关于python:我使用pangu模块做了一个文本格式化小工具

51次阅读

共计 5248 个字符,预计需要花费 14 分钟才能阅读完成。

其实应用 pangu 做文本格式标准化的业务代码在之前就实现了,次要可能将中文文本文档中的文字、标点符号等进行标准化。

浏览全文

然而为了不便起来咱们这里应用了 Qt5 将其做成了一个能够操作的页面利用,这样不相熟 python 的敌人就能够不必写代码间接双击运行应用就 OK 了。

为了使文本格式的丑化过程不影响主线程的应用,顺便采纳 QThread 子线程来专门的运行文本文档丑化的业务过程,接下来还是采纳 pip 的形式将所有须要的非标准模块装置一下。

pip install -i https://pypi.tuna.tsinghua.edu.cn/simple pangu

pip install -i https://pypi.tuna.tsinghua.edu.cn/simple PyQt5

将咱们应用到的 pyqt5 利用制作模块以及业务模块 pangu 导入到咱们的代码块中。

# It imports all the classes, attributes, and methods of the PyQt5.QtCore module into the global symbol table.
from PyQt5.QtCore import *

# It imports all the classes, attributes, and methods of the PyQt5.QtWidgets module into the global symbol table.
from PyQt5.QtWidgets import QApplication, QWidget, QHBoxLayout, QVBoxLayout, QTextBrowser, QLineEdit, QPushButton, \
    QFormLayout, QFileDialog

# It imports all the classes, attributes, and methods of the PyQt5.QtGui module into the global symbol table.
from PyQt5.QtGui import QIcon, QFont, QTextCursor

# It imports the pangu module.
import pangu

# It imports the sys module.
import sys

# It imports the os module.
import os

为了缩小 python 模块在打包时资源占用过多,打的 exe 应用程序的占用空间过大的状况,这次咱们只导入了可能应用到的相干 python 类,这个小细节大家留神一下。

上面创立一个名称为 PanGuUI 的 python 类来实现对整个利用页面的开发,将页面的布局以及组件相干的局部写到这个类中。并且给页面组件绑定好相应的槽函数从而实现页面的 ’ 点击 ’ 等性能。

# It creates a class called PanGuUI that inherits from QWidget.
class PanGuUI(QWidget):
    def __init__(self):
        """
        A constructor. It is called when an object is created from a class and it allows the class to initialize the
        attributes of a class.
        """
        super(PanGuUI, self).__init__()
        self.init_ui()

    def init_ui(self):
        """This function initializes the UI."""
        self.setWindowTitle('文本文档丑化器 公众号:Python 集中营')
        self.setWindowIcon(QIcon('txt.ico'))

        self.brower = QTextBrowser()
        self.brower.setFont(QFont('宋体', 8))
        self.brower.setReadOnly(True)
        self.brower.setPlaceholderText('解决过程展现区域...')
        self.brower.ensureCursorVisible()

        self.txt_file_path = QLineEdit()
        self.txt_file_path.setPlaceholderText('源文本文档门路')
        self.txt_file_path.setReadOnly(True)

        self.txt_file_path_btn = QPushButton()
        self.txt_file_path_btn.setText('导入')
        self.txt_file_path_btn.clicked.connect(self.txt_file_path_btn_click)

        self.new_txt_file_path = QLineEdit()
        self.new_txt_file_path.setPlaceholderText('新文本文档门路')
        self.new_txt_file_path.setReadOnly(True)

        self.new_txt_file_path_btn = QPushButton()
        self.new_txt_file_path_btn.setText('门路')
        self.new_txt_file_path_btn.clicked.connect(self.new_txt_file_path_btn_click)

        self.start_btn = QPushButton()
        self.start_btn.setText('开始导入')
        self.start_btn.clicked.connect(self.start_btn_click)

        hbox = QHBoxLayout()
        hbox.addWidget(self.brower)

        fbox = QFormLayout()
        fbox.addRow(self.txt_file_path, self.txt_file_path_btn)
        fbox.addRow(self.new_txt_file_path, self.new_txt_file_path_btn)

        v_vbox = QVBoxLayout()
        v_vbox.addWidget(self.start_btn)

        vbox = QVBoxLayout()
        vbox.addLayout(fbox)
        vbox.addLayout(v_vbox)

        hbox.addLayout(vbox)

        self.thread_ = PanGuThread(self)
        self.thread_.message.connect(self.show_message)
        self.thread_.finished.connect(self.finshed)

        self.setLayout(hbox)

    def show_message(self, text):
        """
        It shows a message

        :param text: The text to be displayed
        """
        cursor = self.brower.textCursor()
        cursor.movePosition(QTextCursor.End)
        self.brower.append(text)
        self.brower.setTextCursor(cursor)
        self.brower.ensureCursorVisible()

    def txt_file_path_btn_click(self):
        """It opens a file dialog box and allows the user to select a file."""
        txt_file = QFileDialog.getOpenFileName(self, os.getcwd(), '关上文本文档',
                                               'Text File(*.txt)')
        self.txt_file_path.setText(txt_file[0])

    def new_txt_file_path_btn_click(self):
        """This function opens a file dialog box and allows the user to select a file to save the output to."""
        new_txt_file = QFileDialog.getOpenFileName(self, os.getcwd(), '关上文本文档',
                                                   'Text File(*.txt)')
        self.new_txt_file_path.setText(new_txt_file[0])

    def start_btn_click(self):
        """A function that is called when the start button is clicked."""
        self.thread_.start()
        self.start_btn.setEnabled(False)

    def finshed(self, finished):
        """:param finished: A boolean value that is True if the download is finished, False otherwise"""
        if finished is True:
            self.start_btn.setEnabled(True)

创立名称为 PanGuThread 的子线程,将具体实现丑化格式化文本字符串的业务代码块写入到子线程中。子线程继承的是 QThread 的 PyQt5 的线程类,通过创立子线程并且将子线程的信号信息传递到主线程中,在主线程的文本浏览器中进行展现达到实时跟踪执行后果的成果。

# This class is a subclass of QThread, and it's used to split the text into words
class PanGuThread(QThread):
    message = pyqtSignal(str)
    finished = pyqtSignal(bool)

    def __init__(self, parent=None):
        """
        A constructor that initializes the class.

        :param parent: The parent widget
        """
        super(PanGuThread, self).__init__(parent)
        self.working = True
        self.parent = parent

    def __del__(self):
        """A destructor. It is called when the object is destroyed."""
        self.working = True
        self.wait()

    def run(self) -> None:
        """> This function runs the program"""
        try:

            txt_file_path = self.parent.txt_file_path.text().strip()
            self.message.emit('源文件门路信息读取失常!')
            new_txt_file_path = self.parent.new_txt_file_path.text().strip()
            self.message.emit('新文件门路信息读取失常!')
            list_ = []
            with open(txt_file_path, encoding='utf-8') as f:
                lines_ = f.readlines()
                self.message.emit('源文件内容读取实现!')
                n = 1
                for line_ in lines_:
                    text = pangu.spacing_text(line_)
                    self.message.emit('第 {0} 行文档内容格式化实现!'.format(n))
                    list_.append(text)
                    n = n + 1
                self.message.emit('源文件门路信息格式化实现!')

            self.message.emit('行将开始将格式化内容写入新文件!')
            with open(new_txt_file_path, 'a') as f:
                for line_ in list_:
                    f.write(line_ + '\n')
            self.message.emit('新文件内容写入实现!')
            self.finished.emit(True)

        except Exception as e:
            self.message.emit('文件内容读取或格式化产生异样!')


if __name__ == '__main__':
    app = QApplication(sys.argv)
    main = PanGuUI()
    main.show()
    sys.exit(app.exec_())

实现了开发开始测试一下成果如何,创立了两个文本文件 data.txt、new_data.txt,点击 ’ 开始运行 ’ 之后会调起整个的业务子线程实现文本格式化,后果完满运行来看一下执行过程展现。

【往期精彩】

pyqt5 利用的主题款式!

GUI 利用:socket 网络聊天室!

小王,给这 2000 个客户发一下节日祝愿的邮件 …

正文完
 0