askrobots / dbbasic-admin
Public
An admin interface that builds itself from the dbbasic modules you install; its pages follow file paths, like CGI.
discover.py · 3.8 KB · 150 lines
| 1 | """ |
| 2 | TSV table auto-discovery for admin interface |
| 3 | """ |
| 4 | import os |
| 5 | from pathlib import Path |
| 6 | from typing import List, Dict, Any |
| 7 | |
| 8 | |
| 9 | def get_data_dir() -> Path: |
| 10 | """Get the data directory path""" |
| 11 | # Look for data directory in current working directory |
| 12 | cwd = Path.cwd() |
| 13 | data_dir = cwd / "data" |
| 14 | |
| 15 | if not data_dir.exists(): |
| 16 | # Try _data as alternative |
| 17 | data_dir = cwd / "_data" |
| 18 | |
| 19 | return data_dir |
| 20 | |
| 21 | |
| 22 | def discover_tsv_tables() -> List[Dict[str, Any]]: |
| 23 | """ |
| 24 | Auto-discover TSV tables in the data directory. |
| 25 | |
| 26 | Returns: |
| 27 | List of dicts with table metadata: |
| 28 | [ |
| 29 | { |
| 30 | 'name': 'posts', |
| 31 | 'file': 'data/posts.tsv', |
| 32 | 'size': 12345, |
| 33 | 'rows': 42, |
| 34 | 'columns': ['id', 'title', 'content', 'author', 'created'] |
| 35 | }, |
| 36 | ... |
| 37 | ] |
| 38 | """ |
| 39 | data_dir = get_data_dir() |
| 40 | |
| 41 | if not data_dir.exists(): |
| 42 | return [] |
| 43 | |
| 44 | tables = [] |
| 45 | |
| 46 | # Find all .tsv files |
| 47 | for tsv_file in data_dir.glob("*.tsv"): |
| 48 | try: |
| 49 | # Get file size |
| 50 | file_size = tsv_file.stat().st_size |
| 51 | |
| 52 | # Read first line to get columns |
| 53 | columns = [] |
| 54 | row_count = 0 |
| 55 | |
| 56 | with open(tsv_file, 'r', encoding='utf-8') as f: |
| 57 | # First line is column headers |
| 58 | first_line = f.readline().strip() |
| 59 | if first_line: |
| 60 | columns = first_line.split('\t') |
| 61 | row_count = 1 # header |
| 62 | |
| 63 | # Count remaining rows |
| 64 | for line in f: |
| 65 | if line.strip(): |
| 66 | row_count += 1 |
| 67 | |
| 68 | tables.append({ |
| 69 | 'name': tsv_file.stem, |
| 70 | 'file': str(tsv_file.relative_to(Path.cwd())), |
| 71 | 'size': file_size, |
| 72 | 'rows': max(0, row_count - 1), # Exclude header from count |
| 73 | 'columns': columns |
| 74 | }) |
| 75 | |
| 76 | except Exception as e: |
| 77 | # Skip files we can't read |
| 78 | print(f"Warning: Could not read {tsv_file}: {e}") |
| 79 | continue |
| 80 | |
| 81 | # Sort by name |
| 82 | tables.sort(key=lambda x: x['name']) |
| 83 | |
| 84 | return tables |
| 85 | |
| 86 | |
| 87 | def read_tsv_data(table_name: str, limit: int = 100) -> List[Dict[str, str]]: |
| 88 | """ |
| 89 | Read data from a TSV table. |
| 90 | |
| 91 | Args: |
| 92 | table_name: Name of the table (without .tsv extension) |
| 93 | limit: Maximum number of rows to return |
| 94 | |
| 95 | Returns: |
| 96 | List of dicts, one per row |
| 97 | """ |
| 98 | data_dir = get_data_dir() |
| 99 | tsv_file = data_dir / f"{table_name}.tsv" |
| 100 | |
| 101 | if not tsv_file.exists(): |
| 102 | return [] |
| 103 | |
| 104 | rows = [] |
| 105 | |
| 106 | try: |
| 107 | with open(tsv_file, 'r', encoding='utf-8') as f: |
| 108 | # Read header |
| 109 | header_line = f.readline().strip() |
| 110 | if not header_line: |
| 111 | return [] |
| 112 | |
| 113 | columns = header_line.split('\t') |
| 114 | |
| 115 | # Read data rows |
| 116 | for i, line in enumerate(f): |
| 117 | if i >= limit: |
| 118 | break |
| 119 | |
| 120 | line = line.strip() |
| 121 | if not line: |
| 122 | continue |
| 123 | |
| 124 | values = line.split('\t') |
| 125 | |
| 126 | # Pad values if needed |
| 127 | while len(values) < len(columns): |
| 128 | values.append('') |
| 129 | |
| 130 | # Create dict |
| 131 | row_dict = dict(zip(columns, values)) |
| 132 | rows.append(row_dict) |
| 133 | |
| 134 | except Exception as e: |
| 135 | print(f"Error reading {tsv_file}: {e}") |
| 136 | return [] |
| 137 | |
| 138 | return rows |
| 139 | |
| 140 | |
| 141 | def format_file_size(size_bytes: int) -> str: |
| 142 | """Format file size in human-readable format""" |
| 143 | if size_bytes < 1024: |
| 144 | return f"{size_bytes} B" |
| 145 | elif size_bytes < 1024 * 1024: |
| 146 | return f"{size_bytes / 1024:.1f} KB" |
| 147 | elif size_bytes < 1024 * 1024 * 1024: |
| 148 | return f"{size_bytes / (1024 * 1024):.1f} MB" |
| 149 | else: |
| 150 | return f"{size_bytes / (1024 * 1024 * 1024):.1f} GB" |