Update search_api index processors to better handle URL's in text (#503)

* Update search_api index processors to better handle URL's in text.
SU-SWS · Oct 11, 2024 · 463cd60 · 463cd60
1 parent 0f5938b
commit 463cd60
Showing 1 changed file with 35 additions and 15 deletions.
diff --git a/docroot/profiles/sdss/sdss_profile/config/sync/search_api.index.full_site_content.yml b/docroot/profiles/sdss/sdss_profile/config/sync/search_api.index.full_site_content.yml
@@ -3,8 +3,8 @@ langcode: en
 status: true
 dependencies:
   config:
-    - field.storage.node.su_sdss_media_mention
     - field.storage.node.su_news_topics
+    - field.storage.node.su_sdss_media_mention
     - search_api.server.database_search
     - core.entity_view_mode.node.search_indexing
   module:
@@ -120,7 +120,7 @@ processor_settings:
   aggregated_field: {  }
   content_access:
     weights:
-      preprocess_query: -30
+      preprocess_query: -50
   custom_value: {  }
   entity_status: {  }
   entity_type: {  }
@@ -137,8 +137,8 @@ processor_settings:
     highlight_partial: false
   html_filter:
     weights:
-      preprocess_index: -15
-      preprocess_query: -15
+      preprocess_index: -48
+      preprocess_query: -46
     all_fields: false
     fields:
       - rendered_item
@@ -155,32 +155,40 @@ processor_settings:
       strong: 2
   ignore_character:
     weights:
-      preprocess_index: -10
-      preprocess_query: -10
+      preprocess_index: -49
+      preprocess_query: -47
     all_fields: false
     fields:
       - rendered_item
       - su_news_topics
       - title
       - type
-    ignorable: "['¿¡!?,.:;]"
+    ignorable: "['¿¡!?,:;]"
     ignorable_classes:
-      - Pc
-      - Pd
       - Pe
       - Pf
       - Pi
       - Po
       - Ps
+  ignorecase:
+    weights:
+      preprocess_index: -50
+      preprocess_query: -48
+    all_fields: false
+    fields:
+      - rendered_item
+      - su_news_topics
+      - title
+      - type
   language_with_fallback: {  }
   rendered_item: {  }
   role_access:
     weights:
-      preprocess_query: -30
+      preprocess_query: -49
   stemmer:
     weights:
-      preprocess_index: 0
-      preprocess_query: 0
+      preprocess_index: -44
+      preprocess_query: -43
     all_fields: true
     fields:
       - rendered_item
@@ -190,8 +198,8 @@ processor_settings:
       texan: texa
   stopwords:
     weights:
-      preprocess_index: -5
-      preprocess_query: -2
+      preprocess_index: -45
+      preprocess_query: -44
     all_fields: false
     fields:
       - rendered_item
@@ -231,9 +239,21 @@ processor_settings:
       - was
       - will
       - with
+  tokenizer:
+    weights:
+      preprocess_index: -46
+      preprocess_query: -45
+    all_fields: false
+    fields:
+      - rendered_item
+      - title
+    spaces: ._-
+    ignored: ''
+    overlap_cjk: 1
+    minimum_word_size: '3'
   type_boost:
     weights:
-      preprocess_index: 0
+      preprocess_index: -43
     boosts:
       'entity:node':
         datasource_boost: 1.0