Add iinkai extract script

iinkai.py

@@ -0,0 +1,135 @@
+from KAGParser import *
+from html import escape
+import json
+from os.path import isdir, join, basename, splitext, dirname
+from os import listdir, makedirs
+from typing import List
+from csv import DictWriter
+
+
+def extract_script(script_path: str, output_path: str):
+    with open(script_path, "r", encoding="utf-8") as f:
+        script_text = f.read()
+    parser = KAGScriptParser(script_text)
+    script = parser.parse(True)
+    name = None
+    message = ''
+    result = []
+    for line in script:
+        if isinstance(line, CommandNode):
+            cmd = line
+            if cmd.name == 'page':
+                d = {}
+                if name is not None:
+                    d['name'] = name
+                d['message'] = message
+                message = ''
+                result.append(d)
+                name = None
+            elif cmd.name.startswith("【") and cmd.name.endswith("】"):
+                name = cmd.name[1:-1]
+        elif isinstance(line, list):
+            for node in line:
+                if isinstance(node, TextNode):
+                    message += node.text.replace("&", "&amp;").replace("<", "&lt;")
+                elif isinstance(node, TagNode):
+                    data = f"<{escape(node.name)}"
+                    for k, v in node.attributes.items():
+                        data += f' {escape(k)}="{escape(v)}"'
+                    data += ">"
+                    message += data
+    if name is not None or message:
+        d = {}
+        if name is not None:
+            d['name'] = name
+        d['message'] = message
+        result.append(d)
+    with open(output_path, "w", encoding="utf-8") as f:
+        json.dump(result, f, ensure_ascii=False, indent=2)
+
+
+def extract_dict(script_path: str, output_path: str):
+    with open(script_path, "r", encoding="utf-8") as f:
+        script_text = f.read()
+    in_dict = False
+    dict_data = '\n'
+    for line in script_text.splitlines():
+        if line == "var text = '":
+            in_dict = True
+        elif line == "';":
+            in_dict = False
+        elif in_dict:
+            dict_data += line + "\n"
+    script = KAGScriptParser(dict_data).parse(True)
+    dict = {}
+    label = None
+    term: List[str] = []
+    for line in script:
+        if isinstance(line, LabelNode):
+            label = line.name[1:]
+        elif isinstance(line, list):
+            if len(term) > 0:
+                term.append('\n')
+            for node in line:
+                if isinstance(node, TextNode):
+                    term.append(node.text)
+                else:
+                    raise ValueError("Unexpected node type in dict.scn", node)
+        elif isinstance(line, CommandNode):
+            if line.name == "return":
+                # 干掉名字
+                term.pop(0)
+                term.pop(0)
+                # 干掉傻逼片假名
+                if len(term) > 0 and term[0].startswith("【") and term[0].endswith("】"):
+                    term.pop(0)
+                    term.pop(0)  # 去掉换行
+                dict[label] = ''.join(term)
+                term = []
+                label = None
+    with open(output_path, "w", encoding="utf-8-sig", newline="") as f:
+        writer = DictWriter(f, fieldnames=["term", "translation", "description"], lineterminator="\n")
+        writer.writeheader()
+        for k, v in dict.items():
+            writer.writerow({"term": k, "translation": "", "description": v})
+
+def extract_script_auto(script_path: str, output_path: str):
+    if isdir(script_path):
+        for file in listdir(script_path):
+            if not file.lower().endswith(".scn"):
+                continue
+            full_path = join(script_path, file)
+            output_file = splitext(basename(file))[0]
+            if file == "dict.scn":
+                output_file += ".csv"
+            else:
+                output_file += ".json"
+            output_full_path = join(output_path, output_file)
+            pdir = dirname(output_full_path)
+            if pdir and not isdir(pdir):
+                makedirs(pdir, exist_ok=True)
+            if file == "dict.scn":
+                extract_dict(full_path, output_full_path)
+            else:
+                extract_script(full_path, output_full_path)
+    else:
+        pdir = dirname(output_path)
+        if pdir and not isdir(pdir):
+            makedirs(pdir, exist_ok=True)
+        base_name = basename(script_path)
+        if base_name == "dict.scn":
+            extract_dict(script_path, output_path)
+        else:
+            extract_script(script_path, output_path)
+
+
+if __name__ == "__main__":
+    from argparse import ArgumentParser
+    parser = ArgumentParser(description="Process KAG script files")
+    subparser = parser.add_subparsers(title="Commands", dest="command")
+    extract_parser = subparser.add_parser("extract", help="Extract script to JSON")
+    extract_parser.add_argument("script_path", help="Path to KAG script file or directory")
+    extract_parser.add_argument("output_path", help="Path to output JSON file or directory")
+    args = parser.parse_args()
+    if args.command == "extract":
+        extract_script_auto(args.script_path, args.output_path)