Skip to content

[Improve][HDFS][#1336] Fix the path problem of writing to HDFS. #1337

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
FlechazoW merged 1 commit into from
Oct 24, 2022
Merged

[Improve][HDFS][#1336] Fix the path problem of writing to HDFS. #1337

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
11 changes: 8 additions & 3 deletions ...ctor-hdfs/src/main/java/com/dtstack/chunjun/connector/hdfs/sink/BaseHdfsOutputFormat.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -38,7 +38,6 @@
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.fs.PathFilter;

import java.io.File;
import java.io.IOException;
import java.util.ArrayList;
import java.util.List;
Expand Down Expand Up @@ -119,6 +118,12 @@ protected void checkOutputDir() {
}
}

/** 文件分隔符(File.separatorChar)在windows为\，而在linux中为/，在hadoop中路径需要固定为/， */

@FlechazoW FlechazoW Oct 24, 2022

Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Can you comment in English?

protected char getHdfsPathChar() {
// hadoop 文件系统固定为/，避免路径不对，文件写入错误及移动失败

@FlechazoW FlechazoW Oct 24, 2022

Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Same as above.

return '/';
}

@Override
protected void deleteDataDir() {
deleteDirectory(outputFilePath);
Expand Down Expand Up @@ -160,7 +165,7 @@ public String getExtension() {

@Override
protected long getCurrentFileSize() {
String path = tmpPath + File.separatorChar + currentFileName;
String path = tmpPath + getHdfsPathChar() + currentFileName;
try {
if (hdfsConf.getMaxFileSize() > ConstantValue.STORE_SIZE_G) {
return fs.getFileStatus(new Path(path)).getLen();
Expand Down Expand Up @@ -203,7 +208,7 @@ protected void deleteDataFiles(List<String> preCommitFilePathList, String path)
String currentFilePath = "";
try {
for (String fileName : this.preCommitFilePathList) {
currentFilePath = path + File.separatorChar + fileName;
currentFilePath = path + getHdfsPathChar() + fileName;
Path commitFilePath = new Path(currentFilePath);
fs.delete(commitFilePath, true);
LOG.info("delete file:{}", currentFilePath);
Expand Down
3 changes: 1 addition & 2 deletions ...ector-hdfs/src/main/java/com/dtstack/chunjun/connector/hdfs/sink/HdfsOrcOutputFormat.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -51,7 +51,6 @@
import org.apache.hadoop.mapred.RecordWriter;
import org.apache.hadoop.mapred.Reporter;

import java.io.File;
import java.io.IOException;
import java.lang.reflect.Field;
import java.util.ArrayList;
Expand Down Expand Up @@ -163,7 +162,7 @@ protected void nextBlock() {
}

try {
String currentBlockTmpPath = tmpPath + File.separatorChar + currentFileName;
String currentBlockTmpPath = tmpPath + getHdfsPathChar() + currentFileName;
recordWriter =
outputFormat.getRecordWriter(null, jobConf, currentBlockTmpPath, Reporter.NULL);
currentFileIndex++;
Expand Down
3 changes: 1 addition & 2 deletions ...r-hdfs/src/main/java/com/dtstack/chunjun/connector/hdfs/sink/HdfsParquetOutputFormat.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -48,7 +48,6 @@
import org.apache.parquet.schema.PrimitiveType;
import org.apache.parquet.schema.Types;

import java.io.File;
import java.io.IOException;
import java.security.PrivilegedAction;
import java.util.HashMap;
Expand Down Expand Up @@ -95,7 +94,7 @@ protected void nextBlock() {
}

try {
String currentBlockTmpPath = tmpPath + File.separatorChar + currentFileName;
String currentBlockTmpPath = tmpPath + getHdfsPathChar() + currentFileName;
Path writePath = new Path(currentBlockTmpPath);

// Compatible with old code
Expand Down
3 changes: 1 addition & 2 deletions ...ctor-hdfs/src/main/java/com/dtstack/chunjun/connector/hdfs/sink/HdfsTextOutputFormat.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -32,7 +32,6 @@
import org.apache.commons.compress.compressors.gzip.GzipCompressorOutputStream;
import org.apache.hadoop.fs.Path;

import java.io.File;
import java.io.IOException;
import java.io.OutputStream;

Expand All @@ -55,7 +54,7 @@ protected void nextBlock() {
}

try {
String currentBlockTmpPath = tmpPath + File.separatorChar + currentFileName;
String currentBlockTmpPath = tmpPath + getHdfsPathChar() + currentFileName;
Path p = new Path(currentBlockTmpPath);

if (CompressType.TEXT_NONE.equals(compressType)) {
Expand Down