content_type.h

/*********************************************************************************************************************************************/
/*  DocWire SDK: Award-winning modern data processing in C++20. SourceForge Community Choice & Microsoft support. AI-driven processing.      */
/*  Supports nearly 100 data formats, including email boxes and OCR. Boost efficiency in text extraction, web data extraction, data mining,  */
/*  document analysis. Offline processing possible for security and confidentiality                                                          */
/*                                                                                                                                           */
/*  Copyright (c) SILVERCODERS Ltd, http://silvercoders.com                                                                                  */
/*  Project homepage: https://github.com/docwire/docwire                                                                                     */
/*                                                                                                                                           */
/*  SPDX-License-Identifier: AGPL-3.0-only OR LicenseRef-DocWire-Commercial                                                                  */
/*********************************************************************************************************************************************/
 
#ifndef DOCWIRE_CONTENT_TYPE_H
#define DOCWIRE_CONTENT_TYPE_H
 
#include "chain_element.h"
#include "content_type_by_signature.h"
#include "ref_or_owned.h"
 
namespace docwire::content_type
{
 
DOCWIRE_CONTENT_TYPE_EXPORT void detect(data_source& data, const by_signature::database& signatures_db_to_use = by_signature::database{});
 
class detector : public chain_element
{
public:
 
    detector(ref_or_owned<by_signature::database> signatures_db_to_use = by_signature::database{})
        : m_signatures_db_to_use(signatures_db_to_use) {}
 
    continuation operator()(message_ptr msg, const message_callbacks& emit_message) override
    {
        try
        {
            if (msg->is<data_source>())
            {
                data_source& data = msg->get<data_source>();
                content_type::detect(data, m_signatures_db_to_use.get());
            }
            else if (msg->is<document::image>())
            {
                data_source& data = msg->get<document::image>().source;
                content_type::detect(data, m_signatures_db_to_use.get());
            }
        }
        catch (const std::exception& e)
        {
            emit_message(make_nested_ptr(std::current_exception(), DOCWIRE_MAKE_ERROR("Content type detection failed")));
        }
        return emit_message(std::move(msg));
    }
 
    bool is_leaf() const override
    {
        return false;
    }
 
private:
    ref_or_owned<by_signature::database> m_signatures_db_to_use;
};
 
} // namespace docwire::content_type
 
#endif // DOCWIRE_CONTENT_TYPE