pysfi 0.1.6__py3-none-any.whl → 0.1.10__py3-none-any.whl

sfi/docscan/lang/eng.py

@@ -0,0 +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",
+}

sfi/docscan/lang/zhcn.py

@@ -0,0 +1,170 @@
+"""Chinese translations for docscan_gui."""
+
+TRANSLATIONS = {
+    # Window and Tab Titles
+    "window_title": "文档扫描器",
+    "input_config_tab": "输入配置",
+    "scan_options_tab": "扫描选项",
+    # Input Section
+    "input_directory": "输入目录:",
+    "browse": "浏览...",
+    "rules_file": "规则文件:",
+    "file_types": "文件类型:",
+    # Options Section
+    "use_pdf_ocr": "使用 PDF OCR",
+    "use_process_pool": "使用进程池 (CPU 密集型)",
+    "threads": "线程数:",
+    "batch_size": "批处理大小:",
+    # Action Buttons
+    "start_scan": "开始扫描",
+    "pause": "暂停",
+    "resume": "恢复",
+    "stop": "停止",
+    "save_results": "保存结果",
+    "clear_results": "清除结果",
+    # Results Section
+    "results": "结果",
+    "files_scanned": "已扫描文件:",
+    "files_with_matches": "包含匹配项的文件:",
+    "progress_log": "进度日志:",
+    "match_details": "匹配详情:",
+    "selected_match_context": "选中匹配项的上下文:",
+    # Table Headers
+    "file": "文件",
+    "type": "类型",
+    "matches": "匹配数",
+    "time": "时间 (s)",
+    # Dialogs and Messages
+    "select_input_directory": "选择输入目录",
+    "select_rules_file": "选择规则文件",
+    "json_files": "JSON 文件 (*.json)",
+    "save_results_dialog": "保存结果",
+    "default_results_filename": "扫描结果_{datetime}.json",
+    # Error Messages
+    "error": "错误",
+    "warning": "警告",
+    "success": "成功",
+    "invalid_input_directory": "无效的输入目录",
+    "no_valid_rules": "没有找到有效的规则",
+    "failed_to_load_rules": "加载规则失败: {error}",
+    "no_results_to_save": "没有可保存的结果",
+    "failed_to_save_results": "保存结果失败: {error}",
+    "scan_failed": "扫描失败: {error}",
+    # Progress Messages
+    "starting_scan": "开始扫描...",
+    "scan_complete": "扫描完成!",
+    "pausing_scan": "暂停扫描...",
+    "stopping_scan": "停止扫描...",
+    "scan_completed": "扫描完成",
+    "scan_stopped": "扫描已停止",
+    "scan_resumed": "扫描已恢复",
+    "found_matches_files": "在 {count} 个文件中找到匹配项",
+    # File Info
+    "file_info": "文件",
+    "type_info": "类型",
+    "size": "大小",
+    "bytes": "字节",
+    # Match Info
+    "rule": "规则",
+    "description": "描述",
+    "line": "行 {line}: {match}",
+    "context": "上下文",
+    "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",
+    # Menu Items
+    "file_menu": "文件(&F)",
+    "settings_menu": "设置(&S)",
+    "help_menu": "帮助(&H)",
+    "preferences": "首选项(&P)...",
+    "exit": "退出(&X)",
+    "about": "关于(&A)",
+    "about_title": "关于文档扫描器",
+    "about_text": "文档扫描器 GUI\n\n版本 1.0",
+    "language": "语言",
+    # Open Results
+    "open_results": "打开结果...",
+    "open_results_file": "打开扫描结果",
+    "loaded_results_from": "已从以下位置加载结果: {path}",
+    "results_loaded_successfully": "结果已成功从以下位置加载:\n{path}",
+    "failed_to_load_results": "加载结果失败: {error}",
+    # Settings Dialog
+    "language_settings": "语言设置",
+    "processing_options": "处理选项",
+    "performance_settings": "性能设置",
+    "language_label": "语言:",
+    "ocr_tooltip": "为扫描的 PDF 文件启用 OCR 以从图像中提取文本",
+    "process_pool_tooltip": "对 CPU 密集型操作使用多进程（可能会增加内存使用）",
+    "threads_tooltip": "工作线程数量（较高的值可能会提高速度但会使用更多 CPU）",
+    "batch_size_tooltip": "每批处理的文件数量（较大的批次可能会提高吞吐量）",
+    "file_types_tooltip": "要扫描的文件类型（逗号分隔）",
+    # Results Saved Message
+    "results_saved_to": "结果已保存至:\t{path}",
+    # Default Values
+    "files_scanned_zero": "已扫描文件: 0",
+    "files_with_matches_zero": "包含匹配项的文件: 0",
+    # Apply Button
+    "apply": "应用",
+    # Command-line specific translations
+    "document_scanner_description": "扫描文档并使用特定规则提取文本、图像和元数据。",
+    "input_directory_help": "包含待扫描文档的输入目录",
+    "rules_file_help": "规则文件 (JSON格式)",
+    "recursive_help": "递归扫描文件",
+    "file_types_help": "要扫描的文件类型（逗号分隔）",
+    "use_pdf_ocr_help": "对基于图像的PDF文件使用OCR",
+    "use_process_pool_help": "使用进程池而非线程池（更适合CPU密集型任务）",
+    "batch_size_help": "每批次处理的文件数量",
+    "threads_help": "并行扫描的线程数",
+    "progress_help": "显示进度条",
+    "verbose_help": "详细输出",
+    "language_help": "设置语言（en表示英文，zh表示中文）",
+    # Status and logging messages
+    "scanning_directory": "正在扫描目录: {directory}",
+    "found_files_to_scan": "发现 {count} 个文件待扫描",
+    "scan_stopped_before_submitting_tasks": "用户在提交所有任务之前停止扫描",
+    "scan_paused": "扫描已暂停",
+    "scan_stopped_while_paused": "扫描在暂停状态下停止",
+    "scan_stopped_by_user_canceling_tasks": "用户停止扫描，正在取消剩余任务...",
+    "task_timeout_scan_may_be_stopping": "任务超时，扫描可能正在停止",
+    "error_scanning_file": "扫描文件时出错: {error}",
+    "progress_report": "进度: {processed}/{total} 文件已处理",
+    "force_shutting_down_executor": "强制关闭执行器...",
+    "scan_stopped_processed_files": "扫描已停止。已处理 {processed} 个文件",
+    "scan_complete_found_matches": "扫描完成。在 {matches_count} 个文件中找到匹配项",
+    "found_matches_in_file": "找到匹配项: {file_name}",
+    "processed_file_info": "已处理 {file_name} ({ext})，耗时 {time:.3f}秒 - 找到 {matches_count} 个匹配项",
+    "could_not_extract_text_from_file": "无法从 {file_path} 提取文本: {error}",
+    "pymupdf_failed_for_file": "{file_name} 的 PyMuPDF 失败: {error}",
+    "pypdf_also_failed_for_file": "{file_name} 的 pypdf 也失败: {error}",
+    "no_pdf_library_installed": "未安装PDF库 (pymupdf 或 pypdf)",
+    "pymupdf_not_installed": "未安装 PyMuPDF",
+    "no_pages_found_in_file": "在 {file_path} 中未找到页面",
+    "no_metadata_found_in_file": "在 {file_path} 中未找到元数据",
+    "pymupdf_error_trying_fallback": "PyMuPDF 在 {file_path} 上出错: {error}，尝试使用 pypdf 回退",
+    "pypdf_not_installed_skipping_extraction": "未安装 pypdf，跳过PDF提取",
+    "error_extracting_pdf_with_pypdf": "使用 pypdf 提取PDF时出错: {error}",
+    "odfpy_not_installed_skipping_extraction": "未安装 odfpy，跳过ODT提取",
+    "error_extracting_odt": "提取ODT时出错: {error}",
+    "error_extracting_rtf": "提取RTF时出错: {error}",
+    "ebooklib_not_installed_skipping_extraction": "未安装 ebooklib，跳过EPUB提取",
+    "error_extracting_epub": "提取EPUB时出错: {error}",
+    "error_extracting_csv": "提取CSV时出错: {error}",
+    "error_extracting_xml": "提取XML时出错: {error}",
+    "error_extracting_html": "提取HTML时出错: {error}",
+    "error_extracting_markdown": "提取Markdown时出错: {error}",
+    "python_docx_not_installed_skipping_extraction": "未安装 python-docx，跳过DOCX提取",
+    "openpyxl_not_installed_skipping_extraction": "未安装 openpyxl，跳过XLSX提取",
+    "python_pptx_not_installed_skipping_extraction": "未安装 python-pptx，跳过PPTX提取",
+    "pillow_or_tesseract_not_installed_skipping_ocr": "未安装 PIL 或 pytesseract，跳过图像OCR",
+    "could_not_perform_ocr_on_file": "无法对 {file_path} 执行OCR: {error}",
+    "input_directory_does_not_exist": "输入目录不存在: {input_dir}",
+    "using_rules_file": "使用规则文件: {rules_file}",
+    "invalid_json_in_rules_file": "规则文件中的JSON无效: {error}",
+    "invalid_rules_format": "无效的规则格式。期望包含'rules'键的列表或字典",
+    "no_valid_rules_found": "未找到有效规则",
+    "total_time_elapsed": "总耗时: {time:.2f}秒",
+    "invalid_regex_pattern": "无效的正则表达式模式 '{pattern}': {error}",
+    "rules_file_does_not_exist_alt": "规则文件不存在: {rules_file}",
+    "image_files_supported": "支持的图像文件（需要OCR）",
+    "include_image_formats": "包含图像格式",
+    "include_image_formats_tooltip": "在扫描中包含图像格式（jpg, jpeg, png, gif, bmp, tiff）",
+}

sfi/embedinstall/embedinstall.py

@@ -31,6 +31,9 @@ logging.basicConfig(level=logging.INFO, format="%(message)s")
 cwd = Path.cwd()
 logger = logging.getLogger(__name__)
 
+# Default cache directory
+DEFAULT_CACHE_DIR = Path.home() / ".pysfi" / ".cache" / "embed-python"
+
 
 def get_system_arch(manual_arch: str | None = None) -> str:
     """Get system architecture for Python embeddable package."""
@@ -61,12 +64,13 @@ def get_official_url_template(arch: str) -> str:
     return f"https://www.python.org/ftp/python/{{version}}/python-{{version}}-embed-{arch}.zip"
 
 
-def get_latest_patch_version(major_minor: str, arch: str, timeout: int = 5) -> str:
+def get_latest_patch_version(major_minor: str, arch: str, cache_dir: Path, timeout: int = 5) -> str:
     """Get the latest patch version for a given major.minor version.
 
     Args:
         major_minor: Major.minor version (e.g., '3.13') or full version (e.g., '3.13.1')
         arch: Architecture (amd64 or arm64)
+        cache_dir: Cache directory to check for cached versions
         timeout: Request timeout in seconds
 
     Returns:
@@ -83,10 +87,30 @@ def get_latest_patch_version(major_minor: str, arch: str, timeout: int = 5) -> s
         logger.debug(f"Invalid version format: {major_minor}, using as: `3.13.5`")
         return major_minor
 
+    major, minor = major_minor.split(".")
+
+    # Check cache for any cached version matching the major.minor
+    if cache_dir.exists():
+        cached_versions = []
+        for cache_file in cache_dir.glob(f"python-{major}.{minor}.*-embed-{arch}.zip"):
+            try:
+                # Extract version from filename
+                match = cache_file.stem.replace("python-", "").replace(f"-embed-{arch}", "")
+                if match:
+                    cached_versions.append((match, cache_file))
+            except Exception:
+                pass
+
+        if cached_versions:
+            # Return the highest cached version
+            cached_versions.sort(key=lambda x: x[0], reverse=True)
+            latest_cached = cached_versions[0][0]
+            logger.info(f"Using cached version: {latest_cached}")
+            return latest_cached
+
     logger.info(f"Checking latest version for {major_minor}...")
 
     base_url = get_official_url_template(arch)
-    major, minor = major_minor.split(".")
 
     # Try from highest patch number down to 0
     for patch in range(20, -1, -1):
@@ -261,12 +285,21 @@ def install_embed_python(
     version_filename = f"python-{version}-embed-{arch}.zip"
     cache_file = cache_dir / version_filename
 
+    # Check if cached file exists and is valid
     if cache_file.exists():
-        logger.debug(f"Using cached file: {cache_file}")
-    elif offline:
-        logger.error(f"Offline mode: no cached file found for version {version}")
-        return False
-    else:
+        if not zipfile.is_zipfile(cache_file):
+            logger.warning(f"Corrupted cache file detected: {cache_file}")
+            logger.info("Deleting corrupted cache file and re-downloading...")
+            cache_file.unlink()
+        else:
+            logger.debug(f"Using cached file: {cache_file}")
+
+    # Download if cache file doesn't exist or was corrupted
+    if not cache_file.exists():
+        if offline:
+            logger.error(f"Offline mode: no cached file found for version {version}")
+            return False
+
         if skip_speed_test:
             url = get_official_url_template(arch).format(version=version)
             logger.info(f"Skipping speed test, using official URL: {url}")
@@ -279,6 +312,13 @@ def install_embed_python(
             try:
                 logger.info(f"Attempting download {i}/{len(urls)}: {url}")
                 download_with_progress(url, cache_file)
+
+                # Validate downloaded file
+                if not zipfile.is_zipfile(cache_file):
+                    logger.warning("Downloaded file is corrupted, trying next URL...")
+                    cache_file.unlink()
+                    continue
+
                 download_success = True
                 break
             except URLError as e:
@@ -296,11 +336,32 @@ def install_embed_python(
             return False
 
     try:
+        # Final validation before extraction
+        if not zipfile.is_zipfile(cache_file):
+            logger.error(f"Invalid zip file: {cache_file}")
+            return False
+
         extract_zip(cache_file, target_dir)
-    except zipfile.BadZipFile:
-        logger.error(f"Invalid zip file: {cache_file}")
+    except zipfile.BadZipFile as e:
+        logger.error(f"Corrupted zip file: {cache_file}")
+        logger.error(f"Error: {e}")
+        # Delete corrupted file and try to re-download in the next run
         if not keep_cache:
+            logger.info("Deleting corrupted cache file...")
             cache_file.unlink()
+            # Retry download if not offline
+            if not offline:
+                logger.info("Attempting to re-download...")
+                return install_embed_python(
+                    target_dir=target_dir,
+                    version=version,
+                    cache_dir=cache_dir,
+                    offline=offline,
+                    keep_cache=keep_cache,
+                    skip_speed_test=skip_speed_test,
+                    arch=arch,
+                    timeout=timeout,
+                )
         return False
     except Exception as e:
         logger.error(f"Failed to extract: {e}")
@@ -326,10 +387,10 @@ def main() -> None:
         description="Download and install Python embeddable package to a specific directory.",
     )
     parser.add_argument(
-        "--directory",
-        "-D",
+        "directory",
         type=str,
-        default=str(cwd / "runtime"),
+        nargs="?",
+        default=str(cwd / "dist" / "runtime"),
         help="Directory to install Python embeddable package (default: current directory)",
     )
     parser.add_argument("--debug", "-d", action="store_true", help="Enable debug mode")
@@ -350,7 +411,7 @@ def main() -> None:
         "--cache-dir",
         "-C",
         type=str,
-        default=str(cwd / ".cache" / "embedinstall"),
+        default=str(DEFAULT_CACHE_DIR),
         help="Cache directory for downloaded files",
     )
     parser.add_argument(
@@ -384,17 +445,16 @@ def main() -> None:
 
     if args.debug:
         logger.setLevel(logging.DEBUG)
-    else:
-        logger.setLevel(logging.INFO)
 
     target_dir = Path(args.directory)
-    cache_dir = Path(args.cache_dir)
+    target_dir.mkdir(parents=True, exist_ok=True)
 
+    cache_dir = Path(args.cache_dir)
     t0 = time.perf_counter()
     arch = get_system_arch(args.arch)
 
     # Auto-complete version if only major.minor is provided
-    version = get_latest_patch_version(args.version, arch, args.timeout)
+    version = get_latest_patch_version(args.version, arch, cache_dir, args.timeout)
     if "." not in version:
         return
 

sfi/makepython/makepython.py

@@ -1,7 +1,6 @@
 from __future__ import annotations
 
 import argparse
-import json
 import logging
 import os
 import shutil
@@ -9,6 +8,7 @@ import subprocess
 import sys
 from dataclasses import dataclass
 from pathlib import Path
+from typing import Any, Callable
 
 if sys.version_info >= (3, 11):
     import tomllib
@@ -34,8 +34,12 @@ def parse_pyproject_toml(directory: Path) -> dict:
         logger.error(f"No pyproject.toml found in {directory}")
         return {}
 
-    with project_toml.open("rb") as f:
-        return tomllib.load(f)
+    try:
+        with project_toml.open("rb") as f:
+            return tomllib.load(f)
+    except Exception as e:
+        logger.error(f"Error parsing pyproject.toml: {e}")
+        return {}
 
 
 def _get_build_command_from_toml(directory: Path) -> str | None:
@@ -58,8 +62,7 @@ def _get_build_command_from_toml(directory: Path) -> str | None:
                 logger.error(f"Unknown build-backend: {build_backend}")
                 return None
 
-    logger.error("No `build-system` or `build-backend` found in pyproject.toml: ")
-    logger.error(json.dumps(project_data, indent=2, ensure_ascii=False, sort_keys=True))
+    logger.error("No `build-system` or `build-backend` found in pyproject.toml")
     return None
 
 
@@ -83,42 +86,56 @@ def _get_build_command(directory: Path):
 class Command:
     name: str
     alias: str
+    cmds: list[str] | Callable[..., Any] | None = None
 
 
-_COMMANDS = [
-    Command(name="build", alias="b"),
-    Command(name="bumpversion", alias="bump"),
-    Command(name="clean", alias="c"),
-    Command(name="publish", alias="p"),
-    Command(name="token", alias="tk"),
-]
-_CHOICES = [command.alias for command in _COMMANDS]
-_CHOICES.extend([command.name for command in _COMMANDS])
+def _clean(root_dir: Path = cwd):
+    _run_command(["rm", "-rf", "dist", "build", "*.egg-info"], root_dir)
 
 
 def main():
+    # Get build command
+    build_command = _get_build_command(cwd) or ""
+    commands = [
+        Command(name="build", alias="b", cmds=[build_command, "build"]),
+        Command(name="bumpversion", alias="bump", cmds=["bumpversion", "patch", "--tag"]),
+        Command(name="clean", alias="c", cmds=_clean),
+        Command(name="publish", alias="p"),  # No preset commands
+        Command(name="test", alias="t", cmds=lambda: os.system("pytest")),
+        Command(name="test-benchmark", alias="tb", cmds=lambda: os.system("pytest -m benchmark")),
+        Command(name="test-coverage", alias="tc", cmds=lambda: os.system("pytest --cov=sfi")),
+        Command(name="token", alias="tk", cmds=lambda: _set_token(build_command)),
+    ]
+    command_dict = {command.name: command for command in commands}
+    command_dict.update({command.alias: command for command in commands})
+    choices = [command.alias for command in commands]
+    choices.extend([command.name for command in commands])
+
+    # Parse args
     parser = argparse.ArgumentParser(description="Make Python")
-    parser.add_argument("command", type=str, choices=_CHOICES, help=f"Command to run, options: {_CHOICES}")
     parser.add_argument("--debug", "-d", action="store_true", help="Enable debug mode")
-
+    parser.add_argument("command", type=str, choices=choices, help=f"Command to run, options: {choices}")
     args = parser.parse_args()
     if args.debug:
         logger.setLevel(logging.DEBUG)
 
-    build_command = _get_build_command(cwd) or ""
-    logger.info(f"Using build command: {build_command}")
-    if args.command in {"build", "b"}:
-        _run_command([build_command, "build"], cwd)
-    elif args.command in {"bump", "bumpversion"}:
-        _run_command(["bumpversion", "patch"], cwd)
-    elif args.command in {"clean", "c"}:
-        _run_command(["rm", "-rf", "dist", "build", "*.egg-info"], cwd)
-    elif args.command in {"publish", "p"}:
+    logger.debug(f"Using build command: {build_command}")
+    command = command_dict.get(args.command)
+    if command:
+        if callable(command.cmds):
+            command.cmds()
+        elif isinstance(command.cmds, list):
+            _run_command(command.cmds, cwd)
+        else:
+            logger.debug("No preset commands found")
+    else:
+        logger.error(f"Unknown command: {args.command}")
+        sys.exit(1)
+
+    if args.command in {"publish", "p"}:
         if not _check_pypi_token(build_command):
             _set_token(build_command)
         _run_command([build_command, "publish"], cwd)
-    elif args.command in {"token", "tk"}:
-        _set_token(build_command)
 
 
 def _set_token(build_command: str, show_header: bool = True) -> None: