From 0578ff9681edbaab4ae68f67272dc3d4d890d53b Mon Sep 17 00:00:00 2001 From: Sean Owen <sowen@cloudera.com> Date: Wed, 10 Aug 2016 10:14:43 +0100 Subject: [PATCH] [SPARK-16324][SQL] regexp_extract should doc that it returns empty string when match fails ## What changes were proposed in this pull request? Doc that regexp_extract returns empty string when regex or group does not match ## How was this patch tested? Jenkins test, with a few new test cases Author: Sean Owen <sowen@cloudera.com> Closes #14525 from srowen/SPARK-16324. --- python/pyspark/sql/functions.py | 6 +++++- .../src/main/scala/org/apache/spark/sql/functions.scala | 3 ++- .../scala/org/apache/spark/sql/StringFunctionsSuite.scala | 4 ++++ 3 files changed, 11 insertions(+), 2 deletions(-) diff --git a/python/pyspark/sql/functions.py b/python/pyspark/sql/functions.py index 8a01805ec8..4ea83e24bb 100644 --- a/python/pyspark/sql/functions.py +++ b/python/pyspark/sql/functions.py @@ -1440,11 +1440,15 @@ def split(str, pattern): @ignore_unicode_prefix @since(1.5) def regexp_extract(str, pattern, idx): - """Extract a specific(idx) group identified by a java regex, from the specified string column. + """Extract a specific group matched by a Java regex, from the specified string column. + If the regex did not match, or the specified group did not match, an empty string is returned. >>> df = spark.createDataFrame([('100-200',)], ['str']) >>> df.select(regexp_extract('str', '(\d+)-(\d+)', 1).alias('d')).collect() [Row(d=u'100')] + >>> df = spark.createDataFrame([('foo',)], ['str']) + >>> df.select(regexp_extract('str', '(\d+)', 1).alias('d')).collect() + [Row(d=u'')] >>> df = spark.createDataFrame([('aaaac',)], ['str']) >>> df.select(regexp_extract('str', '(a+)(b)?(c)', 2).alias('d')).collect() [Row(d=u'')] diff --git a/sql/core/src/main/scala/org/apache/spark/sql/functions.scala b/sql/core/src/main/scala/org/apache/spark/sql/functions.scala index 81f6ed75e6..18e736ab69 100644 --- a/sql/core/src/main/scala/org/apache/spark/sql/functions.scala +++ b/sql/core/src/main/scala/org/apache/spark/sql/functions.scala @@ -2175,7 +2175,8 @@ object functions { def ltrim(e: Column): Column = withExpr {StringTrimLeft(e.expr) } /** - * Extract a specific(idx) group identified by a java regex, from the specified string column. + * Extract a specific group matched by a Java regex, from the specified string column. + * If the regex did not match, or the specified group did not match, an empty string is returned. * * @group string_funcs * @since 1.5.0 diff --git a/sql/core/src/test/scala/org/apache/spark/sql/StringFunctionsSuite.scala b/sql/core/src/test/scala/org/apache/spark/sql/StringFunctionsSuite.scala index 64b4718538..1cc77464b9 100644 --- a/sql/core/src/test/scala/org/apache/spark/sql/StringFunctionsSuite.scala +++ b/sql/core/src/test/scala/org/apache/spark/sql/StringFunctionsSuite.scala @@ -96,6 +96,10 @@ class StringFunctionsSuite extends QueryTest with SharedSQLContext { test("non-matching optional group") { val df = Seq(Tuple1("aaaac")).toDF("s") + checkAnswer( + df.select(regexp_extract($"s", "(foo)", 1)), + Row("") + ) checkAnswer( df.select(regexp_extract($"s", "(a+)(b)?(c)", 2)), Row("") -- GitLab