File size: 10,620 Bytes
493c56b
15fc415
c170de8
996ff84
4402168
5e2669b
fcfd112
 
86b0d3d
7d762b3
fcfd112
493c56b
c170de8
5020f36
05c3e6c
ca4447f
80e950d
fcfd112
ca4447f
 
a596c07
15fc415
fc69ace
 
 
 
 
 
 
 
137c62e
fc69ace
 
 
 
 
15fc415
 
 
137c62e
996ff84
15fc415
6b9469e
15fc415
 
 
 
38ba4bd
15fc415
4402168
15fc415
4402168
d912bff
 
7d762b3
80e950d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7d762b3
31c9c67
 
80e950d
 
 
6e9250c
7d762b3
 
 
d073aa2
 
6b9469e
 
5e2669b
6b9469e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
a596c07
5020f36
 
 
 
 
 
6b9469e
5020f36
 
 
15fc415
38ba4bd
15fc415
 
 
 
 
049b1c1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
99936bc
4402168
996ff84
b2c72bd
4402168
d912bff
6b9469e
e704c26
d912bff
7d762b3
 
 
 
 
 
 
 
d912bff
5e2669b
 
4402168
e704c26
c5fca32
4402168
519ebe0
6b9469e
519ebe0
72fec47
05c3e6c
 
5e2669b
 
e704c26
5e2669b
05c3e6c
6b9469e
 
 
72fec47
6b9469e
05c3e6c
 
 
74e4fc6
 
 
 
d912bff
7d762b3
86b0d3d
 
 
41ab8a2
d912bff
7d762b3
80e950d
6b9469e
86b0d3d
 
 
 
 
7d762b3
 
 
 
 
74e4fc6
173c6ba
 
 
 
05c3e6c
 
6b9469e
 
 
72fec47
6b9469e
4402168
 
 
 
c60fdb8
 
fcfd112
 
 
 
 
 
 
 
 
 
05c3e6c
 
 
 
 
 
 
 
5e2669b
05c3e6c
 
5e2669b
 
05c3e6c
6e9250c
80e950d
 
 
6e9250c
 
 
80e950d
 
 
31c9c67
 
 
 
 
 
 
 
6e9250c
31c9c67
6e9250c
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
//! This module handles the search route of the search engine website.

use crate::{
    cache::cacher::SharedCache,
    config::parser::Config,
    handler::{file_path, FileType},
    models::{
        aggregation_models::SearchResults,
        engine_models::EngineHandler,
        server_models::{self, SearchParams},
    },
    results::aggregator::aggregate,
};
use actix_web::{get, http::header::ContentType, web, HttpRequest, HttpResponse};
use regex::Regex;
use std::{
    borrow::Cow,
    fs::File,
    io::{BufRead, BufReader, Read},
};
use tokio::join;

/// 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"
/// ```
///
/// Or
///
/// ```bash
/// curl "http://127.0.0.1:8080/search?q=sweden"
/// ```
#[get("/search")]
pub async fn search(
    req: HttpRequest,
    config: web::Data<Config>,
    cache: web::Data<SharedCache>,
) -> Result<HttpResponse, Box<dyn std::error::Error>> {
    use std::sync::Arc;
    let params = web::Query::<SearchParams>::from_query(req.query_string())?;
    match &params.q {
        Some(query) => {
            if query.trim().is_empty() {
                return Ok(HttpResponse::TemporaryRedirect()
                    .insert_header(("location", "/"))
                    .finish());
            }

            let cookie = req.cookie("appCookie");

            // Get search settings using the user's cookie or from the server's config
            let mut search_settings: server_models::Cookie<'_> = cookie
                .and_then(|cookie_value| serde_json::from_str(cookie_value.value()).ok())
                .unwrap_or_else(|| {
                    server_models::Cookie::build(
                        &config.style,
                        config
                            .upstream_search_engines
                            .iter()
                            .filter_map(|(engine, enabled)| {
                                enabled.then_some(Cow::Borrowed(engine.as_str()))
                            })
                            .collect(),
                        config.safe_search,
                    )
                });

            search_settings.safe_search_level = get_safesearch_level(
                &Some(search_settings.safe_search_level),
                &params.safesearch,
                config.safe_search,
            );

            // Closure wrapping the results function capturing local references
            let get_results = |page| results(&config, &cache, query, page, &search_settings);

            // .max(1) makes sure that the page >= 0.
            let page = params.page.unwrap_or(1).max(1) - 1;
            let previous_page = page.saturating_sub(1);
            let next_page = page + 1;

            let mut results = Arc::new((SearchResults::default(), String::default()));
            if page != previous_page {
                let (previous_results, current_results, next_results) = join!(
                    get_results(previous_page),
                    get_results(page),
                    get_results(next_page)
                );
                let (parsed_previous_results, parsed_next_results) =
                    (previous_results?, next_results?);

                let (cache_keys, results_list) = (
                    [
                        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?);

                tokio::spawn(async move { cache.cache_results(&results_list, &cache_keys).await });
            } else {
                let (current_results, next_results) =
                    join!(get_results(page), get_results(page + 1));

                let parsed_next_results = next_results?;

                results = Arc::new(current_results?);

                let (cache_keys, results_list) = (
                    [results.1.clone(), parsed_next_results.1.clone()],
                    [results.0.clone(), parsed_next_results.0],
                );

                tokio::spawn(async move { cache.cache_results(&results_list, &cache_keys).await });
            }

            Ok(HttpResponse::Ok().content_type(ContentType::html()).body(
                crate::templates::views::search::search(
                    &config.style.colorscheme,
                    &config.style.theme,
                    &config.style.animation,
                    query,
                    &results.0,
                )
                .0,
            ))
        }
        None => Ok(HttpResponse::TemporaryRedirect()
            .insert_header(("location", "/"))
            .finish()),
    }
}

/// Fetches the results for a query and page. It First checks the redis cache, if that
/// fails it gets proper results by requesting from the upstream search engines.
///
/// # Arguments
///
/// * `url` - It takes the url of the current page that requested the search results for a
/// particular search query.
/// * `config` - It takes a parsed config struct.
/// * `query` - It takes the page number as u32 value.
/// * `req` - It takes the `HttpRequest` struct as a value.
///
/// # Error
///
/// It returns the `SearchResults` struct if the search results could be successfully fetched from
/// the cache or from the upstream search engines otherwise it returns an appropriate error.
async fn results(
    config: &Config,
    cache: &web::Data<SharedCache>,
    query: &str,
    page: u32,
    search_settings: &server_models::Cookie<'_>,
) -> Result<(SearchResults, String), Box<dyn std::error::Error>> {
    // eagerly parse cookie value to evaluate safe search level
    let safe_search_level = search_settings.safe_search_level;

    let cache_key = format!(
        "http://{}:{}/search?q={}&page={}&safesearch={}&engines={}",
        config.binding_ip,
        config.port,
        query,
        page,
        safe_search_level,
        search_settings.engines.join(",")
    );

    // fetch the cached results json.
    let cached_results = cache.cached_results(&cache_key).await;
    // check if fetched cache results was indeed fetched or it was an error and if so
    // handle the data accordingly.
    match cached_results {
        Ok(results) => Ok((results, cache_key)),
        Err(_) => {
            if safe_search_level == 4 {
                let mut results: SearchResults = SearchResults::default();

                let flag: bool =
                    !is_match_from_filter_list(file_path(FileType::BlockList)?, query)?;
                // Return early when query contains disallowed words,
                if flag {
                    results.set_disallowed();
                    cache
                        .cache_results(&[results.clone()], &[cache_key.clone()])
                        .await?;
                    results.set_safe_search_level(safe_search_level);
                    return Ok((results, cache_key));
                }
            }

            // 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.
            let mut results: SearchResults = match search_settings.engines.is_empty() {
                false => {
                    aggregate(
                        query,
                        page,
                        config,
                        &search_settings
                            .engines
                            .iter()
                            .filter_map(|engine| EngineHandler::new(engine).ok())
                            .collect::<Vec<EngineHandler>>(),
                        safe_search_level,
                    )
                    .await?
                }
                true => {
                    let mut search_results = SearchResults::default();
                    search_results.set_no_engines_selected();
                    search_results
                }
            };
            if results.engine_errors_info().is_empty()
                && results.results().is_empty()
                && !results.no_engines_selected()
            {
                results.set_filtered();
            }
            cache
                .cache_results(&[results.clone()], &[cache_key.clone()])
                .await?;
            results.set_safe_search_level(safe_search_level);
            Ok((results, cache_key))
        }
    }
}

/// A helper function which checks whether the search query contains any keywords which should be
/// disallowed/allowed based on the regex based rules present in the blocklist and allowlist files.
///
/// # Arguments
///
/// * `file_path` - It takes the file path of the list as the argument.
/// * `query` - It takes the search query to be checked against the list as an argument.
///
/// # Error
///
/// Returns a bool indicating whether the results were found in the list or not on success
/// otherwise returns a standard error type on a failure.
fn is_match_from_filter_list(
    file_path: &str,
    query: &str,
) -> Result<bool, Box<dyn std::error::Error>> {
    let mut reader = BufReader::new(File::open(file_path)?);
    for line in reader.by_ref().lines() {
        let re = Regex::new(&line?)?;
        if re.is_match(query) {
            return Ok(true);
        }
    }

    Ok(false)
}

/// A helper function to modify the safe search level based on the url params.
/// The `safe_search` is the one in the user's cookie or
/// the default set by the server config if the cookie was missing.
///
/// # Argurments
///
/// * `url_level` - Safe search level from the url.
/// * `safe_search` - User's cookie, or the safe search level set by the server
/// * `config_level` - Safe search level to fall back to
fn get_safesearch_level(cookie_level: &Option<u8>, url_level: &Option<u8>, config_level: u8) -> u8 {
    match url_level {
        Some(url_level) => {
            if *url_level >= 3 {
                config_level
            } else {
                *url_level
            }
        }
        None => cookie_level.unwrap_or(config_level),
    }
}