X-Git-Url: http://git.vpit.fr/?a=blobdiff_plain;f=README;h=19cb5b7733ad7e7ffc72bc5b3341f9bf2647be33;hb=39b3bffa90cd07a8edd6ff9e22481bc61c33dd6a;hp=78cc7d9bb2899804970eb42790848b5c1eb3aa2b;hpb=7bcbae57add0ff30a2c4b9c70b679a3a65c7bc34;p=perl%2Fmodules%2FRegexp-Wildcards.git diff --git a/README b/README index 78cc7d9..19cb5b7 100644 --- a/README +++ b/README @@ -3,7 +3,7 @@ NAME expressions. VERSION - Version 1.00 + Version 1.02 SYNOPSIS use Regexp::Wildcards; @@ -14,7 +14,7 @@ SYNOPSIS $re = $rw->convert('a{b?,c}*'); # Do it Unix shell style. $re = $rw->convert('a?,b*', 'win32'); # Do it Windows shell style. $re = $rw->convert('*{x,y}?', 'jokers'); # Process the jokers and escape the rest. - $re = $rw->convert('%a_c%', 'sql'); # Turn SQL wildcards into regexps. + $re = $rw->convert('%a_c%', 'sql'); # Turn SQL wildcards into regexps. $rw = Regexp::Wildcards->new( do => [ qw/jokers brackets/ ], # Do jokers and brackets. @@ -33,8 +33,9 @@ DESCRIPTION regular expressions, so that you can use them for matching. It handles the "*" and "?" jokers, as well as Unix bracketed - alternatives "{,}", but also "%" and "_" SQL wildcards. It can also keep - original "(...)" groups. Backspace ("\") is used as an escape character. + alternatives "{,}", but also "%" and "_" SQL wildcards. If required, it + can also keep original "(...)" groups or "^" and "$" anchors. Backspace + ("\") is used as an escape character. Typesets that mimic the behaviour of Windows and Unix shells are also provided. @@ -54,39 +55,53 @@ METHODS more details. "do [ $what | set => $c1, add => $c2, rem => $c3 ]" - Specifies the list of metacharacters to convert. They are classified - into five classes : + Specifies the list of metacharacters to convert or to prevent for + escaping. They fit into six classes : + + * 'jokers' converts "?" to "." and "*" to ".*" ; - 'jokers' converts "?" to "." and "*" to ".*" ; 'a**\\*b??\\?c' ==> 'a.*\\*b..\\?c' - 'sql' converts "_" to "." and "%" to ".*" ; + * 'sql' converts "_" to "." and "%" to ".*" ; + 'a%%\\%b__\\_c' ==> 'a.*\\%b..\\_c' - 'commas' converts all "," to "|" and puts the complete resulting regular - expression inside "(?: ... )" ; + * 'commas' converts all "," to "|" and puts the complete resulting + regular expression inside "(?: ... )" ; + 'a,b{c,d},e' ==> '(?:a|b\\{c|d\\}|e)' - 'brackets' converts all matching "{ ... , ... }" brackets to "(?: ... | - ... )" alternations. If some brackets are unbalanced, it tries to - substitute as many of them as possible, and then escape the remaining - unmatched "{" and "}". Commas outside of any bracket-delimited block are - also escaped ; + * 'brackets' converts all matching "{ ... , ... }" brackets to "(?: + ... | ... )" alternations. If some brackets are unbalanced, it tries + to substitute as many of them as possible, and then escape the + remaining unmatched "{" and "}". Commas outside of any + bracket-delimited block are also escaped ; + 'a,b{c,d},e' ==> 'a\\,b(?:c|d)\\,e' '{a\\{b,c}d,e}' ==> '(?:a\\{b|c)d\\,e\\}' '{a{b,c\\}d,e}' ==> '\\{a\\{b\\,c\\}d\\,e\\}' - 'groups' keeps the parenthesis "( ... )" of the original string without - escaping them. Currently, no check is done to ensure that the - parenthesis are matching. + * 'groups' keeps the parenthesis "( ... )" of the original string + without escaping them. Currently, no check is done to ensure that + the parenthesis are matching. + 'a(b(c))d\\(\\)' ==> (no change) + * 'anchors' prevents the *beginning-of-line* "^" and *end-of-line* "$" + anchors to be escaped. Since "[...]" character class are currently + escaped, a "^" will always be interpreted as *beginning-of-line*. + + 'a^b$c' ==> (no change) + Each $c can be any of : - A hash reference, with wanted metacharacter group names (described - above) as keys and booleans as values ; - An array reference containing the list of wanted metacharacter classes ; - A plain scalar, when only one group is required. + * A hash reference, with wanted metacharacter group names (described + above) as keys and booleans as values ; + + * An array reference containing the list of wanted metacharacter + classes ; + + * A plain scalar, when only one group is required. When "set" is present, the classes given as its value replace the current object options. Then the "add" classes are added, and the "rem" @@ -116,22 +131,26 @@ METHODS Specifies the list of atoms to capture. This method works like "do", except that the classes are different : - 'single' will capture all unescaped *"exactly one"* metacharacters, i.e. - "?" for wildcards or "_" for SQL ; + * 'single' will capture all unescaped *"exactly one"* metacharacters, + i.e. "?" for wildcards or "_" for SQL ; + 'a???b\\??' ==> 'a(.)(.)(.)b\\?(.)' 'a___b\\__' ==> 'a(.)(.)(.)b\\_(.)' - 'any' will capture all unescaped *"any"* metacharacters, i.e. "*" for - wildcards or "%" for SQL ; + * 'any' will capture all unescaped *"any"* metacharacters, i.e. "*" + for wildcards or "%" for SQL ; + 'a***b\\**' ==> 'a(.*)b\\*(.*)' 'a%%%b\\%%' ==> 'a(.*)b\\%(.*)' - 'greedy', when used in conjunction with 'any', will make the 'any' - captures greedy (by default they are not) ; + * 'greedy', when used in conjunction with 'any', will make the 'any' + captures greedy (by default they are not) ; + 'a***b\\**' ==> 'a(.*?)b\\*(.*?)' 'a%%%b\\%%' ==> 'a(.*?)b\\%(.*?)' - 'brackets' will capture matching "{ ... , ... }" alternations. + * 'brackets' will capture matching "{ ... , ... }" alternations. + 'a{b\\},\\{c}' ==> 'a(b\\}|\\{c)' $rw->capture(set => 'single'); # Only capture "exactly one" metacharacters.