Struct llamapun::parallel_data::document::Document

pub struct Document<'d> {
    pub dom: XmlDoc,
    pub path: String,
    pub corpus: &'d Corpus,
    pub dnm: Option<DNM>,
}

One of our math documents, thread-friendly

Fields

dom: XmlDoc

The DOM of the document

path: String

The file path of the document

corpus: &'d Corpus

A reference to the corpus containing this document

dnm: Option<DNM>

If it exists, the DNM corresponding to this document

Implementations

impl<'d> Document<'d>

pub fn new(filepath: String, corpus: &'d Corpus) -> Result<Self, XmlParseError>

Load a new document

pub fn get_heading_nodes(&self) -> Vec<RoNode>

Obtain the problem-free logical headings of a libxml Document

pub fn heading_iter(&self) -> RoNodeIterator<'_>

Get an iterator over the headings of the document

pub fn get_paragraph_nodes(&self) -> Vec<RoNode>

Obtain the problem-free logical paragraphs of a libxml Document

pub fn paragraph_iter(&self) -> RoNodeIterator<'_>

Get an iterator over the paragraphs of the document

pub fn extended_paragraph_iter(&self) -> RoNodeIterator<'_>

Get an iterator over textual paragraphs of the document, in a loose sense, contents: abstract (first p), keywords, logical paragraphs, acknowledgement, table/figure captions

pub fn get_math_nodes(&self) -> Vec<RoNode>

Obtain the MathML $nodes\; of\; a\; libxml$Document

pub fn get_ref_nodes(&self) -> Vec<RoNode>

Obtain the <span[class=ltx_ref]> nodes of a libxml Document

pub fn sentence_iter(&mut self) -> DNMRangeIterator<'_>

Get an iterator over the sentences of the document

pub fn get_xpath_nodes(&self, xpath_str: &str) -> Vec<RoNode>

Obtain the nodes associated with the xpath evaluation over the underlying libxml Document

pub fn get_xpath_node(&self, xpath_str: &str) -> Option<RoNode>

Obtain the first node associated with the xpath evaluation over the underlying libxml Document

pub fn xpath_selector_iter(&self, xpath_str: &str) -> RoNodeIterator<'_>

Get an iterator over a custom xpath selector over the document

pub fn filter_iter(&self, filter: &dyn Fn(&RoNode) -> bool) -> RoNodeIterator<'_>

Get an iterator using a custom closure predicate filter over the document (depth-first descent)