#228 - Support reading custom properties from SDF files during indexing in Bingo Elastic

.claude/claude-docs/bingo-elastic-python.md

@@ -7,7 +7,7 @@ The standalone Python library at `bingo/bingo-elastic/python/` that indexes Indi
 - `bingo_elastic/elastic.py` — `ElasticRepository` and `AsyncElasticRepository` (parallel sync/async classes, both take a `tau_search: bool` flag), `IndexName` enum (`BINGO_MOLECULE`, `BINGO_REACTION`, `BINGO_CUSTOM`), `build_index_body(tau_search)` builder for the index mapping, and `compile_query` (dispatches a query subject + kwargs to the right query class; reroutes substructure to the tautomer path when `options` contains `TAU`).
 - `bingo_elastic/queries.py` — `CompilableQuery` hierarchy: `SubstructureQuery`, `TautomerSubstructureQuery` (subclass swapping in the `sub-tau` fingerprint and `tau_fingerprint` field), `ExactMatch`, similarity matches (`TanimotoSimilarityMatch`, `EuclidSimilarityMatch`, `TverskySimilarityMatch`), plus `KeywordQuery`, `RangeQuery`, `WildcardQuery` for non-chemical fields. `query_factory` maps kwarg keys (`"substructure"`, `"tautomer"`, `"exact"`, …) to a class.
 - `bingo_elastic/model/record.py` — `IndigoRecord` (abstract), `IndigoRecordMolecule`, `IndigoRecordReaction`, and the `WithIndigoObject` descriptor that extracts fingerprints + `cmf` + `hash` from an `IndigoObject` at construction time. The descriptor also computes the `sub-tau` fingerprint when the record was built with `tau_search=True`.
-- `bingo_elastic/model/helpers.py` — file iterators (`iterate_file`, `load_reaction`).
+- `bingo_elastic/model/helpers.py` — file iterators (`iterate_file` generic dispatcher plus format-specific wrappers `iterate_sdf` / `iterate_smiles` / `iterate_cml`) and single-file loaders (`load_molecule`, `load_reaction`).
 - `tests/` — its own pytest suite with `conftest.py` fixtures that connect to `localhost:9200`.
 
 ## Core flow (the non-obvious bit)

bingo/bingo-elastic/python/bingo_elastic/model/record.py

@@ -7,6 +7,27 @@
 
 MOL_TYPES = ["#02: <molecule>", "#03: <query reaction>", "#12: <RDFMolecule>"]
 REAC_TYPES = ["#04: <reaction>", "#05: <query reaction>"]
+RESERVED_FIELDS = frozenset(
+    {
+        "cmf",
+        "name",
+        "hash",
+        "has_error",
+        "rawData",
+        "sim_fingerprint",
+        "sim_fingerprint_len",
+        "sub_fingerprint",
+        "sub_fingerprint_len",
+        "tau_fingerprint",
+        "tau_fingerprint_len",
+        "record_id",
+        "error_handler",
+        "skip_errors",
+        "tau_search",
+        "indigo_object",
+        "elastic_response",
+    }
+)
 
 
 # pylint: disable=unused-argument
@@ -31,7 +52,7 @@ def __set__(self, instance: IndigoRecord, value: Dict):
 
 
 class WithIndigoObject:
-    def __set__(  # pylint: disable=too-many-branches
+    def __set__(  # pylint: disable=too-many-statements, too-many-branches
         self, instance: IndigoRecord, value: IndigoObject
     ) -> None:
         try:
@@ -92,6 +113,15 @@ def __set__(  # pylint: disable=too-many-branches
         except IndigoException as err_:
             check_error(instance, err_)
 
+        try:
+            for prop in value_dup.iterateProperties():
+                prop_name = prop.name()
+                if prop_name in RESERVED_FIELDS:
+                    continue
+                setattr(instance, prop_name, prop.rawData())
+        except IndigoException as err_:
+            check_error(instance, err_)
+
 
 class IndigoRecord:
     """
@@ -143,6 +173,7 @@ def __init__(self, **kwargs) -> None:
         :param skip_errors: if True, all errors will be skipped,
                             no error_handler is required
         :type skip_errors: bool
+        SDF tags are auto populated as attributes
         """
 
         # First check if skip_errors flag passed

bingo/bingo-elastic/python/tests/test_elastic.py

@@ -12,7 +12,7 @@
     ElasticRepository,
     IndexName,
 )
-from bingo_elastic.model.helpers import iterate_file
+from bingo_elastic.model.helpers import iterate_file, iterate_sdf
 from bingo_elastic.model.record import (
     IndigoRecord,
     IndigoRecordMolecule,
@@ -527,6 +527,39 @@ async def test_a_custom_fields(
             assert iupac_inch == "RDHQFKQIGNGIED-UHFFFAOYSA-N"
 
 
+def test_sdf_custom_properties(
+    elastic_repository_molecule: ElasticRepository,
+    resource_loader,
+):
+    for rec in iterate_sdf(
+        resource_loader("molecules/rand_queries_small.sdf")
+    ):
+        elastic_repository_molecule.index_record(rec)
+    time.sleep(1)
+    result = elastic_repository_molecule.filter(n="1")
+    hits = [item for item in result]
+    assert len(hits) >= 1
+    assert hits[0].n == "1"  # type: ignore
+
+
+@pytest.mark.asyncio
+async def test_a_sdf_custom_properties(
+    a_elastic_repository_molecule: AsyncRepositoryT,
+    resource_loader,
+):
+    async with a_elastic_repository_molecule() as rep:
+        for rec in iterate_sdf(
+            resource_loader("molecules/rand_queries_small.sdf")
+        ):
+            await rep.index_record(rec)
+
+    async with a_elastic_repository_molecule() as rep:
+        result = rep.filter(n="1")
+        hits = [item async for item in result]
+        assert len(hits) >= 1
+        assert hits[0].n == "1"  # type: ignore
+
+
 def test_search_empty_fingerprint(
     elastic_repository_molecule: ElasticRepository,
     indigo_fixture: Indigo,