SNAP Library, User Reference  2012-10-02 12:56:23
SNAP, a general purpose network analysis and graph mining library
 All Classes Namespaces Files Functions Variables Typedefs Enumerations Enumerator Friends Defines
TStrUtil Class Reference

List of all members.

Static Public Member Functions

static TChAGetXmlTagVal (TXmlLx &XmlLx, const TChA &TagNm)
static void GetXmlTagNmVal (TXmlLx &XmlLx, TChA &TagNm, TChA &TagVal)
static bool GetXmlTagNmVal2 (TXmlLx &XmlLx, TChA &TagNm, TChA &TagVal, const bool &TakeTagNms)
static TChA GetDomNm (const TChA &UrlChA)
static TChA GetDomNm2 (const TChA &UrlChA)
static TChA GetWebsiteNm (const TChA &UrlChA)
static bool GetNormalizedUrl (const TChA &UrlIn, const TChA &BaseUrl, TChA &UrlOut)
 Quick URL nomalization: Remove ending /, /index.html, etc. and strip starting www.
static bool StripEnd (const TChA &Str, const TChA &SearchStr, TChA &NewStr)
static TChA GetShorStr (const TChA &LongStr, const int MaxLen=50)
static TChA GetCleanStr (const TChA &ChA)
static TChA GetCleanWrdStr (const TChA &ChA)
static int CountWords (const char *CStr)
static int CountWords (const TChA &ChA)
static int CountWords (const TChA &ChA, const TStrHash< TInt > &StopWordH)
static int SplitWords (TChA &ChA, TVec< char * > &WrdV, const bool &SplitOnWs=true)
static int SplitOnCh (TChA &ChA, TVec< char * > &WrdV, const char &Ch, const bool &SkipEmpty=false)
static int SplitLines (TChA &ChA, TVec< char * > &LineV, const bool &SkipEmpty=false)
static int SplitSentences (TChA &ChA, TVec< char * > &SentenceV)
static void RemoveHtmlTags (const TChA &HtmlStr, TChA &TextStr)
static bool IsLatinStr (const TChA &Str, const double &MinAlFrac)
static void GetWIdV (const TStrHash< TInt > &StrH, const char *CStr, TIntV &WIdV)
static void GetAddWIdV (TStrHash< TInt > &StrH, const char *CStr, TIntV &WIdV)
static bool GetTmFromStr (const char *TmStr, TSecTm &Tm)
 Parses time in many different text formats. See source code for details.
static TStr GetStdName (TStr AuthorName)
 Puts person's name (fist middle last) in a standard form: <last_name>_<first name innitial>
static void GetStdNameV (TStr AuthorNames, TStrV &StdNameV)
 Splits a list of people's names.

Detailed Description

String helper functions and utilities. Quick and ditry!


Member Function Documentation

int TStrUtil::CountWords ( const char *  CStr) [static]
int TStrUtil::CountWords ( const TChA ChA) [static]
int TStrUtil::CountWords ( const TChA ChA,
const TStrHash< TInt > &  StopWordH 
) [static]
void TStrUtil::GetAddWIdV ( TStrHash< TInt > &  StrH,
const char *  CStr,
TIntV WIdV 
) [static]
TChA TStrUtil::GetCleanStr ( const TChA ChA) [static]
TChA TStrUtil::GetCleanWrdStr ( const TChA ChA) [static]
TChA TStrUtil::GetDomNm ( const TChA UrlChA) [static]
TChA TStrUtil::GetDomNm2 ( const TChA UrlChA) [static]
bool TStrUtil::GetNormalizedUrl ( const TChA UrlIn,
const TChA BaseUrl,
TChA UrlOut 
) [static]

Quick URL nomalization: Remove ending /, /index.html, etc. and strip starting www.

TChA TStrUtil::GetShorStr ( const TChA LongStr,
const int  MaxLen = 50 
) [static]
TStr TStrUtil::GetStdName ( TStr  AuthorName) [static]

Puts person's name (fist middle last) in a standard form: <last_name>_<first name innitial>

void TStrUtil::GetStdNameV ( TStr  AuthorNames,
TStrV StdNameV 
) [static]

Splits a list of people's names.

bool TStrUtil::GetTmFromStr ( const char *  TmStr,
TSecTm Tm 
) [static]

Parses time in many different text formats. See source code for details.

TChA TStrUtil::GetWebsiteNm ( const TChA UrlChA) [static]
void TStrUtil::GetWIdV ( const TStrHash< TInt > &  StrH,
const char *  CStr,
TIntV WIdV 
) [static]
void TStrUtil::GetXmlTagNmVal ( TXmlLx XmlLx,
TChA TagNm,
TChA TagVal 
) [static]
bool TStrUtil::GetXmlTagNmVal2 ( TXmlLx XmlLx,
TChA TagNm,
TChA TagVal,
const bool &  TakeTagNms 
) [static]
TChA & TStrUtil::GetXmlTagVal ( TXmlLx XmlLx,
const TChA TagNm 
) [static]
bool TStrUtil::IsLatinStr ( const TChA Str,
const double &  MinAlFrac 
) [static]
void TStrUtil::RemoveHtmlTags ( const TChA HtmlStr,
TChA TextStr 
) [static]
int TStrUtil::SplitLines ( TChA ChA,
TVec< char * > &  LineV,
const bool &  SkipEmpty = false 
) [static]
int TStrUtil::SplitOnCh ( TChA ChA,
TVec< char * > &  WrdV,
const char &  Ch,
const bool &  SkipEmpty = false 
) [static]
int TStrUtil::SplitSentences ( TChA ChA,
TVec< char * > &  SentenceV 
) [static]
int TStrUtil::SplitWords ( TChA ChA,
TVec< char * > &  WrdV,
const bool &  SplitOnWs = true 
) [static]
bool TStrUtil::StripEnd ( const TChA Str,
const TChA SearchStr,
TChA NewStr 
) [static]

The documentation for this class was generated from the following files: