mirror of
https://github.com/unicode-org/icu.git
synced 2025-04-06 14:05:32 +00:00
ICU-4152 UnicodeSetIterator::getString() works with code points
X-SVN-Rev: 19028
This commit is contained in:
Andy Heninger
parent
3d0b127c12
commit
64e16dfb5e
3 changed files with 121 additions and 30 deletions
|
|
@ -32,19 +32,19 @@ class UnicodeString;
|
|||
* or methods declared as "protected" to be private. The use of
|
||||
* protected in this class is an artifact of history.
|
||||
*
|
||||
* <p>To iterate over code points, use a loop like this:
|
||||
* <p>To iterate over code points and strings, use a loop like this:
|
||||
* <pre>
|
||||
* UnicodeSetIterator it(set);
|
||||
* while (set.next()) {
|
||||
* if (set.isString()) {
|
||||
* processString(set.getString());
|
||||
* } else {
|
||||
* processCodepoint(set.getCodepoint());
|
||||
* }
|
||||
* processItem(set.getString());
|
||||
* }
|
||||
* </pre>
|
||||
* <p>Each item in the set is accessed as a string. Set elements
|
||||
* consisting of single code points are returned as strings containing
|
||||
* just the one code point.
|
||||
*
|
||||
* <p>To iterate over code point ranges, use a loop like this:
|
||||
* <p>To iterate over code point ranges, instead of individual code points,
|
||||
* use a loop like this:
|
||||
* <pre>
|
||||
* UnicodeSetIterator it(set);
|
||||
* while (it.nextRange()) {
|
||||
|
|
@ -125,9 +125,14 @@ class U_COMMON_API UnicodeSetIterator : public UObject {
|
|||
* caller can retrieve it with <tt>getString()</tt>. If this
|
||||
* method returns false, the current element is a code point or
|
||||
* code point range, depending on whether <tt>next()</tt> or
|
||||
* <tt>nextRange()</tt> was called, and the caller can retrieve it
|
||||
* with <tt>getCodepoint()</tt> and, for a range,
|
||||
* <tt>getCodepointEnd()</tt>.
|
||||
* <tt>nextRange()</tt> was called.
|
||||
* Elements of types string and codepoint can both be retrieved
|
||||
* with the function <tt>getString()</tt>.
|
||||
* Elements of type codepoint can also be retrieved with
|
||||
* <tt>getCodepoint()</tt>.
|
||||
* For ranges, <tt>getCodepoint()</tt> returns the starting codepoint
|
||||
* of the range, and <tt>getCodepointEnd()</tt> returns the end
|
||||
* of the range.
|
||||
* @stable ICU 2.4
|
||||
*/
|
||||
inline UBool isString() const;
|
||||
|
|
@ -161,22 +166,25 @@ class U_COMMON_API UnicodeSetIterator : public UObject {
|
|||
const UnicodeString& getString();
|
||||
|
||||
/**
|
||||
* Returns the next element in the set, either a single code point
|
||||
* or a string. If there are no more elements in the set, return
|
||||
* false. If <tt>codepoint == IS_STRING</tt>, the value is a
|
||||
* string in the <tt>string</tt> field. Otherwise the value is a
|
||||
* single code point in the <tt>codepoint</tt> field.
|
||||
* Advances the iteration position to the next element in the set,
|
||||
* which can be either a single code point or a string.
|
||||
* If there are no more elements in the set, return false.
|
||||
*
|
||||
* <p>
|
||||
* If <tt>isString() == TRUE</tt>, the value is a
|
||||
* string, otherwise the value is a
|
||||
* single code point. Elements of either type can be retrieved
|
||||
* with the function <tt>getString()</tt>, while elements of
|
||||
* consisting of a single code point can be retrieved with
|
||||
* <tt>getCodepoint()</tt>
|
||||
*
|
||||
* <p>The order of iteration is all code points in sorted order,
|
||||
* followed by all strings sorted order. <tt>codepointEnd</tt> is
|
||||
* undefined after calling this method. <tt>string</tt> is
|
||||
* undefined unless <tt>codepoint == IS_STRING</tt>. Do not mix
|
||||
* followed by all strings sorted order. Do not mix
|
||||
* calls to <tt>next()</tt> and <tt>nextRange()</tt> without
|
||||
* calling <tt>reset()</tt> between them. The results of doing so
|
||||
* are undefined.
|
||||
*
|
||||
* @return true if there was another element in the set and this
|
||||
* object contains the element.
|
||||
* @return true if there was another element in the set.
|
||||
* @stable ICU 2.4
|
||||
*/
|
||||
UBool next();
|
||||
|
|
@ -184,21 +192,20 @@ class U_COMMON_API UnicodeSetIterator : public UObject {
|
|||
/**
|
||||
* Returns the next element in the set, either a code point range
|
||||
* or a string. If there are no more elements in the set, return
|
||||
* false. If <tt>codepoint == IS_STRING</tt>, the value is a
|
||||
* string in the <tt>string</tt> field. Otherwise the value is a
|
||||
* range of one or more code points from <tt>codepoint</tt> to
|
||||
* <tt>codepointeEnd</tt> inclusive.
|
||||
* false. If <tt>isString() == TRUE</tt>, the value is a
|
||||
* string and can be accessed with <tt>getString()</tt>. Otherwise the value is a
|
||||
* range of one or more code points from <tt>getCodepoint()</tt> to
|
||||
* <tt>getCodepointeEnd()</tt> inclusive.
|
||||
*
|
||||
* <p>The order of iteration is all code points ranges in sorted
|
||||
* order, followed by all strings sorted order. Ranges are
|
||||
* disjoint and non-contiguous. <tt>string</tt> is undefined
|
||||
* unless <tt>codepoint == IS_STRING</tt>. Do not mix calls to
|
||||
* disjoint and non-contiguous. The value returned from <tt>getString()</tt>
|
||||
* is undefined unless <tt>isString() == TRUE</tt>. Do not mix calls to
|
||||
* <tt>next()</tt> and <tt>nextRange()</tt> without calling
|
||||
* <tt>reset()</tt> between them. The results of doing so are
|
||||
* undefined.
|
||||
*
|
||||
* @return true if there was another element in the set and this
|
||||
* object contains the element.
|
||||
* @return true if there was another element in the set.
|
||||
* @stable ICU 2.4
|
||||
*/
|
||||
UBool nextRange();
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
/*
|
||||
**************************************************************************************
|
||||
* Copyright (C) 1999-2005 Alan Liu ,International Business Machines Corporation and
|
||||
* Copyright (C) 1999-2006 Alan Liu ,International Business Machines Corporation and
|
||||
* others. All Rights Reserved.
|
||||
**************************************************************************************
|
||||
* Date Name Description
|
||||
|
|
@ -68,6 +68,7 @@ UnicodeSetTest::runIndexedTest(int32_t index, UBool exec,
|
|||
CASE(17,TestSymbolTable);
|
||||
CASE(18,TestSurrogate);
|
||||
CASE(19,TestPosixClasses);
|
||||
CASE(20,TestIteration);
|
||||
default: name = ""; break;
|
||||
}
|
||||
}
|
||||
|
|
@ -674,6 +675,87 @@ void UnicodeSetTest::TestAPI() {
|
|||
}
|
||||
}
|
||||
|
||||
void UnicodeSetTest::TestIteration() {
|
||||
UErrorCode ec = U_ZERO_ERROR;
|
||||
int i = 0;
|
||||
int outerLoop;
|
||||
|
||||
// 6 code points, 3 ranges, 2 strings, 8 total elements
|
||||
// Iteration will access them in sorted order - a, b, c, y, z, U0001abcd, "str1", "str2"
|
||||
UnicodeSet set("[zabyc\\U0001abcd{str1}{str2}]", ec);
|
||||
TEST_ASSERT_SUCCESS(ec);
|
||||
UnicodeSetIterator it(set);
|
||||
|
||||
for (outerLoop=0; outerLoop<3; outerLoop++) {
|
||||
// Run the test multiple times, to check that iterator.reset() is working.
|
||||
for (i=0; i<10; i++) {
|
||||
UBool nextv = it.next();
|
||||
UBool isString = it.isString();
|
||||
int32_t codePoint = it.getCodepoint();
|
||||
int32_t codePointEnd = it.getCodepointEnd();
|
||||
UnicodeString s = it.getString();
|
||||
switch (i) {
|
||||
case 0:
|
||||
TEST_ASSERT(nextv == TRUE);
|
||||
TEST_ASSERT(isString == FALSE);
|
||||
TEST_ASSERT(codePoint==0x61);
|
||||
TEST_ASSERT(s == "a");
|
||||
break;
|
||||
case 1:
|
||||
TEST_ASSERT(nextv == TRUE);
|
||||
TEST_ASSERT(isString == FALSE);
|
||||
TEST_ASSERT(codePoint==0x62);
|
||||
TEST_ASSERT(s == "b");
|
||||
break;
|
||||
case 2:
|
||||
TEST_ASSERT(nextv == TRUE);
|
||||
TEST_ASSERT(isString == FALSE);
|
||||
TEST_ASSERT(codePoint==0x63);
|
||||
TEST_ASSERT(s == "c");
|
||||
break;
|
||||
case 3:
|
||||
TEST_ASSERT(nextv == TRUE);
|
||||
TEST_ASSERT(isString == FALSE);
|
||||
TEST_ASSERT(codePoint==0x79);
|
||||
TEST_ASSERT(s == "y");
|
||||
break;
|
||||
case 4:
|
||||
TEST_ASSERT(nextv == TRUE);
|
||||
TEST_ASSERT(isString == FALSE);
|
||||
TEST_ASSERT(codePoint==0x7a);
|
||||
TEST_ASSERT(s == "z");
|
||||
break;
|
||||
case 5:
|
||||
TEST_ASSERT(nextv == TRUE);
|
||||
TEST_ASSERT(isString == FALSE);
|
||||
TEST_ASSERT(codePoint==0x1abcd);
|
||||
TEST_ASSERT(s == UnicodeString((UChar32)0x1abcd));
|
||||
break;
|
||||
case 6:
|
||||
TEST_ASSERT(nextv == TRUE);
|
||||
TEST_ASSERT(isString == TRUE);
|
||||
TEST_ASSERT(s == "str1");
|
||||
break;
|
||||
case 7:
|
||||
TEST_ASSERT(nextv == TRUE);
|
||||
TEST_ASSERT(isString == TRUE);
|
||||
TEST_ASSERT(s == "str2");
|
||||
break;
|
||||
case 8:
|
||||
TEST_ASSERT(nextv == FALSE);
|
||||
break;
|
||||
case 9:
|
||||
TEST_ASSERT(nextv == FALSE);
|
||||
break;
|
||||
}
|
||||
}
|
||||
it.reset(); // prepare to run the iteration again.
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
|
||||
|
||||
void UnicodeSetTest::TestStrings() {
|
||||
UErrorCode ec = U_ZERO_ERROR;
|
||||
|
||||
|
|
|
|||
|
|
@ -1,7 +1,7 @@
|
|||
|
||||
/********************************************************************
|
||||
* COPYRIGHT:
|
||||
* Copyright (c) 1997-2005, International Business Machines Corporation and
|
||||
* Copyright (c) 1997-2006, International Business Machines Corporation and
|
||||
* others. All Rights Reserved.
|
||||
********************************************************************
|
||||
**********************************************************************
|
||||
|
|
@ -47,6 +47,8 @@ private:
|
|||
|
||||
void TestAPI(void);
|
||||
|
||||
void TestIteration(void);
|
||||
|
||||
void TestStrings(void);
|
||||
|
||||
void TestScriptSet(void);
|
||||
|
|
|
|||
Loading…
Add table
Reference in a new issue