formatting

allenai · Oct 2, 2024 · 259c4d9 · 259c4d9
1 parent 9858712
commit 259c4d9
Show file tree

Hide file tree

Showing 3 changed files with 6 additions and 5 deletions.
diff --git a/Cargo.toml b/Cargo.toml
@@ -1,6 +1,6 @@
 [package]
 name = "dolma"
-version = "1.0.15"
+version = "1.1.0"
 edition = "2021"
 license = "Apache-2.0"
 

diff --git a/pyproject.toml b/pyproject.toml
@@ -1,6 +1,6 @@
 [project]
 name = "dolma"
-version = "1.0.15"
+version = "1.1.0"
 description = "Data filters"
 license = { text = "Apache-2.0" }
 readme = "README.md"

diff --git a/python/dolma/warc/processor.py b/python/dolma/warc/processor.py
@@ -134,9 +134,10 @@ def process_single(
             extension = extension.replace(".gz", "").replace(".warc", "") + ".jsonl.gz"
             destination_path = join_path(prot, *base_dst[:-1], base_dst[-1] + extension)
 
-        with smart_open.open(source_path, "rb") as warc_file, smart_open.open(
-            destination_path, "wb"
-        ) as output_file:
+        with (
+            smart_open.open(source_path, "rb") as warc_file,
+            smart_open.open(destination_path, "wb") as output_file,
+        ):
             it = ArchiveIterator(warc_file, record_types=WarcRecordType.response | WarcRecordType.warcinfo)
             for record in it:
                 if record.record_type == WarcRecordType.warcinfo: