clawhdf5-remote: a 200 covering the requested range is the whole file

The first request asks for bytes=0-1048575. RFC 9110 lets a server answer
200 when the range covers the whole representation, so a file under
1 MiB on a server that does support ranges could be refused as 'does not
support range requests'. A 200 whose Content-Length (or, without one, its
body, read at most that far) is within the range asked for is now kept as
the whole file and read from memory; a longer one is still refused unless
allow_full_download is set.

Test: a 9968-byte file served with 200 opens in one request with the
transcript of File::open (it was refused before); with a 4096-byte first
request it is still refused.

Co-Authored-By: Claude Opus 5.5 (1M context) <[email protected]>

crates/clawhdf5-remote/src/http.rs

@@ -12,6 +12,9 @@
 //!   open is [`RemoteError::FileChanged`], never a mix of old and new bytes.
 //!   (A server that sends neither validator cannot be checked beyond the
 //!   length; [`HttpOptions::require_validator`] refuses such servers.)
+//! - a `200` answer to the first request whose body is no longer than the
+//!   range asked for is the whole file (a server may answer so when the
+//!   range covers it): it is kept and read from memory.
 //! - a server that ignores `Range` and answers `200` with the whole file is
 //!   refused with [`RemoteError::RangeNotSupported`], unless
 //!   [`HttpOptions::allow_full_download`] is set: then the file is
@@ -508,15 +511,34 @@ impl HttpStorage {
                 Ok((total, validator, bytes, false))
             }
             200 => {
-                if !self.options.allow_full_download {
+                // RFC 9110 lets a server answer 200 when the range covers
-                    return Err(RemoteError::RangeNotSupported(format!(
+                // the whole file: a body no longer than the range asked
+                // for is the whole file, ranges supported or not.
+                let want: Option<u64> =
+                    header(&resp, "content-length").and_then(|v| v.trim().parse().ok());
+                let refused = || {
+                    RemoteError::RangeNotSupported(format!(
                         "{} answered a range request with the whole file (status 200); set \
                          HttpOptions::allow_full_download to download it",
                         self.redactor.shown()
-                    )));
+                    ))
+                };
+                if !self.options.allow_full_download {
+                    return match want {
+                        Some(w) if w <= n => {
+                            let bytes = self.body(resp, Some(w), 0)?;
+                            Ok((bytes.len() as u64, validator, bytes, true))
+                        }
+                        Some(_) => Err(refused()),
+                        // No length: read at most the range asked for.
+                        None => match self.body(resp, None, n) {
+                            Ok(bytes) => Ok((bytes.len() as u64, validator, bytes, true)),
+                            Err(RemoteError::Usage(_)) => Err(refused()),
+                            Err(e) => Err(e),
+                        },
+                    };
                 }
-                let want = header(&resp, "content-length").and_then(|v| v.trim().parse().ok());
+                if want.is_some_and(|w| w > self.options.max_full_download) {
-                if want.is_some_and(|w: u64| w > self.options.max_full_download) {
                     return Err(RemoteError::Usage(format!(
                         "{}: the file is larger than HttpOptions::max_full_download ({} bytes)",
                         self.redactor.shown(),

crates/clawhdf5-remote/tests/http.rs

@@ -777,3 +777,26 @@ fn redirects_are_followed_safely() {
     let e = open_url_with(&front.url("/s.h5"), &opts).unwrap_err();
     assert!(matches!(e, Error::Remote(RemoteError::Redirect(_))), "{e}");
 }
+
+/// A server may answer the first request (bytes 0 to 1 MiB - 1) with 200
+/// when that covers the whole file: a body no longer than the range asked
+/// for is accepted as the whole file, in one request.
+#[test]
+fn a_200_covering_the_requested_range_is_the_whole_file() {
+    let root = std::path::Path::new(env!("CARGO_MANIFEST_DIR"));
+    let tall = root.join("../clawhdf5/tests/fixtures/tall.h5");
+    let bytes = std::fs::read(&tall).unwrap();
+    assert!(bytes.len() < 1 << 20);
+    let server = Server::start(vec![("/t.h5".into(), bytes.clone())]);
+    server.shared.ignore_range.store(true, Ordering::SeqCst);
+    let storage = storage_for_url(&server.url("/t.h5"), &quick()).unwrap();
+    let f = File::open_storage(storage).unwrap();
+    assert_eq!(f.contiguous_bytes(), Some(&bytes[..]));
+    assert_eq!(transcript(&f), transcript(&File::open(&tall).unwrap()));
+    assert_eq!(server.requests(), 1);
+    // Larger than the range asked for: still refused.
+    let mut opts = quick().http;
+    opts.first_request = 4096;
+    let e = HttpStorage::open(&server.url("/t.h5"), opts).unwrap_err();
+    assert!(matches!(e, RemoteError::RangeNotSupported(_)), "{e}");
+}