def test_tag_counts(fs):
fs.create_file('/notes/one.md', contents='#tag1 #tag1 #tag2')
fs.create_file('/notes/two.md', contents='#tag1 #tag3')
fs.create_file('/notes/three.md', contents='#tag1 #tag3 #tag4')
repo = DirectRepoConf(root_paths={'/notes'}).instantiate()
assert repo.tag_counts(FileQuery()) == {'tag1': 3, 'tag2': 1, 'tag3': 2, 'tag4': 1}
assert repo.tag_counts(FileQuery.parse('tag:tag3')) == {'tag1': 2, 'tag3': 2, 'tag4': 1}
def tag_counts(self, query: FileQueryIsh = FileQuery()) -> Dict[str, int]:
query = FileQuery.parse(query)
result = defaultdict(int)
for info in self.query(query, FileInfoReq(path=True, tags=True)):
for tag in info.tags:
result[tag] += 1
return result
def test_parse_query():
strquery = 'tag:first+tag,second -tag:third,fourth+tag tag:fifth sort:created,-backlinks'
expected = FileQuery(include_tags={'first tag', 'second', 'fifth'},
exclude_tags={'third', 'fourth tag'},
sort_by=[
FileQuerySort(FileQuerySortField.CREATED),
FileQuerySort(FileQuerySortField.BACKLINKS_COUNT,
reverse=True)
])
assert FileQuery.parse(strquery) == expected
def query(self, query: FileQueryIsh = FileQuery(), fields: FileInfoReqIsh = FileInfoReq.internal())\
-> Iterator[FileInfo]:
fields = dataclasses.replace(FileInfoReq.parse(fields),
tags=(fields.tags or query.include_tags
or query.exclude_tags))
query = FileQuery.parse(query)
filtered = query.apply_filtering(
self.info(e.dir_entry.path,
fields,
path_resolved=True,
skip_parse=e.skip_parse) for e in self._paths())
yield from query.apply_sorting(filtered)
def query(self, query: FileQueryIsh = FileQuery(), fields: FileInfoReqIsh = FileInfoReq.internal())\
-> Iterator[FileInfo]:
self._refresh_if_needed()
query = FileQuery.parse(query)
cursor = self.connection.cursor()
cursor.execute('SELECT path FROM files WHERE existent = TRUE')
# TODO: Obviously, this is super lazy and inefficient. We should do as much filtering and data loading in
# the query as we reasonably can.
fields = dataclasses.replace(FileInfoReq.parse(fields),
tags=(fields.tags or query.include_tags
or query.exclude_tags))
filtered = query.apply_filtering(
self.info(path, fields, path_resolved=True) for (path, ) in cursor)
yield from query.apply_sorting(filtered)
def test_query(fs):
fs.create_file('/notes/one.md', contents='#tag1 #tag1 #tag2 #tag4')
fs.create_file('/notes/two.md', contents='#tag1 #tag3')
fs.create_file('/notes/three.md', contents='#tag1 #tag3 #tag4')
repo = DirectRepoConf(root_paths={'/notes'}).instantiate()
paths = {i.path for i in repo.query(FileQuery())}
assert paths == {'/notes/one.md', '/notes/two.md', '/notes/three.md'}
paths = {i.path for i in repo.query(FileQuery.parse('tag:tag3'))}
assert paths == {'/notes/two.md', '/notes/three.md'}
paths = {i.path for i in repo.query(FileQuery.parse('tag:tag1,tag4'))}
assert paths == {'/notes/one.md', '/notes/three.md'}
assert not list(repo.query(FileQuery.parse('tag:bogus')))
paths = {i.path for i in repo.query(FileQuery.parse('-tag:tag2'))}
assert paths == {'/notes/two.md', '/notes/three.md'}
paths = {i.path for i in repo.query(FileQuery.parse('-tag:tag2,tag4'))}
assert paths == {'/notes/two.md'}
assert not list(repo.query(FileQuery.parse('-tag:tag1')))
paths = {i.path for i in repo.query(FileQuery.parse('tag:tag3 -tag:tag4'))}
assert paths == {'/notes/two.md'}
assert [os.path.basename(i.path) for i in repo.query('sort:filename')] == ['one.md', 'three.md', 'two.md']
def test_apply_sorting():
data = [
FileInfo('/a/one',
tags={'baz'},
backlinks=[LinkInfo(referrer='whatever', href='whatever')]),
FileInfo('/b/two', title='Beta', created=datetime(2010, 1, 15)),
FileInfo('/c/Three',
title='Gamma',
created=datetime(2012, 1, 9),
backlinks=[
LinkInfo(referrer='whatever', href='whatever'),
LinkInfo(referrer='whatever', href='whatever')
]),
FileInfo('/d/four',
title='delta',
created=datetime(2012, 1, 9),
tags={'foo', 'bar'})
]
assert FileQuery.parse('sort:path').apply_sorting(data) == data
assert FileQuery.parse('sort:-path').apply_sorting(data) == list(
reversed(data))
assert FileQuery.parse('sort:filename').apply_sorting(data) == [
data[3], data[0], data[2], data[1]
]
assert FileQuery(sort_by=[
FileQuerySort(FileQuerySortField.FILENAME, ignore_case=False)
]).apply_sorting(data) == [data[2], data[3], data[0], data[1]]
assert FileQuery.parse('sort:title').apply_sorting(data) == [
data[1], data[3], data[2], data[0]
]
assert FileQuery(
sort_by=[FileQuerySort(FileQuerySortField.TITLE, ignore_case=False)
]).apply_sorting(data) == [
data[1], data[2], data[3], data[0]
]
assert FileQuery(
sort_by=[FileQuerySort(FileQuerySortField.TITLE, missing_first=True)
]).apply_sorting(data) == [
data[0], data[1], data[3], data[2]
]
assert FileQuery(sort_by=[
FileQuerySort(
FileQuerySortField.TITLE, missing_first=True, reverse=True)
]).apply_sorting(data) == [data[2], data[3], data[1], data[0]]
assert FileQuery.parse('sort:created').apply_sorting(data) == [
data[1], data[2], data[3], data[0]
]
assert FileQuery.parse('sort:-created').apply_sorting(data) == [
data[0], data[2], data[3], data[1]
]
assert FileQuery(sort_by=[
FileQuerySort(FileQuerySortField.CREATED, missing_first=True)
]).apply_sorting(data) == [data[0], data[1], data[2], data[3]]
assert FileQuery.parse('sort:-tags').apply_sorting(data) == [
data[3], data[0], data[1], data[2]
]
assert FileQuery.parse('sort:-backlinks').apply_sorting(data) == [
data[2], data[0], data[1], data[3]
]
assert FileQuery.parse('sort:created,title').apply_sorting(data) == [
data[1], data[3], data[2], data[0]
]
assert FileQuery.parse('sort:created,-title').apply_sorting(data) == [
data[1], data[2], data[3], data[0]
]
def tag_counts(self, query: FileQueryIsh = FileQuery()) -> Dict[str, int]:
"""Returns a map of tag names to the number of files matching the query which posses that tag."""
raise NotImplementedError()
def query(self, query: FileQueryIsh = FileQuery(), fields: FileInfoReqIsh = FileInfoReq.internal())\
-> Iterator[FileInfo]:
"""Returns the requested fields for all files matching the given query."""
raise NotImplementedError()