feat(chunks): aggiunge ChunkerConfig dataclass

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
2026-06-08 16:20:59 +02:00
parent be1347378b
commit bca01dc1c6
2 changed files with 53 additions and 0 deletions
+29
View File
@@ -0,0 +1,29 @@
from chunks.config import ChunkerConfig
def test_default_values():
c = ChunkerConfig()
assert c.max_chars == 1200
assert c.min_chars == 80
assert c.target_chars == 800
assert c.context_depth == 3
assert "indice" in c.skip_headings
assert c.skip_pre_heading is True
assert c.merge_short is True
assert "table" in c.atomic_types
assert "code" in c.atomic_types
def test_custom_values():
c = ChunkerConfig(max_chars=2000, min_chars=100, context_depth=2)
assert c.max_chars == 2000
assert c.min_chars == 100
assert c.context_depth == 2
def test_skip_headings_case_insensitive_check():
c = ChunkerConfig()
skip_lower = {h.lower() for h in c.skip_headings}
assert "indice" in skip_lower
assert "sommario" in skip_lower
assert "bibliografia" in skip_lower