Examples with HiveVariableSource org.apache.hadoop.hive.conf.HiveVariableSource used on opensource projects

Example 1 with HiveVariableSource

use of org.apache.hadoop.hive.conf.HiveVariableSource in project hive by apache.

the class SetProcessor method setConf.

/**
   * @return A console message that is not strong enough to fail the command (e.g. deprecation).
   */
static String setConf(String varname, String key, String varvalue, boolean register) throws IllegalArgumentException {
    String result = null;
    HiveConf conf = SessionState.get().getConf();
    String value = new VariableSubstitution(new HiveVariableSource() {

        @Override
        public Map<String, String> getHiveVariable() {
            return SessionState.get().getHiveVariables();
        }
    }).substitute(conf, varvalue);
    if (conf.getBoolVar(HiveConf.ConfVars.HIVECONFVALIDATION)) {
        HiveConf.ConfVars confVars = HiveConf.getConfVars(key);
        if (confVars != null) {
            if (!confVars.isType(value)) {
                StringBuilder message = new StringBuilder();
                message.append("'SET ").append(varname).append('=').append(varvalue);
                message.append("' FAILED because ").append(key).append(" expects ");
                message.append(confVars.typeString()).append(" type value.");
                throw new IllegalArgumentException(message.toString());
            }
            String fail = confVars.validate(value);
            if (fail != null) {
                StringBuilder message = new StringBuilder();
                message.append("'SET ").append(varname).append('=').append(varvalue);
                message.append("' FAILED in validation : ").append(fail).append('.');
                throw new IllegalArgumentException(message.toString());
            }
        } else if (!removedConfigs.contains(key) && key.startsWith("hive.")) {
            throw new IllegalArgumentException("hive configuration " + key + " does not exists.");
        }
    }
    conf.verifyAndSet(key, value);
    if (HiveConf.ConfVars.HIVE_EXECUTION_ENGINE.varname.equals(key)) {
        if (!"spark".equals(value)) {
            SessionState.get().closeSparkSession();
        }
        if ("mr".equals(value)) {
            result = HiveConf.generateMrDeprecationWarning();
            LOG.warn(result);
        }
    }
    if (register) {
        SessionState.get().getOverriddenConfigurations().put(key, value);
    }
    return result;
}

Example 2 with HiveVariableSource

use of org.apache.hadoop.hive.conf.HiveVariableSource in project hive by apache.

the class Driver method compile.

// deferClose indicates if the close/destroy should be deferred when the process has been
// interrupted, it should be set to true if the compile is called within another method like
// runInternal, which defers the close to the called in that method.
private void compile(String command, boolean resetTaskIds, boolean deferClose) throws CommandProcessorResponse {
    PerfLogger perfLogger = SessionState.getPerfLogger(true);
    perfLogger.PerfLogBegin(CLASS_NAME, PerfLogger.DRIVER_RUN);
    perfLogger.PerfLogBegin(CLASS_NAME, PerfLogger.COMPILE);
    lDrvState.stateLock.lock();
    try {
        lDrvState.driverState = DriverState.COMPILING;
    } finally {
        lDrvState.stateLock.unlock();
    }
    command = new VariableSubstitution(new HiveVariableSource() {

        @Override
        public Map<String, String> getHiveVariable() {
            return SessionState.get().getHiveVariables();
        }
    }).substitute(conf, command);
    String queryStr = command;
    try {
        // command should be redacted to avoid to logging sensitive data
        queryStr = HookUtils.redactLogString(conf, command);
    } catch (Exception e) {
        LOG.warn("WARNING! Query command could not be redacted." + e);
    }
    checkInterrupted("at beginning of compilation.", null, null);
    if (ctx != null && ctx.getExplainAnalyze() != AnalyzeState.RUNNING) {
        // close the existing ctx etc before compiling a new query, but does not destroy driver
        closeInProcess(false);
    }
    if (resetTaskIds) {
        TaskFactory.resetId();
    }
    LockedDriverState.setLockedDriverState(lDrvState);
    String queryId = queryState.getQueryId();
    if (ctx != null) {
        setTriggerContext(queryId);
    }
    // save some info for webUI for use after plan is freed
    this.queryDisplay.setQueryStr(queryStr);
    this.queryDisplay.setQueryId(queryId);
    LOG.info("Compiling command(queryId=" + queryId + "): " + queryStr);
    conf.setQueryString(queryStr);
    // FIXME: sideeffect will leave the last query set at the session level
    SessionState.get().getConf().setQueryString(queryStr);
    SessionState.get().setupQueryCurrentTimestamp();
    // Whether any error occurred during query compilation. Used for query lifetime hook.
    boolean compileError = false;
    boolean parseError = false;
    try {
        // Initialize the transaction manager.  This must be done before analyze is called.
        if (initTxnMgr != null) {
            queryTxnMgr = initTxnMgr;
        } else {
            queryTxnMgr = SessionState.get().initTxnMgr(conf);
        }
        if (queryTxnMgr instanceof Configurable) {
            ((Configurable) queryTxnMgr).setConf(conf);
        }
        queryState.setTxnManager(queryTxnMgr);
        // In case when user Ctrl-C twice to kill Hive CLI JVM, we want to release locks
        // if compile is being called multiple times, clear the old shutdownhook
        ShutdownHookManager.removeShutdownHook(shutdownRunner);
        final HiveTxnManager txnMgr = queryTxnMgr;
        shutdownRunner = new Runnable() {

            @Override
            public void run() {
                try {
                    releaseLocksAndCommitOrRollback(false, txnMgr);
                } catch (LockException e) {
                    LOG.warn("Exception when releasing locks in ShutdownHook for Driver: " + e.getMessage());
                }
            }
        };
        ShutdownHookManager.addShutdownHook(shutdownRunner, SHUTDOWN_HOOK_PRIORITY);
        checkInterrupted("before parsing and analysing the query", null, null);
        if (ctx == null) {
            ctx = new Context(conf);
            setTriggerContext(queryId);
        }
        ctx.setRuntimeStatsSource(runtimeStatsSource);
        ctx.setCmd(command);
        ctx.setHDFSCleanup(true);
        perfLogger.PerfLogBegin(CLASS_NAME, PerfLogger.PARSE);
        // Trigger query hook before compilation
        hookRunner.runBeforeParseHook(command);
        ASTNode tree;
        try {
            tree = ParseUtils.parse(command, ctx);
        } catch (ParseException e) {
            parseError = true;
            throw e;
        } finally {
            hookRunner.runAfterParseHook(command, parseError);
        }
        perfLogger.PerfLogEnd(CLASS_NAME, PerfLogger.PARSE);
        hookRunner.runBeforeCompileHook(command);
        perfLogger.PerfLogBegin(CLASS_NAME, PerfLogger.ANALYZE);
        // Flush the metastore cache.  This assures that we don't pick up objects from a previous
        // query running in this same thread.  This has to be done after we get our semantic
        // analyzer (this is when the connection to the metastore is made) but before we analyze,
        // because at that point we need access to the objects.
        Hive.get().getMSC().flushCache();
        BaseSemanticAnalyzer sem;
        // Do semantic analysis and plan generation
        if (hookRunner.hasPreAnalyzeHooks()) {
            HiveSemanticAnalyzerHookContext hookCtx = new HiveSemanticAnalyzerHookContextImpl();
            hookCtx.setConf(conf);
            hookCtx.setUserName(userName);
            hookCtx.setIpAddress(SessionState.get().getUserIpAddress());
            hookCtx.setCommand(command);
            hookCtx.setHiveOperation(queryState.getHiveOperation());
            tree = hookRunner.runPreAnalyzeHooks(hookCtx, tree);
            sem = SemanticAnalyzerFactory.get(queryState, tree);
            openTransaction();
            sem.analyze(tree, ctx);
            hookCtx.update(sem);
            hookRunner.runPostAnalyzeHooks(hookCtx, sem.getAllRootTasks());
        } else {
            sem = SemanticAnalyzerFactory.get(queryState, tree);
            openTransaction();
            sem.analyze(tree, ctx);
        }
        LOG.info("Semantic Analysis Completed");
        // Retrieve information about cache usage for the query.
        if (conf.getBoolVar(HiveConf.ConfVars.HIVE_QUERY_RESULTS_CACHE_ENABLED)) {
            cacheUsage = sem.getCacheUsage();
        }
        // validate the plan
        sem.validate();
        perfLogger.PerfLogEnd(CLASS_NAME, PerfLogger.ANALYZE);
        checkInterrupted("after analyzing query.", null, null);
        // get the output schema
        schema = getSchema(sem, conf);
        plan = new QueryPlan(queryStr, sem, perfLogger.getStartTime(PerfLogger.DRIVER_RUN), queryId, queryState.getHiveOperation(), schema);
        conf.set("mapreduce.workflow.id", "hive_" + queryId);
        conf.set("mapreduce.workflow.name", queryStr);
        // initialize FetchTask right here
        if (plan.getFetchTask() != null) {
            plan.getFetchTask().initialize(queryState, plan, null, ctx.getOpContext());
        }
        // do the authorization check
        if (!sem.skipAuthorization() && HiveConf.getBoolVar(conf, HiveConf.ConfVars.HIVE_AUTHORIZATION_ENABLED)) {
            try {
                perfLogger.PerfLogBegin(CLASS_NAME, PerfLogger.DO_AUTHORIZATION);
                doAuthorization(queryState.getHiveOperation(), sem, command);
            } catch (AuthorizationException authExp) {
                console.printError("Authorization failed:" + authExp.getMessage() + ". Use SHOW GRANT to get more details.");
                errorMessage = authExp.getMessage();
                SQLState = "42000";
                throw createProcessorResponse(403);
            } finally {
                perfLogger.PerfLogEnd(CLASS_NAME, PerfLogger.DO_AUTHORIZATION);
            }
        }
        if (conf.getBoolVar(ConfVars.HIVE_LOG_EXPLAIN_OUTPUT)) {
            String explainOutput = getExplainOutput(sem, plan, tree);
            if (explainOutput != null) {
                LOG.info("EXPLAIN output for queryid " + queryId + " : " + explainOutput);
                if (conf.isWebUiQueryInfoCacheEnabled()) {
                    queryDisplay.setExplainPlan(explainOutput);
                }
            }
        }
    } catch (CommandProcessorResponse cpr) {
        throw cpr;
    } catch (Exception e) {
        checkInterrupted("during query compilation: " + e.getMessage(), null, null);
        compileError = true;
        ErrorMsg error = ErrorMsg.getErrorMsg(e.getMessage());
        errorMessage = "FAILED: " + e.getClass().getSimpleName();
        if (error != ErrorMsg.GENERIC_ERROR) {
            errorMessage += " [Error " + error.getErrorCode() + "]:";
        }
        // HIVE-4889
        if ((e instanceof IllegalArgumentException) && e.getMessage() == null && e.getCause() != null) {
            errorMessage += " " + e.getCause().getMessage();
        } else {
            errorMessage += " " + e.getMessage();
        }
        if (error == ErrorMsg.TXNMGR_NOT_ACID) {
            errorMessage += ". Failed command: " + queryStr;
        }
        SQLState = error.getSQLState();
        downstreamError = e;
        console.printError(errorMessage, "\n" + org.apache.hadoop.util.StringUtils.stringifyException(e));
        throw createProcessorResponse(error.getErrorCode());
    } finally {
        // before/after execution hook will never be executed.
        if (!parseError) {
            try {
                hookRunner.runAfterCompilationHook(command, compileError);
            } catch (Exception e) {
                LOG.warn("Failed when invoking query after-compilation hook.", e);
            }
        }
        double duration = perfLogger.PerfLogEnd(CLASS_NAME, PerfLogger.COMPILE) / 1000.00;
        ImmutableMap<String, Long> compileHMSTimings = dumpMetaCallTimingWithoutEx("compilation");
        queryDisplay.setHmsTimings(QueryDisplay.Phase.COMPILATION, compileHMSTimings);
        boolean isInterrupted = lDrvState.isAborted();
        if (isInterrupted && !deferClose) {
            closeInProcess(true);
        }
        lDrvState.stateLock.lock();
        try {
            if (isInterrupted) {
                lDrvState.driverState = deferClose ? DriverState.EXECUTING : DriverState.ERROR;
            } else {
                lDrvState.driverState = compileError ? DriverState.ERROR : DriverState.COMPILED;
            }
        } finally {
            lDrvState.stateLock.unlock();
        }
        if (isInterrupted) {
            LOG.info("Compiling command(queryId=" + queryId + ") has been interrupted after " + duration + " seconds");
        } else {
            LOG.info("Completed compiling command(queryId=" + queryId + "); Time taken: " + duration + " seconds");
        }
    }
}

Example 3 with HiveVariableSource

use of org.apache.hadoop.hive.conf.HiveVariableSource in project hive by apache.

the class ColumnStatsSemanticAnalyzer method genRewrittenQuery.

private String genRewrittenQuery(List<String> colNames, HiveConf conf, Map<String, String> partSpec, boolean isPartitionStats) throws SemanticException {
    StringBuilder rewrittenQueryBuilder = new StringBuilder("select ");
    for (int i = 0; i < colNames.size(); i++) {
        if (i > 0) {
            rewrittenQueryBuilder.append(" , ");
        }
        String func = HiveConf.getVar(conf, HiveConf.ConfVars.HIVE_STATS_NDV_ALGO).toLowerCase();
        rewrittenQueryBuilder.append("compute_stats(`");
        rewrittenQueryBuilder.append(escapeBackTicks(colNames.get(i)));
        rewrittenQueryBuilder.append("`, '" + func + "'");
        if ("fm".equals(func)) {
            int numBitVectors = 0;
            try {
                numBitVectors = HiveStatsUtils.getNumBitVectorsForNDVEstimation(conf);
            } catch (Exception e) {
                throw new SemanticException(e.getMessage());
            }
            rewrittenQueryBuilder.append(", " + numBitVectors);
        }
        rewrittenQueryBuilder.append(')');
    }
    if (isPartitionStats) {
        for (FieldSchema fs : tbl.getPartCols()) {
            rewrittenQueryBuilder.append(" , `" + fs.getName() + "`");
        }
    }
    rewrittenQueryBuilder.append(" from `");
    rewrittenQueryBuilder.append(tbl.getDbName());
    rewrittenQueryBuilder.append("`.");
    rewrittenQueryBuilder.append("`" + tbl.getTableName() + "`");
    isRewritten = true;
    // query
    if (isPartitionStats) {
        rewrittenQueryBuilder.append(genPartitionClause(partSpec));
    }
    String rewrittenQuery = rewrittenQueryBuilder.toString();
    rewrittenQuery = new VariableSubstitution(new HiveVariableSource() {

        @Override
        public Map<String, String> getHiveVariable() {
            return SessionState.get().getHiveVariables();
        }
    }).substitute(conf, rewrittenQuery);
    return rewrittenQuery;
}

Example 4 with HiveVariableSource

use of org.apache.hadoop.hive.conf.HiveVariableSource in project hive by apache.

the class CliDriver method processCmd1.

public CommandProcessorResponse processCmd1(String cmd) throws CommandProcessorException {
    CliSessionState ss = (CliSessionState) SessionState.get();
    String cmd_trimmed = HiveStringUtils.removeComments(cmd).trim();
    String[] tokens = tokenizeCmd(cmd_trimmed);
    CommandProcessorResponse response = new CommandProcessorResponse();
    if (cmd_trimmed.toLowerCase().equals("quit") || cmd_trimmed.toLowerCase().equals("exit")) {
        // if we have come this far - either the previous commands
        // are all successful or this is command line. in either case
        // this counts as a successful run
        ss.close();
        System.exit(0);
    } else if (tokens[0].equalsIgnoreCase("source")) {
        String cmd_1 = getFirstCmd(cmd_trimmed, tokens[0].length());
        cmd_1 = new VariableSubstitution(new HiveVariableSource() {

            @Override
            public Map<String, String> getHiveVariable() {
                return SessionState.get().getHiveVariables();
            }
        }).substitute(ss.getConf(), cmd_1);
        File sourceFile = new File(cmd_1);
        if (!sourceFile.isFile()) {
            console.printError("File: " + cmd_1 + " is not a file.");
            throw new CommandProcessorException(1);
        } else {
            try {
                response = processFile(cmd_1);
            } catch (IOException e) {
                console.printError("Failed processing file " + cmd_1 + " " + e.getLocalizedMessage(), stringifyException(e));
                throw new CommandProcessorException(1);
            }
        }
    } else if (cmd_trimmed.startsWith("!")) {
        // for shell commands, use unstripped command
        String shell_cmd = cmd.trim().substring(1);
        shell_cmd = new VariableSubstitution(new HiveVariableSource() {

            @Override
            public Map<String, String> getHiveVariable() {
                return SessionState.get().getHiveVariables();
            }
        }).substitute(ss.getConf(), shell_cmd);
        // shell_cmd = "/bin/bash -c \'" + shell_cmd + "\'";
        try {
            ShellCmdExecutor executor = new ShellCmdExecutor(shell_cmd, ss.out, ss.err);
            int responseCode = executor.execute();
            if (responseCode != 0) {
                console.printError("Command failed with exit code = " + response);
                ss.resetThreadName();
                throw new CommandProcessorException(responseCode);
            }
            response = new CommandProcessorResponse();
        } catch (Exception e) {
            console.printError("Exception raised from Shell command " + e.getLocalizedMessage(), stringifyException(e));
            throw new CommandProcessorException(1);
        }
    } else {
        // local mode
        try {
            try (CommandProcessor proc = CommandProcessorFactory.get(tokens, (HiveConf) conf)) {
                if (proc instanceof IDriver) {
                    // Let Driver strip comments using sql parser
                    response = processLocalCmd(cmd, proc, ss);
                } else {
                    response = processLocalCmd(cmd_trimmed, proc, ss);
                }
            }
        } catch (SQLException e) {
            console.printError("Failed processing command " + tokens[0] + " " + e.getLocalizedMessage(), org.apache.hadoop.util.StringUtils.stringifyException(e));
            throw new CommandProcessorException(1);
        } catch (CommandProcessorException e) {
            throw e;
        } catch (Exception e) {
            throw new RuntimeException(e);
        }
    }
    return response;
}

Example 5 with HiveVariableSource

use of org.apache.hadoop.hive.conf.HiveVariableSource in project hive by apache.

the class AddResourceProcessor method run.

@Override
public CommandProcessorResponse run(String command) throws CommandProcessorException {
    SessionState ss = SessionState.get();
    command = new VariableSubstitution(new HiveVariableSource() {

        @Override
        public Map<String, String> getHiveVariable() {
            return SessionState.get().getHiveVariables();
        }
    }).substitute(ss.getConf(), command);
    String[] tokens = command.split("\\s+");
    SessionState.ResourceType t;
    if (tokens.length < 2 || (t = SessionState.find_resource_type(tokens[0])) == null) {
        console.printError("Usage: add [" + StringUtils.join(SessionState.ResourceType.values(), "|") + "] <value> [<value>]*");
        throw new CommandProcessorException(1);
    }
    CommandProcessorResponse authErrResp = CommandUtil.authorizeCommand(ss, HiveOperationType.ADD, Arrays.asList(tokens));
    if (authErrResp != null) {
        // there was an authorization issue
        return authErrResp;
    }
    try {
        ss.add_resources(t, Arrays.asList(Arrays.copyOfRange(tokens, 1, tokens.length)));
    } catch (Exception e) {
        throw new CommandProcessorException(e);
    }
    return new CommandProcessorResponse();
}