99 lines
3.0 KiB
Java
99 lines
3.0 KiB
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;
|
||
|
|
|
||
|
|
/**
|
||
|
|
* Unified page structure for documents.
|
||
|
|
*
|
||
|
|
* Supports different page types (PDF pages, PPTX slides, Excel sheets)
|
||
|
|
* with character offset boundaries for chunk-to-page mapping.
|
||
|
|
*/
|
||
|
|
@JsonInclude(JsonInclude.Include.NON_ABSENT)
|
||
|
|
@JsonDeserialize(builder = PageStructure.Builder.class)
|
||
|
|
public record PageStructure(
|
||
|
|
/**
|
||
|
|
* Total number of pages/slides/sheets
|
||
|
|
*/
|
||
|
|
@JsonProperty("total_count") int totalCount,
|
||
|
|
/**
|
||
|
|
* Type of paginated unit
|
||
|
|
*/
|
||
|
|
@JsonProperty("unit_type") PageUnitType unitType,
|
||
|
|
/**
|
||
|
|
* Character offset boundaries for each page
|
||
|
|
*
|
||
|
|
* Maps character ranges in the extracted content to page numbers.
|
||
|
|
* Used for chunk page range calculation.
|
||
|
|
*/
|
||
|
|
@Nullable @JsonProperty("boundaries") List<PageBoundary> boundaries,
|
||
|
|
/**
|
||
|
|
* Detailed per-page metadata (optional, only when needed)
|
||
|
|
*/
|
||
|
|
@Nullable @JsonProperty("pages") List<PageInfo> pages
|
||
|
|
) {
|
||
|
|
public static Builder builder() {
|
||
|
|
return new Builder();
|
||
|
|
}
|
||
|
|
|
||
|
|
// CPD-OFF
|
||
|
|
@JsonPOJOBuilder(withPrefix = "with", buildMethodName = "build")
|
||
|
|
public static final class Builder {
|
||
|
|
|
||
|
|
@JsonProperty("total_count")
|
||
|
|
private int totalCount = 0;
|
||
|
|
@JsonProperty("unit_type")
|
||
|
|
private PageUnitType unitType = null;
|
||
|
|
private List<PageBoundary> boundaries = null;
|
||
|
|
private List<PageInfo> pages = null;
|
||
|
|
|
||
|
|
/** Sets the totalCount field. */
|
||
|
|
@JsonProperty("total_count")
|
||
|
|
public Builder withTotalCount(final int value) {
|
||
|
|
this.totalCount = value;
|
||
|
|
return this;
|
||
|
|
}
|
||
|
|
|
||
|
|
/** Sets the unitType field. */
|
||
|
|
@JsonProperty("unit_type")
|
||
|
|
public Builder withUnitType(final PageUnitType value) {
|
||
|
|
this.unitType = value;
|
||
|
|
return this;
|
||
|
|
}
|
||
|
|
|
||
|
|
/** Sets the boundaries field. */
|
||
|
|
@JsonProperty("boundaries")
|
||
|
|
public Builder withBoundaries(final @Nullable List<PageBoundary> value) {
|
||
|
|
this.boundaries = value;
|
||
|
|
return this;
|
||
|
|
}
|
||
|
|
|
||
|
|
/** Sets the pages field. */
|
||
|
|
@JsonProperty("pages")
|
||
|
|
public Builder withPages(final @Nullable List<PageInfo> value) {
|
||
|
|
this.pages = value;
|
||
|
|
return this;
|
||
|
|
}
|
||
|
|
|
||
|
|
/** Builds the PageStructure instance. */
|
||
|
|
public PageStructure build() {
|
||
|
|
return new PageStructure(
|
||
|
|
totalCount,
|
||
|
|
unitType,
|
||
|
|
boundaries,
|
||
|
|
pages
|
||
|
|
);
|
||
|
|
}
|
||
|
|
}
|
||
|
|
// CPD-ON
|
||
|
|
}
|