splurge-dsv 2025.1.0__py3-none-any.whl → 2025.1.2__py3-none-any.whl

splurge_dsv/text_file_helper.py

@@ -22,15 +22,14 @@ Please preserve this header and all related material when sharing!
 This module is licensed under the MIT License.
 """
 
+# Standard library imports
 from collections import deque
+from collections.abc import Iterator
 from os import PathLike
 from pathlib import Path
-from typing import Iterator
 
-from splurge_dsv.exceptions import (
-    SplurgeParameterError,
-    SplurgeFileEncodingError
-)
+# Local imports
+from splurge_dsv.exceptions import SplurgeFileEncodingError, SplurgeParameterError
 from splurge_dsv.path_validator import PathValidator
 from splurge_dsv.resource_manager import safe_file_operation
 
@@ -51,12 +50,7 @@ class TextFileHelper:
     DEFAULT_MODE = "r"
 
     @classmethod
-    def line_count(
-        cls,
-        file_path: PathLike[str] | str,
-        *,
-        encoding: str = DEFAULT_ENCODING
-    ) -> int:
+    def line_count(cls, file_path: PathLike[str] | str, *, encoding: str = DEFAULT_ENCODING) -> int:
         """
         Count the number of lines in a text file.
 
@@ -78,12 +72,9 @@ class TextFileHelper:
         """
         # Validate file path
         validated_path = PathValidator.validate_path(
-            Path(file_path),
-            must_exist=True,
-            must_be_file=True,
-            must_be_readable=True
+            Path(file_path), must_exist=True, must_be_file=True, must_be_readable=True
         )
-        
+
         with safe_file_operation(validated_path, encoding=encoding, mode=cls.DEFAULT_MODE) as stream:
             return sum(1 for _ in stream)
 
@@ -95,7 +86,7 @@ class TextFileHelper:
         max_lines: int = DEFAULT_MAX_LINES,
         strip: bool = DEFAULT_STRIP,
         encoding: str = DEFAULT_ENCODING,
-        skip_header_rows: int = DEFAULT_SKIP_HEADER_ROWS
+        skip_header_rows: int = DEFAULT_SKIP_HEADER_ROWS,
     ) -> list[str]:
         """
         Preview the first N lines of a text file.
@@ -122,34 +113,30 @@ class TextFileHelper:
         """
         if max_lines < 1:
             raise SplurgeParameterError(
-                "TextFileHelper.preview: max_lines is less than 1",
-                details="max_lines must be at least 1"
+                "TextFileHelper.preview: max_lines is less than 1", details="max_lines must be at least 1"
             )
-               
+
         # Validate file path
         validated_path = PathValidator.validate_path(
-            Path(file_path),
-            must_exist=True,
-            must_be_file=True,
-            must_be_readable=True
+            Path(file_path), must_exist=True, must_be_file=True, must_be_readable=True
         )
-        
+
         skip_header_rows = max(skip_header_rows, cls.DEFAULT_SKIP_HEADER_ROWS)
         lines: list[str] = []
-        
+
         with safe_file_operation(validated_path, encoding=encoding, mode=cls.DEFAULT_MODE) as stream:
             # Skip header rows
             for _ in range(skip_header_rows):
                 if not stream.readline():
                     return lines
-            
+
             # Read up to max_lines after skipping headers
             for _ in range(max_lines):
                 line = stream.readline()
                 if not line:
                     break
                 lines.append(line.strip() if strip else line.rstrip("\n"))
-        
+
         return lines
 
     @classmethod
@@ -161,7 +148,7 @@ class TextFileHelper:
         encoding: str = DEFAULT_ENCODING,
         skip_header_rows: int = DEFAULT_SKIP_HEADER_ROWS,
         skip_footer_rows: int = DEFAULT_SKIP_FOOTER_ROWS,
-        chunk_size: int = DEFAULT_CHUNK_SIZE
+        chunk_size: int = DEFAULT_CHUNK_SIZE,
     ) -> Iterator[list[str]]:
         """
         Read a text file as a stream of line chunks.
@@ -192,67 +179,64 @@ class TextFileHelper:
         chunk_size = max(chunk_size, cls.DEFAULT_MIN_CHUNK_SIZE)
         skip_header_rows = max(skip_header_rows, cls.DEFAULT_SKIP_HEADER_ROWS)
         skip_footer_rows = max(skip_footer_rows, cls.DEFAULT_SKIP_FOOTER_ROWS)
-        
+
         # Validate file path
         validated_path = PathValidator.validate_path(
-            Path(file_path),
-            must_exist=True,
-            must_be_file=True,
-            must_be_readable=True
-        )               
-        
+            Path(file_path), must_exist=True, must_be_file=True, must_be_readable=True
+        )
+
         with safe_file_operation(validated_path, encoding=encoding, mode=cls.DEFAULT_MODE) as stream:
             # Skip header rows
             for _ in range(skip_header_rows):
                 if not stream.readline():
                     return
-            
+
             # Use a sliding window to handle footer skipping efficiently
             if skip_footer_rows > 0:
                 # Buffer to hold the last skip_footer_rows lines
                 buffer: deque[str] = deque(maxlen=skip_footer_rows + 1)
                 current_chunk: list[str] = []
-                
+
                 for line in stream:
                     processed_line = line.strip() if strip else line.rstrip("\n")
-                    
+
                     # Add current line to buffer
                     buffer.append(processed_line)
-                    
+
                     # Wait until the buffer is full (skip_footer_rows + 1 lines) before processing lines.
                     # This ensures we have enough lines to reliably identify and skip the footer rows at the end.
                     if len(buffer) < skip_footer_rows + 1:
                         continue
-                    
+
                     # Once the buffer contains more than skip_footer_rows lines, the oldest line (removed with popleft)
                     # is guaranteed not to be part of the footer and can be safely processed and added to the current chunk.
                     safe_line = buffer.popleft()
                     current_chunk.append(safe_line)
-                    
+
                     # Yield chunk when it reaches the desired size
                     if len(current_chunk) >= chunk_size:
                         yield current_chunk
                         current_chunk = []
-                
+
                 # At the end, the buffer contains exactly the footer rows to skip
                 # All other lines have already been processed and yielded
-                
+
                 # Yield any remaining lines in the final chunk
                 if current_chunk:
                     yield current_chunk
             else:
                 # No footer skipping needed - simple streaming
                 chunk: list[str] = []
-                
+
                 for line in stream:
                     processed_line = line.strip() if strip else line.rstrip("\n")
                     chunk.append(processed_line)
-                    
+
                     # Yield chunk when it reaches the desired size
                     if len(chunk) >= chunk_size:
                         yield chunk
                         chunk = []
-                
+
                 # Yield any remaining lines in the final chunk
                 if chunk:
                     yield chunk
@@ -265,7 +249,7 @@ class TextFileHelper:
         strip: bool = DEFAULT_STRIP,
         encoding: str = DEFAULT_ENCODING,
         skip_header_rows: int = DEFAULT_SKIP_HEADER_ROWS,
-        skip_footer_rows: int = DEFAULT_SKIP_FOOTER_ROWS
+        skip_footer_rows: int = DEFAULT_SKIP_FOOTER_ROWS,
     ) -> list[str]:
         """
         Read the entire contents of a text file into a list of strings.
@@ -291,42 +275,39 @@ class TextFileHelper:
         """
         # Validate file path
         validated_path = PathValidator.validate_path(
-            Path(file_path),
-            must_exist=True,
-            must_be_file=True,
-            must_be_readable=True
+            Path(file_path), must_exist=True, must_be_file=True, must_be_readable=True
         )
-                      
+
         skip_header_rows = max(skip_header_rows, cls.DEFAULT_SKIP_HEADER_ROWS)
         skip_footer_rows = max(skip_footer_rows, cls.DEFAULT_SKIP_FOOTER_ROWS)
-        
+
         with safe_file_operation(validated_path, encoding=encoding, mode=cls.DEFAULT_MODE) as stream:
             for _ in range(skip_header_rows):
                 if not stream.readline():
                     return []
-            
+
             try:
                 if skip_footer_rows > 0:
                     # Buffer to hold the last skip_footer_rows + 1 lines
                     buffer = deque(maxlen=skip_footer_rows + 1)
                     result: list[str] = []
-                    
+
                     for line in stream:
                         processed_line = line.strip() if strip else line.rstrip("\n")
-                        
+
                         # Add current line to buffer
                         buffer.append(processed_line)
-                        
+
                         # Wait until the buffer is full (skip_footer_rows + 1 lines) before processing lines.
                         # This ensures we have enough lines to reliably identify and skip the footer rows at the end.
                         if len(buffer) < skip_footer_rows + 1:
                             continue
-                        
+
                         # Once the buffer contains more than skip_footer_rows lines, the oldest line (removed with popleft)
                         # is guaranteed not to be part of the footer and can be safely processed and added to the result.
                         safe_line = buffer.popleft()
                         result.append(safe_line)
-                    
+
                     # At the end, the buffer contains exactly the footer rows to skip
                     # All other lines have already been processed and added to result
                     return result
@@ -337,7 +318,4 @@ class TextFileHelper:
                         result.append(processed_line)
                     return result
             except UnicodeDecodeError as e:
-                raise SplurgeFileEncodingError(
-                    f"Encoding error reading file: {validated_path}",
-                    details=str(e)
-                )
+                raise SplurgeFileEncodingError(f"Encoding error reading file: {validated_path}", details=str(e)) from e

{splurge_dsv-2025.1.0.dist-info → splurge_dsv-2025.1.2.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: splurge-dsv
-Version: 2025.1.0
+Version: 2025.1.2
 Summary: A utility library for working with DSV (Delimited String Values) files
 Author: Jim Schilling
 License-Expression: MIT
@@ -243,6 +243,52 @@ The project follows strict coding standards:
 
 ## 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

splurge_dsv-2025.1.2.dist-info/RECORD

@@ -0,0 +1,14 @@
+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,,

splurge_dsv-2025.1.0.dist-info/RECORD

@@ -1,13 +0,0 @@
-splurge_dsv/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-splurge_dsv/__main__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-splurge_dsv/dsv_helper.py,sha256=gv9Wwf_soqdXuZWkBpxSyvJVqryKDfEoSf9SoAaRX1A,9651
-splurge_dsv/exceptions.py,sha256=tPVLXxf8LPc0yd8L8xjik331B4-NUVYfyd6ifPLUtm4,3052
-splurge_dsv/path_validator.py,sha256=2vXsNnmRTLbdYedDrF5kQZsOUvfLhSxkXyRj26OZyj8,10036
-splurge_dsv/resource_manager.py,sha256=fldvZQpzznANf4ahHre_lSqQ5_FUWndFuSlyccBylGE,13013
-splurge_dsv/string_tokenizer.py,sha256=GDAtJht-d9vt8Kb4yglxfl2iMfSMWGT3esksISNklMU,4203
-splurge_dsv/text_file_helper.py,sha256=htYT1Z0aKuQt24X2IfSKnFHB1AOY3dV7lRU8Vr6iqn0,14237
-splurge_dsv-2025.1.0.dist-info/licenses/LICENSE,sha256=fPgtg-tIFHinQvJH0arRfv50AuxikD5eHw6rrPy2A5w,1091
-splurge_dsv-2025.1.0.dist-info/METADATA,sha256=MUa4M1124GYLHmOYzLIne6-s_biC8wFi9a1PaBEmMXA,10282
-splurge_dsv-2025.1.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-splurge_dsv-2025.1.0.dist-info/top_level.txt,sha256=D6Si3FTfpRYqH7kzM7tSQAyaKbbraO6UPLpcqcY4XXM,12
-splurge_dsv-2025.1.0.dist-info/RECORD,,