1.1 --- /dev/null Thu Jan 01 00:00:00 1970 +0000
1.2 +++ b/extensions/spellcheck/hunspell/src/csutil.hxx Wed Dec 31 06:09:35 2014 +0100
1.3 @@ -0,0 +1,277 @@
1.4 +/******* BEGIN LICENSE BLOCK *******
1.5 + * Version: MPL 1.1/GPL 2.0/LGPL 2.1
1.6 + *
1.7 + * The contents of this file are subject to the Mozilla Public License Version
1.8 + * 1.1 (the "License"); you may not use this file except in compliance with
1.9 + * the License. You may obtain a copy of the License at
1.10 + * http://www.mozilla.org/MPL/
1.11 + *
1.12 + * Software distributed under the License is distributed on an "AS IS" basis,
1.13 + * WITHOUT WARRANTY OF ANY KIND, either express or implied. See the License
1.14 + * for the specific language governing rights and limitations under the
1.15 + * License.
1.16 + *
1.17 + * The Initial Developers of the Original Code are Kevin Hendricks (MySpell)
1.18 + * and László Németh (Hunspell). Portions created by the Initial Developers
1.19 + * are Copyright (C) 2002-2005 the Initial Developers. All Rights Reserved.
1.20 + *
1.21 + * Contributor(s): Kevin Hendricks (kevin.hendricks@sympatico.ca)
1.22 + * David Einstein (deinst@world.std.com)
1.23 + * László Németh (nemethl@gyorsposta.hu)
1.24 + * Caolan McNamara (caolanm@redhat.com)
1.25 + * Davide Prina
1.26 + * Giuseppe Modugno
1.27 + * Gianluca Turconi
1.28 + * Simon Brouwer
1.29 + * Noll Janos
1.30 + * Biro Arpad
1.31 + * Goldman Eleonora
1.32 + * Sarlos Tamas
1.33 + * Bencsath Boldizsar
1.34 + * Halacsy Peter
1.35 + * Dvornik Laszlo
1.36 + * Gefferth Andras
1.37 + * Nagy Viktor
1.38 + * Varga Daniel
1.39 + * Chris Halls
1.40 + * Rene Engelhard
1.41 + * Bram Moolenaar
1.42 + * Dafydd Jones
1.43 + * Harri Pitkanen
1.44 + * Andras Timar
1.45 + * Tor Lillqvist
1.46 + *
1.47 + * Alternatively, the contents of this file may be used under the terms of
1.48 + * either the GNU General Public License Version 2 or later (the "GPL"), or
1.49 + * the GNU Lesser General Public License Version 2.1 or later (the "LGPL"),
1.50 + * in which case the provisions of the GPL or the LGPL are applicable instead
1.51 + * of those above. If you wish to allow use of your version of this file only
1.52 + * under the terms of either the GPL or the LGPL, and not to allow others to
1.53 + * use your version of this file under the terms of the MPL, indicate your
1.54 + * decision by deleting the provisions above and replace them with the notice
1.55 + * and other provisions required by the GPL or the LGPL. If you do not delete
1.56 + * the provisions above, a recipient may use your version of this file under
1.57 + * the terms of any one of the MPL, the GPL or the LGPL.
1.58 + *
1.59 + ******* END LICENSE BLOCK *******/
1.60 +
1.61 +#ifndef __CSUTILHXX__
1.62 +#define __CSUTILHXX__
1.63 +
1.64 +#include "hunvisapi.h"
1.65 +
1.66 +// First some base level utility routines
1.67 +
1.68 +#include <string.h>
1.69 +#include "w_char.hxx"
1.70 +#include "htypes.hxx"
1.71 +
1.72 +#ifdef MOZILLA_CLIENT
1.73 +#include "nscore.h" // for mozalloc headers
1.74 +#endif
1.75 +
1.76 +// casing
1.77 +#define NOCAP 0
1.78 +#define INITCAP 1
1.79 +#define ALLCAP 2
1.80 +#define HUHCAP 3
1.81 +#define HUHINITCAP 4
1.82 +
1.83 +// default encoding and keystring
1.84 +#define SPELL_ENCODING "ISO8859-1"
1.85 +#define SPELL_KEYSTRING "qwertyuiop|asdfghjkl|zxcvbnm"
1.86 +
1.87 +// default morphological fields
1.88 +#define MORPH_STEM "st:"
1.89 +#define MORPH_ALLOMORPH "al:"
1.90 +#define MORPH_POS "po:"
1.91 +#define MORPH_DERI_PFX "dp:"
1.92 +#define MORPH_INFL_PFX "ip:"
1.93 +#define MORPH_TERM_PFX "tp:"
1.94 +#define MORPH_DERI_SFX "ds:"
1.95 +#define MORPH_INFL_SFX "is:"
1.96 +#define MORPH_TERM_SFX "ts:"
1.97 +#define MORPH_SURF_PFX "sp:"
1.98 +#define MORPH_FREQ "fr:"
1.99 +#define MORPH_PHON "ph:"
1.100 +#define MORPH_HYPH "hy:"
1.101 +#define MORPH_PART "pa:"
1.102 +#define MORPH_FLAG "fl:"
1.103 +#define MORPH_HENTRY "_H:"
1.104 +#define MORPH_TAG_LEN strlen(MORPH_STEM)
1.105 +
1.106 +#define MSEP_FLD ' '
1.107 +#define MSEP_REC '\n'
1.108 +#define MSEP_ALT '\v'
1.109 +
1.110 +// default flags
1.111 +#define DEFAULTFLAGS 65510
1.112 +#define FORBIDDENWORD 65510
1.113 +#define ONLYUPCASEFLAG 65511
1.114 +
1.115 +// convert UTF-16 characters to UTF-8
1.116 +LIBHUNSPELL_DLL_EXPORTED char * u16_u8(char * dest, int size, const w_char * src, int srclen);
1.117 +
1.118 +// convert UTF-8 characters to UTF-16
1.119 +LIBHUNSPELL_DLL_EXPORTED int u8_u16(w_char * dest, int size, const char * src);
1.120 +
1.121 +// sort 2-byte vector
1.122 +LIBHUNSPELL_DLL_EXPORTED void flag_qsort(unsigned short flags[], int begin, int end);
1.123 +
1.124 +// binary search in 2-byte vector
1.125 +LIBHUNSPELL_DLL_EXPORTED int flag_bsearch(unsigned short flags[], unsigned short flag, int right);
1.126 +
1.127 +// remove end of line char(s)
1.128 +LIBHUNSPELL_DLL_EXPORTED void mychomp(char * s);
1.129 +
1.130 +// duplicate string
1.131 +LIBHUNSPELL_DLL_EXPORTED char * mystrdup(const char * s);
1.132 +
1.133 +// strcat for limited length destination string
1.134 +LIBHUNSPELL_DLL_EXPORTED char * mystrcat(char * dest, const char * st, int max);
1.135 +
1.136 +// duplicate reverse of string
1.137 +LIBHUNSPELL_DLL_EXPORTED char * myrevstrdup(const char * s);
1.138 +
1.139 +// parse into tokens with char delimiter
1.140 +LIBHUNSPELL_DLL_EXPORTED char * mystrsep(char ** sptr, const char delim);
1.141 +// parse into tokens with char delimiter
1.142 +LIBHUNSPELL_DLL_EXPORTED char * mystrsep2(char ** sptr, const char delim);
1.143 +
1.144 +// parse into tokens with char delimiter
1.145 +LIBHUNSPELL_DLL_EXPORTED char * mystrrep(char *, const char *, const char *);
1.146 +
1.147 +// append s to ends of every lines in text
1.148 +LIBHUNSPELL_DLL_EXPORTED void strlinecat(char * lines, const char * s);
1.149 +
1.150 +// tokenize into lines with new line
1.151 +LIBHUNSPELL_DLL_EXPORTED int line_tok(const char * text, char *** lines, char breakchar);
1.152 +
1.153 +// tokenize into lines with new line and uniq in place
1.154 +LIBHUNSPELL_DLL_EXPORTED char * line_uniq(char * text, char breakchar);
1.155 +LIBHUNSPELL_DLL_EXPORTED char * line_uniq_app(char ** text, char breakchar);
1.156 +
1.157 +// change oldchar to newchar in place
1.158 +LIBHUNSPELL_DLL_EXPORTED char * tr(char * text, char oldc, char newc);
1.159 +
1.160 +// reverse word
1.161 +LIBHUNSPELL_DLL_EXPORTED int reverseword(char *);
1.162 +
1.163 +// reverse word
1.164 +LIBHUNSPELL_DLL_EXPORTED int reverseword_utf(char *);
1.165 +
1.166 +// remove duplicates
1.167 +LIBHUNSPELL_DLL_EXPORTED int uniqlist(char ** list, int n);
1.168 +
1.169 +// free character array list
1.170 +LIBHUNSPELL_DLL_EXPORTED void freelist(char *** list, int n);
1.171 +
1.172 +// character encoding information
1.173 +struct cs_info {
1.174 + unsigned char ccase;
1.175 + unsigned char clower;
1.176 + unsigned char cupper;
1.177 +};
1.178 +
1.179 +LIBHUNSPELL_DLL_EXPORTED int initialize_utf_tbl();
1.180 +LIBHUNSPELL_DLL_EXPORTED void free_utf_tbl();
1.181 +LIBHUNSPELL_DLL_EXPORTED unsigned short unicodetoupper(unsigned short c, int langnum);
1.182 +LIBHUNSPELL_DLL_EXPORTED unsigned short unicodetolower(unsigned short c, int langnum);
1.183 +LIBHUNSPELL_DLL_EXPORTED int unicodeisalpha(unsigned short c);
1.184 +
1.185 +LIBHUNSPELL_DLL_EXPORTED struct cs_info * get_current_cs(const char * es);
1.186 +
1.187 +// get language identifiers of language codes
1.188 +LIBHUNSPELL_DLL_EXPORTED int get_lang_num(const char * lang);
1.189 +
1.190 +// get characters of the given 8bit encoding with lower- and uppercase forms
1.191 +LIBHUNSPELL_DLL_EXPORTED char * get_casechars(const char * enc);
1.192 +
1.193 +// convert null terminated string to all caps using encoding
1.194 +LIBHUNSPELL_DLL_EXPORTED void enmkallcap(char * d, const char * p, const char * encoding);
1.195 +
1.196 +// convert null terminated string to all little using encoding
1.197 +LIBHUNSPELL_DLL_EXPORTED void enmkallsmall(char * d, const char * p, const char * encoding);
1.198 +
1.199 +// convert null terminated string to have initial capital using encoding
1.200 +LIBHUNSPELL_DLL_EXPORTED void enmkinitcap(char * d, const char * p, const char * encoding);
1.201 +
1.202 +// convert null terminated string to all caps
1.203 +LIBHUNSPELL_DLL_EXPORTED void mkallcap(char * p, const struct cs_info * csconv);
1.204 +
1.205 +// convert null terminated string to all little
1.206 +LIBHUNSPELL_DLL_EXPORTED void mkallsmall(char * p, const struct cs_info * csconv);
1.207 +
1.208 +// convert null terminated string to have initial capital
1.209 +LIBHUNSPELL_DLL_EXPORTED void mkinitcap(char * p, const struct cs_info * csconv);
1.210 +
1.211 +// convert first nc characters of UTF-8 string to little
1.212 +LIBHUNSPELL_DLL_EXPORTED void mkallsmall_utf(w_char * u, int nc, int langnum);
1.213 +
1.214 +// convert first nc characters of UTF-8 string to capital
1.215 +LIBHUNSPELL_DLL_EXPORTED void mkallcap_utf(w_char * u, int nc, int langnum);
1.216 +
1.217 +// get type of capitalization
1.218 +LIBHUNSPELL_DLL_EXPORTED int get_captype(char * q, int nl, cs_info *);
1.219 +
1.220 +// get type of capitalization (UTF-8)
1.221 +LIBHUNSPELL_DLL_EXPORTED int get_captype_utf8(w_char * q, int nl, int langnum);
1.222 +
1.223 +// strip all ignored characters in the string
1.224 +LIBHUNSPELL_DLL_EXPORTED void remove_ignored_chars_utf(char * word, unsigned short ignored_chars[], int ignored_len);
1.225 +
1.226 +// strip all ignored characters in the string
1.227 +LIBHUNSPELL_DLL_EXPORTED void remove_ignored_chars(char * word, char * ignored_chars);
1.228 +
1.229 +LIBHUNSPELL_DLL_EXPORTED int parse_string(char * line, char ** out, int ln);
1.230 +
1.231 +LIBHUNSPELL_DLL_EXPORTED int parse_array(char * line, char ** out, unsigned short ** out_utf16,
1.232 + int * out_utf16_len, int utf8, int ln);
1.233 +
1.234 +LIBHUNSPELL_DLL_EXPORTED int fieldlen(const char * r);
1.235 +LIBHUNSPELL_DLL_EXPORTED char * copy_field(char * dest, const char * morph, const char * var);
1.236 +
1.237 +LIBHUNSPELL_DLL_EXPORTED int morphcmp(const char * s, const char * t);
1.238 +
1.239 +LIBHUNSPELL_DLL_EXPORTED int get_sfxcount(const char * morph);
1.240 +
1.241 +// conversion function for protected memory
1.242 +LIBHUNSPELL_DLL_EXPORTED void store_pointer(char * dest, char * source);
1.243 +
1.244 +// conversion function for protected memory
1.245 +LIBHUNSPELL_DLL_EXPORTED char * get_stored_pointer(const char * s);
1.246 +
1.247 +// hash entry macros
1.248 +LIBHUNSPELL_DLL_EXPORTED inline char* HENTRY_DATA(struct hentry *h)
1.249 +{
1.250 + char *ret;
1.251 + if (!h->var)
1.252 + ret = NULL;
1.253 + else if (h->var & H_OPT_ALIASM)
1.254 + ret = get_stored_pointer(HENTRY_WORD(h) + h->blen + 1);
1.255 + else
1.256 + ret = HENTRY_WORD(h) + h->blen + 1;
1.257 + return ret;
1.258 +}
1.259 +
1.260 +// NULL-free version for warning-free OOo build
1.261 +LIBHUNSPELL_DLL_EXPORTED inline const char* HENTRY_DATA2(const struct hentry *h)
1.262 +{
1.263 + const char *ret;
1.264 + if (!h->var)
1.265 + ret = "";
1.266 + else if (h->var & H_OPT_ALIASM)
1.267 + ret = get_stored_pointer(HENTRY_WORD(h) + h->blen + 1);
1.268 + else
1.269 + ret = HENTRY_WORD(h) + h->blen + 1;
1.270 + return ret;
1.271 +}
1.272 +
1.273 +LIBHUNSPELL_DLL_EXPORTED inline char* HENTRY_FIND(struct hentry *h, const char *p)
1.274 +{
1.275 + return (HENTRY_DATA(h) ? strstr(HENTRY_DATA(h), p) : NULL);
1.276 +}
1.277 +
1.278 +#define w_char_eq(a,b) (((a).l == (b).l) && ((a).h == (b).h))
1.279 +
1.280 +#endif
