rust - 如何使用 Rust nom 为这种结构文本编写解析器？

Question

我有以下数据

    let data = r#"title1
title1 line1
title1 line2
sep/
title2
title2 line1
title2 line2
title2 line3
sep/
title3
title3 line1
sep/"#;

基本上它代表三个条目:

struct Entry {
    title: String,
    body: String,
}

每个条目都有一个标题和一个正文。标题占用一行(不包括行尾)，正文占用所有后续行，直到遇到分隔线 (sep/)。我想要的结果是条目向量。我如何使用 nom 来解析它？我是 nom 的新手，我无法让这些部分一起工作并形成一个有效的解析器。以下是我所拥有的:

use nom::IResult;
use nom::branch::alt;
use nom::bytes::complete::{tag, take_until, is_not, is_a};
use nom::error::ErrorKind::ParseTo;
use nom::sequence::{pair, tuple, delimited, terminated};
use nom::combinator::opt;
use nom::error::{Error, ErrorKind};
use nom::character::complete::line_ending;
use nom::regexp::str::{re_find, re_match, re_matches, re_capture};
use nom::multi::many0;

struct Entry {
    title: String,
    body: String,
}

fn get_entry_title(i: &str) -> IResult<&str, &str> {
    delimited(tag(""),
              take_until(alt((
                  tag("\r\n"),
                  tag("\n")
              ))),
              alt((
                  tag("\r\n"),
                  tag("\n")
              ))
    )(i)
}

fn get_entry_body(i: &str) -> IResult<&str, &str> {
    terminated(
        take_until( tag("sep/")),
        tag("sep/")
    )(i)
}

fn main() {
    let data = r#"title1
title1 line1
title1 line2
sep/
title2
title2 line1
title2 line2
title2 line3
sep/
title3
title3 line1
sep/"#;

    let result = get_entry_title(&data);
}

Answer 1

这是一个仅限 nom 的方法(nom 6.1.2):

use nom::IResult;
use nom::branch::alt;
use nom::bytes::complete::{tag, take_while};
use nom::sequence::{terminated, delimited, pair};
use nom::multi::{separated_list0, many1};

#[derive(Debug)]
struct Entry {
    title: String,
    body: String,
}

fn main() {
    let input = r#"title1
title1 line1
title1 line2
sep/
title2
title2 line1
title2 line2
title2 line3
sep/
title3
title3 line1
sep/"#;

    let (_, entries) = parse(input).unwrap();
    println!("{:#?}", entries);
}

fn parse(input: &str) -> IResult<&str, Vec<Entry>> {
    separated_list0(
        separator,
        entry,
    )(input)
}

fn entry(input: &str) -> IResult<&str, Entry> {
    let (input, title) = title(input)?;
    let (input, body_lines) = many1(body_line(title))(input)?;

    let body = body_lines.join("");
    let entry = Entry {
        title: title.to_owned(),
        body,
    };
    
    //TODO: Does it have to end with a separator ? 
    // If it does, either use terminated() in combination with many(), or add
    // an additional check for separator here
    

    IResult::Ok((input, entry))
}

fn title(input: &str) -> IResult<&str, &str> {
    terminated(
        take_while(not_r_n),
        end_of_line,
    )(input)
}

pub fn body_line<'i>(title: &'i str) -> impl FnMut(&'i str) -> IResult<&'i str, &'i str, nom::error::Error<&'i str>>
{
    move |input: &str| {
        delimited(
            pair(tag(title), tag(" ")),
            take_while(not_r_n),
            end_of_line,
        )(input)
    }
}

fn separator(input: &str) -> IResult<&str, &str> {
    terminated(
        tag("sep/"), // the separator is hardcoded, otherwise you have to do the same monstrosity as body_line() above
        end_of_line,
    )(input)
}

fn end_of_line(input: &str) -> IResult<&str, &str> {
    alt((
        tag("\n"),
        tag("\r\n")
    ))(input)
}

fn not_r_n(ch: char) -> bool {
    ch != '\r' && ch != '\n'
}