forked from p46318075/CodePattern
You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
59 lines
1.8 KiB
59 lines
1.8 KiB
8 months ago
|
# -*- coding: utf-8 -*-
|
||
|
|
import cppy.cp_util as util
|
||
|
|
from collections import Counter
|
||
|
|
|
||
|
|
|
||
|
|
class WordFrequencyStateMachine:
|
||
|
|
def __init__(self, file_path):
|
||
|
|
self.file_path = file_path
|
||
|
|
self.content = None
|
||
|
|
self.words = None
|
||
|
|
self.word_freq = None
|
||
|
|
self.state = 'IDLE'
|
||
|
|
|
||
|
|
def transition_to_read_file(self):
|
||
|
|
try:
|
||
|
|
with open(self.file_path, 'r', encoding='utf-8') as file:
|
||
|
|
self.content = file.read()
|
||
|
|
self.state = 'WORDS_SPLIT'
|
||
|
|
except FileNotFoundError:
|
||
|
|
print(f"文件 {self.file_path} 未找到。")
|
||
|
|
except Exception as e:
|
||
|
|
print(f"读取文件时发生错误: {e}")
|
||
|
|
|
||
|
|
def transition_to_split_words(self):
|
||
|
|
if self.content is not None:
|
||
|
|
self.words = util.extract_str_words(self.content)
|
||
|
|
self.state = 'CALCULATE_FREQ'
|
||
|
|
else:
|
||
|
|
print("文件内容为空，无法分割单词。")
|
||
|
|
|
||
|
|
def transition_to_calculate_freq(self):
|
||
|
|
if self.words is not None:
|
||
|
|
self.word_freq = Counter(self.words)
|
||
|
|
self.state = 'DONE'
|
||
|
|
else:
|
||
|
|
print("单词列表为空，无法计算词频。")
|
||
|
|
|
||
|
|
def run(self):
|
||
|
|
while self.state != 'DONE':
|
||
|
|
if self.state == 'IDLE':
|
||
|
|
self.transition_to_read_file()
|
||
|
|
elif self.state == 'WORDS_SPLIT':
|
||
|
|
self.transition_to_split_words()
|
||
|
|
elif self.state == 'CALCULATE_FREQ':
|
||
|
|
self.transition_to_calculate_freq()
|
||
|
|
else:
|
||
|
|
print(f"未知状态: {self.state}")
|
||
|
|
break
|
||
|
|
|
||
|
|
return self.word_freq
|
||
|
|
|
||
|
|
# 使用状态机计算词频
|
||
|
|
|
||
|
|
|
||
|
|
state_machine = WordFrequencyStateMachine(util.testfilepath)
|
||
|
|
word_frequencies = state_machine.run()
|
||
|
|
|
||
|
|
# 打印结果
|
||
|
9 months ago
|
util.print_word_freqs(word_frequencies.most_common(10))
|