Related
Given a string and the constraint of matching on >= 3 characters, how can you ensure that the result string will be as small as possible?
edit with gassa's explicitness:
E.G.
'AAAABBBAC'
If I remove the B's first,
AAAA[BBB]AC -- > AAAAAC, then I can remove all of the A's from the resultant string and be left with:
[AAAAA]C --> C
'C'
If I just remove what is available first (the sequence of A's), I get:
[AAAA]BBBAC -- > [BBB]AC --> AC
'AC'
A tree would definitely get you the shortest string(s).
The tree solution:
Define a State (node) for each current string Input and all its removable sub-strings' int[] Indexes.
Create the tree: For each int index create another State and add it to the parent state State[] Children.
A State with no possible removable sub-strings has no children Children = null.
Get all Descendants State[] of your root State. Order them by their shortest string Input. And that is/are your answer(s).
Test cases:
string result = FindShortest("AAAABBBAC"); // AC
string result2 = FindShortest("AABBAAAC"); // AABBC
string result3 = FindShortest("BAABCCCBBA"); // B
The Code:
Note: Of-course everyone is welcome to enhance the following code in terms of performance and/or fixing any bug.
class Program
{
static void Main(string[] args)
{
string result = FindShortest("AAAABBBAC"); // AC
string result2 = FindShortest("AABBAAAC"); // AABBC
string result3 = FindShortest("BAABCCCBBA"); // B
}
// finds the FIRST shortest string for a given input
private static string FindShortest(string input)
{
// all possible removable strings' indexes
// for this given input
int[] indexes = RemovableIndexes(input);
// each input string and its possible removables are a state
var state = new State { Input = input, Indexes = indexes };
// create the tree
GetChildren(state);
// get the FIRST shortest
// i.e. there would be more than one answer sometimes
// this could be easily changed to get all possible results
var result =
Descendants(state)
.Where(d => d.Children == null || d.Children.Length == 0)
.OrderBy(d => d.Input.Length)
.FirstOrDefault().Input;
return result;
}
// simple get all descendants of a node/state in a tree
private static IEnumerable<State> Descendants(State root)
{
var states = new Stack<State>(new[] { root });
while (states.Any())
{
State node = states.Pop();
yield return node;
if (node.Children != null)
foreach (var n in node.Children) states.Push(n);
}
}
// creates the tree
private static void GetChildren(State state)
{
// for each an index there is a child
state.Children = state.Indexes.Select(
i =>
{
var input = RemoveAllAt(state.Input, i);
return input.Length < state.Input.Length && input.Length > 0
? new State
{
Input = input,
Indexes = RemovableIndexes(input)
}
: null;
}).ToArray();
foreach (var c in state.Children)
GetChildren(c);
}
// find all possible removable strings' indexes
private static int[] RemovableIndexes(string input)
{
var indexes = new List<int>();
char d = input[0];
int count = 1;
for (int i = 1; i < input.Length; i++)
{
if (d == input[i])
count++;
else
{
if (count >= 3)
indexes.Add(i - count);
// reset
d = input[i];
count = 1;
}
}
if (count >= 3)
indexes.Add(input.Length - count);
return indexes.ToArray();
}
// remove all duplicate chars starting from an index
private static string RemoveAllAt(string input, int startIndex)
{
string part1, part2;
int endIndex = startIndex + 1;
int i = endIndex;
for (; i < input.Length; i++)
if (input[i] != input[startIndex])
{
endIndex = i;
break;
}
if (i == input.Length && input[i - 1] == input[startIndex])
endIndex = input.Length;
part1 = startIndex > 0 ? input.Substring(0, startIndex) : string.Empty;
part2 = endIndex <= (input.Length - 1) ? input.Substring(endIndex) : string.Empty;
return part1 + part2;
}
// our node, which is
// an input string &
// all possible removable strings' indexes
// & its children
public class State
{
public string Input;
public int[] Indexes;
public State[] Children;
}
}
I propose O(n^2) solution with dynamic programming.
Let's introduce notation. Prefix and suffix of length l of string A denoted by P[l] and S[l]. And we call our procedure Rcd.
Rcd(A) = Rcd(Rcd(P[n-1])+S[1])
Rcd(A) = Rcd(P[1]+Rcd(S[n-1]))
Note that outer Rcd in the RHS is trivial. So, that's our optimal substructure. Based on this i came up with the following implementation:
#include <iostream>
#include <string>
#include <vector>
#include <cassert>
using namespace std;
string remdupright(string s, bool allowEmpty) {
if (s.size() >= 3) {
auto pos = s.find_last_not_of(s.back());
if (pos == string::npos && allowEmpty) s = "";
else if (pos != string::npos && s.size() - pos > 3) s = s.substr(0, pos + 1);
}
return s;
}
string remdupleft(string s, bool allowEmpty) {
if (s.size() >= 3) {
auto pos = s.find_first_not_of(s.front());
if (pos == string::npos && allowEmpty) s = "";
else if (pos != string::npos && pos >= 3) s = s.substr(pos);
}
return s;
}
string remdup(string s, bool allowEmpty) {
return remdupleft(remdupright(s, allowEmpty), allowEmpty);
}
string run(const string in) {
vector<vector<string>> table(in.size());
for (int i = 0; i < (int)table.size(); ++i) {
table[i].resize(in.size() - i);
}
for (int i = 0; i < (int)table[0].size(); ++i) {
table[0][i] = in.substr(i,1);
}
for (int len = 2; len <= (int)table.size(); ++len) {
for (int pos = 0; pos < (int)in.size() - len + 1; ++pos) {
string base(table[len - 2][pos]);
const char suffix = in[pos + len - 1];
if (base.size() && suffix != base.back()) {
base = remdupright(base, false);
}
const string opt1 = base + suffix;
base = table[len - 2][pos+1];
const char prefix = in[pos];
if (base.size() && prefix != base.front()) {
base = remdupleft(base, false);
}
const string opt2 = prefix + base;
const string nodupopt1 = remdup(opt1, true);
const string nodupopt2 = remdup(opt2, true);
table[len - 1][pos] = nodupopt1.size() > nodupopt2.size() ? opt2 : opt1;
assert(nodupopt1.size() != nodupopt2.size() || nodupopt1 == nodupopt2);
}
}
string& res = table[in.size() - 1][0];
return remdup(res, true);
}
void testRcd(string s, string expected) {
cout << s << " : " << run(s) << ", expected: " << expected << endl;
}
int main()
{
testRcd("BAABCCCBBA", "B");
testRcd("AABBAAAC", "AABBC");
testRcd("AAAA", "");
testRcd("AAAABBBAC", "C");
}
You can check default and run your tests here.
Clearly we are not concerned about any block of repeated characters longer than 2 characters. And there is only one way two blocks of the same character where at least one of the blocks is less than 3 in length can be combined - namely, if the sequence between them can be removed.
So (1) look at pairs of blocks of the same character where at least one is less than 3 in length, and (2) determine if the sequence between them can be removed.
We want to decide which pairs to join so as to minimize the total length of blocks less than 3 characters long. (Note that the number of pairs is bound by the size (and distribution) of the alphabet.)
Let f(b) represent the minimal total length of same-character blocks remaining up to the block b that are less than 3 characters in length. Then:
f(b):
p1 <- previous block of the same character
if b and p1 can combine:
if b.length + p1.length > 2:
f(b) = min(
// don't combine
(0 if b.length > 2 else b.length) +
f(block before b),
// combine
f(block before p1)
)
// b.length + p1.length < 3
else:
p2 <- block previous to p1 of the same character
if p1 and p2 can combine:
f(b) = min(
// don't combine
b.length + f(block before b),
// combine
f(block before p2)
)
else:
f(b) = b.length + f(block before b)
// b and p1 cannot combine
else:
f(b) = b.length + f(block before b)
for all p1 before b
The question is how can we efficiently determine if a block can be combined with the previous block of the same character (aside from the obvious recursion into the sub-block-list between the two blocks).
Python code:
import random
import time
def parse(length):
return length if length < 3 else 0
def f(string):
chars = {}
blocks = [[string[0], 1, 0]]
chars[string[0]] = {'indexes': [0]}
chars[string[0]][0] = {'prev': -1}
p = 0 # pointer to current block
for i in xrange(1, len(string)):
if blocks[len(blocks) - 1][0] == string[i]:
blocks[len(blocks) - 1][1] += 1
else:
p += 1
# [char, length, index, f(i), temp]
blocks.append([string[i], 1, p])
if string[i] in chars:
chars[string[i]][p] = {'prev': chars[string[i]]['indexes'][ len(chars[string[i]]['indexes']) - 1 ]}
chars[string[i]]['indexes'].append(p)
else:
chars[string[i]] = {'indexes': [p]}
chars[string[i]][p] = {'prev': -1}
#print blocks
#print
#print chars
#print
memo = [[None for j in xrange(len(blocks))] for i in xrange(len(blocks))]
def g(l, r, top_level=False):
####
####
#print "(l, r): (%s, %s)" % (l,r)
if l == r:
return parse(blocks[l][1])
if memo[l][r]:
return memo[l][r]
result = [parse(blocks[l][1])] + [None for k in xrange(r - l)]
if l < r:
for i in xrange(l + 1, r + 1):
result[i - l] = parse(blocks[i][1]) + result[i - l - 1]
for i in xrange(l, r + 1):
####
####
#print "\ni: %s" % i
[char, length, index] = blocks[i]
#p1 <- previous block of the same character
p1_idx = chars[char][index]['prev']
####
####
#print "(p1_idx, l, p1_idx >= l): (%s, %s, %s)" % (p1_idx, l, p1_idx >= l)
if p1_idx < l and index > l:
result[index - l] = parse(length) + result[index - l - 1]
while p1_idx >= l:
p1 = blocks[p1_idx]
####
####
#print "(b, p1, p1_idx, l): (%s, %s, %s, %s)\n" % (blocks[i], p1, p1_idx, l)
between = g(p1[2] + 1, index - 1)
####
####
#print "between: %s" % between
#if b and p1 can combine:
if between == 0:
if length + p1[1] > 2:
result[index - l] = min(
result[index - l],
# don't combine
parse(length) + (result[index - l - 1] if index - l > 0 else 0),
# combine: f(block before p1)
result[p1[2] - l - 1] if p1[2] > l else 0
)
# b.length + p1.length < 3
else:
#p2 <- block previous to p1 of the same character
p2_idx = chars[char][p1[2]]['prev']
if p2_idx < l:
p1_idx = chars[char][p1_idx]['prev']
continue
between2 = g(p2_idx + 1, p1[2] - 1)
#if p1 and p2 can combine:
if between2 == 0:
result[index - l] = min(
result[index - l],
# don't combine
parse(length) + (result[index - l - 1] if index - l > 0 else 0),
# combine the block, p1 and p2
result[p2_idx - l - 1] if p2_idx - l > 0 else 0
)
else:
#f(b) = b.length + f(block before b)
result[index - l] = min(
result[index - l],
parse(length) + (result[index - l - 1] if index - l > 0 else 0)
)
# b and p1 cannot combine
else:
#f(b) = b.length + f(block before b)
result[index - l] = min(
result[index - l],
parse(length) + (result[index - l - 1] if index - l > 0 else 0)
)
p1_idx = chars[char][p1_idx]['prev']
#print l,r,result
memo[l][r] = result[r - l]
"""if top_level:
return (result, blocks)
else:"""
return result[r - l]
if len(blocks) == 1:
return ([parse(blocks[0][1])], blocks)
else:
return g(0, len(blocks) - 1, True)
"""s = ""
for i in xrange(300):
s = s + ['A','B','C'][random.randint(0,2)]"""
print f("abcccbcccbacccab") # b
print
print f("AAAABBBAC"); # C
print
print f("CAAAABBBA"); # C
print
print f("AABBAAAC"); # AABBC
print
print f("BAABCCCBBA"); # B
print
print f("aaaa")
print
The string answers for these longer examples were computed using jdehesa's answer:
t0 = time.time()
print f("BCBCCBCCBCABBACCBABAABBBABBBACCBBBAABBACBCCCACABBCAABACBBBBCCCBBAACBAABACCBBCBBAABCCCCCAABBBBACBBAAACACCBCCBBBCCCCCCCACBABACCABBCBBBBBCBABABBACCAACBCBBAACBBBBBCCBABACBBABABAAABCCBBBAACBCACBAABAAAABABB")
# BCBCCBCCBCABBACCBABCCAABBACBACABBCAABACAACBAABACCBBCBBCACCBACBABACCABBCCBABABBACCAACBCBBAABABACBBABABBCCAACBCACBAABBABB
t1 = time.time()
total = t1-t0
print total
t0 = time.time()
print f("CBBACAAAAABBBBCAABBCBAABBBCBCBCACACBAABCBACBBABCABACCCCBACBCBBCBACBBACCCBAAAACACCABAACCACCBCBCABAACAABACBABACBCBAACACCBCBCCCABACABBCABBAAAAABBBBAABAABBCACACABBCBCBCACCCBABCAACBCAAAABCBCABACBABCABCBBBBABCBACABABABCCCBBCCBBCCBAAABCABBAAABBCAAABCCBAABAABCAACCCABBCAABCBCBCBBAACCBBBACBBBCABAABCABABABABCA")
# CBBACCAABBCBAACBCBCACACBAABCBACBBABCABABACBCBBCBACBBABCACCABAACCACCBCBCABAACAABACBABACBCBAACACCBCBABACABBCBBCACACABBCBCBCABABCAACBCBCBCABACBABCABCABCBACABABACCBBCCBBCACBCCBAABAABCBBCAABCBCBCBBAACCACCABAABCABABABABCA
t1 = time.time()
total = t1-t0
print total
t0 = time.time()
print f("AADBDBEBBBBCABCEBCDBBBBABABDCCBCEBABADDCABEEECCECCCADDACCEEAAACCABBECBAEDCEEBDDDBAAAECCBBCEECBAEBEEEECBEEBDACDDABEEABEEEECBABEDDABCDECDAABDAEADEECECEBCBDDAEEECCEEACCBBEACDDDDBDBCCAAECBEDAAAADBEADBAAECBDEACDEABABEBCABDCEEAABABABECDECADCEDAEEEBBBCEDECBCABDEDEBBBABABEEBDAEADBEDABCAEABCCBCCEDCBBEBCECCCA")
# AADBDBECABCEBCDABABDCCBCEBABADDCABCCEADDACCEECCABBECBAEDCEEBBECCBBCEECBAEBCBEEBDACDDABEEABCBABEDDABCDECDAABDAEADEECECEBCBDDACCEEACCBBEACBDBCCAAECBEDDBEADBAAECBDEACDEABABEBCABDCEEAABABABECDECADCEDACEDECBCABDEDEABABEEBDAEADBEDABCAEABCCBCCEDCBBEBCEA
t1 = time.time()
total = t1-t0
print total
Another scala answer, using memoization and tailcall optimization (partly) (updated).
import scala.collection.mutable.HashSet
import scala.annotation._
object StringCondense extends App {
#tailrec
def groupConsecutive (s: String, sofar: List[String]): List[String] = s.toList match {
// def groupConsecutive (s: String): List[String] = s.toList match {
case Nil => sofar
// case Nil => Nil
case c :: str => {
val (prefix, rest) = (c :: str).span (_ == c)
// Strings of equal characters, longer than 3, don't make a difference to just 3
groupConsecutive (rest.mkString(""), (prefix.take (3)).mkString ("") :: sofar)
// (prefix.take (3)).mkString ("") :: groupConsecutive (rest.mkString(""))
}
}
// to count the effect of memoization
var count = 0
// recursively try to eliminate every group of 3 or more, brute forcing
// but for "aabbaabbaaabbbaabb", many reductions will lead sooner or
// later to the same result, so we try to detect these and avoid duplicate
// work
def moreThan2consecutive (s: String, seenbefore: HashSet [String]): String = {
if (seenbefore.contains (s)) s
else
{
count += 1
seenbefore += s
val sublists = groupConsecutive (s, Nil)
// val sublists = groupConsecutive (s)
val atLeast3 = sublists.filter (_.size > 2)
atLeast3.length match {
case 0 => s
case 1 => {
val res = sublists.filter (_.size < 3)
moreThan2consecutive (res.mkString (""), seenbefore)
}
case _ => {
val shrinked = (
for {idx <- (0 until sublists.size)
if (sublists (idx).length >= 3)
pre = (sublists.take (idx)).mkString ("")
post= (sublists.drop (idx+1)).mkString ("")
} yield {
moreThan2consecutive (pre + post, seenbefore)
}
)
(shrinked.head /: shrinked.tail) ((a, b) => if (a.length <= b.length) a else b)
}
}
}
}
// don't know what Rcd means, adopted from other solution but modified
// kind of a unit test **update**: forgot to reset count
testRcd (s: String, expected: String) : Boolean = {
count = 0
val seenbefore = HashSet [String] ()
val result = moreThan2consecutive (s, seenbefore)
val hit = result.equals (expected)
println (s"Input: $s\t result: ${result}\t expected ${expected}\t $hit\t count: $count");
hit
}
// some test values from other users with expected result
// **upd:** more testcases
def testgroup () : Unit = {
testRcd ("baabcccbba", "b")
testRcd ("aabbaaac", "aabbc")
testRcd ("aaaa", "")
testRcd ("aaaabbbac", "c")
testRcd ("abcccbcccbacccab", "b")
testRcd ("AAAABBBAC", "C")
testRcd ("CAAAABBBA", "C")
testRcd ("AABBAAAC", "AABBC")
testRcd ("BAABCCCBBA", "B")
testRcd ("AAABBBAAABBBAAABBBC", "C") // 377 subcalls reported by Yola,
testRcd ("AAABBBAAABBBAAABBBAAABBBC", "C") // 4913 when preceeded with AAABBB
}
testgroup
def testBigs () : Unit = {
/*
testRcd ("BCBCCBCCBCABBACCBABAABBBABBBACCBBBAABBACBCCCACABBCAABACBBBBCCCBBAACBAABACCBBCBBAABCCCCCAABBBBACBBAAACACCBCCBBBCCCCCCCACBABACCABBCBBBBBCBABABBACCAACBCBBAACBBBBBCCBABACBBABABAAABCCBBBAACBCACBAABAAAABABB",
"BCBCCBCCBCABBACCBABCCAABBACBACABBCAABACAACBAABACCBBCBBCACCBACBABACCABBCCBABABBACCAACBCBBAABABACBBABABBCCAACBCACBAABBABB")
*/
testRcd ("CBBACAAAAABBBBCAABBCBAABBBCBCBCACACBAABCBACBBABCABACCCCBACBCBBCBACBBACCCBAAAACACCABAACCACCBCBCABAACAABACBABACBCBAACACCBCBCCCABACABBCABBAAAAABBBBAABAABBCACACABBCBCBCACCCBABCAACBCAAAABCBCABACBABCABCBBBBABCBACABABABCCCBBCCBBCCBAAABCABBAAABBCAAABCCBAABAABCAACCCABBCAABCBCBCBBAACCBBBACBBBCABAABCABABABABCA",
"CBBACCAABBCBAACBCBCACACBAABCBACBBABCABABACBCBBCBACBBABCACCABAACCACCBCBCABAACAABACBABACBCBAACACCBCBABACABBCBBCACACABBCBCBCABABCAACBCBCBCABACBABCABCABCBACABABACCBBCCBBCACBCCBAABAABCBBCAABCBCBCBBAACCACCABAABCABABABABCA")
/*testRcd ("AADBDBEBBBBCABCEBCDBBBBABABDCCBCEBABADDCABEEECCECCCADDACCEEAAACCABBECBAEDCEEBDDDBAAAECCBBCEECBAEBEEEECBEEBDACDDABEEABEEEECBABEDDABCDECDAABDAEADEECECEBCBDDAEEECCEEACCBBEACDDDDBDBCCAAECBEDAAAADBEADBAAECBDEACDEABABEBCABDCEEAABABABECDECADCEDAEEEBBBCEDECBCABDEDEBBBABABEEBDAEADBEDABCAEABCCBCCEDCBBEBCECCCA",
"AADBDBECABCEBCDABABDCCBCEBABADDCABCCEADDACCEECCABBECBAEDCEEBBECCBBCEECBAEBCBEEBDACDDABEEABCBABEDDABCDECDAABDAEADEECECEBCBDDACCEEACCBBEACBDBCCAAECBEDDBEADBAAECBDEACDEABABEBCABDCEEAABABABECDECADCEDACEDECBCABDEDEABABEEBDAEADBEDABCAEABCCBCCEDCBBEBCEA")
*/
}
// for generated input, but with fixed seed, to compare the count with
// and without memoization
import util.Random
val r = new Random (31415)
// generate Strings but with high chances to produce some triples and
// longer sequences of char clones
def genRandomString () : String = {
(1 to 20).map (_ => r.nextInt (6) match {
case 0 => "t"
case 1 => "r"
case 2 => "-"
case 3 => "tt"
case 4 => "rr"
case 5 => "--"
}).mkString ("")
}
def testRandom () : Unit = {
(1 to 10).map (i=> testRcd (genRandomString, "random mode - false might be true"))
}
testRandom
testgroup
testRandom
// testBigs
}
Comparing the effect of memoization lead to interesting results:
Updated measurements. In the old values, I forgot to reset the counter, which leaded to much higher results. Now the spreading of results
is much more impressive and in total, the values are smaller.
No seenbefore:
Input: baabcccbba result: b expected b true count: 4
Input: aabbaaac result: aabbc expected aabbc true count: 2
Input: aaaa result: expected true count: 2
Input: aaaabbbac result: c expected c true count: 5
Input: abcccbcccbacccab result: b expected b true count: 34
Input: AAAABBBAC result: C expected C true count: 5
Input: CAAAABBBA result: C expected C true count: 5
Input: AABBAAAC result: AABBC expected AABBC true count: 2
Input: BAABCCCBBA result: B expected B true count: 4
Input: AAABBBAAABBBAAABBBC res: C expected C true count: 377
Input: AAABBBAAABBBAAABBBAAABBBC r: C expected C true count: 4913
Input: r--t----ttrrrrrr--tttrtttt--rr----result: rr--rr expected ? unknown ? false count: 1959
Input: ttrtt----tr---rrrtttttttrtr--rr result: r--rr expected ? unknown ? false count: 213
Input: tt----r-----ttrr----ttrr-rr--rr-- result: ttrttrrttrr-rr--rr-- ex ? unknown ? false count: 16
Input: --rr---rrrrrrr-r--rr-r--tt--rrrrr result: rr-r--tt-- expected ? unknown ? false count: 32
Input: tt-rrrrr--r--tt--rrtrrr------- result: ttr--tt--rrt expected ? unknown ? false count: 35
Input: --t-ttt-ttt--rrrrrt-rrtrttrr result: --tt-rrtrttrr expected ? unknown ? false count: 35
Input: rrt--rrrr----trrr-rttttrrtttrr result: rrtt- expected ? unknown ? false count: 1310
Input: ---tttrrrrrttrrttrr---tt-----tt result: rrttrr expected ? unknown ? false count: 1011
Input: -rrtt--rrtt---t-r--r---rttr-- result: -rrtt--rr-r--rrttr-- ex ? unknown ? false count: 9
Input: rtttt--rrrrrrrt-rrttt--tt--t result: r--t-rr--tt--t expectd ? unknown ? false count: 16
real 0m0.607s (without testBigs)
user 0m1.276s
sys 0m0.056s
With seenbefore:
Input: baabcccbba result: b expected b true count: 4
Input: aabbaaac result: aabbc expected aabbc true count: 2
Input: aaaa result: expected true count: 2
Input: aaaabbbac result: c expected c true count: 5
Input: abcccbcccbacccab result: b expected b true count: 11
Input: AAAABBBAC result: C expected C true count: 5
Input: CAAAABBBA result: C expected C true count: 5
Input: AABBAAAC result: AABBC expected AABBC true count: 2
Input: BAABCCCBBA result: B expected B true count: 4
Input: AAABBBAAABBBAAABBBC rest: C expected C true count: 28
Input: AAABBBAAABBBAAABBBAAABBBC C expected C true count: 52
Input: r--t----ttrrrrrr--tttrtttt--rr----result: rr--rr expected ? unknown ? false count: 63
Input: ttrtt----tr---rrrtttttttrtr--rr result: r--rr expected ? unknown ? false count: 48
Input: tt----r-----ttrr----ttrr-rr--rr-- result: ttrttrrttrr-rr--rr-- xpe? unknown ? false count: 8
Input: --rr---rrrrrrr-r--rr-r--tt--rrrrr result: rr-r--tt-- expected ? unknown ? false count: 19
Input: tt-rrrrr--r--tt--rrtrrr------- result: ttr--tt--rrt expected ? unknown ? false count: 12
Input: --t-ttt-ttt--rrrrrt-rrtrttrr result: --tt-rrtrttrr expected ? unknown ? false count: 16
Input: rrt--rrrr----trrr-rttttrrtttrr result: rrtt- expected ? unknown ? false count: 133
Input: ---tttrrrrrttrrttrr---tt-----tt result: rrttrr expected ? unknown ? false count: 89
Input: -rrtt--rrtt---t-r--r---rttr-- result: -rrtt--rr-r--rrttr-- ex ? unknown ? false count: 6
Input: rtttt--rrrrrrrt-rrttt--tt--t result: r--t-rr--tt--t expected ? unknown ? false count: 8
real 0m0.474s (without testBigs)
user 0m0.852s
sys 0m0.060s
With tailcall:
real 0m0.478s (without testBigs)
user 0m0.860s
sys 0m0.060s
For some random strings, the difference is bigger than a 10fold.
For long Strings with many groups one could, as an improvement, eliminate all groups which are the only group of that character, for instance:
aa bbb aa ccc xx ddd aa eee aa fff xx
The groups bbb, ccc, ddd, eee and fff are unique in the string, so they can't fit to something else and could all be eliminated, and the order of removal is will not matter. This would lead to the intermediate result
aaaa xx aaaa xx
and a fast solution. Maybe I try to implement it too. However, I guess, it will be possible to produce random Strings, where this will have a big impact and by a different form of random generated strings, to distributions, where the impact is low.
Here is a Python solution (function reduce_min), not particularly smart but I think fairly easy to understand (excessive amount of comments added for answer clarity):
def reductions(s, min_len):
"""
Yields every possible reduction of s by eliminating contiguous blocks
of l or more repeated characters.
For example, reductions('AAABBCCCCBAAC', 3) yields
'BBCCCCBAAC' and 'AAABBBAAC'.
"""
# Current character
curr = ''
# Length of current block
n = 0
# Start position of current block
idx = 0
# For each character
for i, c in enumerate(s):
if c != curr:
# New block begins
if n >= min_len:
# If previous block was long enough
# yield reduced string without it
yield s[:idx] + s[i:]
# Start new block
curr = c
n = 1
idx = i
else:
# Still in the same block
n += 1
# Yield reduction without last block if it was long enough
if n >= min_len:
yield s[:idx]
def reduce_min(s, min_len):
"""
Finds the smallest possible reduction of s by successive
elimination of contiguous blocks of min_len or more repeated
characters.
"""
# Current set of possible reductions
rs = set([s])
# Current best solution
result = s
# While there are strings to reduce
while rs:
# Get one element
r = rs.pop()
# Find reductions
r_red = list(reductions(r, min_len))
# If no reductions are found it is irreducible
if len(r_red) == 0 and len(r) < len(result):
# Replace if shorter than current best
result = r
else:
# Save reductions for next iterations
rs.update(r_red)
return result
assert reduce_min("BAABCCCBBA", 3) == "B"
assert reduce_min("AABBAAAC", 3) == "AABBC"
assert reduce_min("AAAA", 3) == ""
assert reduce_min("AAAABBBAC", 3) == "C"
EDIT: Since people seem to be posting C++ solutions, here is mine in C++ (again, function reduce_min):
#include <string>
#include <vector>
#include <unordered_set>
#include <iterator>
#include <utility>
#include <cassert>
using namespace std;
void reductions(const string &s, unsigned int min_len, vector<string> &rs)
{
char curr = '\0';
unsigned int n = 0;
unsigned int idx = 0;
for (auto it = s.begin(); it != s.end(); ++it)
{
if (curr != *it)
{
auto i = distance(s.begin(), it);
if (n >= min_len)
{
rs.push_back(s.substr(0, idx) + s.substr(i));
}
curr = *it;
n = 1;
idx = i;
}
else
{
n += 1;
}
}
if (n >= min_len)
{
rs.push_back(s.substr(0, idx));
}
}
string reduce_min(const string &s, unsigned int min_len)
{
unordered_set<string> rs { s };
string result = s;
vector<string> rs_new;
while (!rs.empty())
{
auto it = rs.begin();
auto r = *it;
rs.erase(it);
rs_new.clear();
reductions(r, min_len, rs_new);
if (rs_new.empty() && r.size() < result.size())
{
result = move(r);
}
else
{
rs.insert(rs_new.begin(), rs_new.end());
}
}
return result;
}
int main(int argc, char **argv)
{
assert(reduce_min("BAABCCCBBA", 3) == "B");
assert(reduce_min("AABBAAAC", 3) == "AABBC");
assert(reduce_min("AAAA", 3) == "");
assert(reduce_min("AAAABBBAC", 3) == "C");
return 0;
}
If you can use C++17 you can save memory by using string views.
EDIT 2: About the complexity of the algorithm. It is not straightforward to figure out, and as I said the algorithm is meant to be simple more than anything, but let's see. In the end, it is more or less the same as a breadth-first search. Let's say the string length is n, and, for generality, let's say the minimum block length (value 3 in the question) is m. In the first level, we can generate up to n / m reductions in the worst case. For each of these, we can generate up to (n - m) / m reductions, and so on. So basically, at "level" i (loop iteration i) we create up to (n - i * m) / m reductions per string we had, and each of these will take O(n - i * m) time to process. The maximum number of levels we can have is, again, n / m. So the complexity of the algorithm (if I'm not making mistakes) should have the form:
O( sum {i = 0 .. n / m} ( O(n - i * m) * prod {j = 0 .. i} ((n - i * m) / m) ))
|-Outer iters--| |---Cost---| |-Prev lvl-| |---Branching---|
Whew. So this should be something like:
O( sum {i = 0 .. n / m} (n - i * m) * O(n^i / m^i) )
Which in turn would collapse to:
O((n / m)^(n / m))
So yeah, the algorithm is more or less simple, but it can run into exponential cost cases (the bad cases would be strings made entirely of exactly m-long blocks, like AAABBBCCCAAACCC... for m = 3).
I was reading Spark correlation algorithm source code and while going through the code, I coulddn't understand this particular peace of code.
This is from the file : org/apache/spark/mllib/linalg/BLAS.scala
def spr(alpha: Double, v: Vector, U: Array[Double]): Unit = {
val n = v.size
v match {
case DenseVector(values) =>
NativeBLAS.dspr("U", n, alpha, values, 1, U)
case SparseVector(size, indices, values) =>
val nnz = indices.length
var colStartIdx = 0
var prevCol = 0
var col = 0
var j = 0
var i = 0
var av = 0.0
while (j < nnz) {
col = indices(j)
// Skip empty columns.
colStartIdx += (col - prevCol) * (col + prevCol + 1) / 2
av = alpha * values(j)
i = 0
while (i <= j) {
U(colStartIdx + indices(i)) += av * values(i)
i += 1
}
j += 1
prevCol = col
}
}
}
I do not know Scala and that could be the reason I could not understand it. Can someone explain what is happening here.
It is being called from Rowmatrix.scala
def computeGramianMatrix(): Matrix = {
val n = numCols().toInt
checkNumColumns(n)
// Computes n*(n+1)/2, avoiding overflow in the multiplication.
// This succeeds when n <= 65535, which is checked above
val nt = if (n % 2 == 0) ((n / 2) * (n + 1)) else (n * ((n + 1) / 2))
// Compute the upper triangular part of the gram matrix.
val GU = rows.treeAggregate(new BDV[Double](nt))(
seqOp = (U, v) => {
BLAS.spr(1.0, v, U.data)
U
}, combOp = (U1, U2) => U1 += U2)
RowMatrix.triuToFull(n, GU.data)
}
The correlation is defined here:
https://en.wikipedia.org/wiki/Pearson_correlation_coefficient
The final goal is to understand the Spark correlation algorithm.
Update 1: Relevent paper https://stanford.edu/~rezab/papers/linalg.pdf
I am working on an extrusion function to create a mesh given a 2D texture and the thickness of it.
Example:
I have achieved finding the outline of the texture by simply looking for the pixels either near the edge or near transparent ones. It works great even for concave (donut-shaped) shapes but now I am left with an array of outline pixels.
Here is the result:
The problem is that the values, by being ordered from top-left to bottom-right, they are not suitable for building an actual 3D outline.
My current idea is the following:
Step 1.
From index [0], look at the right-hand side for the nearest contiguous point different from the starting point.
If found, move it into another array.
If nothing, look at the bottom. Continue until the starting point has been reached.
Step2.
Pick another pixel, if any, from the pixels remained in the array.
Repeat from Step1.
This, in my head, would work but it seems quite inefficient. Researching, I found about the Moore-Neighbor tracing algorithm but I couldn't find anywhere an example where it worked with convex shapes.
Any thoughts?
At the end, I managed to find my own answer, so here I want to share it:
After finding the outline of a given image (using the alpha value of each pixel), the pixels will be ordered in rows, good for drawing them but bad for constructing a mesh.
So, the next step is to find contiguous lines. This is done by checking first if there are any neighbors to the found pixel giving priority to the ones top/left/right/bottom (otherwise it will skip the corners).
Keep going until no pixels are left in the original array.
Here is the actual implementation (for Babylon.js but the idea works with any other engine):
Playground: https://www.babylonjs-playground.com/#9GPMUY#11
var GetTextureOutline = function (data, keepOutline, keepOtherPixels) {
var not_outline = [];
var pixels_list = [];
for (var j = 0; j < data.length; j = j + 4) {
var alpha = data[j + 3];
var current_alpha_index = j + 3;
// Not Invisible
if (alpha != 0) {
var top_alpha = data[current_alpha_index - (canvasWidth * 4)];
var bottom_alpha = data[current_alpha_index + (canvasWidth * 4)];
var left_alpha = data[current_alpha_index - 4];
var right_alpha = data[current_alpha_index + 4];
if ((top_alpha === undefined || top_alpha == 0) ||
(bottom_alpha === undefined || bottom_alpha == 0) ||
(left_alpha === undefined || left_alpha == 0) ||
(right_alpha === undefined || right_alpha == 0)) {
pixels_list.push({
x: (j / 4) % canvasWidth,
y: parseInt((j / 4) / canvasWidth),
color: new BABYLON.Color3(data[j] / 255, data[j + 1] / 255, data[j + 2] / 255),
alpha: data[j + 3] / 255
});
if (!keepOutline) {
data[j] = 255;
data[j + 1] = 0;
data[j + 2] = 255;
}
} else if (!keepOtherPixels) {
not_outline.push(j);
}
}
}
// Remove not-outline pixels
for (var i = 0; i < not_outline.length; i++) {
if (!keepOtherPixels) {
data[not_outline[i]] = 0;
data[not_outline[i] + 1] = 0;
data[not_outline[i] + 2] = 0;
data[not_outline[i] + 3] = 0;
}
}
return pixels_list;
}
var ExtractLinesFromPixelsList = function (pixelsList, sortPixels) {
if (sortPixels) {
// Sort pixelsList
function sortY(a, b) {
if (a.y == b.y) return a.x - b.x;
return a.y - b.y;
}
pixelsList.sort(sortY);
}
var lines = [];
var line = [];
var pixelAdded = true;
var skipDiagonals = true;
line.push(pixelsList[0]);
pixelsList.splice(0, 1);
var countPixels = 0;
while (pixelsList.length != 0) {
if (!pixelAdded && !skipDiagonals) {
lines.push(line);
line = [];
line.push(pixelsList[0]);
pixelsList.splice(0, 1);
} else if (!pixelAdded) {
skipDiagonals = false;
}
pixelAdded = false;
for (var i = 0; i < pixelsList.length; i++) {
if ((skipDiagonals && (
line[line.length - 1].x + 1 == pixelsList[i].x && line[line.length - 1].y == pixelsList[i].y ||
line[line.length - 1].x - 1 == pixelsList[i].x && line[line.length - 1].y == pixelsList[i].y ||
line[line.length - 1].x == pixelsList[i].x && line[line.length - 1].y + 1 == pixelsList[i].y ||
line[line.length - 1].x == pixelsList[i].x && line[line.length - 1].y - 1 == pixelsList[i].y)) || (!skipDiagonals && (
line[line.length - 1].x + 1 == pixelsList[i].x && line[line.length - 1].y + 1 == pixelsList[i].y ||
line[line.length - 1].x + 1 == pixelsList[i].x && line[line.length - 1].y - 1 == pixelsList[i].y ||
line[line.length - 1].x - 1 == pixelsList[i].x && line[line.length - 1].y + 1 == pixelsList[i].y ||
line[line.length - 1].x - 1 == pixelsList[i].x && line[line.length - 1].y - 1 == pixelsList[i].y
))) {
line.push(pixelsList[i]);
pixelsList.splice(i, 1);
i--;
pixelAdded = true;
skipDiagonals = true;
}
}
}
lines.push(line);
return lines;
}
Algorithm Looping over pixels, we only check each pixel once, skipping empty cells, and store it in a list as there won't be duplicates.
isEmpty implementation depends on how transparency works in your case, if a certain color is considered transparent, below is a case where we have an alpha channel.
threshold is the alpha level that represent the least-visibility for a cell to be considered non-empty.
isBorder will check if any of Moore neighbors is empty, in that case it is a border cell, otherwise it's not because it is surrounded by filled cells.
isEmpty(x,y): image[x,y].alpha <= threshold
isBorder(x,y)
: if isEmpty(x , y-1): return true
: if isEmpty(x , y+1): return true
: if isEmpty(x-1, y ): return true
: if isEmpty(x+1, y ): return true
: if isEmpty(x-1, y-1): return true
: if isEmpty(x-1, y+1): return true
: if isEmpty(x+1, y-1): return true
: if isEmpty(x+1, y+1): return true
: otherwise: return false
getBorderCellList()
: l = empty-list
: for x in 0..image.width
: : for y in 0..image.height
: : : if !isEmpty(x,y)
: : : : if isBorder(x,y)
: : : : : l.add(x,y)
: return l
Optimization You could optimize this by having a pre-computed boolean e[image.width][image.height] where e[x,y] = 1 if image[x,y]is not-empty, then use it directly to check, like isBorder(x,y): e[x-1,y] | e[x+1,y] | .. | e[x+1,y+1].
init()
: for x in 0..image.width
: : for y in 0..image.height
: : : e[x,y] = isEmpty(x,y)
isEmpty(x,y): image[x,y].alpha <= threshold
isBorder(x,y): e[x-1,y] | e[x+1,y] | .. | e[x+1,y+1]
getBorderCellList()
: l = empty-list
: for x in 0..image.width
: : for y in 0..image.height
: : : if not e[x,y]
: : : : if isBorder(x,y)
: : : : : l.add(x,y)
: return l
Based on this question & answer "How to retrieve unique count of a field using Kibana + Elastic Search"
I have been able to collect the individual count of the unique IP addresses from our Apache logs, however, What I actually want to do is to be able to display the count of the individual IP addresses, i.e. how many unique visitors.
I think I need to use the terms_stats facet to do this but I don't know what to set as the "value_field"
This is not possible with the current version of the kibana.
but i have what i did to achieve this is created the custom histogram panel.
to create the custom histogram panel, just copy the existing histogram and modify config.js, module.js to change all the path references to the new panel.
override the doSearch function to use the query http://www.elasticsearch.org/blog/count-elasticsearch/
and update the results parsing logic.
look for function
b.get_data = function(a, j, k)
return b.populate_modal(n), p = n.doSearch(), p.then(function(c) {
if (b.panelMeta.loading = !1, 0 === j && (b.legend = [], b.hits = 0, a = [], b.annotations = [], k = b.query_id = (new Date).getTime()), d.isUndefined(c.error)) {
if (b.query_id === k) {
var i, n, p, q = 0;
o = JSON.parse("[{\"query\":\"*\",\"alias\":\"\",\"color\":\"#7EB26D\",\"id\":0,\"pin\":false,\"type\":\"lucene\",\"enable\":true,\"parent\" : 0}]");
d.each(o, function(e) {
//alert(JSON.stringify(c));
//var f = c.aggregations.monthly.buckets[e.id];
if (d.isUndefined(a[q]) || 0 === j) {
var h = {interval: m,start_date: l && l.from,end_date: l && l.to,fill_style: b.panel.derivative ? "null" : b.panel.zerofill ? "minimal" : "no"};
i = new g.ZeroFilled(h), n = 0, p = {}
} else
i = a[q].time_series, n = a[q].hits, p = a[q].counters;
d.each(c.aggregations.monthly.buckets, function(a) {
var c;
n += a.visitor_count.value, b.hits += a.visitor_count.value, p[a.key] = (p[a.key] || 0) + a.visitor_count.value, "count" === b.panel.mode ? c = (i._data[a.key] || 0) + a.visitor_count.value : "mean" === b.panel.mode ? c = ((i._data[a.key] || 0) * (p[a.key] - a.visitor_count.value) + a.mean * a.visitor_count.value) / p[a.key] : "min" === b.panel.mode ? c = d.isUndefined(i._data[a.key]) ? a.min : i._data[a.key] < a.min ? i._data[a.key] : a.min : "max" === b.panel.mode ? c = d.isUndefined(i._data[a.key]) ? a.max : i._data[a.key] > a.max ? i._data[a.key] : a.max : "total" === b.panel.mode && (c = (i._data[a.key] || 0) + a.total), i.addValue(a.key, c)
}), b.legend[q] = {query: e,hits: n}, a[q] = {info: e,time_series: i,hits: n,counters: p}, q++
}), b.panel.annotate.enable && (b.annotations = b.annotations.concat(d.map(c.hits.hits, function(a) {
var c = d.omit(a, "_source", "sort", "_score"), g = d.extend(e.flatten_json(a._source), c);
return {min: a.sort[1],max: a.sort[1],eventType: "annotation",title: null,description: "<small><i class='icon-tag icon-flip-vertical'></i> " + g[b.panel.annotate.field] + "</small><br>" + f(a.sort[1]).format("YYYY-MM-DD HH:mm:ss"),score: a.sort[0]}
})), b.annotations = d.sortBy(b.annotations, function(a) {
return a.score * ("desc" === b.panel.annotate.sort[1] ? -1 : 1)
}), b.annotations = b.annotations.slice(0, b.panel.annotate.size))
}
} else
b.panel.error = b.parse_error(c.error);
b.$emit("render", a), j < h.indices.length - 1 && b.get_data(a, j + 1, k)
})
I need to create EAN 8 bar code programmatically.
I search an algorithm to calculate the checksum digit.
The algorithm is covered in this wikipedia article on EAN, note that EAN-8 is calculated in the same way as EAN-13.
Here's a worked example from http://www.barcodeisland.com/ean8.phtml :
Assuming we wish to encode the 7-digit message "5512345", we would calculate the checksum in the following manner:
Barcode 5 5 1 2 3 4 5
Odd/Even Pos? O E O E O E O
Weighting 3 1 3 1 3 1 3
Calculation 5*3 5*1 1*3 2*1 3*3 4*1 5*3
Weighted Sum 15 5 3 2 9 4 15
The total is 15 + 5 + 3 + 2 + 9 + 4 + 15 = 53. 7 must be added to 53 to produce a number evenly divisible by 10, thus the checksum digit is 7 and the completed bar code value is "55123457".
string code="55123457";
int sum1 = code[1] + code[3] + code[5]
int sum2 = 3 * (code[0] + code[2] + code[4] + code[6]);
int checksum_value = sum1 + sum2;
int checksum_digit = 10 - (checksum_value % 10);
if (checksum_digit == 10)
checksum_digit = 0;
int checkSum(const std::vector<int>& code) const
{
if (code.size() < 8) return false;
for( SIZE_T i = 0; i< code.size(); i++ )
{
if( code[i] < 0 ) return false;
}
int sum1 = code[1] + code[3] + code[5]
int sum2 = 3 * (code[0] + code[2] + code[4] + code[6]);
int checksum_value = sum1 + sum2;
int checksum_digit = 10 - (checksum_value % 10);
if (checksum_digit == 10) checksum_digit = 0;
return checksum_digit;
}
Sorry for re-opening
JAVA VERSION
public int checkSum(String code){
int val=0;
for(int i=0;i<code.length();i++){
val+=((int)Integer.parseInt(code.charAt(i)+""))*((i%2==0)?1:3);
}
int checksum_digit = 10 - (val % 10);
if (checksum_digit == 10) checksum_digit = 0;
return checksum_digit;
}
Reawakened with a C# version:
public static bool IsValidEan13(string eanBarcode)
{
return IsValidEan(eanBarcode, 13);
}
public static bool IsValidEan12(string eanBarcode)
{
return IsValidEan(eanBarcode, 12);
}
public static bool IsValidEan14(string eanBarcode)
{
return IsValidEan(eanBarcode, 14);
}
public static bool IsValidEan8(string eanBarcode)
{
return IsValidEan(eanBarcode, 8);
}
private static bool IsValidEan(string eanBarcode, int length)
{
if (eanBarcode.Length != length) return false;
var allDigits = eanBarcode.Select(c => int.Parse(c.ToString(CultureInfo.InvariantCulture))).ToArray();
var s = length%2 == 0 ? 3 : 1;
var s2 = s == 3 ? 1 : 3;
return allDigits.Last() == (10 - (allDigits.Take(length-1).Select((c, ci) => c*(ci%2 == 0 ? s : s2)).Sum()%10))%10;
}
Here is a MySQL version for EAN13:
SET #first12digits="123456789012";
SELECT #first12digits,
IF (
(#check:=10-MOD(
(CAST(SUBSTRING(#first12digits, 1, 1) AS DECIMAL))+
(CAST(SUBSTRING(#first12digits, 2, 1) AS DECIMAL) * 3)+
(CAST(SUBSTRING(#first12digits, 3, 1) AS DECIMAL))+
(CAST(SUBSTRING(#first12digits, 4, 1) AS DECIMAL) * 3)+
(CAST(SUBSTRING(#first12digits, 5, 1) AS DECIMAL))+
(CAST(SUBSTRING(#first12digits, 6, 1) AS DECIMAL) * 3)+
(CAST(SUBSTRING(#first12digits, 7, 1) AS DECIMAL))+
(CAST(SUBSTRING(#first12digits, 8, 1) AS DECIMAL) * 3)+
(CAST(SUBSTRING(#first12digits, 9, 1) AS DECIMAL))+
(CAST(SUBSTRING(#first12digits, 10, 1) AS DECIMAL) * 3)+
(CAST(SUBSTRING(#first12digits, 11, 1) AS DECIMAL))+
(CAST(SUBSTRING(#first12digits, 12, 1) AS DECIMAL) * 3)
,10)) = 10, 0, #check
) AS checkDigit;
There was a bug. If Calc result = 10 then check digit = 0.
Here below a better version for EAN14.
SET #first13digits="1234567890123";
SELECT #txCode13:=#first13digits,
#iCheck := (
10 - (
(
MID(#txCode13, 2, 1) +
MID(#txCode13, 4, 1) +
MID(#txCode13, 6, 1) +
MID(#txCode13, 8, 1) +
MID(#txCode13, 10, 1) +
MID(#txCode13, 12, 1)
) + (
MID(#txCode13, 1, 1) +
MID(#txCode13, 3, 1) +
MID(#txCode13, 5, 1) +
MID(#txCode13, 7, 1) +
MID(#txCode13, 9, 1) +
MID(#txCode13, 11, 1) +
MID(#txCode13, 13, 1)
) * 3 ) % 10
) AS iCheck,
#iCheckDigit := IF(#iCheck = 10, 0, #iCheck) AS checkDigit,
CONCAT(#t
xCode13, CAST(#iCheckDigit AS CHAR)) AS EAN14WithCheck
Here is the Java version for EAN13
private int calcChecksum(String first12digits) {
char[] char12digits = first12digits.toCharArray();
int[] ean13 = {1,3};
int sum = 0;
for(int i = 0 ; i<char12digits.length; i++){
sum += Character.getNumericValue(char12digits[i]) * ean13[i%2];
}
int checksum = 10 - sum%10;
if(checksum == 10){
checksum = 0;
}
return checksum;
}
class GTIN(object):
def __init__(self, barcode=''):
self.barcode = barcode
def __checkDigit(self, digits):
total = sum(digits) + sum(map(lambda d: d*2, digits[-1::-2]))
return (10 - (total % 10)) % 10
def validateCheckDigit(self, barcode=''):
barcode = (barcode if barcode else self.barcode)
if len(barcode) in (8,12,13,14) and barcode.isdigit():
digits = map(int, barcode)
checkDigit = self.__checkDigit( digits[0:-1] )
return checkDigit == digits[-1]
return False
def addCheckDigit(self, barcode=''):
barcode = (barcode if barcode else self.barcode)
if len(barcode) in (7,11,12,13) and barcode.isdigit():
digits = map(int, barcode)
return barcode + str(self.__checkDigit(digits))
return ''
Today I need a PHP version, I remember about this page and copy from the Java version. Thank you.
function getEAN13($txEan12)
{
$iVal=0;
for($i=0; $i<strlen($txEan12); $i++)
{
$iSingleCharVal = intval(substr($txEan12, $i, 1)); // extract value of one char
$iSingleCharMult = $iSingleCharVal * ($i%2==0 ? 1 : 3); // calculate depending from position
$iVal+= $iSingleCharMult; // sum
}
$iCheckDigit = 10 - ($iVal % 10);
if ($iCheckDigit == 10) $iCheckDigit = 0;
return $txEan12 . $iCheckDigit;
}
Java Version:
It works perfectly
public static int checkSum(String code){
int val=0;
for(int i=0; i<code.length()-1; i++){
val+=((int)Integer.parseInt(code.charAt(i)+""))*((i%2==0)?1:3);
}
int checksum_digit = (10 - (val % 10)) % 10;
return checksum_digit;
}
Python EAN13 check-digit calculation based on Najoua Mahi's Java function:
def generateEAN13CheckDigit(self, first12digits):
charList = [char for char in first12digits]
ean13 = [1,3]
total = 0
for order, char in enumerate(charList):
total += int(char) * ean13[order % 2]
checkDigit = 10 - total % 10
if (checkDigit == 10):
return 0
return checkDigit
This works on both EAN 13 and EAN8:
public static String generateEAN(String barcode) {
int first = 0;
int second = 0;
if(barcode.length() == 7 || barcode.length() == 12) {
for (int counter = 0; counter < barcode.length() - 1; counter++) {
first = (first + Integer.valueOf(barcode.substring(counter, counter + 1)));
counter++;
second = (second + Integer.valueOf(barcode.substring(counter, counter + 1)));
}
second = second * 3;
int total = second + first;
int roundedNum = Math.round((total + 9) / 10 * 10);
barcode = barcode + String.valueOf(roundedNum - total);
}
return barcode;
}
This is a code I wrote in VFP (Visual FoxPro 9), for both EAN-8 and EAN-13
Lparameters lcBarcode,llShowErrorMessage
If Vartype(m.lcBarcode)<>'C'
If m.llShowErrorMessage
MessageBox([Type of parameter is incorect!],0+16,[Error Message])
EndIf
Return .f.
EndIf
If Len(Chrtran(Alltrim(m.lcBarcode),[0123456789],[]))>0
If m.llShowErrorMessage
MessageBox([Provided barcode contains invalid characters!],0+16,[Error Message])
EndIf
Return .f.
EndIf
If Len(Alltrim(m.lcBarcode))=0
If m.llShowErrorMessage
MessageBox([The length of provided barcode is 0 (zero)!],0+16,[Error Message])
EndIf
Return .f.
EndIf
If !InList(Len(Alltrim(m.lcBarcode)),8,13)
If m.llShowErrorMessage
MessageBox([Provided barcode is not an EAN-8 or EAN-13 barcode!],0+16,[Error Message])
EndIf
Return .f.
EndIf
Local lnCheck as Integer, lnSum as Integer, lnOriginalCheck as Integer,jj as Integer
jj=0
lnSum=0
m.lnOriginalCheck = Cast(Right(Alltrim(m.lcBarcode),1) as Integer)
m.lcBarcode = Left(Alltrim(m.lcBarcode),Len(Alltrim(m.lcBarcode))-1)
For ii = Len(m.lcBarcode) to 1 step -1
jj=jj+1
lnSum = lnSum + Cast(Substr(m.lcBarcode,ii,1) as Integer) * Iif(Mod(jj,2)=0,1,3)
Next
lnCheck = 10-Mod(lnSum,10)
lnCheck = Iif(lnCheck =10,0,lnCheck)
Return (lnCheck = lnOriginalCheck)
JavaScript version for EAN-8 and EAN-13
function checksum(code) {
const sum = code.split('').reverse().reduce((sum, char, idx) => {
let digit = Number.parseInt(char);
let weight = (idx + 1) % 2 === 0 ? 1 : 3;
let partial = digit * weight;
return sum + partial;
}, 0);
const remainder = sum % 10;
const checksum = remainder ? (10 - remainder) : 0;
return checksum;
}
Mini Javascript Version
function checksum(code){
return (10 - (code.split('').reduce((s, e, i) => { return s + parseInt(e) * ((i%2==0)?1:3) },0) % 10)) % 10;
}
=INT(CONCAT([#Code],MOD(10 - MOD((MID([#Code], 2, 1) + MID([#Code], 4, 1) + MID([#Code], 6, 1)) + (3*(MID([#Code], 1, 1) + MID([#Code], 3, 1) + MID([#Code], 5, 1) + MID([#Code], 7, 1))),10), 10)))
The above formula will calculate the check character without the need to use a macro or change to XLSM.
Note: Only works for EAN-8.