v2 chunk 2b: cli format-notes subcommand and reformat_notes()
Wire the v2 note formatter into the CLI so it can be invoked on real markdown drafts. The format-notes subcommand mirrors v1's format subcommand: parser → formatter → reassemble, with concurrent API calls. src/cmos/cli.py: - Import find_notes and format_note_entry alongside the existing v1 imports. - Add reformat_notes(text, formatter, concurrency) that finds pandoc-style markdown footnote definitions via find_notes, formats each definition's text via the v2 note formatter (or an injected fake), and substitutes the formatted text back into the original line position. Non-definition lines preserved byte-for-byte. Returns text unchanged when no definitions found. - Register the format-notes argparse subparser with the same --concurrency flag as v1's format. - Dispatch args.command == "format-notes" to reformat_notes. - Module docstring updated to document both subcommands. tests/test_cli.py: - 7 new tests for reformat_notes covering: in-place substitution, order preservation under concurrency, prose preservation, reference markers staying verbatim, no-op on empty input, trailing newline preservation. - Extended test_python_dash_m_invocation_actually_runs_main to also assert "format-notes" appears in --help, catching accidental subcommand removal. Path B integrity: formatter.py, note_formatter.py, parser.py, linter.py, harness/score.py all unchanged. No LINTER_VERSION bump. 96/96 v1 tests still passing. Total suite: 123/123. Real-API end-to-end smoke test on a temp draft with 2 footnote definitions: both reformatted byte-for-byte, prose and headings preserved, ## Conclusion section after the notes preserved.
This commit is contained in:
+126
-1
@@ -3,6 +3,10 @@
|
||||
The CLI orchestrates parser → formatter → reassemble. Tests inject a fake
|
||||
formatter so no API calls happen; the goal is to pin the glue logic, not the
|
||||
LLM behavior.
|
||||
|
||||
v1: ``reformat_draft`` rewrites the ``## Bibliography`` section.
|
||||
v2: ``reformat_notes`` rewrites pandoc-style markdown footnote definitions
|
||||
in place by line number, preserving everything else byte-for-byte.
|
||||
"""
|
||||
|
||||
import subprocess
|
||||
@@ -11,7 +15,7 @@ from pathlib import Path
|
||||
|
||||
import pytest
|
||||
|
||||
from cmos.cli import reformat_draft
|
||||
from cmos.cli import reformat_draft, reformat_notes
|
||||
from cmos.parser import NoBibliographyError
|
||||
|
||||
|
||||
@@ -80,6 +84,10 @@ def test_python_dash_m_invocation_actually_runs_main():
|
||||
the worst kind of bug, since callers assume the pipeline ran. This
|
||||
test forces the guard to exist by invoking the CLI as a subprocess
|
||||
with --help and asserting argparse actually fired.
|
||||
|
||||
Also acts as a smoke test for both subcommands appearing in the
|
||||
top-level help: catches the case where a future refactor removes
|
||||
a subcommand registration without anyone noticing.
|
||||
"""
|
||||
result = subprocess.run(
|
||||
[sys.executable, "-m", "cmos.cli", "--help"],
|
||||
@@ -98,9 +106,126 @@ def test_python_dash_m_invocation_actually_runs_main():
|
||||
'`if __name__ == "__main__": sys.exit(main())` guard at the bottom.'
|
||||
)
|
||||
assert "format" in result.stdout
|
||||
assert "format-notes" in result.stdout
|
||||
assert "usage" in result.stdout.lower()
|
||||
|
||||
|
||||
# --- reformat_notes (v2 CLI plumbing) ----------------------------------------
|
||||
|
||||
|
||||
def _fake_note_formatter(messy: str) -> str:
|
||||
# Deterministic fake mirroring the v1 fake_formatter pattern.
|
||||
return f"NOTE_FORMATTED({messy.strip()})"
|
||||
|
||||
|
||||
def test_reformat_notes_substitutes_definition_in_place():
|
||||
draft = """\
|
||||
Some prose with a citation.[^1]
|
||||
|
||||
[^1]: yu, charles. interior chinatown. 2020. p 45.
|
||||
"""
|
||||
output = reformat_notes(draft, formatter=_fake_note_formatter)
|
||||
assert "Some prose with a citation.[^1]" in output
|
||||
assert "[^1]: NOTE_FORMATTED(yu, charles. interior chinatown. 2020. p 45.)" in output
|
||||
# The original messy definition line must be gone.
|
||||
assert "[^1]: yu, charles" not in output
|
||||
|
||||
|
||||
def test_reformat_notes_rewrites_multiple_definitions_in_order():
|
||||
draft = """\
|
||||
Prose.[^1] More.[^2] Again.[^3]
|
||||
|
||||
[^1]: first messy.
|
||||
[^2]: second messy.
|
||||
[^3]: third messy.
|
||||
"""
|
||||
output = reformat_notes(draft, formatter=_fake_note_formatter)
|
||||
assert "[^1]: NOTE_FORMATTED(first messy.)" in output
|
||||
assert "[^2]: NOTE_FORMATTED(second messy.)" in output
|
||||
assert "[^3]: NOTE_FORMATTED(third messy.)" in output
|
||||
|
||||
|
||||
def test_reformat_notes_preserves_non_definition_lines():
|
||||
draft = """\
|
||||
# Title
|
||||
|
||||
Some prose with a citation.[^1]
|
||||
|
||||
More prose, no citation here.
|
||||
|
||||
[^1]: messy definition.
|
||||
|
||||
Conclusion paragraph.
|
||||
"""
|
||||
output = reformat_notes(draft, formatter=_fake_note_formatter)
|
||||
assert "# Title" in output
|
||||
assert "Some prose with a citation.[^1]" in output
|
||||
assert "More prose, no citation here." in output
|
||||
assert "Conclusion paragraph." in output
|
||||
assert "[^1]: NOTE_FORMATTED(messy definition.)" in output
|
||||
|
||||
|
||||
def test_reformat_notes_preserves_reference_markers_in_prose():
|
||||
"""The [^1] reference inside the prose must NOT be touched — only
|
||||
the [^1]: definition line should be reformatted."""
|
||||
draft = """\
|
||||
Some prose with a citation.[^1] And another.[^2]
|
||||
|
||||
[^1]: first.
|
||||
[^2]: second.
|
||||
"""
|
||||
output = reformat_notes(draft, formatter=_fake_note_formatter)
|
||||
# References in prose stay verbatim
|
||||
assert "Some prose with a citation.[^1] And another.[^2]" in output
|
||||
# Definitions are reformatted
|
||||
assert "[^1]: NOTE_FORMATTED(first.)" in output
|
||||
assert "[^2]: NOTE_FORMATTED(second.)" in output
|
||||
|
||||
|
||||
def test_reformat_notes_returns_unchanged_when_no_definitions():
|
||||
draft = "Just prose with no footnote definitions.\n"
|
||||
output = reformat_notes(draft, formatter=_fake_note_formatter)
|
||||
assert output == draft
|
||||
|
||||
|
||||
def test_reformat_notes_preserves_trailing_newline():
|
||||
with_trailing = "[^1]: messy.\n"
|
||||
without_trailing = "[^1]: messy."
|
||||
assert reformat_notes(with_trailing, formatter=_fake_note_formatter).endswith("\n")
|
||||
assert not reformat_notes(without_trailing, formatter=_fake_note_formatter).endswith("\n")
|
||||
|
||||
|
||||
def test_reformat_notes_preserves_order_under_concurrency():
|
||||
"""With concurrent execution the formatter is called on all definitions
|
||||
in parallel; the output must reassemble them in input order regardless
|
||||
of which call finishes first. Mirrors the v1 order-preservation test."""
|
||||
import time
|
||||
|
||||
def slow_fake(messy: str) -> str:
|
||||
# Earlier definitions sleep longer so they finish last under naive
|
||||
# completion-order tracking.
|
||||
n = int(messy.split()[-1])
|
||||
time.sleep(0.05 * (5 - n))
|
||||
return f"NOTE_FORMATTED({messy})"
|
||||
|
||||
draft = """\
|
||||
Prose.
|
||||
|
||||
[^1]: definition 0
|
||||
[^2]: definition 1
|
||||
[^3]: definition 2
|
||||
[^4]: definition 3
|
||||
[^5]: definition 4
|
||||
"""
|
||||
output = reformat_notes(draft, formatter=slow_fake, concurrency=4)
|
||||
# Check order: each marker should be paired with its correct definition.
|
||||
assert "[^1]: NOTE_FORMATTED(definition 0)" in output
|
||||
assert "[^2]: NOTE_FORMATTED(definition 1)" in output
|
||||
assert "[^3]: NOTE_FORMATTED(definition 2)" in output
|
||||
assert "[^4]: NOTE_FORMATTED(definition 3)" in output
|
||||
assert "[^5]: NOTE_FORMATTED(definition 4)" in output
|
||||
|
||||
|
||||
def test_reformat_draft_preserves_order_under_concurrency():
|
||||
# With concurrent execution the formatter is called on all entries in
|
||||
# parallel; the CLI must reassemble them in input order regardless of
|
||||
|
||||
Reference in New Issue
Block a user