Nomad changes

docs/snippets/java/metadata/PageBoundaries.md

@@ -0,0 +1,25 @@
+Import dev.kreuzberg.\*;
+import java.nio.charset.StandardCharsets;
+
+var result = Kreuzberg.extractFileSync("document.pdf");
+
+If (result.metadata().pages() != null &&
+result.metadata().pages().boundaries() != null) {
+
+    var contentBytes = result.content().getBytes(StandardCharsets.UTF_8);
+
+    for (var boundary : result.metadata().pages().boundaries().subList(0, 3)) {
+        var pageBytes = Arrays.copyOfRange(
+            contentBytes,
+            boundary.byteStart(),
+            boundary.byteEnd()
+        );
+        var pageText = new String(pageBytes, StandardCharsets.UTF_8);
+
+        System.out.println("Page " + boundary.pageNumber() + ":");
+        System.out.println("  Byte range: " + boundary.byteStart() +
+                           "-" + boundary.byteEnd());
+        System.out.println("  Preview: " + pageText.substring(0, 100) + "...");
+    }
+
+}

docs/snippets/java/metadata/PageTrackingBasic.md

@@ -0,0 +1,18 @@
+Import dev.kreuzberg.\*;
+
+var config = ExtractionConfig.builder()
+.pages(PageConfig.builder()
+.extractPages(true)
+.build())
+.build();
+
+var result = Kreuzberg.extractFileSync("document.pdf", config);
+
+If (result.pages() != null) {
+for (var page : result.pages()) {
+System.out.println("Page " + page.pageNumber() + ":");
+System.out.println(" Content: " + page.content().length() + " chars");
+System.out.println(" Tables: " + page.tables().size());
+System.out.println(" Images: " + page.images().size());
+}
+}

docs/snippets/java/metadata/language_detection.md

@@ -0,0 +1,12 @@
+```java title="Java"
+import dev.kreuzberg.ExtractionConfig;
+import dev.kreuzberg.LanguageDetectionConfig;
+
+ExtractionConfig config = ExtractionConfig.builder()
+    .languageDetection(LanguageDetectionConfig.builder()
+        .enabled(true)
+        .minConfidence(0.9)
+        .detectMultiple(true)
+        .build())
+    .build();
+```

docs/snippets/java/metadata/language_detection_multilingual.md

@@ -0,0 +1,17 @@
+```java title="Java"
+import dev.kreuzberg.Kreuzberg;
+import dev.kreuzberg.ExtractionResult;
+import dev.kreuzberg.ExtractionConfig;
+import dev.kreuzberg.LanguageDetectionConfig;
+
+ExtractionConfig config = ExtractionConfig.builder()
+    .languageDetection(LanguageDetectionConfig.builder()
+        .enabled(true)
+        .minConfidence(0.8)
+        .build())
+    .build();
+
+ExtractionResult result = Kreuzberg.extractFile("multilingual_document.pdf", config);
+
+System.out.println("Detected languages: " + result.getDetectedLanguages());
+```

docs/snippets/java/metadata/metadata.md

@@ -0,0 +1,111 @@
+```java title="Java"
+import dev.kreuzberg.Kreuzberg;
+import dev.kreuzberg.ExtractionResult;
+import dev.kreuzberg.Metadata;
+import dev.kreuzberg.KreuzbergException;
+import java.io.IOException;
+import java.util.Map;
+import java.util.List;
+
+public class Main {
+    public static void main(String[] args) {
+        try {
+            ExtractionResult result = Kreuzberg.extractFileSync("document.pdf");
+
+            // Metadata is flat — format-specific fields are at the top level
+            Metadata metadata = result.getMetadata();
+            metadata.getTitle().ifPresent(t -> System.out.println("Title: " + t));
+            metadata.getAuthors().ifPresent(a -> System.out.println("Authors: " + String.join(", ", a)));
+
+            // Format-specific fields are in the additional map
+            Map<String, Object> extra = metadata.getAdditional();
+            if (extra.get("page_count") != null) {
+                System.out.println("Pages: " + extra.get("page_count"));
+            }
+
+            // Access HTML metadata
+            ExtractionResult htmlResult = Kreuzberg.extractFileSync("page.html");
+            Metadata htmlMeta = htmlResult.getMetadata();
+            htmlMeta.getTitle().ifPresent(t -> System.out.println("Title: " + t));
+
+            Map<String, Object> htmlExtra = htmlMeta.getAdditional();
+            String description = (String) htmlExtra.get("description");
+            if (description != null) {
+                System.out.println("Description: " + description);
+            }
+
+            // Access keywords as array
+            htmlMeta.getKeywords().ifPresent(keywords ->
+                System.out.println("Keywords: " + keywords));
+
+            // Access canonical URL (renamed from canonical)
+            String canonicalUrl = (String) htmlExtra.get("canonical_url");
+            if (canonicalUrl != null) {
+                System.out.println("Canonical URL: " + canonicalUrl);
+            }
+
+            // Access Open Graph fields from map
+            @SuppressWarnings("unchecked")
+            Map<String, String> openGraph = (Map<String, String>) htmlExtra.get("open_graph");
+            if (openGraph != null) {
+                System.out.println("Open Graph Image: " + openGraph.get("image"));
+                System.out.println("Open Graph Title: " + openGraph.get("title"));
+                System.out.println("Open Graph Type: " + openGraph.get("type"));
+            }
+
+            // Access Twitter Card fields from map
+            @SuppressWarnings("unchecked")
+            Map<String, String> twitterCard = (Map<String, String>) htmlExtra.get("twitter_card");
+            if (twitterCard != null) {
+                System.out.println("Twitter Card Type: " + twitterCard.get("card"));
+                System.out.println("Twitter Creator: " + twitterCard.get("creator"));
+            }
+
+            // Access new fields
+            htmlMeta.getLanguage().ifPresent(l -> System.out.println("Language: " + l));
+
+            String textDirection = (String) htmlExtra.get("text_direction");
+            if (textDirection != null) {
+                System.out.println("Text Direction: " + textDirection);
+            }
+
+            // Access headers
+            @SuppressWarnings("unchecked")
+            List<Map<String, Object>> headers = (List<Map<String, Object>>) htmlExtra.get("headers");
+            if (headers != null) {
+                headers.stream()
+                    .map(h -> h.get("text"))
+                    .forEach(text -> System.out.print(text + ", "));
+                System.out.println();
+            }
+
+            // Access links
+            @SuppressWarnings("unchecked")
+            List<Map<String, Object>> links = (List<Map<String, Object>>) htmlExtra.get("links");
+            if (links != null) {
+                for (Map<String, Object> link : links) {
+                    System.out.println("Link: " + link.get("href") + " (" + link.get("text") + ")");
+                }
+            }
+
+            // Access images
+            @SuppressWarnings("unchecked")
+            List<Map<String, Object>> images = (List<Map<String, Object>>) htmlExtra.get("images");
+            if (images != null) {
+                for (Map<String, Object> image : images) {
+                    System.out.println("Image: " + image.get("src"));
+                }
+            }
+
+            // Access structured data
+            @SuppressWarnings("unchecked")
+            List<Map<String, Object>> structuredData = (List<Map<String, Object>>) htmlExtra.get("structured_data");
+            if (structuredData != null) {
+                System.out.println("Structured data items: " + structuredData.size());
+            }
+        } catch (IOException | KreuzbergException e) {
+            System.err.println("Extraction failed: " + e.getMessage());
+        }
+    }
+}
+```

docs/snippets/java/metadata/tables.md

@@ -0,0 +1,27 @@
+```java title="Java"
+import dev.kreuzberg.Kreuzberg;
+import dev.kreuzberg.ExtractionResult;
+import dev.kreuzberg.KreuzbergException;
+import dev.kreuzberg.Table;
+import java.io.IOException;
+import java.util.List;
+
+public class Main {
+    public static void main(String[] args) {
+        try {
+            ExtractionResult result = Kreuzberg.extractFile("document.pdf");
+
+            for (Table table : result.getTables()) {
+                System.out.println("Table with " + table.cells().size() + " rows");
+                System.out.println(table.markdown());
+
+                for (List<String> row : table.cells()) {
+                    System.out.println(row);
+                }
+            }
+        } catch (IOException | KreuzbergException e) {
+            System.err.println("Extraction failed: " + e.getMessage());
+        }
+    }
+}
+```

docs/snippets/java/metadata/vector_database_integration.md

@@ -0,0 +1,18 @@
+```java title="Java"
+import dev.kreuzberg.Kreuzberg;
+import dev.kreuzberg.ExtractionResult;
+import dev.kreuzberg.ExtractionConfig;
+import dev.kreuzberg.ChunkingConfig;
+
+ExtractionConfig config = ExtractionConfig.builder()
+    .chunking(ChunkingConfig.builder()
+        .maxChars(512)
+        .maxOverlap(50)
+        .embedding("balanced")
+        .build())
+    .build();
+
+ExtractionResult result = Kreuzberg.extractFile("document.pdf", config);
+
+System.out.println("Extracted content: " + result.getContent().length() + " characters");
+```