GH-3900: Replace Guava with JDK APIs in parquet-cli (#3906)

Now that the minimum JDK is 17, replace Guava collection factories,
ImmutableList/ImmutableSet/ImmutableMap, Joiner, Splitter, Objects,
MoreObjects and simple Iterables/Predicate/Function usages in
parquet-cli with JDK equivalents, and switch Guava Preconditions to
org.apache.parquet.Preconditions (all call sites use %s-only messages
with matching argument counts) and Objects.requireNonNull.

Guava usages without a clean JDK equivalent are kept: Closeables,
CharMatcher, Ascii, HashCode, CharStreams, Resources, Iterators.transform
and VisibleForTesting.

Co-authored-by: Isaac <no-reply@databricks.com>

Author: Fokko

parquet-cli/src/main/java/org/apache/parquet/cli/BaseCommand.java

@@ -21,7 +21,6 @@
 
 import com.beust.jcommander.internal.Lists;
 import com.google.common.annotations.VisibleForTesting;
-import com.google.common.base.Preconditions;
 import com.google.common.io.CharStreams;
 import com.google.common.io.Resources;
 import java.io.File;
@@ -51,6 +50,7 @@
 import org.apache.hadoop.fs.LocalFileSystem;
 import org.apache.hadoop.fs.Path;
 import org.apache.parquet.HadoopReadOptions;
+import org.apache.parquet.Preconditions;
 import org.apache.parquet.avro.AvroParquetReader;
 import org.apache.parquet.avro.AvroReadSupport;
 import org.apache.parquet.cli.json.AvroJsonReader;

parquet-cli/src/main/java/org/apache/parquet/cli/Help.java

@@ -24,7 +24,7 @@
 import com.beust.jcommander.Parameter;
 import com.beust.jcommander.ParameterDescription;
 import com.beust.jcommander.Parameters;
-import com.google.common.collect.Lists;
+import java.util.ArrayList;
 import java.util.Arrays;
 import java.util.Collections;
 import java.util.List;
@@ -33,7 +33,7 @@
 @Parameters(commandDescription = "Retrieves details on the functions of other commands")
 public class Help implements Command {
   @Parameter(description = "<commands>")
-  List<String> helpCommands = Lists.newArrayList();
+  List<String> helpCommands = new ArrayList<>();
 
   private final JCommander jc;
   private final Logger console;

parquet-cli/src/main/java/org/apache/parquet/cli/Main.java

@@ -24,7 +24,6 @@
 import com.beust.jcommander.ParameterException;
 import com.beust.jcommander.Parameters;
 import com.google.common.annotations.VisibleForTesting;
-import com.google.common.collect.ImmutableSet;
 import java.io.FileInputStream;
 import java.io.InputStream;
 import java.util.List;
@@ -89,7 +88,7 @@ public class Main extends Configured implements Tool {
   @VisibleForTesting
   static final String DEFAULT_PROGRAM_NAME = "parquet";
 
-  private static Set<String> HELP_ARGS = ImmutableSet.of("-h", "-help", "--help", "help");
+  private static Set<String> HELP_ARGS = Set.of("-h", "-help", "--help", "help");
 
   private final Logger console;
   private final Help help;

parquet-cli/src/main/java/org/apache/parquet/cli/Util.java

@@ -29,12 +29,9 @@
 import static org.apache.parquet.format.Encoding.DELTA_LENGTH_BYTE_ARRAY;
 
 import com.google.common.base.Ascii;
-import com.google.common.base.Joiner;
-import com.google.common.base.Preconditions;
-import com.google.common.base.Splitter;
-import com.google.common.collect.Iterables;
 import com.google.common.hash.HashCode;
 import java.util.Set;
+import org.apache.parquet.Preconditions;
 import org.apache.parquet.column.ColumnDescriptor;
 import org.apache.parquet.column.Encoding;
 import org.apache.parquet.column.EncodingStats;
@@ -240,16 +237,14 @@ public static String encodingsAsString(Set<Encoding> encodings, ColumnDescriptor
     return sb.toString();
   }
 
-  private static final Splitter DOT = Splitter.on('.');
-
   public static ColumnDescriptor descriptor(String column, MessageType schema) {
-    String[] path = Iterables.toArray(DOT.split(column), String.class);
+    String[] path = column.split("\\.", -1);
     Preconditions.checkArgument(schema.containsPath(path), "Schema doesn't have column: %s", column);
     return schema.getColumnDescription(path);
   }
 
   public static String columnName(ColumnDescriptor desc) {
-    return Joiner.on('.').join(desc.getPath());
+    return String.join(".", desc.getPath());
   }
 
   public static PrimitiveType primitive(MessageType schema, String[] path) {
@@ -264,7 +259,7 @@ public static PrimitiveType primitive(MessageType schema, String[] path) {
   }
 
   public static PrimitiveType primitive(String column, MessageType schema) {
-    String[] path = Iterables.toArray(DOT.split(column), String.class);
+    String[] path = column.split("\\.", -1);
     Preconditions.checkArgument(schema.containsPath(path), "Schema doesn't have column: %s", column);
     return primitive(schema, path);
   }

parquet-cli/src/main/java/org/apache/parquet/cli/commands/CSVSchemaCommand.java

@@ -22,12 +22,11 @@
 import com.beust.jcommander.Parameter;
 import com.beust.jcommander.Parameters;
 import com.beust.jcommander.internal.Lists;
-import com.google.common.base.Preconditions;
-import com.google.common.collect.ImmutableSet;
 import java.io.IOException;
 import java.nio.charset.Charset;
 import java.util.List;
 import java.util.Set;
+import org.apache.parquet.Preconditions;
 import org.apache.parquet.cli.BaseCommand;
 import org.apache.parquet.cli.csv.AvroCSV;
 import org.apache.parquet.cli.csv.CSVProperties;
@@ -101,9 +100,9 @@ public int run() throws IOException {
         .charset(charsetName)
         .build();
 
-    Set<String> required = ImmutableSet.of();
+    Set<String> required = Set.of();
     if (requiredFields != null) {
-      required = ImmutableSet.copyOf(requiredFields);
+      required = Set.copyOf(requiredFields);
     }
 
     // assume fields are nullable by default, users can easily change this

parquet-cli/src/main/java/org/apache/parquet/cli/commands/CatCommand.java

@@ -22,14 +22,14 @@
 
 import com.beust.jcommander.Parameter;
 import com.beust.jcommander.Parameters;
-import com.google.common.base.Preconditions;
-import com.google.common.collect.Lists;
 import com.google.common.io.Closeables;
 import java.io.Closeable;
 import java.io.IOException;
+import java.util.Arrays;
 import java.util.List;
 import org.apache.avro.Schema;
 import org.apache.avro.SchemaParseException;
+import org.apache.parquet.Preconditions;
 import org.apache.parquet.cli.BaseCommand;
 import org.apache.parquet.cli.util.Expressions;
 import org.apache.parquet.example.data.Group;
@@ -150,7 +150,7 @@ private void runWithGroupReader(String source) throws IOException {
 
   @Override
   public List<String> getExamples() {
-    return Lists.newArrayList(
+    return Arrays.asList(
         "# Show the first 10 records in file \"data.avro\":",
         "data.avro",
         "# Show the first 50 records in file \"data.parquet\":",

parquet-cli/src/main/java/org/apache/parquet/cli/commands/CheckParquet251Command.java

@@ -24,13 +24,10 @@
 import com.beust.jcommander.Parameter;
 import com.beust.jcommander.Parameters;
 import com.beust.jcommander.internal.Lists;
-import com.google.common.base.Predicate;
-import com.google.common.collect.Iterables;
 import java.io.IOException;
 import java.util.Arrays;
 import java.util.Comparator;
 import java.util.List;
-import javax.annotation.Nullable;
 import org.apache.hadoop.fs.Path;
 import org.apache.parquet.CorruptStatistics;
 import org.apache.parquet.Version;
@@ -97,13 +94,11 @@ private String check(String file) throws IOException {
 
       // get just the binary columns
       List<ColumnDescriptor> columns = Lists.newArrayList();
-      Iterables.addAll(
-          columns, Iterables.filter(meta.getSchema().getColumns(), new Predicate<ColumnDescriptor>() {
-            @Override
-            public boolean apply(@Nullable ColumnDescriptor input) {
-              return input != null && input.getType() == BINARY;
-            }
-          }));
+      for (ColumnDescriptor input : meta.getSchema().getColumns()) {
+        if (input != null && input.getType() == BINARY) {
+          columns.add(input);
+        }
+      }
 
       // now check to see if the data is actually corrupt
       try (ParquetFileReader reader =

parquet-cli/src/main/java/org/apache/parquet/cli/commands/ColumnMaskingCommand.java

@@ -23,12 +23,12 @@
 
 import com.beust.jcommander.Parameter;
 import com.beust.jcommander.Parameters;
-import com.google.common.base.Preconditions;
-import com.google.common.collect.Lists;
 import java.io.IOException;
+import java.util.Arrays;
 import java.util.List;
 import org.apache.hadoop.fs.Path;
 import org.apache.parquet.HadoopReadOptions;
+import org.apache.parquet.Preconditions;
 import org.apache.parquet.cli.BaseCommand;
 import org.apache.parquet.hadoop.ParquetFileReader;
 import org.apache.parquet.hadoop.ParquetFileWriter;
@@ -109,7 +109,7 @@ public int run() throws IOException {
 
   @Override
   public List<String> getExamples() {
-    return Lists.newArrayList(
+    return Arrays.asList(
         "# Replace columns with masked values and write to a new Parquet file",
         "-m nullify -i input.parquet -o output.parquet -c col1_name");
   }

parquet-cli/src/main/java/org/apache/parquet/cli/commands/ColumnSizeCommand.java

@@ -21,17 +21,17 @@
 
 import com.beust.jcommander.Parameter;
 import com.beust.jcommander.Parameters;
-import com.google.common.base.Preconditions;
-import com.google.common.collect.Lists;
 import java.io.IOException;
 import java.util.ArrayList;
+import java.util.Arrays;
 import java.util.HashMap;
 import java.util.LinkedHashMap;
 import java.util.List;
 import java.util.Locale;
 import java.util.Map;
 import org.apache.hadoop.conf.Configuration;
 import org.apache.hadoop.fs.Path;
+import org.apache.parquet.Preconditions;
 import org.apache.parquet.cli.BaseCommand;
 import org.apache.parquet.format.converter.ParquetMetadataConverter;
 import org.apache.parquet.hadoop.ParquetFileReader;
@@ -143,7 +143,7 @@ private String formatRatio(float ratio) {
 
   @Override
   public List<String> getExamples() {
-    return Lists.newArrayList(
+    return Arrays.asList(
         "# Print every column size in byte and ratio for a Parquet file",
         "sample.parquet",
         "sample.parquet -c col_1",

parquet-cli/src/main/java/org/apache/parquet/cli/commands/ConvertCSVCommand.java

@@ -25,17 +25,16 @@
 
 import com.beust.jcommander.Parameter;
 import com.beust.jcommander.Parameters;
-import com.google.common.base.Preconditions;
-import com.google.common.collect.ImmutableSet;
-import com.google.common.collect.Lists;
 import java.io.File;
 import java.io.IOException;
 import java.nio.charset.Charset;
+import java.util.Arrays;
 import java.util.List;
 import java.util.Set;
 import org.apache.avro.Schema;
 import org.apache.avro.SchemaNormalization;
 import org.apache.avro.generic.GenericData;
+import org.apache.parquet.Preconditions;
 import org.apache.parquet.avro.AvroParquetWriter;
 import org.apache.parquet.cli.BaseCommand;
 import org.apache.parquet.cli.csv.AvroCSV;
@@ -141,9 +140,9 @@ public int run() throws IOException {
     if (avroSchemaFile != null) {
       csvSchema = Schemas.fromAvsc(open(avroSchemaFile));
     } else {
-      Set<String> required = ImmutableSet.of();
+      Set<String> required = Set.of();
       if (requiredFields != null) {
-        required = ImmutableSet.copyOf(requiredFields);
+        required = Set.copyOf(requiredFields);
       }
 
       String filename = new File(targets.get(0)).getName();
@@ -199,7 +198,7 @@ public int run() throws IOException {
 
   @Override
   public List<String> getExamples() {
-    return Lists.newArrayList(
+    return Arrays.asList(
         "# Create a Parquet file from a CSV file",
         "sample.csv -o sample.parquet --schema schema.avsc",
         "# Create a Parquet file in HDFS from local CSV",