fil/packages/java/dev/kreuzberg/ChunkMetadata.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;

/**
 * Metadata about a chunk's position in the original document.
 */
@JsonInclude(JsonInclude.Include.NON_ABSENT)
@JsonDeserialize(builder = ChunkMetadata.Builder.class)
public record ChunkMetadata(
    /**
     * Byte offset where this chunk starts in the original text (UTF-8 valid boundary).
     */
    @JsonProperty("byte_start") long byteStart,
    /**
     * Byte offset where this chunk ends in the original text (UTF-8 valid boundary).
     */
    @JsonProperty("byte_end") long byteEnd,
    /**
     * Number of tokens in this chunk (if available).
     *
     * This is calculated by the embedding model's tokenizer if embeddings are enabled.
     */
    @Nullable @JsonProperty("token_count") Long tokenCount,
    /**
     * Zero-based index of this chunk in the document.
     */
    @JsonProperty("chunk_index") long chunkIndex,
    /**
     * Total number of chunks in the document.
     */
    @JsonProperty("total_chunks") long totalChunks,
    /**
     * First page number this chunk spans (1-indexed).
     *
     * Only populated when page tracking is enabled in extraction configuration.
     */
    @Nullable @JsonProperty("first_page") Integer firstPage,
    /**
     * Last page number this chunk spans (1-indexed, equal to first_page for single-page chunks).
     *
     * Only populated when page tracking is enabled in extraction configuration.
     */
    @Nullable @JsonProperty("last_page") Integer lastPage,
    /**
     * Heading context when using Markdown chunker.
     *
     * Contains the heading hierarchy this chunk falls under.
     * Only populated when {@code ChunkerType.Markdown} is used.
     */
    @Nullable @JsonProperty("heading_context") HeadingContext headingContext,
    /**
     * Indices into {@code ExtractionResult.images} for images on pages covered by this chunk.
     *
     * Contains zero-based indices into the top-level {@code images} collection for every
     * image whose {@code page_number} falls within {@code [first_page, last_page]}.
     * Empty when image extraction is disabled or the chunk spans no pages with images.
     */
    @Nullable @JsonProperty("image_indices") List<Integer> imageIndices
) {
    public static Builder builder() {
        return new Builder();
    }

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

        @JsonProperty("byte_start")
private long byteStart = 0;
        @JsonProperty("byte_end")
private long byteEnd = 0;
        @JsonProperty("token_count")
private Long tokenCount = null;
        @JsonProperty("chunk_index")
private long chunkIndex = 0;
        @JsonProperty("total_chunks")
private long totalChunks = 0;
        @JsonProperty("first_page")
private Integer firstPage = null;
        @JsonProperty("last_page")
private Integer lastPage = null;
        @JsonProperty("heading_context")
        @Nullable private HeadingContext headingContext = null;
        @JsonProperty("image_indices")
private List<Integer> imageIndices = null;

        /** Sets the byteStart field. */
        @JsonProperty("byte_start")
        public Builder withByteStart(final long value) {
            this.byteStart = value;
            return this;
        }

        /** Sets the byteEnd field. */
        @JsonProperty("byte_end")
        public Builder withByteEnd(final long value) {
            this.byteEnd = value;
            return this;
        }

        /** Sets the tokenCount field. */
        @JsonProperty("token_count")
        public Builder withTokenCount(final @Nullable long value) {
            this.tokenCount = value;
            return this;
        }

        /** Sets the chunkIndex field. */
        @JsonProperty("chunk_index")
        public Builder withChunkIndex(final long value) {
            this.chunkIndex = value;
            return this;
        }

        /** Sets the totalChunks field. */
        @JsonProperty("total_chunks")
        public Builder withTotalChunks(final long value) {
            this.totalChunks = value;
            return this;
        }

        /** Sets the firstPage field. */
        @JsonProperty("first_page")
        public Builder withFirstPage(final @Nullable int value) {
            this.firstPage = value;
            return this;
        }

        /** Sets the lastPage field. */
        @JsonProperty("last_page")
        public Builder withLastPage(final @Nullable int value) {
            this.lastPage = value;
            return this;
        }

        /** Sets the headingContext field. */
        @JsonProperty("heading_context")
        public Builder withHeadingContext(final @Nullable HeadingContext value) {
            this.headingContext = value;
            return this;
        }

        /** Sets the imageIndices field. */
        @JsonProperty("image_indices")
        public Builder withImageIndices(final @Nullable List<Integer> value) {
            this.imageIndices = value;
            return this;
        }

        /** Builds the ChunkMetadata instance. */
        public ChunkMetadata build() {
            return new ChunkMetadata(
                byteStart,
                byteEnd,
                tokenCount,
                chunkIndex,
                totalChunks,
                firstPage,
                lastPage,
                headingContext,
                imageIndices
            );
        }
    }
    // CPD-ON
}