cli-test-framework 0.3.4__tar.gz → 0.3.6__tar.gz

{cli_test_framework-0.3.4/src/cli_test_framework.egg-info → cli_test_framework-0.3.6}/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.4
+Metadata-Version: 2.2
 Name: cli-test-framework
-Version: 0.3.4
+Version: 0.3.6
 Summary: A powerful command line testing framework in Python with setup modules, parallel execution, and file comparison capabilities.
 Home-page: https://github.com/ozil111/cli-test-framework
 Author: Xiaotong Wang
@@ -18,9 +18,8 @@ Classifier: Topic :: Software Development :: Libraries :: Python Modules
 Requires-Python: >=3.9
 Description-Content-Type: text/markdown
 Requires-Dist: dukpy==0.5.0
-Requires-Dist: h5py>=3.10.0
-Requires-Dist: numpy<2.0.0,>=1.24.0
-Requires-Dist: PyYAML>=6.0
+Requires-Dist: h5py>=3.8.0
+Requires-Dist: numpy>=2.0.1
 Requires-Dist: setuptools>=75.8.0
 Requires-Dist: wheel>=0.45.1
 Dynamic: author

{cli_test_framework-0.3.4 → cli_test_framework-0.3.6}/setup.py

@@ -8,7 +8,7 @@ with open(os.path.join(this_directory, 'README.md'), encoding='utf-8') as f:
 
 setup(
     name="cli-test-framework",
-    version="0.3.4",
+    version="0.3.6",
     author="Xiaotong Wang",
     author_email="xiaotongwang98@gmail.com",
     description="A powerful command line testing framework in Python with setup modules, parallel execution, and file comparison capabilities.",
@@ -19,9 +19,8 @@ setup(
     package_dir={"": "src"},
     install_requires=[
         "dukpy==0.5.0",
-        "h5py>=3.10.0",
-        "numpy>=1.24.0,<2.0.0",
-        "PyYAML>=6.0",
+        "h5py>=3.8.0",
+        "numpy>=2.0.1",
         "setuptools>=75.8.0",
         "wheel>=0.45.1"
     ],

{cli_test_framework-0.3.4 → cli_test_framework-0.3.6}/src/cli_test_framework/commands/compare.py

@@ -67,6 +67,10 @@ def parse_arguments():
                          help="Relative tolerance for numerical comparison in HDF5 files")
     h5_group.add_argument("--h5-atol", type=float, default=1e-8,
                          help="Absolute tolerance for numerical comparison in HDF5 files")
+    h5_group.add_argument("--h5-data-filter", type=str,
+                         help="Data filter to apply before comparison. "
+                              "Example: '>1e-6', '<=0.01', 'abs>1e-9'. "
+                              "Filters out data that does not meet the criteria from BOTH files before comparison.")
     h5_group.add_argument("--h5-no-expand-path", dest="h5_expand_path", action="store_false",
                          help="Do not expand HDF5 group paths to compare all sub-items.")
     
@@ -150,6 +154,8 @@ def main():
             comparator_kwargs["show_content_diff"] = args.h5_show_content_diff
             comparator_kwargs["rtol"] = args.h5_rtol
             comparator_kwargs["atol"] = args.h5_atol
+            if args.h5_data_filter:
+                comparator_kwargs["data_filter"] = args.h5_data_filter
             comparator_kwargs["expand_path"] = args.h5_expand_path
         
         if file_type == "binary":

{cli_test_framework-0.3.4 → cli_test_framework-0.3.6}/src/cli_test_framework/file_comparator/factory.py

@@ -65,7 +65,7 @@ class ComparatorFactory:
         if file_type.lower() == 'h5':
             # H5 comparator accepts specific parameters
             h5_kwargs = {k: v for k, v in kwargs.items()
-                        if k in ['tables', 'table_regex', 'encoding', 'chunk_size', 'verbose', 'structure_only', 'show_content_diff', 'debug', 'rtol', 'atol', 'expand_path']}
+                        if k in ['tables', 'table_regex', 'encoding', 'chunk_size', 'verbose', 'structure_only', 'show_content_diff', 'debug', 'rtol', 'atol', 'expand_path', 'data_filter']}
             return comparator_class(**h5_kwargs)
         elif file_type.lower() == 'binary':
             # Binary comparator accepts all parameters, including num_threads

{cli_test_framework-0.3.4 → cli_test_framework-0.3.6}/src/cli_test_framework/file_comparator/h5_comparator.py

@@ -5,7 +5,7 @@ import logging
 import re
 
 class H5Comparator(BaseComparator):
-    def __init__(self, tables=None, table_regex=None, structure_only=False, show_content_diff=False, debug=False, rtol=1e-5, atol=1e-8, expand_path=True, **kwargs):
+    def __init__(self, tables=None, table_regex=None, structure_only=False, show_content_diff=False, debug=False, rtol=1e-5, atol=1e-8, expand_path=True, data_filter=None, **kwargs):
         """
         Initialize H5 comparator
         :param tables: List of table names to compare. If None, compare all tables
@@ -16,6 +16,7 @@ class H5Comparator(BaseComparator):
         :param rtol: Relative tolerance for numerical comparison
         :param atol: Absolute tolerance for numerical comparison
         :param expand_path: If True, expand group paths to compare all sub-items. Defaults to True.
+        :param data_filter: String filter expression for data comparison (e.g., '>1e-6', 'abs>1e-9')
         """
         super().__init__(**kwargs)
         self.tables = tables
@@ -25,12 +26,14 @@ class H5Comparator(BaseComparator):
         self.rtol = rtol
         self.atol = atol
         self.expand_path = expand_path
+        self.data_filter = data_filter
+        self.filter_func = self._parse_filter()
         
         # Set debug level if verbose is enabled
         if kwargs.get('verbose', False) or debug:
             self.logger.setLevel(logging.DEBUG)
             
-        self.logger.debug(f"Initialized H5Comparator with structure_only={structure_only}, show_content_diff={show_content_diff}, rtol={rtol}, atol={atol}, expand_path={expand_path}")
+        self.logger.debug(f"Initialized H5Comparator with structure_only={structure_only}, show_content_diff={show_content_diff}, rtol={rtol}, atol={atol}, expand_path={expand_path}, data_filter={data_filter}")
         if table_regex:
             self.logger.debug(f"Using table regex pattern: {table_regex}")
 
@@ -318,49 +321,60 @@ class H5Comparator(BaseComparator):
                     
                     if isinstance(data1, np.ndarray) and isinstance(data2, np.ndarray):
                         try:
+                            # 应用过滤器
+                            mask1 = self.filter_func(data1) if self.filter_func else np.ones_like(data1, dtype=bool)
+                            mask2 = self.filter_func(data2) if self.filter_func else np.ones_like(data2, dtype=bool)
+                            
+                            # 我们只关心两个文件中都满足条件的位置
+                            combined_mask = mask1 & mask2
+                            
+                            # 过滤后的数据
+                            filtered_data1 = data1[combined_mask]
+                            filtered_data2 = data2[combined_mask]
+                            
+                            if self.filter_func:
+                                self.logger.debug(f"Applied filter to {table_name}: {np.sum(combined_mask)}/{data1.size} elements meet criteria")
+                            
                             # 对于数值类型数据使用 isclose
                             if np.issubdtype(data1.dtype, np.number) and np.issubdtype(data2.dtype, np.number):
-                                equal_mask = np.isclose(data1, data2, equal_nan=True, rtol=self.rtol, atol=self.atol)
-                                if not np.all(equal_mask):
-                                    diff_indices = np.where(~equal_mask)
+                                if not np.all(np.isclose(filtered_data1, filtered_data2, equal_nan=True, rtol=self.rtol, atol=self.atol)):
                                     if self.show_content_diff:
-                                        # Report up to 10 differences
-                                        for idx in zip(*diff_indices)[:10]:
-                                            position = f"{table_name}[{','.join(map(str, idx))}]"
-                                            differences.append(self._create_difference(
-                                                position=position,
-                                                expected=str(data1[idx]),
-                                                actual=str(data2[idx]),
-                                                diff_type="content"
-                                            ))
+                                        # 如果过滤后数据不相等，需要找到原始数据的索引来报告差异
+                                        # 简化处理：直接报告内容不同
+                                        differences.append(self._create_difference(
+                                            position=table_name,
+                                            expected="Same content (after filtering)",
+                                            actual="Content differs (after filtering)",
+                                            diff_type="content"
+                                        ))
                                     else:
                                         # Just report that content differs
                                         differences.append(self._create_difference(
                                             position=table_name,
-                                            expected="Same content",
-                                            actual="Content differs",
+                                            expected="Same content (after filtering)",
+                                            actual="Content differs (after filtering)",
                                             diff_type="content"
                                         ))
                                     identical = False
                             # 对于字符串或其他类型直接比较
                             else:
-                                if not np.array_equal(data1, data2):
+                                if not np.array_equal(filtered_data1, filtered_data2):
                                     if self.show_content_diff:
                                         # For non-numeric arrays, find the first difference
-                                        diff_indices = np.where(data1 != data2)
+                                        diff_indices = np.where(filtered_data1 != filtered_data2)
                                         for idx in zip(*diff_indices)[:10]:
                                             position = f"{table_name}[{','.join(map(str, idx))}]"
                                             differences.append(self._create_difference(
                                                 position=position,
-                                                expected=str(data1[idx]),
-                                                actual=str(data2[idx]),
+                                                expected=str(filtered_data1[idx]),
+                                                actual=str(filtered_data2[idx]),
                                                 diff_type="content"
                                             ))
                                     else:
                                         differences.append(self._create_difference(
                                             position=table_name,
-                                            expected="Same content",
-                                            actual="Content differs",
+                                            expected="Same content (after filtering)",
+                                            actual="Content differs (after filtering)",
                                             diff_type="content"
                                         ))
                                     identical = False
@@ -449,6 +463,43 @@ class H5Comparator(BaseComparator):
         from .result import Difference
         return Difference(position=position, expected=expected, actual=actual, diff_type=diff_type)
 
+    def _parse_filter(self):
+        """Parse data filter string and return a filter function"""
+        if not self.data_filter:
+            return None
+
+        self.logger.debug(f"Parsing data filter: {self.data_filter}")
+        try:
+            # 匹配模式，例如 'abs>0.1', '>=1e-5', '<-10'
+            match = re.match(r"^(abs)?([><]=?|==)([-+]?\d*\.?\d+(?:[eE][-+]?\d+)?)$", self.data_filter.replace(" ", ""))
+            if not match:
+                self.logger.warning(f"Invalid data filter format: {self.data_filter}. Ignoring filter.")
+                return None
+
+            use_abs, op, value_str = match.groups()
+            value = float(value_str)
+
+            op_map = {
+                '>': np.greater,
+                '>=': np.greater_equal,
+                '<': np.less,
+                '<=': np.less_equal,
+                '==': np.equal
+            }
+
+            def filter_func(data):
+                if not isinstance(data, np.ndarray) or not np.issubdtype(data.dtype, np.number):
+                    return np.ones_like(data, dtype=bool)  # 对于非数字类型，不过滤
+                
+                target_data = np.abs(data) if use_abs else data
+                return op_map[op](target_data, value)
+
+            self.logger.debug(f"Created filter function for pattern: {use_abs or ''}{op}{value}")
+            return filter_func
+        except Exception as e:
+            self.logger.error(f"Failed to parse data filter '{self.data_filter}': {e}. Ignoring filter.")
+            return None
+
 # Register the new comparator
 from .factory import ComparatorFactory
 ComparatorFactory.register_comparator('h5', H5Comparator)

{cli_test_framework-0.3.4 → cli_test_framework-0.3.6/src/cli_test_framework.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.4
+Metadata-Version: 2.2
 Name: cli-test-framework
-Version: 0.3.4
+Version: 0.3.6
 Summary: A powerful command line testing framework in Python with setup modules, parallel execution, and file comparison capabilities.
 Home-page: https://github.com/ozil111/cli-test-framework
 Author: Xiaotong Wang
@@ -18,9 +18,8 @@ Classifier: Topic :: Software Development :: Libraries :: Python Modules
 Requires-Python: >=3.9
 Description-Content-Type: text/markdown
 Requires-Dist: dukpy==0.5.0
-Requires-Dist: h5py>=3.10.0
-Requires-Dist: numpy<2.0.0,>=1.24.0
-Requires-Dist: PyYAML>=6.0
+Requires-Dist: h5py>=3.8.0
+Requires-Dist: numpy>=2.0.1
 Requires-Dist: setuptools>=75.8.0
 Requires-Dist: wheel>=0.45.1
 Dynamic: author

{cli_test_framework-0.3.4 → cli_test_framework-0.3.6}/src/cli_test_framework.egg-info/SOURCES.txt

@@ -42,6 +42,7 @@ tests/__init__.py
 tests/performance_test.py
 tests/test1.py
 tests/test_comprehensive_space.py
+tests/test_filter_demo.py
 tests/test_parallel_runner.py
 tests/test_parallel_space.py
 tests/test_report.txt

{cli_test_framework-0.3.4 → cli_test_framework-0.3.6}/src/cli_test_framework.egg-info/requires.txt

@@ -1,6 +1,5 @@
 dukpy==0.5.0
-h5py>=3.10.0
-numpy<2.0.0,>=1.24.0
-PyYAML>=6.0
+h5py>=3.8.0
+numpy>=2.0.1
 setuptools>=75.8.0
 wheel>=0.45.1

cli_test_framework-0.3.6/tests/test_filter_demo.py

@@ -0,0 +1,103 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+
+"""
+Demo script to show the effect of different H5 data filters
+"""
+
+import h5py
+import numpy as np
+import tempfile
+import os
+import subprocess
+import sys
+
+def create_demo_files():
+    """Create demo H5 files with controlled differences"""
+    
+    with tempfile.NamedTemporaryFile(suffix='.h5', delete=False) as f1, \
+         tempfile.NamedTemporaryFile(suffix='.h5', delete=False) as f2:
+        
+        file1_path = f1.name
+        file2_path = f2.name
+    
+    # Create data with specific differences at different magnitudes
+    # Only the largest value (100.0) differs between files
+    data1 = np.array([1e-10, 1e-8, 1e-6, 1e-4, 1e-2, 1.0, 10.0, 100.0])
+    data2 = np.array([1e-10, 1e-8, 1e-6, 1e-4, 1e-2, 1.0, 10.0, 100.1])  # Only this differs
+    
+    with h5py.File(file1_path, 'w') as f:
+        f.create_dataset('demo_data', data=data1)
+    
+    with h5py.File(file2_path, 'w') as f:
+        f.create_dataset('demo_data', data=data2)
+    
+    return file1_path, file2_path
+
+def run_comparison(file1, file2, filter_expr=None):
+    """Run comparison with optional filter"""
+    cmd = [sys.executable, "-m", "src.cli_test_framework.commands.compare", "--file-type", "h5"]
+    
+    if filter_expr:
+        cmd.extend(["--h5-data-filter", filter_expr])
+    
+    cmd.extend([file1, file2])
+    
+    result = subprocess.run(cmd, capture_output=True, text=True, timeout=30)
+    return result.returncode == 0, result.stdout.strip()
+
+def demo_filter_effects():
+    """Demonstrate how different filters affect comparison results"""
+    
+    print("=== H5 Data Filter Demo ===\n")
+    print("Creating demo files with controlled differences...")
+    print("Data: [1e-10, 1e-8, 1e-6, 1e-4, 1e-2, 1.0, 10.0, 100.0] vs [1e-10, 1e-8, 1e-6, 1e-4, 1e-2, 1.0, 10.0, 100.1]")
+    print("Only the largest value (100.0 vs 100.1) differs.\n")
+    
+    file1_path, file2_path = create_demo_files()
+    
+    try:
+        # Test cases with expected results
+        test_cases = [
+            ("No filter", None, "Should detect difference at 100.0 vs 100.1"),
+            ("Filter >1e-6", ">1e-6", "Should detect difference (includes 100.0 vs 100.1)"),
+            ("Filter >1e-4", ">1e-4", "Should detect difference (includes 100.0 vs 100.1)"),
+            ("Filter >1e-2", ">1e-2", "Should detect difference (includes 100.0 vs 100.1)"),
+            ("Filter >1.0", ">1.0", "Should detect difference (includes 100.0 vs 100.1)"),
+            ("Filter >10.0", ">10.0", "Should detect difference (includes 100.0 vs 100.1)"),
+            ("Filter >100.0", ">100.0", "Should NOT detect difference (neither 100.0 nor 100.1 > 100.0)"),
+            ("Filter >=100.0", ">=100.0", "Should detect difference (both >= 100.0, but 100.0 != 100.1)"),
+            ("Filter <1e-6", "<1e-6", "Should NOT detect difference (no values < 1e-6 differ)"),
+            ("Filter <=1e-2", "<=1e-2", "Should NOT detect difference (no values <= 1e-2 differ)"),
+        ]
+        
+        print("Filter Test Results:")
+        print("-" * 80)
+        print(f"{'Filter':<20} {'Result':<10} {'Expected':<15} {'Status':<10}")
+        print("-" * 80)
+        
+        for filter_name, filter_expr, expected in test_cases:
+            identical, output = run_comparison(file1_path, file2_path, filter_expr)
+            
+            # Determine if result matches expectation
+            if "100.0 vs 100.1" in expected:
+                expected_identical = False
+            else:
+                expected_identical = True
+            
+            status = "✓ PASS" if identical == expected_identical else "✗ FAIL"
+            
+            print(f"{filter_name:<20} {'Identical' if identical else 'Different':<10} {expected_identical:<15} {status:<10}")
+            
+            if not identical and "NOT" in expected:
+                print(f"  → Unexpected: Found difference when none expected")
+            elif identical and "NOT" not in expected:
+                print(f"  → Unexpected: No difference found when one expected")
+    
+    finally:
+        os.unlink(file1_path)
+        os.unlink(file2_path)
+        print("\nDemo files cleaned up.")
+
+if __name__ == "__main__":
+    demo_filter_effects()