boxmaker/docs/plans/M5b/files/crates/gatewayd/src/links/inline.rs

//! One paragraph of prose: code spans, escapes, images, links and URLs, left to right.

use super::{BREAKS, Out, runs};

/// What marked lets a backslash escape. Other characters after a backslash are plain text.
const ESCAPABLE: &str = "\\`*{}[]()#+-.!_>|~";

/// What a URL loses at its end: marked leaves these out of a link when they end it.
const TRAILING: [char; 11] = ['.', ',', ':', ';', '!', '?', '*', '_', '~', '\'', '"'];

/// How many characters a search for the end of a construct looks at, so that a reply full of
/// brackets costs time in proportion to its length. An image longer than this still has its `![`
/// put in a code span; a link longer than this keeps only its URL in one.
const WINDOW: usize = 2048;

/// What a paragraph has shown so far that changes how its later code spans may pair.
#[derive(Default)]
struct Seen {
    /// Backtick run lengths that may pair differently in the two parsers from here on.
    hazards: Vec<usize>,
    /// What would close what a plain character opened: marked lets emphasis (`*`, `_`, `~`), a
    /// tag (`<`) and inline LaTeX (`$`) take a backtick before a code span starts.
    closers: Vec<char>,
}

impl Seen {
    /// Add to `hazards`, once each, every length from 1 to that of each backtick run in `text`:
    /// marked may read part of a run as part of a URL, and the rest as a run of its own.
    fn runs(&mut self, text: &str) {
        for (_, len) in runs(text) {
            for part in 1..=len {
                if !self.hazards.contains(&part) {
                    self.hazards.push(part);
                }
            }
        }
    }

    /// A plain character: `*`, `_`, `~` and `$` are their own closers, and `<` is closed by `>`;
    /// push the closer onto `closers` if it is not there yet. Any other character: nothing.
    fn plain(&mut self, c: char) {
        todo!()
    }
}

impl Out {
    /// Write `para` with its images, and when `untrusted` its links and URLs, in code spans.
    pub(super) fn paragraph(&mut self, para: &str, untrusted: bool) {
        let mut seen = Seen::default();
        let mut prev = None;
        let mut at = 0;
        while let Some(rest) = para.get(at..).filter(|rest| !rest.is_empty()) {
            let line_start = at == 0 || para.get(..at).is_some_and(|done| done.ends_with(BREAKS));
            match self.token(rest, prev, line_start, untrusted, &mut seen) {
                Some(used) if used > 0 => {
                    at += used;
                    prev = None;
                }
                _ => {
                    let c = rest.chars().next().unwrap_or_default();
                    self.text.push(c);
                    seen.plain(c);
                    at += c.len_utf8();
                    prev = Some(c);
                }
            }
        }
    }

    /// Write the token `rest` starts with and give its length in bytes, or `None` when `rest`
    /// starts with a plain character, which the caller writes. `prev` is the plain character
    /// before, `None` after a token or at the start.
    fn token(
        &mut self,
        rest: &str,
        prev: Option<char>,
        line_start: bool,
        untrusted: bool,
        seen: &mut Seen,
    ) -> Option<usize> {
        if untrusted && line_start && definition(rest) {
            let end = rest.find(BREAKS).unwrap_or(rest.len());
            return Some(self.link(rest, end, seen));
        }
        match rest.chars().next()? {
            '\\' => escape_len(rest).map(|len| self.copy(rest, len)),
            '`' => Some(self.backticks(rest, seen)),
            '!' if rest.starts_with("![") => {
                // No `]` in reach: the `![` alone is enough to stop the image.
                let len = construct_len(rest.get(1..)?, true).unwrap_or(1);
                Some(self.image(rest, len + 1, seen))
            }
            '[' => self.bracket(rest, untrusted, seen),
            '<' => self.autolink(rest, untrusted, seen),
            _ if url_start(rest, prev) => self.url(rest, untrusted, seen),
            _ => None,
        }
    }

    /// A run of backticks: a code span both parsers read as code is written as it is; any other
    /// run is written as plain text, and its length becomes a hazard.
    fn backticks(&mut self, rest: &str, seen: &mut Seen) -> usize {
        if let Some(len) = span_len(rest, seen) {
            return self.copy(rest, len);
        }
        let run = rest.chars().take_while(|&c| c == '`').count();
        seen.runs(rest.get(..run).unwrap_or_default());
        self.copy(rest, run)
    }

    /// A `[` that starts a link, `[text](…)` or `[text][…]`: see `construct`. Any other `[` is
    /// written escaped if `](` follows within `WINDOW`: marked may still read a link from it, with
    /// a label that takes in new code spans.
    fn bracket(&mut self, rest: &str, untrusted: bool, seen: &mut Seen) -> Option<usize> {
        let Some(len) = construct_len(rest, false) else {
            if !window(rest).contains("](") {
                return None;
            }
            self.text.push_str("\\[");
            return Some(1);
        };
        self.construct(rest, len, untrusted, seen)
    }

    /// A `<` that starts an autolink: see `construct`.
    fn autolink(&mut self, rest: &str, untrusted: bool, seen: &mut Seen) -> Option<usize> {
        let len = autolink_len(rest)?;
        self.construct(rest, len, untrusted, seen)
    }

    /// A URL: see `construct`. In a clean reply it is the most marked may read as the URL
    /// (`url_len` with `whole`), backticks included, since marked reads them as part of it.
    fn url(&mut self, rest: &str, untrusted: bool, seen: &mut Seen) -> Option<usize> {
        let len = url_len(rest, !untrusted);
        self.construct(rest, len, untrusted, seen)
    }

    /// The first `len` bytes of `rest`, a link, go in code spans when `untrusted`, and also in a
    /// clean reply when they hold `![` (CommonMark may read the image where marked reads a link).
    /// Otherwise they are written as they are. Marked may end the link sooner than this, so its
    /// backtick runs become hazards, and each of its characters counts as `Seen::plain`.
    fn construct(
        &mut self,
        rest: &str,
        len: usize,
        untrusted: bool,
        seen: &mut Seen,
    ) -> Option<usize> {
        let construct = rest.get(..len)?;
        if untrusted {
            return Some(self.link(rest, len, seen));
        }
        if construct.contains("![") {
            return Some(self.image(rest, len, seen));
        }
        seen.runs(construct);
        construct.chars().for_each(|c| seen.plain(c));
        Some(self.copy(rest, len))
    }

    fn copy(&mut self, rest: &str, len: usize) -> usize {
        self.text.push_str(rest.get(..len).unwrap_or_default());
        len
    }

    fn image(&mut self, rest: &str, len: usize, seen: &Seen) -> usize {
        self.wrap(
            rest.get(..len).unwrap_or_default(),
            rest.get(len..).unwrap_or_default(),
            &seen.closers,
        );
        len
    }

    fn link(&mut self, rest: &str, len: usize, seen: &Seen) -> usize {
        self.links = true;
        self.image(rest, len, seen)
    }
}

/// `rest` starts with a backslash: `Some(2)` if the next character is one of `ESCAPABLE`, else
/// `None` (the backslash is plain).
fn escape_len(rest: &str) -> Option<usize> {
    todo!()
}

/// `rest` starts with a run of `run` backticks. The span's length, `run + close + run`, if both
/// parsers read it as code: `run` is not in `seen.hazards`; `closing(after, run)` gives `close`
/// in the text `after` the run; and the content between holds no line end (`BREAKS`), no `|`,
/// none of `seen.closers`, and no run (`runs`) whose length is in `seen.hazards`.
fn span_len(rest: &str, seen: &Seen) -> Option<usize> {
    todo!()
}

/// The byte offset in `text` of the first run of exactly `run` backticks, if there is one.
fn closing(text: &str, run: usize) -> Option<usize> {
    let mut start = 0;
    let mut len = 0;
    for (i, c) in text.char_indices() {
        if c == '`' {
            if len == 0 {
                start = i;
            }
            len += 1;
        } else if len > 0 {
            if len == run {
                return Some(start);
            }
            len = 0;
        }
    }
    (len == run).then_some(start)
}

/// At most the first `WINDOW` characters of `text`.
fn window(text: &str) -> &str {
    match text.char_indices().nth(WINDOW) {
        Some((end, _)) => text.get(..end).unwrap_or(text),
        None => text,
    }
}

/// `text` starts with `[`; only `window(text)` is looked at. The label ends at
/// `bracket_end(text, true)`, or if that is `None`, `bracket_end(text, false)`. Right after it: a
/// `(` closed by `paren_end` gives the length through that `)`; or else, after white space
/// (`trim_start`), a `[` closed by `reference_end` gives it through that `]`; or else, only when
/// `bare` (an image may be `![alt]`), through the label's `]`. `None` if nothing fits.
fn construct_len(text: &str, bare: bool) -> Option<usize> {
    todo!()
}

/// `text` starts with `[`: the byte offset of the `]` that closes it. Walk it counting `[` up and
/// `]` down (to 0: found), skipping the character after each backslash. When `code`, a backtick
/// run jumps past the next run of the same length (`closing`), as a CommonMark code span; a run
/// with none is skipped as plain. `None` if no `]` closes it.
fn bracket_end(text: &str, code: bool) -> Option<usize> {
    todo!()
}

/// `text` starts with `(`: the byte offset of the `)` that closes it, counting `(` up and `)` down
/// (to 0: found). A backslash escapes nothing here, as in marked's link destinations. `None` if
/// no `)` closes it.
fn paren_end(text: &str) -> Option<usize> {
    todo!()
}

/// `text` starts with `[`: the byte index of the next `]`, skipping the character after each
/// backslash, if no `[` comes first (a reference label does not nest). `None` otherwise, and when
/// `text` does not start with `[`.
fn reference_end(text: &str) -> Option<usize> {
    let mut chars = text.strip_prefix('[')?.char_indices();
    while let Some((i, c)) = chars.next() {
        match c {
            '\\' => {
                chars.next();
            }
            '[' => return None,
            ']' => return Some(i + 1),
            _ => {}
        }
    }
    None
}

/// `rest` starts with `<`: the length of the autolink it starts, `<` through the first `>` in
/// `window(rest)`, if the text between is not empty, holds no space, tab or no-break space (a line
/// end is allowed, as in marked), and holds `:` or `@` or starts with `www` in any case.
fn autolink_len(rest: &str) -> Option<usize> {
    todo!()
}

/// Whether the line `rest` starts (up to the first of `BREAKS`) is a link reference definition:
/// after white space (`trim_start`), `[`, then a label of at least one character with no `]` in
/// it, then `]:`.
fn definition(rest: &str) -> bool {
    todo!()
}

/// Whether a URL starts at `rest`, after the plain character `prev`: a `scheme` or `www` where
/// `prev` is not an ASCII letter or digit, or a `scheme_less` domain where `prev` is not a
/// letter, digit, `.` or `-`. `prev` is `None` at the start and after a token.
fn url_start(rest: &str, prev: Option<char>) -> bool {
    let word = prev.is_none_or(|p| !p.is_ascii_alphanumeric());
    let run = prev.is_none_or(|p| !(p.is_alphanumeric() || p == '.' || p == '-'));
    (word && (scheme(rest) || www(rest))) || (run && scheme_less(rest))
}

/// Whether `rest` starts with a scheme: an ASCII letter, then ASCII letters, digits, `+`, `.`
/// or `-`, then `:` and a `/`, `%`, or letter or digit of any script.
fn scheme(rest: &str) -> bool {
    rest.starts_with(|c: char| c.is_ascii_alphabetic())
        && rest
            .trim_start_matches(|c: char| c.is_ascii_alphanumeric() || matches!(c, '+' | '.' | '-'))
            .strip_prefix(':')
            .and_then(|after| after.chars().next())
            .is_some_and(|c| c == '/' || c == '%' || c.is_alphanumeric())
}

/// Whether `rest` starts with `www` in any case, then ASCII digits (none or more), then `.` and a
/// character that is not white space.
fn www(rest: &str) -> bool {
    rest.get(..3).is_some_and(|w| w.eq_ignore_ascii_case("www"))
        && rest
            .get(3..)
            .unwrap_or_default()
            .trim_start_matches(|c: char| c.is_ascii_digit())
            .strip_prefix('.')
            .and_then(|after| after.chars().next())
            .is_some_and(|c| !c.is_whitespace())
}

/// Whether `rest` starts with a domain and a `/` (marked links `example.com/x` bare): a run of
/// letters, digits, `.` and `-`, whose part after its last `.` is 2 to 4 letters with something
/// before it, then `/`.
fn scheme_less(rest: &str) -> bool {
    let end = rest
        .find(|c: char| !(c.is_alphanumeric() || c == '.' || c == '-'))
        .unwrap_or(rest.len());
    let (Some(host), Some(after)) = (rest.get(..end), rest.get(end..)) else {
        return false;
    };
    let Some((name, tld)) = host.rsplit_once('.') else {
        return false;
    };
    after.starts_with('/')
        && !name.is_empty()
        && (2..=4).contains(&tld.chars().count())
        && tld.chars().all(char::is_alphabetic)
}

/// The length of the URL `rest` starts with: up to white space, a `)` that closes no `(` of the
/// URL (count them), or a `<` before white space, `(`, `)`, `<`, `>` or the end (marked leaves it
/// out: it may start an autolink); unless `whole`, up to any `<`, `>`, `|` or backtick too. Then
/// less the characters of `TRAILING` at its end. `whole` is the most marked may read as the URL.
fn url_len(rest: &str, whole: bool) -> usize {
    todo!()
}