Merge pull request #930 from htacg/issue-839-2

balthisar · web-flow · commit 39c1e69be3f2 · 2021-06-30T11:21:19.000-04:00
Is. #839 - new message for 'blank' title
diff --git a/include/tidyenum.h b/include/tidyenum.h
@@ -282,7 +282,8 @@ extern "C" {
     FN(VENDOR_SPECIFIC_CHARS)         \
     FN(WHITE_IN_URI)                  \
     FN(XML_DECLARATION_DETECTED)      \
-    FN(XML_ID_SYNTAX)
+    FN(XML_ID_SYNTAX)                 \
+    FN(BLANK_TITLE_ELEMENT)
 
 
 /** These are report messages added by Tidy's accessibility module. 
diff --git a/regression_testing/cases/github-cases/case-839@1.html b/regression_testing/cases/github-cases/case-839@1.html
@@ -0,0 +1,12 @@
+<!--
+This test case represents HTML Tidy issue #839, which describes
+a descrepancy between tidy's behavior and the W3C Nu HTML
+checker behavior. Tidy has historically allowed empty <title>
+elements, but this is not allowed by HTML5, and is flagged by
+the Nu checker. Because a <title> is required by HTML5, it
+would be even worse for HTML Tidy to remove this element, and
+so Tidy will now provide a warning if the title element is
+empty. It is assumed the HTML author will add a title as well
+as addressing other warnings.
+ -->
+<!DOCTYPE html><title></title>
diff --git a/regression_testing/cases/github-expects/case-839.html b/regression_testing/cases/github-expects/case-839.html
@@ -0,0 +1,19 @@
+<!--
+This test case represents HTML Tidy issue #839, which describes
+a descrepancy between tidy's behavior and the W3C Nu HTML
+checker behavior. Tidy has historically allowed empty <title>
+elements, but this is not allowed by HTML5, and is flagged by
+the Nu checker. Because a <title> is required by HTML5, it
+would be even worse for HTML Tidy to remove this element, and
+so Tidy will now provide a warning if the title element is
+empty. It is assumed the HTML author will add a title as well
+as addressing other warnings.
+ -->
+<!DOCTYPE html>
+<html>
+<head>
+  <title></title>
+</head>
+<body>
+</body>
+</html>
diff --git a/regression_testing/cases/github-expects/case-839.txt b/regression_testing/cases/github-expects/case-839.txt
@@ -0,0 +1,14 @@
+line 12 column 16 - Warning: blank 'title' element
+Info: Document content looks like HTML5
+Tidy found 1 warning and 0 errors!
+
+About HTML Tidy: https://github.com/htacg/tidy-html5
+Bug reports and comments: https://github.com/htacg/tidy-html5/issues
+Official mailing list: https://lists.w3.org/Archives/Public/public-htacg/
+Latest HTML specification: http://dev.w3.org/html5/spec-author-view/
+Validate your HTML documents: http://validator.w3.org/nu/
+Lobby your company to join the W3C: http://www.w3.org/Consortium
+
+Do you speak a language other than English, or a different variant of 
+English? Consider helping us to localize HTML Tidy. For details please see 
+https://github.com/htacg/tidy-html5/blob/master/README/LOCALIZE.md
diff --git a/regression_testing/cases/legacy-expects/case-1062511.txt b/regression_testing/cases/legacy-expects/case-1062511.txt
@@ -8,10 +8,11 @@ line 7 column 1 - Warning: <base> isn't allowed in <b> elements
 line 6 column 1 - Info: <b> previously mentioned
 line 6 column 1 - Warning: missing </b> before <hr>
 line 3 column 1 - Warning: content occurs after end of body
+line 2 column 1 - Warning: blank 'title' element
 line 3 column 1 - Warning: trimming empty <marquee>
 line 6 column 1 - Warning: trimming empty <b>
 Info: Document content looks like HTML5
-Tidy found 11 warnings and 0 errors!
+Tidy found 12 warnings and 0 errors!
 
 One or more empty elements were present in the source document but
 dropped on output. If these elements are necessary or you don't want
diff --git a/regression_testing/cases/legacy-expects/case-1674502.txt b/regression_testing/cases/legacy-expects/case-1674502.txt
@@ -1,7 +1,8 @@
 line 1 column 1 - Warning: missing <!DOCTYPE> declaration
 line 7 column 1 - Warning: discarding unexpected XML declaration
+line 3 column 1 - Warning: blank 'title' element
 Info: Document content looks like HTML5
-Tidy found 2 warnings and 0 errors!
+Tidy found 3 warnings and 0 errors!
 
 About HTML Tidy: https://github.com/htacg/tidy-html5
 Bug reports and comments: https://github.com/htacg/tidy-html5/issues
diff --git a/regression_testing/cases/legacy-expects/case-1773932.txt b/regression_testing/cases/legacy-expects/case-1773932.txt
@@ -3,9 +3,10 @@ line 7 column 1 - Warning: missing </font> before <ol>
 line 8 column 9 - Warning: inserting implicit <font>
 line 9 column 10 - Warning: inserting implicit <font>
 line 10 column 10 - Warning: inserting implicit <font>
+line 3 column 1 - Warning: blank 'title' element
 line 7 column 1 - Warning: trimming empty <font>
 Info: Document content looks like HTML5
-Tidy found 6 warnings and 0 errors!
+Tidy found 7 warnings and 0 errors!
 
 You are recommended to use CSS to specify the font and
 properties such as its size and color. This will reduce
diff --git a/regression_testing/cases/legacy-expects/case-427675.txt b/regression_testing/cases/legacy-expects/case-427675.txt
@@ -1,11 +1,12 @@
 line 1 column 1 - Warning: missing <!DOCTYPE> declaration
 line 8 column 1 - Warning: discarding unexpected <frame>
 line 10 column 1 - Warning: missing </noframes>
+line 3 column 3 - Warning: blank 'title' element
 line 5 column 1 - Warning: <frameset> element removed from HTML5
 line 6 column 3 - Warning: <frame> element removed from HTML5
 line 10 column 1 - Warning: <noframes> element removed from HTML5
 Info: Document content looks like HTML5
-Tidy found 6 warnings and 0 errors!
+Tidy found 7 warnings and 0 errors!
 
 About HTML Tidy: https://github.com/htacg/tidy-html5
 Bug reports and comments: https://github.com/htacg/tidy-html5/issues
diff --git a/regression_testing/cases/legacy-expects/case-427676.txt b/regression_testing/cases/legacy-expects/case-427676.txt
@@ -5,9 +5,10 @@ line 6 column 14 - Error: <spanstyle> is not recognized!
 line 6 column 14 - Warning: discarding unexpected <spanstyle>
 line 6 column 44 - Warning: discarding unexpected </span>
 line 6 column 52 - Info: value for attribute "href" missing quote marks
+line 3 column 3 - Warning: blank 'title' element
 line 6 column 52 - Warning: <a> illegal characters found in URI
 Info: Document content looks like HTML5
-Tidy found 6 warnings and 1 error!
+Tidy found 7 warnings and 1 error!
 
 This document has errors that must be fixed before
 using HTML Tidy to generate a tidied up version.
diff --git a/src/language_en.h b/src/language_en.h
@@ -2055,6 +2055,7 @@ static languageDefinition language_en = { whichPluralForm_en, {
     { WHITE_IN_URI,                 0,   "%s discarding whitespace in URI reference"                               },
     { XML_DECLARATION_DETECTED,     0,   "An XML declaration was detected. Did you mean to use input-xml?"         },
     { XML_ID_SYNTAX,                0,   "%s ID \"%s\" uses XML ID syntax"                                         },
+    { BLANK_TITLE_ELEMENT,          0,   "blank 'title' element"                                                   },
 
 
     /***************************************
diff --git a/src/message.c b/src/message.c
@@ -372,6 +372,7 @@ static struct _dispatchTable {
     { WHITE_IN_URI,                 TidyWarning,     formatAttributeReport   },
     { XML_DECLARATION_DETECTED,     TidyWarning,     formatStandard          },
     { XML_ID_SYNTAX,                TidyWarning,     formatAttributeReport   },
+    { BLANK_TITLE_ELEMENT,          TidyWarning,     formatStandard          },
 
     { APPLET_MISSING_ALT,                            TidyAccess, formatAccessReport },
     { AREA_MISSING_ALT,                              TidyAccess, formatAccessReport },
@@ -819,6 +820,7 @@ TidyMessageImpl *formatStandard(TidyDocImpl* doc, Node *element, Node *node, uin
         case NESTED_QUOTATION:
         case SUSPECTED_MISSING_QUOTE:
         case XML_DECLARATION_DETECTED:
+        case BLANK_TITLE_ELEMENT:
             return TY_(tidyMessageCreateWithNode)(doc, rpt, code, level );
 
         case ELEMENT_NOT_EMPTY:
diff --git a/src/parser.c b/src/parser.c
@@ -4713,7 +4713,8 @@ void TY_(ParseDocument)(TidyDocImpl* doc)
         TY_(ParseHTML)(doc, html, IgnoreWhitespace);
     }
 
-    if (!TY_(FindTITLE)(doc))
+    node = TY_(FindTITLE)(doc);
+    if (!node)
     {
         Node* head = TY_(FindHEAD)(doc);
         /* #72, avoid MISSING_TITLE_ELEMENT if show-body-only (but allow InsertNodeAtEnd to avoid new warning) */
@@ -4723,6 +4724,14 @@ void TY_(ParseDocument)(TidyDocImpl* doc)
         }
         TY_(InsertNodeAtEnd)(head, TY_(InferredTag)(doc, TidyTag_TITLE));
     }
+    else if (!node->content && !showingBodyOnly(doc))
+    {
+        /* Is #839 - warn node is blank in HTML5 */
+        if (TY_(IsHTML5Mode)(doc))
+        {
+            TY_(Report)(doc, node, NULL, BLANK_TITLE_ELEMENT);
+        }
+    }
 
     AttributeChecks(doc, &doc->root);
     ReplaceObsoleteElements(doc, &doc->root);
