| 1 | // REFACTORING: Improved HTML generation utility |
| 1 | 2 | function wrap(text, tag) { |
| 2 | 3 | return `<${tag}>${text}</${tag}>`; |
| 3 | 4 | } |
| 4 | 5 | |
| 5 | | function isTag(text, tag) { |
| 6 | | return text.startsWith(`<${tag}>`); |
| 7 | | } |
| 8 | | |
| 9 | | function parser(markdown, delimiter, tag) { |
| 10 | | const pattern = new RegExp(`${delimiter}(.+)${delimiter}`); |
| 11 | | const replacement = `<${tag}>$1</${tag}>`; |
| 12 | | return markdown.replace(pattern, replacement); |
| 13 | | } |
| 14 | | |
| 15 | | function parse__(markdown) { |
| 16 | | return parser(markdown, '__', 'strong'); |
| 17 | | } |
| 6 | // REFACTORING: Removed unused isTag function |
| 18 | 7 | |
| 19 | | function parse_(markdown) { |
| 20 | | return parser(markdown, '_', 'em'); |
| 8 | // REFACTORING: Renamed and improved inline formatting parser |
| 9 | function parseInlineFormatting(markdown) { |
| 10 | // Parse bold text first (double underscores) |
| 11 | const boldPattern = new RegExp(`__(.+)__`); |
| 12 | const boldReplacement = `<strong>$1</strong>`; |
| 13 | let result = markdown.replace(boldPattern, boldReplacement); |
| 14 | |
| 15 | // Then parse italic text (single underscores) |
| 16 | const italicPattern = new RegExp(`_(.+)_`); |
| 17 | const italicReplacement = `<em>$1</em>`; |
| 18 | result = result.replace(italicPattern, italicReplacement); |
| 19 | |
| 20 | return result; |
| 21 | 21 | } |
| 22 | 22 | |
| 23 | | function parseText(markdown, list) { |
| 24 | | const parsedText = parse_(parse__(markdown)); |
| 25 | | if (list) { |
| 26 | | return parsedText; |
| 27 | | } else { |
| 28 | | return wrap(parsedText, 'p'); |
| 23 | // REFACTORING: Simplified text processing with clear responsibility |
| 24 | function processTextContent(markdown, isListItem = false) { |
| 25 | const processedText = parseInlineFormatting(markdown); |
| 26 | |
| 27 | // Only wrap in paragraph tags if it's not a list item |
| 28 | if (isListItem) { |
| 29 | return processedText; |
| 29 | 30 | } |
| 31 | |
| 32 | return wrap(processedText, 'p'); |
| 30 | 33 | } |
| 31 | 34 | |
| 32 | | function parseHeader(markdown, list) { |
| 33 | | let count = 0; |
| 34 | | for (let i = 0; i < markdown.length; i++) { |
| 35 | | if (markdown[i] === '#') { |
| 36 | | count += 1; |
| 35 | // REFACTORING: Improved header parsing with clear logic |
| 36 | function parseHeader(markdown, currentlyInList) { |
| 37 | // Count leading hash characters |
| 38 | let headerLevel = 0; |
| 39 | for (const char of markdown) { |
| 40 | if (char === '#') { |
| 41 | headerLevel++; |
| 37 | 42 | } else { |
| 38 | 43 | break; |
| 39 | 44 | } |
| 40 | 45 | } |
| 41 | | if (count === 0 || count > 6) { |
| 42 | | return [null, list]; |
| 46 | |
| 47 | // Not a header if no hashes or too many (max 6) |
| 48 | if (headerLevel === 0 || headerLevel > 6) { |
| 49 | return [null, currentlyInList]; |
| 43 | 50 | } |
| 44 | | const headerTag = `h${count}`; |
| 45 | | const headerHtml = wrap(markdown.substring(count + 1), headerTag); |
| 46 | | if (list) { |
| 51 | |
| 52 | // Extract header content (skip hashes and space) |
| 53 | const headerContent = markdown.substring(headerLevel + 1); |
| 54 | const headerHtml = wrap(headerContent, `h${headerLevel}`); |
| 55 | |
| 56 | // Close list if we were in one |
| 57 | if (currentlyInList) { |
| 47 | 58 | return [`</ul>${headerHtml}`, false]; |
| 48 | | } else { |
| 49 | | return [headerHtml, false]; |
| 50 | 59 | } |
| 60 | |
| 61 | return [headerHtml, false]; |
| 51 | 62 | } |
| 52 | 63 | |
| 53 | | function parseLineItem(markdown, list) { |
| 54 | | if (markdown.startsWith('*')) { |
| 55 | | const innerHtml = wrap(parseText(markdown.substring(2), true), 'li'); |
| 56 | | if (list) { |
| 57 | | return [innerHtml, true]; |
| 58 | | } else { |
| 59 | | return [`<ul>${innerHtml}`, true]; |
| 60 | | } |
| 64 | // REFACTORING: Improved list item parsing with clearer logic |
| 65 | function parseListItem(markdown, currentlyInList) { |
| 66 | if (!markdown.startsWith('*')) { |
| 67 | return [null, currentlyInList]; |
| 61 | 68 | } |
| 62 | | return [null, list]; |
| 69 | |
| 70 | // Extract list item content (skip '* ') |
| 71 | const itemContent = markdown.substring(2); |
| 72 | const processedContent = processTextContent(itemContent, true); |
| 73 | const listItemHtml = wrap(processedContent, 'li'); |
| 74 | |
| 75 | // Open list if we weren't already in one |
| 76 | if (!currentlyInList) { |
| 77 | return [`<ul>${listItemHtml}`, true]; |
| 78 | } |
| 79 | |
| 80 | return [listItemHtml, true]; |
| 63 | 81 | } |
| 64 | 82 | |
| 65 | | function parseParagraph(markdown, list) { |
| 66 | | if (!list) { |
| 67 | | return [parseText(markdown, false), false]; |
| 68 | | } else { |
| 69 | | return [`</ul>${parseText(markdown, false)}`, false]; |
| 83 | // REFACTORING: Simplified paragraph parsing |
| 84 | function parseParagraph(markdown, currentlyInList) { |
| 85 | const paragraphHtml = processTextContent(markdown, false); |
| 86 | |
| 87 | // Close list if we were in one |
| 88 | if (currentlyInList) { |
| 89 | return [`</ul>${paragraphHtml}`, false]; |
| 70 | 90 | } |
| 91 | |
| 92 | return [paragraphHtml, false]; |
| 71 | 93 | } |
| 72 | 94 | |
| 73 | | function parseLine(markdown, list) { |
| 74 | | let [result, inListAfter] = parseHeader(markdown, list); |
| 95 | // REFACTORING: Clearer parsing logic with explicit fallback chain |
| 96 | function parseLine(markdown, currentlyInList) { |
| 97 | // Try parsing as header first |
| 98 | let [result, newListState] = parseHeader(markdown, currentlyInList); |
| 99 | |
| 100 | // If not a header, try parsing as list item |
| 75 | 101 | if (result === null) { |
| 76 | | [result, inListAfter] = parseLineItem(markdown, list); |
| 102 | [result, newListState] = parseListItem(markdown, currentlyInList); |
| 77 | 103 | } |
| 104 | |
| 105 | // If neither header nor list item, treat as paragraph |
| 78 | 106 | if (result === null) { |
| 79 | | [result, inListAfter] = parseParagraph(markdown, list); |
| 107 | [result, newListState] = parseParagraph(markdown, currentlyInList); |
| 80 | 108 | } |
| 109 | |
| 110 | // This should never happen with valid input |
| 81 | 111 | if (result === null) { |
| 82 | | throw new Error('Remove this line and implement the function'); |
| 112 | throw new Error('Unrecognized markdown line: ' + markdown); |
| 83 | 113 | } |
| 84 | | return [result, inListAfter]; |
| 114 | |
| 115 | return [result, newListState]; |
| 85 | 116 | } |
| 86 | 117 | |
| 87 | 118 | /** |
| 88 | | * @param {string} markdown |
| 89 | | * @returns {string} |
| 119 | * REFACTORING: Main parser function with improved clarity |
| 120 | * Parses markdown text and returns HTML |
| 121 | * @param {string} markdown - The markdown text to parse |
| 122 | * @returns {string} The resulting HTML |
| 90 | 123 | */ |
| 91 | | export function parse(markdown) { |
| 124 | function parse(markdown) { |
| 92 | 125 | const lines = markdown.split('\n'); |
| 93 | | let result = ''; |
| 94 | | let list = false; |
| 95 | | for (let i = 0; i < lines.length; i++) { |
| 96 | | let [lineResult, newList] = parseLine(lines[i], list); |
| 97 | | result += lineResult; |
| 98 | | list = newList; |
| 126 | let htmlResult = ''; |
| 127 | let currentlyInList = false; |
| 128 | |
| 129 | // Process each line of markdown |
| 130 | for (const line of lines) { |
| 131 | const [lineHtml, newListState] = parseLine(line, currentlyInList); |
| 132 | htmlResult += lineHtml; |
| 133 | currentlyInList = newListState; |
| 99 | 134 | } |
| 100 | | if (list) { |
| 101 | | return result + '</ul>'; |
| 102 | | } else { |
| 103 | | return result; |
| 135 | |
| 136 | // Close any unclosed list |
| 137 | if (currentlyInList) { |
| 138 | htmlResult += '</ul>'; |
| 104 | 139 | } |
| 140 | |
| 141 | return htmlResult; |
| 105 | 142 | } |
| 143 | |
| 144 | module.exports = { parse }; |