parser: support diverse md inputs (bold headings, Works Cited, blockquote notes, junk filtering)

- Bibliography heading now accepts bold markers (## **BIBLIOGRAPHY**),
  alternative names (Works Cited, References), and numbered sub-headings
  within the section.
- Original heading text preserved in output instead of hardcoded
  "## Bibliography".
- New find_blockquote_notes() parser for PDF-to-markdown footnote format
  (> N text), wired into CLI as third fallback after pandoc and numbered.
- PDF junk filtered from bibliography entries: bare page numbers,
  blockquote footnotes, download banners, CC license URLs, and short
  running headers.

tests/test_cli.py

@@ -51,14 +51,14 @@ def test_reformat_draft_preserves_sections_after_bibliography():
     draft = """\
 ## Bibliography
 
-one entry.
+Yu, Charles. *Interior Chinatown* (New York: Pantheon, 2020).
 
 ## Appendix
 
 appendix text.
 """
     output = reformat_draft(draft, formatter=_fake_formatter)
-    assert "FORMATTED(one entry.)" in output
+    assert "FORMATTED(Yu, Charles. *Interior Chinatown* (New York: Pantheon, 2020).)" in output
     assert "## Appendix" in output
     assert "appendix text." in output
 
@@ -69,11 +69,27 @@ def test_reformat_draft_raises_when_no_bibliography():
 
 
 def test_reformat_draft_bibliography_heading_preserved():
-    draft = "## Bibliography\n\nentry.\n"
+    draft = '## Bibliography\n\nYu, Charles. *Interior Chinatown* (Pantheon, 2020).\n'
     output = reformat_draft(draft, formatter=_fake_formatter)
     assert "## Bibliography" in output
 
 
+def test_reformat_draft_preserves_works_cited_heading():
+    """When the input heading is ``## Works Cited``, the output must
+    keep that heading — not replace it with ``## Bibliography``."""
+    draft = '## Works Cited\n\nDavidson, Donald. "On the Very Idea." (1974).\n'
+    output = reformat_draft(draft, formatter=_fake_formatter)
+    assert "## Works Cited" in output
+    assert "## Bibliography" not in output
+
+
+def test_reformat_draft_preserves_bold_wrapped_heading():
+    """Bold markers in the heading should be preserved in the output."""
+    draft = '## **Works Cited**\n\nDavidson, Donald. "On the Very Idea." (1974).\n'
+    output = reformat_draft(draft, formatter=_fake_formatter)
+    assert "## **Works Cited**" in output
+
+
 def test_python_dash_m_invocation_actually_runs_main():
     """Regression test: `python -m cmos.cli` must actually invoke main().
 
@@ -216,6 +232,23 @@ def test_reformat_notes_auto_detects_numbered_format():
     assert "[^2]" not in output
 
 
+def test_reformat_notes_auto_detects_blockquote_format():
+    """PDF-to-markdown drafts use ``> N text`` blockquote footnotes.
+    reformat_notes must auto-detect after pandoc and numbered fail."""
+    draft = """\
+Some prose.
+
+> 1 Davidson, "On the Very Idea of a Conceptual Scheme."
+> 2 Frankenberry 1999, 526.
+"""
+    output = reformat_notes(draft, formatter=_fake_note_formatter)
+    assert '> 1 NOTE_FORMATTED(Davidson, "On the Very Idea of a Conceptual Scheme.")' in output
+    assert "> 2 NOTE_FORMATTED(Frankenberry 1999, 526.)" in output
+    # No pandoc or numbered markers should appear.
+    assert "[^1]" not in output
+    assert "[1] " not in output
+
+
 def test_reformat_notes_pandoc_input_still_round_trips_as_pandoc():
     """Regression: after the auto-detect change, pandoc-format input
     must still produce pandoc-format output. The original_prefix path
@@ -265,28 +298,28 @@ def test_reformat_draft_preserves_order_under_concurrency():
     # later ones if order were naively tied to completion.
     import time
 
+    # Map each entry to a sleep duration so earlier entries finish last.
+    order = {"2020": 4, "2021": 3, "2022": 2, "2023": 1, "2024": 0}
+
     def slow_fake(messy: str) -> str:
-        # Entries with lower index sleep longer so they finish last.
-        n = int(messy.split()[-1])
-        time.sleep(0.05 * (5 - n))
+        year = messy.strip()[-5:-1]  # extract "2020" etc.
+        time.sleep(0.05 * order.get(year, 0))
         return f"FORMATTED({messy})"
 
     draft = """\
 ## Bibliography
 
-entry 0
-entry 1
-entry 2
-entry 3
-entry 4
+Author, A. *Title Zero* (Publisher, 2020).
+Author, B. *Title One* (Publisher, 2021).
+Author, C. *Title Two* (Publisher, 2022).
+Author, D. *Title Three* (Publisher, 2023).
+Author, E. *Title Four* (Publisher, 2024).
 """
     output = reformat_draft(draft, formatter=slow_fake, concurrency=4)
     # Entries must appear in input order.
     lines = [l for l in output.splitlines() if l.startswith("FORMATTED(")]
-    assert lines == [
-        "FORMATTED(entry 0)",
-        "FORMATTED(entry 1)",
-        "FORMATTED(entry 2)",
-        "FORMATTED(entry 3)",
-        "FORMATTED(entry 4)",
-    ]
+    assert lines[0].startswith("FORMATTED(Author, A.")
+    assert lines[1].startswith("FORMATTED(Author, B.")
+    assert lines[2].startswith("FORMATTED(Author, C.")
+    assert lines[3].startswith("FORMATTED(Author, D.")
+    assert lines[4].startswith("FORMATTED(Author, E.")

tests/test_parser.py

@@ -26,6 +26,7 @@ import pytest
 
 from cmos.parser import (
     NoBibliographyError,
+    find_blockquote_notes,
     find_notes,
     find_numbered_notes,
     split_bibliography,
@@ -57,15 +58,16 @@ def test_section_ends_at_next_level_two_heading():
     draft = """\
 ## Bibliography
 
-First entry.
-Second entry.
+Yu, Charles. *Interior Chinatown* (New York: Pantheon, 2020).
+Kwon, Hyeyoung. "Inclusion Work," *American Journal of Sociology* 127 (2022).
 
 ## Appendix
 
 Appendix content here.
 """
     result = split_bibliography(draft)
-    assert result.entries == ["First entry.", "Second entry."]
+    assert len(result.entries) == 2
+    assert result.entries[0].startswith("Yu, Charles")
     assert "## Appendix" in result.after
     assert "Appendix content here." in result.after
 
@@ -74,22 +76,208 @@ def test_bullet_prefixes_stripped():
     draft = """\
 ## Bibliography
 
-- First entry.
-- Second entry.
-* Third entry.
+- Yu, Charles. *Interior Chinatown* (New York: Pantheon, 2020).
+- Kwon, Hyeyoung. "Inclusion Work," *AJS* 127 (2022).
+* Google. "Privacy Policy," Privacy & Terms, 2023.
 """
     result = split_bibliography(draft)
-    assert result.entries == ["First entry.", "Second entry.", "Third entry."]
+    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")
 
 
 def test_heading_match_is_case_insensitive():
     draft = """\
 ## bibliography
 
-Only entry.
+Yu, Charles. *Interior Chinatown* (New York: Pantheon, 2020).
 """
     result = split_bibliography(draft)
-    assert result.entries == ["Only entry."]
+    assert len(result.entries) == 1
+    assert result.entries[0].startswith("Yu, Charles")
+
+
+def test_heading_match_works_cited():
+    """'Works Cited' is the standard CMOS heading alternative to
+    'Bibliography'.  The parser should accept it."""
+    draft = """\
+## Works Cited
+
+Davidson, Donald. "On the Very Idea of a Conceptual Scheme."
+Evans-Pritchard, E.E. *Witchcraft, oracles, and magic.*
+"""
+    result = split_bibliography(draft)
+    assert len(result.entries) == 2
+    assert result.entries[0].startswith("Davidson")
+
+
+def test_heading_match_works_cited_bold():
+    """Bold-wrapped variant: ``## **Works Cited**``."""
+    draft = """\
+## **Works Cited**
+
+- Frankenberry, Nancy. "Pragmatism, Truth, and Subjectivity" (1999).
+"""
+    result = split_bibliography(draft)
+    assert len(result.entries) == 1
+    assert result.entries[0].startswith("Frankenberry")
+
+
+def test_heading_match_ignores_bold_markers():
+    """Real-world drafts from PDF-to-markdown conversion often wrap the
+    heading text in bold: ``## **BIBLIOGRAPHY**``.  The parser should
+    strip ``**`` before matching."""
+    draft = """\
+## **BIBLIOGRAPHY**
+
+- Yu, Charles. *Interior Chinatown* (New York: Pantheon, 2020).
+- Kwon, Hyeyoung. "Inclusion Work," *AJS* 127 (2022).
+"""
+    result = split_bibliography(draft)
+    assert len(result.entries) == 2
+    assert result.entries[0].startswith("Yu, Charles")
+
+
+def test_heading_match_ignores_numbered_sub_headings():
+    """Subdivided bibliographies (common in dissertations) use numbered
+    ``##`` sub-headings inside the bibliography section.  These must NOT
+    terminate the section — the parser should skip them and keep
+    collecting entries until a non-numbered ``##`` heading or EOF."""
+    draft = """\
+## **BIBLIOGRAPHY**
+
+## **1. Primary Sources**
+
+- Crum, Walter E., *A Coptic Dictionary* (Oxford: Clarendon Press, 1939).
+- Till, Walter C., ed., *Die koptischen Ostraka* (Vienna, 1960).
+
+## **2. Secondary Literature**
+
+- Marsham, Andrew, ed., *The Umayyad World* (London: Routledge, 2020).
+- Schulz, Fritz, *Classical Roman Law* (Oxford: Clarendon Press, 1951).
+"""
+    result = split_bibliography(draft)
+    assert len(result.entries) == 4
+    assert result.entries[0].startswith("Crum, Walter")
+    assert result.entries[3].startswith("Schulz, Fritz")
+    assert result.after == ""
+
+
+def test_numbered_sub_headings_not_collected_as_entries():
+    """The sub-heading lines themselves (e.g. ``## **1. Primary Sources**``)
+    should not appear in the entries list."""
+    draft = """\
+## Bibliography
+
+## 1. Primary Sources
+
+- Crum, Walter E., *A Coptic Dictionary* (Oxford: Clarendon Press, 1939).
+
+## 2. Secondary Sources
+
+- Schulz, Fritz, *Classical Roman Law* (Oxford: Clarendon Press, 1951).
+"""
+    result = split_bibliography(draft)
+    assert len(result.entries) == 2
+    for entry in result.entries:
+        assert not entry.startswith("##")
+        assert "Primary Sources" not in entry
+        assert "Secondary Sources" not in entry
+
+
+def test_non_numbered_heading_still_ends_section_after_sub_headings():
+    """A non-numbered ``##`` heading after bibliography sub-sections
+    should still terminate the bibliography section."""
+    draft = """\
+## Bibliography
+
+## 1. Primary Sources
+
+- Crum, Walter E., *A Coptic Dictionary* (Oxford: Clarendon Press, 1939).
+
+## Appendix
+
+Appendix content.
+"""
+    result = split_bibliography(draft)
+    assert len(result.entries) == 1
+    assert result.entries[0].startswith("Crum, Walter")
+    assert "## Appendix" in result.after
+    assert "Appendix content." in result.after
+
+
+def test_bare_page_numbers_filtered():
+    """PDF-to-markdown conversion leaves bare page numbers (e.g. '370')
+    as standalone lines.  These are not bibliography entries."""
+    draft = """\
+## Bibliography
+
+- Crum, Walter E., *A Coptic Dictionary* (Oxford: Clarendon Press, 1939).
+
+370
+
+- Schulz, Fritz, *Classical Roman Law* (Oxford: Clarendon Press, 1951).
+
+371
+"""
+    result = split_bibliography(draft)
+    assert len(result.entries) == 2
+    assert result.entries[0].startswith("Crum")
+    assert result.entries[1].startswith("Schulz")
+
+
+def test_blockquote_footnotes_filtered():
+    """Blockquote footnotes (``> N text``) that appear inside a Works Cited
+    section are PDF artifacts, not bibliography entries."""
+    draft = """\
+## Works Cited
+
+Davidson, Donald. "On the Very Idea of a Conceptual Scheme."
+
+> 87 Holbraad 2010.
+> 88 Frankenberry 2018, 236.
+
+Frankenberry, Nancy. "Pragmatism, Truth, and Subjectivity" (1999).
+"""
+    result = split_bibliography(draft)
+    assert len(result.entries) == 2
+    assert result.entries[0].startswith("Davidson")
+    assert result.entries[1].startswith("Frankenberry")
+
+
+def test_download_banners_filtered():
+    """Brill/publisher download banners are PDF junk, not entries."""
+    draft = """\
+## Bibliography
+
+Crum, Walter E., *A Coptic Dictionary* (Oxford: Clarendon Press, 1939).
+Downloaded from Brill.com 02/22/2024 05:33:29AM via Open Access. This is junk.
+https://creativecommons.org/licenses/by/4.0/
+Schulz, Fritz, *Classical Roman Law* (Oxford: Clarendon Press, 1951).
+"""
+    result = split_bibliography(draft)
+    assert len(result.entries) == 2
+    assert result.entries[0].startswith("Crum")
+    assert result.entries[1].startswith("Schulz")
+
+
+def test_running_headers_filtered():
+    """Short lines that are running headers or page footers (e.g. an
+    author surname or abbreviated title) are not entries."""
+    draft = """\
+## Bibliography
+
+Davidson, Donald. "On the Very Idea of a Conceptual Scheme."
+hedrick
+only words apart?
+217
+Frankenberry, Nancy. "Pragmatism, Truth, and Subjectivity" (1999).
+"""
+    result = split_bibliography(draft)
+    assert len(result.entries) == 2
+    assert result.entries[0].startswith("Davidson")
+    assert result.entries[1].startswith("Frankenberry")
 
 
 def test_no_bibliography_raises():
@@ -292,3 +480,83 @@ ________________
     assert len(result.definitions) == 3
     assert result.definitions[0].text == "First reference. https://example.org/path"
     assert result.definitions[2].text == "Rosen, 7."
+
+
+# --- find_blockquote_notes (> N text format, from PDF-to-markdown) ----------
+
+
+def test_find_blockquote_notes_single_definition():
+    draft = """\
+Some prose.
+
+> 1 Donald Davidson, "On the Very Idea of a Conceptual Scheme."
+"""
+    result = find_blockquote_notes(draft)
+    assert len(result.definitions) == 1
+    assert result.definitions[0].marker == "1"
+    assert result.definitions[0].text == 'Donald Davidson, "On the Very Idea of a Conceptual Scheme."'
+
+
+def test_find_blockquote_notes_multiple_in_order():
+    draft = """\
+> 1 First note.
+> 2 Second note.
+> 3 Third note.
+"""
+    result = find_blockquote_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_blockquote_notes_multi_digit_markers():
+    draft = "> 1 one.\n> 42 forty-two.\n> 88 eighty-eight.\n"
+    result = find_blockquote_notes(draft)
+    assert [d.marker for d in result.definitions] == ["1", "42", "88"]
+
+
+def test_find_blockquote_notes_returns_empty_when_no_definitions():
+    draft = "Just prose.\n> A regular blockquote with no number.\n"
+    result = find_blockquote_notes(draft)
+    assert result.definitions == []
+
+
+def test_find_blockquote_notes_records_line_number():
+    draft = """\
+Line zero.
+Line one.
+
+> 1 Note on line three.
+"""
+    result = find_blockquote_notes(draft)
+    assert result.definitions[0].line_number == 3
+
+
+def test_find_blockquote_notes_strips_trailing_whitespace():
+    draft = "> 1 Note text with trailing spaces.   \n"
+    result = find_blockquote_notes(draft)
+    assert result.definitions[0].text == "Note text with trailing spaces."
+
+
+def test_find_blockquote_notes_records_original_prefix():
+    """Reassembly prefix for blockquote format is ``'> N '``."""
+    draft = "> 1 text.\n> 88 text.\n"
+    result = find_blockquote_notes(draft)
+    assert result.definitions[0].original_prefix == "> 1 "
+    assert result.definitions[1].original_prefix == "> 88 "
+
+
+def test_find_blockquote_notes_ignores_non_numeric_blockquotes():
+    """A blockquote without a leading number is regular prose, not a note."""
+    draft = """\
+> This is a regular blockquote.
+> 1 This is a note.
+> Another regular blockquote.
+"""
+    result = find_blockquote_notes(draft)
+    assert len(result.definitions) == 1
+    assert result.definitions[0].marker == "1"