From efb88f94e31198c7359d37097b2e90e6c5772188 Mon Sep 17 00:00:00 2001
From: osobh <om.sobh@gmail.com>
Date: Sat, 26 Sep 2026 18:36:35 -0500
Subject: [PATCH] h5rs: check URL opens the remote file once

open_arg_whole opened and parsed the remote file through open_arg, then
opened it again to download it, so every `h5rs check URL` probed the
server twice. It now opens the storage once and downloads through the
same block cache (whose first block the probe already filled).

Test: check --data of a file within one block costs exactly one request
(two before).

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
---
 crates/clawhdf5-tools/src/h5.rs       | 11 +++++++----
 crates/clawhdf5-tools/tests/remote.rs | 11 +++++++++++
 2 files changed, 18 insertions(+), 4 deletions(-)

diff --git a/crates/clawhdf5-tools/src/h5.rs b/crates/clawhdf5-tools/src/h5.rs
index c130f1f..7cba7c3 100644
--- a/crates/clawhdf5-tools/src/h5.rs
+++ b/crates/clawhdf5-tools/src/h5.rs
@@ -253,13 +253,14 @@ impl H5 {
     /// than `max_download` bytes is refused before anything is read: its
     /// length is only what the server claims.
     pub fn open_arg_whole(arg: &str, max_download: u64) -> Result<H5> {
-        let h5 = H5::open_arg(arg)?;
-        if h5.file.contiguous_bytes().is_some() {
-            return Ok(h5);
+        if !is_url(arg) {
+            return H5::open_arg(arg);
         }
         let name = shown(arg);
         #[cfg(feature = "remote")]
         {
+            // One open (one probe of the server); the download then reads
+            // through the same cache, the first block already in it.
             let storage =
                 clawhdf5_remote::storage_for_url(arg, &clawhdf5_remote::Options::default())
                     .map_err(|e| Error::new(format!("{name}: {e}")))?;
@@ -274,7 +275,9 @@ impl H5 {
         #[cfg(not(feature = "remote"))]
         {
             let _ = max_download;
-            unreachable!("open_arg refuses URLs without the remote feature")
+            Err(Error::new(format!(
+                "{name}: URLs need h5rs built with the `remote` feature"
+            )))
         }
     }
 
diff --git a/crates/clawhdf5-tools/tests/remote.rs b/crates/clawhdf5-tools/tests/remote.rs
index 0ae0b40..de39814 100644
--- a/crates/clawhdf5-tools/tests/remote.rs
+++ b/crates/clawhdf5-tools/tests/remote.rs
@@ -158,3 +158,14 @@ fn credentials_in_urls_are_not_printed() {
         "{out}"
     );
 }
+
+/// `check URL` opens the file once: for a file within the first block,
+/// one request in all (it probed the server twice before).
+#[test]
+fn check_url_probes_the_server_once() {
+    let tall = Path::new(env!("CARGO_MANIFEST_DIR")).join("../clawhdf5/tests/fixtures/tall.h5");
+    let server = server::Server::start(vec![("/t.h5".into(), std::fs::read(&tall).unwrap())]);
+    let (out, rc) = h5rs(&["check", "--data", &server.url("/t.h5")]);
+    assert_eq!(rc, 0, "{out}");
+    assert_eq!(server.requests(), 1, "{:?}", server.log());
+}