[Minor] Fix `www.` prefix matcher

diff --git a/src/libmime/scan_result.c b/src/libmime/scan_result.c
index 080fc0d510d0252e77c2792183660be427b0c010..e84d924944bcb492a7ed662d64ed27119a6f4171 100644 (file)
--- a/src/libmime/scan_result.c
+++ b/src/libmime/scan_result.c
@@ -52,6 +52,7 @@ rspamd_scan_result_dtor(gpointer d)
                        kh_destroy(rspamd_options_hash, sres->options);
                }
        });
+
        kh_destroy(rspamd_symbols_hash, r->symbols);
        kh_destroy(rspamd_symbols_group_hash, r->sym_groups);
 }

diff --git a/src/libmime/scan_result.h b/src/libmime/scan_result.h
index da3fb16088005c5aff175f7563d69917f06fe5ca..46c2de8faee2afd181f55828836806650c54b743 100644 (file)
--- a/src/libmime/scan_result.h
+++ b/src/libmime/scan_result.h
@@ -1,3 +1,19 @@
+/*
+ * Copyright 2023 Vsevolod Stakhov
+ *
+ * Licensed under the Apache License, Version 2.0 (the "License");
+ * you may not use this file except in compliance with the License.
+ * You may obtain a copy of the License at
+ *
+ *    http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
 /**
  * @file scan_result.h
  * Scan result holder
@@ -43,7 +59,7 @@ struct rspamd_symbol_result {
        gssize opts_len;           /**< total size of all options (negative if truncated option is added) */
        guint nshots;
        int flags;
-       struct rspamd_symbol_result *next;
+       struct rspamd_symbol_result *next; /**< for shadow results */
 };
 
 

diff --git a/src/libserver/url.c b/src/libserver/url.c
index ca0b2072e9df7104b5a8e07153257ca34f76534a..0842a1ebd7ed4a9f7bb825a615f7394a85750cd6 100644 (file)
--- a/src/libserver/url.c
+++ b/src/libserver/url.c
@@ -38,10 +38,10 @@ typedef struct url_match_s {
        gchar st;
 } url_match_t;
 
-#define URL_FLAG_NOHTML (1u << 0u)
-#define URL_FLAG_TLD_MATCH (1u << 1u)
-#define URL_FLAG_STAR_MATCH (1u << 2u)
-#define URL_FLAG_REGEXP (1u << 3u)
+#define URL_MATCHER_FLAG_NOHTML (1u << 0u)
+#define URL_MATCHER_FLAG_TLD_MATCH (1u << 1u)
+#define URL_MATCHER_FLAG_STAR_MATCH (1u << 2u)
+#define URL_MATCHER_FLAG_REGEXP (1u << 3u)
 
 struct url_callback_data;
 
@@ -163,8 +163,8 @@ struct url_matcher static_matchers[] = {
         0},
        {"sip:", "", url_web_start, url_web_end,
         0},
-       {"www.", "http://", url_web_start, url_web_end,
-        0},
+       {"www\\.[0-9a-z]", "http://", url_web_start, url_web_end,
+        URL_MATCHER_FLAG_REGEXP},
        {"ftp.", "ftp://", url_web_start, url_web_end,
         0},
        /* Likely emails */
@@ -449,10 +449,10 @@ rspamd_url_parse_tld_file(const gchar *fname,
                        continue;
                }
 
-               flags = URL_FLAG_NOHTML | URL_FLAG_TLD_MATCH;
+               flags = URL_MATCHER_FLAG_NOHTML | URL_MATCHER_FLAG_TLD_MATCH;
 
                if (linebuf[0] == '*') {
-                       flags |= URL_FLAG_STAR_MATCH;
+                       flags |= URL_MATCHER_FLAG_STAR_MATCH;
                        p = strchr(linebuf, '.');
 
                        if (p == NULL) {
@@ -486,7 +486,7 @@ rspamd_url_add_static_matchers(struct url_match_scanner *sc)
        gint n = G_N_ELEMENTS(static_matchers), i;
 
        for (i = 0; i < n; i++) {
-               if (static_matchers[i].flags & URL_FLAG_REGEXP) {
+               if (static_matchers[i].flags & URL_MATCHER_FLAG_REGEXP) {
                        rspamd_multipattern_add_pattern(url_scanner->search_trie_strict,
                                                                                        static_matchers[i].pattern,
                                                                                        RSPAMD_MULTIPATTERN_ICASE | RSPAMD_MULTIPATTERN_UTF8 |
@@ -503,7 +503,7 @@ rspamd_url_add_static_matchers(struct url_match_scanner *sc)
 
        if (sc->matchers_full) {
                for (i = 0; i < n; i++) {
-                       if (static_matchers[i].flags & URL_FLAG_REGEXP) {
+                       if (static_matchers[i].flags & URL_MATCHER_FLAG_REGEXP) {
                                rspamd_multipattern_add_pattern(url_scanner->search_trie_full,
                                                                                                static_matchers[i].pattern,
                                                                                                RSPAMD_MULTIPATTERN_ICASE | RSPAMD_MULTIPATTERN_UTF8 |
@@ -1664,7 +1664,7 @@ rspamd_tld_trie_callback(struct rspamd_multipattern *mp,
                                                         strnum);
        ndots = 1;
 
-       if (matcher->flags & URL_FLAG_STAR_MATCH) {
+       if (matcher->flags & URL_MATCHER_FLAG_STAR_MATCH) {
                /* Skip one more tld component */
                ndots++;
        }
@@ -2595,7 +2595,7 @@ rspamd_tld_trie_find_callback(struct rspamd_multipattern *mp,
        matcher = &g_array_index(url_scanner->matchers_full, struct url_matcher,
                                                         strnum);
 
-       if (matcher->flags & URL_FLAG_STAR_MATCH) {
+       if (matcher->flags & URL_MATCHER_FLAG_STAR_MATCH) {
                /* Skip one more tld component */
                ndots = 2;
        }
@@ -3107,7 +3107,7 @@ static gboolean
 rspamd_url_trie_is_match(struct url_matcher *matcher, const gchar *pos,
                                                 const gchar *end, const gchar *newline_pos)
 {
-       if (matcher->flags & URL_FLAG_TLD_MATCH) {
+       if (matcher->flags & URL_MATCHER_FLAG_TLD_MATCH) {
                /* Immediately check pos for valid chars */
                if (pos < end) {
                        if (pos != newline_pos && !g_ascii_isspace(*pos) && *pos != '/' && *pos != '?' &&
@@ -3156,7 +3156,7 @@ rspamd_url_trie_callback(struct rspamd_multipattern *mp,
        matcher = &g_array_index(cb->matchers, struct url_matcher,
                                                         strnum);
 
-       if ((matcher->flags & URL_FLAG_NOHTML) && cb->how == RSPAMD_URL_FIND_STRICT) {
+       if ((matcher->flags & URL_MATCHER_FLAG_NOHTML) && cb->how == RSPAMD_URL_FIND_STRICT) {
                /* Do not try to match non-html like urls in html texts */
                return 0;
        }
@@ -3313,7 +3313,7 @@ rspamd_url_trie_generic_callback_common(struct rspamd_multipattern *mp,
                                                         strnum);
        pool = cb->pool;
 
-       if ((matcher->flags & URL_FLAG_NOHTML) && cb->how == RSPAMD_URL_FIND_STRICT) {
+       if ((matcher->flags & URL_MATCHER_FLAG_NOHTML) && cb->how == RSPAMD_URL_FIND_STRICT) {
                /* Do not try to match non-html like urls in html texts, continue matching */
                return 0;
        }