"""Tests for src/cmos/parser.py — extract the bibliography section from a draft.

v1 scope: locate a ``## Bibliography`` heading (case-insensitive) and return
the prose before it, the list of entries inside it, and the prose after it.
The section ends at the next ``##`` (level-2) heading or end of file.
Blank lines and bullet markers (``- `` or ``* ``) are stripped from entries.

v2 (notes) parser scope: find pandoc-style markdown footnote definitions
``[^marker]: text`` anywhere in the document. Single-line definitions only;
multi-line continuation is deferred to a later chunk.
"""

import pytest

from cmos.parser import NoBibliographyError, find_notes, split_bibliography


def test_three_entries_under_bibliography_heading():
    draft = """\
Some prose here.

More prose.

## Bibliography

yu, charles. interior chinatown. New York: Pantheon Books, 2020.
Kwon, Hyeyoung. "inclusion work." American Journal of Sociology 127, no. 6 (2022): 1818-1859.
google, "privacy policy," privacy & terms, nov 15 2023, policies.google.com/privacy
"""
    result = split_bibliography(draft)
    assert len(result.entries) == 3
    assert result.entries[0].startswith("yu, charles")
    assert result.entries[1].startswith("Kwon, Hyeyoung")
    assert result.entries[2].startswith("google")
    assert "Some prose here." in result.before
    assert result.after == ""


def test_section_ends_at_next_level_two_heading():
    draft = """\
## Bibliography

First entry.
Second entry.

## Appendix

Appendix content here.
"""
    result = split_bibliography(draft)
    assert result.entries == ["First entry.", "Second entry."]
    assert "## Appendix" in result.after
    assert "Appendix content here." in result.after


def test_bullet_prefixes_stripped():
    draft = """\
## Bibliography

- First entry.
- Second entry.
* Third entry.
"""
    result = split_bibliography(draft)
    assert result.entries == ["First entry.", "Second entry.", "Third entry."]


def test_heading_match_is_case_insensitive():
    draft = """\
## bibliography

Only entry.
"""
    result = split_bibliography(draft)
    assert result.entries == ["Only entry."]


def test_no_bibliography_raises():
    with pytest.raises(NoBibliographyError):
        split_bibliography("## Introduction\n\nJust prose.\n")


# --- find_notes (v2 parser, pandoc-style markdown footnote definitions) ----


def test_find_notes_single_definition():
    draft = """\
Some prose with a citation.[^1]

[^1]: Charles Yu, *Interior Chinatown* (Pantheon Books, 2020), 45.
"""
    result = find_notes(draft)
    assert len(result.definitions) == 1
    assert result.definitions[0].marker == "1"
    assert result.definitions[0].text == "Charles Yu, *Interior Chinatown* (Pantheon Books, 2020), 45."


def test_find_notes_multiple_definitions_in_order():
    draft = """\
Prose.[^1] More prose.[^2] And again.[^3]

[^1]: First note.
[^2]: Second note.
[^3]: Third note.
"""
    result = find_notes(draft)
    assert len(result.definitions) == 3
    assert [d.marker for d in result.definitions] == ["1", "2", "3"]
    assert [d.text for d in result.definitions] == [
        "First note.",
        "Second note.",
        "Third note.",
    ]


def test_find_notes_named_marker():
    draft = """\
Citation.[^smith2020]

[^smith2020]: Smith, J. (2020). Some work.
"""
    result = find_notes(draft)
    assert len(result.definitions) == 1
    assert result.definitions[0].marker == "smith2020"
    assert result.definitions[0].text == "Smith, J. (2020). Some work."


def test_find_notes_returns_empty_when_no_definitions():
    draft = "Just prose with no footnote definitions.\n"
    result = find_notes(draft)
    assert result.definitions == []


def test_find_notes_records_line_number():
    draft = """\
Line zero.
Line one.

[^1]: Note on line three.
"""
    result = find_notes(draft)
    assert len(result.definitions) == 1
    assert result.definitions[0].line_number == 3


def test_find_notes_strips_trailing_whitespace_from_text():
    draft = "[^1]: Note text with trailing spaces.   \n"
    result = find_notes(draft)
    assert result.definitions[0].text == "Note text with trailing spaces."


def test_find_notes_definition_can_appear_before_reference():
    # Pandoc allows definitions anywhere in the doc, not just at the bottom.
    draft = """\
[^1]: A definition before the reference.

Some prose that cites it.[^1]
"""
    result = find_notes(draft)
    assert len(result.definitions) == 1
    assert result.definitions[0].text == "A definition before the reference."