// Use roundtrips, "good one-way" mappings, and some normal fallbacks.
static inline UBool
extFromUUseMapping(UBool useFallback, uint32_t value, UChar32 firstCP) {
return
((value&UCNV_EXT_FROM_U_STATUS_MASK)!=0 ||
FROM_U_USE_FALLBACK(useFallback, firstCP)) &&
(value&UCNV_EXT_FROM_U_RESERVED_MASK)==0;
}
/*
* @param cx pointer to extension data; if NULL, returns 0
* @param firstCP the first code point before all the other UChars
* @param pre UChars that must match; !initialMatch: partial match with them
* @param preLength length of pre, >=0
* @param src UChars that can be used to complete a match
* @param srcLength length of src, >=0
* @param pMatchValue [out] output result value for the match from the data structure
* @param useFallback "use fallback" flag, usually from cnv->useFallback
* @param flush TRUE if the end of the input stream is reached
* @return >1: matched, return value=total match length (number of input units matched)
* 1: matched, no mapping but request for <subchar1>
* (only for the first code point)
* 0: no match
* <0: partial match, return value=negative total match length
* (partial matches are never returned for flush==TRUE)
* (partial matches are never returned as being longer than UCNV_EXT_MAX_UCHARS)
* the matchLength is 2 if only firstCP matched, and >2 if firstCP and
* further code units matched
*/
static int32_t
ucnv_extMatchFromU(const int32_t *cx,
UChar32 firstCP,
const UChar *pre, int32_t preLength,
const UChar *src, int32_t srcLength,
uint32_t *pMatchValue,
UBool useFallback, UBool flush) {
const uint16_t *stage12, *stage3;
const uint32_t *stage3b;
const UChar *fromUTableUChars, *fromUSectionUChars;
const uint32_t *fromUTableValues, *fromUSectionValues;
uint32_t value, matchValue;
int32_t i, j, index, length, matchLength;
UChar c;
if(cx==NULL) {
return 0; /* no extension data, no match */
}
/* trie lookup of firstCP */
index=firstCP>>10; /* stage 1 index */
if(index>=cx[UCNV_EXT_FROM_U_STAGE_1_LENGTH]) {
return 0; /* the first code point is outside the trie */
}
stage12=UCNV_EXT_ARRAY(cx, UCNV_EXT_FROM_U_STAGE_12_INDEX, uint16_t);
stage3=UCNV_EXT_ARRAY(cx, UCNV_EXT_FROM_U_STAGE_3_INDEX, uint16_t);
index=UCNV_EXT_FROM_U(stage12, stage3, index, firstCP);
stage3b=UCNV_EXT_ARRAY(cx, UCNV_EXT_FROM_U_STAGE_3B_INDEX, uint32_t);
value=stage3b[index];
if(value==0) {
return 0;
}
if(UCNV_EXT_TO_U_IS_PARTIAL(value)) {
/* partial match, enter the loop below */
index=(int32_t)UCNV_EXT_FROM_U_GET_PARTIAL_INDEX(value);
/* initialize */
fromUTableUChars=UCNV_EXT_ARRAY(cx, UCNV_EXT_FROM_U_UCHARS_INDEX, UChar);
fromUTableValues=UCNV_EXT_ARRAY(cx, UCNV_EXT_FROM_U_VALUES_INDEX, uint32_t);
matchValue=0;
i=j=matchLength=0;
/* we must not remember fallback matches when not using fallbacks */
/* match input units until there is a full match or the input is consumed */
for(;;) {
/* go to the next section */
fromUSectionUChars=fromUTableUChars+index;
fromUSectionValues=fromUTableValues+index;
/* read first pair of the section */
length=*fromUSectionUChars++;
value=*fromUSectionValues++;
if( value!=0 &&
(UCNV_EXT_FROM_U_IS_ROUNDTRIP(value) ||
FROM_U_USE_FALLBACK(useFallback, firstCP))
) {
/* remember longest match so far */
matchValue=value;
matchLength=2+i+j;
}
/* match pre[] then src[] */
if(i<preLength) {
c=pre[i++];
} else if(j<srcLength) {
c=src[j++];
} else {
/* all input consumed, partial match */
if(flush || (length=(i+j))>UCNV_EXT_MAX_UCHARS) {
/*
* end of the entire input stream, stop with the longest match so far
* or: partial match must not be longer than UCNV_EXT_MAX_UCHARS
* because it must fit into state buffers
*/
break;
} else {
/* continue with more input next time */
return -(2+length);
}
}
/* search for the current UChar */
index=ucnv_extFindFromU(fromUSectionUChars, length, c);
if(index<0) {
/* no match here, stop with the longest match so far */
break;
} else {
value=fromUSectionValues[index];
if(UCNV_EXT_FROM_U_IS_PARTIAL(value)) {
/* partial match, continue */
index=(int32_t)UCNV_EXT_FROM_U_GET_PARTIAL_INDEX(value);
} else {
if( UCNV_EXT_FROM_U_IS_ROUNDTRIP(value) ||
FROM_U_USE_FALLBACK(useFallback, firstCP)
) {
/* full match, stop with result */
matchValue=value;
matchLength=2+i+j;
} else {
/* full match on fallback not taken, stop with the longest match so far */
}
break;
}
}
}
if(matchLength==0) {
/* no match at all */
return 0;
}
} else /* result from firstCP trie lookup */ {
if( UCNV_EXT_FROM_U_IS_ROUNDTRIP(value) ||
FROM_U_USE_FALLBACK(useFallback, firstCP)
) {
/* full match, stop with result */
matchValue=value;
matchLength=2;
} else {
/* fallback not taken */
return 0;
}
}
if(matchValue&UCNV_EXT_FROM_U_RESERVED_MASK) {
/* do not interpret values with reserved bits used, for forward compatibility */
return 0;
}
/* return result */
if(matchValue==UCNV_EXT_FROM_U_SUBCHAR1) {
return 1; /* assert matchLength==2 */
}
*pMatchValue=UCNV_EXT_FROM_U_MASK_ROUNDTRIP(matchValue);
return matchLength;
}
