663 lines
35 KiB
Python
663 lines
35 KiB
Python
import os#用于处理文件和目录路径
|
||
import math
|
||
import tkinter as tk#用于创建图形用户界面（GUI）
|
||
from tkinter import ttk, filedialog, messagebox, scrolledtext
|
||
#提供提供现代风格的 GUI 组件，用于打开文件或文件夹选择对话框，用于显示消息框，用于创建带滚动条的文本框
|
||
from collections import defaultdict, Counter
|
||
#当访问不存在的键时，会自动创建一个默认值。用于统计元素的出现次数
|
||
from tkinter import font#字体
|
||
import nltk#自然语言处理工具包
|
||
from nltk.corpus import stopwords#用于获取停用词列表
|
||
import re#正则表达式模块，用于文本匹配和处理
|
||
from pyecharts import options as opts#用于创建交互式图表，这里用于生成词云，options：用于设置图表的选项
|
||
from pyecharts.charts import WordCloud#用于生成词云图
|
||
import webbrowser#用于在浏览器中打开文件
|
||
import tempfile#用于创建临时文件
|
||
import matplotlib.pyplot as plt#用于绘制图表，热力图和柱状图
|
||
import numpy as np#用于处理数组和矩阵
|
||
from matplotlib.colors import LinearSegmentedColormap#用于创建自定义颜色映射
|
||
plt.rcParams["font.family"] = ["SimHei", "WenQuanYi Micro Hei", "Heiti TC"]#设置 matplotlib 使用的字体，确保中文能够正常显示
|
||
plt.rcParams["axes.unicode_minus"] = False # 解决负号显示问题
|
||
nltk.download('stopwords')# 下载停用词所需数据
|
||
nltk.download('averaged_perceptron_tagger')#下载词性标注所需的数据
|
||
# 获取英文停用词列表
|
||
ENGLISH_STOPWORDS = set(stopwords.words('english'))
|
||
# 用于匹配数词的正则表达式
|
||
NUMBER_REGEX = re.compile(r'^[-+]?\d*\.?\d+([eE][-+]?\d+)?%?$')
|
||
# 英文数词列表
|
||
ENGLISH_NUMBERS = {
|
||
'zero', 'one', 'two', 'three', 'four', 'five', 'six', 'seven', 'eight', 'nine',
|
||
'ten', 'eleven', 'twelve', 'thirteen', 'fourteen', 'fifteen', 'sixteen',
|
||
'seventeen', 'eighteen', 'nineteen', 'twenty', 'thirty', 'forty', 'fifty',
|
||
'sixty', 'seventy', 'eighty', 'ninety', 'hundred', 'thousand', 'million',
|
||
'billion', 'trillion'
|
||
}#数词列表
|
||
CUSTOM_STOPWORDS = {
|
||
"year", "years", "month", "months", "day", "days",
|
||
"whose", "who", "what", "when", "where", "why", "how",
|
||
}#停用词列表
|
||
# 过滤逻辑函数
|
||
def should_include_term(term):#过滤不需要的单词
|
||
term_lower = term.lower()#把单词都转化成小写
|
||
if term_lower in ENGLISH_STOPWORDS or term_lower in CUSTOM_STOPWORDS:#检查这些单词是否在英文停用词列表里
|
||
return False
|
||
if NUMBER_REGEX.match(term) or term_lower in ENGLISH_NUMBERS:#检查这些单词是否在数词列表
|
||
return False
|
||
if len(term) <= 2:#小于等于两个字母的排除
|
||
return False
|
||
return True
|
||
#定义加载文档函数
|
||
def load_documents(folder_path):
|
||
documents = {}#初始化字典存储每个文件的单词列表
|
||
for root, dirs, files in os.walk(folder_path):#遍历指定文件夹及其子文件夹中的所有文件，os.walk(folder_path) 是 Python 内置的文件夹遍历函数
|
||
#每次循环返回一个元组 (root, dirs, files)
|
||
#dirs：当前 root 文件夹下的所有子文件夹名称（列表类型）
|
||
for file in files:
|
||
if file.endswith(('.txt', '.csv', '.json')):
|
||
file_path = os.path.join(root, file)## 拼接文件夹路径和文件名，得到文件的绝对路径
|
||
try:
|
||
with open(file_path, 'r', encoding='utf-8') as f:
|
||
lines = f.readlines()
|
||
words = []#将处理后的单词添加到 words 列表中
|
||
for line_num, line in enumerate(lines, start=1):
|
||
line_words = preprocess_text(line)#调用函数进行预处理
|
||
for word in line_words:
|
||
words.append(word)
|
||
documents[file] = words#将处理后的单词列表存储到字典中
|
||
except Exception as e:
|
||
print(f"读取{file_path}错误: {e}")#如果读取文件时出现错误，打印错误信息
|
||
return documents
|
||
|
||
# 文本预处理函数
|
||
def preprocess_text(text):
|
||
text = text.lower()
|
||
words = re.findall(r'\w+', text)#使用正则表达式 \w+ 提取文本中的所有单词，存储在 words 列表中
|
||
return [word for word in words if should_include_term(word)]#判断每个单词是否应该被包含，返回过滤后的单词列表
|
||
#计算相似度矩阵函数
|
||
def compute_similarity_matrix(documents):#用于计算文本相似度矩阵
|
||
term_vectors = {file: Counter(words) for file, words in documents.items()}#计算每个文件的词频向量。
|
||
similarity_matrix = defaultdict(dict)#初始化相似度矩阵
|
||
filenames = list(documents.keys())#获取所有文件名
|
||
for i, file1 in enumerate(filenames):#双重循环遍历所有文件对
|
||
for j, file2 in enumerate(filenames):
|
||
if i == j:
|
||
similarity_matrix[file1][file2] = 1.0#如果是同一个文件，相似度为 1.0
|
||
else:
|
||
similarity_matrix[file1][file2] = cosine_similarity(term_vectors[file1], term_vectors[file2])#调用 cosine_similarity 函数计算两个文件的余弦相似度
|
||
return similarity_matrix, term_vectors#返回相似度和词频
|
||
|
||
#余弦相似度计算
|
||
def cosine_similarity(vec1, vec2):
|
||
intersection = set(vec1.keys()) & set(vec2.keys())#计算两个向量的交集
|
||
numerator = sum(vec1[x] * vec2[x] for x in intersection)#计算分子
|
||
sum1 = sum(v ** 2 for v in vec1.values())#计算两个向量的模
|
||
sum2 = sum(v ** 2 for v in vec2.values())
|
||
denominator = math.sqrt(sum1) * math.sqrt(sum2)#计算分母
|
||
return numerator / denominator if denominator else 0.0#如果分母不为零，则返回余弦相似度；否则返回 0.0
|
||
#共同词汇查询函数
|
||
def get_common_terms(vec1, vec2):
|
||
return set(vec1.keys()) & set(vec2.keys())#计算两个向量的交集，共同词汇
|
||
# TOP10高频词获取函数
|
||
def get_top10_words(words):
|
||
counter = Counter(words)#全部计数
|
||
return [word for word, _ in counter.most_common(10)]#返回前十
|
||
#TOP10查重矩阵
|
||
def compute_top10_similarity(documents):
|
||
"""计算基于TOP10高频词的相似度矩阵"""
|
||
top10_words_dict = {file: get_top10_words(words) for file, words in documents.items()}#计算每个文件的 TOP10 高频词
|
||
similarity_matrix = defaultdict(dict)#初始化相似度矩阵
|
||
filenames = list(documents.keys())#获取所有文件名
|
||
for i, file1 in enumerate(filenames):
|
||
for j, file2 in enumerate(filenames):
|
||
if i == j:
|
||
similarity_matrix[file1][file2] = 1.0
|
||
else:
|
||
# 计算两个文件TOP10高频词的交集比例
|
||
common_words = set(top10_words_dict[file1]) & set(top10_words_dict[file2])
|
||
similarity_matrix[file1][file2] = len(common_words) / 10.0#计算相似度
|
||
return similarity_matrix, top10_words_dict
|
||
#窗口GUI设计
|
||
class TextSimilarityAnalyzer:
|
||
def __init__(self, root):
|
||
self.root = root#保存主窗口对象
|
||
self.root.title("文本相似度分析工具")#设置窗口标题
|
||
self.root.geometry("1000x800")#尺寸
|
||
self.root.resizable(True, True)#允许窗口调整大小
|
||
self.default_font = font.nametofont("TkDefaultFont")
|
||
self.default_font.configure(family="SimHei", size=10)
|
||
self.root.option_add("*Font", self.default_font)
|
||
|
||
# 初始化所有实例变量（修复外部定义错误）
|
||
self.documents = {}
|
||
self.similarity_matrix = {}
|
||
self.term_vectors = {}
|
||
self.filenames = []
|
||
self.word_positions = {}
|
||
self.top10_similarity_matrix = {}
|
||
self.top10_words_dict = {}
|
||
|
||
# 界面控件变量（统一在__init__中定义）
|
||
self.folder_path_var = tk.StringVar() # 修复实例特性在外部定义的错误
|
||
self.base_file_var = tk.StringVar() # 修复实例特性在外部定义的错误
|
||
self.file1_var = tk.StringVar()
|
||
self.file2_var = tk.StringVar()
|
||
|
||
self.create_widgets()
|
||
|
||
def create_widgets(self):
|
||
main_frame = ttk.Frame(self.root, padding="10")
|
||
main_frame.pack(fill=tk.BOTH, expand=True)
|
||
|
||
# 顶部文件选择区
|
||
top_frame = ttk.LabelFrame(main_frame, text="文件选择", padding="10")
|
||
top_frame.pack(fill=tk.X, pady=(0, 10))
|
||
ttk.Label(top_frame, text="文件夹路径:").grid(row=0, column=0, padx=5, pady=5, sticky=tk.W)
|
||
ttk.Entry(top_frame, textvariable=self.folder_path_var, width=60).grid(row=0, column=1, padx=5, pady=5)
|
||
ttk.Button(top_frame, text="浏览...", command=self.browse_folder).grid(row=0, column=2, padx=5, pady=5)
|
||
ttk.Button(top_frame, text="分析", command=self.analyze_files, style='Accent.TButton').grid(row=0, column=3,
|
||
padx=5, pady=5)
|
||
ttk.Button(top_frame, text="查看热力图", command=self.show_heatmap, style='Accent.TButton').grid(row=0,
|
||
column=4,
|
||
padx=5, pady=5)
|
||
|
||
# TOP10高频词查重功能UI
|
||
top10_frame = ttk.LabelFrame(main_frame, text="TOP10高频词预查重", padding="10")
|
||
top10_frame.pack(fill=tk.X, pady=(0, 10))
|
||
ttk.Label(top10_frame, text="选择基准文件:").grid(row=0, column=0, padx=5, pady=5, sticky=tk.W)
|
||
self.base_file_combo = ttk.Combobox(top10_frame, textvariable=self.base_file_var, state="disabled", width=40)
|
||
self.base_file_combo.grid(row=0, column=1, padx=5, pady=5)
|
||
ttk.Button(top10_frame, text="查看TOP10高频词", command=self.show_top10_words, style='Accent.TButton').grid(
|
||
row=0, column=2, padx=5, pady=5)
|
||
ttk.Button(top10_frame, text="生成预查重报告", command=self.show_top10_similarity, style='Accent.TButton').grid(
|
||
row=0,
|
||
column=3,
|
||
padx=5,
|
||
pady=5)
|
||
|
||
# 中间相似度矩阵区
|
||
middle_frame = ttk.LabelFrame(main_frame, text="相似度矩阵", padding="10")
|
||
middle_frame.pack(fill=tk.BOTH, expand=True, pady=(0, 10))
|
||
columns = ["File"]
|
||
self.similarity_tree = ttk.Treeview(middle_frame, columns=columns, show="headings")
|
||
self.similarity_tree.heading("File", text="文件")
|
||
self.similarity_tree.column("File", width=150, anchor=tk.CENTER)
|
||
tree_scroll_y = ttk.Scrollbar(middle_frame, orient=tk.VERTICAL, command=self.similarity_tree.yview)
|
||
tree_scroll_x = ttk.Scrollbar(middle_frame, orient=tk.HORIZONTAL, command=self.similarity_tree.xview)
|
||
self.similarity_tree.configure(yscrollcommand=tree_scroll_y.set, xscrollcommand=tree_scroll_x.set)
|
||
tree_scroll_y.pack(side=tk.RIGHT, fill=tk.Y)
|
||
tree_scroll_x.pack(side=tk.BOTTOM, fill=tk.X)
|
||
self.similarity_tree.pack(fill=tk.BOTH, expand=True)
|
||
|
||
# 底部公共词汇查询区
|
||
bottom_frame = ttk.LabelFrame(main_frame, text="公共词汇查询", padding="10")
|
||
bottom_frame.pack(fill=tk.X, pady=(0, 10))
|
||
ttk.Label(bottom_frame, text="选择两个文件:").grid(row=0, column=0, padx=5, pady=5, sticky=tk.W)
|
||
self.file1_combo = ttk.Combobox(bottom_frame, textvariable=self.file1_var, state="disabled", width=30)
|
||
self.file1_combo.grid(row=0, column=1, padx=5, pady=5)
|
||
ttk.Label(bottom_frame, text="和").grid(row=0, column=2, padx=5, pady=5)
|
||
self.file2_combo = ttk.Combobox(bottom_frame, textvariable=self.file2_var, state="disabled", width=30)
|
||
self.file2_combo.grid(row=0, column=3, padx=5, pady=5)
|
||
ttk.Button(bottom_frame, text="查询公共词汇", command=self.query_common_terms, style='Accent.TButton').grid(
|
||
row=0, column=4, padx=5, pady=5)
|
||
ttk.Button(bottom_frame, text="查看词云", command=self.show_wordcloud, style='Accent.TButton').grid(row=0,
|
||
column=5,
|
||
padx=5,
|
||
pady=5)
|
||
|
||
# 结果显示区
|
||
result_frame = ttk.LabelFrame(main_frame, text="公共词汇结果", padding="10")
|
||
result_frame.pack(fill=tk.BOTH, expand=True)
|
||
self.result_text = scrolledtext.ScrolledText(result_frame, wrap=tk.WORD, height=6, font=('SimHei', 14))
|
||
self.result_text.pack(fill=tk.BOTH, expand=True)
|
||
|
||
# 样式设置
|
||
style = ttk.Style()
|
||
style.configure('Accent.TButton', font=('SimHei', 10, 'bold'))
|
||
style.configure('Treeview', rowheight=25, font=('SimHei', 14), background='white', borderwidth=1)
|
||
style.configure('Treeview.Heading', font=('SimHei', 14, 'bold'), borderwidth=1)
|
||
style.layout('Treeview', [('Treeview.treearea', {'sticky': 'nswe'})])
|
||
|
||
def browse_folder(self):
|
||
folder_path = filedialog.askdirectory()#打开文件夹选择对话框
|
||
if folder_path:
|
||
self.folder_path_var.set(folder_path)#将选择的文件夹路径设置到 folder_path_var 中
|
||
|
||
def analyze_files(self):
|
||
folder_path = self.folder_path_var.get()#获取选择的文件夹路径
|
||
if not folder_path or not os.path.isdir(folder_path):#检查文件夹路径是否有效
|
||
messagebox.showerror("错误", "请选择有效的文件夹路径")
|
||
return
|
||
for item in self.similarity_tree.get_children():#清空相似度矩阵树形视图
|
||
self.similarity_tree.delete(item)
|
||
self.documents= load_documents(folder_path)#加载指定文件夹中的文本文件
|
||
if not self.documents:#检查是否找到文本文件
|
||
messagebox.showerror("错误", "未找到文本文件")
|
||
return
|
||
|
||
# 计算文本相似度矩阵
|
||
self.similarity_matrix, self.term_vectors = compute_similarity_matrix(self.documents)
|
||
|
||
# 计算TOP10高频词相似度矩阵
|
||
self.top10_similarity_matrix, self.top10_words_dict = compute_top10_similarity(self.documents)
|
||
|
||
self.filenames = sorted(list(self.documents.keys()),
|
||
key=lambda s: [int(t) if t.isdigit() else t.lower() for t in re.split(r'(\d+)', s)])
|
||
columns = ["File"] + self.filenames
|
||
self.similarity_tree.configure(columns=columns)#设置相似度矩阵树形视图的列
|
||
for col in self.filenames:
|
||
self.similarity_tree.heading(col, text=col)
|
||
self.similarity_tree.column(col, width=100, anchor=tk.CENTER)
|
||
for file1 in self.filenames:
|
||
values = [file1] + [f"{self.similarity_matrix[file1][file2]:.4f}" for file2 in self.filenames]
|
||
self.similarity_tree.insert("", tk.END, values=values)#将相似度矩阵插入到树形视图中
|
||
self.file1_combo['values'] = self.filenames#设置下拉框的选项
|
||
self.file2_combo['values'] = self.filenames
|
||
self.file1_combo['state'] = 'readonly'
|
||
self.file2_combo['state'] = 'readonly'#设置下拉框为只读模式
|
||
|
||
# 设置TOP10高频词下拉菜单
|
||
self.base_file_combo['values'] = self.filenames#设置 TOP10 高频词下拉菜单的选项和状态
|
||
self.base_file_combo['state'] = 'readonly'
|
||
if self.filenames:
|
||
self.file1_var.set(self.filenames[0])
|
||
self.file2_var.set(self.filenames[1])
|
||
self.base_file_var.set(self.filenames[0])
|
||
|
||
messagebox.showinfo("成功", f"分析完成，共处理 {len(self.filenames)} 个文件")
|
||
|
||
def query_common_terms(self):
|
||
file1, file2 = self.file1_var.get(), self.file2_var.get()
|
||
if not file1 or not file2 or file1 == file2:
|
||
messagebox.showerror("错误", "请选择不同的两个文件")
|
||
return
|
||
if file1 not in self.term_vectors or file2 not in self.term_vectors:
|
||
messagebox.showerror("错误", "文件未分析")
|
||
return
|
||
common_terms = get_common_terms(self.term_vectors[file1], self.term_vectors[file2])
|
||
filtered = [term for term in common_terms if should_include_term(term)]
|
||
self.result_text.delete(1.0, tk.END)
|
||
if not filtered:
|
||
self.result_text.insert(tk.END, f"{file1} 和 {file2} 无公共词汇")
|
||
return
|
||
self.result_text.insert(tk.END, f"{file1} 和 {file2} 的公共词汇 ({len(filtered)} 个):\n\n")
|
||
grouped = defaultdict(list)
|
||
for term in sorted(filtered):
|
||
clean = term.strip('"\'')
|
||
grouped[clean[0].upper() if clean else '#'].append(clean)
|
||
for initial in sorted(grouped.keys()):
|
||
terms = grouped[initial]
|
||
for i in range(0, len(terms), 10):
|
||
self.result_text.insert(tk.END, f"{initial}: {' '.join(terms[i:i + 10])}\n")#每行显示十个
|
||
|
||
def show_wordcloud(self):
|
||
"""生成类似图片的紧凑词云（公共词汇）"""
|
||
file1, file2 = self.file1_var.get(), self.file2_var.get()
|
||
if not file1 or not file2 or file1 == file2:
|
||
messagebox.showerror("错误", "请选择不同的两个文件")
|
||
return
|
||
if file1 not in self.term_vectors or file2 not in self.term_vectors:
|
||
messagebox.showerror("错误", "文件未分析")
|
||
return
|
||
# 获取过滤后的公共词汇及词频
|
||
common_terms = get_common_terms(self.term_vectors[file1], self.term_vectors[file2])
|
||
filtered_terms = [term for term in common_terms if should_include_term(term)]
|
||
if not filtered_terms:
|
||
messagebox.showinfo("提示", "无符合条件的公共词汇")
|
||
return
|
||
word_freq = {term: min(self.term_vectors[file1][term], self.term_vectors[file2][term]) for term in
|
||
filtered_terms}
|
||
# 使用 pyecharts 生成词云
|
||
words = [(word, freq) for word, freq in word_freq.items()]
|
||
(
|
||
WordCloud()
|
||
.add("", words, word_size_range=[20, 100])
|
||
.set_global_opts(
|
||
title_opts=opts.TitleOpts(title=f"{file1} 与 {file2} 的公共词汇词云"),
|
||
tooltip_opts=opts.TooltipOpts(is_show=True)
|
||
)
|
||
.render("wordcloud_interactive.html")
|
||
)
|
||
webbrowser.open_new_tab("wordcloud_interactive.html")
|
||
|
||
def show_heatmap(self):#self 同样用于访问实例的属性和调用其他实例方法
|
||
if not self.similarity_matrix:
|
||
messagebox.showerror("错误", "请先分析文件")
|
||
return
|
||
matrix_size = len(self.filenames)
|
||
heatmap_matrix = np.zeros((matrix_size, matrix_size))
|
||
for i, file1 in enumerate(self.filenames):
|
||
for j, file2 in enumerate(self.filenames):
|
||
heatmap_matrix[i, j] = self.similarity_matrix[file1][file2]
|
||
fig, ax = plt.subplots(figsize=(14, 10))
|
||
cmap = LinearSegmentedColormap.from_list("custom_cmap", ["blue", "white", "red"])
|
||
im = ax.imshow(heatmap_matrix, cmap=cmap)
|
||
ax.set_xticks(np.arange(matrix_size))
|
||
ax.set_yticks(np.arange(matrix_size))
|
||
ax.set_xticklabels(self.filenames, rotation=45, ha="right", fontsize=10)
|
||
ax.set_yticklabels(self.filenames, fontsize=10)
|
||
for i in range(matrix_size):
|
||
for j in range(matrix_size):
|
||
ax.text(j, i, f"{heatmap_matrix[i, j]:.0%}", ha="center", va="center",
|
||
color="black" if heatmap_matrix[i, j] < 0.5 else "white", fontsize=16)
|
||
cbar = ax.figure.colorbar(im, ax=ax)
|
||
cbar.ax.set_ylabel("相似度", rotation=-90, va="bottom", fontsize=12)
|
||
ax.set_title("文本相似度热力图", fontsize=16)
|
||
plt.tight_layout()
|
||
plt.show()
|
||
|
||
# TOP10高频词相关功能
|
||
def show_top10_words(self):
|
||
file = self.base_file_var.get()
|
||
if not file or file not in self.documents:
|
||
messagebox.showerror("错误", "请选择有效的文件")
|
||
return
|
||
# 严格过滤后重新统计词频
|
||
filtered_words = [word for word in self.documents[file] if should_include_term(word)]
|
||
word_counts = Counter(filtered_words)
|
||
top10 = word_counts.most_common(10)
|
||
words = [w for w, _ in top10]
|
||
counts = [c for _, c in top10]
|
||
# 优化图表大小和布局
|
||
plt.figure(figsize=(14, 8))
|
||
# 根据词频设置颜色
|
||
colors = []
|
||
for count in counts:
|
||
if count >= 15:
|
||
colors.append('#FF4136') # 红：词频>=15
|
||
elif count >= 10:
|
||
colors.append('#FFDC00') # 黄：10<=词频<15
|
||
else:
|
||
colors.append('#0074D9') # 蓝：词频<10
|
||
bars = plt.bar(words, counts, color=colors)
|
||
# 添加网格线增强可读性
|
||
plt.grid(axis='y', linestyle='--', alpha=0.7)
|
||
# 调整x轴标签旋转角度和字体大小
|
||
plt.xticks(rotation=30, ha='right', fontsize=14)
|
||
# 优化数值标注位置和样式
|
||
for bar, count in zip(bars, counts):
|
||
height = bar.get_height()
|
||
plt.text(
|
||
bar.get_x() + bar.get_width() / 2,
|
||
height + max(0.02 * max(counts), 0.3), # 自适应位置
|
||
f'{count}',
|
||
ha='center',
|
||
va='bottom',
|
||
fontsize=14,
|
||
fontweight='bold',
|
||
color='darkslategrey'
|
||
)
|
||
|
||
# 添加颜色图例说明
|
||
from matplotlib.patches import Patch
|
||
legend_elements = [
|
||
Patch(facecolor='#FF4136', label='词频 ≥ 15'),
|
||
Patch(facecolor='#FFDC00', label='10 ≤ 词频 < 15'),
|
||
Patch(facecolor='#0074D9', label='词频 < 10')
|
||
]
|
||
plt.legend(handles=legend_elements, fontsize=12)
|
||
|
||
# 设置更清晰的标题和标签
|
||
plt.ylabel('词频', fontsize=16)
|
||
plt.title(f'{file} 的TOP10高频词（过滤后）', fontsize=20, pad=15)
|
||
|
||
# 调整布局并显示
|
||
plt.tight_layout()
|
||
plt.show()
|
||
|
||
def show_top10_similarity(self):
|
||
"""生成优化后的基于TOP10高频词的可视化查重报告"""
|
||
file = self.base_file_var.get()
|
||
if not file or file not in self.top10_words_dict:
|
||
messagebox.showerror("错误", "请选择有效的文件")
|
||
return
|
||
|
||
# 获取相似度数据并过滤
|
||
similarities = self.top10_similarity_matrix[file]
|
||
sorted_files = sorted(similarities.items(), key=lambda x: x[1], reverse=True)
|
||
valid_files = [item for item in sorted_files if item[0] != file and item[1] > 0]
|
||
excluded_count = len(similarities) - 1 - len(valid_files) # 计算排除的文件数（减去自身）
|
||
|
||
# 创建临时HTML文件（修复temp_file_path作用域错误）
|
||
temp_file_path = None
|
||
with tempfile.NamedTemporaryFile(mode='w', suffix='.html', delete=False, encoding='utf-8') as f:
|
||
html_content = f"""
|
||
<!DOCTYPE html>
|
||
<html lang="zh-CN">
|
||
<head>
|
||
<meta charset="UTF-8">
|
||
<meta name="viewport" content="width=device-width, initial-scale=1.0">
|
||
<title>{file} 基于TOP10高频词的预查重报告</title>
|
||
<style>
|
||
:root {{
|
||
--primary: #2c3e50;
|
||
--secondary: #3498db;
|
||
--highlight: #e74c3c;
|
||
--medium: #f39c12;
|
||
--low: #2ecc71;
|
||
--light-bg: #f8f9fa;
|
||
--border: #dee2e6;
|
||
--base-font-size: 18px; /* 基础字体大小，统一调整 */
|
||
--heading-font-weight: 700; /* 标题字体加粗 */
|
||
--text-font-weight: 400; /* 正文字体粗细 */
|
||
}}
|
||
body {{
|
||
font-family: "SimHei", "Microsoft YaHei", sans-serif;
|
||
margin: 0;
|
||
padding: 20px;
|
||
color: var(--primary);
|
||
background-color: #f5f7fa;
|
||
font-size: var(--base-font-size); /* 应用基础字体大小 */
|
||
}}
|
||
.container {{
|
||
max-width: 1200px;
|
||
margin: 0 auto;
|
||
background: white;
|
||
padding: 30px;
|
||
border-radius: 10px;
|
||
box-shadow: 0 2px 15px rgba(0,0,0,0.1);
|
||
}}
|
||
h1 {{
|
||
color: var(--primary);
|
||
text-align: center;
|
||
margin-bottom: 30px;
|
||
padding-bottom: 15px;
|
||
border-bottom: 2px solid var(--secondary);
|
||
font-size: 28px; /* 加大标题字体 */
|
||
font-weight: var(--heading-font-weight);
|
||
}}
|
||
.report-section {{
|
||
margin-bottom: 35px;
|
||
padding: 20px;
|
||
background-color: var(--light-bg);
|
||
border-radius: 8px;
|
||
}}
|
||
.report-section h2 {{
|
||
color: var(--secondary);
|
||
margin-top: 0;
|
||
padding-bottom: 10px;
|
||
border-bottom: 1px dashed var(--border);
|
||
font-size: 22px; /* 加大二级标题字体 */
|
||
font-weight: var(--heading-font-weight);
|
||
}}
|
||
.top10-words {{
|
||
display: flex;
|
||
flex-wrap: wrap;
|
||
gap: 12px;
|
||
margin-top: 15px;
|
||
}}
|
||
.word-item {{
|
||
background-color: white;
|
||
border: 2px solid var(--secondary);
|
||
padding: 8px 15px;
|
||
border-radius: 20px;
|
||
font-weight: var(--heading-font-weight); /* 高频词标签加粗 */
|
||
display: inline-flex;
|
||
align-items: center;
|
||
box-shadow: 0 2px 5px rgba(0,0,0,0.05);
|
||
font-size: 18px; /* 高频词标签字体大小 */
|
||
}}
|
||
.word-item::before {{
|
||
content: attr(data-index);
|
||
background: var(--secondary);
|
||
color: white;
|
||
width: 24px; /* 加大圆形背景 */
|
||
height: 24px;
|
||
border-radius: 50%;
|
||
display: inline-block;
|
||
text-align: center;
|
||
font-size: 15px; /* 编号字体大小 */
|
||
margin-right: 8px;
|
||
line-height: 24px; /* 垂直居中 */
|
||
}}
|
||
.similarity-table {{
|
||
width: 100%;
|
||
border-collapse: collapse;
|
||
margin-top: 15px;
|
||
overflow: hidden;
|
||
border-radius: 8px;
|
||
box-shadow: 0 2px 8px rgba(0,0,0,0.08);
|
||
}}
|
||
.similarity-table th {{
|
||
background-color: var(--primary);
|
||
color: white;
|
||
text-align: center;
|
||
padding: 12px 10px;
|
||
font-weight: var(--heading-font-weight);
|
||
font-size: 20px; /* 表头字体大小 */
|
||
}}
|
||
.similarity-table td {{
|
||
border: 1px solid var(--border);
|
||
padding: 12px 10px;
|
||
text-align: center;
|
||
font-size: 18px; /* 表格内容字体大小 */
|
||
font-weight: var(--text-font-weight);
|
||
}}
|
||
.similarity-table tr:nth-child(even) {{
|
||
background-color: #f9f9f9;
|
||
}}
|
||
.similarity-table tr:hover {{
|
||
background-color: #f1f7ff;
|
||
}}
|
||
.progress-bar {{
|
||
height: 24px;
|
||
background-color: #e9ecef;
|
||
border-radius: 12px;
|
||
overflow: hidden;
|
||
position: relative;
|
||
box-shadow: inset 0 1px 3px rgba(0,0,0,0.1);
|
||
}}
|
||
.progress {{
|
||
height: 100%;
|
||
transition: width 0.5s ease;
|
||
}}
|
||
.high {{ background-color: var(--highlight); }}
|
||
.medium {{ background-color: var(--medium); }}
|
||
.low {{ background-color: var(--low); }}
|
||
.common-words {{
|
||
font-size: 16px; /* 共同高频词字体大小，稍小于基础 */
|
||
color: #495057;
|
||
word-break: break-all;
|
||
font-weight: var(--text-font-weight);
|
||
}}
|
||
.conclusion {{
|
||
background-color: white;
|
||
border-left: 4px solid var(--secondary);
|
||
padding: 15px 20px;
|
||
margin-top: 15px;
|
||
border-radius: 0 5px 5px 0;
|
||
line-height: 1.6;
|
||
font-size: 18px; /* 结论字体大小 */
|
||
font-weight: var(--text-font-weight);
|
||
}}
|
||
.stats {{
|
||
font-weight: var(--heading-font-weight);
|
||
color: var(--highlight);
|
||
}}
|
||
</style>
|
||
</head>
|
||
<body>
|
||
<div class="container">
|
||
<h1>{file} 的TOP10高频词预查重报告</h1>
|
||
<div class="report-section">
|
||
<h2>基准文件TOP10高频词</h2>
|
||
<div class="top10-words">
|
||
"""
|
||
# 生成带编号的高频词标签
|
||
base_top10 = self.top10_words_dict[file]
|
||
for i, word in enumerate(base_top10, 1):
|
||
html_content += f"""
|
||
<div class="word-item" data-index="{i}">
|
||
{word}
|
||
</div>
|
||
"""
|
||
html_content += f"""
|
||
</div>
|
||
</div>
|
||
<div class="report-section">
|
||
<h2>与其他文件的相似度比较</h2>
|
||
<table class="similarity-table">
|
||
<tr>
|
||
<th>文件名称</th>
|
||
<th>相似度</th>
|
||
<th>相似度直观展示</th>
|
||
<th>共同高频词</th>
|
||
</tr>
|
||
"""
|
||
# 生成带颜色分级的相似度表格
|
||
for other_file, sim in valid_files:
|
||
common_words = list(set(self.top10_words_dict[file]) & set(self.top10_words_dict[other_file]))
|
||
common_words_str = ", ".join(common_words)
|
||
|
||
# 根据相似度设置进度条颜色
|
||
if sim >= 0.7:
|
||
progress_class = "high"
|
||
elif sim >= 0.3:
|
||
progress_class = "medium"
|
||
else:
|
||
progress_class = "low"
|
||
|
||
html_content += f"""
|
||
<tr>
|
||
<td>{other_file}</td>
|
||
<td>{sim:.2%}</td>
|
||
<td>
|
||
<div class="progress-bar">
|
||
<div class="progress {progress_class}" style="width: {sim * 100}%"></div>
|
||
</div>
|
||
</td>
|
||
<td class="common-words">{common_words_str}</td>
|
||
</tr>
|
||
"""
|
||
html_content += f"""
|
||
</table>
|
||
</div>
|
||
<div class="report-section">
|
||
<h2>查重结论与建议</h2>
|
||
<div class="conclusion">
|
||
<p>本次预查重针对基准文件 <strong>{file}</strong> 完成以下分析：</p>
|
||
<ul>
|
||
<li>共检测到 {len(similarities) - 1} 个对比文件，其中 <span class="stats">{excluded_count} 个文件与基准文件重复度为0</span>，已排除无需后续查重</li>
|
||
<li>剩余 {len(valid_files)} 个文件中：
|
||
<ul>
|
||
<li>高相似度文件（≥70%）：{sum(1 for f, s in valid_files if s >= 0.7)} 个，建议重点核查</li>
|
||
<li>中等相似度文件（30%-70%）：{sum(1 for f, s in valid_files if 0.3 <= s < 0.7)} 个，建议适当关注</li>
|
||
<li>低相似度文件（<30%）：{sum(1 for f, s in valid_files if s < 0.3)} 个，相关性较低</li>
|
||
</ul>
|
||
</li>
|
||
<li>共同高频词分析显示：{base_top10[0]}、{base_top10[1]} 等核心词汇在多个文件中出现频率较高，可作为重点比对特征词</li>
|
||
</ul>
|
||
</div>
|
||
</div>
|
||
</div>
|
||
</body>
|
||
</html>
|
||
"""
|
||
f.write(html_content)
|
||
temp_file_path = f.name # 在with块内正确赋值
|
||
# 修复作用域问题：确保在方法内部使用变量
|
||
if temp_file_path:
|
||
webbrowser.open_new_tab(temp_file_path)
|
||
if __name__ == "__main__":
|
||
root = tk.Tk()#创建主窗口对象
|
||
app = TextSimilarityAnalyzer(root)#创建文本相似度分析器对象
|
||
root.mainloop()#进入主事件循环，等待用户交互 |