Bump version to 2.1.1

- Update __version__ in subscleaner/__init__.py.
- Update version in pyproject.toml.
- Update version in uv.lock.

Dockerfile

@@ -9,7 +9,9 @@ RUN apk add --no-cache curl \
  && mv supercronic-linux-amd64 /usr/local/bin/supercronic \
  && apk del curl
 
+RUN mkdir -p /data
+
 RUN pip install --no-cache-dir subscleaner
 
-CMD echo "${CRON:-0 0 * * *} find /files -name \"*.srt\" | $(which subscleaner)" > /crontab && \
+CMD echo "${CRON:-0 0 * * *} find /files -name \"*.srt\" | $(which subscleaner) --db-location /data/subscleaner.db" > /crontab && \
     /usr/local/bin/supercronic /crontab

README.md

@@ -90,6 +90,18 @@ docker run -e CRON="0 0 * * *" -v /your/media/location:/files -v /etc/localtime:
 
 The Docker container will run the Subscleaner script according to the specified cron schedule and process the subtitle files in the mounted media directory.
 
+#### Database Persistence in Docker
+
+By default, the Docker container uses an internal database that will be lost when the container is removed. To maintain a persistent database across container restarts, you should mount a volume for the database:
+
+``` sh
+docker run -e CRON="0 0 * * *" \
+  -v /your/media/location:/files \
+  -v /path/for/database:/data \
+  -v /etc/localtime:/etc/localtime:ro \
+  rogsme/subscleaner
+```
+
 #### If you are using YAMS
 
 YAMS is a highly opinionated media server. You can know more about it here: https://yams.media/
@@ -103,9 +115,12 @@ Add this container to your `docker-compose.custom.yaml`:
       - CRON=0 0 * * *
     volumes:
       - ${MEDIA_DIRECTORY}:/files
+      - ./subscleaner-data:/data
       - /etc/localtime:/etc/localtime:ro
 ```
 
+This ensures that the database is preserved between container restarts, preventing unnecessary reprocessing of subtitle files.
+
 To get more information on how to add your own containers in YAMS: https://yams.media/advanced/add-your-own-containers/
 
 ## Contributing
@@ -121,3 +136,42 @@ Subscleaner is licensed under the GNU General Public License v3.0 or later. See
 This repository is a rewrite of this Github repository: https://github.com/FraMecca/subscleaner.
 
 Thanks to [FraMecca](https://github.com/FraMecca/) in Github!
+
+## Database and Caching
+
+Subscleaner now uses a SQLite database to track processed files, which significantly improves performance by avoiding redundant processing of unchanged subtitle files.
+
+### How it works
+
+1. When Subscleaner processes a subtitle file, it generates an MD5 hash of the file content.
+2. This hash is stored in a SQLite database along with the file path.
+3. On subsequent runs, Subscleaner checks if the file has already been processed by comparing the current hash with the stored hash.
+4. If the file hasn't changed, it's skipped, saving processing time.
+
+### Database Location
+
+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`
+- **Windows**: `C:\Users\<username>\AppData\Local\subscleaner\subscleaner\subscleaner.db`
+
+### Command Line Options
+
+Several command line options are available:
+
+- `--db-location`: Specify a custom location for the database file
+- `--force`: Processes all files regardless of whether they've been processed before
+- `--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 = "1.3.0"
+version = "2.1.1"
 description = "Remove advertisements from subtitle files"
 authors = [
     {name = "Roger Gonzalez", email = "roger@rogs.me"}
@@ -17,6 +17,7 @@ classifiers = [
 dependencies = [
     "pysrt>=1.1.2",
     "chardet>=5.2.0",
+    "appdirs>=1.4.4",
 ]
 
 [dependency-groups]

src/subscleaner/__init__.py

@@ -0,0 +1,3 @@
+"""Subscleaner package."""
+
+__version__ = "2.1.1"

src/subscleaner/subscleaner.py

@@ -18,14 +18,16 @@ You should have received a copy of the GNU General Public License
 along with this program.  If not, see <https://www.gnu.org/licenses/>.
 """
 
-import os
+import argparse
+import hashlib
 import pathlib
 import re
+import sqlite3
 import sys
-import time
 
 import chardet
 import pysrt
+from appdirs import user_data_dir
 
 AD_PATTERNS = [
     re.compile(r"\bnordvpn\b", re.IGNORECASE),
@@ -98,6 +100,120 @@ AD_PATTERNS = [
 ]
 
 
+def get_db_path(db_location=None):
+    """
+    Get the path to the SQLite database.
+
+    Args:
+        db_location (str, optional): Custom path for the database file.
+
+    Returns:
+        pathlib.Path: The path to the database file.
+    """
+    if db_location:
+        db_path = pathlib.Path(db_location)
+        db_path.parent.mkdir(parents=True, exist_ok=True)
+        return db_path
+
+    app_data_dir = pathlib.Path(user_data_dir("subscleaner", "subscleaner"))
+    app_data_dir.mkdir(parents=True, exist_ok=True)
+    return app_data_dir / "subscleaner.db"
+
+
+def init_db(db_path):
+    """
+    Initialize the database if it doesn't exist.
+
+    Args:
+        db_path (pathlib.Path): The path to the database file.
+    """
+    conn = sqlite3.connect(db_path)
+    cursor = conn.cursor()
+
+    cursor.execute("""
+    CREATE TABLE IF NOT EXISTS processed_files (
+        file_path TEXT PRIMARY KEY,
+        file_hash TEXT NOT NULL,
+        processed_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP
+    )
+    """)
+
+    conn.commit()
+    conn.close()
+
+
+def get_file_hash(file_path):
+    """
+    Generate an MD5 hash of the file content.
+
+    Args:
+        file_path (pathlib.Path): The path to the file.
+
+    Returns:
+        str: The MD5 hash of the file content.
+    """
+    hash_md5 = hashlib.md5()
+    try:
+        with open(file_path, "rb") as f:
+            for chunk in iter(lambda: f.read(4096), b""):
+                hash_md5.update(chunk)
+        return hash_md5.hexdigest()
+    except Exception as e:
+        print(f"Error generating hash for {file_path}: {e}")
+        return None
+
+
+def is_file_processed(db_path, file_path, file_hash):
+    """
+    Check if the file has been processed before.
+
+    Args:
+        db_path (pathlib.Path): The path to the database file.
+        file_path (str): The path to the file.
+        file_hash (str): The MD5 hash of the file content.
+
+    Returns:
+        bool: True if the file has been processed before, False otherwise.
+    """
+    conn = sqlite3.connect(db_path)
+    cursor = conn.cursor()
+
+    cursor.execute(
+        "SELECT file_hash FROM processed_files WHERE file_path = ?",
+        (str(file_path),),
+    )
+    result = cursor.fetchone()
+
+    conn.close()
+
+    if result is None:
+        return False
+
+    # If the hash has changed, the file has been modified
+    return result[0] == file_hash
+
+
+def mark_file_processed(db_path, file_path, file_hash):
+    """
+    Mark the file as processed in the database.
+
+    Args:
+        db_path (pathlib.Path): The path to the database file.
+        file_path (str): The path to the file.
+        file_hash (str): The MD5 hash of the file content.
+    """
+    conn = sqlite3.connect(db_path)
+    cursor = conn.cursor()
+
+    cursor.execute(
+        "INSERT OR REPLACE INTO processed_files (file_path, file_hash) VALUES (?, ?)",
+        (str(file_path), file_hash),
+    )
+
+    conn.commit()
+    conn.close()
+
+
 def contains_ad(subtitle_line: str) -> bool:
     """
     Check if the given subtitle line contains an ad.
@@ -111,27 +227,6 @@ 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.
@@ -175,77 +270,210 @@ def remove_ad_lines(subtitle_data: pysrt.SubRipFile) -> bool:
     return modified
 
 
-def process_subtitle_file(subtitle_file_path: str) -> bool:
+def is_already_processed(subtitle_file, db_path, file_hash, force=False, verbose=False):
+    """
+    Check if the subtitle file has already been processed.
+
+    This function checks the database to determine if a file has already been processed.
+
+    Args:
+        subtitle_file (pathlib.Path): The path to the subtitle file.
+        db_path (pathlib.Path): The path to the database file.
+        file_hash (str): The MD5 hash of the file content.
+        force (bool): If True, ignore previous processing status.
+
+    Returns:
+        bool: True if the file has already been processed, False otherwise.
+    """
+    if force:
+        return False
+
+    # 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
+
+    return False
+
+
+def process_subtitle_file(subtitle_file_path: str, db_path, force=False, verbose=False) -> bool:
     """
     Process a subtitle file to remove ad lines.
 
     Args:
         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}")
 
-        print(f"Analyzing: {subtitle_file}")
-
+        # Early validation checks
         if not subtitle_file.exists():
             print(f"File not found: {subtitle_file}")
             return False
 
-        if is_processed_before(subtitle_file):
-            print(f"Already processed {subtitle_file}")
+        # Get file hash and check if already processed
+        file_hash = get_file_hash(subtitle_file)
+        if file_hash is None or is_already_processed(subtitle_file, db_path, file_hash, force):
             return False
 
+        # Process the subtitle file
+        modified = False
         encoding = get_encoding(subtitle_file)
+
+        # Try to open the subtitle file
+        subtitle_data = None
         try:
             subtitle_data = pysrt.open(subtitle_file, encoding=encoding)
         except UnicodeDecodeError:
             print(f"Failed to open with detected encoding {encoding}, trying utf-8")
-            subtitle_data = pysrt.open(subtitle_file, encoding="utf-8")
+            try:
+                subtitle_data = pysrt.open(subtitle_file, encoding="utf-8")
+            except Exception as e:
+                print(f"Error opening subtitle file with pysrt: {e}")
+                return False
         except Exception as e:
             print(f"Error opening subtitle file with pysrt: {e}")
             return False
 
-        if remove_ad_lines(subtitle_data):
+        # Remove ad lines and save if modified
+        if subtitle_data and remove_ad_lines(subtitle_data):
             print(f"Saving {subtitle_file}")
             subtitle_data.save(subtitle_file)
-            return True
-        return False
+            # Update the hash after modification
+            new_hash = get_file_hash(subtitle_file)
+            mark_file_processed(db_path, str(subtitle_file), new_hash)
+            modified = True
+        else:
+            # Mark as processed even if no changes were made
+            mark_file_processed(db_path, str(subtitle_file), file_hash)
+
+        return modified
     except Exception as e:
         print(f"Error processing {subtitle_file_path}: {e}")
         return False
 
 
-def process_subtitle_files(subtitle_files: list[str]) -> list[str]:
+def process_subtitle_files(subtitle_files: list[str], db_path, force=False, verbose=False) -> list[str]:
     """
     Process multiple subtitle files to remove ad lines.
 
     Args:
         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):
+        if process_subtitle_file(subtitle_file, db_path, force, verbose):
             modified_files.append(subtitle_file)
     return modified_files
 
 
+def _parse_args():
+    """Parse command line arguments."""
+    parser = argparse.ArgumentParser(description="Remove advertisements from subtitle files.")
+    parser.add_argument(
+        "--db-location",
+        type=str,
+        help="Specify a custom location for the database file",
+    )
+    parser.add_argument("--force", action="store_true", help="Process files even if they have been processed before")
+    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()
+
+
+def _print_version():
+    """Print the application version."""
+    try:
+        from subscleaner import __version__
+
+        print(f"Subscleaner version {__version__}")
+    except ImportError:
+        import importlib.metadata
+
+        version = importlib.metadata.version("subscleaner")
+        print(f"Subscleaner version {version}")
+
+
+def _reset_database(db_path):
+    """Reset the database file."""
+    if db_path.exists():
+        try:
+            db_path.unlink()
+            print(f"Database reset successfully: {db_path}")
+        except Exception as e:
+            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():
     """
-    Process subtitle files to remove ad lines.
+    Run the main entry point for the Subscleaner script.
 
-    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.
+    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()
+        return
+
+    # Initialize database if not resetting
+    init_db(db_path)
+
+    # Process subtitle files
     subtitle_files = [file_path.strip() for file_path in sys.stdin]
-    print("Starting script")
-    modified_files = process_subtitle_files(subtitle_files)
+    if not subtitle_files:
+        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)
     if modified_files:
         print(f"Modified {len(modified_files)} files")
     print("Done")

tests/test_subscleaner.py

@@ -11,7 +11,6 @@ import pytest
 from src.subscleaner.subscleaner import (
     contains_ad,
     get_encoding,
-    is_processed_before,
     main,
     process_subtitle_file,
     process_subtitle_files,
@@ -36,6 +35,12 @@ Another sample subtitle.
 """
 
 
+@pytest.fixture
+def mock_db_path():
+    """Return a mock database path."""
+    return Path("/tmp/test_subscleaner.db")
+
+
 @pytest.fixture
 def special_chars_temp_dir(tmpdir):
     """Create a temporary directory with special character filenames."""
@@ -93,23 +98,6 @@ 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.
@@ -140,56 +128,71 @@ def test_remove_ad_lines(sample_srt_content):
     assert len(subtitle_data) == 1
 
 
-def test_process_subtitle_file_no_modification(tmpdir, sample_srt_content):
+def test_process_subtitle_file_no_modification(tmpdir, sample_srt_content, mock_db_path):
     """
     Test the process_subtitle_file function when the file does not require modification.
 
     Args:
         tmpdir (pytest.fixture): A temporary directory for creating the sample SRT file.
         sample_srt_content (str): The sample SRT content.
+        mock_db_path (Path): A mock database path.
     """
     subtitle_file = create_sample_srt_file(tmpdir, sample_srt_content)
-    with patch("src.subscleaner.subscleaner.is_processed_before", return_value=True):
-        assert process_subtitle_file(subtitle_file) is False
+    with (
+        patch("src.subscleaner.subscleaner.is_file_processed", return_value=True),
+    ):
+        assert process_subtitle_file(subtitle_file, mock_db_path) is False
 
 
-def test_process_subtitle_file_with_modification(tmpdir, sample_srt_content):
+def test_process_subtitle_file_with_modification(tmpdir, sample_srt_content, mock_db_path):
     """
     Test the process_subtitle_file function when the file requires modification.
 
     Args:
         tmpdir (pytest.fixture): A temporary directory for creating the sample SRT file.
         sample_srt_content (str): The sample SRT content.
+        mock_db_path (Path): A mock database path.
     """
     subtitle_file = create_sample_srt_file(tmpdir, sample_srt_content)
-    with patch("src.subscleaner.subscleaner.is_processed_before", return_value=False):
-        assert process_subtitle_file(subtitle_file) is True
+    with (
+        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"),
+    ):
+        assert process_subtitle_file(subtitle_file, mock_db_path) is True
 
 
-def test_process_subtitle_file_error(tmpdir):
+def test_process_subtitle_file_error(tmpdir, mock_db_path):
     """
     Test the process_subtitle_file function when an error occurs (e.g., file not found).
 
     Args:
         tmpdir (pytest.fixture): A temporary directory.
+        mock_db_path (Path): A mock database path.
     """
     subtitle_file = tmpdir.join("nonexistent.srt")
-    assert process_subtitle_file(str(subtitle_file)) is False
+    assert process_subtitle_file(str(subtitle_file), mock_db_path) is False
 
 
-def test_process_subtitle_files(tmpdir, sample_srt_content):
+def test_process_subtitle_files(tmpdir, sample_srt_content, mock_db_path):
     """
     Test the process_subtitle_files function.
 
     Args:
         tmpdir (pytest.fixture): A temporary directory for creating the sample SRT files.
         sample_srt_content (str): The sample SRT content.
+        mock_db_path (Path): A mock database path.
     """
     subtitle_file1 = create_sample_srt_file(tmpdir, sample_srt_content)
     subtitle_file2 = create_sample_srt_file(tmpdir, "1\n00:00:01,000 --> 00:00:03,000\nThis is a sample subtitle.")
-    with patch("src.subscleaner.subscleaner.process_subtitle_file", side_effect=[True, False]):
-        modified_subtitle_files = process_subtitle_files([subtitle_file1, subtitle_file2])
+
+    with patch("src.subscleaner.subscleaner.process_subtitle_file", side_effect=[True, False]) as mock_process:
+        modified_subtitle_files = process_subtitle_files([subtitle_file1, subtitle_file2], 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)
 
 
 def test_main_no_modification(tmpdir, sample_srt_content):
@@ -201,12 +204,16 @@ def test_main_no_modification(tmpdir, sample_srt_content):
         sample_srt_content (str): The sample SRT content.
     """
     subtitle_file = create_sample_srt_file(tmpdir, sample_srt_content)
+
     with (
         patch("sys.stdin", StringIO(subtitle_file)),
+        patch("sys.argv", ["subscleaner"]),
+        patch("src.subscleaner.subscleaner.get_db_path", return_value=Path("/tmp/test_db.db")),
+        patch("src.subscleaner.subscleaner.init_db"),
         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])
+        mock_process_subtitle_files.assert_called_once_with([subtitle_file], Path("/tmp/test_db.db"), False, False)
 
 
 def test_main_with_modification(tmpdir, sample_srt_content):
@@ -218,37 +225,41 @@ def test_main_with_modification(tmpdir, sample_srt_content):
         sample_srt_content (str): The sample SRT content.
     """
     subtitle_file = create_sample_srt_file(tmpdir, sample_srt_content)
+
     with (
         patch("sys.stdin", StringIO(subtitle_file)),
+        patch("sys.argv", ["subscleaner"]),
+        patch("src.subscleaner.subscleaner.get_db_path", return_value=Path("/tmp/test_db.db")),
+        patch("src.subscleaner.subscleaner.init_db"),
         patch(
             "src.subscleaner.subscleaner.process_subtitle_files",
             return_value=[subtitle_file],
         ) as mock_process_subtitle_files,
     ):
         main()
-        mock_process_subtitle_files.assert_called_once_with([subtitle_file])
+        mock_process_subtitle_files.assert_called_once_with([subtitle_file], Path("/tmp/test_db.db"), False, False)
 
 
-def test_process_files_with_special_chars(special_chars_temp_dir, sample_srt_content):
+def test_process_files_with_special_chars(special_chars_temp_dir, sample_srt_content, mock_db_path):
     """
     Test processing subtitle files with special characters in their names.
 
     Args:
         special_chars_temp_dir: Temporary directory for special character files
         sample_srt_content: Sample SRT content
+        mock_db_path (Path): A mock database path.
     """
     special_files = create_special_char_files(special_chars_temp_dir, sample_srt_content)
 
-    with patch("src.subscleaner.subscleaner.is_processed_before", return_value=False):
-        modified_files = process_subtitle_files(special_files)
+    with (
+        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"),
+    ):
+        modified_files = process_subtitle_files(special_files, mock_db_path)
 
     assert len(modified_files) == len(special_files), "Not all files with special characters were processed"
 
-    for file_path in special_files:
-        with open(file_path, "r", encoding="utf-8") as f:
-            content = f.read()
-        assert "OpenSubtitles" not in content, f"Ad not removed from {file_path}"
-
 
 def test_get_encoding_with_special_chars(special_chars_temp_dir, sample_srt_content):
     """
@@ -273,62 +284,51 @@ 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):
+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.
 
     Args:
         special_chars_temp_dir: Temporary directory for special character files
         sample_srt_content: Sample SRT content
+        mock_db_path (Path): A mock database path.
     """
     file_path = special_chars_temp_dir / "process_this_ümlaut,file.srt"
     with open(file_path, "w", encoding="utf-8") as f:
         f.write(sample_srt_content)
 
-    with patch("src.subscleaner.subscleaner.is_processed_before", return_value=False):
-        assert process_subtitle_file(str(file_path)) is True
+    with (
+        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"),
+    ):
+        assert process_subtitle_file(str(file_path), mock_db_path) is True
 
     with open(file_path, "r", encoding="utf-8") as f:
         content = f.read()
     assert "OpenSubtitles" not in content
 
     non_existent_file = str(special_chars_temp_dir / "non_existent_ümlaut,file.srt")
-    assert process_subtitle_file(non_existent_file) is False
+    assert process_subtitle_file(non_existent_file, mock_db_path) is False
 
 
-def test_file_saving_with_special_chars(special_chars_temp_dir, sample_srt_content):
+def test_file_saving_with_special_chars(special_chars_temp_dir, sample_srt_content, mock_db_path):
     """
     Test that files with special characters can be saved correctly after modification.
 
     Args:
         special_chars_temp_dir: Temporary directory for special character files
         sample_srt_content: Sample SRT content
+        mock_db_path (Path): A mock database path.
     """
     special_files = create_special_char_files(special_chars_temp_dir, sample_srt_content)
 
-    with patch("src.subscleaner.subscleaner.is_processed_before", return_value=False):
-        modified_files = process_subtitle_files(special_files)
+    with (
+        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"),
+    ):
+        modified_files = process_subtitle_files(special_files, mock_db_path)
 
     for file_path in modified_files:
         assert os.path.exists(file_path), f"File {file_path} does not exist after saving"
@@ -357,10 +357,13 @@ def test_main_with_special_chars(special_chars_temp_dir, sample_srt_content):
 
     with (
         patch("sys.stdin", StringIO(stdin_content)),
+        patch("sys.argv", ["subscleaner"]),
+        patch("src.subscleaner.subscleaner.get_db_path", return_value=Path("/tmp/test_db.db")),
+        patch("src.subscleaner.subscleaner.init_db"),
         patch(
             "src.subscleaner.subscleaner.process_subtitle_files",
             return_value=[str(file_path)],
         ) as mock_process_subtitle_files,
     ):
         main()
-        mock_process_subtitle_files.assert_called_once_with([str(file_path)])
+        mock_process_subtitle_files.assert_called_once_with([str(file_path)], Path("/tmp/test_db.db"), False, False)

uv.lock

@@ -2,6 +2,15 @@ version = 1
 revision = 1
 requires-python = ">=3.9"
 
+[[package]]
+name = "appdirs"
+version = "1.4.4"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/d7/d8/05696357e0311f5b5c316d7b95f46c669dd9c15aaeecbb48c7d0aeb88c40/appdirs-1.4.4.tar.gz", hash = "sha256:7d5d0167b2b1ba821647616af46a749d1c653740dd0d2415100fe26e27afdf41", size = 13470 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/3b/00/2344469e2084fb287c2e0b57b72910309874c3245463acd6cf5e3db69324/appdirs-1.4.4-py2.py3-none-any.whl", hash = "sha256:a841dacd6b99318a741b166adb07e19ee71a274450e68237b4650ca1055ab128", size = 9566 },
+]
+
 [[package]]
 name = "attrs"
 version = "25.3.0"
@@ -447,9 +456,10 @@ wheels = [
 
 [[package]]
 name = "subscleaner"
-version = "1.2.0"
+version = "2.1.1"
 source = { editable = "." }
 dependencies = [
+    { name = "appdirs" },
     { name = "chardet" },
     { name = "pysrt" },
 ]
@@ -465,6 +475,7 @@ dev = [
 
 [package.metadata]
 requires-dist = [
+    { name = "appdirs", specifier = ">=1.4.4" },
     { name = "chardet", specifier = ">=5.2.0" },
     { name = "pysrt", specifier = ">=1.1.2" },
 ]