Merge lab into refactor/split-style-css

tests/helpers/document_source.py

@@ -0,0 +1,288 @@
+"""Read the document editor's JavaScript the way the browser loads it.
+
+``static/js/document.js`` is being decomposed. It stays the entry point the
+browser requests -- ``static/index.html`` names it, ``static/sw.js`` precaches
+it, and five modules import it -- but the implementation moves into modules
+under ``static/js/document/``. The implementation set is the entry plus that
+directory.
+
+Two habits in the existing tests do not survive that move, and this module
+exists to replace both.
+
+**Reading the entry file alone.** A membership assertion against
+``document.js`` silently covers less the moment the behaviour it names moves
+out. Use :func:`document_source` for those: it is the whole implementation set,
+so a test keeps finding what it asserts on wherever the code lands.
+
+**Slicing between two adjacent functions.** ``function_body("a")`` means "the region between a and b", which is only
+the body of ``a`` while ``a`` and ``b`` happen to be neighbours in one file.
+After a split they may sit in different modules, and then the slice runs to the
+end of the concatenation and quietly grows: an ``assert "x" in region`` passes
+against code it was never meant to see. Several of these also hard-code the
+entry file's two-space indentation (``"\\n  function showDocTabMenu"``), which
+no extracted module reproduces. Use :func:`function_body` or
+:func:`declaration` instead -- they find the construct by name, in whichever
+module defines it, and end at its real closing brace.
+"""
+
+from __future__ import annotations
+
+import re
+from pathlib import Path
+
+_STATIC = Path(__file__).resolve().parents[2] / "static"
+_ENTRY = _STATIC / "js" / "document.js"
+
+# Extracted implementation modules get one home, so the set is discoverable
+# without a manifest anyone has to remember to update.
+_IMPL_DIR = _STATIC / "js" / "document"
+
+
+def document_source_paths() -> list[Path]:
+    """Every file holding document-editor implementation, entry first.
+
+    The entry comes first so a concatenation reads in the order the browser
+    evaluates the graph's root; the rest are sorted for determinism.
+    """
+    if not _ENTRY.is_file():
+        raise AssertionError(f"document editor entry point is missing: {_ENTRY}")
+    extracted = sorted(_IMPL_DIR.rglob("*.js")) if _IMPL_DIR.is_dir() else []
+    return [_ENTRY, *extracted]
+
+
+def document_source() -> str:
+    """The whole implementation set as one string, entry first.
+
+    For membership assertions (``assert "..." in document_source()``). For
+    anything positional use :func:`function_body` or :func:`declaration`.
+    """
+    return "\n".join(p.read_text(encoding="utf-8") for p in document_source_paths())
+
+
+# --- Locating a construct by name, not by what follows it ------------------
+
+def _defining_source(pattern: re.Pattern[str], what: str) -> tuple[str, int]:
+    """The source text that defines ``what``, and the offset of the match."""
+    hits = []
+    for path in document_source_paths():
+        src = path.read_text(encoding="utf-8")
+        for m in pattern.finditer(src):
+            hits.append((path, src, m.start()))
+    if not hits:
+        raise AssertionError(f"{what} is not defined anywhere in {_describe_set()}")
+    if len(hits) > 1:
+        where = ", ".join(
+            f"{p.relative_to(_STATIC.parent)}:{s.count(chr(10), 0, o) + 1}"
+            for p, s, o in hits
+        )
+        raise AssertionError(f"{what} is defined more than once ({where})")
+    _path, src, offset = hits[0]
+    return src, offset
+
+
+def _describe_set() -> str:
+    return ", ".join(str(p.relative_to(_STATIC.parent)) for p in document_source_paths())
+
+
+def function_body(name: str) -> str:
+    """The full text of function ``name``, signature through closing brace.
+
+    Matches ``function name``, optionally prefixed by ``export`` and/or
+    ``async``, at any indentation, in whichever module of the implementation
+    set defines it. The end is found by matching braces rather than by naming
+    whatever declaration follows, so moving the function -- or the one after
+    it -- does not change the region a test sees.
+    """
+    pattern = re.compile(
+        r"^[ \t]*(?:export\s+)?(?:async\s+)?function\s+" + re.escape(name) + r"\s*\(",
+        re.M,
+    )
+    src, offset = _defining_source(pattern, f"function {name}")
+    # Skip the parameter list before looking for the body. A destructured
+    # parameter -- `function f(table, { headerRow, headerColumn })` -- opens a
+    # brace that is not the body, and matching it would return the signature
+    # alone.
+    body_start = _end_of_params(src, src.index("(", offset))
+    return src[offset : _end_of_block(src, body_start)]
+
+
+def declaration(name: str) -> str:
+    """The full text of a top-level ``const``/``let``/``var`` named ``name``.
+
+    For the array and object tables the tests assert on (toolbar groups, slash
+    commands, input rules). Ends at the declaration's closing bracket or brace,
+    or at the end of the statement for a simple initialiser.
+    """
+    pattern = re.compile(
+        r"^[ \t]*(?:export\s+)?(?:const|let|var)\s+" + re.escape(name) + r"\b",
+        re.M,
+    )
+    src, offset = _defining_source(pattern, f"declaration {name}")
+    return src[offset : _end_of_statement(src, offset)]
+
+
+# --- A brace matcher that is not fooled by braces inside literals ----------
+#
+# `document.js` is full of template literals building DOM, regexes containing
+# braces, and apostrophes inside comments. Counting raw `{`/`}` mis-slices on
+# all three, so the scan tracks what kind of text it is inside.
+
+# After one of these, `/` starts a regex literal; after a value it is division.
+_REGEX_OK_BEFORE = re.compile(r"[({\[,;:=!&|?+\-*~^%<>]\s*$|\b(?:return|typeof|case|in|of|new|delete|void|do|else|yield|await)\s*$")
+
+
+def _scan(src: str, start: int, stop):
+    """Walk ``src`` from ``start``, skipping literals and comments.
+
+    Calls ``stop(index, depth_delta_applied)``-free: instead it yields
+    ``(index, char)`` for code positions only, so callers can track nesting.
+    """
+    i, n = start, len(src)
+    # Stack of template-literal depths: entering `${` pushes brace depth.
+    template_stack: list[int] = []
+    while i < n:
+        c = src[i]
+        two = src[i : i + 2]
+        if two == "//":
+            j = src.find("\n", i)
+            i = n if j == -1 else j + 1
+            continue
+        if two == "/*":
+            j = src.find("*/", i + 2)
+            i = n if j == -1 else j + 2
+            continue
+        if c in "'\"":
+            i = _skip_quoted(src, i, c)
+            continue
+        if c == "`":
+            i += 1
+            i, entered = _skip_template(src, i)
+            if entered:
+                template_stack.append(0)
+            continue
+        if c == "/" and _REGEX_OK_BEFORE.search(src[max(0, i - 24) : i]):
+            j = _skip_regex(src, i)
+            if j is not None:
+                i = j
+                continue
+        if template_stack:
+            # Inside `${ ... }`: a `}` that closes it returns to template text.
+            if c == "{":
+                template_stack[-1] += 1
+            elif c == "}":
+                if template_stack[-1] == 0:
+                    template_stack.pop()
+                    i += 1
+                    i, entered = _skip_template(src, i)
+                    if entered:
+                        template_stack.append(0)
+                    continue
+                template_stack[-1] -= 1
+        yield i, c
+        i += 1
+
+
+def _skip_quoted(src: str, i: int, quote: str) -> int:
+    i += 1
+    n = len(src)
+    while i < n:
+        if src[i] == "\\":
+            i += 2
+            continue
+        if src[i] == quote:
+            return i + 1
+        if src[i] == "\n":  # unterminated; do not run away
+            return i
+        i += 1
+    return n
+
+
+def _skip_template(src: str, i: int) -> tuple[int, bool]:
+    """From inside template text, advance to the backtick end or a ``${``.
+
+    Returns the new index and whether an interpolation was entered.
+    """
+    n = len(src)
+    while i < n:
+        if src[i] == "\\":
+            i += 2
+            continue
+        if src[i] == "`":
+            return i + 1, False
+        if src[i : i + 2] == "${":
+            return i + 2, True
+        i += 1
+    return n, False
+
+
+def _skip_regex(src: str, i: int) -> int | None:
+    """Past a regex literal starting at ``i``, or None if it is not one."""
+    i += 1
+    n = len(src)
+    in_class = False
+    while i < n:
+        c = src[i]
+        if c == "\\":
+            i += 2
+            continue
+        if c == "\n":
+            return None
+        if in_class:
+            if c == "]":
+                in_class = False
+        elif c == "[":
+            in_class = True
+        elif c == "/":
+            i += 1
+            while i < n and src[i].isalpha():  # flags
+                i += 1
+            return i
+        i += 1
+    return None
+
+
+def _end_of_block(src: str, start: int) -> int:
+    """Index just past the ``}`` closing the first ``{`` at or after ``start``."""
+    depth = 0
+    seen = False
+    for i, c in _scan(src, start, None):
+        if c == "{":
+            depth += 1
+            seen = True
+        elif c == "}":
+            depth -= 1
+            if seen and depth == 0:
+                return i + 1
+    raise AssertionError(f"unbalanced braces from offset {start}")
+
+
+def _end_of_statement(src: str, start: int) -> int:
+    """Index just past the end of the declaration statement at ``start``.
+
+    Ends on the ``;`` or newline that closes it at nesting depth zero, so an
+    array or object initialiser is returned whole.
+    """
+    depth = 0
+    for i, c in _scan(src, start, None):
+        if c in "{[(":
+            depth += 1
+        elif c in "}])":
+            depth -= 1
+        elif depth == 0 and c == ";":
+            return i + 1
+        elif depth == 0 and c == "\n" and i > start:
+            return i
+    return len(src)
+
+
+def _end_of_params(src: str, open_paren: int) -> int:
+    """Index just past the ``)`` closing the parameter list at ``open_paren``."""
+    depth = 0
+    for i, c in _scan(src, open_paren, None):
+        if c == "(":
+            depth += 1
+        elif c == ")":
+            depth -= 1
+            if depth == 0:
+                return i + 1
+    raise AssertionError(f"unbalanced parameter list at offset {open_paren}")

tests/helpers/import_state.py

@@ -31,6 +31,7 @@ safe for callers that pass both a parent package and a child module.
 """
 
 import sys
+import types
 from contextlib import contextmanager
 
 _ABSENT = object()
@@ -167,3 +168,33 @@ def preserve_import_state(*module_names):
         # Phase 2: restore all parent-package attributes.
         for name, (_, saved_attr) in saved.items():
             _restore_parent_attr(name, saved_attr)
+
+
+# Names under these prefixes are the ones a leaked stub actually breaks: a
+# later test doing ``import src.x`` or ``import core.x`` silently gets the
+# empty stub instead of the real module.
+_GUARDED_PREFIXES = ("src.", "core.")
+
+
+def bare_module_stubs():
+    """Return the ``src.*``/``core.*`` names currently bound to a bare stub.
+
+    A bare stub is a plain :class:`types.ModuleType` with no on-disk
+    ``__file__`` — the object ``types.ModuleType(name)`` produces. That is the
+    same "is this a fake?" test the ``clear_fake_*`` helpers above use, so a
+    module imported from disk is never reported.
+
+    ``MagicMock`` stand-ins are deliberately out of scope: they answer every
+    attribute, so they fail loudly at use rather than silently, and several
+    test modules install them on purpose.
+    """
+    found = set()
+    for name, mod in list(sys.modules.items()):
+        if not name.startswith(_GUARDED_PREFIXES):
+            continue
+        if type(mod) is not types.ModuleType:
+            continue
+        if getattr(mod, "__file__", None):
+            continue
+        found.add(name)
+    return found

tests/helpers/stylesheets.mjs

@@ -0,0 +1,67 @@
+import { readFile } from 'node:fs/promises';
+import { dirname, join } from 'node:path';
+import { fileURLToPath } from 'node:url';
+
+const HERE = dirname(fileURLToPath(import.meta.url));
+const STATIC = join(HERE, '..', '..', 'static');
+const INDEX = join(STATIC, 'index.html');
+
+const LINK = /<link\b[^>]*\brel\s*=\s*["']stylesheet["'][^>]*\bhref\s*=\s*["']\/static\/([^"'?]+)([^"']*)["']/gi;
+
+async function entries() {
+  const html = await readFile(INDEX, 'utf8');
+  const out = [];
+
+  for (const match of html.matchAll(LINK)) {
+    const rel = match[1];
+    const query = match[2];
+
+    if (rel.startsWith('lib/')) continue;
+
+    out.push({
+      path: join(STATIC, rel),
+      url: `/static/${rel}${query}`,
+    });
+  }
+
+  if (!out.length) {
+    throw new Error(`no app stylesheet <link> tags found in ${INDEX}`);
+  }
+
+  for (const entry of out) {
+    try {
+      await readFile(entry.path);
+    } catch {
+      throw new Error(
+        `index.html links a stylesheet that does not exist: ${entry.path}`,
+      );
+    }
+  }
+
+  return out;
+}
+
+export async function stylesheetPaths() {
+  return (await entries()).map(entry => entry.path);
+}
+
+export async function stylesheetUrls() {
+  return (await entries()).map(entry => entry.url);
+}
+
+export async function stylesheetLinkTags() {
+  return (await stylesheetUrls())
+    .map(url => `<link rel="stylesheet" href="${url}">`)
+    .join('');
+}
+
+export async function appCss() {
+  const paths = await stylesheetPaths();
+  const parts = [];
+
+  for (const path of paths) {
+    parts.push(await readFile(path, 'utf8'));
+  }
+
+  return parts.join('\n');
+}

tests/helpers/stylesheets.py

@@ -1,11 +1,11 @@
 """Read the app's CSS the way the browser does.
 
-``static/style.css`` no longer holds every rule: panel styles live in separate
-files that ``static/index.html`` loads eagerly, in a fixed order, right after
-it. The cascade is the concatenation of those files in that order.
+The former ``static/style.css`` is now an ordered set of numbered fragments,
+followed by the existing panel stylesheets. ``static/index.html`` loads the
+complete cascade eagerly in the order the browser must apply it.
 
-A test that asserts on a rule must therefore look at all of them. Reading
-``static/style.css`` alone ties the test to whichever file a rule happens to
+A test that asserts on a rule must therefore look at the complete cascade.
+Reading one fragment alone ties the test to whichever file a rule happens to
 sit in today, so it goes red the next time a rule moves without anything about
 the rendered page having changed.
 """
@@ -53,8 +53,7 @@ def stylesheet_urls() -> list[str]:
 
 
 def stylesheet_link_tags() -> str:
-    """The <link> tags to drop into a synthetic page so it gets the whole
-    cascade, not just style.css."""
+    """The <link> tags for a synthetic page that needs the whole cascade."""
     return "".join(f'<link rel="stylesheet" href="{u}">' for u in stylesheet_urls())
 
 
@@ -68,8 +67,8 @@ def stylesheet_cache_version() -> str:
 
     The stylesheet is split across several files that must be busted together:
     shipping one fragment under a stale token serves a browser half of an old
-    cascade and half of a new one. Tests that used to read the version off
-    ``style.css`` ask for it here instead, so they keep checking the invariant
+    cascade and half of a new one. Tests ask for the shared version here instead of deriving it from one
+    stylesheet filename, so they keep checking the invariant
     rather than a filename.
     """
     versions = set()

tests/helpers/unix_sockets.py

@@ -0,0 +1,46 @@
+"""Bind an AF_UNIX socket at a path the kernel will actually accept.
+
+``sun_path`` is 104 bytes on macOS, terminator included, so a bind path longer
+than 103 characters fails with ``OSError: AF_UNIX path too long``. pytest's
+``tmp_path`` is rooted at ``$TMPDIR``, which on stock macOS is a 49-character
+``/var/folders/<2>/<30>/T/`` path; adding ``pytest-of-<user>/pytest-<n>/`` and
+the test's own (truncated) name spends the rest of the budget before the
+filename is appended.
+
+That is why this reads as flaky rather than broken. Linux allows 108 bytes and
+roots ``$TMPDIR`` at ``/tmp``, so it never bites there; on macOS whether it
+bites depends on the length of ``$TMPDIR``, the test's name, and how many
+digits pytest's run counter is currently using. A run under a shortened
+``$TMPDIR`` passes, the same checkout under the default one does not.
+
+The path is resolved before it is handed back, for the same reason the rest of
+this change resolves temp paths: on macOS ``/tmp`` is a symlink to
+``/private/tmp``, and a test that binds one spelling and asserts on the other
+is comparing two names for the same socket.
+"""
+
+import os
+import shutil
+import socket
+import tempfile
+from contextlib import contextmanager
+
+# Short enough to leave room for the socket's own name under every platform's
+# sun_path budget. A relative root would depend on the working directory.
+_SHORT_ROOT = os.path.realpath(tempfile.gettempdir() if os.name == "nt" else "/tmp")
+
+
+@contextmanager
+def bound_unix_socket(name="docker.sock"):
+    """Yield the path of a listening AF_UNIX socket, cleaned up on exit."""
+    directory = os.path.realpath(tempfile.mkdtemp(prefix="odysseus-sock-", dir=_SHORT_ROOT))
+    path = os.path.join(directory, name)
+    if len(path) > 103:  # pragma: no cover - guards the guard
+        raise AssertionError(f"socket path is {len(path)} bytes, over the limit: {path}")
+    sock = socket.socket(socket.AF_UNIX)
+    try:
+        sock.bind(path)
+        yield path
+    finally:
+        sock.close()
+        shutil.rmtree(directory, ignore_errors=True)