I'm pretty new to C++ and was looking for a good way to pull the data out of this line.
A sample line that I might need to tokenise is
f 11/65/11 16/70/16 17/69/17
I have a tokenisation method that splits strings into a vector as delimited by a string which may be useful
static void Tokenise(const string& str, vector<string>& tokens, const string& delimiters = " ")
The only way I can think of doing it is to tokenise with " " as a delimiter, remove the first item from the resulting vector, then tokenise each part by itself. Is there a good way to do this all in one?
I see the question is tagged as C++ but the absolutely easiest way to do this is with scanf
int indices[3][3];
sscanf(buffer, "f %d/%d/%d %d/%d/%d %d/%d/%d", &indices[0][0], &indices[0][1],...);
#include <iostream>
#include <sstream>
#include <string>
#include <vector>
class parse_error : public std::exception {};
template< typename Target >
inline Target convert_to(const std::string& value)
{
std::istringstream iss(value);
Target target;
iss >> target >> std::ws;
if(!iss || !iss.eof()) throw parse_error();
return target;
}
template< typename T >
inline T read_delimited_value(std::istream& is, char delim)
{
std::string value;
std::getline(is,value,delim);
if(!is) throw parse_error();
return convert_to<T>(value);
}
template< typename It >
inline void output(std::ostream& os, It begin, It end)
{
while(begin!=end)
os << *begin++ << ' ';
}
int main()
{
std::vector<int> values;
const std::string line = "f 11/65/11 16/70/16 17/69/17";
std::istringstream iss(line);
std::string value;
std::getline(iss,value,' ');
if(value!="f" || !iss) throw parse_error();
while(iss.good()) {
values.push_back( read_delimited_value<int>(iss,'/') );
values.push_back( read_delimited_value<int>(iss,'/') );
values.push_back( read_delimited_value<int>(iss,' ') );
}
if(!iss.eof()) throw parse_error();
output( std::cout, values.begin(), values.end() );
std::cout << '\n';
return 0;
}
You should take a look at Boost.Tokenizer and especially this:
// char_sep_example_1.cpp
#include <iostream>
#include <boost/tokenizer.hpp>
#include <string>
int main()
{
std::string str = ";;Hello|world||-foo--bar;yow;baz|";
typedef boost::tokenizer<boost::char_separator<char> >
tokenizer;
boost::char_separator<char> sep("-;|");
tokenizer tokens(str, sep);
for (tokenizer::iterator tok_iter = tokens.begin();
tok_iter != tokens.end(); ++tok_iter)
std::cout << "<" << *tok_iter << "> ";
std::cout << "\n";
return EXIT_SUCCESS;
}
Judging from the sample line you can use two delimiters ' ' and '/' and you will get all your numbers.
static void Tokenise(const string& str, vector<string>& tokens, const string& delimiters = " /")
You can remove easily the first part until the first blank or the just after the f ( you can get the rest after the first blank with
istringstream iss( line );
std::getline( iss, restStr ,' ' )
Then you can use your tokenize function first on blank space and then on '/', or just use a set of std::getline and istringstreams in one loop.
int main()
{
std::string s = "f 1/2/3 4/4/2";
std::istringstream issLine( s );
std::string result;
// remove the first "f"
std::getline( issLine, result, ' ' );
// parse blanks
while( std::getline( issLine, result, ' ' ) )
{
std::istringstream issToken( result );
std::string token;
//parse content
while( std::getline( issToken, token, '/' ))
{
std::cout << token << ',';
// add your data in whatever you want
}
std::cout << std::endl;
}
}
Related
If I have a string (from user) of "{1, 2, 3, 4, 5}", how would I convert that to a vector of {1, 2, 3, 4, 5} in C++?
I tried to get a string from the user by
vector<int> input;
cin >> input;
but I got error:
./main.cpp:124:9: error: invalid operands to binary expression ('std::istream' (aka 'basic_istream<char>') and 'vector<int>')
cin >> user_input;
So, this is where a library of useful functions comes in. I keep quite a few.
First, we’ll need something to range over a container (such as a string):
#include <utility>
template <typename Iterator>
struct ranger : public std::pair <Iterator, Iterator>
{
ranger( Iterator begin, Iterator end = Iterator() ) : std::pair <Iterator, Iterator> { begin, end } { }
Iterator begin() { return this->first; }
Iterator end () { return this->second; }
};
Next we’ll want something to make iterating over a string with regular expressions easier:
#include <regex>
#include <string>
struct re_ranger : public std::regex, public ranger <std::sregex_iterator>
{
template <typename RegEx>
re_ranger( const RegEx& re, const std::string& s )
: std::regex( re )
, ranger( std::sregex_iterator( s.begin(), s.end(), *this ) )
{ }
};
And we will naturally want to have the ability to turn a string like "7" into an integer like 7:
#include <optional>
#include <sstream>
#include <string>
template <typename T>
auto string_to( const std::string & s )
{
T value;
std::istringstream ss( s );
return ((ss >> value) and (ss >> std::ws).eof())
? value
: std::optional<T> { };
}
This makes selecting and converting the numbers in a string to a vector of integers stupidly simple:
#include <iostream>
#include <vector>
int main()
{
std::string input = "{1, 2, 3, 4, 5}";
std::vector<int> xs;
for (auto m : re_ranger( "[[:digit:]]+", input ))
xs.emplace_back( *string_to<int>(m.str()) );
Since we are converting one way, we might as well be able to convert the other way. Here’s the freebie:
#include <sstream>
#include <string>
template <typename Iterator>
std::string join( Iterator begin, Iterator end, const std::string & separator = " " )
{
std::ostringstream ss;
if (begin != end)
{
ss << *begin++;
while (begin != end)
ss << separator << *begin++;
}
return ss.str();
}
template <typename Container>
std::string join( const Container & xs, const std::string & separator = " " )
{
using std::begin;
using std::end;
return join( begin( xs ), end( xs ), separator );
}
Now we can finish off main():
#include <iostream>
#include <numeric>
#include <vector>
int main()
{
std::string input = "{1, 2, 3, 4, 5}";
std::vector<int> xs;
for (auto s : re_ranger( "[[:digit:]]+", input ))
xs.emplace_back( *string_to<int>( s.str() ) );
std::cout << join( xs, "+" )
<< " = " << std::accumulate( xs.begin(), xs.end(), 0 ) << "\n";
}
Output:
1+2+3+4+5 = 15
PS. You should get user input as a string:
int main()
{
std::string input;
std::cout << "input? ";
getline( std::cin, input );
A suggestion: convert your string into an input stream.
Try something like this:
const std::string input_data="{1, 2, 3, 4, 5}";
std::istringstream input_stream(input_data);
char c; // Used for ignoring characters.
std::vector<int> database;
int number;
// Ignore the first brace
input_stream >> c;
// Read in the first number
input_stream >> number;
database.push_back(number);
// Read in the separator;
input_stream >> c;
// Read in the next number
input_stream >> number;
database.push_back(number);
// ...
The test for the ending brace or end of input are left as an exercise for the OP. :-)
I have this utility function I use to stream in specific characters like { and }
template<class e, class t>
std::basic_istream<e,t>& operator>>(std::basic_istream<e,t>& in, const e& cliteral) {
e buffer; //get buffer
in >> buffer; //read data
if (buffer != cliteral) //if it failed
in.setstate(in.rdstate() | std::ios::failbit); //set the state
return in;
}
And with that, you can use an istream_iterator to stream the ints that the user types directly into the vector:
std::cin >> '{';
std::vector<int> input(std::istream_iterator<int>(std::cin), {});
std::cin >> '}';
Here is another way of parsing the input. It uses a helper type to expect a specific character in the input stream (and eat it).
#include <cctype>
#include <iostream>
struct expect
{
char c;
explicit expect( char c ) : c{c} { }
};
std::istream & operator >> ( std::istream & ins, const expect & c )
{
if (!std::isspace( (unsigned char)c.c )) ins >> std::ws;
if (ins.peek() == c.c) ins.get();
else ins.setstate( std::ios::failbit );
return ins;
}
Now we can write our input function. I’ll overload >> for a vector of integers:
#include <iostream>
#include <sstream>
#include <string>
#include <vector>
std::istream & operator >> ( std::istream & ins, std::vector<int> & xs )
{
int x;
xs.clear();
if (!(ins >> expect( '{' ))) return ins;
while (ins >> x)
{
xs.emplace_back( x );
ins >> expect( ',' );
}
ins.clear();
ins >> expect( '}' );
return ins;
}
Notice how the function works: it expects specific input. If that input fails at any given time the stream will be set to a fail state and the function will return. Now we can use it much like I think you had planned in your question:
int main()
{
std::string input = "{1, 2, 3, 4, 5}";
std::vector<int> xs;
std::istringstream ss( input );
ss >> xs;
for (int x : xs)
std::cout << x << " ";
std::cout << "\n";
}
Helper functions for the win!
PS. There is a companion function/class named accept which does nearly the same thing as expect. It just doesn’t set the fail state if the desired character is not next in the input stream.
struct accept
{
char c;
explicit accept( char c ) : c{c} { }
};
std::istream & operator >> ( std::istream & ins, const accept & c )
{
if (!std::isspace( (unsigned char)c.c )) ins >> std::ws;
if (ins.peek() == c.c) ins.get();
return ins;
}
These two functions are the basis for a lot of very useful parsing powers.
C++ has since over 10 years a dedicated functionality for that. It is the
std::sregex_token_iterator
And since it is existing, and easy to handle, it should be used. The result is very often a one liner.
Please look at one potential solution:
#include <iostream>
#include <vector>
#include <regex>
#include <string>
#include <algorithm>
const std::regex re{ R"(\d+)" };
int main() {
std::string s{ "{1, 2, 3, 4, 5}" };
std::vector<int> result{};
std::transform(std::sregex_token_iterator(s.begin(), s.end(), re), {}, std::back_inserter(result), [](const std::string& v) {return std::stoi(v); });
for (const int i : result) std::cout << i << ' ';
}
If you additionally want to validate the input, you can also use a regex.
Then the solution would look like this:
#include <iostream>
#include <vector>
#include <regex>
#include <string>
#include <algorithm>
const std::regex re{ R"(\d+)" };
const std::regex rv{ R"(\{(\d+\,)*\d+\})" };
int main() {
// Read string and check input
if (std::string s{}; std::getline(std::cin, s) and std::regex_match(s, std::regex{ R"(\{(\d+\,)*\d+\})" })) {
std::vector<int> result{};
// Extract intgers
std::transform(std::sregex_token_iterator(s.begin(), s.end(), re), {}, std::back_inserter(result), [](const std::string& v) {return std::stoi(v); });
// Show debug output
for (const int i : result) std::cout << i << ' ';
}
else std::cerr << "\n***Error: Invald input\n";
}
Input check can be relaxed with other regexes.
I have a database.txt file with comma-separated values:
Name,ID,Year,Gender
I would like to extract each of these elements.
I've started with this code (I've already looked at all the other similar questions and implemented what they've suggested), but it's not printing each piece:
// reading a text file
#include <iostream>
#include <fstream>
#include <string>
#include <vector>
#include <sstream>
using namespace std;
int main () {
string line;
ifstream myfile ("database.txt");
if (myfile.is_open())
{
while ( getline (myfile,line) )
{
std::string str = line;
std::vector<int> vect;
std::stringstream ss(str);
int i;
while (ss >> i)
{
vect.push_back(i);
if (ss.peek() == ',')
ss.ignore();
}
for (i=0; i< vect.size(); i++)
std::cout << vect.at(i)<<std::endl;
//cout << line << '\n';
}
myfile.close();
}
else cout << "Unable to open file";
return 0;
}
How can I modify it to be able to extract each value: name, ID, year, and gender? What am I doing wrong?
Use this function to split each line:
vector<string> split(const string &s, char delim) {
stringstream ss(s);
string item;
vector<string> tokens;
while (getline(ss, item, delim)) {
tokens.push_back(item);
}
return tokens;
}
and your code be like:
// reading a text file
#include <iostream>
#include <fstream>
#include <string>
#include <vector>
#include <sstream>
using namespace std;
int main () {
string line;
ifstream myfile ("database.txt");
if (myfile.is_open())
{
while ( getline (myfile,line) )
{
std::string str = line;
std::vector<string> vect;
vect = split(str, ',') ;
for (int i=0; i< vect.size(); i++)
std::cout << vect.at(i)<<std::endl;
//cout << line << '\n';
}
myfile.close();
}
else cout << "Unable to open file";
return 0;
}
With the help of a utility function and a data structure you can simplify this quite easily.
#include <iostream>
#include <fstream>
#include <vector>
#include <algorithm>
std::vector<std::string> splitString( const std::string& stringToSplit, const std::string& delimiter, const bool keepEmpty ) {
std::vector<std::string> results;
if ( delimiter.empty() {
results.push_back( stringToSplit );
return results;
}
std::string::const_iterator itSubStrStart = stringToSplit.begin(), itSubStrEnd;
while( true ) {
itSubStrEnd = std::search( itSubStrStart, stringToSplit.end(), delimiter.begin(), delimiter.end() );
std::string temp( itSubStrStart, itSubStrEnd );
if ( keepEmpty || !temp.empty() )
results.push_back( temp );
if ( itSubStrEnd == stringToSplit.end() )
break;
itSubStrStart = itSubStrEnd + delimiter.size();
}
return results;
}
struct DataEntry {
std::string name;
unsigned id;
unsigned year;
std::string gender;
};
int main() {
std::string line;
std::fstream file;
file.open( "database.txt" );
std::vector<DataEntry> entries;
std::vector<std::string> elements;
while( file >> line ) {
elements = splitString( line, "," );
DataEntry entry;
entry.name = elements[0];
entry.id = std::stoul( elements[1] );
entry.year = std::stoul( elements[2] );
entry.gender = elements[3];
entries.push_back( entry );
}
file.close();
for ( auto& e : entries ) {
std::cout << e.name << " " << e.id << " "
<< e.year << " " << e.gender << '\n';
}
std::cout << "\nPress any key and enter to quit.\n";
std::cin.get();
return 0;
}
database.txt
John,12345,2010,M
Jane,54321,2012,F
output
John 12345 2010 M
Jane 54321 2012 F
This makes life it a lot easier just by reading in a single line first; then parsing that line of text and from there doing what you will with that data; either storing it to a struct, printing it, manipulating it etc.
Edit
You need to be aware of the fact that when reading in lines of text, and parsing them if you have something like this in your text file:
John Doe,12345,2010,M
It will not give you what you would expect. I'll leave that for you to figure out.
I am trying to read every word a string. I want a string to go in and the first word to come out, then I'll process it, then the second, and so on. But the internet isn't helping me, I know it's probably right under my nose but I can't figure it out!
string lex(string filecontent) {
string t = filecontent;
getline(cin, t);
istringstream iss(t);
string word;
while (iss >> word) {
return word;
}
}
int main() {
string data = load_file(); // Returns a string of words
cout << data;
cout << lex(data);
getchar();
}
Right now this works... sort of it prints out a lot of random gibberish and crazy characters, The file I'm reading's output is ok I check this at cout << data and it is what I expect. Any ideas?
Here is the solution I think you are looking for:
int main() {
string data = load_file(); // Returns a string of words
istringstream iss(data);
while(iss)
{
string tok;
iss >> tok;
cout << "token: " << tok << endl;
//you can do what ever you want with the token here
}
}
Have a look at this, it should help you.
main.cpp
#include "stdafx.h"
#include "Utility.h"
int main() {
using namespace util;
std::string fileName( "sample.txt" );
if ( fileName.empty() ) {
std::cout << "Missing or invalid filename." << std::endl;
return RETURN_ERROR;
}
std::string line;
std::vector<std::string> results;
std::fstream fin;
// Try To Open File For Reading
fin.open( fileName.c_str(), std::ios_base::in );
if ( !fin.is_open() ) {
std::cout << "Can not open file(" << fileName << ") for reading." << std::endl;
return RETURN_ERROR;
}
// Read Line By Line To Get Data Contents Store Into String To Be Parsed
while ( !fin.eof() ) {
std::getline( fin, line );
// Parse Each Line Using Space Character As Delimiter
results = Utility::splitString( line, " " );
// Print The Results On Each Iteration Of This While Loop
// This Is Where You Would Parse The Data Or Store Results Into
// Class Objects, Variables Or Structures.
for ( unsigned u = 0; u < results.size(); u++ ) {
std::cout << results[u] << " ";
}
std::cout << std::endl;
}
// Close File Pointer
fin.close();
// Now Print The Full Vector Of Results - This Is To Show You That Each
// New Line Will Be Overwritten And That Only The Last Line Of The File Will
// Be Stored After The While Loop.
std::cout << "\n-------------------------------------\n";
for ( unsigned u = 0; u < results.size(); u++ ) {
std::cout << results[u] << " ";
}
Utility::pressAnyKeyToQuit();
return RETURN_OK;
} // main
sample.txt
Please help me parse this text file
It spans multiple lines of text
I would like to get each individual word
stdafx.h - Some of these include files may not be needed they are here for I have a larger solution that requires them.
#ifndef STDAFX_H
#define STDAFX_H
#include <Windows.h>
#include <stdio.h>
#include <tchar.h>
#include <conio.h>
#include <string>
#include <sstream>
#include <fstream>
#include <iostream>
#include <iomanip>
#include <vector>
#include <array>
#include <memory>
#include <queue>
#include <functional>
#include <algorithm>
// User Application Specific
// #include "ExceptionHandler.h" - One Of My Class Objects Not Used Here
namespace util {
enum ReturnCode {
RETURN_OK = 0,
RETURN_ERROR = 1,
}; // ReturnCode
extern const unsigned INVALID_UNSIGNED;
extern const unsigned INVALID_UNSIGNED_SHORT;
} // namespace util
#endif // STDAFX_H
stdafx.cpp
#include "stdafx.h"
namespace util {
const unsigned INVALID_UNSIGNED = static_cast<const unsigned>( -1 );
const unsigned INVALID_UNSIGNED_SHORT = static_cast<const unsigned short>( -1 );
} // namespace util
Utility.h
#ifndef UTILITY_H
#define UTILITY_H
namespace util {
class Utility {
public:
static void pressAnyKeyToQuit();
static std::string toUpper(const std::string& str);
static std::string toLower(const std::string& str);
static std::string trim(const std::string& str, const std::string elementsToTrim = " \t\n\r");
static unsigned convertToUnsigned(const std::string& str);
static int convertToInt(const std::string& str);
static float convertToFloat(const std::string& str);
static std::vector<std::string> splitString(const std::string& strStringToSplit, const std::string& strDelimiter, const bool keepEmpty = true);
private:
Utility(); // Private - Not A Class Object
Utility(const Utility& c); // Not Implemented
Utility& operator=(const Utility& c); // Not Implemented
template<typename T>
static bool stringToValue(const std::string& str, T* pValue, unsigned uNumValues);
template<typename T>
static T getValue(const std::string& str, std::size_t& remainder);
}; // Utility
#include "Utility.inl"
} // namespace util
#endif // UTILITY_H
Utility.inl
// ----------------------------------------------------------------------------
// stringToValue()
template<typename T>
static bool Utility::stringToValue(const std::string& str, T* pValue, unsigned uNumValues) {
int numCommas = std::count(str.begin(), str.end(), ',');
if (numCommas != uNumValues - 1) {
return false;
}
std::size_t remainder;
pValue[0] = getValue<T>(str, remainder);
if (uNumValues == 1) {
if (str.size() != remainder) {
return false;
}
}
else {
std::size_t offset = remainder;
if (str.at(offset) != ',') {
return false;
}
unsigned uLastIdx = uNumValues - 1;
for (unsigned u = 1; u < uNumValues; ++u) {
pValue[u] = getValue<T>(str.substr(++offset), remainder);
offset += remainder;
if ((u < uLastIdx && str.at(offset) != ',') ||
(u == uLastIdx && offset != str.size()))
{
return false;
}
}
}
return true;
} // stringToValue
Utility.cpp
#include "stdafx.h"
#include "Utility.h"
namespace util {
// ----------------------------------------------------------------------------
// pressAnyKeyToQuit()
void Utility::pressAnyKeyToQuit() {
std::cout << "\nPress any key to quit" << std::endl;
_getch();
} // pressAnyKeyToQuit
// ----------------------------------------------------------------------------
// toUpper()
std::string Utility::toUpper( const std::string& str ) {
std::string result = str;
std::transform( str.begin(), str.end(), result.begin(), ::toupper );
return result;
} // toUpper
// ----------------------------------------------------------------------------
// toLower()
std::string Utility::toLower( const std::string& str ) {
std::string result = str;
std::transform( str.begin(), str.end(), result.begin(), ::tolower );
return result;
} // toLower
// ----------------------------------------------------------------------------
// trim()
// Removes Elements To Trim From Left And Right Side Of The str
std::string Utility::trim( const std::string& str, const std::string elementsToTrim ) {
std::basic_string<char>::size_type firstIndex = str.find_first_not_of( elementsToTrim );
if ( firstIndex == std::string::npos ) {
return std::string(); // Nothing Left
}
std::basic_string<char>::size_type lastIndex = str.find_last_not_of( elementsToTrim );
return str.substr( firstIndex, lastIndex - firstIndex + 1 );
} // trim
// ----------------------------------------------------------------------------
// getValue()
template<>
float Utility::getValue( const std::string& str, std::size_t& remainder ) {
return std::stof( str, &remainder );
} // getValue <float>
// ----------------------------------------------------------------------------
// getValue()
template<>
int Utility::getValue( const std::string& str, std::size_t& remainder ) {
return std::stoi( str, &remainder );
} // getValue <int>
// ----------------------------------------------------------------------------
// getValue()
template<>
unsigned Utility::getValue( const std::string& str, std::size_t& remainder ) {
return std::stoul( str, &remainder );
} // getValue <unsigned>
// ----------------------------------------------------------------------------
// convertToUnsigned()
unsigned Utility::convertToUnsigned( const std::string& str ) {
unsigned u = 0;
if ( !stringToValue( str, &u, 1 ) ) {
std::ostringstream strStream;
strStream << __FUNCTION__ << " Bad conversion of [" << str << "] to unsigned";
throw strStream.str();
}
return u;
} // convertToUnsigned
// ----------------------------------------------------------------------------
// convertToInt()
int Utility::convertToInt( const std::string& str ) {
int i = 0;
if ( !stringToValue( str, &i, 1 ) ) {
std::ostringstream strStream;
strStream << __FUNCTION__ << " Bad conversion of [" << str << "] to int";
throw strStream.str();
}
return i;
} // convertToInt
// ----------------------------------------------------------------------------
// convertToFloat()
float Utility::convertToFloat(const std::string& str) {
float f = 0;
if (!stringToValue(str, &f, 1)) {
std::ostringstream strStream;
strStream << __FUNCTION__ << " Bad conversion of [" << str << "] to float";
throw strStream.str();
}
return f;
} // convertToFloat
// ----------------------------------------------------------------------------
// splitString()
std::vector<std::string> Utility::splitString( const std::string& strStringToSplit, const std::string& strDelimiter, const bool keepEmpty ) {
std::vector<std::string> vResult;
if ( strDelimiter.empty() ) {
vResult.push_back( strStringToSplit );
return vResult;
}
std::string::const_iterator itSubStrStart = strStringToSplit.begin(), itSubStrEnd;
while ( true ) {
itSubStrEnd = search( itSubStrStart, strStringToSplit.end(), strDelimiter.begin(), strDelimiter.end() );
std::string strTemp( itSubStrStart, itSubStrEnd );
if ( keepEmpty || !strTemp.empty() ) {
vResult.push_back( strTemp );
}
if ( itSubStrEnd == strStringToSplit.end() ) {
break;
}
itSubStrStart = itSubStrEnd + strDelimiter.size();
}
return vResult;
} // splitString
} // namspace util
In my small utility library I have a function that will split a string that can use any delimiter that the user defines. It will search for the first occurrence of that character delimiter and it will save everything before it into a string and it will push that string into a vector of strings, and it will continue this for every occurrence of that character until it is finished parsing the full string that is passed to it. It will then return a vector of strings back to the user. This is very helpful when engaged in parsing text files or even just data types with long strings that need to be broken down. Now if there is a case where you are parsing a text file and lets say you need to have more than one word as a single string, this can be done but requires more work on your part. For example a text file might have personal record on a single line.
LastName, FirstName MiddleInitial Age Phone# Address
Cook, John S 33 1-888-323-4545 324 Complex Avenue
And you would want the 324 Complex Avenue to be in a single string also you don't want the comma stored after the last name. Your structure in code to store this info might look like this:
struct PersonalRecord {
std::string firstName;
std::string lastName;
char middleInitial;
unsigned age;
std::string phoneNumber;
std:string address;
};
What you would have to do is after you read this line in from your file on that same iteration of the while loop is you would have to do multiple parsing.
You would first start by using a temporary string and vector of strings and use the utility function splitString with the delimeter being the comma. So this would save 2 strings in the temp vector of strings the first being: Cook and the second being the rest of the line after the comma including the leading space. The reason you have the temp string and temp vector of strings is that you will need to pop values at when needed. So in this case we would have to do the following, but first how do we resolve the case with multiple words to one string? We can change the line of text in the text file to be enclosed with double quotes as such:
textfile
Cook, John S 33 1-888-323-4545 "324 Complex Avenue"
Evens, Sue A 24 1-888-323-6996 "128 Mission Rd"
Adams, Chris B 49 1-777-293-8234 "2304 Helms Drive"
Then parse it with this logic flow or algorithm.
main.cpp
#including "stdafx.h"
#including "Utility.h"
int main() {
using namespace util;
std::string strFilename( "personalRecord.txt" );
std::ifstream file;
std::string strLine;
std::vector<std::string> vTemp;
std::vector<std::string> vResult;
std::vector<PersonalRecord> vData;
// Open File For Reading
file.open( strFilename.c_str() );
// Check For Error Of Opening File
if ( !file.is_open() ) {
std::cout << "Error opening file (" << strFilename << ")" << std::endl;
return RETURN_ERROR;
}
// Continue Until End Of File
while( !file.eof() ) {
// Get Single Full Line Save To String
std::getline( file, strLine );
// Check For Comma
vTemp = Utility::splitString( strLine, ",");
// Save First String For Laster
std::string lastName = vTemp[0];
// Split String Using A Double Quote Delimiter Delimiter
vTemp = Utility::splitString( vTemp[1], "\"" );
// Check To See If vTemp Has More Than One String
if ( vTemp.size() > 1 ) {
// We Need To Use Pop Back To Account For Last Double Quote
vTemp.pop_back(); // Remove Last Double Quote
std::string temp = vTemp.back();
vTemp.pop_back(); // Remove Wanted String From vTemp.
// At This Point We Need To Parse vTemp Again Using Space Delimiter
vResult = Utility::splitString( vTemp[0], " " );
// Need To Account For Leading Space In Vector
vResult[0].erase();
// Need To Account For Last Space In Vector
vResult.pop_back();
// Now We Can Push Our Last String Back Into vResult
vResult.push_back( temp );
// Replace The First String " " With Our LastName
vResult[0] = lastName;
} else if ( vTemp.size() == 1 ) {
// Just Parse vTemp Using Space Delimiter
vResult = Utility::splitString( vTemp[0], " " );
}
// Print Out Results For Validity
for ( unsigned u = 0; u < vResult.size(); u++) {
std::cout << vResult.at(u) << " ";
}
std::cout << std::endl;
// Here Is Where You Would Populate Your Variables, Structures Or Classes On Each Pass Of The While Loop.
// With This Structure There Should Only Be 8 Entries Into Our vResult
PersonalRecord temp;
temp.lastName = vResult[0];
temp.firstName = vResult[1];
temp.middleInitial = vResult[2][0];
temp.age = Utility::convertToUnsigned( vResult[3] );
temp.phoneNumber = vResult[4];
temp.address = vResult[5];
vData.push_back( temp );
} // while
// Close File
file.close();
std::cout << std::endl << std::endl;
// Print Using Structure For Validity
std::cout << "---------------------------------------\n";
for ( unsigned u = 0; u < vData.size(); u++ ) {
std::cout << vData[u].lastName << " "
<< vData[u].firstName << " "
<< vData[u].middleInitial << " "
<< vData[u].age << " "
<< vData[u].phoneNumber << " "
<< vData[u].address << std::endl;
}
Utility::pressAnyKeyToQuit();
return RETURN_OK;
} // main
So both consideration and are has to be taken when parsing text or strings. You have to account for every single character including your carriage returns, spaces etc. So the format that the text file is written in has to be considered.
Yes the splitString() will also parse tabs, you would just have to use "\t" for tabs, etc. Just remember that it will make a split at every occurrence. So if you have a sentence that has a colon ":" in it, but then you decide to use the colon as your delimiter between values, it will split that sentence as well. Now you could have different rules for each line of text from the file and if you know what line you are on you can parse each line accordingly. This is why most people prefer to write their code to read and parse binary, because it is much easier to program, then writing a text parser.
I chose to use the PersonalRecord structure to show you how you can extract strings from a line of text and to convert them to basic types such as int, float or double by using some of my other functions in my Utility class. All methods in this class are declared as static and the constructor is private, so the class name acts as a wrapper or a namespace so to speak. You can not create an instance of a Utility util; // invalid object. Just include the header file and use the class name with the scope resolution operator :: to access any of the functions and make sure you are using the namespace util.
Java has this easy method to count the tokens that you tokenize:
import java.util.*;
public class Program
{
public static void main(String[] args)
{
String str =
"This is/some text/that I am/parsing/using StringTokenizer/.";
StringTokenizer strTok =
new StringTokenizer(str, "/", false);
System.out.println("Count...");
System.out.println(strTok.countTokens());
}
}
Output:Count...6
Is there any easy way to do in C++?
You could use std::istringstreamclass along with function std::getline. For example
#include <iostream>
#include <sstream>
#include <string>
int main()
{
char s[] = "This is/some text/that I am/parsing/using StringTokenizer/.";
std::istringstream is( s );
size_t count = 0;
std::string line;
while ( std::getline( is, line, '/' ) ) ++count;
std::cout << "There are " << count << " tokens" << std::endl;
}
The output is
There are 6 tokens
Or
#include <iostream>
#include <sstream>
#include <string>
#include <vector>
int main()
{
char s[] = "This is/some text/that I am/parsing/using StringTokenizer/.";
std::istringstream is( s );
std::vector<std::string> v;
std::string line;
while ( std::getline( is, line, '/' ) ) v.push_back( line );
std::cout << "There are " << v.size() << " tokens" << std::endl;
}
To build again the string from the vector you could use for example the following code
#include <iostream>
#include <sstream>
#include <string>
#include <vector>
int main()
{
char s[] = "This is/some text/that I am/parsing/using StringTokenizer/.";
std::istringstream is( s );
std::vector<std::string> v;
std::string line;
while ( std::getline( is, line, '/' ) ) v.push_back( line );
std::cout << "There are " << v.size() << " tokens" << std::endl;
std::string s1;
bool first = true;
for ( const std::string &t : v )
{
if ( first ) first = false;
else s1 += '/';
s1 += t;
}
std::cout << s1 << std::endl;
}
Or you could use standard algorithm std::replace declared in header <algorithm> to replace one delimeter to another in the original string.
If your compiler does not support the range based for loop then you can write instead
for ( std::vector<std::string>::size_type i = 0; i < v.size(); i++ )
{
if ( i != 0 ) s1 += '/';
s1 += v[i];
}
You could try this:
std::vector<std::string> v(std::istream_iterator<std::string>(std::cin), {});
std::cout << "Count..." << v.size() << "\n";
This will of course tokenize at spaces, not at arbitrary separators. To split on arbitary separators, we need std::getline, but now we don't have an easy istream_iterator. Thankfully, this is a solved problem. So we write:
#include <iostream>
#include <iterator>
#include <string>
#include <vector>
namespace detail
{
template <char Sep = '\n'>
class Line : public std::string
{
friend std::istream & operator>>(std::istream & is, Line & line)
{
return std::getline(is, line, Sep);
}
};
}
int main()
{
std::vector<std::string> v(std::istream_iterator<detail::Line<'/'>>(std::cin), {});
std::cout << "Count..." << v.size() << "\n";
for (auto const & s : v) std::cout << s << "\n";
}
If you want to tokenize an existing string rather than the standard input, use a string stream, i.e. replace std::cin with iss, where we have:
#include <sstream>
std::istringstream iss(my_input_string);
So having a string like remixsettings_bits=1; wysiwyg=1,2,3,abc; remixclosed_tabs=0; remixgroup_closed_tabs=786432; remixlang=0; remixchk=5; remixsid=35d4f9907281708019490d07728c27ca5c10e5de7a869c322222225e3219e; audio_vol=100
I wonder how to parse tham into map name <-> value using boost::spirit and than be capable to write it back using boost::spirit?
Update:
So what I have done:
#include <iostream>
#include <sstream>
#include <string>
#include <map>
//...
std::map<std::string, std::string> user_control::parse_cookie( std::string cookie_data )
{
std::map<std::string, std::string> parsed_cookie;
std::string token, token2;
std::istringstream iss(cookie_data);
while ( getline(iss, token, ' ') )
{
std::string name, val;
std::istringstream iss2(token);
int num = 0 ;
while ( getline(iss2, token2, '=') )
{
if ( num == 0)
{
name = token2;
num++;
}
else
{
val = token2;
std::string::iterator it = val.end() - 1;
if (*it == ';')
val.erase(it);
}
}
std::cout << "name: " << name << " value: " << val << std::endl;
parsed_cookie.insert(std::pair<std::string, std::string>(name, val));
}
return parsed_cookie;
}
but I really wonder how to port my code into boost::spirit code.
This should do the trick, parsing pairs and printing the results using Karma, although we should probably both go read Hartmut's article!
#include <boost/spirit/include/qi.hpp> // Parsing
#include <boost/spirit/include/karma.hpp> // Generation
#include <boost/fusion/adapted/std_pair.hpp> // Make std::pair a fusion vector
int main( int argc, char**argv)
{
using namespace boost::spirit;
std::string str = "keyA=value1; keyB=value2;keyC=value3;";
std::map<std::string,std::string> contents;
std::string::iterator first = str.begin();
std::string::iterator last = str.end();
const bool result = qi::phrase_parse(first,last,
*( *(qi::char_-"=") >> qi::lit("=") >> *(qi::char_-";") >> -qi::lit(";") ),
ascii::space, contents);
assert(result && first==last);
std::cout << karma::format(*(karma::string << '=' <<
karma::string << karma::eol), contents);
}
Have you seen this parser article and this generator article? AFAICT, they explain exactly what you're trying to do.