Spaces:

HuggingAI4Engineering
/

CADGenBench

Running

Michael Rabinovich

app: render reports inline via iframe srcdoc (private-Space safe)

0e3b21f 5 months ago

7.06 kB

"""Unit tests for the report-proxy route and the inline iframe viewer.
The Space exposes two paths for the per-submission HTML report:
- ``/reports/{submission_id}.html`` (FastAPI route): re-serves the
  file with ``Content-Type: text/html``. Works under Bearer auth
  for programmatic clients; gets 404'd by HF's edge for logged-in
  browser users on a private Space (no auth carryover across
  same-origin pathname navigations). Kept as a backdoor / for the
  future public migration.
- ``_format_detail_and_report`` (row-click handler): server-side
  fetches the report via ``hf_hub_download`` and inlines it into
  an ``<iframe srcdoc=...>``. No browser HTTP request → no edge
  auth gate → renders for any logged-in user.
Tests stub the Hub fetch via monkeypatch so the suite has zero
network I/O.
"""
from __future__ import annotations

import re
import types

import pandas as pd

import app


def test_serve_report_returns_html_when_file_exists(monkeypatch):
    """Successful fetch -> 200 + text/html + body passthrough."""
    monkeypatch.setattr(
        app,
        "_fetch_report_html",
        lambda sid: b"<!DOCTYPE html><html><body>ok</body></html>",
    )
    resp = app.serve_report("sub-test")
    assert resp.status_code == 200
    assert resp.media_type.startswith("text/html")
    assert resp.body == b"<!DOCTYPE html><html><body>ok</body></html>"


def test_serve_report_returns_404_when_file_missing(monkeypatch):
    """``_fetch_report_html`` returning None -> 404 with a small html body."""
    monkeypatch.setattr(app, "_fetch_report_html", lambda sid: None)
    resp = app.serve_report("sub-missing")
    assert resp.status_code == 404
    # 404 body is still HTML so the browser renders the message.
    assert "Report not found" in resp.body.decode("utf-8")


def test_fetch_report_html_returns_none_on_hub_failure(monkeypatch):
    """A Hub-side exception is caught and surfaced as None.
    The serve handler relies on this to keep a transient Hub blip
    from leaking a stack trace into the Space's HTTP response.
    """
    def boom(*a, **kw):
        raise RuntimeError("simulated Hub failure")

    monkeypatch.setattr(app, "hf_hub_download", boom)
    # The lru_cache on _fetch_report_html caches by arg; use a unique
    # id per test so prior runs don't shortcut this one.
    assert app._fetch_report_html("sub-failure-probe-unique-1") is None


def test_proxy_route_is_registered():
    """The mounted FastAPI app exposes ``/reports/{submission_id}.html`` as GET.
    Catches the regression where the ``add_api_route`` call moves
    below ``mount_gradio_app`` (which would still register the route
    but make this regression silent until someone tries to hit it).
    """
    routes = [getattr(r, "path", None) for r in app.app.routes]
    assert "/reports/{submission_id}.html" in routes


# --- Inline iframe viewer (_format_detail_and_report) ----------------

def _stub_row(**overrides):
    base = {
        "submission_id": "sub-test-x",
        "submission_name": "Test Agent",
        "submitter_name": "team-test",
        "status": "completed",
        "submitted_at": "2026-05-26T12:02:31Z",
        "notes": None,
        "model details (optional)": "_None_",
        "submission_blob_url": "https://example.test/sub-test-x.zip",
        "report_url": "/reports/sub-test-x.html",
        "failure_reason": None,
    }
    base.update(overrides)
    return pd.DataFrame([base])


def _fake_evt(idx=0):
    """Minimal stand-in for gr.SelectData with the .index attr we read."""
    return types.SimpleNamespace(index=[idx, 0])


def test_iframe_viewer_inlines_report_for_modern_row(monkeypatch):
    """A completed modern row's HTML lands inside <iframe srcdoc>.
    Confirms the fetched bytes are HTML-escaped (so `<html>` is not
    re-parsed by the host page) and the iframe carries explicit
    sizing so Gradio's column flex can't clip it vertically.
    """
    monkeypatch.setattr(
        app, "_fetch_report_html",
        lambda sid: b"<!DOCTYPE html><body><h1>Report for " + sid.encode() + b"</h1></body>",
    )
    df = _stub_row()
    md, iframe = app._format_detail_and_report(df, _fake_evt())
    assert "### Test Agent" in md
    assert iframe.startswith('<iframe srcdoc="')
    # HTML-escaped content: literal "<!DOCTYPE html>" becomes
    # "&lt;!DOCTYPE html&gt;" inside the attribute.
    assert "&lt;!DOCTYPE html&gt;" in iframe
    assert "sub-test-x" in iframe
    assert 'style="width:100%; height:90vh; border:0; display:block;"' in iframe


def test_iframe_viewer_empty_for_pending_or_failed_row(monkeypatch):
    """Rows without a report_url get an empty viewer (no iframe at all).
    Pending: still evaluating; no report exists yet. Failed: eval
    crashed; no report uploaded. Legacy: pre-modern-pipeline; the
    file genuinely doesn't exist on the dataset. All three are
    handled by the same `report_url == ""` gate.
    """
    monkeypatch.setattr(app, "_fetch_report_html", lambda sid: b"unused")
    for row_overrides in [
        {"status": "pending", "report_url": ""},
        {"status": "failed", "report_url": "", "failure_reason": "boom"},
        {"status": "completed", "report_url": ""},  # legacy
    ]:
        df = _stub_row(**row_overrides)
        md, iframe = app._format_detail_and_report(df, _fake_evt())
        assert iframe == "", f"expected empty viewer for {row_overrides}"
        # The metadata panel still renders.
        assert "### Test Agent" in md


def test_iframe_viewer_falls_back_to_empty_when_fetch_fails(monkeypatch):
    """If _fetch_report_html returns None (Hub blip), no iframe is emitted.
    Avoids surfacing a broken iframe on a transient failure.
    """
    monkeypatch.setattr(app, "_fetch_report_html", lambda sid: None)
    df = _stub_row()
    _md, iframe = app._format_detail_and_report(df, _fake_evt())
    assert iframe == ""


def test_iframe_viewer_returns_placeholder_on_null_event():
    """A null SelectData (no row clicked) returns placeholder + empty viewer."""
    df = _stub_row()
    fake = types.SimpleNamespace(index=None)
    md, iframe = app._format_detail_and_report(df, fake)
    assert md == app.DETAIL_PLACEHOLDER
    assert iframe == ""


def test_iframe_escape_is_attribute_safe(monkeypatch):
    """Quotes / ampersands inside the report HTML are escaped properly.
    A `"` inside the report would otherwise terminate the srcdoc
    attribute prematurely and break parsing. Regression guard.
    """
    monkeypatch.setattr(
        app, "_fetch_report_html",
        lambda sid: b'<html><body>tag: <a href="https://x.test">x</a> & co.</body></html>',
    )
    df = _stub_row()
    _md, iframe = app._format_detail_and_report(df, _fake_evt())
    # Within the srcdoc value, double-quotes must be HTML-escaped.
    srcdoc = re.search(r'srcdoc="(.*)"\s+style=', iframe, re.DOTALL)
    assert srcdoc is not None
    inner = srcdoc.group(1)
    # No unescaped " inside the attribute value.
    assert '"' not in inner
    assert "&quot;" in inner
    assert "&amp;" in inner

	"""Unit tests for the report-proxy route and the inline iframe viewer.

	The Space exposes two paths for the per-submission HTML report:

	- ``/reports/{submission_id}.html`` (FastAPI route): re-serves the
	file with ``Content-Type: text/html``. Works under Bearer auth
	for programmatic clients; gets 404'd by HF's edge for logged-in
	browser users on a private Space (no auth carryover across
	same-origin pathname navigations). Kept as a backdoor / for the
	future public migration.
	- ``_format_detail_and_report`` (row-click handler): server-side
	fetches the report via ``hf_hub_download`` and inlines it into
	an ``<iframe srcdoc=...>``. No browser HTTP request → no edge
	auth gate → renders for any logged-in user.

	Tests stub the Hub fetch via monkeypatch so the suite has zero
	network I/O.
	"""
	from __future__ import annotations

	import re
	import types

	import pandas as pd

	import app


	def test_serve_report_returns_html_when_file_exists(monkeypatch):
	"""Successful fetch -> 200 + text/html + body passthrough."""
	monkeypatch.setattr(
	app,
	"_fetch_report_html",
	lambda sid: b"<!DOCTYPE html><html><body>ok</body></html>",
	)
	resp = app.serve_report("sub-test")
	assert resp.status_code == 200
	assert resp.media_type.startswith("text/html")
	assert resp.body == b"<!DOCTYPE html><html><body>ok</body></html>"


	def test_serve_report_returns_404_when_file_missing(monkeypatch):
	"""``_fetch_report_html`` returning None -> 404 with a small html body."""
	monkeypatch.setattr(app, "_fetch_report_html", lambda sid: None)
	resp = app.serve_report("sub-missing")
	assert resp.status_code == 404
	# 404 body is still HTML so the browser renders the message.
	assert "Report not found" in resp.body.decode("utf-8")


	def test_fetch_report_html_returns_none_on_hub_failure(monkeypatch):
	"""A Hub-side exception is caught and surfaced as None.

	The serve handler relies on this to keep a transient Hub blip
	from leaking a stack trace into the Space's HTTP response.
	"""
	def boom(a, *kw):
	raise RuntimeError("simulated Hub failure")

	monkeypatch.setattr(app, "hf_hub_download", boom)
	# The lru_cache on _fetch_report_html caches by arg; use a unique
	# id per test so prior runs don't shortcut this one.
	assert app._fetch_report_html("sub-failure-probe-unique-1") is None


	def test_proxy_route_is_registered():
	"""The mounted FastAPI app exposes ``/reports/{submission_id}.html`` as GET.

	Catches the regression where the ``add_api_route`` call moves
	below ``mount_gradio_app`` (which would still register the route
	but make this regression silent until someone tries to hit it).
	"""
	routes = [getattr(r, "path", None) for r in app.app.routes]
	assert "/reports/{submission_id}.html" in routes


	# --- Inline iframe viewer (_format_detail_and_report) ----------------

	def _stub_row(**overrides):
	base = {
	"submission_id": "sub-test-x",
	"submission_name": "Test Agent",
	"submitter_name": "team-test",
	"status": "completed",
	"submitted_at": "2026-05-26T12:02:31Z",
	"notes": None,
	"model details (optional)": "_None_",
	"submission_blob_url": "https://example.test/sub-test-x.zip",
	"report_url": "/reports/sub-test-x.html",
	"failure_reason": None,
	}
	base.update(overrides)
	return pd.DataFrame([base])


	def _fake_evt(idx=0):
	"""Minimal stand-in for gr.SelectData with the .index attr we read."""
	return types.SimpleNamespace(index=[idx, 0])


	def test_iframe_viewer_inlines_report_for_modern_row(monkeypatch):
	"""A completed modern row's HTML lands inside <iframe srcdoc>.

	Confirms the fetched bytes are HTML-escaped (so `<html>` is not
	re-parsed by the host page) and the iframe carries explicit
	sizing so Gradio's column flex can't clip it vertically.
	"""
	monkeypatch.setattr(
	app, "_fetch_report_html",
	lambda sid: b"<!DOCTYPE html><body><h1>Report for " + sid.encode() + b"</h1></body>",
	)
	df = _stub_row()
	md, iframe = app._format_detail_and_report(df, _fake_evt())
	assert "### Test Agent" in md
	assert iframe.startswith('<iframe srcdoc="')
	# HTML-escaped content: literal "<!DOCTYPE html>" becomes
	# "<!DOCTYPE html>" inside the attribute.
	assert "<!DOCTYPE html>" in iframe
	assert "sub-test-x" in iframe
	assert 'style="width:100%; height:90vh; border:0; display:block;"' in iframe


	def test_iframe_viewer_empty_for_pending_or_failed_row(monkeypatch):
	"""Rows without a report_url get an empty viewer (no iframe at all).

	Pending: still evaluating; no report exists yet. Failed: eval
	crashed; no report uploaded. Legacy: pre-modern-pipeline; the
	file genuinely doesn't exist on the dataset. All three are
	handled by the same `report_url == ""` gate.
	"""
	monkeypatch.setattr(app, "_fetch_report_html", lambda sid: b"unused")
	for row_overrides in [
	{"status": "pending", "report_url": ""},
	{"status": "failed", "report_url": "", "failure_reason": "boom"},
	{"status": "completed", "report_url": ""}, # legacy
	]:
	df = _stub_row(**row_overrides)
	md, iframe = app._format_detail_and_report(df, _fake_evt())
	assert iframe == "", f"expected empty viewer for {row_overrides}"
	# The metadata panel still renders.
	assert "### Test Agent" in md


	def test_iframe_viewer_falls_back_to_empty_when_fetch_fails(monkeypatch):
	"""If _fetch_report_html returns None (Hub blip), no iframe is emitted.

	Avoids surfacing a broken iframe on a transient failure.
	"""
	monkeypatch.setattr(app, "_fetch_report_html", lambda sid: None)
	df = _stub_row()
	_md, iframe = app._format_detail_and_report(df, _fake_evt())
	assert iframe == ""


	def test_iframe_viewer_returns_placeholder_on_null_event():
	"""A null SelectData (no row clicked) returns placeholder + empty viewer."""
	df = _stub_row()
	fake = types.SimpleNamespace(index=None)
	md, iframe = app._format_detail_and_report(df, fake)
	assert md == app.DETAIL_PLACEHOLDER
	assert iframe == ""


	def test_iframe_escape_is_attribute_safe(monkeypatch):
	"""Quotes / ampersands inside the report HTML are escaped properly.

	A `"` inside the report would otherwise terminate the srcdoc
	attribute prematurely and break parsing. Regression guard.
	"""
	monkeypatch.setattr(
	app, "_fetch_report_html",
	lambda sid: b'<html><body>tag: <a href="https://x.test">x</a> & co.</body></html>',
	)
	df = _stub_row()
	_md, iframe = app._format_detail_and_report(df, _fake_evt())
	# Within the srcdoc value, double-quotes must be HTML-escaped.
	srcdoc = re.search(r'srcdoc="(.*)"\s+style=', iframe, re.DOTALL)
	assert srcdoc is not None
	inner = srcdoc.group(1)
	# No unescaped " inside the attribute value.
	assert '"' not in inner
	assert """ in inner
	assert "&" in inner