cli

Author: cmungall

poetry.lock

@@ -13,6 +13,7 @@ click = "^8.1.3"
 importlib = "^1.0.4"
 lightrdf = "^0.2.1"
 curies = "^0.2.0"
+prefixmaps = "^0.1.2"
 
 [tool.poetry.dev-dependencies]
 pytest = "^7.1.2"
@@ -22,7 +23,7 @@ sphinx-autodoc-typehints = "^1.19.2"
 sphinx-click = "^4.3.0"
 
 [tool.poetry.scripts]
-rdf-sql-bulkloader = "rdf-sql-bulkloader.cli:main"
+rdf-sql-bulkloader = "rdf_sql_bulkloader.cli:main"
 
 [tool.poetry.extras]
 docs = [

pyproject.toml

@@ -1,12 +1,10 @@
 """Command line interface for rdf-sql-bulkloader."""
+from pathlib import Path
+
 import click
 import logging
 
-from rdf_sql_bulkloader import __version__
-
-__all__ = [
-    "main",
-]
+from rdf_sql_bulkloader import __version__, SqliteBulkloader
 
 logger = logging.getLogger(__name__)
 
@@ -29,10 +27,29 @@ def main(verbose: int, quiet: bool):
     if quiet:
         logger.setLevel(level=logging.ERROR)
 
+
 @main.command()
-def run():
+@click.option("--output", "-o", required=True)
+@click.option("--force/--no-force",
+              default=False,
+              show_default=True,
+              help="Recreates db if already present")
+@click.argument("files", nargs=-1)
+def load_sqlite(files, output, force: bool):
     """Run the rdf-sql-bulkloader's demo command."""
-    demo()
+    output_path = Path(output)
+    if output_path.exists():
+        if force:
+            output_path.unlink()
+        else:
+            raise ValueError(f"Path exists {output_path}")
+    loader = SqliteBulkloader(output)
+    if len(files) > 1:
+        logging.warning(f"Blank nodes may be shared TODO FIX ME")
+    for file in files:
+        print(file)
+        loader.bulkload(file)
+
 
 
 

src/rdf_sql_bulkloader/cli.py

@@ -3,11 +3,12 @@
 from collections import defaultdict
 from dataclasses import dataclass
 from pathlib import Path
-from typing import Union, Tuple, Iterator, Mapping, Optional
+from typing import Union, Tuple, Iterator, Mapping, Optional, List
 
 import curies
 import lightrdf
 from curies import Converter
+from prefixmaps.io.parser import load_multi_context
 
 re_untyped_literal = re.compile(r'^"(.*)"$')
 re_typed_literal = re.compile(r'^"(.*)"\^\^<([\S^"]+)>$')
@@ -72,23 +73,42 @@ def _parse_literal(o: str) -> Tuple[OBJECT_VALUE, OBJECT_DATATYPE, OBJECT_LANG]:
 def _parse_literal_as_value(o: str) -> str:
     return _parse_literal(o)[0]
 
+
+
 @dataclass
 class BulkLoader(ABC):
     """
     Base class for all bulk loaders
     """
     path: str
+    named_prefix_maps: List[str] = None
     prefix_map: PREFIX_MAP = None
     converter: Converter = None
     index_statements = False
 
     def __post_init__(self):
+        if self.prefix_map is None:
+            named_prefix_maps = self.named_prefix_maps
+            if named_prefix_maps is None:
+                named_prefix_maps = ["merged"]
+            if len(named_prefix_maps) > 0:
+                ctxt = load_multi_context(named_prefix_maps)
+                self.prefix_map = ctxt.as_dict()
+        self._set_converter()
+
+    def _set_converter(self):
         if self.prefix_map:
             self.converter = Converter.from_prefix_map(self.prefix_map)
 
     def bulkload(self, path: str):
         raise NotImplemented
 
+    def _parse_node(self, o: str) -> str:
+        if re_blank_node.match(o):
+            return f"_:{o}"
+        else:
+            return self.contract_uri(o)
+
     def contract_uri(self, uri: Optional[URI]) -> Optional[str]:
         if uri is None:
             return None
@@ -139,7 +159,7 @@ def statements(self, path: Union[Path, str]) -> Iterator[STATEMENT]:
 
         # this code could be reduced if https://github.com/ozekik/lightrdf/issues/12 is implemented
         for t in doc.search_triples(None, None, None):
-            s = self.contract_uri(t[0])
+            s = self._parse_node(t[0])
             p = self.contract_uri(t[1])
             o = t[2]
             o_uri = None
@@ -149,10 +169,7 @@ def statements(self, path: Union[Path, str]) -> Iterator[STATEMENT]:
                 o_value, o_datatype, o_lang = _parse_literal(o)
             else:
                 o_value = None
-                if re_blank_node.match(o):
-                    o_uri = f"_:{o}"
-                else:
-                    o_uri = self.contract_uri(o)
+                o_uri = self._parse_node(o)
             yield s, p, o_uri, o_value, o_datatype, o_lang
 
     def ddl(self) -> str:

src/rdf_sql_bulkloader/loaders/bulkloader.py

@@ -22,3 +22,4 @@ def bulkload(self, path: str):
         colstr = ",".join(COLS)
         qs = ",".join(["?" for _ in COLS])
         con.executemany(f"insert into statement({colstr}) values ({qs})", tuples)
+        con.commit()

src/rdf_sql_bulkloader/loaders/sqlite3_bulkloader.py

@@ -8,8 +8,8 @@
 
 CASES =[
     (None, 'GO:0005634', 'RO:0002161', 'NCBITaxon:2', None, None, None, None),
-    (None, 'GO:0005634', 'IAO:0000115', None, "A membrane-bounded organelle of eukaryotic cells in which chromosomes are housed and replicated. In most cells, the nucleus contains all of the cell's chromosomes except the organellar chromosomes, and is the site of RNA synthesis and processing. In some species, or in specialized cell types, RNA metabolism or DNA replication may be absent.", 'http://www.w3.org/2001/XMLSchema#string', None, None)
-
+    (None, 'GO:0005634', 'IAO:0000115', None, "A membrane-bounded organelle of eukaryotic cells in which chromosomes are housed and replicated. In most cells, the nucleus contains all of the cell's chromosomes except the organellar chromosomes, and is the site of RNA synthesis and processing. In some species, or in specialized cell types, RNA metabolism or DNA replication may be absent.", 'http://www.w3.org/2001/XMLSchema#string', None, None),
+    (None, 'GO:0005634', 'rdf:type', 'owl:Class', None, None, None, None),
 ]
 
 class TestSqlit3BulkLoader(unittest.TestCase):