CC/gpt_academic
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

UTF8 Ignore read file errors

Browse Source
This commit is contained in:
fuqingxu
2023-04-12 16:57:01 +08:00
parent 88a86635c6
commit 40bd857c70
8 changed files with 55 additions and 8 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
crazy_functions/Latex全文润色.py
View File

@@ -45,7 +45,7 @@ def 多文件润色(file_manifest, project_folder, llm_kwargs, plugin_kwargs, ch
pfg = PaperFileGroup()
for index, fp in enumerate(file_manifest):
with open(fp, 'r', encoding='utf-8') as f:
with open(fp, 'r', encoding='utf-8', errors='replace') as f:
file_content = f.read()
# 定义注释的正则表达式
comment_pattern = r'%.*'

2
crazy_functions/Latex全文翻译.py
View File

@@ -44,7 +44,7 @@ def 多文件翻译(file_manifest, project_folder, llm_kwargs, plugin_kwargs, ch
pfg = PaperFileGroup()
for index, fp in enumerate(file_manifest):
with open(fp, 'r', encoding='utf-8') as f:
with open(fp, 'r', encoding='utf-8', errors='replace') as f:
file_content = f.read()
# 定义注释的正则表达式
comment_pattern = r'%.*'

4
crazy_functions/代码重写为全英文_多线程.py
View File

@@ -49,7 +49,7 @@ def 全项目切换英文(txt, llm_kwargs, plugin_kwargs, chatbot, history, sys_
# 第4步：随便显示点什么防止卡顿的感觉
for index, fp in enumerate(file_manifest):
# if 'test_project' in fp: continue
with open(fp, 'r', encoding='utf-8') as f:
with open(fp, 'r', encoding='utf-8', errors='replace') as f:
file_content = f.read()
i_say_show_user =f'[{index}/{len(file_manifest)}] 接下来请将以下代码中包含的所有中文转化为英文，只输出转化后的英文代码，请用代码块输出代码: {os.path.abspath(fp)}'
i_say_show_user_buffer.append(i_say_show_user)
@@ -72,7 +72,7 @@ def 全项目切换英文(txt, llm_kwargs, plugin_kwargs, chatbot, history, sys_
if index > 10:
time.sleep(60)
print('Openai 限制免费用户每分钟20次请求，降低请求频率中。')
with open(fp, 'r', encoding='utf-8') as f:
with open(fp, 'r', encoding='utf-8', errors='replace') as f:
file_content = f.read()
i_say_template = lambda fp, file_content: f'接下来请将以下代码中包含的所有中文转化为英文，只输出代码，文件名是{fp}，文件代码是 ```{file_content}```'
try:

2
crazy_functions/批量总结PDF文档pdfminer.py
View File

@@ -68,7 +68,7 @@ def 解析Paper(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbo
print('begin analysis on:', file_manifest)
for index, fp in enumerate(file_manifest):
if ".tex" in fp:
with open(fp, 'r', encoding='utf-8') as f:
with open(fp, 'r', encoding='utf-8', errors='replace') as f:
file_content = f.read()
if ".pdf" in fp.lower():
file_content = readPdf(fp)

2
crazy_functions/生成函数注释.py
View File

@@ -7,7 +7,7 @@ def 生成函数注释(file_manifest, project_folder, llm_kwargs, plugin_kwargs,
import time, os
print('begin analysis on:', file_manifest)
for index, fp in enumerate(file_manifest):
with open(fp, 'r', encoding='utf-8') as f:
with open(fp, 'r', encoding='utf-8', errors='replace') as f:
file_content = f.read()
i_say = f'请对下面的程序文件做一个概述，并对文件中的所有函数生成注释，使用markdown表格输出结果，文件名是{os.path.relpath(fp, project_folder)}，文件内容是 ```{file_content}```'

2
crazy_functions/解析项目源代码.py
View File

@@ -14,7 +14,7 @@ def 解析源代码新(file_manifest, project_folder, llm_kwargs, plugin_kwargs,
############################## <第一步，逐个文件分析，多线程> ##################################
for index, fp in enumerate(file_manifest):
with open(fp, 'r', encoding='utf-8') as f:
with open(fp, 'r', encoding='utf-8', errors='replace') as f:
file_content = f.read()
prefix = "接下来请你逐文件分析下面的工程" if index==0 else ""
i_say = prefix + f'请对下面的程序文件做一个概述文件名是{os.path.relpath(fp, project_folder)}，文件代码是 ```{file_content}```'

2
crazy_functions/读文章写摘要.py
View File

@@ -8,7 +8,7 @@ def 解析Paper(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbo
import time, glob, os
print('begin analysis on:', file_manifest)
for index, fp in enumerate(file_manifest):
with open(fp, 'r', encoding='utf-8') as f:
with open(fp, 'r', encoding='utf-8', errors='replace') as f:
file_content = f.read()
prefix = "接下来请你逐文件分析下面的论文文件，概括其内容" if index==0 else ""