miklosgergely commented on a change in pull request #1756: URL: https://github.com/apache/hive/pull/1756#discussion_r550924729
########## File path: ql/src/java/org/apache/hadoop/hive/ql/ddl/ShowUtils.java ########## @@ -0,0 +1,397 @@ +/* + * 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.hadoop.hive.ql.ddl; + +import com.google.common.collect.Lists; +import org.apache.commons.lang3.StringUtils; +import org.apache.hadoop.fs.FSDataOutputStream; +import org.apache.hadoop.fs.FileSystem; +import org.apache.hadoop.fs.Path; +import org.apache.hadoop.hive.common.type.HiveDecimal; +import org.apache.hadoop.hive.common.type.Timestamp; +import org.apache.hadoop.hive.metastore.api.BinaryColumnStatsData; +import org.apache.hadoop.hive.metastore.api.BooleanColumnStatsData; +import org.apache.hadoop.hive.metastore.api.ColumnStatisticsData; +import org.apache.hadoop.hive.metastore.api.ColumnStatisticsObj; +import org.apache.hadoop.hive.metastore.api.DateColumnStatsData; +import org.apache.hadoop.hive.metastore.api.Decimal; +import org.apache.hadoop.hive.metastore.api.DecimalColumnStatsData; +import org.apache.hadoop.hive.metastore.api.DoubleColumnStatsData; +import org.apache.hadoop.hive.metastore.api.FieldSchema; +import org.apache.hadoop.hive.metastore.api.LongColumnStatsData; +import org.apache.hadoop.hive.metastore.api.StringColumnStatsData; +import org.apache.hadoop.hive.metastore.api.TimestampColumnStatsData; +import org.apache.hadoop.hive.ql.exec.Utilities; +import org.apache.hadoop.hive.ql.metadata.HiveException; +import org.apache.hadoop.hive.serde2.io.DateWritableV2; +import org.apache.hadoop.hive.serde2.io.TimestampWritableV2; +import org.apache.hive.common.util.HiveStringUtils; +import org.codehaus.jackson.map.ObjectMapper; + +import java.io.DataOutputStream; +import java.io.IOException; +import java.io.OutputStream; +import java.io.OutputStreamWriter; +import java.math.BigInteger; +import java.nio.charset.Charset; +import java.util.ArrayList; +import java.util.Arrays; +import java.util.List; +import java.util.Map; +import java.util.Set; +import java.util.SortedMap; +import java.util.TreeMap; + +/** + * Utilities for SHOW ... commands. + */ +public final class ShowUtils { + private ShowUtils() { + throw new UnsupportedOperationException("ShowUtils should not be instantiated"); + } + + public static final Charset UTF_8 = Charset.forName("UTF-8"); + + public static DataOutputStream getOutputStream(Path outputFile, DDLOperationContext context) throws HiveException { + try { + FileSystem fs = outputFile.getFileSystem(context.getConf()); + return fs.create(outputFile); + } catch (Exception e) { + throw new HiveException(e); + } + } + + public static String propertiesToString(Map<String, String> props, Set<String> exclude) { + if (props.isEmpty()) { + return ""; + } + + SortedMap<String, String> sortedProperties = new TreeMap<String, String>(props); + List<String> realProps = new ArrayList<String>(); + for (Map.Entry<String, String> e : sortedProperties.entrySet()) { + if (e.getValue() != null && (exclude == null || !exclude.contains(e.getKey()))) { + realProps.add(" '" + e.getKey() + "'='" + HiveStringUtils.escapeHiveCommand(e.getValue()) + "'"); + } + } + return StringUtils.join(realProps, ", \n"); + } + + public static void writeToFile(String data, String file, DDLOperationContext context) throws IOException { + if (StringUtils.isEmpty(data)) { + return; + } + + Path resFile = new Path(file); + FileSystem fs = resFile.getFileSystem(context.getConf()); + try (FSDataOutputStream out = fs.create(resFile); + OutputStreamWriter writer = new OutputStreamWriter(out, "UTF-8")) { + writer.write(data); + writer.write((char) Utilities.newLineCode); + writer.flush(); + } + } + + public static void appendNonNull(StringBuilder builder, Object value) { + appendNonNull(builder, value, false); + } + + public static void appendNonNull(StringBuilder builder, Object value, boolean firstColumn) { + if (!firstColumn) { + builder.append((char)Utilities.tabCode); + } else if (builder.length() > 0) { + builder.append((char)Utilities.newLineCode); + } + if (value != null) { + builder.append(value); + } + } + + + public static String[] extractColumnValues(FieldSchema column, boolean isColumnStatsAvailable, + ColumnStatisticsObj columnStatisticsObj) { + List<String> values = new ArrayList<>(); + values.add(column.getName()); + values.add(column.getType()); + + if (isColumnStatsAvailable) { + if (columnStatisticsObj != null) { + ColumnStatisticsData statsData = columnStatisticsObj.getStatsData(); + if (statsData.isSetBinaryStats()) { + BinaryColumnStatsData binaryStats = statsData.getBinaryStats(); + values.addAll(Lists.newArrayList("", "", "" + binaryStats.getNumNulls(), "", + "" + binaryStats.getAvgColLen(), "" + binaryStats.getMaxColLen(), "", "", + convertToString(binaryStats.getBitVectors()))); + } else if (statsData.isSetStringStats()) { + StringColumnStatsData stringStats = statsData.getStringStats(); + values.addAll(Lists.newArrayList("", "", "" + stringStats.getNumNulls(), "" + stringStats.getNumDVs(), + "" + stringStats.getAvgColLen(), "" + stringStats.getMaxColLen(), "", "", + convertToString(stringStats.getBitVectors()))); + } else if (statsData.isSetBooleanStats()) { + BooleanColumnStatsData booleanStats = statsData.getBooleanStats(); + values.addAll(Lists.newArrayList("", "", "" + booleanStats.getNumNulls(), "", "", "", + "" + booleanStats.getNumTrues(), "" + booleanStats.getNumFalses(), + convertToString(booleanStats.getBitVectors()))); + } else if (statsData.isSetDecimalStats()) { + DecimalColumnStatsData decimalStats = statsData.getDecimalStats(); + values.addAll(Lists.newArrayList(convertToString(decimalStats.getLowValue()), + convertToString(decimalStats.getHighValue()), "" + decimalStats.getNumNulls(), + "" + decimalStats.getNumDVs(), "", "", "", "", convertToString(decimalStats.getBitVectors()))); + } else if (statsData.isSetDoubleStats()) { + DoubleColumnStatsData doubleStats = statsData.getDoubleStats(); + values.addAll(Lists.newArrayList("" + doubleStats.getLowValue(), "" + doubleStats.getHighValue(), + "" + doubleStats.getNumNulls(), "" + doubleStats.getNumDVs(), "", "", "", "", + convertToString(doubleStats.getBitVectors()))); + } else if (statsData.isSetLongStats()) { + LongColumnStatsData longStats = statsData.getLongStats(); + values.addAll(Lists.newArrayList("" + longStats.getLowValue(), "" + longStats.getHighValue(), + "" + longStats.getNumNulls(), "" + longStats.getNumDVs(), "", "", "", "", + convertToString(longStats.getBitVectors()))); + } else if (statsData.isSetDateStats()) { + DateColumnStatsData dateStats = statsData.getDateStats(); + values.addAll(Lists.newArrayList(convertToString(dateStats.getLowValue()), + convertToString(dateStats.getHighValue()), "" + dateStats.getNumNulls(), "" + dateStats.getNumDVs(), + "", "", "", "", convertToString(dateStats.getBitVectors()))); + } else if (statsData.isSetTimestampStats()) { + TimestampColumnStatsData timestampStats = statsData.getTimestampStats(); + values.addAll(Lists.newArrayList(convertToString(timestampStats.getLowValue()), + convertToString(timestampStats.getHighValue()), "" + timestampStats.getNumNulls(), + "" + timestampStats.getNumDVs(), "", "", "", "", convertToString(timestampStats.getBitVectors()))); + } + } else { + values.addAll(Lists.newArrayList("", "", "", "", "", "", "", "", "")); + } + } + + values.add(column.getComment() != null ? column.getComment() : ""); + return values.toArray(new String[] {}); + } + + public static String convertToString(Decimal val) { + if (val == null) { + return ""; + } + + HiveDecimal result = HiveDecimal.create(new BigInteger(val.getUnscaled()), val.getScale()); + return (result != null) ? result.toString() : ""; + } + + public static String convertToString(org.apache.hadoop.hive.metastore.api.Date val) { + if (val == null) { + return ""; + } + + DateWritableV2 writableValue = new DateWritableV2((int) val.getDaysSinceEpoch()); + return writableValue.toString(); + } + + private static String convertToString(byte[] buffer) { + if (buffer == null || buffer.length == 0) { + return ""; + } + return new String(Arrays.copyOfRange(buffer, 0, 2)); + } + + public static String convertToString(org.apache.hadoop.hive.metastore.api.Timestamp val) { + if (val == null) { + return ""; + } + + TimestampWritableV2 writableValue = new TimestampWritableV2(Timestamp.ofEpochSecond(val.getSecondsSinceEpoch())); + return writableValue.toString(); + } + + /** + * Convert the map to a JSON string. + */ + public static void asJson(OutputStream out, Map<String, Object> data) throws HiveException { + try { + new ObjectMapper().writeValue(out, data); + } catch (IOException e) { + throw new HiveException("Unable to convert to json", e); + } + } + + public static final String FIELD_DELIM = "\t"; + public static final String LINE_DELIM = "\n"; + + public static final int DEFAULT_STRINGBUILDER_SIZE = 2048; + public static final int ALIGNMENT = 20; + + /** + * Prints a row with the given fields into the builder. + * The last field could be a multiline field, and the extra lines should be padded. + * + * @param fields The fields to print + * @param tableInfo The target builder + * @param isLastLinePadded Is the last field could be printed in multiple lines, if contains newlines? + */ + public static void formatOutput(String[] fields, StringBuilder tableInfo, boolean isLastLinePadded, + boolean isFormatted) { + if (!isFormatted) { + for (int i = 0; i < fields.length; i++) { + Object value = HiveStringUtils.escapeJava(fields[i]); + if (value != null) { + tableInfo.append(value); + } + tableInfo.append((i == fields.length - 1) ? LINE_DELIM : FIELD_DELIM); + } + } else { + int[] paddings = new int[fields.length - 1]; + if (fields.length > 1) { + for (int i = 0; i < fields.length - 1; i++) { + if (fields[i] == null) { + tableInfo.append(FIELD_DELIM); + continue; + } + tableInfo.append(String.format("%-" + ALIGNMENT + "s", fields[i])).append(FIELD_DELIM); + paddings[i] = ALIGNMENT > fields[i].length() ? ALIGNMENT : fields[i].length(); + } + } + if (fields.length > 0) { + String value = fields[fields.length - 1]; + String unescapedValue = (isLastLinePadded && value != null) ? + value.replaceAll("\\\\n|\\\\r|\\\\r\\\\n", "\n") : value; + indentMultilineValue(unescapedValue, tableInfo, paddings, false); + } else { + tableInfo.append(LINE_DELIM); + } + } + } + + /** + * Prints a row the given fields to a formatted line. + * + * @param fields The fields to print + * @param tableInfo The target builder + */ + public static void formatOutput(String[] fields, StringBuilder tableInfo) { + formatOutput(fields, tableInfo, false, true); + } + + /** + * Prints the name value pair, and if the value contains newlines, it adds one more empty field + * before the two values (Assumes, the name value pair is already indented with it). + * + * @param name The field name to print + * @param value The value to print - might contain newlines + * @param tableInfo The target builder + */ + public static void formatOutput(String name, String value, StringBuilder tableInfo) { + tableInfo.append(String.format("%-" + ALIGNMENT + "s", name)).append(FIELD_DELIM); + int colNameLength = ALIGNMENT > name.length() ? ALIGNMENT : name.length(); Review comment: Math#max - fixed. ---------------------------------------------------------------- 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. For queries about this service, please contact Infrastructure at: [email protected] --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
