mirror of
https://github.com/nodejs/node.git
synced 2026-11-09 15:11:11 -05:00
Felix Geisendörfer
0da4c67165
Previously v8's WriteUtf8 function would produce invalid utf-8 output when encountering unmatched surrogate code units [1]. The new REPLACE_INVALID_UTF8 option fixes that by replacing invalid code points with the unicode replacement character. [1]: JS Strings are defined as arrays of 16 bit unsigned integers. There is no unicode enforcement, so one can easily end up with invalid unicode code unit sequences inside a string.
73 lines
2.7 KiB
C++
73 lines
2.7 KiB
C++
// Copyright Joyent, Inc. and other Node contributors.
|
|
//
|
|
// Permission is hereby granted, free of charge, to any person obtaining a
|
|
// copy of this software and associated documentation files (the
|
|
// "Software"), to deal in the Software without restriction, including
|
|
// without limitation the rights to use, copy, modify, merge, publish,
|
|
// distribute, sublicense, and/or sell copies of the Software, and to permit
|
|
// persons to whom the Software is furnished to do so, subject to the
|
|
// following conditions:
|
|
//
|
|
// The above copyright notice and this permission notice shall be included
|
|
// in all copies or substantial portions of the Software.
|
|
//
|
|
// THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS
|
|
// OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
|
// MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN
|
|
// NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM,
|
|
// DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
|
|
// OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE
|
|
// USE OR OTHER DEALINGS IN THE SOFTWARE.
|
|
|
|
#ifndef SRC_STRING_BYTES_H_
|
|
#define SRC_STRING_BYTES_H_
|
|
|
|
// Decodes a v8::Handle<v8::String> or Buffer to a raw char*
|
|
|
|
#include "v8.h"
|
|
#include "node.h"
|
|
|
|
namespace node {
|
|
|
|
extern int WRITE_UTF8_FLAGS;
|
|
|
|
using v8::Handle;
|
|
using v8::Local;
|
|
using v8::String;
|
|
using v8::Value;
|
|
|
|
class StringBytes {
|
|
public:
|
|
// Does the string match the encoding? Quick but non-exhaustive.
|
|
// Example: a HEX string must have a length that's a multiple of two.
|
|
// FIXME(bnoordhuis) IsMaybeValidString()? Naming things is hard...
|
|
static bool IsValidString(Handle<String> string, enum encoding enc);
|
|
|
|
// Fast, but can be 2 bytes oversized for Base64, and
|
|
// as much as triple UTF-8 strings <= 65536 chars in length
|
|
static size_t StorageSize(Handle<Value> val, enum encoding enc);
|
|
|
|
// Precise byte count, but slightly slower for Base64 and
|
|
// very much slower for UTF-8
|
|
static size_t Size(Handle<Value> val, enum encoding enc);
|
|
|
|
// Write the bytes from the string or buffer into the char*
|
|
// returns the number of bytes written, which will always be
|
|
// <= buflen. Use StorageSize/Size first to know how much
|
|
// memory to allocate.
|
|
static size_t Write(char* buf,
|
|
size_t buflen,
|
|
Handle<Value> val,
|
|
enum encoding enc,
|
|
int* chars_written = NULL);
|
|
|
|
// Take the bytes in the src, and turn it into a Buffer or String.
|
|
static Local<Value> Encode(const char* buf,
|
|
size_t buflen,
|
|
enum encoding encoding);
|
|
};
|
|
|
|
} // namespace node
|
|
|
|
#endif // SRC_STRING_BYTES_H_
|