Fixed bug where attempting to chunk only whitespace characters would raise ValueError: not enough values to unpack (expected 2, got 0) ([ScrapeGraphAI/Scrapegraph-ai#893](ScrapeGraphAI/Scrapegraph-ai#893))

Author: umarbutler

CHANGELOG.md

@@ -1,6 +1,10 @@
 ## Changelog 🔄
 All notable changes to `semchunk` will be documented here. This project adheres to [Keep a Changelog](https://keepachangelog.com/en/1.1.0/) and [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [3.0.4] - 2025-02-14
+### Fixed
+- Fixed bug where attempting to chunk only whitespace characters would raise `ValueError: not enough values to unpack (expected 2, got 0)` ([ScrapeGraphAI/Scrapegraph-ai#893](https://github.com/ScrapeGraphAI/Scrapegraph-ai/issues/893)).
+
 ## [3.0.3] - 2025-02-13
 ### Fixed
 - Fixed `isaacus/emubert` mistakenly being set to `isaacus-dev/emubert` in the README and tests.
@@ -121,6 +125,7 @@ All notable changes to `semchunk` will be documented here. This project adheres
 ### Added
 - Added the `chunk()` function, which splits text into semantically meaningful chunks of a specified size as determined by a provided token counter.
 
+[3.0.4]: https://github.com/isaacus-dev/semchunk/compare/v3.0.3...v3.0.4
 [3.0.3]: https://github.com/isaacus-dev/semchunk/compare/v3.0.2...v3.0.3
 [3.0.2]: https://github.com/isaacus-dev/semchunk/compare/v3.0.1...v3.0.2
 [3.0.1]: https://github.com/isaacus-dev/semchunk/compare/v3.0.0...v3.0.1

pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "semchunk"
-version = "3.0.3"
+version = "3.0.4"
 authors = [
     {name="Isaacus", email="[email protected]"},
     {name="Umar Butler", email="[email protected]"},

src/semchunk/semchunk.py

@@ -249,12 +249,14 @@ def chunk(
     # If this is the first call, remove any empty chunks as well as chunks comprised entirely of whitespace and then overlap the chunks if desired and finally return the chunks, optionally with their offsets.
     if is_first_call:
         # Remove empty chunks.
-        chunks, offsets = (
-            zip(*[(chunk, offset) for chunk, offset in zip(chunks, offsets) if chunk and not chunk.isspace()])
-            if chunks
-            else ([], [])
-        )  # NOTE `if chunks else ([], [])` ensures that we don't unpack an empty list if there's no chunks (i.e., if the provided text was empty).
-        chunks, offsets = list(chunks), list(offsets)
+        chunks_and_offsets = [(chunk, offset) for chunk, offset in zip(chunks, offsets) if chunk and not chunk.isspace()]
+        
+        if chunks_and_offsets:
+            chunks, offsets = zip(*chunks_and_offsets)
+            chunks, offsets = list(chunks), list(offsets)
+        
+        else:
+            chunks, offsets = [], []
 
         # Overlap chunks if desired.
         if overlap:

tests/test_semchunk.py

@@ -188,6 +188,9 @@ def test_semchunk() -> None:
 
     # Test chunking nothing to ensure no errors are raised.
     semchunk.chunk('', 512, lambda *args: 0)
+    
+    # Test chunking whitespace to ensure no errors are raised.
+    semchunk.chunk('\n\n', 512, lambda *args: 0)
 
 if __name__ == '__main__':
     test_semchunk()