Aho-Corasick algorithm (substrings search) implementation - performance issue
up vote
0
down vote
favorite
I solved this programming challenge where the goal is to give score to strings based on how much score certain substrings are worth (including repeating substrings).
Don't worry about what int values, valIndexes
and the arguments of createTree()
mean, just know that they have nothing to do with the search or organization of the data, they're only there for the score calculation.
The performance bottleneck of my code is interlink()
, everything else works reasonably fast, any suggestions for how to fix this performance issue are greatly appreciated.
The input strings for createTree()
and scan()
are expected to contain only lowercase a-z characters.
class Tree {
public int values, valIndexes;
public Tree branches = new Tree[26];
public Tree link;
public static Tree createTree(String strs, int worth){
Tree mainTree = new Tree();
Tree currentNode;
for(int i = 0; i < strs.length; i++){
currentNode = mainTree;
for(int c = 0; c < strs[i].length(); c++){
int idx = strs[i].charAt(c) - 'a';
if(currentNode.branches[idx] == null)
currentNode.branches[idx] = new Tree();
currentNode = currentNode.branches[idx];
if(strs[i].length() == c + 1)
currentNode.addValue(worth[i], i);
}
}
mainTree.interlink(mainTree, "");
return mainTree;
}
public int scan(String str, int minIdx, int maxIdx){
System.out.println("DNA sequence length = " + str.length());
int score = 0;
ArrayList<Tree> nodes = new ArrayList<Tree>();
for(int index = 0; index < str.length(); index++){
for(int e = 0; e < nodes.size(); e++) // advance nodes to next char
nodes.set(e, nodes.get(e).branches[str.charAt(index) - 'a']);
while(nodes.remove(null));
if(nodes.isEmpty()){ // if no nodes left, continue the search from first node
nodes.add(this.branches[str.charAt(index) - 'a']);
nodes.remove(null);
}
for(int e = 0; e < nodes.size(); e++){
Tree node = nodes.get(e);
if(node.link != null)
if(!nodes.contains(node.link))
nodes.add(node.link);
if(node.values != null)
for(int x = 0; x < node.values.length; x++)
if(node.valIndexes[x] >= minIdx && node.valIndexes[x] <= maxIdx)
score += node.values[x];
}
}
return score;
}
private void interlink(Tree mainTree, String path){
for(int i = 0; i < branches.length; i++){
if(branches[i] != null)
branches[i].interlink(mainTree, path + (char)(i + 'a'));
}
if(path.length() < 2) return;
Tree node;
for(int k = 1; k < path.length(); k++){
node = mainTree.getNode(path.substring(k));
if(node != null){
link = node;
break;
}
}
}
private Tree getNode(String str){
Tree node = this;
for(int c = 0; c < str.length(); c++){
node = node.branches[str.charAt(c) - 'a'];
if(node == null)
break;
}
return node;
}
private void addValue(int val, int idx){
// ... this part is irrelevant ...
}
}
java performance algorithm strings
add a comment |
up vote
0
down vote
favorite
I solved this programming challenge where the goal is to give score to strings based on how much score certain substrings are worth (including repeating substrings).
Don't worry about what int values, valIndexes
and the arguments of createTree()
mean, just know that they have nothing to do with the search or organization of the data, they're only there for the score calculation.
The performance bottleneck of my code is interlink()
, everything else works reasonably fast, any suggestions for how to fix this performance issue are greatly appreciated.
The input strings for createTree()
and scan()
are expected to contain only lowercase a-z characters.
class Tree {
public int values, valIndexes;
public Tree branches = new Tree[26];
public Tree link;
public static Tree createTree(String strs, int worth){
Tree mainTree = new Tree();
Tree currentNode;
for(int i = 0; i < strs.length; i++){
currentNode = mainTree;
for(int c = 0; c < strs[i].length(); c++){
int idx = strs[i].charAt(c) - 'a';
if(currentNode.branches[idx] == null)
currentNode.branches[idx] = new Tree();
currentNode = currentNode.branches[idx];
if(strs[i].length() == c + 1)
currentNode.addValue(worth[i], i);
}
}
mainTree.interlink(mainTree, "");
return mainTree;
}
public int scan(String str, int minIdx, int maxIdx){
System.out.println("DNA sequence length = " + str.length());
int score = 0;
ArrayList<Tree> nodes = new ArrayList<Tree>();
for(int index = 0; index < str.length(); index++){
for(int e = 0; e < nodes.size(); e++) // advance nodes to next char
nodes.set(e, nodes.get(e).branches[str.charAt(index) - 'a']);
while(nodes.remove(null));
if(nodes.isEmpty()){ // if no nodes left, continue the search from first node
nodes.add(this.branches[str.charAt(index) - 'a']);
nodes.remove(null);
}
for(int e = 0; e < nodes.size(); e++){
Tree node = nodes.get(e);
if(node.link != null)
if(!nodes.contains(node.link))
nodes.add(node.link);
if(node.values != null)
for(int x = 0; x < node.values.length; x++)
if(node.valIndexes[x] >= minIdx && node.valIndexes[x] <= maxIdx)
score += node.values[x];
}
}
return score;
}
private void interlink(Tree mainTree, String path){
for(int i = 0; i < branches.length; i++){
if(branches[i] != null)
branches[i].interlink(mainTree, path + (char)(i + 'a'));
}
if(path.length() < 2) return;
Tree node;
for(int k = 1; k < path.length(); k++){
node = mainTree.getNode(path.substring(k));
if(node != null){
link = node;
break;
}
}
}
private Tree getNode(String str){
Tree node = this;
for(int c = 0; c < str.length(); c++){
node = node.branches[str.charAt(c) - 'a'];
if(node == null)
break;
}
return node;
}
private void addValue(int val, int idx){
// ... this part is irrelevant ...
}
}
java performance algorithm strings
add a comment |
up vote
0
down vote
favorite
up vote
0
down vote
favorite
I solved this programming challenge where the goal is to give score to strings based on how much score certain substrings are worth (including repeating substrings).
Don't worry about what int values, valIndexes
and the arguments of createTree()
mean, just know that they have nothing to do with the search or organization of the data, they're only there for the score calculation.
The performance bottleneck of my code is interlink()
, everything else works reasonably fast, any suggestions for how to fix this performance issue are greatly appreciated.
The input strings for createTree()
and scan()
are expected to contain only lowercase a-z characters.
class Tree {
public int values, valIndexes;
public Tree branches = new Tree[26];
public Tree link;
public static Tree createTree(String strs, int worth){
Tree mainTree = new Tree();
Tree currentNode;
for(int i = 0; i < strs.length; i++){
currentNode = mainTree;
for(int c = 0; c < strs[i].length(); c++){
int idx = strs[i].charAt(c) - 'a';
if(currentNode.branches[idx] == null)
currentNode.branches[idx] = new Tree();
currentNode = currentNode.branches[idx];
if(strs[i].length() == c + 1)
currentNode.addValue(worth[i], i);
}
}
mainTree.interlink(mainTree, "");
return mainTree;
}
public int scan(String str, int minIdx, int maxIdx){
System.out.println("DNA sequence length = " + str.length());
int score = 0;
ArrayList<Tree> nodes = new ArrayList<Tree>();
for(int index = 0; index < str.length(); index++){
for(int e = 0; e < nodes.size(); e++) // advance nodes to next char
nodes.set(e, nodes.get(e).branches[str.charAt(index) - 'a']);
while(nodes.remove(null));
if(nodes.isEmpty()){ // if no nodes left, continue the search from first node
nodes.add(this.branches[str.charAt(index) - 'a']);
nodes.remove(null);
}
for(int e = 0; e < nodes.size(); e++){
Tree node = nodes.get(e);
if(node.link != null)
if(!nodes.contains(node.link))
nodes.add(node.link);
if(node.values != null)
for(int x = 0; x < node.values.length; x++)
if(node.valIndexes[x] >= minIdx && node.valIndexes[x] <= maxIdx)
score += node.values[x];
}
}
return score;
}
private void interlink(Tree mainTree, String path){
for(int i = 0; i < branches.length; i++){
if(branches[i] != null)
branches[i].interlink(mainTree, path + (char)(i + 'a'));
}
if(path.length() < 2) return;
Tree node;
for(int k = 1; k < path.length(); k++){
node = mainTree.getNode(path.substring(k));
if(node != null){
link = node;
break;
}
}
}
private Tree getNode(String str){
Tree node = this;
for(int c = 0; c < str.length(); c++){
node = node.branches[str.charAt(c) - 'a'];
if(node == null)
break;
}
return node;
}
private void addValue(int val, int idx){
// ... this part is irrelevant ...
}
}
java performance algorithm strings
I solved this programming challenge where the goal is to give score to strings based on how much score certain substrings are worth (including repeating substrings).
Don't worry about what int values, valIndexes
and the arguments of createTree()
mean, just know that they have nothing to do with the search or organization of the data, they're only there for the score calculation.
The performance bottleneck of my code is interlink()
, everything else works reasonably fast, any suggestions for how to fix this performance issue are greatly appreciated.
The input strings for createTree()
and scan()
are expected to contain only lowercase a-z characters.
class Tree {
public int values, valIndexes;
public Tree branches = new Tree[26];
public Tree link;
public static Tree createTree(String strs, int worth){
Tree mainTree = new Tree();
Tree currentNode;
for(int i = 0; i < strs.length; i++){
currentNode = mainTree;
for(int c = 0; c < strs[i].length(); c++){
int idx = strs[i].charAt(c) - 'a';
if(currentNode.branches[idx] == null)
currentNode.branches[idx] = new Tree();
currentNode = currentNode.branches[idx];
if(strs[i].length() == c + 1)
currentNode.addValue(worth[i], i);
}
}
mainTree.interlink(mainTree, "");
return mainTree;
}
public int scan(String str, int minIdx, int maxIdx){
System.out.println("DNA sequence length = " + str.length());
int score = 0;
ArrayList<Tree> nodes = new ArrayList<Tree>();
for(int index = 0; index < str.length(); index++){
for(int e = 0; e < nodes.size(); e++) // advance nodes to next char
nodes.set(e, nodes.get(e).branches[str.charAt(index) - 'a']);
while(nodes.remove(null));
if(nodes.isEmpty()){ // if no nodes left, continue the search from first node
nodes.add(this.branches[str.charAt(index) - 'a']);
nodes.remove(null);
}
for(int e = 0; e < nodes.size(); e++){
Tree node = nodes.get(e);
if(node.link != null)
if(!nodes.contains(node.link))
nodes.add(node.link);
if(node.values != null)
for(int x = 0; x < node.values.length; x++)
if(node.valIndexes[x] >= minIdx && node.valIndexes[x] <= maxIdx)
score += node.values[x];
}
}
return score;
}
private void interlink(Tree mainTree, String path){
for(int i = 0; i < branches.length; i++){
if(branches[i] != null)
branches[i].interlink(mainTree, path + (char)(i + 'a'));
}
if(path.length() < 2) return;
Tree node;
for(int k = 1; k < path.length(); k++){
node = mainTree.getNode(path.substring(k));
if(node != null){
link = node;
break;
}
}
}
private Tree getNode(String str){
Tree node = this;
for(int c = 0; c < str.length(); c++){
node = node.branches[str.charAt(c) - 'a'];
if(node == null)
break;
}
return node;
}
private void addValue(int val, int idx){
// ... this part is irrelevant ...
}
}
java performance algorithm strings
java performance algorithm strings
asked 4 mins ago
potato
18810
18810
add a comment |
add a comment |
active
oldest
votes
active
oldest
votes
active
oldest
votes
active
oldest
votes
active
oldest
votes
Thanks for contributing an answer to Code Review Stack Exchange!
- Please be sure to answer the question. Provide details and share your research!
But avoid …
- Asking for help, clarification, or responding to other answers.
- Making statements based on opinion; back them up with references or personal experience.
Use MathJax to format equations. MathJax reference.
To learn more, see our tips on writing great answers.
Some of your past answers have not been well-received, and you're in danger of being blocked from answering.
Please pay close attention to the following guidance:
- Please be sure to answer the question. Provide details and share your research!
But avoid …
- Asking for help, clarification, or responding to other answers.
- Making statements based on opinion; back them up with references or personal experience.
To learn more, see our tips on writing great answers.
Sign up or log in
StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
StackExchange.ready(
function () {
StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fcodereview.stackexchange.com%2fquestions%2f208746%2faho-corasick-algorithm-substrings-search-implementation-performance-issue%23new-answer', 'question_page');
}
);
Post as a guest
Required, but never shown
Sign up or log in
StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
Sign up or log in
StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
Sign up or log in
StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown