!752

lib 1004690 // tika

import org.apache.http.HttpEntity;
import org.apache.http.HttpResponse;
import org.apache.http.client.methods.HttpGet;
import org.apache.http.impl.client.DefaultHttpClient;
import org.apache.tika.metadata.Metadata;
import org.apache.tika.metadata.TikaCoreProperties;
import org.apache.tika.parser.AutoDetectParser;
import org.apache.tika.parser.ParseContext;
import org.apache.tika.sax.BodyContentHandler;

static Map<S, O> processFile(File file) ctex {
  new HashMap<S, O> map;
  InputStream input = new FileInputStream(file);
  try {
    BodyContentHandler handler = new BodyContentHandler(-1);
    Metadata metadata = new Metadata();
    AutoDetectParser parser = new AutoDetectParser();
    ParseContext parseContext = new ParseContext();
    parser.parse(input, handler, metadata, parseContext);
    map.put("text", handler.toString());
    map.put("title", metadata.get(TikaCoreProperties.TITLE));
    map.put("pageCount", metadata.get("xmpTPg:NPages"));
  } finally {
    input.close();
  }
  return map;
}

p {
  Map<S, O> extractedMap = processFile(new File(or(get(args, 0), "/home/stefan/Desktop/maude-primer.pdf")));
  S text = (S) extractedMap.get("text");
  print(text);
  print(l(text));
}

Began life as a copy of #1004691