From 873cd8ac9b7c5f95e204c0e6e7bd2d50c6bebeee Mon Sep 17 00:00:00 2001 From: yongzhuo <31341349+yongzhuo@users.noreply.github.com> Date: Sun, 12 May 2019 09:49:24 +0800 Subject: [PATCH] Update text_tools.py --- utils/text_tools.py | 72 ++++++--------------------------------------- 1 file changed, 9 insertions(+), 63 deletions(-) diff --git a/utils/text_tools.py b/utils/text_tools.py index 8c13fac..8e3bc0a 100644 --- a/utils/text_tools.py +++ b/utils/text_tools.py @@ -131,69 +131,6 @@ def get_syboml(ques): answer = re.sub("[\.\!\/_,?;:$%^*<>()+\"\']+|[!,;:。?、“”’‘《》[\](|){}【】~@#¥%…&*\/\-—_]+", " ", ques).strip() return answer -'''xlrd读xls''' - -def xlsRead(sheetName=None, cols=0, fileXlsPath=None): - '''读xls文件''' - workbook = xlrd.open_workbook(fileXlsPath) - # 根据sheet索引或者名称获取sheet内容 - sheet = workbook.sheet_by_name(sheetName) - nrows = sheet.nrows - ncols = sheet.ncols - - listRows = [] - for i in range(nrows): - listRows.append(sheet.row_values(i)) - - return listRows - -'''openpyxl写xlsx''' - -def xlsxWrite(sheetName, writeList, fileXlsName): - wb = Workbook() - print('{}'.format(wb.get_sheet_names())) # 提供一个默认名叫Sheet的表,office2016下新建提供默认Sheet1 - sheet = wb.create_sheet(sheetName) - # i = 0 - for listLine_one in writeList: - # i += 1 - sheet.append(listLine_one) - # if i == 1000: - # break - wb.save(fileXlsName) - -'''读取txt文件''' - -def txtRead(filePath, encodeType='utf-8'): - listLine = [] - try: - file = open(filePath, 'r', encoding=encodeType) - - while True: - line = file.readline() - if not line: - break - - listLine.append(line) - - file.close() - - except Exception as e: - logger.info(str(e)) - - finally: - return listLine - -'''读取txt文件''' - -def txtWrite(listLine, filePath, type='w', encodeType='utf-8'): - - try: - file = open(filePath, type, encoding=encodeType) - file.writelines(listLine) - file.close() - - except Exception as e: - logger.info(str(e)) # -*- coding: cp936 -*- def strQ2B(ustring): @@ -320,6 +257,15 @@ def load_word2vec_model(model_path, binary_type=True, encoding_type = 'utf-8', l return word2vec_model +def text_preprocess(text): + if text.strip(): + text_simple_q2b = strQ2B(text) + text_simple_q2b_only = getChinese1(text_simple_q2b) + return text_simple_q2b_only.lower() + else: + return text + + #todo #句子改写,同义词替换,去停用词等