IDS-Viet/data-comparison
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

first push

Browse Source
This commit is contained in:
arthur 2025-08-20 14:03:58 +07:00
parent 7df12119fb
commit 47097f6be4
5 changed files with 0 additions and 159 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

BIN
.DS_Store vendored
View File

Binary file not shown.

28
test_grouping.py
View File

@ -1,28 +0,0 @@
from data_comparator import KSTCoordiComparator
def test_grouping():
comparator = KSTCoordiComparator('data/sample-data.xlsx')
if comparator.load_data():
summary = comparator.get_comparison_summary()
print("=== GROUPED BY TITLE TEST ===")
print(f"Total unique titles: {len(summary['grouped_by_title']['title_summaries'])}")
print()
# Show top 5 titles with worst match percentages
sorted_titles = sorted(
summary['grouped_by_title']['title_summaries'].items(),
key=lambda x: x[1]['match_percentage']
)
print("Top 5 titles needing attention (worst match %):")
for i, (title, data) in enumerate(sorted_titles[:5]):
print(f"{i+1}. {title}")
print(f" Total Episodes: {data['total_episodes']}")
print(f" Matched: {data['matched_count']} ({data['match_percentage']}%)")
print(f" KST Only: {data['kst_only_count']}")
print(f" Coordi Only: {data['coordi_only_count']}")
print()
if __name__ == "__main__":
test_grouping()

38
test_sheet_filtering.py
View File

@ -1,38 +0,0 @@
from data_comparator import KSTCoordiComparator
def test_sheet_filtering():
comparator = KSTCoordiComparator('data/sample-data.xlsx')
if comparator.load_data():
print("=== SHEET FILTERING TEST ===")
# Test All Sheets
summary_all = comparator.get_comparison_summary()
print(f"All Sheets:")
print(f" Available sheets: {summary_all['sheet_names']}")
print(f" Matched items: {summary_all['matched_items_count']}")
print(f" KST only: {summary_all['mismatches']['kst_only_count']}")
print(f" Coordi only: {summary_all['mismatches']['coordi_only_count']}")
print()
# Test TH URGENT only
summary_th = comparator.get_comparison_summary('TH URGENT')
print(f"TH URGENT only:")
print(f" Matched items: {summary_th['matched_items_count']}")
print(f" KST only: {summary_th['mismatches']['kst_only_count']}")
print(f" Coordi only: {summary_th['mismatches']['coordi_only_count']}")
print()
# Test US URGENT only
summary_us = comparator.get_comparison_summary('US URGENT')
print(f"US URGENT only:")
print(f" Matched items: {summary_us['matched_items_count']}")
print(f" KST only: {summary_us['mismatches']['kst_only_count']}")
print(f" Coordi only: {summary_us['mismatches']['coordi_only_count']}")
print()
print("✓ Sheet filtering functionality working!")
print("✓ Web GUI ready at http://localhost:8080")
print("✓ Dropdown will show: All Sheets, TH URGENT, US URGENT")
if __name__ == "__main__":
test_sheet_filtering()

35
test_simplified_gui.py
View File

@ -1,35 +0,0 @@
from data_comparator import KSTCoordiComparator
def test_simplified_interface():
comparator = KSTCoordiComparator('data/sample-data.xlsx')
if comparator.load_data():
summary = comparator.get_comparison_summary()
print("=== SIMPLIFIED INTERFACE TEST ===")
print(f"Matched items (Summary tab): {summary['matched_items_count']}")
total_different = (summary['mismatches']['kst_only_count'] +
summary['mismatches']['coordi_only_count'] +
summary['mismatches']['kst_duplicates_count'] +
summary['mismatches']['coordi_duplicates_count'])
print(f"Different items (Different tab): {total_different}")
print()
print("Sample items from Different tab (first 5):")
# Show KST-only items
kst_only = summary['mismatch_details']['kst_only'][:3]
for item in kst_only:
print(f"KST: {item['title']} - Episode {item['episode']} | Coordi: (empty) | Reason: Only appears in KST")
# Show Coordi-only items
coordi_only = summary['mismatch_details']['coordi_only'][:2]
for item in coordi_only:
print(f"KST: (empty) | Coordi: {item['title']} - Episode {item['episode']} | Reason: Only appears in Coordi")
print(f"\n✅ Interface ready at http://localhost:8080")
print("✅ Two tabs: Summary (matched items) and Different (mismatches)")
print("✅ Korean title + episode sorting implemented")
if __name__ == "__main__":
test_simplified_interface()

58
test_upload.py
View File

@ -1,58 +0,0 @@
import requests
import os
def test_file_upload():
# Test the upload endpoint
file_path = 'data/sample-data.xlsx'
if not os.path.exists(file_path):
print("Error: Sample file not found")
return
print("=== FILE UPLOAD TEST ===")
print(f"Testing upload of: {file_path}")
# Test upload endpoint
with open(file_path, 'rb') as f:
files = {'file': f}
try:
response = requests.post('http://localhost:8080/upload', files=files, timeout=30)
if response.status_code == 200:
data = response.json()
if data.get('success'):
print("✓ File upload successful!")
print(f" Uploaded filename: {data['filename']}")
print(f" Server file path: {data['file_path']}")
# Test analysis of uploaded file
print("✓ Testing analysis of uploaded file...")
analyze_response = requests.post('http://localhost:8080/analyze',
json={'file_path': data['file_path']},
timeout=30)
if analyze_response.status_code == 200:
analyze_data = analyze_response.json()
if analyze_data.get('success'):
print("✓ Analysis of uploaded file successful!")
results = analyze_data['results']
print(f" Sheets found: {results['sheet_names']}")
print(f" Matched items: {results['matched_items_count']}")
print(f" Different items: {results['mismatches']['kst_only_count'] + results['mismatches']['coordi_only_count']}")
else:
print(f"✗ Analysis failed: {analyze_data.get('error')}")
else:
print(f"✗ Analysis request failed: {analyze_response.status_code}")
else:
print(f"✗ Upload failed: {data.get('error')}")
else:
print(f"✗ Upload request failed: {response.status_code}")
print(f"Response: {response.text}")
except requests.exceptions.RequestException as e:
print(f"✗ Request failed: {e}")
print("Make sure the Flask server is running at http://localhost:8080")
if __name__ == "__main__":
test_file_upload()