AuroraMiddleware/scuffed-code
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

ICU-12766 merge from trunk

Browse Source 
X-SVN-Rev: 39819
This commit is contained in:
Steven R. Loomis 2017-03-15 16:59:48 +00:00
commit 967bf42d24
3 changed files with 95 additions and 65 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
icu4c/source/i18n/simpletz.cpp
View File

@ -1189,13 +1189,22 @@ SimpleTimeZone::initTransitionRules(UErrorCode& status) {
// Create a TimeZoneRule for initial time
if (firstStdStart < firstDstStart) {
initialRule = new InitialTimeZoneRule(tzid+UnicodeString(DST_STR), getRawOffset(), dstRule->getDSTSavings());
if (initialRule == NULL) {
status = U_MEMORY_ALLOCATION_ERROR;
deleteTransitionRules();
return;
}
firstTransition = new TimeZoneTransition(firstStdStart, *initialRule, *stdRule);
} else {
initialRule = new InitialTimeZoneRule(tzid+UnicodeString(STD_STR), getRawOffset(), 0);
if (initialRule == NULL) {
status = U_MEMORY_ALLOCATION_ERROR;
deleteTransitionRules();
return;
}
firstTransition = new TimeZoneTransition(firstDstStart, *initialRule, *dstRule);
}
// Check for null pointers.
if (initialRule == NULL || firstTransition == NULL) {
if (firstTransition == NULL) {
status = U_MEMORY_ALLOCATION_ERROR;
deleteTransitionRules();
return;

113
icu4j/main/classes/collate/src/com/ibm/icu/text/StringSearch.java
View File

@ -32,7 +32,7 @@ import com.ibm.icu.util.ULocale;
// is a leftover from already-disabled Boyer-Moore search code. This Java implementation
// preserves the code, but we should clean this up later.
/**
/**
*
* <tt>StringSearch</tt> is a {@link SearchIterator} that provides
* language-sensitive text searching based on the comparison rules defined
@ -49,7 +49,7 @@ import com.ibm.icu.util.ULocale;
* <br>
* A pattern string P matches a text string S at the offsets [start, end]
* if
* <pre>
* <pre>
* option 1. Some canonical equivalent of P matches some canonical equivalent
* of S'
* option 2. P matches S' and if P starts or ends with a combining mark,
@ -58,10 +58,10 @@ import com.ibm.icu.util.ULocale;
* </pre>
* Option 2. is the default.
* <p>
* This search has APIs similar to that of other text iteration mechanisms
* such as the break iterators in {@link BreakIterator}. Using these
* APIs, it is easy to scan through text looking for all occurrences of
* a given pattern. This search iterator allows changing of direction by
* This search has APIs similar to that of other text iteration mechanisms
* such as the break iterators in {@link BreakIterator}. Using these
* APIs, it is easy to scan through text looking for all occurrences of
* a given pattern. This search iterator allows changing of direction by
* calling a {@link #reset} followed by a {@link #next} or {@link #previous}.
* Though a direction change can occur without calling {@link #reset} first,
* this operation comes with some speed penalty.
@ -109,7 +109,7 @@ import com.ibm.icu.util.ULocale;
* from {@link #getCollator} and using the APIs in {@link RuleBasedCollator}.
* Lastly to update <tt>StringSearch</tt> to the new collator attributes,
* {@link #reset} has to be called.
* <p>
* <p>
* Restriction: <br>
* Currently there are no composite characters that consists of a
* character with combining class &gt; 0 before a character with combining
@ -127,7 +127,7 @@ import com.ibm.icu.util.ULocale;
* @author Laura Werner, synwee
* @stable ICU 2.0
*/
// internal notes: all methods do not guarantee the correct status of the
// internal notes: all methods do not guarantee the correct status of the
// characteriterator. the caller has to maintain the original index position
// if necessary. methods could change the index position as it deems fit
public final class StringSearch extends SearchIterator {
@ -157,15 +157,15 @@ public final class StringSearch extends SearchIterator {
// private char[] canonicalSuffixAccents_;
/**
* Initializes the iterator to use the language-specific rules defined in
* the argument collator to search for argument pattern in the argument
* Initializes the iterator to use the language-specific rules defined in
* the argument collator to search for argument pattern in the argument
* target text. The argument <code>breakiter</code> is used to define logical matches.
* See super class documentation for more details on the use of the target
* See super class documentation for more details on the use of the target
* text and {@link BreakIterator}.
* @param pattern text to look for.
* @param target target text to search for pattern.
* @param target target text to search for pattern.
* @param collator {@link RuleBasedCollator} that defines the language rules
* @param breakiter A {@link BreakIterator} that is used to determine the
* @param breakiter A {@link BreakIterator} that is used to determine the
* boundaries of a logical match. This argument can be null.
* @throws IllegalArgumentException thrown when argument target is null,
* or of length 0
@ -219,11 +219,11 @@ public final class StringSearch extends SearchIterator {
}
/**
* Initializes the iterator to use the language-specific rules defined in
* the argument collator to search for argument pattern in the argument
* Initializes the iterator to use the language-specific rules defined in
* the argument collator to search for argument pattern in the argument
* target text. No {@link BreakIterator}s are set to test for logical matches.
* @param pattern text to look for.
* @param target target text to search for pattern.
* @param target target text to search for pattern.
* @param collator {@link RuleBasedCollator} that defines the language rules
* @throws IllegalArgumentException thrown when argument target is null,
* or of length 0
@ -235,14 +235,14 @@ public final class StringSearch extends SearchIterator {
}
/**
* Initializes the iterator to use the language-specific rules and
* break iterator rules defined in the argument locale to search for
* argument pattern in the argument target text.
* Initializes the iterator to use the language-specific rules and
* break iterator rules defined in the argument locale to search for
* argument pattern in the argument target text.
* @param pattern text to look for.
* @param target target text to search for pattern.
* @param target target text to search for pattern.
* @param locale locale to use for language and break iterator rules
* @throws IllegalArgumentException thrown when argument target is null,
* or of length 0. ClassCastException thrown if the collator for
* or of length 0. ClassCastException thrown if the collator for
* the specified locale is not a RuleBasedCollator.
* @stable ICU 2.0
*/
@ -251,16 +251,16 @@ public final class StringSearch extends SearchIterator {
}
/**
* Initializes the iterator to use the language-specific rules and
* break iterator rules defined in the argument locale to search for
* argument pattern in the argument target text.
* See super class documentation for more details on the use of the target
* Initializes the iterator to use the language-specific rules and
* break iterator rules defined in the argument locale to search for
* argument pattern in the argument target text.
* See super class documentation for more details on the use of the target
* text and {@link BreakIterator}.
* @param pattern text to look for.
* @param target target text to search for pattern.
* @param target target text to search for pattern.
* @param locale locale to use for language and break iterator rules
* @throws IllegalArgumentException thrown when argument target is null,
* or of length 0. ClassCastException thrown if the collator for
* or of length 0. ClassCastException thrown if the collator for
* the specified locale is not a RuleBasedCollator.
* @see BreakIterator
* @see RuleBasedCollator
@ -272,13 +272,13 @@ public final class StringSearch extends SearchIterator {
}
/**
* Initializes the iterator to use the language-specific rules and
* break iterator rules defined in the default locale to search for
* Initializes the iterator to use the language-specific rules and
* break iterator rules defined in the default locale to search for
* argument pattern in the argument target text.
* @param pattern text to look for.
* @param target target text to search for pattern.
* @param target target text to search for pattern.
* @throws IllegalArgumentException thrown when argument target is null,
* or of length 0. ClassCastException thrown if the collator for
* or of length 0. ClassCastException thrown if the collator for
* the default locale is not a RuleBasedCollator.
* @stable ICU 2.0
*/
@ -290,9 +290,9 @@ public final class StringSearch extends SearchIterator {
/**
* Gets the {@link RuleBasedCollator} used for the language rules.
* <p>
* Since <tt>StringSearch</tt> depends on the returned {@link RuleBasedCollator}, any
* changes to the {@link RuleBasedCollator} result should follow with a call to
* either {@link #reset()} or {@link #setCollator(RuleBasedCollator)} to ensure the correct
* Since <tt>StringSearch</tt> depends on the returned {@link RuleBasedCollator}, any
* changes to the {@link RuleBasedCollator} result should follow with a call to
* either {@link #reset()} or {@link #setCollator(RuleBasedCollator)} to ensure the correct
* search behavior.
* </p>
* @return {@link RuleBasedCollator} used by this <tt>StringSearch</tt>
@ -343,7 +343,7 @@ public final class StringSearch extends SearchIterator {
}
/**
* Set the pattern to search for.
* Set the pattern to search for.
* The iterator's position will not be changed by this method.
* @param pattern for searching
* @see #getPattern
@ -361,7 +361,7 @@ public final class StringSearch extends SearchIterator {
}
/**
* Determines whether canonical matches (option 1, as described in the
* Determines whether canonical matches (option 1, as described in the
* class documentation) is set.
* See setCanonical(boolean) for more information.
* @see #setCanonical
@ -422,7 +422,7 @@ public final class StringSearch extends SearchIterator {
textIter_.setOffset(position);
}
/**
/**
* {@inheritDoc}
* @stable ICU 2.8
*/
@ -615,7 +615,7 @@ public final class StringSearch extends SearchIterator {
/**
* Getting the modified collation elements taking into account the collation
* attributes.
*
*
* @param sourcece
* @return the modified collation element
*/
@ -646,20 +646,19 @@ public final class StringSearch extends SearchIterator {
}
/**
* Direct port of ICU4C static int32_t * addTouint32_tArray(...) in usearch.cpp.
* Direct port of ICU4C static int32_t * addTouint32_tArray(...) in usearch.cpp
* (except not taking destination buffer size and status param).
* This is used for appending a PCE to Pattern.PCE_ buffer. We probably should
* implement this in Pattern class.
*
*
* @param destination target array
* @param offset destination offset to add value
* @param destinationlength target array size
* @param value to be added
* @param increments incremental size expected
* @return new destination array, destination if there was no new allocation
*/
private static int[] addToIntArray(int[] destination, int offset, int destinationlength,
int value, int increments) {
int newlength = destinationlength;
private static int[] addToIntArray(int[] destination, int offset, int value, int increments) {
int newlength = destination.length;
if (offset + 1 == newlength) {
newlength += increments;
int temp[] = new int[newlength];
@ -674,7 +673,7 @@ public final class StringSearch extends SearchIterator {
* Direct port of ICU4C static int64_t * addTouint64_tArray(...) in usearch.cpp.
* This is used for appending a PCE to Pattern.PCE_ buffer. We probably should
* implement this in Pattern class.
*
*
* @param destination target array
* @param offset destination offset to add value
* @param destinationlength target array size
@ -706,7 +705,6 @@ public final class StringSearch extends SearchIterator {
// TODO: We probably do not need Pattern CE table.
private int initializePatternCETable() {
int[] cetable = new int[INITIAL_ARRAY_SIZE_];
int cetablesize = cetable.length;
int patternlength = pattern_.text_.length();
CollationElementIterator coleiter = utilIter_;
@ -724,7 +722,7 @@ public final class StringSearch extends SearchIterator {
while ((ce = coleiter.next()) != CollationElementIterator.NULLORDER) {
int newce = getCE(ce);
if (newce != CollationElementIterator.IGNORABLE /* 0 */) {
int[] temp = addToIntArray(cetable, offset, cetablesize, newce,
int[] temp = addToIntArray(cetable, offset, newce,
patternlength - coleiter.getOffset() + 1);
offset++;
cetable = temp;
@ -806,9 +804,9 @@ public final class StringSearch extends SearchIterator {
// *** Boyer-Moore ***
/*
private final void setShiftTable(char shift[],
char backshift[],
int cetable[], int cesize,
private final void setShiftTable(char shift[],
char backshift[],
int cetable[], int cesize,
int expansionsize,
int defaultforward,
int defaultbackward) {
@ -839,6 +837,7 @@ public final class StringSearch extends SearchIterator {
* @internal
* @deprecated This API is ICU internal only.
*/
@Override
@Deprecated
protected void setMatchNotFound() {
super.setMatchNotFound();
@ -1510,7 +1509,7 @@ public final class StringSearch extends SearchIterator {
//
// ICU4C usearch_handleNextExact() is identical to usearch_handleNextCanonical()
// for the linear search implementation. The differences are addressed in search().
//
//
private boolean handleNextExact() {
return handleNextCommonImpl();
}
@ -1585,9 +1584,9 @@ public final class StringSearch extends SearchIterator {
/**
* Gets a substring out of a CharacterIterator
*
*
* Java porting note: Not available in ICU4C
*
*
* @param text CharacterIterator
* @param start start offset
* @param length of substring
@ -1722,12 +1721,12 @@ public final class StringSearch extends SearchIterator {
/**
* Get the processed ordering priority of the next collation element in the text.
* A single character may contain more than one collation element.
*
*
* Note: This is equivalent to
* UCollationPCE::nextProcessed(int32_t *ixLow, int32_t *ixHigh, UErrorCode *status);
*
* @param range receiving the iterator index before/after fetching the CE.
* @return The next collation elements ordering, otherwise returns PROCESSED_NULLORDER
* @return The next collation elements ordering, otherwise returns PROCESSED_NULLORDER
* if an error has occurred or if the end of string has been reached
*/
public long nextProcessed(Range range) {
@ -1765,7 +1764,7 @@ public final class StringSearch extends SearchIterator {
* UCollationPCE::previousProcessed(int32_t *ixLow, int32_t *ixHigh, UErrorCode *status);
*
* @param range receiving the iterator index before/after fetching the CE.
* @return The previous collation elements ordering, otherwise returns
* @return The previous collation elements ordering, otherwise returns
* PROCESSED_NULLORDER if an error has occurred or if the start of
* string has been reached.
*/
@ -1926,7 +1925,7 @@ public final class StringSearch extends SearchIterator {
/**
* Java port of ICU4C CEI (usearch.cpp)
*
*
* CEI Collation Element + source text index.
* These structs are kept in the circular buffer.
*/

34
icu4j/main/tests/collate/src/com/ibm/icu/dev/test/search/SearchTest.java
View File

@ -23,6 +23,7 @@ import static com.ibm.icu.text.SearchIterator.ElementComparisonType.ANY_BASE_WEI
import static com.ibm.icu.text.SearchIterator.ElementComparisonType.PATTERN_BASE_WEIGHT_IS_WILDCARD;
import static com.ibm.icu.text.SearchIterator.ElementComparisonType.STANDARD_ELEMENT_COMPARISON;
import java.text.CharacterIterator;
import java.text.StringCharacterIterator;
import java.util.Locale;
@ -1977,6 +1978,7 @@ public class SearchTest extends TestFmwk {
text = buffer.toString();
targetText.setIndex(targetText.getBeginIndex());
}
@Override
protected int handleNext(int start)
{
int match = text.indexOf(pattern, start);
@ -1988,6 +1990,7 @@ public class SearchTest extends TestFmwk {
setMatchLength(pattern.length());
return match;
}
@Override
protected int handlePrevious(int start)
{
int match = text.lastIndexOf(pattern, start - 1);
@ -2000,6 +2003,7 @@ public class SearchTest extends TestFmwk {
return match;
}
@Override
public int getIndex()
{
int result = targetText.getIndex();
@ -2037,7 +2041,7 @@ public class SearchTest extends TestFmwk {
errln("Error should have reached the start of the iteration");
}
}
//Test for ticket 5024
@Test
public void TestDiactricMatch() {
@ -2110,7 +2114,7 @@ public class SearchTest extends TestFmwk {
public String getPattern() { return pattern; }
public int[] getOffsets() { return offsets; }
}
final PatternAndOffsets[] scKoSrchPatternsOffsets = {
final PatternAndOffsets[] scKoSrchPatternsOffsets = {
new PatternAndOffsets( scKoPat0, scKoSrchOff01 ),
new PatternAndOffsets( scKoPat1, scKoSrchOff01 ),
new PatternAndOffsets( scKoPat2, scKoSrchOff23 ),
@ -2118,7 +2122,7 @@ public class SearchTest extends TestFmwk {
new PatternAndOffsets( scKoPat4, scKoSrchOff45 ),
new PatternAndOffsets( scKoPat5, scKoSrchOff45 ),
};
final PatternAndOffsets[] scKoStndPatternsOffsets = {
final PatternAndOffsets[] scKoStndPatternsOffsets = {
new PatternAndOffsets( scKoPat0, scKoStndOff01 ),
new PatternAndOffsets( scKoPat1, scKoStndOff01 ),
new PatternAndOffsets( scKoPat2, scKoStndOff2 ),
@ -2140,12 +2144,12 @@ public class SearchTest extends TestFmwk {
public String getText() { return text; }
public PatternAndOffsets[] getPatternsAndOffsets() { return patternsAndOffsets; }
}
final TUSCItem[] tuscItems = {
final TUSCItem[] tuscItems = {
new TUSCItem( "root", scKoText, scKoStndPatternsOffsets ),
new TUSCItem( "root@collation=search", scKoText, scKoSrchPatternsOffsets ),
new TUSCItem( "ko@collation=search", scKoText, scKoSrchPatternsOffsets ),
};
String dummyPat = "a";
for (TUSCItem tuscItem: tuscItems) {
@ -2222,6 +2226,24 @@ public class SearchTest extends TestFmwk {
}
}
// Test case for ticket#12555
@Test
public void TestLongPattern() {
StringBuilder pattern = new StringBuilder();
for (int i = 0; i < 255; i++) {
pattern.append('a');
}
// appends a character producing multiple ce32 at
// index 256.
pattern.append('á');
CharacterIterator target = new StringCharacterIterator("not important");
try {
StringSearch ss = new StringSearch(pattern.toString(), target, Locale.ENGLISH);
assertNotNull("Non-null StringSearch instance", ss);
} catch (Exception e) {
errln("Error initializing a new StringSearch object");
}
}
}