openharmony/interface_sdk_c
1
0
Fork 0
mirror of https://github.com/openharmony/interface_sdk_c.git synced 2026-08-26 18:56:40 -04:00
Code Issues Packages Projects Releases Wiki Activity

!375 ICU4C提供为C API

Browse Source 
Merge pull request !375 from 罗博明/master
This commit is contained in:
openharmony_ci
2024-03-15 10:24:38 +00:00
committed by Gitee
parent d8d75c25f6 8fd7779636
commit 6ab6f8a1c6
20 changed files with 19072 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
third_party/icu4c/BUILD.gn
Vendored
+36
View File
@@ -20,13 +20,31 @@ ohos_ndk_library("libicu_ndk") {
output_name = "icu"
system_capability = "SystemCapability.Global.I18n"
system_capability_headers = [
"unicode/parseerr.h",
"unicode/platform.h",
"unicode/ptypes.h",
"unicode/stringoptions.h",
"unicode/ubidi.h",
"unicode/ubrk.h",
"unicode/ucal.h",
"unicode/uchar.h",
"unicode/ucnv.h",
"unicode/ucnv_err.h",
"unicode/ucol.h",
"unicode/uconfig.h",
"unicode/udat.h",
"unicode/udisplaycontext.h",
"unicode/uenum.h",
"unicode/ufieldpositer.h",
"unicode/uloc.h",
"unicode/umachine.h",
"unicode/umisc.h",
"unicode/unorm2.h",
"unicode/unum.h",
"unicode/unumberformatter.h",
"unicode/uscript.h",
"unicode/uset.h",
"unicode/utrans.h",
"unicode/utypes.h",
]
output_extension = "so"
@@ -35,13 +53,31 @@ ohos_ndk_library("libicu_ndk") {
ohos_ndk_headers("icu_unicode_header") {
dest_dir = "$ndk_headers_out_dir/unicode"
sources = [
"ndk_headers/unicode/parseerr.h",
"ndk_headers/unicode/platform.h",
"ndk_headers/unicode/ptypes.h",
"ndk_headers/unicode/stringoptions.h",
"ndk_headers/unicode/ubidi.h",
"ndk_headers/unicode/ubrk.h",
"ndk_headers/unicode/ucal.h",
"ndk_headers/unicode/uchar.h",
"ndk_headers/unicode/ucnv.h",
"ndk_headers/unicode/ucnv_err.h",
"ndk_headers/unicode/ucol.h",
"ndk_headers/unicode/uconfig.h",
"ndk_headers/unicode/udat.h",
"ndk_headers/unicode/udisplaycontext.h",
"ndk_headers/unicode/uenum.h",
"ndk_headers/unicode/ufieldpositer.h",
"ndk_headers/unicode/uloc.h",
"ndk_headers/unicode/umachine.h",
"ndk_headers/unicode/umisc.h",
"ndk_headers/unicode/unorm2.h",
"ndk_headers/unicode/unum.h",
"ndk_headers/unicode/unumberformatter.h",
"ndk_headers/unicode/uscript.h",
"ndk_headers/unicode/uset.h",
"ndk_headers/unicode/utrans.h",
"ndk_headers/unicode/utypes.h",
]
}
third_party/icu4c/libicu.ndk.json
Vendored
+1524
View File
File diff suppressed because it is too large Load Diff
third_party/icu4c/ndk_headers/unicode/parseerr.h
Vendored
+92
View File
@@ -0,0 +1,92 @@
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
**********************************************************************
* Copyright (C) 1999-2005, International Business Machines
* Corporation and others. All Rights Reserved.
**********************************************************************
* Date Name Description
* 03/14/00 aliu Creation.
* 06/27/00 aliu Change from C++ class to C struct
**********************************************************************
*/
#ifndef PARSEERR_H
#define PARSEERR_H
#include "unicode/utypes.h"
/**
* \file
* \brief C API: Parse Error Information
*/
/**
* The capacity of the context strings in UParseError.
* @stable ICU 2.0
*/
enum { U_PARSE_CONTEXT_LEN = 16 };
/**
* A UParseError struct is used to returned detailed information about
* parsing errors. It is used by ICU parsing engines that parse long
* rules, patterns, or programs, where the text being parsed is long
* enough that more information than a UErrorCode is needed to
* localize the error.
*
* <p>The line, offset, and context fields are optional; parsing
* engines may choose not to use to use them.
*
* <p>The preContext and postContext strings include some part of the
* context surrounding the error. If the source text is "let for=7"
* and "for" is the error (e.g., because it is a reserved word), then
* some examples of what a parser might produce are the following:
*
* <pre>
* preContext postContext
* "" "" The parser does not support context
* "let " "=7" Pre- and post-context only
* "let " "for=7" Pre- and post-context and error text
* "" "for" Error text only
* </pre>
*
* <p>Examples of engines which use UParseError (or may use it in the
* future) are Transliterator, RuleBasedBreakIterator, and
* RegexPattern.
*
* @stable ICU 2.0
*/
typedef struct UParseError {
/**
* The line on which the error occurred. If the parser uses this
* field, it sets it to the line number of the source text line on
* which the error appears, which will be a value >= 1. If the
* parse does not support line numbers, the value will be <= 0.
* @stable ICU 2.0
*/
int32_t line;
/**
* The character offset to the error. If the line field is >= 1,
* then this is the offset from the start of the line. Otherwise,
* this is the offset from the start of the text. If the parser
* does not support this field, it will have a value < 0.
* @stable ICU 2.0
*/
int32_t offset;
/**
* Textual context before the error. Null-terminated. The empty
* string if not supported by parser.
* @stable ICU 2.0
*/
UChar preContext[U_PARSE_CONTEXT_LEN];
/**
* The error itself and/or textual context after the error.
* Null-terminated. The empty string if not supported by parser.
* @stable ICU 2.0
*/
UChar postContext[U_PARSE_CONTEXT_LEN];
} UParseError;
#endif
third_party/icu4c/ndk_headers/unicode/stringoptions.h
Vendored
+190
View File
@@ -0,0 +1,190 @@
// © 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
/**
* Titlecase the string as a whole rather than each word.
* (Titlecase only the character at index 0, possibly adjusted.)
* Option bits value for titlecasing APIs that take an options bit set.
*
* It is an error to specify multiple titlecasing iterator options together,
* including both an options bit and an explicit BreakIterator.
*
* @see U_TITLECASE_ADJUST_TO_CASED
* @stable ICU 60
*/
#define U_TITLECASE_WHOLE_STRING 0x20
/**
* Titlecase sentences rather than words.
* (Titlecase only the first character of each sentence, possibly adjusted.)
* Option bits value for titlecasing APIs that take an options bit set.
*
* It is an error to specify multiple titlecasing iterator options together,
* including both an options bit and an explicit BreakIterator.
*
* @see U_TITLECASE_ADJUST_TO_CASED
* @stable ICU 60
*/
#define U_TITLECASE_SENTENCES 0x40
/**
* 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 character at each
* (possibly adjusted) BreakIterator index and
* lowercase all other characters up to the next iterator index.
* With this option, the other characters will not be modified.
*
* @see U_TITLECASE_ADJUST_TO_CASED
* @see UnicodeString::toTitle
* @see CaseMap::toTitle
* @see ucasemap_setOptions
* @see ucasemap_toTitle
* @see ucasemap_utf8ToTitle
* @stable ICU 3.8
*/
#define U_TITLECASE_NO_LOWERCASE 0x100
/**
* Do not adjust the titlecasing BreakIterator 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 to the next relevant character (see U_TITLECASE_ADJUST_TO_CASED),
* and titlecase that one.
*
* Other characters are lowercased.
*
* It is an error to specify multiple titlecasing adjustment options together.
*
* @see U_TITLECASE_ADJUST_TO_CASED
* @see U_TITLECASE_NO_LOWERCASE
* @see UnicodeString::toTitle
* @see CaseMap::toTitle
* @see ucasemap_setOptions
* @see ucasemap_toTitle
* @see ucasemap_utf8ToTitle
* @stable ICU 3.8
*/
#define U_TITLECASE_NO_BREAK_ADJUSTMENT 0x200
/**
* Adjust each titlecasing BreakIterator index to the next cased character.
* (See the Unicode Standard, chapter 3, Default Case Conversion, R3 toTitlecase(X).)
* Option bit for titlecasing APIs that take an options bit set.
*
* This used to be the default index adjustment in ICU.
* Since ICU 60, the default index adjustment is to the next character that is
* a letter, number, symbol, or private use code point.
* (Uncased modifier letters are skipped.)
* The difference in behavior is small for word titlecasing,
* but the new adjustment is much better for whole-string and sentence titlecasing:
* It yields "49ers" and "«丰(abc)»" instead of "49Ers" and "«丰(Abc)»".
*
* It is an error to specify multiple titlecasing adjustment options together.
*
* @see U_TITLECASE_NO_BREAK_ADJUSTMENT
* @stable ICU 60
*/
#define U_TITLECASE_ADJUST_TO_CASED 0x400
/**
* Option for string transformation functions to not first reset the Edits object.
* Used for example in some case-mapping and normalization functions.
*
* @see CaseMap
* @see Edits
* @see Normalizer2
* @stable ICU 60
*/
#define U_EDITS_NO_RESET 0x2000
/**
* 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
* @stable ICU 60
*/
#define U_OMIT_UNCHANGED_TEXT 0x4000
/**
* 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 7
// ucasemap_imp.h #define U_TITLECASE_ITERATOR_MASK 0xe0
// ucasemap_imp.h #define U_TITLECASE_ADJUSTMENT_MASK 0x600
// ustr_imp.h #define _STRNCMP_STYLE 0x1000
// unormcmp.cpp #define _COMPARE_EQUIV 0x80000
#endif // __STRINGOPTIONS_H__
third_party/icu4c/ndk_headers/unicode/ubidi.h
Vendored
+2191
View File
File diff suppressed because it is too large Load Diff
third_party/icu4c/ndk_headers/unicode/ubrk.h
Vendored
+534
View File
@@ -0,0 +1,534 @@
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
******************************************************************************
* Copyright (C) 1996-2015, International Business Machines Corporation and others.
* All Rights Reserved.
******************************************************************************
*/
#ifndef UBRK_H
#define UBRK_H
#include "unicode/utypes.h"
#include "unicode/uloc.h"
#if U_SHOW_CPLUSPLUS_API
#include "unicode/localpointer.h"
#endif // U_SHOW_CPLUSPLUS_API
/**
* A text-break iterator.
* For usage in C programs.
*/
#ifndef UBRK_TYPEDEF_UBREAK_ITERATOR
# define UBRK_TYPEDEF_UBREAK_ITERATOR
/**
* Opaque type representing an ICU Break iterator object.
* @stable ICU 2.0
*/
typedef struct UBreakIterator UBreakIterator;
#endif
#if !UCONFIG_NO_BREAK_ITERATION
/**
* \file
* \brief C API: BreakIterator
*
* <h2> BreakIterator C API </h2>
*
* The BreakIterator C API defines methods for finding the location
* of boundaries in text. Pointer to a UBreakIterator maintain a
* current position and scan over text returning the index of characters
* where boundaries occur.
* <p>
* Line boundary analysis determines where a text string can be broken
* when line-wrapping. The mechanism correctly handles punctuation and
* hyphenated words.
* <p>
* Note: The locale keyword "lb" can be used to modify line break
* behavior according to the CSS level 3 line-break options, see
* <http://dev.w3.org/csswg/css-text/#line-breaking>. For example:
* "ja@lb=strict", "zh@lb=loose".
* <p>
* Sentence boundary analysis allows selection with correct
* interpretation of periods within numbers and abbreviations, and
* trailing punctuation marks such as quotation marks and parentheses.
* <p>
* Note: The locale keyword "ss" can be used to enable use of
* segmentation suppression data (preventing breaks in English after
* abbreviations such as "Mr." or "Est.", for example), as follows:
* "en@ss=standard".
* <p>
* Word boundary analysis is used by search and replace functions, as
* well as within text editing applications that allow the user to
* select words with a double click. Word selection provides correct
* interpretation of punctuation marks within and following
* words. Characters that are not part of a word, such as symbols or
* punctuation marks, have word-breaks on both sides.
* <p>
* Character boundary analysis identifies the boundaries of
* "Extended Grapheme Clusters", which are groupings of codepoints
* that should be treated as character-like units for many text operations.
* Please see Unicode Standard Annex #29, Unicode Text Segmentation,
* http://www.unicode.org/reports/tr29/ for additional information
* on grapheme clusters and guidelines on their use.
* <p>
* Title boundary analysis locates all positions,
* typically starts of words, that should be set to Title Case
* when title casing the text.
* <p>
* The text boundary positions are found according to the rules
* described in Unicode Standard Annex #29, Text Boundaries, and
* Unicode Standard Annex #14, Line Breaking Properties. These
* are available at http://www.unicode.org/reports/tr14/ and
* http://www.unicode.org/reports/tr29/.
* <p>
* In addition to the plain C API defined in this header file, an
* object oriented C++ API with equivalent functionality is defined in the
* file brkiter.h.
* <p>
* Code snippets illustrating the use of the Break Iterator APIs
* are available in the ICU User Guide,
* https://unicode-org.github.io/icu/userguide/boundaryanalysis/
* and in the sample program icu/source/samples/break/break.cpp
*/
/** The possible types of text boundaries. @stable ICU 2.0 */
typedef enum UBreakIteratorType {
/** Character breaks @stable ICU 2.0 */
UBRK_CHARACTER = 0,
/** Word breaks @stable ICU 2.0 */
UBRK_WORD = 1,
/** Line breaks @stable ICU 2.0 */
UBRK_LINE = 2,
/** Sentence breaks @stable ICU 2.0 */
UBRK_SENTENCE = 3,
} UBreakIteratorType;
/** Value indicating all text boundaries have been returned.
* @stable ICU 2.0
*/
#define UBRK_DONE ((int32_t) -1)
/**
* Enum constants for the word break tags returned by
* getRuleStatus(). A range of values is defined for each category of
* word, to allow for further subdivisions of a category in future releases.
* Applications should check for tag values falling within the range, rather
* than for single individual values.
*
* The numeric values of all of these constants are stable (will not change).
*
* @stable ICU 2.2
*/
typedef enum UWordBreak {
/** Tag value for "words" that do not fit into any of other categories.
* Includes spaces and most punctuation. */
UBRK_WORD_NONE = 0,
/** Upper bound for tags for uncategorized words. */
UBRK_WORD_NONE_LIMIT = 100,
/** Tag value for words that appear to be numbers, lower limit. */
UBRK_WORD_NUMBER = 100,
/** Tag value for words that appear to be numbers, upper limit. */
UBRK_WORD_NUMBER_LIMIT = 200,
/** Tag value for words that contain letters, excluding
* hiragana, katakana or ideographic characters, lower limit. */
UBRK_WORD_LETTER = 200,
/** Tag value for words containing letters, upper limit */
UBRK_WORD_LETTER_LIMIT = 300,
/** Tag value for words containing kana characters, lower limit */
UBRK_WORD_KANA = 300,
/** Tag value for words containing kana characters, upper limit */
UBRK_WORD_KANA_LIMIT = 400,
/** Tag value for words containing ideographic characters, lower limit */
UBRK_WORD_IDEO = 400,
/** Tag value for words containing ideographic characters, upper limit */
UBRK_WORD_IDEO_LIMIT = 500
} UWordBreak;
/**
* Enum constants for the line break tags returned by getRuleStatus().
* A range of values is defined for each category of
* word, to allow for further subdivisions of a category in future releases.
* Applications should check for tag values falling within the range, rather
* than for single individual values.
*
* The numeric values of all of these constants are stable (will not change).
*
* @stable ICU 2.8
*/
typedef enum ULineBreakTag {
/** Tag value for soft line breaks, positions at which a line break
* is acceptable but not required */
UBRK_LINE_SOFT = 0,
/** Upper bound for soft line breaks. */
UBRK_LINE_SOFT_LIMIT = 100,
/** Tag value for a hard, or mandatory line break */
UBRK_LINE_HARD = 100,
/** Upper bound for hard line breaks. */
UBRK_LINE_HARD_LIMIT = 200
} ULineBreakTag;
/**
* Enum constants for the sentence break tags returned by getRuleStatus().
* A range of values is defined for each category of
* sentence, to allow for further subdivisions of a category in future releases.
* Applications should check for tag values falling within the range, rather
* than for single individual values.
*
* The numeric values of all of these constants are stable (will not change).
*
* @stable ICU 2.8
*/
typedef enum USentenceBreakTag {
/** Tag value for for sentences ending with a sentence terminator
* ('.', '?', '!', etc.) character, possibly followed by a
* hard separator (CR, LF, PS, etc.)
*/
UBRK_SENTENCE_TERM = 0,
/** Upper bound for tags for sentences ended by sentence terminators. */
UBRK_SENTENCE_TERM_LIMIT = 100,
/** Tag value for for sentences that do not contain an ending
* sentence terminator ('.', '?', '!', etc.) character, but
* are ended only by a hard separator (CR, LF, PS, etc.) or end of input.
*/
UBRK_SENTENCE_SEP = 100,
/** Upper bound for tags for sentences ended by a separator. */
UBRK_SENTENCE_SEP_LIMIT = 200
/** Tag value for a hard, or mandatory line break */
} USentenceBreakTag;
/**
* Open a new UBreakIterator for locating text boundaries for a specified locale.
* A UBreakIterator may be used for detecting character, line, word,
* and sentence breaks in text.
* @param type The type of UBreakIterator to open: one of UBRK_CHARACTER, UBRK_WORD,
* UBRK_LINE, UBRK_SENTENCE
* @param locale The locale specifying the text-breaking conventions. Note that
* locale keys such as "lb" and "ss" may be used to modify text break behavior,
* see general discussion of BreakIterator C API.
* @param text The text to be iterated over. May be null, in which case ubrk_setText() is
* used to specify the text to be iterated.
* @param textLength The number of characters in text, or -1 if null-terminated.
* @param status A UErrorCode to receive any errors.
* @return A UBreakIterator for the specified locale.
* @see ubrk_openRules
* @stable ICU 2.0
*/
U_CAPI UBreakIterator* U_EXPORT2
ubrk_open(UBreakIteratorType type,
const char *locale,
const UChar *text,
int32_t textLength,
UErrorCode *status);
/**
* Open a new UBreakIterator for locating text boundaries using specified breaking rules.
* The rule syntax is ... (TBD)
* @param rules A set of rules specifying the text breaking conventions.
* @param rulesLength The number of characters in rules, or -1 if null-terminated.
* @param text The text to be iterated over. May be null, in which case ubrk_setText() is
* used to specify the text to be iterated.
* @param textLength The number of characters in text, or -1 if null-terminated.
* @param parseErr Receives position and context information for any syntax errors
* detected while parsing the rules.
* @param status A UErrorCode to receive any errors.
* @return A UBreakIterator for the specified rules.
* @see ubrk_open
* @stable ICU 2.2
*/
U_CAPI UBreakIterator* U_EXPORT2
ubrk_openRules(const UChar *rules,
int32_t rulesLength,
const UChar *text,
int32_t textLength,
UParseError *parseErr,
UErrorCode *status);
/**
* Open a new UBreakIterator for locating text boundaries using precompiled binary rules.
* Opening a UBreakIterator this way is substantially faster than using ubrk_openRules.
* Binary rules may be obtained using ubrk_getBinaryRules. The compiled rules are not
* compatible across different major versions of ICU, nor across platforms of different
* endianness or different base character set family (ASCII vs EBCDIC).
* @param binaryRules A set of compiled binary rules specifying the text breaking
* conventions. Ownership of the storage containing the compiled
* rules remains with the caller of this function. The compiled
* rules must not be modified or deleted during the life of the
* break iterator.
* @param rulesLength The length of binaryRules in bytes; must be >= 0.
* @param text The text to be iterated over. May be null, in which case
* ubrk_setText() is used to specify the text to be iterated.
* @param textLength The number of characters in text, or -1 if null-terminated.
* @param status Pointer to UErrorCode to receive any errors.
* @return UBreakIterator for the specified rules.
* @see ubrk_getBinaryRules
* @stable ICU 59
*/
U_CAPI UBreakIterator* U_EXPORT2
ubrk_openBinaryRules(const uint8_t *binaryRules, int32_t rulesLength,
const UChar * text, int32_t textLength,
UErrorCode * status);
#ifndef U_HIDE_DEPRECATED_API
#endif /* U_HIDE_DEPRECATED_API */
/**
* Thread safe cloning operation.
* @param bi iterator to be cloned
* @param status to indicate whether the operation went on smoothly or there were errors
* @return pointer to the new clone
* @stable ICU 69
*/
U_CAPI UBreakIterator * U_EXPORT2
ubrk_clone(const UBreakIterator *bi,
UErrorCode *status);
/**
* Close a UBreakIterator.
* Once closed, a UBreakIterator may no longer be used.
* @param bi The break iterator to close.
* @stable ICU 2.0
*/
U_CAPI void U_EXPORT2
ubrk_close(UBreakIterator *bi);
#if U_SHOW_CPLUSPLUS_API
U_NAMESPACE_BEGIN
/**
* \class LocalUBreakIteratorPointer
* "Smart pointer" class, closes a UBreakIterator via ubrk_close().
* For most methods see the LocalPointerBase base class.
*
* @see LocalPointerBase
* @see LocalPointer
* @stable ICU 4.4
*/
U_DEFINE_LOCAL_OPEN_POINTER(LocalUBreakIteratorPointer, UBreakIterator, ubrk_close);
U_NAMESPACE_END
#endif
/**
* Sets an existing iterator to point to a new piece of text.
* The break iterator retains a pointer to the supplied text.
* The caller must not modify or delete the text while the BreakIterator
* retains the reference.
*
* @param bi The iterator to use
* @param text The text to be set
* @param textLength The length of the text
* @param status The error code
* @stable ICU 2.0
*/
U_CAPI void U_EXPORT2
ubrk_setText(UBreakIterator* bi,
const UChar* text,
int32_t textLength,
UErrorCode* status);
/**
* Determine the most recently-returned text boundary.
*
* @param bi The break iterator to use.
* @return The character index most recently returned by \ref ubrk_next, \ref ubrk_previous,
* \ref ubrk_first, or \ref ubrk_last.
* @stable ICU 2.0
*/
U_CAPI int32_t U_EXPORT2
ubrk_current(const UBreakIterator *bi);
/**
* Advance the iterator to the boundary following the current boundary.
*
* @param bi The break iterator to use.
* @return The character index of the next text boundary, or UBRK_DONE
* if all text boundaries have been returned.
* @see ubrk_previous
* @stable ICU 2.0
*/
U_CAPI int32_t U_EXPORT2
ubrk_next(UBreakIterator *bi);
/**
* Set the iterator position to the boundary preceding the current boundary.
*
* @param bi The break iterator to use.
* @return The character index of the preceding text boundary, or UBRK_DONE
* if all text boundaries have been returned.
* @see ubrk_next
* @stable ICU 2.0
*/
U_CAPI int32_t U_EXPORT2
ubrk_previous(UBreakIterator *bi);
/**
* Set the iterator position to zero, the start of the text being scanned.
* @param bi The break iterator to use.
* @return The new iterator position (zero).
* @see ubrk_last
* @stable ICU 2.0
*/
U_CAPI int32_t U_EXPORT2
ubrk_first(UBreakIterator *bi);
/**
* Set the iterator position to the index immediately <EM>beyond</EM> the last character in the text being scanned.
* This is not the same as the last character.
* @param bi The break iterator to use.
* @return The character offset immediately <EM>beyond</EM> the last character in the
* text being scanned.
* @see ubrk_first
* @stable ICU 2.0
*/
U_CAPI int32_t U_EXPORT2
ubrk_last(UBreakIterator *bi);
/**
* Set the iterator position to the first boundary preceding the specified offset.
* The new position is always smaller than offset, or UBRK_DONE.
* @param bi The break iterator to use.
* @param offset The offset to begin scanning.
* @return The text boundary preceding offset, or UBRK_DONE.
* @see ubrk_following
* @stable ICU 2.0
*/
U_CAPI int32_t U_EXPORT2
ubrk_preceding(UBreakIterator *bi,
int32_t offset);
/**
* Advance the iterator to the first boundary following the specified offset.
* The value returned is always greater than offset, or UBRK_DONE.
* @param bi The break iterator to use.
* @param offset The offset to begin scanning.
* @return The text boundary following offset, or UBRK_DONE.
* @see ubrk_preceding
* @stable ICU 2.0
*/
U_CAPI int32_t U_EXPORT2
ubrk_following(UBreakIterator *bi,
int32_t offset);
/**
* Get a locale for which text breaking information is available.
* A UBreakIterator in a locale returned by this function will perform the correct
* text breaking for the locale.
* @param index The index of the desired locale.
* @return A locale for which number text breaking information is available, or 0 if none.
* @see ubrk_countAvailable
* @stable ICU 2.0
*/
U_CAPI const char* U_EXPORT2
ubrk_getAvailable(int32_t index);
/**
* Determine how many locales have text breaking information available.
* This function is most useful as determining the loop ending condition for
* calls to \ref ubrk_getAvailable.
* @return The number of locales for which text breaking information is available.
* @see ubrk_getAvailable
* @stable ICU 2.0
*/
U_CAPI int32_t U_EXPORT2
ubrk_countAvailable(void);
/**
* Returns true if the specified position is a boundary position. As a side
* effect, leaves the iterator pointing to the first boundary position at
* or after "offset".
* @param bi The break iterator to use.
* @param offset the offset to check.
* @return True if "offset" is a boundary position.
* @stable ICU 2.0
*/
U_CAPI UBool U_EXPORT2
ubrk_isBoundary(UBreakIterator *bi, int32_t offset);
/**
* Return the status from the break rule that determined the most recently
* returned break position. The values appear in the rule source
* within brackets, {123}, for example. For rules that do not specify a
* status, a default value of 0 is returned.
* <p>
* For word break iterators, the possible values are defined in enum UWordBreak.
* @stable ICU 2.2
*/
U_CAPI int32_t U_EXPORT2
ubrk_getRuleStatus(UBreakIterator *bi);
/**
* Get the statuses from the break rules that determined the most recently
* returned break position. The values appear in the rule source
* within brackets, {123}, for example. The default status value for rules
* that do not explicitly provide one is zero.
* <p>
* For word break iterators, the possible values are defined in enum UWordBreak.
* @param bi The break iterator to use
* @param fillInVec an array to be filled in with the status values.
* @param capacity the length of the supplied vector. A length of zero causes
* the function to return the number of status values, in the
* normal way, without attempting to store any values.
* @param status receives error codes.
* @return The number of rule status values from rules that determined
* the most recent boundary returned by the break iterator.
* @stable ICU 3.0
*/
U_CAPI int32_t U_EXPORT2
ubrk_getRuleStatusVec(UBreakIterator *bi, int32_t *fillInVec, int32_t capacity, UErrorCode *status);
/**
* Return the locale of the break iterator. You can choose between the valid and
* the actual locale.
* @param bi break iterator
* @param type locale type (valid or actual)
* @param status error code
* @return locale string
* @stable ICU 2.8
*/
U_CAPI const char* U_EXPORT2
ubrk_getLocaleByType(const UBreakIterator *bi, ULocDataLocaleType type, UErrorCode* status);
/**
* Get a compiled binary version of the rules specifying the behavior of a UBreakIterator.
* The binary rules may be used with ubrk_openBinaryRules to open a new UBreakIterator
* more quickly than using ubrk_openRules. The compiled rules are not compatible across
* different major versions of ICU, nor across platforms of different endianness or
* different base character set family (ASCII vs EBCDIC). Supports preflighting (with
* binaryRules=NULL and rulesCapacity=0) to get the rules length without copying them to
* the binaryRules buffer. However, whether preflighting or not, if the actual length
* is greater than INT32_MAX, then the function returns 0 and sets *status to
* U_INDEX_OUTOFBOUNDS_ERROR.
* @param bi The break iterator to use.
* @param binaryRules Buffer to receive the compiled binary rules; set to NULL for
* preflighting.
* @param rulesCapacity Capacity (in bytes) of the binaryRules buffer; set to 0 for
* preflighting. Must be >= 0.
* @param status Pointer to UErrorCode to receive any errors, such as
* U_BUFFER_OVERFLOW_ERROR, U_INDEX_OUTOFBOUNDS_ERROR, or
* U_ILLEGAL_ARGUMENT_ERROR.
* @return The actual byte length of the binary rules, if <= INT32_MAX;
* otherwise 0. If not preflighting and this is larger than
* rulesCapacity, *status will be set to an error.
* @see ubrk_openBinaryRules
* @stable ICU 59
*/
U_CAPI int32_t U_EXPORT2
ubrk_getBinaryRules(UBreakIterator *bi,
uint8_t * binaryRules, int32_t rulesCapacity,
UErrorCode * status);
#endif /* #if !UCONFIG_NO_BREAK_ITERATION */
#endif
third_party/icu4c/ndk_headers/unicode/ucal.h
Vendored
+1682
View File
File diff suppressed because it is too large Load Diff
third_party/icu4c/ndk_headers/unicode/uchar.h
Vendored
+3900
View File
File diff suppressed because it is too large Load Diff
third_party/icu4c/ndk_headers/unicode/ucol.h
Vendored
+1138
View File
File diff suppressed because it is too large Load Diff
third_party/icu4c/ndk_headers/unicode/udat.h
Vendored
+1588
View File
File diff suppressed because it is too large Load Diff
third_party/icu4c/ndk_headers/unicode/udisplaycontext.h
Vendored
+173
View File
@@ -0,0 +1,173 @@
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
*****************************************************************************************
* Copyright (C) 2014-2016, International Business Machines
* Corporation and others. All Rights Reserved.
*****************************************************************************************
*/
#ifndef UDISPLAYCONTEXT_H
#define UDISPLAYCONTEXT_H
#include "unicode/utypes.h"
#if !UCONFIG_NO_FORMATTING
/**
* \file
* \brief C API: Display context types (enum values)
*/
/**
* Display context types, for getting values of a particular setting.
* Note, the specific numeric values are internal and may change.
* @stable ICU 51
*/
enum UDisplayContextType {
/**
* Type to retrieve the dialect handling setting, e.g.
* UDISPCTX_STANDARD_NAMES or UDISPCTX_DIALECT_NAMES.
* @stable ICU 51
*/
UDISPCTX_TYPE_DIALECT_HANDLING = 0,
/**
* Type to retrieve the capitalization context setting, e.g.
* UDISPCTX_CAPITALIZATION_NONE, UDISPCTX_CAPITALIZATION_FOR_MIDDLE_OF_SENTENCE,
* UDISPCTX_CAPITALIZATION_FOR_BEGINNING_OF_SENTENCE, etc.
* @stable ICU 51
*/
UDISPCTX_TYPE_CAPITALIZATION = 1,
/**
* Type to retrieve the display length setting, e.g.
* UDISPCTX_LENGTH_FULL, UDISPCTX_LENGTH_SHORT.
* @stable ICU 54
*/
UDISPCTX_TYPE_DISPLAY_LENGTH = 2,
/**
* Type to retrieve the substitute handling setting, e.g.
* UDISPCTX_SUBSTITUTE, UDISPCTX_NO_SUBSTITUTE.
* @stable ICU 58
*/
UDISPCTX_TYPE_SUBSTITUTE_HANDLING = 3
};
/**
* @stable ICU 51
*/
typedef enum UDisplayContextType UDisplayContextType;
/**
* Display context settings.
* Note, the specific numeric values are internal and may change.
* @stable ICU 51
*/
enum UDisplayContext {
/**
* ================================
* DIALECT_HANDLING can be set to one of UDISPCTX_STANDARD_NAMES or
* UDISPCTX_DIALECT_NAMES. Use UDisplayContextType UDISPCTX_TYPE_DIALECT_HANDLING
* to get the value.
*/
/**
* A possible setting for DIALECT_HANDLING:
* use standard names when generating a locale name,
* e.g. en_GB displays as 'English (United Kingdom)'.
* @stable ICU 51
*/
UDISPCTX_STANDARD_NAMES = (UDISPCTX_TYPE_DIALECT_HANDLING<<8) + 0,
/**
* A possible setting for DIALECT_HANDLING:
* use dialect names, when generating a locale name,
* e.g. en_GB displays as 'British English'.
* @stable ICU 51
*/
UDISPCTX_DIALECT_NAMES = (UDISPCTX_TYPE_DIALECT_HANDLING<<8) + 1,
/**
* ================================
* CAPITALIZATION can be set to one of UDISPCTX_CAPITALIZATION_NONE,
* UDISPCTX_CAPITALIZATION_FOR_MIDDLE_OF_SENTENCE,
* UDISPCTX_CAPITALIZATION_FOR_BEGINNING_OF_SENTENCE,
* UDISPCTX_CAPITALIZATION_FOR_UI_LIST_OR_MENU, or
* UDISPCTX_CAPITALIZATION_FOR_STANDALONE.
* Use UDisplayContextType UDISPCTX_TYPE_CAPITALIZATION to get the value.
*/
/**
* The capitalization context to be used is unknown (this is the default value).
* @stable ICU 51
*/
UDISPCTX_CAPITALIZATION_NONE = (UDISPCTX_TYPE_CAPITALIZATION<<8) + 0,
/**
* The capitalization context if a date, date symbol or display name is to be
* formatted with capitalization appropriate for the middle of a sentence.
* @stable ICU 51
*/
UDISPCTX_CAPITALIZATION_FOR_MIDDLE_OF_SENTENCE = (UDISPCTX_TYPE_CAPITALIZATION<<8) + 1,
/**
* The capitalization context if a date, date symbol or display name is to be
* formatted with capitalization appropriate for the beginning of a sentence.
* @stable ICU 51
*/
UDISPCTX_CAPITALIZATION_FOR_BEGINNING_OF_SENTENCE = (UDISPCTX_TYPE_CAPITALIZATION<<8) + 2,
/**
* The capitalization context if a date, date symbol or display name is to be
* formatted with capitalization appropriate for a user-interface list or menu item.
* @stable ICU 51
*/
UDISPCTX_CAPITALIZATION_FOR_UI_LIST_OR_MENU = (UDISPCTX_TYPE_CAPITALIZATION<<8) + 3,
/**
* The capitalization context if a date, date symbol or display name is to be
* formatted with capitalization appropriate for stand-alone usage such as an
* isolated name on a calendar page.
* @stable ICU 51
*/
UDISPCTX_CAPITALIZATION_FOR_STANDALONE = (UDISPCTX_TYPE_CAPITALIZATION<<8) + 4,
/**
* ================================
* DISPLAY_LENGTH can be set to one of UDISPCTX_LENGTH_FULL or
* UDISPCTX_LENGTH_SHORT. Use UDisplayContextType UDISPCTX_TYPE_DISPLAY_LENGTH
* to get the value.
*/
/**
* A possible setting for DISPLAY_LENGTH:
* use full names when generating a locale name,
* e.g. "United States" for US.
* @stable ICU 54
*/
UDISPCTX_LENGTH_FULL = (UDISPCTX_TYPE_DISPLAY_LENGTH<<8) + 0,
/**
* A possible setting for DISPLAY_LENGTH:
* use short names when generating a locale name,
* e.g. "U.S." for US.
* @stable ICU 54
*/
UDISPCTX_LENGTH_SHORT = (UDISPCTX_TYPE_DISPLAY_LENGTH<<8) + 1,
/**
* ================================
* SUBSTITUTE_HANDLING can be set to one of UDISPCTX_SUBSTITUTE or
* UDISPCTX_NO_SUBSTITUTE. Use UDisplayContextType UDISPCTX_TYPE_SUBSTITUTE_HANDLING
* to get the value.
*/
/**
* A possible setting for SUBSTITUTE_HANDLING:
* Returns a fallback value (e.g., the input code) when no data is available.
* This is the default value.
* @stable ICU 58
*/
UDISPCTX_SUBSTITUTE = (UDISPCTX_TYPE_SUBSTITUTE_HANDLING<<8) + 0,
/**
* A possible setting for SUBSTITUTE_HANDLING:
* Returns a null value with error code set to U_ILLEGAL_ARGUMENT_ERROR when no
* data is available.
* @stable ICU 58
*/
UDISPCTX_NO_SUBSTITUTE = (UDISPCTX_TYPE_SUBSTITUTE_HANDLING<<8) + 1
};
/**
* @stable ICU 51
*/
typedef enum UDisplayContext UDisplayContext;
#endif /* #if !UCONFIG_NO_FORMATTING */
#endif
third_party/icu4c/ndk_headers/unicode/ufieldpositer.h
Vendored
+123
View File
@@ -0,0 +1,123 @@
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
*****************************************************************************************
* Copyright (C) 2015-2016, International Business Machines
* Corporation and others. All Rights Reserved.
*****************************************************************************************
*/
#ifndef UFIELDPOSITER_H
#define UFIELDPOSITER_H
#include "unicode/utypes.h"
#if !UCONFIG_NO_FORMATTING
#if U_SHOW_CPLUSPLUS_API
#include "unicode/localpointer.h"
#endif // U_SHOW_CPLUSPLUS_API
/**
* \file
* \brief C API: UFieldPositionIterator for use with format APIs.
*
* Usage:
* ufieldpositer_open creates an empty (unset) UFieldPositionIterator.
* This can be passed to format functions such as {@link #udat_formatForFields},
* which will set it to apply to the fields in a particular formatted string.
* ufieldpositer_next can then be used to iterate over those fields,
* providing for each field its type (using values that are specific to the
* particular format type, such as date or number formats), as well as the
* start and end positions of the field in the formatted string.
* A given UFieldPositionIterator can be re-used for different format calls;
* each such call resets it to apply to that format string.
* ufieldpositer_close should be called to dispose of the UFieldPositionIterator
* when it is no longer needed.
*
* @see FieldPositionIterator
*/
/**
* Opaque UFieldPositionIterator object for use in C.
* @stable ICU 55
*/
struct UFieldPositionIterator;
typedef struct UFieldPositionIterator UFieldPositionIterator; /**< C typedef for struct UFieldPositionIterator. @stable ICU 55 */
/**
* Open a new, unset UFieldPositionIterator object.
* @param status
* A pointer to a UErrorCode to receive any errors.
* @return
* A pointer to an empty (unset) UFieldPositionIterator object,
* or NULL if an error occurred.
* @stable ICU 55
*/
U_CAPI UFieldPositionIterator* U_EXPORT2
ufieldpositer_open(UErrorCode* status);
/**
* Close a UFieldPositionIterator object. Once closed it may no longer be used.
* @param fpositer
* A pointer to the UFieldPositionIterator object to close.
* @stable ICU 55
*/
U_CAPI void U_EXPORT2
ufieldpositer_close(UFieldPositionIterator *fpositer);
#if U_SHOW_CPLUSPLUS_API
U_NAMESPACE_BEGIN
/**
* \class LocalUFieldPositionIteratorPointer
* "Smart pointer" class, closes a UFieldPositionIterator via ufieldpositer_close().
* For most methods see the LocalPointerBase base class.
*
* @see LocalPointerBase
* @see LocalPointer
* @stable ICU 55
*/
U_DEFINE_LOCAL_OPEN_POINTER(LocalUFieldPositionIteratorPointer, UFieldPositionIterator, ufieldpositer_close);
U_NAMESPACE_END
#endif
/**
* Get information for the next field in the formatted string to which this
* UFieldPositionIterator currently applies, or return a negative value if there
* are no more fields.
* @param fpositer
* A pointer to the UFieldPositionIterator object containing iteration
* state for the format fields.
* @param beginIndex
* A pointer to an int32_t to receive information about the start offset
* of the field in the formatted string (undefined if the function
* returns a negative value). May be NULL if this information is not needed.
* @param endIndex
* A pointer to an int32_t to receive information about the end offset
* of the field in the formatted string (undefined if the function
* returns a negative value). May be NULL if this information is not needed.
* @return
* The field type (non-negative value), or a negative value if there are
* no more fields for which to provide information. If negative, then any
* values pointed to by beginIndex and endIndex are undefined.
*
* The values for field type depend on what type of formatter the
* UFieldPositionIterator has been set by; for a date formatter, the
* values from the UDateFormatField enum. For more information, see the
* descriptions of format functions that take a UFieldPositionIterator*
* parameter, such as {@link #udat_formatForFields}.
*
* @stable ICU 55
*/
U_CAPI int32_t U_EXPORT2
ufieldpositer_next(UFieldPositionIterator *fpositer,
int32_t *beginIndex, int32_t *endIndex);
#endif /* #if !UCONFIG_NO_FORMATTING */
#endif
third_party/icu4c/ndk_headers/unicode/uloc.h
Vendored
+1380
View File
File diff suppressed because it is too large Load Diff
third_party/icu4c/ndk_headers/unicode/umisc.h
Vendored
+62
View File
@@ -0,0 +1,62 @@
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
**********************************************************************
* Copyright (C) 1999-2006, International Business Machines
* Corporation and others. All Rights Reserved.
**********************************************************************
* file name: umisc.h
* encoding: UTF-8
* tab size: 8 (not used)
* indentation:4
*
* created on: 1999oct15
* created by: Markus W. Scherer
*/
#ifndef UMISC_H
#define UMISC_H
#include "unicode/utypes.h"
/**
* \file
* \brief C API: Miscellaneous definitions
*
* This file contains miscellaneous definitions for the C APIs.
*/
U_CDECL_BEGIN
/** A struct representing a range of text containing a specific field
* @stable ICU 2.0
*/
typedef struct UFieldPosition {
/**
* The field
* @stable ICU 2.0
*/
int32_t field;
/**
* The start of the text range containing field
* @stable ICU 2.0
*/
int32_t beginIndex;
/**
* The limit of the text range containing field
* @stable ICU 2.0
*/
int32_t endIndex;
} UFieldPosition;
#if !UCONFIG_NO_SERVICE
/**
* Opaque type returned by registerInstance, registerFactory and unregister for service registration.
* @stable ICU 2.6
*/
typedef const void* URegistryKey;
#endif
U_CDECL_END
#endif
third_party/icu4c/ndk_headers/unicode/unorm2.h
Vendored
+606
View File
@@ -0,0 +1,606 @@
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
*******************************************************************************
*
* Copyright (C) 2009-2015, International Business Machines
* Corporation and others. All Rights Reserved.
*
*******************************************************************************
* file name: unorm2.h
* encoding: UTF-8
* tab size: 8 (not used)
* indentation:4
*
* created on: 2009dec15
* created by: Markus W. Scherer
*/
#ifndef __UNORM2_H__
#define __UNORM2_H__
/**
* \file
* \brief C API: New API for Unicode Normalization.
*
* Unicode normalization functionality for standard Unicode normalization or
* for using custom mapping tables.
* All instances of UNormalizer2 are unmodifiable/immutable.
* Instances returned by unorm2_getInstance() are singletons that must not be deleted by the caller.
* For more details see the Normalizer2 C++ class.
*/
#include "unicode/utypes.h"
#include "unicode/stringoptions.h"
#include "unicode/uset.h"
#if U_SHOW_CPLUSPLUS_API
#include "unicode/localpointer.h"
#endif // U_SHOW_CPLUSPLUS_API
/**
* Constants for normalization modes.
* For details about standard Unicode normalization forms
* and about the algorithms which are also used with custom mapping tables
* see http://www.unicode.org/unicode/reports/tr15/
* @stable ICU 4.4
*/
typedef enum {
/**
* Decomposition followed by composition.
* Same as standard NFC when using an "nfc" instance.
* Same as standard NFKC when using an "nfkc" instance.
* For details about standard Unicode normalization forms
* see http://www.unicode.org/unicode/reports/tr15/
* @stable ICU 4.4
*/
UNORM2_COMPOSE,
/**
* Map, and reorder canonically.
* Same as standard NFD when using an "nfc" instance.
* Same as standard NFKD when using an "nfkc" instance.
* For details about standard Unicode normalization forms
* see http://www.unicode.org/unicode/reports/tr15/
* @stable ICU 4.4
*/
UNORM2_DECOMPOSE,
/**
* "Fast C or D" form.
* If a string is in this form, then further decomposition <i>without reordering</i>
* would yield the same form as DECOMPOSE.
* Text in "Fast C or D" form can be processed efficiently with data tables
* that are "canonically closed", that is, that provide equivalent data for
* equivalent text, without having to be fully normalized.
* Not a standard Unicode normalization form.
* Not a unique form: Different FCD strings can be canonically equivalent.
* For details see http://www.unicode.org/notes/tn5/#FCD
* @stable ICU 4.4
*/
UNORM2_FCD,
/**
* Compose only contiguously.
* Also known as "FCC" or "Fast C Contiguous".
* The result will often but not always be in NFC.
* The result will conform to FCD which is useful for processing.
* Not a standard Unicode normalization form.
* For details see http://www.unicode.org/notes/tn5/#FCC
* @stable ICU 4.4
*/
UNORM2_COMPOSE_CONTIGUOUS
} UNormalization2Mode;
/**
* Result values for normalization quick check functions.
* For details see http://www.unicode.org/reports/tr15/#Detecting_Normalization_Forms
* @stable ICU 2.0
*/
typedef enum UNormalizationCheckResult {
/**
* The input string is not in the normalization form.
* @stable ICU 2.0
*/
UNORM_NO,
/**
* The input string is in the normalization form.
* @stable ICU 2.0
*/
UNORM_YES,
/**
* The input string may or may not be in the normalization form.
* This value is only returned for composition forms like NFC and FCC,
* when a backward-combining character is found for which the surrounding text
* would have to be analyzed further.
* @stable ICU 2.0
*/
UNORM_MAYBE
} UNormalizationCheckResult;
/**
* Opaque C service object type for the new normalization API.
* @stable ICU 4.4
*/
struct UNormalizer2;
typedef struct UNormalizer2 UNormalizer2; /**< C typedef for struct UNormalizer2. @stable ICU 4.4 */
#if !UCONFIG_NO_NORMALIZATION
/**
* Returns a UNormalizer2 instance for Unicode NFC normalization.
* Same as unorm2_getInstance(NULL, "nfc", UNORM2_COMPOSE, pErrorCode).
* Returns an unmodifiable singleton instance. Do not delete it.
* @param pErrorCode Standard ICU error code. Its input value must
* pass the U_SUCCESS() test, or else the function returns
* immediately. Check for U_FAILURE() on output or use with
* function chaining. (See User Guide for details.)
* @return the requested Normalizer2, if successful
* @stable ICU 49
*/
U_CAPI const UNormalizer2 * U_EXPORT2
unorm2_getNFCInstance(UErrorCode *pErrorCode);
/**
* Returns a UNormalizer2 instance for Unicode NFD normalization.
* Same as unorm2_getInstance(NULL, "nfc", UNORM2_DECOMPOSE, pErrorCode).
* Returns an unmodifiable singleton instance. Do not delete it.
* @param pErrorCode Standard ICU error code. Its input value must
* pass the U_SUCCESS() test, or else the function returns
* immediately. Check for U_FAILURE() on output or use with
* function chaining. (See User Guide for details.)
* @return the requested Normalizer2, if successful
* @stable ICU 49
*/
U_CAPI const UNormalizer2 * U_EXPORT2
unorm2_getNFDInstance(UErrorCode *pErrorCode);
/**
* Returns a UNormalizer2 instance for Unicode NFKC normalization.
* Same as unorm2_getInstance(NULL, "nfkc", UNORM2_COMPOSE, pErrorCode).
* Returns an unmodifiable singleton instance. Do not delete it.
* @param pErrorCode Standard ICU error code. Its input value must
* pass the U_SUCCESS() test, or else the function returns
* immediately. Check for U_FAILURE() on output or use with
* function chaining. (See User Guide for details.)
* @return the requested Normalizer2, if successful
* @stable ICU 49
*/
U_CAPI const UNormalizer2 * U_EXPORT2
unorm2_getNFKCInstance(UErrorCode *pErrorCode);
/**
* Returns a UNormalizer2 instance for Unicode NFKD normalization.
* Same as unorm2_getInstance(NULL, "nfkc", UNORM2_DECOMPOSE, pErrorCode).
* Returns an unmodifiable singleton instance. Do not delete it.
* @param pErrorCode Standard ICU error code. Its input value must
* pass the U_SUCCESS() test, or else the function returns
* immediately. Check for U_FAILURE() on output or use with
* function chaining. (See User Guide for details.)
* @return the requested Normalizer2, if successful
* @stable ICU 49
*/
U_CAPI const UNormalizer2 * U_EXPORT2
unorm2_getNFKDInstance(UErrorCode *pErrorCode);
/**
* Returns a UNormalizer2 instance for Unicode NFKC_Casefold normalization.
* Same as unorm2_getInstance(NULL, "nfkc_cf", UNORM2_COMPOSE, pErrorCode).
* Returns an unmodifiable singleton instance. Do not delete it.
* @param pErrorCode Standard ICU error code. Its input value must
* pass the U_SUCCESS() test, or else the function returns
* immediately. Check for U_FAILURE() on output or use with
* function chaining. (See User Guide for details.)
* @return the requested Normalizer2, if successful
* @stable ICU 49
*/
U_CAPI const UNormalizer2 * U_EXPORT2
unorm2_getNFKCCasefoldInstance(UErrorCode *pErrorCode);
/**
* Returns a UNormalizer2 instance which uses the specified data file
* (packageName/name similar to ucnv_openPackage() and ures_open()/ResourceBundle)
* and which composes or decomposes text according to the specified mode.
* Returns an unmodifiable singleton instance. Do not delete it.
*
* Use packageName=NULL for data files that are part of ICU's own data.
* Use name="nfc" and UNORM2_COMPOSE/UNORM2_DECOMPOSE for Unicode standard NFC/NFD.
* Use name="nfkc" and UNORM2_COMPOSE/UNORM2_DECOMPOSE for Unicode standard NFKC/NFKD.
* Use name="nfkc_cf" and UNORM2_COMPOSE for Unicode standard NFKC_CF=NFKC_Casefold.
*
* @param packageName NULL for ICU built-in data, otherwise application data package name
* @param name "nfc" or "nfkc" or "nfkc_cf" or name of custom data file
* @param mode normalization mode (compose or decompose etc.)
* @param pErrorCode Standard ICU error code. Its input value must
* pass the U_SUCCESS() test, or else the function returns
* immediately. Check for U_FAILURE() on output or use with
* function chaining. (See User Guide for details.)
* @return the requested UNormalizer2, if successful
* @stable ICU 4.4
*/
U_CAPI const UNormalizer2 * U_EXPORT2
unorm2_getInstance(const char *packageName,
const char *name,
UNormalization2Mode mode,
UErrorCode *pErrorCode);
/**
* Constructs a filtered normalizer wrapping any UNormalizer2 instance
* and a filter set.
* Both are aliased and must not be modified or deleted while this object
* is used.
* The filter set should be frozen; otherwise the performance will suffer greatly.
* @param norm2 wrapped UNormalizer2 instance
* @param filterSet USet which determines the characters to be normalized
* @param pErrorCode Standard ICU error code. Its input value must
* pass the U_SUCCESS() test, or else the function returns
* immediately. Check for U_FAILURE() on output or use with
* function chaining. (See User Guide for details.)
* @return the requested UNormalizer2, if successful
* @stable ICU 4.4
*/
U_CAPI UNormalizer2 * U_EXPORT2
unorm2_openFiltered(const UNormalizer2 *norm2, const USet *filterSet, UErrorCode *pErrorCode);
/**
* Closes a UNormalizer2 instance from unorm2_openFiltered().
* Do not close instances from unorm2_getInstance()!
* @param norm2 UNormalizer2 instance to be closed
* @stable ICU 4.4
*/
U_CAPI void U_EXPORT2
unorm2_close(UNormalizer2 *norm2);
#if U_SHOW_CPLUSPLUS_API
U_NAMESPACE_BEGIN
/**
* \class LocalUNormalizer2Pointer
* "Smart pointer" class, closes a UNormalizer2 via unorm2_close().
* For most methods see the LocalPointerBase base class.
*
* @see LocalPointerBase
* @see LocalPointer
* @stable ICU 4.4
*/
U_DEFINE_LOCAL_OPEN_POINTER(LocalUNormalizer2Pointer, UNormalizer2, unorm2_close);
U_NAMESPACE_END
#endif
/**
* Writes the normalized form of the source string to the destination string
* (replacing its contents) and returns the length of the destination string.
* The source and destination strings must be different buffers.
* @param norm2 UNormalizer2 instance
* @param src source string
* @param length length of the source string, or -1 if NUL-terminated
* @param dest destination string; its contents is replaced with normalized src
* @param capacity number of UChars that can be written to dest
* @param pErrorCode Standard ICU error code. Its input value must
* pass the U_SUCCESS() test, or else the function returns
* immediately. Check for U_FAILURE() on output or use with
* function chaining. (See User Guide for details.)
* @return dest
* @stable ICU 4.4
*/
U_CAPI int32_t U_EXPORT2
unorm2_normalize(const UNormalizer2 *norm2,
const UChar *src, int32_t length,
UChar *dest, int32_t capacity,
UErrorCode *pErrorCode);
/**
* Appends the normalized form of the second string to the first string
* (merging them at the boundary) and returns the length of the first string.
* The result is normalized if the first string was normalized.
* The first and second strings must be different buffers.
* @param norm2 UNormalizer2 instance
* @param first string, should be normalized
* @param firstLength length of the first string, or -1 if NUL-terminated
* @param firstCapacity number of UChars that can be written to first
* @param second string, will be normalized
* @param secondLength length of the source string, or -1 if NUL-terminated
* @param pErrorCode Standard ICU error code. Its input value must
* pass the U_SUCCESS() test, or else the function returns
* immediately. Check for U_FAILURE() on output or use with
* function chaining. (See User Guide for details.)
* @return first
* @stable ICU 4.4
*/
U_CAPI int32_t U_EXPORT2
unorm2_normalizeSecondAndAppend(const UNormalizer2 *norm2,
UChar *first, int32_t firstLength, int32_t firstCapacity,
const UChar *second, int32_t secondLength,
UErrorCode *pErrorCode);
/**
* Appends the second string to the first string
* (merging them at the boundary) and returns the length of the first string.
* The result is normalized if both the strings were normalized.
* The first and second strings must be different buffers.
* @param norm2 UNormalizer2 instance
* @param first string, should be normalized
* @param firstLength length of the first string, or -1 if NUL-terminated
* @param firstCapacity number of UChars that can be written to first
* @param second string, should be normalized
* @param secondLength length of the source string, or -1 if NUL-terminated
* @param pErrorCode Standard ICU error code. Its input value must
* pass the U_SUCCESS() test, or else the function returns
* immediately. Check for U_FAILURE() on output or use with
* function chaining. (See User Guide for details.)
* @return first
* @stable ICU 4.4
*/
U_CAPI int32_t U_EXPORT2
unorm2_append(const UNormalizer2 *norm2,
UChar *first, int32_t firstLength, int32_t firstCapacity,
const UChar *second, int32_t secondLength,
UErrorCode *pErrorCode);
/**
* Gets the decomposition mapping of c.
* Roughly equivalent to normalizing the String form of c
* on a UNORM2_DECOMPOSE UNormalizer2 instance, but much faster, and except that this function
* returns a negative value and does not write a string
* if c does not have a decomposition mapping in this instance's data.
* This function is independent of the mode of the UNormalizer2.
* @param norm2 UNormalizer2 instance
* @param c code point
* @param decomposition String buffer which will be set to c's
* decomposition mapping, if there is one.
* @param capacity number of UChars that can be written to decomposition
* @param pErrorCode Standard ICU error code. Its input value must
* pass the U_SUCCESS() test, or else the function returns
* immediately. Check for U_FAILURE() on output or use with
* function chaining. (See User Guide for details.)
* @return the non-negative length of c's decomposition, if there is one; otherwise a negative value
* @stable ICU 4.6
*/
U_CAPI int32_t U_EXPORT2
unorm2_getDecomposition(const UNormalizer2 *norm2,
UChar32 c, UChar *decomposition, int32_t capacity,
UErrorCode *pErrorCode);
/**
* Gets the raw decomposition mapping of c.
*
* This is similar to the unorm2_getDecomposition() function but returns the
* raw decomposition mapping as specified in UnicodeData.txt or
* (for custom data) in the mapping files processed by the gennorm2 tool.
* By contrast, unorm2_getDecomposition() returns the processed,
* recursively-decomposed version of this mapping.
*
* When used on a standard NFKC Normalizer2 instance,
* unorm2_getRawDecomposition() returns the Unicode Decomposition_Mapping (dm) property.
*
* When used on a standard NFC Normalizer2 instance,
* it returns the Decomposition_Mapping only if the Decomposition_Type (dt) is Canonical (Can);
* in this case, the result contains either one or two code points (=1..4 UChars).
*
* This function is independent of the mode of the UNormalizer2.
* @param norm2 UNormalizer2 instance
* @param c code point
* @param decomposition String buffer which will be set to c's
* raw decomposition mapping, if there is one.
* @param capacity number of UChars that can be written to decomposition
* @param pErrorCode Standard ICU error code. Its input value must
* pass the U_SUCCESS() test, or else the function returns
* immediately. Check for U_FAILURE() on output or use with
* function chaining. (See User Guide for details.)
* @return the non-negative length of c's raw decomposition, if there is one; otherwise a negative value
* @stable ICU 49
*/
U_CAPI int32_t U_EXPORT2
unorm2_getRawDecomposition(const UNormalizer2 *norm2,
UChar32 c, UChar *decomposition, int32_t capacity,
UErrorCode *pErrorCode);
/**
* Performs pairwise composition of a & b and returns the composite if there is one.
*
* Returns a composite code point c only if c has a two-way mapping to a+b.
* In standard Unicode normalization, this means that
* c has a canonical decomposition to a+b
* and c does not have the Full_Composition_Exclusion property.
*
* This function is independent of the mode of the UNormalizer2.
* @param norm2 UNormalizer2 instance
* @param a A (normalization starter) code point.
* @param b Another code point.
* @return The non-negative composite code point if there is one; otherwise a negative value.
* @stable ICU 49
*/
U_CAPI UChar32 U_EXPORT2
unorm2_composePair(const UNormalizer2 *norm2, UChar32 a, UChar32 b);
/**
* Gets the combining class of c.
* The default implementation returns 0
* but all standard implementations return the Unicode Canonical_Combining_Class value.
* @param norm2 UNormalizer2 instance
* @param c code point
* @return c's combining class
* @stable ICU 49
*/
U_CAPI uint8_t U_EXPORT2
unorm2_getCombiningClass(const UNormalizer2 *norm2, UChar32 c);
/**
* Tests if the string is normalized.
* Internally, in cases where the quickCheck() method would return "maybe"
* (which is only possible for the two COMPOSE modes) this method
* resolves to "yes" or "no" to provide a definitive result,
* at the cost of doing more work in those cases.
* @param norm2 UNormalizer2 instance
* @param s input string
* @param length length of the string, or -1 if NUL-terminated
* @param pErrorCode Standard ICU error code. Its input value must
* pass the U_SUCCESS() test, or else the function returns
* immediately. Check for U_FAILURE() on output or use with
* function chaining. (See User Guide for details.)
* @return true if s is normalized
* @stable ICU 4.4
*/
U_CAPI UBool U_EXPORT2
unorm2_isNormalized(const UNormalizer2 *norm2,
const UChar *s, int32_t length,
UErrorCode *pErrorCode);
/**
* Tests if the string is normalized.
* For the two COMPOSE modes, the result could be "maybe" in cases that
* would take a little more work to resolve definitively.
* Use spanQuickCheckYes() and normalizeSecondAndAppend() for a faster
* combination of quick check + normalization, to avoid
* re-checking the "yes" prefix.
* @param norm2 UNormalizer2 instance
* @param s input string
* @param length length of the string, or -1 if NUL-terminated
* @param pErrorCode Standard ICU error code. Its input value must
* pass the U_SUCCESS() test, or else the function returns
* immediately. Check for U_FAILURE() on output or use with
* function chaining. (See User Guide for details.)
* @return UNormalizationCheckResult
* @stable ICU 4.4
*/
U_CAPI UNormalizationCheckResult U_EXPORT2
unorm2_quickCheck(const UNormalizer2 *norm2,
const UChar *s, int32_t length,
UErrorCode *pErrorCode);
/**
* Returns the end of the normalized substring of the input string.
* In other words, with <code>end=spanQuickCheckYes(s, ec);</code>
* the substring <code>UnicodeString(s, 0, end)</code>
* will pass the quick check with a "yes" result.
*
* The returned end index is usually one or more characters before the
* "no" or "maybe" character: The end index is at a normalization boundary.
* (See the class documentation for more about normalization boundaries.)
*
* When the goal is a normalized string and most input strings are expected
* to be normalized already, then call this method,
* and if it returns a prefix shorter than the input string,
* copy that prefix and use normalizeSecondAndAppend() for the remainder.
* @param norm2 UNormalizer2 instance
* @param s input string
* @param length length of the string, or -1 if NUL-terminated
* @param pErrorCode Standard ICU error code. Its input value must
* pass the U_SUCCESS() test, or else the function returns
* immediately. Check for U_FAILURE() on output or use with
* function chaining. (See User Guide for details.)
* @return "yes" span end index
* @stable ICU 4.4
*/
U_CAPI int32_t U_EXPORT2
unorm2_spanQuickCheckYes(const UNormalizer2 *norm2,
const UChar *s, int32_t length,
UErrorCode *pErrorCode);
/**
* Tests if the character always has a normalization boundary before it,
* regardless of context.
* For details see the Normalizer2 base class documentation.
* @param norm2 UNormalizer2 instance
* @param c character to test
* @return true if c has a normalization boundary before it
* @stable ICU 4.4
*/
U_CAPI UBool U_EXPORT2
unorm2_hasBoundaryBefore(const UNormalizer2 *norm2, UChar32 c);
/**
* Tests if the character always has a normalization boundary after it,
* regardless of context.
* For details see the Normalizer2 base class documentation.
* @param norm2 UNormalizer2 instance
* @param c character to test
* @return true if c has a normalization boundary after it
* @stable ICU 4.4
*/
U_CAPI UBool U_EXPORT2
unorm2_hasBoundaryAfter(const UNormalizer2 *norm2, UChar32 c);
/**
* Tests if the character is normalization-inert.
* For details see the Normalizer2 base class documentation.
* @param norm2 UNormalizer2 instance
* @param c character to test
* @return true if c is normalization-inert
* @stable ICU 4.4
*/
U_CAPI UBool U_EXPORT2
unorm2_isInert(const UNormalizer2 *norm2, UChar32 c);
/**
* Compares two strings for canonical equivalence.
* Further options include case-insensitive comparison and
* code point order (as opposed to code unit order).
*
* Canonical equivalence between two strings is defined as their normalized
* forms (NFD or NFC) being identical.
* This function compares strings incrementally instead of normalizing
* (and optionally case-folding) both strings entirely,
* improving performance significantly.
*
* Bulk normalization is only necessary if the strings do not fulfill the FCD
* conditions. Only in this case, and only if the strings are relatively long,
* is memory allocated temporarily.
* For FCD strings and short non-FCD strings there is no memory allocation.
*
* Semantically, this is equivalent to
* strcmp[CodePointOrder](NFD(foldCase(NFD(s1))), NFD(foldCase(NFD(s2))))
* where code point order and foldCase are all optional.
*
* UAX 21 2.5 Caseless Matching specifies that for a canonical caseless match
* the case folding must be performed first, then the normalization.
*
* @param s1 First source string.
* @param length1 Length of first source string, or -1 if NUL-terminated.
*
* @param s2 Second source string.
* @param length2 Length of second source string, or -1 if NUL-terminated.
*
* @param options A bit set of options:
* - U_FOLD_CASE_DEFAULT or 0 is used for default options:
* Case-sensitive comparison in code unit order, and the input strings
* are quick-checked for FCD.
*
* - UNORM_INPUT_IS_FCD
* Set if the caller knows that both s1 and s2 fulfill the FCD conditions.
* If not set, the function will quickCheck for FCD
* and normalize if necessary.
*
* - U_COMPARE_CODE_POINT_ORDER
* Set to choose code point order instead of code unit order
* (see u_strCompare for details).
*
* - U_COMPARE_IGNORE_CASE
* Set to compare strings case-insensitively using case folding,
* instead of case-sensitively.
* If set, then the following case folding options are used.
*
* - Options as used with case-insensitive comparisons, currently:
*
* - U_FOLD_CASE_EXCLUDE_SPECIAL_I
* (see u_strCaseCompare for details)
*
* - regular normalization options shifted left by UNORM_COMPARE_NORM_OPTIONS_SHIFT
*
* @param pErrorCode ICU error code in/out parameter.
* Must fulfill U_SUCCESS before the function call.
* @return <0 or 0 or >0 as usual for string comparisons
*
* @see unorm_normalize
* @see UNORM_FCD
* @see u_strCompare
* @see u_strCaseCompare
*
* @stable ICU 2.2
*/
U_CAPI int32_t U_EXPORT2
unorm_compare(const UChar *s1, int32_t length1,
const UChar *s2, int32_t length2,
uint32_t options,
UErrorCode *pErrorCode);
#endif /* !UCONFIG_NO_NORMALIZATION */
#endif /* __UNORM2_H__ */
third_party/icu4c/ndk_headers/unicode/unum.h
Vendored
+1425
View File
File diff suppressed because it is too large Load Diff
third_party/icu4c/ndk_headers/unicode/unumberformatter.h
Vendored
+707
View File
@@ -0,0 +1,707 @@
// © 2018 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
#ifndef __UNUMBERFORMATTER_H__
#define __UNUMBERFORMATTER_H__
#include "unicode/utypes.h"
#if !UCONFIG_NO_FORMATTING
#include "unicode/parseerr.h"
#include "unicode/ufieldpositer.h"
#include "unicode/umisc.h"
/**
* \file
* \brief C API: Localized number formatting; not recommended for C++.
*
* This is the C-compatible version of the NumberFormatter API introduced in ICU 60. C++ users should
* include unicode/numberformatter.h and use the proper C++ APIs.
*
* The C API accepts a number skeleton string for specifying the settings for formatting, which covers a
* very large subset of all possible number formatting features. For more information on number skeleton
* strings, see unicode/numberformatter.h.
*
* When using UNumberFormatter, which is treated as immutable, the results are exported to a mutable
* UFormattedNumber object, which you subsequently use for populating your string buffer or iterating over
* the fields.
*
* Example code:
* <pre>
* // Setup:
* UErrorCode ec = U_ZERO_ERROR;
* UNumberFormatter* uformatter = unumf_openForSkeletonAndLocale(u"precision-integer", -1, "en", &ec);
* UFormattedNumber* uresult = unumf_openResult(&ec);
* if (U_FAILURE(ec)) { return; }
*
* // Format a double:
* unumf_formatDouble(uformatter, 5142.3, uresult, &ec);
* if (U_FAILURE(ec)) { return; }
*
* // Export the string to a malloc'd buffer:
* int32_t len = unumf_resultToString(uresult, NULL, 0, &ec);
* // at this point, ec == U_BUFFER_OVERFLOW_ERROR
* ec = U_ZERO_ERROR;
* UChar* buffer = (UChar*) malloc((len+1)*sizeof(UChar));
* unumf_resultToString(uresult, buffer, len+1, &ec);
* if (U_FAILURE(ec)) { return; }
* // buffer should equal "5,142"
*
* // Cleanup:
* unumf_close(uformatter);
* unumf_closeResult(uresult);
* free(buffer);
* </pre>
*
* If you are a C++ user linking against the C libraries, you can use the LocalPointer versions of these
* APIs. The following example uses LocalPointer with the decimal number and field position APIs:
*
* <pre>
* // Setup:
* LocalUNumberFormatterPointer uformatter(unumf_openForSkeletonAndLocale(u"percent", -1, "en", &ec));
* LocalUFormattedNumberPointer uresult(unumf_openResult(&ec));
* if (U_FAILURE(ec)) { return; }
*
* // Format a decimal number:
* unumf_formatDecimal(uformatter.getAlias(), "9.87E-3", -1, uresult.getAlias(), &ec);
* if (U_FAILURE(ec)) { return; }
*
* // Get the location of the percent sign:
* UFieldPosition ufpos = {UNUM_PERCENT_FIELD, 0, 0};
* unumf_resultNextFieldPosition(uresult.getAlias(), &ufpos, &ec);
* // ufpos should contain beginIndex=7 and endIndex=8 since the string is "0.00987%"
*
* // No need to do any cleanup since we are using LocalPointer.
* </pre>
*/
/**
* An enum declaring how to resolve conflicts between maximum fraction digits and maximum
* significant digits.
*
* There are two modes, RELAXED and STRICT:
*
* - RELAXED: Relax one of the two constraints (fraction digits or significant digits) in order
* to round the number to a higher level of precision.
* - STRICT: Enforce both constraints, resulting in the number being rounded to a lower
* level of precision.
*
* The default settings for compact notation rounding are Max-Fraction = 0 (round to the nearest
* integer), Max-Significant = 2 (round to 2 significant digits), and priority RELAXED (choose
* the constraint that results in more digits being displayed).
*
* Conflicting *minimum* fraction and significant digits are always resolved in the direction that
* results in more trailing zeros.
*
* Example 1: Consider the number 3.141, with various different settings:
*
* - Max-Fraction = 1: "3.1"
* - Max-Significant = 3: "3.14"
*
* The rounding priority determines how to resolve the conflict when both Max-Fraction and
* Max-Significant are set. With RELAXED, the less-strict setting (the one that causes more digits
* to be displayed) will be used; Max-Significant wins. With STRICT, the more-strict setting (the
* one that causes fewer digits to be displayed) will be used; Max-Fraction wins.
*
* Example 2: Consider the number 8317, with various different settings:
*
* - Max-Fraction = 1: "8317"
* - Max-Significant = 3: "8320"
*
* Here, RELAXED favors Max-Fraction and STRICT favors Max-Significant. Note that this larger
* number caused the two modes to favor the opposite result.
*
* @stable ICU 69
*/
typedef enum UNumberRoundingPriority {
/**
* Favor greater precision by relaxing one of the rounding constraints.
*
* @stable ICU 69
*/
UNUM_ROUNDING_PRIORITY_RELAXED,
/**
* Favor adherence to all rounding constraints by producing lower precision.
*
* @stable ICU 69
*/
UNUM_ROUNDING_PRIORITY_STRICT,
} UNumberRoundingPriority;
/**
* An enum declaring how to render units, including currencies. Example outputs when formatting 123 USD and 123
* meters in <em>en-CA</em>:
*
* <p>
* <ul>
* <li>NARROW*: "$123.00" and "123 m"
* <li>SHORT: "US$ 123.00" and "123 m"
* <li>FULL_NAME: "123.00 US dollars" and "123 meters"
* <li>ISO_CODE: "USD 123.00" and undefined behavior
* <li>HIDDEN: "123.00" and "123"
* </ul>
*
* <p>
* This enum is similar to {@link UMeasureFormatWidth}.
*
* @stable ICU 60
*/
typedef enum UNumberUnitWidth {
/**
* Print an abbreviated version of the unit name. Similar to SHORT, but always use the shortest available
* abbreviation or symbol. This option can be used when the context hints at the identity of the unit. For more
* information on the difference between NARROW and SHORT, see SHORT.
*
* <p>
* In CLDR, this option corresponds to the "Narrow" format for measure units and the "¤¤¤¤¤" placeholder for
* currencies.
*
* @stable ICU 60
*/
UNUM_UNIT_WIDTH_NARROW = 0,
/**
* Print an abbreviated version of the unit name. Similar to NARROW, but use a slightly wider abbreviation or
* symbol when there may be ambiguity. This is the default behavior.
*
* <p>
* For example, in <em>es-US</em>, the SHORT form for Fahrenheit is "{0} °F", but the NARROW form is "{0}°",
* since Fahrenheit is the customary unit for temperature in that locale.
*
* <p>
* In CLDR, this option corresponds to the "Short" format for measure units and the "¤" placeholder for
* currencies.
*
* @stable ICU 60
*/
UNUM_UNIT_WIDTH_SHORT = 1,
/**
* Print the full name of the unit, without any abbreviations.
*
* <p>
* In CLDR, this option corresponds to the default format for measure units and the "¤¤¤" placeholder for
* currencies.
*
* @stable ICU 60
*/
UNUM_UNIT_WIDTH_FULL_NAME = 2,
/**
* Use the three-digit ISO XXX code in place of the symbol for displaying currencies. The behavior of this
* option is currently undefined for use with measure units.
*
* <p>
* In CLDR, this option corresponds to the "¤¤" placeholder for currencies.
*
* @stable ICU 60
*/
UNUM_UNIT_WIDTH_ISO_CODE = 3,
/**
* Use the formal variant of the currency symbol; for example, "NT$" for the New Taiwan
* dollar in zh-TW.
*
* <p>
* Behavior of this option with non-currency units is not defined at this time.
*
* @stable ICU 68
*/
UNUM_UNIT_WIDTH_FORMAL = 4,
/**
* Use the alternate variant of the currency symbol; for example, "TL" for the Turkish
* lira (TRY).
*
* <p>
* Behavior of this option with non-currency units is not defined at this time.
*
* @stable ICU 68
*/
UNUM_UNIT_WIDTH_VARIANT = 5,
/**
* Format the number according to the specified unit, but do not display the unit. For currencies, apply
* monetary symbols and formats as with SHORT, but omit the currency symbol. For measure units, the behavior is
* equivalent to not specifying the unit at all.
*
* @stable ICU 60
*/
UNUM_UNIT_WIDTH_HIDDEN = 6,
// Do not conditionalize the following with #ifndef U_HIDE_INTERNAL_API,
// needed for unconditionalized struct MacroProps
/**
* One more than the highest UNumberUnitWidth value.
*
* @internal ICU 60: The numeric value may change over time; see ICU ticket #12420.
*/
UNUM_UNIT_WIDTH_COUNT = 7
} UNumberUnitWidth;
/**
* An enum declaring the strategy for when and how to display grouping separators (i.e., the
* separator, often a comma or period, after every 2-3 powers of ten). The choices are several
* pre-built strategies for different use cases that employ locale data whenever possible. Example
* outputs for 1234 and 1234567 in <em>en-IN</em>:
*
* <ul>
* <li>OFF: 1234 and 12345
* <li>MIN2: 1234 and 12,34,567
* <li>AUTO: 1,234 and 12,34,567
* <li>ON_ALIGNED: 1,234 and 12,34,567
* <li>THOUSANDS: 1,234 and 1,234,567
* </ul>
*
* <p>
* The default is AUTO, which displays grouping separators unless the locale data says that grouping
* is not customary. To force grouping for all numbers greater than 1000 consistently across locales,
* use ON_ALIGNED. On the other hand, to display grouping less frequently than the default, use MIN2
* or OFF. See the docs of each option for details.
*
* <p>
* Note: This enum specifies the strategy for grouping sizes. To set which character to use as the
* grouping separator, use the "symbols" setter.
*
* @stable ICU 63
*/
typedef enum UNumberGroupingStrategy {
/**
* Do not display grouping separators in any locale.
*
* @stable ICU 61
*/
UNUM_GROUPING_OFF,
/**
* Display grouping using locale defaults, except do not show grouping on values smaller than
* 10000 (such that there is a <em>minimum of two digits</em> before the first separator).
*
* <p>
* Note that locales may restrict grouping separators to be displayed only on 1 million or
* greater (for example, ee and hu) or disable grouping altogether (for example, bg currency).
*
* <p>
* Locale data is used to determine whether to separate larger numbers into groups of 2
* (customary in South Asia) or groups of 3 (customary in Europe and the Americas).
*
* @stable ICU 61
*/
UNUM_GROUPING_MIN2,
/**
* Display grouping using the default strategy for all locales. This is the default behavior.
*
* <p>
* Note that locales may restrict grouping separators to be displayed only on 1 million or
* greater (for example, ee and hu) or disable grouping altogether (for example, bg currency).
*
* <p>
* Locale data is used to determine whether to separate larger numbers into groups of 2
* (customary in South Asia) or groups of 3 (customary in Europe and the Americas).
*
* @stable ICU 61
*/
UNUM_GROUPING_AUTO,
/**
* Always display the grouping separator on values of at least 1000.
*
* <p>
* This option ignores the locale data that restricts or disables grouping, described in MIN2 and
* AUTO. This option may be useful to normalize the alignment of numbers, such as in a
* spreadsheet.
*
* <p>
* Locale data is used to determine whether to separate larger numbers into groups of 2
* (customary in South Asia) or groups of 3 (customary in Europe and the Americas).
*
* @stable ICU 61
*/
UNUM_GROUPING_ON_ALIGNED,
/**
* Use the Western defaults: groups of 3 and enabled for all numbers 1000 or greater. Do not use
* locale data for determining the grouping strategy.
*
* @stable ICU 61
*/
UNUM_GROUPING_THOUSANDS
#ifndef U_HIDE_INTERNAL_API
,
/**
* One more than the highest UNumberGroupingStrategy value.
*
* @internal ICU 62: The numeric value may change over time; see ICU ticket #12420.
*/
UNUM_GROUPING_COUNT
#endif /* U_HIDE_INTERNAL_API */
} UNumberGroupingStrategy;
/**
* An enum declaring how to denote positive and negative numbers. Example outputs when formatting
* 123, 0, and -123 in <em>en-US</em>:
*
* <ul>
* <li>AUTO: "123", "0", and "-123"
* <li>ALWAYS: "+123", "+0", and "-123"
* <li>NEVER: "123", "0", and "123"
* <li>ACCOUNTING: "$123", "$0", and "($123)"
* <li>ACCOUNTING_ALWAYS: "+$123", "+$0", and "($123)"
* <li>EXCEPT_ZERO: "+123", "0", and "-123"
* <li>ACCOUNTING_EXCEPT_ZERO: "+$123", "$0", and "($123)"
* </ul>
*
* <p>
* The exact format, including the position and the code point of the sign, differ by locale.
*
* @stable ICU 60
*/
typedef enum UNumberSignDisplay {
/**
* Show the minus sign on negative numbers, and do not show the sign on positive numbers. This is the default
* behavior.
*
* If using this option, a sign will be displayed on negative zero, including negative numbers
* that round to zero. To hide the sign on negative zero, use the NEGATIVE option.
*
* @stable ICU 60
*/
UNUM_SIGN_AUTO,
/**
* Show the minus sign on negative numbers and the plus sign on positive numbers, including zero.
* To hide the sign on zero, see {@link UNUM_SIGN_EXCEPT_ZERO}.
*
* @stable ICU 60
*/
UNUM_SIGN_ALWAYS,
/**
* Do not show the sign on positive or negative numbers.
*
* @stable ICU 60
*/
UNUM_SIGN_NEVER,
/**
* Use the locale-dependent accounting format on negative numbers, and do not show the sign on positive numbers.
*
* <p>
* The accounting format is defined in CLDR and varies by locale; in many Western locales, the format is a pair
* of parentheses around the number.
*
* <p>
* Note: Since CLDR defines the accounting format in the monetary context only, this option falls back to the
* AUTO sign display strategy when formatting without a currency unit. This limitation may be lifted in the
* future.
*
* @stable ICU 60
*/
UNUM_SIGN_ACCOUNTING,
/**
* Use the locale-dependent accounting format on negative numbers, and show the plus sign on
* positive numbers, including zero. For more information on the accounting format, see the
* ACCOUNTING sign display strategy. To hide the sign on zero, see
* {@link UNUM_SIGN_ACCOUNTING_EXCEPT_ZERO}.
*
* @stable ICU 60
*/
UNUM_SIGN_ACCOUNTING_ALWAYS,
/**
* Show the minus sign on negative numbers and the plus sign on positive numbers. Do not show a
* sign on zero, numbers that round to zero, or NaN.
*
* @stable ICU 61
*/
UNUM_SIGN_EXCEPT_ZERO,
/**
* Use the locale-dependent accounting format on negative numbers, and show the plus sign on
* positive numbers. Do not show a sign on zero, numbers that round to zero, or NaN. For more
* information on the accounting format, see the ACCOUNTING sign display strategy.
*
* @stable ICU 61
*/
UNUM_SIGN_ACCOUNTING_EXCEPT_ZERO,
/**
* Same as AUTO, but do not show the sign on negative zero.
*
* @stable ICU 69
*/
UNUM_SIGN_NEGATIVE,
/**
* Same as ACCOUNTING, but do not show the sign on negative zero.
*
* @stable ICU 69
*/
UNUM_SIGN_ACCOUNTING_NEGATIVE,
// Do not conditionalize the following with #ifndef U_HIDE_INTERNAL_API,
// needed for unconditionalized struct MacroProps
/**
* One more than the highest UNumberSignDisplay value.
*
* @internal ICU 60: The numeric value may change over time; see ICU ticket #12420.
*/
UNUM_SIGN_COUNT = 9,
} UNumberSignDisplay;
/**
* An enum declaring how to render the decimal separator.
*
* <p>
* <ul>
* <li>UNUM_DECIMAL_SEPARATOR_AUTO: "1", "1.1"
* <li>UNUM_DECIMAL_SEPARATOR_ALWAYS: "1.", "1.1"
* </ul>
*
* @stable ICU 60
*/
typedef enum UNumberDecimalSeparatorDisplay {
/**
* Show the decimal separator when there are one or more digits to display after the separator, and do not show
* it otherwise. This is the default behavior.
*
* @stable ICU 60
*/
UNUM_DECIMAL_SEPARATOR_AUTO,
/**
* Always show the decimal separator, even if there are no digits to display after the separator.
*
* @stable ICU 60
*/
UNUM_DECIMAL_SEPARATOR_ALWAYS,
// Do not conditionalize the following with #ifndef U_HIDE_INTERNAL_API,
// needed for unconditionalized struct MacroProps
/**
* One more than the highest UNumberDecimalSeparatorDisplay value.
*
* @internal ICU 60: The numeric value may change over time; see ICU ticket #12420.
*/
UNUM_DECIMAL_SEPARATOR_COUNT
} UNumberDecimalSeparatorDisplay;
/**
* An enum declaring how to render trailing zeros.
*
* - UNUM_TRAILING_ZERO_AUTO: 0.90, 1.00, 1.10
* - UNUM_TRAILING_ZERO_HIDE_IF_WHOLE: 0.90, 1, 1.10
*
* @stable ICU 69
*/
typedef enum UNumberTrailingZeroDisplay {
/**
* Display trailing zeros according to the settings for minimum fraction and significant digits.
*
* @stable ICU 69
*/
UNUM_TRAILING_ZERO_AUTO,
/**
* Same as AUTO, but hide trailing zeros after the decimal separator if they are all zero.
*
* @stable ICU 69
*/
UNUM_TRAILING_ZERO_HIDE_IF_WHOLE,
} UNumberTrailingZeroDisplay;
struct UNumberFormatter;
/**
* C-compatible version of icu::number::LocalizedNumberFormatter.
*
* NOTE: This is a C-compatible API; C++ users should build against numberformatter.h instead.
*
* @stable ICU 62
*/
typedef struct UNumberFormatter UNumberFormatter;
struct UFormattedNumber;
/**
* C-compatible version of icu::number::FormattedNumber.
*
* NOTE: This is a C-compatible API; C++ users should build against numberformatter.h instead.
*
* @stable ICU 62
*/
typedef struct UFormattedNumber UFormattedNumber;
/**
* Creates a new UNumberFormatter for the given skeleton string and locale. This is currently the only
* method for creating a new UNumberFormatter.
*
* Objects of type UNumberFormatter returned by this method are threadsafe.
*
* For more details on skeleton strings, see the documentation in numberformatter.h. For more details on
* the usage of this API, see the documentation at the top of unumberformatter.h.
*
* For more information on number skeleton strings, see:
* https://unicode-org.github.io/icu/userguide/format_parse/numbers/skeletons.html
*
* NOTE: This is a C-compatible API; C++ users should build against numberformatter.h instead.
*
* @param skeleton The skeleton string, like u"percent precision-integer"
* @param skeletonLen The number of UChars in the skeleton string, or -1 if it is NUL-terminated.
* @param locale The NUL-terminated locale ID.
* @param ec Set if an error occurs.
* @stable ICU 62
*/
U_CAPI UNumberFormatter* U_EXPORT2
unumf_openForSkeletonAndLocale(const UChar* skeleton, int32_t skeletonLen, const char* locale,
UErrorCode* ec);
/**
* Like unumf_openForSkeletonAndLocale, but accepts a UParseError, which will be populated with the
* location of a skeleton syntax error if such a syntax error exists.
*
* For more information on number skeleton strings, see:
* https://unicode-org.github.io/icu/userguide/format_parse/numbers/skeletons.html
*
* @param skeleton The skeleton string, like u"percent precision-integer"
* @param skeletonLen The number of UChars in the skeleton string, or -1 if it is NUL-terminated.
* @param locale The NUL-terminated locale ID.
* @param perror A parse error struct populated if an error occurs when parsing. Can be NULL.
* If no error occurs, perror->offset will be set to -1.
* @param ec Set if an error occurs.
* @stable ICU 64
*/
U_CAPI UNumberFormatter* U_EXPORT2
unumf_openForSkeletonAndLocaleWithError(
const UChar* skeleton, int32_t skeletonLen, const char* locale, UParseError* perror, UErrorCode* ec);
/**
* Uses a UNumberFormatter to format an integer to a UFormattedNumber. A string, field position, and other
* information can be retrieved from the UFormattedNumber.
*
* The UNumberFormatter can be shared between threads. Each thread should have its own local
* UFormattedNumber, however, for storing the result of the formatting operation.
*
* NOTE: This is a C-compatible API; C++ users should build against numberformatter.h instead.
*
* @param uformatter A formatter object created by unumf_openForSkeletonAndLocale or similar.
* @param value The number to be formatted.
* @param uresult The object that will be mutated to store the result; see unumf_openResult.
* @param ec Set if an error occurs.
* @stable ICU 62
*/
U_CAPI void U_EXPORT2
unumf_formatInt(const UNumberFormatter* uformatter, int64_t value, UFormattedNumber* uresult,
UErrorCode* ec);
/**
* Uses a UNumberFormatter to format a double to a UFormattedNumber. A string, field position, and other
* information can be retrieved from the UFormattedNumber.
*
* The UNumberFormatter can be shared between threads. Each thread should have its own local
* UFormattedNumber, however, for storing the result of the formatting operation.
*
* NOTE: This is a C-compatible API; C++ users should build against numberformatter.h instead.
*
* @param uformatter A formatter object created by unumf_openForSkeletonAndLocale or similar.
* @param value The number to be formatted.
* @param uresult The object that will be mutated to store the result; see unumf_openResult.
* @param ec Set if an error occurs.
* @stable ICU 62
*/
U_CAPI void U_EXPORT2
unumf_formatDouble(const UNumberFormatter* uformatter, double value, UFormattedNumber* uresult,
UErrorCode* ec);
/**
* Uses a UNumberFormatter to format a decimal number to a UFormattedNumber. A string, field position, and
* other information can be retrieved from the UFormattedNumber.
*
* The UNumberFormatter can be shared between threads. Each thread should have its own local
* UFormattedNumber, however, for storing the result of the formatting operation.
*
* The syntax of the unformatted number is a "numeric string" as defined in the Decimal Arithmetic
* Specification, available at http://speleotrove.com/decimal
*
* NOTE: This is a C-compatible API; C++ users should build against numberformatter.h instead.
*
* @param uformatter A formatter object created by unumf_openForSkeletonAndLocale or similar.
* @param value The numeric string to be formatted.
* @param valueLen The length of the numeric string, or -1 if it is NUL-terminated.
* @param uresult The object that will be mutated to store the result; see unumf_openResult.
* @param ec Set if an error occurs.
* @stable ICU 62
*/
U_CAPI void U_EXPORT2
unumf_formatDecimal(const UNumberFormatter* uformatter, const char* value, int32_t valueLen,
UFormattedNumber* uresult, UErrorCode* ec);
/**
* Releases the UNumberFormatter created by unumf_openForSkeletonAndLocale().
*
* @param uformatter An object created by unumf_openForSkeletonAndLocale().
* @stable ICU 62
*/
U_CAPI void U_EXPORT2
unumf_close(UNumberFormatter* uformatter);
#if U_SHOW_CPLUSPLUS_API
U_NAMESPACE_BEGIN
/**
* \class LocalUNumberFormatterPointer
* "Smart pointer" class; closes a UNumberFormatter via unumf_close().
* For most methods see the LocalPointerBase base class.
*
* Usage:
* <pre>
* LocalUNumberFormatterPointer uformatter(unumf_openForSkeletonAndLocale(...));
* // no need to explicitly call unumf_close()
* </pre>
*
* @see LocalPointerBase
* @see LocalPointer
* @stable ICU 62
*/
U_DEFINE_LOCAL_OPEN_POINTER(LocalUNumberFormatterPointer, UNumberFormatter, unumf_close);
/**
* \class LocalUFormattedNumberPointer
* "Smart pointer" class; closes a UFormattedNumber via unumf_closeResult().
* For most methods see the LocalPointerBase base class.
*
* Usage:
* <pre>
* LocalUFormattedNumberPointer uformatter(unumf_openResult(...));
* // no need to explicitly call unumf_closeResult()
* </pre>
*
* @see LocalPointerBase
* @see LocalPointer
* @stable ICU 62
*/
U_DEFINE_LOCAL_OPEN_POINTER(LocalUFormattedNumberPointer, UFormattedNumber, unumf_closeResult);
U_NAMESPACE_END
#endif // U_SHOW_CPLUSPLUS_API
#endif /* #if !UCONFIG_NO_FORMATTING */
#endif //__UNUMBERFORMATTER_H__
third_party/icu4c/ndk_headers/unicode/uscript.h
Vendored
+710
View File
@@ -0,0 +1,710 @@
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
**********************************************************************
* Copyright (C) 1997-2016, International Business Machines
* Corporation and others. All Rights Reserved.
**********************************************************************
*
* File USCRIPT.H
*
* Modification History:
*
* Date Name Description
* 07/06/2001 Ram Creation.
******************************************************************************
*/
#ifndef USCRIPT_H
#define USCRIPT_H
#include "unicode/utypes.h"
/**
* \file
* \brief C API: Unicode Script Information
*/
/**
* Constants for ISO 15924 script codes.
*
* The current set of script code constants supports at least all scripts
* that are encoded in the version of Unicode which ICU currently supports.
* The names of the constants are usually derived from the
* Unicode script property value aliases.
* See UAX #24 Unicode Script Property (http://www.unicode.org/reports/tr24/)
* and http://www.unicode.org/Public/UCD/latest/ucd/PropertyValueAliases.txt .
*
* In addition, constants for many ISO 15924 script codes
* are included, for use with language tags, CLDR data, and similar.
* Some of those codes are not used in the Unicode Character Database (UCD).
* For example, there are no characters that have a UCD script property value of
* Hans or Hant. All Han ideographs have the Hani script property value in Unicode.
*
* Private-use codes Qaaa..Qabx are not included, except as used in the UCD or in CLDR.
*
* Starting with ICU 55, script codes are only added when their scripts
* have been or will certainly be encoded in Unicode,
* and have been assigned Unicode script property value aliases,
* to ensure that their script names are stable and match the names of the constants.
* Script codes like Latf and Aran that are not subject to separate encoding
* may be added at any time.
*
* @stable ICU 2.2
*/
typedef enum UScriptCode {
/*
* Note: UScriptCode constants and their ISO script code comments
* are parsed by preparseucd.py.
* It matches lines like
* USCRIPT_<Unicode Script value name> = <integer>, / * <ISO script code> * /
*/
/** @stable ICU 2.2 */
USCRIPT_INVALID_CODE = -1,
/** @stable ICU 2.2 */
USCRIPT_COMMON = 0, /* Zyyy */
/** @stable ICU 2.2 */
USCRIPT_INHERITED = 1, /* Zinh */ /* "Code for inherited script", for non-spacing combining marks; also Qaai */
/** @stable ICU 2.2 */
USCRIPT_ARABIC = 2, /* Arab */
/** @stable ICU 2.2 */
USCRIPT_ARMENIAN = 3, /* Armn */
/** @stable ICU 2.2 */
USCRIPT_BENGALI = 4, /* Beng */
/** @stable ICU 2.2 */
USCRIPT_BOPOMOFO = 5, /* Bopo */
/** @stable ICU 2.2 */
USCRIPT_CHEROKEE = 6, /* Cher */
/** @stable ICU 2.2 */
USCRIPT_COPTIC = 7, /* Copt */
/** @stable ICU 2.2 */
USCRIPT_CYRILLIC = 8, /* Cyrl */
/** @stable ICU 2.2 */
USCRIPT_DESERET = 9, /* Dsrt */
/** @stable ICU 2.2 */
USCRIPT_DEVANAGARI = 10, /* Deva */
/** @stable ICU 2.2 */
USCRIPT_ETHIOPIC = 11, /* Ethi */
/** @stable ICU 2.2 */
USCRIPT_GEORGIAN = 12, /* Geor */
/** @stable ICU 2.2 */
USCRIPT_GOTHIC = 13, /* Goth */
/** @stable ICU 2.2 */
USCRIPT_GREEK = 14, /* Grek */
/** @stable ICU 2.2 */
USCRIPT_GUJARATI = 15, /* Gujr */
/** @stable ICU 2.2 */
USCRIPT_GURMUKHI = 16, /* Guru */
/** @stable ICU 2.2 */
USCRIPT_HAN = 17, /* Hani */
/** @stable ICU 2.2 */
USCRIPT_HANGUL = 18, /* Hang */
/** @stable ICU 2.2 */
USCRIPT_HEBREW = 19, /* Hebr */
/** @stable ICU 2.2 */
USCRIPT_HIRAGANA = 20, /* Hira */
/** @stable ICU 2.2 */
USCRIPT_KANNADA = 21, /* Knda */
/** @stable ICU 2.2 */
USCRIPT_KATAKANA = 22, /* Kana */
/** @stable ICU 2.2 */
USCRIPT_KHMER = 23, /* Khmr */
/** @stable ICU 2.2 */
USCRIPT_LAO = 24, /* Laoo */
/** @stable ICU 2.2 */
USCRIPT_LATIN = 25, /* Latn */
/** @stable ICU 2.2 */
USCRIPT_MALAYALAM = 26, /* Mlym */
/** @stable ICU 2.2 */
USCRIPT_MONGOLIAN = 27, /* Mong */
/** @stable ICU 2.2 */
USCRIPT_MYANMAR = 28, /* Mymr */
/** @stable ICU 2.2 */
USCRIPT_OGHAM = 29, /* Ogam */
/** @stable ICU 2.2 */
USCRIPT_OLD_ITALIC = 30, /* Ital */
/** @stable ICU 2.2 */
USCRIPT_ORIYA = 31, /* Orya */
/** @stable ICU 2.2 */
USCRIPT_RUNIC = 32, /* Runr */
/** @stable ICU 2.2 */
USCRIPT_SINHALA = 33, /* Sinh */
/** @stable ICU 2.2 */
USCRIPT_SYRIAC = 34, /* Syrc */
/** @stable ICU 2.2 */
USCRIPT_TAMIL = 35, /* Taml */
/** @stable ICU 2.2 */
USCRIPT_TELUGU = 36, /* Telu */
/** @stable ICU 2.2 */
USCRIPT_THAANA = 37, /* Thaa */
/** @stable ICU 2.2 */
USCRIPT_THAI = 38, /* Thai */
/** @stable ICU 2.2 */
USCRIPT_TIBETAN = 39, /* Tibt */
/** Canadian_Aboriginal script. @stable ICU 2.6 */
USCRIPT_CANADIAN_ABORIGINAL = 40, /* Cans */
/** Canadian_Aboriginal script (alias). @stable ICU 2.2 */
USCRIPT_UCAS = USCRIPT_CANADIAN_ABORIGINAL,
/** @stable ICU 2.2 */
USCRIPT_YI = 41, /* Yiii */
/* New scripts in Unicode 3.2 */
/** @stable ICU 2.2 */
USCRIPT_TAGALOG = 42, /* Tglg */
/** @stable ICU 2.2 */
USCRIPT_HANUNOO = 43, /* Hano */
/** @stable ICU 2.2 */
USCRIPT_BUHID = 44, /* Buhd */
/** @stable ICU 2.2 */
USCRIPT_TAGBANWA = 45, /* Tagb */
/* New scripts in Unicode 4 */
/** @stable ICU 2.6 */
USCRIPT_BRAILLE = 46, /* Brai */
/** @stable ICU 2.6 */
USCRIPT_CYPRIOT = 47, /* Cprt */
/** @stable ICU 2.6 */
USCRIPT_LIMBU = 48, /* Limb */
/** @stable ICU 2.6 */
USCRIPT_LINEAR_B = 49, /* Linb */
/** @stable ICU 2.6 */
USCRIPT_OSMANYA = 50, /* Osma */
/** @stable ICU 2.6 */
USCRIPT_SHAVIAN = 51, /* Shaw */
/** @stable ICU 2.6 */
USCRIPT_TAI_LE = 52, /* Tale */
/** @stable ICU 2.6 */
USCRIPT_UGARITIC = 53, /* Ugar */
/** New script code in Unicode 4.0.1 @stable ICU 3.0 */
USCRIPT_KATAKANA_OR_HIRAGANA = 54,/*Hrkt */
/* New scripts in Unicode 4.1 */
/** @stable ICU 3.4 */
USCRIPT_BUGINESE = 55, /* Bugi */
/** @stable ICU 3.4 */
USCRIPT_GLAGOLITIC = 56, /* Glag */
/** @stable ICU 3.4 */
USCRIPT_KHAROSHTHI = 57, /* Khar */
/** @stable ICU 3.4 */
USCRIPT_SYLOTI_NAGRI = 58, /* Sylo */
/** @stable ICU 3.4 */
USCRIPT_NEW_TAI_LUE = 59, /* Talu */
/** @stable ICU 3.4 */
USCRIPT_TIFINAGH = 60, /* Tfng */
/** @stable ICU 3.4 */
USCRIPT_OLD_PERSIAN = 61, /* Xpeo */
/* New script codes from Unicode and ISO 15924 */
/** @stable ICU 3.6 */
USCRIPT_BALINESE = 62, /* Bali */
/** @stable ICU 3.6 */
USCRIPT_BATAK = 63, /* Batk */
/** @stable ICU 3.6 */
USCRIPT_BLISSYMBOLS = 64, /* Blis */
/** @stable ICU 3.6 */
USCRIPT_BRAHMI = 65, /* Brah */
/** @stable ICU 3.6 */
USCRIPT_CHAM = 66, /* Cham */
/** @stable ICU 3.6 */
USCRIPT_CIRTH = 67, /* Cirt */
/** @stable ICU 3.6 */
USCRIPT_OLD_CHURCH_SLAVONIC_CYRILLIC = 68, /* Cyrs */
/** @stable ICU 3.6 */
USCRIPT_DEMOTIC_EGYPTIAN = 69, /* Egyd */
/** @stable ICU 3.6 */
USCRIPT_HIERATIC_EGYPTIAN = 70, /* Egyh */
/** @stable ICU 3.6 */
USCRIPT_EGYPTIAN_HIEROGLYPHS = 71, /* Egyp */
/** @stable ICU 3.6 */
USCRIPT_KHUTSURI = 72, /* Geok */
/** @stable ICU 3.6 */
USCRIPT_SIMPLIFIED_HAN = 73, /* Hans */
/** @stable ICU 3.6 */
USCRIPT_TRADITIONAL_HAN = 74, /* Hant */
/** @stable ICU 3.6 */
USCRIPT_PAHAWH_HMONG = 75, /* Hmng */
/** @stable ICU 3.6 */
USCRIPT_OLD_HUNGARIAN = 76, /* Hung */
/** @stable ICU 3.6 */
USCRIPT_HARAPPAN_INDUS = 77, /* Inds */
/** @stable ICU 3.6 */
USCRIPT_JAVANESE = 78, /* Java */
/** @stable ICU 3.6 */
USCRIPT_KAYAH_LI = 79, /* Kali */
/** @stable ICU 3.6 */
USCRIPT_LATIN_FRAKTUR = 80, /* Latf */
/** @stable ICU 3.6 */
USCRIPT_LATIN_GAELIC = 81, /* Latg */
/** @stable ICU 3.6 */
USCRIPT_LEPCHA = 82, /* Lepc */
/** @stable ICU 3.6 */
USCRIPT_LINEAR_A = 83, /* Lina */
/** @stable ICU 4.6 */
USCRIPT_MANDAIC = 84, /* Mand */
/** @stable ICU 3.6 */
USCRIPT_MANDAEAN = USCRIPT_MANDAIC,
/** @stable ICU 3.6 */
USCRIPT_MAYAN_HIEROGLYPHS = 85, /* Maya */
/** @stable ICU 4.6 */
USCRIPT_MEROITIC_HIEROGLYPHS = 86, /* Mero */
/** @stable ICU 3.6 */
USCRIPT_MEROITIC = USCRIPT_MEROITIC_HIEROGLYPHS,
/** @stable ICU 3.6 */
USCRIPT_NKO = 87, /* Nkoo */
/** @stable ICU 3.6 */
USCRIPT_ORKHON = 88, /* Orkh */
/** @stable ICU 3.6 */
USCRIPT_OLD_PERMIC = 89, /* Perm */
/** @stable ICU 3.6 */
USCRIPT_PHAGS_PA = 90, /* Phag */
/** @stable ICU 3.6 */
USCRIPT_PHOENICIAN = 91, /* Phnx */
/** @stable ICU 52 */
USCRIPT_MIAO = 92, /* Plrd */
/** @stable ICU 3.6 */
USCRIPT_PHONETIC_POLLARD = USCRIPT_MIAO,
/** @stable ICU 3.6 */
USCRIPT_RONGORONGO = 93, /* Roro */
/** @stable ICU 3.6 */
USCRIPT_SARATI = 94, /* Sara */
/** @stable ICU 3.6 */
USCRIPT_ESTRANGELO_SYRIAC = 95, /* Syre */
/** @stable ICU 3.6 */
USCRIPT_WESTERN_SYRIAC = 96, /* Syrj */
/** @stable ICU 3.6 */
USCRIPT_EASTERN_SYRIAC = 97, /* Syrn */
/** @stable ICU 3.6 */
USCRIPT_TENGWAR = 98, /* Teng */
/** @stable ICU 3.6 */
USCRIPT_VAI = 99, /* Vaii */
/** @stable ICU 3.6 */
USCRIPT_VISIBLE_SPEECH = 100,/* Visp */
/** @stable ICU 3.6 */
USCRIPT_CUNEIFORM = 101,/* Xsux */
/** @stable ICU 3.6 */
USCRIPT_UNWRITTEN_LANGUAGES = 102,/* Zxxx */
/** @stable ICU 3.6 */
USCRIPT_UNKNOWN = 103,/* Zzzz */ /* Unknown="Code for uncoded script", for unassigned code points */
/** @stable ICU 3.8 */
USCRIPT_CARIAN = 104,/* Cari */
/** @stable ICU 3.8 */
USCRIPT_JAPANESE = 105,/* Jpan */
/** @stable ICU 3.8 */
USCRIPT_LANNA = 106,/* Lana */
/** @stable ICU 3.8 */
USCRIPT_LYCIAN = 107,/* Lyci */
/** @stable ICU 3.8 */
USCRIPT_LYDIAN = 108,/* Lydi */
/** @stable ICU 3.8 */
USCRIPT_OL_CHIKI = 109,/* Olck */
/** @stable ICU 3.8 */
USCRIPT_REJANG = 110,/* Rjng */
/** @stable ICU 3.8 */
USCRIPT_SAURASHTRA = 111,/* Saur */
/** Sutton SignWriting @stable ICU 3.8 */
USCRIPT_SIGN_WRITING = 112,/* Sgnw */
/** @stable ICU 3.8 */
USCRIPT_SUNDANESE = 113,/* Sund */
/** @stable ICU 3.8 */
USCRIPT_MOON = 114,/* Moon */
/** @stable ICU 3.8 */
USCRIPT_MEITEI_MAYEK = 115,/* Mtei */
/** @stable ICU 4.0 */
USCRIPT_IMPERIAL_ARAMAIC = 116,/* Armi */
/** @stable ICU 4.0 */
USCRIPT_AVESTAN = 117,/* Avst */
/** @stable ICU 4.0 */
USCRIPT_CHAKMA = 118,/* Cakm */
/** @stable ICU 4.0 */
USCRIPT_KOREAN = 119,/* Kore */
/** @stable ICU 4.0 */
USCRIPT_KAITHI = 120,/* Kthi */
/** @stable ICU 4.0 */
USCRIPT_MANICHAEAN = 121,/* Mani */
/** @stable ICU 4.0 */
USCRIPT_INSCRIPTIONAL_PAHLAVI = 122,/* Phli */
/** @stable ICU 4.0 */
USCRIPT_PSALTER_PAHLAVI = 123,/* Phlp */
/** @stable ICU 4.0 */
USCRIPT_BOOK_PAHLAVI = 124,/* Phlv */
/** @stable ICU 4.0 */
USCRIPT_INSCRIPTIONAL_PARTHIAN = 125,/* Prti */
/** @stable ICU 4.0 */
USCRIPT_SAMARITAN = 126,/* Samr */
/** @stable ICU 4.0 */
USCRIPT_TAI_VIET = 127,/* Tavt */
/** @stable ICU 4.0 */
USCRIPT_MATHEMATICAL_NOTATION = 128,/* Zmth */
/** @stable ICU 4.0 */
USCRIPT_SYMBOLS = 129,/* Zsym */
/** @stable ICU 4.4 */
USCRIPT_BAMUM = 130,/* Bamu */
/** @stable ICU 4.4 */
USCRIPT_LISU = 131,/* Lisu */
/** @stable ICU 4.4 */
USCRIPT_NAKHI_GEBA = 132,/* Nkgb */
/** @stable ICU 4.4 */
USCRIPT_OLD_SOUTH_ARABIAN = 133,/* Sarb */
/** @stable ICU 4.6 */
USCRIPT_BASSA_VAH = 134,/* Bass */
/** @stable ICU 54 */
USCRIPT_DUPLOYAN = 135,/* Dupl */
/** @stable ICU 4.6 */
USCRIPT_ELBASAN = 136,/* Elba */
/** @stable ICU 4.6 */
USCRIPT_GRANTHA = 137,/* Gran */
/** @stable ICU 4.6 */
USCRIPT_KPELLE = 138,/* Kpel */
/** @stable ICU 4.6 */
USCRIPT_LOMA = 139,/* Loma */
/** Mende Kikakui @stable ICU 4.6 */
USCRIPT_MENDE = 140,/* Mend */
/** @stable ICU 4.6 */
USCRIPT_MEROITIC_CURSIVE = 141,/* Merc */
/** @stable ICU 4.6 */
USCRIPT_OLD_NORTH_ARABIAN = 142,/* Narb */
/** @stable ICU 4.6 */
USCRIPT_NABATAEAN = 143,/* Nbat */
/** @stable ICU 4.6 */
USCRIPT_PALMYRENE = 144,/* Palm */
/** @stable ICU 54 */
USCRIPT_KHUDAWADI = 145,/* Sind */
/** @stable ICU 4.6 */
USCRIPT_SINDHI = USCRIPT_KHUDAWADI,
/** @stable ICU 4.6 */
USCRIPT_WARANG_CITI = 146,/* Wara */
/** @stable ICU 4.8 */
USCRIPT_AFAKA = 147,/* Afak */
/** @stable ICU 4.8 */
USCRIPT_JURCHEN = 148,/* Jurc */
/** @stable ICU 4.8 */
USCRIPT_MRO = 149,/* Mroo */
/** @stable ICU 4.8 */
USCRIPT_NUSHU = 150,/* Nshu */
/** @stable ICU 4.8 */
USCRIPT_SHARADA = 151,/* Shrd */
/** @stable ICU 4.8 */
USCRIPT_SORA_SOMPENG = 152,/* Sora */
/** @stable ICU 4.8 */
USCRIPT_TAKRI = 153,/* Takr */
/** @stable ICU 4.8 */
USCRIPT_TANGUT = 154,/* Tang */
/** @stable ICU 4.8 */
USCRIPT_WOLEAI = 155,/* Wole */
/** @stable ICU 49 */
USCRIPT_ANATOLIAN_HIEROGLYPHS = 156,/* Hluw */
/** @stable ICU 49 */
USCRIPT_KHOJKI = 157,/* Khoj */
/** @stable ICU 49 */
USCRIPT_TIRHUTA = 158,/* Tirh */
/** @stable ICU 52 */
USCRIPT_CAUCASIAN_ALBANIAN = 159,/* Aghb */
/** @stable ICU 52 */
USCRIPT_MAHAJANI = 160,/* Mahj */
/** @stable ICU 54 */
USCRIPT_AHOM = 161,/* Ahom */
/** @stable ICU 54 */
USCRIPT_HATRAN = 162,/* Hatr */
/** @stable ICU 54 */
USCRIPT_MODI = 163,/* Modi */
/** @stable ICU 54 */
USCRIPT_MULTANI = 164,/* Mult */
/** @stable ICU 54 */
USCRIPT_PAU_CIN_HAU = 165,/* Pauc */
/** @stable ICU 54 */
USCRIPT_SIDDHAM = 166,/* Sidd */
/** @stable ICU 58 */
USCRIPT_ADLAM = 167,/* Adlm */
/** @stable ICU 58 */
USCRIPT_BHAIKSUKI = 168,/* Bhks */
/** @stable ICU 58 */
USCRIPT_MARCHEN = 169,/* Marc */
/** @stable ICU 58 */
USCRIPT_NEWA = 170,/* Newa */
/** @stable ICU 58 */
USCRIPT_OSAGE = 171,/* Osge */
/** @stable ICU 58 */
USCRIPT_HAN_WITH_BOPOMOFO = 172,/* Hanb */
/** @stable ICU 58 */
USCRIPT_JAMO = 173,/* Jamo */
/** @stable ICU 58 */
USCRIPT_SYMBOLS_EMOJI = 174,/* Zsye */
/** @stable ICU 60 */
USCRIPT_MASARAM_GONDI = 175,/* Gonm */
/** @stable ICU 60 */
USCRIPT_SOYOMBO = 176,/* Soyo */
/** @stable ICU 60 */
USCRIPT_ZANABAZAR_SQUARE = 177,/* Zanb */
/** @stable ICU 62 */
USCRIPT_DOGRA = 178,/* Dogr */
/** @stable ICU 62 */
USCRIPT_GUNJALA_GONDI = 179,/* Gong */
/** @stable ICU 62 */
USCRIPT_MAKASAR = 180,/* Maka */
/** @stable ICU 62 */
USCRIPT_MEDEFAIDRIN = 181,/* Medf */
/** @stable ICU 62 */
USCRIPT_HANIFI_ROHINGYA = 182,/* Rohg */
/** @stable ICU 62 */
USCRIPT_SOGDIAN = 183,/* Sogd */
/** @stable ICU 62 */
USCRIPT_OLD_SOGDIAN = 184,/* Sogo */
/** @stable ICU 64 */
USCRIPT_ELYMAIC = 185,/* Elym */
/** @stable ICU 64 */
USCRIPT_NYIAKENG_PUACHUE_HMONG = 186,/* Hmnp */
/** @stable ICU 64 */
USCRIPT_NANDINAGARI = 187,/* Nand */
/** @stable ICU 64 */
USCRIPT_WANCHO = 188,/* Wcho */
/** @stable ICU 66 */
USCRIPT_CHORASMIAN = 189,/* Chrs */
/** @stable ICU 66 */
USCRIPT_DIVES_AKURU = 190,/* Diak */
/** @stable ICU 66 */
USCRIPT_KHITAN_SMALL_SCRIPT = 191,/* Kits */
/** @stable ICU 66 */
USCRIPT_YEZIDI = 192,/* Yezi */
/** @stable ICU 70 */
USCRIPT_CYPRO_MINOAN = 193,/* Cpmn */
/** @stable ICU 70 */
USCRIPT_OLD_UYGHUR = 194,/* Ougr */
/** @stable ICU 70 */
USCRIPT_TANGSA = 195,/* Tnsa */
/** @stable ICU 70 */
USCRIPT_TOTO = 196,/* Toto */
/** @stable ICU 70 */
USCRIPT_VITHKUQI = 197,/* Vith */
/** @stable ICU 72 */
USCRIPT_KAWI = 198,/* Kawi */
/** @stable ICU 72 */
USCRIPT_NAG_MUNDARI = 199,/* Nagm */
} UScriptCode;
/**
* Gets the script codes associated with the given locale or ISO 15924 abbreviation or name.
* Fills in USCRIPT_MALAYALAM given "Malayam" OR "Mlym".
* Fills in USCRIPT_LATIN given "en" OR "en_US"
* If the required capacity is greater than the capacity of the destination buffer,
* then the error code is set to U_BUFFER_OVERFLOW_ERROR and the required capacity is returned.
*
* <p>Note: To search by short or long script alias only, use
* u_getPropertyValueEnum(UCHAR_SCRIPT, alias) instead. That does
* a fast lookup with no access of the locale data.
*
* @param nameOrAbbrOrLocale name of the script, as given in
* PropertyValueAliases.txt, or ISO 15924 code or locale
* @param fillIn the UScriptCode buffer to fill in the script code
* @param capacity the capacity (size) of UScriptCode buffer passed in.
* @param err the error status code.
* @return The number of script codes filled in the buffer passed in
* @stable ICU 2.4
*/
U_CAPI int32_t U_EXPORT2
uscript_getCode(const char* nameOrAbbrOrLocale,UScriptCode* fillIn,int32_t capacity,UErrorCode *err);
/**
* Returns the long Unicode script name, if there is one.
* Otherwise returns the 4-letter ISO 15924 script code.
* Returns "Malayam" given USCRIPT_MALAYALAM.
*
* @param scriptCode UScriptCode enum
* @return long script name as given in PropertyValueAliases.txt, or the 4-letter code,
* or NULL if scriptCode is invalid
* @stable ICU 2.4
*/
U_CAPI const char* U_EXPORT2
uscript_getName(UScriptCode scriptCode);
/**
* Returns the 4-letter ISO 15924 script code,
* which is the same as the short Unicode script name if Unicode has names for the script.
* Returns "Mlym" given USCRIPT_MALAYALAM.
*
* @param scriptCode UScriptCode enum
* @return short script name (4-letter code), or NULL if scriptCode is invalid
* @stable ICU 2.4
*/
U_CAPI const char* U_EXPORT2
uscript_getShortName(UScriptCode scriptCode);
/**
* Gets the script code associated with the given codepoint.
* Returns USCRIPT_MALAYALAM given 0x0D02
* @param codepoint UChar32 codepoint
* @param err the error status code.
* @return The UScriptCode, or 0 if codepoint is invalid
* @stable ICU 2.4
*/
U_CAPI UScriptCode U_EXPORT2
uscript_getScript(UChar32 codepoint, UErrorCode *err);
/**
* Do the Script_Extensions of code point c contain script sc?
* If c does not have explicit Script_Extensions, then this tests whether
* c has the Script property value sc.
*
* Some characters are commonly used in multiple scripts.
* For more information, see UAX #24: http://www.unicode.org/reports/tr24/.
* @param c code point
* @param sc script code
* @return true if sc is in Script_Extensions(c)
* @stable ICU 49
*/
U_CAPI UBool U_EXPORT2
uscript_hasScript(UChar32 c, UScriptCode sc);
/**
* Writes code point c's Script_Extensions as a list of UScriptCode values
* to the output scripts array and returns the number of script codes.
* - If c does have Script_Extensions, then the Script property value
* (normally Common or Inherited) is not included.
* - If c does not have Script_Extensions, then the one Script code is written to the output array.
* - If c is not a valid code point, then the one USCRIPT_UNKNOWN code is written.
* In other words, if the return value is 1,
* then the output array contains exactly c's single Script code.
* If the return value is n>=2, then the output array contains c's n Script_Extensions script codes.
*
* Some characters are commonly used in multiple scripts.
* For more information, see UAX #24: http://www.unicode.org/reports/tr24/.
*
* If there are more than capacity script codes to be written, then
* U_BUFFER_OVERFLOW_ERROR is set and the number of Script_Extensions is returned.
* (Usual ICU buffer handling behavior.)
*
* @param c code point
* @param scripts output script code array
* @param capacity capacity of the scripts array
* @param errorCode Standard ICU error code. Its input value must
* pass the U_SUCCESS() test, or else the function returns
* immediately. Check for U_FAILURE() on output or use with
* function chaining. (See User Guide for details.)
* @return number of script codes in c's Script_Extensions, or 1 for the single Script value,
* written to scripts unless U_BUFFER_OVERFLOW_ERROR indicates insufficient capacity
* @stable ICU 49
*/
U_CAPI int32_t U_EXPORT2
uscript_getScriptExtensions(UChar32 c,
UScriptCode *scripts, int32_t capacity,
UErrorCode *errorCode);
/**
* Script usage constants.
* See UAX #31 Unicode Identifier and Pattern Syntax.
* http://www.unicode.org/reports/tr31/#Table_Candidate_Characters_for_Exclusion_from_Identifiers
*
* @stable ICU 51
*/
typedef enum UScriptUsage {
/** Not encoded in Unicode. @stable ICU 51 */
USCRIPT_USAGE_NOT_ENCODED,
/** Unknown script usage. @stable ICU 51 */
USCRIPT_USAGE_UNKNOWN,
/** Candidate for Exclusion from Identifiers. @stable ICU 51 */
USCRIPT_USAGE_EXCLUDED,
/** Limited Use script. @stable ICU 51 */
USCRIPT_USAGE_LIMITED_USE,
/** Aspirational Use script. @stable ICU 51 */
USCRIPT_USAGE_ASPIRATIONAL,
/** Recommended script. @stable ICU 51 */
USCRIPT_USAGE_RECOMMENDED
} UScriptUsage;
/**
* Writes the script sample character string.
* This string normally consists of one code point but might be longer.
* The string is empty if the script is not encoded.
*
* @param script script code
* @param dest output string array
* @param capacity number of UChars in the dest array
* @param pErrorCode standard ICU in/out error code, must pass U_SUCCESS() on input
* @return the string length, even if U_BUFFER_OVERFLOW_ERROR
* @stable ICU 51
*/
U_CAPI int32_t U_EXPORT2
uscript_getSampleString(UScriptCode script, UChar *dest, int32_t capacity, UErrorCode *pErrorCode);
#if U_SHOW_CPLUSPLUS_API
U_NAMESPACE_BEGIN
class UnicodeString;
U_NAMESPACE_END
/**
* Returns the script sample character string.
* This string normally consists of one code point but might be longer.
* The string is empty if the script is not encoded.
*
* @param script script code
* @return the sample character string
* @stable ICU 51
*/
U_COMMON_API icu::UnicodeString U_EXPORT2
uscript_getSampleUnicodeString(UScriptCode script);
#endif
/**
* Returns the script usage according to UAX #31 Unicode Identifier and Pattern Syntax.
* Returns USCRIPT_USAGE_NOT_ENCODED if the script is not encoded in Unicode.
*
* @param script script code
* @return script usage
* @see UScriptUsage
* @stable ICU 51
*/
U_CAPI UScriptUsage U_EXPORT2
uscript_getUsage(UScriptCode script);
/**
* Returns true if the script is written right-to-left.
* For example, Arab and Hebr.
*
* @param script script code
* @return true if the script is right-to-left
* @stable ICU 51
*/
U_CAPI UBool U_EXPORT2
uscript_isRightToLeft(UScriptCode script);
/**
* Returns true if the script allows line breaks between letters (excluding hyphenation).
* Such a script typically requires dictionary-based line breaking.
* For example, Hani and Thai.
*
* @param script script code
* @return true if the script allows line breaks between letters
* @stable ICU 51
*/
U_CAPI UBool U_EXPORT2
uscript_breaksBetweenLetters(UScriptCode script);
/**
* Returns true if in modern (or most recent) usage of the script case distinctions are customary.
* For example, Latn and Cyrl.
*
* @param script script code
* @return true if the script is cased
* @stable ICU 51
*/
U_CAPI UBool U_EXPORT2
uscript_isCased(UScriptCode script);
#endif
third_party/icu4c/ndk_headers/unicode/uset.h
Vendored
+517
View File
@@ -0,0 +1,517 @@
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
*******************************************************************************
*
* Copyright (C) 2002-2014, International Business Machines
* Corporation and others. All Rights Reserved.
*
*******************************************************************************
* file name: uset.h
* encoding: UTF-8
* tab size: 8 (not used)
* indentation:4
*
* created on: 2002mar07
* created by: Markus W. Scherer
*
* C version of UnicodeSet.
*/
/**
* \file
* \brief C API: Unicode Set
*
* <p>This is a C wrapper around the C++ UnicodeSet class.</p>
*/
#ifndef __USET_H__
#define __USET_H__
#include "unicode/utypes.h"
#include "unicode/uchar.h"
#if U_SHOW_CPLUSPLUS_API
#include "unicode/localpointer.h"
#endif // U_SHOW_CPLUSPLUS_API
#ifndef USET_DEFINED
#ifndef U_IN_DOXYGEN
#define USET_DEFINED
#endif
/**
* USet is the C API type corresponding to C++ class UnicodeSet.
* Use the uset_* API to manipulate. Create with
* uset_open*, and destroy with uset_close.
* @stable ICU 2.4
*/
typedef struct USet USet;
#endif
/**
* Bitmask values to be passed to uset_openPatternOptions() or
* uset_applyPattern() taking an option parameter.
* @stable ICU 2.4
*/
enum {
/**
* Ignore white space within patterns unless quoted or escaped.
* @stable ICU 2.4
*/
USET_IGNORE_SPACE = 1,
/**
* Enable case insensitive matching. E.g., "[ab]" with this flag
* will match 'a', 'A', 'b', and 'B'. "[^ab]" with this flag will
* match all except 'a', 'A', 'b', and 'B'. This performs a full
* closure over case mappings, e.g. U+017F for s.
*
* The resulting set is a superset of the input for the code points but
* not for the strings.
* It performs a case mapping closure of the code points and adds
* full case folding strings for the code points, and reduces strings of
* the original set to their full case folding equivalents.
*
* This is designed for case-insensitive matches, for example
* in regular expressions. The full code point case closure allows checking of
* an input character directly against the closure set.
* Strings are matched by comparing the case-folded form from the closure
* set with an incremental case folding of the string in question.
*
* The closure set will also contain single code points if the original
* set contained case-equivalent strings (like U+00DF for "ss" or "Ss" etc.).
* This is not necessary (that is, redundant) for the above matching method
* but results in the same closure sets regardless of whether the original
* set contained the code point or a string.
*
* @stable ICU 2.4
*/
USET_CASE_INSENSITIVE = 2,
/**
* Enable case insensitive matching. E.g., "[ab]" with this flag
* will match 'a', 'A', 'b', and 'B'. "[^ab]" with this flag will
* match all except 'a', 'A', 'b', and 'B'. This adds the lower-,
* title-, and uppercase mappings as well as the case folding
* of each existing element in the set.
* @stable ICU 3.2
*/
USET_ADD_CASE_MAPPINGS = 4
};
/**
* Argument values for whether span() and similar functions continue while
* the current character is contained vs. not contained in the set.
*
* The functionality is straightforward for sets with only single code points,
* without strings (which is the common case):
* - USET_SPAN_CONTAINED and USET_SPAN_SIMPLE work the same.
* - USET_SPAN_CONTAINED and USET_SPAN_SIMPLE are inverses of USET_SPAN_NOT_CONTAINED.
* - span() and spanBack() partition any string the same way when
* alternating between span(USET_SPAN_NOT_CONTAINED) and
* span(either "contained" condition).
* - Using a complemented (inverted) set and the opposite span conditions
* yields the same results.
*
* When a set contains multi-code point strings, then these statements may not
* be true, depending on the strings in the set (for example, whether they
* overlap with each other) and the string that is processed.
* For a set with strings:
* - The complement of the set contains the opposite set of code points,
* but the same set of strings.
* Therefore, complementing both the set and the span conditions
* may yield different results.
* - When starting spans at different positions in a string
* (span(s, ...) vs. span(s+1, ...)) the ends of the spans may be different
* because a set string may start before the later position.
* - span(USET_SPAN_SIMPLE) may be shorter than
* span(USET_SPAN_CONTAINED) because it will not recursively try
* all possible paths.
* For example, with a set which contains the three strings "xy", "xya" and "ax",
* span("xyax", USET_SPAN_CONTAINED) will return 4 but
* span("xyax", USET_SPAN_SIMPLE) will return 3.
* span(USET_SPAN_SIMPLE) will never be longer than
* span(USET_SPAN_CONTAINED).
* - With either "contained" condition, span() and spanBack() may partition
* a string in different ways.
* For example, with a set which contains the two strings "ab" and "ba",
* and when processing the string "aba",
* span() will yield contained/not-contained boundaries of { 0, 2, 3 }
* while spanBack() will yield boundaries of { 0, 1, 3 }.
*
* Note: If it is important to get the same boundaries whether iterating forward
* or backward through a string, then either only span() should be used and
* the boundaries cached for backward operation, or an ICU BreakIterator
* could be used.
*
* Note: Unpaired surrogates are treated like surrogate code points.
* Similarly, set strings match only on code point boundaries,
* never in the middle of a surrogate pair.
* Illegal UTF-8 sequences are treated like U+FFFD.
* When processing UTF-8 strings, malformed set strings
* (strings with unpaired surrogates which cannot be converted to UTF-8)
* are ignored.
*
* @stable ICU 3.8
*/
typedef enum USetSpanCondition {
/**
* Continues a span() while there is no set element at the current position.
* Increments by one code point at a time.
* Stops before the first set element (character or string).
* (For code points only, this is like while contains(current)==false).
*
* When span() returns, the substring between where it started and the position
* it returned consists only of characters that are not in the set,
* and none of its strings overlap with the span.
*
* @stable ICU 3.8
*/
USET_SPAN_NOT_CONTAINED = 0,
/**
* Spans the longest substring that is a concatenation of set elements (characters or strings).
* (For characters only, this is like while contains(current)==true).
*
* When span() returns, the substring between where it started and the position
* it returned consists only of set elements (characters or strings) that are in the set.
*
* If a set contains strings, then the span will be the longest substring for which there
* exists at least one non-overlapping concatenation of set elements (characters or strings).
* This is equivalent to a POSIX regular expression for <code>(OR of each set element)*</code>.
* (Java/ICU/Perl regex stops at the first match of an OR.)
*
* @stable ICU 3.8
*/
USET_SPAN_CONTAINED = 1,
/**
* Continues a span() while there is a set element at the current position.
* Increments by the longest matching element at each position.
* (For characters only, this is like while contains(current)==true).
*
* When span() returns, the substring between where it started and the position
* it returned consists only of set elements (characters or strings) that are in the set.
*
* If a set only contains single characters, then this is the same
* as USET_SPAN_CONTAINED.
*
* If a set contains strings, then the span will be the longest substring
* with a match at each position with the longest single set element (character or string).
*
* Use this span condition together with other longest-match algorithms,
* such as ICU converters (ucnv_getUnicodeSet()).
*
* @stable ICU 3.8
*/
USET_SPAN_SIMPLE = 2,
} USetSpanCondition;
enum {
/**
* Capacity of USerializedSet::staticArray.
* Enough for any single-code point set.
* Also provides padding for nice sizeof(USerializedSet).
* @stable ICU 2.4
*/
USET_SERIALIZED_STATIC_ARRAY_CAPACITY=8
};
/**
* A serialized form of a Unicode set. Limited manipulations are
* possible directly on a serialized set. See below.
* @stable ICU 2.4
*/
typedef struct USerializedSet {
/**
* The serialized Unicode Set.
* @stable ICU 2.4
*/
const uint16_t *array;
/**
* The length of the array that contains BMP characters.
* @stable ICU 2.4
*/
int32_t bmpLength;
/**
* The total length of the array.
* @stable ICU 2.4
*/
int32_t length;
/**
* A small buffer for the array to reduce memory allocations.
* @stable ICU 2.4
*/
uint16_t staticArray[USET_SERIALIZED_STATIC_ARRAY_CAPACITY];
} USerializedSet;
/*********************************************************************
* USet API
*********************************************************************/
/**
* Creates a USet object that contains the range of characters
* start..end, inclusive. If <code>start > end</code>
* then an empty set is created (same as using uset_openEmpty()).
* @param start first character of the range, inclusive
* @param end last character of the range, inclusive
* @return a newly created USet. The caller must call uset_close() on
* it when done.
* @stable ICU 2.4
*/
U_CAPI USet* U_EXPORT2
uset_open(UChar32 start, UChar32 end);
/**
* Creates a set from the given pattern. See the UnicodeSet class
* description for the syntax of the pattern language.
* @param pattern a string specifying what characters are in the set
* @param patternLength the length of the pattern, or -1 if null
* terminated
* @param ec the error code
* @stable ICU 2.4
*/
U_CAPI USet* U_EXPORT2
uset_openPattern(const UChar* pattern, int32_t patternLength,
UErrorCode* ec);
/**
* Creates a set from the given pattern. See the UnicodeSet class
* description for the syntax of the pattern language.
* @param pattern a string specifying what characters are in the set
* @param patternLength the length of the pattern, or -1 if null
* terminated
* @param options bitmask for options to apply to the pattern.
* Valid options are USET_IGNORE_SPACE and USET_CASE_INSENSITIVE.
* @param ec the error code
* @stable ICU 2.4
*/
U_CAPI USet* U_EXPORT2
uset_openPatternOptions(const UChar* pattern, int32_t patternLength,
uint32_t options,
UErrorCode* ec);
/**
* Disposes of the storage used by a USet object. This function should
* be called exactly once for objects returned by uset_open().
* @param set the object to dispose of
* @stable ICU 2.4
*/
U_CAPI void U_EXPORT2
uset_close(USet* set);
#if U_SHOW_CPLUSPLUS_API
U_NAMESPACE_BEGIN
/**
* \class LocalUSetPointer
* "Smart pointer" class, closes a USet via uset_close().
* For most methods see the LocalPointerBase base class.
*
* @see LocalPointerBase
* @see LocalPointer
* @stable ICU 4.4
*/
U_DEFINE_LOCAL_OPEN_POINTER(LocalUSetPointer, USet, uset_close);
U_NAMESPACE_END
#endif
/**
* Returns a string representation of this set. If the result of
* calling this function is passed to a uset_openPattern(), it
* will produce another set that is equal to this one.
* @param set the set
* @param result the string to receive the rules, may be NULL
* @param resultCapacity the capacity of result, may be 0 if result is NULL
* @param escapeUnprintable if true then convert unprintable
* character to their hex escape representations, \\uxxxx or
* \\Uxxxxxxxx. Unprintable characters are those other than
* U+000A, U+0020..U+007E.
* @param ec error code.
* @return length of string, possibly larger than resultCapacity
* @stable ICU 2.4
*/
U_CAPI int32_t U_EXPORT2
uset_toPattern(const USet* set,
UChar* result, int32_t resultCapacity,
UBool escapeUnprintable,
UErrorCode* ec);
/**
* Adds the given character to the given USet. After this call,
* uset_contains(set, c) will return true.
* A frozen set will not be modified.
* @param set the object to which to add the character
* @param c the character to add
* @stable ICU 2.4
*/
U_CAPI void U_EXPORT2
uset_add(USet* set, UChar32 c);
/**
* Adds the given string to the given USet. After this call,
* uset_containsString(set, str, strLen) will return true.
* A frozen set will not be modified.
* @param set the object to which to add the character
* @param str the string to add
* @param strLen the length of the string or -1 if null terminated.
* @stable ICU 2.4
*/
U_CAPI void U_EXPORT2
uset_addString(USet* set, const UChar* str, int32_t strLen);
/**
* Removes the given character from the given USet. After this call,
* uset_contains(set, c) will return false.
* A frozen set will not be modified.
* @param set the object from which to remove the character
* @param c the character to remove
* @stable ICU 2.4
*/
U_CAPI void U_EXPORT2
uset_remove(USet* set, UChar32 c);
/**
* Removes the given string to the given USet. After this call,
* uset_containsString(set, str, strLen) will return false.
* A frozen set will not be modified.
* @param set the object to which to add the character
* @param str the string to remove
* @param strLen the length of the string or -1 if null terminated.
* @stable ICU 2.4
*/
U_CAPI void U_EXPORT2
uset_removeString(USet* set, const UChar* str, int32_t strLen);
/**
* This is equivalent to
* <code>uset_complementRange(set, 0, 0x10FFFF)</code>.
*
* <strong>Note:</strong> This performs a symmetric difference with all code points
* <em>and thus retains all multicharacter strings</em>.
* In order to achieve a “code point complement” (all code points minus this set),
* the easiest is to <code>uset_complement(set); uset_removeAllStrings(set);</code>.
*
* A frozen set will not be modified.
* @param set the set
* @stable ICU 2.4
*/
U_CAPI void U_EXPORT2
uset_complement(USet* set);
/**
* Removes all of the elements from this set. This set will be
* empty after this call returns.
* A frozen set will not be modified.
* @param set the set
* @stable ICU 2.4
*/
U_CAPI void U_EXPORT2
uset_clear(USet* set);
/**
* Returns true if the given USet contains no characters and no
* strings.
* @param set the set
* @return true if set is empty
* @stable ICU 2.4
*/
U_CAPI UBool U_EXPORT2
uset_isEmpty(const USet* set);
/**
* Returns true if the given USet contains the given character.
* This function works faster with a frozen set.
* @param set the set
* @param c The codepoint to check for within the set
* @return true if set contains c
* @stable ICU 2.4
*/
U_CAPI UBool U_EXPORT2
uset_contains(const USet* set, UChar32 c);
/**
* Returns true if the given USet contains the given string.
* @param set the set
* @param str the string
* @param strLen the length of the string or -1 if null terminated.
* @return true if set contains str
* @stable ICU 2.4
*/
U_CAPI UBool U_EXPORT2
uset_containsString(const USet* set, const UChar* str, int32_t strLen);
/**
* Returns the number of characters and strings contained in this set.
* The last (uset_getItemCount() - uset_getRangeCount()) items are strings.
*
* This is slower than uset_getRangeCount() and uset_getItemCount() because
* it counts the code points of all ranges.
*
* @param set the set
* @return a non-negative integer counting the characters and strings
* contained in set
* @stable ICU 2.4
* @see uset_getRangeCount
*/
U_CAPI int32_t U_EXPORT2
uset_size(const USet* set);
/**
* @param set the set
* @return the number of ranges in this set.
* @stable ICU 70
* @see uset_getItemCount
* @see uset_getItem
* @see uset_size
*/
U_CAPI int32_t U_EXPORT2
uset_getRangeCount(const USet *set);
/**
* Returns the number of items in this set. An item is either a range
* of characters or a single multicharacter string.
* @param set the set
* @return a non-negative integer counting the character ranges
* and/or strings contained in set
* @stable ICU 2.4
*/
U_CAPI int32_t U_EXPORT2
uset_getItemCount(const USet* set);
/**
* Returns an item of this set. An item is either a range of
* characters or a single multicharacter string (which can be the empty string).
*
* If <code>itemIndex</code> is less than uset_getRangeCount(), then this function returns 0,
* and the range is <code>*start</code>..<code>*end</code>.
*
* If <code>itemIndex</code> is at least uset_getRangeCount() and less than uset_getItemCount(), then
* this function copies the string into <code>str[strCapacity]</code> and
* returns the length of the string (0 for the empty string).
*
* If <code>itemIndex</code> is out of range, then this function returns -1.
*
* Note that 0 is returned for each range as well as for the empty string.
*
* @param set the set
* @param itemIndex a non-negative integer in the range 0..uset_getItemCount(set)-1
* @param start pointer to variable to receive first character in range, inclusive;
* can be NULL for a string item
* @param end pointer to variable to receive last character in range, inclusive;
* can be NULL for a string item
* @param str buffer to receive the string, may be NULL
* @param strCapacity capacity of str, or 0 if str is NULL
* @param ec error code; U_INDEX_OUTOFBOUNDS_ERROR if the itemIndex is out of range
* @return the length of the string (0 or >= 2), or 0 if the item is a range,
* or -1 if the itemIndex is out of range
* @stable ICU 2.4
*/
U_CAPI int32_t U_EXPORT2
uset_getItem(const USet* set, int32_t itemIndex,
UChar32* start, UChar32* end,
UChar* str, int32_t strCapacity,
UErrorCode* ec);
#endif
third_party/icu4c/ndk_headers/unicode/utrans.h
Vendored
+494
View File
@@ -0,0 +1,494 @@
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
*******************************************************************************
* Copyright (C) 1997-2011,2014-2015 International Business Machines
* Corporation and others. All Rights Reserved.
*******************************************************************************
* Date Name Description
* 06/21/00 aliu Creation.
*******************************************************************************
*/
#ifndef UTRANS_H
#define UTRANS_H
#include "unicode/utypes.h"
#if !UCONFIG_NO_TRANSLITERATION
#include "unicode/parseerr.h"
#include "unicode/uenum.h"
#include "unicode/uset.h"
#if U_SHOW_CPLUSPLUS_API
#include "unicode/localpointer.h"
#endif // U_SHOW_CPLUSPLUS_API
/********************************************************************
* General Notes
********************************************************************
*/
/**
* \file
* \brief C API: Transliterator
*
* <h2> Transliteration </h2>
* The data structures and functions described in this header provide
* transliteration services. Transliteration services are implemented
* as C++ classes. The comments and documentation in this header
* assume the reader is familiar with the C++ headers translit.h and
* associated documentation.
*
* A significant but incomplete subset of the C++ transliteration
* services are available to C code through this header. In order to
* access more complex transliteration services, refer to the C++
* headers and documentation.
*
* There are two sets of functions for working with transliterator IDs:
*
* An old, deprecated set uses char * IDs, which works for true and pure
* identifiers that these APIs were designed for,
* for example "Cyrillic-Latin".
* It does not work when the ID contains filters ("[:Script=Cyrl:]")
* or even a complete set of rules because then the ID string contains more
* than just "invariant" characters (see utypes.h).
*
* A new set of functions replaces the old ones and uses UChar * IDs,
* paralleling the UnicodeString IDs in the C++ API. (New in ICU 2.8.)
*/
/********************************************************************
* Data Structures
********************************************************************/
/**
* An opaque transliterator for use in C. Open with utrans_openxxx()
* and close with utrans_close() when done. Equivalent to the C++ class
* Transliterator and its subclasses.
* @see Transliterator
* @stable ICU 2.0
*/
typedef void* UTransliterator;
/**
* Direction constant indicating the direction in a transliterator,
* e.g., the forward or reverse rules of a RuleBasedTransliterator.
* Specified when a transliterator is opened. An "A-B" transliterator
* transliterates A to B when operating in the forward direction, and
* B to A when operating in the reverse direction.
* @stable ICU 2.0
*/
typedef enum UTransDirection {
/**
* UTRANS_FORWARD means from &lt;source&gt; to &lt;target&gt; for a
* transliterator with ID &lt;source&gt;-&lt;target&gt;. For a transliterator
* opened using a rule, it means forward direction rules, e.g.,
* "A > B".
*/
UTRANS_FORWARD,
/**
* UTRANS_REVERSE means from &lt;target&gt; to &lt;source&gt; for a
* transliterator with ID &lt;source&gt;-&lt;target&gt;. For a transliterator
* opened using a rule, it means reverse direction rules, e.g.,
* "A < B".
*/
UTRANS_REVERSE
} UTransDirection;
/**
* Position structure for utrans_transIncremental() incremental
* transliteration. This structure defines two substrings of the text
* being transliterated. The first region, [contextStart,
* contextLimit), defines what characters the transliterator will read
* as context. The second region, [start, limit), defines what
* characters will actually be transliterated. The second region
* should be a subset of the first.
*
* <p>After a transliteration operation, some of the indices in this
* structure will be modified. See the field descriptions for
* details.
*
* <p>contextStart <= start <= limit <= contextLimit
*
* <p>Note: All index values in this structure must be at code point
* boundaries. That is, none of them may occur between two code units
* of a surrogate pair. If any index does split a surrogate pair,
* results are unspecified.
*
* @stable ICU 2.0
*/
typedef struct UTransPosition {
/**
* Beginning index, inclusive, of the context to be considered for
* a transliteration operation. The transliterator will ignore
* anything before this index. INPUT/OUTPUT parameter: This parameter
* is updated by a transliteration operation to reflect the maximum
* amount of antecontext needed by a transliterator.
* @stable ICU 2.4
*/
int32_t contextStart;
/**
* Ending index, exclusive, of the context to be considered for a
* transliteration operation. The transliterator will ignore
* anything at or after this index. INPUT/OUTPUT parameter: This
* parameter is updated to reflect changes in the length of the
* text, but points to the same logical position in the text.
* @stable ICU 2.4
*/
int32_t contextLimit;
/**
* Beginning index, inclusive, of the text to be transliterated.
* INPUT/OUTPUT parameter: This parameter is advanced past
* characters that have already been transliterated by a
* transliteration operation.
* @stable ICU 2.4
*/
int32_t start;
/**
* Ending index, exclusive, of the text to be transliterated.
* INPUT/OUTPUT parameter: This parameter is updated to reflect
* changes in the length of the text, but points to the same
* logical position in the text.
* @stable ICU 2.4
*/
int32_t limit;
} UTransPosition;
/********************************************************************
* General API
********************************************************************/
/**
* Open a custom transliterator, given a custom rules string
* OR
* a system transliterator, given its ID.
* Any non-NULL result from this function should later be closed with
* utrans_close().
*
* @param id a valid transliterator ID
* @param idLength the length of the ID string, or -1 if NUL-terminated
* @param dir the desired direction
* @param rules the transliterator rules. See the C++ header rbt.h for
* rules syntax. If NULL then a system transliterator matching
* the ID is returned.
* @param rulesLength the length of the rules, or -1 if the rules
* are NUL-terminated.
* @param parseError a pointer to a UParseError struct to receive the details
* of any parsing errors. This parameter may be NULL if no
* parsing error details are desired.
* @param pErrorCode a pointer to the UErrorCode
* @return a transliterator pointer that may be passed to other
* utrans_xxx() functions, or NULL if the open call fails.
* @stable ICU 2.8
*/
U_CAPI UTransliterator* U_EXPORT2
utrans_openU(const UChar *id,
int32_t idLength,
UTransDirection dir,
const UChar *rules,
int32_t rulesLength,
UParseError *parseError,
UErrorCode *pErrorCode);
/**
* Open an inverse of an existing transliterator. For this to work,
* the inverse must be registered with the system. For example, if
* the Transliterator "A-B" is opened, and then its inverse is opened,
* the result is the Transliterator "B-A", if such a transliterator is
* registered with the system. Otherwise the result is NULL and a
* failing UErrorCode is set. Any non-NULL result from this function
* should later be closed with utrans_close().
*
* @param trans the transliterator to open the inverse of.
* @param status a pointer to the UErrorCode
* @return a pointer to a newly-opened transliterator that is the
* inverse of trans, or NULL if the open call fails.
* @stable ICU 2.0
*/
U_CAPI UTransliterator* U_EXPORT2
utrans_openInverse(const UTransliterator* trans,
UErrorCode* status);
/**
* Create a copy of a transliterator. Any non-NULL result from this
* function should later be closed with utrans_close().
*
* @param trans the transliterator to be copied.
* @param status a pointer to the UErrorCode
* @return a transliterator pointer that may be passed to other
* utrans_xxx() functions, or NULL if the clone call fails.
* @stable ICU 2.0
*/
U_CAPI UTransliterator* U_EXPORT2
utrans_clone(const UTransliterator* trans,
UErrorCode* status);
/**
* Close a transliterator. Any non-NULL pointer returned by
* utrans_openXxx() or utrans_clone() should eventually be closed.
* @param trans the transliterator to be closed.
* @stable ICU 2.0
*/
U_CAPI void U_EXPORT2
utrans_close(UTransliterator* trans);
#if U_SHOW_CPLUSPLUS_API
U_NAMESPACE_BEGIN
/**
* \class LocalUTransliteratorPointer
* "Smart pointer" class, closes a UTransliterator via utrans_close().
* For most methods see the LocalPointerBase base class.
*
* @see LocalPointerBase
* @see LocalPointer
* @stable ICU 4.4
*/
U_DEFINE_LOCAL_OPEN_POINTER(LocalUTransliteratorPointer, UTransliterator, utrans_close);
U_NAMESPACE_END
#endif
/**
* Return the programmatic identifier for this transliterator.
* If this identifier is passed to utrans_openU(), it will open
* a transliterator equivalent to this one, if the ID has been
* registered.
*
* @param trans the transliterator to return the ID of.
* @param resultLength pointer to an output variable receiving the length
* of the ID string; can be NULL
* @return the NUL-terminated ID string. This pointer remains
* valid until utrans_close() is called on this transliterator.
*
* @stable ICU 2.8
*/
U_CAPI const UChar * U_EXPORT2
utrans_getUnicodeID(const UTransliterator *trans,
int32_t *resultLength);
/**
* Register an open transliterator with the system. When
* utrans_open() is called with an ID string that is equal to that
* returned by utrans_getID(adoptedTrans,...), then
* utrans_clone(adoptedTrans,...) is returned.
*
* <p>NOTE: After this call the system owns the adoptedTrans and will
* close it. The user must not call utrans_close() on adoptedTrans.
*
* @param adoptedTrans a transliterator, typically the result of
* utrans_openRules(), to be registered with the system.
* @param status a pointer to the UErrorCode
* @stable ICU 2.0
*/
U_CAPI void U_EXPORT2
utrans_register(UTransliterator* adoptedTrans,
UErrorCode* status);
/**
* Unregister a transliterator from the system. After this call the
* system will no longer recognize the given ID when passed to
* utrans_open(). If the ID is invalid then nothing is done.
*
* @param id an ID to unregister
* @param idLength the length of id, or -1 if id is zero-terminated
* @stable ICU 2.8
*/
U_CAPI void U_EXPORT2
utrans_unregisterID(const UChar* id, int32_t idLength);
/**
* Set the filter used by a transliterator. A filter can be used to
* make the transliterator pass certain characters through untouched.
* The filter is expressed using a UnicodeSet pattern. If the
* filterPattern is NULL or the empty string, then the transliterator
* will be reset to use no filter.
*
* @param trans the transliterator
* @param filterPattern a pattern string, in the form accepted by
* UnicodeSet, specifying which characters to apply the
* transliteration to. May be NULL or the empty string to indicate no
* filter.
* @param filterPatternLen the length of filterPattern, or -1 if
* filterPattern is zero-terminated
* @param status a pointer to the UErrorCode
* @see UnicodeSet
* @stable ICU 2.0
*/
U_CAPI void U_EXPORT2
utrans_setFilter(UTransliterator* trans,
const UChar* filterPattern,
int32_t filterPatternLen,
UErrorCode* status);
/**
* Return the number of system transliterators.
* It is recommended to use utrans_openIDs() instead.
*
* @return the number of system transliterators.
* @stable ICU 2.0
*/
U_CAPI int32_t U_EXPORT2
utrans_countAvailableIDs(void);
/**
* Return a UEnumeration for the available transliterators.
*
* @param pErrorCode Pointer to the UErrorCode in/out parameter.
* @return UEnumeration for the available transliterators.
* Close with uenum_close().
*
* @stable ICU 2.8
*/
U_CAPI UEnumeration * U_EXPORT2
utrans_openIDs(UErrorCode *pErrorCode);
/********************************************************************
* Transliteration API
********************************************************************/
/**
* Transliterate a segment of a UChar* string. The string is passed
* in in a UChar* buffer. The string is modified in place. If the
* result is longer than textCapacity, it is truncated. The actual
* length of the result is returned in *textLength, if textLength is
* non-NULL. *textLength may be greater than textCapacity, but only
* textCapacity UChars will be written to *text, including the zero
* terminator.
*
* @param trans the transliterator
* @param text a pointer to a buffer containing the text to be
* transliterated on input and the result text on output.
* @param textLength a pointer to the length of the string in text.
* If the length is -1 then the string is assumed to be
* zero-terminated. Upon return, the new length is stored in
* *textLength. If textLength is NULL then the string is assumed to
* be zero-terminated.
* @param textCapacity the length of the text buffer
* @param start the beginning index, inclusive; <code>0 <= start <=
* limit</code>.
* @param limit pointer to the ending index, exclusive; <code>start <=
* limit <= repFunc->length(rep)</code>. Upon return, *limit will
* contain the new limit index. The text previously occupying
* <code>[start, limit)</code> has been transliterated, possibly to a
* string of a different length, at <code>[start,
* </code><em>new-limit</em><code>)</code>, where <em>new-limit</em>
* is the return value.
* @param status a pointer to the UErrorCode
* @stable ICU 2.0
*/
U_CAPI void U_EXPORT2
utrans_transUChars(const UTransliterator* trans,
UChar* text,
int32_t* textLength,
int32_t textCapacity,
int32_t start,
int32_t* limit,
UErrorCode* status);
/**
* Transliterate the portion of the UChar* text buffer that can be
* transliterated unambiguously. See utrans_transIncremental(). The
* string is passed in in a UChar* buffer. The string is modified in
* place. If the result is longer than textCapacity, it is truncated.
* The actual length of the result is returned in *textLength, if
* textLength is non-NULL. *textLength may be greater than
* textCapacity, but only textCapacity UChars will be written to
* *text, including the zero terminator. See utrans_transIncremental()
* for usage details.
*
* @param trans the transliterator
* @param text a pointer to a buffer containing the text to be
* transliterated on input and the result text on output.
* @param textLength a pointer to the length of the string in text.
* If the length is -1 then the string is assumed to be
* zero-terminated. Upon return, the new length is stored in
* *textLength. If textLength is NULL then the string is assumed to
* be zero-terminated.
* @param textCapacity the length of the text buffer
* @param pos a struct containing the start and limit indices of the
* text to be read and the text to be transliterated
* @param status a pointer to the UErrorCode
* @see utrans_transIncremental
* @stable ICU 2.0
*/
U_CAPI void U_EXPORT2
utrans_transIncrementalUChars(const UTransliterator* trans,
UChar* text,
int32_t* textLength,
int32_t textCapacity,
UTransPosition* pos,
UErrorCode* status);
/**
* Create a rule string that can be passed to utrans_openU to recreate this
* transliterator.
*
* @param trans The transliterator
* @param escapeUnprintable if true then convert unprintable characters to their
* hex escape representations, \\uxxxx or \\Uxxxxxxxx.
* Unprintable characters are those other than
* U+000A, U+0020..U+007E.
* @param result A pointer to a buffer to receive the rules.
* @param resultLength The maximum size of result.
* @param status A pointer to the UErrorCode. In case of error status, the
* contents of result are undefined.
* @return int32_t The length of the rule string (may be greater than resultLength,
* in which case an error is returned).
* @stable ICU 53
*/
U_CAPI int32_t U_EXPORT2
utrans_toRules( const UTransliterator* trans,
UBool escapeUnprintable,
UChar* result, int32_t resultLength,
UErrorCode* status);
/**
* Returns the set of all characters that may be modified in the input text by
* this UTransliterator, optionally ignoring the transliterator's current filter.
* @param trans The transliterator.
* @param ignoreFilter If false, the returned set incorporates the
* UTransliterator's current filter; if the filter is changed,
* the return value of this function will change. If true, the
* returned set ignores the effect of the UTransliterator's
* current filter.
* @param fillIn Pointer to a USet object to receive the modifiable characters
* set. Previous contents of fillIn are lost. <em>If fillIn is
* NULL, then a new USet is created and returned. The caller
* owns the result and must dispose of it by calling uset_close.</em>
* @param status A pointer to the UErrorCode.
* @return USet* Either fillIn, or if fillIn is NULL, a pointer to a
* newly-allocated USet that the user must close. In case of
* error, NULL is returned.
* @stable ICU 53
*/
U_CAPI USet* U_EXPORT2
utrans_getSourceSet(const UTransliterator* trans,
UBool ignoreFilter,
USet* fillIn,
UErrorCode* status);
/* deprecated API ----------------------------------------------------------- */
#ifndef U_HIDE_DEPRECATED_API
/* see utrans.h documentation for why these functions are deprecated */
#endif /* U_HIDE_DEPRECATED_API */
#endif /* #if !UCONFIG_NO_TRANSLITERATION */
#endif