mirror of
https://github.com/aaronpo97/the-biergarten-app.git
synced 2026-07-16 17:47:22 +00:00
Add timeout to wikipedia enrichment to avoid breaking rate limits, add mock enrichment (#224)
* Add timeout for enrichment, refactor json deserialization * Add location count to application options and as a cli arg * Add mock enrichment process
This commit is contained in:
@@ -0,0 +1,112 @@
|
||||
/**
|
||||
* @file wikipedia/fetch_extract.cc
|
||||
*/
|
||||
|
||||
#include <spdlog/spdlog.h>
|
||||
|
||||
#include <boost/json.hpp>
|
||||
#include <chrono>
|
||||
#include <format>
|
||||
#include <string>
|
||||
#include <string_view>
|
||||
#include <thread>
|
||||
|
||||
#include "services/enrichment/wikipedia_service.h"
|
||||
|
||||
using namespace boost;
|
||||
|
||||
std::string WikipediaEnrichmentService::FetchExtract(std::string_view query) {
|
||||
|
||||
const std::string cache_key(query);
|
||||
|
||||
// 1. Cache Lookup
|
||||
if (const auto cache_it = this->extract_cache_.find(cache_key);
|
||||
cache_it != this->extract_cache_.end()) {
|
||||
spdlog::debug("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) {
|
||||
spdlog::warn("WikipediaService: JSON parse error for '{}': {}", query,
|
||||
ec.message());
|
||||
return {};
|
||||
}
|
||||
|
||||
// 3. Safe Extraction
|
||||
const json::object* obj = doc.if_object();
|
||||
if (obj == nullptr) {
|
||||
spdlog::warn("WikipediaService: Expected root object for '{}'", 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()) {
|
||||
spdlog::warn("WikipediaService: Missing query.pages for '{}'", query);
|
||||
return {};
|
||||
}
|
||||
|
||||
const json::object& pages = pages_ptr->get_object();
|
||||
|
||||
if (pages.empty()) {
|
||||
spdlog::warn("WikipediaService: No pages returned for '{}'", 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()) {
|
||||
spdlog::warn("WikipediaService: Unexpected page format for '{}'", query);
|
||||
return {};
|
||||
}
|
||||
|
||||
const json::object& page = page_val.get_object();
|
||||
|
||||
// Handle 404/Missing status
|
||||
if (page.contains("missing")) {
|
||||
spdlog::warn("WikipediaService: Page '{}' does not exist", 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()) {
|
||||
spdlog::warn("WikipediaService: No extract string found for '{}'", query);
|
||||
this->extract_cache_.emplace(cache_key, "");
|
||||
return {};
|
||||
}
|
||||
|
||||
// 4. Success
|
||||
std::string extract(extract_ptr->as_string());
|
||||
spdlog::info("WikipediaService: Fetched {} chars for '{}'", extract.size(),
|
||||
query);
|
||||
|
||||
this->extract_cache_.insert_or_assign(cache_key, extract);
|
||||
|
||||
return extract;
|
||||
}
|
||||
@@ -0,0 +1,58 @@
|
||||
/**
|
||||
* @file wikipedia/get_summary.cc
|
||||
* @brief WikipediaService::GetLocationContext() implementation.
|
||||
*/
|
||||
|
||||
#include <spdlog/spdlog.h>
|
||||
|
||||
#include <chrono>
|
||||
#include <format>
|
||||
#include <string>
|
||||
#include <thread>
|
||||
|
||||
#include "services/enrichment/wikipedia_service.h"
|
||||
|
||||
std::string WikipediaEnrichmentService::GetLocationContext(const Location& loc) {
|
||||
using namespace std::literals::chrono_literals;
|
||||
if (!this->client_) {
|
||||
spdlog::warn("Client is nullptr.");
|
||||
return {};
|
||||
}
|
||||
|
||||
std::string result;
|
||||
|
||||
// std::string region_query(loc.city);
|
||||
// if (!loc.country.empty()) {
|
||||
// region_query += loc.state_province,
|
||||
// region_query += ", ";
|
||||
// region_query += loc.country;
|
||||
// }
|
||||
|
||||
constexpr std::string_view brewing_query = "brewing";
|
||||
const std::string location_query =
|
||||
std::format("{}, {}", loc.city, loc.iso3166_2);
|
||||
const std::string beer_query = std::format("beer in {}", loc.country);
|
||||
|
||||
auto append_extract = [&result](const std::string& extract) -> void {
|
||||
if (extract.empty()) {
|
||||
return;
|
||||
}
|
||||
if (!result.empty()) {
|
||||
result += "\n\n";
|
||||
}
|
||||
result += extract;
|
||||
};
|
||||
|
||||
try {
|
||||
append_extract(FetchExtract(brewing_query));
|
||||
append_extract(FetchExtract(beer_query));
|
||||
spdlog::info("Done fetching for {}. Sleeping for 10 seconds.",
|
||||
location_query);
|
||||
std::this_thread::sleep_for(10s);
|
||||
|
||||
} catch (const std::runtime_error& e) {
|
||||
spdlog::debug("WikipediaService lookup failed for '{}': {}", location_query,
|
||||
e.what());
|
||||
}
|
||||
return result;
|
||||
}
|
||||
@@ -7,5 +7,6 @@
|
||||
|
||||
#include <utility>
|
||||
|
||||
WikipediaService::WikipediaService(std::unique_ptr<WebClient> client)
|
||||
WikipediaEnrichmentService::WikipediaEnrichmentService(
|
||||
std::unique_ptr<WebClient> client)
|
||||
: client_(std::move(client)) {}
|
||||
@@ -1,61 +0,0 @@
|
||||
/**
|
||||
* @file wikipedia/fetch_extract.cc
|
||||
* @brief WikipediaService::FetchExtract() implementation.
|
||||
*/
|
||||
|
||||
#include <spdlog/spdlog.h>
|
||||
|
||||
#include <boost/json.hpp>
|
||||
#include <string>
|
||||
#include <string_view>
|
||||
|
||||
#include "services/enrichment/wikipedia_service.h"
|
||||
|
||||
std::string WikipediaService::FetchExtract(std::string_view query) {
|
||||
const std::string cache_key(query);
|
||||
const auto cache_it = this->extract_cache_.find(cache_key);
|
||||
if (cache_it != this->extract_cache_.end()) {
|
||||
return cache_it->second;
|
||||
}
|
||||
|
||||
const std::string encoded = this->client_->UrlEncode(cache_key);
|
||||
const std::string url =
|
||||
"https://en.wikipedia.org/w/api.php?action=query&titles=" + encoded +
|
||||
"&prop=extracts&explaintext=1&format=json";
|
||||
|
||||
const std::string body = this->client_->Get(url);
|
||||
|
||||
boost::system::error_code parse_error;
|
||||
boost::json::value doc = boost::json::parse(body, parse_error);
|
||||
|
||||
if (!parse_error && doc.is_object()) {
|
||||
try {
|
||||
auto& pages = doc.at("query").at("pages").get_object();
|
||||
if (!pages.empty()) {
|
||||
auto& page = pages.begin()->value().get_object();
|
||||
if (page.contains("extract") && page.at("extract").is_string()) {
|
||||
const std::string_view extract_view = page.at("extract").as_string();
|
||||
std::string extract(extract_view);
|
||||
|
||||
spdlog::debug("WikipediaService fetched {} chars for '{}'",
|
||||
extract.size(), query);
|
||||
|
||||
this->extract_cache_.emplace(cache_key, extract);
|
||||
return extract;
|
||||
}
|
||||
}
|
||||
this->extract_cache_.emplace(cache_key, std::string{});
|
||||
} catch (const std::exception& e) {
|
||||
spdlog::warn(
|
||||
"WikipediaService: failed to parse response structure for '{}': "
|
||||
"{}",
|
||||
query, e.what());
|
||||
return {};
|
||||
}
|
||||
} else if (parse_error) {
|
||||
spdlog::warn("WikipediaService: JSON parse error for '{}': {}", query,
|
||||
parse_error.message());
|
||||
}
|
||||
|
||||
return {};
|
||||
}
|
||||
@@ -1,47 +0,0 @@
|
||||
/**
|
||||
* @file wikipedia/get_summary.cc
|
||||
* @brief WikipediaService::GetLocationContext() implementation.
|
||||
*/
|
||||
|
||||
#include <spdlog/spdlog.h>
|
||||
|
||||
#include <string>
|
||||
|
||||
#include "services/enrichment/wikipedia_service.h"
|
||||
|
||||
std::string WikipediaService::GetLocationContext(const Location& loc) {
|
||||
if (!client_) {
|
||||
return {};
|
||||
}
|
||||
|
||||
std::string result;
|
||||
|
||||
std::string region_query(loc.city);
|
||||
if (!loc.country.empty()) {
|
||||
region_query += ", ";
|
||||
region_query += loc.country;
|
||||
}
|
||||
|
||||
const std::string beer_query = "beer in " + loc.country;
|
||||
const std::string city_beer_query = "beer in " + loc.city;
|
||||
|
||||
auto append_extract = [&result](const std::string& extract) -> void {
|
||||
if (extract.empty()) {
|
||||
return;
|
||||
}
|
||||
if (!result.empty()) {
|
||||
result += "\n\n";
|
||||
}
|
||||
result += extract;
|
||||
};
|
||||
|
||||
try {
|
||||
append_extract(FetchExtract(region_query));
|
||||
append_extract(FetchExtract(beer_query));
|
||||
append_extract(FetchExtract(city_beer_query));
|
||||
} catch (const std::runtime_error& e) {
|
||||
spdlog::debug("WikipediaService lookup failed for '{}': {}", region_query,
|
||||
e.what());
|
||||
}
|
||||
return result;
|
||||
}
|
||||
Reference in New Issue
Block a user