views: FAIR signposting level 1 support (HTTP Link headers)

invenio_app_rdm/records_ui/views/decorators.py

@@ -10,19 +10,21 @@
 """Routes for record-related pages provided by Invenio-App-RDM."""
 
 from functools import wraps
+from itertools import islice
 
-from flask import g, make_response, redirect, request, session, url_for
+from flask import current_app, g, make_response, redirect, request, session, url_for
 from flask_login import login_required
 from invenio_communities.communities.resources.serializer import (
     UICommunityJSONSerializer,
 )
 from invenio_communities.proxies import current_communities
 from invenio_pidstore.errors import PIDDoesNotExistError
 from invenio_rdm_records.proxies import current_rdm_records
+from invenio_rdm_records.resources.serializers.utils import get_vocabulary_props
 from invenio_records_resources.services.errors import PermissionDeniedError
 from sqlalchemy.orm.exc import NoResultFound
 
-from invenio_app_rdm.urls import record_url_for
+from invenio_app_rdm.urls import download_url_for, export_url_for, record_url_for
 
 
 def service():
@@ -365,20 +367,169 @@ def view(**kwargs):
     return view
 
 
-def add_signposting(f):
-    """Add signposting link to view's response headers."""
+def _get_header(rel, value, link_type=None):
+    header = f'<{value}> ; rel="{rel}"'
+    if link_type:
+        header += f' ; type="{link_type}"'
+    return header
+
+
+def _get_signposting_cite_as(record):
+    """Release self url points to RDM record.
+
+    It points to DataCite URL if the integration is enabled, otherwise it points to the HTML URL.
+    """
+    doi_url = record["links"].get("doi")
+    html_url = record["links"]["self_html"]
+    return _get_header("cite-as", doi_url or html_url)
+
+
+def _get_signposting_types(record):
+    resource_type = record["metadata"]["resource_type"]
+    props = get_vocabulary_props(
+        "resourcetypes",
+        [
+            "props.schema.org",
+        ],
+        resource_type["id"],
+    )
+    url_schema_org = props.get("schema.org")
+    return [
+        _get_header("type", url_schema_org),
+        _get_header("type", "https://schema.org/AboutPage"),
+    ]
+
+
+def _get_signposting_authors(record):
+    authors = []
+    # Limit authors to the first 10.
+    for creator in islice(record["metadata"]["creators"], 0, 10):
+        for identifier in creator["person_or_org"].get("identifiers", []):
+            if identifier["scheme"] == "orcid":
+                authors.append(
+                    _get_header(
+                        "author", "https://orcid.org/" + identifier["identifier"]
+                    )
+                )
+    return authors
+
+
+def _get_signposting_describedbys(pid_value):
+    describedbys = []
+    for export_format, val in current_app.config.get(
+        "APP_RDM_RECORD_EXPORTERS", {}
+    ).items():
+        url = export_url_for(pid_value=pid_value, export_format=export_format)
+        content_type = val["content-type"]
+        describedbys.append(_get_header("describedby", url, content_type))
+    return describedbys
+
+
+def _get_signposting_licenses(record):
+    licenses = []
+    for right in record["metadata"].get("rights", []):
+        # First try to get `props.url` from the standard licenses,
+        # then try to get the optional `link` from the custom license.
+        url = right.get("props", {}).get("url") or right.get("link")
+        if url:
+            licenses.append(_get_header("license", url))
+    return licenses
+
+
+def _get_signposting_items(files, pid_value):
+    items = []
+    # Checking if the user has access to the files.
+    if files:
+        # Limiting the iteration to 100 files maximum.
+        for file in islice(files.to_dict()["entries"], 0, 100):
+            url = download_url_for(pid_value=pid_value, filename=file["key"])
+            items.append(_get_header("item", url, file["mimetype"]))
+    return items
+
+
+def _get_signposting_collection(pid_value):
+    ui_url = record_url_for(pid_value=pid_value)
+    return _get_header("collection", ui_url, "text/html")
+
+
+def _get_signposting_describes(pid_value):
+    ui_url = record_url_for(pid_value=pid_value)
+    return _get_header("describes", ui_url, "text/html")
+
+
+def _get_signposting_linkset(pid_value):
+    api_url = record_url_for(_app="api", pid_value=pid_value)
+    return _get_header("linkset", api_url, "application/linkset+json")
+
+
+def add_signposting_landing_page(f):
+    """Add signposting links to the landing page view's response headers."""
 
     @wraps(f)
     def view(*args, **kwargs):
         response = make_response(f(*args, **kwargs))
 
         # Relies on other decorators having operated before it
         pid_value = kwargs["pid_value"]
-        signposting_link = record_url_for(_app="api", pid_value=pid_value)
+        record = kwargs["record"]
+        files = kwargs["files"]
+
+        signposting_headers = [
+            _get_signposting_cite_as(record),
+            *_get_signposting_types(record),
+            *_get_signposting_authors(record),
+            *_get_signposting_describedbys(pid_value),
+            *_get_signposting_licenses(record),
+            *_get_signposting_items(files, pid_value),
+            _get_signposting_linkset(pid_value),
+        ]
+
+        response.headers["Link"] = " , ".join(signposting_headers)
+
+        return response
+
+    return view
+
+
+def add_signposting_content_resources(f):
+    """Add signposting links to the content resources view's response headers."""
+
+    @wraps(f)
+    def view(*args, **kwargs):
+        response = make_response(f(*args, **kwargs))
+
+        # Relies on other decorators having operated before it
+        pid_value = kwargs["pid_value"]
+
+        signposting_headers = [
+            _get_signposting_collection(pid_value),
+            _get_signposting_linkset(pid_value),
+        ]
+
+        response.headers["Link"] = " , ".join(signposting_headers)
+
+        return response
+
+    return view
+
+
+def add_signposting_metadata_resources(f):
+    """Add signposting links to the metadata resources view's response headers."""
+
+    @wraps(f)
+    def view(*args, **kwargs):
+        response = make_response(f(*args, **kwargs))
+
+        # Relies on other decorators having operated before it
+        pid_value = kwargs["pid_value"]
+
+        signposting_headers = [
+            _get_signposting_describes(pid_value),
+            _get_signposting_linkset(pid_value),
+        ]
+
+        response.headers["Link"] = " , ".join(signposting_headers)
 
-        response.headers["Link"] = (
-            f'<{signposting_link}> ; rel="linkset" ; type="application/linkset+json"'  # fmt: skip
-        )
         return response
 
     return view

invenio_app_rdm/records_ui/views/records.py

@@ -39,7 +39,9 @@
 
 from ..utils import get_external_resources
 from .decorators import (
-    add_signposting,
+    add_signposting_content_resources,
+    add_signposting_landing_page,
+    add_signposting_metadata_resources,
     pass_file_item,
     pass_file_metadata,
     pass_include_deleted,
@@ -141,7 +143,7 @@ def open(self):
 @pass_record_or_draft(expand=True)
 @pass_record_files
 @pass_record_media_files
-@add_signposting
+@add_signposting_landing_page
 def record_detail(
     pid_value, record, files, media_files, is_preview=False, include_deleted=False
 ):
@@ -247,6 +249,7 @@ def record_detail(
 
 @pass_is_preview
 @pass_record_or_draft(expand=False)
+@add_signposting_metadata_resources
 def record_export(
     pid_value, record, export_format=None, permissions=None, is_preview=False
 ):
@@ -309,7 +312,7 @@ def record_file_preview(
 
 @pass_is_preview
 @pass_file_item(is_media=False)
-@add_signposting
+@add_signposting_content_resources
 def record_file_download(pid_value, file_item=None, is_preview=False, **kwargs):
     """Download a file from a record."""
     download = bool(request.args.get("download"))

invenio_app_rdm/urls.py

@@ -60,3 +60,21 @@ def download_url_for(pid_value="", filename=""):
     )
 
     return "/".join(p.strip("/") for p in [url_prefix, url_path])
+
+
+def export_url_for(pid_value="", export_format=""):
+    """Return url for export route."""
+    url_prefix = current_app.config.get(f"SITE_UI_URL", "")
+
+    # We use [] so that this fails and brings to attention the configuration
+    # problem if APP_RDM_ROUTES.record_export is missing
+    # url_path = current_app.config["APP_RDM_ROUTES"]["record_export"].replace(
+    #     "<pid_value>", pid_value
+    # )
+    url_path = (
+        current_app.config["APP_RDM_ROUTES"]["record_export"]
+        .replace("<pid_value>", pid_value)
+        .replace("<export_format>", export_format)
+    )
+
+    return "/".join(p.strip("/") for p in [url_prefix, url_path])

tests/ui/test_signposting_ui.py

@@ -11,23 +11,58 @@
 """
 
 
-def test_link_in_landing_page_response_headers(running_app, client, record):
-    res = client.head(f"/records/{record.id}")
+def test_link_in_landing_page_response_headers(running_app, client, record_with_file):
+    ui_url = f"https://127.0.0.1:5000/records/{record_with_file.id}"
+    api_url = f"https://127.0.0.1:5000/api/records/{record_with_file.id}"
+    filename = "article.txt"
+
+    res = client.head(f"/records/{record_with_file.id}")
 
-    assert (
-        res.headers["Link"]
-        == f'<https://127.0.0.1:5000/api/records/{record.id}> ; rel="linkset" ; type="application/linkset+json"'  # noqa
-    )
+    assert res.headers["Link"].split(" , ") == [
+        f'<{ui_url}> ; rel="cite-as"',
+        '<https://schema.org/Photograph> ; rel="type"',
+        '<https://schema.org/AboutPage> ; rel="type"',
+        # The test record does not have an author with an identifier.
+        f'<{ui_url}/export/json> ; rel="describedby" ; type="application/json"',
+        f'<{ui_url}/export/json-ld> ; rel="describedby" ; type="application/ld+json"',
+        f'<{ui_url}/export/csl> ; rel="describedby" ; type="application/vnd.citationstyles.csl+json"',
+        f'<{ui_url}/export/datacite-json> ; rel="describedby" ; type="application/vnd.datacite.datacite+json"',
+        f'<{ui_url}/export/datacite-xml> ; rel="describedby" ; type="application/vnd.datacite.datacite+xml"',
+        f'<{ui_url}/export/dublincore> ; rel="describedby" ; type="application/x-dc+xml"',
+        f'<{ui_url}/export/marcxml> ; rel="describedby" ; type="application/marcxml+xml"',
+        f'<{ui_url}/export/bibtex> ; rel="describedby" ; type="application/x-bibtex"',
+        f'<{ui_url}/export/geojson> ; rel="describedby" ; type="application/vnd.geo+json"',
+        f'<{ui_url}/export/dcat-ap> ; rel="describedby" ; type="application/dcat+xml"',
+        f'<{ui_url}/export/codemeta> ; rel="describedby" ; type="application/ld+json"',
+        f'<{ui_url}/export/cff> ; rel="describedby" ; type="application/x-yaml"',
+        # The test record does not have a license.
+        f'<{ui_url}/files/{filename}> ; rel="item" ; type="text/plain"',
+        f'<{api_url}> ; rel="linkset" ; type="application/linkset+json"',
+    ]
 
 
 def test_link_in_content_resource_response_headers(
     running_app, client, record_with_file
 ):
+    ui_url = f"https://127.0.0.1:5000/records/{record_with_file.id}"
+    api_url = f"https://127.0.0.1:5000/api/records/{record_with_file.id}"
     filename = "article.txt"
 
     res = client.head(f"/records/{record_with_file.id}/files/{filename}")
 
-    assert (
-        res.headers["Link"]
-        == f'<https://127.0.0.1:5000/api/records/{record_with_file.id}> ; rel="linkset" ; type="application/linkset+json"'  # noqa
-    )
+    assert res.headers["Link"].split(" , ") == [
+        f'<{ui_url}> ; rel="collection" ; type="text/html"',
+        f'<{api_url}> ; rel="linkset" ; type="application/linkset+json"',
+    ]
+
+
+def test_link_in_metadata_resource_response_headers(running_app, client, record):
+    ui_url = f"https://127.0.0.1:5000/records/{record.id}"
+    api_url = f"https://127.0.0.1:5000/api/records/{record.id}"
+
+    res = client.head(f"/records/{record.id}/export/bibtex")
+
+    assert res.headers["Link"].split(" , ") == [
+        f'<{ui_url}> ; rel="describes" ; type="text/html"',
+        f'<{api_url}> ; rel="linkset" ; type="application/linkset+json"',
+    ]