给nougat加线程锁 合并冗余代码

This commit is contained in:
binary-husky
2023-09-13 23:21:00 +08:00
parent fb5467b85b
commit 14de282302
3 changed files with 57 additions and 133 deletions

View File

@@ -1,5 +1,6 @@
from toolbox import update_ui, get_conf, trimmed_format_exc
from toolbox import update_ui, get_conf, trimmed_format_exc, get_log_folder
import threading
import os
def input_clipping(inputs, history, max_token_limit):
import numpy as np
@@ -705,6 +706,40 @@ class knowledge_archive_interface():
)
self.threadLock.release()
return resp, prompt
@Singleton
class nougat_interface():
def __init__(self):
self.threadLock = threading.Lock()
def nougat_with_timeout(self, command, cwd, timeout=3600):
import subprocess
process = subprocess.Popen(command, shell=True, cwd=cwd)
try:
stdout, stderr = process.communicate(timeout=timeout)
except subprocess.TimeoutExpired:
process.kill()
stdout, stderr = process.communicate()
print("Process timed out!")
return False
return True
def NOUGAT_parse_pdf(self, fp):
self.threadLock.acquire()
import glob, threading, os
from toolbox import get_log_folder, gen_time_str
dst = os.path.join(get_log_folder(plugin_name='nougat'), gen_time_str())
os.makedirs(dst)
self.nougat_with_timeout(f'nougat --out "{os.path.abspath(dst)}" "{os.path.abspath(fp)}"', os.getcwd())
res = glob.glob(os.path.join(dst,'*.mmd'))
if len(res) == 0:
raise RuntimeError("Nougat解析论文失败。")
self.threadLock.release()
return res[0]
def try_install_deps(deps, reload_m=[]):
import subprocess, sys, importlib
@@ -715,42 +750,43 @@ def try_install_deps(deps, reload_m=[]):
for m in reload_m:
importlib.reload(__import__(m))
class construct_html():
def __init__(self) -> None:
self.css = """
HTML_CSS = """
.row {
display: flex;
flex-wrap: wrap;
}
.column {
flex: 1;
padding: 10px;
}
.table-header {
font-weight: bold;
border-bottom: 1px solid black;
}
.table-row {
border-bottom: 1px solid lightgray;
}
.table-cell {
padding: 5px;
}
"""
self.html_string = f'<!DOCTYPE html><head><meta charset="utf-8"><title>翻译结果</title><style>{self.css}</style></head>'
"""
def add_row(self, a, b):
tmp = """
TABLE_CSS = """
<div class="row table-row">
<div class="column table-cell">REPLACE_A</div>
<div class="column table-cell">REPLACE_B</div>
</div>
"""
"""
class construct_html():
def __init__(self) -> None:
self.css = HTML_CSS
self.html_string = f'<!DOCTYPE html><head><meta charset="utf-8"><title>翻译结果</title><style>{self.css}</style></head>'
def add_row(self, a, b):
tmp = TABLE_CSS
from toolbox import markdown_convertion
tmp = tmp.replace('REPLACE_A', markdown_convertion(a))
tmp = tmp.replace('REPLACE_B', markdown_convertion(b))
@@ -758,6 +794,6 @@ class construct_html():
def save_file(self, file_name):
with open(f'./gpt_log/{file_name}', 'w', encoding='utf8') as f:
with open(os.path.join(get_log_folder(), file_name), 'w', encoding='utf8') as f:
f.write(self.html_string.encode('utf-8', 'ignore').decode())
return os.path.join(get_log_folder(), file_name)