Merge pull request #11 from reddevilmidzy/#10-recursion

디렉터리 단위로 탐색하여 링크 추출

Author: reddevilmidzy

src/main.rs

@@ -3,18 +3,31 @@ use std::fs;
 use std::path::Path;
 use tokio::time;
 
-fn extract_links_from_file<P: AsRef<Path>>(path: P) -> Vec<String> {
-    let content = fs::read_to_string(&path).unwrap();
-    let url_regex = Regex::new(r"https?://(www\.)?[-a-zA-Z0-9@:%._+~#=]{1,256}\.[a-zA-Z0-9()]{1,6}\b([-a-zA-Z0-9()@:%_+.~#?&/=]*)").unwrap();
+fn process_path(path: &Path, url_regex: &Regex) -> Vec<String> {
+    let mut links = Vec::new();
+
+    if path.is_file() {
+        if let Ok(content) = fs::read_to_string(path) {
+            links.extend(url_regex.find_iter(&content).map(|mat| {
+                mat.as_str()
+                    .trim_end_matches(&[')', '>', '.', ',', ';'][..])
+                    .to_string()
+            }));
+        }
+    } else if path.is_dir() {
+        if let Ok(entries) = fs::read_dir(path) {
+            for entry in entries.flatten() {
+                links.extend(process_path(&entry.path(), url_regex));
+            }
+        }
+    }
 
-    url_regex
-        .find_iter(&content)
-        .map(|mat| {
-            let url = mat.as_str();
-            url.trim_end_matches(&[')', '>', '.', ',', ';'][..])
-                .to_string()
-        })
-        .collect()
+    links
+}
+
+fn extract_links_from_path<P: AsRef<Path>>(path: P) -> Vec<String> {
+    let url_regex = Regex::new(r"https?://(www\.)?[-a-zA-Z0-9@:%._+~#=]{1,256}\.[a-zA-Z0-9()]{1,6}\b([-a-zA-Z0-9()@:%_+.~#?&/=]*)").unwrap();
+    process_path(path.as_ref(), &url_regex)
 }
 
 #[derive(Debug, Eq, PartialEq)]
@@ -55,7 +68,7 @@ async fn check_link(url: &str) -> LinkCheckResult {
 #[tokio::main]
 async fn main() {
     let file_path = "example.md";
-    let links = extract_links_from_file(file_path);
+    let links = extract_links_from_path(file_path);
 
     let mut handles = Vec::new();
     for link in links {
@@ -78,11 +91,11 @@ async fn main() {
 #[cfg(test)]
 mod tests {
     use super::*;
-    use std::fs::File;
+    use std::fs::{self, File};
     use std::io::Write;
 
     #[test]
-    fn extracts_links_from_file() -> Result<(), std::io::Error> {
+    fn test_extracts_links_from_file() -> Result<(), std::io::Error> {
         // 테스트용 파일 생성
         let test_file_path = "test_file.txt";
         let mut file = File::create(test_file_path)?;
@@ -93,7 +106,7 @@ mod tests {
         )?;
 
         // 함수 호출 및 결과 확인
-        let links = extract_links_from_file(test_file_path);
+        let links = extract_links_from_path(test_file_path);
         assert_eq!(
             links,
             vec![
@@ -117,4 +130,36 @@ mod tests {
         let link = "https://lazypazy.tistory.com";
         assert_eq!(check_link(link).await, LinkCheckResult::Valid);
     }
+
+    #[test]
+    fn test_process_path() -> Result<(), std::io::Error> {
+        let test_dir = "test_dir";
+        if Path::new(test_dir).exists() {
+            fs::remove_dir_all(test_dir)?;
+        }
+
+        fs::create_dir_all(test_dir)?;
+
+        let subdir = format!("{}/subdir", test_dir);
+        fs::create_dir(&subdir)?;
+
+        let mut file1 = File::create(format!("{}/file1.txt", test_dir))?;
+        writeln!(file1, "Visit https://example1.com for more info.")?;
+
+        let mut file2 = File::create(format!("{}/file2.txt", subdir))?;
+        writeln!(file2, "Check https://example2.com and https://example3.com")?;
+
+        let url_regex = Regex::new(r"https?://(www\.)?[-a-zA-Z0-9@:%._+~#=]{1,256}\.[a-zA-Z0-9()]{1,6}\b([-a-zA-Z0-9()@:%_+.~#?&/=]*)").unwrap();
+
+        let links = process_path(Path::new(test_dir), &url_regex);
+
+        fs::remove_dir_all(test_dir)?;
+
+        assert_eq!(links.len(), 3);
+        assert!(links.contains(&"https://example1.com".to_string()));
+        assert!(links.contains(&"https://example2.com".to_string()));
+        assert!(links.contains(&"https://example3.com".to_string()));
+
+        Ok(())
+    }
 }