organic/src/parser/citation.rs

use nom::branch::alt;
use nom::bytes::complete::tag;
use nom::bytes::complete::tag_no_case;
use nom::character::complete::anychar;
use nom::combinator::opt;
use nom::combinator::recognize;
use nom::combinator::verify;
use nom::multi::many0;
use nom::multi::many1;
use nom::multi::many_till;
use nom::sequence::tuple;

use super::Context;
use crate::error::CustomError;
use crate::error::Res;
use crate::parser::citation_reference::citation_reference;
use crate::parser::citation_reference::citation_reference_key;
use crate::parser::citation_reference::get_bracket_depth;
use crate::parser::exiting::ExitClass;
use crate::parser::object::Citation;
use crate::parser::object_parser::standard_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::Object;

#[tracing::instrument(ret, level = "debug")]
pub fn citation<'r, 's>(context: Context<'r, 's>, input: &'s str) -> Res<&'s str, Citation<'s>> {
    let (remaining, _) = tag_no_case("[cite")(input)?;
    let (remaining, _) = opt(citestyle)(remaining)?;
    let (remaining, _) = tag(":")(remaining)?;
    let (remaining, _prefix) = parser_with_context!(global_prefix)(context)(remaining)?;
    let (remaining, _references) =
        many0(parser_with_context!(citation_reference)(context))(remaining)?;
    let (remaining, _suffix) = parser_with_context!(global_suffix)(context)(remaining)?;
    let (remaining, _) = tag("]")(remaining)?;
    let source = get_consumed(input, remaining);
    Ok((remaining, Citation { source }))
}

#[tracing::instrument(ret, level = "debug")]
fn citestyle<'r, 's>(input: &'s str) -> Res<&'s str, &'s str> {
    let (remaining, _) = tuple((tag("/"), style))(input)?;
    let (remaining, _) = opt(tuple((tag("/"), variant)))(remaining)?;
    let source = get_consumed(input, remaining);
    Ok((remaining, source))
}

#[tracing::instrument(ret, level = "debug")]
fn style<'r, 's>(input: &'s str) -> Res<&'s str, &'s str> {
    recognize(many1(verify(anychar, |c| {
        c.is_alphanumeric() || "_-".contains(*c)
    })))(input)
}

#[tracing::instrument(ret, level = "debug")]
fn variant<'r, 's>(input: &'s str) -> Res<&'s str, &'s str> {
    recognize(many1(verify(anychar, |c| {
        c.is_alphanumeric() || "_-/".contains(*c)
    })))(input)
}

#[tracing::instrument(ret, level = "debug")]
fn global_prefix<'r, 's>(
    context: Context<'r, 's>,
    input: &'s str,
) -> Res<&'s str, 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::Beta,
            exit_matcher: &global_prefix_end,
        }));
    let (remaining, (children, _exit_contents)) = verify(
        many_till(
            parser_with_context!(standard_set_object)(&parser_context),
            parser_with_context!(exit_matcher_parser)(&parser_context),
        ),
        |(children, _exit_contents)| !children.is_empty(),
    )(input)?;
    Ok((remaining, children))
}

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

#[tracing::instrument(ret, level = "debug")]
fn global_suffix<'r, 's>(
    context: Context<'r, 's>,
    input: &'s str,
) -> Res<&'s str, 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::Beta,
            exit_matcher: &global_suffix_end,
        }));
    let (remaining, (children, _exit_contents)) = verify(
        many_till(
            parser_with_context!(standard_set_object)(&parser_context),
            parser_with_context!(exit_matcher_parser)(&parser_context),
        ),
        |(children, _exit_contents)| !children.is_empty(),
    )(input)?;
    Ok((remaining, children))
}

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