tests/test_charter.py

"""Unit tests for the Charter / Constitution ingester (canlex/charter.py).

Offline only -- every test drives parse() with a fixture cut from the real
Justice Laws markup. The point is the failure mode that emptied dmemos.json on
2026-07-27: if the upstream page is re-shaped the scrape returns nothing, so
parse() must be provably capable of returning [] and build() must refuse to
write that over the stored corpus.
"""
import sys
import unittest
from unittest import mock

from canlex import charter


def _note(text):
    return (f'<p class="MarginalNote"><span class="wb-invisible">Marginal '
            f'note:</span>{text}</p>')


def _section(num, body):
    return (f'<p class="Section"><strong><a class="sectionLabel" id="s-{num}">'
            f'<span class="sectionLabel">{num}</span></a></strong>\xa0{body}</p>')


# Both Acts in sequence, as the page serves them. Section numbers restart at
# the 1982 heading, so "1" appears in each -- only the 1982 one is in scope.
FIXTURE = "".join([
    "<h1>CONSTITUTION ACT, 1867</h1>",
    _note("Short title"),
    _section(1, "This Act may be cited as the Constitution Act, 1867."),
    _note("Legislative Authority of Parliament of Canada"),
    _section(91, "It shall be lawful for the Queen to make Laws for the "
                 "Peace, Order, and good Government of Canada."),
    _note("Subjects of exclusive Provincial Legislation"),
    _section(92, "In each Province the Legislature may exclusively make Laws."),
    "<h1>CONSTITUTION ACT, 1982</h1>",
    _note("Rights and freedoms in Canada"),
    _section(1, "The Canadian Charter of Rights and Freedoms guarantees the "
                "rights and freedoms set out in it."),
    _note("Fundamental freedoms"),
    _section(2, "Everyone has the following fundamental freedoms:"),
    '<ul class="ProvisionList"><li><p class="Paragraph">'
    '<span class="lawlabel">(a)</span>\xa0freedom of conscience and religion;'
    "</p></li></ul>",
    _note("Detention or imprisonment"),
    _section(9, "Everyone has the right not to be arbitrarily detained."),
    _note("Commitment to promote equal opportunities"),
    _section(36, "Parliament and the legislatures are committed to promoting "
                 "equal opportunities."),
    _note("Primacy of Constitution of Canada"),
    _section(52, "The Constitution of Canada is the supreme law of Canada."),
])


class ParseTests(unittest.TestCase):
    def setUp(self):
        self.chunks = charter.parse(FIXTURE)
        self.by_id = {c["id"]: c for c in self.chunks}

    def test_sections_land_in_the_act_they_belong_to(self):
        # s. 1 exists in both Acts; the 1982 one is the Charter's.
        self.assertIn("CONST-1982-s1", self.by_id)
        self.assertNotIn("CONST-1867-s1", self.by_id)
        self.assertIn("CONST-1867-s91", self.by_id)

    def test_ids_stay_unique_across_the_restart_in_numbering(self):
        ids = [c["id"] for c in self.chunks]
        self.assertEqual(len(ids), len(set(ids)))

    def test_out_of_scope_sections_are_dropped(self):
        # 1982 stops at s. 35 (plus s. 52); 1867 keeps only ss. 91-92.
        self.assertNotIn("CONST-1982-s36", self.by_id)
        self.assertIn("CONST-1982-s52", self.by_id)
        self.assertEqual(sorted(c["section"] for c in self.chunks
                                if c["act_code"] == "CONST-1867"),
                         ["91", "92"])

    def test_marginal_note_drops_the_invisible_label(self):
        self.assertEqual(self.by_id["CONST-1982-s9"]["marginal_note"],
                         "Detention or imprisonment")

    def test_section_text_runs_to_the_next_marginal_note(self):
        # s. 2's paragraphs live in a sibling list, outside the Section <p>.
        self.assertIn("freedom of conscience",
                      self.by_id["CONST-1982-s2"]["text"])
        self.assertNotIn("arbitrarily detained",
                         self.by_id["CONST-1982-s2"]["text"])

    def test_chunks_are_citable_legislation(self):
        chunk = self.by_id["CONST-1982-s9"]
        self.assertEqual(chunk["doc_type"], "legislation")
        self.assertEqual(chunk["citation"], "Charter, s. 9")
        self.assertEqual(chunk["source_url"], charter.URL)

    def test_marginal_note_without_a_section_label_is_skipped(self):
        html = ("<h1>CONSTITUTION ACT, 1982</h1>" + _note("Schedule heading") +
                "<p>prose with no section label</p>")
        self.assertEqual(charter.parse(html), [])

    def test_a_reshaped_page_scrapes_to_nothing(self):
        # What a JS-rendered rebuild would look like: heading still there, the
        # MarginalNote/Section markup gone. This is the empty write the guard
        # in build() exists to refuse.
        html = ("<h1>CONSTITUTION ACT, 1982</h1>"
                '<table id="const-tbl" class="wb-tables"></table>')
        self.assertEqual(charter.parse(html), [])

    def test_losing_the_1982_heading_is_an_error_not_a_half_corpus(self):
        # Without the split every 1982 section would be filed under 1867.
        with self.assertRaises(ValueError):
            charter.parse("<h1>CONSTITUTION ACT, 1867</h1>" + _note("x") +
                          _section(91, "text"))


class MainTests(unittest.TestCase):
    """main() has to make a refused write visible to refresh.py, which runs
    this module as a subprocess and only sees the exit status."""

    def _run(self, argv, build_result=True):
        with mock.patch.object(charter, "build") as build:
            build.return_value = build_result
            with mock.patch.object(sys, "argv", argv):
                with self.assertRaises(SystemExit) as caught:
                    charter.main()
        return caught.exception.code, build

    def test_refused_write_exits_nonzero(self):
        code, _build = self._run(["charter"], build_result=False)
        self.assertEqual(code, 1)

    def test_successful_write_exits_zero(self):
        code, _build = self._run(["charter"], build_result=True)
        self.assertEqual(code, 0)

    def test_allow_shrink_flag_reaches_build(self):
        _code, build = self._run(["charter", "--allow-shrink"])
        build.assert_called_once_with(allow_shrink=True)

    def test_guard_is_on_by_default(self):
        _code, build = self._run(["charter"])
        build.assert_called_once_with(allow_shrink=False)


if __name__ == "__main__":
    unittest.main()