Fix issue rendering names
This commit is contained in:
parent
68ccbe0450
commit
b9cb4c4740
6 changed files with 581 additions and 126 deletions
|
@ -30,7 +30,7 @@ endif
|
||||||
|
|
||||||
|
|
||||||
# os=Default is meant to be generic unix/linux
|
# os=Default is meant to be generic unix/linux
|
||||||
linux_CXX := gcc
|
linux_CXX := g++
|
||||||
linux_STRIP := strip
|
linux_STRIP := strip
|
||||||
#Default_LINKFLAGS := -shared
|
#Default_LINKFLAGS := -shared
|
||||||
|
|
||||||
|
|
|
@ -14,7 +14,7 @@ LDFLAGS = -Wall -fPIC -Wl,-Bsymbolic
|
||||||
LDRUNFLAGS = -Wl,--hash-style=both
|
LDRUNFLAGS = -Wl,--hash-style=both
|
||||||
# --trace -Bsymbolic -Bsymbolic-functions
|
# --trace -Bsymbolic -Bsymbolic-functions
|
||||||
|
|
||||||
LDLIBS = -L$(PREBUILT_DIR) -lskia -lproto -lpthread -lrt -lft2 -lexpat -lz -lpng
|
LDLIBS = -L$(PREBUILT_DIR) -lskia -lproto -lpthread -lrt -lft2 -lexpat -lpng -lz
|
||||||
CPP_FILE_EXTENSION = cpp
|
CPP_FILE_EXTENSION = cpp
|
||||||
OBJECTS = $(LOCAL_SRC_FILES:src/%.$(CPP_FILE_EXTENSION)=build/obj-$(os)-$(arch)/%.o)
|
OBJECTS = $(LOCAL_SRC_FILES:src/%.$(CPP_FILE_EXTENSION)=build/obj-$(os)-$(arch)/%.o)
|
||||||
|
|
||||||
|
@ -30,8 +30,8 @@ CPPFLAGS := \
|
||||||
$(C_INCLUDES)
|
$(C_INCLUDES)
|
||||||
|
|
||||||
#target : ../$(RUNFILE)
|
#target : ../$(RUNFILE)
|
||||||
target : $(PREBUILT_DIR)/$(LIBNAME)
|
#target : $(PREBUILT_DIR)/$(LIBNAME)
|
||||||
#target : $(PREBUILT_DIR)/$(LIBNAME) ../$(RUNFILE)
|
target : $(PREBUILT_DIR)/$(LIBNAME) ../$(RUNFILE)
|
||||||
|
|
||||||
|
|
||||||
../$(RUNFILE) : $(OBJECTS) $(PREBUILT_DIR)/libskia.a $(PREBUILT_DIR)/libproto.a Makefile
|
../$(RUNFILE) : $(OBJECTS) $(PREBUILT_DIR)/libskia.a $(PREBUILT_DIR)/libproto.a Makefile
|
||||||
|
@ -45,7 +45,7 @@ $(PREBUILT_DIR)/$(LIBNAME) : build/$(LIBOSNAME)
|
||||||
build/$(LIBOSNAME): $(OBJECTS) $(PREBUILT_DIR)/libskia.a $(PREBUILT_DIR)/libproto.a Makefile
|
build/$(LIBOSNAME): $(OBJECTS) $(PREBUILT_DIR)/libskia.a $(PREBUILT_DIR)/libproto.a Makefile
|
||||||
$(CXX) -shared -o build/$(LIBOSNAME) $(OBJECTS) $(LDFLAGS) $(LDLIBS)
|
$(CXX) -shared -o build/$(LIBOSNAME) $(OBJECTS) $(LDFLAGS) $(LDLIBS)
|
||||||
|
|
||||||
build/obj-$(os)-$(arch)/%.o : src/%.$(CPP_FILE_EXTENSION) $(LOCAL_C_INCLUDES)
|
build/obj-$(os)-$(arch)/%.o : src/%.$(CPP_FILE_EXTENSION) $(LOCAL_C_INCLUDES) src/textdraw.cpp
|
||||||
@mkdir -p `dirname $@`
|
@mkdir -p `dirname $@`
|
||||||
$(CXX) -o $@ -c src/$*.$(CPP_FILE_EXTENSION) $(CPPFLAGS)
|
$(CXX) -o $@ -c src/$*.$(CPP_FILE_EXTENSION) $(CPPFLAGS)
|
||||||
|
|
||||||
|
|
|
@ -11,7 +11,8 @@
|
||||||
|
|
||||||
#include "common.h"
|
#include "common.h"
|
||||||
#include "renderRules.h"
|
#include "renderRules.h"
|
||||||
#include "utf8.cpp"
|
//#include "utf8.cpp"
|
||||||
|
#include "utf8/unchecked.h"
|
||||||
|
|
||||||
|
|
||||||
template <typename T> class quad_tree {
|
template <typename T> class quad_tree {
|
||||||
|
@ -155,6 +156,19 @@ void drawTextOnCanvas(SkCanvas* cv, const char* text, uint16_t len, float center
|
||||||
}
|
}
|
||||||
|
|
||||||
|
|
||||||
|
int nextWord(uint8_t* s, int* charRead) {
|
||||||
|
uint8_t* init = s;
|
||||||
|
while((*s) != 0) {
|
||||||
|
uint32_t tp = utf8::unchecked::next(s);
|
||||||
|
(*charRead) ++;
|
||||||
|
if(tp == ' ' || tp == '\t') {
|
||||||
|
return (s - init);
|
||||||
|
}
|
||||||
|
}
|
||||||
|
return -1;
|
||||||
|
|
||||||
|
}
|
||||||
|
|
||||||
void drawWrappedText(RenderingContext* rc, SkCanvas* cv, TextDrawInfo* text, float textSize, SkPaint& paintText) {
|
void drawWrappedText(RenderingContext* rc, SkCanvas* cv, TextDrawInfo* text, float textSize, SkPaint& paintText) {
|
||||||
if(text->textWrap == 0) {
|
if(text->textWrap == 0) {
|
||||||
// set maximum for all text
|
// set maximum for all text
|
||||||
|
@ -171,18 +185,19 @@ void drawWrappedText(RenderingContext* rc, SkCanvas* cv, TextDrawInfo* text, flo
|
||||||
const char* p_str = c_str;
|
const char* p_str = c_str;
|
||||||
int lastSpace = -1;
|
int lastSpace = -1;
|
||||||
int prevPos = -1;
|
int prevPos = -1;
|
||||||
|
int charRead = 0;
|
||||||
do {
|
do {
|
||||||
int lastSpace = nextWord((uint8_t*)p_str);
|
int lastSpace = nextWord((uint8_t*)p_str, &charRead);
|
||||||
if (lastSpace == -1) {
|
if (lastSpace == -1) {
|
||||||
pos = end;
|
pos = end;
|
||||||
} else {
|
} else {
|
||||||
p_str += lastSpace;
|
p_str += lastSpace;
|
||||||
if(pos != start && pos - start + lastSpace >= text->textWrap){
|
if(pos != start && charRead >= text->textWrap){
|
||||||
break;
|
break;
|
||||||
}
|
}
|
||||||
pos += lastSpace;
|
pos += lastSpace;
|
||||||
}
|
}
|
||||||
} while(pos < end && (pos - start) < text->textWrap);
|
} while(pos < end && charRead < text->textWrap);
|
||||||
|
|
||||||
PROFILE_NATIVE_OPERATION(rc, drawTextOnCanvas(cv, c_str, pos - start , text->centerX, text->centerY + line * (textSize + 2), paintText, text->textShadow));
|
PROFILE_NATIVE_OPERATION(rc, drawTextOnCanvas(cv, c_str, pos - start , text->centerX, text->centerY + line * (textSize + 2), paintText, text->textShadow));
|
||||||
c_str += (pos - start);
|
c_str += (pos - start);
|
||||||
|
|
|
@ -1,117 +0,0 @@
|
||||||
///////////////////////////////////////////////////////////////////
|
|
||||||
//
|
|
||||||
// Fast, small, simple, robust UTF-8 decoder in C
|
|
||||||
//
|
|
||||||
// Copyright (c) 2008-2009 Bjoern Hoehrmann <bjo...@hoehrmann.de>
|
|
||||||
//
|
|
||||||
// This program is free software: you can redistribute it and/or
|
|
||||||
// modify it under the terms of the GNU General Public License as
|
|
||||||
// published by the Free Software Foundation, either version 3 of
|
|
||||||
// the License, or (at your option) any later version.
|
|
||||||
//
|
|
||||||
// This program is distributed in the hope that it will be useful,
|
|
||||||
// but WITHOUT ANY WARRANTY; without even the implied warranty of
|
|
||||||
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
|
||||||
// GNU General Public License for more details.
|
|
||||||
//
|
|
||||||
///////////////////////////////////////////////////////////////////
|
|
||||||
#ifndef _UTF_8_CPP
|
|
||||||
#define _UTF_8_CPP
|
|
||||||
#include <stdio.h>
|
|
||||||
#include <stdlib.h>
|
|
||||||
|
|
||||||
#ifdef _MSC_VER
|
|
||||||
typedef unsigned __int8 uint8_t;
|
|
||||||
typedef unsigned __int32 uint32_t;
|
|
||||||
#else
|
|
||||||
#include <stdint.h>
|
|
||||||
#endif
|
|
||||||
|
|
||||||
#define ASCII_IN_TABLE 1
|
|
||||||
|
|
||||||
/*
|
|
||||||
The first 128 entries are tuples of 4 bit values. The lower bits
|
|
||||||
are a mask that when xor'd with a byte removes the leading utf-8
|
|
||||||
bits. The upper bits are a character class number. The remaining
|
|
||||||
160 entries are a minimal deterministic finite automaton. It has
|
|
||||||
10 states and each state has 13 character class transitions, and
|
|
||||||
3 unused transitions for padding reasons. When the automaton en-
|
|
||||||
ters state zero, it has found a complete valid utf-8 code point;
|
|
||||||
if it enters state one then the input sequence is not utf-8. The
|
|
||||||
start state is state nine. Note the mixture of octal and decimal
|
|
||||||
for stylistic reasons. The ASCII_IN_TABLE macro makes the array
|
|
||||||
bigger and the code simpler--but not necessarily faster--if set.
|
|
||||||
*/
|
|
||||||
|
|
||||||
static const uint8_t utf8d[] = {
|
|
||||||
|
|
||||||
#if ASCII_IN_TABLE
|
|
||||||
0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
|
|
||||||
0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
|
|
||||||
0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
|
|
||||||
0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
|
|
||||||
#endif
|
|
||||||
|
|
||||||
070,070,070,070,070,070,070,070,070,070,070,070,070,070,070,070,
|
|
||||||
050,050,050,050,050,050,050,050,050,050,050,050,050,050,050,050,
|
|
||||||
030,030,030,030,030,030,030,030,030,030,030,030,030,030,030,030,
|
|
||||||
030,030,030,030,030,030,030,030,030,030,030,030,030,030,030,030,
|
|
||||||
204,204,188,188,188,188,188,188,188,188,188,188,188,188,188,188,
|
|
||||||
188,188,188,188,188,188,188,188,188,188,188,188,188,188,188,188,
|
|
||||||
174,158,158,158,158,158,158,158,158,158,158,158,158,142,126,126,
|
|
||||||
111, 95, 95, 95, 79,207,207,207,207,207,207,207,207,207,207,207,
|
|
||||||
|
|
||||||
0,1,1,1,8,7,6,4,5,4,3,2,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
|
|
||||||
1,0,0,0,1,1,1,1,1,1,1,1,1,1,1,1,1,2,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
|
|
||||||
1,2,2,2,1,1,1,1,1,1,1,1,1,1,1,1,1,1,2,2,1,1,1,1,1,1,1,1,1,1,1,1,
|
|
||||||
1,4,4,1,1,1,1,1,1,1,1,1,1,1,1,1,1,4,4,4,1,1,1,1,1,1,1,1,1,1,1,1,
|
|
||||||
1,1,1,4,1,1,1,1,1,1,1,1,1,1,1,1,0,1,1,1,8,7,6,4,5,4,3,2,1,1,1,1,
|
|
||||||
|
|
||||||
};
|
|
||||||
int nextWord(uint8_t* s) {
|
|
||||||
uint8_t data, byte, stat = 9;
|
|
||||||
uint32_t unic = 0;
|
|
||||||
uint8_t counter = 0;
|
|
||||||
|
|
||||||
// http://lists.w3.org/Archives/Public/www-archive/2009Apr/0000
|
|
||||||
|
|
||||||
while ((byte = *s++)) {
|
|
||||||
counter ++;
|
|
||||||
|
|
||||||
data = utf8d[ byte ];
|
|
||||||
stat = utf8d[ 256 + (stat << 4) + (data >> 4) ];
|
|
||||||
byte = (byte ^ (uint8_t)(data << 4));
|
|
||||||
|
|
||||||
unic = (unic << 6) | byte;
|
|
||||||
#if ASCII_IN_TABLE
|
|
||||||
data = utf8d[ byte ];
|
|
||||||
stat = utf8d[ 256 + (stat << 4) + (data >> 4) ];
|
|
||||||
byte = (byte ^ (uint8_t)(data << 4));
|
|
||||||
#else
|
|
||||||
if (byte < 0x80) {
|
|
||||||
stat = utf8d[ 128 + (stat << 4) ];
|
|
||||||
} else {
|
|
||||||
data = utf8d[ byte ];
|
|
||||||
stat = utf8d[ 128 + (stat << 4) + (data >> 4) ];
|
|
||||||
byte = (byte ^ (uint8_t)(data << 4));
|
|
||||||
}
|
|
||||||
#endif
|
|
||||||
|
|
||||||
if (!stat) {
|
|
||||||
// find delimeters (is whitespace)
|
|
||||||
if(unic == ' ' || unic == '\t') {
|
|
||||||
return counter;
|
|
||||||
}
|
|
||||||
// unic is now a proper code point, we just print it out.
|
|
||||||
unic = 0;
|
|
||||||
}
|
|
||||||
|
|
||||||
if (stat == 1) {
|
|
||||||
// the byte is not allowed here; the state would have to
|
|
||||||
// be reset to continue meaningful reading of the string
|
|
||||||
}
|
|
||||||
|
|
||||||
}
|
|
||||||
return -1;
|
|
||||||
}
|
|
||||||
#endif
|
|
329
Osmand-kernel/osmand/src/utf8/core.h
Normal file
329
Osmand-kernel/osmand/src/utf8/core.h
Normal file
|
@ -0,0 +1,329 @@
|
||||||
|
// Copyright 2006 Nemanja Trifunovic
|
||||||
|
|
||||||
|
/*
|
||||||
|
Permission is hereby granted, free of charge, to any person or organization
|
||||||
|
obtaining a copy of the software and accompanying documentation covered by
|
||||||
|
this license (the "Software") to use, reproduce, display, distribute,
|
||||||
|
execute, and transmit the Software, and to prepare derivative works of the
|
||||||
|
Software, and to permit third-parties to whom the Software is furnished to
|
||||||
|
do so, all subject to the following:
|
||||||
|
|
||||||
|
The copyright notices in the Software and this entire statement, including
|
||||||
|
the above license grant, this restriction and the following disclaimer,
|
||||||
|
must be included in all copies of the Software, in whole or in part, and
|
||||||
|
all derivative works of the Software, unless such copies or derivative
|
||||||
|
works are solely in the form of machine-executable object code generated by
|
||||||
|
a source language processor.
|
||||||
|
|
||||||
|
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, TITLE AND NON-INFRINGEMENT. IN NO EVENT
|
||||||
|
SHALL THE COPYRIGHT HOLDERS OR ANYONE DISTRIBUTING THE SOFTWARE BE LIABLE
|
||||||
|
FOR ANY DAMAGES OR OTHER LIABILITY, WHETHER IN CONTRACT, TORT OR OTHERWISE,
|
||||||
|
ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
|
||||||
|
DEALINGS IN THE SOFTWARE.
|
||||||
|
*/
|
||||||
|
|
||||||
|
|
||||||
|
#ifndef UTF8_FOR_CPP_CORE_H_2675DCD0_9480_4c0c_B92A_CC14C027B731
|
||||||
|
#define UTF8_FOR_CPP_CORE_H_2675DCD0_9480_4c0c_B92A_CC14C027B731
|
||||||
|
|
||||||
|
#include <iterator>
|
||||||
|
|
||||||
|
namespace utf8
|
||||||
|
{
|
||||||
|
// The typedefs for 8-bit, 16-bit and 32-bit unsigned integers
|
||||||
|
// You may need to change them to match your system.
|
||||||
|
// These typedefs have the same names as ones from cstdint, or boost/cstdint
|
||||||
|
typedef unsigned char uint8_t;
|
||||||
|
typedef unsigned short uint16_t;
|
||||||
|
typedef unsigned int uint32_t;
|
||||||
|
|
||||||
|
// Helper code - not intended to be directly called by the library users. May be changed at any time
|
||||||
|
namespace internal
|
||||||
|
{
|
||||||
|
// Unicode constants
|
||||||
|
// Leading (high) surrogates: 0xd800 - 0xdbff
|
||||||
|
// Trailing (low) surrogates: 0xdc00 - 0xdfff
|
||||||
|
const uint16_t LEAD_SURROGATE_MIN = 0xd800u;
|
||||||
|
const uint16_t LEAD_SURROGATE_MAX = 0xdbffu;
|
||||||
|
const uint16_t TRAIL_SURROGATE_MIN = 0xdc00u;
|
||||||
|
const uint16_t TRAIL_SURROGATE_MAX = 0xdfffu;
|
||||||
|
const uint16_t LEAD_OFFSET = LEAD_SURROGATE_MIN - (0x10000 >> 10);
|
||||||
|
const uint32_t SURROGATE_OFFSET = 0x10000u - (LEAD_SURROGATE_MIN << 10) - TRAIL_SURROGATE_MIN;
|
||||||
|
|
||||||
|
// Maximum valid value for a Unicode code point
|
||||||
|
const uint32_t CODE_POINT_MAX = 0x0010ffffu;
|
||||||
|
|
||||||
|
template<typename octet_type>
|
||||||
|
inline uint8_t mask8(octet_type oc)
|
||||||
|
{
|
||||||
|
return static_cast<uint8_t>(0xff & oc);
|
||||||
|
}
|
||||||
|
template<typename u16_type>
|
||||||
|
inline uint16_t mask16(u16_type oc)
|
||||||
|
{
|
||||||
|
return static_cast<uint16_t>(0xffff & oc);
|
||||||
|
}
|
||||||
|
template<typename octet_type>
|
||||||
|
inline bool is_trail(octet_type oc)
|
||||||
|
{
|
||||||
|
return ((utf8::internal::mask8(oc) >> 6) == 0x2);
|
||||||
|
}
|
||||||
|
|
||||||
|
template <typename u16>
|
||||||
|
inline bool is_lead_surrogate(u16 cp)
|
||||||
|
{
|
||||||
|
return (cp >= LEAD_SURROGATE_MIN && cp <= LEAD_SURROGATE_MAX);
|
||||||
|
}
|
||||||
|
|
||||||
|
template <typename u16>
|
||||||
|
inline bool is_trail_surrogate(u16 cp)
|
||||||
|
{
|
||||||
|
return (cp >= TRAIL_SURROGATE_MIN && cp <= TRAIL_SURROGATE_MAX);
|
||||||
|
}
|
||||||
|
|
||||||
|
template <typename u16>
|
||||||
|
inline bool is_surrogate(u16 cp)
|
||||||
|
{
|
||||||
|
return (cp >= LEAD_SURROGATE_MIN && cp <= TRAIL_SURROGATE_MAX);
|
||||||
|
}
|
||||||
|
|
||||||
|
template <typename u32>
|
||||||
|
inline bool is_code_point_valid(u32 cp)
|
||||||
|
{
|
||||||
|
return (cp <= CODE_POINT_MAX && !utf8::internal::is_surrogate(cp));
|
||||||
|
}
|
||||||
|
|
||||||
|
template <typename octet_iterator>
|
||||||
|
inline typename std::iterator_traits<octet_iterator>::difference_type
|
||||||
|
sequence_length(octet_iterator lead_it)
|
||||||
|
{
|
||||||
|
uint8_t lead = utf8::internal::mask8(*lead_it);
|
||||||
|
if (lead < 0x80)
|
||||||
|
return 1;
|
||||||
|
else if ((lead >> 5) == 0x6)
|
||||||
|
return 2;
|
||||||
|
else if ((lead >> 4) == 0xe)
|
||||||
|
return 3;
|
||||||
|
else if ((lead >> 3) == 0x1e)
|
||||||
|
return 4;
|
||||||
|
else
|
||||||
|
return 0;
|
||||||
|
}
|
||||||
|
|
||||||
|
template <typename octet_difference_type>
|
||||||
|
inline bool is_overlong_sequence(uint32_t cp, octet_difference_type length)
|
||||||
|
{
|
||||||
|
if (cp < 0x80) {
|
||||||
|
if (length != 1)
|
||||||
|
return true;
|
||||||
|
}
|
||||||
|
else if (cp < 0x800) {
|
||||||
|
if (length != 2)
|
||||||
|
return true;
|
||||||
|
}
|
||||||
|
else if (cp < 0x10000) {
|
||||||
|
if (length != 3)
|
||||||
|
return true;
|
||||||
|
}
|
||||||
|
|
||||||
|
return false;
|
||||||
|
}
|
||||||
|
|
||||||
|
enum utf_error {UTF8_OK, NOT_ENOUGH_ROOM, INVALID_LEAD, INCOMPLETE_SEQUENCE, OVERLONG_SEQUENCE, INVALID_CODE_POINT};
|
||||||
|
|
||||||
|
/// Helper for get_sequence_x
|
||||||
|
template <typename octet_iterator>
|
||||||
|
utf_error increase_safely(octet_iterator& it, octet_iterator end)
|
||||||
|
{
|
||||||
|
if (++it == end)
|
||||||
|
return NOT_ENOUGH_ROOM;
|
||||||
|
|
||||||
|
if (!utf8::internal::is_trail(*it))
|
||||||
|
return INCOMPLETE_SEQUENCE;
|
||||||
|
|
||||||
|
return UTF8_OK;
|
||||||
|
}
|
||||||
|
|
||||||
|
#define UTF8_CPP_INCREASE_AND_RETURN_ON_ERROR(IT, END) {utf_error ret = increase_safely(IT, END); if (ret != UTF8_OK) return ret;}
|
||||||
|
|
||||||
|
/// get_sequence_x functions decode utf-8 sequences of the length x
|
||||||
|
template <typename octet_iterator>
|
||||||
|
utf_error get_sequence_1(octet_iterator& it, octet_iterator end, uint32_t& code_point)
|
||||||
|
{
|
||||||
|
if (it == end)
|
||||||
|
return NOT_ENOUGH_ROOM;
|
||||||
|
|
||||||
|
code_point = utf8::internal::mask8(*it);
|
||||||
|
|
||||||
|
return UTF8_OK;
|
||||||
|
}
|
||||||
|
|
||||||
|
template <typename octet_iterator>
|
||||||
|
utf_error get_sequence_2(octet_iterator& it, octet_iterator end, uint32_t& code_point)
|
||||||
|
{
|
||||||
|
if (it == end)
|
||||||
|
return NOT_ENOUGH_ROOM;
|
||||||
|
|
||||||
|
code_point = utf8::internal::mask8(*it);
|
||||||
|
|
||||||
|
UTF8_CPP_INCREASE_AND_RETURN_ON_ERROR(it, end)
|
||||||
|
|
||||||
|
code_point = ((code_point << 6) & 0x7ff) + ((*it) & 0x3f);
|
||||||
|
|
||||||
|
return UTF8_OK;
|
||||||
|
}
|
||||||
|
|
||||||
|
template <typename octet_iterator>
|
||||||
|
utf_error get_sequence_3(octet_iterator& it, octet_iterator end, uint32_t& code_point)
|
||||||
|
{
|
||||||
|
if (it == end)
|
||||||
|
return NOT_ENOUGH_ROOM;
|
||||||
|
|
||||||
|
code_point = utf8::internal::mask8(*it);
|
||||||
|
|
||||||
|
UTF8_CPP_INCREASE_AND_RETURN_ON_ERROR(it, end)
|
||||||
|
|
||||||
|
code_point = ((code_point << 12) & 0xffff) + ((utf8::internal::mask8(*it) << 6) & 0xfff);
|
||||||
|
|
||||||
|
UTF8_CPP_INCREASE_AND_RETURN_ON_ERROR(it, end)
|
||||||
|
|
||||||
|
code_point += (*it) & 0x3f;
|
||||||
|
|
||||||
|
return UTF8_OK;
|
||||||
|
}
|
||||||
|
|
||||||
|
template <typename octet_iterator>
|
||||||
|
utf_error get_sequence_4(octet_iterator& it, octet_iterator end, uint32_t& code_point)
|
||||||
|
{
|
||||||
|
if (it == end)
|
||||||
|
return NOT_ENOUGH_ROOM;
|
||||||
|
|
||||||
|
code_point = utf8::internal::mask8(*it);
|
||||||
|
|
||||||
|
UTF8_CPP_INCREASE_AND_RETURN_ON_ERROR(it, end)
|
||||||
|
|
||||||
|
code_point = ((code_point << 18) & 0x1fffff) + ((utf8::internal::mask8(*it) << 12) & 0x3ffff);
|
||||||
|
|
||||||
|
UTF8_CPP_INCREASE_AND_RETURN_ON_ERROR(it, end)
|
||||||
|
|
||||||
|
code_point += (utf8::internal::mask8(*it) << 6) & 0xfff;
|
||||||
|
|
||||||
|
UTF8_CPP_INCREASE_AND_RETURN_ON_ERROR(it, end)
|
||||||
|
|
||||||
|
code_point += (*it) & 0x3f;
|
||||||
|
|
||||||
|
return UTF8_OK;
|
||||||
|
}
|
||||||
|
|
||||||
|
#undef UTF8_CPP_INCREASE_AND_RETURN_ON_ERROR
|
||||||
|
|
||||||
|
template <typename octet_iterator>
|
||||||
|
utf_error validate_next(octet_iterator& it, octet_iterator end, uint32_t& code_point)
|
||||||
|
{
|
||||||
|
// Save the original value of it so we can go back in case of failure
|
||||||
|
// Of course, it does not make much sense with i.e. stream iterators
|
||||||
|
octet_iterator original_it = it;
|
||||||
|
|
||||||
|
uint32_t cp = 0;
|
||||||
|
// Determine the sequence length based on the lead octet
|
||||||
|
typedef typename std::iterator_traits<octet_iterator>::difference_type octet_difference_type;
|
||||||
|
const octet_difference_type length = utf8::internal::sequence_length(it);
|
||||||
|
|
||||||
|
// Get trail octets and calculate the code point
|
||||||
|
utf_error err = UTF8_OK;
|
||||||
|
switch (length) {
|
||||||
|
case 0:
|
||||||
|
return INVALID_LEAD;
|
||||||
|
case 1:
|
||||||
|
err = utf8::internal::get_sequence_1(it, end, cp);
|
||||||
|
break;
|
||||||
|
case 2:
|
||||||
|
err = utf8::internal::get_sequence_2(it, end, cp);
|
||||||
|
break;
|
||||||
|
case 3:
|
||||||
|
err = utf8::internal::get_sequence_3(it, end, cp);
|
||||||
|
break;
|
||||||
|
case 4:
|
||||||
|
err = utf8::internal::get_sequence_4(it, end, cp);
|
||||||
|
break;
|
||||||
|
}
|
||||||
|
|
||||||
|
if (err == UTF8_OK) {
|
||||||
|
// Decoding succeeded. Now, security checks...
|
||||||
|
if (utf8::internal::is_code_point_valid(cp)) {
|
||||||
|
if (!utf8::internal::is_overlong_sequence(cp, length)){
|
||||||
|
// Passed! Return here.
|
||||||
|
code_point = cp;
|
||||||
|
++it;
|
||||||
|
return UTF8_OK;
|
||||||
|
}
|
||||||
|
else
|
||||||
|
err = OVERLONG_SEQUENCE;
|
||||||
|
}
|
||||||
|
else
|
||||||
|
err = INVALID_CODE_POINT;
|
||||||
|
}
|
||||||
|
|
||||||
|
// Failure branch - restore the original value of the iterator
|
||||||
|
it = original_it;
|
||||||
|
return err;
|
||||||
|
}
|
||||||
|
|
||||||
|
template <typename octet_iterator>
|
||||||
|
inline utf_error validate_next(octet_iterator& it, octet_iterator end) {
|
||||||
|
uint32_t ignored;
|
||||||
|
return utf8::internal::validate_next(it, end, ignored);
|
||||||
|
}
|
||||||
|
|
||||||
|
} // namespace internal
|
||||||
|
|
||||||
|
/// The library API - functions intended to be called by the users
|
||||||
|
|
||||||
|
// Byte order mark
|
||||||
|
const uint8_t bom[] = {0xef, 0xbb, 0xbf};
|
||||||
|
|
||||||
|
template <typename octet_iterator>
|
||||||
|
octet_iterator find_invalid(octet_iterator start, octet_iterator end)
|
||||||
|
{
|
||||||
|
octet_iterator result = start;
|
||||||
|
while (result != end) {
|
||||||
|
utf8::internal::utf_error err_code = utf8::internal::validate_next(result, end);
|
||||||
|
if (err_code != internal::UTF8_OK)
|
||||||
|
return result;
|
||||||
|
}
|
||||||
|
return result;
|
||||||
|
}
|
||||||
|
|
||||||
|
template <typename octet_iterator>
|
||||||
|
inline bool is_valid(octet_iterator start, octet_iterator end)
|
||||||
|
{
|
||||||
|
return (utf8::find_invalid(start, end) == end);
|
||||||
|
}
|
||||||
|
|
||||||
|
template <typename octet_iterator>
|
||||||
|
inline bool starts_with_bom (octet_iterator it, octet_iterator end)
|
||||||
|
{
|
||||||
|
return (
|
||||||
|
((it != end) && (utf8::internal::mask8(*it++)) == bom[0]) &&
|
||||||
|
((it != end) && (utf8::internal::mask8(*it++)) == bom[1]) &&
|
||||||
|
((it != end) && (utf8::internal::mask8(*it)) == bom[2])
|
||||||
|
);
|
||||||
|
}
|
||||||
|
|
||||||
|
//Deprecated in release 2.3
|
||||||
|
template <typename octet_iterator>
|
||||||
|
inline bool is_bom (octet_iterator it)
|
||||||
|
{
|
||||||
|
return (
|
||||||
|
(utf8::internal::mask8(*it++)) == bom[0] &&
|
||||||
|
(utf8::internal::mask8(*it++)) == bom[1] &&
|
||||||
|
(utf8::internal::mask8(*it)) == bom[2]
|
||||||
|
);
|
||||||
|
}
|
||||||
|
} // namespace utf8
|
||||||
|
|
||||||
|
#endif // header guard
|
||||||
|
|
||||||
|
|
228
Osmand-kernel/osmand/src/utf8/unchecked.h
Normal file
228
Osmand-kernel/osmand/src/utf8/unchecked.h
Normal file
|
@ -0,0 +1,228 @@
|
||||||
|
// Copyright 2006 Nemanja Trifunovic
|
||||||
|
|
||||||
|
/*
|
||||||
|
Permission is hereby granted, free of charge, to any person or organization
|
||||||
|
obtaining a copy of the software and accompanying documentation covered by
|
||||||
|
this license (the "Software") to use, reproduce, display, distribute,
|
||||||
|
execute, and transmit the Software, and to prepare derivative works of the
|
||||||
|
Software, and to permit third-parties to whom the Software is furnished to
|
||||||
|
do so, all subject to the following:
|
||||||
|
|
||||||
|
The copyright notices in the Software and this entire statement, including
|
||||||
|
the above license grant, this restriction and the following disclaimer,
|
||||||
|
must be included in all copies of the Software, in whole or in part, and
|
||||||
|
all derivative works of the Software, unless such copies or derivative
|
||||||
|
works are solely in the form of machine-executable object code generated by
|
||||||
|
a source language processor.
|
||||||
|
|
||||||
|
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, TITLE AND NON-INFRINGEMENT. IN NO EVENT
|
||||||
|
SHALL THE COPYRIGHT HOLDERS OR ANYONE DISTRIBUTING THE SOFTWARE BE LIABLE
|
||||||
|
FOR ANY DAMAGES OR OTHER LIABILITY, WHETHER IN CONTRACT, TORT OR OTHERWISE,
|
||||||
|
ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
|
||||||
|
DEALINGS IN THE SOFTWARE.
|
||||||
|
*/
|
||||||
|
|
||||||
|
|
||||||
|
#ifndef UTF8_FOR_CPP_UNCHECKED_H_2675DCD0_9480_4c0c_B92A_CC14C027B731
|
||||||
|
#define UTF8_FOR_CPP_UNCHECKED_H_2675DCD0_9480_4c0c_B92A_CC14C027B731
|
||||||
|
|
||||||
|
#include "core.h"
|
||||||
|
|
||||||
|
namespace utf8
|
||||||
|
{
|
||||||
|
namespace unchecked
|
||||||
|
{
|
||||||
|
template <typename octet_iterator>
|
||||||
|
octet_iterator append(uint32_t cp, octet_iterator result)
|
||||||
|
{
|
||||||
|
if (cp < 0x80) // one octet
|
||||||
|
*(result++) = static_cast<uint8_t>(cp);
|
||||||
|
else if (cp < 0x800) { // two octets
|
||||||
|
*(result++) = static_cast<uint8_t>((cp >> 6) | 0xc0);
|
||||||
|
*(result++) = static_cast<uint8_t>((cp & 0x3f) | 0x80);
|
||||||
|
}
|
||||||
|
else if (cp < 0x10000) { // three octets
|
||||||
|
*(result++) = static_cast<uint8_t>((cp >> 12) | 0xe0);
|
||||||
|
*(result++) = static_cast<uint8_t>(((cp >> 6) & 0x3f) | 0x80);
|
||||||
|
*(result++) = static_cast<uint8_t>((cp & 0x3f) | 0x80);
|
||||||
|
}
|
||||||
|
else { // four octets
|
||||||
|
*(result++) = static_cast<uint8_t>((cp >> 18) | 0xf0);
|
||||||
|
*(result++) = static_cast<uint8_t>(((cp >> 12) & 0x3f)| 0x80);
|
||||||
|
*(result++) = static_cast<uint8_t>(((cp >> 6) & 0x3f) | 0x80);
|
||||||
|
*(result++) = static_cast<uint8_t>((cp & 0x3f) | 0x80);
|
||||||
|
}
|
||||||
|
return result;
|
||||||
|
}
|
||||||
|
|
||||||
|
template <typename octet_iterator>
|
||||||
|
uint32_t next(octet_iterator& it)
|
||||||
|
{
|
||||||
|
uint32_t cp = utf8::internal::mask8(*it);
|
||||||
|
typename std::iterator_traits<octet_iterator>::difference_type length = utf8::internal::sequence_length(it);
|
||||||
|
switch (length) {
|
||||||
|
case 1:
|
||||||
|
break;
|
||||||
|
case 2:
|
||||||
|
it++;
|
||||||
|
cp = ((cp << 6) & 0x7ff) + ((*it) & 0x3f);
|
||||||
|
break;
|
||||||
|
case 3:
|
||||||
|
++it;
|
||||||
|
cp = ((cp << 12) & 0xffff) + ((utf8::internal::mask8(*it) << 6) & 0xfff);
|
||||||
|
++it;
|
||||||
|
cp += (*it) & 0x3f;
|
||||||
|
break;
|
||||||
|
case 4:
|
||||||
|
++it;
|
||||||
|
cp = ((cp << 18) & 0x1fffff) + ((utf8::internal::mask8(*it) << 12) & 0x3ffff);
|
||||||
|
++it;
|
||||||
|
cp += (utf8::internal::mask8(*it) << 6) & 0xfff;
|
||||||
|
++it;
|
||||||
|
cp += (*it) & 0x3f;
|
||||||
|
break;
|
||||||
|
}
|
||||||
|
++it;
|
||||||
|
return cp;
|
||||||
|
}
|
||||||
|
|
||||||
|
template <typename octet_iterator>
|
||||||
|
uint32_t peek_next(octet_iterator it)
|
||||||
|
{
|
||||||
|
return utf8::unchecked::next(it);
|
||||||
|
}
|
||||||
|
|
||||||
|
template <typename octet_iterator>
|
||||||
|
uint32_t prior(octet_iterator& it)
|
||||||
|
{
|
||||||
|
while (utf8::internal::is_trail(*(--it))) ;
|
||||||
|
octet_iterator temp = it;
|
||||||
|
return utf8::unchecked::next(temp);
|
||||||
|
}
|
||||||
|
|
||||||
|
// Deprecated in versions that include prior, but only for the sake of consistency (see utf8::previous)
|
||||||
|
template <typename octet_iterator>
|
||||||
|
inline uint32_t previous(octet_iterator& it)
|
||||||
|
{
|
||||||
|
return utf8::unchecked::prior(it);
|
||||||
|
}
|
||||||
|
|
||||||
|
template <typename octet_iterator, typename distance_type>
|
||||||
|
void advance (octet_iterator& it, distance_type n)
|
||||||
|
{
|
||||||
|
for (distance_type i = 0; i < n; ++i)
|
||||||
|
utf8::unchecked::next(it);
|
||||||
|
}
|
||||||
|
|
||||||
|
template <typename octet_iterator>
|
||||||
|
typename std::iterator_traits<octet_iterator>::difference_type
|
||||||
|
distance (octet_iterator first, octet_iterator last)
|
||||||
|
{
|
||||||
|
typename std::iterator_traits<octet_iterator>::difference_type dist;
|
||||||
|
for (dist = 0; first < last; ++dist)
|
||||||
|
utf8::unchecked::next(first);
|
||||||
|
return dist;
|
||||||
|
}
|
||||||
|
|
||||||
|
template <typename u16bit_iterator, typename octet_iterator>
|
||||||
|
octet_iterator utf16to8 (u16bit_iterator start, u16bit_iterator end, octet_iterator result)
|
||||||
|
{
|
||||||
|
while (start != end) {
|
||||||
|
uint32_t cp = utf8::internal::mask16(*start++);
|
||||||
|
// Take care of surrogate pairs first
|
||||||
|
if (utf8::internal::is_lead_surrogate(cp)) {
|
||||||
|
uint32_t trail_surrogate = utf8::internal::mask16(*start++);
|
||||||
|
cp = (cp << 10) + trail_surrogate + internal::SURROGATE_OFFSET;
|
||||||
|
}
|
||||||
|
result = utf8::unchecked::append(cp, result);
|
||||||
|
}
|
||||||
|
return result;
|
||||||
|
}
|
||||||
|
|
||||||
|
template <typename u16bit_iterator, typename octet_iterator>
|
||||||
|
u16bit_iterator utf8to16 (octet_iterator start, octet_iterator end, u16bit_iterator result)
|
||||||
|
{
|
||||||
|
while (start < end) {
|
||||||
|
uint32_t cp = utf8::unchecked::next(start);
|
||||||
|
if (cp > 0xffff) { //make a surrogate pair
|
||||||
|
*result++ = static_cast<uint16_t>((cp >> 10) + internal::LEAD_OFFSET);
|
||||||
|
*result++ = static_cast<uint16_t>((cp & 0x3ff) + internal::TRAIL_SURROGATE_MIN);
|
||||||
|
}
|
||||||
|
else
|
||||||
|
*result++ = static_cast<uint16_t>(cp);
|
||||||
|
}
|
||||||
|
return result;
|
||||||
|
}
|
||||||
|
|
||||||
|
template <typename octet_iterator, typename u32bit_iterator>
|
||||||
|
octet_iterator utf32to8 (u32bit_iterator start, u32bit_iterator end, octet_iterator result)
|
||||||
|
{
|
||||||
|
while (start != end)
|
||||||
|
result = utf8::unchecked::append(*(start++), result);
|
||||||
|
|
||||||
|
return result;
|
||||||
|
}
|
||||||
|
|
||||||
|
template <typename octet_iterator, typename u32bit_iterator>
|
||||||
|
u32bit_iterator utf8to32 (octet_iterator start, octet_iterator end, u32bit_iterator result)
|
||||||
|
{
|
||||||
|
while (start < end)
|
||||||
|
(*result++) = utf8::unchecked::next(start);
|
||||||
|
|
||||||
|
return result;
|
||||||
|
}
|
||||||
|
|
||||||
|
// The iterator class
|
||||||
|
template <typename octet_iterator>
|
||||||
|
class iterator : public std::iterator <std::bidirectional_iterator_tag, uint32_t> {
|
||||||
|
octet_iterator it;
|
||||||
|
public:
|
||||||
|
iterator () {};
|
||||||
|
explicit iterator (const octet_iterator& octet_it): it(octet_it) {}
|
||||||
|
// the default "big three" are OK
|
||||||
|
octet_iterator base () const { return it; }
|
||||||
|
uint32_t operator * () const
|
||||||
|
{
|
||||||
|
octet_iterator temp = it;
|
||||||
|
return utf8::unchecked::next(temp);
|
||||||
|
}
|
||||||
|
bool operator == (const iterator& rhs) const
|
||||||
|
{
|
||||||
|
return (it == rhs.it);
|
||||||
|
}
|
||||||
|
bool operator != (const iterator& rhs) const
|
||||||
|
{
|
||||||
|
return !(operator == (rhs));
|
||||||
|
}
|
||||||
|
iterator& operator ++ ()
|
||||||
|
{
|
||||||
|
::std::advance(it, utf8::internal::sequence_length(it));
|
||||||
|
return *this;
|
||||||
|
}
|
||||||
|
iterator operator ++ (int)
|
||||||
|
{
|
||||||
|
iterator temp = *this;
|
||||||
|
::std::advance(it, utf8::internal::sequence_length(it));
|
||||||
|
return temp;
|
||||||
|
}
|
||||||
|
iterator& operator -- ()
|
||||||
|
{
|
||||||
|
utf8::unchecked::prior(it);
|
||||||
|
return *this;
|
||||||
|
}
|
||||||
|
iterator operator -- (int)
|
||||||
|
{
|
||||||
|
iterator temp = *this;
|
||||||
|
utf8::unchecked::prior(it);
|
||||||
|
return temp;
|
||||||
|
}
|
||||||
|
}; // class iterator
|
||||||
|
|
||||||
|
} // namespace utf8::unchecked
|
||||||
|
} // namespace utf8
|
||||||
|
|
||||||
|
|
||||||
|
#endif // header guard
|
||||||
|
|
Loading…
Reference in a new issue