alamb commented on code in PR #7336:
URL: https://github.com/apache/arrow-datafusion/pull/7336#discussion_r1301714499
##########
datafusion/common/Cargo.toml:
##########
@@ -34,19 +34,34 @@ path = "src/lib.rs"
[features]
avro = ["apache-avro"]
-default = []
+compression = ["xz2", "bzip2", "flate2", "zstd", "async-compression"]
+default = ["compression"]
pyarrow = ["pyo3", "arrow/pyarrow"]
[dependencies]
apache-avro = { version = "0.15", default-features = false, features =
["snappy"], optional = true }
arrow = { workspace = true }
arrow-array = { workspace = true }
+async-compression = { version = "0.4.0", features = ["bzip2", "gzip", "xz",
"zstd", "futures-io", "tokio"], optional = true }
+bytes = "1.4"
+bzip2 = { version = "0.4.3", optional = true }
chrono = { version = "0.4", default-features = false }
+flate2 = { version = "1.0.24", optional = true }
+futures = "0.3"
num_cpus = "1.13.0"
object_store = { version = "0.6.1", default-features = false, optional = true }
parquet = { workspace = true, optional = true }
pyo3 = { version = "0.19.0", optional = true }
sqlparser = { workspace = true }
+tokio = { version = "1.28", features = ["macros", "rt", "rt-multi-thread",
"sync", "fs", "parking_lot"] }
Review Comment:
I think some users of datafusion only use parts of it (like dask-sql only
uses the parser / optimizer as I understand it). So I just worry that adding
stuff to datafusion_common makes the dependency footprint for those projects
larger
But I actually haven't checked the footprint / needs of other systems so I
have no specific concerns or requirements I can share
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
