aboutsummaryrefslogtreecommitdiff
path: root/common/unsafe/src/main/java
diff options
context:
space:
mode:
authorNathan Howell <nhowell@godaddy.com>2016-12-01 21:40:49 -0800
committerReynold Xin <rxin@databricks.com>2016-12-01 21:40:49 -0800
commitc82f16c15e0d4bfc54fb890a667d9164a088b5c6 (patch)
tree64d4c58b9c780e27135e33bfc9667abbc5d85ea0 /common/unsafe/src/main/java
parentd3c90b74edecc527ee468bead41d1cca0b667668 (diff)
downloadspark-c82f16c15e0d4bfc54fb890a667d9164a088b5c6.tar.gz
spark-c82f16c15e0d4bfc54fb890a667d9164a088b5c6.tar.bz2
spark-c82f16c15e0d4bfc54fb890a667d9164a088b5c6.zip
[SPARK-18658][SQL] Write text records directly to a FileOutputStream
## What changes were proposed in this pull request? This replaces uses of `TextOutputFormat` with an `OutputStream`, which will either write directly to the filesystem or indirectly via a compressor (if so configured). This avoids intermediate buffering. The inverse of this (reading directly from a stream) is necessary for streaming large JSON records (when `wholeFile` is enabled) so I wanted to keep the read and write paths symmetric. ## How was this patch tested? Existing unit tests. Author: Nathan Howell <nhowell@godaddy.com> Closes #16089 from NathanHowell/SPARK-18658.
Diffstat (limited to 'common/unsafe/src/main/java')
-rw-r--r--common/unsafe/src/main/java/org/apache/spark/unsafe/types/UTF8String.java19
1 files changed, 19 insertions, 0 deletions
diff --git a/common/unsafe/src/main/java/org/apache/spark/unsafe/types/UTF8String.java b/common/unsafe/src/main/java/org/apache/spark/unsafe/types/UTF8String.java
index e09a6b7d93..0255f53113 100644
--- a/common/unsafe/src/main/java/org/apache/spark/unsafe/types/UTF8String.java
+++ b/common/unsafe/src/main/java/org/apache/spark/unsafe/types/UTF8String.java
@@ -147,6 +147,25 @@ public final class UTF8String implements Comparable<UTF8String>, Externalizable,
buffer.position(pos + numBytes);
}
+ public void writeTo(OutputStream out) throws IOException {
+ if (base instanceof byte[] && offset >= BYTE_ARRAY_OFFSET) {
+ final byte[] bytes = (byte[]) base;
+
+ // the offset includes an object header... this is only needed for unsafe copies
+ final long arrayOffset = offset - BYTE_ARRAY_OFFSET;
+
+ // verify that the offset and length points somewhere inside the byte array
+ // and that the offset can safely be truncated to a 32-bit integer
+ if ((long) bytes.length < arrayOffset + numBytes) {
+ throw new ArrayIndexOutOfBoundsException();
+ }
+
+ out.write(bytes, (int) arrayOffset, numBytes);
+ } else {
+ out.write(getBytes());
+ }
+ }
+
/**
* Returns the number of bytes for a code point with the first byte as `b`
* @param b The first byte of a code point