Skip to content

Initial commit of hadoop file system (credit vnvo2409) #1197

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
merged 4 commits into from
Nov 18, 2020
Merged

Initial commit of hadoop file system (credit vnvo2409) #1197

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
9a89bbb
Initial commit of hadoop file system
yongtang Nov 13, 2020
9b7fb29
Update namespace to avoid collision/conflict
yongtang Nov 17, 2020
baae1eb
Add a wrapper to HadoopFileSystem so that it will only be lazily loaded.
yongtang Nov 17, 2020
3125918
Address review comments
yongtang Nov 17, 2020
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: 11 additions & 0 deletions WORKSPACE
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1052,3 +1052,14 @@ http_archive(
"https://pilotfiber.dl.sourceforge.net/project/giflib/giflib-5.2.1.tar.gz",
],
)

http_archive(
name = "hadoop",
build_file = "//third_party:hadoop.BUILD",
sha256 = "5fd5831b12b1e0999bd352d6cca11ef80f883c81ffa898e53c68d8fe8d170e9f",
strip_prefix = "hadoop-3.3.0-src",
urls = [
"https://storage.googleapis.com/mirror.tensorflow.org/downloads.apache.org/hadoop/common/hadoop-3.3.0/hadoop-3.3.0-src.tar.gz",
"https://downloads.apache.org/hadoop/common/hadoop-3.3.0/hadoop-3.3.0-src.tar.gz",
],
)
1 change: 1 addition & 0 deletions tensorflow_io/core/plugins/BUILD
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -30,6 +30,7 @@ cc_library(
linkstatic = True,
deps = [
"//tensorflow_io/core/plugins/az",
"//tensorflow_io/core/plugins/hdfs",
"//tensorflow_io/core/plugins/http",
"//tensorflow_io/core/plugins/s3",
],
Expand Down
3 changes: 2 additions & 1 deletion tensorflow_io/core/plugins/file_system_plugins.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,11 +18,12 @@ limitations under the License.
void TF_InitPlugin(TF_FilesystemPluginInfo* info) {
info->plugin_memory_allocate = tensorflow::io::plugin_memory_allocate;
info->plugin_memory_free = tensorflow::io::plugin_memory_free;
info->num_schemes = 3;
info->num_schemes = 4;
info->ops = static_cast<TF_FilesystemPluginOps*>(
tensorflow::io::plugin_memory_allocate(info->num_schemes *
sizeof(info->ops[0])));
tensorflow::io::az::ProvideFilesystemSupportFor(&info->ops[0], "az");
tensorflow::io::http::ProvideFilesystemSupportFor(&info->ops[1], "http");
tensorflow::io::s3::ProvideFilesystemSupportFor(&info->ops[2], "s3e");
tensorflow::io::hdfs::ProvideFilesystemSupportFor(&info->ops[3], "hdfse");
}
6 changes: 6 additions & 0 deletions tensorflow_io/core/plugins/file_system_plugins.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -32,6 +32,12 @@ void ProvideFilesystemSupportFor(TF_FilesystemPluginOps* ops, const char* uri);

} // namespace az

namespace hdfs {

void ProvideFilesystemSupportFor(TF_FilesystemPluginOps* ops, const char* uri);

} // namespace hdfs

namespace http {

void ProvideFilesystemSupportFor(TF_FilesystemPluginOps* ops, const char* uri);
Expand Down
22 changes: 22 additions & 0 deletions tensorflow_io/core/plugins/hdfs/BUILD
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,22 @@
licenses(["notice"]) # Apache 2.0

package(default_visibility = ["//visibility:public"])

load(
"//:tools/build/tensorflow_io.bzl",
"tf_io_copts",
)

cc_library(
name = "hdfs",
srcs = [
"hadoop_filesystem.cc",
],
copts = tf_io_copts(),
linkstatic = True,
deps = [
"//tensorflow_io/core/plugins:plugins_header",
"@hadoop",
],
alwayslink = 1,
)
Loading