Struct harper_core::Document

pub struct Document { /* private fields */ }

A document containing some amount of lexed and parsed English text. This is

Implementations

impl Document

pub fn new( text: &str, parser: &mut impl Parser, dictionary: &impl Dictionary, ) -> Self

Lexes and parses text to produce a document using a provided language parser and dictionary.

pub fn new_curated(text: &str, parser: &mut impl Parser) -> Self

Lexes and parses text to produce a document using a provided language parser and the included curated dictionary.

pub fn new_from_vec( source: Lrc<Vec<char>>, parser: &mut impl Parser, dictionary: &impl Dictionary, ) -> Self

Lexes and parses text to produce a document using a provided language parser and dictionary.

pub fn new_plain_english_curated(text: &str) -> Self

Parse text to produce a document using the built-in PlainEnglish parser and curated dictionary.

pub fn new_plain_english(text: &str, dictionary: &impl Dictionary) -> Self

Parse text to produce a document using the built-in PlainEnglish parser and a provided dictionary.

pub fn new_markdown_curated(text: &str) -> Self

Parse text to produce a document using the built-in Markdown parser and curated dictionary.

pub fn new_markdown(text: &str, dictionary: &impl Dictionary) -> Self

Parse text to produce a document using the built-in PlainEnglish parser and the curated dictionary.

pub fn get_token_at_char_index(&self, char_index: usize) -> Option<Token>

pub fn get_token(&self, index: usize) -> Option<Token>

Defensively attempt to grab a specific token.

pub fn tokens(&self) -> impl Iterator<Item = Token> + '_

Get an iterator over all the tokens contained in the document.

pub fn fat_tokens(&self) -> impl Iterator<Item = FatToken> + '_

Get an iterator over all the tokens contained in the document.

pub fn chunks(&self) -> impl Iterator<Item = &[Token]> + '_

Iterate over chunks.

For example, the following sentence contains two chunks separated by a comma:

Here is an example, it is short.

pub fn sentences(&self) -> impl Iterator<Item = &[Token]> + '_

Get an iterator over token slices that represent the individual sentences in a document.

pub fn get_span_content(&self, span: Span) -> &[char]

pub fn get_span_content_str(&self, span: Span) -> String

pub fn get_full_string(&self) -> String

pub fn get_full_content(&self) -> &[char]

Trait Implementations

impl Clone for Document

fn clone(&self) -> Document

Returns a copy of the value.

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

Performs copy-assignment from source.

impl Debug for Document

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

Formats the value using the given formatter.

impl Default for Document

fn default() -> Self

Returns the “default value” for a type.

impl Display for Document

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

Formats the value using the given formatter.

impl TokenStringExt for Document

fn first_word(&self) -> Option<Token>

fn last_word(&self) -> Option<Token>

fn iter_word_indices(&self) -> impl Iterator<Item = usize> + '_

fn iter_words(&self) -> impl Iterator<Item = Token> + '_

fn first_space(&self) -> Option<Token>

fn last_space(&self) -> Option<Token>

fn iter_space_indices(&self) -> impl Iterator<Item = usize> + '_

fn iter_spaces(&self) -> impl Iterator<Item = Token> + '_

fn first_apostrophe(&self) -> Option<Token>

fn last_apostrophe(&self) -> Option<Token>

fn iter_apostrophe_indices(&self) -> impl Iterator<Item = usize> + '_

fn iter_apostrophes(&self) -> impl Iterator<Item = Token> + '_

fn first_pipe(&self) -> Option<Token>

fn last_pipe(&self) -> Option<Token>

fn iter_pipe_indices(&self) -> impl Iterator<Item = usize> + '_

fn iter_pipes(&self) -> impl Iterator<Item = Token> + '_

fn first_quote(&self) -> Option<Token>

fn last_quote(&self) -> Option<Token>

fn iter_quote_indices(&self) -> impl Iterator<Item = usize> + '_

fn iter_quotes(&self) -> impl Iterator<Item = Token> + '_

fn first_number(&self) -> Option<Token>

fn last_number(&self) -> Option<Token>

fn iter_number_indices(&self) -> impl Iterator<Item = usize> + '_

fn iter_numbers(&self) -> impl Iterator<Item = Token> + '_

fn first_at(&self) -> Option<Token>

fn last_at(&self) -> Option<Token>

fn iter_at_indices(&self) -> impl Iterator<Item = usize> + '_

fn iter_ats(&self) -> impl Iterator<Item = Token> + '_

fn first_sentence_word(&self) -> Option<Token>

fn first_non_whitespace(&self) -> Option<Token>

fn span(&self) -> Option<Span>

Grab the span that represents the beginning of the first element and the end of the last element.

fn iter_linking_verb_indices(&self) -> impl Iterator<Item = usize> + '_

fn iter_linking_verbs(&self) -> impl Iterator<Item = Token> + '_