Examples with HiveSemanticAnalyzerHook org.apache.hadoop.hive.ql.parse.HiveSemanticAnalyzerHook used

Example 1 with HiveSemanticAnalyzerHook

use of org.apache.hadoop.hive.ql.parse.HiveSemanticAnalyzerHook 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.
public int compile(String command, boolean resetTaskIds, boolean deferClose) {
    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);
    }
    if (isInterrupted()) {
        //indicate if need clean resource
        return handleInterruption("at beginning of compilation.");
    }
    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();
    }
    String queryId = conf.getVar(HiveConf.ConfVars.HIVEQUERYID);
    //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);
    SessionState.get().setupQueryCurrentTimestamp();
    // Whether any error occurred during query compilation. Used for query lifetime hook.
    boolean compileError = false;
    try {
        // Initialize the transaction manager.  This must be done before analyze is called.
        final HiveTxnManager txnManager = SessionState.get().initTxnMgr(conf);
        // 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);
        shutdownRunner = new Runnable() {

            @Override
            public void run() {
                try {
                    releaseLocksAndCommitOrRollback(false, txnManager);
                } catch (LockException e) {
                    LOG.warn("Exception when releasing locks in ShutdownHook for Driver: " + e.getMessage());
                }
            }
        };
        ShutdownHookManager.addShutdownHook(shutdownRunner, SHUTDOWN_HOOK_PRIORITY);
        if (isInterrupted()) {
            return handleInterruption("before parsing and analysing the query");
        }
        if (ctx == null) {
            ctx = new Context(conf);
        }
        ctx.setTryCount(getTryCount());
        ctx.setCmd(command);
        ctx.setHDFSCleanup(true);
        perfLogger.PerfLogBegin(CLASS_NAME, PerfLogger.PARSE);
        ASTNode tree = ParseUtils.parse(command, ctx);
        perfLogger.PerfLogEnd(CLASS_NAME, PerfLogger.PARSE);
        // Trigger query hook before compilation
        queryHooks = loadQueryHooks();
        if (queryHooks != null && !queryHooks.isEmpty()) {
            QueryLifeTimeHookContext qhc = new QueryLifeTimeHookContextImpl();
            qhc.setHiveConf(conf);
            qhc.setCommand(command);
            for (QueryLifeTimeHook hook : queryHooks) {
                hook.beforeCompile(qhc);
            }
        }
        perfLogger.PerfLogBegin(CLASS_NAME, PerfLogger.ANALYZE);
        BaseSemanticAnalyzer sem = SemanticAnalyzerFactory.get(queryState, tree);
        List<HiveSemanticAnalyzerHook> saHooks = getHooks(HiveConf.ConfVars.SEMANTIC_ANALYZER_HOOK, HiveSemanticAnalyzerHook.class);
        // 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();
        // Do semantic analysis and plan generation
        if (saHooks != null && !saHooks.isEmpty()) {
            HiveSemanticAnalyzerHookContext hookCtx = new HiveSemanticAnalyzerHookContextImpl();
            hookCtx.setConf(conf);
            hookCtx.setUserName(userName);
            hookCtx.setIpAddress(SessionState.get().getUserIpAddress());
            hookCtx.setCommand(command);
            for (HiveSemanticAnalyzerHook hook : saHooks) {
                tree = hook.preAnalyze(hookCtx, tree);
            }
            sem.analyze(tree, ctx);
            hookCtx.update(sem);
            for (HiveSemanticAnalyzerHook hook : saHooks) {
                hook.postAnalyze(hookCtx, sem.getAllRootTasks());
            }
        } else {
            sem.analyze(tree, ctx);
        }
        // Record any ACID compliant FileSinkOperators we saw so we can add our transaction ID to
        // them later.
        acidSinks = sem.getAcidFileSinks();
        LOG.info("Semantic Analysis Completed");
        // validate the plan
        sem.validate();
        acidInQuery = sem.hasAcidInQuery();
        perfLogger.PerfLogEnd(CLASS_NAME, PerfLogger.ANALYZE);
        if (isInterrupted()) {
            return handleInterruption("after analyzing query.");
        }
        // get the output schema
        schema = getSchema(sem, conf);
        plan = new QueryPlan(queryStr, sem, perfLogger.getStartTime(PerfLogger.DRIVER_RUN), queryId, queryState.getHiveOperation(), schema);
        conf.setQueryString(queryStr);
        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";
                return 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) {
                if (conf.getBoolVar(ConfVars.HIVE_LOG_EXPLAIN_OUTPUT)) {
                    LOG.info("EXPLAIN output for queryid " + queryId + " : " + explainOutput);
                }
                if (conf.isWebUiQueryInfoCacheEnabled()) {
                    queryDisplay.setExplainPlan(explainOutput);
                }
            }
        }
        return 0;
    } catch (Exception e) {
        if (isInterrupted()) {
            return handleInterruption("during query compilation: " + e.getMessage());
        }
        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));
        //todo: this is bad if returned as cmd shell exit
        return error.getErrorCode();
    // since it exceeds valid range of shell return values
    } finally {
        // before/after execution hook will never be executed.
        try {
            if (queryHooks != null && !queryHooks.isEmpty()) {
                QueryLifeTimeHookContext qhc = new QueryLifeTimeHookContextImpl();
                qhc.setHiveConf(conf);
                qhc.setCommand(command);
                for (QueryLifeTimeHook hook : queryHooks) {
                    hook.afterCompile(qhc, 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 = isInterrupted();
        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");
        }
    }
}

Also used :  HiveSemanticAnalyzerHookContext(org.apache.hadoop.hive.ql.parse.HiveSemanticAnalyzerHookContext) BaseSemanticAnalyzer(org.apache.hadoop.hive.ql.parse.BaseSemanticAnalyzer) AuthorizationException(org.apache.hadoop.hive.ql.metadata.AuthorizationException) HiveVariableSource(org.apache.hadoop.hive.conf.HiveVariableSource) QueryLifeTimeHookContextImpl(org.apache.hadoop.hive.ql.hooks.QueryLifeTimeHookContextImpl) PerfLogger(org.apache.hadoop.hive.ql.log.PerfLogger) QueryLifeTimeHook(org.apache.hadoop.hive.ql.hooks.QueryLifeTimeHook) MetricsQueryLifeTimeHook(org.apache.hadoop.hive.ql.hooks.MetricsQueryLifeTimeHook) LockException(org.apache.hadoop.hive.ql.lockmgr.LockException) HiveSemanticAnalyzerHook(org.apache.hadoop.hive.ql.parse.HiveSemanticAnalyzerHook) ASTNode(org.apache.hadoop.hive.ql.parse.ASTNode)  ParseContext(org.apache.hadoop.hive.ql.parse.ParseContext) HiveAuthzContext(org.apache.hadoop.hive.ql.security.authorization.plugin.HiveAuthzContext) ExecuteWithHookContext(org.apache.hadoop.hive.ql.hooks.ExecuteWithHookContext) HookContext(org.apache.hadoop.hive.ql.hooks.HookContext) QueryLifeTimeHookContext(org.apache.hadoop.hive.ql.hooks.QueryLifeTimeHookContext) HiveSemanticAnalyzerHookContext(org.apache.hadoop.hive.ql.parse.HiveSemanticAnalyzerHookContext) VariableSubstitution(org.apache.hadoop.hive.conf.VariableSubstitution) LockException(org.apache.hadoop.hive.ql.lockmgr.LockException)  IOException(java.io.IOException) HiveException(org.apache.hadoop.hive.ql.metadata.HiveException) AuthorizationException(org.apache.hadoop.hive.ql.metadata.AuthorizationException) HiveSemanticAnalyzerHookContextImpl(org.apache.hadoop.hive.ql.parse.HiveSemanticAnalyzerHookContextImpl) HiveTxnManager(org.apache.hadoop.hive.ql.lockmgr.HiveTxnManager) QueryLifeTimeHookContext(org.apache.hadoop.hive.ql.hooks.QueryLifeTimeHookContext)  Map(java.util.Map) LinkedHashMap(java.util.LinkedHashMap)  ImmutableMap(com.google.common.collect.ImmutableMap) HashMap(java.util.HashMap)

Aggregations

ImmutableMap (com.google.common.collect.ImmutableMap) 1  IOException (java.io.IOException) 1  HashMap(java.util.HashMap) 1  LinkedHashMap (java.util.LinkedHashMap) 1  Map (java.util.Map) 1  HiveVariableSource(org.apache.hadoop.hive.conf.HiveVariableSource) 1  VariableSubstitution(org.apache.hadoop.hive.conf.VariableSubstitution) 1  ExecuteWithHookContext(org.apache.hadoop.hive.ql.hooks.ExecuteWithHookContext) 1  HookContext(org.apache.hadoop.hive.ql.hooks.HookContext) 1  MetricsQueryLifeTimeHook(org.apache.hadoop.hive.ql.hooks.MetricsQueryLifeTimeHook) 1  QueryLifeTimeHook(org.apache.hadoop.hive.ql.hooks.QueryLifeTimeHook) 1  QueryLifeTimeHookContext(org.apache.hadoop.hive.ql.hooks.QueryLifeTimeHookContext) 1  QueryLifeTimeHookContextImpl(org.apache.hadoop.hive.ql.hooks.QueryLifeTimeHookContextImpl) 1  HiveTxnManager(org.apache.hadoop.hive.ql.lockmgr.HiveTxnManager) 1  LockException(org.apache.hadoop.hive.ql.lockmgr.LockException) 1  PerfLogger (org.apache.hadoop.hive.ql.log.PerfLogger) 1 AuthorizationException (org.apache.hadoop.hive.ql.metadata.AuthorizationException) 1  HiveException