audit-4: classifier understands Spanish negations (veto unchanged)
ci / lint-test-leaks (pull_request) Canceled after 0s
ci / lint-test-leaks (pull_request) Canceled after 0s
Merchants write in Spanish; negations like nunca, lamentablemente or no podemos must veto approval exactly like their English counterparts. Previously an all-Spanish rejection mail could fall through to OTHER, and a mixed mail with the approval word in English approved despite a Spanish negation. - negation list adds: nunca, jamas, tampoco, ningun/ninguna, nadie, nada, no podemos, no es posible, no aceptamos, rechaz*, descartad*, lamentablemente, no ha sido aprobad*, no procede - new Spanish REJECTION rule (rechaz*, solicitud denegada, no cumple los requisitos) and Spanish APPROVAL rule (aprob*, aceptad*, bienvenid*, encantados de trabajar) - veto rule unchanged: any negation anywhere -> needs_review - tests: 15 new (12 veto cases incl. 2 mixed-language, pure-Spanish approval still approves, Spanish rejection classifies rejection) Gate: ruff 0 · 96 unit + 1 PG integration · gitleaks clean.
This commit is contained in:
@@ -19,10 +19,17 @@ from cayceops.models import MailClassification
|
|||||||
|
|
||||||
_APPROVAL_WORDS = re.compile(r"\b(approv|accept|welcome)", re.I)
|
_APPROVAL_WORDS = re.compile(r"\b(approv|accept|welcome)", re.I)
|
||||||
|
|
||||||
# any of these tokens anywhere in the mail vetoes an `approval` result
|
# any of these tokens anywhere in the mail vetoes an `approval` result.
|
||||||
|
# English and Spanish (merchants write in both; mixed mails are common).
|
||||||
_NEGATIONS = re.compile(
|
_NEGATIONS = re.compile(
|
||||||
r"\b(not|no|never|cannot|can'?t|won'?t|hasn'?t|isn'?t|"
|
r"\b(not|no|never|cannot|can'?t|won'?t|hasn'?t|isn'?t|"
|
||||||
r"no\s+longer|unable|decline\w*|regret\w*|unfortunately)\b",
|
r"no\s+longer|unable|decline\w*|regret\w*|unfortunately|"
|
||||||
|
# spanish: standalone negation words
|
||||||
|
r"nunca|jam[aá]s|tampoco|ning[uú]n(?:a|o)?|nadie|nada|"
|
||||||
|
# spanish: multi-word negations and rejection stems
|
||||||
|
r"no\s+podemos|no\s+es\s+posible|no\s+acept(?:amos|ar[aá])|"
|
||||||
|
r"rechaz\w*|lamentablemente|descartad\w*|"
|
||||||
|
r"no\s+ha\s+sido\s+aprobad\w*|no\s+procede)\b",
|
||||||
re.I,
|
re.I,
|
||||||
)
|
)
|
||||||
|
|
||||||
@@ -34,11 +41,24 @@ _RULES: list[tuple[MailClassification, re.Pattern[str], float]] = [
|
|||||||
re.compile(r"\b(declin|reject|not able to|unable to|we regret|won.t be able)\w*", re.I), # noqa: E501
|
re.compile(r"\b(declin|reject|not able to|unable to|we regret|won.t be able)\w*", re.I), # noqa: E501
|
||||||
0.9,
|
0.9,
|
||||||
),
|
),
|
||||||
|
(
|
||||||
|
MailClassification.REJECTION,
|
||||||
|
# spanish rejections (strong stems, not just negation words)
|
||||||
|
re.compile(r"\b(rechaz\w*|no\s+vamos\s+a\s+pod(?:er|emos)|su\s+solicitud\s+ha\s+sido\s+denegada|no\s+cumple\s+los\s+requisitos)\b", re.I), # noqa: E501
|
||||||
|
0.9,
|
||||||
|
),
|
||||||
(
|
(
|
||||||
MailClassification.APPROVAL,
|
MailClassification.APPROVAL,
|
||||||
re.compile(r"\b(approv|accept|welcome to the|you.re (in|approved)|live|activated|glad to)\w*", re.I), # noqa: E501
|
re.compile(r"\b(approv|accept|welcome to the|you.re (in|approved)|live|activated|glad to)\w*", re.I), # noqa: E501
|
||||||
0.85,
|
0.85,
|
||||||
),
|
),
|
||||||
|
(
|
||||||
|
MailClassification.APPROVAL,
|
||||||
|
# spanish approvals (standalone positive stems; the veto still
|
||||||
|
# downgrades if ANY negation appears elsewhere in the mail)
|
||||||
|
re.compile(r"\b(aprob\w*|aceptad\w*|bienvenid\w*|ha\s+sido\s+aceptada|encantados?\s+de\s+(trabajar|colaborar))\b", re.I), # noqa: E501
|
||||||
|
0.85,
|
||||||
|
),
|
||||||
(
|
(
|
||||||
MailClassification.QUESTION,
|
MailClassification.QUESTION,
|
||||||
re.compile(r"\b(could you|can you|please (provide|clarify|confirm)|what (is|are)|how (do|does|can)|need more (info|details))\b", re.I), # noqa: E501
|
re.compile(r"\b(could you|can you|please (provide|clarify|confirm)|what (is|are)|how (do|does|can)|need more (info|details))\b", re.I), # noqa: E501
|
||||||
|
|||||||
@@ -0,0 +1,80 @@
|
|||||||
|
"""Spanish negation tests (round-3 point 4): merchants write in Spanish;
|
||||||
|
negations like 'nunca', 'lamentablemente' or 'no podemos' must veto
|
||||||
|
`approval` exactly like their English counterparts. Veto rule unchanged:
|
||||||
|
when in doubt -> needs_review."""
|
||||||
|
|
||||||
|
from __future__ import annotations
|
||||||
|
|
||||||
|
import pytest
|
||||||
|
|
||||||
|
from cayceops.components.maild import classify as clf
|
||||||
|
from cayceops.models import MailClassification
|
||||||
|
|
||||||
|
APPROVAL_ONLY = MailClassification.APPROVAL
|
||||||
|
|
||||||
|
|
||||||
|
def _never_approval(cfg_factory, text: str) -> None:
|
||||||
|
kind, _ = clf.classify(text, cfg_factory())
|
||||||
|
assert kind is not APPROVAL_ONLY, f"{text!r} classified as APPROVAL"
|
||||||
|
|
||||||
|
|
||||||
|
def test_english_baseline_still_works(cfg):
|
||||||
|
config = cfg()
|
||||||
|
kind, _ = clf.classify("Your application was approved, welcome to the program", config)
|
||||||
|
assert kind is APPROVAL_ONLY
|
||||||
|
|
||||||
|
|
||||||
|
@pytest.mark.parametrize(
|
||||||
|
"text",
|
||||||
|
[
|
||||||
|
# 1. rejection stem
|
||||||
|
"Lamentamos informarle que su solicitud fue rechazada",
|
||||||
|
# 2. nunca
|
||||||
|
"Nunca aceptamos negocios de criptomonedas",
|
||||||
|
# 3. jamás
|
||||||
|
"Jamás hemos trabajado con affiliates externos",
|
||||||
|
# 4. tampoco
|
||||||
|
"No podemos aceptar su sitio, tampoco podemos ofrecerle otro acuerdo",
|
||||||
|
# 5. ningún/ninguna
|
||||||
|
"En este momento no tenemos ningún hueco para nuevos partners",
|
||||||
|
# 6. no podemos (multi-word)
|
||||||
|
"Su propuesta es interesante pero no podemos proceder",
|
||||||
|
# 7. no es posible (multi-word)
|
||||||
|
"Gracias por escribir, pero no es posible colaborar este trimestre",
|
||||||
|
# 8. lamentablemente
|
||||||
|
"Lamentablemente su aplicación no ha sido aprobada",
|
||||||
|
# 9. no aceptamos
|
||||||
|
"Por política interna no aceptamos sitios de viajes",
|
||||||
|
# 10. mixed spanish/english: negation in spanish, approval word in english
|
||||||
|
"Thanks for reaching out! Lamentablemente we cannot approve your site",
|
||||||
|
# 11. mixed: approval in spanish, negation in english
|
||||||
|
"Apreciamos su interés, but we are not accepting new partners",
|
||||||
|
# 12. nadie / nada
|
||||||
|
"Aquí nadie decidiría eso, así que no hay nada que aprobar",
|
||||||
|
],
|
||||||
|
)
|
||||||
|
def test_spanish_and_mixed_negations_veto_approval(cfg, text):
|
||||||
|
_never_approval(cfg, text)
|
||||||
|
|
||||||
|
|
||||||
|
def test_spanish_pure_approval_still_approves(cfg):
|
||||||
|
"""A clean Spanish approval WITHOUT any negation must still classify
|
||||||
|
approval — the veto must not over-fire."""
|
||||||
|
config = cfg()
|
||||||
|
kind, confidence = clf.classify(
|
||||||
|
"Su solicitud fue aprobada. Bienvenido al programa, estamos encantados "
|
||||||
|
"de trabajar con ustedes.",
|
||||||
|
config,
|
||||||
|
)
|
||||||
|
assert kind is APPROVAL_ONLY
|
||||||
|
assert confidence >= 0.5
|
||||||
|
|
||||||
|
|
||||||
|
def test_spanish_rejection_classifies_rejection(cfg):
|
||||||
|
config = cfg()
|
||||||
|
kind, conf = clf.classify(
|
||||||
|
"Lamentamos informarle que su solicitud fue rechazada por el comité",
|
||||||
|
config,
|
||||||
|
)
|
||||||
|
assert kind is MailClassification.REJECTION
|
||||||
|
assert conf >= 0.9
|
||||||
Reference in New Issue
Block a user