52 lines
1.4 KiB
Python
52 lines
1.4 KiB
Python
|
from chunks.models import Block, Chunk, Diagnostics, ChunkingResult
|
||
|
|
|
||
|
|
|
||
|
|
def test_block_creation():
|
||
|
|
b = Block(
|
||
|
|
id="blk_0001",
|
||
|
|
kind="paragraph",
|
||
|
|
content="Testo di esempio.",
|
||
|
|
plain_text="Testo di esempio.",
|
||
|
|
atomic=False,
|
||
|
|
start_line=0,
|
||
|
|
end_line=1,
|
||
|
|
header_path=[{"level": 1, "text": "Titolo"}],
|
||
|
|
chars=17,
|
||
|
|
)
|
||
|
|
assert b.id == "blk_0001"
|
||
|
|
assert b.kind == "paragraph"
|
||
|
|
assert not b.atomic
|
||
|
|
assert b.chars == 17
|
||
|
|
|
||
|
|
|
||
|
|
def test_chunk_creation():
|
||
|
|
c = Chunk(
|
||
|
|
chunk_id="chk_000001",
|
||
|
|
chunk_index=1,
|
||
|
|
content_original="Testo.",
|
||
|
|
content_for_embedding="Titolo\n\nTesto.",
|
||
|
|
content_type="section_fragment",
|
||
|
|
chars=6,
|
||
|
|
start_line=0,
|
||
|
|
end_line=1,
|
||
|
|
header_path=[{"level": 1, "text": "Titolo"}],
|
||
|
|
block_ids=["blk_0001"],
|
||
|
|
flags={"has_code": False, "has_table": False, "has_math": False,
|
||
|
|
"is_overflow": False, "is_sparse": False},
|
||
|
|
neighbors={"previous_chunk_id": None, "next_chunk_id": None},
|
||
|
|
assets=[],
|
||
|
|
)
|
||
|
|
assert c.chunk_id == "chk_000001"
|
||
|
|
assert c.assets == []
|
||
|
|
|
||
|
|
|
||
|
|
def test_diagnostics_empty():
|
||
|
|
d = Diagnostics(errors=[], warnings=[], metrics={})
|
||
|
|
assert d.errors == []
|
||
|
|
|
||
|
|
|
||
|
|
def test_chunking_result():
|
||
|
|
r = ChunkingResult(stem="doc", source_path="sources/doc.md", chunks=[], diagnostics=Diagnostics([], [], {}))
|
||
|
|
assert r.stem == "doc"
|
||
|
|
assert r.chunks == []
|