From 8e9aeb9053695a14539653093937158d15385ca6 Mon Sep 17 00:00:00 2001 From: Elliott Hughes Date: Fri, 10 Nov 2017 10:22:07 -0800 Subject: Move libcutils source to C++. Just the minimial changes to get this to actually build, because otherwise we always bog down trying to rewrite everything (when the real answer is usually "stop using libcutils, it's awful"). This doesn't move a handful of files: two are basically just BSD libc source, a couple have outstanding code reviews, and one can be deleted (but I'll do that in a separate change). I'm also skipping the presubmit hooks because otherwise clang-format wants to reformat everything. I'll follow up with that... Bug: N/A Test: builds Change-Id: I06403f465b67c8e493bad466dd76b1151eed5993 --- libcutils/strdup16to8.cpp | 168 ++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 168 insertions(+) create mode 100644 libcutils/strdup16to8.cpp (limited to 'libcutils/strdup16to8.cpp') diff --git a/libcutils/strdup16to8.cpp b/libcutils/strdup16to8.cpp new file mode 100644 index 000000000..d89181e14 --- /dev/null +++ b/libcutils/strdup16to8.cpp @@ -0,0 +1,168 @@ +/* libs/cutils/strdup16to8.c +** +** Copyright 2006, The Android Open Source Project +** +** Licensed under the Apache License, Version 2.0 (the "License"); +** you may not use this file except in compliance with the License. +** You may obtain a copy of the License at +** +** http://www.apache.org/licenses/LICENSE-2.0 +** +** Unless required by applicable law or agreed to in writing, software +** distributed under the License is distributed on an "AS IS" BASIS, +** WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +** See the License for the specific language governing permissions and +** limitations under the License. +*/ + +#include + +#include +#include /* for SIZE_MAX */ +#include + + +/** + * Given a UTF-16 string, compute the length of the corresponding UTF-8 + * string in bytes. + */ +extern size_t strnlen16to8(const char16_t* utf16Str, size_t len) +{ + size_t utf8Len = 0; + + /* A small note on integer overflow. The result can + * potentially be as big as 3*len, which will overflow + * for len > SIZE_MAX/3. + * + * Moreover, the result of a strnlen16to8 is typically used + * to allocate a destination buffer to strncpy16to8 which + * requires one more byte to terminate the UTF-8 copy, and + * this is generally done by careless users by incrementing + * the result without checking for integer overflows, e.g.: + * + * dst = malloc(strnlen16to8(utf16,len)+1) + * + * Due to this, the following code will try to detect + * overflows, and never return more than (SIZE_MAX-1) + * when it detects one. A careless user will try to malloc + * SIZE_MAX bytes, which will return NULL which can at least + * be detected appropriately. + * + * As far as I know, this function is only used by strndup16(), + * but better be safe than sorry. + */ + + /* Fast path for the usual case where 3*len is < SIZE_MAX-1. + */ + if (len < (SIZE_MAX-1)/3) { + while (len != 0) { + len--; + unsigned int uic = *utf16Str++; + + if (uic > 0x07ff) + utf8Len += 3; + else if (uic > 0x7f || uic == 0) + utf8Len += 2; + else + utf8Len++; + } + return utf8Len; + } + + /* The slower but paranoid version */ + while (len != 0) { + len--; + unsigned int uic = *utf16Str++; + size_t utf8Cur = utf8Len; + + if (uic > 0x07ff) + utf8Len += 3; + else if (uic > 0x7f || uic == 0) + utf8Len += 2; + else + utf8Len++; + + if (utf8Len < utf8Cur) /* overflow detected */ + return SIZE_MAX-1; + } + + /* don't return SIZE_MAX to avoid common user bug */ + if (utf8Len == SIZE_MAX) + utf8Len = SIZE_MAX-1; + + return utf8Len; +} + + +/** + * Convert a Java-Style UTF-16 string + length to a JNI-Style UTF-8 string. + * + * This basically means: embedded \0's in the UTF-16 string are encoded + * as "0xc0 0x80" + * + * Make sure you allocate "utf8Str" with the result of strlen16to8() + 1, + * not just "len". + * + * Please note, a terminated \0 is always added, so your result will always + * be "strlen16to8() + 1" bytes long. + */ +extern char* strncpy16to8(char* utf8Str, const char16_t* utf16Str, size_t len) +{ + char* utf8cur = utf8Str; + + /* Note on overflows: We assume the user did check the result of + * strnlen16to8() properly or at a minimum checked the result of + * its malloc(SIZE_MAX) in case of overflow. + */ + while (len != 0) { + len--; + unsigned int uic = *utf16Str++; + + if (uic > 0x07ff) { + *utf8cur++ = (uic >> 12) | 0xe0; + *utf8cur++ = ((uic >> 6) & 0x3f) | 0x80; + *utf8cur++ = (uic & 0x3f) | 0x80; + } else if (uic > 0x7f || uic == 0) { + *utf8cur++ = (uic >> 6) | 0xc0; + *utf8cur++ = (uic & 0x3f) | 0x80; + } else { + *utf8cur++ = uic; + + if (uic == 0) { + break; + } + } + } + + *utf8cur = '\0'; + + return utf8Str; +} + +/** + * Convert a UTF-16 string to UTF-8. + * + */ +char * strndup16to8 (const char16_t* s, size_t n) +{ + if (s == NULL) { + return NULL; + } + + size_t len = strnlen16to8(s, n); + + /* We are paranoid, and we check for SIZE_MAX-1 + * too since it is an overflow value for our + * strnlen16to8 implementation. + */ + if (len >= SIZE_MAX-1) + return NULL; + + char* ret = static_cast(malloc(len + 1)); + if (ret == NULL) + return NULL; + + strncpy16to8 (ret, s, n); + + return ret; +} -- cgit v1.2.3-54-g00ecf