private void combiningNP(Map<String, Rules> rl, Map<String, RuleSet> ruleset, int i) {
RuleSet rs;
String rkey;
int order1, order2;
Rules rule;
List<RuleData> ls;
String keys[] = {
"NNNP", "VBNP", "JJNP", "NNCP", "VBCP", "JJCP",
}; // noun, adj, vb in noun phrase
for (String s : rl.keySet()) {
rule = rl.get(s);
rule.initMap();
// process NP chunk
// cases to considered: PRO-TG (PRO)*
// TG prep1 PRO1 (prep2 PRO2)*
for (String subkey : keys) {
ls = rule.getEvalRules(subkey); // all NP pattern of current trg
if (ls == null) {
continue;
}
rkey = s + i + subkey; // trg + type + pos(first two letters) + chunk type
// has NP patterns
rs = new RuleSet();
order1 = 0;
order2 = 0;
for (RuleData dt : ls) {
if (dt.in_chunk) { // in chunk case
rs.in_chunk = true;
rs.inchunk_count += dt.count; // count number of inchunk event
if (!dt.has_cause) { // all event type without theme2/cause
if (dt.event1) {
rs.ecount += dt.count;
} else {
rs.pcount += dt.count;
}
} else if (i == 5 && dt.has_cause) { // theme2 PRO-TG PRO
rs.t2count += dt.count;
rs.pcount += dt.count;
rs.dist2 = Math.max(rs.dist2, dt.dist2);
} else if (i > 5 && dt.theme_pos && dt.has_cause) { // has cause
rs.pcause += dt.count; // assume only pro is cause : PRO - TG Theme (Pro/Evt)
if (dt.event1) {
rs.ecount += dt.count;
} else {
rs.pcount += dt.count;
}
rs.dist1 = Math.max(rs.dist1, dt.dist1);
}
} else if (dt.theme_pos) { // for all POS : TG - prep - PRO
if ((dt.POS.startsWith("NN") && !dt.prep1.isEmpty())
|| !dt.POS.startsWith("NN")) { // (NN && prep) or (VB/JJ)
if (!dt.has_cause) { // all event type, no theme2 / cause
if (i <= 5) {
rs.pcount += dt.count;
} else {
if (dt.event1) {
rs.ecount += dt.count;
} else {
rs.pcount += dt.count;
}
}
rs.dist1 = Math.max(rs.dist1, dt.dist1);
} else if (dt.cause_pos
&& !dt.prep2.isEmpty()
&& dt.POS.startsWith("NN")) { // TG-prep1-PRO1-prep2-PRO2 ; only NNx
if (i == 5) {
rs.t2count += dt.count;
rs.pcount += dt.count;
} else {
if (dt.event1) {
rs.ecount += dt.count;
} else {
rs.pcount += dt.count;
}
if (dt.event2) {
rs.ecause += dt.count;
} else {
rs.pcause += dt.count;
}
}
rs.dist1 = Math.max(rs.dist1, dt.dist1);
rs.dist2 = Math.max(rs.dist2, dt.dist2);
}
}
} else if (i == 5
&& !dt.theme_pos
&& ((dt.has_cause && dt.cause_pos)
|| !dt.POS.startsWith("NN"))) { // Binding: PRO1 - TG - PRO2
rs.in_front += dt.count;
if (!dt.prep2.isEmpty()) {
rs.prep_2.add(dt.prep2);
}
if (!dt.prep1.isEmpty()) {
rs.prep_1.add(dt.prep1);
}
rs.dist1 = Math.max(rs.dist1, dt.dist1);
rs.dist2 = Math.max(rs.dist2, dt.dist2);
rs.pcount += dt.count;
rs.dist2 = Math.max(rs.dist2, dt.dist2);
}
}
rs.detected = getCountDetectedTG(s, subkey);
if (order2 > order1) {
rs.order = false;
}
if (rs.getFreq() >= 2) {
ruleset.put(rkey, rs);
}
}
}
}
private void combiningVP(Map<String, Rules> rl, Map<String, RuleSet> ruleset, int i) {
RuleSet rs;
String rkey;
int order1;
Rules rule;
List<RuleData> ls;
String keys[] = {"VBVP", "JJVP"}; // noun, adj, vb in noun phrase
for (String s : rl.keySet()) {
rule = rl.get(s);
rule.initMap();
// ** VP JJ
for (String subkey : keys) {
ls = rule.getEvalRules(subkey); // all NP pattern of current trg
if (ls == null) {
continue;
}
rkey = s + i + subkey;
rs = new RuleSet();
order1 = 0;
for (RuleData dt : ls) {
if (dt.count < 2 && i < 5) {
// continue;
}
if (!dt.has_cause) {
if (i <= 5) {
rs.pcount += dt.count;
} else {
if (dt.event1) {
rs.ecount += dt.count;
} else {
rs.pcount += dt.count;
}
}
} else { // has theme2/cause
if (i == 5) {
rs.t2count += dt.count;
rs.pcount += dt.count;
} else {
if (dt.event1) {
rs.ecount += dt.count;
} else {
rs.pcount += dt.count;
}
if (dt.event2) {
rs.ecause += dt.count;
} else {
rs.pcause += dt.count;
}
}
}
if (dt.verb_type == 1 && dt.POS.equals("VBN") && dt.theme_pos) { //
order1 += dt.count;
} else if (dt.verb_type == 1 && dt.POS.equals("VBN") && !dt.theme_pos) {
order1 -= dt.count;
}
rs.dist1 = Math.max(rs.dist1, dt.dist1);
rs.dist2 = Math.max(rs.dist2, dt.dist2);
}
rs.detected = getCountDetectedTG(s, subkey);
if (order1 > 0) {
rs.order = false;
}
if (rs.getFreq() >= 2) {
ruleset.put(rkey, rs);
}
}
}
}