Struct SpatialClusteringConfig 

pub struct SpatialClusteringConfig {
    pub enabled: bool,
    pub enable_paragraph_merging: bool,
    pub enable_spatial_adjacency: bool,
    pub min_line_height: f32,
    pub vertical_gap_threshold_multiplier: f32,
    pub horizontal_alignment_tolerance: f32,
    pub line_grouping_tolerance: f32,
    pub sections: ElementClusteringConfig,
    pub paragraphs: ElementClusteringConfig,
}

Fields

enabled: bool

Enable spatial clustering (if false, falls back to old method)

enable_paragraph_merging: bool

Enable paragraph merging based on Tika’s paragraph_number detection

enable_spatial_adjacency: bool

Enable spatial adjacency clustering (groups spatially adjacent elements)

min_line_height: f32

Minimum line height in points

vertical_gap_threshold_multiplier: f32

Multiplier for line height to detect section breaks (e.g., 0.8 = 80% of line height)

horizontal_alignment_tolerance: f32

X-coordinate tolerance for text alignment in points

line_grouping_tolerance: f32

Line tolerance as percentage of line height for grouping text lines

sections: ElementClusteringConfig

Configuration for section clustering

paragraphs: ElementClusteringConfig

Configuration for paragraph clustering

Trait Implementations

impl Clone for SpatialClusteringConfig

fn clone(&self) -> SpatialClusteringConfig

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for SpatialClusteringConfig

fn fmt(&self, f: &mut Formatter<'_>) -> Result<(), Error>

Formats the value using the given formatter.

impl<'de> Deserialize<'de> for SpatialClusteringConfig

fn deserialize<__D>( __deserializer: __D, ) -> Result<SpatialClusteringConfig, <__D as Deserializer<'de>>::Error>

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Serialize for SpatialClusteringConfig

fn serialize<__S>( &self, __serializer: __S, ) -> Result<<__S as Serializer>::Ok, <__S as Serializer>::Error>

where __S: Serializer,

Serialize this value into the given Serde serializer.