diff options
author | Neil <nyamatongwe@gmail.com> | 2020-05-19 13:23:04 +1000 |
---|---|---|
committer | Neil <nyamatongwe@gmail.com> | 2020-05-19 13:23:04 +1000 |
commit | 24b9ab288ebb48fb4cd7efc0fd6a409f50964664 (patch) | |
tree | 0126e94199c95d13dc2921f6dc2ab6fbe43e5a18 | |
parent | 39eb66f3627b925e4591d3aeb735120b93b0022c (diff) | |
download | scintilla-mirror-24b9ab288ebb48fb4cd7efc0fd6a409f50964664.tar.gz |
Encapsulate common check for PS, LS, and NEL as UTF8IsMultibyteLineEnd.
Avoids construction of temporary array.
-rw-r--r-- | src/CellBuffer.cxx | 9 | ||||
-rw-r--r-- | src/UniConversion.h | 7 |
2 files changed, 10 insertions, 6 deletions
diff --git a/src/CellBuffer.cxx b/src/CellBuffer.cxx index 4298cf7d5..877a2c46f 100644 --- a/src/CellBuffer.cxx +++ b/src/CellBuffer.cxx @@ -735,8 +735,7 @@ bool CellBuffer::ContainsLineEnd(const char *s, Sci::Position length) const noex if ((ch == '\r') || (ch == '\n')) { return true; } else if (utf8LineEnds) { - const unsigned char back3[3] = { chBeforePrev, chPrev, ch }; - if (UTF8IsSeparator(back3) || UTF8IsNEL(back3 + 1)) { + if (UTF8IsMultibyteLineEnd(chBeforePrev, chPrev, ch)) { return true; } } @@ -908,8 +907,7 @@ void CellBuffer::ResetLineEnds() { lineInsert++; } } else if (utf8LineEnds) { - const unsigned char back3[3] = {chBeforePrev, chPrev, ch}; - if (UTF8IsSeparator(back3) || UTF8IsNEL(back3+1)) { + if (UTF8IsMultibyteLineEnd(chBeforePrev, chPrev, ch)) { InsertLine(lineInsert, (position + i) + 1, atLineStart); lineInsert++; } @@ -1083,8 +1081,7 @@ void CellBuffer::BasicInsertString(Sci::Position position, const char *s, Sci::P InsertLine(lineInsert, (position + ptr - s), atLineStart); lineInsert++; } else if (utf8LineEnds && !UTF8IsAscii(ch)) { - const unsigned char back3[3] = { chBeforePrev, chPrev, ch }; - if (UTF8IsSeparator(back3) || UTF8IsNEL(back3 + 1)) { + if (UTF8IsMultibyteLineEnd(chBeforePrev, chPrev, ch)) { InsertLine(lineInsert, (position + ptr - s), atLineStart); lineInsert++; } diff --git a/src/UniConversion.h b/src/UniConversion.h index 4aea824b6..bfa247c06 100644 --- a/src/UniConversion.h +++ b/src/UniConversion.h @@ -75,6 +75,13 @@ inline bool UTF8IsNEL(const unsigned char *us) noexcept { return (us[0] == 0xc2) && (us[1] == 0x85); } +// Is the sequence of 3 char a UTF-8 line end? Only the last two char are tested for a NEL. +constexpr bool UTF8IsMultibyteLineEnd(unsigned char ch0, unsigned char ch1, unsigned char ch2) noexcept { + return + ((ch0 == 0xe2) && (ch1 == 0x80) && ((ch2 == 0xa8) || (ch2 == 0xa9))) || + ((ch1 == 0xc2) && (ch2 == 0x85)); +} + enum { SURROGATE_LEAD_FIRST = 0xD800 }; enum { SURROGATE_LEAD_LAST = 0xDBFF }; enum { SURROGATE_TRAIL_FIRST = 0xDC00 }; |