organic/src/parser/citation_reference.rs

use nom::branch::alt;
use nom::bytes::complete::tag;
use nom::character::complete::anychar;
use nom::combinator::not;
use nom::combinator::opt;
use nom::combinator::recognize;
use nom::combinator::verify;
use nom::multi::many1;
use nom::multi::many_till;
use nom::sequence::preceded;
use nom::sequence::tuple;

use super::org_source::OrgSource;
use super::Context;
use crate::error::CustomError;
use crate::error::Res;
use crate::parser::exiting::ExitClass;
use crate::parser::object::CitationReference;
use crate::parser::object_parser::minimal_set_object;
use crate::parser::parser_context::CitationBracket;
use crate::parser::parser_context::ContextElement;
use crate::parser::parser_context::ExitMatcherNode;
use crate::parser::parser_with_context::parser_with_context;
use crate::parser::util::exit_matcher_parser;
use crate::parser::util::get_consumed;
use crate::parser::util::WORD_CONSTITUENT_CHARACTERS;
use crate::parser::Object;

#[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))]
pub fn citation_reference<'r, 's>(
    context: Context<'r, 's>,
    input: OrgSource<'s>,
) -> Res<OrgSource<'s>, CitationReference<'s>> {
    let (remaining, _prefix) = opt(parser_with_context!(key_prefix)(context))(input)?;
    let (remaining, _key) = parser_with_context!(citation_reference_key)(context)(remaining)?;
    let (remaining, _suffix) = opt(parser_with_context!(key_suffix)(context))(remaining)?;
    let source = get_consumed(input, remaining);

    Ok((
        remaining,
        CitationReference {
            source: source.into(),
        },
    ))
}

#[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))]
pub fn citation_reference_key<'r, 's>(
    context: Context<'r, 's>,
    input: OrgSource<'s>,
) -> Res<OrgSource<'s>, OrgSource<'s>> {
    let (remaining, source) = recognize(tuple((
        tag("@"),
        many1(verify(
            preceded(
                not(parser_with_context!(exit_matcher_parser)(context)),
                anychar,
            ),
            |c| {
                WORD_CONSTITUENT_CHARACTERS.contains(*c) || "-.:?~`'/*@+|(){}<>&_^$#%~".contains(*c)
            },
        )),
    )))(input)?;
    Ok((remaining, source))
}

#[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))]
fn key_prefix<'r, 's>(
    context: Context<'r, 's>,
    input: OrgSource<'s>,
) -> Res<OrgSource<'s>, Vec<Object<'s>>> {
    // TODO: I could insert CitationBracket entries in the context after each matched object to reduce the scanning done for counting brackets which should be more efficient.
    let parser_context = context
        .with_additional_node(ContextElement::CitationBracket(CitationBracket {
            position: input,
            depth: 0,
        }))
        .with_additional_node(ContextElement::ExitMatcherNode(ExitMatcherNode {
            class: ExitClass::Gamma,
            exit_matcher: &key_prefix_end,
        }));
    let (remaining, (children, _exit_contents)) = verify(
        many_till(
            parser_with_context!(minimal_set_object)(&parser_context),
            parser_with_context!(exit_matcher_parser)(&parser_context),
        ),
        |(children, _exit_contents)| !children.is_empty(),
    )(input)?;
    Ok((remaining, children))
}

#[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))]
fn key_suffix<'r, 's>(
    context: Context<'r, 's>,
    input: OrgSource<'s>,
) -> Res<OrgSource<'s>, Vec<Object<'s>>> {
    // TODO: I could insert CitationBracket entries in the context after each matched object to reduce the scanning done for counting brackets which should be more efficient.
    let parser_context = context
        .with_additional_node(ContextElement::CitationBracket(CitationBracket {
            position: input,
            depth: 0,
        }))
        .with_additional_node(ContextElement::ExitMatcherNode(ExitMatcherNode {
            class: ExitClass::Gamma,
            exit_matcher: &key_suffix_end,
        }));
    let (remaining, (children, _exit_contents)) = verify(
        many_till(
            parser_with_context!(minimal_set_object)(&parser_context),
            parser_with_context!(exit_matcher_parser)(&parser_context),
        ),
        |(children, _exit_contents)| !children.is_empty(),
    )(input)?;
    Ok((remaining, children))
}

#[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))]
pub fn get_bracket_depth<'r, 's>(context: Context<'r, 's>) -> Option<&'r CitationBracket<'s>> {
    for node in context.iter() {
        match node.get_data() {
            ContextElement::CitationBracket(depth) => return Some(depth),
            _ => {}
        }
    }
    None
}

#[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))]
fn key_prefix_end<'r, 's>(
    context: Context<'r, 's>,
    input: OrgSource<'s>,
) -> Res<OrgSource<'s>, OrgSource<'s>> {
    let context_depth = get_bracket_depth(context)
        .expect("This function should only be called from inside a citation reference.");
    let text_since_context_entry = get_consumed(context_depth.position, input);
    let mut current_depth = context_depth.depth;
    for c in Into::<&str>::into(text_since_context_entry).chars() {
        match c {
            '[' => {
                current_depth += 1;
            }
            ']' if current_depth == 0 => {
                panic!("Exceeded citation reference key prefix bracket depth.")
            }
            ']' if current_depth > 0 => {
                current_depth -= 1;
            }
            _ => {}
        }
    }
    if current_depth == 0 {
        let close_bracket = tag::<&str, OrgSource<'_>, CustomError<OrgSource<'_>>>("]")(input);
        if close_bracket.is_ok() {
            return close_bracket;
        }
    }
    alt((
        tag(";"),
        recognize(parser_with_context!(citation_reference_key)(context)),
    ))(input)
}

#[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))]
fn key_suffix_end<'r, 's>(
    context: Context<'r, 's>,
    input: OrgSource<'s>,
) -> Res<OrgSource<'s>, OrgSource<'s>> {
    let context_depth = get_bracket_depth(context)
        .expect("This function should only be called from inside a citation reference.");
    let text_since_context_entry = get_consumed(context_depth.position, input);
    let mut current_depth = context_depth.depth;
    for c in Into::<&str>::into(text_since_context_entry).chars() {
        match c {
            '[' => {
                current_depth += 1;
            }
            ']' if current_depth == 0 => {
                panic!("Exceeded citation reference key prefix bracket depth.")
            }
            ']' if current_depth > 0 => {
                current_depth -= 1;
            }
            _ => {}
        }
    }
    if current_depth == 0 {
        let close_bracket = tag::<&str, OrgSource<'_>, CustomError<OrgSource<'_>>>("]")(input);
        if close_bracket.is_ok() {
            return close_bracket;
        }
    }
    tag(";")(input)
}