From 47f85a2036fe804a632fcffb211defafef484fa1 Mon Sep 17 00:00:00 2001
From: Anton Rubin <anton.rubin@eliatra.com>
Date: Wed, 9 Oct 2024 11:16:08 +0100
Subject: [PATCH] add whitespace tokenizer docs

Signed-off-by: Anton Rubin <anton.rubin@eliatra.com>
---
 _analyzers/tokenizers/index.md      |   2 +-
 _analyzers/tokenizers/whitespace.md | 105 ++++++++++++++++++++++++++++
 2 files changed, 106 insertions(+), 1 deletion(-)
 create mode 100644 _analyzers/tokenizers/whitespace.md

diff --git a/_analyzers/tokenizers/index.md b/_analyzers/tokenizers/index.md
index d401851f60..1abc5ee7ff 100644
--- a/_analyzers/tokenizers/index.md
+++ b/_analyzers/tokenizers/index.md
@@ -2,7 +2,7 @@
 layout: default
 title: Tokenizers
 nav_order: 60
-has_children: false
+has_children: true
 has_toc: false
 ---
 
diff --git a/_analyzers/tokenizers/whitespace.md b/_analyzers/tokenizers/whitespace.md
new file mode 100644
index 0000000000..12b7b798ae
--- /dev/null
+++ b/_analyzers/tokenizers/whitespace.md
@@ -0,0 +1,105 @@
+---
+layout: default
+title: Whitespace tokenizer
+parent: Tokenizers
+nav_order: 160
+---
+
+# Whitespace tokenizer
+
+The `whitespace` tokenizer splits text based purely on whitespace characters (like spaces, tabs, and newlines). It treats each word separated by whitespace as a token, without performing any additional analysis or normalization like lowercasing or punctuation removal.
+
+## Example usage
+
+The following example request creates a new index named `my_index` and configures an analyzer with `whitespace` tokenizer:
+
+```
+PUT /my_index
+{
+  "settings": {
+    "analysis": {
+      "tokenizer": {
+        "whitespace_tokenizer": {
+          "type": "whitespace"
+        }
+      },
+      "analyzer": {
+        "my_whitespace_analyzer": {
+          "type": "custom",
+          "tokenizer": "whitespace_tokenizer"
+        }
+      }
+    }
+  },
+  "mappings": {
+    "properties": {
+      "content": {
+        "type": "text",
+        "analyzer": "my_whitespace_analyzer"
+      }
+    }
+  }
+}
+```
+
+## Generated tokens
+
+Use the following request to examine the tokens generated using the created analyzer:
+
+```json
+POST /my_index/_analyze
+{
+  "analyzer": "my_whitespace_analyzer",
+  "text": "OpenSearch is fast! Really fast."
+}
+```
+{% include copy-curl.html %}
+
+The response contains the generated tokens:
+
+```json
+{
+  "tokens": [
+    {
+      "token": "OpenSearch",
+      "start_offset": 0,
+      "end_offset": 10,
+      "type": "word",
+      "position": 0
+    },
+    {
+      "token": "is",
+      "start_offset": 11,
+      "end_offset": 13,
+      "type": "word",
+      "position": 1
+    },
+    {
+      "token": "fast!",
+      "start_offset": 14,
+      "end_offset": 19,
+      "type": "word",
+      "position": 2
+    },
+    {
+      "token": "Really",
+      "start_offset": 20,
+      "end_offset": 26,
+      "type": "word",
+      "position": 3
+    },
+    {
+      "token": "fast.",
+      "start_offset": 27,
+      "end_offset": 32,
+      "type": "word",
+      "position": 4
+    }
+  ]
+}
+```
+
+## Configuration
+
+The `whitespace` tokenizer can be configured with parameter `max_token_length` which sets the maximum length of the produced token. If this length is exceeded, the token is split into multiple tokens at length configured in `max_token_length`. Default is `255` (Integer, _Optional_)
+