Struct BasicTextCleaner 

pub struct BasicTextCleaner { /* private fields */ }

Text cleaner for removing special characters, extra whitespace, and stopwords

Implementations

impl BasicTextCleaner

pub fn new( remove_special_chars: bool, remove_stopwords: bool, normalize_whitespace: bool, ) -> Self

Create a new text cleaner

pub fn with_stopwords( remove_special_chars: bool, remove_stopwords: bool, normalize_whitespace: bool, stopwords: HashSet<String>, ) -> Self

Create a text cleaner with custom stopwords

pub fn add_stopwords(&mut self, words: &[&str])

Add stopwords to the cleaner

pub fn is_stopword(&self, word: &str) -> bool

Check if a word is a stopword

Trait Implementations

impl Clone for BasicTextCleaner

fn clone(&self) -> BasicTextCleaner

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for BasicTextCleaner

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

Formats the value using the given formatter.

impl Default for BasicTextCleaner

fn default() -> Self

Returns the “default value” for a type.

impl TextCleaner for BasicTextCleaner

fn clean(&self, text: &str) -> Result<String>

Clean the input text

fn clean_batch(&self, texts: &[&str]) -> Result<Vec<String>>

Clean a batch of texts