/* ***** BEGIN LICENSE BLOCK *****

 * Version: MPL 1.1/GPL 2.0/LGPL 2.1

 *

 * Copyright (C) 2002-2022 Németh László

 *

 * The contents of this file are subject to the Mozilla Public License Version

 * 1.1 (the "License"); you may not use this file except in compliance with

 * the License. You may obtain a copy of the License at

 * http://www.mozilla.org/MPL/

 *

 * Software distributed under the License is distributed on an "AS IS" basis,

 * WITHOUT WARRANTY OF ANY KIND, either express or implied. See the License

 * for the specific language governing rights and limitations under the

 * License.

 *

 * Hunspell is based on MySpell which is Copyright (C) 2002 Kevin Hendricks.

 *

 * Contributor(s): David Einstein, Davide Prina, Giuseppe Modugno,

 * Gianluca Turconi, Simon Brouwer, Noll János, Bíró Árpád,

 * Goldman Eleonóra, Sarlós Tamás, Bencsáth Boldizsár, Halácsy Péter,

 * Dvornik László, Gefferth András, Nagy Viktor, Varga Dániel, Chris Halls,

 * Rene Engelhard, Bram Moolenaar, Dafydd Jones, Harri Pitkänen

 *

 * Alternatively, the contents of this file may be used under the terms of

 * either the GNU General Public License Version 2 or later (the "GPL"), or

 * the GNU Lesser General Public License Version 2.1 or later (the "LGPL"),

 * in which case the provisions of the GPL or the LGPL are applicable instead

 * of those above. If you wish to allow use of your version of this file only

 * under the terms of either the GPL or the LGPL, and not to allow others to

 * use your version of this file under the terms of the MPL, indicate your

 * decision by deleting the provisions above and replace them with the notice

 * and other provisions required by the GPL or the LGPL. If you do not delete

 * the provisions above, a recipient may use your version of this file under

 * the terms of any one of the MPL, the GPL or the LGPL.

 *

 * ***** END LICENSE BLOCK ***** */

#include <cstdlib>

#include <cstring>

#include <cstdio>

#include <ctype.h>

#include "../hunspell/csutil.hxx"

#include "textparser.hxx"

#include <algorithm>

#ifndef W32

using namespace std;

#endif

// ISO-8859-1 HTML character entities

static const char* LATIN1[] = {

    "À", "Ã", "Å",  "Æ",  "È", "Ê",

    "Ì", "Ï",   "Ð",    "Ñ", "Ò", "Ø",

    "Ù", "Þ",  "à", "ã", "å",  "æ",

    "è", "ê",  "ì", "ï",   "ð",    "ñ",

    "ò", "ø", "ù", "þ",  "ÿ"};

#define LATIN1_LEN (sizeof(LATIN1) / sizeof(char*))

#define ENTITY_APOS "'"

#define UTF8_APOS "\xe2\x80\x99"

#define APOSTROPHE "'"

TextParser::TextParser(const char* wordchars) {

  init(wordchars);

}

TextParser::TextParser(const w_char* wordchars, int len) {

  init(wordchars, len);

}

TextParser::~TextParser() = default;

int TextParser::is_wordchar(const char* w) {

  if (*w == '\0')

    return 0;

  size_t cache_index = (*w + 256) % 256;

  if (utf8) {

    const bool use_cache = cache_index < 0x80;

    if (use_cache)

      return wordcharacters[cache_index];

    if (u8_u16(wc, w, true) < 1)

        return 0;

    unsigned short idx = (unsigned short)wc[0];

    return unicodeisalpha(idx) ||

           (wordchars_utf16 &&

            std::binary_search(wordchars_utf16, wordchars_utf16 + wclen, wc[0]));

  } else {

    return wordcharacters[cache_index];

  }

}

const char* TextParser::get_latin1(const char* s) {

  if (s[0] == '&') {

    unsigned int i = 0;

    while ((i < LATIN1_LEN) && strncmp(LATIN1[i], s, strlen(LATIN1[i])) != 0)

      i++;

    if (i != LATIN1_LEN)

      return LATIN1[i];

  }

  return nullptr;

}

void TextParser::init(const char* wordchars) {

  actual = 0;

  head = 0;

  token = 0;

  state = 0;

  utf8 = 0;

  checkurl = 0;

  wordchars_utf16 = nullptr;

  wclen = 0;

  wordcharacters.resize(256, 0);

  if (!wordchars)

    wordchars = "qwertzuiopasdfghjklyxcvbnmQWERTZUIOPASDFGHJKLYXCVBNM";

  for (unsigned int j = 0; j < strlen(wordchars); ++j) {

    wordcharacters[(wordchars[j] + 256) % 256] = 1;

  }

}

void TextParser::init(const w_char* wc_utf8, int len) {

  actual = 0;

  head = 0;

  token = 0;

  state = 0;

  utf8 = 1;

  checkurl = 0;

  wordchars_utf16 = wc_utf8;

  wclen = len;

  // build a cache for the simple cases

  wordcharacters.resize(0x80);

  w_char wc2;

  wc2.h = 0;

  for (unsigned char idx = 0; idx < 0x80; ++idx) {

    wc2.l = idx;

    int cache = unicodeisalpha(idx) ||

                (wordchars_utf16 &&

                 std::binary_search(wordchars_utf16, wordchars_utf16 + wclen, wc2));

    wordcharacters[idx] = cache;

  }

}

int TextParser::next_char(const char* ln, size_t* pos) {

  if (*(ln + *pos) == '\0')

    return 1;

  if (utf8) {

    if (*(ln + *pos) >> 7) {

      // jump to next UTF-8 character

      for ((*pos)++; (*(ln + *pos) & 0xc0) == 0x80; (*pos)++)

        ;

    } else {

      (*pos)++;

    }

  } else

    (*pos)++;

  return 0;

}

void TextParser::put_line(const char* word) {

  actual = (actual + 1) % MAXPREVLINE;

  line[actual].assign(word);

  token = 0;

  head = 0;

  check_urls();

}

std::string TextParser::get_prevline(int n) const {

  return line[(actual + MAXPREVLINE - n) % MAXPREVLINE];

}

std::string TextParser::get_line() const {

  return get_prevline(0);

}

bool TextParser::next_token(std::string &t) {

  const char* latin1;

  for (;;) {

    switch (state) {

      case 0:  // non word chars

        if (is_wordchar(line[actual].c_str() + head)) {

          state = 1;

          token = head;

        } else if ((latin1 = get_latin1(line[actual].c_str() + head))) {

          state = 1;

          token = head;

          head += strlen(latin1);

        }

        break;

      case 1:  // wordchar

        if ((latin1 = get_latin1(line[actual].c_str() + head))) {

          head += strlen(latin1);

        } else if ((is_wordchar(APOSTROPHE) ||

                    (is_utf8() && is_wordchar(UTF8_APOS))) &&

                   !line[actual].empty() && line[actual][head] == '\'' &&

                   is_wordchar(line[actual].c_str() + head + 1)) {

          head++;

        } else if (is_utf8() &&

                   is_wordchar(APOSTROPHE) &&  // add Unicode apostrophe

                                                      // to the WORDCHARS, if

                                                      // needed

                   strncmp(line[actual].c_str() + head, UTF8_APOS, strlen(UTF8_APOS)) ==

                       0 &&

                   is_wordchar(line[actual].c_str() + head + strlen(UTF8_APOS))) {

          head += strlen(UTF8_APOS) - 1;

        } else if (!is_wordchar(line[actual].c_str() + head)) {

          state = 0;

          if (alloc_token(token, &head, t))

            return true;

        }

        break;

    }

    if (next_char(line[actual].c_str(), &head))

      return false;

  }

}

size_t TextParser::get_tokenpos() {

  return token;

}

int TextParser::change_token(const char* word) {

  if (word) {

    std::string remainder(line[actual].substr(head));

    line[actual].resize(token);

    line[actual].append(word);

    line[actual].append(remainder);

    head = token;

    check_urls();

    return 1;

  }

  return 0;

}

std::string TextParser::get_word(const std::string &tok) {

  return tok;

}

void TextParser::check_urls() {

  urlline.resize(line[actual].size() + 1);

  int url_state = 0;

  size_t url_head = 0;

  size_t url_token = 0;

  int url = 0;

  for (;;) {

    switch (url_state) {

      case 0:  // non word chars

        if (is_wordchar(line[actual].c_str() + url_head)) {

          url_state = 1;

          url_token = url_head;

          // Unix path

        } else if (line[actual][url_head] == '/') {

          url_state = 1;

          url_token = url_head;

          url = 1;

        }

        break;

      case 1:  // wordchar

        char ch = line[actual][url_head];

        // e-mail address

        if ((ch == '@') ||

            // MS-DOS, Windows path

            (strncmp(line[actual].c_str() + url_head, ":\\", 2) == 0) ||

            // URL

            (strncmp(line[actual].c_str() + url_head, "://", 3) == 0)) {

          url = 1;

        } else if (!(is_wordchar(line[actual].c_str() + url_head) || (ch == '-') ||

                     (ch == '_') || (ch == '\\') || (ch == '.') ||

                     (ch == ':') || (ch == '/') || (ch == '~') || (ch == '%') ||

                     (ch == '*') || (ch == '$') || (ch == '[') || (ch == ']') ||

                     (ch == '?') || (ch == '!') ||

                     ((ch >= '0') && (ch <= '9')))) {

          url_state = 0;

          if (url == 1) {

            for (size_t i = url_token; i < url_head; ++i) {

              urlline[i] = true;

            }

          }

          url = 0;

        }

        break;

    }

    urlline[url_head] = false;

    if (next_char(line[actual].c_str(), &url_head))

      return;

  }

}

int TextParser::get_url(size_t token_pos, size_t* hd) {

  for (size_t i = *hd; i < line[actual].size() && urlline[i]; i++, (*hd)++)

    ;

  return checkurl ? 0 : urlline[token_pos];

}

void TextParser::set_url_checking(int check) {

  checkurl = check;

}

bool TextParser::alloc_token(size_t tokn, size_t* hd, std::string& t) {

  if (get_url(tokn, hd))

    return false;

  t = line[actual].substr(tokn, *hd - tokn);

  // remove colon for Finnish and Swedish language

  if (!t.empty() && t[t.size() - 1] == ':') {

    t.resize(t.size() - 1);

    if (t.empty()) {

      return false;

    }

  }

  return true;

}