pysfi 0.1.10__py3-none-any.whl → 0.1.12__py3-none-any.whl

sfi/docdiff/docdiff.py

@@ -0,0 +1,238 @@
+from __future__ import annotations
+
+import argparse
+import atexit
+import json
+import logging
+import platform
+import subprocess
+import time
+from dataclasses import dataclass
+from functools import cached_property
+from pathlib import Path
+from typing import Any
+
+CONFIG_FILE = Path.home() / ".sfi" / "docdiff.json"
+
+logging.basicConfig(level=logging.INFO, format="%(message)s")
+logger = logging.getLogger(__name__)
+
+
+@dataclass
+class DocDiffConfig:
+    """Document comparison configuration."""
+
+    DOC_DIFF_TITLE: str = "Comparison Result"
+    OUTPUT_DIR: str = str(Path.home())  # Use current directory if empty
+    COMPARE_MODE: str = "original"  # Options: original, revised
+    SHOW_CHANGES: bool = True
+    TRACK_REVISIONS: bool = True
+
+    def __init__(self) -> None:
+        if CONFIG_FILE.exists():
+            logger.info("Loading configuration from %s", CONFIG_FILE)
+            config_data = json.loads(CONFIG_FILE.read_text())
+            # Update configuration items, keeping defaults as fallback
+            for key, value in config_data.items():
+                if hasattr(self, key):
+                    setattr(self, key, value)
+        else:
+            logger.info("Using default configuration")
+
+    def save(self) -> None:
+        """Save configuration."""
+        CONFIG_FILE.parent.mkdir(parents=True, exist_ok=True)
+        CONFIG_FILE.write_text(json.dumps(vars(self), indent=4))
+
+
+conf = DocDiffConfig()
+atexit.register(conf.save)
+
+
+@dataclass(frozen=True)
+class DiffDocCommand:
+    """Document comparison command."""
+
+    old_doc: Path
+    new_doc: Path
+    output_path: Path | None = None
+
+    def run(self) -> None:
+        """Run the document comparison command."""
+        if platform.system() != "Windows":
+            logger.error("This tool is only available on Windows.")
+            return
+        if not self.old_doc.exists():
+            logger.error(f"Old file does not exist: {self.old_doc}")
+            return
+
+        if not self.new_doc.exists():
+            logger.error(f"New file does not exist: {self.new_doc}")
+            return
+
+        if not self.validate_files:
+            logger.error("Invalid file paths or extensions")
+            return
+
+        if self.word_app is None:
+            logger.error("Word application is not available")
+            return
+
+        if self.compare_data is None:
+            return
+
+        self.output.parent.mkdir(parents=True, exist_ok=True)
+        try:
+            self.compare_data.SaveAs2(str(self.output))
+            self.compare_data.Close()
+        except Exception as e:
+            logger.exception(f"Comparison failed: {e}")
+        else:
+            logger.info(f"Comparison completed. Saved to: {self.output}")
+        finally:
+            try:
+                self.word_app.Documents.Close(SaveChanges=False)
+            except Exception:
+                logger.exception("Close document failed!")
+            else:
+                self.word_app.Quit()
+
+            try:
+                subprocess.run(
+                    ["taskkill", "/f", "/t", "/im", "WINWORD.EXE"], check=False
+                )
+            except Exception:
+                logger.exception("Taskkill failed!")
+            else:
+                logger.info("Taskkill completed successfully")
+
+    @cached_property
+    def word_app(self) -> Any:
+        try:
+            import win32com.client as win32  # type: ignore
+        except ImportError:
+            logger.exception("win32com.client is not installed, exiting.")
+            raise
+        else:
+            logger.info("Started Word application")
+            app = win32.gencache.EnsureDispatch("Word.Application")  # type: ignore
+            app.Visible = False
+            app.DisplayAlerts = False
+
+            try:
+                app.Options.TrackRevisions = conf.TRACK_REVISIONS
+            except AttributeError:
+                logger.warning(
+                    "TrackRevisions option not available in this Word version"
+                )
+
+            return app
+
+    @cached_property
+    def validate_files(self) -> bool:
+        return all([
+            self.old_doc.exists(),
+            self.new_doc.exists(),
+            self.old_doc.suffix.lower() in [".doc", ".docx"],
+            self.new_doc.suffix.lower() in [".doc", ".docx"],
+        ])
+
+    @cached_property
+    def compare_data(self) -> Any:
+        try:
+            compared = self.word_app.CompareDocuments(
+                self.old_doc_data,
+                self.new_doc_data,
+                0,
+                2 if conf.COMPARE_MODE == "revised" else 0,
+                True,
+            )
+        except Exception as e:
+            logger.exception(f"Comparison failed: {e}")
+            return None
+        else:
+            if compared:
+                logger.info("Comparison completed successfully")
+                compared.ShowRevisions = conf.SHOW_CHANGES
+                return compared
+            return None
+
+    @cached_property
+    def old_doc_data(self) -> Any:
+        logger.info(f"Opening old file: {self.old_doc}")
+        return self.word_app.Documents.Open(str(self.old_doc.resolve()))
+
+    @cached_property
+    def new_doc_data(self) -> Any:
+        logger.info(f"Opening new file: {self.new_doc}")
+        return self.word_app.Documents.Open(str(self.new_doc.resolve()))
+
+    @cached_property
+    def output(self) -> Path:
+        """Determine the output directory for the comparison result."""
+        output_filename = (
+            f"{conf.DOC_DIFF_TITLE}@{time.strftime('%Y%m%d_%H_%M_%S')}.docx"
+        )
+
+        if self.output_path is None:
+            output_dir = (
+                Path(conf.OUTPUT_DIR) if conf.OUTPUT_DIR else self.new_doc.parent
+            )
+            return output_dir / output_filename
+
+        if self.output_path.is_dir():
+            return self.output_path / output_filename
+        elif self.output_path.is_file():
+            return self.output_path
+        else:
+            raise ValueError(f"Invalid output path: {self.output_path}")
+
+
+def parse_args():
+    parser = argparse.ArgumentParser(description="Compare two doc/docx files.")
+    parser.add_argument(
+        "files", nargs=2, help="Two input files to compare (old_file new_file)"
+    )
+    parser.add_argument(
+        "-o", "--output", dest="output", default=".", help="Output file path"
+    )
+    parser.add_argument("--title", help="Title for the comparison result")
+    parser.add_argument(
+        "--show-changes", action="store_true", help="Show changes in the comparison"
+    )
+    parser.add_argument(
+        "--hide-changes", action="store_true", help="Hide changes in the comparison"
+    )
+    parser.add_argument(
+        "--compare-mode",
+        choices=["original", "revised"],
+        help="Compare mode: original or revised",
+    )
+    parser.add_argument("--output-dir", help="Output directory for the result file")
+
+    args = parser.parse_args()
+
+    # Update configuration from command line arguments
+    if args.title:
+        conf.DOC_DIFF_TITLE = args.title
+    if args.show_changes:
+        conf.SHOW_CHANGES = True
+    if args.hide_changes:
+        conf.SHOW_CHANGES = False
+    if args.compare_mode:
+        conf.COMPARE_MODE = args.compare_mode
+    if args.output_dir:
+        conf.OUTPUT_DIR = args.output_dir
+
+    return args
+
+
+def main() -> None:
+    """Compare two doc/docx files."""
+    args = parse_args()
+
+    DiffDocCommand(
+        Path(args.files[0]),
+        Path(args.files[1]),
+        Path(args.output),
+    ).run()

sfi/docscan/__init__.py

@@ -1,3 +1,3 @@
 """Document scanner module for scanning and extracting content from various document formats."""
 
-__version__ = "0.1.10"
+__version__ = "0.1.12"

sfi/docscan/docscan_gui.py

@@ -86,7 +86,7 @@ def t(key: str, **kwargs) -> str:
             try:
                 from src.docscan.lang.eng import ENGLISH_DEFAULTS
             except ImportError:
-                ENGLISH_DEFAULTS = {}
+                ENGLISH_DEFAULTS = {}  # noqa: N806
 
         text = ENGLISH_DEFAULTS.get(key, key)
     else:

sfi/docscan/lang/eng.py

@@ -1,152 +1,152 @@
-"""English translation defaults for docscan GUI."""
-
-ENGLISH_DEFAULTS = {
-    "window_title": "Document Scanner GUI",
-    "input_config_tab": "Input Configuration",
-    "scan_options_tab": "Scan Options",
-    "input_directory": "Input Directory:",
-    "browse": "Browse...",
-    "rules_file": "Rules File:",
-    "file_types": "File Types:",
-    "use_pdf_ocr": "Use PDF OCR",
-    "use_process_pool": "Use Process Pool (CPU-intensive)",
-    "threads": "Threads:",
-    "batch_size": "Batch Size:",
-    "start_scan": "Start Scan",
-    "pause": "Pause",
-    "resume": "Resume",
-    "stop": "Stop",
-    "save_results": "Save Results",
-    "clear_results": "Clear Results",
-    "results": "Results",
-    "files_scanned": "Files Scanned:",
-    "files_with_matches": "Files with Matches:",
-    "progress_log": "Progress Log:",
-    "match_details": "Match Details:",
-    "selected_match_context": "Selected Match Context:",
-    "file": "File",
-    "type": "Type",
-    "matches": "Matches",
-    "time": "Time (s)",
-    "select_input_directory": "Select Input Directory",
-    "select_rules_file": "Select Rules File",
-    "json_files": "JSON Files (*.json)",
-    "save_results_dialog": "Save Results",
-    "default_results_filename": "scan_results_{datetime}.json",
-    "error": "Error",
-    "warning": "Warning",
-    "success": "Success",
-    "invalid_input_directory": "Invalid input directory",
-    "no_valid_rules": "No valid rules found",
-    "failed_to_load_rules": "Failed to load rules: {error}",
-    "no_results_to_save": "No results to save",
-    "failed_to_save_results": "Failed to save results: {error}",
-    "scan_failed": "Scan failed: {error}",
-    "starting_scan": "Starting scan...",
-    "scan_complete": "Scan complete!",
-    "pausing_scan": "Pausing scan...",
-    "stopping_scan": "Stopping scan...",
-    "scan_completed": "Scan completed",
-    "scan_stopped": "Scan stopped",
-    "found_matches_files": "Found matches in {count} files",
-    "file_info": "File",
-    "type_info": "Type",
-    "size": "Size",
-    "bytes": "bytes",
-    "rule": "Rule",
-    "description": "Description",
-    "line": "Line {line}: {match}",
-    "context": "Context:",
-    "default_file_types": "pdf,docx,xlsx,pptx,txt,odt,rtf,epub,csv,xml,html,md,jpg,jpeg,png,gif,bmp,tiff",
-    "default_rules_file": "rules.json",
-    "results_saved_to": "Results saved to:\n{path}",
-    "files_scanned_zero": "Files Scanned: 0",
-    "files_with_matches_zero": "Files with Matches: 0",
-    "language_settings": "Language Settings",
-    "processing_options": "Processing Options",
-    "performance_settings": "Performance Settings",
-    "language_label": "Language:",
-    "ocr_tooltip": "Enable OCR for scanned PDF files to extract text from images",
-    "process_pool_tooltip": "Use multiple processes for CPU-intensive operations (may increase memory usage)",
-    "threads_tooltip": "Number of worker threads (higher values may improve speed but use more CPU)",
-    "batch_size_tooltip": "Number of files to process in each batch (larger batches may improve throughput)",
-    "file_types_tooltip": "File types to scan (comma separated)",
-    "file_menu": "&File",
-    "settings_menu": "&Settings",
-    "help_menu": "&Help",
-    "preferences": "&Preferences...",
-    "exit": "E&xit",
-    "about": "&About",
-    "about_title": "About Document Scanner",
-    "about_text": "Document Scanner GUI\n\nVersion 1.0",
-    "language": "Language",
-    "open_results": "Open Results...",
-    "open_results_file": "Open Scan Results",
-    "loaded_results_from": "Loaded results from: {path}",
-    "results_loaded_successfully": "Results loaded successfully from:\n{path}",
-    "failed_to_load_results": "Failed to load results: {error}",
-    # Command-line specific translations
-    "document_scanner_description": "Scan documents and extract text, images, and metadata with certain rules.",
-    "input_directory_help": "Input directory containing documents to scan",
-    "rules_file_help": "Rules file (JSON)",
-    "recursive_help": "Scan files recursively",
-    "file_types_help": "File types to scan (comma-separated)",
-    "use_pdf_ocr_help": "Use PDF OCR for image-based PDFs",
-    "use_process_pool_help": "Use process pool instead of thread pool (better for CPU-intensive tasks)",
-    "batch_size_help": "Number of files to process in each batch",
-    "threads_help": "Number of threads for parallel scanning",
-    "progress_help": "Show progress bar",
-    "verbose_help": "Verbose output",
-    "language_help": "Set language (en for English, zh for Chinese)",
-    # Status and logging messages
-    "scanning_directory": "Scanning directory: {directory}",
-    "found_files_to_scan": "Found {count} files to scan",
-    "scan_resumed": "Scan resumed",
-    "scan_stopped_before_submitting_tasks": "Scan stopped by user before submitting all tasks",
-    "scan_paused": "Scan paused",
-    "scan_stopped_while_paused": "Scan stopped while paused",
-    "scan_stopped_by_user_canceling_tasks": "Scan stopped by user, cancelling remaining tasks...",
-    "task_timeout_scan_may_be_stopping": "Task timeout, scan may be stopping",
-    "error_scanning_file": "Error scanning file: {error}",
-    "progress_report": "Progress: {processed}/{total} files processed",
-    "force_shutting_down_executor": "Force shutting down executor...",
-    "scan_stopped_processed_files": "Scan stopped. Processed {processed} files",
-    "scan_complete_found_matches": "Scan complete. Found matches in {matches_count} files",
-    "found_matches_in_file": "Found matches in: {file_name}",
-    "processed_file_info": "Processed {file_name} ({ext}) in {time:.3f}s - {matches_count} matches found",
-    "could_not_extract_text_from_file": "Could not extract text from {file_path}: {error}",
-    "pymupdf_failed_for_file": "PyMuPDF failed for {file_name}: {error}",
-    "pypdf_also_failed_for_file": "pypdf also failed for {file_name}: {error}",
-    "no_pdf_library_installed": "No PDF library installed (pymupdf or pypdf)",
-    "pymupdf_not_installed": "PyMuPDF not installed",
-    "no_pages_found_in_file": "No pages found in {file_path}",
-    "no_metadata_found_in_file": "No metadata found in {file_path}",
-    "pymupdf_error_trying_fallback": "PyMuPDF error on {file_path}: {error}, trying pypdf fallback",
-    "pypdf_not_installed_skipping_extraction": "pypdf not installed, skipping PDF extraction",
-    "error_extracting_pdf_with_pypdf": "Error extracting PDF with pypdf: {error}",
-    "odfpy_not_installed_skipping_extraction": "odfpy not installed, skipping ODT extraction",
-    "error_extracting_odt": "Error extracting ODT: {error}",
-    "error_extracting_rtf": "Error extracting RTF: {error}",
-    "ebooklib_not_installed_skipping_extraction": "ebooklib not installed, skipping EPUB extraction",
-    "error_extracting_epub": "Error extracting EPUB: {error}",
-    "error_extracting_csv": "Error extracting CSV: {error}",
-    "error_extracting_xml": "Error extracting XML: {error}",
-    "error_extracting_html": "Error extracting HTML: {error}",
-    "error_extracting_markdown": "Error extracting Markdown: {error}",
-    "python_docx_not_installed_skipping_extraction": "python-docx not installed, skipping DOCX extraction",
-    "openpyxl_not_installed_skipping_extraction": "openpyxl not installed, skipping XLSX extraction",
-    "python_pptx_not_installed_skipping_extraction": "python-pptx not installed, skipping PPTX extraction",
-    "pillow_or_tesseract_not_installed_skipping_ocr": "PIL or pytesseract not installed, skipping image OCR",
-    "could_not_perform_ocr_on_file": "Could not perform OCR on {file_path}: {error}",
-    "input_directory_does_not_exist": "Input directory does not exist: {input_dir}",
-    "using_rules_file": "Using rules file: {rules_file}",
-    "invalid_json_in_rules_file": "Invalid JSON in rules file: {error}",
-    "invalid_rules_format": "Invalid rules format. Expected a list or dict with 'rules' key",
-    "no_valid_rules_found": "No valid rules found",
-    "total_time_elapsed": "Total time elapsed: {time:.2f}s",
-    "invalid_regex_pattern": "Invalid regex pattern '{pattern}': {error}",
-    "rules_file_does_not_exist_alt": "Rules file does not exist: {rules_file}",
-    "image_files_supported": "Image files supported (requires OCR)",
-    "include_image_formats": "Include Image Formats",
-    "include_image_formats_tooltip": "Include image formats (jpg, jpeg, png, gif, bmp, tiff) in scan",
-}
+"""English translation defaults for docscan GUI."""
+
+ENGLISH_DEFAULTS = {
+    "window_title": "Document Scanner GUI",
+    "input_config_tab": "Input Configuration",
+    "scan_options_tab": "Scan Options",
+    "input_directory": "Input Directory:",
+    "browse": "Browse...",
+    "rules_file": "Rules File:",
+    "file_types": "File Types:",
+    "use_pdf_ocr": "Use PDF OCR",
+    "use_process_pool": "Use Process Pool (CPU-intensive)",
+    "threads": "Threads:",
+    "batch_size": "Batch Size:",
+    "start_scan": "Start Scan",
+    "pause": "Pause",
+    "resume": "Resume",
+    "stop": "Stop",
+    "save_results": "Save Results",
+    "clear_results": "Clear Results",
+    "results": "Results",
+    "files_scanned": "Files Scanned:",
+    "files_with_matches": "Files with Matches:",
+    "progress_log": "Progress Log:",
+    "match_details": "Match Details:",
+    "selected_match_context": "Selected Match Context:",
+    "file": "File",
+    "type": "Type",
+    "matches": "Matches",
+    "time": "Time (s)",
+    "select_input_directory": "Select Input Directory",
+    "select_rules_file": "Select Rules File",
+    "json_files": "JSON Files (*.json)",
+    "save_results_dialog": "Save Results",
+    "default_results_filename": "scan_results_{datetime}.json",
+    "error": "Error",
+    "warning": "Warning",
+    "success": "Success",
+    "invalid_input_directory": "Invalid input directory",
+    "no_valid_rules": "No valid rules found",
+    "failed_to_load_rules": "Failed to load rules: {error}",
+    "no_results_to_save": "No results to save",
+    "failed_to_save_results": "Failed to save results: {error}",
+    "scan_failed": "Scan failed: {error}",
+    "starting_scan": "Starting scan...",
+    "scan_complete": "Scan complete!",
+    "pausing_scan": "Pausing scan...",
+    "stopping_scan": "Stopping scan...",
+    "scan_completed": "Scan completed",
+    "scan_stopped": "Scan stopped",
+    "found_matches_files": "Found matches in {count} files",
+    "file_info": "File",
+    "type_info": "Type",
+    "size": "Size",
+    "bytes": "bytes",
+    "rule": "Rule",
+    "description": "Description",
+    "line": "Line {line}: {match}",
+    "context": "Context:",
+    "default_file_types": "pdf,docx,xlsx,pptx,txt,odt,rtf,epub,csv,xml,html,md,jpg,jpeg,png,gif,bmp,tiff",
+    "default_rules_file": "rules.json",
+    "results_saved_to": "Results saved to:\n{path}",
+    "files_scanned_zero": "Files Scanned: 0",
+    "files_with_matches_zero": "Files with Matches: 0",
+    "language_settings": "Language Settings",
+    "processing_options": "Processing Options",
+    "performance_settings": "Performance Settings",
+    "language_label": "Language:",
+    "ocr_tooltip": "Enable OCR for scanned PDF files to extract text from images",
+    "process_pool_tooltip": "Use multiple processes for CPU-intensive operations (may increase memory usage)",
+    "threads_tooltip": "Number of worker threads (higher values may improve speed but use more CPU)",
+    "batch_size_tooltip": "Number of files to process in each batch (larger batches may improve throughput)",
+    "file_types_tooltip": "File types to scan (comma separated)",
+    "file_menu": "&File",
+    "settings_menu": "&Settings",
+    "help_menu": "&Help",
+    "preferences": "&Preferences...",
+    "exit": "E&xit",
+    "about": "&About",
+    "about_title": "About Document Scanner",
+    "about_text": "Document Scanner GUI\n\nVersion 1.0",
+    "language": "Language",
+    "open_results": "Open Results...",
+    "open_results_file": "Open Scan Results",
+    "loaded_results_from": "Loaded results from: {path}",
+    "results_loaded_successfully": "Results loaded successfully from:\n{path}",
+    "failed_to_load_results": "Failed to load results: {error}",
+    # Command-line specific translations
+    "document_scanner_description": "Scan documents and extract text, images, and metadata with certain rules.",
+    "input_directory_help": "Input directory containing documents to scan",
+    "rules_file_help": "Rules file (JSON)",
+    "recursive_help": "Scan files recursively",
+    "file_types_help": "File types to scan (comma-separated)",
+    "use_pdf_ocr_help": "Use PDF OCR for image-based PDFs",
+    "use_process_pool_help": "Use process pool instead of thread pool (better for CPU-intensive tasks)",
+    "batch_size_help": "Number of files to process in each batch",
+    "threads_help": "Number of threads for parallel scanning",
+    "progress_help": "Show progress bar",
+    "verbose_help": "Verbose output",
+    "language_help": "Set language (en for English, zh for Chinese)",
+    # Status and logging messages
+    "scanning_directory": "Scanning directory: {directory}",
+    "found_files_to_scan": "Found {count} files to scan",
+    "scan_resumed": "Scan resumed",
+    "scan_stopped_before_submitting_tasks": "Scan stopped by user before submitting all tasks",
+    "scan_paused": "Scan paused",
+    "scan_stopped_while_paused": "Scan stopped while paused",
+    "scan_stopped_by_user_canceling_tasks": "Scan stopped by user, cancelling remaining tasks...",
+    "task_timeout_scan_may_be_stopping": "Task timeout, scan may be stopping",
+    "error_scanning_file": "Error scanning file: {error}",
+    "progress_report": "Progress: {processed}/{total} files processed",
+    "force_shutting_down_executor": "Force shutting down executor...",
+    "scan_stopped_processed_files": "Scan stopped. Processed {processed} files",
+    "scan_complete_found_matches": "Scan complete. Found matches in {matches_count} files",
+    "found_matches_in_file": "Found matches in: {file_name}",
+    "processed_file_info": "Processed {file_name} ({ext}) in {time:.3f}s - {matches_count} matches found",
+    "could_not_extract_text_from_file": "Could not extract text from {file_path}: {error}",
+    "pymupdf_failed_for_file": "PyMuPDF failed for {file_name}: {error}",
+    "pypdf_also_failed_for_file": "pypdf also failed for {file_name}: {error}",
+    "no_pdf_library_installed": "No PDF library installed (pymupdf or pypdf)",
+    "pymupdf_not_installed": "PyMuPDF not installed",
+    "no_pages_found_in_file": "No pages found in {file_path}",
+    "no_metadata_found_in_file": "No metadata found in {file_path}",
+    "pymupdf_error_trying_fallback": "PyMuPDF error on {file_path}: {error}, trying pypdf fallback",
+    "pypdf_not_installed_skipping_extraction": "pypdf not installed, skipping PDF extraction",
+    "error_extracting_pdf_with_pypdf": "Error extracting PDF with pypdf: {error}",
+    "odfpy_not_installed_skipping_extraction": "odfpy not installed, skipping ODT extraction",
+    "error_extracting_odt": "Error extracting ODT: {error}",
+    "error_extracting_rtf": "Error extracting RTF: {error}",
+    "ebooklib_not_installed_skipping_extraction": "ebooklib not installed, skipping EPUB extraction",
+    "error_extracting_epub": "Error extracting EPUB: {error}",
+    "error_extracting_csv": "Error extracting CSV: {error}",
+    "error_extracting_xml": "Error extracting XML: {error}",
+    "error_extracting_html": "Error extracting HTML: {error}",
+    "error_extracting_markdown": "Error extracting Markdown: {error}",
+    "python_docx_not_installed_skipping_extraction": "python-docx not installed, skipping DOCX extraction",
+    "openpyxl_not_installed_skipping_extraction": "openpyxl not installed, skipping XLSX extraction",
+    "python_pptx_not_installed_skipping_extraction": "python-pptx not installed, skipping PPTX extraction",
+    "pillow_or_tesseract_not_installed_skipping_ocr": "PIL or pytesseract not installed, skipping image OCR",
+    "could_not_perform_ocr_on_file": "Could not perform OCR on {file_path}: {error}",
+    "input_directory_does_not_exist": "Input directory does not exist: {input_dir}",
+    "using_rules_file": "Using rules file: {rules_file}",
+    "invalid_json_in_rules_file": "Invalid JSON in rules file: {error}",
+    "invalid_rules_format": "Invalid rules format. Expected a list or dict with 'rules' key",
+    "no_valid_rules_found": "No valid rules found",
+    "total_time_elapsed": "Total time elapsed: {time:.2f}s",
+    "invalid_regex_pattern": "Invalid regex pattern '{pattern}': {error}",
+    "rules_file_does_not_exist_alt": "Rules file does not exist: {rules_file}",
+    "image_files_supported": "Image files supported (requires OCR)",
+    "include_image_formats": "Include Image Formats",
+    "include_image_formats_tooltip": "Include image formats (jpg, jpeg, png, gif, bmp, tiff) in scan",
+}