AuroraMiddleware/scuffed-code
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

ICU-13234 collect string & character options bits in new stringoptions.h

Browse Source 
X-SVN-Rev: 40162
This commit is contained in:
Markus Scherer 2017-06-08 20:35:40 +00:00
parent 3975adb564
commit 06a03303cb
10 changed files with 140 additions and 128 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
icu4c/source/common/normalizer2impl.cpp
View File

@ -23,7 +23,7 @@
#include "unicode/bytestream.h"
#include "unicode/edits.h"
#include "unicode/normalizer2.h"
#include "unicode/ucasemap.h" // U_OMIT_UNCHANGED_TEXT
#include "unicode/stringoptions.h"
#include "unicode/udata.h"
#include "unicode/ustring.h"
#include "unicode/utf16.h"

4
icu4c/source/common/ucase.h
View File

@ -61,7 +61,7 @@ enum {
/**
* Bit mask for getting just the options from a string compare options word
* that are relevant for case-insensitive string comparison.
* See uchar.h. Also include _STRNCMP_STYLE and U_COMPARE_CODE_POINT_ORDER.
* See stringoptions.h. Also include _STRNCMP_STYLE and U_COMPARE_CODE_POINT_ORDER.
* @internal
*/
#define _STRCASECMP_OPTIONS_MASK 0xffff
@ -69,7 +69,7 @@ enum {
/**
* Bit mask for getting just the options from a string compare options word
* that are relevant for case folding (of a single string or code point).
* See uchar.h.
* See stringoptions.h.
* @internal
*/
#define _FOLD_CASE_OPTIONS_MASK 0xff

9
icu4c/source/common/ucasemap_imp.h
View File

@ -11,15 +11,6 @@
#include "unicode/ucasemap.h"
#include "ucase.h"
#ifndef U_COMPARE_IGNORE_CASE
/* see also unorm.h */
/**
* Option bit for unorm_compare:
* Perform case-insensitive comparison.
*/
#define U_COMPARE_IGNORE_CASE 0x10000
#endif
/**
* Internal API, used by u_strcasecmp() etc.
* Compare strings case-insensitively,

133
icu4c/source/common/unicode/stringoptions.h Normal file
View File

@ -0,0 +1,133 @@
// © 2017 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
// stringoptions.h
// created: 2017jun08 Markus W. Scherer
#ifndef __STRINGOPTIONS_H__
#define __STRINGOPTIONS_H__
#include "unicode/utypes.h"
/**
* \file
* \brief C API: Bit set option bit constants for various string and character processing functions.
*/
/**
* Option value for case folding: Use default mappings defined in CaseFolding.txt.
*
* @stable ICU 2.0
*/
#define U_FOLD_CASE_DEFAULT 0
/**
* Option value for case folding:
*
* Use the modified set of mappings provided in CaseFolding.txt to handle dotted I
* and dotless i appropriately for Turkic languages (tr, az).
*
* Before Unicode 3.2, CaseFolding.txt contains mappings marked with 'I' that
* are to be included for default mappings and
* excluded for the Turkic-specific mappings.
*
* Unicode 3.2 CaseFolding.txt instead contains mappings marked with 'T' that
* are to be excluded for default mappings and
* included for the Turkic-specific mappings.
*
* @stable ICU 2.0
*/
#define U_FOLD_CASE_EXCLUDE_SPECIAL_I 1
/**
* Do not lowercase non-initial parts of words when titlecasing.
* Option bit for titlecasing APIs that take an options bit set.
*
* By default, titlecasing will titlecase the first cased character
* of a word and lowercase all other characters.
* With this option, the other characters will not be modified.
*
* @see ucasemap_setOptions
* @see ucasemap_toTitle
* @see ucasemap_utf8ToTitle
* @see UnicodeString::toTitle
* @stable ICU 3.8
*/
#define U_TITLECASE_NO_LOWERCASE 0x100
/**
* Do not adjust the titlecasing indexes from BreakIterator::next() indexes;
* titlecase exactly the characters at breaks from the iterator.
* Option bit for titlecasing APIs that take an options bit set.
*
* By default, titlecasing will take each break iterator index,
* adjust it by looking for the next cased character, and titlecase that one.
* Other characters are lowercased.
*
* This follows Unicode 4 & 5 section 3.13 Default Case Operations:
*
* R3 toTitlecase(X): Find the word boundaries based on Unicode Standard Annex
* #29, "Text Boundaries." Between each pair of word boundaries, find the first
* cased character F. If F exists, map F to default_title(F); then map each
* subsequent character C to default_lower(C).
*
* @see ucasemap_setOptions
* @see ucasemap_toTitle
* @see ucasemap_utf8ToTitle
* @see UnicodeString::toTitle
* @see U_TITLECASE_NO_LOWERCASE
* @stable ICU 3.8
*/
#define U_TITLECASE_NO_BREAK_ADJUSTMENT 0x200
#ifndef U_HIDE_DRAFT_API
/**
* Omit unchanged text when recording how source substrings
* relate to changed and unchanged result substrings.
* Used for example in some case-mapping and normalization functions.
*
* @see CaseMap
* @see Edits
* @see Normalizer2
* @draft ICU 60
*/
#define U_OMIT_UNCHANGED_TEXT 0x4000
#endif // U_HIDE_DRAFT_API
/**
* Option bit for u_strCaseCompare, u_strcasecmp, unorm_compare, etc:
* Compare strings in code point order instead of code unit order.
* @stable ICU 2.2
*/
#define U_COMPARE_CODE_POINT_ORDER 0x8000
/**
* Option bit for unorm_compare:
* Perform case-insensitive comparison.
* @stable ICU 2.2
*/
#define U_COMPARE_IGNORE_CASE 0x10000
/**
* Option bit for unorm_compare:
* Both input strings are assumed to fulfill FCD conditions.
* @stable ICU 2.2
*/
#define UNORM_INPUT_IS_FCD 0x20000
// Related definitions elsewhere.
// Options that are not meaningful in the same functions
// can share the same bits.
//
// Public:
// unicode/unorm.h #define UNORM_COMPARE_NORM_OPTIONS_SHIFT 20
//
// Internal: (may change or be removed)
// ucase.h #define _STRCASECMP_OPTIONS_MASK 0xffff
// ucase.h #define _FOLD_CASE_OPTIONS_MASK 0xff
// ustr_imp.h #define _STRNCMP_STYLE 0x1000
// unormcmp.cpp #define _COMPARE_EQUIV 0x80000
#endif // __STRINGOPTIONS_H__

51
icu4c/source/common/unicode/ucasemap.h
View File

@ -23,6 +23,7 @@
#include "unicode/utypes.h"
#include "unicode/localpointer.h"
#include "unicode/stringoptions.h"
#include "unicode/ustring.h"
/**
@ -144,56 +145,6 @@ ucasemap_setLocale(UCaseMap *csm, const char *locale, UErrorCode *pErrorCode);
U_STABLE void U_EXPORT2
ucasemap_setOptions(UCaseMap *csm, uint32_t options, UErrorCode *pErrorCode);
/**
* Do not lowercase non-initial parts of words when titlecasing.
* Option bit for titlecasing APIs that take an options bit set.
*
* By default, titlecasing will titlecase the first cased character
* of a word and lowercase all other characters.
* With this option, the other characters will not be modified.
*
* @see ucasemap_setOptions
* @see ucasemap_toTitle
* @see ucasemap_utf8ToTitle
* @see UnicodeString::toTitle
* @stable ICU 3.8
*/
#define U_TITLECASE_NO_LOWERCASE 0x100
/**
* Do not adjust the titlecasing indexes from BreakIterator::next() indexes;
* titlecase exactly the characters at breaks from the iterator.
* Option bit for titlecasing APIs that take an options bit set.
*
* By default, titlecasing will take each break iterator index,
* adjust it by looking for the next cased character, and titlecase that one.
* Other characters are lowercased.
*
* This follows Unicode 4 & 5 section 3.13 Default Case Operations:
*
* R3 toTitlecase(X): Find the word boundaries based on Unicode Standard Annex
* #29, "Text Boundaries." Between each pair of word boundaries, find the first
* cased character F. If F exists, map F to default_title(F); then map each
* subsequent character C to default_lower(C).
*
* @see ucasemap_setOptions
* @see ucasemap_toTitle
* @see ucasemap_utf8ToTitle
* @see UnicodeString::toTitle
* @see U_TITLECASE_NO_LOWERCASE
* @stable ICU 3.8
*/
#define U_TITLECASE_NO_BREAK_ADJUSTMENT 0x200
/**
* Omit unchanged text when case-mapping or normalizing with Edits.
*
* @see CaseMap
* @see Edits
* @draft ICU 60
*/
#define U_OMIT_UNCHANGED_TEXT 0x4000
#if !UCONFIG_NO_BREAK_ITERATION
/**

22
icu4c/source/common/unicode/uchar.h
View File

@ -26,6 +26,7 @@
#define UCHAR_H
#include "unicode/utypes.h"
#include "unicode/stringoptions.h"
U_CDECL_BEGIN
@ -3569,27 +3570,6 @@ u_toupper(UChar32 c);
U_STABLE UChar32 U_EXPORT2
u_totitle(UChar32 c);
/** Option value for case folding: use default mappings defined in CaseFolding.txt. @stable ICU 2.0 */
#define U_FOLD_CASE_DEFAULT 0
/**
* Option value for case folding:
*
* Use the modified set of mappings provided in CaseFolding.txt to handle dotted I
* and dotless i appropriately for Turkic languages (tr, az).
*
* Before Unicode 3.2, CaseFolding.txt contains mappings marked with 'I' that
* are to be included for default mappings and
* excluded for the Turkic-specific mappings.
*
* Unicode 3.2 CaseFolding.txt instead contains mappings marked with 'T' that
* are to be excluded for default mappings and
* included for the Turkic-specific mappings.
*
* @stable ICU 2.0
*/
#define U_FOLD_CASE_EXCLUDE_SPECIAL_I 1
/**
* The given character is mapped to its case folding equivalent according to
* UnicodeData.txt and CaseFolding.txt;

10
icu4c/source/common/unicode/unistr.h
View File

@ -38,16 +38,6 @@
struct UConverter; // unicode/ucnv.h
#ifndef U_COMPARE_CODE_POINT_ORDER
/* see also ustring.h and unorm.h */
/**
* Option bit for u_strCaseCompare, u_strcasecmp, unorm_compare, etc:
* Compare strings in code point order instead of code unit order.
* @stable ICU 2.2
*/
#define U_COMPARE_CODE_POINT_ORDER 0x8000
#endif
#ifndef USTRING_H
/**
* \ingroup ustring_ustrlen

25
icu4c/source/common/unicode/unorm2.h
View File

@ -32,6 +32,7 @@
#include "unicode/utypes.h"
#include "unicode/localpointer.h"
#include "unicode/stringoptions.h"
#include "unicode/uset.h"
/**
@ -526,30 +527,6 @@ unorm2_hasBoundaryAfter(const UNormalizer2 *norm2, UChar32 c);
U_STABLE UBool U_EXPORT2
unorm2_isInert(const UNormalizer2 *norm2, UChar32 c);
/**
* Option bit for unorm_compare:
* Both input strings are assumed to fulfill FCD conditions.
* @stable ICU 2.2
*/
#define UNORM_INPUT_IS_FCD 0x20000
/**
* Option bit for unorm_compare:
* Perform case-insensitive comparison.
* @stable ICU 2.2
*/
#define U_COMPARE_IGNORE_CASE 0x10000
#ifndef U_COMPARE_CODE_POINT_ORDER
/* see also unistr.h and ustring.h */
/**
* Option bit for u_strCaseCompare, u_strcasecmp, unorm_compare, etc:
* Compare strings in code point order instead of code unit order.
* @stable ICU 2.2
*/
#define U_COMPARE_CODE_POINT_ORDER 0x8000
#endif
/**
* Compares two strings for canonical equivalence.
* Further options include case-insensitive comparison and

10
icu4c/source/common/unicode/ustring.h
View File

@ -497,16 +497,6 @@ u_strCompare(const UChar *s1, int32_t length1,
U_STABLE int32_t U_EXPORT2
u_strCompareIter(UCharIterator *iter1, UCharIterator *iter2, UBool codePointOrder);
#ifndef U_COMPARE_CODE_POINT_ORDER
/* see also unistr.h and unorm.h */
/**
* Option bit for u_strCaseCompare, u_strcasecmp, unorm_compare, etc:
* Compare strings in code point order instead of code unit order.
* @stable ICU 2.2
*/
#define U_COMPARE_CODE_POINT_ORDER 0x8000
#endif
/**
* Compare two strings case-insensitively using full case folding.
* This is equivalent to

2
icu4c/source/test/intltest/tstnorm.cpp
View File

@ -13,7 +13,7 @@
#include "unicode/uchar.h"
#include "unicode/errorcode.h"
#include "unicode/normlzr.h"
#include "unicode/ucasemap.h" // U_OMIT_UNCHANGED_TEXT
#include "unicode/stringoptions.h"
#include "unicode/uniset.h"
#include "unicode/usetiter.h"
#include "unicode/schriter.h"