llm-ingestion-okf/tests/test_extract.py

"""Door B extraction registry: file bytes -> text, per file type (Phase 2 step 1).

Core stdlib extractors (md/txt/csv/json/html) plus the fail-fast gates: unknown
extension, the [extract]-gated binary types when the extra is absent, corrupt
(non-UTF-8) bytes, and an empty CSV. All file-type->text extraction lives HERE
(the guard is text-only); this step adds zero runtime dependency and no guard
call — it is pure, deterministic plumbing.
"""

from __future__ import annotations

import importlib.util
import sys
from pathlib import Path

import pytest

from llm_ingestion_okf import ExtractionError, ExtractionWarning, extract_text

FIXTURES = Path(__file__).parent / "fixtures"

# The parser-dependent tests below need the optional extra, so they are skipped
# without it — an optional extra that forced its parser on every test run would
# not be optional. The behaviour that must survive EITHER WAY is the rejection,
# and that one is asserted unconditionally above via the import probe.
requires_extract = pytest.mark.skipif(
    importlib.util.find_spec("pdfplumber") is None,
    reason="the optional [extract] extra is not installed",
)

# --- core extractors: happy path (a fixture per type) ---


def test_md_passthrough() -> None:
    assert extract_text("note.md", b"# Title\n\nBody\n") == "# Title\n\nBody\n"


def test_txt_passthrough() -> None:
    assert extract_text("note.txt", b"plain text") == "plain text"


def test_utf8_sig_bom_is_stripped() -> None:
    # utf-8-sig so a BOM never leaks into the first character (baseline parity
    # with Door A's read_csv).
    assert extract_text("note.txt", b"\xef\xbb\xbfhello") == "hello"


def test_csv_renders_the_phase_1_markdown_table() -> None:
    out = extract_text("data.csv", b"name,age\nAda,36\n")
    assert out == "| name | age |\n| --- | --- |\n| Ada | 36 |\n"


def test_json_is_verbatim_inside_a_fenced_block() -> None:
    out = extract_text("cfg.json", b'{"k": 1}\n')
    assert out == '```\n{"k": 1}\n```\n'


def test_html_text_via_htmlparser() -> None:
    # Block boundaries separate words; tags themselves contribute no text.
    out = extract_text("page.html", b"<h1>Title</h1><p>Hello <b>world</b></p>")
    assert out == "Title Hello world"


def test_html_skips_script_and_style() -> None:
    html = b"<style>.x{color:red}</style><p>Keep</p><script>evil()</script>"
    assert extract_text("page.html", html) == "Keep"


def test_htm_is_an_html_alias() -> None:
    assert extract_text("page.htm", b"<p>hi</p>") == "hi"


def test_extension_dispatch_is_case_insensitive() -> None:
    assert extract_text("NOTE.MD", b"x") == "x"


# --- fail-fast: unknown extension ---


def test_unknown_extension_fails_fast() -> None:
    with pytest.raises(ExtractionError) as excinfo:
        extract_text("archive.zip", b"PK\x03\x04")
    assert excinfo.value.code == "extractor_unknown"


def test_missing_extension_fails_fast() -> None:
    with pytest.raises(ExtractionError) as excinfo:
        extract_text("README", b"x")
    assert excinfo.value.code == "extractor_unknown"


# --- fail-fast: [extract]-gated binary types the extra ships no parser for ---


@pytest.mark.parametrize("name", ["doc.docx", "sheet.xlsx"])
def test_optional_type_without_a_parser_fails_fast(name: str) -> None:
    with pytest.raises(ExtractionError) as excinfo:
        extract_text(name, b"binary")
    assert excinfo.value.code == "extractor_extra_missing"
    # The error names the extra so the operator knows the remedy — never a
    # silent skip, never a bundled parser in core.
    assert "extract" in str(excinfo.value)


def test_pdf_without_the_extra_installed_keeps_the_same_rejection(
    monkeypatch: pytest.MonkeyPatch,
) -> None:
    """The gate became an import probe; the rejection did not change.

    Setting the module to None in sys.modules is what CPython treats as a
    failed import, so this exercises the uninstalled path REGARDLESS of
    whether the extra is installed in the running environment — a skip would
    have preserved nothing on the machine where the parser is present.
    """
    monkeypatch.setitem(sys.modules, "pdfplumber", None)
    with pytest.raises(ExtractionError) as excinfo:
        extract_text("doc.pdf", b"%PDF-1.4")
    assert excinfo.value.code == "extractor_extra_missing"
    assert "extract" in str(excinfo.value)


# --- pdf: the [extract] parser (pdfplumber) ---

# The expected text is frozen against a committed fixture ON PURPOSE. Extraction
# is deterministic within a parser version and NOT guaranteed across one
# (pdfplumber pins pdfminer.six==20260107 exactly; pdfminer.six ships
# date-stamped releases with no stability contract). This literal is what makes
# a parser upgrade break something visible instead of drifting silently.
KRAV_TEXT = "Krav til helning på utkilingen\n60 og 70 1:15"


@requires_extract
def test_pdf_extracts_text_with_label_and_value_on_one_line() -> None:
    data = (FIXTURES / "two-line-krav.pdf").read_bytes()
    with pytest.warns(ExtractionWarning):
        assert extract_text("krav.pdf", data) == KRAV_TEXT


@requires_extract
def test_pdf_extraction_is_byte_stable_across_calls() -> None:
    """Determinism is a promise this library already makes; hold it here too."""
    data = (FIXTURES / "two-line-krav.pdf").read_bytes()
    with pytest.warns(ExtractionWarning):
        first = extract_text("krav.pdf", data)
        second = extract_text("krav.pdf", data)
    assert first == second


@requires_extract
def test_pdf_extraction_warns_that_drawn_content_is_not_recovered() -> None:
    """Figures are vector drawings: only the caption survives leg 2.

    Categorically true of text extraction, so it is stated as a warning on
    every PDF rather than guessed at per document — detecting "is there a
    figure here" would be exactly the layout heuristic this order declined.
    """
    data = (FIXTURES / "two-line-krav.pdf").read_bytes()
    with pytest.warns(ExtractionWarning, match="figures"):
        extract_text("krav.pdf", data)


@requires_extract
def test_pdf_with_no_text_layer_fails_fast() -> None:
    """A scanned PDF yields nothing; an empty concept would be a silent skip."""
    data = (FIXTURES / "no-text-layer.pdf").read_bytes()
    with pytest.raises(ExtractionError) as excinfo:
        extract_text("scan.pdf", data)
    assert excinfo.value.code == "extractor_empty_pdf"


@requires_extract
def test_corrupt_pdf_fails_fast_typed() -> None:
    """Never a leaked pdfminer exception — the "always typed" doctrine holds."""
    with pytest.raises(ExtractionError) as excinfo:
        extract_text("broken.pdf", b"not a pdf at all")
    assert excinfo.value.code == "extractor_pdf_error"


# --- fail-fast: corrupt (non-UTF-8) bytes on a text type ---


def test_invalid_utf8_fails_fast_typed() -> None:
    # Never a leaked UnicodeDecodeError — the "always typed" doctrine holds for
    # Door B too (cf. Door A wrapping path ValueError as SourceError).
    with pytest.raises(ExtractionError) as excinfo:
        extract_text("note.txt", b"\xffbad")
    assert excinfo.value.code == "extractor_decode_error"


# --- fail-fast: empty CSV (no header row) ---


def test_empty_csv_fails_fast() -> None:
    with pytest.raises(ExtractionError) as excinfo:
        extract_text("empty.csv", b"")
    assert excinfo.value.code == "extractor_empty_csv"