mirror of
https://github.com/turnstonelabs/turnstone.git
synced 2026-08-12 23:12:23 -06:00
33d16d19ce
* fix(renderer): handle LaTeX-style \(...\) and \[...\] math delimiters The browser renderer at turnstone/shared_static/renderer.js only recognized TeX-style $...$ / $$...$$ delimiters. Most modern LLMs (GPT-5 / o-series, Claude with reasoning effort) emit LaTeX-style \(...\) for inline math and \[...\] for display by default — those slipped through as raw text in the coord + interactive WebUIs, making KaTeX appear "broken when nested inside a markdown block" (actually broken everywhere, the surrounding markdown just made the failure noticeable). Added a second pass for each delimiter style alongside the existing $...$ / $$...$$ patterns. Both styles now feed the same mathBlocks / inlineMaths placeholder pipeline so all the existing nested-block handling (lists, blockquotes, tables, bold, headings, details, post-render KaTeX markup) Just Works. Edge cases verified by the new test_renderer_js.py harness: - \(...\) inside inline code stays literal - \(...\) inside fenced code blocks stays literal - Solo \[ with no closing \] doesn't trigger spurious math - Markdown links [text](url) untouched (regex uses \[ \], not [ ]) - Mixed TeX + LaTeX delimiters in one message both render The harness drives renderer.js through Node via vm.runInThisContext with stubbed document/katex globals — first JS-side regression guard for the renderer; previously it had no test coverage at all. * fix(renderer): apply Copilot feedback on PR #425 Three review items from Copilot: 1. Display-math sentinel could leak through inline-code spans. The original ordering ran $$...$$ / \[...\] extraction BEFORE inline code, so a backtick span around math (e.g. `$$x$$` or `\[x\]`) had its delimiters consumed by the math regex and replaced with \x00MB…\x00. Inline code then captured the sentinel; restore order put MB after IC, leaving the null-byte placeholder visible inside the rendered <code>. Reorder: inline code first, then display math, then inline math. Code spans now seal their content before any math regex sees it. The reverse edge case (math containing backticks, e.g. \verb|`x`|) is much rarer and KaTeX rejects \verb anyway. 2. Inline LaTeX-style \(...\) regex used [\s\S]+? which allowed newlines, so an unterminated \( on one line would eat the next paragraph until it found a closing \). Aligned with the existing $...$ behavior by switching to [^\n]+? — display math (\[...\] / $$...$$) stays multi-line by design. 3. tests/test_renderer_js.py was guarded with a node-availability skip, but CI's test + test-postgres jobs didn't explicitly install Node, so the suite would have silently no-op'd if the runner image dropped Node. Added actions/setup-node@v5 to both jobs. Four new regression tests cover the leak (both delimiter styles inside backticks must stay literal) and the cross-paragraph span (both \(...\) and $...$ must not eat newlines).
231 lines
7.8 KiB
Python
231 lines
7.8 KiB
Python
"""Smoke tests for ``turnstone/shared_static/renderer.js``.
|
|
|
|
The renderer is browser-only JS with no test framework on the project
|
|
side. These tests drive it through ``node`` against a minimal browser-
|
|
shim harness so a regression on the markdown / KaTeX wiring surfaces
|
|
in CI rather than at runtime in the operator's browser.
|
|
|
|
Each test invokes ``node -e`` with a small wrapper that loads
|
|
``utils.js`` + ``renderer.js`` via ``vm.runInThisContext``, stubs
|
|
``document`` / ``katex`` enough for the renderer to run, then prints
|
|
the rendered HTML for a sample input. The assertions check the
|
|
resulting markup contains the expected ``<span class="katex">…</span>``
|
|
placeholder and not the raw delimiter.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import json
|
|
import shutil
|
|
import subprocess
|
|
from pathlib import Path
|
|
|
|
import pytest
|
|
|
|
_REPO_ROOT = Path(__file__).resolve().parent.parent
|
|
_UTILS_JS = _REPO_ROOT / "turnstone/shared_static/utils.js"
|
|
_RENDERER_JS = _REPO_ROOT / "turnstone/shared_static/renderer.js"
|
|
|
|
|
|
def _has_node() -> bool:
|
|
return shutil.which("node") is not None
|
|
|
|
|
|
pytestmark = pytest.mark.skipif(not _has_node(), reason="node not available")
|
|
|
|
|
|
_HARNESS_TEMPLATE = """
|
|
const vm = require('vm');
|
|
const fs = require('fs');
|
|
global.document = {
|
|
createElement: () => {
|
|
let t = '';
|
|
return {
|
|
get textContent() { return t; },
|
|
set textContent(v) { t = v; },
|
|
get innerHTML() {
|
|
return t.replace(/&/g,'&').replace(/</g,'<').replace(/>/g,'>');
|
|
},
|
|
};
|
|
},
|
|
addEventListener: () => {},
|
|
};
|
|
global.katex = {
|
|
renderToString: (tex, opts) =>
|
|
'<span class="katex">[KATEX:' +
|
|
tex.replace(/\\n/g, '\\\\n') +
|
|
(opts.displayMode ? ':display' : ':inline') +
|
|
']</span>',
|
|
};
|
|
global.window = global;
|
|
vm.runInThisContext(fs.readFileSync(%(utils)s, 'utf8'));
|
|
vm.runInThisContext(fs.readFileSync(%(renderer)s, 'utf8'));
|
|
const input = %(input)s;
|
|
process.stdout.write(renderMarkdown(input));
|
|
"""
|
|
|
|
|
|
def _render(markdown: str) -> str:
|
|
"""Render ``markdown`` through renderer.js + return the HTML."""
|
|
harness = _HARNESS_TEMPLATE % {
|
|
"utils": json.dumps(str(_UTILS_JS)),
|
|
"renderer": json.dumps(str(_RENDERER_JS)),
|
|
"input": json.dumps(markdown),
|
|
}
|
|
result = subprocess.run(
|
|
["node", "-e", harness],
|
|
capture_output=True,
|
|
text=True,
|
|
timeout=10,
|
|
check=True,
|
|
)
|
|
return result.stdout
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# KaTeX delimiter handling — both TeX and LaTeX styles
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
|
def test_tex_inline_math_renders() -> None:
|
|
out = _render("The formula $E = mc^2$ is famous.")
|
|
assert '<span class="katex">' in out
|
|
assert "[KATEX:E = mc^2:inline]" in out
|
|
assert "$E = mc^2$" not in out # raw delimiters consumed
|
|
|
|
|
|
def test_tex_display_math_renders() -> None:
|
|
out = _render("$$\nE = mc^2\n$$")
|
|
assert '<span class="katex">' in out
|
|
assert ":display]" in out
|
|
|
|
|
|
def test_latex_inline_math_renders() -> None:
|
|
r"""LaTeX-style \(...\) inline math. GPT-5 / o-series / Claude
|
|
with reasoning effort emit this style by default; without
|
|
explicit support the model output passed through as raw \(x\)
|
|
text in coord + interactive UIs."""
|
|
out = _render(r"The formula \(E = mc^2\) is famous.")
|
|
assert '<span class="katex">' in out
|
|
assert "[KATEX:E = mc^2:inline]" in out
|
|
assert r"\(E = mc^2\)" not in out
|
|
|
|
|
|
def test_latex_display_math_renders() -> None:
|
|
r"""LaTeX-style \[...\] display math."""
|
|
out = _render("Intro\n\n\\[\nE = mc^2\n\\]\n\nMore")
|
|
assert '<span class="katex">' in out
|
|
assert ":display]" in out
|
|
assert "\\[" not in out
|
|
assert "\\]" not in out
|
|
|
|
|
|
def test_latex_math_in_list_item_renders() -> None:
|
|
"""Nested-in-markdown-block — the original bug report. The list
|
|
item is processed via line-by-line + inlineMarkdown; the math
|
|
placeholder must survive that path."""
|
|
out = _render(r"- Item with \(E = mc^2\) math")
|
|
assert "<li>" in out
|
|
assert '<span class="katex">' in out
|
|
assert "[KATEX:E = mc^2:inline]" in out
|
|
|
|
|
|
def test_latex_math_in_blockquote_renders() -> None:
|
|
out = _render(r"> Note: \(x^2\) is squared.")
|
|
assert "<blockquote>" in out
|
|
assert '<span class="katex">' in out
|
|
|
|
|
|
def test_latex_math_in_bold_renders() -> None:
|
|
out = _render(r"Then **\(x^2\)** end.")
|
|
assert "<strong>" in out
|
|
assert '<span class="katex">' in out
|
|
|
|
|
|
def test_mixed_tex_and_latex_styles() -> None:
|
|
out = _render(r"Here $x$ then \(y\) end.")
|
|
assert out.count('<span class="katex">') == 2
|
|
assert "[KATEX:x:inline]" in out
|
|
assert "[KATEX:y:inline]" in out
|
|
|
|
|
|
def test_latex_math_inside_inline_code_preserved() -> None:
|
|
r"""\(...\) inside inline code must NOT render as math —
|
|
code is escaped + left literal."""
|
|
out = _render(r"Code: `\(x\)` raw.")
|
|
assert r"<code>\(x\)</code>" in out
|
|
assert '<span class="katex">' not in out
|
|
|
|
|
|
def test_latex_math_inside_fenced_code_preserved() -> None:
|
|
r"""\(...\) inside a fenced block must stay literal."""
|
|
out = _render("```\nA \\(x\\) sample\n```")
|
|
assert "<pre><code>" in out
|
|
assert '<span class="katex">' not in out
|
|
|
|
|
|
def test_solo_escaped_bracket_does_not_render_as_math() -> None:
|
|
r"""A lone \[ with no matching \] is not math — it's a markdown
|
|
bracket escape. Don't hijack it."""
|
|
out = _render(r"No math: \[ alone.")
|
|
assert '<span class="katex">' not in out
|
|
|
|
|
|
def test_markdown_link_unaffected_by_math_protection() -> None:
|
|
r"""Math regex uses \[ / \] (escaped brackets), not bare [...].
|
|
Markdown links must still render."""
|
|
out = _render("See [docs](https://example.com).")
|
|
assert '<a href="https://example.com"' in out
|
|
assert ">docs</a>" in out
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Edge cases — Copilot review on PR #425
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
|
def test_display_math_inside_inline_code_stays_literal() -> None:
|
|
r"""``$$...$$`` inside backticks must NOT trigger display-math
|
|
extraction — otherwise the math sentinel ends up wrapped inside
|
|
the <code> placeholder and leaks into rendered HTML as a raw
|
|
null-byte sentinel string.
|
|
|
|
Pre-#425 ordering ran display-math before inline code, which
|
|
caused this leak. The reordering makes inline code seal first.
|
|
"""
|
|
out = _render(r"Use `$$x$$` for display math.")
|
|
assert "<code>$$x$$</code>" in out
|
|
assert '<span class="katex">' not in out
|
|
assert "\x00" not in out # no leaked sentinel
|
|
|
|
|
|
def test_latex_display_math_inside_inline_code_stays_literal() -> None:
|
|
r"""Same as above, but for the LaTeX-style \[...\] delimiter."""
|
|
out = _render(r"Use `\[x\]` for display math.")
|
|
assert r"<code>\[x\]</code>" in out
|
|
assert '<span class="katex">' not in out
|
|
assert "\x00" not in out
|
|
|
|
|
|
def test_inline_latex_math_does_not_span_paragraphs() -> None:
|
|
r"""An unterminated \(...\) on one line must not eat the
|
|
following paragraph until it finds a closing \) — that would
|
|
consume large chunks of text under streaming markdown where
|
|
the closer hasn't arrived yet. Mirrors the $...$ behavior."""
|
|
src = "Open \\(unterminated\n\nNext paragraph with \\(x\\) here."
|
|
out = _render(src)
|
|
# The bare \( on line 1 should NOT match; the well-formed \(x\)
|
|
# on the second paragraph should render normally.
|
|
assert out.count('<span class="katex">') == 1
|
|
assert "[KATEX:x:inline]" in out
|
|
# The "unterminated" stays as raw text.
|
|
assert "unterminated" in out
|
|
|
|
|
|
def test_inline_tex_math_does_not_span_newlines() -> None:
|
|
"""Existing $...$ behavior — regression guard."""
|
|
src = "Open $unterminated\n\nNext paragraph $x$ here."
|
|
out = _render(src)
|
|
assert out.count('<span class="katex">') == 1
|
|
assert "[KATEX:x:inline]" in out
|