Cargo.lock

@@ -245,12 +245,6 @@ version = "1.0.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "f26201604c87b1e01bd3d98f8d5d9a8fcbb815e8cedb41ffccbeb4bf593a35fe"
 
-[[package]]
-name = "adler32"
-version = "1.2.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "aae1277d39aeec15cb388266ecc24b11c80469deae6067e17a1a7aa9e5c1f234"
-
 [[package]]
 name = "aead"
 version = "0.5.2"
@@ -1846,16 +1840,6 @@ dependencies = [
  "winapi-build",
 ]
 
-[[package]]
-name = "keyword_extraction"
-version = "1.3.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "c25710ba2c50e4762b267b7387a989d8d1a8235f5cf26cd84e34aac30b263140"
-dependencies = [
- "regex",
- "unicode-segmentation",
-]
-
 [[package]]
 name = "language-tags"
 version = "0.3.2"
@@ -1874,26 +1858,6 @@ version = "0.2.153"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "9c198f91728a82281a64e1f4f9eeb25d82cb32a5de251c6bd1b5154d63a8e7bd"
 
-[[package]]
-name = "libflate"
-version = "1.4.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "5ff4ae71b685bbad2f2f391fe74f6b7659a34871c08b210fdc039e43bee07d18"
-dependencies = [
- "adler32",
- "crc32fast",
- "libflate_lz77",
-]
-
-[[package]]
-name = "libflate_lz77"
-version = "1.2.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "a52d3a8bfc85f250440e4424db7d857e241a3aebbbe301f3eb606ab15c39acbf"
-dependencies = [
- "rle-decode-fast",
-]
-
 [[package]]
 name = "libmimalloc-sys"
 version = "0.1.35"
@@ -3065,12 +3029,6 @@ dependencies = [
  "windows-sys 0.52.0",
 ]
 
-[[package]]
-name = "rle-decode-fast"
-version = "1.0.3"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "3582f63211428f83597b51b2ddb88e2a91a9d52d12831f9d08f5e624e8977422"
-
 [[package]]
 name = "rustc-demangle"
 version = "0.1.23"
@@ -3473,15 +3431,6 @@ version = "1.2.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "a8f112729512f8e442d81f95a8a7ddf2b7c6b8a1a6f509a95864142b30cab2d3"
 
-[[package]]
-name = "stop-words"
-version = "0.8.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "8500024d809de02ecbf998472b7bed3c4fca380df2be68917f6a473bdb28ddcc"
-dependencies = [
- "serde_json",
-]
-
 [[package]]
 name = "string"
 version = "0.2.1"
@@ -3658,25 +3607,6 @@ dependencies = [
  "utf-8",
 ]
 
-[[package]]
-name = "thesaurus"
-version = "0.5.2"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "3e33ea271e53da683cd3439c04ff3b734f3d6052ea33a65ec9e0fa89a4f96369"
-dependencies = [
- "lazy_static",
- "thesaurus-moby",
-]
-
-[[package]]
-name = "thesaurus-moby"
-version = "0.2.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "28f7806d5dbe7d9b627e332f88269a014a6a1d40ec411d4ea66cb702aabce4cf"
-dependencies = [
- "libflate",
-]
-
 [[package]]
 name = "thousands"
 version = "0.2.0"
@@ -4054,12 +3984,6 @@ dependencies = [
  "tinyvec",
 ]
 
-[[package]]
-name = "unicode-segmentation"
-version = "1.11.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "d4c87d22b6e3f4a18d4d40ef354e97c90fcb14dd91d7dc0aa9d8a1172ebf7202"
-
 [[package]]
 name = "unicode-width"
 version = "0.1.11"
@@ -4295,7 +4219,6 @@ dependencies = [
  "error-stack",
  "fake-useragent",
  "futures 0.3.30",
- "keyword_extraction",
  "lightningcss",
  "log",
  "maud",
@@ -4311,9 +4234,7 @@ dependencies = [
  "serde",
  "serde_json",
  "smallvec 1.13.1",
- "stop-words",
  "tempfile",
- "thesaurus",
  "tokio 1.36.0",
 ]
 

Cargo.toml

@@ -13,82 +13,36 @@ bench = false
 path = "src/bin/websurfx.rs"
 
 [dependencies]
-reqwest = { version = "0.11.24", default-features = false, features = [
-    "rustls-tls",
-    "brotli",
-    "gzip",
-] }
-tokio = { version = "1.32.0", features = [
-    "rt-multi-thread",
-    "macros",
-    "fs",
-    "io-util",
-], default-features = false }
+reqwest = {version="0.11.24", default-features=false, features=["rustls-tls","brotli", "gzip"]}
+tokio = {version="1.32.0",features=["rt-multi-thread","macros", "fs", "io-util"], default-features = false}
 serde = {version="1.0.196", default-features=false, features=["derive"]}
 serde_json = {version="1.0.109", default-features=false}
-maud = { version = "0.25.0", default-features = false, features = [
-    "actix-web",
-] }
+maud = {version="0.25.0", default-features=false, features=["actix-web"]}
 scraper = {version="0.18.1", default-features = false}
-actix-web = { version = "4.4.0", features = [
-    "cookies",
-    "macros",
-    "compress-brotli",
-], default-features = false }
+actix-web = {version="4.4.0", features = ["cookies", "macros", "compress-brotli"], default-features=false}
 actix-files = {version="0.6.5", default-features=false}
 actix-cors = {version="0.7.0", default-features=false}
 fake-useragent = {version="0.1.3", default-features=false}
 env_logger = {version="0.11.1", default-features=false}
 log = {version="0.4.21", default-features=false}
-mlua = { version = "0.9.1", features = [
-    "luajit",
-    "vendored",
-], default-features = false }
-redis = { version = "0.24.0", features = [
-    "tokio-comp",
-    "connection-manager",
-], default-features = false, optional = true }
+mlua = {version="0.9.1", features=["luajit", "vendored"], default-features=false}
+redis = {version="0.24.0", features=["tokio-comp","connection-manager"], default-features = false, optional = true}
 blake3 = {version="1.5.0", default-features=false}
-error-stack = { version = "0.4.0", default-features = false, features = [
-    "std",
-] }
+error-stack = {version="0.4.0", default-features=false, features=["std"]}
 async-trait = {version="0.1.76", default-features=false}
 regex = {version="1.9.4", features=["perf"], default-features = false}
-smallvec = { version = "1.13.1", features = [
-    "union",
-    "serde",
-], default-features = false }
+smallvec = {version="1.13.1", features=["union", "serde"], default-features=false}
 futures = {version="0.3.30", default-features=false, features=["alloc"]}
 dhat = {version="0.3.2", optional = true, default-features=false}
 mimalloc = { version = "0.1.38", default-features = false }
 async-once-cell = {version="0.5.3", default-features=false}
 actix-governor = {version="0.5.0", default-features=false}
-mini-moka = { version = "0.10", optional = true, default-features = false, features = [
-    "sync",
-] }
-async-compression = { version = "0.4.6", default-features = false, features = [
-    "brotli",
-    "tokio",
-], optional = true }
-chacha20poly1305 = { version = "0.10.1", default-features = false, features = [
-    "alloc",
-    "getrandom",
-], optional = true }
+mini-moka = { version="0.10", optional = true, default-features=false, features=["sync"]}
+async-compression = { version = "0.4.6", default-features = false, features=["brotli","tokio"], optional=true}
+chacha20poly1305={version="0.10.1", default-features=false, features=["alloc","getrandom"], optional=true}
 chacha20 = {version="0.9.1", default-features=false, optional=true}
-base64 = { version = "0.21.5", default-features = false, features = [
-    "std",
-], optional = true }
+base64 = {version="0.21.5", default-features=false, features=["std"], optional=true}
 cfg-if = {version="1.0.0", default-features=false,optional=true}
-keyword_extraction = { version = "1.3.0", default-features = false, features = [
-    "tf_idf",
-
-
-] }
-
-stop-words = { version = "0.8.0", default-features = false, features = ["iso"] }
-thesaurus = { version = "0.5.2", default-features = false, optional = true, features = [
-    "moby",
-] }
 
 [dev-dependencies]
 rusty-hook = {version="^0.11.2", default-features=false}
@@ -96,9 +50,7 @@ criterion = { version = "0.5.1", default-features = false }
 tempfile = {version="3.10.1", default-features=false}
 
 [build-dependencies]
-lightningcss = { version = "1.0.0-alpha.52", default-features = false, features = [
-    "grid",
-] }
+lightningcss = {version="1.0.0-alpha.52", default-features=false, features=["grid"]}
 minify-js = {version="0.6.0", default-features=false}
 
 [profile.dev]
@@ -128,7 +80,6 @@ rpath = false
 strip = "symbols"
 
 [features]
-use-synonyms-search = ["thesaurus/static"]
 default = ["memory-cache"]
 dhat-heap = ["dep:dhat"] 
 memory-cache = ["dep:mini-moka"]
@@ -137,4 +88,3 @@ compress-cache-results = ["dep:async-compression", "dep:cfg-if"]
 encrypt-cache-results = ["dep:chacha20poly1305","dep:chacha20"]
 cec-cache-results = ["compress-cache-results","encrypt-cache-results"]
 experimental-io-uring = ["actix-web/experimental-io-uring"]
-use-non-static-synonyms-search = ["thesaurus"]

src/config/parser.rs

@@ -42,8 +42,6 @@ pub struct Config {
     /// It stores the level of safe search to be used for restricting content in the
     /// search results.
     pub safe_search: u8,
-    /// It stores the TCP connection keepalive duration in seconds.
-    pub tcp_connection_keepalive: u8,
 }
 
 impl Config {
@@ -133,7 +131,6 @@ impl Config {
             upstream_search_engines: globals
                 .get::<_, HashMap<String, bool>>("upstream_search_engines")?,
             request_timeout: globals.get::<_, u8>("request_timeout")?,
-            tcp_connection_keepalive: globals.get::<_, u8>("tcp_connection_keepalive")?,
             threads,
             rate_limiter: RateLimiter {
                 number_of_requests: rate_limiter["number_of_requests"],

src/models/aggregation_models.rs

@@ -4,11 +4,7 @@
 use super::engine_models::EngineError;
 use serde::{Deserialize, Serialize};
 use smallvec::SmallVec;
-#[cfg(any(
-    feature = "use-synonyms-search",
-    feature = "use-non-static-synonyms-search"
-))]
-use thesaurus::synonyms;
+
 /// A named struct to store the raw scraped search results scraped search results from the
 /// upstream search engines before aggregating it.It derives the Clone trait which is needed
 /// to write idiomatic rust using `Iterators`.
@@ -24,8 +20,6 @@ pub struct SearchResult {
     pub description: String,
     /// The names of the upstream engines from which this results were provided.
     pub engine: SmallVec<[String; 0]>,
-    /// The td-tdf score of the result in regards to the title, url and description and the user's query
-    pub relevance_score: f32,
 }
 
 impl SearchResult {
@@ -43,49 +37,9 @@ impl SearchResult {
             title: title.to_owned(),
             url: url.to_owned(),
             description: description.to_owned(),
-            relevance_score: 0.0,
             engine: engine.iter().map(|name| name.to_string()).collect(),
         }
     }
-    /// calculates and update the relevance score of the current search.
-
-    /// # Arguments
-    ///
-    /// * query -  the query string  used to obtain the results
-    ///
-    ///
-
-    pub fn calculate_relevance(&mut self, query: &str) {
-        use stop_words::{get, LANGUAGE};
-        // when language settings can change to any of the ones supported on this crate: https://docs.rs/crate/stop-words/0.8.0
-        let documents = [
-            self.title.clone(),
-            self.url.clone(),
-            self.description.clone(),
-        ];
-
-        let stop_words = get(LANGUAGE::English);
-        let punctuation = [
-            ".".to_owned(),
-            ",".to_owned(),
-            ":".to_owned(),
-            ";".to_owned(),
-            "!".to_owned(),
-            "?".to_owned(),
-            "(".to_owned(),
-            ")".to_owned(),
-            "[".to_owned(),
-            "]".to_owned(),
-            "{".to_owned(),
-            "}".to_owned(),
-            "\"".to_owned(),
-            "'".to_owned(),
-            "<".to_owned(),
-            ">".to_owned(),
-        ];
-
-        self.relevance_score = calculate_tf_idf(query, &documents, &stop_words, &punctuation);
-    }
 
     /// A function which adds the engine name provided as a string into a vector of strings.
     ///
@@ -228,53 +182,3 @@ impl SearchResults {
         self.no_engines_selected = true;
     }
 }
-
-/// Helper function to calculate the tf-idf for the search query.
-/// <br> The approach is  as [`as`](https://en.wikipedia.org/wiki/Tf%E2%80%93idf).
-///  <br> Find a sample article about TF-IDF [`here`](https://medium.com/analytics-vidhya/tf-idf-term-frequency-technique-easiest-explanation-for-text-classification-in-nlp-with-code-8ca3912e58c3)
-/// ### Arguments
-/// * `query` -  a user's search query
-/// * `documents` -  a list of text used for comparision (url, title, description)
-/// * `stop_words` - A list of language specific stop words.
-/// * `punctuation` - list of punctuation symbols.
-/// ### Returns
-/// * `score` - The average tf-idf score of the word tokens (and synonyms) in the query
-fn calculate_tf_idf(
-    query: &str,
-    documents: &[String],
-    stop_words: &[String],
-    punctuation: &[String],
-) -> f32 {
-    use keyword_extraction::{
-        tf_idf::{TfIdf, TfIdfParams},
-        tokenizer::Tokenizer,
-    };
-
-    let params = TfIdfParams::UnprocessedDocuments(documents, stop_words, Some(punctuation));
-    let tf_idf = TfIdf::new(params);
-    let tokener = Tokenizer::new(query, stop_words, Some(punctuation));
-    let query_tokens = tokener.split_into_words();
-    let mut search_tokens = vec![];
-
-    for token in query_tokens {
-        #[cfg(any(
-            feature = "use-synonyms-search",
-            feature = "use-non-static-synonyms-search"
-        ))]
-        {
-            // find some synonyms and add them to the search  (from wordnet or moby if feature is enabled)
-            let synonyms = synonyms(&token);
-            search_tokens.extend(synonyms)
-        }
-        search_tokens.push(token);
-    }
-
-    let mut total_score = 0.0f32;
-    for token in search_tokens.iter() {
-        total_score += tf_idf.get_score(token);
-    }
-
-    let result = total_score / (search_tokens.len() as f32);
-
-    f32::from(!result.is_nan()) * result
-}

src/results/aggregator.rs

@@ -8,7 +8,6 @@ use crate::models::{
     aggregation_models::{EngineErrorInfo, SearchResult, SearchResults},
     engine_models::{EngineError, EngineHandler},
 };
-
 use error_stack::Report;
 use futures::stream::FuturesUnordered;
 use regex::Regex;
@@ -78,7 +77,6 @@ pub async fn aggregate(
     let client = CLIENT.get_or_init(|| {
         ClientBuilder::new()
             .timeout(Duration::from_secs(config.request_timeout as u64)) // Add timeout to request to avoid DDOSing the server
-            .tcp_keepalive(Duration::from_secs(config.tcp_connection_keepalive as u64))
             .connect_timeout(Duration::from_secs(config.request_timeout as u64)) // Add timeout to request to avoid DDOSing the server
             .https_only(true)
             .gzip(true)
@@ -185,17 +183,7 @@ pub async fn aggregate(
         drop(blacklist_map);
     }
 
-    let mut results: Vec<SearchResult> = result_map
-        .iter()
-        .map(|(_, value)| {
-            let mut copy = value.clone();
-            if !copy.url.contains("temu.com") {
-                copy.calculate_relevance(query.as_str())
-            }
-            copy
-        })
-        .collect();
-    sort_search_results(&mut results);
+    let results: Vec<SearchResult> = result_map.iter().map(|(_, value)| value.clone()).collect();
 
     Ok(SearchResults::new(results, &engine_errors_info))
 }
@@ -244,21 +232,7 @@ pub async fn filter_with_lists(
 
     Ok(())
 }
-/// Sorts  SearchResults by relevance score.
-/// <br> sort_unstable is used as its faster,stability is not an issue on our side.
-/// For reasons why, check out [`this`](https://rust-lang.github.io/rfcs/1884-unstable-sort.html)
-///  # Arguments
-///  * `results` - A mutable slice or Vec of SearchResults
-///  
-fn sort_search_results(results: &mut [SearchResult]) {
-    results.sort_unstable_by(|a, b| {
-        use std::cmp::Ordering;
 
-        b.relevance_score
-            .partial_cmp(&a.relevance_score)
-            .unwrap_or(Ordering::Less)
-    })
-}
 #[cfg(test)]
 mod tests {
     use super::*;
@@ -277,7 +251,6 @@ mod tests {
                 url: "https://www.example.com".to_owned(),
                 description: "This domain is for use in illustrative examples in documents."
                     .to_owned(),
-                relevance_score: 0.0,
                 engine: smallvec!["Google".to_owned(), "Bing".to_owned()],
             },
         ));
@@ -288,7 +261,6 @@ mod tests {
                 url: "https://www.rust-lang.org/".to_owned(),
                 description: "A systems programming language that runs blazingly fast, prevents segfaults, and guarantees thread safety.".to_owned(),
                 engine: smallvec!["Google".to_owned(), "DuckDuckGo".to_owned()],
-                relevance_score:0.0
             },)
         );
 
@@ -329,7 +301,6 @@ mod tests {
                 description: "This domain is for use in illustrative examples in documents."
                     .to_owned(),
                 engine: smallvec!["Google".to_owned(), "Bing".to_owned()],
-                relevance_score: 0.0,
             },
         ));
         map_to_be_filtered.push((
@@ -339,7 +310,6 @@ mod tests {
                 url: "https://www.rust-lang.org/".to_owned(),
                 description: "A systems programming language that runs blazingly fast, prevents segfaults, and guarantees thread safety.".to_owned(),
                 engine: smallvec!["Google".to_owned(), "DuckDuckGo".to_owned()],
-                relevance_score:0.0
             },
         ));
 
@@ -396,7 +366,6 @@ mod tests {
                 description: "This domain is for use in illustrative examples in documents."
                     .to_owned(),
                 engine: smallvec!["Google".to_owned(), "Bing".to_owned()],
-                relevance_score: 0.0,
             },
         ));
 

websurfx/config.lua

@@ -10,7 +10,6 @@ production_use = false -- whether to use production mode or not (in other words
 -- 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.
 request_timeout = 30 -- timeout for the search requests sent to the upstream search engines to be fetched (value in seconds).
-tcp_connection_keepalive = 30 -- the amount of time the tcp connection should remain alive (or connected to the server). (value in seconds).
 rate_limiter = {
 	number_of_requests = 20, -- The number of request that are allowed within a provided time limit.
 	time_limit = 3, -- The time limit in which the quantity of requests that should be accepted.