lanyuanxiaoyao/hudi
1
0
Fork 0
Code Activity

[HUDI-242] Support for RFC-12/Bootstrapping of external datasets to hudi (#1876)

Browse Source 
- [HUDI-418] Bootstrap Index Implementation using HFile with unit-test
 - [HUDI-421] FileSystem View Changes to support Bootstrap with unit-tests
 - [HUDI-424] Implement Query Side Integration for querying tables containing bootstrap file slices
 - [HUDI-423] Implement upsert functionality for handling updates to these bootstrap file slices
 - [HUDI-421] Bootstrap Write Client with tests
 - [HUDI-425] Added HoodieDeltaStreamer support
 - [HUDI-899] Add a knob to change partition-path style while performing metadata bootstrap
 - [HUDI-900] Metadata Bootstrap Key Generator needs to handle complex keys correctly
 - [HUDI-424] Simplify Record reader implementation
 - [HUDI-423] Implement upsert functionality for handling updates to these bootstrap file slices
 - [HUDI-420] Hoodie Demo working with hive and sparkSQL. Also, Hoodie CLI working with bootstrap tables

Co-authored-by: Mehrotra <uditme@amazon.com>
Co-authored-by: Vinoth Chandar <vinoth@apache.org>
Co-authored-by: Balaji Varadarajan <varadarb@uber.com>
This commit is contained in:
vinoth chandar
2020-08-03 20:19:21 -07:00
committed by GitHub
parent 266bce12b3
commit 539621bd33
175 changed files with 7540 additions and 779 deletions
Download Patch File Download Diff File Expand all files Collapse all files

34
docker/demo/sparksql-incremental.commands
View File

@@ -52,8 +52,38 @@ spark.sql("select key, `_hoodie_partition_path` as datestr, symbol, ts, open, cl
mode(SaveMode.Overwrite).
save("/user/hive/warehouse/stock_ticks_derived_mor");
spark.sql("show tables").show(20, false)
spark.sql("select count(*) from stock_ticks_derived_mor_ro").show(20, false)
spark.sql("select count(*) from stock_ticks_derived_mor_rt").show(20, false)
System.exit(0);
val hoodieIncQueryBsDF = spark.read.format("org.apache.hudi").
option(DataSourceReadOptions.QUERY_TYPE_OPT_KEY, DataSourceReadOptions.QUERY_TYPE_INCREMENTAL_OPT_VAL).
option(DataSourceReadOptions.BEGIN_INSTANTTIME_OPT_KEY, "00000000000001").
load("/user/hive/warehouse/stock_ticks_cow_bs");
hoodieIncQueryBsDF.registerTempTable("stock_ticks_cow_bs_incr")
spark.sql("select `_hoodie_commit_time`, symbol, ts, volume, open, close from stock_ticks_cow_bs_incr where symbol = 'GOOG'").show(100, false);
spark.sql("select key, `_hoodie_partition_path` as datestr, symbol, ts, open, close from stock_ticks_cow_bs_incr").
write.format("org.apache.hudi").
option("hoodie.insert.shuffle.parallelism", "2").
option("hoodie.upsert.shuffle.parallelism","2").
option(DataSourceWriteOptions.TABLE_TYPE_OPT_KEY, DataSourceWriteOptions.MOR_TABLE_TYPE_OPT_VAL).
option(DataSourceWriteOptions.OPERATION_OPT_KEY, DataSourceWriteOptions.UPSERT_OPERATION_OPT_VAL).
option(DataSourceWriteOptions.RECORDKEY_FIELD_OPT_KEY, "key").
option(DataSourceWriteOptions.PARTITIONPATH_FIELD_OPT_KEY, "datestr").
option(DataSourceWriteOptions.PRECOMBINE_FIELD_OPT_KEY, "ts").
option(HoodieWriteConfig.TABLE_NAME, "stock_ticks_derived_mor_bs").
option(DataSourceWriteOptions.HIVE_TABLE_OPT_KEY, "stock_ticks_derived_mor_bs").
option(DataSourceWriteOptions.HIVE_DATABASE_OPT_KEY, "default").
option(DataSourceWriteOptions.HIVE_URL_OPT_KEY, "jdbc:hive2://hiveserver:10000").
option(DataSourceWriteOptions.HIVE_USER_OPT_KEY, "hive").
option(DataSourceWriteOptions.HIVE_PASS_OPT_KEY, "hive").
option(DataSourceWriteOptions.HIVE_SYNC_ENABLED_OPT_KEY, "true").
option(DataSourceWriteOptions.HIVE_PARTITION_FIELDS_OPT_KEY, "datestr").
mode(SaveMode.Overwrite).
save("/user/hive/warehouse/stock_ticks_derived_mor_bs");
spark.sql("show tables").show(20, false)
spark.sql("select count(*) from stock_ticks_derived_mor_bs_ro").show(20, false)
spark.sql("select count(*) from stock_ticks_derived_mor_bs_rt").show(20, false)
System.exit(0);