feat(pii): load generator word pools from embedded data files

.gitattributes

@@ -6,3 +6,8 @@ model/quantized/tokenizer_config.json filter= diff= merge= text
 model/quantized/special_tokens_map.json filter= diff= merge= text
 model/quantized/added_tokens.json filter= diff= merge= text
 *.onnx filter=lfs diff=lfs merge=lfs -text
+
+# PII generator word pools are embedded via //go:embed and parsed line by line.
+# Pin them to LF so the bytes embedded into the binary are identical regardless
+# of the build platform's checkout settings.
+src/backend/pii/generators/data/*.txt text eol=lf

src/backend/pii/generators/data/cities.txt

@@ -0,0 +1,74 @@
+# Dummy city pool for CityGenerator.
+# One value per line. Blank lines and lines starting with '#' are ignored.
+
+# US cities
+Springfield
+Riverside
+Greenville
+Fairview
+Madison
+Georgetown
+Salem
+Arlington
+Franklin
+Clinton
+Bristol
+Chester
+Dayton
+Kingston
+Newport
+Oakland
+Plymouth
+Burlington
+Manchester
+Lexington
+Milton
+Ashland
+Clayton
+Auburn
+Fairfield
+Marion
+Oxford
+Dover
+
+# Canadian cities
+Toronto
+Vancouver
+Calgary
+Ottawa
+Edmonton
+Winnipeg
+Halifax
+Victoria
+Regina
+Saskatoon
+Hamilton
+Kitchener
+London
+Windsor
+Burnaby
+Guelph
+
+# UK cities
+Birmingham
+Edinburgh
+Liverpool
+Leeds
+Sheffield
+Newcastle
+Nottingham
+Southampton
+Portsmouth
+Oxford
+Cambridge
+York
+Bath
+Brighton
+Cardiff
+Belfast
+Glasgow
+Aberdeen
+Dundee
+Swansea
+Norwich
+Exeter

src/backend/pii/generators/data/company_prefixes.txt

@@ -0,0 +1,47 @@
+# Dummy company-name prefix pool for CompanyNameGenerator.
+# One value per line. Blank lines and lines starting with '#' are ignored.
+
+Acme
+Global
+United
+Pacific
+Atlantic
+Northern
+Summit
+Horizon
+Apex
+Vanguard
+Pinnacle
+Premier
+Elite
+Prime
+Sterling
+Meridian
+Coastal
+Central
+National
+Continental
+Metro
+Allied
+Dynamic
+Synergy
+Fusion
+Vertex
+Quantum
+Nova
+Titan
+Omega
+Pioneer
+Frontier
+Legacy
+Heritage
+Keystone
+Benchmark
+Catalyst
+Spectrum
+Nexus
+Compass
+Evergreen
+Cornerstone
+Beacon
+Cascade

src/backend/pii/generators/data/company_suffixes.txt

@@ -0,0 +1,39 @@
+# Dummy company-name suffix pool for CompanyNameGenerator.
+# One value per line. Blank lines and lines starting with '#' are ignored.
+
+# US/International
+Inc
+LLC
+Corp
+Industries
+Solutions
+Group
+Holdings
+Partners
+Enterprises
+Co
+Technologies
+Systems
+Services
+Consulting
+Associates
+International
+Worldwide
+Labs
+Ventures
+
+# UK
+Ltd
+PLC
+Limited
+
+# German
+GmbH
+AG
+
+# French/Spanish
+SA
+SL
+
+# Australian
+Pty Ltd

src/backend/pii/generators/data/countries.txt

@@ -0,0 +1,78 @@
+# Dummy country pool for CountryGenerator.
+# One value per line. Blank lines and lines starting with '#' are ignored.
+
+# North America
+United States
+Canada
+Mexico
+
+# Europe
+United Kingdom
+Germany
+France
+Italy
+Spain
+Netherlands
+Belgium
+Switzerland
+Austria
+Sweden
+Norway
+Denmark
+Finland
+Ireland
+Poland
+Portugal
+Greece
+Czech Republic
+Hungary
+Romania
+Iceland
+Croatia
+
+# Asia
+Japan
+China
+South Korea
+India
+Singapore
+Thailand
+Vietnam
+Indonesia
+Malaysia
+Philippines
+Taiwan
+Hong Kong
+Nepal
+Sri Lanka
+
+# Oceania
+Australia
+New Zealand
+
+# South America
+Brazil
+Argentina
+Chile
+Colombia
+Peru
+Uruguay
+Ecuador
+
+# Africa
+South Africa
+Nigeria
+Kenya
+Egypt
+Morocco
+Ghana
+Tanzania
+Senegal
+
+# Middle East
+United Arab Emirates
+Israel
+Saudi Arabia
+Turkey
+Jordan
+Qatar

src/backend/pii/generators/data/email_firstnames.txt

@@ -0,0 +1,78 @@
+# Dummy email local-part first names for EmailGenerator.
+# One value per line. Blank lines and lines starting with '#' are ignored.
+# Must stay lowercase single ASCII words (no spaces, apostrophes, or accents):
+# the local part is formatted as first.last and is checked against [a-z]+.
+
+# Western
+jane
+john
+alex
+sam
+taylor
+casey
+jordan
+riley
+michael
+sarah
+david
+emily
+james
+emma
+robert
+olivia
+joseph
+laura
+morgan
+avery
+
+# Asian
+wei
+mei
+hiroshi
+yuki
+jin
+min
+raj
+priya
+ravi
+deepa
+
+# African
+amara
+kofi
+zara
+kwame
+nia
+jelani
+thabo
+lerato
+
+# Middle Eastern
+yusuf
+fatima
+omar
+layla
+ali
+nadia
+samir
+rania
+
+# Latin American
+carlos
+maria
+diego
+sofia
+miguel
+lucia
+javier
+daniela
+
+# Eastern European
+dmitri
+anna
+ivan
+katya
+alexei
+elena
+boris
+zofia