Merge branch 'tensorflow:master' into devel

.bazelversion

@@ -1 +1 @@
-4.2.1
+5.0.0

README.md

@@ -126,6 +126,8 @@ of releases [here](https://github.com/tensorflow/io/releases).
 
 | TensorFlow I/O Version | TensorFlow Compatibility | Release Date |
 | --- | --- | --- |
+| 0.26.0 | 2.9.x | May 17, 2022 |
+| 0.25.0 | 2.8.x | Apr 19, 2022 |
 | 0.24.0 | 2.8.x | Feb 04, 2022 |
 | 0.23.1 | 2.7.x | Dec 15, 2021 |
 | 0.23.0 | 2.7.x | Dec 14, 2021 |

RELEASE.md

@@ -1,3 +1,33 @@
+# Release 0.26.0
+
+## Major Features and Bug Fixes
+* Updated arrow version to 7.0.0
+
+## Thanks to our Contributors
+
+This release contains contributions from many people:
+
+372046933, Colin, Yong Tang
+
+We are also grateful to all who filed issues or helped resolve them, asked and
+answered questions, and were part of inspiring discussions.
+
+# Release 0.25.0
+
+## Major Features and Bug Fixes
+* Decrease max bytes read from hdfs
+* Hide mongodb connection uri from being logged
+* Update log level from fetal to error when loading the libhdfs.so failed
+
+## Thanks to our Contributors
+
+This release contains contributions from many people:
+
+Junfan Zhang, Stan Chen, Vignesh Kothapalli, Yong Tang, trabenx, yleeeee
+
+We are also grateful to all who filed issues or helped resolve them, asked and
+answered questions, and were part of inspiring discussions.
+
 # Release 0.24.0
 
 ## Major Features and Bug Fixes

WORKSPACE

@@ -6,11 +6,12 @@ load("@bazel_tools//tools/build_defs/repo:http.bzl", "http_archive")
 http_archive(
     name = "zlib",
     build_file = "//third_party:zlib.BUILD",
-    sha256 = "c3e5e9fdd5004dcb542feda5ee4f0ff0744628baf8ed2dd5d66f8ca1197cb1a1",
-    strip_prefix = "zlib-1.2.11",
+    patch_cmds = ["""sed -i.bak '29i\\'$'\\n#include<zconf.h>\\n' contrib/minizip/crypt.h"""],
+    sha256 = "91844808532e5ce316b3c010929493c0244f3d37593afd6de04f71821d5136d9",
+    strip_prefix = "zlib-1.2.12",
     urls = [
-        "https://storage.googleapis.com/mirror.tensorflow.org/zlib.net/zlib-1.2.11.tar.gz",
-        "https://zlib.net/zlib-1.2.11.tar.gz",
+        "https://storage.googleapis.com/mirror.tensorflow.org/zlib.net/zlib-1.2.12.tar.gz",
+        "https://zlib.net/zlib-1.2.12.tar.gz",
     ],
 )
 
@@ -114,10 +115,10 @@ pip_install()
 
 http_archive(
     name = "org_tensorflow",
-    sha256 = "66b953ae7fba61fd78969a2e24e350b26ec116cf2e6a7eb93d02c63939c6f9f7",
-    strip_prefix = "tensorflow-2.8.0",
+    sha256 = "8087cb0c529f04a4bfe480e49925cd64a904ad16d8ec66b98e2aacdfd53c80ff",
+    strip_prefix = "tensorflow-2.9.0",
     urls = [
-        "https://github.com/tensorflow/tensorflow/archive/refs/tags/v2.8.0.tar.gz",
+        "https://github.com/tensorflow/tensorflow/archive/refs/tags/v2.9.0.tar.gz",
     ],
 )
 
@@ -157,16 +158,11 @@ http_archive(
 http_archive(
     name = "arrow",
     build_file = "//third_party:arrow.BUILD",
-    patch_cmds = [
-        # TODO: Remove the fowllowing once arrow issue is resolved.
-        """sed -i.bak 's/type_traits/std::max<int16_t>(sizeof(int16_t), type_traits/g' cpp/src/parquet/column_reader.cc""",
-        """sed -i.bak 's/value_byte_size/value_byte_size)/g' cpp/src/parquet/column_reader.cc""",
-    ],
-    sha256 = "a27971e2a71c412ae43d998b7b6d06201c7a3da382c804dcdc4a8126ccbabe67",
-    strip_prefix = "arrow-apache-arrow-4.0.0",
+    sha256 = "57e13c62f27b710e1de54fd30faed612aefa22aa41fa2c0c3bacd204dd18a8f3",
+    strip_prefix = "arrow-apache-arrow-7.0.0",
     urls = [
-        "https://storage.googleapis.com/mirror.tensorflow.org/github.com/apache/arrow/archive/apache-arrow-4.0.0.tar.gz",
-        "https://github.com/apache/arrow/archive/apache-arrow-4.0.0.tar.gz",
+        "https://storage.googleapis.com/mirror.tensorflow.org/github.com/apache/arrow/archive/apache-arrow-7.0.0.tar.gz",
+        "https://github.com/apache/arrow/archive/apache-arrow-7.0.0.tar.gz",
     ],
 )
 
@@ -601,10 +597,10 @@ http_archive(
     patch_cmds = [
         "tar -xzf c++/libs/libhdfspp/libhdfspp.tar.gz -C c++/libs/libhdfspp",
     ],
-    sha256 = "abdffe48b8d2e7776c3b541ee2241401e49774941ca4a8c759e5d795daec8a45",
-    strip_prefix = "orc-rel-release-1.6.7",
+    sha256 = "39d983f4c7feb8ea1e8ab8e3e53e9afc643282b7a500b3a93c91aa6490f65c17",
+    strip_prefix = "orc-rel-release-1.6.14",
     urls = [
-        "https://github.com/apache/orc/archive/refs/tags/rel/release-1.6.7.tar.gz",
+        "https://github.com/apache/orc/archive/refs/tags/rel/release-1.6.14.tar.gz",
     ],
 )
 
@@ -861,10 +857,10 @@ http_archive(
 http_archive(
     name = "xsimd",
     build_file = "//third_party:xsimd.BUILD",
-    sha256 = "45337317c7f238fe0d64bb5d5418d264a427efc53400ddf8e6a964b6bcb31ce9",
-    strip_prefix = "xsimd-7.5.0",
+    sha256 = "21b4700e9ef70f6c9a86952047efd8272317df4e6fee35963de9394fd9c5677f",
+    strip_prefix = "xsimd-8.0.1",
     urls = [
-        "https://github.com/xtensor-stack/xsimd/archive/refs/tags/7.5.0.tar.gz",
+        "https://github.com/xtensor-stack/xsimd/archive/refs/tags/8.0.1.tar.gz",
     ],
 )
 

tensorflow_io/core/filesystems/hdfs/hadoop_filesystem.cc

@@ -241,7 +241,7 @@ class LibHDFS {
       if (TF_GetCode(status) == TF_OK) {
         return;
       } else {
-        TF_Log(TF_FATAL, "HadoopFileSystem load error: %s", TF_Message(status));
+        TF_Log(TF_ERROR, "HadoopFileSystem load error: %s", TF_Message(status));
       }
     }
 

tensorflow_io/core/kernels/arrow/arrow_dataset_ops.cc

@@ -14,9 +14,9 @@ limitations under the License.
 ==============================================================================*/
 
 #include "arrow/api.h"
+#include "arrow/io/stdio.h"
 #include "arrow/ipc/api.h"
 #include "arrow/result.h"
-#include "arrow/util/io_util.h"
 #include "tensorflow/core/framework/dataset.h"
 #include "tensorflow/core/graph/graph.h"
 #include "tensorflow/core/public/version.h"

tensorflow_io/core/kernels/json_kernels.cc

@@ -107,16 +107,20 @@ class JSONReadable : public IOReadableInterface {
 
     ::arrow::Status status;
 
-    status = ::arrow::json::TableReader::Make(
+    auto reader_result = ::arrow::json::TableReader::Make(
         ::arrow::default_memory_pool(), json_file_,
         ::arrow::json::ReadOptions::Defaults(),
-        ::arrow::json::ParseOptions::Defaults(), &reader_);
-    if (!status.ok()) {
+        ::arrow::json::ParseOptions::Defaults());
+    if (!reader_result.ok()) {
       return errors::InvalidArgument("unable to make a TableReader: ", status);
+    } else {
+      reader_ = reader_result.ValueOrDie();
     }
-    status = reader_->Read(&table_);
-    if (!status.ok()) {
+    auto table_result = reader_->Read();
+    if (!table_result.ok()) {
       return errors::InvalidArgument("unable to read table: ", status);
+    } else {
+      table_ = table_result.ValueOrDie();
     }
 
     shapes_.clear();

tensorflow_io/core/kernels/mongodb_kernels.cc

@@ -39,9 +39,6 @@ class MongoDBReadableResource : public ResourceBase {
     //   Required to initialize libmongoc's internals
     mongoc_init();
 
-    // Log the uri
-    LOG(INFO) << "Connecting to: " << uri;
-
     // Create a MongoDB URI object from the given string
 
     uri_obj_ = mongoc_uri_new_with_error(uri.c_str(), &error_);
@@ -128,7 +125,7 @@ class MongoDBReadableResource : public ResourceBase {
       return errors::FailedPrecondition(
           "Failed to ping the mongo cluster due to: ", error_.message);
     }
-    LOG(ERROR) << "Ping Successful";
+    LOG(INFO) << "MongoDB connection ping successful";
 
     return Status::OK();
   }
@@ -222,9 +219,6 @@ class MongoDBWritableResource : public ResourceBase {
     //   Required to initialize libmongoc's internals
     mongoc_init();
 
-    // Log the uri
-    LOG(INFO) << "Connecting to: " << uri;
-
     // Create a MongoDB URI object from the given string
 
     uri_obj_ = mongoc_uri_new_with_error(uri.c_str(), &error_);
@@ -308,7 +302,7 @@ class MongoDBWritableResource : public ResourceBase {
       return errors::FailedPrecondition(
           "Failed to ping the mongo cluster due to: ", error_.message);
     }
-    LOG(INFO) << "Ping Successful";
+    LOG(INFO) << "MongoDB connection ping successful";
 
     return Status::OK();
   }

tensorflow_io/python/experimental/filter_ops.py

@@ -22,7 +22,7 @@
 def pad(input, ksize, mode, constant_values):
     input = tf.convert_to_tensor(input)
     ksize = tf.convert_to_tensor(ksize)
-    mode = "CONSTANT" if mode is None else upper(mode)
+    mode = "CONSTANT" if mode is None else str.upper(mode)
     constant_values = (
         tf.zeros([], dtype=input.dtype)
         if constant_values is None

tensorflow_io/python/ops/version_ops.py

@@ -14,5 +14,5 @@
 # ==============================================================================
 """version_ops"""
 
-version = "0.24.0"
-require = "tensorflow>=2.8.0,<2.9.0"
+version = "0.26.0"
+require = "tensorflow>=2.9.0,<2.10.0"

third_party/arrow.BUILD

@@ -84,6 +84,8 @@ cc_library(
             "cpp/src/**/stream_to_file.cc",
             "cpp/src/arrow/util/bpacking_avx2.cc",
             "cpp/src/arrow/util/bpacking_avx512.cc",
+            "cpp/src/arrow/util/bpacking_neon.cc",
+            "cpp/src/arrow/util/tracing_internal.cc",
         ],
     ),
     hdrs = [

third_party/liborc.BUILD

@@ -92,7 +92,7 @@ genrule(
     srcs = ["c++/include/orc/orc-config.hh.in"],
     outs = ["c++/include/orc/orc-config.hh"],
     cmd = ("sed " +
-           "-e 's/@ORC_VERSION@/1.6.7/g' " +
+           "-e 's/@ORC_VERSION@/1.6.14/g' " +
            "-e 's/cmakedefine/define/g' " +
            "$< >$@"),
 )
@@ -107,6 +107,7 @@ genrule(
             "-e 's/cmakedefine HAS_PREAD/undef HAS_PREAD/g' " +
             "-e 's/cmakedefine NEEDS_REDUNDANT_MOVE/undef NEEDS_REDUNDANT_MOVE/g' " +
             "-e 's/cmakedefine NEEDS_Z_PREFIX/undef NEEDS_Z_PREFIX/g' " +
+            "-e 's/cmakedefine HAS_BUILTIN_OVERFLOW_CHECK/undef HAS_BUILTIN_OVERFLOW_CHECK/g' " +
             "-e 's/cmakedefine/define/g' " +
             "$< >$@"
         ),

third_party/xsimd.BUILD

@@ -10,6 +10,8 @@ cc_library(
     hdrs = glob(
         [
             "include/xsimd/*.hpp",
+            "include/xsimd/arch/*.hpp",
+            "include/xsimd/arch/generic/*.hpp",
             "include/xsimd/config/*.hpp",
             "include/xsimd/math/*.hpp",
             "include/xsimd/memory/*.hpp",

tools/release/note_update.py

@@ -55,6 +55,7 @@
 ).stdout.decode("utf-8")
 
 authors = [e.split("\t")[1].strip() for e in logs.rstrip().split("\n")]
+authors = list(filter(lambda e: e != "github-actions[bot]", authors))
 # Replace " " with "@" to allow text wrap without break names, then replace back
 authors = textwrap.fill(", ".join([e.replace(" ", "@") for e in authors]), 80).replace(
     "@", " "