fil/packages/java/dev/kreuzberg/OcrElement.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.Map;
import com.fasterxml.jackson.databind.JsonNode;
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;

/**
 * A unified OCR element representing detected text with full metadata.
 *
 * This is the primary type for structured OCR output, preserving all information
 * from both Tesseract and PaddleOCR backends.
 */
@JsonInclude(JsonInclude.Include.NON_ABSENT)
@JsonDeserialize(builder = OcrElement.Builder.class)
public record OcrElement(
    /**
     * The recognized text content.
     */
    @JsonProperty("text") String text,
    /**
     * Bounding geometry (rectangle or quadrilateral).
     */
    @JsonProperty("geometry") OcrBoundingGeometry geometry,
    /**
     * Confidence scores for detection and recognition.
     */
    @JsonProperty("confidence") OcrConfidence confidence,
    /**
     * Hierarchical level (word, line, block, page).
     */
    @Nullable @JsonProperty("level") OcrElementLevel level,
    /**
     * Rotation information (if detected).
     */
    @Nullable @JsonProperty("rotation") OcrRotation rotation,
    /**
     * Page number (1-indexed).
     */
    @Nullable @JsonProperty("page_number") Integer pageNumber,
    /**
     * Parent element ID for hierarchical relationships.
     *
     * Only used for Tesseract output which has word -> line -> block hierarchy.
     */
    @Nullable @JsonProperty("parent_id") String parentId,
    /**
     * Backend-specific metadata that doesn't fit the unified schema.
     */
    @Nullable @JsonProperty("backend_metadata") Map<String, JsonNode> backendMetadata
) {
    public static Builder builder() {
        return new Builder();
    }

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

private String text = "";
private OcrBoundingGeometry geometry = null;
private OcrConfidence confidence = null;
        @Nullable private OcrElementLevel level = OcrElementLevel.Line;
private OcrRotation rotation = null;
        @JsonProperty("page_number")
private Integer pageNumber = null;
        @JsonProperty("parent_id")
private String parentId = null;
        @JsonProperty("backend_metadata")
private Map<String, JsonNode> backendMetadata = null;

        /** Sets the text field. */
        @JsonProperty("text")
        public Builder withText(final String value) {
            this.text = value;
            return this;
        }

        /** Sets the geometry field. */
        @JsonProperty("geometry")
        public Builder withGeometry(final OcrBoundingGeometry value) {
            this.geometry = value;
            return this;
        }

        /** Sets the confidence field. */
        @JsonProperty("confidence")
        public Builder withConfidence(final OcrConfidence value) {
            this.confidence = value;
            return this;
        }

        /** Sets the level field. */
        @JsonProperty("level")
        public Builder withLevel(final @Nullable OcrElementLevel value) {
            this.level = value;
            return this;
        }

        /** Sets the rotation field. */
        @JsonProperty("rotation")
        public Builder withRotation(final @Nullable OcrRotation value) {
            this.rotation = value;
            return this;
        }

        /** Sets the pageNumber field. */
        @JsonProperty("page_number")
        public Builder withPageNumber(final @Nullable Integer value) {
            this.pageNumber = value;
            return this;
        }

        /** Sets the parentId field. */
        @JsonProperty("parent_id")
        public Builder withParentId(final @Nullable String value) {
            this.parentId = value;
            return this;
        }

        /** Sets the backendMetadata field. */
        @JsonProperty("backend_metadata")
        public Builder withBackendMetadata(final @Nullable Map<String, JsonNode> value) {
            this.backendMetadata = value;
            return this;
        }

        /** Builds the OcrElement instance. */
        public OcrElement build() {
            return new OcrElement(
                text,
                geometry,
                confidence,
                level,
                rotation,
                pageNumber,
                parentId,
                backendMetadata
            );
        }
    }
    // CPD-ON
}