feat/neon_transformers

companion to OpenVoiceOS/ovos-core#163

ovos_classifiers/opm.py

@@ -0,0 +1,38 @@
+from typing import Optional, List
+
+from ovos_plugin_manager.templates.transformers import UtteranceTransformer
+
+from ovos_classifiers.heuristics.normalize import Normalizer, CatalanNormalizer, CzechNormalizer, \
+    PortugueseNormalizer, AzerbaijaniNormalizer, RussianNormalizer, EnglishNormalizer, UkrainianNormalizer
+
+
+class UtteranceNormalizer(UtteranceTransformer):
+
+    def __init__(self, name="ovos-utterance-normalizer", priority=1):
+        super().__init__(name, priority)
+
+    @staticmethod
+    def get_normalizer(lang: str):
+        if lang.startswith("en"):
+            return EnglishNormalizer()
+        elif lang.startswith("pt"):
+            return PortugueseNormalizer()
+        elif lang.startswith("uk"):
+            return UkrainianNormalizer()
+        elif lang.startswith("ca"):
+            return CatalanNormalizer()
+        elif lang.startswith("cz"):
+            return CzechNormalizer()
+        elif lang.startswith("az"):
+            return AzerbaijaniNormalizer()
+        elif lang.startswith("ru"):
+            return RussianNormalizer()
+        return Normalizer()
+
+    def transform(self, utterances: List[str],
+                  context: Optional[dict] = None) -> (list, dict):
+        context = context or {}
+        lang = context.get("lang") or self.config.get("lang", "en-us")
+        normalizer = self.get_normalizer(lang)
+        norm = [normalizer.normalize(u) for u in utterances] + utterances
+        return list(set(norm)), context

setup.py

@@ -80,5 +80,8 @@ def required(requirements_file):
         'Programming Language :: Python :: 3.4',
         'Programming Language :: Python :: 3.5',
         'Programming Language :: Python :: 3.6',
-    ]
+    ],
+    entry_points={
+        'neon.plugin.text': 'ovos-utterance-normalizer=ovos_classifiers.opm:UtteranceNormalizer'
+    }
 )