AaronPo/the-biergarten-app
1
0
Fork 0
mirror of https://github.com/aaronpo97/the-biergarten-app.git synced 2026-10-15 10:04:44 +00:00
Code Issues Packages Projects Releases Wiki Activity

Formatted src/services/enrichment/wikipedia

Browse Source
This commit is contained in:
Aaron Po
2026-07-19 04:10:33 -04:00
parent be90522eae
commit d4c7260127
2 changed files with 183 additions and 184 deletions
Download Patch File Download Diff File Expand all files Collapse all files

276
tooling/pipeline/src/services/enrichment/wikipedia/fetch_extract.cc
View File

@@ -15,147 +15,147 @@
using namespace boost; using namespace boost;
std::string WikipediaEnrichmentService::FetchExtract(std::string_view query) { std::string WikipediaEnrichmentService::FetchExtract(std::string_view query) {
const std::string cache_key(query); const std::string cache_key(query);
// 1. Cache Lookup // 1. Cache Lookup
if (const auto cache_it = this->extract_cache_.find(cache_key); if (const auto cache_it = this->extract_cache_.find(cache_key);
cache_it != this->extract_cache_.end()) { cache_it != this->extract_cache_.end()) {
if (logger_) { if (logger_) {
logger_->Log({.level = LogLevel::Debug,
.phase = PipelinePhase::Enrichment,
.message = std::format("Wikipedia: Cache hit for {}!",
cache_key)});
}
return cache_it->second;
}
const std::string encoded = this->client_->EncodeURL(cache_key);
const std::string url = std::format(
"https://en.wikipedia.org/w/"
"api.php?action=query&titles={}&prop=extracts&explaintext=1&format="
"json",
encoded);
const std::string body = this->client_->Get(url);
{
using namespace std::literals::chrono_literals;
std::this_thread::sleep_for(1s);
}
// 2. Parse JSON
system::error_code ec;
json::value doc = json::parse(body, ec);
if (ec) {
if (logger_) {
logger_->Log({.level = LogLevel::Warn,
.phase = PipelinePhase::Enrichment,
.message = std::format(
"WikipediaService: JSON parse error for '{}': {}",
std::string(query), ec.message())});
}
return {};
}
// 3. Safe Extraction
const json::object* obj = doc.if_object();
if (obj == nullptr) {
if (logger_) {
logger_->Log({.level = LogLevel::Warn,
.phase = PipelinePhase::Enrichment,
.message = std::format(
"WikipediaService: Expected root object for '{}'",
std::string(query))});
}
return {};
}
const json::value* query_ptr = obj->if_contains("query");
const json::value* pages_ptr =
((query_ptr != nullptr) && query_ptr->is_object())
? query_ptr->get_object().if_contains("pages")
: nullptr;
if ((pages_ptr == nullptr) || !pages_ptr->is_object()) {
if (logger_) {
logger_->Log({.level = LogLevel::Warn,
.phase = PipelinePhase::Enrichment,
.message = std::format(
"WikipediaService: Missing query.pages for '{}'",
std::string(query))});
}
return {};
}
const json::object& pages = pages_ptr->get_object();
if (pages.empty()) {
if (logger_) {
logger_->Log({.level = LogLevel::Warn,
.phase = PipelinePhase::Enrichment,
.message = std::format(
"WikipediaService: No pages returned for '{}'",
std::string(query))});
}
this->extract_cache_.emplace(cache_key, "");
return {};
}
// Wikipedia returns the page under a dynamic ID key; we just want the first
// one
const json::value& page_val = pages.begin()->value();
if (!page_val.is_object()) {
if (logger_) {
logger_->Log({.level = LogLevel::Warn,
.phase = PipelinePhase::Enrichment,
.message = std::format(
"WikipediaService: Unexpected page format for '{}'",
std::string(query))});
}
return {};
}
const json::object& page = page_val.get_object();
// Handle 404/Missing status
if (page.contains("missing")) {
if (logger_) {
logger_->Log({.level = LogLevel::Warn,
.phase = PipelinePhase::Enrichment,
.message = std::format(
"WikipediaService: Page '{}' does not exist",
std::string(query))});
}
this->extract_cache_.emplace(cache_key, "");
return {};
}
const json::value* extract_ptr = page.if_contains("extract");
if ((extract_ptr == nullptr) || !extract_ptr->is_string()) {
if (logger_) {
logger_->Log({.level = LogLevel::Warn,
.phase = PipelinePhase::Enrichment,
.message = std::format(
"WikipediaService: No extract string found for '{}'",
std::string(query))});
}
this->extract_cache_.emplace(cache_key, "");
return {};
}
// 4. Success
std::string extract(extract_ptr->as_string());
if (logger_) {
logger_->Log( logger_->Log(
{.level = LogLevel::Debug, {.level = LogLevel::Info,
.phase = PipelinePhase::Enrichment, .phase = PipelinePhase::Enrichment,
.message = std::format("Wikipedia: Cache hit for {}!", cache_key)}); .message = std::format("WikipediaService: Fetched {} chars for '{}'",
} extract.size(), std::string(query))});
return cache_it->second; }
}
const std::string encoded = this->client_->EncodeURL(cache_key); this->extract_cache_.insert_or_assign(cache_key, extract);
const std::string url = std::format(
"https://en.wikipedia.org/w/"
"api.php?action=query&titles={}&prop=extracts&explaintext=1&format="
"json",
encoded);
const std::string body = this->client_->Get(url); return extract;
{
using namespace std::literals::chrono_literals;
std::this_thread::sleep_for(1s);
}
// 2. Parse JSON
system::error_code ec;
json::value doc = json::parse(body, ec);
if (ec) {
if (logger_) {
logger_->Log({.level = LogLevel::Warn,
.phase = PipelinePhase::Enrichment,
.message = std::format(
"WikipediaService: JSON parse error for '{}': {}",
std::string(query), ec.message())});
}
return {};
}
// 3. Safe Extraction
const json::object* obj = doc.if_object();
if (obj == nullptr) {
if (logger_) {
logger_->Log({.level = LogLevel::Warn,
.phase = PipelinePhase::Enrichment,
.message = std::format(
"WikipediaService: Expected root object for '{}'",
std::string(query))});
}
return {};
}
const json::value* query_ptr = obj->if_contains("query");
const json::value* pages_ptr =
((query_ptr != nullptr) && query_ptr->is_object())
? query_ptr->get_object().if_contains("pages")
: nullptr;
if ((pages_ptr == nullptr) || !pages_ptr->is_object()) {
if (logger_) {
logger_->Log({.level = LogLevel::Warn,
.phase = PipelinePhase::Enrichment,
.message = std::format(
"WikipediaService: Missing query.pages for '{}'",
std::string(query))});
}
return {};
}
const json::object& pages = pages_ptr->get_object();
if (pages.empty()) {
if (logger_) {
logger_->Log({.level = LogLevel::Warn,
.phase = PipelinePhase::Enrichment,
.message = std::format(
"WikipediaService: No pages returned for '{}'",
std::string(query))});
}
this->extract_cache_.emplace(cache_key, "");
return {};
}
// Wikipedia returns the page under a dynamic ID key; we just want the first
// one
const json::value& page_val = pages.begin()->value();
if (!page_val.is_object()) {
if (logger_) {
logger_->Log({.level = LogLevel::Warn,
.phase = PipelinePhase::Enrichment,
.message = std::format(
"WikipediaService: Unexpected page format for '{}'",
std::string(query))});
}
return {};
}
const json::object& page = page_val.get_object();
// Handle 404/Missing status
if (page.contains("missing")) {
if (logger_) {
logger_->Log(
{.level = LogLevel::Warn,
.phase = PipelinePhase::Enrichment,
.message = std::format("WikipediaService: Page '{}' does not exist",
std::string(query))});
}
this->extract_cache_.emplace(cache_key, "");
return {};
}
const json::value* extract_ptr = page.if_contains("extract");
if ((extract_ptr == nullptr) || !extract_ptr->is_string()) {
if (logger_) {
logger_->Log({.level = LogLevel::Warn,
.phase = PipelinePhase::Enrichment,
.message = std::format(
"WikipediaService: No extract string found for '{}'",
std::string(query))});
}
this->extract_cache_.emplace(cache_key, "");
return {};
}
// 4. Success
std::string extract(extract_ptr->as_string());
if (logger_) {
logger_->Log(
{.level = LogLevel::Info,
.phase = PipelinePhase::Enrichment,
.message = std::format("WikipediaService: Fetched {} chars for '{}'",
extract.size(), std::string(query))});
}
this->extract_cache_.insert_or_assign(cache_key, extract);
return extract;
} }

91
tooling/pipeline/src/services/enrichment/wikipedia/get_summary.cc
View File

@@ -10,55 +10,54 @@
#include "services/enrichment/wikipedia_service.h" #include "services/enrichment/wikipedia_service.h"
std::string WikipediaEnrichmentService::GetLocationContext( std::string WikipediaEnrichmentService::GetLocationContext(const City& loc) {
const City& loc) { using namespace std::literals::chrono_literals;
using namespace std::literals::chrono_literals; if (!this->client_) {
if (!this->client_) { if (logger_) {
if (logger_) { logger_->Log({.level = LogLevel::Warn,
logger_->Log({.level = LogLevel::Warn, .phase = PipelinePhase::Enrichment,
.phase = PipelinePhase::Enrichment, .message = "Wikipedia client is nullptr."});
.message = "Wikipedia client is nullptr."}); }
} return {};
return {}; }
}
std::string result; std::string result;
constexpr std::string_view brewing_query = "brewing"; constexpr std::string_view brewing_query = "brewing";
const std::string location_query = const std::string location_query =
std::format("{}, {}", loc.city, loc.iso3166_2); std::format("{}, {}", loc.city, loc.iso3166_2);
const std::string beer_query = std::format("beer in {}", loc.country); const std::string beer_query = std::format("beer in {}", loc.country);
auto append_extract = [&result](const std::string& extract) -> void { auto append_extract = [&result](const std::string& extract) -> void {
if (extract.empty()) { if (extract.empty()) {
return; return;
} }
if (!result.empty()) { if (!result.empty()) {
result += "\n\n"; result += "\n\n";
} }
result += extract; result += extract;
}; };
try { try {
append_extract(FetchExtract(brewing_query)); append_extract(FetchExtract(brewing_query));
append_extract(FetchExtract(beer_query)); append_extract(FetchExtract(beer_query));
if (logger_) { if (logger_) {
logger_->Log({.level = LogLevel::Info, logger_->Log({.level = LogLevel::Info,
.phase = PipelinePhase::Enrichment, .phase = PipelinePhase::Enrichment,
.message = std::format( .message = std::format(
"Done fetching for {}. Sleeping for 10 seconds.", "Done fetching for {}. Sleeping for 10 seconds.",
location_query)}); location_query)});
} }
std::this_thread::sleep_for(10s); std::this_thread::sleep_for(10s);
} catch (const std::runtime_error& e) { } catch (const std::runtime_error& e) {
if (logger_) { if (logger_) {
logger_->Log( logger_->Log({.level = LogLevel::Debug,
{.level = LogLevel::Debug, .phase = PipelinePhase::Enrichment,
.phase = PipelinePhase::Enrichment, .message = std::format(
.message = std::format("WikipediaService lookup failed for '{}': {}", "WikipediaService lookup failed for '{}': {}",
location_query, e.what())}); location_query, e.what())});
} }
} }
return result; return result;
} }