mirror of
https://github.com/VectifyAI/PageIndex.git
synced 2026-07-24 21:41:04 +02:00
9f01ba41ac
main's changes landed on the top-level pageindex/page_index.py and page_index_md.py, which are deprecation shims on dev (the pipeline now lives in pageindex/index/). Resolving the conflict by keeping the shims would silently drop main's work, so port it into index/ instead: - page_index.py: prompt-injection hardening (_SYSTEM_HARDENING, _secure_doc_text and the redact/wrap helpers) applied to every prompt builder, plus physical_index validation (_validate_physical_indices, _validate_chunk_physical_indices) wired into toc_index_extractor, process_no_toc and process_toc_no_page_numbers, and TOC-identity validation (reject reordered/modified/count-mismatched LLM output). Combined with dev's existing robustness edits in the same functions. - page_index_md.py: recognize whole-line **bold** as a level-1 heading, skip empty bold headings, use the stored node level. - tests: retarget the ported tests at pageindex.index.* instead of the shim (underscore helpers aren't re-exported by the shim's `import *`, and patching the shim wouldn't intercept the real pipeline calls). 311 passed, 2 skipped.
23 lines
569 B
Python
23 lines
569 B
Python
import unittest
|
|
|
|
from pageindex.index.page_index_md import extract_nodes_from_markdown
|
|
|
|
|
|
class ExtractNodesFromMarkdownTest(unittest.TestCase):
|
|
def test_skips_bold_heading_with_only_whitespace(self):
|
|
nodes, _ = extract_nodes_from_markdown("** **\n**Valid heading**")
|
|
|
|
self.assertEqual(
|
|
nodes,
|
|
[
|
|
{
|
|
"node_title": "Valid heading",
|
|
"line_num": 2,
|
|
"level": 1,
|
|
}
|
|
],
|
|
)
|
|
|
|
|
|
if __name__ == "__main__":
|
|
unittest.main()
|