azalea/kotlin-fork
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

[WASM] Regex std implementation

Browse Source
This commit is contained in:
Igor Yakovlev
2021-11-26 15:23:40 +01:00
committed by TeamCityServer
parent 4f9b54da26
commit d55e16a030
78 changed files with 3403 additions and 1286 deletions
Download Patch File Download Diff File Expand all files Collapse all files
libraries/stdlib/wasm/src/kotlin/Text.kt
-972
View File
@@ -1,972 +0,0 @@
/*
* Copyright 2010-2021 JetBrains s.r.o. and Kotlin Programming Language contributors.
* Use of this source code is governed by the Apache 2.0 license that can be found in the license/LICENSE.txt file.
*/
package kotlin.text
import kotlin.math.abs
actual class Regex {
actual constructor(pattern: String) { TODO("Wasm stdlib: Text") }
actual constructor(pattern: String, option: RegexOption) { TODO("Wasm stdlib: Text") }
actual constructor(pattern: String, options: Set<RegexOption>) { TODO("Wasm stdlib: Text") }
actual val pattern: String = TODO("Wasm stdlib: Text")
actual val options: Set<RegexOption> = TODO("Wasm stdlib: Text")
actual fun matchEntire(input: CharSequence): MatchResult? = TODO("Wasm stdlib: Text")
actual infix fun matches(input: CharSequence): Boolean = TODO("Wasm stdlib: Text")
actual fun containsMatchIn(input: CharSequence): Boolean = TODO("Wasm stdlib: Text")
actual fun replace(input: CharSequence, replacement: String): String = TODO("Wasm stdlib: Text")
actual fun replace(input: CharSequence, transform: (MatchResult) -> CharSequence): String = TODO("Wasm stdlib: Text")
actual fun replaceFirst(input: CharSequence, replacement: String): String = TODO("Wasm stdlib: Text")
actual fun matchAt(input: CharSequence, index: Int): MatchResult? = TODO("Wasm stdlib: Text")
actual fun matchesAt(input: CharSequence, index: Int): Boolean = TODO("Wasm stdlib: Text")
/**
* Returns the first match of a regular expression in the [input], beginning at the specified [startIndex].
*
* @param startIndex An index to start search with, by default 0. Must be not less than zero and not greater than `input.length()`
* @return An instance of [MatchResult] if match was found or `null` otherwise.
* @sample samples.text.Regexps.find
*/
actual fun find(input: CharSequence, startIndex: Int): MatchResult? = TODO("Wasm stdlib: Text")
/**
* Returns a sequence of all occurrences of a regular expression within the [input] string, beginning at the specified [startIndex].
*
* @sample samples.text.Regexps.findAll
*/
actual fun findAll(input: CharSequence, startIndex: Int): Sequence<MatchResult> = TODO("Wasm stdlib: Text")
/**
* Splits the [input] CharSequence to a list of strings around matches of this regular expression.
*
* @param limit Non-negative value specifying the maximum number of substrings the string can be split to.
* Zero by default means no limit is set.
*/
actual fun split(input: CharSequence, limit: Int): List<String> = TODO("Wasm stdlib: Text")
/**
* Splits the [input] CharSequence to a sequence of strings around matches of this regular expression.
*
* @param limit Non-negative value specifying the maximum number of substrings the string can be split to.
* Zero by default means no limit is set.
* @sample samples.text.Regexps.splitToSequence
*/
public actual fun splitToSequence(input: CharSequence, limit: Int): Sequence<String> = TODO("Wasm stdlib: Text")
actual companion object {
actual fun fromLiteral(literal: String): Regex = TODO("Wasm stdlib: Text")
actual fun escape(literal: String): String = TODO("Wasm stdlib: Text")
actual fun escapeReplacement(literal: String): String = TODO("Wasm stdlib: Text")
}
}
actual class MatchGroup {
actual val value: String = TODO("Wasm stdlib: Text")
}
actual enum class RegexOption {
IGNORE_CASE,
MULTILINE
}
// From char.kt
/**
* Returns `true` if this character is a Unicode high-surrogate code unit (also known as leading-surrogate code unit).
*/
public actual fun Char.isHighSurrogate(): Boolean = this in Char.MIN_HIGH_SURROGATE..Char.MAX_HIGH_SURROGATE
/**
* Returns `true` if this character is a Unicode low-surrogate code unit (also known as trailing-surrogate code unit).
*/
public actual fun Char.isLowSurrogate(): Boolean = this in Char.MIN_LOW_SURROGATE..Char.MAX_LOW_SURROGATE
/**
* Converts this character to lower case using Unicode mapping rules of the invariant locale.
*/
@Deprecated("Use lowercaseChar() instead.", ReplaceWith("lowercaseChar()"))
@DeprecatedSinceKotlin(warningSince = "1.5")
public actual fun Char.toLowerCase(): Char = lowercaseCharImpl()
/**
* Converts this character to lower case using Unicode mapping rules of the invariant locale.
*
* This function performs one-to-one character mapping.
* To support one-to-many character mapping use the [lowercase] function.
* If this character has no mapping equivalent, the character itself is returned.
*
* @sample samples.text.Chars.lowercase
*/
@SinceKotlin("1.5")
@WasExperimental(ExperimentalStdlibApi::class)
public actual fun Char.lowercaseChar(): Char = lowercaseCharImpl()
/**
* Converts this character to lower case using Unicode mapping rules of the invariant locale.
*
* This function supports one-to-many character mapping, thus the length of the returned string can be greater than one.
* For example, `'\u0130'.lowercase()` returns `"\u0069\u0307"`,
* where `'\u0130'` is the LATIN CAPITAL LETTER I WITH DOT ABOVE character (`İ`).
* If this character has no lower case mapping, the result of `toString()` of this char is returned.
*
* @sample samples.text.Chars.lowercase
*/
@SinceKotlin("1.5")
@WasExperimental(ExperimentalStdlibApi::class)
public actual fun Char.lowercase(): String = lowercaseImpl()
/**
* Converts this character to upper case using Unicode mapping rules of the invariant locale.
*/
@Deprecated("Use uppercaseChar() instead.", ReplaceWith("uppercaseChar()"))
@DeprecatedSinceKotlin(warningSince = "1.5")
public actual fun Char.toUpperCase(): Char = uppercaseCharImpl()
/**
* Converts this character to upper case using Unicode mapping rules of the invariant locale.
*
* This function performs one-to-one character mapping.
* To support one-to-many character mapping use the [uppercase] function.
* If this character has no mapping equivalent, the character itself is returned.
*
* @sample samples.text.Chars.uppercase
*/
@SinceKotlin("1.5")
@WasExperimental(ExperimentalStdlibApi::class)
public actual fun Char.uppercaseChar(): Char = uppercaseCharImpl()
/**
* Converts this character to upper case using Unicode mapping rules of the invariant locale.
*
* This function supports one-to-many character mapping, thus the length of the returned string can be greater than one.
* For example, `'\uFB00'.uppercase()` returns `"\u0046\u0046"`,
* where `'\uFB00'` is the LATIN SMALL LIGATURE FF character (`ff`).
* If this character has no upper case mapping, the result of `toString()` of this char is returned.
*
* @sample samples.text.Chars.uppercase
*/
@SinceKotlin("1.5")
@WasExperimental(ExperimentalStdlibApi::class)
public actual fun Char.uppercase(): String = uppercaseImpl()
/**
* Converts this character to title case using Unicode mapping rules of the invariant locale.
*
* This function performs one-to-one character mapping.
* To support one-to-many character mapping use the [titlecase] function.
* If this character has no mapping equivalent, the result of calling [uppercaseChar] is returned.
*
* @sample samples.text.Chars.titlecase
*/
@SinceKotlin("1.5")
public actual fun Char.titlecaseChar(): Char = titlecaseCharImpl()
/**
* Returns the Unicode general category of this character.
*/
@SinceKotlin("1.5")
public actual val Char.category: CharCategory
get() = CharCategory.valueOf(getCategoryValue())
/**
* Returns `true` if this character (Unicode code point) is defined in Unicode.
*
* A character is considered to be defined in Unicode if its [category] is not [CharCategory.UNASSIGNED].
*/
@SinceKotlin("1.5")
public actual fun Char.isDefined(): Boolean {
if (this < '\u0080') {
return true
}
return getCategoryValue() != CharCategory.UNASSIGNED.value
}
/**
* Returns `true` if this character is a letter.
*
* A character is considered to be a letter if its [category] is [CharCategory.UPPERCASE_LETTER],
* [CharCategory.LOWERCASE_LETTER], [CharCategory.TITLECASE_LETTER], [CharCategory.MODIFIER_LETTER], or [CharCategory.OTHER_LETTER].
*
* @sample samples.text.Chars.isLetter
*/
@SinceKotlin("1.5")
public actual fun Char.isLetter(): Boolean {
if (this in 'a'..'z' || this in 'A'..'Z') {
return true
}
if (this < '\u0080') {
return false
}
return isLetterImpl()
}
/**
* Returns `true` if this character is a letter or digit.
*
* @see isLetter
* @see isDigit
*
* @sample samples.text.Chars.isLetterOrDigit
*/
@SinceKotlin("1.5")
public actual fun Char.isLetterOrDigit(): Boolean {
if (this in 'a'..'z' || this in 'A'..'Z' || this in '0'..'9') {
return true
}
if (this < '\u0080') {
return false
}
return isDigit() || isLetter()
}
/**
* Returns `true` if this character is a digit.
*
* A character is considered to be a digit if its [category] is [CharCategory.DECIMAL_DIGIT_NUMBER].
*
* @sample samples.text.Chars.isDigit
*/
@SinceKotlin("1.5")
public actual fun Char.isDigit(): Boolean {
if (this in '0'..'9') {
return true
}
if (this < '\u0080') {
return false
}
return isDigitImpl()
}
/**
* Returns `true` if this character is an upper case letter.
*
* A character is considered to be an upper case letter if its [category] is [CharCategory.UPPERCASE_LETTER].
*
* @sample samples.text.Chars.isUpperCase
*/
@SinceKotlin("1.5")
public actual fun Char.isUpperCase(): Boolean {
if (this in 'A'..'Z') {
return true
}
if (this < '\u0080') {
return false
}
return isUpperCaseImpl()
}
/**
* Returns `true` if this character is a lower case letter.
*
* A character is considered to be a lower case letter if its [category] is [CharCategory.LOWERCASE_LETTER].
*
* @sample samples.text.Chars.isLowerCase
*/
@SinceKotlin("1.5")
public actual fun Char.isLowerCase(): Boolean {
if (this in 'a'..'z') {
return true
}
if (this < '\u0080') {
return false
}
return isLowerCaseImpl()
}
/**
* Returns `true` if this character is a title case letter.
*
* A character is considered to be a title case letter if its [category] is [CharCategory.TITLECASE_LETTER].
*
* @sample samples.text.Chars.isTitleCase
*/
@SinceKotlin("1.5")
public actual fun Char.isTitleCase(): Boolean {
if (this < '\u0080') {
return false
}
return getCategoryValue() == CharCategory.TITLECASE_LETTER.value
}
/**
* Returns `true` if this character is an ISO control character.
*
* A character is considered to be an ISO control character if its [category] is [CharCategory.CONTROL].
*
* @sample samples.text.Chars.isISOControl
*/
@SinceKotlin("1.5")
public actual fun Char.isISOControl(): Boolean {
return this <= '\u001F' || this in '\u007F'..'\u009F'
}
/**
* Determines whether a character is whitespace according to the Unicode standard.
* Returns `true` if the character is whitespace.
*
* @sample samples.text.Chars.isWhitespace
*/
public actual fun Char.isWhitespace(): Boolean = isWhitespaceImpl()
// From string.kt
/**
* Converts the characters in the specified array to a string.
*/
@SinceKotlin("1.2")
@Deprecated("Use CharArray.concatToString() instead", ReplaceWith("chars.concatToString()"))
@DeprecatedSinceKotlin(warningSince = "1.4", errorSince = "1.5")
public actual fun String(chars: CharArray): String {
var result = ""
for (char in chars) {
result += char
}
return result
}
/**
* Converts the characters from a portion of the specified array to a string.
*
* @throws IndexOutOfBoundsException if either [offset] or [length] are less than zero
* or `offset + length` is out of [chars] array bounds.
*/
@SinceKotlin("1.2")
@Deprecated("Use CharArray.concatToString(startIndex, endIndex) instead", ReplaceWith("chars.concatToString(offset, offset + length)"))
@DeprecatedSinceKotlin(warningSince = "1.4", errorSince = "1.5")
public actual fun String(chars: CharArray, offset: Int, length: Int): String {
if (offset < 0 || length < 0 || chars.size - offset < length)
throw IndexOutOfBoundsException("size: ${chars.size}; offset: $offset; length: $length")
var result = ""
for (index in offset until offset + length) {
result += chars[index]
}
return result
}
/**
* Concatenates characters in this [CharArray] into a String.
*/
@SinceKotlin("1.4")
@WasExperimental(ExperimentalStdlibApi::class)
public actual fun CharArray.concatToString(): String {
var result = ""
for (char in this) {
result += char
}
return result
}
/**
* Concatenates characters in this [CharArray] or its subrange into a String.
*
* @param startIndex the beginning (inclusive) of the subrange of characters, 0 by default.
* @param endIndex the end (exclusive) of the subrange of characters, size of this array by default.
*
* @throws IndexOutOfBoundsException if [startIndex] is less than zero or [endIndex] is greater than the size of this array.
* @throws IllegalArgumentException if [startIndex] is greater than [endIndex].
*/
@SinceKotlin("1.4")
@WasExperimental(ExperimentalStdlibApi::class)
@Suppress("ACTUAL_FUNCTION_WITH_DEFAULT_ARGUMENTS")
public actual fun CharArray.concatToString(startIndex: Int = 0, endIndex: Int = this.size): String {
AbstractList.checkBoundsIndexes(startIndex, endIndex, this.size)
var result = ""
for (index in startIndex until endIndex) {
result += this[index]
}
return result
}
/**
* Returns a [CharArray] containing characters of this string.
*/
@SinceKotlin("1.4")
@WasExperimental(ExperimentalStdlibApi::class)
public actual fun String.toCharArray(): CharArray {
return CharArray(length) { get(it) }
}
/**
* Returns a [CharArray] containing characters of this string or its substring.
*
* @param startIndex the beginning (inclusive) of the substring, 0 by default.
* @param endIndex the end (exclusive) of the substring, length of this string by default.
*
* @throws IndexOutOfBoundsException if [startIndex] is less than zero or [endIndex] is greater than the length of this string.
* @throws IllegalArgumentException if [startIndex] is greater than [endIndex].
*/
@SinceKotlin("1.4")
@WasExperimental(ExperimentalStdlibApi::class)
@Suppress("ACTUAL_FUNCTION_WITH_DEFAULT_ARGUMENTS")
public actual fun String.toCharArray(startIndex: Int = 0, endIndex: Int = this.length): CharArray {
AbstractList.checkBoundsIndexes(startIndex, endIndex, length)
return CharArray(endIndex - startIndex) { get(startIndex + it) }
}
/**
* Decodes a string from the bytes in UTF-8 encoding in this array.
*
* Malformed byte sequences are replaced by the replacement char `\uFFFD`.
*/
@SinceKotlin("1.4")
@WasExperimental(ExperimentalStdlibApi::class)
public actual fun ByteArray.decodeToString(): String {
return decodeUtf8(this, 0, size, false)
}
/**
* Decodes a string from the bytes in UTF-8 encoding in this array or its subrange.
*
* @param startIndex the beginning (inclusive) of the subrange to decode, 0 by default.
* @param endIndex the end (exclusive) of the subrange to decode, size of this array by default.
* @param throwOnInvalidSequence specifies whether to throw an exception on malformed byte sequence or replace it by the replacement char `\uFFFD`.
*
* @throws IndexOutOfBoundsException if [startIndex] is less than zero or [endIndex] is greater than the size of this array.
* @throws IllegalArgumentException if [startIndex] is greater than [endIndex].
* @throws CharacterCodingException if the byte array contains malformed UTF-8 byte sequence and [throwOnInvalidSequence] is true.
*/
@SinceKotlin("1.4")
@WasExperimental(ExperimentalStdlibApi::class)
@Suppress("ACTUAL_FUNCTION_WITH_DEFAULT_ARGUMENTS")
public actual fun ByteArray.decodeToString(
startIndex: Int = 0,
endIndex: Int = this.size,
throwOnInvalidSequence: Boolean = false
): String {
AbstractList.checkBoundsIndexes(startIndex, endIndex, this.size)
return decodeUtf8(this, startIndex, endIndex, throwOnInvalidSequence)
}
/**
* Encodes this string to an array of bytes in UTF-8 encoding.
*
* Any malformed char sequence is replaced by the replacement byte sequence.
*/
@SinceKotlin("1.4")
@WasExperimental(ExperimentalStdlibApi::class)
public actual fun String.encodeToByteArray(): ByteArray {
return encodeUtf8(this, 0, length, false)
}
/**
* Encodes this string or its substring to an array of bytes in UTF-8 encoding.
*
* @param startIndex the beginning (inclusive) of the substring to encode, 0 by default.
* @param endIndex the end (exclusive) of the substring to encode, length of this string by default.
* @param throwOnInvalidSequence specifies whether to throw an exception on malformed char sequence or replace.
*
* @throws IndexOutOfBoundsException if [startIndex] is less than zero or [endIndex] is greater than the length of this string.
* @throws IllegalArgumentException if [startIndex] is greater than [endIndex].
* @throws CharacterCodingException if this string contains malformed char sequence and [throwOnInvalidSequence] is true.
*/
@SinceKotlin("1.4")
@WasExperimental(ExperimentalStdlibApi::class)
@Suppress("ACTUAL_FUNCTION_WITH_DEFAULT_ARGUMENTS")
public actual fun String.encodeToByteArray(
startIndex: Int = 0,
endIndex: Int = this.length,
throwOnInvalidSequence: Boolean = false
): ByteArray {
AbstractList.checkBoundsIndexes(startIndex, endIndex, length)
return encodeUtf8(this, startIndex, endIndex, throwOnInvalidSequence)
}
/**
* Returns a substring of this string that starts at the specified [startIndex] and continues to the end of the string.
*/
public actual fun String.substring(startIndex: Int): String =
subSequence(startIndex, this.length) as String
/**
* Returns the substring of this string starting at the [startIndex] and ending right before the [endIndex].
*
* @param startIndex the start index (inclusive).
* @param endIndex the end index (exclusive).
*/
public actual fun String.substring(startIndex: Int, endIndex: Int): String =
subSequence(startIndex, endIndex) as String
/**
* Returns a copy of this string converted to upper case using the rules of the default locale.
*/
@Deprecated("Use uppercase() instead.", ReplaceWith("uppercase()"))
@DeprecatedSinceKotlin(warningSince = "1.5")
public actual fun String.toUpperCase(): String = uppercase()
/**
* Returns a copy of this string converted to upper case using Unicode mapping rules of the invariant locale.
*
* This function supports one-to-many and many-to-one character mapping,
* thus the length of the returned string can be different from the length of the original string.
*
* @sample samples.text.Strings.uppercase
*/
@SinceKotlin("1.5")
public actual fun String.uppercase(): String = uppercaseImpl()
/**
* Returns a copy of this string converted to lower case using the rules of the default locale.
*/
@Deprecated("Use lowercase() instead.", ReplaceWith("lowercase()"))
@DeprecatedSinceKotlin(warningSince = "1.5")
public actual fun String.toLowerCase(): String = lowercase()
/**
* Returns a copy of this string converted to lower case using Unicode mapping rules of the invariant locale.
*
* This function supports one-to-many and many-to-one character mapping,
* thus the length of the returned string can be different from the length of the original string.
*
* @sample samples.text.Strings.lowercase
*/
@SinceKotlin("1.5")
public actual fun String.lowercase(): String = lowercaseImpl()
/**
* Returns a copy of this string having its first letter titlecased using the rules of the default locale,
* or the original string if it's empty or already starts with a title case letter.
*
* The title case of a character is usually the same as its upper case with several exceptions.
* The particular list of characters with the special title case form depends on the underlying platform.
*
* @sample samples.text.Strings.capitalize
*/
@Deprecated("Use replaceFirstChar instead.", ReplaceWith("replaceFirstChar { if (it.isLowerCase()) it.titlecase() else it.toString() }"))
@DeprecatedSinceKotlin(warningSince = "1.5")
public actual fun String.capitalize(): String = replaceFirstChar(Char::uppercaseChar)
/**
* Returns a copy of this string having its first letter lowercased using the rules of the default locale,
* or the original string if it's empty or already starts with a lower case letter.
*
* @sample samples.text.Strings.decapitalize
*/
@Deprecated("Use replaceFirstChar instead.", ReplaceWith("replaceFirstChar { it.lowercase() }"))
@DeprecatedSinceKotlin(warningSince = "1.5")
public actual fun String.decapitalize(): String = replaceFirstChar(Char::lowercaseChar)
/**
* Returns a string containing this char sequence repeated [n] times.
* @throws [IllegalArgumentException] when n < 0.
* @sample samples.text.Strings.repeat
*/
public actual fun CharSequence.repeat(n: Int): String {
require(n >= 0) { "Count 'n' must be non-negative, but was $n." }
return when (n) {
0 -> ""
1 -> this.toString()
else -> {
var result = ""
if (!isEmpty()) {
var s = this.toString()
var count = n
while (true) {
if ((count and 1) == 1) {
result += s
}
count = count ushr 1
if (count == 0) {
break
}
s += s
}
}
return result
}
}
}
/**
* Returns a new string with all occurrences of [oldChar] replaced with [newChar].
*/
@Suppress("ACTUAL_FUNCTION_WITH_DEFAULT_ARGUMENTS")
public actual fun String.replace(oldChar: Char, newChar: Char, ignoreCase: Boolean = false): String {
return buildString(length) {
this@replace.forEach { c ->
append(if (c.equals(oldChar, ignoreCase)) newChar else c)
}
}
}
/**
* Returns a new string obtained by replacing all occurrences of the [oldValue] substring in this string
* with the specified [newValue] string.
*/
@Suppress("ACTUAL_FUNCTION_WITH_DEFAULT_ARGUMENTS")
public actual fun String.replace(oldValue: String, newValue: String, ignoreCase: Boolean = false): String {
run {
var occurrenceIndex: Int = indexOf(oldValue, 0, ignoreCase)
// FAST PATH: no match
if (occurrenceIndex < 0) return this
val oldValueLength = oldValue.length
val searchStep = oldValueLength.coerceAtLeast(1)
val newLengthHint = length - oldValueLength + newValue.length
if (newLengthHint < 0) throw OutOfMemoryError()
val stringBuilder = StringBuilder(newLengthHint)
var i = 0
do {
stringBuilder.append(this, i, occurrenceIndex).append(newValue)
i = occurrenceIndex + oldValueLength
if (occurrenceIndex >= length) break
occurrenceIndex = indexOf(oldValue, occurrenceIndex + searchStep, ignoreCase)
} while (occurrenceIndex > 0)
return stringBuilder.append(this, i, length).toString()
}
}
/**
* Returns a new string with the first occurrence of [oldChar] replaced with [newChar].
*/
@Suppress("ACTUAL_FUNCTION_WITH_DEFAULT_ARGUMENTS")
public actual fun String.replaceFirst(oldChar: Char, newChar: Char, ignoreCase: Boolean = false): String {
val index = indexOf(oldChar, ignoreCase = ignoreCase)
return if (index < 0) this else this.replaceRange(index, index + 1, newChar.toString())
}
/**
* Returns a new string obtained by replacing the first occurrence of the [oldValue] substring in this string
* with the specified [newValue] string.
*/
@Suppress("ACTUAL_FUNCTION_WITH_DEFAULT_ARGUMENTS")
public actual fun String.replaceFirst(oldValue: String, newValue: String, ignoreCase: Boolean = false): String {
val index = indexOf(oldValue, ignoreCase = ignoreCase)
return if (index < 0) this else this.replaceRange(index, index + oldValue.length, newValue)
}
/**
* Returns `true` if this string is equal to [other], optionally ignoring character case.
*
* Two strings are considered to be equal if they have the same length and the same character at the same index.
* If [ignoreCase] is true, the result of `Char.uppercaseChar().lowercaseChar()` on each character is compared.
*
* @param ignoreCase `true` to ignore character case when comparing strings. By default `false`.
*/
@Suppress("ACTUAL_FUNCTION_WITH_DEFAULT_ARGUMENTS")
public actual fun String?.equals(other: String?, ignoreCase: Boolean = false): Boolean {
if (this == null) return other == null
if (other == null) return false
if (!ignoreCase) return this == other
if (this.length != other.length) return false
for (index in 0 until this.length) {
val thisChar = this[index]
val otherChar = other[index]
if (!thisChar.equals(otherChar, ignoreCase)) {
return false
}
}
return true
}
/**
* Compares two strings lexicographically, optionally ignoring case differences.
*
* If [ignoreCase] is true, the result of `Char.uppercaseChar().lowercaseChar()` on each character is compared.
*/
@SinceKotlin("1.2")
@Suppress("ACTUAL_FUNCTION_WITH_DEFAULT_ARGUMENTS")
public actual fun String.compareTo(other: String, ignoreCase: Boolean = false): Int {
if (ignoreCase) {
val n1 = this.length
val n2 = other.length
val min = minOf(n1, n2)
if (min == 0) return n1 - n2
for (index in 0 until min) {
var thisChar = this[index]
var otherChar = other[index]
if (thisChar != otherChar) {
thisChar = thisChar.uppercaseChar()
otherChar = otherChar.uppercaseChar()
if (thisChar != otherChar) {
thisChar = thisChar.lowercaseChar()
otherChar = otherChar.lowercaseChar()
if (thisChar != otherChar) {
return thisChar.compareTo(otherChar)
}
}
}
}
return n1 - n2
} else {
return compareTo(other)
}
}
/**
* Returns `true` if the contents of this char sequence are equal to the contents of the specified [other],
* i.e. both char sequences contain the same number of the same characters in the same order.
*
* @sample samples.text.Strings.contentEquals
*/
@SinceKotlin("1.5")
public actual infix fun CharSequence?.contentEquals(other: CharSequence?): Boolean = contentEqualsImpl(other)
/**
* Returns `true` if the contents of this char sequence are equal to the contents of the specified [other], optionally ignoring case difference.
*
* @param ignoreCase `true` to ignore character case when comparing contents.
*
* @sample samples.text.Strings.contentEquals
*/
@SinceKotlin("1.5")
public actual fun CharSequence?.contentEquals(other: CharSequence?, ignoreCase: Boolean): Boolean {
return if (ignoreCase)
this.contentEqualsIgnoreCaseImpl(other)
else
this.contentEqualsImpl(other)
}
/**
* Returns `true` if this string starts with the specified prefix.
*/
@Suppress("ACTUAL_FUNCTION_WITH_DEFAULT_ARGUMENTS")
public actual fun String.startsWith(prefix: String, ignoreCase: Boolean = false): Boolean =
regionMatches(0, prefix, 0, prefix.length, ignoreCase)
/**
* Returns `true` if a substring of this string starting at the specified offset [startIndex] starts with the specified prefix.
*/
@Suppress("ACTUAL_FUNCTION_WITH_DEFAULT_ARGUMENTS")
public actual fun String.startsWith(prefix: String, startIndex: Int, ignoreCase: Boolean = false): Boolean =
regionMatches(startIndex, prefix, 0, prefix.length, ignoreCase)
/**
* Returns `true` if this string ends with the specified suffix.
*/
@Suppress("ACTUAL_FUNCTION_WITH_DEFAULT_ARGUMENTS")
public actual fun String.endsWith(suffix: String, ignoreCase: Boolean = false): Boolean =
regionMatches(length - suffix.length, suffix, 0, suffix.length, ignoreCase)
// From stringsCode.kt
/**
* Returns `true` if this string is empty or consists solely of whitespace characters.
*
* @sample samples.text.Strings.stringIsBlank
*/
public actual fun CharSequence.isBlank(): Boolean = length == 0 || indices.all { this[it].isWhitespace() }
/**
* Returns `true` if the specified range in this char sequence is equal to the specified range in another char sequence.
* @param thisOffset the start offset in this char sequence of the substring to compare.
* @param other the string against a substring of which the comparison is performed.
* @param otherOffset the start offset in the other char sequence of the substring to compare.
* @param length the length of the substring to compare.
*/
actual fun CharSequence.regionMatches(
thisOffset: Int,
other: CharSequence,
otherOffset: Int,
length: Int,
ignoreCase: Boolean
): Boolean {
if ((otherOffset < 0) || (thisOffset < 0) || (thisOffset > this.length - length) || (otherOffset > other.length - length)) {
return false
}
for (index in 0 until length) {
if (!this[thisOffset + index].equals(other[otherOffset + index], ignoreCase))
return false
}
return true
}
private val STRING_CASE_INSENSITIVE_ORDER = Comparator<String> { a, b -> a.compareTo(b, ignoreCase = true) }
/**
* A Comparator that orders strings ignoring character case.
*
* Note that this Comparator does not take locale into account,
* and will result in an unsatisfactory ordering for certain locales.
*/
@SinceKotlin("1.2")
public actual val String.Companion.CASE_INSENSITIVE_ORDER: Comparator<String>
get() = STRING_CASE_INSENSITIVE_ORDER
/**
* Returns `true` if the content of this string is equal to the word "true", ignoring case, and `false` otherwise.
*/
@Deprecated("Use Kotlin compiler 1.4 to avoid deprecation warning.")
@DeprecatedSinceKotlin(hiddenSince = "1.4")
@kotlin.internal.InlineOnly
actual fun String.toBoolean(): Boolean = this.toBoolean()
/**
* Returns `true` if the contents of this string is equal to the word "true", ignoring case, and `false` otherwise.
*
* There are also strict versions of the function available on non-nullable String, [toBooleanStrict] and [toBooleanStrictOrNull].
*/
actual fun String?.toBoolean(): Boolean = this != null && this.lowercase() == "true"
/**
* Parses the string as a signed [Byte] number and returns the result.
* @throws NumberFormatException if the string is not a valid representation of a number.
*/
actual fun String.toByte(): Byte = toByteOrNull() ?: numberFormatError(this)
/**
* Parses the string as a signed [Byte] number and returns the result.
* @throws NumberFormatException if the string is not a valid representation of a number.
* @throws IllegalArgumentException when [radix] is not a valid radix for string to number conversion.
*/
public actual fun String.toByte(radix: Int): Byte = toByteOrNull(radix) ?: numberFormatError(this)
/**
* Parses the string as a [Short] number and returns the result.
* @throws NumberFormatException if the string is not a valid representation of a number.
*/
public actual fun String.toShort(): Short = toShortOrNull() ?: numberFormatError(this)
/**
* Parses the string as a [Short] number and returns the result.
* @throws NumberFormatException if the string is not a valid representation of a number.
* @throws IllegalArgumentException when [radix] is not a valid radix for string to number conversion.
*/
public actual fun String.toShort(radix: Int): Short = toShortOrNull(radix) ?: numberFormatError(this)
/**
* Parses the string as an [Int] number and returns the result.
* @throws NumberFormatException if the string is not a valid representation of a number.
*/
public actual fun String.toInt(): Int = toIntOrNull() ?: numberFormatError(this)
/**
* Parses the string as an [Int] number and returns the result.
* @throws NumberFormatException if the string is not a valid representation of a number.
* @throws IllegalArgumentException when [radix] is not a valid radix for string to number conversion.
*/
public actual fun String.toInt(radix: Int): Int = toIntOrNull(radix) ?: numberFormatError(this)
/**
* Parses the string as a [Long] number and returns the result.
* @throws NumberFormatException if the string is not a valid representation of a number.
*/
public actual fun String.toLong(): Long = toLongOrNull() ?: numberFormatError(this)
/**
* Parses the string as a [Long] number and returns the result.
* @throws NumberFormatException if the string is not a valid representation of a number.
* @throws IllegalArgumentException when [radix] is not a valid radix for string to number conversion.
*/
public actual fun String.toLong(radix: Int): Long = toLongOrNull(radix) ?: numberFormatError(this)
/**
* Parses the string as a [Double] number and returns the result.
* @throws NumberFormatException if the string is not a valid representation of a number.
*/
public actual fun String.toDouble(): Double = kotlin.text.parseDouble(this)
/**
* Parses the string as a [Float] number and returns the result.
* @throws NumberFormatException if the string is not a valid representation of a number.
*/
public actual fun String.toFloat(): Float = toDouble() as Float
/**
* Parses the string as a [Float] number and returns the result
* or `null` if the string is not a valid representation of a number.
*/
public actual fun String.toFloatOrNull(): Float? = toDoubleOrNull() as Float?
/**
* Parses the string as a [Double] number and returns the result
* or `null` if the string is not a valid representation of a number.
*/
public actual fun String.toDoubleOrNull(): Double? {
try {
return toDouble()
} catch (e: NumberFormatException) {
return null
}
}
/**
* Returns a string representation of this [Byte] value in the specified [radix].
*
* @throws IllegalArgumentException when [radix] is not a valid radix for number to string conversion.
*/
@SinceKotlin("1.2")
public actual fun Byte.toString(radix: Int): String = this.toLong().toString(radix)
/**
* Returns a string representation of this [Short] value in the specified [radix].
*
* @throws IllegalArgumentException when [radix] is not a valid radix for number to string conversion.
*/
@SinceKotlin("1.2")
public actual fun Short.toString(radix: Int): String = this.toLong().toString(radix)
/**
* Returns a string representation of this [Int] value in the specified [radix].
*
* @throws IllegalArgumentException when [radix] is not a valid radix for number to string conversion.
*/
@SinceKotlin("1.2")
actual fun Int.toString(radix: Int): String = toLong().toString(radix)
/**
* Returns a string representation of this [Long] value in the specified [radix].
*
* @throws IllegalArgumentException when [radix] is not a valid radix for number to string conversion.
*/
@SinceKotlin("1.2")
actual fun Long.toString(radix: Int): String {
checkRadix(radix)
fun Long.getChar() = toInt().let { if (it < 10) '0' + it else 'a' + (it - 10) }
if (radix == 10) return toString()
if (this in 0 until radix) return getChar().toString()
val isNegative = this < 0
val buffer = CharArray(Long.SIZE_BITS + 1)
var currentBufferIndex= buffer.lastIndex
var current: Long = this
while(current != 0L) {
buffer[currentBufferIndex] = abs(current % radix).getChar()
current /= radix
currentBufferIndex--
}
if (isNegative) {
buffer[currentBufferIndex] = '-'
currentBufferIndex--
}
return buffer.concatToString(currentBufferIndex + 1)
}
@PublishedApi
internal actual fun checkRadix(radix: Int): Int {
if (radix !in Char.MIN_RADIX..Char.MAX_RADIX) {
throw IllegalArgumentException("radix $radix was not in valid range ${Char.MIN_RADIX..Char.MAX_RADIX}")
}
return radix
}
internal actual fun digitOf(char: Char, radix: Int): Int = when {
char >= '0' && char <= '9' -> char - '0'
char >= 'A' && char <= 'Z' -> char - 'A' + 10
char >= 'a' && char <= 'z' -> char - 'a' + 10
char < '\u0080' -> -1
char >= '\uFF21' && char <= '\uFF3A' -> char - '\uFF21' + 10 // full-width latin capital letter
char >= '\uFF41' && char <= '\uFF5A' -> char - '\uFF41' + 10 // full-width latin small letter
else -> char.digitToIntImpl()
}.let { if (it >= radix) -1 else it }
libraries/stdlib/wasm/src/kotlin/text/Appendable.kt
-37
View File
@@ -1,37 +0,0 @@
/*
* Copyright 2010-2020 JetBrains s.r.o. and Kotlin Programming Language contributors.
* Use of this source code is governed by the Apache 2.0 license that can be found in the license/LICENSE.txt file.
*/
package kotlin.text
/**
* An object to which char sequences and values can be appended.
*/
actual interface Appendable {
/**
* Appends the specified character [value] to this Appendable and returns this instance.
*
* @param value the character to append.
*/
actual fun append(value: Char): Appendable
/**
* Appends the specified character sequence [value] to this Appendable and returns this instance.
*
* @param value the character sequence to append. If [value] is `null`, then the four characters `"null"` are appended to this Appendable.
*/
actual fun append(value: CharSequence?): Appendable
/**
* Appends a subsequence of the specified character sequence [value] to this Appendable and returns this instance.
*
* @param value the character sequence from which a subsequence is appended. If [value] is `null`,
* then characters are appended as if [value] contained the four characters `"null"`.
* @param startIndex the beginning (inclusive) of the subsequence to append.
* @param endIndex the end (exclusive) of the subsequence to append.
*
* @throws IndexOutOfBoundsException or [IllegalArgumentException] when [startIndex] or [endIndex] is out of range of the [value] character sequence indices or when `startIndex > endIndex`.
*/
actual fun append(value: CharSequence?, startIndex: Int, endIndex: Int): Appendable
}
libraries/stdlib/wasm/src/kotlin/text/CharCategoryWasm.kt
-176
View File
@@ -1,176 +0,0 @@
/*
* Copyright 2010-2021 JetBrains s.r.o. and Kotlin Programming Language contributors.
* Use of this source code is governed by the Apache 2.0 license that can be found in the license/LICENSE.txt file.
*/
package kotlin.text
/**
* Represents the character general category in the Unicode specification.
*/
public actual enum class CharCategory(public val value: Int, public actual val code: String) {
/**
* General category "Cn" in the Unicode specification.
*/
UNASSIGNED(0, "Cn"),
/**
* General category "Lu" in the Unicode specification.
*/
UPPERCASE_LETTER(1, "Lu"),
/**
* General category "Ll" in the Unicode specification.
*/
LOWERCASE_LETTER(2, "Ll"),
/**
* General category "Lt" in the Unicode specification.
*/
TITLECASE_LETTER(3, "Lt"),
/**
* General category "Lm" in the Unicode specification.
*/
MODIFIER_LETTER(4, "Lm"),
/**
* General category "Lo" in the Unicode specification.
*/
OTHER_LETTER(5, "Lo"),
/**
* General category "Mn" in the Unicode specification.
*/
NON_SPACING_MARK(6, "Mn"),
/**
* General category "Me" in the Unicode specification.
*/
ENCLOSING_MARK(7, "Me"),
/**
* General category "Mc" in the Unicode specification.
*/
COMBINING_SPACING_MARK(8, "Mc"),
/**
* General category "Nd" in the Unicode specification.
*/
DECIMAL_DIGIT_NUMBER(9, "Nd"),
/**
* General category "Nl" in the Unicode specification.
*/
LETTER_NUMBER(10, "Nl"),
/**
* General category "No" in the Unicode specification.
*/
OTHER_NUMBER(11, "No"),
/**
* General category "Zs" in the Unicode specification.
*/
SPACE_SEPARATOR(12, "Zs"),
/**
* General category "Zl" in the Unicode specification.
*/
LINE_SEPARATOR(13, "Zl"),
/**
* General category "Zp" in the Unicode specification.
*/
PARAGRAPH_SEPARATOR(14, "Zp"),
/**
* General category "Cc" in the Unicode specification.
*/
CONTROL(15, "Cc"),
/**
* General category "Cf" in the Unicode specification.
*/
FORMAT(16, "Cf"),
/**
* General category "Co" in the Unicode specification.
*/
PRIVATE_USE(18, "Co"),
/**
* General category "Cs" in the Unicode specification.
*/
SURROGATE(19, "Cs"),
/**
* General category "Pd" in the Unicode specification.
*/
DASH_PUNCTUATION(20, "Pd"),
/**
* General category "Ps" in the Unicode specification.
*/
START_PUNCTUATION(21, "Ps"),
/**
* General category "Pe" in the Unicode specification.
*/
END_PUNCTUATION(22, "Pe"),
/**
* General category "Pc" in the Unicode specification.
*/
CONNECTOR_PUNCTUATION(23, "Pc"),
/**
* General category "Po" in the Unicode specification.
*/
OTHER_PUNCTUATION(24, "Po"),
/**
* General category "Sm" in the Unicode specification.
*/
MATH_SYMBOL(25, "Sm"),
/**
* General category "Sc" in the Unicode specification.
*/
CURRENCY_SYMBOL(26, "Sc"),
/**
* General category "Sk" in the Unicode specification.
*/
MODIFIER_SYMBOL(27, "Sk"),
/**
* General category "So" in the Unicode specification.
*/
OTHER_SYMBOL(28, "So"),
/**
* General category "Pi" in the Unicode specification.
*/
INITIAL_QUOTE_PUNCTUATION(29, "Pi"),
/**
* General category "Pf" in the Unicode specification.
*/
FINAL_QUOTE_PUNCTUATION(30, "Pf");
/**
* Returns `true` if [char] character belongs to this category.
*/
public actual operator fun contains(char: Char): Boolean = char.getCategoryValue() == this.value
public companion object {
public fun valueOf(category: Int): CharCategory =
when (category) {
in 0..16 -> values()[category]
in 18..30 -> values()[category - 1]
else -> throw IllegalArgumentException("Category #$category is not defined.")
}
}
}
libraries/stdlib/wasm/src/kotlin/text/CharWasm.kt
+31 -2
View File
@@ -5,5 +5,34 @@
package kotlin.text
internal fun Char.Companion.toCodePoint(high: Char, low: Char): Int =
(((high - MIN_HIGH_SURROGATE) shl 10) or (low - MIN_LOW_SURROGATE)) + 0x10000
/**
* Returns `true` if this character is an ISO control character.
*
* A character is considered to be an ISO control character if its [category] is [CharCategory.CONTROL].
*
* @sample samples.text.Chars.isISOControl
*/
@SinceKotlin("1.5")
public actual fun Char.isISOControl(): Boolean {
return this <= '\u001F' || this in '\u007F'..'\u009F'
}
/**
* Returns `true` if this character is a Unicode high-surrogate code unit (also known as leading-surrogate code unit).
*/
public actual fun Char.isHighSurrogate(): Boolean = this in Char.MIN_HIGH_SURROGATE..Char.MAX_HIGH_SURROGATE
/**
* Returns `true` if this character is a Unicode low-surrogate code unit (also known as trailing-surrogate code unit).
*/
public actual fun Char.isLowSurrogate(): Boolean = this in Char.MIN_LOW_SURROGATE..Char.MAX_LOW_SURROGATE
internal actual fun digitOf(char: Char, radix: Int): Int = when {
char >= '0' && char <= '9' -> char - '0'
char >= 'A' && char <= 'Z' -> char - 'A' + 10
char >= 'a' && char <= 'z' -> char - 'a' + 10
char < '\u0080' -> -1
char >= '\uFF21' && char <= '\uFF3A' -> char - '\uFF21' + 10 // full-width latin capital letter
char >= '\uFF41' && char <= '\uFF5A' -> char - '\uFF41' + 10 // full-width latin small letter
else -> char.digitToIntImpl()
}.let { if (it >= radix) -1 else it }
libraries/stdlib/wasm/src/kotlin/text/StringNumberConversionsWasm.kt
+162
View File
@@ -0,0 +1,162 @@
/*
* Copyright 2010-2021 JetBrains s.r.o. and Kotlin Programming Language contributors.
* Use of this source code is governed by the Apache 2.0 license that can be found in the license/LICENSE.txt file.
*/
package kotlin.text
import kotlin.math.abs
/**
* Returns `true` if the content of this string is equal to the word "true", ignoring case, and `false` otherwise.
*/
@Deprecated("Use Kotlin compiler 1.4 to avoid deprecation warning.")
@DeprecatedSinceKotlin(hiddenSince = "1.4")
@kotlin.internal.InlineOnly
actual fun String.toBoolean(): Boolean = this.toBoolean()
/**
* Returns `true` if the contents of this string is equal to the word "true", ignoring case, and `false` otherwise.
*
* There are also strict versions of the function available on non-nullable String, [toBooleanStrict] and [toBooleanStrictOrNull].
*/
actual fun String?.toBoolean(): Boolean = this != null && this.lowercase() == "true"
/**
* Parses the string as a signed [Byte] number and returns the result.
* @throws NumberFormatException if the string is not a valid representation of a number.
*/
actual fun String.toByte(): Byte = toByteOrNull() ?: numberFormatError(this)
/**
* Parses the string as a signed [Byte] number and returns the result.
* @throws NumberFormatException if the string is not a valid representation of a number.
* @throws IllegalArgumentException when [radix] is not a valid radix for string to number conversion.
*/
public actual fun String.toByte(radix: Int): Byte = toByteOrNull(radix) ?: numberFormatError(this)
/**
* Parses the string as a [Short] number and returns the result.
* @throws NumberFormatException if the string is not a valid representation of a number.
*/
public actual fun String.toShort(): Short = toShortOrNull() ?: numberFormatError(this)
/**
* Parses the string as a [Short] number and returns the result.
* @throws NumberFormatException if the string is not a valid representation of a number.
* @throws IllegalArgumentException when [radix] is not a valid radix for string to number conversion.
*/
public actual fun String.toShort(radix: Int): Short = toShortOrNull(radix) ?: numberFormatError(this)
/**
* Parses the string as an [Int] number and returns the result.
* @throws NumberFormatException if the string is not a valid representation of a number.
*/
public actual fun String.toInt(): Int = toIntOrNull() ?: numberFormatError(this)
/**
* Parses the string as an [Int] number and returns the result.
* @throws NumberFormatException if the string is not a valid representation of a number.
* @throws IllegalArgumentException when [radix] is not a valid radix for string to number conversion.
*/
public actual fun String.toInt(radix: Int): Int = toIntOrNull(radix) ?: numberFormatError(this)
/**
* Parses the string as a [Long] number and returns the result.
* @throws NumberFormatException if the string is not a valid representation of a number.
*/
public actual fun String.toLong(): Long = toLongOrNull() ?: numberFormatError(this)
/**
* Parses the string as a [Long] number and returns the result.
* @throws NumberFormatException if the string is not a valid representation of a number.
* @throws IllegalArgumentException when [radix] is not a valid radix for string to number conversion.
*/
public actual fun String.toLong(radix: Int): Long = toLongOrNull(radix) ?: numberFormatError(this)
/**
* Parses the string as a [Double] number and returns the result.
* @throws NumberFormatException if the string is not a valid representation of a number.
*/
public actual fun String.toDouble(): Double = kotlin.text.parseDouble(this)
/**
* Parses the string as a [Float] number and returns the result.
* @throws NumberFormatException if the string is not a valid representation of a number.
*/
public actual fun String.toFloat(): Float = toDouble() as Float
/**
* Parses the string as a [Float] number and returns the result
* or `null` if the string is not a valid representation of a number.
*/
public actual fun String.toFloatOrNull(): Float? = toDoubleOrNull() as Float?
/**
* Parses the string as a [Double] number and returns the result
* or `null` if the string is not a valid representation of a number.
*/
public actual fun String.toDoubleOrNull(): Double? {
try {
return toDouble()
} catch (e: NumberFormatException) {
return null
}
}
/**
* Returns a string representation of this [Byte] value in the specified [radix].
*
* @throws IllegalArgumentException when [radix] is not a valid radix for number to string conversion.
*/
@SinceKotlin("1.2")
public actual fun Byte.toString(radix: Int): String = this.toLong().toString(radix)
/**
* Returns a string representation of this [Short] value in the specified [radix].
*
* @throws IllegalArgumentException when [radix] is not a valid radix for number to string conversion.
*/
@SinceKotlin("1.2")
public actual fun Short.toString(radix: Int): String = this.toLong().toString(radix)
/**
* Returns a string representation of this [Int] value in the specified [radix].
*
* @throws IllegalArgumentException when [radix] is not a valid radix for number to string conversion.
*/
@SinceKotlin("1.2")
actual fun Int.toString(radix: Int): String = toLong().toString(radix)
/**
* Returns a string representation of this [Long] value in the specified [radix].
*
* @throws IllegalArgumentException when [radix] is not a valid radix for number to string conversion.
*/
@SinceKotlin("1.2")
actual fun Long.toString(radix: Int): String {
checkRadix(radix)
fun Long.getChar() = toInt().let { if (it < 10) '0' + it else 'a' + (it - 10) }
if (radix == 10) return toString()
if (this in 0 until radix) return getChar().toString()
val isNegative = this < 0
val buffer = CharArray(Long.SIZE_BITS + 1)
var currentBufferIndex = buffer.lastIndex
var current: Long = this
while(current != 0L) {
buffer[currentBufferIndex] = abs(current % radix).getChar()
current /= radix
currentBufferIndex--
}
if (isNegative) {
buffer[currentBufferIndex] = '-'
currentBufferIndex--
}
return buffer.concatToString(currentBufferIndex + 1)
}
libraries/stdlib/wasm/src/kotlin/text/StringsWasm.kt
+454 -3
View File
@@ -29,7 +29,7 @@ internal actual fun String.nativeLastIndexOf(ch: Char, fromIndex: Int): Int {
* Returns the index within this string of the first occurrence of the specified substring, starting from the specified offset.
*/
internal actual fun String.nativeIndexOf(str: String, fromIndex: Int): Int {
for (index in fromIndex.coerceAtLeast(0)..this.length) {
for (index in fromIndex.coerceAtLeast(0)..(this.length - str.length)) {
if (str.regionMatchesImpl(0, this, index, str.length, false)) {
return index
}
@@ -41,10 +41,461 @@ internal actual fun String.nativeIndexOf(str: String, fromIndex: Int): Int {
* Returns the index within this string of the last occurrence of the specified character, starting from the specified offset.
*/
internal actual fun String.nativeLastIndexOf(str: String, fromIndex: Int): Int {
for (index in fromIndex.coerceAtMost(this.lastIndex) downTo 0) {
for (index in fromIndex.coerceAtMost(this.length - str.length) downTo 0) {
if (str.regionMatchesImpl(0, this, index, str.length, false)) {
return index
}
}
return -1
}
}
/**
* Converts the characters in the specified array to a string.
*/
@SinceKotlin("1.2")
@Deprecated("Use CharArray.concatToString() instead", ReplaceWith("chars.concatToString()"))
@DeprecatedSinceKotlin(warningSince = "1.4", errorSince = "1.5")
public actual fun String(chars: CharArray): String {
var result = ""
for (char in chars) {
result += char
}
return result
}
/**
* Converts the characters from a portion of the specified array to a string.
*
* @throws IndexOutOfBoundsException if either [offset] or [length] are less than zero
* or `offset + length` is out of [chars] array bounds.
*/
@SinceKotlin("1.2")
@Deprecated("Use CharArray.concatToString(startIndex, endIndex) instead", ReplaceWith("chars.concatToString(offset, offset + length)"))
@DeprecatedSinceKotlin(warningSince = "1.4", errorSince = "1.5")
public actual fun String(chars: CharArray, offset: Int, length: Int): String {
if (offset < 0 || length < 0 || chars.size - offset < length)
throw IndexOutOfBoundsException("size: ${chars.size}; offset: $offset; length: $length")
var result = ""
for (index in offset until offset + length) {
result += chars[index]
}
return result
}
/**
* Concatenates characters in this [CharArray] into a String.
*/
@SinceKotlin("1.4")
@WasExperimental(ExperimentalStdlibApi::class)
public actual fun CharArray.concatToString(): String =
String.unsafeFromCharArray(this.copyOf())
/**
* Concatenates characters in this [CharArray] or its subrange into a String.
*
* @param startIndex the beginning (inclusive) of the subrange of characters, 0 by default.
* @param endIndex the end (exclusive) of the subrange of characters, size of this array by default.
*
* @throws IndexOutOfBoundsException if [startIndex] is less than zero or [endIndex] is greater than the size of this array.
* @throws IllegalArgumentException if [startIndex] is greater than [endIndex].
*/
@SinceKotlin("1.4")
@WasExperimental(ExperimentalStdlibApi::class)
@Suppress("ACTUAL_FUNCTION_WITH_DEFAULT_ARGUMENTS")
public actual fun CharArray.concatToString(startIndex: Int = 0, endIndex: Int = this.size): String {
AbstractList.checkBoundsIndexes(startIndex, endIndex, this.size)
return String.unsafeFromCharArray(this.copyOfRange(startIndex, endIndex))
}
/**
* Returns a [CharArray] containing characters of this string.
*/
@SinceKotlin("1.4")
@WasExperimental(ExperimentalStdlibApi::class)
public actual fun String.toCharArray(): CharArray {
return CharArray(length) { get(it) }
}
/**
* Returns a [CharArray] containing characters of this string or its substring.
*
* @param startIndex the beginning (inclusive) of the substring, 0 by default.
* @param endIndex the end (exclusive) of the substring, length of this string by default.
*
* @throws IndexOutOfBoundsException if [startIndex] is less than zero or [endIndex] is greater than the length of this string.
* @throws IllegalArgumentException if [startIndex] is greater than [endIndex].
*/
@SinceKotlin("1.4")
@WasExperimental(ExperimentalStdlibApi::class)
@Suppress("ACTUAL_FUNCTION_WITH_DEFAULT_ARGUMENTS")
public actual fun String.toCharArray(startIndex: Int = 0, endIndex: Int = this.length): CharArray {
AbstractList.checkBoundsIndexes(startIndex, endIndex, length)
return CharArray(endIndex - startIndex) { get(startIndex + it) }
}
/**
* Decodes a string from the bytes in UTF-8 encoding in this array.
*
* Malformed byte sequences are replaced by the replacement char `\uFFFD`.
*/
@SinceKotlin("1.4")
@WasExperimental(ExperimentalStdlibApi::class)
public actual fun ByteArray.decodeToString(): String {
return decodeUtf8(this, 0, size, false)
}
/**
* Decodes a string from the bytes in UTF-8 encoding in this array or its subrange.
*
* @param startIndex the beginning (inclusive) of the subrange to decode, 0 by default.
* @param endIndex the end (exclusive) of the subrange to decode, size of this array by default.
* @param throwOnInvalidSequence specifies whether to throw an exception on malformed byte sequence or replace it by the replacement char `\uFFFD`.
*
* @throws IndexOutOfBoundsException if [startIndex] is less than zero or [endIndex] is greater than the size of this array.
* @throws IllegalArgumentException if [startIndex] is greater than [endIndex].
* @throws CharacterCodingException if the byte array contains malformed UTF-8 byte sequence and [throwOnInvalidSequence] is true.
*/
@SinceKotlin("1.4")
@WasExperimental(ExperimentalStdlibApi::class)
@Suppress("ACTUAL_FUNCTION_WITH_DEFAULT_ARGUMENTS")
public actual fun ByteArray.decodeToString(
startIndex: Int = 0,
endIndex: Int = this.size,
throwOnInvalidSequence: Boolean = false
): String {
AbstractList.checkBoundsIndexes(startIndex, endIndex, this.size)
return decodeUtf8(this, startIndex, endIndex, throwOnInvalidSequence)
}
/**
* Encodes this string to an array of bytes in UTF-8 encoding.
*
* Any malformed char sequence is replaced by the replacement byte sequence.
*/
@SinceKotlin("1.4")
@WasExperimental(ExperimentalStdlibApi::class)
public actual fun String.encodeToByteArray(): ByteArray {
return encodeUtf8(this, 0, length, false)
}
/**
* Encodes this string or its substring to an array of bytes in UTF-8 encoding.
*
* @param startIndex the beginning (inclusive) of the substring to encode, 0 by default.
* @param endIndex the end (exclusive) of the substring to encode, length of this string by default.
* @param throwOnInvalidSequence specifies whether to throw an exception on malformed char sequence or replace.
*
* @throws IndexOutOfBoundsException if [startIndex] is less than zero or [endIndex] is greater than the length of this string.
* @throws IllegalArgumentException if [startIndex] is greater than [endIndex].
* @throws CharacterCodingException if this string contains malformed char sequence and [throwOnInvalidSequence] is true.
*/
@SinceKotlin("1.4")
@WasExperimental(ExperimentalStdlibApi::class)
@Suppress("ACTUAL_FUNCTION_WITH_DEFAULT_ARGUMENTS")
public actual fun String.encodeToByteArray(
startIndex: Int = 0,
endIndex: Int = this.length,
throwOnInvalidSequence: Boolean = false
): ByteArray {
AbstractList.checkBoundsIndexes(startIndex, endIndex, length)
return encodeUtf8(this, startIndex, endIndex, throwOnInvalidSequence)
}
/**
* Returns a substring of this string that starts at the specified [startIndex] and continues to the end of the string.
*/
public actual fun String.substring(startIndex: Int): String =
subSequence(startIndex, this.length) as String
/**
* Returns the substring of this string starting at the [startIndex] and ending right before the [endIndex].
*
* @param startIndex the start index (inclusive).
* @param endIndex the end index (exclusive).
*/
public actual fun String.substring(startIndex: Int, endIndex: Int): String =
subSequence(startIndex, endIndex) as String
/**
* Returns a copy of this string converted to upper case using the rules of the default locale.
*/
@Deprecated("Use uppercase() instead.", ReplaceWith("uppercase()"))
@DeprecatedSinceKotlin(warningSince = "1.5")
public actual fun String.toUpperCase(): String = uppercase()
/**
* Returns a copy of this string converted to upper case using Unicode mapping rules of the invariant locale.
*
* This function supports one-to-many and many-to-one character mapping,
* thus the length of the returned string can be different from the length of the original string.
*
* @sample samples.text.Strings.uppercase
*/
@SinceKotlin("1.5")
public actual fun String.uppercase(): String = uppercaseImpl()
/**
* Returns a copy of this string converted to lower case using the rules of the default locale.
*/
@Deprecated("Use lowercase() instead.", ReplaceWith("lowercase()"))
@DeprecatedSinceKotlin(warningSince = "1.5")
public actual fun String.toLowerCase(): String = lowercase()
/**
* Returns a copy of this string converted to lower case using Unicode mapping rules of the invariant locale.
*
* This function supports one-to-many and many-to-one character mapping,
* thus the length of the returned string can be different from the length of the original string.
*
* @sample samples.text.Strings.lowercase
*/
@SinceKotlin("1.5")
public actual fun String.lowercase(): String = lowercaseImpl()
/**
* Returns a copy of this string having its first letter titlecased using the rules of the default locale,
* or the original string if it's empty or already starts with a title case letter.
*
* The title case of a character is usually the same as its upper case with several exceptions.
* The particular list of characters with the special title case form depends on the underlying platform.
*
* @sample samples.text.Strings.capitalize
*/
@Deprecated("Use replaceFirstChar instead.", ReplaceWith("replaceFirstChar { if (it.isLowerCase()) it.titlecase() else it.toString() }"))
@DeprecatedSinceKotlin(warningSince = "1.5")
public actual fun String.capitalize(): String = replaceFirstChar(Char::uppercaseChar)
/**
* Returns a copy of this string having its first letter lowercased using the rules of the default locale,
* or the original string if it's empty or already starts with a lower case letter.
*
* @sample samples.text.Strings.decapitalize
*/
@Deprecated("Use replaceFirstChar instead.", ReplaceWith("replaceFirstChar { it.lowercase() }"))
@DeprecatedSinceKotlin(warningSince = "1.5")
public actual fun String.decapitalize(): String = replaceFirstChar(Char::lowercaseChar)
/**
* Returns a string containing this char sequence repeated [n] times.
* @throws [IllegalArgumentException] when n < 0.
* @sample samples.text.Strings.repeat
*/
public actual fun CharSequence.repeat(n: Int): String {
require(n >= 0) { "Count 'n' must be non-negative, but was $n." }
if (isEmpty()) return ""
return when (n) {
0 -> ""
1 -> this.toString()
else -> {
buildString(n * length) {
repeat(n) {
append(this@repeat)
}
}
}
}
}
/**
* Returns a new string with all occurrences of [oldChar] replaced with [newChar].
*/
@Suppress("ACTUAL_FUNCTION_WITH_DEFAULT_ARGUMENTS")
public actual fun String.replace(oldChar: Char, newChar: Char, ignoreCase: Boolean = false): String {
return buildString(length) {
this@replace.forEach { c ->
append(if (c.equals(oldChar, ignoreCase)) newChar else c)
}
}
}
/**
* Returns a new string obtained by replacing all occurrences of the [oldValue] substring in this string
* with the specified [newValue] string.
*/
@Suppress("ACTUAL_FUNCTION_WITH_DEFAULT_ARGUMENTS")
public actual fun String.replace(oldValue: String, newValue: String, ignoreCase: Boolean = false): String {
run {
var occurrenceIndex: Int = indexOf(oldValue, 0, ignoreCase)
// FAST PATH: no match
if (occurrenceIndex < 0) return this
val oldValueLength = oldValue.length
val searchStep = oldValueLength.coerceAtLeast(1)
val newLengthHint = length - oldValueLength + newValue.length
if (newLengthHint < 0) throw OutOfMemoryError()
val stringBuilder = StringBuilder(newLengthHint)
var i = 0
do {
stringBuilder.append(this, i, occurrenceIndex).append(newValue)
i = occurrenceIndex + oldValueLength
if (occurrenceIndex >= length) break
occurrenceIndex = indexOf(oldValue, occurrenceIndex + searchStep, ignoreCase)
} while (occurrenceIndex > 0)
return stringBuilder.append(this, i, length).toString()
}
}
/**
* Returns a new string with the first occurrence of [oldChar] replaced with [newChar].
*/
@Suppress("ACTUAL_FUNCTION_WITH_DEFAULT_ARGUMENTS")
public actual fun String.replaceFirst(oldChar: Char, newChar: Char, ignoreCase: Boolean = false): String {
val index = indexOf(oldChar, ignoreCase = ignoreCase)
return if (index < 0) this else this.replaceRange(index, index + 1, newChar.toString())
}
/**
* Returns a new string obtained by replacing the first occurrence of the [oldValue] substring in this string
* with the specified [newValue] string.
*/
@Suppress("ACTUAL_FUNCTION_WITH_DEFAULT_ARGUMENTS")
public actual fun String.replaceFirst(oldValue: String, newValue: String, ignoreCase: Boolean = false): String {
val index = indexOf(oldValue, ignoreCase = ignoreCase)
return if (index < 0) this else this.replaceRange(index, index + oldValue.length, newValue)
}
/**
* Returns `true` if this string is equal to [other], optionally ignoring character case.
*
* Two strings are considered to be equal if they have the same length and the same character at the same index.
* If [ignoreCase] is true, the result of `Char.uppercaseChar().lowercaseChar()` on each character is compared.
*
* @param ignoreCase `true` to ignore character case when comparing strings. By default `false`.
*/
@Suppress("ACTUAL_FUNCTION_WITH_DEFAULT_ARGUMENTS")
public actual fun String?.equals(other: String?, ignoreCase: Boolean = false): Boolean {
if (this == null) return other == null
if (other == null) return false
if (!ignoreCase) return this == other
if (this.length != other.length) return false
for (index in 0 until this.length) {
val thisChar = this[index]
val otherChar = other[index]
if (!thisChar.equals(otherChar, ignoreCase)) {
return false
}
}
return true
}
/**
* Compares two strings lexicographically, optionally ignoring case differences.
*
* If [ignoreCase] is true, the result of `Char.uppercaseChar().lowercaseChar()` on each character is compared.
*/
@SinceKotlin("1.2")
@Suppress("ACTUAL_FUNCTION_WITH_DEFAULT_ARGUMENTS")
public actual fun String.compareTo(other: String, ignoreCase: Boolean = false): Int {
if (ignoreCase) {
val n1 = this.length
val n2 = other.length
val min = minOf(n1, n2)
if (min == 0) return n1 - n2
for (index in 0 until min) {
var thisChar = this[index]
var otherChar = other[index]
if (thisChar != otherChar) {
thisChar = thisChar.uppercaseChar()
otherChar = otherChar.uppercaseChar()
if (thisChar != otherChar) {
thisChar = thisChar.lowercaseChar()
otherChar = otherChar.lowercaseChar()
if (thisChar != otherChar) {
return thisChar.compareTo(otherChar)
}
}
}
}
return n1 - n2
} else {
return compareTo(other)
}
}
/**
* Returns `true` if the contents of this char sequence are equal to the contents of the specified [other],
* i.e. both char sequences contain the same number of the same characters in the same order.
*
* @sample samples.text.Strings.contentEquals
*/
@SinceKotlin("1.5")
public actual infix fun CharSequence?.contentEquals(other: CharSequence?): Boolean = contentEqualsImpl(other)
/**
* Returns `true` if the contents of this char sequence are equal to the contents of the specified [other], optionally ignoring case difference.
*
* @param ignoreCase `true` to ignore character case when comparing contents.
*
* @sample samples.text.Strings.contentEquals
*/
@SinceKotlin("1.5")
public actual fun CharSequence?.contentEquals(other: CharSequence?, ignoreCase: Boolean): Boolean {
return if (ignoreCase)
this.contentEqualsIgnoreCaseImpl(other)
else
this.contentEqualsImpl(other)
}
/**
* Returns `true` if this string starts with the specified prefix.
*/
@Suppress("ACTUAL_FUNCTION_WITH_DEFAULT_ARGUMENTS")
public actual fun String.startsWith(prefix: String, ignoreCase: Boolean = false): Boolean =
regionMatches(0, prefix, 0, prefix.length, ignoreCase)
/**
* Returns `true` if a substring of this string starting at the specified offset [startIndex] starts with the specified prefix.
*/
@Suppress("ACTUAL_FUNCTION_WITH_DEFAULT_ARGUMENTS")
public actual fun String.startsWith(prefix: String, startIndex: Int, ignoreCase: Boolean = false): Boolean =
regionMatches(startIndex, prefix, 0, prefix.length, ignoreCase)
/**
* Returns `true` if this string ends with the specified suffix.
*/
@Suppress("ACTUAL_FUNCTION_WITH_DEFAULT_ARGUMENTS")
public actual fun String.endsWith(suffix: String, ignoreCase: Boolean = false): Boolean =
regionMatches(length - suffix.length, suffix, 0, suffix.length, ignoreCase)
// From stringsCode.kt
/**
* Returns `true` if this string is empty or consists solely of whitespace characters.
*
* @sample samples.text.Strings.stringIsBlank
*/
public actual fun CharSequence.isBlank(): Boolean = length == 0 || indices.all { this[it].isWhitespace() }
/**
* Returns `true` if the specified range in this char sequence is equal to the specified range in another char sequence.
* @param thisOffset the start offset in this char sequence of the substring to compare.
* @param other the string against a substring of which the comparison is performed.
* @param otherOffset the start offset in the other char sequence of the substring to compare.
* @param length the length of the substring to compare.
*/
actual fun CharSequence.regionMatches(
thisOffset: Int,
other: CharSequence,
otherOffset: Int,
length: Int,
ignoreCase: Boolean
): Boolean = regionMatchesImpl(thisOffset, other, otherOffset, length, ignoreCase)
private val STRING_CASE_INSENSITIVE_ORDER = Comparator<String> { a, b -> a.compareTo(b, ignoreCase = true) }
/**
* A Comparator that orders strings ignoring character case.
*
* Note that this Comparator does not take locale into account,
* and will result in an unsatisfactory ordering for certain locales.
*/
@SinceKotlin("1.2")
public actual val String.Companion.CASE_INSENSITIVE_ORDER: Comparator<String>
get() = STRING_CASE_INSENSITIVE_ORDER
libraries/stdlib/wasm/src/kotlin/text/regex/BitSet.kt
+257
View File
@@ -0,0 +1,257 @@
/*
* Copyright 2010-2021 JetBrains s.r.o. and Kotlin Programming Language contributors.
* Use of this source code is governed by the Apache 2.0 license that can be found in the license/LICENSE.txt file.
*/
package kotlin.native
/**
* A vector of bits growing if necessary and allowing one to set/clear/read bits from it by a bit index.
* (this is the stripped copy of K/N implementation for Regex)
*
* @constructor creates an empty bit set with the specified [size]
* @param size the size of one element in the array used to store bits.
*/
internal class BitSet constructor(size: Int = ELEMENT_SIZE) {
companion object {
// Default size of one element in the array used to store bits.
private const val ELEMENT_SIZE = 64
private const val MAX_BIT_OFFSET = ELEMENT_SIZE - 1
private const val ALL_TRUE = -1L // 0xFFFF_FFFF_FFFF_FFFF
private const val ALL_FALSE = 0L // 0x0000_0000_0000_0000
}
private var bits: LongArray = LongArray(bitToElementSize(size))
private val lastIndex: Int
get() = size - 1
/** True if this BitSet contains no bits set to true. */
val isEmpty: Boolean
get() = bits.all { it == ALL_FALSE }
/** Actual number of bits available in the set. All bits with indices >= size assumed to be 0 */
var size: Int = size
private set
// Transforms a bit index into an element index in the `bits` array.
private val Int.elementIndex: Int
get() = this / ELEMENT_SIZE
// Transforms a bit index in the set into a bit in the element of the `bits` array.
private val Int.bitOffset: Int
get() = this % ELEMENT_SIZE
// Transforms a bit index in the set into pair of a `bits` element index and a bit index in the element.
private val Int.asBitCoordinates: Pair<Int, Int>
get() = Pair(elementIndex, bitOffset)
// Transforms a bit offset to the mask with only bit set corresponding to the offset.
private val Int.asMask: Long
get() = 0x1L shl this
// Transforms a bit offset to the mask with only bits before the index (inclusive) set.
private val Int.asMaskBefore: Long
get() = getMaskBetween(0, this)
// Transforms a bit offset to the mask with only bits after the index (inclusive) set.
private val Int.asMaskAfter: Long
get() = getMaskBetween(this, MAX_BIT_OFFSET)
// Builds a masks with 1 between fromOffset and toOffset (both inclusive).
private fun getMaskBetween(fromOffset: Int, toOffset: Int): Long {
var res = 0L
val maskToAdd = fromOffset.asMask
for (i in fromOffset..toOffset) {
res = (res shl 1) or maskToAdd
}
return res
}
// Transforms a size in bits to a size in elements of the `bits` array.
private fun bitToElementSize(bitSize: Int): Int = (bitSize + ELEMENT_SIZE - 1) / ELEMENT_SIZE
// Transforms a pair of an element index and a bit offset to a bit index.
private fun bitIndex(elementIndex: Int, bitOffset: Int) =
elementIndex * ELEMENT_SIZE + bitOffset
// Sets all bits after the last available bit (size - 1) to 0.
private fun clearUnusedTail() {
val (lastElementIndex, lastBitOffset) = lastIndex.asBitCoordinates
bits[bits.lastIndex] = bits[bits.lastIndex] and lastBitOffset.asMaskBefore
for (i in lastElementIndex + 1 until bits.size) {
bits[i] = ALL_FALSE
}
}
// Internal function. Sets bits specified by the element index and the given mask to value.
private fun setBitsWithMask(elementIndex: Int, mask: Long, value: Boolean) {
val element = bits[elementIndex]
if (value) {
bits[elementIndex] = element or mask
} else {
bits[elementIndex] = element and mask.inv()
}
}
/**
* Checks if index is valid and extends the `bits` array if the index exceeds its size.
* @throws [IndexOutOfBoundsException] if [index] < 0.
*/
private fun ensureCapacity(index: Int) {
if (index < 0) {
throw IndexOutOfBoundsException()
}
if (index >= size) {
size = index + 1
if (index.elementIndex >= bits.size) {
// Create a new array containing the index-th bit.
bits = bits.copyOf(bitToElementSize(index + 1))
}
// Set all bits after the index to 0. TODO: We can remove it.
clearUnusedTail()
}
}
/** Set the bit specified to the specified value. */
fun set(index: Int, value: Boolean = true) {
ensureCapacity(index)
val (elementIndex, offset) = index.asBitCoordinates
setBitsWithMask(elementIndex, offset.asMask, value)
}
/** Sets the bits with indices between [from] (inclusive) and [to] (exclusive) to the specified value. */
fun set(from : Int, to: Int, value: Boolean = true) = set(from until to, value)
/** Sets the bits from the range specified to the specified value. */
fun set(range: IntRange, value: Boolean = true) {
if (range.start < 0 || range.endInclusive < 0) {
throw IndexOutOfBoundsException()
}
if (range.start > range.endInclusive) { // Empty range.
return
}
ensureCapacity(range.endInclusive)
val (fromIndex, fromOffset) = range.start.asBitCoordinates
val (toIndex, toOffset) = range.endInclusive.asBitCoordinates
if (toIndex == fromIndex) {
val mask = getMaskBetween(fromOffset, toOffset)
setBitsWithMask(fromIndex, mask, value)
} else {
// Set bits in the first element.
setBitsWithMask(fromIndex, fromOffset.asMaskAfter, value)
// Set all bits of all elements (excluding border ones) to 0 or 1 depending.
for (index in fromIndex + 1 until toIndex) {
bits[index] = if (value) ALL_TRUE else ALL_FALSE
}
// Set bits in the last element
setBitsWithMask(toIndex, toOffset.asMaskBefore, value)
}
}
/**
* Returns an index of a next set (if [lookFor] == true) or clear
* (if [lookFor] == false) bit after [startIndex] (inclusive).
* Returns -1 (for [lookFor] == true) or [size] (for lookFor == false)
* if there is no such bits between [startIndex] and [size] - 1.
* @throws IndexOutOfBoundException if [startIndex] < 0.
*/
private fun nextBit(startIndex: Int, lookFor: Boolean): Int {
if (startIndex < 0) {
throw IndexOutOfBoundsException()
}
if (startIndex >= size) {
return if (lookFor) -1 else startIndex
}
val (startElementIndex, startOffset) = startIndex.asBitCoordinates
// Look for the next set bit in the first element.
var element = bits[startElementIndex]
for (offset in startOffset..MAX_BIT_OFFSET) {
val bit = element and (0x1L shl offset) != 0L
if (bit == lookFor) { // Look for not 0 if we need a set bit and look for 0 otherwise.
return bitIndex(startElementIndex, offset)
}
}
// Look for in the remaining elements.
for (index in startElementIndex + 1..bits.lastIndex) {
element = bits[index]
for (offset in 0..MAX_BIT_OFFSET) {
val bit = element and (0x1L shl offset) != 0L
if (bit == lookFor) { // Look for not 0 if we need a set bit and look for 0 otherwise.
return bitIndex(index, offset)
}
}
}
return if (lookFor) -1 else size
}
/**
* Returns an index of a next bit which value is `true` after [startIndex] (inclusive).
* Returns -1 if there is no such bits after [startIndex].
* @throws IndexOutOfBoundException if [startIndex] < 0.
*/
fun nextSetBit(startIndex: Int = 0): Int = nextBit(startIndex, true)
/**
* Returns an index of a next bit which value is `false` after [startIndex] (inclusive).
* Returns [size] if there is no such bits between [startIndex] and [size] - 1 assuming that the set has an infinite
* sequence of `false` bits after (size - 1)-th.
* @throws IndexOutOfBoundException if [startIndex] < 0.
*/
fun nextClearBit(startIndex: Int = 0): Int = nextBit(startIndex, false)
/** Returns a value of a bit with the [index] specified. */
operator fun get(index: Int): Boolean {
if (index < 0) {
throw IndexOutOfBoundsException()
}
if (index >= size) {
return false
}
val (elementIndex, offset) = index.asBitCoordinates
return bits[elementIndex] and offset.asMask != 0L
}
private inline fun doOperation(another: BitSet, operation: Long.(Long) -> Long) {
ensureCapacity(another.lastIndex)
var index = 0
while (index < another.bits.size) {
bits[index] = operation(bits[index], another.bits[index])
index++
}
while (index < bits.size) {
bits[index] = operation(bits[index], ALL_FALSE)
index++
}
}
/** Performs a logical and operation over corresponding bits of this and [another] BitSets. The result is saved in this BitSet. */
fun and(another: BitSet) = doOperation(another, Long::and)
/** Performs a logical or operation over corresponding bits of this and [another] BitSets. The result is saved in this BitSet. */
fun or(another: BitSet) = doOperation(another, Long::or)
/** Performs a logical xor operation over corresponding bits of this and [another] BitSets. The result is saved in this BitSet. */
fun xor(another: BitSet) = doOperation(another, Long::xor)
/** Performs a logical and + not operations over corresponding bits of this and [another] BitSets. The result is saved in this BitSet. */
fun andNot(another: BitSet) {
ensureCapacity(another.lastIndex)
var index = 0
while (index < another.bits.size) {
bits[index] = bits[index] and another.bits[index].inv()
index++
}
while (index < bits.size) {
bits[index] = bits[index] and ALL_TRUE
index++
}
}
/** Returns true if the specified BitSet has any bits set to true that are also set to true in this BitSet. */
fun intersects(another: BitSet): Boolean =
(0 until minOf(bits.size, another.bits.size)).any { bits[it] and another.bits[it] != 0L }
}
libraries/stdlib/wasm/src/kotlin/text/regex/DecompositionHelpers.kt
+318
View File
@@ -0,0 +1,318 @@
/*
* Copyright 2010-2021 JetBrains s.r.o. and Kotlin Programming Language contributors.
* Use of this source code is governed by the Apache 2.0 license that can be found in the license/LICENSE.txt file.
*/
package kotlin.text.regex
/* Contains canonical classes (see http://www.unicode.org/Public/4.0-Update/UnicodeData-4.0.0.txt). */
private val canonicalClassesKeys = intArrayOf(
768, 769, 770, 771, 772, 773, 774, 775, 776, 777, 778, 779, 780, 781, 782, 783, 784, 785, 786, 787, 788, 789, 790,
791, 792, 793, 794, 795, 796, 797, 798, 799, 800, 801, 802, 803, 804, 805, 806, 807, 808, 809, 810, 811, 812, 813,
814, 815, 816, 817, 818, 819, 820, 821, 822, 823, 824, 825, 826, 827, 828, 829, 830, 831, 832, 833, 834, 835, 836,
837, 838, 839, 840, 841, 842, 843, 844, 845, 846, 848, 849, 850, 851, 852, 853, 854, 855, 856, 857, 858, 859, 860,
861, 862, 863, 864, 865, 866, 867, 868, 869, 870, 871, 872, 873, 874, 875, 876, 877, 878, 879, 1155, 1156, 1157, 1158,
1425, 1426, 1427, 1428, 1429, 1430, 1431, 1432, 1433, 1434, 1435, 1436, 1437, 1438, 1439, 1440, 1441, 1442, 1443,
1444, 1445, 1446, 1447, 1448, 1449, 1450, 1451, 1452, 1453, 1454, 1455, 1456, 1457, 1458, 1459, 1460, 1461, 1462,
1463, 1464, 1465, 1467, 1468, 1469, 1471, 1473, 1474, 1476, 1477, 1479, 1552, 1553, 1554, 1555, 1556, 1557, 1611,
1612, 1613, 1614, 1615, 1616, 1617, 1618, 1619, 1620, 1621, 1622, 1623, 1624, 1625, 1626, 1627, 1628, 1629, 1630,
1648, 1750, 1751, 1752, 1753, 1754, 1755, 1756, 1759, 1760, 1761, 1762, 1763, 1764, 1767, 1768, 1770, 1771, 1772,
1773, 1809, 1840, 1841, 1842, 1843, 1844, 1845, 1846, 1847, 1848, 1849, 1850, 1851, 1852, 1853, 1854, 1855, 1856,
1857, 1858, 1859, 1860, 1861, 1862, 1863, 1864, 1865, 1866, 2364, 2381, 2385, 2386, 2387, 2388, 2492, 2509, 2620,
2637, 2748, 2765, 2876, 2893, 3021, 3149, 3157, 3158, 3260, 3277, 3405, 3530, 3640, 3641, 3642, 3656, 3657, 3658,
3659, 3768, 3769, 3784, 3785, 3786, 3787, 3864, 3865, 3893, 3895, 3897, 3953, 3954, 3956, 3962, 3963, 3964, 3965,
3968, 3970, 3971, 3972, 3974, 3975, 4038, 4151, 4153, 4959, 5908, 5940, 6098, 6109, 6313, 6457, 6458, 6459, 6679,
6680, 7616, 7617, 7618, 7619, 8400, 8401, 8402, 8403, 8404, 8405, 8406, 8407, 8408, 8409, 8410, 8411, 8412, 8417,
8421, 8422, 8423, 8424, 8425, 8426, 8427, 12330, 12331, 12332, 12333, 12334, 12335, 12441, 12442, 43014, 64286, 65056,
65057, 65058, 65059, 68109, 68111, 68152, 68153, 68154, 68159, 119141, 119142, 119143, 119144, 119145, 119149, 119150,
119151, 119152, 119153, 119154, 119163, 119164, 119165, 119166, 119167, 119168, 119169, 119170, 119173, 119174,
119175, 119176, 119177, 119178, 119179, 119210, 119211, 119212, 119213, 119362, 119363, 119364,
)
private val canonicalClassesValues = intArrayOf(
230, 230, 230, 230, 230, 230, 230, 230, 230, 230, 230, 230, 230, 230, 230, 230, 230, 230, 230, 230, 230, 232, 220,
220, 220, 220, 232, 216, 220, 220, 220, 220, 220, 202, 202, 220, 220, 220, 220, 202, 202, 220, 220, 220, 220, 220,
220, 220, 220, 220, 220, 220, 1, 1, 1, 1, 1, 220, 220, 220, 220, 230, 230, 230, 230, 230, 230, 230, 230, 240, 230,
220, 220, 220, 230, 230, 230, 220, 220, 230, 230, 230, 220, 220, 220, 220, 230, 232, 220, 220, 230, 233, 234, 234,
233, 234, 234, 233, 230, 230, 230, 230, 230, 230, 230, 230, 230, 230, 230, 230, 230, 230, 230, 230, 230, 220, 230,
230, 230, 230, 220, 230, 230, 230, 222, 220, 230, 230, 230, 230, 230, 230, 220, 220, 220, 220, 220, 220, 230, 230,
220, 230, 230, 222, 228, 230, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 230, 220, 18, 230, 230,
230, 230, 230, 230, 27, 28, 29, 30, 31, 32, 33, 34, 230, 230, 220, 220, 230, 230, 230, 230, 230, 220, 230, 230, 35,
230, 230, 230, 230, 230, 230, 230, 230, 230, 230, 230, 220, 230, 230, 230, 220, 230, 230, 220, 36, 230, 220, 230, 230,
220, 230, 230, 220, 220, 220, 230, 220, 220, 230, 220, 230, 230, 230, 220, 230, 220, 230, 220, 230, 220, 230, 230, 7,
9, 230, 220, 230, 230, 7, 9, 7, 9, 7, 9, 7, 9, 9, 9, 84, 91, 7, 9, 9, 9, 103, 103, 9, 107, 107, 107, 107, 118, 118,
122, 122, 122, 122, 220, 220, 220, 220, 216, 129, 130, 132, 130, 130, 130, 130, 130, 230, 230, 9, 230, 230, 220, 7, 9,
230, 9, 9, 9, 230, 228, 222, 230, 220, 230, 220, 230, 230, 220, 230, 230, 230, 1, 1, 230, 230, 230, 230, 1, 1, 1, 230,
230, 230, 1, 1, 230, 220, 230, 1, 1, 218, 228, 232, 222, 224, 224, 8, 8, 9, 26, 230, 230, 230, 230, 220, 230, 230, 1,
220, 9, 216, 216, 1, 1, 1, 226, 216, 216, 216, 216, 216, 220, 220, 220, 220, 220, 220, 220, 220, 230, 230, 230, 230,
230, 220, 220, 230, 230, 230, 230, 230, 230, 230,
)
/* Symbols that are one symbol decompositions (see http://www.unicode.org/Public/4.0-Update/UnicodeData-4.0.0.txt). */
private val singleDecompositions = intArrayOf(
59, 75, 96, 180, 183, 197, 697, 768, 769, 787, 901, 902, 904, 905, 906, 908, 910, 911, 912, 937, 940, 941, 942, 943,
944, 953, 972, 973, 974, 8194, 8195, 12296, 12297, 13470, 13497, 13499, 13535, 13589, 14062, 14076, 14209, 14383,
14434, 14460, 14535, 14563, 14620, 14650, 14894, 14956, 15076, 15112, 15129, 15177, 15261, 15384, 15438, 15667, 15766,
16044, 16056, 16155, 16380, 16392, 16408, 16441, 16454, 16534, 16611, 16687, 16898, 16935, 17056, 17153, 17204, 17241,
17365, 17369, 17419, 17515, 17707, 17757, 17761, 17771, 17879, 17913, 17973, 18110, 18119, 18837, 18918, 19054, 19062,
19122, 19251, 19406, 19662, 19693, 19704, 19798, 19981, 20006, 20018, 20024, 20025, 20029, 20033, 20098, 20102, 20142,
20160, 20172, 20196, 20320, 20352, 20358, 20363, 20398, 20411, 20415, 20482, 20523, 20602, 20633, 20687, 20698, 20711,
20800, 20805, 20813, 20820, 20836, 20839, 20840, 20841, 20845, 20855, 20864, 20877, 20882, 20885, 20887, 20900, 20908,
20917, 20919, 20937, 20940, 20956, 20958, 20981, 20995, 20999, 21015, 21033, 21050, 21051, 21062, 21106, 21111, 21129,
21147, 21155, 21171, 21191, 21193, 21202, 21214, 21220, 21237, 21242, 21253, 21254, 21271, 21311, 21321, 21329, 21338,
21363, 21365, 21373, 21375, 21443, 21450, 21471, 21477, 21483, 21489, 21510, 21519, 21533, 21560, 21570, 21576, 21608,
21662, 21666, 21693, 21750, 21776, 21843, 21845, 21859, 21892, 21895, 21913, 21917, 21931, 21939, 21952, 21954, 21986,
22022, 22097, 22120, 22132, 22265, 22294, 22295, 22411, 22478, 22516, 22541, 22577, 22578, 22592, 22618, 22622, 22696,
22700, 22707, 22744, 22751, 22766, 22770, 22775, 22790, 22810, 22818, 22852, 22856, 22865, 22868, 22882, 22899, 23000,
23020, 23067, 23079, 23138, 23142, 23221, 23304, 23336, 23358, 23429, 23491, 23512, 23527, 23534, 23539, 23551, 23558,
23586, 23615, 23648, 23650, 23652, 23653, 23662, 23693, 23744, 23833, 23875, 23888, 23915, 23918, 23932, 23986, 23994,
24033, 24034, 24061, 24104, 24125, 24169, 24180, 24230, 24240, 24243, 24246, 24265, 24266, 24274, 24275, 24281, 24300,
24318, 24324, 24354, 24403, 24418, 24425, 24427, 24459, 24474, 24489, 24493, 24525, 24535, 24565, 24569, 24594, 24604,
24705, 24724, 24775, 24792, 24801, 24840, 24900, 24904, 24908, 24910, 24928, 24936, 24954, 24974, 24976, 24996, 25007,
25010, 25054, 25074, 25078, 25088, 25104, 25115, 25134, 25140, 25181, 25265, 25289, 25295, 25299, 25300, 25340, 25342,
25405, 25424, 25448, 25467, 25475, 25504, 25513, 25540, 25541, 25572, 25628, 25634, 25682, 25705, 25719, 25726, 25754,
25757, 25796, 25935, 25942, 25964, 25976, 26009, 26053, 26082, 26083, 26131, 26185, 26228, 26248, 26257, 26268, 26292,
26310, 26356, 26360, 26368, 26391, 26395, 26401, 26446, 26451, 26454, 26462, 26491, 26501, 26519, 26611, 26618, 26647,
26655, 26706, 26753, 26757, 26766, 26792, 26900, 26946, 27043, 27114, 27138, 27155, 27304, 27347, 27355, 27396, 27425,
27476, 27506, 27511, 27513, 27551, 27566, 27578, 27579, 27726, 27751, 27784, 27839, 27852, 27853, 27877, 27926, 27931,
27934, 27956, 27966, 27969, 28009, 28010, 28023, 28024, 28037, 28107, 28122, 28138, 28153, 28186, 28207, 28270, 28316,
28346, 28359, 28363, 28369, 28379, 28431, 28450, 28451, 28526, 28614, 28651, 28670, 28699, 28702, 28729, 28746, 28784,
28791, 28797, 28825, 28845, 28872, 28889, 28997, 29001, 29038, 29084, 29134, 29136, 29200, 29211, 29224, 29227, 29237,
29264, 29282, 29312, 29333, 29359, 29376, 29436, 29482, 29557, 29562, 29575, 29579, 29605, 29618, 29662, 29702, 29705,
29730, 29767, 29788, 29801, 29809, 29829, 29833, 29848, 29898, 29958, 29988, 30011, 30014, 30041, 30053, 30064, 30178,
30224, 30237, 30239, 30274, 30313, 30410, 30427, 30439, 30452, 30465, 30494, 30495, 30528, 30538, 30603, 30631, 30798,
30827, 30860, 30865, 30922, 30924, 30971, 31018, 31036, 31038, 31048, 31049, 31056, 31062, 31069, 31070, 31077, 31103,
31117, 31118, 31119, 31150, 31178, 31211, 31260, 31296, 31306, 31311, 31361, 31409, 31435, 31470, 31520, 31680, 31686,
31689, 31806, 31840, 31867, 31890, 31934, 31954, 31958, 31971, 31975, 31976, 32000, 32016, 32034, 32047, 32091, 32099,
32160, 32190, 32199, 32244, 32258, 32265, 32311, 32321, 32325, 32574, 32626, 32633, 32634, 32645, 32661, 32666, 32701,
32762, 32769, 32773, 32838, 32864, 32879, 32880, 32894, 32907, 32941, 32946, 33027, 33086, 33240, 33256, 33261, 33281,
33284, 33391, 33401, 33419, 33425, 33437, 33457, 33459, 33469, 33509, 33510, 33565, 33571, 33590, 33618, 33619, 33635,
33709, 33725, 33737, 33738, 33740, 33756, 33767, 33775, 33777, 33853, 33865, 33879, 34030, 34033, 34035, 34044, 34070,
34148, 34253, 34298, 34310, 34322, 34349, 34367, 34384, 34396, 34407, 34409, 34440, 34473, 34530, 34574, 34600, 34667,
34681, 34694, 34746, 34785, 34817, 34847, 34892, 34912, 34915, 35010, 35023, 35031, 35038, 35041, 35064, 35066, 35088,
35137, 35172, 35206, 35211, 35222, 35488, 35498, 35519, 35531, 35538, 35542, 35565, 35576, 35582, 35585, 35641, 35672,
35712, 35722, 35912, 35925, 36011, 36033, 36034, 36040, 36051, 36104, 36123, 36215, 36284, 36299, 36335, 36336, 36554,
36564, 36646, 36650, 36664, 36667, 36706, 36766, 36784, 36790, 36899, 36920, 36978, 36988, 37007, 37012, 37070, 37105,
37117, 37137, 37147, 37226, 37273, 37300, 37324, 37327, 37329, 37428, 37432, 37494, 37500, 37591, 37592, 37636, 37706,
37881, 37909, 38283, 38317, 38327, 38446, 38475, 38477, 38517, 38520, 38524, 38534, 38563, 38584, 38595, 38626, 38627,
38646, 38647, 38691, 38706, 38728, 38742, 38875, 38880, 38911, 38923, 38936, 38953, 38971, 39006, 39138, 39151, 39164,
39208, 39209, 39335, 39362, 39409, 39422, 39530, 39698, 39791, 40000, 40023, 40189, 40295, 40372, 40442, 40478, 40575,
40599, 40607, 40635, 40654, 40697, 40702, 40709, 40719, 40726, 40763, 40771, 40845, 40846, 40860, 131362, 132380,
132389, 132427, 132666, 133124, 133342, 133676, 133987, 136420, 136872, 136938, 137672, 138008, 138507, 138724,
138726, 139651, 139679, 140081, 141012, 141380, 141386, 142092, 142321, 143370, 144056, 144223, 144275, 144284,
144323, 144341, 144493, 145059, 145575, 146061, 146170, 146620, 146718, 147153, 147294, 147342, 148067, 148395,
149000, 149301, 149524, 150582, 150674, 151457, 151480, 151620, 151794, 151795, 151833, 151859, 152137, 152605,
153126, 153242, 153285, 153980, 154279, 154539, 154752, 154832, 155526, 156122, 156200, 156231, 156377, 156478,
156890, 156963, 157096, 157607, 157621, 158524, 158774, 158933, 159083, 159532, 159665, 159954, 160714, 161383,
161966, 162150, 162984, 163539, 163631, 165330, 165357, 165678, 166906, 167287, 168261, 168415, 168474, 168970,
169110, 169398, 170800, 172238, 172293, 172558, 172689, 172946, 173568
)
private val decompositionKeys = intArrayOf(
192, 193, 194, 195, 196, 197, 199, 200, 201, 202, 203, 204, 205, 206, 207, 209, 210, 211, 212, 213, 214, 217, 218,
219, 220, 221, 224, 225, 226, 227, 228, 229, 231, 232, 233, 234, 235, 236, 237, 238, 239, 241, 242, 243, 244, 245,
246, 249, 250, 251, 252, 253, 255, 256, 257, 258, 259, 260, 261, 262, 263, 264, 265, 266, 267, 268, 269, 270, 271,
274, 275, 276, 277, 278, 279, 280, 281, 282, 283, 284, 285, 286, 287, 288, 289, 290, 291, 292, 293, 296, 297, 298,
299, 300, 301, 302, 303, 304, 308, 309, 310, 311, 313, 314, 315, 316, 317, 318, 323, 324, 325, 326, 327, 328, 332,
333, 334, 335, 336, 337, 340, 341, 342, 343, 344, 345, 346, 347, 348, 349, 350, 351, 352, 353, 354, 355, 356, 357,
360, 361, 362, 363, 364, 365, 366, 367, 368, 369, 370, 371, 372, 373, 374, 375, 376, 377, 378, 379, 380, 381, 382,
416, 417, 431, 432, 461, 462, 463, 464, 465, 466, 467, 468, 469, 470, 471, 472, 473, 474, 475, 476, 478, 479, 480,
481, 482, 483, 486, 487, 488, 489, 490, 491, 492, 493, 494, 495, 496, 500, 501, 504, 505, 506, 507, 508, 509, 510,
511, 512, 513, 514, 515, 516, 517, 518, 519, 520, 521, 522, 523, 524, 525, 526, 527, 528, 529, 530, 531, 532, 533,
534, 535, 536, 537, 538, 539, 542, 543, 550, 551, 552, 553, 554, 555, 556, 557, 558, 559, 560, 561, 562, 563, 832,
833, 835, 836, 884, 894, 901, 902, 903, 904, 905, 906, 908, 910, 911, 912, 938, 939, 940, 941, 942, 943, 944, 970,
971, 972, 973, 974, 979, 980, 1024, 1025, 1027, 1031, 1036, 1037, 1038, 1049, 1081, 1104, 1105, 1107, 1111, 1116,
1117, 1118, 1142, 1143, 1217, 1218, 1232, 1233, 1234, 1235, 1238, 1239, 1242, 1243, 1244, 1245, 1246, 1247, 1250,
1251, 1252, 1253, 1254, 1255, 1258, 1259, 1260, 1261, 1262, 1263, 1264, 1265, 1266, 1267, 1268, 1269, 1272, 1273,
1570, 1571, 1572, 1573, 1574, 1728, 1730, 1747, 2345, 2353, 2356, 2392, 2393, 2394, 2395, 2396, 2397, 2398, 2399,
2507, 2508, 2524, 2525, 2527, 2611, 2614, 2649, 2650, 2651, 2654, 2888, 2891, 2892, 2908, 2909, 2964, 3018, 3019,
3020, 3144, 3264, 3271, 3272, 3274, 3275, 3402, 3403, 3404, 3546, 3548, 3549, 3550, 3907, 3917, 3922, 3927, 3932,
3945, 3955, 3957, 3958, 3960, 3969, 3987, 3997, 4002, 4007, 4012, 4025, 4134, 7680, 7681, 7682, 7683, 7684, 7685,
7686, 7687, 7688, 7689, 7690, 7691, 7692, 7693, 7694, 7695, 7696, 7697, 7698, 7699, 7700, 7701, 7702, 7703, 7704,
7705, 7706, 7707, 7708, 7709, 7710, 7711, 7712, 7713, 7714, 7715, 7716, 7717, 7718, 7719, 7720, 7721, 7722, 7723,
7724, 7725, 7726, 7727, 7728, 7729, 7730, 7731, 7732, 7733, 7734, 7735, 7736, 7737, 7738, 7739, 7740, 7741, 7742,
7743, 7744, 7745, 7746, 7747, 7748, 7749, 7750, 7751, 7752, 7753, 7754, 7755, 7756, 7757, 7758, 7759, 7760, 7761,
7762, 7763, 7764, 7765, 7766, 7767, 7768, 7769, 7770, 7771, 7772, 7773, 7774, 7775, 7776, 7777, 7778, 7779, 7780,
7781, 7782, 7783, 7784, 7785, 7786, 7787, 7788, 7789, 7790, 7791, 7792, 7793, 7794, 7795, 7796, 7797, 7798, 7799,
7800, 7801, 7802, 7803, 7804, 7805, 7806, 7807, 7808, 7809, 7810, 7811, 7812, 7813, 7814, 7815, 7816, 7817, 7818,
7819, 7820, 7821, 7822, 7823, 7824, 7825, 7826, 7827, 7828, 7829, 7830, 7831, 7832, 7833, 7835, 7840, 7841, 7842,
7843, 7844, 7845, 7846, 7847, 7848, 7849, 7850, 7851, 7852, 7853, 7854, 7855, 7856, 7857, 7858, 7859, 7860, 7861,
7862, 7863, 7864, 7865, 7866, 7867, 7868, 7869, 7870, 7871, 7872, 7873, 7874, 7875, 7876, 7877, 7878, 7879, 7880,
7881, 7882, 7883, 7884, 7885, 7886, 7887, 7888, 7889, 7890, 7891, 7892, 7893, 7894, 7895, 7896, 7897, 7898, 7899,
7900, 7901, 7902, 7903, 7904, 7905, 7906, 7907, 7908, 7909, 7910, 7911, 7912, 7913, 7914, 7915, 7916, 7917, 7918,
7919, 7920, 7921, 7922, 7923, 7924, 7925, 7926, 7927, 7928, 7929, 7936, 7937, 7938, 7939, 7940, 7941, 7942, 7943,
7944, 7945, 7946, 7947, 7948, 7949, 7950, 7951, 7952, 7953, 7954, 7955, 7956, 7957, 7960, 7961, 7962, 7963, 7964,
7965, 7968, 7969, 7970, 7971, 7972, 7973, 7974, 7975, 7976, 7977, 7978, 7979, 7980, 7981, 7982, 7983, 7984, 7985,
7986, 7987, 7988, 7989, 7990, 7991, 7992, 7993, 7994, 7995, 7996, 7997, 7998, 7999, 8000, 8001, 8002, 8003, 8004,
8005, 8008, 8009, 8010, 8011, 8012, 8013, 8016, 8017, 8018, 8019, 8020, 8021, 8022, 8023, 8025, 8027, 8029, 8031,
8032, 8033, 8034, 8035, 8036, 8037, 8038, 8039, 8040, 8041, 8042, 8043, 8044, 8045, 8046, 8047, 8048, 8049, 8050,
8051, 8052, 8053, 8054, 8055, 8056, 8057, 8058, 8059, 8060, 8061, 8064, 8065, 8066, 8067, 8068, 8069, 8070, 8071,
8072, 8073, 8074, 8075, 8076, 8077, 8078, 8079, 8080, 8081, 8082, 8083, 8084, 8085, 8086, 8087, 8088, 8089, 8090,
8091, 8092, 8093, 8094, 8095, 8096, 8097, 8098, 8099, 8100, 8101, 8102, 8103, 8104, 8105, 8106, 8107, 8108, 8109,
8110, 8111, 8112, 8113, 8114, 8115, 8116, 8118, 8119, 8120, 8121, 8122, 8123, 8124, 8126, 8129, 8130, 8131, 8132,
8134, 8135, 8136, 8137, 8138, 8139, 8140, 8141, 8142, 8143, 8144, 8145, 8146, 8147, 8150, 8151, 8152, 8153, 8154,
8155, 8157, 8158, 8159, 8160, 8161, 8162, 8163, 8164, 8165, 8166, 8167, 8168, 8169, 8170, 8171, 8172, 8173, 8174,
8175, 8178, 8179, 8180, 8182, 8183, 8184, 8185, 8186, 8187, 8188, 8189, 8192, 8193, 8486, 8490, 8491, 8602, 8603,
8622, 8653, 8654, 8655, 8708, 8713, 8716, 8740, 8742, 8769, 8772, 8775, 8777, 8800, 8802, 8813, 8814, 8815, 8816,
8817, 8820, 8821, 8824, 8825, 8832, 8833, 8836, 8837, 8840, 8841, 8876, 8877, 8878, 8879, 8928, 8929, 8930, 8931,
8938, 8939, 8940, 8941, 9001, 9002, 10972, 12364, 12366, 12368, 12370, 12372, 12374, 12376, 12378, 12380, 12382,
12384, 12386, 12389, 12391, 12393, 12400, 12401, 12403, 12404, 12406, 12407, 12409, 12410, 12412, 12413, 12436, 12446,
12460, 12462, 12464, 12466, 12468, 12470, 12472, 12474, 12476, 12478, 12480, 12482, 12485, 12487, 12489, 12496, 12497,
12499, 12500, 12502, 12503, 12505, 12506, 12508, 12509, 12532, 12535, 12536, 12537, 12538, 12542, 63744, 63745, 63746,
63747, 63748, 63749, 63750, 63751, 63752, 63753, 63754, 63755, 63756, 63757, 63758, 63759, 63760, 63761, 63762, 63763,
63764, 63765, 63766, 63767, 63768, 63769, 63770, 63771, 63772, 63773, 63774, 63775, 63776, 63777, 63778, 63779, 63780,
63781, 63782, 63783, 63784, 63785, 63786, 63787, 63788, 63789, 63790, 63791, 63792, 63793, 63794, 63795, 63796, 63797,
63798, 63799, 63800, 63801, 63802, 63803, 63804, 63805, 63806, 63807, 63808, 63809, 63810, 63811, 63812, 63813, 63814,
63815, 63816, 63817, 63818, 63819, 63820, 63821, 63822, 63823, 63824, 63825, 63826, 63827, 63828, 63829, 63830, 63831,
63832, 63833, 63834, 63835, 63836, 63837, 63838, 63839, 63840, 63841, 63842, 63843, 63844, 63845, 63846, 63847, 63848,
63849, 63850, 63851, 63852, 63853, 63854, 63855, 63856, 63857, 63858, 63859, 63860, 63861, 63862, 63863, 63864, 63865,
63866, 63867, 63868, 63869, 63870, 63871, 63872, 63873, 63874, 63875, 63876, 63877, 63878, 63879, 63880, 63881, 63882,
63883, 63884, 63885, 63886, 63887, 63888, 63889, 63890, 63891, 63892, 63893, 63894, 63895, 63896, 63897, 63898, 63899,
63900, 63901, 63902, 63903, 63904, 63905, 63906, 63907, 63908, 63909, 63910, 63911, 63912, 63913, 63914, 63915, 63916,
63917, 63918, 63919, 63920, 63921, 63922, 63923, 63924, 63925, 63926, 63927, 63928, 63929, 63930, 63931, 63932, 63933,
63934, 63935, 63936, 63937, 63938, 63939, 63940, 63941, 63942, 63943, 63944, 63945, 63946, 63947, 63948, 63949, 63950,
63951, 63952, 63953, 63954, 63955, 63956, 63957, 63958, 63959, 63960, 63961, 63962, 63963, 63964, 63965, 63966, 63967,
63968, 63969, 63970, 63971, 63972, 63973, 63974, 63975, 63976, 63977, 63978, 63979, 63980, 63981, 63982, 63983, 63984,
63985, 63986, 63987, 63988, 63989, 63990, 63991, 63992, 63993, 63994, 63995, 63996, 63997, 63998, 63999, 64000, 64001,
64002, 64003, 64004, 64005, 64006, 64007, 64008, 64009, 64010, 64011, 64012, 64013, 64016, 64018, 64021, 64022, 64023,
64024, 64025, 64026, 64027, 64028, 64029, 64030, 64032, 64034, 64037, 64038, 64042, 64043, 64044, 64045, 64048, 64049,
64050, 64051, 64052, 64053, 64054, 64055, 64056, 64057, 64058, 64059, 64060, 64061, 64062, 64063, 64064, 64065, 64066,
64067, 64068, 64069, 64070, 64071, 64072, 64073, 64074, 64075, 64076, 64077, 64078, 64079, 64080, 64081, 64082, 64083,
64084, 64085, 64086, 64087, 64088, 64089, 64090, 64091, 64092, 64093, 64094, 64095, 64096, 64097, 64098, 64099, 64100,
64101, 64102, 64103, 64104, 64105, 64106, 64112, 64113, 64114, 64115, 64116, 64117, 64118, 64119, 64120, 64121, 64122,
64123, 64124, 64125, 64126, 64127, 64128, 64129, 64130, 64131, 64132, 64133, 64134, 64135, 64136, 64137, 64138, 64139,
64140, 64141, 64142, 64143, 64144, 64145, 64146, 64147, 64148, 64149, 64150, 64151, 64152, 64153, 64154, 64155, 64156,
64157, 64158, 64159, 64160, 64161, 64162, 64163, 64164, 64165, 64166, 64167, 64168, 64169, 64170, 64171, 64172, 64173,
64174, 64175, 64176, 64177, 64178, 64179, 64180, 64181, 64182, 64183, 64184, 64185, 64186, 64187, 64188, 64189, 64190,
64191, 64192, 64193, 64194, 64195, 64196, 64197, 64198, 64199, 64200, 64201, 64202, 64203, 64204, 64205, 64206, 64207,
64208, 64209, 64210, 64211, 64212, 64213, 64214, 64215, 64216, 64217, 64285, 64287, 64298, 64299, 64300, 64301, 64302,
64303, 64304, 64305, 64306, 64307, 64308, 64309, 64310, 64312, 64313, 64314, 64315, 64316, 64318, 64320, 64321, 64323,
64324, 64326, 64327, 64328, 64329, 64330, 64331, 64332, 64333, 64334, 119134, 119135, 119136, 119137, 119138, 119139,
119140, 119227, 119228, 119229, 119230, 119231, 119232, 194560, 194561, 194562, 194563, 194564, 194565, 194566,
194567, 194568, 194569, 194570, 194571, 194572, 194573, 194574, 194575, 194576, 194577, 194578, 194579, 194580,
194581, 194582, 194583, 194584, 194585, 194586, 194587, 194588, 194589, 194590, 194591, 194592, 194593, 194594,
194595, 194596, 194597, 194598, 194599, 194600, 194601, 194602, 194603, 194604, 194605, 194606, 194607, 194608,
194609, 194610, 194611, 194612, 194613, 194614, 194615, 194616, 194617, 194618, 194619, 194620, 194621, 194622,
194623, 194624, 194625, 194626, 194627, 194628, 194629, 194630, 194631, 194632, 194633, 194634, 194635, 194636,
194637, 194638, 194639, 194640, 194641, 194642, 194643, 194644, 194645, 194646, 194647, 194648, 194649, 194650,
194651, 194652, 194653, 194654, 194655, 194656, 194657, 194658, 194659, 194660, 194661, 194662, 194663, 194664,
194665, 194666, 194667, 194668, 194669, 194670, 194671, 194672, 194673, 194674, 194675, 194676, 194677, 194678,
194679, 194680, 194681, 194682, 194683, 194684, 194685, 194686, 194687, 194688, 194689, 194690, 194691, 194692,
194693, 194694, 194695, 194696, 194697, 194698, 194699, 194700, 194701, 194702, 194703, 194704, 194705, 194706,
194707, 194708, 194709, 194710, 194711, 194712, 194713, 194714, 194715, 194716, 194717, 194718, 194719, 194720,
194721, 194722, 194723, 194724, 194725, 194726, 194727, 194728, 194729, 194730, 194731, 194732, 194733, 194734,
194735, 194736, 194737, 194738, 194739, 194740, 194741, 194742, 194743, 194744, 194745, 194746, 194747, 194748,
194749, 194750, 194751, 194752, 194753, 194754, 194755, 194756, 194757, 194758, 194759, 194760, 194761, 194762,
194763, 194764, 194765, 194766, 194767, 194768, 194769, 194770, 194771, 194772, 194773, 194774, 194775, 194776,
194777, 194778, 194779, 194780, 194781, 194782, 194783, 194784, 194785, 194786, 194787, 194788, 194789, 194790,
194791, 194792, 194793, 194794, 194795, 194796, 194797, 194798, 194799, 194800, 194801, 194802, 194803, 194804,
194805, 194806, 194807, 194808, 194809, 194810, 194811, 194812, 194813, 194814, 194815, 194816, 194817, 194818,
194819, 194820, 194821, 194822, 194823, 194824, 194825, 194826, 194827, 194828, 194829, 194830, 194831, 194832,
194833, 194834, 194835, 194836, 194837, 194838, 194839, 194840, 194841, 194842, 194843, 194844, 194845, 194846,
194847, 194848, 194849, 194850, 194851, 194852, 194853, 194854, 194855, 194856, 194857, 194858, 194859, 194860,
194861, 194862, 194863, 194864, 194865, 194866, 194867, 194868, 194869, 194870, 194871, 194872, 194873, 194874,
194875, 194876, 194877, 194878, 194879, 194880, 194881, 194882, 194883, 194884, 194885, 194886, 194887, 194888,
194889, 194890, 194891, 194892, 194893, 194894, 194895, 194896, 194897, 194898, 194899, 194900, 194901, 194902,
194903, 194904, 194905, 194906, 194907, 194908, 194909, 194910, 194911, 194912, 194913, 194914, 194915, 194916,
194917, 194918, 194919, 194920, 194921, 194922, 194923, 194924, 194925, 194926, 194927, 194928, 194929, 194930,
194931, 194932, 194933, 194934, 194935, 194936, 194937, 194938, 194939, 194940, 194941, 194942, 194943, 194944,
194945, 194946, 194947, 194948, 194949, 194950, 194951, 194952, 194953, 194954, 194955, 194956, 194957, 194958,
194959, 194960, 194961, 194962, 194963, 194964, 194965, 194966, 194967, 194968, 194969, 194970, 194971, 194972,
194973, 194974, 194975, 194976, 194977, 194978, 194979, 194980, 194981, 194982, 194983, 194984, 194985, 194986,
194987, 194988, 194989, 194990, 194991, 194992, 194993, 194994, 194995, 194996, 194997, 194998, 194999, 195000,
195001, 195002, 195003, 195004, 195005, 195006, 195007, 195008, 195009, 195010, 195011, 195012, 195013, 195014,
195015, 195016, 195017, 195018, 195019, 195020, 195021, 195022, 195023, 195024, 195025, 195026, 195027, 195028,
195029, 195030, 195031, 195032, 195033, 195034, 195035, 195036, 195037, 195038, 195039, 195040, 195041, 195042,
195043, 195044, 195045, 195046, 195047, 195048, 195049, 195050, 195051, 195052, 195053, 195054, 195055, 195056,
195057, 195058, 195059, 195060, 195061, 195062, 195063, 195064, 195065, 195066, 195067, 195068, 195069, 195070,
195071, 195072, 195073, 195074, 195075, 195076, 195077, 195078, 195079, 195080, 195081, 195082, 195083, 195084,
195085, 195086, 195087, 195088, 195089, 195090, 195091, 195092, 195093, 195094, 195095, 195096, 195097, 195098,
195099, 195100, 195101
)
private fun getCanonicalClass(ch: Int): Int {
val index: Int = binarySearchRange(canonicalClassesKeys, ch)
if (index == -1 || canonicalClassesKeys[index] != ch) {
return 0
}
return canonicalClassesValues[index]
}
private fun getDecomposition(codePoint: Int): IntArray? {
val index: Int = binarySearchRange(decompositionKeys, codePoint)
if (index == -1 || decompositionKeys[index] != codePoint) {
return null
}
return decompositionValues[index]
}
/** Gets canonical class for given codepoint from decomposition mappings table. */
internal fun getCanonicalClassInternal(ch: Int): Int {
return getCanonicalClass(ch)
}
/** Check if the given character is in table of single decompositions. */
internal fun hasSingleCodepointDecompositionInternal(ch: Int): Boolean {
val index: Int = binarySearchRange(singleDecompositions, ch)
return index != -1 && singleDecompositions[index] == ch
}
/** Returns a decomposition for a given codepoint. */
internal fun getDecompositionInternal(ch: Int): IntArray? = getDecomposition(ch)
/**
* Decomposes the given string represented as an array of codepoints. Saves the decomposition into [outputCodepoints] array.
* Returns the length of the decomposition.
*/
internal fun decomposeString(inputCodePoints: IntArray, inputLength: Int, outputCodePoints: IntArray): Int {
if (inputLength == 0) return 0
var outputLength = 0
for (i in 0 until inputLength) {
val decomposition = getDecomposition(inputCodePoints[i])
if (decomposition == null) {
outputCodePoints[outputLength++] = inputCodePoints[i]
} else {
decomposition.copyInto(outputCodePoints, outputLength)
outputLength += decomposition.size
}
}
return outputLength
}
/**
* Decomposes the given codepoint. Saves the decomposition into [outputCodepoints] array starting with [fromIndex].
* Returns the length of the decomposition.
*/
internal fun decomposeCodePoint(codePoint: Int, outputCodePoints: IntArray, fromIndex: Int): Int {
val decomposition = getDecomposition(codePoint)
if (decomposition == null) {
outputCodePoints[fromIndex] = codePoint
return 1
} else {
decomposition.copyInto(outputCodePoints, fromIndex)
return decomposition.size
}
}
/**
* Returns the index of the largest element in [array] smaller or equal to the specified [needle],
* or -1 if [needle] is smaller than the smallest element in [array].
*/
private fun binarySearchRange(array: IntArray, needle: Int): Int {
var bottom = 0
var top = array.size - 1
var middle = -1
var value = 0
while (bottom <= top) {
middle = (bottom + top) / 2
value = array[middle]
if (needle > value)
bottom = middle + 1
else if (needle == value)
return middle
else
top = middle - 1
}
return middle - (if (needle < value) 1 else 0)
}
libraries/stdlib/wasm/src/kotlin/text/regex/DecompositionValues.kt
+2041
View File
File diff suppressed because it is too large Load Diff