Linting

classify-split-extract-workflow/classify-job/utils.py

@@ -12,6 +12,12 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
+"""
+Utility functions  for obtaining authentication tokens,
+sending callback requests, splitting PDF files into multiple parts,
+getting the current UTC timestamp, and deleting directories.
+"""
+
 import glob
 import io
 import shutil
@@ -73,11 +79,13 @@ def split_pages(file_pattern: str, bucket_name: str, output_dir: str) -> None:
         num_pages = len(reader.pages)
         num_shards = (num_pages + 14) // 15
 
-        pdf_writers = [PyPDF2.PdfWriter() for _ in range(num_shards)]
-        for page_index, page in enumerate(reader.pages):
-            pdf_writers[page_index // 15].add_page(page)
+        for shard_index in range(num_shards):
+            pdf_writer = PyPDF2.PdfWriter()
+            for page_index in range(15):
+                page_number = shard_index * 15 + page_index
+                if page_number < num_pages:
+                    pdf_writer.add_page(reader.pages[page_number])
 
-        for shard_index, pdf_writer in enumerate(pdf_writers):
             output_filename = f"{output_dir}/{file_path[3:-4]} - " \
                               f"part {shard_index + 1} of {num_shards}.pdf"
             blob = bucket.blob(output_filename)