remove cloud feature

Cargo.toml

@@ -6,7 +6,7 @@ repository = "https://github.com/fastlmm/bed-reader"
 readme = "README-rust.md"
 documentation = "https://docs.rs/bed-reader/latest/bed_reader/"
 authors = ["FaST-LMM Team <fastlmm-dev@python.org>"]
-license = "Apache-2.0" # toml-ignore
+license = "Apache-2.0"  # toml-ignore
 keywords = ["bioinformatics", "plink", "genomics", "genotype", "snps"]
 categories = ["science"]
 edition = "2021"
@@ -26,19 +26,8 @@ crate-type = ["cdylib", "rlib"]
 # https://github.com/PyO3/pyo3/discussions/2271
 # https://pyo3.rs/latest/faq.html#i-cant-run-cargo-test-or-i-cant-build-in-a-cargo-workspace-im-having-linker-issues-like-symbol-not-found-or-undefined-reference-to-_pyexc_systemerror
 [features]
-extension-module = ["pyo3/extension-module", "pyo3-asyncio", "cloud", "tokio/full"]
-cloud = [
-    "cloud-file",
-    "object_store",
-    "itertools",
-    "futures-util",
-    "bytes",
-    # "pyo3-asyncio",
-    # "tokio/full",
-    # "bytecount",
-    # "url"
-]
-default = ["cloud", "extension-module"] # remove extension-module from default
+extension-module = ["pyo3/extension-module", "tokio/full"]
+default = [ "extension-module"] # cmk remove extension-module from default
 
 [dependencies]
 thiserror = "1.0.40"
@@ -49,36 +38,24 @@ numpy = "0.20.0"
 ndarray = { version = "0.15.6", features = ["approx", "rayon"] }
 statrs = "0.16.0"
 byteorder = { version = "1.4.3", default-features = false }
-pyo3 = { version = "0.20.0", features = ["extension-module"], optional = true }
 dpc-pariter = "0.4.0" # //  pariter = "0.5.1"
 derive_builder = "0.13.0"
 anyinput = { version = "0.1.6", features = ["ndarray"] }
 fetch-data = "0.1.6"
-
-# Dependencies for cloud feature
-pyo3-asyncio = { version = "0.20.0", features = ["tokio-runtime"], optional = true }
-# when object_store goes to 0.9.1 check if can remove http cloud options work around code.
-object_store = { version = "0.9.0", optional = true }
-tokio = { version = "1.35.0", features = ["full"], optional = true }
-futures-util = { version = "0.3.29", optional = true }
-bytecount = { version = "0.6.7", optional = true }
-itertools = { version = "0.12.0", optional = true }
-bytes = { version = "1.5.0", optional = true }
-url = { version = "2.5.0", optional = true }
+futures-util = { version = "0.3.29"}
+bytecount = { version = "0.6.7"}
+itertools = { version = "0.12.0"}
+bytes = { version = "1.5.0"}
 # cmk cloud-file = { version = "0.1.0-beta.2", optional = true }
-cloud-file = {path="../cloud-file", optional = true}
+cloud-file = {path="../cloud-file"}
+pyo3 = { version = "0.20.0", features = ["extension-module"], optional = true }
+tokio = { version = "1.35.0", features = ["full"], optional = true }
 
 [dev-dependencies]
 ndarray-rand = "0.14.0"
 anyhow = "1.0.75"
 rusoto_credential = "0.48.0"
-pyo3-asyncio = { version = "0.20.0", features = [
-    "tokio-runtime",
-    "attributes",
-    "testing",
-] }
 temp_testdir = "0.2.3"
-object_store = { version = "0.9.0", features = ["aws","http"]}
 thousands = "0.2.0"
 
 

README-rust.md

@@ -106,8 +106,7 @@ at index position 2. (See ["Cloud URLs and `CloudFile` Examples"](supplemental_d
 for details specifying a file in the cloud.)
 
 ```rust
-# #[cfg(feature = "cloud")]  // '#' needed for doctest
-# { use {bed_reader::BedErrorPlus, tokio::runtime::Runtime};
+# { use {bed_reader::BedErrorPlus, tokio::runtime::Runtime}; // '#' needed for doctest
 use ndarray as nd;
 use bed_reader::{assert_eq_nan, BedCloud, ReadOptions};
 # Runtime::new().unwrap().block_on(async {

examples/cloud.rs

@@ -0,0 +1,25 @@
+use bed_reader::{BedCloud, BedErrorPlus, ReadOptions};
+use ndarray::s;
+use std::collections::HashSet;
+
+#[tokio::main]
+async fn main() -> Result<(), Box<BedErrorPlus>> {
+    let url = "https://raw.githubusercontent.com/fastlmm/bed-sample-files/main/some_missing.bed";
+    let cloud_options = [("timeout", "10s")];
+
+    let mut bed_cloud = BedCloud::new_with_options(url, cloud_options).await?;
+    println!("{:?}", bed_cloud.iid().await?.slice(s![..5])); // Outputs ndarray: ["iid_0", "iid_1", "iid_2", "iid_3", "iid_4"]
+    println!("{:?}", bed_cloud.sid().await?.slice(s![..5])); // Outputs ndarray: ["sid_0", "sid_1", "sid_2", "sid_3", "sid_4"]
+    println!(
+        "{:?}",
+        bed_cloud.chromosome().await?.iter().collect::<HashSet<_>>()
+    );
+    // Outputs: {"12", "10", "4", "8", "19", "21", "9", "15", "6", "16", "13", "7", "17", "18", "1", "22", "11", "2", "20", "3", "5", "14"}
+    let _ = ReadOptions::builder()
+        .sid_index(bed_cloud.chromosome().await?.map(|elem| elem == "5"))
+        .f64()
+        .read_cloud(&mut bed_cloud)
+        .await?;
+
+    Ok(())
+}

examples/no_cloud.rs

@@ -0,0 +1,19 @@
+use bed_reader::{sample_bed_file, Bed, BedErrorPlus, ReadOptions};
+use ndarray::s;
+use std::collections::HashSet;
+
+fn main() -> Result<(), Box<BedErrorPlus>> {
+    let file_name = sample_bed_file("some_missing.bed")?;
+
+    let mut bed = Bed::new(file_name)?;
+    println!("{:?}", bed.iid()?.slice(s![..5])); // Outputs ndarray: ["iid_0", "iid_1", "iid_2", "iid_3", "iid_4"]
+    println!("{:?}", bed.sid()?.slice(s![..5])); // Outputs ndarray: ["sid_0", "sid_1", "sid_2", "sid_3", "sid_4"]
+    println!("{:?}", bed.chromosome()?.iter().collect::<HashSet<_>>());
+    // Outputs: {"12", "10", "4", "8", "19", "21", "9", "15", "6", "16", "13", "7", "17", "18", "1", "22", "11", "2", "20", "3", "5", "14"}
+    let _ = ReadOptions::builder()
+        .sid_index(bed.chromosome()?.map(|elem| elem == "5"))
+        .f64()
+        .read(&mut bed)?;
+
+    Ok(())
+}