bikoret/korban_processor/test/test_korban.py

"""
Full pipeline tests — process_korban() end-to-end.

BUILD_KORBAN.md Build Verification:
1. Shechitah test — strips preamble/markdown/hedging/self-reference, preserves Torah
2. Zerikah test — extracts Torah references, Hebrew roots, separates vital from discardable
3. Haktarah test — Prolog propositions syntactically valid and semantically grounded
4. Statelessness test — no state leaks between sequential offerings
5. Empty offering test — graceful rejection when no vital content exists

Architecture §3.5: process_korban() is the gate between the world's raw output
and the system's inner processing.

Kiyyor principle (structure_not_content.md):
The laver. Resets before every offering. Daily manna — gathered fresh.
"""

import re
import pytest

from korban_processor.korban import (
    Korban,
    ProcessedKorban,
    OfferingType,
    Provenance,
    process_korban,
)
from test.fixtures import (
    CLAUDE_HEAVY_PREAMBLE_RESPONSE,
    CLAUDE_EMPTY_OFFERING,
    CLEAN_TORAH_RESPONSE,
    LATIN_TORAH_RESPONSE,
)

_PROLOG_TERM_PATTERN = re.compile(r"^\w+\(.*\)$")


def is_valid_prolog_term(s: str) -> bool:
    return bool(_PROLOG_TERM_PATTERN.match(s.strip()))


class TestBuildVerification1_Shechitah:
    """
    BUILD_KORBAN §1: Feed a Claude API response with heavy preamble, markdown,
    hedging, and self-reference. Verify output contains none of these and
    preserves all Torah references and Hebrew analysis.
    """

    def setup_method(self):
        self.result = process_korban(
            content=CLAUDE_HEAVY_PREAMBLE_RESPONSE,
            source=Provenance.CLAUDE,
            query="analyze bereishit",
            offering_type=OfferingType.OLAH,
        )

    def test_returns_processed_korban(self):
        assert isinstance(self.result, ProcessedKorban)

    def test_strips_preamble(self):
        assert "Great question" not in self.result.vital_content
        assert "I'd be happy" not in self.result.vital_content

    def test_strips_self_reference(self):
        assert "As an AI" not in self.result.vital_content
        assert "language model" not in self.result.vital_content

    def test_strips_hedging(self):
        assert "worth noting" not in self.result.vital_content

    def test_strips_closing(self):
        assert "I hope this helps" not in self.result.vital_content
        assert "Let me know" not in self.result.vital_content

    def test_preserves_bereishit_hebrew(self):
        assert "בְּרֵאשִׁית" in self.result.vital_content

    def test_preserves_root_notation(self):
        assert "ר-א-ש" in self.result.vital_content

    def test_preserves_rashi_reference(self):
        assert "Rashi" in self.result.vital_content

    def test_preserves_torah_reference(self):
        assert "Genesis 1:1" in self.result.vital_content or "Bereishit 1:1" in self.result.vital_content

    def test_provenance_recorded(self):
        assert self.result.provenance == Provenance.CLAUDE

    def test_offering_type_recorded(self):
        assert self.result.offering_type == OfferingType.OLAH


class TestBuildVerification2_Zerikah:
    """
    BUILD_KORBAN §2: Feed a stripped response. Verify it extracts Torah references
    accurately, identifies Hebrew roots, and separates vital content from discardable.
    """

    def setup_method(self):
        self.result = process_korban(
            content=CLEAN_TORAH_RESPONSE,
            source=Provenance.CLAUDE,
            query="analyze bereishit",
            offering_type=OfferingType.OLAH,
        )

    def test_extracts_torah_references(self):
        assert "Genesis 1:1" in self.result.vital_content or "Bereishit" in self.result.vital_content

    def test_extracts_hebrew_roots(self):
        assert "ר-א-ש" in self.result.vital_content or "ראש" in self.result.vital_content

    def test_separates_vital_from_discardable(self):
        # The result has vital content — it was not entirely discarded
        assert self.result.vital_content.strip() != ""

    def test_discarded_is_list(self):
        assert isinstance(self.result.discarded, list)

    def test_multiple_book_references(self):
        result = process_korban(
            content=LATIN_TORAH_RESPONSE,
            source=Provenance.CLAUDE,
            query="list references",
            offering_type=OfferingType.OLAH,
        )
        # All five books appear
        assert "Genesis 1:1" in result.vital_content
        assert "Exodus 3:14" in result.vital_content


class TestBuildVerification3_Haktarah:
    """
    BUILD_KORBAN §3: Feed extracted vital content. Verify Prolog propositions are
    syntactically valid and semantically grounded.
    """

    def setup_method(self):
        self.result = process_korban(
            content=LATIN_TORAH_RESPONSE,
            source=Provenance.CLAUDE,
            query="list references",
            offering_type=OfferingType.OLAH,
        )

    def test_produces_propositions(self):
        assert len(self.result.propositions) > 0

    def test_all_propositions_syntactically_valid(self):
        for prop in self.result.propositions:
            assert is_valid_prolog_term(prop), \
                f"Invalid Prolog proposition: {prop!r}"

    def test_propositions_include_verse_facts(self):
        verse_facts = [p for p in self.result.propositions if p.startswith("verse(")]
        assert len(verse_facts) >= 3, \
            f"Expected ≥3 verse facts, got {len(verse_facts)}: {verse_facts}"

    def test_bereishit_verse_fact_present(self):
        result = process_korban(
            content=CLEAN_TORAH_RESPONSE,
            source=Provenance.CLAUDE,
            query="analyze",
            offering_type=OfferingType.OLAH,
        )
        verse_facts = [p for p in result.propositions if p.startswith("verse(")]
        assert any("bereishit" in p for p in verse_facts), \
            f"No bereishit verse fact in: {verse_facts}"


class TestBuildVerification4_Statelessness:
    """
    BUILD_KORBAN §4: Process two offerings sequentially. Verify no state leaked
    between them. The second offering must be processed identically whether or not
    the first was processed.
    """

    def test_two_offerings_no_state_leak(self):
        # Process first offering
        result1 = process_korban(
            content=CLAUDE_HEAVY_PREAMBLE_RESPONSE,
            source=Provenance.CLAUDE,
            query="query 1",
            offering_type=OfferingType.OLAH,
        )

        # Process second offering
        result2 = process_korban(
            content=LATIN_TORAH_RESPONSE,
            source=Provenance.MISTRAL,
            query="query 2",
            offering_type=OfferingType.MINCHAH,
        )

        # result1 should not contain anything from result2
        assert "Mistral" not in result1.vital_content
        # result2 should not contain anything from result1 (Hebrew preamble content)
        assert "I'd be happy" not in result2.vital_content

    def test_second_offering_identical_with_or_without_first(self):
        """
        Process offering A twice — once with offering B in between,
        once alone. Results must be identical.
        """
        # First: process A alone
        result_a1 = process_korban(
            content=LATIN_TORAH_RESPONSE,
            source=Provenance.CLAUDE,
            query="query A",
            offering_type=OfferingType.OLAH,
        )

        # Process unrelated offering B
        process_korban(
            content=CLAUDE_HEAVY_PREAMBLE_RESPONSE,
            source=Provenance.GPT,
            query="query B",
            offering_type=OfferingType.CHATAT,
        )

        # Process A again — must be identical to first time
        result_a2 = process_korban(
            content=LATIN_TORAH_RESPONSE,
            source=Provenance.CLAUDE,
            query="query A",
            offering_type=OfferingType.OLAH,
        )

        assert result_a1.vital_content == result_a2.vital_content
        assert result_a1.propositions == result_a2.propositions
        assert result_a1.discarded == result_a2.discarded

    def test_provenance_not_shared_between_offerings(self):
        result1 = process_korban(
            content=CLEAN_TORAH_RESPONSE,
            source=Provenance.CLAUDE,
            query="q",
        )
        result2 = process_korban(
            content=CLEAN_TORAH_RESPONSE,
            source=Provenance.MISTRAL,
            query="q",
        )
        # Same content, different provenance — each result has correct provenance
        assert result1.provenance == Provenance.CLAUDE
        assert result2.provenance == Provenance.MISTRAL


class TestBuildVerification5_EmptyOffering:
    """
    BUILD_KORBAN §5: Feed a response that contains only preamble and no vital content.
    Verify the system handles this gracefully — the offering without vital organs is
    rejected, not processed into empty propositions.
    """

    def setup_method(self):
        self.result = process_korban(
            content=CLAUDE_EMPTY_OFFERING,
            source=Provenance.CLAUDE,
            query="test empty",
            offering_type=OfferingType.OLAH,
        )

    def test_returns_processed_korban_not_exception(self):
        """System does not raise on empty offering — handles gracefully."""
        assert isinstance(self.result, ProcessedKorban)

    def test_empty_offering_rejected_not_processed(self):
        """
        The offering without vital organs is REJECTED — not processed
        into empty propositions. BUILD_KORBAN.md §5.
        """
        assert self.result.vital_content == ""
        assert self.result.propositions == []

    def test_discarded_content_recorded(self):
        """What was stripped is recorded — the hide and offal are diagnostic data."""
        assert len(self.result.discarded) > 0

    def test_source_query_preserved(self):
        assert self.result.source_query == "test empty"


class TestPipelineIntegration:
    """Additional integration tests covering edge cases."""

    def test_all_offering_types_route(self):
        """All four offering types process without error."""
        for otype in OfferingType:
            result = process_korban(
                content=CLEAN_TORAH_RESPONSE,
                source=Provenance.CLAUDE,
                query="test",
                offering_type=otype,
            )
            assert isinstance(result, ProcessedKorban)
            assert result.offering_type == otype

    def test_all_provenance_sources_accepted(self):
        """All six provenance sources process without error."""
        for prov in Provenance:
            result = process_korban(
                content=CLEAN_TORAH_RESPONSE,
                source=prov,
                query="test",
            )
            assert result.provenance == prov

    def test_human_input_processes_correctly(self):
        human_input = "What does bereishit mean? The word בְּרֵאשִׁית opens Genesis 1:1."
        result = process_korban(
            content=human_input,
            source=Provenance.HUMAN,
            query="definition query",
            offering_type=OfferingType.SHELAMIM,
        )
        assert result.provenance == Provenance.HUMAN
        assert result.offering_type == OfferingType.SHELAMIM
        assert "בְּרֵאשִׁית" in result.vital_content or "Genesis 1:1" in result.vital_content

    def test_empty_raises_value_error(self):
        """Empty content must be rejected at semichah."""
        with pytest.raises(ValueError, match="Empty korban"):
            process_korban(
                content="",
                source=Provenance.CLAUDE,
                query="test",
            )