Struct ScraperConfig 

pub struct ScraperConfig {

    pub registry_url: Option<String>,
    pub auth_token: Option<String>,
    pub namespace: Option<String>,
    pub chunking_strategy: ChunkingStrategy,
    pub max_chunk_size: usize,
    pub include_overlap: bool,
    pub overlap_size: usize,
    pub language_options: HashMap<String, LanguageConfig>,
    pub exclude_patterns: Vec<String>,
    pub create_hierarchy: bool,
    pub extract_api_surface: bool,
    pub detect_licenses: bool,
    pub request_timeout: u64,
    pub rate_limit: f64,
    pub cache_dir: Option<PathBuf>,
}

Configuration for the scraper

Fields

registry_url: Option<String>

Registry URL for publishing chunks

auth_token: Option<String>

Authentication token for registry

namespace: Option<String>

Namespace for published chunks

chunking_strategy: ChunkingStrategy

Chunking strategy to use

max_chunk_size: usize

Maximum chunk size in bytes

include_overlap: bool

Include overlapping context between chunks

overlap_size: usize

Overlap size in characters

language_options: HashMap<String, LanguageConfig>

Language-specific parsing options

exclude_patterns: Vec<String>

Patterns to exclude from scraping

create_hierarchy: bool

Whether to create hierarchical chunk relationships

extract_api_surface: bool

Auto-extract API surfaces and functions

detect_licenses: bool

Whether to auto-detect licenses

request_timeout: u64

HTTP request timeout in seconds

rate_limit: f64

Rate limit: requests per second

cache_dir: Option<PathBuf>

Local cache directory

Trait Implementations

impl Clone for ScraperConfig

fn clone(&self) -> ScraperConfig

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for ScraperConfig

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

Formats the value using the given formatter.

impl Default for ScraperConfig

fn default() -> Self

Returns the “default value” for a type.

impl<'de> Deserialize<'de> for ScraperConfig

fn deserialize<__D>(__deserializer: __D) -> Result<Self, __D::Error>

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Serialize for ScraperConfig

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

where __S: Serializer,

Serialize this value into the given Serde serializer.