LOG.info("Input path: " + inputPath);
LOG.info("Target-language stopwords: " + eStopwords);
LOG.info("Target-language stemmed stopwords: " + eStemmedStopwords);
LOG.info("Target-language tokenizer model: " + eTokenizerModel);
DocLengthTable mDLTable;
try {
mDLTable = new DocLengthTable4B(env.getDoclengthsData(), fs);
} catch (IOException e1) {
throw new RuntimeException("Error initializing Doclengths file");
}
LOG.info(mDLTable.getAvgDocLength()+" is average source-language document length.");
LOG.info(targetEnv.readCollectionDocumentCount()+" is number of target-language docs. We use the target-side DF table so we set #docs to this value in our scoring model.");
/////// Configuration setup
conf.set(Constants.IndexPath, indexPath);
conf.set("Ivory.ScoringModel", scoringModel);
conf.setFloat("Ivory.AvgDocLen", mDLTable.getAvgDocLength());
conf.setInt(Constants.CollectionDocumentCount, targetEnv.readCollectionDocumentCount());
conf.set(Constants.Language, getConf().get("Ivory.Lang"));
conf.set("Ivory.Normalize", getConf().get("Ivory.Normalize"));
conf.set("Ivory.MinNumTerms", getConf().get("Ivory.MinNumTerms"));