Nomad changes

packages/java/dev/kreuzberg/PageContent.java

@@ -0,0 +1,214 @@
+// 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;
+
+import java.util.List;
+import com.fasterxml.jackson.annotation.JsonProperty;
+import com.fasterxml.jackson.annotation.JsonInclude;
+import com.fasterxml.jackson.databind.annotation.JsonDeserialize;
+import com.fasterxml.jackson.databind.annotation.JsonPOJOBuilder;
+import org.jspecify.annotations.Nullable;
+
+/**
+ * Content for a single page/slide.
+ *
+ * When page extraction is enabled, documents are split into per-page content
+ * with associated tables and images mapped to each page.
+ *
+ * # Performance
+ *
+ * Uses Arc-wrapped tables and images for memory efficiency:
+ * - {@code Vec<Arc<Table>>} enables zero-copy sharing of table data
+ * - {@code Vec<Arc<ExtractedImage>>} enables zero-copy sharing of image data
+ * - Maintains exact JSON compatibility via custom Serialize/Deserialize
+ *
+ * This reduces memory overhead for documents with shared tables/images
+ * by avoiding redundant copies during serialization.
+ */
+@JsonInclude(JsonInclude.Include.NON_ABSENT)
+@JsonDeserialize(builder = PageContent.Builder.class)
+public record PageContent(
+    /**
+     * Page number (1-indexed)
+     */
+    @JsonProperty("page_number") int pageNumber,
+    /**
+     * Text content for this page
+     */
+    @JsonProperty("content") String content,
+    /**
+     * Tables found on this page (uses Arc for memory efficiency)
+     *
+     * Serializes as Table[] for JSON compatibility while maintaining
+     * Arc semantics in-memory for zero-copy sharing.
+     */
+    @Nullable @JsonProperty("tables") List<Table> tables,
+    /**
+     * Indices into {@code ExtractionResult.images} for images found on this page.
+     *
+     * Each value is a zero-based index into the top-level {@code images} collection.
+     * Only populated when {@code extract_images = true} in the extraction config.
+     */
+    @Nullable @JsonProperty("image_indices") List<Integer> imageIndices,
+    /**
+     * Hierarchy information for the page (when hierarchy extraction is enabled)
+     *
+     * Contains text hierarchy levels (H1-H6) extracted from the page content.
+     */
+    @Nullable @JsonProperty("hierarchy") PageHierarchy hierarchy,
+    /**
+     * Whether this page is blank (no meaningful text content)
+     *
+     * Determined during extraction based on text content analysis.
+     * A page is blank if it has fewer than 3 non-whitespace characters
+     * and contains no tables or images.
+     */
+    @Nullable @JsonProperty("is_blank") Boolean isBlank,
+    /**
+     * Layout detection regions for this page (when layout detection is enabled).
+     *
+     * Contains detected layout regions with class, confidence, bounding box,
+     * and area fraction. Only populated when layout detection is configured.
+     */
+    @Nullable @JsonProperty("layout_regions") List<LayoutRegion> layoutRegions,
+    /**
+     * Speaker notes for this slide (PPTX only).
+     *
+     * Contains the text from the slide's notes pane ({@code ppt/notesSlides/notesSlide{N}.xml}).
+     * Only populated when the source is a PPTX file and notes are present.
+     */
+    @Nullable @JsonProperty("speaker_notes") String speakerNotes,
+    /**
+     * Section name this slide belongs to (PPTX only).
+     *
+     * PowerPoint sections group slides into logical chapters ({@code &lt;p:sectionLst&gt;} in
+     * {@code ppt/presentation.xml}). Only populated when the source is a PPTX file and
+     * the slide belongs to a named section.
+     */
+    @Nullable @JsonProperty("section_name") String sectionName,
+    /**
+     * Sheet name for this page (XLSX/ODS only).
+     *
+     * Each spreadsheet sheet maps to one {@code PageContent} entry. This field carries the
+     * sheet's display name as it appears in the workbook. {@code None} for all non-spreadsheet
+     * formats and for sheets with an empty name.
+     */
+    @Nullable @JsonProperty("sheet_name") String sheetName
+) {
+    public static Builder builder() {
+        return new Builder();
+    }
+
+    // CPD-OFF
+    @JsonPOJOBuilder(withPrefix = "with", buildMethodName = "build")
+    public static final class Builder {
+
+        @JsonProperty("page_number")
+private int pageNumber = 0;
+private String content = "";
+private List<Table> tables = null;
+        @JsonProperty("image_indices")
+private List<Integer> imageIndices = null;
+private PageHierarchy hierarchy = null;
+        @JsonProperty("is_blank")
+private Boolean isBlank = null;
+        @JsonProperty("layout_regions")
+private List<LayoutRegion> layoutRegions = null;
+        @JsonProperty("speaker_notes")
+private String speakerNotes = null;
+        @JsonProperty("section_name")
+private String sectionName = null;
+        @JsonProperty("sheet_name")
+private String sheetName = null;
+
+        /** Sets the pageNumber field. */
+        @JsonProperty("page_number")
+        public Builder withPageNumber(final int value) {
+            this.pageNumber = value;
+            return this;
+        }
+
+        /** Sets the content field. */
+        @JsonProperty("content")
+        public Builder withContent(final String value) {
+            this.content = value;
+            return this;
+        }
+
+        /** Sets the tables field. */
+        @JsonProperty("tables")
+        public Builder withTables(final @Nullable List<Table> value) {
+            this.tables = value;
+            return this;
+        }
+
+        /** Sets the imageIndices field. */
+        @JsonProperty("image_indices")
+        public Builder withImageIndices(final @Nullable List<Integer> value) {
+            this.imageIndices = value;
+            return this;
+        }
+
+        /** Sets the hierarchy field. */
+        @JsonProperty("hierarchy")
+        public Builder withHierarchy(final @Nullable PageHierarchy value) {
+            this.hierarchy = value;
+            return this;
+        }
+
+        /** Sets the isBlank field. */
+        @JsonProperty("is_blank")
+        public Builder withIsBlank(final @Nullable boolean value) {
+            this.isBlank = value;
+            return this;
+        }
+
+        /** Sets the layoutRegions field. */
+        @JsonProperty("layout_regions")
+        public Builder withLayoutRegions(final @Nullable List<LayoutRegion> value) {
+            this.layoutRegions = value;
+            return this;
+        }
+
+        /** Sets the speakerNotes field. */
+        @JsonProperty("speaker_notes")
+        public Builder withSpeakerNotes(final @Nullable String value) {
+            this.speakerNotes = value;
+            return this;
+        }
+
+        /** Sets the sectionName field. */
+        @JsonProperty("section_name")
+        public Builder withSectionName(final @Nullable String value) {
+            this.sectionName = value;
+            return this;
+        }
+
+        /** Sets the sheetName field. */
+        @JsonProperty("sheet_name")
+        public Builder withSheetName(final @Nullable String value) {
+            this.sheetName = value;
+            return this;
+        }
+
+        /** Builds the PageContent instance. */
+        public PageContent build() {
+            return new PageContent(
+                pageNumber,
+                content,
+                tables,
+                imageIndices,
+                hierarchy,
+                isBlank,
+                layoutRegions,
+                speakerNotes,
+                sectionName,
+                sheetName
+            );
+        }
+    }
+    // CPD-ON
+}