298 lines
6.4 KiB
C++
298 lines
6.4 KiB
C++
#help_index "WordStat/Dictionary"
|
|
|
|
public U0 WSDWordsLoad()
|
|
{//Put words from word list into hash table.
|
|
I64 size;
|
|
CHashGeneric *temph;
|
|
U8 *in_ptr,*in_start,*st2;
|
|
U16 *d;
|
|
wsd.num_words=0;
|
|
if (in_ptr=FileRead(WSD_WORD_FILENAME,&size)) {
|
|
in_start=in_ptr;
|
|
Free(wsd.word_lst);
|
|
wsd.word_lst=AMAlloc(size);
|
|
MemCpy(wsd.word_lst,in_start,size);
|
|
wsd.word_lst_size=size;
|
|
|
|
while (in_ptr<in_start+size) {
|
|
if (*in_ptr==WSD_WORD_CHAR)
|
|
in_ptr++;
|
|
if (*in_ptr) {
|
|
st2=MStrUtil(in_ptr,SUF_TO_UPPER);
|
|
temph=ACAlloc(sizeof(CHashGeneric)+StrLen(st2)+1);
|
|
StrCpy(temph+1,st2);
|
|
Free(st2);
|
|
in_ptr+=StrLen(in_ptr)+1;
|
|
temph->str=temph+1;
|
|
temph->use_cnt=1;
|
|
temph->type=HTT_DICT_WORD;
|
|
d=in_ptr;
|
|
temph->user_data0=*d;
|
|
in_ptr+=2;
|
|
HashAdd(temph,ws.hash_table);
|
|
wsd.num_words++;
|
|
} else
|
|
in_ptr+=3;
|
|
}
|
|
Free(in_start);
|
|
}
|
|
}
|
|
|
|
public U8 *WSDDefGet(U8 *st,I64 def_num=1)
|
|
{//MAlloc str holding single dict definition of word.
|
|
CFile *f;
|
|
CHashGeneric *temph;
|
|
U8 *result=NULL,*buf,*in_ptr,
|
|
*st2=MStrUtil(st,SUF_TO_UPPER);
|
|
temph=HashFind(st2,ws.hash_table,HTT_DICT_WORD);
|
|
Free(st2);
|
|
if (temph) {
|
|
if (f=FOpen(WSD_DEF_FILENAME,"r")) {
|
|
buf=MAlloc(WSD_BLK_SIZE*2+1);
|
|
buf[WSD_BLK_SIZE*2]=0; //terminate
|
|
FRBlks(f,buf,temph->user_data0*WSD_BLK_SIZE/BLK_SIZE,WSD_BLK_SIZE*2/BLK_SIZE);
|
|
FClose(f);
|
|
in_ptr=buf;
|
|
while (in_ptr<buf+WSD_BLK_SIZE*2) {
|
|
while (*in_ptr!=WSD_WORD_CHAR && in_ptr<buf+WSD_BLK_SIZE*2)
|
|
in_ptr++;
|
|
if (*in_ptr++==WSD_WORD_CHAR) {
|
|
if (!StrICmp(st,in_ptr)) {
|
|
while (def_num && *in_ptr!=WSD_WORD_CHAR
|
|
&& in_ptr<buf+WSD_BLK_SIZE*2) {
|
|
if (*in_ptr==WSD_DEF_CHAR) {
|
|
if (!--def_num)
|
|
break;
|
|
else
|
|
in_ptr++;
|
|
} else
|
|
in_ptr++;
|
|
}
|
|
if (*in_ptr++==WSD_DEF_CHAR) {
|
|
result=StrNew(in_ptr);
|
|
break;
|
|
}
|
|
}
|
|
}
|
|
}
|
|
Free(buf);
|
|
}
|
|
}
|
|
return result;
|
|
}
|
|
|
|
public U8 *WSDDefsGet(U8 *st)
|
|
{//MAlloc str with all dict definitions of word.
|
|
CFile *f;
|
|
CHashGeneric *temph;
|
|
U8 *result=NULL,*buf,*in_ptr,*in_ptr2,
|
|
*st2=MStrUtil(st,SUF_TO_UPPER);
|
|
temph=HashFind(st2,ws.hash_table,HTT_DICT_WORD);
|
|
Free(st2);
|
|
if (temph) {
|
|
if (f=FOpen(WSD_DEF_FILENAME,"r")) {
|
|
buf=MAlloc(WSD_BLK_SIZE*2+1);
|
|
buf[WSD_BLK_SIZE*2]=0; //terminate
|
|
FRBlks(f,buf,temph->user_data0*WSD_BLK_SIZE/BLK_SIZE,WSD_BLK_SIZE*2/BLK_SIZE);
|
|
FClose(f);
|
|
in_ptr=buf;
|
|
while (in_ptr<buf+WSD_BLK_SIZE*2) {
|
|
while (*in_ptr!=WSD_WORD_CHAR && in_ptr<buf+WSD_BLK_SIZE*2)
|
|
in_ptr++;
|
|
if (*in_ptr++==WSD_WORD_CHAR) {
|
|
if (!StrICmp(st,in_ptr)) {
|
|
in_ptr2=in_ptr;
|
|
in_ptr--;
|
|
while (*in_ptr2!=WSD_WORD_CHAR
|
|
&& in_ptr2<buf+WSD_BLK_SIZE*2) {
|
|
in_ptr2++;
|
|
}
|
|
result=MAlloc(in_ptr2+1-in_ptr);
|
|
MemCpy(result,in_ptr,in_ptr2-in_ptr);
|
|
result[in_ptr2-in_ptr]=WSD_END_CHAR;
|
|
break;
|
|
}
|
|
}
|
|
}
|
|
Free(buf);
|
|
}
|
|
}
|
|
return result;
|
|
}
|
|
|
|
/*Fmt of word lst entry:
|
|
U8 WSD_WORD_CHAR
|
|
U8 word[] with terminating zero
|
|
I16 block;
|
|
*/
|
|
public U8 *WSDWordPtAt(U8 *st)
|
|
{//Point to word in word list.
|
|
I64 i;
|
|
U8 *start=wsd.word_lst,*r=start,
|
|
*end=wsd.word_lst+wsd.word_lst_size;
|
|
if (!st || !*st)
|
|
return wsd.word_lst;
|
|
if (wsd.word_lst_size) {
|
|
while (start+3<end) {
|
|
r=(start+end)>>1;
|
|
while (TRUE) {
|
|
while (*r!=WSD_WORD_CHAR && r>wsd.word_lst)
|
|
r--;
|
|
if ((r[2]==WSD_WORD_CHAR||r[1]==WSD_WORD_CHAR)&&r-3>wsd.word_lst)
|
|
r--;
|
|
else
|
|
break;
|
|
}
|
|
if (*r==WSD_WORD_CHAR) {
|
|
i=StrICmp(st,r+1);
|
|
if (i<0)
|
|
end=r-1;
|
|
else if (i>0)
|
|
start=r+StrLen(r)+3;
|
|
else
|
|
return r;
|
|
} else
|
|
break;
|
|
}
|
|
r=(start+end)>>1;
|
|
while (TRUE) {
|
|
while (*r!=WSD_WORD_CHAR && r>wsd.word_lst)
|
|
r--;
|
|
if ((r[2]==WSD_WORD_CHAR||r[1]==WSD_WORD_CHAR)&&r-3>wsd.word_lst)
|
|
r--;
|
|
else
|
|
break;
|
|
}
|
|
if (*r==WSD_WORD_CHAR && StrICmp(st,r+1)>0)
|
|
r+=StrLen(r)+3;
|
|
}
|
|
if (*r==WSD_WORD_CHAR)
|
|
return r;
|
|
else
|
|
return wsd.word_lst;
|
|
}
|
|
|
|
U0 WSDDictWordsAdd(CDoc *doc,U8 *st=NULL)
|
|
{
|
|
I64 i;
|
|
U8 *ptr;
|
|
if (!st)
|
|
st=ws.cur_word;
|
|
if (st && (ptr=WSDWordPtAt(st))) {
|
|
for (i=0;i<WSD_MAX_FILLINS;i++) {
|
|
if (*ptr++!=WSD_WORD_CHAR)
|
|
break;
|
|
if (i)
|
|
DocPrint(doc,"\n");
|
|
wsd.fillins[i]=ptr-1;
|
|
DocPrint(doc,"'%d' %-23ts",i,ptr);
|
|
ptr+=StrLen(ptr)+3;
|
|
}
|
|
wsd.num_fillins=i;
|
|
}
|
|
}
|
|
|
|
U0 WSDFillin(I64 n)
|
|
{
|
|
U8 *s;
|
|
I64 len;
|
|
if (0<=n<wsd.num_fillins) {
|
|
s=wsd.fillins[n]+1;
|
|
len=StrLen(s);
|
|
if (len>ws.partial_len)
|
|
Auto(s+ws.partial_len);
|
|
}
|
|
}
|
|
|
|
public U0 WSDDefsPut(CDoc *doc=NULL,U8 *st,I64 num=-1)
|
|
{//Put to doc a dictionary definition(s) of a word.
|
|
U8 *st2,*st3;
|
|
I64 ch,i=0;
|
|
if (!st) return;
|
|
if (*st==WSD_WORD_CHAR)
|
|
st++;
|
|
DocPrint(doc,"$$WW,1$$$$RED$$%s:$$FG$$\n\n",st);
|
|
if (num<0) {
|
|
if (st3=WSDDefsGet(st)) {
|
|
st2=st3;
|
|
while (ch=*st2++) {
|
|
switch (ch) {
|
|
case WSD_WORD_CHAR:
|
|
break;
|
|
case WSD_DEF_CHAR:
|
|
DocPrint(doc,"$$GREEN$$(%d)$$FG$$ %s\n",
|
|
++i,st2);
|
|
break;
|
|
case WSD_PRONUNCIATION_CHAR:
|
|
DocPrint(doc,"$$LTGREEN$$%s$$FG$$\n",st2);
|
|
break;
|
|
case WSD_POS_CHAR:
|
|
DocPrint(doc,"$$BLACK$$%s$$FG$$\n",st2);
|
|
break;
|
|
case WSD_EXTRA_CHAR:
|
|
DocPrint(doc,"$$LTBLUE$$%s$$FG$$\n",st2);
|
|
break;
|
|
}
|
|
st2+=StrLen(st2)+1;
|
|
}
|
|
Free(st3);
|
|
}
|
|
} else {
|
|
while (st2=WSDDefGet(st,++i)) {
|
|
if (i==num)
|
|
DocPrint(doc,"$$GREEN$$(%d)$$FG$$ %s\n",
|
|
i,st2);
|
|
Free(st2);
|
|
}
|
|
}
|
|
}
|
|
|
|
U0 WSDPopUpDef(U8 *st,I64 num=-1,CTask *parent=NULL)
|
|
{
|
|
U8 *buf;
|
|
buf=MStrPrint("WSDDefsPut(DocPut,\"%s\",%d);View;",st,num);
|
|
PopUp(buf,parent);
|
|
Free(buf);
|
|
}
|
|
|
|
U0 WSDDef(I64 n,CTask *parent=NULL)
|
|
{
|
|
if (0<=n<wsd.num_fillins)
|
|
WSDPopUpDef(wsd.fillins[n],-1,parent);
|
|
}
|
|
|
|
U0 WSFindMisspelled(CDoc *doc)
|
|
{
|
|
Bool unlock=DocLock(doc);
|
|
CDocEntry *doc_e=doc->cur_entry;
|
|
I64 col=doc->cur_data_col,col2,ch;
|
|
do {
|
|
if (doc_e!=doc && doc_e->de_flags&DOCEF_TAG) {
|
|
while (col<doc_e->max_col) {
|
|
while (col<doc_e->max_col && !Bt(chars_bitmap_word,doc_e->tag[col]))
|
|
col++;
|
|
if (col<doc_e->max_col) {
|
|
col2=col;
|
|
while (col2<doc_e->max_col && Bt(chars_bitmap_word,doc_e->tag[col2]))
|
|
col2++;
|
|
ch=doc_e->tag[col2];
|
|
doc_e->tag[col2]=0;
|
|
if (StrICmp(&doc_e->tag[col],WSDWordPtAt(&doc_e->tag[col])+1)) {
|
|
doc_e->tag[col2]=ch;
|
|
doc->cur_entry=doc_e;
|
|
doc->cur_data_col=col;
|
|
goto fm_done;
|
|
}
|
|
doc_e->tag[col2]=ch;
|
|
col=col2;
|
|
}
|
|
}
|
|
}
|
|
doc_e=doc_e->next;
|
|
col=doc_e->min_col;
|
|
} while (doc_e!=doc->cur_entry);
|
|
fm_done:
|
|
if (unlock)
|
|
DocUnlock(doc);
|
|
}
|