Merge pull request #122 from VirtualFlyBrain/fix/preview-id-pattern

Preview every id shape, not just the underscored ones

Author: Robbie1977

src/test/test_link_preview.py

@@ -44,13 +44,27 @@ def _class_with_example():
 
 # --- id validation -----------------------------------------------------------
 
-@pytest.mark.parametrize("value", ["FBbt_00003748", "VFB_jrchjrch", "VFBexp_FBtp0000001", "GO_0001872"])
-def test_is_term_id_accepts_vfb_shapes(value):
+@pytest.mark.parametrize("value", [
+    # underscored ontology ids
+    "FBbt_00003748", "VFB_jrchjrch", "VFBexp_FBtp0000001", "GO_0001872",
+    "GENO_0000346", "FBdv_00007133", "FBbi_00000537",
+    # FlyBase ids -- no underscore at all
+    "FBgn0038978", "FBtp0106402", "FBti0004391", "FBrf0247641", "FBal0331598",
+    # dataset / publication names
+    "Court2017", "Chiang2010", "Robie2017",
+])
+def test_is_term_id_accepts_every_shape_get_term_info_resolves(value):
     assert link_preview.is_term_id(value)
 
 
-@pytest.mark.parametrize("value", ["", None, "medulla", "<script>", "../x", "VFB jrch", "_leading"])
-def test_is_term_id_rejects_free_text(value):
+@pytest.mark.parametrize("value", [
+    "", None, "<script>", "../x", "VFB jrch", "_leading", "x",
+    # FlyBase links VFB thumbnails by label rather than id; that must not be
+    # mistaken for a term.
+    "P{VT057232-GAL4} expression pattern in adult VNS on Virtual Fly Brain",
+    "VFB_00101384/thumbnail.png",
+])
+def test_is_term_id_rejects_junk(value):
     assert not link_preview.is_term_id(value)
 
 

src/vfbquery/ha_api.py

@@ -4197,7 +4197,13 @@ async def _term_info_for_preview(request, short_form):
     if response.status != 200:
         return None
     info = json.loads(response.body)
-    return info if info and info.get("Id") else None
+    # get_term_info answers 200 with an empty shell for an id it does not know
+    # (every field null), so presence is not enough: without a Name there is
+    # nothing to put on a card, and the caller should fall back to its own
+    # redirect rather than be handed a blank preview.
+    if not info or not info.get("Id") or not info.get("Name"):
+        return None
+    return info
 
 
 async def handle_get_preview(request):

src/vfbquery/link_preview.py

@@ -21,7 +21,17 @@
 MAX_DESCRIPTION = 300
 
 _MARKDOWN_LINK = re.compile(r"\[([^\]]*)\]\([^)\s]*\)")
-_ID_PATTERN = re.compile(r"^[A-Za-z][A-Za-z0-9]*_[A-Za-z0-9_]+$")
+# Deliberately broad: VFB ids are not one shape. Underscored ontology ids
+# (FBbt_00003748, VFB_jrchjrch, GO_0016811, VFBexp_FBtp0088219) sit alongside
+# FlyBase ids with no underscore at all (FBgn0038978, FBtp0106402, FBrf0247641)
+# and dataset/publication names (Court2017, Chiang2010) -- all of which
+# get_term_info resolves. An earlier pattern required an underscore and so
+# silently refused a preview for every FlyBase id and every dataset.
+#
+# Over-matching is cheap: an id with no term behind it comes back with a null
+# Id and is refused as a 404, which is what lets a caller fall back to its
+# ordinary redirect. Under-matching is the expensive mistake.
+_ID_PATTERN = re.compile(r"^[A-Za-z][A-Za-z0-9_]+$")
 
 
 def is_term_id(value):