diff --git a/README.md b/README.md index 754d68ce..647904d8 100644 --- a/README.md +++ b/README.md @@ -74,13 +74,13 @@ You can link against this library in your program at the following coordinates: -
groupId: za.co.absa.cobrix
artifactId: spark-cobol_2.11
version: 2.8.1
+
groupId: za.co.absa.cobrix
artifactId: spark-cobol_2.11
version: 2.8.2
-
groupId: za.co.absa.cobrix
artifactId: spark-cobol_2.12
version: 2.8.1
+
groupId: za.co.absa.cobrix
artifactId: spark-cobol_2.12
version: 2.8.2
-
groupId: za.co.absa.cobrix
artifactId: spark-cobol_2.13
version: 2.8.1
+
groupId: za.co.absa.cobrix
artifactId: spark-cobol_2.13
version: 2.8.2
@@ -91,17 +91,17 @@ This package can be added to Spark using the `--packages` command line option. F ### Spark compiled with Scala 2.11 ``` -$SPARK_HOME/bin/spark-shell --packages za.co.absa.cobrix:spark-cobol_2.11:2.8.1 +$SPARK_HOME/bin/spark-shell --packages za.co.absa.cobrix:spark-cobol_2.11:2.8.2 ``` ### Spark compiled with Scala 2.12 ``` -$SPARK_HOME/bin/spark-shell --packages za.co.absa.cobrix:spark-cobol_2.12:2.8.1 +$SPARK_HOME/bin/spark-shell --packages za.co.absa.cobrix:spark-cobol_2.12:2.8.2 ``` ### Spark compiled with Scala 2.13 ``` -$SPARK_HOME/bin/spark-shell --packages za.co.absa.cobrix:spark-cobol_2.13:2.8.1 +$SPARK_HOME/bin/spark-shell --packages za.co.absa.cobrix:spark-cobol_2.13:2.8.2 ``` ## Usage @@ -237,8 +237,8 @@ Cobrix's `spark-cobol` data source depends on the COBOL parser that is a part of The jars that you need to get are: -* spark-cobol_2.12-2.8.1.jar -* cobol-parser_2.12-2.8.1.jar +* spark-cobol_2.12-2.8.2.jar +* cobol-parser_2.12-2.8.2.jar > Versions older than 2.8.0 also need `scodec-core_2.12-1.10.3.jar` and `scodec-bits_2.12-1.1.4.jar`. @@ -246,9 +246,9 @@ The jars that you need to get are: After that you can specify these jars in `spark-shell` command line. Here is an example: ``` -$ spark-shell --packages za.co.absa.cobrix:spark-cobol_2.12:2.8.1 +$ spark-shell --packages za.co.absa.cobrix:spark-cobol_2.12:2.8.2 or -$ spark-shell --master yarn --deploy-mode client --driver-cores 4 --driver-memory 4G --jars spark-cobol_2.12-2.8.1.jar,cobol-parser_2.12-2.8.1.jar +$ spark-shell --master yarn --deploy-mode client --driver-cores 4 --driver-memory 4G --jars spark-cobol_2.12-2.8.2.jar,cobol-parser_2.12-2.8.2.jar Setting default log level to "WARN". To adjust logging level use sc.setLogLevel(newLevel). For SparkR, use setLogLevel(newLevel). @@ -319,7 +319,7 @@ The fat jar will have '-bundle' suffix. You can also download pre-built bundles Then, run `spark-shell` or `spark-submit` adding the fat jar as the option. ```sh -$ spark-shell --jars spark-cobol_2.12_3.3-2.8.2-SNAPSHOT-bundle.jar +$ spark-shell --jars spark-cobol_2.12_3.3-2.8.3-SNAPSHOT-bundle.jar ``` > A note for building and running tests on Windows @@ -1791,6 +1791,15 @@ at org.apache.hadoop.io.nativeio.NativeIO$POSIX.getStat(NativeIO.java:608) A: Update hadoop dll to version 3.2.2 or newer. ## Changelog +- #### 2.8.2 released 25 February 2025. + - [#744](https://github.com/AbsaOSS/cobrix/issues/744) Added the ability to specify default record length for the record length field mapping: + The default record length can be specified by assigning a value to the underscore key `"_"`. For example: + ```scala + .option("record_format", "F") + .option("record_length_field", "RECORD_TYPE") + .option("record_length_map", """{"A":100,"B":200,"_":500}""") + ``` + - #### 2.8.1 released 27 January 2025. - [#730](https://github.com/AbsaOSS/cobrix/issues/730) Added more code pages with euro character in https://github.com/AbsaOSS/cobrix/pull/741. - [#740](https://github.com/AbsaOSS/cobrix/issues/740) Extended binary type support to make sure unsigned binary fields can fit Spark data types in https://github.com/AbsaOSS/cobrix/pull/742. diff --git a/cobol-converters/pom.xml b/cobol-converters/pom.xml index b9aba2cd..46004ab0 100644 --- a/cobol-converters/pom.xml +++ b/cobol-converters/pom.xml @@ -22,7 +22,7 @@ za.co.absa.cobrix cobrix_2.12 - 2.8.2-SNAPSHOT + 2.8.3-SNAPSHOT ../pom.xml diff --git a/cobol-parser/pom.xml b/cobol-parser/pom.xml index 629b7c39..9bf6cdd0 100644 --- a/cobol-parser/pom.xml +++ b/cobol-parser/pom.xml @@ -22,7 +22,7 @@ za.co.absa.cobrix cobrix_2.12 - 2.8.2-SNAPSHOT + 2.8.3-SNAPSHOT ../pom.xml diff --git a/examples/examples-collection/pom.xml b/examples/examples-collection/pom.xml index 0617639e..e2ae59d8 100644 --- a/examples/examples-collection/pom.xml +++ b/examples/examples-collection/pom.xml @@ -31,7 +31,7 @@ 2.11 2.4.8 2.4.16 - 2.8.1 + 2.8.2 diff --git a/examples/spark-cobol-app/build.sbt b/examples/spark-cobol-app/build.sbt index 283fbe88..f4d0b7d6 100644 --- a/examples/spark-cobol-app/build.sbt +++ b/examples/spark-cobol-app/build.sbt @@ -20,7 +20,7 @@ ThisBuild / version := "0.1.0-SNAPSHOT" ThisBuild / scalaVersion := "2.12.17" val sparkVersion = "3.5.3" -val sparkCobolVersion = "2.8.1" +val sparkCobolVersion = "2.8.2" val scalatestVersion = "3.2.14" ThisBuild / libraryDependencies ++= Seq( diff --git a/examples/spark-cobol-app/pom.xml b/examples/spark-cobol-app/pom.xml index b4f1398d..e439de22 100755 --- a/examples/spark-cobol-app/pom.xml +++ b/examples/spark-cobol-app/pom.xml @@ -31,7 +31,7 @@ 2.12 3.2.14 3.5.3 - 2.8.1 + 2.8.2 diff --git a/pom.xml b/pom.xml index ec3d371e..037e0532 100644 --- a/pom.xml +++ b/pom.xml @@ -22,7 +22,7 @@ za.co.absa.cobrix cobrix_2.12 - 2.8.2-SNAPSHOT + 2.8.3-SNAPSHOT pom diff --git a/spark-cobol/pom.xml b/spark-cobol/pom.xml index 024f6113..27ce7cc2 100644 --- a/spark-cobol/pom.xml +++ b/spark-cobol/pom.xml @@ -22,7 +22,7 @@ za.co.absa.cobrix cobrix_2.12 - 2.8.2-SNAPSHOT + 2.8.3-SNAPSHOT ../pom.xml