Main Page | Class Hierarchy | Alphabetical List | Data Structures | Directories | File List | Data Fields | Globals | Related Pages

ucnv.h File Reference

C API: Character conversion. More...

#include "unicode/utypes.h"
#include "unicode/ucnv_err.h"

Go to the source code of this file.

Defines

#define UCNV_MAX_CONVERTER_NAME_LENGTH   60
#define UCNV_MAX_FULL_FILE_NAME_LENGTH   (600+UCNV_MAX_CONVERTER_NAME_LENGTH)
#define UCNV_SI   0x0F
#define UCNV_SO   0x0E
#define UCNV_OPTION_SEP_CHAR   ','
 Character that separates converter names from options and options from each other.
#define UCNV_OPTION_SEP_STRING   ","
 String version of UCNV_OPTION_SEP_CHAR.
#define UCNV_VALUE_SEP_CHAR   '='
 Character that separates a converter option from its value.
#define UCNV_VALUE_SEP_STRING   "="
 String version of UCNV_VALUE_SEP_CHAR.
#define UCNV_LOCALE_OPTION_STRING   ",locale="
 Converter option for specifying a locale.
#define U_CNV_SAFECLONE_BUFFERSIZE   512
 ICU 1.8

Typedefs

typedef UConverter UConverter
 
typedef UConverterToUnicodeArgsargs
typedef UConverterToUnicodeArgs
const char * 
codePoints
typedef UConverterToUnicodeArgs
const char int32_t 
length
typedef UConverterToUnicodeArgs
const char int32_t UConverterCallbackReason 
reason
typedef UConverterToUnicodeArgs
const char int32_t UConverterCallbackReason
UErrorCode *typedef 
void (U_EXPORT2 *UConverterFromUCallback)(const void *context
 Function pointer for error callback in the unicode to codepage direction.
typedef UConverterToUnicodeArgs
const char int32_t UConverterCallbackReason
UErrorCode *typedef UConverterFromUnicodeArgs
const UChar
codeUnits
typedef UConverterToUnicodeArgs
const char int32_t UConverterCallbackReason
UErrorCode *typedef UConverterFromUnicodeArgs
const UChar int32_t UChar32 
codePoint

Enumerations

enum  UConverterType {
  UCNV_UNSUPPORTED_CONVERTER = -1, UCNV_SBCS = 0, UCNV_DBCS = 1, UCNV_MBCS = 2,
  UCNV_LATIN_1 = 3, UCNV_UTF8 = 4, UCNV_UTF16_BigEndian = 5, UCNV_UTF16_LittleEndian = 6,
  UCNV_UTF32_BigEndian = 7, UCNV_UTF32_LittleEndian = 8, UCNV_EBCDIC_STATEFUL = 9, UCNV_ISO_2022 = 10,
  UCNV_LMBCS_1 = 11, UCNV_LMBCS_2, UCNV_LMBCS_3, UCNV_LMBCS_4,
  UCNV_LMBCS_5, UCNV_LMBCS_6, UCNV_LMBCS_8, UCNV_LMBCS_11,
  UCNV_LMBCS_16, UCNV_LMBCS_17, UCNV_LMBCS_18, UCNV_LMBCS_19,
  UCNV_LMBCS_LAST = UCNV_LMBCS_19, UCNV_HZ, UCNV_SCSU, UCNV_ISCII,
  UCNV_US_ASCII, UCNV_UTF7, UCNV_NUMBER_OF_SUPPORTED_CONVERTER_TYPES
}
 Enum for specifying basic types of converters. More...
enum  UConverterPlatform { UCNV_UNKNOWN = -1, UCNV_IBM = 0 }
 Enum for specifying which platform a converter ID refers to. More...

Functions

typedef void (U_EXPORT2 *UConverterToUCallback)(const void *context
 Function pointer for error callback in the codepage to unicode direction.
U_CAPI int U_EXPORT2 ucnv_compareNames (const char *name1, const char *name2)
 Do a fuzzy compare of a two converter/alias names.
U_CAPI UConverter *U_EXPORT2 ucnv_open (const char *converterName, UErrorCode *err)
 Creates a UConverter object with the names specified as a C string.
U_CAPI UConverter *U_EXPORT2 ucnv_openU (const UChar *name, UErrorCode *err)
 Creates a Unicode converter with the names specified as unicode string.
U_CAPI UConverter *U_EXPORT2 ucnv_openCCSID (int32_t codepage, UConverterPlatform platform, UErrorCode *err)
 Creates a UConverter object from a CCSID number and platform pair.
U_CAPI UConverter *U_EXPORT2 ucnv_safeClone (const UConverter *cnv, void *stackBuffer, int32_t *pBufferSize, UErrorCode *status)
 Thread safe cloning operation.
U_CAPI void U_EXPORT2 ucnv_close (UConverter *converter)
 Deletes the unicode converter and releases resources associated with just this instance.
U_CAPI void U_EXPORT2 ucnv_getSubstChars (const UConverter *converter, char *subChars, int8_t *len, UErrorCode *err)
 Fills in the output parameter, subChars, with the substitution characters as multiple bytes.
U_CAPI void U_EXPORT2 ucnv_setSubstChars (UConverter *converter, const char *subChars, int8_t len, UErrorCode *err)
 Sets the substitution chars when converting from unicode to a codepage.
U_CAPI void U_EXPORT2 ucnv_getInvalidChars (const UConverter *converter, char *errBytes, int8_t *len, UErrorCode *err)
 Fills in the output parameter, errBytes, with the error characters from the last failing conversion.
U_CAPI void U_EXPORT2 ucnv_getInvalidUChars (const UConverter *converter, UChar *errUChars, int8_t *len, UErrorCode *err)
 Fills in the output parameter, errChars, with the error characters from the last failing conversion.
U_CAPI void U_EXPORT2 ucnv_reset (UConverter *converter)
 Resets the state of a converter to the default state.
U_CAPI void U_EXPORT2 ucnv_resetToUnicode (UConverter *converter)
 Resets the to-Unicode part of a converter state to the default state.
U_CAPI void U_EXPORT2 ucnv_resetFromUnicode (UConverter *converter)
 Resets the from-Unicode part of a converter state to the default state.
U_CAPI int8_t U_EXPORT2 ucnv_getMaxCharSize (const UConverter *converter)
 Returns the maximum length of bytes used by a character.
U_CAPI int8_t U_EXPORT2 ucnv_getMinCharSize (const UConverter *converter)
 Returns the minimum byte length for characters in this codepage.
U_CAPI int32_t U_EXPORT2 ucnv_getDisplayName (const UConverter *converter, const char *displayLocale, UChar *displayName, int32_t displayNameCapacity, UErrorCode *err)
 Returns the display name of the converter passed in based on the Locale passed in.
U_CAPI const char *U_EXPORT2 ucnv_getName (const UConverter *converter, UErrorCode *err)
 Gets the internal, canonical name of the converter (zero-terminated).
U_CAPI int32_t U_EXPORT2 ucnv_getCCSID (const UConverter *converter, UErrorCode *err)
 Gets a codepage number associated with the converter.
U_CAPI UConverterPlatform
U_EXPORT2 
ucnv_getPlatform (const UConverter *converter, UErrorCode *err)
 Gets a codepage platform associated with the converter.
U_CAPI UConverterType U_EXPORT2 ucnv_getType (const UConverter *converter)
 Gets the type of the converter e.g.
U_CAPI void U_EXPORT2 ucnv_getStarters (const UConverter *converter, UBool starters[256], UErrorCode *err)
 Gets the "starter" (lead) bytes for converters of type MBCS.
U_CAPI void U_EXPORT2 ucnv_getToUCallBack (const UConverter *converter, UConverterToUCallback *action, const void **context)
 Gets the current calback function used by the converter when an illegal or invalid codepage sequence is found.
U_CAPI void U_EXPORT2 ucnv_getFromUCallBack (const UConverter *converter, UConverterFromUCallback *action, const void **context)
 Gets the current callback function used by the converter when illegal or invalid Unicode sequence is found.
U_CAPI void U_EXPORT2 ucnv_setToUCallBack (UConverter *converter, UConverterToUCallback newAction, const void *newContext, UConverterToUCallback *oldAction, const void **oldContext, UErrorCode *err)
 Changes the callback function used by the converter when an illegal or invalid sequence is found.
U_CAPI void U_EXPORT2 ucnv_setFromUCallBack (UConverter *converter, UConverterFromUCallback newAction, const void *newContext, UConverterFromUCallback *oldAction, const void **oldContext, UErrorCode *err)
 Changes the current callback function used by the converter when an illegal or invalid sequence is found.
U_CAPI void U_EXPORT2 ucnv_fromUnicode (UConverter *converter, char **target, const char *targetLimit, const UChar **source, const UChar *sourceLimit, int32_t *offsets, UBool flush, UErrorCode *err)
 Converts an array of unicode characters to an array of codepage characters.
U_CAPI void U_EXPORT2 ucnv_toUnicode (UConverter *converter, UChar **target, const UChar *targetLimit, const char **source, const char *sourceLimit, int32_t *offsets, UBool flush, UErrorCode *err)
 Converts a buffer of codepage bytes into an array of unicode UChars characters.
U_CAPI int32_t U_EXPORT2 ucnv_fromUChars (UConverter *cnv, char *dest, int32_t destCapacity, const UChar *src, int32_t srcLength, UErrorCode *pErrorCode)
 Convert the Unicode string into a codepage string using an existing UConverter.
U_CAPI int32_t U_EXPORT2 ucnv_toUChars (UConverter *cnv, UChar *dest, int32_t destCapacity, const char *src, int32_t srcLength, UErrorCode *pErrorCode)
 Convert the codepage string into a Unicode string using an existing UConverter.
U_CAPI UChar32 U_EXPORT2 ucnv_getNextUChar (UConverter *converter, const char **source, const char *sourceLimit, UErrorCode *err)
 Will convert a codepage buffer into unicode one character at a time.
U_CAPI int32_t U_EXPORT2 ucnv_convert (const char *toConverterName, const char *fromConverterName, char *target, int32_t targetCapacity, const char *source, int32_t sourceLength, UErrorCode *err)
 Will convert a sequence of bytes from one codepage to another.
U_CAPI int32_t U_EXPORT2 ucnv_flushCache (void)
 Frees up memory occupied by unused, cached converter shared data.
U_CAPI int32_t U_EXPORT2 ucnv_countAvailable (void)
 returns the number of available converters, as per the alias file.
U_CAPI const char *U_EXPORT2 ucnv_getAvailableName (int32_t n)
 Gets the name of the specified converter from a list of all converters contaied in the alias file.
U_CAPI uint16_t U_EXPORT2 ucnv_countAliases (const char *alias, UErrorCode *pErrorCode)
 Gives the number of aliases for a given converter or alias name.
U_CAPI const char *U_EXPORT2 ucnv_getAlias (const char *alias, uint16_t n, UErrorCode *pErrorCode)
 Gives the name of the alias at given index of alias list.
U_CAPI void U_EXPORT2 ucnv_getAliases (const char *alias, const char **aliases, UErrorCode *pErrorCode)
 Fill-up the list of alias names for the given alias.
U_CAPI uint16_t U_EXPORT2 ucnv_countStandards (void)
 Gives the number of standards associated to converter names.
U_CAPI const char *U_EXPORT2 ucnv_getStandard (uint16_t n, UErrorCode *pErrorCode)
 Gives the name of the standard at given index of standard list.
U_CAPI const char *U_EXPORT2 ucnv_getStandardName (const char *name, const char *standard, UErrorCode *pErrorCode)
 Returns a standard name for a given converter name.
U_CAPI const char *U_EXPORT2 ucnv_getDefaultName (void)
 returns the current default converter name.
U_CAPI void U_EXPORT2 ucnv_setDefaultName (const char *name)
 sets the current default converter name.
U_CAPI void U_EXPORT2 ucnv_fixFileSeparator (const UConverter *cnv, UChar *source, int32_t sourceLen)
 Fixes the backslash character mismapping.
U_CAPI UBool U_EXPORT2 ucnv_isAmbiguous (const UConverter *cnv)
 Determines if the converter contains ambiguous mappings of the same character or not.
U_CAPI void U_EXPORT2 ucnv_setFallback (UConverter *cnv, UBool usesFallback)
 Sets the converter to use fallback mapping or not.
U_CAPI UBool U_EXPORT2 ucnv_usesFallback (const UConverter *cnv)
 Determines if the converter uses fallback mappings or not.
U_CAPI const char *U_EXPORT2 ucnv_detectUnicodeSignature (const char *source, int32_t sourceLength, int32_t *signatureLength, UErrorCode *pErrorCode)
 Detects Unicode signatures in the given byte stream.


Detailed Description

C API: Character conversion.

Character Conversion C API


Define Documentation

#define UCNV_LOCALE_OPTION_STRING   ",locale="
 

Converter option for specifying a locale.

See also:
ucnv_open

#define UCNV_OPTION_SEP_CHAR   ','
 

Character that separates converter names from options and options from each other.

See also:
ucnv_open

#define UCNV_OPTION_SEP_STRING   ","
 

String version of UCNV_OPTION_SEP_CHAR.

See also:
ucnv_open

#define UCNV_VALUE_SEP_CHAR   '='
 

Character that separates a converter option from its value.

See also:
ucnv_open

#define UCNV_VALUE_SEP_STRING   "="
 

String version of UCNV_VALUE_SEP_CHAR.

See also:
ucnv_open


Typedef Documentation

typedef UConverterToUnicodeArgs const char int32_t UConverterCallbackReason UErrorCode* typedef void(U_EXPORT2 *UConverterFromUCallback)(const void *context
 

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).

Parameters:
context Pointer to the callback's private data
args Information about the conversion in progress
codeUnits Points to 'length' UChars of the concerned Unicode sequence
length Size (in bytes) of the concerned codepage sequence
codePoint Single UChar32 (UTF-32) containing the concerend Unicode codepoint.
reason Defines the reason the callback was invoked
See also:
ucnv_setFromUCallBack


Enumeration Type Documentation

enum UConverterPlatform
 

Enum for specifying which platform a converter ID refers to.

The use of platform/CCSID is not recommended. See ucnv_openCCSID().

See also:
ucnv_getPlatform

ucnv_openCCSID

ucnv_getCCSID

enum UConverterType
 

Enum for specifying basic types of converters.

See also:
ucnv_getType


Function Documentation

U_CAPI void U_EXPORT2 ucnv_close UConverter converter  ) 
 

Deletes the unicode converter and releases resources associated with just this instance.

Does not free up shared converter tables.

Parameters:
converter the converter object to be deleted
See also:
ucnv_open

ucnv_openU

ucnv_openCCSID

U_CAPI int U_EXPORT2 ucnv_compareNames const char *  name1,
const char *  name2
 

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.

Parameters:
name1 a converter name or alias, zero-terminated
name2 a converter name or alias, zero-terminated
Returns:
0 if the names match, or a negative value if the name1 lexically precedes name2, or a positive value if the name1 lexically follows name2.

U_CAPI int32_t U_EXPORT2 ucnv_convert const char *  toConverterName,
const char *  fromConverterName,
char *  target,
int32_t  targetCapacity,
const char *  source,
int32_t  sourceLength,
UErrorCode err
 

Will convert a sequence of bytes from one codepage to another.

This is NOT AN EFFICIENT way to transcode. use {ucnv_toUnicode} and {ucnv_fromUnicode} for efficiency.

Parameters:
toConverterName The name of the converter that will be used in conversion from unicode into the output buffer
fromConverterName,: The name of the converter that will be used in conversion from the source buffer into intermediate unicode.
target Pointer to the output buffer
targetCapacity capacity of the target, in bytes
source Pointer to the input buffer
sourceLength capacity of the source, in bytes
err error status. U_BUFFER_OVERFLOW_ERROR will be set if the target is full and there is still input left in the source.
Returns:
will be filled in with the number of bytes needed in target
See also:
ucnv_fromUnicode

ucnv_toUnicode

ucnv_fromUChars

ucnv_toUChars

ucnv_getNextUChar

U_CAPI uint16_t U_EXPORT2 ucnv_countAliases const char *  alias,
UErrorCode pErrorCode
 

Gives the number of aliases for a given converter or alias name.

Note that additional aliases are recognized by ucnv_open(). This method only enumerates the listed entries in the alias file.

Parameters:
alias alias name
pErrorCode error status
Returns:
number of names on alias list for given alias

U_CAPI int32_t U_EXPORT2 ucnv_countAvailable void   ) 
 

returns the number of available converters, as per the alias file.

Returns:
the number of available converters
See also:
ucnv_getAvailableName

U_CAPI uint16_t U_EXPORT2 ucnv_countStandards void   ) 
 

Gives the number of standards associated to converter names.

Returns:
number of standards

U_CAPI const char* U_EXPORT2 ucnv_detectUnicodeSignature const char *  source,
int32_t  sourceLength,
int32_t *  signatureLength,
UErrorCode pErrorCode
 

Detects Unicode signatures in the given byte stream.

The signature bytes are not consumed, instead the number of bytes that make up the signature is returned. The conversion APIs donot discard signature bytes, so if the caller wishes to discard them, the caller should explicity add code to do that after calling this function.

Usage:

      UErrorCode err = U_ZERO_ERROR;
      char input[] = { '\xEF','\xBB', '\xBF','\x41','\x42','\x43' };
      char* source = input;
      int32_t signatureLength = 0;
      char* encoding = ucnv_detectUnicodeSignatures(source,sizeof(input),&signatureLength,&err);
      UConverter* conv = NULL;
      if(encoding!=NULL && U_SUCCESS(err)){
          // should signature be discarded ?
          if (discardSignature){
              source += signatureLength;
          }
          conv = ucnv_open(encoding, &err);
          .... do the conversion ....
      }

Parameters:
source The source string in which the signature should be detected.
sourceLength Length of the input string, or -1 if NUL-terminated.
signatureLength A pointer to int8_t to receive the number of bytes that make up the signature of the detected UTF. 0 if not detected.
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.
Returns:
The name of the encoding detected. NULL if encoding is not detected.

U_CAPI void U_EXPORT2 ucnv_fixFileSeparator const UConverter cnv,
UChar source,
int32_t  sourceLen
 

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. This function will test the converter to see whether such mapping is required. You can sometimes avoid using this function by using the correct version of Shift-JIS.

Parameters:
cnv The converter representing the target codepage.
source the input buffer to be fixed
sourceLength the length of the input buffer
See also:
ucnv_isAmbiguous

U_CAPI int32_t U_EXPORT2 ucnv_flushCache void   ) 
 

Frees up memory occupied by unused, cached converter shared data.

Returns:
the number of cached converters successfully deleted
See also:
ucnv_close

U_CAPI int32_t U_EXPORT2 ucnv_fromUChars UConverter cnv,
char *  dest,
int32_t  destCapacity,
const UChar src,
int32_t  srcLength,
UErrorCode pErrorCode
 

Convert the Unicode string into a codepage string using an existing UConverter.

The output string is NUL-terminated if possible.

This function is a more convenient but less powerful version of ucnv_fromUnicode(). It is only useful for whole strings, not for streaming conversion.

The maximum output buffer capacity required (barring output from callbacks) will be srcLength*ucnv_getMaxCharSize(cnv).

Parameters:
cnv the converter object to be used (ucnv_resetFromUnicode() will be called)
src the input Unicode string
srcLength the input string length, or -1 if NUL-terminated
dest destination string buffer, can be NULL if destCapacity==0
destCapacity the number of chars available at dest
errorCode normal ICU error code; common error codes that may be set by this function include U_BUFFER_OVERFLOW_ERROR, U_STRING_NOT_TERMINATED_WARNING, U_ILLEGAL_ARGUMENT_ERROR, and conversion errors
Returns:
the length of the output string, not counting the terminating NUL; if the length is greater than destCapacity, then the string will not fit and a buffer of the indicated length would need to be passed in
See also:
ucnv_fromUnicode

ucnv_convert ICU 2.0 (new NUL-termination semantics)

U_CAPI void U_EXPORT2 ucnv_fromUnicode UConverter converter,
char **  target,
const char *  targetLimit,
const UChar **  source,
const UChar sourceLimit,
int32_t *  offsets,
UBool  flush,
UErrorCode err
 

Converts an array of unicode characters to an array of codepage 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.

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 (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.

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 the next empty chunk of target in case of a U_BUFFER_OVERFLOW_ERROR, and updating the source pointers with the next chunk of source when a successful error status is returned, until there are no more chunks of source data.

Parameters:
converter the Unicode converter
target I/O parameter. Input : Points to the beginning of the buffer to copy codepage characters to. Output : points to after the last codepage character copied to target.
targetLimit the pointer just after last of the target buffer
source I/O parameter, pointer to pointer to the source Unicode character buffer.
sourceLimit the pointer just after the last of the source buffer
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.
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 wiht flush set to TRUE until the source buffer is consumed.
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.
See also:
ucnv_fromUChars

ucnv_convert

ucnv_getMinCharSize

ucnv_setToUCallBack

U_CAPI const char* U_EXPORT2 ucnv_getAlias const char *  alias,
uint16_t  n,
UErrorCode pErrorCode
 

Gives the name of the alias at given index of alias list.

Note that additional aliases are recognized by ucnv_open(). This method only enumerates the listed entries in the alias file.

Parameters:
alias alias name
n index in alias list
pErrorCode result of operation
Returns:
returns the name of the alias at given index
See also:
ucnv_countAliases

U_CAPI void U_EXPORT2 ucnv_getAliases const char *  alias,
const char **  aliases,
UErrorCode pErrorCode
 

Fill-up the list of alias names for the given alias.

Note that additional aliases are recognized by ucnv_open(). This method only enumerates the listed entries in the alias file.

Parameters:
alias alias name
aliases fill-in list, aliases is a pointer to an array of ucnv_countAliases() string-pointers (const char *) that will be filled in. The strings themselves are owned by the library.
pErrorCode result of operation

U_CAPI const char* U_EXPORT2 ucnv_getAvailableName int32_t  n  ) 
 

Gets the name of the specified converter from a list of all converters contaied in the alias file.

Parameters:
n the index to a converter available on the system (in the range [0..ucnv_countAvaiable()])
Returns:
a pointer a string (library owned), or NULL if the index is out of bounds.
See also:
ucnv_countAvailable

U_CAPI int32_t U_EXPORT2 ucnv_getCCSID const UConverter converter,
UErrorCode err
 

Gets a codepage number associated with the converter.

This is not guaranteed to be the one used to create the converter. Some converters do not represent platform registered codepages and return zero for the codepage number. The error code fill-in parameter indicates if the codepage number is available. Does not check if the converter is NULL or if converter's data table is NULL.

Important: The use of CCSIDs is not recommended because it is limited to only two platforms in principle and only one (UCNV_IBM) in the current ICU converter API. Also, CCSIDs are insufficient to identify IBM Unicode conversion tables precisely. For more details see ucnv_openCCSID().

Parameters:
converter the Unicode converter
err the error status code.
Returns:
If any error occurrs, -1 will be returned otherwise, the codepage number will be returned
See also:
ucnv_openCCSID

ucnv_getPlatform

U_CAPI const char* U_EXPORT2 ucnv_getDefaultName void   ) 
 

returns the current default converter name.

Returns:
returns the current default converter name; if a default converter name cannot be determined, then NULL is returned. Storage owned by the library
See also:
ucnv_setDefaultName

U_CAPI int32_t U_EXPORT2 ucnv_getDisplayName const UConverter converter,
const char *  displayLocale,
UChar displayName,
int32_t  displayNameCapacity,
UErrorCode err
 

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.

Parameters:
converter the Unicode converter.
displayLocale is the specific Locale we want to localised for
displayName user provided buffer to be filled in
displayNameCapacty size of displayName Buffer
err error status code
Returns:
displayNameLength number of UChar needed in displayName
See also:
ucnv_getName

U_CAPI void U_EXPORT2 ucnv_getFromUCallBack const UConverter converter,
UConverterFromUCallback *  action,
const void **  context
 

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.

Parameters:
converter the unicode converter
action fillin: returns the callback function pointer
context fillin: returns the callback's private void* context
See also:
ucnv_setFromUCallBack

U_CAPI void U_EXPORT2 ucnv_getInvalidChars const UConverter converter,
char *  errBytes,
int8_t *  len,
UErrorCode err
 

Fills in the output parameter, errBytes, with the error characters from the last failing conversion.

Parameters:
converter the Unicode converter
errBytes the codepage bytes which were in error
len on input the capacity of errBytes, on output the number of bytes which were copied to it
err the error status code. If the substitution character array is too small, an U_INDEX_OUTOFBOUNDS_ERROR will be returned.

U_CAPI void U_EXPORT2 ucnv_getInvalidUChars const UConverter converter,
UChar errUChars,
int8_t *  len,
UErrorCode err
 

Fills in the output parameter, errChars, with the error characters from the last failing conversion.

Parameters:
converter the Unicode converter
errUChars the UChars which were in error
len on input the capacity of errUChars, on output the number of UChars which were copied to it
err the error status code. If the substitution character array is too small, an U_INDEX_OUTOFBOUNDS_ERROR will be returned.

U_CAPI int8_t U_EXPORT2 ucnv_getMaxCharSize const UConverter converter  ) 
 

Returns the maximum length of bytes used by a character.

This varies between 1 and 4

Parameters:
converter the Unicode converter
Returns:
the maximum number of bytes allowed by this particular converter
See also:
ucnv_getMinCharSize

U_CAPI int8_t U_EXPORT2 ucnv_getMinCharSize const UConverter converter  ) 
 

Returns the minimum byte length for characters in this codepage.

This is either 1 or 2 for all supported codepages.

Parameters:
converter the Unicode converter
Returns:
the minimum number of bytes allowed by this particular converter
See also:
ucnv_getMaxCharSize

U_CAPI const char* U_EXPORT2 ucnv_getName const UConverter converter,
UErrorCode err
 

Gets the internal, canonical name of the converter (zero-terminated).

The lifetime of the returned string will be that of the converter passed to this function.

Parameters:
converter the Unicode converter
err UErrorCode status
Returns:
the internal name of the converter
See also:
ucnv_getDisplayName

U_CAPI UChar32 U_EXPORT2 ucnv_getNextUChar UConverter converter,
const char **  source,
const char *  sourceLimit,
UErrorCode err
 

Will convert a codepage buffer into unicode one character at a time.

This function was written to be efficient when transcoding small amounts of data at a time. In that case it will be more efficient than {ucnv_toUnicode}. When converting large buffers use {ucnv_toUnicode}.

Handling of surrogate pairs and supplementary-plane code points:
There are two different kinds of codepages that provide mappings for surrogate characters:

  • Codepages like UTF-8, UTF-32, and GB 18030 provide direct representations for Unicode code points U+10000-U+10ffff as well as for single surrogates U+d800-U+dfff. Each valid sequence will result in exactly one returned code point. If a sequence results in a single surrogate, then that will be returned by itself, even if a neighboring sequence encodes the matching surrogate.
  • Codepages like SCSU and LMBCS (and UTF-16) provide direct representations only for BMP code points including surrogates. Code points in supplementary planes are represented with two sequences, each encoding a surrogate. For these codepages, matching pairs of surrogates will be combined into single code points for returning from this function. (Note that SCSU is actually a mix of these codepage types.)

Parameters:
converter an open UConverter
source the address of a pointer to the codepage buffer, will be updated to point after the bytes consumed in the conversion call.
sourceLimit points to the end of the input buffer
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 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 the "buffer" is the return code. However, there might be subsequent output stored in the converter object that will be returned in following calls to this function.
Returns:
a UChar32 resulting from the partial conversion of source
See also:
ucnv_toUnicode

ucnv_toUChars

ucnv_convert

U_CAPI UConverterPlatform U_EXPORT2 ucnv_getPlatform const UConverter converter,
UErrorCode err
 

Gets a codepage platform associated with the converter.

Currently, only UCNV_IBM will be returned. Does not test if the converter is NULL or if converter's data table is NULL.

Parameters:
converter the Unicode converter
err the error status code.
Returns:
The codepage platform

U_CAPI const char* U_EXPORT2 ucnv_getStandard uint16_t  n,
UErrorCode pErrorCode
 

Gives the name of the standard at given index of standard list.

Parameters:
n index in standard list
pErrorCode result of operation
Returns:
returns the name of the standard at given index. Owned by the library.

U_CAPI const char* U_EXPORT2 ucnv_getStandardName const char *  name,
const char *  standard,
UErrorCode pErrorCode
 

Returns a standard name for a given converter name.

Parameters:
name original converter name
standard name of the standard governing the names; MIME and IANA are such standards
Returns:
returns the standard converter name; if a standard converter name cannot be determined, then NULL is returned. Owned by the library.

U_CAPI void U_EXPORT2 ucnv_getStarters const UConverter converter,
UBool  starters[256],
UErrorCode err
 

Gets the "starter" (lead) bytes for converters of type MBCS.

Will fill in an U_ILLEGAL_ARGUMENT_ERROR if converter passed in 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.

Parameters:
converter a valid, opened converter of type MBCS
starters an array of size 256 to be filled in
err error status, U_ILLEGAL_ARGUMENT_ERROR if the converter is not a type which can return starters.
See also:
ucnv_getType

U_CAPI void U_EXPORT2 ucnv_getSubstChars const UConverter converter,
char *  subChars,
int8_t *  len,
UErrorCode err
 

Fills in the output parameter, subChars, with the substitution characters as multiple bytes.

Parameters:
converter the Unicode converter
subChars the subsitution characters
len on input the capacity of subChars, on output the number of bytes copied to it
err the outgoing error status code. If the substitution character array is too small, an U_INDEX_OUTOFBOUNDS_ERROR will be returned.
See also:
ucnv_setSubstChars

U_CAPI void U_EXPORT2 ucnv_getToUCallBack const UConverter converter,
UConverterToUCallback *  action,
const void **  context
 

Gets the current calback function used by the converter when an illegal or invalid codepage sequence is found.

Context pointers are always owned by the caller.

Parameters:
converter the unicode converter
action fillin: returns the callback function pointer
context fillin: returns the callback's private void* context
See also:
ucnv_setToUCallBack

U_CAPI UConverterType U_EXPORT2 ucnv_getType const UConverter converter  ) 
 

Gets the type of the converter e.g.

SBCS, MBCS, DBCS, UTF8, UTF16_BE, UTF16_LE, ISO_2022, EBCDIC_STATEFUL, LATIN_1

Parameters:
converter a valid, opened converter
Returns:
the type of the converter

U_CAPI UBool U_EXPORT2 ucnv_isAmbiguous const UConverter cnv  ) 
 

Determines if the converter contains ambiguous mappings of the same character or not.

Returns:
TRUE if the converter contains ambiguous mapping of the same character, FALSE otherwise.

U_CAPI UConverter* U_EXPORT2 ucnv_open const char *  converterName,
UErrorCode err
 

Creates a UConverter object with the names 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. If NULL is passed for the converter name, it will create one with the getDefaultName return value.

A converter name for ICU 1.5 and above may contain options like a locale specification to control the specific behavior of the newly instantiated converter. The meaning of the options depends on the particular converter. If an option is not defined for or recognized by a given converter, then it is ignored.

Options are appended to the converter name string, with a UCNV_OPTION_SEP_CHAR between the name and the first option and also between adjacent options.

Parameters:
converterName : name of the uconv table, may have options appended
err outgoing error status U_MEMORY_ALLOCATION_ERROR, U_FILE_ACCESS_ERROR
Returns:
the created Unicode converter object, or NULL if an error occured
See also:
ucnv_openU

ucnv_openCCSID

ucnv_close

U_CAPI UConverter* U_EXPORT2 ucnv_openCCSID int32_t  codepage,
UConverterPlatform  platform,
UErrorCode err
 

Creates a UConverter object from a CCSID number and platform pair.

Note that the usefulness of this function is limited to platforms with numeric encoding IDs. Only IBM and Microsoft platforms use numeric (16-bit) identifiers for encodings.

In addition, IBM CCSIDs and Unicode conversion tables are not 1:1 related. For many IBM CCSIDs there are multiple (up to six) Unicode conversion tables, and for some Unicode conversion tables there are multiple CCSIDs. Some "alternate" Unicode conversion tables are provided by the IBM CDRA conversion table registry. The most prominent example of a systematic modification of conversion tables that is not provided in the form of conversion table files in the repository is that S/390 Unix System Services swaps the codes for Line Feed and New Line in all EBCDIC codepages, which requires such a swap in the Unicode conversion tables as well.

Only IBM default conversion tables are accessible with ucnv_openCCSID(). ucnv_getCCSID() will return the same CCSID for all conversion tables that are associated with that CCSID.

Currently, the only "platform" supported in the ICU converter API is UCNV_IBM.

In summary, the use of CCSIDs and the associated API functions is not recommended.

In order to open a converter with the default IBM CDRA Unicode conversion table, you can use this function or use the prefix "ibm-":

     char name[20];
     sprintf(name, "ibm-%hu", ccsid);
     cnv=ucnv_open(name, &errorCode);

In order to open a converter with the IBM S/390 Unix System Services variant of a Unicode/EBCDIC conversion table, you can use the prefix "ibm-" together with the suffix "-s390":

     char name[20];
     sprintf(name, "ibm-%hu-s390", ccsid);
     cnv=ucnv_open(name, &errorCode);

In order to open a converter from a Microsoft codepage number, use the prefix "cp":

     char name[20];
     sprintf(name, "cp%hu", codepageID);
     cnv=ucnv_open(name, &errorCode);

Parameters:
codepage codepage number to create
platform the platform in which the codepage number exists
err error status U_MEMORY_ALLOCATION_ERROR, U_FILE_ACCESS_ERROR
Returns:
the created Unicode converter object, or NULL if an error occured.
See also:
ucnv_open

ucnv_openU

ucnv_close

ucnv_getCCSID

ucnv_getPlatform

UConverterPlatform

U_CAPI UConverter* U_EXPORT2 ucnv_openU const UChar name,
UErrorCode err
 

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 NULL is passed for the converter name, it will create one with the ucnv_getDefaultName() return value.

Parameters:
converterName : name of the uconv table in a zero terminated Unicode string
err outgoing error status U_MEMORY_ALLOCATION_ERROR, U_FILE_ACCESS_ERROR
Returns:
the created Unicode converter object, or NULL if an error occured
See also:
ucnv_open

ucnv_openCCSID

ucnv_close

ucnv_getDefaultName

U_CAPI void U_EXPORT2 ucnv_reset UConverter converter  ) 
 

Resets the state of a converter to the default state.

This is used in the case of an error, to restart a conversion from a known default state. It will also empty the internal output buffers.

Parameters:
converter the Unicode converter

U_CAPI void U_EXPORT2 ucnv_resetFromUnicode UConverter converter  ) 
 

Resets the from-Unicode part of a converter state to the default state.

This is used in the case of an error to restart a conversion from Unicode to a known default state. It will also empty the internal output buffers used for the conversion from Unicode codepoints.

Parameters:
converter the Unicode converter ICU 1.8

U_CAPI void U_EXPORT2 ucnv_resetToUnicode UConverter converter  ) 
 

Resets the to-Unicode part of a converter state to the default state.

This is used in the case of an error to restart a conversion to Unicode to a known default state. It will also empty the internal output buffers used for the conversion to Unicode codepoints.

Parameters:
converter the Unicode converter ICU 1.8

U_CAPI UConverter* U_EXPORT2 ucnv_safeClone const UConverter cnv,
void *  stackBuffer,
int32_t *  pBufferSize,
UErrorCode status
 

Thread safe cloning operation.

Parameters:
cnv converter to be cloned
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_CNV_SAFECLONE_BUFFERSIZE. This will probably be enough to avoid memory allocations.
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.
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.
Returns:
pointer to the new clone ICU 1.8

U_CAPI void U_EXPORT2 ucnv_setDefaultName const char *  name  ) 
 

sets the current default converter name.

Caller must own the storage for 'name' and preserve it indefinitely.

Parameters:
name the converter name to be the default (must exist).
See also:
ucnv_getDefaultName SYSTEM API

U_CAPI void U_EXPORT2 ucnv_setFallback UConverter cnv,
UBool  usesFallback
 

Sets the converter to use fallback mapping or not.

Parameters:
cnv The converter to set the fallback mapping usage on.
usesFallback TRUE if the user wants the converter to take advantage of the fallback mapping, FALSE otherwise.

U_CAPI void U_EXPORT2 ucnv_setFromUCallBack UConverter converter,
UConverterFromUCallback  newAction,
const void *  newContext,
UConverterFromUCallback *  oldAction,
const void **  oldContext,
UErrorCode err
 

Changes the current callback function used by the converter when an illegal or invalid sequence is found.

Context pointers are always owned by the caller.

Parameters:
converter the unicode converter
newAction the new callback function
newContext the new fromUnicode callback context pointer
oldAction fillin: returns the old callback function pointer
oldContext fillin: returns the old callback's private void* context
err The error code status
See also:
ucnv_getFromUCallBack

U_CAPI void U_EXPORT2 ucnv_setSubstChars UConverter converter,
const char *  subChars,
int8_t  len,
UErrorCode err
 

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 NULL byte.

Parameters:
converter the Unicode converter
subChars the substitution character byte sequence we want set
len the number of bytes in subChars
err the error status code. U_INDEX_OUTOFBOUNDS_ERROR if len is bigger than the maximum number of bytes allowed in subchars
See also:
ucnv_getSubstChars

U_CAPI void U_EXPORT2 ucnv_setToUCallBack UConverter converter,
UConverterToUCallback  newAction,
const void *  newContext,
UConverterToUCallback *  oldAction,
const void **  oldContext,
UErrorCode err
 

Changes the callback function used by the converter when an illegal or invalid sequence is found.

Context pointers are always owned by the caller.

Parameters:
converter the unicode converter
newAction the new callback function
newContext the new toUnicode callback context pointer
oldAction fillin: returns the old callback function pointer
oldContext fillin: returns the old callback's private void* context
err The error code status
See also:
ucnv_getToUCallBack

U_CAPI int32_t U_EXPORT2 ucnv_toUChars UConverter cnv,
UChar dest,
int32_t  destCapacity,
const char *  src,
int32_t  srcLength,
UErrorCode pErrorCode
 

Convert the codepage string into a Unicode string using an existing UConverter.

The output string is NUL-terminated if possible.

This function is a more convenient but less powerful version of ucnv_toUnicode(). It is only useful for whole strings, not for streaming conversion.

The maximum output buffer capacity required (barring output from callbacks) will be 2*srcLength (each char may be converted into a surrogate pair).

Parameters:
cnv the converter object to be used (ucnv_resetToUnicode() will be called)
src the input codepage string
srcLength the input string length, or -1 if NUL-terminated
dest destination string buffer, can be NULL if destCapacity==0
destCapacity the number of UChars available at dest
errorCode normal ICU error code; common error codes that may be set by this function include U_BUFFER_OVERFLOW_ERROR, U_STRING_NOT_TERMINATED_WARNING, U_ILLEGAL_ARGUMENT_ERROR, and conversion errors
Returns:
the length of the output string, not counting the terminating NUL; if the length is greater than destCapacity, then the string will not fit and a buffer of the indicated length would need to be passed in
See also:
ucnv_toUnicode

ucnv_convert ICU 2.0 (new NUL-termination semantics)

U_CAPI void U_EXPORT2 ucnv_toUnicode UConverter converter,
UChar **  target,
const UChar targetLimit,
const char **  source,
const char *  sourceLimit,
int32_t *  offsets,
UBool  flush,
UErrorCode err
 

Converts a buffer of codepage bytes into an array of unicode UChars 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.

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. It does NOT necessarily keep UChar sequences together.

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.

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 the next empty chunk of target in case of a U_BUFFER_OVERFLOW_ERROR, and updating the source pointers with the next chunk of source when a successful error status is returned, until there are no more chunks of source data.

Parameters:
converter the Unicode converter
target I/O parameter. Input : Points to the beginning of the buffer to copy UChars into. Output : points to after the last UChar copied.
targetLimit the pointer just after the end of the target buffer
source I/O parameter, pointer to pointer to the source codepage buffer.
sourceLimit the pointer to the byte after the end of the source buffer
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.
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 wiht flush set to TRUE until the source buffer is consumed.
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.
See also:
ucnv_fromUChars

ucnv_convert

ucnv_getMinCharSize

ucnv_setFromUCallBack

ucnv_getNextUChar

U_CAPI UBool U_EXPORT2 ucnv_usesFallback const UConverter cnv  ) 
 

Determines if the converter uses fallback mappings or not.

Returns:
TRUE if the converter uses fallback, FALSE otherwise.

typedef void U_EXPORT2 *  UConverterToUCallback  )  const
 

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).

Parameters:
context Pointer to the callback's private data
args Information about the conversion in progress
codePoints Points to 'length' bytes of the concerned codepage sequence
length Size (in bytes) of the concerned codepage sequence
reason Defines the reason the callback was invoked
See also:
ucnv_setToUCallBack

UConverterToUnicodeArgs


Generated on Mon May 23 00:53:38 2005 for ICU 2.1 by  doxygen 1.4.2