Implemented unit and integration tests for the parser.

10 months ago · 346ee9457b
7 changed files with 312 additions and 10 deletions
--- a/tests/integration/markupIntegration.test.ts
+++ b/tests/integration/markupIntegration.test.ts
@ -0,0 +1,99 @@
				@@ -0,0 +1,99 @@
+import { describe, it, expect } from 'vitest';
+import { parseBasicmarkup } from '../../src/lib/utils/markup/basicMarkupParser';
+import { parseAdvancedmarkup } from '../../src/lib/utils/markup/advancedMarkupParser';
+import { readFileSync } from 'fs';
+import { join } from 'path';
+
+const testFilePath = join(__dirname, './markupTestfile.md');
+const md = readFileSync(testFilePath, 'utf-8');
+
+describe('Markup Integration Test', () => {
+  it('parses markupTestfile.md with the basic parser', async () => {
+    const output = await parseBasicmarkup(md);
+    // Headers (should be present as text, not <h1> tags)
+    expect(output).toContain('This is a test');
+    expect(output).toContain('============');
+    expect(output).toContain('### Disclaimer');
+    // Unordered list
+    expect(output).toContain('<ul');
+    expect(output).toContain('but');
+    // Ordered list
+    expect(output).toContain('<ol');
+    expect(output).toContain('first');
+    // Nested lists
+    expect(output).toMatch(/<ul[^>]*>.*<ul[^>]*>/s);
+    // Blockquotes
+    expect(output).toContain('<blockquote');
+    expect(output).toContain('This is important information');
+    // Inline code
+    expect(output).toContain('<div class="leather min-h-full w-full flex flex-col items-center">');
+    // Images
+    expect(output).toMatch(/<img[^>]+src="https:\/\/upload\.wikimedia\.org\/wikipedia\/commons\/f\/f1\/Heart_coraz%C3%B3n\.svg"/);
+    // Links
+    expect(output).toMatch(/<a[^>]+href="https:\/\/github.com\/nostrability\/nostrability\/issues\/146"/);
+    // Hashtags
+    expect(output).toContain('text-primary-600');
+    // Nostr identifiers (should be njump.me links)
+    expect(output).toContain('https://njump.me/npub1l5sga6xg72phsz5422ykujprejwud075ggrr3z2hwyrfgr7eylqstegx9z');
+    // Wikilinks
+    expect(output).toContain('wikilink');
+    // YouTube iframe
+    expect(output).toMatch(/<iframe[^>]+youtube/);
+    // Tracking token removal: should not contain utm_, fbclid, or gclid in any link
+    expect(output).not.toMatch(/utm_/);
+    expect(output).not.toMatch(/fbclid/);
+    expect(output).not.toMatch(/gclid/);
+    // Horizontal rule (should be present as --- in basic)
+    expect(output).toContain('---');
+    // Footnote references (should be present as [^1] in basic)
+    expect(output).toContain('[^1]');
+    // Table (should be present as | Syntax | Description | in basic)
+    expect(output).toContain('| Syntax      | Description |');
+  });
+
+  it('parses markupTestfile.md with the advanced parser', async () => {
+    const output = await parseAdvancedmarkup(md);
+    // Headers
+    expect(output).toContain('<h1');
+    expect(output).toContain('<h2');
+    expect(output).toContain('Disclaimer');
+    // Unordered list
+    expect(output).toContain('<ul');
+    expect(output).toContain('but');
+    // Ordered list
+    expect(output).toContain('<ol');
+    expect(output).toContain('first');
+    // Nested lists
+    expect(output).toMatch(/<ul[^>]*>.*<ul[^>]*>/s);
+    // Blockquotes
+    expect(output).toContain('<blockquote');
+    expect(output).toContain('This is important information');
+    // Inline code
+    expect(output).toMatch(/<code[^>]*>.*leather min-h-full w-full flex flex-col items-center.*<\/code>/s);
+    // Images
+    expect(output).toMatch(/<img[^>]+src="https:\/\/upload\.wikimedia\.org\/wikipedia\/commons\/f\/f1\/Heart_coraz%C3%B3n\.svg"/);
+    // Links
+    expect(output).toMatch(/<a[^>]+href="https:\/\/github.com\/nostrability\/nostrability\/issues\/146"/);
+    // Hashtags
+    expect(output).toContain('text-primary-600');
+    // Nostr identifiers (should be njump.me links)
+    expect(output).toContain('https://njump.me/npub1l5sga6xg72phsz5422ykujprejwud075ggrr3z2hwyrfgr7eylqstegx9z');
+    // Wikilinks
+    expect(output).toContain('wikilink');
+    // YouTube iframe
+    expect(output).toMatch(/<iframe[^>]+youtube/);
+    // Tracking token removal: should not contain utm_, fbclid, or gclid in any link
+    expect(output).not.toMatch(/utm_/);
+    expect(output).not.toMatch(/fbclid/);
+    expect(output).not.toMatch(/gclid/);
+    // Horizontal rule
+    expect(output).toContain('<hr');
+    // Footnote references and section
+    expect(output).toContain('Footnotes');
+    expect(output).toMatch(/<li id=\"fn-1\">/);
+    // Table
+    expect(output).toContain('<table');
+    // Code blocks
+    expect(output).toContain('<pre');
+  });
+}); 
--- a/src/lib/utils/markup/markupTestfile.md
+++ b/src/lib/utils/markup/markupTestfile.md
@ -25,6 +25,12 @@ npub1l5sga6xg72phsz5422ykujprejwud075ggrr3z2hwyrfgr7eylqstegx9z wrote this. That
				@@ -25,6 +25,12 @@ npub1l5sga6xg72phsz5422ykujprejwud075ggrr3z2hwyrfgr7eylqstegx9z wrote this. That
 > important information
 > with a second[^2] footnote.

+This is a youtube link 
+https://www.youtube.com/watch?v=9aqVxNCpx9s
+
+And here is a link with tracking tokens:
+https://arstechnica.com/science/2019/07/new-data-may-extend-norse-occupancy-in-north-america/?fbclid=IwAR1LOW3BebaMLinfkWFtFpzkLFi48jKNF7P6DV2Ux2r3lnT6Lqj6eiiOZNU
+
 This is an unordered list:
 * but
 * not
--- a/tests/unit/advancedMarkupParser.test.ts
+++ b/tests/unit/advancedMarkupParser.test.ts
@ -0,0 +1,118 @@
				@@ -0,0 +1,118 @@
+import { describe, it, expect } from 'vitest';
+import { parseAdvancedmarkup } from '../../src/lib/utils/markup/advancedMarkupParser';
+
+function stripWS(str: string) {
+  return str.replace(/\s+/g, ' ').trim();
+}
+
+describe('Advanced Markup Parser', () => {
+  it('parses headers (ATX and Setext)', async () => {
+    const input = '# H1\nText\n\nH2\n====\n';
+    const output = await parseAdvancedmarkup(input);
+    expect(stripWS(output)).toContain('H1');
+    expect(stripWS(output)).toContain('H2');
+  });
+
+  it('parses bold, italic, and strikethrough', async () => {
+    const input = '*bold* **bold** _italic_ __italic__ ~strikethrough~ ~~strikethrough~~';
+    const output = await parseAdvancedmarkup(input);
+    expect(output).toContain('<strong>bold</strong>');
+    expect(output).toContain('<em>italic</em>');
+    expect(output).toContain('<del class="line-through">strikethrough</del>');
+  });
+
+  it('parses blockquotes', async () => {
+    const input = '> quote';
+    const output = await parseAdvancedmarkup(input);
+    expect(output).toContain('<blockquote');
+    expect(output).toContain('quote');
+  });
+
+  it('parses multi-line blockquotes', async () => {
+    const input = '> quote\n> quote';
+    const output = await parseAdvancedmarkup(input);
+    expect(output).toContain('<blockquote');
+    expect(output).toContain('quote');
+    expect(output).toContain('quote');
+  });
+
+  it('parses unordered lists', async () => {
+    const input = '* a\n* b';
+    const output = await parseAdvancedmarkup(input);
+    expect(output).toContain('<ul');
+    expect(output).toContain('a');
+    expect(output).toContain('b');
+  });
+
+  it('parses ordered lists', async () => {
+    const input = '1. one\n2. two';
+    const output = await parseAdvancedmarkup(input);
+    expect(output).toContain('<ol');
+    expect(output).toContain('one');
+    expect(output).toContain('two');
+  });
+
+  it('parses links and images', async () => {
+    const input = '[link](https://example.com) ![alt](https://img.com/x.png)';
+    const output = await parseAdvancedmarkup(input);
+    expect(output).toContain('<a');
+    expect(output).toContain('<img');
+  });
+
+  it('parses hashtags', async () => {
+    const input = '#hashtag';
+    const output = await parseAdvancedmarkup(input);
+    expect(output).toContain('text-primary-600');
+    expect(output).toContain('#hashtag');
+  });
+
+  it('parses nostr identifiers', async () => {
+    const input = 'npub1qqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqq';
+    const output = await parseAdvancedmarkup(input);
+    expect(output).toContain('https://njump.me/npub1qqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqq');
+  });
+
+  it('parses emoji shortcodes', async () => {
+    const input = 'hello :smile:';
+    const output = await parseAdvancedmarkup(input);
+    expect(output).toMatch(/😄|:smile:/);
+  });
+
+  it('parses wikilinks', async () => {
+    const input = '[[Test Page|display]]';
+    const output = await parseAdvancedmarkup(input);
+    expect(output).toContain('wikilink');
+    expect(output).toContain('display');
+  });
+
+  it('parses tables (with and without headers)', async () => {
+    const input = `| Syntax | Description |\n|--------|-------------|\n| Header | Title |\n| Paragraph | Text |\n\n| a | b |\n| c | d |`;
+    const output = await parseAdvancedmarkup(input);
+    expect(output).toContain('<table');
+    expect(output).toContain('Header');
+    expect(output).toContain('a');
+  });
+
+  it('parses code blocks (with and without language)', async () => {
+    const input = '```js\nconsole.log(1);\n```\n```\nno lang\n```';
+    const output = await parseAdvancedmarkup(input);
+    const textOnly = output.replace(/<[^>]+>/g, '');
+    expect(output).toContain('<pre');
+    expect(textOnly).toContain('console.log(1);');
+    expect(textOnly).toContain('no lang');
+  });
+
+  it('parses horizontal rules', async () => {
+    const input = '---';
+    const output = await parseAdvancedmarkup(input);
+    expect(output).toContain('<hr');
+  });
+
+  it('parses footnotes (references and section)', async () => {
+    const input = 'Here is a footnote[^1].\n\n[^1]: This is the footnote.';
+    const output = await parseAdvancedmarkup(input);
+    expect(output).toContain('Footnotes');
+    expect(output).toContain('This is the footnote');
+    expect(output).toContain('fn-1');
+  });
+}); 
--- a/tests/unit/basicMarkupParser.test.ts
+++ b/tests/unit/basicMarkupParser.test.ts
@ -0,0 +1,88 @@
				@@ -0,0 +1,88 @@
+import { describe, it, expect } from 'vitest';
+import { parseBasicmarkup } from '../../src/lib/utils/markup/basicMarkupParser';
+
+// Helper to strip whitespace for easier comparison
+function stripWS(str: string) {
+  return str.replace(/\s+/g, ' ').trim();
+}
+
+describe('Basic Markup Parser', () => {
+  it('parses ATX and Setext headers', async () => {
+    const input = '# H1\nText\n\nH2\n====\n';
+    const output = await parseBasicmarkup(input);
+    expect(stripWS(output)).toContain('H1');
+    expect(stripWS(output)).toContain('H2');
+  });
+
+  it('parses bold, italic, and strikethrough', async () => {
+    const input = '*bold* **bold** _italic_ __italic__ ~strikethrough~ ~~strikethrough~~';
+    const output = await parseBasicmarkup(input);
+    expect(output).toContain('<strong>bold</strong>');
+    expect(output).toContain('<em>italic</em>');
+    expect(output).toContain('<del class="line-through">strikethrough</del>');
+  });
+
+  it('parses blockquotes', async () => {
+    const input = '> quote';
+    const output = await parseBasicmarkup(input);
+    expect(output).toContain('<blockquote');
+    expect(output).toContain('quote');
+  });
+
+  it('parses multi-line blockquotes', async () => {
+    const input = '> quote\n> quote';
+    const output = await parseBasicmarkup(input);
+    expect(output).toContain('<blockquote');
+    expect(output).toContain('quote');
+    expect(output).toContain('quote');
+  });
+
+  it('parses unordered lists', async () => {
+    const input = '* a\n* b';
+    const output = await parseBasicmarkup(input);
+    expect(output).toContain('<ul');
+    expect(output).toContain('a');
+    expect(output).toContain('b');
+  });
+
+  it('parses ordered lists', async () => {
+    const input = '1. one\n2. two';
+    const output = await parseBasicmarkup(input);
+    expect(output).toContain('<ol');
+    expect(output).toContain('one');
+    expect(output).toContain('two');
+  });
+
+  it('parses links and images', async () => {
+    const input = '[link](https://example.com) ![alt](https://img.com/x.png)';
+    const output = await parseBasicmarkup(input);
+    expect(output).toContain('<a');
+    expect(output).toContain('<img');
+  });
+
+  it('parses hashtags', async () => {
+    const input = '#hashtag';
+    const output = await parseBasicmarkup(input);
+    expect(output).toContain('text-primary-600');
+    expect(output).toContain('#hashtag');
+  });
+
+  it('parses nostr identifiers', async () => {
+    const input = 'npub1qqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqq';
+    const output = await parseBasicmarkup(input);
+    expect(output).toContain('https://njump.me/npub1qqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqq');
+  });
+
+  it('parses emoji shortcodes', async () => {
+    const input = 'hello :smile:';
+    const output = await parseBasicmarkup(input);
+    expect(output).toMatch(/😄|:smile:/);
+  });
+
+  it('parses wikilinks', async () => {
+    const input = '[[Test Page|display]]';
+    const output = await parseBasicmarkup(input);
+    expect(output).toContain('wikilink');
+    expect(output).toContain('display');
+  });
+}); 
--- a/tests/unit/example.js
+++ b/tests/unit/example.js
@ -1,3 +0,0 @@
				@@ -1,3 +0,0 @@
-export function sum(a, b) {
-  return a + b
-}
--- a/tests/unit/example.unit-test.js
+++ b/tests/unit/example.unit-test.js
@ -1,6 +0,0 @@
				@@ -1,6 +0,0 @@
-import { expect, test } from 'vitest'
-import { sum } from './example.js'
-
-test('adds 1 + 2 to equal 3', () => {
-  expect(sum(1, 2)).toBe(3)
-})
--- a/vite.config.ts
+++ b/vite.config.ts
@ -27,7 +27,7 @@ export default defineConfig({
				@@ -27,7 +27,7 @@ export default defineConfig({
    }
  },
  test: {
-    include: ['./tests/unit/**/*.unit-test.js']
+    include: ['./tests/unit/**/*.test.ts', './tests/integration/**/*.test.ts']
  },
  define: {
    // Expose the app version as a global variable