Gecko [ fernandoquevedodop.com ]

Name	Size	Permission
__pycache__	[ DIR ]	drwxr-xr-x
__init__.py	17.22 KB	-rw-r--r--
da.py	3.6 KB	-rw-r--r--
de.py	4.65 KB	-rw-r--r--
en.py	4.9 KB	-rw-r--r--
es.py	5.71 KB	-rw-r--r--
fi.py	3.26 KB	-rw-r--r--
fr.py	3.48 KB	-rw-r--r--
hu.py	2.03 KB	-rw-r--r--
it.py	5.09 KB	-rw-r--r--
ja.py	30.55 KB	-rw-r--r--
jssplitter.py	6.31 KB	-rw-r--r--
nl.py	4.59 KB	-rw-r--r--
no.py	4.9 KB	-rw-r--r--
pt.py	4.66 KB	-rw-r--r--
ro.py	684 B	-rw-r--r--
ru.py	7.84 KB	-rw-r--r--
sv.py	3.48 KB	-rw-r--r--
tr.py	678 B	-rw-r--r--
zh.py	6.12 KB	-rw-r--r--

Code Editor : zh.py

"""
    sphinx.search.zh
    ~~~~~~~~~~~~~~~~

Chinese search language: includes routine to split words.

:copyright: Copyright 2007-2021 by the Sphinx team, see AUTHORS.
    :license: BSD, see LICENSE for details.
"""

import os
import re
from typing import Dict, List

from sphinx.search import SearchLanguage
from sphinx.util.stemmer import get_stemmer

try:
    import jieba
    JIEBA = True
except ImportError:
    JIEBA = False

english_stopwords = set("""
a  and  are  as  at
be  but  by
for
if  in  into  is  it
near  no  not
of  on  or
such
that  the  their  then  there  these  they  this  to
was  will  with
""".split())

js_porter_stemmer = """
/**
 * Porter Stemmer
 */
var Stemmer = function() {

var step2list = {
    ational: 'ate',
    tional: 'tion',
    enci: 'ence',
    anci: 'ance',
    izer: 'ize',
    bli: 'ble',
    alli: 'al',
    entli: 'ent',
    eli: 'e',
    ousli: 'ous',
    ization: 'ize',
    ation: 'ate',
    ator: 'ate',
    alism: 'al',
    iveness: 'ive',
    fulness: 'ful',
    ousness: 'ous',
    aliti: 'al',
    iviti: 'ive',
    biliti: 'ble',
    logi: 'log'
  };

var step3list = {
    icate: 'ic',
    ative: '',
    alize: 'al',
    iciti: 'ic',
    ical: 'ic',
    ful: '',
    ness: ''
  };

var c = "[^aeiou]";          // consonant
  var v = "[aeiouy]";          // vowel
  var C = c + "[^aeiouy]*";    // consonant sequence
  var V = v + "[aeiou]*";      // vowel sequence

var mgr0 = "^(" + C + ")?" + V + C;                      // [C]VC... is m>0
  var meq1 = "^(" + C + ")?" + V + C + "(" + V + ")?$";    // [C]VC[V] is m=1
  var mgr1 = "^(" + C + ")?" + V + C + V + C;              // [C]VCVC... is m>1
  var s_v   = "^(" + C + ")?" + v;                         // vowel in stem

this.stemWord = function (w) {
    var stem;
    var suffix;
    var firstch;
    var origword = w;

if (w.length < 3)
      return w;

var re;
    var re2;
    var re3;
    var re4;

firstch = w.substr(0,1);
    if (firstch == "y")
      w = firstch.toUpperCase() + w.substr(1);

// Step 1a
    re = /^(.+?)(ss|i)es$/;
    re2 = /^(.+?)([^s])s$/;

if (re.test(w))
      w = w.replace(re,"$1$2");
    else if (re2.test(w))
      w = w.replace(re2,"$1$2");

// Step 1b
    re = /^(.+?)eed$/;
    re2 = /^(.+?)(ed|ing)$/;
    if (re.test(w)) {
      var fp = re.exec(w);
      re = new RegExp(mgr0);
      if (re.test(fp[1])) {
        re = /.$/;
        w = w.replace(re,"");
      }
    }
    else if (re2.test(w)) {
      var fp = re2.exec(w);
      stem = fp[1];
      re2 = new RegExp(s_v);
      if (re2.test(stem)) {
        w = stem;
        re2 = /(at|bl|iz)$/;
        re3 = new RegExp("([^aeiouylsz])\\\\1$");
        re4 = new RegExp("^" + C + v + "[^aeiouwxy]$");
        if (re2.test(w))
          w = w + "e";
        else if (re3.test(w)) {
          re = /.$/;
          w = w.replace(re,"");
        }
        else if (re4.test(w))
          w = w + "e";
      }
    }

// Step 1c
    re = /^(.+?)y$/;
    if (re.test(w)) {
      var fp = re.exec(w);
      stem = fp[1];
      re = new RegExp(s_v);
      if (re.test(stem))
        w = stem + "i";
    }

// Step 2
    re = /^(.+?)(ational|tional|enci|anci|izer|bli|alli|entli|eli|ousli|\
ization|ation|ator|alism|iveness|fulness|ousness|aliti|iviti|biliti|logi)$/;
    if (re.test(w)) {
      var fp = re.exec(w);
      stem = fp[1];
      suffix = fp[2];
      re = new RegExp(mgr0);
      if (re.test(stem))
        w = stem + step2list[suffix];
    }

// Step 3
    re = /^(.+?)(icate|ative|alize|iciti|ical|ful|ness)$/;
    if (re.test(w)) {
      var fp = re.exec(w);
      stem = fp[1];
      suffix = fp[2];
      re = new RegExp(mgr0);
      if (re.test(stem))
        w = stem + step3list[suffix];
    }

// Step 4
    re = /^(.+?)(al|ance|ence|er|ic|able|ible|ant|ement|ment|ent|ou|ism|ate|\
iti|ous|ive|ize)$/;
    re2 = /^(.+?)(s|t)(ion)$/;
    if (re.test(w)) {
      var fp = re.exec(w);
      stem = fp[1];
      re = new RegExp(mgr1);
      if (re.test(stem))
        w = stem;
    }
    else if (re2.test(w)) {
      var fp = re2.exec(w);
      stem = fp[1] + fp[2];
      re2 = new RegExp(mgr1);
      if (re2.test(stem))
        w = stem;
    }

// Step 5
    re = /^(.+?)e$/;
    if (re.test(w)) {
      var fp = re.exec(w);
      stem = fp[1];
      re = new RegExp(mgr1);
      re2 = new RegExp(meq1);
      re3 = new RegExp("^" + C + v + "[^aeiouwxy]$");
      if (re.test(stem) || (re2.test(stem) && !(re3.test(stem))))
        w = stem;
    }
    re = /ll$/;
    re2 = new RegExp(mgr1);
    if (re.test(w) && re2.test(w)) {
      re = /.$/;
      w = w.replace(re,"");
    }

// and turn initial Y back to y
    if (firstch == "y")
      w = firstch.toLowerCase() + w.substr(1);
    return w;
  }
}
"""

class SearchChinese(SearchLanguage):
    """
    Chinese search implementation
    """

lang = 'zh'
    language_name = 'Chinese'
    js_stemmer_code = js_porter_stemmer
    stopwords = english_stopwords
    latin1_letters = re.compile(r'[a-zA-Z0-9_]+')
    latin_terms: List[str] = []

def init(self, options: Dict) -> None:
        if JIEBA:
            dict_path = options.get('dict')
            if dict_path and os.path.isfile(dict_path):
                jieba.load_userdict(dict_path)

self.stemmer = get_stemmer()

def split(self, input: str) -> List[str]:
        chinese: List[str] = []
        if JIEBA:
            chinese = list(jieba.cut_for_search(input))

latin1 = \
            [term.strip() for term in self.latin1_letters.findall(input)]
        self.latin_terms.extend(latin1)
        return chinese + latin1

def word_filter(self, stemmed_word: str) -> bool:
        return len(stemmed_word) > 1

def stem(self, word: str) -> str:
        # Don't stem Latin words that are long enough to be relevant for search
        # if not stemmed, but would be too short after being stemmed
        # avoids some issues with acronyms
        should_not_be_stemmed = (
            word in self.latin_terms and
            len(word) >= 3 and
            len(self.stemmer.stem(word.lower())) < 3
        )
        if should_not_be_stemmed:
            return word.lower()
        return self.stemmer.stem(word.lower())

${this.title}

Code Editor : zh.py