2023-04-27 17:53:28 +03:00
|
|
|
//! This module provides the functionality to handle different routes of the `websurfx`
|
|
|
|
//! meta search engine website and provide approriate response to each route/page
|
|
|
|
//! when requested.
|
|
|
|
|
2023-04-22 14:35:07 +03:00
|
|
|
use std::fs::read_to_string;
|
|
|
|
|
2023-05-02 11:58:21 +03:00
|
|
|
use crate::{
|
|
|
|
cache::cacher::RedisCache,
|
|
|
|
config_parser::parser::Config,
|
2023-05-25 11:50:37 +03:00
|
|
|
handler::public_path_handler::handle_different_public_path,
|
2023-05-02 11:58:21 +03:00
|
|
|
search_results_handler::{aggregation_models::SearchResults, aggregator::aggregate},
|
|
|
|
};
|
2023-04-22 14:35:07 +03:00
|
|
|
use actix_web::{get, web, HttpRequest, HttpResponse};
|
|
|
|
use handlebars::Handlebars;
|
|
|
|
use serde::Deserialize;
|
|
|
|
|
2023-04-27 17:53:28 +03:00
|
|
|
/// A named struct which deserializes all the user provided search parameters and stores them.
|
|
|
|
///
|
|
|
|
/// # Fields
|
|
|
|
///
|
|
|
|
/// * `q` - It stores the search parameter option `q` (or query in simple words)
|
|
|
|
/// of the search url.
|
|
|
|
/// * `page` - It stores the search parameter `page` (or pageno in simple words)
|
|
|
|
/// of the search url.
|
2023-07-14 21:29:01 +03:00
|
|
|
#[derive(Deserialize)]
|
2023-04-22 14:35:07 +03:00
|
|
|
struct SearchParams {
|
|
|
|
q: Option<String>,
|
|
|
|
page: Option<u32>,
|
|
|
|
}
|
|
|
|
|
2023-04-27 17:53:28 +03:00
|
|
|
/// Handles the route of index page or main page of the `websurfx` meta search engine website.
|
2023-04-22 14:35:07 +03:00
|
|
|
#[get("/")]
|
|
|
|
pub async fn index(
|
|
|
|
hbs: web::Data<Handlebars<'_>>,
|
2023-04-30 18:16:08 +03:00
|
|
|
config: web::Data<Config>,
|
2023-04-22 14:35:07 +03:00
|
|
|
) -> Result<HttpResponse, Box<dyn std::error::Error>> {
|
2023-04-30 18:16:08 +03:00
|
|
|
let page_content: String = hbs.render("index", &config.style).unwrap();
|
2023-04-22 14:35:07 +03:00
|
|
|
Ok(HttpResponse::Ok().body(page_content))
|
|
|
|
}
|
|
|
|
|
2023-04-27 17:53:28 +03:00
|
|
|
/// Handles the route of any other accessed route/page which is not provided by the
|
|
|
|
/// website essentially the 404 error page.
|
2023-04-22 14:35:07 +03:00
|
|
|
pub async fn not_found(
|
|
|
|
hbs: web::Data<Handlebars<'_>>,
|
2023-04-30 18:16:08 +03:00
|
|
|
config: web::Data<Config>,
|
2023-04-22 14:35:07 +03:00
|
|
|
) -> Result<HttpResponse, Box<dyn std::error::Error>> {
|
2023-04-30 18:16:08 +03:00
|
|
|
let page_content: String = hbs.render("404", &config.style)?;
|
2023-04-22 14:35:07 +03:00
|
|
|
|
|
|
|
Ok(HttpResponse::Ok()
|
|
|
|
.content_type("text/html; charset=utf-8")
|
|
|
|
.body(page_content))
|
|
|
|
}
|
|
|
|
|
2023-07-15 13:36:46 +03:00
|
|
|
/// A named struct which is used to deserialize the cookies fetched from the client side.
|
|
|
|
///
|
|
|
|
/// # Fields
|
|
|
|
///
|
|
|
|
/// * `theme` - It stores the theme name used in the website.
|
|
|
|
/// * `colorscheme` - It stores the colorscheme name used for the website theme.
|
|
|
|
/// * `engines` - It stores the user selected upstream search engines selected from the UI.
|
2023-07-14 17:20:46 +03:00
|
|
|
#[allow(dead_code)]
|
|
|
|
#[derive(Deserialize)]
|
|
|
|
struct Cookie {
|
|
|
|
theme: String,
|
|
|
|
colorscheme: String,
|
|
|
|
engines: Vec<String>,
|
|
|
|
}
|
|
|
|
|
2023-04-27 17:53:28 +03:00
|
|
|
/// Handles the route of search page of the `websurfx` meta search engine website and it takes
|
|
|
|
/// two search url parameters `q` and `page` where `page` parameter is optional.
|
|
|
|
///
|
|
|
|
/// # Example
|
|
|
|
///
|
|
|
|
/// ```bash
|
|
|
|
/// curl "http://127.0.0.1:8080/search?q=sweden&page=1"
|
|
|
|
/// ```
|
2023-04-30 18:16:08 +03:00
|
|
|
///
|
2023-04-27 17:53:28 +03:00
|
|
|
/// Or
|
|
|
|
///
|
|
|
|
/// ```bash
|
|
|
|
/// curl "http://127.0.0.1:8080/search?q=sweden"
|
|
|
|
/// ```
|
2023-04-22 14:35:07 +03:00
|
|
|
#[get("/search")]
|
|
|
|
pub async fn search(
|
|
|
|
hbs: web::Data<Handlebars<'_>>,
|
|
|
|
req: HttpRequest,
|
2023-04-30 18:16:08 +03:00
|
|
|
config: web::Data<Config>,
|
2023-04-22 14:35:07 +03:00
|
|
|
) -> Result<HttpResponse, Box<dyn std::error::Error>> {
|
|
|
|
let params = web::Query::<SearchParams>::from_query(req.query_string())?;
|
2023-05-02 11:58:21 +03:00
|
|
|
|
|
|
|
//Initialize redis cache connection struct
|
2023-05-15 00:20:43 +00:00
|
|
|
let mut redis_cache = RedisCache::new(config.redis_connection_url.clone())?;
|
2023-04-22 14:35:07 +03:00
|
|
|
match ¶ms.q {
|
|
|
|
Some(query) => {
|
|
|
|
if query.trim().is_empty() {
|
|
|
|
Ok(HttpResponse::Found()
|
|
|
|
.insert_header(("location", "/"))
|
|
|
|
.finish())
|
|
|
|
} else {
|
2023-05-23 09:34:46 +00:00
|
|
|
let page_url: String; // Declare the page_url variable without initializing it
|
2023-05-02 11:58:21 +03:00
|
|
|
|
2023-05-19 17:13:11 +05:30
|
|
|
// ...
|
2023-05-23 09:34:46 +00:00
|
|
|
|
2023-05-02 11:58:21 +03:00
|
|
|
let page = match params.page {
|
|
|
|
Some(page_number) => {
|
|
|
|
if page_number <= 1 {
|
|
|
|
page_url = format!(
|
|
|
|
"http://{}:{}/search?q={}&page={}",
|
|
|
|
config.binding_ip_addr, config.port, query, 1
|
|
|
|
);
|
|
|
|
1
|
|
|
|
} else {
|
|
|
|
page_url = format!(
|
|
|
|
"http://{}:{}/search?q={}&page={}",
|
|
|
|
config.binding_ip_addr, config.port, query, page_number
|
|
|
|
);
|
2023-05-23 09:34:46 +00:00
|
|
|
|
2023-05-02 11:58:21 +03:00
|
|
|
page_number
|
|
|
|
}
|
|
|
|
}
|
|
|
|
None => {
|
|
|
|
page_url = format!(
|
|
|
|
"http://{}:{}{}&page={}",
|
|
|
|
config.binding_ip_addr,
|
|
|
|
config.port,
|
|
|
|
req.uri(),
|
|
|
|
1
|
|
|
|
);
|
2023-05-23 09:34:46 +00:00
|
|
|
|
2023-05-02 11:58:21 +03:00
|
|
|
1
|
|
|
|
}
|
|
|
|
};
|
2023-05-23 09:34:46 +00:00
|
|
|
|
2023-05-02 11:58:21 +03:00
|
|
|
// fetch the cached results json.
|
2023-05-15 00:20:43 +00:00
|
|
|
let cached_results_json = redis_cache.cached_results_json(&page_url);
|
2023-07-15 13:36:46 +03:00
|
|
|
// check if fetched catch results was indeed fetched or it was an error and if so
|
2023-05-02 11:58:21 +03:00
|
|
|
// handle the data accordingly.
|
|
|
|
match cached_results_json {
|
|
|
|
Ok(results_json) => {
|
|
|
|
let new_results_json: SearchResults = serde_json::from_str(&results_json)?;
|
|
|
|
let page_content: String = hbs.render("search", &new_results_json)?;
|
|
|
|
Ok(HttpResponse::Ok().body(page_content))
|
|
|
|
}
|
|
|
|
Err(_) => {
|
2023-07-15 13:36:46 +03:00
|
|
|
// check if the cookie value is empty or not if it is empty then use the
|
|
|
|
// default selected upstream search engines from the config file otherwise
|
|
|
|
// parse the non-empty cookie and grab the user selected engines from the
|
|
|
|
// UI and use that.
|
2023-07-14 17:20:46 +03:00
|
|
|
let mut results_json: crate::search_results_handler::aggregation_models::SearchResults = match req.cookie("appCookie") {
|
|
|
|
Some(cookie_value) => {
|
2023-07-14 21:29:01 +03:00
|
|
|
let cookie_value:Cookie = serde_json::from_str(cookie_value.name_value().1)?;
|
|
|
|
aggregate(query.clone(), page, config.aggregator.random_delay, config.debug, cookie_value.engines).await?
|
2023-07-14 17:20:46 +03:00
|
|
|
},
|
|
|
|
None => aggregate(query.clone(), page, config.aggregator.random_delay, config.debug, config.upstream_search_engines.clone()).await?,
|
|
|
|
};
|
2023-05-02 11:58:21 +03:00
|
|
|
results_json.add_style(config.style.clone());
|
2023-07-15 13:36:46 +03:00
|
|
|
// check whether the results grabbed from the upstream engines are empty or
|
|
|
|
// not if they are empty then set the empty_result_set option to true in
|
|
|
|
// the result json.
|
2023-07-14 21:29:01 +03:00
|
|
|
if results_json.is_empty_result_set() {
|
|
|
|
results_json.set_empty_result_set();
|
|
|
|
}
|
2023-05-15 00:20:43 +00:00
|
|
|
redis_cache
|
|
|
|
.cache_results(serde_json::to_string(&results_json)?, &page_url)?;
|
2023-05-02 11:58:21 +03:00
|
|
|
let page_content: String = hbs.render("search", &results_json)?;
|
|
|
|
Ok(HttpResponse::Ok().body(page_content))
|
|
|
|
}
|
|
|
|
}
|
2023-04-22 14:35:07 +03:00
|
|
|
}
|
|
|
|
}
|
|
|
|
None => Ok(HttpResponse::Found()
|
|
|
|
.insert_header(("location", "/"))
|
|
|
|
.finish()),
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2023-04-27 17:53:28 +03:00
|
|
|
/// Handles the route of robots.txt page of the `websurfx` meta search engine website.
|
2023-04-22 14:35:07 +03:00
|
|
|
#[get("/robots.txt")]
|
|
|
|
pub async fn robots_data(_req: HttpRequest) -> Result<HttpResponse, Box<dyn std::error::Error>> {
|
2023-05-24 17:37:41 +03:00
|
|
|
let page_content: String =
|
2023-05-25 11:50:37 +03:00
|
|
|
read_to_string(format!("{}/robots.txt", handle_different_public_path()?))?;
|
2023-04-22 14:35:07 +03:00
|
|
|
Ok(HttpResponse::Ok()
|
|
|
|
.content_type("text/plain; charset=ascii")
|
|
|
|
.body(page_content))
|
|
|
|
}
|
|
|
|
|
2023-04-27 17:53:28 +03:00
|
|
|
/// Handles the route of about page of the `websurfx` meta search engine website.
|
2023-04-22 14:35:07 +03:00
|
|
|
#[get("/about")]
|
|
|
|
pub async fn about(
|
|
|
|
hbs: web::Data<Handlebars<'_>>,
|
2023-04-30 18:16:08 +03:00
|
|
|
config: web::Data<Config>,
|
2023-04-22 14:35:07 +03:00
|
|
|
) -> Result<HttpResponse, Box<dyn std::error::Error>> {
|
2023-04-30 18:16:08 +03:00
|
|
|
let page_content: String = hbs.render("about", &config.style)?;
|
2023-04-22 14:35:07 +03:00
|
|
|
Ok(HttpResponse::Ok().body(page_content))
|
|
|
|
}
|
|
|
|
|
2023-04-27 17:53:28 +03:00
|
|
|
/// Handles the route of settings page of the `websurfx` meta search engine website.
|
2023-04-22 14:35:07 +03:00
|
|
|
#[get("/settings")]
|
|
|
|
pub async fn settings(
|
|
|
|
hbs: web::Data<Handlebars<'_>>,
|
2023-04-30 18:16:08 +03:00
|
|
|
config: web::Data<Config>,
|
2023-04-22 14:35:07 +03:00
|
|
|
) -> Result<HttpResponse, Box<dyn std::error::Error>> {
|
2023-04-30 18:16:08 +03:00
|
|
|
let page_content: String = hbs.render("settings", &config.style)?;
|
2023-04-22 14:35:07 +03:00
|
|
|
Ok(HttpResponse::Ok().body(page_content))
|
|
|
|
}
|