Merge 26b8d4d7ee into be83907394

crazy_functions/latex_fns/latex_actions.py

@@ -16,7 +16,7 @@ from crazy_functions.latex_fns.latex_pickle_io import objdump, objload
 pj = os.path.join
 
 
-def split_subprocess(txt, project_folder, return_dict, opts):
+def split_subprocess(txt: str, project_folder: str, return_dict, opts):
     """
     break down latex file to a linked list,
     each node use a preserve flag to indicate whether it should
@@ -30,26 +30,24 @@ def split_subprocess(txt, project_folder, return_dict, opts):
     text, mask = set_forbidden_text(text, mask, r"^(.*?)\\begin{document}", re.DOTALL)
     # 吸收iffalse注释
     text, mask = set_forbidden_text(text, mask, r"\\iffalse(.*?)\\fi", re.DOTALL)
-    # 吸收在42行以内的begin-end组合
+    # 吸收在42行以内的begin-end组合 (为什么要吸收啊... 我的theorem基本都被剔除了)
-    text, mask = set_forbidden_text_begin_end(text, mask, r"\\begin\{([a-z\*]*)\}(.*?)\\end\{\1\}", re.DOTALL, limit_n_lines=42)
+    # text, mask = set_forbidden_text_begin_end(text, mask, r"\\begin\{([a-z\*]*)\}(.*?)\\end\{\1\}", re.DOTALL, limit_n_lines=42)
     # 吸收匿名公式
     text, mask = set_forbidden_text(text, mask, [ r"\$\$([^$]+)\$\$",  r"\\\[.*?\\\]" ], re.DOTALL)
     # 吸收其他杂项
-    text, mask = set_forbidden_text(text, mask, [ r"\\section\{(.*?)\}", r"\\section\*\{(.*?)\}", r"\\subsection\{(.*?)\}", r"\\subsubsection\{(.*?)\}" ])
+    text, mask = set_forbidden_text(text, mask, [ r"\\section\*?\{(.*?)\}", r"\\subsection\{(.*?)\}", r"\\subsubsection\{(.*?)\}" ])
     text, mask = set_forbidden_text(text, mask, [ r"\\bibliography\{(.*?)\}", r"\\bibliographystyle\{(.*?)\}" ])
-    text, mask = set_forbidden_text(text, mask, r"\\begin\{thebibliography\}.*?\\end\{thebibliography\}", re.DOTALL)
+    for environment in [
-    text, mask = set_forbidden_text(text, mask, r"\\begin\{lstlisting\}(.*?)\\end\{lstlisting\}", re.DOTALL)
+        "thebibliography", 
-    text, mask = set_forbidden_text(text, mask, r"\\begin\{wraptable\}(.*?)\\end\{wraptable\}", re.DOTALL)
+        "wraptable", "table", "tabular",
-    text, mask = set_forbidden_text(text, mask, r"\\begin\{algorithm\}(.*?)\\end\{algorithm\}", re.DOTALL)
+        "wrapfigure", "figure", "tikzpicture",
-    text, mask = set_forbidden_text(text, mask, [r"\\begin\{wrapfigure\}(.*?)\\end\{wrapfigure\}", r"\\begin\{wrapfigure\*\}(.*?)\\end\{wrapfigure\*\}"], re.DOTALL)
+        "lstlisting", "algorithm", "algorithmic", 
-    text, mask = set_forbidden_text(text, mask, [r"\\begin\{figure\}(.*?)\\end\{figure\}", r"\\begin\{figure\*\}(.*?)\\end\{figure\*\}"], re.DOTALL)
+        "multline", "align", "equation",
-    text, mask = set_forbidden_text(text, mask, [r"\\begin\{multline\}(.*?)\\end\{multline\}", r"\\begin\{multline\*\}(.*?)\\end\{multline\*\}"], re.DOTALL)
+        "minipage", 
-    text, mask = set_forbidden_text(text, mask, [r"\\begin\{table\}(.*?)\\end\{table\}", r"\\begin\{table\*\}(.*?)\\end\{table\*\}"], re.DOTALL)
+    ]:
-    text, mask = set_forbidden_text(text, mask, [r"\\begin\{minipage\}(.*?)\\end\{minipage\}", r"\\begin\{minipage\*\}(.*?)\\end\{minipage\*\}"], re.DOTALL)
+        text, mask = set_forbidden_text(text, mask, rf"\\begin\{{({environment}\*?)\}}(.*?)\\end\{{\1\}}", re.DOTALL)
-    text, mask = set_forbidden_text(text, mask, [r"\\begin\{align\*\}(.*?)\\end\{align\*\}", r"\\begin\{align\}(.*?)\\end\{align\}"], re.DOTALL)
-    text, mask = set_forbidden_text(text, mask, [r"\\begin\{equation\}(.*?)\\end\{equation\}", r"\\begin\{equation\*\}(.*?)\\end\{equation\*\}"], re.DOTALL)
     text, mask = set_forbidden_text(text, mask, [r"\\includepdf\[(.*?)\]\{(.*?)\}", r"\\clearpage", r"\\newpage", r"\\appendix", r"\\tableofcontents", r"\\include\{(.*?)\}"])
-    text, mask = set_forbidden_text(text, mask, [r"\\vspace\{(.*?)\}", r"\\hspace\{(.*?)\}", r"\\label\{(.*?)\}", r"\\begin\{(.*?)\}", r"\\end\{(.*?)\}", r"\\item "])
+    text, mask = set_forbidden_text(text, mask, [r"\\vspace\{(.*?)\}", r"\\hspace\{(.*?)\}", r"\\label\{(.*?)\}", r"\\begin\{(.*?)\}", r"\\end\{(.*?)\}", r"\\item\s?"])
     text, mask = set_forbidden_text_careful_brace(text, mask, r"\\hl\{(.*?)\}", re.DOTALL)
     # reverse 操作必须放在最后
     text, mask = reverse_forbidden_text_careful_brace(text, mask, r"\\caption\{(.*?)\}", re.DOTALL, forbid_wrapper=True)
@@ -97,13 +95,21 @@ class LatexPaperSplit():
         self.title = "unknown"
         self.abstract = "unknown"
 
-    def read_title_and_abstract(self, txt):
+    def shrink_spaces(self, text: str):
+        """删除空白字符 包含\\n, \\\\, \\t, 空格
+        
+        残存BUG: 未考虑\\\\[length]"""
+        text = text.replace('\\\\', ' ')
+        pattern = re.compile(r'\s+')
+        return re.sub(pattern, ' ', text)
+
+    def read_title_and_abstract(self, txt: str):
         try:
             title, abstract = find_title_and_abs(txt)
             if title is not None:
-                self.title = title.replace('\n', ' ').replace('\\\\', ' ').replace('  ', '').replace('  ', '')
+                self.title = self.shrink_spaces(title)
             if abstract is not None:
-                self.abstract = abstract.replace('\n', ' ').replace('\\\\', ' ').replace('  ', '').replace('  ', '')
+                self.abstract = self.shrink_spaces(abstract)
         except:
             pass
 
@@ -147,7 +153,7 @@ class LatexPaperSplit():
         return result_string
 
 
-    def split(self, txt, project_folder, opts):
+    def split(self, txt: str, project_folder: str, opts: list):
         """
         break down latex file to a linked list,
         each node use a preserve flag to indicate whether it should
@@ -215,7 +221,7 @@ class LatexPaperFileGroup():
         return manifest
 
 
-def Latex精细分解与转化(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, mode='proofread', switch_prompt=None, opts=[]):
+def Latex精细分解与转化(file_manifest: list[str], project_folder: str, llm_kwargs: dict[str,str], plugin_kwargs: dict[str,str], chatbot, history:list[str], system_prompt, mode='proofread', switch_prompt=None, opts=[]):
     import time, os, re
     from ..crazy_utils import request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency
     from .latex_actions import LatexPaperFileGroup, LatexPaperSplit

crazy_functions/latex_fns/latex_toolbox.py

@@ -153,9 +153,9 @@ Latex segmentation with a binary mask (PRESERVE=0, TRANSFORM=1)
 def set_forbidden_text(text, mask, pattern, flags=0):
     """
     Add a preserve text area in this paper
-    e.g. with pattern = r"\\begin\{algorithm\}(.*?)\\end\{algorithm\}"
+    e.g. with pattern = r"\\begin\\{algorithm\\}(.*?)\\end\\{algorithm\\}"
     you can mask out (mask = PRESERVE so that text become untouchable for GPT)
-    everything between "\begin{equation}" and "\end{equation}"
+    everything between "\\begin{equation}" and "\\end{equation}"
     """
     if isinstance(pattern, list):
         pattern = "|".join(pattern)
@@ -331,18 +331,59 @@ def find_main_tex_file(file_manifest, mode):
         return candidates[select]
 
 
-def rm_comments(main_file):
+def rm_comments_inline(content: str):
-    new_file_remove_comment_lines = []
+    """删除掉所有行内注释"""
-    for l in main_file.splitlines():
+    pattern = re.compile(r"(?<!\\)%.*\n[ \t\r\f\v]*")
-        # 删除整行的空注释
+    return re.sub(pattern, "", content)
-        if l.lstrip().startswith("%"):
+
-            pass
+
-        else:
+def rm_comments_block(content: str):
-            new_file_remove_comment_lines.append(l)
+    """删除掉所有块注释"""
-    main_file = "\n".join(new_file_remove_comment_lines)
+    stack: list[int] = []
-    # main_file = re.sub(r"\\include{(.*?)}", r"\\input{\1}", main_file)  # 将 \include 命令转换为 \input 命令
+    output: list[str] = []
-    main_file = re.sub(r"(?<!\\)%.*", "", main_file)  # 使用正则表达式查找半行注释, 并替换为空字符串
+    pos = 0
-    return main_file
+    len_text = len(content)
+    pattern = re.compile(r"\\begin\{comment\}|\\end\{comment\}")
+
+    for match in pattern.finditer(content):
+        start, end = match.start(), match.end()
+        tag = match.group()
+
+        # 记录非注释内容
+        if not stack:
+            output.append(content[pos:start])
+
+        # 处理标签
+        if tag == r"\begin{comment}":
+            stack.append(end)  # 记录起始位置
+        else:  # \end{comment}
+            if stack:
+                stack.pop()  # 弹出匹配的\begin{comment}
+            else:
+                raise ValueError("\\end{comment}没有匹配的\\begin{comment}")
+
+        pos = end
+
+    # 添加最后一段内容（如果存在）
+    if stack:
+        raise ValueError("\\begin{comment}没有匹配的\\end{comment}")
+    elif pos < len_text:
+        output.append(content[pos:])
+
+    return "".join(output)
+
+
+def rm_comments(main_file: str):
+    """删除掉所有注释
+
+    TeX文件有数种注释:
+    - % 注释: 删除本行%后所有内容, 删除回车, 删除下一行缩进
+    - \\iffalse ... \\fi 注释: 呃, 删不动... (主要是可能的嵌套问题)
+    - \\begin{comment} ... \\end{comment} 注释: 删除所有内容
+
+    残存BUG: 未考虑 % 在verbatim环境中出现的情况
+    """
+    return rm_comments_block(rm_comments_inline(main_file))
 
 
 def find_tex_file_ignore_case(fp):