Switch to handling the unescaping during the initial parsing.
This preserves the line ending characters unlike the rust .lines() iterator.
This commit is contained in:
parent
afb43ff34f
commit
7ee48ff65c
@ -2,17 +2,22 @@ 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::consumed;
|
||||
use nom::combinator::eof;
|
||||
use nom::combinator::map;
|
||||
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::many_till;
|
||||
use nom::multi::separated_list1;
|
||||
use nom::sequence::preceded;
|
||||
use nom::sequence::tuple;
|
||||
|
||||
use super::org_source::OrgSource;
|
||||
@ -151,7 +156,10 @@ pub(crate) fn example_block<'b, 'g, 'r, 's>(
|
||||
let parser_context = parser_context.with_additional_node(&contexts[2]);
|
||||
let parameters = parameters.map(|(_, parameters)| parameters);
|
||||
|
||||
let (remaining, contents) = parser_with_context!(text_until_exit)(&parser_context)(remaining)?;
|
||||
let (remaining, contents) = many0(preceded(
|
||||
not(parser_with_context!(exit_matcher_parser)(&parser_context)),
|
||||
map(content_line, Into::<&str>::into),
|
||||
))(remaining)?;
|
||||
let (remaining, _end) = lesser_block_end_specialized(&parser_context, remaining)?;
|
||||
|
||||
let source = get_consumed(input, remaining);
|
||||
@ -178,7 +186,7 @@ pub(crate) fn example_block<'b, 'g, 'r, 's>(
|
||||
retain_labels,
|
||||
use_labels,
|
||||
label_format,
|
||||
contents: contents.into(),
|
||||
contents,
|
||||
},
|
||||
))
|
||||
}
|
||||
@ -431,3 +439,10 @@ fn switch_word<'s>(input: OrgSource<'s>) -> Res<OrgSource<'s>, OrgSource<'s>> {
|
||||
is_not(" \t\r\n"),
|
||||
))(input)
|
||||
}
|
||||
|
||||
#[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))]
|
||||
fn content_line<'s>(input: OrgSource<'s>) -> Res<OrgSource<'s>, OrgSource<'s>> {
|
||||
let (remaining, _) = opt(tuple((space0, tag(","), peek(alt((tag("#+"), tag("*")))))))(input)?;
|
||||
let (remaining, line_post_escape) = recognize(many_till(anychar, line_ending))(remaining)?;
|
||||
Ok((remaining, line_post_escape))
|
||||
}
|
||||
|
@ -45,7 +45,7 @@ pub struct ExampleBlock<'s> {
|
||||
pub retain_labels: bool,
|
||||
pub use_labels: bool,
|
||||
pub label_format: Option<&'s str>,
|
||||
pub contents: &'s str,
|
||||
pub contents: Vec<&'s str>,
|
||||
}
|
||||
|
||||
#[derive(Debug)]
|
||||
@ -241,21 +241,12 @@ impl<'s> Comment<'s> {
|
||||
impl<'s> ExampleBlock<'s> {
|
||||
/// Get the inner contents of the ExampleBlock with the escaping commas removed.
|
||||
pub fn get_contents(&self) -> String {
|
||||
let mut ret = String::with_capacity(self.contents.len());
|
||||
for line in self.contents.lines() {
|
||||
let first_comma = line.find(",#+").or_else(|| line.find(",*"));
|
||||
if let Some(first_comma) = first_comma {
|
||||
let before_first_comma = &line[..first_comma];
|
||||
let is_escaping_comma = before_first_comma.chars().all(char::is_whitespace);
|
||||
if is_escaping_comma {
|
||||
ret.push_str(&line[(first_comma + 1)..]);
|
||||
} else {
|
||||
ret.push_str(line);
|
||||
}
|
||||
} else {
|
||||
ret.push_str(line);
|
||||
}
|
||||
let final_size = self.contents.iter().map(|line| line.len()).sum();
|
||||
let mut ret = String::with_capacity(final_size);
|
||||
for line in &self.contents {
|
||||
ret.push_str(line);
|
||||
}
|
||||
|
||||
ret
|
||||
}
|
||||
}
|
||||
|
Loading…
x
Reference in New Issue
Block a user