You are viewing a plain text version of this content. The canonical link for it is here.
Posted to reviews@spark.apache.org by "shujingyang-db (via GitHub)" <gi...@apache.org> on 2023/12/04 18:46:51 UTC
[PR] [SPARK-46248]XML: Support for ignoreCorruptFiles and ignoreMissingFiles options [spark]
shujingyang-db opened a new pull request, #44163:
URL: https://github.com/apache/spark/pull/44163
<!--
Thanks for sending a pull request! Here are some tips for you:
1. If this is your first time, please read our contributor guidelines: https://spark.apache.org/contributing.html
2. Ensure you have added or run the appropriate tests for your PR: https://spark.apache.org/developer-tools.html
3. If the PR is unfinished, add '[WIP]' in your PR title, e.g., '[WIP][SPARK-XXXX] Your PR title ...'.
4. Be sure to keep the PR description updated to reflect all changes.
5. Please write your PR title to summarize what this PR proposes.
6. If possible, provide a concise example to reproduce the issue for a faster review.
7. If you want to add a new configuration, please read the guideline first for naming configurations in
'core/src/main/scala/org/apache/spark/internal/config/ConfigEntry.scala'.
8. If you want to add or modify an error type or message, please read the guideline first in
'core/src/main/resources/error/README.md'.
-->
### What changes were proposed in this pull request?
<!--
Please clarify what changes you are proposing. The purpose of this section is to outline the changes and how this PR fixes the issue.
If possible, please consider writing useful notes for better and faster reviews in your PR. See the examples below.
1. If you refactor some codes with changing classes, showing the class hierarchy will help reviewers.
2. If you fix some SQL features, you can provide some references of other DBMSes.
3. If there is design documentation, please add the link.
4. If there is a discussion in the mailing list, please add the link.
-->
This PR corrects the handling of corrupt or missing multiline XML files by respecting user-specific options.
### Why are the changes needed?
<!--
Please clarify why the changes are needed. For instance,
1. If you propose a new API, clarify the use case for a new API.
2. If you fix a bug, you can clarify why it is a bug.
-->
This PR fixes a bug.
### Does this PR introduce _any_ user-facing change?
<!--
Note that it means *any* user-facing change including all aspects such as the documentation fix.
If yes, please clarify the previous behavior and the change this PR proposes - provide the console output, description and/or an example to show the behavior difference if possible.
If possible, please also clarify if this is a user-facing change compared to the released Spark versions or within the unreleased branches such as master.
If no, write 'No'.
-->
Yes. Previously, corrupt/missing files weren't ignored based on user-specific options. This PR fixes this issue
### How was this patch tested?
<!--
If tests were added, say they were added here. Please make sure to add some test cases that check the changes thoroughly including negative and positive cases if possible.
If it was tested in a way different from regular unit tests, please clarify how you tested step by step, ideally copy and paste-able, so that other reviewers can test and check, and descendants can verify in the future.
If tests were not added, please describe why they were not added and/or why it was difficult to add.
If benchmark tests were added, please run the benchmarks in GitHub Actions for the consistent environment, and the instructions could accord to: https://spark.apache.org/developer-tools.html#github-workflow-benchmarks.
-->
Unit tests
### Was this patch authored or co-authored using generative AI tooling?
<!--
If generative AI tooling has been used in the process of authoring this patch, please include the
phrase: 'Generated-by: ' followed by the name of the tool and its version.
If no, write 'No'.
Please refer to the [ASF Generative Tooling Guidance](https://www.apache.org/legal/generative-tooling.html) for details.
-->
No
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org
Re: [PR] [SPARK-46248][SQL] XML: Support for ignoreCorruptFiles and ignoreMissingFiles options [spark]
Posted by "shujingyang-db (via GitHub)" <gi...@apache.org>.
shujingyang-db commented on code in PR #44163:
URL: https://github.com/apache/spark/pull/44163#discussion_r1414754388
##########
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/xml/XmlInferSchema.scala:
##########
@@ -120,9 +136,27 @@ class XmlInferSchema(options: XmlOptions, caseSensitive: Boolean)
val rootAttributes = StaxXmlParserUtils.gatherRootAttributes(parser)
Some(inferObject(parser, rootAttributes))
} catch {
- case NonFatal(_) if options.parseMode == PermissiveMode =>
- Some(StructType(Seq(StructField(options.columnNameOfCorruptRecord, StringType))))
- case NonFatal(_) =>
+ case e @ (_: XMLStreamException | _: MalformedInputException | _: SAXException) =>
+ handleXmlErrorsByParseMode(options.parseMode, options.columnNameOfCorruptRecord, e)
Review Comment:
yeah, we guard it by NonFatal errors at the end of this code block. Does it look good to you?
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org
Re: [PR] [SPARK-46248][SQL] XML: Support for ignoreCorruptFiles and ignoreMissingFiles options [spark]
Posted by "sandip-db (via GitHub)" <gi...@apache.org>.
sandip-db commented on code in PR #44163:
URL: https://github.com/apache/spark/pull/44163#discussion_r1423270340
##########
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/xml/StaxXmlParser.scala:
##########
@@ -604,6 +606,24 @@ class XmlTokenizer(
return Some(str)
}
} catch {
Review Comment:
Consider this to avoid reader.close repetitions:
```
def next(): Option[String] = {
var nextString: Option[String] = None
try {
if (readUntilStartElement()) {
buffer.append(currentStartTag)
// Don't check whether the end element was found. Even if not, return everything
// that was read, which will invariably cause a parse error later
readUntilEndElement(currentStartTag.endsWith(">"))
nextString = buffer.toString()
buffer = new StringBuilder()
}
} catch {
case e: FileNotFoundException if options.ignoreMissingFiles =>
logWarning(
"Skipping the rest of" +
" the content in the missing file during schema inference",
e)
case NonFatal(e) =>
ExceptionUtils.getRootCause(e) match {
case _: RuntimeException | _: IOException if options.ignoreCorruptFiles =>
logWarning(
"Skipping the rest of" +
" the content in the corrupted file during schema inference",
e
)
}
} finally {
if (var == None) {
reader.close()
reader = null
}
}
nextStr
}
```
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org
Re: [PR] [SPARK-46248][SQL] XML: Support for ignoreCorruptFiles and ignoreMissingFiles options [spark]
Posted by "shujingyang-db (via GitHub)" <gi...@apache.org>.
shujingyang-db commented on code in PR #44163:
URL: https://github.com/apache/spark/pull/44163#discussion_r1414754388
##########
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/xml/XmlInferSchema.scala:
##########
@@ -120,9 +136,27 @@ class XmlInferSchema(options: XmlOptions, caseSensitive: Boolean)
val rootAttributes = StaxXmlParserUtils.gatherRootAttributes(parser)
Some(inferObject(parser, rootAttributes))
} catch {
- case NonFatal(_) if options.parseMode == PermissiveMode =>
- Some(StructType(Seq(StructField(options.columnNameOfCorruptRecord, StringType))))
- case NonFatal(_) =>
+ case e @ (_: XMLStreamException | _: MalformedInputException | _: SAXException) =>
+ handleXmlErrorsByParseMode(options.parseMode, options.columnNameOfCorruptRecord, e)
Review Comment:
yeah, we guard it by NonFatal errors at the end of this code block. Does it look good to you?
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org
Re: [PR] [SPARK-46248][SQL] XML: Support for ignoreCorruptFiles and ignoreMissingFiles options [spark]
Posted by "sandip-db (via GitHub)" <gi...@apache.org>.
sandip-db commented on code in PR #44163:
URL: https://github.com/apache/spark/pull/44163#discussion_r1434601695
##########
sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/xml/XmlSuite.scala:
##########
@@ -2371,4 +2400,104 @@ class XmlSuite extends QueryTest with SharedSparkSession {
}
}
}
+
+ test("SPARK-46248: Enabling/disabling ignoreCorruptFiles/ignoreMissingFiles") {
+ withCorruptFile(inputFile => {
+ withSQLConf(SQLConf.IGNORE_CORRUPT_FILES.key -> "false") {
+ val e = intercept[SparkException] {
+ spark.read
+ .option("rowTag", "ROW")
+ .option("multiLine", false)
+ .xml(inputFile.toURI.toString)
+ .collect()
+ }
+ assert(ExceptionUtils.getRootCause(e).isInstanceOf[EOFException])
+ assert(ExceptionUtils.getRootCause(e).getMessage === "Unexpected end of input stream")
+ val e2 = intercept[SparkException] {
+ spark.read
+ .option("rowTag", "ROW")
+ .option("multiLine", true)
+ .xml(inputFile.toURI.toString)
+ .collect()
+ }
+ assert(ExceptionUtils.getRootCause(e2).isInstanceOf[EOFException])
+ assert(ExceptionUtils.getRootCause(e2).getMessage === "Unexpected end of input stream")
+ }
+ withSQLConf(SQLConf.IGNORE_CORRUPT_FILES.key -> "true") {
+ val result = spark.read
+ .option("rowTag", "ROW")
+ .option("multiLine", false)
+ .xml(inputFile.toURI.toString)
+ .collect()
+ assert(result.isEmpty)
+ }
+ })
+ withTempPath { dir =>
+ import org.apache.hadoop.fs.Path
+ val xmlPath = new Path(dir.getCanonicalPath, "xml")
+ val fs = xmlPath.getFileSystem(spark.sessionState.newHadoopConf())
+
+ sampledTestData.write.option("rowTag", "ROW").xml(xmlPath.toString)
+ val df = spark.read.option("rowTag", "ROW").option("multiLine", true).xml(xmlPath.toString)
+ fs.delete(xmlPath, true)
+ withSQLConf(SQLConf.IGNORE_MISSING_FILES.key -> "false") {
+ val e = intercept[SparkException] {
+ df.collect()
+ }
+ assert(e.getCause.isInstanceOf[SparkFileNotFoundException])
+ assert(e.getCause.getMessage.contains(".xml does not exist"))
+ }
+
+ sampledTestData.write.option("rowTag", "ROW").xml(xmlPath.toString)
+ val df2 = spark.read.option("rowTag", "ROW").option("multiLine", true).xml(xmlPath.toString)
+ fs.delete(xmlPath, true)
+ withSQLConf(SQLConf.IGNORE_MISSING_FILES.key -> "true") {
+ assert(df2.collect().isEmpty)
+ }
+ }
+ }
+
+ test("SPARK-46248: Read from a corrupted compressed file") {
+ withTempDir { dir =>
+ val format = "xml"
+ val numRecords = 10000
+ // create data
+ val data =
+ spark.sparkContext.parallelize(
+ (0 until numRecords).map(i => Row(i.toString, (i * 2).toString)))
+ val schema = buildSchema(field("a1"), field("a2"))
Review Comment:
```suggestion
val schema = buildSchema(
field("a1", LongType),
field("a2", LongType))
```
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org
Re: [PR] [SPARK-46248][SQL] XML: Support for ignoreCorruptFiles and ignoreMissingFiles options [spark]
Posted by "HyukjinKwon (via GitHub)" <gi...@apache.org>.
HyukjinKwon commented on PR #44163:
URL: https://github.com/apache/spark/pull/44163#issuecomment-1853261270
Mind retriggering https://github.com/shujingyang-db/spark/runs/19583242928 please?
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org
Re: [PR] [SPARK-46248]XML: Support for ignoreCorruptFiles and ignoreMissingFiles options [spark]
Posted by "sandip-db (via GitHub)" <gi...@apache.org>.
sandip-db commented on code in PR #44163:
URL: https://github.com/apache/spark/pull/44163#discussion_r1414522386
##########
sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/xml/XmlSuite.scala:
##########
@@ -2178,4 +2186,58 @@ class XmlSuite extends QueryTest with SharedSparkSession {
)
testWriteReadRoundTrip(df, Map("nullValue" -> "null", "prefersDecimal" -> "true"))
}
+
+ test("Enabling/disabling ignoreCorruptFiles/ignoreMissingFiles") {
+ withCorruptFile(inputFile => {
+ withSQLConf(SQLConf.IGNORE_CORRUPT_FILES.key -> "false") {
+ val e = intercept[SparkException] {
+ spark.read.option("rowTag", "ROW").xml(inputFile.toURI.toString).collect()
+ }
+ assert(ExceptionUtils.getRootCause(e).isInstanceOf[EOFException])
+ assert(ExceptionUtils.getRootCause(e).getMessage === "Unexpected end of input stream")
+ val e2 = intercept[SparkException] {
+ spark.read
+ .option("rowTag", "ROW")
+ .option("multiLine", true)
+ .xml(inputFile.toURI.toString)
+ .collect()
+ }
+ assert(ExceptionUtils.getRootCause(e2).isInstanceOf[EOFException])
+ assert(ExceptionUtils.getRootCause(e2).getMessage === "Unexpected end of input stream")
+ }
+ withSQLConf(SQLConf.IGNORE_CORRUPT_FILES.key -> "true") {
+ assert(spark.read.option("rowTag", "ROW").xml(inputFile.toURI.toString).collect().isEmpty)
+ assert(
Review Comment:
Not sure how this is working without `ignoreCorruptFiles` handling in `XMLDataSource`.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org
Re: [PR] [SPARK-46248][SQL] XML: Support for ignoreCorruptFiles and ignoreMissingFiles options [spark]
Posted by "sandip-db (via GitHub)" <gi...@apache.org>.
sandip-db commented on code in PR #44163:
URL: https://github.com/apache/spark/pull/44163#discussion_r1434278718
##########
sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/xml/XmlSuite.scala:
##########
@@ -2371,4 +2400,108 @@ class XmlSuite extends QueryTest with SharedSparkSession {
}
}
}
+
+ test("SPARK-46248: Enabling/disabling ignoreCorruptFiles/ignoreMissingFiles") {
+ withCorruptFile(inputFile => {
+ withSQLConf(SQLConf.IGNORE_CORRUPT_FILES.key -> "false") {
+ val e = intercept[SparkException] {
+ spark.read
+ .option("rowTag", "ROW")
+ .option("multiLine", false)
+ .xml(inputFile.toURI.toString)
+ .collect()
+ }
+ assert(ExceptionUtils.getRootCause(e).isInstanceOf[EOFException])
+ assert(ExceptionUtils.getRootCause(e).getMessage === "Unexpected end of input stream")
+ val e2 = intercept[SparkException] {
+ spark.read
+ .option("rowTag", "ROW")
+ .option("multiLine", true)
+ .xml(inputFile.toURI.toString)
+ .collect()
+ }
+ assert(ExceptionUtils.getRootCause(e2).isInstanceOf[EOFException])
+ assert(ExceptionUtils.getRootCause(e2).getMessage === "Unexpected end of input stream")
+ }
+ withSQLConf(SQLConf.IGNORE_CORRUPT_FILES.key -> "true") {
+ spark.read
+ .option("rowTag", "ROW")
+ .option("multiLine", false)
+ .xml(inputFile.toURI.toString)
+ .collect()
+ assert(
+ spark.read
+ .option("rowTag", "ROW")
+ .option("multiLine", true)
+ .xml(inputFile.toURI.toString)
+ .collect()
+ .isEmpty
+ )
+ }
+ })
+ withTempPath { dir =>
+ import org.apache.hadoop.fs.Path
+ val xmlPath = new Path(dir.getCanonicalPath, "xml")
+ val fs = xmlPath.getFileSystem(spark.sessionState.newHadoopConf())
+
+ sampledTestData.write.option("rowTag", "ROW").xml(xmlPath.toString)
+ val df = spark.read.option("rowTag", "ROW").option("multiLine", true).xml(xmlPath.toString)
+ fs.delete(xmlPath, true)
+ withSQLConf(SQLConf.IGNORE_MISSING_FILES.key -> "false") {
+ val e = intercept[SparkException] {
+ df.collect()
+ }
+ assert(e.getCause.isInstanceOf[SparkFileNotFoundException])
+ assert(e.getCause.getMessage.contains(".xml does not exist"))
+ }
+
+ sampledTestData.write.option("rowTag", "ROW").xml(xmlPath.toString)
+ val df2 = spark.read.option("rowTag", "ROW").option("multiLine", true).xml(xmlPath.toString)
+ fs.delete(xmlPath, true)
+ withSQLConf(SQLConf.IGNORE_MISSING_FILES.key -> "true") {
+ assert(df2.collect().isEmpty)
+ }
+ }
+ }
+
+ test("SPARK-46248: Read from a corrupted compressed file") {
+ withTempDir { dir =>
+ val format = "xml"
+ val numRecords = 10000
+ // create data
+ val data =
+ spark.sparkContext.parallelize(
+ (0 until numRecords).map(i => Row(i.toString, (i * 2).toString)))
+ val schema = buildSchema(field("a1"), field("a2"))
+ val df = spark.createDataFrame(data, schema)
+
+ df.coalesce(4)
+ .write
+ .mode(SaveMode.Overwrite)
+ .format(format)
+ .option("compression", "gZiP")
+ .option("rowTag", "row")
+ .save(dir.getCanonicalPath)
+
+ withCorruptedFile(dir) { corruptedDir =>
+ withSQLConf(SQLConf.IGNORE_CORRUPT_FILES.key -> "true") {
+ val dfCorrupted = spark.read
+ .format(format)
+ .option("multiline", "true")
+ .option("compression", "gzip")
+ .option("rowTag", "row")
+ .load(corruptedDir.getCanonicalPath)
+ assert(dfCorrupted.collect().length > 100)
Review Comment:
```suggestion
val results = dfCorrupted.collect()
assert(results(1) === Row(1, 2))
assert(results.length > 100)
```
##########
sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/xml/XmlSuite.scala:
##########
@@ -2371,4 +2400,108 @@ class XmlSuite extends QueryTest with SharedSparkSession {
}
}
}
+
+ test("SPARK-46248: Enabling/disabling ignoreCorruptFiles/ignoreMissingFiles") {
+ withCorruptFile(inputFile => {
+ withSQLConf(SQLConf.IGNORE_CORRUPT_FILES.key -> "false") {
+ val e = intercept[SparkException] {
+ spark.read
+ .option("rowTag", "ROW")
+ .option("multiLine", false)
+ .xml(inputFile.toURI.toString)
+ .collect()
+ }
+ assert(ExceptionUtils.getRootCause(e).isInstanceOf[EOFException])
+ assert(ExceptionUtils.getRootCause(e).getMessage === "Unexpected end of input stream")
+ val e2 = intercept[SparkException] {
+ spark.read
+ .option("rowTag", "ROW")
+ .option("multiLine", true)
+ .xml(inputFile.toURI.toString)
+ .collect()
+ }
+ assert(ExceptionUtils.getRootCause(e2).isInstanceOf[EOFException])
+ assert(ExceptionUtils.getRootCause(e2).getMessage === "Unexpected end of input stream")
+ }
+ withSQLConf(SQLConf.IGNORE_CORRUPT_FILES.key -> "true") {
+ spark.read
+ .option("rowTag", "ROW")
+ .option("multiLine", false)
+ .xml(inputFile.toURI.toString)
+ .collect()
+ assert(
+ spark.read
+ .option("rowTag", "ROW")
+ .option("multiLine", true)
+ .xml(inputFile.toURI.toString)
+ .collect()
+ .isEmpty
+ )
+ }
+ })
+ withTempPath { dir =>
+ import org.apache.hadoop.fs.Path
+ val xmlPath = new Path(dir.getCanonicalPath, "xml")
+ val fs = xmlPath.getFileSystem(spark.sessionState.newHadoopConf())
+
+ sampledTestData.write.option("rowTag", "ROW").xml(xmlPath.toString)
+ val df = spark.read.option("rowTag", "ROW").option("multiLine", true).xml(xmlPath.toString)
+ fs.delete(xmlPath, true)
+ withSQLConf(SQLConf.IGNORE_MISSING_FILES.key -> "false") {
+ val e = intercept[SparkException] {
+ df.collect()
+ }
+ assert(e.getCause.isInstanceOf[SparkFileNotFoundException])
+ assert(e.getCause.getMessage.contains(".xml does not exist"))
+ }
+
+ sampledTestData.write.option("rowTag", "ROW").xml(xmlPath.toString)
+ val df2 = spark.read.option("rowTag", "ROW").option("multiLine", true).xml(xmlPath.toString)
+ fs.delete(xmlPath, true)
+ withSQLConf(SQLConf.IGNORE_MISSING_FILES.key -> "true") {
+ assert(df2.collect().isEmpty)
+ }
+ }
+ }
+
+ test("SPARK-46248: Read from a corrupted compressed file") {
+ withTempDir { dir =>
+ val format = "xml"
+ val numRecords = 10000
+ // create data
+ val data =
+ spark.sparkContext.parallelize(
+ (0 until numRecords).map(i => Row(i.toString, (i * 2).toString)))
+ val schema = buildSchema(field("a1"), field("a2"))
+ val df = spark.createDataFrame(data, schema)
+
+ df.coalesce(4)
+ .write
+ .mode(SaveMode.Overwrite)
+ .format(format)
+ .option("compression", "gZiP")
+ .option("rowTag", "row")
+ .save(dir.getCanonicalPath)
+
+ withCorruptedFile(dir) { corruptedDir =>
+ withSQLConf(SQLConf.IGNORE_CORRUPT_FILES.key -> "true") {
+ val dfCorrupted = spark.read
+ .format(format)
+ .option("multiline", "true")
+ .option("compression", "gzip")
+ .option("rowTag", "row")
+ .load(corruptedDir.getCanonicalPath)
+ assert(dfCorrupted.collect().length > 100)
+ val dfCorruptedWSchema = spark.read
+ .format(format)
+ .schema(schema)
+ .option("multiline", "true")
+ .option("compression", "gzip")
+ .option("rowTag", "row")
+ .load(corruptedDir.getCanonicalPath)
+ dfCorrupted.equals(dfCorruptedWSchema)
Review Comment:
```suggestion
assert(dfCorrupted.dtypes === dfCorruptedWSchema.dtypes)
checkAnswer(dfCorrupted, dfCorruptedWSchema)
```
##########
sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/xml/XmlSuite.scala:
##########
@@ -2371,4 +2400,108 @@ class XmlSuite extends QueryTest with SharedSparkSession {
}
}
}
+
+ test("SPARK-46248: Enabling/disabling ignoreCorruptFiles/ignoreMissingFiles") {
+ withCorruptFile(inputFile => {
+ withSQLConf(SQLConf.IGNORE_CORRUPT_FILES.key -> "false") {
+ val e = intercept[SparkException] {
+ spark.read
+ .option("rowTag", "ROW")
+ .option("multiLine", false)
+ .xml(inputFile.toURI.toString)
+ .collect()
+ }
+ assert(ExceptionUtils.getRootCause(e).isInstanceOf[EOFException])
+ assert(ExceptionUtils.getRootCause(e).getMessage === "Unexpected end of input stream")
+ val e2 = intercept[SparkException] {
+ spark.read
+ .option("rowTag", "ROW")
+ .option("multiLine", true)
+ .xml(inputFile.toURI.toString)
+ .collect()
+ }
+ assert(ExceptionUtils.getRootCause(e2).isInstanceOf[EOFException])
+ assert(ExceptionUtils.getRootCause(e2).getMessage === "Unexpected end of input stream")
Review Comment:
This is a repeat of the previous spark.read. Why?
##########
sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/xml/XmlSuite.scala:
##########
@@ -2371,4 +2400,108 @@ class XmlSuite extends QueryTest with SharedSparkSession {
}
}
}
+
+ test("SPARK-46248: Enabling/disabling ignoreCorruptFiles/ignoreMissingFiles") {
+ withCorruptFile(inputFile => {
+ withSQLConf(SQLConf.IGNORE_CORRUPT_FILES.key -> "false") {
+ val e = intercept[SparkException] {
+ spark.read
+ .option("rowTag", "ROW")
+ .option("multiLine", false)
+ .xml(inputFile.toURI.toString)
+ .collect()
+ }
+ assert(ExceptionUtils.getRootCause(e).isInstanceOf[EOFException])
+ assert(ExceptionUtils.getRootCause(e).getMessage === "Unexpected end of input stream")
+ val e2 = intercept[SparkException] {
+ spark.read
+ .option("rowTag", "ROW")
+ .option("multiLine", true)
+ .xml(inputFile.toURI.toString)
+ .collect()
+ }
+ assert(ExceptionUtils.getRootCause(e2).isInstanceOf[EOFException])
+ assert(ExceptionUtils.getRootCause(e2).getMessage === "Unexpected end of input stream")
+ }
+ withSQLConf(SQLConf.IGNORE_CORRUPT_FILES.key -> "true") {
+ spark.read
+ .option("rowTag", "ROW")
+ .option("multiLine", false)
+ .xml(inputFile.toURI.toString)
+ .collect()
+ assert(
+ spark.read
+ .option("rowTag", "ROW")
+ .option("multiLine", true)
+ .xml(inputFile.toURI.toString)
+ .collect()
+ .isEmpty
+ )
Review Comment:
```suggestion
val result = spark.read
.option("rowTag", "ROW")
.option("multiLine", false)
.xml(inputFile.toURI.toString)
.collect()
assert(result.isEmpty)
```
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org
Re: [PR] [SPARK-46248]XML: Support for ignoreCorruptFiles and ignoreMissingFiles options [spark]
Posted by "sandip-db (via GitHub)" <gi...@apache.org>.
sandip-db commented on code in PR #44163:
URL: https://github.com/apache/spark/pull/44163#discussion_r1414588409
##########
sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/xml/XmlDataSource.scala:
##########
@@ -172,13 +176,27 @@ object MultiLineXmlDataSource extends XmlDataSource {
parsedOptions: XmlOptions): StructType = {
val xml = createBaseRdd(sparkSession, inputPaths, parsedOptions)
- val tokenRDD = xml.flatMap { portableDataStream =>
- StaxXmlParser.tokenizeStream(
- CodecStreams.createInputStreamWithCloseResource(
- portableDataStream.getConfiguration,
- new Path(portableDataStream.getPath())),
- parsedOptions)
- }
+ val tokenRDD: RDD[String] =
+ xml.flatMap { portableDataStream =>
+ try {
+ StaxXmlParser.tokenizeStream(
+ CodecStreams.createInputStreamWithCloseResource(
+ portableDataStream.getConfiguration,
+ new Path(portableDataStream.getPath())),
+ parsedOptions)
+ } catch {
Review Comment:
Ah. got it. Thx.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org
Re: [PR] [SPARK-46248][SQL] XML: Support for ignoreCorruptFiles and ignoreMissingFiles options [spark]
Posted by "HyukjinKwon (via GitHub)" <gi...@apache.org>.
HyukjinKwon closed pull request #44163: [SPARK-46248][SQL] XML: Support for ignoreCorruptFiles and ignoreMissingFiles options
URL: https://github.com/apache/spark/pull/44163
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org
Re: [PR] [SPARK-46248]XML: Support for ignoreCorruptFiles and ignoreMissingFiles options [spark]
Posted by "shujingyang-db (via GitHub)" <gi...@apache.org>.
shujingyang-db commented on code in PR #44163:
URL: https://github.com/apache/spark/pull/44163#discussion_r1414570468
##########
sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/xml/XmlDataSource.scala:
##########
@@ -172,13 +176,27 @@ object MultiLineXmlDataSource extends XmlDataSource {
parsedOptions: XmlOptions): StructType = {
val xml = createBaseRdd(sparkSession, inputPaths, parsedOptions)
- val tokenRDD = xml.flatMap { portableDataStream =>
- StaxXmlParser.tokenizeStream(
- CodecStreams.createInputStreamWithCloseResource(
- portableDataStream.getConfiguration,
- new Path(portableDataStream.getPath())),
- parsedOptions)
- }
+ val tokenRDD: RDD[String] =
+ xml.flatMap { portableDataStream =>
+ try {
+ StaxXmlParser.tokenizeStream(
+ CodecStreams.createInputStreamWithCloseResource(
+ portableDataStream.getConfiguration,
+ new Path(portableDataStream.getPath())),
+ parsedOptions)
+ } catch {
Review Comment:
It's in `case _: RuntimeException | _: IOException if parsedOptions.ignoreCorruptFiles =>`
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org
Re: [PR] [SPARK-46248][SQL] XML: Support for ignoreCorruptFiles and ignoreMissingFiles options [spark]
Posted by "HyukjinKwon (via GitHub)" <gi...@apache.org>.
HyukjinKwon commented on code in PR #44163:
URL: https://github.com/apache/spark/pull/44163#discussion_r1433676674
##########
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/xml/XmlInferSchema.scala:
##########
@@ -130,10 +147,28 @@ class XmlInferSchema(options: XmlOptions, caseSensitive: Boolean)
parser.close()
Review Comment:
didn't take a super close look but should we maybe close the `parser` with `finally`?
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org
Re: [PR] [SPARK-46248]XML: Support for ignoreCorruptFiles and ignoreMissingFiles options [spark]
Posted by "sandip-db (via GitHub)" <gi...@apache.org>.
sandip-db commented on code in PR #44163:
URL: https://github.com/apache/spark/pull/44163#discussion_r1414443217
##########
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/xml/XmlInferSchema.scala:
##########
@@ -120,9 +136,27 @@ class XmlInferSchema(options: XmlOptions, caseSensitive: Boolean)
val rootAttributes = StaxXmlParserUtils.gatherRootAttributes(parser)
Some(inferObject(parser, rootAttributes))
} catch {
- case NonFatal(_) if options.parseMode == PermissiveMode =>
- Some(StructType(Seq(StructField(options.columnNameOfCorruptRecord, StringType))))
- case NonFatal(_) =>
+ case e @ (_: XMLStreamException | _: MalformedInputException | _: SAXException) =>
+ handleXmlErrorsByParseMode(options.parseMode, options.columnNameOfCorruptRecord, e)
+ case e: CharConversionException if options.charset.isEmpty =>
+ val msg =
+ """XML parser cannot handle a character in its input.
+ |Specifying encoding as an input option explicitly might help to resolve the issue.
+ |""".stripMargin + e.getMessage
+ val wrappedCharException = new CharConversionException(msg)
+ wrappedCharException.initCause(e)
+ handleXmlErrorsByParseMode(
+ options.parseMode,
+ options.columnNameOfCorruptRecord,
+ wrappedCharException)
+ case e: FileNotFoundException if options.ignoreMissingFiles =>
+ logWarning("Skipped missing file", e)
+ Some(StructType(Nil))
+ case e: FileNotFoundException if !options.ignoreMissingFiles => throw e
+ case e @ (_: IOException | _: RuntimeException) if options.ignoreCorruptFiles =>
+ logWarning("Skipped the rest of the content in the corrupted file", e)
+ Some(StructType(Nil))
+ case NonFatal(e) =>
None
Review Comment:
```suggestion
handleXmlErrorsByParseMode(options.parseMode, options.columnNameOfCorruptRecord, e)
```
##########
sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/xml/XmlSuite.scala:
##########
@@ -2178,4 +2186,58 @@ class XmlSuite extends QueryTest with SharedSparkSession {
)
testWriteReadRoundTrip(df, Map("nullValue" -> "null", "prefersDecimal" -> "true"))
}
+
+ test("Enabling/disabling ignoreCorruptFiles/ignoreMissingFiles") {
+ withCorruptFile(inputFile => {
+ withSQLConf(SQLConf.IGNORE_CORRUPT_FILES.key -> "false") {
+ val e = intercept[SparkException] {
+ spark.read.option("rowTag", "ROW").xml(inputFile.toURI.toString).collect()
+ }
+ assert(ExceptionUtils.getRootCause(e).isInstanceOf[EOFException])
+ assert(ExceptionUtils.getRootCause(e).getMessage === "Unexpected end of input stream")
+ val e2 = intercept[SparkException] {
+ spark.read
+ .option("rowTag", "ROW")
+ .option("multiLine", true)
+ .xml(inputFile.toURI.toString)
+ .collect()
+ }
+ assert(ExceptionUtils.getRootCause(e2).isInstanceOf[EOFException])
+ assert(ExceptionUtils.getRootCause(e2).getMessage === "Unexpected end of input stream")
+ }
+ withSQLConf(SQLConf.IGNORE_CORRUPT_FILES.key -> "true") {
+ assert(spark.read.option("rowTag", "ROW").xml(inputFile.toURI.toString).collect().isEmpty)
Review Comment:
`multiLine` is set to `true` by default for XML.
```suggestion
spark.read.option("rowTag", "ROW").option("multiLine", false).xml(inputFile.toURI.toString).collect()
```
##########
sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/xml/XmlDataSource.scala:
##########
@@ -172,13 +176,27 @@ object MultiLineXmlDataSource extends XmlDataSource {
parsedOptions: XmlOptions): StructType = {
val xml = createBaseRdd(sparkSession, inputPaths, parsedOptions)
- val tokenRDD = xml.flatMap { portableDataStream =>
- StaxXmlParser.tokenizeStream(
- CodecStreams.createInputStreamWithCloseResource(
- portableDataStream.getConfiguration,
- new Path(portableDataStream.getPath())),
- parsedOptions)
- }
+ val tokenRDD: RDD[String] =
+ xml.flatMap { portableDataStream =>
+ try {
+ StaxXmlParser.tokenizeStream(
+ CodecStreams.createInputStreamWithCloseResource(
+ portableDataStream.getConfiguration,
+ new Path(portableDataStream.getPath())),
+ parsedOptions)
+ } catch {
Review Comment:
I don't see `ignoreCorruptFiles` handling here
##########
sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/xml/XmlSuite.scala:
##########
@@ -2178,4 +2186,58 @@ class XmlSuite extends QueryTest with SharedSparkSession {
)
testWriteReadRoundTrip(df, Map("nullValue" -> "null", "prefersDecimal" -> "true"))
}
+
+ test("Enabling/disabling ignoreCorruptFiles/ignoreMissingFiles") {
+ withCorruptFile(inputFile => {
+ withSQLConf(SQLConf.IGNORE_CORRUPT_FILES.key -> "false") {
+ val e = intercept[SparkException] {
+ spark.read.option("rowTag", "ROW").xml(inputFile.toURI.toString).collect()
Review Comment:
`multiLine` is set to `true` by default for XML.
```suggestion
spark.read.option("rowTag", "ROW").option("multiLine", false).xml(inputFile.toURI.toString).collect()
```
##########
sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/xml/XmlSuite.scala:
##########
@@ -2178,4 +2186,58 @@ class XmlSuite extends QueryTest with SharedSparkSession {
)
testWriteReadRoundTrip(df, Map("nullValue" -> "null", "prefersDecimal" -> "true"))
}
+
+ test("Enabling/disabling ignoreCorruptFiles/ignoreMissingFiles") {
+ withCorruptFile(inputFile => {
+ withSQLConf(SQLConf.IGNORE_CORRUPT_FILES.key -> "false") {
+ val e = intercept[SparkException] {
+ spark.read.option("rowTag", "ROW").xml(inputFile.toURI.toString).collect()
+ }
+ assert(ExceptionUtils.getRootCause(e).isInstanceOf[EOFException])
+ assert(ExceptionUtils.getRootCause(e).getMessage === "Unexpected end of input stream")
+ val e2 = intercept[SparkException] {
+ spark.read
+ .option("rowTag", "ROW")
+ .option("multiLine", true)
+ .xml(inputFile.toURI.toString)
+ .collect()
+ }
+ assert(ExceptionUtils.getRootCause(e2).isInstanceOf[EOFException])
+ assert(ExceptionUtils.getRootCause(e2).getMessage === "Unexpected end of input stream")
+ }
+ withSQLConf(SQLConf.IGNORE_CORRUPT_FILES.key -> "true") {
+ assert(spark.read.option("rowTag", "ROW").xml(inputFile.toURI.toString).collect().isEmpty)
+ assert(
Review Comment:
Not sure how this is working without `ignoreCorruptFiles` handling in `XMLDataSource`.
##########
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/xml/XmlInferSchema.scala:
##########
@@ -120,9 +136,27 @@ class XmlInferSchema(options: XmlOptions, caseSensitive: Boolean)
val rootAttributes = StaxXmlParserUtils.gatherRootAttributes(parser)
Some(inferObject(parser, rootAttributes))
} catch {
- case NonFatal(_) if options.parseMode == PermissiveMode =>
- Some(StructType(Seq(StructField(options.columnNameOfCorruptRecord, StringType))))
- case NonFatal(_) =>
+ case e @ (_: XMLStreamException | _: MalformedInputException | _: SAXException) =>
+ handleXmlErrorsByParseMode(options.parseMode, options.columnNameOfCorruptRecord, e)
Review Comment:
These might be the only Exceptions. But just for defensive purpose, let's catch all NonFatal errors at the end as indicated.
##########
sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/xml/XmlSuite.scala:
##########
@@ -2178,4 +2186,58 @@ class XmlSuite extends QueryTest with SharedSparkSession {
)
testWriteReadRoundTrip(df, Map("nullValue" -> "null", "prefersDecimal" -> "true"))
}
+
+ test("Enabling/disabling ignoreCorruptFiles/ignoreMissingFiles") {
+ withCorruptFile(inputFile => {
Review Comment:
please add scenarios with user specified schema.
##########
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/xml/XmlInferSchema.scala:
##########
@@ -120,9 +136,27 @@ class XmlInferSchema(options: XmlOptions, caseSensitive: Boolean)
val rootAttributes = StaxXmlParserUtils.gatherRootAttributes(parser)
Some(inferObject(parser, rootAttributes))
} catch {
- case NonFatal(_) if options.parseMode == PermissiveMode =>
- Some(StructType(Seq(StructField(options.columnNameOfCorruptRecord, StringType))))
- case NonFatal(_) =>
+ case e @ (_: XMLStreamException | _: MalformedInputException | _: SAXException) =>
+ handleXmlErrorsByParseMode(options.parseMode, options.columnNameOfCorruptRecord, e)
+ case e: CharConversionException if options.charset.isEmpty =>
+ val msg =
+ """XML parser cannot handle a character in its input.
+ |Specifying encoding as an input option explicitly might help to resolve the issue.
+ |""".stripMargin + e.getMessage
+ val wrappedCharException = new CharConversionException(msg)
+ wrappedCharException.initCause(e)
+ handleXmlErrorsByParseMode(
+ options.parseMode,
+ options.columnNameOfCorruptRecord,
+ wrappedCharException)
+ case e: FileNotFoundException if options.ignoreMissingFiles =>
+ logWarning("Skipped missing file", e)
+ Some(StructType(Nil))
+ case e: FileNotFoundException if !options.ignoreMissingFiles => throw e
+ case e @ (_: IOException | _: RuntimeException) if options.ignoreCorruptFiles =>
+ logWarning("Skipped the rest of the content in the corrupted file", e)
+ Some(StructType(Nil))
Review Comment:
These exceptions are not possible here as input is a `String` as opposed to a stream.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org
Re: [PR] [SPARK-46248][SQL] XML: Support for ignoreCorruptFiles and ignoreMissingFiles options [spark]
Posted by "shujingyang-db (via GitHub)" <gi...@apache.org>.
shujingyang-db commented on code in PR #44163:
URL: https://github.com/apache/spark/pull/44163#discussion_r1418019453
##########
sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/xml/XmlSuite.scala:
##########
@@ -2178,4 +2186,58 @@ class XmlSuite extends QueryTest with SharedSparkSession {
)
testWriteReadRoundTrip(df, Map("nullValue" -> "null", "prefersDecimal" -> "true"))
}
+
+ test("Enabling/disabling ignoreCorruptFiles/ignoreMissingFiles") {
+ withCorruptFile(inputFile => {
Review Comment:
Added this scenario in the test case: "SPARK-46248: Read from a corrupted compressed file"
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org
Re: [PR] [SPARK-46248][SQL] XML: Support for ignoreCorruptFiles and ignoreMissingFiles options [spark]
Posted by "sandip-db (via GitHub)" <gi...@apache.org>.
sandip-db commented on code in PR #44163:
URL: https://github.com/apache/spark/pull/44163#discussion_r1422984743
##########
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/xml/StaxXmlParser.scala:
##########
@@ -750,7 +752,20 @@ object StaxXmlParser {
throw QueryExecutionErrors.endOfStreamError()
}
val curRecord = convert(nextRecord.get)
- nextRecord = xmlTokenizer.next()
+ try {
+ nextRecord = xmlTokenizer.next()
+ } catch {
+ case _: FileNotFoundException if options.ignoreMissingFiles =>
Review Comment:
Move this try..catch into XmlTokenizer.next
##########
sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/xml/XmlSuite.scala:
##########
@@ -2178,4 +2207,108 @@ class XmlSuite extends QueryTest with SharedSparkSession {
)
testWriteReadRoundTrip(df, Map("nullValue" -> "null", "prefersDecimal" -> "true"))
}
+
+ test("SPARK-46248: Enabling/disabling ignoreCorruptFiles/ignoreMissingFiles") {
+ withCorruptFile(inputFile => {
+ withSQLConf(SQLConf.IGNORE_CORRUPT_FILES.key -> "false") {
+ val e = intercept[SparkException] {
+ spark.read
+ .option("rowTag", "ROW")
+ .option("multiLine", false)
+ .xml(inputFile.toURI.toString)
+ .collect()
+ }
+ assert(ExceptionUtils.getRootCause(e).isInstanceOf[EOFException])
+ assert(ExceptionUtils.getRootCause(e).getMessage === "Unexpected end of input stream")
+ val e2 = intercept[SparkException] {
+ spark.read
+ .option("rowTag", "ROW")
+ .option("multiLine", true)
+ .xml(inputFile.toURI.toString)
+ .collect()
+ }
+ assert(ExceptionUtils.getRootCause(e2).isInstanceOf[EOFException])
+ assert(ExceptionUtils.getRootCause(e2).getMessage === "Unexpected end of input stream")
+ }
+ withSQLConf(SQLConf.IGNORE_CORRUPT_FILES.key -> "true") {
+ spark.read
+ .option("rowTag", "ROW")
+ .option("multiLine", false)
+ .xml(inputFile.toURI.toString)
+ .collect()
+ assert(
+ spark.read
+ .option("rowTag", "ROW")
+ .option("multiLine", true)
+ .xml(inputFile.toURI.toString)
+ .collect()
+ .isEmpty
+ )
+ }
+ })
+ withTempPath { dir =>
+ import org.apache.hadoop.fs.Path
+ val xmlPath = new Path(dir.getCanonicalPath, "xml")
+ val fs = xmlPath.getFileSystem(spark.sessionState.newHadoopConf())
+
+ sampledTestData.write.option("rowTag", "ROW").xml(xmlPath.toString)
+ val df = spark.read.option("rowTag", "ROW").option("multiLine", true).xml(xmlPath.toString)
+ fs.delete(xmlPath, true)
+ withSQLConf(SQLConf.IGNORE_MISSING_FILES.key -> "false") {
+ val e = intercept[SparkException] {
+ df.collect()
+ }
+ assert(e.getCause.isInstanceOf[SparkFileNotFoundException])
+ assert(e.getCause.getMessage.contains(".xml does not exist"))
+ }
+
+ sampledTestData.write.option("rowTag", "ROW").xml(xmlPath.toString)
+ val df2 = spark.read.option("rowTag", "ROW").option("multiLine", true).xml(xmlPath.toString)
+ fs.delete(xmlPath, true)
+ withSQLConf(SQLConf.IGNORE_MISSING_FILES.key -> "true") {
+ assert(df2.collect().isEmpty)
+ }
+ }
+ }
+
+ test("SPARK-46248: Read from a corrupted compressed file") {
+ withTempDir { dir =>
+ val format = "xml"
+ val numRecords = 10000
+ // create data
+ val data =
+ spark.sparkContext.parallelize(
+ (0 until numRecords).map(i => Row(i.toString, (i * 2).toString)))
+ val schema = buildSchema(field("a1"), field("a2"))
+ val df = spark.createDataFrame(data, schema)
+
+ df.coalesce(4)
+ .write
+ .mode(SaveMode.Overwrite)
+ .format(format)
+ .option("compression", "gZiP")
+ .option("rowTag", "row")
+ .save(dir.getCanonicalPath)
+
+ withCorruptedFile(dir) { corruptedDir =>
+ withSQLConf(SQLConf.IGNORE_CORRUPT_FILES.key -> "true") {
+ val dfCorrupted = spark.read
+ .format(format)
+ .option("multiline", "true")
+ .option("compression", "gzip")
+ .option("rowTag", "row")
+ .load(corruptedDir.getCanonicalPath)
+ assert(!dfCorrupted.isEmpty)
Review Comment:
```suggestion
assert(dfCorrupted.collect().length > 100)
```
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org
Re: [PR] [SPARK-46248][SQL] XML: Support for ignoreCorruptFiles and ignoreMissingFiles options [spark]
Posted by "sandip-db (via GitHub)" <gi...@apache.org>.
sandip-db commented on code in PR #44163:
URL: https://github.com/apache/spark/pull/44163#discussion_r1443960176
##########
sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/xml/TestXmlData.scala:
##########
@@ -0,0 +1,71 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.sql.execution.datasources.xml
+
+import java.io.{File, RandomAccessFile}
+
+import org.apache.spark.sql.{Dataset, Encoders, SparkSession}
+
+private[xml] trait TestXmlData {
+ protected def spark: SparkSession
+
+ def sampledTestData: Dataset[String] = {
+ spark
+ .range(0, 100, 1)
+ .map { index =>
+ val predefinedSample = Set[Long](3, 18, 20, 24, 50, 60, 87, 99)
+ if (predefinedSample.contains(index)) {
+ index.toString
+ } else {
+ (index.toDouble + 0.1).toString
+ }
+ }(Encoders.STRING)
+ }
+
+ def withCorruptedFile(dir: File, format: String = "gz", numBytesToCorrupt: Int = 50)(
+ f: File => Unit): Unit = {
+ // find the targeted files and corrupt the first one
+ val files = dir.listFiles().filter(file => file.isFile && file.getName.endsWith(format))
+ val raf = new RandomAccessFile(files.head.getPath, "rw")
+
+ // disable checksum verification
+ import org.apache.hadoop.fs.Path
+ val fs = new Path(dir.getPath).getFileSystem(spark.sessionState.newHadoopConf())
+ fs.setVerifyChecksum(false)
+ // delete crc files
+ val crcFiles = dir.listFiles
+ .filter(file => file.isFile && file.getName.endsWith("crc"))
+ crcFiles.foreach { file =>
+ assert(file.exists())
+ file.delete()
+ assert(!file.exists())
+ }
+ fs.close()
Review Comment:
remove
##########
sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/xml/TestXmlData.scala:
##########
@@ -0,0 +1,71 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.sql.execution.datasources.xml
+
+import java.io.{File, RandomAccessFile}
+
+import org.apache.spark.sql.{Dataset, Encoders, SparkSession}
+
+private[xml] trait TestXmlData {
+ protected def spark: SparkSession
+
+ def sampledTestData: Dataset[String] = {
+ spark
+ .range(0, 100, 1)
+ .map { index =>
+ val predefinedSample = Set[Long](3, 18, 20, 24, 50, 60, 87, 99)
+ if (predefinedSample.contains(index)) {
+ index.toString
+ } else {
+ (index.toDouble + 0.1).toString
+ }
+ }(Encoders.STRING)
+ }
+
+ def withCorruptedFile(dir: File, format: String = "gz", numBytesToCorrupt: Int = 50)(
+ f: File => Unit): Unit = {
+ // find the targeted files and corrupt the first one
+ val files = dir.listFiles().filter(file => file.isFile && file.getName.endsWith(format))
+ val raf = new RandomAccessFile(files.head.getPath, "rw")
+
+ // disable checksum verification
+ import org.apache.hadoop.fs.Path
+ val fs = new Path(dir.getPath).getFileSystem(spark.sessionState.newHadoopConf())
+ fs.setVerifyChecksum(false)
+ // delete crc files
+ val crcFiles = dir.listFiles
+ .filter(file => file.isFile && file.getName.endsWith("crc"))
+ crcFiles.foreach { file =>
+ assert(file.exists())
+ file.delete()
+ assert(!file.exists())
+ }
+ fs.close()
+
+ // corrupt the file
+ val fileSize = raf.length()
+ // avoid the last few bytes as it might contain crc
+ raf.seek(fileSize - numBytesToCorrupt - 100)
+ for (_ <- 1 to numBytesToCorrupt) {
+ val randomByte = (Math.random() * 256).toByte
+ raf.writeByte(randomByte)
+ }
+ raf.close()
+ f(dir)
+ }
Review Comment:
Enable checksum at the end to prevent Parquet reader in subsequent tests from throwing leaky stream error:
```suggestion
f(dir)
fs.setVerifyChecksum(true)
}
```
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org
Re: [PR] [SPARK-46248][SQL] XML: Support for ignoreCorruptFiles and ignoreMissingFiles options [spark]
Posted by "HyukjinKwon (via GitHub)" <gi...@apache.org>.
HyukjinKwon commented on PR #44163:
URL: https://github.com/apache/spark/pull/44163#issuecomment-1880226508
Merged to master.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org
Re: [PR] [SPARK-46248][SQL] XML: Support for ignoreCorruptFiles and ignoreMissingFiles options [spark]
Posted by "shujingyang-db (via GitHub)" <gi...@apache.org>.
shujingyang-db commented on code in PR #44163:
URL: https://github.com/apache/spark/pull/44163#discussion_r1434431560
##########
sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/xml/XmlSuite.scala:
##########
@@ -2371,4 +2400,108 @@ class XmlSuite extends QueryTest with SharedSparkSession {
}
}
}
+
+ test("SPARK-46248: Enabling/disabling ignoreCorruptFiles/ignoreMissingFiles") {
+ withCorruptFile(inputFile => {
+ withSQLConf(SQLConf.IGNORE_CORRUPT_FILES.key -> "false") {
+ val e = intercept[SparkException] {
+ spark.read
+ .option("rowTag", "ROW")
+ .option("multiLine", false)
+ .xml(inputFile.toURI.toString)
+ .collect()
+ }
+ assert(ExceptionUtils.getRootCause(e).isInstanceOf[EOFException])
+ assert(ExceptionUtils.getRootCause(e).getMessage === "Unexpected end of input stream")
+ val e2 = intercept[SparkException] {
+ spark.read
+ .option("rowTag", "ROW")
+ .option("multiLine", true)
+ .xml(inputFile.toURI.toString)
+ .collect()
+ }
+ assert(ExceptionUtils.getRootCause(e2).isInstanceOf[EOFException])
+ assert(ExceptionUtils.getRootCause(e2).getMessage === "Unexpected end of input stream")
Review Comment:
These two cases have different multiline options
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org
Re: [PR] [SPARK-46248][SQL] XML: Support for ignoreCorruptFiles and ignoreMissingFiles options [spark]
Posted by "HyukjinKwon (via GitHub)" <gi...@apache.org>.
HyukjinKwon commented on PR #44163:
URL: https://github.com/apache/spark/pull/44163#issuecomment-1867064220
I think the test failure is related ... dunno how and why though. They aren't known as flaky ones, and the tests fail after running XML tests.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org
Re: [PR] [SPARK-46248][SQL] XML: Support for ignoreCorruptFiles and ignoreMissingFiles options [spark]
Posted by "shujingyang-db (via GitHub)" <gi...@apache.org>.
shujingyang-db commented on code in PR #44163:
URL: https://github.com/apache/spark/pull/44163#discussion_r1424733989
##########
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/xml/StaxXmlParser.scala:
##########
@@ -604,6 +606,24 @@ class XmlTokenizer(
return Some(str)
}
} catch {
Review Comment:
Thanks for putting this down! 👍
##########
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/xml/StaxXmlParser.scala:
##########
@@ -604,6 +606,24 @@ class XmlTokenizer(
return Some(str)
}
} catch {
Review Comment:
Thanks for putting this down! 👍
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org