Skip to content

fix(cli): preserve spaces and newlines in treesitter chunking. #120

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
May 6, 2025
Merged
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
13 changes: 11 additions & 2 deletions src/vectorcode/chunking.py
Original file line number Diff line number Diff line change
@@ -150,7 +150,7 @@ def __chunk_node(
f"Traversing at node {node.text.decode()} at position {node.byte_range}"
)
current_chunk: str = ""

prev_node = None
current_start = None

for child in node.children:
@@ -184,10 +184,19 @@ def __chunk_node(
current_start = Point(
row=child.start_point.row + 1, column=child.start_point.column
)
prev_node = child

elif len(current_chunk) + child_length <= self.config.chunk_size:
elif len(current_chunk) + child_length + 1 <= self.config.chunk_size:
# Add to current chunk
if prev_node:
if prev_node.end_point.row != child.start_point.row:
current_chunk += "\n"
else:
current_chunk += " " * (
child.start_point.column - prev_node.end_point.column
)
current_chunk += child_bytes.decode()
prev_node = child

else:
# Yield current chunk and start new one
13 changes: 8 additions & 5 deletions tests/test_chunking.py
Original file line number Diff line number Diff line change
@@ -250,7 +250,7 @@ def bar():


def test_treesitter_chunker_filter_wildcard():
chunker = TreeSitterChunker(Config(chunk_size=30, chunk_filters={"*": [".*foo.*"]}))
chunker = TreeSitterChunker(Config(chunk_size=35, chunk_filters={"*": [".*foo.*"]}))

test_content = r"""
def foo():
@@ -283,12 +283,12 @@ def bar():
test_file = tmp_file.name

chunks = list(str(i) for i in chunker.chunk(test_file))
assert chunks == ['functionbar()return "bar"end']
assert chunks == ['function bar()\n return "bar"\nend']
os.remove(test_file)


def test_treesitter_chunker_lua():
chunker = TreeSitterChunker(Config(chunk_size=30))
chunker = TreeSitterChunker(Config(chunk_size=35))
test_content = r"""
function foo()
return "foo"
@@ -304,7 +304,10 @@ def test_treesitter_chunker_lua():
test_file = tmp_file.name

chunks = list(str(i) for i in chunker.chunk(test_file))
assert chunks == ['functionfoo()return "foo"end', 'functionbar()return "bar"end']
assert chunks == [
'function foo()\n return "foo"\nend',
'function bar()\n return "bar"\nend',
]

os.remove(test_file)

@@ -403,7 +406,7 @@ def bar():
assert len(chunks) >= 2 # Should have at least 2 chunks

# First chunk should contain the function definition start
assert "deffoo():" in chunks[0].text
assert "def foo():" in chunks[0].text
assert chunks[0].start == Point(1, 0)

# Last chunk should contain the final return statement