Translate all French text to English in scripts

- generate_citations_page.py: Translate comments, docstrings, and messages
- generate_citations_page.sh: Translate comments and output messages
- scholar_citations.py: Add helpful comments (kept intentional French strings for Google Scholar parsing)
- github_contributors.py: Translate docstrings, comments, and messages
- scripts/contributors/README.md: Translate documentation
- generate_contributors_page.sh: Translate comments and output messages
- about/citations.md: Regenerated with deduplication
- about/contributors.md: Regenerated with updated data

Author: ocots

about/citations.md

@@ -11,13 +11,13 @@ permalink: /citations/
 <div class="citations-header">
 <h1>📚 Citations</h1>
 <p class="subtitle">Academic papers citing OptimalControl.jl and related control-toolbox projects</p>
-<p class="last-update">Last updated: April 12, 2026 at 11:42 UTC</p>
+<p class="last-update">Last updated: April 14, 2026 at 14:22 UTC</p>
 </div>
 
 <div class="summary-cards">
 <div class="summary-card card-citations">
 <div class="card-label">Total Citations</div>
-<div class="card-value">9</div>
+<div class="card-value">8</div>
 </div>
 </div>
 
@@ -57,6 +57,7 @@ permalink: /citations/
 <h3 class="citation-title"><a href="https://arxiv.org/abs/2510.03932" target="_blank">6. Modeling and optimization of control problems on GPUs</a></h3>
 <p class="citation-authors">A Montoison, JB Caillau - arXiv preprint arXiv:2510.03932, 2025 - arxiv.org</p>
 <p class="citation-snippet">We present a fully Julia-based, GPU-accelerated workflow for solving large-scale sparsenonlinear optimal control problems. Continuous-time dynamics are modeled and then …</p>
+<p class="citation-alt"><a href="https://hal.science/hal-05295809/" target="_blank">Version 2</a> — JB Caillau, A Montoison - 2025 - hal.science</p>
 </div>
 <div class="citation-item">
 <h3 class="citation-title"><a href="https://ieeexplore.ieee.org/abstract/document/11312971/" target="_blank">7. Pulse control of affine systems with applications to quantum control</a></h3>
@@ -68,11 +69,6 @@ permalink: /citations/
 <p class="citation-authors">JI Imizcoz, AG Yabo, W Djema, F Mairet, JL Gouzé - 2025 - inria.hal.science</p>
 <p class="citation-snippet">Resource allocation models are a highly useful tool to study microbial growth in a variety ofcontexts. We use here a model of this kind describing the metabolism of a micro-organism …</p>
 </div>
-<div class="citation-item">
-<h3 class="citation-title"><a href="https://hal.science/hal-05295809/" target="_blank">9. Modeling and Optimization of Control Problems on GPUs</a></h3>
-<p class="citation-authors">JB Caillau, A Montoison - 2025 - hal.science</p>
-<p class="citation-snippet">We present a fully Julia-based, GPUaccelerated workflow for solving large-scale sparsenonlinear optimal control problems. Continuous-time dynamics are modeled and then …</p>
-</div>
 </div>
 </div>
 

about/contributors.md

@@ -1,6 +1,6 @@
 #!/usr/bin/env python3
 """
-Script pour générer une page de citations depuis Google Scholar
+Script to generate a citations page from Google Scholar
 """
 
 import argparse
@@ -29,6 +29,59 @@ def extract_year(citation: Dict) -> int:
     return 0
 
 
+def normalize_title(title: str) -> str:
+    """
+    Normalize a citation title for duplicate detection.
+    Lowercase, keep only alphanumeric characters.
+    """
+    return re.sub(r'[^a-z0-9]', '', title.lower())
+
+
+def extract_author_lastnames(authors_pub: str) -> frozenset:
+    """
+    Extract a frozenset of lowercase last names from an authors_pub string.
+    Splits on the first ' - ' to isolate the author list, then takes the
+    last word of each comma-separated token as the last name.
+    """
+    author_part = authors_pub.split(' - ')[0] if ' - ' in authors_pub else authors_pub
+    lastnames = set()
+    for token in author_part.split(','):
+        token = token.strip().rstrip('\u2026').strip()
+        if token:
+            last = token.split()[-1].lower()
+            last = re.sub(r'[^a-z]', '', last)
+            if last:
+                lastnames.add(last)
+    return frozenset(lastnames)
+
+
+def deduplicate_citations(citations: List[Dict]) -> List[Dict]:
+    """
+    Remove duplicate citations, keeping the first occurrence and storing
+    alternative URLs in an 'alt_urls' list on the primary citation.
+    Two citations are considered identical when their normalized titles
+    and author lastname frozensets are both equal.
+    """
+    seen: dict = {}
+    result: List[Dict] = []
+    for citation in citations:
+        title_key = normalize_title(citation.get('title', ''))
+        authors_key = extract_author_lastnames(citation.get('authors_pub', ''))
+        key = (title_key, authors_key)
+        if key not in seen:
+            citation = dict(citation)
+            citation.setdefault('alt_urls', [])
+            seen[key] = len(result)
+            result.append(citation)
+        else:
+            alt = {
+                'url': citation.get('url', ''),
+                'authors_pub': citation.get('authors_pub', ''),
+            }
+            result[seen[key]]['alt_urls'].append(alt)
+    return result
+
+
 def sort_citations_by_year(citations: List[Dict]) -> List[Dict]:
     """
     Sort citations by year (most recent first)
@@ -45,15 +98,15 @@ def sort_citations_by_year(citations: List[Dict]) -> List[Dict]:
 def generate_web_page(citations: List[Dict], scholar_url: str, 
                      output_file: str = "about/citations.md"):
     """
-    Génère une page web Markdown avec front matter Jekyll pour le site control-toolbox
+    Generate a Markdown web page with Jekyll front matter for the control-toolbox site.
     
     Args:
-        citations: Liste des citations
-        scholar_url: URL Google Scholar utilisée
-        output_file: Nom du fichier de sortie
+        citations: List of citations
+        scholar_url: Google Scholar URL used
+        output_file: Output file name
     """
     if not citations:
-        print("❌ Impossible de générer la page web : aucune citation trouvée.")
+        print("❌ Cannot generate the web page: no citations found.")
         return
 
     with open(output_file, 'w', encoding='utf-8') as f:
@@ -64,33 +117,33 @@ def generate_web_page(citations: List[Dict], scholar_url: str,
         f.write("permalink: /citations/\n")
         f.write("---\n\n")
 
-        # Lien CSS personnalisé
+        # Custom CSS link
         f.write('<link rel="stylesheet" href="/assets/css/citations.css">\n\n')
 
-        # Conteneur principal
+        # Main container
         f.write('<div class="citations-page">\n\n')
 
-        # En-tête
+        # Header
         f.write('<div class="citations-header">\n')
         f.write('<h1>📚 Citations</h1>\n')
         f.write('<p class="subtitle">Academic papers citing OptimalControl.jl and related control-toolbox projects</p>\n')
         f.write(f'<p class="last-update">Last updated: {datetime.now().strftime("%B %d, %Y at %H:%M UTC")}</p>\n')
         f.write('</div>\n\n')
 
-        # Carte de résumé
+        # Summary cards
         f.write('<div class="summary-cards">\n')
         f.write('<div class="summary-card card-citations">\n')
         f.write('<div class="card-label">Total Citations</div>\n')
         f.write(f'<div class="card-value">{len(citations)}</div>\n')
         f.write('</div>\n')
         f.write('</div>\n\n')
 
-        # Note d'information
+        # Info note
         f.write('<div class="info-box">\n')
         f.write('<p><strong>Note:</strong> This page lists academic papers that cite OptimalControl.jl and related control-toolbox projects. Data is automatically retrieved from Google Scholar.</p>\n')
         f.write('</div>\n\n')
 
-        # Liste des citations
+        # Citations list
         f.write('<div class="citations-section">\n')
         f.write('<h2>📖 Citations</h2>\n')
         f.write('<div class="citations-list">\n')
@@ -116,32 +169,42 @@ def generate_web_page(citations: List[Dict], scholar_url: str,
             if snippet:
                 f.write(f'<p class="citation-snippet">{snippet}</p>\n')
 
+            # Alternate versions (duplicates merged)
+            for j, alt in enumerate(citation.get('alt_urls', []), 2):
+                alt_url = alt.get('url', '')
+                alt_authors = alt.get('authors_pub', '')
+                if alt_url:
+                    f.write(f'<p class="citation-alt"><a href="{alt_url}" target="_blank">Version {j}</a>')
+                    if alt_authors:
+                        f.write(f' — {alt_authors}')
+                    f.write('</p>\n')
+            
             f.write('</div>\n')
 
         f.write('</div>\n')
         f.write('</div>\n\n')
 
-        # Pied de page
+        # Footer
         f.write('<hr>\n')
         f.write('<p style="text-align: center; color: #6a737d; font-size: 0.9rem;">\n')
         f.write('<em>🤖 This page is automatically generated from Google Scholar and updated weekly.</em>\n')
         f.write('</p>\n\n')
 
-        # Fermer le conteneur
+        # Close container
         f.write('</div>\n')
 
-    print(f"\n✅ Page web générée : {output_file}")
+    print(f"\n✅ Web page generated: {output_file}")
     return output_file
 
 
 def main():
-    """Fonction principale"""
+    """Main function"""
 
     parser = argparse.ArgumentParser(
-        description="Génère une page de citations depuis Google Scholar",
+        description="Generate a citations page from Google Scholar",
         formatter_class=argparse.RawDescriptionHelpFormatter,
         epilog="""
-Exemples d'utilisation:
+Usage examples:
   python generate_citations_page.py
   python generate_citations_page.py --url "https://scholar.google.com/scholar?cites=PAPER_ID"
   python generate_citations_page.py --max-pages 10
@@ -151,58 +214,67 @@ def main():
     parser.add_argument(
         '--url',
         type=str,
-        help='URL Google Scholar pour les citations (défaut: OptimalControl.jl)'
+        help='Google Scholar URL for citations (default: OptimalControl.jl)'
     )
 
     parser.add_argument(
         '--max-pages',
         type=int,
         default=5,
-        help='Nombre maximum de pages à récupérer (défaut: 5)'
+        help='Maximum number of pages to fetch (default: 5)'
     )
 
     parser.add_argument(
         '--output',
         type=str,
         default='about/citations.md',
-        help='Nom du fichier de sortie (défaut: about/citations.md)'
+        help='Output file name (default: about/citations.md)'
     )
 
     args = parser.parse_args()
 
-    # URL par défaut pour OptimalControl.jl
+    # Default URL for OptimalControl.jl
     if args.url:
         scholar_url = args.url
     else:
         scholar_url = "https://scholar.google.com/scholar?cites=1899455738170204200"
 
     print("\n" + "="*70)
-    print("🔍 RÉCUPÉRATION DES CITATIONS")
+    print("🔍 FETCHING CITATIONS")
     print("="*70)
-    print(f"URL Google Scholar : {scholar_url}")
-    print(f"Pages maximum : {args.max_pages}")
+    print(f"Google Scholar URL: {scholar_url}")
+    print(f"Maximum pages: {args.max_pages}")
     print("="*70 + "\n")
 
-    # Récupération des citations
+    # Fetch citations
     scraper = ScholarCitationScraper(scholar_url)
     citations = scraper.get_citations(max_pages=args.max_pages)
 
-    print(f"\nTotal citations récupérées : {len(citations)}")
+    print(f"\nTotal citations retrieved: {len(citations)}")
 
     if not citations:
-        print("❌ Aucune citation trouvée.")
+        print("❌ No citations found.")
         return
 
-    # Trier par année (plus récent en premier)
+    # Sort by year (most recent first)
     citations = sort_citations_by_year(citations)
-    print("✅ Citations triées par année (plus récent en premier)")
+    print("✅ Citations sorted by year (most recent first)")
+    
+    # Remove duplicates
+    citations_before = len(citations)
+    citations = deduplicate_citations(citations)
+    removed = citations_before - len(citations)
+    if removed:
+        print(f"✅ {removed} duplicate(s) removed ({len(citations)} unique citations)")
+    else:
+        print("✅ No duplicates detected")
 
-    # Obtenir le répertoire racine du projet (2 niveaux au-dessus du script)
+    # Get project root directory (2 levels above the script)
     script_dir = os.path.dirname(os.path.abspath(__file__))
     project_root = os.path.dirname(os.path.dirname(script_dir))
     web_output = os.path.join(project_root, args.output)
 
-    # Génération de la page web
+    # Generate the web page
     generate_web_page(citations, scholar_url, web_output)