mirror of
https://github.com/Dushistov/sdcv.git
synced 2025-12-16 18:01:54 +00:00
remove not used code, use glib wrappers where possible
This commit is contained in:
Evgeniy Dushistov
@@ -16,7 +16,7 @@
|
||||
|
||||
#include "stardict_lib.hpp"
|
||||
|
||||
// Notice: read src/tools/DICTFILE_FORMAT for the dictionary
|
||||
// Notice: read src/tools/DICTFILE_FORMAT for the dictionary
|
||||
// file's format information!
|
||||
|
||||
namespace {
|
||||
@@ -31,19 +31,19 @@ namespace {
|
||||
return( ch=='A' || ch=='E' || ch=='I' || ch=='O' || ch=='U' );
|
||||
}
|
||||
|
||||
static bool bIsPureEnglish(const gchar *str)
|
||||
{
|
||||
static bool bIsPureEnglish(const gchar *str)
|
||||
{
|
||||
// i think this should work even when it is UTF8 string :).
|
||||
for (int i=0; str[i]!=0; i++)
|
||||
for (int i=0; str[i]!=0; i++)
|
||||
//if(str[i]<0)
|
||||
//if(str[i]<32 || str[i]>126) // tab equal 9,so this is not OK.
|
||||
// Better use isascii() but not str[i]<0 while char is default unsigned in arm
|
||||
if (!isascii(str[i]))
|
||||
return false;
|
||||
return true;
|
||||
if (!isascii(str[i]))
|
||||
return false;
|
||||
return true;
|
||||
}
|
||||
|
||||
static inline gint stardict_strcmp(const gchar *s1, const gchar *s2)
|
||||
static inline gint stardict_strcmp(const gchar *s1, const gchar *s2)
|
||||
{
|
||||
const gint a = g_ascii_strcasecmp(s1, s2);
|
||||
if (a == 0)
|
||||
@@ -55,7 +55,7 @@ namespace {
|
||||
static void unicode_strdown(gunichar *str)
|
||||
{
|
||||
while (*str) {
|
||||
*str=g_unichar_tolower(*str);
|
||||
*str = g_unichar_tolower(*str);
|
||||
++str;
|
||||
}
|
||||
}
|
||||
@@ -66,33 +66,29 @@ bool DictInfo::load_from_ifo_file(const std::string& ifofilename,
|
||||
bool istreedict)
|
||||
{
|
||||
ifo_file_name = ifofilename;
|
||||
gchar *buffer;
|
||||
if (!g_file_get_contents(ifofilename.c_str(), &buffer, nullptr, nullptr))
|
||||
glib::CharStr buffer;
|
||||
if (!g_file_get_contents(ifofilename.c_str(), get_addr(buffer), nullptr, nullptr))
|
||||
return false;
|
||||
|
||||
|
||||
static const char TREEDICT_MAGIC_DATA[] = "StarDict's treedict ifo file";
|
||||
static const char DICT_MAGIC_DATA[] = "StarDict's dict ifo file";
|
||||
|
||||
const gchar *magic_data = istreedict ? TREEDICT_MAGIC_DATA : DICT_MAGIC_DATA;
|
||||
static const unsigned char utf8_bom[] = { 0xEF, 0xBB, 0xBF, '\0'};
|
||||
if (!g_str_has_prefix(
|
||||
g_str_has_prefix(buffer, (const gchar *)(utf8_bom)) ? buffer + 3 : buffer,
|
||||
g_str_has_prefix(get_impl(buffer), (const gchar *)(utf8_bom)) ? get_impl(buffer) + 3 : get_impl(buffer),
|
||||
magic_data)) {
|
||||
g_free(buffer);
|
||||
return false;
|
||||
}
|
||||
|
||||
gchar *p1,*p2,*p3;
|
||||
|
||||
p1 = buffer + strlen(magic_data)-1;
|
||||
gchar *p1 = get_impl(buffer) + strlen(magic_data)-1;
|
||||
|
||||
p2 = strstr(p1,"\nwordcount=");
|
||||
if (!p2) {
|
||||
g_free(buffer);
|
||||
return false;
|
||||
}
|
||||
|
||||
p3 = strchr(p2+ sizeof("\nwordcount=")-1,'\n');
|
||||
gchar *p2 = strstr(p1, "\nwordcount=");
|
||||
if (p2 == nullptr)
|
||||
return false;
|
||||
|
||||
gchar *p3 = strchr(p2 + sizeof("\nwordcount=") - 1, '\n');
|
||||
gchar *tmpstr = (gchar *)g_memdup(p2+sizeof("\nwordcount=")-1, p3-(p2+sizeof("\nwordcount=")-1)+1);
|
||||
tmpstr[p3-(p2+sizeof("\nwordcount=")-1)] = '\0';
|
||||
wordcount = atol(tmpstr);
|
||||
@@ -100,36 +96,31 @@ bool DictInfo::load_from_ifo_file(const std::string& ifofilename,
|
||||
|
||||
if (istreedict) {
|
||||
p2 = strstr(p1,"\ntdxfilesize=");
|
||||
if (!p2) {
|
||||
g_free(buffer);
|
||||
if (p2 == nullptr)
|
||||
return false;
|
||||
}
|
||||
|
||||
p3 = strchr(p2+ sizeof("\ntdxfilesize=")-1,'\n');
|
||||
tmpstr = (gchar *)g_memdup(p2+sizeof("\ntdxfilesize=")-1, p3-(p2+sizeof("\ntdxfilesize=")-1)+1);
|
||||
tmpstr[p3-(p2+sizeof("\ntdxfilesize=")-1)] = '\0';
|
||||
index_file_size = atol(tmpstr);
|
||||
g_free(tmpstr);
|
||||
} else {
|
||||
|
||||
|
||||
p2 = strstr(p1,"\nidxfilesize=");
|
||||
if (!p2) {
|
||||
g_free(buffer);
|
||||
if (p2 == nullptr)
|
||||
return false;
|
||||
}
|
||||
|
||||
|
||||
p3 = strchr(p2+ sizeof("\nidxfilesize=")-1,'\n');
|
||||
tmpstr = (gchar *)g_memdup(p2+sizeof("\nidxfilesize=")-1, p3-(p2+sizeof("\nidxfilesize=")-1)+1);
|
||||
tmpstr[p3-(p2+sizeof("\nidxfilesize=")-1)] = '\0';
|
||||
index_file_size = atol(tmpstr);
|
||||
g_free(tmpstr);
|
||||
}
|
||||
|
||||
|
||||
p2 = strstr(p1,"\nbookname=");
|
||||
|
||||
if (!p2) {
|
||||
g_free(buffer);
|
||||
if (p2 == nullptr)
|
||||
return false;
|
||||
}
|
||||
|
||||
p2 = p2 + sizeof("\nbookname=") -1;
|
||||
p3 = strchr(p2, '\n');
|
||||
@@ -171,35 +162,33 @@ bool DictInfo::load_from_ifo_file(const std::string& ifofilename,
|
||||
}
|
||||
|
||||
p2 = strstr(p1,"\nsametypesequence=");
|
||||
if (p2) {
|
||||
if (p2) {
|
||||
p2+=sizeof("\nsametypesequence=")-1;
|
||||
p3 = strchr(p2, '\n');
|
||||
sametypesequence.assign(p2, p3-p2);
|
||||
}
|
||||
|
||||
g_free(buffer);
|
||||
|
||||
return true;
|
||||
return true;
|
||||
}
|
||||
|
||||
gchar* DictBase::GetWordData(guint32 idxitem_offset, guint32 idxitem_size)
|
||||
{
|
||||
for (int i=0; i<WORDDATA_CACHE_NUM; i++)
|
||||
for (int i=0; i<WORDDATA_CACHE_NUM; i++)
|
||||
if (cache[i].data && cache[i].offset == idxitem_offset)
|
||||
return cache[i].data;
|
||||
|
||||
|
||||
if (dictfile)
|
||||
fseek(dictfile, idxitem_offset, SEEK_SET);
|
||||
|
||||
|
||||
gchar *data;
|
||||
if (!sametypesequence.empty()) {
|
||||
gchar *origin_data = (gchar *)g_malloc(idxitem_size);
|
||||
|
||||
|
||||
if (dictfile)
|
||||
fread(origin_data, idxitem_size, 1, dictfile);
|
||||
else
|
||||
dictdzfile->read(origin_data, idxitem_offset, idxitem_size);
|
||||
|
||||
|
||||
guint32 data_size;
|
||||
gint sametypesequence_len = sametypesequence.length();
|
||||
//there have sametypesequence_len char being omitted.
|
||||
@@ -225,7 +214,7 @@ gchar* DictBase::GetWordData(guint32 idxitem_offset, guint32 idxitem_size)
|
||||
else
|
||||
data_size += sizeof(gchar);
|
||||
break;
|
||||
}
|
||||
}
|
||||
data = (gchar *)g_malloc(data_size);
|
||||
gchar *p1,*p2;
|
||||
p1 = data + sizeof(guint32);
|
||||
@@ -266,8 +255,8 @@ gchar* DictBase::GetWordData(guint32 idxitem_offset, guint32 idxitem_size)
|
||||
p1+=sec_size;
|
||||
p2+=sec_size;
|
||||
break;
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
//calculate the last item 's size.
|
||||
sec_size = idxitem_size - (p2-origin_data);
|
||||
*p1=sametypesequence[sametypesequence_len-1];
|
||||
@@ -280,7 +269,7 @@ gchar* DictBase::GetWordData(guint32 idxitem_offset, guint32 idxitem_size)
|
||||
case 'g':
|
||||
case 'x':
|
||||
memcpy(p1, p2, sec_size);
|
||||
p1 += sec_size;
|
||||
p1 += sec_size;
|
||||
*p1='\0';//add the end up '\0';
|
||||
break;
|
||||
case 'W':
|
||||
@@ -301,18 +290,18 @@ gchar* DictBase::GetWordData(guint32 idxitem_offset, guint32 idxitem_size)
|
||||
}
|
||||
break;
|
||||
}
|
||||
g_free(origin_data);
|
||||
g_free(origin_data);
|
||||
set_uint32(data, data_size);
|
||||
} else {
|
||||
} else {
|
||||
data = (gchar *)g_malloc(idxitem_size + sizeof(guint32));
|
||||
if (dictfile)
|
||||
fread(data+sizeof(guint32), idxitem_size, 1, dictfile);
|
||||
fread(data+sizeof(guint32), idxitem_size, 1, dictfile);
|
||||
else
|
||||
dictdzfile->read(data+sizeof(guint32), idxitem_offset, idxitem_size);
|
||||
set_uint32(data, idxitem_size+sizeof(guint32));
|
||||
}
|
||||
}
|
||||
g_free(cache[cache_cur].data);
|
||||
|
||||
|
||||
cache[cache_cur].data = data;
|
||||
cache[cache_cur].offset = idxitem_offset;
|
||||
cache_cur++;
|
||||
@@ -351,7 +340,7 @@ bool DictBase::SearchData(std::vector<std::string> &SearchWords, guint32 idxitem
|
||||
WordFind[j] = true;
|
||||
++nfound;
|
||||
}
|
||||
|
||||
|
||||
|
||||
if (nfound==nWord)
|
||||
return true;
|
||||
@@ -377,12 +366,12 @@ bool DictBase::SearchData(std::vector<std::string> &SearchWords, guint32 idxitem
|
||||
case 'x':
|
||||
sec_size = idxitem_size - (p-origin_data);
|
||||
for (j=0; j<nWord; j++)
|
||||
if (!WordFind[j] &&
|
||||
if (!WordFind[j] &&
|
||||
g_strstr_len(p, sec_size, SearchWords[j].c_str())) {
|
||||
WordFind[j] = true;
|
||||
++nfound;
|
||||
}
|
||||
|
||||
|
||||
|
||||
if (nfound==nWord)
|
||||
return true;
|
||||
@@ -401,7 +390,7 @@ bool DictBase::SearchData(std::vector<std::string> &SearchWords, guint32 idxitem
|
||||
if (!WordFind[j] && strstr(p, SearchWords[j].c_str())) {
|
||||
WordFind[j] = true;
|
||||
++nfound;
|
||||
}
|
||||
}
|
||||
|
||||
if (nfound==nWord)
|
||||
return true;
|
||||
@@ -496,7 +485,7 @@ namespace {
|
||||
std::vector<gchar *> wordlist;
|
||||
};
|
||||
|
||||
void OffsetIndex::page_t::fill(gchar *data, gint nent, glong idx_)
|
||||
void OffsetIndex::page_t::fill(gchar *data, gint nent, glong idx_)
|
||||
{
|
||||
idx=idx_;
|
||||
gchar *p=data;
|
||||
@@ -547,7 +536,7 @@ namespace {
|
||||
g_stat(item.c_str(), &cachestat)!=0)
|
||||
continue;
|
||||
if (cachestat.st_mtime<idxstat.st_mtime)
|
||||
continue;
|
||||
continue;
|
||||
MapFile mf;
|
||||
if (!mf.open(item.c_str(), cachestat.st_size))
|
||||
continue;
|
||||
@@ -608,7 +597,7 @@ namespace {
|
||||
if (!load_cache(url)) {//map file will close after finish of block
|
||||
MapFile map_file;
|
||||
if (!map_file.open(url.c_str(), fsize))
|
||||
return false;
|
||||
return false;
|
||||
const gchar *idxdatabuffer=map_file.begin();
|
||||
|
||||
const gchar *p1 = idxdatabuffer;
|
||||
@@ -646,7 +635,7 @@ namespace {
|
||||
if (page_idx==glong(wordoffset.size()-2))
|
||||
if ((nentr=wordcount%ENTR_PER_PAGE)==0)
|
||||
nentr=ENTR_PER_PAGE;
|
||||
|
||||
|
||||
|
||||
if (page_idx!=page.idx) {
|
||||
page_data.resize(wordoffset[page_idx+1]-wordoffset[page_idx]);
|
||||
@@ -691,7 +680,7 @@ namespace {
|
||||
iFrom=iThisIndex+1;
|
||||
else if (cmpint<0)
|
||||
iTo=iThisIndex-1;
|
||||
else {
|
||||
else {
|
||||
bFound=true;
|
||||
break;
|
||||
}
|
||||
@@ -699,7 +688,7 @@ namespace {
|
||||
if (!bFound)
|
||||
idx = iTo; //prev
|
||||
else
|
||||
idx = iThisIndex;
|
||||
idx = iThisIndex;
|
||||
}
|
||||
if (!bFound) {
|
||||
gulong netr=load_page(idx);
|
||||
@@ -732,11 +721,11 @@ namespace {
|
||||
bool WordListIndex::load(const std::string& url, gulong wc, gulong fsize)
|
||||
{
|
||||
gzFile in = gzopen(url.c_str(), "rb");
|
||||
if (in == nullptr)
|
||||
return false;
|
||||
|
||||
if (in == nullptr)
|
||||
return false;
|
||||
|
||||
idxdatabuf = (gchar *)g_malloc(fsize);
|
||||
|
||||
|
||||
const int len = gzread(in, idxdatabuf, fsize);
|
||||
gzclose(in);
|
||||
if (len < 0)
|
||||
@@ -793,23 +782,23 @@ namespace {
|
||||
if (!bFound)
|
||||
idx = iFrom; //next
|
||||
else
|
||||
idx = iThisIndex;
|
||||
idx = iThisIndex;
|
||||
}
|
||||
return bFound;
|
||||
}
|
||||
}
|
||||
|
||||
bool Dict::load(const std::string& ifofilename)
|
||||
{
|
||||
{
|
||||
gulong idxfilesize;
|
||||
if (!load_ifofile(ifofilename, idxfilesize))
|
||||
return false;
|
||||
|
||||
std::string fullfilename(ifofilename);
|
||||
fullfilename.replace(fullfilename.length()-sizeof("ifo")+1, sizeof("ifo")-1, "dict.dz");
|
||||
|
||||
|
||||
if (g_file_test(fullfilename.c_str(), G_FILE_TEST_EXISTS)) {
|
||||
dictdzfile.reset(new dictData);
|
||||
dictdzfile.reset(new DictData);
|
||||
if (!dictdzfile->open(fullfilename, 0)) {
|
||||
//g_print("open file %s failed!\n",fullfilename);
|
||||
return false;
|
||||
@@ -825,7 +814,7 @@ bool Dict::load(const std::string& ifofilename)
|
||||
|
||||
fullfilename=ifofilename;
|
||||
fullfilename.replace(fullfilename.length()-sizeof("ifo")+1, sizeof("ifo")-1, "idx.gz");
|
||||
|
||||
|
||||
if (g_file_test(fullfilename.c_str(), G_FILE_TEST_EXISTS)) {
|
||||
idx_file.reset(new WordListIndex);
|
||||
} else {
|
||||
@@ -852,7 +841,7 @@ bool Dict::load_ifofile(const std::string& ifofilename, gulong &idxfilesize)
|
||||
wordcount=dict_info.wordcount;
|
||||
bookname=dict_info.bookname;
|
||||
|
||||
idxfilesize=dict_info.index_file_size;
|
||||
idxfilesize=dict_info.index_file_size;
|
||||
|
||||
sametypesequence=dict_info.sametypesequence;
|
||||
|
||||
@@ -862,13 +851,13 @@ bool Dict::load_ifofile(const std::string& ifofilename, gulong &idxfilesize)
|
||||
bool Dict::LookupWithRule(GPatternSpec *pspec, glong *aIndex, int iBuffLen)
|
||||
{
|
||||
int iIndexCount = 0;
|
||||
|
||||
|
||||
for (guint32 i=0; i < narticles() && iIndexCount < (iBuffLen - 1); i++)
|
||||
if (g_pattern_match_string(pspec, get_key(i)))
|
||||
if (g_pattern_match_string(pspec, get_key(i)))
|
||||
aIndex[iIndexCount++] = i;
|
||||
|
||||
aIndex[iIndexCount] = -1; // -1 is the end.
|
||||
|
||||
|
||||
aIndex[iIndexCount] = -1; // -1 is the end.
|
||||
|
||||
return iIndexCount > 0;
|
||||
}
|
||||
|
||||
@@ -888,25 +877,25 @@ void Libs::load_dict(const std::string& url)
|
||||
}
|
||||
|
||||
void Libs::load(const std::list<std::string>& dicts_dirs,
|
||||
const std::list<std::string>& order_list,
|
||||
const std::list<std::string>& order_list,
|
||||
const std::list<std::string>& disable_list)
|
||||
{
|
||||
for_each_file(dicts_dirs, ".ifo", order_list, disable_list,
|
||||
for_each_file(dicts_dirs, ".ifo", order_list, disable_list,
|
||||
[this](const std::string& url, bool disable) -> void {
|
||||
if (!disable)
|
||||
load_dict(url);
|
||||
load_dict(url);
|
||||
});
|
||||
}
|
||||
|
||||
void Libs::reload(const std::list<std::string>& dicts_dirs,
|
||||
const std::list<std::string>& order_list,
|
||||
void Libs::reload(const std::list<std::string>& dicts_dirs,
|
||||
const std::list<std::string>& order_list,
|
||||
const std::list<std::string>& disable_list)
|
||||
{
|
||||
std::vector<Dict *> prev(oLib);
|
||||
oLib.clear();
|
||||
|
||||
for_each_file(dicts_dirs, ".ifo", order_list, disable_list,
|
||||
[&prev, this](const std::string& url, bool disable) -> void {
|
||||
for_each_file(dicts_dirs, ".ifo", order_list, disable_list,
|
||||
[&prev, this](const std::string& url, bool disable) -> void {
|
||||
if (!disable) {
|
||||
auto it = prev.begin();
|
||||
for (; it != prev.end(); ++it)
|
||||
@@ -917,14 +906,14 @@ void Libs::reload(const std::list<std::string>& dicts_dirs,
|
||||
prev.erase(it);
|
||||
oLib.push_back(res);
|
||||
} else
|
||||
load_dict(url);
|
||||
load_dict(url);
|
||||
}
|
||||
});
|
||||
|
||||
for (Dict *p : prev)
|
||||
delete p;
|
||||
}
|
||||
|
||||
|
||||
const gchar *Libs::poGetCurrentWord(glong * iCurrent)
|
||||
{
|
||||
const gchar *poCurrentWord = nullptr;
|
||||
@@ -938,7 +927,7 @@ const gchar *Libs::poGetCurrentWord(glong * iCurrent)
|
||||
poCurrentWord = poGetWord(iCurrent[iLib],iLib);
|
||||
} else {
|
||||
word = poGetWord(iCurrent[iLib],iLib);
|
||||
|
||||
|
||||
if (stardict_strcmp(poCurrentWord, word) > 0 )
|
||||
poCurrentWord = word;
|
||||
}
|
||||
@@ -967,7 +956,7 @@ const gchar *Libs::poGetNextWord(const gchar *sWord, glong *iCurrent)
|
||||
iCurrentLib = iLib;
|
||||
} else {
|
||||
word = poGetWord(iCurrent[iLib],iLib);
|
||||
|
||||
|
||||
if (stardict_strcmp(poCurrentWord, word) > 0 ) {
|
||||
poCurrentWord = word;
|
||||
iCurrentLib = iLib;
|
||||
@@ -1018,7 +1007,7 @@ Libs::poGetPreWord(glong * iCurrent)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
if (poCurrentWord) {
|
||||
iCurrent[iCurrentLib]--;
|
||||
for (std::vector<Dict *>::size_type iLib=0;iLib<oLib.size();iLib++) {
|
||||
@@ -1059,7 +1048,7 @@ bool Libs::LookupSimilarWord(const gchar* sWord, glong & iWordIndex, int iLib)
|
||||
bFound=true;
|
||||
}
|
||||
g_free(casestr);
|
||||
}
|
||||
}
|
||||
// Upper the first character and lower others.
|
||||
if (!bFound) {
|
||||
gchar *nextchar = g_utf8_next_char(sWord);
|
||||
@@ -1073,14 +1062,14 @@ bool Libs::LookupSimilarWord(const gchar* sWord, glong & iWordIndex, int iLib)
|
||||
bFound=true;
|
||||
}
|
||||
g_free(casestr);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
if (bIsPureEnglish(sWord)) {
|
||||
|
||||
if (bIsPureEnglish(sWord)) {
|
||||
// If not Found , try other status of sWord.
|
||||
int iWordLen=strlen(sWord);
|
||||
bool isupcase;
|
||||
|
||||
|
||||
gchar *sNewWord = (gchar *)g_malloc(iWordLen + 1);
|
||||
|
||||
//cut one char "s" or "d"
|
||||
@@ -1101,7 +1090,7 @@ bool Libs::LookupSimilarWord(const gchar* sWord, glong & iWordIndex, int iLib)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
//cut "ly"
|
||||
if(!bFound && iWordLen>2) {
|
||||
isupcase = !strncmp(&sWord[iWordLen-2],"LY",2);
|
||||
@@ -1109,9 +1098,9 @@ bool Libs::LookupSimilarWord(const gchar* sWord, glong & iWordIndex, int iLib)
|
||||
strcpy(sNewWord,sWord);
|
||||
sNewWord[iWordLen-2]='\0'; // cut "ly"
|
||||
if (iWordLen>5 && sNewWord[iWordLen-3]==sNewWord[iWordLen-4]
|
||||
&& !bIsVowel(sNewWord[iWordLen-4]) &&
|
||||
&& !bIsVowel(sNewWord[iWordLen-4]) &&
|
||||
bIsVowel(sNewWord[iWordLen-5])) {//doubled
|
||||
|
||||
|
||||
sNewWord[iWordLen-3]='\0';
|
||||
if( oLib[iLib]->Lookup(sNewWord, iIndex) )
|
||||
bFound=true;
|
||||
@@ -1126,7 +1115,7 @@ bool Libs::LookupSimilarWord(const gchar* sWord, glong & iWordIndex, int iLib)
|
||||
}
|
||||
if (!bFound)
|
||||
sNewWord[iWordLen-3]=sNewWord[iWordLen-4]; //restore
|
||||
}
|
||||
}
|
||||
}
|
||||
if (!bFound) {
|
||||
if (oLib[iLib]->Lookup(sNewWord, iIndex))
|
||||
@@ -1142,7 +1131,7 @@ bool Libs::LookupSimilarWord(const gchar* sWord, glong & iWordIndex, int iLib)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
//cut "ing"
|
||||
if(!bFound && iWordLen>3) {
|
||||
isupcase = !strncmp(&sWord[iWordLen-3],"ING",3);
|
||||
@@ -1150,8 +1139,8 @@ bool Libs::LookupSimilarWord(const gchar* sWord, glong & iWordIndex, int iLib)
|
||||
strcpy(sNewWord,sWord);
|
||||
sNewWord[iWordLen-3]='\0';
|
||||
if ( iWordLen>6 && (sNewWord[iWordLen-4]==sNewWord[iWordLen-5])
|
||||
&& !bIsVowel(sNewWord[iWordLen-5]) &&
|
||||
bIsVowel(sNewWord[iWordLen-6])) { //doubled
|
||||
&& !bIsVowel(sNewWord[iWordLen-5]) &&
|
||||
bIsVowel(sNewWord[iWordLen-6])) { //doubled
|
||||
sNewWord[iWordLen-4]='\0';
|
||||
if (oLib[iLib]->Lookup(sNewWord, iIndex))
|
||||
bFound=true;
|
||||
@@ -1178,7 +1167,7 @@ bool Libs::LookupSimilarWord(const gchar* sWord, glong & iWordIndex, int iLib)
|
||||
bFound=true;
|
||||
}
|
||||
g_free(casestr);
|
||||
}
|
||||
}
|
||||
}
|
||||
if(!bFound) {
|
||||
if (isupcase)
|
||||
@@ -1194,25 +1183,25 @@ bool Libs::LookupSimilarWord(const gchar* sWord, glong & iWordIndex, int iLib)
|
||||
bFound=true;
|
||||
}
|
||||
g_free(casestr);
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
//cut two char "es"
|
||||
if(!bFound && iWordLen>3) {
|
||||
isupcase = (!strncmp(&sWord[iWordLen-2],"ES",2) &&
|
||||
(sWord[iWordLen-3] == 'S' ||
|
||||
sWord[iWordLen-3] == 'X' ||
|
||||
sWord[iWordLen-3] == 'O' ||
|
||||
(iWordLen >4 && sWord[iWordLen-3] == 'H' &&
|
||||
(sWord[iWordLen-4] == 'C' ||
|
||||
isupcase = (!strncmp(&sWord[iWordLen-2],"ES",2) &&
|
||||
(sWord[iWordLen-3] == 'S' ||
|
||||
sWord[iWordLen-3] == 'X' ||
|
||||
sWord[iWordLen-3] == 'O' ||
|
||||
(iWordLen >4 && sWord[iWordLen-3] == 'H' &&
|
||||
(sWord[iWordLen-4] == 'C' ||
|
||||
sWord[iWordLen-4] == 'S'))));
|
||||
if (isupcase ||
|
||||
(!strncmp(&sWord[iWordLen-2],"es",2) &&
|
||||
(sWord[iWordLen-3] == 's' || sWord[iWordLen-3] == 'x' ||
|
||||
sWord[iWordLen-3] == 'o' ||
|
||||
(iWordLen >4 && sWord[iWordLen-3] == 'h' &&
|
||||
if (isupcase ||
|
||||
(!strncmp(&sWord[iWordLen-2],"es",2) &&
|
||||
(sWord[iWordLen-3] == 's' || sWord[iWordLen-3] == 'x' ||
|
||||
sWord[iWordLen-3] == 'o' ||
|
||||
(iWordLen >4 && sWord[iWordLen-3] == 'h' &&
|
||||
(sWord[iWordLen-4] == 'c' || sWord[iWordLen-4] == 's'))))) {
|
||||
strcpy(sNewWord,sWord);
|
||||
sNewWord[iWordLen-2]='\0';
|
||||
@@ -1228,7 +1217,7 @@ bool Libs::LookupSimilarWord(const gchar* sWord, glong & iWordIndex, int iLib)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
//cut "ed"
|
||||
if (!bFound && iWordLen>3) {
|
||||
isupcase = !strncmp(&sWord[iWordLen-2],"ED",2);
|
||||
@@ -1236,8 +1225,8 @@ bool Libs::LookupSimilarWord(const gchar* sWord, glong & iWordIndex, int iLib)
|
||||
strcpy(sNewWord,sWord);
|
||||
sNewWord[iWordLen-2]='\0';
|
||||
if (iWordLen>5 && (sNewWord[iWordLen-3]==sNewWord[iWordLen-4])
|
||||
&& !bIsVowel(sNewWord[iWordLen-4]) &&
|
||||
bIsVowel(sNewWord[iWordLen-5])) {//doubled
|
||||
&& !bIsVowel(sNewWord[iWordLen-4]) &&
|
||||
bIsVowel(sNewWord[iWordLen-5])) {//doubled
|
||||
sNewWord[iWordLen-3]='\0';
|
||||
if (oLib[iLib]->Lookup(sNewWord, iIndex))
|
||||
bFound=true;
|
||||
@@ -1268,7 +1257,7 @@ bool Libs::LookupSimilarWord(const gchar* sWord, glong & iWordIndex, int iLib)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
// cut "ied" , add "y".
|
||||
if (!bFound && iWordLen>3) {
|
||||
isupcase = !strncmp(&sWord[iWordLen-3],"IED",3);
|
||||
@@ -1291,7 +1280,7 @@ bool Libs::LookupSimilarWord(const gchar* sWord, glong & iWordIndex, int iLib)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
// cut "ies" , add "y".
|
||||
if (!bFound && iWordLen>3) {
|
||||
isupcase = !strncmp(&sWord[iWordLen-3],"IES",3);
|
||||
@@ -1333,7 +1322,7 @@ bool Libs::LookupSimilarWord(const gchar* sWord, glong & iWordIndex, int iLib)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
// cut "est".
|
||||
if (!bFound && iWordLen>3) {
|
||||
isupcase = !strncmp(&sWord[iWordLen-3], "EST", 3);
|
||||
@@ -1352,10 +1341,10 @@ bool Libs::LookupSimilarWord(const gchar* sWord, glong & iWordIndex, int iLib)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
g_free(sNewWord);
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
if (bFound)
|
||||
iWordIndex = iIndex;
|
||||
#if 0
|
||||
@@ -1381,7 +1370,7 @@ bool Libs::LookupWithFuzzy(const gchar *sWord, gchar *reslist[], gint reslist_si
|
||||
if (sWord[0] == '\0')
|
||||
return false;
|
||||
|
||||
Fuzzystruct oFuzzystruct[reslist_size];
|
||||
Fuzzystruct oFuzzystruct[reslist_size];
|
||||
|
||||
for (int i = 0; i < reslist_size; i++) {
|
||||
oFuzzystruct[i].pMatchWord = nullptr;
|
||||
@@ -1412,13 +1401,13 @@ bool Libs::LookupWithFuzzy(const gchar *sWord, gchar *reslist[], gint reslist_si
|
||||
sCheck = poGetWord(index,iLib);
|
||||
// tolower and skip too long or too short words
|
||||
iCheckWordLen = g_utf8_strlen(sCheck, -1);
|
||||
if (iCheckWordLen-ucs4_str2_len>=iMaxDistance ||
|
||||
if (iCheckWordLen-ucs4_str2_len>=iMaxDistance ||
|
||||
ucs4_str2_len-iCheckWordLen>=iMaxDistance)
|
||||
continue;
|
||||
ucs4_str1 = g_utf8_to_ucs4_fast(sCheck, -1, nullptr);
|
||||
if (iCheckWordLen > ucs4_str2_len)
|
||||
ucs4_str1[ucs4_str2_len]=0;
|
||||
unicode_strdown(ucs4_str1);
|
||||
unicode_strdown(ucs4_str1);
|
||||
|
||||
iDistance = oEditDistance.CalEditDistance(ucs4_str1, ucs4_str2, iMaxDistance);
|
||||
g_free(ucs4_str1);
|
||||
@@ -1428,7 +1417,7 @@ bool Libs::LookupWithFuzzy(const gchar *sWord, gchar *reslist[], gint reslist_si
|
||||
bool bAlreadyInList = false;
|
||||
int iMaxDistanceAt=0;
|
||||
for (int j=0; j<reslist_size; j++) {
|
||||
if (oFuzzystruct[j].pMatchWord &&
|
||||
if (oFuzzystruct[j].pMatchWord &&
|
||||
strcmp(oFuzzystruct[j].pMatchWord,sCheck)==0 ) {//already in list
|
||||
bAlreadyInList = true;
|
||||
break;
|
||||
@@ -1455,7 +1444,7 @@ bool Libs::LookupWithFuzzy(const gchar *sWord, gchar *reslist[], gint reslist_si
|
||||
|
||||
} // each lib
|
||||
g_free(ucs4_str2);
|
||||
|
||||
|
||||
if (Found)// sort with distance
|
||||
std::sort(oFuzzystruct, oFuzzystruct + reslist_size, [](const Fuzzystruct& lh, const Fuzzystruct& rh) -> bool {
|
||||
if (lh.iMatchWordDistance!=rh.iMatchWordDistance)
|
||||
@@ -1463,26 +1452,26 @@ bool Libs::LookupWithFuzzy(const gchar *sWord, gchar *reslist[], gint reslist_si
|
||||
|
||||
if (lh.pMatchWord && rh.pMatchWord)
|
||||
return stardict_strcmp(lh.pMatchWord, rh.pMatchWord)<0;
|
||||
|
||||
|
||||
return false;
|
||||
});
|
||||
|
||||
|
||||
for (gint i = 0; i < reslist_size; ++i)
|
||||
reslist[i] = oFuzzystruct[i].pMatchWord;
|
||||
|
||||
|
||||
return Found;
|
||||
}
|
||||
|
||||
gint Libs::LookupWithRule(const gchar *word, gchar **ppMatchWord)
|
||||
{
|
||||
{
|
||||
glong aiIndex[MAX_MATCH_ITEM_PER_LIB+1];
|
||||
gint iMatchCount = 0;
|
||||
GPatternSpec *pspec = g_pattern_spec_new(word);
|
||||
|
||||
|
||||
for (std::vector<Dict *>::size_type iLib=0; iLib<oLib.size(); iLib++) {
|
||||
//if(oLibs.LookdupWordsWithRule(pspec,aiIndex,MAX_MATCH_ITEM_PER_LIB+1-iMatchCount,iLib))
|
||||
//if(oLibs.LookdupWordsWithRule(pspec,aiIndex,MAX_MATCH_ITEM_PER_LIB+1-iMatchCount,iLib))
|
||||
// -iMatchCount,so save time,but may got less result and the word may repeat.
|
||||
|
||||
|
||||
if (oLib[iLib]->LookupWithRule(pspec,aiIndex, MAX_MATCH_ITEM_PER_LIB+1)) {
|
||||
if (progress_func)
|
||||
progress_func();
|
||||
@@ -1501,12 +1490,12 @@ gint Libs::LookupWithRule(const gchar *word, gchar **ppMatchWord)
|
||||
}
|
||||
}
|
||||
g_pattern_spec_free(pspec);
|
||||
|
||||
|
||||
if (iMatchCount)// sort it.
|
||||
std::sort(ppMatchWord, ppMatchWord+iMatchCount, [](const char *lh, const char *rh) -> bool {
|
||||
return stardict_strcmp(lh, rh)<0;
|
||||
});
|
||||
|
||||
});
|
||||
|
||||
return iMatchCount;
|
||||
}
|
||||
|
||||
@@ -1577,7 +1566,7 @@ bool Libs::LookupData(const gchar *sWord, std::vector<gchar *> *reslist)
|
||||
for (i = 0; i < oLib.size(); ++i)
|
||||
if (!reslist[i].empty())
|
||||
break;
|
||||
|
||||
|
||||
return i != oLib.size();
|
||||
}
|
||||
|
||||
|
||||
Reference in New Issue
Block a user