Related
I'm trying to solve algorithm task: I need to create MultiMap(key,(values)) using hash-table. I can't use Set and Map libraries. I send code to testing system, but I get time-limit exceeded error on test 20. I don't know what exactly this test contains. The code must do following tasks:
put x y - add pair (x,y).If pair exists, do nothing.
delete x y - delete pair(x,y). If pair doesn't exist, do nothing.
deleteall x - delete all pairs with first element x.
get x - print number of pairs with first element x and second elements.
The amount of operations <= 100000
Time limit - 2s
Example:
multimap.in:
put a a
put a b
put a c
get a
delete a b
get a
deleteall a
get a
multimap.out:
3 b c a
2 c a
0
#include <iostream>
#include <fstream>
#include <vector>
using namespace std;
inline long long h1(const string& key) {
long long number = 0;
const int p = 31;
int pow = 1;
for(auto& x : key){
number += (x - 'a' + 1 ) * pow;
pow *= p;
}
return abs(number) % 1000003;
}
inline void Put(vector<vector<pair<string,string>>>& Hash_table,const long long& hash, const string& key, const string& value) {
int checker = 0;
for(int i = 0; i < Hash_table[hash].size();i++) {
if(Hash_table[hash][i].first == key && Hash_table[hash][i].second == value) {
checker = 1;
break;
}
}
if(checker == 0){
pair <string,string> key_value = make_pair(key,value);
Hash_table[hash].push_back(key_value);
}
}
inline void Delete(vector<vector<pair<string,string>>>& Hash_table,const long long& hash, const string& key, const string& value) {
for(int i = 0; i < Hash_table[hash].size();i++) {
if(Hash_table[hash][i].first == key && Hash_table[hash][i].second == value) {
Hash_table[hash].erase(Hash_table[hash].begin() + i);
break;
}
}
}
inline void Delete_All(vector<vector<pair<string,string>>>& Hash_table,const long long& hash,const string& key) {
for(int i = Hash_table[hash].size() - 1;i >= 0;i--){
if(Hash_table[hash][i].first == key){
Hash_table[hash].erase(Hash_table[hash].begin() + i);
}
}
}
inline string Get(const vector<vector<pair<string,string>>>& Hash_table,const long long& hash, const string& key) {
string result="";
int counter = 0;
for(int i = 0; i < Hash_table[hash].size();i++){
if(Hash_table[hash][i].first == key){
counter++;
result += Hash_table[hash][i].second + " ";
}
}
if(counter != 0)
return to_string(counter) + " " + result + "\n";
else
return "0\n";
}
int main() {
vector<vector<pair<string,string>>> Hash_table;
Hash_table.resize(1000003);
ifstream input("multimap.in");
ofstream output("multimap.out");
string command;
string key;
int k = 0;
string value;
while(true) {
input >> command;
if(input.eof())
break;
if(command == "put") {
input >> key;
long long hash = h1(key);
input >> value;
Put(Hash_table,hash,key,value);
}
if(command == "delete") {
input >> key;
input >> value;
long long hash = h1(key);
Delete(Hash_table,hash,key,value);
}
if(command == "get") {
input >> key;
long long hash = h1(key);
output << Get(Hash_table,hash,key);
}
if(command == "deleteall"){
input >> key;
long long hash = h1(key);
Delete_All(Hash_table,hash,key);
}
}
}
How can I do my code work faster?
At very first, a matter of design: Normally, one would pass the key only to the function and calculate the hash within. Your variant allows a user to place elements anywhere within the hash table (using bad hash values), so user could easily break it.
So e. g. put:
using HashTable = std::vector<std::vector<std::pair<std::string, std::string>>>;
void put(HashTable& table, std::string& key, std::string const& value)
{
auto hash = h1(key);
// ...
}
If at all, the hash function could be parametrised, but then you'd write a separate class for (wrapping the vector of vectors) and provide the hash function in constructor so that a user cannot exchange it arbitrarily (and again break the hash table). A class would come with additional benefits, most important: better encapsulation (hiding the vector away, so user could not change it with vector's own interface):
class HashTable
{
public:
// IF you want to provide hash function:
template <typename Hash>
HashTable(Hash hash) : hash(hash) { }
void put(std::string const& key, std::string const& value);
void remove(std::string const& key, std::string const& value); //(delete is keyword!)
// ...
private:
std::vector<std::vector<std::pair<std::string, std::string>>> data;
// if hash function parametrized:
std::function<size_t(std::string)> hash; // #include <functional> for
};
I'm not 100% sure how efficient std::function really is, so for high performance code, you preferrably use your hash function h1 directly (not implenting constructor as illustrated above).
Coming to optimisations:
For the hash key I would prefer unsigned value: Negative indices are meaningless anyway, so why allow them at all? long long (signed or unsigned) might be a bad choice if testing system is a 32 bit system (might be unlikely, but still...). size_t covers both issues at once: it is unsigned and it is selected in size appropriately for given system (if interested in details: actually adjusted to address bus size, but on modern systems, this is equal to register size as well, which is what we need). Select type of pow to be the same.
deleteAll is implemented inefficiently: With each element you erase you move all the subsequent elements one position towards front. If you delete multiple elements, you do this repeatedly, so one single element can get moved multiple times. Better:
auto pos = vector.begin();
for(auto& pair : vector)
{
if(pair.first != keyToDelete)
*pos++ = std::move(s); // move semantics: faster than copying!
}
vector.erase(pos, vector.end());
This will move each element at most once, erasing all surplus elements in one single go. Appart from the final erasing (which you have to do explicitly then), this is more or less what std::remove and std::remove_if from algorithm library do as well. Are you allowed to use it? Then your code might look like this:
auto condition = [&keyToDelete](std::pair<std::string, std::string> const& p)
{ return p.first == keyToDelete; };
vector.erase(std::remove_if(vector.begin(), vector.end(), condition), vector.end());
and you profit from already highly optimised algorithm.
Just a minor performance gain, but still: You can spare variable initialisation, assignment and conditional branch (the latter one can be relatively expensive operation on some systems) within put if you simply return if an element is found:
//int checker = 0;
for(auto& pair : hashTable[hash]) // just a little more comfortable to write...
{
if(pair.first == key && pair.second == value)
return;
}
auto key_value = std::make_pair(key, value);
hashTable[hash].push_back(key_value);
Again, with algorithm library:
auto key_value = std::make_pair(key, value);
// same condition as above!
if(std::find_if(vector.begin(), vector.end(), condition) == vector.end();
{
vector.push_back(key_value);
}
Then less than 100000 operations does not indicate that each operation will require a separate key/value pair. We might expect that keys are added, removed, re-added, ..., so you most likely don't have to cope with 100000 different values. I'd assume your map is much too large (be aware that it requires initialisation of 100000 vectors as well). I'd assume a much smaller one should suffice already (possibly 1009 or 10007? You might possibly have to experiment a little...).
Keeping the inner vectors sorted might give you some performance boost as well:
put: You could use a binary search to find the two elements in between a new one is to be inserted (if one of these two is equal to given one, no insertion, of course)
delete: Use binary search to find the element to delete.
deleteAll: Find upper and lower bounds for elements to be deleted and erase whole range at once.
get: find lower and upper bound as for deleteAll, distance in between (number of elements) is a simple subtraction and you could print out the texts directly (instead of first building a long string). Which of outputting directly or creating a string really is more efficient is to be found out, though, as outputting directly involves multiple system calls, which in the end might cost previously gained performance again...
Considering your input loop:
Checking for eof() (only) is critical! If there is an error in the file, you'll end up in an endless loop, as the fail bit gets set, operator>> actually won't read anything at all any more and you won't ever reach the end of the file. This even might be the reason for your 20th test failing.
Additionally: You have line based input (each command on a separate line), so reading a whole line at once and only afterwards parse it will spare you some system calls. If some argument is missing, you will detect it correctly instead of (illegally) reading next command (e. g. put) as argument, similarly you won't interpret a surplus argument as next command. If a line is invalid for whatever reason (bad number of arguments as above or unknown command), you can then decide indiviually what you want to do (just ignore the line or abort processing entirely). So:
std::string line;
while(std::getline(std::cin, line))
{
// parse the string; if line is invalid, appropriate error handling
// (ignoring the line, exiting from loop, ...)
}
if(!std::cin.eof())
{
// some error occured, print error message!
}
Basically, I have to use selection sort to sort a string[]. I have done this part but this is what I am having difficulty with.
The sort, however, should be case-insensitive, so that "antenna" would come before "Jupiter". ASCII sorts from uppercase to lowercase, so would there not be a way to just swap the order of the sorted string? Or is there a simpler solution?
void stringSort(string array[], int size) {
int startScan, minIndex;
string minValue;
for(startScan = 0 ; startScan < (size - 1); startScan++) {
minIndex = startScan;
minValue = array[startScan];
for (int index = startScan + 1; index < size; index++) {
if (array[index] < minValue) {
minValue = array[index];
minIndex = index;
}
}
array[minIndex] = array[startScan];
array[startScan] = minValue;
}
}
C++ provides you with sort which takes a comparison function. In your case with a vector<string> you'll be comparing two strings. The comparison function should return true if the first argument is smaller.
For our comparison function we'll want to find the first mismatched character between the strings after tolower has been applied. To do this we can use mismatch which takes a comparator between two characters returning true as long as they are equal:
const auto result = mismatch(lhs.cbegin(), lhs.cend(), rhs.cbegin(), rhs.cend(), [](const unsigned char lhs, const unsigned char rhs){return tolower(lhs) == tolower(rhs);});
To decide if the lhs is smaller than the rhs fed to mismatch we need to test 3 things:
Were the strings of unequal length
Was string lhs shorter
Or was the first mismatched char from lhs smaller than the first mismatched char from rhs
This evaluation can be performed by:
result.second != rhs.cend() && (result.first == lhs.cend() || tolower(*result.first) < tolower(*result.second));
Ultimately, we'll want to wrap this up in a lambda and plug it back into sort as our comparator:
sort(foo.begin(), foo.end(), [](const unsigned char lhs, const unsigned char rhs){
const auto result = mismatch(lhs.cbegin(), lhs.cend(), rhs.cbegin(), rhs.cend(), [](const unsigned char lhs, const unsigned char rhs){return tolower(lhs) == tolower(rhs);});
return result.second != rhs.cend() && (result.first == lhs.cend() || tolower(*result.first) < tolower(*result.second));
});
This will correctly sort vector<string> foo. You can see a live example here: http://ideone.com/BVgyD2
EDIT:
Just saw your question update. You can use sort with string array[] as well. You'll just need to call it like this: sort(array, std::next(array, size), ...
#include <algorithm>
#include <vector>
#include <string>
using namespace std;
void CaseInsensitiveSort(vector<string>& strs)
{
sort(
begin(strs),
end(strs),
[](const string& str1, const string& str2){
return lexicographical_compare(
begin(str1), end(str1),
begin(str2), end(str2),
[](const char& char1, const char& char2) {
return tolower(char1) < tolower(char2);
}
);
}
);
}
I use this lambda function to sort a vectors of strings:
std::sort(entries.begin(), entries.end(), [](const std::string& a, const std::string& b) -> bool {
for (size_t c = 0; c < a.size() and c < b.size(); c++) {
if (std::tolower(a[c]) != std::tolower(b[c]))
return (std::tolower(a[c]) < std::tolower(b[c]));
}
return a.size() < b.size();
});
Instead of the < operator, use a case-insensitive string comparison function.
C89/C99 provide strcoll (string collate), which does a locale-aware string comparison. It's available in C++ as std::strcoll. In some (most?) locales, like en_CA.UTF-8, A and a (and all accented forms of either) are in the same equivalence class. I think strcoll only compares within an equivalence class as a tiebreak if the whole string is otherwise equal, which gives a very similar sort order to a case-insensitive compare. Collation (at least in English locales on GNU/Linux) ignores some characters (like [). So ls /usr/share | sort gives output like
acpi-support
adduser
ADM_scripts
aglfn
aisleriot
I pipe through sort because ls does its own sorting, which isn't quite the same as sort's locale-based sorting.
If you want to sort some user-input arbitrary strings into an order that the user will see directly, locale-aware string comparison is usually what you want. Strings that differ only in case or accents won't compare equal, so this won't work if you were using a stable sort and depending on case-differing strings to compare equal, but otherwise you get nice results. Depending on the use-case, nicer than plain case-insensitive comparison.
FreeBSD's strcoll was and maybe still is case sensitive for locales other than POSIX (ASCII). That forum post suggests that on most other systems it is not case senstive.
MSVC provides a _stricoll for case-insensitive collation, implying that its normal strcoll is case sensitive. However, this might just mean that the fallback to comparing within an equivalence class doesn't happen. Maybe someone can test the following example with MSVC.
// strcoll.c: show that these strings sort in a different order, depending on locale
#include <stdio.h>
#include <locale.h>
int main()
{
// TODO: try some strings containing characters like '[' that strcoll ignores completely.
const char * s[] = { "FooBar - abc", "Foobar - bcd", "FooBar - cde" };
#ifdef USE_LOCALE
setlocale(LC_ALL, ""); // empty string means look at env vars
#endif
strcoll(s[0], s[1]);
strcoll(s[0], s[2]);
strcoll(s[1], s[2]);
return 0;
}
output of gcc -DUSE_LOCALE -Og strcoll.c && ltrace ./a.out (or run LANG=C ltrace a.out):
__libc_start_main(0x400586, 1, ...
setlocale(LC_ALL, "") = "en_CA.UTF-8" # my env contains LANG=en_CA.UTF-8
strcoll("FooBar - abc", "Foobar - bcd") = -1
strcoll("FooBar - abc", "FooBar - cde") = -2
strcoll("Foobar - bcd", "FooBar - cde") = -1
# the three strings are in order
+++ exited (status 0) +++
with gcc -Og -UUSE_LOCALE strcoll.c && ltrace ./a.out:
__libc_start_main(0x400536, ...
# no setlocale, so current locale is C
strcoll("FooBar - abc", "Foobar - bcd") = -32
strcoll("FooBar - abc", "FooBar - cde") = -2
strcoll("Foobar - bcd", "FooBar - cde") = 32 # s[1] should sort after s[2], so it's out of order
+++ exited (status 0) +++
POSIX.1-2001 provides strcasecmp. The POSIX spec says the results are "unspecified" for locales other than plain-ASCII, though, so I'm not sure whether common implementations handle utf-8 correctly or not.
See this post for portability issues with strcasecmp, e.g. to Windows. See other answers on that question for other C++ ways of doing case-insensitive string compares.
Once you have a case-insensitive comparison function, you can use it with other sort algorithms, like C standard lib qsort, or c++ std::sort, instead of writing your own O(n^2) selection-sort.
As b.buchhold's answer points out, doing a case-insensitive comparison on the fly might be slower than converting everything to lowercase once, and sorting an array of indices. The lowercase-version of each strings is needed many times. std::strxfrm will transform a string so that strcmp on the result will give the same result as strcoll on the original string.
You could call tolower on every character you compare. This is probably the easiest, yet not a great solution, becasue:
You look at every char multiple times so you'd call the method more often than necessary
You need extra care to handle wide-characters w.r.t to their encoding (UTF8 etc)
You could also replace the comparator by your own function. I.e. there will be some place where you compare something like stringone[i] < stringtwo[j] or charA < charB. change it to my_less_than(stringone[i], stringtwo[j]) and implement the exact ordering you want based.
another way would be to transform every string to lowercase once and create an array of pairs. then you base your comparisons on the lowercase value only, but you swap whole pairs so that your final strings will be in the right order as well.
finally, you can create an array with lowercase versions and sort this one. whenever you swap two elements in this one, you also swap in the original array.
note that all those proposals would still need proper handling of wide characters (if you need that at all)
This solution is much simpler to understand than Jonathan Mee's and pretty inefficient, but for educational purpose could be fine:
std::string lowercase( std::string s )
{
std::transform( s.begin(), s.end(), s.begin(), ::tolower );
return s;
}
std::sort( array, array + length,
[]( const std::string &s1, const std::string &s2 ) {
return lowercase( s1 ) < lowercase( s2 );
} );
if you have to use your sort function, you can use the same approach:
....
minValue = lowercase( array[startScan] );
for (int index = startScan + 1; index < size; index++) {
const std::string &tstr = lowercase( array[index] );
if (tstr < minValue) {
minValue = tstr;
minIndex = index;
}
}
...
Here is the problem: Remove specified characters from a given string.
Input: The string is "Hello World!" and characters to be deleted are "lor"
Output: "He Wd!"
Solving this involves two sub-parts:
Determining if the given character is to be deleted
If so, then deleting the character
To solve the first part, I am reading the characters to be deleted into a std::unordered_map, i.e. I parse the string "lor" and insert each character into the hashmap. Later, when I am parsing the main string, I will look into this hashmap with each character as the key and if the returned value is non-zero, then I delete the character from the string.
Question 1: Is this the best approach?
Question 2: Which would be better for this problem? std::map or std::unordered_map? Since I am not interested in ordering, I used an unordered_map. But is there a higher overhead for creating the hash table? What to do in such situations? Use a map (balanced tree) or a unordered_map (hash table)?
Now coming to the next part, i.e. deleting the characters from the string. One approach is to delete the character and shift the data from that point on, back by one position. In the worst case, where we have to delete all the characters, this would take O(n^2).
The second approach would be to copy only the required characters to another buffer. This would involve allocating enough memory to hold the original string and copy over character by character leaving out the ones that are to be deleted. Although this requires additional memory, this would be a O(n) operation.
The third approach, would be to start reading and writing from the 0th position, increment the source pointer when every time I read and increment the destination pointer only when I write. Since source pointer will always be same or ahead of destination pointer, I can write over the same buffer. This saves memory and is also an O(n) operation. I am doing the same and calling resize in the end to remove the additional unnecessary characters?
Here is the function I have written:
// str contains the string (Hello World!)
// chars contains the characters to be deleted (lor)
void remove_chars(string& str, const string& chars)
{
unordered_map<char, int> chars_map;
for(string::size_type i = 0; i < chars.size(); ++i)
chars_map[chars[i]] = 1;
string::size_type i = 0; // source
string::size_type j = 0; // destination
while(i < str.size())
{
if(chars_map[str[i]] != 0)
++i;
else
{
str[j] = str[i];
++i;
++j;
}
}
str.resize(j);
}
Question 3: What are the different ways by which I can improve this function. Or is this best we can do?
Thanks!
Good job, now learn about the standard library algorithms and boost:
str.erase(std::remove_if(str.begin(), str.end(), boost::is_any_of("lor")), str.end());
Assuming that you're studying algorithms, and not interested in library solutions:
Hash tables are most valuable when the number of possible keys is large, but you only need to store a few of them. Your hash table would make sense if you were deleting specific 32-bit integers from digit sequences. But with ASCII characters, it's overkill.
Just make an array of 256 bools and set a flag for the characters you want to delete. It only uses one table lookup instruction per input character. Hash map involves at least a few more instructions to compute the hash function. Space-wise, they are probably no more compact once you add up all the auxiliary data.
void remove_chars(string& str, const string& chars)
{
// set up the look-up table
std::vector<bool> discard(256, false);
for (int i = 0; i < chars.size(); ++i)
{
discard[chars[i]] = true;
}
for (int j = 0; j < str.size(); ++j)
{
if (discard[str[j]])
{
// do something, depending on your storage choice
}
}
}
Regarding your storage choices: Choose between options 2 and 3 depending on whether you need to preserve the input data or not. 3 is obviously most efficient, but you don't always want an in-place procedure.
Here is a KISS solution with many advantages:
void remove_chars (char *dest, const char *src, const char *excludes)
{
do {
if (!strchr (excludes, *src))
*dest++ = *src;
} while (*src++);
*dest = '\000';
}
You can ping pong between strcspn and strspn to avoid the need for a hash table:
void remove_chars(
const char *input,
char *output,
const char *characters)
{
const char *next_input= input;
char *next_output= output;
while (*next_input!='\0')
{
int copy_length= strspn(next_input, characters);
memcpy(next_output, next_input, copy_length);
next_output+= copy_length;
next_input+= copy_length;
next_input+= strcspn(next_input, characters);
}
}
I have std::strings containing numbers in the leading section that I need to sort. The numbers can be integers or floats.
The vector<std::string> sort was not optimal, I found the following natural sort program which was much better. I still have a small issue with numbers smaller than zero that do not sort just right. Does anyone have a suggestion to improve? We're using Visual Studio 2003.
The complete program follows.
TIA,
Bert
#include <list>
#include <string>
#include <iostream>
using namespace std;
class MyData
{
public:
string m_str;
MyData(string str) {
m_str = str;
}
long field1() const
{
int second = m_str.find_last_of("-");
int first = m_str.find_last_of("-", second-1);
return atol(m_str.substr(first+1, second-first-1).c_str());
}
long field2() const
{
return atol(m_str.substr(m_str.find_last_of("-")+1).c_str());
}
bool operator < (const MyData& rhs)
{
if (field1() < rhs.field1()) {
return true;
} else if (field1() > rhs.field1()) {
return false;
} else {
return field2() < rhs.field2();
}
}
};
int main()
{
// Create list
list<MyData> mylist;
mylist.push_front(MyData("93.33"));
mylist.push_front(MyData("0.18"));
mylist.push_front(MyData("485"));
mylist.push_front(MyData("7601"));
mylist.push_front(MyData("1001"));
mylist.push_front(MyData("0.26"));
mylist.push_front(MyData("0.26"));
// Sort the list
mylist.sort();
// Dump the list to check the result
for (list<MyData>::const_iterator elem = mylist.begin(); elem != mylist.end(); ++elem)
{
cout << (*elem).m_str << endl;
}
return 1;
}
GOT:
0.26
0.26
0.18
93.33
485
1001
7601
EXPECTED:
0.18
0.26
0.26
93.33
485
1001
7601
Use atof() instead of atol() to have the comparison take the fractional part of the number into account. You will also need to change the return types to doubles.
If it's just float strings, I'd rather suggest to create a table with two columns (first row contains the original string, second row is filled with the string converted to float), sort this by the float column and then output/use the sorted string column.
If the data are all numbers I would create a new class to contain the data.
It can have a string to include the data but then allows you to have better methods to model behaviour - in this case espacially to implement operator <
The implementation could also include use of a library that calculates to exact precion e.g. GNU multiple precision this would do the comparison and canversion from string (or if the numbers do not have that many significant figures you could use doubles)
I would compute the values once and store them.
Because they are not actually part of the objects state (they are just calcualted values) mark them as mutable. Then they can also be set during const methods.
Also note that MyClass is a friend of itself and thus can access the private members of another object of the same class. So there is no need for the extranious accessor methods. Remember Accessor methods are to protect other classes from changes in the implementation not the class you are implementing.
The problem with ordering is that atoi() is only reading the integer (ie it stops at the '.' character. Thus all your numbers smaller than 0 have a zero value for comparison and thus they will appear in a random order. To compare against the full value you need to extract them as a floating point value (double).
class MyData
{
private:
mutable bool gotPos;
mutable double f1;
mutable double f2;
public:
/*
* Why is this public?
*/
std::string m_str;
MyData(std::string str)
:gotPos(false)
,m_str(str) // Use initializer list
{
// If you are always going to build f1,f2 then call BuildPos()
// here and then you don't need the test in the operator <
}
bool operator < (const MyData& rhs)
{
if (!gotPos)
{ buildPos();
}
if (!rhs.gotPos)
{ rhs.buildPos();
}
if (f1 < rhs.f1) return true;
if (f1 > rhs.f1) return false;
return f2 < rhs.f2;
}
private:
void buildPos() const
{
int second = m_str.find_last_of("-");
int first = m_str.find_last_of("-", second-1);
// Use boost lexical cast as it handles doubles
// As well as integers.
f1 = boost::lexical_cast<double>(m_str.substr(first + 1, second-first - 1));
f2 = boost::lexical_cast<double>(m_str.substr(second + 1));
gotPos = true;
}
};
Is there a way to find a nonexisting key in a map?
I am using std::map<int,myclass>, and I want to automatically generate a key for new items. Items may be deleted from the map in different order from their insertion.
The myclass items may, or may not be identical, so they can not serve as a key by themself.
During the run time of the program, there is no limit to the number of items that are generated and deleted, so I can not use a counter as a key.
An alternative data structure that have the same functionality and performance will do.
Edit
I trying to build a container for my items - such that I can delete/modify items according to their keys, and I can iterate over the items. The key value itself means nothing to me, however, other objects will store those keys for their internal usage.
The reason I can not use incremental counter, is that during the life-span of the program they may be more than 2^32 (or theoretically 2^64) items, however item 0 may theoretically still exist even after all other items are deleted.
It would be nice to ask std::map for the lowest-value non-used key, so i can use it for new items, instead of using a vector or some other extrnal storage for non-used keys.
I'd suggest a combination of counter and queue. When you delete an item from the map, add its key to the queue. The queue then keeps track of the keys that have been deleted from the map so that they can be used again. To get a new key, you first check if the queue is empty. If it isn't, pop the top index off and use it, otherwise use the counter to get the next available key.
Let me see if I understand. What you want to do is
look for a key.
If not present, insert an element.
Items may be deleted.
Keep a counter (wait wait) and a vector. The vector will keep the ids of the deleted items.
When you are about to insert the new element,look for a key in the vector. If vector is not empty, remove the key and use it. If its empty, take one from the counter (counter++).
However, if you neveer remove items from the map, you are just stuck with a counter.
Alternative:
How about using the memory address of the element as a key ?
I would say that for general case, when key can have any type allowed by map, this is not possible. Even ability to say whether some unused key exists requires some knowledge about type.
If we consider situation with int, you can store std::set of contiguous segments of unused keys (since these segments do not overlap, natural ordering can be used - simply compare their starting points). When a new key is needed, you take the first segment, cut off first index and place the rest in the set (if the rest is not empty). When some key is released, you find whether there are neighbour segments in the set (due to set nature it's possible with O(log n) complexity) and perform merging if needed, otherwise simply put [n,n] segment into the set.
in this way you will definitely have the same order of time complexity and order of memory consumption as map has independently on requests history (because number of segments cannot be more than map.size()+1)
something like this:
class TKeyManager
{
public:
TKeyManager()
{
FreeKeys.insert(
std::make_pair(
std::numeric_limits<int>::min(),
std::numeric_limits<int>::max());
}
int AlocateKey()
{
if(FreeKeys.empty())
throw something bad;
const std::pair<int,int> freeSegment=*FreeKeys.begin();
if(freeSegment.second>freeSegment.first)
FreeKeys.insert(std::make_pair(freeSegment.first+1,freeSegment.second));
return freeSegment.first;
}
void ReleaseKey(int key)
{
std:set<std::pair<int,int>>::iterator position=FreeKeys.insert(std::make_pair(key,key)).first;
if(position!=FreeKeys.begin())
{//try to merge with left neighbour
std::set<std::pair<int,int>>::iterator left=position;
--left;
if(left->second+1==key)
{
left->second=key;
FreeKeys.erase(position);
position=left;
}
}
if(position!=--FreeKeys.end())
{//try to merge with right neighbour
std::set<std::pair<int,int>>::iterator right=position;
++right;
if(right->first==key+1)
{
position->second=right->second;
FreeKeys.erase(right);
}
}
}
private:
std::set<std::pair<int,int>> FreeKeys;
};
Is there a way to find a nonexisting
key in a map?
I'm not sure what you mean here. How can you find something that doesn't exist? Do you mean, is there a way to tell if a map does not contain a key?
If that's what you mean, you simply use the find function, and if the key doesn't exist it will return an iterator pointing to end().
if (my_map.find(555) == my_map.end()) { /* do something */ }
You go on to say...
I am using std::map, and
I want to automatically generate a key
for new items. Items may be deleted
from the map in different order from
their insertion. The myclass items may, or may not be identical, so they can not serve as a key by themself.
It's a bit unclear to me what you're trying to accomplish here. It seems your problem is that you want to store instances of myclass in a map, but since you may have duplicate values of myclass, you need some way to generate a unique key. Rather than doing that, why not just use std::multiset<myclass> and just store duplicates? When you look up a particular value of myclass, the multiset will return an iterator to all the instances of myclass which have that value. You'll just need to implement a comparison functor for myclass.
Could you please clarify why you can not use a simple incremental counter as auto-generated key? (increment on insert)? It seems that there's no problem doing that.
Consider, that you decided how to generate non-counter based keys and found that generating them in a bulk is much more effective than generating them one-by-one.
Having this generator proved to be "infinite" and "statefull" (it is your requirement), you can create a second fixed sized container with say 1000 unused keys.
Supply you new entries in map with keys from this container, and return keys back for recycling.
Set some low "threshold" to react on key container reaching low level and refill keys in bulk using "infinite" generator.
The actual posted problem still exists "how to make efficient generator based on non-counter". You may want to have a second look at the "infinity" requirement and check if say 64-bit or 128-bit counter still can satisfy your algorithms for some limited period of time like 1000 years.
use uint64_t as a key type of sequence or even if you think that it will be not enough
struct sequence_key_t {
uint64_t upper;
uint64_t lower;
operator++();
bool operator<()
};
Like:
sequence_key_t global_counter;
std::map<sequence_key_t,myclass> my_map;
my_map.insert(std::make_pair(++global_counter, myclass()));
and you will not have any problems.
Like others I am having difficulty figuring out exactly what you want. It sounds like you want to create an item if it is not found. sdt::map::operator[] ( const key_type& x ) will do this for you.
std::map<int, myclass> Map;
myclass instance1, instance2;
Map[instance1] = 5;
Map[instance2] = 6;
Is this what you are thinking of?
Going along with other answers, I'd suggest a simple counter for generating the ids. If you're worried about being perfectly correct, you could use an arbitrary precision integer for the counter, rather than a built in type. Or something like the following, which will iterate through all possible strings.
void string_increment(std::string& counter)
{
bool carry=true;
for (size_t i=0;i<counter.size();++i)
{
unsigned char original=static_cast<unsigned char>(counter[i]);
if (carry)
{
++counter[i];
}
if (original>static_cast<unsigned char>(counter[i]))
{
carry=true;
}
else
{
carry=false;
}
}
if (carry)
{
counter.push_back(0);
}
}
e.g. so that you have:
std::string counter; // empty string
string_increment(counter); // now counter=="\x00"
string_increment(counter); // now counter=="\x01"
...
string_increment(counter); // now counter=="\xFF"
string_increment(counter); // now counter=="\x00\x00"
string_increment(counter); // now counter=="\x01\x00"
...
string_increment(counter); // now counter=="\xFF\x00"
string_increment(counter); // now counter=="\x00\x01"
string_increment(counter); // now counter=="\x01\x01"
...
string_increment(counter); // now counter=="\xFF\xFF"
string_increment(counter); // now counter=="\x00\x00\x00"
string_increment(counter); // now counter=="\x01\x00\x00"
// etc..
Another option, if the working set actually in the map is small enough would be to use an incrementing key, then re-generate the keys when the counter is about to wrap. This solution would only require temporary extra storage. The hash table performance would be unchanged, and the key generation would just be an if and an increment.
The number of items in the current working set would really determine if this approach is viable or not.
I loved Jon Benedicto's and Tom's answer very much. To be fair, the other answers that only used counters may have been the starting point.
Problem with only using counters
You always have to increment higher and higher; never trying to fill the empty gaps.
Once you run out of numbers and wrap around, you have to do log(n) iterations to find unused keys.
Problem with the queue for holding used keys
It is easy to imagine lots and lots of used keys being stored in this queue.
My Improvement to queues!
Rather than storing single used keys in the queue; we store ranges of unused keys.
Interface
using Key = wchar_t; //In my case
struct Range
{
Key first;
Key last;
size_t size() { return last - first + 1; }
};
bool operator< (const Range&,const Range&);
bool operator< (const Range&,Key);
bool operator< (Key,const Range&);
struct KeyQueue__
{
public:
virtual void addKey(Key)=0;
virtual Key getUniqueKey()=0;
virtual bool shouldMorph()=0;
protected:
Key counter = 0;
friend class Morph;
};
struct KeyQueue : KeyQueue__
{
public:
void addKey(Key)override;
Key getUniqueKey()override;
bool shouldMorph()override;
private:
std::vector<Key> pool;
friend class Morph;
};
struct RangeKeyQueue : KeyQueue__
{
public:
void addKey(Key)override;
Key getUniqueKey()override;
bool shouldMorph()override;
private:
boost::container::flat_set<Range,std::less<>> pool;
friend class Morph;
};
void morph(KeyQueue__*);
struct Morph
{
static void morph(const KeyQueue &from,RangeKeyQueue &to);
static void morph(const RangeKeyQueue &from,KeyQueue &to);
};
Implementation
Note: Keys being added are assumed to be key not found in queue
// Assumes that Range is valid. first <= last
// Assumes that Ranges do not overlap
bool operator< (const Range &l,const Range &r)
{
return l.first < r.first;
}
// Assumes that Range is valid. first <= last
bool operator< (const Range &l,Key r)
{
int diff_1 = l.first - r;
int diff_2 = l.last - r;
return diff_1 < -1 && diff_2 < -1;
}
// Assumes that Range is valid. first <= last
bool operator< (Key l,const Range &r)
{
int diff = l - r.first;
return diff < -1;
}
void KeyQueue::addKey(Key key)
{
if(counter - 1 == key) counter = key;
else pool.push_back(key);
}
Key KeyQueue::getUniqueKey()
{
if(pool.empty()) return counter++;
else
{
Key key = pool.back();
pool.pop_back();
return key;
}
}
bool KeyQueue::shouldMorph()
{
return pool.size() > 10;
}
void RangeKeyQueue::addKey(Key key)
{
if(counter - 1 == key) counter = key;
else
{
auto elem = pool.find(key);
if(elem == pool.end()) pool.insert({key,key});
else // Expand existing range
{
Range &range = (Range&)*elem;
// Note at this point, key is 1 value less or greater than range
if(range.first > key) range.first = key;
else range.last = key;
}
}
}
Key RangeKeyQueue::getUniqueKey()
{
if(pool.empty()) return counter++;
else
{
Range &range = (Range&)*pool.begin();
Key key = range.first++;
if(range.first > range.last) // exhausted all keys in range
pool.erase(pool.begin());
return key;
}
}
bool RangeKeyQueue::shouldMorph()
{
return pool.size() == 0 || pool.size() == 1 && pool.begin()->size() < 4;
}
void morph(KeyQueue__ *obj)
{
if(KeyQueue *queue = dynamic_cast<KeyQueue*>(obj))
{
RangeKeyQueue *new_queue = new RangeKeyQueue();
Morph::morph(*queue,*new_queue);
obj = new_queue;
}
else if(RangeKeyQueue *queue = dynamic_cast<RangeKeyQueue*>(obj))
{
KeyQueue *new_queue = new KeyQueue();
Morph::morph(*queue,*new_queue);
obj = new_queue;
}
}
void Morph::morph(const KeyQueue &from,RangeKeyQueue &to)
{
to.counter = from.counter;
for(Key key : from.pool) to.addKey(key);
}
void Morph::morph(const RangeKeyQueue &from,KeyQueue &to)
{
to.counter = from.counter;
for(Range range : from.pool)
while(range.first <= range.last)
to.addKey(range.first++);
}
Usage:
int main()
{
std::vector<Key> keys;
KeyQueue__ *keyQueue = new KeyQueue();
srand(time(NULL));
bool insertKey = true;
for(int i=0; i < 1000; ++i)
{
if(insertKey)
{
Key key = keyQueue->getUniqueKey();
keys.push_back(key);
}
else
{
int index = rand() % keys.size();
Key key = keys[index];
keys.erase(keys.begin()+index);
keyQueue->addKey(key);
}
if(keyQueue->shouldMorph())
{
morph(keyQueue);
}
insertKey = rand() % 3; // more chances of insert
}
}