office-gobmx/lingucomponent/source/languageguessing/guess.cxx

137 lines
3.8 KiB
C++
Raw Normal View History

/***************************************************************************
*
* DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
*
* Copyright 2000, 2010 Oracle and/or its affiliates.
*
* OpenOffice.org - a multi-platform office productivity suite
*
* This file is part of OpenOffice.org.
*
* OpenOffice.org is free software: you can redistribute it and/or modify
* it under the terms of the GNU Lesser General Public License version 3
* only, as published by the Free Software Foundation.
*
* OpenOffice.org is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU Lesser General Public License version 3 for more details
* (a copy is included in the LICENSE file that accompanied this code).
*
* You should have received a copy of the GNU Lesser General Public License
* version 3 along with OpenOffice.org. If not, see
* <http://www.openoffice.org/license.html>
* for a copy of the LGPLv3 License.
*
************************************************************************/
// MARKER(update_precomp.py): autogen include statement, do not remove
#include "precompiled_lingucomponent.hxx"
#include <iostream>
#include <string.h>
#include <libtextcat/textcat.h>
#include <altstrfunc.hxx>
#include <guess.hxx>
using namespace std;
Guess::Guess()
{
language_str = DEFAULT_LANGUAGE;
country_str = DEFAULT_COUNTRY;
encoding_str = DEFAULT_ENCODING;
}
/*
* this use a char * string to build the guess object
* a string like those is made as : [language-country-encoding]...
*
*/
Guess::Guess(char * guess_str)
{
Guess();
string lang;
string country;
string enc;
//if the guess is not like "UNKNOWN" or "SHORT", go into the brackets
// if(strncmp((const char*)(guess_str + 1), _TEXTCAT_RESULT_UNKOWN, strlen(_TEXTCAT_RESULT_UNKOWN)) != 0
// &&
// strncmp((const char*)(guess_str + 1), _TEXTCAT_RESULT_SHORT, strlen(_TEXTCAT_RESULT_SHORT)) != 0)
// {
if(strcmp((const char*)(guess_str + 1), _TEXTCAT_RESULT_UNKOWN) != 0
&&
strcmp((const char*)(guess_str + 1), _TEXTCAT_RESULT_SHORT) != 0)
{
int current_pointer = 0;
//this is to go to the first char of the guess string ( the '[' of "[en-US-utf8]" )
while(!isSeparator(guess_str[current_pointer])){
current_pointer++;
}
current_pointer++;
//this is to pick up the language ( the "en" from "[en-US-utf8]" )
while(!isSeparator(guess_str[current_pointer])){
lang+=guess_str[current_pointer];
current_pointer++;
}
current_pointer++;
//this is to pick up the country ( the "US" from "[en-US-utf8]" )
while(!isSeparator(guess_str[current_pointer])){
country+=guess_str[current_pointer];
current_pointer++;
}
current_pointer++;
//this is to pick up the encoding ( the "utf8" from "[en-US-utf8]" )
while(!isSeparator(guess_str[current_pointer])){
enc+=guess_str[current_pointer];
current_pointer++;
}
if(lang!=""){//if not we use the default value
language_str=lang;
}
CWS-TOOLING: integrate CWS tl66 2009-05-15 12:28:55 +0200 tl r271932 : #i91812# include fixed 2009-05-07 16:52:41 +0200 tl r271680 : #i97200# one more MathML export problem to fix 2009-05-05 08:33:29 +0200 tl r271494 : #i99401# positiv user-dicts vs negativ user-dicts 2009-05-04 14:14:03 +0200 tl r271452 : #i97200# warning free code; MathML 2.0 export 2009-05-04 13:26:30 +0200 tl r271448 : #i97200# write valid MathML 2.0 on export 2009-04-29 14:21:54 +0200 tl r271371 : #i97200# new MathML token 2009-04-29 11:12:07 +0200 tl r271360 : #i97200# inroducing separate files for import and export 2009-04-28 16:47:42 +0200 tl r271331 : #i97200# better MathML pretty printing 2009-04-28 11:21:57 +0200 tl r271315 : #i97200# MathML attributes and default namespace for MathML 2009-04-28 11:21:24 +0200 tl r271314 : #i97200# MathML attributes and default namespace for MathML 2009-04-23 12:44:18 +0200 tl r271154 : #i97200# math.dtd removed 2009-04-23 12:31:56 +0200 tl r271151 : #i97200# MathML: don't use namespace on attributes 2009-04-22 13:21:11 +0200 tl r271099 : warning-free code 2009-04-22 12:20:13 +0200 tl r271092 : #i100757# loop fixed 2009-04-22 11:29:51 +0200 tl r271086 : #97327# adding mongolian fingerprint for language guessing 2009-04-22 11:25:56 +0200 tl r271083 : #97327# adding mongolian fingerprint for language guessing 2009-04-21 10:39:21 +0200 tl r271025 : #99599# code fix for LRE/RLE embedding 2009-04-20 16:36:33 +0200 tl r270992 : #i99604# HasDigits fixed 2009-04-20 14:44:19 +0200 tl r270985 : #i99604# warning-free code for Windows 2009-04-20 13:48:13 +0200 tl r270980 : #i99604# HasDigits fix for non-ASCII characters 2009-04-20 13:47:50 +0200 tl r270979 : #i99604# HasDigits fix for non-ASCII characters 2009-04-20 12:28:15 +0200 tl r270973 : warning-free code after merging 2009-04-20 10:16:19 +0200 tl r270964 : warning-free code after merging 2009-04-17 14:43:36 +0200 tl r270948 : #i96846# 2009-04-16 13:09:15 +0200 tl r270883 : CWS-TOOLING: rebase CWS tl66 to trunk@270723 (milestone: DEV300:m46) 2009-04-14 14:34:08 +0200 tl r270770 : #101067# warning-free code 2009-04-02 09:07:44 +0200 tl r270368 : #i100757# performance patch for start-up (initialize language guessing on demand only) 2009-03-11 10:37:59 +0100 tl r269301 : #i100083# fixed system dictionary lookup 2009-03-06 13:10:23 +0100 tl r268998 : warning-free code for Windows non-pro 2009-02-23 14:01:23 +0100 tl r268355 : #i99401# winning rules for user-dictionaries changed 2009-02-19 14:05:57 +0100 tl r268281 : #i98644# suggestion improvement when first checker does not know any suggestions 2009-02-19 14:05:02 +0100 tl r268280 : #i98644# suggestion improvement when first checker does not know any suggestions 2009-02-19 13:58:51 +0100 tl r268279 : #i98644# suggestion improvement when first checker does not know any suggestions 2009-02-19 11:38:03 +0100 tl r268266 : #i98644# suggestion improvement when first checker does not know any suggestions 2009-02-12 11:58:34 +0100 tl r267642 : #i96846# some properties declared as maybevoid 2009-02-06 12:43:55 +0100 tl r267454 : #i98644# provide sugestions from secondary spell checkers if the primary does not provide ones 2009-02-05 13:02:26 +0100 tl r267418 : #i98880# a bit clean-up in the grammar checking framework 2009-02-04 12:15:37 +0100 tl r267363 : #i91812# remove unused/duplicate code 2009-02-04 12:09:34 +0100 tl r267362 : #i91812# remove unused/duplicate code 2009-02-04 11:07:57 +0100 tl r267355 : #i91812# remove unused code 2009-02-04 11:06:48 +0100 tl r267354 : #i91812# remove unused code 2009-02-03 14:52:43 +0100 tl r267331 : #i91812# remove unused code 2009-02-03 14:26:00 +0100 tl r267324 : #i91198# adding fingerprint for luxembourgish 2009-02-03 14:20:58 +0100 tl r267323 : #i91198# adding fingerprint for luxembourgish 2009-02-03 14:18:33 +0100 tl r267322 : #i91198# adding fingerprint for luxembourgish 2009-02-03 13:56:39 +0100 tl r267319 : #i91812# remove unused code 2009-02-03 12:41:50 +0100 tl r267314 : #i48400# auto-spellcheck improvement when deleting wrong chars 2009-02-03 11:48:51 +0100 tl r267310 : #i91812# remove unused code 2009-02-03 11:14:29 +0100 tl r267307 : warning free code 2009-02-03 10:45:21 +0100 tl r267306 : #i91812# remove unused code 2009-02-03 10:37:04 +0100 tl r267304 : #i33387# name change for 'View/Selection' 2009-02-03 10:36:17 +0100 tl r267303 : #i33387# name change for 'View/Selection' 2009-02-03 10:32:12 +0100 tl r267302 : #i30642# spelling error in context menu fixed 2009-02-03 10:27:34 +0100 tl r267301 : #i92210# remove unused code types.cxx cfgitem.*
2009-05-19 04:31:27 -05:00
country_str=country;
if(enc!=""){//if not we use the default value
encoding_str=enc;
}
}
}
Guess::~Guess(){}
string Guess::GetLanguage()
{
return language_str;
}
string Guess::GetCountry()
{
return country_str;
}
string Guess::GetEncoding()
{
return encoding_str;
}
bool Guess::operator==(string lang)
{
string toString;
toString += GetLanguage();
toString += "-";
toString += GetCountry();
toString += "-";
toString += GetEncoding();
return start(toString, lang);
}