feature: 数据库镜像制作 (#70)

* feature: 数据库镜像制作

* feature: 增加归档包流水线

scripts/db/data-operator-init.sql

@@ -123,7 +123,7 @@ AND o.id IN ('TextFormatter', 'FileWithShortOrLongLengthFilter', 'FileWithHighRe
             'AnonymizedIpAddress', 'AnonymizedPhoneNumber', 'AnonymizedUrlCleaner', 'HtmlTagCleaner', 'XMLTagCleaner',
             'ContentCleaner', 'EmailNumberCleaner', 'EmojiCleaner', 'ExtraSpaceCleaner', 'FullWidthCharacterCleaner',
             'GrableCharactersCleaner', 'InvisibleCharactersCleaner', 'LegendCleaner', 'PoliticalWordCleaner',
-            'SexualAndViolentWordCleaner', 'TraditionalChineseCleaner', 'UnicodeSpaceCleaner');
+            'SexualAndViolentWordCleaner', 'TraditionalChineseCleaner', 'UnicodeSpaceCleaner', 'MineruFormatter');
 
 INSERT IGNORE INTO t_operator_category_relation(category_id, operator_id)
 SELECT c.id, o.id

scripts/images/database/Dockerfile

@@ -0,0 +1,6 @@
+FROM mysql:8
+
+COPY scripts/images/database/utf8.cnf /etc/mysql/conf.d/utf8.cnf
+COPY scripts/db/ /docker-entrypoint-initdb.d/
+
+RUN chmod 644 /etc/mysql/conf.d/utf8.cnf

scripts/images/database/utf8.cnf

@@ -0,0 +1,16 @@
+[mysqld]
+# 设置服务器默认字符集为 utf8mb4 (推荐，支持完整的 UTF-8，包括 emoji)
+character-set-server = utf8mb4
+# 设置默认排序规则
+collation-server = utf8mb4_unicode_ci
+# 或者使用 utf8_general_ci (性能稍好，但排序规则稍宽松)
+default-time-zone = 'Asia/Shanghai'
+log_error=/var/log/datamate/database/error.log
+
+[client]
+# 设置客户端连接默认字符集
+default-character-set = utf8mb4
+
+[mysql]
+# 设置 mysql 命令行客户端默认字符集
+default-character-set = utf8mb4