import java.util.*; import java.util.zip.*; import java.util.List; import java.util.regex.*; import java.util.concurrent.*; import java.util.concurrent.atomic.*; import javax.swing.*; import javax.swing.event.*; import javax.swing.text.*; import javax.swing.table.*; import java.io.*; import java.net.*; import java.lang.reflect.*; import java.lang.ref.*; import java.lang.management.*; import java.security.*; import java.security.spec.*; import java.awt.*; import java.awt.event.*; import java.awt.image.*; import javax.imageio.*; import java.math.*; public class main { static OccTree2 botTree; // adapters are immutable! (plus returns a modified clone) abstract static class Adapter { abstract boolean canMatch(String in, String out); Adapter plus(String in, String out) { return this; } String get(String in) { return in; } abstract double size(); } // node in flight (+ optional adapter) static class InFlight { OccTree2 node; Adapter adapter; InFlight(OccTree2 node) { this.node = node;} InFlight(OccTree2 node, Adapter adapter) { this.adapter = adapter; this.node = node;} E adapted() { // TODO: security when rewriting states return adapter == null ? node.e : new E(adapter.get(node.e.text()), node.e.type()); } } static class LooseBot { static boolean debug, repeat = true; OccTree2 tree; List nodes = new ArrayList(); List rewindStack = new ArrayList(); Object newAdapter; Object grabber; // func(S -> E) // WordAdapter now default LooseBot(OccTree2 tree) { this(tree, new Object() { Object get() { return new WordAdapter(); }}); } LooseBot(OccTree2 tree, Object newAdapter) { this.newAdapter = newAdapter; this.tree = tree;} LooseBot(String theme) { this(makeOccTree(theme)); } LooseBot(String theme, Object newAdapter) { this(makeOccTree(theme), newAdapter); } Adapter makeAdapter() { return newAdapter == null ? null : (Adapter) call(newAdapter); } void take(E in) { remember(); // try starting over from beginning of tree too if (repeat) setAdd(nodes, new InFlight(tree, makeAdapter())); List l = new ArrayList(); // try grabber if (grabber != null && in.q()) try { E grabbed = (E) ( callFunction(grabber, in.text())); if (grabbed != null) { if (debug) print("Grabber worked! " + in.text() + " => " + grabbed); // make a mini tree with Q + A so it is matched in // next call to getSingleOutput() OccTree2 node = new OccTree2(in); node.next.add(new OccTree2(grabbed)); l.add(new InFlight(node)); } else if (debug) print("Grabber didnt't return anything. " + in.text()); } catch (Throwable e) { if (debug) printStackTrace(e); } for (InFlight flight : nodes) for (OccTree2 n : flight.node.next) if (eq(n.e.type(), in.type()) && (flight.adapter != null ? flight.adapter.canMatch(n.e.text(), in.text()) : matchE(n.e, in))) { l.add(new InFlight(n, flight.adapter == null ? null : flight.adapter.plus(n.e.text(), in.text()))); } nodes = l; } void remember() { if (rewindStack != null) rewindStack.add(cloneList(nodes)); } E getSingleOutput() { remember(); List l = new ArrayList(); for (InFlight flight : nodes) for (OccTree2 n : flight.node.next) if (n.e.a() || isCommand(n.e)) l.add(new InFlight(n, flight.adapter)); if (empty(l)) { rewind(); return null; } nodes = l; return first(nodes).adapted(); } void rewind() { nodes = popLast(rewindStack); } boolean isCommand(E e) { return e.state() && matchStart("bot", e.state); } void noRewind() { rewindStack = null; } boolean matchE(E a, E b) { // standard NL matching return eq(a.type(), b.type()) && match(a.text(), b.text()); } String nodesToString(List nodes) { List l = new ArrayList(); l.add(n(l(nodes), "node") + "\n"); for (InFlight flight : nodes) { l.add(str(flight.node.e)); if (flight.adapter != null) l.add(" " + flight.adapter); } return rtrim(fromLines(l)); } String thoughts() { List l = new ArrayList(); l.add(nodesToString(nodes)); if (rewindStack != null) { l.add("\nHistory\n"); for (List nodes : reversedList(rewindStack)) l.add(indent(nodesToString(nodes))); } return fromLines(l); } } static class WordAdapter extends Adapter { Map wordMap = new TreeMap(); List tok(String s) { return nlTok2(dropPunctuation2(s)); } boolean canMatch(String in, String out) { List t1 = tok(in), t2 = tok(out); return l(t1) == l(t2); } Adapter plus(String in, String out) { List t1 = tok(in), t2 = tok(out); if (l(t1) != l(t2)) return this; WordAdapter a = (WordAdapter) ( nuObject(getClass())); a.wordMap = cloneMap(wordMap); for (int i = 1; i < l(t1); i += 2) { String w1 = t1.get(i), w2 = t2.get(i); if (!eqic(w1, w2)) // just overwrite - be flexible! a.wordMap.put(w1.toLowerCase(), w2.toLowerCase()); } return a; } String get(String s) { List tok = nlTok2(s); for (int i = 1; i < l(tok); i += 2) { String w = lookupToken(tok.get(i)); if (nempty(w)) tok.set(i, w); } return join(tok); } String lookupToken(String s) { return wordMap.get(s.toLowerCase()); } double size() { return l(wordMap); } public String toString() { return structure(wordMap); } } static class WordAdapter2 extends WordAdapter { Map wordMap = new TreeMap(); List tok(String s) { return nlTok2(s); } } // LooseBot v5 static class DateAdapter extends WordAdapter2 { static List months = splitAtSpace("___ January February March April May June July August September October November December"); String lookupToken(String s) { int i = indexOf(months, s); if (i >= 0) try { String j = lookupToken(str(i)); print("Month found! " + s + " => " + i + " => " + j); if (nempty(j)) return months.get(parseInt(j)); } catch (Throwable __e) { printStackTrace(__e); } return super.lookupToken(s); } String get(String s) { String o = countFixer(super.get(s)); print("count fixed: " + o); return o; } } static Object makeBot = new Object() { Object get() { LooseBot bot = new LooseBot(botTree, new Object() { Object get() { return new DateAdapter(); }}) { boolean isCommand(E e) { return !isInput(e); } // see Dialog Optimizer boolean isInput(E e) { return e.q() || e.state() && matchStart("result is ", e.text()); } }; bot.debug = true; return bot; }}; static void expandDialogs(List dialogs) { for (Dialog d : dialogs) for (int i = 0; i < l(d.poem); i++) { E e = d.poem.get(i); if (!e.state()) continue; int idx = e.text().indexOf('='); if (idx < 0) continue; d.poem.set(i, E.state("get " + e.text().substring(0, idx))); d.poem.add(i+1, E.state("result is " + e.text().substring(idx+1))); } } static Class getClass(String name) { try { return Class.forName(name); } catch (ClassNotFoundException e) { return null; } } static Class getClass(Object o) { return o instanceof Class ? (Class) o : o.getClass(); } static Class getClass(Object realm, String name) { try { return getClass(realm).getClassLoader().loadClass(classNameToVM(name)); } catch (Throwable __e) { throw __e instanceof RuntimeException ? (RuntimeException) __e : new RuntimeException(__e); }} static OccTree2 makeOccTree(String theme) { return makeOccTree(theme, true); } static OccTree2 makeOccTree(String theme, boolean print) { OccTree2 tree = goodDialogs2occTree2(loadDialogs(theme)); if (print) printOccTree2(tree); return tree; } static OccTree2 makeOccTree(List dialogs) { OccTree2 tree = goodDialogs2occTree2(dialogs); printOccTree2(tree); return tree; } static int indent_default = 2; static String indent(int indent) { return repeat(' ', indent); } static String indent(int indent, String s) { return indent(repeat(' ', indent), s); } static String indent(String indent, String s) { return indent + s.replace("\n", "\n" + indent); } static String indent(String s) { return indent(indent_default, s); } static List indent(String indent, List lines) { List l = new ArrayList(); for (String s : lines) l.add(indent + s); return l; } static List splitAtSpace(String s) { return asList(s.split("\\s+")); } static Object callFunction(Object f, Object... args) { if (f == null) return null; if (f instanceof Runnable) { ((Runnable) f).run(); return null; } else if (f instanceof String) return call(mc(), (String) f, args); else return call(f, "get", args); //else throw fail("Can't call a " + getClassName(f)); } public static String fromLines(List lines) { StringBuilder buf = new StringBuilder(); if (lines != null) for (String line : lines) buf.append(line).append('\n'); return buf.toString(); } // reduced NL parsing without quoted strings and some other stuff static List nlTok2(String s) { List tok = new ArrayList(); int l = s.length(); int i = 0; while (i < l) { int j = i; char c; // scan for whitespace while (j < l) { c = s.charAt(j); if (c == ' ' || c == '\t' || c == '\r' || c == '\n') ++j; else break; } tok.add(s.substring(i, j)); i = j; if (i >= l) break; c = s.charAt(i); // scan for non-whitespace if (Character.isJavaIdentifierStart(c)) do ++j; while (j < l && (Character.isJavaIdentifierPart(s.charAt(j)) /*|| s.charAt(j) == '\''*/)); else if (Character.isDigit(c)) do ++j; while (j < l && Character.isDigit(s.charAt(j))); else ++j; tok.add(s.substring(i, j)); i = j; } if ((tok.size() % 2) == 0) tok.add(""); return tok; } static boolean empty(Collection c) { return isEmpty(c); } static boolean empty(String s) { return isEmpty(s); } static boolean empty(Map map) { return map == null || map.isEmpty(); } static boolean empty(Object o) { if (o instanceof Collection) return empty((Collection) o); if (o instanceof String) return empty((String) o); if (o instanceof Map) return empty((Map) o); return false; } static List countFixer_them = splitAtSpace("nd st rd th"); static String countFixer(String s) { List tok = nlTok2(s); for (int i = 1; i+2 < l(tok); i += 2) if (isInteger(tok.get(i)) && contains(countFixer_them, tok.get(i+2))) try { // Is it correct? long l = parseLong(tok.get(i)); long d = l % 10, h = l % 100; tok.set(i+2, h-d == 10 ? "th" : d == 1 ? "st" : d == 2 ? "nd" : d == 3 ? "rd" : "th"); } catch (Throwable __e) { printStackTrace(__e); } return join(tok); } static boolean matchStart(String pat, String s) { return matchStart(pat, s, null); } // matches are as you expect, plus an extra item for the rest string static boolean matchStart(String pat, String s, Matches matches) { if (s == null) return false; List tokpat = parse3(pat), toks = parse3(s); if (toks.size() < tokpat.size()) return false; String[] m = match2(tokpat, toks.subList(0, tokpat.size())); //print(structure(tokpat) + " on " + structure(toks) + " => " + structure(m)); if (m == null) return false; else { if (matches != null) { matches.m = new String[m.length+1]; arraycopy(m, matches.m); matches.m[m.length] = join(toks.subList(tokpat.size(), toks.size())); // for Matches.rest() } return true; } } public static String join(String glue, Iterable strings) { StringBuilder buf = new StringBuilder(); Iterator i = strings.iterator(); if (i.hasNext()) { buf.append(i.next()); while (i.hasNext()) buf.append(glue).append(i.next()); } return buf.toString(); } public static String join(String glue, String[] strings) { return join(glue, Arrays.asList(strings)); } public static String join(Iterable strings) { return join("", strings); } public static String join(String[] strings) { return join("", strings); } static boolean setAdd(Collection c, A a) { if (c.contains(a)) return false; c.add(a); return true; } static int indexOf(List l, A a, int startIndex) { if (l == null) return -1; for (int i = startIndex; i < l(l); i++) if (eq(l.get(i), a)) return i; return -1; } static int indexOf(List l, A a) { if (l == null) return -1; return l.indexOf(a); } static List reversedList(List l) { List x = cloneList(l); Collections.reverse(x); return x; } static Map cloneMap(Map map) { // assume mutex is equal to collection, which will be true unless you explicitly pass a mutex to synchronizedList() which no one ever does. synchronized(map) { return new HashMap(map); } } static void printStackTrace(Throwable e) { // we go to system.out now - system.err is nonsense print(getStackTrace(e)); } static void printStackTrace() { printStackTrace(new Throwable()); } static boolean match(String pat, String s) { return match3(pat, s); } static boolean match(String pat, String s, Matches matches) { return match3(pat, s, matches); } public static String rtrim(String s) { int i = s.length(); while (i > 0 && " \t\r\n".indexOf(s.charAt(i-1)) >= 0) --i; return i < s.length() ? s.substring(0, i) : s; } static boolean nempty(Collection c) { return !isEmpty(c); } static boolean nempty(CharSequence s) { return !isEmpty(s); } static boolean nempty(Object[] o) { return !isEmpty(o); } static List cloneList(Collection l) { //O mutex = getOpt(l, "mutex"); /*if (mutex != null) synchronized(mutex) { ret new ArrayList(l); } else ret new ArrayList(l);*/ // assume mutex is equal to collection, which will be true unless you explicitly pass a mutex to synchronizedList() which no one ever does. synchronized(l) { return new ArrayList(l); } } static boolean eqic(String a, String b) { if ((a == null) != (b == null)) return false; if (a == null) return true; return a.equalsIgnoreCase(b); } static boolean eq(Object a, Object b) { if (a == null) return b == null; if (a.equals(b)) return true; if (a instanceof BigInteger) { if (b instanceof Integer) return a.equals(BigInteger.valueOf((Integer) b)); if (b instanceof Long) return a.equals(BigInteger.valueOf((Long) b)); } return false; } static int l(Object[] array) { return array == null ? 0 : array.length; } static int l(byte[] array) { return array == null ? 0 : array.length; } static int l(int[] array) { return array == null ? 0 : array.length; } static int l(char[] array) { return array == null ? 0 : array.length; } static int l(Collection c) { return c == null ? 0 : c.size(); } static int l(Map m) { return m == null ? 0 : m.size(); } static int l(String s) { return s == null ? 0 : s.length(); } static String n(long l, String name) { return l + " " + (l == 1 ? name : getPlural(name)); } static String structure(Object o) { HashSet refd = new HashSet(); return structure_2(structure_1(o, 0, new IdentityHashMap(), refd), refd); } // leave to false, unless unstructure() breaks static boolean structure_allowShortening = false; static String structure_1(Object o, int stringSizeLimit, IdentityHashMap seen, HashSet refd) { if (o == null) return "null"; // these are never back-referenced (for readability) if (o instanceof String) return quote(stringSizeLimit != 0 ? shorten((String) o, stringSizeLimit) : (String) o); if (o instanceof BigInteger) return "bigint(" + o + ")"; if (o instanceof Double) return "d(" + quote(str(o)) + ")"; if (o instanceof Long) return o + "L"; if (o instanceof Integer) return str(o); if (o instanceof Boolean) return ((Boolean) o).booleanValue() ? "t" : "f"; if (o instanceof Character) return quoteCharacter((Character) o); Integer ref = seen.get(o); if (ref != null) { refd.add(ref); return "r" + ref; } ref = seen.size()+1; seen.put(o, ref); String r = "m" + ref + " "; // marker String name = o.getClass().getName(); StringBuilder buf = new StringBuilder(); if (o instanceof HashSet) return r + "hashset " + structure_1(new ArrayList((Set) o), stringSizeLimit, seen, refd); if (o instanceof TreeSet) return r + "treeset " + structure_1(new ArrayList((Set) o), stringSizeLimit, seen, refd); if (o instanceof Collection) { for (Object x : (Collection) o) { if (buf.length() != 0) buf.append(", "); buf.append(structure_1(x, stringSizeLimit, seen, refd)); } return r + "[" + buf + "]"; } if (o instanceof Map) { for (Object e : ((Map) o).entrySet()) { if (buf.length() != 0) buf.append(", "); buf.append(structure_1(((Map.Entry) e).getKey(), stringSizeLimit, seen, refd)); buf.append("="); buf.append(structure_1(((Map.Entry) e).getValue(), stringSizeLimit, seen, refd)); } return r + (o instanceof HashMap ? "hashmap" : "") + "{" + buf + "}"; } if (o.getClass().isArray()) { int n = Array.getLength(o); for (int i = 0; i < n; i++) { if (buf.length() != 0) buf.append(", "); buf.append(structure_1(Array.get(o, i), stringSizeLimit, seen, refd)); } return r + "array{" + buf + "}"; } if (o instanceof Class) return r + "class(" + quote(((Class) o).getName()) + ")"; if (o instanceof Throwable) return r + "exception(" + quote(((Throwable) o).getMessage()) + ")"; if (o instanceof BitSet) { BitSet bs = (BitSet) o; for (int i = bs.nextSetBit(0); i >= 0; i = bs.nextSetBit(i+1)) { if (buf.length() != 0) buf.append(", "); buf.append(i); } return "bitset{" + buf + "}"; } // Need more cases? This should cover all library classes... if (name.startsWith("java.") || name.startsWith("javax.")) return r + String.valueOf(o); String shortName = o.getClass().getName().replaceAll("^main\\$", ""); if (shortName.equals("Lisp")) { buf.append("l(" + structure_1(getOpt(o, "head"), stringSizeLimit, seen, refd)); List args = (List) ( getOpt(o, "args")); if (nempty(args)) for (int i = 0; i < l(args); i++) { buf.append(", "); Object arg = args.get(i); // sweet shortening if (arg != null && eq(arg.getClass().getName(), "main$Lisp") && isTrue(call(arg, "isEmpty"))) arg = get(arg, "head"); buf.append(structure_1(arg, stringSizeLimit, seen, refd)); } buf.append(")"); return r + str(buf); } int numFields = 0; String fieldName = ""; if (shortName.equals("DynamicObject")) { shortName = (String) get(o, "className"); Map fieldValues = (Map) get(o, "fieldValues"); for (String _fieldName : fieldValues.keySet()) { fieldName = _fieldName; Object value = fieldValues.get(fieldName); if (value != null) { if (buf.length() != 0) buf.append(", "); buf.append(fieldName + "=" + structure_1(value, stringSizeLimit, seen, refd)); } ++numFields; } } else { // regular class Class c = o.getClass(); while (c != Object.class) { Field[] fields = c.getDeclaredFields(); for (Field field : fields) { if ((field.getModifiers() & Modifier.STATIC) != 0) continue; fieldName = field.getName(); // skip outer object reference if (fieldName.indexOf("$") >= 0) continue; Object value; try { field.setAccessible(true); value = field.get(o); } catch (Exception e) { value = "?"; } // put special cases here... if (value != null) { if (buf.length() != 0) buf.append(", "); buf.append(fieldName + "=" + structure_1(value, stringSizeLimit, seen, refd)); } ++numFields; } c = c.getSuperclass(); } } String b = buf.toString(); if (numFields == 1 && structure_allowShortening) b = b.replaceAll("^" + fieldName + "=", ""); // drop field name if only one String s = shortName; if (buf.length() != 0) s += "(" + b + ")"; return r + s; } // drop unused markers static String structure_2(String s, HashSet refd) { List tok = javaTok(s); StringBuilder out = new StringBuilder(); for (int i = 1; i < l(tok); i += 2) { String t = tok.get(i); if (t.startsWith("m") && isInteger(t.substring(1)) && !refd.contains(parseInt(t.substring(1)))) continue; out.append(t).append(tok.get(i+1)); } return str(out); } static Object call(Object o) { return callFunction(o); } // varargs assignment fixer for a single string array argument static Object call(Object o, String method, String[] arg) { return call(o, method, new Object[] {arg}); } static Object call(Object o, String method, Object... args) { try { if (o instanceof Class) { Method m = call_findStaticMethod((Class) o, method, args, false); m.setAccessible(true); return m.invoke(null, args); } else { Method m = call_findMethod(o, method, args, false); m.setAccessible(true); return m.invoke(o, args); } } catch (Exception e) { throw e instanceof RuntimeException ? (RuntimeException) e : new RuntimeException(e); } } static Method call_findStaticMethod(Class c, String method, Object[] args, boolean debug) { Class _c = c; while (c != null) { for (Method m : c.getDeclaredMethods()) { if (debug) System.out.println("Checking method " + m.getName() + " with " + m.getParameterTypes().length + " parameters");; if (!m.getName().equals(method)) { if (debug) System.out.println("Method name mismatch: " + method); continue; } if ((m.getModifiers() & Modifier.STATIC) == 0 || !call_checkArgs(m, args, debug)) continue; return m; } c = c.getSuperclass(); } throw new RuntimeException("Method '" + method + "' (static) with " + args.length + " parameter(s) not found in " + _c.getName()); } static Method call_findMethod(Object o, String method, Object[] args, boolean debug) { Class c = o.getClass(); while (c != null) { for (Method m : c.getDeclaredMethods()) { if (debug) System.out.println("Checking method " + m.getName() + " with " + m.getParameterTypes().length + " parameters");; if (m.getName().equals(method) && call_checkArgs(m, args, debug)) return m; } c = c.getSuperclass(); } throw new RuntimeException("Method '" + method + "' (non-static) with " + args.length + " parameter(s) not found in " + o.getClass().getName()); } private static boolean call_checkArgs(Method m, Object[] args, boolean debug) { Class[] types = m.getParameterTypes(); if (types.length != args.length) { if (debug) System.out.println("Bad parameter length: " + args.length + " vs " + types.length); return false; } for (int i = 0; i < types.length; i++) if (!(args[i] == null || isInstanceX(types[i], args[i]))) { if (debug) System.out.println("Bad parameter " + i + ": " + args[i] + " vs " + types[i]); return false; } return true; } static String str(Object o) { return String.valueOf(o); } static List dropPunctuation2(List tok) { tok = new ArrayList(tok); for (int i = 1; i < tok.size(); i += 2) { String t = tok.get(i); if (t.length() == 1 && !Character.isLetter(t.charAt(0)) && !Character.isDigit(t.charAt(0)) /* && !dropPunctuation2_keep.contains(t)*/) { tok.set(i-1, tok.get(i-1) + tok.get(i+1)); tok.remove(i); tok.remove(i); i -= 2; } } return tok; } static String dropPunctuation2(String s) { return join(dropPunctuation(nlTok2(s))); } static int parseInt(String s) { return empty(s) ? 0 : Integer.parseInt(s); } static volatile StringBuffer local_log = new StringBuffer(); // not redirected static volatile StringBuffer print_log = local_log; // might be redirected, e.g. to main bot // in bytes - will cut to half that static volatile int print_log_max = 1024*1024; static volatile int local_log_max = 100*1024; static void print() { print(""); } // slightly overblown signature to return original object... static A print(A o) { String s = String.valueOf(o) + "\n"; StringBuffer loc = local_log; StringBuffer buf = print_log; int loc_max = print_log_max; if (buf != loc && buf != null) { print_append(buf, s, print_log_max); loc_max = local_log_max; } if (loc != null) print_append(loc, s, loc_max); System.out.print(s); return o; } static void print(long l) { print(String.valueOf(l)); } static void print(char c) { print(String.valueOf(c)); } static void print_append(StringBuffer buf, String s, int max) { synchronized(buf) { buf.append(s); max /= 2; if (buf.length() > max) try { int newLength = max/2; int ofs = buf.length()-newLength; String newString = buf.substring(ofs); buf.setLength(0); buf.append("[...] ").append(newString); } catch (Exception e) { buf.setLength(0); } } } static A popLast(List l) { return liftLast(l); } static Object nuObject(String className, Object... args) { try { return nuObject(Class.forName(className), args); } catch (Throwable __e) { throw __e instanceof RuntimeException ? (RuntimeException) __e : new RuntimeException(__e); }} static Object nuObject(Object realm, String className, Object... args) { return nuObject(getClass(realm, className), args); } static Object nuObject(Class c, Object... args) { try { Constructor m = nuObject_findConstructor(c, args); m.setAccessible(true); return m.newInstance(args); } catch (Throwable __e) { throw __e instanceof RuntimeException ? (RuntimeException) __e : new RuntimeException(__e); }} static Constructor nuObject_findConstructor(Class c, Object... args) { for (Constructor m : c.getDeclaredConstructors()) { if (!nuObject_checkArgs(m.getParameterTypes(), args, false)) continue; return m; } throw new RuntimeException("Constructor with " + args.length + " matching parameter(s) not found in " + c.getName()); } static boolean nuObject_checkArgs(Class[] types, Object[] args, boolean debug) { if (types.length != args.length) { if (debug) System.out.println("Bad parameter length: " + args.length + " vs " + types.length); return false; } for (int i = 0; i < types.length; i++) if (!(args[i] == null || isInstanceX(types[i], args[i]))) { if (debug) System.out.println("Bad parameter " + i + ": " + args[i] + " vs " + types[i]); return false; } return true; } static Object first(Object list) { return ((List) list).isEmpty() ? null : ((List) list).get(0); } static A first(List list) { return list.isEmpty() ? null : list.get(0); } static A first(A[] bla) { return bla == null || bla.length == 0 ? null : bla[0]; } // match2 matches multiple "*" (matches a single token) wildcards and zero or one "..." wildcards (matches multiple tokens) static String[] match2(List pat, List tok) { // standard case (no ...) int i = pat.indexOf("..."); if (i < 0) return match2_match(pat, tok); pat = new ArrayList(pat); // We're modifying it, so copy first pat.set(i, "*"); while (pat.size() < tok.size()) { pat.add(i, "*"); pat.add(i+1, ""); // doesn't matter } return match2_match(pat, tok); } static String[] match2_match(List pat, List tok) { List result = new ArrayList(); if (pat.size() != tok.size()) { /*if (debug) print("Size mismatch: " + structure(pat) + " vs " + structure(tok));*/ return null; } for (int i = 1; i < pat.size(); i += 2) { String p = pat.get(i), t = tok.get(i); /*if (debug) print("Checking " + p + " against " + t);*/ if (eq(p, "*")) result.add(t); else if (!equalsIgnoreCase(unquote(p), unquote(t))) // bold change - match quoted and unquoted now return null; } return result.toArray(new String[result.size()]); } // class Matches is added by #752 static boolean match3(String pat, String s) { return match3(pat, s, null); } static boolean match3(String pat, String s, Matches matches) { if (s == null) return false; return match3(pat, parse3(s), matches); } static boolean match3(String pat, List toks, Matches matches) { List tokpat = parse3(pat); return match3(tokpat,toks,matches); } static boolean match3(List tokpat, List toks, Matches matches) { String[] m = match2(tokpat, toks); //print(structure(tokpat) + " on " + structure(toks) + " => " + structure(m)); if (m == null) return false; else { if (matches != null) matches.m = m; return true; } } static ArrayList asList(A[] a) { return new ArrayList(Arrays.asList(a)); } static ArrayList asList(int[] a) { ArrayList l = new ArrayList(); for (int i : a) l.add(i); return l; } static ArrayList asList(Collection s) { return s == null ? new ArrayList() : s instanceof ArrayList ? (ArrayList) s : new ArrayList(s); } static boolean isInteger(String s) { return s != null && Pattern.matches("\\-?\\d+", s); } static String quote(String s) { if (s == null) return "null"; return "\"" + s.replace("\\", "\\\\").replace("\"", "\\\"").replace("\r", "\\r").replace("\n", "\\n") + "\""; } static String quote(long l) { return quote("" + l); } static String quote(char c) { return quote("" + c); } static String shorten(String s, int max) { if (s == null) return ""; return s.length() <= max ? s : s.substring(0, Math.min(s.length(), max)) + "..."; } static String getStackTrace(Throwable throwable) { StringWriter writer = new StringWriter(); throwable.printStackTrace(new PrintWriter(writer)); return writer.toString(); } static Class mc() { return getMainClass(); } static String quoteCharacter(char c) { if (c == '\'') return "'\\''"; if (c == '\\') return "'\\\\'"; return "'" + c + "'"; } // extended over Class.isInstance() to handle primitive types static boolean isInstanceX(Class type, Object arg) { if (type == boolean.class) return arg instanceof Boolean; if (type == int.class) return arg instanceof Integer; if (type == long.class) return arg instanceof Long; if (type == float.class) return arg instanceof Float; if (type == short.class) return arg instanceof Short; if (type == char.class) return arg instanceof Character; if (type == byte.class) return arg instanceof Byte; if (type == double.class) return arg instanceof Double; return type.isInstance(arg); } static String getPlural(String s) { if (s.endsWith("y")) return dropSuffix("y", s) + "ies"; return s + "s"; } static String classNameToVM(String name) { return name.replace(".", "$"); } static boolean contains(Collection c, Object o) { return c != null && c.contains(o); } static boolean contains(Object[] x, Object o) { if (x != null) for (Object a : x) if (eq(a, o)) return true; return false; } static OccTree2 goodDialogs2occTree2(List dialogs) { OccTree2 tree = new OccTree2(); for (Dialog d : dialogs) if (d.good) tree.addScript(d.poem); return tree; } static A liftLast(List l) { if (l.isEmpty()) return null; int i = l(l)-1; A a = l.get(i); l.remove(i); return a; } static void printOccTree2(OccTree2 t) { printOccTree2_sub(t, ""); } static void printOccTree2_sub(OccTree2 t, String indent) { print(indent + "[" + t.count + "]" + (t.e == null ? "" : " " + t.e)); for (OccTree2 t2 : t.next) printOccTree2_sub(t2, indent + " "); } // replacement for class JavaTok // maybe incomplete, might want to add floating point numbers // todo also: extended multi-line strings static List javaTok(String s) { List tok = new ArrayList(); int l = s.length(); int i = 0; while (i < l) { int j = i; char c; String cc; // scan for whitespace while (j < l) { c = s.charAt(j); cc = s.substring(j, Math.min(j+2, l)); if (c == ' ' || c == '\t' || c == '\r' || c == '\n') ++j; else if (cc.equals("/*")) { do ++j; while (j < l && !s.substring(j, Math.min(j+2, l)).equals("*/")); j = Math.min(j+2, l); } else if (cc.equals("//")) { do ++j; while (j < l && "\r\n".indexOf(s.charAt(j)) < 0); } else break; } tok.add(s.substring(i, j)); i = j; if (i >= l) break; c = s.charAt(i); // cc is not needed in rest of loop body cc = s.substring(i, Math.min(i+2, l)); // scan for non-whitespace if (c == '\'' || c == '"') { char opener = c; ++j; while (j < l) { if (s.charAt(j) == opener || s.charAt(j) == '\n') { // end at \n to not propagate unclosed string literal errors ++j; break; } else if (s.charAt(j) == '\\' && j+1 < l) j += 2; else ++j; } } else if (Character.isJavaIdentifierStart(c)) do ++j; while (j < l && (Character.isJavaIdentifierPart(s.charAt(j)) || "'".indexOf(s.charAt(j)) >= 0)); // for stuff like "don't" else if (Character.isDigit(c)) { do ++j; while (j < l && Character.isDigit(s.charAt(j))); if (j < l && s.charAt(j) == 'L') ++j; // Long constants like 1L } else if (cc.equals("[[")) { do ++j; while (j+1 < l && !s.substring(j, j+2).equals("]]")); j = Math.min(j+2, l); } else if (cc.equals("[=") && i+2 < l && s.charAt(i+2) == '[') { do ++j; while (j+2 < l && !s.substring(j, j+3).equals("]=]")); j = Math.min(j+3, l); } else ++j; tok.add(s.substring(i, j)); i = j; } if ((tok.size() % 2) == 0) tok.add(""); return tok; } static List javaTok(List tok) { return javaTok(join(tok)); } static List parse3(String s) { return dropPunctuation(javaTokPlusPeriod(s)); } static void arraycopy(Object[] a, Object[] b) { int n = min(a.length, b.length); for (int i = 0; i < n; i++) b[i] = a[i]; } static void arraycopy(Object src, int srcPos, Object dest, int destPos, int n) { System.arraycopy(src, srcPos, dest, destPos, n); } static String repeat(char c, int n) { n = max(n, 0); char[] chars = new char[n]; for (int i = 0; i < n; i++) chars[i] = c; return new String(chars); } static List repeat(A a, int n) { List l = new ArrayList(); for (int i = 0; i < n; i++) l.add(a); return l; } // get purpose 1: access a list/array (safer version of x.get(y)) static A get(List l, int idx) { return idx >= 0 && idx < l(l) ? l.get(idx) : null; } static A get(A[] l, int idx) { return idx >= 0 && idx < l(l) ? l[idx] : null; } // get purpose 2: access a field by reflection or a map static Object get(Object o, String field) { if (o instanceof Class) return get((Class) o, field); if (o instanceof Map) return ((Map) o).get(field); if (o.getClass().getName().equals("main$DynamicObject")) return call(get_raw(o, "fieldValues"), "get", field); return get_raw(o, field); } static Object get_raw(Object o, String field) { try { Field f = get_findField(o.getClass(), field); f.setAccessible(true); return f.get(o); } catch (Exception e) { throw new RuntimeException(e); } } static Object get(Class c, String field) { try { Field f = get_findStaticField(c, field); f.setAccessible(true); return f.get(null); } catch (Exception e) { throw new RuntimeException(e); } } static Field get_findStaticField(Class c, String field) { Class _c = c; do { for (Field f : _c.getDeclaredFields()) if (f.getName().equals(field) && (f.getModifiers() & Modifier.STATIC) != 0) return f; _c = _c.getSuperclass(); } while (_c != null); throw new RuntimeException("Static field '" + field + "' not found in " + c.getName()); } static Field get_findField(Class c, String field) { Class _c = c; do { for (Field f : _c.getDeclaredFields()) if (f.getName().equals(field)) return f; _c = _c.getSuperclass(); } while (_c != null); throw new RuntimeException("Field '" + field + "' not found in " + c.getName()); } static List dropPunctuation_keep = litlist("*", "<", ">"); static List dropPunctuation(List tok) { tok = new ArrayList(tok); for (int i = 1; i < tok.size(); i += 2) { String t = tok.get(i); if (t.length() == 1 && !Character.isLetter(t.charAt(0)) && !Character.isDigit(t.charAt(0)) && !dropPunctuation_keep.contains(t)) { tok.set(i-1, tok.get(i-1) + tok.get(i+1)); tok.remove(i); tok.remove(i); i -= 2; } } return tok; } static String dropPunctuation(String s) { return join(dropPunctuation(nlTok(s))); } static boolean isEmpty(Collection c) { return c == null || c.isEmpty(); } static boolean isEmpty(CharSequence s) { return s == null || s.length() == 0; } static boolean isEmpty(Object[] a) { return a == null || a.length == 0; } static boolean isEmpty(Map map) { return map == null || map.isEmpty(); } static List loadDialogs(String themeOrID) { List snippets; if (isSnippetID(themeOrID)) { Snippet s = new Snippet(); s.id = themeOrID; s.title = getSnippetTitle(s.id); snippets = litlist(s); } else snippets = sortSnippetsByID(findDialogsNamed(themeOrID)); //psl(snippets); List dialogs = new ArrayList(); for (Snippet s : snippets) { Dialog d = new Dialog(); d.snippet = s; d.good = !cic(javaTok(s.title), "bad"); d.poem = parsePoem(s.id); dialogs.add(d); } //psl(dialogs); return dialogs; } static boolean isTrue(Object o) { return booleanValue(o); } static Object getOpt(Object o, String field) { if (o instanceof String) o = getBot ((String) o); if (o == null) return null; if (o instanceof Class) return getOpt((Class) o, field); if (o.getClass().getName().equals("main$DynamicObject")) return call(getOpt_raw(o, "fieldValues"), "get", field); if (o instanceof Map) return ((Map) o).get(field); return getOpt_raw(o, field); } static Object getOpt_raw(Object o, String field) { try { Field f = getOpt_findField(o.getClass(), field); if (f == null) return null; f.setAccessible(true); return f.get(o); } catch (Exception e) { throw new RuntimeException(e); } } static Object getOpt(Class c, String field) { try { Field f = getOpt_findStaticField(c, field); if (f == null) return null; f.setAccessible(true); return f.get(null); } catch (Exception e) { throw new RuntimeException(e); } } static Field getOpt_findStaticField(Class c, String field) { Class _c = c; do { for (Field f : _c.getDeclaredFields()) if (f.getName().equals(field) && (f.getModifiers() & Modifier.STATIC) != 0) return f; _c = _c.getSuperclass(); } while (_c != null); return null; } static Field getOpt_findField(Class c, String field) { Class _c = c; do { for (Field f : _c.getDeclaredFields()) if (f.getName().equals(field)) return f; _c = _c.getSuperclass(); } while (_c != null); return null; } static long parseLong(String s) { if (s == null) return 0; return Long.parseLong(dropSuffix("L", s)); } static long parseLong(Object s) { return Long.parseLong((String) s); } static String getSnippetTitle(String id) { try { return loadPage(new URL("http://tinybrain.de:8080/tb-int/getfield.php?id=" + parseSnippetID(id) + "&field=title")); } catch (Throwable __e) { throw __e instanceof RuntimeException ? (RuntimeException) __e : new RuntimeException(__e); }} static List parsePoem(String input) { if (isSnippetID(input)) return loadPoemAndParse(input); return parsePoem(toLinesFullTrim(input)); } static List parsePoem(List lines) { char mode = ' '; List entries = new ArrayList(); for (String line : lines) { E e = new E(); if (line.startsWith("!")) { e.test = true; line = line.substring(1).trim(); } if (swicAny(line, litlist("Q:", "U:", "Usr:"))) { mode = 'q'; line = line.substring(line.indexOf(':')+1).trim(); } else if (swicAny(line, litlist("A:", "B:", "Bot:"))) { mode = 'a'; line = line.substring(line.indexOf(':')+1).trim(); } else if (startsWith(line, "[")) mode = 's'; if (mode == 'q') e.q = line; else if (mode == 'a') e.a = line; else { String s = javaDropComments(line).trim(); e.state = dropPrefix("[", dropSuffix("]", s)).trim(); } entries.add(e); } return entries; } static Object getBot(String botID) { return callOpt(getMainBot(), "getBot", botID); } static boolean equalsIgnoreCase(String a, String b) { return a == null ? b == null : a.equalsIgnoreCase(b); } // This is made for NL parsing. // It's javaTok extended with "..." token, "$n" and "#n" and // special quotes (which are converted to normal ones). static List javaTokPlusPeriod(String s) { List tok = new ArrayList(); int l = s.length(); int i = 0; while (i < l) { int j = i; char c; String cc; // scan for whitespace while (j < l) { c = s.charAt(j); cc = s.substring(j, Math.min(j+2, l)); if (c == ' ' || c == '\t' || c == '\r' || c == '\n') ++j; else if (cc.equals("/*")) { do ++j; while (j < l && !s.substring(j, Math.min(j+2, l)).equals("*/")); j = Math.min(j+2, l); } else if (cc.equals("//")) { do ++j; while (j < l && "\r\n".indexOf(s.charAt(j)) < 0); } else break; } tok.add(s.substring(i, j)); i = j; if (i >= l) break; c = s.charAt(i); cc = s.substring(i, Math.min(i+2, l)); // scan for non-whitespace if (c == '\u201C' || c == '\u201D') c = '"'; // normalize quotes if (c == '\'' || c == '"') { char opener = c; ++j; while (j < l) { char _c = s.charAt(j); if (_c == '\u201C' || _c == '\u201D') _c = '"'; // normalize quotes if (_c == opener) { ++j; break; } else if (s.charAt(j) == '\\' && j+1 < l) j += 2; else ++j; } if (j-1 >= i+1) { tok.add(opener + s.substring(i+1, j-1) + opener); i = j; continue; } } else if (Character.isJavaIdentifierStart(c)) do ++j; while (j < l && (Character.isJavaIdentifierPart(s.charAt(j)) || s.charAt(j) == '\'')); // for things like "this one's" else if (Character.isDigit(c)) do ++j; while (j < l && Character.isDigit(s.charAt(j))); else if (cc.equals("[[")) { do ++j; while (j+1 < l && !s.substring(j, j+2).equals("]]")); j = Math.min(j+2, l); } else if (cc.equals("[=") && i+2 < l && s.charAt(i+2) == '[') { do ++j; while (j+2 < l && !s.substring(j, j+3).equals("]=]")); j = Math.min(j+3, l); } else if (s.substring(j, Math.min(j+3, l)).equals("...")) j += 3; else if (c == '$' || c == '#') do ++j; while (j < l && Character.isDigit(s.charAt(j))); else ++j; tok.add(s.substring(i, j)); i = j; } if ((tok.size() % 2) == 0) tok.add(""); return tok; } static boolean booleanValue(Object o) { return eq(true, o); } static boolean cic(List l, String s) { return containsIgnoreCase(l, s); } static boolean cic(String[] l, String s) { return containsIgnoreCase(l, s); } static boolean cic(String s, char c) { return containsIgnoreCase(s, c); } static boolean cic(String a, String b) { return containsIgnoreCase(a, b); } public static boolean isSnippetID(String s) { try { parseSnippetID(s); return true; } catch (RuntimeException e) { return false; } } static int min(int a, int b) { return Math.min(a, b); } static double min(double[] c) { double x = Double.MAX_VALUE; for (double d : c) x = Math.min(x, d); return x; } static byte min(byte[] c) { byte x = 127; for (byte d : c) if (d < x) x = d; return x; } static ArrayList litlist(A... a) { return new ArrayList(Arrays.asList(a)); } public static String unquote(String s) { if (s.startsWith("[")) { int i = 1; while (i < s.length() && s.charAt(i) == '=') ++i; if (i < s.length() && s.charAt(i) == '[') { String m = s.substring(1, i); if (s.endsWith("]" + m + "]")) return s.substring(i+1, s.length()-i-1); } } if (s.startsWith("\"") /*&& s.endsWith("\"")*/ && s.length() > 1) { String st = s.substring(1, s.endsWith("\"") ? s.length()-1 : s.length()); StringBuilder sb = new StringBuilder(st.length()); for (int i = 0; i < st.length(); i++) { char ch = st.charAt(i); if (ch == '\\') { char nextChar = (i == st.length() - 1) ? '\\' : st .charAt(i + 1); // Octal escape? if (nextChar >= '0' && nextChar <= '7') { String code = "" + nextChar; i++; if ((i < st.length() - 1) && st.charAt(i + 1) >= '0' && st.charAt(i + 1) <= '7') { code += st.charAt(i + 1); i++; if ((i < st.length() - 1) && st.charAt(i + 1) >= '0' && st.charAt(i + 1) <= '7') { code += st.charAt(i + 1); i++; } } sb.append((char) Integer.parseInt(code, 8)); continue; } switch (nextChar) { case '\\': ch = '\\'; break; case 'b': ch = '\b'; break; case 'f': ch = '\f'; break; case 'n': ch = '\n'; break; case 'r': ch = '\r'; break; case 't': ch = '\t'; break; case '\"': ch = '\"'; break; case '\'': ch = '\''; break; // Hex Unicode: u???? case 'u': if (i >= st.length() - 5) { ch = 'u'; break; } int code = Integer.parseInt( "" + st.charAt(i + 2) + st.charAt(i + 3) + st.charAt(i + 4) + st.charAt(i + 5), 16); sb.append(Character.toChars(code)); i += 5; continue; default: ch = nextChar; // added by Stefan } i++; } sb.append(ch); } return sb.toString(); } else return s; // return original } static Class getMainClass() { try { return Class.forName("main"); } catch (Throwable __e) { throw __e instanceof RuntimeException ? (RuntimeException) __e : new RuntimeException(__e); }} static Class getMainClass(Object o) { try { return (o instanceof Class ? (Class) o : o.getClass()).getClassLoader().loadClass("main"); } catch (Throwable __e) { throw __e instanceof RuntimeException ? (RuntimeException) __e : new RuntimeException(__e); }} static int max(int a, int b) { return Math.max(a, b); } static long max(int a, long b) { return Math.max((long) a, b); } static long max(long a, long b) { return Math.max(a, b); } static double max(int a, double b) { return Math.max((double) a, b); } static int max(Collection c) { int x = Integer.MIN_VALUE; for (int i : c) x = max(x, i); return x; } static double max(double[] c) { if (c.length == 0) return Double.MIN_VALUE; double x = c[0]; for (int i = 1; i < c.length; i++) x = Math.max(x, c[i]); return x; } static byte max(byte[] c) { byte x = -128; for (byte d : c) if (d > x) x = d; return x; } static List findDialogsNamed(String name) { List snippets = snippetsFromHTML("http://tinybrain.de:8080/tb/snippets.php?type=48&order=changed&reverse=1&longlist=1&prefix=" + urlencode(name)); List dialogs = new ArrayList(); for (Snippet s : snippets) if (swic(s.title.trim(), name)) dialogs.add(s); return dialogs; } static String dropSuffix(String suffix, String s) { return s.endsWith(suffix) ? s.substring(0, l(s)-l(suffix)) : s; } static List nlTok(String s) { return javaTokPlusPeriod(s); } static List sortSnippetsByID(List l) { return sorted(l, new Object() { Object get(Snippet a, Snippet b) { return stdcompare(parseSnippetID(a.id), parseSnippetID(b.id)) ; }}); } static String urlencode(String x) { try { return URLEncoder.encode(unnull(x), "UTF-8"); } catch (UnsupportedEncodingException e) { throw new RuntimeException(e); } } static String dropPrefix(String prefix, String s) { return s.startsWith(prefix) ? s.substring(l(prefix)) : s; } static List loadPoemAndParse(String snippetID) { return parsePoem(loadPoem(snippetID).lines); } static List sorted(List l, final Object comparator) { sort(l = cloneList(l), new Comparator() { public int compare(Object a, Object b) { return (int) callFunction(comparator, a, b); } }); return l; } static List toLinesFullTrim(String s) { List l = toLines(s); for (ListIterator i = l.listIterator(); i.hasNext(); ) { String line = i.next().trim(); if (line.length() == 0) i.remove(); else i.set(line); } return l; } static Object callOpt(Object o, String method, Object... args) { try { if (o == null) return null; if (o instanceof Class) { Method m = callOpt_findStaticMethod((Class) o, method, args, false); if (m == null) return null; m.setAccessible(true); return m.invoke(null, args); } else { Method m = callOpt_findMethod(o, method, args, false); if (m == null) return null; m.setAccessible(true); return m.invoke(o, args); } } catch (Exception e) { throw new RuntimeException(e); } } static Method callOpt_findStaticMethod(Class c, String method, Object[] args, boolean debug) { Class _c = c; while (c != null) { for (Method m : c.getDeclaredMethods()) { if (debug) System.out.println("Checking method " + m.getName() + " with " + m.getParameterTypes().length + " parameters");; if (!m.getName().equals(method)) { if (debug) System.out.println("Method name mismatch: " + method); continue; } if ((m.getModifiers() & Modifier.STATIC) == 0 || !callOpt_checkArgs(m, args, debug)) continue; return m; } c = c.getSuperclass(); } return null; } static Method callOpt_findMethod(Object o, String method, Object[] args, boolean debug) { Class c = o.getClass(); while (c != null) { for (Method m : c.getDeclaredMethods()) { if (debug) System.out.println("Checking method " + m.getName() + " with " + m.getParameterTypes().length + " parameters");; if (m.getName().equals(method) && callOpt_checkArgs(m, args, debug)) return m; } c = c.getSuperclass(); } return null; } private static boolean callOpt_checkArgs(Method m, Object[] args, boolean debug) { Class[] types = m.getParameterTypes(); if (types.length != args.length) { if (debug) System.out.println("Bad parameter length: " + args.length + " vs " + types.length); return false; } for (int i = 0; i < types.length; i++) if (!(args[i] == null || isInstanceX(types[i], args[i]))) { if (debug) System.out.println("Bad parameter " + i + ": " + args[i] + " vs " + types[i]); return false; } return true; } static boolean swic(String a, String b) { return startsWithIgnoreCase(a, b); } static Object mainBot; static Object getMainBot() { return mainBot; } public static long parseSnippetID(String snippetID) { long id = Long.parseLong(shortenSnippetID(snippetID)); if (id == 0) fail("0 is not a snippet ID"); return id; } static List snippetsFromHTML(String url) { String html = loadPage(url); TableFinder finder = new TableFinder(); finder.go(html); List l = new ArrayList(); for (int i = 1; i < finder.data.size(); i++) { List row = finder.getRow(i); Snippet s = new Snippet(); s.title = dropAllTags(htmldecode(row.get(0))); s.id = dropAllTags(row.get(1)); s.md5 = dropAllTags(row.get(2)); l.add(s); } return l; } static ThreadLocal loadPage_charset = new ThreadLocal(); static boolean loadPage_allowGzip = true, loadPage_debug; public static String loadPageSilently(String url) { try { return loadPageSilently(new URL(loadPage_preprocess(url))); } catch (IOException e) { throw new RuntimeException(e); } } public static String loadPageSilently(URL url) { try { IOException e = null; for (int tries = 0; tries < 60; tries++) try { URLConnection con = url.openConnection(); return loadPage(con, url); } catch (IOException _e) { e = _e; print("Retrying because of: " + e); sleepSeconds(1); } throw e; } catch (IOException e) { throw new RuntimeException(e); } } static String loadPage_preprocess(String url) { if (url.startsWith("tb/")) url = "tinybrain.de:8080/" + url; if (url.indexOf("://") < 0) url = "http://" + url; return url; } public static String loadPage(String url) { try { return loadPage(new URL(loadPage_preprocess(url))); } catch (IOException e) { throw new RuntimeException(e); } } public static String loadPage(URL url) { print("Loading: " + url.toExternalForm()); return loadPageSilently(url); } public static String loadPage(URLConnection con, URL url) throws IOException { String computerID = getComputerID(); try { if (computerID != null) con.setRequestProperty("X-ComputerID", computerID); if (loadPage_allowGzip) con.setRequestProperty("Accept-Encoding", "gzip"); } catch (Throwable e) {} // fails if within doPost String contentType = con.getContentType(); if (contentType == null) throw new IOException("Page could not be read: " + url); //print("Content-Type: " + contentType); String charset = loadPage_charset == null ? null : loadPage_charset.get(); if (charset == null) charset = loadPage_guessCharset(contentType); InputStream in = con.getInputStream(); if ("gzip".equals(con.getContentEncoding())) { if (loadPage_debug) print("loadPage: Using gzip."); in = new GZIPInputStream(in); } Reader r = new InputStreamReader(in, charset); StringBuilder buf = new StringBuilder(); while (true) { int ch = r.read(); if (ch < 0) break; //Log.info("Chars read: " + buf.length()); buf.append((char) ch); } return buf.toString(); } static String loadPage_guessCharset(String contentType) { Pattern p = Pattern.compile("text/[a-z]+;\\s+charset=([^\\s]+)\\s*"); Matcher m = p.matcher(contentType); /* If Content-Type doesn't match this pre-conception, choose default and hope for the best. */ return m.matches() ? m.group(1) : "ISO-8859-1"; } static boolean containsIgnoreCase(List l, String s) { for (String x : l) if (eqic(x, s)) return true; return false; } static boolean containsIgnoreCase(String[] l, String s) { for (String x : l) if (eqic(x, s)) return true; return false; } static boolean containsIgnoreCase(String s, char c) { return indexOfIgnoreCase(s, String.valueOf(c)) >= 0; } static boolean containsIgnoreCase(String a, String b) { return indexOfIgnoreCase(a, b) >= 0; } static String javaDropComments(String s) { List tok = javaTok(s); replaceLastElement(tok, ""); return join(tok); } static boolean swicAny(String a, List l) { for (String b : l) if (swic(a, b)) return true; return false; } static int stdcompare(String a, String b) { return a == null ? b == null ? 0 : -1 : a.compareTo(b); } static int stdcompare(long a, long b) { return a < b ? -1 : a > b ? 1 : 0; } static boolean startsWith(String a, String b) { return a != null && a.startsWith(b); } static boolean startsWith(List a, List b) { if (a == null || l(b) > l(a)) return false; for (int i = 0; i < l(b); i++) if (neq(a.get(i), b.get(i))) return false; return true; } static Text loadPoem(String snippetID) { return first(loadPoems(snippetID)); } static String shortenSnippetID(String snippetID) { if (snippetID.startsWith("#")) snippetID = snippetID.substring(1); String httpBlaBla = "http://tinybrain.de/"; if (snippetID.startsWith(httpBlaBla)) snippetID = snippetID.substring(httpBlaBla.length()); return "" + parseLong(snippetID); } static RuntimeException fail() { throw new RuntimeException("fail"); } static RuntimeException fail(Object msg) { throw new RuntimeException(String.valueOf(msg)); } static RuntimeException fail(String msg) { throw new RuntimeException(unnull(msg)); } static RuntimeException fail(String msg, Object... args) { throw new RuntimeException(format(msg, args)); } static String unnull(String s) { return s == null ? "" : s; } static List unnull(List l) { return l == null ? emptyList() : l; } static Object[] unnull(Object[] a) { return a == null ? new Object[0] : a; } static String getComputerID() { try { return computerID(); } catch (Throwable __e) { throw __e instanceof RuntimeException ? (RuntimeException) __e : new RuntimeException(__e); }} static List toLines(File f) { return toLines(loadTextFile(f)); } public static List toLines(String s) { List lines = new ArrayList(); if (s == null) return lines; int start = 0; while (true) { int i = toLines_nextLineBreak(s, start); if (i < 0) { if (s.length() > start) lines.add(s.substring(start)); break; } lines.add(s.substring(start, i)); if (s.charAt(i) == '\r' && i+1 < s.length() && s.charAt(i+1) == '\n') i += 2; else ++i; start = i; } return lines; } private static int toLines_nextLineBreak(String s, int start) { for (int i = start; i < s.length(); i++) { char c = s.charAt(i); if (c == '\r' || c == '\n') return i; } return -1; } static String htmldecode(final String input) { if (input == null) return null; final int MIN_ESCAPE = 2; final int MAX_ESCAPE = 6; StringWriter writer = null; int len = input.length(); int i = 1; int st = 0; while (true) { // look for '&' while (i < len && input.charAt(i-1) != '&') i++; if (i >= len) break; // found '&', look for ';' int j = i; while (j < len && j < i + MAX_ESCAPE + 1 && input.charAt(j) != ';') j++; if (j == len || j < i + MIN_ESCAPE || j == i + MAX_ESCAPE + 1) { i++; continue; } // found escape if (input.charAt(i) == '#') { // numeric escape int k = i + 1; int radix = 10; final char firstChar = input.charAt(k); if (firstChar == 'x' || firstChar == 'X') { k++; radix = 16; } try { int entityValue = Integer.parseInt(input.substring(k, j), radix); if (writer == null) writer = new StringWriter(input.length()); writer.append(input.substring(st, i - 1)); if (entityValue > 0xFFFF) { final char[] chrs = Character.toChars(entityValue); writer.write(chrs[0]); writer.write(chrs[1]); } else { writer.write(entityValue); } } catch (NumberFormatException ex) { i++; continue; } } else { // named escape CharSequence value = htmldecode_lookupMap.get(input.substring(i, j)); if (value == null) { i++; continue; } if (writer == null) writer = new StringWriter(input.length()); writer.append(input.substring(st, i - 1)); writer.append(value); } // skip escape st = j + 1; i = st; } if (writer != null) { writer.append(input.substring(st, len)); return writer.toString(); } return input; } private static final String[][] htmldecode_ESCAPES = { {"\"", "quot"}, // " - double-quote {"&", "amp"}, // & - ampersand {"<", "lt"}, // < - less-than {">", "gt"}, // > - greater-than // Mapping to escape ISO-8859-1 characters to their named HTML 3.x equivalents. {"\u00A0", "nbsp"}, // non-breaking space {"\u00A1", "iexcl"}, // inverted exclamation mark {"\u00A2", "cent"}, // cent sign {"\u00A3", "pound"}, // pound sign {"\u00A4", "curren"}, // currency sign {"\u00A5", "yen"}, // yen sign = yuan sign {"\u00A6", "brvbar"}, // broken bar = broken vertical bar {"\u00A7", "sect"}, // section sign {"\u00A8", "uml"}, // diaeresis = spacing diaeresis {"\u00A9", "copy"}, // copyright sign {"\u00AA", "ordf"}, // feminine ordinal indicator {"\u00AB", "laquo"}, // left-pointing double angle quotation mark = left pointing guillemet {"\u00AC", "not"}, // not sign {"\u00AD", "shy"}, // soft hyphen = discretionary hyphen {"\u00AE", "reg"}, // registered trademark sign {"\u00AF", "macr"}, // macron = spacing macron = overline = APL overbar {"\u00B0", "deg"}, // degree sign {"\u00B1", "plusmn"}, // plus-minus sign = plus-or-minus sign {"\u00B2", "sup2"}, // superscript two = superscript digit two = squared {"\u00B3", "sup3"}, // superscript three = superscript digit three = cubed {"\u00B4", "acute"}, // acute accent = spacing acute {"\u00B5", "micro"}, // micro sign {"\u00B6", "para"}, // pilcrow sign = paragraph sign {"\u00B7", "middot"}, // middle dot = Georgian comma = Greek middle dot {"\u00B8", "cedil"}, // cedilla = spacing cedilla {"\u00B9", "sup1"}, // superscript one = superscript digit one {"\u00BA", "ordm"}, // masculine ordinal indicator {"\u00BB", "raquo"}, // right-pointing double angle quotation mark = right pointing guillemet {"\u00BC", "frac14"}, // vulgar fraction one quarter = fraction one quarter {"\u00BD", "frac12"}, // vulgar fraction one half = fraction one half {"\u00BE", "frac34"}, // vulgar fraction three quarters = fraction three quarters {"\u00BF", "iquest"}, // inverted question mark = turned question mark {"\u00C0", "Agrave"}, // ? - uppercase A, grave accent {"\u00C1", "Aacute"}, // ? - uppercase A, acute accent {"\u00C2", "Acirc"}, // ? - uppercase A, circumflex accent {"\u00C3", "Atilde"}, // ? - uppercase A, tilde {"\u00C4", "Auml"}, // ? - uppercase A, umlaut {"\u00C5", "Aring"}, // ? - uppercase A, ring {"\u00C6", "AElig"}, // ? - uppercase AE {"\u00C7", "Ccedil"}, // ? - uppercase C, cedilla {"\u00C8", "Egrave"}, // ? - uppercase E, grave accent {"\u00C9", "Eacute"}, // ? - uppercase E, acute accent {"\u00CA", "Ecirc"}, // ? - uppercase E, circumflex accent {"\u00CB", "Euml"}, // ? - uppercase E, umlaut {"\u00CC", "Igrave"}, // ? - uppercase I, grave accent {"\u00CD", "Iacute"}, // ? - uppercase I, acute accent {"\u00CE", "Icirc"}, // ? - uppercase I, circumflex accent {"\u00CF", "Iuml"}, // ? - uppercase I, umlaut {"\u00D0", "ETH"}, // ? - uppercase Eth, Icelandic {"\u00D1", "Ntilde"}, // ? - uppercase N, tilde {"\u00D2", "Ograve"}, // ? - uppercase O, grave accent {"\u00D3", "Oacute"}, // ? - uppercase O, acute accent {"\u00D4", "Ocirc"}, // ? - uppercase O, circumflex accent {"\u00D5", "Otilde"}, // ? - uppercase O, tilde {"\u00D6", "Ouml"}, // ? - uppercase O, umlaut {"\u00D7", "times"}, // multiplication sign {"\u00D8", "Oslash"}, // ? - uppercase O, slash {"\u00D9", "Ugrave"}, // ? - uppercase U, grave accent {"\u00DA", "Uacute"}, // ? - uppercase U, acute accent {"\u00DB", "Ucirc"}, // ? - uppercase U, circumflex accent {"\u00DC", "Uuml"}, // ? - uppercase U, umlaut {"\u00DD", "Yacute"}, // ? - uppercase Y, acute accent {"\u00DE", "THORN"}, // ? - uppercase THORN, Icelandic {"\u00DF", "szlig"}, // ? - lowercase sharps, German {"\u00E0", "agrave"}, // ? - lowercase a, grave accent {"\u00E1", "aacute"}, // ? - lowercase a, acute accent {"\u00E2", "acirc"}, // ? - lowercase a, circumflex accent {"\u00E3", "atilde"}, // ? - lowercase a, tilde {"\u00E4", "auml"}, // ? - lowercase a, umlaut {"\u00E5", "aring"}, // ? - lowercase a, ring {"\u00E6", "aelig"}, // ? - lowercase ae {"\u00E7", "ccedil"}, // ? - lowercase c, cedilla {"\u00E8", "egrave"}, // ? - lowercase e, grave accent {"\u00E9", "eacute"}, // ? - lowercase e, acute accent {"\u00EA", "ecirc"}, // ? - lowercase e, circumflex accent {"\u00EB", "euml"}, // ? - lowercase e, umlaut {"\u00EC", "igrave"}, // ? - lowercase i, grave accent {"\u00ED", "iacute"}, // ? - lowercase i, acute accent {"\u00EE", "icirc"}, // ? - lowercase i, circumflex accent {"\u00EF", "iuml"}, // ? - lowercase i, umlaut {"\u00F0", "eth"}, // ? - lowercase eth, Icelandic {"\u00F1", "ntilde"}, // ? - lowercase n, tilde {"\u00F2", "ograve"}, // ? - lowercase o, grave accent {"\u00F3", "oacute"}, // ? - lowercase o, acute accent {"\u00F4", "ocirc"}, // ? - lowercase o, circumflex accent {"\u00F5", "otilde"}, // ? - lowercase o, tilde {"\u00F6", "ouml"}, // ? - lowercase o, umlaut {"\u00F7", "divide"}, // division sign {"\u00F8", "oslash"}, // ? - lowercase o, slash {"\u00F9", "ugrave"}, // ? - lowercase u, grave accent {"\u00FA", "uacute"}, // ? - lowercase u, acute accent {"\u00FB", "ucirc"}, // ? - lowercase u, circumflex accent {"\u00FC", "uuml"}, // ? - lowercase u, umlaut {"\u00FD", "yacute"}, // ? - lowercase y, acute accent {"\u00FE", "thorn"}, // ? - lowercase thorn, Icelandic {"\u00FF", "yuml"}, // ? - lowercase y, umlaut {"'", "apos"}, // the controversial (but who cares!) ' // stackoverflow.com/questions/2083754/why-shouldnt-apos-be-used-to-escape-single-quotes }; private static final HashMap htmldecode_lookupMap; static { htmldecode_lookupMap = new HashMap(); for (final CharSequence[] seq : htmldecode_ESCAPES) htmldecode_lookupMap.put(seq[1].toString(), seq[0]); } // tok should be the output of htmlcoarsetok static List dropAllTags(List tok) { List list = new ArrayList(); for (int i = 0; i < tok.size(); i++) { String t = tok.get(i); if (t.startsWith("<")) { list.set(list.size()-1, list.get(list.size()-1) + tok.get(i+1)); ++i; } else list.add(tok.get(i)); } return list; } // alternatively, call this convenient function static String dropAllTags(String html) { return join(dropAllTags(htmlcoarsetok(html))); } // works on lists and strings and null static int indexOfIgnoreCase(Object a, Object b) { if (a == null) return -1; if (a instanceof String) { Matcher m = Pattern.compile((String) b, Pattern.CASE_INSENSITIVE + Pattern.LITERAL).matcher((String) a); if (m.find()) return m.start(); else return -1; } if (a instanceof List) { for (int i = 0; i < ((List) a).size(); i++) { Object o = ((List) a).get(i); if (o != null && ((String) o).equalsIgnoreCase((String) b)) return i; } return -1; } throw fail("Unknown type: " + a); } static boolean startsWithIgnoreCase(String a, String b) { return a != null && a.regionMatches(true, 0, b, 0, b.length()); } static boolean neq(Object a, Object b) { return !eq(a, b); } static void sort(T[] a, Comparator c) { Arrays.sort(a, c); } static void sort(List a, Comparator c) { Collections.sort(a, c); } static void sleepSeconds(long s) { if (s > 0) sleep(s*1000); } static void replaceLastElement(List l, A a) { if (nempty(l)) l.set(l(l)-1, a); } static void sleep(long ms) { try { Thread.sleep(ms); } catch (Exception e) { throw new RuntimeException(e); } } static void sleep() { try { print("Sleeping."); synchronized(main.class) { main.class.wait(); } } catch (Throwable __e) { throw __e instanceof RuntimeException ? (RuntimeException) __e : new RuntimeException(__e); }} // TODO: process CDATA? static List htmlcoarsetok(String s) { List tok = new ArrayList(); int l = s.length(); int i = 0; while (i < l) { int j = i; char c; // scan for non-tags while (j < l) { if (s.charAt(j) != '<') // regular character ++j; else if (s.substring(j, Math.min(j+4, l)).equals("")); j = Math.min(j+3, l); } else // it's a tag break; } tok.add(s.substring(i, j)); i = j; if (i >= l) break; c = s.charAt(i); // scan for tags if (c == '<') { ++j; while (j < l && s.charAt(j) != '>') ++j; // TODO: strings? if (j < l) ++j; } tok.add(s.substring(i, j)); i = j; } if ((tok.size() % 2) == 0) tok.add(""); return tok; } static String _computerID; public static String computerID() { try { if (_computerID == null) { File file = new File(userHome(), ".tinybrain/computer-id"); _computerID = loadTextFile(file.getPath(), null); if (_computerID == null) { _computerID = makeRandomID(12); saveTextFile(file.getPath(), _computerID); } } return _computerID; } catch (Throwable __e) { throw __e instanceof RuntimeException ? (RuntimeException) __e : new RuntimeException(__e); }} static String format(String pat, Object... args) { return format3(pat, args); } static List emptyList() { return new ArrayList(); //ret Collections.emptyList(); } static class Text { String title; List lines = new ArrayList(); } static List loadPoems() { List texts = new ArrayList(); List snippets = listSnippetsOfType(48); // "Natural Language" for (Snippet sn : snippets) try { if (parseSnippetID(sn.id) < 1003000) break; texts.addAll(loadPoems(sn.id)); } catch (Throwable __e) { printStackTrace(__e); } print("Got " + n(l(texts), "text") + " (" + structure(collect(texts, "title")) + ")"); return texts; } static List loadPoems(String snippetID) { List texts = new ArrayList(); List lines = toLinesFullTrim(loadSnippet(snippetID)); int i = 0; while (i < l(lines)) { Text text = new Text(); // title if (i+1 < l(lines) && lines.get(i+1).startsWith("-")) { text.title = lines.get(i); i += 2; } else text.title = ""; // text while (i < l(lines) && (i+1 >= l(lines) || !lines.get(i+1).startsWith("-"))) text.lines.add(lines.get(i++)); texts.add(text); } return texts; } public static String loadTextFile(String fileName) { try { return loadTextFile(fileName, null); } catch (IOException e) { throw new RuntimeException(e); } } public static String loadTextFile(String fileName, String defaultContents) throws IOException { if (!new File(fileName).exists()) return defaultContents; FileInputStream fileInputStream = new FileInputStream(fileName); InputStreamReader inputStreamReader = new InputStreamReader(fileInputStream, "UTF-8"); return loadTextFile(inputStreamReader); } public static String loadTextFile(File fileName) { try { return loadTextFile(fileName, null); } catch (IOException e) { throw new RuntimeException(e); } } public static String loadTextFile(File fileName, String defaultContents) throws IOException { try { return loadTextFile(fileName.getPath(), defaultContents); } catch (IOException e) { throw new RuntimeException(e); } } public static String loadTextFile(Reader reader) throws IOException { StringBuilder builder = new StringBuilder(); try { char[] buffer = new char[1024]; int n; while (-1 != (n = reader.read(buffer))) builder.append(buffer, 0, n); } finally { reader.close(); } return builder.toString(); } static String _userHome; static String userHome() { if (_userHome == null) { if (isAndroid()) _userHome = "/storage/sdcard0/"; else _userHome = System.getProperty("user.home"); //System.out.println("userHome: " + _userHome); } return _userHome; } static String format3(String pat, Object... args) { if (args.length == 0) return pat; List tok = javaTokPlusPeriod(pat); int argidx = 0; for (int i = 1; i < tok.size(); i += 2) if (tok.get(i).equals("*")) tok.set(i, format3_formatArg(argidx < args.length ? args[argidx++] : "null")); return join(tok); } static String format3_formatArg(Object arg) { if (arg == null) return "null"; if (arg instanceof String) { String s = (String) arg; return isIdentifier(s) || isNonNegativeInteger(s) ? s : quote(s); } if (arg instanceof Integer || arg instanceof Long) return String.valueOf(arg); return quote(structure(arg)); } /** writes safely (to temp file, then rename) */ public static void saveTextFile(String fileName, String contents) throws IOException { File file = new File(fileName); File parentFile = file.getParentFile(); if (parentFile != null) parentFile.mkdirs(); String tempFileName = fileName + "_temp"; if (contents != null) { FileOutputStream fileOutputStream = new FileOutputStream(tempFileName); OutputStreamWriter outputStreamWriter = new OutputStreamWriter(fileOutputStream, "UTF-8"); PrintWriter printWriter = new PrintWriter(outputStreamWriter); printWriter.print(contents); printWriter.close(); } if (file.exists() && !file.delete()) throw new IOException("Can't delete " + fileName); if (contents != null) if (!new File(tempFileName).renameTo(file)) throw new IOException("Can't rename " + tempFileName + " to " + fileName); } public static void saveTextFile(File fileName, String contents) { try { saveTextFile(fileName.getPath(), contents); } catch (IOException e) { throw new RuntimeException(e); } } static List collect(Collection c, String field) { return collectField(c, field); } static boolean preferCached = false; public static String loadSnippet(String snippetID) { try { return loadSnippet(parseSnippetID(snippetID), preferCached); } catch (IOException e) { throw new RuntimeException(e); } } public static String loadSnippet(String snippetID, boolean preferCached) throws IOException { return loadSnippet(parseSnippetID(snippetID), preferCached); } public static String loadSnippet(long snippetID, boolean preferCached) throws IOException { String text; // boss bot disabled for now for shorter transpilations /*text = getSnippetFromBossBot(snippetID); if (text != null) return text;*/ initSnippetCache(); text = DiskSnippetCache_get(snippetID); if (preferCached && text != null) return text; try { if (text != null) System.err.println("md5: " + md5(text)); URL url = new URL("http://tinybrain.de:8080/getraw.php?id=" + snippetID + "&utf8=1"); text = loadPage(url); } catch (RuntimeException e) { e.printStackTrace(); throw new IOException("Snippet #" + snippetID + " not found or not public"); } try { initSnippetCache(); DiskSnippetCache_put(snippetID, text); } catch (IOException e) { System.err.println("Minor warning: Couldn't save snippet to cache (" + DiskSnippetCache_getDir() + ")"); } return text; } static File DiskSnippetCache_dir; public static void initDiskSnippetCache(File dir) { DiskSnippetCache_dir = dir; dir.mkdirs(); } public static synchronized String DiskSnippetCache_get(long snippetID) throws IOException { return loadTextFile(DiskSnippetCache_getFile(snippetID).getPath(), null); } private static File DiskSnippetCache_getFile(long snippetID) { return new File(DiskSnippetCache_dir, "" + snippetID); } public static synchronized void DiskSnippetCache_put(long snippetID, String snippet) throws IOException { saveTextFile(DiskSnippetCache_getFile(snippetID).getPath(), snippet); } public static File DiskSnippetCache_getDir() { return DiskSnippetCache_dir; } public static void initSnippetCache() { if (DiskSnippetCache_dir == null) initDiskSnippetCache(new File(System.getProperty("user.home"), ".tinybrain/snippet-cache")); } static String makeRandomID(int length) { Random random = new Random(); char[] id = new char[length]; for (int i = 0; i < id.length; i++) id[i] = (char) ((int) 'a' + random.nextInt(26)); return new String(id); } static List listSnippetsOfType(int type) { return snippetsFromHTML("http://tinybrain.de:8080/tb/snippets.php?type=" + type + "&order=changed&reverse=1&longlist=1"); } static List collectField(Collection c, String field) { List l = new ArrayList(); for (Object a : c) l.add(getOpt(a, field)); return l; } static String md5(String text) { try { if (text == null) return "-"; return bytesToHex(md5_impl(text.getBytes("UTF-8"))); // maybe different than the way PHP does it... } catch (Throwable __e) { throw __e instanceof RuntimeException ? (RuntimeException) __e : new RuntimeException(__e); }} static String md5(byte[] data) { return bytesToHex(md5_impl(data)); } static byte[] md5_impl(byte[] data) { try { return MessageDigest.getInstance("MD5").digest(data); } catch (Exception e) { throw e instanceof RuntimeException ? (RuntimeException) e : new RuntimeException(e); } } static String md5(File file) { try { return md5(loadBinaryFile(file)); } catch (Throwable __e) { throw __e instanceof RuntimeException ? (RuntimeException) __e : new RuntimeException(__e); }} static boolean isIdentifier(String s) { return isJavaIdentifier(s); } static boolean isNonNegativeInteger(String s) { return s != null && Pattern.matches("\\d+", s); } static boolean isAndroid() { return System.getProperty("java.vendor").toLowerCase().indexOf("android") >= 0; } static boolean isJavaIdentifier(String s) { if (s.length() == 0 || !Character.isJavaIdentifierStart(s.charAt(0))) return false; for (int i = 1; i < s.length(); i++) if (!Character.isJavaIdentifierPart(s.charAt(i))) return false; return true; } public static String bytesToHex(byte[] bytes) { return bytesToHex(bytes, 0, bytes.length); } public static String bytesToHex(byte[] bytes, int ofs, int len) { StringBuilder stringBuilder = new StringBuilder(len*2); for (int i = 0; i < len; i++) { String s = "0" + Integer.toHexString(bytes[ofs+i]); stringBuilder.append(s.substring(s.length()-2, s.length())); } return stringBuilder.toString(); } public static byte[] loadBinaryFile(String fileName) throws IOException { if (!new File(fileName).exists()) return null; FileInputStream in = new FileInputStream(fileName); byte buf[] = new byte[1024]; ByteArrayOutputStream out = new ByteArrayOutputStream(); int l; while (true) { l = in.read(buf); if (l <= 0) break; out.write(buf, 0, l); } in.close(); return out.toByteArray(); } public static byte[] loadBinaryFile(File file) throws IOException { return loadBinaryFile(file.getPath()); } static class TableFinder { List tok; // list of tokens in HTML document List table; // list of tokens in table List> rows; // for every row, list of tokens in row List> data; // for every row, for every cell, inner data int i; boolean debug; void go(String html) { tok = htmlcoarsetok(html); i = 1; findTable(); } boolean findTable() { if (debug) print("Finding table."); for (; i < tok.size(); i += 2) if (isTag(tok.get(i), "table")) for (int j = i+2; j < tok.size(); j += 2) if (isTag(tok.get(j), "/table")) { if (debug) print("Table found!"); table = tok.subList(i-1, j+2); findRows(); i = j; return true; } return false; } void findRows() { List tok = table; rows = new ArrayList>(); data = new ArrayList>(); int rowStart = 0; for (int i = 1; i < table.size(); i += 2) { //print(tok.get(i)); if (isTag(tok.get(i), "tr")) rowStart = i; else if (isTag(tok.get(i), "/tr") && rowStart != 0) { List row = table.subList(rowStart-1, i+2); rows.add(row); data.add(getData(row)); } } if (debug) print(rows.size() + " row(s)"); if (debug) print("Top left cell: " + data.get(0).get(0)); } boolean isTag(String token, String tag) { return token.regionMatches(true, 0, "<" + tag + " ", 0, tag.length()+2) || token.regionMatches(true, 0, "<" + tag + ">", 0, tag.length()+2); } // called internally List getData(List row) { int colStart = 0; List cols = new ArrayList(); for (int i = 1; i < row.size(); i += 2) { String t = row.get(i); if (isTag(t, "td") || isTag(t, "th")) colStart = i; else if ((isTag(t, "/td") || isTag(t, "/th")) && colStart != 0) cols.add(join(row.subList(colStart+1, i))); } return cols; } // for clients List getRow(int row) { return data.get(row); } } static class Snippet { String id, title, md5; } // union-type entry static class E { String q, a, state; boolean test; // not used anymore probably String comment; // not checked for comparison E() {} E(String text, String type) { if (eq(type, "q")) q = text; else if (eq(type, "a")) a = text; else state = text; } // does not compare the "test" bit boolean eqTo(E y) { E x = this; return eq/*ic*/(x.q, y.q) && eq/*ic*/(x.a, y.a) && eq/*ic*/(x.state, y.state); } public boolean equals(Object o) { return o instanceof E && eqTo((E) o); } public int hashCode() { return stdHash(this, "q", "a", "state"); } static E state(String state) { if (state == null) return null; E e = new E(); e.state = state; return e; } static E q(String q) { if (q == null) return null; E e = new E(); e.q = q; return e; } static E a(String a) { if (a == null) return null; E e = new E(); e.a = a; return e; } public String toString() { return unparsePoemLine(this); } boolean q() { return q != null; } boolean a() { return a != null; } boolean state() { return state != null; } String type() { return q() ? "q" : a() ? "a" : "state"; } String text() { return q() ? q : a() ? a : state; } } static class Dialog { boolean good; Snippet snippet; List poem; } static class OccTree2 { OccTree2 parent; E e; List next = new ArrayList(); int count; OccTree2() {} OccTree2(E e) { this.e = e;} void addScript(List script) { OccTree2 node = this; ++count; for (E c : script) (node = node.getOrMakeFollowUp(c)).count++; } OccTree2 getOrMakeFollowUp(E e) { OccTree2 node = followUp(e); if (node == null) next.add(node = newChild(e)); return node; } OccTree2 followUp(E e) { for (OccTree2 t : next) if (eq(t.e, e)) return t; return null; } List followUpKeys() { return collect(next, "e"); } OccTree2 newChild(E e) { OccTree2 child = new OccTree2(e); child.parent = this; return child; } // size including all nodes int size() { int n = 1; for (OccTree2 t : next) n += t.size(); return n; } List allLeaves() { List l = new ArrayList(); collectLeaves(l); return l; } // does not include root node as it has no input line associated List allNodes() { List l = new ArrayList(); collectNodes(l); return l; } void collectLeaves(List l) { if (isLeaf()) l.add(this); else for (OccTree2 t : next) t.collectLeaves(l); } void collectNodes(List l) { if (!isRoot()) l.add(this); for (OccTree2 t : next) t.collectNodes(l); } boolean isRoot() { return e == null; } boolean isLeaf() { return !isRoot() && isEmpty(next); } int level() { int n = 0; OccTree2 node = this; while (node.parent != null) { ++n; node = node.parent; } return n; } } static class Matches { String[] m; String get(int i) { return m[i]; } String unq(int i) { return unquote(m[i]); } String fsi(int i) { return formatSnippetID(unq(i)); } String fsi() { return fsi(0); } String tlc(int i) { return unq(i).toLowerCase(); } boolean bool(int i) { return "true".equals(unq(i)); } String rest() { return m[m.length-1]; } // for matchStart int psi(int i) { return Integer.parseInt(unq(i)); } } static String formatSnippetID(String id) { return "#" + parseSnippetID(id); } static String formatSnippetID(long id) { return "#" + id; } static boolean equals(Object a, Object b) { return a == null ? b == null : a.equals(b); } static int stdHash(Object a, String... fields) { if (a == null) return 0; int hash = 0; for (String field : fields) hash = hash*2+hashCode(getOpt(a, field)); return hash; } static boolean isTag(String token, String tag) { return token.regionMatches(true, 0, "<" + tag + " ", 0, tag.length()+2) || token.regionMatches(true, 0, "<" + tag + ">", 0, tag.length()+2); } static String unparsePoemLine(E e) { return trim(unparsePoem(litlist(e))); } static String unparsePoem(List poem) { List l = new ArrayList(); for (E e : poem) if (e.q != null) l.add("Usr: " + trim(e.q)); else if (e.a != null) l.add("Bot: " + trim(e.a)); else if (e.state != null) l.add("[" + trim(e.state) + "]"); else l.add("?"); return joinLines(l); } static String trim(String s) { return s == null ? null : s.trim(); } static String trim(StringBuilder buf) { return buf.toString().trim(); } static String trim(StringBuffer buf) { return buf.toString().trim(); } static int hashCode(Object a) { return a == null ? 0 : a.hashCode(); } public static String joinLines(List lines) { return fromLines(lines); } }