File size: 3,516 Bytes
ae97c5d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
from __future__ import annotations
import re
from typing import Any

ROLE_NOTE = " Select the value by its printed label and requested role. Do not infer the role from the spelling or prefix of an identifier. A similar-looking value under another label is not the requested value. Return null if that role is absent."
_GENERIC_NAMES = {"reference", "value"}
_PURCHASE_ORDER = re.compile("\\bpurchase[\\s-]+order\\s+reference\\b", re.IGNORECASE)
_LITERAL = re.compile(
    "\\b(?:exact|printed|verbatim|copy|extract|read)\\b", re.IGNORECASE
)
_EXCLUDED = re.compile(
    "\\b(?:not|exclude|excluding|ignore|rather than)\\b[^.;:\\n]*$", re.IGNORECASE
)
_OTHER_ROLE = re.compile(
    "\\b(?:invoice|receipt|payment|tracking|sales[\\s-]+order|account)\\s+(?:reference|number|identifier|id|code)\\b",
    re.IGNORECASE,
)
_TRANSFORM = re.compile(
    "\\b(?:compare|combine|join|concatenate|compute|calculate|sum|count|hash|mask|normalize|convert|format|summarize|(?:first|last)\\s+\\d+)\\b",
    re.IGNORECASE,
)
_STATE_TEXT = re.compile(
    "\\b(?:state|accompanying)\\s+(?:state\\s+)?text\\b", re.IGNORECASE
)
_QUOTED_LITERAL_TARGET = re.compile(
    "\\b(?:copy|extract|read|return)\\s+(?:the\\s+)?(?:(?:exact|printed|literal|verbatim)\\s+)*(?:phrase|words?|sentence|string)\\s*:?\\s*(?:\"([^\"\\n]+)\"|'([^'\\n]+)'|“([^”\\n]+)”|‘([^’\\n]+)’|`([^`\\n]+)`)",
    re.IGNORECASE,
)
_LITERAL_COMMAND_NEGATION = re.compile(
    "\\b(?:never|don['’]t)\\b[^.;:\\n]*$", re.IGNORECASE
)


def _positive(pattern: re.Pattern[str], instructions: str) -> bool:
    return any(
        (
            not _EXCLUDED.search(instructions[: match.start()])
            for match in pattern.finditer(instructions)
        )
    )


def _literal_target(instructions: str) -> bool:
    for match in _QUOTED_LITERAL_TARGET.finditer(instructions):
        prefix = instructions[: match.start()]
        if not (_EXCLUDED.search(prefix) or _LITERAL_COMMAND_NEGATION.search(prefix)):
            if any(
                (
                    _PURCHASE_ORDER.search(text)
                    for text in match.groups()
                    if text is not None
                )
            ):
                return True
    return False


def prepare_fields(
    fields: dict[str, dict[str, Any]], *, has_media: bool
) -> tuple[dict[str, dict[str, Any]], dict[str, str]]:
    if not has_media:
        return (fields, {})
    (changed, labels) = ({}, {})
    for name, spec in fields.items():
        if (
            not isinstance(name, str)
            or name.casefold() not in _GENERIC_NAMES
            or (not isinstance(spec, dict))
            or (spec.get("type") != "text")
            or spec.get("knowledge")
            or (spec.get("nullable", True) is False)
            or ("enum" in spec)
        ):
            continue
        instructions = spec.get("instructions", "")
        if (
            not isinstance(instructions, str)
            or not _LITERAL.search(instructions)
            or _TRANSFORM.search(instructions)
            or _STATE_TEXT.search(instructions)
            or _literal_target(instructions)
            or (not _positive(_PURCHASE_ORDER, instructions))
            or _positive(_OTHER_ROLE, instructions)
        ):
            continue
        if not instructions.endswith(ROLE_NOTE):
            changed[name] = {**spec, "instructions": instructions + ROLE_NOTE}
        labels[name] = "purchase_order_reference"
    return ({**fields, **changed} if changed else fields, labels)