You are viewing a plain text version of this content. The canonical link for it is here.
Posted to dev@weex.apache.org by GitBox <gi...@apache.org> on 2018/09/19 08:53:16 UTC
[GitHub] YorkShen closed pull request #1540: use gnustl_static instead of c++_static, reimplement utf16 convert to…
YorkShen closed pull request #1540: use gnustl_static instead of c++_static, reimplement utf16 convert to…
URL: https://github.com/apache/incubator-weex/pull/1540
This is a PR merged from a forked repository.
As GitHub hides the original diff on merge, it is displayed below for
the sake of provenance:
As this is a foreign pull request (from a fork), the diff is supplied
below (as it won't show otherwise due to GitHub magic):
diff --git a/android/sdk/build.gradle b/android/sdk/build.gradle
index 3b0d24cbe8..e3733a2695 100755
--- a/android/sdk/build.gradle
+++ b/android/sdk/build.gradle
@@ -124,7 +124,7 @@ android {
cmake {
arguments '-DANDROID_PLATFORM=android-14',
'-DANDROID_TOOLCHAIN=gcc',
- '-DANDROID_STL=c++_static',
+ '-DANDROID_STL=gnustl_static',
'-DCMAKE_BUILD_TYPE=Release'
}
}
@@ -267,4 +267,4 @@ task checkNdkVersion() {
}
}
-preBuild.dependsOn checkNdkVersion
\ No newline at end of file
+preBuild.dependsOn checkNdkVersion
diff --git a/android/sdk/libs/armeabi-v7a/libweexcore.so b/android/sdk/libs/armeabi-v7a/libweexcore.so
index 54b1d8a8f1..5a99801276 100644
Binary files a/android/sdk/libs/armeabi-v7a/libweexcore.so and b/android/sdk/libs/armeabi-v7a/libweexcore.so differ
diff --git a/android/sdk/libs/armeabi/libweexcore.so b/android/sdk/libs/armeabi/libweexcore.so
index 73160fe45f..2933571d03 100644
Binary files a/android/sdk/libs/armeabi/libweexcore.so and b/android/sdk/libs/armeabi/libweexcore.so differ
diff --git a/weex_core/Source/CMakeLists.txt b/weex_core/Source/CMakeLists.txt
index e4b8e26653..d2b782b3a9 100644
--- a/weex_core/Source/CMakeLists.txt
+++ b/weex_core/Source/CMakeLists.txt
@@ -1,8 +1,12 @@
cmake_minimum_required(VERSION 3.4.1)
set(WEEXCORE_LIBRARY_NAME weexcore)
-set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -std=c++11")
-#add_compile_options(-std=c++11)
+message("${ANDROID_STL} ")
+if ("${ANDROID_STL}" STREQUAL "c++_static")
+ set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -std=c++1y")
+elseif ("${ANDROID_STL}" STREQUAL "gnustl_static")
+ set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -std=gnu++1y")
+endif ()
add_compile_options(-fexceptions)
@@ -24,6 +28,7 @@ set(COMMON_SRCS
./base/message_loop/message_loop.cc
./base/message_loop/message_pump_posix.cc
./base/message_loop/message_pump_android.cc
+ ./base/third_party/icu/icu_utf.cpp
./core/render/manager/render_manager.cpp
./core/render/page/render_page.cpp
diff --git a/weex_core/Source/android/bridge/script_bridge_in_multi_so.cpp b/weex_core/Source/android/bridge/script_bridge_in_multi_so.cpp
index 0632ddec5e..03b6e141f2 100644
--- a/weex_core/Source/android/bridge/script_bridge_in_multi_so.cpp
+++ b/weex_core/Source/android/bridge/script_bridge_in_multi_so.cpp
@@ -20,6 +20,7 @@
#include "script_bridge_in_multi_so.h"
#include <base/thread/waitable_event.h>
#include <dlfcn.h>
+#include <malloc.h>
#include "android/base/log_utils.h"
#include "android/bridge/multi_so_initializer.h"
#include "android/bridge/script/script_side_in_multi_so.h"
@@ -497,4 +498,4 @@ FunctionsExposedByCore *ScriptBridgeInMultiSo::GetExposedFunctions() {
memcpy(functions, &temp, sizeof(FunctionsExposedByCore));
return functions;
}
-} // namespace WeexCore
\ No newline at end of file
+} // namespace WeexCore
diff --git a/weex_core/Source/android/utils/IPCStringResult.cpp b/weex_core/Source/android/utils/IPCStringResult.cpp
index ac8eccf426..95d7b92493 100644
--- a/weex_core/Source/android/utils/IPCStringResult.cpp
+++ b/weex_core/Source/android/utils/IPCStringResult.cpp
@@ -16,6 +16,7 @@
* specific language governing permissions and limitations
* under the License.
*/
+#include <malloc.h>
#include "IPCStringResult.h"
diff --git a/weex_core/Source/base/message_loop/message_loop.h b/weex_core/Source/base/message_loop/message_loop.h
index d56853d678..e988f78f71 100644
--- a/weex_core/Source/base/message_loop/message_loop.h
+++ b/weex_core/Source/base/message_loop/message_loop.h
@@ -19,6 +19,7 @@
#ifndef BASE_MESSAGE_LOOP_MESSAGE_LOOP_H
#define BASE_MESSAGE_LOOP_MESSAGE_LOOP_H
+#include <memory>
#include <deque>
#include <mutex>
#include <queue>
diff --git a/weex_core/Source/base/string_util.h b/weex_core/Source/base/string_util.h
index d08d0b5250..a993078994 100644
--- a/weex_core/Source/base/string_util.h
+++ b/weex_core/Source/base/string_util.h
@@ -22,11 +22,15 @@
#include <sstream>
#include <string>
-#include <codecvt>
+#include <malloc.h>
+
+#include "base/third_party/icu/icu_utf.h"
namespace weex {
namespace base {
+constexpr int32_t kErrorCodePoint = 0xFFFD;
+
template <typename T>
std::string to_string(T value) {
std::ostringstream os;
@@ -34,11 +38,50 @@ std::string to_string(T value) {
return os.str();
}
+static bool IsValidCodepoint(uint32_t code_point) {
+ // Excludes the surrogate code points ([0xD800, 0xDFFF]) and
+ // codepoints larger than 0x10FFFF (the highest codepoint allowed).
+ // Non-characters and unassigned codepoints are allowed.
+ return code_point < 0xD800u ||
+ (code_point >= 0xE000u && code_point <= 0x10FFFFu);
+}
+
+static uint32_t convert_single_char(char16_t in) {
+ if (!CBU16_IS_SINGLE(in) || !IsValidCodepoint(in)) {
+ return kErrorCodePoint;
+ }
+ return in;
+}
+
inline static std::string to_utf8(uint16_t* utf16, size_t length) {
char16_t *WC = reinterpret_cast<char16_t *>(utf16);
- std::u16string str(WC, length);
- /* 转换宽字符字符串 */
- return std::wstring_convert<std::codecvt_utf8_utf16<char16_t>, char16_t>{}.to_bytes(str);
+ char* dest = static_cast<char*>(malloc(length * sizeof(char16_t) + sizeof(char16_t)));
+ memset(dest, 0, length * sizeof(char16_t) + sizeof(char16_t));
+ int32_t i = 0;
+ int32_t d_len = 0;
+ int32_t* dest_len = &d_len;
+ // Always have another symbol in order to avoid checking boundaries in the
+ // middle of the surrogate pair.
+ while (i < length - 1) {
+ int32_t code_point;
+
+ if (CBU16_IS_LEAD(WC[i]) && CBU16_IS_TRAIL(WC[i + 1])) {
+ code_point = CBU16_GET_SUPPLEMENTARY(WC[i], WC[i + 1]);
+ i += 2;
+ } else {
+ code_point = convert_single_char(WC[i]);
+ ++i;
+ }
+
+ CBU8_APPEND_UNSAFE(dest, *dest_len, code_point);
+ }
+
+ if (i < length)
+ CBU8_APPEND_UNSAFE(dest, *dest_len, convert_single_char(WC[i]));
+
+ std::string output(dest);
+ free(dest);
+ return output;
}
} // namespace base
diff --git a/weex_core/Source/base/third_party/icu/icu_utf.cpp b/weex_core/Source/base/third_party/icu/icu_utf.cpp
new file mode 100644
index 0000000000..025081b115
--- /dev/null
+++ b/weex_core/Source/base/third_party/icu/icu_utf.cpp
@@ -0,0 +1,149 @@
+/**
+ * Licensed to the Apache Software Foundation (ASF) under one
+ * or more contributor license agreements. See the NOTICE file
+ * distributed with this work for additional information
+ * regarding copyright ownership. The ASF licenses this file
+ * to you 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.
+ */
+// © 2016 and later: Unicode, Inc. and others.
+// License & terms of use: http://www.unicode.org/copyright.html
+/*
+******************************************************************************
+*
+* Copyright (C) 1999-2012, International Business Machines
+* Corporation and others. All Rights Reserved.
+*
+******************************************************************************
+* file name: utf_impl.cpp
+* encoding: UTF-8
+* tab size: 8 (not used)
+* indentation:4
+*
+* created on: 1999sep13
+* created by: Markus W. Scherer
+*
+* This file provides implementation functions for macros in the utfXX.h
+* that would otherwise be too long as macros.
+*/
+
+#include "base/third_party/icu/icu_utf.h"
+
+namespace base_icu {
+
+// source/common/utf_impl.cpp
+
+static const UChar32
+utf8_errorValue[6]={
+ // Same values as UTF8_ERROR_VALUE_1, UTF8_ERROR_VALUE_2, UTF_ERROR_VALUE,
+ // but without relying on the obsolete unicode/utf_old.h.
+ 0x15, 0x9f, 0xffff,
+ 0x10ffff
+};
+
+static UChar32
+errorValue(int32_t count, int8_t strict) {
+ if(strict>=0) {
+ return utf8_errorValue[count];
+ } else if(strict==-3) {
+ return 0xfffd;
+ } else {
+ return CBU_SENTINEL;
+ }
+}
+
+/*
+ * Handle the non-inline part of the U8_NEXT() and U8_NEXT_FFFD() macros
+ * and their obsolete sibling UTF8_NEXT_CHAR_SAFE().
+ *
+ * U8_NEXT() supports NUL-terminated strings indicated via length<0.
+ *
+ * The "strict" parameter controls the error behavior:
+ * <0 "Safe" behavior of U8_NEXT():
+ * -1: All illegal byte sequences yield U_SENTINEL=-1.
+ * -2: Same as -1, except for lenient treatment of surrogate code points as legal.
+ * Some implementations use this for roundtripping of
+ * Unicode 16-bit strings that are not well-formed UTF-16, that is, they
+ * contain unpaired surrogates.
+ * -3: All illegal byte sequences yield U+FFFD.
+ * 0 Obsolete "safe" behavior of UTF8_NEXT_CHAR_SAFE(..., FALSE):
+ * All illegal byte sequences yield a positive code point such that this
+ * result code point would be encoded with the same number of bytes as
+ * the illegal sequence.
+ * >0 Obsolete "strict" behavior of UTF8_NEXT_CHAR_SAFE(..., TRUE):
+ * Same as the obsolete "safe" behavior, but non-characters are also treated
+ * like illegal sequences.
+ *
+ * Note that a UBool is the same as an int8_t.
+ */
+UChar32
+utf8_nextCharSafeBody(const uint8_t *s, int32_t *pi, int32_t length, UChar32 c, UBool strict) {
+ // *pi is one after byte c.
+ int32_t i=*pi;
+ // length can be negative for NUL-terminated strings: Read and validate one byte at a time.
+ if(i==length || c>0xf4) {
+ // end of string, or not a lead byte
+ } else if(c>=0xf0) {
+ // Test for 4-byte sequences first because
+ // U8_NEXT() handles shorter valid sequences inline.
+ uint8_t t1=s[i], t2, t3;
+ c&=7;
+ if(CBU8_IS_VALID_LEAD4_AND_T1(c, t1) &&
+ ++i!=length && (t2=s[i]-0x80)<=0x3f &&
+ ++i!=length && (t3=s[i]-0x80)<=0x3f) {
+ ++i;
+ c=(c<<18)|((t1&0x3f)<<12)|(t2<<6)|t3;
+ // strict: forbid non-characters like U+fffe
+ if(strict<=0 || !CBU_IS_UNICODE_NONCHAR(c)) {
+ *pi=i;
+ return c;
+ }
+ }
+ } else if(c>=0xe0) {
+ c&=0xf;
+ if(strict!=-2) {
+ uint8_t t1=s[i], t2;
+ if(CBU8_IS_VALID_LEAD3_AND_T1(c, t1) &&
+ ++i!=length && (t2=s[i]-0x80)<=0x3f) {
+ ++i;
+ c=(c<<12)|((t1&0x3f)<<6)|t2;
+ // strict: forbid non-characters like U+fffe
+ if(strict<=0 || !CBU_IS_UNICODE_NONCHAR(c)) {
+ *pi=i;
+ return c;
+ }
+ }
+ } else {
+ // strict=-2 -> lenient: allow surrogates
+ uint8_t t1=s[i]-0x80, t2;
+ if(t1<=0x3f && (c>0 || t1>=0x20) &&
+ ++i!=length && (t2=s[i]-0x80)<=0x3f) {
+ *pi=i+1;
+ return (c<<12)|(t1<<6)|t2;
+ }
+ }
+ } else if(c>=0xc2) {
+ uint8_t t1=s[i]-0x80;
+ if(t1<=0x3f) {
+ *pi=i+1;
+ return ((c-0xc0)<<6)|t1;
+ }
+ } // else 0x80<=c<0xc2 is not a lead byte
+
+ /* error handling */
+ c=errorValue(i-*pi, strict);
+ *pi=i;
+ return c;
+}
+
+} // namespace base_icu
diff --git a/weex_core/Source/base/third_party/icu/icu_utf.h b/weex_core/Source/base/third_party/icu/icu_utf.h
new file mode 100644
index 0000000000..de172f8337
--- /dev/null
+++ b/weex_core/Source/base/third_party/icu/icu_utf.h
@@ -0,0 +1,460 @@
+/**
+ * Licensed to the Apache Software Foundation (ASF) under one
+ * or more contributor license agreements. See the NOTICE file
+ * distributed with this work for additional information
+ * regarding copyright ownership. The ASF licenses this file
+ * to you 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.
+ */
+// © 2016 and later: Unicode, Inc. and others.
+// License & terms of use: http://www.unicode.org/copyright.html
+/*
+******************************************************************************
+*
+* Copyright (C) 1999-2015, International Business Machines
+* Corporation and others. All Rights Reserved.
+*
+******************************************************************************
+*/
+
+#ifndef BASE_THIRD_PARTY_ICU_ICU_UTF_H_
+#define BASE_THIRD_PARTY_ICU_ICU_UTF_H_
+
+#include <stdint.h>
+
+namespace base_icu {
+
+// source/common/unicode/umachine.h
+
+/** The ICU boolean type @stable ICU 2.0 */
+typedef int8_t UBool;
+
+/**
+ * Define UChar32 as a type for single Unicode code points.
+ * UChar32 is a signed 32-bit integer (same as int32_t).
+ *
+ * The Unicode code point range is 0..0x10ffff.
+ * All other values (negative or >=0x110000) are illegal as Unicode code points.
+ * They may be used as sentinel values to indicate "done", "error"
+ * or similar non-code point conditions.
+ *
+ * Before ICU 2.4 (Jitterbug 2146), UChar32 was defined
+ * to be wchar_t if that is 32 bits wide (wchar_t may be signed or unsigned)
+ * or else to be uint32_t.
+ * That is, the definition of UChar32 was platform-dependent.
+ *
+ * @see U_SENTINEL
+ * @stable ICU 2.4
+ */
+typedef int32_t UChar32;
+
+/**
+ * This value is intended for sentinel values for APIs that
+ * (take or) return single code points (UChar32).
+ * It is outside of the Unicode code point range 0..0x10ffff.
+ *
+ * For example, a "done" or "error" value in a new API
+ * could be indicated with U_SENTINEL.
+ *
+ * ICU APIs designed before ICU 2.4 usually define service-specific "done"
+ * values, mostly 0xffff.
+ * Those may need to be distinguished from
+ * actual U+ffff text contents by calling functions like
+ * CharacterIterator::hasNext() or UnicodeString::length().
+ *
+ * @return -1
+ * @see UChar32
+ * @stable ICU 2.4
+ */
+#define CBU_SENTINEL (-1)
+
+// source/common/unicode/utf.h
+
+/**
+ * Is this code point a Unicode noncharacter?
+ * @param c 32-bit code point
+ * @return TRUE or FALSE
+ * @stable ICU 2.4
+ */
+#define CBU_IS_UNICODE_NONCHAR(c) \
+ ((c)>=0xfdd0 && \
+ ((c)<=0xfdef || ((c)&0xfffe)==0xfffe) && (c)<=0x10ffff)
+
+/**
+ * Is c 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.
+ *
+ * @param c 32-bit code point
+ * @return TRUE or FALSE
+ * @stable ICU 2.4
+ */
+#define CBU_IS_UNICODE_CHAR(c) \
+ ((uint32_t)(c)<0xd800 || \
+ (0xdfff<(c) && (c)<=0x10ffff && !CBU_IS_UNICODE_NONCHAR(c)))
+
+/**
+ * Is this code point a surrogate (U+d800..U+dfff)?
+ * @param c 32-bit code point
+ * @return TRUE or FALSE
+ * @stable ICU 2.4
+ */
+#define CBU_IS_SURROGATE(c) (((c)&0xfffff800)==0xd800)
+
+/**
+ * Assuming c is a surrogate code point (U_IS_SURROGATE(c)),
+ * is it a lead surrogate?
+ * @param c 32-bit code point
+ * @return TRUE or FALSE
+ * @stable ICU 2.4
+ */
+#define CBU_IS_SURROGATE_LEAD(c) (((c)&0x400)==0)
+
+// source/common/unicode/utf8.h
+
+/**
+ * Internal bit vector for 3-byte UTF-8 validity check, for use in U8_IS_VALID_LEAD3_AND_T1.
+ * Each bit indicates whether one lead byte + first trail byte pair starts a valid sequence.
+ * Lead byte E0..EF bits 3..0 are used as byte index,
+ * first trail byte bits 7..5 are used as bit index into that byte.
+ * @see U8_IS_VALID_LEAD3_AND_T1
+ * @internal
+ */
+#define CBU8_LEAD3_T1_BITS "\x20\x30\x30\x30\x30\x30\x30\x30\x30\x30\x30\x30\x30\x10\x30\x30"
+
+/**
+ * Internal 3-byte UTF-8 validity check.
+ * Non-zero if lead byte E0..EF and first trail byte 00..FF start a valid sequence.
+ * @internal
+ */
+#define CBU8_IS_VALID_LEAD3_AND_T1(lead, t1) (CBU8_LEAD3_T1_BITS[(lead)&0xf]&(1<<((uint8_t)(t1)>>5)))
+
+/**
+ * Internal bit vector for 4-byte UTF-8 validity check, for use in U8_IS_VALID_LEAD4_AND_T1.
+ * Each bit indicates whether one lead byte + first trail byte pair starts a valid sequence.
+ * First trail byte bits 7..4 are used as byte index,
+ * lead byte F0..F4 bits 2..0 are used as bit index into that byte.
+ * @see U8_IS_VALID_LEAD4_AND_T1
+ * @internal
+ */
+#define CBU8_LEAD4_T1_BITS "\x00\x00\x00\x00\x00\x00\x00\x00\x1E\x0F\x0F\x0F\x00\x00\x00\x00"
+
+/**
+ * Internal 4-byte UTF-8 validity check.
+ * Non-zero if lead byte F0..F4 and first trail byte 00..FF start a valid sequence.
+ * @internal
+ */
+#define CBU8_IS_VALID_LEAD4_AND_T1(lead, t1) (CBU8_LEAD4_T1_BITS[(uint8_t)(t1)>>4]&(1<<((lead)&7)))
+
+/**
+ * Function for handling "next code point" with error-checking.
+ *
+ * This is internal since it is not meant to be called directly by external clie
+nts;
+ * however it is U_STABLE (not U_INTERNAL) since it is called by public macros i
+n this
+ * file and thus must remain stable, and should not be hidden when other interna
+l
+ * functions are hidden (otherwise public macros would fail to compile).
+ * @internal
+ */
+UChar32
+utf8_nextCharSafeBody(const uint8_t *s, int32_t *pi, int32_t length, ::base_icu::UChar32 c, ::base_icu::UBool strict);
+
+/**
+ * Does this code unit (byte) encode a code point by itself (US-ASCII 0..0x7f)?
+ * @param c 8-bit code unit (byte)
+ * @return TRUE or FALSE
+ * @stable ICU 2.4
+ */
+#define CBU8_IS_SINGLE(c) (((c)&0x80)==0)
+
+/**
+ * Is this code unit (byte) a UTF-8 lead byte? (0xC2..0xF4)
+ * @param c 8-bit code unit (byte)
+ * @return TRUE or FALSE
+ * @stable ICU 2.4
+ */
+#define CBU8_IS_LEAD(c) ((uint8_t)((c)-0xc2)<=0x32)
+
+/**
+ * Is this code unit (byte) a UTF-8 trail byte? (0x80..0xBF)
+ * @param c 8-bit code unit (byte)
+ * @return TRUE or FALSE
+ * @stable ICU 2.4
+ */
+#define CBU8_IS_TRAIL(c) ((int8_t)(c)<-0x40)
+
+/**
+ * How many code units (bytes) are used for the UTF-8 encoding
+ * of this Unicode code point?
+ * @param c 32-bit code point
+ * @return 1..4, or 0 if c is a surrogate or not a Unicode code point
+ * @stable ICU 2.4
+ */
+#define CBU8_LENGTH(c) \
+ ((uint32_t)(c)<=0x7f ? 1 : \
+ ((uint32_t)(c)<=0x7ff ? 2 : \
+ ((uint32_t)(c)<=0xd7ff ? 3 : \
+ ((uint32_t)(c)<=0xdfff || (uint32_t)(c)>0x10ffff ? 0 : \
+ ((uint32_t)(c)<=0xffff ? 3 : 4)\
+ ) \
+ ) \
+ ) \
+ )
+
+/**
+ * The maximum number of UTF-8 code units (bytes) per Unicode code point (U+0000..U+10ffff).
+ * @return 4
+ * @stable ICU 2.4
+ */
+#define CBU8_MAX_LENGTH 4
+
+/**
+ * Get a code point from a string at a code point boundary offset,
+ * and advance the offset to the next code point boundary.
+ * (Post-incrementing forward iteration.)
+ * "Safe" macro, checks for illegal sequences and for string boundaries.
+ *
+ * The length can be negative for a NUL-terminated string.
+ *
+ * The offset may point to the lead byte of a multi-byte sequence,
+ * in which case the macro will read the whole sequence.
+ * If the offset points to a trail byte or an illegal UTF-8 sequence, then
+ * c is set to a negative value.
+ *
+ * @param s const uint8_t * string
+ * @param i int32_t string offset, must be i<length
+ * @param length int32_t string length
+ * @param c output UChar32 variable, set to <0 in case of an error
+ * @see U8_NEXT_UNSAFE
+ * @stable ICU 2.4
+ */
+#define CBU8_NEXT(s, i, length, c) { \
+ (c)=(uint8_t)(s)[(i)++]; \
+ if(!CBU8_IS_SINGLE(c)) { \
+ uint8_t __t1, __t2; \
+ if( /* handle U+0800..U+FFFF inline */ \
+ (0xe0<=(c) && (c)<0xf0) && \
+ (((i)+1)<(length) || (length)<0) && \
+ CBU8_IS_VALID_LEAD3_AND_T1((c), __t1=(s)[i]) && \
+ (__t2=(s)[(i)+1]-0x80)<=0x3f) { \
+ (c)=(((c)&0xf)<<12)|((__t1&0x3f)<<6)|__t2; \
+ (i)+=2; \
+ } else if( /* handle U+0080..U+07FF inline */ \
+ ((c)<0xe0 && (c)>=0xc2) && \
+ ((i)!=(length)) && \
+ (__t1=(s)[i]-0x80)<=0x3f) { \
+ (c)=(((c)&0x1f)<<6)|__t1; \
+ ++(i); \
+ } else { \
+ /* function call for "complicated" and error cases */ \
+ (c)=::base_icu::utf8_nextCharSafeBody((const uint8_t *)s, &(i), (length), c, -1); \
+ } \
+ } \
+}
+
+/**
+ * Append a code point to a string, overwriting 1 to 4 bytes.
+ * The offset points to the current end of the string contents
+ * and is advanced (post-increment).
+ * "Unsafe" macro, assumes a valid code point and sufficient space in the string.
+ * Otherwise, the result is undefined.
+ *
+ * @param s const uint8_t * string buffer
+ * @param i string offset
+ * @param c code point to append
+ * @see U8_APPEND
+ * @stable ICU 2.4
+ */
+#define CBU8_APPEND_UNSAFE(s, i, c) { \
+ 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); \
+ } \
+}
+
+// source/common/unicode/utf16.h
+
+/**
+ * Does this code unit alone encode a code point (BMP, not a surrogate)?
+ * @param c 16-bit code unit
+ * @return TRUE or FALSE
+ * @stable ICU 2.4
+ */
+#define CBU16_IS_SINGLE(c) !CBU_IS_SURROGATE(c)
+
+/**
+ * Is this code unit a lead surrogate (U+d800..U+dbff)?
+ * @param c 16-bit code unit
+ * @return TRUE or FALSE
+ * @stable ICU 2.4
+ */
+#define CBU16_IS_LEAD(c) (((c)&0xfffffc00)==0xd800)
+
+/**
+ * Is this code unit a trail surrogate (U+dc00..U+dfff)?
+ * @param c 16-bit code unit
+ * @return TRUE or FALSE
+ * @stable ICU 2.4
+ */
+#define CBU16_IS_TRAIL(c) (((c)&0xfffffc00)==0xdc00)
+
+/**
+ * Is this code unit a surrogate (U+d800..U+dfff)?
+ * @param c 16-bit code unit
+ * @return TRUE or FALSE
+ * @stable ICU 2.4
+ */
+#define CBU16_IS_SURROGATE(c) CBU_IS_SURROGATE(c)
+
+/**
+ * Assuming c is a surrogate code point (U16_IS_SURROGATE(c)),
+ * is it a lead surrogate?
+ * @param c 16-bit code unit
+ * @return TRUE or FALSE
+ * @stable ICU 2.4
+ */
+#define CBU16_IS_SURROGATE_LEAD(c) (((c)&0x400)==0)
+
+/**
+ * Helper constant for U16_GET_SUPPLEMENTARY.
+ * @internal
+ */
+#define CBU16_SURROGATE_OFFSET ((0xd800<<10UL)+0xdc00-0x10000)
+
+/**
+ * Get a supplementary code point value (U+10000..U+10ffff)
+ * from its lead and trail surrogates.
+ * The result is undefined if the input values are not
+ * lead and trail surrogates.
+ *
+ * @param lead lead surrogate (U+d800..U+dbff)
+ * @param trail trail surrogate (U+dc00..U+dfff)
+ * @return supplementary code point (U+10000..U+10ffff)
+ * @stable ICU 2.4
+ */
+#define CBU16_GET_SUPPLEMENTARY(lead, trail) \
+ (((::base_icu::UChar32)(lead)<<10UL)+(::base_icu::UChar32)(trail)-CBU16_SURROGATE_OFFSET)
+
+/**
+ * Get the lead surrogate (0xd800..0xdbff) for a
+ * supplementary code point (0x10000..0x10ffff).
+ * @param supplementary 32-bit code point (U+10000..U+10ffff)
+ * @return lead surrogate (U+d800..U+dbff) for supplementary
+ * @stable ICU 2.4
+ */
+#define CBU16_LEAD(supplementary) (::base_icu::UChar)(((supplementary)>>10)+0xd7c0)
+
+/**
+ * Get the trail surrogate (0xdc00..0xdfff) for a
+ * supplementary code point (0x10000..0x10ffff).
+ * @param supplementary 32-bit code point (U+10000..U+10ffff)
+ * @return trail surrogate (U+dc00..U+dfff) for supplementary
+ * @stable ICU 2.4
+ */
+#define CBU16_TRAIL(supplementary) (::base_icu::UChar)(((supplementary)&0x3ff)|0xdc00)
+
+/**
+ * How many 16-bit code units are used to encode this Unicode code point? (1 or 2)
+ * The result is not defined if c is not a Unicode code point (U+0000..U+10ffff).
+ * @param c 32-bit code point
+ * @return 1 or 2
+ * @stable ICU 2.4
+ */
+#define CBU16_LENGTH(c) ((uint32_t)(c)<=0xffff ? 1 : 2)
+
+/**
+ * The maximum number of 16-bit code units per Unicode code point (U+0000..U+10ffff).
+ * @return 2
+ * @stable ICU 2.4
+ */
+#define CBU16_MAX_LENGTH 2
+
+/**
+ * Get a code point from a string at a code point boundary offset,
+ * and advance the offset to the next code point boundary.
+ * (Post-incrementing forward iteration.)
+ * "Safe" macro, handles unpaired surrogates and checks for string boundaries.
+ *
+ * The length can be negative for a NUL-terminated string.
+ *
+ * The offset may point to the lead surrogate unit
+ * for a supplementary code point, in which case the macro will read
+ * the following trail surrogate as well.
+ * If the offset points to a trail surrogate or
+ * to a single, unpaired lead surrogate, then c is set to that unpaired surrogate.
+ *
+ * @param s const UChar * string
+ * @param i string offset, must be i<length
+ * @param length string length
+ * @param c output UChar32 variable
+ * @see U16_NEXT_UNSAFE
+ * @stable ICU 2.4
+ */
+#define CBU16_NEXT(s, i, length, c) { \
+ (c)=(s)[(i)++]; \
+ if(CBU16_IS_LEAD(c)) { \
+ uint16_t __c2; \
+ if((i)!=(length) && CBU16_IS_TRAIL(__c2=(s)[(i)])) { \
+ ++(i); \
+ (c)=CBU16_GET_SUPPLEMENTARY((c), __c2); \
+ } \
+ } \
+}
+
+/**
+ * Append a code point to a string, overwriting 1 or 2 code units.
+ * The offset points to the current end of the string contents
+ * and is advanced (post-increment).
+ * "Unsafe" macro, assumes a valid code point and sufficient space in the string.
+ * Otherwise, the result is undefined.
+ *
+ * @param s const UChar * string buffer
+ * @param i string offset
+ * @param c code point to append
+ * @see U16_APPEND
+ * @stable ICU 2.4
+ */
+#define CBU16_APPEND_UNSAFE(s, i, c) { \
+ 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); \
+ } \
+}
+
+} // namesapce base_icu
+
+#endif // BASE_THIRD_PARTY_ICU_ICU_UTF_H_
diff --git a/weex_core/Source/core/data_render/parser.cc b/weex_core/Source/core/data_render/parser.cc
index dc016fb623..0984a8f093 100644
--- a/weex_core/Source/core/data_render/parser.cc
+++ b/weex_core/Source/core/data_render/parser.cc
@@ -19,6 +19,7 @@
#include "core/data_render/parser.h"
#include <sstream>
+#include <cstdlib>
#include "base/string_util.h"
#include "core/data_render/ast_factory.h"
#include "core/data_render/rax_parser_builder.h"
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
With regards,
Apache Git Services