Skip to content

Don't create as many garbage objects during reads #12

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

Open
ash211 wants to merge 1 commit into
base: master
Choose a base branch
from
Open

Don't create as many garbage objects during reads #12

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
28 changes: 12 additions & 16 deletions src/main/java/com/bizo/hive/serde/csv/CSVSerde.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -26,6 +26,7 @@
import org.apache.hadoop.io.Text;
import org.apache.hadoop.io.Writable;

import au.com.bytecode.opencsv.CSVParser;
import au.com.bytecode.opencsv.CSVReader;
import au.com.bytecode.opencsv.CSVWriter;

Expand All @@ -45,7 +46,7 @@ public final class CSVSerde implements SerDe {
private char separatorChar;
private char quoteChar;
private char escapeChar;

private CSVParser csvParser;

@Override
public void initialize(final Configuration conf, final Properties tbl) throws SerDeException {
Expand All @@ -71,6 +72,11 @@ public void initialize(final Configuration conf, final Properties tbl) throws Se
separatorChar = getProperty(tbl, "separatorChar", CSVWriter.DEFAULT_SEPARATOR);
quoteChar = getProperty(tbl, "quoteChar", CSVWriter.DEFAULT_QUOTE_CHARACTER);
escapeChar = getProperty(tbl, "escapeChar", CSVWriter.DEFAULT_ESCAPE_CHARACTER);
if (CSVWriter.DEFAULT_ESCAPE_CHARACTER == escapeChar) {
this.csvParser = new CSVParser(separatorChar, quoteChar);
} else {
this.csvParser = new CSVParser(separatorChar, quoteChar, escapeChar);
}
}

private final char getProperty(final Properties tbl, final String property, final char def) {
Expand Down Expand Up @@ -122,15 +128,13 @@ public Writable serialize(Object obj, ObjectInspector objInspector) throws SerDe
@Override
public Object deserialize(final Writable blob) throws SerDeException {
Text rowText = (Text) blob;

CSVReader csv = null;

try {
csv = newReader(new CharArrayReader(rowText.toString().toCharArray()), separatorChar, quoteChar, escapeChar);
final String[] read = csv.readNext();
final String[] strings = this.csvParser.parseLine(rowText.toString());

for (int i=0; i< numCols; i++) {
if (read != null && i < read.length) {
row.set(i, read[i]);
for (int i=0; i < numCols; i++) {
if (strings != null && i < strings.length) {
row.set(i, strings[i]);
} else {
row.set(i, null);
}
Expand All @@ -139,14 +143,6 @@ public Object deserialize(final Writable blob) throws SerDeException {
return row;
} catch (final Exception e) {
throw new SerDeException(e);
} finally {
if (csv != null) {
try {
csv.close();
} catch (final Exception e) {
// ignore
}
}
}
}

Expand Down