Extract data from HTML to allow for simpler extraction

src/solo_turnier/tests/test_worker.py

@@ -2,6 +2,7 @@ from solo_turnier import worker
 import os
 import json
 import pytest
+import pytest_mock
 
 def __importJSONData(name):
     path = os.path.join(os.path.dirname(__file__), 'worker', name)
@@ -190,3 +191,28 @@ def test_consolidateGroups_failing(fixture_consolidateGroups_fail):
 
     with pytest.raises(Exception):
         dataWorker.consolidateGroups(data)
+
+def test_createHtmlLUT(mocker):
+    mock = mocker.patch('solo_turnier.html_parser.HtmlParser.guessDataFromHtmlTitle')
+    mock.side_effect= [
+        {'group': 'group1', 'class_': 'class1', 'dance': 'dance1'},
+        {'group': 'group2', 'class_': 'class2', 'dance': 'dance2'},
+        {'group': 'group3', 'class_': 'class3', 'dance': 'dance3'},
+    ]
+    
+    importMock1 = mocker.patch('solo_turnier.html_parser.HtmlImport')
+    importMock2 = mocker.patch('solo_turnier.html_parser.HtmlImport')
+    importMock3 = mocker.patch('solo_turnier.html_parser.HtmlImport')
+    importMock1.title = 'Fake title 1'
+    importMock2.title = 'Fake title 2'
+    importMock3.title = 'Fake title 3'
+
+    dataWorker = worker.DataWorker()
+    structure = dataWorker._createHtmlLUT([importMock1, importMock2, importMock3])
+
+    expected = {
+        ('group1', 'class1', 'dance1'): importMock1,
+        ('group2', 'class2', 'dance2'): importMock2,
+        ('group3', 'class3', 'dance3'): importMock3,
+    }
+    assert expected == structure

src/solo_turnier/worker.py

@@ -1,5 +1,6 @@
 import logging
 
+from solo_turnier import html_parser
 class ResultRow:
     def __init__(self, firstName, lastName, club, id, group, class_, dance, place, placeTo, competitionGroup, competitionClass):
         self.firstName = firstName
@@ -196,3 +197,13 @@ class DataWorker:
                 raise Exception(f'{person} cannot have different groups.')
             
         return (not ambiguous, warnChange)
+
+    def _createHtmlLUT(self, htmlImports: list[html_parser.HtmlImport]):
+        ret = {}
+        parser = html_parser.HtmlParser()
+        for imp in htmlImports:
+            parsed = parser.guessDataFromHtmlTitle(imp.title)
+            key = (parsed['group'], parsed['class_'], parsed['dance'])
+            ret[key] = imp
+        return ret
+