Pipeline: City rename, add address/postal-code generation, add xeger generation (#232)

This commit is contained in:
Aaron Po
2026-07-19 03:59:06 -04:00
parent 901f30ffd8
commit 8e7ecf2fc3
56 changed files with 2454 additions and 1151 deletions

View File

@@ -36,7 +36,9 @@ static std::string FormatLocalLanguageCodes(
static constexpr int kBreweryInitialMaxTokens = 2800;
BreweryResult LlamaGenerator::GenerateBrewery(
const Location& location, const std::string& region_context) {
const EnrichedCity& enriched_city) {
const City& location = enriched_city.location;
const std::string& region_context = enriched_city.region_context;
/**
* Preprocess and truncate region context to manageable size
*/
@@ -66,7 +68,7 @@ BreweryResult LlamaGenerator::GenerateBrewery(
* Store location context for retry prompts (without repeating full context)
*/
const std::string retry_location =
std::format("Location: {}{}\nLocal language codes: {}", location.city,
std::format("City: {}{}\nLocal language codes: {}", location.city,
country_suffix, local_language_codes);
/**

View File

@@ -8,14 +8,14 @@
#include "data_generation/mock_generator.h"
size_t MockGenerator::DeterministicHash(const Location& location) {
size_t MockGenerator::DeterministicHash(const City& location) {
size_t seed = 0;
boost::hash_combine(seed, location.city);
boost::hash_combine(seed, location.country);
return seed;
}
size_t MockGenerator::DeterministicHash(const Location& location,
size_t MockGenerator::DeterministicHash(const City& location,
const UserPersona& persona,
const Name& name) {
size_t seed = DeterministicHash(location);

View File

@@ -11,7 +11,8 @@
#include "data_generation/mock_generator.h"
BreweryResult MockGenerator::GenerateBrewery(
const Location& location, const std::string& /*region_context*/) {
const EnrichedCity& enriched_city) {
const City& location = enriched_city.location;
const size_t hash = DeterministicHash(location);
const std::string_view adjective =