github_mirrors/vectorscan
3
0
Fork 1
mirror of https://github.com/VectorCamp/vectorscan.git synced 2025-06-28 16:41:01 +03:00
Code Issues Packages Projects Releases Wiki Activity

Treat characters between \Q \E as codepoints in UTF8 mode.

Browse Source 
fixes github issue #57
This commit is contained in:
Alex Coyte 2017-06-19 11:03:05 +10:00 committed by Matthew Barr
parent 2b788f1234
commit a185be5a4f
1 changed files with 29 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

29
src/parser/Parser.rl
View File

@ -1155,6 +1155,35 @@ unichar readUtf8CodePoint4c(const char *s) {
'\\E' => {
fgoto main;
};
#unicode chars
utf8_2c when is_utf8 => {
assert(mode.utf8);
/* leverage ComponentClass to generate the vertices */
auto cc = getComponentClass(mode);
cc->add(readUtf8CodePoint2c(ts));
cc->finalize();
currentSeq->addComponent(move(cc));
};
utf8_3c when is_utf8 => {
assert(mode.utf8);
/* leverage ComponentClass to generate the vertices */
auto cc = getComponentClass(mode);
cc->add(readUtf8CodePoint3c(ts));
cc->finalize();
currentSeq->addComponent(move(cc));
};
utf8_4c when is_utf8 => {
assert(mode.utf8);
/* leverage ComponentClass to generate the vertices */
auto cc = getComponentClass(mode);
cc->add(readUtf8CodePoint4c(ts));
cc->finalize();
currentSeq->addComponent(move(cc));
};
# Literal character
any => {
addLiteral(currentSeq, *ts, mode);