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.reflect.*; import java.net.*; import java.io.*; 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 { public static void main(String[] args) throws Exception { // List all JavaX programs List ids = searchSnippets("type:34 type:40"); // all main programs print(ids.size() + " JavaX programs found"); // Load their sources // Find questions // Group } // returns list of snippet IDs static List searchSnippets(String query) { try { String url = "http://tinybrain.de:8080/tb/search.php?q=" + urlencode(query); String page = loadPage(url); Matcher m = Pattern.compile(">(#\\d+) - (.*?)
").matcher(page); List ids = new ArrayList(); while (m.find()) ids.add(m.group(1)); return ids; } catch (Throwable __e) { throw __e instanceof RuntimeException ? (RuntimeException) __e : new RuntimeException(__e); }} static List findQuestions(String src) { List questions = new ArrayList(); List tok = javaTok(src); for (int i = 1; i+4 < tok.size(); i += 2) if (tok.get(i).equals("match3") && tok.get(i+2).equals("(") && isQuoted(tok.get(i+4))) questions.add(tok.get(i+4)); return questions; } // supports the usual quotings (', ", variable length double brackets) static boolean isQuoted(String s) { if (s.startsWith("'") || s.startsWith("\"")) return true; if (!s.startsWith("[")) return false; int i = 1; while (i < s.length() && s.charAt(i) == '=') ++i; return i < s.length() && s.charAt(i) == '['; //return Pattern.compile("^\\[=*\\[").matcher(s).find(); } // 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) { ++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))); 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 ++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 loadPage(String url) { try { if(url.startsWith("tb/")) url = "tinybrain.de:8080/" + url; if (url.indexOf("://") < 0) url = "http://" + url; return loadPage(new URL(url)); } catch (IOException e) { throw new RuntimeException(e); } } public static String loadPage(URL url) { try { System.out.println("Loading: " + url.toExternalForm()); URLConnection con = url.openConnection(); return loadPage(con, url); } catch (IOException e) { throw new RuntimeException(e); } } public static String loadPage(URLConnection con, URL url) throws IOException { String contentType = con.getContentType(); if (contentType == null) throw new IOException("Page could not be read: " + url); //Log.info("Content-Type: " + contentType); String charset = loadPage_guessCharset(contentType); Reader r = new InputStreamReader(con.getInputStream(), 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/html;\\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 String urlencode(String x) { try { return URLEncoder.encode(unnull(x), "UTF-8"); } catch (UnsupportedEncodingException e) { throw new RuntimeException(e); } } static String unnull(String s) { return s == null ? "" : s; } }