23375: Phil Pennock: =~, zsh/regex etc. etc.

4 files changed, 50 insertions, 3 deletions

diff --git a/Doc/Makefile.in b/Doc/Makefile.in
index 711376ae9..3938c4d03 100644
--- a/Doc/Makefile.in
+++ b/Doc/Makefile.in
@@ -61,7 +61,7 @@ Zsh/mod_computil.yo \
 Zsh/mod_datetime.yo Zsh/mod_deltochar.yo \
 Zsh/mod_example.yo Zsh/mod_files.yo \
 Zsh/mod_mapfile.yo Zsh/mod_mathfunc.yo Zsh/mod_newuser.yo \
-Zsh/mod_parameter.yo Zsh/mod_pcre.yo \
+Zsh/mod_parameter.yo Zsh/mod_pcre.yo Zsh/mod_regex.yo \
 Zsh/mod_sched.yo Zsh/mod_socket.yo \
 Zsh/mod_stat.yo  Zsh/mod_system.yo Zsh/mod_tcp.yo \
 Zsh/mod_termcap.yo Zsh/mod_terminfo.yo \
diff --git a/Doc/Zsh/cond.yo b/Doc/Zsh/cond.yo
index 49e42d50d..1b7630d78 100644
--- a/Doc/Zsh/cond.yo
+++ b/Doc/Zsh/cond.yo
@@ -109,6 +109,20 @@ backward compatibility and should be considered obsolete.
 item(var(string) tt(!=) var(pattern))(
 true if var(string) does not match var(pattern).
 )
+item(var(string) tt(=~) var(regexp))(
+true if var(string) matches the regular expression
+var(regexp).  If the option tt(RE_MATCH_PCRE) is set
+var(regexp) is tested as a PCRE regular expression using
+the tt(zsh/pcre) module, else it is tested as a POSIX
+regular expression using the tt(zsh/regex) module.
+If the option tt(BASH_REMATCH) is set the array
+tt(BASH_REMATCH) is set to the substring that matched the pattern
+followed by the substrings that matched parenthesised
+subexpressions within the pattern; otherwise, the scalar parameter
+tt(MATCH) is set to the substring that matched the pattern and
+and the array tt(match) to the substrings that matched parenthesised
+subexpressions.
+)
 item(var(string1) tt(<) var(string2))(
 true if var(string1) comes before var(string2)
 based on ASCII value of their characters.
diff --git a/Doc/Zsh/mod_pcre.yo b/Doc/Zsh/mod_pcre.yo
index 58833823a..f6131f5e4 100644
--- a/Doc/Zsh/mod_pcre.yo
+++ b/Doc/Zsh/mod_pcre.yo
@@ -22,14 +22,17 @@ Studies the previously-compiled PCRE which may result in faster
 matching.
 )
 findex(pcre_match)
-item(tt(pcre_match) [ tt(-a) var(arr) ] var(string))(
+item(tt(pcre_match) [ tt(-v) var(var) ] [ tt(-a) var(arr) ] var(string))(
 Returns successfully if tt(string) matches the previously-compiled
 PCRE.
 
 If the expression captures substrings within parentheses,
 tt(pcre_match) will set the array var($match) to those
 substrings, unless the tt(-a) option is given, in which
-case it will set the array var(arr).
+case it will set the array var(arr).  Similarly, the variable
+var(MATCH) will be set to the entire matched portion of the
+string, unless the tt(-v) option is given, in which case the variable
+var(var) will be set.
 )
 enditem()
 
diff --git a/Doc/Zsh/options.yo b/Doc/Zsh/options.yo
index 7933e16c9..c8b651132 100644
--- a/Doc/Zsh/options.yo
+++ b/Doc/Zsh/options.yo
@@ -319,6 +319,13 @@ will cause case-insensitive matching.  For example, tt(cvs+LPAR()/+RPAR())
 can match the directory tt(CVS) owing to the presence of the globbing flag
 (unless the option tt(BARE_GLOB_QUAL) is unset).
 )
+pindex(CASE_MATCH)
+cindex(case-insensitive regular expression matches, option)
+cindex(regular expressions, case-insensitive matching, option)
+item(tt(CASE_MATCH) <D>)(
+Make regular expressions using the tt(zsh/regex) module (including
+matches with tt(=~)) sensitive to case.
+)
 pindex(CSH_NULL_GLOB)
 cindex(csh, null globbing style)
 cindex(null globbing style, csh)
@@ -478,6 +485,15 @@ var(xx) is set to tt(LPAR())var(a b c)tt(RPAR()), are substituted with
 `var(fooabar foobbar foocbar)' instead of the default
 `var(fooa b cbar)'.
 )
+pindex(REMATCH_PCRE)
+cindex(regexp, PCRE)
+cindex(PCRE, regexp)
+item(tt(REMATCH_PCRE) <Z>)(
+If set, regular expression matching with the tt(=~) operator will use
+Perl-Compatible Regular Expressions from the PCRE library, if available.
+If not set, regular expressions will use the extended regexp syntax
+provided by the system libraries.
+)
 pindex(SH_GLOB)
 cindex(sh, globbing style)
 cindex(globbing style, sh)
@@ -1131,6 +1147,20 @@ enditem()
 
 subsect(Shell Emulation)
 startitem()
+pindex(BASH_REMATCH)
+cindex(bash, BASH_REMATCH variable)
+cindex(regexp, bash BASH_REMATCH variable)
+item(tt(BASH_REMATCH))(
+When set, matches performed with the tt(=~) operator will set the
+tt(BASH_REMATCH) array variable, instead of the default tt(MATCH) and
+tt(match) variables.  The first element of the tt(BASH_REMATCH) array
+will contain the entire matched text and subsequent elements will contain
+extracted substrings.  This option makes more sense when tt(KSH_ARRAYS) is
+also set, so that the entire matched portion is stored at index 0 and the
+first substring is at index 1.  Without this option, the tt(MATCH) variable
+contains the entire matched text and the tt(match) array variable contains
+substrings.
+)
 pindex(BSD_ECHO)
 cindex(echo, BSD compatible)
 item(tt(BSD_ECHO) <S>)(