infernap12/jdk
1
0
Fork 0
mirror of https://github.com/openjdk/jdk.git synced 2026-03-15 18:33:41 +00:00
Code Issues Packages Projects Releases Wiki Activity

8302590: Add String.indexOf(int ch, int fromIndex, int toIndex)

Browse Source 
Reviewed-by: rriggs, alanb
This commit is contained in:
Raffaello Giulietti 2023-03-03 20:51:13 +00:00
parent cd4b88d0d2
commit 5b2e2e4695
4 changed files with 295 additions and 17 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

63
src/java.base/share/classes/java/lang/String.java
View File

@ -2439,10 +2439,69 @@ public final class String
* character sequence represented by this object that is greater
* than or equal to {@code fromIndex}, or {@code -1}
* if the character does not occur.
*
* @apiNote
* Unlike {@link #substring(int)}, for example, this method does not throw
* an exception when {@code fromIndex} is outside the valid range.
* Rather, it returns -1 when {@code fromIndex} is larger than the length of
* the string.
* This result is, by itself, indistinguishable from a genuine absence of
* {@code ch} in the string.
* If stricter behavior is needed, {@link #indexOf(int, int, int)}
* should be considered instead.
* On a {@link String} {@code s}, for example,
* {@code s.indexOf(ch, fromIndex, s.length())} would throw if
* {@code fromIndex} were larger than the string length, or were negative.
*/
public int indexOf(int ch, int fromIndex) {
return isLatin1() ? StringLatin1.indexOf(value, ch, fromIndex)
: StringUTF16.indexOf(value, ch, fromIndex);
return isLatin1() ? StringLatin1.indexOf(value, ch, fromIndex, length())
: StringUTF16.indexOf(value, ch, fromIndex, length());
}
/**
* Returns the index within this string of the first occurrence of the
* specified character, starting the search at {@code beginIndex} and
* stopping before {@code endIndex}.
*
* <p>If a character with value {@code ch} occurs in the
* character sequence represented by this {@code String}
* object at an index no smaller than {@code beginIndex} but smaller than
* {@code endIndex}, then
* the index of the first such occurrence is returned. For values
* of {@code ch} in the range from 0 to 0xFFFF (inclusive),
* this is the smallest value <i>k</i> such that:
* <blockquote><pre>
* (this.charAt(<i>k</i>) == ch) &amp;&amp; (beginIndex &lt;= <i>k</i> &lt; endIndex)
* </pre></blockquote>
* is true. For other values of {@code ch}, it is the
* smallest value <i>k</i> such that:
* <blockquote><pre>
* (this.codePointAt(<i>k</i>) == ch) &amp;&amp; (beginIndex &lt;= <i>k</i> &lt; endIndex)
* </pre></blockquote>
* is true. In either case, if no such character occurs in this
* string at or after position {@code beginIndex} and before position
* {@code endIndex}, then {@code -1} is returned.
*
* <p>All indices are specified in {@code char} values
* (Unicode code units).
*
* @param ch a character (Unicode code point).
* @param beginIndex the index to start the search from (included).
* @param endIndex the index to stop the search at (excluded).
* @return the index of the first occurrence of the character in the
* character sequence represented by this object that is greater
* than or equal to {@code beginIndex} and less than {@code endIndex},
* or {@code -1} if the character does not occur.
* @throws StringIndexOutOfBoundsException if {@code beginIndex}
* is negative, or {@code endIndex} is larger than the length of
* this {@code String} object, or {@code beginIndex} is larger than
* {@code endIndex}.
* @since 21
*/
public int indexOf(int ch, int beginIndex, int endIndex) {
checkBoundsBeginEnd(beginIndex, endIndex, length());
return isLatin1() ? StringLatin1.indexOf(value, ch, beginIndex, endIndex)
: StringUTF16.indexOf(value, ch, beginIndex, endIndex);
}
/**

12
src/java.base/share/classes/java/lang/StringLatin1.java
View File

@ -192,18 +192,16 @@ final class StringLatin1 {
};
}
public static int indexOf(byte[] value, int ch, int fromIndex) {
public static int indexOf(byte[] value, int ch, int fromIndex, int toIndex) {
if (!canEncode(ch)) {
return -1;
}
int max = value.length;
if (fromIndex < 0) {
fromIndex = 0;
} else if (fromIndex >= max) {
// Note: fromIndex might be near -1>>>1.
fromIndex = Math.max(fromIndex, 0);
toIndex = Math.min(toIndex, value.length);
if (fromIndex >= toIndex) {
return -1;
}
return indexOfChar(value, ch, fromIndex, max);
return indexOfChar(value, ch, fromIndex, toIndex);
}
@IntrinsicCandidate

14
src/java.base/share/classes/java/lang/StringUTF16.java
View File

@ -419,20 +419,18 @@ final class StringUTF16 {
};
}
public static int indexOf(byte[] value, int ch, int fromIndex) {
int max = value.length >> 1;
if (fromIndex < 0) {
fromIndex = 0;
} else if (fromIndex >= max) {
// Note: fromIndex might be near -1>>>1.
public static int indexOf(byte[] value, int ch, int fromIndex, int toIndex) {
fromIndex = Math.max(fromIndex, 0);
toIndex = Math.min(toIndex, value.length >> 1);
if (fromIndex >= toIndex) {
return -1;
}
if (ch < Character.MIN_SUPPLEMENTARY_CODE_POINT) {
// handle most cases here (ch is a BMP code point or a
// negative value (invalid code point))
return indexOfChar(value, ch, fromIndex, max);
return indexOfChar(value, ch, fromIndex, toIndex);
} else {
return indexOfSupplementary(value, ch, fromIndex, max);
return indexOfSupplementary(value, ch, fromIndex, toIndex);
}
}

223
test/jdk/java/lang/String/IndexOfBeginEnd.java Normal file
View File

@ -0,0 +1,223 @@
/*
* Copyright (c) 2023, Oracle and/or its affiliates. All rights reserved.
* DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
*
* This code is free software; you can redistribute it and/or modify it
* under the terms of the GNU General Public License version 2 only, as
* published by the Free Software Foundation.
*
* This code is distributed in the hope that it will be useful, but WITHOUT
* ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
* FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
* version 2 for more details (a copy is included in the LICENSE file that
* accompanied this code).
*
* You should have received a copy of the GNU General Public License version
* 2 along with this work; if not, write to the Free Software Foundation,
* Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA.
*
* Please contact Oracle, 500 Oracle Parkway, Redwood Shores, CA 94065 USA
* or visit www.oracle.com if you need additional information or have any
* questions.
*/
import org.testng.annotations.DataProvider;
import org.testng.annotations.Test;
import static org.testng.Assert.assertEquals;
import static org.testng.Assert.assertThrows;
/*
* @test
* @bug 8302590
* @summary This one is for String.indexOf(int,int,int).
* @run testng IndexOfBeginEnd
*/
public class IndexOfBeginEnd {
private static final String STRING_EMPTY = "";
private static final String STRING_L1 = "A";
private static final String STRING_L2 = "AB";
private static final String STRING_L4 = "ABCD";
private static final String STRING_LLONG = "ABCDEFGH";
private static final String STRING_U1 = "\uFF21";
private static final String STRING_U2 = "\uFF21\uFF22";
private static final String STRING_LDUPLICATE = "ABABABABAB";
private static final String STRING_M11 = "A\uFF21";
private static final String STRING_M12 = "\uFF21A";
private static final String STRING_UDUPLICATE = "\uFF21\uFF22\uFF21\uFF22\uFF21\uFF22\uFF21\uFF22\uFF21\uFF22";
private static final String STRING_SUPPLEMENTARY = "\uD801\uDC00\uD801\uDC01\uFF21A";
private static final String STRING_MDUPLICATE1 = "\uFF21A\uFF21A\uFF21A\uFF21A\uFF21A";
private static final String STRING_MDUPLICATE2 = "A\uFF21A\uFF21A\uFF21A\uFF21A\uFF21";
@DataProvider
public Object[][] results() {
return new Object[][] {
new Object[] { STRING_EMPTY, (int) 'Z', 0, 0, -1 },
new Object[] { STRING_L1, (int) 'A', 0, 1, 0 },
new Object[] { STRING_L1, (int) 'A', 1, 1, -1 },
new Object[] { STRING_L1, (int) 'Z', 0, 1, -1 },
new Object[] { STRING_L2, (int) 'A', 0, 2, 0 },
new Object[] { STRING_L2, (int) 'A', 0, 1, 0 },
new Object[] { STRING_L2, (int) 'A', 1, 1, -1 },
new Object[] { STRING_L2, (int) 'A', 1, 2, -1 },
new Object[] { STRING_L2, (int) 'B', 0, 2, 1 },
new Object[] { STRING_L2, (int) 'B', 0, 1, -1 },
new Object[] { STRING_L2, (int) 'B', 1, 1, -1 },
new Object[] { STRING_L2, (int) 'B', 1, 2, 1 },
new Object[] { STRING_L2, (int) 'B', 2, 2, -1 },
new Object[] { STRING_L2, (int) 'Z', 0, 2, -1 },
new Object[] { STRING_L4, (int) 'A', 0, 4, 0 },
new Object[] { STRING_L4, (int) 'A', 0, 1, 0 },
new Object[] { STRING_L4, (int) 'A', 1, 4, -1 },
new Object[] { STRING_L4, (int) 'D', 0, 4, 3 },
new Object[] { STRING_L4, (int) 'D', 0, 3, -1 },
new Object[] { STRING_L4, (int) 'D', 3, 4, 3 },
new Object[] { STRING_L4, (int) 'D', 4, 4, -1 },
new Object[] { STRING_L4, (int) 'Z', 0, 4, -1 },
new Object[] { STRING_LLONG, (int) 'A', 0, 8, 0 },
new Object[] { STRING_LLONG, (int) 'A', 0, 1, 0 },
new Object[] { STRING_LLONG, (int) 'A', 1, 1, -1 },
new Object[] { STRING_LLONG, (int) 'A', 1, 8, -1 },
new Object[] { STRING_LLONG, (int) 'H', 0, 8, 7 },
new Object[] { STRING_LLONG, (int) 'H', 0, 7, -1 },
new Object[] { STRING_LLONG, (int) 'H', 7, 8, 7 },
new Object[] { STRING_LLONG, (int) 'H', 8, 8, -1 },
new Object[] { STRING_LLONG, (int) 'Z', 0, 8, -1 },
new Object[] { STRING_U1, (int) '\uFF21', 0, 1, 0 },
new Object[] { STRING_U1, (int) '\uFF21', 0, 0, -1 },
new Object[] { STRING_U1, (int) '\uFF21', 1, 1, -1 },
new Object[] { STRING_U1, (int) 'A', 0, 1, -1 },
new Object[] { STRING_U2, (int) '\uFF21', 0, 2, 0 },
new Object[] { STRING_U2, (int) '\uFF21', 0, 1, 0 },
new Object[] { STRING_U2, (int) '\uFF21', 1, 2, -1 },
new Object[] { STRING_U2, (int) '\uFF22', 0, 2, 1 },
new Object[] { STRING_U2, (int) '\uFF22', 0, 1, -1 },
new Object[] { STRING_U2, (int) '\uFF22', 1, 2, 1 },
new Object[] { STRING_U2, (int) '\uFF22', 2, 2, -1 },
new Object[] { STRING_U2, (int) '\uFF3A', 0, 2, -1 },
new Object[] { STRING_LDUPLICATE, (int) 'A', 0, 10, 0 },
new Object[] { STRING_LDUPLICATE, (int) 'A', 1, 3, 2 },
new Object[] { STRING_LDUPLICATE, (int) 'A', 3, 3, -1 },
new Object[] { STRING_LDUPLICATE, (int) 'A', 3, 5, 4 },
new Object[] { STRING_LDUPLICATE, (int) 'B', 0, 10, 1 },
new Object[] { STRING_LDUPLICATE, (int) 'B', 2, 4, 3 },
new Object[] { STRING_LDUPLICATE, (int) 'B', 4, 6, 5 },
new Object[] { STRING_M11, (int) 'A', 0, 2, 0 },
new Object[] { STRING_M11, (int) 'A', 0, 1, 0 },
new Object[] { STRING_M11, (int) 'A', 1, 2, -1 },
new Object[] { STRING_M11, (int) 'A', 2, 2, -1 },
new Object[] { STRING_M11, (int) '\uFF21', 0, 2, 1 },
new Object[] { STRING_M11, (int) '\uFF21', 0, 1, -1 },
new Object[] { STRING_M11, (int) '\uFF21', 1, 2, 1 },
new Object[] { STRING_M11, (int) '\uFF21', 2, 2, -1 },
new Object[] { STRING_M11, (int) '\uFF3A', 0, 2, -1 },
new Object[] { STRING_M12, (int) '\uFF21', 0, 2, 0 },
new Object[] { STRING_M12, (int) '\uFF21', 0, 1, 0 },
new Object[] { STRING_M12, (int) '\uFF21', 1, 2, -1 },
new Object[] { STRING_M12, (int) '\uFF21', 2, 2, -1 },
new Object[] { STRING_M12, (int) 'A', 0, 2, 1 },
new Object[] { STRING_M12, (int) 'A', 0, 1, -1 },
new Object[] { STRING_M12, (int) 'A', 1, 2, 1 },
new Object[] { STRING_M12, (int) 'A', 2, 2, -1 },
new Object[] { STRING_M12, (int) '\uFF3A', 0, 2, -1 },
new Object[] { STRING_UDUPLICATE, (int) '\uFF21', 0, 10, 0 },
new Object[] { STRING_UDUPLICATE, (int) '\uFF21', 1, 3, 2 },
new Object[] { STRING_UDUPLICATE, (int) '\uFF21', 3, 3, -1 },
new Object[] { STRING_UDUPLICATE, (int) '\uFF21', 3, 5, 4 },
new Object[] { STRING_UDUPLICATE, (int) '\uFF22', 0, 10, 1 },
new Object[] { STRING_UDUPLICATE, (int) '\uFF22', 2, 4, 3 },
new Object[] { STRING_UDUPLICATE, (int) '\uFF22', 4, 6, 5 },
new Object[] { STRING_SUPPLEMENTARY, 'A', 0, 6, 5 },
new Object[] { STRING_SUPPLEMENTARY, 'A', 2, 6, 5 },
new Object[] { STRING_SUPPLEMENTARY, 'A', 2, 4, -1 },
new Object[] { STRING_SUPPLEMENTARY, 'A', 4, 4, -1 },
new Object[] { STRING_SUPPLEMENTARY, '\uFF21', 0, 6, 4 },
new Object[] { STRING_SUPPLEMENTARY, '\uFF21', 2, 2, -1 },
new Object[] { STRING_SUPPLEMENTARY, '\uFF21', 2, 6, 4 },
new Object[] { STRING_SUPPLEMENTARY, '\uFF21', 2, 4, -1 },
new Object[] { STRING_SUPPLEMENTARY,
Character.toCodePoint('\uD801', '\uDC00'), 0, 6, 0 },
new Object[] { STRING_SUPPLEMENTARY,
Character.toCodePoint('\uD801', '\uDC00'), 0, 3, 0 },
new Object[] { STRING_SUPPLEMENTARY,
Character.toCodePoint('\uD801', '\uDC00'), 0, 1, -1 },
new Object[] { STRING_SUPPLEMENTARY,
Character.toCodePoint('\uD801', '\uDC00'), 1, 4, -1 },
new Object[] { STRING_SUPPLEMENTARY,
Character.toCodePoint('\uD801', '\uDC01'), 0, 6, 2 },
new Object[] { STRING_SUPPLEMENTARY,
Character.toCodePoint('\uD801', '\uDC01'), 2, 2, -1 },
new Object[] { STRING_SUPPLEMENTARY,
Character.toCodePoint('\uD801', '\uDC01'), 2, 5, 2 },
new Object[] { STRING_SUPPLEMENTARY,
Character.toCodePoint('\uD801', '\uDC01'), 2, 3, -1 },
new Object[] { STRING_SUPPLEMENTARY,
Character.toCodePoint('\uD801', '\uDC01'), 3, 6, -1 },
};
}
@DataProvider
public Object[][] exceptions() {
return new Object[][]{
new Object[]{STRING_LDUPLICATE, 'A', -1, 0},
new Object[]{STRING_LDUPLICATE, 'A', 0, 100},
new Object[]{STRING_LDUPLICATE, 'A', -1, 100},
new Object[]{STRING_LDUPLICATE, 'A', 3, 1},
new Object[]{STRING_UDUPLICATE, 'A', -1, 0},
new Object[]{STRING_UDUPLICATE, 'A', 0, 100},
new Object[]{STRING_UDUPLICATE, 'A', -1, 100},
new Object[]{STRING_UDUPLICATE, 'A', 3, 1},
new Object[]{STRING_MDUPLICATE1, 'A', -1, 0},
new Object[]{STRING_MDUPLICATE1, 'A', 0, 100},
new Object[]{STRING_MDUPLICATE1, 'A', -1, 100},
new Object[]{STRING_MDUPLICATE1, 'A', 3, 1},
new Object[]{STRING_MDUPLICATE2, 'A', -1, 0},
new Object[]{STRING_MDUPLICATE2, 'A', 0, 100},
new Object[]{STRING_MDUPLICATE2, 'A', -1, 100},
new Object[]{STRING_MDUPLICATE2, 'A', 3, 1},
};
}
@Test(dataProvider = "results")
public void testIndexOf(String str, int ch, int from, int to, int expected) {
assertEquals(str.indexOf(ch, from, to), expected,
String.format("testing String(%s).indexOf(%d,%d,%d)",
escapeNonASCIIs(str), ch, from, to));
}
@Test(dataProvider = "exceptions")
public void testIndexOf(String str, int ch, int from, int to) {
assertThrows(StringIndexOutOfBoundsException.class,
() -> str.indexOf(ch, from, to));
}
private static String escapeNonASCIIs(String s) {
StringBuilder sb = new StringBuilder();
for (int i = 0; i < s.length(); ++i) {
char c = s.charAt(i);
if (c >= 0x100) {
sb.append("\\u").append(Integer.toHexString(c));
} else {
sb.append(c);
}
}
return sb.toString();
}
}