breakpilot-core/control-pipeline/tests/test_d3_metadata.py

"""Tests for D3: Structural metadata flow (section priority, page in citation)."""

import json
from typing import Optional

from services.rag_client import RAGSearchResult


def _make_chunk(
    article: str = "",
    paragraph: str = "",
    page: Optional[int] = None,
) -> RAGSearchResult:
    return RAGSearchResult(
        text="Test chunk text",
        regulation_code="DSGVO",
        regulation_name="Datenschutz-Grundverordnung",
        regulation_short="DSGVO",
        category="data_protection",
        article=article,
        paragraph=paragraph,
        source_url="https://example.com",
        score=0.95,
        collection="bp_compliance_de",
        page=page,
    )


class TestRAGSearchResultPage:
    """RAGSearchResult now carries a page field."""

    def test_page_default_none(self):
        chunk = _make_chunk()
        assert chunk.page is None

    def test_page_set(self):
        chunk = _make_chunk(page=42)
        assert chunk.page == 42

    def test_page_zero(self):
        chunk = _make_chunk(page=0)
        assert chunk.page == 0


class TestQdrantPayloadPriority:
    """section (D2) should take priority over article (legacy)."""

    def test_section_preferred_over_article(self):
        payload = {"section": "§ 312k", "article": "Art. 312", "section_title": "Kuendigungsbutton"}
        article = payload.get("section", "") or payload.get("article", "") or payload.get("section_title", "")
        assert article == "§ 312k"

    def test_article_fallback_when_no_section(self):
        payload = {"section": "", "article": "Art. 35", "section_title": ""}
        article = payload.get("section", "") or payload.get("article", "") or payload.get("section_title", "")
        assert article == "Art. 35"

    def test_section_title_last_resort(self):
        payload = {"section": "", "article": "", "section_title": "Informationspflichten"}
        article = payload.get("section", "") or payload.get("article", "") or payload.get("section_title", "")
        assert article == "Informationspflichten"

    def test_all_empty(self):
        payload = {"section": "", "article": "", "section_title": ""}
        article = payload.get("section", "") or payload.get("article", "") or payload.get("section_title", "")
        assert article == ""

    def test_page_from_payload(self):
        payload = {"page": 847}
        assert payload.get("page") == 847

    def test_page_none_from_payload(self):
        payload = {}
        assert payload.get("page") is None


class TestSourceCitationPage:
    """source_citation dict should include page when available."""

    def _build_citation(self, chunk: RAGSearchResult) -> dict:
        """Mirrors the citation-building logic from control_generator.py."""
        return {
            "source": chunk.regulation_name,
            "article": chunk.article,
            "paragraph": chunk.paragraph,
            "page": chunk.page,
            "license": "free_use",
            "source_type": "law",
            "url": chunk.source_url or "",
        }

    def test_citation_with_page(self):
        chunk = _make_chunk(article="§ 312k", paragraph="Abs. 1", page=847)
        citation = self._build_citation(chunk)
        assert citation["page"] == 847

    def test_citation_without_page(self):
        chunk = _make_chunk(article="§ 312k", paragraph="Abs. 1")
        citation = self._build_citation(chunk)
        assert citation["page"] is None

    def test_citation_serializable(self):
        chunk = _make_chunk(article="Art. 35", page=12)
        citation = self._build_citation(chunk)
        serialized = json.dumps(citation)
        restored = json.loads(serialized)
        assert restored["page"] == 12


class TestFormatCitation:
    """_format_citation should include page number."""

    def _format_citation(self, citation) -> str:
        """Mirrors _format_citation from decomposition_pass.py."""
        if not citation:
            return ""
        if isinstance(citation, str):
            try:
                c = json.loads(citation)
                if isinstance(c, dict):
                    parts = []
                    if c.get("source"):
                        parts.append(c["source"])
                    if c.get("article"):
                        parts.append(c["article"])
                    if c.get("paragraph"):
                        parts.append(c["paragraph"])
                    if c.get("page") is not None:
                        parts.append(f"S. {c['page']}")
                    return " ".join(parts) if parts else citation
            except (json.JSONDecodeError, TypeError):
                return citation
        return str(citation)

    def test_format_with_page(self):
        citation = json.dumps({
            "source": "DSGVO",
            "article": "Art. 35",
            "paragraph": "Abs. 1",
            "page": 42,
        })
        result = self._format_citation(citation)
        assert result == "DSGVO Art. 35 Abs. 1 S. 42"

    def test_format_without_page(self):
        citation = json.dumps({
            "source": "BGB",
            "article": "§ 312k",
            "paragraph": "",
        })
        result = self._format_citation(citation)
        assert result == "BGB § 312k"

    def test_format_page_zero(self):
        citation = json.dumps({
            "source": "BGB",
            "article": "§ 1",
            "paragraph": "",
            "page": 0,
        })
        result = self._format_citation(citation)
        assert result == "BGB § 1 S. 0"

    def test_format_empty_citation(self):
        assert self._format_citation("") == ""
        assert self._format_citation(None) == ""