mirror of
https://github.com/infiniflow/ragflow.git
synced 2026-08-23 00:31:06 +08:00
875ca966e9
Stop flattening `<table>` into a single text blob. A `<table>` now emits: 1. an inlined `doc_type_kwd:"text"` item keeping the `<table>…</table>` markup (row/column structure survives for embedding/retrieval/LLM rendering), 2. a structured `doc_type_kwd:"table"` / `ck_type:"table"` item appended after the walk, consumed by the downstream chunker.
34 lines
1.4 KiB
JSON
34 lines
1.4 KiB
JSON
{
|
|
"meta": {
|
|
"python_engine": "deepdoc.parser.html_parser.RAGFlowHtmlParser",
|
|
"generator": "rag/flow/parser/parser.py:_html (HtmlParser()(name, blob, 512))",
|
|
"sample": "internal/parser/parser/testdata/html.sample.zh.html",
|
|
"delimiter": "\\n!?;。；！？",
|
|
"separate_tables": false,
|
|
"accepted_divergences": ["table"],
|
|
"note": "No generator script is committed. To regenerate: call RAGFlowHtmlParser.read_text_recursively on the sample at chunk_token_num=512, apply the TITLE_TAGS heading prefix (\"# \"/\"## \" …) inline, emit every block (including the inline <table>…</table> markup) as a {\"text\": …, \"doc_type_kwd\": \"text\"} record, then wrap in {meta, items}. Go also appends a structured doc_type_kwd:\"table\" item; that extra record is excluded via meta.accepted_divergences in the alignment test."
|
|
},
|
|
"items": [
|
|
{
|
|
"text": "# 产品指南",
|
|
"doc_type_kwd": "text"
|
|
},
|
|
{
|
|
"text": "第一步：打开应用。第二步：点击设置完成配置。",
|
|
"doc_type_kwd": "text"
|
|
},
|
|
{
|
|
"text": "<table>\n<tr><th>姓名</th><th>年龄</th></tr>\n<tr><td>张三</td><td>30</td></tr>\n<tr><td>李四</td><td>25</td></tr>\n</table>",
|
|
"doc_type_kwd": "text"
|
|
},
|
|
{
|
|
"text": "## 使用条款",
|
|
"doc_type_kwd": "text"
|
|
},
|
|
{
|
|
"text": "欢迎使用我们的智能助手，它能帮你快速完成任务。",
|
|
"doc_type_kwd": "text"
|
|
}
|
|
]
|
|
}
|