More information about this API can be found in our + *
More information about this API can be found in our * User's * Guide.
*/ @@ -88,46 +90,82 @@ U_CDECL_BEGIN * @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; /** @@ -201,7 +239,7 @@ 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 */ @@ -215,7 +253,7 @@ U_CDECL_END #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 */ @@ -233,7 +271,7 @@ U_CDECL_END /** * Converter option for specifying a version selector (0..9) for some converters. - * For example, + * For example, * \code * ucnv_open("UTF-7,version=1", &errorCode); * \endcode @@ -305,6 +343,8 @@ ucnv_compareNames(const char *name1, const char *name2); * other than its an alias starting with the letters "cp". Please do not * associate any meaning to these aliases. * + * \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-", @@ -323,29 +363,29 @@ ucnv_compareNames(const char *name1, const char *name2); * @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 * 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 NULL is passed for the converter name, it will create + * If NULL 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. * *See ucnv_open for the complete details
- * @param name Name of the UConverter table in a zero terminated + * @param name Name of the UConverter table in a zero terminated * Unicode string - * @param err outgoing error status U_MEMORY_ALLOCATION_ERROR, + * @param err outgoing error status U_MEMORY_ALLOCATION_ERROR, * U_FILE_ACCESS_ERROR - * @return the created Unicode converter object, or NULL if an + * @return the created Unicode converter object, or NULL if an * error occured * @see ucnv_open * @see ucnv_openCCSID @@ -353,7 +393,7 @@ ucnv_open(const char *converterName, UErrorCode *err); * @see ucnv_compareNames * @stable ICU 2.0 */ -U_STABLE UConverter* U_EXPORT2 +U_STABLE UConverter* U_EXPORT2 ucnv_openU(const UChar *name, UErrorCode *err); @@ -428,20 +468,20 @@ ucnv_openCCSID(int32_t codepage, /** *Creates a UConverter object specified from a packageName and a converterName.
- * + * *The packageName and converterName must point to an ICU udata object, as defined by
* udata_open( packageName, "cnv", converterName, err) or equivalent.
* Typically, packageName will refer to a (.dat) file, or to a package registered with
* udata_setAppData(). Using a full file or directory pathname for packageName is deprecated.
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.
* *A future version of ICU may add alias table lookups and/or caching * to this function.
- * + * *Example Use:
* cnv = ucnv_openPackage("myapp", "myconverter", &err);
*
U_BUFFER_OVERFLOW_ERROR will be set if the target is full and there is
+ * U_BUFFER_OVERFLOW_ERROR 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
@@ -1087,7 +1140,7 @@ ucnv_setFromUCallBack (UConverter * converter,
* @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,
@@ -1102,15 +1155,15 @@ ucnv_fromUnicode (UConverter * converter,
* 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
@@ -1122,7 +1175,7 @@ ucnv_fromUnicode (UConverter * converter,
* 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 stateful 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
@@ -1134,21 +1187,21 @@ ucnv_fromUnicode (UConverter * converter,
* @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 target 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 target. Will fill in offsets from target to source pointer
* e.g: offsets[3] is equal to 6, it means that the target[3] was a result of transcoding source[6]
* 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 TRUE if the current source buffer is the last available
* chunk of the source, FALSE otherwise. Note that if a failing status is returned,
* this function may have to be called multiple times with flush set to TRUE until
* the source buffer is consumed.
* @param err the error status. U_ILLEGAL_ARGUMENT_ERROR will be set if the
* converter is NULL.
- * U_BUFFER_OVERFLOW_ERROR will be set if the target is full and there is
- * still data to be written to the target.
+ * U_BUFFER_OVERFLOW_ERROR 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
@@ -1156,7 +1209,7 @@ ucnv_fromUnicode (UConverter * converter,
* @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,
@@ -1287,8 +1340,8 @@ ucnv_toUChars(UConverter *cnv,
* 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)
- * U_INDEX_OUTOFBOUNDS_ERROR will be set if the input
- * is empty or does not convert to any output (e.g.: pure state-change
+ * U_INDEX_OUTOFBOUNDS_ERROR 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 U_BUFFER_OVERFLOW_ERROR because
@@ -1392,7 +1445,7 @@ ucnv_getNextUChar(UConverter * converter,
* NULL, NULL, NULL, NULL,
* TRUE, TRUE,
* pErrorCode);
- *
+ *
* myReleaseCachedUTF8Converter(utf8Cnv);
*
* // return the output string length, but without preflighting
@@ -1680,7 +1733,7 @@ ucnv_openAllNames(UErrorCode *pErrorCode);
* @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);
/**
@@ -1695,7 +1748,7 @@ 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);
/**
@@ -1711,7 +1764,7 @@ 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);
/**
@@ -1821,6 +1874,7 @@ ucnv_getCanonicalName(const char *alias, const char *standard, UErrorCode *pErro
U_STABLE const char * U_EXPORT2
ucnv_getDefaultName(void);
+#ifndef U_HIDE_SYSTEM_API
/**
* 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
@@ -1839,11 +1893,12 @@ ucnv_getDefaultName(void);
*/
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.
@@ -1864,7 +1919,7 @@ ucnv_fixFileSeparator(const UConverter *cnv, UChar *source, int32_t sourceLen);
* 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
*/
@@ -1881,12 +1936,12 @@ ucnv_isAmbiguous(const UConverter *cnv);
* 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);
/**
@@ -1898,7 +1953,7 @@ ucnv_setFallback(UConverter *cnv, UBool usesFallback);
* @stable ICU 2.0
* @see ucnv_setFallback
*/
-U_STABLE UBool U_EXPORT2
+U_STABLE UBool U_EXPORT2
ucnv_usesFallback(const UConverter *cnv);
/**
@@ -1918,43 +1973,16 @@ ucnv_usesFallback(const UConverter *cnv);
* instead of the input signature bytes.
* * Usage: - * @code - * UErrorCode err = U_ZERO_ERROR; - * char input[] = { '\xEF','\xBB', '\xBF','\x41','\x42','\x43' }; - * int32_t signatureLength = 0; - * char *encoding = ucnv_detectUnicodeSignature(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 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. + * @return The name of the encoding detected. NULL if encoding is not detected. * @stable ICU 2.4 */ U_STABLE const char* U_EXPORT2 @@ -1964,8 +1992,8 @@ ucnv_detectUnicodeSignature(const char* source, 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 + * 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 @@ -1979,7 +2007,7 @@ 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 + * 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 @@ -1991,6 +2019,24 @@ ucnv_fromUCountPending(const UConverter* cnv, UErrorCode* status); 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 units 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