tree-sitter-analyzer 1.6.1.3__py3-none-any.whl → 1.6.1.4__py3-none-any.whl

tree_sitter_analyzer/__init__.py

@@ -11,7 +11,7 @@ Architecture:
 - Data Models: Generic and language-specific code element representations
 """
 
-__version__ = "1.6.1.3"
+__version__ = "1.6.1.4"
 __author__ = "aisheng.yu"
 __email__ = "aimasteracc@gmail.com"
 

tree_sitter_analyzer/encoding_utils.py

@@ -456,6 +456,61 @@ def extract_text_slice(
     )
 
 
+def read_file_safe_streaming(file_path: str | Path):
+    """
+    Context manager for streaming file reading with automatic encoding detection.
+    
+    This function opens a file with the correct encoding detected from the file's
+    content and yields a file handle that can be used for line-by-line reading.
+    This is memory-efficient for large files as it doesn't load the entire content.
+    
+    Args:
+        file_path: Path to the file to read
+        
+    Yields:
+        File handle opened with the correct encoding
+        
+    Example:
+        with read_file_safe_streaming("large_file.txt") as f:
+            for line_num, line in enumerate(f, 1):
+                if line_num >= start_line:
+                    # Process line
+                    pass
+    """
+    import contextlib
+    
+    file_path = Path(file_path)
+    
+    # First, detect encoding by reading a small sample
+    try:
+        with open(file_path, "rb") as f:
+            # Read first 8KB to detect encoding
+            sample_data = f.read(8192)
+            
+        if not sample_data:
+            # Empty file, use default encoding
+            detected_encoding = EncodingManager.DEFAULT_ENCODING
+        else:
+            # Detect encoding from sample with file path for caching
+            detected_encoding = EncodingManager.detect_encoding(sample_data, str(file_path))
+            
+    except OSError as e:
+        log_warning(f"Failed to read file for encoding detection {file_path}: {e}")
+        raise e
+    
+    # Open file with detected encoding for streaming
+    @contextlib.contextmanager
+    def _file_context():
+        try:
+            with open(file_path, "r", encoding=detected_encoding, errors="replace") as f:
+                yield f
+        except OSError as e:
+            log_warning(f"Failed to open file for streaming {file_path}: {e}")
+            raise e
+    
+    return _file_context()
+
+
 def clear_encoding_cache() -> None:
     """Clear the global encoding cache"""
     _encoding_cache.clear()

tree_sitter_analyzer/file_handler.py

@@ -5,9 +5,10 @@ File Handler Module
 This module provides file reading functionality with encoding detection and fallback.
 """
 
+import itertools
 from pathlib import Path
 
-from .encoding_utils import read_file_safe
+from .encoding_utils import read_file_safe, read_file_safe_streaming
 from .utils import log_error, log_info, log_warning
 
 
@@ -81,7 +82,10 @@ def read_file_partial(
     end_column: int | None = None,
 ) -> str | None:
     """
-    Read partial file content by line/column range
+    Read partial file content by line/column range using streaming approach.
+    
+    This function uses a memory-efficient streaming approach that reads only
+    the required lines from the file, making it suitable for very large files.
 
     Args:
         file_path: Path to file
@@ -109,30 +113,39 @@ def read_file_partial(
         return None
 
     try:
-        # Read whole file safely
-        content, detected_encoding = read_file_safe(file_path)
-
-        # Split to lines
-        lines = content.splitlines(keepends=True)
-        total_lines = len(lines)
-
-        # Adjust line indexes
-        start_idx = start_line - 1  # convert to 0-based
-        end_idx = min(
-            end_line - 1 if end_line is not None else total_lines - 1, total_lines - 1
-        )
-
-        # Range check
-        if start_idx >= total_lines:
-            log_warning(
-                f"start_line ({start_line}) exceeds file length ({total_lines})"
-            )
-            return ""
-
-        # Select lines
-        selected_lines = lines[start_idx : end_idx + 1]
+        # Use streaming approach for memory efficiency
+        with read_file_safe_streaming(file_path) as f:
+            # Convert to 0-based indexing
+            start_idx = start_line - 1
+            end_idx = end_line - 1 if end_line is not None else None
+            
+            # Use itertools.islice for efficient line selection
+            if end_idx is not None:
+                # Read specific range
+                selected_lines_iter = itertools.islice(f, start_idx, end_idx + 1)
+            else:
+                # Read from start_line to end of file
+                selected_lines_iter = itertools.islice(f, start_idx, None)
+            
+            # Convert iterator to list for processing
+            selected_lines = list(selected_lines_iter)
+            
+            # Check if we got any lines
+            if not selected_lines:
+                # Check if start_line is beyond file length by counting lines
+                with read_file_safe_streaming(file_path) as f_count:
+                    total_lines = sum(1 for _ in f_count)
+                
+                if start_idx >= total_lines:
+                    log_warning(
+                        f"start_line ({start_line}) exceeds file length ({total_lines})"
+                    )
+                    return ""
+                else:
+                    # File might be empty or other issue
+                    return ""
 
-        # Handle column range
+        # Handle column range if specified
         if start_column is not None or end_column is not None:
             processed_lines = []
             for i, line in enumerate(selected_lines):
@@ -167,7 +180,7 @@ def read_file_partial(
                 # Preserve original newline (except last line)
                 if i < len(selected_lines) - 1:
                     # Detect original newline char of the line
-                    original_line = lines[start_idx + i]
+                    original_line = selected_lines[i]
                     if original_line.endswith("\r\n"):
                         line_content += "\r\n"
                     elif original_line.endswith("\n"):
@@ -182,9 +195,12 @@ def read_file_partial(
             # No column range: join lines directly
             result = "".join(selected_lines)
 
+        # Calculate end line for logging
+        actual_end_line = end_line or (start_line + len(selected_lines) - 1)
+        
         log_info(
             f"Successfully read partial file {file_path}: "
-            f"lines {start_line}-{end_line or total_lines}"
+            f"lines {start_line}-{actual_end_line}"
             f"{f', columns {start_column}-{end_column}' if start_column is not None or end_column is not None else ''}"
         )
 

{tree_sitter_analyzer-1.6.1.3.dist-info → tree_sitter_analyzer-1.6.1.4.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: tree-sitter-analyzer
-Version: 1.6.1.3
+Version: 1.6.1.4
 Summary: Extensible multi-language code analyzer framework using Tree-sitter with dynamic plugin architecture
 Project-URL: Homepage, https://github.com/aimasteracc/tree-sitter-analyzer
 Project-URL: Documentation, https://github.com/aimasteracc/tree-sitter-analyzer#readme
@@ -165,11 +165,11 @@ Description-Content-Type: text/markdown
 
 [![Python Version](https://img.shields.io/badge/python-3.10%2B-blue.svg)](https://python.org)
 [![License](https://img.shields.io/badge/license-MIT-green.svg)](LICENSE)
-[![Tests](https://img.shields.io/badge/tests-1967%20tests-brightgreen.svg)](#quality-assurance)
+[![Tests](https://img.shields.io/badge/tests-1980%20tests-brightgreen.svg)](#quality-assurance)
 [![Coverage](https://img.shields.io/badge/coverage-71.48%25-green.svg)](#quality-assurance)
 [![Quality](https://img.shields.io/badge/quality-enterprise%20grade-blue.svg)](#quality-assurance)
 [![PyPI](https://img.shields.io/pypi/v/tree-sitter-analyzer.svg)](https://pypi.org/project/tree-sitter-analyzer/)
-[![Version](https://img.shields.io/badge/version-1.6.1.3-blue.svg)](https://github.com/aimasteracc/tree-sitter-analyzer/releases)
+[![Version](https://img.shields.io/badge/version-1.6.1.4-blue.svg)](https://github.com/aimasteracc/tree-sitter-analyzer/releases)
 [![GitHub Stars](https://img.shields.io/github/stars/aimasteracc/tree-sitter-analyzer.svg?style=social)](https://github.com/aimasteracc/tree-sitter-analyzer)
 
 ## 🚀 Enterprise-Grade Code Analysis Tool for the AI Era
@@ -224,7 +224,7 @@ Tree-sitter Analyzer is an enterprise-grade code analysis tool designed for the
 - **More Languages** - Basic support for C/C++, Rust, Go
 
 ### 🏆 Production Ready
-- **1893 Tests** - Comprehensive test coverage, enterprise-grade quality assurance
+- **1980 Tests** - Comprehensive test coverage, enterprise-grade quality assurance
 - **71.48% Coverage** - Comprehensive test suite
 - **Cross-Platform Support** - Full compatibility with Windows, macOS, Linux
 - **Continuous Maintenance** - Active development and community support
@@ -731,7 +731,7 @@ Powerful file discovery and content search based on fd and ripgrep:
 ## 🏆 Quality Assurance
 
 ### 📊 Quality Metrics
-- **1893 Tests** - Comprehensive test coverage ✅
+- **1980 Tests** - Comprehensive test coverage ✅
 - **71.48% Code Coverage** - Comprehensive test suite
 - **Zero Test Failures** - Production ready
 - **Cross-Platform Support** - Windows, macOS, Linux
@@ -784,7 +784,7 @@ uv run pytest tests/test_mcp_server_initialization.py -v
 **Verification Environment:**
 - Operating Systems: Windows 10, macOS, Linux
 - Python Version: 3.10+
-- Project Version: tree-sitter-analyzer v1.6.1.3
+- Project Version: tree-sitter-analyzer v1.6.1.4
 - Test Files: BigService.java (1419 lines), sample.py (256 lines), MultiClass.java (54 lines)
 
 ---

{tree_sitter_analyzer-1.6.1.3.dist-info → tree_sitter_analyzer-1.6.1.4.dist-info}/RECORD

@@ -1,11 +1,11 @@
-tree_sitter_analyzer/__init__.py,sha256=GnE09UdDRFn4KIFZSjDA_KKrsE8qmAyHvZf0IG5rf5Y,3069
+tree_sitter_analyzer/__init__.py,sha256=uQLp3KXeuJDq1B5eHowray1HngjGdDoPOJu3Qf3gmiM,3069
 tree_sitter_analyzer/__main__.py,sha256=Zl79tpe4UaMu-7yeztc06tgP0CVMRnvGgas4ZQP5SCs,228
 tree_sitter_analyzer/api.py,sha256=jzwID6fJNdhQkJP3D0lzBVPhOnGIN4tyyMtmRYdK9zI,22753
 tree_sitter_analyzer/cli_main.py,sha256=BuaM-L-Jx3G49qvAUOQVsw0wEM-X0UzPaRszRZBist4,10374
 tree_sitter_analyzer/constants.py,sha256=7w3sLFt_6vPaKsxzrc21K1rOKpLGMyyA1203nu3pDOQ,1889
-tree_sitter_analyzer/encoding_utils.py,sha256=BgdBKnW20EueEFJT-aLrQI38bTOcR5rWQ3Dpa-ALszA,14805
+tree_sitter_analyzer/encoding_utils.py,sha256=hPPoRzMHHYZ2hLREjp3OHWkmmVmjC6H0TX3SxyBXcGg,16704
 tree_sitter_analyzer/exceptions.py,sha256=AZryCQyKXekAg8lQZd3zqULnjhCKovBNNpnUlNGDhcI,11615
-tree_sitter_analyzer/file_handler.py,sha256=mtWz-DE4yfmak347s0e20xFNy3qddcek58Enom5GlZQ,6689
+tree_sitter_analyzer/file_handler.py,sha256=f89N0CcnxfZxphu4QDpormc5AXoUko132EYK-kFoTx0,7753
 tree_sitter_analyzer/language_detector.py,sha256=pn3nQClo8b_Ar8dS5X3hq9_t5IIlIcizIC0twMaowU4,11693
 tree_sitter_analyzer/language_loader.py,sha256=gBUXGPTv91bRNs_urH23wzNKgh7ki6KkvpQ7iNPe3Rw,8922
 tree_sitter_analyzer/logging_manager.py,sha256=pQYQAQi1RheWokGsokNuF9Ik466jQK5UQC8PSVOxpEU,12669
@@ -89,7 +89,7 @@ tree_sitter_analyzer/security/__init__.py,sha256=ZTqTt24hsljCpTXAZpJC57L7MU5lJLT
 tree_sitter_analyzer/security/boundary_manager.py,sha256=3eeENRKWtz2pyZHzd8DiVaq8fdeC6s1eVOuBylSmQPg,9347
 tree_sitter_analyzer/security/regex_checker.py,sha256=jWK6H8PTPgzbwRPfK_RZ8bBTS6rtEbgjY5vr3YWjQ_U,9616
 tree_sitter_analyzer/security/validator.py,sha256=yR4qTWEcXpR--bSFwtWvSgY0AzqujOFAqlc1Z7dlTdk,9809
-tree_sitter_analyzer-1.6.1.3.dist-info/METADATA,sha256=8BOPv3ykHXzGMhNJMBEiu0qiAogfUce1q55UYrrHmAY,32236
-tree_sitter_analyzer-1.6.1.3.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-tree_sitter_analyzer-1.6.1.3.dist-info/entry_points.txt,sha256=dEQkGMGmGGBzssEKlXW9F0-VlO3XJW2fJUv9i7898Ho,701
-tree_sitter_analyzer-1.6.1.3.dist-info/RECORD,,
+tree_sitter_analyzer-1.6.1.4.dist-info/METADATA,sha256=pjEnX5EfNgtmFlaQeQLjR_KUYp1olwOZHHAK32S49MQ,32236
+tree_sitter_analyzer-1.6.1.4.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+tree_sitter_analyzer-1.6.1.4.dist-info/entry_points.txt,sha256=dEQkGMGmGGBzssEKlXW9F0-VlO3XJW2fJUv9i7898Ho,701
+tree_sitter_analyzer-1.6.1.4.dist-info/RECORD,,