fil/packages/java/dev/kreuzberg/PageInfo.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 for individual page/slide/sheet.
 *
 * Captures per-page information including dimensions, content counts,
 * and visibility state (for presentations).
 */
@JsonInclude(JsonInclude.Include.NON_ABSENT)
@JsonDeserialize(builder = PageInfo.Builder.class)
public record PageInfo(
    /**
     * Page number (1-indexed)
     */
    @JsonProperty("number") int number,
    /**
     * Page title (usually for presentations)
     */
    @Nullable @JsonProperty("title") String title,
    /**
     * Dimensions in points (PDF) or pixels (images): (width, height)
     */
    @Nullable @JsonProperty("dimensions") List<Double> dimensions,
    /**
     * Number of images on this page
     */
    @Nullable @JsonProperty("image_count") Integer imageCount,
    /**
     * Number of tables on this page
     */
    @Nullable @JsonProperty("table_count") Integer tableCount,
    /**
     * Whether this page is hidden (e.g., in presentations)
     */
    @Nullable @JsonProperty("hidden") Boolean hidden,
    /**
     * Whether this page is blank (no meaningful text, no images, no tables)
     *
     * A page is considered blank if it has fewer than 3 non-whitespace characters
     * and contains no tables or images. This is useful for filtering out empty pages
     * in scanned documents or PDFs with blank separator pages.
     */
    @Nullable @JsonProperty("is_blank") Boolean isBlank,
    /**
     * Whether this page contains non-trivial vector graphics (paths, shapes, curves)
     *
     * Indicates the presence of vector-drawn content such as charts, diagrams,
     * or geometric shapes (e.g., from Adobe InDesign, LaTeX TikZ). These are
     * invisible to {@code ExtractionResult.images} since they are not embedded as raster
     * XObjects. Set to {@code true} when path count exceeds a heuristic threshold,
     * signaling that downstream consumers may want to rasterize the page to
     * capture this content.
     *
     * Only populated for PDFs; {@code None} for other document types.
     */
    @Nullable @JsonProperty("has_vector_graphics") Boolean hasVectorGraphics
) {
    public static Builder builder() {
        return new Builder();
    }

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

private int number = 0;
private String title = null;
private List<Double> dimensions = null;
        @JsonProperty("image_count")
private Integer imageCount = null;
        @JsonProperty("table_count")
private Integer tableCount = null;
private Boolean hidden = null;
        @JsonProperty("is_blank")
private Boolean isBlank = null;
        @JsonProperty("has_vector_graphics")
private Boolean hasVectorGraphics = null;

        /** Sets the number field. */
        @JsonProperty("number")
        public Builder withNumber(final int value) {
            this.number = value;
            return this;
        }

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

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

        /** Sets the imageCount field. */
        @JsonProperty("image_count")
        public Builder withImageCount(final @Nullable int value) {
            this.imageCount = value;
            return this;
        }

        /** Sets the tableCount field. */
        @JsonProperty("table_count")
        public Builder withTableCount(final @Nullable int value) {
            this.tableCount = value;
            return this;
        }

        /** Sets the hidden field. */
        @JsonProperty("hidden")
        public Builder withHidden(final @Nullable boolean value) {
            this.hidden = value;
            return this;
        }

        /** Sets the isBlank field. */
        @JsonProperty("is_blank")
        public Builder withIsBlank(final @Nullable boolean value) {
            this.isBlank = value;
            return this;
        }

        /** Sets the hasVectorGraphics field. */
        @JsonProperty("has_vector_graphics")
        public Builder withHasVectorGraphics(final @Nullable Boolean value) {
            this.hasVectorGraphics = value;
            return this;
        }

        /** Builds the PageInfo instance. */
        public PageInfo build() {
            return new PageInfo(
                number,
                title,
                dimensions,
                imageCount,
                tableCount,
                hidden,
                isBlank,
                hasVectorGraphics
            );
        }
    }
    // CPD-ON
}