Publish version 0.1.3.

This additional exit condition was causing property drawers to parse incorrectly.

Cargo.toml

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

build.rs

@@ -75,6 +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_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_unicode_hearts" => Some("Unicode is coming out of emacs strange."),
         _ => None,
     }
 }

elisp_snippets/README.md

@@ -0,0 +1 @@
+This folder is for snippets of elisp that are useful for development.

elisp_snippets/dump_org_element_affiliated_keywords.el

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

elisp_snippets/dump_org_entities.el

@@ -0,0 +1,5 @@
+(dolist (var org-entities)
+  (when (listp var)
+      (message "\"%s\"," (nth 0 var))
+    )
+  )

org_mode_samples/greater_element/plain_list/description_eof.org

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

org_mode_samples/greater_element/plain_list/description_list.org

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

org_mode_samples/greater_element/property_drawer/properties_with_underscore.org

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

org_mode_samples/lesser_element/keyword/floating_affiliated_keyword.org

@@ -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

org_mode_samples/object/plain_link/empty_links.org

@@ -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

org_mode_samples/object/plain_link/end_with_punctuation.org

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

org_mode_samples/sections_and_headings/empty_section.org

@@ -0,0 +1,9 @@
+* Foo
+
+* Bar
+
+
+
+
+
+* Baz

org_mode_samples/unicode/hearts.org

@@ -0,0 +1 @@
+🧡💛💚💙💜

src/compare/util.rs

@@ -51,7 +51,7 @@ pub fn assert_bounds<'s, S: Source<'s>>(
     );
     let (rust_begin, rust_end) = get_offsets(source, rust);
     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(())
@@ -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
         .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))
+}

src/main.rs

@@ -55,20 +55,21 @@ fn read_stdin_to_string() -> Result<String, Box<dyn std::error::Error>> {
 fn run_compare<P: AsRef<str>>(org_contents: P) -> Result<(), Box<dyn std::error::Error>> {
     let emacs_version = get_emacs_version()?;
     let org_mode_version = get_org_mode_version()?;
+    let org_contents = org_contents.as_ref();
     eprintln!("Using emacs version: {}", emacs_version.trim());
     eprintln!("Using org-mode version: {}", org_mode_version.trim());
-    let (remaining, rust_parsed) = document(org_contents.as_ref()).map_err(|e| e.to_string())?;
-    let org_sexp = emacs_parse_org_document(org_contents.as_ref())?;
+    let (remaining, rust_parsed) = document(org_contents).map_err(|e| e.to_string())?;
+    let org_sexp = emacs_parse_org_document(org_contents)?;
     let (_remaining, parsed_sexp) =
         sexp_with_padding(org_sexp.as_str()).map_err(|e| e.to_string())?;
 
-    println!("{}\n\n\n", org_contents.as_ref());
+    println!("{}\n\n\n", org_contents);
     println!("{}", org_sexp);
     println!("{:#?}", rust_parsed);
 
     // We do the diffing after printing out both parsed forms in case the diffing panics
     let diff_result = compare_document(&parsed_sexp, &rust_parsed)?;
-    diff_result.print()?;
+    diff_result.print(org_contents)?;
 
     if diff_result.is_bad() {
         Err("Diff results do not match.")?;
@@ -85,7 +86,7 @@ fn run_compare<P: AsRef<str>>(org_contents: P) -> Result<(), Box<dyn std::error:
     eprintln!(
         "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);
     Ok(())
 }

src/parser/document.rs

@@ -283,10 +283,21 @@ fn _heading<'r, 's>(
         headline(context, input, parent_stars)?;
     let section_matcher = parser_with_context!(section)(context);
     let heading_matcher = parser_with_context!(heading(star_count))(context);
-    let (remaining, children) = many0(alt((
-        map(heading_matcher, DocumentElement::Heading),
-        map(section_matcher, DocumentElement::Section),
-    )))(remaining)?;
+    let (remaining, maybe_section) =
+        opt(map(section_matcher, DocumentElement::Section))(remaining)?;
+    let (remaining, mut children) =
+        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);
     Ok((
         remaining,

src/parser/element_parser.rs

@@ -12,6 +12,7 @@ use super::fixed_width_area::fixed_width_area;
 use super::footnote_definition::footnote_definition;
 use super::greater_block::greater_block;
 use super::horizontal_rule::horizontal_rule;
+use super::keyword::affiliated_keyword;
 use super::keyword::keyword;
 use super::latex_environment::latex_environment;
 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 horizontal_rule_matcher = parser_with_context!(horizontal_rule)(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 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((
         map(plain_list_matcher, Element::PlainList),
         map(greater_block_matcher, Element::GreaterBlock),
@@ -84,6 +87,7 @@ fn _element<'r, 's>(
         map(fixed_width_area_matcher, Element::FixedWidthArea),
         map(horizontal_rule_matcher, Element::HorizontalRule),
         map(latex_environment_matcher, Element::LatexEnvironment),
+        map(keyword_matcher, Element::Keyword),
     ))(remaining)
     {
         the_ok @ Ok(_) => the_ok,
@@ -93,12 +97,12 @@ fn _element<'r, 's>(
                     the_ok @ Ok(_) => the_ok,
                     Err(_) => {
                         affiliated_keywords.clear();
-                        map(keyword_matcher, Element::Keyword)(input)
+                        map(affiliated_keyword_matcher, Element::Keyword)(input)
                     }
                 }
             } else {
                 affiliated_keywords.clear();
-                map(keyword_matcher, Element::Keyword)(input)
+                map(affiliated_keyword_matcher, Element::Keyword)(input)
             }
         }
     }?;

src/parser/entity.rs

@@ -9,11 +9,429 @@ use nom::combinator::recognize;
 
 use super::org_source::OrgSource;
 use super::Context;
+use crate::error::CustomError;
+use crate::error::MyError;
 use crate::error::Res;
 use crate::parser::object::Entity;
-use crate::parser::parser_with_context::parser_with_context;
 use crate::parser::util::get_consumed;
 
+// TODO: Make this a user-provided variable corresponding to elisp's org-entities
+const ORG_ENTITIES: [&'static str; 413] = [
+    "Agrave",
+    "agrave",
+    "Aacute",
+    "aacute",
+    "Acirc",
+    "acirc",
+    "Amacr",
+    "amacr",
+    "Atilde",
+    "atilde",
+    "Auml",
+    "auml",
+    "Aring",
+    "AA",
+    "aring",
+    "AElig",
+    "aelig",
+    "Ccedil",
+    "ccedil",
+    "Egrave",
+    "egrave",
+    "Eacute",
+    "eacute",
+    "Ecirc",
+    "ecirc",
+    "Euml",
+    "euml",
+    "Igrave",
+    "igrave",
+    "Iacute",
+    "iacute",
+    "Idot",
+    "inodot",
+    "Icirc",
+    "icirc",
+    "Iuml",
+    "iuml",
+    "Ntilde",
+    "ntilde",
+    "Ograve",
+    "ograve",
+    "Oacute",
+    "oacute",
+    "Ocirc",
+    "ocirc",
+    "Otilde",
+    "otilde",
+    "Ouml",
+    "ouml",
+    "Oslash",
+    "oslash",
+    "OElig",
+    "oelig",
+    "Scaron",
+    "scaron",
+    "szlig",
+    "Ugrave",
+    "ugrave",
+    "Uacute",
+    "uacute",
+    "Ucirc",
+    "ucirc",
+    "Uuml",
+    "uuml",
+    "Yacute",
+    "yacute",
+    "Yuml",
+    "yuml",
+    "fnof",
+    "real",
+    "image",
+    "weierp",
+    "ell",
+    "imath",
+    "jmath",
+    "Alpha",
+    "alpha",
+    "Beta",
+    "beta",
+    "Gamma",
+    "gamma",
+    "Delta",
+    "delta",
+    "Epsilon",
+    "epsilon",
+    "varepsilon",
+    "Zeta",
+    "zeta",
+    "Eta",
+    "eta",
+    "Theta",
+    "theta",
+    "thetasym",
+    "vartheta",
+    "Iota",
+    "iota",
+    "Kappa",
+    "kappa",
+    "Lambda",
+    "lambda",
+    "Mu",
+    "mu",
+    "nu",
+    "Nu",
+    "Xi",
+    "xi",
+    "Omicron",
+    "omicron",
+    "Pi",
+    "pi",
+    "Rho",
+    "rho",
+    "Sigma",
+    "sigma",
+    "sigmaf",
+    "varsigma",
+    "Tau",
+    "Upsilon",
+    "upsih",
+    "upsilon",
+    "Phi",
+    "phi",
+    "varphi",
+    "Chi",
+    "chi",
+    "acutex",
+    "Psi",
+    "psi",
+    "tau",
+    "Omega",
+    "omega",
+    "piv",
+    "varpi",
+    "partial",
+    "alefsym",
+    "aleph",
+    "gimel",
+    "beth",
+    "dalet",
+    "ETH",
+    "eth",
+    "THORN",
+    "thorn",
+    "dots",
+    "cdots",
+    "hellip",
+    "middot",
+    "iexcl",
+    "iquest",
+    "shy",
+    "ndash",
+    "mdash",
+    "quot",
+    "acute",
+    "ldquo",
+    "rdquo",
+    "bdquo",
+    "lsquo",
+    "rsquo",
+    "sbquo",
+    "laquo",
+    "raquo",
+    "lsaquo",
+    "rsaquo",
+    "circ",
+    "vert",
+    "vbar",
+    "brvbar",
+    "S",
+    "sect",
+    "amp",
+    "lt",
+    "gt",
+    "tilde",
+    "slash",
+    "plus",
+    "under",
+    "equal",
+    "asciicirc",
+    "dagger",
+    "dag",
+    "Dagger",
+    "ddag",
+    "nbsp",
+    "ensp",
+    "emsp",
+    "thinsp",
+    "curren",
+    "cent",
+    "pound",
+    "yen",
+    "euro",
+    "EUR",
+    "dollar",
+    "USD",
+    "copy",
+    "reg",
+    "trade",
+    "minus",
+    "pm",
+    "plusmn",
+    "times",
+    "frasl",
+    "colon",
+    "div",
+    "frac12",
+    "frac14",
+    "frac34",
+    "permil",
+    "sup1",
+    "sup2",
+    "sup3",
+    "radic",
+    "sum",
+    "prod",
+    "micro",
+    "macr",
+    "deg",
+    "prime",
+    "Prime",
+    "infin",
+    "infty",
+    "prop",
+    "propto",
+    "not",
+    "neg",
+    "land",
+    "wedge",
+    "lor",
+    "vee",
+    "cap",
+    "cup",
+    "smile",
+    "frown",
+    "int",
+    "therefore",
+    "there4",
+    "because",
+    "sim",
+    "cong",
+    "simeq",
+    "asymp",
+    "approx",
+    "ne",
+    "neq",
+    "equiv",
+    "triangleq",
+    "le",
+    "leq",
+    "ge",
+    "geq",
+    "lessgtr",
+    "lesseqgtr",
+    "ll",
+    "Ll",
+    "lll",
+    "gg",
+    "Gg",
+    "ggg",
+    "prec",
+    "preceq",
+    "preccurlyeq",
+    "succ",
+    "succeq",
+    "succcurlyeq",
+    "sub",
+    "subset",
+    "sup",
+    "supset",
+    "nsub",
+    "sube",
+    "nsup",
+    "supe",
+    "setminus",
+    "forall",
+    "exist",
+    "exists",
+    "nexist",
+    "nexists",
+    "empty",
+    "emptyset",
+    "isin",
+    "in",
+    "notin",
+    "ni",
+    "nabla",
+    "ang",
+    "angle",
+    "perp",
+    "parallel",
+    "sdot",
+    "cdot",
+    "lceil",
+    "rceil",
+    "lfloor",
+    "rfloor",
+    "lang",
+    "rang",
+    "langle",
+    "rangle",
+    "hbar",
+    "mho",
+    "larr",
+    "leftarrow",
+    "gets",
+    "lArr",
+    "Leftarrow",
+    "uarr",
+    "uparrow",
+    "uArr",
+    "Uparrow",
+    "rarr",
+    "to",
+    "rightarrow",
+    "rArr",
+    "Rightarrow",
+    "darr",
+    "downarrow",
+    "dArr",
+    "Downarrow",
+    "harr",
+    "leftrightarrow",
+    "hArr",
+    "Leftrightarrow",
+    "crarr",
+    "hookleftarrow",
+    "arccos",
+    "arcsin",
+    "arctan",
+    "arg",
+    "cos",
+    "cosh",
+    "cot",
+    "coth",
+    "csc",
+    "deg",
+    "det",
+    "dim",
+    "exp",
+    "gcd",
+    "hom",
+    "inf",
+    "ker",
+    "lg",
+    "lim",
+    "liminf",
+    "limsup",
+    "ln",
+    "log",
+    "max",
+    "min",
+    "Pr",
+    "sec",
+    "sin",
+    "sinh",
+    "sup",
+    "tan",
+    "tanh",
+    "bull",
+    "bullet",
+    "star",
+    "lowast",
+    "ast",
+    "odot",
+    "oplus",
+    "otimes",
+    "check",
+    "checkmark",
+    "para",
+    "ordf",
+    "ordm",
+    "cedil",
+    "oline",
+    "uml",
+    "zwnj",
+    "zwj",
+    "lrm",
+    "rlm",
+    "smiley",
+    "blacksmile",
+    "sad",
+    "frowny",
+    "clubs",
+    "clubsuit",
+    "spades",
+    "spadesuit",
+    "hearts",
+    "heartsuit",
+    "diams",
+    "diamondsuit",
+    "diamond",
+    "Diamond",
+    "loz",
+    "_ ",
+    "_  ",
+    "_   ",
+    "_    ",
+    "_     ",
+    "_      ",
+    "_       ",
+    "_        ",
+    "_         ",
+    "_          ",
+    "_           ",
+    "_            ",
+    "_             ",
+    "_              ",
+    "_               ",
+    "_                ",
+    "_                 ",
+    "_                  ",
+    "_                   ",
+    "_                    ",
+];
+
 #[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))]
 pub fn entity<'r, 's>(
     context: Context<'r, 's>,
@@ -21,10 +439,7 @@ pub fn entity<'r, 's>(
 ) -> Res<OrgSource<'s>, Entity<'s>> {
     let (remaining, _) = tag("\\")(input)?;
     let (remaining, entity_name) = name(context, remaining)?;
-    let (remaining, _) = alt((
-        tag("{}"),
-        peek(recognize(parser_with_context!(entity_end)(context))),
-    ))(remaining)?;
+    let (remaining, _) = alt((tag("{}"), peek(recognize(entity_end))))(remaining)?;
     let (remaining, _) = space0(remaining)?;
 
     let source = get_consumed(input, remaining);
@@ -43,20 +458,23 @@ fn name<'r, 's>(
     input: OrgSource<'s>,
 ) -> Res<OrgSource<'s>, OrgSource<'s>> {
     // TODO: This should be defined by org-entities and optionally org-entities-user
+    for entity in ORG_ENTITIES {
+        let result = tag_no_case::<_, _, CustomError<_>>(entity)(input);
+        match result {
+            Ok((remaining, ent)) => {
+                return Ok((remaining, ent));
+            }
+            Err(_) => {}
+        }
+    }
 
-    // TODO: Add the rest of the entities, this is a very incomplete list
-    let (remaining, proto) = alt((alt((
-        tag_no_case("delta"),
-        tag_no_case("pi"),
-        tag_no_case("ast"),
-        tag_no_case("lt"),
-        tag_no_case("gt"),
-    )),))(input)?;
-    Ok((remaining, proto))
+    Err(nom::Err::Error(CustomError::MyError(MyError(
+        "NoEntity".into(),
+    ))))
 }
 
 #[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))]
-fn entity_end<'r, 's>(_context: Context<'r, 's>, input: OrgSource<'s>) -> Res<OrgSource<'s>, ()> {
+fn entity_end<'s>(input: OrgSource<'s>) -> Res<OrgSource<'s>, ()> {
     let (remaining, _) = alt((eof, recognize(satisfy(|c| !c.is_alphabetic()))))(input)?;
 
     Ok((remaining, ()))

src/parser/greater_element.rs

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

src/parser/keyword.rs

@@ -2,6 +2,8 @@ use nom::branch::alt;
 use nom::bytes::complete::is_not;
 use nom::bytes::complete::tag;
 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::space0;
 use nom::character::complete::space1;
@@ -9,14 +11,24 @@ use nom::combinator::eof;
 use nom::combinator::not;
 use nom::combinator::peek;
 use nom::combinator::recognize;
+use nom::multi::many_till;
 use nom::sequence::tuple;
 
+use super::org_source::BracketDepth;
 use super::org_source::OrgSource;
 use super::Context;
+use crate::error::CustomError;
+use crate::error::MyError;
 use crate::error::Res;
 use crate::parser::util::start_of_line;
 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"))]
 pub fn keyword<'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)
+}

src/parser/object.rs

@@ -374,3 +374,9 @@ impl<'s> Source<'s> for Timestamp<'s> {
         self.source
     }
 }
+
+impl<'s> Source<'s> for PlainText<'s> {
+    fn get_source(&'s self) -> &'s str {
+        self.source
+    }
+}

src/parser/org_macro.rs

@@ -1,5 +1,6 @@
 use nom::bytes::complete::tag;
 use nom::character::complete::anychar;
+use nom::character::complete::space0;
 use nom::combinator::not;
 use nom::combinator::opt;
 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_args) = opt(parser_with_context!(org_macro_args)(context))(remaining)?;
     let (remaining, _) = tag("}}}")(remaining)?;
+    let (remaining, _trailing_whitespace) = space0(remaining)?;
 
     let source = get_consumed(input, remaining);
     Ok((

src/parser/plain_link.rs

@@ -7,6 +7,7 @@ use nom::character::complete::one_of;
 use nom::combinator::eof;
 use nom::combinator::peek;
 use nom::combinator::recognize;
+use nom::combinator::verify;
 use nom::multi::many_till;
 
 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::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"))]
 pub fn plain_link<'r, 's>(
     context: Context<'r, 's>,
@@ -73,36 +101,19 @@ pub fn protocol<'r, 's>(
     input: OrgSource<'s>,
 ) -> Res<OrgSource<'s>, OrgSource<'s>> {
     // TODO: This should be defined by org-link-parameters
-    let (remaining, proto) = alt((
-        alt((
-            tag_no_case("id"),
-            tag_no_case("eww"),
-            tag_no_case("rmail"),
-            tag_no_case("mhe"),
-            tag_no_case("irc"),
-            tag_no_case("info"),
-            tag_no_case("gnus"),
-            tag_no_case("docview"),
-            tag_no_case("bibtex"),
-            tag_no_case("bbdb"),
-            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))
+    for link_parameter in ORG_LINK_PARAMETERS {
+        let result = tag_no_case::<_, _, CustomError<_>>(link_parameter)(input);
+        match result {
+            Ok((remaining, ent)) => {
+                return Ok((remaining, ent));
+            }
+            Err(_) => {}
+        }
+    }
+
+    Err(nom::Err::Error(CustomError::MyError(MyError(
+        "NoLinkProtocol".into(),
+    ))))
 }
 
 #[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 (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))
 }
 
@@ -128,5 +143,10 @@ fn path_plain_end<'r, 's>(
     _context: Context<'r, 's>,
     input: 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)
 }

src/parser/plain_list.rs

@@ -6,19 +6,24 @@ use nom::character::complete::one_of;
 use nom::character::complete::space0;
 use nom::character::complete::space1;
 use nom::combinator::eof;
+use nom::combinator::not;
 use nom::combinator::opt;
+use nom::combinator::peek;
 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::greater_element::PlainList;
 use super::greater_element::PlainListItem;
+use super::object_parser::standard_set_object;
 use super::org_source::OrgSource;
 use super::parser_with_context::parser_with_context;
 use super::util::non_whitespace_character;
 use super::Context;
+use super::Object;
 use crate::error::CustomError;
 use crate::error::MyError;
 use crate::error::Res;
@@ -138,7 +143,6 @@ pub fn plain_list_item<'r, 's>(
         Into::<&str>::into(bull) != "*" || indent_level > 0
     })(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);
     match maybe_contentless_item {
         Ok((rem, _ws)) => {
@@ -149,6 +153,7 @@ pub fn plain_list_item<'r, 's>(
                     source: source.into(),
                     indentation: indent_level,
                     bullet: bull.into(),
+                    tag: Vec::new(),
                     children: Vec::new(),
                 },
             ));
@@ -156,7 +161,12 @@ pub fn plain_list_item<'r, 's>(
         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 parser_context = context
         .with_additional_node(ContextElement::ConsumeTrailingWhitespace(true))
@@ -167,7 +177,10 @@ pub fn plain_list_item<'r, 's>(
 
     let (remaining, (children, _exit_contents)) = many_till(
         parser_with_context!(element(true))(&parser_context),
+        alt((
+            peek(recognize(tuple((start_of_line, many0(blank_line), eof)))),
             parser_with_context!(exit_matcher_parser)(&parser_context),
+        )),
     )(remaining)?;
 
     let (remaining, _trailing_ws) =
@@ -180,6 +193,9 @@ pub fn plain_list_item<'r, 's>(
             source: source.into(),
             indentation: indent_level,
             bullet: bull.into(),
+            tag: maybe_tag
+                .map(|(_ws, item_tag, _divider)| item_tag)
+                .unwrap_or(Vec::new()),
             children,
         },
     ));
@@ -262,6 +278,60 @@ fn _line_indented_lte<'r, 's>(
     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)]
 mod tests {
     use super::*;

src/parser/property_drawer.rs

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

tests/test_template

@@ -11,7 +11,7 @@ fn {name}() {{
     let diff_result =
         compare_document(&parsed_sexp, &rust_parsed).expect("Compare parsed documents.");
     diff_result
-        .print()
+        .print(org_contents.as_str())
         .expect("Print document parse tree diff.");
     assert!(!diff_result.is_bad());
     assert_eq!(remaining, "");