Add scripts to patch/extract .ks (KiriKiri) file

extract_ks.py

@@ -0,0 +1,79 @@
+import re
+from os.path import splitext
+from os import listdir
+import json
+
+
+def extract_dialogue_from_ks(file_path, encoding='cp932'):
+    # 存储结果
+    dialogues = []
+    
+    try:
+        with open(file_path, 'r', encoding=encoding) as file:
+            content = file.read()
+        contents = content.split('\n')
+        block_text = ''
+        block_name = ''
+        for line in contents:
+            if line.endswith('|'):
+                if block_text:
+                    if block_name:
+                        dialogues.append({
+                            'name': block_name,
+                            'message': block_text
+                        })
+                    else:
+                        dialogues.append({
+                            'message': block_text
+                        })
+                    block_text = ''
+                    block_name = ''
+                continue
+            if line.startswith('@exlink') or line.startswith('@e_xlink'):
+                a = re.search(r'txt="([^"]+)"', line)
+                if a:
+                    dialogues.append({
+                        'message': a.group(1),
+                    })
+                continue
+            if line.startswith('@nm'):
+                a = re.search(r't="([^"]+)"', line)
+                if a:
+                    block_name = a.group(1)
+                continue
+            if not (line.endswith('[r]') or line.endswith('[np]')):
+                continue
+            block_text += line.replace('\n', '').replace('[r]', '\n').replace('[np]', '')
+        if block_text:
+            if block_name:
+                dialogues.append({
+                    'name': block_name,
+                    'message': block_text
+                })
+            else:
+                dialogues.append({
+                    'message': block_text
+                })
+        return dialogues
+            
+    except Exception as e:
+        print(f"Error processing file: {e}")
+        return []
+
+
+def get_ks_files(directory):
+    """
+    获取指定目录下的所有.ks文件
+    :param directory: 目录路径
+    :return: ks文件列表
+    """
+    return [f for f in listdir(directory) if splitext(f)[1].lower() == '.ks']
+
+
+if __name__ == "__main__":
+    for f in get_ks_files('.'):
+        print(f"Processing file: {f}")
+        result = extract_dialogue_from_ks(f)
+        print(f"Extracted {len(result)} dialogues from {f}")
+        with open(f"{splitext(f)[0]}.json", 'w', encoding='utf-8') as output_file:
+            json.dump(result, output_file, ensure_ascii=False, indent=4)

patch_ks.py

@@ -0,0 +1,120 @@
+import re
+from os.path import splitext, exists, dirname, join
+from os import listdir, makedirs
+import json
+
+
+def replace_fallback(str, fallback):
+    """
+    替换字符串中的回退字符
+    :param str: 原始字符串
+    :param fallback: 回退字典
+    :return: 替换后的字符串
+    """
+    for key, value in fallback.items():
+        str = str.replace(key, value)
+    return str
+
+
+def patch_ks_file(file_path, string):
+    """
+    替换.ks文件中的字符串
+    :param file_path: 文件路径
+    :param string: 替换的字符串
+    """
+    with open(file_path, 'r', encoding='cp932') as file:
+        content = file.read()
+    contents = content.split('\n')
+    i = 0
+    result = []
+    texts = []
+    insert_loc = 0
+    have_text = False
+    for line in contents:
+        if line.endswith('|'):
+            if len(texts):
+                if have_text:
+                    ts = string[i]['message'].replace('\n', '[r]\n').split('\n')
+                    ts[-1] += '[np]'
+                    texts = texts[0:insert_loc] + ts + texts[insert_loc:]
+                    i += 1
+                result.append('\n'.join(texts))
+                texts = []
+            have_text = False
+            texts.append(line)
+            continue
+        if line.startswith('@exlink') or line.startswith('@e_xlink'):
+            a = re.search(r'txt="([^"]+)"', line)
+            if a:
+                texts.append(line.replace(a.group(1), string[i]['message']))
+                i += 1
+            continue
+        if line.startswith('@nm'):
+            a = re.search(r't="([^"]+)"', line)
+            if a:
+                texts.append(line.replace(a.group(1), string[i]['name']))
+            continue
+        if line.endswith('[r]') or line.endswith('[np]'):
+            insert_loc = len(texts)
+            have_text = True
+            continue
+        texts.append(line)
+    if len(texts):
+        if have_text:
+            ts = string[i]['message'].replace('\n', '[r]\n').split('\n')
+            ts[-1] += '[np]'
+            texts = texts[0:insert_loc] + ts + texts[insert_loc:]
+            i += 1
+            if i < len(string):
+                print('Warning: not all strings are used')
+        result.append('\n'.join(texts))
+    output = join(dirname(file_path), '../patched', f"{splitext(file_path)[0]}.ks")
+    if not exists(dirname(output)):
+        makedirs(dirname(output))
+    with open(output, 'w', encoding='cp932') as file:
+        file.write('\n'.join(result))
+    print(f"Patched file saved to: {output}")
+        
+
+def get_ks_files(directory):
+    """
+    获取指定目录下的所有.ks文件
+    :param directory: 目录路径
+    :return: ks文件列表
+    """
+    return [f for f in listdir(directory) if splitext(f)[1].lower() == '.ks']
+
+
+if __name__ == "__main__":
+    fallback = {}
+    if exists('jis_fallback.json'):
+        with open('jis_fallback.json', 'r', encoding='utf-8') as file:
+            fallback = json.load(file)
+    for f in get_ks_files('.'):
+        print(f"Processing file: {f}")
+        json_file = f"{splitext(f)[0]}.json"
+        with open(json_file, 'r', encoding='utf-8') as file:
+            content = json.load(file)
+        bcontent = []
+        for d in content:
+            da = {}
+            name = d.get('name')
+            if name:
+                name = replace_fallback(name, fallback)
+                try:
+                    name.encode('cp932')
+                    da['name'] = name
+                except UnicodeEncodeError as e:
+                    print(d, name, name[e.start:e.end], 'is not cp932')
+                    raise e
+            message = d['message']
+            message = replace_fallback(message, fallback)
+            try:
+                message.encode('cp932')
+                da['message'] = message
+            except UnicodeEncodeError as e:
+                print(d, message, message[e.start:e.end], 'is not cp932')
+                raise e
+            bcontent.append(da)
+        patch_ks_file(f, bcontent)
+