1.1 --- /dev/null Thu Jan 01 00:00:00 1970 +0000
1.2 +++ b/media/omx-plugin/include/ics/utils/Unicode.h Wed Dec 31 06:09:35 2014 +0100
1.3 @@ -0,0 +1,170 @@
1.4 +/*
1.5 + * Copyright (C) 2005 The Android Open Source Project
1.6 + *
1.7 + * Licensed under the Apache License, Version 2.0 (the "License");
1.8 + * you may not use this file except in compliance with the License.
1.9 + * You may obtain a copy of the License at
1.10 + *
1.11 + * http://www.apache.org/licenses/LICENSE-2.0
1.12 + *
1.13 + * Unless required by applicable law or agreed to in writing, software
1.14 + * distributed under the License is distributed on an "AS IS" BASIS,
1.15 + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
1.16 + * See the License for the specific language governing permissions and
1.17 + * limitations under the License.
1.18 + */
1.19 +
1.20 +#ifndef ANDROID_UNICODE_H
1.21 +#define ANDROID_UNICODE_H
1.22 +
1.23 +#include <sys/types.h>
1.24 +#include <stdint.h>
1.25 +
1.26 +extern "C" {
1.27 +
1.28 +#if !defined(__cplusplus) || __cplusplus == 199711L // C or C++98
1.29 +typedef uint32_t char32_t;
1.30 +typedef uint16_t char16_t;
1.31 +#endif
1.32 +
1.33 +// Standard string functions on char16_t strings.
1.34 +int strcmp16(const char16_t *, const char16_t *);
1.35 +int strncmp16(const char16_t *s1, const char16_t *s2, size_t n);
1.36 +size_t strlen16(const char16_t *);
1.37 +size_t strnlen16(const char16_t *, size_t);
1.38 +char16_t *strcpy16(char16_t *, const char16_t *);
1.39 +char16_t *strncpy16(char16_t *, const char16_t *, size_t);
1.40 +
1.41 +// Version of comparison that supports embedded nulls.
1.42 +// This is different than strncmp() because we don't stop
1.43 +// at a nul character and consider the strings to be different
1.44 +// if the lengths are different (thus we need to supply the
1.45 +// lengths of both strings). This can also be used when
1.46 +// your string is not nul-terminated as it will have the
1.47 +// equivalent result as strcmp16 (unlike strncmp16).
1.48 +int strzcmp16(const char16_t *s1, size_t n1, const char16_t *s2, size_t n2);
1.49 +
1.50 +// Version of strzcmp16 for comparing strings in different endianness.
1.51 +int strzcmp16_h_n(const char16_t *s1H, size_t n1, const char16_t *s2N, size_t n2);
1.52 +
1.53 +// Standard string functions on char32_t strings.
1.54 +size_t strlen32(const char32_t *);
1.55 +size_t strnlen32(const char32_t *, size_t);
1.56 +
1.57 +/**
1.58 + * Measure the length of a UTF-32 string in UTF-8. If the string is invalid
1.59 + * such as containing a surrogate character, -1 will be returned.
1.60 + */
1.61 +ssize_t utf32_to_utf8_length(const char32_t *src, size_t src_len);
1.62 +
1.63 +/**
1.64 + * Stores a UTF-8 string converted from "src" in "dst", if "dst_length" is not
1.65 + * large enough to store the string, the part of the "src" string is stored
1.66 + * into "dst" as much as possible. See the examples for more detail.
1.67 + * Returns the size actually used for storing the string.
1.68 + * dst" is not null-terminated when dst_len is fully used (like strncpy).
1.69 + *
1.70 + * Example 1
1.71 + * "src" == \u3042\u3044 (\xE3\x81\x82\xE3\x81\x84)
1.72 + * "src_len" == 2
1.73 + * "dst_len" >= 7
1.74 + * ->
1.75 + * Returned value == 6
1.76 + * "dst" becomes \xE3\x81\x82\xE3\x81\x84\0
1.77 + * (note that "dst" is null-terminated)
1.78 + *
1.79 + * Example 2
1.80 + * "src" == \u3042\u3044 (\xE3\x81\x82\xE3\x81\x84)
1.81 + * "src_len" == 2
1.82 + * "dst_len" == 5
1.83 + * ->
1.84 + * Returned value == 3
1.85 + * "dst" becomes \xE3\x81\x82\0
1.86 + * (note that "dst" is null-terminated, but \u3044 is not stored in "dst"
1.87 + * since "dst" does not have enough size to store the character)
1.88 + *
1.89 + * Example 3
1.90 + * "src" == \u3042\u3044 (\xE3\x81\x82\xE3\x81\x84)
1.91 + * "src_len" == 2
1.92 + * "dst_len" == 6
1.93 + * ->
1.94 + * Returned value == 6
1.95 + * "dst" becomes \xE3\x81\x82\xE3\x81\x84
1.96 + * (note that "dst" is NOT null-terminated, like strncpy)
1.97 + */
1.98 +void utf32_to_utf8(const char32_t* src, size_t src_len, char* dst);
1.99 +
1.100 +/**
1.101 + * Returns the unicode value at "index".
1.102 + * Returns -1 when the index is invalid (equals to or more than "src_len").
1.103 + * If returned value is positive, it is able to be converted to char32_t, which
1.104 + * is unsigned. Then, if "next_index" is not NULL, the next index to be used is
1.105 + * stored in "next_index". "next_index" can be NULL.
1.106 + */
1.107 +int32_t utf32_from_utf8_at(const char *src, size_t src_len, size_t index, size_t *next_index);
1.108 +
1.109 +
1.110 +/**
1.111 + * Returns the UTF-8 length of UTF-16 string "src".
1.112 + */
1.113 +ssize_t utf16_to_utf8_length(const char16_t *src, size_t src_len);
1.114 +
1.115 +/**
1.116 + * Converts a UTF-16 string to UTF-8. The destination buffer must be large
1.117 + * enough to fit the UTF-16 as measured by utf16_to_utf8_length with an added
1.118 + * NULL terminator.
1.119 + */
1.120 +void utf16_to_utf8(const char16_t* src, size_t src_len, char* dst);
1.121 +
1.122 +/**
1.123 + * Returns the length of "src" when "src" is valid UTF-8 string.
1.124 + * Returns 0 if src is NULL or 0-length string. Returns -1 when the source
1.125 + * is an invalid string.
1.126 + *
1.127 + * This function should be used to determine whether "src" is valid UTF-8
1.128 + * characters with valid unicode codepoints. "src" must be null-terminated.
1.129 + *
1.130 + * If you are going to use other utf8_to_... functions defined in this header
1.131 + * with string which may not be valid UTF-8 with valid codepoint (form 0 to
1.132 + * 0x10FFFF), you should use this function before calling others, since the
1.133 + * other functions do not check whether the string is valid UTF-8 or not.
1.134 + *
1.135 + * If you do not care whether "src" is valid UTF-8 or not, you should use
1.136 + * strlen() as usual, which should be much faster.
1.137 + */
1.138 +ssize_t utf8_length(const char *src);
1.139 +
1.140 +/**
1.141 + * Measure the length of a UTF-32 string.
1.142 + */
1.143 +size_t utf8_to_utf32_length(const char *src, size_t src_len);
1.144 +
1.145 +/**
1.146 + * Stores a UTF-32 string converted from "src" in "dst". "dst" must be large
1.147 + * enough to store the entire converted string as measured by
1.148 + * utf8_to_utf32_length plus space for a NULL terminator.
1.149 + */
1.150 +void utf8_to_utf32(const char* src, size_t src_len, char32_t* dst);
1.151 +
1.152 +/**
1.153 + * Returns the UTF-16 length of UTF-8 string "src".
1.154 + */
1.155 +ssize_t utf8_to_utf16_length(const uint8_t* src, size_t srcLen);
1.156 +
1.157 +/**
1.158 + * Convert UTF-8 to UTF-16 including surrogate pairs.
1.159 + * Returns a pointer to the end of the string (where a null terminator might go
1.160 + * if you wanted to add one).
1.161 + */
1.162 +char16_t* utf8_to_utf16_no_null_terminator(const uint8_t* src, size_t srcLen, char16_t* dst);
1.163 +
1.164 +/**
1.165 + * Convert UTF-8 to UTF-16 including surrogate pairs. The destination buffer
1.166 + * must be large enough to hold the result as measured by utf8_to_utf16_length
1.167 + * plus an added NULL terminator.
1.168 + */
1.169 +void utf8_to_utf16(const uint8_t* src, size_t srcLen, char16_t* dst);
1.170 +
1.171 +}
1.172 +
1.173 +#endif
