tesseract v5.3.3.20231005
paragraphs.cpp File Reference
#include "paragraphs.h"
#include "helpers.h"
#include "host.h"
#include "mutableiterator.h"
#include "ocrblock.h"
#include "ocrpara.h"
#include "ocrrow.h"
#include "pageres.h"
#include "paragraphs_internal.h"
#include "pdblock.h"
#include "polyblk.h"
#include "ratngs.h"
#include "rect.h"
#include "statistc.h"
#include "tprintf.h"
#include "unicharset.h"
#include "werd.h"
#include <tesseract/pageiterator.h>
#include <tesseract/publictypes.h>
#include <tesseract/unichar.h>
#include <algorithm>
#include <cctype>
#include <cmath>
#include <cstdio>
#include <cstdlib>
#include <cstring>
#include <memory>

Go to the source code of this file.

Classes

class  tesseract::UnicodeSpanSkipper
 
struct  tesseract::Cluster
 
class  tesseract::SimpleClusterer
 
struct  tesseract::GeometricClassifierState
 
struct  tesseract::Interval
 

Namespaces

namespace  tesseract
 

Functions

bool tesseract::AsciiLikelyListItem (const std::string &word)
 
template<class T >
void tesseract::push_back_new (std::vector< T > &vector, const T &data)
 
void tesseract::LeftWordAttributes (const UNICHARSET *unicharset, const WERD_CHOICE *werd, const std::string &utf8, bool *is_list, bool *starts_idea, bool *ends_idea)
 
void tesseract::RightWordAttributes (const UNICHARSET *unicharset, const WERD_CHOICE *werd, const std::string &utf8, bool *is_list, bool *starts_idea, bool *ends_idea)
 
bool tesseract::ValidFirstLine (const std::vector< RowScratchRegisters > *rows, int row, const ParagraphModel *model)
 
bool tesseract::ValidBodyLine (const std::vector< RowScratchRegisters > *rows, int row, const ParagraphModel *model)
 
bool tesseract::CrownCompatible (const std::vector< RowScratchRegisters > *rows, int a, int b, const ParagraphModel *model)
 
void tesseract::RecomputeMarginsAndClearHypotheses (std::vector< RowScratchRegisters > *rows, int start, int end, int percentile)
 
int tesseract::InterwordSpace (const std::vector< RowScratchRegisters > &rows, int row_start, int row_end)
 
bool tesseract::FirstWordWouldHaveFit (const RowScratchRegisters &before, const RowScratchRegisters &after, tesseract::ParagraphJustification justification)
 
bool tesseract::FirstWordWouldHaveFit (const RowScratchRegisters &before, const RowScratchRegisters &after)
 
bool tesseract::RowsFitModel (const std::vector< RowScratchRegisters > *rows, int start, int end, const ParagraphModel *model)
 
void tesseract::CanonicalizeDetectionResults (std::vector< PARA * > *row_owners, PARA_LIST *paragraphs)
 
void tesseract::DetectParagraphs (int debug_level, std::vector< RowInfo > *row_infos, std::vector< PARA * > *row_owners, PARA_LIST *paragraphs, std::vector< ParagraphModel * > *models)
 
void tesseract::DetectParagraphs (int debug_level, bool after_text_recognition, const MutableIterator *block_start, std::vector< ParagraphModel * > *models)
 

Variables

const ParagraphModel * tesseract::kCrownLeft
 
const ParagraphModel * tesseract::kCrownRight