From ccc5ae7ae13138eb3acf3a15e92983a49e53dd90 Mon Sep 17 00:00:00 2001 From: "Gregory P. Smith" Date: Mon, 2 Mar 2009 05:21:55 +0000 Subject: Merged revisions 70090 via svnmerge from svn+ssh://pythondev@svn.python.org/python/trunk ........ r70090 | gregory.p.smith | 2009-03-01 21:13:57 -0800 (Sun, 01 Mar 2009) | 3 lines Adds an optional flags argument to re.split, re.sub and re.subn to be consistent with the other re module functions. ........ --- Doc/library/re.rst | 19 ++++++++++++++++--- Lib/re.py | 12 ++++++------ Misc/NEWS | 2 ++ 3 files changed, 24 insertions(+), 9 deletions(-) diff --git a/Doc/library/re.rst b/Doc/library/re.rst index 9399a49..ed50ddb 100644 --- a/Doc/library/re.rst +++ b/Doc/library/re.rst @@ -571,7 +571,7 @@ form. instead. -.. function:: split(pattern, string[, maxsplit=0]) +.. function:: split(pattern, string[, maxsplit=0, flags=0]) Split *string* by the occurrences of *pattern*. If capturing parentheses are used in *pattern*, then the text of all groups in the pattern are also returned @@ -585,6 +585,8 @@ form. ['Words', ', ', 'words', ', ', 'words', '.', ''] >>> re.split('\W+', 'Words, words, words.', 1) ['Words', 'words, words.'] + >>> re.split('[a-f]+', '0a3B9', flags=re.IGNORECASE) + ['0', '3', '9'] If there are capturing groups in the separator and it matches at the start of the string, the result will start with an empty string. The same holds for @@ -605,6 +607,9 @@ form. >>> re.split("(?m)^$", "foo\n\nbar\n") ['foo\n\nbar\n'] + .. versionchanged:: 2.7,3.1 + Added the optional flags argument. + .. function:: findall(pattern, string[, flags]) @@ -625,7 +630,7 @@ form. match. -.. function:: sub(pattern, repl, string[, count]) +.. function:: sub(pattern, repl, string[, count, flags]) Return the string obtained by replacing the leftmost non-overlapping occurrences of *pattern* in *string* by the replacement *repl*. If the pattern isn't found, @@ -650,6 +655,8 @@ form. ... else: return '-' >>> re.sub('-{1,2}', dashrepl, 'pro----gram-files') 'pro--gram files' + >>> re.sub(r'\sAND\s', ' & ', 'Baked Beans And Spam', flags=re.IGNORECASE) + 'Baked Beans & Spam' The pattern may be a string or an RE object; if you need to specify regular expression flags, you must use a RE object, or use embedded modifiers in a @@ -670,12 +677,18 @@ form. character ``'0'``. The backreference ``\g<0>`` substitutes in the entire substring matched by the RE. + .. versionchanged:: 2.7,3.1 + Added the optional flags argument. + -.. function:: subn(pattern, repl, string[, count]) +.. function:: subn(pattern, repl, string[, count, flags]) Perform the same operation as :func:`sub`, but return a tuple ``(new_string, number_of_subs_made)``. + .. versionchanged:: 2.7,3.1 + Added the optional flags argument. + .. function:: escape(string) diff --git a/Lib/re.py b/Lib/re.py index d2fc25d..9bd913a 100644 --- a/Lib/re.py +++ b/Lib/re.py @@ -156,16 +156,16 @@ def search(pattern, string, flags=0): a match object, or None if no match was found.""" return _compile(pattern, flags).search(string) -def sub(pattern, repl, string, count=0): +def sub(pattern, repl, string, count=0, flags=0): """Return the string obtained by replacing the leftmost non-overlapping occurrences of the pattern in string by the replacement repl. repl can be either a string or a callable; if a string, backslash escapes in it are processed. If it is a callable, it's passed the match object and must return a replacement string to be used.""" - return _compile(pattern, 0).sub(repl, string, count) + return _compile(pattern, flags).sub(repl, string, count) -def subn(pattern, repl, string, count=0): +def subn(pattern, repl, string, count=0, flags=0): """Return a 2-tuple containing (new_string, number). new_string is the string obtained by replacing the leftmost non-overlapping occurrences of the pattern in the source @@ -174,12 +174,12 @@ def subn(pattern, repl, string, count=0): callable; if a string, backslash escapes in it are processed. If it is a callable, it's passed the match object and must return a replacement string to be used.""" - return _compile(pattern, 0).subn(repl, string, count) + return _compile(pattern, flags).subn(repl, string, count) -def split(pattern, string, maxsplit=0): +def split(pattern, string, maxsplit=0, flags=0): """Split the source string by the occurrences of the pattern, returning a list containing the resulting substrings.""" - return _compile(pattern, 0).split(string, maxsplit) + return _compile(pattern, flags).split(string, maxsplit) def findall(pattern, string, flags=0): """Return a list of all non-overlapping matches in the string. diff --git a/Misc/NEWS b/Misc/NEWS index 7f5a99b..0272e79 100644 --- a/Misc/NEWS +++ b/Misc/NEWS @@ -170,6 +170,8 @@ Core and Builtins - Issue #4748: Lambda generators no longer return a value. +- The re.sub(), re.subn() and re.split() functions now accept a flags parameter. + Library ------- -- cgit v0.12