X-Git-Url: https://code.citadel.org/?a=blobdiff_plain;f=citadel%2Fserver%2Fmodules%2Ffulltext%2Fft_wordbreaker.c;h=5f510e82027c3d9a1dd124a9182be4681449f5cc;hb=2bf4ae9ae7e2c80380b4c8369754b2b5fa455e52;hp=d8a11e55cfd437ddfab4a104a13609d3862190bf;hpb=d0fa5441a64b2ce2be78b3a72e726fa6b0c416cd;p=citadel.git

diff --git a/citadel/server/modules/fulltext/ft_wordbreaker.c b/citadel/server/modules/fulltext/ft_wordbreaker.c
index d8a11e55c..5f510e820 100644
--- a/citadel/server/modules/fulltext/ft_wordbreaker.c
+++ b/citadel/server/modules/fulltext/ft_wordbreaker.c
@@ -1,16 +1,7 @@
-/*
- * Default wordbreaker module for full text indexing.
- *
- * Copyright (c) 2005-2017 by the citadel.org team
- *
- * This program is open source software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 3.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- */
+// Default wordbreaker module for full text indexing.
+//
+// Copyright (c) 2005-2024 by the citadel.org team
+// This program is open source software.  Use, duplication, or disclosure is subject to the GNU General Public License v3.
 
 #include "../../sysdep.h"
 #include <stdlib.h>
@@ -40,11 +31,8 @@
 #include "crc16.h"
 #include "../../ctdl_module.h"
 
-/*
- * Noise words are not included in search indices.
- * NOTE: if the noise word list is altered in any way, the FT_WORDBREAKER_ID
- * must also be changed, so that the index is rebuilt.
- */
+// Noise words are not included in search indices.
+// NOTE: if the noise word list is altered in any way, the FT_WORDBREAKER_ID must also be changed, so that the index is rebuilt.
 static char *noise_words[] = {
 	"about",
 	"after",
@@ -111,9 +99,7 @@ static char *noise_words[] = {
 #define NUM_NOISE (sizeof(noise_words) / sizeof(char *))
 
 
-/*
- * Compare function
- */
+// Compare function
 int intcmp(const void *rec1, const void *rec2) {
 	int i1, i2;
 
@@ -136,11 +122,11 @@ Array *wordbreaker(const char *text) {
 	int i;
 	int word_crc;
 
-	if (text == NULL) {		/* no NULL text please */
+	if (text == NULL) {		// no NULL text please
 		return(NULL);
 	}
 
-	if (text[0] == 0) {		/* no empty text either */
+	if (text[0] == 0) {		// no empty text either
 		return(NULL);
 	}
 
@@ -163,7 +149,7 @@ Array *wordbreaker(const char *text) {
 		if ( (!isalnum(ch)) && (word_start) ) {
 			word_end = ptr;
 
-			/* extract the word */
+			// extract the word
 			word_len = word_end - word_start;
 			if (word_len >= sizeof word) {
 				syslog(LOG_DEBUG, "wordbreaker: invalid word length: %d", word_len);
@@ -176,20 +162,19 @@ Array *wordbreaker(const char *text) {
 			}
 			word_start = NULL;
 
-			/* are we ok with the length? */
+			// are we ok with the length?
 			if ( (word_len >= WB_MIN) && (word_len <= WB_MAX) ) {
 				for (i=0; i<word_len; ++i) {
 					word[i] = tolower(word[i]);
 				}
-				/* disqualify noise words */
+				// disqualify noise words
 				for (i=0; i<NUM_NOISE; ++i) {
 					if (!strcasecmp(word, noise_words[i])) {
 						word_len = 0;
 						break;
 					}
 				}
-				/* FIXME make this case insensitive */
-				/* add it to the array */
+				// add it to the array (FIXME make this case insensitive)
 				if (word_len > 0) {
 					word_crc = (int) CalcCRC16Bytes(word_len, word);
 					array_append(found_tokens, &word_crc);
@@ -198,7 +183,7 @@ Array *wordbreaker(const char *text) {
 		}
 	}
 
-	/* sort and purge dups */
+	// sort and purge dups
 	if (array_len(found_tokens) > 1) {
 		array_sort(found_tokens, intcmp);
 		for (i=0; i<(array_len(found_tokens)); ++i) {
@@ -210,4 +195,3 @@ Array *wordbreaker(const char *text) {
 	}
 	return(found_tokens);
 }
-