organicmaps/icu
13
Fork 0
mirror of https://github.com/unicode-org/icu.git synced 2025-04-07 22:44:49 +00:00
Code Issues 1 Projects Releases Wiki Activity Actions 2

ICU-12716 Resolved StringEquality issues reported by ErrorProne (Android)

Browse source 
X-SVN-Rev: 39334
This commit is contained in:
Craig Cornelius 2016-09-22 22:49:46 +00:00
parent 6b3edc198e
commit f7e4a8f205
8 changed files with 134 additions and 115 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
icu4j/main/classes/charset/src/com/ibm/icu/charset/CharsetLMBCS.java
View file

@ -506,7 +506,7 @@ class CharsetLMBCS extends CharsetICU {
}
while (LocaleLMBCSGrpMap[index].LocaleID != null) {
if (LocaleLMBCSGrpMap[index].LocaleID == LocaleID) {
if (LocaleLMBCSGrpMap[index].LocaleID.equals(LocaleID)) {
return LocaleLMBCSGrpMap[index].OptGroup;
} else if (LocaleLMBCSGrpMap[index].LocaleID.compareTo(LocaleID) > 0){
break;

5
icu4j/main/classes/collate/src/com/ibm/icu/impl/coll/TailoredSet.java
View file

@ -17,6 +17,7 @@ import java.util.Iterator;
import com.ibm.icu.impl.Normalizer2Impl.Hangul;
import com.ibm.icu.impl.Trie2;
import com.ibm.icu.impl.Utility;
import com.ibm.icu.text.UnicodeSet;
import com.ibm.icu.util.CharsTrie;
import com.ibm.icu.util.CharsTrie.Entry;
@ -258,7 +259,7 @@ public final class TailoredSet {
bp = none;
}
}
if (tp == none && bp == none) {
if (Utility.sameObjects(tp, none) && Utility.sameObjects(bp, none)) {
break;
}
int cmp = tp.compareTo(bp);
@ -315,7 +316,7 @@ public final class TailoredSet {
bs = none;
}
}
if (ts == none && bs == none) {
if (Utility.sameObjects(ts, none) && Utility.sameObjects(bs, none)) {
break;
}
int cmp = ts.compareTo(bs);

9
icu4j/main/classes/core/src/com/ibm/icu/impl/Utility.java
View file

@ -172,6 +172,15 @@ public final class Utility {
return true;
}
/**
* Trivial reference equality.
* This method should help document that we really want == not equals(),
* and to have a single place to suppress warnings from static analysis tools.
*/
public static final boolean sameObjects(Object a, Object b) {
return a == b;
}
/**
* Convenience utility. Does null checks on objects, then calls equals.
*/

6
icu4j/main/classes/core/src/com/ibm/icu/impl/locale/AsciiUtil.java
View file

@ -8,9 +8,11 @@
*/
package com.ibm.icu.impl.locale;
import com.ibm.icu.impl.Utility;
public final class AsciiUtil {
public static boolean caseIgnoreMatch(String s1, String s2) {
if (s1 == s2) {
if (Utility.sameObjects(s1, s2)) {
return true;
}
int len = s1.length();
@ -30,7 +32,7 @@ public final class AsciiUtil {
}
public static int caseIgnoreCompare(String s1, String s2) {
if (s1 == s2) {
if (Utility.sameObjects(s1, s2)) {
return 0;
}
return AsciiUtil.toLowerString(s1).compareTo(AsciiUtil.toLowerString(s2));

42
icu4j/main/classes/core/src/com/ibm/icu/text/CurrencyMetaInfo.java
View file

@ -14,19 +14,20 @@ import java.util.Date;
import java.util.List;
import com.ibm.icu.impl.Grego;
import com.ibm.icu.impl.Utility;
import com.ibm.icu.util.Currency.CurrencyUsage;
/**
* Provides information about currencies that is not specific to a locale.
*
*
* A note about currency dates. The CLDR data provides data to the day,
* inclusive. The date information used by CurrencyInfo and CurrencyFilter
* is represented by milliseconds, which is overly precise. These times are
* is represented by milliseconds, which is overly precise. These times are
* in GMT, so queries involving dates should use GMT times, but more generally
* you should avoid relying on time of day in queries.
*
*
* This class is not intended for public subclassing.
*
*
* @stable ICU 4.4
*/
public class CurrencyMetaInfo {
@ -43,7 +44,7 @@ public class CurrencyMetaInfo {
}
/**
* Returns the unique instance of the currency meta info, or null if
* Returns the unique instance of the currency meta info, or null if
* noSubstitute is true and there is no data to support this API.
* @param noSubstitute true if no substitute data should be used
* @return the meta info, or null
@ -101,7 +102,7 @@ public class CurrencyMetaInfo {
* @stable ICU 4.4
*/
public final long to;
/**
* true if we are filtering only for currencies used as legal tender.
* @internal
@ -116,7 +117,7 @@ public class CurrencyMetaInfo {
this.from = from;
this.to = to;
this.tenderOnly = tenderOnly;
}
private static final CurrencyFilter ALL = new CurrencyFilter(
@ -187,7 +188,7 @@ public class CurrencyMetaInfo {
public static CurrencyFilter onDateRange(Date from, Date to) {
return ALL.withDateRange(from, to);
}
/**
* Returns a filter that accepts all currencies in use on the given date.
* @param date the date as milliseconds after Jan 1, 1970
@ -210,7 +211,7 @@ public class CurrencyMetaInfo {
public static CurrencyFilter onDateRange(long from, long to) {
return ALL.withDateRange(from, to);
}
/**
* Returns a CurrencyFilter for finding currencies that were either once used,
* are used, or will be used as tender.
@ -268,7 +269,7 @@ public class CurrencyMetaInfo {
long toLong = to == null ? Long.MAX_VALUE : to.getTime();
return new CurrencyFilter(this.region, this.currency, fromLong, toLong, this.tenderOnly);
}
/**
* Returns a copy of this filter that accepts all currencies in use on
* the given date.
@ -292,7 +293,7 @@ public class CurrencyMetaInfo {
public CurrencyFilter withDateRange(long from, long to) {
return new CurrencyFilter(this.region, this.currency, from, to, this.tenderOnly);
}
/**
* Returns a copy of this filter that filters for currencies that were
* either once used, are used, or will be used as tender.
@ -359,7 +360,8 @@ public class CurrencyMetaInfo {
}
private static boolean equals(String lhs, String rhs) {
return lhs == rhs || (lhs != null && lhs.equals(rhs));
return (Utility.sameObjects(lhs, rhs) ||
(lhs != null && lhs.equals(rhs)));
}
}
@ -422,8 +424,8 @@ public class CurrencyMetaInfo {
public final String code;
/**
* Date on which the currency was first officially used in the region.
* This is midnight at the start of the first day on which the currency was used, GMT.
* Date on which the currency was first officially used in the region.
* This is midnight at the start of the first day on which the currency was used, GMT.
* If there is no date, this is Long.MIN_VALUE;
* @stable ICU 4.4
*/
@ -433,7 +435,7 @@ public class CurrencyMetaInfo {
* Date at which the currency stopped being officially used in the region.
* This is one millisecond before midnight at the end of the last day on which the currency was used, GMT.
* If there is no date, this is Long.MAX_VALUE.
*
*
* @stable ICU 4.4
*/
public final long to;
@ -445,8 +447,8 @@ public class CurrencyMetaInfo {
* @stable ICU 49
*/
public final int priority;
private final boolean tender;
/**
@ -456,10 +458,10 @@ public class CurrencyMetaInfo {
public CurrencyInfo(String region, String code, long from, long to, int priority) {
this(region, code, from, to, priority, true);
}
/**
* Constructs a currency info.
*
*
* @internal
* @deprecated This API is ICU internal only.
*/
@ -482,7 +484,7 @@ public class CurrencyMetaInfo {
public String toString() {
return debugString(this);
}
/**
* Determine whether or not this currency was once used, is used,
* or will be used as tender in this region.

3
icu4j/main/classes/core/src/com/ibm/icu/text/SpoofChecker.java
View file

@ -33,6 +33,7 @@ import java.util.regex.Pattern;
import com.ibm.icu.impl.ICUBinary;
import com.ibm.icu.impl.ICUBinary.Authenticate;
import com.ibm.icu.impl.Utility;
import com.ibm.icu.lang.UCharacter;
import com.ibm.icu.lang.UCharacterCategory;
import com.ibm.icu.lang.UProperty;
@ -1792,7 +1793,7 @@ public class SpoofChecker {
return false;
if (!Arrays.equals(fCFUValues, otherData.fCFUValues))
return false;
if (fCFUStrings != otherData.fCFUStrings && fCFUStrings != null
if (!Utility.sameObjects(fCFUStrings, otherData.fCFUStrings) && fCFUStrings != null
&& !fCFUStrings.equals(otherData.fCFUStrings))
return false;
return true;

177
icu4j/main/classes/core/src/com/ibm/icu/text/UTF16.java
View file

@ -9,6 +9,8 @@
package com.ibm.icu.text;
import com.ibm.icu.impl.Utility;
/**
* <p>
* Standalone utility class providing UTF16 character conversions and indexing conversions.
@ -23,27 +25,27 @@ package com.ibm.icu.text;
* <strong>Examples:</strong>
* <p>
* The following examples illustrate use of some of these methods.
*
*
* <pre>
* // iteration forwards: Original
* for (int i = 0; i &lt; s.length(); ++i) {
* char ch = s.charAt(i);
* doSomethingWith(ch);
* }
*
*
* // iteration forwards: Changes for UTF-32
* int ch;
* for (int i = 0; i &lt; s.length(); i += UTF16.getCharCount(ch)) {
* ch = UTF16.charAt(s, i);
* doSomethingWith(ch);
* }
*
*
* // iteration backwards: Original
* for (int i = s.length() - 1; i &gt;= 0; --i) {
* char ch = s.charAt(i);
* doSomethingWith(ch);
* }
*
*
* // iteration backwards: Changes for UTF-32
* int ch;
* for (int i = s.length() - 1; i &gt; 0; i -= UTF16.getCharCount(ch)) {
@ -51,7 +53,7 @@ package com.ibm.icu.text;
* doSomethingWith(ch);
* }
* </pre>
*
*
* <strong>Notes:</strong>
* <ul>
* <li> <strong>Naming:</strong> For clarity, High and Low surrogates are called <code>Lead</code>
@ -75,7 +77,7 @@ package com.ibm.icu.text;
* compiler doesn't fold static final methods. Since surrogate pairs will form an exceeding small
* percentage of all the text in the world, the singleton case should always be optimized for. </li>
* </ul>
*
*
* @author Mark Davis, with help from Markus Scherer
* @stable ICU 2.1
*/
@ -87,7 +89,7 @@ public final class UTF16 {
* Value returned in {@link #bounds(String, int) bounds()}.
* These values are chosen specifically so that it actually represents the position of the
* character [offset16 - (value &gt;&gt; 2), offset16 + (value &amp; 3)]
*
*
* @stable ICU 2.1
*/
public static final int SINGLE_CHAR_BOUNDARY = 1, LEAD_SURROGATE_BOUNDARY = 2,
@ -95,63 +97,63 @@ public final class UTF16 {
/**
* The lowest Unicode code point value.
*
*
* @stable ICU 2.1
*/
public static final int CODEPOINT_MIN_VALUE = 0;
/**
* The highest Unicode code point value (scalar value) according to the Unicode Standard.
*
*
* @stable ICU 2.1
*/
public static final int CODEPOINT_MAX_VALUE = 0x10ffff;
/**
* The minimum value for Supplementary code points
*
*
* @stable ICU 2.1
*/
public static final int SUPPLEMENTARY_MIN_VALUE = 0x10000;
/**
* Lead surrogate minimum value
*
*
* @stable ICU 2.1
*/
public static final int LEAD_SURROGATE_MIN_VALUE = 0xD800;
/**
* Trail surrogate minimum value
*
*
* @stable ICU 2.1
*/
public static final int TRAIL_SURROGATE_MIN_VALUE = 0xDC00;
/**
* Lead surrogate maximum value
*
*
* @stable ICU 2.1
*/
public static final int LEAD_SURROGATE_MAX_VALUE = 0xDBFF;
/**
* Trail surrogate maximum value
*
*
* @stable ICU 2.1
*/
public static final int TRAIL_SURROGATE_MAX_VALUE = 0xDFFF;
/**
* Surrogate minimum value
*
*
* @stable ICU 2.1
*/
public static final int SURROGATE_MIN_VALUE = LEAD_SURROGATE_MIN_VALUE;
/**
* Maximum surrogate value
*
*
* @stable ICU 2.1
*/
public static final int SURROGATE_MAX_VALUE = TRAIL_SURROGATE_MAX_VALUE;
@ -206,7 +208,7 @@ public final class UTF16 {
* on the return value. If the char retrieved is part of a surrogate pair, its supplementary
* character will be returned. If a complete supplementary character is not found the incomplete
* character will be returned
*
*
* @param source Array of UTF-16 chars
* @param offset16 UTF-16 offset to the start of the character.
* @return UTF-32 value for the UTF-32 value that contains the char at offset16. The boundaries
@ -260,7 +262,7 @@ public final class UTF16 {
* on the return value. If the char retrieved is part of a surrogate pair, its supplementary
* character will be returned. If a complete supplementary character is not found the incomplete
* character will be returned
*
*
* @param source Array of UTF-16 chars
* @param offset16 UTF-16 offset to the start of the character.
* @return UTF-32 value for the UTF-32 value that contains the char at offset16. The boundaries
@ -316,7 +318,7 @@ public final class UTF16 {
* on the return value. If the char retrieved is part of a surrogate pair, its supplementary
* character will be returned. If a complete supplementary character is not found the incomplete
* character will be returned
*
*
* @param source UTF-16 chars string buffer
* @param offset16 UTF-16 offset to the start of the character.
* @return UTF-32 value for the UTF-32 value that contains the char at offset16. The boundaries
@ -366,7 +368,7 @@ public final class UTF16 {
* on the return value. If the char retrieved is part of a surrogate pair, its supplementary
* character will be returned. If a complete supplementary character is not found the incomplete
* character will be returned
*
*
* @param source Array of UTF-16 chars
* @param start Offset to substring in the source array for analyzing
* @param limit Offset to substring in the source array for analyzing
@ -419,7 +421,7 @@ public final class UTF16 {
* on the return value. If the char retrieved is part of a surrogate pair, its supplementary
* character will be returned. If a complete supplementary character is not found the incomplete
* character will be returned
*
*
* @param source UTF-16 chars string buffer
* @param offset16 UTF-16 offset to the start of the character.
* @return UTF-32 value for the UTF-32 value that contains the char at offset16. The boundaries
@ -465,7 +467,7 @@ public final class UTF16 {
* Determines how many chars this char32 requires. If a validity check is required, use <code>
* <a href="../lang/UCharacter.html#isLegal(char)">isLegal()</a></code>
* on char32 before calling.
*
*
* @param char32 The input codepoint.
* @return 2 if is in supplementary space, otherwise 1.
* @stable ICU 2.1
@ -479,7 +481,7 @@ public final class UTF16 {
/**
* Returns the type of the boundaries around the char at offset16. Used for random access.
*
*
* @param source Text to analyse
* @param offset16 UTF-16 offset
* @return
@ -515,7 +517,7 @@ public final class UTF16 {
/**
* Returns the type of the boundaries around the char at offset16. Used for random access.
*
*
* @param source String buffer to analyse
* @param offset16 UTF16 offset
* @return
@ -553,7 +555,7 @@ public final class UTF16 {
* Returns the type of the boundaries around the char at offset16. Used for random access. Note
* that the boundaries are determined with respect to the subarray, hence the char array
* {0xD800, 0xDC00} has the result SINGLE_CHAR_BOUNDARY for start = offset16 = 0 and limit = 1.
*
*
* @param source Char array to analyse
* @param start Offset to substring in the source array for analyzing
* @param limit Offset to substring in the source array for analyzing
@ -595,7 +597,7 @@ public final class UTF16 {
/**
* Determines whether the code value is a surrogate.
*
*
* @param char16 The input character.
* @return true If the input character is a surrogate.
* @stable ICU 2.1
@ -606,7 +608,7 @@ public final class UTF16 {
/**
* Determines whether the character is a trail surrogate.
*
*
* @param char16 The input character.
* @return true If the input character is a trail surrogate.
* @stable ICU 2.1
@ -617,7 +619,7 @@ public final class UTF16 {
/**
* Determines whether the character is a lead surrogate.
*
*
* @param char16 The input character.
* @return true If the input character is a lead surrogate
* @stable ICU 2.1
@ -630,7 +632,7 @@ public final class UTF16 {
* Returns the lead surrogate. If a validity check is required, use
* <code><a href="../lang/UCharacter.html#isLegal(char)">isLegal()</a></code> on char32
* before calling.
*
*
* @param char32 The input character.
* @return lead surrogate if the getCharCount(ch) is 2; <br>
* and 0 otherwise (note: 0 is not a valid lead surrogate).
@ -647,7 +649,7 @@ public final class UTF16 {
* Returns the trail surrogate. If a validity check is required, use
* <code><a href="../lang/UCharacter.html#isLegal(char)">isLegal()</a></code> on char32
* before calling.
*
*
* @param char32 The input character.
* @return the trail surrogate if the getCharCount(ch) is 2; <br>
* otherwise the character itself
@ -664,7 +666,7 @@ public final class UTF16 {
* Convenience method corresponding to String.valueOf(char). Returns a one or two char string
* containing the UTF-32 value in UTF16 format. If a validity check is required, use
* {@link com.ibm.icu.lang.UCharacter#isLegal(int)} on char32 before calling.
*
*
* @param char32 The input character.
* @return string value of char32 in UTF16 format
* @exception IllegalArgumentException Thrown if char32 is a invalid codepoint.
@ -684,7 +686,7 @@ public final class UTF16 {
* required, use {@link com.ibm.icu.lang.UCharacter#isLegal(int)} on the
* codepoint at offset16 before calling. The result returned will be a newly created String
* obtained by calling source.substring(..) with the appropriate indexes.
*
*
* @param source The input string.
* @param offset16 The UTF16 index to the codepoint in source
* @return string value of char32 in UTF16 format
@ -708,7 +710,7 @@ public final class UTF16 {
* is required, use {@link com.ibm.icu.lang.UCharacter#isLegal(int)} on
* the codepoint at offset16 before calling. The result returned will be a newly created String
* obtained by calling source.substring(..) with the appropriate indexes.
*
*
* @param source The input string buffer.
* @param offset16 The UTF16 index to the codepoint in source
* @return string value of char32 in UTF16 format
@ -734,7 +736,7 @@ public final class UTF16 {
* {@link com.ibm.icu.lang.UCharacter#isLegal(int)} on the codepoint at
* offset16 before calling. The result returned will be a newly created String containing the
* relevant characters.
*
*
* @param source The input char array.
* @param start Start index of the subarray
* @param limit End index of the subarray
@ -755,7 +757,7 @@ public final class UTF16 {
/**
* Returns the UTF-16 offset that corresponds to a UTF-32 offset. Used for random access. See
* the {@link UTF16 class description} for notes on roundtripping.
*
*
* @param source The UTF-16 string
* @param offset32 UTF-32 offset
* @return UTF-16 offset
@ -787,7 +789,7 @@ public final class UTF16 {
/**
* Returns the UTF-16 offset that corresponds to a UTF-32 offset. Used for random access. See
* the {@link UTF16 class description} for notes on roundtripping.
*
*
* @param source The UTF-16 string buffer
* @param offset32 UTF-32 offset
* @return UTF-16 offset
@ -819,7 +821,7 @@ public final class UTF16 {
/**
* Returns the UTF-16 offset that corresponds to a UTF-32 offset. Used for random access. See
* the {@link UTF16 class description} for notes on roundtripping.
*
*
* @param source The UTF-16 char array whose substring is to be analysed
* @param start Offset of the substring to be analysed
* @param limit Offset of the substring to be analysed
@ -858,11 +860,11 @@ public final class UTF16 {
* of the <strong>lead</strong> of the pair is returned. </i>
* <p>
* To find the UTF-32 length of a string, use:
*
*
* <pre>
* len32 = countCodePoint(source, source.length());
* </pre>
*
*
* @param source Text to analyse
* @param offset16 UTF-16 offset &lt; source text length.
* @return UTF-32 offset
@ -909,7 +911,7 @@ public final class UTF16 {
* of the <strong>lead</strong> of the pair is returned. </i>
* <p>
* To find the UTF-32 length of a string, use:
*
*
* <pre>
* len32 = countCodePoint(source);
* </pre>
@ -960,7 +962,7 @@ public final class UTF16 {
* of the <strong>lead</strong> of the pair is returned. </i>
* <p>
* To find the UTF-32 length of a substring, use:
*
*
* <pre>
* len32 = countCodePoint(source, start, limit);
* </pre>
@ -1010,7 +1012,7 @@ public final class UTF16 {
* Append a single UTF-32 value to the end of a StringBuffer. If a validity check is required,
* use {@link com.ibm.icu.lang.UCharacter#isLegal(int)} on char32 before
* calling.
*
*
* @param target The buffer to append to
* @param char32 Value to append.
* @return the updated StringBuffer
@ -1036,7 +1038,7 @@ public final class UTF16 {
/**
* Cover JDK 1.5 APIs. Append the code point to the buffer and return the buffer as a
* convenience.
*
*
* @param target The buffer to append to
* @param cp The code point to append
* @return the updated StringBuffer
@ -1049,7 +1051,7 @@ public final class UTF16 {
/**
* Adds a codepoint to offset16 position of the argument char array.
*
*
* @param target Char array to be append with the new code point
* @param limit UTF16 offset which the codepoint will be appended.
* @param char32 Code point to be appended
@ -1075,7 +1077,7 @@ public final class UTF16 {
/**
* Number of codepoints in a UTF16 String
*
*
* @param source UTF16 string
* @return number of codepoint in string
* @stable ICU 2.1
@ -1089,7 +1091,7 @@ public final class UTF16 {
/**
* Number of codepoints in a UTF16 String buffer
*
*
* @param source UTF16 string buffer
* @return number of codepoint in string
* @stable ICU 2.1
@ -1103,7 +1105,7 @@ public final class UTF16 {
/**
* Number of codepoints in a UTF16 char array substring
*
*
* @param source UTF16 char array
* @param start Offset of the substring
* @param limit Offset of the substring
@ -1121,7 +1123,7 @@ public final class UTF16 {
/**
* Set a code point into a UTF16 position. Adjusts target according if we are replacing a
* non-supplementary codepoint with a supplementary and vice versa.
*
*
* @param target Stringbuffer
* @param offset16 UTF16 position to insert into
* @param char32 Code point
@ -1152,7 +1154,7 @@ public final class UTF16 {
/**
* Set a code point into a UTF16 position in a char array. Adjusts target according if we are
* replacing a non-supplementary codepoint with a supplementary and vice versa.
*
*
* @param target char array
* @param limit numbers of valid chars in target, different from target.length. limit counts the
* number of chars in target that represents a string, not the size of array target.
@ -1218,7 +1220,7 @@ public final class UTF16 {
/**
* Shifts offset16 by the argument number of codepoints
*
*
* @param source string
* @param offset16 UTF16 position to shift
* @param shift32 number of codepoints to shift
@ -1272,7 +1274,7 @@ public final class UTF16 {
/**
* Shifts offset16 by the argument number of codepoints
*
*
* @param source String buffer
* @param offset16 UTF16 position to shift
* @param shift32 Number of codepoints to shift
@ -1326,7 +1328,7 @@ public final class UTF16 {
/**
* Shifts offset16 by the argument number of codepoints within a subarray.
*
*
* @param source Char array
* @param start Position of the subarray to be performed on
* @param limit Position of the subarray to be performed on
@ -1401,7 +1403,7 @@ public final class UTF16 {
* <p>
* The offset argument must be greater than or equal to 0, and less than or equal to the length
* of source.
*
*
* @param target String buffer to insert to
* @param offset16 Offset which char32 will be inserted in
* @param char32 Codepoint to be inserted
@ -1429,7 +1431,7 @@ public final class UTF16 {
* </p>
* <p>
* The offset argument must be greater than or equal to 0, and less than or equal to the limit.
*
*
* @param target Char array to insert to
* @param limit End index of the char array, limit &lt;= target.length
* @param offset16 Offset which char32 will be inserted in
@ -1458,7 +1460,7 @@ public final class UTF16 {
/**
* Removes the codepoint at the specified position in this target (shortening target by 1
* character if the codepoint is a non-supplementary, 2 otherwise).
*
*
* @param target String buffer to remove codepoint from
* @param offset16 Offset which the codepoint will be removed
* @return a reference to target
@ -1483,7 +1485,7 @@ public final class UTF16 {
/**
* Removes the codepoint at the specified position in this target (shortening target by 1
* character if the codepoint is a non-supplementary, 2 otherwise).
*
*
* @param target String buffer to remove codepoint from
* @param limit End index of the char array, limit &lt;= target.length
* @param offset16 Offset which the codepoint will be removed
@ -1523,7 +1525,7 @@ public final class UTF16 {
* </p>
* Note this method is provided as support to jdk 1.3, which does not support supplementary
* characters to its fullest.
*
*
* @param source UTF16 format Unicode string that will be searched
* @param char32 Codepoint to search for
* @return the index of the first occurrence of the codepoint in the argument Unicode string, or
@ -1577,7 +1579,7 @@ public final class UTF16 {
* </p>
* Note this method is provided as support to jdk 1.3, which does not support supplementary
* characters to its fullest.
*
*
* @param source UTF16 format Unicode string that will be searched
* @param str UTF16 format Unicode string to search for
* @return the index of the first occurrence of the codepoint in the argument Unicode string, or
@ -1623,7 +1625,7 @@ public final class UTF16 {
* </p>
* Note this method is provided as support to jdk 1.3, which does not support supplementary
* characters to its fullest.
*
*
* @param source UTF16 format Unicode string that will be searched
* @param char32 Codepoint to search for
* @param fromIndex The index to start the search from.
@ -1679,7 +1681,7 @@ public final class UTF16 {
* </p>
* Note this method is provided as support to jdk 1.3, which does not support supplementary
* characters to its fullest.
*
*
* @param source UTF16 format Unicode string that will be searched
* @param str UTF16 format Unicode string to search for
* @param fromIndex The index to start the search from.
@ -1726,7 +1728,7 @@ public final class UTF16 {
* </p>
* Note this method is provided as support to jdk 1.3, which does not support supplementary
* characters to its fullest.
*
*
* @param source UTF16 format Unicode string that will be searched
* @param char32 Codepoint to search for
* @return the index of the last occurrence of the codepoint in source, or -1 if the codepoint
@ -1780,7 +1782,7 @@ public final class UTF16 {
* </p>
* Note this method is provided as support to jdk 1.3, which does not support supplementary
* characters to its fullest.
*
*
* @param source UTF16 format Unicode string that will be searched
* @param str UTF16 format Unicode string to search for
* @return the index of the last occurrence of the codepoint in source, or -1 if the codepoint
@ -1832,7 +1834,7 @@ public final class UTF16 {
* </p>
* Note this method is provided as support to jdk 1.3, which does not support supplementary
* characters to its fullest.
*
*
* @param source UTF16 format Unicode string that will be searched
* @param char32 Codepoint to search for
* @param fromIndex the index to start the search from. There is no restriction on the value of
@ -1898,7 +1900,7 @@ public final class UTF16 {
* </p>
* Note this method is provided as support to jdk 1.3, which does not support supplementary
* characters to its fullest.
*
*
* @param source UTF16 format Unicode string that will be searched
* @param str UTF16 format Unicode string to search for
* @param fromIndex the index to start the search from. There is no restriction on the value of
@ -1953,7 +1955,7 @@ public final class UTF16 {
* </p>
* Note this method is provided as support to jdk 1.3, which does not support supplementary
* characters to its fullest.
*
*
* @param source UTF16 format Unicode string which the codepoint replacements will be based on.
* @param oldChar32 Non-zero old codepoint to be replaced.
* @param newChar32 The new codepoint to replace oldChar32
@ -2014,7 +2016,7 @@ public final class UTF16 {
* </p>
* Note this method is provided as support to jdk 1.3, which does not support supplementary
* characters to its fullest.
*
*
* @param source UTF16 format Unicode string which the replacements will be based on.
* @param oldStr Non-zero-length string to be replaced.
* @param newStr The new string to replace oldStr
@ -2049,7 +2051,7 @@ public final class UTF16 {
* Examples:<br>
* UTF16.reverse(new StringBuffer( "Supplementary characters \ud800\udc00\ud801\udc01"))<br>
* returns "\ud801\udc01\ud800\udc00 sretcarahc yratnemelppuS".
*
*
* @param source The source StringBuffer that contains UTF16 format Unicode string to be reversed
* @return a modified source with reversed UTF16 format Unicode string.
* @stable ICU 2.6
@ -2080,7 +2082,7 @@ public final class UTF16 {
* certain range, and never needs to count more than 'number + 1' code points. Logically
* equivalent to (countCodePoint(s) &gt; number). A Unicode code point may occupy either one or two
* code units.
*
*
* @param source The input string.
* @param number The number of code points in the string is compared against the 'number'
* parameter.
@ -2142,7 +2144,7 @@ public final class UTF16 {
* needs to count more than 'number + 1' code points. Logically equivalent to
* (countCodePoint(source, start, limit) &gt; number). A Unicode code point may occupy either one
* or two code units.
*
*
* @param source Array of UTF-16 chars
* @param start Offset to substring in the source array for analyzing
* @param limit Offset to substring in the source array for analyzing
@ -2209,7 +2211,7 @@ public final class UTF16 {
* length is within a certain range, and never needs to count more than 'number + 1' code
* points. Logically equivalent to (countCodePoint(s) &gt; number). A Unicode code point may
* occupy either one or two code units.
*
*
* @param source The input string buffer.
* @param number The number of code points in the string buffer is compared against the 'number'
* parameter.
@ -2266,7 +2268,7 @@ public final class UTF16 {
/**
* Cover JDK 1.5 API. Create a String from an array of codePoints.
*
*
* @param codePoints The code array
* @param offset The start of the text in the code point array
* @param count The number of code points
@ -2326,7 +2328,7 @@ public final class UTF16 {
* supplementary code points because they are stored as pairs of surrogates which are at
* &#92;ud800..&#92;udfff.
* </p>
*
*
* @see #FOLD_CASE_DEFAULT
* @see #FOLD_CASE_EXCLUDE_SPECIAL_I
* @stable ICU 2.1
@ -2336,7 +2338,7 @@ public final class UTF16 {
/**
* Default constructor that does code unit comparison and case sensitive comparison.
*
*
* @stable ICU 2.1
*/
public StringComparator() {
@ -2345,7 +2347,7 @@ public final class UTF16 {
/**
* Constructor that does comparison based on the argument options.
*
*
* @param codepointcompare Flag to indicate true for code point comparison or false for code unit
* comparison.
* @param ignorecase False for case sensitive comparison, true for case-insensitive comparison
@ -2373,7 +2375,7 @@ public final class UTF16 {
*
* <p>Comparison is case insensitive, strings are folded using default mappings defined in
* Unicode data file CaseFolding.txt, before comparison.
*
*
* @stable ICU 2.4
*/
public static final int FOLD_CASE_DEFAULT = 0;
@ -2385,7 +2387,7 @@ public final class UTF16 {
*
* <p>Comparison is case insensitive, strings are folded using modified mappings defined in
* Unicode data file CaseFolding.txt, before comparison.
*
*
* @stable ICU 2.4
* @see com.ibm.icu.lang.UCharacter#FOLD_CASE_EXCLUDE_SPECIAL_I
*/
@ -2398,7 +2400,7 @@ public final class UTF16 {
/**
* Sets the comparison mode to code point compare if flag is true. Otherwise comparison mode
* is set to code unit compare
*
*
* @param flag True for code point compare, false for code unit compare
* @stable ICU 2.4
*/
@ -2413,7 +2415,7 @@ public final class UTF16 {
/**
* Sets the Comparator to case-insensitive comparison mode if argument is true, otherwise
* case sensitive comparison mode if set to false.
*
*
* @param ignorecase True for case-insitive comparison, false for case sensitive comparison
* @param foldcaseoption FOLD_CASE_DEFAULT or FOLD_CASE_EXCLUDE_SPECIAL_I. This option is used only
* when ignorecase is set to true. If ignorecase is false, this option is
@ -2434,7 +2436,7 @@ public final class UTF16 {
/**
* Checks if the comparison mode is code point compare.
*
*
* @return true for code point compare, false for code unit compare
* @stable ICU 2.4
*/
@ -2444,7 +2446,7 @@ public final class UTF16 {
/**
* Checks if Comparator is in the case insensitive mode.
*
*
* @return true if Comparator performs case insensitive comparison, false otherwise
* @stable ICU 2.4
*/
@ -2454,7 +2456,7 @@ public final class UTF16 {
/**
* Gets the fold case options set in Comparator to be used with case insensitive comparison.
*
*
* @return either FOLD_CASE_DEFAULT or FOLD_CASE_EXCLUDE_SPECIAL_I
* @see #FOLD_CASE_DEFAULT
* @see #FOLD_CASE_EXCLUDE_SPECIAL_I
@ -2468,7 +2470,7 @@ public final class UTF16 {
/**
* Compare two strings depending on the options selected during construction.
*
*
* @param a first source string.
* @param b second source string.
* @return 0 returned if a == b. If a &lt; b, a negative value is returned. Otherwise if a &gt; b,
@ -2476,8 +2478,9 @@ public final class UTF16 {
* @exception ClassCastException thrown when either a or b is not a String object
* @stable ICU 4.4
*/
@Override
public int compare(String a, String b) {
if (a == b) {
if (Utility.sameObjects(a, b)) {
return 0;
}
if (a == null) {
@ -2521,7 +2524,7 @@ public final class UTF16 {
/**
* Compares case insensitive. This is a direct port of ICU4C, to make maintainence life
* easier.
*
*
* @param s1
* first string to compare
* @param s2
@ -2536,7 +2539,7 @@ public final class UTF16 {
/**
* Compares case sensitive. This is a direct port of ICU4C, to make maintainence life
* easier.
*
*
* @param s1
* first string to compare
* @param s2
@ -2619,7 +2622,7 @@ public final class UTF16 {
}
// at this point, len = 2
int cp = Character.codePointAt(s, 0);
int cp = Character.codePointAt(s, 0);
if (cp > 0xFFFF) { // is surrogate pair
return cp;
}
@ -2691,7 +2694,7 @@ public final class UTF16 {
* <p>
* The result is a string whose length is 1 for non-supplementary code points, 2 otherwise.
* </p>
*
*
* @param ch
* code point
* @return string representation of the code point

5
icu4j/main/classes/translit/src/com/ibm/icu/text/TransliteratorRegistry.java
View file

@ -25,6 +25,7 @@ import java.util.ResourceBundle;
import com.ibm.icu.impl.ICUData;
import com.ibm.icu.impl.ICUResourceBundle;
import com.ibm.icu.impl.LocaleUtility;
import com.ibm.icu.impl.Utility;
import com.ibm.icu.lang.UScript;
import com.ibm.icu.text.RuleBasedTransliterator.Data;
import com.ibm.icu.util.CaseInsensitiveString;
@ -145,7 +146,7 @@ class TransliteratorRegistry {
}
public void reset() {
if (spec != top) { // [sic] pointer comparison
if (!Utility.sameObjects(spec, top)) {
spec = top;
isSpecLocale = (res != null);
setupNext();
@ -167,7 +168,7 @@ class TransliteratorRegistry {
}
} else {
// Fallback to the script, which may be null
if (nextSpec != scriptName) {
if (!Utility.sameObjects(nextSpec, scriptName)) {
nextSpec = scriptName;
} else {
nextSpec = null;