organicmaps/icu
13
Fork 0
mirror of https://github.com/unicode-org/icu.git synced 2025-04-21 12:40:02 +00:00
Code Issues 1 Projects Releases Wiki Activity Actions 1

ICU-1930 read some of the indirect values from the UCA

Browse source 
X-SVN-Rev: 8879
This commit is contained in:
Vladimir Weinstein 2002-06-13 18:32:38 +00:00
parent ff40ad6613
commit 293c766940
1 changed files with 56 additions and 46 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

102
icu4c/source/i18n/ucol_tok.cpp
View file

@ -90,6 +90,53 @@ uhash_freeBlockWrapper(void *obj) {
uhash_freeBlock(obj);
}
typedef struct {
uint32_t startCE;
uint32_t startContCE;
uint32_t limitCE;
uint32_t limitContCE;
} indirectBoundaries;
/* these values are used for finding CE values for indirect positioning. */
/* Indirect positioning is a mechanism for allowing resets on symbolic */
/* values. It only works for resets and you cannot tailor indirect names */
/* An indirect name can define either an anchor point or a range. An */
/* anchor point behaves in exactly the same way as a code point in reset */
/* would, except that it cannot be tailored. A range (we currently only */
/* know for the [top] range will explicitly set the upper bound for */
/* generated CEs, thus allowing for better control over how many CEs can */
/* be squeezed between in the range without performance penalty. */
/* In that respect, we use [top] for tailoring of locales that use CJK */
/* characters. Other indirect values are currently a pure convenience, */
/* they can be used to assure that the CEs will be always positioned in */
/* the same place relative to a point with known properties (e.g. first */
/* primary ignorable). */
static indirectBoundaries ucolIndirectBoundaries[11] = {
{ UCOL_RESET_TOP_VALUE, 0,
UCOL_NEXT_TOP_VALUE, 0 },
{ UCOL_FIRST_PRIMARY_IGNORABLE, 0,
0, 0 },
{ UCOL_LAST_PRIMARY_IGNORABLE, UCOL_LAST_PRIMARY_IGNORABLE_CONT,
0, 0 },
{ UCOL_FIRST_SECONDARY_IGNORABLE, 0,
0, 0 },
{ UCOL_LAST_SECONDARY_IGNORABLE, 0,
0, 0 },
{ UCOL_FIRST_TERTIARY_IGNORABLE, 0,
0, 0 },
{ UCOL_LAST_TERTIARY_IGNORABLE, 0,
0, 0 },
{ UCOL_FIRST_VARIABLE, 0,
0, 0 },
{ UCOL_LAST_VARIABLE, 0,
0, 0 },
{ UCOL_FIRST_NON_VARIABLE, 0,
0, 0 },
{ UCOL_LAST_NON_VARIABLE, 0,
0, 0 },
};
void ucol_tok_initTokenList(UColTokenParser *src, const UChar *rules, const uint32_t rulesLength, UCollator *UCA, UErrorCode *status) {
uint32_t nSize = 0;
uint32_t estimatedSize = (2*rulesLength+UCOL_TOK_EXTRA_RULE_SPACE_SIZE);
@ -143,6 +190,15 @@ void ucol_tok_initTokenList(UColTokenParser *src, const UChar *rules, const uint
src->lh = 0;
src->lh = (UColTokListHeader *)uprv_malloc(512*sizeof(UColTokListHeader));
src->resultLen = 0;
UCAConstants *consts = (UCAConstants *)((uint8_t *)src->UCA->image + src->UCA->image->UCAConsts);
// Set values for the top - TODO: once we have values for all the indirects, we are going
// to initalize here.
ucolIndirectBoundaries[0].startCE = consts->UCA_RESET_TOP_VALUE;
ucolIndirectBoundaries[0].startContCE = 0;
ucolIndirectBoundaries[0].limitCE = consts->UCA_NEXT_TOP_VALUE;
ucolIndirectBoundaries[0].limitContCE = 0;
}
static inline
@ -201,52 +257,6 @@ void ucol_uprv_tok_setOptionInImage(UColOptionSet *opts, UColAttribute attrib, U
}
}
typedef struct {
uint32_t startCE;
uint32_t startContCE;
uint32_t limitCE;
uint32_t limitContCE;
} indirectBoundaries;
/* these values are used for finding CE values for indirect positioning. */
/* Indirect positioning is a mechanism for allowing resets on symbolic */
/* values. It only works for resets and you cannot tailor indirect names */
/* An indirect name can define either an anchor point or a range. An */
/* anchor point behaves in exactly the same way as a code point in reset */
/* would, except that it cannot be tailored. A range (we currently only */
/* know for the [top] range will explicitly set the upper bound for */
/* generated CEs, thus allowing for better control over how many CEs can */
/* be squeezed between in the range without performance penalty. */
/* In that respect, we use [top] for tailoring of locales that use CJK */
/* characters. Other indirect values are currently a pure convenience, */
/* they can be used to assure that the CEs will be always positioned in */
/* the same place relative to a point with known properties (e.g. first */
/* primary ignorable). */
static const indirectBoundaries ucolIndirectBoundaries[] = {
{ UCOL_RESET_TOP_VALUE, 0,
UCOL_NEXT_TOP_VALUE, 0 },
{ UCOL_FIRST_PRIMARY_IGNORABLE, 0,
0, 0 },
{ UCOL_LAST_PRIMARY_IGNORABLE, UCOL_LAST_PRIMARY_IGNORABLE_CONT,
0, 0 },
{ UCOL_FIRST_SECONDARY_IGNORABLE, 0,
0, 0 },
{ UCOL_LAST_SECONDARY_IGNORABLE, 0,
0, 0 },
{ UCOL_FIRST_TERTIARY_IGNORABLE, 0,
0, 0 },
{ UCOL_LAST_TERTIARY_IGNORABLE, 0,
0, 0 },
{ UCOL_FIRST_VARIABLE, 0,
0, 0 },
{ UCOL_LAST_VARIABLE, 0,
0, 0 },
{ UCOL_FIRST_NON_VARIABLE, 0,
0, 0 },
{ UCOL_LAST_NON_VARIABLE, 0,
0, 0 },
};
#define UTOK_OPTION_COUNT 17
static UBool didInit = FALSE;