public static boolean shouldBeInjected(String path, String contentType, String contentPreview) { int score = 0; if (log.isDebugEnabled()) { log.debug("shouldBeInjected(\"" + path + "\", \"" + contentType + "\", \"...\")"); } for (Rule rule : rules) { int scoreDelta = rule.score(path, contentType, contentPreview); if (log.isDebugEnabled()) { log.debug(" applied rule " + rule + ": " + scoreDelta); } score += scoreDelta; } boolean shouldInject = (score > INJECTION_THRESHOLD); if (log.isDebugEnabled()) { log.debug( " total : " + score + ">" + INJECTION_THRESHOLD + "? (should " + (shouldInject ? "" : "not ") + "inject)"); } return shouldInject; }
public Object formResult() { Set brs = new HashSet(); Set urs = new HashSet(); // scan each rule / history pair int ruleCount = 0; for (Iterator pairI = rulePairs.keySet().iterator(); pairI.hasNext(); ) { if (ruleCount % 100 == 0) { System.err.println("Rules multiplied: " + ruleCount); } ruleCount++; Pair rulePair = (Pair) pairI.next(); Rule baseRule = (Rule) rulePair.first; String baseLabel = (String) ruleToLabel.get(baseRule); List history = (List) rulePair.second; double totalProb = 0; for (int depth = 1; depth <= HISTORY_DEPTH() && depth <= history.size(); depth++) { List subHistory = history.subList(0, depth); double c_label = labelPairs.getCount(new Pair(baseLabel, subHistory)); double c_rule = rulePairs.getCount(new Pair(baseRule, subHistory)); // System.out.println("Multiplying out "+baseRule+" with history "+subHistory); // System.out.println("Count of "+baseLabel+" with "+subHistory+" is "+c_label); // System.out.println("Count of "+baseRule+" with "+subHistory+" is "+c_rule ); double prob = (1.0 / HISTORY_DEPTH()) * (c_rule) / (c_label); totalProb += prob; for (int childDepth = 0; childDepth <= Math.min(HISTORY_DEPTH() - 1, depth); childDepth++) { Rule rule = specifyRule(baseRule, subHistory, childDepth); rule.score = (float) Math.log(totalProb); // System.out.println("Created "+rule+" with score "+rule.score); if (rule instanceof UnaryRule) { urs.add(rule); } else { brs.add(rule); } } } } System.out.println("Total states: " + stateNumberer.total()); BinaryGrammar bg = new BinaryGrammar(stateNumberer.total()); UnaryGrammar ug = new UnaryGrammar(stateNumberer.total()); for (Iterator brI = brs.iterator(); brI.hasNext(); ) { BinaryRule br = (BinaryRule) brI.next(); bg.addRule(br); } for (Iterator urI = urs.iterator(); urI.hasNext(); ) { UnaryRule ur = (UnaryRule) urI.next(); ug.addRule(ur); } return new Pair(ug, bg); }