tesseract  5.0.0-alpha-619-ge9db
paragraphs.cpp File Reference
#include "paragraphs.h"
#include <cctype>
#include <cmath>
#include <cstdio>
#include <cstdlib>
#include <cstring>
#include <algorithm>
#include <memory>
#include <tesseract/genericvector.h>
#include <tesseract/helpers.h>
#include "host.h"
#include "mutableiterator.h"
#include "ocrblock.h"
#include "ocrpara.h"
#include "ocrrow.h"
#include <tesseract/pageiterator.h>
#include "pageres.h"
#include "paragraphs_internal.h"
#include "pdblock.h"
#include "polyblk.h"
#include <tesseract/publictypes.h>
#include "ratngs.h"
#include "rect.h"
#include "statistc.h"
#include <tesseract/strngs.h>
#include "tprintf.h"
#include <tesseract/unichar.h>
#include "unicharset.h"
#include "unicodes.h"
#include "werd.h"

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

 tesseract
 

Functions

bool tesseract::AsciiLikelyListItem (const STRING &word)
 
int tesseract::UnicodeFor (const UNICHARSET *u, const WERD_CHOICE *werd, int pos)
 
void tesseract::LeftWordAttributes (const UNICHARSET *unicharset, const WERD_CHOICE *werd, const STRING &utf8, bool *is_list, bool *starts_idea, bool *ends_idea)
 
void tesseract::RightWordAttributes (const UNICHARSET *unicharset, const WERD_CHOICE *werd, const STRING &utf8, bool *is_list, bool *starts_idea, bool *ends_idea)
 
bool tesseract::ValidFirstLine (const GenericVector< RowScratchRegisters > *rows, int row, const ParagraphModel *model)
 
bool tesseract::ValidBodyLine (const GenericVector< RowScratchRegisters > *rows, int row, const ParagraphModel *model)
 
bool tesseract::CrownCompatible (const GenericVector< RowScratchRegisters > *rows, int a, int b, const ParagraphModel *model)
 
void tesseract::RecomputeMarginsAndClearHypotheses (GenericVector< RowScratchRegisters > *rows, int start, int end, int percentile)
 
int tesseract::InterwordSpace (const GenericVector< 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 GenericVector< RowScratchRegisters > *rows, int start, int end, const ParagraphModel *model)
 
void tesseract::CanonicalizeDetectionResults (GenericVector< PARA * > *row_owners, PARA_LIST *paragraphs)
 
void tesseract::DetectParagraphs (int debug_level, GenericVector< RowInfo > *row_infos, GenericVector< PARA * > *row_owners, PARA_LIST *paragraphs, GenericVector< ParagraphModel * > *models)
 
void tesseract::DetectParagraphs (int debug_level, bool after_text_recognition, const MutableIterator *block_start, GenericVector< ParagraphModel * > *models)
 

Variables

const ParagraphModeltesseract::kCrownLeft = reinterpret_cast<ParagraphModel *>(static_cast<uintptr_t>(0xDEAD111F))
 
const ParagraphModeltesseract::kCrownRight = reinterpret_cast<ParagraphModel *>(static_cast<uintptr_t>(0xDEAD888F))