markdown-magic 3.0.0 → 3.0.1

package/lib/utils/md/fixtures/file-with-links.md

@@ -49,6 +49,10 @@ authors:
 
 ![](https://avatars2.githubusercontent.com/u/532272?v=3&s=400)
 
+This is the weird markdown link syntax <https://foooooooooooo.com>
+
+this is less than sign
+
 Hear Bob Bobster discuss the evolution of Serverless and the launch of ABC at the AWS Serverless Community Day.
 
 <iframe width="560" height="315" src="https://www.youtube.com/embed/KX7tj3giizI" frameBorder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture" allowFullScreen></iframe>
@@ -61,6 +65,12 @@ Hear Bob Bobster discuss the evolution of Serverless and the launch of ABC at th
   <img src="/img/deploy/button.svg">
 </a>
 
+
+<a href="https://www.yoursite.com/pricing?utm_source=active%20users&utm_medium=email&utm_campaign=feature%20launch&utm_content=bottom%20cta%20button">
+  Utm params link
+</a>
+
+
 Title xyz
 ============================
 

package/lib/utils/md/md.test.js

@@ -3,10 +3,9 @@ const path = require('path')
 const { test } = require('uvu')
 const assert = require('uvu/assert')
 const { deepLog } = require('../logs')
-const { stringify } = require('../html-to-json')
 const { parseMarkdown } = require('./parse')
 const { findLinks } = require('./find-links')
-const { findFrontmatter } = require('./find-frontmatter')
+const { parseFrontmatter } = require('./find-frontmatter')
 
 const FILE_PATH = path.join(__dirname, 'fixtures/file-with-links.md')
 // const FILE_PATH = path.join(__dirname, 'fixtures/2022-01-22-date-in-filename.md')
@@ -14,7 +13,6 @@ const fileContents = fs.readFileSync(FILE_PATH, 'utf-8')
 
 test('parseMarkdown API', async () => {
   const res = parseMarkdown(fileContents, { filePath: FILE_PATH })
-  // deepLog(res)
   assert.is(typeof res, 'object')
   assert.is(typeof res.ast, 'object')
   assert.is(typeof res.data, 'object')
@@ -23,8 +21,78 @@ test('parseMarkdown API', async () => {
   assert.is(Array.isArray(res.errors), true)
 })
 
+test('Verify contents', async () => {
+  const res = parseMarkdown(fileContents, { 
+    filePath: FILE_PATH 
+  })
+  deepLog('Results:', res)
+  assert.equal(res.links, [
+    'https://funky-frontmatter.com',
+    'https://www.front.com/blog/open-beta-changes',
+    'https://youtu.be/A1bL4pHuivU',
+    'https://foooooooooooo.com',
+    'https://www.youtube.com/embed/KX7tj3giizI',
+    'https://app.netlify.com/start/deploy',
+    'https://www.yoursite.com/pricing?utm_source=active%20users&utm_medium=email&utm_campaign=feature%20launch&utm_content=bottom%20cta%20button',
+    'https://ABC.com/sign-up',
+    'http://jobs.ABC.net',
+    '/foobar'
+  ])
+  assert.equal(res.images, [
+    '/assets/images/lol-frontmatter.jpg',
+    '/assets/images/lol.jpg',
+    'assets/images/san-juan-mountains.jpg',
+    'https://res.cloudinary.com/ABC/image/upload/f_auto,q_auto/c_fill,w_1200/v1668114635/what-you-can-build_p8uape.png',
+    'https://avatars2.githubusercontent.com/u/532272?v=3&s=400',
+    'https://dope-frontmatter.com/img/deploy/button.svg',
+    'https://frontmatter.com/img/deploy/button.svg',
+    '/img/in-nested-frontmatter/button.svg',
+    'https://www.netlify.com/img/deploy/button.svg',
+    'https://fooo.com/img/deploy/button.svg',
+    '/img/deploy/button.svg',
+    'img/deploy/button.svg',
+    '../img/deploy/button.svg'
+  ])
+})
+
+test('opts - includeAst false', async () => {
+  const res = parseMarkdown(fileContents, { 
+    filePath: FILE_PATH,
+  })
+  // deepLog('Results:', res)
+  assert.ok(Array.isArray(res.ast))
+  /* Disable AST */
+  const resTwo = parseMarkdown(fileContents, { 
+    filePath: FILE_PATH,
+    includeAst: false,
+  })
+  // deepLog('Results two:', resTwo)
+  assert.ok(typeof resTwo.ast === 'undefined')
+})
+
+test('opts - includeImages false', async () => {
+  const res = parseMarkdown(fileContents, { 
+    filePath: FILE_PATH,
+    // includeAst: false,
+    includeImages: false,
+  })
+  deepLog('Results:', res)
+  assert.ok(typeof res.links === 'object')
+  assert.ok(typeof res.images === 'undefined')
+})
+
+test('opts - includeLinks false', async () => {
+  const res = parseMarkdown(fileContents, { 
+    filePath: FILE_PATH,
+    includeLinks: false,
+  })
+  deepLog('Results:', res)
+  assert.ok(typeof res.links === 'undefined')
+  assert.ok(typeof res.images === 'object')
+})
+
 // test('File have correct extensions', async () => {
-//   const { data } = findFrontmatter(fileWithLinks, FILE_PATH)
+//   const { data } = parseFrontmatter(fileWithLinks, FILE_PATH)
 //   console.log('frontmatter data', data)
 //   const links = findLinks(fileWithLinks, { frontmatter: data })
 //   // console.log('links', links)

package/lib/utils/md/parse.js

@@ -1,54 +1,74 @@
-// const { validateHtml } = require('./validate-html')
-const { findFrontmatter } = require('./find-frontmatter')
-const { parse } = require('../html-to-json')
-const { getLineCount } = require('./utils')
+const { parse } = require('micro-mdx-parser')
+const { parseFrontmatter } = require('./find-frontmatter')
 const { findUnmatchedHtmlTags } = require('./find-unmatched-html-tags')
 const { findLinks } = require('./find-links')
 const { findDate } = require('./find-date')
 const { findCodeBlocks, REMOVE_CODE_BLOCK_REGEX } = require('./find-code-blocks')
-// const { findImages, findLiveImages } = require('./find-images')
-// const { findHtmlTags } = require('./find-html-tags')
+const { getLineCount } = require('./utils')
 
 function parseMarkdown(text, opts = {}) {
-  const { filePath, validateHtml } = opts
+  const { 
+    filePath,
+    validator,
+    astParser,
+    includeAst = true,
+    includeLinks = true,
+    includeImages = true,
+    includeCodeBlocks = true,
+    includePositions = false,
+    includeRawFrontmatter = false,
+  } = opts
   let errors = []
-  let frontmatter = {}
+  let result = {}
   let alreadySetError = false
   try {
-    frontmatter = findFrontmatter(text, filePath)
+    result = parseFrontmatter(text)
   } catch (err) {
     console.log(`Broken frontmatter in ${filePath}...`)
     errors.push(err.message)
     alreadySetError = true
   }
-  const { data, content = '', rawFrontMatter = '' } = frontmatter
+  const { data, content = '', frontMatterRaw = '' } = result
   if (!data || !Object.keys(data).length) {
     if (!alreadySetError) {
       errors.push(`Missing or broken frontmatter in ${filePath}. Double check file for --- frontmatter tags`)
     }
   }
 
-  // const imagesInYml = findLinksInFrontMatter(data, findLiveImages)
-  // console.log('linksInYml', linksInYml)
-  // const links = findLiveLinks(text)
-  //console.log(`links ${filePath}`, links)
-  // const relativeLinks = findRelativeLinks(text)
-  // console.log(`relativeLinks ${filePath}`, relativeLinks)
-  /* gets all images in file */
-  // const images = findLiveImages(text) // findImages(text)
-  // console.log(`images ${filePath}`, images)
-  // const htmlTags = findHtmlTags(text)
-  const linkData = findLinks(text)
-
-  const html = parse(content, {
-    includePositions: true,
-    offset: {
-      lineOffset: getLineCount(rawFrontMatter),
-      charOffset: rawFrontMatter.length 
+  let links
+  let images
+  if (includeLinks || includeImages) {
+    const linkData = findLinks(text, {
+      frontmatter: data
+    })
+    links = linkData.links
+    images = linkData.images
+  }
+
+  let ast = []
+  if (includeAst) {
+    /* If custom parser supplied */
+    if (astParser) {
+      ast = astParser(content, opts)
+    } else {
+      /* Default parser */
+      ast = parse(content, {
+        includePositions,
+        // offset: {
+        //   lineOffset: getLineCount(frontMatterRaw),
+        //   charOffset: frontMatterRaw.length 
+        // }
+      })
     }
-  })
+  }
+
+  // console.log('html', html)
   // console.log(`htmlTags ${filePath}`, htmlTags)
-  const codeBlocks = findCodeBlocks(text, filePath)
+  let codeBlocks
+  if (includeCodeBlocks) {
+    codeBlocks = findCodeBlocks(text, { filePath, includePositions })
+  }
+
   // console.log(`codeBlocks ${filePath}`, codeBlocks)
   const tagsErrors = findUnmatchedHtmlTags(text, filePath)
 
@@ -58,9 +78,9 @@ function parseMarkdown(text, opts = {}) {
   // }
 
   let htmlValidation = []
-  if (validateHtml) {
-    const contentsNoCodeBlocks = content.replace(REMOVE_CODE_BLOCK_REGEX, '')
-    htmlValidation = validateHtml(contentsNoCodeBlocks, filePath)
+  if (typeof validator === 'function') {
+    // const contentsNoCodeBlocks = content.replace(REMOVE_CODE_BLOCK_REGEX, '')
+    htmlValidation = validator(content, filePath)
   }
 
   if (htmlValidation && htmlValidation.length) {
@@ -76,45 +96,49 @@ function parseMarkdown(text, opts = {}) {
     errors = errors.concat(codeBlocks.errors)
   }
 
-  const frontMatterData = data || {}
+  const frontmatter = data || {}
   const date = findDate({
-    frontmatter: frontMatterData, 
+    frontmatter,
     filePath
   })
 
-  const markdownInfo = {
-    ...(filePath) ? { filePath } : {},
-    ...(date) ? { date } : {},
-    ast: html,
-    data: frontMatterData,
-    links: linkData.links,
-    images: linkData.images,
-    codeBlocks,
-    content,
-    errors,
-    // frontMatterRaw: rawFrontMatter,
-    // ...frontmatter
-  }
-
-  /* // Debugger
-  const path = require('path')
-  if (path.basename(filePath)=== '2020-06-30-welcome-to-vendia.md') {
-    // console.log('text', text)
-    // console.log('Frontmatter')
-    // console.log(data)
-    // console.log('findLinks')
-    // deepLog(links)
-    // console.log('components')
-    // deepLog(components)
-    console.log('markdownInfo')
-    deepLog(markdownInfo)
-
-    deepLog(stringify(html))
-    process.exit(1)
-  }
-  /** */
-
-  return markdownInfo
+  const parseResult = {}
+
+  if (filePath) {
+    parseResult.filePath = filePath
+  }
+
+  if (date) {
+    parseResult.date = date
+  }
+
+  if (includeAst) {
+    parseResult.ast = ast
+  }
+
+  /* Include frontmatter as data object */
+  parseResult.data = frontmatter
+
+  if (includeRawFrontmatter) {
+    parseResult.frontMatterRaw = frontMatterRaw
+  }
+
+  if (includeLinks) {
+    parseResult.links = links
+  }
+
+  if (includeImages) {
+    parseResult.images = images
+  }
+
+  if (includeCodeBlocks) {
+    parseResult.codeBlocks = codeBlocks.blocks
+  }
+
+  parseResult.content = content
+  parseResult.errors = errors
+
+  return parseResult
 }
 
 module.exports = {

package/lib/utils/regex-timeout.js

@@ -33,7 +33,8 @@ This is normal text in markdown. Keep it.
 // var pattern = /([ \t]*)(?:<!-{2,}(?:.*|\r?|\n?|\s*)docs-start\s*([(\[\{]*[A-Za-z0-9_$-]*[)\]\}]*)\s*)((?:.*?|.*?\r?\n?)*?)<!-{2,}(?:.*|\r?|\n?|\s*)docs-end(?:.|\r?\n)*?-{2,}>/gim
 
 function safeRegex(str) {
-  const syntaxInfo = getSyntaxInfo('md')
+  const syntax = 'md'
+  const syntaxInfo = getSyntaxInfo(syntax)
   if (!syntaxInfo.pattern) {
     throw new Error(`Unknown syntax "${syntax}"`)
   }

package/lib/utils/regex.js

@@ -2,6 +2,7 @@
 // REGEX to look for regex
 // https://github.com/kgryte/regex-regex/blob/master/lib/index.js
 const REGEX_REGEX = /^\/((?:\\\/|[^\/])+)\/([imgy]*)$/
+const LINEBREAK_MATCHER = /\r\n|[\r\n\u2028\u2029]/;
 
 function escapeRegexString(string) {
 	if (typeof string !== 'string') {
@@ -54,7 +55,7 @@ function cleanStepMatches(matches) {
 /**
  * Match comment steps in files
  */
-function getSteps() {
+function getSteps(matches) {
   const steps = cleanStepMatches(matches)
 
   const sortedSteps = steps.reduce((accumulator, currentValue, currentIndex, array) => {
@@ -97,7 +98,7 @@ const TABEL_ROW_REGEX = /^\s*\|.*?\|\s*$/
  * @param {string} text  The text to validate.
  * @returns {boolean}
  */
-const isTableRow = (text) => text.match(TABEL_ROW_REGEX);
+const isTableRow = (text) => Boolean(text.match(TABEL_ROW_REGEX))
 
 module.exports = {
   REGEX_REGEX,

package/lib/utils/remoteRequest.js

@@ -3,6 +3,7 @@ const request = require('sync-request')
 module.exports = function remoteRequest(url) {
   let body
   try {
+    // @ts-expect-error
     const res = request('GET', url)
     body = res.getBody('utf8')
   } catch (e) {

package/lib/utils/syntax.js

@@ -69,6 +69,9 @@ const syntaxMap = {
   yml: yaml
 }
 
+// Additional comment syntaxes for future
+// https://github.com/apidoc/apidoc/tree/27566b48a9e8bad2fb3920c02473940917eabe70#supported-programming-languages
+
 function getSyntaxInfo(syntax = '') {
   return syntaxMap[syntax.toLowerCase()] || {}
 }

package/lib/utils/text.js

@@ -37,6 +37,25 @@ function getTextBetweenChars(text, start, end) {
   return text.slice(start, end)
 }
 
+/**
+ * Get text between two words
+ * @param {string} s 
+ * @param {string} prefix 
+ * @param {string} suffix
+ * @returns {string}
+ */
+function getTextBetweenWords(s, prefix, suffix) {
+  let i = s.indexOf(prefix)
+  if (i === -1) return ''
+  s = s.substring(i + prefix.length)
+  if (suffix) {
+    i = s.indexOf(suffix)
+    if (i === -1) return ''
+    s = s.substring(0, i)
+  }
+  return s
+}
+
 function replaceTextBetweenChars(str = '', start, end, newStr) {
   return str.substring(0, start) + newStr + str.substring(end)
 }
@@ -77,7 +96,7 @@ function stripIndent(string, indentation) {
 
 /**
  * Trim leading & trailing spaces/line breaks in code and keeps the indentation of the first non-empty line
- * @param {string} str 
+ * @param {string|number} str 
  * @returns string
  */
  function trimString(str = '') {
@@ -149,10 +168,10 @@ function stripCommentBlockOld(str, syntax = 'md') {
 /**
  * Strip out comment blocks
  * @param {string} str 
- * @param {'md' | 'js'} syntax 
+ * @param {typeof import('../types')['syntaxType']} syntax 
  * @returns {string} clean commentless string
  */
-function stripComments(str, { syntax = 'md' }) {
+function stripComments(str, syntax = 'md') {
   const syntaxData = syntaxMap[syntax]
   const [ openPattern, closePattern ] = syntaxData.pattern
   const OR = (syntaxData.singleLine) ? `|\\s?[ \\t]*${syntaxData.singleLine}` : ''
@@ -236,7 +255,55 @@ function convertCommentSyntax(str, { from, to }) {
   return str.replace(regexToUse, newText)
 }
 
+/**
+ * capitalize first letter
+ * @param {string} str 
+ * @returns 
+ */
+function capitalizeFirstLetter(str) {
+  return capitalize(str.charAt(0)) + str.slice(1)
+}
+
+/**
+ * capitalize string
+ * @param {string} str 
+ * @returns 
+ */
+function capitalize(str = '') {
+  return str.toUpperCase()
+}
+
+function camelCase(str = '') {
+  return str.replace(/[-_ ](\w)/g, (_, c) => c.toUpperCase())
+}
+
+function kebabCase(str = '') {
+  return str.replace(/\B([A-Z])/g, '-$1').toLowerCase()
+}
+
+const smallWords = /^(a|an|and|as|at|but|by|en|for|if|in|nor|of|on|or|per|the|to|vs?\.?|via)$/i;
+
+function toTitleCase(str = '') {
+	return str.replace(/[A-Za-z0-9\u00C0-\u00FF]+[^\s-]*/g, (match, index, title) => {
+		if (index > 0
+			&& index + match.length !== title.length
+			&& match.search(smallWords) > -1
+			&& title.charAt(index - 2) !== ':'
+			&& (title.charAt(index + match.length) !== '-' || title.charAt(index - 1) === '-')
+			&& title.charAt(index - 1).search(/[^\s-]/) < 0) {
+			return match.toLowerCase();
+		}
+
+		if (match.substr(1).search(/[A-Z]|\../) > -1) {
+			return match;
+		}
+
+		return match.charAt(0).toUpperCase() + match.substr(1);
+	})
+}
+
 module.exports = {
+  toTitleCase,
   getLines,
   getLineCount,
   getWordCount,
@@ -245,6 +312,7 @@ module.exports = {
   getLastCharacter,
   getRowAndColumnFromCharPos,
   getTextBetweenChars,
+  getTextBetweenWords,
   getTextBetweenLines,
   replaceTextBetweenChars,
   stripIndent,

package/lib/utils/text.test.js

@@ -88,9 +88,7 @@ nice
 `
 
 test('Remove Markdown comments', () => {
-  const parsedValue = stripComments(md, {
-    syntax: 'md'
-  })
+  const parsedValue = stripComments(md, 'md')
   /*
   console.log('parsedValue')
   logOutput(parsedValue)
@@ -162,9 +160,7 @@ console.log('inline') /* inline klsjlkajdsalkjd *****/
 
 /* inline */
 console.log('nice')
-`, {
-  syntax: 'js'
-})
+`, 'js')
   /*
   console.log('parsedValue')
   logOutput(parsedValue)
@@ -195,9 +191,7 @@ test('Remove YAML comments', () => {
   steve: 'cool' # inline comment
   foo:
     bar: lol
-`, {
-  syntax: 'yml'
-})
+`, 'yml')
 
   /*
   console.log('yml', dedentString(parsedValue))