organic/src/parser/citation.rs
2023-09-03 16:22:40 -04:00

218 lines
8.8 KiB
Rust

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::many1;
use nom::multi::many_till;
use nom::multi::separated_list1;
use nom::sequence::tuple;
use super::citation_reference::must_balance_bracket;
use super::org_source::BracketDepth;
use super::org_source::OrgSource;
use super::util::maybe_consume_object_trailing_whitespace_if_not_exiting;
use crate::context::parser_with_context;
use crate::context::ContextElement;
use crate::context::ContextMatcher;
use crate::context::ExitClass;
use crate::context::ExitMatcherNode;
use crate::context::RefContext;
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::object_parser::standard_set_object;
use crate::parser::util::exit_matcher_parser;
use crate::parser::util::get_consumed;
use crate::types::Citation;
use crate::types::Object;
#[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))]
pub fn citation<'b, 'g, 'r, 's>(
context: RefContext<'b, 'g, 'r, 's>,
input: OrgSource<'s>,
) -> Res<OrgSource<'s>, Citation<'s>> {
// TODO: Despite being a standard object, citations cannot exist inside the global prefix/suffix for other citations because citations must contain something that matches @key which is forbidden inside the global prefix/suffix. This TODO is to evaluate if its worth putting in an explicit check for this (which can be easily accomplished by checking the output of `get_bracket_depth()`). I suspect its not worth it because I expect, outside of intentionally crafted inputs, this parser will exit immediately inside a citation since it is unlikely to find the "[cite" substring inside a citation global prefix/suffix.
let (remaining, _) = tag_no_case("[cite")(input)?;
let (remaining, _) = opt(citestyle)(remaining)?;
let (remaining, _) = tag(":")(remaining)?;
let (remaining, _prefix) =
must_balance_bracket(opt(parser_with_context!(global_prefix)(context)))(remaining)?;
let (remaining, _references) =
separated_list1(tag(";"), parser_with_context!(citation_reference)(context))(remaining)?;
let (remaining, _suffix) = must_balance_bracket(opt(tuple((
tag(";"),
parser_with_context!(global_suffix)(context),
))))(remaining)?;
let (remaining, _) = tag("]")(remaining)?;
let (remaining, _trailing_whitespace) =
maybe_consume_object_trailing_whitespace_if_not_exiting(context, remaining)?;
let source = get_consumed(input, remaining);
Ok((
remaining,
Citation {
source: source.into(),
},
))
}
#[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))]
fn citestyle<'s>(input: OrgSource<'s>) -> Res<OrgSource<'s>, OrgSource<'s>> {
let (remaining, _) = tuple((tag("/"), style))(input)?;
let (remaining, _) = opt(tuple((tag("/"), variant)))(remaining)?;
let source = get_consumed(input, remaining);
Ok((remaining, source))
}
#[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))]
fn style<'s>(input: OrgSource<'s>) -> Res<OrgSource<'s>, OrgSource<'s>> {
recognize(many1(verify(anychar, |c| {
c.is_alphanumeric() || "_-".contains(*c)
})))(input)
}
#[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))]
fn variant<'s>(input: OrgSource<'s>) -> Res<OrgSource<'s>, OrgSource<'s>> {
recognize(many1(verify(anychar, |c| {
c.is_alphanumeric() || "_-/".contains(*c)
})))(input)
}
#[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))]
fn global_prefix<'b, 'g, 'r, 's>(
context: RefContext<'b, 'g, 'r, 's>,
input: OrgSource<'s>,
) -> Res<OrgSource<'s>, Vec<Object<'s>>> {
let exit_with_depth = global_prefix_end(input.get_bracket_depth());
let parser_context = ContextElement::ExitMatcherNode(ExitMatcherNode {
class: ExitClass::Gamma,
exit_matcher: &exit_with_depth,
});
let parser_context = context.with_additional_node(&parser_context);
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)?;
let (remaining, _) = tag(";")(remaining)?;
Ok((remaining, children))
}
fn global_prefix_end(starting_bracket_depth: BracketDepth) -> impl ContextMatcher {
move |context, input: OrgSource<'_>| _global_prefix_end(context, input, starting_bracket_depth)
}
#[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))]
fn _global_prefix_end<'b, 'g, 'r, 's>(
context: RefContext<'b, 'g, 'r, 's>,
input: OrgSource<'s>,
starting_bracket_depth: BracketDepth,
) -> Res<OrgSource<'s>, OrgSource<'s>> {
let current_depth = input.get_bracket_depth() - starting_bracket_depth;
if current_depth < 0 {
// This shouldn't be possible because if depth is 0 then a closing bracket should end the citation.
unreachable!("Exceeded citation global prefix bracket depth.")
}
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 global_suffix<'b, 'g, 'r, 's>(
context: RefContext<'b, 'g, 'r, 's>,
input: OrgSource<'s>,
) -> Res<OrgSource<'s>, Vec<Object<'s>>> {
let exit_with_depth = global_suffix_end(input.get_bracket_depth());
let parser_context = ContextElement::ExitMatcherNode(ExitMatcherNode {
class: ExitClass::Gamma,
exit_matcher: &exit_with_depth,
});
let parser_context = context.with_additional_node(&parser_context);
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))
}
fn global_suffix_end(starting_bracket_depth: BracketDepth) -> impl ContextMatcher {
move |context, input: OrgSource<'_>| _global_suffix_end(context, input, starting_bracket_depth)
}
#[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))]
fn _global_suffix_end<'b, 'g, 'r, 's>(
context: RefContext<'b, 'g, 'r, 's>,
input: OrgSource<'s>,
starting_bracket_depth: BracketDepth,
) -> Res<OrgSource<'s>, OrgSource<'s>> {
let current_depth = input.get_bracket_depth() - starting_bracket_depth;
if current_depth < 0 {
// This shouldn't be possible because if depth is 0 then a closing bracket should end the citation.
unreachable!("Exceeded citation global suffix bracket depth.")
}
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(test)]
mod tests {
use super::*;
use crate::context::Context;
use crate::context::GlobalSettings;
use crate::context::List;
use crate::parser::element_parser::element;
use crate::types::Element;
use crate::types::Source;
#[test]
fn citation_simple() {
let input = OrgSource::new("[cite:@foo]");
let global_settings = GlobalSettings::default();
let initial_context = ContextElement::document_context();
let initial_context = Context::new(&global_settings, List::new(&initial_context));
let paragraph_matcher = parser_with_context!(element(true))(&initial_context);
let (remaining, first_paragraph) = paragraph_matcher(input).expect("Parse first paragraph");
let first_paragraph = match first_paragraph {
Element::Paragraph(paragraph) => paragraph,
_ => panic!("Should be a paragraph!"),
};
assert_eq!(Into::<&str>::into(remaining), "");
assert_eq!(first_paragraph.get_source(), "[cite:@foo]");
assert_eq!(first_paragraph.children.len(), 1);
assert_eq!(
first_paragraph
.children
.get(0)
.expect("Len already asserted to be 1"),
&Object::Citation(Citation {
source: "[cite:@foo]"
})
);
}
}