File size: 6,697 Bytes
0ec6423 f45f4a9 0ec6423 d288030 0ec6423 d288030 0ec6423 f45f4a9 0ec6423 d288030 0ec6423 d288030 0ec6423 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 |
/**
* LaTeX Metadata Extractor
* Extracts document metadata from LaTeX files for frontmatter generation
*/
/**
* Extract metadata from LaTeX content
* @param {string} latexContent - Raw LaTeX content
* @returns {object} - Extracted metadata object
*/
export function extractLatexMetadata(latexContent) {
const metadata = {};
// Extract title
const titleMatch = latexContent.match(/\\title\s*\{\s*([^}]+)\s*\}/s);
if (titleMatch) {
metadata.title = titleMatch[1]
.replace(/\\[a-zA-Z]+/g, '') // Remove LaTeX commands
.replace(/\n/g, ' ')
.trim();
}
// Extract authors with their specific affiliations
const authors = [];
const authorMatches = latexContent.matchAll(/\\authorOne\[[^\]]*\]\{([^}]+)\}/g);
for (const match of authorMatches) {
const fullAuthorInfo = match[1];
// Determine affiliations based on macros present
const affiliations = [];
if (fullAuthorInfo.includes('\\ensps')) {
affiliations.push(1); // École Normale Supérieure
}
if (fullAuthorInfo.includes('\\oxford')) {
affiliations.push(1); // University of Oxford (index 1 dans le frontmatter)
}
if (fullAuthorInfo.includes('\\hf')) {
affiliations.push(2); // Hugging Face (index 2 dans le frontmatter)
}
// Clean author name by removing macros
let authorName = fullAuthorInfo
.replace(/\\ensps/g, '') // Remove École macro
.replace(/\\hf/g, '') // Remove Hugging Face macro
.replace(/\\oxford/g, '') // Remove Oxford macro
.replace(/\\[a-zA-Z]+/g, '') // Remove any other LaTeX commands
.replace(/\s+/g, ' ') // Normalize whitespace
.trim();
// Skip empty authors or placeholder entries
if (authorName && authorName !== '...') {
authors.push({
name: authorName,
affiliations: affiliations.length > 0 ? affiliations : [2] // Default to HF if no macro
});
}
}
if (authors.length > 0) {
metadata.authors = authors;
}
// Extract affiliations dynamically from \contribution command
const contributionMatch = latexContent.match(/\\contribution\[\]\{([^}]+)\}/);
if (contributionMatch) {
const contributionText = contributionMatch[1];
// Parse affiliations from contribution text
const affiliations = [];
// Split by common separators and clean up
const parts = contributionText
.split(/[,;]/)
.map(part => part.trim())
.filter(part => part.length > 0);
for (const part of parts) {
// Remove LaTeX commands and clean up
const cleanName = part
.replace(/\\[a-zA-Z]+/g, '') // Remove LaTeX commands like \oxford, \hf
.replace(/\s+/g, ' ') // Normalize whitespace
.trim();
if (cleanName && cleanName.length > 0) {
affiliations.push({
name: cleanName
});
}
}
if (affiliations.length > 0) {
metadata.affiliations = affiliations;
}
}
// Fallback to hardcoded affiliations if no \contribution found
if (!metadata.affiliations || metadata.affiliations.length === 0) {
metadata.affiliations = [
{
name: "École Normale Supérieure Paris-Saclay"
},
{
name: "University of Oxford"
},
{
name: "Hugging Face"
}
];
}
// Extract date if available (common LaTeX patterns)
const datePatterns = [
/\\date\s*\{([^}]+)\}/,
/\\newcommand\s*\{\\date\}\s*\{([^}]+)\}/,
];
for (const pattern of datePatterns) {
const dateMatch = latexContent.match(pattern);
if (dateMatch) {
metadata.published = dateMatch[1].trim();
break;
}
}
// Fallback to current date if no date found
if (!metadata.published) {
metadata.published = new Date().toLocaleDateString('en-US', {
year: 'numeric',
month: 'short',
day: '2-digit'
});
}
return metadata;
}
/**
* Generate YAML frontmatter from metadata object
* @param {object} metadata - Metadata object
* @returns {string} - YAML frontmatter string
*/
export function generateFrontmatter(metadata) {
let frontmatter = '---\n';
// Title
if (metadata.title) {
frontmatter += `title: "${metadata.title}"\n`;
}
// Authors
if (metadata.authors && metadata.authors.length > 0) {
frontmatter += 'authors:\n';
metadata.authors.forEach(author => {
frontmatter += ` - name: "${author.name}"\n`;
if (author.url) {
frontmatter += ` url: "${author.url}"\n`;
}
frontmatter += ` affiliations: [${author.affiliations.join(', ')}]\n`;
});
}
// Affiliations
if (metadata.affiliations && metadata.affiliations.length > 0) {
frontmatter += 'affiliations:\n';
metadata.affiliations.forEach((affiliation, index) => {
frontmatter += ` - name: "${affiliation.name}"\n`;
if (affiliation.url) {
frontmatter += ` url: "${affiliation.url}"\n`;
}
});
}
// Publication date
if (metadata.published) {
frontmatter += `published: "${metadata.published}"\n`;
}
// Additional metadata
if (metadata.doi) {
frontmatter += `doi: "${metadata.doi}"\n`;
}
if (metadata.description) {
frontmatter += `description: "${metadata.description}"\n`;
}
if (metadata.licence) {
frontmatter += `licence: >\n ${metadata.licence}\n`;
}
if (metadata.tags && metadata.tags.length > 0) {
frontmatter += 'tags:\n';
metadata.tags.forEach(tag => {
frontmatter += ` - ${tag}\n`;
});
}
// Default Astro configuration
frontmatter += 'tableOfContentsAutoCollapse: true\n';
frontmatter += '---\n\n';
return frontmatter;
}
/**
* Extract and generate frontmatter from LaTeX content
* @param {string} latexContent - Raw LaTeX content
* @returns {string} - Complete YAML frontmatter
*/
export function extractAndGenerateFrontmatter(latexContent) {
const metadata = extractLatexMetadata(latexContent);
return generateFrontmatter(metadata);
}
|