"""Chinese search language: includes routine to split words."""

from __future__ import annotations

import re
from pathlib import Path
from typing import TYPE_CHECKING

import snowballstemmer

from sphinx.search import SearchLanguage

if TYPE_CHECKING:
    from collections.abc import Iterator

try:
    import jieba  # type: ignore[import-not-found]
    from jieba import cut_for_search
    from jieba import load_userdict as jieba_load_userdict
except ImportError:
    JIEBA_DEFAULT_DICT = ''

    def jieba_load_userdict(f: str) -> None:
        pass

    def cut_for_search(sentence: str, HMM: bool = True) -> Iterator[str]:
        yield from ()

else:
    JIEBA_DEFAULT_DICT = (
        Path(jieba.__file__, '..', jieba.DEFAULT_DICT_NAME).resolve().as_posix()
    )
    del jieba

english_stopwords = {
    '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',
}  # fmt: skip

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_]+')

    def __init__(self, options: dict[str, str]) -> None:
        super().__init__(options)
        self.latin_terms: set[str] = set()

    def init(self, options: dict[str, str]) -> None:
        dict_path = options.get('dict', JIEBA_DEFAULT_DICT)
        if dict_path and Path(dict_path).is_file():
            jieba_load_userdict(str(dict_path))

        self.stemmer = snowballstemmer.stemmer('english')

    def split(self, input: str) -> list[str]:
        chinese: list[str] = list(cut_for_search(input))

        latin1 = [term.strip() for term in self.latin1_letters.findall(input)]
        self.latin_terms.update(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
        stemmed = self.stemmer.stemWord(word.lower())
        should_not_be_stemmed = (
            len(word) >= 3 > len(stemmed) and word in self.latin_terms
        )
        if should_not_be_stemmed:
            return word.lower()
        return stemmed