remove-markdown 0.6.3 → 0.6.4

package/README.md

@@ -33,7 +33,8 @@ const plainText = removeMd(markdown, {
   abbr: true,                  // remove abbreviations, if present (default: false)
   replaceLinksWithURL: true,   // remove inline links, if present (default: false)
   separateLinksAndTexts: ': ', // replace inline links with text, separator and link, if present (default: null)
-  htmlTagsToSkip: ['a', 'b']   // HTML tags to skip, if present (default: [])
+  htmlTagsToSkip: ['a', 'b'],  // HTML tags to skip, if present (default: [])
+  throwError: false,           // throw errors instead of catching and logging (default: false)
 });
 ```
 

package/index.d.ts

@@ -2,11 +2,12 @@ declare function removeMd(md: string, options?: {
   stripListLeaders?: boolean;
   listUnicodeChar?: string;
   gfm?: boolean;
-  useImgAltText: boolean;
+  useImgAltText?: boolean;
   abbr?: boolean;
   replaceLinksWithURL?: boolean;
   separateLinksAndTexts?: string;
   htmlTagsToSkip?: string[];
+  throwError?: boolean;
 }): string;
 
 export = removeMd;

package/index.js

@@ -63,7 +63,7 @@ module.exports = function(md, options) {
       // Remove images
       .replace(/\!\[(.*?)\][\[\(].*?[\]\)]/g, options.useImgAltText ? '$1' : '')
       // Remove inline links
-      .replace(/\[([\s\S]*?)\]\s*[\(\[].*?[\)\]]/g, options.replaceLinksWithURL ? '$2' : '$1')
+      .replace(/\[([\s\S]*?)\]\s*[\(\[](.*?)[\)\]]/g, options.replaceLinksWithURL ? '$2' : '$1')
       // Remove blockquotes
       .replace(/^(\n)?\s{0,3}>\s?/gm, '$1')
       // .replace(/(^|\n)\s{0,3}>\s?/g, '\n\n')

package/package.json

@@ -1,8 +1,14 @@
 {
   "name": "remove-markdown",
-  "version": "0.6.3",
+  "version": "0.6.4",
   "description": "Remove Markdown formatting from text",
   "main": "index.js",
+  "files": [
+    "index.js",
+    "index.d.ts",
+    "README.md",
+    "LICENSE"
+  ],
   "scripts": {
     "test": "./node_modules/.bin/mocha -R spec test/remove-markdown.js"
   },

package/.claude/settings.local.json

@@ -1,8 +0,0 @@
-{
-  "permissions": {
-    "allow": [
-      "mcp__acp__Bash",
-      "mcp__acp__Write"
-    ]
-  }
-}

package/.github/workflows/default.yaml

@@ -1,27 +0,0 @@
-name: Run tests
-
-on:
-  push:
-    branches: [ main ]
-  pull_request:
-    branches: [ main ]
-
-jobs:
-  build:
-    runs-on: ubuntu-latest
-
-    strategy:
-      matrix:
-        node-version: [18.x, 20.x, 22.x]
-        # See supported Node.js release schedule at https://nodejs.org/en/about/releases/
-
-    steps:
-    - uses: actions/checkout@v3
-    - name: Use Node.js ${{ matrix.node-version }}
-      uses: actions/setup-node@v3
-      with:
-        node-version: ${{ matrix.node-version }}
-        cache: 'npm'
-    - run: npm ci
-    - run: npm run build --if-present
-    - run: npm test

package/CHANGELOG.md

@@ -1,32 +0,0 @@
-# Changelog
-
-All notable changes to this project will be documented in this file.
-
-## [0.6.3] - 2026-01-14
-
-### Added
-
-- New `separateLinksAndTexts` option to replace inline links with text and URL separated by a custom string ([#101](https://github.com/zuchka/remove-markdown/pull/101) by [@tafel](https://github.com/tafel))
-  - Example: `removeMd('[link](http://example.com)', { separateLinksAndTexts: ': ' })` returns `'link: http://example.com'`
-
-## [0.6.2] - 2025-05-02
-
-### Fixed
-
-- Improved handling of links with square brackets inside them ([#93](https://github.com/zuchka/remove-markdown/pull/93))
-
-## [0.6.1] - 2025-05-02
-
-### Improved
-
-- Better support for multiline code blocks ([#96](https://github.com/zuchka/remove-markdown/pull/96) by [@johnjiang](https://github.com/johnjiang))
-
-## [0.6.0] - 2024-12-16
-
-### Added
-
-- `htmlTagsToSkip` option to preserve specific HTML tags while stripping others ([#88](https://github.com/zuchka/remove-markdown/pull/88))
-
-### Fixed
-
-- Horizontal rules regex pattern ([#91](https://github.com/zuchka/remove-markdown/pull/91))

package/CLAUDE.md

@@ -1,70 +0,0 @@
-# CLAUDE.md
-
-This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
-
-## Project Overview
-
-**remove-markdown** is a Node.js module that strips Markdown formatting from text, leaving only plain text. It's designed for use cases like displaying excerpts without Markdown syntax.
-
-The entire implementation is a single-file module (`index.js`) that exports one function which applies a series of regex replacements to remove various Markdown elements.
-
-## Development Commands
-
-### Running Tests
-```bash
-npm test
-```
-Runs the Mocha test suite with the spec reporter.
-
-### Running a Single Test
-To run a specific test, use Mocha's grep flag:
-```bash
-./node_modules/.bin/mocha -R spec test/remove-markdown.js --grep "test description pattern"
-```
-
-## Code Architecture
-
-### Core Structure
-- **index.js** (97 lines): Main module that exports a single function
-  - Takes markdown text and an options object as parameters
-  - Applies regex replacements in a specific order to strip Markdown syntax
-  - Returns plain text or original input if error occurs (unless `throwError` option is set)
-
-### Key Implementation Details
-
-**Regex Application Order Matters**: The order of regex replacements is critical. For example, horizontal rules must be removed before list leaders to avoid conflicts (see index.js:15).
-
-**Options System**: All options default to specific values if not provided. The module uses `options.hasOwnProperty()` checks rather than simple truthy checks to allow `false` values to be explicitly set.
-
-**Error Handling**: The entire regex processing is wrapped in try-catch. By default, errors are logged and the original markdown is returned. Set `options.throwError: true` to propagate errors.
-
-**HTML Tag Filtering**: The `htmlTagsToSkip` option dynamically builds a regex to preserve specific HTML tags while removing others (see index.js:41-49).
-
-**Link Replacement**: Two mutually exclusive link handling modes:
-- `replaceLinksWithURL: true` - replaces links with URLs (note: implementation at index.js:66 references `$2` which appears to be a bug as it should extract the URL)
-- `separateLinksAndTexts` - replaces `[text](url)` with `text<separator>url` format (applied first at index.js:52)
-
-### Test Structure
-- **test/remove-markdown.js** (258 lines): Comprehensive test suite using Mocha and Chai
-- Tests cover all markdown elements: headers, emphasis, lists, links, images, code blocks, blockquotes, HTML tags
-- Includes performance tests to prevent ReDoS vulnerabilities
-- Tests edge cases like emphasis with spaces, nested brackets, indentation
-
-## Important Considerations
-
-### When Adding Features
-- New regex patterns must be carefully positioned in the replacement chain (index.js:18-89)
-- Test edge cases thoroughly, especially patterns that could conflict with existing ones
-- Consider performance implications - some patterns are vulnerable to ReDoS if not carefully written
-
-### Known Quirks
-- The `replaceLinksWithURL` option appears to have a bug where it references `$2` but the capturing group setup may not work as intended (index.js:66)
-- Empty or invalid markdown input is handled gracefully by returning the original input
-- The module preserves code block content (including newlines) while stripping the fencing
-
-### Testing Strategy
-When modifying regex patterns:
-1. Run the full test suite first
-2. Add specific test cases for your changes
-3. Test performance with large inputs and repeated patterns
-4. Verify your changes don't break the order-dependent behavior

package/test/remove-markdown.js

@@ -1,258 +0,0 @@
-'use strict';
-const expect = require('chai').expect;
-const removeMd = require('../');
-
-describe('remove Markdown', function () {
-  describe('removeMd', function () {
-    it('should leave a string alone without markdown', function () {
-      const string = 'Javascript Developers are the best.';
-      expect(removeMd(string)).to.equal(string);
-    });
-
-    it('should strip out remaining markdown', function () {
-      const string = '*Javascript* developers are the _best_.';
-      const expected = 'Javascript developers are the best.';
-      expect(removeMd(string)).to.equal(expected);
-    });
-
-    it('should leave non-matching markdown markdown', function () {
-      const string = '*Javascript* developers* are the _best_.';
-      const expected = 'Javascript developers* are the best.';
-      expect(removeMd(string)).to.equal(expected);
-    });
-
-    it('should leave non-matching markdown, but strip empty anchors', function () {
-      const string = '*Javascript* [developers]()* are the _best_.';
-      const expected = 'Javascript developers* are the best.';
-      expect(removeMd(string)).to.equal(expected);
-    });
-
-    it('should strip HTML', function () {
-      const string = '<p>Hello World</p>';
-      const expected = 'Hello World';
-      expect(removeMd(string)).to.equal(expected);
-    });
-
-    it('should strip anchors', function () {
-      const string = '*Javascript* [developers](https://engineering.condenast.io/)* are the _best_.';
-      const expected = 'Javascript developers* are the best.';
-      expect(removeMd(string)).to.equal(expected);
-    });
-
-    it('should strip img tags', function () {
-      const string = '![](https://placebear.com/640/480)*Javascript* developers are the _best_.';
-      const expected = 'Javascript developers are the best.';
-      expect(removeMd(string)).to.equal(expected);
-    });
-
-    it('should use the alt-text of an image, if it is provided', function () {
-      const string = '![This is the alt-text](https://www.example.com/images/logo.png)';
-      const expected = 'This is the alt-text';
-      expect(removeMd(string)).to.equal(expected);
-    });
-
-    it('should strip code tags', function () {
-      const string = 'In `Getting Started` we set up `something` foo.';
-      const expected = 'In Getting Started we set up something foo.';
-      expect(removeMd(string)).to.equal(expected);
-    });
-
-    it('should strip simple multiline code tags', function () {
-      const string = '```\ncode\n```';
-      const expected = 'code';
-      expect(removeMd(string)).to.equal(expected);
-    });
-
-    it('should strip complex multiline code blocks with language specified', function () {
-      const string = '```javascript\nconst x = 1;\nconst y = 2;\nconsole.log(x + y);\n```';
-      const expected = 'const x = 1;\nconst y = 2;\nconsole.log(x + y);';
-      expect(removeMd(string)).to.equal(expected);
-    });
-
-    it('should strip multiline code blocks with multiple paragraphs', function () {
-      const string = 'Text before\n\n```\ncode line 1\n\ncode line 2\n```\n\nText after';
-      const expected = 'Text before\n\ncode line 1\n\ncode line 2\n\nText after';
-      expect(removeMd(string)).to.equal(expected);
-    });
-
-    it('should leave hashtags in headings', function () {
-      const string = '## This #heading contains #hashtags';
-      const expected = 'This #heading contains #hashtags';
-      expect(removeMd(string)).to.equal(expected);
-    });
-
-    it('should remove emphasis', function () {
-      const string = 'I italicized an *I* and it _made_ me *sad*.';
-      const expected = 'I italicized an I and it made me sad.';
-      expect(removeMd(string)).to.equal(expected);
-    });
-
-    it('should remove emphasis only if there is no space between word and emphasis characters.', function () {
-      const string = 'There should be no _space_, *before* *closing * _ephasis character _.';
-      const expected = 'There should be no space, before *closing * _ephasis character _.';
-      expect(removeMd(string)).to.equal(expected);
-    });
-
-    it('should remove "_" emphasis only if there is space before opening and after closing emphasis characters.', function () {
-      const string = '._Spaces_ _ before_ and _after _ emphasised character results in no emphasis.';
-      const expected = '.Spaces _ before_ and _after _ emphasised character results in no emphasis.';
-      expect(removeMd(string)).to.equal(expected);
-    });
-
-    it('should remove double emphasis', function () {
-      const string = '**this sentence has __double styling__**';
-      const expected = 'this sentence has double styling';
-      expect(removeMd(string)).to.equal(expected);
-    });
-
-    it('should not mistake a horizontal rule when symbols are mixed ', function () {
-      const string = 'Some text on a line\n\n--*\n\nA line below';
-      const expected = 'Some text on a line\n\n--*\n\nA line below';
-      expect(removeMd(string)).to.equal(expected);
-    });
-
-    it('should remove horizontal rules', function () {
-      const string = 'Some text on a line\n\n---\n\nA line below';
-      const expected = 'Some text on a line\n\nA line below';
-      expect(removeMd(string)).to.equal(expected);
-    });
-
-    it('should remove horizontal rules with space-separated asterisks', function () {
-      const string = 'Some text on a line\n\n* * *\n\nA line below';
-      const expected = 'Some text on a line\n\nA line below';
-      expect(removeMd(string)).to.equal(expected);
-    });
-
-    it('should remove blockquotes', function () {
-      const string = '>I am a blockquote';
-      const expected = 'I am a blockquote';
-      expect(removeMd(string)).to.equal(expected);
-    });
-
-    it('should remove blockquotes with spaces', function () {
-      const string = '> I am a blockquote';
-      const expected = 'I am a blockquote';
-      expect(removeMd(string)).to.equal(expected);
-    });
-
-    it('should remove indented blockquotes', function () {
-        var tests = [
-            { string: ' > I am a blockquote', expected: 'I am a blockquote' },
-            { string: '  > I am a blockquote', expected: 'I am a blockquote' },
-            { string: '   > I am a blockquote', expected: 'I am a blockquote' },
-        ];
-        tests.forEach(function (test) {
-            expect(removeMd(test.string)).to.equal(test.expected);
-        });
-    });
-
-    it('should remove blockquotes over multiple lines', function () {
-      const string = '> I am a blockquote firstline  \n>I am a blockquote secondline';
-      const expected = 'I am a blockquote firstline  \nI am a blockquote secondline';
-      expect(removeMd(string)).to.equal(expected);
-    });
-
-    it('should remove blockquotes following other content', function () {
-      const string = '## A headline\n\nA paragraph of text\n\n> I am a blockquote';
-      const expected = 'A headline\n\nA paragraph of text\n\nI am a blockquote';
-
-      expect(removeMd(string)).to.equal(expected);
-    });
-
-    it('should not remove greater than signs', function () {
-      var tests = [
-        { string: '100 > 0', expected: '100 > 0' },
-        { string: '100 >= 0', expected: '100 >= 0' },
-        { string: '100>0', expected: '100>0' },
-        { string: '> 100 > 0', expected: '100 > 0' },
-        { string: '1 < 100', expected: '1 < 100' },
-        { string: '1 <= 100', expected: '1 <= 100' },
-      ];
-      tests.forEach(function (test) {
-        expect(removeMd(test.string)).to.equal(test.expected);
-      });
-    });
-
-    it('should strip unordered list leaders', function () {
-      const string = 'Some text on a line\n\n* A list Item\n* Another list item';
-      const expected = 'Some text on a line\n\nA list Item\nAnother list item';
-      expect(removeMd(string)).to.equal(expected);
-    });
-
-    it('should strip ordered list leaders', function () {
-      const string = 'Some text on a line\n\n9. A list Item\n10. Another list item';
-      const expected = 'Some text on a line\n\nA list Item\nAnother list item';
-      expect(removeMd(string)).to.equal(expected);
-    });
-
-    it('should strip list items with bold word in the beginning', function () {
-      const string = 'Some text on a line\n\n- **A** list Item\n- **Another** list item';
-      const expected = 'Some text on a line\n\nA list Item\nAnother list item';
-      expect(removeMd(string)).to.equal(expected);
-    });
-
-    it('should handle paragraphs with markdown', function () {
-      const paragraph = '\n## This is a heading ##\n\nThis is a paragraph with [a link](http://www.disney.com/).\n\n### This is another heading\n\nIn `Getting Started` we set up `something` foo.\n\n  * Some list\n  * With items\n    * Even indented';
-      const expected = '\nThis is a heading\n\nThis is a paragraph with a link.\n\nThis is another heading\n\nIn Getting Started we set up something foo.\n\n  Some list\n  With items\n    Even indented';
-      expect(removeMd(paragraph)).to.equal(expected);
-    });
-
-    it('should remove links', function () {
-      const string = 'This is a [link](http://www.disney.com/).';
-      const expected = 'This is a link.';
-      expect(removeMd(string)).to.equal(expected);
-    });
-
-    it('should remove links with square brackets', function () {
-      const string = 'This is a [link [with brackets]](http://www.disney.com/).';
-      const expected = 'This is a link [with brackets].';
-      expect(removeMd(string)).to.equal(expected);
-    });
-
-    it('should not strip paragraphs without content', function() {
-      const paragraph = '\n#This paragraph\n##This paragraph#';
-      const expected = paragraph;
-      expect(removeMd(paragraph)).to.equal(expected);
-    });
-
-    it('should not trigger ReDoS with atx-headers', function () {
-      const start = Date.now();
-
-      const paragraph = '\n## This is a long "'+' '.repeat(200)+'" heading ##\n';
-      const expected = /\nThis is a long " {200}" heading\n/;
-      expect(removeMd(paragraph)).to.match(expected);
-
-      const duration = Date.now()-start;
-      expect(duration).to.be.lt(1000);
-    });
-
-    it('should work fast even with lots of whitespace', function () {
-      const string = 'Some text with lots of                                                                                                                                                                                                       whitespace';
-      const expected = 'Some text with lots of                                                                                                                                                                                                       whitespace';
-      expect(removeMd(string)).to.equal(expected);
-    });
-
-    it('should still remove escaped markdown syntax', function () {
-      const string = '\# Heading in _italic_';
-      const expected = 'Heading in italic';
-      expect(removeMd(string)).to.equal(expected);
-    });
-
-    it('should skip specified HTML tags when htmlTagsToSkip option is provided', () => {
-      const markdown =
-        '<div>HTML content <sub>Superscript</sub> <span>span text</span></div>'
-      const result = removeMd(markdown, {htmlTagsToSkip: ['sub']})
-      expect(result).to.equal('HTML content <sub>Superscript</sub> span text')
-      const result2 = removeMd(markdown, {htmlTagsToSkip: ['sub', 'span']})
-      expect(result2).to.equal(
-        'HTML content <sub>Superscript</sub> <span>span text</span>',
-      )
-    })
-
-    it('should replace inline link with text and link, with separator', function () {
-      const string = 'some [inline link](http://www.disney.com/).';
-      const expected = 'some inline link: http://www.disney.com/.';
-      expect(removeMd(string, {separateLinksAndTexts: ': '})).to.equal(expected);
-    });
-  });
-});