import { describe, expect, it } from 'bun:test' import { parseTeamsContent, teamsHtmlToText } from './message-content' const AMS_IMAGE_URL = 'https://kr-prod.asyncgw.teams.microsoft.com/v1/objects/0-skr-d1-abc/views/imgo' const ATTACHMENT_URL = 'https://contoso-my.sharepoint.com/personal/alice/Documents/report.pdf' describe('parseTeamsContent', () => { it('keeps the raw html and lists inline images for rich messages', () => { const html = `

Look at this

image

Thoughts?

` const parsed = parseTeamsContent(html, { messagetype: 'RichText/Html' }) expect(parsed).toEqual({ content: 'Look at this\n\nThoughts?', html, files: [AMS_IMAGE_URL], }) }) it('omits html and files for plain text messages', () => { const parsed = parseTeamsContent('Tom & Jerry', { messagetype: 'Text' }) expect(parsed).toEqual({ content: 'Tom & Jerry', html: undefined, files: undefined }) }) it('lists inline images before attachments from properties.files', () => { const properties = { files: JSON.stringify([{ '@type': 'http://schema.skype.com/File', objectUrl: ATTACHMENT_URL }]), } const html = `

See

` const parsed = parseTeamsContent(html, { messagetype: 'RichText/Html', properties }) expect(parsed.files).toEqual([AMS_IMAGE_URL, ATTACHMENT_URL]) }) it('falls back to fileInfo.fileUrl when an attachment has no objectUrl', () => { const properties = { files: [{ fileInfo: { fileUrl: ATTACHMENT_URL } }] } const parsed = parseTeamsContent('

report

', { messagetype: 'RichText/Html', properties }) expect(parsed.files).toEqual([ATTACHMENT_URL]) }) it('reads attachments when properties itself arrives as a JSON string', () => { const properties = JSON.stringify({ files: JSON.stringify([{ objectUrl: ATTACHMENT_URL }]) }) const parsed = parseTeamsContent('

report

', { messagetype: 'RichText/Html', properties }) expect(parsed.files).toEqual([ATTACHMENT_URL]) }) it('ignores malformed properties.files', () => { const parsed = parseTeamsContent('

hi

', { messagetype: 'RichText/Html', properties: { files: '{not json' } }) expect(parsed.files).toBeUndefined() }) it('does not treat emoji, stickers, or GIFs as files', () => { const html = '

hi πŸ™‡

' + '' + 'Happy Dog GIF' const parsed = parseTeamsContent(html, { messagetype: 'RichText/Html' }) expect(parsed.files).toBeUndefined() expect(parsed.content).toBe('hi πŸ™‡') }) it('treats channel content without a messagetype as html only when it has tags', () => { expect(parseTeamsContent('

a < b

')).toEqual({ content: 'a < b', html: '

a < b

', files: undefined, }) expect(parseTeamsContent('a < b')).toEqual({ content: 'a < b', html: undefined, files: undefined }) }) it('returns empty content for a missing body', () => { expect(parseTeamsContent(undefined, { messagetype: 'RichText/Html' }).content).toBe('') }) }) describe('teamsHtmlToText', () => { it('turns block elements and line breaks into newlines', () => { expect(teamsHtmlToText('

one
two

\r\n

 

\r\n
three
')).toBe('one\ntwo\n\nthree') }) it('treats source newlines as whitespace, like a browser', () => { expect( teamsHtmlToText( '

title
\r\nhttps://example.com
\r\nbody\r\ncontinues

', ), ).toBe('title\nhttps://example.com\nbody continues') }) it('decodes named and numeric entities once', () => { expect(teamsHtmlToText('

으둜 😀 "q" &lt;

')).toBe('으둜 πŸ˜€ "q" <') }) it('decodes common typographic named entities', () => { expect(teamsHtmlToText('

© 2026 — “ok”…

')).toBe('Β© 2026 β€” β€œok”…') }) it('keeps link targets that differ from the link text', () => { expect(teamsHtmlToText('Docs & more')).toBe( 'Docs & more (https://example.com/a?x=1&y=2)', ) }) it('does not repeat a link target that matches the link text', () => { expect(teamsHtmlToText('https://example.com')).toBe('https://example.com') expect(teamsHtmlToText('alice@example.com')).toBe('alice@example.com') }) it('preserves whitespace inside pre blocks', () => { expect(teamsHtmlToText('

code:

{\n  "a": 1\n}

done

')).toBe( 'code:\n\n{\n "a": 1\n}\n\ndone', ) }) it('leaves blank lines and leading spaces inside pre blocks untouched', () => { expect(teamsHtmlToText('
  indented\n\n\n\nafter gap  
')).toBe(' indented\n\n\n\nafter gap ') }) it('collapses runs of spaces within a line', () => { expect(teamsHtmlToText('

a b\t c

')).toBe('a b c') }) })