splurge-dsv 2025.1.2__py3-none-any.whl → 2025.1.4__py3-none-any.whl

splurge_dsv/__init__.py

@@ -44,7 +44,7 @@ from splurge_dsv.resource_manager import (
 from splurge_dsv.string_tokenizer import StringTokenizer
 from splurge_dsv.text_file_helper import TextFileHelper
 
-__version__ = "2025.1.2"
+__version__ = "2025.1.4"
 __author__ = "Jim Schilling"
 __license__ = "MIT"
 

splurge_dsv/__main__.py

@@ -2,14 +2,14 @@
 Command-line interface entry point for splurge-dsv.
 
 This module serves as the entry point when running the package as a module.
-It imports and calls the main CLI function from the cli module.
+It imports and calls the run_cli function from the cli module.
 """
 
 # Standard library imports
 import sys
 
 # Local imports
-from splurge_dsv.cli import main
+from splurge_dsv.cli import run_cli
 
 if __name__ == "__main__":
-    sys.exit(main())
+    sys.exit(run_cli())

splurge_dsv/cli.py

@@ -4,17 +4,21 @@ Command-line interface for splurge-dsv.
 This module provides a command-line interface for the splurge-dsv library,
 allowing users to parse DSV files from the command line.
 
-Usage:
-    python -m splurge_dsv <file_path> [options]
-    python -m splurge_dsv --help
+Copyright (c) 2025 Jim Schilling
+
+This module is licensed under the MIT License.
+
+Please preserve this header and all related material when sharing!
 """
 
 # Standard library imports
 import argparse
+import json
 import sys
 from pathlib import Path
 
 # Local imports
+from splurge_dsv import __version__
 from splurge_dsv.dsv_helper import DsvHelper
 from splurge_dsv.exceptions import SplurgeDsvError
 
@@ -54,7 +58,14 @@ Examples:
 
     parser.add_argument("--chunk-size", type=int, default=500, help="Chunk size for streaming (default: 500)")
 
-    parser.add_argument("--version", action="version", version="%(prog)s 2025.1.2")
+    parser.add_argument(
+        "--output-format",
+        choices=["table", "json"],
+        default="table",
+        help="Output format for results (default: table)",
+    )
+
+    parser.add_argument("--version", action="version", version=f"%(prog)s {__version__}")
 
     return parser.parse_args()
 
@@ -88,12 +99,29 @@ def print_results(rows: list[list[str]], delimiter: str) -> None:
                 print("-" * (sum(max_widths) + len(max_widths) * 3 - 1))
 
 
-def main() -> int:
-    """Main entry point for the command-line interface."""
+def run_cli() -> int:
+    """Run the command-line interface for DSV file parsing.
+
+    This function serves as the main entry point for the splurge-dsv CLI tool.
+    It parses command-line arguments, validates the input file, and processes
+    DSV files according to the specified options. Supports both regular parsing
+    and streaming modes for large files.
+
+    Returns:
+        int: Exit code indicating success or failure:
+            - 0: Success
+            - 1: Generic error (file not found, parsing error, etc.)
+            - 2: Invalid arguments
+            - 130: Operation interrupted (Ctrl+C)
+
+    Raises:
+        SystemExit: Terminates the program with the appropriate exit code.
+            This is handled internally and should not be caught by callers.
+    """
     try:
         args = parse_arguments()
 
-        # Validate file path
+        # Validate file path (kept local to maintain test compatibility)
         file_path = Path(args.file_path)
         if not file_path.exists():
             print(f"Error: File '{args.file_path}' not found.", file=sys.stderr)
@@ -105,7 +133,8 @@ def main() -> int:
 
         # Parse the file
         if args.stream:
-            print(f"Streaming file '{args.file_path}' with delimiter '{args.delimiter}'...")
+            if args.output_format != "json":
+                print(f"Streaming file '{args.file_path}' with delimiter '{args.delimiter}'...")
             chunk_count = 0
             total_rows = 0
 
@@ -122,13 +151,18 @@ def main() -> int:
             ):
                 chunk_count += 1
                 total_rows += len(chunk)
-                print(f"Chunk {chunk_count}: {len(chunk)} rows")
-                print_results(chunk, args.delimiter)
-                print()
-
-            print(f"Total: {total_rows} rows in {chunk_count} chunks")
+                if args.output_format == "json":
+                    print(json.dumps(chunk, ensure_ascii=False))
+                else:
+                    print(f"Chunk {chunk_count}: {len(chunk)} rows")
+                    print_results(chunk, args.delimiter)
+                    print()
+
+            if args.output_format != "json":
+                print(f"Total: {total_rows} rows in {chunk_count} chunks")
         else:
-            print(f"Parsing file '{args.file_path}' with delimiter '{args.delimiter}'...")
+            if args.output_format != "json":
+                print(f"Parsing file '{args.file_path}' with delimiter '{args.delimiter}'...")
             rows = DsvHelper.parse_file(
                 file_path,
                 delimiter=args.delimiter,
@@ -140,8 +174,11 @@ def main() -> int:
                 skip_footer_rows=args.skip_footer,
             )
 
-            print(f"Parsed {len(rows)} rows")
-            print_results(rows, args.delimiter)
+            if args.output_format == "json":
+                print(json.dumps(rows, ensure_ascii=False))
+            else:
+                print(f"Parsed {len(rows)} rows")
+                print_results(rows, args.delimiter)
 
         return 0
 

splurge_dsv/path_validator.py

@@ -198,7 +198,7 @@ class PathValidator:
             False otherwise
         """
         # Must be C: at the end of the string, or C:\ (or C:/) followed by path
-        return re.match(r"^[A-Za-z]:$", path_str) or re.match(r"^[A-Za-z]:[\\/]", path_str)
+        return bool(re.match(r"^[A-Za-z]:$", path_str)) or bool(re.match(r"^[A-Za-z]:[\\/]", path_str))
 
     @classmethod
     def _check_dangerous_characters(cls, path_str: str) -> None:

{splurge_dsv-2025.1.2.dist-info → splurge_dsv-2025.1.4.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: splurge-dsv
-Version: 2025.1.2
+Version: 2025.1.4
 Summary: A utility library for working with DSV (Delimited String Values) files
 Author: Jim Schilling
 License-Expression: MIT
@@ -53,8 +53,8 @@ A robust Python library for parsing and processing delimited-separated value (DS
 - **Error Recovery**: Graceful error handling with detailed error messages
 
 ### 🧪 Testing & Quality
-- **Comprehensive Test Suite**: 90%+ code coverage with 250+ tests
-- **Cross-Platform Support**: Tested on Windows, Linux, and macOS
+- **Comprehensive Test Suite**: 250+ tests with 85%+ coverage gate
+- **Cross-Platform Support**: Tested on Windows, and should pass on Linux and macOS
 - **Type Safety**: Full type annotations and validation
 - **Documentation**: Complete API documentation with examples
 
@@ -238,97 +238,22 @@ The project follows strict coding standards:
 - PEP 8 compliance
 - Type annotations for all functions
 - Google-style docstrings
-- 90%+ test coverage requirement
+- 85%+ coverage gate enforced via CI
 - Comprehensive error handling
 
 ## Changelog
 
-### 2025.1.2 (2025-09-02)
-
-#### 🧪 Comprehensive End-to-End Testing
-- **Complete E2E Test Suite**: Implemented 25 comprehensive end-to-end workflow tests covering all major CLI functionality
-- **Real CLI Execution**: Tests run actual `splurge-dsv` commands with real files, not just mocked components
-- **Workflow Coverage**: Tests cover CSV/TSV parsing, file operations, data processing, error handling, and performance scenarios
-- **Cross-Platform Compatibility**: Handles Windows-specific encoding issues and platform differences gracefully
-- **Performance Testing**: Large file processing tests (1,000+ and 10,000+ rows) with streaming and chunking validation
-
-#### 📊 Test Coverage Improvements
-- **CLI Coverage**: Increased from 64% to **95%** with comprehensive CLI workflow testing
-- **DSV Helper Coverage**: Improved from 75% to **93%** with real-world usage scenarios
-- **Overall Coverage**: Improved from 60% to **73%** across the entire codebase
-- **Integration Testing**: Added real file system operations and complete pipeline validation
-
-#### 🔄 Test Categories
-- **CLI Workflows**: 19 tests covering basic parsing, custom delimiters, header/footer skipping, streaming, and error scenarios
-- **Error Handling**: 3 tests for invalid arguments, missing parameters, and CLI error conditions
-- **Integration Scenarios**: 3 tests for data analysis, transformation, and multi-format workflows
-
-#### 📚 Documentation & Examples
-- **E2E Testing Guide**: Created comprehensive documentation (`docs/e2e_testing_coverage.md`) explaining test coverage and usage
-- **Real-World Examples**: Tests serve as practical examples of library usage patterns
-- **Error Scenario Coverage**: Comprehensive testing of edge cases and failure conditions
-
-### 2025.1.1 (2025-08-XX)
-
-#### 🔧 Code Quality Improvements
-- **Refactored Complex Regex Logic**: Extracted Windows drive letter validation logic from `_check_dangerous_characters` into a dedicated `_is_valid_windows_drive_pattern` helper method in `PathValidator` for better readability and maintainability
-- **Exception Handling Consistency**: Fixed inconsistency in `ResourceManager.acquire()` method to properly re-raise `NotImplementedError` without wrapping it in `SplurgeResourceAcquisitionError`
-- **Import Organization**: Moved all imports to the top of modules across the entire codebase for better code structure and PEP 8 compliance
-
-#### 🧪 Testing Enhancements
-- **Public API Focus**: Removed all tests that validated private implementation details, focusing exclusively on public API behavior validation
-- **Comprehensive Resource Manager Tests**: Added extensive test suite for `ResourceManager` module covering all public methods, edge cases, error scenarios, and context manager behavior
-- **Bookend Logic Clarification**: Updated and corrected all tests related to `StringTokenizer.remove_bookends` to properly reflect its single-character, symmetric bookend matching behavior
-- **Path Validation Test Clarity**: Clarified test expectations and comments for Windows drive-relative paths (e.g., "C:file.txt") to reflect the validator's intentionally strict security design
-
-#### 🐛 Bug Fixes
-- **Test Reliability**: Fixed failing tests in `ResourceManager` context manager scenarios by properly handling file truncation and line ending normalization
-- **Ruff Compliance**: Resolved all linting warnings including unused variables and imports
-
-#### 📚 Documentation Updates
-- **Method Documentation**: Updated `ResourceManager.acquire()` docstring to include `NotImplementedError` in the Raises section
-- **Test Comments**: Enhanced test documentation with clearer explanations of expected behaviors and edge cases
-
-### 2025.1.0 (2025-08-25)
-
-#### 🎉 Major Features
-- **Complete DSV Parser**: Full-featured delimited-separated value parser with support for CSV, TSV, and custom delimiters
-- **Streaming Support**: Memory-efficient streaming for large files with configurable chunk sizes
-- **Advanced Parsing Options**: Bookend removal, whitespace handling, and encoding support
-- **Header/Footer Skipping**: Skip specified numbers of rows from start or end of files
-
-#### 🛡️ Security Enhancements
-- **Path Validation System**: Comprehensive file path security validation with traversal attack prevention
-- **File Permission Checks**: Automatic file accessibility and permission validation
-- **Encoding Validation**: Robust encoding error detection and handling
-
-#### 🔧 Core Components
-- **DsvHelper**: Main DSV parsing class with parse, parses, parse_file, and parse_stream methods
-- **TextFileHelper**: Utility class for text file operations (line counting, preview, reading, streaming)
-- **PathValidator**: Security-focused path validation utilities
-- **ResourceManager**: Context managers for safe resource handling
-- **StringTokenizer**: Core string parsing functionality
-
-#### 🧪 Testing & Quality
-- **Comprehensive Test Suite**: 250+ tests with 90%+ code coverage
-- **Cross-Platform Testing**: Tested on Windows, Linux, and macOS
-- **Type Safety**: Full type annotations throughout the codebase
-- **Error Handling**: Custom exception hierarchy with detailed error messages
-
-#### 📚 Documentation
-- **Complete API Documentation**: Google-style docstrings for all public methods
-- **Usage Examples**: Comprehensive examples for all major features
-- **Error Documentation**: Detailed error handling documentation
-
-#### 🚀 Performance
-- **Memory Efficiency**: Streaming support for large files
-- **Optimized Parsing**: Efficient string tokenization and processing
-- **Resource Management**: Automatic cleanup and resource management
+See the [CHANGELOG](CHANGELOG.md) for full release notes.
 
 ## License
 
 This project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.
 
+## More Documentation
+
+- Detailed docs: [docs/README-details.md](docs/README-details.md)
+- E2E testing coverage: [docs/e2e_testing_coverage.md](docs/e2e_testing_coverage.md)
+
 ## Contributing
 
 Contributions are welcome! Please feel free to submit a Pull Request. For major changes, please open an issue first to discuss what you would like to change.

splurge_dsv-2025.1.4.dist-info/RECORD

@@ -0,0 +1,14 @@
+splurge_dsv/__init__.py,sha256=I_BAM3zHWRZLyY5ndCweBCg1w_cbBDZhdKlxUp6Sx8Q,2415
+splurge_dsv/__main__.py,sha256=CX8zVMaK6vaaCaC396FyXA1E_-jqKz4zh3CVW8mGKac,359
+splurge_dsv/cli.py,sha256=hcoF2OC3gHrN4SegSUFQeGxHuWWIBAJn-fTNW19KnyA,7261
+splurge_dsv/dsv_helper.py,sha256=VRq2ejx6y-JBtFKJdAaK-GD4V0eoxZZfmoX0I3CSbDI,9428
+splurge_dsv/exceptions.py,sha256=cu9Jd2pGhy7GBbbngH6zs0lfZzLp_OvGwbnsG5khp80,3035
+splurge_dsv/path_validator.py,sha256=RuRFjtHWE1Z5-DlSBBZMoHJegQEFYEQ0HJgN7ndre2k,9969
+splurge_dsv/resource_manager.py,sha256=g4igv1hhJdPtw4A1P-WdaNKcYMfEGCtZ4xaU4ynVbKw,12045
+splurge_dsv/string_tokenizer.py,sha256=wBKWdi68rreTqf3RF-8Oxh1nz6QdnbOyWflw2x8pGWY,4022
+splurge_dsv/text_file_helper.py,sha256=vdhEv9uK0hsNXvTO5SoWwFsI9fPkhdIUXuaJs80DVDA,13573
+splurge_dsv-2025.1.4.dist-info/licenses/LICENSE,sha256=fPgtg-tIFHinQvJH0arRfv50AuxikD5eHw6rrPy2A5w,1091
+splurge_dsv-2025.1.4.dist-info/METADATA,sha256=sxdtsP6DfbVRkdVx6LcgcH23DEguS01gniAzN9ELlZM,8573
+splurge_dsv-2025.1.4.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+splurge_dsv-2025.1.4.dist-info/top_level.txt,sha256=D6Si3FTfpRYqH7kzM7tSQAyaKbbraO6UPLpcqcY4XXM,12
+splurge_dsv-2025.1.4.dist-info/RECORD,,

splurge_dsv-2025.1.2.dist-info/RECORD

@@ -1,14 +0,0 @@
-splurge_dsv/__init__.py,sha256=UBfew2IVQhg5VbHjTe_O7e2b1QeoYen_so--4B6p0h4,2415
-splurge_dsv/__main__.py,sha256=RkXcU3P3tHpFa6iGJfx8sAZ4aUcz6z7TIN_1q_5N9xE,354
-splurge_dsv/cli.py,sha256=tRIQT0InflJPzy8SGUaHyD0aPMr7CgmyHbSVRkaQeoo,5759
-splurge_dsv/dsv_helper.py,sha256=VRq2ejx6y-JBtFKJdAaK-GD4V0eoxZZfmoX0I3CSbDI,9428
-splurge_dsv/exceptions.py,sha256=cu9Jd2pGhy7GBbbngH6zs0lfZzLp_OvGwbnsG5khp80,3035
-splurge_dsv/path_validator.py,sha256=R314U2TmQjYVe_KOv4ni08z1_tLuo4_Uuld__dhX_gw,9957
-splurge_dsv/resource_manager.py,sha256=g4igv1hhJdPtw4A1P-WdaNKcYMfEGCtZ4xaU4ynVbKw,12045
-splurge_dsv/string_tokenizer.py,sha256=wBKWdi68rreTqf3RF-8Oxh1nz6QdnbOyWflw2x8pGWY,4022
-splurge_dsv/text_file_helper.py,sha256=vdhEv9uK0hsNXvTO5SoWwFsI9fPkhdIUXuaJs80DVDA,13573
-splurge_dsv-2025.1.2.dist-info/licenses/LICENSE,sha256=fPgtg-tIFHinQvJH0arRfv50AuxikD5eHw6rrPy2A5w,1091
-splurge_dsv-2025.1.2.dist-info/METADATA,sha256=z0qLKtJ0Y8PgVhstBLpVUTATsWRQEv-GI34aaJOxbfs,14021
-splurge_dsv-2025.1.2.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-splurge_dsv-2025.1.2.dist-info/top_level.txt,sha256=D6Si3FTfpRYqH7kzM7tSQAyaKbbraO6UPLpcqcY4XXM,12
-splurge_dsv-2025.1.2.dist-info/RECORD,,