From 725b860e2b7b675d95b10c46f2b329c30cd21faf Mon Sep 17 00:00:00 2001 From: hyukjinkwon Date: Fri, 8 Apr 2016 00:28:59 -0700 Subject: [SPARK-14103][SQL] Parse unescaped quotes in CSV data source. ## What changes were proposed in this pull request? This PR resolves the problem during parsing unescaped quotes in input data. For example, currently the data below: ``` "a"b,ccc,ddd e,f,g ``` produces a data below: - **Before** ```bash ["a"b,ccc,ddd[\n]e,f,g] <- as a value. ``` - **After** ```bash ["a"b], [ccc], [ddd] [e], [f], [g] ``` This PR bumps up the Univocity parser's version. This was fixed in `2.0.2`, https://github.com/uniVocity/univocity-parsers/issues/60. ## How was this patch tested? Unit tests in `CSVSuite` and `sbt/sbt scalastyle`. Author: hyukjinkwon Closes #12226 from HyukjinKwon/SPARK-14103-quote. --- dev/deps/spark-deps-hadoop-2.2 | 2 +- dev/deps/spark-deps-hadoop-2.3 | 2 +- dev/deps/spark-deps-hadoop-2.4 | 2 +- dev/deps/spark-deps-hadoop-2.6 | 2 +- dev/deps/spark-deps-hadoop-2.7 | 2 +- 5 files changed, 5 insertions(+), 5 deletions(-) (limited to 'dev') diff --git a/dev/deps/spark-deps-hadoop-2.2 b/dev/deps/spark-deps-hadoop-2.2 index 2c24366cc3..2794b3d235 100644 --- a/dev/deps/spark-deps-hadoop-2.2 +++ b/dev/deps/spark-deps-hadoop-2.2 @@ -175,7 +175,7 @@ stax-api-1.0.1.jar stream-2.7.0.jar stringtemplate-3.2.1.jar super-csv-2.2.0.jar -univocity-parsers-1.5.6.jar +univocity-parsers-2.0.2.jar xbean-asm5-shaded-4.4.jar xmlenc-0.52.jar xz-1.0.jar diff --git a/dev/deps/spark-deps-hadoop-2.3 b/dev/deps/spark-deps-hadoop-2.3 index e9cb0d8f3e..4906fe9cfa 100644 --- a/dev/deps/spark-deps-hadoop-2.3 +++ b/dev/deps/spark-deps-hadoop-2.3 @@ -166,7 +166,7 @@ stax-api-1.0.1.jar stream-2.7.0.jar stringtemplate-3.2.1.jar super-csv-2.2.0.jar -univocity-parsers-1.5.6.jar +univocity-parsers-2.0.2.jar xbean-asm5-shaded-4.4.jar xmlenc-0.52.jar xz-1.0.jar diff --git a/dev/deps/spark-deps-hadoop-2.4 b/dev/deps/spark-deps-hadoop-2.4 index d8d1840da5..23ff5cfa2e 100644 --- a/dev/deps/spark-deps-hadoop-2.4 +++ b/dev/deps/spark-deps-hadoop-2.4 @@ -167,7 +167,7 @@ stax-api-1.0.1.jar stream-2.7.0.jar stringtemplate-3.2.1.jar super-csv-2.2.0.jar -univocity-parsers-1.5.6.jar +univocity-parsers-2.0.2.jar xbean-asm5-shaded-4.4.jar xmlenc-0.52.jar xz-1.0.jar diff --git a/dev/deps/spark-deps-hadoop-2.6 b/dev/deps/spark-deps-hadoop-2.6 index 8beede1e38..9b5a5643f3 100644 --- a/dev/deps/spark-deps-hadoop-2.6 +++ b/dev/deps/spark-deps-hadoop-2.6 @@ -173,7 +173,7 @@ stax-api-1.0.1.jar stream-2.7.0.jar stringtemplate-3.2.1.jar super-csv-2.2.0.jar -univocity-parsers-1.5.6.jar +univocity-parsers-2.0.2.jar xbean-asm5-shaded-4.4.jar xercesImpl-2.9.1.jar xmlenc-0.52.jar diff --git a/dev/deps/spark-deps-hadoop-2.7 b/dev/deps/spark-deps-hadoop-2.7 index a9d814f944..1dca2fc55a 100644 --- a/dev/deps/spark-deps-hadoop-2.7 +++ b/dev/deps/spark-deps-hadoop-2.7 @@ -174,7 +174,7 @@ stax-api-1.0.1.jar stream-2.7.0.jar stringtemplate-3.2.1.jar super-csv-2.2.0.jar -univocity-parsers-1.5.6.jar +univocity-parsers-2.0.2.jar xbean-asm5-shaded-4.4.jar xercesImpl-2.9.1.jar xmlenc-0.52.jar -- cgit v1.2.3