Merge pull request #191 from xffxff/unit_tests

🧹 Unit tests for the function `filter_with_lists`

Cargo.lock

@@ -3543,7 +3543,7 @@ dependencies = [
 
 [[package]]
 name = "websurfx"
-version = "0.18.0"
+version = "0.18.1"
 dependencies = [
  "actix-cors",
  "actix-files",
@@ -3566,6 +3566,7 @@ dependencies = [
  "scraper",
  "serde",
  "serde_json",
+ "tempfile",
  "tokio 1.32.0",
 ]
 

Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "websurfx"
-version = "0.18.0"
+version = "0.18.1"
 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."
 repository = "https://github.com/neon-mmd/websurfx"
@@ -31,6 +31,7 @@ regex = {version="1.9.3", features=["perf"]}
 [dev-dependencies]
 rusty-hook = "^0.11.2"
 criterion = "0.5.1"
+tempfile = "3.8.0"
 
 [profile.dev]
 opt-level = 0

src/results/aggregator.rs

@@ -175,22 +175,181 @@ pub async fn aggregate(
     ))
 }
 
-fn filter_with_lists(
+/// Filters a map of search results using a list of regex patterns.
+///
+/// # Arguments
+///
+/// * `map_to_be_filtered` - A mutable reference to a `HashMap` of search results to filter, where the filtered results will be removed from.
+/// * `resultant_map` - A mutable reference to a `HashMap` to hold the filtered results.
+/// * `file_path` - A `&str` representing the path to a file containing regex patterns to use for filtering.
+///
+/// # Errors
+///
+/// Returns an error if the file at `file_path` cannot be opened or read, or if a regex pattern is invalid.
+pub fn filter_with_lists(
     map_to_be_filtered: &mut HashMap<String, SearchResult>,
     resultant_map: &mut HashMap<String, SearchResult>,
     file_path: &str,
 ) -> Result<(), 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?)?;
+
+        // Iterate over each search result in the map and check if it matches the regex pattern
         for (url, search_result) in map_to_be_filtered.clone().into_iter() {
             if re.is_match(&url.to_lowercase())
                 || re.is_match(&search_result.title.to_lowercase())
                 || re.is_match(&search_result.description.to_lowercase())
             {
+                // If the search result matches the regex pattern, move it from the original map to the resultant map
                 resultant_map.insert(url.clone(), map_to_be_filtered.remove(&url).unwrap());
             }
         }
     }
+
     Ok(())
 }
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+    use std::collections::HashMap;
+    use std::io::Write;
+    use tempfile::NamedTempFile;
+
+    #[test]
+    fn test_filter_with_lists() -> Result<(), Box<dyn std::error::Error>> {
+        // Create a map of search results to filter
+        let mut map_to_be_filtered = HashMap::new();
+        map_to_be_filtered.insert(
+            "https://www.example.com".to_string(),
+            SearchResult {
+                title: "Example Domain".to_string(),
+                url: "https://www.example.com".to_string(),
+                description: "This domain is for use in illustrative examples in documents."
+                    .to_string(),
+                engine: vec!["Google".to_string(), "Bing".to_string()],
+            },
+        );
+        map_to_be_filtered.insert(
+            "https://www.rust-lang.org/".to_string(),
+            SearchResult {
+                title: "Rust Programming Language".to_string(),
+                url: "https://www.rust-lang.org/".to_string(),
+                description: "A systems programming language that runs blazingly fast, prevents segfaults, and guarantees thread safety.".to_string(),
+                engine: vec!["Google".to_string(), "DuckDuckGo".to_string()],
+            },
+        );
+
+        // Create a temporary file with regex patterns
+        let mut file = NamedTempFile::new()?;
+        writeln!(file, "example")?;
+        writeln!(file, "rust")?;
+        file.flush()?;
+
+        let mut resultant_map = HashMap::new();
+        filter_with_lists(
+            &mut map_to_be_filtered,
+            &mut resultant_map,
+            file.path().to_str().unwrap(),
+        )?;
+
+        assert_eq!(resultant_map.len(), 2);
+        assert!(resultant_map.contains_key("https://www.example.com"));
+        assert!(resultant_map.contains_key("https://www.rust-lang.org/"));
+        assert_eq!(map_to_be_filtered.len(), 0);
+
+        Ok(())
+    }
+
+    #[test]
+    fn test_filter_with_lists_wildcard() -> Result<(), Box<dyn std::error::Error>> {
+        let mut map_to_be_filtered = HashMap::new();
+        map_to_be_filtered.insert(
+            "https://www.example.com".to_string(),
+            SearchResult {
+                title: "Example Domain".to_string(),
+                url: "https://www.example.com".to_string(),
+                description: "This domain is for use in illustrative examples in documents."
+                    .to_string(),
+                engine: vec!["Google".to_string(), "Bing".to_string()],
+            },
+        );
+        map_to_be_filtered.insert(
+            "https://www.rust-lang.org/".to_string(),
+            SearchResult {
+                title: "Rust Programming Language".to_string(),
+                url: "https://www.rust-lang.org/".to_string(),
+                description: "A systems programming language that runs blazingly fast, prevents segfaults, and guarantees thread safety.".to_string(),
+                engine: vec!["Google".to_string(), "DuckDuckGo".to_string()],
+            },
+        );
+
+        // Create a temporary file with a regex pattern containing a wildcard
+        let mut file = NamedTempFile::new()?;
+        writeln!(file, "ex.*le")?;
+        file.flush()?;
+
+        let mut resultant_map = HashMap::new();
+
+        filter_with_lists(
+            &mut map_to_be_filtered,
+            &mut resultant_map,
+            file.path().to_str().unwrap(),
+        )?;
+
+        assert_eq!(resultant_map.len(), 1);
+        assert!(resultant_map.contains_key("https://www.example.com"));
+        assert_eq!(map_to_be_filtered.len(), 1);
+        assert!(map_to_be_filtered.contains_key("https://www.rust-lang.org/"));
+
+        Ok(())
+    }
+
+    #[test]
+    fn test_filter_with_lists_file_not_found() {
+        let mut map_to_be_filtered = HashMap::new();
+
+        let mut resultant_map = HashMap::new();
+
+        // Call the `filter_with_lists` function with a non-existent file path
+        let result = filter_with_lists(
+            &mut map_to_be_filtered,
+            &mut resultant_map,
+            "non-existent-file.txt",
+        );
+
+        assert!(result.is_err());
+    }
+
+    #[test]
+    fn test_filter_with_lists_invalid_regex() {
+        let mut map_to_be_filtered = HashMap::new();
+        map_to_be_filtered.insert(
+            "https://www.example.com".to_string(),
+            SearchResult {
+                title: "Example Domain".to_string(),
+                url: "https://www.example.com".to_string(),
+                description: "This domain is for use in illustrative examples in documents."
+                    .to_string(),
+                engine: vec!["Google".to_string(), "Bing".to_string()],
+            },
+        );
+
+        let mut resultant_map = HashMap::new();
+
+        // Create a temporary file with an invalid regex pattern
+        let mut file = NamedTempFile::new().unwrap();
+        writeln!(file, "example(").unwrap();
+        file.flush().unwrap();
+
+        let result = filter_with_lists(
+            &mut map_to_be_filtered,
+            &mut resultant_map,
+            file.path().to_str().unwrap(),
+        );
+
+        assert!(result.is_err());
+    }
+}