strformat.h

Go to the documentation of this file.

// strformat.h
#ifndef STRFORMAT_H
#define STRFORMAT_H
#include <iostream>
#include <string>
#include <vector>
#include <algorithm>
#include <sstream>
#include <set>
#include <cstring>

//this file is upcase.h 
//namespace KZUtility {
// causing too much trouble

using namespace std;
int wc(const string &str);  // word cound
bool isnumber(const string &str); // all digits
// whether is it a number with other chars
// such as 1.2, 1,000, -1
bool isnumber(const string &str, const string dc);
// all of the char is in upper case
bool isupper(const string &str);

/*** Case transformation function 
 */
void upper(const char lo[], char *up);
string getLower(const string &str);
void strTolower(string &str);
void strTolower(const string &str1, string &str2);
void strToupper(string &str);
string str2upper(const string &str);
string lc(const string &str);

int cmp_nocase(const string &s1, const string &s2);
bool intersect(vector<string> &s1, vector<string> &s2);

/****** Modification  *****
 * replace, deletion
 */
string delall(const string& str, const char c);
string delall(const string& str, const string& c);
string deleteChr(const string &str, char c);

string tr(const string& str, char i, char o);
void trim(string &str); 
void trimLeadingSpace(string &str);

void dlc(char a[]); //deltes the last character
void rmtsp(char a[]); //remove trailing white characters such as space and \n
void rmsp(char a[]);
//removes extra white-char (space, \t, and \n) from the string, so 
//that only one space is left to separate words
void singleSpace(string &str);
void rmsp(const char a[], char b[]);
//overloaded version.   input string a, output string b
void rmdquote(char a[]); //removes double quote
void rpldquote(char a[], const char r); //replace double quote with r

void newline(istream &ins); //removes remaining character from input stream


int getNumber(char *&ptr);  
int getInt(const string &str);
vector<int> getAllInt(const string &str);


//get number from a pointer that is on the first digit of a string.  
//The pointer will be advanced to the first non-digit character
int itoa(unsigned int n, char a[]);
string itos(int n);
template<class T> string toString(const T &val) {
   ostringstream ous;
   ous << val;
   return ous.str();
}

template<class T> string anyToString(const T &val) {
   ostringstream ous;
   ous << val;
   return ous.str();
}
vector<int> extractInt(const string &str);


int substr(const char ln[], int s, char sub[]);

int substr(const char ln[], int s, int f, char sub[]);

void firstwd(const char ln[], char sub[], char term=' ');
string firstword(const string &str, const string &delim=" ,.()");
void lastwd(const char ln[], char wd[], char sep = ' ');
string lastword(const string &str, const string &delim=" ,.()");

string acronym(const string&str, int n=1);
string acronymWithDigit(const string&str, int n=1);
// if taild with digit, then all will be added
string acronymWithTag(const string&str, int n=1);

void append(char *&head, const char *tail, int &len, int &maxlen, 
                int incr);
//carefull, these are managed by new allocation
//incr is the size increment, should be larger than strlen(tail)
//if not the function will increase it automatically
void append(char *&head, const char *tail, int &len, int &maxlen);

/******** Digestion ***********/

vector<string> split(const string &str, const char sep='\t');

vector<string> split(const string &str, const char sep[]);

//vector<string> split(const string &str); //default separator ( \t,.;)

// will split the string use any one char in delims
vector<string> splitOneOf(const string &str, const string &delims = ",. \t");

vector<string> dissect(const string &str, const string &delims = ",. \t");
set<string> digest2set(const string &str, const string &delims=",. \t");

pair<string,string> breakString(const string &str, const string &sep);


//write sequence to ous line by line; seq is a long string
void writeSequence(const string &seq, ostream &ous, const int width=70);

int isName(char *n);
//return 1 if the string is a scientific organism name such as Homo sapiens

//}

bool codonIsStop(const string &codon);
//{ return codon == "TAA" || codon == "TAG" || codon == "TGA"; }
//bool codonIsStop(char codon[3]) { return !strcmp(codon, "TAA") || !strcmp(codon, "TAG") || !strcmp(codon, "TGA"); }
bool subseqIsStop(const string &seq, int i);
//{ return seq.substr(i,3) == "TAA" || seq.substr(i,3) == "TAG" || seq.substr(i,3) == "TGA"; }

#endif