Skip to content

Mash Module API

Overview

The mash module is the read/retrieval layer for source data in GKC workflows.

It includes:

  • Generic Wikibase API retrieval via WikibaseApiClient
  • MediaWiki page wikitext retrieval and SPARQL-block extraction primitives
  • MashSourceAdapter plugin contract for source loader integrations
  • Wikidata loaders and template objects
  • Wikipedia template retrieval
  • Utility functions for template preparation and label hydration

Use mash for reads and template shaping. Write operations belong in shipper.

Quick Start

from gkc.mash import WikibaseApiClient, WikibaseLoader

# Generic Wikibase read (works with Wikidata or Data Distillery API URLs)
api = WikibaseApiClient(api_url="https://www.wikidata.org/w/api.php")
entity = api.get_entity("Q42")

# Wikidata convenience loader
loader = WikibaseLoader()
template = loader.load_item("Q42")
print(template.summary())

Public API Quick Starts

WikibaseApiClient

from gkc.mash import WikibaseApiClient

client = WikibaseApiClient(api_url="https://datadistillery.wikibase.cloud/w/api.php")

results = client.search_entities(
    label="GKC Property Specification",
    entity_type="item",
    language="en",
    limit=5,
)

batch = client.get_entities(["Q1", "Q2"])
single = client.get_entity("Q1")

raw = client.request({"action": "query", "format": "json", "meta": "siteinfo"})
print(len(results), sorted(batch.keys()), single.get("id"), bool(raw))

WikibaseApiClient sends a default User-Agent header automatically when one is not provided. You can still pass a custom user_agent value in the constructor to override it for your workflow.

fetch_mediawiki_page_wikitext()

from gkc.mash import WikibaseApiClient, fetch_mediawiki_page_wikitext

api_client = WikibaseApiClient(api_url="https://datadistillery.wikibase.cloud/w/api.php")
wikitext = fetch_mediawiki_page_wikitext(api_client, "Item_talk:Q4")
print(wikitext[:200])

extract_sparql_blocks() and extract_first_sparql_block()

from gkc.mash import extract_first_sparql_block, extract_sparql_blocks

wikitext = """
<sparql>SELECT ?item ?itemLabel WHERE { ?item ?p ?o }</sparql>
<sparql>SELECT ?other WHERE { ?other ?p ?o }</sparql>
"""

all_blocks = extract_sparql_blocks(wikitext)
first_block = extract_first_sparql_block(wikitext)

print(len(all_blocks), first_block[:40])

DataTemplate (Protocol)

from dataclasses import dataclass
from gkc.mash import DataTemplate

@dataclass
class MinimalTemplate(DataTemplate):
    value: str

    def summary(self):
        return {"value": self.value}

    def to_dict(self):
        return {"value": self.value}

template = MinimalTemplate("example")
print(template.summary(), template.to_dict())

MashSourceAdapter (Protocol)

from gkc.mash import MashSourceAdapter, WikibaseMashSourceAdapter

adapter: MashSourceAdapter = WikibaseMashSourceAdapter()
print(adapter.source_name, adapter.can_load("Q42"))

WikibaseMashSourceAdapter

from gkc.mash import WikibaseMashSourceAdapter

adapter = WikibaseMashSourceAdapter()

single = adapter.load("Q42")
batch = adapter.load_many(["Q42", "P31", "E502"])

print(single.summary())
print(sorted(batch.keys()))

WikipediaMashSourceAdapter

from gkc.mash import WikipediaMashSourceAdapter

adapter = WikipediaMashSourceAdapter()
template = adapter.load("Template:Infobox settlement")

print(template.summary())

fetch_property_labels()

from gkc.mash import fetch_property_labels

labels = fetch_property_labels(["P31", "P279"], language="en")
print(labels)

strip_entity_identifiers()

from gkc.mash import strip_entity_identifiers

entity_data = {
    "id": "Q42",
    "lastrevid": 123,
    "claims": {"P31": [{"id": "Q42$abc", "mainsnak": {"hash": "h1"}}]},
}

shell = strip_entity_identifiers(entity_data)
print(shell)

ClaimSummary

from gkc.mash import ClaimSummary

claim = ClaimSummary(property_id="P31", value="Q5", rank="normal")
print(claim.property_id, claim.value, claim.rank)

WikibaseItemTemplate

from gkc.mash import (
    WikibaseLoader,
    apply_item_property_filters,
    apply_template_language_filter,
)

loader = WikibaseLoader()
template = loader.load_item("Q42")

apply_item_property_filters(template, include_properties=["P31", "P21"])
template.filter_qualifiers()
template.filter_references()
apply_template_language_filter(template, ["en"])

print(template.summary())
print(template.to_dict().keys())
print(template.to_simple_dict().keys())
print(template.to_shell().keys())
print(template.to_qsv1(for_new_item=False)[:120])

try:
    template.to_gkc_entity_profile()
except NotImplementedError:
    pass

WikibasePropertyTemplate

from gkc.mash import WikibaseLoader, apply_template_language_filter

loader = WikibaseLoader()
prop = loader.load_property("P31")

apply_template_language_filter(prop, ["en"])
print(prop.summary())
print(prop.to_dict().keys())
print(prop.to_shell().keys())

try:
    prop.to_gkc_entity_profile()
except NotImplementedError:
    pass

WikibaseEntitySchemaTemplate

from gkc.mash import WikibaseLoader, apply_template_language_filter

loader = WikibaseLoader()
schema = loader.load_entity_schema("E502")

apply_template_language_filter(schema, ["en"])
print(schema.summary())
print(schema.to_dict().keys())
print(schema.to_shell().keys())

try:
    schema.to_gkc_entity_profile()
except NotImplementedError:
    pass

WikibaseLoader

from gkc.mash import WikibaseLoader

loader = WikibaseLoader(api_url="https://www.wikidata.org/w/api.php")

item = loader.load_item("Q42")
legacy = loader.load("Q42")  # Deprecated alias
batch = loader.load_items(["Q42", "Q5"])
prop = loader.load_property("P31")
schema = loader.load_entity_schema("E502")
raw_entity = loader.load_entity_data("Q42")

print(item.qid, legacy.qid, sorted(batch.keys()), prop.pid, schema.eid, raw_entity.get("id"))

WikipediaTemplate and WikipediaLoader

from gkc.mash import WikipediaLoader

loader = WikipediaLoader()
template = loader.load_template("Infobox settlement")

print(template.summary())
print(template.to_dict().keys())

API Reference (mkdocstrings)

WikibaseApiClient

Generic MediaWiki/Wikibase API helper.

Plain meaning: Reusable client for wbsearchentities and wbgetentities across Wikidata, Data Distillery, or any compatible Wikibase API endpoint.

Source code in gkc/mash/core.py 
 39
 40
 41
 42
 43
 44
 45
 46
 47
 48
 49
 50
 51
 52
 53
 54
 55
 56
 57
 58
 59
 60
 61
 62
 63
 64
 65
 66
 67
 68
 69
 70
 71
 72
 73
 74
 75
 76
 77
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
class WikibaseApiClient:
    """Generic MediaWiki/Wikibase API helper.

    Plain meaning: Reusable client for wbsearchentities and wbgetentities across
    Wikidata, Data Distillery, or any compatible Wikibase API endpoint.
    """

    def __init__(
        self,
        api_url: str = "https://www.wikidata.org/w/api.php",
        *,
        session: Optional[requests.Session] = None,
        user_agent: Optional[str] = None,
        timeout: int = 30,
    ):
        self.api_url = api_url
        self.timeout = timeout
        self.session = session or requests.Session()
        self.user_agent = user_agent or DEFAULT_USER_AGENT
        session_headers = getattr(self.session, "headers", None)
        if session_headers is None:
            try:
                setattr(self.session, "headers", {})
                session_headers = self.session.headers
            except Exception:
                session_headers = None

        if hasattr(session_headers, "update"):
            session_headers.update({"User-Agent": self.user_agent})

    def search_entities(
        self,
        *,
        label: str,
        entity_type: str,
        language: str,
        limit: int = 10,
    ) -> list[dict[str, Any]]:
        payload = self.request(
            {
                "action": "wbsearchentities",
                "format": "json",
                "search": label,
                "language": language,
                "type": entity_type,
                "limit": limit,
            }
        )
        return payload.get("search", [])

    def get_entities(self, entity_ids: list[str]) -> dict[str, dict[str, Any]]:
        if not entity_ids:
            return {}

        payload = self.request(
            {
                "action": "wbgetentities",
                "format": "json",
                "ids": "|".join(entity_ids),
            }
        )
        entities = payload.get("entities", {})
        if not isinstance(entities, dict):
            return {}

        return {
            eid: entity_data
            for eid, entity_data in entities.items()
            if isinstance(entity_data, dict) and "missing" not in entity_data
        }

    def get_entity(self, entity_id: str) -> dict[str, Any]:
        entities = self.get_entities([entity_id])
        if entity_id not in entities:
            raise RuntimeError(f"Entity '{entity_id}' not found")
        return entities[entity_id]

    def request(self, params: dict[str, Any]) -> dict[str, Any]:
        try:
            response = self.session.get(
                self.api_url,
                params=params,
                timeout=self.timeout,
            )
            response.raise_for_status()
        except requests.RequestException as exc:
            raise RuntimeError(f"Wikibase API request failed: {exc}") from exc

        try:
            payload = response.json()
        except ValueError as exc:
            raise RuntimeError("Wikibase API returned non-JSON response") from exc

        if "error" in payload:
            raise RuntimeError(f"Wikibase API returned error: {payload['error']}")

        return payload

fetch_mediawiki_page_wikitext()

Fetch page wikitext from a MediaWiki API endpoint.

Parameters:

Name Type Description Default
api_client WikibaseApiClient

Configured Wikibase/MediaWiki API client.

 required
title str

Full page title (for example, Item_talk:Q4).

 required

Returns:

Type Description
str

Page wikitext as a string.

Raises:

Type Description
RuntimeError

If page content is missing or cannot be parsed.
Source code in gkc/mash/core.py 
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
def fetch_mediawiki_page_wikitext(api_client: WikibaseApiClient, title: str) -> str:
    """Fetch page wikitext from a MediaWiki API endpoint.

    Args:
        api_client: Configured Wikibase/MediaWiki API client.
        title: Full page title (for example, ``Item_talk:Q4``).

    Returns:
        Page wikitext as a string.

    Raises:
        RuntimeError: If page content is missing or cannot be parsed.
    """
    payload = api_client.request(
        {
            "action": "query",
            "format": "json",
            "formatversion": 2,
            "prop": "revisions",
            "rvprop": "content",
            "rvslots": "main",
            "titles": title,
        }
    )

    pages = payload.get("query", {}).get("pages", [])
    if not isinstance(pages, list) or not pages:
        raise RuntimeError(f"MediaWiki page '{title}' not found")

    page = pages[0]
    if not isinstance(page, dict) or page.get("missing"):
        raise RuntimeError(f"MediaWiki page '{title}' not found")

    revisions = page.get("revisions", [])
    if not isinstance(revisions, list) or not revisions:
        raise RuntimeError(f"No revision content found for page '{title}'")

    revision = revisions[0]
    if not isinstance(revision, dict):
        raise RuntimeError(f"Invalid revision payload for page '{title}'")

    slots = revision.get("slots", {})
    main_slot = slots.get("main") if isinstance(slots, dict) else None
    if isinstance(main_slot, dict):
        content = main_slot.get("content")
        if isinstance(content, str):
            return content

    # Backward compatibility for installations using legacy '*' content key.
    content = revision.get("*")
    if isinstance(content, str):
        return content

    raise RuntimeError(f"No wikitext content found for page '{title}'")

extract_sparql_blocks()

Extract SPARQL blocks from wikitext in source order.

Source code in gkc/mash/core.py 
226
227
228
229
230
231
232
233
def extract_sparql_blocks(wikitext: str) -> list[str]:
    """Extract SPARQL blocks from wikitext in source order."""
    blocks: list[str] = []
    for match in _SPARQL_BLOCK_PATTERN.findall(wikitext):
        snippet = match.strip()
        if snippet:
            blocks.append(snippet)
    return blocks

extract_first_sparql_block()

Return the first SPARQL block from wikitext.

Raises:

Type Description
RuntimeError

If no <sparql>...</sparql> block exists.
Source code in gkc/mash/core.py 
236
237
238
239
240
241
242
243
244
245
def extract_first_sparql_block(wikitext: str) -> str:
    """Return the first SPARQL block from wikitext.

    Raises:
        RuntimeError: If no ``<sparql>...</sparql>`` block exists.
    """
    blocks = extract_sparql_blocks(wikitext)
    if not blocks:
        raise RuntimeError("No <sparql> block found in page content")
    return blocks[0]

DataTemplate

Bases: Protocol

Abstract interface for all data templates in the mash module.

All template types (Wikidata, CSV, JSON, etc.) should implement this protocol to ensure consistent behavior across different data sources.

This protocol defines the minimum interface that templates must provide: - summary(): Return a dict with basic metadata about the template - to_dict(): Serialize the template to a dictionary

Future template implementations should follow this pattern to ensure compatibility with formatters and other downstream components.

Plain meaning: The blueprint that all data templates must follow.

Source code in gkc/mash/core.py 
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
class DataTemplate(Protocol):
    """Abstract interface for all data templates in the mash module.

    All template types (Wikidata, CSV, JSON, etc.) should implement this
    protocol to ensure consistent behavior across different data sources.

    This protocol defines the minimum interface that templates must provide:
    - summary(): Return a dict with basic metadata about the template
    - to_dict(): Serialize the template to a dictionary

    Future template implementations should follow this pattern to ensure
    compatibility with formatters and other downstream components.

    Plain meaning: The blueprint that all data templates must follow.
    """

    def summary(self) -> dict[str, Any]:
        """Return a summary of the template for display.

        Plain meaning: Get a quick overview without full details.
        """
        ...

    def to_dict(self) -> dict[str, Any]:
        """Serialize to a dictionary.

        Plain meaning: Return the original entity JSON for round-trip safety.
        """
        ...

summary()

Return a summary of the template for display.

Plain meaning: Get a quick overview without full details.

Source code in gkc/mash/core.py 
562
563
564
565
566
567
def summary(self) -> dict[str, Any]:
    """Return a summary of the template for display.

    Plain meaning: Get a quick overview without full details.
    """
    ...

to_dict()

Serialize to a dictionary.

Plain meaning: Return the original entity JSON for round-trip safety.

Source code in gkc/mash/core.py 
569
570
571
572
573
574
def to_dict(self) -> dict[str, Any]:
    """Serialize to a dictionary.

    Plain meaning: Return the original entity JSON for round-trip safety.
    """
    ...

MashSourceAdapter

Bases: Protocol

Contract for mash source adapters.

A source adapter handles loading one or more source references and returning templates that satisfy the DataTemplate protocol.

Source code in gkc/mash/protocols.py 
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
@runtime_checkable
class MashSourceAdapter(Protocol):
    """Contract for mash source adapters.

    A source adapter handles loading one or more source references and returning
    templates that satisfy the ``DataTemplate`` protocol.
    """

    source_name: str

    def can_load(self, source_ref: str) -> bool:
        """Return True when this adapter can load the provided source reference."""

    def load(self, source_ref: str) -> DataTemplate:
        """Load one source reference into a template."""

    def load_many(self, source_refs: list[str]) -> dict[str, DataTemplate]:
        """Load multiple source references into templates keyed by source ref."""

can_load(source_ref)

Return True when this adapter can load the provided source reference.

Source code in gkc/mash/protocols.py 
24
25
def can_load(self, source_ref: str) -> bool:
    """Return True when this adapter can load the provided source reference."""

load(source_ref)

Load one source reference into a template.

Source code in gkc/mash/protocols.py 
27
28
def load(self, source_ref: str) -> DataTemplate:
    """Load one source reference into a template."""

load_many(source_refs)

Load multiple source references into templates keyed by source ref.

Source code in gkc/mash/protocols.py 
30
31
def load_many(self, source_refs: list[str]) -> dict[str, DataTemplate]:
    """Load multiple source references into templates keyed by source ref."""

WikibaseMashSourceAdapter

Bases: MashSourceAdapter

Mash source adapter for Wikibase entity references.

Supports item/property/schema IDs and delegates loading to WikibaseLoader.

Source code in gkc/mash/core.py 
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
class WikibaseMashSourceAdapter(MashSourceAdapter):
    """Mash source adapter for Wikibase entity references.

    Supports item/property/schema IDs and delegates loading to ``WikibaseLoader``.
    """

    source_name = "wikibase"

    def __init__(self, loader: Optional[WikibaseLoader] = None):
        self.loader = loader or WikibaseLoader()

    @staticmethod
    def _is_wikibase_entity_ref(source_ref: str) -> bool:
        if not source_ref or len(source_ref) < 2:
            return False

        prefix = source_ref[0]
        suffix = source_ref[1:]
        return prefix in {"Q", "P", "E"} and suffix.isdigit()

    def can_load(self, source_ref: str) -> bool:
        """Return True for Wikibase entity IDs (Q/P/E)."""
        return self._is_wikibase_entity_ref(source_ref)

    def load(self, source_ref: str) -> DataTemplate:
        """Load a Wikibase entity ID into the appropriate template type."""
        if not self.can_load(source_ref):
            raise ValueError(
                f"WikibaseMashSourceAdapter cannot load source reference: {source_ref}"
            )

        prefix = source_ref[0]
        if prefix == "Q":
            return self.loader.load_item(source_ref)
        if prefix == "P":
            return self.loader.load_property(source_ref)
        if prefix == "E":
            return self.loader.load_entity_schema(source_ref)

        raise ValueError(f"Unsupported Wikibase entity reference: {source_ref}")

    def load_many(self, source_refs: list[str]) -> dict[str, DataTemplate]:
        """Load multiple Wikibase references into templates keyed by source ref."""
        if not source_refs:
            return {}

        invalid_refs = [
            source_ref for source_ref in source_refs if not self.can_load(source_ref)
        ]
        if invalid_refs:
            raise ValueError(
                f"Invalid Wikibase source references: {', '.join(invalid_refs)}"
            )

        loaded: dict[str, DataTemplate] = {}

        qids = [source_ref for source_ref in source_refs if source_ref.startswith("Q")]
        if qids:
            loaded.update(self.loader.load_items(qids))

        for source_ref in source_refs:
            if source_ref in loaded:
                continue
            loaded[source_ref] = self.load(source_ref)

        return loaded

can_load(source_ref)

Return True for Wikibase entity IDs (Q/P/E).

Source code in gkc/mash/core.py 
1959
1960
1961
def can_load(self, source_ref: str) -> bool:
    """Return True for Wikibase entity IDs (Q/P/E)."""
    return self._is_wikibase_entity_ref(source_ref)

load(source_ref)

Load a Wikibase entity ID into the appropriate template type.

Source code in gkc/mash/core.py 
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
def load(self, source_ref: str) -> DataTemplate:
    """Load a Wikibase entity ID into the appropriate template type."""
    if not self.can_load(source_ref):
        raise ValueError(
            f"WikibaseMashSourceAdapter cannot load source reference: {source_ref}"
        )

    prefix = source_ref[0]
    if prefix == "Q":
        return self.loader.load_item(source_ref)
    if prefix == "P":
        return self.loader.load_property(source_ref)
    if prefix == "E":
        return self.loader.load_entity_schema(source_ref)

    raise ValueError(f"Unsupported Wikibase entity reference: {source_ref}")

load_many(source_refs)

Load multiple Wikibase references into templates keyed by source ref.

Source code in gkc/mash/core.py 
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
def load_many(self, source_refs: list[str]) -> dict[str, DataTemplate]:
    """Load multiple Wikibase references into templates keyed by source ref."""
    if not source_refs:
        return {}

    invalid_refs = [
        source_ref for source_ref in source_refs if not self.can_load(source_ref)
    ]
    if invalid_refs:
        raise ValueError(
            f"Invalid Wikibase source references: {', '.join(invalid_refs)}"
        )

    loaded: dict[str, DataTemplate] = {}

    qids = [source_ref for source_ref in source_refs if source_ref.startswith("Q")]
    if qids:
        loaded.update(self.loader.load_items(qids))

    for source_ref in source_refs:
        if source_ref in loaded:
            continue
        loaded[source_ref] = self.load(source_ref)

    return loaded

WikipediaMashSourceAdapter

Bases: MashSourceAdapter

Mash source adapter for Wikipedia template references.

Source code in gkc/mash/core.py 
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
class WikipediaMashSourceAdapter(MashSourceAdapter):
    """Mash source adapter for Wikipedia template references."""

    source_name = "wikipedia-template"

    def __init__(self, loader: Optional[WikipediaLoader] = None):
        self.loader = loader or WikipediaLoader()

    @staticmethod
    def _normalize_template_name(source_ref: str) -> str:
        name = source_ref.strip()
        if name.startswith("Template:"):
            return name.removeprefix("Template:")
        return name

    def can_load(self, source_ref: str) -> bool:
        """Return True for non-empty template references."""
        return bool(source_ref and source_ref.strip())

    def load(self, source_ref: str) -> WikipediaTemplate:
        """Load a Wikipedia template by name."""
        if not self.can_load(source_ref):
            raise ValueError(
                "WikipediaMashSourceAdapter requires a non-empty template reference"
            )

        template_name = self._normalize_template_name(source_ref)
        return self.loader.load_template(template_name)

    def load_many(self, source_refs: list[str]) -> dict[str, WikipediaTemplate]:
        """Load multiple Wikipedia templates keyed by the original source ref."""
        loaded: dict[str, WikipediaTemplate] = {}
        for source_ref in source_refs:
            loaded[source_ref] = self.load(source_ref)
        return loaded

can_load(source_ref)

Return True for non-empty template references.

Source code in gkc/mash/core.py 
2022
2023
2024
def can_load(self, source_ref: str) -> bool:
    """Return True for non-empty template references."""
    return bool(source_ref and source_ref.strip())

load(source_ref)

Load a Wikipedia template by name.

Source code in gkc/mash/core.py 
2026
2027
2028
2029
2030
2031
2032
2033
2034
def load(self, source_ref: str) -> WikipediaTemplate:
    """Load a Wikipedia template by name."""
    if not self.can_load(source_ref):
        raise ValueError(
            "WikipediaMashSourceAdapter requires a non-empty template reference"
        )

    template_name = self._normalize_template_name(source_ref)
    return self.loader.load_template(template_name)

load_many(source_refs)

Load multiple Wikipedia templates keyed by the original source ref.

Source code in gkc/mash/core.py 
2036
2037
2038
2039
2040
2041
def load_many(self, source_refs: list[str]) -> dict[str, WikipediaTemplate]:
    """Load multiple Wikipedia templates keyed by the original source ref."""
    loaded: dict[str, WikipediaTemplate] = {}
    for source_ref in source_refs:
        loaded[source_ref] = self.load(source_ref)
    return loaded

fetch_property_labels()

Fetch human-readable labels for Wikidata properties using SPARQL.

Parameters:

Name Type Description Default
property_ids list[str]

List of property IDs (e.g., ['P31', 'P21']).

 required
language Optional[str]

Language code for labels (defaults to package configuration).

 None

Returns:

Type Description
dict[str, str]

Dict mapping property IDs to their labels (e.g., {'P31': 'instance of'}).

Plain meaning: Look up property names efficiently to make QS output more readable.

Source code in gkc/mash/core.py 
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
def fetch_property_labels(
    property_ids: list[str], language: Optional[str] = None
) -> dict[str, str]:
    """Fetch human-readable labels for Wikidata properties using SPARQL.

    Args:
        property_ids: List of property IDs (e.g., ['P31', 'P21']).
        language: Language code for labels (defaults to package configuration).

    Returns:
        Dict mapping property IDs to their labels (e.g., {'P31': 'instance of'}).

    Plain meaning: Look up property names efficiently to make QS output more readable.
    """
    if not property_ids:
        return {}
    if language is None:
        import gkc

        languages = gkc.get_languages()
        if languages == "all":
            language = "en"
        elif isinstance(languages, str):
            language = languages
        else:
            language = languages[0] if languages else "en"
    return fetch_entity_labels(property_ids, languages=[language])

strip_entity_identifiers()

Return a copy of entity data with identifiers stripped for new-item use.

Removes fields that prevent using the JSON as a new item template: - Item-level: id, pageid, lastrevid, modified, ns, title - Statement-level: id (statement GUID) - Snak-level: hash (in mainsnak, qualifiers, and references)

Plain meaning: Remove IDs that prevent using the JSON as a new item template.

Source code in gkc/mash/core.py 
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
def strip_entity_identifiers(entity_data: dict[str, Any]) -> dict[str, Any]:
    """Return a copy of entity data with identifiers stripped for new-item use.

    Removes fields that prevent using the JSON as a new item template:
    - Item-level: id, pageid, lastrevid, modified, ns, title
    - Statement-level: id (statement GUID)
    - Snak-level: hash (in mainsnak, qualifiers, and references)

    Plain meaning: Remove IDs that prevent using the JSON as a new item template.
    """

    cleaned = copy.deepcopy(entity_data)

    # Remove item-level identifiers and metadata
    cleaned.pop("id", None)
    cleaned.pop("pageid", None)
    cleaned.pop("lastrevid", None)
    cleaned.pop("modified", None)
    cleaned.pop("ns", None)
    cleaned.pop("title", None)

    # Remove statement-level identifiers and hashes
    claims = cleaned.get("claims")
    if isinstance(claims, dict):
        for statements in claims.values():
            if not isinstance(statements, list):
                continue
            for statement in statements:
                if isinstance(statement, dict):
                    statement.pop("id", None)

                    # Remove hash from mainsnak
                    mainsnak = statement.get("mainsnak")
                    if isinstance(mainsnak, dict):
                        mainsnak.pop("hash", None)

                    # Remove hash from qualifiers
                    qualifiers = statement.get("qualifiers")
                    if isinstance(qualifiers, dict):
                        for qualifier_snaks in qualifiers.values():
                            if isinstance(qualifier_snaks, list):
                                for snak in qualifier_snaks:
                                    if isinstance(snak, dict):
                                        snak.pop("hash", None)

                    # Remove hash from references
                    references = statement.get("references")
                    if isinstance(references, list):
                        for reference in references:
                            if isinstance(reference, dict):
                                reference.pop("hash", None)
                                ref_snaks = reference.get("snaks")
                                if isinstance(ref_snaks, dict):
                                    for ref_snak_list in ref_snaks.values():
                                        if isinstance(ref_snak_list, list):
                                            for snak in ref_snak_list:
                                                if isinstance(snak, dict):
                                                    snak.pop("hash", None)

    return cleaned

ClaimSummary

Simplified representation of a Wikidata claim for display and export.

Plain meaning: A simple view of a claim without requiring RDF knowledge.

Source code in gkc/mash/core.py 
668
669
670
671
672
673
674
675
676
677
678
679
680
@dataclass
class ClaimSummary:
    """Simplified representation of a Wikidata claim for display and export.

    Plain meaning: A simple view of a claim without requiring RDF knowledge.
    """

    property_id: str
    value: str
    qualifiers: list[dict] = field(default_factory=list)
    references: list[dict] = field(default_factory=list)
    rank: str = "normal"
    value_metadata: Optional[dict[str, Any]] = None

WikibaseItemTemplate

An extracted Wikidata item ready for filtering and export.

This is the Wikidata-specific implementation of the DataTemplate protocol.

Plain meaning: A loaded Wikidata item template ready for modification.

Source code in gkc/mash/core.py 
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
@dataclass
class WikibaseItemTemplate:
    """An extracted Wikidata item ready for filtering and export.

    This is the Wikidata-specific implementation of the DataTemplate protocol.

    Plain meaning: A loaded Wikidata item template ready for modification.
    """

    qid: str
    labels: dict[str, str]
    descriptions: dict[str, str]
    aliases: dict[str, list[str]]
    claims: list[ClaimSummary]
    entity_data: dict[str, Any]

    def filter_qualifiers(self) -> None:
        """Remove all qualifiers from claims in-place.

        Plain meaning: Strip qualifier detail from claims.
        """

        for claim in self.claims:
            claim.qualifiers = []

        claims = self.entity_data.get("claims")
        if isinstance(claims, dict):
            for statements in claims.values():
                if not isinstance(statements, list):
                    continue
                for statement in statements:
                    if isinstance(statement, dict):
                        statement.pop("qualifiers", None)
                        statement.pop("qualifiers-order", None)

    def filter_references(self) -> None:
        """Remove all references from claims in-place.

        Plain meaning: Strip reference detail from claims.
        """

        for claim in self.claims:
            claim.references = []

        claims = self.entity_data.get("claims")
        if isinstance(claims, dict):
            for statements in claims.values():
                if not isinstance(statements, list):
                    continue
                for statement in statements:
                    if isinstance(statement, dict):
                        statement.pop("references", None)

    def summary(self) -> dict[str, Any]:
        """Return a summary of the template for display.

        Plain meaning: Get a quick overview without full details.
        """

        return {
            "qid": self.qid,
            "labels": self.labels,
            "descriptions": self.descriptions,
            "total_statements": len(self.claims),
            "aliases": self.aliases,
        }

    def to_dict(self) -> dict[str, Any]:
        """Serialize to a dictionary.

        Plain meaning: Convert to a form suitable for JSON export.
        """

        return copy.deepcopy(self.entity_data)

    def to_simple_dict(self) -> dict[str, Any]:
        """Serialize to a simplified dictionary.

        Plain meaning: Convert to a compact summary structure.
        """

        return {
            "qid": self.qid,
            "labels": self.labels,
            "descriptions": self.descriptions,
            "aliases": self.aliases,
            "claims": [
                {
                    "property_id": c.property_id,
                    "value": c.value,
                    "qualifiers": c.qualifiers,
                    "references": c.references,
                    "rank": c.rank,
                }
                for c in self.claims
            ],
        }

    def to_shell(self) -> dict[str, Any]:
        """Strip identifiers and metadata to create a shell for new item creation.

        Returns entity data with all system IDs, metadata, and hashes removed,
        suitable for use as a template for creating new items.

        Returns:
            Dict with identifiers stripped, ready for new item creation.

        Plain meaning: Prepare this template as a clean shell for a new item.
        """
        return strip_entity_identifiers(self.entity_data)

    def to_qsv1(
        self, for_new_item: bool = False, entity_labels: Optional[dict[str, str]] = None
    ) -> str:
        """Convert to QuickStatements V1 format.

        Args:
            for_new_item: If True, use CREATE/LAST syntax for new items.
                         If False, use the item's QID for updates.
            entity_labels: Optional dict mapping entity IDs to labels for comments.

        Returns:
            QuickStatements V1 formatted string.

        Plain meaning: Export as QuickStatements commands for bulk operations.
        """
        from gkc.mash_formatters import QSV1Formatter

        formatter = QSV1Formatter(entity_labels=entity_labels or {})
        return formatter.format(self, for_new_item=for_new_item)

    def to_gkc_entity_profile(self) -> dict[str, Any]:
        """Convert to GKC Entity Profile format.

        Returns:
            Dict representing the GKC Entity Profile.

        Raises:
            NotImplementedError: This transformation is not yet implemented for items.

        Plain meaning: Transform into a GKC Entity Profile (not yet implemented).
        """
        raise NotImplementedError(
            "Item to GKC Entity Profile transformation is not yet implemented. "
            "This will be added in a future version."
        )

filter_qualifiers()

Remove all qualifiers from claims in-place.

Plain meaning: Strip qualifier detail from claims.

Source code in gkc/mash/core.py 
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
def filter_qualifiers(self) -> None:
    """Remove all qualifiers from claims in-place.

    Plain meaning: Strip qualifier detail from claims.
    """

    for claim in self.claims:
        claim.qualifiers = []

    claims = self.entity_data.get("claims")
    if isinstance(claims, dict):
        for statements in claims.values():
            if not isinstance(statements, list):
                continue
            for statement in statements:
                if isinstance(statement, dict):
                    statement.pop("qualifiers", None)
                    statement.pop("qualifiers-order", None)

filter_references()

Remove all references from claims in-place.

Plain meaning: Strip reference detail from claims.

Source code in gkc/mash/core.py 
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
def filter_references(self) -> None:
    """Remove all references from claims in-place.

    Plain meaning: Strip reference detail from claims.
    """

    for claim in self.claims:
        claim.references = []

    claims = self.entity_data.get("claims")
    if isinstance(claims, dict):
        for statements in claims.values():
            if not isinstance(statements, list):
                continue
            for statement in statements:
                if isinstance(statement, dict):
                    statement.pop("references", None)

summary()

Return a summary of the template for display.

Plain meaning: Get a quick overview without full details.

Source code in gkc/mash/core.py 
736
737
738
739
740
741
742
743
744
745
746
747
748
def summary(self) -> dict[str, Any]:
    """Return a summary of the template for display.

    Plain meaning: Get a quick overview without full details.
    """

    return {
        "qid": self.qid,
        "labels": self.labels,
        "descriptions": self.descriptions,
        "total_statements": len(self.claims),
        "aliases": self.aliases,
    }

to_dict()

Serialize to a dictionary.

Plain meaning: Convert to a form suitable for JSON export.

Source code in gkc/mash/core.py 
750
751
752
753
754
755
756
def to_dict(self) -> dict[str, Any]:
    """Serialize to a dictionary.

    Plain meaning: Convert to a form suitable for JSON export.
    """

    return copy.deepcopy(self.entity_data)

to_gkc_entity_profile()

Convert to GKC Entity Profile format.

Returns:

Type Description
dict[str, Any]

Dict representing the GKC Entity Profile.

Raises:

Type Description
NotImplementedError

This transformation is not yet implemented for items.

Plain meaning: Transform into a GKC Entity Profile (not yet implemented).

Source code in gkc/mash/core.py 
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
def to_gkc_entity_profile(self) -> dict[str, Any]:
    """Convert to GKC Entity Profile format.

    Returns:
        Dict representing the GKC Entity Profile.

    Raises:
        NotImplementedError: This transformation is not yet implemented for items.

    Plain meaning: Transform into a GKC Entity Profile (not yet implemented).
    """
    raise NotImplementedError(
        "Item to GKC Entity Profile transformation is not yet implemented. "
        "This will be added in a future version."
    )

to_qsv1(for_new_item=False, entity_labels=None)

Convert to QuickStatements V1 format.

Parameters:

Name Type Description Default
for_new_item bool

If True, use CREATE/LAST syntax for new items. If False, use the item's QID for updates.

 False
entity_labels Optional[dict[str, str]]

Optional dict mapping entity IDs to labels for comments.

 None

Returns:

Type Description
str

QuickStatements V1 formatted string.

Plain meaning: Export as QuickStatements commands for bulk operations.

Source code in gkc/mash/core.py 
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
def to_qsv1(
    self, for_new_item: bool = False, entity_labels: Optional[dict[str, str]] = None
) -> str:
    """Convert to QuickStatements V1 format.

    Args:
        for_new_item: If True, use CREATE/LAST syntax for new items.
                     If False, use the item's QID for updates.
        entity_labels: Optional dict mapping entity IDs to labels for comments.

    Returns:
        QuickStatements V1 formatted string.

    Plain meaning: Export as QuickStatements commands for bulk operations.
    """
    from gkc.mash_formatters import QSV1Formatter

    formatter = QSV1Formatter(entity_labels=entity_labels or {})
    return formatter.format(self, for_new_item=for_new_item)

to_shell()

Strip identifiers and metadata to create a shell for new item creation.

Returns entity data with all system IDs, metadata, and hashes removed, suitable for use as a template for creating new items.

Returns:

Type Description
dict[str, Any]

Dict with identifiers stripped, ready for new item creation.

Plain meaning: Prepare this template as a clean shell for a new item.

Source code in gkc/mash/core.py 
781
782
783
784
785
786
787
788
789
790
791
792
def to_shell(self) -> dict[str, Any]:
    """Strip identifiers and metadata to create a shell for new item creation.

    Returns entity data with all system IDs, metadata, and hashes removed,
    suitable for use as a template for creating new items.

    Returns:
        Dict with identifiers stripped, ready for new item creation.

    Plain meaning: Prepare this template as a clean shell for a new item.
    """
    return strip_entity_identifiers(self.entity_data)

to_simple_dict()

Serialize to a simplified dictionary.

Plain meaning: Convert to a compact summary structure.

Source code in gkc/mash/core.py 
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
def to_simple_dict(self) -> dict[str, Any]:
    """Serialize to a simplified dictionary.

    Plain meaning: Convert to a compact summary structure.
    """

    return {
        "qid": self.qid,
        "labels": self.labels,
        "descriptions": self.descriptions,
        "aliases": self.aliases,
        "claims": [
            {
                "property_id": c.property_id,
                "value": c.value,
                "qualifiers": c.qualifiers,
                "references": c.references,
                "rank": c.rank,
            }
            for c in self.claims
        ],
    }

WikibasePropertyTemplate

An extracted Wikidata property ready for filtering and export.

This is the property-specific implementation of the DataTemplate protocol.

Plain meaning: A loaded Wikidata property template ready for modification.

Source code in gkc/mash/core.py 
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
@dataclass
class WikibasePropertyTemplate:
    """An extracted Wikidata property ready for filtering and export.

    This is the property-specific implementation of the DataTemplate protocol.

    Plain meaning: A loaded Wikidata property template ready for modification.
    """

    pid: str
    labels: dict[str, str]
    descriptions: dict[str, str]
    aliases: dict[str, list[str]]
    datatype: Optional[str]
    formatter_url: Optional[str]
    entity_data: dict[str, Any]

    def summary(self) -> dict[str, Any]:
        """Return a summary of the template for display.

        Plain meaning: Get a quick overview without full details.
        """
        return {
            "pid": self.pid,
            "labels": self.labels,
            "descriptions": self.descriptions,
            "datatype": self.datatype,
            "formatter_url": self.formatter_url,
            "aliases": self.aliases,
        }

    def to_dict(self) -> dict[str, Any]:
        """Serialize to a dictionary.

        Plain meaning: Convert to a form suitable for JSON export.
        """
        return copy.deepcopy(self.entity_data)

    def to_shell(self) -> dict[str, Any]:
        """Strip identifiers and metadata to create a shell for new property creation.

        Returns entity data with all system IDs, metadata, and hashes removed,
        suitable for use as a template for creating new properties.

        Returns:
            Dict with identifiers stripped, ready for new property creation.

        Plain meaning: Prepare this template as a clean shell for a new property.
        """
        return strip_entity_identifiers(self.entity_data)

    def to_gkc_entity_profile(self) -> dict[str, Any]:
        """Convert to GKC Entity Profile format.

        Returns:
            Dict representing the GKC Entity Profile.

        Raises:
            NotImplementedError: This transformation is not yet implemented
                for properties.

        Plain meaning: Transform into a GKC Entity Profile
            (not yet implemented).
        """
        raise NotImplementedError(
            "Property to GKC Entity Profile transformation is not yet implemented. "
            "This will be added in a future version."
        )

summary()

Return a summary of the template for display.

Plain meaning: Get a quick overview without full details.

Source code in gkc/mash/core.py 
848
849
850
851
852
853
854
855
856
857
858
859
860
def summary(self) -> dict[str, Any]:
    """Return a summary of the template for display.

    Plain meaning: Get a quick overview without full details.
    """
    return {
        "pid": self.pid,
        "labels": self.labels,
        "descriptions": self.descriptions,
        "datatype": self.datatype,
        "formatter_url": self.formatter_url,
        "aliases": self.aliases,
    }

to_dict()

Serialize to a dictionary.

Plain meaning: Convert to a form suitable for JSON export.

Source code in gkc/mash/core.py 
862
863
864
865
866
867
def to_dict(self) -> dict[str, Any]:
    """Serialize to a dictionary.

    Plain meaning: Convert to a form suitable for JSON export.
    """
    return copy.deepcopy(self.entity_data)

to_gkc_entity_profile()

Convert to GKC Entity Profile format.

Returns:

Type Description
dict[str, Any]

Dict representing the GKC Entity Profile.

Raises:

Type Description
NotImplementedError

This transformation is not yet implemented for properties.
Transform into a GKC Entity Profile

(not yet implemented).

Source code in gkc/mash/core.py 
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
def to_gkc_entity_profile(self) -> dict[str, Any]:
    """Convert to GKC Entity Profile format.

    Returns:
        Dict representing the GKC Entity Profile.

    Raises:
        NotImplementedError: This transformation is not yet implemented
            for properties.

    Plain meaning: Transform into a GKC Entity Profile
        (not yet implemented).
    """
    raise NotImplementedError(
        "Property to GKC Entity Profile transformation is not yet implemented. "
        "This will be added in a future version."
    )

to_shell()

Strip identifiers and metadata to create a shell for new property creation.

Returns entity data with all system IDs, metadata, and hashes removed, suitable for use as a template for creating new properties.

Returns:

Type Description
dict[str, Any]

Dict with identifiers stripped, ready for new property creation.

Plain meaning: Prepare this template as a clean shell for a new property.

Source code in gkc/mash/core.py 
869
870
871
872
873
874
875
876
877
878
879
880
def to_shell(self) -> dict[str, Any]:
    """Strip identifiers and metadata to create a shell for new property creation.

    Returns entity data with all system IDs, metadata, and hashes removed,
    suitable for use as a template for creating new properties.

    Returns:
        Dict with identifiers stripped, ready for new property creation.

    Plain meaning: Prepare this template as a clean shell for a new property.
    """
    return strip_entity_identifiers(self.entity_data)

WikibaseEntitySchemaTemplate

An extracted Wikidata EntitySchema ready for filtering and export.

This is the EntitySchema-specific implementation of the DataTemplate protocol.

Plain meaning: A loaded Wikidata EntitySchema template ready for modification.

Source code in gkc/mash/core.py 
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
@dataclass
class WikibaseEntitySchemaTemplate:
    """An extracted Wikidata EntitySchema ready for filtering and export.

    This is the EntitySchema-specific implementation of the DataTemplate protocol.

    Plain meaning: A loaded Wikidata EntitySchema template ready for modification.
    """

    eid: str
    labels: dict[str, str]
    descriptions: dict[str, str]
    schema_text: str
    entity_data: dict[str, Any]

    def summary(self) -> dict[str, Any]:
        """Return a summary of the template for display.

        Plain meaning: Get a quick overview without full details.
        """
        return {
            "eid": self.eid,
            "labels": self.labels,
            "descriptions": self.descriptions,
            "schema_text_length": len(self.schema_text),
        }

    def to_dict(self) -> dict[str, Any]:
        """Serialize to a dictionary.

        Plain meaning: Convert to a form suitable for JSON export.
        """
        return copy.deepcopy(self.entity_data)

    def to_shell(self) -> dict[str, Any]:
        """Strip identifiers and metadata for new EntitySchema creation.

        Returns entity data with all system IDs and metadata removed,
        suitable for use as a template for creating new EntitySchemas.

        Returns:
            Dict with identifiers stripped, ready for new EntitySchema creation.

        Plain meaning: Prepare this template as a clean shell for a new EntitySchema.
        """
        return strip_entity_identifiers(self.entity_data)

    def to_gkc_entity_profile(self) -> dict[str, Any]:
        """Convert to GKC Entity Profile format.

        Returns:
            Dict representing the GKC Entity Profile.

        Raises:
            NotImplementedError: EntitySchema to Entity Profile transformation
                is not yet supported. This functionality will be restored
                when the new Entity Profile architecture is finalized.

        Plain meaning: Transform into a GKC Entity Profile (not yet supported).
        """
        raise NotImplementedError(
            "EntitySchema to GKC Entity Profile transformation is not yet supported. "
            "This functionality will be restored when the new Entity Profile "
            "architecture is finalized."
        )

summary()

Return a summary of the template for display.

Plain meaning: Get a quick overview without full details.

Source code in gkc/mash/core.py 
916
917
918
919
920
921
922
923
924
925
926
def summary(self) -> dict[str, Any]:
    """Return a summary of the template for display.

    Plain meaning: Get a quick overview without full details.
    """
    return {
        "eid": self.eid,
        "labels": self.labels,
        "descriptions": self.descriptions,
        "schema_text_length": len(self.schema_text),
    }

to_dict()

Serialize to a dictionary.

Plain meaning: Convert to a form suitable for JSON export.

Source code in gkc/mash/core.py 
928
929
930
931
932
933
def to_dict(self) -> dict[str, Any]:
    """Serialize to a dictionary.

    Plain meaning: Convert to a form suitable for JSON export.
    """
    return copy.deepcopy(self.entity_data)

to_gkc_entity_profile()

Convert to GKC Entity Profile format.

Returns:

Type Description
dict[str, Any]

Dict representing the GKC Entity Profile.

Raises:

Type Description
NotImplementedError

EntitySchema to Entity Profile transformation is not yet supported. This functionality will be restored when the new Entity Profile architecture is finalized.

Plain meaning: Transform into a GKC Entity Profile (not yet supported).

Source code in gkc/mash/core.py 
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
def to_gkc_entity_profile(self) -> dict[str, Any]:
    """Convert to GKC Entity Profile format.

    Returns:
        Dict representing the GKC Entity Profile.

    Raises:
        NotImplementedError: EntitySchema to Entity Profile transformation
            is not yet supported. This functionality will be restored
            when the new Entity Profile architecture is finalized.

    Plain meaning: Transform into a GKC Entity Profile (not yet supported).
    """
    raise NotImplementedError(
        "EntitySchema to GKC Entity Profile transformation is not yet supported. "
        "This functionality will be restored when the new Entity Profile "
        "architecture is finalized."
    )

to_shell()

Strip identifiers and metadata for new EntitySchema creation.

Returns entity data with all system IDs and metadata removed, suitable for use as a template for creating new EntitySchemas.

Returns:

Type Description
dict[str, Any]

Dict with identifiers stripped, ready for new EntitySchema creation.

Plain meaning: Prepare this template as a clean shell for a new EntitySchema.

Source code in gkc/mash/core.py 
935
936
937
938
939
940
941
942
943
944
945
946
def to_shell(self) -> dict[str, Any]:
    """Strip identifiers and metadata for new EntitySchema creation.

    Returns entity data with all system IDs and metadata removed,
    suitable for use as a template for creating new EntitySchemas.

    Returns:
        Dict with identifiers stripped, ready for new EntitySchema creation.

    Plain meaning: Prepare this template as a clean shell for a new EntitySchema.
    """
    return strip_entity_identifiers(self.entity_data)

WikibaseLoader

Load a Wikidata item as a template for bulk modification.

This is the Wikidata-specific implementation of a data loader. Future loaders for CSV, JSON APIs, etc. should follow a similar pattern.

Plain meaning: Fetch and parse a Wikidata item into a usable template.

Source code in gkc/mash/core.py 
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
class WikibaseLoader:
    """Load a Wikidata item as a template for bulk modification.

    This is the Wikidata-specific implementation of a data loader.
    Future loaders for CSV, JSON APIs, etc. should follow a similar pattern.

    Plain meaning: Fetch and parse a Wikidata item into a usable template.
    """

    def __init__(
        self,
        user_agent: Optional[str] = None,
        api_url: str = "https://www.wikidata.org/w/api.php",
        api_client: Optional[WikibaseApiClient] = None,
        auth: Optional[Any] = None,
    ):
        """Initialize the loader.

        Args:
            user_agent: Custom user agent for Wikidata requests.
                       If not provided, a default GKC user agent is used.
            api_client: Optional pre-configured WikibaseApiClient.
            auth: Optional WikiverseAuth instance. When provided and the
                authenticated user has the ``apihighlimits`` right, batch
                requests are made in chunks of 500 instead of 50.
        """

        if user_agent is None:
            user_agent = DEFAULT_USER_AGENT

        self.user_agent = user_agent
        self.api_url = api_url
        self.api_client = api_client or WikibaseApiClient(
            api_url=api_url,
            user_agent=user_agent,
        )
        has_high_limits = (
            auth is not None
            and callable(getattr(auth, "has_api_high_limits", None))
            and auth.has_api_high_limits()
        )
        self.entity_batch_size: int = 500 if has_high_limits else 50

    def load_item(self, qid: str) -> WikibaseItemTemplate:
        """Load a Wikidata item and return it as a template.

        Args:
            qid: The Wikidata item ID (e.g., 'Q42').

        Returns:
            WikibaseItemTemplate with the item's structure.

        Raises:
            RuntimeError: If the item cannot be fetched or parsed.

        Plain meaning: Retrieve the item and return it ready for use.

        Example:
            >>> loader = WikibaseLoader()
            >>> template = loader.load_item("Q42")
            >>> print(template.summary())
        """

        entity_data = self.load_entity_data(qid)

        # Convert to MashTemplate
        template = self._build_template(qid, entity_data)

        return template

    def load(self, qid: str) -> WikibaseItemTemplate:
        """Load a Wikidata item and return it as a template.

        .. deprecated:: 1.0
            Use :meth:`load_item` instead. This method is maintained for
            backwards compatibility and will be removed in a future version.

        Args:
            qid: The Wikidata item ID (e.g., 'Q42').

        Returns:
            WikibaseItemTemplate with the item's structure.

        Plain meaning: Retrieve the item and return it ready for use.
        """
        return self.load_item(qid)

    def load_entities_raw(self, entity_ids: list[str]) -> dict[str, dict[str, Any]]:
        """Load raw entity JSON in wbgetentities-sized batches.

        Uses ``self.entity_batch_size`` so authenticated sessions with
        ``apihighlimits`` can fetch 500 entities per request.
        """
        if not entity_ids:
            return {}

        result: dict[str, dict[str, Any]] = {}

        for i in range(0, len(entity_ids), self.entity_batch_size):
            batch = entity_ids[i : i + self.entity_batch_size]
            batch_results = self._fetch_entities_batch(batch)
            result.update(batch_results)

        return result

    def load_items(self, qids: list[str]) -> dict[str, WikibaseItemTemplate]:
        """Load multiple Wikidata items in batch and return them as templates.

        Uses the wbgetentities API to efficiently fetch multiple items in
        ``self.entity_batch_size`` chunks. Handles partial failures gracefully.

        Args:
            qids: List of Wikidata item IDs (e.g., ['Q42', 'Q5']).

        Returns:
            Dict mapping QIDs to WikidataTemplates. Only successfully loaded
            items are included in the result.

        Raises:
            RuntimeError: If the API request fails completely.

        Plain meaning: Load multiple items efficiently in batch.

        Example:
            >>> loader = WikibaseLoader()
            >>> templates = loader.load_items(["Q42", "Q5", "Q30"])
            >>> print(len(templates))
            3
        """
        if not qids:
            return {}

        result: dict[str, WikibaseItemTemplate] = {}
        batch_results = self.load_entities_raw(qids)

        # Build templates for each successfully fetched entity
        for qid, entity_data in batch_results.items():
            try:
                template = self._build_template(qid, entity_data)
                result[qid] = template
            except Exception:
                # Skip items that fail to parse
                continue

        return result

    def load_property(self, pid: str) -> WikibasePropertyTemplate:
        """Load a Wikidata property and return it as a template.

        Args:
            pid: The Wikidata property ID (e.g., 'P31').

        Returns:
            WikibasePropertyTemplate with the property's metadata.

        Raises:
            RuntimeError: If the property cannot be fetched or parsed.

        Plain meaning: Retrieve a property definition and return it ready for use.

        Example:
            >>> loader = WikibaseLoader()
            >>> prop = loader.load_property("P31")
            >>> print(prop.summary())
        """
        entity_data = self.load_entity_data(pid)
        return self._build_property_template(pid, entity_data)

    def load_entity_schema(self, eid: str) -> WikibaseEntitySchemaTemplate:
        """Load a Wikidata EntitySchema and return it as a template.

        Args:
            eid: The Wikidata EntitySchema ID (e.g., 'E502').

        Returns:
            WikibaseEntitySchemaTemplate with the schema content.

        Raises:
            RuntimeError: If the EntitySchema cannot be fetched or parsed.

        Plain meaning: Retrieve an EntitySchema and return it ready for use.

        Example:
            >>> loader = WikibaseLoader()
            >>> schema = loader.load_entity_schema("E502")
            >>> print(schema.summary())
        """
        entity_data = fetch_entity_schema_json(eid, user_agent=self.user_agent)
        return self._build_entity_schema_template(eid, entity_data)

    def _fetch_entities_batch(self, entity_ids: list[str]) -> dict[str, dict[str, Any]]:
        """Fetch multiple entities using wbgetentities API.

        Args:
            entity_ids: List of entity IDs (max 50).

        Returns:
            Dict mapping entity IDs to their entity data.

        Raises:
            RuntimeError: If the API request fails.

        Plain meaning: Fetch a batch of entities from Wikidata.
        """
        try:
            return self.api_client.get_entities(entity_ids)
        except RuntimeError as exc:
            raise RuntimeError(f"Failed to fetch entities batch: {exc}") from exc

    def load_entity_data(self, qid: str) -> dict[str, Any]:
        """Load raw Wikidata entity data.

        Plain meaning: Return the entity JSON as provided by Wikidata.
        """

        # Fetch the item via Special:EntityData endpoint which returns JSON
        # This is equivalent to wbgetentities but simpler for single-item fetches
        json_text = self._fetch_entity_json(qid)

        # Parse the JSON response from Wikidata
        return self._parse_wikidata_json(json_text, qid)

    def _fetch_entity_json(self, qid: str) -> str:
        """Fetch a single Wikidata entity as JSON.

        Args:
            qid: The Wikidata item ID (e.g., 'Q42').

        Returns:
            JSON string with entity data.

        Raises:
            RuntimeError: If the fetch fails or entity doesn't exist.

        Plain meaning: Download the item from Wikidata as JSON.
        """

        parsed = urlparse(self.api_url)
        if not parsed.scheme or not parsed.netloc:
            raise RuntimeError(f"Invalid API URL configured: {self.api_url}")

        url = f"{parsed.scheme}://{parsed.netloc}/wiki/Special:EntityData/{qid}.json"

        headers = {}
        if self.user_agent:
            headers["User-Agent"] = self.user_agent

        try:
            response = requests.get(url, headers=headers, timeout=30)

            # Handle 404 or 400 errors which indicate item doesn't exist
            if response.status_code == 404:
                raise RuntimeError(f"no-such-entity: {qid} not found on Wikidata")
            if response.status_code == 400:
                raise RuntimeError(f"no-such-entity: {qid} is invalid")

            response.raise_for_status()
            return response.text
        except requests.RequestException as exc:
            raise RuntimeError(f"Failed to load item {qid}: {exc}") from exc

    def _parse_wikidata_json(self, json_text: str, qid: str) -> dict[str, Any]:
        """Parse Wikidata JSON response from Special:EntityData endpoint.

        Args:
            json_text: Raw JSON response text.
            qid: The QID being parsed (used for error messages).

        Returns:
            Dictionary with entity data.

        Raises:
            ValueError: If JSON parsing fails or format is unexpected.

        Plain meaning: Extract entity data from the API response.
        """

        try:
            response = json.loads(json_text)
        except json.JSONDecodeError as exc:
            raise ValueError(f"Failed to parse JSON response for {qid}: {exc}") from exc

        if not isinstance(response, dict):
            raise ValueError(f"Expected JSON object for {qid}, got {type(response)}")

        # Special:EntityData wraps data in an "entities" key
        entities = response.get("entities", {})
        entity_data: dict[str, Any] = entities.get(qid, {})

        # Check for API error
        if "error" in entity_data:
            error_code = entity_data["error"].get("code", "unknown")
            error_info = entity_data["error"].get("info", "No error details")
            raise ValueError(
                f"Wikidata API error for {qid} ({error_code}): {error_info}"
            )

        if not entity_data:
            raise ValueError(f"Entity {qid} not found in response")

        return entity_data

    def _build_template(
        self, qid: str, entity_data: dict[str, Any]
    ) -> WikibaseItemTemplate:
        """Convert entity data to a WikibaseItemTemplate.

        Plain meaning: Transform API data into our simplified format.
        """

        # Extract labels, descriptions, aliases
        labels = entity_data.get("labels", {})
        descriptions = entity_data.get("descriptions", {})
        aliases = entity_data.get("aliases", {})

        # Simplify to language -> value mappings
        labels_dict = {
            lang: item.get("value", "")
            for lang, item in labels.items()
            if isinstance(item, dict)
        }
        descriptions_dict = {
            lang: item.get("value", "")
            for lang, item in descriptions.items()
            if isinstance(item, dict)
        }
        aliases_dict = {
            lang: [alias.get("value", "") for alias in alias_list]
            for lang, alias_list in aliases.items()
            if isinstance(alias_list, list)
        }

        # Extract claims
        claims = self._extract_claims(entity_data.get("claims", {}))

        return WikibaseItemTemplate(
            qid=qid,
            labels=labels_dict,
            descriptions=descriptions_dict,
            aliases=aliases_dict,
            claims=claims,
            entity_data=copy.deepcopy(entity_data),
        )

    @staticmethod
    def _extract_claims(claims_data: dict[str, Any]) -> list[ClaimSummary]:
        """Extract claims from entity data.

        Plain meaning: Parse statement data into simplified claim objects.
        """

        claims: list[ClaimSummary] = []

        for prop_id, statements in claims_data.items():
            if not isinstance(statements, list):
                continue

            for statement in statements:
                claim = WikibaseLoader._statement_to_claim(prop_id, statement)
                if claim:
                    claims.append(claim)

        return claims

    def _build_property_template(
        self, pid: str, entity_data: dict[str, Any]
    ) -> WikibasePropertyTemplate:
        """Convert entity data to a WikibasePropertyTemplate.

        Plain meaning: Transform API data into our simplified property format.
        """
        # Extract labels, descriptions, aliases
        labels = entity_data.get("labels", {})
        descriptions = entity_data.get("descriptions", {})
        aliases = entity_data.get("aliases", {})

        # Simplify to language -> value mappings
        labels_dict = {
            lang: item.get("value", "")
            for lang, item in labels.items()
            if isinstance(item, dict)
        }
        descriptions_dict = {
            lang: item.get("value", "")
            for lang, item in descriptions.items()
            if isinstance(item, dict)
        }
        aliases_dict = {
            lang: [alias.get("value", "") for alias in alias_list]
            for lang, alias_list in aliases.items()
            if isinstance(alias_list, list)
        }

        # Extract property-specific metadata
        datatype = entity_data.get("datatype")

        # Formatter URL is in claims P1630
        formatter_url = None
        claims = entity_data.get("claims", {})
        p1630_statements = claims.get("P1630", [])
        if p1630_statements and isinstance(p1630_statements, list):
            first_statement = p1630_statements[0]
            mainsnak = first_statement.get("mainsnak", {})
            datavalue = mainsnak.get("datavalue", {})
            if datavalue.get("type") == "string":
                formatter_url = datavalue.get("value")

        return WikibasePropertyTemplate(
            pid=pid,
            labels=labels_dict,
            descriptions=descriptions_dict,
            aliases=aliases_dict,
            datatype=datatype,
            formatter_url=formatter_url,
            entity_data=copy.deepcopy(entity_data),
        )

    def _build_entity_schema_template(
        self, eid: str, entity_data: dict[str, Any]
    ) -> WikibaseEntitySchemaTemplate:
        """Convert entity data to a WikibaseEntitySchemaTemplate.

        Plain meaning: Transform API data into our simplified EntitySchema format.
        """
        # Extract labels and descriptions
        labels = entity_data.get("labels", {})
        descriptions = entity_data.get("descriptions", {})

        # Simplify to language -> value mappings
        labels_dict = {
            lang: item.get("value", "")
            for lang, item in labels.items()
            if isinstance(item, dict)
        }
        descriptions_dict = {
            lang: item.get("value", "")
            for lang, item in descriptions.items()
            if isinstance(item, dict)
        }

        # Extract schema text
        schema_text = entity_data.get("schemaText", "")

        return WikibaseEntitySchemaTemplate(
            eid=eid,
            labels=labels_dict,
            descriptions=descriptions_dict,
            schema_text=schema_text,
            entity_data=copy.deepcopy(entity_data),
        )

    @staticmethod
    def _statement_to_claim(
        prop_id: str, statement: dict[str, Any]
    ) -> Optional[ClaimSummary]:
        """Convert a single statement to a ClaimSummary.

        Plain meaning: Simplify a statement object for display.
        """

        # Extract main value
        mainsnak = statement.get("mainsnak", {})
        value, value_metadata = WikibaseLoader._snak_to_value(mainsnak)
        if value is None:
            return None

        # Extract qualifiers with their values
        qualifiers = statement.get("qualifiers", {})
        qualifiers_list = []
        for prop, snaks in qualifiers.items():
            if snaks:
                # Extract value from the first snak of each qualifier property
                snak = snaks[0]
                qual_value, qual_metadata = WikibaseLoader._snak_to_value(snak)
                if qual_value:
                    qualifier_dict = {"property": prop, "value": qual_value}
                    if qual_metadata:
                        qualifier_dict["metadata"] = qual_metadata
                    qualifiers_list.append(qualifier_dict)

        # Extract references
        references = statement.get("references", [])
        references_list = [{"count": len(ref.get("snaks", {}))} for ref in references]

        rank = statement.get("rank", "normal")

        return ClaimSummary(
            property_id=prop_id,
            value=value,
            qualifiers=qualifiers_list,
            references=references_list,
            rank=rank,
            value_metadata=value_metadata,
        )

    @staticmethod
    def _snak_to_value(
        snak: dict[str, Any],
    ) -> tuple[Optional[str], Optional[dict[str, Any]]]:
        """Extract a human-readable value from a snak with metadata.

        Returns:
            Tuple of (value_string, metadata_dict) where metadata contains
            things like precision for dates, units for quantities, etc.

        Plain meaning: Get a simple string representation of the value plus metadata.
        """

        snaktype = snak.get("snaktype", "value")

        if snaktype == "novalue":
            return "[no value]", None
        if snaktype == "somevalue":
            return "[unknown value]", None

        datavalue = snak.get("datavalue")
        if not datavalue:
            return None, None

        dv_type = datavalue.get("type", "")
        dv_value = datavalue.get("value")

        if dv_type == "wikibase-entityid":
            if isinstance(dv_value, dict):
                return dv_value.get("id", "[entity]"), None
            return str(dv_value), None

        if dv_type == "quantity":
            if isinstance(dv_value, dict):
                amount = dv_value.get("amount", "[quantity]")
                unit = dv_value.get("unit")
                metadata = {"unit": unit} if unit else None
                return amount, metadata
            return str(dv_value), None

        if dv_type == "time":
            if isinstance(dv_value, dict):
                time_str = dv_value.get("time", "[time]")
                precision = dv_value.get("precision")
                metadata = {"precision": precision} if precision is not None else None
                return time_str, metadata
            return str(dv_value), None

        if dv_type == "monolingualtext":
            if isinstance(dv_value, dict):
                return dv_value.get("text", "[text]"), None
            return str(dv_value), None

        if dv_type == "string":
            return str(dv_value), None

        if dv_type == "globecoordinate":
            if isinstance(dv_value, dict):
                lat = dv_value.get("latitude", "?")
                lon = dv_value.get("longitude", "?")
                precision_val = dv_value.get("precision")
                metadata = (
                    {"precision": precision_val} if precision_val is not None else None
                )
                return f"({lat}, {lon})", metadata
            return str(dv_value), None

        return (str(dv_value), None) if dv_value else (None, None)

__init__(user_agent=None, api_url='https://www.wikidata.org/w/api.php', api_client=None, auth=None)

Initialize the loader.

Parameters:

Name Type Description Default
user_agent Optional[str]

Custom user agent for Wikidata requests. If not provided, a default GKC user agent is used.

 None
api_client Optional[WikibaseApiClient]

Optional pre-configured WikibaseApiClient.

 None
auth Optional[Any]

Optional WikiverseAuth instance. When provided and the authenticated user has the apihighlimits right, batch requests are made in chunks of 500 instead of 50.

 None
Source code in gkc/mash/core.py 
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
def __init__(
    self,
    user_agent: Optional[str] = None,
    api_url: str = "https://www.wikidata.org/w/api.php",
    api_client: Optional[WikibaseApiClient] = None,
    auth: Optional[Any] = None,
):
    """Initialize the loader.

    Args:
        user_agent: Custom user agent for Wikidata requests.
                   If not provided, a default GKC user agent is used.
        api_client: Optional pre-configured WikibaseApiClient.
        auth: Optional WikiverseAuth instance. When provided and the
            authenticated user has the ``apihighlimits`` right, batch
            requests are made in chunks of 500 instead of 50.
    """

    if user_agent is None:
        user_agent = DEFAULT_USER_AGENT

    self.user_agent = user_agent
    self.api_url = api_url
    self.api_client = api_client or WikibaseApiClient(
        api_url=api_url,
        user_agent=user_agent,
    )
    has_high_limits = (
        auth is not None
        and callable(getattr(auth, "has_api_high_limits", None))
        and auth.has_api_high_limits()
    )
    self.entity_batch_size: int = 500 if has_high_limits else 50

load(qid)

Load a Wikidata item and return it as a template.

.. deprecated:: 1.0 Use :meth:load_item instead. This method is maintained for backwards compatibility and will be removed in a future version.

Parameters:

Name Type Description Default
qid str

The Wikidata item ID (e.g., 'Q42').

 required

Returns:

Type Description
WikibaseItemTemplate

WikibaseItemTemplate with the item's structure.

Plain meaning: Retrieve the item and return it ready for use.

Source code in gkc/mash/core.py 
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
def load(self, qid: str) -> WikibaseItemTemplate:
    """Load a Wikidata item and return it as a template.

    .. deprecated:: 1.0
        Use :meth:`load_item` instead. This method is maintained for
        backwards compatibility and will be removed in a future version.

    Args:
        qid: The Wikidata item ID (e.g., 'Q42').

    Returns:
        WikibaseItemTemplate with the item's structure.

    Plain meaning: Retrieve the item and return it ready for use.
    """
    return self.load_item(qid)

load_entities_raw(entity_ids)

Load raw entity JSON in wbgetentities-sized batches.

Uses self.entity_batch_size so authenticated sessions with apihighlimits can fetch 500 entities per request.

Source code in gkc/mash/core.py 
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
def load_entities_raw(self, entity_ids: list[str]) -> dict[str, dict[str, Any]]:
    """Load raw entity JSON in wbgetentities-sized batches.

    Uses ``self.entity_batch_size`` so authenticated sessions with
    ``apihighlimits`` can fetch 500 entities per request.
    """
    if not entity_ids:
        return {}

    result: dict[str, dict[str, Any]] = {}

    for i in range(0, len(entity_ids), self.entity_batch_size):
        batch = entity_ids[i : i + self.entity_batch_size]
        batch_results = self._fetch_entities_batch(batch)
        result.update(batch_results)

    return result

load_entity_data(qid)

Load raw Wikidata entity data.

Plain meaning: Return the entity JSON as provided by Wikidata.

Source code in gkc/mash/core.py 
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
def load_entity_data(self, qid: str) -> dict[str, Any]:
    """Load raw Wikidata entity data.

    Plain meaning: Return the entity JSON as provided by Wikidata.
    """

    # Fetch the item via Special:EntityData endpoint which returns JSON
    # This is equivalent to wbgetentities but simpler for single-item fetches
    json_text = self._fetch_entity_json(qid)

    # Parse the JSON response from Wikidata
    return self._parse_wikidata_json(json_text, qid)

load_entity_schema(eid)

Load a Wikidata EntitySchema and return it as a template.

Parameters:

Name Type Description Default
eid str

The Wikidata EntitySchema ID (e.g., 'E502').

 required

Returns:

Type Description
WikibaseEntitySchemaTemplate

WikibaseEntitySchemaTemplate with the schema content.

Raises:

Type Description
RuntimeError

If the EntitySchema cannot be fetched or parsed.

Plain meaning: Retrieve an EntitySchema and return it ready for use.

Example

loader = WikibaseLoader() schema = loader.load_entity_schema("E502") print(schema.summary())

Source code in gkc/mash/core.py 
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
def load_entity_schema(self, eid: str) -> WikibaseEntitySchemaTemplate:
    """Load a Wikidata EntitySchema and return it as a template.

    Args:
        eid: The Wikidata EntitySchema ID (e.g., 'E502').

    Returns:
        WikibaseEntitySchemaTemplate with the schema content.

    Raises:
        RuntimeError: If the EntitySchema cannot be fetched or parsed.

    Plain meaning: Retrieve an EntitySchema and return it ready for use.

    Example:
        >>> loader = WikibaseLoader()
        >>> schema = loader.load_entity_schema("E502")
        >>> print(schema.summary())
    """
    entity_data = fetch_entity_schema_json(eid, user_agent=self.user_agent)
    return self._build_entity_schema_template(eid, entity_data)

load_item(qid)

Load a Wikidata item and return it as a template.

Parameters:

Name Type Description Default
qid str

The Wikidata item ID (e.g., 'Q42').

 required

Returns:

Type Description
WikibaseItemTemplate

WikibaseItemTemplate with the item's structure.

Raises:

Type Description
RuntimeError

If the item cannot be fetched or parsed.

Plain meaning: Retrieve the item and return it ready for use.

Example

loader = WikibaseLoader() template = loader.load_item("Q42") print(template.summary())

Source code in gkc/mash/core.py 
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
def load_item(self, qid: str) -> WikibaseItemTemplate:
    """Load a Wikidata item and return it as a template.

    Args:
        qid: The Wikidata item ID (e.g., 'Q42').

    Returns:
        WikibaseItemTemplate with the item's structure.

    Raises:
        RuntimeError: If the item cannot be fetched or parsed.

    Plain meaning: Retrieve the item and return it ready for use.

    Example:
        >>> loader = WikibaseLoader()
        >>> template = loader.load_item("Q42")
        >>> print(template.summary())
    """

    entity_data = self.load_entity_data(qid)

    # Convert to MashTemplate
    template = self._build_template(qid, entity_data)

    return template

load_items(qids)

Load multiple Wikidata items in batch and return them as templates.

Uses the wbgetentities API to efficiently fetch multiple items in self.entity_batch_size chunks. Handles partial failures gracefully.

Parameters:

Name Type Description Default
qids list[str]

List of Wikidata item IDs (e.g., ['Q42', 'Q5']).

 required

Returns:

Type Description
dict[str, WikibaseItemTemplate]

Dict mapping QIDs to WikidataTemplates. Only successfully loaded
dict[str, WikibaseItemTemplate]

items are included in the result.

Raises:

Type Description
RuntimeError

If the API request fails completely.

Plain meaning: Load multiple items efficiently in batch.

Example

loader = WikibaseLoader() templates = loader.load_items(["Q42", "Q5", "Q30"]) print(len(templates)) 3

Source code in gkc/mash/core.py 
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
def load_items(self, qids: list[str]) -> dict[str, WikibaseItemTemplate]:
    """Load multiple Wikidata items in batch and return them as templates.

    Uses the wbgetentities API to efficiently fetch multiple items in
    ``self.entity_batch_size`` chunks. Handles partial failures gracefully.

    Args:
        qids: List of Wikidata item IDs (e.g., ['Q42', 'Q5']).

    Returns:
        Dict mapping QIDs to WikidataTemplates. Only successfully loaded
        items are included in the result.

    Raises:
        RuntimeError: If the API request fails completely.

    Plain meaning: Load multiple items efficiently in batch.

    Example:
        >>> loader = WikibaseLoader()
        >>> templates = loader.load_items(["Q42", "Q5", "Q30"])
        >>> print(len(templates))
        3
    """
    if not qids:
        return {}

    result: dict[str, WikibaseItemTemplate] = {}
    batch_results = self.load_entities_raw(qids)

    # Build templates for each successfully fetched entity
    for qid, entity_data in batch_results.items():
        try:
            template = self._build_template(qid, entity_data)
            result[qid] = template
        except Exception:
            # Skip items that fail to parse
            continue

    return result

load_property(pid)

Load a Wikidata property and return it as a template.

Parameters:

Name Type Description Default
pid str

The Wikidata property ID (e.g., 'P31').

 required

Returns:

Type Description
WikibasePropertyTemplate

WikibasePropertyTemplate with the property's metadata.

Raises:

Type Description
RuntimeError

If the property cannot be fetched or parsed.

Plain meaning: Retrieve a property definition and return it ready for use.

Example

loader = WikibaseLoader() prop = loader.load_property("P31") print(prop.summary())

Source code in gkc/mash/core.py 
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
def load_property(self, pid: str) -> WikibasePropertyTemplate:
    """Load a Wikidata property and return it as a template.

    Args:
        pid: The Wikidata property ID (e.g., 'P31').

    Returns:
        WikibasePropertyTemplate with the property's metadata.

    Raises:
        RuntimeError: If the property cannot be fetched or parsed.

    Plain meaning: Retrieve a property definition and return it ready for use.

    Example:
        >>> loader = WikibaseLoader()
        >>> prop = loader.load_property("P31")
        >>> print(prop.summary())
    """
    entity_data = self.load_entity_data(pid)
    return self._build_property_template(pid, entity_data)

WikipediaTemplate

A Wikipedia template loaded from Wikimedia API for use in Wikipedia editing.

This is the Wikipedia-specific implementation of the DataTemplate protocol.

Plain meaning: A loaded Wikipedia template ready for display and use in editing workflows.

Source code in gkc/mash/core.py 
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
@dataclass
class WikipediaTemplate:
    """A Wikipedia template loaded from Wikimedia API for use in Wikipedia editing.

    This is the Wikipedia-specific implementation of the DataTemplate protocol.

    Plain meaning: A loaded Wikipedia template ready for display and use
    in editing workflows.
    """

    title: str
    description: str
    params: dict[str, Any]
    param_order: list[str]
    raw_data: dict[str, Any]

    def summary(self) -> dict[str, Any]:
        """Return a summary of the template for display.

        Returns:
            Dict with title, description, and number of parameters.

        Plain meaning: Get a quick overview without full details.
        """
        return {
            "title": self.title,
            "description": self.description,
            "param_count": len(self.params),
        }

    def to_dict(self) -> dict[str, Any]:
        """Serialize to a dictionary.

        Returns:
            Dict containing title, description, params, and paramOrder.

        Plain meaning: Convert to a form suitable for JSON export.
        """
        return {
            "title": self.title,
            "description": self.description,
            "params": self.params,
            "paramOrder": self.param_order,
        }

summary()

Return a summary of the template for display.

Returns:

Type Description
dict[str, Any]

Dict with title, description, and number of parameters.

Plain meaning: Get a quick overview without full details.

Source code in gkc/mash/core.py 
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
def summary(self) -> dict[str, Any]:
    """Return a summary of the template for display.

    Returns:
        Dict with title, description, and number of parameters.

    Plain meaning: Get a quick overview without full details.
    """
    return {
        "title": self.title,
        "description": self.description,
        "param_count": len(self.params),
    }

to_dict()

Serialize to a dictionary.

Returns:

Type Description
dict[str, Any]

Dict containing title, description, params, and paramOrder.

Plain meaning: Convert to a form suitable for JSON export.

Source code in gkc/mash/core.py 
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
def to_dict(self) -> dict[str, Any]:
    """Serialize to a dictionary.

    Returns:
        Dict containing title, description, params, and paramOrder.

    Plain meaning: Convert to a form suitable for JSON export.
    """
    return {
        "title": self.title,
        "description": self.description,
        "params": self.params,
        "paramOrder": self.param_order,
    }

WikipediaLoader

Load Wikipedia templates from Wikimedia API as templates for editing workflows.

This is the Wikipedia-specific implementation of a data loader.

Plain meaning: Fetch and parse a Wikipedia template into a usable format.

Source code in gkc/mash/core.py 
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
class WikipediaLoader:
    """Load Wikipedia templates from Wikimedia API as templates for editing workflows.

    This is the Wikipedia-specific implementation of a data loader.

    Plain meaning: Fetch and parse a Wikipedia template into a usable format.
    """

    def __init__(self, user_agent: Optional[str] = None):
        """Initialize the loader.

        Args:
            user_agent: Custom user agent for Wikimedia API requests.
                       If not provided, a default GKC user agent is used.

        Plain meaning: Set up the loader with optional custom user agent.
        """
        if user_agent is None:
            user_agent = DEFAULT_USER_AGENT

        self.user_agent = user_agent
        self.base_url = "https://en.wikipedia.org/w/api.php"

    def load_template(self, template_name: str) -> WikipediaTemplate:
        """Load a Wikipedia template and return it as a template.

        Args:
            template_name: The Wikipedia template name (e.g., 'Infobox settlement').

        Returns:
            WikipediaTemplate with the template's structure.

        Raises:
            RuntimeError: If the template cannot be fetched or parsed.

        Plain meaning: Retrieve the template and return it ready for use.

        Example:
            >>> loader = WikipediaLoader()
            >>> template = loader.load_template("Infobox settlement")
            >>> print(template.summary())
        """
        # Fetch template data from Wikimedia API
        params: dict[str, Any] = {
            "action": "templatedata",
            "format": "json",
            "titles": f"Template:{template_name}",
        }

        try:
            response = requests.get(
                self.base_url,
                params=params,
                headers={"User-Agent": self.user_agent},
                timeout=10,
            )
            response.raise_for_status()
        except requests.RequestException as exc:
            raise RuntimeError(
                f"Failed to fetch template '{template_name}' from Wikimedia API: {exc}"
            ) from exc

        try:
            data = response.json()
        except ValueError as exc:
            raise RuntimeError(
                f"Failed to parse JSON response for template '{template_name}': {exc}"
            ) from exc

        # Extract pages from response. The templatedata API returns pages directly,
        # not nested under a "query" key like other Mediawiki APIs.
        pages = data.get("pages", {})
        if not pages:
            raise RuntimeError(
                f"Template '{template_name}' not found in Wikimedia API response"
            )

        # Get the first (and only) page
        page_data = next(iter(pages.values()))

        # Check if this page has template data
        if "notabledescriptions" in page_data or "missing" in page_data:
            raise RuntimeError(
                f"Template '{template_name}' not found or has no template data"
            )

        # Extract required fields
        title = page_data.get("title", template_name)

        # Get description in English, or empty string if not available
        descriptions = page_data.get("description", {})
        if isinstance(descriptions, dict):
            description = descriptions.get("en", "")
        else:
            description = str(descriptions) if descriptions else ""

        params_data = page_data.get("params", {})
        param_order = page_data.get("paramOrder", [])

        # Build and return the template
        return WikipediaTemplate(
            title=title,
            description=description,
            params=params_data,
            param_order=param_order,
            raw_data=page_data,
        )

__init__(user_agent=None)

Initialize the loader.

Parameters:

Name Type Description Default
user_agent Optional[str]

Custom user agent for Wikimedia API requests. If not provided, a default GKC user agent is used.

 None

Plain meaning: Set up the loader with optional custom user agent.

Source code in gkc/mash/core.py 
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
def __init__(self, user_agent: Optional[str] = None):
    """Initialize the loader.

    Args:
        user_agent: Custom user agent for Wikimedia API requests.
                   If not provided, a default GKC user agent is used.

    Plain meaning: Set up the loader with optional custom user agent.
    """
    if user_agent is None:
        user_agent = DEFAULT_USER_AGENT

    self.user_agent = user_agent
    self.base_url = "https://en.wikipedia.org/w/api.php"

load_template(template_name)

Load a Wikipedia template and return it as a template.

Parameters:

Name Type Description Default
template_name str

The Wikipedia template name (e.g., 'Infobox settlement').

 required

Returns:

Type Description
WikipediaTemplate

WikipediaTemplate with the template's structure.

Raises:

Type Description
RuntimeError

If the template cannot be fetched or parsed.

Plain meaning: Retrieve the template and return it ready for use.

Example

loader = WikipediaLoader() template = loader.load_template("Infobox settlement") print(template.summary())

Source code in gkc/mash/core.py 
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
def load_template(self, template_name: str) -> WikipediaTemplate:
    """Load a Wikipedia template and return it as a template.

    Args:
        template_name: The Wikipedia template name (e.g., 'Infobox settlement').

    Returns:
        WikipediaTemplate with the template's structure.

    Raises:
        RuntimeError: If the template cannot be fetched or parsed.

    Plain meaning: Retrieve the template and return it ready for use.

    Example:
        >>> loader = WikipediaLoader()
        >>> template = loader.load_template("Infobox settlement")
        >>> print(template.summary())
    """
    # Fetch template data from Wikimedia API
    params: dict[str, Any] = {
        "action": "templatedata",
        "format": "json",
        "titles": f"Template:{template_name}",
    }

    try:
        response = requests.get(
            self.base_url,
            params=params,
            headers={"User-Agent": self.user_agent},
            timeout=10,
        )
        response.raise_for_status()
    except requests.RequestException as exc:
        raise RuntimeError(
            f"Failed to fetch template '{template_name}' from Wikimedia API: {exc}"
        ) from exc

    try:
        data = response.json()
    except ValueError as exc:
        raise RuntimeError(
            f"Failed to parse JSON response for template '{template_name}': {exc}"
        ) from exc

    # Extract pages from response. The templatedata API returns pages directly,
    # not nested under a "query" key like other Mediawiki APIs.
    pages = data.get("pages", {})
    if not pages:
        raise RuntimeError(
            f"Template '{template_name}' not found in Wikimedia API response"
        )

    # Get the first (and only) page
    page_data = next(iter(pages.values()))

    # Check if this page has template data
    if "notabledescriptions" in page_data or "missing" in page_data:
        raise RuntimeError(
            f"Template '{template_name}' not found or has no template data"
        )

    # Extract required fields
    title = page_data.get("title", template_name)

    # Get description in English, or empty string if not available
    descriptions = page_data.get("description", {})
    if isinstance(descriptions, dict):
        description = descriptions.get("en", "")
    else:
        description = str(descriptions) if descriptions else ""

    params_data = page_data.get("params", {})
    param_order = page_data.get("paramOrder", [])

    # Build and return the template
    return WikipediaTemplate(
        title=title,
        description=description,
        params=params_data,
        param_order=param_order,
        raw_data=page_data,
    )

See Also