#include "PdfTools_Types.h"
#include "PdfTools_PdfToolsSys.h"

Macros
#define	PDFTOOLS_CALL

Functions
PDFTOOLS_EXPORT TPdfToolsExtraction_TextOptions *PDFTOOLS_CALL	PdfToolsExtraction_TextOptions_New (void)

PDFTOOLS_EXPORT TPdfToolsExtraction_TextExtractionFormat PDFTOOLS_CALL	PdfToolsExtraction_TextOptions_GetExtractionFormat (TPdfToolsExtraction_TextOptions *pTextOptions)
	Format of the extracted text.

PDFTOOLS_EXPORT BOOL PDFTOOLS_CALL	PdfToolsExtraction_TextOptions_SetExtractionFormat (TPdfToolsExtraction_TextOptions *pTextOptions, TPdfToolsExtraction_TextExtractionFormat iExtractionFormat)
	Format of the extracted text.

PDFTOOLS_EXPORT BOOL PDFTOOLS_CALL	PdfToolsExtraction_TextOptions_GetAdvanceWidth (TPdfToolsExtraction_TextOptions pTextOptions, double pAdvanceWidth)

PDFTOOLS_EXPORT BOOL PDFTOOLS_CALL	PdfToolsExtraction_TextOptions_SetAdvanceWidth (TPdfToolsExtraction_TextOptions pTextOptions, const double pAdvanceWidth)

PDFTOOLS_EXPORT BOOL PDFTOOLS_CALL	PdfToolsExtraction_TextOptions_GetLineHeight (TPdfToolsExtraction_TextOptions pTextOptions, double pLineHeight)

PDFTOOLS_EXPORT BOOL PDFTOOLS_CALL	PdfToolsExtraction_TextOptions_SetLineHeight (TPdfToolsExtraction_TextOptions pTextOptions, const double pLineHeight)

PDFTOOLS_EXPORT double PDFTOOLS_CALL	PdfToolsExtraction_TextOptions_GetWordSeparationFactor (TPdfToolsExtraction_TextOptions *pTextOptions)

PDFTOOLS_EXPORT BOOL PDFTOOLS_CALL	PdfToolsExtraction_TextOptions_SetWordSeparationFactor (TPdfToolsExtraction_TextOptions *pTextOptions, double dWordSeparationFactor)

PDFTOOLS_EXPORT TPdfToolsExtraction_Extractor *PDFTOOLS_CALL	PdfToolsExtraction_Extractor_New (void)

PDFTOOLS_EXPORT BOOL PDFTOOLS_CALL	PdfToolsExtraction_Extractor_ExtractText (TPdfToolsExtraction_Extractor pExtractor, TPdfToolsPdf_Document pInDoc, const TPdfToolsSys_StreamDescriptor pOutStreamDesc, TPdfToolsExtraction_TextOptions pOptions, const int pFirstPage, const int pLastPage)
	Extract text from a PDF document.

Macro Definition Documentation

◆ PDFTOOLS_CALL

#define PDFTOOLS_CALL

Function Documentation

◆ PdfToolsExtraction_Extractor_ExtractText()

PDFTOOLS_EXPORT BOOL PDFTOOLS_CALL PdfToolsExtraction_Extractor_ExtractText	(	TPdfToolsExtraction_Extractor *	pExtractor,
		TPdfToolsPdf_Document *	pInDoc,
		const TPdfToolsSys_StreamDescriptor *	pOutStreamDesc,
		TPdfToolsExtraction_TextOptions *	pOptions,
		const int *	pFirstPage,
		const int *	pLastPage )

Extract text from a PDF document.

Parameters

[in,out]	pExtractor	Acts as a handle to the native object of type TPdfToolsExtraction_Extractor.
[in,out]	pInDoc	The input PDF document.
[in,out]	pOutStreamDesc	The stream to which output file the extracted text is written.
[in,out]	pOptions	The option object that controls the text extraction.
[in]	pFirstPage	Optional parameter denoting the index of the first page to be copied. This index is one-based. If set, the number must be in the range of `1` (first page) to PdfToolsPdf_Document_GetPageCount (last page). If not set, `1` is used.
[in]	pLastPage	Optional parameter denoting the index of the last page to be copied. This index is one-based. If set, the number must be in the range of `1` (first page) to PdfToolsPdf_Document_GetPageCount (last page). If not set, PdfToolsPdf_Document_GetPageCount is used.

Returns: TRUE if the operation is successful; FALSE if there is an error.

Note

An error occurred when FALSE was returned. Retrieve specific error code by calling PdfTools_GetLastError. Get the error message with PdfTools_GetLastErrorMessage. Possible error codes:

ePdfTools_Error_License The license check has failed.
ePdfTools_Error_Processing The processing has failed.
ePdfTools_Error_IO Writing to the output text file has failed.
ePdfTools_Error_Generic A generic error occurred.
ePdfTools_Error_IllegalArgument The pFirstPage or pLastPage are not in the allowed range.

◆ PdfToolsExtraction_Extractor_New()

PDFTOOLS_EXPORT TPdfToolsExtraction_Extractor *PDFTOOLS_CALL PdfToolsExtraction_Extractor_New ( void )

Returns: Handle to the newly created native object.

NULL if there is an error.

Note: An error occurred when NULL was returned. Retrieve specific error code by calling PdfTools_GetLastError. Get the error message with PdfTools_GetLastErrorMessage.

◆ PdfToolsExtraction_TextOptions_GetAdvanceWidth()

PDFTOOLS_EXPORT BOOL PDFTOOLS_CALL PdfToolsExtraction_TextOptions_GetAdvanceWidth	(	TPdfToolsExtraction_TextOptions *	pTextOptions,
		double *	pAdvanceWidth )

The horizontal space in a PDF that corresponds to a character in monospaced text output.

If NULL, the horizontal space is 7.2pt.

Default value: NULL

Parameters

[in,out]	pTextOptions	Acts as a handle to the native object of type TPdfToolsExtraction_TextOptions.
[out]	pAdvanceWidth	Retrieved value.

Returns: FALSE if either an error occurred or the [out] argument returns NULL. To determine if an error has occurred, check the error code as described in the note section below.

Note: An error occurred when FALSE was returned and the error code returned by PdfTools_GetLastError is different from ePdfTools_Error_Success. Get the error message with PdfTools_GetLastErrorMessage.

◆ PdfToolsExtraction_TextOptions_GetExtractionFormat()

PDFTOOLS_EXPORT TPdfToolsExtraction_TextExtractionFormat PDFTOOLS_CALL PdfToolsExtraction_TextOptions_GetExtractionFormat ( TPdfToolsExtraction_TextOptions * pTextOptions )

Format of the extracted text.

Specifies the format of the extracted text.

Default value: ePdfToolsExtraction_TextExtractionFormat_DocumentOrder

Parameters

[in,out] pTextOptions Acts as a handle to the native object of type TPdfToolsExtraction_TextOptions.

Returns: Retrieved value.

May indicate an error in certain scenarios. For further information see the note section below.

Note: An error occurred when 0 was returned. Retrieve specific error code by calling PdfTools_GetLastError. Get the error message with PdfTools_GetLastErrorMessage.

◆ PdfToolsExtraction_TextOptions_GetLineHeight()

PDFTOOLS_EXPORT BOOL PDFTOOLS_CALL PdfToolsExtraction_TextOptions_GetLineHeight	(	TPdfToolsExtraction_TextOptions *	pTextOptions,
		double *	pLineHeight )

The vertical space in a PDF that triggers a new line in monospaced text output.

If NULL, no extra blank lines are added in the text output.

Default value: NULL

Parameters

[in,out]	pTextOptions	Acts as a handle to the native object of type TPdfToolsExtraction_TextOptions.
[out]	pLineHeight	Retrieved value.

Returns: FALSE if either an error occurred or the [out] argument returns NULL. To determine if an error has occurred, check the error code as described in the note section below.

Note: An error occurred when FALSE was returned and the error code returned by PdfTools_GetLastError is different from ePdfTools_Error_Success. Get the error message with PdfTools_GetLastErrorMessage.

◆ PdfToolsExtraction_TextOptions_GetWordSeparationFactor()

PDFTOOLS_EXPORT double PDFTOOLS_CALL PdfToolsExtraction_TextOptions_GetWordSeparationFactor ( TPdfToolsExtraction_TextOptions * pTextOptions )

This parameter defines a factor multiplied by the width of the space character to determine word boundaries. If the distance between two characters exceeds this calculated value, it is recognized as a word separation.

Default value: 0.3

Parameters

[in,out] pTextOptions Acts as a handle to the native object of type TPdfToolsExtraction_TextOptions.

Returns: Retrieved value.

May indicate an error in certain scenarios. For further information see the note section below.

Note

An error occurred when -1.0 was returned. Retrieve specific error code by calling PdfTools_GetLastError. Get the error message with PdfTools_GetLastErrorMessage. Possible error codes:

ePdfTools_Error_IllegalArgument The word separation factor is invalid.

◆ PdfToolsExtraction_TextOptions_New()

PDFTOOLS_EXPORT TPdfToolsExtraction_TextOptions *PDFTOOLS_CALL PdfToolsExtraction_TextOptions_New ( void )

Returns: Handle to the newly created native object.

NULL if there is an error.

Note: An error occurred when NULL was returned. Retrieve specific error code by calling PdfTools_GetLastError. Get the error message with PdfTools_GetLastErrorMessage.

◆ PdfToolsExtraction_TextOptions_SetAdvanceWidth()

PDFTOOLS_EXPORT BOOL PDFTOOLS_CALL PdfToolsExtraction_TextOptions_SetAdvanceWidth	(	TPdfToolsExtraction_TextOptions *	pTextOptions,
		const double *	pAdvanceWidth )

The horizontal space in a PDF that corresponds to a character in monospaced text output.

If NULL, the horizontal space is 7.2pt.

Default value: NULL

Parameters

[in,out]	pTextOptions	Acts as a handle to the native object of type TPdfToolsExtraction_TextOptions.
[in]	pAdvanceWidth	Set value.

Returns: TRUE if the operation is successful; FALSE if there is an error.

Note: An error occurred when FALSE was returned. Retrieve specific error code by calling PdfTools_GetLastError. Get the error message with PdfTools_GetLastErrorMessage.

◆ PdfToolsExtraction_TextOptions_SetExtractionFormat()

PDFTOOLS_EXPORT BOOL PDFTOOLS_CALL PdfToolsExtraction_TextOptions_SetExtractionFormat	(	TPdfToolsExtraction_TextOptions *	pTextOptions,
		TPdfToolsExtraction_TextExtractionFormat	iExtractionFormat )

Format of the extracted text.

Specifies the format of the extracted text.

Default value: ePdfToolsExtraction_TextExtractionFormat_DocumentOrder

Parameters

[in,out]	pTextOptions	Acts as a handle to the native object of type TPdfToolsExtraction_TextOptions.
[in]	iExtractionFormat	Set value.

Returns: TRUE if the operation is successful; FALSE if there is an error.

Note: An error occurred when FALSE was returned. Retrieve specific error code by calling PdfTools_GetLastError. Get the error message with PdfTools_GetLastErrorMessage.

◆ PdfToolsExtraction_TextOptions_SetLineHeight()

PDFTOOLS_EXPORT BOOL PDFTOOLS_CALL PdfToolsExtraction_TextOptions_SetLineHeight	(	TPdfToolsExtraction_TextOptions *	pTextOptions,
		const double *	pLineHeight )

The vertical space in a PDF that triggers a new line in monospaced text output.

If NULL, no extra blank lines are added in the text output.

Default value: NULL

Parameters

[in,out]	pTextOptions	Acts as a handle to the native object of type TPdfToolsExtraction_TextOptions.
[in]	pLineHeight	Set value.

Returns: TRUE if the operation is successful; FALSE if there is an error.

Note: An error occurred when FALSE was returned. Retrieve specific error code by calling PdfTools_GetLastError. Get the error message with PdfTools_GetLastErrorMessage.

◆ PdfToolsExtraction_TextOptions_SetWordSeparationFactor()

PDFTOOLS_EXPORT BOOL PDFTOOLS_CALL PdfToolsExtraction_TextOptions_SetWordSeparationFactor	(	TPdfToolsExtraction_TextOptions *	pTextOptions,
		double	dWordSeparationFactor )

This parameter defines a factor multiplied by the width of the space character to determine word boundaries. If the distance between two characters exceeds this calculated value, it is recognized as a word separation.

Default value: 0.3

Parameters

[in,out]	pTextOptions	Acts as a handle to the native object of type TPdfToolsExtraction_TextOptions.
[in]	dWordSeparationFactor	Set value.

Returns: TRUE if the operation is successful; FALSE if there is an error.

Note

An error occurred when FALSE was returned. Retrieve specific error code by calling PdfTools_GetLastError. Get the error message with PdfTools_GetLastErrorMessage. Possible error codes:

ePdfTools_Error_IllegalArgument The word separation factor is invalid.

Macros

Functions

Macro Definition Documentation

◆ PDFTOOLS_CALL

Function Documentation

◆ PdfToolsExtraction_Extractor_ExtractText()

◆ PdfToolsExtraction_Extractor_New()

◆ PdfToolsExtraction_TextOptions_GetAdvanceWidth()

◆ PdfToolsExtraction_TextOptions_GetExtractionFormat()

◆ PdfToolsExtraction_TextOptions_GetLineHeight()

◆ PdfToolsExtraction_TextOptions_GetWordSeparationFactor()

◆ PdfToolsExtraction_TextOptions_New()

◆ PdfToolsExtraction_TextOptions_SetAdvanceWidth()

◆ PdfToolsExtraction_TextOptions_SetExtractionFormat()

◆ PdfToolsExtraction_TextOptions_SetLineHeight()

◆ PdfToolsExtraction_TextOptions_SetWordSeparationFactor()