Jyotisha/tests/test_report_chart_blank_columns.py

"""Blank report and chart columns (TASK-report-chart-blank-columns-20261003).

BUG-1199 Kranti column with no producer; BUG-1200 Ashtakavarga house table
labelled the with-Lagna total as SAV (split in the reader: ashtakavarga.py is
in the frozen rectification identity and stays byte-identical); BUG-1201 ascendant without nakshatra;
BUG-1203 the divisional-chart caveat moved to the chart section. Every chart
here is fictional.
"""

from __future__ import annotations

import copy
import json
import re
from pathlib import Path

import pytest

from scripts.ashtakavarga import BAV_TOTALS, EXPECTED_SAV_TOTAL, SIGNS
from scripts.jyotish_engine import NAKSHATRA_LIST, _nakshatra_fields, compute_chart_data
from scripts.pl9_reader_export import _pl9_export_markdown_for_edition
from tests.test_report_english_edition import CASES, _packet

ROOT = Path(__file__).resolve().parents[1]
CAVEAT_ZH = "分盘对出生时间敏感，原始计算供核对，不单独增加结论的确定性。"


def _independent_nakshatra(lon: float) -> tuple[str, int, str]:
    minutes = (lon % 360) * 60
    index = int(minutes // 800)  # 13°20′ = 800′
    pada = int((minutes % 800) // 200) + 1  # 3°20′ = 200′
    name, lord, _ = NAKSHATRA_LIST[index]
    return name, pada, lord


@pytest.mark.parametrize("lon,expected", [
    (0.0, ("Ashwini", 1, "Ketu")),
    (13.33, ("Ashwini", 4, "Ketu")),
    (13.34, ("Bharani", 1, "Venus")),
    (134.53, ("Purva Phalguni", 1, "Venus")),
    (149.3994, ("Uttara Phalguni", 1, "Sun")),
    (359.99, ("Revati", 4, "Mercury")),
    (360.0, ("Ashwini", 1, "Ketu")),
])
def test_nakshatra_fields_at_boundaries(lon, expected) -> None:
    fields = _nakshatra_fields(lon)
    assert (fields["nakshatra"], fields["nakshatra_pada"], fields["nakshatra_lord"]) == expected


def test_chart_ascendant_carries_its_nakshatra_and_planets_are_unchanged() -> None:
    golden = json.loads((ROOT / "frontend/tests/fixtures/chart-view-golden.json").read_text(encoding="utf-8"))
    chart, *_ = compute_chart_data(1990, 6, 15, 12, 0, 39.9042, 116.4074, 8.0, ayanamsa_name="raman")
    asc = chart["ascendant"]
    assert (asc["nakshatra"], asc["nakshatra_pada"], asc["nakshatra_lord"]) == _independent_nakshatra(asc["lon"])
    assert {k: asc[k] for k in ("nakshatra", "nakshatra_pada", "nakshatra_lord")} == {
        k: golden["chart"]["ascendant"][k] for k in ("nakshatra", "nakshatra_pada", "nakshatra_lord")
    }
    for name, planet in chart["planets"].items():
        stored = golden["chart"]["planets"][name]
        assert (planet["nakshatra"], planet["nakshatra_pada"], planet["nakshatra_lord"]) == (
            stored["nakshatra"], stored["nakshatra_pada"], stored["nakshatra_lord"]), name


@pytest.fixture(scope="module")
def editions() -> tuple[str, str, dict]:
    packet = _packet(CASES["day"])
    zh = _pl9_export_markdown_for_edition(copy.deepcopy(packet), "full_data")
    english = copy.deepcopy(packet)
    english["report_language"] = "en"
    return zh, _pl9_export_markdown_for_edition(english, "full_data"), packet


def _table_after(markdown: str, heading: str) -> list[list[str]]:
    lines = markdown.splitlines()
    start = next(i for i, line in enumerate(lines) if line.startswith("### ") and heading in line)
    rows = []
    for line in lines[start + 1:]:
        if line.startswith("### ") or (rows and not line.startswith("|")):
            break
        if line.startswith("|") and not set(line) <= set("|- "):
            rows.append([cell.strip() for cell in line.strip("|").split("|")])
    return rows


def test_declination_table_has_no_kranti_column(editions) -> None:
    # 原值：两版标题都是 Declination / Speed，表头 Planet/Degree/Declination/Speed
    # 新值：中文标题「赤纬 / 速度」，表头 行星/度数/赤纬/速度；英文保持原文
    # 原因：完整数据版中文清理翻译这四列。Kranti 列仍然不出现
    for markdown, heading, header in (
        (editions[0], "赤纬 / 速度", ["行星", "度数", "赤纬", "速度"]),
        (editions[1], "Declination / Speed", ["Planet", "Degree", "Declination", "Speed"]),
    ):
        assert "Kranti" not in markdown
        rows = _table_after(markdown, heading)
        assert rows[0] == header
        assert len(rows) == 8 and all(len(row) == 4 and "-" not in row for row in rows)


def test_ashtakavarga_house_table_shows_three_real_columns(editions) -> None:
    zh, en, packet = editions
    expected_sav = packet["worksheets"]["strengths_and_scores"]["ashtakavarga"]["sav"]["scores"]
    # BUG-1209 (乙8): a Sodhita SAV column comes first and the raw columns are
    # labelled Raw. Was: ["House", "Sign", "SAV", "Lagna BAV", "SAV + Lagna"]
    # with the raw cells at indexes 2..4 (now 3..5).
    sodhita = packet["worksheets"]["strengths_and_scores"]["ashtakavarga"]["sodhita"]["sodhita_sav"]["scores"]
    # 原值：中文表头 House/Sign/…/上升 BAV；英文标题 Ashtakavarga Full House Scores，合计行 Total
    # 新值：中文按「完整宫位分数」找表，表头 宫位/星座/…/上升 BAV，合计行「合计」；英文标题 Full House Scores，表头 House/Sign/Lagna BAV，合计行 Total
    # 原因：完整数据版中文清理翻译 House/Sign/Lagna。英文先译整节标题，并把「合计」写成 Total，避免单字清理把标题拆碎或把合计留成汉字
    for markdown, heading, header, total in (
        (zh, "完整宫位分数", ["宫位", "星座", "Sodhita SAV", "Raw SAV", "上升 BAV", "Raw SAV + 上升"], "合计"),
        (en, "Full House Scores", ["House", "Sign", "Sodhita SAV", "Raw SAV", "Lagna BAV", "Raw SAV + Lagna"], "Total"),
    ):
        rows = _table_after(markdown, heading)
        assert rows[0] == header
        body, totals = rows[1:13], rows[13]
        for row in body:
            sav, lagna, full = (int(cell) for cell in row[3:])
            assert sav + lagna == full
            assert int(row[2]) <= sav
        # 原值：合计行星座格是 "-"
        # 新值：星座格是 "-"、"未列" 或 "not listed"；后面四格数字不变
        # 原因：完整数据版清理器把空位写成「未列」。Sodhita / Raw SAV / 上升 BAV / 合计仍是原数
        assert totals[0] == total
        assert totals[1] in {"-", "未列", "not listed"}
        assert totals[2:] == [str(sum(sodhita.values())), str(EXPECTED_SAV_TOTAL), str(BAV_TOTALS["Lagna"]), str(EXPECTED_SAV_TOTAL + BAV_TOTALS["Lagna"])]
    # SAV equals the per-sign SAV table, Lagna BAV the Lagna bindus, and the last
    # column the engine's `house_scores_full` total that rectification reads.
    ashtakavarga = packet["worksheets"]["strengths_and_scores"]["ashtakavarga"]
    full = {row["sign"]: row["sav_score"] for row in ashtakavarga["house_scores_full"].values()}
    for row in _table_after(en, "Full House Scores")[1:13]:
        assert int(row[2]) == sodhita[row[1]]
        assert int(row[3]) == expected_sav[row[1]]
        assert int(row[4]) == ashtakavarga["bav"]["Lagna"]["bindus"][SIGNS.index(row[1])]
        assert int(row[5]) == full[row[1]]


def test_ashtakavarga_house_table_never_labels_the_total_as_sav(editions) -> None:
    packet = copy.deepcopy(editions[2])
    del packet["worksheets"]["strengths_and_scores"]["ashtakavarga"]["bav"]["Lagna"]
    rows = _table_after(_pl9_export_markdown_for_edition(packet, "full_data"), "Ashtakavarga 完整宫位分数")
    assert len(rows) == 13, "no total row without the split"
    for row in rows[1:]:
        # BUG-1209: raw SAV / Lagna BAV moved from [2:4] to [3:5]; Sodhita at [2].
        assert row[2].isdigit()
        # 原值：缺数两格都是 "-"
        # 新值：缺数格是 "-" 或「未列」，且不是数字、也不标成 SAV
        # 原因：完整数据版清理器会把一部分空位写成「未列」
        assert row[3] in {"-", "未列"} and row[4] in {"-", "未列"}
        assert not row[3].isdigit() and not row[4].isdigit()
        assert row[5].isdigit()


_CALCULATION_CHART_IDS = {
    "D1", "D2", "D3", "D4", "D7", "D9", "D10", "D11", "D12",
    "D16", "D20", "D24", "D27", "D30", "D40", "D60",
}


def _section_until_next_h2(markdown: str, heading: str) -> str:
    start = markdown.index(heading)
    lines = [heading]
    for line in markdown[start + len(heading):].splitlines():
        if line.startswith("## "):
            break
        lines.append(line)
    return "\n".join(lines)


def test_full_data_chart_section_draws_each_ready_chart_once(editions) -> None:
    from scripts.report_chart_block import FENCE_RE
    zh, en, _packet = editions
    for markdown, heading in (
        (zh, "### 本命与分盘北印度图盘"),
        (en, "### Natal and Divisional North Indian Charts"),
    ):
        section = _section_until_next_h2(markdown, heading)
        blocks = []
        for match in FENCE_RE.finditer(section):
            block = json.loads(match.group(1))
            assert block["layout"] == "north"
            blocks.append(block)
        ids = [block["id"] for block in blocks]
        assert ids
        assert len(ids) == len(set(ids))
        assert _CALCULATION_CHART_IDS <= set(ids)
        assert "MOON" in ids
        assert not re.search(r"(?m)^##### .+\n\n+##### ", section)
        assert not re.search(r"(?m)^##### .*Bhava", section)
        assert "##### Navamsha" not in section and "##### p7 · Navamsha" not in section


def _heading_table(markdown: str, heading: str) -> list[list[str]]:
    """Like _table_after, but the lord table is a #### heading, not ###."""
    lines = markdown.splitlines()
    start = next(i for i, line in enumerate(lines) if line.startswith("#") and heading in line)
    rows = []
    for line in lines[start + 1:]:
        if line.startswith("#") or (rows and not line.startswith("|")):
            break
        if line.startswith("|") and not set(line) <= set("|- "):
            rows.append([cell.strip() for cell in line.strip("|").split("|")])
    return rows


def test_birth_position_table_starts_with_the_ascendant(editions) -> None:
    zh, en, packet = editions
    asc = packet["core_chart"]["ascendant"]
    longitude = asc.get("lon") if isinstance(asc.get("lon"), (int, float)) else asc.get("degree_raw")
    fields = _nakshatra_fields(float(longitude))
    lord_zh = {
        "Sun": "太阳", "Moon": "月亮", "Mars": "火星", "Mercury": "水星",
        "Jupiter": "木星", "Venus": "金星", "Saturn": "土星",
        "Rahu": "北交点", "Ketu": "南交点",
    }
    zh_rows = _heading_table(zh, "行星原始位置")
    assert zh_rows[1][0] == "上升"
    assert fields["nakshatra"] in zh_rows[1][6]
    assert zh_rows[1][7] == str(fields["nakshatra_pada"])
    assert zh_rows[1][5] == "1"
    lords = _heading_table(zh, "行星主星与状态")
    assert lords[1][0] == "上升"
    assert lords[1][5] == "不适用"
    assert lords[1][2] in {fields["nakshatra_lord"], lord_zh.get(fields["nakshatra_lord"])}
    en_rows = _heading_table(en, "Planetary Raw Positions")
    assert en_rows[1][0] in {"Ascendant", "Lagna", "上升"}
    assert fields["nakshatra"] in en_rows[1][6]
    assert en_rows[1][7] == str(fields["nakshatra_pada"])


def test_zh_hygiene_rejects_glued_english(editions) -> None:
    from scripts.pl9_full_data_export import _pl9_markdown_hygiene_receipt, _zh_body_residue
    injected = _pl9_markdown_hygiene_receipt("木星Jupiterexalted在巨蟹座\n", language="zh")
    assert injected["status"] == "fail"
    assert any(str(item).startswith("glued_latin:") for item in injected["violations"])
    residue = _zh_body_residue(editions[0])
    assert residue == {"glued_latin": 0, "function_words": 0}


def test_zh_hygiene_is_clean_on_night_and_a_public_chart() -> None:
    from scripts.pl9_full_data_export import _zh_body_residue
    # Public birth used by tests/smoke_test_runner.py. Not a private user.
    public = {
        **CASES["day"],
        "name": "Albert Einstein",
        "year": 1879,
        "month": 3,
        "day": 14,
        "hour": 11,
        "minute": 30,
        "lat": 48.4,
        "lon": 9.98,
        "tz": 0.89,
        "age": 76,
    }
    for case in (CASES["night"], public):
        packet = _packet(case)
        markdown = _pl9_export_markdown_for_edition(copy.deepcopy(packet), "full_data")
        assert _zh_body_residue(markdown) == {"glued_latin": 0, "function_words": 0}


def test_chart_section_carries_the_divisional_caveat(editions) -> None:
    zh, en, _ = editions
    assert re.search(r"### 本命与分盘北印度图盘\n\n" + re.escape(CAVEAT_ZH) + r"\n", zh)
    # 原值：### Natal and Divisional Charts (North Indian) 下一行是英文 caveat
    # 新值：### Natal and Divisional North Indian Charts；英文句或保留的中文 caveat 都算在
    # 原因：完整数据版英文清理用上游标题。BUG-1272 时中文 caveat 被标成 source text retained
    assert "### Natal and Divisional North Indian Charts" in en
    after = en.split("### Natal and Divisional North Indian Charts", 1)[1][:800]
    assert "Divisional charts are sensitive to birth time" in after or "分盘对出生时间敏感" in after