rxiv-maker 1.17.0__py3-none-any.whl → 1.18.1__py3-none-any.whl

rxiv_maker/__version__.py

@@ -1,3 +1,3 @@
 """Version information."""
 
-__version__ = "1.17.0"
+__version__ = "1.18.1"

rxiv_maker/cli/framework/workflow_commands.py

@@ -30,8 +30,10 @@ class InitCommand(BaseCommand):
         self.engine = "local"  # Only local engine is supported
 
         # Store manuscript path without PathManager validation since we're creating the directory
+        # NOTE: For init command, we should NOT use environment variable MANUSCRIPT_PATH
+        # as it's meant for finding existing manuscripts, not determining where to initialize
         if manuscript_path is None:
-            manuscript_path = EnvironmentManager.get_manuscript_path() or "MANUSCRIPT"
+            manuscript_path = "MANUSCRIPT"
 
         # Store the raw path for use in execute_operation
         self.raw_manuscript_path = manuscript_path

rxiv_maker/exporters/docx_citation_mapper.py

@@ -8,6 +8,7 @@ import re
 from typing import Dict, List
 
 from ..converters.citation_processor import extract_citations_from_text
+from ..utils.citation_range_formatter import format_citation_ranges
 
 
 class CitationMapper:
@@ -17,97 +18,15 @@ class CitationMapper:
     def _format_citation_ranges(text: str) -> str:
         """Format consecutive citations as ranges.
 
-        Converts patterns like [1][2][3] to [1-3], [15][16] to [15-16], etc.
-        Also formats comma-separated lists like [1, 2, 3] to [1-3].
+        Uses centralized citation range formatter from utils module.
 
         Args:
             text: Text with numbered citations
 
         Returns:
             Text with consecutive citations formatted as ranges
-
-        Example:
-            >>> CitationMapper._format_citation_ranges("text [1][2][3] more")
-            'text [1-3] more'
-            >>> CitationMapper._format_citation_ranges("text [1, 2, 3] more")
-            'text [1-3] more'
-            >>> CitationMapper._format_citation_ranges("text [1][3][4] more")
-            'text [1][3-4] more'
-        """
-
-        # Pattern 1: Handle adjacent bracketed citations [1][2][3] or [1] [2] [3]
-        def combine_adjacent(match_obj):
-            # Extract all numbers from consecutive brackets (allowing spaces between)
-            numbers = [int(n) for n in re.findall(r"\[(\d+)\]", match_obj.group(0))]
-            return CitationMapper._format_number_list(numbers)
-
-        # Find sequences of adjacent bracketed numbers (with optional spaces between)
-        text = re.sub(r"(?:\[\d+\]\s*){2,}", combine_adjacent, text)
-
-        # Pattern 2: Handle comma-separated citations within single brackets [1, 2, 3]
-        def combine_comma_separated(match_obj):
-            # Extract all numbers from comma-separated list
-            numbers_str = match_obj.group(1)
-            numbers = [int(n.strip()) for n in numbers_str.split(",")]
-            return CitationMapper._format_number_list(numbers)
-
-        text = re.sub(r"\[([\d,\s]+)\]", combine_comma_separated, text)
-
-        return text
-
-    @staticmethod
-    def _format_number_list(numbers: List[int]) -> str:
-        """Format a list of citation numbers as ranges.
-
-        Args:
-            numbers: List of citation numbers
-
-        Returns:
-            Formatted string with ranges
-
-        Example:
-            >>> CitationMapper._format_number_list([1, 2, 3, 5, 6, 8])
-            '[1-3, 5-6, 8]'
-            >>> CitationMapper._format_number_list([15, 16])
-            '[15-16]'
-            >>> CitationMapper._format_number_list([1, 3, 5])
-            '[1, 3, 5]'
         """
-        if not numbers:
-            return "[]"
-
-        # Sort numbers
-        sorted_nums = sorted(set(numbers))
-
-        # Build ranges
-        ranges = []
-        start = sorted_nums[0]
-        end = sorted_nums[0]
-
-        for num in sorted_nums[1:]:
-            if num == end + 1:
-                # Continue current range
-                end = num
-            else:
-                # End current range and start new one
-                if start == end:
-                    # Single number
-                    ranges.append(str(start))
-                else:
-                    # Range (including 2 consecutive numbers like 15-16)
-                    ranges.append(f"{start}-{end}")
-                start = num
-                end = num
-
-        # Add final range
-        if start == end:
-            # Single number
-            ranges.append(str(start))
-        else:
-            # Range (including 2 consecutive numbers like 15-16)
-            ranges.append(f"{start}-{end}")
-
-        return f"[{', '.join(ranges)}]"
+        return format_citation_ranges(text)
 
     def create_mapping(self, citations: List[str]) -> Dict[str, int]:
         """Create citation key → number mapping.

rxiv_maker/exporters/docx_content_processor.py

@@ -7,30 +7,12 @@ DOCX generation with python-docx.
 import re
 from typing import Any, Dict, List, Optional
 
+from ..utils.comment_filter import is_metadata_comment
+
 
 class DocxContentProcessor:
     """Parses markdown content into structured format for DOCX writing."""
 
-    @staticmethod
-    def _is_metadata_comment(comment_text: str) -> bool:
-        """Check if a comment is metadata/informational and should be skipped.
-
-        Args:
-            comment_text: The comment text to check
-
-        Returns:
-            True if comment should be skipped, False if it should be included
-        """
-        if not comment_text:
-            return True
-
-        # Normalize to lowercase for case-insensitive matching
-        normalized = comment_text.lower().strip()
-
-        # Skip comments that start with common metadata keywords
-        metadata_prefixes = ["note:", "note ", "comment:", "comment "]
-        return any(normalized.startswith(prefix) for prefix in metadata_prefixes)
-
     def parse(self, markdown: str, citation_map: Dict[str, int]) -> Dict[str, Any]:
         """Parse markdown into structured sections for DOCX.
 
@@ -83,7 +65,7 @@ class DocxContentProcessor:
                     # Single-line comment
                     comment_text = line.strip()[4:-3].strip()
                     # Skip metadata comments (e.g., "note that...", "Comment: ...")
-                    if comment_text and not self._is_metadata_comment(comment_text):
+                    if comment_text and not is_metadata_comment(comment_text):
                         sections.append({"type": "comment", "text": comment_text})
                     i += 1
                     continue
@@ -104,7 +86,7 @@ class DocxContentProcessor:
                     # Join and add comment
                     comment_text = " ".join(comment_lines).strip()
                     # Skip metadata comments (e.g., "note that...", "Comment: ...")
-                    if comment_text and not self._is_metadata_comment(comment_text):
+                    if comment_text and not is_metadata_comment(comment_text):
                         sections.append({"type": "comment", "text": comment_text})
                     continue
 
@@ -445,7 +427,7 @@ class DocxContentProcessor:
             elif match.group(6):  # Inline HTML comment
                 comment_text = match.group(7).strip()
                 # Skip metadata comments (e.g., "note that...", "Comment: ...")
-                if comment_text and not self._is_metadata_comment(comment_text):
+                if comment_text and not is_metadata_comment(comment_text):
                     runs.append({"type": "inline_comment", "text": comment_text})
             elif match.group(8):  # Markdown link [text](url)
                 runs.append(

rxiv_maker/exporters/docx_exporter.py

@@ -54,6 +54,8 @@ class DocxExporter:
         docx_config = config.get("docx", {})
         self.hide_si = docx_config.get("hide_si", False)  # Default to False (don't hide SI) for backwards compatibility
         self.figures_at_end = docx_config.get("figures_at_end", False)  # Default to False (inline figures)
+        self.hide_highlighting = docx_config.get("hide_highlighting", False)  # Default to False (show highlights)
+        self.hide_comments = docx_config.get("hide_comments", False)  # Default to False (include comments)
 
         # Components
         self.citation_mapper = CitationMapper()
@@ -125,10 +127,13 @@ class DocxExporter:
         # Step 5.5: Replace figure and equation references with numbers
         import re
 
+        # Extract all labels using centralized utility
+        from ..utils.label_extractor import LabelExtractor
+
+        label_extractor = LabelExtractor()
+
         # Find all figures and create mapping
-        # Allow hyphens and underscores in label names
-        figure_labels = re.findall(r"!\[[^\]]*\]\([^)]+\)\s*\n\s*\{#fig:([\w-]+)", markdown_with_numbers)
-        figure_map = {label: i + 1 for i, label in enumerate(figure_labels)}
+        figure_map = label_extractor.extract_figure_labels(markdown_with_numbers)
 
         # Replace @fig:label with "Fig. X" in text, handling optional panel letters
         # Pattern matches: @fig:label optionally followed by space and panel letter(s)
@@ -146,11 +151,9 @@ class DocxExporter:
         logger.debug(f"Mapped {len(figure_map)} figure labels to numbers")
 
         # Find all supplementary figures and create mapping
-        # Allow hyphens and underscores in label names
         # IMPORTANT: When SI is excluded, extract from SI content (where figures are defined)
         content_to_scan_for_sfigs = si_content_for_mapping if si_content_for_mapping else markdown_with_numbers
-        sfig_labels = re.findall(r"!\[[^\]]*\]\([^)]+\)\s*\n\s*\{#sfig:([\w-]+)", content_to_scan_for_sfigs)
-        sfig_map = {label: i + 1 for i, label in enumerate(sfig_labels)}
+        sfig_map = label_extractor.extract_supplementary_figure_labels(content_to_scan_for_sfigs)
 
         # Replace @sfig:label with "Supp. Fig. X" in text, handling optional panel letters
         for label, num in sfig_map.items():
@@ -166,24 +169,9 @@ class DocxExporter:
 
         # Find all tables and create mapping (looking for {#stable:label} or \label{stable:label} tags)
         # IMPORTANT: PDF uses the order that tables are DEFINED in the document (order of \label{stable:X})
-        # NOT the order of caption references (%{#stable:X}) which are just metadata
         # When SI is excluded from export, we still need to extract labels from SI
-
         content_to_scan_for_tables = si_content_for_mapping if si_content_for_mapping else markdown_with_numbers
-
-        # Extract table labels in document order (both {#stable:label} markdown format and \label{stable:label} LaTeX format)
-        # The PDF numbering follows the order these labels appear in the document
-        markdown_labels = re.findall(r"\{#stable:([\w-]+)\}", content_to_scan_for_tables)
-        latex_labels = re.findall(r"\\label\{stable:([\w-]+)\}", content_to_scan_for_tables)
-
-        # Combine both formats, preferring LaTeX labels if present (since that's what PDF uses)
-        table_labels = latex_labels if latex_labels else markdown_labels
-
-        # Remove duplicates while preserving order
-        seen = set()
-        table_labels = [label for label in table_labels if not (label in seen or seen.add(label))]
-
-        table_map = {label: i + 1 for i, label in enumerate(table_labels)}
+        table_map = label_extractor.extract_supplementary_table_labels(content_to_scan_for_tables)
         logger.debug(f"Mapped {len(table_map)} supplementary tables: {table_map}")
 
         # Replace @stable:label with "Supp. Table X" in text
@@ -193,11 +181,9 @@ class DocxExporter:
             )
 
         # Find all supplementary notes and create mapping (looking for {#snote:label} tags)
-        # Allow hyphens and underscores in label names
         # IMPORTANT: When SI is excluded, extract from SI content (where notes are defined)
         content_to_scan_for_snotes = si_content_for_mapping if si_content_for_mapping else markdown_with_numbers
-        snote_labels = re.findall(r"\{#snote:([\w-]+)\}", content_to_scan_for_snotes)
-        snote_map = {label: i + 1 for i, label in enumerate(snote_labels)}
+        snote_map = label_extractor.extract_supplementary_note_labels(content_to_scan_for_snotes)
 
         # Replace @snote:label with "Supp. Note X" in text
         for label, num in snote_map.items():
@@ -208,9 +194,7 @@ class DocxExporter:
         logger.debug(f"Mapped {len(snote_map)} supplementary note labels to numbers")
 
         # Find all equations and create mapping (looking for {#eq:label} tags)
-        # Allow hyphens and underscores in label names
-        equation_labels = re.findall(r"\{#eq:([\w-]+)\}", markdown_with_numbers)
-        equation_map = {label: i + 1 for i, label in enumerate(equation_labels)}
+        equation_map = label_extractor.extract_equation_labels(markdown_with_numbers)
 
         # Replace @eq:label with "Eq. X"
         # Handle both @eq:label and (@eq:label) formats
@@ -247,6 +231,8 @@ class DocxExporter:
             metadata=metadata,
             table_map=table_map,
             figures_at_end=self.figures_at_end,
+            hide_highlighting=self.hide_highlighting,
+            hide_comments=self.hide_comments,
         )
         logger.info(f"DOCX exported successfully: {docx_path}")