maplib 0.15.11__cp39-abi3-manylinux_2_24_x86_64.whl

maplib/.gitignore

@@ -0,0 +1 @@
+*.so

maplib/__init__.py

@@ -0,0 +1,58 @@
+# r'''
+# # Overview
+#
+# '''
+
+__all__ = [
+    "Mapping",
+    "a",
+    "Triple",
+    "SolutionMappings",
+    "IndexingOptions",
+    "ValidationReport",
+    "Instance",
+    "Template",
+    "Argument",
+    "Parameter",
+    "Variable",
+    "RDFType",
+    "XSD",
+    "IRI",
+    "Literal",
+    "Prefix",
+    "BlankNode",
+    "explore",
+    "add_triples"]
+
+import pathlib
+from .maplib import *
+from .add_triples import add_triples
+
+if (pathlib.Path(__file__).parent.resolve() / "graph_explorer").exists():
+    from .graph_explorer import explore
+else:
+    async def explore(
+            m: "Mapping",
+            host: str = "localhost",
+            port: int = 8000,
+            bind: str = "localhost",
+            popup=True,
+            fts=True,
+    ):
+        """Starts a graph explorer session.
+        To run from Jupyter Notebook use:
+        >>> from maplib import explore
+        >>>
+        >>> await explore(m)
+
+        This will block further execution of the notebook until you stop the cell.
+
+        :param m: The Mapping to explore
+        :param host: The hostname that we will point the browser to.
+        :param port: The port where the graph explorer webserver listens on.
+        :param bind: Bind to the following host / ip.
+        :param popup: Pop up the browser window.
+        :param fts: Enable full text search indexing
+        """
+        print("Contact Data Treehouse to try!")
+

maplib/__init__.pyi

@@ -0,0 +1,768 @@
+from pathlib import Path
+from typing import Union, List, Dict, Optional, Callable, Tuple, Literal as LiteralType
+from polars import DataFrame
+from datetime import datetime, date
+
+
+class RDFType:
+    """
+    The type of a column containing a RDF variable.
+    For instance, xsd:string is RDFType.Literal("http://www.w3.org/2001/XMLSchema#string")
+    """
+
+    IRI: Callable[[], "RDFType"]
+    BlankNode: Callable[[], "RDFType"]
+    Literal: Callable[[Union[str, "IRI"]], "RDFType"]
+    Multi: Callable[[List["RDFType"]], "RDFType"]
+    Nested: Callable[["RDFType"], "RDFType"]
+    Unknown: Callable[[], "RDFType"]
+
+class SolutionMappings:
+    """
+    Detailed information about the solution mappings and the types of the variables.
+    """
+
+    mappings: DataFrame
+    rdf_types: Dict[str, RDFType]
+
+class Variable:
+    """
+    A variable in a template.
+    """
+
+    name: str
+
+    def __init__(self, name: str):
+        """
+        Create a new variable.
+        :param name: The name of the variable.
+        """
+        ...
+
+class IRI:
+    iri: str
+    """
+    An IRI.
+    """
+
+    def __init__(self, iri: str):
+        """
+        Create a new IRI
+        :param iri: IRI (without < and >).
+        """
+
+class BlankNode:
+    """
+    A Blank Node.
+    """
+
+    name: str
+
+    def __init__(self, name: str):
+        """
+        Create a new Blank Node
+        :param name: Name of blank node (without _:).
+        """
+
+class Prefix:
+    """
+    A prefix that can be used to ergonomically build iris.
+    """
+
+    def __init__(self, prefix, iri):
+        """
+        Create a new prefix.
+        :param prefix: The name of the prefix
+        :param iri: The prefix IRI.
+        """
+
+    def suf(self, suffix: str) -> IRI:
+        """
+        Create a IRI by appending the suffix.
+        :param suffix: The suffix to append.
+        :return:
+        """
+
+class Literal:
+    """
+    An RDF literal.
+    """
+
+    value: str
+    datatype: Optional[IRI]
+    language: Optional[str]
+
+    def __init__(self, value: str, data_type: IRI = None, language: str = None):
+        """
+        Create a new RDF Literal
+        :param value: The lexical representation of the value.
+        :param data_type: The data type of the value (an IRI).
+        :param language: The language tag of the value.
+        """
+
+    def to_native(self) -> Union[int, float, bool, str, datetime, date]:
+        """
+
+        :return:
+        """
+
+class Parameter:
+    variable: Variable
+    optional: bool
+    allow_blank: bool
+    rdf_type: Optional[RDFType]
+    default_value: Optional[Union[Literal, IRI, BlankNode]]
+    """
+    Parameters for template signatures.
+    """
+
+    def __init__(
+        self,
+        variable: Variable,
+        optional: Optional[bool] = False,
+        allow_blank: Optional[bool] = True,
+        rdf_type: Optional[RDFType] = None,
+        default_value: Optional[Union[Literal, IRI, BlankNode]] = None,
+    ):
+        """
+        Create a new parameter for a Template.
+        :param variable: The variable.
+        :param optional: Can the variable be unbound?
+        :param allow_blank: Can the variable be bound to a blank node?
+        :param rdf_type: The type of the variable. Can be nested.
+        :param default_value: Default value when no value provided.
+        """
+
+class Argument:
+    def __init__(
+        self, term: Union[Variable, IRI, Literal], list_expand: Optional[bool] = False
+    ):
+        """
+        An argument for a template instance.
+        :param term: The term.
+        :param list_expand: Should the argument be expanded? Used with the list_expander argument of instance.
+        """
+
+class Instance:
+    def __init__(
+        self,
+        iri: IRI,
+        arguments: List[Union[Argument, Variable, IRI, Literal, BlankNode, None]],
+        list_expander: Optional[LiteralType["cross", "zipMin", "zipMax"]] = None,
+    ):
+        """
+        A template instance.
+        :param iri: The IRI of the template to be instantiated.
+        :param arguments: The arguments for template instantiation.
+        :param list_expander: (How) should we do list expansion?
+        """
+
+class Template:
+    iri: str
+    parameters: List[Parameter]
+    instances: List[Instance]
+    """
+    An OTTR Template.
+    Note that accessing parameters- or instances-fields returns copies. 
+    To change these fields, you must assign new lists of parameters or instances.  
+    """
+
+    def __init__(
+        self,
+        iri: IRI,
+        parameters: List[Union[Parameter, Variable]],
+        instances: List[Instance],
+    ):
+        """
+        Create a new OTTR Template
+        :param iri: The IRI of the template
+        :param parameters:
+        :param instances:
+        """
+
+    def instance(
+        self,
+        arguments: List[Union[Argument, Variable, IRI, Literal, None]],
+        list_expander: LiteralType["cross", "zipMin", "zipMax"] = None,
+    ) -> Instance:
+        """
+
+        :param arguments: The arguments to the template.
+        :param list_expander: (How) should we list-expand?
+        :return:
+        """
+
+def Triple(
+    subject: Union["Argument", IRI, Variable, BlankNode],
+    predicate: Union["Argument", IRI, Variable, BlankNode],
+    object: Union["Argument", IRI, Variable, Literal, BlankNode],
+    list_expander: Optional[LiteralType["cross", "zipMin", "zipMax"]] = None,
+):
+    """
+    An OTTR Triple Pattern used for creating templates.
+    This is the basis pattern which all template instances are rewritten into.
+    Equivalent to:
+
+    >>> ottr = Prefix("http://ns.ottr.xyz/0.4/")
+    ... Instance(ottr.suf("Triple"), subject, predicate, object, list_expander)
+
+    :param subject:
+    :param predicate:
+    :param object:
+    :param list_expander:
+    :return:
+    """
+
+class XSD:
+    """
+    The xsd namespace, for convenience.
+    """
+
+    boolean: IRI
+    byte: IRI
+    date: IRI
+    dateTime: IRI
+    dateTimeStamp: IRI
+    decimal: IRI
+    double: IRI
+    duration: IRI
+    float: IRI
+    int_: IRI
+    integer: IRI
+    language: IRI
+    long: IRI
+    short: IRI
+    string: IRI
+
+    def __init__(self):
+        """
+        Create the xsd namespace helper.
+        """
+
+def a() -> IRI:
+    """
+    :return: IRI("http://www.w3.org/1999/02/22-rdf-syntax-ns#type")
+    """
+
+# END COMMON WITH CHRONTEXT
+
+class IndexingOptions:
+    """
+    Options for indexing
+    """
+
+    def __init__(
+        self,
+        object_sort_all: bool = None,
+        object_sort_some: List["IRI"] = None,
+        fts_path: str = None,
+    ):
+        """
+        Defaults to indexing on subjects and objects for select types (e.g. rdf:type and rdfs:label)
+
+        :param object_sort_all: Enable object-indexing for all suitable predicates (doubles memory requirement).
+        :param object_sort_some: Enable object-indexing for a selected list of predicates.
+        :param fts_path: Enable full text search, stored at the path
+        """
+
+ParametersType = Dict[str, Tuple[DataFrame, Dict[str, RDFType]]]
+
+class ValidationReport:
+    """
+    SHACL Validation report.
+    Only constructed by maplib.
+    """
+
+    conforms: bool
+    shape_targets: DataFrame
+    performance: DataFrame
+
+    def results(
+        self,
+        native_dataframe: bool = False,
+        include_datatypes: bool = False,
+        streaming: bool = False,
+    ) -> Optional[Union[DataFrame, SolutionMappings]]:
+        """
+        Return the results of the validation report, if they exist.
+
+        :param native_dataframe: Return columns with maplib-native formatting. Useful for round-trips.
+        :param include_datatypes: Return datatypes of the results DataFrame (returns SolutionMappings instead of DataFrame).
+        :param streaming: Use the Polars streaming functionality.
+        :return: The SHACL validation report, as a DataFrame
+        """
+
+    def details(
+        self,
+        native_dataframe: bool = False,
+        include_datatypes: bool = False,
+        streaming: bool = False,
+    ) -> Optional[DataFrame]:
+        """
+        Returns the details of the validation report.
+        Only available if validation was called with include_details=True.
+
+        :param native_dataframe: Return columns with maplib-native formatting. Useful for round-trips.
+        :param include_datatypes: Return datatypes of the results DataFrame (returns SolutionMappings instead of DataFrame).
+        :param streaming: Use the Polars streaming functionality.
+        :return: Details of the SHACL validation report, as a DataFrame
+        """
+
+    def graph(self, indexing=None) -> "Mapping":
+        """
+        Creates a new mapping object where the base graph is the validation report with results.
+        Includes the details of the validation report in the new graph if they exist.
+
+        :param indexing: Should the constructed graph be indexed?
+                         If not specified it is inherited from the mapping where validate was called.
+        :return:
+        """
+
+class Mapping:
+    """
+    A mapping session allowing:
+
+    * Iterative mapping using OTTR templates
+    * Interactive SPARQL querying and enrichment
+    * SHACL validation
+
+    Usage:
+
+    >>> from maplib import Mapping
+    ... doc = '''
+    ... :prefix ex:<http://example.net/ns#>.
+    ... ex:ExampleTemplate [?MyValue] :: {
+    ...    ottr:Triple(ex:myObject, ex:hasValue, ?MyValue)
+    ... } .'''
+    ... m = Mapping(doc)
+
+    :param documents: a stOTTR document or a list of these
+    :param indexing_options: options for indexing
+    """
+
+    def __init__(
+        self,
+        documents: Union[str, List[str]] = None,
+        indexing_options: "IndexingOptions" = None,
+    ) -> "Mapping": ...
+    def add_template(self, template: Union["Template", str]):
+        """
+        Add a template to the mapping. Overwrites any existing template with the same IRI.
+        :param template: The template to add, as a stOTTR string or as a programmatically constructed Template.
+        :return:
+        """
+
+    def expand(
+        self,
+        template: Union[str, "Template", IRI],
+        df: DataFrame = None,
+        graph: str = None,
+        types: Dict[str, RDFType] = None,
+        validate_iris: bool = True,
+        delay_index: bool = True,
+    ) -> None:
+        """
+        Expand a template using a DataFrame
+        Usage:
+
+        >>> m.expand("ex:ExampleTemplate", df)
+
+        If the template has no arguments, the df argument is not necessary.
+
+        :param template: Template, IRI, IRI string or prefixed template name.
+        :param df: DataFrame where the columns have the same names as the template arguments
+        :param graph: The IRI of the graph to add triples to.
+        :param types: The types of the columns.
+        :param validate_iris: Validate any IRI-columns.
+        :param delay_index: Delay index construction - reduces write amplification when doing many expansions
+        """
+
+    def expand_triples(
+        self,
+        df: DataFrame = None,
+        verb: str = None,
+        graph: str = None,
+        types: Dict[str, RDFType] = None,
+        validate_iris: bool = True,
+        delay_index: bool = True,
+    ) -> None:
+        """
+        Expand a template using a DataFrame with columns subject, object and verb
+        The verb column can also be supplied as a string if it is the same for all rows.
+        Usage:
+
+        >>> m.expand_triples(df)
+
+        If the template has no arguments, the df argument is not necessary.
+
+        :param df: DataFrame where the columns are named subject and object. May also contain a verb-column.
+        :param verb: The uri of the verb.
+        :param graph: The IRI of the graph to add triples to.
+        :param types: The types of the columns.
+        :param validate_iris: Validate any IRI-columns.
+        :param delay_index: Delay index construction - reduces write amplification when doing many expansions
+        """
+
+    def expand_default(
+        self,
+        df: DataFrame,
+        primary_key_column: str,
+        dry_run: bool = False,
+        graph: str = None,
+        types: Dict[str, RDFType] = None,
+        validate_iris: bool = True,
+        delay_index: bool = True,
+    ) -> str:
+        """
+        Create a default template and expand it based on a dataframe.
+        Usage:
+
+        >>> template_string = m.expand_default(df, "myKeyCol")
+        ... print(template_string)
+
+        :param df: DataFrame where the columns have the same names as the template arguments
+        :param primary_key_column: This column will be the subject of all triples in the generated template.
+        :param dry_run: Do not expand the template, only return the string.
+        :param graph: The IRI of the graph to add triples to.
+        :param types: The types of the columns.
+        :param validate_iris: Validate any IRI-columns.
+        :param delay_index: Delay index construction - reduces write amplification when doing many expansions
+        :return: The generated template
+        """
+
+    def query(
+        self,
+        query: str,
+        parameters: ParametersType = None,
+        include_datatypes: bool = False,
+        native_dataframe: bool = False,
+        graph: str = None,
+        streaming: bool = False,
+        return_json: bool = False,
+        include_transient: bool = True,
+    ) -> Union[
+        DataFrame, SolutionMappings, List[Union[DataFrame, SolutionMappings, str]], None
+    ]:
+        """
+        Query the contained knowledge graph using SPARQL
+        Currently, SELECT, CONSTRUCT and INSERT are supported.
+        Usage:
+
+        >>> df = mapping.query('''
+        ... PREFIX ex:<http://example.net/ns#>
+        ... SELECT ?obj1 ?obj2 WHERE {
+        ...    ?obj1 ex:hasObj ?obj2
+        ... }''')
+        ... print(df)
+
+        :param query: The SPARQL query string
+        :param parameters: PVALUES Parameters, a DataFrame containing the value bindings in the custom PVALUES construction.
+        :param native_dataframe: Return columns with maplib-native formatting. Useful for round-trips.
+        :param include_datatypes: Datatypes are not returned by default, set to true to return a dict with the solution mappings and the datatypes.
+        :param graph: The IRI of the graph to query.
+        :param streaming: Use Polars streaming
+        :param return_json: Return JSON string.
+        :param include_transient: Include transient triples when querying.
+        :return: DataFrame (Select), list of DataFrames (Construct) containing results, or None for Insert-queries
+
+        """
+
+    def insert(
+        self,
+        query: str,
+        parameters: ParametersType = None,
+        include_datatypes: bool = False,
+        native_dataframe: bool = False,
+        transient: bool = False,
+        streaming: bool = False,
+        source_graph: str = None,
+        target_graph: str = None,
+        delay_index: bool = True,
+        include_transient: bool = True,
+    ):
+        """
+        Insert the results of a Construct query in the graph.
+        Useful for being able to use the same query for inspecting what will be inserted and actually inserting.
+        Usage:
+
+        >>> m = Mapping(doc)
+        ... # Omitted
+        ... hpizzas = '''
+        ... PREFIX pizza:<https://github.com/magbak/maplib/pizza#>
+        ... PREFIX ing:<https://github.com/magbak/maplib/pizza/ingredients#>
+        ... CONSTRUCT { ?p a pizza:HeterodoxPizza }
+        ... WHERE {
+        ... ?p a pizza:Pizza .
+        ... ?p pizza:hasIngredient ing:Pineapple .
+        ... }'''
+        ... m.insert(hpizzas)
+
+        :param query: The SPARQL Insert query string
+        :param parameters: PVALUES Parameters, a DataFrame containing the value bindings in the custom PVALUES construction.
+        :param native_dataframe: Return columns with maplib-native formatting. Useful for round-trips.
+        :param include_datatypes: Datatypes are not returned by default, set to true to return a dict with the solution mappings and the datatypes.
+        :param transient: Should the inserted triples be transient?
+        :param source_graph: The IRI of the source graph to execute the construct query.
+        :param target_graph: The IRI of the target graph to insert into.
+        :param streaming: Use Polars streaming
+        :param delay_index: Delay indexing, use when making multiple inserts of the same predicate.
+        :param include_transient: Include transient triples when querying (but see "transient" above).
+        :return: None
+        """
+
+    def validate(
+        self,
+        shape_graph: str,
+        include_details: bool = False,
+        include_conforms: bool = False,
+        include_shape_graph: bool = True,
+        streaming: bool = False,
+        max_shape_results: int = None,
+        result_storage: str = None,
+        only_shapes: List[str] = None,
+        deactivate_shapes: List[str] = None,
+        dry_run: bool = False,
+    ) -> ValidationReport:
+        """
+        Validate the contained knowledge graph using SHACL
+        Assumes that the contained knowledge graph also contains SHACL Shapes.
+
+        :param shape_graph: The IRI of the Shape Graph.
+        :param include_details: Include details of SHACL evaluation alongside the report. Currently uses a lot of memory.
+        :param include_conforms: Include those results that conformed. Also applies to details.
+        :param include_shape_graph: Include the shape graph in the report, useful when creating the graph from the report.
+        :param include_datatypes: Return the datatypes of the validation report (and details).
+        :param streaming: Use Polars streaming
+        :param max_shape_results: Maximum number of results per shape. Reduces the size of the result set.
+        :param result_storage: Where to store validation results. Can reduce memory use for large result sets.
+        :param only_shapes: Validate only these shapes, None means all shapes are validated (must be IRI, cannot be used with deactivate_shapes).
+        :param deactivate_shapes: Disable validation of these shapes (must be IRI, cannot be used with deactivate_shapes).
+        :param dry_run: Only find targets of shapes, but do not validate them.
+        :return: Validation report containing a report (report.df) and whether the graph conforms (report.conforms)
+        """
+
+    def read_triples(
+        self,
+        file_path: Union[str, Path],
+        format: LiteralType["ntriples", "turtle", "rdf/xml", "xml", "rdfxml"] = None,
+        base_iri: str = None,
+        transient: bool = False,
+        parallel: bool = False,
+        checked: bool = True,
+        graph: str = None,
+        replace_graph: bool = False,
+    ) -> None:
+        """
+        Reads triples from a file path.
+        You can specify the format, or it will be derived using file extension, e.g. filename.ttl or filename.nt.
+        Specify transient if you only want the triples to be available for further querying and validation,
+        but not persisted using write-methods.
+
+        Usage:
+
+        >>> m.read_triples("my_triples.ttl")
+
+        :param file_path: The path of the file containing triples
+        :param format: One of "ntriples", "turtle", "rdf/xml", otherwise it is inferred from the file extension.
+        :param base_iri: Base iri
+        :param transient: Should these triples be included when writing the graph to the file system?
+        :param parallel: Parse triples in parallel, currently only NTRiples. Assumes all prefixes are in the beginning of the document.
+        :param checked: Check IRIs etc.
+        :param graph: The IRI of the graph to read the triples into, if None, it will be the default graph.
+        :param replace_graph: Replace the graph with these triples? Will replace the default graph if no graph is specified.
+        """
+
+    def read_triples_string(
+        self,
+        s: str,
+        format: LiteralType["ntriples", "turtle", "rdf/xml", "xml", "rdfxml"],
+        base_iri: str = None,
+        transient: bool = False,
+        parallel: bool = False,
+        checked: bool = True,
+        graph: str = None,
+        replace_graph: bool = False,
+    ) -> None:
+        """
+        Reads triples from a string.
+        Specify transient if you only want the triples to be available for further querying and validation,
+        but not persisted using write-methods.
+
+        Usage:
+
+        >>> m.read_triples(my_ntriples_string, format="ntriples")
+
+        :param s: String containing serialized triples.
+        :param format: One of "ntriples", "turtle", "rdf/xml".
+        :param base_iri: Base iri
+        :param transient: Should these triples be included when writing the graph to the file system?
+        :param parallel: Parse triples in parallel, currently only NTRiples. Assumes all prefixes are in the beginning of the document.
+        :param checked: Check IRIs etc.
+        :param graph: The IRI of the graph to read the triples into.
+        :param replace_graph: Replace the graph with these triples? Will replace the default graph if no graph is specified.
+        """
+
+    def write_ntriples(self, file_path: Union[str, Path], graph: str = None) -> None:
+        """
+        DEPRECATED: use write_triples with format="ntriples"
+        Write the non-transient triples to the file path specified in the NTriples format.
+
+        Usage:
+
+        >>> m.write_ntriples("my_triples.nt")
+
+        :param file_path: The path of the file containing triples
+        :param graph: The IRI of the graph to write.
+        """
+
+    def write_triples(
+        self,
+        file_path: Union[str, Path],
+        format=LiteralType["ntriples", "turtle", "rdf/xml"],
+        graph: str = None,
+    ) -> None:
+        """
+        Write the non-transient triples to the file path specified in the NTriples format.
+
+        Usage:
+
+        >>> m.write_triples("my_triples.nt", format="ntriples")
+
+        :param file_path: The path of the file containing triples
+        :param format: One of "ntriples", "turtle", "rdf/xml".
+        :param graph: The IRI of the graph to write.
+        """
+
+    def write_ntriples_string(self, graph: str = None) -> str:
+        """
+        DEPRECATED: use write_triples_string with format="ntriples"
+        Write the non-transient triples to a string in memory.
+
+        Usage:
+
+        >>> s = m.write_ntriples_string()
+
+        :param graph: The IRI of the graph to write.
+        :return Triples in mapping in the NTriples format (potentially a large string)
+        """
+
+    def write_triples_string(
+        self, format=LiteralType["ntriples", "turtle", "rdf/xml"], graph: str = None
+    ) -> str:
+        """
+        DEPRECATED: use write_triples_string with format="ntriples"
+        Write the non-transient triples to a string in memory.
+
+        Usage:
+
+        >>> s = m.write_ntriples_string(format="turtle")
+
+        :param format: One of "ntriples", "turtle", "rdf/xml".
+        :param graph: The IRI of the graph to write.
+        :return Triples in mapping in the NTriples format (potentially a large string)
+        """
+
+    def write_native_parquet(
+        self, folder_path: Union[str, Path], graph: str = None
+    ) -> None:
+        """
+        Write non-transient triples using the internal native Parquet format.
+
+        Usage:
+
+        >>> m.write_native_parquet("output_folder")
+
+        :param folder_path: The path of the folder to write triples in the native format.
+        :param graph: The IRI of the graph to write.
+        """
+
+    def create_sprout(self):
+        """
+        A sprout is a simplified way of dealing with multiple graphs.
+        See also `Mapping.insert_sprout` and `Mapping.detach_sprout`
+
+        :return:
+        """
+
+    def insert_sprout(
+        self,
+        query: str,
+        parameters: ParametersType = None,
+        include_datatypes: bool = False,
+        native_dataframe: bool = False,
+        transient: bool = False,
+        streaming: bool = False,
+        source_graph: str = None,
+        target_graph: str = None,
+        delay_index: bool = True,
+        include_transient: bool = True,
+    ):
+        """
+        Insert the results of a Construct query in a sprouted graph, which is created if no sprout is active.
+        Sprouts are simplified way of dealing with multiple graphs.
+        Useful for being able to use the same query for inspecting what will be inserted and actually inserting.
+        See also `Mapping.detach_sprout`
+
+        Usage:
+
+        >>> m = Mapping(doc)
+        ... m.create_sprout()
+        ... # Omitted
+        ... hpizzas = '''
+        ... PREFIX pizza:<https://github.com/magbak/maplib/pizza#>
+        ... PREFIX ing:<https://github.com/magbak/maplib/pizza/ingredients#>
+        ... CONSTRUCT { ?p a pizza:HeterodoxPizza }
+        ... WHERE {
+        ... ?p a pizza:Pizza .
+        ... ?p pizza:hasIngredient ing:Pineapple .
+        ... }'''
+        ... m.insert_sprout(hpizzas)
+
+        :param query: The SPARQL Insert query string
+        :param parameters: PVALUES Parameters, a DataFrame containing the value bindings in the custom PVALUES construction.
+        :param native_dataframe: Return columns with maplib-native formatting. Useful for round-trips.
+        :param include_datatypes: Datatypes are not returned by default, set to true to return a dict with the solution mappings and the datatypes.
+        :param transient: Should the inserted triples be included in exports?
+        :param source_graph: The IRI of the source graph to execute the construct query.
+        :param target_graph: The IRI of the target graph to insert into.
+        :param streaming: Use Polars streaming
+        :param delay_index: Delay indexing, use when making multiple inserts of the same predicate to improve performance.
+        :param include_transient: Include transient triples when querying (see also "transient" above).
+        :return: None
+        """
+
+    def detach_sprout(self) -> "Mapping":
+        """
+        Detaches and returns the sprout from the mapping.
+
+        :return: The sprout as its own Mapping.
+        """
+
+    def get_predicate_iris(
+        self, graph: str = None, include_transient: bool = False
+    ) -> List["IRI"]:
+        """
+        :param graph: The graph to get the predicate iris from.
+        :param include_transient: Should we include predicates only between transient triples?
+        :return: The IRIs of the predicates currently in the given graph.
+        """
+
+    def get_predicate(
+        self, iri: "IRI", graph: str = None, include_transient: bool = False
+    ) -> List["SolutionMappings"]:
+        """
+        :param iri: The predicate IRI
+        :param graph: The graph to get the predicate from.
+        :param include_transient: Should we include transient triples?
+        :return: A list of the underlying tables that store a given predicate.
+        """
+
+    def create_index(
+        self, options: "IndexingOptions" = None, all: bool = True, graph: str = None
+    ):
+        """
+        :param options: Indexing options
+        :param all: Apply to all existing and new graphs
+        :param graph: The graph where indexes should be added
+        :return:
+        """

maplib/add_triples.py

@@ -0,0 +1,29 @@
+from maplib.maplib import Mapping, Template, IRI, Triple, Variable
+
+
+def add_triples(
+    source: Mapping, target: Mapping, source_graph: str = None, target_graph: str = None
+):
+    """(Zero) copy the triples from one Mapping into another.
+
+    :param source: The source mapping
+    :param target: The target mapping
+    :param source_graph: The named graph in the source mapping to copy from. None means default graph.
+    :param target_graph: The named graph in the target mapping to copy into. None means default graph.
+    """
+    for p in source.get_predicate_iris(source_graph):
+        subject = Variable("subject")
+        object = Variable("object")
+        template = Template(
+            iri=IRI("urn:maplib:tmp"),
+            parameters=[subject, object],
+            instances=[Triple(subject, p, object)],
+        )
+        sms = source.get_predicate(p, source_graph)
+        for sm in sms:
+            target.expand(
+                template,
+                sm.mappings,
+                types=sm.rdf_types,
+                graph=target_graph,
+            )

maplib-0.15.11.dist-info/METADATA

@@ -0,0 +1,206 @@
+Metadata-Version: 2.3
+Name: maplib
+Version: 0.15.11
+Classifier: Development Status :: 4 - Beta
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Programming Language :: Python :: 3 :: Only
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Rust
+Classifier: Topic :: Database :: Database Engines/Servers
+Classifier: Topic :: Scientific/Engineering
+Requires-Dist: polars >=0.20.13
+Requires-Dist: pyarrow >=7.0.0
+License-File: LICENSE
+Summary: Dataframe-based interactive knowledge graph construction
+Keywords: rdf,graph,dataframe,sparql,ottr
+Author-email: Magnus Bakken <magnus@data-treehouse.com>
+Requires-Python: >=3.9
+Description-Content-Type: text/markdown; charset=UTF-8; variant=GFM
+Project-URL: Homepage, https://github.com/DataTreehouse/maplib
+Project-URL: Documentation, https://datatreehouse.github.io/maplib/maplib/maplib.html
+Project-URL: Repository, https://github.com/DataTreehouse/maplib
+Project-URL: Changelog, https://github.com/DataTreehouse/maplib/releases
+
+## maplib: High-performance RDF knowledge graph construction, SHACL validation and SPARQL-based enrichment in Python
+maplib is a knowledge graph construction library for building RDF knowledge graphs using template expansion ([OTTR](https://ottr.xyz/) Templates). Maplib features SPARQL- and SHACL-engines that are available as the graph is being constructed, allowing enrichment and validation. It can construct and validate knowledge graphs with millions of nodes in seconds.
+
+maplib allows you to leverage your existing skills with Pandas or Polars to extract and wrangle data from existing databases and spreadsheets, before applying simple templates to them to build a knowledge graph. 
+
+Template expansion is typically zero-copy and nearly instantaneous, and the built-in SPARQL and SHACL engines means you can query, inspect, enrich and validate the knowledge graph immediately.      
+
+maplib is written in Rust, it is built on [Apache Arrow](https://arrow.apache.org/) using [Pola.rs](https://www.pola.rs/) and uses libraries from [Oxigraph](https://github.com/oxigraph/oxigraph) for handling linked data as well as parsing SPARQL queries.
+
+## Installing
+The package is published on [PyPi](https://pypi.org/project/maplib/) and the API documented [here](https://datatreehouse.github.io/maplib/maplib.html):
+```shell
+pip install maplib
+```
+Please send us a message, e.g. on LinkedIn (search for Data Treehouse) or on our [webpage](https://www.data-treehouse.com/contact-8) if you want to try out SHACL.  
+
+## Mapping
+We can easily map DataFrames to RDF-graphs using the Python library. Below is a reproduction of the example in the paper [1]. Assume that we have a DataFrame given by: 
+
+```python
+import polars as pl
+pl.Config.set_fmt_str_lengths(150)
+
+pi = "https://github.com/DataTreehouse/maplib/pizza#"
+df = pl.DataFrame({
+    "p":[pi + "Hawaiian", pi + "Grandiosa"],
+    "c":[pi + "CAN", pi + "NOR"],
+    "ings": [[pi + "Pineapple", pi + "Ham"],
+             [pi + "Pepper", pi + "Meat"]]
+})
+print(df)
+```
+That is, our DataFrame is:
+
+| p                             | c                              | ings                                     |
+|-------------------------------|--------------------------------|------------------------------------------|
+| str                           | str                            | list[str]                                |
+| "https://.../pizza#Hawaiian"  | "https://.../maplib/pizza#CAN" | [".../pizza#Pineapple", ".../pizza#Ham"] |
+| "https://.../pizza#Grandiosa" | "https://.../maplib/pizza#NOR" | [".../pizza#Pepper", ".../pizza#Meat"]   |
+
+Then we can define a OTTR template, and create our knowledge graph by expanding this template with our DataFrame as input:
+```python
+from maplib import Mapping, Prefix, Template, Argument, Parameter, Variable, RDFType, Triple, a
+pi = Prefix("pi", pi)
+
+p_var = Variable("p")
+c_var = Variable("c")
+ings_var = Variable("ings")
+
+template = Template(
+    iri= pi.suf("PizzaTemplate"),
+    parameters= [
+        Parameter(variable=p_var, rdf_type=RDFType.IRI()),
+        Parameter(variable=c_var, rdf_type=RDFType.IRI()),
+        Parameter(variable=ings_var, rdf_type=RDFType.Nested(RDFType.IRI()))
+    ],
+    instances= [
+        Triple(p_var, a(), pi.suf("Pizza")),
+        Triple(p_var, pi.suf("fromCountry"), c_var),
+        Triple(
+            p_var, 
+            pi.suf("hasIngredient"), 
+            Argument(term=ings_var, list_expand=True), 
+            list_expander="cross")
+    ]
+)
+
+m = Mapping()
+m.expand(template, df)
+hpizzas = """
+    PREFIX pi:<https://github.com/DataTreehouse/maplib/pizza#>
+    CONSTRUCT { ?p a pi:HeterodoxPizza } 
+    WHERE {
+        ?p a pi:Pizza .
+        ?p pi:hasIngredient pi:Pineapple .
+    }"""
+m.insert(hpizzas)
+return m
+```
+
+We can immediately query the mapped knowledge graph:
+
+```python
+m.query("""
+PREFIX pi:<https://github.com/DataTreehouse/maplib/pizza#>
+SELECT ?p ?i WHERE {
+?p a pi:Pizza .
+?p pi:hasIngredient ?i .
+}
+""")
+```
+
+The query gives the following result (a DataFrame):
+
+| p                               | i                                     |
+|---------------------------------|---------------------------------------|
+| str                             | str                                   |
+| "<https://.../pizza#Grandiosa>" | "<https://.../pizza#Meat>"      |
+| "<https://.../pizza#Grandiosa>" | "<https://.../pizza#Pepper>"    |
+| "<https://.../pizza#Hawaiian>"  | "<https://.../pizza#Pineapple>" |
+| "<https://.../pizza#Hawaiian>"  | "<https://.../pizza#Ham>"       |
+
+Next, we are able to perform a construct query, which creates new triples but does not insert them. 
+
+```python
+hpizzas = """
+PREFIX pi:<https://github.com/DataTreehouse/maplib/pizza#>
+CONSTRUCT { ?p a pi:UnorthodoxPizza } 
+WHERE {
+    ?p a pi:Pizza .
+    ?p pi:hasIngredient pi:Pineapple .
+}"""
+res = m.query(hpizzas)
+res[0]
+```
+
+The resulting triples are given below:
+
+| subject                        | verb                                 | object                                |
+|--------------------------------|--------------------------------------|---------------------------------------|
+| str                            | str                                  | str                                   |
+| "<https://.../pizza#Hawaiian>" | "<http://.../22-rdf-syntax-ns#type>" | "<https://.../pizza#UnorthodoxPizza>" |
+
+If we are happy with the output of this construct-query, we can insert it in the mapping state. Afterwards we check that the triple is added with a query.
+
+```python
+m.insert(hpizzas)
+m.query("""
+PREFIX pi:<https://github.com/DataTreehouse/maplib/pizza#>
+
+SELECT ?p WHERE {
+?p a pi:UnorthodoxPizza
+}
+""")
+```
+
+Indeed, we have added the triple: 
+
+| p                                                          |
+|------------------------------------------------------------|
+| str                                                        |
+| "<https://github.com/DataTreehouse/maplib/pizza#Hawaiian>" |
+
+## API
+The [API](https://datatreehouse.github.io/maplib/maplib.html) is simple, and contains only one class and a few methods for:
+- expanding templates
+- querying with SPARQL
+- validating with SHACL
+- importing triples (Turtle, RDF/XML, NTriples)
+- writing triples (Turtle, RDF/XML, NTriples)
+- creating a new Mapping object (sprout) based on queries over the current Mapping object.
+
+The API is documented [HERE](https://datatreehouse.github.io/maplib/maplib.html)
+
+## Roadmap of features and optimizations
+Spring 2025
+- Datalog reasoning support
+- Reduced memory footprint
+- Further SPARQL optimizations
+- JSON-LD support
+
+Fall 2025
+- SHACL rules support
+- Improved TTL serialization (prettier and faster)
++++
+
+Roadmap is subject to changes,particularly user and customer requests. 
+
+## References
+There is an associated paper [1] with associated benchmarks showing superior performance and scalability that can be found [here](https://ieeexplore.ieee.org/document/10106242). OTTR is described in [2].
+
+[1] M. Bakken, "maplib: Interactive, literal RDF model mapping for industry," in IEEE Access, doi: 10.1109/ACCESS.2023.3269093.
+
+[2] M. G. Skjæveland, D. P. Lupp, L. H. Karlsen, and J. W. Klüwer, “Ottr: Formal templates for pattern-based ontology engineering.” in WOP (Book),
+2021, pp. 349–377.
+
+## Licensing
+All code produced since August 1st. 2023 is copyrighted to [Data Treehouse AS](https://www.data-treehouse.com/) with an Apache 2.0 license unless otherwise noted. 
+
+All code which was produced before August 1st. 2023 copyrighted to [Prediktor AS](https://www.prediktor.com/) with an Apache 2.0 license unless otherwise noted, and has been financed by [The Research Council of Norway](https://www.forskningsradet.no/en/) (grant no. 316656) and [Prediktor AS](https://www.prediktor.com/) as part of a PhD Degree. The code at this state is archived in the repository at [https://github.com/magbak/maplib](https://github.com/magbak/maplib).
+

maplib-0.15.11.dist-info/RECORD

@@ -0,0 +1,10 @@
+maplib-0.15.11.dist-info/METADATA,sha256=F0jVNMeBpo166-vMIY-MHeXMP9a7p2d8d12tkojw9tc,9058
+maplib-0.15.11.dist-info/WHEEL,sha256=CJlf0CwwxWB9-lL4mEcOQbzkizXEbn7t6nPcVV_BBq8,106
+maplib-0.15.11.dist-info/licenses/LICENSE,sha256=jAD7dAxI84Df1hzrP67O-yOMrEfOrhLQcI8qEY6KRu8,11459
+maplib/add_triples.py,sha256=DRT-FWrYiSnj8uue7i50ed32LOAcmx8_XPnDD22xU4A,1074
+maplib/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+maplib/.gitignore,sha256=XJr_ApsGWXGOqPaqA-Z7RsnZMR07sG0hbTPurJVGFAw,5
+maplib/__init__.py,sha256=8wOl80QJmT6y9MwPrllV9WSjGURcgaN_CRrtiod1lI8,1405
+maplib/__init__.pyi,sha256=IkfExJJiGL1CDssp1QqA2cdFGJRWCU0vXxOiNxL0RsA,27079
+maplib/maplib.abi3.so,sha256=vy4t2zq20I0DSM7ArLdfQIJ6ckSo57FjYzdWON5hp00,67783184
+maplib-0.15.11.dist-info/RECORD,,

maplib-0.15.11.dist-info/WHEEL

@@ -0,0 +1,4 @@
+Wheel-Version: 1.0
+Generator: maturin (1.7.4)
+Root-Is-Purelib: false
+Tag: cp39-abi3-manylinux_2_24_x86_64

maplib-0.15.11.dist-info/licenses/LICENSE

@@ -0,0 +1,202 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright code / files produced 2022 - July 31.2023 Prediktor AS
+   Copyright code / files produced on or after August 1. 2023 Data Treehouse AS
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.