Merge branch 'dev'

pull/9/head
zj3D 8 months ago
commit 4e95560355

@ -1,56 +0,0 @@
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
for word, freq in word_frequencies.most_common(10):
print(f"{word}: {freq}")

@ -0,0 +1,60 @@
# -*- 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
for word, freq in word_frequencies.most_common(10):
print(f"{word}: {freq}")

@ -0,0 +1,33 @@
# -*- coding: utf-8 -*-
import cppy.cp_util as util
# 每一列是一个数据元素和一个公式,第一列是输入数据,所以没有公式
all_words = [(), None]
non_stop_words = [(), util.extract_str_words]
frequencies = [(), util.get_frequencies]
sorted_data = [(), util.sort_dict]
# 整个电子表格
all_columns = [all_words, non_stop_words,\
frequencies, sorted_data]
# 每次输入数据后调用此方法
def update():
global all_columns
for c in all_columns[1::]:
if c[1] == util.extract_str_words:
c[0] = c[1](all_words[0])
elif c[1] == util.get_frequencies:
c[0] = c[1](non_stop_words[0])
elif c[1] == util.sort_dict:
c[0] = c[1](frequencies[0])
# 将固定数据加载到第一列中
all_words[0] = util.read_file(util.testfilepath)
# 调用update函数遍历列表
update()
#打印结果
util.print_word_freqs(sorted_data[0])
Loading…
Cancel
Save