Package org.apache.lucene.tests.util

Class TestUtil

java.lang.Object

org.apache.lucene.tests.util.TestUtil

public final class TestUtil
extends Object

General utility methods for Lucene unit tests.

Field Summary

Fields

Modifier and Type	Field	Description
static Comparator<CharSequence>	STRING_CODEPOINT_COMPARATOR	A comparator that compares UTF-16 strings / char sequences according to Unicode code point order.

Method Summary

Modifier and Type	Method	Description
static void	addIndexesSlowly(IndexWriter writer, DirectoryReader... readers)
static Codec	alwaysDocValuesFormat(DocValuesFormat format)	Return a Codec that can read any of the default codecs and formats, but always writes in the specified format.
static Codec	alwaysPostingsFormat(PostingsFormat format)	Return a Codec that can read any of the default codecs and formats, but always writes in the specified format.
static boolean	anyFilesExceptWriteLock(Directory dir)
static <T> void	assertAttributeReflection(AttributeImpl att, Map<String,T> reflectedValues)	Checks some basic behaviour of an AttributeImpl
static void	assertConsistent(TopDocs expected, TopDocs actual)	Assert that the given TopDocs have the same top docs and consistent hit counts.
static String	bytesRefToString(BytesRef br)	For debugging: tries to include br.utf8ToString(), but if that fails (because it's not valid utf8, which is fine!), just use ordinary toString.
static CharSequence	bytesToCharSequence(BytesRef ref, Random random)
static CheckIndex.Status	checkIndex(Directory dir)	This runs the CheckIndex tool on the index in.
static CheckIndex.Status	checkIndex(Directory dir, boolean doSlowChecks)
static CheckIndex.Status	checkIndex(Directory dir, boolean doSlowChecks, boolean failFast, boolean concurrent, ByteArrayOutputStream output)	If failFast is true, then throw the first exception when index corruption is hit, instead of moving on to other fields/segments to look for any other corruption.
static <T> void	checkIterator(Iterator<T> iterator)	Checks that the provided iterator is well-formed.
static <T> void	checkIterator(Iterator<T> iterator, long expectedSize, boolean allowNull)	Checks that the provided iterator is well-formed.
static void	checkReader(IndexReader reader)	This runs the CheckIndex tool on the Reader.
static void	checkReader(LeafReader reader, boolean doSlowChecks)
static <T> void	checkReadOnly(Collection<T> coll)	Checks that the provided collection is read-only.
static Document	cloneDocument(Document doc1)
static boolean	disableVirusChecker(Directory in)	Returns true if VirusCheckingFS is in use and was in fact already enabled
static PostingsEnum	docs(Random random, IndexReader r, String field, BytesRef term, PostingsEnum reuse, int flags)
static PostingsEnum	docs(Random random, TermsEnum termsEnum, PostingsEnum reuse, int flags)
static boolean	doubleUlpEquals(double x, double y, int maxUlps)	Returns true if the arguments are equal or within the range of allowed error (inclusive).
static void	enableVirusChecker(Directory in)
static boolean	fieldSupportsHugeBinaryDocValues(String field)
static boolean	floatUlpEquals(float x, float y, short maxUlps)	Returns true if the arguments are equal or within the range of allowed error (inclusive).
static Codec	getDefaultCodec()	Returns the actual default codec (e.g.
static DocValuesFormat	getDefaultDocValuesFormat()	Returns the actual default docvalues format (e.g.
static KnnVectorsFormat	getDefaultKnnVectorsFormat()	Returns the actual default vector format (e.g.
static PostingsFormat	getDefaultPostingsFormat()	Returns the actual default postings format (e.g.
static PostingsFormat	getDefaultPostingsFormat(int minItemsPerBlock, int maxItemsPerBlock)	Returns the actual default postings format (e.g.
static String	getDocValuesFormat(String field)
static String	getDocValuesFormat(Codec codec, String field)
static String	getPostingsFormat(String field)
static String	getPostingsFormat(Codec codec, String field)
static PostingsFormat	getPostingsFormatWithOrds(Random r)	Returns a random postings format that supports term ordinals
static boolean	hasVirusChecker(Path path)
static boolean	hasVirusChecker(Directory dir)
static boolean	hasWindowsFS(Path path)
static boolean	hasWindowsFS(Directory dir)
static BigInteger	nextBigInteger(Random random, int maxBytes)	Returns a randomish big integer with 1 .. maxBytes storage.
static int	nextInt(Random r, int start, int end)	start and end are BOTH inclusive
static long	nextLong(Random r, long start, long end)	start and end are BOTH inclusive
static Directory	ramCopyOf(Directory dir)	Returns a copy of the source directory, with file contents stored in RAM.
static String	randomAnalysisString(Random random, int maxLength, boolean simple)
static BytesRef	randomBinaryTerm(Random r)	Returns a random binary term.
static BytesRef	randomBinaryTerm(Random r, int length)	Returns a random binary with a given length
static String	randomFixedByteLengthUnicodeString(Random r, int length)	Returns random string, with a given UTF-8 byte length
static void	randomFixedLengthUnicodeString(Random random, char[] chars, int offset, int length)	Fills provided char[] with valid random unicode code unit sequence.
static String	randomHtmlishString(Random random, int numElements)
static String	randomlyRecaseCodePoints(Random random, String str)	Randomly upcases, downcases, or leaves intact each code point in the given string
static Pattern	randomPattern(Random random)	Returns a valid (compiling) Pattern instance with random stuff inside.
static String	randomRealisticUnicodeString(Random r)	Returns random string of length between 0-20 codepoints, all codepoints within the same unicode block.
static String	randomRealisticUnicodeString(Random r, int maxLength)	Returns random string of length up to maxLength codepoints , all codepoints within the same unicode block.
static String	randomRealisticUnicodeString(Random r, int minLength, int maxLength)	Returns random string of length between min and max codepoints, all codepoints within the same unicode block.
static String	randomRegexpishString(Random r)	Returns a String thats "regexpish" (contains lots of operators typically found in regular expressions) If you call this enough times, you might get a valid regex!
static String	randomRegexpishString(Random r, int maxLength)	Returns a String thats "regexpish" (contains lots of operators typically found in regular expressions) If you call this enough times, you might get a valid regex!
static String	randomSimpleString(Random r)
static String	randomSimpleString(Random r, int maxLength)
static String	randomSimpleString(Random r, int minLength, int maxLength)
static String	randomSimpleStringRange(Random r, char minChar, char maxChar, int maxLength)
static String	randomSubString(Random random, int wordLength, boolean simple)
static String	randomUnicodeString(Random r)	Returns random string, including full unicode range.
static String	randomUnicodeString(Random r, int maxLength)	Returns a random string up to a certain length.
static void	reduceOpenFiles(IndexWriter w)	just tries to configure things to keep the open file count lowish
static void	shutdownExecutorService(ExecutorService ex)	Shutdown ExecutorService and wait for its.
static CharSequence	stringToCharSequence(String string, Random random)
static void	syncConcurrentMerges(IndexWriter writer)
static void	syncConcurrentMerges(MergeScheduler ms)
static void	unzip(InputStream in, Path destDir)	Convenience method unzipping zipName into destDir.

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Field Detail

STRING_CODEPOINT_COMPARATOR

public static final Comparator<CharSequence> STRING_CODEPOINT_COMPARATOR

A comparator that compares UTF-16 strings / char sequences according to Unicode code point order. This can be used to verify BytesRef order.

Warning: This comparator is rather inefficient, because it converts the strings to a int[] array on each invocation.

Method Detail

unzip

public static void unzip(InputStream in,
                         Path destDir)
                  throws IOException

Convenience method unzipping zipName into destDir. You must pass it a clean destDir.

Closes the given InputStream after extracting!

Throws:

IOException

checkIterator

public static <T> void checkIterator(Iterator<T> iterator,
                                     long expectedSize,
                                     boolean allowNull)

Checks that the provided iterator is well-formed.

• is read-only: does not allow remove
• returns expectedSize number of elements
• does not return null elements, unless allowNull is true.
• throws NoSuchElementException if next is called after hasNext returns false.

checkIterator

public static <T> void checkIterator(Iterator<T> iterator)

Checks that the provided iterator is well-formed.

• is read-only: does not allow remove
• does not return null elements.
• throws NoSuchElementException if next is called after hasNext returns false.

checkReadOnly

public static <T> void checkReadOnly(Collection<T> coll)

Checks that the provided collection is read-only.

See Also:

checkIterator(Iterator)

syncConcurrentMerges

public static void syncConcurrentMerges(IndexWriter writer)

syncConcurrentMerges

public static void syncConcurrentMerges(MergeScheduler ms)

checkIndex

public static CheckIndex.Status checkIndex(Directory dir)
                                    throws IOException

This runs the CheckIndex tool on the index in. If any issues are hit, a RuntimeException is thrown; else, true is returned.

Throws:

IOException

checkIndex

public static CheckIndex.Status checkIndex(Directory dir,
                                           boolean doSlowChecks)
                                    throws IOException

Throws:

IOException

checkIndex

public static CheckIndex.Status checkIndex(Directory dir,
                                           boolean doSlowChecks,
                                           boolean failFast,
                                           boolean concurrent,
                                           ByteArrayOutputStream output)
                                    throws IOException

If failFast is true, then throw the first exception when index corruption is hit, instead of moving on to other fields/segments to look for any other corruption.

Throws:

IOException

checkReader

public static void checkReader(IndexReader reader)
                        throws IOException

This runs the CheckIndex tool on the Reader. If any issues are hit, a RuntimeException is thrown

Throws:

IOException

checkReader

public static void checkReader(LeafReader reader,
                               boolean doSlowChecks)
                        throws IOException

Throws:

IOException

floatUlpEquals

public static boolean floatUlpEquals(float x,
                                     float y,
                                     short maxUlps)

Returns true if the arguments are equal or within the range of allowed error (inclusive). Returns false if either of the arguments is NaN.

Two float numbers are considered equal if there are (maxUlps - 1) (or fewer) floating point numbers between them, i.e. two adjacent floating point numbers are considered equal.

Adapted from org.apache.commons.numbers.core.Precision

github: https://github.com/apache/commons-numbers release 1.2

Parameters:

x - first value

y - second value

maxUlps - (maxUlps - 1) is the number of floating point values between x and y.

Returns:

true if there are fewer than maxUlps floating point values between x and y.

doubleUlpEquals

public static boolean doubleUlpEquals(double x,
                                      double y,
                                      int maxUlps)

Returns true if the arguments are equal or within the range of allowed error (inclusive). Returns false if either of the arguments is NaN.

Two double numbers are considered equal if there are (maxUlps - 1) (or fewer) floating point numbers between them, i.e. two adjacent floating point numbers are considered equal.

Adapted from org.apache.commons.numbers.core.Precision

github: https://github.com/apache/commons-numbers release 1.2

Parameters:

x - first value

y - second value

maxUlps - (maxUlps - 1) is the number of floating point values between x and y.

Returns:

true if there are fewer than maxUlps floating point values between x and y.

nextInt

public static int nextInt(Random r,
                          int start,
                          int end)

start and end are BOTH inclusive

nextLong

public static long nextLong(Random r,
                            long start,
                            long end)

start and end are BOTH inclusive

nextBigInteger

public static BigInteger nextBigInteger(Random random,
                                        int maxBytes)

Returns a randomish big integer with 1 .. maxBytes storage.

randomSimpleString

public static String randomSimpleString(Random r,
                                        int maxLength)

randomSimpleString

public static String randomSimpleString(Random r,
                                        int minLength,
                                        int maxLength)

randomSimpleStringRange

public static String randomSimpleStringRange(Random r,
                                             char minChar,
                                             char maxChar,
                                             int maxLength)

randomSimpleString

public static String randomSimpleString(Random r)

randomUnicodeString

public static String randomUnicodeString(Random r)

Returns random string, including full unicode range.

randomUnicodeString

public static String randomUnicodeString(Random r,
                                         int maxLength)

Returns a random string up to a certain length.

randomFixedLengthUnicodeString

public static void randomFixedLengthUnicodeString(Random random,
                                                  char[] chars,
                                                  int offset,
                                                  int length)

Fills provided char[] with valid random unicode code unit sequence.

randomRegexpishString

public static String randomRegexpishString(Random r)

Returns a String thats "regexpish" (contains lots of operators typically found in regular expressions) If you call this enough times, you might get a valid regex!

randomRegexpishString

public static String randomRegexpishString(Random r,
                                           int maxLength)

Returns a String thats "regexpish" (contains lots of operators typically found in regular expressions) If you call this enough times, you might get a valid regex!

Note: to avoid practically endless backtracking patterns we replace asterisk and plus operators with bounded repetitions. See LUCENE-4111 for more info.

Parameters:

maxLength - A hint about maximum length of the regexpish string. It may be exceeded by a few characters.

randomHtmlishString

public static String randomHtmlishString(Random random,
                                         int numElements)

randomlyRecaseCodePoints

public static String randomlyRecaseCodePoints(Random random,
                                              String str)

Randomly upcases, downcases, or leaves intact each code point in the given string

randomRealisticUnicodeString

public static String randomRealisticUnicodeString(Random r)

Returns random string of length between 0-20 codepoints, all codepoints within the same unicode block.

randomRealisticUnicodeString

public static String randomRealisticUnicodeString(Random r,
                                                  int maxLength)

Returns random string of length up to maxLength codepoints , all codepoints within the same unicode block.

randomRealisticUnicodeString

public static String randomRealisticUnicodeString(Random r,
                                                  int minLength,
                                                  int maxLength)

Returns random string of length between min and max codepoints, all codepoints within the same unicode block.

randomFixedByteLengthUnicodeString

public static String randomFixedByteLengthUnicodeString(Random r,
                                                        int length)

Returns random string, with a given UTF-8 byte length

randomBinaryTerm

public static BytesRef randomBinaryTerm(Random r)

Returns a random binary term.

randomBinaryTerm

public static BytesRef randomBinaryTerm(Random r,
                                        int length)

Returns a random binary with a given length

alwaysPostingsFormat

public static Codec alwaysPostingsFormat(PostingsFormat format)

Return a Codec that can read any of the default codecs and formats, but always writes in the specified format.

alwaysDocValuesFormat

public static Codec alwaysDocValuesFormat(DocValuesFormat format)

Return a Codec that can read any of the default codecs and formats, but always writes in the specified format.

getDefaultCodec

public static Codec getDefaultCodec()

Returns the actual default codec (e.g. LuceneMNCodec) for this version of Lucene. This may be different than Codec.getDefault() because that is randomized.

getDefaultPostingsFormat

public static PostingsFormat getDefaultPostingsFormat()

Returns the actual default postings format (e.g. LuceneMNPostingsFormat for this version of Lucene.

getDefaultPostingsFormat

public static PostingsFormat getDefaultPostingsFormat(int minItemsPerBlock,
                                                      int maxItemsPerBlock)

Returns the actual default postings format (e.g. LuceneMNPostingsFormat for this version of Lucene.

NOTE: This API is for internal purposes only and might change in incompatible ways in the next release.

this may disappear at any time

getPostingsFormatWithOrds

public static PostingsFormat getPostingsFormatWithOrds(Random r)

Returns a random postings format that supports term ordinals

getDefaultDocValuesFormat

public static DocValuesFormat getDefaultDocValuesFormat()

Returns the actual default docvalues format (e.g. LuceneMNDocValuesFormat for this version of Lucene.

getPostingsFormat

public static String getPostingsFormat(String field)

getPostingsFormat

public static String getPostingsFormat(Codec codec,
                                       String field)

getDocValuesFormat

public static String getDocValuesFormat(String field)

getDocValuesFormat

public static String getDocValuesFormat(Codec codec,
                                        String field)

fieldSupportsHugeBinaryDocValues

public static boolean fieldSupportsHugeBinaryDocValues(String field)

getDefaultKnnVectorsFormat

public static KnnVectorsFormat getDefaultKnnVectorsFormat()

Returns the actual default vector format (e.g. LuceneMNKnnVectorsFormat for this version of Lucene.

anyFilesExceptWriteLock

public static boolean anyFilesExceptWriteLock(Directory dir)
                                       throws IOException

Throws:

IOException

addIndexesSlowly

public static void addIndexesSlowly(IndexWriter writer,
                                    DirectoryReader... readers)
                             throws IOException

Throws:

IOException

reduceOpenFiles

public static void reduceOpenFiles(IndexWriter w)

just tries to configure things to keep the open file count lowish

assertAttributeReflection

public static <T> void assertAttributeReflection(AttributeImpl att,
                                                 Map<String,T> reflectedValues)

Checks some basic behaviour of an AttributeImpl

Parameters:

reflectedValues - contains a map with "AttributeClass#key" as values

assertConsistent

public static void assertConsistent(TopDocs expected,
                                    TopDocs actual)

Assert that the given TopDocs have the same top docs and consistent hit counts.

cloneDocument

public static Document cloneDocument(Document doc1)

docs

public static PostingsEnum docs(Random random,
                                IndexReader r,
                                String field,
                                BytesRef term,
                                PostingsEnum reuse,
                                int flags)
                         throws IOException

Throws:

IOException

docs

public static PostingsEnum docs(Random random,
                                TermsEnum termsEnum,
                                PostingsEnum reuse,
                                int flags)
                         throws IOException

Throws:

IOException

stringToCharSequence

public static CharSequence stringToCharSequence(String string,
                                                Random random)

bytesToCharSequence

public static CharSequence bytesToCharSequence(BytesRef ref,
                                               Random random)

shutdownExecutorService

public static void shutdownExecutorService(ExecutorService ex)

Shutdown ExecutorService and wait for its.

randomPattern

public static Pattern randomPattern(Random random)

Returns a valid (compiling) Pattern instance with random stuff inside. Be careful when applying random patterns to longer strings as certain types of patterns may explode into exponential times in backtracking implementations (such as Java's).

randomAnalysisString

public static String randomAnalysisString(Random random,
                                          int maxLength,
                                          boolean simple)

randomSubString

public static String randomSubString(Random random,
                                     int wordLength,
                                     boolean simple)

bytesRefToString

public static String bytesRefToString(BytesRef br)

For debugging: tries to include br.utf8ToString(), but if that fails (because it's not valid utf8, which is fine!), just use ordinary toString.

ramCopyOf

public static Directory ramCopyOf(Directory dir)
                           throws IOException

Returns a copy of the source directory, with file contents stored in RAM.

Throws:

IOException

hasWindowsFS

public static boolean hasWindowsFS(Directory dir)

hasWindowsFS

public static boolean hasWindowsFS(Path path)

hasVirusChecker

public static boolean hasVirusChecker(Directory dir)

hasVirusChecker

public static boolean hasVirusChecker(Path path)

disableVirusChecker

public static boolean disableVirusChecker(Directory in)

Returns true if VirusCheckingFS is in use and was in fact already enabled

enableVirusChecker

public static void enableVirusChecker(Directory in)