From 8183bac6daa4eb5256172e692ac7d0ce193ca1db Mon Sep 17 00:00:00 2001
From: Pablo Castellano <pablo@anche.no>
Date: Sun, 31 Jan 2016 00:50:12 +0100
Subject: [PATCH] elasticsearch: asciifolding (issue #10)

---
 borme/search_backends.py | 42 ++++++++++++++++++++++++++++++++++++++++
 libreborme/settings.py   |  4 ++--
 2 files changed, 44 insertions(+), 2 deletions(-)
 create mode 100644 borme/search_backends.py

diff --git a/borme/search_backends.py b/borme/search_backends.py
new file mode 100644
index 0000000..5605a28
--- /dev/null
+++ b/borme/search_backends.py
@@ -0,0 +1,42 @@
+from haystack.backends.elasticsearch_backend import ElasticsearchSearchBackend
+from haystack.backends.elasticsearch_backend import ElasticsearchSearchEngine
+
+
+class AsciifoldingElasticBackend(ElasticsearchSearchBackend):
+
+    def __init__(self, *args, **kwargs):
+        super(AsciifoldingElasticBackend, self).__init__(*args, **kwargs)
+        analyzer = {
+            "ascii_analyser": {
+                "tokenizer": "standard",
+                "filter": ["standard", "asciifolding", "lowercase"]
+            },
+            "ngram_analyzer": {
+                "type": "custom",
+                "tokenizer": "lowercase",
+                "filter": ["haystack_ngram", "asciifolding"]
+            },
+            "edgengram_analyzer": {
+                "type": "custom",
+                "tokenizer": "lowercase",
+                "filter": ["haystack_edgengram", "asciifolding"]
+            }
+        }
+        self.DEFAULT_SETTINGS['settings']['analysis']['analyzer'] = analyzer
+
+    def build_schema(self, fields):
+        content_field_name, mapping = super(AsciifoldingElasticBackend, self).build_schema(fields)
+
+        for field_name, field_class in fields.items():
+            field_mapping = mapping[field_class.index_fieldname]
+
+            if field_mapping['type'] == 'string' and field_class.indexed:
+                if not hasattr(field_class, 'facet_for') and not field_class.field_type in('ngram', 'edge_ngram'):
+                    field_mapping['analyzer'] = "ascii_analyser"
+
+            mapping.update({field_class.index_fieldname: field_mapping})
+        return (content_field_name, mapping)
+
+
+class AsciifoldingElasticSearchEngine(ElasticsearchSearchEngine):
+    backend = AsciifoldingElasticBackend
diff --git a/libreborme/settings.py b/libreborme/settings.py
index b6f53d0..c6f456a 100644
--- a/libreborme/settings.py
+++ b/libreborme/settings.py
@@ -109,9 +109,9 @@
 # haystack search using elasticsearch
 HAYSTACK_CONNECTIONS = {
     'default': {
-        'ENGINE': 'haystack.backends.elasticsearch_backend.ElasticsearchSearchEngine',
+        'ENGINE': 'borme.search_backends.AsciifoldingElasticSearchEngine',
         'URL': 'http://127.0.0.1:9200/',
-        'INDEX_NAME': 'haystack',
+        'INDEX_NAME': 'libreborme',
     },
 }