test-framework/org.gnit.lucenekmp.tests.analysis/BaseTokenStreamTestCase/Companion

Companion

Functions

fun assertAnalyzesTo(a: Analyzer, input: String, output: Array<String>, types: Array<String>)

fun assertAnalyzesTo(a: Analyzer, input: String, output: Array<String>, posIncrements: IntArray)

fun assertAnalyzesTo(a: Analyzer, input: String, output: Array<String>, startOffsets: IntArray, endOffsets: IntArray, posIncrements: IntArray)

fun assertAnalyzesTo(a: Analyzer, input: String, output: Array<String>, startOffsets: IntArray, endOffsets: IntArray, types: Array<String>, posIncrements: IntArray)

fun assertAnalyzesTo(a: Analyzer, input: String, output: Array<String>, startOffsets: IntArray, endOffsets: IntArray, types: Array<String>?, posIncrements: IntArray, posLengths: IntArray?, graphOffsetsAreCorrect: Boolean)

fun assertAnalyzesTo(a: Analyzer, input: String, output: Array<String>, startOffsets: IntArray? = null, endOffsets: IntArray? = null, types: Array<String>? = null, posIncrements: IntArray? = null, posLengths: IntArray? = null, boost: FloatArray? = null)

fun assertAnalyzesTo(a: Analyzer, input: String, output: Array<String>, startOffsets: IntArray, endOffsets: IntArray, types: Array<String>, posIncrements: IntArray, posLengths: IntArray, graphOffsetsAreCorrect: Boolean, payloads: Array<ByteArray>)

assertAnalyzesToPositions

fun assertAnalyzesToPositions(a: Analyzer, input: String, output: Array<String>, posIncrements: IntArray, posLengths: IntArray)

fun assertAnalyzesToPositions(a: Analyzer, input: String, output: Array<String>, types: Array<String>, posIncrements: IntArray, posLengths: IntArray)

assertGraphStrings

fun assertGraphStrings(tokenStream: TokenStream, vararg expectedStrings: String)

Enumerates all accepted strings in the token graph created by the already initialized [ ].

fun assertGraphStrings(analyzer: Analyzer, text: String, vararg expectedStrings: String)

Enumerates all accepted strings in the token graph created by the analyzer on the provided text, and then asserts that it's equal to the expected strings. Uses [ ] to create an automaton. Asserts the finite strings of the automaton are all and only the given valid strings.

assertStreamHasNumberOfTokens

fun assertStreamHasNumberOfTokens(ts: TokenStream, expectedCount: Int)

Asserts that the given stream has expected number of tokens.

assertTokenStreamContents

fun assertTokenStreamContents(ts: TokenStream, output: Array<String>, types: Array<String>)

fun assertTokenStreamContents(ts: TokenStream, output: Array<String>, posIncrements: IntArray)

fun assertTokenStreamContents(ts: TokenStream, output: Array<String>, startOffsets: IntArray, endOffsets: IntArray, finalOffset: Int)

fun assertTokenStreamContents(ts: TokenStream, output: Array<String>, startOffsets: IntArray, endOffsets: IntArray, posIncrements: IntArray)

fun assertTokenStreamContents(ts: TokenStream, output: Array<String>, startOffsets: IntArray, endOffsets: IntArray, posIncrements: IntArray, finalOffset: Int)

fun assertTokenStreamContents(ts: TokenStream, output: Array<String>, startOffsets: IntArray, endOffsets: IntArray, types: Array<String>, posIncrements: IntArray, finalOffset: Int)

fun assertTokenStreamContents(ts: TokenStream, output: Array<String>, startOffsets: IntArray, endOffsets: IntArray, posIncrements: IntArray, posLengths: IntArray, finalOffset: Int)

fun assertTokenStreamContents(ts: TokenStream, output: Array<String>, startOffsets: IntArray? = null, endOffsets: IntArray? = null, types: Array<String>? = null, posIncrements: IntArray? = null, posLengths: IntArray? = null, finalOffset: Int? = null, graphOffsetsAreCorrect: Boolean = true)

fun assertTokenStreamContents(ts: TokenStream, output: Array<String>, startOffsets: IntArray?, endOffsets: IntArray?, types: Array<String>?, posIncrements: IntArray?, posLengths: IntArray?, finalOffset: Int, graphOffsetsAreCorrect: Boolean, boost: FloatArray?)

@JvmOverloads

fun assertTokenStreamContents(ts: TokenStream, output: Array<String>, startOffsets: IntArray?, endOffsets: IntArray?, types: Array<String>?, posIncrements: IntArray?, posLengths: IntArray?, finalOffset: Int?, keywordAtts: BooleanArray?, graphOffsetsAreCorrect: Boolean, boost: FloatArray? = null)

fun assertTokenStreamContents(ts: TokenStream, output: Array<String>, startOffsets: IntArray, endOffsets: IntArray, types: Array<String>, posIncrements: IntArray, posLengths: IntArray, finalOffset: Int, finalPosInc: Int?, keywordAtts: BooleanArray?, graphOffsetsAreCorrect: Boolean, payloads: Array<ByteArray>)

fun assertTokenStreamContents(ts: TokenStream, output: Array<String>, startOffsets: IntArray, endOffsets: IntArray, types: Array<String>, posIncrements: IntArray, posLengths: IntArray, finalOffset: Int, finalPosInc: Int, keywordAtts: BooleanArray, graphOffsetsAreCorrect: Boolean, payloads: Array<ByteArray>, flags: IntArray)

fun assertTokenStreamContents(ts: TokenStream, output: Array<String>, startOffsets: IntArray?, endOffsets: IntArray?, types: Array<String>?, posIncrements: IntArray?, posLengths: IntArray?, finalOffset: Int?, finalPosInc: Int?, keywordAtts: BooleanArray?, graphOffsetsAreCorrect: Boolean, payloads: Array<ByteArray>?, flags: IntArray?, boost: FloatArray?)

checkAnalysisConsistency

@JvmOverloads

fun checkAnalysisConsistency(random: Random, a: Analyzer, useCharFilter: Boolean, text: String, graphOffsetsAreCorrect: Boolean = true)

checkOneTerm

fun checkOneTerm(a: Analyzer, input: String, expected: String)

checkRandomData

fun checkRandomData(random: Random, a: Analyzer, iterations: Int, simple: Boolean)

@JvmOverloads

fun checkRandomData(random: Random, a: Analyzer, iterations: Int, maxWordLength: Int = 20, simple: Boolean = false, graphOffsetsAreCorrect: Boolean = true)

utility method for blasting tokenstreams with data to make sure they don't do anything crazy

checkResetException

fun checkResetException(a: Analyzer, input: String)

escape

fun escape(s: String): String

getGraphStrings

fun getGraphStrings(tokenStream: TokenStream): MutableSet<String>

Returns all paths accepted by the token stream graph produced by the already initialized [ ].

fun getGraphStrings(analyzer: Analyzer, text: String): MutableSet<String>

Returns all paths accepted by the token stream graph produced by analyzing text with the provided analyzer. The tokens CharTermAttribute values are concatenated, and separated with space.

newAttributeFactory

@JvmOverloads

fun newAttributeFactory(random: Random = LuceneTestCase.random()): AttributeFactory

Returns a random AttributeFactory impl

toString

fun toString(analyzer: Analyzer, text: String): String

Returns a String summary of the tokens this analyzer produces on this text

whitespaceMockTokenizer

@JvmStatic

fun whitespaceMockTokenizer(input: Reader): MockTokenizer