feat: add recognizeNoValueAttribute option for issue #75

readme.md

@@ -81,45 +81,50 @@ Tag objects can contain three keys. The `tag` key takes the name of the tag as t
 ## Options
 
 ### `directives`
-Type: `Array`  
-Default: `[{name: '!doctype', start: '<', end: '>'}]`   
-Description: *Adds processing of custom directives. Note: The property ```name``` in custom directives can be ```String``` or ```RegExp``` type*  
+Type: `Array`
+Default: `[{name: '!doctype', start: '<', end: '>'}]`
+Description: *Adds processing of custom directives. Note: The property ```name``` in custom directives can be ```String``` or ```RegExp``` type*
 
 ### `xmlMode`
-Type: `Boolean`  
-Default: `false`   
+Type: `Boolean`
+Default: `false`
 Description: *Indicates whether special tags (`<script>` and `<style>`) should get special treatment and if "empty" tags (eg. `<br>`) can have children. If false, the content of special tags will be text only. For feeds and other XML content (documents that don't consist of HTML), set this to true.*
 
 ### `decodeEntities`
-Type: `Boolean`  
-Default: `false`   
+Type: `Boolean`
+Default: `false`
 Description: *If set to true, entities within the document will be decoded.*
 
 ### `lowerCaseTags`
-Type: `Boolean`  
-Default: `false`   
+Type: `Boolean`
+Default: `false`
 Description: *If set to true, all tags will be lowercased. If `xmlMode` is disabled.*
 
 ### `lowerCaseAttributeNames`
-Type: `Boolean`  
-Default: `false`   
+Type: `Boolean`
+Default: `false`
 Description: *If set to true, all attribute names will be lowercased. This has noticeable impact on speed.*
 
 ### `recognizeCDATA`
-Type: `Boolean`  
-Default: `false`   
+Type: `Boolean`
+Default: `false`
 Description: *If set to true, CDATA sections will be recognized as text even if the `xmlMode` option is not enabled. NOTE: If `xmlMode` is set to `true` then CDATA sections will always be recognized as text.*
 
 ### `recognizeSelfClosing`
-Type: `Boolean`  
-Default: `false`   
+Type: `Boolean`
+Default: `false`
 Description: *If set to true, self-closing tags will trigger the `onclosetag` event even if `xmlMode` is not set to `true`. NOTE: If `xmlMode` is set to `true` then self-closing tags will always be recognized.*
 
-### `sourceLocations`  
-Type: `Boolean`  
-Default: `false`  
+### `sourceLocations`
+Type: `Boolean`
+Default: `false`
 Description: *If set to true, AST nodes will have a `location` property containing the `start` and `end` line and column position of the node.*
 
+### `recognizeNoValueAttribute`
+Type: `Boolean`
+Default: `false`
+Description: *If set to true, AST nodes will recognize attribute with no value and mark as `true` which will be correctly rendered by `posthtml-render` package*
+
 ## License
 
 [MIT](LICENSE)

src/index.ts

@@ -10,6 +10,7 @@ export type Directive = {
 export type Options = {
   directives?: Directive[];
   sourceLocations?: boolean;
+  recognizeNoValueAttribute?: boolean;
 } & ParserOptions;
 
 export type Tag = string | boolean;
@@ -45,6 +46,7 @@ export const parser = (html: string, options: Options = {}): Node[] => {
   const bufArray: Node[] = [];
   const results: Node[] = [];
   let lastOpenTagEndIndex = 0;
+  let noValueAttributes: Record<string, true> = {};
 
   function bufferArrayLast(): Node {
     return bufArray[bufArray.length - 1];
@@ -70,6 +72,11 @@ export const parser = (html: string, options: Options = {}): Node[] => {
       const object: Attributes = {};
 
       object[key] = String(attrs[key]).replace(/&quot;/g, '"');
+
+      if (options.recognizeNoValueAttribute && noValueAttributes[key]) {
+        object[key] = true;
+      }
+
       Object.assign(result, object);
     });
 
@@ -122,6 +129,17 @@ export const parser = (html: string, options: Options = {}): Node[] => {
     }
   }
 
+  function onattribute(name: string, value: string, quote?: string | undefined | null) {
+    // Quote: Quotes used around the attribute.
+    // `null` if the attribute has no quotes around the value,
+    // `undefined` if the attribute has no value.
+    if (quote === undefined) {
+      // `true` is recognized by posthtml-render as attrubute without value
+      // See: https://github.com/posthtml/posthtml-render/blob/master/src/index.ts#L268
+      noValueAttributes[name] = true;
+    }
+  }
+
   function onopentag(tag: string, attrs: Attributes) {
     const buf: NodeTag = { tag };
 
@@ -137,6 +155,10 @@ export const parser = (html: string, options: Options = {}): Node[] => {
       buf.attrs = normalizeArributes(attrs);
     }
 
+    // Always reset after normalizeArributes
+    // Reason: onopentag callback will fire after all attrubutes have been processed
+    noValueAttributes = {};
+
     bufArray.push(buf);
   }
 
@@ -201,6 +223,7 @@ export const parser = (html: string, options: Options = {}): Node[] => {
   const parser = new Parser({
     onprocessinginstruction,
     oncomment,
+    onattribute,
     onopentag,
     onclosetag,
     ontext

test/test-core.spec.ts

@@ -370,3 +370,30 @@ test('should parse with input in button', t => {
   ];
   t.deepEqual(tree, expected);
 });
+
+test('should parse no value attribute as `true` when `recognizeNoValueAttribute` is `true` ', t => {
+  const tree = parser(
+    '<div class="className" hasClass>Content</div>',
+    { recognizeNoValueAttribute: true }
+  );
+  const expected = [
+    {
+      tag: 'div',
+      attrs: { class: 'className', hasClass: true },
+      content: ['Content']
+    }
+  ];
+  t.deepEqual(tree, expected);
+});
+
+test('should parse no value attribute as empty string when `recognizeNoValueAttribute` is `false` or not set ', t => {
+  const tree = parser('<div class="className" hasClass>Content</div>');
+  const expected = [
+    {
+      tag: 'div',
+      attrs: { class: 'className', hasClass: '' },
+      content: ['Content']
+    }
+  ];
+  t.deepEqual(tree, expected);
+});