[
{
"path": ".github/CODEOWNERS",
"content": "* @HiveRunner/hiverunner-committers\n"
},
{
"path": ".github/ISSUE_TEMPLATE/bug_report.md",
"content": "---\nname: Bug report\nabout: Create a report to help us improve\n\n---\n\n**Describe the bug**\nA clear and concise description of what the bug is.\n\n**To Reproduce**\nSteps to reproduce the behaviour ideally including the configuration files you are using (feel free to rename any sensitive information like server and table names etc.) \nEven better would be the source code of your unit test or a pull request against the HiveRunner unit tests containing a test that demonstrates the issue.\n\n**Expected behavior**\nA clear and concise description of what you expected to happen.\n\n**Logs**\nPlease add the log output from HiveRunner when the error occurs, full stack traces are especially useful.\n\n**Versions (please complete the following information):**\n - HiveRunner Version: \n - Hive Versions: for whatever version of Hive you are using for your tests\n\n**Additional context**\nAdd any other context about the problem here.\n"
},
{
"path": ".github/ISSUE_TEMPLATE/feature_request.md",
"content": "---\nname: Feature request\nabout: Suggest an idea for this project\n\n---\n\n**Is your feature request related to a problem? Please describe.**\nA clear and concise description of what the problem is. For example - I'm always frustrated when [...]\n\n**Describe the solution you'd like**\nA clear and concise description of what you want to happen.\n\n**Describe alternatives you've considered**\nA clear and concise description of any alternative solutions or features you've considered.\n\n**Additional context**\nAdd any other context or screenshots about the feature request here.\n"
},
{
"path": ".github/workflows/deploy.yml",
"content": "name: Deploy SNAPSHOT\non:\n workflow_dispatch:\n inputs:\n branch:\n description: \"The branch to use to deploy a SNAPSHOT from.\"\n required: true\n default: \"main\"\njobs:\n deploy:\n name: Deploy SNAPSHOT to Sonatype\n runs-on: ubuntu-20.04\n steps:\n - uses: actions/checkout@v2\n with:\n fetch-depth: 0\n ref: ${{ github.event.inputs.branch }}\n - name: Set up JDK\n uses: actions/setup-java@v2\n with:\n distribution: 'adopt'\n java-version: '8'\n # this creates a settings.xml with the following server\n settings-path: ${{ github.workspace }}\n server-id: ossrh # Value of the distributionManagement/repository/id field of the pom.xml\n server-username: SONATYPE_USERNAME # env variable for username in deploy\n server-password: SONATYPE_PASSWORD # env variable for token in deploy \n # only signed artifacts will be released to maven central. this sets up things for the maven-gpg-plugin\n gpg-private-key: ${{ secrets.GPG_PRIVATE_KEY }} # Value of the GPG private key to import\n gpg-passphrase: GPG_PASSPHRASE # env variable for GPG private key passphrase\n \n - name: Run Maven Targets\n run: mvn deploy --settings $GITHUB_WORKSPACE/settings.xml --batch-mode --show-version --no-transfer-progress --activate-profiles oss-release\n env:\n SONATYPE_PASSWORD: ${{ secrets.SONATYPE_PASSWORD }}\n SONATYPE_USERNAME: ${{ secrets.SONATYPE_USERNAME }}\n GPG_PASSPHRASE: ${{ secrets.GPG_PRIVATE_KEY_PASSPHRASE }}\n"
},
{
"path": ".github/workflows/main.yml",
"content": "name: build\n\non: \n pull_request:\n push:\n branches: \n - main\n\njobs:\n test:\n name: Package and run all tests\n runs-on: ubuntu-20.04\n steps:\n - uses: actions/checkout@v2\n with:\n fetch-depth: 0\n - name: Set up JDK\n uses: actions/setup-java@v2\n with:\n distribution: 'adopt'\n java-version: '8'\n - name: Run Maven Targets\n run: mvn package --batch-mode --show-version --no-transfer-progress\n"
},
{
"path": ".github/workflows/release.yml",
"content": "name: Release to Maven Central\non:\n workflow_dispatch:\n inputs:\n branch:\n description: \"The branch to use to release from.\"\n required: true\n default: \"main\"\njobs:\n release:\n name: Release to Maven Central\n runs-on: ubuntu-20.04\n\n steps:\n - name: Checkout source code\n uses: actions/checkout@v2\n with:\n fetch-depth: 0\n ref: ${{ github.event.inputs.branch }}\n\n - name: Set up JDK\n uses: actions/setup-java@v2\n with:\n distribution: 'adopt'\n java-version: '8'\n # this creates a settings.xml with the following server\n settings-path: ${{ github.workspace }}\n server-id: ossrh # Value of the distributionManagement/repository/id field of the pom.xml\n server-username: SONATYPE_USERNAME # env variable for username in deploy\n server-password: SONATYPE_PASSWORD # env variable for token in deploy \n # only signed artifacts will be released to maven central. this sets up things for the maven-gpg-plugin\n gpg-private-key: ${{ secrets.GPG_PRIVATE_KEY }} # Value of the GPG private key to import\n gpg-passphrase: GPG_PASSPHRASE # env variable for GPG private key passphrase\n\n - name: Configure Git User\n run: |\n git config user.email \"actions@github.com\"\n git config user.name \"GitHub Actions\"\n\n - name: Run Maven Targets\n run: mvn release:prepare release:perform --settings $GITHUB_WORKSPACE/settings.xml --activate-profiles oss-release --batch-mode --show-version --no-transfer-progress \n env:\n SONATYPE_PASSWORD: ${{ secrets.SONATYPE_PASSWORD }}\n SONATYPE_USERNAME: ${{ secrets.SONATYPE_USERNAME }}\n GPG_PASSPHRASE: ${{secrets.GPG_PRIVATE_KEY_PASSPHRASE}}\n GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}\n"
},
{
"path": ".gitignore",
"content": "# Project files #\n#################\n*.iml\n*.ipr\n*.iws\nnbactions.xml\n/.idea/\n\n# Compiled source #\n###################\n*.com\n*.class\n*.dll\n*.exe\n*.o\n*.so\n\n# Maven target #\n################\n/target/**\n\n# H2 db files #\n###############\nmem.h2.db\nmem.lock.db\n\n# HSQLDB files #\n################\ntestdb.log\ntestdb.properties\ntestdb.script\n\n# Packages #\n############\n# it's better to unpack these files and commit the raw source\n# git has its own built in compression methods\n*.7z\n*.dmg\n*.gz\n*.iso\n*.jar\n*.rar\n*.tar\n*.zip\n\n# Logs and databases #\n######################\n*.log\n*.sqlite\nmetastore_db\n\n# OS generated files #\n######################\n.DS_Store\n.DS_Store?\n._*\n.Spotlight-V100\n.Trashes\nIcon?\nehthumbs.db\nThumbs.db\n\n# Temporary files #\n###################\n*~\n\n# Eclipse #\n###########\n.classpath\n.project\n.settings/\n\n# IntelliJ #\n############\n.gradle/\n*.eml\n\n# jEnv #\n########\n/.java-version\n\n# Misc #\n########\n/pubring.kbx\n"
},
{
"path": "CHANGELOG.md",
"content": "# Changelog\nAll notable changes to this project will be documented in this file.\n\nThe format is based on [Keep a Changelog](http://keepachangelog.com/en/1.0.0/) and this project adheres to [Semantic Versioning](http://semver.org/spec/v2.0.0.html).\n## [7.0.0] - 2024-11-22\n### Added\n- Added version `6.0.9` of `datanucleus-core`.\n- Added version `6.0.4` of `datanucleus-api-jdo`.\n- Added version `6.0.9` of `datanucleus-rdbms`.\n- Added version `1.3` of `javax.transaction-api`.\n- Added version `6.1.14` of `spring-jdbc`.\n- Added version `10.15.2.0` of `derby`.\n- Added version `10.15.2.0` of `derbytools`.\n- Added version `5.6.2` of `kryo`.\n- Added version `4.9.3` of `antlr4-runtime`.\n- Added version `4.0.1` of `kafka-handler`.\n- Added missing Hive & Datanucleus properties in StandaloneHiveServerContext so now the framework works with a new Hive dependency versions.\n\n### Changed\n- Updated `hadoop-mapreduce-client-common` from `3.1.0` to `3.4.1`.\n- Updated `hadoop-mapreduce-client-core` from `3.1.0` to `3.4.1`.\n- Updated `hadoop-client-runtime` from `3.1.0` to `3.4.1`.\n- Updated `hive-exec` from `3.1.2` to `4.0.1`.\n- Updated `hive-serde` from `3.1.0` to `3.4.1`.\n- Updated `hive-jdbc` from `3.1.0` to `3.4.1`.\n- Updated `hive-contrib` from `3.1.0` to `3.4.1`.\n- Updated `hive-webhcat-java-client` from `3.1.0` to `3.4.1`.\n- Updated `jackson-annotations` from `2.9.5` to `2.18.1`.\n- Updated `reflections` from `0.9.8` to `0.10.2`.\n- Updated `mockito-core` from `3.8.0` to `5.14.2`.\n- Updated `mockito-junit-jupiter` from `3.8.0` to `5.14.2`.\n- Updated `tez-common` from `0.9.1` to `0.10.4`.\n- Updated `tez-mapreduce` from `0.9.1` to `0.10.4`.\n- Updated `junit-jupiter` from `5.7.1` to `5.11.3`.\n- Updated `junit-vintage-engine` from `5.7.1` to `5.11.2`.\n- Updated `maven-surefire-plugin` from `2.22.2` to `3.5.1`.\n- Updated `maven-compiler-plugin` from `3.7.0` to `3.13.0`.\n- Updated `maven-jar-plugin` from `3.2.0` to `3.4.2`.\n- Updated `maven-release-plugin` from `3.0.0-M1` to `3.1.1`.\n- Updated `nexus-staging-maven-plugin` from `1.6.8` to `1.7.0`.\n- Updated `maven-source-plugin` from `3.2.0` to `3.3.1`.\n- Updated `maven-javadoc-plugin` from `3.2.0` to `3.10.1`.\n- Updated `maven-gpg-plugin` from `1.6` to `3.2.7`.\n- Updated `HiveConf` property names in `StandaloneHiveServerContext`\n- Set `METASTORE_VALIDATE_CONSTRAINTS`, `METASTORE_VALIDATE_COLUMNS`, `METASTORE_VALIDATE_TABLES` properties to false in StandaloneHiveServerContext.\n\n### Removed\n- Removed `com.google.common.base.Predicates` in `HiveRunnerExtension`/`StandaloneHiveRunner` as it is no longer used in a new version of `org.reflections:reflections` library.\n\n### Fixed\n- Fixed warning \"org.apache.hadoop.hive.metastore.MetastoreDirectSqlUtils - Failed to execute [select \"FUNCS\".\"FUNC_ID\" from \"FUNCS\" LEFT JOIN \"DBS\" ON \"FUNCS\".\"DB_ID\" = \"DBS\".\"DB_ID\" where \"DBS\".\"CTLG_NAME\" = ? ]...\" is not logged anymore.\n- Fixed `IgnoreClosePrintStream` as NPE was thrown after upgrading to Java >= 11\n- Fixed error \"org.apache.hadoop.hive.ql.exec.tez.DagUtils - Failed to add credential supplier java.lang.ClassNotFoundException: org.apache.hadoop.hive.kafka.KafkaDagCredentialSupplier\"\n\n## [6.1.0] - 2021-04-28\n### Changed\n- Maven Group Id changed from `com.klarna` to `io.github.hiverunner`.\n- Set `HIVE_IN_TEST` to true in `StandaloneHiverServerContext` instead of `StandaloneHiveRunner` so checks for non-existent tables are skipped by both the JUnit4 runner and the JUnit5 extension (this removes a lot of log noise from tests using the latter).\n- Made `HiveRunnerScript` constructor public.\n- Made `scriptsUnderTest` variable in `HiveRunnerExtension` protected so it can be used in [MutantSwarm](https://github.com/HotelsDotCom/mutant-swarm).\n- Fixed bug that appears in [Mutant Swarm](https://github.com/HotelsDotCom/mutant-swarm) when updating HiveRunner to version 5.2.1.\n- Renamed `HelloAnnotatedHiveRunner` in `com.klarna.hiverunner.examples` to `HelloAnnotatedHiveRunnerTest`.\n- Renamed `HelloHiveRunner` in `com.klarna.hiverunner.examples` to `HelloHiveRunnerTest`.\n- Renamed `InsertTestData` in `com.klarna.hiverunner.examples` to `InsertTestDataTest`.\n- Renamed `SetHiveConfValues` in `com.klarna.hiverunner.examples` to `SetHiveConfValuesTest`.\n- Renamed `HelloAnnotatedHiveRunner` in `com.klarna.hiverunner.examples.junit4` to `HelloAnnotatedHiveRunnerTest`.\n- Renamed `HelloHiveRunner` in `com.klarna.hiverunner.examples.junit4` to `HelloHiveRunnerTest`.\n- Renamed `InsertTestData` in `com.klarna.hiverunner.examples.junit4` to `InsertTestDataTest`.\n- Renamed `SetHiveConfValues` in `com.klarna.hiverunner.examples.junit4` to `SetHiveConfValuesTest`.\n- Updated `surefire-version-plugin` from `2.21.0` to `2.22.0`.\n- Updated `junit.jupiter.version` (JUnit5) from `5.6.0` to `5.7.1`.\n- Updated `junit` (JUnit4) from `4.13.1` to `4.13.2`.\n- Updated `mockito-core` from `2.18.3` to `3.8.0`.\n\n### Added\n- Added `getScriptPaths` method in `HiveRunnerCore`.\n- Added `getScriptPaths` method in `HiveRunnerExtension` to be able to access the other method in `HiveRunnerCore` so that it can be used downstream in [MutantSwarm](https://github.com/HotelsDotCom/mutant-swarm).\n- Added `fromScriptPaths` method in `HiveShellBuilder`.\n- Added version `5.7.1` of `junit-vintage-engine`.\n- Added version `3.8.0` of `mockito-junit-jupiter`.\n\n### Fixed\n- Fixed bug where the files specified in `@HiveSQL` weren't being run when using `HiveRunnerExtension`.\n- Successful tests using \"SET\" no longer marked as \"terminated\" when run in IntelliJ. See [#94](https://github.com/klarna/HiveRunner/issues/94).\n\n## [6.0.1] - 2020-09-07\n### Removed\n- Removed shaded jar that was being produced as a side-effect.\n\n## [6.0.0] - 2020-09-03\n### Changed\n- Upgraded Hive version to 3.1.2 (was 2.3.7).\n\n## [5.x]\n### NOTE\n- Releases from the 5.x (Hive 2) line are not tracked in this CHANGELOG, it only tracks 6.0.0 and above. For changes in 5.x please refer to https://github.com/klarna/HiveRunner/blob/hive-2.x/CHANGELOG.md.\n\n## [5.0.0] - 2019-09-30\n### Added\n- JUnit5 [Extension](https://junit.org/junit5/docs/current/user-guide/#extensions) support with `HiveRunnerExtension`. See [#106](https://github.com/klarna/HiveRunner/issues/106).\n\n### Changed\n- Default supported Hive version is now 2.3.4 (was 2.3.3) as version 2.3.3 has a [vulnerability](https://nvd.nist.gov/vuln/detail/CVE-2018-1314).\n- `TemporaryFolder` ([JUnit 4](https://junit.org/junit4/javadoc/4.12/org/junit/rules/TemporaryFolder.html)) has been changed to `Path` ([Java NIO](https://docs.oracle.com/javase/8/docs/api/java/nio/file/Path.html)) throughout the project for the JUnit5 update. \n- NOTE: The `HiveServerContext` class now uses `Path` instead of `TemporaryFolder` in the constructor.\n\n## [4.1.0] - 2019-02-27\n### Changed\n- Internal refactoring to support upcoming \"Mutant Swarm\" project which provides unit test coverage for Hive SQL scripts. See [#65](https://github.com/klarna/HiveRunner/issues/65).\n\n## [4.0.0] - 2018-07-17\n### Added\n- Support shell-specific `source` (`hive`) and ``!run`` (`beeline`) commands. These commands allow one to import and execute the contents of external files in statements or scripts.\n\n### Changed\n- Default supported Hive version is now 2.3.3 (was 1.2.1).\n- Default supported Tez version is now 0.9.1 (was 0.7.0).\n- Supported Java version is 8 (was 7).\n- In-memory DB used by HiveRunner is now Derby (was HSQLDB).\n- Log4J configuration file removed from jar artifact.\n- System property to configure command shell emulation mode renamed to `commandShellEmulator` (was `commandShellEmulation`).\n\n## [3.2.1] - 2018-05-31\n### Changed\n- Fixed issue where if case of column name in a file was different to case in table definition they would be treated as different [#73](https://github.com/klarna/HiveRunner/issues/73).\n- The way of setting writable permissions on JUnit temporary folder changed to make it compatible with Windows [#63](https://github.com/klarna/HiveRunner/issues/63).\n\n## [3.2.0] - 2017-02-09\n### Added\n- Added functionality for headers in TSV parser. This way you can dynamically add TSV files declaring a subset of columns using insertInto.\n\n## [3.1.1] - 2017-01-27\n### Added\n- Added debug logging of result set. Enable by setting ```log4j.logger.com.klarna.hiverunner.HiveServerContainer=DEBUG``` in log4j.properties.\n\n## [3.1.0] - 2016-10-17\n### Added\n- Added methods to the shell that allow statements contained in files to be executed and their results gathered. These are particularly useful for HQL scripts that generate no table based data and instead write results to STDOUT. In practice we've seen these scripts used in data processing job orchestration scripts (e.g `bash`) to check for new data, calculate processing boundaries, etc. These values are then used to appropriately configure and launch some downstream job.\n- Support abstract base class [#48](https://github.com/klarna/HiveRunner/issues/48).\n\n## [3.0.0] - 2016-02-05\n### Changed\n- Upgraded to Hive 1.2.1 (Note: new major release with backwards incompatibility issues). As of Hive 1.2 there are a number of new reserved keywords, see [DDL manual](https://cwiki.apache.org/confluence/display/Hive/LanguageManual+DDL#LanguageManualDDL-Keywords,Non-reservedKeywordsandReservedKeywords) for more information. If you happen to have one of these as an identifier, you could either backtick quote them (e.g. \\`date\\`, \\`timestamp\\` or \\`update\\`) or set hive.support.sql11.reserved.keywords=false. \n- Users of Hive version 0.14 or older are recommended to use HiveRunner version 2.6.0.\n- Removed the custom HiveConf hive.vs. Use hadoop.tmp.dir instead.\n\n## [2.6.0] - 2015-12-01\n### Added\n- Introduced command shell emulations to replicate different handling of full line comments in `hive` and `beeline` shells. Now strips full line comments for executed scripts to match the behaviour of the `hive -f` file option. \n- Option to use files as input for com.klarna.hiverunner.HiveShell.execute(...).\n\n## [2.5.1] - 2015-11-12\n### Changed\n- Fixed deadlock in `ThrowOnTimeout.java` that occurred when running with long running test case and disabled timeout.\n\n## [2.5.0]\n### Added\n- Added support with `HiveShell.insertInto` for fluently generating test data in a table storage format agnostic manner.\n\n## [2.4.0]\n### Changed\n- Enabled any hiveconf variables to be set as System properties by using the naming convention hiveconf_[HiveConf property name]. e.g: hiveconf_hive.execution.engine.\n- Fixed bug: Results sets bigger than 100 rows only returned the first 100 rows. \n\n## [2.3.0]\n### Changed\n- Merged Tez and MR context into the same context again. Now, the same test suite may alter between execution engines by doing e.g.: \n\n hive> set hive.execution.engine=tez;\n hive> [some query]\n hive> set hive.execution.engine=mr;\n hive> [some query]\n\n## [2.2.0]\n### Added\n- Added support for setting hivevars via HiveShell.\n"
},
{
"path": "CODE-OF-CONDUCT.md",
"content": "# Contributor Covenant Code of Conduct\n\n## Our Pledge\n\nIn the interest of fostering an open and welcoming environment, we as\ncontributors and maintainers pledge to making participation in our project and\nour community a harassment-free experience for everyone, regardless of age, body\nsize, disability, ethnicity, gender identity and expression, level of experience,\nnationality, personal appearance, race, religion, or sexual identity and\norientation.\n\n## Our Standards\n\nExamples of behaviour that contributes to creating a positive environment\ninclude:\n\n* Using welcoming and inclusive language\n* Being respectful of differing viewpoints and experiences\n* Gracefully accepting constructive criticism\n* Focusing on what is best for the community\n* Showing empathy towards other community members\n\nExamples of unacceptable behaviour by participants include:\n\n* The use of sexualised language or imagery and unwelcome sexual attention or\n advances\n* Trolling, insulting/derogatory comments, and personal or political attacks\n* Public or private harassment\n* Publishing others' private information, such as a physical or electronic\n address, without explicit permission\n* Other conduct which could reasonably be considered inappropriate in a\n professional setting\n\n## Our Responsibilities\n\nProject maintainers are responsible for clarifying the standards of acceptable\nbehaviour and are expected to take appropriate and fair corrective action in\nresponse to any instances of unacceptable behaviour.\n\nProject maintainers have the right and responsibility to remove, edit, or\nreject comments, commits, code, wiki edits, issues, and other contributions\nthat are not aligned to this Code of Conduct, or to ban temporarily or\npermanently any contributor for other behaviours that they deem inappropriate,\nthreatening, offensive, or harmful.\n\n## Scope\n\nThis Code of Conduct applies both within project spaces and in public spaces\nwhen an individual is representing the project or its community. Examples of\nrepresenting a project or community include using an official project e-mail\naddress, posting via an official social media account, or acting as an appointed\nrepresentative at an online or offline event. Representation of a project may be\nfurther defined and clarified by project maintainers.\n\n## Enforcement\n\nInstances of abusive, harassing, or otherwise unacceptable behaviour may be\nreported by contacting [a member of the project team](https://github.com/orgs/HiveRunner/teams/hiverunner-committers). All\ncomplaints will be reviewed and investigated and will result in a response that\nis deemed necessary and appropriate to the circumstances. The project team is\nobligated to maintain confidentiality with regard to the reporter of an incident.\nFurther details of specific enforcement policies may be posted separately.\n\nProject maintainers who do not follow or enforce the Code of Conduct in good\nfaith may face temporary or permanent repercussions as determined by other\nmembers of the project's leadership.\n\n## Attribution\n\nThis Code of Conduct is adapted from the [Contributor Covenant][homepage], version 1.4,\navailable at https://www.contributor-covenant.org/version/1/4/code-of-conduct.html\n\n[homepage]: https://www.contributor-covenant.org\n\n"
},
{
"path": "CONTRIBUTING.md",
"content": "# How To Contribute\n\nWe'd love to accept your patches and contributions to this project. There are just a few guidelines you need to follow which are described in detail below.\n\n## 1. Fork this repo\n\nYou should create a fork of this project in your account and work from there. You can create a fork by clicking the fork button in GitHub.\n\n## 2. One feature, one branch\n\nWork for each new feature/issue should occur in its own branch. To create a new branch from the command line:\n```shell\ngit checkout -b my-new-feature\n```\nwhere \"my-new-feature\" describes what you're working on.\n\n## 3. Add unit tests\nIf your contribution modifies existing or adds new code please add corresponding unit tests for this.\n\n## 4. Ensure that the build passes\n\nRun\n```shell\nmvn package\n```\nand check that there are no errors.\n\n## 5. Add documentation for new or updated functionality\n\nPlease review all of the .md files in this project to see if they are impacted by your change and update them accordingly.\n\n## 6. Add to CHANGELOG.md\n\nAny notable changes should be recorded in the CHANGELOG.md following the [Keep a Changelog](https://keepachangelog.com/en/1.0.0/) conventions.\n\n## 7. Submit a pull request and describe the change\n\nPush your changes to your branch and open a pull request against the parent repo on GitHub. The project administrators will review your pull request and respond with feedback.\n\n# How your contribution gets merged\n\nUpon pull request submission, your code will be reviewed by the maintainers. They will confirm at least the following:\n\n- Tests run successfully (unit, coverage, integration, style).\n- Contribution policy has been followed.\n\nTwo (human) reviewers will need to sign off on your pull request before it can be merged.\n"
},
{
"path": "LICENSE.txt",
"content": "\n Apache License\n Version 2.0, January 2004\n http://www.apache.org/licenses/\n\n TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION\n\n 1. Definitions.\n\n \"License\" shall mean the terms and conditions for use, reproduction,\n and distribution as defined by Sections 1 through 9 of this document.\n\n \"Licensor\" shall mean the copyright owner or entity authorized by\n the copyright owner that is granting the License.\n\n \"Legal Entity\" shall mean the union of the acting entity and all\n other entities that control, are controlled by, or are under common\n control with that entity. For the purposes of this definition,\n \"control\" means (i) the power, direct or indirect, to cause the\n direction or management of such entity, whether by contract or\n otherwise, or (ii) ownership of fifty percent (50%) or more of the\n outstanding shares, or (iii) beneficial ownership of such entity.\n\n \"You\" (or \"Your\") shall mean an individual or Legal Entity\n exercising permissions granted by this License.\n\n \"Source\" form shall mean the preferred form for making modifications,\n including but not limited to software source code, documentation\n source, and configuration files.\n\n \"Object\" form shall mean any form resulting from mechanical\n transformation or translation of a Source form, including but\n not limited to compiled object code, generated documentation,\n and conversions to other media types.\n\n \"Work\" shall mean the work of authorship, whether in Source or\n Object form, made available under the License, as indicated by a\n copyright notice that is included in or attached to the work\n (an example is provided in the Appendix below).\n\n \"Derivative Works\" shall mean any work, whether in Source or Object\n form, that is based on (or derived from) the Work and for which the\n editorial revisions, annotations, elaborations, or other modifications\n represent, as a whole, an original work of authorship. For the purposes\n of this License, Derivative Works shall not include works that remain\n separable from, or merely link (or bind by name) to the interfaces of,\n the Work and Derivative Works thereof.\n\n \"Contribution\" shall mean any work of authorship, including\n the original version of the Work and any modifications or additions\n to that Work or Derivative Works thereof, that is intentionally\n submitted to Licensor for inclusion in the Work by the copyright owner\n or by an individual or Legal Entity authorized to submit on behalf of\n the copyright owner. For the purposes of this definition, \"submitted\"\n means any form of electronic, verbal, or written communication sent\n to the Licensor or its representatives, including but not limited to\n communication on electronic mailing lists, source code control systems,\n and issue tracking systems that are managed by, or on behalf of, the\n Licensor for the purpose of discussing and improving the Work, but\n excluding communication that is conspicuously marked or otherwise\n designated in writing by the copyright owner as \"Not a Contribution.\"\n\n \"Contributor\" shall mean Licensor and any individual or Legal Entity\n on behalf of whom a Contribution has been received by Licensor and\n subsequently incorporated within the Work.\n\n 2. Grant of Copyright License. Subject to the terms and conditions of\n this License, each Contributor hereby grants to You a perpetual,\n worldwide, non-exclusive, no-charge, royalty-free, irrevocable\n copyright license to reproduce, prepare Derivative Works of,\n publicly display, publicly perform, sublicense, and distribute the\n Work and such Derivative Works in Source or Object form.\n\n 3. Grant of Patent License. Subject to the terms and conditions of\n this License, each Contributor hereby grants to You a perpetual,\n worldwide, non-exclusive, no-charge, royalty-free, irrevocable\n (except as stated in this section) patent license to make, have made,\n use, offer to sell, sell, import, and otherwise transfer the Work,\n where such license applies only to those patent claims licensable\n by such Contributor that are necessarily infringed by their\n Contribution(s) alone or by combination of their Contribution(s)\n with the Work to which such Contribution(s) was submitted. If You\n institute patent litigation against any entity (including a\n cross-claim or counterclaim in a lawsuit) alleging that the Work\n or a Contribution incorporated within the Work constitutes direct\n or contributory patent infringement, then any patent licenses\n granted to You under this License for that Work shall terminate\n as of the date such litigation is filed.\n\n 4. Redistribution. You may reproduce and distribute copies of the\n Work or Derivative Works thereof in any medium, with or without\n modifications, and in Source or Object form, provided that You\n meet the following conditions:\n\n (a) You must give any other recipients of the Work or\n Derivative Works a copy of this License; and\n\n (b) You must cause any modified files to carry prominent notices\n stating that You changed the files; and\n\n (c) You must retain, in the Source form of any Derivative Works\n that You distribute, all copyright, patent, trademark, and\n attribution notices from the Source form of the Work,\n excluding those notices that do not pertain to any part of\n the Derivative Works; and\n\n (d) If the Work includes a \"NOTICE\" text file as part of its\n distribution, then any Derivative Works that You distribute must\n include a readable copy of the attribution notices contained\n within such NOTICE file, excluding those notices that do not\n pertain to any part of the Derivative Works, in at least one\n of the following places: within a NOTICE text file distributed\n as part of the Derivative Works; within the Source form or\n documentation, if provided along with the Derivative Works; or,\n within a display generated by the Derivative Works, if and\n wherever such third-party notices normally appear. The contents\n of the NOTICE file are for informational purposes only and\n do not modify the License. You may add Your own attribution\n notices within Derivative Works that You distribute, alongside\n or as an addendum to the NOTICE text from the Work, provided\n that such additional attribution notices cannot be construed\n as modifying the License.\n\n You may add Your own copyright statement to Your modifications and\n may provide additional or different license terms and conditions\n for use, reproduction, or distribution of Your modifications, or\n for any such Derivative Works as a whole, provided Your use,\n reproduction, and distribution of the Work otherwise complies with\n the conditions stated in this License.\n\n 5. Submission of Contributions. Unless You explicitly state otherwise,\n any Contribution intentionally submitted for inclusion in the Work\n by You to the Licensor shall be under the terms and conditions of\n this License, without any additional terms or conditions.\n Notwithstanding the above, nothing herein shall supersede or modify\n the terms of any separate license agreement you may have executed\n with Licensor regarding such Contributions.\n\n 6. Trademarks. This License does not grant permission to use the trade\n names, trademarks, service marks, or product names of the Licensor,\n except as required for reasonable and customary use in describing the\n origin of the Work and reproducing the content of the NOTICE file.\n\n 7. Disclaimer of Warranty. Unless required by applicable law or\n agreed to in writing, Licensor provides the Work (and each\n Contributor provides its Contributions) on an \"AS IS\" BASIS,\n WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or\n implied, including, without limitation, any warranties or conditions\n of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A\n PARTICULAR PURPOSE. You are solely responsible for determining the\n appropriateness of using or redistributing the Work and assume any\n risks associated with Your exercise of permissions under this License.\n\n 8. Limitation of Liability. In no event and under no legal theory,\n whether in tort (including negligence), contract, or otherwise,\n unless required by applicable law (such as deliberate and grossly\n negligent acts) or agreed to in writing, shall any Contributor be\n liable to You for damages, including any direct, indirect, special,\n incidental, or consequential damages of any character arising as a\n result of this License or out of the use or inability to use the\n Work (including but not limited to damages for loss of goodwill,\n work stoppage, computer failure or malfunction, or any and all\n other commercial damages or losses), even if such Contributor\n has been advised of the possibility of such damages.\n\n 9. Accepting Warranty or Additional Liability. While redistributing\n the Work or Derivative Works thereof, You may choose to offer,\n and charge a fee for, acceptance of support, warranty, indemnity,\n or other liability obligations and/or rights consistent with this\n License. However, in accepting such obligations, You may act only\n on Your own behalf and on Your sole responsibility, not on behalf\n of any other Contributor, and only if You agree to indemnify,\n defend, and hold each Contributor harmless for any liability\n incurred by, or claims asserted against, such Contributor by reason\n of your accepting any such warranty or additional liability.\n\n END OF TERMS AND CONDITIONS\n\n APPENDIX: How to apply the Apache License to your work.\n\n To apply the Apache License to your work, attach the following\n boilerplate notice, with the fields enclosed by brackets \"[]\"\n replaced with your own identifying information. (Don't include\n the brackets!) The text should be enclosed in the appropriate\n comment syntax for the file format. We also recommend that a\n file or class name and description of purpose be included on the\n same \"printed page\" as the copyright notice for easier\n identification within third-party archives.\n\n Copyright [yyyy] [name of copyright owner]\n\n Licensed under the Apache License, Version 2.0 (the \"License\");\n you may not use this file except in compliance with the License.\n You may obtain a copy of the License at\n\n http://www.apache.org/licenses/LICENSE-2.0\n\n Unless required by applicable law or agreed to in writing, software\n distributed under the License is distributed on an \"AS IS\" BASIS,\n WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n See the License for the specific language governing permissions and\n limitations under the License.\n"
},
{
"path": "README.md",
"content": "\n[](https://maven-badges.herokuapp.com/maven-central/io.github.hiverunner/hiverunner) \n[](https://github.com/HiveRunner/HiveRunner/actions?query=workflow:\"build\")\n[](https://opensource.org/licenses/Apache-2.0)\n\n\n\n# HiveRunner\n\nWelcome to HiveRunner - Zero installation open source unit testing of [Hive](https://hive.apache.org/) applications.\n\n[Watch the HiveRunner teaser on youtube!](http://youtu.be/B7yEAHwgi2w)\n\nWelcome to the open source project HiveRunner. HiveRunner is a unit test framework based on JUnit (4 & 5) and enables \nTDD development of Hive SQL without the need for any installed dependencies. All you need is to add HiveRunner to your \n`pom.xml` as any other library and you're good to go.\n\nHiveRunner is under constant development. It is used extensively by many companies. Please feel free to suggest \nimprovements both as pull requests and as written requests.\n\n\n## Overview\n\nHiveRunner enables you to write Hive SQL as releasable tested artifacts. It will require you to parametrize and \nmodularize Hive SQL in order to make it testable. The bits and pieces of code should then be wired together with some \norchestration/workflow/build tool of your choice, to be runnable in your environment (e.g. Oozie, Pentaho, Talend, \nMaven, etc.) \n\nSo, even though your current Hive SQL probably won't run off the shelf within HiveRunner, we believe the enforced \ntestability and enabling of a TDD workflow will do as much good to the scripting world of SQL as it has for the Java \ncommunity.\n\n## Versions\n\nDifferent versions of HiveRunner target different versions of Hive as follows:\n\n| HiveRunner Version | Hive Version | Status | Source Code Branch |\n|--------------------|--------------|----------------------------|--------------------------------------------------------|\n| 7.x | 4.x | New, active development | https://github.com/HiveRunner/HiveRunner/tree/hive-4.x |\n| 6.x | 3.x | Stable, active development | https://github.com/HiveRunner/HiveRunner (i.e. `main`) |\n| 5.x | 2.x | Stable, bug fixes only | https://github.com/HiveRunner/HiveRunner/tree/hive-2.x |\n\n\n# Cook Book\n\n## 1. Include HiveRunner\n\nHiveRunner is published to [Maven Central](https://search.maven.org/search?q=hiverunner). To start to use it, add a dependency to HiveRunner to your pom file:\n\n \n io.github.hiverunner\n hiverunner\n [HIVERUNNER VERSION]\n test\n \n\nAlternatively, if you want to build from source, clone this repo and build with:\n\n mvn install\n\nThen add the dependency as mentioned above.\n\nAlso explicitly add the surefire plugin and configure forkMode=always to avoid OutOfMemory when building big test suites.\n\n \n org.apache.maven.plugins\n maven-surefire-plugin\n 2.21.0\n \n always\n \n \n\nAs an alternative if this does not solve the OOM issues, try increase the -Xmx and -XX:MaxPermSize settings. For example:\n\n \n org.apache.maven.plugins\n maven-surefire-plugin\n 2.21.0\n \n 1\n false\n -Xmx2048m -XX:MaxPermSize=512m\n \n \n\n(please note that the forkMode option is deprecated and you should use forkCount and reuseForks instead)\n\nWith forkCount and reuseForks there is a possibility to reduce the test execution time drastically, depending on your hardware. A plugin configuration which are using one fork per CPU core and reuse threads would look like:\n\n \n org.apache.maven.plugins\n maven-surefire-plugin\n 2.21.0\n \n 1C\n true\n -Xmx2048m -XX:MaxPermSize=512m\n \n \n\nBy default, HiveRunner uses mapreduce (mr) as the execution engine for Hive. If you wish to run using Tez, set the \nSystem property `hiveconf_hive.execution.engine` to 'tez'.\n\n(Any Hive conf property may be overridden by prefixing it with 'hiveconf_')\n \n \n org.apache.maven.plugins\n maven-surefire-plugin\n 2.21.0\n \n \n tez\n 1000\n \n \n \n\n### Timeout\nIt's possible to configure HiveRunner to make tests time out after some time and retry those tests a couple of times, but only when using `StandaloneHiveRunner` as this is not available in the `HiveRunnerExtension` (from HiveRunner 5.x and up). This is to cover for the bug\nhttps://issues.apache.org/jira/browse/TEZ-2475 that at times causes test cases to not terminate due to a lost DAG reference.\nThe timeout feature can be configured via the 'enableTimeout', 'timeoutSeconds' and 'timeoutRetries' properties.\nA configuration which enables timeouts after 30 seconds and allows 2 retries would look like:\n\n \n org.apache.maven.plugins\n maven-surefire-plugin\n 2.21.0\n \n \n true\n 30\n 2\n \n \n \n\n\n### Logging\n\nHiveRunner uses [SLF4J](https://www.slf4j.org/) so you should configure logging in your tests using any compatible logging framework.\n\n## 2. Look at the examples\n\nLook at the [com.klarna.hiverunner.examples.HelloHiveRunnerTest](/src/test/java/com/klarna/hiverunner/examples/HelloHiveRunnerTest.java) reference test case to get a feeling for how a typical test case looks like in JUnit5. To find JUnit4 versions of the examples, look at [com.klarna.hiverunner.examples.junit4.HelloHiveRunnerTest](/src/test/java/com/klarna/hiverunner/examples/junit4/HelloHiveRunnerTest.java).\n\nIf you're put off by the verbosity of the annotations, there's always the possibility to use HiveShell in a more interactive mode. The [com.klarna.hiverunner.SerdeTest](/src/test/java/com/klarna/hiverunner/SerdeTest.java) adds a resource (test data) interactively with HiveShell instead of using annotations.\n\nAnnotations and interactive mode can be mixed and matched, however you'll always need to include the [com.klarna.hiverunner.annotations.HiveSQL](/src/main/java/com/klarna/hiverunner/annotations/HiveSQL.java) annotation e.g:\n\n @HiveSQL(files = {\"serdeTest/create_table.sql\", \"serdeTest/hql_custom_serde.sql\"}, autoStart = false)\n public HiveShell hiveShell;\n\nNote that the *autostart = false* is needed for the interactive mode. It can be left out when running with only annotations.\n\n### Sequence files\nIf you work with __sequence files__ (Or anything else than regular text files) make sure to take a look at [ResourceOutputStreamTest](/src/test/java/com/klarna/hiverunner/ResourceOutputStreamTest.java) \nfor an example of how to use the new method [HiveShell](src/main/java/com/klarna/hiverunner/HiveShell.java)\\#getResourceOutputStream to manage test input data. \n\n### Programatically create test input data\n\nTest data can be programmatically inserted into any Hive table using `HiveShell.insertInto(...)`. This seamlessly handles different storage formats and partitioning types allowing you to focus on the data required by your test scenarios:\n\n hiveShell.execute(\"create database test_db\");\n hiveShell.execute(\"create table test_db.test_table (\"\n + \"c1 string,\"\n + \"c2 string,\"\n + \"c3 string\"\n + \")\"\n + \"partitioned by (p1 string)\"\n + \"stored as orc\");\n\n hiveShell.insertInto(\"test_db\", \"test_table\")\n .withColumns(\"c1\", \"p1\").addRow(\"v1\", \"p1\") // add { \"v1\", null, null, \"p1\" }\n .withAllColumns().addRow(\"v1\", \"v2\", \"v3\", \"p1\") // add { \"v1\", \"v2\", \"v3\", \"p1\" }\n .copyRow().set(\"c1\", \"v4\") // add { \"v4\", \"v2\", \"v3\", \"p1\" }\n .addRowsFromTsv(file) // parses TSV data out of a file resource\n .addRowsFrom(file, fileParser) // parses custom data out of a file resource\n .commit();\n\nSee [com.klarna.hiverunner.examples.InsertTestDataTest](/src/test/java/com/klarna/hiverunner/examples/InsertTestDataTest.java) for working examples.\n\n## 3. Understand the order of execution\n\nHiveRunner will in default mode set up and start the HiveShell before the test method is invoked. If autostart is set to false, the [HiveShell](/src/main/java/com/klarna/hiverunner/HiveShell.java) must be started manually from within the test method. Either way, HiveRunner will do the following steps when start is invoked:\n\n1. Merge any [@HiveProperties](/src/main/java/com/klarna/hiverunner/annotations/HiveProperties.java) from the test case with the Hive conf\n2. Start the HiveServer with the merged conf\n3. Copy all [@HiveResource](/src/main/java/com/klarna/hiverunner/annotations/HiveResource.java) data into the temp file area for the test\n4. Execute all fields annotated with [@HiveSetupScript](/src/main/java/com/klarna/hiverunner/annotations/HiveSetupScript.java)\n5. Execute the script files given in the [@HiveSQL](/src/main/java/com/klarna/hiverunner/annotations/HiveSQL.java) annotation\n\nThe [HiveShell](/src/main/java/com/klarna/hiverunner/HiveShell.java) field annotated with [@HiveSQL](/src/main/java/com/klarna/hiverunner/annotations/HiveSQL.java) will always be injected before the test method is invoked.\n\n\n# Hive version compatibility\n\n- This version of HiveRunner is built for Hive 3.1.2.\n- For Hive 2.x support please use HiveRunner 5.x.\n- Command shell emulations are provided to closely match the behaviour of both the Hive CLI and Beeline interactive shells. The desired emulation can be specified in your `pom.xml` file like so: \n\n \n org.apache.maven.plugins\n maven-surefire-plugin\n 2.21.0\n \n \n \n BEELINE\n \n \n \n\n Or provided on the command line using a system property:\n\n mvn -DcommandShellEmulator=BEELINE test\n\n# Future work and Limitations\n\n* HiveRunner does not allow the `add jar` statement. It is considered bad practice to keep environment specific code together with the business logic that targets HiveRunner. Keep environment specific stuff in separate files and use your build/orchestration/workflow tool to run the right files in the right order in the right environment. When running HiveRunner, all SerDes available on the classpath of the IDE/maven will be available.\n\n* HiveRunner runs Hive and Hive runs on top of Hadoop, and Hadoop has limited support for Windows machines. Installing [Cygwin](http://www.cygwin.com/ \"Cygwin\") might help out.\n\n* Currently the HiveServer spins up and tears down for every test method. As a performance option it should be possible to clean the HiveServer and metastore between each test method invocation. The choice should probably be exposed to the test writer. By switching between different strategies, side effects/leakage can be ruled out during test case debugging. See [#69](https://github.com/HiveRunner/HiveRunner/issues/69).\n\n# Known Issues\n\n### UnknownHostException\nI've had issues with UnknownHostException on OS X after upgrading my system or running Docker. \nUsually a restart of my machine solved it, but last time I got some corporate \nstuff installed the restarts stopped working and I kept getting UnknownHostExceptions. \nFollowing this simple guide solved my problem:\nhttp://crunchify.com/getting-java-net-unknownhostexception-nodename-nor-servname-provided-or-not-known-error-on-mac-os-x-update-your-privateetchosts-file/\n\n### Tez queries do not terminate\nTez will at times forget the process id of a random DAG. This will cause the query to never terminate. To get around this there is \na timeout and retry functionality implemented in HiveRunner:\n \n \n org.apache.maven.plugins\n maven-surefire-plugin\n 2.21.0\n \n \n true\n 30\n 2\n \n \n \n \nMake sure to set the timeoutSeconds to that of your slowest test in the test suite and then add some padding.\n\n# Contact\n\n# Mailing List\nIf you would like to ask any questions about or discuss HiveRunner please join our mailing list at\n\n [https://groups.google.com/forum/#!forum/hive-runner-user](https://groups.google.com/forum/#!forum/hive-runner-user)\n\n# History\nThis project was initially developed and maintained by [Klarna](https://klarna.github.io/) and then by [Expedia Group](https://expediagroup.github.io/) before moving to its own top-level organisation on GitHub.\n\n# Legal\nThis project is available under the [Apache 2.0 License](http://www.apache.org/licenses/LICENSE-2.0.html).\n\nCopyright 2021-2024 The HiveRunner Contributors.\n\nCopyright 2013-2021 Klarna AB.\n"
},
{
"path": "RELEASING.md",
"content": "# Releasing HiveRunner to Maven Central\n\nHiveRunner has been set up to build continuously and also to deploy SNAPSHOTS to Sonatype and releases to Maven Central via GitHub Actions.\n\n## Deploying a SNAPSHOT to Sonatype\n\n* Select the https://github.com/HiveRunner/HiveRunner/actions/workflows/deploy.yml worfklow\n* Click \"Run workflow\"\n* Select the branch to use to deploy a SNAPSHOT from:\n * Use `main` as the branch for a Hive 3.x release\n * Use `hive-4.x` as the branch for a Hive 4.x release\n * Use `hive-2.x` as the branch for a Hive 2.x release\n* Run the workflow\n* SNAPSHOT artifacts will be available at https://s01.oss.sonatype.org/content/repositories/snapshots/io/github/hiverunner/hiverunner/\n\n## Deploying a release to Maven Central\n\n* Ensure the `pom.xml` has the SNAPSHOT version set to the value you would like to make a release from\n* Update `CHANGELOG.md` with the date corresponding to when you're performing the release\n* Select the https://github.com/HiveRunner/HiveRunner/actions/workflows/release.yml worfklow\n* Click \"Run workflow\"\n* Select the branch to use to deploy a release from:\n * Use `main` as the branch for a Hive 3.x release\n * Use `hive-4.x` as the branch for a Hive 4.x release \n * Use `hive-2.x` as the branch for a Hive 2.x release\n* Run the workflow\n* Release artifacts will be available at https://repo1.maven.org/maven2/io/github/hiverunner/hiverunner/\n* It can take a few hours before the artifacts show up in searches performed at https://search.maven.org/search?q=hiverunner\n"
},
{
"path": "pom.xml",
"content": "\n 4.0.0\n\n io.github.hiverunner\n hiverunner\n 6.1.1-SNAPSHOT\n HiveRunner\n HiveRunner is a unit test framework based on JUnit (4 or 5) that enables TDD development of Hive SQL without the need of any installed dependencies.\n https://github.com/HiveRunner/HiveRunner\n \n 2021\n\n \n \n The Apache Software License, Version 2.0\n http://www.apache.org/licenses/LICENSE-2.0.txt\n repo\n \n \n \n \n \n HiveRunner Committers\n HiveRunner\n https://github.com/HiveRunner\n \n \n\n \n scm:git:https://github.com/HiveRunner/HiveRunner.git\n scm:git:https://github.com/HiveRunner/HiveRunner.git\n git@github.com:HiveRunner/HiveRunner.git\n HEAD\n \n\n \n UTF-8\n\n 3.1.0\n mr\n 3.1.2\n 5.7.1\n 3.0\n 0.9.1\n 3.8.0\n \n \n \n \n org.apache.hive\n hive-serde\n ${hive.version}\n \n\n \n com.fasterxml.jackson.core\n jackson-annotations\n 2.9.5\n \n\n \n org.apache.hive\n hive-jdbc\n ${hive.version}\n \n\n \n org.apache.hive.hcatalog\n hive-webhcat-java-client\n ${hive.version}\n \n\n \n org.apache.hive\n hive-service\n ${hive.version}\n \n\n \n tez-dag\n org.apache.tez\n ${tez.version}\n \n\n \n tez-common\n org.apache.tez\n ${tez.version}\n \n\n \n tez-mapreduce\n org.apache.tez\n ${tez.version}\n \n\n \n org.apache.hive\n hive-contrib\n ${hive.version}\n test\n \n\n \n org.reflections\n reflections\n 0.9.8\n \n\n \n org.apache.hadoop\n hadoop-mapreduce-client-common\n ${hadoop.version}\n \n\n \n org.apache.hadoop\n hadoop-mapreduce-client-core\n ${hadoop.version}\n \n\n \n com.github.stefanbirkner\n system-rules\n 1.19.0\n test\n \n\n \n \n org.hamcrest\n hamcrest-all\n 1.3\n test\n \n\n \n org.mockito\n mockito-core\n ${mockito.version}\n test\n \n\n \n org.mockito\n mockito-junit-jupiter\n ${mockito.version}\n test\n \n\n \n junit\n junit\n 4.13.2\n provided\n \n\n \n org.junit.jupiter\n junit-jupiter\n ${junit.jupiter.version}\n \n\n \n org.junit.vintage\n junit-vintage-engine\n ${junit.jupiter.version}\n \n\n \n\n \n \n \n \n org.apache.maven.plugins\n maven-surefire-plugin\n 2.22.2\n \n \n -Xmx2024m\n \n false\n \n \n ${hive.execution.engine}\n 1000\n false\n 30\n 2\n \n \n \n \n org.apache.maven.plugins\n maven-compiler-plugin\n 3.7.0\n \n 1.8\n 1.8\n \n \n \n org.apache.maven.plugins\n maven-jar-plugin\n 3.2.0\n \n \n \n ${project.version}\n ${maven.build.timestamp}\n ${project.groupId}\n ${project.artifactId}\n \n \n \n \n\n \n com.mycila\n license-maven-plugin\n ${license.maven.plugin.version}\n \n \n com.mycila\n license-maven-plugin-git\n ${license.maven.plugin.version}\n \n \n \n src/main/license/APACHE-2.txt\n \n The HiveRunner Contributors\n \n \n src/main/java/**\n src/test/java/**\n \n \n \n \n validate\n \n format\n \n \n \n \n \n \n org.apache.maven.plugins\n maven-release-plugin\n 3.0.0-M1\n \n v@{project.version}\n true\n false\n oss-release\n deploy\n \n \n\n \n org.sonatype.plugins\n nexus-staging-maven-plugin\n 1.6.8\n true\n \n ossrh\n https://s01.oss.sonatype.org/\n true\n \n \n\n \n \n\n \n \n oss-release\n \n \n ossrh\n https://s01.oss.sonatype.org/content/repositories/snapshots\n \n \n ossrh\n https://s01.oss.sonatype.org/service/local/staging/deploy/maven2/\n \n \n \n \n \n org.apache.maven.plugins\n maven-source-plugin\n 3.2.0\n \n \n attach-sources\n \n jar-no-fork\n \n \n \n \n \n org.apache.maven.plugins\n maven-javadoc-plugin\n 3.2.0\n \n ${project.build.sourceEncoding}\n 8\n false\n none\n \n \n \n attach-javadocs\n \n jar\n \n \n \n \n \n org.apache.maven.plugins\n maven-gpg-plugin\n 1.6\n \n \n sign-artifacts\n verify\n \n sign\n \n \n \n --pinentry-mode\n loopback\n \n \n \n \n \n \n \n \n \n tez\n \n tez\n \n \n \n\n"
},
{
"path": "src/main/java/com/klarna/hiverunner/HiveRunnerCore.java",
"content": "/**\n * Copyright (C) 2013-2021 Klarna AB\n * Copyright (C) 2021 The HiveRunner Contributors\n *\n * Licensed under the Apache License, Version 2.0 (the \"License\");\n * you may not use this file except in compliance with the License.\n * You may obtain a copy of the License at\n *\n * http://www.apache.org/licenses/LICENSE-2.0\n *\n * Unless required by applicable law or agreed to in writing, software\n * distributed under the License is distributed on an \"AS IS\" BASIS,\n * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n * See the License for the specific language governing permissions and\n * limitations under the License.\n */\npackage com.klarna.hiverunner;\n\nimport static org.reflections.ReflectionUtils.withAnnotation;\n\nimport java.io.File;\nimport java.io.IOException;\nimport java.lang.reflect.Field;\nimport java.net.URISyntaxException;\nimport java.nio.charset.Charset;\nimport java.nio.charset.StandardCharsets;\nimport java.nio.file.Files;\nimport java.nio.file.Path;\nimport java.nio.file.Paths;\nimport java.util.ArrayList;\nimport java.util.List;\nimport java.util.Map;\nimport java.util.Set;\n\nimport com.google.common.base.Preconditions;\nimport com.google.common.io.Resources;\nimport com.klarna.hiverunner.annotations.HiveProperties;\nimport com.klarna.hiverunner.annotations.HiveResource;\nimport com.klarna.hiverunner.annotations.HiveSQL;\nimport com.klarna.hiverunner.annotations.HiveSetupScript;\nimport com.klarna.hiverunner.builder.HiveShellBuilder;\nimport com.klarna.hiverunner.builder.Script;\nimport com.klarna.hiverunner.config.HiveRunnerConfig;\nimport com.klarna.reflection.ReflectionUtils;\n\nclass HiveRunnerCore {\n\n /**\n * Traverses the test case annotations. Will inject a HiveShell in the test case that envelopes the HiveServer.\n */\n HiveShellContainer createHiveServerContainer(List scripts, Object testCase,\n Path baseDir, HiveRunnerConfig config)\n throws IOException {\n\n HiveServerContext context = new StandaloneHiveServerContext(baseDir, config);\n\n return buildShell(scripts, testCase, config, context);\n }\n\n private HiveShellContainer buildShell(List scripts, Object testCase, HiveRunnerConfig config,\n HiveServerContext context) throws IOException {\n HiveServerContainer hiveTestHarness = new HiveServerContainer(context);\n\n HiveShellBuilder hiveShellBuilder = new HiveShellBuilder();\n hiveShellBuilder.setCommandShellEmulation(config.getCommandShellEmulator());\n\n HiveShellField shellSetter = loadScriptUnderTest(testCase, hiveShellBuilder);\n if (!scripts.isEmpty()) {\n hiveShellBuilder.overrideScriptsUnderTest(scripts);\n }\n\n hiveShellBuilder.setHiveServerContainer(hiveTestHarness);\n\n loadAnnotatedResources(testCase, hiveShellBuilder);\n\n loadAnnotatedProperties(testCase, hiveShellBuilder);\n\n loadAnnotatedSetupScripts(testCase, hiveShellBuilder);\n\n // Build shell\n HiveShellContainer shell = hiveShellBuilder.buildShell();\n\n // Set shell\n shellSetter.setShell(shell);\n\n if (shellSetter.isAutoStart()) {\n shell.start();\n }\n return shell;\n }\n\n private HiveShellField loadScriptUnderTest(Object testCaseInstance, HiveShellBuilder hiveShellBuilder) {\n try {\n Set fields = ReflectionUtils.getAllFields(testCaseInstance.getClass(), withAnnotation(HiveSQL.class));\n\n Preconditions.checkState(fields.size() == 1, \"Exact one field should to be annotated with @HiveSQL\");\n\n Field field = fields.iterator().next();\n HiveSQL annotation = field.getAnnotation(HiveSQL.class);\n List scriptPaths = getScriptPaths(annotation);\n Charset charset = annotation.encoding().equals(\"\") ?\n Charset.defaultCharset() : Charset.forName(annotation.encoding());\n\n boolean isAutoStart = annotation.autoStart();\n\n hiveShellBuilder.setScriptsUnderTest(scriptPaths, charset);\n\n return new HiveShellField() {\n @Override\n public void setShell(HiveShell shell) {\n ReflectionUtils.setField(testCaseInstance, field.getName(), shell);\n }\n\n @Override\n public boolean isAutoStart() {\n return isAutoStart;\n }\n };\n } catch (Throwable t) {\n throw new IllegalArgumentException(\"Failed to init field annotated with @HiveSQL: \" + t.getMessage(), t);\n }\n }\n\n protected List getScriptPaths(HiveSQL annotation) throws URISyntaxException {\n List scriptPaths = new ArrayList<>();\n for (String scriptFilePath : annotation.files()) {\n Path file = Paths.get(Resources.getResource(scriptFilePath).toURI());\n assertFileExists(file);\n scriptPaths.add(file);\n }\n return scriptPaths;\n }\n\n private void assertFileExists(Path file) {\n Preconditions.checkState(Files.exists(file), \"File \" + file + \" does not exist\");\n }\n\n private void loadAnnotatedSetupScripts(Object testCase, HiveShellBuilder workFlowBuilder) {\n Set setupScriptFields = ReflectionUtils.getAllFields(testCase.getClass(),\n withAnnotation(HiveSetupScript.class));\n\n for (Field setupScriptField : setupScriptFields) {\n if (ReflectionUtils.isOfType(setupScriptField, String.class)) {\n String script = ReflectionUtils.getFieldValue(testCase, setupScriptField.getName(), String.class);\n workFlowBuilder.addSetupScript(script);\n } else if (ReflectionUtils.isOfType(setupScriptField, File.class) ||\n ReflectionUtils.isOfType(setupScriptField, Path.class)) {\n Path path = getMandatoryPathFromField(testCase, setupScriptField);\n workFlowBuilder.addSetupScript(readAll(path));\n } else {\n throw new IllegalArgumentException(\n \"Field annotated with @HiveSetupScript currently only supports type String, File and Path\");\n }\n }\n }\n\n private static String readAll(Path path) {\n try {\n return new String(Files.readAllBytes(path), StandardCharsets.UTF_8);\n } catch (IOException e) {\n throw new IllegalStateException(\"Unable to read \" + path + \": \" + e.getMessage(), e);\n }\n }\n\n private void loadAnnotatedResources(Object testCase, HiveShellBuilder workFlowBuilder) throws IOException {\n Set fields = ReflectionUtils.getAllFields(testCase.getClass(), withAnnotation(HiveResource.class));\n\n for (Field resourceField : fields) {\n\n HiveResource annotation = resourceField.getAnnotation(HiveResource.class);\n String targetFile = annotation.targetFile();\n\n if (ReflectionUtils.isOfType(resourceField, String.class)) {\n String data = ReflectionUtils.getFieldValue(testCase, resourceField.getName(), String.class);\n workFlowBuilder.addResource(targetFile, data);\n } else if (ReflectionUtils.isOfType(resourceField, File.class) ||\n ReflectionUtils.isOfType(resourceField, Path.class)) {\n Path dataFile = getMandatoryPathFromField(testCase, resourceField);\n workFlowBuilder.addResource(targetFile, dataFile);\n } else {\n throw new IllegalArgumentException(\n \"Fields annotated with @HiveResource currently only supports field type String, File or Path\");\n }\n }\n }\n\n private Path getMandatoryPathFromField(Object testCase, Field resourceField) {\n Path path;\n if (ReflectionUtils.isOfType(resourceField, File.class)) {\n File dataFile = ReflectionUtils.getFieldValue(testCase, resourceField.getName(), File.class);\n path = Paths.get(dataFile.toURI());\n } else if (ReflectionUtils.isOfType(resourceField, Path.class)) {\n path = ReflectionUtils.getFieldValue(testCase, resourceField.getName(), Path.class);\n } else {\n throw new IllegalArgumentException(\n \"Only Path or File type is allowed on annotated field \" + resourceField);\n }\n\n Preconditions.checkArgument(Files.exists(path), \"File %s does not exist\", path);\n return path;\n }\n\n private void loadAnnotatedProperties(Object testCase, HiveShellBuilder workFlowBuilder) {\n for (Field hivePropertyField : ReflectionUtils.getAllFields(testCase.getClass(),\n withAnnotation(HiveProperties.class))) {\n Preconditions.checkState(ReflectionUtils.isOfType(hivePropertyField, Map.class),\n \"Field annotated with @HiveProperties should be of type Map\");\n workFlowBuilder.putAllProperties(\n ReflectionUtils.getFieldValue(testCase, hivePropertyField.getName(), Map.class));\n }\n }\n\n /**\n * Used as a handle for the HiveShell field in the test case so that we may set it once the\n * HiveShell has been instantiated.\n */\n interface HiveShellField {\n\n void setShell(HiveShell shell);\n\n boolean isAutoStart();\n }\n}\n"
},
{
"path": "src/main/java/com/klarna/hiverunner/HiveRunnerExtension.java",
"content": "/**\n * Copyright (C) 2013-2021 Klarna AB\n * Copyright (C) 2021 The HiveRunner Contributors\n *\n * Licensed under the Apache License, Version 2.0 (the \"License\");\n * you may not use this file except in compliance with the License.\n * You may obtain a copy of the License at\n *\n * http://www.apache.org/licenses/LICENSE-2.0\n *\n * Unless required by applicable law or agreed to in writing, software\n * distributed under the License is distributed on an \"AS IS\" BASIS,\n * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n * See the License for the specific language governing permissions and\n * limitations under the License.\n */\npackage com.klarna.hiverunner;\n\nimport static org.reflections.ReflectionUtils.withAnnotation;\nimport static org.reflections.ReflectionUtils.withType;\n\nimport java.io.IOException;\nimport java.io.UncheckedIOException;\nimport java.lang.reflect.Field;\nimport java.net.URISyntaxException;\nimport java.nio.file.Files;\nimport java.nio.file.Path;\nimport java.util.ArrayList;\nimport java.util.List;\nimport java.util.Set;\n\nimport org.apache.commons.io.FileUtils;\nimport org.junit.jupiter.api.extension.AfterEachCallback;\nimport org.junit.jupiter.api.extension.ExtensionContext;\nimport org.junit.jupiter.api.extension.TestInstancePostProcessor;\nimport org.slf4j.Logger;\nimport org.slf4j.LoggerFactory;\n\nimport com.google.common.base.Preconditions;\nimport com.google.common.base.Predicates;\nimport com.klarna.hiverunner.annotations.HiveRunnerSetup;\nimport com.klarna.hiverunner.annotations.HiveSQL;\nimport com.klarna.hiverunner.builder.Script;\nimport com.klarna.hiverunner.config.HiveRunnerConfig;\nimport com.klarna.reflection.ReflectionUtils;\n\npublic class HiveRunnerExtension implements AfterEachCallback, TestInstancePostProcessor {\n\n private static final Logger LOGGER = LoggerFactory.getLogger(HiveRunnerExtension.class);\n\n private final HiveRunnerCore core;\n private final HiveRunnerConfig config = new HiveRunnerConfig();\n private Path basedir;\n private HiveShellContainer container;\n protected List