doc and test access to formatters from formatters

html-to-text · Dec 6, 2022 · 69e3a24 · 69e3a24
1 parent 5e8e413
commit 69e3a24
Show file tree

Hide file tree

Showing 2 changed files with 55 additions and 0 deletions.
diff --git a/packages/html-to-text/README.md b/packages/html-to-text/README.md
@@ -291,6 +291,35 @@ Refer to [generic formatters](https://github.com/html-to-text/node-html-to-text/
 
 Refer to [BlockTextBuilder](https://github.com/html-to-text/node-html-to-text/blob/master/packages/base/src/block-text-builder.js) for available functions and arguments.
 
+#### Call other formatters from a custom formatter
+
+Most of the times this is *not* what you actually need. Most practical problems can be solved with [selectors](#selectors).
+
+If you really need to inspect the node internals, not just attributes, then you can do it like this:
+
+```javascript
+const options = {
+  // ...
+  formatters: {
+    filterBlockFormatter: function (elem, walk, builder, formatOptions) {
+      // all built-in and custom formatters available by name
+      const blockFormatter = builder.options.formatters['block'];
+      if (blockFormatter && elem.children.some(/* predicate */)) {
+        blockFormatter(elem, walk, builder, formatOptions);
+      }
+    }
+  },
+  selectors: [
+    {
+      selector: 'div.questionable',
+      format: 'filterBlockFormatter',
+      options: { leadingLineBreaks: 1, trailingLineBreaks: 1 }
+    }
+  ],
+  // ...
+}
+```
+
 ## Example
 
 * Input text: [test.html](https://github.com/html-to-text/node-html-to-text/blob/master/packages/html-to-text/test/test.html)

diff --git a/packages/html-to-text/test/tags.js b/packages/html-to-text/test/tags.js
@@ -950,6 +950,32 @@ describe('tags', function () {
       expect(htmlToText(html, options)).to.equal(expected);
     });
 
+    it('should allow to call existing formatters from other formatters', function () {
+      const html = '<div>Useful</div><div>Advertisement</div><article>Handy <section><div>info</div><div>Advertisement</div></section></article><article>ads galore</article>';
+      const options = {
+        formatters: {
+          adFreeBlock: function (elem, walk, builder, formatOptions) {
+            // domutils package has functions more suitable in similar situations. This is just a test.
+            const regExp = formatOptions.filterRegExp || /advertisement/i;
+            if (elem.children.some(ch => ch.type === 'text' && regExp.test(ch.data))) {
+              // do nothing
+            } else {
+              const blockFormatter = builder.options.formatters['block'];
+              if (blockFormatter) {
+                blockFormatter(elem, walk, builder, formatOptions);
+              }
+            }
+          }
+        },
+        selectors: [
+          { selector: 'div', format: 'adFreeBlock' },
+          { selector: 'article', format: 'adFreeBlock', options: { filterRegExp: /^ad/i, leadingLineBreaks: 4 } }
+        ]
+      };
+      const expected = 'Useful\n\n\n\nHandy\ninfo';
+      expect(htmlToText(html, options)).to.equal(expected);
+    });
+
   });
 
   describe('selectors', function () {