searcharray 0.0.25__tar.gz → 0.0.26__tar.gz
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- {searcharray-0.0.25 → searcharray-0.0.26}/PKG-INFO +1 -1
- {searcharray-0.0.25 → searcharray-0.0.26}/searcharray/phrase/middle_out.py +1 -1
- {searcharray-0.0.25 → searcharray-0.0.26}/searcharray.egg-info/PKG-INFO +1 -1
- {searcharray-0.0.25 → searcharray-0.0.26}/setup.py +1 -1
- {searcharray-0.0.25 → searcharray-0.0.26}/test/test_tmdb.py +13 -0
- {searcharray-0.0.25 → searcharray-0.0.26}/README.md +0 -0
- {searcharray-0.0.25 → searcharray-0.0.26}/pyproject.toml +0 -0
- {searcharray-0.0.25 → searcharray-0.0.26}/searcharray/__init__.py +0 -0
- {searcharray-0.0.25 → searcharray-0.0.26}/searcharray/phrase/__init__.py +0 -0
- {searcharray-0.0.25 → searcharray-0.0.26}/searcharray/phrase/posn_diffs.py +0 -0
- {searcharray-0.0.25 → searcharray-0.0.26}/searcharray/phrase/scan_merge.py +0 -0
- {searcharray-0.0.25 → searcharray-0.0.26}/searcharray/postings.py +0 -0
- {searcharray-0.0.25 → searcharray-0.0.26}/searcharray/solr.py +0 -0
- {searcharray-0.0.25 → searcharray-0.0.26}/searcharray/term_dict.py +0 -0
- {searcharray-0.0.25 → searcharray-0.0.26}/searcharray/utils/__init__.py +0 -0
- {searcharray-0.0.25 → searcharray-0.0.26}/searcharray/utils/bitcount.py +0 -0
- {searcharray-0.0.25 → searcharray-0.0.26}/searcharray/utils/mat_set.py +0 -0
- {searcharray-0.0.25 → searcharray-0.0.26}/searcharray/utils/roaringish.py +0 -0
- {searcharray-0.0.25 → searcharray-0.0.26}/searcharray/utils/row_viewable_matrix.py +0 -0
- {searcharray-0.0.25 → searcharray-0.0.26}/searcharray.egg-info/SOURCES.txt +0 -0
- {searcharray-0.0.25 → searcharray-0.0.26}/searcharray.egg-info/dependency_links.txt +0 -0
- {searcharray-0.0.25 → searcharray-0.0.26}/searcharray.egg-info/entry_points.txt +0 -0
- {searcharray-0.0.25 → searcharray-0.0.26}/searcharray.egg-info/requires.txt +0 -0
- {searcharray-0.0.25 → searcharray-0.0.26}/searcharray.egg-info/top_level.txt +0 -0
- {searcharray-0.0.25 → searcharray-0.0.26}/setup.cfg +0 -0
- {searcharray-0.0.25 → searcharray-0.0.26}/test/test_extension_array.py +0 -0
- {searcharray-0.0.25 → searcharray-0.0.26}/test/test_msmarco.py +0 -0
- {searcharray-0.0.25 → searcharray-0.0.26}/test/test_phrase_matches.py +0 -0
- {searcharray-0.0.25 → searcharray-0.0.26}/test/test_search.py +0 -0
- {searcharray-0.0.25 → searcharray-0.0.26}/test/test_solr.py +0 -0
- {searcharray-0.0.25 → searcharray-0.0.26}/test/test_utils.py +0 -0
|
@@ -316,7 +316,7 @@ class PosnBitArray:
|
|
|
316
316
|
doc_ids = encoder.keys(term_posns)
|
|
317
317
|
change_indices = np.nonzero(np.diff(doc_ids))[0]
|
|
318
318
|
change_indices = np.concatenate((np.asarray([0]), change_indices + 1))
|
|
319
|
-
posns =
|
|
319
|
+
posns = term_posns & encoder.payload_lsb_mask
|
|
320
320
|
bit_counts = bit_count64(posns)
|
|
321
321
|
|
|
322
322
|
term_freqs = np.add.reduceat(bit_counts, change_indices)
|
|
@@ -36,7 +36,7 @@ setup(
|
|
|
36
36
|
# For a discussion on single-sourcing the version across setup.py and the
|
|
37
37
|
# project code, see
|
|
38
38
|
# https://packaging.python.org/guides/single-sourcing-package-version/
|
|
39
|
-
version="0.0.
|
|
39
|
+
version="0.0.26", # Required
|
|
40
40
|
# This is a one-line description or tagline of what your project does. This
|
|
41
41
|
# corresponds to the "Summary" metadata field:
|
|
42
42
|
# https://packaging.python.org/specifications/core-metadata/#summary
|
|
@@ -91,6 +91,19 @@ def test_slice_then_search(tmdb_data):
|
|
|
91
91
|
assert skywalker_bm25.shape[0] == 3
|
|
92
92
|
|
|
93
93
|
|
|
94
|
+
tmdb_term_matches = [
|
|
95
|
+
("Star", ['11', '330459', '76180']),
|
|
96
|
+
("Black", ['374430']),
|
|
97
|
+
]
|
|
98
|
+
|
|
99
|
+
|
|
100
|
+
@pytest.mark.parametrize("term,expected_matches", tmdb_term_matches)
|
|
101
|
+
def test_term_freqs(tmdb_data, term, expected_matches):
|
|
102
|
+
sliced = tmdb_data[tmdb_data['doc_id'].isin(expected_matches)]
|
|
103
|
+
term_freqs = sliced['title_tokens'].array.term_freq(term)
|
|
104
|
+
assert np.all(term_freqs == 1)
|
|
105
|
+
|
|
106
|
+
|
|
94
107
|
tmdb_phrase_matches = [
|
|
95
108
|
(["Star", "Wars"], ['11', '330459', '76180']),
|
|
96
109
|
(["Black", "Mirror:"], ['374430']),
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|