Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Implement LocatedSpan::get_line(). #66

Merged
merged 10 commits into from
Oct 18, 2020
Merged
39 changes: 39 additions & 0 deletions src/lib.rs
Original file line number Diff line number Diff line change
Expand Up @@ -277,6 +277,45 @@ impl<T: AsBytes, X> LocatedSpan<T, X> {
(column, &before_self[self.offset - (column - 1)..])
}

/// Return the line that contains this LocatedSpan.
///
/// The `get_column` and `get_utf8_column` functions returns
/// indexes that corresponds to the line returned by this function.
///
/// ```
/// # extern crate nom_locate;
/// # extern crate nom;
/// # use nom_locate::LocatedSpan;
/// # use nom::{Slice, FindSubstring};
/// #
/// # fn main() {
/// let program = LocatedSpan::new(
/// "Hello World!\
/// \nThis is a multi-line input\
/// \nthat ends after this line.\n");
/// let multi = program.find_substring("multi").unwrap();
///
/// assert_eq!(
/// program.slice(multi..).get_line(),
/// Some("This is a multi-line input".as_ref()),
/// );
/// # }
/// ```
pub fn get_line(&self) -> Option<&[u8]> {
let self_bytes = self.fragment.as_bytes();
let self_ptr = self_bytes.as_ptr();
let offset = self.get_column() - 1;
let the_line = unsafe {
assert!(
offset <= isize::max_value() as usize,
"offset is too big"
);
let line_start_ptr = self_ptr.offset(-(offset as isize));
slice::from_raw_parts(line_start_ptr, offset + self_bytes.len())
};
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I feel like this code could/should be shared with get_columns_and_bytes_before. Could you add a private (unsafe) function for this?

the_line.split(|c| *c == b'\n').next()
}

/// Return the column index, assuming 1 byte = 1 column.
///
/// Use it for ascii text, or use get_utf8_column for UTF8.
Expand Down
93 changes: 93 additions & 0 deletions src/tests.rs
Original file line number Diff line number Diff line change
Expand Up @@ -414,3 +414,96 @@ fn it_should_display_hex() {
"00000000\t61 62 63 \tabc\n".to_owned()
);
}

#[test]
fn line_of_empty_span_is_empty() {
assert_eq!(
StrSpan::new("").get_line(),
Some("".as_ref()),
);
}

#[test]
fn line_of_single_line_start_is_whole() {
assert_eq!(
StrSpan::new("A single line").get_line(),
Some("A single line".as_ref()),
);
}
#[test]
fn line_of_single_line_end_is_whole() {
let data = "A single line";
assert_eq!(
StrSpan::new(data).slice(data.len()..).get_line(),
Some("A single line".as_ref()),
);
}

#[test]
fn line_of_start_is_first() {
assert_eq!(
StrSpan::new(
"One line of text\
\nFollowed by a second\
\nand a third\n"
).get_line(),
Some("One line of text".as_ref()),
);
}

#[test]
fn line_of_nl_is_before() {
let data =
"One line of text\
\nFollowed by a second\
\nand a third\n";
assert_eq!(
StrSpan::new(data).slice(data.find('\n').unwrap()..).get_line(),
Some("One line of text".as_ref()),
);
}

#[test]
fn line_of_end_after_nl_is_empty() {
let data =
"One line of text\
\nFollowed by a second\
\nand a third\n";
assert_eq!(
StrSpan::new(data).slice(data.len()..).get_line(),
Some("".as_ref()),
);
}

#[test]
fn line_of_end_no_nl_is_last() {
let data =
"One line of text\
\nFollowed by a second\
\nand a third";
assert_eq!(
StrSpan::new(data).slice(data.len()..).get_line(),
Some("and a third".as_ref()),
);
}

#[test]
fn line_for_non_ascii_chars() {
// I don't really know if this Oriya text makes sense.
kaj marked this conversation as resolved.
Show resolved Hide resolved
let data = StrSpan::new(
"Några rader text på Svenska.\
\nFörra raden var först, den här är i mitten\
\noch här är sista raden.\n");
let s = data.slice(data.find_substring("först").unwrap()..);
assert_eq!(
format!(
"{line_no:3}: {line_text}\n {0:>lpos$}^- The match\n",
"",
line_no = s.location_line(),
line_text = core::str::from_utf8(s.get_line().unwrap()).unwrap(),
lpos = s.get_utf8_column(),
),
" 2: Förra raden var först, den här är i mitten\
\n ^- The match\n",
);
}