Adding docstrings and removing unused imports

schemasheets/schemamaker.py

@@ -1,26 +1,23 @@
+"""Converts a schema sheet into a LinkML schema"""
 import codecs
 import contextlib
-import os
 import sys
 import csv
 import logging
-import tempfile
 from urllib.request import urlopen
 
 import click
 import yaml
 from dataclasses import dataclass
 from typing import List, Union, Any, Dict, Tuple, Generator, TextIO
 
-from linkml_runtime.dumpers import yaml_dumper
 from linkml_runtime.linkml_model import Annotation, Example
 from linkml_runtime.linkml_model.meta import SchemaDefinition, ClassDefinition, Prefix, \
     SlotDefinition, EnumDefinition, PermissibleValue, SubsetDefinition, TypeDefinition, Element
 from linkml_runtime.utils.schema_as_dict import schema_as_dict
 from linkml_runtime.utils.schemaview import SchemaView, re
 
-from schemasheets.schemasheet_datamodel import ColumnConfig, TableConfig, get_configmodel, get_metamodel, COL_NAME, \
-    DESCRIPTOR, \
+from schemasheets.schemasheet_datamodel import ColumnConfig, TableConfig, get_configmodel, COL_NAME, \
     tmap, T_CLASS, T_PV, T_SLOT, T_SUBSET, T_SCHEMA, T_ENUM, T_PREFIX, T_TYPE, SchemaSheet
 from schemasheets.conf.configschema import Cardinality
 from schemasheets.utils.google_sheets import gsheets_download_url
@@ -34,23 +31,38 @@ class SchemaSheetRowException(Exception):
 @dataclass
 class SchemaMaker:
     """
-    Engine for making LinkML schemas from Schema Sheets
+    Engine for making LinkML schemas from Schema Sheets.
     """
     schema: SchemaDefinition = None
+    """Generated schema."""
+
     element_map: Dict[Tuple[str, str], Element] = None
+
     metamodel: SchemaView = None
+    """Schema describing LinkML elements."""
+
     cardinality_vocabulary: str = None
+
     use_attributes: bool = None
+    """If True, use attributes instead of slots."""
+
     default_name: str = None
+    """Default name for the schema."""
+
     unique_slots: bool = None
+    """If True, slots are unique across classes."""
+
     gsheet_id: str = None
+    """Google sheet ID."""
+
     table_config_path: str = None
+    """Path to table configuration file."""
 
     def create_schema(self, csv_files: Union[str, List[str]], **kwargs) -> SchemaDefinition:
         """
-        Create a LinkML schema from a collection of Schema Sheets
+        Create a LinkML schema from one or more Schema Sheets.
 
-        :param csv_files: schema sheets
+        :param csv_files: schema sheets paths
         :param kwargs:
         :return: generated schema
         """
@@ -61,7 +73,7 @@ def create_schema(self, csv_files: Union[str, List[str]], **kwargs) -> SchemaDef
         if not isinstance(csv_files, list):
             csv_files = [csv_files]
         for f in csv_files:
-            self.merge_sheet(f, **kwargs)
+            self.load_and_merge_sheet(f, **kwargs)
         self.schema.imports.append('linkml:types')
         self.schema.prefixes['linkml'] = Prefix('linkml', 'https://w3id.org/linkml/')
         self._tidy_slot_usage()
@@ -73,7 +85,7 @@ def create_schema(self, csv_files: Union[str, List[str]], **kwargs) -> SchemaDef
 
     def _tidy_slot_usage(self):
         """
-        removes all slot usages marked inapplicable
+        removes all slot usages marked inapplicable.
 
         :return:
         """
@@ -83,18 +95,15 @@ def _tidy_slot_usage(self):
                 c.slots.remove(sn)
                 del c.slot_usage[sn]
 
-
-    def merge_sheet(self, file_name: str, delimiter='\t') -> None:
+    def load_and_merge_sheet(self, file_name: str, delimiter='\t') -> None:
         """
-        Merge information from the given schema sheet into the current schema
+        Merge information from the given schema sheet into the current schema.
 
         :param file_name: schema sheet
         :param delimiter: default is tab
         :return:
         """
         logging.info(f'READING {file_name} D={delimiter}')
-        #with self.ensure_file(file_name) as tsv_file:
-        #    reader = csv.DictReader(tsv_file, delimiter=delimiter)
         with self.ensure_csvreader(file_name, delimiter=delimiter) as reader:
             schemasheet = SchemaSheet.from_dictreader(reader)
             if self.table_config_path:

schemasheets/schemasheet_datamodel.py

@@ -1,3 +1,4 @@
+"""Core data model for a SchemaSheet."""
 import csv
 from dataclasses import dataclass
 from typing import Union, Dict, List, Any
@@ -16,8 +17,7 @@
 DESCRIPTOR = str
 ROW = Dict[str, Any]
 
-
-#c = ClassDefinition
+# Vocabulary for types
 T_SCHEMA = 'schema'
 T_CLASS = 'class'
 T_SLOT = 'slot'
@@ -95,6 +95,9 @@ def add_info(self, info: Union[Dict, DESCRIPTOR]) -> None:
                 self.maps_to = info
             mm = get_metamodel()
             snmap = mm.slot_name_mappings()
+            for k, v in snmap.items():
+                if k != v.name:
+                    print(k,v.name)
             # TODO: use alias
             snmap['uri'] = snmap['type_uri']
             if self.maps_to.startswith("metaslot."):
@@ -265,4 +268,4 @@ def get_configmodel() -> SchemaView:
     """
     package = 'schemasheets.conf.configschema'
     data = pkgutil.get_data(package, f'configschema.yaml')
-    return SchemaView(data.decode("utf-8"))
+    return SchemaView(data.decode("utf-8"))

tests/test_schema_exporter.py

@@ -60,7 +60,7 @@
 
 def test_roundtrip_schema():
     """
-    Tests linkml2sheets by roundtripping from the standard personinfo schema in YAML
+    Tests linkml2sheets by round-tripping from the standard personinfo schema in YAML
     """
     sm = SchemaMaker()
     # sheets2linkml, from SHEET

tests/test_structured_syntax.py

@@ -34,6 +34,9 @@
 
 
 def test_structured_syntax():
+    """
+    Test that structured syntax is roundtripped
+    """
     sm = ss.SchemaMaker()
     sheet_path = str(INPUT_DIR / "structured_syntax.tsv")
     out_path = str(OUTPUT_DIR / "structured_syntax-roundtrip.tsv")