Pdftools SDK
Loading...
Searching...
No Matches
include
PdfTools_PdfToolsExtraction.h
Go to the documentation of this file.
1
/******************************************************************************
2
*
3
* File: PdfTools_PdfToolsExtraction.h
4
*
5
* Description: Sub Header file for Pdftools SDK
6
*
7
* Author: PDF Tools AG
8
*
9
* Copyright: Copyright (C) 2023 - 2025 PDF Tools AG, Switzerland
10
* All rights reserved.
11
*
12
* Notice: By downloading and using this artifact, you accept PDF Tools AG's
13
* [license agreement](https://www.pdf-tools.com/license-agreement/),
14
* [privacy policy](https://www.pdf-tools.com/privacy-policy/),
15
* and allow PDF Tools AG to track your usage data.
16
*
17
*****************************************************************************/
18
19
#ifndef PDFTOOLS_PDFTOOLSEXTRACTION_H__
20
#define PDFTOOLS_PDFTOOLSEXTRACTION_H__
21
22
#ifndef PDFTOOLS_CALL
23
#if defined(WIN32)
24
#define PDFTOOLS_CALL __stdcall
25
#else
26
#define PDFTOOLS_CALL
27
#endif
28
#endif
29
30
#include "
PdfTools_Types.h
"
31
#include "
PdfTools_PdfToolsSys.h
"
32
33
#ifdef __cplusplus
34
extern
"C"
35
{
36
#endif
37
38
#ifdef _UNICODE
39
#else
40
#endif
41
42
/******************************************************************************
43
* TextOptions
44
*****************************************************************************/
53
PDFTOOLS_EXPORT
TPdfToolsExtraction_TextOptions
*
PDFTOOLS_CALL
PdfToolsExtraction_TextOptions_New
(
void
);
54
72
PDFTOOLS_EXPORT
TPdfToolsExtraction_TextExtractionFormat
PDFTOOLS_CALL
73
PdfToolsExtraction_TextOptions_GetExtractionFormat
(
TPdfToolsExtraction_TextOptions
* pTextOptions);
92
PDFTOOLS_EXPORT
BOOL
PDFTOOLS_CALL
PdfToolsExtraction_TextOptions_SetExtractionFormat
(
93
TPdfToolsExtraction_TextOptions
* pTextOptions,
TPdfToolsExtraction_TextExtractionFormat
iExtractionFormat);
114
PDFTOOLS_EXPORT
BOOL
PDFTOOLS_CALL
115
PdfToolsExtraction_TextOptions_GetAdvanceWidth
(
TPdfToolsExtraction_TextOptions
* pTextOptions,
double
* pAdvanceWidth);
135
PDFTOOLS_EXPORT
BOOL
PDFTOOLS_CALL
PdfToolsExtraction_TextOptions_SetAdvanceWidth
(
136
TPdfToolsExtraction_TextOptions
* pTextOptions,
const
double
* pAdvanceWidth);
157
PDFTOOLS_EXPORT
BOOL
PDFTOOLS_CALL
158
PdfToolsExtraction_TextOptions_GetLineHeight
(
TPdfToolsExtraction_TextOptions
* pTextOptions,
double
* pLineHeight);
178
PDFTOOLS_EXPORT
BOOL
PDFTOOLS_CALL
179
PdfToolsExtraction_TextOptions_SetLineHeight
(
TPdfToolsExtraction_TextOptions
* pTextOptions,
const
double
* pLineHeight);
200
PDFTOOLS_EXPORT
double
PDFTOOLS_CALL
201
PdfToolsExtraction_TextOptions_GetWordSeparationFactor
(
TPdfToolsExtraction_TextOptions
* pTextOptions);
223
PDFTOOLS_EXPORT
BOOL
PDFTOOLS_CALL
PdfToolsExtraction_TextOptions_SetWordSeparationFactor
(
224
TPdfToolsExtraction_TextOptions
* pTextOptions,
double
dWordSeparationFactor);
225
226
/******************************************************************************
227
* Extractor
228
*****************************************************************************/
237
PDFTOOLS_EXPORT
TPdfToolsExtraction_Extractor
*
PDFTOOLS_CALL
PdfToolsExtraction_Extractor_New
(
void
);
238
275
PDFTOOLS_EXPORT
BOOL
PDFTOOLS_CALL
PdfToolsExtraction_Extractor_ExtractText
(
276
TPdfToolsExtraction_Extractor
* pExtractor,
TPdfToolsPdf_Document
* pInDoc,
277
const
TPdfToolsSys_StreamDescriptor
* pOutStreamDesc,
TPdfToolsExtraction_TextOptions
* pOptions,
278
const
int
* pFirstPage,
const
int
* pLastPage);
279
280
#ifdef __cplusplus
281
}
282
#endif
283
284
#endif
/* PDFTOOLS_PDFTOOLSEXTRACTION_H__ */
PdfToolsExtraction_TextOptions_SetAdvanceWidth
PDFTOOLS_EXPORT BOOL PDFTOOLS_CALL PdfToolsExtraction_TextOptions_SetAdvanceWidth(TPdfToolsExtraction_TextOptions *pTextOptions, const double *pAdvanceWidth)
PdfToolsExtraction_TextOptions_GetExtractionFormat
PDFTOOLS_EXPORT TPdfToolsExtraction_TextExtractionFormat PDFTOOLS_CALL PdfToolsExtraction_TextOptions_GetExtractionFormat(TPdfToolsExtraction_TextOptions *pTextOptions)
Format of the extracted text.
PdfToolsExtraction_TextOptions_GetAdvanceWidth
PDFTOOLS_EXPORT BOOL PDFTOOLS_CALL PdfToolsExtraction_TextOptions_GetAdvanceWidth(TPdfToolsExtraction_TextOptions *pTextOptions, double *pAdvanceWidth)
PdfToolsExtraction_Extractor_New
PDFTOOLS_EXPORT TPdfToolsExtraction_Extractor *PDFTOOLS_CALL PdfToolsExtraction_Extractor_New(void)
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.
PdfToolsExtraction_TextOptions_SetExtractionFormat
PDFTOOLS_EXPORT BOOL PDFTOOLS_CALL PdfToolsExtraction_TextOptions_SetExtractionFormat(TPdfToolsExtraction_TextOptions *pTextOptions, TPdfToolsExtraction_TextExtractionFormat iExtractionFormat)
Format of the extracted text.
PdfToolsExtraction_TextOptions_GetLineHeight
PDFTOOLS_EXPORT BOOL PDFTOOLS_CALL PdfToolsExtraction_TextOptions_GetLineHeight(TPdfToolsExtraction_TextOptions *pTextOptions, double *pLineHeight)
PdfToolsExtraction_TextOptions_SetLineHeight
PDFTOOLS_EXPORT BOOL PDFTOOLS_CALL PdfToolsExtraction_TextOptions_SetLineHeight(TPdfToolsExtraction_TextOptions *pTextOptions, const double *pLineHeight)
PdfToolsExtraction_TextOptions_New
PDFTOOLS_EXPORT TPdfToolsExtraction_TextOptions *PDFTOOLS_CALL PdfToolsExtraction_TextOptions_New(void)
PDFTOOLS_CALL
#define PDFTOOLS_CALL
Definition
PdfTools_PdfToolsExtraction.h:26
PdfToolsExtraction_TextOptions_SetWordSeparationFactor
PDFTOOLS_EXPORT BOOL PDFTOOLS_CALL PdfToolsExtraction_TextOptions_SetWordSeparationFactor(TPdfToolsExtraction_TextOptions *pTextOptions, double dWordSeparationFactor)
PdfToolsExtraction_TextOptions_GetWordSeparationFactor
PDFTOOLS_EXPORT double PDFTOOLS_CALL PdfToolsExtraction_TextOptions_GetWordSeparationFactor(TPdfToolsExtraction_TextOptions *pTextOptions)
PdfTools_PdfToolsSys.h
PDFTOOLS_EXPORT
#define PDFTOOLS_EXPORT
Definition
PdfTools_Platform.h:143
PdfTools_Types.h
TPdfToolsExtraction_TextExtractionFormat
TPdfToolsExtraction_TextExtractionFormat
Definition
PdfTools_Types.h:1782
BOOL
#define BOOL
Definition
PdfTools_Types.h:23
TPdfToolsExtraction_Extractor
TPdfToolsExtraction_TextOptions
Options for text extraction This class specifies the details of text extraction.
TPdfToolsPdf_Document
The PDF document PDF documents are either opened using PdfToolsPdf_Document_Open or the result of an ...
TPdfToolsSys_StreamDescriptor
Structure that groups a set of callbacks that model streams.
Definition
PdfTools_PdfToolsSys.h:49
Generated by
1.10.0