mirror of
git://git.code.sf.net/p/zsh/code
synced 2025-01-01 05:16:05 +01:00
23375: Phil Pennock: =~, zsh/regex etc. etc.
This commit is contained in:
parent
eb4c3d4bf2
commit
7f03c3d851
14 changed files with 392 additions and 51 deletions
|
@ -1,3 +1,12 @@
|
|||
2007-05-01 Peter Stephenson <p.w.stephenson@ntlworld.com>
|
||||
|
||||
* Phil Pennock + tweaks: 23375: configure.ac, Doc/Makefile.in,
|
||||
Doc/Zsh/cond.yo, Doc/Zsh/mod_pcre.yo, Doc/Zsh/options.yo,
|
||||
Src/cond.c, Src/options.c, Src/parse.c, Src/text.c, Src/zsh.h,
|
||||
Src/Modules/pcre.c, Src/Modules/regex.c, Src/Modules/regex.mdd:
|
||||
Add zsh/regex option, =~ syntax and related options
|
||||
BASH_REMATCH, NO_CASE_MATCH, RE_MATCH_PCRE.
|
||||
|
||||
2007-05-01 Peter Stephenson <pws@csr.com>
|
||||
|
||||
* unposted: Doc/Zsh/contrib.yo: typo in widget name.
|
||||
|
|
|
@ -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 \
|
||||
|
|
|
@ -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.
|
||||
|
|
|
@ -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()
|
||||
|
||||
|
|
|
@ -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>)(
|
||||
|
|
|
@ -3,7 +3,7 @@
|
|||
*
|
||||
* This file is part of zsh, the Z shell.
|
||||
*
|
||||
* Copyright (c) 2001, 2002, 2003, 2004 Clint Adams
|
||||
* Copyright (c) 2001, 2002, 2003, 2004, 2007 Clint Adams
|
||||
* All rights reserved.
|
||||
*
|
||||
* Permission is hereby granted, without written agreement and without
|
||||
|
@ -40,6 +40,37 @@
|
|||
static pcre *pcre_pattern;
|
||||
static pcre_extra *pcre_hints;
|
||||
|
||||
/**/
|
||||
static int
|
||||
zpcre_utf8_enabled(void)
|
||||
{
|
||||
#if defined(MULTIBYTE_SUPPORT) && defined(HAVE_NL_LANGINFO) && defined(CODESET)
|
||||
static int have_utf8_pcre = -1;
|
||||
|
||||
/* value can toggle based on MULTIBYTE, so don't
|
||||
* be too eager with caching */
|
||||
if (have_utf8_pcre < -1)
|
||||
return 0;
|
||||
|
||||
if (!isset(MULTIBYTE))
|
||||
return 0;
|
||||
|
||||
if ((have_utf8_pcre == -1) &&
|
||||
(!strcmp(nl_langinfo(CODESET), "UTF-8"))) {
|
||||
|
||||
if (pcre_config(PCRE_CONFIG_UTF8, &have_utf8_pcre))
|
||||
have_utf8_pcre = -2; /* erk, failed to ask */
|
||||
}
|
||||
|
||||
if (have_utf8_pcre < 0)
|
||||
return 0;
|
||||
return have_utf8_pcre;
|
||||
|
||||
#else
|
||||
return 0;
|
||||
#endif
|
||||
}
|
||||
|
||||
/**/
|
||||
static int
|
||||
bin_pcre_compile(char *nam, char **args, Options ops, UNUSED(int func))
|
||||
|
@ -52,8 +83,14 @@ bin_pcre_compile(char *nam, char **args, Options ops, UNUSED(int func))
|
|||
if(OPT_ISSET(ops,'m')) pcre_opts |= PCRE_MULTILINE;
|
||||
if(OPT_ISSET(ops,'x')) pcre_opts |= PCRE_EXTENDED;
|
||||
|
||||
if (zpcre_utf8_enabled())
|
||||
pcre_opts |= PCRE_UTF8;
|
||||
|
||||
pcre_hints = NULL; /* Is this necessary? */
|
||||
|
||||
if (pcre_pattern)
|
||||
pcre_free(pcre_pattern);
|
||||
|
||||
pcre_pattern = pcre_compile(*args, pcre_opts, &pcre_error, &pcre_errptr, NULL);
|
||||
|
||||
if (pcre_pattern == NULL)
|
||||
|
@ -100,37 +137,52 @@ bin_pcre_study(char *nam, UNUSED(char **args), UNUSED(Options ops), UNUSED(int f
|
|||
|
||||
/**/
|
||||
static int
|
||||
zpcre_get_substrings(char *arg, int *ovec, int ret, char *receptacle)
|
||||
zpcre_get_substrings(char *arg, int *ovec, int ret, char *matchvar, char *substravar, int matchedinarr)
|
||||
{
|
||||
char **captures, **matches;
|
||||
char **captures, **match_all, **matches;
|
||||
int capture_start = 1;
|
||||
|
||||
if(!pcre_get_substring_list(arg, ovec, ret, (const char ***)&captures)) {
|
||||
|
||||
matches = zarrdup(&captures[1]); /* first one would be entire string */
|
||||
if (receptacle == NULL)
|
||||
setaparam("match", matches);
|
||||
else
|
||||
setaparam(receptacle, matches);
|
||||
|
||||
pcre_free_substring_list((const char **)captures);
|
||||
}
|
||||
if (matchedinarr)
|
||||
capture_start = 0;
|
||||
if (matchvar == NULL)
|
||||
matchvar = "MATCH";
|
||||
if (substravar == NULL)
|
||||
substravar = "match";
|
||||
|
||||
return 0;
|
||||
/* captures[0] will be entire matched string, [1] first substring */
|
||||
if(!pcre_get_substring_list(arg, ovec, ret, (const char ***)&captures)) {
|
||||
match_all = ztrdup(captures[0]);
|
||||
setsparam(matchvar, match_all);
|
||||
matches = zarrdup(&captures[capture_start]);
|
||||
setaparam(substravar, matches);
|
||||
pcre_free_substring_list((const char **)captures);
|
||||
}
|
||||
|
||||
return 0;
|
||||
}
|
||||
|
||||
/**/
|
||||
static int
|
||||
bin_pcre_match(char *nam, char **args, Options ops, UNUSED(int func))
|
||||
{
|
||||
int ret, capcount, *ovec, ovecsize;
|
||||
int ret, capcount, *ovec, ovecsize, c;
|
||||
char *matched_portion = NULL;
|
||||
char *receptacle = NULL;
|
||||
int return_value = 1;
|
||||
|
||||
if (pcre_pattern == NULL) {
|
||||
zwarnnam(nam, "no pattern has been compiled");
|
||||
return 1;
|
||||
}
|
||||
|
||||
if(OPT_ISSET(ops,'a')) {
|
||||
receptacle = *args++;
|
||||
if(!*args) {
|
||||
zwarnnam(nam, "not enough arguments");
|
||||
return 1;
|
||||
}
|
||||
if(OPT_HASARG(ops,c='a')) {
|
||||
receptacle = OPT_ARG(ops,c);
|
||||
}
|
||||
if(OPT_HASARG(ops,c='v')) {
|
||||
matched_portion = OPT_ARG(ops,c);
|
||||
}
|
||||
if(!*args) {
|
||||
zwarnnam(nam, "not enough arguments");
|
||||
}
|
||||
|
||||
if ((ret = pcre_fullinfo(pcre_pattern, pcre_hints, PCRE_INFO_CAPTURECOUNT, &capcount)))
|
||||
|
@ -144,18 +196,20 @@ bin_pcre_match(char *nam, char **args, Options ops, UNUSED(int func))
|
|||
|
||||
ret = pcre_exec(pcre_pattern, pcre_hints, *args, strlen(*args), 0, 0, ovec, ovecsize);
|
||||
|
||||
if (ret==0) return 0;
|
||||
else if (ret==PCRE_ERROR_NOMATCH) return 1; /* no match */
|
||||
if (ret==0) return_value = 0;
|
||||
else if (ret==PCRE_ERROR_NOMATCH) /* no match */;
|
||||
else if (ret>0) {
|
||||
zpcre_get_substrings(*args, ovec, ret, receptacle);
|
||||
return 0;
|
||||
zpcre_get_substrings(*args, ovec, ret, matched_portion, receptacle, 0);
|
||||
return_value = 0;
|
||||
}
|
||||
else {
|
||||
zwarnnam(nam, "error in pcre_exec");
|
||||
return 1;
|
||||
}
|
||||
|
||||
return 1;
|
||||
if (ovec)
|
||||
zfree(ovec, ovecsize*sizeof(int));
|
||||
|
||||
return return_value;
|
||||
}
|
||||
|
||||
/**/
|
||||
|
@ -164,33 +218,63 @@ cond_pcre_match(char **a, int id)
|
|||
{
|
||||
pcre *pcre_pat;
|
||||
const char *pcre_err;
|
||||
char *lhstr, *rhre;
|
||||
char *lhstr, *rhre, *avar=NULL;
|
||||
int r = 0, pcre_opts = 0, pcre_errptr, capcnt, *ov, ovsize;
|
||||
int return_value = 0;
|
||||
|
||||
if (zpcre_utf8_enabled())
|
||||
pcre_opts |= PCRE_UTF8;
|
||||
|
||||
lhstr = cond_str(a,0,0);
|
||||
rhre = cond_str(a,1,0);
|
||||
pcre_pat = ov = NULL;
|
||||
|
||||
if (isset(BASHREMATCH))
|
||||
avar="BASH_REMATCH";
|
||||
|
||||
switch(id) {
|
||||
case CPCRE_PLAIN:
|
||||
pcre_pat = pcre_compile(rhre, pcre_opts, &pcre_err, &pcre_errptr, NULL);
|
||||
pcre_fullinfo(pcre_pat, NULL, PCRE_INFO_CAPTURECOUNT, &capcnt);
|
||||
ovsize = (capcnt+1)*3;
|
||||
ov = zalloc(ovsize*sizeof(int));
|
||||
r = pcre_exec(pcre_pat, NULL, lhstr, strlen(lhstr), 0, 0, ov, ovsize);
|
||||
if (r==0) return 1;
|
||||
pcre_pat = pcre_compile(rhre, pcre_opts, &pcre_err, &pcre_errptr, NULL);
|
||||
if (pcre_pat == NULL) {
|
||||
zwarn("failed to compile regexp /%s/: %s", rhre, pcre_err);
|
||||
break;
|
||||
}
|
||||
pcre_fullinfo(pcre_pat, NULL, PCRE_INFO_CAPTURECOUNT, &capcnt);
|
||||
ovsize = (capcnt+1)*3;
|
||||
ov = zalloc(ovsize*sizeof(int));
|
||||
r = pcre_exec(pcre_pat, NULL, lhstr, strlen(lhstr), 0, 0, ov, ovsize);
|
||||
/* r < 0 => error; r==0 match but not enough size in ov
|
||||
* r > 0 => (r-1) substrings found; r==1 => no substrings
|
||||
*/
|
||||
if (r==0) {
|
||||
zwarn("reportable zsh problem: pcre_exec() returned 0");
|
||||
return_value = 1;
|
||||
break;
|
||||
}
|
||||
else if (r==PCRE_ERROR_NOMATCH) return 0; /* no match */
|
||||
else if (r<0) {
|
||||
zwarn("pcre_exec() error: %d", r);
|
||||
break;
|
||||
}
|
||||
else if (r>0) {
|
||||
zpcre_get_substrings(lhstr, ov, r, NULL);
|
||||
return 1;
|
||||
zpcre_get_substrings(lhstr, ov, r, NULL, avar, isset(BASHREMATCH));
|
||||
return_value = 1;
|
||||
break;
|
||||
}
|
||||
break;
|
||||
}
|
||||
|
||||
return 0;
|
||||
if (pcre_pat)
|
||||
pcre_free(pcre_pat);
|
||||
if (ov)
|
||||
zfree(ov, ovsize*sizeof(int));
|
||||
|
||||
return return_value;
|
||||
}
|
||||
|
||||
static struct conddef cotab[] = {
|
||||
CONDDEF("pcre-match", CONDF_INFIX, cond_pcre_match, 0, 0, CPCRE_PLAIN)
|
||||
/* CONDDEF can register =~ but it won't be found */
|
||||
};
|
||||
|
||||
/**/
|
||||
|
@ -206,7 +290,7 @@ static struct conddef cotab[] = {
|
|||
static struct builtin bintab[] = {
|
||||
BUILTIN("pcre_compile", 0, bin_pcre_compile, 1, 1, 0, "aimx", NULL),
|
||||
BUILTIN("pcre_study", 0, bin_pcre_study, 0, 0, 0, NULL, NULL),
|
||||
BUILTIN("pcre_match", 0, bin_pcre_match, 1, 2, 0, "a", NULL)
|
||||
BUILTIN("pcre_match", 0, bin_pcre_match, 1, 1, 0, "a:v:", NULL)
|
||||
};
|
||||
|
||||
|
||||
|
|
161
Src/Modules/regex.c
Normal file
161
Src/Modules/regex.c
Normal file
|
@ -0,0 +1,161 @@
|
|||
/*
|
||||
* regex.c
|
||||
*
|
||||
* This file is part of zsh, the Z shell.
|
||||
*
|
||||
* Copyright (c) 2007 Phil Pennock
|
||||
* All Rights Reserved.
|
||||
*
|
||||
* Permission is hereby granted, without written agreement and without
|
||||
* license or royalty fees, to use, copy, modify, and distribute this
|
||||
* software and to distribute modified versions of this software for any
|
||||
* purpose, provided that the above copyright notice and the following
|
||||
* two paragraphs appear in all copies of this software.
|
||||
*
|
||||
* In no event shall Phil Pennock or the Zsh Development Group be liable
|
||||
* to any party for direct, indirect, special, incidental, or consequential
|
||||
* damages arising out of the use of this software and its documentation,
|
||||
* even if Phil Pennock and the Zsh Development Group have been advised of
|
||||
* the possibility of such damage.
|
||||
*
|
||||
* Phil Pennock and the Zsh Development Group specifically disclaim any
|
||||
* warranties, including, but not limited to, the implied warranties of
|
||||
* merchantability and fitness for a particular purpose. The software
|
||||
* provided hereunder is on an "as is" basis, and Phil Pennock and the
|
||||
* Zsh Development Group have no obligation to provide maintenance,
|
||||
* support, updates, enhancements, or modifications.
|
||||
*
|
||||
*/
|
||||
|
||||
#include "regex.mdh"
|
||||
#include "regex.pro"
|
||||
|
||||
#include <regex.h>
|
||||
|
||||
/* we default to a vaguely modern syntax and set of capabilities */
|
||||
#define ZREGEX_EXTENDED 0
|
||||
/* if you want Basic syntax, make it an alternative options */
|
||||
|
||||
static void
|
||||
zregex_regerrwarn(int r, regex_t *re, char *msg)
|
||||
{
|
||||
char *errbuf;
|
||||
size_t errbufsz;
|
||||
|
||||
errbufsz = regerror(r, re, NULL, 0);
|
||||
errbuf = zalloc(errbufsz*sizeof(char));
|
||||
regerror(r, re, errbuf, errbufsz);
|
||||
zwarn("%s: %s", msg, errbuf);
|
||||
zfree(errbuf, errbufsz);
|
||||
}
|
||||
|
||||
/**/
|
||||
static int
|
||||
zcond_regex_match(char **a, int id)
|
||||
{
|
||||
regex_t re;
|
||||
regmatch_t *m, *matches = NULL;
|
||||
size_t matchessz;
|
||||
char *lhstr, *rhre, *s, **arr, **x;
|
||||
int r, n, return_value, rcflags, reflags, nelem, start;
|
||||
|
||||
lhstr = cond_str(a,0,0);
|
||||
rhre = cond_str(a,1,0);
|
||||
rcflags = reflags = 0;
|
||||
return_value = 0; /* 1 => matched successfully */
|
||||
|
||||
switch(id) {
|
||||
case ZREGEX_EXTENDED:
|
||||
rcflags |= REG_EXTENDED;
|
||||
if (!isset(CASEMATCH))
|
||||
rcflags |= REG_ICASE;
|
||||
r = regcomp(&re, rhre, rcflags);
|
||||
if (r) {
|
||||
zregex_regerrwarn(r, &re, "failed to compile regex");
|
||||
break;
|
||||
}
|
||||
/* re.re_nsub is number of parenthesized groups, we also need
|
||||
* 1 for the 0 offset, which is the entire matched portion
|
||||
*/
|
||||
if (re.re_nsub < 0) {
|
||||
zwarn("INTERNAL ERROR: regcomp() returned "
|
||||
"negative subpattern count %d", re.re_nsub);
|
||||
break;
|
||||
}
|
||||
matchessz = (re.re_nsub + 1) * sizeof(regmatch_t);
|
||||
matches = zalloc(matchessz);
|
||||
r = regexec(&re, lhstr, re.re_nsub+1, matches, reflags);
|
||||
if (r == REG_NOMATCH) /**/;
|
||||
else if (r == 0) {
|
||||
return_value = 1;
|
||||
if (isset(BASHREMATCH)) {
|
||||
start = 0;
|
||||
nelem = re.re_nsub + 1;
|
||||
} else {
|
||||
start = 1;
|
||||
nelem = re.re_nsub;
|
||||
}
|
||||
arr = NULL; /* bogus gcc warning of used uninitialised */
|
||||
/* entire matched portion + re_nsub substrings + NULL */
|
||||
if (nelem) {
|
||||
arr = x = (char **) zalloc(sizeof(char *) * (nelem + 1));
|
||||
for (m = matches + start, n = start; n <= re.re_nsub; ++n, ++m, ++x) {
|
||||
*x = ztrduppfx(lhstr + m->rm_so, m->rm_eo - m->rm_so);
|
||||
}
|
||||
*x = NULL;
|
||||
}
|
||||
if (isset(BASHREMATCH)) {
|
||||
setaparam("BASH_REMATCH", arr);
|
||||
} else {
|
||||
m = matches;
|
||||
s = ztrduppfx(lhstr + m->rm_so, m->rm_eo - m->rm_so);
|
||||
setsparam("MATCH", s);
|
||||
if (nelem)
|
||||
setaparam("match", arr);
|
||||
}
|
||||
}
|
||||
else zregex_regerrwarn(r, &re, "regex matching error");
|
||||
break;
|
||||
default:
|
||||
DPUTS(1, "bad regex option");
|
||||
break;
|
||||
}
|
||||
|
||||
if (matches)
|
||||
zfree(matches, matchessz);
|
||||
regfree(&re);
|
||||
return return_value;
|
||||
}
|
||||
|
||||
static struct conddef cotab[] = {
|
||||
CONDDEF("regex-match", CONDF_INFIX, zcond_regex_match, 0, 0, ZREGEX_EXTENDED)
|
||||
};
|
||||
|
||||
/**/
|
||||
int
|
||||
setup_(UNUSED(Module m))
|
||||
{
|
||||
return 0;
|
||||
}
|
||||
|
||||
/**/
|
||||
int
|
||||
boot_(Module m)
|
||||
{
|
||||
return !addconddefs(m->nam, cotab, sizeof(cotab)/sizeof(*cotab));
|
||||
}
|
||||
|
||||
/**/
|
||||
int
|
||||
cleanup_(Module m)
|
||||
{
|
||||
deleteconddefs(m->nam, cotab, sizeof(cotab)/sizeof(*cotab));
|
||||
return 0;
|
||||
}
|
||||
|
||||
/**/
|
||||
int
|
||||
finish_(UNUSED(Module m))
|
||||
{
|
||||
return 0;
|
||||
}
|
10
Src/Modules/regex.mdd
Normal file
10
Src/Modules/regex.mdd
Normal file
|
@ -0,0 +1,10 @@
|
|||
name=zsh/regex
|
||||
link=`if test x$ac_cv_func_regcomp = xyes && \
|
||||
test x$ac_cv_func_regexec = xyes && \
|
||||
test x$ac_cv_func_regerror = xyes && \
|
||||
test x$ac_cv_func_regfree = xyes; then echo dynamic; else echo no; fi`
|
||||
load=no
|
||||
|
||||
autobins=""
|
||||
|
||||
objects="regex.o"
|
26
Src/cond.c
26
Src/cond.c
|
@ -34,7 +34,7 @@ int tracingcond;
|
|||
|
||||
static char *condstr[COND_MOD] = {
|
||||
"!", "&&", "||", "==", "!=", "<", ">", "-nt", "-ot", "-ef", "-eq",
|
||||
"-ne", "-lt", "-gt", "-le", "-ge"
|
||||
"-ne", "-lt", "-gt", "-le", "-ge", "=~"
|
||||
};
|
||||
|
||||
/*
|
||||
|
@ -53,14 +53,14 @@ int
|
|||
evalcond(Estate state, char *fromtest)
|
||||
{
|
||||
struct stat *st;
|
||||
char *left, *right;
|
||||
char *left, *right, *overridename, overridebuf[13];
|
||||
Wordcode pcode;
|
||||
wordcode code;
|
||||
int ctype, htok = 0, ret;
|
||||
|
||||
rec:
|
||||
|
||||
left = right = NULL;
|
||||
left = right = overridename = NULL;
|
||||
pcode = state->pc++;
|
||||
code = *pcode;
|
||||
ctype = WC_COND_TYPE(code);
|
||||
|
@ -92,13 +92,28 @@ evalcond(Estate state, char *fromtest)
|
|||
state->pc = pcode + (WC_COND_SKIP(code) + 1);
|
||||
return ret;
|
||||
}
|
||||
case COND_REGEX:
|
||||
{
|
||||
char *modname = isset(REMATCHPCRE) ? "zsh/pcre" : "zsh/regex";
|
||||
if (!load_module_silence(modname, 1)) {
|
||||
zwarnnam(fromtest, "%s not available for regex",
|
||||
modname);
|
||||
return 2;
|
||||
}
|
||||
sprintf(overridename = overridebuf, "-%s-match", modname+4);
|
||||
ctype = COND_MODI;
|
||||
}
|
||||
/*FALLTHROUGH*/
|
||||
case COND_MOD:
|
||||
case COND_MODI:
|
||||
{
|
||||
Conddef cd;
|
||||
char *name = ecgetstr(state, EC_NODUP, NULL), **strs;
|
||||
char *name = overridename;
|
||||
char **strs;
|
||||
int l = WC_COND_SKIP(code);
|
||||
|
||||
if (name == NULL)
|
||||
name = ecgetstr(state, EC_NODUP, NULL);
|
||||
if (ctype == COND_MOD)
|
||||
strs = ecgetarr(state, l, EC_DUP, NULL);
|
||||
else {
|
||||
|
@ -139,7 +154,8 @@ evalcond(Estate state, char *fromtest)
|
|||
return !cd->handler(strs, cd->condid);
|
||||
} else {
|
||||
zwarnnam(fromtest,
|
||||
"unrecognized condition: `%s'", name);
|
||||
"unrecognized condition: `%s'",
|
||||
name ? name : "<null>");
|
||||
}
|
||||
}
|
||||
/* module not found, error */
|
||||
|
|
|
@ -88,11 +88,13 @@ static struct optname optns[] = {
|
|||
{{NULL, "banghist", OPT_NONBOURNE}, BANGHIST},
|
||||
{{NULL, "bareglobqual", OPT_EMULATE|OPT_ZSH}, BAREGLOBQUAL},
|
||||
{{NULL, "bashautolist", 0}, BASHAUTOLIST},
|
||||
{{NULL, "bashrematch", 0}, BASHREMATCH},
|
||||
{{NULL, "beep", OPT_ALL}, BEEP},
|
||||
{{NULL, "bgnice", OPT_EMULATE|OPT_NONBOURNE},BGNICE},
|
||||
{{NULL, "braceccl", OPT_EMULATE}, BRACECCL},
|
||||
{{NULL, "bsdecho", OPT_EMULATE|OPT_SH}, BSDECHO},
|
||||
{{NULL, "caseglob", OPT_ALL}, CASEGLOB},
|
||||
{{NULL, "casematch", OPT_ALL}, CASEMATCH},
|
||||
{{NULL, "cbases", 0}, CBASES},
|
||||
{{NULL, "cdablevars", OPT_EMULATE}, CDABLEVARS},
|
||||
{{NULL, "chasedots", OPT_EMULATE}, CHASEDOTS},
|
||||
|
@ -201,6 +203,7 @@ static struct optname optns[] = {
|
|||
{{NULL, "rcquotes", OPT_EMULATE}, RCQUOTES},
|
||||
{{NULL, "rcs", OPT_ALL}, RCS},
|
||||
{{NULL, "recexact", 0}, RECEXACT},
|
||||
{{NULL, "rematchpcre", 0}, REMATCHPCRE},
|
||||
{{NULL, "restricted", OPT_SPECIAL}, RESTRICTED},
|
||||
{{NULL, "rmstarsilent", OPT_BOURNE}, RMSTARSILENT},
|
||||
{{NULL, "rmstarwait", 0}, RMSTARWAIT},
|
||||
|
|
|
@ -2124,6 +2124,12 @@ par_cond_triple(char *a, char *b, char *c)
|
|||
ecstr(a);
|
||||
ecstr(c);
|
||||
ecadd(ecnpats++);
|
||||
} else if ((b[0] == Equals || b[0] == '=') &&
|
||||
(b[1] == '~' || b[1] == Tilde) && ~b[2]) {
|
||||
ecadd(WCB_COND(COND_REGEX, 0));
|
||||
ecstr(a);
|
||||
ecstr(c);
|
||||
ecadd(ecnpats++);
|
||||
} else if (b[0] == '-') {
|
||||
if ((t0 = get_cond_num(b + 1)) > -1) {
|
||||
ecadd(WCB_COND(t0 + COND_NT, 0));
|
||||
|
|
|
@ -640,7 +640,7 @@ gettext2(Estate state)
|
|||
{
|
||||
static char *c1[] = {
|
||||
"=", "!=", "<", ">", "-nt", "-ot", "-ef", "-eq",
|
||||
"-ne", "-lt", "-gt", "-le", "-ge"
|
||||
"-ne", "-lt", "-gt", "-le", "-ge", "=~"
|
||||
};
|
||||
|
||||
int ctype;
|
||||
|
@ -724,7 +724,7 @@ gettext2(Estate state)
|
|||
}
|
||||
break;
|
||||
default:
|
||||
if (ctype <= COND_GE) {
|
||||
if (ctype < COND_MOD) {
|
||||
/* Binary test: `a = b' etc. */
|
||||
taddstr(ecgetstr(state, EC_NODUP, NULL));
|
||||
taddstr(" ");
|
||||
|
|
|
@ -519,8 +519,9 @@ struct timedfn {
|
|||
#define COND_GT 13
|
||||
#define COND_LE 14
|
||||
#define COND_GE 15
|
||||
#define COND_MOD 16
|
||||
#define COND_MODI 17
|
||||
#define COND_REGEX 16
|
||||
#define COND_MOD 17
|
||||
#define COND_MODI 18
|
||||
|
||||
typedef int (*CondHandler) _((char **, int));
|
||||
|
||||
|
@ -1588,11 +1589,13 @@ enum {
|
|||
BANGHIST,
|
||||
BAREGLOBQUAL,
|
||||
BASHAUTOLIST,
|
||||
BASHREMATCH,
|
||||
BEEP,
|
||||
BGNICE,
|
||||
BRACECCL,
|
||||
BSDECHO,
|
||||
CASEGLOB,
|
||||
CASEMATCH,
|
||||
CBASES,
|
||||
CDABLEVARS,
|
||||
CHASEDOTS,
|
||||
|
@ -1695,6 +1698,7 @@ enum {
|
|||
RCQUOTES,
|
||||
RCS,
|
||||
RECEXACT,
|
||||
REMATCHPCRE,
|
||||
RESTRICTED,
|
||||
RMSTARSILENT,
|
||||
RMSTARWAIT,
|
||||
|
|
|
@ -1135,7 +1135,8 @@ AC_CHECK_FUNCS(strftime strptime mktime timelocal \
|
|||
erand48 open_memstream \
|
||||
wctomb iconv \
|
||||
grantpt unlockpt ptsname \
|
||||
htons ntohs)
|
||||
htons ntohs \
|
||||
regcomp regexec regerror regfree)
|
||||
AC_FUNC_STRCOLL
|
||||
|
||||
if test x$enable_cap = xyes; then
|
||||
|
|
Loading…
Reference in a new issue