0
0
mirror of https://github.com/neon-mmd/websurfx.git synced 2024-12-22 20:38:22 -05:00

Merge branch 'rolling' into ability-to-have-config-on-diff-paths

This commit is contained in:
zhou fan 2023-05-24 17:10:07 +08:00 committed by GitHub
commit e6bb981133
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
9 changed files with 48 additions and 13 deletions

View File

@ -19,7 +19,16 @@ jobs:
profile: minimal
toolchain: stable
components: rustfmt, clippy
- name: Format
uses: actions-rs/cargo@v1
with:
command: fmt
args: -- --check
- name: Clippy
uses: actions-rs/cargo@v1
with:
command: clippy
args: --all-features --all-targets --all
- name: Run cargo check
uses: actions-rs/cargo@v1
with:

Binary file not shown.

After

Width:  |  Height:  |  Size: 8.1 KiB

View File

@ -1,6 +1,6 @@
{{>header this}}
<main class="search-container">
<img src="images/fps_logo.png" alt="Websurfx meta-search engine logo" />
<img src="../images/websurfx_logo.png" alt="Websurfx meta-search engine logo" />
{{>search_bar}}
</main>
<script src="static/index.js"></script>

2
src/cache/mod.rs vendored
View File

@ -1 +1 @@
pub mod cacher;
pub mod cacher;

View File

@ -24,6 +24,14 @@ pub struct Config {
pub binding_ip_addr: String,
pub style: Style,
pub redis_connection_url: String,
pub aggregator: AggreatorConfig,
}
/// Configuration options for the aggregator.
#[derive(Clone)]
pub struct AggreatorConfig {
/// Whether to introduce a random delay before sending the request to the search engine.
pub random_delay: bool,
}
impl Config {
@ -45,6 +53,15 @@ impl Config {
)?)
.exec()?;
let production_use = globals.get::<_, bool>("production_use")?;
let aggregator_config = if production_use {
AggreatorConfig { random_delay: true }
} else {
AggreatorConfig {
random_delay: false,
}
};
Ok(Config {
port: globals.get::<_, u16>("port")?,
binding_ip_addr: globals.get::<_, String>("binding_ip_addr")?,
@ -53,6 +70,7 @@ impl Config {
globals.get::<_, String>("colorscheme")?,
),
redis_connection_url: globals.get::<_, String>("redis_connection_url")?,
aggregator: aggregator_config,
})
})
}

View File

@ -116,7 +116,7 @@ impl RawSearchResult {
}
}
/// A named struct to store, serialize, deserialize the all the search results scraped and
/// A named struct to store, serialize, deserialize the all the search results scraped and
/// aggregated from the upstream search engines.
///
/// # Fields

View File

@ -29,6 +29,7 @@ use crate::engines::{duckduckgo, searx};
///
/// * `query` - Accepts a string to query with the above upstream search engines.
/// * `page` - Accepts an u32 page number.
/// * `random_delay` - Accepts a boolean value to add a random delay before making the request.
///
/// # Error
///
@ -38,14 +39,17 @@ use crate::engines::{duckduckgo, searx};
pub async fn aggregate(
query: &str,
page: u32,
random_delay: bool,
) -> Result<SearchResults, Box<dyn std::error::Error>> {
let user_agent: String = random_user_agent();
let mut result_map: HashMap<String, RawSearchResult> = HashMap::new();
// Add a random delay before making the request.
let mut rng = rand::thread_rng();
let delay_secs = rng.gen_range(1..10);
std::thread::sleep(Duration::from_secs(delay_secs));
if random_delay {
let mut rng = rand::thread_rng();
let delay_secs = rng.gen_range(1..10);
std::thread::sleep(Duration::from_secs(delay_secs));
}
// fetch results from upstream search engines simultaneously/concurrently.
let (ddg_map_results, searx_map_results) = join!(

View File

@ -81,10 +81,10 @@ pub async fn search(
.insert_header(("location", "/"))
.finish())
} else {
let page_url: String; // Declare the page_url variable without initializing it
let page_url: String; // Declare the page_url variable without initializing it
// ...
let page = match params.page {
Some(page_number) => {
if page_number <= 1 {
@ -98,7 +98,7 @@ pub async fn search(
"http://{}:{}/search?q={}&page={}",
config.binding_ip_addr, config.port, query, page_number
);
page_number
}
}
@ -110,11 +110,11 @@ pub async fn search(
req.uri(),
1
);
1
}
};
// fetch the cached results json.
let cached_results_json = redis_cache.cached_results_json(&page_url);
// check if fetched results was indeed fetched or it was an error and if so
@ -127,7 +127,7 @@ pub async fn search(
}
Err(_) => {
let mut results_json: crate::search_results_handler::aggregation_models::SearchResults =
aggregate(query, page).await?;
aggregate(query, page, config.aggregator.random_delay).await?;
results_json.add_style(config.style.clone());
redis_cache
.cache_results(serde_json::to_string(&results_json)?, &page_url)?;

View File

@ -19,3 +19,7 @@ theme = "simple" -- the theme name which should be used for the website
-- Caching
redis_connection_url = "redis://127.0.0.1:8082" -- redis connection url address on which the client should connect on.
production_use = false -- whether to use production mode or not (in other words this option should be used if it is to be used to host it on the server to provide a service to a large number of users)
-- if production_use is set to true
-- There will be a random delay before sending the request to the search engines, this is to prevent DDoSing the upstream search engines from a large number of simultaneous requests.