diff --git a/.github/ISSUE_TEMPLATE/config.yml b/.github/ISSUE_TEMPLATE/config.yml index 545ccc8c21d7..368469f283ed 100644 --- a/.github/ISSUE_TEMPLATE/config.yml +++ b/.github/ISSUE_TEMPLATE/config.yml @@ -16,5 +16,5 @@ blank_issues_enabled: false contact_links: - name: Gluten Discussions - url: https://github.com/apache/incubator-gluten/discussions + url: https://github.com/apache/gluten/discussions about: Ask questions or discuss new feature ideas here. diff --git a/.github/PULL_REQUEST_TEMPLATE b/.github/PULL_REQUEST_TEMPLATE index c6fda31113e3..2ee082cb9b8b 100644 --- a/.github/PULL_REQUEST_TEMPLATE +++ b/.github/PULL_REQUEST_TEMPLATE @@ -2,7 +2,7 @@ Thank you for submitting a pull request! Here are some tips: 1. For first-time contributors, please read our contributing guide: - https://github.com/apache/incubator-gluten/blob/main/CONTRIBUTING.md + https://github.com/apache/gluten/blob/main/CONTRIBUTING.md 2. If necessary, create a GitHub issue for discussion beforehand to avoid duplicate work. 3. If the PR is specific to a single backend, include [VL] or [CH] in the PR title to indicate the Velox or ClickHouse backend, respectively. diff --git a/.github/workflows/dev_cron/pr_issue_linker.js b/.github/workflows/dev_cron/pr_issue_linker.js index 2fa2c7cd5e1f..0a9a892b2a2f 100644 --- a/.github/workflows/dev_cron/pr_issue_linker.js +++ b/.github/workflows/dev_cron/pr_issue_linker.js @@ -29,7 +29,7 @@ function detectIssueID(title) { } async function appendToPRDescription(github, context, pullRequestNumber, issuesID) { - const issueURL = `https://github.com/apache/incubator-gluten/issues/${issuesID}`; + const issueURL = `https://github.com/apache/gluten/issues/${issuesID}`; const issueReference = `#${issuesID}` // Fetch the current PR description. diff --git a/.github/workflows/velox_weekly.yml b/.github/workflows/velox_weekly.yml index 3ae0139671d5..1e0cd10155e6 100644 --- a/.github/workflows/velox_weekly.yml +++ b/.github/workflows/velox_weekly.yml @@ -62,7 +62,7 @@ jobs: export PATH=$JAVA_HOME/bin:$PATH # action/checkout does not work centos7 anymore, so we clone the branch instead. - git clone -b main --depth=1 https://github.com/apache/incubator-gluten.git && cd incubator-gluten/ + git clone -b main --depth=1 https://github.com/apache/gluten.git && cd gluten/ if [ ${{ github.event_name }} = "pull_request" ]; then git fetch origin ${{ github.ref }}:pr_branch && git checkout pr_branch fi diff --git a/.idea/vcs.xml b/.idea/vcs.xml index da48af121a44..f46f934cc9f6 100644 --- a/.idea/vcs.xml +++ b/.idea/vcs.xml @@ -25,7 +25,7 @@ GitHub share the sequence number of issues and pull requests, and it will redirect to the right place when the the sequence number not match kind. --> - diff --git a/CONTRIBUTING.md b/CONTRIBUTING.md index 67a0f235ad8a..fe061481538c 100644 --- a/CONTRIBUTING.md +++ b/CONTRIBUTING.md @@ -44,15 +44,15 @@ please add at least one UT to ensure code quality and reduce regression issues f Please update document for your proposed code change if necessary. -If a new config property is being introduced, please update [Configuration.md](https://github.com/apache/incubator-gluten/blob/main/docs/Configuration.md). +If a new config property is being introduced, please update [Configuration.md](https://github.com/apache/gluten/blob/main/docs/Configuration.md). ### Code Style ##### Java/Scala code style -Developer can import the code style setting to IDE and format Java/Scala code with spotless maven plugin. See [Java/Scala code style](https://github.com/apache/incubator-gluten/blob/main/docs/developers/NewToGluten.md#javascala-code-style). +Developer can import the code style setting to IDE and format Java/Scala code with spotless maven plugin. See [Java/Scala code style](https://github.com/apache/gluten/blob/main/docs/developers/NewToGluten.md#javascala-code-style). ##### C/C++ code style -There are some code style conventions need to comply. See [CppCodingStyle.md](https://github.com/apache/incubator-gluten/blob/main/docs/developers/CppCodingStyle.md). +There are some code style conventions need to comply. See [CppCodingStyle.md](https://github.com/apache/gluten/blob/main/docs/developers/CppCodingStyle.md). For Velox backend, developer can just execute `dev/formatcppcode.sh` to format C/C++ code. It requires `clang-format-15` installed in your development env. @@ -68,7 +68,7 @@ You can execute a script to fix license header issue, as the following shows. ### Gluten CI ##### ClickHouse Backend CI -To check CI failure for CH backend, please log in with the public account/password provided [here](https://github.com/apache/incubator-gluten/blob/main/docs/get-started/ClickHouse.md#new-ci-system). +To check CI failure for CH backend, please log in with the public account/password provided [here](https://github.com/apache/gluten/blob/main/docs/get-started/ClickHouse.md#new-ci-system). To re-trigger CH CI, please post the below comment on PR page: `Run Gluten Clickhouse CI` @@ -79,7 +79,7 @@ To check CI failure for Velox backend, please go into the GitHub action page fro To see the perf. impact on Velox backend, you can comment `/Benchmark Velox` on PR page to trigger a pretest. The benchmark (currently TPC-H) result will be posted after completed. -If some new dependency is required to be installed, you may need to do some change for CI docker at [this folder](https://github.com/apache/incubator-gluten/tree/main/tools/gluten-te). +If some new dependency is required to be installed, you may need to do some change for CI docker at [this folder](https://github.com/apache/gluten/tree/main/tools/gluten-te). ### Code Review diff --git a/README.md b/README.md index 134ce258f790..0fc3aa55d804 100644 --- a/README.md +++ b/README.md @@ -126,7 +126,7 @@ to view past discussions, or [subscribe to the mailing list](mailto:dev-subscrib ### Slack Channel (English) -Request an invitation to the ASF Slack workspace via [this page](https://github.com/apache/incubator-gluten/discussions/8429). Once invited, you can join the **incubator-gluten** channel. +Request an invitation to the ASF Slack workspace via [this page](https://github.com/apache/gluten/discussions/8429). Once invited, you can join the **gluten** channel. The ASF Slack login entry: https://the-asf.slack.com/. @@ -166,6 +166,6 @@ Gluten is licensed under [Apache License Version 2.0](https://www.apache.org/lic Gluten was initiated by Intel and Kyligence in 2022. Several other companies are also actively contributing to its development, including BIGO, Meituan, Alibaba Cloud, NetEase, Baidu, Microsoft, IBM, Google, etc. - - + + diff --git a/backends-clickhouse/src/main/scala/org/apache/gluten/backendsapi/clickhouse/CHRuleApi.scala b/backends-clickhouse/src/main/scala/org/apache/gluten/backendsapi/clickhouse/CHRuleApi.scala index 96e53c7a0d69..92693c7e9c96 100644 --- a/backends-clickhouse/src/main/scala/org/apache/gluten/backendsapi/clickhouse/CHRuleApi.scala +++ b/backends-clickhouse/src/main/scala/org/apache/gluten/backendsapi/clickhouse/CHRuleApi.scala @@ -181,7 +181,7 @@ object CHRuleApi { } /** - * Since https://github.com/apache/incubator-gluten/pull/883. + * Since https://github.com/apache/gluten/pull/883. * * TODO: Remove this since tricky to maintain. */ diff --git a/backends-clickhouse/src/main/scala/org/apache/gluten/backendsapi/clickhouse/CHValidatorApi.scala b/backends-clickhouse/src/main/scala/org/apache/gluten/backendsapi/clickhouse/CHValidatorApi.scala index ce2f127c2718..33fa68353125 100644 --- a/backends-clickhouse/src/main/scala/org/apache/gluten/backendsapi/clickhouse/CHValidatorApi.scala +++ b/backends-clickhouse/src/main/scala/org/apache/gluten/backendsapi/clickhouse/CHValidatorApi.scala @@ -114,7 +114,7 @@ object CHValidatorApi { * and make it into a new column which the shuffle will refer to. But we need to remove it from * the result columns from the shuffle. * - * Since https://github.com/apache/incubator-gluten/pull/1071. + * Since https://github.com/apache/gluten/pull/1071. */ def supportShuffleWithProject(outputPartitioning: Partitioning, child: SparkPlan): Boolean = { child match { diff --git a/backends-clickhouse/src/main/scala/org/apache/gluten/execution/CHColumnarToCarrierRowExec.scala b/backends-clickhouse/src/main/scala/org/apache/gluten/execution/CHColumnarToCarrierRowExec.scala index 95ac277ec0eb..b9defa667ad5 100644 --- a/backends-clickhouse/src/main/scala/org/apache/gluten/execution/CHColumnarToCarrierRowExec.scala +++ b/backends-clickhouse/src/main/scala/org/apache/gluten/execution/CHColumnarToCarrierRowExec.scala @@ -29,7 +29,7 @@ case class CHColumnarToCarrierRowExec(override val child: SparkPlan) override def rowType0(): Convention.RowType = CHCarrierRowType override protected def withNewChildInternal(newChild: SparkPlan): SparkPlan = copy(child = newChild) - // Since https://github.com/apache/incubator-gluten/pull/1595. + // Since https://github.com/apache/gluten/pull/1595. override protected def doExecuteColumnar(): RDD[ColumnarBatch] = { if (child.supportsColumnar) { child.executeColumnar() diff --git a/backends-clickhouse/src/main/scala/org/apache/gluten/expression/CHExpressions.scala b/backends-clickhouse/src/main/scala/org/apache/gluten/expression/CHExpressions.scala index 70d45a4e5232..96850a55085d 100644 --- a/backends-clickhouse/src/main/scala/org/apache/gluten/expression/CHExpressions.scala +++ b/backends-clickhouse/src/main/scala/org/apache/gluten/expression/CHExpressions.scala @@ -24,7 +24,7 @@ import org.apache.spark.sql.catalyst.expressions.aggregate.AggregateFunction // Static helper object for handling expressions that are specifically used in CH backend. object CHExpressions { - // Since https://github.com/apache/incubator-gluten/pull/1937. + // Since https://github.com/apache/gluten/pull/1937. def createAggregateFunction(context: SubstraitContext, aggregateFunc: AggregateFunction): Long = { val expressionExtensionTransformer = ExpressionExtensionTrait.findExpressionExtension(aggregateFunc.getClass) diff --git a/backends-clickhouse/src/test/scala/org/apache/gluten/execution/GlutenFunctionValidateSuite.scala b/backends-clickhouse/src/test/scala/org/apache/gluten/execution/GlutenFunctionValidateSuite.scala index 88abe3ae2e05..811eec08551e 100644 --- a/backends-clickhouse/src/test/scala/org/apache/gluten/execution/GlutenFunctionValidateSuite.scala +++ b/backends-clickhouse/src/test/scala/org/apache/gluten/execution/GlutenFunctionValidateSuite.scala @@ -861,7 +861,7 @@ class GlutenFunctionValidateSuite extends GlutenClickHouseWholeStageTransformerS } test("test parse string with blank to integer") { - // issue https://github.com/apache/incubator-gluten/issues/4956 + // issue https://github.com/apache/gluten/issues/4956 val sql = "select cast(concat(' ', cast(id as string)) as bigint) from range(10)" runQueryAndCompare(sql)(checkGlutenPlan[ProjectExecTransformer]) } @@ -915,7 +915,7 @@ class GlutenFunctionValidateSuite extends GlutenClickHouseWholeStageTransformerS } } - test("test issue: https://github.com/apache/incubator-gluten/issues/6561") { + test("test issue: https://github.com/apache/gluten/issues/6561") { val sql = """ |select diff --git a/backends-clickhouse/src/test/scala/org/apache/gluten/execution/compatibility/GlutenClickhouseFunctionSuite.scala b/backends-clickhouse/src/test/scala/org/apache/gluten/execution/compatibility/GlutenClickhouseFunctionSuite.scala index e5a88ff64819..e09c71c1077d 100644 --- a/backends-clickhouse/src/test/scala/org/apache/gluten/execution/compatibility/GlutenClickhouseFunctionSuite.scala +++ b/backends-clickhouse/src/test/scala/org/apache/gluten/execution/compatibility/GlutenClickhouseFunctionSuite.scala @@ -72,7 +72,7 @@ class GlutenClickhouseFunctionSuite extends ParquetSuite { } } - test("https://github.com/apache/incubator-gluten/issues/6938") { + test("https://github.com/apache/gluten/issues/6938") { val testSQL = s""" |select * from ( @@ -372,7 +372,7 @@ class GlutenClickhouseFunctionSuite extends ParquetSuite { } } - test("GLUTEN-7545: https://github.com/apache/incubator-gluten/issues/7545") { + test("GLUTEN-7545: https://github.com/apache/gluten/issues/7545") { withTable("regexp_test") { sql("create table if not exists regexp_test (id string) using parquet") sql("insert into regexp_test values('1999-6-1')") diff --git a/backends-clickhouse/src/test/scala/org/apache/gluten/execution/hive/GlutenClickHouseNativeWriteTableSuite.scala b/backends-clickhouse/src/test/scala/org/apache/gluten/execution/hive/GlutenClickHouseNativeWriteTableSuite.scala index a3c19c63ef4f..7202cc262b0c 100644 --- a/backends-clickhouse/src/test/scala/org/apache/gluten/execution/hive/GlutenClickHouseNativeWriteTableSuite.scala +++ b/backends-clickhouse/src/test/scala/org/apache/gluten/execution/hive/GlutenClickHouseNativeWriteTableSuite.scala @@ -514,7 +514,7 @@ class GlutenClickHouseNativeWriteTableSuite ("decimal_field", "decimal(23,12)"), ("date_field", "date") // ("timestamp_field", "timestamp") - // FIXME https://github.com/apache/incubator-gluten/issues/8053 + // FIXME https://github.com/apache/gluten/issues/8053 ) val origin_table = "origin_table" withSource(genTestData(), origin_table) { diff --git a/backends-clickhouse/src/test/scala/org/apache/gluten/execution/tpch/GlutenClickHouseTPCHColumnarShuffleParquetAQESuite.scala b/backends-clickhouse/src/test/scala/org/apache/gluten/execution/tpch/GlutenClickHouseTPCHColumnarShuffleParquetAQESuite.scala index c112a3b7797c..1187e3553a9e 100644 --- a/backends-clickhouse/src/test/scala/org/apache/gluten/execution/tpch/GlutenClickHouseTPCHColumnarShuffleParquetAQESuite.scala +++ b/backends-clickhouse/src/test/scala/org/apache/gluten/execution/tpch/GlutenClickHouseTPCHColumnarShuffleParquetAQESuite.scala @@ -319,7 +319,7 @@ class GlutenClickHouseTPCHColumnarShuffleParquetAQESuite extends ParquetTPCHSuit } } - ignore("https://github.com/apache/incubator-gluten/issues/7726") { + ignore("https://github.com/apache/gluten/issues/7726") { runQueryAndCompare(Arm.withResource( Source.fromFile(new File(s"$queryPath/tpch-schema-related/7726.sql"), "UTF-8"))(_.mkString)) { df => diff --git a/backends-velox/src-iceberg/test/scala/org/apache/gluten/execution/enhanced/VeloxIcebergSuite.scala b/backends-velox/src-iceberg/test/scala/org/apache/gluten/execution/enhanced/VeloxIcebergSuite.scala index c3d3c8edc658..888ccf6ec0c9 100644 --- a/backends-velox/src-iceberg/test/scala/org/apache/gluten/execution/enhanced/VeloxIcebergSuite.scala +++ b/backends-velox/src-iceberg/test/scala/org/apache/gluten/execution/enhanced/VeloxIcebergSuite.scala @@ -325,7 +325,7 @@ class VeloxIcebergSuite extends IcebergSuite { val lastExecId = statusStore.executionsList().last.executionId val executionMetrics = statusStore.executionMetrics(lastExecId) - // TODO: fix https://github.com/apache/incubator-gluten/issues/11510 + // TODO: fix https://github.com/apache/gluten/issues/11510 assert(executionMetrics(metrics("numWrittenFiles").id).toLong == 0) } } diff --git a/backends-velox/src/main/scala/org/apache/gluten/backendsapi/velox/VeloxBackend.scala b/backends-velox/src/main/scala/org/apache/gluten/backendsapi/velox/VeloxBackend.scala index 2ab3af7ceaad..6d5a2a6c2abd 100644 --- a/backends-velox/src/main/scala/org/apache/gluten/backendsapi/velox/VeloxBackend.scala +++ b/backends-velox/src/main/scala/org/apache/gluten/backendsapi/velox/VeloxBackend.scala @@ -154,7 +154,7 @@ object VeloxBackendSettings extends BackendSettingsApi { case ParquetReadFormat => val parquetOptions = new ParquetOptions(CaseInsensitiveMap(properties), SQLConf.get) if (parquetOptions.mergeSchema) { - // https://github.com/apache/incubator-gluten/issues/7174 + // https://github.com/apache/gluten/issues/7174 Some(s"not support when merge schema is true") } else { None diff --git a/backends-velox/src/main/scala/org/apache/gluten/backendsapi/velox/VeloxListenerApi.scala b/backends-velox/src/main/scala/org/apache/gluten/backendsapi/velox/VeloxListenerApi.scala index 8722ae8616b8..ba0f1570f802 100644 --- a/backends-velox/src/main/scala/org/apache/gluten/backendsapi/velox/VeloxListenerApi.scala +++ b/backends-velox/src/main/scala/org/apache/gluten/backendsapi/velox/VeloxListenerApi.scala @@ -315,7 +315,7 @@ object VeloxListenerApi { var parsed: Map[String, String] = GlutenConfigUtil.parseConfig(conf.getAll.toMap) - // Workaround for https://github.com/apache/incubator-gluten/issues/7837 + // Workaround for https://github.com/apache/gluten/issues/7837 if (isDriver && !inLocalMode(conf)) { parsed += (COLUMNAR_VELOX_CACHE_ENABLED.key -> "false") } diff --git a/backends-velox/src/main/scala/org/apache/gluten/backendsapi/velox/VeloxValidatorApi.scala b/backends-velox/src/main/scala/org/apache/gluten/backendsapi/velox/VeloxValidatorApi.scala index 8b2193b58042..2d2193a53871 100644 --- a/backends-velox/src/main/scala/org/apache/gluten/backendsapi/velox/VeloxValidatorApi.scala +++ b/backends-velox/src/main/scala/org/apache/gluten/backendsapi/velox/VeloxValidatorApi.scala @@ -90,11 +90,11 @@ class VeloxValidatorApi extends ValidatorApi { child: SparkPlan): Option[String] = { if (!BackendsApiManager.getSettings.supportEmptySchemaColumnarShuffle()) { if (outputAttributes.isEmpty) { - // See: https://github.com/apache/incubator-gluten/issues/7600. + // See: https://github.com/apache/gluten/issues/7600. return Some("Shuffle with empty output schema is not supported") } if (child.output.isEmpty) { - // See: https://github.com/apache/incubator-gluten/issues/7600. + // See: https://github.com/apache/gluten/issues/7600. return Some("Shuffle with empty input schema is not supported") } } diff --git a/backends-velox/src/test/scala/org/apache/gluten/execution/ArrowCsvScanSuite.scala b/backends-velox/src/test/scala/org/apache/gluten/execution/ArrowCsvScanSuite.scala index d2339b9cf2d8..97de504ffa40 100644 --- a/backends-velox/src/test/scala/org/apache/gluten/execution/ArrowCsvScanSuite.scala +++ b/backends-velox/src/test/scala/org/apache/gluten/execution/ArrowCsvScanSuite.scala @@ -97,7 +97,7 @@ class ArrowCsvScanWithTableCacheSuite extends ArrowCsvScanSuiteBase { } /** - * Test for GLUTEN-8453: https://github.com/apache/incubator-gluten/issues/8453. To make sure no + * Test for GLUTEN-8453: https://github.com/apache/gluten/issues/8453. To make sure no * error is thrown when caching an Arrow Java query plan. */ test("csv scan v1 with table cache") { @@ -107,7 +107,7 @@ class ArrowCsvScanWithTableCacheSuite extends ArrowCsvScanSuiteBase { } } -/** Since https://github.com/apache/incubator-gluten/pull/5850. */ +/** Since https://github.com/apache/gluten/pull/5850. */ @Ignore abstract class ArrowCsvScanSuite extends ArrowCsvScanSuiteBase { diff --git a/backends-velox/src/test/scala/org/apache/gluten/execution/MiscOperatorSuite.scala b/backends-velox/src/test/scala/org/apache/gluten/execution/MiscOperatorSuite.scala index e1a0fd98eeb5..e3f12e939e14 100644 --- a/backends-velox/src/test/scala/org/apache/gluten/execution/MiscOperatorSuite.scala +++ b/backends-velox/src/test/scala/org/apache/gluten/execution/MiscOperatorSuite.scala @@ -1998,7 +1998,7 @@ class MiscOperatorSuite extends VeloxWholeStageTransformerSuite with AdaptiveSpa } } - // Enable the test after fixing https://github.com/apache/incubator-gluten/issues/6827 + // Enable the test after fixing https://github.com/apache/gluten/issues/6827 ignore("Test round expression") { val df1 = runQueryAndCompare("SELECT round(cast(0.5549999999999999 as double), 2)") { _ => } checkLengthAndPlan(df1, 1) @@ -2032,7 +2032,7 @@ class MiscOperatorSuite extends VeloxWholeStageTransformerSuite with AdaptiveSpa } } - // Since https://github.com/apache/incubator-gluten/pull/7330. + // Since https://github.com/apache/gluten/pull/7330. test("field names contain non-ASCII characters") { withTempPath { path => diff --git a/backends-velox/src/test/scala/org/apache/gluten/execution/VeloxColumnarCacheSuite.scala b/backends-velox/src/test/scala/org/apache/gluten/execution/VeloxColumnarCacheSuite.scala index 1f135dd8e2d2..62f2c1d157c2 100644 --- a/backends-velox/src/test/scala/org/apache/gluten/execution/VeloxColumnarCacheSuite.scala +++ b/backends-velox/src/test/scala/org/apache/gluten/execution/VeloxColumnarCacheSuite.scala @@ -109,7 +109,7 @@ class VeloxColumnarCacheSuite extends VeloxWholeStageTransformerSuite with Adapt } } - // See issue https://github.com/apache/incubator-gluten/issues/8497. + // See issue https://github.com/apache/gluten/issues/8497. test("Input fallen back vanilla Spark columnar scan") { def withId(id: Int): Metadata = new MetadataBuilder().putLong("parquet.field.id", id).build() diff --git a/backends-velox/src/test/scala/org/apache/gluten/extension/columnar/transition/VeloxTransitionSuite.scala b/backends-velox/src/test/scala/org/apache/gluten/extension/columnar/transition/VeloxTransitionSuite.scala index 79f4b918e1ac..40770c5fb35a 100644 --- a/backends-velox/src/test/scala/org/apache/gluten/extension/columnar/transition/VeloxTransitionSuite.scala +++ b/backends-velox/src/test/scala/org/apache/gluten/extension/columnar/transition/VeloxTransitionSuite.scala @@ -82,7 +82,7 @@ class VeloxTransitionSuite extends SharedSparkSession with TransitionSuiteBase { val out = BackendTransitions.insert(in, outputsColumnar = false) // No explicit transition needed for ArrowNative-to-Velox. // FIXME: Add explicit transitions. - // See https://github.com/apache/incubator-gluten/issues/7313. + // See https://github.com/apache/gluten/issues/7313. assert( out == VeloxColumnarToRowExec( BatchUnary( diff --git a/backends-velox/src/test/scala/org/apache/gluten/functions/ScalarFunctionsValidateSuite.scala b/backends-velox/src/test/scala/org/apache/gluten/functions/ScalarFunctionsValidateSuite.scala index 302b4aa603d3..c040412cdf9a 100644 --- a/backends-velox/src/test/scala/org/apache/gluten/functions/ScalarFunctionsValidateSuite.scala +++ b/backends-velox/src/test/scala/org/apache/gluten/functions/ScalarFunctionsValidateSuite.scala @@ -496,7 +496,7 @@ abstract class ScalarFunctionsValidateSuite extends FunctionsValidateSuite { } } - // FIXME: Ignored: https://github.com/apache/incubator-gluten/issues/7600. + // FIXME: Ignored: https://github.com/apache/gluten/issues/7600. ignore("monotonically_increasintestg_id") { runQueryAndCompare("""SELECT monotonically_increasing_id(), l_orderkey | from lineitem limit 100""".stripMargin) { diff --git a/cpp-ch/local-engine/Parser/ExpressionParser.cpp b/cpp-ch/local-engine/Parser/ExpressionParser.cpp index 12392a9dfe13..08ad1dac129d 100644 --- a/cpp-ch/local-engine/Parser/ExpressionParser.cpp +++ b/cpp-ch/local-engine/Parser/ExpressionParser.cpp @@ -345,7 +345,7 @@ ExpressionParser::NodeRawConstPtr ExpressionParser::parseExpression(ActionsDAG & } else if ((isMap(denull_input_type) || isArray(denull_input_type) || isTuple(denull_input_type)) && isString(denull_output_type)) { - /// https://github.com/apache/incubator-gluten/issues/9049 + /// https://github.com/apache/gluten/issues/9049 result_node = toFunctionNode(actions_dag, "sparkCastComplexTypesToString", args); } else if (isString(denull_input_type) && substrait_type.has_bool_()) @@ -357,7 +357,7 @@ ExpressionParser::NodeRawConstPtr ExpressionParser::parseExpression(ActionsDAG & else if (isString(denull_input_type) && isInt(denull_output_type)) { /// Spark cast(x as INT) if x is String -> CH cast(trim(x) as INT) - /// Refer to https://github.com/apache/incubator-gluten/issues/4956 and https://github.com/apache/incubator-gluten/issues/8598 + /// Refer to https://github.com/apache/gluten/issues/4956 and https://github.com/apache/gluten/issues/8598 const auto * trim_str_arg = addConstColumn(actions_dag, std::make_shared(), " \t\n\r\f"); args[0] = toFunctionNode(actions_dag, "trimBothSpark", {args[0], trim_str_arg}); args.emplace_back(addConstColumn(actions_dag, std::make_shared(), output_type->getName())); diff --git a/cpp-ch/local-engine/Parser/scalar_function_parser/arrayHighOrderFunctions.cpp b/cpp-ch/local-engine/Parser/scalar_function_parser/arrayHighOrderFunctions.cpp index 5248a811da3d..7a8075ff18ee 100644 --- a/cpp-ch/local-engine/Parser/scalar_function_parser/arrayHighOrderFunctions.cpp +++ b/cpp-ch/local-engine/Parser/scalar_function_parser/arrayHighOrderFunctions.cpp @@ -96,7 +96,7 @@ class FunctionParserArrayTransform : public FunctionParser { /// Convert Array(T) to Array(U) if needed, Array(T) is the type of the first argument of transform. /// U is the argument type of lambda function. In some cases Array(T) is not equal to Array(U). - /// e.g. in the second query of https://github.com/apache/incubator-gluten/issues/6561, T is String, and U is Nullable(String) + /// e.g. in the second query of https://github.com/apache/gluten/issues/6561, T is String, and U is Nullable(String) /// The difference of both types will result in runtime exceptions in function capture. const auto & src_array_type = parsed_args[0]->result_type; DataTypePtr dst_array_type = std::make_shared(lambda_args.front().type); diff --git a/cpp-ch/local-engine/Storages/Output/NormalFileWriter.cpp b/cpp-ch/local-engine/Storages/Output/NormalFileWriter.cpp index d5cc0b9dcb4d..20e4e5a8ed39 100644 --- a/cpp-ch/local-engine/Storages/Output/NormalFileWriter.cpp +++ b/cpp-ch/local-engine/Storages/Output/NormalFileWriter.cpp @@ -39,7 +39,7 @@ const std::vector FileNameGenerator::SUPPORT_PLACEHOLDERS{"{id}", " /// For Nullable(Map(K, V)) or Nullable(Array(T)), if the i-th row is null, we must make sure its nested data is empty. /// It is for ORC/Parquet writing compatiability. For more details, refer to -/// https://github.com/apache/incubator-gluten/issues/8022 and https://github.com/apache/incubator-gluten/issues/8021 +/// https://github.com/apache/gluten/issues/8022 and https://github.com/apache/gluten/issues/8021 static ColumnPtr truncateNestedDataIfNull(const ColumnPtr & column) { if (const auto * col_const = checkAndGetColumn(column.get())) @@ -166,7 +166,7 @@ DB::Block NormalFileWriter::castBlock(const DB::Block & block) const /// In case input block didn't have the same types as the preferred schema, we cast the input block to the preferred schema. /// Notice that preferred_schema is the actual file schema, which is also the data schema of current inserted table. - /// Refer to issue: https://github.com/apache/incubator-gluten/issues/6588 + /// Refer to issue: https://github.com/apache/gluten/issues/6588 size_t index = 0; const auto & preferred_schema = file->getPreferredSchema(); for (auto & column : res) diff --git a/cpp/velox/operators/plannodes/CudfVectorStream.cc b/cpp/velox/operators/plannodes/CudfVectorStream.cc index 85cd2c021dba..2cec9b67b237 100644 --- a/cpp/velox/operators/plannodes/CudfVectorStream.cc +++ b/cpp/velox/operators/plannodes/CudfVectorStream.cc @@ -57,7 +57,7 @@ bool CudfVectorStreamBase::hasNext() { // driver to make the current task open to spilling. // // When a task is getting spilled, it should have been suspended so has zero running threads, otherwise there's - // possibility that this spill call hangs. See https://github.com/apache/incubator-gluten/issues/7243. + // possibility that this spill call hangs. See https://github.com/apache/gluten/issues/7243. // As of now, non-zero running threads usually happens when: // 1. Task A spills task B; // 2. Task A tries to grow buffers created by task B, during which spill is requested on task A again. diff --git a/cpp/velox/operators/plannodes/RowVectorStream.cc b/cpp/velox/operators/plannodes/RowVectorStream.cc index 7c0b00979a74..806da83b92c7 100644 --- a/cpp/velox/operators/plannodes/RowVectorStream.cc +++ b/cpp/velox/operators/plannodes/RowVectorStream.cc @@ -59,7 +59,7 @@ bool RowVectorStream::hasNext() { // driver to make the current task open to spilling. // // When a task is getting spilled, it should have been suspended so has zero running threads, otherwise there's - // possibility that this spill call hangs. See https://github.com/apache/incubator-gluten/issues/7243. + // possibility that this spill call hangs. See https://github.com/apache/gluten/issues/7243. // As of now, non-zero running threads usually happens when: // 1. Task A spills task B; // 2. Task A tries to grow buffers created by task B, during which spill is requested on task A again. diff --git a/cpp/velox/operators/serializer/VeloxColumnarBatchSerializer.cc b/cpp/velox/operators/serializer/VeloxColumnarBatchSerializer.cc index c12259420a58..1931b910ecb6 100644 --- a/cpp/velox/operators/serializer/VeloxColumnarBatchSerializer.cc +++ b/cpp/velox/operators/serializer/VeloxColumnarBatchSerializer.cc @@ -60,7 +60,7 @@ void VeloxColumnarBatchSerializer::append(const std::shared_ptr& auto rowVector = VeloxColumnarBatch::from(veloxPool_.get(), batch)->getRowVector(); if (serializer_ == nullptr) { // Using first batch's schema to create the Velox serializer. This logic was introduced in - // https://github.com/apache/incubator-gluten/pull/1568. It's a bit suboptimal because the schemas + // https://github.com/apache/gluten/pull/1568. It's a bit suboptimal because the schemas // across different batches may vary. auto numRows = rowVector->size(); auto rowType = asRowType(rowVector->type()); diff --git a/cpp/velox/substrait/SubstraitToVeloxPlanValidator.cc b/cpp/velox/substrait/SubstraitToVeloxPlanValidator.cc index 38d81320f9d9..39c67c0f8c6b 100644 --- a/cpp/velox/substrait/SubstraitToVeloxPlanValidator.cc +++ b/cpp/velox/substrait/SubstraitToVeloxPlanValidator.cc @@ -651,7 +651,7 @@ bool SubstraitToVeloxPlanValidator::validate(const ::substrait::WindowRel& windo } if (types.empty()) { - // See: https://github.com/apache/incubator-gluten/issues/7600. + // See: https://github.com/apache/gluten/issues/7600. LOG_VALIDATION_MSG("Validation failed for empty input schema in WindowRel."); return false; } diff --git a/dev/docker/Dockerfile.centos7-gcc13-static-build b/dev/docker/Dockerfile.centos7-gcc13-static-build index 89ac3f501208..1bd887995f5c 100644 --- a/dev/docker/Dockerfile.centos7-gcc13-static-build +++ b/dev/docker/Dockerfile.centos7-gcc13-static-build @@ -35,7 +35,7 @@ RUN set -ex; \ -e 's/mirror\.centos\.org/vault.centos.org/' \ /etc/yum.repos.d/CentOS-SCLo-scl-rh.repo; \ yum install -y git patch sudo java-1.8.0-openjdk-devel ccache; \ - git clone --depth=1 https://github.com/apache/incubator-gluten /opt/gluten; \ + git clone --depth=1 https://github.com/apache/gluten /opt/gluten; \ echo "check_certificate = off" >> ~/.wgetrc; \ cd /opt/gluten && bash ./dev/vcpkg/setup-build-depends.sh; \ yum remove gcc -y && yum clean all; \ diff --git a/dev/docker/Dockerfile.centos7-static-build b/dev/docker/Dockerfile.centos7-static-build index dcf6124a0b1f..638f144e0b5f 100644 --- a/dev/docker/Dockerfile.centos7-static-build +++ b/dev/docker/Dockerfile.centos7-static-build @@ -35,7 +35,7 @@ RUN set -ex; \ -e 's/mirror\.centos\.org/vault.centos.org/' \ /etc/yum.repos.d/CentOS-SCLo-scl-rh.repo; \ yum install -y git patch sudo java-1.8.0-openjdk-devel ccache; \ - git clone --depth=1 https://github.com/apache/incubator-gluten /opt/gluten; \ + git clone --depth=1 https://github.com/apache/gluten /opt/gluten; \ echo "check_certificate = off" >> ~/.wgetrc; \ cd /opt/gluten && bash ./dev/vcpkg/setup-build-depends.sh; \ mkdir -p ${VCPKG_PATH}; \ diff --git a/dev/docker/Dockerfile.centos8-dynamic-build b/dev/docker/Dockerfile.centos8-dynamic-build index 9e49b524e19f..785c6c545b85 100644 --- a/dev/docker/Dockerfile.centos8-dynamic-build +++ b/dev/docker/Dockerfile.centos8-dynamic-build @@ -36,7 +36,7 @@ RUN set -ex; \ wget -nv ${mirror_host}/celeborn/celeborn-0.6.1/apache-celeborn-0.6.1-bin.tgz?action=download -O /opt/apache-celeborn-0.6.1-bin.tgz; \ wget -nv ${mirror_host}/uniffle/0.10.0/apache-uniffle-0.10.0-bin.tar.gz?action=download -O /opt/apache-uniffle-0.10.0-bin.tar.gz; \ wget -nv ${mirror_host}/hadoop/common/hadoop-2.8.5/hadoop-2.8.5.tar.gz?action=download -O /opt/hadoop-2.8.5.tar.gz; \ - git clone --depth=1 https://github.com/apache/incubator-gluten /opt/gluten; \ + git clone --depth=1 https://github.com/apache/gluten /opt/gluten; \ cd /opt/gluten/.github/workflows/util/; \ ./install-resources.sh 3.3; \ ./install-resources.sh 3.4; \ diff --git a/dev/docker/Dockerfile.centos8-gcc13-static-build b/dev/docker/Dockerfile.centos8-gcc13-static-build index 1e92be37fd91..e4abfef2bef7 100644 --- a/dev/docker/Dockerfile.centos8-gcc13-static-build +++ b/dev/docker/Dockerfile.centos8-gcc13-static-build @@ -33,7 +33,7 @@ RUN set -ex; \ pip3 install cmake; \ rpm -qa | grep tzdata; \ dnf clean all; \ - git clone --depth=1 https://github.com/apache/incubator-gluten /opt/gluten; \ + git clone --depth=1 https://github.com/apache/gluten /opt/gluten; \ mkdir -p ${VCPKG_PATH}; \ echo "Build arrow, then install the native libs to system paths and jar package to .m2/ directory."; \ if [ "$(uname -m)" = "aarch64" ]; then \ diff --git a/dev/docker/Dockerfile.centos8-static-build b/dev/docker/Dockerfile.centos8-static-build index 40884d82ddcd..91448e346e47 100644 --- a/dev/docker/Dockerfile.centos8-static-build +++ b/dev/docker/Dockerfile.centos8-static-build @@ -33,7 +33,7 @@ RUN set -ex; \ yum install -y java-1.8.0-openjdk-devel patch git perl; \ rpm -qa | grep tzdata; \ dnf clean all; \ - git clone --depth=1 https://github.com/apache/incubator-gluten /opt/gluten; \ + git clone --depth=1 https://github.com/apache/gluten /opt/gluten; \ cd /opt/gluten && bash ./dev/vcpkg/setup-build-depends.sh; \ mkdir -p ${VCPKG_PATH}; \ echo "Build arrow, then install the native libs to system paths and jar package to .m2/ directory."; \ diff --git a/dev/docker/Dockerfile.centos9-dynamic-build b/dev/docker/Dockerfile.centos9-dynamic-build index c6b846f567b2..25866155cc96 100644 --- a/dev/docker/Dockerfile.centos9-dynamic-build +++ b/dev/docker/Dockerfile.centos9-dynamic-build @@ -34,7 +34,7 @@ RUN set -ex; \ wget -nv ${mirror_host}/celeborn/celeborn-0.6.1/apache-celeborn-0.6.1-bin.tgz?action=download -O /opt/apache-celeborn-0.6.1-bin.tgz; \ wget -nv ${mirror_host}/uniffle/0.10.0/apache-uniffle-0.10.0-bin.tar.gz?action=download -O /opt/apache-uniffle-0.10.0-bin.tar.gz; \ wget -nv ${mirror_host}/hadoop/common/hadoop-2.8.5/hadoop-2.8.5.tar.gz?action=download -O /opt/hadoop-2.8.5.tar.gz; \ - git clone --depth=1 https://github.com/apache/incubator-gluten /opt/gluten; \ + git clone --depth=1 https://github.com/apache/gluten /opt/gluten; \ cd /opt/gluten/.github/workflows/util/; \ ./install-resources.sh 3.3; \ ./install-resources.sh 3.4; \ diff --git a/dev/docker/Dockerfile.centos9-static-build b/dev/docker/Dockerfile.centos9-static-build index 43e7cac088fa..b3aeb1f16316 100644 --- a/dev/docker/Dockerfile.centos9-static-build +++ b/dev/docker/Dockerfile.centos9-static-build @@ -30,7 +30,7 @@ RUN set -ex; \ echo "check_certificate = off" >> ~/.wgetrc; \ yum install -y java-17-openjdk-devel patch git perl; \ dnf clean all; \ - git clone --depth=1 https://github.com/apache/incubator-gluten /opt/gluten; \ + git clone --depth=1 https://github.com/apache/gluten /opt/gluten; \ cd /opt/gluten && bash ./dev/vcpkg/setup-build-depends.sh; \ mkdir -p ${VCPKG_PATH}; \ echo "Build arrow, then install the native libs to system paths and jar package to .m2/ directory."; \ diff --git a/dev/docker/cudf/Dockerfile b/dev/docker/cudf/Dockerfile index 41598046ac6b..8f74b41528f0 100644 --- a/dev/docker/cudf/Dockerfile +++ b/dev/docker/cudf/Dockerfile @@ -25,7 +25,7 @@ RUN yum install -y sudo patch perl && \ dnf autoremove -y && dnf clean all; \ rm -rf /opt/rh/gcc-toolset-12 && ln -s /opt/rh/gcc-toolset-14 /opt/rh/gcc-toolset-12; \ ln -sf /usr/local/bin/cmake /usr/bin && \ - git clone --depth=1 https://github.com/apache/incubator-gluten /opt/gluten && \ + git clone --depth=1 https://github.com/apache/gluten /opt/gluten && \ cd /opt/gluten && \ source /opt/rh/gcc-toolset-14/enable && \ bash ./dev/buildbundle-veloxbe.sh --run_setup_script=OFF --build_arrow=ON --spark_version=3.4 --build_tests=ON --build_benchmarks=ON --enable_gpu=ON && \ diff --git a/dev/release/package-release.sh b/dev/release/package-release.sh index ae9b50668a44..4e9ed85cb688 100755 --- a/dev/release/package-release.sh +++ b/dev/release/package-release.sh @@ -62,14 +62,14 @@ for v in $SPARK_VERSIONS; do done SRC_ZIP="${TAG}.zip" -SRC_DIR="incubator-gluten-${RELEASE_VERSION}" +SRC_DIR="gluten-${RELEASE_VERSION}" echo "Packaging source code..." -wget https://github.com/apache/incubator-gluten/archive/refs/tags/${SRC_ZIP} +wget https://github.com/apache/gluten/archive/refs/tags/${SRC_ZIP} unzip -q ${SRC_ZIP} # Rename folder to remove "rc*" for formal release. -mv incubator-gluten-${TAG_VERSION} ${SRC_DIR} +mv gluten-${TAG_VERSION} ${SRC_DIR} # Remove .git and .github and other unwanted files from the source dir. rm -rf ${SRC_DIR}/.git \ ${SRC_DIR}/.github \ diff --git a/docs/_config.yml b/docs/_config.yml index 0d42e06f4fd1..e20ded9530b5 100644 --- a/docs/_config.yml +++ b/docs/_config.yml @@ -16,7 +16,7 @@ remote_theme: pmarsceill/just-the-docs aux_links: "Gluten on Github": - - "//github.com/apache/incubator-gluten" + - "//github.com/apache/gluten" plugins: - jekyll-optional-front-matter # GitHub Pages diff --git a/docs/developers/HowTo.md b/docs/developers/HowTo.md index 63d94c740040..256473a65cde 100644 --- a/docs/developers/HowTo.md +++ b/docs/developers/HowTo.md @@ -163,7 +163,7 @@ to let it override the corresponding C standard functions entirely. It may help Now, both Parquet and DWRF format files are supported, related scripts and files are under the directory of `${GLUTEN_HOME}/backends-velox/workload/tpch`. The file `README.md` under `${GLUTEN_HOME}/backends-velox/workload/tpch` offers some useful help, but it's still not enough and exact. -One way of run TPC-H test is to run velox-be by workflow, you can refer to [velox_backend.yml](https://github.com/apache/incubator-gluten/blob/main/.github/workflows/velox_backend.yml#L280) +One way of run TPC-H test is to run velox-be by workflow, you can refer to [velox_backend.yml](https://github.com/apache/gluten/blob/main/.github/workflows/velox_backend.yml#L280) Here we will explain how to run TPC-H on Velox backend with the Parquet file format. 1. First, prepare the datasets, you have two choices. diff --git a/docs/developers/HowToRelease.md b/docs/developers/HowToRelease.md index c5dcf5ea4995..051e39df2a9a 100644 --- a/docs/developers/HowToRelease.md +++ b/docs/developers/HowToRelease.md @@ -38,7 +38,7 @@ clone the repository of Gluten with a specific git tag that you want to build on We are taking `v1.6.0-example-rc3` as an example git tag in this guide. ```bash -git clone --branch v1.6.0-example-rc3 https://github.com/apache/incubator-gluten.git /workspace +git clone --branch v1.6.0-example-rc3 https://github.com/apache/gluten.git /workspace ``` ### Build @@ -85,7 +85,7 @@ total 481628 -rw-r--r--. 1 root root 104595103 Oct 14 14:19 apache-gluten-1.6.0-example-bin-spark-3.5.tar.gz ``` - + # Publish the Release This section outlines the steps for releasing Apache Gluten according to the Apache release guidelines. @@ -262,13 +262,13 @@ Hello, https://dist.apache.org/repos/dist/dev/gluten/{release-version}/ Release notes: - https://github.com/apache/incubator-gluten/releases/tag/{release-version} + https://github.com/apache/gluten/releases/tag/{release-version} Git tag for the release: - https://github.com/apache/incubator-gluten/releases/tag/{release-version} + https://github.com/apache/gluten/releases/tag/{release-version} Git commit id for the release: - https://github.com/apache/incubator-gluten/commit/{id} + https://github.com/apache/gluten/commit/{id} Keys to verify the Release Candidate: https://downloads.apache.org/gluten/KEYS @@ -292,7 +292,7 @@ Hello, To compile from the source, please refer to: - https://github.com/apache/incubator-gluten#building-from-source + https://github.com/apache/gluten#building-from-source Thanks, @@ -312,12 +312,12 @@ Whether it's a community forum, help center, or knowledge management platform, y Download Links: https://downloads.apache.org/gluten/ -Release Notes: https://github.com/apache/incubator-gluten/releases/tag/{release-version} +Release Notes: https://github.com/apache/gluten/releases/tag/{release-version} Website: https://gluten.apache.org/ Resources: -- Issue: https://github.com/apache/incubator-gluten/issues +- Issue: https://github.com/apache/gluten/issues - Mailing list: dev@gluten.apache.org Thanks, diff --git a/docs/developers/NewToGluten.md b/docs/developers/NewToGluten.md index 2d11cfba81bc..dd801f249ed0 100644 --- a/docs/developers/NewToGluten.md +++ b/docs/developers/NewToGluten.md @@ -128,7 +128,7 @@ compiling Gluten. Note: If you have previously compiled Velox in release mode, use the command below to compile in debug mode. ```bash -cd incubator-gluten/ep/build-velox/build/velox_ep +cd gluten/ep/build-velox/build/velox_ep # Build the Velox debug version in /_build/debug make debug EXTRA_CMAKE_FLAGS="-DVELOX_ENABLE_PARQUET=ON -DENABLE_HDFS=ON -DVELOX_BUILD_TESTING=OFF -DVELOX_ENABLE_DUCKDB=ON -DVELOX_BUILD_TEST_UTILS=ON" @@ -396,7 +396,7 @@ valgrind --leak-check=yes ./exec_backend_test ## Run TPC-H and TPC-DS We supply `/tools/gluten-it` to execute these queries. -See [velox_backend_x86.yml](https://github.com/apache/incubator-gluten/blob/main/.github/workflows/velox_backend_x86.yml). +See [velox_backend_x86.yml](https://github.com/apache/gluten/blob/main/.github/workflows/velox_backend_x86.yml). ## Enable Gluten for Spark diff --git a/docs/developers/QueryTrace.md b/docs/developers/QueryTrace.md index e3c1694ad22f..e133b1007718 100644 --- a/docs/developers/QueryTrace.md +++ b/docs/developers/QueryTrace.md @@ -6,7 +6,7 @@ parent: Developer Overview --- # Background -Currently, we have [MicroBenchmarks](https://github.com/apache/incubator-gluten/blob/main/docs/developers/MicroBenchmarks.md) to profile the Velox plan execution in stage level, now we have query trace replayer to specify plan node id to profile in operator level. +Currently, we have [MicroBenchmarks](https://github.com/apache/gluten/blob/main/docs/developers/MicroBenchmarks.md) to profile the Velox plan execution in stage level, now we have query trace replayer to specify plan node id to profile in operator level. We cannot profile operator level directly because ValueStreamNode cannot serialize and deserialize, so we should generate benchmark first, and then enable query trace in benchmark which replaces the ValueStreamNode to ValuesNode. diff --git a/docs/developers/SubstraitModifications.md b/docs/developers/SubstraitModifications.md index 8ca2ab4f107b..c91f2a3fb847 100644 --- a/docs/developers/SubstraitModifications.md +++ b/docs/developers/SubstraitModifications.md @@ -17,23 +17,23 @@ alternatives like `AdvancedExtension` could be considered. ## Modifications to algebra.proto -* Added `JsonReadOptions` and `TextReadOptions` in `FileOrFiles`([#1584](https://github.com/apache/incubator-gluten/pull/1584)). -* Changed join type `JOIN_TYPE_SEMI` to `JOIN_TYPE_LEFT_SEMI` and `JOIN_TYPE_RIGHT_SEMI`([#408](https://github.com/apache/incubator-gluten/pull/408)). +* Added `JsonReadOptions` and `TextReadOptions` in `FileOrFiles`([#1584](https://github.com/apache/gluten/pull/1584)). +* Changed join type `JOIN_TYPE_SEMI` to `JOIN_TYPE_LEFT_SEMI` and `JOIN_TYPE_RIGHT_SEMI`([#408](https://github.com/apache/gluten/pull/408)). * Added `WindowRel`, added `column_name` and `window_type` in `WindowFunction`, -changed `Unbounded` in `WindowFunction` into `Unbounded_Preceding` and `Unbounded_Following`, and added WindowType([#485](https://github.com/apache/incubator-gluten/pull/485)). -* Added `output_schema` in RelRoot([#1901](https://github.com/apache/incubator-gluten/pull/1901)). -* Added `ExpandRel`([#1361](https://github.com/apache/incubator-gluten/pull/1361)). -* Added `GenerateRel`([#574](https://github.com/apache/incubator-gluten/pull/574)). -* Added `PartitionColumn` in `LocalFiles`([#2405](https://github.com/apache/incubator-gluten/pull/2405)). -* Added `WriteRel` ([#3690](https://github.com/apache/incubator-gluten/pull/3690)). -* Added `TopNRel` ([#5409](https://github.com/apache/incubator-gluten/pull/5409)). -* Added `ref` field in window bound `Preceding` and `Following` ([#5626](https://github.com/apache/incubator-gluten/pull/5626)). -* Added `BucketSpec` field in `WriteRel`([#8386](https://github.com/apache/incubator-gluten/pull/8386)) -* Added `StreamKafka` in `ReadRel`([#8321](https://github.com/apache/incubator-gluten/pull/8321)) +changed `Unbounded` in `WindowFunction` into `Unbounded_Preceding` and `Unbounded_Following`, and added WindowType([#485](https://github.com/apache/gluten/pull/485)). +* Added `output_schema` in RelRoot([#1901](https://github.com/apache/gluten/pull/1901)). +* Added `ExpandRel`([#1361](https://github.com/apache/gluten/pull/1361)). +* Added `GenerateRel`([#574](https://github.com/apache/gluten/pull/574)). +* Added `PartitionColumn` in `LocalFiles`([#2405](https://github.com/apache/gluten/pull/2405)). +* Added `WriteRel` ([#3690](https://github.com/apache/gluten/pull/3690)). +* Added `TopNRel` ([#5409](https://github.com/apache/gluten/pull/5409)). +* Added `ref` field in window bound `Preceding` and `Following` ([#5626](https://github.com/apache/gluten/pull/5626)). +* Added `BucketSpec` field in `WriteRel`([#8386](https://github.com/apache/gluten/pull/8386)) +* Added `StreamKafka` in `ReadRel`([#8321](https://github.com/apache/gluten/pull/8321)) ## Modifications to type.proto -* Added `Nothing` in `Type`([#791](https://github.com/apache/incubator-gluten/pull/791)). -* Added `names` in `Struct`([#1878](https://github.com/apache/incubator-gluten/pull/1878)). -* Added `PartitionColumns` in `NamedStruct`([#320](https://github.com/apache/incubator-gluten/pull/320)). -* Remove `PartitionColumns` and add `column_types` in `NamedStruct`([#2405](https://github.com/apache/incubator-gluten/pull/2405)). +* Added `Nothing` in `Type`([#791](https://github.com/apache/gluten/pull/791)). +* Added `names` in `Struct`([#1878](https://github.com/apache/gluten/pull/1878)). +* Added `PartitionColumns` in `NamedStruct`([#320](https://github.com/apache/gluten/pull/320)). +* Remove `PartitionColumns` and add `column_types` in `NamedStruct`([#2405](https://github.com/apache/gluten/pull/2405)). diff --git a/docs/developers/velox-backend-build-in-docker.md b/docs/developers/velox-backend-build-in-docker.md index a1b1d734afc1..2bcb0562d56a 100755 --- a/docs/developers/velox-backend-build-in-docker.md +++ b/docs/developers/velox-backend-build-in-docker.md @@ -28,8 +28,8 @@ FROM apache/gluten:vcpkg-centos-7 # Build Gluten Jar RUN source /opt/rh/devtoolset-11/enable && \ - git clone https://github.com/apache/incubator-gluten.git && \ - cd incubator-gluten && \ + git clone https://github.com/apache/gluten.git && \ + cd gluten && \ ./dev/builddeps-veloxbe.sh --run_setup_script=OFF --enable_s3=ON --enable_gcs=ON --enable_abfs=ON --enable_vcpkg=ON --build_arrow=OFF && \ mvn clean package -Pbackends-velox -Pceleborn -Piceberg -Pdelta -Pspark-3.4 -DskipTests ``` @@ -39,7 +39,7 @@ The command builds Gluten jar in 'glutenimage': ``` docker build -t glutenimage -f dockerfile ``` -The gluten jar can be copied from glutenimage:/incubator-gluten/package/target/gluten-velox-bundle-*.jar +The gluten jar can be copied from glutenimage:/gluten/package/target/gluten-velox-bundle-*.jar # Dynamic link The dynamic link approach needs to install the dependencies libraries. It then dynamically link the .so files into libvelox.so and libgluten.so. Currently, Centos-7/8/9 and @@ -52,8 +52,8 @@ FROM apache/gluten:centos-8-jdk8 # Build Gluten Jar RUN source /opt/rh/devtoolset-11/enable && \ - git clone https://github.com/apache/incubator-gluten.git && \ - cd incubator-gluten && \ + git clone https://github.com/apache/gluten.git && \ + cd gluten && \ ./dev/builddeps-veloxbe.sh --run_setup_script=ON --enable_hdfs=ON --enable_vcpkg=OFF --build_arrow=OFF && \ mvn clean package -Pbackends-velox -Pceleborn -Piceberg -Pdelta -Pspark-3.4 -DskipTests && \ ./dev/build-thirdparty.sh @@ -65,4 +65,4 @@ The command builds Gluten jar in 'glutenimage': ``` docker build -t glutenimage -f dockerfile ``` -The gluten jar can be copied from glutenimage:/incubator-gluten/package/target/gluten-velox-bundle-*.jar and glutenimage:/incubator-gluten/package/target/gluten-thirdparty-lib-*.jar +The gluten jar can be copied from glutenimage:/gluten/package/target/gluten-velox-bundle-*.jar and glutenimage:/gluten/package/target/gluten-thirdparty-lib-*.jar diff --git a/docs/get-started/ClickHouse.md b/docs/get-started/ClickHouse.md index 20af8d9ec47e..15c06abc0266 100644 --- a/docs/get-started/ClickHouse.md +++ b/docs/get-started/ClickHouse.md @@ -52,7 +52,7 @@ You need to install the following software manually: Then, get Gluten code: ```shell -git clone https://github.com/apache/incubator-gluten.git +git clone https://github.com/apache/gluten.git ``` #### Setup ClickHouse backend development environment @@ -64,7 +64,7 @@ clone gluten repo ```shell -git clone https://github.com/apache/incubator-gluten.git +git clone https://github.com/apache/gluten.git ``` clone Kyligence/ClickHouse repo @@ -176,8 +176,8 @@ The prerequisites are the same as the one mentioned above. Compile Gluten with C - for Spark 3.3.1 ``` - git clone https://github.com/apache/incubator-gluten.git - cd incubator-gluten/ + git clone https://github.com/apache/gluten.git + cd gluten/ export MAVEN_OPTS="-Xmx8g -XX:ReservedCodeCacheSize=2g" mvn clean install -Pbackends-clickhouse -Phadoop-2.7.4 -Pspark-3.3 -Dhadoop.version=2.8.5 -DskipTests -Dcheckstyle.skip ls -al backends-clickhouse/target/gluten-XXXXX-spark-3.3-jar-with-dependencies.jar diff --git a/docs/get-started/Velox.md b/docs/get-started/Velox.md index 81c1b02818b6..27ff7d74560e 100644 --- a/docs/get-started/Velox.md +++ b/docs/get-started/Velox.md @@ -44,7 +44,7 @@ export PATH=$JAVA_HOME/bin:$PATH ## config maven, like proxy in ~/.m2/settings.xml ## fetch gluten code -git clone https://github.com/apache/incubator-gluten.git +git clone https://github.com/apache/gluten.git ``` # Build Gluten with Velox Backend @@ -173,7 +173,7 @@ cp /path/to/hdfs-client.xml hdfs-client.xml One typical deployment on Spark/HDFS cluster is to enable [short-circuit reading](https://hadoop.apache.org/docs/stable/hadoop-project-dist/hadoop-hdfs/ShortCircuitLocalReads.html). Short-circuit reads provide a substantial performance boost to many applications. -By default libhdfs3 does not set the default hdfs domain socket path to support HDFS short-circuit read. If this feature is required in HDFS setup, users may need to setup the domain socket path correctly by patching the libhdfs3 source code or by setting the correct config environment. In Gluten the short-circuit domain socket path is set to "/var/lib/hadoop-hdfs/dn_socket" in [build-velox.sh](https://github.com/apache/incubator-gluten/blob/main/ep/build-velox/src/build-velox.sh) So we need to make sure the folder existed and user has write access as below script. +By default libhdfs3 does not set the default hdfs domain socket path to support HDFS short-circuit read. If this feature is required in HDFS setup, users may need to setup the domain socket path correctly by patching the libhdfs3 source code or by setting the correct config environment. In Gluten the short-circuit domain socket path is set to "/var/lib/hadoop-hdfs/dn_socket" in [build-velox.sh](https://github.com/apache/gluten/blob/main/ep/build-velox/src/build-velox.sh) So we need to make sure the folder existed and user has write access as below script. ``` sudo mkdir -p /var/lib/hadoop-hdfs/ @@ -412,7 +412,7 @@ Spark3.3 has 387 functions in total. ~240 are commonly used. To get the support To identify what can be offloaded in a query and detailed fallback reasons, user can follow below steps to retrieve corresponding logs. ``` -1) Enable Gluten by proper [configuration](https://github.com/apache/incubator-gluten/blob/main/docs/Configuration.md). +1) Enable Gluten by proper [configuration](https://github.com/apache/gluten/blob/main/docs/Configuration.md). 2) Disable Spark AQE to trigger plan validation in Gluten spark.sql.adaptive.enabled = false diff --git a/docs/get-started/VeloxGPU.md b/docs/get-started/VeloxGPU.md index 7ee7584d0032..2a0503340b68 100644 --- a/docs/get-started/VeloxGPU.md +++ b/docs/get-started/VeloxGPU.md @@ -23,7 +23,7 @@ parent: Getting-Started - **NVIDIA Drivers**: Compatible with CUDA 12.8. - **Container Toolkit**: Install `nvidia-container-toolkit` ([guide](https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/latest/install-guide.html)). - **System Reboot**: Required after driver installation. -- **Environment Setup**: Use [`start-cudf.sh`](https://github.com/apache/incubator-gluten/tree/main/dev/start-cudf.sh) for host configuration . +- **Environment Setup**: Use [`start-cudf.sh`](https://github.com/apache/gluten/tree/main/dev/start-cudf.sh) for host configuration . --- @@ -86,4 +86,4 @@ Single Operator like Hash Agg shows 5x speedup. ## **9. Relevant Resources** 1. [CUDF Docs](https://docs.rapids.ai/api/cudf/stable/libcudf_docs/) - GPU operator APIs. -2. [Gluten GPU Issue #9098](https://github.com/apache/incubator-gluten/issues/8851) - Development tracker. +2. [Gluten GPU Issue #9098](https://github.com/apache/gluten/issues/8851) - Development tracker. diff --git a/docs/get-started/VeloxStageResourceAdj.md b/docs/get-started/VeloxStageResourceAdj.md index 77d9308b0ba1..dc8998afeab0 100644 --- a/docs/get-started/VeloxStageResourceAdj.md +++ b/docs/get-started/VeloxStageResourceAdj.md @@ -72,4 +72,4 @@ And the execution plan will like following with ApplyResourceProfile node insert • Tested with YARN/Kubernetes; other resource managers may need validation. -For issues or feedback, refer to [GLUTEN-8018](https://github.com/apache/incubator-gluten/issues/8018). +For issues or feedback, refer to [GLUTEN-8018](https://github.com/apache/gluten/issues/8018). diff --git a/docs/index.md b/docs/index.md index fc66717bc0e9..76b76ef6b7be 100644 --- a/docs/index.md +++ b/docs/index.md @@ -36,7 +36,7 @@ The basic rule of Gluten's design is that we would reuse spark's whole control f ## 1.3 Target User Gluten's target user is anyone who wants to accelerate SparkSQL fundamentally. As a plugin to Spark, Gluten doesn't require any change for dataframe API or SQL query, but only requires user to make correct configuration. -See Gluten configuration properties [here](https://github.com/apache/incubator-gluten/blob/main/docs/Configuration.md). +See Gluten configuration properties [here](https://github.com/apache/gluten/blob/main/docs/Configuration.md). ## 1.4 References diff --git a/docs/velox-backend-limitations.md b/docs/velox-backend-limitations.md index 6d7ef4457598..9dc830fb334a 100644 --- a/docs/velox-backend-limitations.md +++ b/docs/velox-backend-limitations.md @@ -9,9 +9,9 @@ must fall back to vanilla spark, etc. ### Override of Spark classes (For Spark3.2 and Spark3.3) Gluten avoids to modify Spark's existing code and use Spark APIs if possible. However, some APIs aren't exposed in Vanilla spark and we have to copy the Spark file and do the hardcode changes. The list of override classes can be found as ignoreClasses in package/pom.xml . If you use customized Spark, you may check if the files are modified in your spark, otherwise your changes will be overrided. -So you need to ensure preferentially load the Gluten jar to overwrite the jar of vanilla spark. Refer to [How to prioritize loading Gluten jars in Spark](https://github.com/apache/incubator-gluten/blob/main/docs/velox-backend-troubleshooting.md#incompatible-class-error-when-using-native-writer). +So you need to ensure preferentially load the Gluten jar to overwrite the jar of vanilla spark. Refer to [How to prioritize loading Gluten jars in Spark](https://github.com/apache/gluten/blob/main/docs/velox-backend-troubleshooting.md#incompatible-class-error-when-using-native-writer). -If not officially supported spark3.2/3.3 version is used, NoSuchMethodError can be thrown at runtime. More details see [issue-4514](https://github.com/apache/incubator-gluten/issues/4514). +If not officially supported spark3.2/3.3 version is used, NoSuchMethodError can be thrown at runtime. More details see [issue-4514](https://github.com/apache/gluten/issues/4514). ### Fallbacks Except the unsupported operators, functions, file formats, data sources listed in , there are some known cases also fall back to Vanilla Spark. @@ -156,7 +156,7 @@ CSV read will also fall back to vanilla Spark and log warning when user specifie ### Utilizing Map Type as Hash Keys in ColumnarShuffleExchange Spark uses the `spark.sql.legacy.allowHashOnMapType` configuration to support hash map key functions. -Gluten enables this configuration during the creation of ColumnarShuffleExchange, as shown in the code [link](https://github.com/apache/incubator-gluten/blob/0dacac84d3bf3d2759a5dd7e0735147852d2845d/backends-velox/src/main/scala/org/apache/gluten/backendsapi/velox/VeloxSparkPlanExecApi.scala#L355-L363). +Gluten enables this configuration during the creation of ColumnarShuffleExchange, as shown in the code [link](https://github.com/apache/gluten/blob/0dacac84d3bf3d2759a5dd7e0735147852d2845d/backends-velox/src/main/scala/org/apache/gluten/backendsapi/velox/VeloxSparkPlanExecApi.scala#L355-L363). This method bypasses Spark's unresolved checks and creates projects with the hash(mapType) operator before ColumnarShuffleExchange. However, if `spark.sql.legacy.allowHashOnMapType` is disabled in a test environment, projects using the hash(mapType) expression may throw an `Invalid call to dataType on unresolved object` exception during validation, causing them to fallback to vanilla Spark, as referenced in the code [link](https://github.com/apache/spark/blob/de5fa426e23b84fc3c2bddeabcd2e1eda515abd5/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/hash.scala#L291-L296). Enabling this configuration allows the project to be offloaded to Velox. diff --git a/gluten-arrow/src/main/java/org/apache/gluten/memory/listener/ManagedReservationListener.java b/gluten-arrow/src/main/java/org/apache/gluten/memory/listener/ManagedReservationListener.java index 96b0f544c15d..4fc9d5d5edd7 100644 --- a/gluten-arrow/src/main/java/org/apache/gluten/memory/listener/ManagedReservationListener.java +++ b/gluten-arrow/src/main/java/org/apache/gluten/memory/listener/ManagedReservationListener.java @@ -32,7 +32,7 @@ public class ManagedReservationListener implements ReservationListener { private final SimpleMemoryUsageRecorder sharedUsage; // Lock shared by task. Using a common lock avoids ABBA deadlock // when multiple listeners created under the same TMM. - // See: https://github.com/apache/incubator-gluten/issues/6622 + // See: https://github.com/apache/gluten/issues/6622 private final Object sharedLock; public ManagedReservationListener( diff --git a/gluten-arrow/src/main/java/org/apache/spark/sql/execution/unsafe/UnsafeByteArray.java b/gluten-arrow/src/main/java/org/apache/spark/sql/execution/unsafe/UnsafeByteArray.java index 8a25beec21c8..089abdfd29d9 100644 --- a/gluten-arrow/src/main/java/org/apache/spark/sql/execution/unsafe/UnsafeByteArray.java +++ b/gluten-arrow/src/main/java/org/apache/spark/sql/execution/unsafe/UnsafeByteArray.java @@ -157,7 +157,7 @@ public void readExternal(ObjectInput in) throws IOException { * It's needed once the broadcast variable is garbage collected. Since now, we don't have an * elegant way to free the underlying memory in off-heap. * - *

Since: https://github.com/apache/incubator-gluten/pull/8127. + *

Since: https://github.com/apache/gluten/pull/8127. */ public void finalize() throws Throwable { release(); diff --git a/gluten-core/src/main/java/org/apache/gluten/memory/memtarget/DynamicOffHeapSizingMemoryTarget.java b/gluten-core/src/main/java/org/apache/gluten/memory/memtarget/DynamicOffHeapSizingMemoryTarget.java index 3124f78fb79a..396a80b100c3 100644 --- a/gluten-core/src/main/java/org/apache/gluten/memory/memtarget/DynamicOffHeapSizingMemoryTarget.java +++ b/gluten-core/src/main/java/org/apache/gluten/memory/memtarget/DynamicOffHeapSizingMemoryTarget.java @@ -36,7 +36,7 @@ /** * The memory target used by dynamic off-heap sizing. Since - * https://github.com/apache/incubator-gluten/issues/5439. + * https://github.com/apache/gluten/issues/5439. */ @Experimental public class DynamicOffHeapSizingMemoryTarget implements MemoryTarget, KnownNameAndStats { @@ -143,7 +143,7 @@ public long borrow(long size) { } // Only JVM shrinking can reclaim space from the total JVM memory. - // See https://github.com/apache/incubator-gluten/issues/9276. + // See https://github.com/apache/gluten/issues/9276. long totalHeapMemory = Runtime.getRuntime().totalMemory(); long freeHeapMemory = Runtime.getRuntime().freeMemory(); long usedOffHeapMemory = USED_OFF_HEAP_BYTES.get(); diff --git a/gluten-core/src/main/java/org/apache/gluten/memory/memtarget/MemoryTargets.java b/gluten-core/src/main/java/org/apache/gluten/memory/memtarget/MemoryTargets.java index b5138bd4c6d8..4a01ff94e4d3 100644 --- a/gluten-core/src/main/java/org/apache/gluten/memory/memtarget/MemoryTargets.java +++ b/gluten-core/src/main/java/org/apache/gluten/memory/memtarget/MemoryTargets.java @@ -87,11 +87,11 @@ public static TreeMemoryTarget newConsumer( // We don't need to retry on OOM in the case one single task occupies the whole executor. return consumer; } - // Since https://github.com/apache/incubator-gluten/pull/8132. + // Since https://github.com/apache/gluten/pull/8132. // Retry of spilling is needed in multi-slot and legacy mode (formerly named as share mode) // because the maxMemoryPerTask defined by vanilla Spark's ExecutionMemoryPool is dynamic. // - // See the original issue https://github.com/apache/incubator-gluten/issues/8128. + // See the original issue https://github.com/apache/gluten/issues/8128. return new RetryOnOomMemoryTarget( consumer, () -> { diff --git a/gluten-core/src/main/scala/org/apache/gluten/config/GlutenCoreConfig.scala b/gluten-core/src/main/scala/org/apache/gluten/config/GlutenCoreConfig.scala index d362060ded98..0caf90c659a0 100644 --- a/gluten-core/src/main/scala/org/apache/gluten/config/GlutenCoreConfig.scala +++ b/gluten-core/src/main/scala/org/apache/gluten/config/GlutenCoreConfig.scala @@ -186,7 +186,7 @@ object GlutenCoreConfig extends ConfigRegistry { .intConf .createWithDefaultString("-1") - // Since https://github.com/apache/incubator-gluten/issues/5439. + // Since https://github.com/apache/gluten/issues/5439. val DYNAMIC_OFFHEAP_SIZING_ENABLED = buildStaticConf("spark.gluten.memory.dynamic.offHeap.sizing.enabled") .experimental() @@ -204,7 +204,7 @@ object GlutenCoreConfig extends ConfigRegistry { .booleanConf .createWithDefault(false) - // Since https://github.com/apache/incubator-gluten/issues/5439. + // Since https://github.com/apache/gluten/issues/5439. val DYNAMIC_OFFHEAP_SIZING_MEMORY_FRACTION = buildStaticConf("spark.gluten.memory.dynamic.offHeap.sizing.memory.fraction") .experimental() diff --git a/gluten-core/src/main/scala/org/apache/gluten/extension/GlutenColumnarRule.scala b/gluten-core/src/main/scala/org/apache/gluten/extension/GlutenColumnarRule.scala index da0fa12bb059..15a6fa0c5a15 100644 --- a/gluten-core/src/main/scala/org/apache/gluten/extension/GlutenColumnarRule.scala +++ b/gluten-core/src/main/scala/org/apache/gluten/extension/GlutenColumnarRule.scala @@ -95,7 +95,7 @@ case class GlutenColumnarRule( case _ => throw new IllegalStateException( "This should not happen. Please leave an issue at" + - " https://github.com/apache/incubator-gluten.") + " https://github.com/apache/gluten.") } val vanillaPlan = Transitions.insert(originalPlan, outputsColumnar) val applier = applierBuilder.apply(session) diff --git a/gluten-core/src/main/scala/org/apache/gluten/extension/columnar/enumerated/planner/metadata/Schema.scala b/gluten-core/src/main/scala/org/apache/gluten/extension/columnar/enumerated/planner/metadata/Schema.scala index 1e8ff1ae59db..b17c5fe62d6d 100644 --- a/gluten-core/src/main/scala/org/apache/gluten/extension/columnar/enumerated/planner/metadata/Schema.scala +++ b/gluten-core/src/main/scala/org/apache/gluten/extension/columnar/enumerated/planner/metadata/Schema.scala @@ -56,7 +56,7 @@ object Schema { if (one != other) { // We apply loose restriction on schema. Since Gluten still have some customized // logics causing schema of an operator to change after being transformed. - // For example: https://github.com/apache/incubator-gluten/pull/5171 + // For example: https://github.com/apache/gluten/pull/5171 logWarning(s"Warning: Schema mismatch: one: $one, other: $other") } } diff --git a/gluten-core/src/main/scala/org/apache/gluten/extension/columnar/heuristic/RewriteSparkPlanRulesManager.scala b/gluten-core/src/main/scala/org/apache/gluten/extension/columnar/heuristic/RewriteSparkPlanRulesManager.scala index 24fa7a6fc974..5bbb5d6e8447 100644 --- a/gluten-core/src/main/scala/org/apache/gluten/extension/columnar/heuristic/RewriteSparkPlanRulesManager.scala +++ b/gluten-core/src/main/scala/org/apache/gluten/extension/columnar/heuristic/RewriteSparkPlanRulesManager.scala @@ -75,7 +75,7 @@ class RewriteSparkPlanRulesManager private ( } catch { case e: Exception => // TODO: Remove this catch block - // See https://github.com/apache/incubator-gluten/issues/7766 + // See https://github.com/apache/gluten/issues/7766 (origin, Option(e.getMessage)) } } diff --git a/gluten-core/src/main/scala/org/apache/spark/sql/execution/adaptive/GlutenCost.scala b/gluten-core/src/main/scala/org/apache/spark/sql/execution/adaptive/GlutenCost.scala index df0b6fafe900..dbdbb3c5d046 100644 --- a/gluten-core/src/main/scala/org/apache/spark/sql/execution/adaptive/GlutenCost.scala +++ b/gluten-core/src/main/scala/org/apache/spark/sql/execution/adaptive/GlutenCost.scala @@ -19,7 +19,7 @@ package org.apache.spark.sql.execution.adaptive import org.apache.spark.sql.errors.QueryExecutionErrors import org.apache.spark.sql.execution.SparkPlan -/** Since https://github.com/apache/incubator-gluten/pull/6143. */ +/** Since https://github.com/apache/gluten/pull/6143. */ class GlutenCost(val eval: CostEvaluator, val plan: SparkPlan) extends Cost { override def compare(that: Cost): Int = that match { case that: GlutenCost if plan eq that.plan => diff --git a/gluten-core/src/main/scala/org/apache/spark/sql/execution/adaptive/GlutenCostEvaluator.scala b/gluten-core/src/main/scala/org/apache/spark/sql/execution/adaptive/GlutenCostEvaluator.scala index f53a80639af0..6c5300aa0dac 100644 --- a/gluten-core/src/main/scala/org/apache/spark/sql/execution/adaptive/GlutenCostEvaluator.scala +++ b/gluten-core/src/main/scala/org/apache/spark/sql/execution/adaptive/GlutenCostEvaluator.scala @@ -25,7 +25,7 @@ import org.apache.spark.util.{SparkVersionUtil, Utils} /** * This [[CostEvaluator]] is to force use the new physical plan when cost is equal. * - * Since https://github.com/apache/incubator-gluten/pull/6143. + * Since https://github.com/apache/gluten/pull/6143. */ case class GlutenCostEvaluator() extends CostEvaluator with SQLConfHelper { diff --git a/gluten-flink/docs/Flink.md b/gluten-flink/docs/Flink.md index 572df629c17b..1c800fb42db9 100644 --- a/gluten-flink/docs/Flink.md +++ b/gluten-flink/docs/Flink.md @@ -57,7 +57,7 @@ mvn clean install -DskipTests -Dgpg.skip -Dspotless.skip=true ## config maven, like proxy in ~/.m2/settings.xml ## fetch gluten code -git clone https://github.com/apache/incubator-gluten.git +git clone https://github.com/apache/gluten.git ``` # Build Gluten Flink with Velox Backend @@ -126,7 +126,7 @@ bin/flink run examples/table/StreamSQLExample.jar Then you can get the result in `log/flink-*-taskexecutor-*.out`. And you can see an operator named `gluten-cal` from the web frontend of your flink job. -**Notice: current this example will cause npe until [issue-10315](https://github.com/apache/incubator-gluten/issues/10315) get resolved.** +**Notice: current this example will cause npe until [issue-10315](https://github.com/apache/gluten/issues/10315) get resolved.** #### All operators executed by native Another example supports all operators executed by native. diff --git a/gluten-hudi/src/main/scala/org/apache/gluten/execution/OffloadHudiScan.scala b/gluten-hudi/src/main/scala/org/apache/gluten/execution/OffloadHudiScan.scala index f2cc24ceafaf..60bf12a51b77 100644 --- a/gluten-hudi/src/main/scala/org/apache/gluten/execution/OffloadHudiScan.scala +++ b/gluten-hudi/src/main/scala/org/apache/gluten/execution/OffloadHudiScan.scala @@ -20,7 +20,7 @@ import org.apache.gluten.extension.columnar.offload.OffloadSingleNode import org.apache.spark.sql.execution.SparkPlan -/** Since https://github.com/apache/incubator-gluten/pull/6049. */ +/** Since https://github.com/apache/gluten/pull/6049. */ case class OffloadHudiScan() extends OffloadSingleNode { override def offload(plan: SparkPlan): SparkPlan = { plan match { diff --git a/gluten-iceberg/src/main/scala/org/apache/gluten/execution/IcebergScanTransformer.scala b/gluten-iceberg/src/main/scala/org/apache/gluten/execution/IcebergScanTransformer.scala index 483f5c147f9e..e4151c823c83 100644 --- a/gluten-iceberg/src/main/scala/org/apache/gluten/execution/IcebergScanTransformer.scala +++ b/gluten-iceberg/src/main/scala/org/apache/gluten/execution/IcebergScanTransformer.scala @@ -155,7 +155,7 @@ case class IcebergScanTransformer( return ValidationResult.failed("Delete file format puffin is not supported") } } - // https://github.com/apache/incubator-gluten/issues/11135 + // https://github.com/apache/gluten/issues/11135 if (metadata.propertyAsBoolean(TableProperties.SPARK_WRITE_ACCEPT_ANY_SCHEMA, false)) { return ValidationResult.failed("Not support read the file with accept any schema") } diff --git a/gluten-ras/common/src/main/scala/org/apache/gluten/ras/Ras.scala b/gluten-ras/common/src/main/scala/org/apache/gluten/ras/Ras.scala index ad02e0b5f8c1..b222b7180cd0 100644 --- a/gluten-ras/common/src/main/scala/org/apache/gluten/ras/Ras.scala +++ b/gluten-ras/common/src/main/scala/org/apache/gluten/ras/Ras.scala @@ -22,7 +22,7 @@ import org.apache.gluten.ras.rule.{EnforcerRuleFactory, RasRule} /** * Entrypoint of RAS (relational algebra selector) 's search engine. See the basic introduction of - * RAS: https://github.com/apache/incubator-gluten/issues/5057. + * RAS: https://github.com/apache/gluten/issues/5057. */ trait Optimization[T <: AnyRef] { def newPlanner(plan: T, constraintSet: PropertySet[T]): RasPlanner[T] diff --git a/gluten-substrait/src/main/scala/org/apache/gluten/backendsapi/SubstraitBackend.scala b/gluten-substrait/src/main/scala/org/apache/gluten/backendsapi/SubstraitBackend.scala index f8fc12228b74..94d2738b6196 100644 --- a/gluten-substrait/src/main/scala/org/apache/gluten/backendsapi/SubstraitBackend.scala +++ b/gluten-substrait/src/main/scala/org/apache/gluten/backendsapi/SubstraitBackend.scala @@ -93,7 +93,7 @@ trait SubstraitBackend extends Backend with Logging { object SubstraitBackend extends Logging { - /** Since https://github.com/apache/incubator-gluten/pull/2247. */ + /** Since https://github.com/apache/gluten/pull/2247. */ private def postBuildInfoEvent(sc: SparkContext): Unit = { // export gluten version to property to spark System.setProperty("gluten.version", GlutenBuildInfo.VERSION) @@ -135,7 +135,7 @@ object SubstraitBackend extends Logging { // Disable vanilla columnar readers, to prevent columnar-to-columnar conversions. // FIXME: Do we still need this trick since - // https://github.com/apache/incubator-gluten/pull/1931 was merged? + // https://github.com/apache/gluten/pull/1931 was merged? if (!conf.get(GlutenConfig.VANILLA_VECTORIZED_READERS_ENABLED)) { // FIXME Hongze 22/12/06 // BatchScan.scala in shim was not always loaded by class loader. diff --git a/gluten-substrait/src/main/scala/org/apache/gluten/config/GlutenConfig.scala b/gluten-substrait/src/main/scala/org/apache/gluten/config/GlutenConfig.scala index 63e8794bb500..be818981b48e 100644 --- a/gluten-substrait/src/main/scala/org/apache/gluten/config/GlutenConfig.scala +++ b/gluten-substrait/src/main/scala/org/apache/gluten/config/GlutenConfig.scala @@ -170,7 +170,7 @@ class GlutenConfig(conf: SQLConf) extends GlutenCoreConfig(conf) { .equals("org.apache.spark.shuffle.sort.ColumnarShuffleManager") // Whether to use CelebornShuffleManager. - // TODO: Deprecate the API: https://github.com/apache/incubator-gluten/issues/10107. + // TODO: Deprecate the API: https://github.com/apache/gluten/issues/10107. def isUseCelebornShuffleManager: Boolean = conf .getConfString("spark.shuffle.manager", "sort") diff --git a/gluten-substrait/src/main/scala/org/apache/gluten/execution/ValidatablePlan.scala b/gluten-substrait/src/main/scala/org/apache/gluten/execution/ValidatablePlan.scala index 1df804ebfd59..3a36d5b94267 100644 --- a/gluten-substrait/src/main/scala/org/apache/gluten/execution/ValidatablePlan.scala +++ b/gluten-substrait/src/main/scala/org/apache/gluten/execution/ValidatablePlan.scala @@ -28,7 +28,7 @@ import org.apache.spark.sql.catalyst.analysis.UnresolvedException /** * Base interface for a Gluten query plan that is also open to validation calls. * - * Since https://github.com/apache/incubator-gluten/pull/2185. + * Since https://github.com/apache/gluten/pull/2185. */ trait ValidatablePlan extends GlutenPlan with LogLevelUtil { protected def glutenConf: GlutenConfig = GlutenConfig.get diff --git a/gluten-substrait/src/main/scala/org/apache/gluten/execution/WholeStageTransformer.scala b/gluten-substrait/src/main/scala/org/apache/gluten/execution/WholeStageTransformer.scala index acef5d798ea0..f89b73acf58d 100644 --- a/gluten-substrait/src/main/scala/org/apache/gluten/execution/WholeStageTransformer.scala +++ b/gluten-substrait/src/main/scala/org/apache/gluten/execution/WholeStageTransformer.scala @@ -86,7 +86,7 @@ trait TransformSupport extends ValidatablePlan { */ def columnarInputRDDs: Seq[RDD[ColumnarBatch]] - // Since https://github.com/apache/incubator-gluten/pull/2185. + // Since https://github.com/apache/gluten/pull/2185. protected def doNativeValidation(context: SubstraitContext, node: RelNode): ValidationResult = { if (node != null && enableNativeValidation) { val planNode = PlanBuilder.makePlan(context, Lists.newArrayList(node)) diff --git a/gluten-substrait/src/main/scala/org/apache/gluten/expression/ScalarSubqueryTransformer.scala b/gluten-substrait/src/main/scala/org/apache/gluten/expression/ScalarSubqueryTransformer.scala index a1c6e9b71524..41d9cecbcb90 100644 --- a/gluten-substrait/src/main/scala/org/apache/gluten/expression/ScalarSubqueryTransformer.scala +++ b/gluten-substrait/src/main/scala/org/apache/gluten/expression/ScalarSubqueryTransformer.scala @@ -32,7 +32,7 @@ case class ScalarSubqueryTransformer(substraitExprName: String, query: ScalarSub if (TransformerState.underValidationState) { return ExpressionBuilder.makeLiteral(null, query.dataType, true) } - // After https://github.com/apache/incubator-gluten/pull/5862, we do not need to execute + // After https://github.com/apache/gluten/pull/5862, we do not need to execute // subquery manually so the exception behavior is same with vanilla Spark. // Note that, this code change is just for simplify. The subquery has already been materialized // before doing transform. diff --git a/gluten-substrait/src/main/scala/org/apache/gluten/extension/columnar/LoggedRule.scala b/gluten-substrait/src/main/scala/org/apache/gluten/extension/columnar/LoggedRule.scala index 8aa68c4ad13e..ada8cf7e7d50 100644 --- a/gluten-substrait/src/main/scala/org/apache/gluten/extension/columnar/LoggedRule.scala +++ b/gluten-substrait/src/main/scala/org/apache/gluten/extension/columnar/LoggedRule.scala @@ -25,7 +25,7 @@ import org.apache.spark.sql.catalyst.rules.Rule import org.apache.spark.sql.catalyst.util.sideBySide import org.apache.spark.sql.execution.SparkPlan -/** Since https://github.com/apache/incubator-gluten/pull/7606. */ +/** Since https://github.com/apache/gluten/pull/7606. */ class LoggedRule(delegate: Rule[SparkPlan]) extends Rule[SparkPlan] with Logging with LogLevelUtil { override val ruleName: String = delegate.ruleName diff --git a/gluten-substrait/src/main/scala/org/apache/gluten/extension/columnar/MiscColumnarRules.scala b/gluten-substrait/src/main/scala/org/apache/gluten/extension/columnar/MiscColumnarRules.scala index cb248b7add11..ca63bab6fbd2 100644 --- a/gluten-substrait/src/main/scala/org/apache/gluten/extension/columnar/MiscColumnarRules.scala +++ b/gluten-substrait/src/main/scala/org/apache/gluten/extension/columnar/MiscColumnarRules.scala @@ -47,7 +47,7 @@ object MiscColumnarRules { override def apply(plan: SparkPlan): SparkPlan = { val out = plan.transformWithSubqueries { case p => - // Since https://github.com/apache/incubator-gluten/pull/1851. + // Since https://github.com/apache/gluten/pull/1851. // // When AQE is on, the AQE sub-query cache should already be filled with // row-based SubqueryBroadcastExec for reusing. Thus we are doing the same diff --git a/gluten-substrait/src/main/scala/org/apache/gluten/extension/columnar/PruneNestedColumnsInHiveTableScan.scala b/gluten-substrait/src/main/scala/org/apache/gluten/extension/columnar/PruneNestedColumnsInHiveTableScan.scala index b8972b6d0e2c..ec24f1048763 100644 --- a/gluten-substrait/src/main/scala/org/apache/gluten/extension/columnar/PruneNestedColumnsInHiveTableScan.scala +++ b/gluten-substrait/src/main/scala/org/apache/gluten/extension/columnar/PruneNestedColumnsInHiveTableScan.scala @@ -22,7 +22,7 @@ import org.apache.spark.sql.catalyst.rules.Rule import org.apache.spark.sql.execution.SparkPlan import org.apache.spark.sql.hive.HiveTableScanNestedColumnPruning -// Since https://github.com/apache/incubator-gluten/pull/7268. +// Since https://github.com/apache/gluten/pull/7268. // Used only by CH backend as of now. object PruneNestedColumnsInHiveTableScan extends Rule[SparkPlan] { override def apply(plan: SparkPlan): SparkPlan = plan.transformUp { diff --git a/gluten-substrait/src/main/scala/org/apache/gluten/extension/columnar/enumerated/RasOffload.scala b/gluten-substrait/src/main/scala/org/apache/gluten/extension/columnar/enumerated/RasOffload.scala index af1fe35f7c18..6c4e56a19df1 100644 --- a/gluten-substrait/src/main/scala/org/apache/gluten/extension/columnar/enumerated/RasOffload.scala +++ b/gluten-substrait/src/main/scala/org/apache/gluten/extension/columnar/enumerated/RasOffload.scala @@ -110,7 +110,7 @@ object RasOffload { } catch { case e: Exception => // TODO: Remove this catch block - // See https://github.com/apache/incubator-gluten/issues/7766 + // See https://github.com/apache/gluten/issues/7766 logWarning( s"Exception thrown during rewriting the plan ${node.nodeName}. Skip offloading it", e) diff --git a/gluten-substrait/src/main/scala/org/apache/spark/sql/execution/ColumnarWriteFilesExec.scala b/gluten-substrait/src/main/scala/org/apache/spark/sql/execution/ColumnarWriteFilesExec.scala index 998f4f86b50b..5e5d269cc333 100644 --- a/gluten-substrait/src/main/scala/org/apache/spark/sql/execution/ColumnarWriteFilesExec.scala +++ b/gluten-substrait/src/main/scala/org/apache/spark/sql/execution/ColumnarWriteFilesExec.scala @@ -67,7 +67,7 @@ abstract class ColumnarWriteFilesExec protected ( * processing or columnar processing. It's true because Spark only calls `doExecuteWrite` of the * object. * - * Since https://github.com/apache/incubator-gluten/pull/6745. + * Since https://github.com/apache/gluten/pull/6745. */ override def batchType(): Convention.BatchType = BackendsApiManager.getSettings.primaryBatchType override def rowType0(): RowType = { diff --git a/gluten-substrait/src/main/scala/org/apache/spark/util/SparkPlanRules.scala b/gluten-substrait/src/main/scala/org/apache/spark/util/SparkPlanRules.scala index bbaee81a5987..2e27ae0b758c 100644 --- a/gluten-substrait/src/main/scala/org/apache/spark/util/SparkPlanRules.scala +++ b/gluten-substrait/src/main/scala/org/apache/spark/util/SparkPlanRules.scala @@ -22,7 +22,7 @@ import org.apache.spark.sql.catalyst.rules.Rule import org.apache.spark.sql.execution.SparkPlan object SparkPlanRules extends Logging { - // Since https://github.com/apache/incubator-gluten/pull/1523 + // Since https://github.com/apache/gluten/pull/1523 def extendedColumnarRule(ruleNamesStr: String): SparkSession => Rule[SparkPlan] = (session: SparkSession) => { val ruleNames = ruleNamesStr.split(",").filter(_.nonEmpty) diff --git a/gluten-ut/spark32/src/test/scala/org/apache/gluten/utils/clickhouse/ClickHouseTestSettings.scala b/gluten-ut/spark32/src/test/scala/org/apache/gluten/utils/clickhouse/ClickHouseTestSettings.scala index dc44facd7ef9..0f9cae024309 100644 --- a/gluten-ut/spark32/src/test/scala/org/apache/gluten/utils/clickhouse/ClickHouseTestSettings.scala +++ b/gluten-ut/spark32/src/test/scala/org/apache/gluten/utils/clickhouse/ClickHouseTestSettings.scala @@ -729,7 +729,7 @@ class ClickHouseTestSettings extends BackendTestSettings { .exclude("DATE_FROM_UNIX_DATE") .exclude("UNIX_SECONDS") .exclude("TIMESTAMP_SECONDS") // refer to https://github.com/ClickHouse/ClickHouse/issues/69280 - .exclude("TIMESTAMP_MICROS") // refer to https://github.com/apache/incubator-gluten/issues/7127 + .exclude("TIMESTAMP_MICROS") // refer to https://github.com/apache/gluten/issues/7127 .exclude("SPARK-33498: GetTimestamp,UnixTimestamp,ToUnixTimestamp with parseError") .exclude("SPARK-34739,SPARK-35889: add a year-month interval to a timestamp") .exclude("SPARK-34761,SPARK-35889: add a day-time interval to a timestamp") @@ -880,7 +880,7 @@ class ClickHouseTestSettings extends BackendTestSettings { .exclude("REPEAT") .exclude("ParseUrl") .exclude("SPARK-33468: ParseUrl in ANSI mode should fail if input string is not a valid url") - .exclude("FORMAT") // refer https://github.com/apache/incubator-gluten/issues/6765 + .exclude("FORMAT") // refer https://github.com/apache/gluten/issues/6765 .exclude( "soundex unit test" ) // CH and spark returns different results when input non-ASCII characters diff --git a/gluten-ut/spark32/src/test/scala/org/apache/gluten/utils/velox/VeloxTestSettings.scala b/gluten-ut/spark32/src/test/scala/org/apache/gluten/utils/velox/VeloxTestSettings.scala index 48315d2697ea..001516de624d 100644 --- a/gluten-ut/spark32/src/test/scala/org/apache/gluten/utils/velox/VeloxTestSettings.scala +++ b/gluten-ut/spark32/src/test/scala/org/apache/gluten/utils/velox/VeloxTestSettings.scala @@ -357,9 +357,9 @@ class VeloxTestSettings extends BackendTestSettings { // Not useful and time consuming. .exclude("SPARK-33084: Add jar support Ivy URI in SQL") .exclude("SPARK-33084: Add jar support Ivy URI in SQL -- jar contains udf class") - // https://github.com/apache/incubator-gluten/pull/9145. + // https://github.com/apache/gluten/pull/9145. .exclude("SPARK-17515: CollectLimit.execute() should perform per-partition limits") - // https://github.com/apache/incubator-gluten/pull/9145. + // https://github.com/apache/gluten/pull/9145. .exclude("SPARK-19650: An action on a Command should not trigger a Spark job") enableSuite[GlutenDatasetAggregatorSuite] enableSuite[GlutenDatasetOptimizationSuite] @@ -369,9 +369,9 @@ class VeloxTestSettings extends BackendTestSettings { .exclude("dropDuplicates: columns with same column name") .exclude("groupBy.as") enableSuite[GlutenJsonExpressionsSuite] - // https://github.com/apache/incubator-gluten/issues/8102 + // https://github.com/apache/gluten/issues/8102 .exclude("$.store.book") - // https://github.com/apache/incubator-gluten/issues/10948 + // https://github.com/apache/gluten/issues/10948 .exclude("$['key with spaces']") .exclude("$") .exclude("$.store.book[0]") @@ -415,7 +415,7 @@ class VeloxTestSettings extends BackendTestSettings { .exclude("File source v2: support passing data filters to FileScan without partitionFilters") // DISABLED: GLUTEN-4893 Vanilla UT checks scan operator by exactly matching the class type .exclude("File source v2: support partition pruning") - // https://github.com/apache/incubator-gluten/pull/9145. + // https://github.com/apache/gluten/pull/9145. .excludeGlutenTest("SPARK-25237 compute correct input metrics in FileScanRDD") enableSuite[GlutenEnsureRequirementsSuite] // Rewrite to change the shuffle partitions for optimizing repartition @@ -640,7 +640,7 @@ class VeloxTestSettings extends BackendTestSettings { .exclude("SPARK-17091: Convert IN predicate to Parquet filter push-down") .exclude("Support Parquet column index") .exclude("SPARK-34562: Bloom filter push down") - // https://github.com/apache/incubator-gluten/issues/7174 + // https://github.com/apache/gluten/issues/7174 .excludeGlutenTest("Filter applied on merged Parquet schema with new column should work") enableSuite[GlutenParquetInteroperabilitySuite] .exclude("parquet timestamp conversion") diff --git a/gluten-ut/spark32/src/test/scala/org/apache/spark/sql/catalyst/expressions/GlutenMathExpressionsSuite.scala b/gluten-ut/spark32/src/test/scala/org/apache/spark/sql/catalyst/expressions/GlutenMathExpressionsSuite.scala index 1f343e1bbffc..7d5ca0c23676 100644 --- a/gluten-ut/spark32/src/test/scala/org/apache/spark/sql/catalyst/expressions/GlutenMathExpressionsSuite.scala +++ b/gluten-ut/spark32/src/test/scala/org/apache/spark/sql/catalyst/expressions/GlutenMathExpressionsSuite.scala @@ -126,7 +126,7 @@ class GlutenMathExpressionsSuite extends MathExpressionsSuite with GlutenTestsTr checkEvaluation(Round(12345.67890123456789, 6), 12345.678901) checkEvaluation(Round(44, -1), 40) checkEvaluation(Round(78, 1), 78) - // Enable the test after fixing https://github.com/apache/incubator-gluten/issues/6827 + // Enable the test after fixing https://github.com/apache/gluten/issues/6827 // checkEvaluation(Round(0.5549999999999999, 2), 0.55) checkEvaluation(BRound(2.5, 0), 2.0) checkEvaluation(BRound(3.5, 0), 4.0) diff --git a/gluten-ut/spark33/src/test/scala/org/apache/gluten/utils/clickhouse/ClickHouseTestSettings.scala b/gluten-ut/spark33/src/test/scala/org/apache/gluten/utils/clickhouse/ClickHouseTestSettings.scala index c6bb67748e9b..2ba48f9e546c 100644 --- a/gluten-ut/spark33/src/test/scala/org/apache/gluten/utils/clickhouse/ClickHouseTestSettings.scala +++ b/gluten-ut/spark33/src/test/scala/org/apache/gluten/utils/clickhouse/ClickHouseTestSettings.scala @@ -399,7 +399,7 @@ class ClickHouseTestSettings extends BackendTestSettings { enableSuite[GlutenJsonExpressionsSuite] .exclude( "$.store.basket[0][*].b" - ) // issue: https://github.com/apache/incubator-gluten/issues/8529 + ) // issue: https://github.com/apache/gluten/issues/8529 .exclude("from_json - invalid data") .exclude("from_json - input=object, schema=array, output=array of single row") .exclude("from_json - input=empty object, schema=array, output=array of single row with null") @@ -749,7 +749,7 @@ class ClickHouseTestSettings extends BackendTestSettings { .exclude("DATE_FROM_UNIX_DATE") .exclude("UNIX_SECONDS") .exclude("TIMESTAMP_SECONDS") // refer to https://github.com/ClickHouse/ClickHouse/issues/69280 - .exclude("TIMESTAMP_MICROS") // refer to https://github.com/apache/incubator-gluten/issues/7127 + .exclude("TIMESTAMP_MICROS") // refer to https://github.com/apache/gluten/issues/7127 .exclude("SPARK-33498: GetTimestamp,UnixTimestamp,ToUnixTimestamp with parseError") .exclude("SPARK-34739,SPARK-35889: add a year-month interval to a timestamp") .exclude("SPARK-34761,SPARK-35889: add a day-time interval to a timestamp") @@ -797,9 +797,9 @@ class ClickHouseTestSettings extends BackendTestSettings { .exclude("default") .exclude("SPARK-37967: Literal.create support ObjectType") enableSuite[GlutenMathExpressionsSuite] - .exclude("unhex") // https://github.com/apache/incubator-gluten/issues/7232 - .exclude("round/bround/floor/ceil") // https://github.com/apache/incubator-gluten/issues/7233 - .exclude("atan2") // https://github.com/apache/incubator-gluten/issues/7233 + .exclude("unhex") // https://github.com/apache/gluten/issues/7232 + .exclude("round/bround/floor/ceil") // https://github.com/apache/gluten/issues/7233 + .exclude("atan2") // https://github.com/apache/gluten/issues/7233 enableSuite[GlutenMiscExpressionsSuite] enableSuite[GlutenNondeterministicSuite] .exclude("MonotonicallyIncreasingID") @@ -856,7 +856,7 @@ class ClickHouseTestSettings extends BackendTestSettings { .exclude("REPEAT") .exclude("ParseUrl") .exclude("SPARK-33468: ParseUrl in ANSI mode should fail if input string is not a valid url") - .exclude("FORMAT") // refer https://github.com/apache/incubator-gluten/issues/6765 + .exclude("FORMAT") // refer https://github.com/apache/gluten/issues/6765 .exclude( "soundex unit test" ) // CH and spark returns different results when input non-ASCII characters diff --git a/gluten-ut/spark33/src/test/scala/org/apache/gluten/utils/velox/VeloxTestSettings.scala b/gluten-ut/spark33/src/test/scala/org/apache/gluten/utils/velox/VeloxTestSettings.scala index 4a850690d336..9c51dee8a6f3 100644 --- a/gluten-ut/spark33/src/test/scala/org/apache/gluten/utils/velox/VeloxTestSettings.scala +++ b/gluten-ut/spark33/src/test/scala/org/apache/gluten/utils/velox/VeloxTestSettings.scala @@ -153,9 +153,9 @@ class VeloxTestSettings extends BackendTestSettings { enableSuite[GlutenGeneratorExpressionSuite] enableSuite[GlutenIntervalExpressionsSuite] enableSuite[GlutenJsonExpressionsSuite] - // https://github.com/apache/incubator-gluten/issues/8102 + // https://github.com/apache/gluten/issues/8102 .exclude("$.store.book") - // https://github.com/apache/incubator-gluten/issues/10948 + // https://github.com/apache/gluten/issues/10948 .exclude("$['key with spaces']") .exclude("$") .exclude("$.store.book[0]") @@ -803,7 +803,7 @@ class VeloxTestSettings extends BackendTestSettings { .exclude("File source v2: support passing data filters to FileScan without partitionFilters") // DISABLED: GLUTEN-4893 Vanilla UT checks scan operator by exactly matching the class type .exclude("File source v2: support partition pruning") - // https://github.com/apache/incubator-gluten/pull/9145. + // https://github.com/apache/gluten/pull/9145. .excludeGlutenTest("SPARK-25237 compute correct input metrics in FileScanRDD") enableSuite[GlutenFileScanSuite] enableSuite[GlutenGeneratorFunctionSuite] @@ -845,9 +845,9 @@ class VeloxTestSettings extends BackendTestSettings { // Not useful and time consuming. .exclude("SPARK-33084: Add jar support Ivy URI in SQL") .exclude("SPARK-33084: Add jar support Ivy URI in SQL -- jar contains udf class") - // https://github.com/apache/incubator-gluten/pull/9145. + // https://github.com/apache/gluten/pull/9145. .exclude("SPARK-17515: CollectLimit.execute() should perform per-partition limits") - // https://github.com/apache/incubator-gluten/pull/9145. + // https://github.com/apache/gluten/pull/9145. .exclude("SPARK-19650: An action on a Command should not trigger a Spark job") enableSuite[GlutenSQLQueryTestSuite] enableSuite[GlutenStatisticsCollectionSuite] diff --git a/gluten-ut/spark33/src/test/scala/org/apache/spark/sql/catalyst/expressions/GlutenMathExpressionsSuite.scala b/gluten-ut/spark33/src/test/scala/org/apache/spark/sql/catalyst/expressions/GlutenMathExpressionsSuite.scala index e4c59095eea0..a256b80ef25b 100644 --- a/gluten-ut/spark33/src/test/scala/org/apache/spark/sql/catalyst/expressions/GlutenMathExpressionsSuite.scala +++ b/gluten-ut/spark33/src/test/scala/org/apache/spark/sql/catalyst/expressions/GlutenMathExpressionsSuite.scala @@ -285,7 +285,7 @@ class GlutenMathExpressionsSuite extends MathExpressionsSuite with GlutenTestsTr checkEvaluation(Round(1.12345678901234567, 8), 1.12345679) checkEvaluation(Round(-0.98765432109876543, 5), -0.98765) checkEvaluation(Round(12345.67890123456789, 6), 12345.678901) - // Enable the test after fixing https://github.com/apache/incubator-gluten/issues/6827 + // Enable the test after fixing https://github.com/apache/gluten/issues/6827 // checkEvaluation(Round(0.5549999999999999, 2), 0.55) checkEvaluation(Round(-35, -1), -40) checkEvaluation(Round(44, -1), 40) diff --git a/gluten-ut/spark34/src/test/scala/org/apache/gluten/utils/clickhouse/ClickHouseTestSettings.scala b/gluten-ut/spark34/src/test/scala/org/apache/gluten/utils/clickhouse/ClickHouseTestSettings.scala index 71b621081746..a2f6499e27b6 100644 --- a/gluten-ut/spark34/src/test/scala/org/apache/gluten/utils/clickhouse/ClickHouseTestSettings.scala +++ b/gluten-ut/spark34/src/test/scala/org/apache/gluten/utils/clickhouse/ClickHouseTestSettings.scala @@ -647,7 +647,7 @@ class ClickHouseTestSettings extends BackendTestSettings { .exclude("DATE_FROM_UNIX_DATE") .exclude("UNIX_SECONDS") .exclude("TIMESTAMP_SECONDS") // refer to https://github.com/ClickHouse/ClickHouse/issues/69280 - .exclude("TIMESTAMP_MICROS") // refer to https://github.com/apache/incubator-gluten/issues/7127 + .exclude("TIMESTAMP_MICROS") // refer to https://github.com/apache/gluten/issues/7127 .exclude("SPARK-33498: GetTimestamp,UnixTimestamp,ToUnixTimestamp with parseError") .exclude("SPARK-34739,SPARK-35889: add a year-month interval to a timestamp") .exclude("SPARK-34761,SPARK-35889: add a day-time interval to a timestamp") @@ -791,7 +791,7 @@ class ClickHouseTestSettings extends BackendTestSettings { .exclude("REPEAT") .exclude("ParseUrl") .exclude("SPARK-33468: ParseUrl in ANSI mode should fail if input string is not a valid url") - .exclude("FORMAT") // refer https://github.com/apache/incubator-gluten/issues/6765 + .exclude("FORMAT") // refer https://github.com/apache/gluten/issues/6765 .exclude( "soundex unit test" ) // CH and spark returns different results when input non-ASCII characters diff --git a/gluten-ut/spark34/src/test/scala/org/apache/gluten/utils/velox/VeloxTestSettings.scala b/gluten-ut/spark34/src/test/scala/org/apache/gluten/utils/velox/VeloxTestSettings.scala index 87d085ec510d..9ff2ce221ea6 100644 --- a/gluten-ut/spark34/src/test/scala/org/apache/gluten/utils/velox/VeloxTestSettings.scala +++ b/gluten-ut/spark34/src/test/scala/org/apache/gluten/utils/velox/VeloxTestSettings.scala @@ -151,9 +151,9 @@ class VeloxTestSettings extends BackendTestSettings { enableSuite[GlutenHigherOrderFunctionsSuite] enableSuite[GlutenIntervalExpressionsSuite] enableSuite[GlutenJsonExpressionsSuite] - // https://github.com/apache/incubator-gluten/issues/8102 + // https://github.com/apache/gluten/issues/8102 .exclude("$.store.book") - // https://github.com/apache/incubator-gluten/issues/10948 + // https://github.com/apache/gluten/issues/10948 .exclude("$['key with spaces']") .exclude("$") .exclude("$.store.book[0]") diff --git a/gluten-ut/spark34/src/test/scala/org/apache/spark/sql/catalyst/expressions/GlutenMathExpressionsSuite.scala b/gluten-ut/spark34/src/test/scala/org/apache/spark/sql/catalyst/expressions/GlutenMathExpressionsSuite.scala index 826176334c1c..c755a475ed5a 100644 --- a/gluten-ut/spark34/src/test/scala/org/apache/spark/sql/catalyst/expressions/GlutenMathExpressionsSuite.scala +++ b/gluten-ut/spark34/src/test/scala/org/apache/spark/sql/catalyst/expressions/GlutenMathExpressionsSuite.scala @@ -250,7 +250,7 @@ class GlutenMathExpressionsSuite extends MathExpressionsSuite with GlutenTestsTr checkEvaluation(BRound(-3.5, 0), -4.0) checkEvaluation(BRound(-0.35, 1), -0.4) checkEvaluation(BRound(-35, -1), -40) - // Enable the test after fixing https://github.com/apache/incubator-gluten/issues/6827 + // Enable the test after fixing https://github.com/apache/gluten/issues/6827 // checkEvaluation(Round(0.5549999999999999, 2), 0.55) checkEvaluation(BRound(BigDecimal("45.00"), -1), BigDecimal(40)) checkEvaluation(checkDataTypeAndCast(RoundFloor(Literal(2.5), Literal(0))), Decimal(2)) diff --git a/gluten-ut/spark35/src/test/scala/org/apache/gluten/utils/clickhouse/ClickHouseTestSettings.scala b/gluten-ut/spark35/src/test/scala/org/apache/gluten/utils/clickhouse/ClickHouseTestSettings.scala index 29d7534e8fae..30ee897ab42c 100644 --- a/gluten-ut/spark35/src/test/scala/org/apache/gluten/utils/clickhouse/ClickHouseTestSettings.scala +++ b/gluten-ut/spark35/src/test/scala/org/apache/gluten/utils/clickhouse/ClickHouseTestSettings.scala @@ -1046,7 +1046,7 @@ class ClickHouseTestSettings extends BackendTestSettings { .excludeCH( "SPARK-45882: BroadcastHashJoinExec propagate partitioning should respect CoalescedHashPartitioning") enableSuite[GlutenJsonExpressionsSuite] - // https://github.com/apache/incubator-gluten/issues/8102 + // https://github.com/apache/gluten/issues/8102 .includeCH("$.store.book") .includeCH("$") .includeCH("$.store.book[0]") diff --git a/gluten-ut/spark35/src/test/scala/org/apache/gluten/utils/velox/VeloxTestSettings.scala b/gluten-ut/spark35/src/test/scala/org/apache/gluten/utils/velox/VeloxTestSettings.scala index 1207121da708..121de63a9433 100644 --- a/gluten-ut/spark35/src/test/scala/org/apache/gluten/utils/velox/VeloxTestSettings.scala +++ b/gluten-ut/spark35/src/test/scala/org/apache/gluten/utils/velox/VeloxTestSettings.scala @@ -151,9 +151,9 @@ class VeloxTestSettings extends BackendTestSettings { enableSuite[GlutenHigherOrderFunctionsSuite] enableSuite[GlutenIntervalExpressionsSuite] enableSuite[GlutenJsonExpressionsSuite] - // https://github.com/apache/incubator-gluten/issues/8102 + // https://github.com/apache/gluten/issues/8102 .exclude("$.store.book") - // https://github.com/apache/incubator-gluten/issues/10948 + // https://github.com/apache/gluten/issues/10948 .exclude("$['key with spaces']") .exclude("$") .exclude("$.store.book[0]") diff --git a/gluten-ut/spark35/src/test/scala/org/apache/spark/sql/catalyst/expressions/GlutenMathExpressionsSuite.scala b/gluten-ut/spark35/src/test/scala/org/apache/spark/sql/catalyst/expressions/GlutenMathExpressionsSuite.scala index d49bbd3555eb..b4459df4209b 100644 --- a/gluten-ut/spark35/src/test/scala/org/apache/spark/sql/catalyst/expressions/GlutenMathExpressionsSuite.scala +++ b/gluten-ut/spark35/src/test/scala/org/apache/spark/sql/catalyst/expressions/GlutenMathExpressionsSuite.scala @@ -253,7 +253,7 @@ class GlutenMathExpressionsSuite extends MathExpressionsSuite with GlutenTestsTr checkEvaluation(Round(1.12345678901234567, 8), 1.12345679) checkEvaluation(Round(-0.98765432109876543, 5), -0.98765) checkEvaluation(Round(12345.67890123456789, 6), 12345.678901) - // Enable the test after fixing https://github.com/apache/incubator-gluten/issues/6827 + // Enable the test after fixing https://github.com/apache/gluten/issues/6827 // checkEvaluation(Round(0.5549999999999999, 2), 0.55) checkEvaluation(BRound(BigDecimal("45.00"), -1), BigDecimal(40)) checkEvaluation(checkDataTypeAndCast(RoundFloor(Literal(2.5), Literal(0))), Decimal(2)) diff --git a/gluten-ut/spark40/src/test/scala/org/apache/gluten/utils/clickhouse/ClickHouseTestSettings.scala b/gluten-ut/spark40/src/test/scala/org/apache/gluten/utils/clickhouse/ClickHouseTestSettings.scala index ec99089c324e..5a04389186b2 100644 --- a/gluten-ut/spark40/src/test/scala/org/apache/gluten/utils/clickhouse/ClickHouseTestSettings.scala +++ b/gluten-ut/spark40/src/test/scala/org/apache/gluten/utils/clickhouse/ClickHouseTestSettings.scala @@ -1022,7 +1022,7 @@ class ClickHouseTestSettings extends BackendTestSettings { .excludeCH( "SPARK-45882: BroadcastHashJoinExec propagate partitioning should respect CoalescedHashPartitioning") enableSuite[GlutenJsonExpressionsSuite] - // https://github.com/apache/incubator-gluten/issues/8102 + // https://github.com/apache/gluten/issues/8102 .includeCH("$.store.book") .includeCH("$") .includeCH("$.store.book[0]") diff --git a/gluten-ut/spark40/src/test/scala/org/apache/gluten/utils/velox/VeloxTestSettings.scala b/gluten-ut/spark40/src/test/scala/org/apache/gluten/utils/velox/VeloxTestSettings.scala index 4f7c67daaad6..0f18950da398 100644 --- a/gluten-ut/spark40/src/test/scala/org/apache/gluten/utils/velox/VeloxTestSettings.scala +++ b/gluten-ut/spark40/src/test/scala/org/apache/gluten/utils/velox/VeloxTestSettings.scala @@ -161,9 +161,9 @@ class VeloxTestSettings extends BackendTestSettings { enableSuite[GlutenHigherOrderFunctionsSuite] enableSuite[GlutenIntervalExpressionsSuite] enableSuite[GlutenJsonExpressionsSuite] - // https://github.com/apache/incubator-gluten/issues/10948 + // https://github.com/apache/gluten/issues/10948 .exclude("$['key with spaces']") - // https://github.com/apache/incubator-gluten/issues/8102 + // https://github.com/apache/gluten/issues/8102 .exclude("$.store.book") .exclude("$") .exclude("$.store.book[0]") @@ -623,7 +623,7 @@ class VeloxTestSettings extends BackendTestSettings { // error message mismatch is accepted .exclude("schema mismatch failure error message for parquet reader") .exclude("schema mismatch failure error message for parquet vectorized reader") - // https://github.com/apache/incubator-gluten/issues/11220 + // https://github.com/apache/gluten/issues/11220 .excludeByPrefix("SPARK-40819") .excludeByPrefix("SPARK-46056") // TODO: fix in Spark-4.0 .exclude("CANNOT_MERGE_SCHEMAS: Failed merging schemas") @@ -943,7 +943,7 @@ class VeloxTestSettings extends BackendTestSettings { .exclude("SPARK-41048: Improve output partitioning and ordering with AQE cache") // Rewrite this test since it checks the physical operator which is changed in Gluten .exclude("SPARK-27439: Explain result should match collected result after view change") - // https://github.com/apache/incubator-gluten/issues/11570 + // https://github.com/apache/gluten/issues/11570 .exclude("getRows: binary") enableSuite[GlutenDataFrameTimeWindowingSuite] enableSuite[GlutenDataFrameTungstenSuite] diff --git a/gluten-ut/spark40/src/test/scala/org/apache/spark/sql/catalyst/expressions/GlutenMathExpressionsSuite.scala b/gluten-ut/spark40/src/test/scala/org/apache/spark/sql/catalyst/expressions/GlutenMathExpressionsSuite.scala index d49bbd3555eb..b4459df4209b 100644 --- a/gluten-ut/spark40/src/test/scala/org/apache/spark/sql/catalyst/expressions/GlutenMathExpressionsSuite.scala +++ b/gluten-ut/spark40/src/test/scala/org/apache/spark/sql/catalyst/expressions/GlutenMathExpressionsSuite.scala @@ -253,7 +253,7 @@ class GlutenMathExpressionsSuite extends MathExpressionsSuite with GlutenTestsTr checkEvaluation(Round(1.12345678901234567, 8), 1.12345679) checkEvaluation(Round(-0.98765432109876543, 5), -0.98765) checkEvaluation(Round(12345.67890123456789, 6), 12345.678901) - // Enable the test after fixing https://github.com/apache/incubator-gluten/issues/6827 + // Enable the test after fixing https://github.com/apache/gluten/issues/6827 // checkEvaluation(Round(0.5549999999999999, 2), 0.55) checkEvaluation(BRound(BigDecimal("45.00"), -1), BigDecimal(40)) checkEvaluation(checkDataTypeAndCast(RoundFloor(Literal(2.5), Literal(0))), Decimal(2)) diff --git a/gluten-ut/spark41/src/test/scala/org/apache/gluten/utils/clickhouse/ClickHouseTestSettings.scala b/gluten-ut/spark41/src/test/scala/org/apache/gluten/utils/clickhouse/ClickHouseTestSettings.scala index ec99089c324e..5a04389186b2 100644 --- a/gluten-ut/spark41/src/test/scala/org/apache/gluten/utils/clickhouse/ClickHouseTestSettings.scala +++ b/gluten-ut/spark41/src/test/scala/org/apache/gluten/utils/clickhouse/ClickHouseTestSettings.scala @@ -1022,7 +1022,7 @@ class ClickHouseTestSettings extends BackendTestSettings { .excludeCH( "SPARK-45882: BroadcastHashJoinExec propagate partitioning should respect CoalescedHashPartitioning") enableSuite[GlutenJsonExpressionsSuite] - // https://github.com/apache/incubator-gluten/issues/8102 + // https://github.com/apache/gluten/issues/8102 .includeCH("$.store.book") .includeCH("$") .includeCH("$.store.book[0]") diff --git a/gluten-ut/spark41/src/test/scala/org/apache/gluten/utils/velox/VeloxTestSettings.scala b/gluten-ut/spark41/src/test/scala/org/apache/gluten/utils/velox/VeloxTestSettings.scala index 0dadfa1d0bd8..e8516ce742f2 100644 --- a/gluten-ut/spark41/src/test/scala/org/apache/gluten/utils/velox/VeloxTestSettings.scala +++ b/gluten-ut/spark41/src/test/scala/org/apache/gluten/utils/velox/VeloxTestSettings.scala @@ -169,9 +169,9 @@ class VeloxTestSettings extends BackendTestSettings { enableSuite[GlutenHigherOrderFunctionsSuite] enableSuite[GlutenIntervalExpressionsSuite] enableSuite[GlutenJsonExpressionsSuite] - // https://github.com/apache/incubator-gluten/issues/10948 + // https://github.com/apache/gluten/issues/10948 .exclude("$['key with spaces']") - // https://github.com/apache/incubator-gluten/issues/8102 + // https://github.com/apache/gluten/issues/8102 .exclude("$.store.book") .exclude("$") .exclude("$.store.book[0]") @@ -407,7 +407,7 @@ class VeloxTestSettings extends BackendTestSettings { enableSuite[GlutenV2SessionCatalogTableSuite] enableSuite[GlutenCSVv1Suite] enableSuite[GlutenCSVv2Suite] - // https://github.com/apache/incubator-gluten/issues/11505 + // https://github.com/apache/gluten/issues/11505 enableSuite[GlutenCSVLegacyTimeParserSuite] .exclude("Write timestamps correctly in ISO8601 format by default") .exclude("csv with variant") @@ -584,7 +584,7 @@ class VeloxTestSettings extends BackendTestSettings { // error message mismatch is accepted .exclude("schema mismatch failure error message for parquet reader") .exclude("schema mismatch failure error message for parquet vectorized reader") - // https://github.com/apache/incubator-gluten/issues/11220 + // https://github.com/apache/gluten/issues/11220 .excludeByPrefix("SPARK-40819") .excludeByPrefix("SPARK-46056") // TODO: fix in Spark-4.0 .exclude("CANNOT_MERGE_SCHEMAS: Failed merging schemas") @@ -913,7 +913,7 @@ class VeloxTestSettings extends BackendTestSettings { .exclude("SPARK-41048: Improve output partitioning and ordering with AQE cache") // Rewrite this test since it checks the physical operator which is changed in Gluten .exclude("SPARK-27439: Explain result should match collected result after view change") - // https://github.com/apache/incubator-gluten/issues/11570 + // https://github.com/apache/gluten/issues/11570 .exclude("getRows: binary") enableSuite[GlutenDataFrameTimeWindowingSuite] enableSuite[GlutenDataFrameTungstenSuite] diff --git a/gluten-ut/spark41/src/test/scala/org/apache/spark/sql/catalyst/expressions/GlutenMathExpressionsSuite.scala b/gluten-ut/spark41/src/test/scala/org/apache/spark/sql/catalyst/expressions/GlutenMathExpressionsSuite.scala index d49bbd3555eb..b4459df4209b 100644 --- a/gluten-ut/spark41/src/test/scala/org/apache/spark/sql/catalyst/expressions/GlutenMathExpressionsSuite.scala +++ b/gluten-ut/spark41/src/test/scala/org/apache/spark/sql/catalyst/expressions/GlutenMathExpressionsSuite.scala @@ -253,7 +253,7 @@ class GlutenMathExpressionsSuite extends MathExpressionsSuite with GlutenTestsTr checkEvaluation(Round(1.12345678901234567, 8), 1.12345679) checkEvaluation(Round(-0.98765432109876543, 5), -0.98765) checkEvaluation(Round(12345.67890123456789, 6), 12345.678901) - // Enable the test after fixing https://github.com/apache/incubator-gluten/issues/6827 + // Enable the test after fixing https://github.com/apache/gluten/issues/6827 // checkEvaluation(Round(0.5549999999999999, 2), 0.55) checkEvaluation(BRound(BigDecimal("45.00"), -1), BigDecimal(40)) checkEvaluation(checkDataTypeAndCast(RoundFloor(Literal(2.5), Literal(0))), Decimal(2)) diff --git a/mkdocs.yml b/mkdocs.yml index 1c03a1ce600a..4ba589908f76 100644 --- a/mkdocs.yml +++ b/mkdocs.yml @@ -15,7 +15,7 @@ site_name: Gluten repo_name: 'Fork on GitHub ' -repo_url: "https://github.com/apache/incubator-gluten.git" +repo_url: "https://github.com/apache/gluten.git" edit_uri: "" diff --git a/pom.xml b/pom.xml index df2c3a1a8eb4..4637a9e77781 100644 --- a/pom.xml +++ b/pom.xml @@ -29,7 +29,7 @@ Gluten Parent Pom Apache Gluten - https://github.com/apache/incubator-gluten.git + https://github.com/apache/gluten.git Apache Software Foundation @@ -53,9 +53,9 @@ - scm:git:git://github.com/apache/incubator-gluten.git - scm:git:ssh://github.com:apache/incubator-gluten.git - https://github.com/apache/incubator-gluten/tree/main + scm:git:git://github.com/apache/gluten.git + scm:git:ssh://github.com:apache/gluten.git + https://github.com/apache/gluten/tree/main diff --git a/shims/common/src/main/scala/org/apache/gluten/GlutenBuildInfo.scala b/shims/common/src/main/scala/org/apache/gluten/GlutenBuildInfo.scala index 623e924dffa5..f96920103933 100644 --- a/shims/common/src/main/scala/org/apache/gluten/GlutenBuildInfo.scala +++ b/shims/common/src/main/scala/org/apache/gluten/GlutenBuildInfo.scala @@ -20,7 +20,7 @@ import java.util.Properties import scala.util.Try -/** Since https://github.com/apache/incubator-gluten/pull/1973. */ +/** Since https://github.com/apache/gluten/pull/1973. */ object GlutenBuildInfo { private val buildFile = "gluten-build-info.properties" private val buildFileStream = diff --git a/shims/common/src/main/scala/org/apache/gluten/execution/BatchCarrierRow.scala b/shims/common/src/main/scala/org/apache/gluten/execution/BatchCarrierRow.scala index f4fb69586e83..443a1ca9e531 100644 --- a/shims/common/src/main/scala/org/apache/gluten/execution/BatchCarrierRow.scala +++ b/shims/common/src/main/scala/org/apache/gluten/execution/BatchCarrierRow.scala @@ -96,7 +96,7 @@ object BatchCarrierRow { * A [[BatchCarrierRow]] implementation that is backed by a * [[org.apache.spark.sql.vectorized.ColumnarBatch]]. * - * Serialization code originated since https://github.com/apache/incubator-gluten/issues/9270. + * Serialization code originated since https://github.com/apache/gluten/issues/9270. */ abstract class TerminalRow extends BatchCarrierRow { def batch(): ColumnarBatch diff --git a/tools/gluten-it/README.md b/tools/gluten-it/README.md index a1f7ccc8919f..745c8523a36b 100644 --- a/tools/gluten-it/README.md +++ b/tools/gluten-it/README.md @@ -6,13 +6,13 @@ The project makes it easy to test Gluten build locally. Gluten is a native Spark SQL implementation as a standard Spark plug-in. -https://github.com/apache/incubator-gluten +https://github.com/apache/gluten ## Getting Started ### 1. Build Gluten -See official Gluten build guidance https://github.com/apache/incubator-gluten#build-from-source. +See official Gluten build guidance https://github.com/apache/gluten#build-from-source. ### 2. Build and run gluten-it diff --git a/tools/gluten-te/centos/defaults.conf b/tools/gluten-te/centos/defaults.conf index c39b396ba446..b1338a6df3a1 100755 --- a/tools/gluten-te/centos/defaults.conf +++ b/tools/gluten-te/centos/defaults.conf @@ -11,7 +11,7 @@ DEFAULT_NON_INTERACTIVE=OFF DEFAULT_PRESERVE_CONTAINER=OFF # The codes will be used in build -DEFAULT_GLUTEN_REPO=https://github.com/apache/incubator-gluten.git +DEFAULT_GLUTEN_REPO=https://github.com/apache/gluten.git DEFAULT_GLUTEN_BRANCH=main # Create debug build diff --git a/tools/gluten-te/ubuntu/README.md b/tools/gluten-te/ubuntu/README.md index f617d8368675..d293ed1af601 100644 --- a/tools/gluten-te/ubuntu/README.md +++ b/tools/gluten-te/ubuntu/README.md @@ -1,6 +1,6 @@ # Portable Test Environment of Gluten (gluten-te) -Build and run [gluten](https://github.com/apache/incubator-gluten) and [gluten-it](https://github.com/apache/incubator-gluten/tree/main/tools/gluten-it) in a portable docker container, from scratch. +Build and run [gluten](https://github.com/apache/gluten) and [gluten-it](https://github.com/apache/gluten/tree/main/tools/gluten-it) in a portable docker container, from scratch. # Prerequisites @@ -9,7 +9,7 @@ Only Linux and MacOS are currently supported. Before running the scripts, make s # Getting Started (Build Gluten code, Velox backend) ```sh -git clone -b main https://github.com/apache/incubator-gluten.git gluten # Gluten main code +git clone -b main https://github.com/apache/gluten.git gluten # Gluten main code export HTTP_PROXY_HOST=myproxy.example.com # in case you are behind http proxy export HTTP_PROXY_PORT=55555 # in case you are behind http proxy @@ -21,7 +21,7 @@ tools/gluten-te/ubuntu/examples/buildhere-veloxbe/run.sh # Getting Started (TPC, Velox backend) ```sh -git clone -b main https://github.com/apache/incubator-gluten.git gluten # Gluten main code +git clone -b main https://github.com/apache/gluten.git gluten # Gluten main code export HTTP_PROXY_HOST=myproxy.example.com # in case you are behind http proxy export HTTP_PROXY_PORT=55555 # in case you are behind http proxy @@ -32,7 +32,7 @@ cd gluten/gluten-te # Configurations -See the [config file](https://github.com/apache/incubator-gluten/blob/main/tools/gluten-te/ubuntu/defaults.conf). You can modify the file to configure gluten-te, or pass env variables during running the scripts. +See the [config file](https://github.com/apache/gluten/blob/main/tools/gluten-te/ubuntu/defaults.conf). You can modify the file to configure gluten-te, or pass env variables during running the scripts. # Example Usages diff --git a/tools/gluten-te/ubuntu/defaults.conf b/tools/gluten-te/ubuntu/defaults.conf index 393b23a4736e..c4f3c7649761 100644 --- a/tools/gluten-te/ubuntu/defaults.conf +++ b/tools/gluten-te/ubuntu/defaults.conf @@ -11,7 +11,7 @@ DEFAULT_NON_INTERACTIVE=OFF DEFAULT_PRESERVE_CONTAINER=OFF # The codes will be used in build -DEFAULT_GLUTEN_REPO=https://github.com/apache/incubator-gluten.git +DEFAULT_GLUTEN_REPO=https://github.com/apache/gluten.git DEFAULT_GLUTEN_BRANCH=main # Create debug build diff --git a/tools/workload/benchmark_velox/analysis/sparklog.ipynb b/tools/workload/benchmark_velox/analysis/sparklog.ipynb index fe671a3d6f8c..e878bd9dec7c 100644 --- a/tools/workload/benchmark_velox/analysis/sparklog.ipynb +++ b/tools/workload/benchmark_velox/analysis/sparklog.ipynb @@ -5912,7 +5912,7 @@ " \n", " pr_link=''\n", " if pr:\n", - " pr_link=f'https://github.com/apache/incubator-gluten/pull/{pr}'\n", + " pr_link=f'https://github.com/apache/gluten/pull/{pr}'\n", " title=!wget --quiet -O - $pr_link | sed -n -e 's!.*\\(.*\\).*!\\1!p'\n", " if not title:\n", " raise Exception(f'Failed to fetch PR link: {pr_link}')\n", diff --git a/tools/workload/benchmark_velox/initialize.ipynb b/tools/workload/benchmark_velox/initialize.ipynb index 2e80ac77c873..1d3e6397b6bc 100644 --- a/tools/workload/benchmark_velox/initialize.ipynb +++ b/tools/workload/benchmark_velox/initialize.ipynb @@ -313,7 +313,7 @@ "\n", "```bash\n", "cd ~\n", - "git clone https://github.com/apache/incubator-gluten.git gluten\n", + "git clone https://github.com/apache/gluten.git gluten\n", "```" ] }, @@ -2229,7 +2229,7 @@ "source": [ "import os\n", "if not os.path.exists('gluten'):\n", - " !git clone https://github.com/apache/incubator-gluten.git gluten" + " !git clone https://github.com/apache/gluten.git gluten" ] }, {