fast-sentence-segment 1.4.5__py3-none-any.whl → 1.5.3__py3-none-any.whl

fast_sentence_segment/cli.py

@@ -100,10 +100,13 @@ def main():
     parser.add_argument(
         "--format",
         action="store_true",
-        help="Format output with dialog-aware paragraph grouping",
+        help="Format output with dialog-aware paragraph grouping (implies --unwrap)",
     )
     args = parser.parse_args()
 
+    # --format implies --unwrap
+    unwrap = args.unwrap or args.format
+
     # Get input text
     if args.file:
         with open(args.file, "r", encoding="utf-8") as f:
@@ -118,7 +121,7 @@ def main():
 
     # Segment and output
     result = segment_text(
-        text.strip(), flatten=True, unwrap=args.unwrap,
+        text.strip(), flatten=True, unwrap=unwrap,
         format="dialog" if args.format else None
     )
 
@@ -170,7 +173,6 @@ def _process_single_file(
     # Step 3: Write output
     if format:
         # Format mode returns a string
-        sentence_count = result.count("\n") + 1 if result else 0
         print(f"\r  {GREEN}✓{RESET} Segmented text ({elapsed:.2f}s)")
         with open(output_file, "w", encoding="utf-8") as f:
             f.write(result + "\n")
@@ -221,10 +223,13 @@ def file_main():
     parser.add_argument(
         "--format",
         action="store_true",
-        help="Format output with dialog-aware paragraph grouping",
+        help="Format output with dialog-aware paragraph grouping (implies --unwrap)",
     )
     args = parser.parse_args()
 
+    # --format implies --unwrap
+    unwrap = args.unwrap or args.format
+
     # Validate arguments
     if not args.input_file and not args.input_dir:
         print(f"  {YELLOW}Error:{RESET} Either --input-file or --input-dir is required")
@@ -240,36 +245,37 @@ def file_main():
 
     # Process directory
     if args.input_dir:
-        if not os.path.isdir(args.input_dir):
-            print(f"  {YELLOW}Error:{RESET} Directory not found: {args.input_dir}")
+        input_dir = os.path.expanduser(args.input_dir)
+        if not os.path.isdir(input_dir):
+            print(f"  {YELLOW}Error:{RESET} Directory not found: {input_dir}")
             sys.exit(1)
 
         # Find all .txt files
         txt_files = sorted([
-            f for f in os.listdir(args.input_dir)
+            f for f in os.listdir(input_dir)
             if f.endswith(".txt") and not f.endswith("-clean.txt")
         ])
 
         if not txt_files:
-            print(f"  {YELLOW}Error:{RESET} No .txt files found in {args.input_dir}")
+            print(f"  {YELLOW}Error:{RESET} No .txt files found in {input_dir}")
             sys.exit(1)
 
         _header("segment-file (batch)")
         print(f"  {DIM}Processing {len(txt_files)} files in directory{RESET}")
         print()
-        _param("Directory", args.input_dir)
+        _param("Directory", input_dir)
         _param("Files", str(len(txt_files)))
-        _param("Unwrap", "enabled" if args.unwrap else "disabled")
+        _param("Unwrap", "enabled" if unwrap else "disabled")
         _param("Normalize quotes", "disabled" if not normalize else "enabled")
         _param("Format", "dialog" if args.format else "default (one sentence per line)")
         print()
 
         format_value = "dialog" if args.format else None
         for i, filename in enumerate(txt_files, 1):
-            input_path = os.path.join(args.input_dir, filename)
+            input_path = os.path.join(input_dir, filename)
             output_path = _generate_output_path(input_path)
             print(f"  {BOLD}[{i}/{len(txt_files)}]{RESET} {filename}")
-            _process_single_file(input_path, output_path, args.unwrap, normalize, format_value)
+            _process_single_file(input_path, output_path, unwrap, normalize, format_value)
             print()
 
         print(f"  {GREEN}Done! Processed {len(txt_files)} files.{RESET}")
@@ -277,18 +283,20 @@ def file_main():
         return
 
     # Process single file
-    if not os.path.isfile(args.input_file):
-        print(f"  {YELLOW}Error:{RESET} File not found: {args.input_file}")
+    input_file = os.path.expanduser(args.input_file)
+    if not os.path.isfile(input_file):
+        print(f"  {YELLOW}Error:{RESET} File not found: {input_file}")
         sys.exit(1)
 
-    output_file = args.output_file or _generate_output_path(args.input_file)
+    output_file = args.output_file or _generate_output_path(input_file)
+    output_file = os.path.expanduser(output_file)
 
     _header("segment-file")
     print(f"  {DIM}Segmenting text file into sentences{RESET}")
     print()
 
     format_value = "dialog" if args.format else None
-    _process_single_file(args.input_file, output_file, args.unwrap, normalize, format_value)
+    _process_single_file(input_file, output_file, unwrap, normalize, format_value)
 
     print(f"\n  {GREEN}Done!{RESET}")
     print()

fast_sentence_segment/dmo/dialog_formatter.py

@@ -37,16 +37,129 @@ DOUBLE_QUOTES = '""\""'
 SINGLE_QUOTES = "'''"
 ALL_QUOTES = DOUBLE_QUOTES + SINGLE_QUOTES
 
+# Known elision words (case-insensitive)
+# These are specific words where an apostrophe replaces omitted letters at the start
+KNOWN_ELISION_WORDS = {
+    # 'it' elisions
+    "tis", "twas", "twere", "twill", "twould", "taint", "tother",
+    # Archaic oaths (very specific words)
+    "sblood", "sdeath", "swounds", "sbodikins", "slid", "strewth", "zounds",
+    # Common elisions with a-/be- prefix dropped
+    "bout", "bove", "cross", "fore", "fraid", "gainst", "live", "loft", "lone",
+    "long", "mid", "midst", "mong", "mongst", "neath", "round", "sleep", "tween",
+    "twixt", "wake", "ware", "way", "cause", "cuz", "coz", "hind", "low", "side",
+    "yond", "cept", "scaped", "specially", "splain", "spect",
+    # Cockney/dialect h-dropping (common words and their forms)
+    "e", "em", "er", "ere", "im", "is", "ave", "avin", "ead", "ear", "eard",
+    "eart", "eaven", "eavens", "eavy", "eck", "edge", "eel", "eight", "ell",
+    "elp", "en", "ero", "igh", "ill", "imself", "int", "it", "itch", "obby",
+    "old", "ole", "oliday", "oller", "ollow", "oly", "ome", "onest", "oney",
+    "onor", "onour", "ood", "ook", "oop", "ope", "orizon", "orn", "orrible",
+    "orse", "ospital", "ot", "otel", "our", "ouse", "ow", "owever", "uge",
+    "undred", "ungry", "unt", "urry", "urt", "usband", "alf", "all", "am",
+    "and", "andsome", "appen", "appy", "ard", "arm", "at", "ate",
+    # Cockney th-dropping
+    "at", "ese", "ey", "ose", "ough", "rough",
+    # Other prefix elisions
+    "count", "fter", "gain", "gin", "less", "nother", "nough", "nuff", "pears",
+    "pon", "prentice", "scuse", "spite", "spose", "stead", "tarnal", "tend",
+    "thout", "til", "till", "un",
+    # Modern colloquial
+    "kay", "sup", "dya", "ja", "yer", "copter",
+    # Musical
+    "cello",
+    # Year abbreviations handled separately (digits)
+    # 'member (remember)
+    "member",
+}
+
+
+def _is_elision(text: str, pos: int) -> bool:
+    """Check if apostrophe at position is a word-initial elision.
+
+    Elisions like 'tis, 'twas, 'cello, 'em replace omitted letters at word start.
+    Dialog quotes like 'Hello!' surround quoted speech.
+
+    Args:
+        text: The full text.
+        pos: Position of the apostrophe character.
+
+    Returns:
+        True if this appears to be an elision, not a dialog quote.
+    """
+    if pos >= len(text) - 1:
+        return False
+
+    next_char = text[pos + 1]
+
+    # If followed by a digit, it's a year abbreviation ('99, '20s)
+    if next_char.isdigit():
+        return True
+
+    # Extract the word after the apostrophe (letters only, up to non-letter)
+    word_start = pos + 1
+    word_end = word_start
+    while word_end < len(text) and text[word_end].isalpha():
+        word_end += 1
+
+    if word_end == word_start:
+        return False  # No letters after apostrophe
+
+    word = text[word_start:word_end].lower()
+
+    # Check if it's a known elision word
+    return word in KNOWN_ELISION_WORDS
+
 
 def _count_quotes(text: str) -> int:
-    """Count quote characters in text (both single and double)."""
-    return sum(1 for c in text if c in ALL_QUOTES)
+    """Count actual quote characters in text, excluding apostrophes.
+
+    Apostrophes in contractions (don't, can't), possessives (Jack's, Joselito's),
+    and word-initial elisions ('tis, 'twas, 'cello, 'em) are NOT counted as quotes
+    because they don't indicate dialog boundaries.
+
+    A quote character is considered an apostrophe (not a quote) if:
+    - It's preceded by a letter AND followed by a letter (mid-word: don't, Joselito's)
+    - It's a word-initial elision ('tis, 'Twas, 'cello, '99)
+    """
+    count = 0
+    for i, c in enumerate(text):
+        if c not in ALL_QUOTES:
+            continue
+
+        # Check if this is a mid-word apostrophe (contraction/possessive)
+        prev_is_letter = i > 0 and text[i - 1].isalpha()
+        next_is_letter = i < len(text) - 1 and text[i + 1].isalpha()
+
+        if prev_is_letter and next_is_letter:
+            # Mid-word apostrophe (contraction/possessive) - don't count
+            continue
+
+        # Check if this is a word-initial elision
+        prev_is_word_boundary = i == 0 or not text[i - 1].isalnum()
+        if prev_is_word_boundary and c in SINGLE_QUOTES and _is_elision(text, i):
+            # Word-initial elision - don't count
+            continue
+
+        count += 1
+    return count
 
 
 def _starts_with_quote(text: str) -> bool:
-    """Check if text starts with a quote character."""
+    """Check if text starts with a dialog quote (not an elision).
+
+    Returns True only for actual dialog openings, not for elisions
+    like 'tis, 'twas, 'cello, etc.
+    """
     text = text.lstrip()
-    return text and text[0] in ALL_QUOTES
+    if not text or text[0] not in ALL_QUOTES:
+        return False
+
+    # Check if this is an elision rather than a dialog quote
+    if text[0] in SINGLE_QUOTES and _is_elision(text, 0):
+        return False
+
+    return True
 
 
 def _ends_with_closing_quote(text: str) -> bool:
@@ -211,7 +324,6 @@ def format_dialog(sentences: List[str]) -> str:
         quote_count = _count_quotes(sentence)
         starts_quote = _starts_with_quote(sentence)
         is_narrative = _is_narrative(sentence)
-        is_complete = _is_complete_quote(sentence)
 
         # Get info about previous sentence
         prev_sentence = current_para[-1] if current_para else ""
@@ -230,6 +342,10 @@ def format_dialog(sentences: List[str]) -> str:
         elif starts_quote:
             # New quote starting - always new paragraph
             should_start_new_para = True
+        elif is_narrative and prev_was_narrative:
+            # Consecutive narrative sentences - each gets its own paragraph
+            # This gives clean ebook formatting with paragraph breaks
+            should_start_new_para = True
         elif is_narrative and prev_was_complete and not prev_was_narrative:
             # Narrative after complete dialog - new paragraph
             should_start_new_para = True

fast_sentence_segment/dmo/unwrap_hard_wrapped_text.py

@@ -5,13 +5,60 @@ Joins lines within paragraphs into continuous strings while
 preserving paragraph boundaries (blank lines). Also dehyphenates
 words that were split across lines for typesetting.
 
-Related GitHub Issue:
+Related GitHub Issues:
     #8 - Add dehyphenation support for words split across lines
     https://github.com/craigtrim/fast-sentence-segment/issues/8
+
+    #12 - Unwrap fails when hard-wrap splits across blank line
+    https://github.com/craigtrim/fast-sentence-segment/issues/12
+
+    #14 - Make unwrap quote-aware to join text across blank lines inside open quotes
+    https://github.com/craigtrim/fast-sentence-segment/issues/14
 """
 
 import re
 
+# Quote characters to track for dialog detection
+# Includes straight and curly/smart quotes
+DOUBLE_QUOTES = '"""\u201c\u201d'  # " " " " "
+SINGLE_QUOTES = "'''\u2018\u2019"  # ' ' ' ' '
+ALL_QUOTES = DOUBLE_QUOTES + SINGLE_QUOTES
+
+# Known elision words where an apostrophe replaces omitted letters at word start
+# These should NOT be counted as dialog quotes
+KNOWN_ELISION_WORDS = {
+    # 'it' elisions
+    "tis", "twas", "twere", "twill", "twould", "taint", "tother",
+    # Archaic oaths
+    "sblood", "sdeath", "swounds", "sbodikins", "slid", "strewth", "zounds",
+    # Common elisions with a-/be- prefix dropped
+    "bout", "bove", "cross", "fore", "fraid", "gainst", "live", "loft", "lone",
+    "long", "mid", "midst", "mong", "mongst", "neath", "round", "sleep", "tween",
+    "twixt", "wake", "ware", "way", "cause", "cuz", "coz", "hind", "low", "side",
+    "yond", "cept", "scaped", "specially", "splain", "spect",
+    # Cockney/dialect h-dropping
+    "e", "em", "er", "ere", "im", "is", "ave", "avin", "ead", "ear", "eard",
+    "eart", "eaven", "eavens", "eavy", "eck", "edge", "eel", "eight", "ell",
+    "elp", "en", "ero", "igh", "ill", "imself", "int", "it", "itch", "obby",
+    "old", "ole", "oliday", "oller", "ollow", "oly", "ome", "onest", "oney",
+    "onor", "onour", "ood", "ook", "oop", "ope", "orizon", "orn", "orrible",
+    "orse", "ospital", "ot", "otel", "our", "ouse", "ow", "owever", "uge",
+    "undred", "ungry", "unt", "urry", "urt", "usband", "alf", "all", "am",
+    "and", "andsome", "appen", "appy", "ard", "arm", "at", "ate",
+    # Cockney th-dropping
+    "ese", "ey", "ose", "ough", "rough",
+    # Other prefix elisions
+    "count", "fter", "gain", "gin", "less", "nother", "nough", "nuff", "pears",
+    "pon", "prentice", "scuse", "spite", "spose", "stead", "tarnal", "tend",
+    "thout", "til", "till", "un",
+    # Modern colloquial
+    "kay", "sup", "dya", "ja", "yer", "copter",
+    # Musical
+    "cello",
+    # 'member (remember)
+    "member",
+}
+
 # Pattern to match hyphenated word breaks at end of line:
 # - A single hyphen (not -- em-dash)
 # - Followed by newline and optional whitespace
@@ -19,6 +66,128 @@ import re
 _HYPHEN_LINE_BREAK_PATTERN = re.compile(r'(?<!-)-\n\s*([a-z])')
 
 
+def _is_elision(text: str, pos: int) -> bool:
+    """Check if apostrophe at position is a word-initial elision.
+
+    Elisions like 'tis, 'twas, 'cello, 'em replace omitted letters at word start.
+    Dialog quotes like 'Hello!' surround quoted speech.
+
+    Args:
+        text: The full text.
+        pos: Position of the apostrophe character.
+
+    Returns:
+        True if this appears to be an elision, not a dialog quote.
+    """
+    if pos >= len(text) - 1:
+        return False
+
+    next_char = text[pos + 1]
+
+    # If followed by a digit, it's a year abbreviation ('99, '20s)
+    if next_char.isdigit():
+        return True
+
+    # Extract the word after the apostrophe (letters only, up to non-letter)
+    word_start = pos + 1
+    word_end = word_start
+    while word_end < len(text) and text[word_end].isalpha():
+        word_end += 1
+
+    if word_end == word_start:
+        return False  # No letters after apostrophe
+
+    word = text[word_start:word_end].lower()
+
+    # Check if it's a known elision word
+    return word in KNOWN_ELISION_WORDS
+
+
+def _count_quotes(text: str) -> int:
+    """Count actual quote characters in text, excluding apostrophes.
+
+    Apostrophes in contractions (don't, can't), possessives (Jack's, Joselito's),
+    and word-initial elisions ('tis, 'twas, 'cello, 'em) are NOT counted as quotes
+    because they don't indicate dialog boundaries.
+
+    A quote character is considered an apostrophe (not a quote) if:
+    - It's preceded by a letter AND followed by a letter (mid-word: don't, Joselito's)
+    - It's a word-initial elision ('tis, 'Twas, 'cello, '99)
+
+    Args:
+        text: The text to count quotes in.
+
+    Returns:
+        Number of actual quote characters (not apostrophes).
+    """
+    count = 0
+    for i, c in enumerate(text):
+        if c not in ALL_QUOTES:
+            continue
+
+        # Check if this is a mid-word apostrophe (contraction/possessive)
+        prev_is_letter = i > 0 and text[i - 1].isalpha()
+        next_is_letter = i < len(text) - 1 and text[i + 1].isalpha()
+
+        if prev_is_letter and next_is_letter:
+            # Mid-word apostrophe (contraction/possessive) - don't count
+            continue
+
+        # Check if this is a word-initial elision
+        prev_is_word_boundary = i == 0 or not text[i - 1].isalnum()
+        if prev_is_word_boundary and c in SINGLE_QUOTES and _is_elision(text, i):
+            # Word-initial elision - don't count
+            continue
+
+        count += 1
+    return count
+
+
+def _is_inside_open_quote(text: str) -> bool:
+    """Check if text ends with an unclosed quote.
+
+    Counts quote characters (excluding apostrophes) and returns True
+    if the count is odd, meaning there's an open quote.
+
+    Args:
+        text: The text to check.
+
+    Returns:
+        True if there's an unclosed quote at the end of text.
+    """
+    return _count_quotes(text) % 2 == 1
+
+# Characters that indicate end of sentence
+_SENTENCE_END_PUNCT = {'.', '?', '!'}
+
+
+def _ends_with_sentence_punct(text: str) -> bool:
+    """Check if text ends with sentence-ending punctuation.
+
+    Handles trailing quotes/parens: 'He said "Hello."' -> True
+    Handles ellipsis: 'He wondered...' -> True
+
+    Args:
+        text: The text to check.
+
+    Returns:
+        True if text ends with . ? ! or ... (possibly followed by quotes/parens).
+    """
+    if not text:
+        return False
+
+    # Strip trailing whitespace and quotes/parens (including curly quotes)
+    stripped = text.rstrip()
+    trailing_chars = {'"', "'", ')', ']', '\u201d', '\u2019'}  # " ' ) ] " '
+    while stripped and stripped[-1] in trailing_chars:
+        stripped = stripped[:-1]
+
+    if not stripped:
+        return False
+
+    return stripped[-1] in _SENTENCE_END_PUNCT
+
+
 def _dehyphenate_block(block: str) -> str:
     """Remove hyphens from words split across lines.
 
@@ -47,11 +216,26 @@ def unwrap_hard_wrapped_text(text: str) -> str:
     single spaces. Also dehyphenates words that were split
     across lines for typesetting purposes.
 
+    Special handling for spurious blank lines (issue #12):
+    When a single blank line appears mid-sentence (previous line
+    doesn't end with .?! and next line starts lowercase), the
+    text is joined rather than treated as a paragraph break.
+
+    Quote-aware joining (issue #14):
+    When we're inside an open quote (odd number of quote characters),
+    join across blank lines even if the previous line ends with
+    sentence punctuation and the next starts uppercase. This keeps
+    multi-sentence dialog together.
+
     Examples:
         >>> unwrap_hard_wrapped_text("a bot-\\ntle of wine")
         'a bottle of wine'
         >>> unwrap_hard_wrapped_text("line one\\nline two")
         'line one line two'
+        >>> unwrap_hard_wrapped_text("His colour\\n\\nmounted;")
+        'His colour mounted;'
+        >>> unwrap_hard_wrapped_text("'First.\\n\\nSecond.'")
+        "'First. Second.'"
 
     Args:
         text: Raw text with hard-wrapped lines.
@@ -60,15 +244,75 @@ def unwrap_hard_wrapped_text(text: str) -> str:
         Text with paragraphs unwrapped into continuous strings,
         separated by double newlines, with hyphenated words rejoined.
     """
-    blocks = re.split(r'\n\s*\n', text)
-    unwrapped = []
+    lines = text.splitlines()
+    paragraphs: list[list[str]] = []
+    current_para_lines: list[str] = []
+    blank_line_count = 0
+
+    for line in lines:
+        stripped = line.strip()
+
+        if not stripped:
+            # Blank line (or whitespace-only)
+            blank_line_count += 1
+        else:
+            # Non-blank line
+            if current_para_lines and blank_line_count > 0:
+                # We have previous content and saw blank line(s)
+                # Build the current paragraph text to check ending
+                prev_para = ' '.join(ln.strip() for ln in current_para_lines if ln.strip())
 
-    for block in blocks:
+                # Issue #12: Join across single blank line if:
+                # 1. Exactly one blank line
+                # 2. Previous paragraph doesn't end with sentence punctuation
+                # 3. Current line starts with lowercase
+                issue_12_join = (
+                    blank_line_count == 1
+                    and prev_para
+                    and not _ends_with_sentence_punct(prev_para)
+                    and stripped[0].islower()
+                )
+
+                # Issue #14: Join across blank line if inside open quote
+                # Even if previous ends with sentence punct and next starts uppercase,
+                # we should join if we're inside an unclosed quote
+                issue_14_join = (
+                    blank_line_count == 1
+                    and prev_para
+                    and _is_inside_open_quote(prev_para)
+                )
+
+                should_join = issue_12_join or issue_14_join
+
+                if should_join:
+                    # Treat as continuation of current paragraph
+                    current_para_lines.append(line)
+                else:
+                    # Finish current paragraph, start new one
+                    paragraphs.append(current_para_lines)
+                    current_para_lines = [line]
+            else:
+                # No blank lines seen, add to current paragraph
+                current_para_lines.append(line)
+
+            blank_line_count = 0
+
+    # Don't forget the last paragraph
+    if current_para_lines:
+        paragraphs.append(current_para_lines)
+
+    # Process each paragraph: dehyphenate and join lines
+    unwrapped = []
+    for para_lines in paragraphs:
+        block = '\n'.join(para_lines)
         # First, dehyphenate words split across lines
         block = _dehyphenate_block(block)
         # Then join remaining lines with spaces
-        lines = block.splitlines()
-        joined = ' '.join(line.strip() for line in lines if line.strip())
+        joined_lines = block.splitlines()
+        joined = ' '.join(ln.strip() for ln in joined_lines if ln.strip())
+        # Normalize multiple spaces to single space (OCR artifacts, formatting)
+        while '  ' in joined:
+            joined = joined.replace('  ', ' ')
         if joined:
             unwrapped.append(joined)
 

fast_sentence_segment/svc/perform_sentence_segmentation.py

@@ -43,19 +43,20 @@ def _load_spacy_model(model_name: str = "en_core_web_sm"):
 
         return spacy.load(model_name)
 
-from fast_sentence_segment.dmo import AbbreviationMerger
-from fast_sentence_segment.dmo import AbbreviationSplitter
-from fast_sentence_segment.dmo import TitleNameMerger
-from fast_sentence_segment.dmo import EllipsisNormalizer
-from fast_sentence_segment.dmo import NewlinesToPeriods
-from fast_sentence_segment.dmo import BulletPointCleaner
-from fast_sentence_segment.dmo import NumberedListNormalizer
-from fast_sentence_segment.dmo import QuestionExclamationSplitter
-from fast_sentence_segment.dmo import SpacyDocSegmenter
-from fast_sentence_segment.dmo import PostProcessStructure
-from fast_sentence_segment.dmo import StripTrailingPeriodAfterQuote
-from fast_sentence_segment.dmo import Dehyphenator
-from fast_sentence_segment.dmo import OcrArtifactFixer
+# Imports after lazy spacy loading function (intentional)
+from fast_sentence_segment.dmo import AbbreviationMerger  # noqa: E402
+from fast_sentence_segment.dmo import AbbreviationSplitter  # noqa: E402
+from fast_sentence_segment.dmo import TitleNameMerger  # noqa: E402
+from fast_sentence_segment.dmo import EllipsisNormalizer  # noqa: E402
+from fast_sentence_segment.dmo import NewlinesToPeriods  # noqa: E402
+from fast_sentence_segment.dmo import BulletPointCleaner  # noqa: E402
+from fast_sentence_segment.dmo import NumberedListNormalizer  # noqa: E402
+from fast_sentence_segment.dmo import QuestionExclamationSplitter  # noqa: E402
+from fast_sentence_segment.dmo import SpacyDocSegmenter  # noqa: E402
+from fast_sentence_segment.dmo import PostProcessStructure  # noqa: E402
+from fast_sentence_segment.dmo import StripTrailingPeriodAfterQuote  # noqa: E402
+from fast_sentence_segment.dmo import Dehyphenator  # noqa: E402
+from fast_sentence_segment.dmo import OcrArtifactFixer  # noqa: E402
 
 
 class PerformSentenceSegmentation(BaseObject):

{fast_sentence_segment-1.4.5.dist-info → fast_sentence_segment-1.5.3.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: fast-sentence-segment
-Version: 1.4.5
+Version: 1.5.3
 Summary: Fast and Efficient Sentence Segmentation
 Home-page: https://github.com/craigtrim/fast-sentence-segment
 License: MIT
@@ -164,21 +164,24 @@ segment-file --input-file book.txt --output-file sentences.txt
 
 # Unwrap hard-wrapped e-texts (Project Gutenberg, etc.)
 segment-file --input-file book.txt --output-file sentences.txt --unwrap
+
+# Dialog-aware formatting (implies --unwrap)
+segment -f book.txt --format
 ```
 
 ## API Reference
 
 | Function | Parameters | Returns | Description |
 |----------|------------|---------|-------------|
-| `segment_text()` | `input_text: str`, `flatten: bool = False`, `unwrap: bool = False` | `list` | Main entry point for segmentation |
+| `segment_text()` | `input_text: str`, `flatten: bool = False`, `unwrap: bool = False`, `format: str = None` | `list` or `str` | Main entry point for segmentation. Use `format="dialog"` for dialog-aware output. |
 | `Segmenter.input_text()` | `input_text: str` | `list[list[str]]` | Cached paragraph-aware segmentation |
 
 ### CLI Commands
 
 | Command | Description |
 |---------|-------------|
-| `segment [text]` | Segment text from argument, `-f FILE`, or stdin. Use `-n` for numbered output. |
-| `segment-file --input-file IN --output-file OUT [--unwrap]` | Segment a file and write one sentence per line. Use `--unwrap` for hard-wrapped e-texts. |
+| `segment [text]` | Segment text from argument, `-f FILE`, or stdin. Use `-n` for numbered output, `--format` for dialog-aware paragraph grouping. |
+| `segment-file --input-file IN --output-file OUT [--unwrap] [--format]` | Segment a file and write one sentence per line. Use `--unwrap` for hard-wrapped e-texts, `--format` for dialog-aware formatting. |
 
 ## Why Nested Lists?
 

{fast_sentence_segment-1.4.5.dist-info → fast_sentence_segment-1.5.3.dist-info}/RECORD

@@ -1,7 +1,7 @@
 fast_sentence_segment/__init__.py,sha256=DI7cyxtqnWd_5lrtGXqkIm8Aje0h55nGAHGgP6zXRyE,2278
 fast_sentence_segment/bp/__init__.py,sha256=j2-WfQ9WwVuXeGSjvV6XLVwEdvau8sdAQe4Pa4DrYi8,33
 fast_sentence_segment/bp/segmenter.py,sha256=UW6DguPgA56h-pPYRsfJhjIzBe40j6NdjkwYxamASyA,1928
-fast_sentence_segment/cli.py,sha256=8AA_V3hcOVL8ENXboFDuJTimFbHKK5KbjzIeS9Cs-xA,9568
+fast_sentence_segment/cli.py,sha256=WFhHTYrHUP0PqXeJ-6bR6hlXsV4ql190c2S2nBf-uCA,9775
 fast_sentence_segment/core/__init__.py,sha256=uoBersYyVStJ5a8zJpQz1GDGaloEdAv2jGHw1292hRM,108
 fast_sentence_segment/core/base_object.py,sha256=AYr7yzusIwawjbKdvcv4yTEnhmx6M583kDZzhzPOmq4,635
 fast_sentence_segment/core/stopwatch.py,sha256=hE6hMz2q6rduaKi58KZmiAL-lRtyh_wWCANhl4KLkRQ,879
@@ -11,7 +11,7 @@ fast_sentence_segment/dmo/abbreviation_splitter.py,sha256=03mSyJcLooNyIjXx6mPlrn
 fast_sentence_segment/dmo/abbreviations.py,sha256=CGJrJDo6pmYd3pTNEQbdOo8N6tnkCnwyL2X7Si663Os,2530
 fast_sentence_segment/dmo/bullet_point_cleaner.py,sha256=WOZQRWXiiyRi8rOuEIw36EmkaXmATHL9_Dxb2rderw4,1606
 fast_sentence_segment/dmo/dehyphenator.py,sha256=6BJTie7tClRAifeiW8V2CdAAbcbknhtqmKylAdRZ7ko,1776
-fast_sentence_segment/dmo/dialog_formatter.py,sha256=C5r3t3vY6ZbU26g0JGIk8BRlXhMn1LGPljw_WPTuCSg,8276
+fast_sentence_segment/dmo/dialog_formatter.py,sha256=CLtXGTRBC4PmH47vQ4WSlWIFi5r4rtJ7mFxs4xyBcmg,12824
 fast_sentence_segment/dmo/ellipsis_normalizer.py,sha256=lHs9dLFfKJe-2vFNe17Hik90g3_kXX347OzGP_IOT08,1521
 fast_sentence_segment/dmo/group_quoted_sentences.py,sha256=Ifh_kUwi7sMbzbZvrTgEKkzWe50AafUDhVKVPR9h7wQ,5092
 fast_sentence_segment/dmo/newlines_to_periods.py,sha256=PUrXreqZWiITINfoJL5xRRlXJH6noH0cdXtW1EqAh8I,1517
@@ -23,12 +23,12 @@ fast_sentence_segment/dmo/question_exclamation_splitter.py,sha256=cRsWRu8zb6wOWG
 fast_sentence_segment/dmo/spacy_doc_segmenter.py,sha256=Kb65TYMhrbpTYEey5vb7TyhCjUHVxmugHYIeKkntCwk,5147
 fast_sentence_segment/dmo/strip_trailing_period_after_quote.py,sha256=wYkoLy5XJKZIblJXBvDAB8-a81UTQOhOf2u91wjJWUw,2259
 fast_sentence_segment/dmo/title_name_merger.py,sha256=zbG04_VjwM8TtT8LhavvmZqIZL_2xgT2OTxWkK_Zt1s,5133
-fast_sentence_segment/dmo/unwrap_hard_wrapped_text.py,sha256=V1T5RsJBaII_iGJMyWvv6rb2mny8pnVd428oVZL0n5I,2457
+fast_sentence_segment/dmo/unwrap_hard_wrapped_text.py,sha256=UlWQSb6H8hGwCu719mYEuc4rBzH68wGWwuRH9c4S_xw,11573
 fast_sentence_segment/svc/__init__.py,sha256=9B12mXxBnlalH4OAm1AMLwUMa-RLi2ilv7qhqv26q7g,144
 fast_sentence_segment/svc/perform_paragraph_segmentation.py,sha256=zLKw9rSzb0NNfx4MyEeoGrHwhxTtH5oDrYcAL2LMVHY,1378
-fast_sentence_segment/svc/perform_sentence_segmentation.py,sha256=vpZ7lyOKxIAgHRk-rfgNI4BtAC38vU5UbYokkw8JhK8,7639
-fast_sentence_segment-1.4.5.dist-info/LICENSE,sha256=vou5JCLAT5nHcsUv-AkjUYAihYfN9mwPDXxV2DHyHBo,1067
-fast_sentence_segment-1.4.5.dist-info/METADATA,sha256=1xZQ63f20VnbsLC_leQ40nIXLRbSkfUwnbxZmtBGYo0,7785
-fast_sentence_segment-1.4.5.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
-fast_sentence_segment-1.4.5.dist-info/entry_points.txt,sha256=Zc8OwFKj3ofnjy5ZIFqHzDkIEWweV1AP1xap1ZFGD8M,107
-fast_sentence_segment-1.4.5.dist-info/RECORD,,
+fast_sentence_segment/svc/perform_sentence_segmentation.py,sha256=I58wdpoRqa79qrn-GxZhqPSg7DF-5curtLhIBBdi33E,7879
+fast_sentence_segment-1.5.3.dist-info/LICENSE,sha256=vou5JCLAT5nHcsUv-AkjUYAihYfN9mwPDXxV2DHyHBo,1067
+fast_sentence_segment-1.5.3.dist-info/METADATA,sha256=0TIiLm5CuM0-_h1Rr_CWHeBlkcYsFS2t5-NWgHdpwUI,8038
+fast_sentence_segment-1.5.3.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
+fast_sentence_segment-1.5.3.dist-info/entry_points.txt,sha256=Zc8OwFKj3ofnjy5ZIFqHzDkIEWweV1AP1xap1ZFGD8M,107
+fast_sentence_segment-1.5.3.dist-info/RECORD,,