From aee6efd79321b5fb10d8988da4fbf8c22e18c964 Mon Sep 17 00:00:00 2001
From: mibali <mtbdesigns01@gmail.com>
Date: Wed, 27 May 2026 16:58:46 +0100
Subject: [PATCH] fix: restore branch-only regressions safely

---
 extension-ready/popup.js           |  4 +++-
 shared/role-profile-service.js     | 35 ++++++++++++++++++++++++++++++
 tests/popup-stats-ui.test.js       | 22 +++++++++++++++++++
 tests/role-profile-service.test.js |  7 ++++++
 4 files changed, 67 insertions(+), 1 deletion(-)

diff --git a/extension-ready/popup.js b/extension-ready/popup.js
index 5e66a98..c93689d 100644
--- a/extension-ready/popup.js
+++ b/extension-ready/popup.js
@@ -1041,7 +1041,9 @@ document.addEventListener('DOMContentLoaded', async () => {
     const li  = text.match(/(?:https?:\/\/)?(?:www\.)?linkedin\.com\/in\/[\w-]+\/?/i);
     const gh  = text.match(/(?:https?:\/\/)?(?:www\.)?github\.com\/[\w-]+\/?/i);
     const tw  = text.match(/(?:https?:\/\/)?(?:www\.)?(?:twitter|x)\.com\/[\w-]+\/?/i);
-    const web = text.match(/\b(?:https?:\/\/|www\.)(?!(?:www\.)?(?:linkedin|github|twitter|x)\.com\b)[\w.-]+\.[a-z]{2,}(?:\/[\w./-]*)?/i);
+    const web = text.match(
+      /(?<!@)\b(?:(?:https?:\/\/|www\.)?(?!(?:www\.)?(?:linkedin|github|twitter|x)\.com\b)(?:[a-z0-9](?:[a-z0-9-]{0,61}[a-z0-9])?\.)+[a-z]{2,63}(?:\/[a-z0-9\-._~:/?#[\]@!$&'()*+,;=%]*)?)/i
+    );
     return {
       linkedin:  ensure(li?.[0]),
       github:    ensure(gh?.[0]),
diff --git a/shared/role-profile-service.js b/shared/role-profile-service.js
index 06b335b..27470a0 100644
--- a/shared/role-profile-service.js
+++ b/shared/role-profile-service.js
@@ -122,6 +122,41 @@ export const ROLE_PROFILES = [
     ],
     positioning: 'Position the CV around analytical judgement, decision support, data quality, stakeholder requirements, and reporting outcomes. Avoid advanced modelling claims unless the CV proves them.',
   },
+  {
+    id: 'data_engineer',
+    family: 'Data Engineering',
+    domain: 'data_engineering',
+    aliases: [
+      'data engineer',
+      'database architect',
+      'data architect',
+      'database developer',
+      'database programmer',
+      'data warehouse developer',
+      'data warehousing specialist',
+      'etl developer',
+    ],
+    titlePatterns: [
+      /\bdata\s+engineer\b/i,
+      /\bdatabase\s+architect\b/i,
+      /\bdata\s+architect\b/i,
+      /\bdata\s+warehouse\b/i,
+      /\bdata\s+warehousing\b/i,
+      /\betl\s+developer\b/i,
+    ],
+    credibilitySignals: ['data pipelines', 'ETL/ELT delivery', 'data modelling', 'data quality', 'warehouse performance', 'reliable datasets'],
+    evidencePatterns: [/\b(?:etl|elt)\b/i, /\bpipeline\b/i, /\bdata\s+model/i, /\bwarehouse\b/i, /\b(sql|postgres|mysql|snowflake|bigquery|redshift)\b/i, /\b(airflow|prefect|dagster)\b/i, /\bdbt\b/i],
+    riskClaims: ['enterprise data strategy ownership', 'org-wide data governance ownership', 'security/compliance sign-off', '24/7 production on-call'],
+    transferableEvidence: ['backend engineering -> data service reliability', 'analytics/reporting -> dataset quality improvement', 'platform engineering -> workflow orchestration and observability'],
+    skillCategories: [
+      { label: 'Pipelines & Orchestration', skills: ['ETL/ELT', 'Batch Pipelines', 'Streaming Basics', 'Workflow Orchestration'] },
+      { label: 'Data Modelling & Warehousing', skills: ['Dimensional Modelling', 'Schema Design', 'Data Warehousing', 'Performance Tuning'] },
+      { label: 'Quality & Reliability', skills: ['Data Quality Checks', 'Testing', 'Monitoring', 'Incident Response'] },
+      { label: 'SQL & Storage', skills: ['SQL', 'PostgreSQL', 'Snowflake', 'BigQuery', 'Redshift'] },
+      { label: 'Automation & Governance', skills: ['Automation', 'Documentation', 'Lineage Basics', 'Access Controls Basics'] },
+    ],
+    positioning: 'Position the CV around reliable data pipelines, data modelling, warehouse performance, data quality, and dependable datasets for stakeholders. Avoid data strategy/governance ownership claims unless explicitly proven.',
+  },
   {
     id: 'customer_success',
     family: 'Customer Success / Support',
diff --git a/tests/popup-stats-ui.test.js b/tests/popup-stats-ui.test.js
index af78e74..ac8fd82 100644
--- a/tests/popup-stats-ui.test.js
+++ b/tests/popup-stats-ui.test.js
@@ -1,4 +1,5 @@
 import fs from 'node:fs';
+import vm from 'node:vm';
 import { describe, expect, it } from 'vitest';
 
 const popupHtml = fs.readFileSync(new URL('../extension-ready/popup.html', import.meta.url), 'utf8');
@@ -7,6 +8,14 @@ const contentJs = fs.readFileSync(new URL('../extension-ready/content.js', impor
 const contentCss = fs.readFileSync(new URL('../extension-ready/content.css', import.meta.url), 'utf8');
 const backgroundJs = fs.readFileSync(new URL('../extension-ready/background.js', import.meta.url), 'utf8');
 
+function loadExtractCvContactUrls() {
+  const match = popupJs.match(/function extractCvContactUrls\(text\) \{[\s\S]*?\n  \}/);
+  if (!match) throw new Error('extractCvContactUrls not found');
+  const sandbox = {};
+  vm.runInNewContext(`${match[0]}\nglobalThis.__extractCvContactUrls = extractCvContactUrls;`, sandbox);
+  return sandbox.__extractCvContactUrls;
+}
+
 describe('popup productivity stats UI', () => {
   it('renders the empty collapsed state', () => {
     expect(popupHtml).toContain('id="stats-summary">No activity yet</span>');
@@ -90,4 +99,17 @@ describe('popup productivity stats UI', () => {
     expect(contentJs).toContain('labelTextWithoutControls');
     expect(contentJs).toContain("field.closest?.('label')");
   });
+
+  it('extracts bare portfolio domains without treating emails as websites', () => {
+    const extractCvContactUrls = loadExtractCvContactUrls();
+    const urls = extractCvContactUrls(`Jane Doe
+jane@example.xyz
+linkedin.com/in/janedoe
+github.com/janedoe
+portfolio.xyz/work`);
+
+    expect(urls.linkedin).toBe('https://linkedin.com/in/janedoe');
+    expect(urls.github).toBe('https://github.com/janedoe');
+    expect(urls.website).toBe('https://portfolio.xyz/work');
+  });
 });
diff --git a/tests/role-profile-service.test.js b/tests/role-profile-service.test.js
index 4e81309..4d490c9 100644
--- a/tests/role-profile-service.test.js
+++ b/tests/role-profile-service.test.js
@@ -24,6 +24,13 @@ describe('RoleProfileService', () => {
     expect(service.classify({ jobTitle: 'Healthcare Administrator' })?.id).toBe('healthcare_admin');
   });
 
+  it('classifies data-engineering job titles into the data engineering role profile', () => {
+    expect(service.classify({ jobTitle: 'Data Engineer' })?.id).toBe('data_engineer');
+    expect(service.classify({ jobTitle: 'Database Architect' })?.id).toBe('data_engineer');
+    expect(service.classify({ jobTitle: 'ETL Developer' })?.id).toBe('data_engineer');
+    expect(service.enrichJDData({ jobTitle: 'Data Engineer' }).domain).toBe('data_engineering');
+  });
+
   it('enriches parsed JD data with positioning, credibility signals, risks, and skill categories', () => {
     const enriched = service.enrichJDData({
       jobTitle: 'Product Manager',