epub2text 0.2.2__tar.gz → 0.2.3__tar.gz

epub2text-0.2.3/.codecrate.toml

@@ -0,0 +1,10 @@
+[codecrate]
+output = "context_epub2text.md"
+keep_docstrings = true
+dedupe = true
+metadata = false
+respect_gitignore = true
+exclude = ["examples", "*/.venv/*"]
+include = ["**/*.py", "**/*.toml", "**/*.rst", "**/*.md"]
+split_max_chars = 0
+layout = "full"

{epub2text-0.2.2 → epub2text-0.2.3}/.gitignore

@@ -206,3 +206,4 @@ marimo/_static/
 marimo/_lsp/
 __marimo__/
 epub2text/_version.py
+context_epub2text.md

{epub2text-0.2.2 → epub2text-0.2.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: epub2text
-Version: 0.2.2
+Version: 0.2.3
 Summary: A simple tool to extract text from EPUB files.
 Author-email: Holger Nahrstaedt <nahrstaedt@gmail.com>
 License: MIT License
@@ -45,10 +45,9 @@ Requires-Dist: rich>=13.0.0
 Requires-Dist: ebooklib>=0.18
 Requires-Dist: beautifulsoup4>=4.12.0
 Requires-Dist: defusedxml>=0.7.1
+Requires-Dist: phrasplit>=0.3.2
 Provides-Extra: lxml
 Requires-Dist: lxml>=4.9.0; extra == "lxml"
-Provides-Extra: sentences
-Requires-Dist: phrasplit>=0.1.0; extra == "sentences"
 Provides-Extra: dev
 Requires-Dist: pytest>=7.0.0; extra == "dev"
 Requires-Dist: ruff>=0.1.0; extra == "dev"

{epub2text-0.2.2 → epub2text-0.2.3}/docs/installation.rst

@@ -31,10 +31,6 @@ For better HTML parsing performance::
 
     pip install epub2text[lxml]
 
-For sentence-level formatting (requires phrasplit/spaCy)::
-
-    pip install epub2text[sentences]
-
 After installing, download a spaCy language model::
 
     python -m spacy download en_core_web_sm

{epub2text-0.2.2 → epub2text-0.2.3}/epub2text/_version.py

@@ -28,7 +28,7 @@ version_tuple: VERSION_TUPLE
 commit_id: COMMIT_ID
 __commit_id__: COMMIT_ID
 
-__version__ = version = '0.2.2'
-__version_tuple__ = version_tuple = (0, 2, 2)
+__version__ = version = '0.2.3'
+__version_tuple__ = version_tuple = (0, 2, 3)
 
-__commit_id__ = commit_id = 'ga27a7539e'
+__commit_id__ = commit_id = 'g82e1d316b'

{epub2text-0.2.2 → epub2text-0.2.3}/epub2text/cleaner.py

@@ -147,8 +147,6 @@ class TextCleaner:
     def apply_gutenberg_spacing(self, text: str) -> str:
         """Apply Gutenberg Project formatting: two spaces after sentences and colons.
 
-        Uses phrasplit for accurate sentence boundary detection.
-
         Args:
             text: Text to format
 

{epub2text-0.2.2 → epub2text-0.2.3}/epub2text/formatters.py

@@ -1,70 +1,15 @@
 """Text formatting utilities for different output styles."""
 
 import re
-from typing import Callable, Optional
-
-# Type aliases for phrasplit functions
-_SplitFunc = Callable[[str, str], list[str]]
-_SplitLongLinesFunc = Callable[[str, int, str], list[str]]
-
-# Try to import phrasplit, fall back to None when not available
-PHRASPLIT_AVAILABLE: bool
-phrasplit_clauses: Optional[_SplitFunc]
-phrasplit_long_lines: Optional[_SplitLongLinesFunc]
-phrasplit_paragraphs: Optional[Callable[[str], list[str]]]
-phrasplit_sentences: Optional[_SplitFunc]
-
-try:
-    from phrasplit import (  # type: ignore[import-not-found]
-        split_clauses as _phrasplit_clauses,
-    )
-    from phrasplit import (
-        split_long_lines as _phrasplit_long_lines,
-    )
-    from phrasplit import (
-        split_paragraphs as _phrasplit_paragraphs,
-    )
-    from phrasplit import (
-        split_sentences as _phrasplit_sentences,
-    )
-
-    PHRASPLIT_AVAILABLE = True
-    phrasplit_clauses = _phrasplit_clauses
-    phrasplit_long_lines = _phrasplit_long_lines
-    phrasplit_paragraphs = _phrasplit_paragraphs
-    phrasplit_sentences = _phrasplit_sentences
-except ImportError:
-    PHRASPLIT_AVAILABLE = False
-    phrasplit_clauses = None
-    phrasplit_long_lines = None
-    phrasplit_paragraphs = None
-    phrasplit_sentences = None
-
-
-def _check_phrasplit() -> None:
-    """Check if phrasplit is available, raise ImportError if not."""
-    if not PHRASPLIT_AVAILABLE:
-        raise ImportError(
-            "phrasplit is required for this feature. "
-            "Install with: pip install epub2text[sentences]"
-        )
-
-
-def split_paragraphs(text: str) -> list[str]:
-    """
-    Split text into paragraphs (separated by double newlines).
 
-    This function works without phrasplit by using a simple regex split.
-
-    Args:
-        text: Input text
-
-    Returns:
-        List of paragraphs (non-empty, stripped)
-    """
-    # Simple implementation that doesn't require phrasplit
-    paragraphs = re.split(r"\n\s*\n", text)
-    return [p.strip() for p in paragraphs if p.strip()]
+from phrasplit import (
+    split_clauses,
+    split_paragraphs,
+    split_sentences,
+)
+from phrasplit import (
+    split_long_lines as _phrasplit_split_long_lines,
+)
 
 
 def collapse_paragraph(paragraph: str) -> str:
@@ -146,8 +91,6 @@ def format_sentences(
     """
     Format text with one sentence per line.
 
-    Requires phrasplit to be installed.
-
     Args:
         text: Input text with paragraph breaks
         separator: String to prepend at paragraph boundaries (default: "  ")
@@ -157,9 +100,6 @@ def format_sentences(
         Text with one sentence per line, separator at paragraph boundaries.
         Chapter titles are preserved.
     """
-    _check_phrasplit()
-    assert phrasplit_sentences is not None
-
     paragraphs = split_paragraphs(text)
 
     if not paragraphs:
@@ -180,7 +120,7 @@ def format_sentences(
             continue
 
         # Process paragraph into sentences using phrasplit
-        sentences = phrasplit_sentences(para, language_model)
+        sentences = split_sentences(para, language_model)
 
         if not sentences:
             continue
@@ -224,8 +164,6 @@ def format_clauses(
             "I do like coffee,
             and I like wine."
     """
-    _check_phrasplit()
-    assert phrasplit_clauses is not None
 
     paragraphs = split_paragraphs(text)
 
@@ -246,7 +184,7 @@ def format_clauses(
             continue
 
         # Process paragraph into clauses using phrasplit
-        clauses = phrasplit_clauses(para, language_model)
+        clauses = split_clauses(para, language_model)
 
         if not clauses:
             continue
@@ -277,8 +215,6 @@ def split_long_lines(
     2. If still too long, split at clause boundaries (commas, semicolons, etc.)
     3. If still too long, split at word boundaries
 
-    Requires phrasplit to be installed.
-
     Args:
         text: Input text (may already be formatted)
         max_length: Maximum line length in characters
@@ -288,9 +224,6 @@ def split_long_lines(
     Returns:
         Text with long lines split. Chapter titles are preserved.
     """
-    _check_phrasplit()
-    assert phrasplit_long_lines is not None
-
     lines = text.split("\n")
     result_lines: list[str] = []
 
@@ -315,9 +248,13 @@ def split_long_lines(
         has_separator = line.startswith(separator) if separator else False
         content = line[len(separator) :] if has_separator else line
 
-        # Split the long line using phrasplit
-        split_lines_list = phrasplit_long_lines(content, max_length, language_model)
-
+        # Split the long line using phrasplit (avoid calling ourselves)
+        split_lines_list = _phrasplit_split_long_lines(
+            content, max_length, language_model
+        )
+        # Defensive: if upstream ever returns a string, normalize to list
+        if isinstance(split_lines_list, str):
+            split_lines_list = [split_lines_list]
         # Add separator to first line if original had it
         for k, split_line in enumerate(split_lines_list):
             if k == 0 and has_separator:
@@ -328,32 +265,11 @@ def split_long_lines(
     return "\n".join(result_lines)
 
 
-# Keep backward compatibility alias
-def format_as_sentences(text: str, language_model: str = "en_core_web_sm") -> str:
-    """
-    Format text with one sentence per line using spaCy.
-
-    Deprecated: Use format_sentences() instead.
-
-    Requires phrasplit to be installed.
-
-    Args:
-        text: Input text with paragraph breaks
-        language_model: spaCy language model to use (default: "en_core_web_sm")
-
-    Returns:
-        Text with sentences separated by newlines
-    """
-    return format_sentences(text, separator="", language_model=language_model)
-
-
 __all__ = [
-    "PHRASPLIT_AVAILABLE",
     "collapse_paragraph",
     "format_paragraphs",
     "format_sentences",
     "format_clauses",
     "split_long_lines",
-    "format_as_sentences",
     "split_paragraphs",
 ]

{epub2text-0.2.2 → epub2text-0.2.3}/epub2text/parser.py

@@ -57,9 +57,25 @@ class EPUBParser:
         self._metadata: Optional[Metadata] = None
         self._page_list_nav: Optional[tuple[Any, str]] = None
         self._page_list_nav_checked = False
+        self._nav_processed = False
+        self._upper_title_cache: Optional[set[str]] = None
 
         self._load_epub()
 
+    def _get_upper_titles_for_toc(self) -> set[str]:
+        if self._upper_title_cache is not None:
+            return self._upper_title_cache
+        titles: set[str] = set()
+        meta = self.get_metadata()
+        if meta.title:
+            titles.add(meta.title.upper())
+        # IMPORTANT: no chapter text allocation here
+        for ch in self.get_chapters(include_text=False):
+            if ch.title:
+                titles.add(ch.title.upper())
+        self._upper_title_cache = titles
+        return titles
+
     def _load_epub(self) -> None:
         """Load and parse the EPUB file."""
         try:
@@ -133,7 +149,8 @@ class EPUBParser:
         """
         # First, process the navigation structure
         self._process_epub_content_nav()
-
+        if not self._nav_processed:
+            self._process_epub_content_nav()
         # Convert the navigation structure to Chapter objects
         chapters: list[Chapter] = []
         self._build_chapters_from_nav(
@@ -201,6 +218,8 @@ class EPUBParser:
         Process EPUB content using ITEM_NAVIGATION (NAV HTML) or ITEM_NCX.
         Globally orders navigation entries and slices content between them.
         """
+        if self._nav_processed:
+            return
         logger.info("Processing EPUB using navigation document (NAV/NCX)...")
         nav_item = None
         nav_type = None
@@ -483,6 +502,8 @@ class EPUBParser:
                     logger.info("Added prefix content chapter")
 
         logger.info(f"Finished processing. Found {len(self.content_texts)} sections")
+        self._nav_processed = True
+        self._upper_title_cache = None  # invalidate if reprocessed for any reason
 
     def _find_doc_key(
         self,
@@ -817,6 +838,7 @@ class EPUBParser:
         chapter_ids: Optional[list[str]] = None,
         deduplicate_chapter_titles: bool = True,
         skip_toc: bool = False,
+        include_chapter_title: bool = False,
     ) -> str:
         """
         Extract text from selected chapters.
@@ -826,6 +848,8 @@ class EPUBParser:
             deduplicate_chapter_titles: If True, removes duplicate chapter titles
                 that appear as the first line of chapter content (default: True)
             skip_toc: If True, skip TOC and front matter chapters (default: False)
+            include_chapter_title: If True, includes chapter titles in the output
+                (default: False)
 
         Returns:
             Combined text from all selected chapters with chapter titles separated
@@ -870,12 +894,14 @@ class EPUBParser:
 
                 # Format: 4 linebreaks (if not first), chapter title,
                 # 2 linebreaks, content
-                if i == 0:
+                if i == 0 and include_chapter_title:
                     # First chapter: no leading linebreaks
                     parts.append(f"{chapter.title}\n\n{cleaned_text}")
-                else:
+                elif i > 0 and include_chapter_title:
                     # Subsequent chapters: 4 linebreaks before title
                     parts.append(f"\n\n\n\n{chapter.title}\n\n{cleaned_text}")
+                else:
+                    parts.append(cleaned_text)
 
         return "".join(parts)
 
@@ -1242,9 +1268,16 @@ class EPUBParser:
 
         return pages
 
-    def _split_into_sentences(self, text: str) -> list[str]:
+    def _split_into_sentences(
+        self,
+        text: str,
+        language_model: str = "en_core_web_sm",
+        apply_corrections: bool = True,
+        split_on_colon: bool = True,
+        use_spacy: bool = False,
+    ) -> list[str]:
         """
-        Split text into sentences using regex, preserving paragraph breaks.
+        Split text into sentences, preserving paragraph breaks.
 
         Handles common abbreviations and edge cases to avoid incorrect splits.
         Paragraph breaks (\\n\\n) are preserved within the sentence list.
@@ -1258,106 +1291,26 @@ class EPUBParser:
         if not text or not text.strip():
             return []
 
-        sentences: list[str] = []
+        from phrasplit import split_paragraphs, split_sentences
 
-        # Split by paragraphs first to preserve structure
-        paragraphs = text.split("\n\n")
+        sentences: list[str] = []
+        paragraphs = split_paragraphs(text)
 
         for para_idx, paragraph in enumerate(paragraphs):
             if not paragraph.strip():
                 continue
 
-            # Normalize whitespace within paragraph (but not between paragraphs)
-            paragraph = re.sub(r"[ \t]+", " ", paragraph)
-            paragraph = paragraph.replace("\n", " ")
-
-            # Common abbreviations that shouldn't end sentences
-            abbreviations = {
-                "Mr",
-                "Mrs",
-                "Ms",
-                "Dr",
-                "Prof",
-                "Sr",
-                "Jr",
-                "vs",
-                "etc",
-                "Inc",
-                "Ltd",
-                "Corp",
-                "Co",
-                "St",
-                "Ave",
-                "Blvd",
-                "Rd",
-                "Fig",
-                "No",
-                "Vol",
-                "pp",
-                "Jan",
-                "Feb",
-                "Mar",
-                "Apr",
-                "Jun",
-                "Jul",
-                "Aug",
-                "Sep",
-                "Oct",
-                "Nov",
-                "Dec",
-                "e.g",
-                "i.e",
-            }
-
-            current_sentence: list[str] = []
-
-            # Split by whitespace and process word by word
-            words = paragraph.split()
-
-            for i, word in enumerate(words):
-                current_sentence.append(word)
-
-                # Check if this word ends a sentence
-                if word and word[-1] in ".!?":
-                    # Check if it's an abbreviation
-                    word_without_punct = word.rstrip(".!?")
-                    is_abbreviation = word_without_punct in abbreviations
-
-                    # Check for ellipsis (... or . . .)
-                    is_ellipsis = word == "..." or (
-                        word == "."
-                        and i >= 2
-                        and words[i - 1] == "."
-                        and words[i - 2] == "."
-                    )
-
-                    # Check if next word starts with capital (if exists)
-                    next_word_capital = False
-                    if i + 1 < len(words):
-                        next_word = words[i + 1]
-                        if next_word and next_word[0].isupper():
-                            next_word_capital = True
-
-                    # End sentence if:
-                    # - Not an abbreviation
-                    # - Not an ellipsis
-                    # - Either at end of text or next word starts with capital
-                    if (
-                        not is_abbreviation
-                        and not is_ellipsis
-                        and (i + 1 >= len(words) or next_word_capital)
-                    ):
-                        sentence = " ".join(current_sentence)
-                        if sentence.strip():
-                            sentences.append(sentence.strip())
-                        current_sentence = []
-
-            # Add any remaining text as final sentence
-            if current_sentence:
-                sentence = " ".join(current_sentence)
-                if sentence.strip():
-                    sentences.append(sentence.strip())
-
+            para_sentences = split_sentences(
+                paragraph,
+                language_model=language_model,
+                apply_corrections=apply_corrections,
+                split_on_colon=split_on_colon,
+                use_spacy=use_spacy,
+            )
+            for sent in para_sentences:
+                sent = sent.strip()
+                if sent:
+                    sentences.append(sent)
             # Add paragraph break marker after each paragraph (except the last)
             if para_idx < len(paragraphs) - 1:
                 sentences.append("\n\n")  # Paragraph break marker
@@ -1665,20 +1618,7 @@ class EPUBParser:
         if page.chapter_title and page.chapter_title.upper() in front_matter_keywords:
             return True
 
-        # Build list of terms to look for in TOC
-        search_terms = []
-
-        # Add book title
-        metadata = self.get_metadata()
-        if metadata.title:
-            search_terms.append(metadata.title.upper())
-
-        # Add all chapter titles
-        chapters = self.get_chapters()
-        for chapter in chapters:
-            if chapter.title:
-                search_terms.append(chapter.title.upper())
-
+        search_terms = list(self._get_upper_titles_for_toc())
         if not search_terms:
             return False
 
@@ -1716,9 +1656,7 @@ class EPUBParser:
             return page_text
 
         # Build list of chapter titles to detect TOC
-        chapters = self.get_chapters()
-        chapter_titles = {ch.title.upper() for ch in chapters if ch.title}
-
+        chapter_titles = self._get_upper_titles_for_toc()
         if not chapter_titles:
             return page_text
 

{epub2text-0.2.2 → epub2text-0.2.3}/epub2text.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: epub2text
-Version: 0.2.2
+Version: 0.2.3
 Summary: A simple tool to extract text from EPUB files.
 Author-email: Holger Nahrstaedt <nahrstaedt@gmail.com>
 License: MIT License
@@ -45,10 +45,9 @@ Requires-Dist: rich>=13.0.0
 Requires-Dist: ebooklib>=0.18
 Requires-Dist: beautifulsoup4>=4.12.0
 Requires-Dist: defusedxml>=0.7.1
+Requires-Dist: phrasplit>=0.3.2
 Provides-Extra: lxml
 Requires-Dist: lxml>=4.9.0; extra == "lxml"
-Provides-Extra: sentences
-Requires-Dist: phrasplit>=0.1.0; extra == "sentences"
 Provides-Extra: dev
 Requires-Dist: pytest>=7.0.0; extra == "dev"
 Requires-Dist: ruff>=0.1.0; extra == "dev"

{epub2text-0.2.2 → epub2text-0.2.3}/epub2text.egg-info/SOURCES.txt

@@ -1,3 +1,4 @@
+.codecrate.toml
 .coveragerc
 .gitignore
 .pre-commit-config.yaml

{epub2text-0.2.2 → epub2text-0.2.3}/epub2text.egg-info/requires.txt

@@ -3,6 +3,7 @@ rich>=13.0.0
 ebooklib>=0.18
 beautifulsoup4>=4.12.0
 defusedxml>=0.7.1
+phrasplit>=0.3.2
 
 [dev]
 pytest>=7.0.0
@@ -10,6 +11,3 @@ ruff>=0.1.0
 
 [lxml]
 lxml>=4.9.0
-
-[sentences]
-phrasplit>=0.1.0

{epub2text-0.2.2 → epub2text-0.2.3}/examples/demo.py

@@ -30,7 +30,6 @@ from epub2text import (
     epub2txt,
 )
 from epub2text.formatters import (
-    PHRASPLIT_AVAILABLE,
     collapse_paragraph,
     format_clauses,
     format_paragraphs,
@@ -549,11 +548,6 @@ def example_formatters_sentences() -> None:
     print("EXAMPLE: Sentence Formatting")
     print("=" * 60)
 
-    if not PHRASPLIT_AVAILABLE:
-        print("\nNote: Install phrasplit for sentence formatting:")
-        print("  pip install epub2text[sentences]")
-        return
-
     text = """Dr. Smith went to Washington D.C. for a meeting. She arrived
 at 3 p.m. and stayed until evening. The conference was very productive.
 
@@ -579,11 +573,6 @@ def example_formatters_clauses() -> None:
     print("EXAMPLE: Clause Formatting")
     print("=" * 60)
 
-    if not PHRASPLIT_AVAILABLE:
-        print("\nNote: Install phrasplit for clause formatting:")
-        print("  pip install epub2text[sentences]")
-        return
-
     text = """When the sun rises, the birds begin to sing, and the world slowly awakens.
 
 Complex sentences, like this one, benefit from clause splitting,
@@ -609,11 +598,6 @@ def example_formatters_long_lines() -> None:
     print("EXAMPLE: Long Line Splitting")
     print("=" * 60)
 
-    if not PHRASPLIT_AVAILABLE:
-        print("\nNote: Install phrasplit for long line splitting:")
-        print("  pip install epub2text[sentences]")
-        return
-
     long_text = (
         "This is an extremely long line that contains multiple sentences "
         "and clauses, which would be difficult to read on a narrow display, "

{epub2text-0.2.2 → epub2text-0.2.3}/pyproject.toml

@@ -22,6 +22,7 @@ dependencies = [
     "ebooklib>=0.18",
     "beautifulsoup4>=4.12.0",
     "defusedxml>=0.7.1",
+    "phrasplit>=0.3.2",
 ]
 classifiers=[
     'Intended Audience :: Developers',
@@ -43,9 +44,6 @@ dynamic=["version"]
 lxml = [
     "lxml>=4.9.0",
 ]
-sentences = [
-    "phrasplit>=0.1.0",
-]
 dev = [
     "pytest>=7.0.0",
     "ruff>=0.1.0",

{epub2text-0.2.2 → epub2text-0.2.3}/tests/test_epub_download.py

@@ -2,6 +2,7 @@
 
 from __future__ import annotations
 
+import contextlib
 import threading
 import time
 from collections.abc import Generator
@@ -43,8 +44,12 @@ def serve_directory(
         host, port = server.server_address[:2]
         yield f"http://{host}:{port}"
     finally:
-        server.shutdown()
-        thread.join()
+        # Stop the loop, then close the listening socket to avoid FD/memory growth
+        with contextlib.suppress(Exception):
+            server.shutdown()
+        thread.join(timeout=5)
+        with contextlib.suppress(Exception):
+            server.server_close()
 
 
 def _create_epub(epub_path: Path) -> None:

{epub2text-0.2.2 → epub2text-0.2.3}/tests/test_epub_generation.py

@@ -13,7 +13,6 @@ import pypub  # type: ignore[import-untyped]
 import pytest
 
 from epub2text import EPUBParser, epub2txt
-from epub2text.formatters import PHRASPLIT_AVAILABLE
 
 # Check if spaCy language model is available
 try:
@@ -29,12 +28,8 @@ except ImportError:
     SPACY_AVAILABLE = False
     SPACY_MODEL_AVAILABLE = False
 
-requires_phrasplit = pytest.mark.skipif(
-    not PHRASPLIT_AVAILABLE,
-    reason="phrasplit required. Install with: pip install epub2text[sentences]",
-)
 requires_spacy_model = pytest.mark.skipif(
-    not (PHRASPLIT_AVAILABLE and SPACY_MODEL_AVAILABLE),
+    not SPACY_MODEL_AVAILABLE,
     reason=(
         "phrasplit + spaCy model required. Install with: pip install "
         "epub2text[sentences] and python -m spacy download en_core_web_sm"
@@ -959,17 +954,16 @@ class TestMetadataExtraction:
     class TestFormatters:
         """Test text formatting functions."""
 
-    @requires_phrasplit
     def test_split_at_clauses_preserves_all_text(self) -> None:
         """Test that _split_at_clauses doesn't lose any text."""
-        from phrasplit.splitter import _split_at_clauses
+        from phrasplit import split_clauses
 
         text = (
             "When the professor picked up the ancient manuscript for the "
             "ninth time, Sarah whispered, 'You will find the answer in the margins.'"
         )
 
-        result = _split_at_clauses(text, max_length=80)
+        result = split_clauses(text)
         joined = " ".join(result)
 
         # All words from original should be in result
@@ -979,17 +973,16 @@ class TestMetadataExtraction:
         assert "Sarah whispered" in joined
         assert "margins" in joined
 
-    @requires_phrasplit
     def test_split_at_clauses_no_trailing_comma(self) -> None:
         """Test that _split_at_clauses doesn't produce lines ending with just comma."""
-        from phrasplit.splitter import _split_at_clauses
+        from phrasplit import split_clauses
 
         text = (
             "When the professor picked up the ancient manuscript for the "
             "ninth time, Sarah whispered, 'You will find the answer in the margins.'"
         )
 
-        result = _split_at_clauses(text, max_length=80)
+        result = split_clauses(text)
 
         # No line should end with just a comma (indicates lost text)
         for line in result:

{epub2text-0.2.2 → epub2text-0.2.3}/tests/test_title_deduplication.py

@@ -211,7 +211,9 @@ class TestTitleDeduplication:
         parser = EPUBParser(str(epub_with_duplicate_titles))
 
         # Extract with deduplication (default)
-        text = parser.extract_chapters(deduplicate_chapter_titles=True)
+        text = parser.extract_chapters(
+            deduplicate_chapter_titles=True, include_chapter_title=True
+        )
 
         # Chapter should have title in new format (preceded by 4 newlines
         # or at start, followed by 2 newlines)