This is an automated email from the ASF dual-hosted git repository.
JingsongLi pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/paimon.git
The following commit(s) were added to refs/heads/master by this push:
new 2e4b9cdd2a [docs] Fix full-text index option defaults and search query
examples (#9062)
2e4b9cdd2a is described below
commit 2e4b9cdd2ad13847bb523d05374d0a783b127781
Author: Eunbin Son <[email protected]>
AuthorDate: Fri Aug 7 14:15:02 2026 +0900
[docs] Fix full-text index option defaults and search query examples (#9062)
---
docs/docs/flink/procedures.md | 2 +-
docs/docs/primary-key-table/global-index.mdx | 6 +++---
paimon-full-text/README.md | 16 +++++++++-------
3 files changed, 13 insertions(+), 11 deletions(-)
diff --git a/docs/docs/flink/procedures.md b/docs/docs/flink/procedures.md
index e3039f69b3..57772549f1 100644
--- a/docs/docs/flink/procedures.md
+++ b/docs/docs/flink/procedures.md
@@ -1164,7 +1164,7 @@ All available procedures are listed below.
CALL sys.full_text_search(<br/>
`table` => 'default.articles',<br/>
`column` => 'content',<br/>
- query => '{"match":{"column":"content","terms":"paimon
lake"}}',<br/>
+ query => '{"match":{"query":"paimon lake"}}',<br/>
top_k => 10,<br/>
projection => 'id,content,__paimon_search_score')
</td>
diff --git a/docs/docs/primary-key-table/global-index.mdx
b/docs/docs/primary-key-table/global-index.mdx
index db6ebe00d1..b96341e7b1 100644
--- a/docs/docs/primary-key-table/global-index.mdx
+++ b/docs/docs/primary-key-table/global-index.mdx
@@ -414,7 +414,7 @@ SELECT id, content, __paimon_search_score
FROM full_text_search(
'items',
'content',
- '{"match":{"column":"content","terms":"paimon lake"}}',
+ '{"match":{"query":"paimon lake"}}',
10
)
ORDER BY __paimon_search_score DESC;
@@ -431,7 +431,7 @@ relevance score is required. `top_k` must be between 1 and
10,000.
CALL sys.full_text_search(
`table` => 'default.items',
`column` => 'content',
- query => '{"match":{"column":"content","terms":"paimon lake"}}',
+ query => '{"match":{"query":"paimon lake"}}',
top_k => 10,
projection => 'id,content,__paimon_search_score'
);
@@ -480,7 +480,7 @@ FROM hybrid_search(
'options', map())),
array(named_struct(
'column', 'content',
- 'query', '{"match":{"column":"content","terms":"paimon lake"}}',
+ 'query', '{"match":{"query":"paimon lake"}}',
'limit', 20,
'weight', 1.0f,
'options', map())),
diff --git a/paimon-full-text/README.md b/paimon-full-text/README.md
index 2d17cccfb9..914aa03c85 100644
--- a/paimon-full-text/README.md
+++ b/paimon-full-text/README.md
@@ -129,7 +129,7 @@ scores through its configured `rrf`, `weighted_score`, or
`mrr` ranker.
CALL sys.full_text_search(
`table` => 'default.articles',
`column` => 'content',
- query => '{"match":{"column":"content","terms":"paimon lake"}}',
+ query => '{"match":{"query":"paimon lake"}}',
top_k => 10,
projection => 'id,content,__paimon_search_score'
);
@@ -178,16 +178,18 @@ Available tokenizer options:
| Option | Default | Description |
|--------|---------|-------------|
| `full-text.tokenizer` | `default` | Tokenizer used by the full-text index.
Supported values: `default`, `simple`, `whitespace`, `raw`, `ngram`, `jieba`. |
-| `full-text.ngram.min-gram` | `2` | Minimum gram length for the `ngram`
tokenizer. |
-| `full-text.ngram.max-gram` | `2` | Maximum gram length for the `ngram`
tokenizer. |
+| `full-text.ngram.min-gram` | `3` | Minimum gram length for the `ngram`
tokenizer. |
+| `full-text.ngram.max-gram` | `3` | Maximum gram length for the `ngram`
tokenizer. |
| `full-text.ngram.prefix-only` | `false` | Whether the `ngram` tokenizer only
emits prefix ngrams. |
+| `full-text.jieba.search-mode` | `true` | Whether the `jieba` tokenizer uses
search mode. |
+| `full-text.jieba.ordinal-position` | `true` | Whether the `jieba` tokenizer
uses ordinal positions. |
| `full-text.lower-case` | `true` | Whether configurable tokenizers lowercase
emitted tokens. |
| `full-text.max-token-length` | `40` | Maximum token length kept by
configurable tokenizers. |
-| `full-text.ascii-folding` | `false` | Whether to normalize non-ASCII Latin
characters to ASCII. |
-| `full-text.stem` | `false` | Whether to apply stemming to emitted tokens. |
+| `full-text.ascii-folding` | `true` | Whether to normalize non-ASCII Latin
characters to ASCII. |
+| `full-text.stem` | `true` | Whether to apply stemming to emitted tokens. |
| `full-text.language` | `english` | Language used by stemming and built-in
stop word filters. |
-| `full-text.remove-stop-words` | `false` | Whether to remove built-in stop
words for the configured language. |
-| `full-text.stop-words` | ` ` | Semicolon-separated custom stop words to
remove. |
+| `full-text.remove-stop-words` | `true` | Whether to remove built-in stop
words for the configured language. |
+| `full-text.stop-words` | empty | Semicolon-separated custom stop words to
remove. Requires `full-text.remove-stop-words=true`. |
| `full-text.with-position` | `true` | Whether to store term positions for
phrase queries. |
Tokenizer settings are persisted in each global index file's metadata. Readers
use that metadata
