defuddle 0.2.4 → 0.3.1

package/README.md

@@ -34,6 +34,19 @@ console.log(article.content);  // HTML string of the main content
 console.log(article.title);    // Title of the article
 ```
 
+### Debug mode
+
+You can enable debug mode by passing an options object when creating a new Defuddle instance:
+
+```typescript
+const article = new Defuddle(document, { debug: true }).parse();
+```
+
+- More verbose console logging about the parsing process
+- Preserves HTML class and id attributes that are normally stripped
+- Retains all data-* attributes
+- Skips div flattening to preserve document structure
+
 ### Server-side usage
 
 When using Defuddle in a Node.js environment, you can use JSDOM to create a DOM document:
@@ -78,11 +91,13 @@ Defuddle attempts to standardize HTML elements to provide a consistent input for
 
 ### Headings
 
-Anchor links in `<h1>` to `<h6>` elements are removed and become plain headings.
+- The first H1 or H2 heading is removed if it matches the title.
+- H1s are converted to H2s.
+- Anchor links in H1 to H6 elements are removed and become plain headings.
 
 ### Code blocks
 
-Code block are standardized to the following output. If present, line numbers and syntax highlighting are removed, but the language is retained and added as a data attribute and class.
+Code block are standardized. If present, line numbers and syntax highlighting are removed, but the language is retained and added as a data attribute and class.
 
 ```html
 <pre>
@@ -110,6 +125,18 @@ Inline reference<sup id="fnref:1"><a href="#fn:1">1</a></sup>.
 </div>
 ```
 
+### Math
+
+Math elements, including MathJax and KaTeX, are converted to standard MathML:
+
+```html
+<math xmlns="http://www.w3.org/1998/Math/MathML" display="inline" data-latex="a \neq 0">
+  <mi>a</mi>
+  <mo>≠</mo>
+  <mn>0</mn>
+</math>
+```
+
 ## Development
 
 ### Build

package/dist/constants.d.ts

@@ -0,0 +1,14 @@
+export declare const ENTRY_POINT_ELEMENTS: string[];
+export declare const MOBILE_WIDTH = 600;
+export declare const BLOCK_ELEMENTS: string[];
+export declare const PRESERVE_ELEMENTS: Set<string>;
+export declare const INLINE_ELEMENTS: Set<string>;
+export declare const HIDDEN_ELEMENT_SELECTORS: string;
+export declare const EXACT_SELECTORS: string[];
+export declare const PARTIAL_SELECTORS: string[];
+export declare const FOOTNOTE_INLINE_REFERENCES: string;
+export declare const FOOTNOTE_LIST_SELECTORS: string;
+export declare const ALLOWED_EMPTY_ELEMENTS: Set<string>;
+export declare const ALLOWED_ATTRIBUTES: Set<string>;
+export declare const ALLOWED_ATTRIBUTES_DEBUG: Set<string>;
+export declare const SUPPORTED_LANGUAGES: Set<string>;

package/dist/defuddle.d.ts

@@ -19,12 +19,14 @@ export declare class Defuddle {
     private applyMobileStyles;
     private removeHiddenElements;
     private removeClutter;
+    private flattenDivs;
     private cleanContent;
     private removeTrailingHeadings;
     private handleHeadings;
     private removeHtmlComments;
     private stripUnwantedAttributes;
     private removeEmptyElements;
+    private removeEmptyLines;
     private createFootnoteItem;
     private collectFootnotes;
     private findOuterFootnoteContainer;