[pre-commit.ci] pre-commit autoupdate (#381)

* [pre-commit.ci] pre-commit autoupdate

updates:
- [github.com/psf/black: 21.12b0 → 22.1.0](psf/black@21.12b0...22.1.0)
- [github.com/Lucas-C/pre-commit-hooks: v1.1.10 → v1.1.11](Lucas-C/pre-commit-hooks@v1.1.10...v1.1.11)

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>

Author: pre-commit-ci[bot]

.pre-commit-config.yaml

@@ -47,14 +47,14 @@ repos:
 
 # Black, the code formatter, natively supports pre-commit
 - repo: https://github.com/psf/black
-  rev: 21.12b0 # Keep in sync with blacken-docs
+  rev: 22.1.0 # Keep in sync with blacken-docs
   hooks:
   - id: black
     exclude: ^pii_processing/
 
 # Changes tabs to spaces
 - repo: https://github.com/Lucas-C/pre-commit-hooks
-  rev: v1.1.10
+  rev: v1.1.11
   hooks:
   - id: remove-tabs
     exclude: ^(pii_processing|.*Makefile)

kenlm_training/cc_net/jsonql.py

@@ -1019,7 +1019,7 @@ def open_write(
 
 
 def parse_size(size):
-    unit_map = {"B": 1, "K": 1024, "M": 1024 ** 2, "G": 1024 ** 3}
+    unit_map = {"B": 1, "K": 1024, "M": 1024**2, "G": 1024**3}
     unit = size[-1].upper()
     assert (
         unit in unit_map
@@ -1102,7 +1102,7 @@ def request_get_content(url: str, n_retry: int = 3) -> bytes:
             warnings.warn(
                 f"Swallowed error {e} while downloading {url} ({i} out of {n_retry})"
             )
-            time.sleep(10 * 2 ** i)
+            time.sleep(10 * 2**i)
     dl_time = time.time() - t0
     dl_speed = len(r.content) / dl_time / 1024
     logging.info(
@@ -1148,7 +1148,7 @@ def sharded_file(file_pattern: Path, mode: str, max_size: str = "4G") -> MultiFi
     assert 0 < n < 8
     assert "?" * n in name, f"The '?' need to be adjacents in {file_pattern}"
     assert "r" not in mode
-    files = (folder / name.replace("?" * n, f"%0{n}d" % i) for i in range(10 ** n))
+    files = (folder / name.replace("?" * n, f"%0{n}d" % i) for i in range(10**n))
 
     return MultiFile(files, mode, max_size)
 

kenlm_training/cc_net/regroup.py

@@ -105,7 +105,7 @@ def fast_reshard(
 
 
 def determine_groups(
-    inputs: List[Path], target_size: int = 4 * 1024 ** 3
+    inputs: List[Path], target_size: int = 4 * 1024**3
 ) -> List[List[Path]]:
     if len(inputs) == 0:
         return []

kenlm_training/cc_net/tools/expand_corpus.py

@@ -26,7 +26,7 @@
 
 KENLM = Path("./bin/lmplz")
 KENLM_BUILD = Path("./bin/build_binary")
-VOCAB_SIZE = 2 ** 16 - 10
+VOCAB_SIZE = 2**16 - 10
 PROCESSES = 16
 
 

kenlm_training/tests/test_flat_hash_set.py

@@ -69,7 +69,7 @@ def check_reload(h, dump, load, tmp_path):
 @pytest.mark.parametrize("hash_set_cls", [FlatHashSet, NaiveHashSet])
 def test_loading(tmp_path, hash_set_cls):
     h = hash_set_cls()
-    x = np.random.randint(0, 2 ** 32, (100,), dtype=h.dtype)
+    x = np.random.randint(0, 2**32, (100,), dtype=h.dtype)
     h.add(x)
 
     check_reload(h, hash_set_cls.dump, hash_set_cls.load, tmp_path)