# -*- coding: utf-8 -*-
"""
Multi cut -- Thai word segmentation with maximum matching. The original source
code is from Korakot Chaovavanich.
:See Also:
* `Facebook post \
<https://www.facebook.com/groups/408004796247683/permalink/431283740586455/>`_
* `GitHub Gist \
<https://gist.github.com/korakot/fe26c65dc9eed467f4497f784a805716>`_
"""
import re
from collections import defaultdict
from typing import List
from pythainlp.tokenize import DEFAULT_WORD_DICT_TRIE
from pythainlp.util import Trie
class LatticeString(str):
"""
String subclass เพื่อเก็บวิธีตัดหลายๆ วิธี
"""
def __new__(cls, value, multi=None, in_dict=True):
return str.__new__(cls, value)
def __init__(self, value, multi=None, in_dict=True):
self.unique = True
if multi:
self.multi = list(multi)
if len(self.multi) > 1:
self.unique = False
else:
self.multi = [value]
self.in_dict = in_dict # บอกว่าเป็นคำมีในดิกหรือเปล่า
_RE_NONTHAI = r"""(?x)
[-a-zA-Z]+| # Latin
\d[\d,\.]*| # number
[ \t]+| # space
\r?\n # newline
"""
_PAT_NONTHAI = re.compile(_RE_NONTHAI)
def _multicut(text: str, custom_dict: Trie = DEFAULT_WORD_DICT_TRIE):
"""
ส่งคืน LatticeString คืนมาเป็นก้อนๆ
"""
if not custom_dict:
custom_dict = DEFAULT_WORD_DICT_TRIE
len_text = len(text)
words_at = defaultdict(list) # main data structure
def serialize(p, p2): # helper function
for w in words_at[p]:
p_ = p + len(w)
if p_ == p2:
yield w
elif p_ < p2:
for path in serialize(p_, p2):
yield w + "/" + path
q = {0}
last_p = 0 # last position for yield
while min(q) < len_text:
p = min(q)
q -= {p} # q.pop, but for set
for w in custom_dict.prefixes(text[p:]):
words_at[p].append(w)
q.add(p + len(w))
len_q = len(q)
if len_q == 1:
q0 = min(q)
yield LatticeString(text[last_p:q0], serialize(last_p, q0))
last_p = q0
elif len_q == 0: # len(q) == 0 means not found in dictionary
m = _PAT_NONTHAI.match(text[p:])
if m: # non-Thai toekn
i = p + m.span()[1]
else: # non-Thai token, find minimum skip
for i in range(p, len_text):
ww = custom_dict.prefixes(text[i:])
m = _PAT_NONTHAI.match(text[i:])
if ww or m:
break
else:
i = len_text
w = text[p:i]
words_at[p].append(w)
yield LatticeString(w, in_dict=False)
last_p = i
q.add(i)
def mmcut(text: str):
res = []
for w in _multicut(text):
mm = min(w.multi, key=lambda x: x.count("/"))
res.extend(mm.split("/"))
return res
def _combine(ww: str):
if ww == []:
yield ""
else:
w = ww[0]
for tail in _combine(ww[1:]):
if w.unique:
yield w + "|" + tail
else:
for m in w.multi:
yield m.replace("/", "|") + "|" + tail
[docs]def segment(
text: str, custom_dict: Trie = DEFAULT_WORD_DICT_TRIE
) -> List[str]:
"""
Dictionary-based maximum matching word segmentation.
:param str text: text to be tokenized to words
:param pythainlp.util.Trie custom_dict: dictionary for tokenization
:return: list of words, tokenized from the text
"""
if not text or not isinstance(text, str):
return []
return list(_multicut(text, custom_dict=custom_dict))
[docs]def find_all_segment(
text: str, custom_dict: Trie = DEFAULT_WORD_DICT_TRIE
) -> List[str]:
"""
Get all possible segment variations
:param str text: input string to be tokenized
:return: returns list of segment variations
"""
if not text or not isinstance(text, str):
return []
ww = list(_multicut(text, custom_dict=custom_dict))
return list(_combine(ww))