Latex File Name Bug Patch

config.py

@@ -56,6 +56,9 @@ LOCAL_MODEL_DEVICE = "cpu" # 可选 "cuda"
 # 设置gradio的并行线程数（不需要修改）
 CONCURRENT_COUNT = 100
 
+# 是否在提交时自动清空输入框
+AUTO_CLEAR_TXT = False
+
 # 加一个live2d装饰
 ADD_WAIFU = False
 

core_functional.py

@@ -63,6 +63,7 @@ def get_core_functions():
             "Prefix":   r"我需要你找一张网络图片。使用Unsplash API(https://source.unsplash.com/960x640/?<英语关键词>)获取图片URL，" +
                         r"然后请使用Markdown格式封装，并且不要有反斜线，不要用代码块。现在，请按以下描述给我发送图片：" + "\n\n",
             "Suffix":   r"",
+            "Visible": False,
         },
         "解释代码": {
             "Prefix":   r"请解释以下代码：" + "\n```\n",
@@ -73,6 +74,5 @@ def get_core_functions():
                         r"Note that, reference styles maybe more than one kind, you should transform each item correctly." +
                         r"Items need to be transformed:",
             "Suffix":   r"",
-            "Visible": False,
         }
     }

crazy_functions/crazy_functions_test.py

@@ -193,8 +193,9 @@ def test_Latex():
     # txt = r"https://arxiv.org/abs/2212.10156"
     # txt = r"https://arxiv.org/abs/2211.11559"
     # txt = r"https://arxiv.org/abs/2303.08774"
-    txt = r"https://arxiv.org/abs/2303.12712"
+    # txt = r"https://arxiv.org/abs/2303.12712"
     # txt = r"C:\Users\fuqingxu\arxiv_cache\2303.12712\workfolder"
+    txt = r"2306.17157" # 这个paper有个input命令文件名大小写错误！
     
 
     for cookies, cb, hist, msg in (Latex翻译中文并重新编译PDF)(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):

crazy_functions/latex_utils.py

@@ -27,6 +27,24 @@ def set_forbidden_text(text, mask, pattern, flags=0):
         mask[res.span()[0]:res.span()[1]] = PRESERVE
     return text, mask
 
+def reverse_forbidden_text(text, mask, pattern, flags=0, forbid_wrapper=True):
+    """
+    Move area out of preserve area (make text editable for GPT)
+    count the number of the braces so as to catch compelete text area. 
+    e.g.
+    \begin{abstract} blablablablablabla. \end{abstract} 
+    """
+    if isinstance(pattern, list): pattern = '|'.join(pattern)
+    pattern_compile = re.compile(pattern, flags)
+    for res in pattern_compile.finditer(text):
+        if not forbid_wrapper:
+            mask[res.span()[0]:res.span()[1]] = TRANSFORM
+        else:
+            mask[res.regs[0][0]: res.regs[1][0]] = PRESERVE   # '\\begin{abstract}'
+            mask[res.regs[1][0]: res.regs[1][1]] = TRANSFORM   # abstract
+            mask[res.regs[1][1]: res.regs[0][1]] = PRESERVE   # abstract
+    return text, mask
+
 def set_forbidden_text_careful_brace(text, mask, pattern, flags=0):
     """
     Add a preserve text area in this paper (text become untouchable for GPT).
@@ -171,6 +189,18 @@ def rm_comments(main_file):
     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
     return main_file
 
+def find_tex_file_ignore_case(fp):
+    dir_name = os.path.dirname(fp)
+    base_name = os.path.basename(fp)
+    if not base_name.endswith('.tex'): base_name+='.tex'
+    if os.path.exists(pj(dir_name, base_name)): return pj(dir_name, base_name)
+    # go case in-sensitive
+    import glob
+    for f in glob.glob(dir_name+'/*.tex'):
+        base_name_s = os.path.basename(fp)
+        if base_name_s.lower() == base_name.lower(): return f
+    return None
+
 def merge_tex_files_(project_foler, main_file, mode):
     """
     Merge Tex project recrusively
@@ -179,14 +209,11 @@ def merge_tex_files_(project_foler, main_file, mode):
     for s in reversed([q for q in re.finditer(r"\\input\{(.*?)\}", main_file, re.M)]):
         f = s.group(1)
         fp = os.path.join(project_foler, f)
-        if os.path.exists(fp):  
-            # e.g., \input{srcs/07_appendix.tex}
-            with open(fp, 'r', encoding='utf-8', errors='replace') as fx:
-                c = fx.read()
-        else:  
-            # e.g., \input{srcs/07_appendix}
-            with open(fp+'.tex', 'r', encoding='utf-8', errors='replace') as fx:
-                c = fx.read()
+        fp = find_tex_file_ignore_case(fp)
+        if fp:
+            with open(fp, 'r', encoding='utf-8', errors='replace') as fx: c = fx.read()
+        else:
+            raise RuntimeError(f'找不到{fp}，Tex源文件缺失！')
         c = merge_tex_files_(project_foler, c, mode)
         main_file = main_file[:s.span()[0]] + c + main_file[s.span()[1]:]
     return main_file
@@ -326,6 +353,7 @@ def split_subprocess(txt, project_folder, return_dict, opts):
     # 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)
     text, mask = reverse_forbidden_text_careful_brace(text, mask, r"\\abstract\{(.*?)\}", re.DOTALL, forbid_wrapper=True)
+    text, mask = reverse_forbidden_text(text, mask, r"\\begin\{abstract\}(.*?)\\end\{abstract\}", re.DOTALL, forbid_wrapper=True)
     root = convert_to_linklist(text, mask)
 
     # 修复括号
@@ -672,10 +700,9 @@ def remove_buggy_lines(file_path, log_path, tex_name, tex_name_pure, n_fix, work
         print("Fatal error occurred, but we cannot identify error, please download zip, read latex log, and compile manually.")
         return False, -1, [-1]
     
-
-def compile_latex_with_timeout(command, timeout=60):
+def compile_latex_with_timeout(command, cwd, timeout=60):
     import subprocess
-    process = subprocess.Popen(command, shell=True, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
+    process = subprocess.Popen(command, shell=True, stdout=subprocess.PIPE, stderr=subprocess.PIPE, cwd=cwd)
     try:
         stdout, stderr = process.communicate(timeout=timeout)
     except subprocess.TimeoutExpired:
@@ -699,24 +726,24 @@ def 编译Latex(chatbot, history, main_file_original, main_file_modified, work_f
 
         # https://stackoverflow.com/questions/738755/dont-make-me-manually-abort-a-latex-compile-when-theres-an-error
         yield from update_ui_lastest_msg(f'尝试第 {n_fix}/{max_try} 次编译, 编译原始PDF ...', chatbot, history)   # 刷新Gradio前端界面
-        os.chdir(work_folder_original); ok = compile_latex_with_timeout(f'pdflatex -interaction=batchmode -file-line-error {main_file_original}.tex'); os.chdir(current_dir)
+        ok = compile_latex_with_timeout(f'pdflatex -interaction=batchmode -file-line-error {main_file_original}.tex', work_folder_original)
 
         yield from update_ui_lastest_msg(f'尝试第 {n_fix}/{max_try} 次编译, 编译转化后的PDF ...', chatbot, history)   # 刷新Gradio前端界面
-        os.chdir(work_folder_modified); ok = compile_latex_with_timeout(f'pdflatex -interaction=batchmode -file-line-error {main_file_modified}.tex'); os.chdir(current_dir)
+        ok = compile_latex_with_timeout(f'pdflatex -interaction=batchmode -file-line-error {main_file_modified}.tex', work_folder_modified)
         
         if ok and os.path.exists(pj(work_folder_modified, f'{main_file_modified}.pdf')):
             # 只有第二步成功，才能继续下面的步骤
             yield from update_ui_lastest_msg(f'尝试第 {n_fix}/{max_try} 次编译, 编译BibTex ...', chatbot, history)    # 刷新Gradio前端界面
             if not os.path.exists(pj(work_folder_original, f'{main_file_original}.bbl')):
-                os.chdir(work_folder_original); ok = compile_latex_with_timeout(f'bibtex  {main_file_original}.aux'); os.chdir(current_dir)
+                ok = compile_latex_with_timeout(f'bibtex  {main_file_original}.aux', work_folder_original)
             if not os.path.exists(pj(work_folder_modified, f'{main_file_modified}.bbl')):
-                os.chdir(work_folder_modified); ok = compile_latex_with_timeout(f'bibtex  {main_file_modified}.aux'); os.chdir(current_dir)
+                ok = compile_latex_with_timeout(f'bibtex  {main_file_modified}.aux', work_folder_modified)
 
             yield from update_ui_lastest_msg(f'尝试第 {n_fix}/{max_try} 次编译, 编译文献交叉引用 ...', chatbot, history)  # 刷新Gradio前端界面
-            os.chdir(work_folder_original); ok = compile_latex_with_timeout(f'pdflatex -interaction=batchmode -file-line-error {main_file_original}.tex'); os.chdir(current_dir)
-            os.chdir(work_folder_modified); ok = compile_latex_with_timeout(f'pdflatex -interaction=batchmode -file-line-error {main_file_modified}.tex'); os.chdir(current_dir)
-            os.chdir(work_folder_original); ok = compile_latex_with_timeout(f'pdflatex -interaction=batchmode -file-line-error {main_file_original}.tex'); os.chdir(current_dir)
-            os.chdir(work_folder_modified); ok = compile_latex_with_timeout(f'pdflatex -interaction=batchmode -file-line-error {main_file_modified}.tex'); os.chdir(current_dir)
+            ok = compile_latex_with_timeout(f'pdflatex -interaction=batchmode -file-line-error {main_file_original}.tex', work_folder_original)
+            ok = compile_latex_with_timeout(f'pdflatex -interaction=batchmode -file-line-error {main_file_modified}.tex', work_folder_modified)
+            ok = compile_latex_with_timeout(f'pdflatex -interaction=batchmode -file-line-error {main_file_original}.tex', work_folder_original)
+            ok = compile_latex_with_timeout(f'pdflatex -interaction=batchmode -file-line-error {main_file_modified}.tex', work_folder_modified)
 
             if mode!='translate_zh':
                 yield from update_ui_lastest_msg(f'尝试第 {n_fix}/{max_try} 次编译, 使用latexdiff生成论文转化前后对比 ...', chatbot, history) # 刷新Gradio前端界面
@@ -724,13 +751,11 @@ def 编译Latex(chatbot, history, main_file_original, main_file_modified, work_f
                 ok = compile_latex_with_timeout(f'latexdiff --encoding=utf8 --append-safecmd=subfile {work_folder_original}/{main_file_original}.tex  {work_folder_modified}/{main_file_modified}.tex --flatten > {work_folder}/merge_diff.tex')
 
                 yield from update_ui_lastest_msg(f'尝试第 {n_fix}/{max_try} 次编译, 正在编译对比PDF ...', chatbot, history)   # 刷新Gradio前端界面
-                os.chdir(work_folder); ok = compile_latex_with_timeout(f'pdflatex  -interaction=batchmode -file-line-error merge_diff.tex'); os.chdir(current_dir)
-                os.chdir(work_folder); ok = compile_latex_with_timeout(f'bibtex    merge_diff.aux'); os.chdir(current_dir)
-                os.chdir(work_folder); ok = compile_latex_with_timeout(f'pdflatex  -interaction=batchmode -file-line-error merge_diff.tex'); os.chdir(current_dir)
-                os.chdir(work_folder); ok = compile_latex_with_timeout(f'pdflatex  -interaction=batchmode -file-line-error merge_diff.tex'); os.chdir(current_dir)
+                ok = compile_latex_with_timeout(f'pdflatex  -interaction=batchmode -file-line-error merge_diff.tex', work_folder)
+                ok = compile_latex_with_timeout(f'bibtex    merge_diff.aux', work_folder)
+                ok = compile_latex_with_timeout(f'pdflatex  -interaction=batchmode -file-line-error merge_diff.tex', work_folder)
+                ok = compile_latex_with_timeout(f'pdflatex  -interaction=batchmode -file-line-error merge_diff.tex', work_folder)
 
-        # <--------------------->
-        os.chdir(current_dir)
 
         # <---------- 检查结果 ----------->
         results_ = ""
@@ -766,7 +791,6 @@ def 编译Latex(chatbot, history, main_file_original, main_file_modified, work_f
             yield from update_ui_lastest_msg(f'由于最为关键的转化PDF编译失败, 将根据报错信息修正tex源文件并重试, 当前报错的latex代码处于第{buggy_lines}行 ...', chatbot, history)   # 刷新Gradio前端界面
             if not can_retry: break
 
-    os.chdir(current_dir)
     return False # 失败啦
 
 

crazy_functions/图片生成.py

@@ -27,8 +27,10 @@ def gen_image(llm_kwargs, prompt, resolution="256x256"):
     }
     response = requests.post(url, headers=headers, json=data, proxies=proxies)
     print(response.content)
-    image_url = json.loads(response.content.decode('utf8'))['data'][0]['url']
-
+    try:
+        image_url = json.loads(response.content.decode('utf8'))['data'][0]['url']
+    except:
+        raise RuntimeError(response.content.decode())
     # 文件保存到本地
     r = requests.get(image_url, proxies=proxies)
     file_path = 'gpt_log/image_gen/'

crazy_functions/批量翻译PDF文档_多线程.py

@@ -1,5 +1,5 @@
 from toolbox import CatchException, report_execption, write_results_to_file
-from toolbox import update_ui
+from toolbox import update_ui, promote_file_to_downloadzone
 from .crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
 from .crazy_utils import request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency
 from .crazy_utils import read_and_clean_pdf_text
@@ -147,23 +147,14 @@ def 解析PDF(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot,
             print('writing html result failed:', trimmed_format_exc())
 
     # 准备文件的下载
-    import shutil
     for pdf_path in generated_conclusion_files:
         # 重命名文件
-        rename_file = f'./gpt_log/翻译-{os.path.basename(pdf_path)}'
-        if os.path.exists(rename_file):
-            os.remove(rename_file)
-        shutil.copyfile(pdf_path, rename_file)
-        if os.path.exists(pdf_path):
-            os.remove(pdf_path)
+        rename_file = f'翻译-{os.path.basename(pdf_path)}'
+        promote_file_to_downloadzone(pdf_path, rename_file=rename_file, chatbot=chatbot)
     for html_path in generated_html_files:
         # 重命名文件
-        rename_file = f'./gpt_log/翻译-{os.path.basename(html_path)}'
-        if os.path.exists(rename_file):
-            os.remove(rename_file)
-        shutil.copyfile(html_path, rename_file)
-        if os.path.exists(html_path):
-            os.remove(html_path)
+        rename_file = f'翻译-{os.path.basename(html_path)}'
+        promote_file_to_downloadzone(html_path, rename_file=rename_file, chatbot=chatbot)
     chatbot.append(("给出输出文件清单", str(generated_conclusion_files + generated_html_files)))
     yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
 

main.py

@@ -6,8 +6,8 @@ def main():
     from request_llm.bridge_all import predict
     from toolbox import format_io, find_free_port, on_file_uploaded, on_report_generated, get_conf, ArgsGeneralWrapper, DummyWith
     # 建议您复制一个config_private.py放自己的秘密, 如API和代理网址, 避免不小心传github被别人看到
-    proxies, WEB_PORT, LLM_MODEL, CONCURRENT_COUNT, AUTHENTICATION, CHATBOT_HEIGHT, LAYOUT, API_KEY, AVAIL_LLM_MODELS = \
-        get_conf('proxies', 'WEB_PORT', 'LLM_MODEL', 'CONCURRENT_COUNT', 'AUTHENTICATION', 'CHATBOT_HEIGHT', 'LAYOUT', 'API_KEY', 'AVAIL_LLM_MODELS')
+    proxies, WEB_PORT, LLM_MODEL, CONCURRENT_COUNT, AUTHENTICATION, CHATBOT_HEIGHT, LAYOUT, API_KEY, AVAIL_LLM_MODELS, AUTO_CLEAR_TXT = \
+        get_conf('proxies', 'WEB_PORT', 'LLM_MODEL', 'CONCURRENT_COUNT', 'AUTHENTICATION', 'CHATBOT_HEIGHT', 'LAYOUT', 'API_KEY', 'AVAIL_LLM_MODELS', 'AUTO_CLEAR_TXT')
 
     # 如果WEB_PORT是-1, 则随机选取WEB端口
     PORT = find_free_port() if WEB_PORT <= 0 else WEB_PORT
@@ -104,7 +104,7 @@ def main():
                     system_prompt = gr.Textbox(show_label=True, placeholder=f"System Prompt", label="System prompt", value=initial_prompt)
                     top_p = gr.Slider(minimum=-0, maximum=1.0, value=1.0, step=0.01,interactive=True, label="Top-p (nucleus sampling)",)
                     temperature = gr.Slider(minimum=-0, maximum=2.0, value=1.0, step=0.01, interactive=True, label="Temperature",)
-                    max_length_sl = gr.Slider(minimum=256, maximum=4096, value=512, step=1, interactive=True, label="Local LLM MaxLength",)
+                    max_length_sl = gr.Slider(minimum=256, maximum=8192, value=4096, step=1, interactive=True, label="Local LLM MaxLength",)
                     checkboxes = gr.CheckboxGroup(["基础功能区", "函数插件区", "底部输入区", "输入清除键", "插件参数区"], value=["基础功能区", "函数插件区"], label="显示/隐藏功能区")
                     md_dropdown = gr.Dropdown(AVAIL_LLM_MODELS, value=LLM_MODEL, label="更换LLM模型/请求源").style(container=False)
 
@@ -144,6 +144,11 @@ def main():
         resetBtn2.click(lambda: ([], [], "已重置"), None, [chatbot, history, status])
         clearBtn.click(lambda: ("",""), None, [txt, txt2])
         clearBtn2.click(lambda: ("",""), None, [txt, txt2])
+        if AUTO_CLEAR_TXT:
+            submitBtn.click(lambda: ("",""), None, [txt, txt2])
+            submitBtn2.click(lambda: ("",""), None, [txt, txt2])
+            txt.submit(lambda: ("",""), None, [txt, txt2])
+            txt2.submit(lambda: ("",""), None, [txt, txt2])
         # 基础功能区的回调函数注册
         for k in functional:
             if ("Visible" in functional[k]) and (not functional[k]["Visible"]): continue

request_llm/bridge_all.py

@@ -152,7 +152,7 @@ model_info = {
         "token_cnt": get_token_num_gpt4,
     },
 
-    # chatglm
+    # 将 chatglm 直接对齐到 chatglm2
     "chatglm": {
         "fn_with_ui": chatglm_ui,
         "fn_without_ui": chatglm_noui,
@@ -161,6 +161,15 @@ model_info = {
         "tokenizer": tokenizer_gpt35,
         "token_cnt": get_token_num_gpt35,
     },
+    "chatglm2": {
+        "fn_with_ui": chatglm_ui,
+        "fn_without_ui": chatglm_noui,
+        "endpoint": None,
+        "max_token": 1024,
+        "tokenizer": tokenizer_gpt35,
+        "token_cnt": get_token_num_gpt35,
+    },
+    
     # newbing
     "newbing": {
         "fn_with_ui": newbing_ui,

request_llm/bridge_chatglm.py

@@ -40,12 +40,12 @@ class GetGLMHandle(Process):
         while True:
             try:
                 if self.chatglm_model is None:
-                    self.chatglm_tokenizer = AutoTokenizer.from_pretrained("THUDM/chatglm-6b", trust_remote_code=True)
+                    self.chatglm_tokenizer = AutoTokenizer.from_pretrained("THUDM/chatglm2-6b", trust_remote_code=True)
                     device, = get_conf('LOCAL_MODEL_DEVICE')
                     if device=='cpu':
-                        self.chatglm_model = AutoModel.from_pretrained("THUDM/chatglm-6b", trust_remote_code=True).float()
+                        self.chatglm_model = AutoModel.from_pretrained("THUDM/chatglm2-6b", trust_remote_code=True).float()
                     else:
-                        self.chatglm_model = AutoModel.from_pretrained("THUDM/chatglm-6b", trust_remote_code=True).half().cuda()
+                        self.chatglm_model = AutoModel.from_pretrained("THUDM/chatglm2-6b", trust_remote_code=True).half().cuda()
                     self.chatglm_model = self.chatglm_model.eval()
                     break
                 else: