From ffe1f41595f39a24aab5f83829dcb8ea3c423238 Mon Sep 17 00:00:00 2001 From: Reuben Thomas Date: Wed, 18 Aug 2010 00:11:33 +0100 Subject: [PATCH 2/2] Document syntax flags better. regex.texi: Add documentation for missing syntax flags. regex.h: correct and clarify documentation for RE_CONTEXT_INVALID_DUP Remove commented-out documentation of defunct syntax option RE_NO_EMPTY_ALTS. Correct name of RE_CHAR_CLASSES in one incorrect occurrence. --- doc/regex.texi | 84 ++++++++++++++++++++++++++++++++++---------------------- lib/regex.h | 4 +- 2 files changed, 53 insertions(+), 35 deletions(-) diff --git a/doc/regex.texi b/doc/regex.texi index 59dfd8b..5147e7a 100644 --- a/doc/regex.texi +++ b/doc/regex.texi @@ -159,6 +159,12 @@ open-group or alternation operator. The same holds for @samp{@{} (or it is the beginning of a valid interval and the syntax bit @code{RE_INTERVALS} is set. +@cnindex RE_CONTEXT_INVALID_DUP +@item RE_CONTEXT_INVALID_DUP +If this bit is set, then an open-interval operator cannot occur at the +start of a regular expression, or immediately after an alternation, +open-group or close-interval operator. + @cnindex RE_CONTEXT_INVALID_OPS @item RE_CONTEXT_INVALID_OPS If this bit is set, then repetition and alternation operators can't be @@ -183,6 +189,12 @@ repetition and alternation characters anywhere in a regular expression. Whether or not they will in fact be operators in certain positions depends on other syntax bits. +@cnindex RE_DEBUG +@item RE_DEBUG +If this bit is set, and the regex library was compiled with +@code{-DDEBUG}, then internal debugging is turned on; if unset, then +it is turned off. + @cnindex RE_DOT_NEWLINE @item RE_DOT_NEWLINE If this bit is set, then the match-any-character operator matches @@ -193,11 +205,27 @@ a newline; if this bit isn't set, then it doesn't. If this bit is set, then the match-any-character operator doesn't match a null character; if this bit isn't set, then it does. +@cnindex RE_HAT_LISTS_NOT_NEWLINE +@item RE_HAT_LISTS_NOT_NEWLINE +If this bit is set, nonmatching lists @samp{[^...]} do not match +newline; if not set, they do. + +@cnindex RE_ICASE +@item RE_ICASE +If this bit is set, then ignore case when matching; otherwise, case is +significant. + @cnindex RE_INTERVALS @item RE_INTERVALS If this bit is set, then Regex recognizes interval operators; if this bit isn't set, then it doesn't. +@cnindex RE_INVALID_INTERVAL_ORD +@item RE_INVALID_INTERVAL_ORD +If this bit is set, a syntactically invalid interval is treated as a +string of ordinary characters. For example, the extended regular +expression @samp{a{1} is treated as @samp{a\{1}. + @cnindex RE_LIMITED_OPS @item RE_LIMITED_OPS If this bit is set, then Regex doesn't recognize the match-one-or-more, @@ -241,6 +269,22 @@ If this bit is set, then a regular expression with a range whose ending point collates lower than its starting point is invalid; if this bit isn't set, then Regex considers such a range to be empty. +@cnindex RE_NO_GNU_OPS +@item RE_NO_GNU_OPS +If this bit is set, GNU regex operators are not recognized; otherwise, +they are. + +@cnindex RE_NO_POSIX_BACKTRACKING +@item RE_NO_POSIX_BACKTRACKING +If this bit is set, succeed as soon as we match the whole pattern, +without further backtracking. This means that a match may not be +the leftmost longest; @pxref{What Gets Matched?} for what this means. + +@cnindex RE_NO_SUB +@item RE_NO_SUB +If this bit is set, then @code{no_sub} will be set to one during +@code{re_compile_pattern}; @pxref{POSIX Matching}, for what this means. + @cnindex RE_UNMATCHED_RIGHT_PAREN_ORD @item RE_UNMATCHED_RIGHT_PAREN_ORD If this bit is set and the regular expression has no matching open-group @@ -713,32 +757,6 @@ example, supposing that @samp{|} is the alternation operator, then @samp{foo|bar|quux} would match any of @samp{foo}, @samp{bar} or @samp{quux}. -@ignore -@c Nobody needs to disallow empty alternatives any more. -If the syntax bit @code{RE_NO_EMPTY_ALTS} is set, then if either of the regular -expressions @var{a} or @var{b} is empty, the -regular expression is invalid. More precisely, if this syntax bit is -set, then the alternation operator can't: - -@itemize @bullet -@item -be first or last in a regular expression; - -@item -follow either another alternation operator or an open-group operator -(@pxref{Grouping Operators}); or - -@item -precede a close-group operator. - -@end itemize - -@noindent -For example, supposing @samp{(} and @samp{)} represent the open and -close-group operators, then @samp{|foo}, @samp{foo|}, @samp{foo||bar}, -@samp{foo(|bar)}, and @samp{(foo|)bar} would all be invalid. -@end ignore - The alternation operator operates on the @emph{largest} possible surrounding regular expressions. (Put another way, it has the lowest precedence of any regular expression operator.) @@ -908,13 +926,13 @@ symbol. @cindex @samp{[:} in regex @cindex @samp{:]} in regex -If the syntax bit @code{RE_CHARACTER_CLASSES} is set, then Regex -recognizes character class expressions inside lists. A @dfn{character -class expression} matches one character from a given class. You form a -character class expression by putting a character class name between an -@dfn{open-character-class operator} (represented by @samp{[:}) and a -@dfn{close-character-class operator} (represented by @samp{:]}). The -character class names and their meanings are: +If the syntax bit @code{RE_CHAR_CLASSES} is set, then Regex recognizes +character class expressions inside lists. A @dfn{character class +expression} matches one character from a given class. You form a +character class expression by putting a character class name between +an @dfn{open-character-class operator} (represented by @samp{[:}) and +a @dfn{close-character-class operator} (represented by @samp{:]}). +The character class names and their meanings are: @table @code diff --git a/lib/regex.h b/lib/regex.h index a239c31..053e612 100644 --- a/lib/regex.h +++ b/lib/regex.h @@ -219,8 +219,8 @@ typedef unsigned long int reg_syntax_t; whether ^ should be special. */ # define RE_CARET_ANCHORS_HERE (RE_ICASE << 1) -/* If this bit is set, then \{ cannot be first in an bre or - immediately after an alternation or begin-group operator. */ +/* If this bit is set, then \{ cannot be first in a regex or + immediately after an alternation, open-group or \} operator. */ # define RE_CONTEXT_INVALID_DUP (RE_CARET_ANCHORS_HERE << 1) /* If this bit is set, then no_sub will be set to 1 during -- 1.7.1