Skip to content

Instantly share code, notes, and snippets.

@aucampia

aucampia/README.md Secret

Last active March 12, 2023 13:24
Show Gist options
  • Save aucampia/37995587ce3296f74f7ed32e1943689d to your computer and use it in GitHub Desktop.
Save aucampia/37995587ce3296f74f7ed32e1943689d to your computer and use it in GitHub Desktop.
Download ZIP
Compact diff for `iwana-20230312T1355-type_sparql`
Raw
README.md

Compact diff generated with:

20230312T142412 iwana@teekai.zoic.eu.org:~/sw/d/github.com/iafork/rdflib.work0
$ git log -1
commit 176d4d3af4494e39ad7084ae14a5232299cb5a84 (HEAD -> iwana-20230312T1355-type_sparql, origin/iwana-20230312T1355-type_sparql)
Author: Iwan Aucamp <aucampia@gmail.com>
Date:   Sun Mar 12 13:23:36 2023 +0000

    feat: more type hints for `rdflib.plugins.sparql`
    
    A bit of a roundabout reason why this matters now, but basically:
    
    I want to add examples for securing RDFLib with `sys.addaudithook`
    and `urllib.request.install_opener`. I also want to be sure examples
    are actually valid, and runnable, so I was adding static analysis
    and simple execution of examples to our CI.
    
    During this I noticed that examples use `initBindings` with
    `Dict[str,...]`, which was not valid according to mypy, but then after
    some investigation I realized the type hints in some places were too
    strict.
    
    So the main impetus for this is actually to relax the type hints in
    `rdflib.graph`, but to ensure this is valid I'm adding a bunch of type
    hints I had saved up to `rdflib.plugins.sparql`.
    
    Even though this PR looks big, it has no runtime changes.
20230312T142414 iwana@teekai.zoic.eu.org:~/sw/d/github.com/iafork/rdflib.work0
$ git status
On branch iwana-20230312T1355-type_sparql
Your branch is up to date with 'origin/iwana-20230312T1355-type_sparql'.

nothing to commit, working tree clean
20230312T142416 iwana@teekai.zoic.eu.org:~/sw/d/github.com/iafork/rdflib.work0
$ PYLOGGING_LEVEL=INFO task run -- git difftool -y -x $(readlink -f devtools/diffrtpy.py) upstream/main | tee /var/tmp/compact.diff
task: [venv:run] poetry run git difftool -y -x /home/iwana/sw/d/github.com/iafork/rdflib.work0/devtools/diffrtpy.py upstream/main
Raw
compact.diff
--- a/rdflib/graph.py
+++ b/rdflib/graph.py
@@ -47,11 +47,10 @@
Identifier,
Literal,
Node,
RDFLibGenid,
URIRef,
- Variable,
)
if TYPE_CHECKING:
import typing_extensions as te
import rdflib.query
--- a/rdflib/plugins/sparql/aggregates.py
+++ b/rdflib/plugins/sparql/aggregates.py
@@ -1,11 +1,29 @@
+from __future__ import annotations
from decimal import Decimal
-from rdflib import XSD, Literal
+from typing import (
+ Any,
+ Callable,
+ Dict,
+ Iterable,
+ List,
+ Mapping,
+ MutableMapping,
+ Optional,
+ Set,
+ Tuple,
+ TypeVar,
+ Union,
+ overload,
+)
+from rdflib.namespace import XSD
from rdflib.plugins.sparql.datatypes import type_promotion
-from rdflib.plugins.sparql.evalutils import NotBoundError, _eval, _val
+from rdflib.plugins.sparql.evalutils import _eval, _val
from rdflib.plugins.sparql.operators import numeric
-from rdflib.plugins.sparql.sparql import SPARQLTypeError
+from rdflib.plugins.sparql.parserutils import CompValue
+from rdflib.plugins.sparql.sparql import FrozenBindings, NotBoundError, SPARQLTypeError
+from rdflib.term import BNode, Identifier, Literal, URIRef, Variable
class Accumulator(object):
def __init__(self, aggregation):
self.var = aggregation.res
@@ -52,10 +70,20 @@
def eval_full_row(self, row):
return row
def use_row(self, row):
return self.eval_row(row) not in self.seen
+
+
+@overload
+def type_safe_numbers(*args):
+ ...
+
+
+@overload
+def type_safe_numbers(*args):
+ ...
def type_safe_numbers(*args):
if any((isinstance(arg, float) for arg in args)) and any(
(isinstance(arg, Decimal) for arg in args)
@@ -143,10 +171,13 @@
pass
except SPARQLTypeError:
pass
+_ValueT = TypeVar("_ValueT", Variable, BNode, URIRef, Literal)
+
+
class Minimum(Extremum):
def compare(self, val1, val2):
return min(val1, val2, key=_val)
--- a/rdflib/plugins/sparql/datatypes.py
+++ b/rdflib/plugins/sparql/datatypes.py
@@ -1,7 +1,11 @@
-from rdflib import XSD
+from __future__ import annotations
+from typing import TYPE_CHECKING, Dict, List, Optional, Set
+from rdflib.namespace import XSD
+if TYPE_CHECKING:
+ from rdflib.term import URIRef
XSD_DTs = set(
(
XSD.integer,
XSD.decimal,
XSD.float,
@@ -72,8 +76,10 @@
t1 = _super_types.get(t1, t1)
t2 = _super_types.get(t2, t2)
if t1 == t2:
return t1
try:
+ if TYPE_CHECKING:
+ assert t2 is not None
return _typePromotionMap[t1][t2]
except KeyError:
raise TypeError("Operators cannot combine datatypes %s and %s" % (t1, t2))
--- a/rdflib/plugins/sparql/evaluate.py
+++ b/rdflib/plugins/sparql/evaluate.py
@@ -1,10 +1,23 @@
+from __future__ import annotations
import collections
import itertools
import json as j
import re
-from typing import Any, Deque, Dict, Generator, Iterable, List, Tuple, Union
+from typing import (
+ TYPE_CHECKING,
+ Any,
+ Deque,
+ Dict,
+ Generator,
+ Iterable,
+ List,
+ Mapping,
+ Optional,
+ Tuple,
+ Union,
+)
from urllib.parse import urlencode
from urllib.request import Request, urlopen
from pyparsing import ParseException
from rdflib.graph import Graph
from rdflib.plugins.sparql import CUSTOM_EVALS, parser
@@ -26,10 +39,12 @@
QueryContext,
SPARQLError,
)
from rdflib.term import BNode, Identifier, Literal, URIRef, Variable
+if TYPE_CHECKING:
+ from rdflib.paths import Path
_Triple = Tuple[Identifier, Identifier, Identifier]
def evalBGP(ctx, bgp):
if not bgp:
@@ -148,10 +163,12 @@
graphSolution = [{part.term: graph.identifier}]
for x in _join(evalPart(c, part.p), graphSolution):
x.ctx.graph = prev_graph
yield x
else:
+ if TYPE_CHECKING:
+ assert not isinstance(graph, Graph)
c = ctx.pushGraph(ctx.dataset.get_context(graph))
for x in evalPart(c, part.p):
x.ctx.graph = prev_graph
yield x
--- a/rdflib/plugins/sparql/evalutils.py
+++ b/rdflib/plugins/sparql/evalutils.py
@@ -1,11 +1,32 @@
+from __future__ import annotations
import collections
-from typing import Dict, Iterable
+from typing import (
+ Any,
+ DefaultDict,
+ Generator,
+ Iterable,
+ Mapping,
+ Set,
+ Tuple,
+ TypeVar,
+ Union,
+ overload,
+)
from rdflib.plugins.sparql.operators import EBV
from rdflib.plugins.sparql.parserutils import CompValue, Expr
-from rdflib.plugins.sparql.sparql import FrozenDict, NotBoundError, SPARQLError
-from rdflib.term import BNode, Literal, URIRef, Variable
+from rdflib.plugins.sparql.sparql import (
+ FrozenBindings,
+ FrozenDict,
+ NotBoundError,
+ QueryContext,
+ SPARQLError,
+)
+from rdflib.term import BNode, Identifier, Literal, URIRef, Variable
+
+_ContextType = Union[FrozenBindings, QueryContext]
+_FrozenDictT = TypeVar("_FrozenDictT", bound=FrozenDict)
def _diff(a, b, expr):
res = set()
for x in a:
@@ -16,10 +37,20 @@
def _minus(a, b):
for x in a:
if all((not x.compatible(y) or x.disjointDomain(y) for y in b)):
yield x
+
+
+@overload
+def _join(a, b):
+ ...
+
+
+@overload
+def _join(a, b):
+ ...
def _join(a, b):
for x in a:
for y in b:
@@ -43,10 +74,20 @@
try:
return EBV(ctx[expr])
except:
return False
return False
+
+
+@overload
+def _eval(expr, ctx, raise_not_bound_error=...):
+ ...
+
+
+@overload
+def _eval(expr, ctx, raise_not_bound_error=...):
+ ...
def _eval(expr, ctx, raise_not_bound_error=True):
if isinstance(expr, (Literal, URIRef)):
return expr
@@ -85,10 +126,13 @@
]
if _s is not None and _p is not None and _o is not None:
yield (_s, _p, _o)
+_ValueT = TypeVar("_ValueT", Variable, BNode, URIRef, Literal)
+
+
def _val(v):
if isinstance(v, Variable):
return 0, v
elif isinstance(v, BNode):
return 1, v
--- a/rdflib/plugins/sparql/parser.py
+++ b/rdflib/plugins/sparql/parser.py
@@ -1,8 +1,9 @@
+from __future__ import annotations
import re
import sys
-from typing import Any, BinaryIO
+from typing import Any, BinaryIO, List
from typing import Optional as OptionalType
from typing import TextIO, Tuple, Union
from pyparsing import CaselessKeyword as Keyword
from pyparsing import (
Combine,
@@ -19,11 +20,11 @@
restOfLine,
)
import rdflib
from rdflib.compat import decodeUnicodeEscape
from . import operators as op
-from .parserutils import Comp, Param, ParamList
+from .parserutils import Comp, CompValue, Param, ParamList
DEBUG = False
def neg(literal):
--- a/rdflib/plugins/sparql/parserutils.py
+++ b/rdflib/plugins/sparql/parserutils.py
@@ -1,8 +1,19 @@
+from __future__ import annotations
from collections import OrderedDict
from types import MethodType
-from typing import TYPE_CHECKING, Any, List, Tuple, Union
+from typing import (
+ TYPE_CHECKING,
+ Any,
+ Callable,
+ List,
+ Mapping,
+ Optional,
+ Tuple,
+ TypeVar,
+ Union,
+)
from pyparsing import ParseResults, TokenConverter, originalTextFor
from rdflib import BNode, Variable
from rdflib.term import Identifier
if TYPE_CHECKING:
@@ -56,10 +67,13 @@
class ParamList(Param):
def __init__(self, name, expr):
Param.__init__(self, name, expr, True)
+
+
+_ValT = TypeVar("_ValT")
class CompValue(OrderedDict):
def __init__(self, name, **values):
OrderedDict.__init__(self)
--- a/rdflib/plugins/sparql/processor.py
+++ b/rdflib/plugins/sparql/processor.py
@@ -1,11 +1,15 @@
+from __future__ import annotations
+from typing import Any, Mapping, Optional, Union
+from rdflib.graph import Graph
from rdflib.plugins.sparql.algebra import translateQuery, translateUpdate
from rdflib.plugins.sparql.evaluate import evalQuery
from rdflib.plugins.sparql.parser import parseQuery, parseUpdate
-from rdflib.plugins.sparql.sparql import Query
+from rdflib.plugins.sparql.sparql import Query, Update
from rdflib.plugins.sparql.update import evalUpdate
from rdflib.query import Processor, Result, UpdateProcessor
+from rdflib.term import Identifier
def prepareQuery(queryString, initNs={}, base=None):
ret = translateQuery(parseQuery(queryString), base, initNs)
ret._original_args = queryString, initNs, base
--- a/rdflib/plugins/sparql/sparql.py
+++ b/rdflib/plugins/sparql/sparql.py
@@ -1,17 +1,34 @@
+from __future__ import annotations
import collections
import datetime
import itertools
import typing as t
-from typing import Any, Container, Dict, Iterable, List, Optional, Tuple, Union
+from typing import (
+ TYPE_CHECKING,
+ Any,
+ Container,
+ Dict,
+ Generator,
+ Iterable,
+ List,
+ Optional,
+ Tuple,
+ TypeVar,
+ Union,
+)
import isodate
import rdflib.plugins.sparql
from rdflib.compat import Mapping, MutableMapping
from rdflib.graph import ConjunctiveGraph, Graph
from rdflib.namespace import NamespaceManager
from rdflib.plugins.sparql.parserutils import CompValue
from rdflib.term import BNode, Identifier, Literal, Node, URIRef, Variable
+
+if TYPE_CHECKING:
+ from rdflib.paths import Path
+_AnyT = TypeVar("_AnyT")
class SPARQLError(Exception):
def __init__(self, msg=None):
Exception.__init__(self, msg)
--- a/rdflib/plugins/sparql/update.py
+++ b/rdflib/plugins/sparql/update.py
@@ -1,9 +1,13 @@
-from rdflib import Graph, Variable
+from __future__ import annotations
+from typing import TYPE_CHECKING, Iterator, Mapping, Optional, Sequence
+from rdflib.graph import Graph
from rdflib.plugins.sparql.evaluate import evalBGP, evalPart
from rdflib.plugins.sparql.evalutils import _fillTemplate, _join
-from rdflib.plugins.sparql.sparql import QueryContext
+from rdflib.plugins.sparql.parserutils import CompValue
+from rdflib.plugins.sparql.sparql import FrozenDict, QueryContext, Update
+from rdflib.term import Identifier, URIRef, Variable
def _graphOrDefault(ctx, g):
if g == "DEFAULT":
return ctx.graph
@@ -23,10 +27,12 @@
else:
return [ctx.dataset.get_context(g)]
def evalLoad(ctx, u):
+ if TYPE_CHECKING:
+ assert isinstance(u.iri, URIRef)
if u.graphiri:
ctx.load(u.iri, default=False, publicID=u.graphiri)
else:
ctx.load(u.iri, default=True)
--- a/rdflib/plugins/stores/memory.py
+++ b/rdflib/plugins/stores/memory.py
@@ -25,11 +25,11 @@
_TriplePatternType,
_TripleType,
)
from rdflib.plugins.sparql.sparql import Query, Update
from rdflib.query import Result
- from rdflib.term import Identifier, URIRef, Variable
+ from rdflib.term import Identifier, URIRef
__all__ = ["SimpleMemory", "Memory"]
ANY = None
class SimpleMemory(Store):
--- a/rdflib/store.py
+++ b/rdflib/store.py
@@ -27,11 +27,11 @@
_TriplePatternType,
_TripleType,
)
from rdflib.plugins.sparql.sparql import Query, Update
from rdflib.query import Result
- from rdflib.term import Identifier, Node, URIRef, Variable
+ from rdflib.term import Identifier, Node, URIRef
VALID_STORE = 1
CORRUPTED_STORE = 0
NO_STORE = -1
UNKNOWN = None
Pickler = pickle.Pickler
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment