Merge pull request #52 from mwisnowski/chore/cleanup-debug-workflow

chore: comment out debug step in similarity cache workflow
This commit is contained in:
mwisnowski 2026-02-20 11:49:53 -08:00 committed by GitHub
commit 65680fb920
No known key found for this signature in database
GPG key ID: B5690EEEBB952194

View file

@ -89,44 +89,45 @@ jobs:
exit 1 exit 1
fi fi
- name: Debug - Inspect Parquet file after tagging # Debug step - uncomment if needed to inspect Parquet file contents
if: steps.check_cache.outputs.needs_build == 'true' # - name: Debug - Inspect Parquet file after tagging
run: | # if: steps.check_cache.outputs.needs_build == 'true'
python -c " # run: |
import pandas as pd # python -c "
from pathlib import Path # import pandas as pd
from code.path_util import get_processed_cards_path # from pathlib import Path
# from code.path_util import get_processed_cards_path
parquet_path = Path(get_processed_cards_path()) #
print(f'Reading Parquet file: {parquet_path}') # parquet_path = Path(get_processed_cards_path())
print(f'File exists: {parquet_path.exists()}') # print(f'Reading Parquet file: {parquet_path}')
# print(f'File exists: {parquet_path.exists()}')
if not parquet_path.exists(): #
raise FileNotFoundError(f'Parquet file not found: {parquet_path}') # if not parquet_path.exists():
# raise FileNotFoundError(f'Parquet file not found: {parquet_path}')
df = pd.read_parquet(parquet_path) #
print(f'Loaded {len(df)} rows from Parquet file') # df = pd.read_parquet(parquet_path)
print(f'Columns: {list(df.columns)}') # print(f'Loaded {len(df)} rows from Parquet file')
print('') # print(f'Columns: {list(df.columns)}')
# print('')
# Show first 5 rows completely #
print('First 5 complete rows:') # # Show first 5 rows completely
print('=' * 100) # print('First 5 complete rows:')
for idx, row in df.head(5).iterrows(): # print('=' * 100)
print(f'Row {idx}:') # for idx, row in df.head(5).iterrows():
for col in df.columns: # print(f'Row {idx}:')
value = row[col] # for col in df.columns:
if isinstance(value, (list, tuple)) or hasattr(value, '__array__'): # value = row[col]
# For array-like, show type and length # if isinstance(value, (list, tuple)) or hasattr(value, '__array__'):
try: # # For array-like, show type and length
length = len(value) # try:
print(f' {col}: {type(value).__name__}[{length}] = {value}') # length = len(value)
except: # print(f' {col}: {type(value).__name__}[{length}] = {value}')
print(f' {col}: {type(value).__name__} = {value}') # except:
else: # print(f' {col}: {type(value).__name__} = {value}')
print(f' {col}: {value}') # else:
print('-' * 100) # print(f' {col}: {value}')
" # print('-' * 100)
# "
- name: Generate theme catalog - name: Generate theme catalog
if: steps.check_cache.outputs.needs_build == 'true' if: steps.check_cache.outputs.needs_build == 'true'