Browse Source
Merge
Merge
Former-commit-id:mainaa69376aa1
[formerly8e92e0569d
] Former-commit-id:785529f043
10 changed files with 250 additions and 2723 deletions
-
177examples/dtmc/crowds/crowds.pm
-
72examples/pmdp/coin8/coin8.pm
-
2resources/3rdparty/include_cpptemplate.cmake
-
12resources/3rdparty/utf8_v2_3_4/doc/ReleaseNotes
-
1789resources/3rdparty/utf8_v2_3_4/doc/utf8cpp.html
-
34resources/3rdparty/utf8_v2_3_4/source/utf8.h
-
327resources/3rdparty/utf8_v2_3_4/source/utf8/checked.h
-
329resources/3rdparty/utf8_v2_3_4/source/utf8/core.h
-
228resources/3rdparty/utf8_v2_3_4/source/utf8/unchecked.h
-
3src/CMakeLists.txt
@ -0,0 +1,177 @@ |
|||||
|
// CROWDS [Reiter,Rubin] |
||||
|
// Vitaly Shmatikov, 2002 |
||||
|
|
||||
|
// Note: |
||||
|
// Change everything marked CWDSIZ when changing the size of the crowd |
||||
|
// Change everything marked CWDMAX when increasing max size of the crowd |
||||
|
|
||||
|
dtmc |
||||
|
|
||||
|
// Probability of forwarding |
||||
|
const double PF = 0.8; |
||||
|
|
||||
|
// Probability that a crowd member is bad |
||||
|
const double badC = 0.091; |
||||
|
// const double badC = 0.167; |
||||
|
|
||||
|
const int TotalRuns; // Total number of protocol runs to analyze |
||||
|
const int CrowdSize; // CWDSIZ: actual number of good crowd members |
||||
|
const int MaxGood=20; // CWDMAX: maximum number of good crowd members |
||||
|
|
||||
|
// Process definitions |
||||
|
module crowds |
||||
|
|
||||
|
// Auxiliary variables |
||||
|
launch: bool init true; // Start modeling? |
||||
|
new: bool init false; // Initialize a new protocol instance? |
||||
|
runCount: [0..TotalRuns] init TotalRuns; // Counts protocol instances |
||||
|
start: bool init false; // Start the protocol? |
||||
|
run: bool init false; // Run the protocol? |
||||
|
lastSeen: [0..MaxGood] init MaxGood; // Last crowd member to touch msg |
||||
|
good: bool init false; // Crowd member is good? |
||||
|
bad: bool init false; // ... bad? |
||||
|
recordLast: bool init false; // Record last seen crowd member? |
||||
|
badObserve: bool init false; // Bad members observes who sent msg? |
||||
|
deliver: bool init false; // Deliver message to destination? |
||||
|
done: bool init false; // Protocol instance finished? |
||||
|
|
||||
|
// Counters for attackers' observations |
||||
|
// CWDMAX: 1 counter per each good crowd member |
||||
|
observe0: [0..TotalRuns] init 0; |
||||
|
observe1: [0..TotalRuns] init 0; |
||||
|
observe2: [0..TotalRuns] init 0; |
||||
|
observe3: [0..TotalRuns] init 0; |
||||
|
observe4: [0..TotalRuns] init 0; |
||||
|
observe5: [0..TotalRuns] init 0; |
||||
|
observe6: [0..TotalRuns] init 0; |
||||
|
observe7: [0..TotalRuns] init 0; |
||||
|
observe8: [0..TotalRuns] init 0; |
||||
|
observe9: [0..TotalRuns] init 0; |
||||
|
observe10: [0..TotalRuns] init 0; |
||||
|
observe11: [0..TotalRuns] init 0; |
||||
|
observe12: [0..TotalRuns] init 0; |
||||
|
observe13: [0..TotalRuns] init 0; |
||||
|
observe14: [0..TotalRuns] init 0; |
||||
|
observe15: [0..TotalRuns] init 0; |
||||
|
observe16: [0..TotalRuns] init 0; |
||||
|
observe17: [0..TotalRuns] init 0; |
||||
|
observe18: [0..TotalRuns] init 0; |
||||
|
observe19: [0..TotalRuns] init 0; |
||||
|
|
||||
|
[] launch -> (new'=true) & (runCount'=TotalRuns) & (launch'=false); |
||||
|
// Set up a new protocol instance |
||||
|
[] new & runCount>0 -> (runCount'=runCount-1) & (new'=false) & (start'=true); |
||||
|
|
||||
|
// SENDER |
||||
|
// Start the protocol |
||||
|
[] start -> (lastSeen'=0) & (run'=true) & (deliver'=false) & (start'=false); |
||||
|
|
||||
|
// CROWD MEMBERS |
||||
|
// Good or bad crowd member? |
||||
|
[] !good & !bad & !deliver & run -> |
||||
|
1-badC : (good'=true) & (recordLast'=true) & (run'=false) + |
||||
|
badC : (bad'=true) & (badObserve'=true) & (run'=false); |
||||
|
|
||||
|
// GOOD MEMBERS |
||||
|
// Forward with probability PF, else deliver |
||||
|
[] good & !deliver & run -> PF : (good'=false) + 1-PF : (deliver'=true); |
||||
|
// Record the last crowd member who touched the msg; |
||||
|
// all good members may appear with equal probability |
||||
|
// Note: This is backward. In the real protocol, each honest |
||||
|
// forwarder randomly chooses the next forwarder. |
||||
|
// Here, the identity of an honest forwarder is randomly |
||||
|
// chosen *after* it has forwarded the message. |
||||
|
[] recordLast & CrowdSize=2 -> |
||||
|
1/2 : (lastSeen'=0) & (recordLast'=false) & (run'=true) + |
||||
|
1/2 : (lastSeen'=1) & (recordLast'=false) & (run'=true); |
||||
|
[] recordLast & CrowdSize=4 -> |
||||
|
1/4 : (lastSeen'=0) & (recordLast'=false) & (run'=true) + |
||||
|
1/4 : (lastSeen'=1) & (recordLast'=false) & (run'=true) + |
||||
|
1/4 : (lastSeen'=2) & (recordLast'=false) & (run'=true) + |
||||
|
1/4 : (lastSeen'=3) & (recordLast'=false) & (run'=true); |
||||
|
[] recordLast & CrowdSize=5 -> |
||||
|
1/5 : (lastSeen'=0) & (recordLast'=false) & (run'=true) + |
||||
|
1/5 : (lastSeen'=1) & (recordLast'=false) & (run'=true) + |
||||
|
1/5 : (lastSeen'=2) & (recordLast'=false) & (run'=true) + |
||||
|
1/5 : (lastSeen'=3) & (recordLast'=false) & (run'=true) + |
||||
|
1/5 : (lastSeen'=4) & (recordLast'=false) & (run'=true); |
||||
|
[] recordLast & CrowdSize=10 -> |
||||
|
1/10 : (lastSeen'=0) & (recordLast'=false) & (run'=true) + |
||||
|
1/10 : (lastSeen'=1) & (recordLast'=false) & (run'=true) + |
||||
|
1/10 : (lastSeen'=2) & (recordLast'=false) & (run'=true) + |
||||
|
1/10 : (lastSeen'=3) & (recordLast'=false) & (run'=true) + |
||||
|
1/10 : (lastSeen'=4) & (recordLast'=false) & (run'=true) + |
||||
|
1/10 : (lastSeen'=5) & (recordLast'=false) & (run'=true) + |
||||
|
1/10 : (lastSeen'=6) & (recordLast'=false) & (run'=true) + |
||||
|
1/10 : (lastSeen'=7) & (recordLast'=false) & (run'=true) + |
||||
|
1/10 : (lastSeen'=8) & (recordLast'=false) & (run'=true) + |
||||
|
1/10 : (lastSeen'=9) & (recordLast'=false) & (run'=true); |
||||
|
[] recordLast & CrowdSize=15 -> |
||||
|
1/15 : (lastSeen'=0) & (recordLast'=false) & (run'=true) + |
||||
|
1/15 : (lastSeen'=1) & (recordLast'=false) & (run'=true) + |
||||
|
1/15 : (lastSeen'=2) & (recordLast'=false) & (run'=true) + |
||||
|
1/15 : (lastSeen'=3) & (recordLast'=false) & (run'=true) + |
||||
|
1/15 : (lastSeen'=4) & (recordLast'=false) & (run'=true) + |
||||
|
1/15 : (lastSeen'=5) & (recordLast'=false) & (run'=true) + |
||||
|
1/15 : (lastSeen'=6) & (recordLast'=false) & (run'=true) + |
||||
|
1/15 : (lastSeen'=7) & (recordLast'=false) & (run'=true) + |
||||
|
1/15 : (lastSeen'=8) & (recordLast'=false) & (run'=true) + |
||||
|
1/15 : (lastSeen'=9) & (recordLast'=false) & (run'=true) + |
||||
|
1/15 : (lastSeen'=10) & (recordLast'=false) & (run'=true) + |
||||
|
1/15 : (lastSeen'=11) & (recordLast'=false) & (run'=true) + |
||||
|
1/15 : (lastSeen'=12) & (recordLast'=false) & (run'=true) + |
||||
|
1/15 : (lastSeen'=13) & (recordLast'=false) & (run'=true) + |
||||
|
1/15 : (lastSeen'=14) & (recordLast'=false) & (run'=true); |
||||
|
[] recordLast & CrowdSize=20 -> |
||||
|
1/20 : (lastSeen'=0) & (recordLast'=false) & (run'=true) + |
||||
|
1/20 : (lastSeen'=1) & (recordLast'=false) & (run'=true) + |
||||
|
1/20 : (lastSeen'=2) & (recordLast'=false) & (run'=true) + |
||||
|
1/20 : (lastSeen'=3) & (recordLast'=false) & (run'=true) + |
||||
|
1/20 : (lastSeen'=4) & (recordLast'=false) & (run'=true) + |
||||
|
1/20 : (lastSeen'=5) & (recordLast'=false) & (run'=true) + |
||||
|
1/20 : (lastSeen'=6) & (recordLast'=false) & (run'=true) + |
||||
|
1/20 : (lastSeen'=7) & (recordLast'=false) & (run'=true) + |
||||
|
1/20 : (lastSeen'=8) & (recordLast'=false) & (run'=true) + |
||||
|
1/20 : (lastSeen'=9) & (recordLast'=false) & (run'=true) + |
||||
|
1/20 : (lastSeen'=10) & (recordLast'=false) & (run'=true) + |
||||
|
1/20 : (lastSeen'=11) & (recordLast'=false) & (run'=true) + |
||||
|
1/20 : (lastSeen'=12) & (recordLast'=false) & (run'=true) + |
||||
|
1/20 : (lastSeen'=13) & (recordLast'=false) & (run'=true) + |
||||
|
1/20 : (lastSeen'=14) & (recordLast'=false) & (run'=true) + |
||||
|
1/20 : (lastSeen'=15) & (recordLast'=false) & (run'=true) + |
||||
|
1/20 : (lastSeen'=16) & (recordLast'=false) & (run'=true) + |
||||
|
1/20 : (lastSeen'=17) & (recordLast'=false) & (run'=true) + |
||||
|
1/20 : (lastSeen'=18) & (recordLast'=false) & (run'=true) + |
||||
|
1/20 : (lastSeen'=19) & (recordLast'=false) & (run'=true); |
||||
|
|
||||
|
// BAD MEMBERS |
||||
|
// Remember from whom the message was received and deliver |
||||
|
// CWDMAX: 1 rule per each good crowd member |
||||
|
[] lastSeen=0 & badObserve & observe0 <TotalRuns -> (observe0' =observe0 +1) & (deliver'=true) & (run'=true) & (badObserve'=false); |
||||
|
[] lastSeen=1 & badObserve & observe1 <TotalRuns -> (observe1' =observe1 +1) & (deliver'=true) & (run'=true) & (badObserve'=false); |
||||
|
[] lastSeen=2 & badObserve & observe2 <TotalRuns -> (observe2' =observe2 +1) & (deliver'=true) & (run'=true) & (badObserve'=false); |
||||
|
[] lastSeen=3 & badObserve & observe3 <TotalRuns -> (observe3' =observe3 +1) & (deliver'=true) & (run'=true) & (badObserve'=false); |
||||
|
[] lastSeen=4 & badObserve & observe4 <TotalRuns -> (observe4' =observe4 +1) & (deliver'=true) & (run'=true) & (badObserve'=false); |
||||
|
[] lastSeen=5 & badObserve & observe5 <TotalRuns -> (observe5' =observe5 +1) & (deliver'=true) & (run'=true) & (badObserve'=false); |
||||
|
[] lastSeen=6 & badObserve & observe6 <TotalRuns -> (observe6' =observe6 +1) & (deliver'=true) & (run'=true) & (badObserve'=false); |
||||
|
[] lastSeen=7 & badObserve & observe7 <TotalRuns -> (observe7' =observe7 +1) & (deliver'=true) & (run'=true) & (badObserve'=false); |
||||
|
[] lastSeen=8 & badObserve & observe8 <TotalRuns -> (observe8' =observe8 +1) & (deliver'=true) & (run'=true) & (badObserve'=false); |
||||
|
[] lastSeen=9 & badObserve & observe9 <TotalRuns -> (observe9' =observe9 +1) & (deliver'=true) & (run'=true) & (badObserve'=false); |
||||
|
[] lastSeen=10 & badObserve & observe10<TotalRuns -> (observe10'=observe10+1) & (deliver'=true) & (run'=true) & (badObserve'=false); |
||||
|
[] lastSeen=11 & badObserve & observe11<TotalRuns -> (observe11'=observe11+1) & (deliver'=true) & (run'=true) & (badObserve'=false); |
||||
|
[] lastSeen=12 & badObserve & observe12<TotalRuns -> (observe12'=observe12+1) & (deliver'=true) & (run'=true) & (badObserve'=false); |
||||
|
[] lastSeen=13 & badObserve & observe13<TotalRuns -> (observe13'=observe13+1) & (deliver'=true) & (run'=true) & (badObserve'=false); |
||||
|
[] lastSeen=14 & badObserve & observe14<TotalRuns -> (observe14'=observe14+1) & (deliver'=true) & (run'=true) & (badObserve'=false); |
||||
|
[] lastSeen=15 & badObserve & observe15<TotalRuns -> (observe15'=observe15+1) & (deliver'=true) & (run'=true) & (badObserve'=false); |
||||
|
[] lastSeen=16 & badObserve & observe16<TotalRuns -> (observe16'=observe16+1) & (deliver'=true) & (run'=true) & (badObserve'=false); |
||||
|
[] lastSeen=17 & badObserve & observe17<TotalRuns -> (observe17'=observe17+1) & (deliver'=true) & (run'=true) & (badObserve'=false); |
||||
|
[] lastSeen=18 & badObserve & observe18<TotalRuns -> (observe18'=observe18+1) & (deliver'=true) & (run'=true) & (badObserve'=false); |
||||
|
[] lastSeen=19 & badObserve & observe19<TotalRuns -> (observe19'=observe19+1) & (deliver'=true) & (run'=true) & (badObserve'=false); |
||||
|
|
||||
|
// RECIPIENT |
||||
|
// Delivery to destination |
||||
|
[] deliver & run -> (done'=true) & (deliver'=false) & (run'=false) & (good'=false) & (bad'=false); |
||||
|
// Start a new instance |
||||
|
[] done -> (new'=true) & (done'=false) & (run'=false) & (lastSeen'=MaxGood); |
||||
|
|
||||
|
endmodule |
@ -0,0 +1,72 @@ |
|||||
|
//Randomised Consensus Protocol |
||||
|
|
||||
|
mdp |
||||
|
const double p1; // in [0.2 , 0.8] |
||||
|
const double p2; // in [0.2 , 0.8] |
||||
|
const double p3; // in [0.2 , 0.8] |
||||
|
const double p4; // in [0.2 , 0.8] |
||||
|
const double p5; |
||||
|
const double p6; |
||||
|
const double p7; |
||||
|
const double p8; |
||||
|
|
||||
|
|
||||
|
const int N=8; |
||||
|
const int K; |
||||
|
const int range = 2*(K+1)*N; |
||||
|
const int counter_init = (K+1)*N; |
||||
|
const int left = N; |
||||
|
const int right = 2*(K+1)*N - N; |
||||
|
|
||||
|
// shared coin |
||||
|
global counter : [0..range] init counter_init; |
||||
|
|
||||
|
module process1 |
||||
|
|
||||
|
// program counter |
||||
|
pc1 : [0..3]; |
||||
|
// 0 - flip |
||||
|
// 1 - write |
||||
|
// 2 - check |
||||
|
// 3 - finished |
||||
|
|
||||
|
// local coin |
||||
|
coin1 : [0..1]; |
||||
|
|
||||
|
// flip coin |
||||
|
[] (pc1=0) -> p1 : (coin1'=0) & (pc1'=1) + 1 - p1 : (coin1'=1) & (pc1'=1); |
||||
|
// write tails -1 (reset coin to add regularity) |
||||
|
[] (pc1=1) & (coin1=0) & (counter>0) -> (counter'=counter-1) & (pc1'=2) & (coin1'=0); |
||||
|
// write heads +1 (reset coin to add regularity) |
||||
|
[] (pc1=1) & (coin1=1) & (counter<range) -> (counter'=counter+1) & (pc1'=2) & (coin1'=0); |
||||
|
// check |
||||
|
// decide tails |
||||
|
[] (pc1=2) & (counter<=left) -> (pc1'=3) & (coin1'=0); |
||||
|
// decide heads |
||||
|
[] (pc1=2) & (counter>=right) -> (pc1'=3) & (coin1'=1); |
||||
|
// flip again |
||||
|
[] (pc1=2) & (counter>left) & (counter<right) -> (pc1'=0); |
||||
|
// loop (all loop together when done) |
||||
|
[done] (pc1=3) -> (pc1'=3); |
||||
|
|
||||
|
endmodule |
||||
|
|
||||
|
module process2 = process1[pc1=pc2,coin1=coin2,p1=p2] endmodule |
||||
|
module process3 = process1[pc1=pc3,coin1=coin3,p1=p3] endmodule |
||||
|
module process4 = process1[pc1=pc4,coin1=coin4,p1=p4] endmodule |
||||
|
module process5 = process1[pc1=pc5,coin1=coin5,p1=p5] endmodule |
||||
|
module process6 = process1[pc1=pc6,coin1=coin6,p1=p6] endmodule |
||||
|
module process7 = process1[pc1=pc7,coin1=coin7,p1=p7] endmodule |
||||
|
module process8 = process1[pc1=pc8,coin1=coin8,p1=p8] endmodule |
||||
|
|
||||
|
label "finished" = pc1=3 &pc2=3 &pc3=3 &pc4=3 & pc5=3 & pc6=3 & pc7=3 & pc8=3; |
||||
|
label "all_coins_equal_1" = coin1 = 1 & coin2 = 1 & coin3 = 1 & coin4 = 1 & coin5 = 1 & coin6 = 1 & coin7 = 1 & coin8 = 1; |
||||
|
label "all_coins_equal_0" = coin1 = 0 & coin2 = 0 & coin3 = 0 & coin4 = 0 & coin5 = 0 & coin6 = 0 & coin7 = 0 & coin8 = 0; |
||||
|
label "agree" = coin1=coin2 & coin2=coin3 & coin3 = coin4 & coin4 = coin5 & coin5 = coin6 & coin6 = coin7 & coin7 = coin8; |
||||
|
|
||||
|
rewards "steps" |
||||
|
true : 1; |
||||
|
endrewards |
||||
|
|
||||
|
|
||||
|
|
@ -1,12 +0,0 @@ |
|||||
utf8 cpp library |
|
||||
Release 2.3.4 |
|
||||
|
|
||||
A minor bug fix release. Thanks to all who reported bugs. |
|
||||
|
|
||||
Note: Version 2.3.3 contained a regression, and therefore was removed. |
|
||||
|
|
||||
Changes from version 2.3.2 |
|
||||
- Bug fix [39]: checked.h Line 273 and unchecked.h Line 182 have an extra ';' |
|
||||
- Bug fix [36]: replace_invalid() only works with back_inserter |
|
||||
|
|
||||
Files included in the release: utf8.h, core.h, checked.h, unchecked.h, utf8cpp.html, ReleaseNotes |
|
1789
resources/3rdparty/utf8_v2_3_4/doc/utf8cpp.html
File diff suppressed because it is too large
View File
File diff suppressed because it is too large
View File
@ -1,34 +0,0 @@ |
|||||
// 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_2675DCD0_9480_4c0c_B92A_CC14C027B731 |
|
||||
#define UTF8_FOR_CPP_2675DCD0_9480_4c0c_B92A_CC14C027B731 |
|
||||
|
|
||||
#include "utf8/checked.h" |
|
||||
#include "utf8/unchecked.h" |
|
||||
|
|
||||
#endif // header guard |
|
@ -1,327 +0,0 @@ |
|||||
// 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_CHECKED_H_2675DCD0_9480_4c0c_B92A_CC14C027B731 |
|
||||
#define UTF8_FOR_CPP_CHECKED_H_2675DCD0_9480_4c0c_B92A_CC14C027B731 |
|
||||
|
|
||||
#include "core.h" |
|
||||
#include <stdexcept> |
|
||||
|
|
||||
namespace utf8 |
|
||||
{ |
|
||||
// Base for the exceptions that may be thrown from the library |
|
||||
class exception : public ::std::exception { |
|
||||
}; |
|
||||
|
|
||||
// Exceptions that may be thrown from the library functions. |
|
||||
class invalid_code_point : public exception { |
|
||||
uint32_t cp; |
|
||||
public: |
|
||||
invalid_code_point(uint32_t cp) : cp(cp) {} |
|
||||
virtual const char* what() const throw() { return "Invalid code point"; } |
|
||||
uint32_t code_point() const {return cp;} |
|
||||
}; |
|
||||
|
|
||||
class invalid_utf8 : public exception { |
|
||||
uint8_t u8; |
|
||||
public: |
|
||||
invalid_utf8 (uint8_t u) : u8(u) {} |
|
||||
virtual const char* what() const throw() { return "Invalid UTF-8"; } |
|
||||
uint8_t utf8_octet() const {return u8;} |
|
||||
}; |
|
||||
|
|
||||
class invalid_utf16 : public exception { |
|
||||
uint16_t u16; |
|
||||
public: |
|
||||
invalid_utf16 (uint16_t u) : u16(u) {} |
|
||||
virtual const char* what() const throw() { return "Invalid UTF-16"; } |
|
||||
uint16_t utf16_word() const {return u16;} |
|
||||
}; |
|
||||
|
|
||||
class not_enough_room : public exception { |
|
||||
public: |
|
||||
virtual const char* what() const throw() { return "Not enough space"; } |
|
||||
}; |
|
||||
|
|
||||
/// The library API - functions intended to be called by the users |
|
||||
|
|
||||
template <typename octet_iterator> |
|
||||
octet_iterator append(uint32_t cp, octet_iterator result) |
|
||||
{ |
|
||||
if (!utf8::internal::is_code_point_valid(cp)) |
|
||||
throw invalid_code_point(cp); |
|
||||
|
|
||||
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, typename output_iterator> |
|
||||
output_iterator replace_invalid(octet_iterator start, octet_iterator end, output_iterator out, uint32_t replacement) |
|
||||
{ |
|
||||
while (start != end) { |
|
||||
octet_iterator sequence_start = start; |
|
||||
internal::utf_error err_code = utf8::internal::validate_next(start, end); |
|
||||
switch (err_code) { |
|
||||
case internal::UTF8_OK : |
|
||||
for (octet_iterator it = sequence_start; it != start; ++it) |
|
||||
*out++ = *it; |
|
||||
break; |
|
||||
case internal::NOT_ENOUGH_ROOM: |
|
||||
throw not_enough_room(); |
|
||||
case internal::INVALID_LEAD: |
|
||||
out = utf8::append (replacement, out); |
|
||||
++start; |
|
||||
break; |
|
||||
case internal::INCOMPLETE_SEQUENCE: |
|
||||
case internal::OVERLONG_SEQUENCE: |
|
||||
case internal::INVALID_CODE_POINT: |
|
||||
out = utf8::append (replacement, out); |
|
||||
++start; |
|
||||
// just one replacement mark for the sequence |
|
||||
while (start != end && utf8::internal::is_trail(*start)) |
|
||||
++start; |
|
||||
break; |
|
||||
} |
|
||||
} |
|
||||
return out; |
|
||||
} |
|
||||
|
|
||||
template <typename octet_iterator, typename output_iterator> |
|
||||
inline output_iterator replace_invalid(octet_iterator start, octet_iterator end, output_iterator out) |
|
||||
{ |
|
||||
static const uint32_t replacement_marker = utf8::internal::mask16(0xfffd); |
|
||||
return utf8::replace_invalid(start, end, out, replacement_marker); |
|
||||
} |
|
||||
|
|
||||
template <typename octet_iterator> |
|
||||
uint32_t next(octet_iterator& it, octet_iterator end) |
|
||||
{ |
|
||||
uint32_t cp = 0; |
|
||||
internal::utf_error err_code = utf8::internal::validate_next(it, end, cp); |
|
||||
switch (err_code) { |
|
||||
case internal::UTF8_OK : |
|
||||
break; |
|
||||
case internal::NOT_ENOUGH_ROOM : |
|
||||
throw not_enough_room(); |
|
||||
case internal::INVALID_LEAD : |
|
||||
case internal::INCOMPLETE_SEQUENCE : |
|
||||
case internal::OVERLONG_SEQUENCE : |
|
||||
throw invalid_utf8(*it); |
|
||||
case internal::INVALID_CODE_POINT : |
|
||||
throw invalid_code_point(cp); |
|
||||
} |
|
||||
return cp; |
|
||||
} |
|
||||
|
|
||||
template <typename octet_iterator> |
|
||||
uint32_t peek_next(octet_iterator it, octet_iterator end) |
|
||||
{ |
|
||||
return utf8::next(it, end); |
|
||||
} |
|
||||
|
|
||||
template <typename octet_iterator> |
|
||||
uint32_t prior(octet_iterator& it, octet_iterator start) |
|
||||
{ |
|
||||
// can't do much if it == start |
|
||||
if (it == start) |
|
||||
throw not_enough_room(); |
|
||||
|
|
||||
octet_iterator end = it; |
|
||||
// Go back until we hit either a lead octet or start |
|
||||
while (utf8::internal::is_trail(*(--it))) |
|
||||
if (it == start) |
|
||||
throw invalid_utf8(*it); // error - no lead byte in the sequence |
|
||||
return utf8::peek_next(it, end); |
|
||||
} |
|
||||
|
|
||||
/// Deprecated in versions that include "prior" |
|
||||
template <typename octet_iterator> |
|
||||
uint32_t previous(octet_iterator& it, octet_iterator pass_start) |
|
||||
{ |
|
||||
octet_iterator end = it; |
|
||||
while (utf8::internal::is_trail(*(--it))) |
|
||||
if (it == pass_start) |
|
||||
throw invalid_utf8(*it); // error - no lead byte in the sequence |
|
||||
octet_iterator temp = it; |
|
||||
return utf8::next(temp, end); |
|
||||
} |
|
||||
|
|
||||
template <typename octet_iterator, typename distance_type> |
|
||||
void advance (octet_iterator& it, distance_type n, octet_iterator end) |
|
||||
{ |
|
||||
for (distance_type i = 0; i < n; ++i) |
|
||||
utf8::next(it, end); |
|
||||
} |
|
||||
|
|
||||
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::next(first, last); |
|
||||
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)) { |
|
||||
if (start != end) { |
|
||||
uint32_t trail_surrogate = utf8::internal::mask16(*start++); |
|
||||
if (utf8::internal::is_trail_surrogate(trail_surrogate)) |
|
||||
cp = (cp << 10) + trail_surrogate + internal::SURROGATE_OFFSET; |
|
||||
else |
|
||||
throw invalid_utf16(static_cast<uint16_t>(trail_surrogate)); |
|
||||
} |
|
||||
else |
|
||||
throw invalid_utf16(static_cast<uint16_t>(cp)); |
|
||||
|
|
||||
} |
|
||||
// Lone trail surrogate |
|
||||
else if (utf8::internal::is_trail_surrogate(cp)) |
|
||||
throw invalid_utf16(static_cast<uint16_t>(cp)); |
|
||||
|
|
||||
result = utf8::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::next(start, end); |
|
||||
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::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::next(start, end); |
|
||||
|
|
||||
return result; |
|
||||
} |
|
||||
|
|
||||
// The iterator class |
|
||||
template <typename octet_iterator> |
|
||||
class iterator : public std::iterator <std::bidirectional_iterator_tag, uint32_t> { |
|
||||
octet_iterator it; |
|
||||
octet_iterator range_start; |
|
||||
octet_iterator range_end; |
|
||||
public: |
|
||||
iterator () {} |
|
||||
explicit iterator (const octet_iterator& octet_it, |
|
||||
const octet_iterator& range_start, |
|
||||
const octet_iterator& range_end) : |
|
||||
it(octet_it), range_start(range_start), range_end(range_end) |
|
||||
{ |
|
||||
if (it < range_start || it > range_end) |
|
||||
throw std::out_of_range("Invalid utf-8 iterator position"); |
|
||||
} |
|
||||
// the default "big three" are OK |
|
||||
octet_iterator base () const { return it; } |
|
||||
uint32_t operator * () const |
|
||||
{ |
|
||||
octet_iterator temp = it; |
|
||||
return utf8::next(temp, range_end); |
|
||||
} |
|
||||
bool operator == (const iterator& rhs) const |
|
||||
{ |
|
||||
if (range_start != rhs.range_start || range_end != rhs.range_end) |
|
||||
throw std::logic_error("Comparing utf-8 iterators defined with different ranges"); |
|
||||
return (it == rhs.it); |
|
||||
} |
|
||||
bool operator != (const iterator& rhs) const |
|
||||
{ |
|
||||
return !(operator == (rhs)); |
|
||||
} |
|
||||
iterator& operator ++ () |
|
||||
{ |
|
||||
utf8::next(it, range_end); |
|
||||
return *this; |
|
||||
} |
|
||||
iterator operator ++ (int) |
|
||||
{ |
|
||||
iterator temp = *this; |
|
||||
utf8::next(it, range_end); |
|
||||
return temp; |
|
||||
} |
|
||||
iterator& operator -- () |
|
||||
{ |
|
||||
utf8::prior(it, range_start); |
|
||||
return *this; |
|
||||
} |
|
||||
iterator operator -- (int) |
|
||||
{ |
|
||||
iterator temp = *this; |
|
||||
utf8::prior(it, range_start); |
|
||||
return temp; |
|
||||
} |
|
||||
}; // class iterator |
|
||||
|
|
||||
} // namespace utf8 |
|
||||
|
|
||||
#endif //header guard |
|
||||
|
|
||||
|
|
@ -1,329 +0,0 @@ |
|||||
// 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 |
|
||||
|
|
||||
|
|
@ -1,228 +0,0 @@ |
|||||
// 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 |
|
||||
|
|
Write
Preview
Loading…
Cancel
Save
Reference in new issue