Jon Strait: 26778, 26781: extra options for PCRE matching

ChangeLog

@@ -1,5 +1,8 @@
 2009-03-25  Peter Stephenson  <pws@csr.com>
 
+	* Jon Strait: 26778, 26781: Doc/Zsh/mod_pcre.yo,
+	Src/Modules/pcre.c:  a couple of extra options for PCRE matching.
+
 	* Michael Hwang: 26776: Src/builtin.c: improved column alignment
 	with print -c -P.
 
@@ -11487,5 +11490,5 @@
 
 *****************************************************
 * This is used by the shell to define $ZSH_PATCHLEVEL
-* $Revision: 1.4636 $
+* $Revision: 1.4637 $
 *****************************************************

Doc/Zsh/mod_pcre.yo

@@ -6,7 +6,7 @@ The tt(zsh/pcre) module makes some commands available as builtins:
 
 startitem()
 findex(pcre_compile)
-item(tt(pcre_compile) [ tt(-aimx) ] var(PCRE))(
+item(tt(pcre_compile) [ tt(-aimxs) ] var(PCRE))(
 Compiles a perl-compatible regular expression.
 
 Option tt(-a) will force the pattern to be anchored.
@@ -15,6 +15,8 @@ Option tt(-m) will compile a multi-line pattern; that is,
 tt(^) and tt($) will match newlines within the pattern.
 Option tt(-x) will compile an extended pattern, wherein
 whitespace and tt(#) comments are ignored.
+Option tt(-s) makes the dot metacharacter match all characters,
+including those that indicate newline.
 )
 findex(pcre_study)
 item(tt(pcre_study))(
@@ -22,7 +24,8 @@ Studies the previously-compiled PCRE which may result in faster
 matching.
 )
 findex(pcre_match)
-item(tt(pcre_match) [ tt(-v) var(var) ] [ tt(-a) var(arr) ] var(string))(
+item(tt(pcre_match) [ tt(-v) var(var) ] [ tt(-a) var(arr) ] \
+[ tt(-n) var(offset) ] [ tt(-b) ] var(string))(
 Returns successfully if tt(string) matches the previously-compiled
 PCRE.
 
@@ -35,6 +38,36 @@ 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.
 No variables are altered if there is no successful match.
+A tt(-n) option starts searching for a match from the
+byte var(offset) position in var(string).  If the tt(-b) option is given,
+the variable var(ZPCRE_OP) will be set to an offset pair string,
+representing the byte offset positions of the entire matched portion
+within the var(string).  For example, a var(ZPCRE_OP) set to "32 45" indicates
+that the matched portion began on byte offset 32 and ended on byte offset 44.
+Here, byte offset position 45 is the position directly after the matched
+portion.  Keep in mind that the byte position isn't necessarily the same
+as the character position when UTF-8 characters are involved.
+Consequently, the byte offset positions are only to be relied on in the
+context of using them for subsequent searches on var(string), using an offset
+position as an argument to the tt(-n) option.  This is mostly
+used to implement the "find all non-overlapping matches" functionality.
+
+A simple example of "find all non-overlapping matches":
+
+example(
+string="The following zip codes: 78884 90210 99513"
+pcre_compile -m "\d{5}"
+accum=()
+pcre_match -b -- $string
+while [[ $? -eq 0 ]] do
+    b=($=ZPCRE_OP)
+    accum+=$MATCH
+    pcre_match -b -n $b[2] -- $string
+done
+print -l $accum
+
+
+)
 )
 enditem()
 

Src/Modules/pcre.c

@@ -82,6 +82,7 @@ bin_pcre_compile(char *nam, char **args, Options ops, UNUSED(int func))
     if(OPT_ISSET(ops,'i')) pcre_opts |= PCRE_CASELESS;
     if(OPT_ISSET(ops,'m')) pcre_opts |= PCRE_MULTILINE;
     if(OPT_ISSET(ops,'x')) pcre_opts |= PCRE_EXTENDED;
+    if(OPT_ISSET(ops,'s')) pcre_opts |= PCRE_DOTALL;
     
     if (zpcre_utf8_enabled())
 	pcre_opts |= PCRE_UTF8;
@@ -137,9 +138,11 @@ 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 *matchvar, char *substravar, int matchedinarr)
+zpcre_get_substrings(char *arg, int *ovec, int ret, char *matchvar, char *substravar, 
+    int want_offset_pair, int matchedinarr)
 {
     char **captures, *match_all, **matches;
+    char offset_all[50];
     int capture_start = 1;
 
     if (matchedinarr)
@@ -148,9 +151,14 @@ zpcre_get_substrings(char *arg, int *ovec, int ret, char *matchvar, char *substr
 	matchvar = "MATCH";
     if (substravar == NULL)
 	substravar = "match";
-
+    
     /* captures[0] will be entire matched string, [1] first substring */
-    if(!pcre_get_substring_list(arg, ovec, ret, (const char ***)&captures)) {
+    if (!pcre_get_substring_list(arg, ovec, ret, (const char ***)&captures)) {
+	/* Set to the offsets of the complete match */
+	if (want_offset_pair) {
+	    sprintf(offset_all, "%d %d", ovec[0], ovec[1]);
+	    setsparam("ZPCRE_OP", ztrdup(offset_all));
+	}
 	match_all = ztrdup(captures[0]);
 	setsparam(matchvar, match_all);
 	matches = zarrdup(&captures[capture_start]);
@@ -161,6 +169,22 @@ zpcre_get_substrings(char *arg, int *ovec, int ret, char *matchvar, char *substr
     return 0;
 }
 
+/**/
+static int
+getposint(char *instr, char *nam)
+{
+    char *eptr;
+    int ret;
+
+    ret = (int)zstrtol(instr, &eptr, 10);
+    if (*eptr || ret < 0) {
+	zwarnnam(nam, "integer expected: %s", instr);
+	return -1;
+    }
+
+    return ret;
+}
+
 /**/
 static int
 bin_pcre_match(char *nam, char **args, Options ops, UNUSED(int func))
@@ -169,6 +193,10 @@ bin_pcre_match(char *nam, char **args, Options ops, UNUSED(int func))
     char *matched_portion = NULL;
     char *receptacle = NULL;
     int return_value = 1;
+    /* The subject length and offset start are both int values in pcre_exec */
+    int subject_len;
+    int offset_start = 0;
+    int want_offset_pair = 0;
 
     if (pcre_pattern == NULL) {
 	zwarnnam(nam, "no pattern has been compiled");
@@ -181,6 +209,12 @@ bin_pcre_match(char *nam, char **args, Options ops, UNUSED(int func))
     if(OPT_HASARG(ops,c='v')) {
 	matched_portion = OPT_ARG(ops,c);
     }
+    if(OPT_HASARG(ops,c='n')) { /* The offset position to start the search, in bytes. */
+	offset_start = getposint(OPT_ARG(ops,c), nam);
+    }
+    /* For the entire match, 'Return' the offset byte positions instead of the matched string */
+    if(OPT_ISSET(ops,'b')) want_offset_pair = 1; 
+    
     if(!*args) {
 	zwarnnam(nam, "not enough arguments");
     }
@@ -194,12 +228,17 @@ bin_pcre_match(char *nam, char **args, Options ops, UNUSED(int func))
     ovecsize = (capcount+1)*3;
     ovec = zalloc(ovecsize*sizeof(int));
     
-    ret = pcre_exec(pcre_pattern, pcre_hints, *args, strlen(*args), 0, 0, ovec, ovecsize);
-    
+    subject_len = (int)strlen(*args);
+
+    if (offset_start < 0 || offset_start >= subject_len)
+	ret = PCRE_ERROR_NOMATCH;
+    else
+	ret = pcre_exec(pcre_pattern, pcre_hints, *args, subject_len, offset_start, 0, ovec, ovecsize);
+
     if (ret==0) return_value = 0;
     else if (ret==PCRE_ERROR_NOMATCH) /* no match */;
     else if (ret>0) {
-	zpcre_get_substrings(*args, ovec, ret, matched_portion, receptacle, 0);
+	zpcre_get_substrings(*args, ovec, ret, matched_portion, receptacle, want_offset_pair, 0);
 	return_value = 0;
     }
     else {
@@ -258,7 +297,7 @@ cond_pcre_match(char **a, int id)
 		    break;
 		}
                 else if (r>0) {
-		    zpcre_get_substrings(lhstr, ov, r, NULL, avar, isset(BASHREMATCH));
+		    zpcre_get_substrings(lhstr, ov, r, NULL, avar, 0, isset(BASHREMATCH));
 		    return_value = 1;
 		    break;
 		}
@@ -289,8 +328,8 @@ static struct conddef cotab[] = {
 #endif /* !(HAVE_PCRE_COMPILE && HAVE_PCRE_EXEC) */
 
 static struct builtin bintab[] = {
-    BUILTIN("pcre_compile", 0, bin_pcre_compile, 1, 1, 0, "aimx",  NULL),
-    BUILTIN("pcre_match",   0, bin_pcre_match,   1, 1, 0, "a:v:",    NULL),
+    BUILTIN("pcre_compile", 0, bin_pcre_compile, 1, 1, 0, "aimxs",  NULL),
+    BUILTIN("pcre_match",   0, bin_pcre_match,   1, 1, 0, "a:v:n:b",    NULL),
     BUILTIN("pcre_study",   0, bin_pcre_study,   0, 0, 0, NULL,    NULL)
 };