make token analyzers configurable modules

[nominatim.git] / test / python / test_tokenizer_icu.py

diff --git a/test/python/test_tokenizer_icu.py b/test/python/test_tokenizer_icu.py
index 9a6f5a94f01c7b3486bfe659bd4878979581838b..52cca6a7a0d31a7e20543a342088641221ecdf43 100644 (file)
--- a/test/python/test_tokenizer_icu.py
+++ b/test/python/test_tokenizer_icu.py
@@ -69,10 +69,11 @@ def analyzer(tokenizer_factory, test_config, monkeypatch,
     def _mk_analyser(norm=("[[:Punctuation:][:Space:]]+ > ' '",), trans=(':: upper()',),
                      variants=('~gasse -> gasse', 'street => st', ),
                      sanitizers=[]):
     def _mk_analyser(norm=("[[:Punctuation:][:Space:]]+ > ' '",), trans=(':: upper()',),
                      variants=('~gasse -> gasse', 'street => st', ),
                      sanitizers=[]):

-        cfgstr = {'normalization' : list(norm),
-                  'sanitizers' : sanitizers,
-                  'transliteration' : list(trans),
-                  'variants' : [ {'words': list(variants)}]}
+        cfgstr = {'normalization': list(norm),
+                  'sanitizers': sanitizers,
+                  'transliteration': list(trans),
+                  'token-analysis': [{'analyzer': 'generic',
+                                      'variants': [{'words': list(variants)}]}]}

         (test_config.project_dir / 'icu_tokenizer.yaml').write_text(yaml.dump(cfgstr))
         tok.loader = ICURuleLoader(test_config)
 
         (test_config.project_dir / 'icu_tokenizer.yaml').write_text(yaml.dump(cfgstr))
         tok.loader = ICURuleLoader(test_config)