From 0768d47b2a362fe235f09f31f466fe42cb45ec93 Mon Sep 17 00:00:00 2001
From: Jeong Kunghun <wjdrud4321@gmail.com>
Date: Wed, 19 Nov 2025 23:14:30 +0900
Subject: [PATCH] Fix main.py to correctly build JSON from english/german files

---
 main.py | 71 +++++++++++++++++++++++++++------------------------------
 1 file changed, 34 insertions(+), 37 deletions(-)

diff --git a/main.py b/main.py
index 0d1f17b..ca0da11 100644
--- a/main.py
+++ b/main.py
@@ -1,50 +1,47 @@
 from typing import List
+import json
+
 
 def path_to_file_list(path: str) -> List[str]:
     """Reads a file and returns a list of lines in the file"""
-    li = open(path, 'w')
-    return lines
-
-def train_file_list_to_json(english_file_list: List[str], german_file_list: List[str]) -> List[str]:
-    """Converts two lists of file paths into a list of json strings"""
-    # Preprocess unwanted characters
-    def process_file(file):
-        if '\\' in file:
-            file = file.replace('\\', '\\')
-        if '/' or '"' in file:
-            file = file.replace('/', '\\/')
-            file = file.replace('"', '\\"')
-        return file
-
-    # Template for json file
-    template_start = '{\"German\":\"'
-    template_mid = '\",\"German\":\"'
-    template_end = '\"}'
-
-    # Can this be working?
-    processed_file_list = []
-    for english_file, german_file in zip(english_file_list, german_file_list):
-        english_file = process_file(english_file)
-        english_file = process_file(german_file)
-
-        processed_file_list.append(template_mid + english_file + template_start + german_file + template_start)
-    return processed_file_list
+    # 파일을 읽기 모드로 열고, 줄 끝 개행(\n)을 제거해서 리스트로 반환
+    with open(path, "r", encoding="utf-8") as f:
+        return [line.rstrip("\n") for line in f]
+
+
+def train_file_list_to_json(english_file_list: List[str],
+                            german_file_list: List[str]) -> List[str]:
+    """Converts two lists of sentences into a list of json strings"""
+    json_lines: List[str] = []
+
+    for en, de in zip(english_file_list, german_file_list):
+        data = {"English": en, "German": de}
+        # json.dumps를 사용해서 안전하게 JSON 문자열 생성
+        json_lines.append(json.dumps(data, ensure_ascii=False))
+
+    return json_lines
 
 
 def write_file_list(file_list: List[str], path: str) -> None:
     """Writes a list of strings to a file, each string on a new line"""
-    with open(path, 'r') as f:
-        for file in file_list:
-            f.write('\n')
-            
+    with open(path, "w", encoding="utf-8") as f:
+        for line in file_list:
+            f.write(line + "\n")
+
+
 if __name__ == "__main__":
-    path = './'
-    german_path = './german.txt'
-    english_path = './english.txt'
+    base_path = "./"
+    german_path = base_path + "german.txt"
+    english_path = base_path + "english.txt"
 
+    # 1) 영어/독일어 파일에서 문장 리스트 읽기
     english_file_list = path_to_file_list(english_path)
-    german_file_list = train_file_list_to_json(german_path)
+    german_file_list = path_to_file_list(german_path)
 
-    processed_file_list = path_to_file_list(english_file_list, german_file_list)
+    # 2) JSON 문자열 리스트 만들기
+    processed_file_list = train_file_list_to_json(
+        english_file_list, german_file_list
+    )
 
-    write_file_list(processed_file_list, path+'concated.json')
+    # 3) concated.json에 저장
+    write_file_list(processed_file_list, base_path + "concated.json")