The table search code has been modified to provide a simpler interface, we have added some checks for false positives in the code and it now has an interface similar to the SeerSuite Inteface - the way to run the code would include setting up the class path to include the bin directory of tablesearch, PDFBox library, the FontBox library, jdom , the log4j library jar files (which can be found in the lib directory) into the path and running java edu/psu/seersuite/extractors/tableextractor/extraction/SeerSuiteTableExtractor PDFFILE ID