Nomad changes

e2e/java/mvnw

@@ -0,0 +1,295 @@
+#!/bin/sh
+# ----------------------------------------------------------------------------
+# Licensed to the Apache Software Foundation (ASF) under one
+# or more contributor license agreements.  See the NOTICE file
+# distributed with this work for additional information
+# regarding copyright ownership.  The ASF licenses this file
+# to you under the Apache License, Version 2.0 (the
+# "License"); you may not use this file except in compliance
+# with the License.  You may obtain a copy of the License at
+#
+#    http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing,
+# software distributed under the License is distributed on an
+# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+# KIND, either express or implied.  See the License for the
+# specific language governing permissions and limitations
+# under the License.
+# ----------------------------------------------------------------------------
+
+# ----------------------------------------------------------------------------
+# Apache Maven Wrapper startup batch script, version 3.3.4
+#
+# Optional ENV vars
+# -----------------
+#   JAVA_HOME - location of a JDK home dir, required when download maven via java source
+#   MVNW_REPOURL - repo url base for downloading maven distribution
+#   MVNW_USERNAME/MVNW_PASSWORD - user and password for downloading maven
+#   MVNW_VERBOSE - true: enable verbose log; debug: trace the mvnw script; others: silence the output
+# ----------------------------------------------------------------------------
+
+set -euf
+[ "${MVNW_VERBOSE-}" != debug ] || set -x
+
+# OS specific support.
+native_path() { printf %s\\n "$1"; }
+case "$(uname)" in
+CYGWIN* | MINGW*)
+  [ -z "${JAVA_HOME-}" ] || JAVA_HOME="$(cygpath --unix "$JAVA_HOME")"
+  native_path() { cygpath --path --windows "$1"; }
+  ;;
+esac
+
+# set JAVACMD and JAVACCMD
+set_java_home() {
+  # For Cygwin and MinGW, ensure paths are in Unix format before anything is touched
+  if [ -n "${JAVA_HOME-}" ]; then
+    if [ -x "$JAVA_HOME/jre/sh/java" ]; then
+      # IBM's JDK on AIX uses strange locations for the executables
+      JAVACMD="$JAVA_HOME/jre/sh/java"
+      JAVACCMD="$JAVA_HOME/jre/sh/javac"
+    else
+      JAVACMD="$JAVA_HOME/bin/java"
+      JAVACCMD="$JAVA_HOME/bin/javac"
+
+      if [ ! -x "$JAVACMD" ] || [ ! -x "$JAVACCMD" ]; then
+        echo "The JAVA_HOME environment variable is not defined correctly, so mvnw cannot run." >&2
+        echo "JAVA_HOME is set to \"$JAVA_HOME\", but \"\$JAVA_HOME/bin/java\" or \"\$JAVA_HOME/bin/javac\" does not exist." >&2
+        return 1
+      fi
+    fi
+  else
+    JAVACMD="$(
+      'set' +e
+      'unset' -f command 2>/dev/null
+      'command' -v java
+    )" || :
+    JAVACCMD="$(
+      'set' +e
+      'unset' -f command 2>/dev/null
+      'command' -v javac
+    )" || :
+
+    if [ ! -x "${JAVACMD-}" ] || [ ! -x "${JAVACCMD-}" ]; then
+      echo "The java/javac command does not exist in PATH nor is JAVA_HOME set, so mvnw cannot run." >&2
+      return 1
+    fi
+  fi
+}
+
+# hash string like Java String::hashCode
+hash_string() {
+  str="${1:-}" h=0
+  while [ -n "$str" ]; do
+    char="${str%"${str#?}"}"
+    h=$(((h * 31 + $(LC_CTYPE=C printf %d "'$char")) % 4294967296))
+    str="${str#?}"
+  done
+  printf %x\\n $h
+}
+
+verbose() { :; }
+[ "${MVNW_VERBOSE-}" != true ] || verbose() { printf %s\\n "${1-}"; }
+
+die() {
+  printf %s\\n "$1" >&2
+  exit 1
+}
+
+trim() {
+  # MWRAPPER-139:
+  #   Trims trailing and leading whitespace, carriage returns, tabs, and linefeeds.
+  #   Needed for removing poorly interpreted newline sequences when running in more
+  #   exotic environments such as mingw bash on Windows.
+  printf "%s" "${1}" | tr -d '[:space:]'
+}
+
+scriptDir="$(dirname "$0")"
+scriptName="$(basename "$0")"
+
+# parse distributionUrl and optional distributionSha256Sum, requires .mvn/wrapper/maven-wrapper.properties
+while IFS="=" read -r key value; do
+  case "${key-}" in
+  distributionUrl) distributionUrl=$(trim "${value-}") ;;
+  distributionSha256Sum) distributionSha256Sum=$(trim "${value-}") ;;
+  esac
+done <"$scriptDir/.mvn/wrapper/maven-wrapper.properties"
+[ -n "${distributionUrl-}" ] || die "cannot read distributionUrl property in $scriptDir/.mvn/wrapper/maven-wrapper.properties"
+
+case "${distributionUrl##*/}" in
+maven-mvnd-*bin.*)
+  MVN_CMD=mvnd.sh _MVNW_REPO_PATTERN=/maven/mvnd/
+  case "${PROCESSOR_ARCHITECTURE-}${PROCESSOR_ARCHITEW6432-}:$(uname -a)" in
+  *AMD64:CYGWIN* | *AMD64:MINGW*) distributionPlatform=windows-amd64 ;;
+  :Darwin*x86_64) distributionPlatform=darwin-amd64 ;;
+  :Darwin*arm64) distributionPlatform=darwin-aarch64 ;;
+  :Linux*x86_64*) distributionPlatform=linux-amd64 ;;
+  *)
+    echo "Cannot detect native platform for mvnd on $(uname)-$(uname -m), use pure java version" >&2
+    distributionPlatform=linux-amd64
+    ;;
+  esac
+  distributionUrl="${distributionUrl%-bin.*}-$distributionPlatform.zip"
+  ;;
+maven-mvnd-*) MVN_CMD=mvnd.sh _MVNW_REPO_PATTERN=/maven/mvnd/ ;;
+*) MVN_CMD="mvn${scriptName#mvnw}" _MVNW_REPO_PATTERN=/org/apache/maven/ ;;
+esac
+
+# apply MVNW_REPOURL and calculate MAVEN_HOME
+# maven home pattern: ~/.m2/wrapper/dists/{apache-maven-<version>,maven-mvnd-<version>-<platform>}/<hash>
+[ -z "${MVNW_REPOURL-}" ] || distributionUrl="$MVNW_REPOURL$_MVNW_REPO_PATTERN${distributionUrl#*"$_MVNW_REPO_PATTERN"}"
+distributionUrlName="${distributionUrl##*/}"
+distributionUrlNameMain="${distributionUrlName%.*}"
+distributionUrlNameMain="${distributionUrlNameMain%-bin}"
+MAVEN_USER_HOME="${MAVEN_USER_HOME:-${HOME}/.m2}"
+MAVEN_HOME="${MAVEN_USER_HOME}/wrapper/dists/${distributionUrlNameMain-}/$(hash_string "$distributionUrl")"
+
+exec_maven() {
+  unset MVNW_VERBOSE MVNW_USERNAME MVNW_PASSWORD MVNW_REPOURL || :
+  exec "$MAVEN_HOME/bin/$MVN_CMD" "$@" || die "cannot exec $MAVEN_HOME/bin/$MVN_CMD"
+}
+
+if [ -d "$MAVEN_HOME" ]; then
+  verbose "found existing MAVEN_HOME at $MAVEN_HOME"
+  exec_maven "$@"
+fi
+
+case "${distributionUrl-}" in
+*?-bin.zip | *?maven-mvnd-?*-?*.zip) ;;
+*) die "distributionUrl is not valid, must match *-bin.zip or maven-mvnd-*.zip, but found '${distributionUrl-}'" ;;
+esac
+
+# prepare tmp dir
+if TMP_DOWNLOAD_DIR="$(mktemp -d)" && [ -d "$TMP_DOWNLOAD_DIR" ]; then
+  clean() { rm -rf -- "$TMP_DOWNLOAD_DIR"; }
+  trap clean HUP INT TERM EXIT
+else
+  die "cannot create temp dir"
+fi
+
+mkdir -p -- "${MAVEN_HOME%/*}"
+
+# Download and Install Apache Maven
+verbose "Couldn't find MAVEN_HOME, downloading and installing it ..."
+verbose "Downloading from: $distributionUrl"
+verbose "Downloading to: $TMP_DOWNLOAD_DIR/$distributionUrlName"
+
+# select .zip or .tar.gz
+if ! command -v unzip >/dev/null; then
+  distributionUrl="${distributionUrl%.zip}.tar.gz"
+  distributionUrlName="${distributionUrl##*/}"
+fi
+
+# verbose opt
+__MVNW_QUIET_WGET=--quiet __MVNW_QUIET_CURL=--silent __MVNW_QUIET_UNZIP=-q __MVNW_QUIET_TAR=''
+[ "${MVNW_VERBOSE-}" != true ] || __MVNW_QUIET_WGET='' __MVNW_QUIET_CURL='' __MVNW_QUIET_UNZIP='' __MVNW_QUIET_TAR=v
+
+# normalize http auth
+case "${MVNW_PASSWORD:+has-password}" in
+'') MVNW_USERNAME='' MVNW_PASSWORD='' ;;
+has-password) [ -n "${MVNW_USERNAME-}" ] || MVNW_USERNAME='' MVNW_PASSWORD='' ;;
+esac
+
+if [ -z "${MVNW_USERNAME-}" ] && command -v wget >/dev/null; then
+  verbose "Found wget ... using wget"
+  wget ${__MVNW_QUIET_WGET:+"$__MVNW_QUIET_WGET"} "$distributionUrl" -O "$TMP_DOWNLOAD_DIR/$distributionUrlName" || die "wget: Failed to fetch $distributionUrl"
+elif [ -z "${MVNW_USERNAME-}" ] && command -v curl >/dev/null; then
+  verbose "Found curl ... using curl"
+  curl ${__MVNW_QUIET_CURL:+"$__MVNW_QUIET_CURL"} -f -L -o "$TMP_DOWNLOAD_DIR/$distributionUrlName" "$distributionUrl" || die "curl: Failed to fetch $distributionUrl"
+elif set_java_home; then
+  verbose "Falling back to use Java to download"
+  javaSource="$TMP_DOWNLOAD_DIR/Downloader.java"
+  targetZip="$TMP_DOWNLOAD_DIR/$distributionUrlName"
+  cat >"$javaSource" <<-END
+	public class Downloader extends java.net.Authenticator
+	{
+	  protected java.net.PasswordAuthentication getPasswordAuthentication()
+	  {
+	    return new java.net.PasswordAuthentication( System.getenv( "MVNW_USERNAME" ), System.getenv( "MVNW_PASSWORD" ).toCharArray() );
+	  }
+	  public static void main( String[] args ) throws Exception
+	  {
+	    setDefault( new Downloader() );
+	    java.nio.file.Files.copy( java.net.URI.create( args[0] ).toURL().openStream(), java.nio.file.Paths.get( args[1] ).toAbsolutePath().normalize() );
+	  }
+	}
+	END
+  # For Cygwin/MinGW, switch paths to Windows format before running javac and java
+  verbose " - Compiling Downloader.java ..."
+  "$(native_path "$JAVACCMD")" "$(native_path "$javaSource")" || die "Failed to compile Downloader.java"
+  verbose " - Running Downloader.java ..."
+  "$(native_path "$JAVACMD")" -cp "$(native_path "$TMP_DOWNLOAD_DIR")" Downloader "$distributionUrl" "$(native_path "$targetZip")"
+fi
+
+# If specified, validate the SHA-256 sum of the Maven distribution zip file
+if [ -n "${distributionSha256Sum-}" ]; then
+  distributionSha256Result=false
+  if [ "$MVN_CMD" = mvnd.sh ]; then
+    echo "Checksum validation is not supported for maven-mvnd." >&2
+    echo "Please disable validation by removing 'distributionSha256Sum' from your maven-wrapper.properties." >&2
+    exit 1
+  elif command -v sha256sum >/dev/null; then
+    if echo "$distributionSha256Sum  $TMP_DOWNLOAD_DIR/$distributionUrlName" | sha256sum -c - >/dev/null 2>&1; then
+      distributionSha256Result=true
+    fi
+  elif command -v shasum >/dev/null; then
+    if echo "$distributionSha256Sum  $TMP_DOWNLOAD_DIR/$distributionUrlName" | shasum -a 256 -c >/dev/null 2>&1; then
+      distributionSha256Result=true
+    fi
+  else
+    echo "Checksum validation was requested but neither 'sha256sum' or 'shasum' are available." >&2
+    echo "Please disable validation by removing 'distributionSha256Sum' from your maven-wrapper.properties." >&2
+    exit 1
+  fi
+  if [ $distributionSha256Result = false ]; then
+    echo "Error: Failed to validate Maven distribution SHA-256, your Maven distribution might be compromised." >&2
+    echo "If you updated your Maven version, you need to update the specified distributionSha256Sum property." >&2
+    exit 1
+  fi
+fi
+
+# unzip and move
+if command -v unzip >/dev/null; then
+  unzip ${__MVNW_QUIET_UNZIP:+"$__MVNW_QUIET_UNZIP"} "$TMP_DOWNLOAD_DIR/$distributionUrlName" -d "$TMP_DOWNLOAD_DIR" || die "failed to unzip"
+else
+  tar xzf${__MVNW_QUIET_TAR:+"$__MVNW_QUIET_TAR"} "$TMP_DOWNLOAD_DIR/$distributionUrlName" -C "$TMP_DOWNLOAD_DIR" || die "failed to untar"
+fi
+
+# Find the actual extracted directory name (handles snapshots where filename != directory name)
+actualDistributionDir=""
+
+# First try the expected directory name (for regular distributions)
+if [ -d "$TMP_DOWNLOAD_DIR/$distributionUrlNameMain" ]; then
+  if [ -f "$TMP_DOWNLOAD_DIR/$distributionUrlNameMain/bin/$MVN_CMD" ]; then
+    actualDistributionDir="$distributionUrlNameMain"
+  fi
+fi
+
+# If not found, search for any directory with the Maven executable (for snapshots)
+if [ -z "$actualDistributionDir" ]; then
+  # enable globbing to iterate over items
+  set +f
+  for dir in "$TMP_DOWNLOAD_DIR"/*; do
+    if [ -d "$dir" ]; then
+      if [ -f "$dir/bin/$MVN_CMD" ]; then
+        actualDistributionDir="$(basename "$dir")"
+        break
+      fi
+    fi
+  done
+  set -f
+fi
+
+if [ -z "$actualDistributionDir" ]; then
+  verbose "Contents of $TMP_DOWNLOAD_DIR:"
+  verbose "$(ls -la "$TMP_DOWNLOAD_DIR")"
+  die "Could not find Maven distribution directory in extracted archive"
+fi
+
+verbose "Found extracted Maven distribution directory: $actualDistributionDir"
+printf %s\\n "$distributionUrl" >"$TMP_DOWNLOAD_DIR/$actualDistributionDir/mvnw.url"
+mv -- "$TMP_DOWNLOAD_DIR/$actualDistributionDir" "$MAVEN_HOME" || [ -d "$MAVEN_HOME" ] || die "fail to move MAVEN_HOME"
+
+clean || :
+exec_maven "$@"

e2e/java/mvnw.cmd

@@ -0,0 +1,189 @@
+<# : batch portion
+@REM ----------------------------------------------------------------------------
+@REM Licensed to the Apache Software Foundation (ASF) under one
+@REM or more contributor license agreements.  See the NOTICE file
+@REM distributed with this work for additional information
+@REM regarding copyright ownership.  The ASF licenses this file
+@REM to you under the Apache License, Version 2.0 (the
+@REM "License"); you may not use this file except in compliance
+@REM with the License.  You may obtain a copy of the License at
+@REM
+@REM    http://www.apache.org/licenses/LICENSE-2.0
+@REM
+@REM Unless required by applicable law or agreed to in writing,
+@REM software distributed under the License is distributed on an
+@REM "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+@REM KIND, either express or implied.  See the License for the
+@REM specific language governing permissions and limitations
+@REM under the License.
+@REM ----------------------------------------------------------------------------
+
+@REM ----------------------------------------------------------------------------
+@REM Apache Maven Wrapper startup batch script, version 3.3.4
+@REM
+@REM Optional ENV vars
+@REM   MVNW_REPOURL - repo url base for downloading maven distribution
+@REM   MVNW_USERNAME/MVNW_PASSWORD - user and password for downloading maven
+@REM   MVNW_VERBOSE - true: enable verbose log; others: silence the output
+@REM ----------------------------------------------------------------------------
+
+@IF "%__MVNW_ARG0_NAME__%"=="" (SET __MVNW_ARG0_NAME__=%~nx0)
+@SET __MVNW_CMD__=
+@SET __MVNW_ERROR__=
+@SET __MVNW_PSMODULEP_SAVE=%PSModulePath%
+@SET PSModulePath=
+@FOR /F "usebackq tokens=1* delims==" %%A IN (`powershell -noprofile "& {$scriptDir='%~dp0'; $script='%__MVNW_ARG0_NAME__%'; icm -ScriptBlock ([Scriptblock]::Create((Get-Content -Raw '%~f0'))) -NoNewScope}"`) DO @(
+  IF "%%A"=="MVN_CMD" (set __MVNW_CMD__=%%B) ELSE IF "%%B"=="" (echo %%A) ELSE (echo %%A=%%B)
+)
+@SET PSModulePath=%__MVNW_PSMODULEP_SAVE%
+@SET __MVNW_PSMODULEP_SAVE%
+@SET __MVNW_ARG0_NAME__=
+@SET MVNW_USERNAME=
+@SET MVNW_PASSWORD=
+@IF NOT "%__MVNW_CMD__%"=="" ("%__MVNW_CMD__%" %*)
+@echo Cannot start maven from wrapper >&2 && exit /b 1
+@GOTO :EOF
+: end batch / begin powershell #>
+
+$ErrorActionPreference = "Stop"
+if ($env:MVNW_VERBOSE -eq "true") {
+  $VerbosePreference = "Continue"
+}
+
+# calculate distributionUrl, requires .mvn/wrapper/maven-wrapper.properties
+$distributionUrl = (Get-Content -Raw "$scriptDir/.mvn/wrapper/maven-wrapper.properties" | ConvertFrom-StringData).distributionUrl
+if (!$distributionUrl) {
+  Write-Error "cannot read distributionUrl property in $scriptDir/.mvn/wrapper/maven-wrapper.properties"
+}
+
+switch -wildcard -casesensitive ( $($distributionUrl -replace '^.*/','') ) {
+  "maven-mvnd-*" {
+    $USE_MVND = $true
+    $distributionUrl = $distributionUrl -replace '-bin\.[^.]*$',"-windows-amd64.zip"
+    $MVN_CMD = "mvnd.cmd"
+    break
+  }
+  default {
+    $USE_MVND = $false
+    $MVN_CMD = $script -replace '^mvnw','mvn'
+    break
+  }
+}
+
+# apply MVNW_REPOURL and calculate MAVEN_HOME
+# maven home pattern: ~/.m2/wrapper/dists/{apache-maven-<version>,maven-mvnd-<version>-<platform>}/<hash>
+if ($env:MVNW_REPOURL) {
+  $MVNW_REPO_PATTERN = if ($USE_MVND -eq $False) { "/org/apache/maven/" } else { "/maven/mvnd/" }
+  $distributionUrl = "$env:MVNW_REPOURL$MVNW_REPO_PATTERN$($distributionUrl -replace "^.*$MVNW_REPO_PATTERN",'')"
+}
+$distributionUrlName = $distributionUrl -replace '^.*/',''
+$distributionUrlNameMain = $distributionUrlName -replace '\.[^.]*$','' -replace '-bin$',''
+
+$MAVEN_M2_PATH = "$HOME/.m2"
+if ($env:MAVEN_USER_HOME) {
+  $MAVEN_M2_PATH = "$env:MAVEN_USER_HOME"
+}
+
+if (-not (Test-Path -Path $MAVEN_M2_PATH)) {
+    New-Item -Path $MAVEN_M2_PATH -ItemType Directory | Out-Null
+}
+
+$MAVEN_WRAPPER_DISTS = $null
+if ((Get-Item $MAVEN_M2_PATH).Target[0] -eq $null) {
+  $MAVEN_WRAPPER_DISTS = "$MAVEN_M2_PATH/wrapper/dists"
+} else {
+  $MAVEN_WRAPPER_DISTS = (Get-Item $MAVEN_M2_PATH).Target[0] + "/wrapper/dists"
+}
+
+$MAVEN_HOME_PARENT = "$MAVEN_WRAPPER_DISTS/$distributionUrlNameMain"
+$MAVEN_HOME_NAME = ([System.Security.Cryptography.SHA256]::Create().ComputeHash([byte[]][char[]]$distributionUrl) | ForEach-Object {$_.ToString("x2")}) -join ''
+$MAVEN_HOME = "$MAVEN_HOME_PARENT/$MAVEN_HOME_NAME"
+
+if (Test-Path -Path "$MAVEN_HOME" -PathType Container) {
+  Write-Verbose "found existing MAVEN_HOME at $MAVEN_HOME"
+  Write-Output "MVN_CMD=$MAVEN_HOME/bin/$MVN_CMD"
+  exit $?
+}
+
+if (! $distributionUrlNameMain -or ($distributionUrlName -eq $distributionUrlNameMain)) {
+  Write-Error "distributionUrl is not valid, must end with *-bin.zip, but found $distributionUrl"
+}
+
+# prepare tmp dir
+$TMP_DOWNLOAD_DIR_HOLDER = New-TemporaryFile
+$TMP_DOWNLOAD_DIR = New-Item -Itemtype Directory -Path "$TMP_DOWNLOAD_DIR_HOLDER.dir"
+$TMP_DOWNLOAD_DIR_HOLDER.Delete() | Out-Null
+trap {
+  if ($TMP_DOWNLOAD_DIR.Exists) {
+    try { Remove-Item $TMP_DOWNLOAD_DIR -Recurse -Force | Out-Null }
+    catch { Write-Warning "Cannot remove $TMP_DOWNLOAD_DIR" }
+  }
+}
+
+New-Item -Itemtype Directory -Path "$MAVEN_HOME_PARENT" -Force | Out-Null
+
+# Download and Install Apache Maven
+Write-Verbose "Couldn't find MAVEN_HOME, downloading and installing it ..."
+Write-Verbose "Downloading from: $distributionUrl"
+Write-Verbose "Downloading to: $TMP_DOWNLOAD_DIR/$distributionUrlName"
+
+$webclient = New-Object System.Net.WebClient
+if ($env:MVNW_USERNAME -and $env:MVNW_PASSWORD) {
+  $webclient.Credentials = New-Object System.Net.NetworkCredential($env:MVNW_USERNAME, $env:MVNW_PASSWORD)
+}
+[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12
+$webclient.DownloadFile($distributionUrl, "$TMP_DOWNLOAD_DIR/$distributionUrlName") | Out-Null
+
+# If specified, validate the SHA-256 sum of the Maven distribution zip file
+$distributionSha256Sum = (Get-Content -Raw "$scriptDir/.mvn/wrapper/maven-wrapper.properties" | ConvertFrom-StringData).distributionSha256Sum
+if ($distributionSha256Sum) {
+  if ($USE_MVND) {
+    Write-Error "Checksum validation is not supported for maven-mvnd. `nPlease disable validation by removing 'distributionSha256Sum' from your maven-wrapper.properties."
+  }
+  Import-Module $PSHOME\Modules\Microsoft.PowerShell.Utility -Function Get-FileHash
+  if ((Get-FileHash "$TMP_DOWNLOAD_DIR/$distributionUrlName" -Algorithm SHA256).Hash.ToLower() -ne $distributionSha256Sum) {
+    Write-Error "Error: Failed to validate Maven distribution SHA-256, your Maven distribution might be compromised. If you updated your Maven version, you need to update the specified distributionSha256Sum property."
+  }
+}
+
+# unzip and move
+Expand-Archive "$TMP_DOWNLOAD_DIR/$distributionUrlName" -DestinationPath "$TMP_DOWNLOAD_DIR" | Out-Null
+
+# Find the actual extracted directory name (handles snapshots where filename != directory name)
+$actualDistributionDir = ""
+
+# First try the expected directory name (for regular distributions)
+$expectedPath = Join-Path "$TMP_DOWNLOAD_DIR" "$distributionUrlNameMain"
+$expectedMvnPath = Join-Path "$expectedPath" "bin/$MVN_CMD"
+if ((Test-Path -Path $expectedPath -PathType Container) -and (Test-Path -Path $expectedMvnPath -PathType Leaf)) {
+  $actualDistributionDir = $distributionUrlNameMain
+}
+
+# If not found, search for any directory with the Maven executable (for snapshots)
+if (!$actualDistributionDir) {
+  Get-ChildItem -Path "$TMP_DOWNLOAD_DIR" -Directory | ForEach-Object {
+    $testPath = Join-Path $_.FullName "bin/$MVN_CMD"
+    if (Test-Path -Path $testPath -PathType Leaf) {
+      $actualDistributionDir = $_.Name
+    }
+  }
+}
+
+if (!$actualDistributionDir) {
+  Write-Error "Could not find Maven distribution directory in extracted archive"
+}
+
+Write-Verbose "Found extracted Maven distribution directory: $actualDistributionDir"
+Rename-Item -Path "$TMP_DOWNLOAD_DIR/$actualDistributionDir" -NewName $MAVEN_HOME_NAME | Out-Null
+try {
+  Move-Item -Path "$TMP_DOWNLOAD_DIR/$MAVEN_HOME_NAME" -Destination $MAVEN_HOME_PARENT | Out-Null
+} catch {
+  if (! (Test-Path -Path "$MAVEN_HOME" -PathType Container)) {
+    Write-Error "fail to move MAVEN_HOME"
+  }
+} finally {
+  try { Remove-Item $TMP_DOWNLOAD_DIR -Recurse -Force | Out-Null }
+  catch { Write-Warning "Cannot remove $TMP_DOWNLOAD_DIR" }
+}
+
+Write-Output "MVN_CMD=$MAVEN_HOME/bin/$MVN_CMD"

e2e/java/pom.xml

@@ -0,0 +1,98 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project xmlns="http://maven.apache.org/POM/4.0.0"
+         xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
+         xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
+    <modelVersion>4.0.0</modelVersion>
+
+    <groupId>dev.kreuzberg</groupId>
+    <artifactId>kreuzberg-e2e-java</artifactId>
+    <version>0.1.0</version>
+
+    <properties>
+        <maven.compiler.source>25</maven.compiler.source>
+        <maven.compiler.target>25</maven.compiler.target>
+        <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
+        <junit.version>6.1.0</junit.version>
+    </properties>
+
+    <dependencyManagement>
+        <dependencies>
+            <dependency>
+                <groupId>org.junit</groupId>
+                <artifactId>junit-bom</artifactId>
+                <version>${junit.version}</version>
+                <type>pom</type>
+                <scope>import</scope>
+            </dependency>
+        </dependencies>
+    </dependencyManagement>
+
+    <dependencies>
+        <dependency>
+            <groupId>dev.kreuzberg</groupId>
+            <artifactId>kreuzberg</artifactId>
+            <version>5.0.0-rc.3</version>
+            <scope>system</scope>
+            <systemPath>${project.basedir}/../../packages/java/target/kreuzberg-5.0.0-rc.3.jar</systemPath>
+        </dependency>
+        <dependency>
+            <groupId>com.fasterxml.jackson.core</groupId>
+            <artifactId>jackson-databind</artifactId>
+            <version>2.18.2</version>
+        </dependency>
+        <dependency>
+            <groupId>com.fasterxml.jackson.datatype</groupId>
+            <artifactId>jackson-datatype-jdk8</artifactId>
+            <version>2.18.2</version>
+        </dependency>
+        <dependency>
+            <groupId>org.jetbrains</groupId>
+            <artifactId>annotations</artifactId>
+            <version>24.1.0</version>
+        </dependency>
+        <dependency>
+            <groupId>org.junit.jupiter</groupId>
+            <artifactId>junit-jupiter</artifactId>
+            <version>${junit.version}</version>
+            <scope>test</scope>
+        </dependency>
+        <dependency>
+            <groupId>org.junit.platform</groupId>
+            <artifactId>junit-platform-launcher</artifactId>
+            <scope>test</scope>
+        </dependency>
+    </dependencies>
+
+    <build>
+        <plugins>
+            <plugin>
+                <groupId>org.codehaus.mojo</groupId>
+                <artifactId>build-helper-maven-plugin</artifactId>
+                <version>3.6.1</version>
+                <executions>
+                    <execution>
+                        <id>add-test-source</id>
+                        <phase>generate-test-sources</phase>
+                        <goals>
+                            <goal>add-test-source</goal>
+                        </goals>
+                        <configuration>
+                            <sources>
+                                <source>src/test/java</source>
+                            </sources>
+                        </configuration>
+                    </execution>
+                </executions>
+            </plugin>
+            <plugin>
+                <groupId>org.apache.maven.plugins</groupId>
+                <artifactId>maven-surefire-plugin</artifactId>
+                <version>3.5.2</version>
+                <configuration>
+                    <argLine>--enable-preview --enable-native-access=ALL-UNNAMED -Djava.library.path=${project.basedir}/../../target/release</argLine>
+                    <workingDirectory>${project.basedir}/../../test_documents</workingDirectory>
+                </configuration>
+            </plugin>
+        </plugins>
+    </build>
+</project>

e2e/java/src/test/java/dev/kreuzberg/e2e/AsyncTest.java

@@ -0,0 +1,63 @@
+// This file is auto-generated by alef — DO NOT EDIT.
+// alef:hash:4e15143f4af1ae8bafbdb1506ef057da924484c66a19483966333558ad437e75
+// To regenerate: alef generate
+// To verify freshness: alef verify --exit-code
+// Issues & docs: https://github.com/kreuzberg-dev/alef
+
+package dev.kreuzberg.e2e;
+
+import org.junit.jupiter.api.Test;
+import static org.junit.jupiter.api.Assertions.*;
+import dev.kreuzberg.Kreuzberg;
+import dev.kreuzberg.ExtractionConfig;
+import java.util.Optional;
+import dev.kreuzberg.JsonUtil;
+
+/** E2e tests for category: async. */
+class AsyncTest {
+
+    @Test
+    void testAsyncExtractBytes() throws Exception {
+        // Async extract_bytes call on PDF document
+        var result = Kreuzberg.extractBytes(java.nio.file.Files.readAllBytes(java.nio.file.Path.of("pdf/fake_memo.pdf")), "application/pdf", ExtractionConfig.builder().build());
+assertEquals("application/pdf", result.mimeType().trim());assertTrue(result.content().length() >= 50, "expected length >= 50");
+
+    }
+
+
+    @Test
+    void testAsyncExtractBytesEmptyMime() throws Exception {
+        // extract_bytes empty MIME async
+        // Wrap setup_lines + call_expr inside the lambda so error fixtures
+        // catch failures at *any* step — including `<Type>.fromJson(...)`
+        // calls that throw on malformed JSON (e.g. error fixtures with an
+        // invalid enum value like `"purpose":"invalid-purpose"`). Mirrors
+        // the C# `Assert.ThrowsAnyAsync(() => client.X(Type.FromJson(...)))`
+        // pattern.
+        assertThrows(Exception.class, () -> {
+        var config = JsonUtil.fromJson("{}", ExtractionConfig.class);
+
+            Kreuzberg.extractBytes(java.nio.file.Files.readAllBytes(java.nio.file.Path.of("text/plain.txt")), "", config);
+        });
+
+    }
+
+
+    @Test
+    void testAsyncExtractBytesInvalidMime() throws Exception {
+        // extract_bytes unsupported MIME async
+        // Wrap setup_lines + call_expr inside the lambda so error fixtures
+        // catch failures at *any* step — including `<Type>.fromJson(...)`
+        // calls that throw on malformed JSON (e.g. error fixtures with an
+        // invalid enum value like `"purpose":"invalid-purpose"`). Mirrors
+        // the C# `Assert.ThrowsAnyAsync(() => client.X(Type.FromJson(...)))`
+        // pattern.
+        assertThrows(Exception.class, () -> {
+        var config = JsonUtil.fromJson("{}", ExtractionConfig.class);
+
+            Kreuzberg.extractBytes(java.nio.file.Files.readAllBytes(java.nio.file.Path.of("text/plain.txt")), "application/x-nonexistent", config);
+        });
+
+    }
+
+}

e2e/java/src/test/java/dev/kreuzberg/e2e/BatchTest.java

@@ -0,0 +1,110 @@
+// This file is auto-generated by alef — DO NOT EDIT.
+// alef:hash:4e15143f4af1ae8bafbdb1506ef057da924484c66a19483966333558ad437e75
+// To regenerate: alef generate
+// To verify freshness: alef verify --exit-code
+// Issues & docs: https://github.com/kreuzberg-dev/alef
+
+package dev.kreuzberg.e2e;
+
+import org.junit.jupiter.api.Test;
+import static org.junit.jupiter.api.Assertions.*;
+import dev.kreuzberg.Kreuzberg;
+import dev.kreuzberg.BatchBytesItem;
+import dev.kreuzberg.BatchFileItem;
+import dev.kreuzberg.ExtractionConfig;
+import java.util.Optional;
+import dev.kreuzberg.JsonUtil;
+
+/** E2e tests for category: batch. */
+class BatchTest {
+
+    @Test
+    void testBatchBytesInvalidMime() throws Exception {
+        // batch_extract_bytes_sync invalid MIME
+        var result = Kreuzberg.batchExtractBytesSync(java.util.Arrays.asList(new BatchBytesItem(new byte[] {(byte) 72, (byte) 101, (byte) 108, (byte) 108, (byte) 111}, "application/x-nonexistent", null)), ExtractionConfig.builder().build());
+
+
+    }
+
+
+    @Test
+    void testBatchExtractBytesHappy() throws Exception {
+        // batch_extract_bytes: happy path with mixed inputs
+        var result = Kreuzberg.batchExtractBytes(java.util.Arrays.asList(new BatchBytesItem(new byte[] {(byte) 72, (byte) 101, (byte) 108, (byte) 108, (byte) 111, (byte) 44, (byte) 32, (byte) 119, (byte) 111, (byte) 114, (byte) 108, (byte) 100, (byte) 33}, "text/plain", null), new BatchBytesItem(new byte[] {(byte) 60, (byte) 104, (byte) 116, (byte) 109, (byte) 108, (byte) 62, (byte) 60, (byte) 98, (byte) 111, (byte) 100, (byte) 121, (byte) 62, (byte) 84, (byte) 101, (byte) 115, (byte) 116, (byte) 60, (byte) 47, (byte) 98, (byte) 111, (byte) 100, (byte) 121, (byte) 62, (byte) 60, (byte) 47, (byte) 104, (byte) 116, (byte) 109, (byte) 108, (byte) 62}, "text/html", null)), ExtractionConfig.builder().build());
+assertTrue(result.size() >= 1, "expected at least 1 elements");
+
+    }
+
+
+    @Test
+    void testBatchExtractBytesMixedFormat() throws Exception {
+        // batch_extract_bytes: handles unsupported MIME gracefully
+        var result = Kreuzberg.batchExtractBytes(java.util.Arrays.asList(new BatchBytesItem(new byte[] {(byte) 80, (byte) 68, (byte) 70, (byte) 32, (byte) 112, (byte) 108, (byte) 97, (byte) 99, (byte) 101, (byte) 104, (byte) 111, (byte) 108, (byte) 100, (byte) 101, (byte) 114}, "application/x-unknown", null)), ExtractionConfig.builder().build());
+
+
+    }
+
+
+    @Test
+    void testBatchExtractBytesSyncEmptyList() throws Exception {
+        // batch_extract_bytes_sync: empty batch
+        var result = Kreuzberg.batchExtractBytesSync(java.util.Arrays.asList(), ExtractionConfig.builder().build());
+assertEquals(0, result.size(), "expected exactly 0 elements");
+
+    }
+
+
+    @Test
+    void testBatchExtractBytesSyncInvalidMime() throws Exception {
+        // batch_extract_bytes_sync: unsupported MIME
+        var result = Kreuzberg.batchExtractBytesSync(java.util.Arrays.asList(new BatchBytesItem(new byte[] {(byte) 100, (byte) 97, (byte) 116, (byte) 97}, "application/x-unknown", null)), ExtractionConfig.builder().build());
+
+
+    }
+
+
+    @Test
+    void testBatchFileAsyncBasic() throws Exception {
+        // Extract text from multiple files asynchronously
+        var result = Kreuzberg.batchExtractFiles(java.util.Arrays.asList(new BatchFileItem(java.nio.file.Paths.get("pdf/fake_memo.pdf"), null), new BatchFileItem(java.nio.file.Paths.get("text/fake_text.txt"), null)), ExtractionConfig.builder().build());
+
+
+    }
+
+
+    @Test
+    void testBatchFileAsyncNotFound() throws Exception {
+        // batch_extract_file async nonexistent
+        var result = Kreuzberg.batchExtractFiles(java.util.Arrays.asList(new BatchFileItem(java.nio.file.Paths.get("/nonexistent/a.pdf"), null)), ExtractionConfig.builder().build());
+
+
+    }
+
+
+    @Test
+    void testBatchFileNotFound() throws Exception {
+        // batch_extract_file_sync nonexistent
+        var result = Kreuzberg.batchExtractFilesSync(java.util.Arrays.asList(new BatchFileItem(java.nio.file.Paths.get("/nonexistent/a.pdf"), null), new BatchFileItem(java.nio.file.Paths.get("/nonexistent/b.txt"), null)), ExtractionConfig.builder().build());
+
+
+    }
+
+
+    @Test
+    void testBatchFilePartial() throws Exception {
+        // batch_extract_file_sync mixed
+        var result = Kreuzberg.batchExtractFilesSync(java.util.Arrays.asList(new BatchFileItem(java.nio.file.Paths.get("text/plain.txt"), null), new BatchFileItem(java.nio.file.Paths.get("/nonexistent/missing.pdf"), null)), ExtractionConfig.builder().build());
+
+
+    }
+
+
+    @Test
+    void testBatchFileSyncBasic() throws Exception {
+        // Extract text from multiple files synchronously
+        var result = Kreuzberg.batchExtractFilesSync(java.util.Arrays.asList(new BatchFileItem(java.nio.file.Paths.get("pdf/fake_memo.pdf"), null), new BatchFileItem(java.nio.file.Paths.get("text/fake_text.txt"), null)), ExtractionConfig.builder().build());
+
+
+    }
+
+}

e2e/java/src/test/java/dev/kreuzberg/e2e/CodeTest.java

@@ -0,0 +1,27 @@
+// This file is auto-generated by alef — DO NOT EDIT.
+// alef:hash:4e15143f4af1ae8bafbdb1506ef057da924484c66a19483966333558ad437e75
+// To regenerate: alef generate
+// To verify freshness: alef verify --exit-code
+// Issues & docs: https://github.com/kreuzberg-dev/alef
+
+package dev.kreuzberg.e2e;
+
+import org.junit.jupiter.api.Test;
+import static org.junit.jupiter.api.Assertions.*;
+import dev.kreuzberg.Kreuzberg;
+import dev.kreuzberg.ExtractionConfig;
+import java.util.Optional;
+import dev.kreuzberg.JsonUtil;
+
+/** E2e tests for category: code. */
+class CodeTest {
+
+    @Test
+    void testCodeShebangDetection() throws Exception {
+        // Test language detection from shebang line via bytes input
+        var result = Kreuzberg.extractFileSync(java.nio.file.Path.of("code/script.sh"), "text/x-source-code", ExtractionConfig.builder().build());
+assertEquals("text/x-source-code", result.mimeType().trim());assertTrue(result.content().length() >= 10, "expected length >= 10");assertTrue(result.content().contains("build"), "expected to contain: " + "build");assertTrue(result.content().contains("clean"), "expected to contain: " + "clean");
+
+    }
+
+}

e2e/java/src/test/java/dev/kreuzberg/e2e/ContractTest.java

@@ -0,0 +1,197 @@
+// This file is auto-generated by alef — DO NOT EDIT.
+// alef:hash:4e15143f4af1ae8bafbdb1506ef057da924484c66a19483966333558ad437e75
+// To regenerate: alef generate
+// To verify freshness: alef verify --exit-code
+// Issues & docs: https://github.com/kreuzberg-dev/alef
+
+package dev.kreuzberg.e2e;
+
+import org.junit.jupiter.api.Test;
+import static org.junit.jupiter.api.Assertions.*;
+import dev.kreuzberg.Kreuzberg;
+import dev.kreuzberg.ExtractionConfig;
+import java.util.Optional;
+import dev.kreuzberg.JsonUtil;
+
+/** E2e tests for category: contract. */
+class ContractTest {
+
+    @Test
+    void testApiBatchBytesAsync() throws Exception {
+        // Tests async batch bytes extraction API (batch_extract_bytes)
+        var result = Kreuzberg.extractFile(java.nio.file.Path.of("pdf/fake_memo.pdf"), null, ExtractionConfig.builder().build());
+assertEquals("application/pdf", result.mimeType().trim());assertTrue(result.content().length() >= 10, "expected length >= 10");assertTrue(result.content().contains("May 5, 2023") || result.content().contains("Mallori"), "expected to contain at least one of the specified values");
+
+    }
+
+
+    @Test
+    void testApiBatchBytesWithConfigsAsync() throws Exception {
+        // Tests async batch bytes extraction with per-file configs (batch_extract_bytes with file_configs parameter)
+        var config = JsonUtil.fromJson("{\"output_format\":\"markdown\"}", ExtractionConfig.class);
+
+        var result = Kreuzberg.extractFile(java.nio.file.Path.of("pdf/fake_memo.pdf"), null, config);
+assertEquals("application/pdf", result.mimeType().trim());assertTrue(result.content().length() >= 10, "expected length >= 10");        // skipped: field 'metadata.output_format' not available on result type
+
+    }
+
+
+    @Test
+    void testApiBatchFileAsync() throws Exception {
+        // Tests async batch file extraction API (batch_extract_file)
+        var result = Kreuzberg.extractFile(java.nio.file.Path.of("pdf/fake_memo.pdf"), null, ExtractionConfig.builder().build());
+assertEquals("application/pdf", result.mimeType().trim());assertTrue(result.content().length() >= 10, "expected length >= 10");assertTrue(result.content().contains("May 5, 2023") || result.content().contains("Mallori"), "expected to contain at least one of the specified values");
+
+    }
+
+
+    @Test
+    void testApiBatchFileWithConfigsAsync() throws Exception {
+        // Tests async batch file extraction with per-file configs (batch_extract_files with file_configs parameter)
+        var config = JsonUtil.fromJson("{\"output_format\":\"markdown\"}", ExtractionConfig.class);
+
+        var result = Kreuzberg.extractFile(java.nio.file.Path.of("pdf/fake_memo.pdf"), null, config);
+assertEquals("application/pdf", result.mimeType().trim());assertTrue(result.content().length() >= 10, "expected length >= 10");        // skipped: field 'metadata.output_format' not available on result type
+
+    }
+
+
+    @Test
+    void testApiExtractBytesAsync() throws Exception {
+        // Tests async bytes extraction API (extract_bytes)
+        var result = Kreuzberg.extractFile(java.nio.file.Path.of("pdf/fake_memo.pdf"), null, ExtractionConfig.builder().build());
+assertEquals("application/pdf", result.mimeType().trim());assertTrue(result.content().length() >= 10, "expected length >= 10");assertTrue(result.content().contains("May 5, 2023") || result.content().contains("Mallori"), "expected to contain at least one of the specified values");
+
+    }
+
+
+    @Test
+    void testApiExtractFileAsync() throws Exception {
+        // Tests async file extraction API (extract_file)
+        var result = Kreuzberg.extractFile(java.nio.file.Path.of("pdf/fake_memo.pdf"), null, ExtractionConfig.builder().build());
+assertEquals("application/pdf", result.mimeType().trim());assertTrue(result.content().length() >= 10, "expected length >= 10");assertTrue(result.content().contains("May 5, 2023") || result.content().contains("Mallori"), "expected to contain at least one of the specified values");
+
+    }
+
+
+    @Test
+    void testConfigChunkingPrependHeadingContext() throws Exception {
+        // Tests markdown chunker prepends heading hierarchy to chunk content
+        var config = JsonUtil.fromJson("{\"chunking\":{\"chunker_type\":\"markdown\",\"max_chars\":300,\"max_overlap\":50,\"prepend_heading_context\":true}}", ExtractionConfig.class);
+
+        var result = Kreuzberg.extractFileSync(java.nio.file.Path.of("markdown/extraction_test.md"), null, config);
+assertTrue(result.content().length() >= 10, "expected length >= 10");        // skipped: field 'chunks' not available on result type        assertTrue(java.util.Optional.ofNullable(result.chunks()).orElse(java.util.List.of()).stream().allMatch(c -> c.content() != null && !c.content().isBlank()), "expected true");        assertTrue(java.util.Optional.ofNullable(result.chunks()).orElse(java.util.List.of()).stream().allMatch(c -> c.metadata().headingContext() != null), "expected true");        assertTrue(java.util.Optional.ofNullable(result.chunks()).orElse(java.util.List.of()).stream().findFirst().map(c -> c.metadata().headingContext() != null).orElse(false), "expected true");
+
+    }
+
+
+    @Test
+    void testConfigDocumentStructureWithHeadings() throws Exception {
+        // Tests document structure with DOCX heading-driven nesting
+        var config = JsonUtil.fromJson("{\"include_document_structure\":true}", ExtractionConfig.class);
+
+        var result = Kreuzberg.extractFileSync(java.nio.file.Path.of("docx/fake.docx"), null, config);
+assertEquals("application/vnd.openxmlformats-officedocument.wordprocessingml.document", result.mimeType().trim());        // skipped: field 'document' not available on result type        // skipped: field 'document.nodes' not available on result type
+
+    }
+
+
+    @Test
+    void testConfigElementTypes() throws Exception {
+        // Tests element-based result format with element type assertions on DOCX
+        var config = JsonUtil.fromJson("{\"result_format\":\"element_based\"}", ExtractionConfig.class);
+
+        var result = Kreuzberg.extractFileSync(java.nio.file.Path.of("docx/unit_test_headers.docx"), null, config);
+assertTrue(result.mimeType().contains("application/vnd.openxmlformats-officedocument.wordprocessingml.document"), "expected to contain at least one of the specified values");        // skipped: field 'elements' not available on result type
+
+    }
+
+
+    @Test
+    void testConfigExtractionTimeout() throws Exception {
+        // Tests that extraction_timeout_secs config field is accepted and does not affect fast extractions
+        var config = JsonUtil.fromJson("{\"extraction_timeout_secs\":300}", ExtractionConfig.class);
+
+        var result = Kreuzberg.extractFileSync(java.nio.file.Path.of("pdf/fake_memo.pdf"), null, config);
+assertEquals("application/pdf", result.mimeType().trim());assertTrue(result.content().length() >= 10, "expected length >= 10");
+
+    }
+
+
+    @Test
+    void testConfigKeywords() throws Exception {
+        // Tests keyword extraction via YAKE algorithm
+        var config = JsonUtil.fromJson("{\"keywords\":{\"algorithm\":\"yake\",\"max_keywords\":10}}", ExtractionConfig.class);
+
+        var result = Kreuzberg.extractFileSync(java.nio.file.Path.of("pdf/fake_memo.pdf"), null, config);
+assertEquals("application/pdf", result.mimeType().trim());assertTrue(result.content().length() >= 10, "expected length >= 10");        // skipped: field 'keywords' not available on Java ExtractionResult        // skipped: field 'keywords' not available on Java ExtractionResult
+
+    }
+
+
+    @Test
+    void testConfigPages() throws Exception {
+        // Tests page extraction and page marker configuration
+        var config = JsonUtil.fromJson("{\"pages\":{\"extract_pages\":true,\"insert_page_markers\":true}}", ExtractionConfig.class);
+
+        var result = Kreuzberg.extractFileSync(java.nio.file.Path.of("pdf/fake_memo.pdf"), null, config);
+assertEquals("application/pdf", result.mimeType().trim());assertTrue(result.content().length() >= 10, "expected length >= 10");assertTrue(result.content().contains("PAGE"), "expected to contain at least one of the specified values");
+
+    }
+
+
+    @Test
+    void testConfigQualityEnabled() throws Exception {
+        // Tests quality scoring produces a score value in [0.0, 1.0]
+        var config = JsonUtil.fromJson("{\"enable_quality_processing\":true}", ExtractionConfig.class);
+
+        var result = Kreuzberg.extractFileSync(java.nio.file.Path.of("pdf/fake_memo.pdf"), null, config);
+assertEquals("application/pdf", result.mimeType().trim());assertTrue(result.content().length() >= 10, "expected length >= 10");        // skipped: field 'quality_score' not available on result type        // skipped: field 'quality_score' not available on result type        // skipped: field 'quality_score' not available on result type
+
+    }
+
+
+    @Test
+    void testConfigSecurityLimits() throws Exception {
+        // Tests archive extraction with custom security limits
+        var config = JsonUtil.fromJson("{\"security_limits\":{\"max_archive_size\":104857600,\"max_compression_ratio\":50,\"max_files_in_archive\":100}}", ExtractionConfig.class);
+
+        var result = Kreuzberg.extractFileSync(java.nio.file.Path.of("archives/documents.zip"), null, config);
+assertTrue(result.mimeType().contains("application/zip") || result.mimeType().contains("application/x-zip-compressed"), "expected to contain at least one of the specified values");assertTrue(result.content().length() >= 10, "expected length >= 10");
+
+    }
+
+
+    @Test
+    void testConfigTreeSitter() throws Exception {
+        // Tests tree-sitter configuration round-trip
+        var config = JsonUtil.fromJson("{\"tree_sitter\":{\"groups\":[\"web\"],\"languages\":[\"python\",\"rust\"],\"process\":{\"comments\":false,\"diagnostics\":false,\"docstrings\":false,\"exports\":true,\"imports\":true,\"structure\":true,\"symbols\":false}}}", ExtractionConfig.class);
+
+        var result = Kreuzberg.extractFileSync(java.nio.file.Path.of("code/hello.py"), null, config);
+assertEquals("text/x-source-code", result.mimeType().trim());assertTrue(result.content().length() >= 5, "expected length >= 5");
+
+    }
+
+
+    @Test
+    void testOutputFormatBytesMarkdown() throws Exception {
+        // Tests markdown output format via bytes extraction API
+        var config = JsonUtil.fromJson("{\"output_format\":\"markdown\"}", ExtractionConfig.class);
+
+        var result = Kreuzberg.extractBytesSync(java.nio.file.Files.readAllBytes(java.nio.file.Path.of("pdf/fake_memo.pdf")), "application/pdf", config);
+assertEquals("application/pdf", result.mimeType().trim());assertTrue(result.content().length() >= 10, "expected length >= 10");        // skipped: field 'metadata.output_format' not available on result type
+
+    }
+
+
+    @Test
+    void testOutputFormatMarkdown() throws Exception {
+        // Tests Markdown output format
+        var config = JsonUtil.fromJson("{\"output_format\":\"markdown\"}", ExtractionConfig.class);
+
+        var result = Kreuzberg.extractFileSync(java.nio.file.Path.of("pdf/fake_memo.pdf"), null, config);
+assertEquals("application/pdf", result.mimeType().trim());assertTrue(result.content().length() >= 10, "expected length >= 10");        // skipped: field 'metadata.output_format' not available on result type
+
+    }
+
+}

e2e/java/src/test/java/dev/kreuzberg/e2e/DetectionTest.java

@@ -0,0 +1,61 @@
+// This file is auto-generated by alef — DO NOT EDIT.
+// alef:hash:4e15143f4af1ae8bafbdb1506ef057da924484c66a19483966333558ad437e75
+// To regenerate: alef generate
+// To verify freshness: alef verify --exit-code
+// Issues & docs: https://github.com/kreuzberg-dev/alef
+
+package dev.kreuzberg.e2e;
+
+import org.junit.jupiter.api.Test;
+import static org.junit.jupiter.api.Assertions.*;
+import dev.kreuzberg.Kreuzberg;
+import dev.kreuzberg.ExtractionConfig;
+import java.util.Optional;
+import dev.kreuzberg.JsonUtil;
+
+/** E2e tests for category: detection. */
+class DetectionTest {
+
+    @Test
+    void testDetectMimeBytesHtml() throws Exception {
+        // Detect HTML MIME from bytes
+        var result = Kreuzberg.detectMimeTypeFromBytes(java.nio.file.Files.readAllBytes(java.nio.file.Path.of("html/html.html")));
+
+
+    }
+
+
+    @Test
+    void testDetectMimeBytesPdf() throws Exception {
+        // Detect PDF MIME type from bytes
+        var result = Kreuzberg.detectMimeTypeFromBytes(java.nio.file.Files.readAllBytes(java.nio.file.Path.of("pdf/fake_memo.pdf")));
+
+
+    }
+
+
+    @Test
+    void testDetectMimeBytesPng() throws Exception {
+        // Detect PNG MIME type from bytes
+        var result = Kreuzberg.detectMimeTypeFromBytes(java.nio.file.Files.readAllBytes(java.nio.file.Path.of("images/test_hello_world.png")));
+
+
+    }
+
+
+    @Test
+    void testGetExtensionsUnknownMime() throws Exception {
+        // get_extensions unknown MIME
+        // Wrap setup_lines + call_expr inside the lambda so error fixtures
+        // catch failures at *any* step — including `<Type>.fromJson(...)`
+        // calls that throw on malformed JSON (e.g. error fixtures with an
+        // invalid enum value like `"purpose":"invalid-purpose"`). Mirrors
+        // the C# `Assert.ThrowsAnyAsync(() => client.X(Type.FromJson(...)))`
+        // pattern.
+        assertThrows(Exception.class, () -> {
+            Kreuzberg.getExtensionsForMime("application/x-totally-unknown");
+        });
+
+    }
+
+}

e2e/java/src/test/java/dev/kreuzberg/e2e/DocumentExtractorManagementTest.java

@@ -0,0 +1,36 @@
+// This file is auto-generated by alef — DO NOT EDIT.
+// alef:hash:4e15143f4af1ae8bafbdb1506ef057da924484c66a19483966333558ad437e75
+// To regenerate: alef generate
+// To verify freshness: alef verify --exit-code
+// Issues & docs: https://github.com/kreuzberg-dev/alef
+
+package dev.kreuzberg.e2e;
+
+import org.junit.jupiter.api.Test;
+import static org.junit.jupiter.api.Assertions.*;
+import dev.kreuzberg.Kreuzberg;
+import dev.kreuzberg.ExtractionConfig;
+import java.util.Optional;
+import dev.kreuzberg.JsonUtil;
+
+/** E2e tests for category: document_extractor_management. */
+class DocumentExtractorManagementTest {
+
+    @Test
+    void testDocumentExtractorsClear() throws Exception {
+        // Clear all document extractors and verify list is empty
+        Kreuzberg.clearDocumentExtractors();
+
+
+    }
+
+
+    @Test
+    void testExtractorsList() throws Exception {
+        // List all registered document extractors
+        var result = Kreuzberg.listDocumentExtractors();
+
+
+    }
+
+}

e2e/java/src/test/java/dev/kreuzberg/e2e/EmbedAsyncPendingTest.java

@@ -0,0 +1,48 @@
+// This file is auto-generated by alef — DO NOT EDIT.
+// alef:hash:4e15143f4af1ae8bafbdb1506ef057da924484c66a19483966333558ad437e75
+// To regenerate: alef generate
+// To verify freshness: alef verify --exit-code
+// Issues & docs: https://github.com/kreuzberg-dev/alef
+
+package dev.kreuzberg.e2e;
+
+import org.junit.jupiter.api.Test;
+import static org.junit.jupiter.api.Assertions.*;
+import dev.kreuzberg.Kreuzberg;
+import dev.kreuzberg.EmbeddingConfig;
+import dev.kreuzberg.ExtractionConfig;
+import java.util.Optional;
+import dev.kreuzberg.JsonUtil;
+
+/** E2e tests for category: embed_async_pending. */
+class EmbedAsyncPendingTest {
+
+    @Test
+    void testEmbedTextsAsyncEmptyInput() throws Exception {
+        // embed_texts_async: empty text list
+        var result = Kreuzberg.embedTextsAsync(java.util.List.of(), EmbeddingConfig.builder().build());
+        // skipped: field 'embeddings' not available on result type
+
+    }
+
+
+    @Test
+    void testEmbedTextsAsyncHappy() throws Exception {
+        // embed_texts_async: basic async embedding
+        var result = Kreuzberg.embedTextsAsync(java.util.Arrays.asList(JsonUtil.fromJson("\"First\"", String.class), JsonUtil.fromJson("\"Second\"", String.class)), EmbeddingConfig.builder().build());
+        // skipped: field 'embeddings' not available on result type
+
+    }
+
+
+    @Test
+    void testEmbedTextsAsyncPresetSwitch() throws Exception {
+        // embed_texts_async: preset override
+        var config = JsonUtil.fromJson("{\"model\":{\"name\":\"balanced\",\"type\":\"preset\"}}", EmbeddingConfig.class);
+
+        var result = Kreuzberg.embedTextsAsync(java.util.Arrays.asList(JsonUtil.fromJson("\"Text\"", String.class)), config);
+
+
+    }
+
+}

e2e/java/src/test/java/dev/kreuzberg/e2e/EmbedExtraTest.java

@@ -0,0 +1,30 @@
+// This file is auto-generated by alef — DO NOT EDIT.
+// alef:hash:4e15143f4af1ae8bafbdb1506ef057da924484c66a19483966333558ad437e75
+// To regenerate: alef generate
+// To verify freshness: alef verify --exit-code
+// Issues & docs: https://github.com/kreuzberg-dev/alef
+
+package dev.kreuzberg.e2e;
+
+import org.junit.jupiter.api.Test;
+import static org.junit.jupiter.api.Assertions.*;
+import dev.kreuzberg.Kreuzberg;
+import dev.kreuzberg.EmbeddingConfig;
+import dev.kreuzberg.ExtractionConfig;
+import java.util.Optional;
+import dev.kreuzberg.JsonUtil;
+
+/** E2e tests for category: embed_extra. */
+class EmbedExtraTest {
+
+    @Test
+    void testEmbedTextsBatch() throws Exception {
+        // Batch embed texts
+        var config = JsonUtil.fromJson("{\"model\":{\"name\":\"balanced\",\"type\":\"preset\"}}", EmbeddingConfig.class);
+
+        var result = Kreuzberg.embedTexts(java.util.Arrays.asList(JsonUtil.fromJson("\"Hello\"", String.class), JsonUtil.fromJson("\"World\"", String.class)), config);
+
+
+    }
+
+}

e2e/java/src/test/java/dev/kreuzberg/e2e/EmbeddingBackendManagementTest.java

@@ -0,0 +1,36 @@
+// This file is auto-generated by alef — DO NOT EDIT.
+// alef:hash:4e15143f4af1ae8bafbdb1506ef057da924484c66a19483966333558ad437e75
+// To regenerate: alef generate
+// To verify freshness: alef verify --exit-code
+// Issues & docs: https://github.com/kreuzberg-dev/alef
+
+package dev.kreuzberg.e2e;
+
+import org.junit.jupiter.api.Test;
+import static org.junit.jupiter.api.Assertions.*;
+import dev.kreuzberg.Kreuzberg;
+import dev.kreuzberg.ExtractionConfig;
+import java.util.Optional;
+import dev.kreuzberg.JsonUtil;
+
+/** E2e tests for category: embedding_backend_management. */
+class EmbeddingBackendManagementTest {
+
+    @Test
+    void testEmbeddingBackendsClear() throws Exception {
+        // Clear all embedding backends and verify list is empty
+        Kreuzberg.clearEmbeddingBackends();
+
+
+    }
+
+
+    @Test
+    void testEmbeddingBackendsList() throws Exception {
+        // List all registered embedding backends
+        var result = Kreuzberg.listEmbeddingBackends();
+
+
+    }
+
+}

e2e/java/src/test/java/dev/kreuzberg/e2e/EmbeddingsTest.java

@@ -0,0 +1,67 @@
+// This file is auto-generated by alef — DO NOT EDIT.
+// alef:hash:4e15143f4af1ae8bafbdb1506ef057da924484c66a19483966333558ad437e75
+// To regenerate: alef generate
+// To verify freshness: alef verify --exit-code
+// Issues & docs: https://github.com/kreuzberg-dev/alef
+
+package dev.kreuzberg.e2e;
+
+import org.junit.jupiter.api.Test;
+import static org.junit.jupiter.api.Assertions.*;
+import dev.kreuzberg.Kreuzberg;
+import dev.kreuzberg.EmbeddingConfig;
+import dev.kreuzberg.ExtractionConfig;
+import java.util.Optional;
+import dev.kreuzberg.JsonUtil;
+
+/** E2e tests for category: embeddings. */
+class EmbeddingsTest {
+
+    @Test
+    void testEmbedTextsDifferentPreset() throws Exception {
+        // embed_texts: multilingual preset
+        var config = JsonUtil.fromJson("{\"model\":{\"name\":\"multilingual\",\"type\":\"preset\"}}", EmbeddingConfig.class);
+
+        var result = Kreuzberg.embedTexts(java.util.Arrays.asList(JsonUtil.fromJson("\"Hello world\"", String.class), JsonUtil.fromJson("\"Test\"", String.class)), config);
+        // skipped: field 'embeddings' not available on result type
+
+    }
+
+
+    @Test
+    void testGetEmbeddingPresetKnown() throws Exception {
+        // get_embedding_preset: known preset
+        var result = Kreuzberg.getEmbeddingPreset("balanced");
+
+
+    }
+
+
+    @Test
+    void testGetEmbeddingPresetNominal() throws Exception {
+        // get_embedding_preset: nominal case
+        var result = Kreuzberg.getEmbeddingPreset("balanced");
+
+
+    }
+
+
+    @Test
+    void testGetEmbeddingPresetUnknown() throws Exception {
+        // get_embedding_preset: unknown preset fails
+        var result = Kreuzberg.getEmbeddingPreset("nonexistent-xyz");
+        assertNull(result, "expected empty value");
+
+
+    }
+
+
+    @Test
+    void testListEmbeddingPresetsSanity() throws Exception {
+        // list_embedding_presets: returns at least one
+        var result = Kreuzberg.listEmbeddingPresets();
+assertFalse(result.isEmpty(), "expected non-empty value");
+
+    }
+
+}

e2e/java/src/test/java/dev/kreuzberg/e2e/ErrorTest.java

@@ -0,0 +1,101 @@
+// This file is auto-generated by alef — DO NOT EDIT.
+// alef:hash:4e15143f4af1ae8bafbdb1506ef057da924484c66a19483966333558ad437e75
+// To regenerate: alef generate
+// To verify freshness: alef verify --exit-code
+// Issues & docs: https://github.com/kreuzberg-dev/alef
+
+package dev.kreuzberg.e2e;
+
+import org.junit.jupiter.api.Test;
+import static org.junit.jupiter.api.Assertions.*;
+import dev.kreuzberg.Kreuzberg;
+import dev.kreuzberg.ExtractionConfig;
+import java.util.Optional;
+import dev.kreuzberg.JsonUtil;
+
+/** E2e tests for category: error. */
+class ErrorTest {
+
+    @Test
+    void testErrorEmptyBytes() throws Exception {
+        // Graceful handling of empty bytes (should not error)
+        var config = JsonUtil.fromJson("{}", ExtractionConfig.class);
+
+        var result = Kreuzberg.extractBytesSync(java.nio.file.Files.readAllBytes(java.nio.file.Path.of("text/empty.txt")), "text/plain", config);
+
+
+    }
+
+
+    @Test
+    void testErrorEmptyMime() throws Exception {
+        // Error when extracting with empty MIME type
+        // Wrap setup_lines + call_expr inside the lambda so error fixtures
+        // catch failures at *any* step — including `<Type>.fromJson(...)`
+        // calls that throw on malformed JSON (e.g. error fixtures with an
+        // invalid enum value like `"purpose":"invalid-purpose"`). Mirrors
+        // the C# `Assert.ThrowsAnyAsync(() => client.X(Type.FromJson(...)))`
+        // pattern.
+        assertThrows(Exception.class, () -> {
+        var config = JsonUtil.fromJson("{}", ExtractionConfig.class);
+
+            Kreuzberg.extractBytesSync(java.nio.file.Files.readAllBytes(java.nio.file.Path.of("text/plain.txt")), "", config);
+        });
+
+    }
+
+
+    @Test
+    void testErrorExtractBytesConflictingOcr() throws Exception {
+        // extract_bytes force+disable OCR
+        // Wrap setup_lines + call_expr inside the lambda so error fixtures
+        // catch failures at *any* step — including `<Type>.fromJson(...)`
+        // calls that throw on malformed JSON (e.g. error fixtures with an
+        // invalid enum value like `"purpose":"invalid-purpose"`). Mirrors
+        // the C# `Assert.ThrowsAnyAsync(() => client.X(Type.FromJson(...)))`
+        // pattern.
+        assertThrows(Exception.class, () -> {
+        var config = JsonUtil.fromJson("{\"disable_ocr\":true,\"force_ocr\":true}", ExtractionConfig.class);
+
+            Kreuzberg.extractBytesSync(java.nio.file.Files.readAllBytes(java.nio.file.Path.of("text/fake_text.txt")), "text/plain", config);
+        });
+
+    }
+
+
+    @Test
+    void testErrorInvalidMimeFormat() throws Exception {
+        // Error when extracting with invalid MIME type format
+        // Wrap setup_lines + call_expr inside the lambda so error fixtures
+        // catch failures at *any* step — including `<Type>.fromJson(...)`
+        // calls that throw on malformed JSON (e.g. error fixtures with an
+        // invalid enum value like `"purpose":"invalid-purpose"`). Mirrors
+        // the C# `Assert.ThrowsAnyAsync(() => client.X(Type.FromJson(...)))`
+        // pattern.
+        assertThrows(Exception.class, () -> {
+        var config = JsonUtil.fromJson("{}", ExtractionConfig.class);
+
+            Kreuzberg.extractBytesSync(java.nio.file.Files.readAllBytes(java.nio.file.Path.of("text/plain.txt")), "not-a-mime", config);
+        });
+
+    }
+
+
+    @Test
+    void testErrorUnsupportedMime() throws Exception {
+        // Error when extracting with unsupported MIME type
+        // Wrap setup_lines + call_expr inside the lambda so error fixtures
+        // catch failures at *any* step — including `<Type>.fromJson(...)`
+        // calls that throw on malformed JSON (e.g. error fixtures with an
+        // invalid enum value like `"purpose":"invalid-purpose"`). Mirrors
+        // the C# `Assert.ThrowsAnyAsync(() => client.X(Type.FromJson(...)))`
+        // pattern.
+        assertThrows(Exception.class, () -> {
+        var config = JsonUtil.fromJson("{}", ExtractionConfig.class);
+
+            Kreuzberg.extractBytesSync(java.nio.file.Files.readAllBytes(java.nio.file.Path.of("text/plain.txt")), "application/x-nonexistent", config);
+        });
+
+    }
+
+}

e2e/java/src/test/java/dev/kreuzberg/e2e/FormatSpecificTest.java

@@ -0,0 +1,63 @@
+// This file is auto-generated by alef — DO NOT EDIT.
+// alef:hash:4e15143f4af1ae8bafbdb1506ef057da924484c66a19483966333558ad437e75
+// To regenerate: alef generate
+// To verify freshness: alef verify --exit-code
+// Issues & docs: https://github.com/kreuzberg-dev/alef
+
+package dev.kreuzberg.e2e;
+
+import org.junit.jupiter.api.Test;
+import static org.junit.jupiter.api.Assertions.*;
+import dev.kreuzberg.Kreuzberg;
+import dev.kreuzberg.ExtractionConfig;
+import java.util.Optional;
+import dev.kreuzberg.JsonUtil;
+
+/** E2e tests for category: format_specific. */
+class FormatSpecificTest {
+
+    @Test
+    void testFormatDocxStandalone() throws Exception {
+        // Standalone DOCX extraction using extract_bytes_sync
+        var result = Kreuzberg.extractBytesSync(java.nio.file.Files.readAllBytes(java.nio.file.Path.of("docx/fake.docx")), "application/vnd.openxmlformats-officedocument.wordprocessingml.document", ExtractionConfig.builder().build());
+assertTrue(result.content().length() >= 20, "expected length >= 20");
+
+    }
+
+
+    @Test
+    void testFormatHwpxStandalone() throws Exception {
+        // Standalone HWPX extraction using extract_bytes_sync
+        var result = Kreuzberg.extractBytesSync(java.nio.file.Files.readAllBytes(java.nio.file.Path.of("hwpx/simple.hwpx")), "application/haansofthwpx", ExtractionConfig.builder().build());
+assertTrue(result.content().length() >= 20, "expected length >= 20");assertTrue(result.content().contains("Hello from HWPX"), "expected to contain: " + "Hello from HWPX");
+
+    }
+
+
+    @Test
+    void testFormatPdfText() throws Exception {
+        // Standalone PDF text extraction using extract_bytes_sync
+        var result = Kreuzberg.extractBytesSync(java.nio.file.Files.readAllBytes(java.nio.file.Path.of("pdf/fake_memo.pdf")), "application/pdf", ExtractionConfig.builder().build());
+assertTrue(result.content().length() >= 50, "expected length >= 50");assertTrue(result.content().contains("Mallori") || result.content().contains("May"), "expected to contain at least one of the specified values");
+
+    }
+
+
+    @Test
+    void testFormatPptx() throws Exception {
+        // PPTX presentation extraction using extract_file_sync
+        var result = Kreuzberg.extractFileSync(java.nio.file.Path.of("pptx/simple.pptx"), "application/vnd.openxmlformats-officedocument.presentationml.presentation", ExtractionConfig.builder().build());
+
+
+    }
+
+
+    @Test
+    void testFormatXlsx() throws Exception {
+        // XLSX spreadsheet extraction using extract_file_sync
+        var result = Kreuzberg.extractFileSync(java.nio.file.Path.of("xlsx/stanley_cups.xlsx"), "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet", ExtractionConfig.builder().build());
+
+
+    }
+
+}

e2e/java/src/test/java/dev/kreuzberg/e2e/MimeUtilitiesTest.java

@@ -0,0 +1,45 @@
+// This file is auto-generated by alef — DO NOT EDIT.
+// alef:hash:4e15143f4af1ae8bafbdb1506ef057da924484c66a19483966333558ad437e75
+// To regenerate: alef generate
+// To verify freshness: alef verify --exit-code
+// Issues & docs: https://github.com/kreuzberg-dev/alef
+
+package dev.kreuzberg.e2e;
+
+import org.junit.jupiter.api.Test;
+import static org.junit.jupiter.api.Assertions.*;
+import dev.kreuzberg.Kreuzberg;
+import dev.kreuzberg.ExtractionConfig;
+import java.util.Optional;
+import dev.kreuzberg.JsonUtil;
+
+/** E2e tests for category: mime_utilities. */
+class MimeUtilitiesTest {
+
+    @Test
+    void testMimeDetectBytes() throws Exception {
+        // Detect MIME type from file bytes
+        var result = Kreuzberg.detectMimeTypeFromBytes(java.nio.file.Files.readAllBytes(java.nio.file.Path.of("pdf/fake_memo.pdf")));
+assertTrue(result.contains("pdf"), "expected to contain: " + "pdf");
+
+    }
+
+
+    @Test
+    void testMimeDetectImage() throws Exception {
+        // Detect MIME type from PNG image bytes
+        var result = Kreuzberg.detectMimeTypeFromBytes(java.nio.file.Files.readAllBytes(java.nio.file.Path.of("images/test_hello_world.png")));
+assertTrue(result.contains("png"), "expected to contain: " + "png");
+
+    }
+
+
+    @Test
+    void testMimeGetExtensions() throws Exception {
+        // Get file extensions for a MIME type
+        var result = Kreuzberg.getExtensionsForMime("application/pdf");
+assertTrue(result.contains("pdf"), "expected to contain: " + "pdf");
+
+    }
+
+}

e2e/java/src/test/java/dev/kreuzberg/e2e/OcrBackendManagementTest.java

@@ -0,0 +1,45 @@
+// This file is auto-generated by alef — DO NOT EDIT.
+// alef:hash:4e15143f4af1ae8bafbdb1506ef057da924484c66a19483966333558ad437e75
+// To regenerate: alef generate
+// To verify freshness: alef verify --exit-code
+// Issues & docs: https://github.com/kreuzberg-dev/alef
+
+package dev.kreuzberg.e2e;
+
+import org.junit.jupiter.api.Test;
+import static org.junit.jupiter.api.Assertions.*;
+import dev.kreuzberg.Kreuzberg;
+import dev.kreuzberg.ExtractionConfig;
+import java.util.Optional;
+import dev.kreuzberg.JsonUtil;
+
+/** E2e tests for category: ocr_backend_management. */
+class OcrBackendManagementTest {
+
+    @Test
+    void testOcrBackendsClear() throws Exception {
+        // Clear all OCR backends and verify list is empty
+        Kreuzberg.clearOcrBackends();
+
+
+    }
+
+
+    @Test
+    void testOcrBackendsList() throws Exception {
+        // List all registered OCR backends
+        var result = Kreuzberg.listOcrBackends();
+
+
+    }
+
+
+    @Test
+    void testOcrBackendsUnregister() throws Exception {
+        // Unregister nonexistent OCR backend gracefully
+        Kreuzberg.unregisterOcrBackend("nonexistent-backend-xyz");
+
+
+    }
+
+}

e2e/java/src/test/java/dev/kreuzberg/e2e/PdfTest.java

@@ -0,0 +1,45 @@
+// This file is auto-generated by alef — DO NOT EDIT.
+// alef:hash:4e15143f4af1ae8bafbdb1506ef057da924484c66a19483966333558ad437e75
+// To regenerate: alef generate
+// To verify freshness: alef verify --exit-code
+// Issues & docs: https://github.com/kreuzberg-dev/alef
+
+package dev.kreuzberg.e2e;
+
+import org.junit.jupiter.api.Test;
+import static org.junit.jupiter.api.Assertions.*;
+import dev.kreuzberg.Kreuzberg;
+import dev.kreuzberg.ExtractionConfig;
+import java.util.Optional;
+import dev.kreuzberg.JsonUtil;
+
+/** E2e tests for category: pdf. */
+class PdfTest {
+
+    @Test
+    void testRenderPdfPageFirst() throws Exception {
+        // render_pdf_page_to_png: first page
+        var result = Kreuzberg.renderPdfPageToPng(java.nio.file.Files.readAllBytes(java.nio.file.Path.of("pdf/fake_memo.pdf")), 0, null, null);
+        assertNotNull(result, "expected non-null byte[] response");
+        // skipped: assertion type 'min_length' not supported on byte[] result
+
+
+    }
+
+
+    @Test
+    void testRenderPdfPageOutOfRange() throws Exception {
+        // render_pdf_page_to_png: page out of range
+        // Wrap setup_lines + call_expr inside the lambda so error fixtures
+        // catch failures at *any* step — including `<Type>.fromJson(...)`
+        // calls that throw on malformed JSON (e.g. error fixtures with an
+        // invalid enum value like `"purpose":"invalid-purpose"`). Mirrors
+        // the C# `Assert.ThrowsAnyAsync(() => client.X(Type.FromJson(...)))`
+        // pattern.
+        assertThrows(Exception.class, () -> {
+            Kreuzberg.renderPdfPageToPng(java.nio.file.Files.readAllBytes(java.nio.file.Path.of("pdf/fake_memo.pdf")), 999, null, null);
+        });
+
+    }
+
+}

e2e/java/src/test/java/dev/kreuzberg/e2e/PluginApiTest.java

@@ -0,0 +1,293 @@
+// This file is auto-generated by alef — DO NOT EDIT.
+// alef:hash:4e15143f4af1ae8bafbdb1506ef057da924484c66a19483966333558ad437e75
+// To regenerate: alef generate
+// To verify freshness: alef verify --exit-code
+// Issues & docs: https://github.com/kreuzberg-dev/alef
+
+package dev.kreuzberg.e2e;
+
+import org.junit.jupiter.api.Test;
+import static org.junit.jupiter.api.Assertions.*;
+import dev.kreuzberg.Kreuzberg;
+import dev.kreuzberg.ExtractionConfig;
+import java.util.Optional;
+import dev.kreuzberg.JsonUtil;
+
+/** E2e tests for category: plugin_api. */
+class PluginApiTest {
+
+    @Test
+    void testRegisterDocumentExtractorTraitBridge() throws Exception {
+        // register_document_extractor: trait bridge
+        class TestStubRegisterDocumentExtractorTraitBridge implements dev.kreuzberg.IDocumentExtractor {
+    @Override
+    public String extract_bytes(byte[] content, String mimeType, dev.kreuzberg.ExtractionConfig config) {
+        return "";
+    }
+    @Override
+    public String extract_file(java.nio.file.Path path, String mimeType, dev.kreuzberg.ExtractionConfig config) {
+        return "";
+    }
+    @Override
+    public java.util.List<String> supported_mime_types() {
+        return new java.util.ArrayList<>();
+    }
+    @Override
+    public int priority() {
+        return 0;
+    }
+    @Override
+    public boolean can_handle(java.nio.file.Path path, String mimeType) {
+        return false;
+    }
+    @Override
+    public String name() { return "test-extractor"; }
+    @Override
+    public String version() {
+        return "";
+    }
+    @Override
+    public void initialize() {}
+    @Override
+    public void shutdown() {}
+}
+
+        Kreuzberg.registerDocumentExtractor(new TestStubRegisterDocumentExtractorTraitBridge());
+
+        Kreuzberg.unregisterDocumentExtractor("test-extractor");
+
+    }
+
+
+    @Test
+    void testRegisterEmbeddingBackendTraitBridge() throws Exception {
+        // register_embedding_backend: trait bridge
+        class TestStubRegisterEmbeddingBackendTraitBridge implements dev.kreuzberg.IEmbeddingBackend {
+    @Override
+    public long dimensions() {
+        return 0;
+    }
+    @Override
+    public java.util.List<java.util.List<Float>> embed(java.util.List<String> texts) {
+        return new java.util.ArrayList<>();
+    }
+    @Override
+    public String name() { return "test-embedding-backend"; }
+    @Override
+    public String version() {
+        return "";
+    }
+    @Override
+    public void initialize() {}
+    @Override
+    public void shutdown() {}
+}
+
+        Kreuzberg.registerEmbeddingBackend(new TestStubRegisterEmbeddingBackendTraitBridge());
+
+        Kreuzberg.unregisterEmbeddingBackend("test-embedding-backend");
+
+    }
+
+
+    @Test
+    void testRegisterOcrBackendTraitBridge() throws Exception {
+        // register_ocr_backend: trait bridge
+        class TestStubRegisterOcrBackendTraitBridge implements dev.kreuzberg.IOcrBackend {
+    @Override
+    public dev.kreuzberg.ExtractionResult process_image(byte[] imageBytes, dev.kreuzberg.OcrConfig config) {
+        return null;
+    }
+    @Override
+    public dev.kreuzberg.ExtractionResult process_image_file(java.nio.file.Path path, dev.kreuzberg.OcrConfig config) {
+        return null;
+    }
+    @Override
+    public boolean supports_language(String lang) {
+        return false;
+    }
+    @Override
+    public String backend_type() {
+        return "";
+    }
+    @Override
+    public java.util.List<String> supported_languages() {
+        return new java.util.ArrayList<>();
+    }
+    @Override
+    public boolean supports_table_detection() {
+        return false;
+    }
+    @Override
+    public boolean supports_document_processing() {
+        return false;
+    }
+    @Override
+    public dev.kreuzberg.ExtractionResult process_document(java.nio.file.Path path, dev.kreuzberg.OcrConfig config) {
+        return null;
+    }
+    @Override
+    public String name() { return "test-backend"; }
+    @Override
+    public String version() {
+        return "";
+    }
+    @Override
+    public void initialize() {}
+    @Override
+    public void shutdown() {}
+}
+
+        Kreuzberg.registerOcrBackend(new TestStubRegisterOcrBackendTraitBridge());
+
+        Kreuzberg.unregisterOcrBackend("test-backend");
+
+    }
+
+
+    @Test
+    void testRegisterPostProcessorTraitBridge() throws Exception {
+        // register_post_processor: trait bridge
+        class TestStubRegisterPostProcessorTraitBridge implements dev.kreuzberg.IPostProcessor {
+    @Override
+    public void process(dev.kreuzberg.ExtractionResult result, dev.kreuzberg.ExtractionConfig config) {}
+    @Override
+    public String processing_stage() {
+        return "";
+    }
+    @Override
+    public boolean should_process(dev.kreuzberg.ExtractionResult result, dev.kreuzberg.ExtractionConfig config) {
+        return false;
+    }
+    @Override
+    public long estimated_duration_ms(dev.kreuzberg.ExtractionResult result) {
+        return 0;
+    }
+    @Override
+    public int priority() {
+        return 0;
+    }
+    @Override
+    public String name() { return "test-processor"; }
+    @Override
+    public String version() {
+        return "";
+    }
+    @Override
+    public void initialize() {}
+    @Override
+    public void shutdown() {}
+}
+
+        Kreuzberg.registerPostProcessor(new TestStubRegisterPostProcessorTraitBridge());
+
+        Kreuzberg.unregisterPostProcessor("test-processor");
+
+    }
+
+
+    @Test
+    void testRegisterRendererTraitBridge() throws Exception {
+        // register_renderer: trait bridge
+        class TestStubRegisterRendererTraitBridge implements dev.kreuzberg.IRenderer {
+    @Override
+    public String render(String doc) {
+        return "";
+    }
+    @Override
+    public String name() { return "test-renderer"; }
+    @Override
+    public String version() {
+        return "";
+    }
+    @Override
+    public void initialize() {}
+    @Override
+    public void shutdown() {}
+}
+
+        Kreuzberg.registerRenderer(new TestStubRegisterRendererTraitBridge());
+
+        Kreuzberg.unregisterRenderer("test-renderer");
+
+    }
+
+
+    @Test
+    void testRegisterValidatorTraitBridge() throws Exception {
+        // register_validator: trait bridge
+        class TestStubRegisterValidatorTraitBridge implements dev.kreuzberg.IValidator {
+    @Override
+    public void validate(dev.kreuzberg.ExtractionResult result, dev.kreuzberg.ExtractionConfig config) {}
+    @Override
+    public boolean should_validate(dev.kreuzberg.ExtractionResult result, dev.kreuzberg.ExtractionConfig config) {
+        return false;
+    }
+    @Override
+    public int priority() {
+        return 0;
+    }
+    @Override
+    public String name() { return "test-validator"; }
+    @Override
+    public String version() {
+        return "";
+    }
+    @Override
+    public void initialize() {}
+    @Override
+    public void shutdown() {}
+}
+
+        Kreuzberg.registerValidator(new TestStubRegisterValidatorTraitBridge());
+
+        Kreuzberg.unregisterValidator("test-validator");
+
+    }
+
+
+    @Test
+    void testUnregisterDocumentExtractorAfterRegister() throws Exception {
+        // unregister_document_extractor
+        Kreuzberg.unregisterDocumentExtractor("test-extractor");
+
+
+    }
+
+
+    @Test
+    void testUnregisterEmbeddingBackendAfterRegister() throws Exception {
+        // unregister_embedding_backend
+        Kreuzberg.unregisterEmbeddingBackend("test-embedding-backend");
+
+
+    }
+
+
+    @Test
+    void testUnregisterPostProcessorAfterRegister() throws Exception {
+        // unregister_post_processor
+        Kreuzberg.unregisterPostProcessor("test-processor");
+
+
+    }
+
+
+    @Test
+    void testUnregisterRendererAfterRegister() throws Exception {
+        // unregister_renderer
+        Kreuzberg.unregisterRenderer("test-renderer");
+
+
+    }
+
+
+    @Test
+    void testUnregisterValidatorAfterRegister() throws Exception {
+        // unregister_validator
+        Kreuzberg.unregisterValidator("test-validator");
+
+
+    }
+
+}

e2e/java/src/test/java/dev/kreuzberg/e2e/PostProcessorManagementTest.java

@@ -0,0 +1,36 @@
+// This file is auto-generated by alef — DO NOT EDIT.
+// alef:hash:4e15143f4af1ae8bafbdb1506ef057da924484c66a19483966333558ad437e75
+// To regenerate: alef generate
+// To verify freshness: alef verify --exit-code
+// Issues & docs: https://github.com/kreuzberg-dev/alef
+
+package dev.kreuzberg.e2e;
+
+import org.junit.jupiter.api.Test;
+import static org.junit.jupiter.api.Assertions.*;
+import dev.kreuzberg.Kreuzberg;
+import dev.kreuzberg.ExtractionConfig;
+import java.util.Optional;
+import dev.kreuzberg.JsonUtil;
+
+/** E2e tests for category: post_processor_management. */
+class PostProcessorManagementTest {
+
+    @Test
+    void testPostProcessorsClear() throws Exception {
+        // Clear all post-processors and verify list is empty
+        Kreuzberg.clearPostProcessors();
+
+
+    }
+
+
+    @Test
+    void testPostProcessorsList() throws Exception {
+        // List all registered post-processors
+        var result = Kreuzberg.listPostProcessors();
+
+
+    }
+
+}

e2e/java/src/test/java/dev/kreuzberg/e2e/RegistryOperationsTest.java

@@ -0,0 +1,45 @@
+// This file is auto-generated by alef — DO NOT EDIT.
+// alef:hash:4e15143f4af1ae8bafbdb1506ef057da924484c66a19483966333558ad437e75
+// To regenerate: alef generate
+// To verify freshness: alef verify --exit-code
+// Issues & docs: https://github.com/kreuzberg-dev/alef
+
+package dev.kreuzberg.e2e;
+
+import org.junit.jupiter.api.Test;
+import static org.junit.jupiter.api.Assertions.*;
+import dev.kreuzberg.Kreuzberg;
+import dev.kreuzberg.ExtractionConfig;
+import java.util.Optional;
+import dev.kreuzberg.JsonUtil;
+
+/** E2e tests for category: registry_operations. */
+class RegistryOperationsTest {
+
+    @Test
+    void testExtensionsDocx() throws Exception {
+        // Get file extensions for DOCX MIME type
+        var result = Kreuzberg.getExtensionsForMime("application/vnd.openxmlformats-officedocument.wordprocessingml.document");
+
+
+    }
+
+
+    @Test
+    void testExtensionsHtml() throws Exception {
+        // Get file extensions for HTML MIME type
+        var result = Kreuzberg.getExtensionsForMime("text/html");
+
+
+    }
+
+
+    @Test
+    void testExtensionsPdf() throws Exception {
+        // Get file extensions for PDF MIME type
+        var result = Kreuzberg.getExtensionsForMime("application/pdf");
+
+
+    }
+
+}

e2e/java/src/test/java/dev/kreuzberg/e2e/RegistryTest.java

@@ -0,0 +1,72 @@
+// This file is auto-generated by alef — DO NOT EDIT.
+// alef:hash:4e15143f4af1ae8bafbdb1506ef057da924484c66a19483966333558ad437e75
+// To regenerate: alef generate
+// To verify freshness: alef verify --exit-code
+// Issues & docs: https://github.com/kreuzberg-dev/alef
+
+package dev.kreuzberg.e2e;
+
+import org.junit.jupiter.api.Test;
+import static org.junit.jupiter.api.Assertions.*;
+import dev.kreuzberg.Kreuzberg;
+import dev.kreuzberg.ExtractionConfig;
+import java.util.Optional;
+import dev.kreuzberg.JsonUtil;
+
+/** E2e tests for category: registry. */
+class RegistryTest {
+
+    @Test
+    void testListDocumentExtractors() throws Exception {
+        // List document extractors
+        var result = Kreuzberg.listDocumentExtractors();
+
+
+    }
+
+
+    @Test
+    void testListEmbeddingBackends() throws Exception {
+        // List embedding backends
+        var result = Kreuzberg.listEmbeddingBackends();
+
+
+    }
+
+
+    @Test
+    void testListOcrBackends() throws Exception {
+        // List OCR backends
+        var result = Kreuzberg.listOcrBackends();
+
+
+    }
+
+
+    @Test
+    void testListPostProcessors() throws Exception {
+        // List post-processors
+        var result = Kreuzberg.listPostProcessors();
+
+
+    }
+
+
+    @Test
+    void testListRenderers() throws Exception {
+        // List renderers
+        var result = Kreuzberg.listRenderers();
+
+
+    }
+
+
+    @Test
+    void testListValidators() throws Exception {
+        // List validators
+        var result = Kreuzberg.listValidators();
+
+
+    }
+
+}

e2e/java/src/test/java/dev/kreuzberg/e2e/RendererManagementTest.java

@@ -0,0 +1,36 @@
+// This file is auto-generated by alef — DO NOT EDIT.
+// alef:hash:4e15143f4af1ae8bafbdb1506ef057da924484c66a19483966333558ad437e75
+// To regenerate: alef generate
+// To verify freshness: alef verify --exit-code
+// Issues & docs: https://github.com/kreuzberg-dev/alef
+
+package dev.kreuzberg.e2e;
+
+import org.junit.jupiter.api.Test;
+import static org.junit.jupiter.api.Assertions.*;
+import dev.kreuzberg.Kreuzberg;
+import dev.kreuzberg.ExtractionConfig;
+import java.util.Optional;
+import dev.kreuzberg.JsonUtil;
+
+/** E2e tests for category: renderer_management. */
+class RendererManagementTest {
+
+    @Test
+    void testRenderersClear() throws Exception {
+        // Clear all renderers and verify list is empty
+        Kreuzberg.clearRenderers();
+
+
+    }
+
+
+    @Test
+    void testRenderersList() throws Exception {
+        // List all registered renderers
+        var result = Kreuzberg.listRenderers();
+
+
+    }
+
+}

e2e/java/src/test/java/dev/kreuzberg/e2e/SmokeTest.java

@@ -0,0 +1,106 @@
+// This file is auto-generated by alef — DO NOT EDIT.
+// alef:hash:4e15143f4af1ae8bafbdb1506ef057da924484c66a19483966333558ad437e75
+// To regenerate: alef generate
+// To verify freshness: alef verify --exit-code
+// Issues & docs: https://github.com/kreuzberg-dev/alef
+
+package dev.kreuzberg.e2e;
+
+import org.junit.jupiter.api.Test;
+import static org.junit.jupiter.api.Assertions.*;
+import dev.kreuzberg.Kreuzberg;
+import dev.kreuzberg.ExtractionConfig;
+import java.util.Optional;
+import dev.kreuzberg.JsonUtil;
+
+/** E2e tests for category: smoke. */
+class SmokeTest {
+
+    @Test
+    void testOcrImagePng() throws Exception {
+        // OCR: PNG image extraction with OCR enabled. In WASM this exercises the Uint8Array bridge parameter and Promise await in the generated OcrBackend bridge.
+        var config = JsonUtil.fromJson("{}", ExtractionConfig.class);
+
+        var result = Kreuzberg.extractBytes(java.nio.file.Files.readAllBytes(java.nio.file.Path.of("images/test_hello_world.png")), "image/png", config);
+assertEquals("image/png", result.mimeType().trim());assertTrue(result.content().length() >= 1, "expected length >= 1");assertTrue(result.content().contains("Hello") || result.content().contains("World") || result.content().contains("hello") || result.content().contains("world"), "expected to contain at least one of the specified values");
+
+    }
+
+
+    @Test
+    void testSmokeDocxBasic() throws Exception {
+        // Smoke test: DOCX with formatted text
+        var config = JsonUtil.fromJson("{}", ExtractionConfig.class);
+
+        var result = Kreuzberg.extractFile(java.nio.file.Path.of("docx/fake.docx"), "application/vnd.openxmlformats-officedocument.wordprocessingml.document", config);
+assertEquals("application/vnd.openxmlformats-officedocument.wordprocessingml.document", result.mimeType().trim());assertTrue(result.content().length() >= 20, "expected length >= 20");assertTrue(result.content().contains("Lorem") || result.content().contains("ipsum") || result.content().contains("document") || result.content().contains("text"), "expected to contain at least one of the specified values");
+
+    }
+
+
+    @Test
+    void testSmokeHtmlBasic() throws Exception {
+        // Smoke test: HTML table extraction
+        var config = JsonUtil.fromJson("{}", ExtractionConfig.class);
+
+        var result = Kreuzberg.extractFile(java.nio.file.Path.of("html/simple_table.html"), "text/html", config);
+assertEquals("text/html", result.mimeType().trim());assertTrue(result.content().length() >= 10, "expected length >= 10");assertTrue(result.content().contains("Sample Data Table") || result.content().contains("Laptop") || result.content().contains("Electronics") || result.content().contains("Product"), "expected to contain at least one of the specified values");
+
+    }
+
+
+    @Test
+    void testSmokeImagePng() throws Exception {
+        // Smoke test: PNG image (without OCR, metadata only)
+        var config = JsonUtil.fromJson("{\"disable_ocr\":true}", ExtractionConfig.class);
+
+        var result = Kreuzberg.extractFile(java.nio.file.Path.of("images/sample.png"), null, config);
+assertEquals("image/png", result.mimeType().trim());
+
+    }
+
+
+    @Test
+    void testSmokeJsonBasic() throws Exception {
+        // Smoke test: JSON file extraction
+        var config = JsonUtil.fromJson("{}", ExtractionConfig.class);
+
+        var result = Kreuzberg.extractFile(java.nio.file.Path.of("json/simple.json"), "application/json", config);
+assertEquals("application/json", result.mimeType().trim());assertTrue(result.content().length() >= 5, "expected length >= 5");
+
+    }
+
+
+    @Test
+    void testSmokePdfBasic() throws Exception {
+        // Smoke test: PDF with simple text extraction
+        var config = JsonUtil.fromJson("{}", ExtractionConfig.class);
+
+        var result = Kreuzberg.extractFile(java.nio.file.Path.of("pdf/fake_memo.pdf"), "application/pdf", config);
+assertEquals("application/pdf", result.mimeType().trim());assertTrue(result.content().length() >= 50, "expected length >= 50");assertTrue(result.content().contains("May 5, 2023") || result.content().contains("To Whom it May Concern"), "expected to contain at least one of the specified values");
+
+    }
+
+
+    @Test
+    void testSmokeTxtBasic() throws Exception {
+        // Smoke test: Plain text file
+        var config = JsonUtil.fromJson("{}", ExtractionConfig.class);
+
+        var result = Kreuzberg.extractFile(java.nio.file.Path.of("text/report.txt"), "text/plain", config);
+assertEquals("text/plain", result.mimeType().trim());assertTrue(result.content().length() >= 5, "expected length >= 5");
+
+    }
+
+
+    @Test
+    void testSmokeXlsxBasic() throws Exception {
+        // Smoke test: XLSX with basic spreadsheet data including tables
+        var config = JsonUtil.fromJson("{}", ExtractionConfig.class);
+
+        var result = Kreuzberg.extractFile(java.nio.file.Path.of("xlsx/stanley_cups.xlsx"), "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet", config);
+assertEquals("application/vnd.openxmlformats-officedocument.spreadsheetml.sheet", result.mimeType().trim());assertTrue(result.content().length() >= 100, "expected length >= 100");assertTrue(result.content().contains("Team"), "expected to contain: " + "Team");assertTrue(result.content().contains("Location"), "expected to contain: " + "Location");assertTrue(result.content().contains("Stanley Cups"), "expected to contain: " + "Stanley Cups");assertTrue(result.content().contains("Blues"), "expected to contain: " + "Blues");assertTrue(result.content().contains("Flyers"), "expected to contain: " + "Flyers");assertTrue(result.content().contains("Maple Leafs"), "expected to contain: " + "Maple Leafs");assertTrue(result.content().contains("STL"), "expected to contain: " + "STL");assertTrue(result.content().contains("PHI"), "expected to contain: " + "PHI");assertTrue(result.content().contains("TOR"), "expected to contain: " + "TOR");        // skipped: field 'tables' not available on result type        // skipped: field 'metadata.format.excel.sheet_count' not available on result type        // skipped: field 'metadata.format.excel.sheet_names' not available on result type
+
+    }
+
+}

e2e/java/src/test/java/dev/kreuzberg/e2e/ValidatorManagementTest.java

@@ -0,0 +1,36 @@
+// This file is auto-generated by alef — DO NOT EDIT.
+// alef:hash:4e15143f4af1ae8bafbdb1506ef057da924484c66a19483966333558ad437e75
+// To regenerate: alef generate
+// To verify freshness: alef verify --exit-code
+// Issues & docs: https://github.com/kreuzberg-dev/alef
+
+package dev.kreuzberg.e2e;
+
+import org.junit.jupiter.api.Test;
+import static org.junit.jupiter.api.Assertions.*;
+import dev.kreuzberg.Kreuzberg;
+import dev.kreuzberg.ExtractionConfig;
+import java.util.Optional;
+import dev.kreuzberg.JsonUtil;
+
+/** E2e tests for category: validator_management. */
+class ValidatorManagementTest {
+
+    @Test
+    void testValidatorsClear() throws Exception {
+        // Clear all validators and verify list is empty
+        Kreuzberg.clearValidators();
+
+
+    }
+
+
+    @Test
+    void testValidatorsList() throws Exception {
+        // List all registered validators
+        var result = Kreuzberg.listValidators();
+
+
+    }
+
+}