Newsgroups: php.internals
Path: news.php.net
Xref: news.php.net php.internals:124377
Precedence: bulk
MIME-Version: 1.0
References: <14b769e9-acb7-46d2-85ab-f276e82f3069@app.fastmail.com>
 <keevagftCJrsIAsW2GsdWDH5Eu_FIagaX1iSkCticfGCILUlLDUXKUwiJIg3dzzBDTvcLY80s6ZQpHR0iPAhhrRG3Mc_jUh_moHaeqlYDas=@gpb.moe>
 <0cfec69f-2b0c-4c1e-9e47-e6379cf90ea2@app.fastmail.com>
In-Reply-To: <0cfec69f-2b0c-4c1e-9e47-e6379cf90ea2@app.fastmail.com>
Date: Thu, 11 Jul 2024 01:11:36 +0200
Message-ID: <CAG9XoMRwCJuXNTCt47r716Q6-A3A84UyUgD9DLDfAoWrL9K-Mw@mail.gmail.com>
Subject: Re: [PHP-DEV] [low priority] WeakMaps with scalar keys
To: Rob Landers <rob@bottled.codes>
Cc: "Gina P. Banyard" <internals@gpb.moe>, internals@lists.php.net
Content-Type: multipart/alternative; boundary="0000000000003e39b8061cecc553"
From: benjamin.morel@gmail.com (Benjamin Morel)

--0000000000003e39b8061cecc553
Content-Type: text/plain; charset="UTF-8"
Content-Transfer-Encoding: quoted-printable

>
> The answer is: it depends. If you don=E2=80=99t need the array to clean u=
p after
> itself, you can indeed use an array of WeakReference to get most of the w=
ay
> there. If you want it to clean up after an object gets removed, you eithe=
r
> need to add support to the stored object=E2=80=99s destructor (which isn=
=E2=80=99t always
> possible for built-in or final types), or create your own garbage collect=
or
> that scans the array.
>

It is indeed doable in userland using WeakReferences, with a small
performance penalty:

```
class ReverseWeakMap implements Countable, IteratorAggregate, ArrayAccess
{
    /**
     * @var array<int|string, WeakReference>
     */
    private array $map =3D [];

    public function count(): int
    {
        foreach ($this->map as $value =3D> $weakReference) {
            if ($weakReference->get() =3D=3D=3D null) {
                unset($this->map[$value]);
            }
        }

        return count($this->map);
    }

    public function getIterator(): Generator
    {
        foreach ($this->map as $value =3D> $weakReference) {
            $object =3D $weakReference->get();

            if ($object =3D=3D=3D null) {
                unset($this->map[$value]);
            } else {
                yield $value =3D> $object;
            }
        }
    }

    public function offsetExists(mixed $offset)
    {
        if (isset($this->map[$offset])) {
            $object =3D $this->map[$offset]->get();

            if ($object !=3D=3D null) {
                return true;
            }

            unset($this->map[$offset]);
        }

        return false;
    }

    public function offsetGet(mixed $offset): object
    {
        if (isset($this->map[$offset])) {
            $object =3D $this->map[$offset]->get();

            if ($object !=3D=3D null) {
                return $object;
            }

            unset($this->map[$offset]);
        }

        throw new Exception('Undefined offset');
    }

    public function offsetSet(mixed $offset, mixed $value): void
    {
        $this->map[$offset] =3D WeakReference::create($value);
    }

    public function offsetUnset(mixed $offset): void
    {
        unset($this->map[$offset]);
    }
}
```

Now that I think about it, it might be simpler to add an =E2=80=9ConRemove(=
)=E2=80=9D
> method that takes a callback for the WeakReference class.
>
> =E2=80=94 Rob
>


A callback when an object goes out of scope would be a great addition to
both WeakReference & WeakMap indeed, it would allow custom userland weak
maps like the above, with next to no performance penalty!

- Benjamin

--0000000000003e39b8061cecc553
Content-Type: text/html; charset="UTF-8"
Content-Transfer-Encoding: quoted-printable

<div dir=3D"ltr"><div class=3D"gmail_quote"><blockquote class=3D"gmail_quot=
e" style=3D"margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204)=
;padding-left:1ex"><div class=3D"msg-3759682570413819344"><div>The answer i=
s: it depends. If you don=E2=80=99t need the array to clean up after itself=
, you can indeed use an array of WeakReference to get most of the way there=
. If you want it to clean up after an object gets removed, you either need =
to add support to the stored object=E2=80=99s destructor (which isn=E2=80=
=99t always possible for built-in or final types), or create your own garba=
ge collector that scans the array.=C2=A0</div></div></blockquote><div><br><=
/div><div>It is indeed doable in userland using WeakReferences, with a smal=
l performance penalty:</div><div><br></div><div>```</div><div>class Reverse=
WeakMap implements Countable, IteratorAggregate, ArrayAccess<br>{<br>=C2=A0=
 =C2=A0 /**<br>=C2=A0 =C2=A0 =C2=A0* @var array&lt;int|string, WeakReferenc=
e&gt;<br>=C2=A0 =C2=A0 =C2=A0*/<br>=C2=A0 =C2=A0 private array $map =3D [];=
<br><br>=C2=A0 =C2=A0 public function count(): int<br>=C2=A0 =C2=A0 {<br>=
=C2=A0 =C2=A0 =C2=A0 =C2=A0 foreach ($this-&gt;map as $value =3D&gt; $weakR=
eference) {<br>=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 if ($weakReference=
-&gt;get() =3D=3D=3D null) {<br>=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =
=C2=A0 =C2=A0 unset($this-&gt;map[$value]);<br>=C2=A0 =C2=A0 =C2=A0 =C2=A0 =
=C2=A0 =C2=A0 }<br>=C2=A0 =C2=A0 =C2=A0 =C2=A0 }<br><br>=C2=A0 =C2=A0 =C2=
=A0 =C2=A0 return count($this-&gt;map);<br>=C2=A0 =C2=A0 }<br><br>=C2=A0 =
=C2=A0 public function getIterator(): Generator<br>=C2=A0 =C2=A0 {<br>=C2=
=A0 =C2=A0 =C2=A0 =C2=A0 foreach ($this-&gt;map as $value =3D&gt; $weakRefe=
rence) {<br>=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 $object =3D $weakRefe=
rence-&gt;get();<br><br>=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 if ($obje=
ct =3D=3D=3D null) {<br>=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =
=C2=A0 unset($this-&gt;map[$value]);<br>=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =
=C2=A0 } else {<br>=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =
yield $value =3D&gt; $object;<br>=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =
}<br>=C2=A0 =C2=A0 =C2=A0 =C2=A0 }<br>=C2=A0 =C2=A0 }<br><br>=C2=A0 =C2=A0 =
public function offsetExists(mixed $offset)<br>=C2=A0 =C2=A0 {<br>=C2=A0 =
=C2=A0 =C2=A0 =C2=A0 if (isset($this-&gt;map[$offset])) {<br>=C2=A0 =C2=A0 =
=C2=A0 =C2=A0 =C2=A0 =C2=A0 $object =3D $this-&gt;map[$offset]-&gt;get();<b=
r><br>=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 if ($object !=3D=3D null) {=
<br>=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 return true;<br=
>=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 }<br><br>=C2=A0 =C2=A0 =C2=A0 =
=C2=A0 =C2=A0 =C2=A0 unset($this-&gt;map[$offset]);<br>=C2=A0 =C2=A0 =C2=A0=
 =C2=A0 }<br><br>=C2=A0 =C2=A0 =C2=A0 =C2=A0 return false;<br>=C2=A0 =C2=A0=
 }<br><br>=C2=A0 =C2=A0 public function offsetGet(mixed $offset): object<br=
>=C2=A0 =C2=A0 {<br>=C2=A0 =C2=A0 =C2=A0 =C2=A0 if (isset($this-&gt;map[$of=
fset])) {<br>=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 $object =3D $this-&g=
t;map[$offset]-&gt;get();<br><br>=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =
if ($object !=3D=3D null) {<br>=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =
=C2=A0 =C2=A0 return $object;<br>=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =
}<br><br>=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 unset($this-&gt;map[$off=
set]);<br>=C2=A0 =C2=A0 =C2=A0 =C2=A0 }<br><br>=C2=A0 =C2=A0 =C2=A0 =C2=A0 =
throw new Exception(&#39;Undefined offset&#39;);<br>=C2=A0 =C2=A0 }<br><br>=
=C2=A0 =C2=A0 public function offsetSet(mixed $offset, mixed $value): void<=
br>=C2=A0 =C2=A0 {<br>=C2=A0 =C2=A0 =C2=A0 =C2=A0 $this-&gt;map[$offset] =
=3D WeakReference::create($value);<br>=C2=A0 =C2=A0 }<br><br>=C2=A0 =C2=A0 =
public function offsetUnset(mixed $offset): void<br>=C2=A0 =C2=A0 {<br>=C2=
=A0 =C2=A0 =C2=A0 =C2=A0 unset($this-&gt;map[$offset]);<br>=C2=A0 =C2=A0 }<=
br>}<br></div><div>```=C2=A0</div><div><br></div><blockquote class=3D"gmail=
_quote" style=3D"margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204=
,204);padding-left:1ex"><div>Now that I think about it, it might be simpler=
 to add an =E2=80=9ConRemove()=E2=80=9D method that takes a callback for th=
e WeakReference class.=C2=A0</div><div><br></div><div id=3D"m_-375968257041=
3819344sig121229152">=E2=80=94 Rob</div></blockquote><div><br></div><div><b=
r></div><div>A callback when an object goes out of scope would be a great a=
ddition to both WeakReference &amp; WeakMap indeed, it would allow custom u=
serland weak maps like the above, with next to no performance penalty!</div=
><div><br></div><div>- Benjamin</div><div>=C2=A0<br></div></div></div>

--0000000000003e39b8061cecc553--