implement continueOnParseError

README.md

@@ -45,6 +45,7 @@ Most of the options are disabled by default.
 | `collapseInlineTagWhitespace`  | Don't leave any spaces between `display:inline;` elements when collapsing. Must be used in conjunction with `collapseWhitespace=true` | `false` |
 | `collapseWhitespace`           | [Collapse white space that contributes to text nodes in a document tree](http://perfectionkills.com/experimenting-with-html-minifier/#collapse_whitespace) | `false` |
 | `conservativeCollapse`         | Always collapse to 1 space (never remove it entirely). Must be used in conjunction with `collapseWhitespace=true` | `false` |
+| `continueOnParseError`         | [Handle parse errors](https://html.spec.whatwg.org/multipage/parsing.html#parse-errors) instead of aborting. | `false` |
 | `customAttrAssign`             | Arrays of regex'es that allow to support custom attribute assign expressions (e.g. `'<div flex?="{{mode != cover}}"></div>'`) | `[ ]` |
 | `customAttrCollapse`           | Regex that specifies custom attribute to strip newlines from (e.g. `/ng-class/`) | |
 | `customAttrSurround`           | Arrays of regex'es that allow to support custom attribute surround expressions (e.g. `<input {{#if value}}checked="checked"{{/if}}>`) | `[ ]` |

cli.js

@@ -103,6 +103,7 @@ var mainOptions = {
   collapseInlineTagWhitespace: 'Collapse white space around inline tag',
   collapseWhitespace: 'Collapse white space that contributes to text nodes in a document tree.',
   conservativeCollapse: 'Always collapse to 1 space (never remove it entirely)',
+  continueOnParseError: 'Handle parse errors instead of aborting',
   customAttrAssign: ['Arrays of regex\'es that allow to support custom attribute assign expressions (e.g. \'<div flex?="{{mode != cover}}"></div>\')', parseJSONRegExpArray],
   customAttrCollapse: ['Regex that specifies custom attribute to strip newlines from (e.g. /ng-class/)', parseRegExp],
   customAttrSurround: ['Arrays of regex\'es that allow to support custom attribute surround expressions (e.g. <input {{#if value}}checked="checked"{{/if}}>)', parseJSONRegExpArray],

sample-cli-config-file.conf

@@ -4,6 +4,7 @@
   "collapseInlineTagWhitespace": false,
   "collapseWhitespace": true,
   "conservativeCollapse": false,
+  "continueOnParseError": true,
   "customAttrCollapse": ".*",
   "decodeEntities": true,
   "html5": true,

src/htmlminifier.js

@@ -965,6 +965,9 @@ function minify(value, options, partialMarkup) {
 
   new HTMLParser(value, {
     partialMarkup: partialMarkup,
+    continueOnParseError: options.continueOnParseError,
+    customAttrAssign: options.customAttrAssign,
+    customAttrSurround: options.customAttrSurround,
     html5: options.html5,
 
     start: function(tag, attrs, unary, unarySlash, autoGenerated) {
@@ -1241,9 +1244,7 @@ function minify(value, options, partialMarkup) {
       buffer.push(options.useShortDoctype ? '<!doctype' +
         (options.removeTagWhitespace ? '' : ' ') + 'html>' :
         collapseWhitespaceAll(doctype));
-    },
-    customAttrAssign: options.customAttrAssign,
-    customAttrSurround: options.customAttrSurround
+    }
   });
 
   if (options.removeOptionalTags) {

src/htmlparser.js

@@ -182,6 +182,11 @@ function HTMLParser(html, handler) {
           prevTag = startTagMatch.tagName.toLowerCase();
           continue;
         }
+
+        // Treat `<` as text
+        if (handler.continueOnParseError) {
+          textEnd = html.indexOf('<', 1);
+        }
       }
 
       var text;
@@ -213,7 +218,6 @@ function HTMLParser(html, handler) {
         handler.chars(text, prevTag, nextTag);
       }
       prevTag = '';
-
     }
     else {
       var stackedTag = lastTag.toLowerCase();

tests/minifier.js

@@ -64,6 +64,9 @@ QUnit.test('parsing non-trivial markup', function(assert) {
   assert.throws(function() {
     minify(input);
   }, 'Invalid tag name');
+  assert.equal(minify(input, {
+    continueOnParseError: true,
+  }), input);
 
   input = '<begriffs.pagination ng-init="perPage=20" collection="logs" url="\'/api/logs?user=-1\'" per-page="perPage" per-page-presets="[10,20,50,100]" template-url="/assets/paginate-anything.html"></begriffs.pagination>';
   assert.equal(minify(input), input);
@@ -93,9 +96,13 @@ QUnit.test('parsing non-trivial markup', function(assert) {
   // https://github.com/kangax/html-minifier/issues/507
   input = '<tag v-ref:vm_pv :imgs=" objpicsurl_ "></tag>';
   assert.equal(minify(input), input);
+  input = '<tag v-ref:vm_pv :imgs=" objpicsurl_ " ss"123>';
   assert.throws(function() {
-    minify('<tag v-ref:vm_pv :imgs=" objpicsurl_ " ss"123></tag>');
+    minify(input);
   }, 'invalid attribute name');
+  assert.equal(minify(input, {
+    continueOnParseError: true,
+  }), input);
 
   // https://github.com/kangax/html-minifier/issues/512
   input = '<input class="form-control" type="text" style="" id="{{vm.formInputName}}" name="{{vm.formInputName}}"' +
@@ -106,18 +113,29 @@ QUnit.test('parsing non-trivial markup', function(assert) {
           ' data-ng-pattern="vm.options.format"' +
           ' data-options="vm.datepickerOptions">';
   assert.equal(minify(input), input);
+  input = '<input class="form-control" type="text" style="" id="{{vm.formInputName}}" name="{{vm.formInputName}}"' +
+          ' <!--FIXME hardcoded placeholder - dates may not be used for service required fields yet. -->' +
+          ' placeholder="YYYY-MM-DD"' +
+          ' date-range-picker' +
+          ' data-ng-model="vm.value"' +
+          ' data-ng-model-options="{ debounce: 1000 }"' +
+          ' data-ng-pattern="vm.options.format"' +
+          ' data-options="vm.datepickerOptions">';
   assert.throws(function() {
-    minify(
-      '<input class="form-control" type="text" style="" id="{{vm.formInputName}}" name="{{vm.formInputName}}"' +
-      ' <!--FIXME hardcoded placeholder - dates may not be used for service required fields yet. -->' +
-      ' placeholder="YYYY-MM-DD"' +
-      ' date-range-picker' +
-      ' data-ng-model="vm.value"' +
-      ' data-ng-model-options="{ debounce: 1000 }"' +
-      ' data-ng-pattern="vm.options.format"' +
-      ' data-options="vm.datepickerOptions">'
-    );
+    minify(input);
   }, 'HTML comment inside tag');
+  assert.equal(minify(input, {
+    continueOnParseError: true,
+  }), input);
+
+  // https://github.com/kangax/html-minifier/issues/974
+  input = '<!–– Failing New York Times Comment -->';
+  assert.throws(function() {
+    minify(input);
+  }, 'invalid HTML comment');
+  assert.equal(minify(input, {
+    continueOnParseError: true,
+  }), input);
 
   input = '<br a=\u00A0 b="&nbsp;" c="\u00A0">';
   output = '<br a="\u00A0" b="&nbsp;" c="\u00A0">';