Struct ExtractorConfig 

pub struct ExtractorConfig {
    pub max_length: usize,
    pub timeout_secs: u64,
    pub clean_text: bool,
    pub preserve_whitespace: bool,
    pub user_agent: String,
    pub follow_redirects: bool,
    pub max_redirects: usize,
    pub sanitize: bool,
    pub redact_pii: bool,
    pub detect_injection: bool,
}

Configuration for content extraction

Fields

max_length: usize

Maximum content length to extract (in characters)

timeout_secs: u64

Request timeout in seconds

clean_text: bool

Whether to extract clean text (remove HTML tags, scripts, etc.)

preserve_whitespace: bool

Whether to preserve whitespace formatting

user_agent: String

User agent for web requests

follow_redirects: bool

Whether to follow redirects

max_redirects: usize

Maximum redirects to follow

sanitize: bool

Whether to sanitize output via hanzo-guard

redact_pii: bool

Whether to redact PII

detect_injection: bool

Whether to detect injection attempts

Implementations

impl ExtractorConfig

pub fn with_max_length(self, max_length: usize) -> Self

Create a new config with custom max length

pub fn with_timeout(self, timeout_secs: u64) -> Self

Create a new config with custom timeout

pub fn with_clean_text(self, clean: bool) -> Self

Enable or disable text cleaning

pub fn with_sanitize(self, sanitize: bool) -> Self

Enable or disable sanitization

pub fn with_redact_pii(self, redact: bool) -> Self

Enable or disable PII redaction

pub fn with_detect_injection(self, detect: bool) -> Self

Enable or disable injection detection

Trait Implementations

impl Clone for ExtractorConfig

fn clone(&self) -> ExtractorConfig

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for ExtractorConfig

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

Formats the value using the given formatter.

impl Default for ExtractorConfig

fn default() -> Self

Returns the “default value” for a type.

impl<'de> Deserialize<'de> for ExtractorConfig

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

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Serialize for ExtractorConfig

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

where __S: Serializer,

Serialize this value into the given Serde serializer.