Yasuhiro Horimoto 2019-02-08 17:49:43 +0900 (Fri, 08 Feb 2019) Revision: 1e1b1919672d5183012ddc153bd05fcfd8bd0cf6 https://github.com/groonga/groonga.org/commit/1e1b1919672d5183012ddc153bd05fcfd8bd0cf6 Message: blog en: use English in examples Modified files: en/_posts/2019-02-09-groonga-9.0.0.md Modified: en/_posts/2019-02-09-groonga-9.0.0.md (+45 -45) =================================================================== --- en/_posts/2019-02-09-groonga-9.0.0.md 2019-02-08 16:12:51 +0900 (7d7992b5f) +++ en/_posts/2019-02-09-groonga-9.0.0.md 2019-02-08 17:49:43 +0900 (bf742ff6f) @@ -22,7 +22,7 @@ Here are important changes in this release: * [Tokenizers](/docs/reference/tokenizers.html) Added a new tokenizer ``TokenTable``. -* [select](/docs/reference/commands/select.html) Supported similer search against index column. +* [select](/docs/reference/commands/select.html) Added support for similer search against index column. * [Normalizers](/docs/reference/normalizers.html) Added new option `remove_blank` for `NormalizerNFKC100`. @@ -36,43 +36,37 @@ This tokenizer extracts only token that matches the regular expression. You can also specify multiple patterns of regular expression. ``` -tokenize 'TokenPattern("pattern", "\\\\d+円", "pattern", "りんご|みかん")' "私は100円のりんごと50円のみかんを129円で買いました。" +tokenize 'TokenPattern("pattern", "\\\\$[0-9]", "pattern", "apples|oranges")' "I bought apples for $3 and oranges for $4." [ [ 0, - 0.0, - 0.0 + 1549612606.784344, + 0.0003230571746826172 ], [ { - "value": "100円", + "value": "apples", "position": 0, "force_prefix": false, "force_prefix_search": false }, { - "value": "りんご", + "value": "$3", "position": 1, "force_prefix": false, "force_prefix_search": false }, { - "value": "50円", + "value": "oranges", "position": 2, "force_prefix": false, "force_prefix_search": false }, { - "value": "みかん", + "value": "$4", "position": 3, "force_prefix": false, "force_prefix_search": false - }, - { - "value": "129円", - "position": 4, - "force_prefix": false, - "force_prefix_search": false } ] ] @@ -86,32 +80,32 @@ You can extract tokens by a key of existing a table as below. table_create Keywords TABLE_PAT_KEY ShortText --normalizer NormalizerNFKC100 load --table Keywords [ -{"_key": "100円"}, -{"_key": "りんご"}, -{"_key": "29円"} +{"_key": "$4"}, +{"_key": "apples"}, +{"_key": "$3"} ] -tokenize 'TokenTable("table", "Keywords")' "私は100円のりんごを２9円で買いました。" +tokenize 'TokenTable("table", "Keywords")' "I bought apples for $4 at $3." [ [ 0, - 0.0, - 0.0 + 1549613095.146393, + 0.0003008842468261719 ], [ { - "value": "100円", + "value": "apples", "position": 0, "force_prefix": false, "force_prefix_search": false }, { - "value": "りんご", + "value": "$4", "position": 1, "force_prefix": false, "force_prefix_search": false }, { - "value": "２9円", + "value": "$3", "position": 2, "force_prefix": false, "force_prefix_search": false @@ -133,31 +127,31 @@ column_create Terms document_index COLUMN_INDEX|WITH_POSITION|WITH_SECTION Docum load --table Documents [ ["_key", "content1"], -["groonga の概要", "groonga は転置索引を用いた高速・高精度な全文検索エンジンであり、登録された文書をすぐに検索結果に反映できます。"], -["全文検索と即時更新", "一般的なデータベースにおいては、追加・削除などの操作がすぐに反映されます。一方、全文検索においては、転置索引が逐次更新の難しいデータ構造であることから、文書の追加・削除に対応しないエンジンが少なくありません。"], -["カラムストアと集計クエリ", "現代は、インターネットを情報源とすれば、いくらでも情報を収集できる時代です。"] +["Groonga overview", "Groonga is a fast and accurate full text search engine based on inverted index. One of the characteristics of Groonga is that a newly registered document instantly appears in search results."], +["Full text search and Instant update", "In widely used DBMSs, updates are immediately processed, for example, a newly registered record appears in the result of the next query. In contrast, some full text search engines do not support instant updates, because it is difficult to dynamically update inverted indexes, the underlying data structure."], +["Column store and aggregate query", "People can collect more than enough data in the Internet era."] ] load --table Documents [ ["_key", "content2"], -["転置索引とトークナイザ", "転置索引は大規模な全文検索に用いられる伝統的なデータ構造です"], -["共有可能なストレージと参照ロックフリー", "CPU のマルチコア化が進んでいるため、同時に複数のクエリを実行したり、一つのクエリを複数のスレッドで実行したりすることの重要性はますます高まっています。"], -["位置情報（緯度・経度）検索", "GPS に代表される測位システムを搭載した高機能な携帯端末の普及などによって、位置情報を扱うサービスはますます便利になっています。"], -["groonga ライブラリ", "Groonga の基本機能は C ライブラリとして提供されているので、任意のアプリケーションに組み込んで利用することができます。"], -["groonga サーバ", "groonga にはサーバ機能があるため、レンタルサーバなどの新しいライブラリをインストールできない環境においても利用できます。"], -["groonga ストレージエンジン", "groonga は独自のカラムストアを持つ列指向のデータベースとしての側面を持っていますが、既存の RDBMS のストレージエンジンとして利用することもできます。"] +["Inverted index and tokenizer", "An inverted index is a traditional data structure used for large-scale full text search."], +["Sharable storage and read lock-free", "Multi-core processors are mainstream today and the number of cores per processor is increasing."], +["Geo-location (latitude and longitude) search", "Location services are getting more convenient because of mobile devices with GPS."], +["Groonga library", "The basic functions of Groonga are provided in a C library and any application can use Groonga as a full text search engine or a column-oriented database."], +["Groonga server", "Groonga provides a built-in server command which supports HTTP, the memcached binary protocol and the Groonga Query Transfer Protocol (GQTP)."], +["Mroonga storage engine", "Groonga works not only as an independent column-oriented DBMS but also as storage engines of well-known DBMSs."] ] -select Documents --filter 'Terms.document_index *S "MySQLで全文検索"' --output_columns '_key, _score, content1, content2' +select Documents --filter 'Terms.document_index *S "Full text seach by MySQL"' --output_columns '_key, _score, content1, content2' [ [ 0, - 1549608674.553312, - 0.0007221698760986328 + 1549615598.381915, + 0.0007889270782470703 ], [ [ [ - 3 + 4 ], [ [ @@ -178,22 +172,28 @@ select Documents --filter 'Terms.document_index *S "MySQLで全文検索"' --out ] ], [ - "groonga の概要", - 419432, - "groonga は転置索引を用いた高速・高精度な全文検索エンジンであり、登録された文書をすぐに検索結果に反映できます。", + "Groonga overview", + 87382, + "Groonga is a fast and accurate full text search engine based on inverted index. One of the characteristics of Groonga is that a newly registered document instantly appears in search results.", "" ], [ - "全文検索と即時更新", - 209716, - "一般的なデータベースにおいては、追加・削除などの操作がすぐに反映されます。一方、全文検索においては、転置索引が逐次更新の難しいデータ構造であることから、文書の追加・削除に対応しないエンジンが少なくありません。", + "Full text search and Instant update", + 87382, + "In widely used DBMSs, updates are immediately processed, for example, a newly registered record appears in the result of the next query. In contrast, some full text search engines do not support instant updates, because it is difficult to dynamically update inverted indexes, the underlying data structure.", "" ], [ - "転置索引とトークナイザ", - 209716, + "Inverted index and tokenizer", + 87382, + "", + "An inverted index is a traditional data structure used for large-scale full text search." + ], + [ + "Groonga library", + 87382, "", - "転置索引は大規模な全文検索に用いられる伝統的なデータ構造です" + "The basic functions of Groonga are provided in a C library and any application can use Groonga as a full text search engine or a column-oriented database." ] ] ] -------------- next part -------------- An HTML attachment was scrubbed... URL: <https://lists.osdn.me/mailman/archives/groonga-commit/attachments/20190208/0580e271/attachment-0001.html>
