summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorGiuseppe D'Angelo <giuseppe.dangelo@kdab.com>2022-01-24 00:38:27 +0100
committerQt Cherry-pick Bot <cherrypick_bot@qt-project.org>2022-03-17 05:53:07 +0000
commitb26b25bfaa68d875afbbb2e5e6c2c2a67cbd936c (patch)
tree472fba6f989c20ff07615be993cb01423e1be792
parent16249e74fc92c92d7170afd33a99f8cfdaa9b308 (diff)
QByteArray: fix isUpper/isLower
577d698b8e72bc0969ae7545a1a56d3a3d08bdda changed QString::isUpper / isLower behaviors to match Unicode semantics: a string is uppercase if it's identical to its own toLower/toUpper folding. These semantics come from Unicode so they're not up for debate. That commit however left QByteArray untouched. Generally speaking, we want to move away from QByteArray as "text storage" -- this has partially happened between Qt 5 and Qt 6, where QByteArray went from Latin-1 semantics to ASCII semantics. Still, QByteArray offers toUpper/toLower and isUpper/isLower and all this family of functions should be consistent in behavior. Apply the same fix that was applied to QString. [ChangeLog][Important Behavior Changes] The semantics of QByteArray::isLower() and QByteArray::isUpper() have been changed. Now lowercase (resp. uppercase) byte arrays are allowed to contain any character; a byte array is considered lowercase (resp. uppercase) if it's equal to its own toLower() (resp. toUpper()) folding. For instance, the "abc123" byte array is now considered to be lowercase. Previously, the isLower() (resp. isUpper()) functions checked whether the byte array only contained ASCII lowercase (resp. uppercase) characters, and was at least 1 character long. This had the side effect that byte array containing ASCII non-letters (e.g. numbers, symbols, etc.) were not lowercase nor uppercase. [ChangeLog][QtCore][QByteArray] QByteArray::isLower() and QByteArray::isUpper() now work correctly with empty byte arrays. The semantics of these functions have been changed. Fixes: QTBUG-100107 Change-Id: Id56a42f01b2d1af5387bf0e6ccff0f824f757155 Reviewed-by: Thiago Macieira <thiago.macieira@intel.com> (cherry picked from commit 2d95b7534530fec1e1e52ef7e8be289abb48b822) Reviewed-by: Qt Cherry-pick Bot <cherrypick_bot@qt-project.org>
-rw-r--r--src/corelib/text/qbytearray.cpp58
-rw-r--r--tests/auto/corelib/text/qbytearray/tst_qbytearray.cpp32
2 files changed, 43 insertions, 47 deletions
diff --git a/src/corelib/text/qbytearray.cpp b/src/corelib/text/qbytearray.cpp
index 03dbbfed93..23082944a9 100644
--- a/src/corelib/text/qbytearray.cpp
+++ b/src/corelib/text/qbytearray.cpp
@@ -64,6 +64,8 @@
#include <string.h>
#include <stdlib.h>
+#include <algorithm>
+
#define IS_RAW_DATA(d) ((d)->flags() & QArrayData::RawDataType)
QT_BEGIN_NAMESPACE
@@ -2743,56 +2745,44 @@ static constexpr inline bool isUpperCaseAscii(char c)
return c >= 'A' && c <= 'Z';
}
+/*
+ Returns true if \a c is an lowercase ASCII letter.
+ */
+static constexpr inline bool isLowerCaseAscii(char c)
+{
+ return c >= 'a' && c <= 'z';
+}
+
/*!
- Returns \c true if this byte array contains only ASCII uppercase letters,
- otherwise returns \c false.
+ Returns \c true if this byte array is uppercase, that is, if
+ it's identical to its toUpper() folding.
+
+ Note that this does \e not mean that the byte array only contains
+ uppercase letters; only that it contains no ASCII lowercase letters.
+
\since 5.12
\sa isLower(), toUpper()
*/
bool QByteArray::isUpper() const
{
- if (isEmpty())
- return false;
-
- const char *d = data();
-
- for (qsizetype i = 0, max = size(); i < max; ++i) {
- if (!isUpperCaseAscii(d[i]))
- return false;
- }
-
- return true;
-}
-
-/*
- Returns true if \a c is an lowercase ASCII letter.
- */
-static constexpr inline bool isLowerCaseAscii(char c)
-{
- return c >= 'a' && c <= 'z';
+ return std::none_of(begin(), end(), isLowerCaseAscii);
}
/*!
- Returns \c true if this byte array contains only lowercase ASCII letters,
- otherwise returns \c false.
+ Returns \c true if this byte array is lowercase, that is, if
+ it's identical to its toLower() folding.
+
+ Note that this does \e not mean that the byte array only contains
+ lowercase letters; only that it contains no ASCII uppercase letters.
+
\since 5.12
\sa isUpper(), toLower()
*/
bool QByteArray::isLower() const
{
- if (isEmpty())
- return false;
-
- const char *d = data();
-
- for (qsizetype i = 0, max = size(); i < max; ++i) {
- if (!isLowerCaseAscii(d[i]))
- return false;
- }
-
- return true;
+ return std::none_of(begin(), end(), isUpperCaseAscii);
}
/*!
diff --git a/tests/auto/corelib/text/qbytearray/tst_qbytearray.cpp b/tests/auto/corelib/text/qbytearray/tst_qbytearray.cpp
index 073bb2dc08..37b9c90ab4 100644
--- a/tests/auto/corelib/text/qbytearray/tst_qbytearray.cpp
+++ b/tests/auto/corelib/text/qbytearray/tst_qbytearray.cpp
@@ -2240,10 +2240,16 @@ void tst_QByteArray::toUpperLower()
QFETCH(QByteArray, input);
QFETCH(QByteArray, upper);
QFETCH(QByteArray, lower);
+ QVERIFY(upper.isUpper());
+ QVERIFY(lower.isLower());
QCOMPARE(lower.toLower(), lower);
+ QVERIFY(lower.toLower().isLower());
QCOMPARE(upper.toUpper(), upper);
+ QVERIFY(upper.toUpper().isUpper());
QCOMPARE(input.toUpper(), upper);
+ QVERIFY(input.toUpper().isUpper());
QCOMPARE(input.toLower(), lower);
+ QVERIFY(input.toLower().isLower());
QByteArray copy = input;
QCOMPARE(std::move(copy).toUpper(), upper);
@@ -2272,12 +2278,12 @@ void tst_QByteArray::toUpperLower()
void tst_QByteArray::isUpper()
{
- QVERIFY(!QByteArray().isUpper());
- QVERIFY(!QByteArray("").isUpper());
+ QVERIFY(QByteArray().isUpper());
+ QVERIFY(QByteArray("").isUpper());
QVERIFY(QByteArray("TEXT").isUpper());
- QVERIFY(!QByteArray("\xD0\xDE").isUpper()); // non-ASCII is neither upper nor lower
- QVERIFY(!QByteArray("\xD7").isUpper());
- QVERIFY(!QByteArray("\xDF").isUpper());
+ QVERIFY(QByteArray("\xD0\xDE").isUpper());
+ QVERIFY(QByteArray("\xD7").isUpper());
+ QVERIFY(QByteArray("\xDF").isUpper());
QVERIFY(!QByteArray("text").isUpper());
QVERIFY(!QByteArray("Text").isUpper());
QVERIFY(!QByteArray("tExt").isUpper());
@@ -2287,19 +2293,19 @@ void tst_QByteArray::isUpper()
QVERIFY(!QByteArray("teXT").isUpper());
QVERIFY(!QByteArray("tEXt").isUpper());
QVERIFY(!QByteArray("tExT").isUpper());
- QVERIFY(!QByteArray("@ABYZ[").isUpper());
+ QVERIFY(QByteArray("@ABYZ[").isUpper());
QVERIFY(!QByteArray("@abyz[").isUpper());
- QVERIFY(!QByteArray("`ABYZ{").isUpper());
+ QVERIFY(QByteArray("`ABYZ{").isUpper());
QVERIFY(!QByteArray("`abyz{").isUpper());
}
void tst_QByteArray::isLower()
{
- QVERIFY(!QByteArray().isLower());
- QVERIFY(!QByteArray("").isLower());
+ QVERIFY(QByteArray().isLower());
+ QVERIFY(QByteArray("").isLower());
QVERIFY(QByteArray("text").isLower());
- QVERIFY(!QByteArray("\xE0\xFF").isLower()); // non-ASCII is neither upper nor lower
- QVERIFY(!QByteArray("\xF7").isLower());
+ QVERIFY(QByteArray("\xE0\xFF").isLower());
+ QVERIFY(QByteArray("\xF7").isLower());
QVERIFY(!QByteArray("Text").isLower());
QVERIFY(!QByteArray("tExt").isLower());
QVERIFY(!QByteArray("teXt").isLower());
@@ -2310,9 +2316,9 @@ void tst_QByteArray::isLower()
QVERIFY(!QByteArray("tExT").isLower());
QVERIFY(!QByteArray("TEXT").isLower());
QVERIFY(!QByteArray("@ABYZ[").isLower());
- QVERIFY(!QByteArray("@abyz[").isLower());
+ QVERIFY(QByteArray("@abyz[").isLower());
QVERIFY(!QByteArray("`ABYZ{").isLower());
- QVERIFY(!QByteArray("`abyz{").isLower());
+ QVERIFY(QByteArray("`abyz{").isLower());
}
void tst_QByteArray::macTypes()