ICU 64.2  64.2
Macros | Variables
utf_old.h File Reference

C API: Deprecated macros for Unicode string handling. More...

#include "unicode/utf.h"
#include "unicode/utf8.h"
#include "unicode/utf16.h"

Go to the source code of this file.

Macros

#define U_HIDE_OBSOLETE_UTF_OLD_H   0
 The macros in utf_old.h are all deprecated and their use discouraged. More...
 
#define UTF_SIZE   16
 Number of bits in a Unicode string code unit - ICU uses 16-bit Unicode. More...
 
#define UTF_SAFE
 The default choice for general Unicode string macros is to use the ..._SAFE macro implementations with strict=FALSE. More...
 
#define UTF8_ERROR_VALUE_1   0x15
 UTF8_ERROR_VALUE_1 and UTF8_ERROR_VALUE_2 are special error values for UTF-8, which need 1 or 2 bytes in UTF-8: More...
 
#define UTF8_ERROR_VALUE_2   0x9f
 See documentation on UTF8_ERROR_VALUE_1 for details. More...
 
#define UTF_ERROR_VALUE   0xffff
 Error value for all UTFs. More...
 
#define UTF_IS_ERROR(c)   (((c)&0xfffe)==0xfffe || (c)==UTF8_ERROR_VALUE_1 || (c)==UTF8_ERROR_VALUE_2)
 Is a given 32-bit code an error value as returned by one of the macros for any UTF? More...
 
#define UTF_IS_VALID(c)
 This is a combined macro: Is c a valid Unicode value and not an error code? More...
 
#define UTF_IS_SURROGATE(uchar)   (((uchar)&0xfffff800)==0xd800)
 Is this code unit or code point a surrogate (U+d800..U+dfff)? More...
 
#define UTF_IS_UNICODE_NONCHAR(c)
 Is a given 32-bit code point a Unicode noncharacter? More...
 
#define UTF_IS_UNICODE_CHAR(c)
 Is a given 32-bit value a Unicode code point value (0..U+10ffff) that can be assigned a character? More...
 
#define UTF8_COUNT_TRAIL_BYTES(leadByte)   (utf8_countTrailBytes[(uint8_t)leadByte])
 Count the trail bytes for a UTF-8 lead byte. More...
 
#define UTF8_MASK_LEAD_BYTE(leadByte, countTrailBytes)   ((leadByte)&=(1<<(6-(countTrailBytes)))-1)
 Mask a UTF-8 lead byte, leave only the lower bits that form part of the code point value. More...
 
#define UTF8_IS_SINGLE(uchar)   (((uchar)&0x80)==0)
 Is this this code point a single code unit (byte)? More...
 
#define UTF8_IS_LEAD(uchar)   ((uint8_t)((uchar)-0xc0)<0x3e)
 Is this this code unit the lead code unit (byte) of a code point? More...
 
#define UTF8_IS_TRAIL(uchar)   (((uchar)&0xc0)==0x80)
 Is this this code unit a trailing code unit (byte) of a code point? More...
 
#define UTF8_NEED_MULTIPLE_UCHAR(c)   ((uint32_t)(c)>0x7f)
 Does this scalar Unicode value need multiple code units for storage? More...
 
#define UTF8_CHAR_LENGTH(c)
 Given the lead character, how many bytes are taken by this code point. More...
 
#define UTF8_MAX_CHAR_LENGTH   4
 The maximum number of bytes per code point. More...
 
#define UTF8_ARRAY_SIZE(size)   ((5*(size))/2)
 Average number of code units compared to UTF-16. More...
 
#define UTF8_GET_CHAR_UNSAFE(s, i, c)
 
#define UTF8_GET_CHAR_SAFE(s, start, i, length, c, strict)
 
#define UTF8_NEXT_CHAR_UNSAFE(s, i, c)
 
#define UTF8_APPEND_CHAR_UNSAFE(s, i, c)
 
#define UTF8_FWD_1_UNSAFE(s, i)
 
#define UTF8_FWD_N_UNSAFE(s, i, n)
 
#define UTF8_SET_CHAR_START_UNSAFE(s, i)
 
#define UTF8_NEXT_CHAR_SAFE(s, i, length, c, strict)
 
#define UTF8_APPEND_CHAR_SAFE(s, i, length, c)
 
#define UTF8_FWD_1_SAFE(s, i, length)   U8_FWD_1(s, i, length)
 
#define UTF8_FWD_N_SAFE(s, i, length, n)   U8_FWD_N(s, i, length, n)
 
#define UTF8_SET_CHAR_START_SAFE(s, start, i)   U8_SET_CP_START(s, start, i)
 
#define UTF8_PREV_CHAR_UNSAFE(s, i, c)
 
#define UTF8_BACK_1_UNSAFE(s, i)
 
#define UTF8_BACK_N_UNSAFE(s, i, n)
 
#define UTF8_SET_CHAR_LIMIT_UNSAFE(s, i)
 
#define UTF8_PREV_CHAR_SAFE(s, start, i, c, strict)
 
#define UTF8_BACK_1_SAFE(s, start, i)   U8_BACK_1(s, start, i)
 
#define UTF8_BACK_N_SAFE(s, start, i, n)   U8_BACK_N(s, start, i, n)
 
#define UTF8_SET_CHAR_LIMIT_SAFE(s, start, i, length)   U8_SET_CP_LIMIT(s, start, i, length)
 
#define UTF_IS_FIRST_SURROGATE(uchar)   (((uchar)&0xfffffc00)==0xd800)
 Is uchar a first/lead surrogate? More...
 
#define UTF_IS_SECOND_SURROGATE(uchar)   (((uchar)&0xfffffc00)==0xdc00)
 Is uchar a second/trail surrogate? More...
 
#define UTF_IS_SURROGATE_FIRST(c)   (((c)&0x400)==0)
 Assuming c is a surrogate, is it a first/lead surrogate? More...
 
#define UTF_SURROGATE_OFFSET   ((0xd800<<10UL)+0xdc00-0x10000)
 Helper constant for UTF16_GET_PAIR_VALUE. More...
 
#define UTF16_GET_PAIR_VALUE(first, second)   (((first)<<10UL)+(second)-UTF_SURROGATE_OFFSET)
 Get the UTF-32 value from the surrogate code units. More...
 
#define UTF_FIRST_SURROGATE(supplementary)   (UChar)(((supplementary)>>10)+0xd7c0)
 
#define UTF_SECOND_SURROGATE(supplementary)   (UChar)(((supplementary)&0x3ff)|0xdc00)
 
#define UTF16_LEAD(supplementary)   UTF_FIRST_SURROGATE(supplementary)
 
#define UTF16_TRAIL(supplementary)   UTF_SECOND_SURROGATE(supplementary)
 
#define UTF16_IS_SINGLE(uchar)   !UTF_IS_SURROGATE(uchar)
 
#define UTF16_IS_LEAD(uchar)   UTF_IS_FIRST_SURROGATE(uchar)
 
#define UTF16_IS_TRAIL(uchar)   UTF_IS_SECOND_SURROGATE(uchar)
 
#define UTF16_NEED_MULTIPLE_UCHAR(c)   ((uint32_t)(c)>0xffff)
 Does this scalar Unicode value need multiple code units for storage? More...
 
#define UTF16_CHAR_LENGTH(c)   ((uint32_t)(c)<=0xffff ? 1 : 2)
 
#define UTF16_MAX_CHAR_LENGTH   2
 
#define UTF16_ARRAY_SIZE(size)   (size)
 Average number of code units compared to UTF-16. More...
 
#define UTF16_GET_CHAR_UNSAFE(s, i, c)
 Get a single code point from an offset that points to any of the code units that belong to that code point. More...
 
#define UTF16_GET_CHAR_SAFE(s, start, i, length, c, strict)
 
#define UTF16_NEXT_CHAR_UNSAFE(s, i, c)
 
#define UTF16_APPEND_CHAR_UNSAFE(s, i, c)
 
#define UTF16_FWD_1_UNSAFE(s, i)
 
#define UTF16_FWD_N_UNSAFE(s, i, n)
 
#define UTF16_SET_CHAR_START_UNSAFE(s, i)
 
#define UTF16_NEXT_CHAR_SAFE(s, i, length, c, strict)
 
#define UTF16_APPEND_CHAR_SAFE(s, i, length, c)
 
#define UTF16_FWD_1_SAFE(s, i, length)   U16_FWD_1(s, i, length)
 
#define UTF16_FWD_N_SAFE(s, i, length, n)   U16_FWD_N(s, i, length, n)
 
#define UTF16_SET_CHAR_START_SAFE(s, start, i)   U16_SET_CP_START(s, start, i)
 
#define UTF16_PREV_CHAR_UNSAFE(s, i, c)
 
#define UTF16_BACK_1_UNSAFE(s, i)
 
#define UTF16_BACK_N_UNSAFE(s, i, n)
 
#define UTF16_SET_CHAR_LIMIT_UNSAFE(s, i)
 
#define UTF16_PREV_CHAR_SAFE(s, start, i, c, strict)
 
#define UTF16_BACK_1_SAFE(s, start, i)   U16_BACK_1(s, start, i)
 
#define UTF16_BACK_N_SAFE(s, start, i, n)   U16_BACK_N(s, start, i, n)
 
#define UTF16_SET_CHAR_LIMIT_SAFE(s, start, i, length)   U16_SET_CP_LIMIT(s, start, i, length)
 
#define UTF32_IS_SAFE(c, strict)
 
#define UTF32_IS_SINGLE(uchar)   1
 
#define UTF32_IS_LEAD(uchar)   0
 
#define UTF32_IS_TRAIL(uchar)   0
 
#define UTF32_NEED_MULTIPLE_UCHAR(c)   0
 
#define UTF32_CHAR_LENGTH(c)   1
 
#define UTF32_MAX_CHAR_LENGTH   1
 
#define UTF32_ARRAY_SIZE(size)   (size)
 
#define UTF32_GET_CHAR_UNSAFE(s, i, c)
 
#define UTF32_GET_CHAR_SAFE(s, start, i, length, c, strict)
 
#define UTF32_NEXT_CHAR_UNSAFE(s, i, c)
 
#define UTF32_APPEND_CHAR_UNSAFE(s, i, c)
 
#define UTF32_FWD_1_UNSAFE(s, i)
 
#define UTF32_FWD_N_UNSAFE(s, i, n)
 
#define UTF32_SET_CHAR_START_UNSAFE(s, i)
 
#define UTF32_NEXT_CHAR_SAFE(s, i, length, c, strict)
 
#define UTF32_APPEND_CHAR_SAFE(s, i, length, c)
 
#define UTF32_FWD_1_SAFE(s, i, length)
 
#define UTF32_FWD_N_SAFE(s, i, length, n)
 
#define UTF32_SET_CHAR_START_SAFE(s, start, i)
 
#define UTF32_PREV_CHAR_UNSAFE(s, i, c)
 
#define UTF32_BACK_1_UNSAFE(s, i)
 
#define UTF32_BACK_N_UNSAFE(s, i, n)
 
#define UTF32_SET_CHAR_LIMIT_UNSAFE(s, i)
 
#define UTF32_PREV_CHAR_SAFE(s, start, i, c, strict)
 
#define UTF32_BACK_1_SAFE(s, start, i)
 
#define UTF32_BACK_N_SAFE(s, start, i, n)
 
#define UTF32_SET_CHAR_LIMIT_SAFE(s, i, length)
 
#define UTF_ARRAY_SIZE(size)   UTF16_ARRAY_SIZE(size)
 Estimate the number of code units for a string based on the number of UTF-16 code units. More...
 
#define UTF_GET_CHAR_UNSAFE(s, i, c)   UTF16_GET_CHAR_UNSAFE(s, i, c)
 
#define UTF_GET_CHAR_SAFE(s, start, i, length, c, strict)   UTF16_GET_CHAR_SAFE(s, start, i, length, c, strict)
 
#define UTF_NEXT_CHAR_UNSAFE(s, i, c)   UTF16_NEXT_CHAR_UNSAFE(s, i, c)
 
#define UTF_NEXT_CHAR_SAFE(s, i, length, c, strict)   UTF16_NEXT_CHAR_SAFE(s, i, length, c, strict)
 
#define UTF_APPEND_CHAR_UNSAFE(s, i, c)   UTF16_APPEND_CHAR_UNSAFE(s, i, c)
 
#define UTF_APPEND_CHAR_SAFE(s, i, length, c)   UTF16_APPEND_CHAR_SAFE(s, i, length, c)
 
#define UTF_FWD_1_UNSAFE(s, i)   UTF16_FWD_1_UNSAFE(s, i)
 
#define UTF_FWD_1_SAFE(s, i, length)   UTF16_FWD_1_SAFE(s, i, length)
 
#define UTF_FWD_N_UNSAFE(s, i, n)   UTF16_FWD_N_UNSAFE(s, i, n)
 
#define UTF_FWD_N_SAFE(s, i, length, n)   UTF16_FWD_N_SAFE(s, i, length, n)
 
#define UTF_SET_CHAR_START_UNSAFE(s, i)   UTF16_SET_CHAR_START_UNSAFE(s, i)
 
#define UTF_SET_CHAR_START_SAFE(s, start, i)   UTF16_SET_CHAR_START_SAFE(s, start, i)
 
#define UTF_PREV_CHAR_UNSAFE(s, i, c)   UTF16_PREV_CHAR_UNSAFE(s, i, c)
 
#define UTF_PREV_CHAR_SAFE(s, start, i, c, strict)   UTF16_PREV_CHAR_SAFE(s, start, i, c, strict)
 
#define UTF_BACK_1_UNSAFE(s, i)   UTF16_BACK_1_UNSAFE(s, i)
 
#define UTF_BACK_1_SAFE(s, start, i)   UTF16_BACK_1_SAFE(s, start, i)
 
#define UTF_BACK_N_UNSAFE(s, i, n)   UTF16_BACK_N_UNSAFE(s, i, n)
 
#define UTF_BACK_N_SAFE(s, start, i, n)   UTF16_BACK_N_SAFE(s, start, i, n)
 
#define UTF_SET_CHAR_LIMIT_UNSAFE(s, i)   UTF16_SET_CHAR_LIMIT_UNSAFE(s, i)
 
#define UTF_SET_CHAR_LIMIT_SAFE(s, start, i, length)   UTF16_SET_CHAR_LIMIT_SAFE(s, start, i, length)
 
#define UTF_IS_SINGLE(uchar)   U16_IS_SINGLE(uchar)
 Does this code unit alone encode a code point (BMP, not a surrogate)? Same as UTF16_IS_SINGLE. More...
 
#define UTF_IS_LEAD(uchar)   U16_IS_LEAD(uchar)
 Is this code unit the first one of several (a lead surrogate)? Same as UTF16_IS_LEAD. More...
 
#define UTF_IS_TRAIL(uchar)   U16_IS_TRAIL(uchar)
 Is this code unit one of several but not the first one (a trail surrogate)? Same as UTF16_IS_TRAIL. More...
 
#define UTF_NEED_MULTIPLE_UCHAR(c)   UTF16_NEED_MULTIPLE_UCHAR(c)
 Does this code point require multiple code units (is it a supplementary code point)? Same as UTF16_NEED_MULTIPLE_UCHAR. More...
 
#define UTF_CHAR_LENGTH(c)   U16_LENGTH(c)
 How many code units are used to encode this code point (1 or 2)? Same as UTF16_CHAR_LENGTH. More...
 
#define UTF_MAX_CHAR_LENGTH   U16_MAX_LENGTH
 How many code units are used at most for any Unicode code point (2)? Same as UTF16_MAX_CHAR_LENGTH. More...
 
#define UTF_GET_CHAR(s, start, i, length, c)   U16_GET(s, start, i, length, c)
 Set c to the code point that contains the code unit i. More...
 
#define UTF_NEXT_CHAR(s, i, length, c)   U16_NEXT(s, i, length, c)
 Set c to the code point that starts at code unit i and advance i to beyond the code units of this code point (post-increment). More...
 
#define UTF_APPEND_CHAR(s, i, length, c)   UTF16_APPEND_CHAR_SAFE(s, i, length, c)
 Append the code units of code point c to the string at index i and advance i to beyond the new code units (post-increment). More...
 
#define UTF_FWD_1(s, i, length)   U16_FWD_1(s, i, length)
 Advance i to beyond the code units of the code point that begins at i. More...
 
#define UTF_FWD_N(s, i, length, n)   U16_FWD_N(s, i, length, n)
 Advance i to beyond the code units of the n code points where the first one begins at i. More...
 
#define UTF_SET_CHAR_START(s, start, i)   U16_SET_CP_START(s, start, i)
 Take the random-access index i and adjust it so that it points to the beginning of a code point. More...
 
#define UTF_PREV_CHAR(s, start, i, c)   U16_PREV(s, start, i, c)
 Set c to the code point that has code units before i and move i backward (towards the beginning of the string) to the first code unit of this code point (pre-increment). More...
 
#define UTF_BACK_1(s, start, i)   U16_BACK_1(s, start, i)
 Move i backward (towards the beginning of the string) to the first code unit of the code point that has code units before i. More...
 
#define UTF_BACK_N(s, start, i, n)   U16_BACK_N(s, start, i, n)
 Move i backward (towards the beginning of the string) to the first code unit of the n code points that have code units before i. More...
 
#define UTF_SET_CHAR_LIMIT(s, start, i, length)   U16_SET_CP_LIMIT(s, start, i, length)
 Take the random-access index i and adjust it so that it points beyond a code point. More...
 

Variables

U_CFUNC U_IMPORT const uint8_t utf8_countTrailBytes []
 Internal array with numbers of trail bytes for any given byte used in lead byte position. More...
 

Detailed Description

C API: Deprecated macros for Unicode string handling.

Definition in file utf_old.h.

Macro Definition Documentation

◆ U_HIDE_OBSOLETE_UTF_OLD_H

#define U_HIDE_OBSOLETE_UTF_OLD_H   0

The macros in utf_old.h are all deprecated and their use discouraged.

Some of the design principles behind the set of UTF macros have changed or proved impractical. Almost all of the old "UTF macros" are at least renamed. If you are looking for a new equivalent to an old macro, please see the comment at the old one.

Brief summary of reasons for deprecation:

  • Switch on UTF_SIZE (selection of UTF-8/16/32 default string processing) was impractical.
  • Switch on UTF_SAFE etc. (selection of unsafe/safe/strict default string processing) was of little use and impractical.
  • Whole classes of macros became obsolete outside of the UTF_SIZE/UTF_SAFE selection framework: UTF32_ macros (all trivial) and UTF_ default and intermediate macros (all aliases).
  • The selection framework also caused many macro aliases.
  • Change in Unicode standard: "irregular" sequences (3.0) became illegal (3.2).
  • Change of language in Unicode standard: Growing distinction between internal x-bit Unicode strings and external UTF-x forms, with the former more lenient. Suggests renaming of UTF16_ macros to U16_.
  • The prefix "UTF_" without a width number confused some users.
  • "Safe" append macros needed the addition of an error indicator output.
  • "Safe" UTF-8 macros used legitimate (if rarely used) code point values to indicate error conditions.
  • The use of the "_CHAR" infix for code point operations confused some users.

More details:

Until ICU 2.2, utf.h theoretically allowed to choose among UTF-8/16/32 for string processing, and among unsafe/safe/strict default macros for that.

It proved nearly impossible to write non-trivial, high-performance code that is UTF-generic. Unsafe default macros would be dangerous for default string processing, and the main reason for the "strict" versions disappeared: Between Unicode 3.0 and 3.2 all "irregular" UTF-8 sequences became illegal. The only other conditions that "strict" checked for were non-characters, which are valid during processing. Only during text input/output should they be checked, and at that time other well-formedness checks may be necessary or useful as well. This can still be done by using U16_NEXT and U_IS_UNICODE_NONCHAR or U_IS_UNICODE_CHAR.

The old UTF8_..._SAFE macros also used some normal Unicode code points to indicate malformed sequences. The new UTF8_ macros without suffix use negative values instead.

The entire contents of utf32.h was moved here without replacement because all those macros were trivial and were meaningful only in the framework of choosing the UTF size.

See Jitterbug 2150 and its discussion on the ICU mailing list in September 2002.

Obsolete part of pre-ICU 2.4 utf.h file documentation:

The original concept for these files was for ICU to allow in principle to set which UTF (UTF-8/16/32) is used internally by defining UTF_SIZE to either 8, 16, or 32. utf.h would then define the UChar type accordingly. UTF-16 was the default.

This concept has been abandoned. A lot of the ICU source code assumes UChar strings are in UTF-16. This is especially true for low-level code like conversion, normalization, and collation. The utf.h header enforces the default of UTF-16. The UTF-8 and UTF-32 macros remain for now for completeness and backward compatibility.

Accordingly, utf.h defines UChar to be an unsigned 16-bit integer. If this matches wchar_t, then UChar is defined to be exactly wchar_t, otherwise uint16_t.

UChar32 is defined to be a signed 32-bit integer (int32_t), large enough for a 21-bit Unicode code point (Unicode scalar value, 0..0x10ffff). Before ICU 2.4, the definition of UChar32 was similarly platform-dependent as the definition of UChar. For details see the documentation for UChar32 itself.

utf.h also defines a number of C macros for handling single Unicode code points and for using UTF Unicode strings. It includes utf8.h, utf16.h, and utf32.h for the actual implementations of those macros and then aliases one set of them (for UTF-16) for general use. The UTF-specific macros have the UTF size in the macro name prefixes (UTF16_...), while the general alias macros always begin with UTF_...

Many string operations can be done with or without error checking. Where such a distinction is useful, there are two versions of the macros, "unsafe" and "safe" ones with ..._UNSAFE and ..._SAFE suffixes. The unsafe macros are fast but may cause program failures if the strings are not well-formed. The safe macros have an additional, boolean parameter "strict". If strict is FALSE, then only illegal sequences are detected. Otherwise, irregular sequences and non-characters are detected as well (like single surrogates). Safe macros return special error code points for illegal/irregular sequences: Typically, U+ffff, or values that would result in a code unit sequence of the same length as the erroneous input sequence.
Note that _UNSAFE macros have fewer parameters: They do not have the strictness parameter, and they do not have start/length parameters for boundary checking.

Here, the macros are aliased in two steps: In the first step, the UTF-specific macros with UTF16_ prefix and UNSAFE and _SAFE suffixes are aliased according to the UTF_SIZE to macros with UTF prefix and the same suffixes and signatures. Then, in a second step, the default, general alias macros are set to use either the unsafe or the safe/not strict (default) or the safe/strict macro; these general macros do not have a strictness parameter.

It is possible to change the default choice for the general alias macros to be unsafe, safe/not strict or safe/strict. The default is safe/not strict. It is not recommended to select the unsafe macros as the basis for Unicode string handling in ICU! To select this, define UTF_SAFE, UTF_STRICT, or UTF_UNSAFE.

For general use, one should use the default, general macros with UTF_ prefix and no SAFE/_UNSAFE suffix. Only in some cases it may be necessary to control the choice of macro directly and use a less generic alias. For example, if it can be assumed that a string is well-formed and the index will stay within the bounds, then the _UNSAFE version may be used. If a UTF-8 string is to be processed, then the macros with UTF8 prefixes need to be used.

Deprecated:
ICU 2.4. Use the macros in utf.h, utf16.h, utf8.h instead.

Hides the obsolete definitions in unicode/utf_old.h. Recommended to be set to 1 at compile time to make sure the long-deprecated macros are no longer used.

For reasons for the deprecation see the utf_old.h file comments.

Internal:
Do not use. This API is for internal use only.

Definition at line 160 of file utf_old.h.

◆ UTF16_APPEND_CHAR_SAFE

#define UTF16_APPEND_CHAR_SAFE (   s,
  i,
  length,
  c 
)
Value:
{ \
if((uint32_t)(c)<=0xffff) { \
(s)[(i)++]=(uint16_t)(c); \
} else if((uint32_t)(c)<=0x10ffff) { \
if((i)+1<(length)) { \
(s)[(i)++]=(uint16_t)(((c)>>10)+0xd7c0); \
(s)[(i)++]=(uint16_t)(((c)&0x3ff)|0xdc00); \
} else /* not enough space */ { \
(s)[(i)++]=UTF_ERROR_VALUE; \
} \
} else /* c>0x10ffff, write error value */ { \
(s)[(i)++]=UTF_ERROR_VALUE; \
} \
}
UTF_ERROR_VALUE
#define UTF_ERROR_VALUE
Error value for all UTFs.
Definition: utf_old.h:226
Deprecated:
ICU 2.4.

Use U16_APPEND instead, see utf_old.h.

Definition at line 695 of file utf_old.h.

◆ UTF16_APPEND_CHAR_UNSAFE

#define UTF16_APPEND_CHAR_UNSAFE (   s,
  i,
  c 
)
Value:
{ \
if((uint32_t)(c)<=0xffff) { \
(s)[(i)++]=(uint16_t)(c); \
} else { \
(s)[(i)++]=(uint16_t)(((c)>>10)+0xd7c0); \
(s)[(i)++]=(uint16_t)(((c)&0x3ff)|0xdc00); \
} \
}
Deprecated:
ICU 2.4.

Renamed to U16_APPEND_UNSAFE, see utf_old.h.

Definition at line 643 of file utf_old.h.

◆ UTF16_ARRAY_SIZE

#define UTF16_ARRAY_SIZE (   size)    (size)

Average number of code units compared to UTF-16.

Deprecated:
ICU 2.4. Obsolete, see utf_old.h.

Definition at line 583 of file utf_old.h.

◆ UTF16_BACK_1_SAFE

#define UTF16_BACK_1_SAFE (   s,
  start,
  i 
)    U16_BACK_1(s, start, i)
Deprecated:
ICU 2.4.

Renamed to U16_BACK_1, see utf_old.h.

Definition at line 770 of file utf_old.h.

◆ UTF16_BACK_1_UNSAFE

#define UTF16_BACK_1_UNSAFE (   s,
  i 
)
Value:
{ \
if(UTF_IS_SECOND_SURROGATE((s)[--(i)])) { \
--(i); \
} \
}
UTF_IS_SECOND_SURROGATE
#define UTF_IS_SECOND_SURROGATE(uchar)
Is uchar a second/trail surrogate?
Definition: utf_old.h:540
Deprecated:
ICU 2.4.

Renamed to U16_BACK_1_UNSAFE, see utf_old.h.

Definition at line 728 of file utf_old.h.

◆ UTF16_BACK_N_SAFE

#define UTF16_BACK_N_SAFE (   s,
  start,
  i,
  n 
)    U16_BACK_N(s, start, i, n)
Deprecated:
ICU 2.4.

Renamed to U16_BACK_N, see utf_old.h.

Definition at line 773 of file utf_old.h.

◆ UTF16_BACK_N_UNSAFE

#define UTF16_BACK_N_UNSAFE (   s,
  i,
  n 
)
Value:
{ \
int32_t __N=(n); \
while(__N>0) { \
UTF16_BACK_1_UNSAFE(s, i); \
--__N; \
} \
}
Deprecated:
ICU 2.4.

Renamed to U16_BACK_N_UNSAFE, see utf_old.h.

Definition at line 735 of file utf_old.h.

◆ UTF16_CHAR_LENGTH

#define UTF16_CHAR_LENGTH (   c)    ((uint32_t)(c)<=0xffff ? 1 : 2)
Deprecated:
ICU 2.4.

Renamed to U16_LENGTH, see utf_old.h.

Definition at line 577 of file utf_old.h.

◆ UTF16_FWD_1_SAFE

#define UTF16_FWD_1_SAFE (   s,
  i,
  length 
)    U16_FWD_1(s, i, length)
Deprecated:
ICU 2.4.

Renamed to U16_FWD_1, see utf_old.h.

Definition at line 711 of file utf_old.h.

◆ UTF16_FWD_1_UNSAFE

#define UTF16_FWD_1_UNSAFE (   s,
  i 
)
Value:
{ \
if(UTF_IS_FIRST_SURROGATE((s)[(i)++])) { \
++(i); \
} \
}
UTF_IS_FIRST_SURROGATE
#define UTF_IS_FIRST_SURROGATE(uchar)
Is uchar a first/lead surrogate?
Definition: utf_old.h:537
Deprecated:
ICU 2.4.

Renamed to U16_FWD_1_UNSAFE, see utf_old.h.

Definition at line 653 of file utf_old.h.

◆ UTF16_FWD_N_SAFE

#define UTF16_FWD_N_SAFE (   s,
  i,
  length,
  n 
)    U16_FWD_N(s, i, length, n)
Deprecated:
ICU 2.4.

Renamed to U16_FWD_N, see utf_old.h.

Definition at line 714 of file utf_old.h.

◆ UTF16_FWD_N_UNSAFE

#define UTF16_FWD_N_UNSAFE (   s,
  i,
  n 
)
Value:
{ \
int32_t __N=(n); \
while(__N>0) { \
UTF16_FWD_1_UNSAFE(s, i); \
--__N; \
} \
}
Deprecated:
ICU 2.4.

Renamed to U16_FWD_N_UNSAFE, see utf_old.h.

Definition at line 660 of file utf_old.h.

◆ UTF16_GET_CHAR_SAFE

#define UTF16_GET_CHAR_SAFE (   s,
  start,
  i,
  length,
  c,
  strict 
)
Value:
{ \
(c)=(s)[i]; \
if(UTF_IS_SURROGATE(c)) { \
uint16_t __c2; \
if(UTF_IS_SURROGATE_FIRST(c)) { \
if((i)+1<(length) && UTF_IS_SECOND_SURROGATE(__c2=(s)[(i)+1])) { \
(c)=UTF16_GET_PAIR_VALUE((c), __c2); \
/* strict: ((c)&0xfffe)==0xfffe is caught by UTF_IS_ERROR() and UTF_IS_UNICODE_CHAR() */ \
} else if(strict) {\
/* unmatched first surrogate */ \
(c)=UTF_ERROR_VALUE; \
} \
} else { \
if((i)-1>=(start) && UTF_IS_FIRST_SURROGATE(__c2=(s)[(i)-1])) { \
(c)=UTF16_GET_PAIR_VALUE(__c2, (c)); \
/* strict: ((c)&0xfffe)==0xfffe is caught by UTF_IS_ERROR() and UTF_IS_UNICODE_CHAR() */ \
} else if(strict) {\
/* unmatched second surrogate */ \
(c)=UTF_ERROR_VALUE; \
} \
} \
} else if((strict) && !UTF_IS_UNICODE_CHAR(c)) { \
(c)=UTF_ERROR_VALUE; \
} \
}
UTF_IS_SECOND_SURROGATE
#define UTF_IS_SECOND_SURROGATE(uchar)
Is uchar a second/trail surrogate?
Definition: utf_old.h:540
UTF16_GET_PAIR_VALUE
#define UTF16_GET_PAIR_VALUE(first, second)
Get the UTF-32 value from the surrogate code units.
Definition: utf_old.h:549
UTF_IS_FIRST_SURROGATE
#define UTF_IS_FIRST_SURROGATE(uchar)
Is uchar a first/lead surrogate?
Definition: utf_old.h:537
UTF_IS_SURROGATE_FIRST
#define UTF_IS_SURROGATE_FIRST(c)
Assuming c is a surrogate, is it a first/lead surrogate?
Definition: utf_old.h:543
UTF_IS_UNICODE_CHAR
#define UTF_IS_UNICODE_CHAR(c)
Is a given 32-bit value a Unicode code point value (0..U+10ffff) that can be assigned a character...
Definition: utf_old.h:277
UTF_IS_SURROGATE
#define UTF_IS_SURROGATE(uchar)
Is this code unit or code point a surrogate (U+d800..U+dfff)?
Definition: utf_old.h:250
UTF_ERROR_VALUE
#define UTF_ERROR_VALUE
Error value for all UTFs.
Definition: utf_old.h:226
Deprecated:
ICU 2.4.

Use U16_GET instead, see utf_old.h.

Definition at line 608 of file utf_old.h.

◆ UTF16_GET_CHAR_UNSAFE

#define UTF16_GET_CHAR_UNSAFE (   s,
  i,
  c 
)
Value:
{ \
(c)=(s)[i]; \
if(UTF_IS_SURROGATE(c)) { \
if(UTF_IS_SURROGATE_FIRST(c)) { \
(c)=UTF16_GET_PAIR_VALUE((c), (s)[(i)+1]); \
} else { \
(c)=UTF16_GET_PAIR_VALUE((s)[(i)-1], (c)); \
} \
} \
}
UTF16_GET_PAIR_VALUE
#define UTF16_GET_PAIR_VALUE(first, second)
Get the UTF-32 value from the surrogate code units.
Definition: utf_old.h:549
UTF_IS_SURROGATE_FIRST
#define UTF_IS_SURROGATE_FIRST(c)
Assuming c is a surrogate, is it a first/lead surrogate?
Definition: utf_old.h:543
UTF_IS_SURROGATE
#define UTF_IS_SURROGATE(uchar)
Is this code unit or code point a surrogate (U+d800..U+dfff)?
Definition: utf_old.h:250

Get a single code point from an offset that points to any of the code units that belong to that code point.

Assume 0<=i<length.

This could be used for iteration together with UTF16_CHAR_LENGTH() and UTF_IS_ERROR(), but the use of UTF16_NEXT_CHAR[_UNSAFE]() and UTF16_PREV_CHAR[_UNSAFE]() is more efficient for that.

Deprecated:
ICU 2.4. Renamed to U16_GET_UNSAFE, see utf_old.h.

Definition at line 596 of file utf_old.h.

◆ UTF16_GET_PAIR_VALUE

#define UTF16_GET_PAIR_VALUE (   first,
  second 
)    (((first)<<10UL)+(second)-UTF_SURROGATE_OFFSET)

Get the UTF-32 value from the surrogate code units.

Deprecated:
ICU 2.4. Renamed to U16_GET_SUPPLEMENTARY, see utf_old.h.

Definition at line 549 of file utf_old.h.

◆ UTF16_IS_LEAD

#define UTF16_IS_LEAD (   uchar)    UTF_IS_FIRST_SURROGATE(uchar)
Deprecated:
ICU 2.4.

Renamed to U16_IS_LEAD, see utf_old.h.

Definition at line 568 of file utf_old.h.

◆ UTF16_IS_SINGLE

#define UTF16_IS_SINGLE (   uchar)    !UTF_IS_SURROGATE(uchar)
Deprecated:
ICU 2.4.

Renamed to U16_IS_SINGLE, see utf_old.h.

Definition at line 565 of file utf_old.h.

◆ UTF16_IS_TRAIL

#define UTF16_IS_TRAIL (   uchar)    UTF_IS_SECOND_SURROGATE(uchar)
Deprecated:
ICU 2.4.

Renamed to U16_IS_TRAIL, see utf_old.h.

Definition at line 571 of file utf_old.h.

◆ UTF16_LEAD

#define UTF16_LEAD (   supplementary)    UTF_FIRST_SURROGATE(supplementary)
Deprecated:
ICU 2.4.

Renamed to U16_LEAD, see utf_old.h.

Definition at line 559 of file utf_old.h.

◆ UTF16_MAX_CHAR_LENGTH

#define UTF16_MAX_CHAR_LENGTH   2
Deprecated:
ICU 2.4.

Renamed to U16_MAX_LENGTH, see utf_old.h.

Definition at line 580 of file utf_old.h.

◆ UTF16_NEED_MULTIPLE_UCHAR

#define UTF16_NEED_MULTIPLE_UCHAR (   c)    ((uint32_t)(c)>0xffff)

Does this scalar Unicode value need multiple code units for storage?

Deprecated:
ICU 2.4.

Use U16_LENGTH or test ((uint32_t)(c)>0xffff) instead, see utf_old.h.

Definition at line 574 of file utf_old.h.

◆ UTF16_NEXT_CHAR_SAFE

#define UTF16_NEXT_CHAR_SAFE (   s,
  i,
  length,
  c,
  strict 
)
Value:
{ \
(c)=(s)[(i)++]; \
if(UTF_IS_FIRST_SURROGATE(c)) { \
uint16_t __c2; \
if((i)<(length) && UTF_IS_SECOND_SURROGATE(__c2=(s)[(i)])) { \
++(i); \
(c)=UTF16_GET_PAIR_VALUE((c), __c2); \
/* strict: ((c)&0xfffe)==0xfffe is caught by UTF_IS_ERROR() and UTF_IS_UNICODE_CHAR() */ \
} else if(strict) {\
/* unmatched first surrogate */ \
(c)=UTF_ERROR_VALUE; \
} \
} else if((strict) && !UTF_IS_UNICODE_CHAR(c)) { \
/* unmatched second surrogate or other non-character */ \
(c)=UTF_ERROR_VALUE; \
} \
}
UTF_IS_SECOND_SURROGATE
#define UTF_IS_SECOND_SURROGATE(uchar)
Is uchar a second/trail surrogate?
Definition: utf_old.h:540
UTF16_GET_PAIR_VALUE
#define UTF16_GET_PAIR_VALUE(first, second)
Get the UTF-32 value from the surrogate code units.
Definition: utf_old.h:549
UTF_IS_FIRST_SURROGATE
#define UTF_IS_FIRST_SURROGATE(uchar)
Is uchar a first/lead surrogate?
Definition: utf_old.h:537
UTF_IS_UNICODE_CHAR
#define UTF_IS_UNICODE_CHAR(c)
Is a given 32-bit value a Unicode code point value (0..U+10ffff) that can be assigned a character...
Definition: utf_old.h:277
UTF_ERROR_VALUE
#define UTF_ERROR_VALUE
Error value for all UTFs.
Definition: utf_old.h:226
Deprecated:
ICU 2.4.

Use U16_NEXT instead, see utf_old.h.

Definition at line 676 of file utf_old.h.

◆ UTF16_NEXT_CHAR_UNSAFE

#define UTF16_NEXT_CHAR_UNSAFE (   s,
  i,
  c 
)
Value:
{ \
(c)=(s)[(i)++]; \
if(UTF_IS_FIRST_SURROGATE(c)) { \
(c)=UTF16_GET_PAIR_VALUE((c), (s)[(i)++]); \
} \
}
UTF16_GET_PAIR_VALUE
#define UTF16_GET_PAIR_VALUE(first, second)
Get the UTF-32 value from the surrogate code units.
Definition: utf_old.h:549
UTF_IS_FIRST_SURROGATE
#define UTF_IS_FIRST_SURROGATE(uchar)
Is uchar a first/lead surrogate?
Definition: utf_old.h:537
Deprecated:
ICU 2.4.

Renamed to U16_NEXT_UNSAFE, see utf_old.h.

Definition at line 635 of file utf_old.h.

◆ UTF16_PREV_CHAR_SAFE

#define UTF16_PREV_CHAR_SAFE (   s,
  start,
  i,
  c,
  strict 
)
Value:
{ \
(c)=(s)[--(i)]; \
if(UTF_IS_SECOND_SURROGATE(c)) { \
uint16_t __c2; \
if((i)>(start) && UTF_IS_FIRST_SURROGATE(__c2=(s)[(i)-1])) { \
--(i); \
(c)=UTF16_GET_PAIR_VALUE(__c2, (c)); \
/* strict: ((c)&0xfffe)==0xfffe is caught by UTF_IS_ERROR() and UTF_IS_UNICODE_CHAR() */ \
} else if(strict) {\
/* unmatched second surrogate */ \
(c)=UTF_ERROR_VALUE; \
} \
} else if((strict) && !UTF_IS_UNICODE_CHAR(c)) { \
/* unmatched first surrogate or other non-character */ \
(c)=UTF_ERROR_VALUE; \
} \
}
UTF_IS_SECOND_SURROGATE
#define UTF_IS_SECOND_SURROGATE(uchar)
Is uchar a second/trail surrogate?
Definition: utf_old.h:540
UTF16_GET_PAIR_VALUE
#define UTF16_GET_PAIR_VALUE(first, second)
Get the UTF-32 value from the surrogate code units.
Definition: utf_old.h:549
UTF_IS_FIRST_SURROGATE
#define UTF_IS_FIRST_SURROGATE(uchar)
Is uchar a first/lead surrogate?
Definition: utf_old.h:537
UTF_IS_UNICODE_CHAR
#define UTF_IS_UNICODE_CHAR(c)
Is a given 32-bit value a Unicode code point value (0..U+10ffff) that can be assigned a character...
Definition: utf_old.h:277
UTF_ERROR_VALUE
#define UTF_ERROR_VALUE
Error value for all UTFs.
Definition: utf_old.h:226
Deprecated:
ICU 2.4.

Use U16_PREV instead, see utf_old.h.

Definition at line 751 of file utf_old.h.

◆ UTF16_PREV_CHAR_UNSAFE

#define UTF16_PREV_CHAR_UNSAFE (   s,
  i,
  c 
)
Value:
{ \
(c)=(s)[--(i)]; \
if(UTF_IS_SECOND_SURROGATE(c)) { \
(c)=UTF16_GET_PAIR_VALUE((s)[--(i)], (c)); \
} \
}
UTF_IS_SECOND_SURROGATE
#define UTF_IS_SECOND_SURROGATE(uchar)
Is uchar a second/trail surrogate?
Definition: utf_old.h:540
UTF16_GET_PAIR_VALUE
#define UTF16_GET_PAIR_VALUE(first, second)
Get the UTF-32 value from the surrogate code units.
Definition: utf_old.h:549
Deprecated:
ICU 2.4.

Renamed to U16_PREV_UNSAFE, see utf_old.h.

Definition at line 720 of file utf_old.h.

◆ UTF16_SET_CHAR_LIMIT_SAFE

#define UTF16_SET_CHAR_LIMIT_SAFE (   s,
  start,
  i,
  length 
)    U16_SET_CP_LIMIT(s, start, i, length)
Deprecated:
ICU 2.4.

Renamed to U16_SET_CP_LIMIT, see utf_old.h.

Definition at line 776 of file utf_old.h.

◆ UTF16_SET_CHAR_LIMIT_UNSAFE

#define UTF16_SET_CHAR_LIMIT_UNSAFE (   s,
  i 
)
Value:
{ \
if(UTF_IS_FIRST_SURROGATE((s)[(i)-1])) { \
++(i); \
} \
}
UTF_IS_FIRST_SURROGATE
#define UTF_IS_FIRST_SURROGATE(uchar)
Is uchar a first/lead surrogate?
Definition: utf_old.h:537
Deprecated:
ICU 2.4.

Renamed to U16_SET_CP_LIMIT_UNSAFE, see utf_old.h.

Definition at line 744 of file utf_old.h.

◆ UTF16_SET_CHAR_START_SAFE

#define UTF16_SET_CHAR_START_SAFE (   s,
  start,
  i 
)    U16_SET_CP_START(s, start, i)
Deprecated:
ICU 2.4.

Renamed to U16_SET_CP_START, see utf_old.h.

Definition at line 717 of file utf_old.h.

◆ UTF16_SET_CHAR_START_UNSAFE

#define UTF16_SET_CHAR_START_UNSAFE (   s,
  i 
)
Value:
{ \
if(UTF_IS_SECOND_SURROGATE((s)[i])) { \
--(i); \
} \
}
UTF_IS_SECOND_SURROGATE
#define UTF_IS_SECOND_SURROGATE(uchar)
Is uchar a second/trail surrogate?
Definition: utf_old.h:540
Deprecated:
ICU 2.4.

Renamed to U16_SET_CP_START_UNSAFE, see utf_old.h.

Definition at line 669 of file utf_old.h.

◆ UTF16_TRAIL

#define UTF16_TRAIL (   supplementary)    UTF_SECOND_SURROGATE(supplementary)
Deprecated:
ICU 2.4.

Renamed to U16_TRAIL, see utf_old.h.

Definition at line 562 of file utf_old.h.

◆ UTF32_APPEND_CHAR_SAFE

#define UTF32_APPEND_CHAR_SAFE (   s,
  i,
  length,
  c 
)
Value:
{ \
if((uint32_t)(c)<=0x10ffff) { \
(s)[(i)++]=(c); \
} else /* c>0x10ffff, write 0xfffd */ { \
(s)[(i)++]=0xfffd; \
} \
}
Deprecated:
ICU 2.4.

Obsolete, see utf_old.h.

Definition at line 880 of file utf_old.h.

◆ UTF32_APPEND_CHAR_UNSAFE

#define UTF32_APPEND_CHAR_UNSAFE (   s,
  i,
  c 
)
Value:
{ \
(s)[(i)++]=(c); \
}
Deprecated:
ICU 2.4.

Obsolete, see utf_old.h.

Definition at line 853 of file utf_old.h.

◆ UTF32_ARRAY_SIZE

#define UTF32_ARRAY_SIZE (   size)    (size)
Deprecated:
ICU 2.4.

Obsolete, see utf_old.h.

Definition at line 830 of file utf_old.h.

◆ UTF32_BACK_1_SAFE

#define UTF32_BACK_1_SAFE (   s,
  start,
  i 
)
Value:
{ \
--(i); \
}
Deprecated:
ICU 2.4.

Obsolete, see utf_old.h.

Definition at line 934 of file utf_old.h.

◆ UTF32_BACK_1_UNSAFE

#define UTF32_BACK_1_UNSAFE (   s,
  i 
)
Value:
{ \
--(i); \
}
Deprecated:
ICU 2.4.

Obsolete, see utf_old.h.

Definition at line 912 of file utf_old.h.

◆ UTF32_BACK_N_SAFE

#define UTF32_BACK_N_SAFE (   s,
  start,
  i,
  n 
)
Value:
{ \
(i)-=(n); \
if((i)<(start)) { \
(i)=(start); \
} \
}
Deprecated:
ICU 2.4.

Obsolete, see utf_old.h.

Definition at line 939 of file utf_old.h.

◆ UTF32_BACK_N_UNSAFE

#define UTF32_BACK_N_UNSAFE (   s,
  i,
  n 
)
Value:
{ \
(i)-=(n); \
}
Deprecated:
ICU 2.4.

Obsolete, see utf_old.h.

Definition at line 917 of file utf_old.h.

◆ UTF32_CHAR_LENGTH

#define UTF32_CHAR_LENGTH (   c)    1
Deprecated:
ICU 2.4.

Obsolete, see utf_old.h.

Definition at line 823 of file utf_old.h.

◆ UTF32_FWD_1_SAFE

#define UTF32_FWD_1_SAFE (   s,
  i,
  length 
)
Value:
{ \
++(i); \
}
Deprecated:
ICU 2.4.

Obsolete, see utf_old.h.

Definition at line 889 of file utf_old.h.

◆ UTF32_FWD_1_UNSAFE

#define UTF32_FWD_1_UNSAFE (   s,
  i 
)
Value:
{ \
++(i); \
}
Deprecated:
ICU 2.4.

Obsolete, see utf_old.h.

Definition at line 858 of file utf_old.h.

◆ UTF32_FWD_N_SAFE

#define UTF32_FWD_N_SAFE (   s,
  i,
  length,
  n 
)
Value:
{ \
if(((i)+=(n))>(length)) { \
(i)=(length); \
} \
}
Deprecated:
ICU 2.4.

Obsolete, see utf_old.h.

Definition at line 894 of file utf_old.h.

◆ UTF32_FWD_N_UNSAFE

#define UTF32_FWD_N_UNSAFE (   s,
  i,
  n 
)
Value:
{ \
(i)+=(n); \
}
Deprecated:
ICU 2.4.

Obsolete, see utf_old.h.

Definition at line 863 of file utf_old.h.

◆ UTF32_GET_CHAR_SAFE

#define UTF32_GET_CHAR_SAFE (   s,
  start,
  i,
  length,
  c,
  strict 
)
Value:
{ \
(c)=(s)[i]; \
if(!UTF32_IS_SAFE(c, strict)) { \
(c)=UTF_ERROR_VALUE; \
} \
}
UTF32_IS_SAFE
#define UTF32_IS_SAFE(c, strict)
Definition: utf_old.h:796
UTF_ERROR_VALUE
#define UTF_ERROR_VALUE
Error value for all UTFs.
Definition: utf_old.h:226
Deprecated:
ICU 2.4.

Obsolete, see utf_old.h.

Definition at line 838 of file utf_old.h.

◆ UTF32_GET_CHAR_UNSAFE

#define UTF32_GET_CHAR_UNSAFE (   s,
  i,
  c 
)
Value:
{ \
(c)=(s)[i]; \
}
Deprecated:
ICU 2.4.

Obsolete, see utf_old.h.

Definition at line 833 of file utf_old.h.

◆ UTF32_IS_LEAD

#define UTF32_IS_LEAD (   uchar)    0
Deprecated:
ICU 2.4.

Obsolete, see utf_old.h.

Definition at line 814 of file utf_old.h.

◆ UTF32_IS_SAFE

#define UTF32_IS_SAFE (   c,
  strict 
)
Value:
(!(strict) ? \
(uint32_t)(c)<=0x10ffff : \
UTF_IS_UNICODE_CHAR(c))
UTF_IS_UNICODE_CHAR
#define UTF_IS_UNICODE_CHAR(c)
Is a given 32-bit value a Unicode code point value (0..U+10ffff) that can be assigned a character...
Definition: utf_old.h:277
Deprecated:
ICU 2.4.

Obsolete, see utf_old.h.

Definition at line 796 of file utf_old.h.

◆ UTF32_IS_SINGLE

#define UTF32_IS_SINGLE (   uchar)    1
Deprecated:
ICU 2.4.

Obsolete, see utf_old.h.

Definition at line 812 of file utf_old.h.

◆ UTF32_IS_TRAIL

#define UTF32_IS_TRAIL (   uchar)    0
Deprecated:
ICU 2.4.

Obsolete, see utf_old.h.

Definition at line 816 of file utf_old.h.

◆ UTF32_MAX_CHAR_LENGTH

#define UTF32_MAX_CHAR_LENGTH   1
Deprecated:
ICU 2.4.

Obsolete, see utf_old.h.

Definition at line 825 of file utf_old.h.

◆ UTF32_NEED_MULTIPLE_UCHAR

#define UTF32_NEED_MULTIPLE_UCHAR (   c)    0
Deprecated:
ICU 2.4.

Obsolete, see utf_old.h.

Definition at line 821 of file utf_old.h.

◆ UTF32_NEXT_CHAR_SAFE

#define UTF32_NEXT_CHAR_SAFE (   s,
  i,
  length,
  c,
  strict 
)
Value:
{ \
(c)=(s)[(i)++]; \
if(!UTF32_IS_SAFE(c, strict)) { \
(c)=UTF_ERROR_VALUE; \
} \
}
UTF32_IS_SAFE
#define UTF32_IS_SAFE(c, strict)
Definition: utf_old.h:796
UTF_ERROR_VALUE
#define UTF_ERROR_VALUE
Error value for all UTFs.
Definition: utf_old.h:226
Deprecated:
ICU 2.4.

Obsolete, see utf_old.h.

Definition at line 872 of file utf_old.h.

◆ UTF32_NEXT_CHAR_UNSAFE

#define UTF32_NEXT_CHAR_UNSAFE (   s,
  i,
  c 
)
Value:
{ \
(c)=(s)[(i)++]; \
}
Deprecated:
ICU 2.4.

Obsolete, see utf_old.h.

Definition at line 848 of file utf_old.h.

◆ UTF32_PREV_CHAR_SAFE

#define UTF32_PREV_CHAR_SAFE (   s,
  start,
  i,
  c,
  strict 
)
Value:
{ \
(c)=(s)[--(i)]; \
if(!UTF32_IS_SAFE(c, strict)) { \
(c)=UTF_ERROR_VALUE; \
} \
}
UTF32_IS_SAFE
#define UTF32_IS_SAFE(c, strict)
Definition: utf_old.h:796
UTF_ERROR_VALUE
#define UTF_ERROR_VALUE
Error value for all UTFs.
Definition: utf_old.h:226
Deprecated:
ICU 2.4.

Obsolete, see utf_old.h.

Definition at line 926 of file utf_old.h.

◆ UTF32_PREV_CHAR_UNSAFE

#define UTF32_PREV_CHAR_UNSAFE (   s,
  i,
  c 
)
Value:
{ \
(c)=(s)[--(i)]; \
}
Deprecated:
ICU 2.4.

Obsolete, see utf_old.h.

Definition at line 907 of file utf_old.h.

◆ UTF32_SET_CHAR_LIMIT_SAFE

#define UTF32_SET_CHAR_LIMIT_SAFE (   s,
  i,
  length 
)
Value:
{ \
}
Deprecated:
ICU 2.4.

Obsolete, see utf_old.h.

Definition at line 947 of file utf_old.h.

◆ UTF32_SET_CHAR_LIMIT_UNSAFE

#define UTF32_SET_CHAR_LIMIT_UNSAFE (   s,
  i 
)
Value:
{ \
}
Deprecated:
ICU 2.4.

Obsolete, see utf_old.h.

Definition at line 922 of file utf_old.h.

◆ UTF32_SET_CHAR_START_SAFE

#define UTF32_SET_CHAR_START_SAFE (   s,
  start,
  i 
)
Value:
{ \
}
Deprecated:
ICU 2.4.

Obsolete, see utf_old.h.

Definition at line 901 of file utf_old.h.

◆ UTF32_SET_CHAR_START_UNSAFE

#define UTF32_SET_CHAR_START_UNSAFE (   s,
  i 
)
Value:
{ \
}
Deprecated:
ICU 2.4.

Obsolete, see utf_old.h.

Definition at line 868 of file utf_old.h.

◆ UTF8_APPEND_CHAR_SAFE

#define UTF8_APPEND_CHAR_SAFE (   s,
  i,
  length,
  c 
)
Value:
{ \
if((uint32_t)(c)<=0x7f) { \
(s)[(i)++]=(uint8_t)(c); \
} else { \
(i)=utf8_appendCharSafeBody(s, (int32_t)(i), (int32_t)(length), c, NULL); \
} \
}
NULL
#define NULL
Define NULL if necessary, to nullptr for C++ and to ((void *)0) for C.
Definition: utypes.h:188
utf8_appendCharSafeBody
int32_t utf8_appendCharSafeBody(uint8_t *s, int32_t i, int32_t length, UChar32 c, UBool *pIsError)
Function for handling "append code point" with error-checking.
Deprecated:
ICU 2.4.

Use U8_APPEND instead, see utf_old.h.

Definition at line 453 of file utf_old.h.

◆ UTF8_APPEND_CHAR_UNSAFE

#define UTF8_APPEND_CHAR_UNSAFE (   s,
  i,
  c 
)
Value:
{ \
if((uint32_t)(c)<=0x7f) { \
(s)[(i)++]=(uint8_t)(c); \
} else { \
if((uint32_t)(c)<=0x7ff) { \
(s)[(i)++]=(uint8_t)(((c)>>6)|0xc0); \
} else { \
if((uint32_t)(c)<=0xffff) { \
(s)[(i)++]=(uint8_t)(((c)>>12)|0xe0); \
} else { \
(s)[(i)++]=(uint8_t)(((c)>>18)|0xf0); \
(s)[(i)++]=(uint8_t)((((c)>>12)&0x3f)|0x80); \
} \
(s)[(i)++]=(uint8_t)((((c)>>6)&0x3f)|0x80); \
} \
(s)[(i)++]=(uint8_t)(((c)&0x3f)|0x80); \
} \
}
Deprecated:
ICU 2.4.

Renamed to U8_APPEND_UNSAFE, see utf_old.h.

Definition at line 402 of file utf_old.h.

◆ UTF8_ARRAY_SIZE

#define UTF8_ARRAY_SIZE (   size)    ((5*(size))/2)

Average number of code units compared to UTF-16.

Deprecated:
ICU 2.4. Obsolete, see utf_old.h.

Definition at line 365 of file utf_old.h.

◆ UTF8_BACK_1_SAFE

#define UTF8_BACK_1_SAFE (   s,
  start,
  i 
)    U8_BACK_1(s, start, i)
Deprecated:
ICU 2.4.

Renamed to U8_BACK_1, see utf_old.h.

Definition at line 526 of file utf_old.h.

◆ UTF8_BACK_1_UNSAFE

#define UTF8_BACK_1_UNSAFE (   s,
  i 
)
Value:
{ \
while(UTF8_IS_TRAIL((s)[--(i)])) {} \
}
UTF8_IS_TRAIL
#define UTF8_IS_TRAIL(uchar)
Is this this code unit a trailing code unit (byte) of a code point?
Definition: utf_old.h:321
Deprecated:
ICU 2.4.

Renamed to U8_BACK_1_UNSAFE, see utf_old.h.

Definition at line 494 of file utf_old.h.

◆ UTF8_BACK_N_SAFE

#define UTF8_BACK_N_SAFE (   s,
  start,
  i,
  n 
)    U8_BACK_N(s, start, i, n)
Deprecated:
ICU 2.4.

Renamed to U8_BACK_N, see utf_old.h.

Definition at line 529 of file utf_old.h.

◆ UTF8_BACK_N_UNSAFE

#define UTF8_BACK_N_UNSAFE (   s,
  i,
  n 
)
Value:
{ \
int32_t __N=(n); \
while(__N>0) { \
UTF8_BACK_1_UNSAFE(s, i); \
--__N; \
} \
}
Deprecated:
ICU 2.4.

Renamed to U8_BACK_N_UNSAFE, see utf_old.h.

Definition at line 499 of file utf_old.h.

◆ UTF8_CHAR_LENGTH

#define UTF8_CHAR_LENGTH (   c)
Value:
((uint32_t)(c)<=0x7f ? 1 : \
((uint32_t)(c)<=0x7ff ? 2 : \
((uint32_t)((c)-0x10000)>0xfffff ? 3 : 4) \
) \
)

Given the lead character, how many bytes are taken by this code point.

ICU does not deal with code points >0x10ffff unless necessary for advancing in the byte stream.

These length macros take into account that for values >0x10ffff the UTF8_APPEND_CHAR_SAFE macros would write the error code point 0xffff with 3 bytes. Code point comparisons need to be in uint32_t because UChar32 may be a signed type, and negative values must be recognized.

Deprecated:
ICU 2.4. Use U8_LENGTH instead, see utf.h.

Definition at line 340 of file utf_old.h.

◆ UTF8_COUNT_TRAIL_BYTES

#define UTF8_COUNT_TRAIL_BYTES (   leadByte)    (utf8_countTrailBytes[(uint8_t)leadByte])

Count the trail bytes for a UTF-8 lead byte.

Deprecated:
ICU 2.4. Renamed to U8_COUNT_TRAIL_BYTES, see utf_old.h.

Definition at line 308 of file utf_old.h.

◆ UTF8_ERROR_VALUE_1

#define UTF8_ERROR_VALUE_1   0x15

UTF8_ERROR_VALUE_1 and UTF8_ERROR_VALUE_2 are special error values for UTF-8, which need 1 or 2 bytes in UTF-8:

Deprecated:
ICU 2.4.

Obsolete, see utf_old.h.

Deprecated:
ICU 2.4.

Obsolete, see utf_old.h.

U+0015 = NAK = Negative Acknowledge, C0 control character
U+009f = highest C1 control character

These are used by UTF8_..._SAFE macros so that they can return an error value that needs the same number of code units (bytes) as were seen by a macro. They should be tested with UTF_IS_ERROR() or UTF_IS_VALID().

Deprecated:
ICU 2.4. Obsolete, see utf_old.h.

Definition at line 211 of file utf_old.h.

◆ UTF8_ERROR_VALUE_2

#define UTF8_ERROR_VALUE_2   0x9f

See documentation on UTF8_ERROR_VALUE_1 for details.

Deprecated:
ICU 2.4. Obsolete, see utf_old.h.

Definition at line 218 of file utf_old.h.

◆ UTF8_FWD_1_SAFE

#define UTF8_FWD_1_SAFE (   s,
  i,
  length 
)    U8_FWD_1(s, i, length)
Deprecated:
ICU 2.4.

Renamed to U8_FWD_1, see utf_old.h.

Definition at line 462 of file utf_old.h.

◆ UTF8_FWD_1_UNSAFE

#define UTF8_FWD_1_UNSAFE (   s,
  i 
)
Value:
{ \
(i)+=1+UTF8_COUNT_TRAIL_BYTES((s)[i]); \
}
UTF8_COUNT_TRAIL_BYTES
#define UTF8_COUNT_TRAIL_BYTES(leadByte)
Count the trail bytes for a UTF-8 lead byte.
Definition: utf_old.h:308
Deprecated:
ICU 2.4.

Renamed to U8_FWD_1_UNSAFE, see utf_old.h.

Definition at line 422 of file utf_old.h.

◆ UTF8_FWD_N_SAFE

#define UTF8_FWD_N_SAFE (   s,
  i,
  length,
  n 
)    U8_FWD_N(s, i, length, n)
Deprecated:
ICU 2.4.

Renamed to U8_FWD_N, see utf_old.h.

Definition at line 465 of file utf_old.h.

◆ UTF8_FWD_N_UNSAFE

#define UTF8_FWD_N_UNSAFE (   s,
  i,
  n 
)
Value:
{ \
int32_t __N=(n); \
while(__N>0) { \
UTF8_FWD_1_UNSAFE(s, i); \
--__N; \
} \
}
Deprecated:
ICU 2.4.

Renamed to U8_FWD_N_UNSAFE, see utf_old.h.

Definition at line 427 of file utf_old.h.

◆ UTF8_GET_CHAR_SAFE

#define UTF8_GET_CHAR_SAFE (   s,
  start,
  i,
  length,
  c,
  strict 
)
Value:
{ \
int32_t _utf8_get_char_safe_index=(int32_t)(i); \
UTF8_SET_CHAR_START_SAFE(s, start, _utf8_get_char_safe_index); \
UTF8_NEXT_CHAR_SAFE(s, _utf8_get_char_safe_index, length, c, strict); \
}
Deprecated:
ICU 2.4.

Use U8_GET instead, see utf_old.h.

Definition at line 375 of file utf_old.h.

◆ UTF8_GET_CHAR_UNSAFE

#define UTF8_GET_CHAR_UNSAFE (   s,
  i,
  c 
)
Value:
{ \
int32_t _utf8_get_char_unsafe_index=(int32_t)(i); \
UTF8_SET_CHAR_START_UNSAFE(s, _utf8_get_char_unsafe_index); \
UTF8_NEXT_CHAR_UNSAFE(s, _utf8_get_char_unsafe_index, c); \
}
Deprecated:
ICU 2.4.

Renamed to U8_GET_UNSAFE, see utf_old.h.

Definition at line 368 of file utf_old.h.

◆ UTF8_IS_LEAD

#define UTF8_IS_LEAD (   uchar)    ((uint8_t)((uchar)-0xc0)<0x3e)

Is this this code unit the lead code unit (byte) of a code point?

Deprecated:
ICU 2.4.

Renamed to U8_IS_LEAD, see utf_old.h.

Definition at line 319 of file utf_old.h.

◆ UTF8_IS_SINGLE

#define UTF8_IS_SINGLE (   uchar)    (((uchar)&0x80)==0)

Is this this code point a single code unit (byte)?

Deprecated:
ICU 2.4.

Renamed to U8_IS_SINGLE, see utf_old.h.

Definition at line 317 of file utf_old.h.

◆ UTF8_IS_TRAIL

#define UTF8_IS_TRAIL (   uchar)    (((uchar)&0xc0)==0x80)

Is this this code unit a trailing code unit (byte) of a code point?

Deprecated:
ICU 2.4.

Renamed to U8_IS_TRAIL, see utf_old.h.

Definition at line 321 of file utf_old.h.

◆ UTF8_MASK_LEAD_BYTE

#define UTF8_MASK_LEAD_BYTE (   leadByte,
  countTrailBytes 
)    ((leadByte)&=(1<<(6-(countTrailBytes)))-1)

Mask a UTF-8 lead byte, leave only the lower bits that form part of the code point value.

Deprecated:
ICU 2.4. Renamed to U8_MASK_LEAD_BYTE, see utf_old.h.

Definition at line 314 of file utf_old.h.

◆ UTF8_MAX_CHAR_LENGTH

#define UTF8_MAX_CHAR_LENGTH   4

The maximum number of bytes per code point.

Deprecated:
ICU 2.4. Renamed to U8_MAX_LENGTH, see utf_old.h.

Definition at line 362 of file utf_old.h.

◆ UTF8_NEED_MULTIPLE_UCHAR

#define UTF8_NEED_MULTIPLE_UCHAR (   c)    ((uint32_t)(c)>0x7f)

Does this scalar Unicode value need multiple code units for storage?

Deprecated:
ICU 2.4.

Use U8_LENGTH or test ((uint32_t)(c)>0x7f) instead, see utf_old.h.

Definition at line 324 of file utf_old.h.

◆ UTF8_NEXT_CHAR_SAFE

#define UTF8_NEXT_CHAR_SAFE (   s,
  i,
  length,
  c,
  strict 
)
Value:
{ \
(c)=(s)[(i)++]; \
if((c)>=0x80) { \
if(UTF8_IS_LEAD(c)) { \
(c)=utf8_nextCharSafeBody(s, &(i), (int32_t)(length), c, strict); \
} else { \
(c)=UTF8_ERROR_VALUE_1; \
} \
} \
}
UTF8_ERROR_VALUE_1
#define UTF8_ERROR_VALUE_1
UTF8_ERROR_VALUE_1 and UTF8_ERROR_VALUE_2 are special error values for UTF-8, which need 1 or 2 bytes...
Definition: utf_old.h:211
UTF8_IS_LEAD
#define UTF8_IS_LEAD(uchar)
Is this this code unit the lead code unit (byte) of a code point?
Definition: utf_old.h:319
utf8_nextCharSafeBody
UChar32 utf8_nextCharSafeBody(const uint8_t *s, int32_t *pi, int32_t length, UChar32 c, UBool strict)
Function for handling "next code point" with error-checking.
Deprecated:
ICU 2.4.

Use U8_NEXT instead, see utf_old.h.

Definition at line 441 of file utf_old.h.

◆ UTF8_NEXT_CHAR_UNSAFE

#define UTF8_NEXT_CHAR_UNSAFE (   s,
  i,
  c 
)
Value:
{ \
(c)=(s)[(i)++]; \
if((uint8_t)((c)-0xc0)<0x35) { \
uint8_t __count=UTF8_COUNT_TRAIL_BYTES(c); \
UTF8_MASK_LEAD_BYTE(c, __count); \
switch(__count) { \
/* each following branch falls through to the next one */ \
case 3: \
(c)=((c)<<6)|((s)[(i)++]&0x3f); \
case 2: \
(c)=((c)<<6)|((s)[(i)++]&0x3f); \
case 1: \
(c)=((c)<<6)|((s)[(i)++]&0x3f); \
/* no other branches to optimize switch() */ \
break; \
} \
} \
}
UTF8_COUNT_TRAIL_BYTES
#define UTF8_COUNT_TRAIL_BYTES(leadByte)
Count the trail bytes for a UTF-8 lead byte.
Definition: utf_old.h:308
Deprecated:
ICU 2.4.

Renamed to U8_NEXT_UNSAFE, see utf_old.h.

Definition at line 382 of file utf_old.h.

◆ UTF8_PREV_CHAR_SAFE

#define UTF8_PREV_CHAR_SAFE (   s,
  start,
  i,
  c,
  strict 
)
Value:
{ \
(c)=(s)[--(i)]; \
if((c)>=0x80) { \
if((c)<=0xbf) { \
(c)=utf8_prevCharSafeBody(s, start, &(i), c, strict); \
} else { \
(c)=UTF8_ERROR_VALUE_1; \
} \
} \
}
UTF8_ERROR_VALUE_1
#define UTF8_ERROR_VALUE_1
UTF8_ERROR_VALUE_1 and UTF8_ERROR_VALUE_2 are special error values for UTF-8, which need 1 or 2 bytes...
Definition: utf_old.h:211
utf8_prevCharSafeBody
UChar32 utf8_prevCharSafeBody(const uint8_t *s, int32_t start, int32_t *pi, UChar32 c, UBool strict)
Function for handling "previous code point" with error-checking.
Deprecated:
ICU 2.4.

Use U8_PREV instead, see utf_old.h.

Definition at line 514 of file utf_old.h.

◆ UTF8_PREV_CHAR_UNSAFE

#define UTF8_PREV_CHAR_UNSAFE (   s,
  i,
  c 
)
Value:
{ \
(c)=(s)[--(i)]; \
if(UTF8_IS_TRAIL(c)) { \
uint8_t __b, __count=1, __shift=6; \
\
/* c is a trail byte */ \
(c)&=0x3f; \
for(;;) { \
__b=(s)[--(i)]; \
if(__b>=0xc0) { \
UTF8_MASK_LEAD_BYTE(__b, __count); \
(c)|=(UChar32)__b<<__shift; \
break; \
} else { \
(c)|=(UChar32)(__b&0x3f)<<__shift; \
++__count; \
__shift+=6; \
} \
} \
} \
}
UChar32
int32_t UChar32
Define UChar32 as a type for single Unicode code points.
Definition: umachine.h:389
UTF8_IS_TRAIL
#define UTF8_IS_TRAIL(uchar)
Is this this code unit a trailing code unit (byte) of a code point?
Definition: utf_old.h:321
Deprecated:
ICU 2.4.

Renamed to U8_PREV_UNSAFE, see utf_old.h.

Definition at line 471 of file utf_old.h.

◆ UTF8_SET_CHAR_LIMIT_SAFE

#define UTF8_SET_CHAR_LIMIT_SAFE (   s,
  start,
  i,
  length 
)    U8_SET_CP_LIMIT(s, start, i, length)
Deprecated:
ICU 2.4.

Renamed to U8_SET_CP_LIMIT, see utf_old.h.

Definition at line 532 of file utf_old.h.

◆ UTF8_SET_CHAR_LIMIT_UNSAFE

#define UTF8_SET_CHAR_LIMIT_UNSAFE (   s,
  i 
)
Value:
{ \
UTF8_BACK_1_UNSAFE(s, i); \
UTF8_FWD_1_UNSAFE(s, i); \
}
Deprecated:
ICU 2.4.

Renamed to U8_SET_CP_LIMIT_UNSAFE, see utf_old.h.

Definition at line 508 of file utf_old.h.

◆ UTF8_SET_CHAR_START_SAFE

#define UTF8_SET_CHAR_START_SAFE (   s,
  start,
  i 
)    U8_SET_CP_START(s, start, i)
Deprecated:
ICU 2.4.

Renamed to U8_SET_CP_START, see utf_old.h.

Definition at line 468 of file utf_old.h.

◆ UTF8_SET_CHAR_START_UNSAFE

#define UTF8_SET_CHAR_START_UNSAFE (   s,
  i 
)
Value:
{ \
while(UTF8_IS_TRAIL((s)[i])) { --(i); } \
}
UTF8_IS_TRAIL
#define UTF8_IS_TRAIL(uchar)
Is this this code unit a trailing code unit (byte) of a code point?
Definition: utf_old.h:321
Deprecated:
ICU 2.4.

Renamed to U8_SET_CP_START_UNSAFE, see utf_old.h.

Definition at line 436 of file utf_old.h.

◆ UTF_APPEND_CHAR

#define UTF_APPEND_CHAR (   s,
  i,
  length,
  c 
)    UTF16_APPEND_CHAR_SAFE(s, i, length, c)

Append the code units of code point c to the string at index i and advance i to beyond the new code units (post-increment).

The code units beginning at index i will be overwritten. Same as UTF16_APPEND_CHAR.

Precondition
0<=c<=0x10ffff
0<=i<length
Postcondition
0<i<=length
Deprecated:
ICU 2.4. Use U16_APPEND instead, see utf_old.h.

Definition at line 1107 of file utf_old.h.

◆ UTF_APPEND_CHAR_SAFE

#define UTF_APPEND_CHAR_SAFE (   s,
  i,
  length,
  c 
)    UTF16_APPEND_CHAR_SAFE(s, i, length, c)
Deprecated:
ICU 2.4.

Use U16_APPEND instead, see utf_old.h.

Definition at line 977 of file utf_old.h.

◆ UTF_APPEND_CHAR_UNSAFE

#define UTF_APPEND_CHAR_UNSAFE (   s,
  i,
  c 
)    UTF16_APPEND_CHAR_UNSAFE(s, i, c)
Deprecated:
ICU 2.4.

Renamed to U16_APPEND_UNSAFE, see utf_old.h.

Definition at line 974 of file utf_old.h.

◆ UTF_ARRAY_SIZE

#define UTF_ARRAY_SIZE (   size)    UTF16_ARRAY_SIZE(size)

Estimate the number of code units for a string based on the number of UTF-16 code units.

Deprecated:
ICU 2.4. Obsolete, see utf_old.h.

Definition at line 957 of file utf_old.h.

◆ UTF_BACK_1

#define UTF_BACK_1 (   s,
  start,
  i 
)    U16_BACK_1(s, start, i)

Move i backward (towards the beginning of the string) to the first code unit of the code point that has code units before i.

I.e., move i backward by one code point. i must point to the first code unit after the last unit of a code point (i==length is allowed). Same as UTF16_BACK_1.

Precondition
start<i<=length
Postcondition
start<=i<length
Deprecated:
ICU 2.4. Renamed to U16_BACK_1, see utf_old.h.

Definition at line 1171 of file utf_old.h.

◆ UTF_BACK_1_SAFE

#define UTF_BACK_1_SAFE (   s,
  start,
  i 
)    UTF16_BACK_1_SAFE(s, start, i)
Deprecated:
ICU 2.4.

Renamed to U16_BACK_1, see utf_old.h.

Definition at line 1012 of file utf_old.h.

◆ UTF_BACK_1_UNSAFE

#define UTF_BACK_1_UNSAFE (   s,
  i 
)    UTF16_BACK_1_UNSAFE(s, i)
Deprecated:
ICU 2.4.

Renamed to U16_BACK_1_UNSAFE, see utf_old.h.

Definition at line 1009 of file utf_old.h.

◆ UTF_BACK_N

#define UTF_BACK_N (   s,
  start,
  i,
  n 
)    U16_BACK_N(s, start, i, n)

Move i backward (towards the beginning of the string) to the first code unit of the n code points that have code units before i.

I.e., move i backward by n code points. i must point to the first code unit after the last unit of a code point (i==length is allowed). Same as UTF16_BACK_N.

Precondition
start<i<=length
Postcondition
start<=i<length
Deprecated:
ICU 2.4. Renamed to U16_BACK_N, see utf_old.h.

Definition at line 1184 of file utf_old.h.

◆ UTF_BACK_N_SAFE

#define UTF_BACK_N_SAFE (   s,
  start,
  i,
  n 
)    UTF16_BACK_N_SAFE(s, start, i, n)
Deprecated:
ICU 2.4.

Renamed to U16_BACK_N, see utf_old.h.

Definition at line 1019 of file utf_old.h.

◆ UTF_BACK_N_UNSAFE

#define UTF_BACK_N_UNSAFE (   s,
  i,
  n 
)    UTF16_BACK_N_UNSAFE(s, i, n)
Deprecated:
ICU 2.4.

Renamed to U16_BACK_N_UNSAFE, see utf_old.h.

Definition at line 1016 of file utf_old.h.

◆ UTF_CHAR_LENGTH

#define UTF_CHAR_LENGTH (   c)    U16_LENGTH(c)

How many code units are used to encode this code point (1 or 2)? Same as UTF16_CHAR_LENGTH.

Deprecated:
ICU 2.4. Renamed to U16_LENGTH, see utf_old.h.

Definition at line 1063 of file utf_old.h.

◆ UTF_ERROR_VALUE

#define UTF_ERROR_VALUE   0xffff

Error value for all UTFs.

This code point value will be set by macros with error checking if an error is detected.

Deprecated:
ICU 2.4. Obsolete, see utf_old.h.

Definition at line 226 of file utf_old.h.

◆ UTF_FIRST_SURROGATE

#define UTF_FIRST_SURROGATE (   supplementary)    (UChar)(((supplementary)>>10)+0xd7c0)
Deprecated:
ICU 2.4.

Renamed to U16_LEAD, see utf_old.h.

Definition at line 553 of file utf_old.h.

◆ UTF_FWD_1

#define UTF_FWD_1 (   s,
  i,
  length 
)    U16_FWD_1(s, i, length)

Advance i to beyond the code units of the code point that begins at i.

I.e., advance i by one code point. Same as UTF16_FWD_1.

Precondition
0<=i<length
Postcondition
0<i<=length
Deprecated:
ICU 2.4. Renamed to U16_FWD_1, see utf_old.h.

Definition at line 1118 of file utf_old.h.

◆ UTF_FWD_1_SAFE

#define UTF_FWD_1_SAFE (   s,
  i,
  length 
)    UTF16_FWD_1_SAFE(s, i, length)
Deprecated:
ICU 2.4.

Renamed to U16_FWD_1, see utf_old.h.

Definition at line 984 of file utf_old.h.

◆ UTF_FWD_1_UNSAFE

#define UTF_FWD_1_UNSAFE (   s,
  i 
)    UTF16_FWD_1_UNSAFE(s, i)
Deprecated:
ICU 2.4.

Renamed to U16_FWD_1_UNSAFE, see utf_old.h.

Definition at line 981 of file utf_old.h.

◆ UTF_FWD_N

#define UTF_FWD_N (   s,
  i,
  length,
  n 
)    U16_FWD_N(s, i, length, n)

Advance i to beyond the code units of the n code points where the first one begins at i.

I.e., advance i by n code points. Same as UT16_FWD_N.

Precondition
0<=i<length
Postcondition
0<i<=length
Deprecated:
ICU 2.4. Renamed to U16_FWD_N, see utf_old.h.

Definition at line 1129 of file utf_old.h.

◆ UTF_FWD_N_SAFE

#define UTF_FWD_N_SAFE (   s,
  i,
  length,
  n 
)    UTF16_FWD_N_SAFE(s, i, length, n)
Deprecated:
ICU 2.4.

Renamed to U16_FWD_N, see utf_old.h.

Definition at line 991 of file utf_old.h.

◆ UTF_FWD_N_UNSAFE

#define UTF_FWD_N_UNSAFE (   s,
  i,
  n 
)    UTF16_FWD_N_UNSAFE(s, i, n)
Deprecated:
ICU 2.4.

Renamed to U16_FWD_N_UNSAFE, see utf_old.h.

Definition at line 988 of file utf_old.h.

◆ UTF_GET_CHAR

#define UTF_GET_CHAR (   s,
  start,
  i,
  length,
  c 
)    U16_GET(s, start, i, length, c)

Set c to the code point that contains the code unit i.

i could point to the lead or the trail surrogate for the code point. i is not modified. Same as UTF16_GET_CHAR.

Precondition
0<=i<length
Deprecated:
ICU 2.4. Renamed to U16_GET, see utf_old.h.

Definition at line 1081 of file utf_old.h.

◆ UTF_GET_CHAR_SAFE

#define UTF_GET_CHAR_SAFE (   s,
  start,
  i,
  length,
  c,
  strict 
)    UTF16_GET_CHAR_SAFE(s, start, i, length, c, strict)
Deprecated:
ICU 2.4.

Use U16_GET instead, see utf_old.h.

Definition at line 963 of file utf_old.h.

◆ UTF_GET_CHAR_UNSAFE

#define UTF_GET_CHAR_UNSAFE (   s,
  i,
  c 
)    UTF16_GET_CHAR_UNSAFE(s, i, c)
Deprecated:
ICU 2.4.

Renamed to U16_GET_UNSAFE, see utf_old.h.

Definition at line 960 of file utf_old.h.

◆ UTF_IS_ERROR

#define UTF_IS_ERROR (   c)    (((c)&0xfffe)==0xfffe || (c)==UTF8_ERROR_VALUE_1 || (c)==UTF8_ERROR_VALUE_2)

Is a given 32-bit code an error value as returned by one of the macros for any UTF?

Deprecated:
ICU 2.4. Obsolete, see utf_old.h.

Definition at line 234 of file utf_old.h.

◆ UTF_IS_FIRST_SURROGATE

#define UTF_IS_FIRST_SURROGATE (   uchar)    (((uchar)&0xfffffc00)==0xd800)

Is uchar a first/lead surrogate?

Deprecated:
ICU 2.4.

Renamed to U_IS_LEAD and U16_IS_LEAD, see utf_old.h.

Definition at line 537 of file utf_old.h.

◆ UTF_IS_LEAD

#define UTF_IS_LEAD (   uchar)    U16_IS_LEAD(uchar)

Is this code unit the first one of several (a lead surrogate)? Same as UTF16_IS_LEAD.

Deprecated:
ICU 2.4. Renamed to U_IS_LEAD and U16_IS_LEAD, see utf_old.h.

Definition at line 1042 of file utf_old.h.

◆ UTF_IS_SECOND_SURROGATE

#define UTF_IS_SECOND_SURROGATE (   uchar)    (((uchar)&0xfffffc00)==0xdc00)

Is uchar a second/trail surrogate?

Deprecated:
ICU 2.4.

Renamed to U_IS_TRAIL and U16_IS_TRAIL, see utf_old.h.

Definition at line 540 of file utf_old.h.

◆ UTF_IS_SINGLE

#define UTF_IS_SINGLE (   uchar)    U16_IS_SINGLE(uchar)

Does this code unit alone encode a code point (BMP, not a surrogate)? Same as UTF16_IS_SINGLE.

Deprecated:
ICU 2.4. Renamed to U_IS_SINGLE and U16_IS_SINGLE, see utf_old.h.

Definition at line 1035 of file utf_old.h.

◆ UTF_IS_SURROGATE

#define UTF_IS_SURROGATE (   uchar)    (((uchar)&0xfffff800)==0xd800)

Is this code unit or code point a surrogate (U+d800..U+dfff)?

Deprecated:
ICU 2.4.

Renamed to U_IS_SURROGATE and U16_IS_SURROGATE, see utf_old.h.

Definition at line 250 of file utf_old.h.

◆ UTF_IS_SURROGATE_FIRST

#define UTF_IS_SURROGATE_FIRST (   c)    (((c)&0x400)==0)

Assuming c is a surrogate, is it a first/lead surrogate?

Deprecated:
ICU 2.4.

Renamed to U_IS_SURROGATE_LEAD and U16_IS_SURROGATE_LEAD, see utf_old.h.

Definition at line 543 of file utf_old.h.

◆ UTF_IS_TRAIL

#define UTF_IS_TRAIL (   uchar)    U16_IS_TRAIL(uchar)

Is this code unit one of several but not the first one (a trail surrogate)? Same as UTF16_IS_TRAIL.

Deprecated:
ICU 2.4. Renamed to U_IS_TRAIL and U16_IS_TRAIL, see utf_old.h.

Definition at line 1049 of file utf_old.h.

◆ UTF_IS_UNICODE_CHAR

#define UTF_IS_UNICODE_CHAR (   c)
Value:
((uint32_t)(c)<0xd800 || \
((uint32_t)(c)>0xdfff && \
(uint32_t)(c)<=0x10ffff && \
!UTF_IS_UNICODE_NONCHAR(c)))
UTF_IS_UNICODE_NONCHAR
#define UTF_IS_UNICODE_NONCHAR(c)
Is a given 32-bit code point a Unicode noncharacter?
Definition: utf_old.h:257

Is a given 32-bit value a Unicode code point value (0..U+10ffff) that can be assigned a character?

Code points that are not characters include:

  • single surrogate code points (U+d800..U+dfff, 2048 code points)
  • the last two code points on each plane (U+__fffe and U+__ffff, 34 code points)
  • U+fdd0..U+fdef (new with Unicode 3.1, 32 code points)
  • the highest Unicode code point value is U+10ffff

This means that all code points below U+d800 are character code points, and that boundary is tested first for performance.

Deprecated:
ICU 2.4. Renamed to U_IS_UNICODE_CHAR, see utf_old.h.

Definition at line 277 of file utf_old.h.

◆ UTF_IS_UNICODE_NONCHAR

#define UTF_IS_UNICODE_NONCHAR (   c)
Value:
((c)>=0xfdd0 && \
((uint32_t)(c)<=0xfdef || ((c)&0xfffe)==0xfffe) && \
(uint32_t)(c)<=0x10ffff)

Is a given 32-bit code point a Unicode noncharacter?

Deprecated:
ICU 2.4. Renamed to U_IS_UNICODE_NONCHAR, see utf_old.h.

Definition at line 257 of file utf_old.h.

◆ UTF_IS_VALID

#define UTF_IS_VALID (   c)
Value:
(UTF_IS_UNICODE_CHAR(c) && \
(c)!=UTF8_ERROR_VALUE_1 && (c)!=UTF8_ERROR_VALUE_2)
UTF8_ERROR_VALUE_1
#define UTF8_ERROR_VALUE_1
UTF8_ERROR_VALUE_1 and UTF8_ERROR_VALUE_2 are special error values for UTF-8, which need 1 or 2 bytes...
Definition: utf_old.h:211
UTF8_ERROR_VALUE_2
#define UTF8_ERROR_VALUE_2
See documentation on UTF8_ERROR_VALUE_1 for details.
Definition: utf_old.h:218
UTF_IS_UNICODE_CHAR
#define UTF_IS_UNICODE_CHAR(c)
Is a given 32-bit value a Unicode code point value (0..U+10ffff) that can be assigned a character...
Definition: utf_old.h:277

This is a combined macro: Is c a valid Unicode value and not an error code?

Deprecated:
ICU 2.4. Obsolete, see utf_old.h.

Definition at line 242 of file utf_old.h.

◆ UTF_MAX_CHAR_LENGTH

#define UTF_MAX_CHAR_LENGTH   U16_MAX_LENGTH

How many code units are used at most for any Unicode code point (2)? Same as UTF16_MAX_CHAR_LENGTH.

Deprecated:
ICU 2.4. Renamed to U16_MAX_LENGTH, see utf_old.h.

Definition at line 1070 of file utf_old.h.

◆ UTF_NEED_MULTIPLE_UCHAR

#define UTF_NEED_MULTIPLE_UCHAR (   c)    UTF16_NEED_MULTIPLE_UCHAR(c)

Does this code point require multiple code units (is it a supplementary code point)? Same as UTF16_NEED_MULTIPLE_UCHAR.

Deprecated:
ICU 2.4. Use U16_LENGTH or test ((uint32_t)(c)>0xffff) instead.

Definition at line 1056 of file utf_old.h.

◆ UTF_NEXT_CHAR

#define UTF_NEXT_CHAR (   s,
  i,
  length,
  c 
)    U16_NEXT(s, i, length, c)

Set c to the code point that starts at code unit i and advance i to beyond the code units of this code point (post-increment).

i must point to the first code unit of a code point. Otherwise c is set to the trail unit (surrogate) itself. Same as UTF16_NEXT_CHAR.

Precondition
0<=i<length
Postcondition
0<i<=length
Deprecated:
ICU 2.4. Renamed to U16_NEXT, see utf_old.h.

Definition at line 1094 of file utf_old.h.

◆ UTF_NEXT_CHAR_SAFE

#define UTF_NEXT_CHAR_SAFE (   s,
  i,
  length,
  c,
  strict 
)    UTF16_NEXT_CHAR_SAFE(s, i, length, c, strict)
Deprecated:
ICU 2.4.

Use U16_NEXT instead, see utf_old.h.

Definition at line 970 of file utf_old.h.

◆ UTF_NEXT_CHAR_UNSAFE

#define UTF_NEXT_CHAR_UNSAFE (   s,
  i,
  c 
)    UTF16_NEXT_CHAR_UNSAFE(s, i, c)
Deprecated:
ICU 2.4.

Renamed to U16_NEXT_UNSAFE, see utf_old.h.

Definition at line 967 of file utf_old.h.

◆ UTF_PREV_CHAR

#define UTF_PREV_CHAR (   s,
  start,
  i,
  c 
)    U16_PREV(s, start, i, c)

Set c to the code point that has code units before i and move i backward (towards the beginning of the string) to the first code unit of this code point (pre-increment).

i must point to the first code unit after the last unit of a code point (i==length is allowed). Same as UTF16_PREV_CHAR.

Precondition
start<i<=length
Postcondition
start<=i<length
Deprecated:
ICU 2.4. Renamed to U16_PREV, see utf_old.h.

Definition at line 1158 of file utf_old.h.

◆ UTF_PREV_CHAR_SAFE

#define UTF_PREV_CHAR_SAFE (   s,
  start,
  i,
  c,
  strict 
)    UTF16_PREV_CHAR_SAFE(s, start, i, c, strict)
Deprecated:
ICU 2.4.

Use U16_PREV instead, see utf_old.h.

Definition at line 1005 of file utf_old.h.

◆ UTF_PREV_CHAR_UNSAFE

#define UTF_PREV_CHAR_UNSAFE (   s,
  i,
  c 
)    UTF16_PREV_CHAR_UNSAFE(s, i, c)
Deprecated:
ICU 2.4.

Renamed to U16_PREV_UNSAFE, see utf_old.h.

Definition at line 1002 of file utf_old.h.

◆ UTF_SAFE

#define UTF_SAFE

The default choice for general Unicode string macros is to use the ..._SAFE macro implementations with strict=FALSE.

Deprecated:
ICU 2.4. Obsolete, see utf_old.h.

Definition at line 191 of file utf_old.h.

◆ UTF_SECOND_SURROGATE

#define UTF_SECOND_SURROGATE (   supplementary)    (UChar)(((supplementary)&0x3ff)|0xdc00)
Deprecated:
ICU 2.4.

Renamed to U16_TRAIL, see utf_old.h.

Definition at line 556 of file utf_old.h.

◆ UTF_SET_CHAR_LIMIT

#define UTF_SET_CHAR_LIMIT (   s,
  start,
  i,
  length 
)    U16_SET_CP_LIMIT(s, start, i, length)

Take the random-access index i and adjust it so that it points beyond a code point.

The input index points beyond any code unit of a code point and is moved to point beyond the last code unit of the same code point. i is never decremented. In other words, if i points to a trail surrogate that is preceded by a matching lead surrogate, then i is incremented. Otherwise it is not modified. This can be used to start an iteration with UTF_PREV_CHAR() from a random index. Same as UTF16_SET_CHAR_LIMIT.

Precondition
start<i<=length
Postcondition
start<i<=length
Deprecated:
ICU 2.4. Renamed to U16_SET_CP_LIMIT, see utf_old.h.

Definition at line 1200 of file utf_old.h.

◆ UTF_SET_CHAR_LIMIT_SAFE

#define UTF_SET_CHAR_LIMIT_SAFE (   s,
  start,
  i,
  length 
)    UTF16_SET_CHAR_LIMIT_SAFE(s, start, i, length)
Deprecated:
ICU 2.4.

Renamed to U16_SET_CP_LIMIT, see utf_old.h.

Definition at line 1026 of file utf_old.h.

◆ UTF_SET_CHAR_LIMIT_UNSAFE

#define UTF_SET_CHAR_LIMIT_UNSAFE (   s,
  i 
)    UTF16_SET_CHAR_LIMIT_UNSAFE(s, i)
Deprecated:
ICU 2.4.

Renamed to U16_SET_CP_LIMIT_UNSAFE, see utf_old.h.

Definition at line 1023 of file utf_old.h.

◆ UTF_SET_CHAR_START

#define UTF_SET_CHAR_START (   s,
  start,
  i 
)    U16_SET_CP_START(s, start, i)

Take the random-access index i and adjust it so that it points to the beginning of a code point.

The input index points to any code unit of a code point and is moved to point to the first code unit of the same code point. i is never incremented. In other words, if i points to a trail surrogate that is preceded by a matching lead surrogate, then i is decremented. Otherwise it is not modified. This can be used to start an iteration with UTF_NEXT_CHAR() from a random index. Same as UTF16_SET_CHAR_START.

Precondition
start<=i<length
Postcondition
start<=i<length
Deprecated:
ICU 2.4. Renamed to U16_SET_CP_START, see utf_old.h.

Definition at line 1145 of file utf_old.h.

◆ UTF_SET_CHAR_START_SAFE

#define UTF_SET_CHAR_START_SAFE (   s,
  start,
  i 
)    UTF16_SET_CHAR_START_SAFE(s, start, i)
Deprecated:
ICU 2.4.

Renamed to U16_SET_CP_START, see utf_old.h.

Definition at line 998 of file utf_old.h.

◆ UTF_SET_CHAR_START_UNSAFE

#define UTF_SET_CHAR_START_UNSAFE (   s,
  i 
)    UTF16_SET_CHAR_START_UNSAFE(s, i)
Deprecated:
ICU 2.4.

Renamed to U16_SET_CP_START_UNSAFE, see utf_old.h.

Definition at line 995 of file utf_old.h.

◆ UTF_SIZE

#define UTF_SIZE   16

Number of bits in a Unicode string code unit - ICU uses 16-bit Unicode.

Deprecated:
ICU 2.4. Obsolete, see utf_old.h.

Definition at line 183 of file utf_old.h.

◆ UTF_SURROGATE_OFFSET

#define UTF_SURROGATE_OFFSET   ((0xd800<<10UL)+0xdc00-0x10000)

Helper constant for UTF16_GET_PAIR_VALUE.

Deprecated:
ICU 2.4. Renamed to U16_SURROGATE_OFFSET, see utf_old.h.

Definition at line 546 of file utf_old.h.

Variable Documentation

◆ utf8_countTrailBytes

utf8_countTrailBytes

Internal array with numbers of trail bytes for any given byte used in lead byte position.

This is internal since it is not meant to be called directly by external clients; however it is called by public macros in this file and thus must remain stable, and should not be hidden when other internal functions are hidden (otherwise public macros would fail to compile).

Internal:
Do not use. This API is for internal use only.

Definition at line 301 of file utf_old.h.

Generated by   doxygen 1.8.13