Added web interface, crawler and more work on local storage

This commit is contained in:
simon
2018-02-21 20:07:59 -05:00
parent de0a835ecd
commit 165844e4ca
24 changed files with 1346 additions and 235 deletions

View File

@@ -1,10 +1,22 @@
from unittest import TestCase
from parsing import GenericFileParser, Sha1CheckSumCalculator, ExtensionMimeGuesser
from crawler import Crawler
class CrawlerTest(TestCase):
def test_dir_walk(self):
c = Crawler()
c = Crawler([GenericFileParser([Sha1CheckSumCalculator()], ExtensionMimeGuesser())])
c.crawl("test_folder")
self.assertEqual(len(c.documents), 28)
def test_get_parser_by_ext(self):
c = Crawler([GenericFileParser([Sha1CheckSumCalculator()], ExtensionMimeGuesser())])
self.assertIsInstance(c.get_parser_by_ext("any"), GenericFileParser)
# todo add more parsers here