mirror of
https://github.com/neon-mmd/websurfx.git
synced 2024-11-25 07:28:22 -05:00
Compare commits
6 Commits
3a1ff0f307
...
948d20d8fb
Author | SHA1 | Date | |
---|---|---|---|
|
948d20d8fb | ||
|
4315221385 | ||
|
b22d60f166 | ||
|
acee5d892d | ||
|
9a5f1c5f44 | ||
|
ebee1f4a6c |
18
Cargo.lock
generated
18
Cargo.lock
generated
@ -851,7 +851,7 @@ dependencies = [
|
|||||||
"clap",
|
"clap",
|
||||||
"criterion-plot",
|
"criterion-plot",
|
||||||
"is-terminal",
|
"is-terminal",
|
||||||
"itertools",
|
"itertools 0.10.5",
|
||||||
"num-traits",
|
"num-traits",
|
||||||
"once_cell",
|
"once_cell",
|
||||||
"oorandom",
|
"oorandom",
|
||||||
@ -870,7 +870,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
|
|||||||
checksum = "6b50826342786a51a89e2da3a28f1c32b06e387201bc2d19791f622c673706b1"
|
checksum = "6b50826342786a51a89e2da3a28f1c32b06e387201bc2d19791f622c673706b1"
|
||||||
dependencies = [
|
dependencies = [
|
||||||
"cast",
|
"cast",
|
||||||
"itertools",
|
"itertools 0.10.5",
|
||||||
]
|
]
|
||||||
|
|
||||||
[[package]]
|
[[package]]
|
||||||
@ -1881,6 +1881,15 @@ dependencies = [
|
|||||||
"either",
|
"either",
|
||||||
]
|
]
|
||||||
|
|
||||||
|
[[package]]
|
||||||
|
name = "itertools"
|
||||||
|
version = "0.13.0"
|
||||||
|
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||||
|
checksum = "413ee7dfc52ee1a4949ceeb7dbc8a33f2d6c088194d9f922fb8318faf1f01186"
|
||||||
|
dependencies = [
|
||||||
|
"either",
|
||||||
|
]
|
||||||
|
|
||||||
[[package]]
|
[[package]]
|
||||||
name = "itoa"
|
name = "itoa"
|
||||||
version = "0.4.8"
|
version = "0.4.8"
|
||||||
@ -1983,7 +1992,7 @@ dependencies = [
|
|||||||
"cssparser-color",
|
"cssparser-color",
|
||||||
"data-encoding",
|
"data-encoding",
|
||||||
"getrandom",
|
"getrandom",
|
||||||
"itertools",
|
"itertools 0.10.5",
|
||||||
"lazy_static",
|
"lazy_static",
|
||||||
"parcel_selectors",
|
"parcel_selectors",
|
||||||
"paste",
|
"paste",
|
||||||
@ -4440,7 +4449,7 @@ dependencies = [
|
|||||||
|
|
||||||
[[package]]
|
[[package]]
|
||||||
name = "websurfx"
|
name = "websurfx"
|
||||||
version = "1.17.0"
|
version = "1.17.20"
|
||||||
dependencies = [
|
dependencies = [
|
||||||
"actix-cors",
|
"actix-cors",
|
||||||
"actix-files",
|
"actix-files",
|
||||||
@ -4460,6 +4469,7 @@ dependencies = [
|
|||||||
"error-stack",
|
"error-stack",
|
||||||
"fake-useragent",
|
"fake-useragent",
|
||||||
"futures 0.3.30",
|
"futures 0.3.30",
|
||||||
|
"itertools 0.13.0",
|
||||||
"keyword_extraction",
|
"keyword_extraction",
|
||||||
"lightningcss",
|
"lightningcss",
|
||||||
"log",
|
"log",
|
||||||
|
@ -1,6 +1,6 @@
|
|||||||
[package]
|
[package]
|
||||||
name = "websurfx"
|
name = "websurfx"
|
||||||
version = "1.17.0"
|
version = "1.17.20"
|
||||||
edition = "2021"
|
edition = "2021"
|
||||||
description = "An open-source alternative to Searx that provides clean, ad-free, and organic results with incredible speed while keeping privacy and security in mind."
|
description = "An open-source alternative to Searx that provides clean, ad-free, and organic results with incredible speed while keeping privacy and security in mind."
|
||||||
repository = "https://github.com/neon-mmd/websurfx"
|
repository = "https://github.com/neon-mmd/websurfx"
|
||||||
@ -82,14 +82,13 @@ base64 = { version = "0.21.5", default-features = false, features = [
|
|||||||
cfg-if = { version = "1.0.0", default-features = false, optional = true }
|
cfg-if = { version = "1.0.0", default-features = false, optional = true }
|
||||||
keyword_extraction = { version = "1.4.3", default-features = false, features = [
|
keyword_extraction = { version = "1.4.3", default-features = false, features = [
|
||||||
"tf_idf",
|
"tf_idf",
|
||||||
|
|
||||||
|
|
||||||
] }
|
] }
|
||||||
|
|
||||||
stop-words = { version = "0.8.0", default-features = false, features = ["iso"] }
|
stop-words = { version = "0.8.0", default-features = false, features = ["iso"] }
|
||||||
thesaurus = { version = "0.5.2", default-features = false, optional = true, features = [
|
thesaurus = { version = "0.5.2", default-features = false, optional = true, features = [
|
||||||
"moby",
|
"moby",
|
||||||
] }
|
]}
|
||||||
|
itertools = {version = "0.13.0", default-features = false}
|
||||||
|
|
||||||
[dev-dependencies]
|
[dev-dependencies]
|
||||||
rusty-hook = { version = "^0.11.2", default-features = false }
|
rusty-hook = { version = "^0.11.2", default-features = false }
|
||||||
|
15
src/cache/redis_cacher.rs
vendored
15
src/cache/redis_cacher.rs
vendored
@ -4,7 +4,10 @@
|
|||||||
use super::error::CacheError;
|
use super::error::CacheError;
|
||||||
use error_stack::Report;
|
use error_stack::Report;
|
||||||
use futures::stream::FuturesUnordered;
|
use futures::stream::FuturesUnordered;
|
||||||
use redis::{aio::ConnectionManager, AsyncCommands, Client, RedisError};
|
use redis::{
|
||||||
|
aio::ConnectionManager, AsyncCommands, Client, ExistenceCheck, RedisError, SetExpiry,
|
||||||
|
SetOptions,
|
||||||
|
};
|
||||||
|
|
||||||
/// A constant holding the redis pipeline size.
|
/// A constant holding the redis pipeline size.
|
||||||
const REDIS_PIPELINE_SIZE: usize = 3;
|
const REDIS_PIPELINE_SIZE: usize = 3;
|
||||||
@ -139,8 +142,14 @@ impl RedisCache {
|
|||||||
self.current_connection = Default::default();
|
self.current_connection = Default::default();
|
||||||
|
|
||||||
for (key, json_result) in keys.zip(json_results) {
|
for (key, json_result) in keys.zip(json_results) {
|
||||||
self.pipeline
|
self.pipeline.set_options(
|
||||||
.set_ex(key, json_result, self.cache_ttl.into());
|
key,
|
||||||
|
json_result,
|
||||||
|
SetOptions::default()
|
||||||
|
.conditional_set(ExistenceCheck::NX)
|
||||||
|
.get(true)
|
||||||
|
.with_expiration(SetExpiry::EX(self.cache_ttl.into())),
|
||||||
|
);
|
||||||
}
|
}
|
||||||
|
|
||||||
let mut result: Result<(), RedisError> = self
|
let mut result: Result<(), RedisError> = self
|
||||||
|
@ -12,6 +12,7 @@ use crate::{
|
|||||||
results::aggregator::aggregate,
|
results::aggregator::aggregate,
|
||||||
};
|
};
|
||||||
use actix_web::{get, http::header::ContentType, web, HttpRequest, HttpResponse};
|
use actix_web::{get, http::header::ContentType, web, HttpRequest, HttpResponse};
|
||||||
|
use itertools::Itertools;
|
||||||
use regex::Regex;
|
use regex::Regex;
|
||||||
use std::borrow::Cow;
|
use std::borrow::Cow;
|
||||||
use tokio::{
|
use tokio::{
|
||||||
@ -40,7 +41,6 @@ pub async fn search(
|
|||||||
config: web::Data<&'static Config>,
|
config: web::Data<&'static Config>,
|
||||||
cache: web::Data<&'static SharedCache>,
|
cache: web::Data<&'static SharedCache>,
|
||||||
) -> Result<HttpResponse, Box<dyn std::error::Error>> {
|
) -> Result<HttpResponse, Box<dyn std::error::Error>> {
|
||||||
use std::sync::Arc;
|
|
||||||
let params = web::Query::<SearchParams>::from_query(req.query_string())?;
|
let params = web::Query::<SearchParams>::from_query(req.query_string())?;
|
||||||
match ¶ms.q {
|
match ¶ms.q {
|
||||||
Some(query) => {
|
Some(query) => {
|
||||||
@ -83,44 +83,36 @@ pub async fn search(
|
|||||||
let previous_page = page.saturating_sub(1);
|
let previous_page = page.saturating_sub(1);
|
||||||
let next_page = page + 1;
|
let next_page = page + 1;
|
||||||
|
|
||||||
let mut results = Arc::new((SearchResults::default(), String::default()));
|
let results: (SearchResults, String, bool);
|
||||||
if page != previous_page {
|
if page != previous_page {
|
||||||
let (previous_results, current_results, next_results) = join!(
|
let (previous_results, current_results, next_results) = join!(
|
||||||
get_results(previous_page),
|
get_results(previous_page),
|
||||||
get_results(page),
|
get_results(page),
|
||||||
get_results(next_page)
|
get_results(next_page)
|
||||||
);
|
);
|
||||||
let (parsed_previous_results, parsed_next_results) =
|
|
||||||
(previous_results?, next_results?);
|
|
||||||
|
|
||||||
let (cache_keys, results_list) = (
|
results = current_results?;
|
||||||
[
|
|
||||||
parsed_previous_results.1,
|
|
||||||
results.1.clone(),
|
|
||||||
parsed_next_results.1,
|
|
||||||
],
|
|
||||||
[
|
|
||||||
parsed_previous_results.0,
|
|
||||||
results.0.clone(),
|
|
||||||
parsed_next_results.0,
|
|
||||||
],
|
|
||||||
);
|
|
||||||
|
|
||||||
results = Arc::new(current_results?);
|
let (results_list, cache_keys): (Vec<SearchResults>, Vec<String>) =
|
||||||
|
[previous_results?, results.clone(), next_results?]
|
||||||
|
.into_iter()
|
||||||
|
.filter_map(|(result, cache_key, flag)| {
|
||||||
|
dbg!(flag).then_some((result, cache_key))
|
||||||
|
})
|
||||||
|
.multiunzip();
|
||||||
|
|
||||||
tokio::spawn(async move { cache.cache_results(&results_list, &cache_keys).await });
|
tokio::spawn(async move { cache.cache_results(&results_list, &cache_keys).await });
|
||||||
} else {
|
} else {
|
||||||
let (current_results, next_results) =
|
let (current_results, next_results) =
|
||||||
join!(get_results(page), get_results(page + 1));
|
join!(get_results(page), get_results(page + 1));
|
||||||
|
|
||||||
let parsed_next_results = next_results?;
|
results = current_results?;
|
||||||
|
|
||||||
results = Arc::new(current_results?);
|
let (results_list, cache_keys): (Vec<SearchResults>, Vec<String>) =
|
||||||
|
[results.clone(), next_results?]
|
||||||
let (cache_keys, results_list) = (
|
.into_iter()
|
||||||
[results.1.clone(), parsed_next_results.1.clone()],
|
.filter_map(|(result, cache_key, flag)| flag.then_some((result, cache_key)))
|
||||||
[results.0.clone(), parsed_next_results.0],
|
.multiunzip();
|
||||||
);
|
|
||||||
|
|
||||||
tokio::spawn(async move { cache.cache_results(&results_list, &cache_keys).await });
|
tokio::spawn(async move { cache.cache_results(&results_list, &cache_keys).await });
|
||||||
}
|
}
|
||||||
@ -163,7 +155,7 @@ async fn results(
|
|||||||
query: &str,
|
query: &str,
|
||||||
page: u32,
|
page: u32,
|
||||||
search_settings: &server_models::Cookie<'_>,
|
search_settings: &server_models::Cookie<'_>,
|
||||||
) -> Result<(SearchResults, String), Box<dyn std::error::Error>> {
|
) -> Result<(SearchResults, String, bool), Box<dyn std::error::Error>> {
|
||||||
// eagerly parse cookie value to evaluate safe search level
|
// eagerly parse cookie value to evaluate safe search level
|
||||||
let safe_search_level = search_settings.safe_search_level;
|
let safe_search_level = search_settings.safe_search_level;
|
||||||
|
|
||||||
@ -182,7 +174,7 @@ async fn results(
|
|||||||
// check if fetched cache results was indeed fetched or it was an error and if so
|
// check if fetched cache results was indeed fetched or it was an error and if so
|
||||||
// handle the data accordingly.
|
// handle the data accordingly.
|
||||||
match cached_results {
|
match cached_results {
|
||||||
Ok(results) => Ok((results, cache_key)),
|
Ok(results) => Ok((results, cache_key, false)),
|
||||||
Err(_) => {
|
Err(_) => {
|
||||||
if safe_search_level == 4 {
|
if safe_search_level == 4 {
|
||||||
let mut results: SearchResults = SearchResults::default();
|
let mut results: SearchResults = SearchResults::default();
|
||||||
@ -196,7 +188,7 @@ async fn results(
|
|||||||
.cache_results(&[results.clone()], &[cache_key.clone()])
|
.cache_results(&[results.clone()], &[cache_key.clone()])
|
||||||
.await?;
|
.await?;
|
||||||
results.set_safe_search_level(safe_search_level);
|
results.set_safe_search_level(safe_search_level);
|
||||||
return Ok((results, cache_key));
|
return Ok((results, cache_key, true));
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
@ -235,7 +227,7 @@ async fn results(
|
|||||||
.cache_results(&[results.clone()], &[cache_key.clone()])
|
.cache_results(&[results.clone()], &[cache_key.clone()])
|
||||||
.await?;
|
.await?;
|
||||||
results.set_safe_search_level(safe_search_level);
|
results.set_safe_search_level(safe_search_level);
|
||||||
Ok((results, cache_key))
|
Ok((results, cache_key, true))
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
Loading…
Reference in New Issue
Block a user