Skip to content
Open
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
3 changes: 2 additions & 1 deletion pageindex/page_index_classic.py
Original file line number Diff line number Diff line change
Expand Up @@ -528,7 +528,8 @@ def page_list_to_group_text(page_contents, token_lengths, max_tokens=20000, over
average_tokens_per_part = math.ceil(((num_tokens / expected_parts_num) + max_tokens) / 2)

for i, (page_content, page_tokens) in enumerate(zip(page_contents, token_lengths)):
if current_token_count + page_tokens > average_tokens_per_part:
# without the guard, an oversized first page flushes an empty chunk
if current_subset and current_token_count + page_tokens > average_tokens_per_part:

subsets.append(''.join(current_subset))
# Start new subset from overlap if specified
Expand Down
35 changes: 35 additions & 0 deletions tests/test_page_index.py
Original file line number Diff line number Diff line change
Expand Up @@ -3,6 +3,7 @@

from pageindex.page_index_classic import (
_secure_doc_text,
page_list_to_group_text,
process_no_toc,
process_toc_no_page_numbers,
)
Expand Down Expand Up @@ -65,5 +66,39 @@ def test_secure_doc_text_neutralizes_document_delimiters(self):
self.assertIn("<physical_index_1>", wrapped)


class PageListToGroupTextTest(unittest.TestCase):
PAGES = ["PAGE-A", "PAGE-B", "PAGE-C"]

def test_oversized_first_page_does_not_emit_an_empty_chunk(self):
chunks = page_list_to_group_text(
self.PAGES, [60000, 500, 500], max_tokens=20000
)

self.assertNotIn("", chunks)

def test_every_page_survives_an_oversized_first_page(self):
chunks = page_list_to_group_text(
self.PAGES, [60000, 500, 500], max_tokens=20000
)

joined = "".join(chunks)
for page in self.PAGES:
self.assertIn(page, joined)

def test_oversized_middle_page_is_unaffected(self):
chunks = page_list_to_group_text(
self.PAGES, [100, 60000, 100], max_tokens=20000
)

self.assertNotIn("", chunks)

def test_document_under_the_limit_stays_one_chunk(self):
chunks = page_list_to_group_text(
self.PAGES, [100, 100, 100], max_tokens=20000
)

self.assertEqual(chunks, ["PAGE-APAGE-BPAGE-C"])


if __name__ == "__main__":
unittest.main()