ICU 76.1 76.1
|
C API: Unicode stdio-like API. More...
#include <stdio.h>
#include <stdarg.h>
#include "unicode/utypes.h"
#include "unicode/ucnv.h"
#include "unicode/utrans.h"
#include "unicode/unum.h"
#include "unicode/localpointer.h"
Go to the source code of this file.
Namespaces | |
namespace | icu |
File coll.h. | |
Macros | |
#define | U_EOF 0xFFFF |
When an end of file is encountered, this value can be returned. | |
Typedefs | |
typedef struct UFILE | UFILE |
Forward declaration of a Unicode-aware file. | |
Enumerations | |
enum | UFileDirection { U_READ = 1 , U_WRITE = 2 , U_READWRITE =3 } |
Enum for which direction of stream a transliterator applies to. More... | |
Functions | |
U_CAPI UFILE * | u_fopen (const char *filename, const char *perm, const char *locale, const char *codepage) |
Open a UFILE. | |
U_CAPI UFILE * | u_fopen_u (const UChar *filename, const char *perm, const char *locale, const char *codepage) |
Open a UFILE with a UChar* filename A UFILE is a wrapper around a FILE* that is locale and codepage aware. | |
U_CAPI UFILE * | u_finit (FILE *f, const char *locale, const char *codepage) |
Open a UFILE on top of an existing FILE* stream. | |
U_CAPI UFILE * | u_fadopt (FILE *f, const char *locale, const char *codepage) |
Open a UFILE on top of an existing FILE* stream. | |
U_CAPI UFILE * | u_fstropen (UChar *stringBuf, int32_t capacity, const char *locale) |
Create a UFILE that can be used for localized formatting or parsing. | |
U_CAPI void | u_fclose (UFILE *file) |
Close a UFILE. | |
U_CAPI UBool | u_feof (UFILE *f) |
Tests if the UFILE is at the end of the file stream. | |
U_CAPI void | u_fflush (UFILE *file) |
Flush output of a UFILE. | |
U_CAPI void | u_frewind (UFILE *file) |
Rewind the file pointer to the beginning of the file. | |
U_CAPI FILE * | u_fgetfile (UFILE *f) |
Get the FILE* associated with a UFILE. | |
U_CAPI const char * | u_fgetlocale (UFILE *file) |
Get the locale whose conventions are used to format and parse output. | |
U_CAPI int32_t | u_fsetlocale (UFILE *file, const char *locale) |
Set the locale whose conventions will be used to format and parse output. | |
U_CAPI const char * | u_fgetcodepage (UFILE *file) |
Get the codepage in which data is written to and read from the UFILE. | |
U_CAPI int32_t | u_fsetcodepage (const char *codepage, UFILE *file) |
Set the codepage in which data will be written to and read from the UFILE. | |
U_CAPI UConverter * | u_fgetConverter (UFILE *f) |
Returns an alias to the converter being used for this file. | |
U_CAPI const UNumberFormat * | u_fgetNumberFormat (UFILE *f) |
Returns an alias to the number formatter being used for this file. | |
U_CAPI int32_t | u_printf (const char *patternSpecification,...) |
Write formatted data to stdout . | |
U_CAPI int32_t | u_fprintf (UFILE *f, const char *patternSpecification,...) |
Write formatted data to a UFILE. | |
U_CAPI int32_t | u_vfprintf (UFILE *f, const char *patternSpecification, va_list ap) |
Write formatted data to a UFILE. | |
U_CAPI int32_t | u_printf_u (const UChar *patternSpecification,...) |
Write formatted data to stdout . | |
U_CAPI UFILE * | u_get_stdout (void) |
Get a UFILE for stdout . | |
U_CAPI int32_t | u_fprintf_u (UFILE *f, const UChar *patternSpecification,...) |
Write formatted data to a UFILE. | |
U_CAPI int32_t | u_vfprintf_u (UFILE *f, const UChar *patternSpecification, va_list ap) |
Write formatted data to a UFILE. | |
U_CAPI int32_t | u_fputs (const UChar *s, UFILE *f) |
Write a Unicode to a UFILE. | |
U_CAPI UChar32 | u_fputc (UChar32 uc, UFILE *f) |
Write a UChar to a UFILE. | |
U_CAPI int32_t | u_file_write (const UChar *ustring, int32_t count, UFILE *f) |
Write Unicode to a UFILE. | |
U_CAPI int32_t | u_fscanf (UFILE *f, const char *patternSpecification,...) |
Read formatted data from a UFILE. | |
U_CAPI int32_t | u_vfscanf (UFILE *f, const char *patternSpecification, va_list ap) |
Read formatted data from a UFILE. | |
U_CAPI int32_t | u_fscanf_u (UFILE *f, const UChar *patternSpecification,...) |
Read formatted data from a UFILE. | |
U_CAPI int32_t | u_vfscanf_u (UFILE *f, const UChar *patternSpecification, va_list ap) |
Read formatted data from a UFILE. | |
U_CAPI UChar * | u_fgets (UChar *s, int32_t n, UFILE *f) |
Read one line of text into a UChar* string from a UFILE. | |
U_CAPI UChar | u_fgetc (UFILE *f) |
Read a UChar from a UFILE. | |
U_CAPI UChar32 | u_fgetcx (UFILE *f) |
Read a UChar32 from a UFILE. | |
U_CAPI UChar32 | u_fungetc (UChar32 c, UFILE *f) |
Unget a UChar from a UFILE. | |
U_CAPI int32_t | u_file_read (UChar *chars, int32_t count, UFILE *f) |
Read Unicode from a UFILE. | |
U_CAPI UTransliterator * | u_fsettransliterator (UFILE *file, UFileDirection direction, UTransliterator *adopt, UErrorCode *status) |
Set a transliterator on the UFILE. | |
U_CAPI int32_t | u_sprintf (UChar *buffer, const char *patternSpecification,...) |
Write formatted data to a Unicode string. | |
U_CAPI int32_t | u_snprintf (UChar *buffer, int32_t count, const char *patternSpecification,...) |
Write formatted data to a Unicode string. | |
U_CAPI int32_t | u_vsprintf (UChar *buffer, const char *patternSpecification, va_list ap) |
Write formatted data to a Unicode string. | |
U_CAPI int32_t | u_vsnprintf (UChar *buffer, int32_t count, const char *patternSpecification, va_list ap) |
Write formatted data to a Unicode string. | |
U_CAPI int32_t | u_sprintf_u (UChar *buffer, const UChar *patternSpecification,...) |
Write formatted data to a Unicode string. | |
U_CAPI int32_t | u_snprintf_u (UChar *buffer, int32_t count, const UChar *patternSpecification,...) |
Write formatted data to a Unicode string. | |
U_CAPI int32_t | u_vsprintf_u (UChar *buffer, const UChar *patternSpecification, va_list ap) |
Write formatted data to a Unicode string. | |
U_CAPI int32_t | u_vsnprintf_u (UChar *buffer, int32_t count, const UChar *patternSpecification, va_list ap) |
Write formatted data to a Unicode string. | |
U_CAPI int32_t | u_sscanf (const UChar *buffer, const char *patternSpecification,...) |
Read formatted data from a Unicode string. | |
U_CAPI int32_t | u_vsscanf (const UChar *buffer, const char *patternSpecification, va_list ap) |
Read formatted data from a Unicode string. | |
U_CAPI int32_t | u_sscanf_u (const UChar *buffer, const UChar *patternSpecification,...) |
Read formatted data from a Unicode string. | |
U_CAPI int32_t | u_vsscanf_u (const UChar *buffer, const UChar *patternSpecification, va_list ap) |
Read formatted data from a Unicode string. | |
C API: Unicode stdio-like API.
This API provides an stdio-like API wrapper around ICU's other formatting and parsing APIs. It is meant to ease the transition of adding Unicode support to a preexisting applications using stdio. The following is a small list of noticeable differences between stdio and ICU I/O's ustdio implementation.
General printf format:
%[format modifier][width][.precision][type modifier][format]
General scanf format:
%[*][format modifier][width][type modifier][format]
format | default printf type | default scanf type | description |
E | double | float | Scientific with an uppercase exponent |
e | double | float | Scientific with a lowercase exponent |
G | double | float | Use E or f for best format |
g | double | float | Use e or f for best format |
f | double | float | Simple floating point without the exponent |
X | int32_t | int32_t | ustdio special uppercase hex radix formatting |
x | int32_t | int32_t | ustdio special lowercase hex radix formatting |
d | int32_t | int32_t | Decimal format |
i | int32_t | int32_t | Same as d |
n | int32_t | int32_t | count (write the number of UTF-16 codeunits read/written) |
o | int32_t | int32_t | ustdio special octal radix formatting |
u | uint32_t | uint32_t | Decimal format |
p | void * | void * | Prints the pointer value |
s | char * | char * | Use default converter or specified converter from fopen |
c | char | char | Use default converter or specified converter from fopen When width is specified for scanf, this acts like a non-NULL-terminated char * string. By default, only one char is written. |
S | UChar * | UChar * | Null terminated UTF-16 string |
C | UChar | UChar | 16-bit Unicode code unit When width is specified for scanf, this acts like a non-NULL-terminated UChar * string By default, only one codepoint is written. |
%[] | UChar * | Null terminated UTF-16 string which contains the filtered set of characters specified by the UnicodeSet | |
%% | Show a percent sign |
Format modifiers
modifier | formats | type | comments |
h | d, i, o, x | int16_t | short format |
h | u | uint16_t | short format |
h | c | char | (Unimplemented) Use invariant converter |
h | s | char * | (Unimplemented) Use invariant converter |
h | C | char | (Unimplemented) 8-bit Unicode code unit |
h | S | char * | (Unimplemented) Null terminated UTF-8 string |
l | d, i, o, x | int32_t | long format (no effect) |
l | u | uint32_t | long format (no effect) |
l | c | N/A | (Unimplemented) Reserved for future implementation |
l | s | N/A | (Unimplemented) Reserved for future implementation |
l | C | UChar32 | (Unimplemented) 32-bit Unicode code unit |
l | S | UChar32 * | (Unimplemented) Null terminated UTF-32 string |
ll | d, i, o, x | int64_t | long long format |
ll | u | uint64_t | (Unimplemented) long long format |
%- | all | N/A | Left justify |
%+ | d, i, o, x, e, f, g, E, G | N/A | Always show the plus or minus sign. Needs data for plus sign. |
% | d, i, o, x, e, f, g, E, G | N/A | Instead of a "+" output a blank character for positive numbers. |
%# | d, i, o, x, e, f, g, E, G | N/A | Precede octal value with 0, hex with 0x and show the decimal point for floats. |
%n | all | N/A | Width of input/output. num is an actual number from 0 to some large number. |
%.n | e, f, g, E, F, G | N/A | Significant digits precision. num is an actual number from 0 to some large number. If * is used in printf, then the precision is passed in as an argument before the number to be formatted. |
printf modifier %* int32_t Next argument after this one specifies the width
scanf modifier %* N/A This field is scanned, but not stored
If you are using this C API instead of the ustream.h API for C++, you can use one of the following u_fprintf examples to display a UnicodeString.
UFILE *out = u_finit(stdout, NULL, NULL);
UnicodeString string1("string 1");
UnicodeString string2("string 2");
u_fprintf(out, "%S\n", string1.getTerminatedBuffer());
u_fprintf(out, "%.*S\n", string2.length(), string2.getBuffer());
u_fclose(out);
Definition in file ustdio.h.
#define U_EOF 0xFFFF |
enum UFileDirection |
Enum for which direction of stream a transliterator applies to.
Open a UFILE on top of an existing FILE* stream.
The FILE* stream ownership is transferred to the new UFILE. It will be closed when the UFILE is closed.
f | The FILE* which this UFILE will take ownership of. |
locale | The locale whose conventions will be used to format and parse output. If this parameter is NULL, the default locale will be used. |
codepage | The codepage in which data will be written to and read from the file. If this parameter is NULL, data will be written and read using the default codepage for locale , unless locale is NULL, in which case the system default codepage will be used. |
Tests if the UFILE is at the end of the file stream.
f | The UFILE from which to read. |
Flush output of a UFILE.
Implies a flush of converter/transliterator state. (That is, a logical break is made in the output stream - for example if a different type of output is desired.) The underlying OS level file is also flushed. Note that for a stateful encoding, the converter may write additional bytes to return the stream to default state.
file | The UFILE to flush. |
Read a UChar from a UFILE.
It is recommended that u_fgetcx
used instead for proper parsing functions, but sometimes reading code units is needed instead of codepoints.
f | The UFILE from which to read. |
Get the codepage in which data is written to and read from the UFILE.
This is the same codepage passed in the preceding call to u_fsetcodepage
or u_fopen
.
file | The UFILE to query. |
U_CAPI UConverter * u_fgetConverter | ( | UFILE * | f | ) |
Returns an alias to the converter being used for this file.
f | The UFILE to get the value from |
Read a UChar32 from a UFILE.
f | The UFILE from which to read. |
Get the FILE* associated with a UFILE.
f | The UFILE |
Get the locale whose conventions are used to format and parse output.
This is the same locale passed in the preceding call tou_fsetlocale
or u_fopen
.
file | The UFILE to set. |
U_CAPI const UNumberFormat * u_fgetNumberFormat | ( | UFILE * | f | ) |
Returns an alias to the number formatter being used for this file.
f | The UFILE to get the value from |
Read one line of text into a UChar* string from a UFILE.
The newline at the end of the line is read into the string. The string is always null terminated
f | The UFILE from which to read. |
n | The maximum number of characters - 1 to read. |
s | The UChar* to receive the read data. Characters will be stored successively in s until a newline or EOF is reached. A null character (U+0000) will be appended to s . |
s
, or NULL if no characters were available. Read Unicode from a UFILE.
Bytes will be converted from the UFILE's underlying codepage, with subsequent conversion to Unicode. The data will not be NULL terminated.
chars | A pointer to receive the Unicode data. |
count | The number of Unicode characters to read. |
f | The UFILE from which to read. |
Write Unicode to a UFILE.
The ustring passed in will be converted to the UFILE's underlying codepage before it is written.
ustring | A pointer to the Unicode data to write. |
count | The number of Unicode characters to write |
f | The UFILE to which to write. |
Open a UFILE on top of an existing FILE* stream.
The FILE* stream ownership remains with the caller. To have the UFILE take over ownership and responsibility for the FILE* stream, use the function u_fadopt.
f | The FILE* to which this UFILE will attach and use. |
locale | The locale whose conventions will be used to format and parse output. If this parameter is NULL, the default locale will be used. |
codepage | The codepage in which data will be written to and read from the file. If this parameter is NULL, data will be written and read using the default codepage for locale , unless locale is NULL, in which case the system default codepage will be used. |
U_CAPI UFILE * u_fopen | ( | const char * | filename, |
const char * | perm, | ||
const char * | locale, | ||
const char * | codepage | ||
) |
Open a UFILE.
A UFILE is a wrapper around a FILE* that is locale and codepage aware. That is, data written to a UFILE will be formatted using the conventions specified by that UFILE's Locale; this data will be in the character set specified by that UFILE's codepage.
filename | The name of the file to open. Must be 0-terminated. |
perm | The read/write permission for the UFILE; one of "r", "w", "rw" |
locale | The locale whose conventions will be used to format and parse output. If this parameter is NULL, the default locale will be used. |
codepage | The codepage in which data will be written to and read from the file. If this parameter is NULL the system default codepage will be used. |
U_CAPI UFILE * u_fopen_u | ( | const UChar * | filename, |
const char * | perm, | ||
const char * | locale, | ||
const char * | codepage | ||
) |
Open a UFILE with a UChar* filename A UFILE is a wrapper around a FILE* that is locale and codepage aware.
That is, data written to a UFILE will be formatted using the conventions specified by that UFILE's Locale; this data will be in the character set specified by that UFILE's codepage.
filename | The name of the file to open. Must be 0-terminated. |
perm | The read/write permission for the UFILE; one of "r", "w", "rw" |
locale | The locale whose conventions will be used to format and parse output. If this parameter is NULL, the default locale will be used. |
codepage | The codepage in which data will be written to and read from the file. If this parameter is NULL the system default codepage will be used. |
Write formatted data to a UFILE.
f | The UFILE to which to write. |
patternSpecification | A pattern specifying how u_fprintf will interpret the variable arguments received and format the data. |
f
. Write formatted data to a UFILE.
f | The UFILE to which to write. |
patternSpecification | A pattern specifying how u_fprintf will interpret the variable arguments received and format the data. |
f
. Write a UChar to a UFILE.
uc | The UChar to write. |
f | The UFILE to which to write. |
Write a Unicode to a UFILE.
The null (U+0000) terminated UChar* s
will be written to f
, excluding the NULL terminator. A newline will be added to f
.
s | The UChar* to write. |
f | The UFILE to which to write. |
Rewind the file pointer to the beginning of the file.
file | The UFILE to rewind. |
Read formatted data from a UFILE.
f | The UFILE from which to read. |
patternSpecification | A pattern specifying how u_fscanf will interpret the variable arguments received and parse the data. |
Read formatted data from a UFILE.
f | The UFILE from which to read. |
patternSpecification | A pattern specifying how u_fscanf will interpret the variable arguments received and parse the data. |
Set the codepage in which data will be written to and read from the UFILE.
All Unicode data written to the UFILE will be converted to this codepage before it is written to the underlying FILE*. It it generally a bad idea to mix codepages within a file. This should only be called right after opening the UFile
, or after calling u_frewind
.
codepage | The codepage in which data will be written to and read from the file. For example "latin-1" or "ibm-943" . A value of NULL means the default codepage for the UFILE's current locale will be used. |
file | The UFILE to set. |
Set the locale whose conventions will be used to format and parse output.
locale | The locale whose conventions will be used to format and parse output. |
file | The UFILE to query. |
U_CAPI UTransliterator * u_fsettransliterator | ( | UFILE * | file, |
UFileDirection | direction, | ||
UTransliterator * | adopt, | ||
UErrorCode * | status | ||
) |
Set a transliterator on the UFILE.
The transliterator will be owned by the UFILE.
file | The UFILE to set transliteration on |
adopt | The UTransliterator to set. Can be NULL, which will mean that no transliteration is used. |
direction | either U_READ, U_WRITE, or U_READWRITE - sets which direction the transliterator is to be applied to. If U_READWRITE, the "Read" transliteration will be in the inverse direction. |
status | ICU error code. |
Create a UFILE that can be used for localized formatting or parsing.
The u_sprintf and u_sscanf functions do not read or write numbers for a specific locale. The ustdio.h file functions can be used on this UFILE. The string is usable once u_fclose or u_fflush has been called on the returned UFILE.
stringBuf | The string used for reading or writing. |
capacity | The number of code units available for use in stringBuf |
locale | The locale whose conventions will be used to format and parse output. If this parameter is NULL, the default locale will be used. |
Unget a UChar from a UFILE.
If this function is not the first to operate on f
after a call to u_fgetc
, the results are undefined. If this function is passed a character that was not received from the previous u_fgetc
or u_fgetcx
call, the results are undefined.
c | The UChar to put back on the stream. |
f | The UFILE to receive c . |
U_CAPI int32_t u_printf | ( | const char * | patternSpecification, |
... | |||
) |
Write formatted data to stdout
.
patternSpecification | A pattern specifying how u_printf will interpret the variable arguments received and format the data. |
stdout
Write formatted data to stdout
.
patternSpecification | A pattern specifying how u_printf_u will interpret the variable arguments received and format the data. |
stdout
Write formatted data to a Unicode string.
When the number of code units required to store the data exceeds count
, then count
code units of data are stored in buffer
and a negative value is returned. When the number of code units required to store the data equals count
, the string is not null terminated and count
is returned.
buffer | The Unicode String to which to write. |
count | The number of code units to read. |
patternSpecification | A pattern specifying how u_sprintf will interpret the variable arguments received and format the data. |
buffer
had count been sufficiently large. This does not include the terminating null character. U_CAPI int32_t u_snprintf_u | ( | UChar * | buffer, |
int32_t | count, | ||
const UChar * | patternSpecification, | ||
... | |||
) |
Write formatted data to a Unicode string.
When the number of code units required to store the data exceeds count
, then count
code units of data are stored in buffer
and a negative value is returned. When the number of code units required to store the data equals count
, the string is not null terminated and count
is returned.
buffer | The Unicode string to which to write. |
count | The number of code units to read. |
patternSpecification | A pattern specifying how u_sprintf will interpret the variable arguments received and format the data. |
buffer
had count been sufficiently large. Write formatted data to a Unicode string.
buffer | The Unicode String to which to write. |
patternSpecification | A pattern specifying how u_sprintf will interpret the variable arguments received and format the data. |
buffer
. This does not include the terminating null character. Write formatted data to a Unicode string.
buffer | The Unicode string to which to write. |
patternSpecification | A pattern specifying how u_sprintf will interpret the variable arguments received and format the data. |
buffer
. Read formatted data from a Unicode string.
buffer | The Unicode string from which to read. |
patternSpecification | A pattern specifying how u_sscanf will interpret the variable arguments received and parse the data. |
Read formatted data from a Unicode string.
buffer | The Unicode string from which to read. |
patternSpecification | A pattern specifying how u_sscanf will interpret the variable arguments received and parse the data. |
Write formatted data to a UFILE.
This is identical to u_fprintf
, except that it will not call va_start
and va_end
.
f | The UFILE to which to write. |
patternSpecification | A pattern specifying how u_fprintf will interpret the variable arguments received and format the data. |
ap | The argument list to use. |
f
. Write formatted data to a UFILE.
This is identical to u_fprintf_u
, except that it will not call va_start
and va_end
.
f | The UFILE to which to write. |
patternSpecification | A pattern specifying how u_fprintf will interpret the variable arguments received and format the data. |
ap | The argument list to use. |
f
. Read formatted data from a UFILE.
This is identical to u_fscanf
, except that it will not call va_start
and va_end
.
f | The UFILE from which to read. |
patternSpecification | A pattern specifying how u_fscanf will interpret the variable arguments received and parse the data. |
ap | The argument list to use. |
Read formatted data from a UFILE.
This is identical to u_fscanf_u
, except that it will not call va_start
and va_end
.
f | The UFILE from which to read. |
patternSpecification | A pattern specifying how u_fscanf will interpret the variable arguments received and parse the data. |
ap | The argument list to use. |
U_CAPI int32_t u_vsnprintf | ( | UChar * | buffer, |
int32_t | count, | ||
const char * | patternSpecification, | ||
va_list | ap | ||
) |
Write formatted data to a Unicode string.
This is identical to u_snprintf
, except that it will not call va_start
and va_end
.
When the number of code units required to store the data exceeds count
, then count
code units of data are stored in buffer
and a negative value is returned. When the number of code units required to store the data equals count
, the string is not null terminated and count
is returned.
buffer | The Unicode string to which to write. |
count | The number of code units to read. |
patternSpecification | A pattern specifying how u_sprintf will interpret the variable arguments received and format the data. |
ap | The argument list to use. |
buffer
had count been sufficiently large. U_CAPI int32_t u_vsnprintf_u | ( | UChar * | buffer, |
int32_t | count, | ||
const UChar * | patternSpecification, | ||
va_list | ap | ||
) |
Write formatted data to a Unicode string.
This is identical to u_snprintf_u
, except that it will not call va_start
and va_end
. When the number of code units required to store the data exceeds count
, then count
code units of data are stored in buffer
and a negative value is returned. When the number of code units required to store the data equals count
, the string is not null terminated and count
is returned.
buffer | The Unicode string to which to write. |
count | The number of code units to read. |
patternSpecification | A pattern specifying how u_sprintf will interpret the variable arguments received and format the data. |
ap | The argument list to use. |
f
had count been sufficiently large. Write formatted data to a Unicode string.
This is identical to u_sprintf
, except that it will not call va_start
and va_end
.
buffer | The Unicode string to which to write. |
patternSpecification | A pattern specifying how u_sprintf will interpret the variable arguments received and format the data. |
ap | The argument list to use. |
buffer
. Write formatted data to a Unicode string.
This is identical to u_sprintf_u
, except that it will not call va_start
and va_end
.
buffer | The Unicode string to which to write. |
patternSpecification | A pattern specifying how u_sprintf will interpret the variable arguments received and format the data. |
ap | The argument list to use. |
f
. Read formatted data from a Unicode string.
This is identical to u_sscanf
, except that it will not call va_start
and va_end
.
buffer | The Unicode string from which to read. |
patternSpecification | A pattern specifying how u_sscanf will interpret the variable arguments received and parse the data. |
ap | The argument list to use. |
Read formatted data from a Unicode string.
This is identical to u_sscanf_u
, except that it will not call va_start
and va_end
.
buffer | The Unicode string from which to read. |
patternSpecification | A pattern specifying how u_sscanf will interpret the variable arguments received and parse the data. |
ap | The argument list to use. |