field() function now supports a string as field delimiter

also done a  bugfix: field() function did never return "***FIELD NOT FOUND***"
instead it returned "***ERROR in field() FUNCTION***" in that case

3 files changed, 73 insertions, 9 deletions

diff --git a/ChangeLog b/ChangeLog
index 3746d3f1..4944987c 100644
--- a/ChangeLog
+++ b/ChangeLog
@@ -1,7 +1,10 @@
 ---------------------------------------------------------------------------
 Version 7.3.7  [devel] 2013-02-??
+- field() function now supports a string as field delimiter
 - bugfix: mmjsonparse segfault if new-style config was used
 - bugfix: script == comparison did not work properly on JSON objects
+- bugfix: field() function did never return "***FIELD NOT FOUND***"
+  instead it returned "***ERROR in field() FUNCTION***" in that case
 ---------------------------------------------------------------------------
 Version 7.3.6  [devel] 2013-01-28
 - greatly improved speed of large-array  [N]EQ RainerScript comparisons
diff --git a/doc/rainerscript.html b/doc/rainerscript.html
index c9f00386..d76316ed 100644
--- a/doc/rainerscript.html
+++ b/doc/rainerscript.html
@@ -67,10 +67,20 @@ variable, if it exists. Returns an empty string if it does not exist.
 <li>cnum(expr) - converts expr to a number (integer)
 <li>re_match(expr, re) - returns 1, if expr matches re, 0 otherwise
 <li>field(str, delim, matchnbr) - returns a field-based substring. str is the string
-to search, delim is the numerical ascii value of the field delimiter (so that
-non-printable characters can by specified) and matchnbr is the match to search
+to search, delim is the delimiter and matchnbr is the match to search
 for (the first match starts at 1). This works similar as the field based
 property-replacer option.
+Versions prior to 7.3.7 only support a single character as delimiter character.
+Starting with version 7.3.7, a full string can be used as delimiter. If a single
+character is being used as delimiter,   delim is the numerical ascii value of the
+field delimiter character (so that non-printable characters can by specified). If a
+string is used as delmiter, a multi-character string (e.g. "#011") is to be
+specified. Samples:<br>
+set $!usr!field = field($msg, 32, 3); -- the third field, delimited by space<br>
+set $!usr!field = field($msg, "#011", 3); -- the third field, delmited by "#011"<br>
+Note that when a single character is specified as string [field($msg, ",", 3)] a
+string-based extraction is done, which is more performance intense than the
+equivalent single-character [field($msg, 44 ,3)] extraction.
 <li>prifilt(constant) - mimics a traditional PRI-based filter (like "*.*" or
 "mail.info"). The traditional filter string must be given as a <b>constant string</b>.
 Dynamic string evaluation is not permitted (for performance reasons).
diff --git a/grammar/rainerscript.c b/grammar/rainerscript.c
index 83ed7680..6dbdad63 100644
--- a/grammar/rainerscript.c
+++ b/grammar/rainerscript.c
@@ -1137,8 +1137,8 @@ var2CString(struct var *r, int *bMustFree)
 	return cstr;
 }
 
-rsRetVal
-doExtractField(uchar *str, uchar delim, int matchnbr, uchar **resstr)
+static rsRetVal
+doExtractFieldByChar(uchar *str, uchar delim, int matchnbr, uchar **resstr)
 {
 	int iCurrFld;
 	int iLen;
@@ -1175,8 +1175,51 @@ doExtractField(uchar *str, uchar delim, int matchnbr, uchar **resstr)
 		/* now copy */
 		memcpy(pBuf, pFld, iLen);
 		pBuf[iLen] = '\0'; /* terminate it */
-		if(*(pFldEnd+1) != '\0')
-			++pFldEnd; /* OK, skip again over delimiter char */
+		*resstr = pBuf;
+	} else {
+		ABORT_FINALIZE(RS_RET_FIELD_NOT_FOUND);
+	}
+finalize_it:
+	RETiRet;
+}
+
+
+static rsRetVal
+doExtractFieldByStr(uchar *str, char *delim, rs_size_t lenDelim, int matchnbr, uchar **resstr)
+{
+	int iCurrFld;
+	int iLen;
+	uchar *pBuf;
+	uchar *pFld;
+	uchar *pFldEnd;
+	DEFiRet;
+
+	/* first, skip to the field in question */
+	iCurrFld = 1;
+	pFld = str;
+	while(pFld != NULL && iCurrFld < matchnbr) {
+		if((pFld = (uchar*) strstr((char*)pFld, delim)) != NULL) {
+			pFld += lenDelim;
+			++iCurrFld;
+		}
+	}
+	dbgprintf("field() field requested %d, field found %d\n", matchnbr, iCurrFld);
+	
+	if(iCurrFld == matchnbr) {
+		/* field found, now extract it */
+		/* first of all, we need to find the end */
+		pFldEnd = (uchar*) strstr((char*)pFld, delim);
+		if(pFldEnd == NULL) {
+			iLen = strlen((char*) pFld);
+		} else { /* found delmiter!  Note that pFldEnd *is* already on 
+			  * the first delmi char, we don't need that. */
+			iLen = pFldEnd - pFld;
+		}
+		/* we got our end pointer, now do the copy */
+		CHKmalloc(pBuf = MALLOC((iLen + 1) * sizeof(char)));
+		/* now copy */
+		memcpy(pBuf, pFld, iLen);
+		pBuf[iLen] = '\0'; /* terminate it */
 		*resstr = pBuf;
 	} else {
 		ABORT_FINALIZE(RS_RET_FIELD_NOT_FOUND);
@@ -1289,13 +1332,21 @@ doFuncCall(struct cnffunc *func, struct var *ret, void* usrptr)
 		cnfexprEval(func->expr[1], &r[1], usrptr);
 		cnfexprEval(func->expr[2], &r[2], usrptr);
 		str = (char*) var2CString(&r[0], &bMustFree);
-		delim = var2Number(&r[1], NULL);
 		matchnbr = var2Number(&r[2], NULL);
-		localRet = doExtractField((uchar*)str, (char) delim, matchnbr, &resStr);
+		if(r[1].datatype == 'S') {
+			char *delimstr;
+			delimstr = (char*) es_str2cstr(r[1].d.estr, NULL);
+			localRet = doExtractFieldByStr((uchar*)str, delimstr, es_strlen(r[1].d.estr),
+							matchnbr, &resStr);
+			free(delimstr);
+		} else {
+			delim = var2Number(&r[1], NULL);
+			localRet = doExtractFieldByChar((uchar*)str, (char) delim, matchnbr, &resStr);
+		}
 		if(localRet == RS_RET_OK) {
 			ret->d.estr = es_newStrFromCStr((char*)resStr, strlen((char*)resStr));
 			free(resStr);
-		} else if(localRet == RS_RET_OK) {
+		} else if(localRet == RS_RET_FIELD_NOT_FOUND) {
 			ret->d.estr = es_newStrFromCStr("***FIELD NOT FOUND***",
 					sizeof("***FIELD NOT FOUND***")-1);
 		} else {