Created
May 2, 2012 02:44
-
-
Save jerluc/2573222 to your computer and use it in GitHub Desktop.
Exact token pattern matching
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
public class ExactMatchPOC { | |
private static final String TOKEN_DELIMITER = " "; | |
private static final String PHRASE_DELIMITER = ","; | |
public static void main(String[] args) { | |
String[] phraseTokens = buildTokenHashArray(args[0]); | |
String[][] labelTokens = buildMultiTokenHashArray(args[1]); | |
int i; | |
int[] t = new int[labelTokens.length]; | |
Integer[] m = new Integer[phraseTokens.length]; | |
fill(m, -1); | |
for (i = 0; i < phraseTokens.length; i++) { | |
for (int x = 0; x < labelTokens.length; x++) { | |
if (t[x] != labelTokens[x].length) { | |
if (phraseTokens[i].equals(labelTokens[x][t[x]])) { | |
t[x]++; | |
if (t[x] == labelTokens[x].length) { | |
for (int a = i; a > i - t[x]; a--) { | |
if (m[a] < 0) { | |
m[a] = x; | |
} | |
} | |
} | |
} | |
else { | |
t[x] = 0; | |
} | |
} | |
} | |
} | |
for (int a = 0; a < m.length; a++) { | |
if (m[a] > -1) | |
System.out.print(labelTokens[m[a]][a % labelTokens[m[a]].length] + "(" + m[a] + ") "); | |
else | |
System.out.print("- "); | |
} | |
System.out.println("\nFound token(s) in " + i + " iteration(s)"); | |
} | |
private static <T> void fill(T[] arr, T v) { | |
for (int i = 0; i < arr.length; i++) | |
arr[i] = v; | |
} | |
private static String[] buildTokenHashArray(String phrase) { | |
return phrase.split(TOKEN_DELIMITER); | |
} | |
private static String[][] buildMultiTokenHashArray(String multiPhrases) { | |
String[] phrases = multiPhrases.split(PHRASE_DELIMITER); | |
String[][] multiTokenHashes = new String[phrases.length][]; | |
for (int i = 0; i < phrases.length; i++) | |
multiTokenHashes[i] = buildTokenHashArray(phrases[i]); | |
return multiTokenHashes; | |
} | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment