Update validation script and tests for new structured format

- Remove citation column requirement from validation (now built from fields)
- Allow local file paths (data/pdfs/...) as valid URLs
- Update tests to use new structured field format instead of citation/links_html

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

Author: jeremymanning

scripts/validate_data.py

@@ -19,6 +19,9 @@ def validate_publications(project_root: Path) -> List[str]:
     """Validate publications.xlsx data.
 
     Returns list of error messages (empty if valid).
+
+    Note: Citations are now built from structured fields (authors, year, title, etc.)
+    rather than a single 'citation' column. Only 'title' is required.
     """
     errors = []
     xlsx_path = project_root / 'data' / 'publications.xlsx'
@@ -33,7 +36,8 @@ def validate_publications(project_root: Path) -> List[str]:
         errors.append(f"Error loading {xlsx_path}: {e}")
         return errors
 
-    required_fields = ['title', 'citation']
+    # Only title is required - citations are built from structured fields
+    required_fields = ['title']
     image_dir = project_root / 'images' / 'publications'
 
     for sheet_name, items in data.items():
@@ -44,9 +48,10 @@ def validate_publications(project_root: Path) -> List[str]:
                 if not val or (isinstance(val, str) and not val.strip()):
                     errors.append(f"publications/{sheet_name} row {i}: missing {field}")
 
-            # Check URL format (validate_url_format returns True if valid)
+            # Check URL format - allow local file paths (data/pdfs/...) which get
+            # converted to GitHub URLs by the build script
             url = item.get('title_url', '')
-            if url and not validate_url_format(url):
+            if url and not validate_url_format(url) and not url.startswith('data/'):
                 errors.append(f"publications/{sheet_name} row {i}: invalid URL '{url}'")
 
             # Check image file exists (check_file_exists returns error msg or None)

tests/test_build_people.py

@@ -95,7 +95,7 @@ def test_generates_director_with_links(self):
             'name_url': '',
             'role': 'lab director',
             'bio': 'Bio paragraph here.',
-            'links_html': '[<a href="#">CV</a>]'
+            'links_html': 'CV:http://example.com/cv'
         }
 
         html = generate_director_content(director)
@@ -105,7 +105,8 @@ def test_generates_director_with_links(self):
         assert 'jeremy manning' in html
         assert 'lab director' in html
         assert 'Bio paragraph here.' in html
-        assert '[<a href="#">CV</a>]' in html
+        assert 'CV' in html
+        assert 'http://example.com/cv' in html
 
     def test_handles_no_links(self):
         """Test director without links."""

tests/test_build_publications.py

@@ -90,30 +90,33 @@ def test_generates_basic_card(self):
             'image': 'test.png',
             'title': 'Test Paper',
             'title_url': 'http://example.com',
-            'citation': 'Author (2024) Test Paper',
-            'links_html': '[<a href="#">PDF</a>]'
+            'authors': 'Author A',
+            'year': '2024',
+            'journal': 'Journal',
+            'pdf_link': 'http://example.com/pdf'
         }
 
-        html = generate_publication_card(pub)
+        html = generate_publication_card(pub, 'papers')
 
         assert '<div class="publication-card">' in html
         assert 'images/publications/test.png' in html
         assert 'Test Paper' in html
         assert 'http://example.com' in html
-        assert 'Author (2024) Test Paper' in html
-        assert '[<a href="#">PDF</a>]' in html
+        assert 'Author A' in html
+        assert '2024' in html
 
     def test_handles_no_url(self):
         """Test card with no title URL."""
         pub = {
             'image': 'test.png',
             'title': 'Test Paper',
             'title_url': '',
-            'citation': 'Citation',
-            'links_html': ''
+            'authors': 'Author',
+            'year': '2024',
+            'journal': 'Journal'
         }
 
-        html = generate_publication_card(pub)
+        html = generate_publication_card(pub, 'papers')
 
         assert '<h4>Test Paper</h4>' in html
         assert 'href=' not in html.split('<h4>')[1].split('</h4>')[0]
@@ -124,25 +127,30 @@ def test_handles_no_links(self):
             'image': 'test.png',
             'title': 'Test Paper',
             'title_url': '',
-            'citation': 'Citation',
-            'links_html': ''
+            'authors': 'Author',
+            'year': '2024',
+            'journal': 'Journal'
         }
 
-        html = generate_publication_card(pub)
+        html = generate_publication_card(pub, 'papers')
 
         assert 'publication-links' not in html
 
-    def test_preserves_html_in_citation(self):
-        """Test that HTML in citation is preserved."""
+    def test_generates_citation_with_journal(self):
+        """Test that citation includes journal in italics."""
         pub = {
             'image': 'test.png',
             'title': 'Test',
             'title_url': '',
-            'citation': 'Author (2024) <em>Journal Name</em>, 1(1): 1-10.',
-            'links_html': ''
+            'authors': 'Author',
+            'year': '2024',
+            'journal': 'Journal Name',
+            'volume': '1',
+            'issue': '1',
+            'pages': '1-10'
         }
 
-        html = generate_publication_card(pub)
+        html = generate_publication_card(pub, 'papers')
 
         assert '<em>Journal Name</em>' in html
 
@@ -153,19 +161,19 @@ class TestGenerateSectionContent:
     def test_generates_multiple_cards(self):
         """Test generating content with multiple publications."""
         pubs = [
-            {'image': 'a.png', 'title': 'Paper A', 'title_url': '', 'citation': 'A', 'links_html': ''},
-            {'image': 'b.png', 'title': 'Paper B', 'title_url': '', 'citation': 'B', 'links_html': ''},
+            {'image': 'a.png', 'title': 'Paper A', 'title_url': '', 'authors': 'A', 'year': '2024', 'journal': 'J'},
+            {'image': 'b.png', 'title': 'Paper B', 'title_url': '', 'authors': 'B', 'year': '2024', 'journal': 'J'},
         ]
 
-        html = generate_section_content(pubs)
+        html = generate_section_content(pubs, 'papers')
 
         assert html.count('publication-card') == 2
         assert 'Paper A' in html
         assert 'Paper B' in html
 
     def test_handles_empty_list(self):
         """Test generating content with no publications."""
-        html = generate_section_content([])
+        html = generate_section_content([], 'papers')
 
         assert html == ''
 
@@ -188,11 +196,20 @@ def test_builds_complete_page(self, temp_dir):
 
         for sheet_name in ['papers', 'chapters', 'dissertations', 'talks', 'courses', 'posters']:
             ws = wb.create_sheet(title=sheet_name)
-            ws.append(['image', 'title', 'title_url', 'citation', 'links_html'])
             if sheet_name == 'papers':
+                ws.append(['image', 'title', 'title_url', 'authors', 'year', 'journal', 'volume', 'pages'])
                 ws.append(['paper.png', 'Test Paper', 'http://example.com',
-                          'Author (2024) Test Paper. <em>Journal</em>.',
-                          '[<a href="#">PDF</a>]'])
+                          'Author A', '2024', 'Journal Name', '1', '1-10'])
+            elif sheet_name == 'chapters':
+                ws.append(['image', 'title', 'title_url', 'authors', 'year', 'editors', 'book_title', 'publisher'])
+            elif sheet_name == 'dissertations':
+                ws.append(['image', 'title', 'title_url', 'authors', 'year', 'degree_type', 'institution', 'location'])
+            elif sheet_name == 'talks':
+                ws.append(['image', 'title', 'title_url', 'authors', 'year', 'venue_name'])
+            elif sheet_name == 'courses':
+                ws.append(['image', 'title', 'title_url', 'description'])
+            elif sheet_name == 'posters':
+                ws.append(['image', 'title', 'title_url', 'authors', 'year', 'conference', 'location'])
 
         wb.save(xlsx_path)
 
@@ -218,7 +235,7 @@ def test_builds_complete_page(self, temp_dir):
         result = output_path.read_text()
         assert 'Test Paper' in result
         assert 'paper.png' in result
-        assert '<em>Journal</em>' in result
+        assert '<em>Journal Name</em>' in result
 
     def test_handles_special_characters(self, temp_dir):
         """Test that special characters are preserved."""
@@ -228,10 +245,20 @@ def test_handles_special_characters(self, temp_dir):
 
         for sheet_name in ['papers', 'chapters', 'dissertations', 'talks', 'courses', 'posters']:
             ws = wb.create_sheet(title=sheet_name)
-            ws.append(['image', 'title', 'title_url', 'citation', 'links_html'])
             if sheet_name == 'papers':
+                ws.append(['image', 'title', 'title_url', 'authors', 'year', 'journal'])
                 ws.append(['test.png', "Paper & O'Brien's \"quoted\"", '',
-                          "Author & O'Brien (2024)", ''])
+                          "Author & O'Brien", '2024', 'Journal'])
+            elif sheet_name == 'chapters':
+                ws.append(['image', 'title', 'title_url', 'authors', 'year', 'editors', 'book_title', 'publisher'])
+            elif sheet_name == 'dissertations':
+                ws.append(['image', 'title', 'title_url', 'authors', 'year', 'degree_type', 'institution', 'location'])
+            elif sheet_name == 'talks':
+                ws.append(['image', 'title', 'title_url', 'authors', 'year', 'venue_name'])
+            elif sheet_name == 'courses':
+                ws.append(['image', 'title', 'title_url', 'description'])
+            elif sheet_name == 'posters':
+                ws.append(['image', 'title', 'title_url', 'authors', 'year', 'conference', 'location'])
 
         wb.save(xlsx_path)
 

tests/test_build_software.py

@@ -85,7 +85,7 @@ def test_generates_complete_item(self):
         item = {
             'name': 'MyTool',
             'description': 'Does something useful.',
-            'links_html': '[<a href="#">GitHub</a>]'
+            'github_link': 'https://github.com/example/mytool'
         }
 
         html = generate_software_item(item)
@@ -94,7 +94,8 @@ def test_generates_complete_item(self):
         assert '</p>' in html
         assert '<strong>MyTool.</strong>' in html
         assert 'Does something useful.' in html
-        assert '[<a href="#">GitHub</a>]' in html
+        assert 'GitHub' in html
+        assert 'https://github.com/example/mytool' in html
 
     def test_handles_missing_links(self):
         """Test item without links."""