Substitute htsnexus_test_NA12878 test data with hg38-based alternative

data/README.md

@@ -15,10 +15,10 @@ crypt4gh keygen --sk c4gh/keys/bob.sec --pk c4gh/keys/bob.pub
 Files were encrypted by running:
 
 ```sh
-crypt4gh encrypt --sk c4gh/keys/alice.sec --recipient_pk c4gh/keys/bob.pub < bam/htsnexus_test_NA12878.bam > c4gh/htsnexus_test_NA12878.bam.c4gh
+crypt4gh encrypt --sk c4gh/keys/alice.sec --recipient_pk c4gh/keys/bob.pub < bam/seraseq_cebpa_larger.bam > c4gh/seraseq_cebpa_larger.bam.c4gh
 crypt4gh encrypt --sk c4gh/keys/alice.sec --recipient_pk c4gh/keys/bob.pub < bcf/sample1-bcbio-cancer.bcf > c4gh/sample1-bcbio-cancer.bcf.c4gh
 crypt4gh encrypt --sk c4gh/keys/alice.sec --recipient_pk c4gh/keys/bob.pub < bcf/spec-v4.3.bcf > c4gh/spec-v4.3.bcf.c4gh
-crypt4gh encrypt --sk c4gh/keys/alice.sec --recipient_pk c4gh/keys/bob.pub < cram/htsnexus_test_NA12878.cram > c4gh/htsnexus_test_NA12878.cram.c4gh
+crypt4gh encrypt --sk c4gh/keys/alice.sec --recipient_pk c4gh/keys/bob.pub < cram/seraseq_cebpa_larger.cram > c4gh/seraseq_cebpa_larger.cram.c4gh
 crypt4gh encrypt --sk c4gh/keys/alice.sec --recipient_pk c4gh/keys/bob.pub < vcf/sample1-bcbio-cancer.vcf.gz > c4gh/sample1-bcbio-cancer.vcf.gz.c4gh
 crypt4gh encrypt --sk c4gh/keys/alice.sec --recipient_pk c4gh/keys/bob.pub < vcf/spec-v4.3.vcf.gz > c4gh/spec-v4.3.vcf.gz.c4gh
 ```

docker/examples/file/README.md

@@ -13,7 +13,7 @@ This launches a `File` htsget-actix server serving data from the [`data`][data]
 The htsget-rs server can then be queried:
 
 ```sh
-curl http://127.0.0.1:8080/reads/data/bam/htsnexus_test_NA12878
+curl http://127.0.0.1:8080/reads/data/bam/seraseq_cebpa_larger
 ```
 
 Which outputs:
@@ -23,7 +23,7 @@ Which outputs:
     "format": "BAM",
     "urls": [
       {
-        "url": "http://0.0.0.0:8081/data/bam/htsnexus_test_NA12878.bam",
+        "url": "http://0.0.0.0:8081/data/bam/seraseq_cebpa_larger.bam",
         "headers": {
           "Range": "bytes=0-2596770"
         }

docker/examples/minio/README.md

@@ -32,7 +32,7 @@ docker compose up
 Then:
 
 ```sh
-curl http://127.0.0.1:8080/reads/bam/htsnexus_test_NA12878
+curl http://127.0.0.1:8080/reads/bam/seraseq_cebpa_larger
 ```
 
 Outputs:
@@ -43,7 +43,7 @@ Outputs:
     "format": "BAM",
     "urls": [
       {
-        "url": "http://data.minio:9000/bam/htsnexus_test_NA12878.bam?x-id=GetObject&X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Credential=user%2F20240320%2Fus-east-1%2Fs3%2Faws4_request&X-Amz-Date=20240320T014007Z&X-Amz-Expires=1000&X-Amz-SignedHeaders=host%3Brange&X-Amz-Signature=33a75bd6363ccbfd5ce8edf7e102a5edff8ca7cee17e3c654db01a880e98072d",
+        "url": "http://data.minio:9000/bam/seraseq_cebpa_larger.bam?x-id=GetObject&X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Credential=user%2F20240320%2Fus-east-1%2Fs3%2Faws4_request&X-Amz-Date=20240320T014007Z&X-Amz-Expires=1000&X-Amz-SignedHeaders=host%3Brange&X-Amz-Signature=33a75bd6363ccbfd5ce8edf7e102a5edff8ca7cee17e3c654db01a880e98072d",
         "headers": {
           "Range": "bytes=0-2596770"
         }
@@ -59,7 +59,7 @@ Outputs:
 The url tickets can then be fetched within the compose network context:
 
 ```sh
-docker exec -it minio curl -H "Range: bytes=0-2596770" "http://data.minio:9000/bam/htsnexus_test_NA12878.bam?x-id=GetObject&X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Credential=user%2F20240320%2Fus-east-1%2Fs3%2Faws4_request&X-Amz-Date=20240320T014007Z&X-Amz-Expires=1000&X-Amz-SignedHeaders=host%3Brange&X-Amz-Signature=33a75bd6363ccbfd5ce8edf7e102a5edff8ca7cee17e3c654db01a880e98072d"
+docker exec -it minio curl -H "Range: bytes=0-2596770" "http://data.minio:9000/bam/seraseq_cebpa_larger.bam?x-id=GetObject&X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Credential=user%2F20240320%2Fus-east-1%2Fs3%2Faws4_request&X-Amz-Date=20240320T014007Z&X-Amz-Expires=1000&X-Amz-SignedHeaders=host%3Brange&X-Amz-Signature=33a75bd6363ccbfd5ce8edf7e102a5edff8ca7cee17e3c654db01a880e98072d"
 ```
 
 [path-style-deprecated]: https://aws.amazon.com/blogs/aws/amazon-s3-path-deprecation-plan-the-rest-of-the-story/

htsget-actix/benches/request_benchmarks.rs

@@ -234,8 +234,8 @@ fn criterion_benchmark(c: &mut Criterion) {
   bench_pair(
     &mut group,
     "[LIGHT] simple request",
-    format_url(&htsget_rs_url, "reads/data/bam/htsnexus_test_NA12878"),
-    format_url(&htsget_refserver_url, "reads/htsnexus_test_NA12878"),
+    format_url(&htsget_rs_url, "reads/data/bam/seraseq_cebpa_larger"),
+    format_url(&htsget_refserver_url, "reads/seraseq_cebpa_larger"),
     &json_content,
   );
 
@@ -254,8 +254,8 @@ fn criterion_benchmark(c: &mut Criterion) {
   bench_pair(
     &mut group,
     "[LIGHT] with region",
-    format_url(&htsget_rs_url, "reads/data/bam/htsnexus_test_NA12878"),
-    format_url(&htsget_refserver_url, "reads/htsnexus_test_NA12878"),
+    format_url(&htsget_rs_url, "reads/data/bam/seraseq_cebpa_larger"),
+    format_url(&htsget_refserver_url, "reads/seraseq_cebpa_larger"),
     &json_content,
   );
 
@@ -281,8 +281,8 @@ fn criterion_benchmark(c: &mut Criterion) {
   bench_pair(
     &mut group,
     "[LIGHT] with two regions",
-    format_url(&htsget_rs_url, "reads/data/bam/htsnexus_test_NA12878"),
-    format_url(&htsget_refserver_url, "reads/htsnexus_test_NA12878"),
+    format_url(&htsget_rs_url, "reads/data/bam/seraseq_cebpa_larger"),
+    format_url(&htsget_refserver_url, "reads/seraseq_cebpa_larger"),
     &json_content,
   );
 

htsget-axum/README.md

@@ -122,7 +122,7 @@ cargo run -p htsget-axum --features experimental -- --config htsget-config/examp
 Crypt4GH encrypted byte ranges can be queried:
 
 ```sh
-curl 'http://localhost:8080/reads/data/c4gh/htsnexus_test_NA12878?referenceName=11&start=5000000&end=5050000'
+curl 'http://localhost:8080/reads/data/c4gh/seraseq_cebpa_larger?referenceName=11&start=5000000&end=5050000'
 ```
 
 The output consists of the Crypt4GH header, which includes the original header, the edit lists, and the re-encrypted header that
@@ -137,7 +137,7 @@ the recipient can use to decrypt bytes:
         "url": "data:;base64,Y3J5cHQ0Z2gBAAAAAwAAAA=="
       },
       {
-        "url": "http://127.0.0.1:8081/data/c4gh/htsnexus_test_NA12878.bam.c4gh",
+        "url": "http://127.0.0.1:8081/data/c4gh/seraseq_cebpa_larger.bam.c4gh",
         "headers": {
           "Range": "bytes=16-123"
         }
@@ -146,13 +146,13 @@ the recipient can use to decrypt bytes:
         "url": "data:;base64,bAAAAAAAAABPIoRdk+d+ifp2PWRFeXoe6Z9kPOj+HrREhzxZ3QiDa2SYh+0Gy8aKpFic4MtTa+ywMpkHziJgojVbcmbvBAr3G7o01lDubsBW98aQ/U1AcalIUCp0fGNkrtdTBN4NaVNIdtQmbAAAAAAAAABPIoRdk+d+ifp2PWRFeXoe6Z9kPOj+HrREhzxZ3QiDa+xJ+yh+52zHvw8qQXMyCtqT6jTFvaYhRPw/6ZzvOdt98YPQgCcTIut58VeTGmR3ien0TdcQFxmfE10MH4qapF2blgjX"
       },
       {
-        "url": "http://127.0.0.1:8081/data/c4gh/htsnexus_test_NA12878.bam.c4gh",
+        "url": "http://127.0.0.1:8081/data/c4gh/seraseq_cebpa_larger.bam.c4gh",
         "headers": {
           "Range": "bytes=124-1114711"
         }
       },
       {
-        "url": "http://127.0.0.1:8081/data/c4gh/htsnexus_test_NA12878.bam.c4gh",
+        "url": "http://127.0.0.1:8081/data/c4gh/seraseq_cebpa_larger.bam.c4gh",
         "headers": {
           "Range": "bytes=2557120-2598042"
         }
@@ -165,7 +165,7 @@ the recipient can use to decrypt bytes:
 For example, using a [htsget client][htsget-client], the data can be concatenated, and then decrypted using the [Crypt4GH CLI][crypt4gh-cli]:
 
 ```sh
-htsget 'http://localhost:8080/reads/data/c4gh/htsnexus_test_NA12878?referenceName=11&start=5000000&end=5050000' > out.c4gh
+htsget 'http://localhost:8080/reads/data/c4gh/seraseq_cebpa_larger?referenceName=11&start=5000000&end=5050000' > out.c4gh
 crypt4gh decrypt --sk data/c4gh/keys/alice.sec < out.c4gh > out.bam
 samtools view out.bam
 ```

htsget-config/README.md

@@ -30,7 +30,7 @@ cargo run --all-features -p htsget-axum -- --config <your_config_file.toml>
 This will serve files under the [`data`][data] directory:
 
 ```sh
-curl 'http://localhost:8080/reads/bam/htsnexus_test_NA12878'
+curl 'http://localhost:8080/reads/bam/seraseq_cebpa_larger'
 ```
 
 Locations allow htsget-rs access to bioinformatics files and indexes. Instead of local files, htsget-rs can access
@@ -55,8 +55,8 @@ locations = [ "file://data/bam", "file://data/cram" ]
 This allows htsget-rs to serve data only when the request also contains the prefix:
 
 ```sh
-curl 'http://localhost:8080/reads/bam/htsnexus_test_NA12878'
-curl 'http://localhost:8080/reads/cram/htsnexus_test_NA12878?format=CRAM'
+curl 'http://localhost:8080/reads/bam/seraseq_cebpa_larger'
+curl 'http://localhost:8080/reads/cram/seraseq_cebpa_larger?format=CRAM'
 ```
 
 Locations can be mixed, and don't all need to have the same directory or resource:

htsget-http/src/lib.rs

@@ -134,10 +134,10 @@ mod tests {
     let request = HashMap::new();
 
     let mut expected_response_headers = Headers::default();
-    expected_response_headers.insert("Range".to_string(), "bytes=0-2596798".to_string());
+    expected_response_headers.insert("Range".to_string(), "bytes=0-986643".to_string());
 
     let request = Request::new(
-      "bam/htsnexus_test_NA12878".to_string(),
+      "bam/seraseq_cebpa_larger".to_string(),
       request,
       Default::default(),
     );
@@ -154,7 +154,7 @@ mod tests {
     request.insert("format".to_string(), "VCF".to_string());
 
     let request = Request::new(
-      "bam/htsnexus_test_NA12878".to_string(),
+      "bam/seraseq_cebpa_larger".to_string(),
       request,
       Default::default(),
     );
@@ -189,7 +189,7 @@ mod tests {
 
   #[tokio::test]
   async fn post_request() {
-    let request = Request::new_with_id("bam/htsnexus_test_NA12878".to_string());
+    let request = Request::new_with_id("bam/seraseq_cebpa_larger".to_string());
     let body = PostRequest {
       format: None,
       class: None,
@@ -200,7 +200,7 @@ mod tests {
     };
 
     let mut expected_response_headers = Headers::default();
-    expected_response_headers.insert("Range".to_string(), "bytes=0-2596798".to_string());
+    expected_response_headers.insert("Range".to_string(), "bytes=0-986643".to_string());
 
     assert_eq!(
       post(get_searcher(), body, request, Endpoint::Reads).await,
@@ -210,7 +210,7 @@ mod tests {
 
   #[tokio::test]
   async fn post_variants_request_with_reads_format() {
-    let request = Request::new_with_id("bam/htsnexus_test_NA12878".to_string());
+    let request = Request::new_with_id("bam/seraseq_cebpa_larger".to_string());
     let body = PostRequest {
       format: Some("BAM".to_string()),
       class: None,
@@ -265,7 +265,7 @@ mod tests {
     JsonResponse::from(Response::new(
       Bam,
       vec![
-        Url::new("http://127.0.0.1:8081/bam/htsnexus_test_NA12878.bam".to_string())
+        Url::new("http://127.0.0.1:8081/bam/seraseq_cebpa_larger.bam".to_string())
           .with_headers(headers),
       ],
     ))

htsget-search/README.md

@@ -78,19 +78,19 @@ produce minimal byte ranges. For example, consider this [file][example-file]:
 * Using just this data, the following query with: 
   * `referenceName=11`, `start=5015000`, and `end=5050000`
 * Would produce these byte ranges:
-  * `bytes=0-4667`
+  * `bytes=0-38969`
   * `bytes=256721-1065951`
 * However, an equally valid response, with smaller byte ranges is:
-  * `bytes=0-4667`
+  * `bytes=0-38969`
   * `bytes=256721-647345`
   * `bytes=824361-842100`
   * `bytes=977196-996014`
 
 To produce the smallest byte ranges, htsget-rs needs can search through GZI files and regular index files. It does not
 read data from the underlying target file.
 
-[example-file]: ../data/bam/htsnexus_test_NA12878.bam
-[example-index]: ../data/bam/htsnexus_test_NA12878.bam.bai
+[example-file]: ../data/bam/seraseq_cebpa_larger.bam
+[example-index]: ../data/bam/seraseq_cebpa_larger.bam.bai
 
 ## Benchmarks
 

htsget-search/benches/search_benchmarks.rs

@@ -45,39 +45,39 @@ fn criterion_benchmark(c: &mut Criterion) {
   bench_query(
     &mut group,
     "[LIGHT] Bam query all",
-    Query::new_with_default_request("bam/htsnexus_test_NA12878", Bam),
+    Query::new_with_default_request("bam/seraseq_cebpa_larger", Bam),
   );
   bench_query(
     &mut group,
     "[LIGHT] Bam query specific",
-    Query::new_with_default_request("bam/htsnexus_test_NA12878", Bam)
-      .with_reference_name("11")
+    Query::new_with_default_request("bam/seraseq_cebpa_larger", Bam)
+      .with_reference_name("chr19")
       .with_start(4999977)
       .with_end(5008321),
   );
   bench_query(
     &mut group,
     "[LIGHT] Bam query header",
-    Query::new_with_default_request("bam/htsnexus_test_NA12878", Bam).with_class(Header),
+    Query::new_with_default_request("bam/seraseq_cebpa_larger", Bam).with_class(Header),
   );
 
   bench_query(
     &mut group,
     "[LIGHT] Cram query all",
-    Query::new_with_default_request("cram/htsnexus_test_NA12878", Cram),
+    Query::new_with_default_request("cram/seraseq_cebpa_larger", Cram),
   );
   bench_query(
     &mut group,
     "[LIGHT] Cram query specific",
-    Query::new_with_default_request("cram/htsnexus_test_NA12878", Cram)
-      .with_reference_name("11")
+    Query::new_with_default_request("cram/seraseq_cebpa_larger", Cram)
+      .with_reference_name("chr19")
       .with_start(4999977)
       .with_end(5008321),
   );
   bench_query(
     &mut group,
     "[LIGHT] Cram query header",
-    Query::new_with_default_request("cram/htsnexus_test_NA12878", Cram).with_class(Header),
+    Query::new_with_default_request("cram/seraseq_cebpa_larger", Cram).with_class(Header),
   );
 
   bench_query(