import javax.imageio.*; import java.awt.image.*; import java.awt.event.*; import java.awt.*; import java.security.NoSuchAlgorithmException; import java.security.MessageDigest; import java.lang.management.*; import java.lang.ref.*; import java.lang.reflect.*; import java.net.*; import java.io.*; import javax.swing.table.*; import javax.swing.text.*; import javax.swing.event.*; import javax.swing.*; import java.util.concurrent.atomic.*; import java.util.concurrent.*; import java.util.regex.*; import java.util.List; import java.util.zip.*; import java.util.*; public class main { static List rules = new ArrayList(); static List statements = new ArrayList(); public static void main(String[] args) throws Exception { rules.add("\"$1 is the singular of $2.\" <=> \"$2 is the plural of $1.\""); statements.add("house is the singular of houses."); process(); print(fromLines(statements)); } static void process() { for (String rule : rules) { Matches m = new Matches(); if (match3("* <=> *", rule, m)) { String l = m.unq(0), r = m.unq(1); for (Map map : matchStatements(l)) addStatement(convert(r, map)); } } } static List> matchStatements(String pat) { List> l = new ArrayList>(); for (String s : statements) { Map m = match4(pat, s); if (m != null) l.add(m); } return l; } static Map match4(String pat, String s) { List tok1 = parse3(pat), tok2 = parse3(s); if (tok1.size() != tok2.size()) return null; Map m = new TreeMap(); for (int i = 1; i < tok1.size(); i += 2) { String t1 = tok1.get(i), t2 = tok2.get(i); if (isVar(t1)) m.put(t1, t2); else if (!t1.equalsIgnoreCase(t2)) return null; } return m; } static boolean isVar(String s) { return s.startsWith("$") && s.length() > 1; } static String convert(String r, Map matches) { List tok = javaTokPlusPeriod(r); for (int i = 1; i < tok.size(); i += 2) { if (tok.get(i).startsWith("$")) { String m = matches.get(tok.get(i)); if (m != null) tok.set(i, m); } } return join(tok); } static void addStatement(String s) { for (String st : statements) if (match3(st, s)) return; statements.add(s); } 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.length()-1); 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; } i++; } sb.append(ch); } return sb.toString(); } else return s; // return original } // unquote static boolean parseBoolean(String s) { return eq(s, "true"); } // parseBoolean static String formatSnippetID(String id) { return "#" + parseSnippetID(id); } static String formatSnippetID(long id) { return "#" + id; } // formatSnippetID static List parse3(String s) { return dropPunctuation(javaTokPlusPeriod(s)); } static class Matches { String[] m; String unq(int i) { return unquote(m[i]); } String fsi(int i) { return formatSnippetID(unq(i)); } boolean bool(int i) { return parseBoolean(unq(i)); } } // class Matches 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; List tokpat = parse3(pat), toks = parse3(s); 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 boolean eq(Object a, Object b) { return a == null ? b == null : a.equals(b); } // This is made for NL parsing. // It's javaTok extended with "..." token and "$n" 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 == '\'' || c == '"') { char opener = c; ++j; while (j < l) { if (s.charAt(j) == opener) { ++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)) || 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 (s.substring(j, Math.min(j+3, l)).equals("...")) j += 3; else if (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 void print() { System.out.println(); } static void print(Object o) { System.out.println(o); } static void print(long i) { System.out.println(i); } public static String fromLines(List lines) { StringBuilder buf = new StringBuilder(); for (String line : lines) { buf.append(line).append('\n'); } return buf.toString(); } 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); } public static long parseSnippetID(String snippetID) { return Long.parseLong(shortenSnippetID(snippetID)); } 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)) && !t.equals("*")) { tok.set(i-1, tok.get(i-1) + tok.get(i+1)); tok.remove(i); tok.remove(i); i -= 2; } } return tok; } // 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 ("*".equals(p)) result.add(t); else if (!p.equalsIgnoreCase(t)) return null; } return result.toArray(new String[result.size()]); } 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 snippetID; } }