52253: support pcre callouts with shell evaluation of the callout string

ChangeLog

@@ -1,5 +1,8 @@
 2023-11-02  Oliver Kiddle  <opk@zsh.org>
 
+	* 52253: Src/Modules/pcre.c: support pcre callouts with shell
+	evaluation of the callout string
+
 	* 52260: Completion/Unix/Command/_sudo: handle variable assignments
 	before the command in sudo completion
 

Doc/Zsh/mod_pcre.yo

@@ -69,6 +69,11 @@ print -l $accum)
 )
 enditem()
 
+If the regular expression contains callouts, these are executed as shell code.
+During the execution of the callout, the string the regular expression is
+matching against is available in the parameter tt(.pcre.subject). If there is a
+non-zero return status from the shell code, the callout does not match.
+
 The option tt(-d) uses the alternative breadth-first DFA search algorithm of
 pcre. This sets tt(match), or the array given with tt(-a), to all the matches
 found from the same start point in the subject.

Src/Modules/pcre.c

@@ -128,6 +128,31 @@ bin_pcre_study(char *nam, UNUSED(char **args), UNUSED(Options ops), UNUSED(int f
     return 0;
 }
 
+static int
+pcre_callout(pcre2_callout_block_8 *block, void *)
+{
+    Eprog prog;
+    int ret=0;
+
+    if (!block->callout_number &&
+	    ((prog = parse_string((char *) block->callout_string, 0))))
+    {
+	int ef = errflag, lv = lastval;
+
+	setsparam(".pcre.subject",
+		metafy((char *) block->subject, block->subject_length, META_DUP));
+	setiparam(".pcre.pos", block->current_position + 1);
+	execode(prog, 1, 0, "pcre");
+	ret = lastval | errflag;
+
+	/* Restore any user interrupt error status */
+	errflag = ef | (errflag & ERRFLAG_INT);
+	lastval = lv;
+    }
+
+    return ret;
+}
+
 static int
 zpcre_get_substrings(pcre2_code *pat, char *arg, pcre2_match_data *mdata,
 	int captured_count, char *matchvar, char *substravar, char *namedassoc,
@@ -339,6 +364,9 @@ bin_pcre_match(char *nam, char **args, Options ops, UNUSED(int func))
     plaintext = ztrdup(*args);
     unmetafy(plaintext, &subject_len);
 
+    pcre2_match_context_8 *mcontext = pcre2_match_context_create(NULL);
+    pcre2_set_callout(mcontext, &pcre_callout, 0);
+
     if (offset_start > 0 && offset_start >= subject_len)
 	ret = PCRE2_ERROR_NOMATCH;
     else if (use_dfa) {
@@ -347,7 +375,7 @@ bin_pcre_match(char *nam, char **args, Options ops, UNUSED(int func))
 	pcre_mdata = pcre2_match_data_create(capcount, NULL);
 	do {
 	    ret = pcre2_dfa_match(pcre_pattern, (PCRE2_SPTR) plaintext, subject_len,
-		offset_start, 0, pcre_mdata, NULL, (int *) workspace, wscount);
+		offset_start, 0, pcre_mdata, mcontext, (int *) workspace, wscount);
 	    if (ret == PCRE2_ERROR_DFA_WSSIZE) {
 		old = wscount;
 		wscount += wscount / 2;
@@ -362,7 +390,7 @@ bin_pcre_match(char *nam, char **args, Options ops, UNUSED(int func))
     } else {
 	pcre_mdata = pcre2_match_data_create_from_pattern(pcre_pattern, NULL);
 	ret = pcre2_match(pcre_pattern, (PCRE2_SPTR) plaintext, subject_len,
-		offset_start, 0, pcre_mdata, NULL);
+		offset_start, 0, pcre_mdata, mcontext);
     }
 
     if (ret==0) return_value = 0;
@@ -380,6 +408,8 @@ bin_pcre_match(char *nam, char **args, Options ops, UNUSED(int func))
     
     if (pcre_mdata)
 	pcre2_match_data_free(pcre_mdata);
+    if (mcontext)
+	pcre2_match_context_free(mcontext);
     zsfree(plaintext);
 
     return return_value;