README.md

@@ -152,8 +152,8 @@ Subscleaner now uses a SQLite database to track processed files, which significa
 
 The SQLite database is stored in the following locations, depending on your operating system:
 
-- **Linux**: `~/.local/share/subscleaner/subscleaner.db`
-- **macOS**: `~/Library/Application Support/subscleaner/subscleaner.db`
+- **Linux**: `~/.local/share/subscleaner/subscleaner/subscleaner.db`
+- **macOS**: `~/Library/Application Support/subscleaner/subscleaner/subscleaner.db`
 - **Windows**: `C:\Users\<username>\AppData\Local\subscleaner\subscleaner\subscleaner.db`
 
 ### Command Line Options
@@ -165,13 +165,11 @@ Several command line options are available:
 - `--reset-db`: Reset the database (remove all stored file hashes)
 - `--list-patterns`: List all advertisement patterns being used
 - `--version`: Show version information and exit
-- `-v`, `--verbose`: Increase output verbosity (show analyzing/skipping messages)
 
 Example usage:
 ```sh
 find /your/media/location -name "*.srt" | subscleaner --force
 find /your/media/location -name "*.srt" | subscleaner --db-location /path/to/custom/database.db
-find /your/media/location -name "*.srt" | subscleaner --verbose
 ```
 
 This feature makes Subscleaner more efficient, especially when running regularly via cron jobs or other scheduled tasks, as it will only process new or modified subtitle files.

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "subscleaner"
-version = "2.1.1"
+version = "2.0.0"
 description = "Remove advertisements from subtitle files"
 authors = [
     {name = "Roger Gonzalez", email = "roger@rogs.me"}

src/subscleaner/__init__.py

@@ -1,3 +1,3 @@
 """Subscleaner package."""
 
-__version__ = "2.1.1"
+__version__ = "1.3.0"

src/subscleaner/subscleaner.py

@@ -20,10 +20,12 @@ along with this program.  If not, see <https://www.gnu.org/licenses/>.
 
 import argparse
 import hashlib
+import os
 import pathlib
 import re
 import sqlite3
 import sys
+import time
 
 import chardet
 import pysrt
@@ -227,6 +229,27 @@ def contains_ad(subtitle_line: str) -> bool:
     return any(pattern.search(subtitle_line) for pattern in AD_PATTERNS)
 
 
+def is_processed_before(subtitle_file: pathlib.Path) -> bool:
+    """
+    Check if the subtitle file has already been processed.
+
+    Args:
+        subtitle_file (pathlib.Path): The path to the subtitle file.
+
+    Returns:
+        bool: True if the subtitle file has already been processed, False otherwise.
+    """
+    try:
+        file_creation_time = os.path.getctime(subtitle_file)
+        processed_timestamp = time.mktime(
+            time.strptime("2021-05-13 00:00:00", "%Y-%m-%d %H:%M:%S"),
+        )
+        return file_creation_time < processed_timestamp
+    except Exception as e:
+        print(f"Error checking if file was processed before: {e}")
+        return False
+
+
 def get_encoding(subtitle_file: pathlib.Path) -> str:
     """
     Detect the encoding of the subtitle file.
@@ -270,11 +293,12 @@ def remove_ad_lines(subtitle_data: pysrt.SubRipFile) -> bool:
     return modified
 
 
-def is_already_processed(subtitle_file, db_path, file_hash, force=False, verbose=False):
+def is_already_processed(subtitle_file, db_path, file_hash, force=False):
     """
     Check if the subtitle file has already been processed.
 
-    This function checks the database to determine if a file has already been processed.
+    This function checks both the database and the timestamp to determine
+    if a file has already been processed.
 
     Args:
         subtitle_file (pathlib.Path): The path to the subtitle file.
@@ -290,14 +314,20 @@ def is_already_processed(subtitle_file, db_path, file_hash, force=False, verbose
 
     # Check if the file is in the database with the same hash
     if is_file_processed(db_path, str(subtitle_file), file_hash):
-        if verbose:
         print(f"Already processed {subtitle_file} (hash match)")
         return True
 
+    # Check based on timestamp
+    if is_processed_before(subtitle_file):
+        print(f"Already processed {subtitle_file} (timestamp check)")
+        # Still mark it in the database
+        mark_file_processed(db_path, str(subtitle_file), file_hash)
+        return True
+
     return False
 
 
-def process_subtitle_file(subtitle_file_path: str, db_path, force=False, verbose=False) -> bool:
+def process_subtitle_file(subtitle_file_path: str, db_path, force=False) -> bool:
     """
     Process a subtitle file to remove ad lines.
 
@@ -305,14 +335,12 @@ def process_subtitle_file(subtitle_file_path: str, db_path, force=False, verbose
         subtitle_file_path (str): The path to the subtitle file.
         db_path (pathlib.Path): The path to the database file.
         force (bool): If True, process the file even if it has been processed before.
-        verbose (bool): If True, print detailed processing information.
 
     Returns:
         bool: True if the subtitle file was modified, False otherwise.
     """
     try:
         subtitle_file = pathlib.Path(subtitle_file_path)
-        if verbose:
         print(f"Analyzing: {subtitle_file}")
 
         # Early validation checks
@@ -362,7 +390,7 @@ def process_subtitle_file(subtitle_file_path: str, db_path, force=False, verbose
         return False
 
 
-def process_subtitle_files(subtitle_files: list[str], db_path, force=False, verbose=False) -> list[str]:
+def process_subtitle_files(subtitle_files: list[str], db_path, force=False) -> list[str]:
     """
     Process multiple subtitle files to remove ad lines.
 
@@ -370,20 +398,25 @@ def process_subtitle_files(subtitle_files: list[str], db_path, force=False, verb
         subtitle_files (list[str]): A list of subtitle file paths.
         db_path (pathlib.Path): The path to the database file.
         force (bool): If True, process files even if they have been processed before.
-        verbose (bool): If True, print detailed processing information.
 
     Returns:
         list[str]: A list of modified subtitle file paths.
     """
     modified_files = []
     for subtitle_file in subtitle_files:
-        if process_subtitle_file(subtitle_file, db_path, force, verbose):
+        if process_subtitle_file(subtitle_file, db_path, force):
             modified_files.append(subtitle_file)
     return modified_files
 
 
-def _parse_args():
-    """Parse command line arguments."""
+def main():
+    """
+    Process subtitle files to remove ad lines.
+
+    Read subtitle file paths from standard input, process each file to remove ad lines,
+    and print the result. Keep track of the modified files and print
+    a summary at the end.
+    """
     parser = argparse.ArgumentParser(description="Remove advertisements from subtitle files.")
     parser.add_argument(
         "--db-location",
@@ -394,17 +427,10 @@ def _parse_args():
     parser.add_argument("--version", action="store_true", help="Show version information and exit")
     parser.add_argument("--reset-db", action="store_true", help="Reset the database (remove all stored file hashes)")
     parser.add_argument("--list-patterns", action="store_true", help="List all advertisement patterns being used")
-    parser.add_argument(
-        "-v",
-        "--verbose",
-        action="store_true",
-        help="Increase output verbosity (show analyzing/skipping messages)",
-    )
-    return parser.parse_args()
+    args = parser.parse_args()
 
-
-def _print_version():
-    """Print the application version."""
+    # Handle version request
+    if args.version:
         try:
             from subscleaner import __version__
 
@@ -414,10 +440,13 @@ def _print_version():
 
             version = importlib.metadata.version("subscleaner")
             print(f"Subscleaner version {version}")
+        return
 
+    # Get database path
+    db_path = get_db_path(args.db_location)
 
-def _reset_database(db_path):
-    """Reset the database file."""
+    # Handle reset database request
+    if args.reset_db:
         if db_path.exists():
             try:
                 db_path.unlink()
@@ -426,43 +455,16 @@ def _reset_database(db_path):
                 print(f"Error resetting database: {e}")
         else:
             print(f"No database found at {db_path}")
-
-
-def _list_patterns():
-    """List the configured ad patterns."""
-    print("Advertisement patterns being used:")
-    for i, pattern in enumerate(AD_PATTERNS, 1):
-        print(f"{i}. {pattern.pattern}")
-
-
-def main():
-    """
-    Run the main entry point for the Subscleaner script.
-
-    Parse arguments, handle special commands like version or reset-db,
-    and processes subtitle files provided via stdin.
-    """
-    args = _parse_args()
-
-    # Handle version request
-    if args.version:
-        _print_version()
-        return
-
-    # Get database path
-    db_path = get_db_path(args.db_location)
-
-    # Handle reset database request
-    if args.reset_db:
-        _reset_database(db_path)
         return
 
     # Handle list patterns request
     if args.list_patterns:
-        _list_patterns()
+        print("Advertisement patterns being used:")
+        for i, pattern in enumerate(AD_PATTERNS, 1):
+            print(f"{i}. {pattern.pattern}")
         return
 
-    # Initialize database if not resetting
+    # Initialize database
     init_db(db_path)
 
     # Process subtitle files
@@ -471,9 +473,8 @@ def main():
         print("No subtitle files provided. Pipe filenames to subscleaner or use --help for more information.")
         return
 
-    if args.verbose:
     print("Starting script")
-    modified_files = process_subtitle_files(subtitle_files, db_path, args.force, args.verbose)
+    modified_files = process_subtitle_files(subtitle_files, db_path, args.force)
     if modified_files:
         print(f"Modified {len(modified_files)} files")
     print("Done")

tests/test_subscleaner.py

@@ -11,6 +11,7 @@ import pytest
 from src.subscleaner.subscleaner import (
     contains_ad,
     get_encoding,
+    is_processed_before,
     main,
     process_subtitle_file,
     process_subtitle_files,
@@ -98,6 +99,23 @@ def test_contains_ad(subtitle_line, expected_result):
     assert contains_ad(subtitle_line) is expected_result
 
 
+def test_is_processed_before(tmpdir):
+    """
+    Test the is_processed_before function.
+
+    Args:
+        tmpdir (pytest.fixture): A temporary directory for creating the sample SRT file.
+    """
+    subtitle_file = create_sample_srt_file(tmpdir, "")
+    subtitle_path = Path(subtitle_file)
+
+    with patch("os.path.getctime", return_value=0):
+        assert is_processed_before(subtitle_path) is True
+
+    with patch("os.path.getctime", return_value=9999999999):
+        assert is_processed_before(subtitle_path) is False
+
+
 def test_get_encoding(tmpdir, sample_srt_content):
     """
     Test the get_encoding function.
@@ -139,6 +157,7 @@ def test_process_subtitle_file_no_modification(tmpdir, sample_srt_content, mock_
     """
     subtitle_file = create_sample_srt_file(tmpdir, sample_srt_content)
     with (
+        patch("src.subscleaner.subscleaner.is_processed_before", return_value=True),
         patch("src.subscleaner.subscleaner.is_file_processed", return_value=True),
     ):
         assert process_subtitle_file(subtitle_file, mock_db_path) is False
@@ -155,6 +174,7 @@ def test_process_subtitle_file_with_modification(tmpdir, sample_srt_content, moc
     """
     subtitle_file = create_sample_srt_file(tmpdir, sample_srt_content)
     with (
+        patch("src.subscleaner.subscleaner.is_processed_before", return_value=False),
         patch("src.subscleaner.subscleaner.is_file_processed", return_value=False),
         patch("src.subscleaner.subscleaner.get_file_hash", return_value="mockhash"),
         patch("src.subscleaner.subscleaner.mark_file_processed"),
@@ -191,8 +211,8 @@ def test_process_subtitle_files(tmpdir, sample_srt_content, mock_db_path):
         assert modified_subtitle_files == [subtitle_file1]
         assert mock_process.call_count == 2  # noqa PLR2004
         # Check that db_path was passed to process_subtitle_file
-        mock_process.assert_any_call(subtitle_file1, mock_db_path, False, False)
-        mock_process.assert_any_call(subtitle_file2, mock_db_path, False, False)
+        mock_process.assert_any_call(subtitle_file1, mock_db_path, False)
+        mock_process.assert_any_call(subtitle_file2, mock_db_path, False)
 
 
 def test_main_no_modification(tmpdir, sample_srt_content):
@@ -213,7 +233,7 @@ def test_main_no_modification(tmpdir, sample_srt_content):
         patch("src.subscleaner.subscleaner.process_subtitle_files", return_value=[]) as mock_process_subtitle_files,
     ):
         main()
-        mock_process_subtitle_files.assert_called_once_with([subtitle_file], Path("/tmp/test_db.db"), False, False)
+        mock_process_subtitle_files.assert_called_once_with([subtitle_file], Path("/tmp/test_db.db"), False)
 
 
 def test_main_with_modification(tmpdir, sample_srt_content):
@@ -237,7 +257,7 @@ def test_main_with_modification(tmpdir, sample_srt_content):
         ) as mock_process_subtitle_files,
     ):
         main()
-        mock_process_subtitle_files.assert_called_once_with([subtitle_file], Path("/tmp/test_db.db"), False, False)
+        mock_process_subtitle_files.assert_called_once_with([subtitle_file], Path("/tmp/test_db.db"), False)
 
 
 def test_process_files_with_special_chars(special_chars_temp_dir, sample_srt_content, mock_db_path):
@@ -252,6 +272,7 @@ def test_process_files_with_special_chars(special_chars_temp_dir, sample_srt_con
     special_files = create_special_char_files(special_chars_temp_dir, sample_srt_content)
 
     with (
+        patch("src.subscleaner.subscleaner.is_processed_before", return_value=False),
         patch("src.subscleaner.subscleaner.is_file_processed", return_value=False),
         patch("src.subscleaner.subscleaner.get_file_hash", return_value="mockhash"),
         patch("src.subscleaner.subscleaner.mark_file_processed"),
@@ -284,6 +305,27 @@ def test_get_encoding_with_special_chars(special_chars_temp_dir, sample_srt_cont
         pytest.fail(f"get_encoding raised {e} with non-existent file")
 
 
+def test_is_processed_before_with_special_chars(special_chars_temp_dir):
+    """
+    Test is_processed_before function with special character filenames.
+
+    Args:
+        special_chars_temp_dir: Temporary directory for special character files
+    """
+    file_path = special_chars_temp_dir / "check_processed_ümlaut.srt"
+    with open(file_path, "w", encoding="utf-8") as f:
+        f.write("Test content")
+
+    with patch("os.path.getctime", return_value=0):
+        assert is_processed_before(file_path) is True
+
+    with patch("os.path.getctime", return_value=9999999999):
+        assert is_processed_before(file_path) is False
+
+    non_existent_file = special_chars_temp_dir / "non_existent_ümlaut.srt"
+    assert is_processed_before(non_existent_file) is False
+
+
 def test_process_subtitle_file_with_special_chars(special_chars_temp_dir, sample_srt_content, mock_db_path):
     """
     Test process_subtitle_file function with special character filenames.
@@ -298,6 +340,7 @@ def test_process_subtitle_file_with_special_chars(special_chars_temp_dir, sample
         f.write(sample_srt_content)
 
     with (
+        patch("src.subscleaner.subscleaner.is_processed_before", return_value=False),
         patch("src.subscleaner.subscleaner.is_file_processed", return_value=False),
         patch("src.subscleaner.subscleaner.get_file_hash", return_value="mockhash"),
         patch("src.subscleaner.subscleaner.mark_file_processed"),
@@ -324,6 +367,7 @@ def test_file_saving_with_special_chars(special_chars_temp_dir, sample_srt_conte
     special_files = create_special_char_files(special_chars_temp_dir, sample_srt_content)
 
     with (
+        patch("src.subscleaner.subscleaner.is_processed_before", return_value=False),
         patch("src.subscleaner.subscleaner.is_file_processed", return_value=False),
         patch("src.subscleaner.subscleaner.get_file_hash", return_value="mockhash"),
         patch("src.subscleaner.subscleaner.mark_file_processed"),
@@ -366,4 +410,4 @@ def test_main_with_special_chars(special_chars_temp_dir, sample_srt_content):
         ) as mock_process_subtitle_files,
     ):
         main()
-        mock_process_subtitle_files.assert_called_once_with([str(file_path)], Path("/tmp/test_db.db"), False, False)
+        mock_process_subtitle_files.assert_called_once_with([str(file_path)], Path("/tmp/test_db.db"), False)

uv.lock

@@ -456,7 +456,7 @@ wheels = [
 
 [[package]]
 name = "subscleaner"
-version = "2.1.1"
+version = "1.3.0"
 source = { editable = "." }
 dependencies = [
     { name = "appdirs" },