106 lines
3.1 KiB
Java
106 lines
3.1 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;
|
||
|
|
|
||
|
|
/**
|
||
|
|
* A text block with hierarchy level assignment.
|
||
|
|
*
|
||
|
|
* Represents a block of text with semantic heading information extracted from
|
||
|
|
* font size clustering and hierarchical analysis.
|
||
|
|
*/
|
||
|
|
@JsonInclude(JsonInclude.Include.NON_ABSENT)
|
||
|
|
@JsonDeserialize(builder = HierarchicalBlock.Builder.class)
|
||
|
|
public record HierarchicalBlock(
|
||
|
|
/**
|
||
|
|
* The text content of this block
|
||
|
|
*/
|
||
|
|
@JsonProperty("text") String text,
|
||
|
|
/**
|
||
|
|
* The font size of the text in this block
|
||
|
|
*/
|
||
|
|
@JsonProperty("font_size") float fontSize,
|
||
|
|
/**
|
||
|
|
* The hierarchy level of this block (H1-H6 or Body)
|
||
|
|
*
|
||
|
|
* Levels correspond to HTML heading tags:
|
||
|
|
* - "h1": Top-level heading
|
||
|
|
* - "h2": Secondary heading
|
||
|
|
* - "h3": Tertiary heading
|
||
|
|
* - "h4": Quaternary heading
|
||
|
|
* - "h5": Quinary heading
|
||
|
|
* - "h6": Senary heading
|
||
|
|
* - "body": Body text (no heading level)
|
||
|
|
*/
|
||
|
|
@JsonProperty("level") String level,
|
||
|
|
/**
|
||
|
|
* Bounding box information for the block
|
||
|
|
*
|
||
|
|
* Contains coordinates as (left, top, right, bottom) in PDF units.
|
||
|
|
*/
|
||
|
|
@Nullable @JsonProperty("bbox") List<Float> bbox
|
||
|
|
) {
|
||
|
|
public static Builder builder() {
|
||
|
|
return new Builder();
|
||
|
|
}
|
||
|
|
|
||
|
|
// CPD-OFF
|
||
|
|
@JsonPOJOBuilder(withPrefix = "with", buildMethodName = "build")
|
||
|
|
public static final class Builder {
|
||
|
|
|
||
|
|
private String text = "";
|
||
|
|
@JsonProperty("font_size")
|
||
|
|
private float fontSize = 0.0f;
|
||
|
|
private String level = "";
|
||
|
|
private List<Float> bbox = null;
|
||
|
|
|
||
|
|
/** Sets the text field. */
|
||
|
|
@JsonProperty("text")
|
||
|
|
public Builder withText(final String value) {
|
||
|
|
this.text = value;
|
||
|
|
return this;
|
||
|
|
}
|
||
|
|
|
||
|
|
/** Sets the fontSize field. */
|
||
|
|
@JsonProperty("font_size")
|
||
|
|
public Builder withFontSize(final float value) {
|
||
|
|
this.fontSize = value;
|
||
|
|
return this;
|
||
|
|
}
|
||
|
|
|
||
|
|
/** Sets the level field. */
|
||
|
|
@JsonProperty("level")
|
||
|
|
public Builder withLevel(final String value) {
|
||
|
|
this.level = value;
|
||
|
|
return this;
|
||
|
|
}
|
||
|
|
|
||
|
|
/** Sets the bbox field. */
|
||
|
|
@JsonProperty("bbox")
|
||
|
|
public Builder withBbox(final @Nullable List<Float> value) {
|
||
|
|
this.bbox = value;
|
||
|
|
return this;
|
||
|
|
}
|
||
|
|
|
||
|
|
/** Builds the HierarchicalBlock instance. */
|
||
|
|
public HierarchicalBlock build() {
|
||
|
|
return new HierarchicalBlock(
|
||
|
|
text,
|
||
|
|
fontSize,
|
||
|
|
level,
|
||
|
|
bbox
|
||
|
|
);
|
||
|
|
}
|
||
|
|
}
|
||
|
|
// CPD-ON
|
||
|
|
}
|