[Rust] Add Reset method to buffer and cleanup comments on component.

.github/workflows/cpp.yml

@@ -175,10 +175,15 @@ jobs:
       ARROW_BUILD_STATIC: OFF
       ARROW_BOOST_USE_SHARED: OFF
       ARROW_VERBOSE_THIRDPARTY_BUILD: OFF
-      BOOST_SOURCE: BUNDLED
+      BOOST_ROOT: C:\local\boost_1_67_0
+      BOOST_LIBRARYDIR: C:\local\boost_1_67_0\lib64-msvc-14.1\
     steps:
       - name: Disable Crash Dialogs
         run: reg add "HKCU\SOFTWARE\Microsoft\Windows\Windows Error Reporting" /v DontShowUI /t REG_DWORD /d 1 /f
+      - name: Installed Packages
+        run: choco list -l
+      - name: Install Boost
+        run: choco install -y boost-msvc-14.1
       - name: Checkout Arrow
         uses: actions/checkout@v1
         with:

README.md

@@ -21,7 +21,7 @@
 
 [![Build Status](https://ci.appveyor.com/api/projects/status/github/apache/arrow/branch/master?svg=true)](https://ci.appveyor.com/project/ApacheSoftwareFoundation/arrow/branch/master)
 [![Coverage Status](https://codecov.io/gh/apache/arrow/branch/master/graph/badge.svg)](https://codecov.io/gh/apache/arrow?branch=master)
-[![Fuzzit Status](https://app.fuzzit.dev/badge?org_id=yMxZh42xl9qy6bvg3EiJ&branch=master)](https://app.fuzzit.dev/admin/yMxZh42xl9qy6bvg3EiJ/dashboard)
+[![Fuzzing Status](https://oss-fuzz-build-logs.storage.googleapis.com/badges/arrow.svg)](https://bugs.chromium.org/p/oss-fuzz/issues/list?sort=-opened&can=1&q=proj:arrow)
 [![License](http://img.shields.io/:license-Apache%202-blue.svg)](https://github.com/apache/arrow/blob/master/LICENSE.txt)
 [![Twitter Follow](https://img.shields.io/twitter/follow/apachearrow.svg?style=social&label=Follow)](https://twitter.com/apachearrow)
 

ci/docker/conda-python-dask.dockerfile

@@ -23,3 +23,6 @@ FROM ${repo}:${arch}-conda-python-${python}
 ARG dask=latest
 COPY ci/scripts/install_dask.sh /arrow/ci/scripts/
 RUN /arrow/ci/scripts/install_dask.sh ${dask}
+
+# The Spark tests currently break with pandas >= 1.0
+RUN if [ ${dask} == "latest" ]; then conda install pandas=0.25.3; fi

cpp/src/arrow/compare.cc

@@ -1196,6 +1196,13 @@ inline bool SparseTensorEqualsImplDispatch(const SparseTensorImpl<SparseIndexTyp
                                                                               right_csc);
     }
 
+    case SparseTensorFormat::CSF: {
+      const auto& right_csf =
+          checked_cast<const SparseTensorImpl<SparseCSFIndex>&>(right);
+      return SparseTensorEqualsImpl<SparseIndexType, SparseCSFIndex>::Compare(left,
+                                                                              right_csf);
+    }
+
     default:
       return false;
   }
@@ -1232,6 +1239,11 @@ bool SparseTensorEquals(const SparseTensor& left, const SparseTensor& right) {
       return SparseTensorEqualsImplDispatch(left_csc, right);
     }
 
+    case SparseTensorFormat::CSF: {
+      const auto& left_csf = checked_cast<const SparseTensorImpl<SparseCSFIndex>&>(left);
+      return SparseTensorEqualsImplDispatch(left_csf, right);
+    }
+
     default:
       return false;
   }

cpp/src/arrow/dataset/file_ipc_test.cc

@@ -34,16 +34,14 @@
 namespace arrow {
 namespace dataset {
 
-constexpr int64_t kDefaultOutputStreamSize = 1024;
 constexpr int64_t kBatchSize = 1UL << 12;
 constexpr int64_t kBatchRepetitions = 1 << 5;
 constexpr int64_t kNumRows = kBatchSize * kBatchRepetitions;
 
 class ArrowIpcWriterMixin : public ::testing::Test {
  public:
   std::shared_ptr<Buffer> Write(std::vector<RecordBatchReader*> readers) {
-    EXPECT_OK_AND_ASSIGN(auto sink, io::BufferOutputStream::Create(
-                                        kDefaultOutputStreamSize, default_memory_pool()));
+    EXPECT_OK_AND_ASSIGN(auto sink, io::BufferOutputStream::Create());
     auto writer_schema = readers[0]->schema();
 
     EXPECT_OK_AND_ASSIGN(auto writer,
@@ -69,8 +67,7 @@ class ArrowIpcWriterMixin : public ::testing::Test {
   }
 
   std::shared_ptr<Buffer> Write(const Table& table) {
-    EXPECT_OK_AND_ASSIGN(auto sink, io::BufferOutputStream::Create(
-                                        kDefaultOutputStreamSize, default_memory_pool()));
+    EXPECT_OK_AND_ASSIGN(auto sink, io::BufferOutputStream::Create());
 
     EXPECT_OK_AND_ASSIGN(auto writer,
                          ipc::RecordBatchFileWriter::Open(sink.get(), table.schema()));

cpp/src/arrow/extension_type_test.cc

@@ -217,7 +217,7 @@ TEST_F(TestExtensionType, ExtensionTypeTest) {
 
 auto RoundtripBatch = [](const std::shared_ptr<RecordBatch>& batch,
                          std::shared_ptr<RecordBatch>* out) {
-  ASSERT_OK_AND_ASSIGN(auto out_stream, io::BufferOutputStream::Create(1024));
+  ASSERT_OK_AND_ASSIGN(auto out_stream, io::BufferOutputStream::Create());
   ASSERT_OK(ipc::WriteRecordBatchStream({batch}, ipc::IpcOptions::Defaults(),
                                         out_stream.get()));
 
@@ -255,7 +255,7 @@ TEST_F(TestExtensionType, UnrecognizedExtension) {
 
   // Write full IPC stream including schema, then unregister type, then read
   // and ensure that a plain instance of the storage type is created
-  ASSERT_OK_AND_ASSIGN(auto out_stream, io::BufferOutputStream::Create(1024));
+  ASSERT_OK_AND_ASSIGN(auto out_stream, io::BufferOutputStream::Create());
   ASSERT_OK(ipc::WriteRecordBatchStream({batch}, ipc::IpcOptions::Defaults(),
                                         out_stream.get()));
 

cpp/src/arrow/flight/test_util.cc

@@ -454,7 +454,8 @@ Status TestClientBasicAuthHandler::GetToken(std::string* token) {
 Status GetTestResourceRoot(std::string* out) {
   const char* c_root = std::getenv("ARROW_TEST_DATA");
   if (!c_root) {
-    return Status::IOError("Test resources not found, set ARROW_TEST_DATA");
+    return Status::IOError(
+        "Test resources not found, set ARROW_TEST_DATA to <repo root>/testing/data");
   }
   *out = std::string(c_root);
   return Status::OK();

cpp/src/arrow/io/compressed_test.cc

@@ -127,7 +127,7 @@ void CheckCompressedInputStream(Codec* codec, const std::vector<uint8_t>& data)
 void CheckCompressedOutputStream(Codec* codec, const std::vector<uint8_t>& data,
                                  bool do_flush) {
   // Create compressed output stream
-  ASSERT_OK_AND_ASSIGN(auto buffer_writer, BufferOutputStream::Create(1024));
+  ASSERT_OK_AND_ASSIGN(auto buffer_writer, BufferOutputStream::Create());
   ASSERT_OK_AND_ASSIGN(auto stream, CompressedOutputStream::Make(codec, buffer_writer));
   ASSERT_OK_AND_EQ(0, stream->Tell());
 

cpp/src/arrow/io/memory.h

@@ -46,7 +46,7 @@ class ARROW_EXPORT BufferOutputStream : public OutputStream {
   /// \param[in,out] pool a MemoryPool to use for allocations
   /// \return the created stream
   static Result<std::shared_ptr<BufferOutputStream>> Create(
-      int64_t initial_capacity, MemoryPool* pool = default_memory_pool());
+      int64_t initial_capacity = 4096, MemoryPool* pool = default_memory_pool());
 
   ARROW_DEPRECATED("Use Result-returning overload")
   static Status Create(int64_t initial_capacity, MemoryPool* pool,

cpp/src/arrow/ipc/feather_test.cc

@@ -281,7 +281,7 @@ void CheckBatches(const RecordBatch& expected, const RecordBatch& result) {
 class TestTableReader : public ::testing::Test {
  public:
   void SetUp() {
-    ASSERT_OK_AND_ASSIGN(stream_, io::BufferOutputStream::Create(1024));
+    ASSERT_OK_AND_ASSIGN(stream_, io::BufferOutputStream::Create());
     ASSERT_OK(TableWriter::Open(stream_, &writer_));
   }
 
@@ -356,7 +356,7 @@ TEST_F(TestTableReader, ReadNames) {
 class TestTableWriter : public ::testing::Test {
  public:
   void SetUp() {
-    ASSERT_OK_AND_ASSIGN(stream_, io::BufferOutputStream::Create(1024));
+    ASSERT_OK_AND_ASSIGN(stream_, io::BufferOutputStream::Create());
     ASSERT_OK(TableWriter::Open(stream_, &writer_));
   }