organic/src/parser/document.rs

use nom::branch::alt;
use nom::bytes::complete::tag;
use nom::character::complete::line_ending;
use nom::character::complete::space1;
use nom::combinator::eof;
use nom::combinator::map;
use nom::combinator::not;
use nom::combinator::opt;
use nom::combinator::recognize;
use nom::combinator::verify;
use nom::multi::many0;
use nom::multi::many1;
use nom::multi::many1_count;
use nom::multi::many_till;
use nom::sequence::tuple;

use super::element::Element;
use super::object::Object;
use super::parser_with_context::parser_with_context;
use super::source::Source;
use super::token::Token;
use super::util::exit_matcher_parser;
use super::util::get_consumed;
use super::util::start_of_line;
use super::Context;
use crate::error::Res;
use crate::parser::comment::comment;
use crate::parser::element_parser::element;
use crate::parser::exiting::ExitClass;
use crate::parser::object_parser::standard_set_object;
use crate::parser::parser_context::ContextElement;
use crate::parser::parser_context::ContextTree;
use crate::parser::parser_context::ExitMatcherNode;
use crate::parser::planning::planning;
use crate::parser::property_drawer::property_drawer;
use crate::parser::util::blank_line;
use crate::parser::util::maybe_consume_trailing_whitespace_if_not_exiting;

#[derive(Debug)]
pub struct Document<'s> {
    pub source: &'s str,
    pub zeroth_section: Option<Section<'s>>,
    pub children: Vec<Heading<'s>>,
}

#[derive(Debug)]
pub struct Heading<'s> {
    pub source: &'s str,
    pub stars: usize,
    pub title: Vec<Object<'s>>,
    pub children: Vec<DocumentElement<'s>>,
}

#[derive(Debug)]
pub struct Section<'s> {
    pub source: &'s str,
    pub children: Vec<Element<'s>>,
}

#[derive(Debug)]
pub enum DocumentElement<'s> {
    Heading(Heading<'s>),
    Section(Section<'s>),
}

impl<'s> Source<'s> for Document<'s> {
    fn get_source(&'s self) -> &'s str {
        self.source
    }
}

impl<'s> Source<'s> for DocumentElement<'s> {
    fn get_source(&'s self) -> &'s str {
        match self {
            DocumentElement::Heading(obj) => obj.source,
            DocumentElement::Section(obj) => obj.source,
        }
    }
}

impl<'s> Source<'s> for Section<'s> {
    fn get_source(&'s self) -> &'s str {
        self.source
    }
}

impl<'s> Source<'s> for Heading<'s> {
    fn get_source(&'s self) -> &'s str {
        self.source
    }
}

#[tracing::instrument(ret, level = "debug")]
#[allow(dead_code)]
pub fn document(input: &str) -> Res<&str, Document> {
    let initial_context: ContextTree<'_, '_> = ContextTree::new();
    let document_context =
        initial_context.with_additional_node(ContextElement::DocumentRoot(input));
    let zeroth_section_matcher = parser_with_context!(zeroth_section)(&document_context);
    let heading_matcher = parser_with_context!(heading)(&document_context);
    let (remaining, _blank_lines) = many0(blank_line)(input)?;
    let (remaining, zeroth_section) = opt(zeroth_section_matcher)(remaining)?;
    let (remaining, children) = many0(heading_matcher)(remaining)?;
    let source = get_consumed(input, remaining);
    Ok((
        remaining,
        Document {
            source,
            zeroth_section,
            children,
        },
    ))
}

#[tracing::instrument(ret, level = "debug")]
fn zeroth_section<'r, 's>(context: Context<'r, 's>, input: &'s str) -> Res<&'s str, Section<'s>> {
    // TODO: The zeroth section is specialized so it probably needs its own parser
    let parser_context = context
        .with_additional_node(ContextElement::ConsumeTrailingWhitespace(true))
        .with_additional_node(ContextElement::Context("section"))
        .with_additional_node(ContextElement::ExitMatcherNode(ExitMatcherNode {
            class: ExitClass::Document,
            exit_matcher: &section_end,
        }));
    let without_consuming_whitespace_context =
        parser_context.with_additional_node(ContextElement::ConsumeTrailingWhitespace(false));

    let element_matcher = parser_with_context!(element(true))(&parser_context);
    let exit_matcher = parser_with_context!(exit_matcher_parser)(&parser_context);

    let (remaining, comment_and_property_drawer_element) = opt(tuple((
        opt(parser_with_context!(comment)(
            &without_consuming_whitespace_context,
        )),
        parser_with_context!(property_drawer)(&without_consuming_whitespace_context),
        many0(blank_line),
    )))(input)?;

    let (remaining, (mut children, _exit_contents)) = verify(
        many_till(element_matcher, exit_matcher),
        |(children, _exit_contents)| {
            !children.is_empty() || comment_and_property_drawer_element.is_some()
        },
    )(remaining)?;

    comment_and_property_drawer_element.map(|(comment, property_drawer, _ws)| {
        children.insert(0, Element::PropertyDrawer(property_drawer));
        comment
            .map(Element::Comment)
            .map(|ele| children.insert(0, ele));
    });

    let (remaining, _trailing_ws) =
        maybe_consume_trailing_whitespace_if_not_exiting(context, remaining)?;

    let source = get_consumed(input, remaining);
    Ok((remaining, Section { source, children }))
}

#[tracing::instrument(ret, level = "debug")]
fn section<'r, 's>(context: Context<'r, 's>, mut input: &'s str) -> Res<&'s str, Section<'s>> {
    // TODO: The zeroth section is specialized so it probably needs its own parser
    let parser_context = context
        .with_additional_node(ContextElement::ConsumeTrailingWhitespace(true))
        .with_additional_node(ContextElement::Context("section"))
        .with_additional_node(ContextElement::ExitMatcherNode(ExitMatcherNode {
            class: ExitClass::Document,
            exit_matcher: &section_end,
        }));
    let element_matcher = parser_with_context!(element(true))(&parser_context);
    let exit_matcher = parser_with_context!(exit_matcher_parser)(&parser_context);
    let (mut remaining, (planning_element, property_drawer_element)) = tuple((
        opt(parser_with_context!(planning)(&parser_context)),
        opt(parser_with_context!(property_drawer)(&parser_context)),
    ))(input)?;
    if planning_element.is_none() && property_drawer_element.is_none() {
        let (remain, _ws) = many0(blank_line)(remaining)?;
        remaining = remain;
        input = remain;
    }
    let (remaining, (mut children, _exit_contents)) = verify(
        many_till(element_matcher, exit_matcher),
        |(children, _exit_contents)| {
            !children.is_empty() || property_drawer_element.is_some() || planning_element.is_some()
        },
    )(remaining)?;
    property_drawer_element
        .map(Element::PropertyDrawer)
        .map(|ele| children.insert(0, ele));
    planning_element
        .map(Element::Planning)
        .map(|ele| children.insert(0, ele));

    let (remaining, _trailing_ws) =
        maybe_consume_trailing_whitespace_if_not_exiting(context, remaining)?;

    let source = get_consumed(input, remaining);
    Ok((remaining, Section { source, children }))
}

#[tracing::instrument(ret, level = "debug")]
fn section_end<'r, 's>(context: Context<'r, 's>, input: &'s str) -> Res<&'s str, &'s str> {
    let headline_matcher = parser_with_context!(headline)(context);
    recognize(headline_matcher)(input)
}

#[tracing::instrument(ret, level = "debug")]
fn heading<'r, 's>(context: Context<'r, 's>, input: &'s str) -> Res<&'s str, Heading<'s>> {
    not(|i| context.check_exit_matcher(i))(input)?;
    let (remaining, (star_count, _ws, title)) = headline(context, input)?;
    let section_matcher = parser_with_context!(section)(context);
    let heading_matcher = parser_with_context!(heading)(context);
    let (remaining, children) = many0(alt((
        map(
            verify(heading_matcher, |h| h.stars > star_count),
            DocumentElement::Heading,
        ),
        map(section_matcher, DocumentElement::Section),
    )))(remaining)?;
    let source = get_consumed(input, remaining);
    Ok((
        remaining,
        Heading {
            source,
            stars: star_count,
            title,
            children,
        },
    ))
}

#[tracing::instrument(ret, level = "debug")]
fn headline<'r, 's>(
    context: Context<'r, 's>,
    input: &'s str,
) -> Res<&'s str, (usize, &'s str, Vec<Object<'s>>)> {
    let parser_context =
        context.with_additional_node(ContextElement::ExitMatcherNode(ExitMatcherNode {
            class: ExitClass::Document,
            exit_matcher: &headline_end,
        }));
    let standard_set_object_matcher = parser_with_context!(standard_set_object)(&parser_context);
    let start_of_line_matcher = parser_with_context!(start_of_line)(&parser_context);

    let (remaining, (_sol, star_count, ws, title, _line_ending)) = tuple((
        start_of_line_matcher,
        many1_count(tag("*")),
        space1,
        many1(standard_set_object_matcher),
        alt((line_ending, eof)),
    ))(input)?;
    Ok((remaining, (star_count, ws, title)))
}

#[tracing::instrument(ret, level = "debug")]
fn headline_end<'r, 's>(_context: Context<'r, 's>, input: &'s str) -> Res<&'s str, &'s str> {
    line_ending(input)
}

impl<'s> Document<'s> {
    pub fn iter_tokens<'r>(&'r self) -> impl Iterator<Item = Token<'r, 's>> {
        self.zeroth_section
            .iter()
            .map(Token::Section)
            .chain(self.children.iter().map(Token::Heading))
    }
}

impl<'s> Heading<'s> {
    pub fn iter_tokens<'r>(&'r self) -> impl Iterator<Item = Token<'r, 's>> {
        self.title.iter().map(Token::Object).chain(self.children.iter().map(
            |de| {
                match de {
                    DocumentElement::Heading(obj) => Token::Heading(obj),
                    DocumentElement::Section(obj) => Token::Section(obj),
                }
            }
        ))
    }
}

impl<'s> Section<'s> {
    pub fn iter_tokens<'r>(&'r self) -> impl Iterator<Item = Token<'r, 's>> {
        self.children.iter().map(Token::Element)
    }
}