formatting_style.h

/***************************************************************************************************************************************************/
/*  DocToText - A multifaceted, data extraction software development toolkit that converts all sorts of files to plain text and html.              */
/*  Written in C++, this data extraction tool has a parser able to convert PST & OST files along with a brand new API for better file processing.  */
/*  To enhance its utility, DocToText, as a data extraction tool, can be integrated with other data mining and data analytics applications.        */
/*  It comes equipped with a high grade, scriptable and trainable OCR that has LSTM neural networks based character recognition.                   */
/*                                                                                                                                                 */
/*  This document parser is able to extract metadata along with annotations and supports a list of formats that include:                           */
/*  DOC, XLS, XLSB, PPT, RTF, ODF (ODT, ODS, ODP), OOXML (DOCX, XLSX, PPTX), iWork (PAGES, NUMBERS, KEYNOTE), ODFXML (FODP, FODS, FODT),           */
/*  PDF, EML, HTML, Outlook (PST, OST), Image (JPG, JPEG, JFIF, BMP, PNM, PNG, TIFF, WEBP) and DICOM (DCM)                                         */
/*                                                                                                                                                 */
/*  Copyright (c) SILVERCODERS Ltd                                                                                                                 */
/*  http://silvercoders.com                                                                                                                        */
/*                                                                                                                                                 */
/*  Project homepage:                                                                                                                              */
/*  http://silvercoders.com/en/products/doctotext                                                                                                  */
/*  https://www.docwire.io/                                                                                                                        */
/*                                                                                                                                                 */
/*  The GNU General Public License version 2 as published by the Free Software Foundation and found in the file COPYING.GPL permits                */
/*  the distribution and/or modification of this application.                                                                                      */
/*                                                                                                                                                 */
/*  Please keep in mind that any attempt to circumvent the terms of the GNU General Public License by employing wrappers, pipelines,               */
/*  client/server protocols, etc. is illegal. You must purchase a commercial license if your program, which is distributed under a license         */
/*  other than the GNU General Public License version 2, directly or indirectly calls any portion of this code.                                    */
/*  Simply stop using the product if you disagree with this viewpoint.                                                                             */
/*                                                                                                                                                 */
/*  According to the terms of the license provided by SILVERCODERS and included in the file COPYING.COM, licensees in possession of                */
/*  a current commercial license for this product may use this file.                                                                               */
/*                                                                                                                                                 */
/*  This program is provided WITHOUT ANY WARRANTY, not even the implicit warranty of merchantability or fitness for a particular purpose.          */
/*  It is supplied in the hope that it will be useful.                                                                                             */
/***************************************************************************************************************************************************/
 
#ifndef DOCTOTEXT_FORMATTING_STYLE_H
#define DOCTOTEXT_FORMATTING_STYLE_H
 
#include <string>
#include "defines.h"
 
namespace doctotext
{
    enum TableStyle { TABLE_STYLE_TABLE_LOOK, TABLE_STYLE_ONE_ROW, TABLE_STYLE_ONE_COL, };
    enum UrlStyle { URL_STYLE_TEXT_ONLY, URL_STYLE_EXTENDED, URL_STYLE_UNDERSCORED, };
 
    class DllExport ListStyle
    {
        private:
            struct Implementation;
            Implementation* m_impl;
 
        public:
            ListStyle();
            ~ListStyle();
            ListStyle(const ListStyle& style);
            ListStyle& operator = (const ListStyle& style);
            void setPrefix(const std::string& prefix);
            void setPrefix(const char* prefix);
            const char* getPrefix() const;
    };
 
    struct FormattingStyle
    {
        FormattingStyle()
        : table_style(TABLE_STYLE_TABLE_LOOK), url_style(URL_STYLE_EXTENDED)
        {}
        FormattingStyle(const TableStyle &tableStyle, const UrlStyle &urlStyle)
            : table_style(tableStyle), url_style(urlStyle)
        {}
        TableStyle table_style;
        UrlStyle url_style;
        ListStyle list_style;
    };
 
    enum class Language 
    {
        english,
        spanish,
        russian,
        polish,
    };
    DllExport std::string languageToName(const Language lang);
    DllExport Language nameToLanguage(const std::string& name);
 
    enum XmlParseMode { PARSE_XML, FIX_XML, STRIP_XML };
} // namespace doctotext
 
#endif