Accept letters with strokes or diacritics

pinterest · Jul 7, 2022 · 55ce3e2 · 55ce3e2
1 parent 2fc863e
commit 55ce3e2
Show file tree

Hide file tree

Showing 7 changed files with 81 additions and 90 deletions.
diff --git a/...t-standard/src/main/kotlin/com/pinterest/ktlint/ruleset/standard/EnumEntryNameCaseRule.kt b/...t-standard/src/main/kotlin/com/pinterest/ktlint/ruleset/standard/EnumEntryNameCaseRule.kt
@@ -1,7 +1,7 @@
 package com.pinterest.ktlint.ruleset.standard
 
 import com.pinterest.ktlint.core.Rule
-import com.pinterest.ktlint.ruleset.standard.internal.removeDiacriticsFromLetters
+import com.pinterest.ktlint.ruleset.standard.internal.regExIgnoringDiacriticsAndStrokesOnLetters
 import org.jetbrains.kotlin.com.intellij.lang.ASTNode
 import org.jetbrains.kotlin.com.intellij.psi.impl.source.tree.CompositeElement
 import org.jetbrains.kotlin.psi.KtEnumEntry
@@ -11,7 +11,7 @@ import org.jetbrains.kotlin.psi.KtEnumEntry
  */
 public class EnumEntryNameCaseRule : Rule("enum-entry-name-case") {
     internal companion object {
-        val regex = Regex("[A-Z]([A-Za-z\\d]*|[A-Z_\\d]*)")
+        val regex = "[A-Z]([A-Za-z\\d]*|[A-Z_\\d]*)".regExIgnoringDiacriticsAndStrokesOnLetters()
     }
 
     override fun visit(
@@ -25,7 +25,7 @@ public class EnumEntryNameCaseRule : Rule("enum-entry-name-case") {
         val enumEntry = node.psi as? KtEnumEntry ?: return
         val name = enumEntry.name ?: return
 
-        if (!name.removeDiacriticsFromLetters().matches(regex)) {
+        if (!name.matches(regex)) {
             emit(
                 node.startOffset,
                 "Enum entry name should be uppercase underscore-separated names like \"ENUM_ENTRY\" or upper camel-case like \"EnumEntry\"",

diff --git a/...nt-ruleset-standard/src/main/kotlin/com/pinterest/ktlint/ruleset/standard/FilenameRule.kt b/...nt-ruleset-standard/src/main/kotlin/com/pinterest/ktlint/ruleset/standard/FilenameRule.kt
@@ -11,7 +11,7 @@ import com.pinterest.ktlint.core.ast.ElementType.PROPERTY
 import com.pinterest.ktlint.core.ast.ElementType.TYPEALIAS
 import com.pinterest.ktlint.core.ast.ElementType.TYPE_REFERENCE
 import com.pinterest.ktlint.core.ast.children
-import com.pinterest.ktlint.ruleset.standard.internal.removeDiacriticsFromLetters
+import com.pinterest.ktlint.ruleset.standard.internal.regExIgnoringDiacriticsAndStrokesOnLetters
 import java.nio.file.Paths
 import org.jetbrains.kotlin.com.intellij.lang.ASTNode
 import org.jetbrains.kotlin.com.intellij.lang.FileASTNode
@@ -167,7 +167,7 @@ public class FilenameRule : Rule(
     private fun String.shouldMatchPascalCase(
         emit: (offset: Int, errorMessage: String, canBeAutoCorrected: Boolean) -> Unit
     ) {
-        if (!this.removeDiacriticsFromLetters().matches(pascalCaseRegEx)) {
+        if (!this.matches(pascalCaseRegEx)) {
             emit(0, "File name '$this.kt' should conform PascalCase", false)
         }
     }
@@ -199,7 +199,7 @@ public class FilenameRule : Rule(
             }
 
     private companion object {
-        val pascalCaseRegEx = Regex("""^[A-Z][A-Za-z\d]*$""")
+        val pascalCaseRegEx = "^[A-Z][A-Za-z\\d]*$".regExIgnoringDiacriticsAndStrokesOnLetters()
         val NON_CLASS_RELATED_TOP_LEVEL_DECLARATION_TYPES = listOf(OBJECT_DECLARATION, TYPEALIAS, PROPERTY)
     }
 }
diff --git a/...main/kotlin/com/pinterest/ktlint/ruleset/standard/internal/RemoveDiacriticsFromLetters.kt b/...main/kotlin/com/pinterest/ktlint/ruleset/standard/internal/RemoveDiacriticsFromLetters.kt
@@ -1,23 +1,11 @@
 package com.pinterest.ktlint.ruleset.standard.internal
 
-import java.text.Normalizer
-
 /**
- * Removes diacritics from letters. Note that ligatures æ (ae), œ (oe), Æ (AE), Œ (OE), and letters with strokes ł (l),
- * ø (o), ß (s), Ł (L), Ø (O) are not changed.
+ * 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.removeDiacriticsFromLetters() =
-    map { originalChar ->
-        Normalizer
-            // Decompose characters having a diacritic into an ascii alphabetic character (a-zA-Z) followed by the diacritic(s)
-            .normalize(originalChar.toString(), Normalizer.Form.NFD)
-            .let {
-                if (it.first().isLetterOrDigit()) {
-                    // Ignore all diacritics
-                    it.first()
-                } else {
-                    it
-                }
-            }
-    }.joinToString(separator = "")
+internal fun String.regExIgnoringDiacriticsAndStrokesOnLetters() =
+    replace("A-Z", "\\p{Lu}")
+        .replace("a-z", "\\p{Ll}")
+        .toRegex()
diff --git a/...andard/src/test/kotlin/com/pinterest/ktlint/ruleset/standard/EnumEntryNameCaseRuleTest.kt b/...andard/src/test/kotlin/com/pinterest/ktlint/ruleset/standard/EnumEntryNameCaseRuleTest.kt
@@ -67,8 +67,8 @@ class EnumEntryNameCaseRuleTest {
         val code =
             """
             enum class SomeEnum {
-                ŸÈŚ_THÎS_IS_ALLOWED,
-                ŸèśThîsIsAllowed,
+                ŸÈŚ_THÎS_IS_ALLOWED_123,
+                ŸèśThîsIsAllowed123,
             }
             """.trimIndent()
         enumEntryNameCaseRuleAssertThat(code).hasNoLintViolations()

diff --git a/...uleset-standard/src/test/kotlin/com/pinterest/ktlint/ruleset/standard/FilenameRuleTest.kt b/...uleset-standard/src/test/kotlin/com/pinterest/ktlint/ruleset/standard/FilenameRuleTest.kt
@@ -242,7 +242,7 @@ class FilenameRuleTest {
     fun `Issue 1530 - Given a file which name should match PascalCase then this name may also contain letters with diacritics`() {
         val code = "// some code"
         fileNameRuleAssertThat(code)
-            .asFileWithPath("ŸëšThïsĮsÂllòwed.kt")
+            .asFileWithPath("ŸëšThïsĮsÂllòwed123.kt")
             .hasNoLintViolations()
     }
 

diff --git a/.../kotlin/com/pinterest/ktlint/ruleset/standard/internal/RemoveDiacriticsFromLettersTest.kt b/.../kotlin/com/pinterest/ktlint/ruleset/standard/internal/RemoveDiacriticsFromLettersTest.kt
@@ -1,53 +1,38 @@
 package com.pinterest.ktlint.ruleset.standard.internal
 
 import org.assertj.core.api.Assertions.assertThat
-import org.junit.jupiter.api.Test
 import org.junit.jupiter.params.ParameterizedTest
-import org.junit.jupiter.params.provider.CsvSource
 import org.junit.jupiter.params.provider.ValueSource
 
 class RemoveDiacriticsFromLettersTest {
     @ParameterizedTest(name = "Original character: {0}, expected result: {1}")
-    @CsvSource(
-        value = [
-            "àáâäãåā,aaaaaaa",
-            "çćč,ccc",
-            "èéêëēėę,eeeeeee",
-            "îïíīįì,iiiiii",
-            "ñń,nn",
-            "ôöòóōõ,oooooo",
-            "śš,ss",
-            "ûüùúū,uuuuu",
-            "ÿ,y",
-            "žźż,zzz",
-            "ÀÁÂÄÃÅĀ,AAAAAAA",
-            "ÇĆČ,CCC",
-            "ÈÉÊËĒĖĘ,EEEEEEE",
-            "ÎÏÍĪĮÌ,IIIIII",
-            "ÑŃ,NN",
-            "ÔÖÒÓŌÕ,OOOOOO",
-            "ŚŠ,SS",
-            "ÛÜÙÚŪ,UUUUU",
-            "Ÿ,Y",
-            "ŽŹŻ,ZZZ"
-        ]
-    )
-    fun `Given a letter with a diacritic then remove it`(original: String, expected: String) {
-        assertThat(original.removeDiacriticsFromLetters()).isEqualTo(expected)
-    }
-
-    @ParameterizedTest(name = "Character: {0}")
     @ValueSource(
         strings = [
-            "æ", "ł", "œ", "ø", "ß", "Æ", "Ł", "Œ", "Ø"
+            "àáâäæãåā",
+            "çćč",
+            "èéêëēėę",
+            "îïíīįì",
+            "ł",
+            "ñń",
+            "ôöòóœøōõ",
+            "ßśš",
+            "ûüùúū",
+            "ÿ",
+            "žźż",
+            "ÀÁÂÄÆÃÅĀ",
+            "ÇĆČ",
+            "ÈÉÊËĒĖĘ",
+            "ÎÏÍĪĮÌ",
+            "Ł",
+            "ÑŃ",
+            "ÔÖÒÓŒØŌÕ",
+            "ŚŠ",
+            "ÛÜÙÚŪ",
+            "Ÿ",
+            "ŽŹŻ"
         ]
     )
-    fun `Given a ligature or letter with stroke then keep it unchanged`(original: String) {
-        assertThat(original.removeDiacriticsFromLetters()).isEqualTo(original)
-    }
-
-    @Test
-    fun `Given a string containing`() {
-        assertThat("ÅÄÖāăąēîïĩíĝġńñšŝśûůŷ".removeDiacriticsFromLetters()).isEqualTo("AAOaaaeiiiiggnnsssuuy")
+    fun `Given a letter with a diacritic then remove it`(original: String) {
+        assertThat(original.matches("[A-Za-z]*".regExIgnoringDiacriticsAndStrokesOnLetters())).isTrue
     }
 }
diff --git a/ktlint/src/main/kotlin/com/pinterest/ktlint/internal/FileUtils.kt b/ktlint/src/main/kotlin/com/pinterest/ktlint/internal/FileUtils.kt
@@ -15,6 +15,7 @@ import java.nio.file.Paths
 import java.nio.file.SimpleFileVisitor
 import java.nio.file.attribute.BasicFileAttributes
 import kotlin.system.exitProcess
+import kotlin.system.measureTimeMillis
 import mu.KotlinLogging
 
 private val logger = KotlinLogging.logger {}.initKtLintKLogger()
@@ -66,33 +67,50 @@ internal fun FileSystem.fileSequence(
             }
     }
 
-    Files.walkFileTree(
-        rootDir,
-        object : SimpleFileVisitor<Path>() {
-            override fun visitFile(
-                filePath: Path,
-                fileAttrs: BasicFileAttributes
-            ): FileVisitResult {
-                if (negatedPathMatchers.none { it.matches(filePath) } &&
-                    pathMatchers.any { it.matches(filePath) }
-                ) {
-                    result.add(filePath)
+    logger.debug {
+        """
+        Start walkFileTree for rootDir: '$rootDir'
+           include:
+        ${pathMatchers.map { "      - $it" }}
+           exlcude:
+        ${negatedPathMatchers.map { "      - $it" }}
+        """.trimIndent()
+    }
+    val duration = measureTimeMillis {
+        Files.walkFileTree(
+            rootDir,
+            object : SimpleFileVisitor<Path>() {
+                override fun visitFile(
+                    filePath: Path,
+                    fileAttrs: BasicFileAttributes
+                ): FileVisitResult {
+                    if (negatedPathMatchers.none { it.matches(filePath) } &&
+                        pathMatchers.any { it.matches(filePath) }
+                    ) {
+                        logger.debug { "- File: $filePath: Include" }
+                        result.add(filePath)
+                    } else {
+                        logger.debug { "- File: $filePath: Ignore" }
+                    }
+                    return FileVisitResult.CONTINUE
                 }
-                return FileVisitResult.CONTINUE
-            }
 
-            override fun preVisitDirectory(
-                dirPath: Path,
-                dirAttr: BasicFileAttributes
-            ): FileVisitResult {
-                return if (Files.isHidden(dirPath)) {
-                    FileVisitResult.SKIP_SUBTREE
-                } else {
-                    FileVisitResult.CONTINUE
+                override fun preVisitDirectory(
+                    dirPath: Path,
+                    dirAttr: BasicFileAttributes
+                ): FileVisitResult {
+                    return if (Files.isHidden(dirPath)) {
+                        logger.debug { "- Dir: $dirPath: Ignore" }
+                        FileVisitResult.SKIP_SUBTREE
+                    } else {
+                        logger.debug { "- Dir: $dirPath: Traverse" }
+                        FileVisitResult.CONTINUE
+                    }
                 }
             }
-        }
-    )
+        )
+    }
+    logger.debug { "Results: include ${result.count()} files in $duration ms" }
 
     return result.asSequence()
 }