Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Strip headings for readability / wikilinks compatibility #34

Merged
merged 1 commit into from
Feb 18, 2024
Merged

Strip headings for readability / wikilinks compatibility #34

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
46 changes: 42 additions & 4 deletions main.js
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,12 +1,14 @@
let Plugin = class {}
let MarkdownRenderer = {}
let MarkdownRenderChild = class {}
let htmlToMarkdown = (html) => html

if (isObsidian()) {
const obsidian = require('obsidian')
Plugin = obsidian.Plugin
MarkdownRenderer = obsidian.MarkdownRenderer
MarkdownRenderChild = obsidian.MarkdownRenderChild
htmlToMarkdown = obsidian.htmlToMarkdown
}

const codeblockId = 'table-of-contents'
Expand Down Expand Up @@ -159,11 +161,47 @@ function getMarkdownInlineFirstLevelFromHeadings(headings, options) {
}

function getMarkdownHeading(heading, options) {
const stripMarkdown = (text) => {
text = text.replaceAll('*', '').replaceAll('_', '').replaceAll('`', '')
text = text.replaceAll('==', '').replaceAll('~~', '')
text = text.replace(/\[([^\]]+)\]\([^)]+\)/g, '$1') // Strip markdown links
return text
}
const stripHtml = (text) => stripMarkdown(htmlToMarkdown(text))
const stripWikilinks = (text, isForLink) => {
// Strip [[link|text]] format
// For the text part of the final link we only keep "text"
// For the link part we need the text + link
// Example: "# Some [[file.md|heading]]" must be translated to "[[#Some file.md heading|Some heading]]"
text = text.replace(/\[\[([^\]]+)\|([^\]]+)\]\]/g, isForLink ? '$1 $2' : '$2')
text = text.replace(/\[\[([^\]]+)\]\]/g, '$1') // Strip [[link]] format
return text
}
const stripTags = (text) => text.replaceAll('#', '')
if (options.includeLinks) {
let cleaned = heading.heading
// Strip reserved wikilink characters
cleaned = cleaned.replaceAll('|', '-').replaceAll('[', '{').replaceAll(']', '}')
return `[[#${cleaned}]]`
// Remove markdown, HTML & wikilinks from text for readability, as they are not rendered in a wikilink
let text = heading.heading
text = stripMarkdown(text)
text = stripHtml(text)
text = stripWikilinks(text, false)
// Remove wikilinks & tags from link or it won't be clickable (on the other hand HTML & markdown must stay)
let link = heading.heading
link = stripWikilinks(link, true)
link = stripTags(link)

// Return wiklink style link
return `[[#${link}|${text}]]`
// Why not markdown links? Because even if it looks like the text part would have a better compatibility
// with complex headings (as it would support HTML, markdown, etc) the link part is messy,
// because it requires some encoding that looks buggy and undocumented; official docs state the link must be URL encoded
// (https://help.obsidian.md/Linking+notes+and+files/Internal+links#Supported+formats+for+internal+links)
// but it doesn't work properly, example: "## Some <em>heading</em> with simple HTML" must be encoded as:
// [Some <em>heading</em> with simple HTML](#Some%20<em>heading</em>%20with%20simpler%20HTML)
// and not
// [Some <em>heading</em> with simple HTML](#Some%20%3Cem%3Eheading%3C%2Fem%3E%20with%20simpler%20HTML)
// Also it won't be clickable at all if the heading contains #tags or more complex HTML
// (example: ## Some <em style="background: red">heading</em> #with-a-tag)
// (unless there is a way to encode these use cases that I didn't find)
}
return heading.heading
}
Expand Down
90 changes: 60 additions & 30 deletions test/headings.test.js
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,7 +4,7 @@ const {
} = require('../main.js')

const testStandardHeadings = [
{ heading: 'Title [1] | level 1', level: 1 }, // With wiklink characters to be stripped
{ heading: 'Title 1 level 1', level: 1 },
{ heading: 'Title 1 level 2', level: 2 },
{ heading: 'Title 1 level 3', level: 3 },
{ heading: 'Title 2 level 1', level: 1 },
Expand All @@ -21,17 +21,23 @@ const testHeadingsWithoutFirstLevel = [
{ heading: 'Title 3 level 3', level: 3 },
]

const testHeadingsWithSpecialChars = [
{ heading: 'Title 1 `level 1` {with special chars}, **bold**, _italic_, #a-tag, ==highlighted== and ~~strikethrough~~ text', level: 1 },
{ heading: 'Title 1 level 2 <em style="color: black">with HTML</em>', level: 2 },
{ heading: 'Title 1 level 2 [[wikilink1]] [[wikilink2|wikitext2]] [mdlink](https://mdurl)', level: 2 },
]

describe('Headings', () => {
test('Returns indented list with links', () => {
const options = parseOptionsFromSourceText('')
const md = getMarkdownFromHeadings(testStandardHeadings, options)
const expectedMd = sanitizeMd(`
- [[#Title {1} - level 1]]
- [[#Title 1 level 2]]
- [[#Title 1 level 3]]
- [[#Title 2 level 1]]
- [[#Title 3 level 1]]
- [[#Title 3 level 2]]
- [[#Title 1 level 1|Title 1 level 1]]
- [[#Title 1 level 2|Title 1 level 2]]
- [[#Title 1 level 3|Title 1 level 3]]
- [[#Title 2 level 1|Title 2 level 1]]
- [[#Title 3 level 1|Title 3 level 1]]
- [[#Title 3 level 2|Title 3 level 2]]
`)
expect(md).toEqual(expectedMd)
})
Expand All @@ -40,12 +46,12 @@ describe('Headings', () => {
const options = parseOptionsFromSourceText('')
const md = getMarkdownFromHeadings(testHeadingsWithoutFirstLevel, options)
const expectedMd = sanitizeMd(`
- [[#Title 1 level 2]]
- [[#Title 1 level 3]]
- [[#Title 1 level 4]]
- [[#Title 2 level 2]]
- [[#Title 3 level 2]]
- [[#Title 3 level 3]]
- [[#Title 1 level 2|Title 1 level 2]]
- [[#Title 1 level 3|Title 1 level 3]]
- [[#Title 1 level 4|Title 1 level 4]]
- [[#Title 2 level 2|Title 2 level 2]]
- [[#Title 3 level 2|Title 3 level 2]]
- [[#Title 3 level 3|Title 3 level 3]]
`)
expect(md).toEqual(expectedMd)
})
Expand All @@ -55,9 +61,9 @@ describe('Headings', () => {
options.minLevel = 2
const md = getMarkdownFromHeadings(testStandardHeadings, options)
const expectedMd = sanitizeMd(`
- [[#Title 1 level 2]]
- [[#Title 1 level 3]]
- [[#Title 3 level 2]]
- [[#Title 1 level 2|Title 1 level 2]]
- [[#Title 1 level 3|Title 1 level 3]]
- [[#Title 3 level 2|Title 3 level 2]]
`)
expect(md).toEqual(expectedMd)
})
Expand All @@ -67,11 +73,11 @@ describe('Headings', () => {
options.maxLevel = 2
const md = getMarkdownFromHeadings(testStandardHeadings, options)
const expectedMd = sanitizeMd(`
- [[#Title {1} - level 1]]
- [[#Title 1 level 2]]
- [[#Title 2 level 1]]
- [[#Title 3 level 1]]
- [[#Title 3 level 2]]
- [[#Title 1 level 1|Title 1 level 1]]
- [[#Title 1 level 2|Title 1 level 2]]
- [[#Title 2 level 1|Title 2 level 1]]
- [[#Title 3 level 1|Title 3 level 1]]
- [[#Title 3 level 2|Title 3 level 2]]
`)
expect(md).toEqual(expectedMd)
})
Expand All @@ -81,7 +87,7 @@ describe('Headings', () => {
options.includeLinks = false
const md = getMarkdownFromHeadings(testStandardHeadings, options)
const expectedMd = sanitizeMd(`
- Title [1] | level 1
- Title 1 level 1
- Title 1 level 2
- Title 1 level 3
- Title 2 level 1
Expand All @@ -97,22 +103,46 @@ describe('Headings', () => {
const md = getMarkdownFromHeadings(testStandardHeadings, options)
const expectedMd = sanitizeMd(`
# My TOC
- [[#Title {1} - level 1]]
- [[#Title 1 level 2]]
- [[#Title 1 level 3]]
- [[#Title 2 level 1]]
- [[#Title 3 level 1]]
- [[#Title 3 level 2]]
- [[#Title 1 level 1|Title 1 level 1]]
- [[#Title 1 level 2|Title 1 level 2]]
- [[#Title 1 level 3|Title 1 level 3]]
- [[#Title 2 level 1|Title 2 level 1]]
- [[#Title 3 level 1|Title 3 level 1]]
- [[#Title 3 level 2|Title 3 level 2]]
`)
expect(md).toEqual(expectedMd)
})

test('Returns indented list with sanitized links from special chars', () => {
const options = parseOptionsFromSourceText('')
const md = getMarkdownFromHeadings(testHeadingsWithSpecialChars, options)
const expectedMd = sanitizeMd(`
- [[#Title 1 \`level 1\` {with special chars}, **bold**, _italic_, a-tag, ==highlighted== and ~~strikethrough~~ text|Title 1 level 1 {with special chars}, bold, italic, #a-tag, highlighted and strikethrough text]]
- [[#Title 1 level 2 <em style="color: black">with HTML</em>|Title 1 level 2 <em style="color: black">with HTML</em>]]
- [[#Title 1 level 2 wikilink1 wikilink2 wikitext2 [mdlink](https://mdurl)|Title 1 level 2 wikilink1 wikitext2 mdlink]]
`)
expect(md).toEqual(expectedMd)
})

test('Returns indented list without links from special chars', () => {
const options = parseOptionsFromSourceText('')
options.includeLinks = false
const md = getMarkdownFromHeadings(testHeadingsWithSpecialChars, options)
const expectedMd = sanitizeMd(`
- Title 1 \`level 1\` {with special chars}, **bold**, _italic_, #a-tag, ==highlighted== and ~~strikethrough~~ text
- Title 1 level 2 <em style="color: black">with HTML</em>
- Title 1 level 2 [[wikilink1]] [[wikilink2|wikitext2]] [mdlink](https://mdurl)
`)
expect(md).toEqual(expectedMd)
})


test('Returns flat first-level list with links', () => {
const options = parseOptionsFromSourceText('')
options.style = 'inlineFirstLevel'
const md = getMarkdownFromHeadings(testStandardHeadings, options)
const expectedMd = sanitizeMd(`
[[#Title {1} - level 1]] | [[#Title 2 level 1]] | [[#Title 3 level 1]]
[[#Title 1 level 1|Title 1 level 1]] | [[#Title 2 level 1|Title 2 level 1]] | [[#Title 3 level 1|Title 3 level 1]]
`)
expect(md).toEqual(expectedMd)
})
Expand All @@ -123,7 +153,7 @@ describe('Headings', () => {
options.includeLinks = false
const md = getMarkdownFromHeadings(testStandardHeadings, options)
const expectedMd = sanitizeMd(`
Title [1] | level 1 | Title 2 level 1 | Title 3 level 1
Title 1 level 1 | Title 2 level 1 | Title 3 level 1
`)
expect(md).toEqual(expectedMd)
})
Expand Down
Loading