Initial implementation for citations.

This implementation definitely has bugs and is completely untested at this point. I'm just committing the initial "assume everything works" version before I did into debugging and fixing.
This commit is contained in:
Tom Alexander 2023-07-21 17:52:18 -04:00
parent e24b413cd0
commit 6b47a6c6c3
Signed by: talexander
GPG Key ID: D3A179C9A53C0EDE
2 changed files with 181 additions and 7 deletions

View File

@ -1,10 +1,178 @@
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::util::not_yet_implemented;
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>> {
not_yet_implemented()?;
todo!()
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)
}

View File

@ -30,7 +30,7 @@ pub fn citation_reference<'r, 's>(
input: &'s str,
) -> Res<&'s str, CitationReference<'s>> {
let (remaining, _prefix) = parser_with_context!(key_prefix)(context)(input)?;
let (remaining, _key) = parser_with_context!(key)(context)(remaining)?;
let (remaining, _key) = parser_with_context!(citation_reference_key)(context)(remaining)?;
let (remaining, _suffix) = parser_with_context!(key_suffix)(context)(remaining)?;
let source = get_consumed(input, remaining);
@ -38,7 +38,10 @@ pub fn citation_reference<'r, 's>(
}
#[tracing::instrument(ret, level = "debug")]
fn key<'r, 's>(context: Context<'r, 's>, input: &'s str) -> Res<&'s str, &'s str> {
pub fn citation_reference_key<'r, 's>(
context: Context<'r, 's>,
input: &'s str,
) -> Res<&'s str, &'s str> {
let (remaining, source) = recognize(tuple((
tag("@"),
many1(verify(
@ -99,7 +102,7 @@ fn key_suffix<'r, 's>(context: Context<'r, 's>, input: &'s str) -> Res<&'s str,
}
#[tracing::instrument(ret, level = "debug")]
fn get_bracket_depth<'r, 's>(context: Context<'r, 's>) -> Option<&'r CitationBracket<'s>> {
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),
@ -135,7 +138,10 @@ fn key_prefix_end<'r, 's>(context: Context<'r, 's>, input: &'s str) -> Res<&'s s
return close_bracket;
}
}
alt((tag(";"), recognize(parser_with_context!(key)(context))))(input)
alt((
tag(";"),
recognize(parser_with_context!(citation_reference_key)(context)),
))(input)
}
#[tracing::instrument(ret, level = "debug")]