Files
claudetools/projects/dataforth-dos/datasheet-pipeline/scmvas-hvas-research/existing-database/export-datasheets.js
Mike Swanson 45083f4735 Add SCMVAS/SCMHVAS datasheet pipeline extension (Dataforth)
Extends the Test Datasheet Pipeline on AD2:C:\Shares\testdatadb to
generate web-published datasheets for the SCMVAS-Mxxx (obsolete) and
SCMHVAS-Mxxxx (replacement) High Voltage Input Module product lines.
Both are tested either with the existing TESTHV3 software (production
VASLOG .DAT logs) or in Engineering with plain .txt output.

Key changes on AD2 (all deployed 2026-04-12 with dated backups):

- parsers/spec-reader.js: getSpecs() returns a `{_family:'SCMVAS',
  _noSpecs:true}` sentinel for SCMVAS/SCMHVAS/VAS-M/HVAS-M model prefixes
  so the export pipeline does not silently skip them for missing specs.
- templates/datasheet-exact.js: new Accuracy-only template branch
  (generateSCMVASDatasheet + helpers) that mirrors the existing shipped
  format byte-for-byte. Extraction regex covers both QuickBASIC STR$()
  output formats: scientific-with-trailing-status-digit (98.4% of
  records) and plain-decimal (1.6% of records above QB's threshold).
- parsers/vaslog-engtxt.js (new): parses the Engineering-Tested .txt
  files in TS-3R\LOGS\VASLOG\VASLOG - Engineering Tested\. Filename SN
  regex strips optional trailing 14-digit timestamp; in-file "SN:"
  header is the authoritative source when the filename is malformed.
- database/import.js: LOG_TYPES grows a VASLOG_ENG entry with
  subfolder + recursive flags. Pre-existing 7 log types keep their
  implicit recursive=true behaviour (config.recursive !== false).
  importFiles() routes VASLOG_ENG paths before the generic loop so a
  VASLOG - Engineering Tested/*.txt path does not mis-dispatch to the
  multiline parser.
- database/export-datasheets.js: VASLOG_ENG records are written
  verbatim via fs.copyFileSync(source_file, For_Web/<SN>.TXT) for true
  byte-level pass-through, with a graceful raw_data fallback when the
  source file is no longer on disk.

Deploy outcome:
- 27,503 SCMVAS/SCMHVAS datasheets rendered (27,065 from scientific +
  438 from plain-decimal PASS lines, post-patch rerun)
- 434 Engineering-Tested .txt files pass-through-copied to For_Web
- 0 errors across both batches

Repo layout added here:
- scmvas-hvas-research/: discovery artifacts (source .BAS, hvin.dat,
  sample .DAT + .txt, binary-format notes, IMPLEMENTATION_PLAN.md)
- implementation/: staged final code + deploy helpers + local test
  harness + per-step verification scripts
- backups/pre-deploy-20260412/: independent local snapshot of the 4
  AD2 files replaced, pulled byte-for-byte before deploy

All helper scripts fetch the AD2 password at runtime from the SOPS
vault (clients/dataforth/ad2.sops.yaml). None of the committed files
contain the plaintext credential. Known vault-entry hygiene issue
(stale shell-escape backslash before the `!`) is documented in the
fetcher comments and stripped at read-time; flagged separately for
cleanup.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-13 07:36:45 -07:00

217 lines
7.0 KiB
JavaScript

/**
* Export Datasheets
*
* Generates TXT datasheets for unexported PASS records and writes them to X:\For_Web\.
* Updates forweb_exported_at after successful export.
*
* Usage:
* node export-datasheets.js Export all pending (batch mode)
* node export-datasheets.js --limit 100 Export up to 100 records
* node export-datasheets.js --file <paths> Export records matching specific source files
* node export-datasheets.js --serial 178439-1 Export a specific serial number
* node export-datasheets.js --dry-run Show what would be exported without writing
*/
const fs = require('fs');
const path = require('path');
const db = require('./db');
const { loadAllSpecs, getSpecs } = require('../parsers/spec-reader');
const { generateExactDatasheet } = require('../templates/datasheet-exact');
// Configuration
const OUTPUT_DIR = 'X:\\For_Web';
const BATCH_SIZE = 500;
async function run() {
const args = process.argv.slice(2);
const dryRun = args.includes('--dry-run');
const limitIdx = args.indexOf('--limit');
const limit = limitIdx >= 0 ? parseInt(args[limitIdx + 1]) : 0;
const serialIdx = args.indexOf('--serial');
const serial = serialIdx >= 0 ? args[serialIdx + 1] : null;
const fileIdx = args.indexOf('--file');
const files = fileIdx >= 0 ? args.slice(fileIdx + 1).filter(f => !f.startsWith('--')) : null;
console.log('========================================');
console.log('Datasheet Export');
console.log('========================================');
console.log(`Output: ${OUTPUT_DIR}`);
console.log(`Dry run: ${dryRun}`);
if (limit) console.log(`Limit: ${limit}`);
if (serial) console.log(`Serial: ${serial}`);
console.log(`Start: ${new Date().toISOString()}`);
if (!dryRun && !fs.existsSync(OUTPUT_DIR)) {
console.error(`ERROR: Output directory does not exist: ${OUTPUT_DIR}`);
process.exit(1);
}
console.log('\nLoading model specs...');
const specMap = loadAllSpecs();
// Build query
const conditions = [`overall_result = 'PASS'`, `forweb_exported_at IS NULL`];
const params = [];
let paramIdx = 0;
if (serial) {
paramIdx++;
conditions.push(`serial_number = $${paramIdx}`);
params.push(serial);
}
if (files && files.length > 0) {
const placeholders = files.map(() => { paramIdx++; return `$${paramIdx}`; }).join(',');
conditions.push(`source_file IN (${placeholders})`);
params.push(...files);
}
let sql = `SELECT * FROM test_records WHERE ${conditions.join(' AND ')} ORDER BY test_date DESC`;
if (limit) {
paramIdx++;
sql += ` LIMIT $${paramIdx}`;
params.push(limit);
}
const records = await db.query(sql, params);
console.log(`\nFound ${records.length} records to export`);
if (records.length === 0) {
console.log('Nothing to export.');
await db.close();
return { exported: 0, skipped: 0, errors: 0 };
}
let exported = 0;
let skipped = 0;
let errors = 0;
let noSpecs = 0;
let pendingUpdates = [];
for (const record of records) {
try {
const specs = getSpecs(specMap, record.model_number);
if (!specs) {
noSpecs++;
skipped++;
continue;
}
const txt = generateExactDatasheet(record, specs);
if (!txt) {
skipped++;
continue;
}
const filename = record.serial_number + '.TXT';
const outputPath = path.join(OUTPUT_DIR, filename);
if (dryRun) {
console.log(` [DRY RUN] Would write: ${filename}`);
exported++;
} else {
fs.writeFileSync(outputPath, txt, 'utf8');
pendingUpdates.push(record.id);
exported++;
// Batch commit
if (pendingUpdates.length >= BATCH_SIZE) {
await flushUpdates(pendingUpdates);
pendingUpdates = [];
process.stdout.write(`\r Exported: ${exported} / ${records.length}`);
}
}
} catch (err) {
console.error(`\n ERROR exporting ${record.serial_number}: ${err.message}`);
errors++;
}
}
// Flush remaining updates
if (pendingUpdates.length > 0) {
await flushUpdates(pendingUpdates);
}
console.log(`\n\n========================================`);
console.log(`Export Complete`);
console.log(`========================================`);
console.log(`Exported: ${exported}`);
console.log(`Skipped: ${skipped} (${noSpecs} missing specs)`);
console.log(`Errors: ${errors}`);
console.log(`End: ${new Date().toISOString()}`);
await db.close();
return { exported, skipped, errors };
}
async function flushUpdates(ids) {
const now = new Date().toISOString();
await db.transaction(async (txClient) => {
for (const id of ids) {
await txClient.execute(
'UPDATE test_records SET forweb_exported_at = $1 WHERE id = $2',
[now, id]
);
}
});
}
// Export function for use by import.js (no db argument -- uses shared pool)
async function exportNewRecords(specMap, filePaths) {
if (!fs.existsSync(OUTPUT_DIR)) {
console.log(`[EXPORT] Output directory not found: ${OUTPUT_DIR}`);
return 0;
}
const conditions = [`overall_result = 'PASS'`, `forweb_exported_at IS NULL`];
const params = [];
let paramIdx = 0;
if (filePaths && filePaths.length > 0) {
const placeholders = filePaths.map(() => { paramIdx++; return `$${paramIdx}`; }).join(',');
conditions.push(`source_file IN (${placeholders})`);
params.push(...filePaths);
}
const sql = `SELECT * FROM test_records WHERE ${conditions.join(' AND ')}`;
const records = await db.query(sql, params);
if (records.length === 0) return 0;
let exported = 0;
await db.transaction(async (txClient) => {
for (const record of records) {
const specs = getSpecs(specMap, record.model_number);
if (!specs) continue;
const txt = generateExactDatasheet(record, specs);
if (!txt) continue;
const filename = record.serial_number + '.TXT';
const outputPath = path.join(OUTPUT_DIR, filename);
try {
fs.writeFileSync(outputPath, txt, 'utf8');
await txClient.execute(
'UPDATE test_records SET forweb_exported_at = $1 WHERE id = $2',
[new Date().toISOString(), record.id]
);
exported++;
} catch (err) {
console.error(`[EXPORT] Error writing ${filename}: ${err.message}`);
}
}
});
console.log(`[EXPORT] Generated ${exported} datasheet(s)`);
return exported;
}
if (require.main === module) {
run().catch(console.error);
}
module.exports = { exportNewRecords };