Merge branch 'master' of https://github.com/amundsen-io/amundsendatab…

…uilder into aws-sqs-publisher
amundsen-io · Feb 14, 2021 · f7723ac · f7723ac
2 parents 851814e + f02c823
commit f7723ac
Show file tree

Hide file tree

Showing 20 changed files with 769 additions and 39 deletions.
diff --git a/.github/workflows/monthly_release.yml b/.github/workflows/monthly_release.yml
@@ -0,0 +1,48 @@
+name: Monthly Release
+
+on:
+  schedule:
+    - cron: 0 0 1 * *
+  workflow_dispatch:
+    logLevel:
+      description: "Log level"
+      required: true
+      default: "warning"
+
+jobs:
+  release:
+    runs-on: ubuntu-latest
+    env:
+      BRANCH_NAME: new-release-${{ github.run_id }}
+    steps:
+      - uses: actions/setup-python@v2
+        with:
+          python-version: 3.6
+      - name: Checkout master
+        uses: actions/checkout@v2
+        with:
+          fetch-depth: "0"
+      - name: Semantic release
+        id: semantic-release
+        run: |
+          pip install python-semantic-release
+          git config user.name github-actions
+          git config user.email [email protected]
+          semantic-release version
+          echo ::set-output name=version::$(semantic-release print-version --current)
+          semantic-release changelog > './CHANGELOG.md'
+      - name: Create release pull request
+        uses: peter-evans/create-pull-request@v3
+        with:
+          token: ${{ secrets.GITHUB_TOKEN }}
+          commit-message: Bumped version to ${{ steps.semantic-release.outputs.version }}
+          committer: github-actions <[email protected]>
+          author: github-actions <[email protected]>
+          signoff: true
+          branch: ${{ env.BRANCH_NAME }}
+          delete-branch: true
+          title: |
+            chore: Bumped version for release ${{ steps.semantic-release.outputs.version }}
+          body: |
+            Bumped version to ${{ steps.semantic-release.outputs.version }}
+          team-reviewers: amundsen-io/amundsen-committers
diff --git a/.github/workflows/publish_release.yml b/.github/workflows/publish_release.yml
@@ -0,0 +1,43 @@
+name: Publish Monthly Release
+
+on:
+  push:
+    branches:
+      - master
+    paths:
+      # triggered when version is bumped
+      - "setup.py"
+      - "CHANGELOG.md"
+jobs:
+  release:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v2
+      - name: Setup python 3.6
+        uses: actions/setup-python@v1
+        with:
+          python-version: 3.6
+      - name: Get version
+        id: vers
+        run: |
+          pip install python-semantic-release
+          echo ::set-output name=version::$(semantic-release print-version --current)
+      - name: Create release
+        id: create_release
+        uses: actions/create-release@v1
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+        with:
+          tag_name: ${{ steps.vers.outputs.version }}
+          release_name: New Features & Bug Fixes
+          body_path: ./CHANGELOG.md
+      - name: Add wheel dependency
+        run: pip install wheel
+      - name: Generate dist
+        run: python setup.py sdist bdist_wheel
+      - name: Publish to PyPI
+        uses: pypa/gh-action-pypi-publish@master
+        with:
+          user: __token__
+          password: ${{ secrets.pypi_password }}
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -0,0 +1,60 @@
+### Feature
+* Multi-yield transformers ([#396](https://github.com/amundsen-io/amundsendatabuilder/issues/396)) ([`49ae0ed`](https://github.com/amundsen-io/amundsendatabuilder/commit/49ae0ed253aabec38346d0f26479218dec62081f))
+* Atlas_search_extractor | :tada: Initial commit. ([#415](https://github.com/amundsen-io/amundsendatabuilder/issues/415)) ([`8c63307`](https://github.com/amundsen-io/amundsendatabuilder/commit/8c633072da81b7fb2e343aa31e6e7f9c3bfae07d))
+* Sample Feast job with ES publisher ([#425](https://github.com/amundsen-io/amundsendatabuilder/issues/425)) ([`453a18b`](https://github.com/amundsen-io/amundsendatabuilder/commit/453a18b9f70b94226bf01180d7e44b915ca2ddcf))
+* Adding CsvTableBadgeExtractor ([#417](https://github.com/amundsen-io/amundsendatabuilder/issues/417)) ([`592ee71`](https://github.com/amundsen-io/amundsendatabuilder/commit/592ee7139070c6e86ab8c3050ab72465ec9ee688))
+* Feast extractor ([#414](https://github.com/amundsen-io/amundsendatabuilder/issues/414)) ([`2343a90`](https://github.com/amundsen-io/amundsendatabuilder/commit/2343a90b09932a173cbef13ad912bd2e7864dea0))
+* Adding first pass of delta lake metadata extractor as well as a sample script on how it would be used. ([#351](https://github.com/amundsen-io/amundsendatabuilder/issues/351)) ([`e8679aa`](https://github.com/amundsen-io/amundsendatabuilder/commit/e8679aadbcf940fb1b422b1d44298a314f2e5f12))
+* Use parameters to allow special characters in neo4j cypher statement ([#382](https://github.com/amundsen-io/amundsendatabuilder/issues/382)) ([`6fd5035`](https://github.com/amundsen-io/amundsendatabuilder/commit/6fd503563d49157a4a2611ad66fca2680dc62c68))
+* Column level badges cont. ([#381](https://github.com/amundsen-io/amundsendatabuilder/issues/381)) ([`af4b512`](https://github.com/amundsen-io/amundsendatabuilder/commit/af4b51265e11d1ee9e8651cebeb0d00592eec2d5))
+* Support dashboard chart in search ([#383](https://github.com/amundsen-io/amundsendatabuilder/issues/383)) ([`6cced36`](https://github.com/amundsen-io/amundsendatabuilder/commit/6cced36bdccd7a007872928f4075f7528daa8449))
+* Column level badges ([#375](https://github.com/amundsen-io/amundsendatabuilder/issues/375)) ([`8beee3e`](https://github.com/amundsen-io/amundsendatabuilder/commit/8beee3ea2ba0a81f4cc321791b9185a4316d9193))
+* Added Dremio extractor ([#377](https://github.com/amundsen-io/amundsendatabuilder/issues/377)) ([`63f239f`](https://github.com/amundsen-io/amundsendatabuilder/commit/63f239fd793e6b362f1d9aa064862f23b4718c09))
+* Add an extractor for pulling user information from BambooHR ([#369](https://github.com/amundsen-io/amundsendatabuilder/issues/369)) ([`6802ab1`](https://github.com/amundsen-io/amundsendatabuilder/commit/6802ab13d18d9a3f27d54dd7a7e43b4c3606da39))
+* Add sample_glue_loader script ([#366](https://github.com/amundsen-io/amundsendatabuilder/issues/366)) ([`fa3f11b`](https://github.com/amundsen-io/amundsendatabuilder/commit/fa3f11b32560fe43d95bfcdab402832898858b44))
+* Parameterize Snowflake Schema in Snowflake Metadata Extractor ([#361](https://github.com/amundsen-io/amundsendatabuilder/issues/361)) ([`aa4416c`](https://github.com/amundsen-io/amundsendatabuilder/commit/aa4416c51668e887817d197edd5a7365f83446d3))
+* Mode Batch dashboard charrt API ([#362](https://github.com/amundsen-io/amundsendatabuilder/issues/362)) ([`87213c5`](https://github.com/amundsen-io/amundsendatabuilder/commit/87213c5ae45e1cbe116295eafa568a775d21a889))
+* Create a RedshiftMetadataExtractor that supports late binding views ([#356](https://github.com/amundsen-io/amundsendatabuilder/issues/356)) ([`4113cfd`](https://github.com/amundsen-io/amundsendatabuilder/commit/4113cfd309ddf633b42ae511b0f0215bd3642621))
+* Add MySQL sample data loader ([#359](https://github.com/amundsen-io/amundsendatabuilder/issues/359)) ([`871a176`](https://github.com/amundsen-io/amundsendatabuilder/commit/871a1763a7b0837bb6c0ba12810b9264aaa67d59))
+* Add Snowflake table last updated timestamp extractor ([#348](https://github.com/amundsen-io/amundsendatabuilder/issues/348)) ([`0bac11b`](https://github.com/amundsen-io/amundsendatabuilder/commit/0bac11bcb7cd1de974548d7d3428d209fb65d4f4))
+* Add Tableau dashboard metadata extractors ([#333](https://github.com/amundsen-io/amundsendatabuilder/issues/333)) ([`46207ee`](https://github.com/amundsen-io/amundsendatabuilder/commit/46207eee9bc50b7cb09e0effbff61edcb34e5d3b))
+* Add github actions for databuilder ([#336](https://github.com/amundsen-io/amundsendatabuilder/issues/336)) ([`236e7de`](https://github.com/amundsen-io/amundsendatabuilder/commit/236e7dec1d6f059e0227bf92ed6df457b448ee56))
+* Allow hive sql to be provided as config ([#312](https://github.com/amundsen-io/amundsendatabuilder/issues/312)) ([`8075a6c`](https://github.com/amundsen-io/amundsendatabuilder/commit/8075a6c7604c0f9c3491cdd85c0e1e97a7fd5b99))
+* Enhance glue extractor ([#306](https://github.com/amundsen-io/amundsendatabuilder/issues/306)) ([`faa795c`](https://github.com/amundsen-io/amundsendatabuilder/commit/faa795ce335e12323fb69b1041435df38034b158))
+* Add RedashDashboardExtractor for extracting dashboards from redash.io ([#300](https://github.com/amundsen-io/amundsendatabuilder/issues/300)) ([`f1b0dfa`](https://github.com/amundsen-io/amundsendatabuilder/commit/f1b0dfa399295124484242a666ddf2f20791aff7))
+* Add a transformer that adds tags to all tables created in a job ([#287](https://github.com/amundsen-io/amundsendatabuilder/issues/287)) ([`d2f4bd3`](https://github.com/amundsen-io/amundsendatabuilder/commit/d2f4bd308c1ef92ea2bbfb7a7443cb42113f03f9))
+
+### Fix
+* Move 'grouped_tables' into `_retrieve_tables` ([#430](https://github.com/amundsen-io/amundsendatabuilder/issues/430)) ([`26a0d0a`](https://github.com/amundsen-io/amundsendatabuilder/commit/26a0d0a4ffe5bf004507c9d1598a5f08b30ecdf0))
+* Address PyAthena version ([#429](https://github.com/amundsen-io/amundsendatabuilder/issues/429)) ([`7157c24`](https://github.com/amundsen-io/amundsendatabuilder/commit/7157c24305a48e124ac873529f54c0eabe5d5190))
+* Add csv badges back in Quickstart ([#418](https://github.com/amundsen-io/amundsendatabuilder/issues/418)) ([`c0296b7`](https://github.com/amundsen-io/amundsendatabuilder/commit/c0296b70de8aae4116fd3869233cd9de0d08fbbc))
+* Typo in Readme ([#424](https://github.com/amundsen-io/amundsendatabuilder/issues/424)) ([`29bd72f`](https://github.com/amundsen-io/amundsendatabuilder/commit/29bd72f442ce8feb002a6b56b39f38b099186604))
+* Fix redash dashboard exporter ([#422](https://github.com/amundsen-io/amundsendatabuilder/issues/422)) ([`fa626f5`](https://github.com/amundsen-io/amundsendatabuilder/commit/fa626f5cb2f92e5627c1a62ba5834b458ad0994d))
+* Update the key format of set 'grouped_tables' ([#421](https://github.com/amundsen-io/amundsendatabuilder/issues/421)) ([`4c9e5f7`](https://github.com/amundsen-io/amundsendatabuilder/commit/4c9e5f753bab6a21f116337005e995e1d38ef268))
+* Retry loop for exception caused by deadlock on badge node ([#404](https://github.com/amundsen-io/amundsendatabuilder/issues/404)) ([`9fd1513`](https://github.com/amundsen-io/amundsendatabuilder/commit/9fd1513b0eb0b7426d9ba8852f1e61457536adee))
+* FsNeo4jCSVLoader fails if nodes have disjoint keys ([#408](https://github.com/amundsen-io/amundsendatabuilder/issues/408)) ([`c07cec9`](https://github.com/amundsen-io/amundsendatabuilder/commit/c07cec9588e30e8c87682882417a72dca1d1866d))
+* Cast dashboard usage to be int ([#412](https://github.com/amundsen-io/amundsendatabuilder/issues/412)) ([`8bcc489`](https://github.com/amundsen-io/amundsendatabuilder/commit/8bcc4894c15d2de7f57e838668ff9709b97239ed))
+* Pandas 'nan' values ([#409](https://github.com/amundsen-io/amundsendatabuilder/issues/409)) ([`3a28f46`](https://github.com/amundsen-io/amundsendatabuilder/commit/3a28f46915e3757c8445f2dfe6b7714a7789820a))
+* Add databuilder missing dependencies ([#400](https://github.com/amundsen-io/amundsendatabuilder/issues/400)) ([`6718396`](https://github.com/amundsen-io/amundsendatabuilder/commit/6718396ed0aca467f61638c307822c18fbec6f65))
+* Allow BigQuery Usage Extractor to extract usage for views ([#399](https://github.com/amundsen-io/amundsendatabuilder/issues/399)) ([`8779229`](https://github.com/amundsen-io/amundsendatabuilder/commit/8779229ce8446408fff310fc9bb50f472f0eca87))
+* Hive metadata extractor not work on postgresql ([#394](https://github.com/amundsen-io/amundsendatabuilder/issues/394)) ([`2992618`](https://github.com/amundsen-io/amundsendatabuilder/commit/2992618d5d29e7061755dd62acba0eb53635fc1b))
+* Issues with inconsistency in case conversion ([#388](https://github.com/amundsen-io/amundsendatabuilder/issues/388)) ([`9595866`](https://github.com/amundsen-io/amundsendatabuilder/commit/95958660e72b9c17f491f6e09994a47a84b55697))
+* Update elasticsearch table index mapping ([#373](https://github.com/amundsen-io/amundsendatabuilder/issues/373)) ([`88c0552`](https://github.com/amundsen-io/amundsendatabuilder/commit/88c055228412aa36ab0f9d82b57b6442d7064b7c))
+* Fix programmatic source data ([#367](https://github.com/amundsen-io/amundsendatabuilder/issues/367)) ([`4f5df39`](https://github.com/amundsen-io/amundsendatabuilder/commit/4f5df39cd6ddf05d2347b6d2b280f5cf0fdda5b9))
+* Update connection string in Snowflake extractor to include wareh… ([#357](https://github.com/amundsen-io/amundsendatabuilder/issues/357)) ([`a11d206`](https://github.com/amundsen-io/amundsendatabuilder/commit/a11d20698fce49fbba97040d12411181aff0b194))
+* Edge case in Snowflake information_schema.last_altered value ([#360](https://github.com/amundsen-io/amundsendatabuilder/issues/360)) ([`c3e713e`](https://github.com/amundsen-io/amundsendatabuilder/commit/c3e713e7f39e7240f3038daa3a3937fb060dbecb))
+* Correct typo in Snowflake Last Updated extract query ([#358](https://github.com/amundsen-io/amundsendatabuilder/issues/358)) ([`5c2e98e`](https://github.com/amundsen-io/amundsendatabuilder/commit/5c2e98eb81aa9875f48b3e20eb5bef84ed9c481f))
+* Set Tableau URLs (base + API) via config ([#349](https://github.com/amundsen-io/amundsendatabuilder/issues/349)) ([`1baec33`](https://github.com/amundsen-io/amundsendatabuilder/commit/1baec33899df8394b42b6a667ff2a5d1224b8528))
+* Fix invalid timestamp handling in dashboard transformer ([#339](https://github.com/amundsen-io/amundsendatabuilder/issues/339)) ([`030ef49`](https://github.com/amundsen-io/amundsendatabuilder/commit/030ef4995d16711c35e205c213f90b3d72ff1499))
+* Update postgres_sample_dag to set table extract job as upstream for elastic search publisher ([#340](https://github.com/amundsen-io/amundsendatabuilder/issues/340)) ([`c79935e`](https://github.com/amundsen-io/amundsendatabuilder/commit/c79935e01efdc8c9734727e07238f25c545bfd5d))
+* **deps:** Unpin attrs ([#332](https://github.com/amundsen-io/amundsendatabuilder/issues/332)) ([`86f658d`](https://github.com/amundsen-io/amundsendatabuilder/commit/86f658d1ea9750ad916a91056a678e34a71654fb))
+* Cypher statement param issue in Neo4jStalenessRemovalTask ([#307](https://github.com/amundsen-io/amundsendatabuilder/issues/307)) ([`0078761`](https://github.com/amundsen-io/amundsendatabuilder/commit/0078761dc94c33c785557df09bb86411ef8f6f46))
+* Added missing job tag key in hive_sample_dag.py ([#308](https://github.com/amundsen-io/amundsendatabuilder/issues/308)) ([`d6714b7`](https://github.com/amundsen-io/amundsendatabuilder/commit/d6714b72c75328195a51a6a456d1ab46063243b0))
+* Fix sql for missing columns and mysql based dialects (#550) ([#305](https://github.com/amundsen-io/amundsendatabuilder/issues/305)) ([`4b7b147`](https://github.com/amundsen-io/amundsendatabuilder/commit/4b7b147b1d32cd8fce6aa7c24fa1db8d823b8038))
+* Escape backslashes in Neo4jCsvPublisher  ([`1faa713`](https://github.com/amundsen-io/amundsendatabuilder/commit/1faa713374c88cf0eb04f744908756c1ef70206e))
+* Variable organization in Model URL ([#293](https://github.com/amundsen-io/amundsendatabuilder/issues/293)) ([`b4c24ef`](https://github.com/amundsen-io/amundsendatabuilder/commit/b4c24ef891ba13fc4678faef0faaa5c7bf4c5cb6))
+
+### Documentation
+* Update DashboardMetadata docs ([#402](https://github.com/amundsen-io/amundsendatabuilder/issues/402)) ([`093b3d6`](https://github.com/amundsen-io/amundsendatabuilder/commit/093b3d6fbe40040b6f720c030aa6d8504178b0ea))
+* Fix broken doc link to dashboard_execution model ([#296](https://github.com/amundsen-io/amundsendatabuilder/issues/296)) ([`24b3b0a`](https://github.com/amundsen-io/amundsendatabuilder/commit/24b3b0afdf4ad3c6b13f9677d9f805ff43f42de7))
+* Fix README.md ([#301](https://github.com/amundsen-io/amundsendatabuilder/issues/301)) ([`ad5765a`](https://github.com/amundsen-io/amundsendatabuilder/commit/ad5765a1cb0ae5fceffb1168876031801b44a79f))
diff --git a/README.md b/README.md
@@ -444,6 +444,15 @@ job = DefaultJob(
 job.launch()
 ```
 
+#### [VerticaMetadataExtractor](https://github.com/amundsen-io/amundsendatabuilder/blob/master/databuilder/extractor/vertica_metadata_extractor.py "MysqlMetadataExtractor")
+An extractor that extracts table and column metadata including database, schema, table name, column name and column datatype from a Vertica database.
+
+A sample loading script for Vertica is provided [here](https://github.com/amundsen-io/amundsendatabuilder/blob/master/databuilder/extractor/databuilder/example/scripts/sample_vertica_loader.py)
+
+By default, the Vertica database name is used as the cluster name. The `where_clause_suffix` in the example can be used to define which schemas you would like to query.
+
+
+
 #### [SQLAlchemyExtractor](https://github.com/amundsen-io/amundsendatabuilder/blob/master/databuilder/extractor/sql_alchemy_extractor.py "SQLAlchemyExtractor")
 An extractor utilizes [SQLAlchemy](https://www.sqlalchemy.org/ "SQLAlchemy") to extract record from any database that support SQL Alchemy.
 ```python
@@ -938,8 +947,15 @@ job.launch()
 
 
 ## List of transformers
+
+Transformers are implemented by subclassing [Transformer](https://github.com/amundsen-io/amundsendatabuilder/blob/master/databuilder/transformer/base_transformer.py#L12 "Transformer") and implementing `transform(self, record)`. A transformer can:
+
+- Modify a record and return it,
+- Return `None` to filter a record out,
+- Yield multiple records. This is useful for e.g. inferring metadata (such as ownership) from table descriptions.
+
 #### [ChainedTransformer](https://github.com/amundsen-io/amundsendatabuilder/blob/master/databuilder/transformer/base_transformer.py#L41 "ChainedTransformer")
-A chanined transformer that can take multiple transformer.
+A chanined transformer that can take multiple transformers, passing each record through the chain.
 
 #### [RegexStrReplaceTransformer](https://github.com/amundsen-io/amundsendatabuilder/blob/master/databuilder/transformer/regex_str_replace_transformer.py "RegexStrReplaceTransformer")
 Generic string replacement transformer using REGEX. User can pass list of tuples where tuple contains regex and replacement pair.

diff --git a/databuilder/extractor/dashboard/redash/redash_dashboard_extractor.py b/databuilder/extractor/dashboard/redash/redash_dashboard_extractor.py
@@ -107,7 +107,7 @@ def _get_extract_iter(self) -> Iterator[Any]:
             if not record:
                 break  # the end.
 
-            record = self._transformer.transform(record=record)
+            record = next(self._transformer.transform(record=record), None)
 
             if not self._is_published_dashboard(record):
                 continue  # filter this one out

diff --git a/databuilder/extractor/dashboard/tableau/tableau_dashboard_extractor.py b/databuilder/extractor/dashboard/tableau/tableau_dashboard_extractor.py
@@ -110,7 +110,7 @@ def extract(self) -> Any:
         if not record:
             return None
 
-        return self._transformer.transform(record=record)
+        return next(self._transformer.transform(record=record), None)
 
     def get_scope(self) -> str:
         return 'extractor.tableau_dashboard_metadata'

diff --git a/databuilder/extractor/dashboard/tableau/tableau_dashboard_last_modified_extractor.py b/databuilder/extractor/dashboard/tableau/tableau_dashboard_last_modified_extractor.py
@@ -100,7 +100,7 @@ def extract(self) -> Any:
         if not record:
             return None
 
-        return self._transformer.transform(record=record)
+        return next(self._transformer.transform(record=record), None)
 
     def get_scope(self) -> str:
         return 'extractor.tableau_dashboard_last_modified'

diff --git a/databuilder/extractor/dashboard/tableau/tableau_dashboard_query_extractor.py b/databuilder/extractor/dashboard/tableau/tableau_dashboard_query_extractor.py
@@ -97,7 +97,7 @@ def extract(self) -> Any:
         if not record:
             return None
 
-        return self._transformer.transform(record=record)
+        return next(self._transformer.transform(record=record), None)
 
     def get_scope(self) -> str:
         return 'extractor.tableau_dashboard_query'

diff --git a/databuilder/extractor/dashboard/tableau/tableau_dashboard_table_extractor.py b/databuilder/extractor/dashboard/tableau/tableau_dashboard_table_extractor.py
@@ -137,7 +137,7 @@ def extract(self) -> Any:
         if not record:
             return None
 
-        return self._transformer.transform(record=record)
+        return next(self._transformer.transform(record=record), None)
 
     def get_scope(self) -> str:
         return 'extractor.tableau_dashboard_table'

diff --git a/databuilder/extractor/hive_table_metadata_extractor.py b/databuilder/extractor/hive_table_metadata_extractor.py
@@ -105,7 +105,7 @@ def init(self, conf: ConfigTree) -> None:
 
         self.sql_stmt = conf.get_string(HiveTableMetadataExtractor.EXTRACT_SQL, default=default_sql)
 
-        LOGGER.info('SQL for hive metastore: %i', self.sql_stmt)
+        LOGGER.info('SQL for hive metastore: %s', self.sql_stmt)
 
         sql_alch_conf = sql_alch_conf.with_fallback(ConfigFactory.from_dict(
             {SQLAlchemyExtractor.EXTRACT_SQL: self.sql_stmt}))