Allow diacritics in names of classes, functions packages, and propert…

…ies (#1780)

Closes #1757

CHANGELOG.md

@@ -57,6 +57,7 @@ If you do want to ignore the value of `ktlint_experimental` as set by the user,
 * Fix with array-syntax annotations on the same line as other annotations `annotation` ([#1765](https://github.com/pinterest/ktlint/issues/1765))
 * Do not enable the experimental rules by default when `.editorconfig` properties `disabled_rules` or `ktlint_disabled_rules` are set. ([#1771](https://github.com/pinterest/ktlint/issues/1771))
 * A function signature not having any parameters which exceeds the `max-line-length` should be ignored by rule `function-signature` ([#1773](https://github.com/pinterest/ktlint/issues/1773))
+* Allow diacritics in names of classes, functions packages, and properties `class-naming`, `function-naming`, `package-name`, `property-naming` ([#1757](https://github.com/pinterest/ktlint/issues/1757))
 * Prevent violation of `file-name` rule on code snippets ([#1768](https://github.com/pinterest/ktlint/issues/1768))
 * Clarify that API Consumers have to enable experimental rules ([#1768](https://github.com/pinterest/ktlint/issues/1768))
 * Trim spaces in the `.editorconfig` property `ij_kotlin_imports_layout`'s entries ([#1770](https://github.com/pinterest/ktlint/pull/1770))

ktlint-ruleset-experimental/src/main/kotlin/com/pinterest/ktlint/ruleset/experimental/ClassNamingRule.kt

@@ -5,6 +5,7 @@ import com.pinterest.ktlint.core.ast.ElementType
 import com.pinterest.ktlint.core.ast.ElementType.CLASS
 import com.pinterest.ktlint.core.ast.ElementType.IDENTIFIER
 import com.pinterest.ktlint.core.ast.ElementType.OBJECT_DECLARATION
+import com.pinterest.ktlint.ruleset.experimental.internal.regExIgnoringDiacriticsAndStrokesOnLetters
 import org.jetbrains.kotlin.com.intellij.lang.ASTNode
 
 /**
@@ -51,7 +52,7 @@ public class ClassNamingRule : Rule("$EXPERIMENTAL_RULE_SET_ID:class-naming") {
         text.matches(BACK_TICKED_FUNCTION_NAME_REGEXP)
 
     private companion object {
-        val VALID_CLASS_NAME_REGEXP = Regex("[A-Z][A-Za-z\\d]*")
+        val VALID_CLASS_NAME_REGEXP = "[A-Z][A-Za-z\\d]*".regExIgnoringDiacriticsAndStrokesOnLetters()
         val BACK_TICKED_FUNCTION_NAME_REGEXP = Regex("`.*`")
     }
 }

ktlint-ruleset-experimental/src/main/kotlin/com/pinterest/ktlint/ruleset/experimental/FunctionNamingRule.kt

@@ -4,6 +4,7 @@ import com.pinterest.ktlint.core.Rule
 import com.pinterest.ktlint.core.ast.ElementType.FUN
 import com.pinterest.ktlint.core.ast.ElementType.IDENTIFIER
 import com.pinterest.ktlint.core.ast.ElementType.IMPORT_DIRECTIVE
+import com.pinterest.ktlint.ruleset.experimental.internal.regExIgnoringDiacriticsAndStrokesOnLetters
 import org.jetbrains.kotlin.com.intellij.lang.ASTNode
 import org.jetbrains.kotlin.psi.KtFunction
 import org.jetbrains.kotlin.psi.KtImportDirective
@@ -68,8 +69,8 @@ public class FunctionNamingRule : Rule("$EXPERIMENTAL_RULE_SET_ID:function-namin
             .matches(VALID_FUNCTION_NAME_REGEXP)
 
     private companion object {
-        val VALID_FUNCTION_NAME_REGEXP = Regex("[a-z][A-Za-z\\d]*")
-        val VALID_TEST_FUNCTION_NAME_REGEXP = Regex("(`.*`)|([a-z][A-Za-z\\d_]*)")
+        val VALID_FUNCTION_NAME_REGEXP = "[a-z][A-Za-z\\d]*".regExIgnoringDiacriticsAndStrokesOnLetters()
+        val VALID_TEST_FUNCTION_NAME_REGEXP = "(`.*`)|([a-z][A-Za-z\\d_]*)".regExIgnoringDiacriticsAndStrokesOnLetters()
         private const val KOTLIN_TEST = "kotlin.test"
         private const val ORG_JUNIT = "org.junit"
         private const val ORG_TESTNG = "org.testng"

ktlint-ruleset-experimental/src/main/kotlin/com/pinterest/ktlint/ruleset/experimental/PropertyNamingRule.kt

@@ -13,6 +13,7 @@ import com.pinterest.ktlint.core.ast.ElementType.PROPERTY
 import com.pinterest.ktlint.core.ast.ElementType.PROPERTY_ACCESSOR
 import com.pinterest.ktlint.core.ast.ElementType.VAL_KEYWORD
 import com.pinterest.ktlint.core.ast.children
+import com.pinterest.ktlint.ruleset.experimental.internal.regExIgnoringDiacriticsAndStrokesOnLetters
 import org.jetbrains.kotlin.com.intellij.lang.ASTNode
 import org.jetbrains.kotlin.com.intellij.psi.tree.IElementType
 
@@ -136,8 +137,8 @@ public class PropertyNamingRule : Rule("$EXPERIMENTAL_RULE_SET_ID:property-namin
             .any { it.text == identifier }
 
     private companion object {
-        val LOWER_CAMEL_CASE_REGEXP = Regex("[a-z][a-zA-Z0-9]*")
-        val SCREAMING_SNAKE_CASE_REGEXP = Regex("[A-Z][_A-Z0-9]*")
-        val BACKING_PROPERTY_LOWER_CAMEL_CASE_REGEXP = Regex("_[a-z][a-zA-Z0-9]*")
+        val LOWER_CAMEL_CASE_REGEXP = "[a-z][a-zA-Z0-9]*".regExIgnoringDiacriticsAndStrokesOnLetters()
+        val SCREAMING_SNAKE_CASE_REGEXP = "[A-Z][_A-Z0-9]*".regExIgnoringDiacriticsAndStrokesOnLetters()
+        val BACKING_PROPERTY_LOWER_CAMEL_CASE_REGEXP = "_[a-z][a-zA-Z0-9]*".regExIgnoringDiacriticsAndStrokesOnLetters()
     }
 }

ktlint-ruleset-experimental/src/main/kotlin/com/pinterest/ktlint/ruleset/experimental/internal/RegExIgnoringDiacriticsAndStrokesOnLetters.kt

@@ -0,0 +1,11 @@
+package com.pinterest.ktlint.ruleset.experimental.internal
+
+/**
+ * Transforms a string containing regular expression ranges like "A-Z" and "a-z" to a RegEx which checks whether a
+ * unicode character has an uppercase versus a lowercase mapping to a letter. This function intents to keep the original
+ * expression more readable
+ */
+internal fun String.regExIgnoringDiacriticsAndStrokesOnLetters() =
+    replace("A-Z", "\\p{Lu}")
+        .replace("a-z", "\\p{Ll}")
+        .toRegex()

ktlint-ruleset-experimental/src/test/kotlin/com/pinterest/ktlint/ruleset/experimental/ClassNamingRuleTest.kt

@@ -140,4 +140,13 @@ class ClassNamingRuleTest {
             classNamingRuleAssertThat(code).hasNoLintViolations()
         }
     }
+
+    @Test
+    fun `Issue 1757 - Given a class name containing diacritics is allowed`() {
+        val code =
+            """
+            class ŸèśThîsIsAllowed123
+            """.trimIndent()
+        classNamingRuleAssertThat(code).hasNoLintViolations()
+    }
 }

ktlint-ruleset-experimental/src/test/kotlin/com/pinterest/ktlint/ruleset/experimental/FunctionNamingRuleTest.kt

@@ -140,4 +140,39 @@ class FunctionNamingRuleTest {
             """.trimIndent()
         functionNamingRuleAssertThat(code).hasNoLintViolations()
     }
+
+    @Test
+    fun `Issue 1757 - Given a function name containing diacritics then do not report a violation on the diacritics`() {
+        val code =
+            """
+            fun ÿèśThîsIsAllowed123() = "foo"
+            """.trimIndent()
+        functionNamingRuleAssertThat(code).hasNoLintViolations()
+    }
+
+    @ParameterizedTest(name = "Junit import: {0}")
+    @ValueSource(
+        strings = [
+            "org.junit.jupiter.api.Test",
+            "org.junit.jupiter.api.*",
+            "org.junit.jupiter.*",
+            "org.junit.*",
+            "kotlin.test.*",
+            "org.testng.*",
+        ],
+    )
+    fun `Given file which imports a class from the JUnit Jupiter then do not emit`(
+        import: String,
+    ) {
+        val code =
+            """
+            import $import
+
+            class FunTest {
+                @Test
+                fun `Ÿèś thîs is allowed 123`() {}
+            }
+            """.trimIndent()
+        functionNamingRuleAssertThat(code).hasNoLintViolations()
+    }
 }

ktlint-ruleset-experimental/src/test/kotlin/com/pinterest/ktlint/ruleset/experimental/PropertyNamingRuleTest.kt

@@ -41,6 +41,7 @@ class PropertyNamingRuleTest {
             """
             const val foo = "foo"
             const val FOO_BAR_2 = "foo-bar-2"
+            const val ŸÈŠ_THÎS_IS_ALLOWED_123 = "Yes this is allowed"
             """.trimIndent()
         propertyNamingRuleAssertThat(code)
             .hasLintViolationWithoutAutoCorrect(1, 11, "Property name should use the screaming snake case notation when the value can not be changed")
@@ -106,9 +107,23 @@ class PropertyNamingRuleTest {
         val code =
             """
             class Foo {
-                private val _element2List = mutableListOf<Element>()
+                private val _elementList = mutableListOf<Element>()
 
-                val element2List: List<Element>
+                val elementList: List<Element>
+                    get() = _elementList
+            }
+            """.trimIndent()
+        propertyNamingRuleAssertThat(code).hasNoLintViolations()
+    }
+
+    @Test
+    fun `Given a backing val property name containing diacritics having a custom get function and not in screaming case notation then do not emit`() {
+        val code =
+            """
+            class Foo {
+                private val _elementŁîšt = mutableListOf<Element>()
+
+                val elementŁîšt: List<Element>
                     get() = _elementList
             }
             """.trimIndent()

ktlint-ruleset-standard/src/main/kotlin/com/pinterest/ktlint/ruleset/standard/PackageNameRule.kt

@@ -4,6 +4,7 @@ import com.pinterest.ktlint.core.Rule
 import com.pinterest.ktlint.core.ast.ElementType
 import com.pinterest.ktlint.core.ast.ElementType.PACKAGE_DIRECTIVE
 import com.pinterest.ktlint.core.ast.nextCodeSibling
+import com.pinterest.ktlint.ruleset.standard.internal.regExIgnoringDiacriticsAndStrokesOnLetters
 import org.jetbrains.kotlin.com.intellij.lang.ASTNode
 
 /**
@@ -33,6 +34,6 @@ public class PackageNameRule : Rule("package-name") {
     }
 
     private companion object {
-        val VALID_PACKAGE_NAME_REGEXP = Regex("[a-z_][a-zA-Z\\d_]*(\\.[a-z_][a-zA-Z\\d_]*)*")
+        val VALID_PACKAGE_NAME_REGEXP = "[a-z_][a-zA-Z\\d_]*(\\.[a-z_][a-zA-Z\\d_]*)*".regExIgnoringDiacriticsAndStrokesOnLetters()
     }
 }

ktlint-ruleset-standard/src/test/kotlin/com/pinterest/ktlint/ruleset/standard/PackageNameRuleTest.kt

@@ -90,4 +90,13 @@ class PackageNameRuleTest {
             """.trimIndent()
         packageNameRuleAssertThat(code).hasNoLintViolations()
     }
+
+    @Test
+    fun `Issue 1757 - Given a package name containing diacritics then do no report a violation`() {
+        val code =
+            """
+            package ÿèś.thîs.can.be.used
+            """.trimIndent()
+        packageNameRuleAssertThat(code).hasNoLintViolations()
+    }
 }