diff --git a/org_mode_samples/lesser_block/export_with_no_data.org b/org_mode_samples/lesser_block/export_with_no_data.org new file mode 100644 index 0000000..db2940e --- /dev/null +++ b/org_mode_samples/lesser_block/export_with_no_data.org @@ -0,0 +1,3 @@ +#+begin_export +This would be LaTeX code. +#+end_export diff --git a/org_mode_samples/lesser_block/export_with_two_words.org b/org_mode_samples/lesser_block/export_with_two_words.org new file mode 100644 index 0000000..661f739 --- /dev/null +++ b/org_mode_samples/lesser_block/export_with_two_words.org @@ -0,0 +1,3 @@ +#+begin_export latex html +This would be LaTeX code. +#+end_export diff --git a/org_mode_samples/lesser_block/simple.org b/org_mode_samples/lesser_block/simple.org new file mode 100644 index 0000000..d9ef763 --- /dev/null +++ b/org_mode_samples/lesser_block/simple.org @@ -0,0 +1,19 @@ +#+begin_comment +This is a comment. +#+end_comment + +#+begin_example +This is an example. +#+end_example + +#+begin_export latex +This would be LaTeX code. +#+end_export + +#+begin_src sh + echo "this is a source block." +#+end_src + +#+begin_verse +This is a verse block. +#+end_verse diff --git a/org_mode_samples/lesser_block/src_with_no_data.org b/org_mode_samples/lesser_block/src_with_no_data.org new file mode 100644 index 0000000..a6d55b0 --- /dev/null +++ b/org_mode_samples/lesser_block/src_with_no_data.org @@ -0,0 +1,3 @@ +#+begin_src + echo "this is a source block." +#+end_src diff --git a/src/compare/diff.rs b/src/compare/diff.rs index 11975d2..d471e02 100644 --- a/src/compare/diff.rs +++ b/src/compare/diff.rs @@ -2,10 +2,13 @@ use super::sexp::Token; use super::util::assert_bounds; use super::util::assert_name; use crate::parser::Comment; +use crate::parser::CommentBlock; use crate::parser::Document; use crate::parser::DocumentElement; use crate::parser::Drawer; use crate::parser::Element; +use crate::parser::ExampleBlock; +use crate::parser::ExportBlock; use crate::parser::FootnoteDefinition; use crate::parser::GreaterBlock; use crate::parser::Heading; @@ -14,9 +17,11 @@ use crate::parser::PlainList; use crate::parser::PlainListItem; use crate::parser::PropertyDrawer; use crate::parser::Section; +use crate::parser::SrcBlock; use crate::parser::Table; use crate::parser::TableCell; use crate::parser::TableRow; +use crate::parser::VerseBlock; use crate::DynamicBlock; #[derive(Debug)] @@ -202,6 +207,11 @@ fn compare_element<'s>( Element::Drawer(obj) => compare_drawer(source, emacs, obj), Element::PropertyDrawer(obj) => compare_property_drawer(source, emacs, obj), Element::Table(obj) => compare_table(source, emacs, obj), + Element::VerseBlock(obj) => compare_verse_block(source, emacs, obj), + Element::CommentBlock(obj) => compare_comment_block(source, emacs, obj), + Element::ExampleBlock(obj) => compare_example_block(source, emacs, obj), + Element::ExportBlock(obj) => compare_export_block(source, emacs, obj), + Element::SrcBlock(obj) => compare_src_block(source, emacs, obj), } } @@ -548,3 +558,122 @@ fn compare_table_cell<'s>( children: child_status, }) } + +fn compare_verse_block<'s>( + source: &'s str, + emacs: &'s Token<'s>, + rust: &'s VerseBlock<'s>, +) -> Result> { + let children = emacs.as_list()?; + let mut child_status = Vec::new(); + let mut this_status = DiffStatus::Good; + let emacs_name = "verse-block"; + if assert_name(emacs, emacs_name).is_err() { + this_status = DiffStatus::Bad; + } + + if assert_bounds(source, emacs, rust).is_err() { + this_status = DiffStatus::Bad; + } + + for (emacs_child, rust_child) in children.iter().skip(2).zip(rust.children.iter()) {} + + Ok(DiffResult { + status: this_status, + name: emacs_name.to_owned(), + message: None, + children: child_status, + }) +} + +fn compare_comment_block<'s>( + source: &'s str, + emacs: &'s Token<'s>, + rust: &'s CommentBlock<'s>, +) -> Result> { + let mut this_status = DiffStatus::Good; + let emacs_name = "comment-block"; + if assert_name(emacs, emacs_name).is_err() { + this_status = DiffStatus::Bad; + } + + if assert_bounds(source, emacs, rust).is_err() { + this_status = DiffStatus::Bad; + } + + Ok(DiffResult { + status: this_status, + name: emacs_name.to_owned(), + message: None, + children: Vec::new(), + }) +} + +fn compare_example_block<'s>( + source: &'s str, + emacs: &'s Token<'s>, + rust: &'s ExampleBlock<'s>, +) -> Result> { + let mut this_status = DiffStatus::Good; + let emacs_name = "example-block"; + if assert_name(emacs, emacs_name).is_err() { + this_status = DiffStatus::Bad; + } + + if assert_bounds(source, emacs, rust).is_err() { + this_status = DiffStatus::Bad; + } + + Ok(DiffResult { + status: this_status, + name: emacs_name.to_owned(), + message: None, + children: Vec::new(), + }) +} + +fn compare_export_block<'s>( + source: &'s str, + emacs: &'s Token<'s>, + rust: &'s ExportBlock<'s>, +) -> Result> { + let mut this_status = DiffStatus::Good; + let emacs_name = "export-block"; + if assert_name(emacs, emacs_name).is_err() { + this_status = DiffStatus::Bad; + } + + if assert_bounds(source, emacs, rust).is_err() { + this_status = DiffStatus::Bad; + } + + Ok(DiffResult { + status: this_status, + name: emacs_name.to_owned(), + message: None, + children: Vec::new(), + }) +} + +fn compare_src_block<'s>( + source: &'s str, + emacs: &'s Token<'s>, + rust: &'s SrcBlock<'s>, +) -> Result> { + let mut this_status = DiffStatus::Good; + let emacs_name = "src-block"; + if assert_name(emacs, emacs_name).is_err() { + this_status = DiffStatus::Bad; + } + + if assert_bounds(source, emacs, rust).is_err() { + this_status = DiffStatus::Bad; + } + + Ok(DiffResult { + status: this_status, + name: emacs_name.to_owned(), + message: None, + children: Vec::new(), + }) +} diff --git a/src/parser/element.rs b/src/parser/element.rs index ea1f2b1..dfc8663 100644 --- a/src/parser/element.rs +++ b/src/parser/element.rs @@ -5,7 +5,12 @@ use super::greater_element::PlainList; use super::greater_element::PropertyDrawer; use super::greater_element::Table; use super::lesser_element::Comment; +use super::lesser_element::CommentBlock; +use super::lesser_element::ExampleBlock; +use super::lesser_element::ExportBlock; use super::lesser_element::Paragraph; +use super::lesser_element::SrcBlock; +use super::lesser_element::VerseBlock; use super::source::Source; use super::Drawer; @@ -20,6 +25,11 @@ pub enum Element<'s> { Drawer(Drawer<'s>), PropertyDrawer(PropertyDrawer<'s>), Table(Table<'s>), + VerseBlock(VerseBlock<'s>), + CommentBlock(CommentBlock<'s>), + ExampleBlock(ExampleBlock<'s>), + ExportBlock(ExportBlock<'s>), + SrcBlock(SrcBlock<'s>), } impl<'s> Source<'s> for Element<'s> { @@ -34,6 +44,11 @@ impl<'s> Source<'s> for Element<'s> { Element::Drawer(obj) => obj.source, Element::PropertyDrawer(obj) => obj.source, Element::Table(obj) => obj.source, + Element::VerseBlock(obj) => obj.source, + Element::CommentBlock(obj) => obj.source, + Element::ExampleBlock(obj) => obj.source, + Element::ExportBlock(obj) => obj.source, + Element::SrcBlock(obj) => obj.source, } } } diff --git a/src/parser/element_parser.rs b/src/parser/element_parser.rs index 7a6743a..1c865e7 100644 --- a/src/parser/element_parser.rs +++ b/src/parser/element_parser.rs @@ -5,6 +5,11 @@ use super::element::Element; use super::error::Res; use super::footnote_definition::footnote_definition; use super::greater_block::greater_block; +use super::lesser_block::comment_block; +use super::lesser_block::example_block; +use super::lesser_block::export_block; +use super::lesser_block::src_block; +use super::lesser_block::verse_block; use super::paragraph::paragraph; use super::plain_list::plain_list; use super::Context; @@ -35,6 +40,11 @@ pub fn non_paragraph_element<'r, 's>( let comment_matcher = parser_with_context!(comment)(context); let drawer_matcher = parser_with_context!(drawer)(context); let table_matcher = parser_with_context!(org_mode_table)(context); + let verse_block_matcher = parser_with_context!(verse_block)(context); + let comment_block_matcher = parser_with_context!(comment_block)(context); + let example_block_matcher = parser_with_context!(example_block)(context); + let export_block_matcher = parser_with_context!(export_block)(context); + let src_block_matcher = parser_with_context!(src_block)(context); alt(( map(plain_list_matcher, Element::PlainList), map(greater_block_matcher, Element::GreaterBlock), @@ -43,5 +53,10 @@ pub fn non_paragraph_element<'r, 's>( map(comment_matcher, Element::Comment), map(drawer_matcher, Element::Drawer), map(table_matcher, Element::Table), + map(verse_block_matcher, Element::VerseBlock), + map(comment_block_matcher, Element::CommentBlock), + map(example_block_matcher, Element::ExampleBlock), + map(export_block_matcher, Element::ExportBlock), + map(src_block_matcher, Element::SrcBlock), ))(input) } diff --git a/src/parser/greater_block.rs b/src/parser/greater_block.rs index 73b1de4..f22dd4b 100644 --- a/src/parser/greater_block.rs +++ b/src/parser/greater_block.rs @@ -37,7 +37,6 @@ pub fn greater_block<'r, 's>( // TODO: Do I need to differentiate between different greater block types. start_of_line(context, input)?; let (remaining, _leading_whitespace) = space0(input)?; - // TODO: Not handling indentation before start of block let (remaining, (_begin, name)) = tuple(( tag_no_case("#+begin_"), verify(name, |name: &str| match name.to_lowercase().as_str() { diff --git a/src/parser/lesser_block.rs b/src/parser/lesser_block.rs new file mode 100644 index 0000000..7db6420 --- /dev/null +++ b/src/parser/lesser_block.rs @@ -0,0 +1,293 @@ +use nom::branch::alt; +use nom::bytes::complete::is_not; +use nom::bytes::complete::tag_no_case; +use nom::character::complete::line_ending; +use nom::character::complete::space0; +use nom::character::complete::space1; +use nom::combinator::consumed; +use nom::combinator::eof; +use nom::combinator::map; +use nom::combinator::opt; +use nom::combinator::verify; +use nom::multi::many_till; +use nom::sequence::tuple; + +use super::error::Res; +use super::Context; +use crate::parser::exiting::ExitClass; +use crate::parser::lesser_element::CommentBlock; +use crate::parser::lesser_element::ExampleBlock; +use crate::parser::lesser_element::ExportBlock; +use crate::parser::lesser_element::SrcBlock; +use crate::parser::lesser_element::VerseBlock; +use crate::parser::object::Object; +use crate::parser::object::PlainText; +use crate::parser::object_parser::standard_set_object; +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::blank_line; +use crate::parser::util::exit_matcher_parser; +use crate::parser::util::get_consumed; +use crate::parser::util::maybe_consume_trailing_whitespace_if_not_exiting; +use crate::parser::util::start_of_line; + +#[tracing::instrument(ret, level = "debug")] +pub fn verse_block<'r, 's>( + context: Context<'r, 's>, + input: &'s str, +) -> Res<&'s str, VerseBlock<'s>> { + let (remaining, name) = lesser_block_begin("verse")(context, input)?; + let (remaining, parameters) = opt(tuple((space1, data)))(remaining)?; + let (remaining, _nl) = line_ending(remaining)?; + let lesser_block_end_specialized = lesser_block_end("verse"); + let parser_context = context + .with_additional_node(ContextElement::ConsumeTrailingWhitespace(true)) + .with_additional_node(ContextElement::Context("lesser block")) + .with_additional_node(ContextElement::ExitMatcherNode(ExitMatcherNode { + class: ExitClass::Beta, + exit_matcher: &lesser_block_end_specialized, + })); + let parameters = match parameters { + Some((_ws, parameters)) => Some(parameters), + None => None, + }; + + let object_matcher = parser_with_context!(standard_set_object)(&parser_context); + let exit_matcher = parser_with_context!(exit_matcher_parser)(&parser_context); + // Check for a completely empty block + let (remaining, children) = match consumed(many_till(blank_line, exit_matcher))(remaining) { + Ok((remaining, (whitespace, (_children, _exit_contents)))) => ( + remaining, + vec![Object::PlainText(PlainText { source: whitespace })], + ), + Err(_) => { + let (remaining, (children, _exit_contents)) = + many_till(object_matcher, exit_matcher)(remaining)?; + (remaining, children) + } + }; + let (remaining, _end) = lesser_block_end_specialized(&parser_context, remaining)?; + + let (remaining, _trailing_ws) = + maybe_consume_trailing_whitespace_if_not_exiting(context, remaining)?; + + let source = get_consumed(input, remaining); + Ok(( + remaining, + VerseBlock { + source, + name, + data: parameters, + children, + }, + )) +} + +#[tracing::instrument(ret, level = "debug")] +pub fn comment_block<'r, 's>( + context: Context<'r, 's>, + input: &'s str, +) -> Res<&'s str, CommentBlock<'s>> { + let (remaining, name) = lesser_block_begin("comment")(context, input)?; + let (remaining, parameters) = opt(tuple((space1, data)))(remaining)?; + let (remaining, _nl) = line_ending(remaining)?; + let lesser_block_end_specialized = lesser_block_end("comment"); + let parser_context = context + .with_additional_node(ContextElement::ConsumeTrailingWhitespace(true)) + .with_additional_node(ContextElement::Context("lesser block")) + .with_additional_node(ContextElement::ExitMatcherNode(ExitMatcherNode { + class: ExitClass::Beta, + exit_matcher: &lesser_block_end_specialized, + })); + let parameters = match parameters { + Some((_ws, parameters)) => Some(parameters), + None => None, + }; + + let (remaining, contents) = map(parser_with_context!(plain_text)(&parser_context), |obj| { + obj.source + })(remaining)?; + let (remaining, _end) = lesser_block_end_specialized(&parser_context, remaining)?; + + let (remaining, _trailing_ws) = + maybe_consume_trailing_whitespace_if_not_exiting(context, remaining)?; + + let source = get_consumed(input, remaining); + Ok(( + remaining, + CommentBlock { + source, + name, + data: parameters, + contents, + }, + )) +} + +#[tracing::instrument(ret, level = "debug")] +pub fn example_block<'r, 's>( + context: Context<'r, 's>, + input: &'s str, +) -> Res<&'s str, ExampleBlock<'s>> { + let (remaining, name) = lesser_block_begin("example")(context, input)?; + let (remaining, parameters) = opt(tuple((space1, data)))(remaining)?; + let (remaining, _nl) = line_ending(remaining)?; + let lesser_block_end_specialized = lesser_block_end("example"); + let parser_context = context + .with_additional_node(ContextElement::ConsumeTrailingWhitespace(true)) + .with_additional_node(ContextElement::Context("lesser block")) + .with_additional_node(ContextElement::ExitMatcherNode(ExitMatcherNode { + class: ExitClass::Beta, + exit_matcher: &lesser_block_end_specialized, + })); + let parameters = match parameters { + Some((_ws, parameters)) => Some(parameters), + None => None, + }; + + let (remaining, contents) = map(parser_with_context!(plain_text)(&parser_context), |obj| { + obj.source + })(remaining)?; + let (remaining, _end) = lesser_block_end_specialized(&parser_context, remaining)?; + + let (remaining, _trailing_ws) = + maybe_consume_trailing_whitespace_if_not_exiting(context, remaining)?; + + let source = get_consumed(input, remaining); + Ok(( + remaining, + ExampleBlock { + source, + name, + data: parameters, + contents, + }, + )) +} + +#[tracing::instrument(ret, level = "debug")] +pub fn export_block<'r, 's>( + context: Context<'r, 's>, + input: &'s str, +) -> Res<&'s str, ExportBlock<'s>> { + let (remaining, name) = lesser_block_begin("export")(context, input)?; + // https://orgmode.org/worg/org-syntax.html#Blocks claims that export blocks must have a single word for data but testing shows no data and multi-word data still parses as an export block. + let (remaining, parameters) = opt(tuple((space1, data)))(remaining)?; + let (remaining, _nl) = line_ending(remaining)?; + let lesser_block_end_specialized = lesser_block_end("export"); + let parser_context = context + .with_additional_node(ContextElement::ConsumeTrailingWhitespace(true)) + .with_additional_node(ContextElement::Context("lesser block")) + .with_additional_node(ContextElement::ExitMatcherNode(ExitMatcherNode { + class: ExitClass::Beta, + exit_matcher: &lesser_block_end_specialized, + })); + let parameters = match parameters { + Some((_ws, parameters)) => Some(parameters), + None => None, + }; + + let (remaining, contents) = map(parser_with_context!(plain_text)(&parser_context), |obj| { + obj.source + })(remaining)?; + let (remaining, _end) = lesser_block_end_specialized(&parser_context, remaining)?; + + let (remaining, _trailing_ws) = + maybe_consume_trailing_whitespace_if_not_exiting(context, remaining)?; + + let source = get_consumed(input, remaining); + Ok(( + remaining, + ExportBlock { + source, + name, + data: parameters, + contents, + }, + )) +} + +#[tracing::instrument(ret, level = "debug")] +pub fn src_block<'r, 's>(context: Context<'r, 's>, input: &'s str) -> Res<&'s str, SrcBlock<'s>> { + let (remaining, name) = lesser_block_begin("src")(context, input)?; + // https://orgmode.org/worg/org-syntax.html#Blocks claims that data is mandatory and must follow the LANGUAGE SWITCHES ARGUMENTS pattern but testing has shown that no data and incorrect data here will still parse to a src block. + let (remaining, parameters) = opt(tuple((space1, data)))(remaining)?; + let (remaining, _nl) = line_ending(remaining)?; + let lesser_block_end_specialized = lesser_block_end("src"); + let parser_context = context + .with_additional_node(ContextElement::ConsumeTrailingWhitespace(true)) + .with_additional_node(ContextElement::Context("lesser block")) + .with_additional_node(ContextElement::ExitMatcherNode(ExitMatcherNode { + class: ExitClass::Beta, + exit_matcher: &lesser_block_end_specialized, + })); + let parameters = match parameters { + Some((_ws, parameters)) => Some(parameters), + None => None, + }; + + let (remaining, contents) = map(parser_with_context!(plain_text)(&parser_context), |obj| { + obj.source + })(remaining)?; + let (remaining, _end) = lesser_block_end_specialized(&parser_context, remaining)?; + + let (remaining, _trailing_ws) = + maybe_consume_trailing_whitespace_if_not_exiting(context, remaining)?; + + let source = get_consumed(input, remaining); + Ok(( + remaining, + SrcBlock { + source, + name, + data: parameters, + contents, + }, + )) +} + +#[tracing::instrument(ret, level = "debug")] +fn name<'s>(input: &'s str) -> Res<&'s str, &'s str> { + is_not(" \t\r\n")(input) +} + +#[tracing::instrument(ret, level = "debug")] +fn data<'s>(input: &'s str) -> Res<&'s str, &'s str> { + is_not("\r\n")(input) +} + +fn lesser_block_end( + current_name: &str, +) -> impl for<'r, 's> Fn(Context<'r, 's>, &'s str) -> Res<&'s str, &'s str> { + let current_name_lower = current_name.to_lowercase(); + move |context: Context, input: &str| { + start_of_line(context, input)?; + let (remaining, _leading_whitespace) = space0(input)?; + let (remaining, (_begin, _name, _ws)) = tuple(( + tag_no_case("#+end_"), + tag_no_case(current_name_lower.as_str()), + alt((eof, line_ending)), + ))(remaining)?; + let source = get_consumed(input, remaining); + Ok((remaining, source)) + } +} + +fn lesser_block_begin( + current_name: &str, +) -> impl for<'r, 's> Fn(Context<'r, 's>, &'s str) -> Res<&'s str, &'s str> { + let current_name_lower = current_name.to_lowercase(); + move |context: Context, input: &str| { + start_of_line(context, input)?; + let (remaining, _leading_whitespace) = space0(input)?; + let (remaining, (_begin, name)) = tuple(( + tag_no_case("#+begin_"), + verify(name, |name: &str| { + name.to_lowercase().as_str() == current_name_lower + }), + ))(remaining)?; + Ok((remaining, name)) + } +} diff --git a/src/parser/lesser_element.rs b/src/parser/lesser_element.rs index faf32a1..4c3c822 100644 --- a/src/parser/lesser_element.rs +++ b/src/parser/lesser_element.rs @@ -19,6 +19,46 @@ pub struct TableCell<'s> { pub children: Vec>, } +#[derive(Debug)] +pub struct VerseBlock<'s> { + pub source: &'s str, + pub name: &'s str, + pub data: Option<&'s str>, + pub children: Vec>, +} + +#[derive(Debug)] +pub struct CommentBlock<'s> { + pub source: &'s str, + pub name: &'s str, + pub data: Option<&'s str>, + pub contents: &'s str, +} + +#[derive(Debug)] +pub struct ExampleBlock<'s> { + pub source: &'s str, + pub name: &'s str, + pub data: Option<&'s str>, + pub contents: &'s str, +} + +#[derive(Debug)] +pub struct ExportBlock<'s> { + pub source: &'s str, + pub name: &'s str, + pub data: Option<&'s str>, + pub contents: &'s str, +} + +#[derive(Debug)] +pub struct SrcBlock<'s> { + pub source: &'s str, + pub name: &'s str, + pub data: Option<&'s str>, + pub contents: &'s str, +} + impl<'s> Paragraph<'s> { pub fn of_text(input: &'s str) -> Self { let mut objects = Vec::with_capacity(1); @@ -47,3 +87,29 @@ impl<'s> Source<'s> for Comment<'s> { self.source } } + +impl<'s> Source<'s> for VerseBlock<'s> { + fn get_source(&'s self) -> &'s str { + self.source + } +} +impl<'s> Source<'s> for CommentBlock<'s> { + fn get_source(&'s self) -> &'s str { + self.source + } +} +impl<'s> Source<'s> for ExampleBlock<'s> { + fn get_source(&'s self) -> &'s str { + self.source + } +} +impl<'s> Source<'s> for ExportBlock<'s> { + fn get_source(&'s self) -> &'s str { + self.source + } +} +impl<'s> Source<'s> for SrcBlock<'s> { + fn get_source(&'s self) -> &'s str { + self.source + } +} diff --git a/src/parser/mod.rs b/src/parser/mod.rs index 234b0ab..3f6e752 100644 --- a/src/parser/mod.rs +++ b/src/parser/mod.rs @@ -9,6 +9,7 @@ mod exiting; mod footnote_definition; mod greater_block; mod greater_element; +mod lesser_block; mod lesser_element; mod list; mod object; @@ -38,7 +39,12 @@ pub use greater_element::PropertyDrawer; pub use greater_element::Table; pub use greater_element::TableRow; pub use lesser_element::Comment; +pub use lesser_element::CommentBlock; +pub use lesser_element::ExampleBlock; +pub use lesser_element::ExportBlock; pub use lesser_element::Paragraph; +pub use lesser_element::SrcBlock; pub use lesser_element::TableCell; +pub use lesser_element::VerseBlock; pub use source::Source; type Context<'r, 's> = &'r parser_context::ContextTree<'r, 's>;