dataflow/api/routes/sources.js
Paul Trowbridge 291c665ed1 Consolidate all SQL into database/queries/, switch to literal SQL in routes
- Add database/queries/{sources,rules,mappings,records}.sql — one file per
  route, all business logic in PostgreSQL functions
- Replace parameterized queries in all four route files with lit()/jsonLit()
  literal interpolation for debuggability
- Add api/lib/sql.js with lit(), jsonLit(), arr() helpers
- Fix get_view_data to use json_agg (preserves column order) with subquery
  (guarantees sort order is respected before aggregation)
- Fix jsonLit() for JSONB params so plain strings become valid JSON
- Update manage.py option 3 to deploy database/queries/ instead of functions.sql
- Add SPEC.md covering architecture, philosophy, and manage.py

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-05 22:36:53 -04:00

194 lines
6.7 KiB
JavaScript

/**
* Sources Routes
* Manage data sources
*/
const express = require('express');
const multer = require('multer');
const { parse } = require('csv-parse/sync');
const { lit, arr } = require('../lib/sql');
const upload = multer({ storage: multer.memoryStorage() });
module.exports = (pool) => {
const router = express.Router();
// List all sources
router.get('/', async (req, res, next) => {
try {
const result = await pool.query(`SELECT * FROM list_sources()`);
res.json(result.rows);
} catch (err) {
next(err);
}
});
// Get single source
router.get('/:name', async (req, res, next) => {
try {
const result = await pool.query(`SELECT * FROM get_source(${lit(req.params.name)})`);
if (result.rows.length === 0) return res.status(404).json({ error: 'Source not found' });
res.json(result.rows[0]);
} catch (err) {
next(err);
}
});
// Suggest source definition from CSV
router.post('/suggest', upload.single('file'), async (req, res, next) => {
try {
if (!req.file) return res.status(400).json({ error: 'No file uploaded' });
const records = parse(req.file.buffer, { columns: true, skip_empty_lines: true, trim: true });
if (records.length === 0) return res.status(400).json({ error: 'CSV file is empty' });
const sample = records[0];
const fields = Object.keys(sample).map(key => {
const val = sample[key];
let type = 'text';
if (!isNaN(parseFloat(val)) && isFinite(val) && val.charAt(0) !== '0') {
type = 'numeric';
} else if (Date.parse(val) > Date.parse('1950-01-01') && Date.parse(val) < Date.parse('2050-01-01')) {
type = 'date';
}
return { name: key, type };
});
res.json({ name: '', dedup_fields: [], fields });
} catch (err) {
next(err);
}
});
// Create source
router.post('/', async (req, res, next) => {
try {
const { name, dedup_fields, config } = req.body;
if (!name || !dedup_fields || !Array.isArray(dedup_fields)) {
return res.status(400).json({ error: 'Missing required fields: name, dedup_fields (array)' });
}
const result = await pool.query(
`SELECT * FROM create_source(${lit(name)}, ${arr(dedup_fields)}, ${lit(config || {})})`
);
res.status(201).json(result.rows[0]);
} catch (err) {
if (err.code === '23505') return res.status(409).json({ error: 'Source already exists' });
next(err);
}
});
// Update source
router.put('/:name', async (req, res, next) => {
try {
const { dedup_fields, config } = req.body;
const result = await pool.query(
`SELECT * FROM update_source(${lit(req.params.name)}, ${dedup_fields ? arr(dedup_fields) : 'NULL'}, ${config ? lit(config) : 'NULL'})`
);
if (result.rows.length === 0) return res.status(404).json({ error: 'Source not found' });
res.json(result.rows[0]);
} catch (err) {
next(err);
}
});
// Delete source
router.delete('/:name', async (req, res, next) => {
try {
const result = await pool.query(`SELECT * FROM delete_source(${lit(req.params.name)})`);
if (result.rows.length === 0) return res.status(404).json({ error: 'Source not found' });
res.json({ success: true, deleted: result.rows[0].delete_source });
} catch (err) {
next(err);
}
});
// Import CSV data
router.post('/:name/import', upload.single('file'), async (req, res, next) => {
try {
if (!req.file) return res.status(400).json({ error: 'No file uploaded' });
const records = parse(req.file.buffer, { columns: true, skip_empty_lines: true, trim: true });
const result = await pool.query(
`SELECT import_records(${lit(req.params.name)}, ${lit(records)}) as result`
);
res.json(result.rows[0].result);
} catch (err) {
next(err);
}
});
// Get import log
router.get('/:name/import-log', async (req, res, next) => {
try {
const result = await pool.query(`SELECT * FROM get_import_log(${lit(req.params.name)})`);
res.json(result.rows);
} catch (err) {
next(err);
}
});
// Apply transformations
router.post('/:name/transform', async (req, res, next) => {
try {
const result = await pool.query(`SELECT apply_transformations(${lit(req.params.name)}) as result`);
res.json(result.rows[0].result);
} catch (err) {
next(err);
}
});
// Get all known field names for a source
router.get('/:name/fields', async (req, res, next) => {
try {
const result = await pool.query(`SELECT * FROM get_source_fields(${lit(req.params.name)})`);
res.json(result.rows);
} catch (err) {
next(err);
}
});
// Generate output view
router.post('/:name/view', async (req, res, next) => {
try {
const result = await pool.query(`SELECT generate_source_view(${lit(req.params.name)}) as result`);
res.json(result.rows[0].result);
} catch (err) {
next(err);
}
});
// Reprocess all records
router.post('/:name/reprocess', async (req, res, next) => {
try {
const result = await pool.query(`SELECT reprocess_records(${lit(req.params.name)}) as result`);
res.json(result.rows[0].result);
} catch (err) {
next(err);
}
});
// Get statistics
router.get('/:name/stats', async (req, res, next) => {
try {
const result = await pool.query(`SELECT * FROM get_source_stats(${lit(req.params.name)})`);
res.json(result.rows[0]);
} catch (err) {
next(err);
}
});
// Get view data (paginated, sortable)
router.get('/:name/view-data', async (req, res, next) => {
try {
const { limit = 100, offset = 0, sort_col, sort_dir } = req.query;
const result = await pool.query(
`SELECT get_view_data(${lit(req.params.name)}, ${lit(parseInt(limit))}, ${lit(parseInt(offset))}, ${lit(sort_col || null)}, ${lit(sort_dir || 'asc')}) as result`
);
res.json(result.rows[0].result);
} catch (err) {
next(err);
}
});
return router;
};