Add schema-based parsing (#43)

.gitignore

@@ -3,3 +3,4 @@
 build
 profilers
 testdata
+hotspot_*.log

build.gradle

@@ -1,6 +1,7 @@
 import me.champeau.jmh.JmhBytecodeGeneratorTask
-import org.gradle.internal.os.OperatingSystem
 import org.ajoberstar.grgit.Grgit
+import org.gradle.internal.os.OperatingSystem
+
 import java.time.Duration
 
 plugins {
@@ -42,20 +43,20 @@ java {
 }
 
 ext {
-    junitVersion = '5.9.1'
-    jsoniterScalaVersion = '2.24.4'
+    junitVersion = '5.10.2'
+    jsoniterScalaVersion = '2.28.4'
 }
 
 dependencies {
-    jmhImplementation group: 'com.fasterxml.jackson.core', name: 'jackson-databind', version: '2.16.0'
-    jmhImplementation group: 'com.alibaba.fastjson2', name: 'fastjson2', version: '2.0.42'
-    jmhImplementation group: 'com.jsoniter', name: 'jsoniter', version: '0.9.23'
+    jmhImplementation group: 'com.fasterxml.jackson.core', name: 'jackson-databind', version: '2.17.0'
+    jmhImplementation group: 'com.alibaba.fastjson2', name: 'fastjson2', version: '2.0.49'
     jmhImplementation group: 'com.github.plokhotnyuk.jsoniter-scala', name: 'jsoniter-scala-core_2.13', version: jsoniterScalaVersion
     jmhImplementation group: 'com.google.guava', name: 'guava', version: '32.1.2-jre'
     compileOnly group: 'com.github.plokhotnyuk.jsoniter-scala', name: 'jsoniter-scala-macros_2.13', version: jsoniterScalaVersion
 
     testImplementation group: 'org.assertj', name: 'assertj-core', version: '3.24.2'
     testImplementation group: 'org.apache.commons', name: 'commons-text', version: '1.10.0'
+    testImplementation group: 'org.junit-pioneer', name: 'junit-pioneer', version: '2.2.0'
     testImplementation group: 'org.junit.jupiter', name: 'junit-jupiter-api', version: junitVersion
     testImplementation group: 'org.junit.jupiter', name: 'junit-jupiter-params', version: junitVersion
     testRuntimeOnly group: 'org.junit.jupiter', name: 'junit-jupiter-engine', version: junitVersion
@@ -136,15 +137,21 @@ jmh {
             '--add-modules=jdk.incubator.vector'
     ]
     if (getBooleanProperty('jmh.profilersEnabled', false)) {
+        createDirIfDoesNotExist('./profilers')
         if (OperatingSystem.current().isLinux()) {
-            profilers = [
-                    'perf',
-                    'perfasm:intelSyntax=true',
-                    'async:verbose=true;output=flamegraph;event=cpu;dir=./profilers/async;libPath=' + getAsyncProfilerLibPath('LD_LIBRARY_PATH')
+            def profilerList = [
+                    'async:verbose=true;output=flamegraph;event=cpu;dir=./profilers/async;libPath=' + getLibPath('LD_LIBRARY_PATH')
             ]
+            if (getBooleanProperty('jmh.jitLogEnabled', false)) {
+                createDirIfDoesNotExist('./profilers/perfasm')
+                profilerList += [
+                        'perfasm:intelSyntax=true;saveLog=true;saveLogTo=./profilers/perfasm'
+                ]
+            }
+            profilers = profilerList
         } else if (OperatingSystem.current().isMacOsX()) {
             profilers = [
-                    'async:verbose=true;output=flamegraph;event=cpu;dir=./profilers/async;libPath=' + getAsyncProfilerLibPath('DYLD_LIBRARY_PATH')
+                    'async:verbose=true;output=flamegraph;event=cpu;dir=./profilers/async;libPath=' + getLibPath('DYLD_LIBRARY_PATH')
             ]
         }
     }
@@ -218,6 +225,11 @@ def getBooleanProperty(String name, boolean defaultValue) {
     Boolean.valueOf((project.findProperty(name) ?: defaultValue) as String)
 }
 
-static def getAsyncProfilerLibPath(String envVarName) {
+static def getLibPath(String envVarName) {
     System.getenv(envVarName) ?: System.getProperty('java.library.path')
 }
+
+static createDirIfDoesNotExist(String dir) {
+    File file = new File(dir)
+    file.mkdirs()
+}

src/jmh/java/org/simdjson/NumberParserBenchmark.java

@@ -21,7 +21,7 @@
 public class NumberParserBenchmark {
 
     private final Tape tape = new Tape(100);
-    private final NumberParser numberParser = new NumberParser(tape);
+    private final NumberParser numberParser = new NumberParser();
 
     @Param({
             "2.2250738585072013e-308", // fast path
@@ -43,7 +43,7 @@ public double baseline() {
     @Benchmark
     public double simdjson() {
         tape.reset();
-        numberParser.parseNumber(numberUtf8Bytes, 0);
+        numberParser.parseNumber(numberUtf8Bytes, 0, tape);
         return tape.getDouble(0);
     }
 }

src/jmh/java/org/simdjson/ParseAndSelectBenchmark.java

@@ -4,10 +4,6 @@
 import com.alibaba.fastjson2.JSONObject;
 import com.fasterxml.jackson.databind.JsonNode;
 import com.fasterxml.jackson.databind.ObjectMapper;
-import com.github.plokhotnyuk.jsoniter_scala.core.ReaderConfig$;
-import com.github.plokhotnyuk.jsoniter_scala.core.package$;
-import com.jsoniter.JsonIterator;
-import com.jsoniter.any.Any;
 import org.openjdk.jmh.annotations.Benchmark;
 import org.openjdk.jmh.annotations.BenchmarkMode;
 import org.openjdk.jmh.annotations.Level;
@@ -43,19 +39,7 @@ public void setup() throws IOException {
             buffer = is.readAllBytes();
             bufferPadded = padded(buffer);
         }
-    }
-
-    @Benchmark
-    public int countUniqueUsersWithDefaultProfile_jsoniter_scala() throws IOException {
-        Twitter twitter = package$.MODULE$.readFromArray(buffer, ReaderConfig$.MODULE$, Twitter$.MODULE$.codec());
-        Set<String> defaultUsers = new HashSet<>();
-        for (Status tweet: twitter.statuses()) {
-            User user = tweet.user();
-            if (user.default_profile()) {
-                defaultUsers.add(user.screen_name());
-            }
-        }
-        return defaultUsers.size();
+        System.out.println("VectorSpecies = " + StructuralIndexer.BYTE_SPECIES);
     }
 
     @Benchmark
@@ -88,19 +72,6 @@ public int countUniqueUsersWithDefaultProfile_fastjson() {
         return defaultUsers.size();
     }
 
-    @Benchmark
-    public int countUniqueUsersWithDefaultProfile_jsoniter() {
-        Any json = JsonIterator.deserialize(buffer);
-        Set<String> defaultUsers = new HashSet<>();
-        for (Any tweet : json.get("statuses")) {
-            Any user = tweet.get("user");
-            if (user.get("default_profile").toBoolean()) {
-                defaultUsers.add(user.get("screen_name").toString());
-            }
-        }
-        return defaultUsers.size();
-    }
-
     @Benchmark
     public int countUniqueUsersWithDefaultProfile_simdjson() {
         JsonValue simdJsonValue = simdJsonParser.parse(buffer, buffer.length);

src/jmh/java/org/simdjson/SchemaBasedParseAndSelectBenchmark.java

@@ -0,0 +1,123 @@
+package org.simdjson;
+
+import com.alibaba.fastjson2.JSON;
+import com.fasterxml.jackson.databind.DeserializationFeature;
+import com.fasterxml.jackson.databind.ObjectMapper;
+import com.github.plokhotnyuk.jsoniter_scala.core.ReaderConfig$;
+import com.github.plokhotnyuk.jsoniter_scala.core.package$;
+import org.openjdk.jmh.annotations.Benchmark;
+import org.openjdk.jmh.annotations.BenchmarkMode;
+import org.openjdk.jmh.annotations.Level;
+import org.openjdk.jmh.annotations.Mode;
+import org.openjdk.jmh.annotations.OutputTimeUnit;
+import org.openjdk.jmh.annotations.Scope;
+import org.openjdk.jmh.annotations.Setup;
+import org.openjdk.jmh.annotations.State;
+
+import java.io.IOException;
+import java.io.InputStream;
+import java.util.HashSet;
+import java.util.List;
+import java.util.Set;
+import java.util.concurrent.TimeUnit;
+
+import static org.simdjson.SimdJsonPaddingUtil.padded;
+
+@State(Scope.Benchmark)
+@BenchmarkMode(Mode.Throughput)
+@OutputTimeUnit(TimeUnit.SECONDS)
+public class SchemaBasedParseAndSelectBenchmark {
+
+    private final SimdJsonParser simdJsonParser = new SimdJsonParser();
+    private final ObjectMapper objectMapper = new ObjectMapper()
+            .configure(DeserializationFeature.FAIL_ON_UNKNOWN_PROPERTIES, false);
+
+    private byte[] buffer;
+    private byte[] bufferPadded;
+
+    @Setup(Level.Trial)
+    public void setup() throws IOException {
+        try (InputStream is = ParseBenchmark.class.getResourceAsStream("/twitter.json")) {
+            buffer = is.readAllBytes();
+            bufferPadded = padded(buffer);
+        }
+        System.out.println("VectorSpecies = " + StructuralIndexer.BYTE_SPECIES);
+    }
+
+    @Benchmark
+    public int countUniqueUsersWithDefaultProfile_simdjson() {
+        Set<String> defaultUsers = new HashSet<>();
+        SimdJsonTwitter twitter = simdJsonParser.parse(buffer, buffer.length, SimdJsonTwitter.class);
+        for (SimdJsonStatus status : twitter.statuses()) {
+            SimdJsonUser user = status.user();
+            if (user.default_profile()) {
+                defaultUsers.add(user.screen_name());
+            }
+        }
+        return defaultUsers.size();
+    }
+
+    @Benchmark
+    public int countUniqueUsersWithDefaultProfile_simdjsonPadded() {
+        Set<String> defaultUsers = new HashSet<>();
+        SimdJsonTwitter twitter = simdJsonParser.parse(bufferPadded, buffer.length, SimdJsonTwitter.class);
+        for (SimdJsonStatus status : twitter.statuses()) {
+            SimdJsonUser user = status.user();
+            if (user.default_profile()) {
+                defaultUsers.add(user.screen_name());
+            }
+        }
+        return defaultUsers.size();
+    }
+
+    @Benchmark
+    public int countUniqueUsersWithDefaultProfile_jackson() throws IOException {
+        Set<String> defaultUsers = new HashSet<>();
+        SimdJsonTwitter twitter = objectMapper.readValue(buffer, SimdJsonTwitter.class);
+        for (SimdJsonStatus status : twitter.statuses()) {
+            SimdJsonUser user = status.user();
+            if (user.default_profile()) {
+                defaultUsers.add(user.screen_name());
+            }
+        }
+        return defaultUsers.size();
+    }
+
+    @Benchmark
+    public int countUniqueUsersWithDefaultProfile_jsoniter_scala() {
+        Twitter twitter = package$.MODULE$.readFromArray(buffer, ReaderConfig$.MODULE$, Twitter$.MODULE$.codec());
+        Set<String> defaultUsers = new HashSet<>();
+        for (Status tweet: twitter.statuses()) {
+            User user = tweet.user();
+            if (user.default_profile()) {
+                defaultUsers.add(user.screen_name());
+            }
+        }
+        return defaultUsers.size();
+    }
+
+    @Benchmark
+    public int countUniqueUsersWithDefaultProfile_fastjson() {
+        Set<String> defaultUsers = new HashSet<>();
+        SimdJsonTwitter twitter = JSON.parseObject(buffer, SimdJsonTwitter.class);
+        for (SimdJsonStatus status : twitter.statuses()) {
+            SimdJsonUser user = status.user();
+            if (user.default_profile()) {
+                defaultUsers.add(user.screen_name());
+            }
+        }
+        return defaultUsers.size();
+    }
+
+    record SimdJsonUser(boolean default_profile, String screen_name) {
+
+    }
+
+    record SimdJsonStatus(SimdJsonUser user) {
+
+    }
+
+    record SimdJsonTwitter(List<SimdJsonStatus> statuses) {
+
+    }
+}

src/main/java/org/simdjson/BitIndexes.java

@@ -44,11 +44,26 @@ private long clearLowestBit(long bits) {
         return bits & (bits - 1);
     }
 
-    int advance() {
+    void advance() {
+        readIdx++;
+    }
+
+    int getAndAdvance() {
+        assert readIdx <= writeIdx;
         return indexes[readIdx++];
     }
 
+    int getLast() {
+        return indexes[writeIdx - 1];
+    }
+
+    int advanceAndGet() {
+        assert readIdx + 1 <= writeIdx;
+        return indexes[++readIdx];
+    }
+
     int peek() {
+        assert readIdx <= writeIdx;
         return indexes[readIdx];
     }
 
@@ -60,6 +75,26 @@ boolean isEnd() {
         return writeIdx == readIdx;
     }
 
+    boolean isPastEnd() {
+        return readIdx > writeIdx;
+    }
+
+    void finish() {
+        // If we go past the end of the detected structural indexes, it means we are dealing with an invalid JSON.
+        // Thus, we need to stop processing immediately and throw an exception. To avoid checking after every increment
+        // of readIdx whether this has happened, we jump to the first structural element. This should produce the
+        // desired outcome, i.e., an iterator should detect invalid JSON. To understand how this works, let's first
+        // exclude primitive values (numbers, strings, booleans, nulls) from the scope of possible JSON documents. We
+        // can do this because, when these values are parsed, the length of the input buffer is verified, ensuring we
+        // never go past its end. Therefore, we can focus solely on objects and arrays. Since we always check that if
+        // the first character is '{', the last one must be '}', and if the first character is '[', the last one must
+        // be ']', we know that if we've reached beyond the buffer without crashing, the input is either '{...}' or '[...]'.
+        // Thus, if we jump to the first structural element, we will generate either '{...}{' or '[...]['. Both of these
+        // are invalid sequences and will be detected by the iterator, which will then stop processing and throw an
+        // exception informing about the invalid JSON.
+        indexes[writeIdx] = 0;
+    }
+
     void reset() {
         writeIdx = 0;
         readIdx = 0;

src/main/java/org/simdjson/ClassResolver.java

@@ -0,0 +1,24 @@
+package org.simdjson;
+
+import java.lang.reflect.Type;
+import java.util.HashMap;
+import java.util.Map;
+
+class ClassResolver {
+
+    private final Map<Type, ResolvedClass> classCache = new HashMap<>();
+
+    ResolvedClass resolveClass(Type type) {
+        ResolvedClass resolvedClass = classCache.get(type);
+        if (resolvedClass != null) {
+            return resolvedClass;
+        }
+        resolvedClass = new ResolvedClass(type, this);
+        classCache.put(type, resolvedClass);
+        return resolvedClass;
+    }
+
+    void reset() {
+        classCache.clear();
+    }
+}

src/main/java/org/simdjson/ConstructorArgument.java

@@ -0,0 +1,4 @@
+package org.simdjson;
+
+record ConstructorArgument(int idx, ResolvedClass resolvedClass) {
+}