Characters can be accessed in two ways: as code units or as * code points. * Unicode code points are 21-bit integers and are the scalar values * of Unicode characters. ICU uses the type UChar32 for them. * Unicode code units are the storage units of a given * Unicode/UCS Transformation Format (a character encoding scheme). * With UTF-16, all code points can be represented with either one * or two code units ("surrogates"). * String storage is typically based on code units, while properties * of characters are typically determined using code point values. * Some processes may be designed to work with sequences of code units, * or it may be known that all characters that are important to an * algorithm can be represented with single code units. * Other processes will need to use the code point access functions.
* *ForwardCharacterIterator provides nextPostInc() to access
* a code unit and advance an internal position into the text object,
* similar to a return text[position++].
* It provides next32PostInc() to access a code point and advance an internal
* position.
ChoiceFormat splits
* the real number line -Inf to +Inf into two
* or more contiguous ranges. Each range is mapped to a
* string. ChoiceFormat is generally used in a
* MessageFormat for displaying grammatically correct
* plurals such as "There are 2 files."
=======================================================================
==uimacpp/include/unicode/coleitr.h
=======================================================================
/*
******************************************************************************
* Copyright (C) 1997-2005, International Business Machines
* Corporation and others. All Rights Reserved.
******************************************************************************
*/
/**
* File coleitr.h
*
*
*
* Created by: Helena Shih
*
* Modification History:
*
* Date Name Description
*
* 8/18/97 helena Added internal API documentation.
* 08/03/98 erm Synched with 1.2 version CollationElementIterator.java
* 12/10/99 aliu Ported Thai collation support from Java.
* 01/25/01 swquek Modified into a C++ wrapper calling C APIs (ucoliter.h)
* 02/19/01 swquek Removed CollationElementsIterator() since it is
* private constructor and no calls are made to it
*/
#ifndef COLEITR_H
#define COLEITR_H
#include "unicode/utypes.h"
/**
* \file
* \brief C++ API: Collation Element Iterator.
*/
#if !UCONFIG_NO_COLLATION
#include "unicode/uobject.h"
#include "unicode/tblcoll.h"
#include "unicode/ucoleitr.h"
/**
* The UCollationElements struct.
* For usage in C programs.
* @stable ICU 2.0
*/
typedef struct UCollationElements UCollationElements;
U_NAMESPACE_BEGIN
=======================================================================
==uimacpp/include/unicode/coll.h
=======================================================================
/*
******************************************************************************
* Copyright (C) 1996-2006, International Business Machines *
* Corporation and others. All Rights Reserved. *
******************************************************************************
*/
/**
* File coll.h
*
* Created by: Helena Shih
*
* Modification History:
*
* Date Name Description
* 02/5/97 aliu Modified createDefault to load collation data from
* binary files when possible. Added related methods
* createCollationFromFile, chopLocale, createPathName.
* 02/11/97 aliu Added members addToCache, findInCache, and fgCache.
* 02/12/97 aliu Modified to create objects from RuleBasedCollator cache.
* Moved cache out of Collation class.
* 02/13/97 aliu Moved several methods out of this class and into
* RuleBasedCollator, with modifications. Modified
* createDefault() to call new RuleBasedCollator(Locale&)
* constructor. General clean up and documentation.
* 02/20/97 helena Added clone, operator==, operator!=, operator=, copy
* constructor and getDynamicClassID.
* 03/25/97 helena Updated with platform independent data types.
* 05/06/97 helena Added memory allocation error detection.
* 06/20/97 helena Java class name change.
* 09/03/97 helena Added createCollationKeyValues().
* 02/10/98 damiba Added compare() with length as parameter.
* 04/23/99 stephen Removed EDecompositionMode, merged with
* Normalizer::EMode.
* 11/02/99 helena Collator performance enhancements. Eliminates the
* UnicodeString construction and special case for NO_OP.
* 11/23/99 srl More performance enhancements. Inlining of
* critical accessors.
* 05/15/00 helena Added version information API.
* 01/29/01 synwee Modified into a C++ wrapper which calls C apis
* (ucoll.h).
*/
#ifndef COLL_H
#define COLL_H
#include "unicode/utypes.h"
/**
* \file
=======================================================================
==uimacpp/include/unicode/curramt.h
=======================================================================
/*
**********************************************************************
* Copyright (c) 2004-2006, International Business Machines
* Corporation and others. All Rights Reserved.
**********************************************************************
* Author: Alan Liu
* Created: April 26, 2004
* Since: ICU 3.0
**********************************************************************
*/
#ifndef __CURRENCYAMOUNT_H__
#define __CURRENCYAMOUNT_H__
#include "unicode/utypes.h"
#if !UCONFIG_NO_FORMATTING
#include "unicode/measure.h"
#include "unicode/currunit.h"
/**
* \file
* \brief C++ API: Currency Amount Object.
*/
U_NAMESPACE_BEGIN
/**
*
* A currency together with a numeric amount, such as 200 USD.
*
* @author Alan Liu
* @stable ICU 3.0
*/
class U_I18N_API CurrencyAmount: public Measure {
public:
/**
* Construct an object with the given numeric amount and the given
* ISO currency code.
* @param amount a numeric object; amount.isNumeric() must be TRUE
* @param isoCode the 3-letter ISO 4217 currency code; must not be
* NULL and must have length 3
* @param ec input-output error code. If the amount or the isoCode
* is invalid, then this will be set to a failing value.
* @stable ICU 3.0
*/
CurrencyAmount(const Formattable& amount, const UChar* isoCode,
UErrorCode &ec);
/**
=======================================================================
==uimacpp/include/unicode/currunit.h
=======================================================================
/*
**********************************************************************
* Copyright (c) 2004-2006, International Business Machines
* Corporation and others. All Rights Reserved.
**********************************************************************
* Author: Alan Liu
* Created: April 26, 2004
* Since: ICU 3.0
**********************************************************************
*/
#ifndef __CURRENCYUNIT_H__
#define __CURRENCYUNIT_H__
#include "unicode/utypes.h"
#if !UCONFIG_NO_FORMATTING
#include "unicode/measunit.h"
/**
* \file
* \brief C++ API: Currency Unit Information.
*/
U_NAMESPACE_BEGIN
/**
* A unit of currency, such as USD (U.S. dollars) or JPY (Japanese
* yen). This class is a thin wrapper over a UChar string that
* subclasses MeasureUnit, for use with Measure and MeasureFormat.
*
* @author Alan Liu
* @stable ICU 3.0
*/
class U_I18N_API CurrencyUnit: public MeasureUnit {
public:
/**
* Construct an object with the given ISO currency code.
* @param isoCode the 3-letter ISO 4217 currency code; must not be
* NULL and must have length 3
* @param ec input-output error code. If the isoCode is invalid,
* then this will be set to a failing value.
* @stable ICU 3.0
*/
CurrencyUnit(const UChar* isoCode, UErrorCode &ec);
/**
* Copy constructor
* @stable ICU 3.0
*/
=======================================================================
==uimacpp/include/unicode/datefmt.h
=======================================================================
/*
********************************************************************************
* Copyright (C) 1997-2005, International Business Machines
* Corporation and others. All Rights Reserved.
********************************************************************************
*
* File DATEFMT.H
*
* Modification History:
*
* Date Name Description
* 02/19/97 aliu Converted from java.
* 04/01/97 aliu Added support for centuries.
* 07/23/98 stephen JDK 1.2 sync
* 11/15/99 weiv Added support for week of year/day of week formatting
********************************************************************************
*/
#ifndef DATEFMT_H
#define DATEFMT_H
#include "unicode/utypes.h"
#if !UCONFIG_NO_FORMATTING
#include "unicode/udat.h"
#include "unicode/calendar.h"
#include "unicode/numfmt.h"
#include "unicode/format.h"
#include "unicode/locid.h"
/**
* \file
* \brief C++ API: Abstract class for converting dates.
*/
U_NAMESPACE_BEGIN
class TimeZone;
/**
* DateFormat is an abstract class for a family of classes that convert dates and
* times from their internal representations to textual form and back again in a
* language-independent manner. Converting from the internal representation (milliseconds
* since midnight, January 1, 1970) to text is known as "formatting," and converting
* from text to millis is known as "parsing." We currently define only one concrete
* subclass of DateFormat: SimpleDateFormat, which can handle pretty much all normal
* date formatting and parsing actions.
* * DateFormat helps you to format and parse dates for any locale. Your code can ======================================================================= ==uimacpp/include/unicode/dbbi.h ======================================================================= /* ********************************************************************** * Copyright (C) 1999-2006 IBM Corp. All rights reserved. ********************************************************************** * Date Name Description * 12/1/99 rgillam Complete port from Java. * 01/13/2000 helena Added UErrorCode to ctors. ********************************************************************** */ #ifndef DBBI_H #define DBBI_H #include "unicode/rbbi.h" #if !UCONFIG_NO_BREAK_ITERATION /** * \file * \brief C++ API: Dictionary Based Break Iterator */ U_NAMESPACE_BEGIN /** * An obsolete subclass of RuleBasedBreakIterator. Handling of dictionary- * based break iteration has been folded into the base class. This class * is deprecated as of ICU 3.6. */ #ifndef U_HIDE_DEPRECATED_API typedef RuleBasedBreakIterator DictionaryBasedBreakIterator; #endif U_NAMESPACE_END #endif /* #if !UCONFIG_NO_BREAK_ITERATION */ #endif ======================================================================= ==uimacpp/include/unicode/dcfmtsym.h ======================================================================= /* ******************************************************************************** * Copyright (C) 1997-2006, International Business Machines * Corporation and others. All Rights Reserved. ******************************************************************************** * * File DCFMTSYM.H * * Modification History: * * Date Name Description * 02/19/97 aliu Converted from java. * 03/18/97 clhuang Updated per C++ implementation. * 03/27/97 helena Updated to pass the simple test after code review. * 08/26/97 aliu Added currency/intl currency symbol support. * 07/22/98 stephen Changed to match C++ style * currencySymbol -> fCurrencySymbol * Constants changed from CAPS to kCaps * 06/24/99 helena Integrated Alan's NF enhancements and Java2 bug fixes * 09/22/00 grhoten Marked deprecation tags with a pointer to replacement * functions. ******************************************************************************** */ #ifndef DCFMTSYM_H #define DCFMTSYM_H #include "unicode/utypes.h" #if !UCONFIG_NO_FORMATTING #include "unicode/uobject.h" #include "unicode/locid.h" /** * \file * \brief C++ API: Symbols for formatting numbers. */ U_NAMESPACE_BEGIN /** * This class represents the set of symbols needed by DecimalFormat * to format numbers. DecimalFormat creates for itself an instance of * DecimalFormatSymbols from its locale data. If you need to change any * of these symbols, you can get the DecimalFormatSymbols object from * your DecimalFormat and modify it. *
* Here are the special characters used in the parts of the ======================================================================= ==uimacpp/include/unicode/decimfmt.h ======================================================================= /* ******************************************************************************** * Copyright (C) 1997-2006, International Business Machines * Corporation and others. All Rights Reserved. ******************************************************************************** * * File DECIMFMT.H * * Modification History: * * Date Name Description * 02/19/97 aliu Converted from java. * 03/20/97 clhuang Updated per C++ implementation. * 04/03/97 aliu Rewrote parsing and formatting completely, and * cleaned up and debugged. Actually works now. * 04/17/97 aliu Changed DigitCount to int per code review. * 07/10/97 helena Made ParsePosition a class and get rid of the function * hiding problems. * 09/09/97 aliu Ported over support for exponential formats. * 07/20/98 stephen Changed documentation ******************************************************************************** */ #ifndef DECIMFMT_H #define DECIMFMT_H #include "unicode/utypes.h" /** * \file * \brief C++ API: Formats decimal numbers. */ #if !UCONFIG_NO_FORMATTING #include "unicode/dcfmtsym.h" #include "unicode/numfmt.h" #include "unicode/locid.h" U_NAMESPACE_BEGIN class DigitList; class ChoiceFormat; /** * DecimalFormat is a concrete subclass of NumberFormat that formats decimal * numbers. It has a variety of features designed to make it possible to parse * and format numbers in any locale, including support for Western, Arabic, or * Indic digits. It also supports different flavors of numbers, including * integers ("123"), fixed-point numbers ("123.4"), scientific notation * ("1.23E4"), percentages ("12%"), and currency amounts ("$123"). All of these ======================================================================= ==uimacpp/include/unicode/docmain.h ======================================================================= /******************************************************************** * COPYRIGHT: * Copyright (c) 1997-2005, International Business Machines Corporation and * others. All Rights Reserved. * * FILE NAME: DOCMAIN.h * * Date Name Description * 12/11/2000 Ram Creation. */ /* This file contains documentation for Doxygen and doesnot have * any significance with respect to C or C++ API */ /*! \mainpage * * \section API API Reference Usage * *
Use Class Hierarchy or Alphabetical List * or Compound List * to find the class you are interested in. For example, to find BreakIterator, * you can go to the Alphabetical List, then click on * "BreakIterator". Once you are at the class, you will find an inheritance * chart, a list of the public members, a detailed description of the class, * then detailed member descriptions.
* *Use Module List or File Members * to find a list of all the functions and constants. * For example, to find BreakIterator functions you would click on * File List, * then find "ubrk.h" and click on it. You will find descriptions of Defines, * Typedefs, Enumerations, and Functions, with detailed descriptions below. * If you want to find a specific function, such as ubrk_next(), then click * first on File Members, then use your browser * Find dialog to search for "ubrk_next()".
* * *The API References for each release of ICU are also available as * a zip file from the ICU * download page.
* *
* Rather than first creating a DateFormatSymbols to get a date-time formatter
* by using a SimpleDateFormat constructor, clients are encouraged to create a
* date-time formatter using the getTimeInstance(), getDateInstance(), or
* getDateTimeInstance() method in DateFormat. Each of these methods can return a
* date/time formatter initialized with a default format pattern along with the
* date-time formatting data for a given or default locale. After a formatter is
=======================================================================
==uimacpp/include/unicode/fieldpos.h
=======================================================================
/*
********************************************************************************
* Copyright (C) 1997-2005, International Business Machines
* Corporation and others. All Rights Reserved.
********************************************************************************
*
* File FIELDPOS.H
*
* Modification History:
*
* Date Name Description
* 02/25/97 aliu Converted from java.
* 03/17/97 clhuang Updated per Format implementation.
* 07/17/98 stephen Added default/copy ctors, and operators =, ==, !=
********************************************************************************
*/
// *****************************************************************************
// This file was generated from the java source file FieldPosition.java
// *****************************************************************************
#ifndef FIELDPOS_H
#define FIELDPOS_H
#include "unicode/utypes.h"
/**
* \file
* \brief C++ API: FieldPosition identifies the fields in a formatted output.
*/
#if !UCONFIG_NO_FORMATTING
#include "unicode/uobject.h"
U_NAMESPACE_BEGIN
/**
* FieldPosition is a simple class used by Format
* and its subclasses to identify fields in formatted output. Fields are
* identified by constants, whose names typically end with _FIELD,
* defined in the various subclasses of Format. See
* ERA_FIELD and its friends in DateFormat for
* an example.
*
*
* FieldPosition keeps track of the position of the
* field within the formatted output with two indices: the index
* of the first character of the field and the index of the last
* character of the field.
=======================================================================
==uimacpp/include/unicode/fmtable.h
=======================================================================
/*
********************************************************************************
* Copyright (C) 1997-2006, International Business Machines
* Corporation and others. All Rights Reserved.
********************************************************************************
*
* File FMTABLE.H
*
* Modification History:
*
* Date Name Description
* 02/29/97 aliu Creation.
********************************************************************************
*/
#ifndef FMTABLE_H
#define FMTABLE_H
#include "unicode/utypes.h"
#include "unicode/unistr.h"
/**
* \file
* \brief C++ API: Formattable is a thin wrapper for primitive numeric types.
*/
#if !UCONFIG_NO_FORMATTING
U_NAMESPACE_BEGIN
/**
* Formattable objects can be passed to the Format class or
* its subclasses for formatting. Formattable is a thin wrapper
* class which interconverts between the primitive numeric types
* (double, long, etc.) as well as UDate and UnicodeString.
*
*
Internally, a Formattable object is a union of primitive types. * As such, it can only store one flavor of data at a time. To * determine what flavor of data it contains, use the getType method. * *
As of ICU 3.0, Formattable may also wrap a UObject pointer, * which it owns. This allows an instance of any ICU class to be * encapsulated in a Formattable. For legacy reasons and for * efficiency, primitive numeric types are still stored directly * within a Formattable. * *
The Formattable class is not suitable for subclassing. */ class U_I18N_API Formattable : public UObject { public: /** * This enum is only used to let callers distinguish between ======================================================================= ==uimacpp/include/unicode/format.h ======================================================================= /* ******************************************************************************** * Copyright (C) 1997-2006, International Business Machines Corporation and others. * All Rights Reserved. ******************************************************************************** * * File FORMAT.H * * Modification History: * * Date Name Description * 02/19/97 aliu Converted from java. * 03/17/97 clhuang Updated per C++ implementation. * 03/27/97 helena Updated to pass the simple test after code review. ******************************************************************************** */ // ***************************************************************************** // This file was generated from the java source file Format.java // ***************************************************************************** #ifndef FORMAT_H #define FORMAT_H #include "unicode/utypes.h" /** * \file * \brief C++ API: Base class for all formats. */ #if !UCONFIG_NO_FORMATTING #include "unicode/unistr.h" #include "unicode/fmtable.h" #include "unicode/fieldpos.h" #include "unicode/parsepos.h" #include "unicode/parseerr.h" #include "unicode/locid.h" U_NAMESPACE_BEGIN /** * Base class for all formats. This is an abstract base class which * specifies the protocol for classes which convert other objects or * values, such as numeric values and dates, and their string * representations. In some cases these representations may be * localized or contain localized characters or strings. For example, * a numeric formatter such as DecimalFormat may convert a numeric * value such as 12345 to the string "$12,345". It may also parse ======================================================================= ==uimacpp/include/unicode/gregocal.h ======================================================================= /* * Copyright (C) 1997-2006, International Business Machines Corporation and others. * All Rights Reserved. ******************************************************************************** * * File GREGOCAL.H * * Modification History: * * Date Name Description * 04/22/97 aliu Overhauled header. * 07/28/98 stephen Sync with JDK 1.2 * 09/04/98 stephen Re-sync with JDK 8/31 putback * 09/14/98 stephen Changed type of kOneDay, kOneWeek to double. * Fixed bug in roll() * 10/15/99 aliu Fixed j31, incorrect WEEK_OF_YEAR computation. * Added documentation of WEEK_OF_YEAR computation. * 10/15/99 aliu Fixed j32, cannot set date to Feb 29 2000 AD. * {JDK bug 4210209 4209272} * 11/07/2003 srl Update, clean up documentation. ******************************************************************************** */ #ifndef GREGOCAL_H #define GREGOCAL_H #include "unicode/utypes.h" #if !UCONFIG_NO_FORMATTING #include "unicode/calendar.h" /** * \file * \brief C++ API: Concrete class which provides the standard calendar. */ U_NAMESPACE_BEGIN /** * Concrete class which provides the standard calendar used by most of the world. *
* The standard (Gregorian) calendar has 2 eras, BC and AD. *
* This implementation handles a single discontinuity, which corresponds by default to * the date the Gregorian calendar was originally instituted (October 15, 1582). Not all * countries adopted the Gregorian calendar then, so this cutover date may be changed by * the caller. *
* Prior to the institution of the Gregorian Calendar, New Year's Day was March 25. To
=======================================================================
==uimacpp/include/unicode/locid.h
=======================================================================
/*
******************************************************************************
*
* Copyright (C) 1996-2006, International Business Machines
* Corporation and others. All Rights Reserved.
*
******************************************************************************
*
* File locid.h
*
* Created by: Helena Shih
*
* Modification History:
*
* Date Name Description
* 02/11/97 aliu Changed gLocPath to fgLocPath and added methods to
* get and set it.
* 04/02/97 aliu Made operator!= inline; fixed return value of getName().
* 04/15/97 aliu Cleanup for AIX/Win32.
* 04/24/97 aliu Numerous changes per code review.
* 08/18/98 stephen Added tokenizeString(),changed getDisplayName()
* 09/08/98 stephen Moved definition of kEmptyString for Mac Port
* 11/09/99 weiv Added const char * getName() const;
* 04/12/00 srl removing unicodestring api's and cached hash code
* 08/10/01 grhoten Change the static Locales to accessor functions
******************************************************************************
*/
#ifndef LOCID_H
#define LOCID_H
#include "unicode/utypes.h"
#include "unicode/uobject.h"
#include "unicode/unistr.h"
#include "unicode/putil.h"
#include "unicode/uloc.h"
#include "unicode/strenum.h"
/**
* \file
* \brief C++ API: Locale ID object.
*/
/**
* A Locale object represents a specific geographical, political,
* or cultural region. An operation that requires a Locale to perform
* its task is called locale-sensitive and uses the Locale
* to tailor information for the user. For example, displaying a number
* is a locale-sensitive operation--the number should be formatted
* according to the customs/conventions of the user's native country,
=======================================================================
==uimacpp/include/unicode/measfmt.h
=======================================================================
/*
**********************************************************************
* Copyright (c) 2004-2006, International Business Machines
* Corporation and others. All Rights Reserved.
**********************************************************************
* Author: Alan Liu
* Created: April 20, 2004
* Since: ICU 3.0
**********************************************************************
*/
#ifndef MEASUREFORMAT_H
#define MEASUREFORMAT_H
#include "unicode/utypes.h"
#if !UCONFIG_NO_FORMATTING
#include "unicode/format.h"
/**
* \file
* \brief C++ API: Formatter for measure objects.
*/
U_NAMESPACE_BEGIN
/**
*
* A formatter for measure objects. This is an abstract base class.
*
*
To format or parse a measure object, first create a formatter * object using a MeasureFormat factory method. Then use that * object's format and parse methods. * *
This is an abstract class. * * @see Format * @author Alan Liu * @stable ICU 3.0 */ class U_I18N_API MeasureFormat : public Format { public: /** * Return a formatter for CurrencyAmount objects in the given * locale. * @param locale desired locale * @param ec input-output error code * @return a formatter object, or NULL upon error ======================================================================= ==uimacpp/include/unicode/measunit.h ======================================================================= /* ********************************************************************** * Copyright (c) 2004-2006, International Business Machines * Corporation and others. All Rights Reserved. ********************************************************************** * Author: Alan Liu * Created: April 26, 2004 * Since: ICU 3.0 ********************************************************************** */ #ifndef __MEASUREUNIT_H__ #define __MEASUREUNIT_H__ #include "unicode/utypes.h" #if !UCONFIG_NO_FORMATTING #include "unicode/fmtable.h" /** * \file * \brief C++ API: A unit for measuring a quantity. */ U_NAMESPACE_BEGIN /** * A unit such as length, mass, volume, currency, etc. A unit is * coupled with a numeric amount to produce a Measure. * *
This is an abstract class. * * @author Alan Liu * @stable ICU 3.0 */ class U_I18N_API MeasureUnit: public UObject { public: /** * Return a polymorphic clone of this object. The result will * have the same class as returned by getDynamicClassID(). * @stable ICU 3.0 */ virtual UObject* clone() const = 0; /** * Destructor * @stable ICU 3.0 */ virtual ~MeasureUnit(); ======================================================================= ==uimacpp/include/unicode/measure.h ======================================================================= /* ********************************************************************** * Copyright (c) 2004-2006, International Business Machines * Corporation and others. All Rights Reserved. ********************************************************************** * Author: Alan Liu * Created: April 26, 2004 * Since: ICU 3.0 ********************************************************************** */ #ifndef __MEASURE_H__ #define __MEASURE_H__ #include "unicode/utypes.h" /** * \file * \brief C++ API: MeasureUnit object. */ #if !UCONFIG_NO_FORMATTING #include "unicode/fmtable.h" U_NAMESPACE_BEGIN class MeasureUnit; /** * An amount of a specified unit, consisting of a number and a Unit. * For example, a length measure consists of a number and a length * unit, such as feet or meters. This is an abstract class. * Subclasses specify a concrete Unit type. * *
Measure objects are parsed and formatted by subclasses of * MeasureFormat. * *
Measure objects are immutable. * *
This is an abstract class. * * @author Alan Liu * @stable ICU 3.0 */ class U_I18N_API Measure: public UObject { public: /** * Construct an object with the given numeric amount and the given * unit. After this call, the caller must not delete the given * unit object. ======================================================================= ==uimacpp/include/unicode/msgfmt.h ======================================================================= /* * Copyright (C) 1997-2006, International Business Machines Corporation and others. All Rights Reserved. ******************************************************************************** * * File MSGFMT.H * * Modification History: * * Date Name Description * 02/19/97 aliu Converted from java. * 03/20/97 helena Finished first cut of implementation. * 07/22/98 stephen Removed operator!= (defined in Format) * 08/19/2002 srl Removing Javaisms ******************************************************************************** */ #ifndef MSGFMT_H #define MSGFMT_H #include "unicode/utypes.h" /** * \file * \brief C++ API: Formats messages in a language-neutral way. */ #if !UCONFIG_NO_FORMATTING #include "unicode/format.h" #include "unicode/locid.h" #include "unicode/parseerr.h" U_NAMESPACE_BEGIN class NumberFormat; class DateFormat; /** * * A MessageFormat produces concatenated messages in a * language-neutral way. It should be used for all string * concatenations that are visible to end users. *
* A MessageFormat contains an array of subformats arranged * within a template string. Together, the subformats and * template string determine how the MessageFormat will operate during * formatting and parsing. *
* Typically, both the subformats and the template string are * specified at once in a pattern. By using different ======================================================================= ==uimacpp/include/unicode/normlzr.h ======================================================================= /* ******************************************************************** * COPYRIGHT: * Copyright (c) 1996-2006, International Business Machines Corporation and * others. All Rights Reserved. ******************************************************************** */ #ifndef NORMLZR_H #define NORMLZR_H #include "unicode/utypes.h" /** * \file * \brief C++ API: Unicode Normalization */ #if !UCONFIG_NO_NORMALIZATION #include "unicode/uobject.h" #include "unicode/unistr.h" #include "unicode/chariter.h" #include "unicode/unorm.h" struct UCharIterator; typedef struct UCharIterator UCharIterator; /**< C typedef for struct UCharIterator. @stable ICU 2.1 */ U_NAMESPACE_BEGIN /** * The Normalizer class supports the standard normalization forms described in * * Unicode Standard Annex #15: Unicode Normalization Forms. * * The Normalizer class consists of two parts: * - static functions that normalize strings or test if strings are normalized * - a Normalizer object is an iterator that takes any kind of text and * provides iteration over its normalized form * * The Normalizer class is not suitable for subclassing. * * The static functions are basically wrappers around the C implementation, * using UnicodeString instead of UChar*. * For basic information about normalization forms and details about the C API * please see the documentation in unorm.h. * * The iterator API with the Normalizer constructors and the non-static functions * uses a CharacterIterator as input. It is possible to pass a string which * is then internally wrapped in a CharacterIterator. ======================================================================= ==uimacpp/include/unicode/numfmt.h ======================================================================= /* ******************************************************************************** * Copyright (C) 1997-2006, International Business Machines Corporation and others. * All Rights Reserved. ******************************************************************************** * * File NUMFMT.H * * Modification History: * * Date Name Description * 02/19/97 aliu Converted from java. * 03/18/97 clhuang Updated per C++ implementation. * 04/17/97 aliu Changed DigitCount to int per code review. * 07/20/98 stephen JDK 1.2 sync up. Added scientific support. * Changed naming conventions to match C++ guidelines * Derecated Java style constants (eg, INTEGER_FIELD) ******************************************************************************** */ #ifndef NUMFMT_H #define NUMFMT_H #include "unicode/utypes.h" /** * \file * \brief C++ API: Abstract base class for all number formats. */ #if !UCONFIG_NO_FORMATTING #include "unicode/unistr.h" #include "unicode/format.h" #include "unicode/unum.h" // UNumberFormatStyle #include "unicode/locid.h" U_NAMESPACE_BEGIN #if !UCONFIG_NO_SERVICE class NumberFormatFactory; class StringEnumeration; #endif /** * * Abstract base class for all number formats. Provides interface for * formatting and parsing a number. Also provides methods for * determining which locales have number formats, and what their names ======================================================================= ==uimacpp/include/unicode/parseerr.h ======================================================================= /* ********************************************************************** * 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. * *
The line, offset, and context fields are optional; parsing * engines may choose not to use to use them. * *
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: * *
* 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 ** *
Examples of engines which use UParseError (or may use it in the
=======================================================================
==uimacpp/include/unicode/parsepos.h
=======================================================================
/*
* Copyright (C) 1997-2005, International Business Machines Corporation and others. All Rights Reserved.
*******************************************************************************
*
* File PARSEPOS.H
*
* Modification History:
*
* Date Name Description
* 07/09/97 helena Converted from java.
* 07/17/98 stephen Added errorIndex support.
* 05/11/99 stephen Cleaned up.
*******************************************************************************
*/
#ifndef PARSEPOS_H
#define PARSEPOS_H
#include "unicode/utypes.h"
#include "unicode/uobject.h"
U_NAMESPACE_BEGIN
/**
* \file
* \brief C++ API: Canonical Iterator
*/
/**
* ParsePosition is a simple class used by Format
* and its subclasses to keep track of the current position during parsing.
* The parseObject method in the various Format
* classes requires a ParsePosition object as an argument.
*
*
* By design, as you parse through a string with different formats,
* you can use the same The ICU API for processing regular expressions consists of two classes,
* Class Note that by constructing An implicit aspect of the
* SearchIterator defines a protocol for text searching.
* Subclasses provide concrete implementations of various search algorithms.
* For example, StringSearch implements language-sensitive pattern
* matching based on the comparison rules defined in a
=======================================================================
==uimacpp/include/unicode/simpletz.h
=======================================================================
/*
* Copyright (C) {1997-2005}, International Business Machines Corporation and others. All Rights Reserved.
* *
********************************************************************************
*
* File SIMPLETZ.H
*
* Modification History:
*
* Date Name Description
* 04/21/97 aliu Overhauled header.
* 08/10/98 stephen JDK 1.2 sync
* Added setStartRule() / setEndRule() overloads
* Added hasSameRules()
* 09/02/98 stephen Added getOffset(monthLen)
* Changed getOffset() to take UErrorCode
* 07/09/99 stephen Removed millisPerHour (unused, for HP compiler)
* 12/02/99 aliu Added TimeMode and constructor and setStart/EndRule
* methods that take TimeMode. Added to docs.
********************************************************************************
*/
#ifndef SIMPLETZ_H
#define SIMPLETZ_H
#include "unicode/utypes.h"
/**
* \file
* \brief C++ API: SimpleTimeZone is a concrete subclass of TimeZone.
*/
#if !UCONFIG_NO_FORMATTING
#include "unicode/timezone.h"
U_NAMESPACE_BEGIN
/**
*
* When specifying daylight-savings-time begin and end dates, use a negative value for
*
* Clients are encouraged to create a date-time formatter using DateFormat::getInstance(),
* getDateInstance(), getDateInstance(), or getDateTimeInstance() rather than
=======================================================================
==uimacpp/include/unicode/sortkey.h
=======================================================================
/*
*****************************************************************************
* Copyright (C) 1996-2006, International Business Machines Corporation and others.
* All Rights Reserved.
*****************************************************************************
*
* File sortkey.h
*
* Created by: Helena Shih
*
* Modification History:
*
* Date Name Description
*
* 6/20/97 helena Java class name change.
* 8/18/97 helena Added internal API documentation.
* 6/26/98 erm Changed to use byte arrays and memcmp.
*****************************************************************************
*/
#ifndef SORTKEY_H
#define SORTKEY_H
#include "unicode/utypes.h"
/**
* \file
* \brief C++ API: Keys for comparing strings multiple times.
*/
#if !UCONFIG_NO_COLLATION
#include "unicode/uobject.h"
#include "unicode/unistr.h"
#include "unicode/coll.h"
U_NAMESPACE_BEGIN
/* forward declaration */
class RuleBasedCollator;
/**
*
* Collation keys are generated by the Collator class. Use the CollationKey objects
* instead of Collator to compare strings multiple times. A CollationKey
* preprocesses the comparison information from the Collator object to
* make the comparison faster. If you are not going to comparing strings
* multiple times, then using the Collator object is generally faster,
* since it only processes as much of the string as needed to make a
* comparison.
=======================================================================
==uimacpp/include/unicode/strenum.h
=======================================================================
/*
*******************************************************************************
*
* Copyright (C) 2002-2006, International Business Machines
* Corporation and others. All Rights Reserved.
*
*******************************************************************************
*/
#ifndef STRENUM_H
#define STRENUM_H
#include "unicode/uobject.h"
#include "unicode/unistr.h"
/**
* \file
* \brief C++ API: String Enumeration
*/
U_NAMESPACE_BEGIN
/**
* Base class for 'pure' C++ implementations of uenum api. Adds a
* method that returns the next UnicodeString since in C++ this can
* be a common storage format for strings.
*
* The model is that the enumeration is over strings maintained by
* a 'service.' At any point, the service might change, invalidating
* the enumerator (though this is expected to be rare). The iterator
* returns an error if this has occurred. Lack of the error is no
* guarantee that the service didn't change immediately after the
* call, so the returned string still might not be 'valid' on
* subsequent use. Strings may take the form of const char*, const UChar*, or const
* UnicodeString*. The type you get is determine by the variant of
* 'next' that you call. In general the StringEnumeration is
* optimized for one of these types, but all StringEnumerations can
* return all types. Returned strings are each terminated with a NUL.
* Depending on the service data, they might also include embedded NUL
* characters, so API is provided to optionally return the true
* length, counting the embedded NULs but not counting the terminating
* NUL. The pointers returned by next, unext, and snext become invalid
* upon any subsequent call to the enumeration's destructor, next,
* unext, snext, or reset.
* The algorithm implemented is a modified form of the Boyer Moore's search.
* For more information see
*
* "Efficient Text Searching in Java", published in Java Report
* in February, 1999, for further information on the algorithm.
*
* There are 2 match options for selection: A symbol table maintains two kinds of mappings. The first is
* between symbolic names and their values. For example, if the
* variable with the name "start" is set to the value "alpha"
* (perhaps, though not necessarily, through an expression such as
* "$start=alpha"), then the call lookup("start") will return the
* char[] array ['a', 'l', 'p', 'h', 'a'].
*
* The second kind of mapping is between character values and
* UnicodeMatcher objects. This is used by RuleBasedTransliterator,
* which uses characters in the private use area to represent objects
* such as UnicodeSets. If U+E015 is mapped to the UnicodeSet [a-z],
* then lookupMatcher(0xE015) will return the UnicodeSet [a-z].
*
* Finally, a symbol table defines parsing behavior for symbolic
* names. All symbolic names start with the SYMBOL_REF character.
* When a parser encounters this character, it calls parseReference()
* with the position immediately following the SYMBOL_REF. The symbol
* table parses the name, if there is one, and returns it.
=======================================================================
==uimacpp/include/unicode/tblcoll.h
=======================================================================
/*
******************************************************************************
* Copyright (C) 1996-2006, International Business Machines Corporation and
* others. All Rights Reserved.
******************************************************************************
*/
/**
* File tblcoll.h
*
* Created by: Helena Shih
*
* Modification History:
*
* Date Name Description
* 2/5/97 aliu Added streamIn and streamOut methods. Added
* constructor which reads RuleBasedCollator object from
* a binary file. Added writeToFile method which streams
* RuleBasedCollator out to a binary file. The streamIn
* and streamOut methods use istream and ostream objects
* in binary mode.
* 2/12/97 aliu Modified to use TableCollationData sub-object to
* hold invariant data.
* 2/13/97 aliu Moved several methods into this class from Collation.
* Added a private RuleBasedCollator(Locale&) constructor,
* to be used by Collator::createDefault(). General
* clean up.
* 2/20/97 helena Added clone, operator==, operator!=, operator=, and copy
* constructor and getDynamicClassID.
* 3/5/97 aliu Modified constructFromFile() to add parameter
* specifying whether or not binary loading is to be
* attempted. This is required for dynamic rule loading.
* 05/07/97 helena Added memory allocation error detection.
* 6/17/97 helena Added IDENTICAL strength for compare, changed getRules to
* use MergeCollation::getPattern.
* 6/20/97 helena Java class name change.
* 8/18/97 helena Added internal API documentation.
* 09/03/97 helena Added createCollationKeyValues().
* 02/10/98 damiba Added compare with "length" parameter
* 08/05/98 erm Synched with 1.2 version of RuleBasedCollator.java
* 04/23/99 stephen Removed EDecompositionMode, merged with
* Normalizer::EMode
* 06/14/99 stephen Removed kResourceBundleSuffix
* 11/02/99 helena Collator performance enhancements. Eliminates the
* UnicodeString construction and special case for NO_OP.
* 11/23/99 srl More performance enhancements. Updates to NormalizerIterator
* internal state management.
* 12/15/99 aliu Update to support Thai collation. Move NormalizerIterator
* to implementation file.
* 01/29/01 synwee Modified into a C++ wrapper which calls C API
=======================================================================
==uimacpp/include/unicode/timezone.h
=======================================================================
/*
* Copyright (C) {1997-2005}, International Business Machines Corporation and others. All Rights Reserved.
********************************************************************************
*
* File TIMEZONE.H
*
* Modification History:
*
* Date Name Description
* 04/21/97 aliu Overhauled header.
* 07/09/97 helena Changed createInstance to createDefault.
* 08/06/97 aliu Removed dependency on internal header for Hashtable.
* 08/10/98 stephen Changed getDisplayName() API conventions to match
* 08/19/98 stephen Changed createTimeZone() to never return 0
* 09/02/98 stephen Sync to JDK 1.2 8/31
* - Added getOffset(... monthlen ...)
* - Added hasSameRules()
* 09/15/98 stephen Added getStaticClassID
* 12/03/99 aliu Moved data out of static table into icudata.dll.
* Hashtable replaced by new static data structures.
* 12/14/99 aliu Made GMT public.
* 08/15/01 grhoten Made GMT private and added the getGMT() function
********************************************************************************
*/
#ifndef TIMEZONE_H
#define TIMEZONE_H
#include "unicode/utypes.h"
/**
* \file
* \brief C++ API: TimeZone object
*/
#if !UCONFIG_NO_FORMATTING
#include "unicode/uobject.h"
#include "unicode/unistr.h"
#include "unicode/ures.h"
U_NAMESPACE_BEGIN
class StringEnumeration;
/**
*
* Although script conversion is its most common use, a
* transliterator can actually perform a more general class of tasks.
* In fact,
*
* Note: Libraries that perform a bidirectional algorithm and
* reorder strings accordingly are sometimes called "Storage Layout Engines".
* ICU's BiDi and shaping (u_shapeArabic()) APIs can be used at the core of such
* "Storage Layout Engines".
*
*
*
* The "limit" of a sequence of characters is the position just after their
* last character, i.e., one more than that position.
*
* Some of the API functions provide access to "runs".
=======================================================================
==uimacpp/include/unicode/ubrk.h
=======================================================================
/*
******************************************************************************
* Copyright (C) 1996-2006, International Business Machines Corporation and others.
* All Rights Reserved.
******************************************************************************
*/
#ifndef UBRK_H
#define UBRK_H
#include "unicode/utypes.h"
#include "unicode/uloc.h"
#include "unicode/utext.h"
/**
* 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 void UBreakIterator;
#endif
#if !UCONFIG_NO_BREAK_ITERATION
#include "unicode/parseerr.h"
/**
* \file
* \brief C API: BreakIterator
*
*
* Line boundary analysis determines where a text string can be broken
* when line-wrapping. The mechanism correctly handles punctuation and
* hyphenated words.
*
* Sentence boundary analysis allows selection with correct
* interpretation of periods within numbers and abbreviations, and
* trailing punctuation marks such as quotation marks and parentheses.
*
=======================================================================
==uimacpp/include/unicode/ucal.h
=======================================================================
/*
*******************************************************************************
* Copyright (C) 1996-2006, International Business Machines Corporation and
* others. All Rights Reserved.
*******************************************************************************
*/
#ifndef UCAL_H
#define UCAL_H
#include "unicode/utypes.h"
#include "unicode/uenum.h"
#include "unicode/uloc.h"
#if !UCONFIG_NO_FORMATTING
/**
* \file
* \brief C API: Calendar
*
*
* Types of
* Like other locale-sensitive C API, calendar API provides a
* function,
* For ensuring the availability of necessary data, an application should
* open the service objects (converters, collators, etc.) that it will use
* and check for error codes there.
*
* Documentation for ICU 2.6 to ICU 3.4:
*
* This function loads and initializes data items
* that are required internally by various ICU functions. Use of this explicit
* initialization is required in multi-threaded applications; in
* single threaded apps, use is optional, but incurs little additional
* cost, and is thus recommended.
*
* In multi-threaded applications, u_init() should be called in the
* main thread before starting additional threads, or, alternatively
* it can be called in each individual thread once, before other ICU
* functions are called in that thread. In this second scenario, the
* application must guarantee that the first call to u_init() happen
=======================================================================
==uimacpp/include/unicode/ucnv.h
=======================================================================
/*
**********************************************************************
* Copyright (C) 1999-2006, International Business Machines
* Corporation and others. All Rights Reserved.
**********************************************************************
* ucnv.h:
* External APIs for the ICU's codeset conversion library
* Bertrand A. Damiba
*
* Modification History:
*
* Date Name Description
* 04/04/99 helena Fixed internal header inclusion.
* 05/11/00 helena Added setFallback and usesFallback APIs.
* 06/29/2000 helena Major rewrite of the callback APIs.
* 12/07/2000 srl Update of documentation
*/
/**
* \file
* \brief C API: Character conversion
*
* This API is used to convert codepage or character encoded data to and
* from UTF-16. You can open a converter with {@link ucnv_open() }. With that
* converter, you can get its properties, set options, convert your data and
* close the converter. Since many software programs recogize different converter names for
* different types of converters, there are other functions in this API to
* iterate over the converter aliases. The functions {@link ucnv_getAvailableName() },
* {@link ucnv_getAlias() } and {@link ucnv_getStandardName() } are some of the
* more frequently used alias functions to get this information. When a converter encounters an illegal, irregular, invalid or unmappable character
* its default behavior is to use a substitution character to replace the
* bad byte sequence. This behavior can be changed by using {@link ucnv_setFromUCallBack() }
* or {@link ucnv_setToUCallBack() } on the converter. The header ucnv_err.h defines
* many other callback actions that can be used instead of a character substitution. More information about this API can be found in our
* User's
* Guide.
* For more information about the collation service see
* the users guide.
*
* Collation service provides correct sorting orders for most locales supported in ICU.
* If specific data for a locale is not available, the orders eventually falls back
* to the UCA sort order.
*
* Sort ordering may be customized by providing your own set of rules. For more on
* this subject see the
*
* Collation customization section of the users guide.
*
* @see UCollationResult
* @see UNormalizationMode
* @see UCollationStrength
* @see UCollationElements
=======================================================================
==uimacpp/include/unicode/ucoleitr.h
=======================================================================
/*
*******************************************************************************
* Copyright (C) 2001-2004, International Business Machines
* Corporation and others. All Rights Reserved.
*******************************************************************************
*
* File ucoleitr.cpp
*
* Modification History:
*
* Date Name Description
* 02/15/2001 synwee Modified all methods to process its own function
* instead of calling the equivalent c++ api (coleitr.h)
*******************************************************************************/
#ifndef UCOLEITR_H
#define UCOLEITR_H
#include "unicode/utypes.h"
#if !UCONFIG_NO_COLLATION
/**
* This indicates an error has occured during processing or if no more CEs is
* to be returned.
* @stable ICU 2.0
*/
#define UCOL_NULLORDER ((int32_t)0xFFFFFFFF)
#include "unicode/ucol.h"
/**
* The UCollationElements struct.
* For usage in C programs.
* @stable ICU 2.0
*/
typedef struct UCollationElements UCollationElements;
/**
* \file
* \brief C API: UCollationElements
*
* The UCollationElements API is used as an iterator to walk through each
* character of an international string. Use the iterator to return the
* ordering priority of the positioned character. The ordering priority of a
* character, which we refer to as a key, defines how a character is collated
* in the given collation object.
* For example, consider the following in Spanish:
*
* Character set detection is at best an imprecise operation. The detection
* process will attempt to identify the charset that best matches the characteristics
* of the byte data, but the process is partly statistical in nature, and
* the results can not be guaranteed to always be correct.
*
* For best accuracy in charset detection, the input data should be primarily
* in a single language, and a minimum of a few hundred bytes worth of plain text
* in the language are needed. The detection process will attempt to
* ignore html or xml style markup that could otherwise obscure the content.
*/
struct UCharsetDetector;
/**
* Structure representing a charset detector
* @draft ICU 3.6
=======================================================================
==uimacpp/include/unicode/ucurr.h
=======================================================================
/*
**********************************************************************
* Copyright (c) 2002-2006, International Business Machines
* Corporation and others. All Rights Reserved.
**********************************************************************
*/
#ifndef _UCURR_H_
#define _UCURR_H_
#include "unicode/utypes.h"
#include "unicode/uenum.h"
/**
* \file
* \brief C API: Encapsulates information about a currency.
*/
#if !UCONFIG_NO_FORMATTING
/**
* The ucurr API encapsulates information about a currency, as defined by
* ISO 4217. A currency is represented by a 3-character string
* containing its ISO 4217 code. This API can return various data
* necessary the proper display of a currency:
*
*
* Date Format helps you to format and parse dates for any locale. Your code can
* be completely independent of the locale conventions for months, days of the
* week, or even the calendar format: lunar vs. solar.
*
* To format a date for the current Locale with default time and date style,
* use one of the static factory methods:
*
* You create a
* Takes a set of objects, formats them, then inserts the formatted
* strings into the pattern at the appropriate places.
*
* Here are some examples of usage:
* Example 1:
* Note: UnicodeFilter currently stubs out two pure virtual methods
* of its base class, UnicodeMatcher. These methods are toPattern()
* and matchesIndexValue(). This is done so that filter classes that
* are not actually used as matchers -- specifically, those in the
* UnicodeFilterLogic component, and those in tests -- can continue to
* work without defining these methods. As long as a filter is not
* used in an RBT during real transliteration, these methods will not
* be called. However, this breaks the UnicodeMatcher base class
* protocol, and it is not a correct solution.
*
=======================================================================
==uimacpp/include/unicode/unifunct.h
=======================================================================
/*
**********************************************************************
* Copyright (c) 2002-2005, International Business Machines Corporation
* and others. All Rights Reserved.
**********************************************************************
* Date Name Description
* 01/14/2002 aliu Creation.
**********************************************************************
*/
#ifndef UNIFUNCT_H
#define UNIFUNCT_H
#include "unicode/utypes.h"
#include "unicode/uobject.h"
/**
* \file
* \brief C++ API: Unicode Functor
*/
U_NAMESPACE_BEGIN
class UnicodeMatcher;
class UnicodeReplacer;
class TransliterationRuleData;
/**
* This is a mixin class.
* @author Alan Liu
* @stable ICU 2.4
*/
class U_I18N_API UnicodeReplacer /* not : public UObject because this is an interface/mixin class */ {
public:
/**
* Destructor.
* @stable ICU 2.4
*/
virtual ~UnicodeReplacer();
/**
* Replace characters in 'text' from 'start' to 'limit' with the
* output text of this object. Update the 'cursor' parameter to
* give the cursor position and return the length of the
* replacement text.
=======================================================================
==uimacpp/include/unicode/uniset.h
=======================================================================
/*
***************************************************************************
* Copyright (C) 1999-2006, International Business Machines Corporation
* and others. All Rights Reserved.
***************************************************************************
* Date Name Description
* 10/20/99 alan Creation.
***************************************************************************
*/
#ifndef UNICODESET_H
#define UNICODESET_H
#include "unicode/unifilt.h"
#include "unicode/unistr.h"
#include "unicode/uset.h"
/**
* \file
* \brief C++ API: Unicode Set
*/
U_NAMESPACE_BEGIN
class ParsePosition;
class SymbolTable;
class UVector;
class RuleCharacterIterator;
/**
* A mutable set of Unicode characters and multicharacter strings. Objects of this class
* represent character classes used in regular expressions.
* A character specifies a subset of Unicode code points. Legal
* code points are U+0000 to U+10FFFF, inclusive.
*
* The UnicodeSet class is not designed to be subclassed.
*
*
* UNumberFormat helps you to format and parse numbers for any locale.
* Your code can be completely independent of the locale conventions
* for decimal points, thousands-separators, or even the particular
* decimal digits used, or whether the number format is even decimal.
* There are different number format styles like decimal, currency,
* percent and spellout.
*
* To format a number for the current Locale, use one of the static
* factory methods:
* This is a C wrapper around the C++ RegexPattern and RegexMatcher classes.
* Resource bundles in ICU4C are currently defined using text files which conform to the following
* BNF definition.
* More on resource bundle concepts and syntax can be found in the
* Users Guide.
*
*/
/**
* UResourceBundle is an opaque type for handles for resource bundles in C APIs.
* @stable ICU 2.0
*/
=======================================================================
==uimacpp/include/unicode/uscript.h
=======================================================================
/*
**********************************************************************
* Copyright (C) 1997-2006, 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.
*
* Many of these script codes - those from Unicode's ScriptNames.txt -
* are character property values for Unicode's Script property.
* See UAX #24 Script Names (http://www.unicode.org/reports/tr24/).
*
* Starting with ICU 3.6, constants for most ISO 15924 script codes
* are included (currently excluding private-use codes Qaaa..Qabx).
* For scripts for which there are codes in ISO 15924 but which are not
* used in the Unicode Character Database (UCD), there are no Unicode characters
* associated with those scripts.
*
* For example, there are no characters that have a UCD script code of
* Hans or Hant. All Han ideographs have the Hani script code.
* The Hans and Hant script codes are used with CLDR data.
*
* ISO 15924 script codes are included for use with CLDR and similar.
*
* @stable ICU 2.2
*/
typedef enum UScriptCode {
USCRIPT_INVALID_CODE = -1,
USCRIPT_COMMON = 0 , /* Zyyy */
USCRIPT_INHERITED = 1, /* Qaai */
USCRIPT_ARABIC = 2, /* Arab */
USCRIPT_ARMENIAN = 3, /* Armn */
=======================================================================
==uimacpp/include/unicode/usearch.h
=======================================================================
/*
**********************************************************************
* Copyright (C) 2001-2005 IBM and others. All rights reserved.
**********************************************************************
* Date Name Description
* 06/28/2001 synwee Creation.
**********************************************************************
*/
#ifndef USEARCH_H
#define USEARCH_H
#include "unicode/utypes.h"
#if !UCONFIG_NO_COLLATION
#include "unicode/ucol.h"
#include "unicode/ucoleitr.h"
#include "unicode/ubrk.h"
/**
* \file
* \brief C API: StringSearch
*
* C Apis for an engine that provides language-sensitive text searching based
* on the comparison rules defined in a UCollator data struct,
* see ucol.h. This ensures that language eccentricity can be
* handled, e.g. for the German collator, characters ß and SS will be matched
* if case is chosen to be ignored.
* See the
* "ICU Collation Design Document" for more information.
*
* The algorithm implemented is a modified form of the Boyer Moore's search.
* For more information see
*
* "Efficient Text Searching in Java", published in Java Report
* in February, 1999, for further information on the algorithm.
*
* There are 2 match options for selection: This is a C wrapper around the C++ UnicodeSet class. To iterate over code points and strings, use a loop like this:
* Each item in the set is accessed as a string. Set elements
* consisting of single code points are returned as strings containing
* just the one code point.
*
* To iterate over code point ranges, instead of individual code points,
* use a loop like this:
* This function performs basic operations for "shaping" Arabic text. It is most
* useful for use with legacy data formats and legacy display technology
* (simple terminals). All operations are performed on Unicode characters. Text-based shaping means that some character code points in the text are
* replaced by others depending on the context. It transforms one kind of text
* into another. In comparison, modern displays for Arabic text select
* appropriate, context-dependent font glyphs for each text element, which means
* that they transform text into a glyph vector. Text transformations are necessary when modern display technology is not
* available or when text needs to be transformed to or from legacy formats that
* use "shaped" characters. Since the Arabic script is cursive, connecting
* adjacent letters to each other, computers select images for each letter based
* on the surrounding letters. This usually results in four images per Arabic
* letter: initial, middle, final, and isolated forms. In Unicode, on the other
* hand, letters are normally stored abstract, and a display system is expected
* to select the necessary glyphs. (This makes searching and other text
* processing easier because the same letter has only one code.) It is possible
* to mimic this with text transformations because there are characters in
=======================================================================
==uimacpp/include/unicode/usprep.h
=======================================================================
/*
*******************************************************************************
*
* Copyright (C) 2003-2006, International Business Machines
* Corporation and others. All Rights Reserved.
*
*******************************************************************************
* file name: usprep.h
* encoding: US-ASCII
* tab size: 8 (not used)
* indentation:4
*
* created on: 2003jul2
* created by: Ram Viswanadha
*/
#ifndef __USPREP_H__
#define __USPREP_H__
/**
* \file
* \brief C API: Implements the StringPrep algorithm.
*/
#include "unicode/utypes.h"
/**
*
* StringPrep API implements the StingPrep framework as described by RFC 3454.
* StringPrep prepares Unicode strings for use in network protocols.
* Profiles of StingPrep are set of rules and data according to with the
* Unicode Strings are prepared. Each profiles contains tables which describe
* how a code point should be treated. The tables are broadly classied into
* ParsePosition, since the index parameter
* records the current position.
*
* The ParsePosition class is not suitable for subclassing.
*
* @version 1.3 10/30/97
* @author Mark Davis, Helena Shih
* @see java.text.Format
*/
class U_COMMON_API ParsePosition : public UObject {
public:
/**
* Default constructor, the index starts with 0 as default.
=======================================================================
==uimacpp/include/unicode/putil.h
=======================================================================
/*
******************************************************************************
*
* Copyright (C) 1997-2005, International Business Machines
* Corporation and others. All Rights Reserved.
*
******************************************************************************
*
* FILE NAME : putil.h
*
* Date Name Description
* 05/14/98 nos Creation (content moved here from utypes.h).
* 06/17/99 erm Added IEEE_754
* 07/22/98 stephen Added IEEEremainder, max, min, trunc
* 08/13/98 stephen Added isNegativeInfinity, isPositiveInfinity
* 08/24/98 stephen Added longBitsFromDouble
* 03/02/99 stephen Removed openFile(). Added AS400 support.
* 04/15/99 stephen Converted to C
* 11/15/99 helena Integrated S/390 changes for IEEE support.
* 01/11/00 helena Added u_getVersion.
******************************************************************************
*/
#ifndef PUTIL_H
#define PUTIL_H
#include "unicode/utypes.h"
/**
* \file
* \brief C API: Platform Utilities
*/
/* Define this to 1 if your platform supports IEEE 754 floating point,
to 0 if it does not. */
#ifndef IEEE_754
# define IEEE_754 1
#endif
/*==========================================================================*/
/* Platform utilities */
/*==========================================================================*/
/**
* Platform utilities isolates the platform dependencies of the
* libarary. For each platform which this code is ported to, these
* functions may have to be re-implemented.
*/
/**
* Return the ICU data directory.
=======================================================================
==uimacpp/include/unicode/pwin32.h
=======================================================================
/*
******************************************************************************
*
* Copyright (C) 1997-2006, International Business Machines
* Corporation and others. All Rights Reserved.
*
******************************************************************************
*
* FILE NAME : platform.h
*
* Date Name Description
* 05/13/98 nos Creation (content moved here from ptypes.h).
* 03/02/99 stephen Added AS400 support.
* 03/30/99 stephen Added Linux support.
* 04/13/99 stephen Reworked for autoconf.
******************************************************************************
*/
/**
* \file
* \brief Configuration constants for the Windows platform
*/
/* Define the platform we're on. */
#ifndef U_WINDOWS
#define U_WINDOWS
#endif
#if defined(__BORLANDC__)
#define U_HAVE_PLACEMENT_NEW 0
#define U_HAVE_INTTYPES_H 1
#define __STDC_CONSTANT_MACROS
#endif
/* _MSC_VER is used to detect the Microsoft compiler. */
#if defined(_MSC_VER)
#define U_INT64_IS_LONG_LONG 0
#else
#define U_INT64_IS_LONG_LONG 1
#endif
/* Define whether inttypes.h is available */
#ifndef U_HAVE_INTTYPES_H
#define U_HAVE_INTTYPES_H 0
#endif
/*
* Define what support for C++ streams is available.
* If U_IOSTREAM_SOURCE is set to 199711, then Regular Expression API
*
* RegexPattern and RegexMatcher.
* RegexPattern objects represent a pre-processed, or compiled
* regular expression. They are created from a regular expression pattern string,
* and can be used to create RegexMatcher objects for the pattern.RegexMatcher bundles together a regular expression
* pattern and a target string to which the search pattern will be applied.
* RegexMatcher includes API for doing plain find or search
* operations, for search and replace operations, and for obtaining detailed
* information about bounds of a match. RegexMatcher objects directly from regular
* expression pattern strings application code can be simplified and the explicit
* need for RegexPattern objects can usually be eliminated.
* Replaceable is an abstract base class representing a
* string of characters that supports the replacement of a range of
* itself with a new string of characters. It is used by APIs that
* change a piece of text while retaining metadata. Metadata is data
* other than the Unicode characters returned by char32At(). One
* example of metadata is style attributes; another is an edit
* history, marking each character with an author and revision number.
*
* Replaceable API is that
* during a replace operation, new characters take on the metadata of
* the old characters. For example, if the string "the bold
* font" has range (4, 8) replaced with "strong", then it becomes "the
* strong font".
*
* Replaceable specifies ranges using a start
* offset and a limit offset. The range of characters thus specified
* includes the characters at offset start..limit-1. That is, the
* start offset is inclusive, and the limit offset is exclusive.
*
* Replaceable also includes API to access characters
* in the string: length(), charAt(),
* char32At(), and extractBetween().
=======================================================================
==uimacpp/include/unicode/resbund.h
=======================================================================
/*
******************************************************************************
*
* Copyright (C) 1996-2005, International Business Machines Corporation
* and others. All Rights Reserved.
*
******************************************************************************
*
* File resbund.h
*
* CREATED BY
* Richard Gillam
*
* Modification History:
*
* Date Name Description
* 2/5/97 aliu Added scanForLocaleInFile. Added
* constructor which attempts to read resource bundle
* from a specific file, without searching other files.
* 2/11/97 aliu Added UErrorCode return values to constructors. Fixed
* infinite loops in scanForFile and scanForLocale.
* Modified getRawResourceData to not delete storage
* in localeData and resourceData which it doesn't own.
* Added Mac compatibility #ifdefs for tellp() and
* ios::nocreate.
* 2/18/97 helena Updated with 100% documentation coverage.
* 3/13/97 aliu Rewrote to load in entire resource bundle and store
* it as a Hashtable of ResourceBundleData objects.
* Added state table to govern parsing of files.
* Modified to load locale index out of new file
* distinct from default.txt.
* 3/25/97 aliu Modified to support 2-d arrays, needed for timezone
* data. Added support for custom file suffixes. Again,
* needed to support timezone data.
* 4/7/97 aliu Cleaned up.
* 03/02/99 stephen Removed dependency on FILE*.
* 03/29/99 helena Merged Bertrand and Stephen's changes.
* 06/11/99 stephen Removed parsing of .txt files.
* Reworked to use new binary format.
* Cleaned up.
* 06/14/99 stephen Removed methods taking a filename suffix.
* 11/09/99 weiv Added getLocale(), fRealLocale, removed fRealLocaleID
******************************************************************************
*/
#ifndef RESBUND_H
#define RESBUND_H
#include "unicode/utypes.h"
#include "unicode/uobject.h"
=======================================================================
==uimacpp/include/unicode/schriter.h
=======================================================================
/*
******************************************************************************
*
* Copyright (C) 1998-2005, International Business Machines
* Corporation and others. All Rights Reserved.
*
******************************************************************************
*
* File schriter.h
*
* Modification History:
*
* Date Name Description
* 05/05/99 stephen Cleaned up.
******************************************************************************
*/
#ifndef SCHRITER_H
#define SCHRITER_H
#include "unicode/utypes.h"
#include "unicode/chariter.h"
#include "unicode/uchriter.h"
/**
* \file
* \brief C++ API: String Character Iterator
*/
U_NAMESPACE_BEGIN
/**
* A concrete subclass of CharacterIterator that iterates over the
* characters (code units or code points) in a UnicodeString.
* It's possible not only to create an
* iterator that iterates over an entire UnicodeString, but also to
* create one that iterates over only a subrange of a UnicodeString
* (iterators over different subranges of the same UnicodeString don't
* compare equal).
* @see CharacterIterator
* @see ForwardCharacterIterator
* @stable ICU 2.0
*/
class U_COMMON_API StringCharacterIterator : public UCharCharacterIterator {
public:
/**
* Create an iterator over the UnicodeString referred to by "textStr".
* The UnicodeString object is copied.
* The iteration range is the whole string, and the starting position is 0.
* @param textStr The unicode string used to create an iterator
* @stable ICU 2.0
=======================================================================
==uimacpp/include/unicode/search.h
=======================================================================
/*
**********************************************************************
* Copyright (C) 2001-2005 IBM and others. All rights reserved.
**********************************************************************
* Date Name Description
* 03/22/2000 helena Creation.
**********************************************************************
*/
#ifndef SEARCH_H
#define SEARCH_H
#include "unicode/utypes.h"
/**
* \file
* \brief C++ API: SearchIterator object.
*/
#if !UCONFIG_NO_COLLATION
#include "unicode/uobject.h"
#include "unicode/unistr.h"
#include "unicode/chariter.h"
#include "unicode/brkiter.h"
#include "unicode/usearch.h"
/**
* @stable ICU 2.0
*/
struct USearch;
/**
* @stable ICU 2.0
*/
typedef struct USearch USearch;
U_NAMESPACE_BEGIN
/**
*
* SearchIterator is an abstract base class that provides
* methods to search for a pattern within a text string. Instances of
* SearchIterator maintain a current position and scans over the
* target text, returning the indices the pattern is matched and the length
* of each match.
* SimpleTimeZone is a concrete subclass of TimeZone
* that represents a time zone for use with a Gregorian calendar. This
* class does not handle historical changes.
* dayOfWeekInMonth to indicate that SimpleTimeZone should
* count from the end of the month backwards. For example, in the U.S., Daylight Savings
* Time ends at the last (dayOfWeekInMonth = -1) Sunday in October, at 2 AM in standard
* time.
*
* @see Calendar
=======================================================================
==uimacpp/include/unicode/smpdtfmt.h
=======================================================================
/*
* Copyright (C) 1997-2006, International Business Machines Corporation and others. All Rights Reserved.
*******************************************************************************
*
* File SMPDTFMT.H
*
* Modification History:
*
* Date Name Description
* 02/19/97 aliu Converted from java.
* 07/09/97 helena Make ParsePosition into a class.
* 07/21/98 stephen Added GMT_PLUS, GMT_MINUS
* Changed setTwoDigitStartDate to set2DigitYearStart
* Changed getTwoDigitStartDate to get2DigitYearStart
* Removed subParseLong
* Removed getZoneIndex (added in DateFormatSymbols)
* 06/14/99 stephen Removed fgTimeZoneDataSuffix
* 10/14/99 aliu Updated class doc to describe 2-digit year parsing
* {j28 4182066}.
*******************************************************************************
*/
#ifndef SMPDTFMT_H
#define SMPDTFMT_H
#include "unicode/utypes.h"
/**
* \file
* \brief C++ API: Format and parse dates in a language-independent manner.
*/
#if !UCONFIG_NO_FORMATTING
#include "unicode/datefmt.h"
U_NAMESPACE_BEGIN
class DateFormatSymbols;
class DateFormat;
/**
*
* SimpleDateFormat is a concrete class for formatting and parsing dates in a
* language-independent manner. It allows for formatting (millis -> text),
* parsing (text -> millis), and normalization. Formats/Parses a date or time,
* which is the standard milliseconds since 24:00 GMT, Jan 1, 1970.
*
* Let S' be the sub-string of a text string S between the offsets start and
* end
* A pattern string P matches a text string S at the offsets TimeZone represents a time zone offset, and also figures out daylight
* savings.
*
=======================================================================
==uimacpp/include/unicode/translit.h
=======================================================================
/*
**********************************************************************
* Copyright (C) 1999-2006, International Business Machines
* Corporation and others. All Rights Reserved.
**********************************************************************
* Date Name Description
* 11/17/99 aliu Creation.
**********************************************************************
*/
#ifndef TRANSLIT_H
#define TRANSLIT_H
#include "unicode/utypes.h"
/**
* \file
* \brief C++ API: Tranforms text from one format to another.
*/
#if !UCONFIG_NO_TRANSLITERATION
#include "unicode/uobject.h"
#include "unicode/unistr.h"
#include "unicode/parseerr.h"
#include "unicode/utrans.h" // UTransPosition, UTransDirection
#include "unicode/strenum.h"
U_NAMESPACE_BEGIN
class UnicodeFilter;
class UnicodeSet;
class CompoundTransliterator;
class TransliteratorParser;
class NormalizationTransliterator;
class TransliteratorIDParser;
/**
*
* Transliterator is an abstract class that
* transliterates text from one format to another. The most common
* kind of transliterator is a script, or alphabet, transliterator.
* For example, a Russian to Latin transliterator changes Russian text
* written in Cyrillic characters to phonetically equivalent Latin
* characters. It does not translate Russian to English!
* Transliteration, unlike translation, operates on characters, without
* reference to the meanings of words and sentences.
*
* Transliterator defines a very general API
=======================================================================
==uimacpp/include/unicode/ubidi.h
=======================================================================
/*
******************************************************************************
*
* Copyright (C) 1999-2006, International Business Machines
* Corporation and others. All Rights Reserved.
*
******************************************************************************
* file name: ubidi.h
* encoding: US-ASCII
* tab size: 8 (not used)
* indentation:4
*
* created on: 1999jul27
* created by: Markus W. Scherer
*/
#ifndef UBIDI_H
#define UBIDI_H
#include "unicode/utypes.h"
#include "unicode/uchar.h"
/**
*\file
* \brief C API: BIDI algorithm
*
* BIDI algorithm for ICU
*
* This is an implementation of the Unicode Bidirectional algorithm.
* The algorithm is defined in the
* Unicode Standard Annex #9,
* version 13, also described in The Unicode Standard, Version 4.0 .General remarks about the API:
*
* In functions with an error code parameter,
* the pErrorCode pointer must be valid
* and the value that it points to must not indicate a failure before
* the function call. Otherwise, the function returns immediately.
* After the function call, the value indicates success or failure. BreakIterator C API
*
* 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.
* Calendar C API
*
* UCalendar C API is used for converting between a UDate object
* and a set of integer fields such as UCAL_YEAR, UCAL_MONTH,
* UCAL_DAY, UCAL_HOUR, and so on.
* (A UDate object represents a specific instant in
* time with millisecond precision. See UDate
* for information about the UDate .)
*
* UCalendar interpret a UDate
* according to the rules of a specific calendar system. The U_STABLE
* provides the enum UCalendarType with UCAL_TRADITIONAL and
* UCAL_GREGORIAN.
* ucal_open(), which returns a pointer to
* UCalendar whose time fields have been initialized
* with the current date and time. We need to specify the type of
* calendar to be opened and the timezoneId.
* \htmlonly\endhtmlonly
*
* \code
* UCalendar *caldef;
* UChar *tzId;
* UErrorCode status;
* tzId=(UChar*)malloc(sizeof(UChar) * (strlen("PST") +1) );
* u_uastrcpy(tzId, "PST");
* caldef=ucal_open(tzID, u_strlen(tzID), NULL, UCAL_TRADITIONAL, &status);
* \endcode
=======================================================================
==uimacpp/include/unicode/ucasemap.h
=======================================================================
/*
*******************************************************************************
*
* Copyright (C) 2005, International Business Machines
* Corporation and others. All Rights Reserved.
*
*******************************************************************************
* file name: ucasemap.h
* encoding: US-ASCII
* tab size: 8 (not used)
* indentation:4
*
* created on: 2005may06
* created by: Markus W. Scherer
*
* Case mapping service object and functions using it.
*/
#ifndef __UCASEMAP_H__
#define __UCASEMAP_H__
#include "unicode/utypes.h"
#include "unicode/ustring.h"
/**
* \file
* \brief C API: Unicode case mapping functions using a UCaseMap service object.
*
* The service object takes care of memory allocations, data loading, and setup
* for the attributes, as usual.
*
* Currently, the functionality provided here does not overlap with uchar.h
* and ustring.h.
*
* ucasemap_utf8ToLower() and ucasemap_utf8ToUpper() operate directly on
* UTF-8 strings.
*/
/**
* UCaseMap is an opaque service object for newer ICU case mapping functions.
* Older functions did not use a service object.
* @draft ICU 3.4
*/
struct UCaseMap;
typedef struct UCaseMap UCaseMap; /**< C typedef for struct UCaseMap. @draft ICU 3.4 */
/**
* Open a UCaseMap service object for a locale and a set of options.
* The locale ID and options are preprocessed so that functions using the
* service object need not process them in each call.
=======================================================================
==uimacpp/include/unicode/ucat.h
=======================================================================
/*
**********************************************************************
* Copyright (c) 2003-2004, International Business Machines
* Corporation and others. All Rights Reserved.
**********************************************************************
* Author: Alan Liu
* Created: March 19 2003
* Since: ICU 2.6
**********************************************************************
*/
#ifndef UCAT_H
#define UCAT_H
#include "unicode/utypes.h"
#include "unicode/ures.h"
/**
* \file
* \brief C API: Message Catalog Wrappers
*
* This C API provides look-alike functions that deliberately resemble
* the POSIX catopen, catclose, and catgets functions. The underlying
* implementation is in terms of ICU resource bundles, rather than
* POSIX message catalogs.
*
* The ICU resource bundles obey standard ICU inheritance policies.
* To facilitate this, sets and messages are flattened into one tier.
* This is done by creating resource bundle keys of the form
* <set_num>%<msg_num> where set_num is the set number and msg_num is
* the message number, formatted as decimal strings.
*
* Example: Consider a message catalog containing two sets:
*
* Set 1: Message 4 = "Good morning."
* Message 5 = "Good afternoon."
* Message 7 = "Good evening."
* Message 8 = "Good night."
* Set 4: Message 14 = "Please "
* Message 19 = "Thank you."
* Message 20 = "Sincerely,"
*
* The ICU resource bundle source file would, assuming it is named
* "greet.txt", would look like this:
*
* greet
* {
* 1%4 { "Good morning." }
* 1%5 { "Good afternoon." }
* 1%7 { "Good evening." }
* 1%8 { "Good night." }
=======================================================================
==uimacpp/include/unicode/uchar.h
=======================================================================
/*
**********************************************************************
* Copyright (C) 1997-2006, International Business Machines
* Corporation and others. All Rights Reserved.
**********************************************************************
*
* File UCHAR.H
*
* Modification History:
*
* Date Name Description
* 04/02/97 aliu Creation.
* 03/29/99 helena Updated for C APIs.
* 4/15/99 Madhu Updated for C Implementation and Javadoc
* 5/20/99 Madhu Added the function u_getVersion()
* 8/19/1999 srl Upgraded scripts to Unicode 3.0
* 8/27/1999 schererm UCharDirection constants: U_...
* 11/11/1999 weiv added u_isalnum(), cleaned comments
* 01/11/2000 helena Renamed u_getVersion to u_getUnicodeVersion().
******************************************************************************
*/
#ifndef UCHAR_H
#define UCHAR_H
#include "unicode/utypes.h"
U_CDECL_BEGIN
/*==========================================================================*/
/* Unicode version number */
/*==========================================================================*/
/**
* Unicode version number, default for the current ICU version.
* The actual Unicode Character Database (UCD) data is stored in uprops.dat
* and may be generated from UCD files from a different Unicode version.
* Call u_getUnicodeVersion to get the actual Unicode version of the data.
*
* @see u_getUnicodeVersion
* @stable ICU 2.0
*/
#define U_UNICODE_VERSION "5.0"
/**
* \file
* \brief C API: Unicode Properties
*
* This C API provides low-level access to the Unicode Character Database.
* In addition to raw property values, some convenience functions calculate
* derived properties, for example for Java-style programming.
=======================================================================
==uimacpp/include/unicode/uchriter.h
=======================================================================
/*
**********************************************************************
* Copyright (C) 1998-2005, International Business Machines
* Corporation and others. All Rights Reserved.
**********************************************************************
*/
#ifndef UCHRITER_H
#define UCHRITER_H
#include "unicode/utypes.h"
#include "unicode/chariter.h"
/**
* \file
* \brief C++ API: UChar Character Iterator
*/
U_NAMESPACE_BEGIN
/**
* A concrete subclass of CharacterIterator that iterates over the
* characters (code units or code points) in a UChar array.
* It's possible not only to create an
* iterator that iterates over an entire UChar array, but also to
* create one that iterates over only a subrange of a UChar array
* (iterators over different subranges of the same UChar array don't
* compare equal).
* @see CharacterIterator
* @see ForwardCharacterIterator
* @stable ICU 2.0
*/
class U_COMMON_API UCharCharacterIterator : public CharacterIterator {
public:
/**
* Create an iterator over the UChar array referred to by "textPtr".
* The iteration range is 0 to length-1.
* text is only aliased, not adopted (the
* destructor will not delete it).
* @param textPtr The UChar array to be iterated over
* @param length The length of the UChar array
* @stable ICU 2.0
*/
UCharCharacterIterator(const UChar* textPtr, int32_t length);
/**
* Create an iterator over the UChar array referred to by "textPtr".
* The iteration range is 0 to length-1.
* text is only aliased, not adopted (the
* destructor will not delete it).
=======================================================================
==uimacpp/include/unicode/uclean.h
=======================================================================
/*
******************************************************************************
* *
* Copyright (C) 2001-2005, International Business Machines *
* Corporation and others. All Rights Reserved. *
* *
******************************************************************************
* file name: uclean.h
* encoding: US-ASCII
* tab size: 8 (not used)
* indentation:4
*
* created on: 2001July05
* created by: George Rhoten
*/
#ifndef __UCLEAN_H__
#define __UCLEAN_H__
#include "unicode/utypes.h"
/**
* \file
* \brief C API: Initialize and clean up ICU
*/
/**
* Initialize ICU. The description further below applies to ICU 2.6 to ICU 3.4.
* Starting with ICU 3.4, u_init() needs not be called any more for
* ensuring thread safety, but it can give an indication for whether ICU
* can load its data. In ICU 3.4, it will try to load the converter alias table
* (cnvalias.icu) and give an error code if that fails.
* This may change in the future.
* Character Conversion C API
*
* Callback API for UConverter
*
* These functions are provided here for the convenience of the callback
* writer. If you are just looking for callback functions to use, please
* see ucnv_err.h. DO NOT call these functions directly when you are
* working with converters, unless your code has been called as a callback
* via ucnv_setFromUCallback or ucnv_setToUCallback !!
*
* A note about error codes and overflow. Unlike other ICU functions,
* these functions do not expect the error status to be U_ZERO_ERROR.
* Callbacks must be much more careful about their error codes.
* The error codes used here are in/out parameters, which should be passed
* back in the callback's error parameter.
*
* For example, if you call ucnv_cbfromUWriteBytes to write data out
* to the output codepage, it may return U_BUFFER_OVERFLOW_ERROR if
* the data did not fit in the target. But this isn't a failing error,
* in fact, ucnv_cbfromUWriteBytes may be called AGAIN with the error
* status still U_BUFFER_OVERFLOW_ERROR to attempt to write further bytes,
* which will also go into the internal overflow buffers.
*
* Concerning offsets, the 'offset' parameters here are relative to the start
* of SOURCE. For example, Suppose the string "ABCD" was being converted
* from Unicode into a codepage which doesn't have a mapping for 'B'.
* 'A' will be written out correctly, but
* The FromU Callback will be called on an unassigned character for 'B'.
* At this point, this is the state of the world:
* Target: A [..] [points after A]
* Source: A B [C] D [points to C - B has been consumed]
* 0 1 2 3
* codePoint = "B" [the unassigned codepoint]
*
=======================================================================
==uimacpp/include/unicode/ucnv_err.h
=======================================================================
/*
**********************************************************************
* Copyright (C) 1999-2005, International Business Machines
* Corporation and others. All Rights Reserved.
**********************************************************************
*
*
* ucnv_err.h:
*/
/**
* \file
* \brief C UConverter predefined error callbacks
*
* Error Behaviour Functions
* Defines some error behaviour functions called by ucnv_{from,to}Unicode
* These are provided as part of ICU and many are stable, but they
* can also be considered only as an example of what can be done with
* callbacks. You may of course write your own.
*
* If you want to write your own, you may also find the functions from
* ucnv_cb.h useful when writing your own callbacks.
*
* These functions, although public, should NEVER be called directly.
* They should be used as parameters to the ucnv_setFromUCallback
* and ucnv_setToUCallback functions, to set the behaviour of a converter
* when it encounters ILLEGAL/UNMAPPED/INVALID sequences.
*
* usage example: 'STOP' doesn't need any context, but newContext
* could be set to something other than 'NULL' if needed. The available
* contexts in this header can modify the default behavior of the callback.
*
* \code
* UErrorCode err = U_ZERO_ERROR;
* UConverter *myConverter = ucnv_open("ibm-949", &err);
* const void *oldContext;
* UConverterFromUCallback oldAction;
*
*
* if (U_SUCCESS(err))
* {
* ucnv_setFromUCallBack(myConverter,
* UCNV_FROM_U_CALLBACK_STOP,
* NULL,
* &oldAction,
* &oldContext,
* &status);
* }
* \endcode
*
=======================================================================
==uimacpp/include/unicode/ucol.h
=======================================================================
/*
*******************************************************************************
* Copyright (c) 1996-2006, International Business Machines Corporation and others.
* All Rights Reserved.
*******************************************************************************
*/
#ifndef UCOL_H
#define UCOL_H
#include "unicode/utypes.h"
#if !UCONFIG_NO_COLLATION
#include "unicode/unorm.h"
#include "unicode/parseerr.h"
#include "unicode/uloc.h"
#include "unicode/uset.h"
/**
* \file
* \brief C API: Collator
*
* Collator C API
*
* The C API for Collator performs locale-sensitive
* string comparison. You use this service to build
* searching and sorting routines for natural language text.
* Important: The ICU collation service has been reimplemented
* in order to achieve better performance and UCA compliance.
* For details, see the
*
* collation design document.
*
* . "ca" -> the first key is key('c') and second key is key('a').
=======================================================================
==uimacpp/include/unicode/uconfig.h
=======================================================================
/*
**********************************************************************
* Copyright (C) 2002-2006, International Business Machines
* Corporation and others. All Rights Reserved.
**********************************************************************
* file name: uconfig.h
* encoding: US-ASCII
* tab size: 8 (not used)
* indentation:4
*
* created on: 2002sep19
* created by: Markus W. Scherer
*/
#ifndef __UCONFIG_H__
#define __UCONFIG_H__
/*!
* \file
* \brief Switches for excluding parts of ICU library code modules.
*
* Allows to build partial, smaller libraries for special purposes.
* By default, all modules are built.
* The switches are fairly coarse, controlling large modules.
* Basic services cannot be turned off.
*
* Building with any of these options does not guarantee that the
* ICU build process will completely work. It is recommended that
* the ICU libraries and data be built using the normal build.
* At that time you should remove the data used by those services.
* After building the ICU data library, you should rebuild the ICU
* libraries with these switches customized to your needs.
*
* @stable ICU 2.4
*/
/**
* \def UCONFIG_ONLY_COLLATION
* This switch turns off modules that are not needed for collation.
*
* It does not turn off legacy conversion because that is necessary
* for ICU to work on EBCDIC platforms (for the default converter).
* If you want "only collation" and do not build for EBCDIC,
* then you can define UCONFIG_NO_LEGACY_CONVERSION 1 as well.
*
* @stable ICU 2.4
*/
#ifndef UCONFIG_ONLY_COLLATION
# define UCONFIG_ONLY_COLLATION 0
#endif
=======================================================================
==uimacpp/include/unicode/ucsdet.h
=======================================================================
/*
**********************************************************************
* Copyright (C) 2005-2006, International Business Machines
* Corporation and others. All Rights Reserved.
**********************************************************************
* file name: ucsdet.h
* encoding: US-ASCII
* indentation:4
*
* created on: 2005Aug04
* created by: Andy Heninger
*
* ICU Character Set Detection, API for C
*
* Draft version 18 Oct 2005
*
*/
#ifndef __UCSDET_H
#define __UCSDET_H
#include "unicode/utypes.h"
#if !UCONFIG_NO_CONVERSION
#include "unicode/uenum.h"
/**
* \file
* \brief C API: Charset Detection API
*
* This API provides a facility for detecting the
* charset or encoding of character data in an unknown text format.
* The input data can be from an array of bytes.
*
*
* The DecimalFormat class uses these data to display
* currencies.
* @author Alan Liu
* @since ICU 2.2
*/
/**
* Finds a currency code for the given locale.
* @param locale the locale for which to retrieve a currency code.
* Currency can be specified by the "currency" keyword
* in which case it overrides the default currency code
* @param buff fill in buffer. Can be NULL for preflighting.
* @param buffCapacity capacity of the fill in buffer. Can be 0 for
* preflighting. If it is non-zero, the buff parameter
* must not be NULL.
* @param ec error code
* @return length of the currency string. It should always be 3. If 0,
* currency couldn't be found or the input values are
* invalid.
* @stable ICU 2.8
=======================================================================
==uimacpp/include/unicode/udat.h
=======================================================================
/*
*******************************************************************************
* Copyright (C) 1996-2006, International Business Machines Corporation and others.
* All Rights Reserved.
*******************************************************************************
*/
#ifndef UDAT_H
#define UDAT_H
#include "unicode/utypes.h"
#if !UCONFIG_NO_FORMATTING
#include "unicode/ucal.h"
#include "unicode/unum.h"
/**
* \file
* \brief C API: DateFormat
*
* Date Format C API
*
* Date Format C API consists of functions that convert dates and
* times from their internal representations to textual form and back again in a
* language-independent manner. Converting from the internal representation (milliseconds
* since midnight, January 1, 1970) to text is known as "formatting," and converting
* from text to millis is known as "parsing." We currently define only one concrete
* structure UDateFormat, which can handle pretty much all normal
* date formatting and parsing actions.
*
* \code
* UErrorCode status = U_ZERO_ERROR;
* UChar *myString;
* int32_t myStrlen = 0;
* UDateFormat* dfmt = udat_open(UDAT_DEFAULT, UDAT_DEFAULT, NULL, NULL, -1, NULL, -1, &status);
* myStrlen = udat_format(dfmt, myDate, NULL, myStrlen, NULL, &status);
* if (status==U_BUFFER_OVERFLOW_ERROR){
* status=U_ZERO_ERROR;
* myString=(UChar*)malloc(sizeof(UChar) * (myStrlen+1) );
* udat_format(dfmt, myDate, myString, myStrlen+1, NULL, &status);
* }
* \endcode
*
=======================================================================
==uimacpp/include/unicode/udata.h
=======================================================================
/*
******************************************************************************
*
* Copyright (C) 1999-2006, International Business Machines
* Corporation and others. All Rights Reserved.
*
******************************************************************************
* file name: udata.h
* encoding: US-ASCII
* tab size: 8 (not used)
* indentation:4
*
* created on: 1999oct25
* created by: Markus W. Scherer
*/
#ifndef __UDATA_H__
#define __UDATA_H__
#include "unicode/utypes.h"
U_CDECL_BEGIN
/**
* \file
* \brief C API: Data loading interface
*
* Information about data loading interface
*
* This API is used to find and efficiently load data for ICU and applications
* using ICU. It provides an abstract interface that specifies a data type and
* name to find and load the data. Normally this API is used by other ICU APIs
* to load required data out of the ICU data library, but it can be used to
* load data out of other places.
*
* See the User Guide Data Management chapter.
*/
#ifndef U_HIDE_INTERNAL_API
/**
* Character used to separate package names from tree names
* @internal ICU 3.0
*/
#define U_TREE_SEPARATOR '-'
/**
* String used to separate package names from tree names
* @internal ICU 3.0
*/
#define U_TREE_SEPARATOR_STRING "-"
=======================================================================
==uimacpp/include/unicode/udeprctd.h
=======================================================================
/*
*******************************************************************************
* Copyright (C) 2004-2006, International Business Machines
* Corporation and others. All Rights Reserved.
*******************************************************************************
*
* file name:
* encoding: US-ASCII
* tab size: 8 (not used)
* indentation:4
*
* Created by: genheaders.pl, a perl script written by Ram Viswanadha
*
* Contains data for commenting out APIs.
* Gets included by umachine.h
*
* THIS FILE IS MACHINE-GENERATED, DON'T PLAY WITH IT IF YOU DON'T KNOW WHAT
* YOU ARE DOING, OTHERWISE VERY BAD THINGS WILL HAPPEN!
*/
#ifndef UDEPRCTD_H
#define UDEPRCTD_H
#ifdef U_HIDE_DEPRECATED_API
# if U_DISABLE_RENAMING
# define ucol_getContractions ucol_getContractions_DEPRECATED_API_DO_NOT_USE
# define ucol_getLocale ucol_getLocale_DEPRECATED_API_DO_NOT_USE
# define ures_countArrayItems ures_countArrayItems_DEPRECATED_API_DO_NOT_USE
# define ures_getLocale ures_getLocale_DEPRECATED_API_DO_NOT_USE
# define ures_getVersionNumber ures_getVersionNumber_DEPRECATED_API_DO_NOT_USE
# define utrans_getAvailableID utrans_getAvailableID_DEPRECATED_API_DO_NOT_USE
# define utrans_getID utrans_getID_DEPRECATED_API_DO_NOT_USE
# define utrans_open utrans_open_DEPRECATED_API_DO_NOT_USE
# define utrans_unregister utrans_unregister_DEPRECATED_API_DO_NOT_USE
# else
# define ucol_getContractions_3_6 ucol_getContractions_DEPRECATED_API_DO_NOT_USE
# define ucol_getLocale_3_6 ucol_getLocale_DEPRECATED_API_DO_NOT_USE
# define ures_countArrayItems_3_6 ures_countArrayItems_DEPRECATED_API_DO_NOT_USE
# define ures_getLocale_3_6 ures_getLocale_DEPRECATED_API_DO_NOT_USE
# define ures_getVersionNumber_3_6 ures_getVersionNumber_DEPRECATED_API_DO_NOT_USE
# define utrans_getAvailableID_3_6 utrans_getAvailableID_DEPRECATED_API_DO_NOT_USE
# define utrans_getID_3_6 utrans_getID_DEPRECATED_API_DO_NOT_USE
# define utrans_open_3_6 utrans_open_DEPRECATED_API_DO_NOT_USE
# define utrans_unregister_3_6 utrans_unregister_DEPRECATED_API_DO_NOT_USE
# endif /* U_DISABLE_RENAMING */
#endif /* U_HIDE_DEPRECATED_API */
#endif /* UDEPRCTD_H */
=======================================================================
==uimacpp/include/unicode/udraft.h
=======================================================================
/*
*******************************************************************************
* Copyright (C) 2004-2006, International Business Machines
* Corporation and others. All Rights Reserved.
*******************************************************************************
*
* file name:
* encoding: US-ASCII
* tab size: 8 (not used)
* indentation:4
*
* Created by: genheaders.pl, a perl script written by Ram Viswanadha
*
* Contains data for commenting out APIs.
* Gets included by umachine.h
*
* THIS FILE IS MACHINE-GENERATED, DON'T PLAY WITH IT IF YOU DON'T KNOW WHAT
* YOU ARE DOING, OTHERWISE VERY BAD THINGS WILL HAPPEN!
*/
#ifndef UDRAFT_H
#define UDRAFT_H
#ifdef U_HIDE_DRAFT_API
# if U_DISABLE_RENAMING
# define u_fclose u_fclose_DRAFT_API_DO_NOT_USE
# define u_feof u_feof_DRAFT_API_DO_NOT_USE
# define u_fflush u_fflush_DRAFT_API_DO_NOT_USE
# define u_fgetConverter u_fgetConverter_DRAFT_API_DO_NOT_USE
# define u_fgetc u_fgetc_DRAFT_API_DO_NOT_USE
# define u_fgetcodepage u_fgetcodepage_DRAFT_API_DO_NOT_USE
# define u_fgetcx u_fgetcx_DRAFT_API_DO_NOT_USE
# define u_fgetfile u_fgetfile_DRAFT_API_DO_NOT_USE
# define u_fgetlocale u_fgetlocale_DRAFT_API_DO_NOT_USE
# define u_fgets u_fgets_DRAFT_API_DO_NOT_USE
# define u_file_read u_file_read_DRAFT_API_DO_NOT_USE
# define u_file_write u_file_write_DRAFT_API_DO_NOT_USE
# define u_finit u_finit_DRAFT_API_DO_NOT_USE
# define u_fopen u_fopen_DRAFT_API_DO_NOT_USE
# define u_fprintf u_fprintf_DRAFT_API_DO_NOT_USE
# define u_fprintf_u u_fprintf_u_DRAFT_API_DO_NOT_USE
# define u_fputc u_fputc_DRAFT_API_DO_NOT_USE
# define u_fputs u_fputs_DRAFT_API_DO_NOT_USE
# define u_frewind u_frewind_DRAFT_API_DO_NOT_USE
# define u_fscanf u_fscanf_DRAFT_API_DO_NOT_USE
# define u_fscanf_u u_fscanf_u_DRAFT_API_DO_NOT_USE
# define u_fsetcodepage u_fsetcodepage_DRAFT_API_DO_NOT_USE
# define u_fsetlocale u_fsetlocale_DRAFT_API_DO_NOT_USE
# define u_fsettransliterator u_fsettransliterator_DRAFT_API_DO_NOT_USE
=======================================================================
==uimacpp/include/unicode/uenum.h
=======================================================================
/*
*******************************************************************************
*
* Copyright (C) 2002-2005, International Business Machines
* Corporation and others. All Rights Reserved.
*
*******************************************************************************
* file name: uenum.h
* encoding: US-ASCII
* tab size: 8 (not used)
* indentation:2
*
* created on: 2002jul08
* created by: Vladimir Weinstein
*/
#ifndef __UENUM_H
#define __UENUM_H
#include "unicode/utypes.h"
/**
* \file
* \brief C API: String Enumeration
*/
/**
* An enumeration object.
* For usage in C programs.
* @stable ICU 2.2
*/
struct UEnumeration;
/** structure representing an enumeration object instance @stable ICU 2.2 */
typedef struct UEnumeration UEnumeration;
/**
* Disposes of resources in use by the iterator. If en is NULL,
* does nothing. After this call, any char* or UChar* pointer
* returned by uenum_unext() or uenum_next() is invalid.
* @param en UEnumeration structure pointer
* @stable ICU 2.2
*/
U_STABLE void U_EXPORT2
uenum_close(UEnumeration* en);
/**
* Returns the number of elements that the iterator traverses. If
* the iterator is out-of-sync with its service, status is set to
* U_ENUM_OUT_OF_SYNC_ERROR.
* This is a convenience function. It can end up being very
=======================================================================
==uimacpp/include/unicode/uidna.h
=======================================================================
/*
*******************************************************************************
*
* Copyright (C) 2003-2006, International Business Machines
* Corporation and others. All Rights Reserved.
*
*******************************************************************************
* file name: uidna.h
* encoding: US-ASCII
* tab size: 8 (not used)
* indentation:4
*
* created on: 2003feb1
* created by: Ram Viswanadha
*/
#ifndef __UIDNA_H__
#define __UIDNA_H__
#include "unicode/utypes.h"
#if !UCONFIG_NO_IDNA
#include "unicode/parseerr.h"
/**
* \file
* \brief C API: Internationalized Domain Names in Applications Tranformation
*
* UIDNA API implements the IDNA protocol as defined in the IDNA RFC
* (http://www.ietf.org/rfc/rfc3490.txt).
* The RFC defines 2 operations: ToASCII and ToUnicode. Domain labels
* containing non-ASCII code points are required to be processed by
* ToASCII operation before passing it to resolver libraries. Domain names
* that are obtained from resolver libraries are required to be processed by
* ToUnicode operation before displaying the domain name to the user.
* IDNA requires that implementations process input strings with Nameprep
* (http://www.ietf.org/rfc/rfc3491.txt),
* which is a profile of Stringprep (http://www.ietf.org/rfc/rfc3454.txt),
* and then with Punycode (http://www.ietf.org/rfc/rfc3492.txt).
* Implementations of IDNA MUST fully implement Nameprep and Punycode;
* neither Nameprep nor Punycode are optional.
* The input and output of ToASCII and ToUnicode operations are Unicode
* and are designed to be chainable, i.e., applying ToASCII or ToUnicode operations
* multiple times to an input string will yield the same result as applying the operation
* once.
* ToUnicode(ToUnicode(ToUnicode...(ToUnicode(string)))) == ToUnicode(string)
* ToASCII(ToASCII(ToASCII...(ToASCII(string))) == ToASCII(string).
*
*/
=======================================================================
==uimacpp/include/unicode/uintrnal.h
=======================================================================
/*
*******************************************************************************
* Copyright (C) 2004-2006, International Business Machines
* Corporation and others. All Rights Reserved.
*******************************************************************************
*
* file name:
* encoding: US-ASCII
* tab size: 8 (not used)
* indentation:4
*
* Created by: genheaders.pl, a perl script written by Ram Viswanadha
*
* Contains data for commenting out APIs.
* Gets included by umachine.h
*
* THIS FILE IS MACHINE-GENERATED, DON'T PLAY WITH IT IF YOU DON'T KNOW WHAT
* YOU ARE DOING, OTHERWISE VERY BAD THINGS WILL HAPPEN!
*/
#ifndef UINTRNAL_H
#define UINTRNAL_H
#ifdef U_HIDE_INTERNAL_API
# if U_DISABLE_RENAMING
# define RegexPatternDump RegexPatternDump_INTERNAL_API_DO_NOT_USE
# define ucol_collatorToIdentifier ucol_collatorToIdentifier_INTERNAL_API_DO_NOT_USE
# define ucol_equals ucol_equals_INTERNAL_API_DO_NOT_USE
# define ucol_forgetUCA ucol_forgetUCA_INTERNAL_API_DO_NOT_USE
# define ucol_getAttributeOrDefault ucol_getAttributeOrDefault_INTERNAL_API_DO_NOT_USE
# define ucol_getUnsafeSet ucol_getUnsafeSet_INTERNAL_API_DO_NOT_USE
# define ucol_identifierToShortString ucol_identifierToShortString_INTERNAL_API_DO_NOT_USE
# define ucol_openFromIdentifier ucol_openFromIdentifier_INTERNAL_API_DO_NOT_USE
# define ucol_prepareShortStringOpen ucol_prepareShortStringOpen_INTERNAL_API_DO_NOT_USE
# define ucol_shortStringToIdentifier ucol_shortStringToIdentifier_INTERNAL_API_DO_NOT_USE
# define uprv_getDefaultCodepage uprv_getDefaultCodepage_INTERNAL_API_DO_NOT_USE
# define uprv_getDefaultLocaleID uprv_getDefaultLocaleID_INTERNAL_API_DO_NOT_USE
# define ures_openFillIn ures_openFillIn_INTERNAL_API_DO_NOT_USE
# define utf8_appendCharSafeBody utf8_appendCharSafeBody_INTERNAL_API_DO_NOT_USE
# define utf8_back1SafeBody utf8_back1SafeBody_INTERNAL_API_DO_NOT_USE
# define utf8_countTrailBytes utf8_countTrailBytes_INTERNAL_API_DO_NOT_USE
# define utf8_nextCharSafeBody utf8_nextCharSafeBody_INTERNAL_API_DO_NOT_USE
# define utf8_prevCharSafeBody utf8_prevCharSafeBody_INTERNAL_API_DO_NOT_USE
# else
# define RegexPatternDump_3_6 RegexPatternDump_INTERNAL_API_DO_NOT_USE
# define ucol_collatorToIdentifier_3_6 ucol_collatorToIdentifier_INTERNAL_API_DO_NOT_USE
# define ucol_equals_3_6 ucol_equals_INTERNAL_API_DO_NOT_USE
# define ucol_forgetUCA_3_6 ucol_forgetUCA_INTERNAL_API_DO_NOT_USE
# define ucol_getAttributeOrDefault_3_6 ucol_getAttributeOrDefault_INTERNAL_API_DO_NOT_USE
=======================================================================
==uimacpp/include/unicode/uiter.h
=======================================================================
/*
*******************************************************************************
*
* Copyright (C) 2002-2005, International Business Machines
* Corporation and others. All Rights Reserved.
*
*******************************************************************************
* file name: uiter.h
* encoding: US-ASCII
* tab size: 8 (not used)
* indentation:4
*
* created on: 2002jan18
* created by: Markus W. Scherer
*/
#ifndef __UITER_H__
#define __UITER_H__
/**
* \file
* \brief C API: Unicode Character Iteration
*
* @see UCharIterator
*/
#include "unicode/utypes.h"
#ifdef XP_CPLUSPLUS
U_NAMESPACE_BEGIN
class CharacterIterator;
class Replaceable;
U_NAMESPACE_END
#endif
U_CDECL_BEGIN
struct UCharIterator;
typedef struct UCharIterator UCharIterator; /**< C typedef for struct UCharIterator. @stable ICU 2.1 */
/**
* Origin constants for UCharIterator.getIndex() and UCharIterator.move().
* @see UCharIteratorMove
* @see UCharIterator
* @stable ICU 2.1
*/
typedef enum UCharIteratorOrigin {
UITER_START, UITER_CURRENT, UITER_LIMIT, UITER_ZERO, UITER_LENGTH
=======================================================================
==uimacpp/include/unicode/uloc.h
=======================================================================
/*
**********************************************************************
* Copyright (C) 1997-2006, International Business Machines
* Corporation and others. All Rights Reserved.
**********************************************************************
*
* File ULOC.H
*
* Modification History:
*
* Date Name Description
* 04/01/97 aliu Creation.
* 08/22/98 stephen JDK 1.2 sync.
* 12/08/98 rtg New C API for Locale
* 03/30/99 damiba overhaul
* 03/31/99 helena Javadoc for uloc functions.
* 04/15/99 Madhu Updated Javadoc
********************************************************************************
*/
#ifndef ULOC_H
#define ULOC_H
#include "unicode/utypes.h"
#include "unicode/uenum.h"
/**
* \file
* \brief C API: Locale
*
* ULoc C API for Locale
* A Locale represents a specific geographical, political,
* or cultural region. An operation that requires a Locale to perform
* its task is called locale-sensitive and uses the Locale
* to tailor information for the user. For example, displaying a number
* is a locale-sensitive operation--the number should be formatted
* according to the customs/conventions of the user's native country,
* region, or culture. In the C APIs, a locales is simply a const char string.
*
* Locale with one of the three options listed below.
* Each of the component is separated by '_' in the locale string.
* \htmlonly\endhtmlonly
*
* \code
* newLanguage
*
* newLanguage + newCountry
*
* newLanguage + newCountry + newVariant
=======================================================================
==uimacpp/include/unicode/ulocdata.h
=======================================================================
/*
******************************************************************************
* *
* Copyright (C) 2003-2006, International Business Machines *
* Corporation and others. All Rights Reserved. *
* *
******************************************************************************
* file name: ulocdata.h
* encoding: US-ASCII
* tab size: 8 (not used)
* indentation:4
*
* created on: 2003Oct21
* created by: Ram Viswanadha
*/
#ifndef __ULOCDATA_H__
#define __ULOCDATA_H__
#include "unicode/ures.h"
#include "unicode/uloc.h"
#include "unicode/uset.h"
/**
* \file
* \brief C API: Provides access to locale data.
*/
/** Forward declaration of the ULocaleData structure. @draft ICU 3.6 */
struct ULocaleData;
/** A locale data object. @draft ICU 3.6 */
typedef struct ULocaleData ULocaleData;
/** The possible types of exemplar character sets.
* @draft ICU 3.4
*/
typedef enum ULocaleDataExemplarSetType {
#ifndef U_HIDE_DRAFT_API
ULOCDATA_ES_STANDARD=0, /* Basic set */
ULOCDATA_ES_AUXILIARY=1, /* Auxiliary set */
#endif
ULOCDATA_ES_COUNT=3
} ULocaleDataExemplarSetType;
/** The possible types of delimiters.
* @draft ICU 3.4
*/
=======================================================================
==uimacpp/include/unicode/umachine.h
=======================================================================
/*
******************************************************************************
*
* Copyright (C) 1999-2006, International Business Machines
* Corporation and others. All Rights Reserved.
*
******************************************************************************
* file name: umachine.h
* encoding: US-ASCII
* tab size: 8 (not used)
* indentation:4
*
* created on: 1999sep13
* created by: Markus W. Scherer
*
* This file defines basic types and constants for utf.h to be
* platform-independent. umachine.h and utf.h are included into
* utypes.h to provide all the general definitions for ICU.
* All of these definitions used to be in utypes.h before
* the UTF-handling macros made this unmaintainable.
*/
#ifndef __UMACHINE_H__
#define __UMACHINE_H__
/**
* \file
* \brief Basic types and constants for UTF
*
* Basic types and constants for UTF
* This file defines basic types and constants for utf.h to be
* platform-independent. umachine.h and utf.h are included into
* utypes.h to provide all the general definitions for ICU.
* All of these definitions used to be in utypes.h before
* the UTF-handling macros made this unmaintainable.
*
*/
/*==========================================================================*/
/* Include platform-dependent definitions */
/* which are contained in the platform-specific file platform.h */
/*==========================================================================*/
#if defined(U_PALMOS)
# include "unicode/ppalmos.h"
#elif defined(WIN32) || defined(_WIN32) || defined(WIN64) || defined(_WIN64)
# include "unicode/pwin32.h"
#else
# include "unicode/platform.h"
#endif
=======================================================================
==uimacpp/include/unicode/umisc.h
=======================================================================
/*
**********************************************************************
* Copyright (C) 1999-2006, International Business Machines
* Corporation and others. All Rights Reserved.
**********************************************************************
* file name: umisc.h
* encoding: US-ASCII
* 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:misc 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
=======================================================================
==uimacpp/include/unicode/umsg.h
=======================================================================
/*
*******************************************************************************
* Copyright (C) 1996-2006, International Business Machines Corporation
* and others. All Rights Reserved.
*******************************************************************************
*
* file name: umsg.h
* encoding: US-ASCII
* tab size: 8 (not used)
* indentation:4
*
* Change history:
*
* 08/5/2001 Ram Added C wrappers for C++ API.
*
*
*/
#ifndef UMSG_H
#define UMSG_H
#include "unicode/utypes.h"
#if !UCONFIG_NO_FORMATTING
#include "unicode/uloc.h"
#include "unicode/parseerr.h"
#include Message Format C API
*
* Provides means to produce concatenated messages in language-neutral way.
* Use this for all concatenations that show up to end users.
*
* \code
* UChar *result, *tzID, *str;
* UChar pattern[100];
* int32_t resultLengthOut, resultlength;
* UCalendar *cal;
* UDate d1;
* UDateFormat *def1;
=======================================================================
==uimacpp/include/unicode/unifilt.h
=======================================================================
/*
**********************************************************************
* Copyright (C) 1999-2006, International Business Machines Corporation and others.
* All Rights Reserved.
**********************************************************************
* Date Name Description
* 11/17/99 aliu Creation.
**********************************************************************
*/
#ifndef UNIFILT_H
#define UNIFILT_H
#include "unicode/unifunct.h"
#include "unicode/unimatch.h"
/**
* \file
* \brief C++ API: Unicode Filter
*/
U_NAMESPACE_BEGIN
/**
* U_ETHER is used to represent character values for positions outside
* a range. For example, transliterator uses this to represent
* characters outside the range contextStart..contextLimit-1. This
* allows explicit matching by rules and UnicodeSets of text outside a
* defined range.
* @stable ICU 3.0
*/
#define U_ETHER ((UChar)0xFFFF)
/**
*
*
UnicodeFilter defines a protocol for selecting a
* subset of the full range (U+0000 to U+10FFFF) of Unicode characters.
* Currently, filters are used in conjunction with classes like {@link
* Transliterator} to only process selected characters through a
* transformation.
*
* UnicodeFunctor is an abstract base class for objects
* that perform match and/or replace operations on Unicode strings.
* @author Alan Liu
* @stable ICU 2.4
*/
class U_COMMON_API UnicodeFunctor : public UObject {
public:
/**
* Destructor
* @stable ICU 2.4
*/
virtual ~UnicodeFunctor();
/**
* Return a copy of this object. All UnicodeFunctor objects
* have to support cloning in order to allow classes using
* UnicodeFunctor to implement cloning.
* @stable ICU 2.4
*/
virtual UnicodeFunctor* clone() const = 0;
=======================================================================
==uimacpp/include/unicode/unimatch.h
=======================================================================
/*
* Copyright (C) 2001-2005, International Business Machines Corporation and others. All Rights Reserved.
**********************************************************************
* Date Name Description
* 07/18/01 aliu Creation.
**********************************************************************
*/
#ifndef UNIMATCH_H
#define UNIMATCH_H
#include "unicode/utypes.h"
/**
* \file
* \brief C++ API: Unicode Matcher
*/
U_NAMESPACE_BEGIN
class Replaceable;
class UnicodeString;
class UnicodeSet;
/**
* Constants returned by UnicodeMatcher::matches()
* indicating the degree of match.
* @stable ICU 2.4
*/
enum UMatchDegree {
/**
* Constant returned by matches() indicating a
* mismatch between the text and this matcher. The text contains
* a character which does not match, or the text does not contain
* all desired characters for a non-incremental match.
* @stable ICU 2.4
*/
U_MISMATCH,
/**
* Constant returned by matches() indicating a
* partial match between the text and this matcher. This value is
* only returned for incremental match operations. All characters
* of the text match, but more characters are required for a
* complete match. Alternatively, for variable-length matchers,
* all characters of the text match, and if more characters were
* supplied at limit, they might also match.
* @stable ICU 2.4
*/
U_PARTIAL_MATCH,
=======================================================================
==uimacpp/include/unicode/unirepl.h
=======================================================================
/*
**********************************************************************
* Copyright (c) 2002-2005, International Business Machines Corporation
* and others. All Rights Reserved.
**********************************************************************
* Date Name Description
* 01/14/2002 aliu Creation.
**********************************************************************
*/
#ifndef UNIREPL_H
#define UNIREPL_H
#include "unicode/utypes.h"
/**
* \file
* \brief C++ API: UnicodeReplacer
*/
U_NAMESPACE_BEGIN
class Replaceable;
class UnicodeString;
class UnicodeSet;
/**
* UnicodeReplacer defines a protocol for objects that
* replace a range of characters in a Replaceable string with output
* text. The replacement is done via the Replaceable API so as to
* preserve out-of-band data.
*
* UnicodeSet supports two APIs. The first is the
* operand API that allows the caller to modify the value of
* a UnicodeSet object. It conforms to Java 2's
* java.util.Set interface, although
* UnicodeSet does not actually implement that
* interface. All methods of Set are supported, with the
* modification that they take a character range or single character
* instead of an Object, and they take a
* UnicodeSet instead of a Collection. The
* operand API may be thought of in terms of boolean logic: a boolean
* OR is implemented by add, a boolean AND is implemented
* by retain, a boolean XOR is implemented by
* complement taking an argument, and a boolean NOT is
=======================================================================
==uimacpp/include/unicode/unistr.h
=======================================================================
/*
**********************************************************************
* Copyright (C) 1998-2006, International Business Machines
* Corporation and others. All Rights Reserved.
**********************************************************************
*
* File unistr.h
*
* Modification History:
*
* Date Name Description
* 09/25/98 stephen Creation.
* 11/11/98 stephen Changed per 11/9 code review.
* 04/20/99 stephen Overhauled per 4/16 code review.
* 11/18/99 aliu Made to inherit from Replaceable. Added method
* handleReplaceBetween(); other methods unchanged.
* 06/25/01 grhoten Remove dependency on iostream.
******************************************************************************
*/
#ifndef UNISTR_H
#define UNISTR_H
/**
* \file
* \brief C++ API: Unicode String
*/
#include "unicode/rep.h"
struct UConverter; // unicode/ucnv.h
class StringThreadTest;
#ifndef U_COMPARE_CODE_POINT_ORDER
/* see also ustring.h and unorm.h */
/**
* Option bit for u_strCaseCompare, u_strcasecmp, unorm_compare, etc:
* Compare strings in code point order instead of code unit order.
* @stable ICU 2.2
*/
#define U_COMPARE_CODE_POINT_ORDER 0x8000
#endif
#ifndef USTRING_H
/**
* \ingroup ustring_ustrlen
*/
U_STABLE int32_t U_EXPORT2
u_strlen(const UChar *s);
#endif
=======================================================================
==uimacpp/include/unicode/unorm.h
=======================================================================
/*
*******************************************************************************
* Copyright (c) 1996-2005, International Business Machines Corporation
* and others. All Rights Reserved.
*******************************************************************************
* File unorm.h
*
* Created by: Vladimir Weinstein 12052000
*
* Modification history :
*
* Date Name Description
* 02/01/01 synwee Added normalization quickcheck enum and method.
*/
#ifndef UNORM_H
#define UNORM_H
#include "unicode/utypes.h"
#if !UCONFIG_NO_NORMALIZATION
#include "unicode/uiter.h"
/**
* \file
* \brief C API: Unicode Normalization
*
* Unicode normalization API
*
* unorm_normalize transforms Unicode text into an equivalent composed or
* decomposed form, allowing for easier sorting and searching of text.
* unorm_normalize supports the standard normalization forms described in
*
* Unicode Standard Annex #15: Unicode Normalization Forms.
*
* Characters with accents or other adornments can be encoded in
* several different ways in Unicode. For example, take the character A-acute.
* In Unicode, this can be encoded as a single character (the
* "composed" form):
*
* \code
* 00C1 LATIN CAPITAL LETTER A WITH ACUTE
* \endcode
*
* or as two separate characters (the "decomposed" form):
*
* \code
* 0041 LATIN CAPITAL LETTER A
* 0301 COMBINING ACUTE ACCENT
* \endcode
=======================================================================
==uimacpp/include/unicode/unum.h
=======================================================================
/*
*******************************************************************************
* Copyright (C) 1997-2006, International Business Machines Corporation and others.
* All Rights Reserved.
* Modification History:
*
* Date Name Description
* 06/24/99 helena Integrated Alan's NF enhancements and Java2 bug fixes
*******************************************************************************
*/
#ifndef _UNUM
#define _UNUM
#include "unicode/utypes.h"
#if !UCONFIG_NO_FORMATTING
#include "unicode/uloc.h"
#include "unicode/umisc.h"
#include "unicode/parseerr.h"
/**
* \file
* \brief C API: NumberFormat
*
* Number Format C API
*
* Number Format C API Provides functions for
* formatting and parsing a number. Also provides methods for
* determining which locales have number formats, and what their names
* are.
*
* \code
* UChar myString[20];
* double myNumber = 7.0;
* UErrorCode status = U_ZERO_ERROR;
* UNumberFormat* nf = unum_open(UNUM_DEFAULT, NULL, -1, NULL, NULL, &status);
* unum_formatDouble(nf, myNumber, myString, 20, NULL, &status);
* printf(" Example 1: %s\n", austrdup(myString) ); //austrdup( a function used to convert UChar* to char*)
* \endcode
=======================================================================
==uimacpp/include/unicode/uobject.h
=======================================================================
/*
******************************************************************************
*
* Copyright (C) 2002-2006, International Business Machines
* Corporation and others. All Rights Reserved.
*
******************************************************************************
* file name: uobject.h
* encoding: US-ASCII
* tab size: 8 (not used)
* indentation:4
*
* created on: 2002jun26
* created by: Markus W. Scherer
*/
#ifndef __UOBJECT_H__
#define __UOBJECT_H__
#include "unicode/utypes.h"
U_NAMESPACE_BEGIN
/**
* \file
* \brief C++ API: Common ICU base class UObject.
*/
/** U_OVERRIDE_CXX_ALLOCATION - Define this to override operator new and
* delete in UMemory. Enabled by default for ICU.
*
* Enabling forces all allocation of ICU object types to use ICU's
* memory allocation. On Windows, this allows the ICU DLL to be used by
* applications that statically link the C Runtime library, meaning that
* the app and ICU will be using different heaps.
*
* @stable ICU 2.2
*/
#ifndef U_OVERRIDE_CXX_ALLOCATION
#define U_OVERRIDE_CXX_ALLOCATION 1
#endif
/** U_HAVE_PLACEMENT_NEW - Define this to define the placement new and
* delete in UMemory for STL.
*
* @stable ICU 2.6
*/
#ifndef U_HAVE_PLACEMENT_NEW
#define U_HAVE_PLACEMENT_NEW 1
#endif
=======================================================================
==uimacpp/include/unicode/uobslete.h
=======================================================================
/*
*******************************************************************************
* Copyright (C) 2004-2006, International Business Machines
* Corporation and others. All Rights Reserved.
*******************************************************************************
*
* file name:
* encoding: US-ASCII
* tab size: 8 (not used)
* indentation:4
*
* Created by: genheaders.pl, a perl script written by Ram Viswanadha
*
* Contains data for commenting out APIs.
* Gets included by umachine.h
*
* THIS FILE IS MACHINE-GENERATED, DON'T PLAY WITH IT IF YOU DON'T KNOW WHAT
* YOU ARE DOING, OTHERWISE VERY BAD THINGS WILL HAPPEN!
*/
#ifndef UOBSLETE_H
#define UOBSLETE_H
#ifdef U_HIDE_OBSOLETE_API
# if U_DISABLE_RENAMING
# else
# endif /* U_DISABLE_RENAMING */
#endif /* U_HIDE_OBSOLETE_API */
#endif /* UOBSLETE_H */
=======================================================================
==uimacpp/include/unicode/uregex.h
=======================================================================
/*
**********************************************************************
* Copyright (C) 2004-2006, International Business Machines
* Corporation and others. All Rights Reserved.
**********************************************************************
* file name: regex.h
* encoding: US-ASCII
* indentation:4
*
* created on: 2004mar09
* created by: Andy Heninger
*
* ICU Regular Expressions, API for C
*/
/**
* \file
* \brief C API: Regular Expressions
*
* C API: Resource Bundle
*
* C API representing a collection of resource information pertaining to a given
* locale. A resource bundle provides a way of accessing locale- specific information in
* a data file. You create a resource bundle that manages the resources for a given
* locale and then ask it for individual resources.
*
* Let S' be the sub-string of a text string S between the offsets start and
* end
* A pattern string P matches a text string S at the offsets
* option 1. Some canonical equivalent of P matches some canonical equivalent
* of S'
* option 2. P matches S' and if P starts or ends with a combining mark,
* there exists no non-ignorable combining mark before or after S'
* in S respectively.
*
=======================================================================
==uimacpp/include/unicode/uset.h
=======================================================================
/*
*******************************************************************************
*
* Copyright (C) 2002-2006, International Business Machines
* Corporation and others. All Rights Reserved.
*
*******************************************************************************
* file name: uset.h
* encoding: US-ASCII
* 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
*
*
* UnicodeSetIterator it(set);
* while (set.next()) {
* processItem(set.getString());
* }
*
*
* UnicodeSetIterator it(set);
* while (it.nextRange()) {
=======================================================================
==uimacpp/include/unicode/ushape.h
=======================================================================
/*
******************************************************************************
*
* Copyright (C) 2000-2004, International Business Machines
* Corporation and others. All Rights Reserved.
*
******************************************************************************
* file name: ushape.h
* encoding: US-ASCII
* tab size: 8 (not used)
* indentation:4
*
* created on: 2000jun29
* created by: Markus W. Scherer
*/
#ifndef __USHAPE_H__
#define __USHAPE_H__
#include "unicode/utypes.h"
/**
* \file
* \brief C API: Arabic shaping
*
*/
/**
* Shape Arabic text on a character basis.
*
*
*
*
* The procedure for preparing Unicode strings:
*
*
Transliteration
* 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).
*
=======================================================================
==uimacpp/include/unicode/utypes.h
=======================================================================
/*
**********************************************************************
* Copyright (C) 1996-2006, International Business Machines
* Corporation and others. All Rights Reserved.
**********************************************************************
*
* FILE NAME : UTYPES.H (formerly ptypes.h)
*
* Date Name Description
* 12/11/96 helena Creation.
* 02/27/97 aliu Added typedefs for UClassID, int8, int16, int32,
* uint8, uint16, and uint32.
* 04/01/97 aliu Added XP_CPLUSPLUS and modified to work under C as
* well as C++.
* Modified to use memcpy() for uprv_arrayCopy() fns.
* 04/14/97 aliu Added TPlatformUtilities.
* 05/07/97 aliu Added import/export specifiers (replacing the old
* broken EXT_CLASS). Added version number for our
* code. Cleaned up header.
* 6/20/97 helena Java class name change.
* 08/11/98 stephen UErrorCode changed from typedef to enum
* 08/12/98 erm Changed T_ANALYTIC_PACKAGE_VERSION to 3
* 08/14/98 stephen Added uprv_arrayCopy() for int8_t, int16_t, int32_t
* 12/09/98 jfitz Added BUFFER_OVERFLOW_ERROR (bug 1100066)
* 04/20/99 stephen Cleaned up & reworked for autoconf.
* Renamed to utypes.h.
* 05/05/99 stephen Changed to use