libextractor

commit 2e994884cc62fe321a5bdc7791d992306b28ce91
parent 22104c21d0308e912d0b59ed26db44613080e59f
Author: Christian Grothoff <christian@grothoff.org>
Date:   Tue, 30 Jun 2026 18:43:04 +0200

handle NULL returns from libtidy

Diffstat:
M
src/plugins/html_extractor.c
 | 
9
++++++++-

1 file changed, 8 insertions(+), 1 deletion(-)
diff --git a/src/plugins/html_extractor.c b/src/plugins/html_extractor.c
@@ -264,6 +264,8 @@ EXTRACTOR_html_extract_method (struct EXTRACTOR_ExtractContext *ec)
     case TidyNode_Start:
     case TidyNode_StartEnd:
       name = tidyNodeGetName (child);
+      if (NULL == name)
+        break;
       if ( (0 == strcasecmp (name, "title")) &&
            (NULL != (title = tidyGetChild (child))) )
       {
@@ -291,13 +293,18 @@ EXTRACTOR_html_extract_method (struct EXTRACTOR_ExtractContext *ec)
         if (NULL == (attr = tidyAttrGetById (child,
                                              TidyAttr_NAME)))
           break;
+        name = tidyAttrValue (attr);
+        if (NULL == name)
+          break;
         if (EXTRACTOR_METATYPE_RESERVED ==
-            (type = tag_to_type (tidyAttrValue (attr))))
+            (type = tag_to_type (name)))
           break;
         if (NULL == (attr = tidyAttrGetById (child,
                                              TidyAttr_CONTENT)))
           break;
         name = tidyAttrValue (attr);
+        if (NULL == name)
+          break;
         if (0 !=
             ec->proc (ec->cls,
                       "html",