biocypher 0.5.19__py3-none-any.whl → 0.5.21__py3-none-any.whl

biocypher/_write.py

@@ -125,7 +125,6 @@ class _BatchWriter(ABC):
 
     def __init__(
         self,
-        ontology: "Ontology",
         translator: "Translator",
         deduplicator: "Deduplicator",
         delimiter: str,
@@ -167,10 +166,6 @@ class _BatchWriter(ABC):
             - _get_import_script_name
 
         Args:
-            ontology:
-                Instance of :py:class:`Ontology` to enable translation and
-                ontology queries
-
             translator:
                 Instance of :py:class:`Translator` to enable translation of
                 nodes and manipulation of properties.
@@ -251,8 +246,6 @@ class _BatchWriter(ABC):
         self.wipe = wipe
         self.strict_mode = strict_mode
 
-        self.extended_schema = ontology.extended_schema
-        self.ontology = ontology
         self.translator = translator
         self.deduplicator = deduplicator
         self.node_property_dict = {}
@@ -352,34 +345,34 @@ class _BatchWriter(ABC):
             bool: The return value. True for success, False otherwise.
         """
         passed = False
-        # unwrap generator in one step
         edges = list(edges)  # force evaluation to handle empty generator
         if edges:
-            z = zip(
-                *(
-                    (
-                        e.get_node(),
-                        [
-                            e.get_source_edge(),
-                            e.get_target_edge(),
-                        ],
-                    )
-                    if isinstance(e, BioCypherRelAsNode)
-                    else (None, [e])
-                    for e in edges
-                )
-            )
-            nod, edg = (list(a) for a in z)
-            nod = [n for n in nod if n]
-            edg = [val for sublist in edg for val in sublist]  # flatten
+            nodes_flat = []
+            edges_flat = []
+            for edge in edges:
+                if isinstance(edge, BioCypherRelAsNode):
+                    # check if relationship has already been written, if so skip
+                    if self.deduplicator.rel_as_node_seen(edge):
+                        continue
 
-            if nod and edg:
-                passed = self.write_nodes(nod) and self._write_edge_data(
-                    edg,
+                    nodes_flat.append(edge.get_node())
+                    edges_flat.append(edge.get_source_edge())
+                    edges_flat.append(edge.get_target_edge())
+
+                else:
+                    # check if relationship has already been written, if so skip
+                    if self.deduplicator.edge_seen(edge):
+                        continue
+
+                    edges_flat.append(edge)
+
+            if nodes_flat and edges_flat:
+                passed = self.write_nodes(nodes_flat) and self._write_edge_data(
+                    edges_flat,
                     batch_size,
                 )
             else:
-                passed = self._write_edge_data(edg, batch_size)
+                passed = self._write_edge_data(edges_flat, batch_size)
 
         else:
             # is this a problem? if the generator or list is empty, we
@@ -451,8 +444,12 @@ class _BatchWriter(ABC):
                     bin_l[label] = 1
 
                     # get properties from config if present
-                    cprops = self.extended_schema.get(label).get(
-                        "properties",
+                    cprops = (
+                        self.translator.ontology.mapping.extended_schema.get(
+                            label
+                        ).get(
+                            "properties",
+                        )
                     )
                     if cprops:
                         d = dict(cprops)
@@ -486,7 +483,7 @@ class _BatchWriter(ABC):
 
                     # get label hierarchy
                     # multiple labels:
-                    all_labels = self.ontology.get_ancestors(label)
+                    all_labels = self.translator.ontology.get_ancestors(label)
 
                     if all_labels:
                         # convert to pascal case
@@ -682,10 +679,6 @@ class _BatchWriter(ABC):
             # for each label to check for consistency and their type
             # for now, relevant for `int`
             for edge in edges:
-                # check for duplicates
-                if self.deduplicator.edge_seen(edge):
-                    continue
-
                 if not (edge.get_source_id() and edge.get_target_id()):
                     logger.error(
                         "Edge must have source and target node. "
@@ -706,13 +699,23 @@ class _BatchWriter(ABC):
                     # (may not be if it is an edge that carries the
                     # "label_as_edge" property)
                     cprops = None
-                    if label in self.extended_schema:
-                        cprops = self.extended_schema.get(label).get(
+                    if (
+                        label
+                        in self.translator.ontology.mapping.extended_schema
+                    ):
+                        cprops = self.translator.ontology.mapping.extended_schema.get(
+                            label
+                        ).get(
                             "properties",
                         )
                     else:
                         # try via "label_as_edge"
-                        for k, v in self.extended_schema.items():
+                        for (
+                            k,
+                            v,
+                        ) in (
+                            self.translator.ontology.mapping.extended_schema.items()
+                        ):
                             if isinstance(v, dict):
                                 if v.get("label_as_edge") == label:
                                     cprops = v.get("properties")
@@ -873,9 +876,14 @@ class _BatchWriter(ABC):
 
             if label in ["IS_SOURCE_OF", "IS_TARGET_OF", "IS_PART_OF"]:
                 skip_id = True
-            elif not self.extended_schema.get(label):
+            elif not self.translator.ontology.mapping.extended_schema.get(
+                label
+            ):
                 # find label in schema by label_as_edge
-                for k, v in self.extended_schema.items():
+                for (
+                    k,
+                    v,
+                ) in self.translator.ontology.mapping.extended_schema.items():
                     if v.get("label_as_edge") == label:
                         schema_label = k
                         break
@@ -884,7 +892,9 @@ class _BatchWriter(ABC):
 
             if schema_label:
                 if (
-                    self.extended_schema.get(schema_label).get("use_id")
+                    self.translator.ontology.mapping.extended_schema.get(
+                        schema_label
+                    ).get("use_id")
                     == False
                 ):
                     skip_id = True
@@ -1009,6 +1019,7 @@ class _Neo4jBatchWriter(_BatchWriter):
 
     This class inherits from the abstract class "_BatchWriter" and implements the
     Neo4j-specific methods:
+
         - _write_node_headers
         - _write_edge_headers
         - _construct_import_call
@@ -1181,9 +1192,14 @@ class _Neo4jBatchWriter(_BatchWriter):
 
             if label in ["IS_SOURCE_OF", "IS_TARGET_OF", "IS_PART_OF"]:
                 skip_id = True
-            elif not self.extended_schema.get(label):
+            elif not self.translator.ontology.mapping.extended_schema.get(
+                label
+            ):
                 # find label in schema by label_as_edge
-                for k, v in self.extended_schema.items():
+                for (
+                    k,
+                    v,
+                ) in self.translator.ontology.mapping.extended_schema.items():
                     if v.get("label_as_edge") == label:
                         schema_label = k
                         break
@@ -1194,7 +1210,9 @@ class _Neo4jBatchWriter(_BatchWriter):
 
             if schema_label:
                 if (
-                    self.extended_schema.get(schema_label).get("use_id")
+                    self.translator.ontology.mapping.extended_schema.get(
+                        schema_label
+                    ).get("use_id")
                     == False
                 ):
                     skip_id = True
@@ -1352,9 +1370,9 @@ class _ArangoDBBatchWriter(_Neo4jBatchWriter):
                 f.write(row)
 
             # add collection from schema config
-            collection = self.extended_schema[label].get(
-                "db_collection_name", None
-            )
+            collection = self.translator.ontology.mapping.extended_schema[
+                label
+            ].get("db_collection_name", None)
 
             # add file path to neo4 admin import statement
             # do once for each part file
@@ -1433,16 +1451,19 @@ class _ArangoDBBatchWriter(_Neo4jBatchWriter):
                 f.write(row)
 
             # add collection from schema config
-            if not self.extended_schema.get(label):
-                for _, v in self.extended_schema.items():
+            if not self.translator.ontology.mapping.extended_schema.get(label):
+                for (
+                    _,
+                    v,
+                ) in self.translator.ontology.mapping.extended_schema.items():
                     if v.get("label_as_edge") == label:
                         collection = v.get("db_collection_name", None)
                         break
 
             else:
-                collection = self.extended_schema[label].get(
-                    "db_collection_name", None
-                )
+                collection = self.translator.ontology.mapping.extended_schema[
+                    label
+                ].get("db_collection_name", None)
 
             # add file path to neo4 admin import statement (import call path
             # may be different from actual output path)
@@ -1520,6 +1541,7 @@ class _PostgreSQLBatchWriter(_BatchWriter):
 
     This class inherits from the abstract class "_BatchWriter" and implements the
     PostgreSQL-specific methods:
+
         - _write_node_headers
         - _write_edge_headers
         - _construct_import_call
@@ -1839,7 +1861,6 @@ DBMS_TO_CLASS = {
 def get_writer(
     dbms: str,
     translator: "Translator",
-    ontology: "Ontology",
     deduplicator: "Deduplicator",
     output_directory: str,
     strict_mode: bool,
@@ -1854,8 +1875,6 @@ def get_writer(
 
         translator: the Translator object.
 
-        ontology: the Ontology object.
-
         output_directory: the directory to write the output files to.
 
         strict_mode: whether to use strict mode.
@@ -1879,7 +1898,6 @@ def get_writer(
 
     if writer is not None:
         return writer(
-            ontology=ontology,
             translator=translator,
             deduplicator=deduplicator,
             delimiter=dbms_config.get("delimiter"),

{biocypher-0.5.19.dist-info → biocypher-0.5.21.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: biocypher
-Version: 0.5.19
+Version: 0.5.21
 Summary: A unifying framework for biomedical research knowledge graphs
 Home-page: https://github.com/biocypher/biocypher
 License: MIT
@@ -25,8 +25,10 @@ Requires-Dist: more_itertools
 Requires-Dist: neo4j-utils (==0.0.7)
 Requires-Dist: networkx (>=3.0,<4.0)
 Requires-Dist: pandas (>=2.0.1,<3.0.0)
+Requires-Dist: pooch (>=1.7.0,<2.0.0)
 Requires-Dist: rdflib (>=6.2.0,<7.0.0)
 Requires-Dist: stringcase (>=1.2.0,<2.0.0)
+Requires-Dist: tqdm (>=4.65.0,<5.0.0)
 Requires-Dist: treelib (>=1.6.1,<2.0.0)
 Project-URL: Bug Tracker, https://github.com/biocypher/biocypher/issues
 Project-URL: Repository, https://github.com/biocypher/biocypher
@@ -38,7 +40,9 @@ Description-Content-Type: text/markdown
 ![Python](https://img.shields.io/badge/python-3.10-blue.svg)
 [![PyPI version](https://badge.fury.io/py/biocypher.svg)](https://badge.fury.io/py/biocypher)
 [![Project Status: Active – The project has reached a stable, usable state and is being actively developed.](https://www.repostatus.org/badges/latest/active.svg)](https://www.repostatus.org/#active)
-![Docs build](https://github.com/biocypher/biocypher/actions/workflows/sphinx_autodoc.yml/badge.svg)
+[![CI](https://github.com/biocypher/biocypher/actions/workflows/ci_cd.yaml/badge.svg)](https://github.com/biocypher/biocypher/actions/workflows/ci_cd.yaml)
+![Coverage](https://raw.githubusercontent.com/biocypher/biocypher/coverage/coverage.svg)
+[![Docs build](https://github.com/biocypher/biocypher/actions/workflows/sphinx_autodoc.yaml/badge.svg)](https://github.com/biocypher/biocypher/actions/workflows/sphinx_autodoc.yaml)
 [![Downloads](https://static.pepy.tech/badge/biocypher)](https://pepy.tech/project/biocypher)
 [![pre-commit](https://img.shields.io/badge/pre--commit-enabled-brightgreen?logo=pre-commit)](https://github.com/pre-commit/pre-commit)
 [![PRs Welcome](https://img.shields.io/badge/PRs-welcome-brightgreen.svg?style=flat-square)](http://makeapullrequest.com)

{biocypher-0.5.19.dist-info → biocypher-0.5.21.dist-info}/RECORD

@@ -5,19 +5,20 @@ biocypher/_config/test_config.yaml,sha256=Np8jeS5_EP6HHOvMKb7B_Tkyqd5YaYlYz_DVsX
 biocypher/_config/test_schema_config.yaml,sha256=D1600WgEj3iTXrumVU9LIivJHJO36iaxfkOgyam9zVU,3129
 biocypher/_config/test_schema_config_disconnected.yaml,sha256=Qm8FLxEn2spHcyj_5F859KjcDvKSxNhxDvi4b4LLkvQ,68
 biocypher/_config/test_schema_config_extended.yaml,sha256=wn3A76142hhjnImhMF6RODbCFESTJ2TtPvcFdIFsAT0,3309
-biocypher/_connect.py,sha256=i62424Cbdnm2oI4ECLkcMF2V2A6aShCK2eSSwaGLbVE,12603
-biocypher/_core.py,sha256=Sg7ESentsTsqp9KbzPC_jh1fRAqOGzyy98Xzma7BBkw,17100
+biocypher/_connect.py,sha256=0oSyO6CEIlKL8rHo-HHE7y0FzGfSi4vnEXSDy1TnIUE,12456
+biocypher/_core.py,sha256=cc8iOOAhaByobN6zOwdUm1hZFAJ5CpGpKmQnBIIQrbY,21090
 biocypher/_create.py,sha256=vpUchUdEpWupZi1LgFLxAWMtqoBwnWbP7PwEDUCBS4A,10202
-biocypher/_deduplicate.py,sha256=ah2i6ONx6ml4MbQMXIe6NfbVzf1bjav0l3gLj1xGDE0,3288
+biocypher/_deduplicate.py,sha256=BBvfpXzu6L5YDY5FdtXxnf8YlsbJpbCE8RdUoKsm0n0,4949
+biocypher/_get.py,sha256=MHjHEqvPr4Z7Ud05qBcUJkR--iZ1SgUvUoft8MfwUic,8996
 biocypher/_logger.py,sha256=soYtz1DiduLFw3XrMnphWWUxeuJqvSof4AYhlafxl08,2933
 biocypher/_mapping.py,sha256=XJZjmXTPnXVkyub1ZU0h3EKXQ2YROaGaJOaGyPMqgy4,9338
-biocypher/_metadata.py,sha256=24UdhQ8vslHBfHf0S6oF9A5asyiM9SVOjfVqvRPnFvY,1658
+biocypher/_metadata.py,sha256=CHGBWJ8qYrb7QNQO-Fk0ROkRDXHvtFECSoex9GytJ4A,1658
 biocypher/_misc.py,sha256=wsjGVOqBDVM5hxbE_TEaZ69u1kJc8HXwRAtQHUgE8XQ,4545
-biocypher/_ontology.py,sha256=vCGIHJn_IH5bmOMTA6GJQZB-eNVOlyjYnMzwmwfni0Q,21375
-biocypher/_pandas.py,sha256=2qaCtUCk_nhr8dCqXqUr8zgMhCetPh9EDq-3z-8Qxi0,2021
-biocypher/_translate.py,sha256=e5XhPxbPArd0aK-Zk7F533ECV12jMR_ZzoAlGD3TAzc,16540
-biocypher/_write.py,sha256=kOb_l1LMu_weu5RLxEDLvSrpgdU1PZZe7ObaNhJRkdU,66943
-biocypher-0.5.19.dist-info/LICENSE,sha256=SjUaQkq671iQUZOxEUpC4jvJxXOlfSiHTTueyz9kXJM,1065
-biocypher-0.5.19.dist-info/WHEEL,sha256=vxFmldFsRN_Hx10GDvsdv1wroKq8r5Lzvjp6GZ4OO8c,88
-biocypher-0.5.19.dist-info/METADATA,sha256=_7DNxOzmag2EO1vxTpjE7dcsX7YclymnoIVEkoMXlJ4,9103
-biocypher-0.5.19.dist-info/RECORD,,
+biocypher/_ontology.py,sha256=pHc4hO8iZx-yg9gzqfBR9khoIni-lKAxWgnRFyNP91E,21530
+biocypher/_pandas.py,sha256=GVCFM68J7yBjh40MpkNVgD8qT1RFMrrIjMOtD3iKsf4,3040
+biocypher/_translate.py,sha256=nj4Y60F0U3JBH36N2dh5pFcC8Ot86rskJ2ChJwje9dI,16494
+biocypher/_write.py,sha256=2ynF-VkvTr8WT2qPt2wji3iupP3WON94TlT6NpfDvCs,67738
+biocypher-0.5.21.dist-info/LICENSE,sha256=SjUaQkq671iQUZOxEUpC4jvJxXOlfSiHTTueyz9kXJM,1065
+biocypher-0.5.21.dist-info/WHEEL,sha256=vxFmldFsRN_Hx10GDvsdv1wroKq8r5Lzvjp6GZ4OO8c,88
+biocypher-0.5.21.dist-info/METADATA,sha256=wJ1Hnuq_erwEJRMCKA3e7VeUF7cLibnZdcnSCryynx0,9505
+biocypher-0.5.21.dist-info/RECORD,,