feature: 北向接口:支持通过模板创建清洗任务 (#111)

feature: 北向接口:支持通过模板创建清洗任务
This commit is contained in:
hhhhsc701
2025-11-26 17:30:54 +08:00
committed by GitHub
parent 0ca5f29885
commit 91390cace0
15 changed files with 312 additions and 253 deletions

View File

@@ -70,7 +70,7 @@ INSERT IGNORE INTO t_operator
VALUES ('TextFormatter', 'TXT文本抽取', '抽取TXT中的文本。', '1.0.0', 'text', 'text', null, null, '', false),
('UnstructuredFormatter', 'Unstructured文本抽取', '基于Unstructured抽取非结构化文件的文本,目前支持PowerPoint演示文稿、Word文档以及Excel工作簿。', '1.0.0', 'text', 'text', null, null, '', false),
('MineruFormatter', 'MinerU PDF文本抽取', '基于MinerU API,抽取PDF中的文本。', '1.0.0', 'text', 'text', null, null, '', false),
('FileExporter', '落盘算子', '将文件保存到本地目录。', '1.0.0', 'all', 'all', null, null, '', false),
('FileExporter', '落盘算子', '将文件保存到本地目录。', '1.0.0', 'multimodal', 'multimodal', null, null, '', false),
('FileWithHighRepeatPhraseRateFilter', '文档词重复率检查', '去除重复词过多的文档。', '1.0.0', 'text', 'text', null, '{"repeatPhraseRatio": {"name": "文档词重复率", "description": "某个词的统计数/文档总词数 > 设定值,该文档被去除。", "type": "slider", "defaultVal": 0.5, "min": 0, "max": 1, "step": 0.1}, "hitStopwords": {"name": "去除停用词", "description": "统计重复词时,选择是否要去除停用词。", "type": "switch", "defaultVal": false, "required": true, "checkedLabel": "去除", "unCheckedLabel": "不去除"}}', '', 'false'),
('FileWithHighRepeatWordRateFilter', '文档字重复率检查', '去除重复字过多的文档。', '1.0.0', 'text', 'text', null, '{"repeatWordRatio": {"name": "文档字重复率", "description": "某个字的统计数/文档总字数 > 设定值,该文档被去除。", "type": "slider", "defaultVal": 0.5, "min": 0, "max": 1, "step": 0.1}}', '', 'false'),
('FileWithHighSpecialCharRateFilter', '文档特殊字符率检查', '去除特殊字符过多的文档。', '1.0.0', 'text', 'text', null, '{"specialCharRatio": {"name": "文档特殊字符率", "description": "特殊字符的统计数/文档总字数 > 设定值,该文档被去除。", "type": "slider", "defaultVal": 0.3, "min": 0, "max": 1, "step": 0.1}}', '', 'false'),