guanjihuan/py.guanjihuan.com
1
1
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

0.1.192

Browse Source
This commit is contained in:
guanjihuan
2025-12-08 12:46:30 +08:00
parent 01a35075d2
commit 7bcf9f0c87
3 changed files with 29 additions and 27 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
PyPI/setup.cfg
View File

@@ -1,7 +1,7 @@
[metadata]
# replace with your username:
name = guan
version = 0.1.191
version = 0.1.192
author = guanjihuan
author_email = guanjihuan@163.com
description = An open source python package

2
PyPI/src/guan.egg-info/PKG-INFO
View File

@@ -1,6 +1,6 @@
Metadata-Version: 2.4
Name: guan
Version: 0.1.191
Version: 0.1.192
Summary: An open source python package
Home-page: https://py.guanjihuan.com
Author: guanjihuan

52
PyPI/src/guan/data_processing.py
View File

@@ -83,24 +83,25 @@ def loop_calculation_with_three_parameters(function_name, parameter_array_1, par
# 文本对比
def word_diff(a, b, print_show=1):
import difflib
import re
import guan
a_words = guan.divide_text_into_words(a)
b_words = guan.divide_text_into_words(b)
import jieba
import logging
jieba.setLogLevel(logging.ERROR)
a_words = jieba.lcut(a)
b_words = jieba.lcut(b)
sm = difflib.SequenceMatcher(None, a_words, b_words)
result = []
for tag, i1, i2, j1, j2 in sm.get_opcodes():
if tag == "equal":
result.extend(a_words[i1:i2])
elif tag == "delete":
result.append("\033[91m" + " ".join(a_words[i1:i2]) + "\033[0m")
result.append("\033[9;91m" + "".join(a_words[i1:i2]) + "\033[0m")
elif tag == "insert":
result.append("\033[92m" + " ".join(b_words[j1:j2]) + "\033[0m")
result.append("\033[92m" + "".join(b_words[j1:j2]) + "\033[0m")
elif tag == "replace":
result.append("\033[91m" + " ".join(a_words[i1:i2]) + "\033[0m")
result.append("\033[92m" + " ".join(b_words[j1:j2]) + "\033[0m")
diff_result = " ".join(result)
diff_result = re.sub(r' +', ' ', diff_result)
result.append("\033[9;91m" + "".join(a_words[i1:i2]) + "\033[0m")
result.append(" ")
result.append("\033[92m" + "".join(b_words[j1:j2]) + "\033[0m")
diff_result = "".join(result)
if print_show:
print(diff_result)
return diff_result
@@ -109,33 +110,34 @@ def word_diff(a, b, print_show=1):
def word_diff_to_html(a, b, filename='diff_result', write_file=1):
import difflib
from html import escape
import re
import guan
a_words = guan.divide_text_into_words(a)
b_words = guan.divide_text_into_words(b)
import jieba
import logging
jieba.setLogLevel(logging.ERROR)
a_words = jieba.lcut(a)
b_words = jieba.lcut(b)
sm = difflib.SequenceMatcher(None, a_words, b_words)
html_parts = []
for tag, i1, i2, j1, j2 in sm.get_opcodes():
if tag == "equal":
html_parts.append(" ".join(map(escape, a_words[i1:i2])))
html_parts.append("".join(map(escape, a_words[i1:i2])))
elif tag == "delete":
html_parts.append(f"<span style='background:#e74c3c;color:white;padding:1px 2px;border-radius:2px'>"
+ " ".join(map(escape, a_words[i1:i2]))
html_parts.append(f"<span style='background:#e74c3c;color:white;padding:1px 2px;border-radius:2px;text-decoration:line-through;'>"
+ "".join(map(escape, a_words[i1:i2]))
+ "</span>")
elif tag == "insert":
html_parts.append(f"<span style='background:#2ecc71;color:white;padding:1px 2px;border-radius:2px'>"
+ " ".join(map(escape, b_words[j1:j2]))
html_parts.append(f"<span style='background:#2ecc71;color:white;padding:1px 2px;border-radius:2px;'>"
+ "".join(map(escape, b_words[j1:j2]))
+ "</span>")
elif tag == "replace":
html_parts.append(f"<span style='background:#e74c3c;color:white;padding:1px 2px;border-radius:2px'>"
+ " ".join(map(escape, a_words[i1:i2]))
html_parts.append(f"<span style='background:#e74c3c;color:white;padding:1px 2px;border-radius:2px;text-decoration:line-through;'>"
+ "".join(map(escape, a_words[i1:i2]))
+ "</span>")
html_parts.append(f"<span style='background:#2ecc71;color:white;padding:1px 2px;border-radius:2px'>"
+ " ".join(map(escape, b_words[j1:j2]))
html_parts.append(" ")
html_parts.append(f"<span style='background:#2ecc71;color:white;padding:1px 2px;border-radius:2px;'>"
+ "".join(map(escape, b_words[j1:j2]))
+ "</span>")
diff_result = " ".join(html_parts)
diff_result = "".join(html_parts)
diff_result = diff_result.replace("\n", "<br>")
diff_result = re.sub(r' +', ' ', diff_result)
if write_file:
with open(filename+'.html', 'w', encoding='UTF-8') as f:
f.write(diff_result)