Files
jorgecuadros-platform/migration/render_catalog_md.py
T
rmancinas 7e65fc81d5 Add legacy database structural reference for non-Windows machines
docs/LEGACY_DATABASES.md documents all three source Access databases
(every table, column, type, and known data-quality quirk) generated
from a live read of the real files, so no Windows/Access driver is
needed to understand their structure going forward.

New migration/ tooling: catalog_schema.py connects to the real files
and walks every table (including excluded scratch tables);
render_catalog_md.py renders that into the doc's appendix. Raw output
checked in at migration/catalog.json so the doc can be regenerated
without touching Access again.
2026-07-22 01:41:53 -07:00

99 lines
3.4 KiB
Python

"""
Renders catalog.json (from catalog_schema.py) into a Markdown appendix:
one section per source file, one subsection per table, with a column
table. Excluded (scratch/template/report) tables are marked and collapsed
to a one-liner rather than a full column dump, since they carry no data
worth documenting column-by-column.
Usage:
python render_catalog_md.py catalog.json --output appendix.md
"""
from __future__ import annotations
import argparse
import json
from pathlib import Path
SOURCE_TITLES = {
"utilities": "UTILITIES.accdb",
"seguros": "SEGUROS 16_be.mdb",
"scothia": "SCOTHIA.mdb",
}
def render_table(name: str, entry: dict) -> str:
lines = [f"#### `{name}`"]
if entry.get("excluded"):
lines.append("")
lines.append(f"**Excluded from migration** — {entry.get('row_count', '?')} rows. Not detailed here; see the exclusion rationale table above.")
lines.append("")
return "\n".join(lines)
if "error" in entry:
lines.append("")
lines.append(f"**Could not read this table:** `{entry['error']}`")
lines.append("")
return "\n".join(lines)
lines.append("")
lines.append(f"Rows: {entry['row_count']} | Columns: {entry['column_count']}")
lines.append("")
lines.append("| Column | Type | Nullable |")
lines.append("|---|---|---|")
for col in entry["columns"]:
type_label = col["access_type"] or f"_(inferred: {col['pandas_dtype']})_"
nullable = "yes" if col["nullable"] else ("no" if col["nullable"] is False else "—")
col_name = col["name"].replace("|", "\\|")
lines.append(f"| `{col_name}` | {type_label} | {nullable} |")
lines.append("")
return "\n".join(lines)
def render_source(source_name: str, source_data: dict) -> str:
title = SOURCE_TITLES.get(source_name, source_name)
lines = [f"### {title}", ""]
tables = source_data["tables"]
included = sorted(t for t, e in tables.items() if not e.get("excluded"))
excluded = sorted(t for t, e in tables.items() if e.get("excluded"))
lines.append(f"{len(tables)} tables total — {len(included)} included in migration, {len(excluded)} excluded (scratch/template/report tables).")
lines.append("")
for table_name in included:
lines.append(render_table(table_name, tables[table_name]))
if excluded:
lines.append("#### Excluded tables")
lines.append("")
lines.append("| Table | Rows |")
lines.append("|---|---|")
for table_name in excluded:
entry = tables[table_name]
lines.append(f"| `{table_name}` | {entry.get('row_count', '?')} |")
lines.append("")
return "\n".join(lines)
def main() -> None:
parser = argparse.ArgumentParser(description=__doc__)
parser.add_argument("catalog", type=Path)
parser.add_argument("--output", type=Path, default=Path("appendix.md"))
args = parser.parse_args()
catalog = json.loads(args.catalog.read_text(encoding="utf-8"))
sections = ["## Appendix: full table catalog", "", "Generated by `migration/catalog_schema.py` + `migration/render_catalog_md.py`. Regenerate after any change to the source files.", ""]
for source_name in ["utilities", "seguros", "scothia"]:
sections.append(render_source(source_name, catalog[source_name]))
args.output.write_text("\n".join(sections), encoding="utf-8")
print(f"Wrote {args.output}")
if __name__ == "__main__":
main()