feat(extractor): Add DiscreteMaterialPlanExtractor class for batch data extraction
- Create DiscreteMaterialPlanExtractor class orchestrating web operations and post-processing - Implement extract_and_process() combining download + Excel conversion - Implement post_process_downloads() using ExcelConverter for merge - Add extract_from_file() convenience function for file-based ID input - Add component test file verifying class structure and methods - Follow existing patterns: verbose logging, explicit parameters, English comments
This commit is contained in:
120
tests/test_extractor_component.py
Normal file
120
tests/test_extractor_component.py
Normal file
@@ -0,0 +1,120 @@
|
||||
"""
|
||||
Test DiscreteMaterialPlanExtractor component structure
|
||||
"""
|
||||
|
||||
import sys
|
||||
from pathlib import Path
|
||||
|
||||
# Add project root to Python path
|
||||
PROJECT_ROOT = Path(__file__).resolve().parent.parent
|
||||
sys.path.insert(0, str(PROJECT_ROOT))
|
||||
|
||||
# Load environment variables
|
||||
from dotenv import load_dotenv
|
||||
load_dotenv(PROJECT_ROOT / ".env")
|
||||
|
||||
# Configure browser path (not used in this test, but consistent with other tests)
|
||||
import os
|
||||
os.environ["PLAYWRIGHT_BROWSERS_PATH"] = os.getenv("PLAYWRIGHT_BROWSERS_PATH", "")
|
||||
|
||||
print("=" * 60)
|
||||
print("Testing DiscreteMaterialPlanExtractor Component")
|
||||
print("=" * 60)
|
||||
|
||||
try:
|
||||
# Test 1: Import the component
|
||||
print("\n[1/4] Importing DiscreteMaterialPlanExtractor...")
|
||||
from utils.discrete_material_plan.extractor import (
|
||||
DiscreteMaterialPlanExtractor,
|
||||
extract_from_file
|
||||
)
|
||||
print("[OK] Import successful")
|
||||
|
||||
# Test 2: Verify class exists and has expected methods
|
||||
print("\n[2/4] Verifying class structure...")
|
||||
expected_methods = [
|
||||
'__init__',
|
||||
'_print',
|
||||
'_cleanup_temp_files',
|
||||
'_get_login_url',
|
||||
'_chunk_order_ids',
|
||||
'_download_batches',
|
||||
'post_process_downloads',
|
||||
'extract_and_process',
|
||||
'extract_from_file'
|
||||
]
|
||||
|
||||
missing_methods = []
|
||||
for method in expected_methods:
|
||||
if not hasattr(DiscreteMaterialPlanExtractor, method):
|
||||
missing_methods.append(method)
|
||||
|
||||
if missing_methods:
|
||||
print(f"[FAIL] Missing methods: {missing_methods}")
|
||||
raise AttributeError(f"Missing methods: {missing_methods}")
|
||||
|
||||
print(f"[OK] All {len(expected_methods)} expected methods found")
|
||||
|
||||
# Test 3: Test instantiation with dummy parameters (no browser)
|
||||
print("\n[3/4] Testing class instantiation...")
|
||||
extractor = DiscreteMaterialPlanExtractor(
|
||||
username="test_user",
|
||||
password="test_password",
|
||||
base_url="https://example.com",
|
||||
headless=True,
|
||||
ignore_https_errors=True,
|
||||
verbose=True,
|
||||
download_dir=None,
|
||||
batch_size=10
|
||||
)
|
||||
|
||||
# Verify attributes are set correctly
|
||||
assert extractor.username == "test_user", "Username not set correctly"
|
||||
assert extractor.password == "test_password", "Password not set correctly"
|
||||
assert extractor.base_url == "https://example.com", "Base URL not set correctly"
|
||||
assert extractor.headless == True, "Headless not set correctly"
|
||||
assert extractor.ignore_https_errors == True, "HTTPS errors setting not set correctly"
|
||||
assert extractor.verbose == True, "Verbose not set correctly"
|
||||
assert extractor.batch_size == 10, "Batch size not set correctly"
|
||||
assert hasattr(extractor, 'download_dir'), "Download dir not set"
|
||||
|
||||
print("[OK] Instantiation successful, all attributes verified")
|
||||
|
||||
# Test 4: Test helper methods
|
||||
print("\n[4/4] Testing helper methods...")
|
||||
|
||||
# Test _get_login_url
|
||||
login_url = extractor._get_login_url()
|
||||
expected_url = "https://example.com/yonbip/resources/uap/rbac/login/main/index.html"
|
||||
assert login_url == expected_url, f"Login URL incorrect: {login_url}"
|
||||
print(f"[OK] _get_login_url() returns: {login_url}")
|
||||
|
||||
# Test _chunk_order_ids
|
||||
test_ids = ["ID1", "ID2", "ID3", "ID4", "ID5"]
|
||||
extractor.batch_size = 2
|
||||
chunks = extractor._chunk_order_ids(test_ids)
|
||||
expected_chunks = [["ID1", "ID2"], ["ID3", "ID4"], ["ID5"]]
|
||||
assert chunks == expected_chunks, f"Chunking incorrect: {chunks}"
|
||||
print(f"[OK] _chunk_order_ids() works correctly: {chunks}")
|
||||
|
||||
# Test _print (should not raise)
|
||||
extractor._print("Test message")
|
||||
print("[OK] _print() works correctly")
|
||||
|
||||
# Cleanup
|
||||
extractor._cleanup_temp_files()
|
||||
|
||||
print("\n" + "=" * 60)
|
||||
print("[SUCCESS] All component tests passed!")
|
||||
print("=" * 60)
|
||||
|
||||
except Exception as e:
|
||||
print(f"\n[ERROR] Component test failed!")
|
||||
print(f"Error: {e}")
|
||||
import traceback
|
||||
traceback.print_exc()
|
||||
sys.exit(1)
|
||||
|
||||
print("\n" + "=" * 60)
|
||||
print("Test completed successfully")
|
||||
print("=" * 60)
|
||||
Reference in New Issue
Block a user