a

�abx�@s�dZd
dl
Z
d
dlZd
dlmZmZ
d
dlmZ
d
dlm	Z	
zd
dl
Z
dZWneyb


dZYn0e
d���
Zd	ZGd
d�de�ZdS)z�
    sphinx.search.zh
    ~~~~~~~~~~~~~~~~

    Chinese search language: includes routine to split words.

    :copyright: Copyright 2007-2022 by the Sphinx team, see AUTHORS.
    :license: BSD, see LICENSE for details.
�N)�Dict�List)
�SearchLanguage)
�get_stemmerTFz�
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
a
/**
 * 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;
  }
}
c@s�eZ
dZUd
ZdZdZeZeZ	e
�d�
ZgZ
eeed<edd�dd	�Zeeed
�dd�Zeed
�dd�Zeed�dd�ZdS)�
SearchChinesez'
    Chinese search implementation
    �zhZChinesez
[a-zA-Z0-9_]+�latin_termsN)�options�returncCs4tr(|
�
d
�
}|r(tj�|�
r(t�|�

t�|_dS)N�dict)	�JIEBA�get�os�path�isfile�jiebaZ
load_userdictr�stemmer)�selfr	Z	dict_path�r�4/usr/lib/python3.9/site-packages/sphinx/search/zh.py�init�s






zSearchChinese.init)�inputr
cCs@g}trt
t�|
�
�
}d
d�|j�|
�
D�
}|j�|�

||S)Nc
Ssg|]}
|
���qSr)
�strip)�.0Ztermrrr�
<listcomp>��z'SearchChinese.split.<locals>.<listcomp>)r�listrZcut_for_search�latin1_letters�findallr�extend)rr�chinese�latin1rrr�split�s


�
zSearchChinese.split)�stemmed_wordr
cCst|
�
d
kS)N�
)
�len)rr#rrr�word_filter�s
zSearchChinese.word_filter)�wordr
cCsJ|
|jvo,t
|
�
d
ko,t
|j�|
���
�
d
k}|r:|
��S|j�|
���
S)N�)rr%r�stem�lower)rr'Zshould_not_be_stemmedrrrr)
s


��

zSearchChinese.stem)�__name__�
__module__�__qualname__�__doc__�langZ
language_name�js_porter_stemmerZjs_stemmer_code�english_stopwordsZ	stopwords�re�compilerrr�str�__annotations__rrr"�boolr&r)rrrrr�s








r)r.rr2�typingrrZ
sphinx.searchrZsphinx.util.stemmerrrr�ImportError�setr"r1r0rrrrr�<module>
s








<