Fix JVM locale dependent casing (#10521)

apache · Jun 18, 2024 · 7911406 · 7911406
1 parent 9dbfbbb
commit 7911406
Show file tree

Hide file tree

Showing 18 changed files with 48 additions and 26 deletions.
diff --git a/aliyun/src/main/java/org/apache/iceberg/aliyun/oss/OSSURI.java b/aliyun/src/main/java/org/apache/iceberg/aliyun/oss/OSSURI.java
@@ -19,6 +19,7 @@
 package org.apache.iceberg.aliyun.oss;
 
 import com.aliyun.oss.internal.OSSUtils;
+import java.util.Locale;
 import java.util.Set;
 import org.apache.iceberg.exceptions.ValidationException;
 import org.apache.iceberg.relocated.com.google.common.base.Preconditions;
@@ -64,7 +65,7 @@ public OSSURI(String location) {
 
     String scheme = schemeSplit[0];
     ValidationException.check(
-        VALID_SCHEMES.contains(scheme.toLowerCase()),
+        VALID_SCHEMES.contains(scheme.toLowerCase(Locale.ROOT)),
         "Invalid scheme: %s in OSS location %s",
         scheme,
         location);

diff --git a/api/src/main/java/org/apache/iceberg/catalog/TableIdentifier.java b/api/src/main/java/org/apache/iceberg/catalog/TableIdentifier.java
@@ -19,6 +19,7 @@
 package org.apache.iceberg.catalog;
 
 import java.util.Arrays;
+import java.util.Locale;
 import java.util.Objects;
 import org.apache.iceberg.relocated.com.google.common.base.Preconditions;
 import org.apache.iceberg.relocated.com.google.common.base.Splitter;
@@ -80,7 +81,7 @@ public String name() {
   public TableIdentifier toLowerCase() {
     String[] newLevels =
         Arrays.stream(namespace().levels()).map(String::toLowerCase).toArray(String[]::new);
-    String newName = name().toLowerCase();
+    String newName = name().toLowerCase(Locale.ROOT);
     return TableIdentifier.of(Namespace.of(newLevels), newName);
   }
 

diff --git a/aws/src/test/java/org/apache/iceberg/aws/s3/signer/S3SignerServlet.java b/aws/src/test/java/org/apache/iceberg/aws/s3/signer/S3SignerServlet.java
@@ -31,6 +31,7 @@
 import java.time.ZoneId;
 import java.util.Arrays;
 import java.util.List;
+import java.util.Locale;
 import java.util.Map;
 import java.util.Set;
 import java.util.function.Predicate;
@@ -185,12 +186,12 @@ private S3SignResponse signRequest(S3SignRequest request) {
 
     Map<String, List<String>> unsignedHeaders =
         request.headers().entrySet().stream()
-            .filter(e -> UNSIGNED_HEADERS.contains(e.getKey().toLowerCase()))
+            .filter(e -> UNSIGNED_HEADERS.contains(e.getKey().toLowerCase(Locale.ROOT)))
             .collect(Collectors.toMap(Map.Entry::getKey, Map.Entry::getValue));
 
     Map<String, List<String>> signedHeaders =
         request.headers().entrySet().stream()
-            .filter(e -> !UNSIGNED_HEADERS.contains(e.getKey().toLowerCase()))
+            .filter(e -> !UNSIGNED_HEADERS.contains(e.getKey().toLowerCase(Locale.ROOT)))
             .collect(Collectors.toMap(Map.Entry::getKey, Map.Entry::getValue));
 
     SdkHttpFullRequest sign =

diff --git a/aws/src/test/java/org/apache/iceberg/aws/s3/signer/TestS3RestSigner.java b/aws/src/test/java/org/apache/iceberg/aws/s3/signer/TestS3RestSigner.java
@@ -23,6 +23,7 @@
 import java.nio.file.Path;
 import java.nio.file.Paths;
 import java.util.List;
+import java.util.Locale;
 import java.util.Map;
 import java.util.concurrent.ScheduledThreadPoolExecutor;
 import java.util.stream.Collectors;
@@ -327,7 +328,10 @@ private SdkHttpFullRequest signWithAwsSigner(
       // back after signing
       Map<String, List<String>> unsignedHeaders =
           request.headers().entrySet().stream()
-              .filter(e -> S3SignerServlet.UNSIGNED_HEADERS.contains(e.getKey().toLowerCase()))
+              .filter(
+                  e ->
+                      S3SignerServlet.UNSIGNED_HEADERS.contains(
+                          e.getKey().toLowerCase(Locale.ROOT)))
               .collect(Collectors.toMap(Map.Entry::getKey, Map.Entry::getValue));
 
       SdkHttpFullRequest.Builder builder = request.toBuilder();

diff --git a/core/src/main/java/org/apache/iceberg/avro/AvroSchemaUtil.java b/core/src/main/java/org/apache/iceberg/avro/AvroSchemaUtil.java
@@ -19,6 +19,7 @@
 package org.apache.iceberg.avro;
 
 import java.util.List;
+import java.util.Locale;
 import java.util.Map;
 import java.util.Set;
 import java.util.function.BiFunction;
@@ -528,6 +529,6 @@ private static String sanitize(char character) {
     if (Character.isDigit(character)) {
       return "_" + character;
     }
-    return "_x" + Integer.toHexString(character).toUpperCase();
+    return "_x" + Integer.toHexString(character).toUpperCase(Locale.ROOT);
   }
 }
diff --git a/core/src/test/java/org/apache/iceberg/encryption/KeyStoreKmsClient.java b/core/src/test/java/org/apache/iceberg/encryption/KeyStoreKmsClient.java
@@ -28,6 +28,7 @@
 import java.security.UnrecoverableKeyException;
 import java.security.cert.CertificateException;
 import java.util.Enumeration;
+import java.util.Locale;
 import java.util.Map;
 import javax.crypto.SecretKey;
 import org.apache.iceberg.relocated.com.google.common.base.Preconditions;
@@ -50,13 +51,13 @@ public class KeyStoreKmsClient extends MemoryMockKMS {
   @Override
   public ByteBuffer wrapKey(ByteBuffer key, String wrappingKeyId) {
     // keytool keeps key names in lower case
-    return super.wrapKey(key, wrappingKeyId.toLowerCase());
+    return super.wrapKey(key, wrappingKeyId.toLowerCase(Locale.ROOT));
   }
 
   @Override
   public ByteBuffer unwrapKey(ByteBuffer wrappedKey, String wrappingKeyId) {
     // keytool keeps key names in lower case
-    return super.unwrapKey(wrappedKey, wrappingKeyId.toLowerCase());
+    return super.unwrapKey(wrappedKey, wrappingKeyId.toLowerCase(Locale.ROOT));
   }
 
   @Override

diff --git a/core/src/test/java/org/apache/iceberg/hadoop/TestStaticTable.java b/core/src/test/java/org/apache/iceberg/hadoop/TestStaticTable.java
@@ -21,6 +21,7 @@
 import static org.assertj.core.api.Assertions.assertThat;
 import static org.assertj.core.api.Assertions.assertThatThrownBy;
 
+import java.util.Locale;
 import org.apache.iceberg.HasTableOperations;
 import org.apache.iceberg.MetadataTableType;
 import org.apache.iceberg.StaticTableOperations;
@@ -113,8 +114,8 @@ public void testImmutable() {
   @Test
   public void testMetadataTables() {
     for (MetadataTableType type : MetadataTableType.values()) {
-      String enumName = type.name().replace("_", "").toLowerCase();
-      assertThat(getStaticTable(type).getClass().getName().toLowerCase())
+      String enumName = type.name().replace("_", "").toLowerCase(Locale.ROOT);
+      assertThat(getStaticTable(type).getClass().getName().toLowerCase(Locale.ROOT))
           .as("Should be able to get MetadataTable of type : " + type)
           .contains(enumName);
     }

diff --git a/data/src/test/java/org/apache/iceberg/io/TestBaseTaskWriter.java b/data/src/test/java/org/apache/iceberg/io/TestBaseTaskWriter.java
@@ -27,6 +27,7 @@
 import java.nio.file.Paths;
 import java.util.Arrays;
 import java.util.List;
+import java.util.Locale;
 import java.util.stream.Collectors;
 import org.apache.iceberg.FileFormat;
 import org.apache.iceberg.Parameter;
@@ -175,7 +176,7 @@ public void testRollIfExceedTargetFileSize() throws IOException {
 
         int id = record.get(0, Integer.class);
         String data = record.get(1, String.class);
-        Record newRecord = createRecord(id, data.toUpperCase());
+        Record newRecord = createRecord(id, data.toUpperCase(Locale.ROOT));
         expected.add(newRecord);
         taskWriter.write(newRecord);
       }

diff --git a/dell/src/main/java/org/apache/iceberg/dell/ecs/EcsURI.java b/dell/src/main/java/org/apache/iceberg/dell/ecs/EcsURI.java
@@ -19,6 +19,7 @@
 package org.apache.iceberg.dell.ecs;
 
 import java.net.URI;
+import java.util.Locale;
 import java.util.Set;
 import org.apache.iceberg.exceptions.ValidationException;
 import org.apache.iceberg.relocated.com.google.common.base.Preconditions;
@@ -40,7 +41,9 @@ class EcsURI {
 
     URI uri = URI.create(location);
     ValidationException.check(
-        VALID_SCHEME.contains(uri.getScheme().toLowerCase()), "Invalid ecs location: %s", location);
+        VALID_SCHEME.contains(uri.getScheme().toLowerCase(Locale.ROOT)),
+        "Invalid ecs location: %s",
+        location);
     this.bucket = uri.getHost();
     this.name = uri.getPath().replaceAll("^/*", "");
   }

diff --git a/flink/v1.17/flink/src/test/java/org/apache/iceberg/flink/sink/TestIcebergStreamWriter.java b/flink/v1.17/flink/src/test/java/org/apache/iceberg/flink/sink/TestIcebergStreamWriter.java
@@ -24,6 +24,7 @@
 import java.io.IOException;
 import java.util.Arrays;
 import java.util.List;
+import java.util.Locale;
 import java.util.Map;
 import java.util.Set;
 import org.apache.flink.streaming.api.operators.BoundedOneInput;
@@ -201,7 +202,7 @@ private Set<String> scanDataFiles() throws IOException {
         LocatedFileStatus status = iterators.next();
         if (status.isFile()) {
           Path path = status.getPath();
-          if (path.getName().endsWith("." + format.toString().toLowerCase())) {
+          if (path.getName().endsWith("." + format.toString().toLowerCase(Locale.ROOT))) {
             paths.add(path.toString());
           }
         }

diff --git a/flink/v1.18/flink/src/test/java/org/apache/iceberg/flink/sink/TestIcebergStreamWriter.java b/flink/v1.18/flink/src/test/java/org/apache/iceberg/flink/sink/TestIcebergStreamWriter.java
@@ -24,6 +24,7 @@
 import java.io.IOException;
 import java.util.Arrays;
 import java.util.List;
+import java.util.Locale;
 import java.util.Map;
 import java.util.Set;
 import org.apache.flink.streaming.api.operators.BoundedOneInput;
@@ -201,7 +202,7 @@ private Set<String> scanDataFiles() throws IOException {
         LocatedFileStatus status = iterators.next();
         if (status.isFile()) {
           Path path = status.getPath();
-          if (path.getName().endsWith("." + format.toString().toLowerCase())) {
+          if (path.getName().endsWith("." + format.toString().toLowerCase(Locale.ROOT))) {
             paths.add(path.toString());
           }
         }

diff --git a/flink/v1.19/flink/src/test/java/org/apache/iceberg/flink/sink/TestIcebergStreamWriter.java b/flink/v1.19/flink/src/test/java/org/apache/iceberg/flink/sink/TestIcebergStreamWriter.java
@@ -24,6 +24,7 @@
 import java.io.IOException;
 import java.util.Arrays;
 import java.util.List;
+import java.util.Locale;
 import java.util.Map;
 import java.util.Set;
 import org.apache.flink.streaming.api.operators.BoundedOneInput;
@@ -201,7 +202,7 @@ private Set<String> scanDataFiles() throws IOException {
         LocatedFileStatus status = iterators.next();
         if (status.isFile()) {
           Path path = status.getPath();
-          if (path.getName().endsWith("." + format.toString().toLowerCase())) {
+          if (path.getName().endsWith("." + format.toString().toLowerCase(Locale.ROOT))) {
             paths.add(path.toString());
           }
         }

diff --git a/hive-metastore/src/main/java/org/apache/iceberg/hive/CachedClientPool.java b/hive-metastore/src/main/java/org/apache/iceberg/hive/CachedClientPool.java
@@ -148,7 +148,7 @@ static Key extractKey(String cacheKeys, Configuration conf) {
             !confElements.containsKey(key), "Conf key element %s already specified", key);
         confElements.put(key, conf.get(key));
       } else {
-        KeyElementType type = KeyElementType.valueOf(trimmed.toUpperCase());
+        KeyElementType type = KeyElementType.valueOf(trimmed.toUpperCase(Locale.ROOT));
         switch (type) {
           case UGI:
           case USER_NAME:

diff --git a/mr/src/main/java/org/apache/hadoop/hive/ql/exec/vector/VectorizedSupport.java b/mr/src/main/java/org/apache/hadoop/hive/ql/exec/vector/VectorizedSupport.java
@@ -18,6 +18,7 @@
  */
 package org.apache.hadoop.hive.ql.exec.vector;
 
+import java.util.Locale;
 import java.util.Map;
 import org.apache.iceberg.relocated.com.google.common.collect.Maps;
 
@@ -30,7 +31,7 @@ public enum Support {
     final String lowerCaseName;
 
     Support() {
-      this.lowerCaseName = name().toLowerCase();
+      this.lowerCaseName = name().toLowerCase(Locale.ROOT);
     }
 
     public static final Map<String, Support> nameToSupportMap = Maps.newHashMap();

diff --git a/mr/src/main/java/org/apache/iceberg/mr/hive/HiveIcebergMetaHook.java b/mr/src/main/java/org/apache/iceberg/mr/hive/HiveIcebergMetaHook.java
@@ -19,6 +19,7 @@
 package org.apache.iceberg.mr.hive;
 
 import java.util.List;
+import java.util.Locale;
 import java.util.Properties;
 import java.util.Set;
 import org.apache.hadoop.conf.Configuration;
@@ -84,7 +85,7 @@ public void preCreateTable(org.apache.hadoop.hive.metastore.api.Table hmsTable)
         .getParameters()
         .put(
             BaseMetastoreTableOperations.TABLE_TYPE_PROP,
-            BaseMetastoreTableOperations.ICEBERG_TABLE_TYPE_VALUE.toUpperCase());
+            BaseMetastoreTableOperations.ICEBERG_TABLE_TYPE_VALUE.toUpperCase(Locale.ROOT));
 
     if (!Catalogs.hiveCatalog(conf, catalogProperties)) {
       // For non-HiveCatalog tables too, we should set the input and output format

diff --git a/...n/java/org/apache/iceberg/mr/hive/serde/objectinspector/IcebergRecordObjectInspector.java b/...n/java/org/apache/iceberg/mr/hive/serde/objectinspector/IcebergRecordObjectInspector.java
@@ -20,6 +20,7 @@
 
 import java.util.Collections;
 import java.util.List;
+import java.util.Locale;
 import java.util.Objects;
 import java.util.stream.Collectors;
 import org.apache.hadoop.hive.serde2.objectinspector.ObjectInspector;
@@ -52,7 +53,7 @@ public IcebergRecordObjectInspector(
           Types.NestedField.of(
               field.fieldId(),
               field.isOptional(),
-              field.name().toLowerCase(),
+              field.name().toLowerCase(Locale.ROOT),
               field.type(),
               field.doc());
       IcebergRecordStructField structField =

diff --git a/mr/src/test/java/org/apache/iceberg/mr/hive/TestHiveIcebergStorageHandlerNoScan.java b/mr/src/test/java/org/apache/iceberg/mr/hive/TestHiveIcebergStorageHandlerNoScan.java
@@ -28,6 +28,7 @@
 import java.util.Collection;
 import java.util.Collections;
 import java.util.List;
+import java.util.Locale;
 import java.util.Map;
 import java.util.Properties;
 import java.util.Set;
@@ -785,7 +786,7 @@ public void testIcebergAndHmsTableProperties() throws Exception {
               hive_metastoreConstants.META_TABLE_STORAGE, HiveIcebergStorageHandler.class.getName())
           .containsEntry(
               BaseMetastoreTableOperations.TABLE_TYPE_PROP,
-              BaseMetastoreTableOperations.ICEBERG_TABLE_TYPE_VALUE.toUpperCase())
+              BaseMetastoreTableOperations.ICEBERG_TABLE_TYPE_VALUE.toUpperCase(Locale.ROOT))
           .containsEntry(
               BaseMetastoreTableOperations.METADATA_LOCATION_PROP,
               getCurrentSnapshotForHiveCatalogTable(icebergTable))

diff --git a/mr/src/test/java/org/apache/iceberg/mr/hive/TestHiveIcebergStorageHandlerWithEngine.java b/mr/src/test/java/org/apache/iceberg/mr/hive/TestHiveIcebergStorageHandlerWithEngine.java
@@ -29,6 +29,7 @@
 import java.time.LocalDateTime;
 import java.util.Collection;
 import java.util.List;
+import java.util.Locale;
 import java.util.Map;
 import java.util.concurrent.TimeUnit;
 import java.util.stream.Collectors;
@@ -311,8 +312,8 @@ public void testJoinTablesSupportedTypes() throws IOException {
       if (type == Types.UUIDType.get() && fileFormat == FileFormat.PARQUET) {
         continue;
       }
-      String tableName = type.typeId().toString().toLowerCase() + "_table_" + i;
-      String columnName = type.typeId().toString().toLowerCase() + "_column";
+      String tableName = type.typeId().toString().toLowerCase(Locale.ROOT) + "_table_" + i;
+      String columnName = type.typeId().toString().toLowerCase(Locale.ROOT) + "_column";
 
       Schema schema = new Schema(required(1, columnName, type));
       List<Record> records = TestHelper.generateRandomRecords(schema, 1, 0L);
@@ -349,8 +350,8 @@ public void testSelectDistinctFromTable() throws IOException {
       if (type == Types.UUIDType.get() && fileFormat == FileFormat.PARQUET) {
         continue;
       }
-      String tableName = type.typeId().toString().toLowerCase() + "_table_" + i;
-      String columnName = type.typeId().toString().toLowerCase() + "_column";
+      String tableName = type.typeId().toString().toLowerCase(Locale.ROOT) + "_table_" + i;
+      String columnName = type.typeId().toString().toLowerCase(Locale.ROOT) + "_column";
 
       Schema schema = new Schema(required(1, columnName, type));
       List<Record> records = TestHelper.generateRandomRecords(schema, 4, 0L);
@@ -411,7 +412,7 @@ public void testInsertSupportedTypes() throws IOException {
       if (type.equals(Types.BinaryType.get()) || type.equals(Types.FixedType.ofLength(5))) {
         continue;
       }
-      String columnName = type.typeId().toString().toLowerCase() + "_column";
+      String columnName = type.typeId().toString().toLowerCase(Locale.ROOT) + "_column";
 
       Schema schema =
           new Schema(required(1, "id", Types.LongType.get()), required(2, columnName, type));
@@ -420,7 +421,7 @@ public void testInsertSupportedTypes() throws IOException {
       Table table =
           testTables.createTable(
               shell,
-              type.typeId().toString().toLowerCase() + "_table_" + i,
+              type.typeId().toString().toLowerCase(Locale.ROOT) + "_table_" + i,
               schema,
               PartitionSpec.unpartitioned(),
               fileFormat,