NLP文本处理小工具函数

1. 控制字符去除

import unicodedata
def remove_control_character(content):
    result = ""
    for ch in content:
        if ch not in ("\t", "\n", "\r") and unicodedata.category(ch) in ("Cc", "Cf"):
            continue
        #0xfffd主要是windows的一些字符编码在unicode中没有对应的，相当于[UNK]
        if ord(ch) in (0, 0xfffd):
            continue
        result += ch
    return result

2. 标点符号判断

def is_punctuation(char):
  cp = ord(char)
  if ((cp >= 33 and cp <= 47) or (cp >= 58 and cp <= 64) or
      (cp >= 91 and cp <= 96) or (cp >= 123 and cp <= 126)):
    return True
  cat = unicodedata.category(char)
  if cat.startswith("P"):
    return True
  return False

4. 全角转半角

def strQ2B(ustring):
    """全角转半角"""
    rstring = ""
    for uchar in ustring:
        inside_code=ord(uchar)
        if inside_code == 12288:                              #全角空格直接转换            
            inside_code = 32
        elif (inside_code >= 65281 and inside_code <= 65374): #全角字符（除空格）根据关系转化
            inside_code -= 65248

        rstring += chr(inside_code)
    return rstring

6. 空白字符格式化，空白用’# '代替，多个连续空白算一个

def format_white_space(content):
    result = ""
    last = 1
    content = list(content)
    for index in range(len(content)):
        ch = content[index]
        if ch in ("\n", "\t", "\r") or unicodedata.category(ch) in ("Zs", "Zp", "Zl"):
            if last == 0 and index > 0 and is_punctuation(content[index-1])==False:
                #可以换成其他字符串
                ch = "# "
            else:
                ch = ""
            last = 1
        else:
            last = 0
        result += ch
    return result

7. 文章/章节拆成句子，考虑括号的闭合

def chapter_to_sentences(chapter):
    sentences = []
    sentence = ""
    stop_ch = ["。", " ", "，", "？", "！","；","…", "?", "!"]
    last_ch = ""
    next_ch = ""
    left_brackets = ["{", "[", "【", "「", "(", "（", "“", "‘", "<"]
    right_brackets = ["}", "]", "】", "」", ")", "）", "”", "’", ">"]
    matcher = {"}":"{", "]":"[", "】":"【","」":"「",")":"(", "）":"（", "”":"“", "’":"‘", ">":"<"}
    brackets_vis = {}
    brackets_close = True
    #括号内内容的长度限制，防止括号本身没闭合的情况
    inline_content_max_length = 15
    inline_count = 0
    for index in range(len(chapter)):
        ch = chapter[index]
        if index < len(chapter) - 1:
            next_ch = chapter[index+1]
        sentence += ch
        inline_count += 1
        #.,可能是数字中间的分隔符
        if ch in stop_ch or (ch == ',' and (is_chinese(last_ch) or is_chinese(next_ch))) \
                or (ch=="." and is_number(last_ch)==False):
            if brackets_close == True or inline_count > inline_content_max_length:
                sentences.append(sentence)
                sentence = ""
                brackets_vis.clear()
                brackets_close = True
        if ch in left_brackets:
            brackets_vis[ch] = True
            brackets_close = False
            inline_count = 0
        elif ch in right_brackets:
            if matcher[ch] in brackets_vis:
                del brackets_vis[matcher[ch]]
                if len(brackets_vis) == 0:
                    brackets_close = True

        last_ch = ch
    if len(sentence) > 0:
        sentences.append(sentence)
    return sentences