Added support for . separator in timestamps

CHANGELOG.md

@@ -1,6 +1,8 @@
 # 1.2.4 (Pre-release)
-- **Subtitle generation is now available for all languages!** Abogen now supports subtitle generation for non-English languages using duration-based timing. Available modes include `Line`, `Sentence`, and `Sentence + Comma`. (Note: Word-level subtitle modes remain English-only due to Kokoro's timestamp token limitations.)
+- **Subtitle generation is now available for all languages!** Abogen now supports subtitle generation for non-English languages using audio duration-based timing. Available modes include `Line`, `Sentence`, and `Sentence + Comma`. (Note: Word-level subtitle modes remain English-only due to Kokoro's timestamp token limitations.)
+- Added support for `.` separator in timestamps (e.g. `HH:MM:SS.ms`) for timestamp-based text files.
 - Optimized regex compilation and eliminated busy-wait loops.
+- Fixed unused regex patterns and variable naming conventions.
 - Improvements in code and documentation.
 
 # 1.2.3

README.md

@@ -235,7 +235,7 @@ Similar to chapter markers, it is possible to add metadata tags for `M4B` files.
 > Note: `METADATA_COVER_PATH` is used to embed a cover image into the generated M4B file. Abogen automatically extracts the cover from EPUB and PDF files and adds this tag for you.
 
 ## `About Timestamp-based Text Files`
-Similar to converting subtitle files to audio, Abogen can automatically detect text files that contain timestamps in `HH:MM:SS` or `HH:MM:SS,ms` format. When timestamps are found inside your text file, Abogen will ask if you want to use them for audio timing. This is useful for creating timed narrations, scripts, or transcripts where you need exact control over when each segment is spoken.
+Similar to converting subtitle files to audio, Abogen can automatically detect text files that contain timestamps in `HH:MM:SS`, `HH:MM:SS,ms` or `HH:MM:SS.ms` format. When timestamps are found inside your text file, Abogen will ask if you want to use them for audio timing. This is useful for creating timed narrations, scripts, or transcripts where you need exact control over when each segment is spoken.
 
 Format your text file like this:
 ```
@@ -250,7 +250,7 @@ And this is the third segment, starting at 45 seconds.
 ```
 
 **Important notes:**
-- Timestamps must be in `HH:MM:SS` or `HH:MM:SS,ms` format (e.g., `00:05:30` for 5 minutes 30 seconds, or `00:05:30,500` for 5 minutes 30.5 seconds)
+- Timestamps must be in `HH:MM:SS`, `HH:MM:SS,ms` or `HH:MM:SS.ms` format (e.g., `00:05:30` for 5 minutes 30 seconds, or `00:05:30.500` for 5 minutes 30.5 seconds)
 - Milliseconds are optional and provide precision up to 1/1000th of a second
 - Text before the first timestamp (if any) will automatically start at `00:00:00`
 - When using timestamps, the subtitle generation mode setting is ignored

abogen/conversion.py

@@ -38,16 +38,14 @@ _HTML_TAG_PATTERN = re.compile(r"<[^>]+>")
 _VOICE_TAG_PATTERN = re.compile(r"{[^}]+}")
 _ASS_STYLING_PATTERN = re.compile(r"\{[^}]+\}")
 _ASS_NEWLINE_N_PATTERN = re.compile(r"\\N")
-_ASS_NEWLINE_n_PATTERN = re.compile(r"\\n")
-_BRACKETED_NUMBERS_PATTERN = re.compile(r"\[\s*\d+\s*\]")
+_ASS_NEWLINE_LOWER_N_PATTERN = re.compile(r"\\n")
 _CHAPTER_MARKER_SEARCH_PATTERN = re.compile(r"<<CHAPTER_MARKER:(.*?)>>")
 _WEBVTT_HEADER_PATTERN = re.compile(r"^WEBVTT.*?\n", re.MULTILINE)
 _VTT_STYLE_PATTERN = re.compile(r"STYLE\s*\n.*?(?=\n\n|$)", re.DOTALL)
 _VTT_NOTE_PATTERN = re.compile(r"NOTE\s*\n.*?(?=\n\n|$)", re.DOTALL)
 _DOUBLE_NEWLINE_SPLIT_PATTERN = re.compile(r"\n\s*\n")
-_SRT_TIMESTAMP_PATTERN = re.compile(r"(\d{2}:\d{2}:\d{2},\d{3})\s*-->\s*(\d{2}:\d{2}:\d{2},\d{3})")
 _VTT_TIMESTAMP_PATTERN = re.compile(r"([\d:.]+)\s*-->\s*([\d:.]+)")
-_TIMESTAMP_ONLY_PATTERN = re.compile(r"^(\d{1,2}:\d{2}:\d{2}(?:,\d{1,3})?)$")
+_TIMESTAMP_ONLY_PATTERN = re.compile(r"^(\d{1,2}:\d{2}:\d{2}(?:[.,]\d{1,3})?)$")
 _WINDOWS_ILLEGAL_CHARS_PATTERN = re.compile(r'[<>:"/\\|?*]')
 _CONTROL_CHARS_PATTERN = re.compile(r"[\x00-\x1f]")
 _LINUX_CONTROL_CHARS_PATTERN = re.compile(r"[\x01-\x1f]")  # Linux: exclude \x00 for separate handling
@@ -239,20 +237,14 @@ def parse_timestamp_text_file(file_path):
         content = f.read()
 
     # Split by timestamp pattern (supports HH:MM:SS or HH:MM:SS,ms)
-    pattern = r"^(\d{1,2}:\d{2}:\d{2}(?:,\d{1,3})?)$"
+    pattern = r"^(\d{1,2}:\d{2}:\d{2}(?:[.,]\d{1,3})?)$"
     lines = content.split("\n")
 
     def parse_time(time_str):
         """Convert HH:MM:SS or HH:MM:SS,ms to seconds as float."""
-        if "," in time_str:
-            time_part, ms_part = time_str.split(",")
-            parts = time_part.split(":")
-            seconds = int(parts[0]) * 3600 + int(parts[1]) * 60 + int(parts[2])
-            milliseconds = int(ms_part.ljust(3, "0"))  # Pad to 3 digits
-            return seconds + milliseconds / 1000.0
-        else:
+        time_str = time_str.replace(",", ".")
         parts = time_str.split(":")
-            return float(int(parts[0]) * 3600 + int(parts[1]) * 60 + int(parts[2]))
+        return float(int(parts[0]) * 3600 + int(parts[1]) * 60 + float(parts[2]))
 
     entries = []
     current_time = None
@@ -377,7 +369,7 @@ def parse_ass_file(file_path):
                 # Clean text of ASS styling tags using pre-compiled patterns
                 text = _ASS_STYLING_PATTERN.sub("", text)  # Remove {tags}
                 text = _ASS_NEWLINE_N_PATTERN.sub("\n", text)  # Convert \N to newline
-                text = _ASS_NEWLINE_n_PATTERN.sub("\n", text)  # Convert \n to newline
+                text = _ASS_NEWLINE_LOWER_N_PATTERN.sub("\n", text)  # Convert \n to newline
                 # Remove chapter markers and metadata tags
                 text = clean_subtitle_text(text)