diff options
author | Kurt Pattyn <pattyn.kurt@gmail.com> | 2013-10-06 11:40:47 +0200 |
---|---|---|
committer | The Qt Project <gerrit-noreply@qt-project.org> | 2013-10-17 09:50:58 +0200 |
commit | add2bf739ae96603cb919b908cbb53c00d0628cc (patch) | |
tree | 9702a95d145fc9f429aa6f2ec104cfab75cae753 /tests/benchmarks/corelib/tools/qstring/main.cpp | |
parent | e8853506bf82e569009e68a23437d6a134176f63 (diff) |
Allow non-character codes in utf8 strings
Changed the processing of non-character code handling in the UTF8 codec.
Non-character codes are now accepted in QStrings, QUrls and QJson strings.
Unit tests were adapted accordingly.
For more info about non-character codes,
see: http://www.unicode.org/versions/corrigendum9.html
[ChangeLog][QtCore][QUtf8]
UTF-8 now accepts non-character unicode points; these are not replaced
by the replacement character anymore
[ChangeLog][QtCore][QUrl]
QUrl now fully accepts non-character unicode points; they are encoded as
percent characters; they can also be pretty decoded
[ChangeLog][QtCore][QJson]
The Writer and the Parser now fully accept non-character unicode points.
Change-Id: I77cf4f0e6210741eac8082912a0b6118eced4f77
Task-number: QTBUG-33229
Reviewed-by: Lars Knoll <lars.knoll@digia.com>
Reviewed-by: Thiago Macieira <thiago.macieira@intel.com>
Diffstat (limited to 'tests/benchmarks/corelib/tools/qstring/main.cpp')
-rw-r--r-- | tests/benchmarks/corelib/tools/qstring/main.cpp | 18 |
1 files changed, 8 insertions, 10 deletions
diff --git a/tests/benchmarks/corelib/tools/qstring/main.cpp b/tests/benchmarks/corelib/tools/qstring/main.cpp index 67ed4c32b9..6101cfe8fb 100644 --- a/tests/benchmarks/corelib/tools/qstring/main.cpp +++ b/tests/benchmarks/corelib/tools/qstring/main.cpp @@ -1980,16 +1980,15 @@ int fromUtf8_qt47(ushort *dst, const char *chars, int len) --need; if (!need) { // utf-8 bom composes into 0xfeff code point - bool nonCharacter; if (!headerdone && uc == 0xfeff) { // don't do anything, just skip the BOM - } else if (!(nonCharacter = QChar::isNonCharacter(uc)) && QChar::requiresSurrogates(uc) && uc <= QChar::LastValidCodePoint) { + } else if (QChar::requiresSurrogates(uc) && uc <= QChar::LastValidCodePoint) { // surrogate pair //Q_ASSERT((qch - (ushort*)result.unicode()) + 2 < result.length()); *qch++ = QChar::highSurrogate(uc); *qch++ = QChar::lowSurrogate(uc); - } else if ((uc < min_uc) || QChar::isSurrogate(uc) || nonCharacter || uc > QChar::LastValidCodePoint) { - // error: overlong sequence, UTF16 surrogate or non-character + } else if ((uc < min_uc) || QChar::isSurrogate(uc) || uc > QChar::LastValidCodePoint) { + // error: overlong sequence or UTF16 surrogate *qch++ = replacement; ++invalid; } else { @@ -2086,16 +2085,15 @@ int fromUtf8_qt47_stateless(ushort *dst, const char *chars, int len) --need; if (!need) { // utf-8 bom composes into 0xfeff code point - bool nonCharacter; if (!headerdone && uc == 0xfeff) { // don't do anything, just skip the BOM - } else if (!(nonCharacter = QChar::isNonCharacter(uc)) && QChar::requiresSurrogates(uc) && uc <= QChar::LastValidCodePoint) { + } else if (QChar::requiresSurrogates(uc) && uc <= QChar::LastValidCodePoint) { // surrogate pair //Q_ASSERT((qch - (ushort*)result.unicode()) + 2 < result.length()); *qch++ = QChar::highSurrogate(uc); *qch++ = QChar::lowSurrogate(uc); - } else if ((uc < min_uc) || QChar::isSurrogate(uc) || nonCharacter || uc > QChar::LastValidCodePoint) { - // error: overlong sequence, UTF16 surrogate or non-character + } else if ((uc < min_uc) || QChar::isSurrogate(uc) || uc > QChar::LastValidCodePoint) { + // error: overlong sequence or UTF16 surrogate *qch++ = replacement; ++invalid; } else { @@ -2214,7 +2212,7 @@ static inline void extract_utf8_multibyte(ushort *&dst, const char *&chars, qptr chars += 2; len -= 2; if (!trusted && - (ucs < 0x800 || QChar::isNonCharacter(ucs) || QChar::isSurrogate(ucs))) + (ucs < 0x800 || QChar::isSurrogate(ucs))) dst[counter] = QChar::ReplacementCharacter; else dst[counter] = ucs; @@ -2245,7 +2243,7 @@ static inline void extract_utf8_multibyte(ushort *&dst, const char *&chars, qptr // dst[counter] will correspond to chars[counter..counter+2], so adjust chars += 3; len -= 3; - if (trusted || (QChar::requiresSurrogates(ucs) && ucs <= QChar::LastValidCodePoint && !QChar::isNonCharacter(ucs))) { + if (trusted || (QChar::requiresSurrogates(ucs) && ucs <= QChar::LastValidCodePoint)) { dst[counter + 0] = QChar::highSurrogate(ucs); dst[counter + 1] = QChar::lowSurrogate(ucs); counter += 2; |