From 23b2778f1ae5e17bbd4968287a1da031835ea1fc Mon Sep 17 00:00:00 2001
From: Andy Ragusa <aragusa@cisco.com>
Date: Tue, 9 Jul 2024 10:54:42 -0700
Subject: [PATCH] blah

---
 libclamav/htmlnorm.c | 21 ++++++++++++++++++++-
 libclamav/scanners.c | 41 ++++++++++++++++++++++++++++++++---------
 2 files changed, 52 insertions(+), 10 deletions(-)

diff --git a/libclamav/htmlnorm.c b/libclamav/htmlnorm.c
index 10c3aa34a7..e33e1ce34d 100644
--- a/libclamav/htmlnorm.c
+++ b/libclamav/htmlnorm.c
@@ -684,7 +684,26 @@ bool html_insert_form_data(const char * const value, form_data_t *tags) {
 
 void html_form_data_tag_free(form_data_t *tags) {
     fprintf(stderr, "%s::%d::UNIMPLEMENTED!!!\n", __FUNCTION__, __LINE__);
-    exit(1);
+    fprintf(stderr, "%s::%d::UNIMPLEMENTED!!!\n", __FUNCTION__, __LINE__);
+    fprintf(stderr, "%s::%d::UNIMPLEMENTED!!!\n", __FUNCTION__, __LINE__);
+    fprintf(stderr, "%s::%d::UNIMPLEMENTED!!!\n", __FUNCTION__, __LINE__);
+    fprintf(stderr, "%s::%d::UNIMPLEMENTED!!!\n", __FUNCTION__, __LINE__);
+    fprintf(stderr, "%s::%d::UNIMPLEMENTED!!!\n", __FUNCTION__, __LINE__);
+    fprintf(stderr, "%s::%d::UNIMPLEMENTED!!!\n", __FUNCTION__, __LINE__);
+    fprintf(stderr, "%s::%d::UNIMPLEMENTED!!!\n", __FUNCTION__, __LINE__);
+    fprintf(stderr, "%s::%d::UNIMPLEMENTED!!!\n", __FUNCTION__, __LINE__);
+    fprintf(stderr, "%s::%d::UNIMPLEMENTED!!!\n", __FUNCTION__, __LINE__);
+    fprintf(stderr, "%s::%d::UNIMPLEMENTED!!!\n", __FUNCTION__, __LINE__);
+    fprintf(stderr, "%s::%d::UNIMPLEMENTED!!!\n", __FUNCTION__, __LINE__);
+    fprintf(stderr, "%s::%d::UNIMPLEMENTED!!!\n", __FUNCTION__, __LINE__);
+    fprintf(stderr, "%s::%d::UNIMPLEMENTED!!!\n", __FUNCTION__, __LINE__);
+    fprintf(stderr, "%s::%d::UNIMPLEMENTED!!!\n", __FUNCTION__, __LINE__);
+    fprintf(stderr, "%s::%d::UNIMPLEMENTED!!!\n", __FUNCTION__, __LINE__);
+    fprintf(stderr, "%s::%d::UNIMPLEMENTED!!!\n", __FUNCTION__, __LINE__);
+    fprintf(stderr, "%s::%d::UNIMPLEMENTED!!!\n", __FUNCTION__, __LINE__);
+    fprintf(stderr, "%s::%d::UNIMPLEMENTED!!!\n", __FUNCTION__, __LINE__);
+    fprintf(stderr, "%s::%d::UNIMPLEMENTED!!!\n", __FUNCTION__, __LINE__);
+//    exit(1);
 }
 
 static bool cli_html_normalise(cli_ctx *ctx, int fd, m_area_t *m_area, const char *dirname, tag_arguments_t *hrefs, const struct cli_dconf *dconf, form_data_t * form_data)
diff --git a/libclamav/scanners.c b/libclamav/scanners.c
index 4a3ba5684c..22d8c1475b 100644
--- a/libclamav/scanners.c
+++ b/libclamav/scanners.c
@@ -2491,10 +2491,12 @@ static bool is_url(const char *const str)
     return bRet;
 #undef MATCH
 }
-static void save_urls(cli_ctx *ctx, tag_arguments_t *hrefs)
+static void save_urls(cli_ctx *ctx, tag_arguments_t *hrefs, form_data_t * form_data)
 {
     int i        = 0;
-    bool haveOne = false;
+    bool bAdded = false;
+    json_object *ary = NULL;
+
     if (NULL == hrefs) {
         return;
     }
@@ -2507,14 +2509,37 @@ static void save_urls(cli_ctx *ctx, tag_arguments_t *hrefs)
         return;
     }
 
+    /*Add hrefs*/
     for (i = 0; i < hrefs->count; i++) {
         if (is_url((const char *)hrefs->value[i])) {
-            haveOne = true;
-            break;
+            if (NULL == ary){
+                ary = cli_jsonarray(ctx->wrkproperty, HTML_URLS_JSON_KEY);
+                if (!ary){
+                    cli_dbgmsg("[cli_scanhtml] Failed to add \"%s\" entry JSON array\n", HTML_URLS_JSON_KEY);
+                    return;
+                }
+            }
+            cli_jsonstr(ary, NULL, (const char *)hrefs->value[i]);
         }
     }
 
-    if (!haveOne) {
+    /*Add form_data*/
+    for (i = 0; i < form_data->count; i++) {
+        if (is_url((const char *)form_data->tag[i])) {
+            if (NULL == ary){
+                ary = cli_jsonarray(ctx->wrkproperty, HTML_URLS_JSON_KEY);
+                if (!ary){
+                    cli_dbgmsg("[cli_scanhtml] Failed to add \"%s\" entry JSON array\n", HTML_URLS_JSON_KEY);
+                    return;
+                }
+            }
+            cli_jsonstr(ary, NULL, (const char *)form_data->tag[i]);
+        }
+    }
+
+
+#if 0
+    if (!bAdded) {
         return;
     }
 
@@ -2528,6 +2553,7 @@ static void save_urls(cli_ctx *ctx, tag_arguments_t *hrefs)
     } else {
         cli_dbgmsg("[cli_scanhtml] Failed to add \"%s\" entry JSON array\n", HTML_URLS_JSON_KEY);
     }
+#endif
 }
 
 static cl_error_t cli_scanhtml(cli_ctx *ctx)
@@ -2567,10 +2593,7 @@ static cl_error_t cli_scanhtml(cli_ctx *ctx)
         hrefs.scanContents    = 1;
         form_data_t form_data = {0};
         (void)html_normalise_map_form_data(ctx, map, tempname, &hrefs, ctx->dconf, &form_data);
-        save_urls(ctx, &hrefs);
-
-fprintf(stderr, "%s::%d::SAVE THE FORM DATA TAGS HERE, TOOO!!!\n", __FUNCTION__, __LINE__); exit(11);
-
+        save_urls(ctx, &hrefs, &form_data);
         html_form_data_tag_free(&form_data);
     } else {
         (void)html_normalise_map(ctx, map, tempname, NULL, ctx->dconf);