rxiv-maker 1.19.0__tar.gz → 1.19.1__tar.gz

{rxiv_maker-1.19.0 → rxiv_maker-1.19.1}/CHANGELOG.md

@@ -7,6 +7,23 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+## [1.19.1] - 2026-02-05
+
+### Fixed
+
+- **bioRxiv Character Encoding**: Enhanced HTML entity encoding to handle all Unicode characters
+  - Now uses numeric character references (e.g., `č` for č) for characters without named HTML entities
+  - Properly encodes Lithuanian characters (č, ū, ė) and other special characters
+  - Example: "Vaitkevičiūtė" → "Vaitkevičiūtė"
+  - Ensures bioRxiv TSV files handle international author names correctly
+
+- **LaTeX Section Spacing**: Fixed spacing issues in PDF output for section headers
+  - Added proper blank lines (`\n\n`) after all LaTeX section commands in markdown conversion
+  - Increased spacing after `\subsubsection` titles from 1pt to 8pt in LaTeX class file
+  - Changed subsubsection title format to use `\enskip` for consistent visual spacing
+  - Fixes runin format issue where text appeared to run directly into section titles
+  - Example fix: "Manuscripts.A central" → "Manuscripts. A central" (with visible space)
+
 ## [1.19.0] - 2026-02-05
 
 ### Added

{rxiv_maker-1.19.0 → rxiv_maker-1.19.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: rxiv-maker
-Version: 1.19.0
+Version: 1.19.1
 Summary: Write scientific preprints in Markdown. Generate publication-ready PDFs efficiently.
 Project-URL: Homepage, https://github.com/HenriquesLab/rxiv-maker
 Project-URL: Documentation, https://github.com/HenriquesLab/rxiv-maker#readme

{rxiv_maker-1.19.0 → rxiv_maker-1.19.1}/src/rxiv_maker/__version__.py

@@ -1,3 +1,3 @@
 """Version information."""
 
-__version__ = "1.19.0"
+__version__ = "1.19.1"

{rxiv_maker-1.19.0 → rxiv_maker-1.19.1}/src/rxiv_maker/converters/md2tex.py

@@ -185,7 +185,7 @@ def convert_markdown_to_latex(
 
     # Post-processing: catch any remaining unconverted headers
     # This is a safety net in case some headers weren't converted properly
-    content = re.sub(r"^### (.+)$", r"\\subsubsection{\1}", content, flags=re.MULTILINE)
+    content = re.sub(r"^### (.+)$", r"\\subsubsection{\1}\n\n", content, flags=re.MULTILINE)
 
     # Process supplementary note references BEFORE citations
     # (for both main and supplementary content)
@@ -457,26 +457,26 @@ def _process_tables_with_protection(
 
 
 def _convert_headers(content: LatexContent, is_supplementary: bool = False) -> LatexContent:
-    """Convert markdown headers to LaTeX sections."""
+    """Convert markdown headers to LaTeX sections with proper spacing."""
     if is_supplementary:
         # For supplementary content, use \\section* for the first header
         # to avoid "Note 1:" prefix
         # First, find the first # header and replace it with \section*
-        content = re.sub(r"^# (.+)$", r"\\section*{\1}", content, flags=re.MULTILINE, count=1)
+        content = re.sub(r"^# (.+)$", r"\\section*{\1}\n\n", content, flags=re.MULTILINE, count=1)
         # Then replace any remaining # headers with regular \section
-        content = re.sub(r"^# (.+)$", r"\\section{\1}", content, flags=re.MULTILINE)
+        content = re.sub(r"^# (.+)$", r"\\section{\1}\n\n", content, flags=re.MULTILINE)
     else:
-        content = re.sub(r"^# (.+)$", r"\\section{\1}", content, flags=re.MULTILINE)
+        content = re.sub(r"^# (.+)$", r"\\section{\1}\n\n", content, flags=re.MULTILINE)
 
-    content = re.sub(r"^## (.+)$", r"\\subsection{\1}", content, flags=re.MULTILINE)
+    content = re.sub(r"^## (.+)$", r"\\subsection{\1}\n\n", content, flags=re.MULTILINE)
 
     # For supplementary content, ### headers are handled by the
     # supplementary note processor
     # For non-supplementary content, convert all ### headers normally
     if not is_supplementary:
-        content = re.sub(r"^### (.+)$", r"\\subsubsection{\1}", content, flags=re.MULTILINE)
+        content = re.sub(r"^### (.+)$", r"\\subsubsection{\1}\n\n", content, flags=re.MULTILINE)
 
-    content = re.sub(r"^#### (.+)$", r"\\paragraph{\1}", content, flags=re.MULTILINE)
+    content = re.sub(r"^#### (.+)$", r"\\paragraph{\1}\n\n", content, flags=re.MULTILINE)
     return content
 
 

{rxiv_maker-1.19.0 → rxiv_maker-1.19.1}/src/rxiv_maker/engines/operations/prepare_biorxiv.py

@@ -23,13 +23,15 @@ def encode_html_entities(text: str) -> str:
 
     bioRxiv's TSV upload requires special characters to be encoded as HTML entities.
     For example, "António" becomes "António", "Åbo" becomes "Åbo".
+    Characters without named entities use numeric references (e.g., "č" -> "č").
 
     Args:
         text: Text that may contain Unicode characters
 
     Returns:
         Text with Unicode characters converted to HTML entities
-        (e.g., "António" -> "António", "Åbo" -> "Åbo")
+        (e.g., "António" -> "António", "Åbo" -> "Åbo",
+        "Vaitkevičiūtė" -> "Vaitkevičiūtė")
 
     Examples:
         >>> encode_html_entities("António")
@@ -38,6 +40,8 @@ def encode_html_entities(text: str) -> str:
         'Åbo'
         >>> encode_html_entities("José García")
         'José García'
+        >>> encode_html_entities("Vaitkevičiūtė")
+        'Vaitkevičiūtė'
     """
     if not text:
         return text
@@ -50,13 +54,19 @@ def encode_html_entities(text: str) -> str:
         if ord(char) > 127:
             char_to_entity[char] = f"&{entity_name};"
 
-    # Convert each character to HTML entity if it has one
+    # Convert each character to HTML entity (named or numeric)
     result = []
     for char in text:
-        if char in char_to_entity:
+        char_code = ord(char)
+        if char_code <= 127:
+            # Basic ASCII - keep as-is
+            result.append(char)
+        elif char in char_to_entity:
+            # Has named entity - use it
             result.append(char_to_entity[char])
         else:
-            result.append(char)
+            # No named entity - use numeric character reference
+            result.append(f"&#{char_code};")
 
     return "".join(result)
 

{rxiv_maker-1.19.0 → rxiv_maker-1.19.1}/src/tex/style/rxiv_maker_style.cls

@@ -418,7 +418,7 @@
   {\sffamily\small\bfseries\itshape}
   {\thesubsubsection.}
   {0.5em}
-  {#1. }
+  {#1.\enskip}
   []
 \titleformat{\paragraph}[runin]
   {\sffamily\small\bfseries}
@@ -427,7 +427,7 @@
   {#1}
 \titlespacing*{\section}{0pc}{1.5ex \@plus2pt \@minus1pt}{2pt}
 \titlespacing*{\subsection}{0pc}{1.2ex \@plus2pt \@minus1pt}{1pt}
-\titlespacing*{\subsubsection}{0pc}{1ex \@plus1pt \@minus0.5pt}{1pt}
+\titlespacing*{\subsubsection}{0pc}{1ex \@plus1pt \@minus0.5pt}{8pt}
 \titlespacing*{\paragraph}{0pc}{0.8ex \@plus1pt \@minus0.5pt}{8pt}
 
 %% Figure caption style

{rxiv_maker-1.19.0 → rxiv_maker-1.19.1}/tests/unit/test_prepare_biorxiv.py

@@ -329,6 +329,14 @@ class TestEncodeHtmlEntities:
         assert encode_html_entities("Åbo") == "Åbo"
         assert encode_html_entities("Øyvind") == "Øyvind"
 
+    def test_lithuanian_characters(self):
+        """Test encoding of Lithuanian characters using numeric character references."""
+        # Lithuanian characters don't have named HTML entities, so use numeric references
+        assert encode_html_entities("Vaitkevičiūtė") == "Vaitkevičiūtė"
+        assert encode_html_entities("č") == "č"  # c with caron
+        assert encode_html_entities("ū") == "ū"  # u with macron
+        assert encode_html_entities("ė") == "ė"  # e with dot above
+
     def test_complex_text(self):
         """Test encoding of text with multiple special characters."""
         text = "Instituto de Tecnologia Química e Biológica António Xavier"