From 5c5e0b04c83f2a54a59816b23f138409d2bed658 Mon Sep 17 00:00:00 2001
From: "github-actions[bot]" <github-actions[bot]@users.noreply.github.com>
Date: Mon, 9 Dec 2024 17:24:08 +0000
Subject: [PATCH] add thai tokenizer docs (#8489)

* add thai tokenizer docs

Signed-off-by: Anton Rubin <anton.rubin@eliatra.com>

* Doc review

Signed-off-by: Fanit Kolchina <kolchfa@amazon.com>

* Apply suggestions from code review

Co-authored-by: Nathan Bower <nbower@amazon.com>
Signed-off-by: kolchfa-aws <105444904+kolchfa-aws@users.noreply.github.com>

---------

Signed-off-by: Anton Rubin <anton.rubin@eliatra.com>
Signed-off-by: Fanit Kolchina <kolchfa@amazon.com>
Signed-off-by: kolchfa-aws <105444904+kolchfa-aws@users.noreply.github.com>
Co-authored-by: Fanit Kolchina <kolchfa@amazon.com>
Co-authored-by: kolchfa-aws <105444904+kolchfa-aws@users.noreply.github.com>
Co-authored-by: Nathan Bower <nbower@amazon.com>
(cherry picked from commit 5e338e6de51750c509da33f04f32344e6d3149b9)
Signed-off-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
---
 _analyzers/tokenizers/thai.md | 108 ++++++++++++++++++++++++++++++++++
 1 file changed, 108 insertions(+)
 create mode 100644 _analyzers/tokenizers/thai.md

diff --git a/_analyzers/tokenizers/thai.md b/_analyzers/tokenizers/thai.md
new file mode 100644
index 0000000000..4afb14a9eb
--- /dev/null
+++ b/_analyzers/tokenizers/thai.md
@@ -0,0 +1,108 @@
+---
+layout: default
+title: Thai
+parent: Tokenizers
+nav_order: 140
+---
+
+# Thai tokenizer
+
+The `thai` tokenizer tokenizes Thai language text. Because words in Thai language are not separated by spaces, the tokenizer must identify word boundaries based on language-specific rules.
+
+## Example usage
+
+The following example request creates a new index named `thai_index` and configures an analyzer with a `thai` tokenizer:
+
+```json
+PUT /thai_index
+{
+  "settings": {
+    "analysis": {
+      "tokenizer": {
+        "thai_tokenizer": {
+          "type": "thai"
+        }
+      },
+      "analyzer": {
+        "thai_analyzer": {
+          "type": "custom",
+          "tokenizer": "thai_tokenizer"
+        }
+      }
+    }
+  },
+  "mappings": {
+    "properties": {
+      "content": {
+        "type": "text",
+        "analyzer": "thai_analyzer"
+      }
+    }
+  }
+}
+```
+{% include copy-curl.html %}
+
+## Generated tokens
+
+Use the following request to examine the tokens generated using the analyzer:
+
+```json
+POST /thai_index/_analyze
+{
+  "analyzer": "thai_analyzer",
+  "text": "ฉันชอบไปเที่ยวที่เชียงใหม่"
+}
+```
+{% include copy-curl.html %}
+
+The response contains the generated tokens:
+
+```json
+{
+  "tokens": [
+    {
+      "token": "ฉัน",
+      "start_offset": 0,
+      "end_offset": 3,
+      "type": "word",
+      "position": 0
+    },
+    {
+      "token": "ชอบ",
+      "start_offset": 3,
+      "end_offset": 6,
+      "type": "word",
+      "position": 1
+    },
+    {
+      "token": "ไป",
+      "start_offset": 6,
+      "end_offset": 8,
+      "type": "word",
+      "position": 2
+    },
+    {
+      "token": "เที่ยว",
+      "start_offset": 8,
+      "end_offset": 14,
+      "type": "word",
+      "position": 3
+    },
+    {
+      "token": "ที่",
+      "start_offset": 14,
+      "end_offset": 17,
+      "type": "word",
+      "position": 4
+    },
+    {
+      "token": "เชียงใหม่",
+      "start_offset": 17,
+      "end_offset": 26,
+      "type": "word",
+      "position": 5
+    }
+  ]
+}
+```