Update usage of Wikidata entities to use shared dict

CONTRIBUTING.md

@@ -154,6 +154,13 @@ pre-commit install  # install pre-commit hooks
 # pre-commit run --all-files  # lint and fix common problems in the codebase
 ```
 
+> [!NOTE]
+> If you are having issues with pre-commit and want to send along your changes regardless, you can ignore the pre-commit hooks via the following:
+>
+> ```bash
+> git commit --no-verify -m "COMMIT_MESSAGE"
+> ```
+
 If you face any issues, consider reinstalling Scribe-data by running the following:
 
 ```bash

src/scribe_data/resources/wikidata_qids_pids.json

@@ -0,0 +1,4 @@
+{
+  "instance_of": "P31",
+  "ietf_language_tag": "P305"
+}

src/scribe_data/utils.py

@@ -23,7 +23,6 @@
 
 import ast
 import contextlib
-import requests
 import json
 import os
 import re
@@ -33,6 +32,7 @@
 from typing import Any, Optional
 
 import questionary
+import requests
 from rich import print as rprint
 
 # MARK: Utils Variables
@@ -55,6 +55,9 @@
 LEXEME_FORM_METADATA_FILE = (
     Path(__file__).parent / "resources" / "lexeme_form_metadata.json"
 )
+WIKIDATA_QIDS_PIDS_FILE = (
+    Path(__file__).parent / "resources" / "wikidata_qids_pids.json"
+)
 DATA_DIR = Path(DEFAULT_JSON_EXPORT_DIR)
 
 try:
@@ -79,6 +82,13 @@
 except (IOError, json.JSONDecodeError) as e:
     print(f"Error reading lexeme form metadata: {e}")
 
+try:
+    with WIKIDATA_QIDS_PIDS_FILE.open("r", encoding="utf-8") as file:
+        wikidata_qids_pids = json.load(file)
+
+except (IOError, json.JSONDecodeError) as e:
+    print(f"Error reading language metadata: {e}")
+
 
 language_map = {}
 language_to_qid = {}
@@ -762,8 +772,10 @@ def check_qid_is_language(qid: str):
     request = requests.get(request_string, timeout=5)
     request_result = request.json()
 
-    if request_result["statements"]["P31"]:
-        instance_of_values = request_result["statements"]["P31"]
+    if request_result["statements"][wikidata_qids_pids["instance_of"]]:
+        instance_of_values = request_result["statements"][
+            wikidata_qids_pids["instance_of"]
+        ]
         for val in instance_of_values:
             if val["value"]["content"] == "Q34770":
                 print(f"{request_result['labels']['en']} ({qid}) is a language.\n")
@@ -796,9 +808,9 @@ def get_language_iso_code(qid: str):
     response = requests.get(api_endpoint)
     data = response.json()
     try:
-        return data["entities"][qid]["claims"]["P305"][0]["mainsnak"]["datavalue"][
-            "value"
-        ]
+        return data["entities"][qid]["claims"][wikidata_qids_pids["ietf_language_tag"]][
+            0
+        ]["mainsnak"]["datavalue"]["value"]
 
     except ValueError:
         raise ValueError("The passed Wikidata QID is not a language.")

tests/cli/test_total.py

@@ -20,6 +20,7 @@
     -->
 """
 
+import json
 import unittest
 from unittest.mock import MagicMock, call, patch
 
@@ -29,7 +30,14 @@
     get_total_lexemes,
     total_wrapper,
 )
-from scribe_data.utils import check_qid_is_language
+from scribe_data.utils import WIKIDATA_QIDS_PIDS_FILE, check_qid_is_language
+
+try:
+    with WIKIDATA_QIDS_PIDS_FILE.open("r", encoding="utf-8") as file:
+        wikidata_qids_pids = json.load(file)
+
+except (IOError, json.JSONDecodeError) as e:
+    print(f"Error reading language metadata: {e}")
 
 
 class TestTotalLexemes(unittest.TestCase):
@@ -217,7 +225,9 @@ class TestCheckQidIsLanguage(unittest.TestCase):
     def test_check_qid_is_language_valid(self, mock_get):
         mock_response = MagicMock()
         mock_response.json.return_value = {
-            "statements": {"P31": [{"value": {"content": "Q34770"}}]},
+            "statements": {
+                wikidata_qids_pids["instance_of"]: [{"value": {"content": "Q34770"}}]
+            },
             "labels": {"en": "English"},
         }
         mock_get.return_value = mock_response
@@ -232,7 +242,9 @@ def test_check_qid_is_language_valid(self, mock_get):
     def test_check_qid_is_language_invalid(self, mock_get):
         mock_response = MagicMock()
         mock_response.json.return_value = {
-            "statements": {"P31": [{"value": {"content": "Q5"}}]},
+            "statements": {
+                wikidata_qids_pids["instance_of"]: [{"value": {"content": "Q5"}}]
+            },
             "labels": {"en": "Human"},
         }
         mock_get.return_value = mock_response