Add parseNumberCounter. numbersoup test fails

rallyhealth · Mar 9, 2022 · a3d913d · a3d913d
1 parent a12c795
commit a3d913d
Show file tree

Hide file tree

Showing 4 changed files with 90 additions and 12 deletions.
diff --git a/bench/src/main/scala/bench/JsoniterScalaBench.scala b/bench/src/main/scala/bench/JsoniterScalaBench.scala
@@ -1,7 +1,7 @@
 package bench
 
+import com.rallyhealth.weejson.v1.BufferedValue
 import com.rallyhealth.weejson.v1.wee_jsoniter_scala.FromJsoniterScala
-import com.rallyhealth.weepickle.v1.WeePickle.ToScala
 import org.openjdk.jmh.annotations._
 
 import java.util.concurrent.TimeUnit
@@ -10,17 +10,17 @@ import java.util.concurrent.TimeUnit
   * Quick and dirty test to see how badly we're butchering performance of floats.
   *
   * ==Quick Run==
-  * bench / Jmh / run .*JsoniterScalabench
+  * bench / Jmh / run .*JsoniterScalaBench
   *
   * ==Profile with Flight Recorder==
-  * bench / Jmh / run -prof jfr .*JsoniterScalabench
+  * bench / Jmh / run -prof jfr .*JsoniterScalaBench
   *
   * ==Jmh Visualizer Report==
-  * bench / Jmh / run -prof gc -rf json -rff JsoniterScalabench-results.json .*JsoniterScalabench
+  * bench / Jmh / run -prof gc -rf json -rff JsoniterScalaBench-results.json .*JsoniterScalaBench
   *
   * @see https://github.com/ktoso/sbt-jmh
   */
-@Warmup(iterations = 15, time = 1, timeUnit = TimeUnit.SECONDS)
+@Warmup(iterations = 5, time = 1, timeUnit = TimeUnit.SECONDS)
 @Measurement(iterations = 15, time = 1, timeUnit = TimeUnit.SECONDS)
 @State(Scope.Benchmark)
 @BenchmarkMode(Array(Mode.Throughput))
@@ -31,11 +31,15 @@ import java.util.concurrent.TimeUnit
   value = 1
 )
 class JsoniterScalaBench {
-  private val input = "348249875e105".getBytes()
+
+  /**
+    * Values that end with a number throw an expensive exception internally when reaching EOF.
+    * The only time this would happen in the wild would be when parsing a JSON text of a single number.
+    * To make this more realistic, we're intentionally adding a whitespace suffix here.
+    */
+  private val piBytes = "-3.14 ".getBytes()
 
   @Benchmark
-  def parseDouble = {
-    FromJsoniterScala(input).transform(ToScala[Double])
-  }
+  def pi = FromJsoniterScala(piBytes).transform(BufferedValue.Builder)
 
 }
diff --git a/bench/src/test/scala/bench/JsoniterScalaBenchTests.scala b/bench/src/test/scala/bench/JsoniterScalaBenchTests.scala
@@ -0,0 +1,12 @@
+package bench
+
+import com.rallyhealth.weejson.v1.BufferedValue._
+import utest._
+
+object JsoniterScalaBenchTests extends TestSuite {
+
+  val tests = Tests {
+    val bench = new JsoniterScalaBench()
+    test("pi")(bench.pi ==> Num("-3.14", 2, -1))
+  }
+}
diff --git a/project/plugins.sbt b/project/plugins.sbt
@@ -1,5 +1,5 @@
 addSbtPlugin("com.typesafe" % "sbt-mima-plugin" % "0.9.2")
 addSbtPlugin("com.dwijnand" % "sbt-dynver" % "4.1.1")
-addSbtPlugin("pl.project13.scala" % "sbt-jmh" % "0.3.7")
+addSbtPlugin("pl.project13.scala" % "sbt-jmh" % "0.4.3")
 addSbtPlugin("org.xerial.sbt" % "sbt-sonatype" % "3.9.7")
 addSbtPlugin("com.github.sbt" % "sbt-pgp" % "2.1.2")
diff --git a/...c/main/scala/com/rallyhealth/weejson/v1/wee_jsoniter_scala/WeePickleJsonValueCodecs.scala b/...c/main/scala/com/rallyhealth/weejson/v1/wee_jsoniter_scala/WeePickleJsonValueCodecs.scala
@@ -74,7 +74,7 @@ object WeePickleJsonValueCodecs {
         if (in.readBoolean()) v.visitTrue() else v.visitFalse()
       } else if ((b >= '0' && b <= '9') || b == '-') {
         in.rollbackToken()
-        parseNumber(in, v)
+        parseNumberCounter(in, v)
       } else if (b == '[') {
         val depthM1 = depth - 1
         if (depthM1 < 0) in.decodeError("depth limit exceeded")
@@ -121,7 +121,69 @@ object WeePickleJsonValueCodecs {
       }
     }
 
-    private def parseNumber[J](
+    private def parseNumberCounter[J](
+      in: JsonReader,
+      v: Visitor[_, J]
+    ): J = {
+      in.setMark()
+      var b = in.nextByte()
+      var digits, index = 0
+      var decIndex, expIndex = -1
+      if (b == '-') {
+        b = in.nextByte()
+        index += 1
+      }
+      try {
+        digits -= index
+        while (b >= '0' && b <= '9') {
+          b = in.nextByte()
+          index += 1
+        }
+        digits += index
+        if (b == '.') {
+          decIndex = index
+          b = in.nextByte()
+          index += 1
+        }
+        digits -= index
+        while (b >= '0' && b <= '9') {
+          b = in.nextByte()
+          index += 1
+        }
+        digits += index
+        if ((b | 0x20) == 'e') {
+          expIndex = index
+          b = in.nextByte()
+          index += 1
+          if (b == '-' || b == '+') {
+            b = in.nextByte()
+            index += 1
+          }
+          while (b >= '0' && b <= '9') {
+            b = in.nextByte()
+            index += 1
+          }
+        }
+      } catch {
+        case _: JsonReaderException =>
+          index += 1 // for length calcs, pretend that nextByte() didn't hit EOF
+      } finally in.rollbackToMark()
+      if ((decIndex & expIndex) == -1) {
+        if (digits < 19) v.visitInt64(in.readLong())
+        else {
+          val x = in.readBigInt(null)
+          if (x.bitLength < 64) v.visitInt64(x.longValue)
+          else v.visitFloat64StringParts(x.toString, -1, -1)
+        }
+      } else {
+        val cs = new String(in.readRawValAsBytes(), StandardCharsets.US_ASCII)
+        require(cs.length == index, "invalid number")
+        v.visitFloat64StringParts(cs, decIndex, expIndex)
+      }
+    }
+
+
+    private def parseNumberRegex[J](
       in: JsonReader,
       v: Visitor[_, J]
     ): J = {