Add shared multi-language visual benchmarks

minipdf-java/README.md

@@ -0,0 +1,70 @@
+# MiniPdf for Java
+
+MiniPdf for Java is a Java 17 library and command-line tool for converting
+DOCX, XLSX, and PPTX files to PDF without Microsoft Office or LibreOffice.
+
+## Install
+
+The library is available from Maven Central:
+
+```xml
+<dependency>
+    <groupId>io.github.shps951023</groupId>
+    <artifactId>minipdf</artifactId>
+    <version>0.1.1</version>
+</dependency>
+```
+
+## Library
+
+```java
+import io.github.minisoftware.minipdf.MiniPdf;
+
+import java.nio.file.Path;
+
+MiniPdf.convertToPdf(
+        Path.of("document.docx"),
+        Path.of("document.pdf"));
+```
+
+Use `MiniPdf.convertBytesToPdf` when the Office document is already in memory.
+`ConversionOptions.withPageSize` overrides the output page size.
+
+## CLI
+
+Download the executable JAR with Maven:
+
+```powershell
+mvn dependency:copy `
+  -Dartifact=io.github.shps951023:minipdf-cli:0.1.1 `
+  -DoutputDirectory=.
+```
+
+Convert a document:
+
+```powershell
+java -jar minipdf-cli-0.1.1.jar input.pptx -o output.pdf
+```
+
+The CLI accepts `.docx`, `.xlsx`, and `.pptx` files. Run it with `--help` for
+page-size and font-directory options.
+
+## Current Scope
+
+The Java implementation currently provides text-first Office conversion:
+
+- DOCX paragraphs, tabs, and line breaks
+- XLSX shared strings, inline strings, numbers, and booleans
+- PPTX slide text, native slide dimensions, and one PDF page per slide
+- bounded OOXML ZIP loading and XML external-entity protection
+
+Advanced Office layout, images, charts, and embedded fonts are not yet fully
+reproduced by the Java renderer.
+
+## Build and Test
+
+From this directory:
+
+```powershell
+mvn -B -ntp verify
+```

minipdf-java/minipdf-cli/pom.xml

@@ -7,7 +7,7 @@
     <parent>
         <groupId>io.github.shps951023</groupId>
         <artifactId>minipdf-java-parent</artifactId>
-        <version>0.1.0</version>
+        <version>0.1.1</version>
     </parent>
 
     <artifactId>minipdf-cli</artifactId>

minipdf-java/minipdf-cli/src/main/java/io/github/minisoftware/minipdf/cli/MiniPdfCommand.java

@@ -20,8 +20,8 @@
 
 @Command(
         name = "minipdf",
-    version = "minipdf-java 0.1.0",
-        description = "Convert XLSX and DOCX files to PDF with the Java MiniPdf engine.",
+    version = "minipdf-java 0.1.1",
+    description = "Convert XLSX, DOCX, and PPTX files to PDF with the Java MiniPdf engine.",
         mixinStandardHelpOptions = true,
         subcommands = MiniPdfCommand.ConvertCommand.class)
 public final class MiniPdfCommand implements Callable<Integer> {
@@ -131,10 +131,10 @@ private static int convert(Path input, ConversionArguments arguments, CommandLin
         String fileName = input.getFileName().toString();
         int dot = fileName.lastIndexOf('.');
         String extension = dot < 0 ? "" : fileName.substring(dot + 1).toLowerCase(Locale.ROOT);
-        if (!extension.equals("xlsx") && !extension.equals("docx")) {
+        if (!extension.equals("xlsx") && !extension.equals("docx") && !extension.equals("pptx")) {
             throw new CommandLine.ParameterException(
                     commandLine,
-                    "unsupported file type '." + extension + "'. Supported: .xlsx, .docx");
+                "unsupported file type '." + extension + "'. Supported: .xlsx, .docx, .pptx");
         }
 
         if (arguments.fonts != null) {

minipdf-java/minipdf-cli/src/test/java/io/github/minisoftware/minipdf/cli/MiniPdfCommandTest.java

@@ -47,6 +47,18 @@ void convertsDocxWithSubcommandAndCustomSize() throws Exception {
                 .contains("/MediaBox [0 0 400 500]"));
     }
 
+        @Test
+        void convertsPptxWithDirectSyntax() throws Exception {
+                Path source = REPOSITORY_ROOT.resolve("tests/Issue_Files/pptx/Asian Pacific.pptx");
+                Path output = temporaryDirectory.resolve("slides.pdf");
+
+                CommandResult result = execute(source.toString(), "-o", output.toString());
+
+                assertEquals(0, result.exitCode());
+                assertTrue(Files.readString(output, StandardCharsets.ISO_8859_1).startsWith("%PDF-1.4"));
+                assertTrue(result.stdout().contains(output.toString()));
+        }
+
     @Test
     void rejectsConflictingPageOptions() {
         Path source = REPOSITORY_ROOT.resolve(

minipdf-java/minipdf/pom.xml

@@ -7,7 +7,7 @@
     <parent>
         <groupId>io.github.shps951023</groupId>
         <artifactId>minipdf-java-parent</artifactId>
-        <version>0.1.0</version>
+        <version>0.1.1</version>
     </parent>
 
     <artifactId>minipdf</artifactId>

minipdf-java/minipdf/src/main/java/io/github/minisoftware/minipdf/MiniPdf.java

@@ -2,6 +2,7 @@
 
 import io.github.minisoftware.minipdf.internal.OfficePackageDetector;
 import io.github.minisoftware.minipdf.internal.docx.DocxConverter;
+import io.github.minisoftware.minipdf.internal.pptx.PptxConverter;
 import io.github.minisoftware.minipdf.internal.xlsx.XlsxConverter;
 
 import java.io.IOException;
@@ -59,7 +60,8 @@ public static byte[] convertBytesToPdf(byte[] input, ConversionOptions options)
         return switch (format) {
             case DOCX -> DocxConverter.convert(input, options);
             case XLSX -> XlsxConverter.convert(input, options);
-            case PPTX, UNKNOWN -> throw new MiniPdfException(
+            case PPTX -> PptxConverter.convert(input, options);
+            case UNKNOWN -> throw new MiniPdfException(
                 MiniPdfException.Kind.UNSUPPORTED_FORMAT,
                 "unsupported or unknown Office document format");
         };

minipdf-java/minipdf/src/main/java/io/github/minisoftware/minipdf/internal/SimplePdfTextRenderer.java

@@ -18,20 +18,29 @@ private SimplePdfTextRenderer() {
     }
 
     public static byte[] render(List<String> sourceLines, ConversionOptions options) {
-        PageSize size = options.pageSize().orElse(PageSize.A4);
+        return renderPages(List.of(sourceLines), options, PageSize.A4);
+    }
+
+    public static byte[] renderPages(
+            List<List<String>> sourcePages,
+            ConversionOptions options,
+            PageSize defaultPageSize) {
+        PageSize size = options.pageSize().orElse(defaultPageSize);
         PdfDocument document = new PdfDocument();
-        PdfPage page = document.addPage(size.width(), size.height());
-        float y = size.height() - MARGIN;
         int maxCharacters = Math.max(1, (int) ((size.width() - MARGIN * 2.0f) / (FONT_SIZE * 0.52f)));
 
-        for (String sourceLine : sourceLines) {
-            for (String line : wrap(sourceLine, maxCharacters)) {
-                if (y < MARGIN) {
-                    page = document.addPage(size.width(), size.height());
-                    y = size.height() - MARGIN;
+        for (List<String> sourcePage : sourcePages) {
+            PdfPage page = document.addPage(size.width(), size.height());
+            float y = size.height() - MARGIN;
+            for (String sourceLine : sourcePage) {
+                for (String line : wrap(sourceLine, maxCharacters)) {
+                    if (y < MARGIN) {
+                        page = document.addPage(size.width(), size.height());
+                        y = size.height() - MARGIN;
+                    }
+                    page.addText(line, MARGIN, y, FONT_SIZE, PdfColor.BLACK, false);
+                    y -= LINE_HEIGHT;
                 }
-                page.addText(line, MARGIN, y, FONT_SIZE, PdfColor.BLACK, false);
-                y -= LINE_HEIGHT;
             }
         }
         return document.toBytes();