Repository: hadoop Updated Branches: refs/heads/branch-2 e163c1e0d -> f02c06965 refs/heads/trunk b543d1a39 -> 3dfa8161f
HADOOP-12009 Clarify FileSystem.listStatus() sorting order & fix FileSystemContractBaseTest:testListStatus. (J.Andreina via stevel) Project: http://git-wip-us.apache.org/repos/asf/hadoop/repo Commit: http://git-wip-us.apache.org/repos/asf/hadoop/commit/f02c0696 Tree: http://git-wip-us.apache.org/repos/asf/hadoop/tree/f02c0696 Diff: http://git-wip-us.apache.org/repos/asf/hadoop/diff/f02c0696 Branch: refs/heads/branch-2 Commit: f02c06965c7caecb64c56c65b03648e998643c67 Parents: e163c1e Author: Steve Loughran <[email protected]> Authored: Sun Jun 28 19:13:48 2015 +0100 Committer: Steve Loughran <[email protected]> Committed: Sun Jun 28 19:13:48 2015 +0100 ---------------------------------------------------------------------- hadoop-common-project/hadoop-common/CHANGES.txt | 4 ++++ .../main/java/org/apache/hadoop/fs/FileSystem.java | 17 ++++++++++++++++- .../src/site/markdown/filesystem/filesystem.md | 4 ++++ .../hadoop/fs/FileSystemContractBaseTest.java | 11 ++++++++--- 4 files changed, 32 insertions(+), 4 deletions(-) ---------------------------------------------------------------------- http://git-wip-us.apache.org/repos/asf/hadoop/blob/f02c0696/hadoop-common-project/hadoop-common/CHANGES.txt ---------------------------------------------------------------------- diff --git a/hadoop-common-project/hadoop-common/CHANGES.txt b/hadoop-common-project/hadoop-common/CHANGES.txt index 0f87877..3409e59 100644 --- a/hadoop-common-project/hadoop-common/CHANGES.txt +++ b/hadoop-common-project/hadoop-common/CHANGES.txt @@ -163,6 +163,10 @@ Release 2.8.0 - UNRELEASED HADOOP-11958. MetricsSystemImpl fails to show backtrace when an error occurs (Jason Lowe via jeagles) + + HADOOP-12009 Clarify FileSystem.listStatus() sorting order & fix + FileSystemContractBaseTest:testListStatus. (J.Andreina via stevel) + OPTIMIZATIONS HADOOP-11785. Reduce the number of listStatus operation in distcp http://git-wip-us.apache.org/repos/asf/hadoop/blob/f02c0696/hadoop-common-project/hadoop-common/src/main/java/org/apache/hadoop/fs/FileSystem.java ---------------------------------------------------------------------- diff --git a/hadoop-common-project/hadoop-common/src/main/java/org/apache/hadoop/fs/FileSystem.java b/hadoop-common-project/hadoop-common/src/main/java/org/apache/hadoop/fs/FileSystem.java index 48633a1..c8f8aa1 100644 --- a/hadoop-common-project/hadoop-common/src/main/java/org/apache/hadoop/fs/FileSystem.java +++ b/hadoop-common-project/hadoop-common/src/main/java/org/apache/hadoop/fs/FileSystem.java @@ -1498,7 +1498,9 @@ public abstract class FileSystem extends Configured implements Closeable { /** * List the statuses of the files/directories in the given path if the path is * a directory. - * + * <p> + * Does not guarantee to return the List of files/directories status in a + * sorted order. * @param f given path * @return the statuses of the files/directories in the given patch * @throws FileNotFoundException when the path does not exist; @@ -1540,6 +1542,9 @@ public abstract class FileSystem extends Configured implements Closeable { /** * Filter files/directories in the given path using the user-supplied path * filter. + * <p> + * Does not guarantee to return the List of files/directories status in a + * sorted order. * * @param f * a path name @@ -1560,6 +1565,9 @@ public abstract class FileSystem extends Configured implements Closeable { /** * Filter files/directories in the given list of paths using default * path filter. + * <p> + * Does not guarantee to return the List of files/directories status in a + * sorted order. * * @param files * a list of paths @@ -1576,6 +1584,9 @@ public abstract class FileSystem extends Configured implements Closeable { /** * Filter files/directories in the given list of paths using user-supplied * path filter. + * <p> + * Does not guarantee to return the List of files/directories status in a + * sorted order. * * @param files * a list of paths @@ -1737,6 +1748,8 @@ public abstract class FileSystem extends Configured implements Closeable { * while consuming the entries. Each file system implementation should * override this method and provide a more efficient implementation, if * possible. + * Does not guarantee to return the iterator that traverses statuses + * of the files in a sorted order. * * @param p target path * @return remote iterator @@ -1764,6 +1777,8 @@ public abstract class FileSystem extends Configured implements Closeable { /** * List the statuses and block locations of the files in the given path. + * Does not guarantee to return the iterator that traverses statuses + * of the files in a sorted order. * * If the path is a directory, * if recursive is false, returns files in the directory; http://git-wip-us.apache.org/repos/asf/hadoop/blob/f02c0696/hadoop-common-project/hadoop-common/src/site/markdown/filesystem/filesystem.md ---------------------------------------------------------------------- diff --git a/hadoop-common-project/hadoop-common/src/site/markdown/filesystem/filesystem.md b/hadoop-common-project/hadoop-common/src/site/markdown/filesystem/filesystem.md index 84e3755..f323374 100644 --- a/hadoop-common-project/hadoop-common/src/site/markdown/filesystem/filesystem.md +++ b/hadoop-common-project/hadoop-common/src/site/markdown/filesystem/filesystem.md @@ -183,6 +183,10 @@ to the same path: forall fs in listStatus(Path) : fs == getFileStatus(fs.path) +**Ordering of results**: there is no guarantee of ordering of the listed entries. +While HDFS currently returns an alphanumerically sorted list, neither the Posix `readdir()` +nor Java's `File.listFiles()` API calls define any ordering of returned values. Applications +which require a uniform sort order on the results must perform the sorting themselves. ### Atomicity and Consistency http://git-wip-us.apache.org/repos/asf/hadoop/blob/f02c0696/hadoop-common-project/hadoop-common/src/test/java/org/apache/hadoop/fs/FileSystemContractBaseTest.java ---------------------------------------------------------------------- diff --git a/hadoop-common-project/hadoop-common/src/test/java/org/apache/hadoop/fs/FileSystemContractBaseTest.java b/hadoop-common-project/hadoop-common/src/test/java/org/apache/hadoop/fs/FileSystemContractBaseTest.java index 84e4e43..f3d33df 100644 --- a/hadoop-common-project/hadoop-common/src/test/java/org/apache/hadoop/fs/FileSystemContractBaseTest.java +++ b/hadoop-common-project/hadoop-common/src/test/java/org/apache/hadoop/fs/FileSystemContractBaseTest.java @@ -20,6 +20,7 @@ package org.apache.hadoop.fs; import java.io.FileNotFoundException; import java.io.IOException; +import java.util.ArrayList; import junit.framework.TestCase; @@ -203,9 +204,13 @@ public abstract class FileSystemContractBaseTest extends TestCase { paths = fs.listStatus(path("/test/hadoop")); assertEquals(3, paths.length); - assertEquals(path("/test/hadoop/a"), paths[0].getPath()); - assertEquals(path("/test/hadoop/b"), paths[1].getPath()); - assertEquals(path("/test/hadoop/c"), paths[2].getPath()); + ArrayList<String> list = new ArrayList<String>(); + for (FileStatus fileState : paths) { + list.add(fileState.getPath().toString()); + } + assertTrue(list.contains(path("/test/hadoop/a"))); + assertTrue(list.contains(path("/test/hadoop/b"))); + assertTrue(list.contains(path("/test/hadoop/c"))); paths = fs.listStatus(path("/test/hadoop/a")); assertEquals(0, paths.length);
