// This file is autogenerated: please see the codegen template "Options" #ifndef PDFTRON_H_CPPPDFDataExtractionOptions #define PDFTRON_H_CPPPDFDataExtractionOptions #include namespace pdftron{ namespace PDF{ class DataExtractionOptions : public OptionsBase { public: DataExtractionOptions(); ~DataExtractionOptions(); /** * Gets the value DeepLearningAssist from the options object. * Specifies if Deep Learning is used with table recognition in the * DocStructure engine. The default is false. When true, table * recognition accuracy improves at the cost of increased processing * time. This only affects the DocStructure engine. * @return The current value for DeepLearningAssist. */ bool GetDeepLearningAssist(); /** * Sets the value for DeepLearningAssist in the options object. * Specifies if Deep Learning is used with table recognition in the * DocStructure engine. The default is false. When true, table * recognition accuracy improves at the cost of increased processing * time. This only affects the DocStructure engine. * @param value The new value for DeepLearningAssist. * @return This object, for call chaining. */ DataExtractionOptions& SetDeepLearningAssist(bool value); /** * Adds the value to the ExclusionZonesForPage array. * Optional list of page areas to be excluded from analysis. Zones should * be provided as a collection of Rects paired with a page number. The * Rects are then applied to the corresponding page. Rects are specified * in User Space coordinates. If this is set, the specified areas will * not be analyzed. If neither this nor InclusionZonesForPage is set, * the entire page will be analyzed. This option only affects the * GenericKeyValue, FormKeyValue, and FormField engines. * @param value List of page areas to be excluded from analysis. * @param page_num The page number (1-indexed) to which the regions are applied. * @return This object, for call chaining. */ DataExtractionOptions& AddExclusionZonesForPage(RectCollection& value, int page_num); /** * Gets the value FormExtractionEngine from the options object. * Specifies the form extraction engine used in * DetectAndAddFormFieldsToPDF, either 'Form' or 'FormKeyValue'. The * default is 'Form'. * @return The current value for FormExtractionEngine. */ UString GetFormExtractionEngine(); /** * Sets the value for FormExtractionEngine in the options object. * Specifies the form extraction engine used in * DetectAndAddFormFieldsToPDF, either 'Form' or 'FormKeyValue'. The * default is 'Form'. * @param value The new value for FormExtractionEngine. * @return This object, for call chaining. */ DataExtractionOptions& SetFormExtractionEngine(const UString& value); /** * Adds the value to the InclusionZonesForPage array. * Optional list of page areas to be included in analysis (to the * exclusion of all other areas). Zones should be provided as a * collection of Rects paired with a page number. The Rects are then * applied to the corresponding page. Rects are specified in User Space * coordinates. If this is set, only the areas specified will be * analyzed. If neither this nor ExclusionZonesForPage is set, the entire * page will be analyzed. This option only affects the GenericKeyValue, * FormKeyValue, and FormField engines. * @param value List of page areas to be included in analysis. * @param page_num The page number (1-indexed) to which the regions are applied. * @return This object, for call chaining. */ DataExtractionOptions& AddInclusionZonesForPage(RectCollection& value, int page_num); /** * Gets the value Language from the options object. * Specifies the OCR language(s). Use 3-letter ISO 639-2 language codes, * separated by spaces. Example: "eng deu spa fra". The default is * English. * @return The current value for Language. */ UString GetLanguage(); /** * Sets the value for Language in the options object. * Specifies the OCR language(s). Use 3-letter ISO 639-2 language codes, * separated by spaces. Example: "eng deu spa fra". The default is * English. * @param value The new value for Language. * @return This object, for call chaining. */ DataExtractionOptions& SetLanguage(const UString& value); /** * Gets the value OverlappingFormFieldBehavior from the options object. * When a detected form field overlaps with an existing one, keep either * the old field (value 'KeepOld'), or the new one (value 'KeepNew', * default). * @return The current value for OverlappingFormFieldBehavior. */ UString GetOverlappingFormFieldBehavior(); /** * Sets the value for OverlappingFormFieldBehavior in the options object. * When a detected form field overlaps with an existing one, keep either * the old field (value 'KeepOld'), or the new one (value 'KeepNew', * default). * @param value The new value for OverlappingFormFieldBehavior. * @return This object, for call chaining. */ DataExtractionOptions& SetOverlappingFormFieldBehavior(const UString& value); /** * Gets the value PDFPassword from the options object. * Specifies the password if the PDF requires one. The default is no * password. * @return The current value for PDFPassword. */ UString GetPDFPassword(); /** * Sets the value for PDFPassword in the options object. * Specifies the password if the PDF requires one. The default is no * password. * @param value The new value for PDFPassword. * @return This object, for call chaining. */ DataExtractionOptions& SetPDFPassword(const UString& value); /** * Gets the value Pages from the options object. * Specifies a range of pages to be converted, such as "1-5". By default * all pages are converted. The first page has the page number of 1. * @return The current value for Pages. */ UString GetPages(); /** * Sets the value for Pages in the options object. * Specifies a range of pages to be converted, such as "1-5". By default * all pages are converted. The first page has the page number of 1. * @param value The new value for Pages. * @return This object, for call chaining. */ DataExtractionOptions& SetPages(const UString& value); }; } } #include "../Impl/DataExtractionOptions.inl" #endif // PDFTRON_H_CPPPDFDataExtractionOptions