test_diffing.py

import math

from backend.app.diffing import (
    compute_analyst_metrics,
    cosine_similarity_score,
    diff_paragraphs,
    fog_index,
    section_breakdown,
)


def test_diff_paragraphs_classifies_unchanged_added_removed():
    a = ["Alpha paragraph.", "Beta paragraph.", "Gamma paragraph."]
    b = ["Alpha paragraph.", "Gamma paragraph.", "Delta paragraph."]
    chunks, summary = diff_paragraphs(a, b)

    types = {c["text"]: c["type"] for c in chunks}
    assert types["Alpha paragraph."] == "unchanged"
    assert types["Beta paragraph."] == "removed"
    assert types["Delta paragraph."] == "added"
    assert summary["added_chunks"] == 1
    assert summary["removed_chunks"] == 1
    assert summary["unchanged_chunks"] == 2  # Alpha + Gamma


def test_diff_paragraphs_replace_renders_as_remove_then_insert():
    a = ["We face intense competition."]
    b = ["We face intense competition from new market entrants."]
    chunks, summary = diff_paragraphs(a, b)

    assert [c["type"] for c in chunks] == ["removed", "added"]
    assert summary["removed_chunks"] == 1
    assert summary["added_chunks"] == 1


def test_diff_paragraphs_identical_input_is_all_unchanged():
    a = ["One.", "Two.", "Three."]
    chunks, summary = diff_paragraphs(a, list(a))
    assert all(c["type"] == "unchanged" for c in chunks)
    assert summary["added_chunks"] == 0
    assert summary["removed_chunks"] == 0
    assert summary["unchanged_chunks"] == 3


def test_cosine_similarity_identical_text_is_100():
    text = "Our business depends on continued demand for our products and services."
    assert cosine_similarity_score(text, text) == 100.0


def test_cosine_similarity_disjoint_text_is_zero():
    assert cosine_similarity_score("apple banana cherry", "xylophone zeppelin quokka") == 0.0


def test_cosine_similarity_empty_text_is_zero():
    assert cosine_similarity_score("", "some text here") == 0.0
    assert cosine_similarity_score("some text here", "") == 0.0


def test_fog_index_higher_for_longer_more_complex_sentences():
    simple = "We are a company. We sell goods. We make money."
    complex_text = (
        "Our multinational organization systematically evaluates macroeconomic "
        "considerations affecting operational profitability across jurisdictions."
    )
    simple_fog = fog_index(simple)
    complex_fog = fog_index(complex_text)
    assert simple_fog is not None and complex_fog is not None
    assert complex_fog > simple_fog


def test_fog_index_empty_text_returns_none():
    assert fog_index("") is None


def test_compute_analyst_metrics_word_count_change_pct():
    a = "one two three four"
    b = "one two three four five six"
    metrics = compute_analyst_metrics(a, b)
    assert metrics["word_count_from"] == 4
    assert metrics["word_count_to"] == 6
    assert math.isclose(metrics["word_count_change_pct"], 50.0, abs_tol=0.1)


def test_section_breakdown_groups_under_real_headings():
    chunks = [
        {"type": "unchanged", "text": "Cybersecurity Risks", "heading": True},
        {"type": "unchanged", "text": "We face risks from cyber attacks on our systems.", "heading": False},
        {"type": "added", "text": "New disclosure about a recent security incident response.", "heading": False},
        {"type": "unchanged", "text": "Regulatory Risks", "heading": True},
        {"type": "removed", "text": "Old language about a since-resolved regulatory matter.", "heading": False},
    ]
    sections = section_breakdown(chunks)
    titles = [s["title"] for s in sections]
    assert "Cybersecurity Risks" in titles
    assert "Regulatory Risks" in titles

    cyber = next(s for s in sections if s["title"] == "Cybersecurity Risks")
    assert cyber["added_words"] > 0
    assert cyber["removed_words"] == 0

    reg = next(s for s in sections if s["title"] == "Regulatory Risks")
    assert reg["removed_words"] > 0

    assert math.isclose(sum(s["share_pct"] for s in sections), 100.0, abs_tol=0.5)


def test_section_breakdown_no_headings_falls_under_general():
    chunks = [{"type": "unchanged", "text": "Just a plain paragraph with no heading before it.", "heading": False}]
    sections = section_breakdown(chunks)
    assert len(sections) == 1
    assert sections[0]["title"] == "General disclosures"


def test_section_breakdown_empty_chunks_returns_empty():
    assert section_breakdown([]) == []