From 772b626311033ecc3fe52664924ff9b7a4463f35 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?H=C3=BCseyin=20Emre=20Arma=C4=9Fan?=
 <huseyinemre_armagan@hotmail.com>
Date: Mon, 15 Apr 2024 18:21:46 +0100
Subject: [PATCH] Add CategorizeText aggregation (#1589)

---
 elasticsearch_dsl/aggs.py |  4 ++++
 tests/test_aggs.py        | 17 +++++++++++++++++
 2 files changed, 21 insertions(+)

diff --git a/elasticsearch_dsl/aggs.py b/elasticsearch_dsl/aggs.py
index 69c2d85e..96b830e0 100644
--- a/elasticsearch_dsl/aggs.py
+++ b/elasticsearch_dsl/aggs.py
@@ -309,6 +309,10 @@ class MultiTerms(Bucket):
     name = "multi_terms"
 
 
+class CategorizeText(Bucket):
+    name = "categorize_text"
+
+
 # metric aggregations
 class TopHits(Agg):
     name = "top_hits"
diff --git a/tests/test_aggs.py b/tests/test_aggs.py
index aa928de4..e2848864 100644
--- a/tests/test_aggs.py
+++ b/tests/test_aggs.py
@@ -342,6 +342,23 @@ def test_multi_terms_aggregation():
     } == a.to_dict()
 
 
+def test_categorize_text_aggregation():
+    a = aggs.CategorizeText(
+        field="tags",
+        categorization_filters=["\\w+\\_\\d{3}"],
+        max_matched_tokens=2,
+        similarity_threshold=30,
+    )
+    assert {
+        "categorize_text": {
+            "field": "tags",
+            "categorization_filters": ["\\w+\\_\\d{3}"],
+            "max_matched_tokens": 2,
+            "similarity_threshold": 30,
+        }
+    } == a.to_dict()
+
+
 def test_median_absolute_deviation_aggregation():
     a = aggs.MedianAbsoluteDeviation(field="rating")