Tools/加密后软件工具/exe/文章对比查看/源代码/Compare1_latest.py

import datetime, shutil, os
import time
from sympy import *
import uuid
from sklearn.feature_extraction.text import CountVectorizer
import numpy as np
from win32com.client import Dispatch
from multiprocessing import Process, Lock, Manager
import multiprocessing
from pyDes import *
from PyQt5.QtWidgets import QApplication, QMainWindow, QFileDialog, QMessageBox, QDialog, QVBoxLayout,QLabel,QPushButton
from PyQt5 import QtCore
from PyQt5.QtCore import Qt
from MainForm import Ui_MainWindow
import encryption
import re

# def getMachineCode():
#     m_wmi = wmi.WMI()
#     cpu_info = m_wmi.Win32_Processor()
#     serial_number = 0
#     if len(cpu_info) > 0:
#         serial_number = cpu_info[0].ProcessorId
#     serial_number = serial_number.encode("utf-8")
#     machine_code = hashlib.md5(serial_number).hexdigest()
#     tm = time.localtime()
#     date = '%04d' % tm.tm_year + '%02d' % tm.tm_mon + '%02d' % tm.tm_mday
#     machine_code = machine_code + date
#     return machine_code
#
# def Encrypted(code):
#     # 使用DES-CBC加密算法加密机器码
#     Des_key = "fda34hfk"         # 自定义 Key
#     Des_IV = "\x11\2\x2a\3\1\x27\2\0"    # IV向量
#     k = des(Des_key, CBC, Des_IV, pad=None, padmode=PAD_PKCS5)
#     EncryptStr = k.encrypt(code)
#     return EncryptStr
#
# def Decrypted(code):
#     # 使用DES-CBC加密算法加密机器码
#     Des_key = "fda34hfk"         # 自定义 Key
#     Des_IV = "\x11\2\x2a\3\1\x27\2\0"    # IV向量
#     k = des(Des_key, CBC, Des_IV, pad=None, padmode=PAD_PKCS5)
#     DecryptStr = k.decrypt(code)
#     return DecryptStr
#
# def checkCode():
#     # 获取机器码
#     machine_code = getMachineCode()
#     # 自己定义 Encrypted 函数进行加密处理
#     encrypt_code = Encrypted(machine_code.encode("utf-8"))
#
#     # 读取本地的授权文件
#     if os.path.exists("C:/Users/{0}/AppData/Roaming/cpregister.bin".format(getpass.getuser())):
#         with open("C:/Users/{0}/AppData/Roaming/cpregister.bin".format(getpass.getuser()), "r") as f:
#             key_code = f.read()
#             decrypt_code = Decrypted(key_code)
#             cpucode = decrypt_code
#             # 如果机器码经过加密后的值，等于授权码的值，则验证通过，否则验证失败
#             if key_code == encrypt_code:
#                 return True
#             else:
#                 return False
#     else:
#         print('机器码：' + str(machine_code))
#         registercode = input('注册码：')
#         if registercode == encrypt_code:
#             with open("C:/Users/{0}/AppData/Roaming/cpregister.bin".format(getpass.getuser()), 'wb') as file:
#                 string_bytes = registercode.encode('utf-8')
#                 file.write(string_bytes)
#             print('验证成功！')
#         else:
#             print('注册码有误！')

def dataGet(s0):
    aa = 0
    datekey = {
        'ze':'0','im':'1','tw':'2','ee':'3','fr':'4','ve':'5',
        'ix':'6','se':'7','ei':'8','ni':'9'
    }
    ii = 0
    dastr = []
    while ii < 8:
        x1 = 2 * ii
        y1 = x1 + 2
        das = datekey[s0[x1:y1]]
        dastr.append(das)
        ii = ii + 1
    datestr = ''.join(dastr)
    mm = int(datestr[:2])
    dd = int(datestr[2:4])
    yy = int(datestr[4:])
    tm = time.localtime()
    dy = int(tm.tm_year)
    dm = int(tm.tm_mon)
    dday=int(tm.tm_mday)
    if dy < yy:
        aa = 1.7
    elif dy == yy:
        if dm < mm:
            aa = 1.7
        elif dm == mm:
            if dday <= dd:
                aa = 1.7
            else:
                aa = -3
        else:
            aa = -3
    else:
        aa = -3
    return aa
def macget(sy0,ma0):
    mackey = {
        'a':'10','b':'11','c':'12','d':'13','e':'14','f':'15'
    }
    aa = 0
    sy = list(sy0)
    ma = list(ma0)
    ii = 0
    node = uuid.getnode()
    MAC = uuid.UUID(int = node).hex[-12:]
    mac = MAC.lower()
    while ii < 4:
        try:
            syi = int(sy[ii])
            mai = ma[ii]
            maci = mac[syi]
            if maci == mai:
                aa = 0
            else:
                aa = -2
                break
        except:
            syi = int(mackey[sy[ii]])
            mai = ma[ii]
            maci = mac[syi]
            if maci == mai:
                aa = 0
            else:
                aa = -2
                break
        ii = ii + 1
    if aa == 0:
        aa = 1.7
    else:
        aa = -2
    return aa
def pdd(kk):
    n = Symbol('n')
    if kk > limit(((3*n*n - 5)/(2*n*n + n)),n,oo) and kk < (integrate(n**2,[n,0,1]) * 6):
    # ----------------这句才是程序运行代码----------------------------------
        return 0
    # ----------------这句才是程序运行代码----------------------------------
    elif kk == -1:
        aa = encryption.macget()
        bb = encryption.plusmac(aa)
        cc = encryption.ordermac(bb)
        # print('密钥：' + cc)
        dialog = CustomDialog()
        dialog.label_text('许可文件不存在！复制密钥交给管理员获取许可\n密钥：' + cc)
        dialog.exec_()
        return kk
        # arcpy.AddMessage ('The License File Does Not Exist!')
    elif kk == -2:
        # arcpy.AddMessage ('License Password Error!')
        return kk
    elif kk == -3:
        # arcpy.AddMessage('Out Of Permitted Time!')
        return kk
    else:
        # arcpy.AddMessage ('License File Corrupted!')
        return kk
def bsfGet(s0):
    aa = 0
    bsfkey = {
        'bd':'a','cd':'c','7a':'d','ae':'e','97':'g','6k':'h',
        '57':'i','22':'D','2c':'m','8m':'o','3w':'p','11':'I',
        '5d':'r','4u':'s','9t':'t','au':'u','23':'x','yk':'y',
        'za':'z','k4':'0','v6':'1','tw':'2','h0':'5','op':'7',
        'po':'8','wt':'9','8x':':','yy':',','lo':' ',
    }
    ii = 0
    lens0 = len(s0)
    bsfstr = []
    while ii < (lens0 / 2):
        x1 = 2 * ii
        y1 = x1 + 2
        bsf = bsfkey[s0[x1:y1]]
        bsfstr.append(bsf)
        ii = ii + 1
    bsstr = ''.join(bsfstr)
    return bsstr
def licen():
    aa = 0
    linsy = ''
    linma = ''
    s1 = 'aucd8x'
    s2 = '3w5d8m7aaucd9tlo11228x'
    s3 = 'cd573w6kae5d8x'
    # path = 'D:\\CMCtbxLisence\\tbxLisence.txt'
    # isExists=os.path.exists(path)
    # if not isExists:
    #     path1 = 'E:\\CMCtbxLisence\\tbxLisence.txt'
    #     isExists1=os.path.exists(path1)
    #     if not isExists1:
    #         path2 = 'F:\\CMCtbxLisence\\tbxLisence.txt'
    #         isExists2=os.path.exists(path2)
    #         if not isExists2:
    #             aa = -1
    #         else:
    #             outpath = 'F:\\CMCtbxLisence\\tbxLisence.txt'
    #     else:
    #         outpath = 'E:\\CMCtbxLisence\\tbxLisence.txt'
    # else:
    #     outpath = 'D:\\CMCtbxLisence\\tbxLisence.txt'
    outpath = os.path.expandvars("%APPDATA%") + '\\CMCexeLisence\\compaLisence.txt'
    isExists = os.path.exists(outpath)
    if not isExists:
        aa = -1
    if aa != -1:
        with open(outpath, 'r') as lines:
            for line in lines:
                t = bsfGet(s1)
                if re.search(bsfGet(s1),line):
                    try:
                        linrq1 = line.split(':',-1)[-1]
                        linrq = linrq1.replace('\n','')
                        aa = dataGet(linrq)
                        if aa == -3:
                            break
                    except:
                        aa = -9999
                if re.search(bsfGet(s2),line):
                    try:
                        linSY1 = line.split('-',-1)[-1]
                        linSY = linSY1.replace('\n','')
                        linsy = linSY.lower()
                    except:
                        aa = -9999
                if re.search(bsfGet(s3),line):
                    try:
                        linma1 = line.split('-',-1)[0]
                        linMA1 = linma1.split(':',-1)[-1]
                        linMA = linMA1.replace('\n','')
                        linma = linMA.lower()
                        aa = macget(linsy,linma)
                    except:
                        aa = -9999
    else:
        aa = -1
    return pdd(aa)

class MainWindow(QMainWindow, Ui_MainWindow):
    def __init__(self):
        super(MainWindow, self).__init__()
        self.setupUi(self)
        self.retranslateUi(self)
        self.initUI()
        self.set_window()  # 定制窗口
        self.miniButton.clicked.connect(self.window().showMinimized)
        self.setAttribute(QtCore.Qt.WA_TranslucentBackground)
        self.closeButton.clicked.connect(self.window().close)
        self.draggable = False
        self.offset = None

    def mousePressEvent(self, event):
        if event.button() == QtCore.Qt.LeftButton:
            self.draggable = True
            self.offset = event.pos()

    def mouseMoveEvent(self, event):
        if self.draggable:
            self.move(event.globalPos() - self.offset)

    def mouseReleaseEvent(self, event):
        if event.button() == QtCore.Qt.LeftButton:
            self.draggable = False

    def set_window(self):
       # 关闭系统标题栏
       self.setWindowFlag(QtCore.Qt.FramelessWindowHint)

    def initUI(self):
        self.setWindowTitle('文章对比查重')
        self.setFixedSize(self.width(), self.height())

        self.toolButton_5.clicked.connect(lambda: self.open_file_dialog(3))
        self.toolButton_4.clicked.connect(lambda: self.open_file_dialog(2))
        self.toolButton_3.clicked.connect(lambda: self.open_file_dialog(1))
        self.pushButton_2.clicked.connect(self.btn_ok)

    def open_file_dialog(self, flag):
        if flag == 1:
            file_name = QFileDialog.getExistingDirectory(self, '打开文件夹', 'C:/', QFileDialog.ShowDirsOnly)
            if file_name != '':
                self.lineEdit.setText(file_name)
                self.lineEdit.setFocus()
        if flag == 2:
            file_name = QFileDialog.getOpenFileName(self, '打开文件', '/path/to/dir', "Word文件 (*.doc *.docx)")
            if file_name != '':
                file_name, _ = file_name
                self.lineEdit_2.setText(file_name)
                self.lineEdit_2.setFocus()
        if flag == 3:
            file_name, _ = QFileDialog.getOpenFileName(self, '打开文件', '/path/to/dir', "Word文件 (*.doc *.docx)")
            if file_name:
                self.lineEdit.setText(os.path.dirname(file_name))
                self.lineEdit_3.setText(file_name)
                self.lineEdit_3.setFocus()

    def btn_ok(self):
        if self.lineEdit_3.text() == '':
            QMessageBox.warning(self, '消息', '待查文章文件不可为空！')
            return
        elif self.lineEdit_2.text() == '':
            QMessageBox.warning(self, '消息', '对比文章文件不可为空！')
            return
        elif self.lineEdit.text() == '':
            QMessageBox.warning(self, '消息', '结果输出文件夹不可为空！')
            return

        licencode = licen()
        if licencode == 0:
            try:
                inpath = self.lineEdit_3.text()
                dbpath = self.lineEdit_2.text()
                outpath = self.lineEdit.text()
                wordcompare(inpath, dbpath, outpath)
            except Exception as e:
                QMessageBox.critical(self, '错误', str(e))
                return
            QMessageBox.information(self, '消息', '对比完成')
        elif licencode == -2:
            # QMessageBox.warning(self, '警告', '许可密钥错误！')
            aa = encryption.macget()
            bb = encryption.plusmac(aa)
            cc = encryption.ordermac(bb)
            dialog = CustomDialog()
            dialog.label_text('许可密钥错误！复制密钥交给管理员获取许可\n密钥：' + cc)
            dialog.exec_()
        elif licencode == -3:
            # QMessageBox.warning(self, '警告', '超过许可时间！')
            aa = encryption.macget()
            bb = encryption.plusmac(aa)
            cc = encryption.ordermac(bb)
            dialog = CustomDialog()
            dialog.label_text('超过许可时间！复制密钥交给管理员获取许可\n密钥：' + cc)
            dialog.exec_()
        elif licencode != -1:
            # QMessageBox.warning(self, '警告', '许可文件损坏！')
            aa = encryption.macget()
            bb = encryption.plusmac(aa)
            cc = encryption.ordermac(bb)
            dialog = CustomDialog()
            dialog.label_text('许可文件损坏！复制密钥交给管理员获取许可\n密钥：' + cc)
            dialog.exec_()

# 提示窗口，显示密钥
class CustomDialog(QDialog):
    def __init__(self, parent=None):
        super().__init__(parent)

        # 设置对话框的标题
        self.setWindowTitle("提示")

        # 创建一个垂直布局
        layout = QVBoxLayout()

        # 创建一个QLabel来显示文本
        self.label = QLabel("这是一段可复制的文本内容。你可以尝试选择它并复制。")
        # 启用文本交互，允许用户选择文本
        self.label.setTextInteractionFlags(Qt.TextSelectableByMouse | Qt.TextSelectableByKeyboard)

        # 将QLabel添加到布局中
        layout.addWidget(self.label)

        # 创建一个按钮来关闭对话框
        self.close_button = QPushButton("关闭")
        # 将按钮的clicked信号连接到close槽函数来关闭对话框
        self.close_button.clicked.connect(self.close)

        # 将按钮添加到布局中
        layout.addWidget(self.close_button)

        # 设置对话框的布局
        self.setLayout(layout)

    def label_text(self, new_text):
        self.label.setText(new_text)


def getText(wordname,word):
    doc = word.Documents.Open(FileName=wordname, Encoding='gbk')
    texts = []
    wd = ''
    for para in doc.paragraphs:
        txt = para.Range.Text.strip().rstrip(chr(13)+'\x07')
        txt = txt.rstrip(chr(13) + '\n')
        txt = txt.rstrip(chr(13))
        txt = txt.rstrip('\x01')
        texts.append(txt)
        wd += txt
    doc.Close()
    return texts, wd


def is_Chinese(word):
    for ch in word:
        if '\u4e00' <= ch <= '\u9fff':
            return True
    return False


def msplit(s, seperators='\?|。|？|！'):
    return re.split(seperators, s)


def readDocx(docfile,word):
    print('*' * 80)
    print('文件', docfile, '加载中……')
    t1 = datetime.datetime.now()
    paras, wd = getText(docfile,word)
    segs = []
    for p in paras:
        temp = []
        for s in msplit(p):
            temp.append(s.replace(' ', ""))
            # temp += s.replace(' ', "")
        if len(temp) > 0:
            segs.append(temp)
    t2 = datetime.datetime.now()
    print('加载完成，用时: ', t2 - t1)
    showInfo(segs, docfile)
    return segs, wd

chars = 0
def showInfo(doc, filename='filename'):
    global chars
    segs = 0
    for p in doc:
        for s in p:
            segs = segs + 1
            chars = chars + len(s)
    print('段落数: {0:>8d} 个。'.format(len(doc)))
    print('短句数: {0:>8d} 句。'.format(segs))
    print('字符数: {0:>8d} 个。'.format(chars))


def jaccard_similarity(s1, s2):
    def add_space(s):
        return ' '.join(list(s))

    # 将字中间加入空格
    s1, s2 = add_space(s1), add_space(s2)
    # 转化为TF矩阵
    cv = CountVectorizer(tokenizer=lambda s: s.split())
    corpus = [s1, s2]

    # fit_transform() 方法可以将字符串转化为词频矩阵
    vectors = cv.fit_transform(corpus).toarray()

    # 求交集
    numerator = np.sum(np.min(vectors, axis=0))
    # 求并集
    denominator = np.sum(np.max(vectors, axis=0))
    # 计算杰卡德系数
    return 1.0 * numerator / denominator


def compareParagraph(doc1, i, doc2, j):
    p1 = doc1[i]
    p2 = doc2[j]
    flag = False
    repetion = [flag]
    cosine_sim = 0
    similarity = 0
    for s1 in p1:
        if len(s1) == 0 or s1.__contains__('\r'):
            continue
        for s2 in p2:
            if len(s2) == 0 or s2.__contains__('\r'):
                continue
            if len(s1) > 10:
                # # 使用TF-IDF向量化文本
                # vectorizer = TfidfVectorizer().fit_transform([s1, s2]).toarray()
                # # 计算余弦相似度
                # cosine_sim = cosine_similarity(vectorizer[0:1], vectorizer[1:2])[0][0]
                cosine_sim = jaccard_similarity(s1, s2)
                if cosine_sim > 0.5:
                    comment = '重复内容：{0}\n重复度：{1:.2f}%'.format(s2, cosine_sim * 100)
                    repetion[0] = True
                    temp = [flag, i, p1.index(s1), comment]
                    repetion.append(temp)
            elif len(s1) >= 2 and len(s1) <= 10:
                similarity = jaccard_similarity(s1, s2)
                if similarity > 0.5:
                    comment = '重复内容：{0}\n重复度：{1:.2f}%'.format(s2, similarity * 100)
                    repetion[0] = True
                    temp = [flag, i, p1.index(s1), comment]
                    repetion.append(temp)
    return repetion
    # if repetion[0] == False:
    #     return repetion


repetion_char = 0
mark_count = 0
def mark(docdb, marklist):
    global repetion_char
    global mark_count
    for i in range(len(marklist)):
        para_index = marklist[i][1]
        sentence_index = marklist[i][2]
        comment = marklist[i][3]
        para = docdb.paragraphs[para_index]
        if para.Range.Sentences.Count == 1:
            txt = para.Range.Text
        else:
            txt = para.Range.Sentences[sentence_index].Text

        txt = txt.strip().rstrip(chr(13) + '\n')
        txt = txt.rstrip(chr(13) + '\x07')
        txt = txt.rstrip(chr(13))
        txt = txt.rstrip('\x01')
        repetion_char += len(txt)
        if para.Range.Sentences.Count == 1:
            docdb.Comments.Add(
                Range=docdb.Range(Start=docdb.paragraphs[para_index].Range.Characters[0].Start,
                                End=docdb.paragraphs[para_index].Range.Characters[len(txt) - 1].End),
                Text=comment)
            mark_count = mark_count + 1
            print('已标记'+str(mark_count)+'处')
        else:
            docdb.Comments.Add(
                Range=docdb.Range(Start=docdb.paragraphs[para_index].Range.Sentences[sentence_index].Characters[0].Start,
                                End=docdb.paragraphs[para_index].Range.Sentences[sentence_index].Characters[
                                    len(txt) - 1].End),
                Text=comment)
            mark_count = mark_count + 1
            print('已标记' + str(mark_count) + '处')
        docdb.Save()


def compare(doc1, doc2, start, end, result):
    # word = Dispatch('Word.Application')
    # word.Visible = False
    # path = os.path.join(dst_dir, '对比.docx')
    # docdb = word.Documents.Open(FileName=path, Encoding='gbk')
    for i in range(start, end):
        for j in range(len(doc2)):
            rp = compareParagraph(doc1, i, doc2, j)
            if rp[0] == True:
                print(str(i))
                with Lock():
                    # 使用锁来同步写入结果，防止多进程写入冲突
                    for i in range(1, len(rp)):
                        result.append(rp[i])
                break


def wordcompare(src_file, db_file, dst_dir):
    shutil.copy(src_file, os.path.join(dst_dir, '对比结果' + os.path.splitext(src_file)[1]))

    word = Dispatch('Word.Application')
    word.Visible = 0
    doc1, wd1 = readDocx(src_file, word)
    charcount = chars
    doc2, wd2 = readDocx(db_file, word)
    word.Quit()

    # # 使用TF-IDF向量化文本
    # vectorizer = TfidfVectorizer().fit_transform([wd1, wd2]).toarray()
    # # 计算余弦相似度
    # cosine = cosine_similarity(vectorizer[0:1], vectorizer[1:2])[0][0]

    print('开始对比...'.center(80, '*'))
    t1 = datetime.datetime.now()
    index1 = [0, len(doc1) // 2]
    index2 = [len(doc1) // 2, len(doc1)]
    manager = Manager()
    result = manager.list()
    processes = []
    p1 = Process(target=compare, args=(doc1, doc2, index1[0], index1[1], result))
    p2 = Process(target=compare, args=(doc1, doc2, index2[0], index2[1], result))

    processes.append(p1)
    processes.append(p2)

    # 启动进程
    for p in processes:
        p.start()

    # 等待所有进程完成
    for p in processes:
        p.join()

    print('共有'+str(len(result))+'处相似')
    word1 = Dispatch('Word.Application')
    word1.Visible = 0
    path = os.path.join(dst_dir, '对比结果' + os.path.splitext(src_file)[1])
    docdb = word1.Documents.Open(FileName=path, Encoding='gbk')
    mark(docdb, result)

    cosine = repetion_char/charcount
    myRange = docdb.Range(0, 0)
    myRange.InsertBefore('整体相似度：' + '%.2f' % (cosine * 100) + '%\n')
    docdb.Save()
    docdb.Close()
    word1.Quit()
    t2 = datetime.datetime.now()
    print('\n对比完成，总用时: ', t2 - t1)


if __name__ == '__main__':
    multiprocessing.freeze_support()
    app = QApplication(sys.argv)
    myshow = MainWindow()
    myshow.show()
    sys.exit(app.exec_())
    # wordcompare('F://2024//07//文章对比查重//6月20日-甘孜抽水蓄能电站预可阶段测绘技术服务（中水、永鸿、田册）招标//甘孜抽水蓄能电站预可阶段'
    #             '测绘技术服务技术文件2024.6.18-测绘公司.docx',
    #             'F://2024//07//文章对比查重//6月20日-甘孜抽水蓄能电站预可阶段测绘技术服务（中水、永鸿、田册）招标//甘孜抽水蓄能电站预可阶段测绘技术服务-田册.docx',
    #             'F://2024//07//文章对比查重//')