def selected_document():
docid = get_docid(main_buf[main_win.cursor[0] - 1])
if docid:
fields = headers + ('bibtex', 'tags', 'filename', 'notes')
docs = list(ref.select_documents(fields, (docid,)))
if docs:
return docs[0]
def test_insert_document(self):
doc = \
{'author': 'Koren',
'bibtex': '@inproceedings{koren2008factorization,\n title={Factorization meets the neighborhood: a multifaceted collaborative filtering model},\n author={Koren, Y.},\n booktitle={Proceeding of the 14th ACM SIGKDD international conference on Knowledge discovery and data mining},\n pages={426--434},\n year={2008},\n organization={ACM}\n}\n',
'docid': 3,
'filename': 'Koren - 2008 - Factorization meets the neighborhood a multifaceted collaborative filtering model - 3.pdf',
'journal': 'Proceeding of the 14th ACM SIGKDD international conference on Knowledge discovery and data mining',
'notes': '',
'rating': 'U',
'tags': '',
'title': 'Factorization meets the neighborhood: a multifaceted collaborative filtering model',
'year': 2008}
# normal usecase test
self.assertEqual(ref.insert_document('data/kdd08koren.pdf'), 3)
self.assertDictEqual(dict(ref.select_documents('*', docids=[3]).fetchone()), doc)
self.assertTrue(self.file_in_docdir(doc['filename']))
# duplicate
with self.assertRaises(ref.DuplicateError) as e:
ref.insert_document('data/kdd08koren.pdf')
self.assertEqual(e.exception.message, doc['filename'])
with self.assertRaises(IOError):
ref.insert_document('not_exist.pdf')
with self.assertRaises(IOError):
ref.insert_document('data')
with self.assertRaises(ValueError):
ref.insert_document('test_ref.py')
def test_insert_document(self):
doc = \
{'author': 'Koren',
'bibtex': '@inproceedings{koren2008factorization,\n title={Factorization meets the neighborhood: a multifaceted collaborative filtering model},\n author={Koren, Y.},\n booktitle={Proceeding of the 14th ACM SIGKDD international conference on Knowledge discovery and data mining},\n pages={426--434},\n year={2008},\n organization={ACM}\n}\n',
'docid': 3,
'filename': 'Koren - 2008 - Factorization meets the neighborhood a multifaceted collaborative filtering model - 3.pdf',
'journal': 'Proceeding of the 14th ACM SIGKDD international conference on Knowledge discovery and data mining',
'notes': '',
'rating': 'U',
'tags': '',
'title': 'Factorization meets the neighborhood: a multifaceted collaborative filtering model',
'year': 2008}
# normal usecase test
self.assertEqual(ref.insert_document('data/kdd08koren.pdf'), 3)
self.assertDictEqual(
dict(ref.select_documents('*', docids=[3]).fetchone()), doc)
self.assertTrue(self.file_in_docdir(doc['filename']))
# duplicate
with self.assertRaises(ref.DuplicateError) as e:
ref.insert_document('data/kdd08koren.pdf')
self.assertEqual(e.exception.message, doc['filename'])
with self.assertRaises(IOError):
ref.insert_document('not_exist.pdf')
with self.assertRaises(IOError):
ref.insert_document('data')
with self.assertRaises(ValueError):
ref.insert_document('test_ref.py')
def test_update_document(self):
get_doc = lambda: dict(
ref.select_documents('*', docids=(2, )).fetchone())
doc = dict(self.documents[2])
ref.update_document(doc)
self.assertDictEqual(self.documents[2], doc)
self.assertDictEqual(self.documents[2], get_doc())
self.assertTrue(self.file_in_docdir(doc['filename']))
doc = \
{'author': 'author',
'bibtex': 'bibtex',
'docid': 2,
'filename': 'Yu et al - 2010 - Feature engineering and classifier ensemble for KDD cup 2010 - 2.pdf',
'journal': 'journal',
'notes': 'notes',
'rating': 'rating',
'tags': 'tags',
'title': 'title',
'year': 42}
ref.update_document(dict(doc))
doc['filename'] = 'author - 42 - title - 2.pdf'
self.assertDictEqual(doc, get_doc())
self.assertTrue(self.file_in_docdir(doc['filename']))
def selected_document():
docid = get_docid(main_buf[main_win.cursor[0] - 1])
if docid:
fields = headers + ('bibtex', 'tags', 'filename', 'notes')
docs = list(ref.select_documents(fields, (docid, )))
if docs:
return docs[0]
def parse_info():
bibtex, rest, notes = '\n'.join(info_buf).split('\n---')
doc = ref.parse_bibtex(bibtex)
doc.update(dict(re.findall(r'(\w+)=(.*)', rest)))
doc['bibtex'] = bibtex
doc['docid'] = int(doc['docid'])
doc['notes'] = notes.strip()
doc.update(next(ref.select_documents(('filename',), (doc['docid'],))))
tags.update(doc['tags'].split('; '))
return doc
def parse_info():
bibtex, rest, notes = '\n'.join(info_buf).split('\n---')
doc = ref.parse_bibtex(bibtex)
doc.update(dict(re.findall(r'(\w+)=(.*)', rest)))
doc['bibtex'] = bibtex
doc['docid'] = int(doc['docid'])
doc['notes'] = notes.strip()
doc.update(next(ref.select_documents(('filename', ), (doc['docid'], ))))
tags.update(doc['tags'].split('; '))
return doc
def update_main(docids=None):
if not docids:
docids = filter(None, (get_docid(line) for line in main_buf))
if not docids:
return
cur = ref.select_documents(headers, docids)
docs = {doc['docid']: str_document(doc) for doc in cur}
for i, line in enumerate(main_buf):
id = get_docid(line)
if id in docs:
main_buf[i] = docs[id]
def update_main(docids=None):
if not docids:
docids = filter(None, (get_docid(line) for line in main_buf))
if not docids:
return
cur = ref.select_documents(headers, docids)
docs = {doc['docid']: str_document(doc) for doc in cur}
for i, line in enumerate(main_buf):
id = get_docid(line)
if id in docs:
main_buf[i] = docs[id]
def test_select_documents(self):
r = [(r['docid'], r['title']) for r in ref.select_documents(['docid', 'title'])]
self.assertListEqual(r,
[(2, 'Feature engineering and classifier ensemble for KDD cup 2010'),
(1, 'Improving regularized singular value decomposition for collaborative filtering')])
with self.assertRaises(IndexError):
ref.select_documents(['docid']).fetchone()['title']
self.assertListEqual([r['docid'] for r in ref.select_documents('*', order='year ASC')], [1, 2])
self.assertListEqual([r['docid'] for r in ref.select_documents('*', docids=[1])], [1])
self.assertDictEqual(dict(ref.select_documents('*', docids=(1,)).fetchone()), self.documents[1])
def test_update_document(self):
get_doc = lambda: dict(ref.select_documents('*', docids=(2,)).fetchone())
doc = dict(self.documents[2])
ref.update_document(doc)
self.assertDictEqual(self.documents[2], doc)
self.assertDictEqual(self.documents[2], get_doc())
self.assertTrue(self.file_in_docdir(doc['filename']))
doc = \
{'author': 'author',
'bibtex': 'bibtex',
'docid': 2,
'filename': 'Yu et al - 2010 - Feature engineering and classifier ensemble for KDD cup 2010 - 2.pdf',
'journal': 'journal',
'notes': 'notes',
'rating': 'rating',
'tags': 'tags',
'title': 'title',
'year': 42}
ref.update_document(dict(doc))
doc['filename'] = 'author - 42 - title - 2.pdf'
self.assertDictEqual(doc, get_doc())
self.assertTrue(self.file_in_docdir(doc['filename']))
def test_select_documents(self):
r = [(r['docid'], r['title'])
for r in ref.select_documents(['docid', 'title'])]
self.assertListEqual(r, [
(2,
'Feature engineering and classifier ensemble for KDD cup 2010'),
(1,
'Improving regularized singular value decomposition for collaborative filtering'
)
])
with self.assertRaises(IndexError):
ref.select_documents(['docid']).fetchone()['title']
self.assertListEqual(
[r['docid'] for r in ref.select_documents('*', order='year ASC')],
[1, 2])
self.assertListEqual(
[r['docid'] for r in ref.select_documents('*', docids=[1])], [1])
self.assertDictEqual(
dict(ref.select_documents('*', docids=(1, )).fetchone()),
self.documents[1])
def test_update_document(self):
t = time()
for doc in map(dict, ref.select_documents('*', docids=range(100))):
doc['notes'] += 'foo bar baz'
ref.update_document(doc)
self.assertLess(time() - t, 0.2)
def add_document(fname):
docid = ref.insert_document(fname)
if docid:
doc = next(ref.select_documents(headers, (docid, )))
main_buf[:0] = [str_document(doc)]
main_win.cursor = (1, 0)
def reload_main():
global last_select_cmd
last_select_cmd = reload_main
docs = list(map(str_document, ref.select_documents(headers, order=order)))
main_buf[:] = docs
def test_select_documents(self):
t = time()
for i in range(100):
ref.select_documents(['docid'], docids=[i])
self.assertLess(time() - t, 0.2)
def add_document(fname):
docid = ref.insert_document(fname)
if docid:
doc = next(ref.select_documents(headers, (docid,)))
main_buf[:0] = [str_document(doc)]
main_win.cursor = (1, 0)
def reload_main():
global last_select_cmd
last_select_cmd = reload_main
docs = list(map(str_document, ref.select_documents(headers, order=order)))
main_buf[:] = docs
def test_select_documents(self):
t = time()
for i in range(100):
ref.select_documents(['docid'], docids=[i])
self.assertLess(time() - t, 0.2)
def test_update_document(self):
t = time()
for doc in map(dict, ref.select_documents('*', docids=range(100))):
doc['notes'] += 'foo bar baz'
ref.update_document(doc)
self.assertLess(time() - t, 0.2)