biocypher 0.8.0__py3-none-any.whl → 0.9.1__py3-none-any.whl

biocypher/output/write/_get_writer.py

@@ -1,15 +1,18 @@
-"""
-BioCypher 'offline' module. Handles the writing of node and edge representations
-suitable for import into a DBMS.
+"""Module to provide one of the available writer classes.
+
+The writer classes are responsible for writing the node and edge representations
+to disk in a format suitable for import into a DBMS.
 """
 
 from typing import TYPE_CHECKING
 
 from biocypher._config import config as _config
 from biocypher._logger import logger
+from biocypher.output.write._batch_writer import _BatchWriter
 from biocypher.output.write.graph._arangodb import _ArangoDBBatchWriter
 from biocypher.output.write.graph._neo4j import _Neo4jBatchWriter
 from biocypher.output.write.graph._networkx import _NetworkXWriter
+from biocypher.output.write.graph._owl import _OWLWriter
 from biocypher.output.write.graph._rdf import _RDFWriter
 from biocypher.output.write.relational._csv import _PandasCSVWriter
 from biocypher.output.write.relational._postgresql import _PostgreSQLBatchWriter
@@ -37,6 +40,8 @@ DBMS_TO_CLASS = {
     "sqlite3": _SQLiteBatchWriter,
     "rdf": _RDFWriter,
     "RDF": _RDFWriter,
+    "owl": _OWLWriter,
+    "OWL": _OWLWriter,
     "csv": _PandasCSVWriter,
     "CSV": _PandasCSVWriter,
     "pandas": _PandasCSVWriter,
@@ -54,12 +59,11 @@ def get_writer(
     deduplicator: "Deduplicator",
     output_directory: str,
     strict_mode: bool,
-):
-    """
-    Function to return the writer class based on the selection in the config
-    file.
+) -> _BatchWriter | None:
+    """Return the writer class based on the selection in the config file.
 
     Args:
+    ----
         dbms: the database management system; for options, see DBMS_TO_CLASS.
         translator: the Translator object.
         deduplicator: the Deduplicator object.
@@ -67,15 +71,26 @@ def get_writer(
         strict_mode: whether to use strict mode.
 
     Returns:
+    -------
         instance: an instance of the selected writer class.
-    """
 
-    dbms_config = _config(dbms)
+    """
+    dbms_config = _config(dbms) or {}
 
     writer = DBMS_TO_CLASS[dbms]
 
+    if "rdf_format" in dbms_config:
+        logger.warning("The 'rdf_format' config option is deprecated, use 'file_format' instead.")
+        if "file_format" not in dbms_config:
+            format = dbms_config["rdf_format"]
+            logger.warning(f"I will set 'file_format: {format}' for you.")
+            dbms_config["file_format"] = format
+            dbms_config.pop("rdf_format")
+        logger.warning("NOTE: this warning will become an error in next versions.")
+
     if not writer:
-        raise ValueError(f"Unknown dbms: {dbms}")
+        msg = f"Unknown dbms: {dbms}"
+        raise ValueError(msg)
 
     if writer is not None:
         return writer(
@@ -95,6 +110,8 @@ def get_writer(
             db_user=dbms_config.get("user"),  # psql
             db_password=dbms_config.get("password"),  # psql
             db_port=dbms_config.get("port"),  # psql
-            rdf_format=dbms_config.get("rdf_format"),  # rdf
-            rdf_namespaces=dbms_config.get("rdf_namespaces"),  # rdf
+            file_format=dbms_config.get("file_format"),  # rdf, owl
+            rdf_namespaces=dbms_config.get("rdf_namespaces"),  # rdf, owl
+            edge_model=dbms_config.get("edge_model"),  # owl
         )
+    return None

biocypher/output/write/graph/_arangodb.py

@@ -1,3 +1,5 @@
+"""Module to provide the ArangoDB writer class."""
+
 import os
 
 from biocypher._logger import logger
@@ -5,38 +7,43 @@ from biocypher.output.write.graph._neo4j import _Neo4jBatchWriter
 
 
 class _ArangoDBBatchWriter(_Neo4jBatchWriter):
-    """
-    Class for writing node and edge representations to disk using the format
-    specified by ArangoDB for the use of "arangoimport". Output files are
-    similar to Neo4j, but with a different header format.
+    """Class for writing node and edge representations to disk.
+
+    Uses the format specified by ArangoDB for the use of "arangoimport".
+    Output files are similar to Neo4j, but with a different header format.
     """
 
     def _get_default_import_call_bin_prefix(self):
-        """
-        Method to provide the default string for the import call bin prefix.
+        """Provide the default string for the import call bin prefix.
 
-        Returns:
+        Returns
+        -------
             str: The default location for the neo4j admin import location
+
         """
         return ""
 
     def _get_import_script_name(self) -> str:
-        """
-        Returns the name of the neo4j admin import script
+        """Return the name of the neo4j admin import script.
 
-        Returns:
+        Returns
+        -------
             str: The name of the import script (ending in .sh)
+
         """
         return "arangodb-import-call.sh"
 
     def _write_node_headers(self):
-        """
-        Writes single CSV file for a graph entity that is represented
-        as a node as per the definition in the `schema_config.yaml`,
-        containing only the header for this type of node.
+        """Write single CSV file for a graph entity.
+
+        The graph entity is represented as a node as per the definition
+        in the `schema_config.yaml`, containing only the header for this type
+        of node.
 
-        Returns:
+        Returns
+        -------
             bool: The return value. True for success, False otherwise.
+
         """
         # load headers from data parse
         if not self.node_property_dict:
@@ -86,9 +93,9 @@ class _ArangoDBBatchWriter(_Neo4jBatchWriter):
             parts = self.parts.get(label, [])
 
             if not parts:
-                raise ValueError(
-                    f"No parts found for node label {label}. " f"Check that the data was parsed first.",
-                )
+                msg = f"No parts found for node label {label}. Check that the data was parsed first."
+                logger.error(msg)
+                raise ValueError(msg)
 
             for part in parts:
                 import_call_header_path = os.path.join(
@@ -105,19 +112,22 @@ class _ArangoDBBatchWriter(_Neo4jBatchWriter):
                         import_call_header_path,
                         import_call_parts_path,
                         collection,
-                    )
+                    ),
                 )
 
         return True
 
     def _write_edge_headers(self):
-        """
-        Writes single CSV file for a graph entity that is represented
-        as an edge as per the definition in the `schema_config.yaml`,
-        containing only the header for this type of edge.
+        """Write single CSV file for a graph entity.
 
-        Returns:
+        The graph entity is represented as an edge as per the definition
+        in the `schema_config.yaml`, containing only the header for this type
+        of edge.
+
+        Returns
+        -------
             bool: The return value. True for success, False otherwise.
+
         """
         # load headers from data parse
         if not self.edge_property_dict:
@@ -182,22 +192,24 @@ class _ArangoDBBatchWriter(_Neo4jBatchWriter):
                     header_import_call_path,
                     parts_import_call_path,
                     collection,
-                )
+                ),
             )
 
         return True
 
     def _construct_import_call(self) -> str:
-        """
-        Function to construct the import call detailing folder and
-        individual node and edge headers and data files, as well as
-        delimiters and database name. Built after all data has been
+        """Construct the import call.
+
+        Details folder and individual node and edge headers and data files,
+        as well as delimiters and database name. Built after all data has been
         processed to ensure that nodes are called before any edges.
 
-        Returns:
-            str: a bash command for neo4j-admin import
+        Returns
+        -------
+            str: a bash command for arangoimport
+
         """
-        import_call = f"{self.import_call_bin_prefix}arangoimp " f"--type csv " f'--separator="{self.escaped_delim}" '
+        import_call = f"{self.import_call_bin_prefix}arangoimp --type csv " f'--separator="{self.escaped_delim}" '
 
         if self.quote == "'":
             import_call += f'--quote="{self.quote}" '

biocypher/output/write/graph/_neo4j.py

@@ -1,3 +1,5 @@
+"""Module to provide the Neo4j writer class."""
+
 import os
 
 from biocypher._logger import logger
@@ -45,10 +47,7 @@ class _Neo4jBatchWriter(_BatchWriter):
         return "bin/"
 
     def _quote_string(self, value: str) -> str:
-        """
-        Quote a string. Quote character is escaped by doubling it.
-        """
-
+        """Quote a string. Quote character is escaped by doubling it."""
         return f"{self.quote}{value.replace(self.quote, self.quote * 2)}{self.quote}"
 
     def _write_array_string(self, string_list):