You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@couchdb.apache.org by be...@apache.org on 2014/02/13 19:12:15 UTC
[17/57] [abbrv] remove couch_collate
http://git-wip-us.apache.org/repos/asf/couchdb/blob/81332b78/apps/couch_collate/platform/osx/icu/unicode/ucnv_cb.h
----------------------------------------------------------------------
diff --git a/apps/couch_collate/platform/osx/icu/unicode/ucnv_cb.h b/apps/couch_collate/platform/osx/icu/unicode/ucnv_cb.h
deleted file mode 100644
index f0e67ba..0000000
--- a/apps/couch_collate/platform/osx/icu/unicode/ucnv_cb.h
+++ /dev/null
@@ -1,162 +0,0 @@
-/*
-**********************************************************************
-* Copyright (C) 2000-2004, International Business Machines
-* Corporation and others. All Rights Reserved.
-**********************************************************************
- * ucnv_cb.h:
- * External APIs for the ICU's codeset conversion library
- * Helena Shih
- *
- * Modification History:
- *
- * Date Name Description
- */
-
-/**
- * \file
- * \brief C UConverter functions to aid the writers of callbacks
- *
- * <h2> Callback API for UConverter </h2>
- *
- * 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]
- *
- * Now, suppose a callback wants to write the substitution character '?' to
- * the target. It calls ucnv_cbFromUWriteBytes() to write the ?.
- * It should pass ZERO as the offset, because the offset as far as the
- * callback is concerned is relative to the SOURCE pointer [which points
- * before 'C'.] If the callback goes into the args and consumes 'C' also,
- * it would call FromUWriteBytes with an offset of 1 (and advance the source
- * pointer).
- *
- */
-
-#ifndef UCNV_CB_H
-#define UCNV_CB_H
-
-#include "unicode/utypes.h"
-
-#if !UCONFIG_NO_CONVERSION
-
-#include "unicode/ucnv.h"
-#include "unicode/ucnv_err.h"
-
-/**
- * ONLY used by FromU callback functions.
- * Writes out the specified byte output bytes to the target byte buffer or to converter internal buffers.
- *
- * @param args callback fromUnicode arguments
- * @param source source bytes to write
- * @param length length of bytes to write
- * @param offsetIndex the relative offset index from callback.
- * @param err error status. If <TT>U_BUFFER_OVERFLOW</TT> is returned, then U_BUFFER_OVERFLOW <STRONG>must</STRONG>
- * be returned to the user, because it means that not all data could be written into the target buffer, and some is
- * in the converter error buffer.
- * @see ucnv_cbFromUWriteSub
- * @stable ICU 2.0
- */
-U_STABLE void U_EXPORT2
-ucnv_cbFromUWriteBytes (UConverterFromUnicodeArgs *args,
- const char* source,
- int32_t length,
- int32_t offsetIndex,
- UErrorCode * err);
-
-/**
- * ONLY used by FromU callback functions.
- * This function will write out the correct substitution character sequence
- * to the target.
- *
- * @param args callback fromUnicode arguments
- * @param offsetIndex the relative offset index from the current source pointer to be used
- * @param err error status. If <TT>U_BUFFER_OVERFLOW</TT> is returned, then U_BUFFER_OVERFLOW <STRONG>must</STRONG>
- * be returned to the user, because it means that not all data could be written into the target buffer, and some is
- * in the converter error buffer.
- * @see ucnv_cbFromUWriteBytes
- * @stable ICU 2.0
- */
-U_STABLE void U_EXPORT2
-ucnv_cbFromUWriteSub (UConverterFromUnicodeArgs *args,
- int32_t offsetIndex,
- UErrorCode * err);
-
-/**
- * ONLY used by fromU callback functions.
- * This function will write out the error character(s) to the target UChar buffer.
- *
- * @param args callback fromUnicode arguments
- * @param source pointer to pointer to first UChar to write [on exit: 1 after last UChar processed]
- * @param sourceLimit pointer after last UChar to write
- * @param offsetIndex the relative offset index from callback which will be set
- * @param err error status <TT>U_BUFFER_OVERFLOW</TT>
- * @see ucnv_cbToUWriteSub
- * @stable ICU 2.0
- */
-U_STABLE void U_EXPORT2 ucnv_cbFromUWriteUChars(UConverterFromUnicodeArgs *args,
- const UChar** source,
- const UChar* sourceLimit,
- int32_t offsetIndex,
- UErrorCode * err);
-
-/**
- * ONLY used by ToU callback functions.
- * This function will write out the specified characters to the target
- * UChar buffer.
- *
- * @param args callback toUnicode arguments
- * @param source source string to write
- * @param length the length of source string
- * @param offsetIndex the relative offset index which will be written.
- * @param err error status <TT>U_BUFFER_OVERFLOW</TT>
- * @see ucnv_cbToUWriteSub
- * @stable ICU 2.0
- */
-U_STABLE void U_EXPORT2 ucnv_cbToUWriteUChars (UConverterToUnicodeArgs *args,
- const UChar* source,
- int32_t length,
- int32_t offsetIndex,
- UErrorCode * err);
-
-/**
- * ONLY used by ToU callback functions.
- * This function will write out the Unicode substitution character (U+FFFD).
- *
- * @param args callback fromUnicode arguments
- * @param offsetIndex the relative offset index from callback.
- * @param err error status <TT>U_BUFFER_OVERFLOW</TT>
- * @see ucnv_cbToUWriteUChars
- * @stable ICU 2.0
- */
-U_STABLE void U_EXPORT2 ucnv_cbToUWriteSub (UConverterToUnicodeArgs *args,
- int32_t offsetIndex,
- UErrorCode * err);
-#endif
-
-#endif
http://git-wip-us.apache.org/repos/asf/couchdb/blob/81332b78/apps/couch_collate/platform/osx/icu/unicode/ucnv_err.h
----------------------------------------------------------------------
diff --git a/apps/couch_collate/platform/osx/icu/unicode/ucnv_err.h b/apps/couch_collate/platform/osx/icu/unicode/ucnv_err.h
deleted file mode 100644
index 6fde696..0000000
--- a/apps/couch_collate/platform/osx/icu/unicode/ucnv_err.h
+++ /dev/null
@@ -1,463 +0,0 @@
-/*
-**********************************************************************
-* Copyright (C) 1999-2007, International Business Machines
-* Corporation and others. All Rights Reserved.
-**********************************************************************
- *
- *
- * ucnv_err.h:
- */
-
-/**
- * \file
- * \brief C UConverter predefined error callbacks
- *
- * <h2>Error Behaviour Functions</h2>
- * 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
- *
- * The code above tells "myConverter" to stop when it encounters an
- * ILLEGAL/TRUNCATED/INVALID sequences when it is used to convert from
- * Unicode -> Codepage. The behavior from Codepage to Unicode is not changed,
- * and ucnv_setToUCallBack would need to be called in order to change
- * that behavior too.
- *
- * Here is an example with a context:
- *
- * \code
- * UErrorCode err = U_ZERO_ERROR;
- * UConverter *myConverter = ucnv_open("ibm-949", &err);
- * const void *oldContext;
- * UConverterFromUCallback oldAction;
- *
- *
- * if (U_SUCCESS(err))
- * {
- * ucnv_setToUCallBack(myConverter,
- * UCNV_TO_U_CALLBACK_SUBSTITUTE,
- * UCNV_SUB_STOP_ON_ILLEGAL,
- * &oldAction,
- * &oldContext,
- * &status);
- * }
- * \endcode
- *
- * The code above tells "myConverter" to stop when it encounters an
- * ILLEGAL/TRUNCATED/INVALID sequences when it is used to convert from
- * Codepage -> Unicode. Any unmapped and legal characters will be
- * substituted to be the default substitution character.
- */
-
-#ifndef UCNV_ERR_H
-#define UCNV_ERR_H
-
-#include "unicode/utypes.h"
-
-#if !UCONFIG_NO_CONVERSION
-
-/** Forward declaring the UConverter structure. @stable ICU 2.0 */
-struct UConverter;
-
-/** @stable ICU 2.0 */
-typedef struct UConverter UConverter;
-
-/**
- * FROM_U, TO_U context options for sub callback
- * @stable ICU 2.0
- */
-#define UCNV_SUB_STOP_ON_ILLEGAL "i"
-
-/**
- * FROM_U, TO_U context options for skip callback
- * @stable ICU 2.0
- */
-#define UCNV_SKIP_STOP_ON_ILLEGAL "i"
-
-/**
- * FROM_U_CALLBACK_ESCAPE context option to escape the code unit according to ICU (%UXXXX)
- * @stable ICU 2.0
- */
-#define UCNV_ESCAPE_ICU NULL
-/**
- * FROM_U_CALLBACK_ESCAPE context option to escape the code unit according to JAVA (\\uXXXX)
- * @stable ICU 2.0
- */
-#define UCNV_ESCAPE_JAVA "J"
-/**
- * FROM_U_CALLBACK_ESCAPE context option to escape the code unit according to C (\\uXXXX \\UXXXXXXXX)
- * TO_U_CALLBACK_ESCAPE option to escape the character value accoding to C (\\xXXXX)
- * @stable ICU 2.0
- */
-#define UCNV_ESCAPE_C "C"
-/**
- * FROM_U_CALLBACK_ESCAPE context option to escape the code unit according to XML Decimal escape \htmlonly(&#DDDD;)\endhtmlonly
- * TO_U_CALLBACK_ESCAPE context option to escape the character value accoding to XML Decimal escape \htmlonly(&#DDDD;)\endhtmlonly
- * @stable ICU 2.0
- */
-#define UCNV_ESCAPE_XML_DEC "D"
-/**
- * FROM_U_CALLBACK_ESCAPE context option to escape the code unit according to XML Hex escape \htmlonly(&#xXXXX;)\endhtmlonly
- * TO_U_CALLBACK_ESCAPE context option to escape the character value accoding to XML Hex escape \htmlonly(&#xXXXX;)\endhtmlonly
- * @stable ICU 2.0
- */
-#define UCNV_ESCAPE_XML_HEX "X"
-/**
- * FROM_U_CALLBACK_ESCAPE context option to escape the code unit according to Unicode (U+XXXXX)
- * @stable ICU 2.0
- */
-#define UCNV_ESCAPE_UNICODE "U"
-
-/**
- * FROM_U_CALLBACK_ESCAPE context option to escape the code unit according to CSS2 conventions (\\HH..H<space>, that is,
- * a backslash, 1..6 hex digits, and a space)
- * @draft ICU 4.0
- */
-#define UCNV_ESCAPE_CSS2 "S"
-
-/**
- * The process condition code to be used with the callbacks.
- * Codes which are greater than UCNV_IRREGULAR should be
- * passed on to any chained callbacks.
- * @stable ICU 2.0
- */
-typedef enum {
- UCNV_UNASSIGNED = 0, /**< The code point is unassigned.
- The error code U_INVALID_CHAR_FOUND will be set. */
- UCNV_ILLEGAL = 1, /**< The code point is illegal. For example,
- \\x81\\x2E is illegal in SJIS because \\x2E
- is not a valid trail byte for the \\x81
- lead byte.
- Also, starting with Unicode 3.0.1, non-shortest byte sequences
- in UTF-8 (like \\xC1\\xA1 instead of \\x61 for U+0061)
- are also illegal, not just irregular.
- The error code U_ILLEGAL_CHAR_FOUND will be set. */
- UCNV_IRREGULAR = 2, /**< The codepoint is not a regular sequence in
- the encoding. For example, \\xED\\xA0\\x80..\\xED\\xBF\\xBF
- are irregular UTF-8 byte sequences for single surrogate
- code points.
- The error code U_INVALID_CHAR_FOUND will be set. */
- UCNV_RESET = 3, /**< The callback is called with this reason when a
- 'reset' has occured. Callback should reset all
- state. */
- UCNV_CLOSE = 4, /**< Called when the converter is closed. The
- callback should release any allocated memory.*/
- UCNV_CLONE = 5 /**< Called when ucnv_safeClone() is called on the
- converter. the pointer available as the
- 'context' is an alias to the original converters'
- context pointer. If the context must be owned
- by the new converter, the callback must clone
- the data and call ucnv_setFromUCallback
- (or setToUCallback) with the correct pointer.
- @stable ICU 2.2
- */
-} UConverterCallbackReason;
-
-
-/**
- * The structure for the fromUnicode callback function parameter.
- * @stable ICU 2.0
- */
-typedef struct {
- uint16_t size; /**< The size of this struct. @stable ICU 2.0 */
- UBool flush; /**< The internal state of converter will be reset and data flushed if set to TRUE. @stable ICU 2.0 */
- UConverter *converter; /**< Pointer to the converter that is opened and to which this struct is passed as an argument. @stable ICU 2.0 */
- const UChar *source; /**< Pointer to the source source buffer. @stable ICU 2.0 */
- const UChar *sourceLimit; /**< Pointer to the limit (end + 1) of source buffer. @stable ICU 2.0 */
- char *target; /**< Pointer to the target buffer. @stable ICU 2.0 */
- const char *targetLimit; /**< Pointer to the limit (end + 1) of target buffer. @stable ICU 2.0 */
- int32_t *offsets; /**< Pointer to the buffer that recieves the offsets. *offset = blah ; offset++;. @stable ICU 2.0 */
-} UConverterFromUnicodeArgs;
-
-
-/**
- * The structure for the toUnicode callback function parameter.
- * @stable ICU 2.0
- */
-typedef struct {
- uint16_t size; /**< The size of this struct @stable ICU 2.0 */
- UBool flush; /**< The internal state of converter will be reset and data flushed if set to TRUE. @stable ICU 2.0 */
- UConverter *converter; /**< Pointer to the converter that is opened and to which this struct is passed as an argument. @stable ICU 2.0 */
- const char *source; /**< Pointer to the source source buffer. @stable ICU 2.0 */
- const char *sourceLimit; /**< Pointer to the limit (end + 1) of source buffer. @stable ICU 2.0 */
- UChar *target; /**< Pointer to the target buffer. @stable ICU 2.0 */
- const UChar *targetLimit; /**< Pointer to the limit (end + 1) of target buffer. @stable ICU 2.0 */
- int32_t *offsets; /**< Pointer to the buffer that recieves the offsets. *offset = blah ; offset++;. @stable ICU 2.0 */
-} UConverterToUnicodeArgs;
-
-
-/**
- * DO NOT CALL THIS FUNCTION DIRECTLY!
- * This From Unicode callback STOPS at the ILLEGAL_SEQUENCE,
- * returning the error code back to the caller immediately.
- *
- * @param context Pointer to the callback's private data
- * @param fromUArgs Information about the conversion in progress
- * @param codeUnits Points to 'length' UChars of the concerned Unicode sequence
- * @param length Size (in bytes) of the concerned codepage sequence
- * @param codePoint Single UChar32 (UTF-32) containing the concerend Unicode codepoint.
- * @param reason Defines the reason the callback was invoked
- * @param err This should always be set to a failure status prior to calling.
- * @stable ICU 2.0
- */
-U_STABLE void U_EXPORT2 UCNV_FROM_U_CALLBACK_STOP (
- const void *context,
- UConverterFromUnicodeArgs *fromUArgs,
- const UChar* codeUnits,
- int32_t length,
- UChar32 codePoint,
- UConverterCallbackReason reason,
- UErrorCode * err);
-
-
-
-/**
- * DO NOT CALL THIS FUNCTION DIRECTLY!
- * This To Unicode callback STOPS at the ILLEGAL_SEQUENCE,
- * returning the error code back to the caller immediately.
- *
- * @param context Pointer to the callback's private data
- * @param toUArgs Information about the conversion in progress
- * @param codeUnits Points to 'length' bytes of the concerned codepage sequence
- * @param length Size (in bytes) of the concerned codepage sequence
- * @param reason Defines the reason the callback was invoked
- * @param err This should always be set to a failure status prior to calling.
- * @stable ICU 2.0
- */
-U_STABLE void U_EXPORT2 UCNV_TO_U_CALLBACK_STOP (
- const void *context,
- UConverterToUnicodeArgs *toUArgs,
- const char* codeUnits,
- int32_t length,
- UConverterCallbackReason reason,
- UErrorCode * err);
-
-/**
- * DO NOT CALL THIS FUNCTION DIRECTLY!
- * This From Unicode callback skips any ILLEGAL_SEQUENCE, or
- * skips only UNASSINGED_SEQUENCE depending on the context parameter
- * simply ignoring those characters.
- *
- * @param context The function currently recognizes the callback options:
- * UCNV_SKIP_STOP_ON_ILLEGAL: STOPS at the ILLEGAL_SEQUENCE,
- * returning the error code back to the caller immediately.
- * NULL: Skips any ILLEGAL_SEQUENCE
- * @param fromUArgs Information about the conversion in progress
- * @param codeUnits Points to 'length' UChars of the concerned Unicode sequence
- * @param length Size (in bytes) of the concerned codepage sequence
- * @param codePoint Single UChar32 (UTF-32) containing the concerend Unicode codepoint.
- * @param reason Defines the reason the callback was invoked
- * @param err Return value will be set to success if the callback was handled,
- * otherwise this value will be set to a failure status.
- * @stable ICU 2.0
- */
-U_STABLE void U_EXPORT2 UCNV_FROM_U_CALLBACK_SKIP (
- const void *context,
- UConverterFromUnicodeArgs *fromUArgs,
- const UChar* codeUnits,
- int32_t length,
- UChar32 codePoint,
- UConverterCallbackReason reason,
- UErrorCode * err);
-
-/**
- * DO NOT CALL THIS FUNCTION DIRECTLY!
- * This From Unicode callback will Substitute the ILLEGAL SEQUENCE, or
- * UNASSIGNED_SEQUENCE depending on context parameter, with the
- * current substitution string for the converter. This is the default
- * callback.
- *
- * @param context The function currently recognizes the callback options:
- * UCNV_SUB_STOP_ON_ILLEGAL: STOPS at the ILLEGAL_SEQUENCE,
- * returning the error code back to the caller immediately.
- * NULL: Substitutes any ILLEGAL_SEQUENCE
- * @param fromUArgs Information about the conversion in progress
- * @param codeUnits Points to 'length' UChars of the concerned Unicode sequence
- * @param length Size (in bytes) of the concerned codepage sequence
- * @param codePoint Single UChar32 (UTF-32) containing the concerend Unicode codepoint.
- * @param reason Defines the reason the callback was invoked
- * @param err Return value will be set to success if the callback was handled,
- * otherwise this value will be set to a failure status.
- * @see ucnv_setSubstChars
- * @stable ICU 2.0
- */
-U_STABLE void U_EXPORT2 UCNV_FROM_U_CALLBACK_SUBSTITUTE (
- const void *context,
- UConverterFromUnicodeArgs *fromUArgs,
- const UChar* codeUnits,
- int32_t length,
- UChar32 codePoint,
- UConverterCallbackReason reason,
- UErrorCode * err);
-
-/**
- * DO NOT CALL THIS FUNCTION DIRECTLY!
- * This From Unicode callback will Substitute the ILLEGAL SEQUENCE with the
- * hexadecimal representation of the illegal codepoints
- *
- * @param context The function currently recognizes the callback options:
- * <ul>
- * <li>UCNV_ESCAPE_ICU: Substitues the ILLEGAL SEQUENCE with the hexadecimal
- * representation in the format %UXXXX, e.g. "%uFFFE%u00AC%uC8FE").
- * In the Event the converter doesn't support the characters {%,U}[A-F][0-9],
- * it will substitute the illegal sequence with the substitution characters.
- * Note that codeUnit(32bit int eg: unit of a surrogate pair) is represented as
- * %UD84D%UDC56</li>
- * <li>UCNV_ESCAPE_JAVA: Substitues the ILLEGAL SEQUENCE with the hexadecimal
- * representation in the format \\uXXXX, e.g. "\\uFFFE\\u00AC\\uC8FE").
- * In the Event the converter doesn't support the characters {\,u}[A-F][0-9],
- * it will substitute the illegal sequence with the substitution characters.
- * Note that codeUnit(32bit int eg: unit of a surrogate pair) is represented as
- * \\uD84D\\uDC56</li>
- * <li>UCNV_ESCAPE_C: Substitues the ILLEGAL SEQUENCE with the hexadecimal
- * representation in the format \\uXXXX, e.g. "\\uFFFE\\u00AC\\uC8FE").
- * In the Event the converter doesn't support the characters {\,u,U}[A-F][0-9],
- * it will substitute the illegal sequence with the substitution characters.
- * Note that codeUnit(32bit int eg: unit of a surrogate pair) is represented as
- * \\U00023456</li>
- * <li>UCNV_ESCAPE_XML_DEC: Substitues the ILLEGAL SEQUENCE with the decimal
- * representation in the format \htmlonly&#DDDDDDDD;, e.g. "&#65534;&#172;&#51454;")\endhtmlonly.
- * In the Event the converter doesn't support the characters {&,#}[0-9],
- * it will substitute the illegal sequence with the substitution characters.
- * Note that codeUnit(32bit int eg: unit of a surrogate pair) is represented as
- * &#144470; and Zero padding is ignored.</li>
- * <li>UCNV_ESCAPE_XML_HEX:Substitues the ILLEGAL SEQUENCE with the decimal
- * representation in the format \htmlonly&#xXXXX; e.g. "&#xFFFE;&#x00AC;&#xC8FE;")\endhtmlonly.
- * In the Event the converter doesn't support the characters {&,#,x}[0-9],
- * it will substitute the illegal sequence with the substitution characters.
- * Note that codeUnit(32bit int eg: unit of a surrogate pair) is represented as
- * \htmlonly&#x23456;\endhtmlonly</li>
- * </ul>
- * @param fromUArgs Information about the conversion in progress
- * @param codeUnits Points to 'length' UChars of the concerned Unicode sequence
- * @param length Size (in bytes) of the concerned codepage sequence
- * @param codePoint Single UChar32 (UTF-32) containing the concerend Unicode codepoint.
- * @param reason Defines the reason the callback was invoked
- * @param err Return value will be set to success if the callback was handled,
- * otherwise this value will be set to a failure status.
- * @stable ICU 2.0
- */
-U_STABLE void U_EXPORT2 UCNV_FROM_U_CALLBACK_ESCAPE (
- const void *context,
- UConverterFromUnicodeArgs *fromUArgs,
- const UChar* codeUnits,
- int32_t length,
- UChar32 codePoint,
- UConverterCallbackReason reason,
- UErrorCode * err);
-
-
-/**
- * DO NOT CALL THIS FUNCTION DIRECTLY!
- * This To Unicode callback skips any ILLEGAL_SEQUENCE, or
- * skips only UNASSINGED_SEQUENCE depending on the context parameter
- * simply ignoring those characters.
- *
- * @param context The function currently recognizes the callback options:
- * UCNV_SKIP_STOP_ON_ILLEGAL: STOPS at the ILLEGAL_SEQUENCE,
- * returning the error code back to the caller immediately.
- * NULL: Skips any ILLEGAL_SEQUENCE
- * @param toUArgs Information about the conversion in progress
- * @param codeUnits Points to 'length' bytes of the concerned codepage sequence
- * @param length Size (in bytes) of the concerned codepage sequence
- * @param reason Defines the reason the callback was invoked
- * @param err Return value will be set to success if the callback was handled,
- * otherwise this value will be set to a failure status.
- * @stable ICU 2.0
- */
-U_STABLE void U_EXPORT2 UCNV_TO_U_CALLBACK_SKIP (
- const void *context,
- UConverterToUnicodeArgs *toUArgs,
- const char* codeUnits,
- int32_t length,
- UConverterCallbackReason reason,
- UErrorCode * err);
-
-/**
- * DO NOT CALL THIS FUNCTION DIRECTLY!
- * This To Unicode callback will Substitute the ILLEGAL SEQUENCE,or
- * UNASSIGNED_SEQUENCE depending on context parameter, with the
- * Unicode substitution character, U+FFFD.
- *
- * @param context The function currently recognizes the callback options:
- * UCNV_SUB_STOP_ON_ILLEGAL: STOPS at the ILLEGAL_SEQUENCE,
- * returning the error code back to the caller immediately.
- * NULL: Substitutes any ILLEGAL_SEQUENCE
- * @param toUArgs Information about the conversion in progress
- * @param codeUnits Points to 'length' bytes of the concerned codepage sequence
- * @param length Size (in bytes) of the concerned codepage sequence
- * @param reason Defines the reason the callback was invoked
- * @param err Return value will be set to success if the callback was handled,
- * otherwise this value will be set to a failure status.
- * @stable ICU 2.0
- */
-U_STABLE void U_EXPORT2 UCNV_TO_U_CALLBACK_SUBSTITUTE (
- const void *context,
- UConverterToUnicodeArgs *toUArgs,
- const char* codeUnits,
- int32_t length,
- UConverterCallbackReason reason,
- UErrorCode * err);
-
-/**
- * DO NOT CALL THIS FUNCTION DIRECTLY!
- * This To Unicode callback will Substitute the ILLEGAL SEQUENCE with the
- * hexadecimal representation of the illegal bytes
- * (in the format %XNN, e.g. "%XFF%X0A%XC8%X03").
- *
- * @param context This function currently recognizes the callback options:
- * UCNV_ESCAPE_ICU, UCNV_ESCAPE_JAVA, UCNV_ESCAPE_C, UCNV_ESCAPE_XML_DEC,
- * UCNV_ESCAPE_XML_HEX and UCNV_ESCAPE_UNICODE.
- * @param toUArgs Information about the conversion in progress
- * @param codeUnits Points to 'length' bytes of the concerned codepage sequence
- * @param length Size (in bytes) of the concerned codepage sequence
- * @param reason Defines the reason the callback was invoked
- * @param err Return value will be set to success if the callback was handled,
- * otherwise this value will be set to a failure status.
- * @stable ICU 2.0
- */
-
-U_STABLE void U_EXPORT2 UCNV_TO_U_CALLBACK_ESCAPE (
- const void *context,
- UConverterToUnicodeArgs *toUArgs,
- const char* codeUnits,
- int32_t length,
- UConverterCallbackReason reason,
- UErrorCode * err);
-
-#endif
-
-#endif
-
-/*UCNV_ERR_H*/
http://git-wip-us.apache.org/repos/asf/couchdb/blob/81332b78/apps/couch_collate/platform/osx/icu/unicode/ucol.h
----------------------------------------------------------------------
diff --git a/apps/couch_collate/platform/osx/icu/unicode/ucol.h b/apps/couch_collate/platform/osx/icu/unicode/ucol.h
deleted file mode 100644
index 9fd952e..0000000
--- a/apps/couch_collate/platform/osx/icu/unicode/ucol.h
+++ /dev/null
@@ -1,1132 +0,0 @@
-/*
-*******************************************************************************
-* Copyright (c) 1996-2008, 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
- *
- * <h2> Collator C API </h2>
- *
- * The C API for Collator performs locale-sensitive
- * string comparison. You use this service to build
- * searching and sorting routines for natural language text.
- * <em>Important: </em>The ICU collation service has been reimplemented
- * in order to achieve better performance and UCA compliance.
- * For details, see the
- * <a href="http://source.icu-project.org/repos/icu/icuhtml/trunk/design/collation/ICU_collation_design.htm">
- * collation design document</a>.
- * <p>
- * For more information about the collation service see
- * <a href="http://icu-project.org/userguide/Collate_Intro.html">the users guide</a>.
- * <p>
- * 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 <a href="http://www.unicode.org/unicode/reports/tr10/">UCA sort order</a>.
- * <p>
- * Sort ordering may be customized by providing your own set of rules. For more on
- * this subject see the
- * <a href="http://icu-project.org/userguide/Collate_Customization.html">
- * Collation customization</a> section of the users guide.
- * <p>
- * @see UCollationResult
- * @see UNormalizationMode
- * @see UCollationStrength
- * @see UCollationElements
- */
-
-/** A collator.
-* For usage in C programs.
-*/
-struct UCollator;
-/** structure representing a collator object instance
- * @stable ICU 2.0
- */
-typedef struct UCollator UCollator;
-
-
-/**
- * UCOL_LESS is returned if source string is compared to be less than target
- * string in the u_strcoll() method.
- * UCOL_EQUAL is returned if source string is compared to be equal to target
- * string in the u_strcoll() method.
- * UCOL_GREATER is returned if source string is compared to be greater than
- * target string in the u_strcoll() method.
- * @see u_strcoll()
- * <p>
- * Possible values for a comparison result
- * @stable ICU 2.0
- */
-typedef enum {
- /** string a == string b */
- UCOL_EQUAL = 0,
- /** string a > string b */
- UCOL_GREATER = 1,
- /** string a < string b */
- UCOL_LESS = -1
-} UCollationResult ;
-
-
-/** Enum containing attribute values for controling collation behavior.
- * Here are all the allowable values. Not every attribute can take every value. The only
- * universal value is UCOL_DEFAULT, which resets the attribute value to the predefined
- * value for that locale
- * @stable ICU 2.0
- */
-typedef enum {
- /** accepted by most attributes */
- UCOL_DEFAULT = -1,
-
- /** Primary collation strength */
- UCOL_PRIMARY = 0,
- /** Secondary collation strength */
- UCOL_SECONDARY = 1,
- /** Tertiary collation strength */
- UCOL_TERTIARY = 2,
- /** Default collation strength */
- UCOL_DEFAULT_STRENGTH = UCOL_TERTIARY,
- UCOL_CE_STRENGTH_LIMIT,
- /** Quaternary collation strength */
- UCOL_QUATERNARY=3,
- /** Identical collation strength */
- UCOL_IDENTICAL=15,
- UCOL_STRENGTH_LIMIT,
-
- /** Turn the feature off - works for UCOL_FRENCH_COLLATION,
- UCOL_CASE_LEVEL, UCOL_HIRAGANA_QUATERNARY_MODE
- & UCOL_DECOMPOSITION_MODE*/
- UCOL_OFF = 16,
- /** Turn the feature on - works for UCOL_FRENCH_COLLATION,
- UCOL_CASE_LEVEL, UCOL_HIRAGANA_QUATERNARY_MODE
- & UCOL_DECOMPOSITION_MODE*/
- UCOL_ON = 17,
-
- /** Valid for UCOL_ALTERNATE_HANDLING. Alternate handling will be shifted */
- UCOL_SHIFTED = 20,
- /** Valid for UCOL_ALTERNATE_HANDLING. Alternate handling will be non ignorable */
- UCOL_NON_IGNORABLE = 21,
-
- /** Valid for UCOL_CASE_FIRST -
- lower case sorts before upper case */
- UCOL_LOWER_FIRST = 24,
- /** upper case sorts before lower case */
- UCOL_UPPER_FIRST = 25,
-
- UCOL_ATTRIBUTE_VALUE_COUNT
-
-} UColAttributeValue;
-
-/**
- * Base letter represents a primary difference. Set comparison
- * level to UCOL_PRIMARY to ignore secondary and tertiary differences.
- * Use this to set the strength of a Collator object.
- * Example of primary difference, "abc" < "abd"
- *
- * Diacritical differences on the same base letter represent a secondary
- * difference. Set comparison level to UCOL_SECONDARY to ignore tertiary
- * differences. Use this to set the strength of a Collator object.
- * Example of secondary difference, "ä" >> "a".
- *
- * Uppercase and lowercase versions of the same character represents a
- * tertiary difference. Set comparison level to UCOL_TERTIARY to include
- * all comparison differences. Use this to set the strength of a Collator
- * object.
- * Example of tertiary difference, "abc" <<< "ABC".
- *
- * Two characters are considered "identical" when they have the same
- * unicode spellings. UCOL_IDENTICAL.
- * For example, "ä" == "ä".
- *
- * UCollationStrength is also used to determine the strength of sort keys
- * generated from UCollator objects
- * These values can be now found in the UColAttributeValue enum.
- * @stable ICU 2.0
- **/
-typedef UColAttributeValue UCollationStrength;
-
-/** Attributes that collation service understands. All the attributes can take UCOL_DEFAULT
- * value, as well as the values specific to each one.
- * @stable ICU 2.0
- */
-typedef enum {
- /** Attribute for direction of secondary weights - used in French.
- * Acceptable values are UCOL_ON, which results in secondary weights
- * being considered backwards and UCOL_OFF which treats secondary
- * weights in the order they appear.*/
- UCOL_FRENCH_COLLATION,
- /** Attribute for handling variable elements.
- * Acceptable values are UCOL_NON_IGNORABLE (default)
- * which treats all the codepoints with non-ignorable
- * primary weights in the same way,
- * and UCOL_SHIFTED which causes codepoints with primary
- * weights that are equal or below the variable top value
- * to be ignored on primary level and moved to the quaternary
- * level.*/
- UCOL_ALTERNATE_HANDLING,
- /** Controls the ordering of upper and lower case letters.
- * Acceptable values are UCOL_OFF (default), which orders
- * upper and lower case letters in accordance to their tertiary
- * weights, UCOL_UPPER_FIRST which forces upper case letters to
- * sort before lower case letters, and UCOL_LOWER_FIRST which does
- * the opposite. */
- UCOL_CASE_FIRST,
- /** Controls whether an extra case level (positioned before the third
- * level) is generated or not. Acceptable values are UCOL_OFF (default),
- * when case level is not generated, and UCOL_ON which causes the case
- * level to be generated. Contents of the case level are affected by
- * the value of UCOL_CASE_FIRST attribute. A simple way to ignore
- * accent differences in a string is to set the strength to UCOL_PRIMARY
- * and enable case level. */
- UCOL_CASE_LEVEL,
- /** Controls whether the normalization check and necessary normalizations
- * are performed. When set to UCOL_OFF (default) no normalization check
- * is performed. The correctness of the result is guaranteed only if the
- * input data is in so-called FCD form (see users manual for more info).
- * When set to UCOL_ON, an incremental check is performed to see whether
- * the input data is in the FCD form. If the data is not in the FCD form,
- * incremental NFD normalization is performed. */
- UCOL_NORMALIZATION_MODE,
- /** An alias for UCOL_NORMALIZATION_MODE attribute */
- UCOL_DECOMPOSITION_MODE = UCOL_NORMALIZATION_MODE,
- /** The strength attribute. Can be either UCOL_PRIMARY, UCOL_SECONDARY,
- * UCOL_TERTIARY, UCOL_QUATERNARY or UCOL_IDENTICAL. The usual strength
- * for most locales (except Japanese) is tertiary. Quaternary strength
- * is useful when combined with shifted setting for alternate handling
- * attribute and for JIS x 4061 collation, when it is used to distinguish
- * between Katakana and Hiragana (this is achieved by setting the
- * UCOL_HIRAGANA_QUATERNARY mode to on. Otherwise, quaternary level
- * is affected only by the number of non ignorable code points in
- * the string. Identical strength is rarely useful, as it amounts
- * to codepoints of the NFD form of the string. */
- UCOL_STRENGTH,
- /** When turned on, this attribute positions Hiragana before all
- * non-ignorables on quaternary level This is a sneaky way to produce JIS
- * sort order */
- UCOL_HIRAGANA_QUATERNARY_MODE,
- /** When turned on, this attribute generates a collation key
- * for the numeric value of substrings of digits.
- * This is a way to get '100' to sort AFTER '2'. */
- UCOL_NUMERIC_COLLATION,
- UCOL_ATTRIBUTE_COUNT
-} UColAttribute;
-
-/** Options for retrieving the rule string
- * @stable ICU 2.0
- */
-typedef enum {
- /** Retrieve tailoring only */
- UCOL_TAILORING_ONLY,
- /** Retrieve UCA rules and tailoring */
- UCOL_FULL_RULES
-} UColRuleOption ;
-
-/**
- * Open a UCollator for comparing strings.
- * The UCollator pointer is used in all the calls to the Collation
- * service. After finished, collator must be disposed of by calling
- * {@link #ucol_close }.
- * @param loc The locale containing the required collation rules.
- * Special values for locales can be passed in -
- * if NULL is passed for the locale, the default locale
- * collation rules will be used. If empty string ("") or
- * "root" are passed, UCA rules will be used.
- * @param status A pointer to an UErrorCode to receive any errors
- * @return A pointer to a UCollator, or 0 if an error occurred.
- * @see ucol_openRules
- * @see ucol_safeClone
- * @see ucol_close
- * @stable ICU 2.0
- */
-U_STABLE UCollator* U_EXPORT2
-ucol_open(const char *loc, UErrorCode *status);
-
-/**
- * Produce an UCollator instance according to the rules supplied.
- * The rules are used to change the default ordering, defined in the
- * UCA in a process called tailoring. The resulting UCollator pointer
- * can be used in the same way as the one obtained by {@link #ucol_strcoll }.
- * @param rules A string describing the collation rules. For the syntax
- * of the rules please see users guide.
- * @param rulesLength The length of rules, or -1 if null-terminated.
- * @param normalizationMode The normalization mode: One of
- * UCOL_OFF (expect the text to not need normalization),
- * UCOL_ON (normalize), or
- * UCOL_DEFAULT (set the mode according to the rules)
- * @param strength The default collation strength; one of UCOL_PRIMARY, UCOL_SECONDARY,
- * UCOL_TERTIARY, UCOL_IDENTICAL,UCOL_DEFAULT_STRENGTH - can be also set in the rules.
- * @param parseError A pointer to UParseError to recieve information about errors
- * occurred during parsing. This argument can currently be set
- * to NULL, but at users own risk. Please provide a real structure.
- * @param status A pointer to an UErrorCode to receive any errors
- * @return A pointer to a UCollator. It is not guaranteed that NULL be returned in case
- * of error - please use status argument to check for errors.
- * @see ucol_open
- * @see ucol_safeClone
- * @see ucol_close
- * @stable ICU 2.0
- */
-U_STABLE UCollator* U_EXPORT2
-ucol_openRules( const UChar *rules,
- int32_t rulesLength,
- UColAttributeValue normalizationMode,
- UCollationStrength strength,
- UParseError *parseError,
- UErrorCode *status);
-
-/**
- * Open a collator defined by a short form string.
- * The structure and the syntax of the string is defined in the "Naming collators"
- * section of the users guide:
- * http://icu-project.org/userguide/Collate_Concepts.html#Naming_Collators
- * Attributes are overriden by the subsequent attributes. So, for "S2_S3", final
- * strength will be 3. 3066bis locale overrides individual locale parts.
- * The call to this function is equivalent to a call to ucol_open, followed by a
- * series of calls to ucol_setAttribute and ucol_setVariableTop.
- * @param definition A short string containing a locale and a set of attributes.
- * Attributes not explicitly mentioned are left at the default
- * state for a locale.
- * @param parseError if not NULL, structure that will get filled with error's pre
- * and post context in case of error.
- * @param forceDefaults if FALSE, the settings that are the same as the collator
- * default settings will not be applied (for example, setting
- * French secondary on a French collator would not be executed).
- * If TRUE, all the settings will be applied regardless of the
- * collator default value. If the definition
- * strings are to be cached, should be set to FALSE.
- * @param status Error code. Apart from regular error conditions connected to
- * instantiating collators (like out of memory or similar), this
- * API will return an error if an invalid attribute or attribute/value
- * combination is specified.
- * @return A pointer to a UCollator or 0 if an error occured (including an
- * invalid attribute).
- * @see ucol_open
- * @see ucol_setAttribute
- * @see ucol_setVariableTop
- * @see ucol_getShortDefinitionString
- * @see ucol_normalizeShortDefinitionString
- * @stable ICU 3.0
- *
- */
-U_STABLE UCollator* U_EXPORT2
-ucol_openFromShortString( const char *definition,
- UBool forceDefaults,
- UParseError *parseError,
- UErrorCode *status);
-
-/**
- * Get a set containing the contractions defined by the collator. The set includes
- * both the UCA contractions and the contractions defined by the collator. This set
- * will contain only strings. If a tailoring explicitly suppresses contractions from
- * the UCA (like Russian), removed contractions will not be in the resulting set.
- * @param coll collator
- * @param conts the set to hold the result. It gets emptied before
- * contractions are added.
- * @param status to hold the error code
- * @return the size of the contraction set
- *
- * @deprecated ICU 3.4, use ucol_getContractionsAndExpansions instead
- */
-U_DEPRECATED int32_t U_EXPORT2
-ucol_getContractions( const UCollator *coll,
- USet *conts,
- UErrorCode *status);
-
-/**
- * Get a set containing the expansions defined by the collator. The set includes
- * both the UCA expansions and the expansions defined by the tailoring
- * @param coll collator
- * @param contractions if not NULL, the set to hold the contractions
- * @param expansions if not NULL, the set to hold the expansions
- * @param addPrefixes add the prefix contextual elements to contractions
- * @param status to hold the error code
- *
- * @stable ICU 3.4
- */
-U_STABLE void U_EXPORT2
-ucol_getContractionsAndExpansions( const UCollator *coll,
- USet *contractions, USet *expansions,
- UBool addPrefixes, UErrorCode *status);
-
-/**
- * Close a UCollator.
- * Once closed, a UCollator should not be used. Every open collator should
- * be closed. Otherwise, a memory leak will result.
- * @param coll The UCollator to close.
- * @see ucol_open
- * @see ucol_openRules
- * @see ucol_safeClone
- * @stable ICU 2.0
- */
-U_STABLE void U_EXPORT2
-ucol_close(UCollator *coll);
-
-/**
- * Compare two strings.
- * The strings will be compared using the options already specified.
- * @param coll The UCollator containing the comparison rules.
- * @param source The source string.
- * @param sourceLength The length of source, or -1 if null-terminated.
- * @param target The target string.
- * @param targetLength The length of target, or -1 if null-terminated.
- * @return The result of comparing the strings; one of UCOL_EQUAL,
- * UCOL_GREATER, UCOL_LESS
- * @see ucol_greater
- * @see ucol_greaterOrEqual
- * @see ucol_equal
- * @stable ICU 2.0
- */
-U_STABLE UCollationResult U_EXPORT2
-ucol_strcoll( const UCollator *coll,
- const UChar *source,
- int32_t sourceLength,
- const UChar *target,
- int32_t targetLength);
-
-/**
- * Determine if one string is greater than another.
- * This function is equivalent to {@link #ucol_strcoll } == UCOL_GREATER
- * @param coll The UCollator containing the comparison rules.
- * @param source The source string.
- * @param sourceLength The length of source, or -1 if null-terminated.
- * @param target The target string.
- * @param targetLength The length of target, or -1 if null-terminated.
- * @return TRUE if source is greater than target, FALSE otherwise.
- * @see ucol_strcoll
- * @see ucol_greaterOrEqual
- * @see ucol_equal
- * @stable ICU 2.0
- */
-U_STABLE UBool U_EXPORT2
-ucol_greater(const UCollator *coll,
- const UChar *source, int32_t sourceLength,
- const UChar *target, int32_t targetLength);
-
-/**
- * Determine if one string is greater than or equal to another.
- * This function is equivalent to {@link #ucol_strcoll } != UCOL_LESS
- * @param coll The UCollator containing the comparison rules.
- * @param source The source string.
- * @param sourceLength The length of source, or -1 if null-terminated.
- * @param target The target string.
- * @param targetLength The length of target, or -1 if null-terminated.
- * @return TRUE if source is greater than or equal to target, FALSE otherwise.
- * @see ucol_strcoll
- * @see ucol_greater
- * @see ucol_equal
- * @stable ICU 2.0
- */
-U_STABLE UBool U_EXPORT2
-ucol_greaterOrEqual(const UCollator *coll,
- const UChar *source, int32_t sourceLength,
- const UChar *target, int32_t targetLength);
-
-/**
- * Compare two strings for equality.
- * This function is equivalent to {@link #ucol_strcoll } == UCOL_EQUAL
- * @param coll The UCollator containing the comparison rules.
- * @param source The source string.
- * @param sourceLength The length of source, or -1 if null-terminated.
- * @param target The target string.
- * @param targetLength The length of target, or -1 if null-terminated.
- * @return TRUE if source is equal to target, FALSE otherwise
- * @see ucol_strcoll
- * @see ucol_greater
- * @see ucol_greaterOrEqual
- * @stable ICU 2.0
- */
-U_STABLE UBool U_EXPORT2
-ucol_equal(const UCollator *coll,
- const UChar *source, int32_t sourceLength,
- const UChar *target, int32_t targetLength);
-
-/**
- * Compare two UTF-8 encoded trings.
- * The strings will be compared using the options already specified.
- * @param coll The UCollator containing the comparison rules.
- * @param sIter The source string iterator.
- * @param tIter The target string iterator.
- * @return The result of comparing the strings; one of UCOL_EQUAL,
- * UCOL_GREATER, UCOL_LESS
- * @param status A pointer to an UErrorCode to receive any errors
- * @see ucol_strcoll
- * @stable ICU 2.6
- */
-U_STABLE UCollationResult U_EXPORT2
-ucol_strcollIter( const UCollator *coll,
- UCharIterator *sIter,
- UCharIterator *tIter,
- UErrorCode *status);
-
-/**
- * Get the collation strength used in a UCollator.
- * The strength influences how strings are compared.
- * @param coll The UCollator to query.
- * @return The collation strength; one of UCOL_PRIMARY, UCOL_SECONDARY,
- * UCOL_TERTIARY, UCOL_QUATERNARY, UCOL_IDENTICAL
- * @see ucol_setStrength
- * @stable ICU 2.0
- */
-U_STABLE UCollationStrength U_EXPORT2
-ucol_getStrength(const UCollator *coll);
-
-/**
- * Set the collation strength used in a UCollator.
- * The strength influences how strings are compared.
- * @param coll The UCollator to set.
- * @param strength The desired collation strength; one of UCOL_PRIMARY,
- * UCOL_SECONDARY, UCOL_TERTIARY, UCOL_QUATERNARY, UCOL_IDENTICAL, UCOL_DEFAULT
- * @see ucol_getStrength
- * @stable ICU 2.0
- */
-U_STABLE void U_EXPORT2
-ucol_setStrength(UCollator *coll,
- UCollationStrength strength);
-
-/**
- * Get the display name for a UCollator.
- * The display name is suitable for presentation to a user.
- * @param objLoc The locale of the collator in question.
- * @param dispLoc The locale for display.
- * @param result A pointer to a buffer to receive the attribute.
- * @param resultLength The maximum size of result.
- * @param status A pointer to an UErrorCode to receive any errors
- * @return The total buffer size needed; if greater than resultLength,
- * the output was truncated.
- * @stable ICU 2.0
- */
-U_STABLE int32_t U_EXPORT2
-ucol_getDisplayName( const char *objLoc,
- const char *dispLoc,
- UChar *result,
- int32_t resultLength,
- UErrorCode *status);
-
-/**
- * Get a locale for which collation rules are available.
- * A UCollator in a locale returned by this function will perform the correct
- * collation for the locale.
- * @param index The index of the desired locale.
- * @return A locale for which collation rules are available, or 0 if none.
- * @see ucol_countAvailable
- * @stable ICU 2.0
- */
-U_STABLE const char* U_EXPORT2
-ucol_getAvailable(int32_t index);
-
-/**
- * Determine how many locales have collation rules available.
- * This function is most useful as determining the loop ending condition for
- * calls to {@link #ucol_getAvailable }.
- * @return The number of locales for which collation rules are available.
- * @see ucol_getAvailable
- * @stable ICU 2.0
- */
-U_STABLE int32_t U_EXPORT2
-ucol_countAvailable(void);
-
-#if !UCONFIG_NO_SERVICE
-/**
- * Create a string enumerator of all locales for which a valid
- * collator may be opened.
- * @param status input-output error code
- * @return a string enumeration over locale strings. The caller is
- * responsible for closing the result.
- * @stable ICU 3.0
- */
-U_STABLE UEnumeration* U_EXPORT2
-ucol_openAvailableLocales(UErrorCode *status);
-#endif
-
-/**
- * Create a string enumerator of all possible keywords that are relevant to
- * collation. At this point, the only recognized keyword for this
- * service is "collation".
- * @param status input-output error code
- * @return a string enumeration over locale strings. The caller is
- * responsible for closing the result.
- * @stable ICU 3.0
- */
-U_STABLE UEnumeration* U_EXPORT2
-ucol_getKeywords(UErrorCode *status);
-
-/**
- * Given a keyword, create a string enumeration of all values
- * for that keyword that are currently in use.
- * @param keyword a particular keyword as enumerated by
- * ucol_getKeywords. If any other keyword is passed in, *status is set
- * to U_ILLEGAL_ARGUMENT_ERROR.
- * @param status input-output error code
- * @return a string enumeration over collation keyword values, or NULL
- * upon error. The caller is responsible for closing the result.
- * @stable ICU 3.0
- */
-U_STABLE UEnumeration* U_EXPORT2
-ucol_getKeywordValues(const char *keyword, UErrorCode *status);
-
-/**
- * Return the functionally equivalent locale for the given
- * requested locale, with respect to given keyword, for the
- * collation service. If two locales return the same result, then
- * collators instantiated for these locales will behave
- * equivalently. The converse is not always true; two collators
- * may in fact be equivalent, but return different results, due to
- * internal details. The return result has no other meaning than
- * that stated above, and implies nothing as to the relationship
- * between the two locales. This is intended for use by
- * applications who wish to cache collators, or otherwise reuse
- * collators when possible. The functional equivalent may change
- * over time. For more information, please see the <a
- * href="http://icu-project.org/userguide/locale.html#services">
- * Locales and Services</a> section of the ICU User Guide.
- * @param result fillin for the functionally equivalent locale
- * @param resultCapacity capacity of the fillin buffer
- * @param keyword a particular keyword as enumerated by
- * ucol_getKeywords.
- * @param locale the requested locale
- * @param isAvailable if non-NULL, pointer to a fillin parameter that
- * indicates whether the requested locale was 'available' to the
- * collation service. A locale is defined as 'available' if it
- * physically exists within the collation locale data.
- * @param status pointer to input-output error code
- * @return the actual buffer size needed for the locale. If greater
- * than resultCapacity, the returned full name will be truncated and
- * an error code will be returned.
- * @stable ICU 3.0
- */
-U_STABLE int32_t U_EXPORT2
-ucol_getFunctionalEquivalent(char* result, int32_t resultCapacity,
- const char* keyword, const char* locale,
- UBool* isAvailable, UErrorCode* status);
-
-/**
- * Get the collation rules from a UCollator.
- * The rules will follow the rule syntax.
- * @param coll The UCollator to query.
- * @param length
- * @return The collation rules.
- * @stable ICU 2.0
- */
-U_STABLE const UChar* U_EXPORT2
-ucol_getRules( const UCollator *coll,
- int32_t *length);
-
-/** Get the short definition string for a collator. This API harvests the collator's
- * locale and the attribute set and produces a string that can be used for opening
- * a collator with the same properties using the ucol_openFromShortString API.
- * This string will be normalized.
- * The structure and the syntax of the string is defined in the "Naming collators"
- * section of the users guide:
- * http://icu-project.org/userguide/Collate_Concepts.html#Naming_Collators
- * This API supports preflighting.
- * @param coll a collator
- * @param locale a locale that will appear as a collators locale in the resulting
- * short string definition. If NULL, the locale will be harvested
- * from the collator.
- * @param buffer space to hold the resulting string
- * @param capacity capacity of the buffer
- * @param status for returning errors. All the preflighting errors are featured
- * @return length of the resulting string
- * @see ucol_openFromShortString
- * @see ucol_normalizeShortDefinitionString
- * @stable ICU 3.0
- */
-U_STABLE int32_t U_EXPORT2
-ucol_getShortDefinitionString(const UCollator *coll,
- const char *locale,
- char *buffer,
- int32_t capacity,
- UErrorCode *status);
-
-/** Verifies and normalizes short definition string.
- * Normalized short definition string has all the option sorted by the argument name,
- * so that equivalent definition strings are the same.
- * This API supports preflighting.
- * @param source definition string
- * @param destination space to hold the resulting string
- * @param capacity capacity of the buffer
- * @param parseError if not NULL, structure that will get filled with error's pre
- * and post context in case of error.
- * @param status Error code. This API will return an error if an invalid attribute
- * or attribute/value combination is specified. All the preflighting
- * errors are also featured
- * @return length of the resulting normalized string.
- *
- * @see ucol_openFromShortString
- * @see ucol_getShortDefinitionString
- *
- * @stable ICU 3.0
- */
-
-U_STABLE int32_t U_EXPORT2
-ucol_normalizeShortDefinitionString(const char *source,
- char *destination,
- int32_t capacity,
- UParseError *parseError,
- UErrorCode *status);
-
-
-/**
- * Get a sort key for a string from a UCollator.
- * Sort keys may be compared using <TT>strcmp</TT>.
- * @param coll The UCollator containing the collation rules.
- * @param source The string to transform.
- * @param sourceLength The length of source, or -1 if null-terminated.
- * @param result A pointer to a buffer to receive the attribute.
- * @param resultLength The maximum size of result.
- * @return The size needed to fully store the sort key.
- * If there was an internal error generating the sort key,
- * a zero value is returned.
- * @see ucol_keyHashCode
- * @stable ICU 2.0
- */
-U_STABLE int32_t U_EXPORT2
-ucol_getSortKey(const UCollator *coll,
- const UChar *source,
- int32_t sourceLength,
- uint8_t *result,
- int32_t resultLength);
-
-
-/** Gets the next count bytes of a sort key. Caller needs
- * to preserve state array between calls and to provide
- * the same type of UCharIterator set with the same string.
- * The destination buffer provided must be big enough to store
- * the number of requested bytes. Generated sortkey is not
- * compatible with sortkeys generated using ucol_getSortKey
- * API, since we don't do any compression. If uncompressed
- * sortkeys are required, this API can be used.
- * @param coll The UCollator containing the collation rules.
- * @param iter UCharIterator containing the string we need
- * the sort key to be calculated for.
- * @param state Opaque state of sortkey iteration.
- * @param dest Buffer to hold the resulting sortkey part
- * @param count number of sort key bytes required.
- * @param status error code indicator.
- * @return the actual number of bytes of a sortkey. It can be
- * smaller than count if we have reached the end of
- * the sort key.
- * @stable ICU 2.6
- */
-U_STABLE int32_t U_EXPORT2
-ucol_nextSortKeyPart(const UCollator *coll,
- UCharIterator *iter,
- uint32_t state[2],
- uint8_t *dest, int32_t count,
- UErrorCode *status);
-
-/** enum that is taken by ucol_getBound API
- * See below for explanation
- * do not change the values assigned to the
- * members of this enum. Underlying code
- * depends on them having these numbers
- * @stable ICU 2.0
- */
-typedef enum {
- /** lower bound */
- UCOL_BOUND_LOWER = 0,
- /** upper bound that will match strings of exact size */
- UCOL_BOUND_UPPER = 1,
- /** upper bound that will match all the strings that have the same initial substring as the given string */
- UCOL_BOUND_UPPER_LONG = 2,
- UCOL_BOUND_VALUE_COUNT
-} UColBoundMode;
-
-/**
- * Produce a bound for a given sortkey and a number of levels.
- * Return value is always the number of bytes needed, regardless of
- * whether the result buffer was big enough or even valid.<br>
- * Resulting bounds can be used to produce a range of strings that are
- * between upper and lower bounds. For example, if bounds are produced
- * for a sortkey of string "smith", strings between upper and lower
- * bounds with one level would include "Smith", "SMITH", "sMiTh".<br>
- * There are two upper bounds that can be produced. If UCOL_BOUND_UPPER
- * is produced, strings matched would be as above. However, if bound
- * produced using UCOL_BOUND_UPPER_LONG is used, the above example will
- * also match "Smithsonian" and similar.<br>
- * For more on usage, see example in cintltst/capitst.c in procedure
- * TestBounds.
- * Sort keys may be compared using <TT>strcmp</TT>.
- * @param source The source sortkey.
- * @param sourceLength The length of source, or -1 if null-terminated.
- * (If an unmodified sortkey is passed, it is always null
- * terminated).
- * @param boundType Type of bound required. It can be UCOL_BOUND_LOWER, which
- * produces a lower inclusive bound, UCOL_BOUND_UPPER, that
- * produces upper bound that matches strings of the same length
- * or UCOL_BOUND_UPPER_LONG that matches strings that have the
- * same starting substring as the source string.
- * @param noOfLevels Number of levels required in the resulting bound (for most
- * uses, the recommended value is 1). See users guide for
- * explanation on number of levels a sortkey can have.
- * @param result A pointer to a buffer to receive the resulting sortkey.
- * @param resultLength The maximum size of result.
- * @param status Used for returning error code if something went wrong. If the
- * number of levels requested is higher than the number of levels
- * in the source key, a warning (U_SORT_KEY_TOO_SHORT_WARNING) is
- * issued.
- * @return The size needed to fully store the bound.
- * @see ucol_keyHashCode
- * @stable ICU 2.1
- */
-U_STABLE int32_t U_EXPORT2
-ucol_getBound(const uint8_t *source,
- int32_t sourceLength,
- UColBoundMode boundType,
- uint32_t noOfLevels,
- uint8_t *result,
- int32_t resultLength,
- UErrorCode *status);
-
-/**
- * Gets the version information for a Collator. Version is currently
- * an opaque 32-bit number which depends, among other things, on major
- * versions of the collator tailoring and UCA.
- * @param coll The UCollator to query.
- * @param info the version # information, the result will be filled in
- * @stable ICU 2.0
- */
-U_STABLE void U_EXPORT2
-ucol_getVersion(const UCollator* coll, UVersionInfo info);
-
-/**
- * Gets the UCA version information for a Collator. Version is the
- * UCA version number (3.1.1, 4.0).
- * @param coll The UCollator to query.
- * @param info the version # information, the result will be filled in
- * @stable ICU 2.8
- */
-U_STABLE void U_EXPORT2
-ucol_getUCAVersion(const UCollator* coll, UVersionInfo info);
-
-/**
- * Merge two sort keys. The levels are merged with their corresponding counterparts
- * (primaries with primaries, secondaries with secondaries etc.). Between the values
- * from the same level a separator is inserted.
- * example (uncompressed):
- * 191B1D 01 050505 01 910505 00 and 1F2123 01 050505 01 910505 00
- * will be merged as
- * 191B1D 02 1F212301 050505 02 050505 01 910505 02 910505 00
- * This allows for concatenating of first and last names for sorting, among other things.
- * If the destination buffer is not big enough, the results are undefined.
- * If any of source lengths are zero or any of source pointers are NULL/undefined,
- * result is of size zero.
- * @param src1 pointer to the first sortkey
- * @param src1Length length of the first sortkey
- * @param src2 pointer to the second sortkey
- * @param src2Length length of the second sortkey
- * @param dest buffer to hold the result
- * @param destCapacity size of the buffer for the result
- * @return size of the result. If the buffer is big enough size is always
- * src1Length+src2Length-1
- * @stable ICU 2.0
- */
-U_STABLE int32_t U_EXPORT2
-ucol_mergeSortkeys(const uint8_t *src1, int32_t src1Length,
- const uint8_t *src2, int32_t src2Length,
- uint8_t *dest, int32_t destCapacity);
-
-/**
- * Universal attribute setter
- * @param coll collator which attributes are to be changed
- * @param attr attribute type
- * @param value attribute value
- * @param status to indicate whether the operation went on smoothly or there were errors
- * @see UColAttribute
- * @see UColAttributeValue
- * @see ucol_getAttribute
- * @stable ICU 2.0
- */
-U_STABLE void U_EXPORT2
-ucol_setAttribute(UCollator *coll, UColAttribute attr, UColAttributeValue value, UErrorCode *status);
-
-/**
- * Universal attribute getter
- * @param coll collator which attributes are to be changed
- * @param attr attribute type
- * @return attribute value
- * @param status to indicate whether the operation went on smoothly or there were errors
- * @see UColAttribute
- * @see UColAttributeValue
- * @see ucol_setAttribute
- * @stable ICU 2.0
- */
-U_STABLE UColAttributeValue U_EXPORT2
-ucol_getAttribute(const UCollator *coll, UColAttribute attr, UErrorCode *status);
-
-/** Variable top
- * is a two byte primary value which causes all the codepoints with primary values that
- * are less or equal than the variable top to be shifted when alternate handling is set
- * to UCOL_SHIFTED.
- * Sets the variable top to a collation element value of a string supplied.
- * @param coll collator which variable top needs to be changed
- * @param varTop one or more (if contraction) UChars to which the variable top should be set
- * @param len length of variable top string. If -1 it is considered to be zero terminated.
- * @param status error code. If error code is set, the return value is undefined.
- * Errors set by this function are: <br>
- * U_CE_NOT_FOUND_ERROR if more than one character was passed and there is no such
- * a contraction<br>
- * U_PRIMARY_TOO_LONG_ERROR if the primary for the variable top has more than two bytes
- * @return a 32 bit value containing the value of the variable top in upper 16 bits.
- * Lower 16 bits are undefined
- * @see ucol_getVariableTop
- * @see ucol_restoreVariableTop
- * @stable ICU 2.0
- */
-U_STABLE uint32_t U_EXPORT2
-ucol_setVariableTop(UCollator *coll,
- const UChar *varTop, int32_t len,
- UErrorCode *status);
-
-/**
- * Gets the variable top value of a Collator.
- * Lower 16 bits are undefined and should be ignored.
- * @param coll collator which variable top needs to be retrieved
- * @param status error code (not changed by function). If error code is set,
- * the return value is undefined.
- * @return the variable top value of a Collator.
- * @see ucol_setVariableTop
- * @see ucol_restoreVariableTop
- * @stable ICU 2.0
- */
-U_STABLE uint32_t U_EXPORT2 ucol_getVariableTop(const UCollator *coll, UErrorCode *status);
-
-/**
- * Sets the variable top to a collation element value supplied. Variable top is
- * set to the upper 16 bits.
- * Lower 16 bits are ignored.
- * @param coll collator which variable top needs to be changed
- * @param varTop CE value, as returned by ucol_setVariableTop or ucol)getVariableTop
- * @param status error code (not changed by function)
- * @see ucol_getVariableTop
- * @see ucol_setVariableTop
- * @stable ICU 2.0
- */
-U_STABLE void U_EXPORT2
-ucol_restoreVariableTop(UCollator *coll, const uint32_t varTop, UErrorCode *status);
-
-/**
- * Thread safe cloning operation. The result is a clone of a given collator.
- * @param coll collator to be cloned
- * @param stackBuffer user allocated space for the new clone.
- * If NULL new memory will be allocated.
- * If buffer is not large enough, new memory will be allocated.
- * Clients can use the U_COL_SAFECLONE_BUFFERSIZE.
- * This will probably be enough to avoid memory allocations.
- * @param pBufferSize pointer to size of allocated space.
- * If *pBufferSize == 0, a sufficient size for use in cloning will
- * be returned ('pre-flighting')
- * If *pBufferSize is not enough for a stack-based safe clone,
- * new memory will be allocated.
- * @param status to indicate whether the operation went on smoothly or there were errors
- * An informational status value, U_SAFECLONE_ALLOCATED_ERROR, is used if any
- * allocations were necessary.
- * @return pointer to the new clone
- * @see ucol_open
- * @see ucol_openRules
- * @see ucol_close
- * @stable ICU 2.0
- */
-U_STABLE UCollator* U_EXPORT2
-ucol_safeClone(const UCollator *coll,
- void *stackBuffer,
- int32_t *pBufferSize,
- UErrorCode *status);
-
-/** default memory size for the new clone. It needs to be this large for os/400 large pointers
- * @stable ICU 2.0
- */
-#define U_COL_SAFECLONE_BUFFERSIZE 512
-
-/**
- * Returns current rules. Delta defines whether full rules are returned or just the tailoring.
- * Returns number of UChars needed to store rules. If buffer is NULL or bufferLen is not enough
- * to store rules, will store up to available space.
- * @param coll collator to get the rules from
- * @param delta one of UCOL_TAILORING_ONLY, UCOL_FULL_RULES.
- * @param buffer buffer to store the result in. If NULL, you'll get no rules.
- * @param bufferLen lenght of buffer to store rules in. If less then needed you'll get only the part that fits in.
- * @return current rules
- * @stable ICU 2.0
- */
-U_STABLE int32_t U_EXPORT2
-ucol_getRulesEx(const UCollator *coll, UColRuleOption delta, UChar *buffer, int32_t bufferLen);
-
-/**
- * gets the locale name of the collator. If the collator
- * is instantiated from the rules, then this function returns
- * NULL.
- * @param coll The UCollator for which the locale is needed
- * @param type You can choose between requested, valid and actual
- * locale. For description see the definition of
- * ULocDataLocaleType in uloc.h
- * @param status error code of the operation
- * @return real locale name from which the collation data comes.
- * If the collator was instantiated from rules, returns
- * NULL.
- * @deprecated ICU 2.8 Use ucol_getLocaleByType instead
- */
-U_DEPRECATED const char * U_EXPORT2
-ucol_getLocale(const UCollator *coll, ULocDataLocaleType type, UErrorCode *status);
-
-
-/**
- * gets the locale name of the collator. If the collator
- * is instantiated from the rules, then this function returns
- * NULL.
- * @param coll The UCollator for which the locale is needed
- * @param type You can choose between requested, valid and actual
- * locale. For description see the definition of
- * ULocDataLocaleType in uloc.h
- * @param status error code of the operation
- * @return real locale name from which the collation data comes.
- * If the collator was instantiated from rules, returns
- * NULL.
- * @stable ICU 2.8
- */
-U_STABLE const char * U_EXPORT2
-ucol_getLocaleByType(const UCollator *coll, ULocDataLocaleType type, UErrorCode *status);
-
-/**
- * Get an Unicode set that contains all the characters and sequences tailored in
- * this collator. The result must be disposed of by using uset_close.
- * @param coll The UCollator for which we want to get tailored chars
- * @param status error code of the operation
- * @return a pointer to newly created USet. Must be be disposed by using uset_close
- * @see ucol_openRules
- * @see uset_close
- * @stable ICU 2.4
- */
-U_STABLE USet * U_EXPORT2
-ucol_getTailoredSet(const UCollator *coll, UErrorCode *status);
-
-/**
- * Universal attribute getter that returns UCOL_DEFAULT if the value is default
- * @param coll collator which attributes are to be changed
- * @param attr attribute type
- * @return attribute value or UCOL_DEFAULT if the value is default
- * @param status to indicate whether the operation went on smoothly or there were errors
- * @see UColAttribute
- * @see UColAttributeValue
- * @see ucol_setAttribute
- * @internal ICU 3.0
- */
-U_INTERNAL UColAttributeValue U_EXPORT2
-ucol_getAttributeOrDefault(const UCollator *coll, UColAttribute attr, UErrorCode *status);
-
-/** Check whether two collators are equal. Collators are considered equal if they
- * will sort strings the same. This means that both the current attributes and the
- * rules must be equivalent. Currently used for RuleBasedCollator::operator==.
- * @param source first collator
- * @param target second collator
- * @return TRUE or FALSE
- * @internal ICU 3.0
- */
-U_INTERNAL UBool U_EXPORT2
-ucol_equals(const UCollator *source, const UCollator *target);
-
-/** Calculates the set of unsafe code points, given a collator.
- * A character is unsafe if you could append any character and cause the ordering to alter significantly.
- * Collation sorts in normalized order, so anything that rearranges in normalization can cause this.
- * Thus if you have a character like a_umlaut, and you add a lower_dot to it,
- * then it normalizes to a_lower_dot + umlaut, and sorts differently.
- * @param coll Collator
- * @param unsafe a fill-in set to receive the unsafe points
- * @param status for catching errors
- * @return number of elements in the set
- * @internal ICU 3.0
- */
-U_INTERNAL int32_t U_EXPORT2
-ucol_getUnsafeSet( const UCollator *coll,
- USet *unsafe,
- UErrorCode *status);
-
-/** Reset UCA's static pointers. You don't want to use this, unless your static memory can go away.
- * @internal ICU 3.2.1
- */
-U_INTERNAL void U_EXPORT2
-ucol_forgetUCA(void);
-
-/** Touches all resources needed for instantiating a collator from a short string definition,
- * thus filling up the cache.
- * @param definition A short string containing a locale and a set of attributes.
- * Attributes not explicitly mentioned are left at the default
- * state for a locale.
- * @param parseError if not NULL, structure that will get filled with error's pre
- * and post context in case of error.
- * @param forceDefaults if FALSE, the settings that are the same as the collator
- * default settings will not be applied (for example, setting
- * French secondary on a French collator would not be executed).
- * If TRUE, all the settings will be applied regardless of the
- * collator default value. If the definition
- * strings are to be cached, should be set to FALSE.
- * @param status Error code. Apart from regular error conditions connected to
- * instantiating collators (like out of memory or similar), this
- * API will return an error if an invalid attribute or attribute/value
- * combination is specified.
- * @see ucol_openFromShortString
- * @internal ICU 3.2.1
- */
-U_INTERNAL void U_EXPORT2
-ucol_prepareShortStringOpen( const char *definition,
- UBool forceDefaults,
- UParseError *parseError,
- UErrorCode *status);
-
-/** Creates a binary image of a collator. This binary image can be stored and
- * later used to instantiate a collator using ucol_openBinary.
- * This API supports preflighting.
- * @param coll Collator
- * @param buffer a fill-in buffer to receive the binary image
- * @param capacity capacity of the destination buffer
- * @param status for catching errors
- * @return size of the image
- * @see ucol_openBinary
- * @stable ICU 3.2
- */
-U_STABLE int32_t U_EXPORT2
-ucol_cloneBinary(const UCollator *coll,
- uint8_t *buffer, int32_t capacity,
- UErrorCode *status);
-
-/** Opens a collator from a collator binary image created using
- * ucol_cloneBinary. Binary image used in instantiation of the
- * collator remains owned by the user and should stay around for
- * the lifetime of the collator. The API also takes a base collator
- * which usualy should be UCA.
- * @param bin binary image owned by the user and required through the
- * lifetime of the collator
- * @param length size of the image. If negative, the API will try to
- * figure out the length of the image
- * @param base fallback collator, usually UCA. Base is required to be
- * present through the lifetime of the collator. Currently
- * it cannot be NULL.
- * @param status for catching errors
- * @return newly created collator
- * @see ucol_cloneBinary
- * @stable ICU 3.2
- */
-U_STABLE UCollator* U_EXPORT2
-ucol_openBinary(const uint8_t *bin, int32_t length,
- const UCollator *base,
- UErrorCode *status);
-
-
-#endif /* #if !UCONFIG_NO_COLLATION */
-
-#endif
-