divjotarora commented on code in PR #3858: URL: https://github.com/apache/parquet-java/pull/3858#discussion_r4280675892
########## parquet-cli/src/test/java/org/apache/parquet/cli/ReadCliTest.java: ########## @@ -0,0 +1,147 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one + * or more contributor license agreements. See the NOTICE file + * distributed with this work for additional information + * regarding copyright ownership. The ASF licenses this file + * to you under the Apache License, Version 2.0 (the + * "License"); you may not use this file except in compliance + * with the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, + * software distributed under the License is distributed on an + * "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY + * KIND, either express or implied. See the License for the + * specific language governing permissions and limitations + * under the License. + */ +package org.apache.parquet.cli; + +import static org.assertj.core.api.Assertions.assertThat; + +import com.fasterxml.jackson.core.type.TypeReference; +import com.fasterxml.jackson.databind.ObjectMapper; +import java.io.IOException; +import java.nio.file.Path; +import java.util.ArrayList; +import java.util.List; +import java.util.Map; +import java.util.stream.IntStream; +import org.apache.parquet.example.data.Group; +import org.apache.parquet.example.data.simple.SimpleGroupFactory; +import org.apache.parquet.hadoop.ParquetWriter; +import org.apache.parquet.hadoop.example.ExampleParquetWriter; +import org.apache.parquet.schema.LogicalTypeAnnotation; +import org.apache.parquet.schema.MessageType; +import org.apache.parquet.schema.PrimitiveType.PrimitiveTypeName; +import org.apache.parquet.schema.Types; +import org.junit.jupiter.api.BeforeEach; +import org.junit.jupiter.api.Test; + +class ReadCliTest extends CliTestBase { + + private Path input; + + @BeforeEach + void createInput() throws IOException { + input = writeRecords("read input.parquet", 0, 12); + } + + @Test + void headPrintsFirstTenRecordsByDefault() throws Exception { + CliResult result = cli("head", input.toString()); + + assertThat(result.exitCode()).isZero(); + assertThat(readRecords(result.output())).containsExactlyElementsOf(expectedRecords(10)); + } + + @Test + void headUsesRequestedRecordLimit() throws Exception { + CliResult result = cli("head", "--num-records", "3", input.toString()); + + assertThat(result.exitCode()).isZero(); + assertThat(readRecords(result.output())).containsExactlyElementsOf(expectedRecords(3)); + } + + @Test + void catPrintsAllRecordsByDefault() throws Exception { + CliResult result = cli("cat", input.toString()); + + assertThat(result.exitCode()).isZero(); + assertThat(readRecords(result.output())).containsExactlyElementsOf(expectedRecords(12)); + } + + @Test + void catPrintsOnlyRequestedColumns() throws Exception { + CliResult result = cli("cat", "--columns", "id,label", input.toString()); + + List<Map<String, Object>> expected = IntStream.range(0, 12) + .mapToObj(i -> Map.<String, Object>of("id", i, "label", "row-" + i)) + .toList(); + assertThat(result.exitCode()).isZero(); + assertThat(readRecords(result.output())).containsExactlyElementsOf(expected); + } + + @Test + void scanCountsRecordsAcrossInputFiles() throws Exception { + Path second = writeRecords("second input.parquet", 100, 3); + + CliResult result = cli("scan", input.toString(), second.toString()); + + assertThat(result.exitCode()).isZero(); + assertThat(result.output()) + .contains( + "Scanned 12 records from " + input, + "Scanned 3 records from " + second, + "Scanned 15 records from 2 file(s)"); + } + + @Test + void scanRejectsColumnMissingFromInputSchema() throws Exception { + CliResult result = cli("scan", "--columns", "missing_field", input.toString()); + + assertThat(result.exitCode()).isNotZero(); + assertThat(result.output()).contains("Cannot find field", "missing_field"); + } + + private Path writeRecords(String name, int firstId, int count) throws IOException { + Path path = getTempFolder().toPath().resolve(name); + MessageType schema = Types.buildMessage() + .required(PrimitiveTypeName.INT32) + .named("id") + .required(PrimitiveTypeName.BINARY) + .as(LogicalTypeAnnotation.stringType()) + .named("label") + .required(PrimitiveTypeName.INT32) + .named("unused") + .named("record"); + SimpleGroupFactory groups = new SimpleGroupFactory(schema); + try (ParquetWriter<Group> writer = ExampleParquetWriter.builder(new org.apache.hadoop.fs.Path(path.toUri())) Review Comment: [nit] Add an import for `org.apache.hadoop.fs.Path`? -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected] --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
