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

2020-10-13 02:39:07 +03:00
parent 9b429fb535
commit 46b7a774b5
40 changed files with 3573 additions and 62 deletions
@@ -227,3 +227,88 @@ public fun Char.equals(other: Char, ignoreCase: Boolean = false): Boolean {
 * Returns `true` if this character is a Unicode surrogate code unit.
 */
 public fun Char.isSurrogate(): Boolean = this in Char.MIN_SURROGATE..Char.MAX_SURROGATE
+
+/**
+ * Returns the Unicode general category of this character.
+ */
+public expect val Char.category: CharCategory
+
+/**
+ * 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].
+ */
+public expect fun Char.isDefined(): Boolean
+
+/**
+ * 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
+ */
+public expect fun Char.isLetter(): Boolean
+
+/**
+ * Returns `true` if this character is a letter or digit.
+ *
+ * @see isLetter
+ * @see isDigit
+ *
+ * @sample samples.text.Chars.isLetterOrDigit
+ */
+public expect fun Char.isLetterOrDigit(): Boolean
+
+/**
+ * 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
+ */
+public expect fun Char.isDigit(): Boolean
+
+/**
+ * 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
+ */
+public expect fun Char.isUpperCase(): Boolean
+
+/**
+ * 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
+ */
+public expect fun Char.isLowerCase(): Boolean
+
+/**
+ * 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
+ */
+public expect fun Char.isTitleCase(): Boolean
+
+/**
+ * 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
+ */
+public expect fun Char.isISOControl(): Boolean
+
+/**
+ * Determines whether a character is whitespace according to the Unicode standard.
+ * Returns `true` if the character is whitespace.
+ *
+ * @sample samples.text.Chars.isWhitespace
+ */
+public expect fun Char.isWhitespace(): Boolean
@@ -0,0 +1,171 @@
+/*
+ * 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 expect enum class CharCategory {
+    /**
+     * General category "Cn" in the Unicode specification.
+     */
+    UNASSIGNED,
+
+    /**
+     * General category "Lu" in the Unicode specification.
+     */
+    UPPERCASE_LETTER,
+
+    /**
+     * General category "Ll" in the Unicode specification.
+     */
+    LOWERCASE_LETTER,
+
+    /**
+     * General category "Lt" in the Unicode specification.
+     */
+    TITLECASE_LETTER,
+
+    /**
+     * General category "Lm" in the Unicode specification.
+     */
+    MODIFIER_LETTER,
+
+    /**
+     * General category "Lo" in the Unicode specification.
+     */
+    OTHER_LETTER,
+
+    /**
+     * General category "Mn" in the Unicode specification.
+     */
+    NON_SPACING_MARK,
+
+    /**
+     * General category "Me" in the Unicode specification.
+     */
+    ENCLOSING_MARK,
+
+    /**
+     * General category "Mc" in the Unicode specification.
+     */
+    COMBINING_SPACING_MARK,
+
+    /**
+     * General category "Nd" in the Unicode specification.
+     */
+    DECIMAL_DIGIT_NUMBER,
+
+    /**
+     * General category "Nl" in the Unicode specification.
+     */
+    LETTER_NUMBER,
+
+    /**
+     * General category "No" in the Unicode specification.
+     */
+    OTHER_NUMBER,
+
+    /**
+     * General category "Zs" in the Unicode specification.
+     */
+    SPACE_SEPARATOR,
+
+    /**
+     * General category "Zl" in the Unicode specification.
+     */
+    LINE_SEPARATOR,
+
+    /**
+     * General category "Zp" in the Unicode specification.
+     */
+    PARAGRAPH_SEPARATOR,
+
+    /**
+     * General category "Cc" in the Unicode specification.
+     */
+    CONTROL,
+
+    /**
+     * General category "Cf" in the Unicode specification.
+     */
+    FORMAT,
+
+    /**
+     * General category "Co" in the Unicode specification.
+     */
+    PRIVATE_USE,
+
+    /**
+     * General category "Cs" in the Unicode specification.
+     */
+    SURROGATE,
+
+    /**
+     * General category "Pd" in the Unicode specification.
+     */
+    DASH_PUNCTUATION,
+
+    /**
+     * General category "Ps" in the Unicode specification.
+     */
+    START_PUNCTUATION,
+
+    /**
+     * General category "Pe" in the Unicode specification.
+     */
+    END_PUNCTUATION,
+
+    /**
+     * General category "Pc" in the Unicode specification.
+     */
+    CONNECTOR_PUNCTUATION,
+
+    /**
+     * General category "Po" in the Unicode specification.
+     */
+    OTHER_PUNCTUATION,
+
+    /**
+     * General category "Sm" in the Unicode specification.
+     */
+    MATH_SYMBOL,
+
+    /**
+     * General category "Sc" in the Unicode specification.
+     */
+    CURRENCY_SYMBOL,
+
+    /**
+     * General category "Sk" in the Unicode specification.
+     */
+    MODIFIER_SYMBOL,
+
+    /**
+     * General category "So" in the Unicode specification.
+     */
+    OTHER_SYMBOL,
+
+    /**
+     * General category "Pi" in the Unicode specification.
+     */
+    INITIAL_QUOTE_PUNCTUATION,
+
+    /**
+     * General category "Pf" in the Unicode specification.
+     */
+    FINAL_QUOTE_PUNCTUATION;
+
+    /**
+     * Two-letter code of this general category in the Unicode specification.
+     */
+    public val code: String
+
+    /**
+     * Returns `true` if [char] character belongs to this category.
+     */
+    public operator fun contains(char: Char): Boolean
+}