42、多线程编程：实现与优化

多线程编程：实现与优化

1. 二级线程的实现

在多线程编程中，为了实现高效的页面索引，我们引入了二级线程。这里以 Walker 类为例，它继承自 QThread ，用于处理文件索引的工作。

class Walker(QThread):
    COMMON_WORDS_THRESHOLD = 250
    MIN_WORD_LEN = 3
    MAX_WORD_LEN = 25
    INVALID_FIRST_OR_LAST = frozenset("0123456789_")
    STRIPHTML_RE = re.compile(r"<[^>]*?>", re.IGNORECASE|re.MULTILINE)
    ENTITY_RE = re.compile(r"&(\w+?);|&#(\d+?);")
    SPLIT_RE = re.compile(r"\W+", re.IGNORECASE|re.MULTILINE)

    def __init__(self, lock, parent=None):
        super(Walker, self).__init__(parent)
        self.lock = lock
        self.stopped = False
        self.mutex = QMutex()
        self.path = None
        self.completed = False

    def initialize(self,