read.markets/tests/test_news_tagging.py

"""Tests for the deterministic half of news_tagging: vocabulary filtering
and JSON-response parsing. The LLM call itself isn't exercised."""
from __future__ import annotations

import pytest

from app.services.news_tagging import (
    MAX_TAGS_PER_HEADLINE,
    TAG_LABELS,
    TAG_VOCABULARY,
    _parse_batch_response,
    _validate_tags,
)


# ---------------------------------------------------------------------------
# Vocabulary integrity
# ---------------------------------------------------------------------------


def test_every_vocab_tag_has_a_label():
    """Display labels must cover every tag — missing keys would render
    the raw machine-name in the UI."""
    for t in TAG_VOCABULARY:
        assert t in TAG_LABELS, f"missing label for {t}"


def test_other_is_the_fallback_tag():
    assert "other" in TAG_VOCABULARY


# ---------------------------------------------------------------------------
# _validate_tags
# ---------------------------------------------------------------------------


def test_validate_drops_unknown_tags():
    out = _validate_tags(["markets", "wibble", "tech"])
    assert out == ["markets", "tech"]


def test_validate_normalises_spaces_to_hyphens():
    """Common drift: model returns 'monetary policy' instead of
    'monetary-policy'. We normalise."""
    out = _validate_tags(["monetary policy"])
    assert out == ["monetary-policy"]


def test_validate_normalises_case():
    out = _validate_tags(["MARKETS", "Geopolitics"])
    assert out == ["markets", "geopolitics"]


def test_validate_caps_at_max_tags():
    out = _validate_tags(["markets", "tech", "china", "economy", "energy"])
    assert len(out) == MAX_TAGS_PER_HEADLINE


def test_validate_dedupes():
    out = _validate_tags(["markets", "markets", "tech"])
    assert out == ["markets", "tech"]


def test_validate_rejects_non_list():
    assert _validate_tags(None) == []
    assert _validate_tags("markets") == []
    assert _validate_tags({"tag": "markets"}) == []


def test_validate_skips_non_string_entries():
    out = _validate_tags(["markets", 42, None, "tech"])
    assert out == ["markets", "tech"]


# ---------------------------------------------------------------------------
# _parse_batch_response
# ---------------------------------------------------------------------------


def test_parse_basic_json_array():
    raw = '[{"id": 1, "tags": ["markets", "tech"]}, {"id": 2, "tags": ["china"]}]'
    out = _parse_batch_response(raw, {1, 2})
    assert out == {1: ["markets", "tech"], 2: ["china"]}


def test_parse_strips_leading_prose():
    """Models occasionally prepend 'Here is the output:' before the JSON."""
    raw = 'Sure! Here are the tags:\n[{"id": 1, "tags": ["markets"]}]'
    out = _parse_batch_response(raw, {1})
    assert out == {1: ["markets"]}


def test_parse_strips_markdown_fences():
    raw = "```json\n[{\"id\": 1, \"tags\": [\"tech\"]}]\n```"
    out = _parse_batch_response(raw, {1})
    assert out == {1: ["tech"]}


def test_parse_drops_unexpected_ids():
    raw = '[{"id": 99, "tags": ["markets"]}, {"id": 1, "tags": ["tech"]}]'
    out = _parse_batch_response(raw, {1, 2})
    assert out == {1: ["tech"]}


def test_parse_empty_tags_falls_back_to_other():
    """An item whose tags list ends up empty after validation gets
    tagged 'other' so the row is marked tagged, not left NULL."""
    raw = '[{"id": 1, "tags": ["nonsense"]}]'
    out = _parse_batch_response(raw, {1})
    assert out == {1: ["other"]}


def test_parse_unparseable_returns_empty():
    """Garbage in → empty out. The caller leaves those rows untagged
    so they get retried on the next run."""
    assert _parse_batch_response("nope, no JSON here", {1}) == {}
    assert _parse_batch_response("[invalid json", {1}) == {}


def test_parse_ignores_non_dict_items():
    raw = '[{"id": 1, "tags": ["markets"]}, "lol", null, {"id": 2, "tags": ["tech"]}]'
    out = _parse_batch_response(raw, {1, 2})
    assert out == {1: ["markets"], 2: ["tech"]}


def test_parse_handles_string_id_coercion():
    """Some models render the id as a string. We coerce."""
    raw = '[{"id": "1", "tags": ["markets"]}]'
    out = _parse_batch_response(raw, {1})
    assert out == {1: ["markets"]}