As one would do with a blockchain, I want to check if a hash satisfies a size requirement. This is fairly easy in Python, but I am having some difficulty implementing the same system in C++. To be clear about what I am after, this first example is the python implementation:
difficulty = 25
hash = "0000004fbbc4261dc666d31d4718566b7e11770c2414e1b48c9e37e380e8e0f0"
print(int(hash, 16) < 2 ** (256 - difficulty))
The main problem I'm having is with these numbers - it is difficult to deal with such large numbers in C++ (2 ** 256, for example). This is solved with the boost/multiprecision library:
boost::multiprecision::cpp_int x = boost::multiprecision::pow(2, 256)
However, I cannot seem to find a way to convert my hash into a numeric value for comparison. Here is a generic example of what I am trying to do:
int main() {
string hash = "0000004fbbc4261dc666d31d4718566b7e11770c2414e1b48c9e37e380e8e0f0";
double difficulty = 256 - 25;
cpp_int requirement = boost::multiprecision::pow(2, difficulty);
// Something to convert hash into a number for comparison (converted_hash)
if (converted_hash < requirement) {
cout << "True" << endl;
}
return 1;
}
The hash is either being received from my web server or from a local python script, in which case the hash is read into the C++ program via fstream. Either way, it will be a string upon arrival.
Since I am already integrating python into this project, I am not entirely opposed to simply using the Python version of this algorithm; however, sometimes taking the easier path prevents you from learning, so unless this is a really cumbersome task, I would like to try to accomplish it in C++.
Your basic need is to compute how many zero bits exist before the first non-zero bit. This has nothing to do with multi-precision really, it can be reformulated into a simple counting problem:
// takes hexadecimal ASCII [0-9a-fA-F]
inline int count_zeros(char ch) {
if (ch < '1') return 4;
if (ch < '2') return 3;
if (ch < '4') return 2;
if (ch < '8') return 1;
return 0; // see ASCII table, [a-zA-Z] are all greater than '8'
}
int count_zeros(const std::string& hash) {
int sum = 0;
for (char ch : hash) {
int zeros = count_zeros(ch);
sum += zeros;
if (zeros < 4)
break;
}
return sum;
}
A fun optimization is to realize there are two termination conditions for the loop, and we can fold them together if we check for characters less than '0' which includes the null terminator and also will stop on any invalid input:
// takes hexadecimal [0-9a-fA-F]
inline int count_zeros(char ch) {
if (ch < '0') return 0; // change 1
if (ch < '1') return 4;
if (ch < '2') return 3;
if (ch < '4') return 2;
if (ch < '8') return 1;
return 0; // see ASCII table, [a-zA-Z] are all greater than '8'
}
int count_zeros(const std::string& hash) {
int sum = 0;
for (const char* it = hash.c_str(); ; ++it) { // change 2
int zeros = count_zeros(*it);
sum += zeros;
if (zeros < 4)
break;
}
return sum;
}
This produces smaller code when compiled with g++ -Os.
Write a C++ program to perform addition of two hexadecimal numerals which are less than 100 digits long. Use arrays to store hexadecimal numerals as arrays of characters.the solution is to add the corresponding digits in the format of hexadecimal directly. From right to left, add one to the digit on the left if the sum of the current digits exceed 16. You should be able to handle the case when two numbers have different digits.
The correct way to get the input is to store as character array. You can either first store in a string and convert to character array, or you can use methods such as cin.getline(), getc(), cin.get() to read in the characters.
I don't know what is wrong with my program and it I don't know how to use the function getline() and eof()
char a[number1],b[number1],c[number2],h;
int m,n,p(0),q(0),k,d[number1],z[number1],s[number2],L,M;
cout<<"Input two hexadecimal numerals(both of them within 100 digits):\n";
cin.getline(a,100);
cin.getline(b,100);
int x=strlen(a) ;
int y=strlen(b);
for(int i=0;i<(x/2);i++)
{
m=x-1-i;
h=a[i];
a[i]=a[m];
a[m]=h;
}
for(int j=0;j<(y/2);j++)
{
n=y-1-j;
h=b[j];
b[j]=b[n];
b[n]=h;
}
if(x>y)
{
for(int o=0;o<x;o++)//calculate a add b
{
if(o>=(y-1))
z[o]=0;//let array b(with no character)=0
if(a[o]=='A')
d[o]=10;
else if(a[o]=='B')
d[o]=11;
else if(a[o]=='C')
d[o]=12;
else if(a[o]=='D')
d[o]=13;
else if(a[o]=='E')
d[o]=14;
else if(a[o]=='F')
d[o]=15;
else if(a[o]=='0')
d[o]=0;
else if(a[o]=='1')
d[o]=1;
else if(a[o]=='2')
d[o]=2;
else if(a[o]=='3')
d[o]=3;
else if(a[o]=='4')
d[o]=4;
else if(a[o]=='5')
d[o]=5;
else if(a[o]=='6')
d[o]=6;
else if(a[o]=='7')
d[o]=7;
else if(a[o]=='8')
d[o]=8;
else if(a[o]=='9')
d[o]=9;
if(b[o]=='A')
z[o]=10;
else if(b[o]=='B')
z[o]=11;
else if(b[o]=='C')
z[o]=12;
else if(b[o]=='D')
z[o]=13;
else if(b[o]=='E')
z[o]=14;
else if(b[o]=='F')
z[o]=15;
else if(b[o]=='0')
z[o]=0;
else if(b[o]=='1')
z[o]=1;
else if(b[o]=='2')
z[o]=2;
else if(b[o]=='3')
z[o]=3;
else if(b[o]=='4')
z[o]=4;
else if(b[o]=='5')
z[o]=5;
else if(b[o]=='6')
z[o]=6;
else if(b[o]=='7')
z[o]=7;
else if(b[o]=='8')
z[o]=8;
else if(b[o]=='9')
z[o]=9;
p=d[o]+z[o]+q;
if(p>=16)//p is the remained number
{
q=1;
p=p%16;
}
else
q=0;
if(p==0)
c[o]='0';
else if(p==1)
c[o]='1';
else if(p==2)
c[o]='2';
else if(p==3)
c[o]='3';
else if(p==4)
c[o]='4';
else if(p==5)
c[o]='5';
else if(p==6)
c[o]='6';
else if(p==7)
c[o]='7';
else if(p==8)
c[o]='8';
else if(p==9)
c[o]='9';
else if(p==10)
c[o]='A';
else if(p==11)
c[o]='B';
else if(p==12)
c[o]='C';
else if(p==13)
c[o]='D';
else if(p==14)
c[o]='E';
else if(p==15)
c[o]='F';
}
k=x+1;
if(q==1)//calculate c[k]
{
c[k]='1';
for(int f=0;f<=(k/2);f++)
{
m=k-f;
h=c[f];
c[f]=c[m];
c[m]=h;
}
}
else
{
for(int e=0;e<=(x/2);e++)
{
m=x-e;
h=c[e];
c[e]=c[m];
c[m]=h;
}
}
}
if(x=y)
{
for(int o=0;o<x;o++)//calculate a add b
{
if(a[o]=='A')
d[o]=10;
else if(a[o]=='B')
d[o]=11;
else if(a[o]=='C')
d[o]=12;
else if(a[o]=='D')
d[o]=13;
else if(a[o]=='E')
d[o]=14;
else if(a[o]=='F')
d[o]=15;
else if(a[o]=='0')
d[o]=0;
else if(a[o]=='1')
d[o]=1;
else if(a[o]=='2')
d[o]=2;
else if(a[o]=='3')
d[o]=3;
else if(a[o]=='4')
d[o]=4;
else if(a[o]=='5')
d[o]=5;
else if(a[o]=='6')
d[o]=6;
else if(a[o]=='7')
d[o]=7;
else if(a[o]=='8')
d[o]=8;
else if(a[o]=='9')
d[o]=9;
if(b[o]=='A')
z[o]=10;
else if(b[o]=='B')
z[o]=11;
else if(b[o]=='C')
z[o]=12;
else if(b[o]=='D')
z[o]=13;
else if(b[o]=='E')
z[o]=14;
else if(b[o]=='F')
z[o]=15;
else if(b[o]=='0')
z[o]=0;
else if(b[o]=='1')
z[o]=1;
else if(b[o]=='2')
z[o]=2;
else if(b[o]=='3')
z[o]=3;
else if(b[o]=='4')
z[o]=4;
else if(b[o]=='5')
z[o]=5;
else if(b[o]=='6')
z[o]=6;
else if(b[o]=='7')
z[o]=7;
else if(b[o]=='8')
z[o]=8;
else if(b[o]=='9')
z[o]=9;
p=d[o]+z[o]+q;
M=p;
if(p>=16)
{
q=1;
p=p%16;
}
else
q=0;
s[o]=p;
if(p==0)
c[o]='0';
else if(p==1)
c[o]='1';
else if(p==2)
c[o]='2';
else if(p==3)
c[o]='3';
else if(p==4)
c[o]='4';
else if(p==5)
c[o]='5';
else if(p==6)
c[o]='6';
else if(p==7)
c[o]='7';
else if(p==8)
c[o]='8';
else if(p==9)
c[o]='9';
else if(p==10)
c[o]='A';
else if(p==11)
c[o]='B';
else if(p==12)
c[o]='C';
else if(p==13)
c[o]='D';
else if(p==14)
c[o]='E';
else if(p==15)
c[o]='F';
}
k=x+1;
if(q==1)
{
c[k]='1';
for(int f=0;f<=(k/2);f++)
{
m=k-f;
h=c[f];
c[f]=c[m];
c[m]=h;
}
}
else
{
for(int e=0;e<=(x/2);e++)
{
m=x-e;
h=c[e];
c[e]=c[m];
c[m]=h;
}
}
}
Lets look at what cin.getline does:
Extracts characters from stream until end of line. After constructing
and checking the sentry object, extracts characters from *this and
stores them in successive locations of the array whose first element
is pointed to by s, until any of the following occurs (tested in the
order shown):
end of file condition occurs in the input sequence (in which case setstate(eofbit) is executed)
the next available character c is the delimiter, as determined by Traits::eq(c, delim). The delimiter is extracted (unlike basic_istream::get()) and counted towards gcount(), but is not stored.
count-1 characters have been extracted (in which case setstate(failbit) is executed).
If the function extracts no characters (e.g. if count < 1), setstate(failbit)
is executed. In any case, if count>0, it then stores a null character
CharT() into the next successive location of the array and updates
gcount().
The result of that is in all cases, s now points to a null terminated string, of at most count-1 characters.
In your usage, you have up to 99 digits, and can use strlen to count exactly how many. eof is not a character, nor it is a member function of char.
You then reverse in place the inputs, and go about your overly repetitious conversions.
However, it's much simpler to use functions, both those you write yourself and those provided by the standard.
// translate from '0' - '9', 'A' - 'F', 'a' - 'f' to 0 - 15
static std::map<char, int> hexToDec { { '0', 0 }, { '1', 1 }, ... { 'f', 15 }, { 'F', 15 } };
// translate from 0 - 15 to '0' - '9', 'A' - 'F'
static std::map<int, char> decToHex { { 0, '0' }, { 1, '1' }, ... { 15, 'F' } };
std::pair<char, bool> hex_add(char left, char right, bool carry)
{
// translate each hex "digit" and add them
int sum = hexToDec[left] + hexToDec[right];
// we have a carry from the previous sum
if (carry) { ++sum; }
// translate back to hex, and check if carry
return std::make_pair(decToHex[sum % 16], sum >= 16);
}
int main()
{
std::cout << "Input two hexadecimal numerals(both of them within 100 digits):\n";
// read two strings
std::string first, second;
std::cin >> first >> second;
// reserve enough for final carry
std::string reverse_result(std::max(first.size(), second.size()) + 1, '\0');
// traverse the strings in reverse
std::string::const_reverse_iterator fit = first.rbegin();
std::string::const_reverse_iterator sit = second.rbegin();
std::string::iterator rit = reverse_result.begin();
bool carry = false;
// while there are letters in both inputs, add (with carry) from both
for (; (fit != first.rend()) && (sit != second.rend()); ++fit, ++sit, ++rit)
{
std::tie(*rit, carry) = hex_add(*fit, *sit, carry);
}
// now add the remaining digits of first (will do nothing if second is longer)
for (; (fit != first.rend()); ++fit)
{
// we need to account for a carry in the last place
// potentially all the way up if we are adding e.g. "FFFF" to "1"
std::tie(*rit, carry) = hex_add(*fit, *rit++, carry);
}
// or add the remaining digits of second
for (; (sit != second.rend()); ++sit)
{
// we need to account for a carry in the last place
// potentially all the way up if we are adding e.g. "FFFF" to "1"
std::tie(*rit, carry) = hex_add(*sit, *rit++, carry);
}
// result has been assembled in reverse, so output it reversed
std::cout << reverse_result.reverse();
}
Regarding the text of your problem: “add one to the digit on the left if the sum of the current digits exceed 16” is wrong; it should be 15, not 16.
Regarding your code: I did not have the patience to read all your code, however:
I have noticed one long if/else. Use a switch (but you do not need one).
To find out if a character is a hex digit use isxdigit (#include <cctype>).
The user might input uppercase and lowercase characters: convert them to the same case using toupper/tolower.
To convert a hex digit to an integer:
if the digit is between ‘0’ and ‘9’ simply subtract ‘0’. This works because the codes for ‘0’, ‘1’… are 0x30, 0x31... (google ASCII codes).
if the digit is between ‘A’ and ‘F’, subtract ‘A’ and add 10.
Solving the problem:
“less than 100 digits long” This is a clear indication regarding how your data must be stored: a simple 100 long array, no std::string, no std::vector:
#define MAX_DIGITS 100
typedef int long_hex_t[MAX_DIGITS];
In other words your numbers are 100 digits wide, at most.
Decide how you store the number: least significant digit first or last? I would chose to store the least significant first. 123 is stored as {3,2,1,0,…0}
Use functions to simplify your code. You will need three functions: read, print and add:
int main()
{
long_hex_t a;
read( a );
long_hex_t b;
read( b );
long_hex_t c;
add( c, a, b );
print( c );
return 0;
}
The easiest function to write is add followed by print and read.
For read use get and putback to analyze the input stream: get extracts the next character from stream and putback is inserting it back in stream (if we do not know how to handle it).
Here it is a full solution (try it):
#include <iostream>
#include <cctype>
#define MAX_DIGITS 100
typedef int long_hex_t[MAX_DIGITS];
void add( long_hex_t c, long_hex_t a, long_hex_t b )
{
int carry = 0;
for ( int i = 0; i < MAX_DIGITS; ++i )
{
int t = a[i] + b[i] + carry;
c[i] = t % 16;
carry = t / 16;
}
}
void print( long_hex_t h )
{
//
int i;
// skip leading zeros
for ( i = MAX_DIGITS - 1; i >= 0 && h[i] == 0; --i )
;
// all zero
if ( i < 0 )
{
std::cout << '0';
return;
}
// print remaining digits
for ( i; i >= 0; --i )
std::cout << char( h[i] < 10 ? h[i] + '0' : h[i] - 10 + 'A' );
}
void read( long_hex_t h )
{
// skip ws
std::ws( std::cin );
// skip zeros
{
char c;
while ( std::cin.get( c ) && c == '0' )
;
std::cin.putback( c );
}
//
int count;
{
int i;
for ( i = 0; i < MAX_DIGITS; ++i )
{
char c;
if ( !std::cin.get( c ) )
break;
if ( !std::isxdigit( c ) )
{
std::cin.putback( c );
break;
}
c = std::toupper( c );
h[i] = c <= '9'
? ( c - '0' )
: ( c - 'A' + 10 );
}
count = i;
}
// reverse
for ( int i = 0, ri = count - 1; i < count / 2; ++i, --ri )
{
int t = h[i];
h[i] = h[ri];
h[ri] = t;
}
// fill the rest with zero
for ( int i = count; i < MAX_DIGITS; ++i )
h[i] = 0;
}
int main()
{
long_hex_t a;
read( a );
long_hex_t b;
read( b );
long_hex_t c;
add( c, a, b );
print( c );
return 0;
}
This is a long answer. Because you have much bug in your code. Your using of getline is ok. But your are calling a eof() like e.eof() which is wrong. If you have looked at your compilation error, you would see that it was complaining about calling eof() on the variable e because it is of non-class type. Simple meaning it is not an object of some class. You cannot put the dot operator . on primitive types like that. I think what you are wanting to do, is to terminate the loop when you have reached the end of line. So that index1 and index2 can get the length of the string input. If I were you, I would just use C++ builtin strlen() function for that. And in the first place, you should use C++ class string to handle strings. Also strings have a null - terminating character '\0' at the end of them. If you don't know about it, I suggest you take some time to read about strings.
Secondly, you have many bugs and errors in your code. The way you are reversing your string is not correct. Ask yourself, what are the contents of the arrays a and b at position which have higher index than the length of the string? You should use reverse() for reversing strings and arrays.
You have errors on adding loop also. Note, you are changing the arrays value when they are A, B, C, D, and so on for hexadecimal values with the corresponding decimal values 10,11,12,13 and so on. But you should change the values for the character '0' - '9' also. Because when the array holds '0' it is not integer 0. But is is ASCII '0' which has integer value of 48. And the character '1' has integer value of 49 and so on. You want to replace this values with corresponding integer values also. When you are also storing the result values in c, you are only handling only those values which are above 9 and replacing them with corresponding characters. You should also replace the integers 0 - 9 with there corresponding ASCII characters. Also don't forget to put a null terminating character at the end of the result.
Also, when p is getting larger than 15, you are only changing your carry, but you should also change p accordingly.
I believe you can reverse the result array c in a much more elegant way. By only reversing when the calculation has been performed totally. You can simple call reverse() for that.
I believe you can think hard a little bit more, and write the code in the right way. I have a few suggestions for you, don't use variable names like a,b,c,o. Try to name variables with what are they really doing. Also, you can improve your algorithm and shorten your code and headache with one simple change in the algorithm. First find the length of a and then find the length of b. If there lengths are unequal, find out which has lesser length. Then add 0s in front of it to make both lengths equal. Now, you can simply start from the back, and perform the addition. Also, you should use builtin methods like reverse() , swap() and also string class to make your life easier ;)
#include <iostream>
#include <algorithm>
#include <string>
using namespace std;
int main(){
string firstVal,secondVal;
cout<<"Input two hexadecimal numerals(both of them within 100 digits):\n";
cin >> firstVal >> secondVal;
//Adjust the length.
if(firstVal.size() < secondVal.size()){
//Find out the number of leading zeroes needed
int leading_zeroes = secondVal.size() - firstVal.size();
for(int i = 0; i < leading_zeroes; i++){
firstVal = '0' + firstVal;
}
}
else if(firstVal.size() > secondVal.size()){
int leading_zeroes = firstVal.size() - secondVal.size();
for(int i = 0; i < leading_zeroes; i++){
secondVal = '0' + secondVal;
}
}
// Now, perform addition.
string result;
int digit_a,digit_b,carry=0;
for(int i = firstVal.size()-1; i >= 0; i--){
if(firstVal[i] >= '0' && firstVal[i] <= '9') digit_a = firstVal[i] - '0';
else digit_a = firstVal[i] - 'A' + 10;
if(secondVal[i] >= '0' && secondVal[i] <= '9') digit_b = secondVal[i] - '0';
else digit_b = secondVal[i] - 'A' + 10;
int sum = digit_a + digit_b + carry;
if(sum > 15){
carry = 1;
sum = sum % 16;
}
else{
carry = 0;
}
// Convert sum to char.
char char_sum;
if(sum >= 0 && sum <= 9) char_sum = sum + '0';
else char_sum = sum - 10 + 'A';
//Append to result.
result = result + char_sum;
}
if(carry > 0) result = result + (char)(carry + '0');
//Result is in reverse order.
reverse(result.begin(),result.end());
cout << result << endl;
}
I am using a Constructor to take an unsigned int as an argument, break it into digits and assign the appropriate true and false values to a vector object. But the problem is that, my poor logic assigns the values in reverse order as the last digit is separated first and so on. The Code I have written is:
vector<bool> _bits;
uBinary(unsigned int num){
int i = 1;
while(num > 0)
{
int d = num%10;
num /= 10;
_bits.resize(i++);
if(d == 1)
{
_bits[_bits.size() - 1] = true;
}
else if(d==0)
{
_bits[_bits.size() - 1] = false;
}
}
}
For example: if argument 10011 is passed to the function uBinary() the vector object will be assigned the values in this order 11001 or true,true,false,false,true which is reversed.
All I need to do here is that, I want to assign the values without reversing the order and I don't want to use another loop for this purpose.
One way is to start at the highest possible digit (unsigned int can only hold values up to 4294967295 on most platforms) and ignore leading zeros until the first actual digit is found:
for (uint32_t divisor = 1000000000; divisor != 0; divisor /= 10) {
uint32_t digit = num / divisor % 10;
if (digit == 0 && _bits.size() == 0 && divisor != 1)
continue; // ignore leading zeros
_bits.push_back(digit == 1);
}
But finding the digits in reverse and then simply reversing them is much simpler (and at least as efficient):
do {
_bits.push_back(num % 10 == 1);
num /= 10;
} while (num != 0);
std::reverse(_bits.begin(), _bits.end());
One way you can do the reversing with another loop or std::reverse is to use recursion. With recursion you can walk down the int until you hit the last digit and then you add the values to the vector as the calls return. That would look like
void uBinary(unsigned int num)
{
if (num == 0)
return;
uBinary(num / 10);
_bits.push_back(num % 10 ? true : false);
}
Which you can see working with
int main()
{
uBinary(10110);
for (auto e : _bits)
std::cout << e << " ";
}
Live Example
Do note that it is advisable not to use leading underscores in variables names. Some names are reserved for the implementation and if you use one it is undefined behavior. For a full explanation of underscores in names see: What are the rules about using an underscore in a C++ identifier?
I am trying to solve this problem.
I am implementing it with strings. Here is my code snippet
string s,ss;
// s and ss both contains integer input.
while(s <= ss )
//while( s<=ss && s.size() <= ss.size())
{
int i = inc, j = dec; // inc and dec are middle values. both equal if odd else different
while((s[j]-'0')==9 && i < len && j>=0){
// for cases like 999
s[i] = s[j] = '0';
i++;
j--;
}
if(j<0){
s = "1" + s;
int l = s[len-1] - '0';
l++;
//cout<<l<<"\n";
s[len] = (l + '0');
}
else{
int l = s[j] - '0';
l++;
s[i] = s[j] = (l+'0');
}
if(s <= ss)
cout<<"out in wild "<<s<<" and "<<ss<<"\n";
}
cout<<s<<endl;
The problem that I am facing is when input is like 999 or 9999. The outer while loop keeps on looping even when the value of s increases, but if I add while( s<=ss && s.size() <= ss.size()) it works completely fine. Why is while(s<=ss) is not working? I rarely use the string class, so I don't understand it completely. Why don't string s= 101 and ss=99 stop the while loop?
Complete code link is here
You are comparing strings with lexicographical order, not numbers , so "101" is less than "99" (because '1' < '9') , e.g.
int main(){
std::string s = "99";
std::string ss = "101";
std::cout << std::boolalpha << (s <= ss);
}
Outputs false.
Notes:
A better design for your program would be to manipulate numbers (int or double ...) and not strings in the first place, so this kind of expressions would naturally work as you expect.
E.g. "101" + "99" is "10199", not "200" ...
But if you really need strings, consider this post to sort strings containing numbers.
As pointed by #Deduplicator, a program that needlessly overuses strings is sometimes called Stringly Typed
Also see std::lexicographical_compare
Since your input explicitly only involves positive integers without leading 0, writing a comparison function is trivial, something like : (untested)
/* Returns 1 if the integer represented by s1 > the integer represented by s2
* Returns -1 if the integer represented by s1 < the integer represented by s2
* Return 0 is both are equals
*
* s1 and s2 must be strings representing positive integers without trailing 0
*/
int compare(const std::string& s1, const std::string& s2)
{
if(s1.size() > s2.size())
return 1;
if(s2.size() > s1.size())
return -1;
for(std::size_t i = 0 ; i < s1.size() ; ++i)
{
if(s1[i] - '0' < s2[i] - '0')
return 1;
if(s2[i] - '0' < s1[i] - '0')
return -1;
}
return 0;
}
While s and ss are string variables, they are compared character by character.
In the case that you mentioned being: s = "101" & ss = "99", by first hand it will check the first character in each string, and as '1' < '9' it exit up with s < ss. I would advise you to convert those values to integers before comparison.
As the s is compared with ss in lexicographical order, I would suggest you to compare one char from tail with one char from head (one by one till you reach the middle) to solve that problem.
I need to compare string into following way. Can anyone provide me some insight or algorithm in c++.
For example:
"a5" < "a11" - because 5 is less than 11
"6xxx < 007asdf" - because 6 < 7
"00042Q < 42s" - because Q < s alphabetically
"6 8" < "006 9" - because 8 < 9
I suggest you look at the algorithm strverscmp uses - indeed it might be that this function will do the job for you.
What this function does is the following. If both strings are equal,
return 0. Otherwise find the position between two bytes with the
property that before it both strings are equal, while directly after
it there is a difference. Find the largest consecutive digit strings
containing (or starting at, or ending at) this position. If one or
both of these is empty, then return what strcmp(3) would have
returned (numerical ordering of byte values). Otherwise, compare both
digit strings numerically, where digit strings with one or more
leading zeros are interpreted as if they have a decimal point in front
(so that in particular digit strings with more leading zeros come
before digit strings with fewer leading zeros). Thus, the ordering is
000, 00, 01, 010, 09, 0, 1, 9, 10.
Your examples only show digits, letters, and spaces. So for the moment I'll assume you ignore every other symbol (effectively treat them as spaces). You also seem to want to treat uppercase and lowercase letters as equivalent.
It also appears that you interpret runs of digits as a "term" and runs of letters as a "term", with any transition between a letter and a digit being equivalent to a space. A single space is considered equivalent to any number of spaces.
(Note: You are conspicuously missing an example of what to do in cases like:
"5a" vs "a11"
"a5" vs "11a"
So you have to work out what to do when you face a comparison of a numeric term with a string term. You also don't mention intrinsic equalities...such as should "5 a" == "5a" just because "5 a" < "5b"?)
One clear way of doing this would be turn the strings into std::vector of "terms", and then compare these vectors (rather than trying to compare the strings directly). These terms would be either numeric or string. This might help get you started, especially the STL answer:
how to split a string value that contains characters and numbers
Trickier methods that worked on the strings themselves without making an intermediary will be faster in one-off comparisons. But they'll likely be harder to understand and modify, and perhaps slower if you are going to repeatedly compare the same structures.
A nice aspect of parsing into a structure is that you get an intrinsic "cleanup" of the data in the process. Getting the information into a canonical form is often a goal in programs that are tolerating such a variety of inputs.
I'm assuming that you want the compare to be done in this order: presence of digits in range 1-9; value of digits; number of digits; value of the string after the digits.
It's in C, but you can easily transform it into using the C++ std::string class.
int isdigit(int c)
{
return c >= '1' && c <= '9';
}
int ndigits(const char *s)
{
int i, nd = 0;
int n = strlen(s);
for (i = 0; i < n; i++) {
if (isdigit(s[i]))
nd++;
}
return nd;
}
int compare(const char *s, const char *t)
{
int sd, td;
int i, j;
sd = ndigits(s);
td = ndigits(t);
/* presence of digits */
if (!sd && !td)
return strcasecmp(s, t);
else if (!sd)
return 1;
else if (!td)
return -1;
/* value of digits */
for (i = 0, j = 0; i < sd && j < td; i++, j++) {
while (! isdigit(*s))
s++;
while (! isdigit(*t))
t++;
if (*s != *t)
return *s - *t;
s++;
t++;
}
/* number of digits */
if (i < sd)
return 1;
else if (j < td)
return -1;
/* value of string after last digit */
return strcasecmp(s, t);
}
Try this and read about std::string.compare:
#include <iostream>
using namespace std;
int main(){
std::string fred = "a5";
std::string joe = "a11";
char x;
if ( fred.compare( joe ) )
{
std::cout << "fred is less than joe" << std::endl;
}
else
{
std::cout << "joe is less than fred" << std::endl;
}
cin >> x;
}