[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 <gurwls223@gmail.com>

Closes #12226 from HyukjinKwon/SPARK-14103-quote.

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

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

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

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

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

sql/core/pom.xml

@@ -39,7 +39,7 @@
     <dependency>
       <groupId>com.univocity</groupId>
       <artifactId>univocity-parsers</artifactId>
-      <version>1.5.6</version>
+      <version>2.0.2</version>
       <type>jar</type>
     </dependency>
     <dependency>

sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/csv/CSVParser.scala

@@ -47,6 +47,7 @@ private[sql] abstract class CsvReader(params: CSVOptions, headers: Seq[String])
     settings.setMaxColumns(params.maxColumns)
     settings.setNullValue(params.nullValue)
     settings.setMaxCharsPerColumn(params.maxCharsPerColumn)
+    settings.setParseUnescapedQuotesUntilDelimiter(true)
     if (headers != null) settings.setHeaders(headers: _*)
 
     new CsvParser(settings)

sql/core/src/test/resources/unescaped-quotes.csv

+"a"b,ccc,ddd
+ab,cc"c,ddd"

sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/csv/CSVSuite.scala

@@ -45,6 +45,7 @@ class CSVSuite extends QueryTest with SharedSQLContext with SQLTestUtils {
   private val disableCommentsFile = "disable_comments.csv"
   private val boolFile = "bool.csv"
   private val simpleSparseFile = "simple_sparse.csv"
+  private val unescapedQuotesFile = "unescaped-quotes.csv"
 
   private def testFile(fileName: String): String = {
     Thread.currentThread().getContextClassLoader.getResource(fileName).toString
@@ -140,6 +141,17 @@ class CSVSuite extends QueryTest with SharedSQLContext with SQLTestUtils {
     verifyCars(cars, withHeader = true)
   }
 
+  test("parse unescaped quotes with maxCharsPerColumn") {
+    val rows = sqlContext.read
+      .format("csv")
+      .option("maxCharsPerColumn", "4")
+      .load(testFile(unescapedQuotesFile))
+
+    val expectedRows = Seq(Row("\"a\"b", "ccc", "ddd"), Row("ab", "cc\"c", "ddd\""))
+
+    checkAnswer(rows, expectedRows)
+  }
+
   test("bad encoding name") {
     val exception = intercept[UnsupportedCharsetException] {
       sqlContext