1.1 --- /dev/null Thu Jan 01 00:00:00 1970 +0000
1.2 +++ b/extensions/spellcheck/hunspell/src/dictmgr.cpp Wed Dec 31 06:09:35 2014 +0100
1.3 @@ -0,0 +1,213 @@
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): László Németh (nemethl@gyorsposta.hu)
1.22 + * Caolan McNamara (caolanm@redhat.com)
1.23 + *
1.24 + * Alternatively, the contents of this file may be used under the terms of
1.25 + * either the GNU General Public License Version 2 or later (the "GPL"), or
1.26 + * the GNU Lesser General Public License Version 2.1 or later (the "LGPL"),
1.27 + * in which case the provisions of the GPL or the LGPL are applicable instead
1.28 + * of those above. If you wish to allow use of your version of this file only
1.29 + * under the terms of either the GPL or the LGPL, and not to allow others to
1.30 + * use your version of this file under the terms of the MPL, indicate your
1.31 + * decision by deleting the provisions above and replace them with the notice
1.32 + * and other provisions required by the GPL or the LGPL. If you do not delete
1.33 + * the provisions above, a recipient may use your version of this file under
1.34 + * the terms of any one of the MPL, the GPL or the LGPL.
1.35 + *
1.36 + ******* END LICENSE BLOCK *******/
1.37 +
1.38 +#include <stdlib.h>
1.39 +#include <string.h>
1.40 +#include <ctype.h>
1.41 +#include <stdio.h>
1.42 +
1.43 +#include "dictmgr.hxx"
1.44 +
1.45 +DictMgr::DictMgr(const char * dictpath, const char * etype) : numdict(0)
1.46 +{
1.47 + // load list of etype entries
1.48 + pdentry = (dictentry *)malloc(MAXDICTIONARIES*sizeof(struct dictentry));
1.49 + if (pdentry) {
1.50 + if (parse_file(dictpath, etype)) {
1.51 + numdict = 0;
1.52 + // no dictionary.lst found is okay
1.53 + }
1.54 + }
1.55 +}
1.56 +
1.57 +
1.58 +DictMgr::~DictMgr()
1.59 +{
1.60 + dictentry * pdict = NULL;
1.61 + if (pdentry) {
1.62 + pdict = pdentry;
1.63 + for (int i=0;i<numdict;i++) {
1.64 + if (pdict->lang) {
1.65 + free(pdict->lang);
1.66 + pdict->lang = NULL;
1.67 + }
1.68 + if (pdict->region) {
1.69 + free(pdict->region);
1.70 + pdict->region=NULL;
1.71 + }
1.72 + if (pdict->filename) {
1.73 + free(pdict->filename);
1.74 + pdict->filename = NULL;
1.75 + }
1.76 + pdict++;
1.77 + }
1.78 + free(pdentry);
1.79 + pdentry = NULL;
1.80 + pdict = NULL;
1.81 + }
1.82 + numdict = 0;
1.83 +}
1.84 +
1.85 +
1.86 +// read in list of etype entries and build up structure to describe them
1.87 +int DictMgr::parse_file(const char * dictpath, const char * etype)
1.88 +{
1.89 +
1.90 + int i;
1.91 + char line[MAXDICTENTRYLEN+1];
1.92 + dictentry * pdict = pdentry;
1.93 +
1.94 + // open the dictionary list file
1.95 + FILE * dictlst;
1.96 + dictlst = fopen(dictpath,"r");
1.97 + if (!dictlst) {
1.98 + return 1;
1.99 + }
1.100 +
1.101 + // step one is to parse the dictionary list building up the
1.102 + // descriptive structures
1.103 +
1.104 + // read in each line ignoring any that dont start with etype
1.105 + while (fgets(line,MAXDICTENTRYLEN,dictlst)) {
1.106 + mychomp(line);
1.107 +
1.108 + /* parse in a dictionary entry */
1.109 + if (strncmp(line,etype,4) == 0) {
1.110 + if (numdict < MAXDICTIONARIES) {
1.111 + char * tp = line;
1.112 + char * piece;
1.113 + i = 0;
1.114 + while ((piece=mystrsep(&tp,' '))) {
1.115 + if (*piece != '\0') {
1.116 + switch(i) {
1.117 + case 0: break;
1.118 + case 1: pdict->lang = mystrdup(piece); break;
1.119 + case 2: if (strcmp (piece, "ANY") == 0)
1.120 + pdict->region = mystrdup("");
1.121 + else
1.122 + pdict->region = mystrdup(piece);
1.123 + break;
1.124 + case 3: pdict->filename = mystrdup(piece); break;
1.125 + default: break;
1.126 + }
1.127 + i++;
1.128 + }
1.129 + free(piece);
1.130 + }
1.131 + if (i == 4) {
1.132 + numdict++;
1.133 + pdict++;
1.134 + } else {
1.135 + switch (i) {
1.136 + case 3:
1.137 + free(pdict->region);
1.138 + pdict->region=NULL;
1.139 + case 2: //deliberate fallthrough
1.140 + free(pdict->lang);
1.141 + pdict->lang=NULL;
1.142 + default:
1.143 + break;
1.144 + }
1.145 + fprintf(stderr,"dictionary list corruption in line \"%s\"\n",line);
1.146 + fflush(stderr);
1.147 + }
1.148 + }
1.149 + }
1.150 + }
1.151 + fclose(dictlst);
1.152 + return 0;
1.153 +}
1.154 +
1.155 +// return text encoding of dictionary
1.156 +int DictMgr::get_list(dictentry ** ppentry)
1.157 +{
1.158 + *ppentry = pdentry;
1.159 + return numdict;
1.160 +}
1.161 +
1.162 +
1.163 +
1.164 +// strip strings into token based on single char delimiter
1.165 +// acts like strsep() but only uses a delim char and not
1.166 +// a delim string
1.167 +
1.168 +char * DictMgr::mystrsep(char ** stringp, const char delim)
1.169 +{
1.170 + char * rv = NULL;
1.171 + char * mp = *stringp;
1.172 + size_t n = strlen(mp);
1.173 + if (n > 0) {
1.174 + char * dp = (char *)memchr(mp,(int)((unsigned char)delim),n);
1.175 + if (dp) {
1.176 + *stringp = dp+1;
1.177 + size_t nc = dp - mp;
1.178 + rv = (char *) malloc(nc+1);
1.179 + if (rv) {
1.180 + memcpy(rv,mp,nc);
1.181 + *(rv+nc) = '\0';
1.182 + }
1.183 + } else {
1.184 + rv = (char *) malloc(n+1);
1.185 + if (rv) {
1.186 + memcpy(rv, mp, n);
1.187 + *(rv+n) = '\0';
1.188 + *stringp = mp + n;
1.189 + }
1.190 + }
1.191 + }
1.192 + return rv;
1.193 +}
1.194 +
1.195 +
1.196 +// replaces strdup with ansi version
1.197 +char * DictMgr::mystrdup(const char * s)
1.198 +{
1.199 + char * d = NULL;
1.200 + if (s) {
1.201 + int sl = strlen(s)+1;
1.202 + d = (char *) malloc(sl);
1.203 + if (d) memcpy(d,s,sl);
1.204 + }
1.205 + return d;
1.206 +}
1.207 +
1.208 +
1.209 +// remove cross-platform text line end characters
1.210 +void DictMgr:: mychomp(char * s)
1.211 +{
1.212 + int k = strlen(s);
1.213 + if ((k > 0) && ((*(s+k-1)=='\r') || (*(s+k-1)=='\n'))) *(s+k-1) = '\0';
1.214 + if ((k > 1) && (*(s+k-2) == '\r')) *(s+k-2) = '\0';
1.215 +}
1.216 +
