|
|
@@ -1239,11 +1239,13 @@ main() {
|
|
|
|
|
|
e2e)
|
|
|
# 完整端到端测试
|
|
|
+ # 注意:上传后会自动触发 RAG向量化、结构化解析、NER提取
|
|
|
check_test_file
|
|
|
check_service
|
|
|
register_test_user
|
|
|
|
|
|
- print_header "步骤 1/4: 文件上传"
|
|
|
+ print_header "步骤 1/3: 文件上传"
|
|
|
+ print_info "上传后将自动触发: RAG向量化 + 结构化解析 + NER提取"
|
|
|
test_upload
|
|
|
|
|
|
if [ -z "$DOCUMENT_ID" ] && [ -f "${SCRIPT_DIR}/.last_document_id" ]; then
|
|
|
@@ -1255,34 +1257,31 @@ main() {
|
|
|
exit 1
|
|
|
fi
|
|
|
|
|
|
- print_header "步骤 2/4: 等待解析完成"
|
|
|
+ print_header "步骤 2/3: 等待解析完成"
|
|
|
if ! poll_parse_status "$DOCUMENT_ID" 60 3; then
|
|
|
print_error "解析未完成,终止测试"
|
|
|
exit 1
|
|
|
fi
|
|
|
|
|
|
- print_header "步骤 3/4: 向量提取"
|
|
|
- if get_document_text "$DOCUMENT_ID"; then
|
|
|
- test_vector_extraction "$DOCUMENT_ID" "$DOCUMENT_TEXT"
|
|
|
- else
|
|
|
- print_info "跳过向量提取(无法获取文本)"
|
|
|
- fi
|
|
|
-
|
|
|
- print_header "步骤 4/5: NER 提取"
|
|
|
- test_ner_extraction "$DOCUMENT_ID"
|
|
|
-
|
|
|
- print_header "步骤 5/5: 结构化解析"
|
|
|
- test_structured_extraction "$DOCUMENT_ID"
|
|
|
-
|
|
|
- # 等待自动处理完成
|
|
|
- print_info "等待后台自动处理完成 (5秒)..."
|
|
|
- sleep 5
|
|
|
+ # 等待自动处理完成(RAG + 结构化解析 + NER)
|
|
|
+ # NER 可能需要较长时间(约4-5分钟),这里先等待一小段时间查看初始结果
|
|
|
+ print_header "步骤 3/3: 等待后台自动处理并查看结果"
|
|
|
+ print_info "后台正在自动执行: RAG向量化、结构化解析、NER提取"
|
|
|
+ print_info "NER 提取可能需要几分钟,可稍后使用 -g 查看 GraphNode 列表"
|
|
|
+ print_info "等待 10 秒后查看初始结果..."
|
|
|
+ sleep 10
|
|
|
|
|
|
- # 获取 GraphNode 列表
|
|
|
- print_header "步骤 6/6: 查看处理结果"
|
|
|
- test_get_graph_nodes "$DOCUMENT_ID"
|
|
|
+ # 查看结构化解析结果(通常很快完成)
|
|
|
+ print_step "查看结构化解析结果"
|
|
|
test_get_images "$DOCUMENT_ID"
|
|
|
test_get_tables "$DOCUMENT_ID"
|
|
|
+
|
|
|
+ # 查看 GraphNode(如果 NER 还未完成,可能为空)
|
|
|
+ print_step "查看 GraphNode 列表 (NER 结果)"
|
|
|
+ test_get_graph_nodes "$DOCUMENT_ID"
|
|
|
+
|
|
|
+ print_info ""
|
|
|
+ print_info "提示: NER 提取需要几分钟,可稍后运行 '$0 -g' 查看完整结果"
|
|
|
;;
|
|
|
esac
|
|
|
|