fil/packages/java/dev/kreuzberg/DocumentStructure.java

// 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;

/**
 * Top-level structured document representation.
 *
 * A flat array of nodes with index-based parent/child references forming a tree.
 * Root-level nodes have {@code parent: None}. Use {@code body_roots()} and {@code furniture_roots()}
 * to iterate over top-level content by layer.
 *
 * # Validation
 *
 * Call {@code validate()} after construction to verify all node indices are in bounds
 * and parent-child relationships are bidirectionally consistent.
 */
@JsonInclude(JsonInclude.Include.NON_ABSENT)
@JsonDeserialize(builder = DocumentStructure.Builder.class)
public record DocumentStructure(
    /**
     * All nodes in document/reading order.
     */
    @JsonProperty("nodes") List<DocumentNode> nodes,
    /**
     * Origin format identifier (e.g. "docx", "pptx", "html", "pdf").
     *
     * Allows renderers to apply format-aware heuristics when converting
     * the document tree to output formats.
     */
    @Nullable @JsonProperty("source_format") String sourceFormat,
    /**
     * Resolved relationships between nodes (footnote refs, citations, anchor links, etc.).
     *
     * Populated during derivation from the internal document representation.
     * Empty when no relationships are detected.
     */
    @Nullable @JsonProperty("relationships") List<DocumentRelationship> relationships,
    /**
     * Sorted, deduplicated list of node type names present in this document.
     *
     * Each value is the snake_case {@code node_type} tag of the corresponding
     * NodeContent variant (e.g. {@code "paragraph"}, {@code "heading"}, {@code "table"}, …).
     *
     * Computed from nodes via DocumentStructure.finalize_node_types.
     * Empty until that method is called (internal construction paths call it
     * at the end of derivation).
     */
    @Nullable @JsonProperty("node_types") List<String> nodeTypes
) {
    public static Builder builder() {
        return new Builder();
    }

    // CPD-OFF
    @JsonPOJOBuilder(withPrefix = "with", buildMethodName = "build")
    public static final class Builder {

private List<DocumentNode> nodes = List.of();
        @JsonProperty("source_format")
private String sourceFormat = null;
private List<DocumentRelationship> relationships = null;
        @JsonProperty("node_types")
private List<String> nodeTypes = null;

        /** Sets the nodes field. */
        @JsonProperty("nodes")
        public Builder withNodes(final List<DocumentNode> value) {
            this.nodes = value;
            return this;
        }

        /** Sets the sourceFormat field. */
        @JsonProperty("source_format")
        public Builder withSourceFormat(final @Nullable String value) {
            this.sourceFormat = value;
            return this;
        }

        /** Sets the relationships field. */
        @JsonProperty("relationships")
        public Builder withRelationships(final @Nullable List<DocumentRelationship> value) {
            this.relationships = value;
            return this;
        }

        /** Sets the nodeTypes field. */
        @JsonProperty("node_types")
        public Builder withNodeTypes(final @Nullable List<String> value) {
            this.nodeTypes = value;
            return this;
        }

        /** Builds the DocumentStructure instance. */
        public DocumentStructure build() {
            return new DocumentStructure(
                nodes,
                sourceFormat,
                relationships,
                nodeTypes
            );
        }
    }
    // CPD-ON
    public static DocumentStructure defaultInstance() {
        throw new UnsupportedOperationException("defaultInstance is not yet bridged via JNI; use the Builder instead.");
    }
}