bikoret/korban_processor/test/test_zerikah.py

"""
Tests for zerikah — extract vital content.

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

Architecture §3.5: zerikah extracts Torah references, Hebrew text, root
analysis, novel insights, logical propositions. Records discards.
"""

from korban_processor.korban import Korban, OfferingType, Provenance
from korban_processor.zerikah import (
    zerikah,
    is_vital,
    extract_torah_references,
    extract_hebrew_words,
    extract_roots,
    split_sentences,
)
from test.fixtures import CLEAN_TORAH_RESPONSE, LATIN_TORAH_RESPONSE


def make_korban(content: str) -> Korban:
    return Korban(
        raw_content=content,
        provenance=Provenance.CLAUDE,
        offering_type=OfferingType.OLAH,
        source_query="test query",
    )


class TestIsVital:
    def test_torah_reference_is_vital(self):
        assert is_vital("Genesis 1:1 begins the Torah.")

    def test_bereishit_reference_is_vital(self):
        assert is_vital("Bereishit 1:1 opens with creation.")

    def test_exodus_reference_is_vital(self):
        assert is_vital("Exodus 3:14 reveals the divine name.")

    def test_hebrew_text_is_vital(self):
        assert is_vital("The word בְּרֵאשִׁית opens the Torah.")

    def test_root_notation_is_vital(self):
        assert is_vital("The root ר-א-ש means head or beginning.")

    def test_rashi_reference_is_vital(self):
        assert is_vital("Rashi explains this verse in his commentary.")

    def test_gematria_mention_is_vital(self):
        assert is_vital("The gematria of this word is 613.")

    def test_binyan_mention_is_vital(self):
        assert is_vital("The verb is in the piel binyan, indicating intensity.")

    def test_means_insight_is_vital(self):
        assert is_vital("The root means 'to create from nothing' in this context.")

    def test_indicates_insight_is_vital(self):
        assert is_vital("This word indicates a continuous action.")

    def test_generic_filler_not_vital(self):
        assert not is_vital("There are many perspectives on this topic.")

    def test_empty_sentence_not_vital(self):
        assert not is_vital("")

    def test_whitespace_only_not_vital(self):
        assert not is_vital("   ")


class TestExtractTorahReferences:
    def test_extracts_genesis(self):
        refs = extract_torah_references("See Genesis 1:1 and Genesis 2:3.")
        assert len(refs) == 2
        assert any("Genesis 1:1" in r for r in refs)
        assert any("Genesis 2:3" in r for r in refs)

    def test_extracts_bereishit(self):
        refs = extract_torah_references("Bereishit 1:1 is the first verse.")
        assert len(refs) == 1
        assert "Bereishit 1:1" in refs[0]

    def test_extracts_exodus(self):
        refs = extract_torah_references("Exodus 3:14 reveals Ehyeh asher Ehyeh.")
        assert len(refs) >= 1

    def test_extracts_multiple_books(self):
        text = "Genesis 1:1, Exodus 3:14, Leviticus 19:18, Numbers 15:38, Deuteronomy 6:4."
        refs = extract_torah_references(text)
        assert len(refs) == 5

    def test_no_refs_returns_empty(self):
        refs = extract_torah_references("This is general commentary without citations.")
        assert refs == []


class TestExtractHebrewWords:
    def test_extracts_hebrew_word(self):
        words = extract_hebrew_words("The word בְּרֵאשִׁית opens Torah.")
        assert len(words) >= 1
        assert any("בר" in w or "בְּר" in w for w in words)

    def test_extracts_multiple_hebrew_words(self):
        words = extract_hebrew_words("בְּרֵאשִׁית בָּרָא אֱלֹהִים")
        assert len(words) >= 3

    def test_no_hebrew_returns_empty(self):
        words = extract_hebrew_words("No Hebrew here, only Latin script.")
        assert words == []


class TestExtractRoots:
    def test_extracts_dash_separated_root(self):
        roots = extract_roots("The root ר-א-ש means head.")
        assert len(roots) >= 1

    def test_extracts_dot_separated_root(self):
        roots = extract_roots("The root ר.א.ש means head.")
        assert len(roots) >= 1

    def test_no_roots_returns_empty(self):
        roots = extract_roots("No roots mentioned here.")
        assert roots == []


class TestZerikah:
    def test_returns_vital_and_discarded(self):
        korban = make_korban(CLEAN_TORAH_RESPONSE)
        vital, discarded = zerikah(CLEAN_TORAH_RESPONSE, korban)
        assert isinstance(vital, str)
        assert isinstance(discarded, list)

    def test_vital_content_contains_torah_refs(self):
        """BUILD_KORBAN verification §2: extracts Torah references accurately."""
        korban = make_korban(CLEAN_TORAH_RESPONSE)
        vital, _ = zerikah(CLEAN_TORAH_RESPONSE, korban)
        assert "Genesis 1:1" in vital or "Bereishit" in vital

    def test_vital_content_contains_hebrew(self):
        """BUILD_KORBAN verification §2: identifies Hebrew roots."""
        korban = make_korban(CLEAN_TORAH_RESPONSE)
        vital, _ = zerikah(CLEAN_TORAH_RESPONSE, korban)
        # The fixture has Hebrew text
        assert "בְּרֵאשִׁית" in vital or "ר-א-ש" in vital

    def test_vital_content_contains_rashi(self):
        korban = make_korban(CLEAN_TORAH_RESPONSE)
        vital, _ = zerikah(CLEAN_TORAH_RESPONSE, korban)
        assert "Rashi" in vital

    def test_latin_torah_refs_are_vital(self):
        """BUILD_KORBAN verification §2: separates vital from discardable."""
        korban = make_korban(LATIN_TORAH_RESPONSE)
        vital, _ = zerikah(LATIN_TORAH_RESPONSE, korban)
        assert "Genesis 1:1" in vital
        assert "Exodus 3:14" in vital

    def test_empty_content_returns_empty_vital(self):
        korban = make_korban(".")
        vital, discarded = zerikah("", korban)
        assert vital == ""
        assert discarded == []

    def test_all_filler_rejected(self):
        """
        If nothing is vital, zerikah returns empty vital content.
        BUILD_KORBAN.md §5: the offering without vital organs is rejected.
        """
        filler = "There are many perspectives. People disagree. Context matters."
        korban = make_korban(filler)
        vital, discarded = zerikah(filler, korban)
        assert vital == ""
        assert len(discarded) > 0

    def test_stateless_between_calls(self):
        """Kiyyor principle: second call unaffected by first."""
        k1 = make_korban(CLEAN_TORAH_RESPONSE)
        k2 = make_korban(LATIN_TORAH_RESPONSE)
        vital1a, _ = zerikah(CLEAN_TORAH_RESPONSE, k1)
        vital2, _ = zerikah(LATIN_TORAH_RESPONSE, k2)
        vital1b, _ = zerikah(CLEAN_TORAH_RESPONSE, k1)
        # Same input → same output, regardless of what was processed between
        assert vital1a == vital1b


class TestInsightMarkersOnWordBoundaries:
    """Tablet 58: a marker is a word, not a substring. "shorashim" is not Rashi."""

    def test_pod_name_is_not_rashi(self):
        assert not is_vital("It lives at specs/sugya.md, commit dc938058, pod shorashim-675b48f47-v4x9c.")

    def test_rashi_as_a_word_is_vital(self):
        assert is_vital("Rashi reads the verse as a question.")
        assert is_vital("The Mishnah records the opinion that lost.")

    def test_embedded_markers_are_not_words(self):
        assert not is_vital("The surname Rambanovich is not a source.")
        assert not is_vital("The talmudic_engine container restarted.")