Struct TextCleaner 

pub struct TextCleaner {
    pub newlines: Newlines,
    pub remove_non_basic_ascii: bool,
    pub remove_citations: bool,
}

Fields

newlines: Newlines

remove_non_basic_ascii: bool

remove_citations: bool

Implementations

impl TextCleaner

pub fn new() -> Self

pub fn do_not_reduce_newlines(self) -> Self

pub fn reduce_newlines_to_single_space(self) -> Self

pub fn reduce_newlines_to_single_newline(self) -> Self

pub fn reduce_newlines_to_double_newline(self) -> Self

pub fn remove_non_basic_ascii(self) -> Self

pub fn remove_citations(self) -> Self

pub fn run(&self, text: &str) -> String

Single-pass text cleaning with integrated citation removal, whitespace collapsing, and newline normalization. Uses a blacklist approach for character filtering to preserve all visible text including URLs, code, and multilingual content.

Trait Implementations

impl Default for TextCleaner

fn default() -> TextCleaner

Returns the “default value” for a type.