![]() |
#include <TextExtractor.h>
Public Member Functions | |
int | GetNumWords () |
bool | IsSimpleLine () |
const double * | GetBBox () |
void | GetQuad (double out_quad[8]) |
Word | GetFirstWord () |
Word | GetWord (int word_idx) |
Line | GetNextLine () |
int | GetCurrentNum () |
Style | GetStyle () |
int | GetParagraphID () |
int | GetFlowID () |
bool | EndsWithHyphen () |
bool | IsValid () |
bool | operator== (const Line &) |
bool | operator!= (const Line &) |
Line () |
Each line consists of a sequence of words, and each words in one or more styles.
pdftron::PDF::TextExtractor::Line::Line | ( | ) |
int pdftron::PDF::TextExtractor::Line::GetNumWords | ( | ) |
bool pdftron::PDF::TextExtractor::Line::IsSimpleLine | ( | ) |
const double* pdftron::PDF::TextExtractor::Line::GetBBox | ( | ) |
out_bbox | The bounding box for this line (in unrotated page coordinates). |
void pdftron::PDF::TextExtractor::Line::GetQuad | ( | double | out_quad[8] | ) |
out_quad | The quadrilateral representing a tight bounding box for this line (in unrotated page coordinates). |
Word pdftron::PDF::TextExtractor::Line::GetFirstWord | ( | ) |
Word pdftron::PDF::TextExtractor::Line::GetWord | ( | int | word_idx | ) |
Line pdftron::PDF::TextExtractor::Line::GetNextLine | ( | ) |
int pdftron::PDF::TextExtractor::Line::GetCurrentNum | ( | ) |
Style pdftron::PDF::TextExtractor::Line::GetStyle | ( | ) |
int pdftron::PDF::TextExtractor::Line::GetParagraphID | ( | ) |
int pdftron::PDF::TextExtractor::Line::GetFlowID | ( | ) |
bool pdftron::PDF::TextExtractor::Line::EndsWithHyphen | ( | ) |
bool pdftron::PDF::TextExtractor::Line::IsValid | ( | ) |
bool pdftron::PDF::TextExtractor::Line::operator== | ( | const Line & | ) |
bool pdftron::PDF::TextExtractor::Line::operator!= | ( | const Line & | ) |