ENH: Implement property from dict generation

src/caoscrawler/converters.py

@@ -811,43 +811,148 @@ class DictElementConverter(Converter):
         return match_name_and_value(self.definition, element.name, element.value)
 
 
-class HeuristicDictConverter(DictElementConverter):
+class PropertiesFromDictConverter(DictElementConverter):
     """Extend the :py:class:`DictElementConverter` by a heuristic to set
     property values from the dictionary keys.
 
     """
 
-    def _validate_definition(self, definition: dict, name: str):
+    def _validate_definition(self):
 
-        if "record_from_dict" not in definition or definition["record_from_dict"] is None:
+        if "record_from_dict" not in self.definition or self.definition["record_from_dict"] is None:
 
             raise ValueError(
                 "You need to specify the (root) record, the properties of "
-                f"which will be set from the dict in converter {name}."
+                f"which will be set from the dict in converter {self.name}."
             )
 
-    def __init__(self, definition: dict, name: str, converter_registry: dict):
+        if not "variable_name" in self.definition["record_from_dict"] or not self.definition["record_from_dict"]["variable_name"]:
+
+            raise ValueError(
+                f"The root record in converter {self.name} needs to have a "
+                "`variable_name` by which it is accessed in the subtree."
+            )
+
+    def __init__(self, definition: dict, name: str, converter_registry: dict,
+                 referenced_record_callback: Optional[callable] = None):
 
-        _validate_definition(definition)
         super().__init__(definition, name, converter_registry)
+        self._validate_definition()
+        self.referenced_record_callback = referenced_record_callback
+
+    def _recursively_create_records(self, subdict: dict, root_record: db.Record,
+                                    root_rec_name: str,
+                                    values: GeneralStore, records: RecordStore,
+                                    referenced_record_callback: callable,
+                                    keys_modified: list = []
+                                    ):
+        """Create a record form the given `subdict` and recursively create referenced records."""
+
+        blacklisted_keys = self.definition["record_from_dict"][
+            "properties_blacklist"] if "properties_blacklist" in self.definition["record_from_dict"] else []
+        special_references = self.definition["record_from_dict"]["references"] if "references" in self.definition["record_from_dict"] else [
+        ]
+
+        for key, value in subdict.items():
+
+            if key in blacklisted_keys:
+                # We ignore this in the automated property generation
+                continue
+            if isinstance(value, list):
+                if not any([isinstance(val, dict) for val in value]):
+                    # no dict in list, i.e., no references, so this is simple
+                    root_record.add_property(name=key, value=value)
+                else:
+                    if not all([isinstance(val, dict) for val in value]):
+                        # if this is not an error (most probably it is), this
+                        # needs to be handled manually for now.
+                        raise ValueError(
+                            f"{key} in {subdict} contains a mixed list of references and scalars.")
+                    ref_recs = []
+                    for ii, ref_dict in enumerate(value):
+                        ref_rec = db.Record()
+                        ref_var_name = f"{root_rec_name}.{key}.{ii}"
+                        if key in special_references:
+                            for par in special_references[key]["parents"]:
+                                ref_rec.add_parent(par)
+                        else:
+                            ref_rec.add_parent(key)
+                        records[ref_var_name] = ref_rec
+                        values[ref_var_name] = ref_rec
+                        keys_modified, ref_rec = self._recursively_create_records(
+                            subdict=ref_dict,
+                            root_record=ref_rec,
+                            root_rec_name=ref_var_name,
+                            values=values,
+                            records=records,
+                            referenced_record_callback=referenced_record_callback,
+                            keys_modified=keys_modified,
+                        )
+                        ref_recs.append(ref_rec)
+                    root_record.add_property(name=key, value=ref_recs)
+
+            elif isinstance(value, dict):
+                ref_rec = db.Record()
+                ref_var_name = f"{root_rec_name}.{key}"
+                if key in special_references:
+                    for par in special_references[key]["parents"]:
+                        ref_rec.add_parent(par)
+                else:
+                    ref_rec.add_parent(key)
+                records[ref_var_name] = ref_rec
+                values[ref_var_name] = ref_rec
+                keys_modified, ref_rec = self._recursively_create_records(
+                    subdict=value,
+                    root_record=ref_rec,
+                    root_rec_name=ref_var_name,
+                    values=values,
+                    records=records,
+                    referenced_record_callback=referenced_record_callback,
+                    keys_modified=keys_modified
+                )
+                root_record.add_property(key, ref_rec)
+            else:
+                if key.lower() in SPECIAL_PROPERTIES:
+                    setattr(root_record, key.lower(), value)
+                else:
+                    root_record.add_property(name=key, value=value)
+            keys_modified.append((root_rec_name, key))
 
-    def create_records(self, values: GeneralStore, records: RecordStore,
-                       element: StructureElement, referenced_record_callback:
-                       Optional[callable] = None):
+        if referenced_record_callback:
+            root_record = referenced_record_callback(root_record)
 
-        keys_modified = []
+        return keys_modified, root_record
 
-        def _insert_into_stores(rec: db.Record, rec_name: str):
+    def create_records(self, values: GeneralStore, records: RecordStore,
+                       element: StructureElement):
 
-            records[rec_name] = rec
-            values[rec_name] = rec
+        keys_modified = []
 
-        def _create_or_return_record(rec_name: str, parent_names: Optional[Union[str, List[str]]] = None):
+        rfd = self.definition["record_from_dict"]
+        if rfd["variable_name"] not in records:
+            rec = db.Record()
+            if "name" in rfd:
+                rec.name = rfd["name"]
+            if "parents" in rfd:
+                for par in rfd["parents"]:
+                    rec.add_parent(par)
+            else:
+                rec.add_parent(rfd["variable_name"])
+            records[rfd["variable_name"]] = rec
+            values[rfd["variable_name"]] = rec
 
-            if parent_names is None:
-                parent_names = [rec_name]
-            elif not isinstance(parent_names, list):
-                parent_names = [parent_names]
+        else:
+            rec = records[rfd["variable_name"]]
+
+        keys_modified, rec = self._recursively_create_records(
+            subdict=element.value,
+            root_record=rec,
+            root_rec_name=rfd["variable_name"],
+            values=values,
+            records=records,
+            referenced_record_callback=self.referenced_record_callback,
+            keys_modified=keys_modified,
+        )
 
         keys_modified.extend(super().create_records(
             values=values, records=records, element=element))

unittests/test_converters.py

@@ -28,12 +28,15 @@ import importlib
 import json
 import logging
 import os
+import pytest
 import sys
+import yaml
+
 from itertools import product
 from pathlib import Path
 
-import pytest
-import yaml
+import linkahead as db
+
 from caoscrawler.converters import (Converter, ConverterValidationError,
                                     DateElementConverter, DictElementConverter,
                                     DictIntegerElementConverter,
@@ -697,6 +700,7 @@ def test_properties_from_dict_basic(converter_registry):
         "a": 5,
         "b": ["a", "b", "c"],
         "scalar_ref": {
+            "name": "Scalar Ref",
             "a": 23,
             "blacklisted_int": 42
         },
@@ -718,7 +722,7 @@ def test_properties_from_dict_basic(converter_registry):
         "blacklisted_ref": {
             "a": 25
         },
-        "author": {
+        "authors": {
             "full_name": "Some Author"
         }
     })
@@ -726,6 +730,9 @@ def test_properties_from_dict_basic(converter_registry):
     assert "MyRec" in records
     my_rec = records["MyRec"]
     assert isinstance(my_rec, db.Record)
+    assert len(my_rec.parents) == 2
+    assert "DictRT1" in [par.name for par in my_rec.parents]
+    assert "DictRT2" in [par.name for par in my_rec.parents]
 
     # scalar prop
     assert my_rec.get_property("a") is not None
@@ -741,8 +748,9 @@ def test_properties_from_dict_basic(converter_registry):
     assert my_rec.get_property("scalar_ref") is not None
     referenced = my_rec.get_property("scalar_ref").value
     assert isinstance(referenced, db.Record)
+    assert referenced.name == "Scalar Ref"
     assert len(referenced.parents) == 1
-    assert referenced.has_parent("scalar_ref")
+    assert "scalar_ref" in [par.name for par in referenced.parents]
     assert referenced.get_property("a") is not None
     assert referenced.get_property("a").value == 23
     # blacklisted
@@ -755,9 +763,9 @@ def test_properties_from_dict_basic(converter_registry):
     for rec in my_rec.get_property("list_ref").value:
         assert isinstance(rec, db.Record)
         assert len(rec.parents) == 1
-        assert rec.has_parent("list_ref")
+        assert "list_ref" in [par.name for par in rec.parents]
         assert rec.get_property("c") is not None
-        assert type(rec.get_property("c")) is bool
+        assert type(rec.get_property("c").value) is bool
     assert True in [rec.get_property("c").value for rec in my_rec.get_property("list_ref").value]
     assert False in [rec.get_property("c").value for rec in my_rec.get_property("list_ref").value]
 
@@ -766,14 +774,14 @@ def test_properties_from_dict_basic(converter_registry):
     outer_rec = my_rec.get_property("ref_with_ref").value
     assert isinstance(outer_rec, db.Record)
     assert len(outer_rec.parents) == 1
-    assert outer_rec.has_parent("ref_with_ref")
+    assert "ref_with_ref" in [par.name for par in outer_rec.parents]
     assert outer_rec.get_property("a") is not None
     assert outer_rec.get_property("a").value == 789
     assert outer_rec.get_property("ref_in_ref") is not None
     inner_rec = outer_rec.get_property("ref_in_ref").value
     assert isinstance(inner_rec, db.Record)
     assert len(inner_rec.parents) == 1
-    assert inner_rec.has_parent("ref_in_ref")
+    assert "ref_in_ref" in [par.name for par in inner_rec.parents]
     assert inner_rec.get_property("b") is not None
     assert inner_rec.get_property("b").value == "something"
 
@@ -782,11 +790,11 @@ def test_properties_from_dict_basic(converter_registry):
     assert my_rec.get_property("blacklisted_ref") is None
 
     # named reference property
-    assert my_rec.get_property("author") is not None
-    author_rec = my_rec.get_property("author").value
+    assert my_rec.get_property("authors") is not None
+    author_rec = my_rec.get_property("authors").value
     assert isinstance(author_rec, db.Record)
     assert len(author_rec.parents) == 1
-    assert author_rec.has_parent("Person")
+    assert "Person" in [par.name for par in author_rec.parents]
     assert author_rec.get_property("full_name") is not None
     assert author_rec.get_property("full_name").value == "Some Author"
 
@@ -834,13 +842,13 @@ def test_properties_from_dict_callable(converter_registry):
     pdfc = PropertiesFromDictConverter(
         definition={
             "record_from_dict": {
-                "variable_name": "MyRec"
+                "variable_name": "MyRec",
                 "name": "My New Record"
+            }
         },
         name="TestConverter",
         converter_registry=converter_registry,
         referenced_record_callback=convert_some_values
-        }
     )
 
     values = GeneralStore()
@@ -851,7 +859,7 @@ def test_properties_from_dict_callable(converter_registry):
             "url": "referenced"
         },
         "referenced2": {
-            "nourl": "something else"
+            "nourl": "something else",
             "url": "https://indiscale.com"
         }
     })
@@ -860,7 +868,7 @@ def test_properties_from_dict_callable(converter_registry):
     my_rec = records["MyRec"]
     assert isinstance(my_rec, db.Record)
     assert len(my_rec.parents) == 1
-    assert my_rec.has_parent("MyRec")
+    assert "MyRec" in [par.name for par in my_rec.parents]
     assert my_rec.name == "My New Record"
 
     # simple conversion