slpNPatternDict

class slpNPatternDict

Public Functions

string ReplaceString(string subject, const string &search, const string &replace)
Parameters:
  • subject

  • search

  • replace

Returns:

string

string ReplaceStringRestricted(string subject, const string &search, const string &replace)
Parameters:
  • subject

  • search

  • replace

Returns:

string

void loadFileCSV(map<string, vector<int>> &synonym, vector<vector<string>> &synrows, const string filename = "")
Parameters:
  • synonym

  • synrows

  • filename

string toDev(string s)
Parameters:

s

Returns:

string toslp1(string s)
Parameters:

s

Returns:

void printmapinDev(map<string, int> m1)
Parameters:

m1

void printmap(map<string, int> &m1)
Parameters:

m1

void printmapstrstr(map<string, string> &m1)
Parameters:

m1

void printmapWFreq(map<string, int> &m1)
Parameters:

m1

void loadCwordsPair(string wordL, string wordR, map<string, string> &CPair, map<string, int> &Dict, map<string, int> &PWords)
Parameters:
  • wordL

  • wordR

  • CPair

  • Dict

  • PWords

void loadCwordsPairs(string wordL, string wordR, map<string, set<string>> &CPairs, map<string, int> &Dict, map<string, int> &PWords)
Parameters:
  • wordL

  • wordR

  • CPairs

  • Dict

  • PWords

void loadCPairs(string filename, map<string, set<string>> &CPairs, map<string, int> &Dict, map<string, int> &PWords)
Parameters:
  • filename

  • CPairs

  • Dict

  • PWords

void loadMapNV(string fileName, map<string, int> &OCRWords, vector<string> &vec, string GBook)
Parameters:
  • fileName

  • OCRWords

  • vec

  • GBook

bool hasM40PerAsci(string word1)
Parameters:

word1

Returns:

bool hasNoAsci(string word1)
Parameters:

word1

Returns:

void loadMap(string fileName, map<string, int> &OCRWords, string GBook)
Parameters:
  • fileName

  • OCRWords

  • GBook

bool insertPatternstoMap(string str, map<string, int> &TPWordsP, size_t &count, size_t &count6)
Parameters:
  • str

  • TPWordsP

  • count

  • count6

Returns:

size_t loadDictPatternstoMap(map<string, int> &TPWordsP, map<string, int> &PWords, size_t &count6)
Parameters:
  • TPWordsP

  • PWords

  • count6

Returns:

bool getNgramFeaturesinVect(string str, map<string, int> &Dict, vector<bool> &vb, vector<size_t> &vbf, size_t &count)
Parameters:
  • str

  • Dict

  • vb

  • vbf

  • count

Returns:

bool endsWith(const std::string &s, const std::string &suffix)

slpNPatternDict::endsWith

Note

//https://stackoverflow.com/questions/14265581/parse-split-a-string-in-c-using-string-delimiter-standard-c

Parameters:
  • s

  • suffix

Returns:

void removeEndCommonSpaces(string &str1, string &str2)
Parameters:
  • str1

  • str2

bool searchS1inGVec(string s1, size_t iocrdone, vector<string> &gocr, size_t winig)
Parameters:
  • s1

  • iocrdone

  • gocr

  • winig

Returns:

void find_and_replace(string &source, string const &find, string const &replace)
Parameters:
  • source

  • find

  • replace

string find_and_replace_oddInstancesblue(string source)
Parameters:

source

Returns:

string find_and_replace_oddInstancesorange(string source)
Parameters:

source

Returns:

void allignlcsnew(string &str1, string &str2, string &str3)
Parameters:
  • str1

  • str2

  • str3

bool isNonVowel(string ocrp)
Parameters:

ocrp

Returns:

string removeSpaces(string input)
Parameters:

input

Returns:

void findConfisions(string ocr, string correct, vector<string> &vec)
Parameters:
  • ocr

  • correct

  • vec

void findConfisionsNindex(string ocr, string correct, vector<string> &vec, vector<int> &vind)
Parameters:
  • ocr

  • correct

  • vec

  • vind

void appendConfusionsPairs(string str1, string str2, vector<string> &vec)
Parameters:
  • str1

  • str2

  • vec

string appendConfusionsPairsNindex(string str1, string str2, vector<string> &vec, vector<int> &vecind)
Parameters:
  • str1

  • str2

  • vec

  • vecind

Returns:

void loadvectomap(vector<string> ConfP, map<string, int> &ConfPmap)
Parameters:
  • ConfP

  • ConfPmap

void printvecstr(vector<string> ConfP)
Parameters:

ConfP

void printvecint(vector<int> ConfP)
Parameters:

ConfP

void loadConfusions(string fileName, map<string, int> &ConfPmap)
Parameters:
  • fileName

  • ConfPmap

void loadConfusions2(string fileName1, string fileName2, map<string, int> &ConfPmap)
Parameters:
  • fileName1

  • fileName2

  • ConfPmap

void loadConfusionsFont(vector<string> fileName1, vector<string> fileName2, map<string, int> &ConfPmap)
Parameters:
  • fileName1

  • fileName2

  • ConfPmap

void generateCorrectionPairs(vector<string> &wrong, vector<string> &right, string localFilenameI, string localFilenameC)
Parameters:
  • wrong

  • right

  • localFilenameI

  • localFilenameC

void generatePairs(vector<string> &wrong, vector<string> &right, string localFilenameI, string localFilenameC)
Parameters:
  • wrong

  • right

  • localFilenameI

  • localFilenameC

void generatePairsIEROCR(string localFilenameI, string localFilenameC, string Rep, string Repy)
Parameters:
  • localFilenameI

  • localFilenameC

  • Rep

  • Repy

void generatePairsSpaced(vector<string> &wrong, vector<string> &right, string localFilenameI, string localFilenameC)

slpNPatternDict::generatePairsSpaced

Parameters:
  • wrong

  • right

  • localFilenameI

  • localFilenameC

void loadTopConfusions(map<string, int> &ConfPmap, map<string, string> &TopConfusions, map<string, int> &TopConfusionsMask)
Parameters:
  • ConfPmap

  • TopConfusions

  • TopConfusionsMask

std::string tokenize(const std::string &s)
Parameters:

s

Returns:

void printConfusionRulesmap(map<string, int> &ConfPmap)
Parameters:

ConfPmap

int loadWConfusionsNindex1(string str1, string str2, map<string, int> &ConfPmap, vector<string> &wordConfusions, vector<int> &wCindex)
Parameters:
  • str1

  • str2

  • ConfPmap

  • wordConfusions

  • wCindex

Returns:

string loadWConfusionsNindex(string str1, string str2, map<string, int> &ConfPmap, vector<string> &wordConfusions, vector<int> &wCindex)

for alligning OCR Pair words

void replacestrcnf(string &newstring, size_t i, string cnfn)
Parameters:
  • newstring

  • i

  • cnfn

bool endswithHalanta(string str)

parts from SamasBreakComb.hpp

Parameters:

str

Returns:

void removeEndSpaces(string &str1)
Parameters:

str1

string deletePoornaVirams(string input)
Parameters:

input

Returns:

size_t cntSamas(string in, string &out)
Parameters:
  • in

  • out

Returns:

string SamasLR(string s1, map<string, int> &m1)
Parameters:
  • s1

  • m1

Returns:

string SamasRL(string s1, map<string, int> &m1)
Parameters:
  • s1

  • m1

Returns:

string print2OCRSugg(string str1, string str2, map<string, int> &ConfPmap, map<string, int> &Dict)
Parameters:
  • str1

  • str2

  • ConfPmap

  • Dict

Returns:

string bestIG(string s1, string s2, map<string, int> &m1)
Parameters:
  • s1

  • s2

  • m1

Returns:

void loadSandhiRules(string fileName, map<string, vector<string>> &SRules)
Parameters:
  • fileName

  • SRules

void printSandhiRUles(map<string, vector<string>> &SRules)
Parameters:

SRules

bool SamasCheck(string OCRNew, map<string, int> &Dict)
Parameters:
  • OCRNew

  • Dict

Returns:

bool SandhiCheck(string OCRNew, map<string, int> &Dict, map<string, vector<string>> &SRules)
Parameters:
  • OCRNew

  • Dict

  • SRules

Returns:

string generatePossibilitesNsuggest(string OCRWord, map<string, string> &TopConfusions, map<string, int> &TopConfusionsMask, map<string, int> &Dict, map<string, vector<string>> &SRules)
Parameters:
  • OCRWord

  • TopConfusions

  • TopConfusionsMask

  • Dict

  • SRules

Returns:

class cpp