[SPARK-17805][PYSPARK] Fix in sqlContext.read.text when pass in list …

…of paths

## What changes were proposed in this pull request?
If given a list of paths, `pyspark.sql.readwriter.text` will attempt to use an undefined variable `paths`.  This change checks if the param `paths` is a basestring and then converts it to a list, so that the same variable `paths` can be used for both cases

## How was this patch tested?
Added unit test for reading list of files

Author: Bryan Cutler <cutlerb@gmail.com>

Closes #15379 from BryanCutler/sql-readtext-paths-SPARK-17805.

python/pyspark/sql/readwriter.py

@@ -289,8 +289,8 @@ def text(self, paths):
         [Row(value=u'hello'), Row(value=u'this')]
         """
         if isinstance(paths, basestring):
-            path = [paths]
-        return self._df(self._jreader.text(self._spark._sc._jvm.PythonUtils.toSeq(path)))
+            paths = [paths]
+        return self._df(self._jreader.text(self._spark._sc._jvm.PythonUtils.toSeq(paths)))
 
     @since(2.0)
     def csv(self, path, schema=None, sep=None, encoding=None, quote=None, escape=None,

python/pyspark/sql/tests.py

@@ -1702,6 +1702,12 @@ def test_cache(self):
             "does_not_exist",
             lambda: spark.catalog.uncacheTable("does_not_exist"))
 
+    def test_read_text_file_list(self):
+        df = self.spark.read.text(['python/test_support/sql/text-test.txt',
+                                   'python/test_support/sql/text-test.txt'])
+        count = df.count()
+        self.assertEquals(count, 4)
+
 
 class HiveSparkSubmitTests(SparkSubmitTests):