fix ids

gogole/commands/index_command.py

@@ -5,7 +5,7 @@ def run_index_command(collection, args):
     indexer = collection.indexer
 
     if args.index_command == 'build':
-        build_index = False
+        build_index = args.build_no_cache
 
         if not args.build_no_cache:
             # try to load index from the disk
@@ -18,11 +18,11 @@ def run_index_command(collection, args):
             print('...   loading the documents...')
 
             count_documents = 0
-            for doc_id, document in enumerate(parser.find_documents(limit=None)):
+            for document in parser.find_documents(limit=None):
                 count_documents += 1
                 tokens = tokenizer.get_tokens(document)
 
-                indexer.add_document_tokens(doc_id, tokens)
+                indexer.add_document_tokens(document.document_id, tokens)
 
             print('...   {} documents loaded'.format(count_documents))
 

gogole/indexer/bsbi_indexer.py

@@ -117,7 +117,7 @@ class BSBIIndexer:
         """
 
         if token not in self.tokens_map:
-            return []
+            return set()
 
         token_id = self.tokens_map[token]
 

gogole/parser/stanford_parser.py

 from gogole.document import StanfordDocument
 from os import listdir
+import itertools
 
 class StanfordParser:
 
@@ -7,16 +8,17 @@ class StanfordParser:
 
 
     def find_documents(self, limit=None):
-        counter = 0 # count documents found
+        counter = itertools.count() # count documents found
 
         for collection_index in range(10):
             collection_dir = self.DIRECTORY + "/" + str(collection_index)
 
             for filename in listdir(collection_dir):
                 with open(collection_dir + "/" + filename, 'r') as f:
-                    current_document_id = str(collection_index) + filename
+                    url = str(collection_index) + filename
+                    current_document_id = next(counter)
                     current_document = StanfordDocument(current_document_id)
-                    counter += 1
+
                     content = ""
 
                     for line in f:

main.py

@@ -62,7 +62,7 @@ def build_cli_search_parser(root_parser):
     search_parser.add_argument('--vectorial', action='store_const', const='vectorial', dest='search_query_type', help="use the vectorial model")
 
 
-    search_parser.add_argument('query', help="your query")
+    search_parser.add_argument('query', help="your query", nargs='*')
 
     search_parser.set_defaults(search_query_type='boolean')