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

Commonize CharCategory and related functions #KT-39177 #KT-43216 #KT-39906 #KT-30652

Browse Source
This commit is contained in:
Abduqodiri Qurbonzoda
2020-10-13 02:39:07 +03:00
parent 9b429fb535
commit 46b7a774b5
40 changed files with 3573 additions and 62 deletions
Download Patch File Download Diff File Expand all files Collapse all files
libraries/stdlib/jvm/src/kotlin/text/CharCategory.kt → libraries/stdlib/jvm/src/kotlin/text/CharCategoryJVM.kt
+46 -42
View File
@@ -1,173 +1,177 @@
/*
* Copyright 2010-2018 JetBrains s.r.o. and Kotlin Programming Language contributors.
* 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
/**
* Represents the character general category in the Unicode specification.
*/
public enum class CharCategory(public val value: Int, public val code: String) {
public actual enum class CharCategory(public val value: Int, public actual val code: String) {
/**
* General category "Cn" in the Unicode specification.
*/
UNASSIGNED(Character.UNASSIGNED.toInt(), "Cn"),
UNASSIGNED(0, "Cn"),
/**
* General category "Lu" in the Unicode specification.
*/
UPPERCASE_LETTER(Character.UPPERCASE_LETTER.toInt(), "Lu"),
UPPERCASE_LETTER(1, "Lu"),
/**
* General category "Ll" in the Unicode specification.
*/
LOWERCASE_LETTER(Character.LOWERCASE_LETTER.toInt(), "Ll"),
LOWERCASE_LETTER(2, "Ll"),
/**
* General category "Lt" in the Unicode specification.
*/
TITLECASE_LETTER(Character.TITLECASE_LETTER.toInt(), "Lt"),
TITLECASE_LETTER(3, "Lt"),
/**
* General category "Lm" in the Unicode specification.
*/
MODIFIER_LETTER(Character.MODIFIER_LETTER.toInt(), "Lm"),
MODIFIER_LETTER(4, "Lm"),
/**
* General category "Lo" in the Unicode specification.
*/
OTHER_LETTER(Character.OTHER_LETTER.toInt(), "Lo"),
OTHER_LETTER(5, "Lo"),
/**
* General category "Mn" in the Unicode specification.
*/
NON_SPACING_MARK(Character.NON_SPACING_MARK.toInt(), "Mn"),
NON_SPACING_MARK(6, "Mn"),
/**
* General category "Me" in the Unicode specification.
*/
ENCLOSING_MARK(Character.ENCLOSING_MARK.toInt(), "Me"),
ENCLOSING_MARK(7, "Me"),
/**
* General category "Mc" in the Unicode specification.
*/
COMBINING_SPACING_MARK(Character.COMBINING_SPACING_MARK.toInt(), "Mc"),
COMBINING_SPACING_MARK(8, "Mc"),
/**
* General category "Nd" in the Unicode specification.
*/
DECIMAL_DIGIT_NUMBER(Character.DECIMAL_DIGIT_NUMBER.toInt(), "Nd"),
DECIMAL_DIGIT_NUMBER(9, "Nd"),
/**
* General category "Nl" in the Unicode specification.
*/
LETTER_NUMBER(Character.LETTER_NUMBER.toInt(), "Nl"),
LETTER_NUMBER(10, "Nl"),
/**
* General category "No" in the Unicode specification.
*/
OTHER_NUMBER(Character.OTHER_NUMBER.toInt(), "No"),
OTHER_NUMBER(11, "No"),
/**
* General category "Zs" in the Unicode specification.
*/
SPACE_SEPARATOR(Character.SPACE_SEPARATOR.toInt(), "Zs"),
SPACE_SEPARATOR(12, "Zs"),
/**
* General category "Zl" in the Unicode specification.
*/
LINE_SEPARATOR(Character.LINE_SEPARATOR.toInt(), "Zl"),
LINE_SEPARATOR(13, "Zl"),
/**
* General category "Zp" in the Unicode specification.
*/
PARAGRAPH_SEPARATOR(Character.PARAGRAPH_SEPARATOR.toInt(), "Zp"),
PARAGRAPH_SEPARATOR(14, "Zp"),
/**
* General category "Cc" in the Unicode specification.
*/
CONTROL(Character.CONTROL.toInt(), "Cc"),
CONTROL(15, "Cc"),
/**
* General category "Cf" in the Unicode specification.
*/
FORMAT(Character.FORMAT.toInt(), "Cf"),
FORMAT(16, "Cf"),
/**
* General category "Co" in the Unicode specification.
*/
PRIVATE_USE(Character.PRIVATE_USE.toInt(), "Co"),
PRIVATE_USE(18, "Co"),
/**
* General category "Cs" in the Unicode specification.
*/
SURROGATE(Character.SURROGATE.toInt(), "Cs"),
SURROGATE(19, "Cs"),
/**
* General category "Pd" in the Unicode specification.
*/
DASH_PUNCTUATION(Character.DASH_PUNCTUATION.toInt(), "Pd"),
DASH_PUNCTUATION(20, "Pd"),
/**
* General category "Ps" in the Unicode specification.
*/
START_PUNCTUATION(Character.START_PUNCTUATION.toInt(), "Ps"),
START_PUNCTUATION(21, "Ps"),
/**
* General category "Pe" in the Unicode specification.
*/
END_PUNCTUATION(Character.END_PUNCTUATION.toInt(), "Pe"),
END_PUNCTUATION(22, "Pe"),
/**
* General category "Pc" in the Unicode specification.
*/
CONNECTOR_PUNCTUATION(Character.CONNECTOR_PUNCTUATION.toInt(), "Pc"),
CONNECTOR_PUNCTUATION(23, "Pc"),
/**
* General category "Po" in the Unicode specification.
*/
OTHER_PUNCTUATION(Character.OTHER_PUNCTUATION.toInt(), "Po"),
OTHER_PUNCTUATION(24, "Po"),
/**
* General category "Sm" in the Unicode specification.
*/
MATH_SYMBOL(Character.MATH_SYMBOL.toInt(), "Sm"),
MATH_SYMBOL(25, "Sm"),
/**
* General category "Sc" in the Unicode specification.
*/
CURRENCY_SYMBOL(Character.CURRENCY_SYMBOL.toInt(), "Sc"),
CURRENCY_SYMBOL(26, "Sc"),
/**
* General category "Sk" in the Unicode specification.
*/
MODIFIER_SYMBOL(Character.MODIFIER_SYMBOL.toInt(), "Sk"),
MODIFIER_SYMBOL(27, "Sk"),
/**
* General category "So" in the Unicode specification.
*/
OTHER_SYMBOL(Character.OTHER_SYMBOL.toInt(), "So"),
OTHER_SYMBOL(28, "So"),
/**
* General category "Pi" in the Unicode specification.
*/
INITIAL_QUOTE_PUNCTUATION(Character.INITIAL_QUOTE_PUNCTUATION.toInt(), "Pi"),
INITIAL_QUOTE_PUNCTUATION(29, "Pi"),
/**
* General category "Pf" in the Unicode specification.
*/
FINAL_QUOTE_PUNCTUATION(Character.FINAL_QUOTE_PUNCTUATION.toInt(), "Pf");
FINAL_QUOTE_PUNCTUATION(30, "Pf");
/**
* Returns `true` if [char] character belongs to this category.
*/
public operator fun contains(char: Char): Boolean = Character.getType(char) == this.value
public actual operator fun contains(char: Char): Boolean = Character.getType(char) == this.value
public companion object {
private val categoryMap by lazy { CharCategory.values().associateBy { it.value } }
public fun valueOf(category: Int): CharCategory = categoryMap[category] ?: throw IllegalArgumentException("Category #$category is not defined.")
companion object {
/**
* Returns the [CharCategory] corresponding to the specified [category] that represents a Java general category constant.
*
* @throws IllegalArgumentException if the [category] does not represent a Java general category constant.
*/
public fun valueOf(category: Int): CharCategory =
when (category) {
in 0..16 -> values()[category]
in 18..30 -> values()[category - 1]
else -> throw IllegalArgumentException("Category #$category is not defined.")
}
}
}
}
libraries/stdlib/jvm/src/kotlin/text/CharJVM.kt
+32 -14
View File
@@ -10,32 +10,51 @@ package kotlin.text
import java.util.Locale
/**
* Returns the Unicode general category of this character.
*/
public actual val Char.category: CharCategory
get() = CharCategory.valueOf(Character.getType(this))
/**
* 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].
*/
@kotlin.internal.InlineOnly
public inline fun Char.isDefined(): Boolean = Character.isDefined(this)
public actual inline fun Char.isDefined(): Boolean = Character.isDefined(this)
/**
* 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
*/
@kotlin.internal.InlineOnly
public inline fun Char.isLetter(): Boolean = Character.isLetter(this)
public actual inline fun Char.isLetter(): Boolean = Character.isLetter(this)
/**
* Returns `true` if this character is a letter or digit.
*
* @see isLetter
* @see isDigit
*
* @sample samples.text.Chars.isLetterOrDigit
*/
@kotlin.internal.InlineOnly
public inline fun Char.isLetterOrDigit(): Boolean = Character.isLetterOrDigit(this)
public actual inline fun Char.isLetterOrDigit(): Boolean = Character.isLetterOrDigit(this)
/**
* Returns `true` if this character (Unicode code point) is a digit.
* 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
*/
@kotlin.internal.InlineOnly
public inline fun Char.isDigit(): Boolean = Character.isDigit(this)
public actual inline fun Char.isDigit(): Boolean = Character.isDigit(this)
/**
@@ -47,10 +66,13 @@ public inline fun Char.isIdentifierIgnorable(): Boolean = Character.isIdentifier
/**
* 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
*/
@kotlin.internal.InlineOnly
public inline fun Char.isISOControl(): Boolean = Character.isISOControl(this)
public actual inline fun Char.isISOControl(): Boolean = Character.isISOControl(this)
/**
* Returns `true` if this character (Unicode code point) may be part of a Java identifier as other than the first character.
@@ -69,6 +91,7 @@ public inline fun Char.isJavaIdentifierStart(): Boolean = Character.isJavaIdenti
/**
* 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 = Character.isWhitespace(this) || Character.isSpaceChar(this)
@@ -78,14 +101,14 @@ public actual fun Char.isWhitespace(): Boolean = Character.isWhitespace(this) ||
* @sample samples.text.Chars.isUpperCase
*/
@kotlin.internal.InlineOnly
public inline fun Char.isUpperCase(): Boolean = Character.isUpperCase(this)
public actual inline fun Char.isUpperCase(): Boolean = Character.isUpperCase(this)
/**
* Returns `true` if this character is lower case.
* @sample samples.text.Chars.isLowerCase
*/
@kotlin.internal.InlineOnly
public inline fun Char.isLowerCase(): Boolean = Character.isLowerCase(this)
public actual inline fun Char.isLowerCase(): Boolean = Character.isLowerCase(this)
/**
* Converts this character to lower case using Unicode mapping rules of the invariant locale.
@@ -192,7 +215,7 @@ public fun Char.lowercase(locale: Locale): String = toString().lowercase(locale)
* @sample samples.text.Chars.isTitleCase
*/
@kotlin.internal.InlineOnly
public inline fun Char.isTitleCase(): Boolean = Character.isTitleCase(this)
public actual inline fun Char.isTitleCase(): Boolean = Character.isTitleCase(this)
/**
* Converts this character to title case using Unicode mapping rules of the invariant locale.
@@ -260,11 +283,6 @@ public fun Char.titlecase(locale: Locale): String {
return titlecaseChar().toString()
}
/**
* Returns a value indicating a character's general category.
*/
public val Char.category: CharCategory get() = CharCategory.valueOf(Character.getType(this))
/**
* Returns the Unicode directionality property for the given character.
*/