1 /* 2 * Copyright (C) 2011 The Android Open Source Project 3 * 4 * Licensed under the Apache License, Version 2.0 (the "License"); 5 * you may not use this file except in compliance with the License. 6 * You may obtain a copy of the License at 7 * 8 * http://www.apache.org/licenses/LICENSE-2.0 9 * 10 * Unless required by applicable law or agreed to in writing, software 11 * distributed under the License is distributed on an "AS IS" BASIS, 12 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 13 * See the License for the specific language governing permissions and 14 * limitations under the License. 15 */ 16 17 #ifndef ART_RUNTIME_UTF_H_ 18 #define ART_RUNTIME_UTF_H_ 19 20 #include "base/macros.h" 21 #include "base/mutex.h" 22 23 #include <stddef.h> 24 #include <stdint.h> 25 26 /* 27 * All UTF-8 in art is actually modified UTF-8. Mostly, this distinction 28 * doesn't matter. 29 * 30 * See http://en.wikipedia.org/wiki/UTF-8#Modified_UTF-8 for the details. 31 */ 32 namespace art { 33 34 namespace mirror { 35 template<class T> class PrimitiveArray; 36 typedef PrimitiveArray<uint16_t> CharArray; 37 } // namespace mirror 38 39 /* 40 * Returns the number of UTF-16 characters in the given modified UTF-8 string. 41 */ 42 size_t CountModifiedUtf8Chars(const char* utf8); 43 44 /* 45 * Returns the number of modified UTF-8 bytes needed to represent the given 46 * UTF-16 string. 47 */ 48 size_t CountUtf8Bytes(const uint16_t* chars, size_t char_count); 49 50 /* 51 * Convert from Modified UTF-8 to UTF-16. 52 */ 53 void ConvertModifiedUtf8ToUtf16(uint16_t* utf16_out, const char* utf8_in); 54 55 /* 56 * Compare two modified UTF-8 strings as UTF-16 code point values in a non-locale sensitive manner 57 */ 58 ALWAYS_INLINE int CompareModifiedUtf8ToModifiedUtf8AsUtf16CodePointValues(const char* utf8_1, 59 const char* utf8_2); 60 61 /* 62 * Compare a null-terminated modified UTF-8 string with a UTF-16 string (not null-terminated) 63 * as code point values in a non-locale sensitive manner. 64 */ 65 int CompareModifiedUtf8ToUtf16AsCodePointValues(const char* utf8, const uint16_t* utf16, 66 size_t utf16_length); 67 68 /* 69 * Convert from UTF-16 to Modified UTF-8. Note that the output is _not_ 70 * NUL-terminated. You probably need to call CountUtf8Bytes before calling 71 * this anyway, so if you want a NUL-terminated string, you know where to 72 * put the NUL byte. 73 */ 74 void ConvertUtf16ToModifiedUtf8(char* utf8_out, const uint16_t* utf16_in, size_t char_count); 75 76 /* 77 * The java.lang.String hashCode() algorithm. 78 */ 79 int32_t ComputeUtf16Hash(mirror::CharArray* chars, int32_t offset, size_t char_count) 80 SHARED_LOCKS_REQUIRED(Locks::mutator_lock_); 81 int32_t ComputeUtf16Hash(const uint16_t* chars, size_t char_count); 82 83 // Compute a hash code of a modified UTF-8 string. Not the standard java hash since it returns a 84 // size_t and hashes individual chars instead of codepoint words. 85 size_t ComputeModifiedUtf8Hash(const char* chars); 86 87 /* 88 * Retrieve the next UTF-16 character or surrogate pair from a UTF-8 string. 89 * single byte, 2-byte and 3-byte UTF-8 sequences result in a single UTF-16 90 * character (possibly one half of a surrogate) whereas 4-byte UTF-8 sequences 91 * result in a surrogate pair. Use GetLeadingUtf16Char and GetTrailingUtf16Char 92 * to process the return value of this function. 93 * 94 * Advances "*utf8_data_in" to the start of the next character. 95 * 96 * WARNING: If a string is corrupted by dropping a '\0' in the middle 97 * of a multi byte sequence, you can end up overrunning the buffer with 98 * reads (and possibly with the writes if the length was computed and 99 * cached before the damage). For performance reasons, this function 100 * assumes that the string being parsed is known to be valid (e.g., by 101 * already being verified). Most strings we process here are coming 102 * out of dex files or other internal translations, so the only real 103 * risk comes from the JNI NewStringUTF call. 104 */ 105 uint32_t GetUtf16FromUtf8(const char** utf8_data_in); 106 107 /** 108 * Gets the leading UTF-16 character from a surrogate pair, or the sole 109 * UTF-16 character from the return value of GetUtf16FromUtf8. 110 */ 111 ALWAYS_INLINE uint16_t GetLeadingUtf16Char(uint32_t maybe_pair); 112 113 /** 114 * Gets the trailing UTF-16 character from a surrogate pair, or 0 otherwise 115 * from the return value of GetUtf16FromUtf8. 116 */ 117 ALWAYS_INLINE uint16_t GetTrailingUtf16Char(uint32_t maybe_pair); 118 119 } // namespace art 120 121 #endif // ART_RUNTIME_UTF_H_ 122