From 2dfae7ccc767c3d0d391ee809faec9365275668a Mon Sep 17 00:00:00 2001
From: Anton Rubin <anton.rubin@eliatra.com>
Date: Thu, 10 Oct 2024 11:14:39 +0100
Subject: [PATCH 1/3] add thai tokenizer docs

Signed-off-by: Anton Rubin <anton.rubin@eliatra.com>
---
 _analyzers/tokenizers/index.md |   2 +-
 _analyzers/tokenizers/thai.md  | 108 +++++++++++++++++++++++++++++++++
 2 files changed, 109 insertions(+), 1 deletion(-)
 create mode 100644 _analyzers/tokenizers/thai.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/thai.md b/_analyzers/tokenizers/thai.md
new file mode 100644
index 0000000000..4999c420b4
--- /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 is designed for tokenizing Thai language text. As 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 `thai` tokenizer:
+
+```
+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 created 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
+    }
+  ]
+}
+```

From 70c122b7b5072541f00f8a44ec394c491d89d3bc Mon Sep 17 00:00:00 2001
From: Fanit Kolchina <kolchfa@amazon.com>
Date: Thu, 5 Dec 2024 13:57:09 -0500
Subject: [PATCH 2/3] Doc review

Signed-off-by: Fanit Kolchina <kolchfa@amazon.com>
---
 _analyzers/tokenizers/thai.md | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/_analyzers/tokenizers/thai.md b/_analyzers/tokenizers/thai.md
index 4999c420b4..d1d83ff07e 100644
--- a/_analyzers/tokenizers/thai.md
+++ b/_analyzers/tokenizers/thai.md
@@ -7,13 +7,13 @@ nav_order: 140
 
 # Thai tokenizer
 
-The `thai` tokenizer is designed for tokenizing Thai language text. As words in Thai language are not separated by spaces, the tokenizer must identify word boundaries based on language-specific rules.
+The `thai` tokenizer is designed for tokenizing 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 `thai` tokenizer:
+The following example request creates a new index named `thai_index` and configures an analyzer with a `thai` tokenizer:
 
-```
+```json
 PUT /thai_index
 {
   "settings": {
@@ -45,7 +45,7 @@ PUT /thai_index
 
 ## Generated tokens
 
-Use the following request to examine the tokens generated using the created analyzer:
+Use the following request to examine the tokens generated using the analyzer:
 
 ```json
 POST /thai_index/_analyze

From 2508ddee59175251da5843c685574cd5bc18502a Mon Sep 17 00:00:00 2001
From: kolchfa-aws <105444904+kolchfa-aws@users.noreply.github.com>
Date: Mon, 9 Dec 2024 12:18:20 -0500
Subject: [PATCH 3/3] 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>
---
 _analyzers/tokenizers/thai.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/_analyzers/tokenizers/thai.md b/_analyzers/tokenizers/thai.md
index d1d83ff07e..4afb14a9eb 100644
--- a/_analyzers/tokenizers/thai.md
+++ b/_analyzers/tokenizers/thai.md
@@ -7,7 +7,7 @@ nav_order: 140
 
 # Thai tokenizer
 
-The `thai` tokenizer is designed for tokenizing Thai language text. Because words in Thai language are not separated by spaces, the tokenizer must identify word boundaries based on language-specific rules.
+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