digital-brain/backend/orchestrator/memory_graph_terms.py at main · githubdoramon/digital-brain · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
"""Shared lexical hints for personal memory-graph routing and retrieval."""

import re

PERSONAL_DOCUMENT_TERMS = frozenset(
    {
        "doc",
        "docs",
        "document",
        "documents",
        "file",
        "files",
        "paperwork",
        "record",
        "records",
        "report",
        "reports",
        "result",
        "results",
        "prescription",
        "prescriptions",
        "rx",
        "spec",
        "specs",
        "specification",
        "specifications",
        "lab",
        "labs",
        "medical",
        "glasses",
        "eyeglasses",
        "lens",
        "lenses",
        "id",
        "identity",
    }
)


def extract_normalized_tokens(text: str) -> set[str]:
    return set(re.findall(r"[a-z0-9]+", (text or "").lower()))


def contains_personal_document_term(text: str) -> bool:
    return any(term in extract_normalized_tokens(text) for term in PERSONAL_DOCUMENT_TERMS)