# 编译环境：Pycharm2018、Python3.7# 项目名称：词频统计——基本功能（结对编程）# 作者: 1613072050：马钰#         1613072051：朱佳豪#         1613072052:申可佳

lines = len(open(dst, 'r').readlines())

def process_buffer(dst, phrase_words, regex):words = open(dst, 'r', encoding="gb2312").read()  # 文本读取bvffer = words.lower()  # 将文本内容都改为小写# 将文本中的缩写都替换bvffer = bvffer.replace('’t', '')bvffer = bvffer.replace('’m', '')bvffer = bvffer.replace('’s', '')bvffer = bvffer.replace('’ve', '')for i in range(len(phrase_words)):  # 将文本中的“停词”删除掉bvffer = bvffer.replace(' ' + phrase_words[i] + ' ', ' ')result = re.findall(regex, bvffer)  # 正则查找词组word_freq = {}for word in result:  # 将正则匹配的结果进行统计word_freq[word] = word_freq.get(word, 0) + 1return word_freq

def input_result(dst, lines, words, items):  # 写入文件with open(dst, 'w') as w:w.write(lines)w.write(words)for item in items:  # 格式化item = '<' + str(item[0]) + '>:' + str(item[1]) + '\n'w.write(item)print('写入result文件已完成！')w.close()

def process_buffer(bvffer, dst):txt_words = open(dst, 'r', encoding="iso-8859-1").readlines()  # 读取停词表文件stop_words = []  # 存放停词表的listfor i in range(len(txt_words)):txt_words[i] = txt_words[i].replace('\n', '')# 写入list要将换行符取代stop_words.append(txt_words[i])if bvffer:word_freq = {}  # 下面添加处理缓冲区 bvffer代码，统计每个单词的频率，存放在字典word_freqbvffer = bvffer.lower()  # 将文本内容都改为小写for ch in '“‘!;,.?’”':  # 除去文本中的中英文标点符号bvffer = bvffer.replace(ch, " ")words = bvffer.strip().split()# strip()删除空白符（包括'/n', '/r','/t'）；split()以空格分割字符串for word in words:if word in stop_words:  # 如果word在停词表里就跳过continueelse:word_freq[word] = word_freq.get(word, 0) + 1return word_freq

def create_stop_words(dst):  # 创建停词表txt_words = open(dst, encoding='gb2312').readlines()  # 文本读取phrase_words = []  # 存放停词表的listfor i in range(len(txt_words)):txt_words[i] = txt_words[i].replace('\n', '')# 因为读取文本是readlines所以写入list要将换行符取代phrase_words.append(txt_words[i])return phrase_wordsdef process_buffer(dst, phrase_words, regex):words = open(dst, 'r', encoding="iso-8859-1").read()  # 文本读取bvffer = words.lower()  # 将文本内容都改为小写# 将文本中的缩写都替换（进过程序发现以下是最常见的）bvffer = bvffer.replace('’t', '')bvffer = bvffer.replace('’m', '')bvffer = bvffer.replace('’s', '')bvffer = bvffer.replace('’ve', '')# 其实上面的替换可以防在停词中但是涉及到空格等问题就放在前面直接替换了for i in range(len(phrase_words)):  # 将文本中的“停词”删除掉，这样会使结果很清晰更能接受bvffer = bvffer.replace(' ' + phrase_words[i] + ' ', ' ')result = re.findall(regex, bvffer)  # 正则查找词组word_freq = {}for word in result:  # 将正则匹配的结果进行统计word_freq[word] = word_freq.get(word, 0) + 1return word_freq