Created
April 15, 2020 03:53
-
-
Save romain-grecourt/8218a1ba2a6c91cbcadbddd9d8f9f28e to your computer and use it in GitHub Desktop.
reactive html encoder
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
/** | |
* Reactive HTML entities "encoder". | |
*/ | |
class HtmlEntityEncoder extends BaseProcessor<DataChunk, DataChunk> { | |
private static final ByteBufferCache BBCACHE = new ByteBufferCache( | |
(int index) -> ByteBuffer.wrap(HtmlEscape.ENTITIES[index][1].getBytes()), HtmlEscape.ENTITIES.length); | |
protected final VirtualBuffer vbuf = new VirtualBuffer(); | |
private boolean started; | |
/** | |
* Create a new encoder. | |
*/ | |
HtmlEntityEncoder() { | |
} | |
protected final void insert(ByteBuffer bb) { | |
vbuf.insert(bb); | |
vbuf.incrementPosition(bb.remaining()); | |
} | |
/** | |
* Signals the start of the page. | |
*/ | |
protected void onPageStart(){ } | |
/** | |
* Signals the end of the page. | |
*/ | |
protected void onPageEnd() { } | |
@Override | |
public final void hookOnNext(DataChunk item) { | |
vbuf.offer(item.data()); | |
VirtualChunk.Parent parent = new VirtualChunk.Parent(item); | |
if (!started) { | |
onPageStart(); | |
started = true; | |
} | |
while (vbuf.remaining() > 0) { | |
byte b1 = vbuf.get(); | |
int mark = vbuf.position(); | |
int limit = vbuf.limit(); | |
int nbytes = 0; | |
char c = '?'; | |
if (b1 >= 0) { | |
nbytes = 1; | |
c = (char) b1; | |
} else if ((b1 >> 5) == -2 && (b1 & 0x1e) != 0) { | |
// 2 bytes, 11 bits: 110xxxxx 10xxxxxx | |
int b2 = vbuf.get(); | |
if (!((b2 & 0xc0) != 0x80)) { | |
nbytes = 2; | |
c = (char) (((b1 << 6) ^ b2) | |
^ (((byte) 0xC0 << 6) | |
^ ((byte) 0x80))); | |
} | |
} else if ((b1 >> 4) == -2) { | |
// 3 bytes, 16 bits: 1110xxxx 10xxxxxx 10xxxxxx | |
int remaining = limit - mark; | |
if (remaining >= 2) { | |
int b2 = vbuf.get(); | |
int b3 = vbuf.get(); | |
if (!((b1 == (byte) 0xe0 && (b2 & 0xe0) == 0x80) | |
|| (b2 & 0xc0) != 0x80 || (b3 & 0xc0) != 0x80)) { | |
c = (char) ((b1 << 12) | |
^ (b2 << 6) | |
^ (b3 | |
^ (((byte) 0xE0 << 12) | |
^ ((byte) 0x80 << 6) | |
^ ((byte) 0x80)))); | |
if (!Character.isSurrogate(c)) { | |
nbytes = 3; | |
} | |
} | |
} | |
} | |
int htmlEntityId = HtmlEscape.entityId(c); | |
if (htmlEntityId >= 0) { | |
vbuf.deletePrevious(nbytes); | |
insert(BBCACHE.get(htmlEntityId)); | |
} | |
} | |
// It's not possible to submit a VirtualBuffer as-is (yet) | |
// using drop() to get the underlying buffers as-is | |
for (ByteBuffer bb : vbuf.position(0).drop()) { | |
submit(new VirtualChunk(parent, bb)); | |
// re-using buffers | |
bb.position(0); | |
} | |
} | |
@Override | |
protected void hookOnComplete() { | |
onPageEnd(); | |
for (ByteBuffer bb : vbuf.position(0).drop()) { | |
submit(DataChunk.create(bb)); | |
} | |
} | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment