fix subprocess bug in Windows

crazy_functions/latex_utils.py

@@ -192,61 +192,7 @@ def fix_content(final_tex, node_string):
             final_tex = node_string # 出问题了，还原原文
     return final_tex
 
-
+def split_subprocess(txt, project_folder, return_dict):
-class LatexPaperSplit():
-    """
-    break down latex file to a linked list,
-    each node use a preserve flag to indicate whether it should
-    be proccessed by GPT.
-    """
-    def __init__(self) -> None:
-        self.nodes = None
-        self.msg = "{\\scriptsize\\textbf{警告：该PDF由GPT-Academic开源项目调用大语言模型+Latex翻译插件一键生成，" + \
-            "版权归原文作者所有。翻译内容可靠性无任何保障，请仔细鉴别并以原文为准。" + \
-            "项目Github地址 \\url{https://github.com/binary-husky/gpt_academic/}。"
-        # 请您不要删除或修改这行警告，除非您是论文的原作者（如果您是论文原作者，欢迎加REAME中的QQ联系开发者）
-        self.msg_declare = "为了防止大语言模型的意外谬误产生扩散影响，禁止移除或修改此警告。}}\\\\" 
-
-    def merge_result(self, arr, mode, msg):
-        """
-        Merge the result after the GPT process completed
-        """
-        result_string = ""
-        p = 0
-        for node in self.nodes:
-            if node.preserve:
-                result_string += node.string
-            else:
-                result_string += fix_content(arr[p], node.string)
-                p += 1
-        if mode == 'translate_zh':
-            pattern = re.compile(r'\\begin\{abstract\}.*\n')
-            match = pattern.search(result_string)
-            position = match.end()
-            result_string = result_string[:position] + self.msg + msg + self.msg_declare + result_string[position:]
-        return result_string
-
-    def split(self, txt, project_folder): 
-        """
-        break down latex file to a linked list,
-        each node use a preserve flag to indicate whether it should
-        be proccessed by GPT.
-        P.S. use multiprocessing to avoid timeout error
-        """
-        import multiprocessing
-        manager = multiprocessing.Manager()
-        return_dict = manager.dict()
-        p = multiprocessing.Process(
-            target=lambda lps, txt, project_folder, return_dict: 
-            lps.split_subprocess(txt, project_folder, return_dict), 
-            args=(self, txt, project_folder, return_dict))
-        p.start()
-        p.join()
-        self.nodes = return_dict['nodes']
-        self.sp = return_dict['segment_parts_for_gpt']
-        return self.sp
-
-    def split_subprocess(self, txt, project_folder, return_dict):
     """
     break down latex file to a linked list,
     each node use a preserve flag to indicate whether it should
@@ -388,6 +334,62 @@ class LatexPaperSplit():
     return_dict['segment_parts_for_gpt'] = segment_parts_for_gpt
     return return_dict
 
+
+
+class LatexPaperSplit():
+    """
+    break down latex file to a linked list,
+    each node use a preserve flag to indicate whether it should
+    be proccessed by GPT.
+    """
+    def __init__(self) -> None:
+        self.nodes = None
+        self.msg = "{\\scriptsize\\textbf{警告：该PDF由GPT-Academic开源项目调用大语言模型+Latex翻译插件一键生成，" + \
+            "版权归原文作者所有。翻译内容可靠性无任何保障，请仔细鉴别并以原文为准。" + \
+            "项目Github地址 \\url{https://github.com/binary-husky/gpt_academic/}。"
+        # 请您不要删除或修改这行警告，除非您是论文的原作者（如果您是论文原作者，欢迎加REAME中的QQ联系开发者）
+        self.msg_declare = "为了防止大语言模型的意外谬误产生扩散影响，禁止移除或修改此警告。}}\\\\" 
+
+    def merge_result(self, arr, mode, msg):
+        """
+        Merge the result after the GPT process completed
+        """
+        result_string = ""
+        p = 0
+        for node in self.nodes:
+            if node.preserve:
+                result_string += node.string
+            else:
+                result_string += fix_content(arr[p], node.string)
+                p += 1
+        if mode == 'translate_zh':
+            pattern = re.compile(r'\\begin\{abstract\}.*\n')
+            match = pattern.search(result_string)
+            position = match.end()
+            result_string = result_string[:position] + self.msg + msg + self.msg_declare + result_string[position:]
+        return result_string
+
+    def split(self, txt, project_folder): 
+        """
+        break down latex file to a linked list,
+        each node use a preserve flag to indicate whether it should
+        be proccessed by GPT.
+        P.S. use multiprocessing to avoid timeout error
+        """
+        import multiprocessing
+        manager = multiprocessing.Manager()
+        return_dict = manager.dict()
+        p = multiprocessing.Process(
+            target=split_subprocess, 
+            args=(txt, project_folder, return_dict))
+        p.start()
+        p.join()
+        self.nodes = return_dict['nodes']
+        self.sp = return_dict['segment_parts_for_gpt']
+        return self.sp
+
+
+
 class LatexPaperFileGroup():
     """
     use tokenizer to break down text according to max_token_limit