I want use ParquetDatasetFactory to create a dataset for s3, but failed! The 
error message as follows


/build/apache-arrow-7.0.0/cpp/src/arrow/result.cc:28: ValueOrDie called on an 
error: IOError: Path does not exist 'iceberg-test/warehouse/test/metadata' 
/lib/x86_64-linux-gnu/libarrow.so.700(+0x10430bb)[0x7f4ee6fe50bb] 
/lib/x86_64-linux-gnu/libarrow.so.700(_ZN5arrow4util8ArrowLogD1Ev+0xed)[0x7f4ee6fe52fd]
 
/lib/x86_64-linux-gnu/libarrow.so.700(_ZN5arrow8internal17InvalidValueOrDieERKNS_6StatusE+0x17e)[0x7f4ee7104a2e]
 ./example(+0xd97d)[0x564087f3e97d] ./example(+0x8bc2)[0x564087f39bc2] 
./example(+0x94c8)[0x564087f3a4c8] ./example(+0x9fb4)[0x564087f3afb4] 
/lib/x86_64-linux-gnu/libc.so.6(__libc_start_main+0xf3)[0x7f4ee572b0b3] 
./example(+0x69fe)[0x564087f379fe] Aborted (core dumped)


In the follow code snippet??There is a line of comment code??use 
FileSystemDatasetFactory to create dataset, It works well, Can't a dataset be 
created through a ParquetDatasetFactory????


std::shared_ptr<ds::Dataset&gt; GetDatasetFromS3(const std::string&amp; 
access_key,
                                              const std::string&amp; secret_key,
                                              const std::string&amp; 
endpoint_override,
                                              const std::string&amp; 
bucket_uri) {
  EnsureS3Initialized();

  S3Options s3Options = S3Options::FromAccessKey(access_key, secret_key);
  s3Options.endpoint_override = endpoint_override;
  s3Options.scheme = "http";

  std::shared_ptr<S3FileSystem&gt; s3fs = 
S3FileSystem::Make(s3Options).ValueOrDie();

  std::string path;
  std::stringstream ss;
  ss << "s3://" << access_key << ":" << secret_key
      << "@" << K_METADATA_PATH
      << "?scheme=http&amp;endpoint_override=" << endpoint_override;
  auto fs = arrow::fs::FileSystemFromUri(ss.str(), &amp;path).ValueOrDie();
  // auto fileInfo = fs-&gt;GetFileInfo().ValueOrDie();

  auto format = std::make_shared<ParquetFileFormat&gt;();

  // FileSelector selector;
  // selector.base_dir = bucket_uri;

  // FileSystemFactoryOptions options;
  ds::ParquetFactoryOptions options;

  std::string metadata_path = bucket_uri;

  ds::FileSource source(bucket_uri, s3fs);
  //auto factory = ds::ParquetDatasetFactory::Make(source, bucket_uri, fs, 
format, options).ValueOrDie();
  auto factory = ds::ParquetDatasetFactory::Make(path, fs, format, 
options).ValueOrDie();

  //auto factory = FileSystemDatasetFactory::Make(s3fs, selector, format, 
options).ValueOrDie();
  return factory-&gt;Finish().ValueOrDie();
}

Reply via email to