Coverage for src / crump / __init__.py: 100%

1"""Sync CSV, Parquet, and CDF science files into database. 

2 

3This package provides both a CLI tool and programmatic API for syncing 

4CSV, Parquet, and CDF files into a database (PostgreSQL or SQLite). 

5 

6CLI Usage: 

7 crump sync <file> <config> <job> --db-url <url> 

8 crump prepare <file> <config> <job> 

9 crump inspect <file> 

10 crump extract <file> --output-dir <dir> 

11 

12Programmatic Usage: 

13 from crump import sync_file_to_db, analyze_tabular_file_types_and_nullable 

14 from pathlib import Path 

15 

16 # Sync a tabular file (CSV or Parquet) 

17 sync_file_to_db( 

18 file_path=Path("data.parquet"), 

19 job=job_config, 

20 db_connection_string="postgresql://localhost/mydb" 

21 ) 

22""" 

23 

24__version__ = "0.4.1" 

25 

26# Export main API functions 

27from crump.config import ( 

28 ColumnMapping, 

29 CrumpConfig, 

30 CrumpJob, 

31 FailureMode, 

32 Index, 

33 IndexColumn, 

34) 

35from crump.database import ( 

36 DryRunSummary, 

37 sync_file_to_db, 

38 sync_file_to_db_dry_run, 

39) 

40from crump.type_detection import ( 

41 analyze_tabular_file_types_and_nullable, 

42 suggest_id_column, 

43) 

44 

45__all__ = [ 

46 "__version__", 

47 # Configuration 

48 "CrumpConfig", 

49 "CrumpJob", 

50 "ColumnMapping", 

51 "FailureMode", 

52 "Index", 

53 "IndexColumn", 

54 # Database operations 

55 "sync_file_to_db", 

56 "sync_file_to_db_dry_run", 

57 "DryRunSummary", 

58 # Type detection 

59 "analyze_tabular_file_types_and_nullable", 

60 "suggest_id_column", 

61]