#!/usr/bin/env python
'''
@note: to be removed
'''
import argparse
from lucenesearch.lucene_index import lucene_index
from lucenesearch.lucene_search import lucene_search
if __name__ == "__main__":
arg_parser = argparse.ArgumentParser(description='Lucene index and search')
arg_parser.add_argument("-d", dest="input_folder", type=str,
help="The root directory to index and search",
required=True)
arg_parser.add_argument("-o", dest="output_folder", type=str, help="Output directory of index",
default="/home/abhiramj/code/temp/index",
required=False)
arg_parser.add_argument("-q", dest="query_text", type=str, help="Query to search for")
arg_parser.add_argument("-l", dest="limit", type=int, help="Maximum number of results")
args = arg_parser.parse_args()
lucene_index(args.input_folder,args.output_folder)
responsive = lucene_search(args.output_folder, args.limit, args.query_text)
query = raw_input('Enter query: ') # 'Human computer interaction'
limit = int(raw_input('Limit: '))
if search_algorithm == 'LDA':
None
# Process the query
# responsive_docs, non_responsive_docs = process_query(query, dictionary, lda, index, doc_paths, limit)
# nrd = np.array(non_responsive_docs)
# nrd_paths = [os.path.join(dir_path, nrd[idx,2]) for idx, dir_path in enumerate(nrd[:,1])] # looks like i'm not getting full file paths
elif search_algorithm == 'Lucene':
# None
responsive_docs = lucene_search(lucene_index_file, limit, query)
non_responsive_docs = []
for file_name in find_files_in_folder(DATA_PATH):
if os.path.dirname(file_name) is not lucene_index_file: # skipping index directory
if file_name not in responsive_docs:
non_responsive_docs.append(file_name)
nrd_paths=non_responsive_docs
print 'Number of responsive documents:', len(responsive_docs)
print 'Number of non responsive documents:', len(non_responsive_docs)
print 'The responsive files are: '
for f in responsive_docs:
print f
