+// © 2016 and later: Unicode, Inc. and others.
+// License & terms of use: http://www.unicode.org/copyright.html
/*
**********************************************************************
-* Copyright (C) 1999-2004, International Business Machines
+* Copyright (C) 1999-2014, International Business Machines
* Corporation and others. All Rights Reserved.
**********************************************************************
* ucnv.h:
/**
* \file
- * \brief C API: Character conversion
+ * \brief C API: Character conversion
*
* <h2>Character Conversion C API</h2>
*
* converter, you can get its properties, set options, convert your data and
* close the converter.</p>
*
- * <p>Since many software programs recogize different converter names for
+ * <p>Since many software programs recognize 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
*
* <p>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_getFromUCallBack() }
- * or {@link ucnv_getToUCallBack() } on the converter. The header ucnv_err.h defines
+ * 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.</p>
*
- * <p>More information about this API can be found in our
- * <a href="http://oss.software.ibm.com/icu/userguide/conversion.html">User's
+ * <p>More information about this API can be found in our
+ * <a href="http://icu-project.org/userguide/conversion.html">User's
* Guide</a>.</p>
*/
#include "unicode/ucnv_err.h"
#include "unicode/uenum.h"
+#include "unicode/localpointer.h"
-#ifndef __USET_H__
+#if !defined(USET_DEFINED) && !defined(U_IN_DOXYGEN)
+
+#define USET_DEFINED
/**
- * USet is the C API type for Unicode sets.
- * It is forward-declared here to avoid including the header file if related
+ * USet is the C API type corresponding to C++ class UnicodeSet.
+ * It is forward-declared here to avoid including unicode/uset.h file if related
* conversion APIs are not used.
- * See unicode/uset.h
*
* @see ucnv_getUnicodeSet
- * @stable ICU 2.6
+ * @stable ICU 2.4
*/
-struct USet;
-/** @stable ICU 2.6 */
typedef struct USet USet;
#endif
* @stable ICU 2.0
*/
typedef enum {
+ /** @stable ICU 2.0 */
UCNV_UNSUPPORTED_CONVERTER = -1,
+ /** @stable ICU 2.0 */
UCNV_SBCS = 0,
+ /** @stable ICU 2.0 */
UCNV_DBCS = 1,
+ /** @stable ICU 2.0 */
UCNV_MBCS = 2,
+ /** @stable ICU 2.0 */
UCNV_LATIN_1 = 3,
+ /** @stable ICU 2.0 */
UCNV_UTF8 = 4,
+ /** @stable ICU 2.0 */
UCNV_UTF16_BigEndian = 5,
+ /** @stable ICU 2.0 */
UCNV_UTF16_LittleEndian = 6,
+ /** @stable ICU 2.0 */
UCNV_UTF32_BigEndian = 7,
+ /** @stable ICU 2.0 */
UCNV_UTF32_LittleEndian = 8,
+ /** @stable ICU 2.0 */
UCNV_EBCDIC_STATEFUL = 9,
+ /** @stable ICU 2.0 */
UCNV_ISO_2022 = 10,
+ /** @stable ICU 2.0 */
UCNV_LMBCS_1 = 11,
- UCNV_LMBCS_2,
+ /** @stable ICU 2.0 */
+ UCNV_LMBCS_2,
+ /** @stable ICU 2.0 */
UCNV_LMBCS_3,
+ /** @stable ICU 2.0 */
UCNV_LMBCS_4,
+ /** @stable ICU 2.0 */
UCNV_LMBCS_5,
+ /** @stable ICU 2.0 */
UCNV_LMBCS_6,
+ /** @stable ICU 2.0 */
UCNV_LMBCS_8,
+ /** @stable ICU 2.0 */
UCNV_LMBCS_11,
+ /** @stable ICU 2.0 */
UCNV_LMBCS_16,
+ /** @stable ICU 2.0 */
UCNV_LMBCS_17,
+ /** @stable ICU 2.0 */
UCNV_LMBCS_18,
+ /** @stable ICU 2.0 */
UCNV_LMBCS_19,
+ /** @stable ICU 2.0 */
UCNV_LMBCS_LAST = UCNV_LMBCS_19,
+ /** @stable ICU 2.0 */
UCNV_HZ,
+ /** @stable ICU 2.0 */
UCNV_SCSU,
+ /** @stable ICU 2.0 */
UCNV_ISCII,
+ /** @stable ICU 2.0 */
UCNV_US_ASCII,
+ /** @stable ICU 2.0 */
UCNV_UTF7,
+ /** @stable ICU 2.2 */
UCNV_BOCU1,
+ /** @stable ICU 2.2 */
UCNV_UTF16,
+ /** @stable ICU 2.2 */
UCNV_UTF32,
+ /** @stable ICU 2.2 */
UCNV_CESU8,
+ /** @stable ICU 2.4 */
UCNV_IMAP_MAILBOX,
+ /** @stable ICU 4.8 */
+ UCNV_COMPOUND_TEXT,
/* Number of converter types for which we have conversion routines. */
UCNV_NUMBER_OF_SUPPORTED_CONVERTER_TYPES
-
} UConverterType;
/**
/**
* Function pointer for error callback in the codepage to unicode direction.
- * Called when an error has occured in conversion to unicode, or on open/close of the callback (see reason).
+ * Called when an error has occurred in conversion to unicode, or on open/close of the callback (see reason).
* @param context Pointer to the callback's private data
* @param args 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 pErrorCode ICU error code in/out parameter.
+ * For converter callback functions, set to a conversion error
+ * before the call, and the callback may reset it to U_ZERO_ERROR.
* @see ucnv_setToUCallBack
* @see UConverterToUnicodeArgs
* @stable ICU 2.0
const char *codeUnits,
int32_t length,
UConverterCallbackReason reason,
- UErrorCode *);
+ UErrorCode *pErrorCode);
/**
* Function pointer for error callback in the unicode to codepage direction.
- * Called when an error has occured in conversion from unicode, or on open/close of the callback (see reason).
+ * Called when an error has occurred in conversion from unicode, or on open/close of the callback (see reason).
* @param context Pointer to the callback's private data
* @param args 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 pErrorCode ICU error code in/out parameter.
+ * For converter callback functions, set to a conversion error
+ * before the call, and the callback may reset it to U_ZERO_ERROR.
* @see ucnv_setFromUCallBack
* @stable ICU 2.0
*/
int32_t length,
UChar32 codePoint,
UConverterCallbackReason reason,
- UErrorCode *);
+ UErrorCode *pErrorCode);
U_CDECL_END
#define UCNV_OPTION_SEP_CHAR ','
/**
- * String version of UCNV_OPTION_SEP_CHAR.
+ * String version of UCNV_OPTION_SEP_CHAR.
* @see ucnv_open
* @stable ICU 2.0
*/
#define UCNV_VALUE_SEP_CHAR '='
/**
- * String version of UCNV_VALUE_SEP_CHAR.
+ * String version of UCNV_VALUE_SEP_CHAR.
* @see ucnv_open
* @stable ICU 2.0
*/
/**
* Converter option for specifying a version selector (0..9) for some converters.
- * For example, ucnv_open("UTF-7,version=1", &errorCode);
+ * For example,
+ * \code
+ * ucnv_open("UTF-7,version=1", &errorCode);
+ * \endcode
* See convrtrs.txt.
*
* @see ucnv_open
#define UCNV_SWAP_LFNL_OPTION_STRING ",swaplfnl"
/**
- * Do a fuzzy compare of a two converter/alias names. The comparison
- * is case-insensitive. It also ignores the characters '-', '_', and
- * ' ' (dash, underscore, and space). Thus the strings "UTF-8",
- * "utf_8", and "Utf 8" are exactly equivalent.
- *
+ * Do a fuzzy compare of two converter/alias names.
+ * The comparison is case-insensitive, ignores leading zeroes if they are not
+ * followed by further digits, and ignores all but letters and digits.
+ * Thus the strings "UTF-8", "utf_8", "u*T@f08" and "Utf 8" are exactly equivalent.
+ * See section 1.4, Charset Alias Matching in Unicode Technical Standard #22
+ * at http://www.unicode.org/reports/tr22/
+ *
* @param name1 a converter name or alias, zero-terminated
* @param name2 a converter name or alias, zero-terminated
* @return 0 if the names match, or a negative value if the name1
/**
- * Creates a UConverter object with the names specified as a C string.
+ * Creates a UConverter object with the name of a coded character set specified as a C string.
* The actual name will be resolved with the alias file
* using a case-insensitive string comparison that ignores
- * the delimiters '-', '_', and ' ' (dash, underscore, and space).
- * E.g., the names "UTF8", "utf-8", and "Utf 8" are all equivalent.
+ * leading zeroes and all non-alphanumeric characters.
+ * E.g., the names "UTF8", "utf-8", "u*T@f08" and "Utf 8" are all equivalent.
+ * (See also ucnv_compareNames().)
* If <code>NULL</code> is passed for the converter name, it will create one with the
* getDefaultName return value.
*
*
* <p>The conversion behavior and names can vary between platforms. ICU may
* convert some characters differently from other platforms. Details on this topic
- * are in the <a href="http://oss.software.ibm.com/icu/userguide/conversion.html">User's
- * Guide</a>.</p>
- *
- * @param converterName Name of the uconv table, may have options appended
+ * are in the <a href="http://icu-project.org/userguide/conversion.html">User's
+ * Guide</a>. Aliases starting with a "cp" prefix have no specific meaning
+ * other than its an alias starting with the letters "cp". Please do not
+ * associate any meaning to these aliases.</p>
+ *
+ * \snippet samples/ucnv/convsamp.cpp ucnv_open
+ *
+ * @param converterName Name of the coded character set table.
+ * This may have options appended to the string.
+ * IANA alias character set names, IBM CCSIDs starting with "ibm-",
+ * Windows codepage numbers starting with "windows-" are frequently
+ * used for this parameter. See ucnv_getAvailableName and
+ * ucnv_getAlias for a complete list that is available.
+ * If this parameter is NULL, the default converter will be used.
* @param err outgoing error status <TT>U_MEMORY_ALLOCATION_ERROR, U_FILE_ACCESS_ERROR</TT>
- * @return the created Unicode converter object, or <TT>NULL</TT> if an error occured
+ * @return the created Unicode converter object, or <TT>NULL</TT> if an error occurred
* @see ucnv_openU
* @see ucnv_openCCSID
+ * @see ucnv_getAvailableName
+ * @see ucnv_getAlias
+ * @see ucnv_getDefaultName
* @see ucnv_close
+ * @see ucnv_compareNames
* @stable ICU 2.0
*/
-U_STABLE UConverter* U_EXPORT2
+U_STABLE UConverter* U_EXPORT2
ucnv_open(const char *converterName, UErrorCode *err);
/**
- * Creates a Unicode converter with the names specified as unicode string.
+ * Creates a Unicode converter with the names specified as unicode string.
* The name should be limited to the ASCII-7 alphanumerics range.
* The actual name will be resolved with the alias file
* using a case-insensitive string comparison that ignores
- * the delimiters '-', '_', and ' ' (dash, underscore, and space).
- * E.g., the names "UTF8", "utf-8", and "Utf 8" are all equivalent.
- * If <TT>NULL</TT> is passed for the converter name, it will create
+ * leading zeroes and all non-alphanumeric characters.
+ * E.g., the names "UTF8", "utf-8", "u*T@f08" and "Utf 8" are all equivalent.
+ * (See also ucnv_compareNames().)
+ * If <TT>NULL</TT> is passed for the converter name, it will create
* one with the ucnv_getDefaultName() return value.
* If the alias is ambiguous, then the preferred converter is used
* and the status is set to U_AMBIGUOUS_ALIAS_WARNING.
- * @param name : name of the uconv table in a zero terminated
+ *
+ * <p>See ucnv_open for the complete details</p>
+ * @param name Name of the UConverter table in a zero terminated
* Unicode string
- * @param err outgoing error status <TT>U_MEMORY_ALLOCATION_ERROR,
+ * @param err outgoing error status <TT>U_MEMORY_ALLOCATION_ERROR,
* U_FILE_ACCESS_ERROR</TT>
- * @return the created Unicode converter object, or <TT>NULL</TT> if an
- * error occured
+ * @return the created Unicode converter object, or <TT>NULL</TT> if an
+ * error occurred
* @see ucnv_open
* @see ucnv_openCCSID
* @see ucnv_close
- * @see ucnv_getDefaultName
+ * @see ucnv_compareNames
* @stable ICU 2.0
*/
-U_STABLE UConverter* U_EXPORT2
+U_STABLE UConverter* U_EXPORT2
ucnv_openU(const UChar *name,
UErrorCode *err);
* @param platform the platform in which the codepage number exists
* @param err error status <TT>U_MEMORY_ALLOCATION_ERROR, U_FILE_ACCESS_ERROR</TT>
* @return the created Unicode converter object, or <TT>NULL</TT> if an error
- * occured.
+ * occurred.
* @see ucnv_open
* @see ucnv_openU
* @see ucnv_close
/**
* <p>Creates a UConverter object specified from a packageName and a converterName.</p>
- *
+ *
* <p>The packageName and converterName must point to an ICU udata object, as defined by
* <code> udata_open( packageName, "cnv", converterName, err) </code> or equivalent.
* Typically, packageName will refer to a (.dat) file, or to a package registered with
- * udata_setAppData().</p>
- *
+ * udata_setAppData(). Using a full file or directory pathname for packageName is deprecated.</p>
+ *
* <p>The name will NOT be looked up in the alias mechanism, nor will the converter be
* stored in the converter cache or the alias table. The only way to open further converters
- * is call this function multiple times, or use the ucnv_safeClone() function to clone a
+ * is call this function multiple times, or use the ucnv_safeClone() function to clone a
* 'master' converter.</p>
*
* <p>A future version of ICU may add alias table lookups and/or caching
* to this function.</p>
- *
+ *
* <p>Example Use:
* <code>cnv = ucnv_openPackage("myapp", "myconverter", &err);</code>
* </p>
* @param packageName name of the package (equivalent to 'path' in udata_open() call)
* @param converterName name of the data item to be used, without suffix.
* @param err outgoing error status <TT>U_MEMORY_ALLOCATION_ERROR, U_FILE_ACCESS_ERROR</TT>
- * @return the created Unicode converter object, or <TT>NULL</TT> if an error occured
+ * @return the created Unicode converter object, or <TT>NULL</TT> if an error occurred
* @see udata_open
* @see ucnv_open
* @see ucnv_safeClone
* @see ucnv_close
* @stable ICU 2.2
*/
-U_STABLE UConverter* U_EXPORT2
+U_STABLE UConverter* U_EXPORT2
ucnv_openPackage(const char *packageName, const char *converterName, UErrorCode *err);
/**
- * Thread safe cloning operation
+ * Thread safe converter cloning operation.
+ * For most efficient operation, pass in a stackBuffer (and a *pBufferSize)
+ * with at least U_CNV_SAFECLONE_BUFFERSIZE bytes of space.
+ * If the buffer size is sufficient, then the clone will use the stack buffer;
+ * otherwise, it will be allocated, and *pBufferSize will indicate
+ * the actual size. (This should not occur with U_CNV_SAFECLONE_BUFFERSIZE.)
+ *
+ * You must ucnv_close() the clone in any case.
+ *
+ * If *pBufferSize==0, (regardless of whether stackBuffer==NULL or not)
+ * then *pBufferSize will be changed to a sufficient size
+ * for cloning this converter,
+ * without actually cloning the converter ("pure pre-flighting").
+ *
+ * If *pBufferSize is greater than zero but not large enough for a stack-based
+ * clone, then the converter is cloned using newly allocated memory
+ * and *pBufferSize is changed to the necessary size.
+ *
+ * If the converter clone fits into the stack buffer but the stack buffer is not
+ * sufficiently aligned for the clone, then the clone will use an
+ * adjusted pointer and use an accordingly smaller buffer size.
+ *
* @param cnv converter to be cloned
- * @param stackBuffer user allocated space for the new clone. If NULL new memory will be allocated.
+ * @param stackBuffer <em>Deprecated functionality as of ICU 52, use NULL.</em><br>
+ * 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_CNV_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 pBufferSize <em>Deprecated functionality as of ICU 52, use NULL or 1.</em><br>
+ * pointer to size of allocated space.
* @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.
+ * An informational status value, U_SAFECLONE_ALLOCATED_WARNING,
+ * is used if any allocations were necessary.
+ * However, it is better to check if *pBufferSize grew for checking for
+ * allocations because warning codes can be overridden by subsequent
+ * function calls.
* @return pointer to the new clone
* @stable ICU 2.0
*/
-U_STABLE UConverter * U_EXPORT2
-ucnv_safeClone(const UConverter *cnv,
+U_STABLE UConverter * U_EXPORT2
+ucnv_safeClone(const UConverter *cnv,
void *stackBuffer,
- int32_t *pBufferSize,
+ int32_t *pBufferSize,
UErrorCode *status);
+#ifndef U_HIDE_DEPRECATED_API
+
/**
* \def U_CNV_SAFECLONE_BUFFERSIZE
* Definition of a buffer size that is designed to be large enough for
* converters to be cloned with ucnv_safeClone().
- * @stable ICU 2.0
+ * @deprecated ICU 52. Do not rely on ucnv_safeClone() cloning into any provided buffer.
*/
#define U_CNV_SAFECLONE_BUFFERSIZE 1024
+#endif /* U_HIDE_DEPRECATED_API */
+
/**
* Deletes the unicode converter and releases resources associated
* with just this instance.
U_STABLE void U_EXPORT2
ucnv_close(UConverter * converter);
+#if U_SHOW_CPLUSPLUS_API
+
+U_NAMESPACE_BEGIN
+
+/**
+ * \class LocalUConverterPointer
+ * "Smart pointer" class, closes a UConverter via ucnv_close().
+ * For most methods see the LocalPointerBase base class.
+ *
+ * @see LocalPointerBase
+ * @see LocalPointer
+ * @stable ICU 4.4
+ */
+U_DEFINE_LOCAL_OPEN_POINTER(LocalUConverterPointer, UConverter, ucnv_close);
+
+U_NAMESPACE_END
+
+#endif
+
/**
* Fills in the output parameter, subChars, with the substitution characters
* as multiple bytes.
+ * If ucnv_setSubstString() set a Unicode string because the converter is
+ * stateful, then subChars will be an empty string.
*
* @param converter the Unicode converter
- * @param subChars the subsitution characters
- * @param len on input the capacity of subChars, on output the number
+ * @param subChars the substitution characters
+ * @param len on input the capacity of subChars, on output the number
* of bytes copied to it
* @param err the outgoing error status code.
* If the substitution character array is too small, an
* <TT>U_INDEX_OUTOFBOUNDS_ERROR</TT> will be returned.
+ * @see ucnv_setSubstString
* @see ucnv_setSubstChars
* @stable ICU 2.0
*/
/**
* Sets the substitution chars when converting from unicode to a codepage. The
* substitution is specified as a string of 1-4 bytes, and may contain
- * <TT>NULL</TT> byte.
+ * <TT>NULL</TT> bytes.
+ * The subChars must represent a single character. The caller needs to know the
+ * byte sequence of a valid character in the converter's charset.
+ * For some converters, for example some ISO 2022 variants, only single-byte
+ * substitution characters may be supported.
+ * The newer ucnv_setSubstString() function relaxes these limitations.
+ *
* @param converter the Unicode converter
* @param subChars the substitution character byte sequence we want set
* @param len the number of bytes in subChars
* @param err the error status code. <TT>U_INDEX_OUTOFBOUNDS_ERROR </TT> if
* len is bigger than the maximum number of bytes allowed in subchars
+ * @see ucnv_setSubstString
* @see ucnv_getSubstChars
* @stable ICU 2.0
*/
int8_t len,
UErrorCode *err);
+/**
+ * Set a substitution string for converting from Unicode to a charset.
+ * The caller need not know the charset byte sequence for each charset.
+ *
+ * Unlike ucnv_setSubstChars() which is designed to set a charset byte sequence
+ * for a single character, this function takes a Unicode string with
+ * zero, one or more characters, and immediately verifies that the string can be
+ * converted to the charset.
+ * If not, or if the result is too long (more than 32 bytes as of ICU 3.6),
+ * then the function returns with an error accordingly.
+ *
+ * Also unlike ucnv_setSubstChars(), this function works for stateful charsets
+ * by converting on the fly at the point of substitution rather than setting
+ * a fixed byte sequence.
+ *
+ * @param cnv The UConverter object.
+ * @param s The Unicode string.
+ * @param length The number of UChars in s, or -1 for a NUL-terminated string.
+ * @param err Pointer to a standard ICU error code. Its input value must
+ * pass the U_SUCCESS() test, or else the function returns
+ * immediately. Check for U_FAILURE() on output or use with
+ * function chaining. (See User Guide for details.)
+ *
+ * @see ucnv_setSubstChars
+ * @see ucnv_getSubstChars
+ * @stable ICU 3.6
+ */
+U_STABLE void U_EXPORT2
+ucnv_setSubstString(UConverter *cnv,
+ const UChar *s,
+ int32_t length,
+ UErrorCode *err);
+
/**
* Fills in the output parameter, errBytes, with the error characters from the
* last failing conversion.
*
* @param converter the Unicode converter
* @param errUChars the UChars which were in error
- * @param len on input the capacity of errUChars, on output the number of
+ * @param len on input the capacity of errUChars, on output the number of
* UChars which were copied to it
* @param err the error status code.
* If the substitution character array is too small, an
* @param converter the Unicode converter
* @stable ICU 2.0
*/
-U_STABLE void U_EXPORT2
+U_STABLE void U_EXPORT2
ucnv_resetToUnicode(UConverter *converter);
/**
* @param converter the Unicode converter
* @stable ICU 2.0
*/
-U_STABLE void U_EXPORT2
+U_STABLE void U_EXPORT2
ucnv_resetFromUnicode(UConverter *converter);
/**
* - ISO-2022-CN: 8 (4-byte designator sequences + 2-byte SS2/SS3 + DBCS)
*
* @param converter The Unicode converter.
- * @return The maximum number of bytes per UChar that are output by ucnv_fromUnicode(),
- * to be used together with UCNV_GET_MAX_BYTES_FOR_STRING for buffer allocation.
+ * @return The maximum number of bytes per UChar (16 bit code unit)
+ * that are output by ucnv_fromUnicode(),
+ * to be used together with UCNV_GET_MAX_BYTES_FOR_STRING
+ * for buffer allocation.
*
* @see UCNV_GET_MAX_BYTES_FOR_STRING
* @see ucnv_getMinCharSize
U_STABLE int8_t U_EXPORT2
ucnv_getMaxCharSize(const UConverter *converter);
-#ifndef U_HIDE_DRAFT_API
-
/**
* Calculates the size of a buffer for conversion from Unicode to a charset.
* The calculated size is guaranteed to be sufficient for this conversion.
* converting length UChars with the converter that returned the maxCharSize.
*
* @see ucnv_getMaxCharSize
- * @draft ICU 2.8
+ * @stable ICU 2.8
*/
#define UCNV_GET_MAX_BYTES_FOR_STRING(length, maxCharSize) \
(((int32_t)(length)+10)*(int32_t)(maxCharSize))
-#endif /*U_HIDE_DRAFT_API*/
-
/**
- * Returns the minimum byte length for characters in this codepage.
+ * Returns the minimum byte length (per codepoint) for characters in this codepage.
* This is usually either 1 or 2.
* @param converter the Unicode converter
- * @return the minimum number of bytes allowed by this particular converter
+ * @return the minimum number of bytes per codepoint allowed by this particular converter
* @see ucnv_getMaxCharSize
* @stable ICU 2.0
*/
ucnv_getMinCharSize(const UConverter *converter);
/**
- * Returns the display name of the converter passed in based on the Locale
+ * Returns the display name of the converter passed in based on the Locale
* passed in. If the locale contains no display name, the internal ASCII
* name will be filled in.
*
* @param converter the Unicode converter.
- * @param displayLocale is the specific Locale we want to localised for
+ * @param displayLocale is the specific Locale we want to localized for
* @param displayName user provided buffer to be filled in
* @param displayNameCapacity size of displayName Buffer
* @param err error status code
/**
* Gets the internal, canonical name of the converter (zero-terminated).
- * The lifetime of the returned string will be that of the converter
+ * The lifetime of the returned string will be that of the converter
* passed to this function.
* @param converter the Unicode converter
* @param err UErrorCode status
* @see ucnv_getDisplayName
* @stable ICU 2.0
*/
-U_STABLE const char * U_EXPORT2
+U_STABLE const char * U_EXPORT2
ucnv_getName(const UConverter *converter, UErrorCode *err);
/**
*
* @param converter the Unicode converter
* @param err the error status code.
- * @return If any error occurrs, -1 will be returned otherwise, the codepage number
+ * @return If any error occurs, -1 will be returned otherwise, the codepage number
* will be returned
* @see ucnv_openCCSID
* @see ucnv_getPlatform
UErrorCode *err);
/**
- * Gets a codepage platform associated with the converter. Currently,
+ * Gets a codepage platform associated with the converter. Currently,
* only <TT>UCNV_IBM</TT> will be returned.
- * Does not test if the converter is <TT>NULL</TT> or if converter's data
- * table is <TT>NULL</TT>.
+ * Does not test if the converter is <TT>NULL</TT> or if converter's data
+ * table is <TT>NULL</TT>.
* @param converter the Unicode converter
* @param err the error status code.
* @return The codepage platform
/**
* Gets the type of the converter
- * e.g. SBCS, MBCS, DBCS, UTF8, UTF16_BE, UTF16_LE, ISO_2022,
+ * e.g. SBCS, MBCS, DBCS, UTF8, UTF16_BE, UTF16_LE, ISO_2022,
* EBCDIC_STATEFUL, LATIN_1
* @param converter a valid, opened converter
* @return the type of the converter
/**
* Gets the "starter" (lead) bytes for converters of type MBCS.
* Will fill in an <TT>U_ILLEGAL_ARGUMENT_ERROR</TT> if converter passed in
- * is not MBCS. Fills in an array of type UBool, with the value of the byte
+ * is not MBCS. Fills in an array of type UBool, with the value of the byte
* as offset to the array. For example, if (starters[0x20] == TRUE) at return,
* it means that the byte 0x20 is a starter byte in this converter.
* Context pointers are always owned by the caller.
- *
+ *
* @param converter a valid, opened converter of type MBCS
* @param starters an array of size 256 to be filled in
- * @param err error status, <TT>U_ILLEGAL_ARGUMENT_ERROR</TT> if the
+ * @param err error status, <TT>U_ILLEGAL_ARGUMENT_ERROR</TT> if the
* converter is not a type which can return starters.
* @see ucnv_getType
* @stable ICU 2.0
*/
U_STABLE void U_EXPORT2
-ucnv_getStarters(const UConverter* converter,
+ucnv_getStarters(const UConverter* converter,
UBool starters[256],
UErrorCode* err);
typedef enum UConverterUnicodeSet {
/** Select the set of roundtrippable Unicode code points. @stable ICU 2.6 */
UCNV_ROUNDTRIP_SET,
- /** Number of UConverterUnicodeSet selectors. @stable ICU 2.6 */
+ /** Select the set of Unicode code points with roundtrip or fallback mappings. @stable ICU 4.0 */
+ UCNV_ROUNDTRIP_AND_FALLBACK_SET,
+#ifndef U_HIDE_DEPRECATED_API
+ /**
+ * Number of UConverterUnicodeSet selectors.
+ * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420.
+ */
UCNV_SET_COUNT
+#endif // U_HIDE_DEPRECATED_API
} UConverterUnicodeSet;
/**
* Returns the set of Unicode code points that can be converted by an ICU converter.
*
- * The current implementation returns only one kind of set (UCNV_ROUNDTRIP_SET):
+ * Returns one of several kinds of set:
+ *
+ * 1. UCNV_ROUNDTRIP_SET
+ *
* The set of all Unicode code points that can be roundtrip-converted
- * (converted without any data loss) with the converter.
+ * (converted without any data loss) with the converter (ucnv_fromUnicode()).
* This set will not include code points that have fallback mappings
* or are only the result of reverse fallback mappings.
+ * This set will also not include PUA code points with fallbacks, although
+ * ucnv_fromUnicode() will always uses those mappings despite ucnv_setFallback().
* See UTR #22 "Character Mapping Markup Language"
* at http://www.unicode.org/reports/tr22/
*
* by comparing its roundtrip set with the set of ExemplarCharacters from
* ICU's locale data or other sources
*
+ * 2. UCNV_ROUNDTRIP_AND_FALLBACK_SET
+ *
+ * The set of all Unicode code points that can be converted with the converter (ucnv_fromUnicode())
+ * when fallbacks are turned on (see ucnv_setFallback()).
+ * This set includes all code points with roundtrips and fallbacks (but not reverse fallbacks).
+ *
* In the future, there may be more UConverterUnicodeSet choices to select
* sets with different properties.
*
/**
* Gets the current calback function used by the converter when an illegal
- * or invalid codepage sequence is found.
+ * or invalid codepage sequence is found.
* Context pointers are always owned by the caller.
*
* @param converter the unicode converter
const void **context);
/**
- * Gets the current callback function used by the converter when illegal
+ * Gets the current callback function used by the converter when illegal
* or invalid Unicode sequence is found.
* Context pointers are always owned by the caller.
*
* characters. This function is optimized for converting a continuous
* stream of data in buffer-sized chunks, where the entire source and
* target does not fit in available buffers.
- *
- * The source pointer is an in/out parameter. It starts out pointing where the
- * conversion is to begin, and ends up pointing after the last UChar consumed.
- *
+ *
+ * The source pointer is an in/out parameter. It starts out pointing where the
+ * conversion is to begin, and ends up pointing after the last UChar consumed.
+ *
* Target similarly starts out pointer at the first available byte in the output
* buffer, and ends up pointing after the last byte written to the output.
- *
- * The converter always attempts to consume the entire source buffer, unless
+ *
+ * The converter always attempts to consume the entire source buffer, unless
* (1.) the target buffer is full, or (2.) a failing error is returned from the
* current callback function. When a successful error status has been
* returned, it means that all of the source buffer has been
* consumed. At that point, the caller should reset the source and
* sourceLimit pointers to point to the next chunk.
- *
+ *
* At the end of the stream (flush==TRUE), the input is completely consumed
* when *source==sourceLimit and no error code is set.
* The converter object is then automatically reset by this function.
* (This means that a converter need not be reset explicitly between data
* streams if it finishes the previous stream without errors.)
- *
+ *
* This is a <I>stateful</I> conversion. Additionally, even when all source data has
* been consumed, some data may be in the converters' internal state.
* Call this function repeatedly, updating the target pointers with
* codepage characters to. Output : points to after the last codepage character copied
* to <TT>target</TT>.
* @param targetLimit the pointer just after last of the <TT>target</TT> buffer
- * @param source I/O parameter, pointer to pointer to the source Unicode character buffer.
+ * @param source I/O parameter, pointer to pointer to the source Unicode character buffer.
* @param sourceLimit the pointer just after the last of the source buffer
* @param offsets if NULL is passed, nothing will happen to it, otherwise it needs to have the same number
* of allocated cells as <TT>target</TT>. Will fill in offsets from target to source pointer
* e.g: <TT>offsets[3]</TT> is equal to 6, it means that the <TT>target[3]</TT> was a result of transcoding <TT>source[6]</TT>
* For output data carried across calls, and other data without a specific source character
- * (such as from escape sequences or callbacks) -1 will be placed for offsets.
+ * (such as from escape sequences or callbacks) -1 will be placed for offsets.
* @param flush set to <TT>TRUE</TT> if the current source buffer is the last available
* chunk of the source, <TT>FALSE</TT> otherwise. Note that if a failing status is returned,
* this function may have to be called multiple times with flush set to <TT>TRUE</TT> until
* the source buffer is consumed.
* @param err the error status. <TT>U_ILLEGAL_ARGUMENT_ERROR</TT> will be set if the
* converter is <TT>NULL</TT>.
- * <code>U_BUFFER_OVERFLOW_ERROR</code> will be set if the target is full and there is
+ * <code>U_BUFFER_OVERFLOW_ERROR</code> will be set if the target is full and there is
* still data to be written to the target.
* @see ucnv_fromUChars
* @see ucnv_convert
* @see ucnv_setToUCallBack
* @stable ICU 2.0
*/
-U_STABLE void U_EXPORT2
+U_STABLE void U_EXPORT2
ucnv_fromUnicode (UConverter * converter,
char **target,
const char *targetLimit,
* characters. This function is optimized for converting a continuous
* stream of data in buffer-sized chunks, where the entire source and
* target does not fit in available buffers.
- *
- * The source pointer is an in/out parameter. It starts out pointing where the
- * conversion is to begin, and ends up pointing after the last byte of source consumed.
- *
+ *
+ * The source pointer is an in/out parameter. It starts out pointing where the
+ * conversion is to begin, and ends up pointing after the last byte of source consumed.
+ *
* Target similarly starts out pointer at the first available UChar in the output
- * buffer, and ends up pointing after the last UChar written to the output.
+ * buffer, and ends up pointing after the last UChar written to the output.
* It does NOT necessarily keep UChar sequences together.
- *
- * The converter always attempts to consume the entire source buffer, unless
+ *
+ * The converter always attempts to consume the entire source buffer, unless
* (1.) the target buffer is full, or (2.) a failing error is returned from the
* current callback function. When a successful error status has been
* returned, it means that all of the source buffer has been
* The converter object is then automatically reset by this function.
* (This means that a converter need not be reset explicitly between data
* streams if it finishes the previous stream without errors.)
- *
+ *
* This is a <I>stateful</I> conversion. Additionally, even when all source data has
* been consumed, some data may be in the converters' internal state.
* Call this function repeatedly, updating the target pointers with
* @param target I/O parameter. Input : Points to the beginning of the buffer to copy
* UChars into. Output : points to after the last UChar copied.
* @param targetLimit the pointer just after the end of the <TT>target</TT> buffer
- * @param source I/O parameter, pointer to pointer to the source codepage buffer.
+ * @param source I/O parameter, pointer to pointer to the source codepage buffer.
* @param sourceLimit the pointer to the byte after the end of the source buffer
* @param offsets if NULL is passed, nothing will happen to it, otherwise it needs to have the same number
* of allocated cells as <TT>target</TT>. Will fill in offsets from target to source pointer
* e.g: <TT>offsets[3]</TT> is equal to 6, it means that the <TT>target[3]</TT> was a result of transcoding <TT>source[6]</TT>
* For output data carried across calls, and other data without a specific source character
- * (such as from escape sequences or callbacks) -1 will be placed for offsets.
+ * (such as from escape sequences or callbacks) -1 will be placed for offsets.
* @param flush set to <TT>TRUE</TT> if the current source buffer is the last available
* chunk of the source, <TT>FALSE</TT> otherwise. Note that if a failing status is returned,
* this function may have to be called multiple times with flush set to <TT>TRUE</TT> until
* the source buffer is consumed.
* @param err the error status. <TT>U_ILLEGAL_ARGUMENT_ERROR</TT> will be set if the
* converter is <TT>NULL</TT>.
- * <code>U_BUFFER_OVERFLOW_ERROR</code> will be set if the target is full and there is
- * still data to be written to the target.
+ * <code>U_BUFFER_OVERFLOW_ERROR</code> will be set if the target is full and there is
+ * still data to be written to the target.
* @see ucnv_fromUChars
* @see ucnv_convert
* @see ucnv_getMinCharSize
* @see ucnv_getNextUChar
* @stable ICU 2.0
*/
-U_STABLE void U_EXPORT2
+U_STABLE void U_EXPORT2
ucnv_toUnicode(UConverter *converter,
UChar **target,
const UChar *targetLimit,
* updated to point after the bytes consumed in the conversion call.
* @param sourceLimit points to the end of the input buffer
* @param err fills in error status (see ucnv_toUnicode)
- * <code>U_INDEX_OUTOFBOUNDS_ERROR</code> will be set if the input
- * is empty or does not convert to any output (e.g.: pure state-change
+ * <code>U_INDEX_OUTOFBOUNDS_ERROR</code> will be set if the input
+ * is empty or does not convert to any output (e.g.: pure state-change
* codes SI/SO, escape sequences for ISO 2022,
* or if the callback did not output anything, ...).
* This function will not set a <code>U_BUFFER_OVERFLOW_ERROR</code> because
* Internally, two conversions - ucnv_toUnicode() and ucnv_fromUnicode() -
* are used, "pivoting" through 16-bit Unicode.
*
+ * Important: For streaming conversion (multiple function calls for successive
+ * parts of a text stream), the caller must provide a pivot buffer explicitly,
+ * and must preserve the pivot buffer and associated pointers from one
+ * call to another. (The buffer may be moved if its contents and the relative
+ * pointer positions are preserved.)
+ *
* There is a similar function, ucnv_convert(),
* which has the following limitations:
* - it takes charset names, not converter objects, so that
*
* By contrast, ucnv_convertEx()
* - takes UConverter parameters instead of charset names
- * - fully exposes the pivot buffer for complete error handling
+ * - fully exposes the pivot buffer for streaming conversion and complete error handling
*
* ucnv_convertEx() also provides further convenience:
* - an option to reset the converters at the beginning
* or set U_STRING_NOT_TERMINATED_WARNING if the output exactly fills
* the target buffer
* - the pivot buffer can be provided internally;
+ * possible only for whole-string conversion, not streaming conversion;
* in this case, the caller will not be able to get details about where an
* error occurred
* (if pivotStart==NULL, see below)
* return 0;
* }
*
+ * if(length<0) {
+ * length=strlen(s);
+ * }
* target=u8;
- * ucnv_convertEx(cnv, utf8Cnv,
+ * ucnv_convertEx(utf8Cnv, cnv,
* &target, u8+capacity,
- * &s, length>=0 ? s+length : NULL,
+ * &s, s+length,
* NULL, NULL, NULL, NULL,
* TRUE, TRUE,
* pErrorCode);
- *
+ *
* myReleaseCachedUTF8Converter(utf8Cnv);
*
* // return the output string length, but without preflighting
* @return number of names on alias list for given alias
* @stable ICU 2.0
*/
-U_STABLE uint16_t U_EXPORT2
+U_STABLE uint16_t U_EXPORT2
ucnv_countAliases(const char *alias, UErrorCode *pErrorCode);
/**
* @see ucnv_countAliases
* @stable ICU 2.0
*/
-U_STABLE const char * U_EXPORT2
+U_STABLE const char * U_EXPORT2
ucnv_getAlias(const char *alias, uint16_t n, UErrorCode *pErrorCode);
/**
* @param pErrorCode result of operation
* @stable ICU 2.0
*/
-U_STABLE void U_EXPORT2
+U_STABLE void U_EXPORT2
ucnv_getAliases(const char *alias, const char **aliases, UErrorCode *pErrorCode);
/**
ucnv_getCanonicalName(const char *alias, const char *standard, UErrorCode *pErrorCode);
/**
- * returns the current default converter name.
+ * Returns the current default converter name. If you want to open
+ * a default converter, you do not need to use this function.
+ * It is faster if you pass a NULL argument to ucnv_open the
+ * default converter.
+ *
+ * If U_CHARSET_IS_UTF8 is defined to 1 in utypes.h then this function
+ * always returns "UTF-8".
*
- * @return returns the current default converter name;
- * if a default converter name cannot be determined,
- * then <code>NULL</code> is returned.
+ * @return returns the current default converter name.
* Storage owned by the library
* @see ucnv_setDefaultName
* @stable ICU 2.0
U_STABLE const char * U_EXPORT2
ucnv_getDefaultName(void);
+#ifndef U_HIDE_SYSTEM_API
/**
- * sets the current default converter name. Caller must own the storage for 'name'
- * and preserve it indefinitely.
- * @param name the converter name to be the default (must exist).
+ * This function is not thread safe. DO NOT call this function when ANY ICU
+ * function is being used from more than one thread! This function sets the
+ * current default converter name. If this function needs to be called, it
+ * should be called during application initialization. Most of the time, the
+ * results from ucnv_getDefaultName() or ucnv_open with a NULL string argument
+ * is sufficient for your application.
+ *
+ * If U_CHARSET_IS_UTF8 is defined to 1 in utypes.h then this function
+ * does nothing.
+ *
+ * @param name the converter name to be the default (must be known by ICU).
* @see ucnv_getDefaultName
- * @system SYSTEM API
+ * @system
* @stable ICU 2.0
*/
U_STABLE void U_EXPORT2
ucnv_setDefaultName(const char *name);
+#endif /* U_HIDE_SYSTEM_API */
/**
- * Fixes the backslash character mismapping. For example, in SJIS, the backslash
- * character in the ASCII portion is also used to represent the yen currency sign.
- * When mapping from Unicode character 0x005C, it's unclear whether to map the
+ * Fixes the backslash character mismapping. For example, in SJIS, the backslash
+ * character in the ASCII portion is also used to represent the yen currency sign.
+ * When mapping from Unicode character 0x005C, it's unclear whether to map the
* character back to yen or backslash in SJIS. This function will take the input
* buffer and replace all the yen sign characters with backslash. This is necessary
* when the user tries to open a file with the input buffer on Windows.
* Determines if the converter contains ambiguous mappings of the same
* character or not.
* @param cnv the converter to be tested
- * @return TRUE if the converter contains ambiguous mapping of the same
+ * @return TRUE if the converter contains ambiguous mapping of the same
* character, FALSE otherwise.
* @stable ICU 2.0
*/
ucnv_isAmbiguous(const UConverter *cnv);
/**
- * Sets the converter to use fallback mapping or not.
+ * Sets the converter to use fallback mappings or not.
+ * Regardless of this flag, the converter will always use
+ * fallbacks from Unicode Private Use code points, as well as
+ * reverse fallbacks (to Unicode).
+ * For details see ".ucm File Format"
+ * in the Conversion Data chapter of the ICU User Guide:
+ * http://www.icu-project.org/userguide/conversion-data.html#ucmformat
+ *
* @param cnv The converter to set the fallback mapping usage on.
- * @param usesFallback TRUE if the user wants the converter to take advantage of the fallback
+ * @param usesFallback TRUE if the user wants the converter to take advantage of the fallback
* mapping, FALSE otherwise.
* @stable ICU 2.0
+ * @see ucnv_usesFallback
*/
-U_STABLE void U_EXPORT2
+U_STABLE void U_EXPORT2
ucnv_setFallback(UConverter *cnv, UBool usesFallback);
/**
* Determines if the converter uses fallback mappings or not.
+ * This flag has restrictions, see ucnv_setFallback().
+ *
* @param cnv The converter to be tested
* @return TRUE if the converter uses fallback, FALSE otherwise.
* @stable ICU 2.0
+ * @see ucnv_setFallback
*/
-U_STABLE UBool U_EXPORT2
+U_STABLE UBool U_EXPORT2
ucnv_usesFallback(const UConverter *cnv);
/**
* instead of the input signature bytes.
* <p>
* Usage:
- * @code
- * UErrorCode err = U_ZERO_ERROR;
- * char input[] = { '\xEF','\xBB', '\xBF','\x41','\x42','\x43' };
- * int32_t signatureLength = 0;
- * char *encoding = ucnv_detectUnicodeSignatures(input,sizeof(input),&signatureLength,&err);
- * UConverter *conv = NULL;
- * UChar output[100];
- * UChar *target = output, *out;
- * char *source = input;
- * if(encoding!=NULL && U_SUCCESS(err)){
- * // should signature be discarded ?
- * conv = ucnv_open(encoding, &err);
- * // do the conversion
- * ucnv_toUnicode(conv,
- * target, output + sizeof(output)/U_SIZEOF_UCHAR,
- * source, input + sizeof(input),
- * NULL, TRUE, &err);
- * out = output;
- * if (discardSignature){
- * ++out; // ignore initial U+FEFF
- * }
- * while(out != target) {
- * printf("%04x ", *out++);
- * }
- * puts("");
- * }
- *
- * @endcode
+ * \snippet samples/ucnv/convsamp.cpp ucnv_detectUnicodeSignature
*
* @param source The source string in which the signature should be detected.
* @param sourceLength Length of the input string, or -1 if terminated with a NUL byte.
- * @param signatureLength A pointer to int32_t to receive the number of bytes that make up the signature
+ * @param signatureLength A pointer to int32_t to receive the number of bytes that make up the signature
* of the detected UTF. 0 if not detected.
* Can be a NULL pointer.
- * @param pErrorCode A pointer to receive information about any errors that may occur during detection.
- * Must be a valid pointer to an error code value, which must not indicate a failure
- * before the function call.
- * @return The name of the encoding detected. NULL if encoding is not detected.
+ * @param pErrorCode ICU error code in/out parameter.
+ * Must fulfill U_SUCCESS before the function call.
+ * @return The name of the encoding detected. NULL if encoding is not detected.
* @stable ICU 2.4
*/
U_STABLE const char* U_EXPORT2
int32_t *signatureLength,
UErrorCode *pErrorCode);
+/**
+ * Returns the number of UChars held in the converter's internal state
+ * because more input is needed for completing the conversion. This function is
+ * useful for mapping semantics of ICU's converter interface to those of iconv,
+ * and this information is not needed for normal conversion.
+ * @param cnv The converter in which the input is held
+ * @param status ICU error code in/out parameter.
+ * Must fulfill U_SUCCESS before the function call.
+ * @return The number of UChars in the state. -1 if an error is encountered.
+ * @stable ICU 3.4
+ */
+U_STABLE int32_t U_EXPORT2
+ucnv_fromUCountPending(const UConverter* cnv, UErrorCode* status);
+
+/**
+ * Returns the number of chars held in the converter's internal state
+ * because more input is needed for completing the conversion. This function is
+ * useful for mapping semantics of ICU's converter interface to those of iconv,
+ * and this information is not needed for normal conversion.
+ * @param cnv The converter in which the input is held as internal state
+ * @param status ICU error code in/out parameter.
+ * Must fulfill U_SUCCESS before the function call.
+ * @return The number of chars in the state. -1 if an error is encountered.
+ * @stable ICU 3.4
+ */
+U_STABLE int32_t U_EXPORT2
+ucnv_toUCountPending(const UConverter* cnv, UErrorCode* status);
+
+/**
+ * Returns whether or not the charset of the converter has a fixed number of bytes
+ * per charset character.
+ * An example of this are converters that are of the type UCNV_SBCS or UCNV_DBCS.
+ * Another example is UTF-32 which is always 4 bytes per character.
+ * A Unicode code point may be represented by more than one UTF-8 or UTF-16 code unit
+ * but a UTF-32 converter encodes each code point with 4 bytes.
+ * Note: This method is not intended to be used to determine whether the charset has a
+ * fixed ratio of bytes to Unicode codes <i>units</i> for any particular Unicode encoding form.
+ * FALSE is returned with the UErrorCode if error occurs or cnv is NULL.
+ * @param cnv The converter to be tested
+ * @param status ICU error code in/out paramter
+ * @return TRUE if the converter is fixed-width
+ * @stable ICU 4.8
+ */
+U_STABLE UBool U_EXPORT2
+ucnv_isFixedWidth(UConverter *cnv, UErrorCode *status);
+
#endif
#endif
projects / apple / icu.git / blobdiff