26 Commits

Author SHA1 Message Date
Tom Alexander
28aca041f7 Publish version 0.1.3.
Some checks failed
rustfmt Build rustfmt has failed
rust-test Build rust-test has failed
rust-build Build rust-build has succeeded
2023-08-29 23:05:36 -04:00
Tom Alexander
d82def2a70 Merge branch 'compare_improvements'
All checks were successful
rustfmt Build rustfmt has succeeded
rust-test Build rust-test has succeeded
rust-build Build rust-build has succeeded
2023-08-29 22:58:42 -04:00
Tom Alexander
d471f7178b Wrap the components of headlines in diff layers. 2023-08-29 22:57:08 -04:00
Tom Alexander
2c5c26c55f Allow diff layers that are not associated with tokens. 2023-08-29 22:47:40 -04:00
Tom Alexander
7944659802 Compare headline level. 2023-08-29 22:11:56 -04:00
Tom Alexander
58aca53144 Move get_property into util. 2023-08-29 22:07:23 -04:00
Tom Alexander
6f2d90162b Do not use the plain text parser for property drawers.
This additional exit condition was causing property drawers to parse incorrectly.
2023-08-29 22:03:20 -04:00
Tom Alexander
f170a557ed Use character offsets in diff. 2023-08-29 21:49:16 -04:00
Tom Alexander
eaa38ce772 Include an error message for failed bounds checking.
All checks were successful
rustfmt Build rustfmt has succeeded
rust-test Build rust-test has succeeded
rust-build Build rust-build has succeeded
2023-08-29 21:27:54 -04:00
Tom Alexander
a6d742a536 Fix handling line breaks after divider in description lists. 2023-08-29 21:27:54 -04:00
Tom Alexander
45be9e7bde Merge branch 'description_list'
All checks were successful
rustfmt Build rustfmt has succeeded
rust-test Build rust-test has succeeded
rust-build Build rust-build has succeeded
2023-08-29 19:36:45 -04:00
Tom Alexander
f6c895319f Add support for diffing description lists. 2023-08-29 19:35:54 -04:00
Tom Alexander
2682779534 Add support for parsing description lists. 2023-08-29 18:13:55 -04:00
Tom Alexander
b48d472546 Fix build.
All checks were successful
rustfmt Build rustfmt has succeeded
rust-test Build rust-test has succeeded
rust-build Build rust-build has succeeded
2023-08-29 18:07:35 -04:00
Tom Alexander
ea6faf728c Add test for description list. 2023-08-29 18:07:35 -04:00
Tom Alexander
f4ea1b7303 Merge branch 'accuracy_fixes_from_feeding_large_documents'
Some checks failed
rustfmt Build rustfmt has succeeded
rust-test Build rust-test has succeeded
rust-build Build rust-build has failed
2023-08-29 17:49:19 -04:00
Tom Alexander
80b55fdd45 Consume trailing whitespace for macro. 2023-08-29 17:42:58 -04:00
Tom Alexander
f426e32798 Do not include trailing punctuation or whitespace in plain links. 2023-08-29 17:35:04 -04:00
Tom Alexander
66037356c5 Add test showing plain links ending in punctuation currently do not parse correctly. 2023-08-29 17:24:44 -04:00
Tom Alexander
1bcd1895c0 Allow affiliating keywords with regular keywords. 2023-08-29 17:19:13 -04:00
Tom Alexander
e3d38cfbe2 Add a test for floating affiliated keywords. 2023-08-29 17:05:19 -04:00
Tom Alexander
2ba0dc49be Support export affiliated keywords. 2023-08-29 17:01:35 -04:00
Tom Alexander
9df40fb13f Only allow specific keywords for affiliated keywords. 2023-08-29 16:56:07 -04:00
Tom Alexander
cc671925db Support empty sections under headings. 2023-08-29 16:07:43 -04:00
Tom Alexander
950baa9d5d Only allow a single section under a heading. 2023-08-29 16:03:13 -04:00
Tom Alexander
56865c68fc Do not allow plain links without a path. 2023-08-29 15:44:04 -04:00
22 changed files with 1222 additions and 440 deletions

View File

@@ -1,6 +1,6 @@
[package] [package]
name = "organic" name = "organic"
version = "0.1.2" version = "0.1.3"
authors = ["Tom Alexander <tom@fizz.buzz>"] authors = ["Tom Alexander <tom@fizz.buzz>"]
description = "An org-mode parser." description = "An org-mode parser."
edition = "2021" edition = "2021"
@@ -14,7 +14,8 @@ include = [
"LICENSE", "LICENSE",
"**/*.rs", "**/*.rs",
"Cargo.toml", "Cargo.toml",
"tests/*" "tests/*",
"org_mode_samples/"
] ]
[lib] [lib]
@@ -40,7 +41,7 @@ tracing-subscriber = { version = "0.3.17", optional = true, features = ["env-fil
walkdir = "2.3.3" walkdir = "2.3.3"
[features] [features]
default = ["compare"] default = []
compare = [] compare = []
tracing = ["dep:opentelemetry", "dep:opentelemetry-otlp", "dep:opentelemetry-semantic-conventions", "dep:tokio", "dep:tracing", "dep:tracing-opentelemetry", "dep:tracing-subscriber"] tracing = ["dep:opentelemetry", "dep:opentelemetry-otlp", "dep:opentelemetry-semantic-conventions", "dep:tokio", "dep:tracing", "dep:tracing-opentelemetry", "dep:tracing-subscriber"]

View File

@@ -75,7 +75,7 @@ fn is_expect_fail(name: &str) -> Option<&str> {
"autogen_greater_element_drawer_drawer_with_headline_inside" => Some("Apparently lines with :end: become their own paragraph. This odd behavior needs to be investigated more."), "autogen_greater_element_drawer_drawer_with_headline_inside" => Some("Apparently lines with :end: become their own paragraph. This odd behavior needs to be investigated more."),
"autogen_element_container_priority_footnote_definition_dynamic_block" => Some("Apparently broken begin lines become their own paragraph."), "autogen_element_container_priority_footnote_definition_dynamic_block" => Some("Apparently broken begin lines become their own paragraph."),
"autogen_lesser_element_paragraphs_paragraph_with_backslash_line_breaks" => Some("The text we're getting out of the parse tree is already processed to remove line breaks, so our comparison needs to take that into account."), "autogen_lesser_element_paragraphs_paragraph_with_backslash_line_breaks" => Some("The text we're getting out of the parse tree is already processed to remove line breaks, so our comparison needs to take that into account."),
"autogen_sections_and_headings_empty_section" => Some("We are not yet handling empty sections properly."), "autogen_unicode_hearts" => Some("Unicode is coming out of emacs strange."),
_ => None, _ => None,
} }
} }

View File

@@ -0,0 +1,3 @@
(dolist (var org-element-affiliated-keywords)
(message "\"%s\"," (downcase var))
)

View File

@@ -0,0 +1,2 @@
- foo ::

View File

@@ -0,0 +1,11 @@
- foo :: bar
- cat ::
dog
- lorem
:: ipsum
-
lorem :: ipsum
- dolar *bold* foo :: ipsum
- big gap ::
stuff

View File

@@ -0,0 +1,7 @@
** foo
:PROPERTIES:
:DESCRIPTION: lorem
:ALT_TITLE: ipsum
:END:
bar

View File

@@ -0,0 +1,15 @@
#+name: foo
#+caption: bar
#+caption: baz
[[file:lorem/ipsum.png]]
#+name: cat
#+foo: dog
[[file:lorem/ipsum.png]]
#+name: cat
#+foo: dog
foo

View File

@@ -0,0 +1,52 @@
non-link text
eww://
rmail://
mhe://
irc://
info://
gnus://
docview://
bibtex://
bbdb://
w3m://
doi://
file+sys://
file+emacs://
shell://
news://
mailto://
https://
http://
ftp://
help://
file://
elisp://
randomfakeprotocl://
non-link text
non-link text
eww:
rmail:
mhe:
irc:
info:
gnus:
docview:
bibtex:
bbdb:
w3m:
doi:
file+sys:
file+emacs:
shell:
news:
mailto:
https:
http:
ftp:
help:
file:
elisp:
randomfakeprotocl:
non-link text

View File

@@ -0,0 +1,3 @@
mailto:foo@bar.baz.
mailto:foo@bar.baz....

View File

@@ -0,0 +1 @@
🧡💛💚💙💜

File diff suppressed because it is too large Load Diff

View File

@@ -51,7 +51,7 @@ pub fn assert_bounds<'s, S: Source<'s>>(
); );
let (rust_begin, rust_end) = get_offsets(source, rust); let (rust_begin, rust_end) = get_offsets(source, rust);
if (rust_begin + 1) != begin || (rust_end + 1) != end { if (rust_begin + 1) != begin || (rust_end + 1) != end {
Err(format!("Rust bounds ({rust_begin}, {rust_end}) do not match emacs bounds ({emacs_begin}, {emacs_end})", rust_begin = rust_begin + 1, rust_end = rust_end + 1, emacs_begin=begin, emacs_end=end))?; Err(format!("Rust bounds (in bytes) ({rust_begin}, {rust_end}) do not match emacs bounds ({emacs_begin}, {emacs_end})", rust_begin = rust_begin + 1, rust_end = rust_end + 1, emacs_begin=begin, emacs_end=end))?;
} }
Ok(()) Ok(())
@@ -137,3 +137,23 @@ fn maybe_token_to_usize(
.flatten() // Outer option is whether or not the param exists, inner option is whether or not it is nil .flatten() // Outer option is whether or not the param exists, inner option is whether or not it is nil
.map_or(Ok(None), |r| r.map(Some))?) .map_or(Ok(None), |r| r.map(Some))?)
} }
pub fn get_property<'s, 'x>(
emacs: &'s Token<'s>,
key: &'x str,
) -> Result<Option<&'s Token<'s>>, Box<dyn std::error::Error>> {
let children = emacs.as_list()?;
let attributes_child = children
.iter()
.nth(1)
.ok_or("Should have an attributes child.")?;
let attributes_map = attributes_child.as_map()?;
let prop = attributes_map
.get(key)
.ok_or(format!("Missing {} attribute.", key))?;
match prop.as_atom() {
Ok("nil") => return Ok(None),
_ => {}
};
Ok(Some(*prop))
}

View File

@@ -86,7 +86,7 @@ fn run_compare<P: AsRef<str>>(org_contents: P) -> Result<(), Box<dyn std::error:
eprintln!( eprintln!(
"This program was built with compare disabled. Only parsing with organic, not comparing." "This program was built with compare disabled. Only parsing with organic, not comparing."
); );
let (remaining, rust_parsed) = document(org_contents.as_ref()).map_err(|e| e.to_string())?; let (_remaining, rust_parsed) = document(org_contents.as_ref()).map_err(|e| e.to_string())?;
println!("{:#?}", rust_parsed); println!("{:#?}", rust_parsed);
Ok(()) Ok(())
} }

View File

@@ -283,10 +283,21 @@ fn _heading<'r, 's>(
headline(context, input, parent_stars)?; headline(context, input, parent_stars)?;
let section_matcher = parser_with_context!(section)(context); let section_matcher = parser_with_context!(section)(context);
let heading_matcher = parser_with_context!(heading(star_count))(context); let heading_matcher = parser_with_context!(heading(star_count))(context);
let (remaining, children) = many0(alt(( let (remaining, maybe_section) =
map(heading_matcher, DocumentElement::Heading), opt(map(section_matcher, DocumentElement::Section))(remaining)?;
map(section_matcher, DocumentElement::Section), let (remaining, mut children) =
)))(remaining)?; many0(map(heading_matcher, DocumentElement::Heading))(remaining)?;
if let Some(section) = maybe_section {
children.insert(0, section);
}
let remaining = if children.is_empty() {
// Support empty headings
let (remain, _ws) = many0(blank_line)(remaining)?;
remain
} else {
remaining
};
let source = get_consumed(input, remaining); let source = get_consumed(input, remaining);
Ok(( Ok((
remaining, remaining,

View File

@@ -12,6 +12,7 @@ use super::fixed_width_area::fixed_width_area;
use super::footnote_definition::footnote_definition; use super::footnote_definition::footnote_definition;
use super::greater_block::greater_block; use super::greater_block::greater_block;
use super::horizontal_rule::horizontal_rule; use super::horizontal_rule::horizontal_rule;
use super::keyword::affiliated_keyword;
use super::keyword::keyword; use super::keyword::keyword;
use super::latex_environment::latex_environment; use super::latex_environment::latex_environment;
use super::lesser_block::comment_block; use super::lesser_block::comment_block;
@@ -62,10 +63,12 @@ fn _element<'r, 's>(
let fixed_width_area_matcher = parser_with_context!(fixed_width_area)(context); let fixed_width_area_matcher = parser_with_context!(fixed_width_area)(context);
let horizontal_rule_matcher = parser_with_context!(horizontal_rule)(context); let horizontal_rule_matcher = parser_with_context!(horizontal_rule)(context);
let keyword_matcher = parser_with_context!(keyword)(context); let keyword_matcher = parser_with_context!(keyword)(context);
let affiliated_keyword_matcher = parser_with_context!(affiliated_keyword)(context);
let paragraph_matcher = parser_with_context!(paragraph)(context); let paragraph_matcher = parser_with_context!(paragraph)(context);
let latex_environment_matcher = parser_with_context!(latex_environment)(context); let latex_environment_matcher = parser_with_context!(latex_environment)(context);
let (remaining, mut affiliated_keywords) = many0(keyword_matcher)(input)?; // TODO: Affiliated keywords cannot be on comments, clocks, headings, inlinetasks, items, node properties, planning, property drawers, sections, and table rows
let (remaining, mut affiliated_keywords) = many0(affiliated_keyword_matcher)(input)?;
let (remaining, mut element) = match alt(( let (remaining, mut element) = match alt((
map(plain_list_matcher, Element::PlainList), map(plain_list_matcher, Element::PlainList),
map(greater_block_matcher, Element::GreaterBlock), map(greater_block_matcher, Element::GreaterBlock),
@@ -84,6 +87,7 @@ fn _element<'r, 's>(
map(fixed_width_area_matcher, Element::FixedWidthArea), map(fixed_width_area_matcher, Element::FixedWidthArea),
map(horizontal_rule_matcher, Element::HorizontalRule), map(horizontal_rule_matcher, Element::HorizontalRule),
map(latex_environment_matcher, Element::LatexEnvironment), map(latex_environment_matcher, Element::LatexEnvironment),
map(keyword_matcher, Element::Keyword),
))(remaining) ))(remaining)
{ {
the_ok @ Ok(_) => the_ok, the_ok @ Ok(_) => the_ok,
@@ -93,12 +97,12 @@ fn _element<'r, 's>(
the_ok @ Ok(_) => the_ok, the_ok @ Ok(_) => the_ok,
Err(_) => { Err(_) => {
affiliated_keywords.clear(); affiliated_keywords.clear();
map(keyword_matcher, Element::Keyword)(input) map(affiliated_keyword_matcher, Element::Keyword)(input)
} }
} }
} else { } else {
affiliated_keywords.clear(); affiliated_keywords.clear();
map(keyword_matcher, Element::Keyword)(input) map(affiliated_keyword_matcher, Element::Keyword)(input)
} }
} }
}?; }?;

View File

@@ -15,7 +15,8 @@ use crate::error::Res;
use crate::parser::object::Entity; use crate::parser::object::Entity;
use crate::parser::util::get_consumed; use crate::parser::util::get_consumed;
const ENTITIES: [&'static str; 413] = [ // TODO: Make this a user-provided variable corresponding to elisp's org-entities
const ORG_ENTITIES: [&'static str; 413] = [
"Agrave", "Agrave",
"agrave", "agrave",
"Aacute", "Aacute",
@@ -457,8 +458,7 @@ fn name<'r, 's>(
input: OrgSource<'s>, input: OrgSource<'s>,
) -> Res<OrgSource<'s>, OrgSource<'s>> { ) -> Res<OrgSource<'s>, OrgSource<'s>> {
// TODO: This should be defined by org-entities and optionally org-entities-user // TODO: This should be defined by org-entities and optionally org-entities-user
for entity in ENTITIES { for entity in ORG_ENTITIES {
// foo
let result = tag_no_case::<_, _, CustomError<_>>(entity)(input); let result = tag_no_case::<_, _, CustomError<_>>(entity)(input);
match result { match result {
Ok((remaining, ent)) => { Ok((remaining, ent)) => {

View File

@@ -1,6 +1,7 @@
use super::element::Element; use super::element::Element;
use super::lesser_element::TableCell; use super::lesser_element::TableCell;
use super::source::Source; use super::source::Source;
use super::Object;
#[derive(Debug)] #[derive(Debug)]
pub struct PlainList<'s> { pub struct PlainList<'s> {
@@ -13,6 +14,7 @@ pub struct PlainListItem<'s> {
pub source: &'s str, pub source: &'s str,
pub indentation: usize, pub indentation: usize,
pub bullet: &'s str, pub bullet: &'s str,
pub tag: Vec<Object<'s>>,
pub children: Vec<Element<'s>>, pub children: Vec<Element<'s>>,
} }

View File

@@ -2,6 +2,8 @@ use nom::branch::alt;
use nom::bytes::complete::is_not; use nom::bytes::complete::is_not;
use nom::bytes::complete::tag; use nom::bytes::complete::tag;
use nom::bytes::complete::tag_no_case; use nom::bytes::complete::tag_no_case;
use nom::bytes::complete::take_while1;
use nom::character::complete::anychar;
use nom::character::complete::line_ending; use nom::character::complete::line_ending;
use nom::character::complete::space0; use nom::character::complete::space0;
use nom::character::complete::space1; use nom::character::complete::space1;
@@ -9,14 +11,24 @@ use nom::combinator::eof;
use nom::combinator::not; use nom::combinator::not;
use nom::combinator::peek; use nom::combinator::peek;
use nom::combinator::recognize; use nom::combinator::recognize;
use nom::multi::many_till;
use nom::sequence::tuple; use nom::sequence::tuple;
use super::org_source::BracketDepth;
use super::org_source::OrgSource; use super::org_source::OrgSource;
use super::Context; use super::Context;
use crate::error::CustomError;
use crate::error::MyError;
use crate::error::Res; use crate::error::Res;
use crate::parser::util::start_of_line; use crate::parser::util::start_of_line;
use crate::parser::Keyword; use crate::parser::Keyword;
const ORG_ELEMENT_AFFILIATED_KEYWORDS: [&'static str; 13] = [
"caption", "data", "header", "headers", "label", "name", "plot", "resname", "result",
"results", "source", "srcname", "tblname",
];
const ORG_ELEMENT_DUAL_KEYWORDS: [&'static str; 2] = ["caption", "results"];
#[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))] #[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))]
pub fn keyword<'r, 's>( pub fn keyword<'r, 's>(
_context: Context<'r, 's>, _context: Context<'r, 's>,
@@ -41,3 +53,111 @@ pub fn keyword<'r, 's>(
}, },
)) ))
} }
#[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))]
pub fn affiliated_keyword<'r, 's>(
_context: Context<'r, 's>,
input: OrgSource<'s>,
) -> Res<OrgSource<'s>, Keyword<'s>> {
start_of_line(input)?;
// TODO: When key is a member of org-element-parsed-keywords, value can contain the standard set objects, excluding footnote references.
let (remaining, rule) = recognize(tuple((
space0,
tag("#+"),
affiliated_key,
tag(":"),
alt((recognize(tuple((space1, is_not("\r\n")))), space0)),
alt((line_ending, eof)),
)))(input)?;
Ok((
remaining,
Keyword {
source: rule.into(),
},
))
}
#[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))]
fn affiliated_key<'s>(input: OrgSource<'s>) -> Res<OrgSource<'s>, OrgSource<'s>> {
alt((
recognize(tuple((dual_affiliated_key, tag("["), optval, tag("]")))),
plain_affiliated_key,
export_keyword,
))(input)
}
#[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))]
fn plain_affiliated_key<'s>(input: OrgSource<'s>) -> Res<OrgSource<'s>, OrgSource<'s>> {
for keyword in ORG_ELEMENT_AFFILIATED_KEYWORDS {
let result = tag_no_case::<_, _, CustomError<_>>(keyword)(input);
match result {
Ok((remaining, ent)) => {
return Ok((remaining, ent));
}
Err(_) => {}
}
}
Err(nom::Err::Error(CustomError::MyError(MyError(
"NoKeywordKey".into(),
))))
}
#[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))]
fn dual_affiliated_key<'s>(input: OrgSource<'s>) -> Res<OrgSource<'s>, OrgSource<'s>> {
for keyword in ORG_ELEMENT_DUAL_KEYWORDS {
let result = tag_no_case::<_, _, CustomError<_>>(keyword)(input);
match result {
Ok((remaining, ent)) => {
return Ok((remaining, ent));
}
Err(_) => {}
}
}
Err(nom::Err::Error(CustomError::MyError(MyError(
"NoKeywordKey".into(),
))))
}
#[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))]
fn optval<'s>(input: OrgSource<'s>) -> Res<OrgSource<'s>, OrgSource<'s>> {
recognize(many_till(
anychar,
peek(optval_end(input.get_bracket_depth())),
))(input)
}
const fn optval_end(
starting_bracket_depth: BracketDepth,
) -> impl for<'s> Fn(OrgSource<'s>) -> Res<OrgSource<'s>, OrgSource<'s>> {
move |input: OrgSource<'_>| _optval_end(input, starting_bracket_depth)
}
#[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))]
fn _optval_end<'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 opval.
unreachable!("Exceeded optval bracket depth.")
}
if current_depth == 0 {
let close_bracket = tag::<_, _, CustomError<_>>("]")(input);
if close_bracket.is_ok() {
return close_bracket;
}
}
tag("\n")(input)
}
#[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))]
fn export_keyword<'s>(input: OrgSource<'s>) -> Res<OrgSource<'s>, OrgSource<'s>> {
recognize(tuple((
tag_no_case("attr_"),
take_while1(|c: char| c.is_alphanumeric() || "-_".contains(c)),
)))(input)
}

View File

@@ -1,5 +1,6 @@
use nom::bytes::complete::tag; use nom::bytes::complete::tag;
use nom::character::complete::anychar; use nom::character::complete::anychar;
use nom::character::complete::space0;
use nom::combinator::not; use nom::combinator::not;
use nom::combinator::opt; use nom::combinator::opt;
use nom::combinator::peek; use nom::combinator::peek;
@@ -24,6 +25,7 @@ pub fn org_macro<'r, 's>(
let (remaining, macro_name) = org_macro_name(context, remaining)?; let (remaining, macro_name) = org_macro_name(context, remaining)?;
let (remaining, macro_args) = opt(parser_with_context!(org_macro_args)(context))(remaining)?; let (remaining, macro_args) = opt(parser_with_context!(org_macro_args)(context))(remaining)?;
let (remaining, _) = tag("}}}")(remaining)?; let (remaining, _) = tag("}}}")(remaining)?;
let (remaining, _trailing_whitespace) = space0(remaining)?;
let source = get_consumed(input, remaining); let source = get_consumed(input, remaining);
Ok(( Ok((

View File

@@ -7,6 +7,7 @@ use nom::character::complete::one_of;
use nom::combinator::eof; use nom::combinator::eof;
use nom::combinator::peek; use nom::combinator::peek;
use nom::combinator::recognize; use nom::combinator::recognize;
use nom::combinator::verify;
use nom::multi::many_till; use nom::multi::many_till;
use super::org_source::OrgSource; use super::org_source::OrgSource;
@@ -23,6 +24,33 @@ use crate::parser::util::exit_matcher_parser;
use crate::parser::util::get_consumed; use crate::parser::util::get_consumed;
use crate::parser::util::WORD_CONSTITUENT_CHARACTERS; use crate::parser::util::WORD_CONSTITUENT_CHARACTERS;
// TODO: Make this a user-provided variable corresponding to elisp's org-link-parameters
const ORG_LINK_PARAMETERS: [&'static str; 23] = [
"id",
"eww",
"rmail",
"mhe",
"irc",
"info",
"gnus",
"docview",
"bibtex",
"bbdb",
"w3m",
"doi",
"file+sys",
"file+emacs",
"shell",
"news",
"mailto",
"https",
"http",
"ftp",
"help",
"file",
"elisp",
];
#[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))] #[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))]
pub fn plain_link<'r, 's>( pub fn plain_link<'r, 's>(
context: Context<'r, 's>, context: Context<'r, 's>,
@@ -73,36 +101,19 @@ pub fn protocol<'r, 's>(
input: OrgSource<'s>, input: OrgSource<'s>,
) -> Res<OrgSource<'s>, OrgSource<'s>> { ) -> Res<OrgSource<'s>, OrgSource<'s>> {
// TODO: This should be defined by org-link-parameters // TODO: This should be defined by org-link-parameters
let (remaining, proto) = alt(( for link_parameter in ORG_LINK_PARAMETERS {
alt(( let result = tag_no_case::<_, _, CustomError<_>>(link_parameter)(input);
tag_no_case("id"), match result {
tag_no_case("eww"), Ok((remaining, ent)) => {
tag_no_case("rmail"), return Ok((remaining, ent));
tag_no_case("mhe"), }
tag_no_case("irc"), Err(_) => {}
tag_no_case("info"), }
tag_no_case("gnus"), }
tag_no_case("docview"),
tag_no_case("bibtex"), Err(nom::Err::Error(CustomError::MyError(MyError(
tag_no_case("bbdb"), "NoLinkProtocol".into(),
tag_no_case("w3m"), ))))
)),
alt((
tag_no_case("doi"),
tag_no_case("file+sys"),
tag_no_case("file+emacs"),
tag_no_case("shell"),
tag_no_case("news"),
tag_no_case("mailto"),
tag_no_case("https"),
tag_no_case("http"),
tag_no_case("ftp"),
tag_no_case("help"),
tag_no_case("file"),
tag_no_case("elisp"),
)),
))(input)?;
Ok((remaining, proto))
} }
#[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))] #[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))]
@@ -119,7 +130,11 @@ fn path_plain<'r, 's>(
let exit_matcher = parser_with_context!(exit_matcher_parser)(&parser_context); let exit_matcher = parser_with_context!(exit_matcher_parser)(&parser_context);
let (remaining, path) = recognize(many_till(anychar, peek(exit_matcher)))(input)?; let (remaining, path) = recognize(verify(
many_till(anychar, peek(exit_matcher)),
|(children, _exit_contents)| !children.is_empty(),
))(input)?;
Ok((remaining, path)) Ok((remaining, path))
} }
@@ -128,5 +143,10 @@ fn path_plain_end<'r, 's>(
_context: Context<'r, 's>, _context: Context<'r, 's>,
input: OrgSource<'s>, input: OrgSource<'s>,
) -> Res<OrgSource<'s>, OrgSource<'s>> { ) -> Res<OrgSource<'s>, OrgSource<'s>> {
recognize(one_of(" \t\r\n()[]<>"))(input) recognize(many_till(
verify(anychar, |c| {
*c != '/' && (c.is_ascii_punctuation() || c.is_whitespace())
}),
one_of(" \t\r\n()[]<>"),
))(input)
} }

View File

@@ -6,19 +6,24 @@ use nom::character::complete::one_of;
use nom::character::complete::space0; use nom::character::complete::space0;
use nom::character::complete::space1; use nom::character::complete::space1;
use nom::combinator::eof; use nom::combinator::eof;
use nom::combinator::not;
use nom::combinator::opt; use nom::combinator::opt;
use nom::combinator::peek;
use nom::combinator::recognize; use nom::combinator::recognize;
use nom::combinator::verify; use nom::combinator::verify;
use nom::multi::many0;
use nom::multi::many1; use nom::multi::many1;
use nom::multi::many_till; use nom::multi::many_till;
use nom::sequence::tuple; use nom::sequence::tuple;
use super::greater_element::PlainList; use super::greater_element::PlainList;
use super::greater_element::PlainListItem; use super::greater_element::PlainListItem;
use super::object_parser::standard_set_object;
use super::org_source::OrgSource; use super::org_source::OrgSource;
use super::parser_with_context::parser_with_context; use super::parser_with_context::parser_with_context;
use super::util::non_whitespace_character; use super::util::non_whitespace_character;
use super::Context; use super::Context;
use super::Object;
use crate::error::CustomError; use crate::error::CustomError;
use crate::error::MyError; use crate::error::MyError;
use crate::error::Res; use crate::error::Res;
@@ -138,7 +143,6 @@ pub fn plain_list_item<'r, 's>(
Into::<&str>::into(bull) != "*" || indent_level > 0 Into::<&str>::into(bull) != "*" || indent_level > 0
})(remaining)?; })(remaining)?;
// TODO: This isn't taking into account items that immediately line break and then have contents
let maybe_contentless_item: Res<OrgSource<'_>, OrgSource<'_>> = eof(remaining); let maybe_contentless_item: Res<OrgSource<'_>, OrgSource<'_>> = eof(remaining);
match maybe_contentless_item { match maybe_contentless_item {
Ok((rem, _ws)) => { Ok((rem, _ws)) => {
@@ -149,6 +153,7 @@ pub fn plain_list_item<'r, 's>(
source: source.into(), source: source.into(),
indentation: indent_level, indentation: indent_level,
bullet: bull.into(), bullet: bull.into(),
tag: Vec::new(),
children: Vec::new(), children: Vec::new(),
}, },
)); ));
@@ -156,7 +161,12 @@ pub fn plain_list_item<'r, 's>(
Err(_) => {} Err(_) => {}
}; };
let (remaining, _ws) = alt((space1, line_ending))(remaining)?; let (remaining, maybe_tag) = opt(tuple((
space1,
parser_with_context!(item_tag)(context),
tag(" ::"),
)))(remaining)?;
let (remaining, _ws) = item_tag_post_gap(context, remaining)?;
let exit_matcher = plain_list_item_end(indent_level); let exit_matcher = plain_list_item_end(indent_level);
let parser_context = context let parser_context = context
.with_additional_node(ContextElement::ConsumeTrailingWhitespace(true)) .with_additional_node(ContextElement::ConsumeTrailingWhitespace(true))
@@ -167,7 +177,10 @@ pub fn plain_list_item<'r, 's>(
let (remaining, (children, _exit_contents)) = many_till( let (remaining, (children, _exit_contents)) = many_till(
parser_with_context!(element(true))(&parser_context), parser_with_context!(element(true))(&parser_context),
parser_with_context!(exit_matcher_parser)(&parser_context), alt((
peek(recognize(tuple((start_of_line, many0(blank_line), eof)))),
parser_with_context!(exit_matcher_parser)(&parser_context),
)),
)(remaining)?; )(remaining)?;
let (remaining, _trailing_ws) = let (remaining, _trailing_ws) =
@@ -180,6 +193,9 @@ pub fn plain_list_item<'r, 's>(
source: source.into(), source: source.into(),
indentation: indent_level, indentation: indent_level,
bullet: bull.into(), bullet: bull.into(),
tag: maybe_tag
.map(|(_ws, item_tag, _divider)| item_tag)
.unwrap_or(Vec::new()),
children, children,
}, },
)); ));
@@ -262,6 +278,60 @@ fn _line_indented_lte<'r, 's>(
Ok(matched) Ok(matched)
} }
#[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))]
fn item_tag<'r, 's>(
context: Context<'r, 's>,
input: OrgSource<'s>,
) -> Res<OrgSource<'s>, Vec<Object<'s>>> {
let parser_context =
context.with_additional_node(ContextElement::ExitMatcherNode(ExitMatcherNode {
class: ExitClass::Gamma,
exit_matcher: &item_tag_end,
}));
let (remaining, (children, _exit_contents)) = verify(
many_till(
// TODO: Should this be using a different set like the minimal set?
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))
}
#[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))]
fn item_tag_end<'r, 's>(
_context: Context<'r, 's>,
input: OrgSource<'s>,
) -> Res<OrgSource<'s>, OrgSource<'s>> {
recognize(alt((
line_ending,
tag(" :: "),
recognize(tuple((tag(" ::"), alt((line_ending, eof))))),
)))(input)
}
#[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))]
fn item_tag_post_gap<'r, 's>(
context: Context<'r, 's>,
input: OrgSource<'s>,
) -> Res<OrgSource<'s>, OrgSource<'s>> {
verify(
recognize(tuple((
alt((blank_line, space0)),
many_till(
blank_line,
alt((
peek(recognize(not(blank_line))),
peek(recognize(tuple((many0(blank_line), eof)))),
parser_with_context!(exit_matcher_parser)(context),
)),
),
))),
|gap| gap.len() > 0,
)(input)
}
#[cfg(test)] #[cfg(test)]
mod tests { mod tests {
use super::*; use super::*;

View File

@@ -2,13 +2,14 @@ use nom::branch::alt;
use nom::bytes::complete::is_not; use nom::bytes::complete::is_not;
use nom::bytes::complete::tag; use nom::bytes::complete::tag;
use nom::bytes::complete::tag_no_case; use nom::bytes::complete::tag_no_case;
use nom::character::complete::anychar;
use nom::character::complete::line_ending; use nom::character::complete::line_ending;
use nom::character::complete::space0; use nom::character::complete::space0;
use nom::character::complete::space1; use nom::character::complete::space1;
use nom::combinator::eof; use nom::combinator::eof;
use nom::combinator::map;
use nom::combinator::opt; use nom::combinator::opt;
use nom::combinator::recognize; use nom::combinator::recognize;
use nom::combinator::verify;
use nom::multi::many_till; use nom::multi::many_till;
use nom::sequence::tuple; use nom::sequence::tuple;
@@ -23,7 +24,6 @@ use crate::parser::greater_element::PropertyDrawer;
use crate::parser::parser_context::ContextElement; use crate::parser::parser_context::ContextElement;
use crate::parser::parser_context::ExitMatcherNode; use crate::parser::parser_context::ExitMatcherNode;
use crate::parser::parser_with_context::parser_with_context; use crate::parser::parser_with_context::parser_with_context;
use crate::parser::plain_text::plain_text;
use crate::parser::util::exit_matcher_parser; use crate::parser::util::exit_matcher_parser;
use crate::parser::util::get_consumed; use crate::parser::util::get_consumed;
use crate::parser::util::immediate_in_section; use crate::parser::util::immediate_in_section;
@@ -147,11 +147,16 @@ fn node_property_name<'r, 's>(
})); }));
let (remaining, name) = recognize(tuple(( let (remaining, name) = recognize(tuple((
map(parser_with_context!(plain_text)(&parser_context), |pt| { verify(
pt.source many_till(
}), anychar,
parser_with_context!(exit_matcher_parser)(&parser_context),
),
|(children, _exit_contents)| !children.is_empty(),
),
opt(tag("+")), opt(tag("+")),
)))(input)?; )))(input)?;
Ok((remaining, name)) Ok((remaining, name))
} }