AIL/ail-framework
7
0
Fork 0
mirror of https://github.com/ail-project/ail-framework.git synced 2024-11-14 02:28:23 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

-s option added to find similar documents

Browse source 
By default, the index is not storing the vector of the document (Whoosh
document schema). It won't work if you don't change the schema of the
index for the content. It depends of your storage strategy.
This commit is contained in:
Alexandre Dulaunoy 2014-08-12 13:42:26 +02:00
parent fd6e1a8436
commit 0b4a80b7ea
1 changed files with 12 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

12
bin/tests/indexer_lookup.py
View file

@ -35,11 +35,13 @@ argParser.add_argument('-n', action='store_true', default=False, help='return nu
argParser.add_argument('-t', action='store_true', default=False, help='dump top 500 terms') argParser.add_argument('-t', action='store_true', default=False, help='dump top 500 terms')
argParser.add_argument('-l', action='store_true', default=False, help='dump all terms encountered in indexed documents') argParser.add_argument('-l', action='store_true', default=False, help='dump all terms encountered in indexed documents')
argParser.add_argument('-f', action='store_true', default=False, help='dump each matching document') argParser.add_argument('-f', action='store_true', default=False, help='dump each matching document')
argParser.add_argument('-s', action='append', help='search similar documents')
args = argParser.parse_args() args = argParser.parse_args()
from whoosh import index from whoosh import index
from whoosh.fields import * from whoosh.fields import *
import whoosh
schema = Schema(title=TEXT(stored=True), path=ID(stored=True), content=TEXT) schema = Schema(title=TEXT(stored=True), path=ID(stored=True), content=TEXT)
ix = index.open_dir(indexpath) ix = index.open_dir(indexpath)
@ -62,6 +64,16 @@ if args.t:
print (x) print (x)
exit(0) exit(0)
if args.s:
# By default, the index is not storing the vector of the document (Whoosh
# document schema). It won't work if you don't change the schema of the
# index for the content. It depends of your storage strategy.
docnum = ix.searcher().document_number(path=args.s)
r = ix.searcher().more_like(docnum, "content")
for hit in r:
print(hit["path"])
exit(0)
if args.q is None: if args.q is None:
argParser.print_help() argParser.print_help()
exit(1) exit(1)