如何在Python中找到字符串中的中文或日文字符？

Question

如:

str = 'sdf344asfasf????3?sdfsdf'

添加()到中文和日文字符:

strAfterConvert = 'sdfasfasf(????)3(?)sdfsdf'

Answer 1

首先,您可以检查该字符是否位于以下unicode块之一:

• Unicode Block'CJK Unified Ideographs' - U + 4E00到U + 9FFF
• Unicode Block'CJK Unified Ideographs Extension A' - U + 3400到U + 4DBF
• Unicode Block'CJK Unified Ideographs Extension B' - U + 20000到U + 2A6DF
• Unicode Block'CJK Unified Ideographs Extension C' - U + 2A700到U + 2B73F
• Unicode Block'CJK Unified Ideographs Extension D' - U + 2B740到U + 2B81F

之后,您需要做的就是遍历字符串,检查字符是中文,日文还是韩文(CJK)并相应地追加:

# -*- coding:utf-8 -*-
ranges = [
  {"from": ord(u"\u3300"), "to": ord(u"\u33ff")},         # compatibility ideographs
  {"from": ord(u"\ufe30"), "to": ord(u"\ufe4f")},         # compatibility ideographs
  {"from": ord(u"\uf900"), "to": ord(u"\ufaff")},         # compatibility ideographs
  {"from": ord(u"\U0002F800"), "to": ord(u"\U0002fa1f")}, # compatibility ideographs
  {'from': ord(u'\u3040'), 'to': ord(u'\u309f')},         # Japanese Hiragana
  {"from": ord(u"\u30a0"), "to": ord(u"\u30ff")},         # Japanese Katakana
  {"from": ord(u"\u2e80"), "to": ord(u"\u2eff")},         # cjk radicals supplement
  {"from": ord(u"\u4e00"), "to": ord(u"\u9fff")},
  {"from": ord(u"\u3400"), "to": ord(u"\u4dbf")},
  {"from": ord(u"\U00020000"), "to": ord(u"\U0002a6df")},
  {"from": ord(u"\U0002a700"), "to": ord(u"\U0002b73f")},
  {"from": ord(u"\U0002b740"), "to": ord(u"\U0002b81f")},
  {"from": ord(u"\U0002b820"), "to": ord(u"\U0002ceaf")}  # included as of Unicode 8.0
]

def is_cjk(char):
  return any([range["from"] <= ord(char) <= range["to"] for range in ranges])

def cjk_substrings(string):
  i = 0
  while i<len(string):
    if is_cjk(string[i]):
      start = i
      while is_cjk(string[i]): i += 1
      yield string[start:i]
    i += 1

string = "sdf344asfasf????3?sdfsdf".decode("utf-8")
for sub in cjk_substrings(string):
  string = string.replace(sub, "(" + sub + ")")
print string

以上打印

sdf344asfasf(????)3(?)sdfsdf

为了面向未来,您可能需要留意CJK Unified Ideographs Extension E.它将附带Unicode 8.0,计划于2015年6月发布.我已将它添加到范围中,但在发布Unicode 8.0之前不应包含它.

[编辑]

增加了CJK兼容性表意文字,日本假名和CJK激进派.

Answer 2

您可以使用regex包进行编辑,该包支持检查每个字符的Unicode" Script "属性,并且是re包的替代品:

import regex as re

pattern = re.compile(r'([\p{IsHan}\p{IsBopo}\p{IsHira}\p{IsKatakana}]+)', re.UNICODE)

input = u'sdf344asfasf????3?sdfsdf'
output = pattern.sub(r'(\1)', input)
print output  # Prints: sdf344asfasf(????)3(?)sdfsdf

您应该\p{Is...}使用您认为是"中文或日文"的字符脚本/块来调整序列.

Answer 3

来自Moses机器翻译工具包启发的前沿之一NLTK：

def is_cjk(character):
    """"
    Checks whether character is CJK.

        >>> is_cjk(u'\u33fe')
        True
        >>> is_cjk(u'\uFE5F')
        False

    :param character: The character that needs to be checked.
    :type character: char
    :return: bool
    """
    return any([start <= ord(character) <= end for start, end in 
                [(4352, 4607), (11904, 42191), (43072, 43135), (44032, 55215), 
                 (63744, 64255), (65072, 65103), (65381, 65500), 
                 (131072, 196607)]
                ])

有关ord()数字的详细信息：

class CJKChars(object):
    """
    An object that enumerates the code points of the CJK characters as listed on
    http://en.wikipedia.org/wiki/Basic_Multilingual_Plane#Basic_Multilingual_Plane

    This is a Python port of the CJK code point enumerations of Moses tokenizer:
    https://github.com/moses-smt/mosesdecoder/blob/master/scripts/tokenizer/detokenizer.perl#L309
    """
    # Hangul Jamo (1100–11FF)
    Hangul_Jamo = (4352, 4607) # (ord(u"\u1100"), ord(u"\u11ff"))

    # CJK Radicals Supplement (2E80–2EFF)
    # Kangxi Radicals (2F00–2FDF)
    # Ideographic Description Characters (2FF0–2FFF)
    # CJK Symbols and Punctuation (3000–303F)
    # Hiragana (3040–309F)
    # Katakana (30A0–30FF)
    # Bopomofo (3100–312F)
    # Hangul Compatibility Jamo (3130–318F)
    # Kanbun (3190–319F)
    # Bopomofo Extended (31A0–31BF)
    # CJK Strokes (31C0–31EF)
    # Katakana Phonetic Extensions (31F0–31FF)
    # Enclosed CJK Letters and Months (3200–32FF)
    # CJK Compatibility (3300–33FF)
    # CJK Unified Ideographs Extension A (3400–4DBF)
    # Yijing Hexagram Symbols (4DC0–4DFF)
    # CJK Unified Ideographs (4E00–9FFF)
    # Yi Syllables (A000–A48F)
    # Yi Radicals (A490–A4CF)
    CJK_Radicals = (11904, 42191) # (ord(u"\u2e80"), ord(u"\ua4cf"))

    # Phags-pa (A840–A87F)
    Phags_Pa = (43072, 43135) # (ord(u"\ua840"), ord(u"\ua87f"))

    # Hangul Syllables (AC00–D7AF)
    Hangul_Syllables = (44032, 55215) # (ord(u"\uAC00"), ord(u"\uD7AF"))

    # CJK Compatibility Ideographs (F900–FAFF)
    CJK_Compatibility_Ideographs = (63744, 64255) # (ord(u"\uF900"), ord(u"\uFAFF"))

    # CJK Compatibility Forms (FE30–FE4F)
    CJK_Compatibility_Forms = (65072, 65103) # (ord(u"\uFE30"), ord(u"\uFE4F"))

    # Range U+FF65–FFDC encodes halfwidth forms, of Katakana and Hangul characters
    Katakana_Hangul_Halfwidth = (65381, 65500) # (ord(u"\uFF65"), ord(u"\uFFDC"))

    # Supplementary Ideographic Plane 20000–2FFFF
    Supplementary_Ideographic_Plane = (131072, 196607) # (ord(u"\U00020000"), ord(u"\U0002FFFF"))

    ranges = [Hangul_Jamo, CJK_Radicals, Phags_Pa, Hangul_Syllables, 
              CJK_Compatibility_Ideographs, CJK_Compatibility_Forms, 
              Katakana_Hangul_Halfwidth, Supplementary_Ideographic_Plane]

结合is_cjk()这个答案和@EvenLisle子字符串答案

>>> from nltk.tokenize.util import is_cjk
>>> text = u'sdf344asfasf????3?sdfsdf'
>>> [1 if is_cjk(ch) else 0 for ch in text]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 0, 1, 0, 0, 0, 0, 0, 0]
>>> def cjk_substrings(string):
...     i = 0
...     while i<len(string):
...         if is_cjk(string[i]):
...             start = i
...             while is_cjk(string[i]): i += 1
...             yield string[start:i]
...         i += 1
... 
>>> string = "sdf344asfasf????3?sdfsdf".decode("utf-8")
>>> for sub in cjk_substrings(string):
...     string = string.replace(sub, "(" + sub + ")")
... 
>>> string
u'sdf344asfasf(\u5929\u5730\u65b9\u76ca)3(\u6a29)sdfsdf'
>>> print string
sdf344asfasf(????)3(?)sdfsdf

Answer 4

如果您无法使用提供对属性regex的访问的模块，如@\xe4\xb8\x80\xe4\xba\x8c\xe4\xb8\x89\ 的答案所示；您可以使用@EvenLisle\'s 答案中的字符范围和 stdlib\'sIsKatakanaIsHanre模块一起使用：

\n\n

>>> import re\n>>> print(re.sub(u"([\\u3300-\\u33ff\\ufe30-\\ufe4f\\uf900-\\ufaff\\U0002f800-\\U0002fa1f\\u30a0-\\u30ff\\u2e80-\\u2eff\\u4e00-\\u9fff\\u3400-\\u4dbf\\U00020000-\\U0002a6df\\U0002a700-\\U0002b73f\\U0002b740-\\U0002b81f\\U0002b820-\\U0002ceaf]+)", r"(\\1)", u\'sdf344asfasf\xe5\xa4\xa9\xe5\x9c\xb0\xe6\x96\xb9\xe7\x9b\x8a3\xe6\xa8\xa9sdfsdf\'))\nsdf344asfasf(\xe5\xa4\xa9\xe5\x9c\xb0\xe6\x96\xb9\xe7\x9b\x8a)3(\xe6\xa8\xa9)sdfsdf\n

\n\n

注意已知问题。

\n\n

您还可以检查 Unicode 类别：

\n\n

>>> import unicodedata\n>>> unicodedata.category(u\'\xe5\xa4\xa9\')\n\'Lo\'\n>>> unicodedata.category(u\'s\')\n\'Ll\'\n

\n