diff --git a/regression_testing/cases/github-cases/case-946.conf b/regression_testing/cases/github-cases/case-946.conf new file mode 100755 index 0000000..16ee2e7 --- /dev/null +++ b/regression_testing/cases/github-cases/case-946.conf @@ -0,0 +1,3 @@ +# Sample config for 946 +gdoc: yes +wrap: 999 diff --git a/regression_testing/cases/github-cases/case-946@1.html b/regression_testing/cases/github-cases/case-946@1.html new file mode 100644 index 0000000..aafb1a5 Binary files /dev/null and b/regression_testing/cases/github-cases/case-946@1.html differ diff --git a/regression_testing/cases/github-expects/case-946.html b/regression_testing/cases/github-expects/case-946.html new file mode 100644 index 0000000..980afc7 --- /dev/null +++ b/regression_testing/cases/github-expects/case-946.html @@ -0,0 +1,44 @@ + + + + + + + +
<"r>
+ + + + +-align="center" nowrap="">me=rap="">me="i�" value="ISO�8859-1" type="hidden"> +
&nbsp;
+ + +gleg/1x/googleg_standard_color_128dp.png" itemprop="image"> +Google + + + diff --git a/regression_testing/cases/github-expects/case-946.txt b/regression_testing/cases/github-expects/case-946.txt new file mode 100644 index 0000000..ac88bf5 --- /dev/null +++ b/regression_testing/cases/github-expects/case-946.txt @@ -0,0 +1,330 @@ +line 1 column 1 - Warning: discarding malformed +line 1 column 26 - Warning: replacing invalid UTF-8 bytes (char. code U+00A5) +line 1 column 27 - Warning: replacing invalid UTF-8 bytes (char. code U+009F) +line 1 column 32 - Warning: replacing invalid UTF-8 bytes (char. code U+008D) +line 1 column 33 - Warning: replacing invalid UTF-8 bytes (char. code U+008D) +line 1 column 20 - Warning:
attribute name "i��ioz{��~" (value="la") is invalid +line 1 column 33 - Warning: inserting implicit +line 1 column 41 - Warning: attribute with missing trailing quote mark +line 1 column 56 - Warning:
attribute "!doctype" lacks value +line 1 column 114 - Warning: replacing invalid UTF-8 bytes (char. code U+0080) +line 1 column 216 - Warning: attribute with missing trailing quote mark +line 1 column 216 - Warning: attribute with missing trailing quote mark +line 1 column 318 - Warning: missing
before
+line 1 column 216 - Warning: missing before
+line 1 column 148 - Warning: missing before +line 1 column 142 - Warning: missing before +line 1 column 74 - Warning: missing before +line 1 column 56 - Warning: missing
before +line 1 column 41 - Warning: missing before
+line 1 column 20 - Warning: missing
before +line 1 column 403 - Warning: unexpected or duplicate quote mark +line 1 column 500 - Warning: replacing invalid UTF-8 bytes (char. code U+0083) +line 1 column 513 - Warning: replacing invalid UTF-8 bytes (char. code U+0000) +line 1 column 578 - Warning: replacing invalid UTF-8 bytes (char. code U+0091) +line 2 column 114 - Warning: before before before before +line 1 column 33 - Warning: missing before +line 1 column 1 - Warning: missing before +line 2 column 193 - Warning: replacing invalid UTF-8 bytes (char. code U+0091) +line 2 column 177 - Warning: discarding unexpected +line 2 column 1448 - Warning: attribute "conten/body" lacks value +line 2 column 1466 - Warning: discarding unexpected +line 2 column 1515 - Warning: attribute with missing trailing quote mark +line 2 column 1596 - Warning: discarding unexpected +line 2 column 1709 - Warning: replacing invalid UTF-8 bytes (char. code U+00FF) +line 2 column 2542 - Warning: replacing invalid UTF-8 bytes (char. code U+00B5) +line 2 column 2909 - Warning: replacing invalid UTF-8 bytes (char. code U+0005) +line 4 column 49 - Warning: unescaped & or unknown entity "&ei" +line 4 column 61 - Warning: unescaped & or unknown entity "&ei" +line 4 column 86 - Warning: unescaped & or unknown entity "&lei" +line 4 column 110 - Warning: unescaped & or unknown entity "&lei" +line 4 column 129 - Warning: unescaped & or unknown entity "&window._cshid" +line 4 column 144 - Warning: unescaped & or unknown entity "&-1" +line 4 column 159 - Warning: unescaped & or unknown entity "&cshid" +line 4 column 184 - Warning: unescaped & or unknown entity "&cshid" +line 4 column 240 - Warning: unescaped & or unknown entity "&ct" +line 4 column 246 - Warning: replacing invalid UTF-8 bytes (char. code U+00FF) +line 4 column 247 - Warning: replacing invalid UTF-8 bytes (char. code U+00FF) +line 4 column 249 - Warning: unescaped & or unknown entity "&cad" +line 4 column 261 - Warning: unescaped & or unknown entity "&zx" +line 4 column 346 - Warning: unescaped & or unknown entity "&google.ml" +line 4 column 619 - Warning: replacing invalid UTF-8 bytes (char. code U+001D) +line 4 column 619 - Warning: attribute "(a)*a;l" lacks value +line 4 column 632 - Warning: replacing invalid UTF-8 bytes (char. code U+00FF) +line 4 column 633 - Warning: replacing invalid UTF-8 bytes (char. code U+00FF) +line 4 column 619 - Warning: attribute "h(ao��widte" lacks value +line 4 column 619 - Warning: attribute name "h[e]};a.src" (value="c}};google.logUrl=m;}).call(thi);(function(){") is invalid +line 5 column 25 - Warning: replacing invalid UTF-8 bytes (char. code U+0010) +line 4 column 619 - Info: value for attribute "google.y" missing quote marks +line 4 column 619 - Info: value for attribute "c" missing quote marks +line 4 column 619 - Info: value for attribute "c" missing quote marks +line 4 column 619 - Warning: attribute "document.documentelement.addeventlistener("submit",function(b){var" lacks value +line 4 column 619 - Warning: attribute name "a;if(a" (value="b.target){var") is invalid +line 6 column 184 - Warning: replacing invalid UTF-8 bytes (char. code U+00FF) +line 6 column 185 - Warning: replacing invalid UTF-8 bytes (char. code U+00FF) +line 6 column 186 - Warning: replacing invalid UTF-8 bytes (char. code U+00FF) +line 6 column 187 - Warning: replacing invalid UTF-8 bytes (char. code U+008D) +line 4 column 619 - Info: value for attribute "c" missing quote marks +line 6 column 321 - Warning: unescaped & or unknown entity "&a" +line 4 column 619 - Warning: attribute name "ion())},!0);document.documentelement.addeventlistener("click",function(b){var0a;a:{for(a" (value="b.target;a&&a!=document.documentElement;a=a.parentElement)if("A"==a.tagName){a="1"==a.getAttribute("data-nohref");break") is invalid +line 6 column 439 - Warning: unescaped & or unknown entity "&b.preventDefault" +line 4 column 619 - Warning: missing '>' for end of tag +line 4 column 619 - Warning: attribute name "a}a" (value="!1}a&&b.preventDefault()},!0);}).call(this);") is invalid +line 4 column 619 - Warning: dropping value "a.id;else{do" for repeated attribute "c" +line 4 column 619 - Warning: dropping value "Math.random();while(google.y[c])}google.y[c]=[a,b];return!1};google.sx=f64,1960,718,530,2,61,174,44unction(a){google.sy.push(a)};google.lm=[];google.plm=function(a){google.lm.push.apply(google.lm,a)};google.lq=[];google.load=function(a,b,c){google.lq.push([[a],b,c])};google.loadAll=function(a,b){google.lq.push([a,b])};google.bx=!1;google.lx=function(){};}).call(this);google.f={};(function(){" for repeated attribute "c" +line 2 column 1583 - Warning: missing before +line 2 column 1515 - Warning: missing before +line 2 column 1448 - Warning: missing </meta> before <meta> +line 2 column 1442 - Warning: missing </head> before <meta> +line 2 column 275 - Warning: missing </script> before <head> +line 7 column 1034 - Warning: replacing invalid UTF-8 bytes (char. code U+00BC) +line 7 column 1137 - Warning: discarding unexpected </head> +line 8 column 23 - Warning: unescaped & or unknown entity "&document.f.q.focus" +line 8 column 59 - Warning: unescaped & or unknown entity "&document.gbqf.q.focus" +line 10 column 30 - Info: value for attribute "id" missing quote marks +line 10 column 49 - Info: value for attribute "class" missing quote marks +line 10 column 73 - Info: value for attribute "class" missing quote marks +line 10 column 127 - Warning: unescaped & or unknown entity "&tab" +line 10 column 147 - Info: value for attribute "class" missing quote marks +line 10 column 201 - Warning: unescaped & or unknown entity "&tab" +line 10 column 219 - Info: value for attribute "class" missing quote marks +line 10 column 268 - Warning: unescaped & or unknown entity "&tab" +line 10 column 286 - Info: value for attribute "class" missing quote marks +line 10 column 334 - Warning: unescaped & or unknown entity "&tab" +line 10 column 355 - Info: value for attribute "class" missing quote marks +line 10 column 416 - Info: value for attribute "class" missing quote marks +line 10 column 483 - Info: value for attribute "class" missing quote marks +line 10 column 546 - Info: value for attribute "class" missing quote marks +line 10 column 686 - Info: value for attribute "id" missing quote marks +line 10 column 686 - Info: value for attribute "width" missing quote marks +line 10 column 717 - Info: value for attribute "id" missing quote marks +line 10 column 717 - Info: value for attribute "class" missing quote marks +line 10 column 747 - Info: value for attribute "id" missing quote marks +line 10 column 747 - Info: value for attribute "class" missing quote marks +line 10 column 777 - Info: value for attribute "id" missing quote marks +line 10 column 797 - Info: value for attribute "class" missing quote marks +line 10 column 880 - Info: value for attribute "class" missing quote marks +line 10 column 935 - Info: value for attribute "target" missing quote marks +line 10 column 935 - Info: value for attribute "id" missing quote marks +line 10 column 1011 - Warning: unescaped & or unknown entity "&passive" +line 10 column 1024 - Warning: unescaped & or unknown entity "&continue" +line 10 column 1056 - Warning: unescaped & or unknown entity "&ec" +line 10 column 935 - Info: value for attribute "class" missing quote marks +line 10 column 1102 - Info: value for attribute "class" missing quote marks +line 10 column 1102 - Info: value for attribute "style" missing quote marks +line 10 column 1136 - Info: value for attribute "class" missing quote marks +line 10 column 1136 - Info: value for attribute "style" missing quote marks +line 10 column 1391 - Warning: missing </br> before <br> +line 10 column 1225 - Warning: missing </img> before <br> +line 10 column 1211 - Warning: missing </div> before <img> +line 10 column 1493 - Info: value for attribute "width" missing quote marks +line 10 column 1753 - Warning: missing </dlv> before <input> +line 10 column 1721 - Warning: missing </input> before <dlv> +line 10 column 1689 - Warning: missing </input> before <input> +line 10 column 1643 - Warning: missing </input> before <input> +line 10 column 1598 - Warning: missing </input> before <input> +line 10 column 1548 - Warning: missing </input> before <input> +line 10 column 1519 - Warning: missing </td> before <input> +line 10 column 1476 - Warning: missing </tr> before <td> +line 10 column 1437 - Warning: missing </table> before <tr> +line 10 column 1405 - Warning: missing </form> before <table> +line 10 column 1185 - Warning: missing </br> before <form> +line 10 column 1177 - Warning: missing </center> before <br> +line 10 column 15 - Warning: missing </div> before <center> +line 10 column 2025 - Warning: missing </span> before <input> +line 10 column 2161 - Warning: missing </input> before <input> +line 10 column 2142 - Warning: missing </span> before <input> +line 11 column 149 - Warning: discarding unexpected </td> +line 11 column 155 - Warning: replacing invalid UTF-8 bytes (char. code U+00FF) +line 11 column 156 - Warning: replacing invalid UTF-8 bytes (char. code U+00FF) +line 11 column 277 - Warning: discarding unexpected </td> +line 11 column 282 - Warning: discarding unexpected </tr> +line 11 column 287 - Warning: discarding unexpected </table> +line 12 column 25 - Warning: unescaped & or unknown entity "&document.getElementById" +line 1 column 20 - Warning: missing </div> +line 1 column 20 - Warning: missing </div> +line 1 column 33 - Warning: inserting missing 'title' element +line 4 column 619 - Warning: <area> lacks "alt" attribute +line 4 column 619 - Warning: <area> lacks "href" attribute +line 10 column 1225 - Warning: <img> lacks "alt" attribute +line 10 column 1225 - Warning: <img> lacks "src" attribute +line 10 column 717 - Warning: trimming empty <span> +line 10 column 747 - Warning: trimming empty <span> +line 10 column 777 - Warning: trimming empty <span> +line 10 column 1177 - Warning: <center> element removed from HTML5 +line 1 column 56 - Warning: <br> proprietary attribute "html" +line 1 column 74 - Warning: <html> proprietary attribute "itemscope" +line 1 column 74 - Warning: <html> proprietary attribute "itemtype" +line 1 column 74 - Warning: <html> proprietary attribute "lang" +line 1 column 148 - Warning: <meta> proprietary attribute "content" +line 1 column 148 - Warning: <meta> proprietary attribute "http-equiv" +line 1 column 216 - Warning: <meta> proprietary attribute "content" +line 1 column 216 - Warning: <meta> proprietary attribute "style" +line 1 column 364 - Warning: <table> proprietary attribute "cellpadding" +line 1 column 364 - Warning: <table> proprietary attribute "cellspacing" +line 1 column 432 - Warning: <td> proprietary attribute "width" +line 1 column 536 - Warning: <input> proprietary attribute "value" +line 1 column 536 - Warning: <input> proprietary attribute "name" +line 1 column 536 - Warning: <input> proprietary attribute "type" +line 1 column 581 - Warning: <input> proprietary attribute "name" +line 1 column 581 - Warning: <input> proprietary attribute "tg" +line 1 column 581 - Warning: <input> proprietary attribute "ype" +line 1 column 581 - Warning: <input> proprietary attribute "value" +line 2 column 25 - Warning: <input> proprietary attribute "name" +line 2 column 25 - Warning: <input> proprietary attribute "type" +line 2 column 275 - Warning: <script> proprietary attribute "nonce" +line 2 column 1515 - Warning: <meta> proprietary attribute "itemprop" +line 4 column 619 - Warning: <area> proprietary attribute "google.y" +line 4 column 619 - Warning: <area> proprietary attribute "c" +line 7 column 1087 - Warning: <script> proprietary attribute "nonce" +line 7 column 1144 - Warning: <body> proprietary attribute "bgcolor" +line 7 column 1165 - Warning: <script> proprietary attribute "nonce" +line 10 column 15 - Warning: <div> proprietary attribute "id" +line 10 column 30 - Warning: <div> proprietary attribute "id" +line 10 column 43 - Warning: <nobr> is not approved by W3C +line 10 column 49 - Warning: <b> proprietary attribute "class" +line 10 column 73 - Warning: <a> proprietary attribute "class" +line 10 column 73 - Warning: <a> proprietary attribute "href" +line 10 column 147 - Warning: <a> proprietary attribute "class" +line 10 column 147 - Warning: <a> proprietary attribute "href" +line 10 column 219 - Warning: <a> proprietary attribute "class" +line 10 column 219 - Warning: <a> proprietary attribute "href" +line 10 column 286 - Warning: <a> proprietary attribute "class" +line 10 column 286 - Warning: <a> proprietary attribute "href" +line 10 column 355 - Warning: <a> proprietary attribute "class" +line 10 column 355 - Warning: <a> proprietary attribute "href" +line 10 column 416 - Warning: <a> proprietary attribute "class" +line 10 column 416 - Warning: <a> proprietary attribute "href" +line 10 column 483 - Warning: <a> proprietary attribute "class" +line 10 column 483 - Warning: <a> proprietary attribute "href" +line 10 column 546 - Warning: <a> proprietary attribute "class" +line 10 column 546 - Warning: <a> proprietary attribute "style" +line 10 column 546 - Warning: <a> proprietary attribute "href" +line 10 column 686 - Warning: <div> proprietary attribute "id" +line 10 column 686 - Warning: <div> proprietary attribute "width" +line 10 column 711 - Warning: <nobr> is not approved by W3C +line 10 column 797 - Warning: <a> proprietary attribute "href" +line 10 column 797 - Warning: <a> proprietary attribute "class" +line 10 column 880 - Warning: <a> proprietary attribute "href" +line 10 column 880 - Warning: <a> proprietary attribute "class" +line 10 column 935 - Warning: <a> proprietary attribute "target" +line 10 column 935 - Warning: <a> proprietary attribute "id" +line 10 column 935 - Warning: <a> proprietary attribute "href" +line 10 column 935 - Warning: <a> proprietary attribute "class" +line 10 column 1102 - Warning: <div> proprietary attribute "class" +line 10 column 1102 - Warning: <div> proprietary attribute "style" +line 10 column 1136 - Warning: <div> proprietary attribute "class" +line 10 column 1136 - Warning: <div> proprietary attribute "style" +line 10 column 1185 - Warning: <br> proprietary attribute "clear" +line 10 column 1185 - Warning: <br> proprietary attribute "id" +line 10 column 1211 - Warning: <div> proprietary attribute "id" +line 10 column 1225 - Warning: <img> proprietary attribute "alt" +line 10 column 1225 - Warning: <img> proprietary attribute "height" +line 10 column 1225 - Warning: <img> proprietary attribute "src" +line 10 column 1225 - Warning: <img> proprietary attribute "style" +line 10 column 1225 - Warning: <img> proprietary attribute "width" +line 10 column 1225 - Warning: <img> proprietary attribute "id" +line 10 column 1405 - Warning: <form> proprietary attribute "action" +line 10 column 1405 - Warning: <form> proprietary attribute "name" +line 10 column 1437 - Warning: <table> proprietary attribute "cellpadding" +line 10 column 1437 - Warning: <table> proprietary attribute "cellspacing" +line 10 column 1476 - Warning: <tr> proprietary attribute "valign" +line 10 column 1493 - Warning: <td> proprietary attribute "width" +line 10 column 1519 - Warning: <td> proprietary attribute "align" +line 10 column 1519 - Warning: <td> proprietary attribute "nowrap" +line 10 column 1548 - Warning: <input> proprietary attribute "name" +line 10 column 1548 - Warning: <input> proprietary attribute "value" +line 10 column 1548 - Warning: <input> proprietary attribute "type" +line 10 column 1598 - Warning: <input> proprietary attribute "value" +line 10 column 1598 - Warning: <input> proprietary attribute "name" +line 10 column 1598 - Warning: <input> proprietary attribute "type" +line 10 column 1643 - Warning: <input> proprietary attribute "name" +line 10 column 1643 - Warning: <input> proprietary attribute "type" +line 10 column 1643 - Warning: <input> proprietary attribute "value" +line 10 column 1689 - Warning: <input> proprietary attribute "name" +line 10 column 1689 - Warning: <input> proprietary attribute "type" +line 10 column 1721 - Warning: <input> proprietary attribute "name" +line 10 column 1721 - Warning: <input> proprietary attribute "type" +line 10 column 1802 - Warning: <input> proprietary attribute "class" +line 10 column 1802 - Warning: <input> proprietary attribute "style" +line 10 column 1802 - Warning: <input> proprietary attribute "autocomplete" +line 10 column 1802 - Warning: <input> proprietary attribute "value" +line 10 column 1802 - Warning: <input> proprietary attribute "title" +line 10 column 1802 - Warning: <input> proprietary attribute "maxlength" +line 10 column 1802 - Warning: <input> proprietary attribute "name" +line 10 column 1802 - Warning: <input> proprietary attribute "size" +line 10 column 1982 - Warning: <br> proprietary attribute "style" +line 10 column 2008 - Warning: <span> proprietary attribute "class" +line 10 column 2025 - Warning: <span> proprietary attribute "class" +line 10 column 2044 - Warning: <input> proprietary attribute "class" +line 10 column 2044 - Warning: <input> proprietary attribute "value" +line 10 column 2044 - Warning: <input> proprietary attribute "name" +line 10 column 2044 - Warning: <input> proprietary attribute "type" +line 10 column 2125 - Warning: <span> proprietary attribute "class" +line 10 column 2142 - Warning: <span> proprietary attribute "class" +line 10 column 2161 - Warning: <input> proprietary attribute "class" +line 10 column 2161 - Warning: <input> proprietary attribute "lue" +line 10 column 2161 - Warning: <input> proprietary attribute "name" +line 10 column 2161 - Warning: <input> proprietary attribute "type" +line 10 column 2229 - Warning: <script> proprietary attribute "nonce" +line 11 column 47 - Warning: <input> proprietary attribute "value" +line 11 column 47 - Warning: <input> proprietary attribute "name" +line 11 column 47 - Warning: <input> proprietary attribute "type" +line 11 column 207 - Warning: <a> proprietary attribute "href" +line 11 column 295 - Warning: <input> proprietary attribute "id" +line 11 column 295 - Warning: <input> proprietary attribute "name" +line 11 column 295 - Warning: <input> proprietary attribute "type" +line 11 column 295 - Warning: <input> proprietary attribute "value" +line 11 column 346 - Warning: <script> proprietary attribute "nonce" +Info: Document content looks like HTML5 +Tidy found 256 warnings and 0 errors! + +Character codes for UTF-8 must be in the range: U+0000 to U+10FFFF. +The definition of UTF-8 in Annex D of ISO/IEC 10646-1:2000 also +allows for the use of five- and six-byte sequences to encode +characters that are outside the range of the Unicode character set; +those five- and six-byte sequences are illegal for the use of +UTF-8 as a transformation of Unicode characters. ISO/IEC 10646 +does not allow mapping of unpaired surrogates, nor U+FFFE and U+FFFF +(but it does allow other noncharacters). For more information please refer to +https://home.unicode.org/ and https://www.cl.cam.ac.uk/~mgk25/unicode.html + +The alt attribute should be used to give a short description +of an image; longer descriptions should be given with the +longdesc attribute which takes a URL linked to the description. +These measures are needed for people using non-graphical browsers. + +For hypertext links defined using a client-side image map, you +need to use the alt attribute to provide a textual description +of the link for people using non-graphical browsers. + +For further advice on how to make your pages accessible +see https://www.w3.org/WAI/GL. +You are recommended to use CSS to control line wrapping. +Use "white-space: nowrap" to inhibit wrapping in place +of inserting <NOBR>...</NOBR> into the markup. + +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 +this behavior, then consider setting the option "drop-empty-elements" +to no. + +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: https://html.spec.whatwg.org/multipage/ +Validate your HTML documents: https://validator.w3.org/nu/ +Lobby your company to join the W3C: https://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/src/gdoc.c b/src/gdoc.c index 50cd9bc..8f5f8ff 100644 --- a/src/gdoc.c +++ b/src/gdoc.c @@ -96,14 +96,15 @@ static void DiscardContainer( TidyDocImpl* doc, Node *element, Node **pnode) static void CleanNode( TidyDocImpl* doc, Node *node ) { + Stack *stack = TY_(newStack)(doc, 16); Node *child, *next; - if (node->content) + if ( (child = node->content) ) { - for (child = node->content; child != NULL; child = next) + while (child) { next = child->next; - + if (TY_(nodeIsElement)(child)) { if (nodeIsSTYLE(child)) @@ -131,10 +132,14 @@ static void CleanNode( TidyDocImpl* doc, Node *node ) if (child->attributes) TY_(DropAttrByName)( doc, child, "class" ); - CleanNode(doc, child); + TY_(push)(stack,next); + child = child->content; + continue; } } + child = next ? next : TY_(pop)(stack); } + TY_(freeStack)(stack); } } diff --git a/version.txt b/version.txt index 3ff913e..76a976e 100644 --- a/version.txt +++ b/version.txt @@ -1,2 +1,2 @@ -5.9.7 -2021.07.30 +5.9.8 +2021.07.31