Merge branch 'compare_improvements'

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

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,
     }
 }

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/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/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))
 }