GH-39214: [Java] Support reproducible build

dev/release/01-prepare-test.rb

@@ -264,18 +264,17 @@ def test_version_pre_tag
     end
 
     Dir.glob("java/**/pom.xml") do |path|
-      version = "<version>#{@snapshot_version}</version>"
-      lines = File.readlines(path, chomp: true)
-      target_lines = lines.grep(/#{Regexp.escape(version)}/)
-      hunks = []
-      target_lines.each do |line|
-        new_line = line.gsub(@snapshot_version) do
-          @release_version
+      hunks = generate_hunks(File.readlines(path, chomp: true)) do |line|
+        if line.include?("<version>#{@snapshot_version}</version>")
+          new_line = line.gsub(@snapshot_version) do
+            @release_version
+          end
+          [line, new_line]
+        elsif line.include?("<project.build.outputTimestamp>")
+          [line, normalize_pom_xml_output_timestamp(line)]
+        else
+          [nil, nil]
         end
-        hunks << [
-          "-#{line}",
-          "+#{new_line}",
-        ]
       end
       expected_changes << {hunks: hunks, path: path}
     end

dev/release/post-11-bump-versions-test.rb

@@ -262,37 +262,19 @@ def test_version_post_tag
       end
 
       import_path = "github.com/apache/arrow/go/v#{@snapshot_major_version}"
-      hunks = []
       if release_type == :major
-        lines = File.readlines(path, chomp: true)
-        target_lines = lines.each_with_index.select do |line, i|
-          line.include?(import_path)
-        end
-        next if target_lines.empty?
-        n_context_lines = 3 # The default of Git's diff.context
-        target_hunks = [[target_lines.first[0]]]
-        previous_i = target_lines.first[1]
-        target_lines[1..-1].each do |line, i|
-          if i - previous_i < n_context_lines
-            target_hunks.last << line
-          else
-            target_hunks << [line]
-          end
-          previous_i = i
-        end
-        target_hunks.each do |lines|
-          hunk = []
-          lines.each do |line,|
-            hunk << "-#{line}"
-          end
-          lines.each do |line|
+        hunks = generate_hunks(File.readlines(path, chomp: true)) do |line|
+          if line.include?(import_path)
             new_line = line.gsub("v#{@snapshot_major_version}") do
               "v#{@next_major_version}"
             end
-            hunk << "+#{new_line}"
+            [line, new_line]
+          else
+            [nil, nil]
           end
-          hunks << hunk
         end
+      else
+        hunks = []
       end
       if path == "go/parquet/writer_properties.go"
         hunks << [
@@ -305,18 +287,17 @@ def test_version_post_tag
     end
 
     Dir.glob("java/**/pom.xml") do |path|
-      version = "<version>#{@snapshot_version}</version>"
-      lines = File.readlines(path, chomp: true)
-      target_lines = lines.grep(/#{Regexp.escape(version)}/)
-      hunks = []
-      target_lines.each do |line|
-        new_line = line.gsub(@snapshot_version) do
-          @next_snapshot_version
+      hunks = generate_hunks(File.readlines(path, chomp: true)) do |line|
+        if line.include?("<version>#{@snapshot_version}</version>")
+          new_line = line.gsub(@snapshot_version) do
+            @next_snapshot_version
+          end
+          [line, new_line]
+        elsif line.include?("<project.build.outputTimestamp>")
+          [line, normalize_pom_xml_output_timestamp(line)]
+        else
+          [nil, nil]
         end
-        hunks << [
-          "-#{line}",
-          "+#{new_line}",
-        ]
       end
       expected_changes << {hunks: hunks, path: path}
     end

dev/release/test-helper.rb

@@ -83,15 +83,59 @@ def parse_patch(patch)
       when /\A@@/
         in_hunk = true
         diffs.last[:hunks] << []
-      when /\A[-+]/
+      when /\A-/
         next unless in_hunk
         diffs.last[:hunks].last << line.chomp
+      when /\A\+/
+        next unless in_hunk
+        diffs.last[:hunks].last << normalize_added_line(line.chomp)
       end
     end
     diffs.sort_by do |diff|
       diff[:path]
     end
   end
+
+  def generate_hunks(lines)
+    git_diff_context = 3 # The default of Git's diff.context
+    max_lines_for_same_hunk = git_diff_context * 2 + 1
+    previous_i = nil
+    grouped_change_blocks = []
+    lines.each_with_index do |line, i|
+      deleted, added = yield(line)
+      next if deleted.nil? and added.nil?
+      if previous_i.nil? or (i - previous_i) > max_lines_for_same_hunk
+        grouped_change_blocks << []
+      end
+      if i - 1 != previous_i
+        grouped_change_blocks.last << []
+      end
+      grouped_change_blocks.last.last << [deleted, added]
+      previous_i = i
+    end
+    grouped_change_blocks.collect do |change_blocks|
+      hunk = []
+      change_blocks.each do |continuous_changes|
+        continuous_changes.each do |deleted, _|
+          hunk << "-#{deleted}" if deleted
+        end
+        continuous_changes.each do |_, added|
+          hunk << "+#{added}" if added
+        end
+      end
+      hunk
+    end
+  end
+
+  def normalize_pom_xml_output_timestamp(line)
+    line.gsub(/<project\.build\.outputTimestamp>.+?</) do
+      "<project.build.outputTimestamp>1980-01-01T00:00:02Z<"
+    end
+  end
+
+  def normalize_added_line(line)
+    normalize_pom_xml_output_timestamp(line)
+  end
 end
 
 module VersionDetectable

java/adapter/avro/pom.xml

@@ -25,6 +25,10 @@
   <description>(Contrib/Experimental) A library for converting Avro data to Arrow data.</description>
   <url>http://maven.apache.org</url>
 
+  <properties>
+    <project.build.outputTimestamp>1980-01-01T00:00:02Z</project.build.outputTimestamp>
+  </properties>
+
   <dependencies>
 
     <!-- https://mvnrepository.com/artifact/org.apache.arrow/arrow-memory-core -->

java/adapter/jdbc/pom.xml

@@ -25,6 +25,10 @@
     <description>(Contrib/Experimental)A library for converting JDBC data to Arrow data.</description>
     <url>http://maven.apache.org</url>
 
+    <properties>
+        <project.build.outputTimestamp>1980-01-01T00:00:02Z</project.build.outputTimestamp>
+    </properties>
+
     <dependencies>
 
         <!-- https://mvnrepository.com/artifact/org.apache.arrow/arrow-memory-core -->

java/algorithm/pom.xml

@@ -20,6 +20,10 @@
   <name>Arrow Algorithms</name>
   <description>(Experimental/Contrib) A collection of algorithms for working with ValueVectors.</description>
 
+  <properties>
+    <project.build.outputTimestamp>1980-01-01T00:00:02Z</project.build.outputTimestamp>
+  </properties>
+
   <dependencies>
     <dependency>
       <groupId>org.apache.arrow</groupId>

java/bom/pom.xml

@@ -15,7 +15,7 @@
   <parent>
     <groupId>org.apache</groupId>
     <artifactId>apache</artifactId>
-    <version>18</version>
+    <version>31</version>
   </parent>
 
   <groupId>org.apache.arrow</groupId>
@@ -26,6 +26,7 @@
   <description>Arrow Bill of Materials</description>
 
   <properties>
+    <minimalMavenBuildVersion>3.5.0</minimalMavenBuildVersion>
     <arrow.vector.classifier/>
   </properties>
 

java/c/pom.xml

@@ -22,6 +22,7 @@
     <description>Java implementation of C Data Interface</description>
     <packaging>jar</packaging>
     <properties>
+        <project.build.outputTimestamp>1980-01-01T00:00:02Z</project.build.outputTimestamp>
         <arrow.c.jni.dist.dir>./build</arrow.c.jni.dist.dir>
     </properties>
 

java/compression/pom.xml

@@ -20,6 +20,10 @@
   <name>Arrow Compression</name>
   <description>(Experimental/Contrib) A library for working with the compression/decompression of Arrow data.</description>
 
+  <properties>
+    <project.build.outputTimestamp>1980-01-01T00:00:02Z</project.build.outputTimestamp>
+  </properties>
+
   <dependencies>
     <dependency>
       <groupId>org.apache.arrow</groupId>

java/dataset/pom.xml

@@ -24,6 +24,7 @@
     <description>Java implementation of Arrow Dataset API/Framework</description>
     <packaging>jar</packaging>
     <properties>
+        <project.build.outputTimestamp>1980-01-01T00:00:02Z</project.build.outputTimestamp>
         <arrow.cpp.build.dir>../../../cpp/release-build/</arrow.cpp.build.dir>
         <protobuf.version>2.5.0</protobuf.version>
         <parquet.version>1.13.1</parquet.version>

java/flight/flight-core/pom.xml

@@ -24,6 +24,7 @@
   <packaging>jar</packaging>
 
   <properties>
+    <project.build.outputTimestamp>1980-01-01T00:00:02Z</project.build.outputTimestamp>
     <forkCount>1</forkCount>
   </properties>
 
@@ -288,7 +289,7 @@
       </plugin>
       <plugin>
         <artifactId>maven-assembly-plugin</artifactId>
-        <version>3.0.0</version>
+        <version>3.2.0</version>
         <configuration>
           <descriptorRefs>
             <descriptorRef>jar-with-dependencies</descriptorRef>

java/flight/flight-integration-tests/pom.xml

@@ -24,6 +24,10 @@
     <description>Integration tests for Flight RPC.</description>
     <packaging>jar</packaging>
 
+    <properties>
+        <project.build.outputTimestamp>1980-01-01T00:00:02Z</project.build.outputTimestamp>
+    </properties>
+
     <dependencies>
         <dependency>
             <groupId>org.apache.arrow</groupId>
@@ -64,7 +68,7 @@
         <plugins>
             <plugin>
                 <artifactId>maven-assembly-plugin</artifactId>
-                <version>3.0.0</version>
+                <version>3.2.0</version>
                 <configuration>
                     <descriptorRefs>
                         <descriptorRef>jar-with-dependencies</descriptorRef>

java/flight/flight-sql-jdbc-core/pom.xml

@@ -28,6 +28,7 @@
     <url>https://arrow.apache.org</url>
 
     <properties>
+        <project.build.outputTimestamp>1980-01-01T00:00:02Z</project.build.outputTimestamp>
         <org.apache.arrow.flight.name>${project.parent.groupId}:${project.parent.artifactId}</org.apache.arrow.flight.name>
         <org.apache.arrow.flight.version>${project.parent.version}</org.apache.arrow.flight.version>
         <org.apache.arrow.flight.jdbc-driver.name>${project.name}</org.apache.arrow.flight.jdbc-driver.name>

java/flight/flight-sql-jdbc-driver/pom.xml

@@ -27,6 +27,10 @@
     <packaging>jar</packaging>
     <url>https://arrow.apache.org</url>
 
+    <properties>
+        <project.build.outputTimestamp>1980-01-01T00:00:02Z</project.build.outputTimestamp>
+    </properties>
+
     <dependencies>
         <!-- https://mvnrepository.com/artifact/org.hamcrest/hamcrest -->
         <dependency>

java/flight/flight-sql/pom.xml

@@ -24,6 +24,7 @@
   <packaging>jar</packaging>
 
   <properties>
+    <project.build.outputTimestamp>1980-01-01T00:00:02Z</project.build.outputTimestamp>
     <forkCount>1</forkCount>
   </properties>
 

java/format/pom.xml

@@ -23,6 +23,10 @@
 <name>Arrow Format</name>
 <description>Generated Java files from the IPC Flatbuffer definitions.</description>
 
+  <properties>
+    <project.build.outputTimestamp>1980-01-01T00:00:02Z</project.build.outputTimestamp>
+  </properties>
+
   <dependencies>
     <dependency>
       <groupId>com.google.flatbuffers</groupId>

java/gandiva/pom.xml

@@ -23,6 +23,7 @@
     <name>Arrow Gandiva</name>
     <description>Java wrappers around the native Gandiva SQL expression compiler.</description>
     <properties>
+        <project.build.outputTimestamp>1980-01-01T00:00:02Z</project.build.outputTimestamp>
         <maven.compiler.source>1.8</maven.compiler.source>
         <maven.compiler.target>1.8</maven.compiler.target>
         <protobuf.version>3.25.1</protobuf.version>

java/maven/module-info-compiler-maven-plugin/pom.xml

@@ -30,6 +30,7 @@
   </prerequisites>
 
   <properties>
+    <project.build.outputTimestamp>1980-01-01T00:00:02Z</project.build.outputTimestamp>
     <maven.version>3.8.7</maven.version>
   </properties>
 

java/memory/memory-core/pom.xml

@@ -22,6 +22,10 @@
   <name>Arrow Memory - Core</name>
   <description>Core off-heap memory management libraries for Arrow ValueVectors.</description>
 
+  <properties>
+    <project.build.outputTimestamp>1980-01-01T00:00:02Z</project.build.outputTimestamp>
+  </properties>
+
   <dependencies>
     <dependency>
       <groupId>com.google.code.findbugs</groupId>

java/memory/memory-netty/pom.xml

@@ -21,6 +21,10 @@
   <name>Arrow Memory - Netty</name>
   <description>Netty allocator and utils for allocating memory in Arrow</description>
 
+  <properties>
+    <project.build.outputTimestamp>1980-01-01T00:00:02Z</project.build.outputTimestamp>
+  </properties>
+
   <dependencies>
     <dependency>
       <groupId>org.apache.arrow</groupId>

java/memory/memory-unsafe/pom.xml

@@ -21,6 +21,9 @@
   <name>Arrow Memory - Unsafe</name>
   <description>Allocator and utils for allocating memory in Arrow based on sun.misc.Unsafe</description>
 
+  <properties>
+    <project.build.outputTimestamp>1980-01-01T00:00:02Z</project.build.outputTimestamp>
+  </properties>
 
   <dependencies>
     <dependency>

java/performance/pom.xml

@@ -80,6 +80,7 @@
     </dependencies>
 
     <properties>
+        <project.build.outputTimestamp>1980-01-01T00:00:02Z</project.build.outputTimestamp>
         <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
         <jmh.version>1.37</jmh.version>
         <javac.target>1.8</javac.target>