def downloadCorpus(snapshotDir, corpusDir, projectName, configInfo):
# 2. Dump the snapshots for a project
msg = '---------------------------------------------------- \n'
msg += ' Dump the corpus for project %s \n' % projectName
msg += '---------------------------------------------------- \n'
print(msg)
project_snapshot_dir = os.path.join(snapshotDir, projectName)
project_corpus_dir = os.path.join(corpusDir, projectName)
if os.path.isdir(project_corpus_dir):
print "!! %s already exists...returning \n" % project_corpus_dir
#return
corpus = Corpus(project_snapshot_dir, 'java', project_corpus_dir,
configInfo)
#logging.debug(corpus)
#print corpus
corpus.dump()
if not os.path.isdir(args.proj_dir):
print "!! Please provide a valid directory, given: %s" % (
args.proj_dir)
sys.exit()
print "Going to process project %s for %s" % (args.proj_dir, args.lang)
print "Creating output directory at %s" % (args.out_dir)
Util.cleanup(args.log_file)
#od = OutDir(args.out_dir)
#od.create_out_dir(args.out_dir)
Log.setLogger(args.verbose, args.log_file)
cfg = Config(args.config_file)
corpus = Corpus(args.proj_dir, args.lang, args.out_dir, cfg)
logging.debug(corpus)
corpus.dump()
#print corpus.printSnapshots()
#1. Fetch one line changes of a given project for a given language from the database
#edits = fetchEdits(cfg, args.proj_dir, args.lang)
#2. build the test corpus based on each edit
#createTrainingCorpus(args.proj_dir, args.lang, args.out_dir, edits)
#createTestCorpus(args.proj_dir, args.lang, od, edits)
