),
(
'
\\
([abc]*
\\
)x'
,
'abcx'
,
SUCCEED
,
'found+"-"+g1'
,
'abcx-abc'
),
(
'
\\
([abc]*
\\
)x'
,
'abc'
,
FAIL
),
(
'
\\
([xyz]*
\\
)x'
,
'abcx'
,
SUCCEED
,
'found+"-"+g1'
,
'x-'
),
(
'
\\
(a
\\
)+b
\\
|aac'
,
'aac'
,
SUCCEED
,
'found+"-"+g1'
,
'aac-None'
)
]
Lib/test/test_regex.py
Dosyayı görüntüle @
876736cd
...
...
@@ -60,3 +60,51 @@ except regex.error:
print
'caught expected exception'
else
:
print
'expected regex.error not raised'
from
regex_tests
import
*
if
verbose
:
print
'Running regex_tests test suite'
for
t
in
tests
:
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
=
regex
.
compile
(
pattern
)
except
regex
.
error
:
if
outcome
==
SYNTAX_ERROR
:
pass
# Expected a syntax error
else
:
# Regex syntax errors aren't yet reported, so for
# the official test suite they'll be quietly ignored.
pass
#print '=== Syntax error:', t
else
:
try
:
result
=
obj
.
search
(
s
)
except
regex
.
error
,
msg
:
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
==-
1
:
pass
# No match, as expected
else
:
print
'=== Succeeded incorrectly'
,
t
elif
outcome
==
SUCCEED
:
if
result
!=-
1
:
# Matched, as expected, so now we compute the
# result string and compare it to our expected result.
start
,
end
=
obj
.
regs
[
0
]
found
=
s
[
start
:
end
]
groups
=
obj
.
group
(
1
,
2
,
3
,
4
,
5
,
6
,
7
,
8
,
9
,
10
)
vardict
=
vars
()
for
i
in
range
(
len
(
groups
)):
vardict
[
'g'
+
str
(
i
+
1
)]
=
str
(
groups
[
i
])
repl
=
eval
(
repl
)
if
repl
!=
expected
:
print
'=== grouping error'
,
t
,
repr
(
repl
)
+
' should be '
+
repr
(
expected
)
else
:
print
'=== Failed incorrectly'
,
t
Write
Preview
Markdown
is supported
0%
Try again
or
attach a new file
Attach a file
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Cancel
Please
register
or
sign in
to comment