Skip to content

perf: decode parser byte ranges in bulk instead of char by char #1229

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
pjfanning wants to merge 1 commit into
base: main
Choose a base branch
from
Open

perf: decode parser byte ranges in bulk instead of char by char #1229

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
15 changes: 8 additions & 7 deletions http-core/src/main/scala/org/apache/pekko/http/impl/engine/parsing/package.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13,14 +13,13 @@

package org.apache.pekko.http.impl.engine

import java.lang.{ StringBuilder => JStringBuilder }
import org.apache.pekko
import pekko.http.scaladsl.settings.ParserSettings

import scala.annotation.tailrec
import pekko.event.LoggingAdapter
import pekko.util.ByteString
import pekko.http.scaladsl.model.{ ErrorInfo, StatusCode, StatusCodes }
import pekko.http.impl.util.ISO88591
import pekko.http.impl.util.SingletonException

/**
Expand All @@ -41,11 +40,13 @@ package object parsing {
private[http] def byteAt(input: ByteString, ix: Int): Byte =
if (ix < input.length) input(ix) else throw NotEnoughDataException

private[http] def asciiString(input: ByteString, start: Int, end: Int): String = {
@tailrec def build(ix: Int = start, sb: JStringBuilder = new JStringBuilder(end - start)): String =
if (ix == end) sb.toString else build(ix + 1, sb.append(input(ix).toChar))
if (start == end) "" else build()
}
/**
* Decodes the given range as a String, one character per byte. Bytes above 0x7F are decoded as
* ISO-8859-1, as [[pekko.http.impl.util.ByteStringParserInput.sliceString]] already does; most
* callers have validated the range as 7-bit ASCII, for which the two agree.
*/
private[http] def asciiString(input: ByteString, start: Int, end: Int): String =
if (start == end) "" else input.slice(start, end).decodeString(ISO88591)

private[http] def logParsingError(info: ErrorInfo, log: LoggingAdapter,
settings: ParserSettings.ErrorLoggingVerbosity,
Expand Down
14 changes: 14 additions & 0 deletions http-core/src/test/scala/org/apache/pekko/http/impl/engine/parsing/ResponseParserSpec.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -103,6 +103,20 @@ abstract class ResponseParserSpec(mode: String, newLine: String) extends PekkoSp
closeAfterResponseCompletion shouldEqual Seq(false)
}

"a response with a non-ASCII header name, when illegal header names are ignored" in new Test {
override def parserSettings: ParserSettings =
super.parserSettings.withIllegalResponseHeaderNameProcessingMode(
ParserSettings.IllegalResponseHeaderNameProcessingMode.Ignore)

// a header name that is not 7-bit ASCII is an opaque byte range, decoded one character per
// byte (ISO-8859-1) rather than sign extended into \uFFxx characters
val name = new String("f\u00f6o".getBytes(java.nio.charset.StandardCharsets.UTF_8),
java.nio.charset.StandardCharsets.ISO_8859_1)
s"HTTP/1.1 200 OK${newLine}föo: bar${newLine}Content-Length: 0${newLine}${newLine}" should parseTo(
HttpResponse(headers = List(RawHeader(name, "bar"))))
closeAfterResponseCompletion shouldEqual Seq(false)
}

"a response with a missing reason phrase" in new Test {
s"HTTP/1.1 404 ${newLine}Content-Length: 0${newLine}${newLine}" should parseTo(HttpResponse(NotFound))
closeAfterResponseCompletion shouldEqual Seq(false)
Expand Down