feat(chunks): rilevamento universale has_math/has_table + dollarmath plugin
- parser.py: integra dollarmath_plugin (graceful fallback) — blocchi $$…$$ → token math_block atomico
- segmenter.py: gestisce math_block → Block(kind=math, atomic=True, plain_text=[formula])
- packer.py: has_table rileva anche <table> in blocchi html; has_math rileva $$ e \begin{ nel contenuto
- +11 test (parser×3, segmenter×3, packer×5) — totale 65 test
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
@@ -191,6 +191,25 @@ def segment(tokens: list[Token], lines: list[str], config: ChunkerConfig) -> lis
|
||||
i += 1
|
||||
continue
|
||||
|
||||
# ── Math block (dollarmath plugin) ───────────────────────────────────
|
||||
if tok.type == "math_block":
|
||||
start = tok.map[0] if tok.map else 0
|
||||
end = tok.map[1] if tok.map else start + 1
|
||||
content = _lines_content(lines, start, end)
|
||||
blocks.append(Block(
|
||||
id=_make_id(),
|
||||
kind="math",
|
||||
content=content,
|
||||
plain_text="[formula]",
|
||||
atomic=True,
|
||||
start_line=start,
|
||||
end_line=end,
|
||||
header_path=header_path,
|
||||
chars=len(content),
|
||||
))
|
||||
i += 1
|
||||
continue
|
||||
|
||||
# ── HTML block ────────────────────────────────────────────────────────
|
||||
if tok.type == "html_block":
|
||||
start = tok.map[0] if tok.map else 0
|
||||
|
||||
Reference in New Issue
Block a user