organic/src/compare/util.rs

use super::elisp_fact::GetElispFact;
use super::sexp::Token;
use crate::compare::sexp::unquote;
use crate::types::GetStandardProperties;
use crate::types::StandardProperties;

/// Check if the child string slice is a slice of the parent string slice.
fn is_slice_of(parent: &str, child: &str) -> bool {
    let parent_start = parent.as_ptr() as usize;
    let parent_end = parent_start + parent.len();
    let child_start = child.as_ptr() as usize;
    let child_end = child_start + child.len();
    child_start >= parent_start && child_end <= parent_end
}

/// Get the byte offset into source that the rust object exists at.
///
/// These offsets are zero-based unlike the elisp ones.
fn get_rust_byte_offsets<'s, S: StandardProperties<'s> + ?Sized>(
    original_document: &'s str,
    rust_ast_node: &'s S,
) -> (usize, usize) {
    let rust_object_source = rust_ast_node.get_source();
    debug_assert!(is_slice_of(original_document, rust_object_source));
    let offset = rust_object_source.as_ptr() as usize - original_document.as_ptr() as usize;
    let end = offset + rust_object_source.len();
    (offset, end)
}

pub(crate) fn compare_standard_properties<
    's,
    S: GetStandardProperties<'s> + GetElispFact<'s> + ?Sized,
>(
    original_document: &'s str,
    emacs: &'s Token<'s>,
    rust: &'s S,
) -> Result<(), Box<dyn std::error::Error>> {
    assert_name(emacs, rust.get_elisp_fact().get_elisp_name())?;
    assert_bounds(original_document, emacs, rust.get_standard_properties())?;
    Ok(())
}

pub(crate) fn assert_name<'s, S: AsRef<str>>(
    emacs: &'s Token<'s>,
    name: S,
) -> Result<(), Box<dyn std::error::Error>> {
    let name = name.as_ref();
    let children = emacs.as_list()?;
    let first_child = children
        .first()
        .ok_or("Should have at least one child.")?
        .as_atom()?;
    if first_child != name {
        Err(format!(
            "AST node name mismatch. Expected a (rust) {expected} cell, but found a (emacs) {found} cell.",
            expected = name,
            found = first_child
        ))?;
    }
    Ok(())
}

/// Assert that the character ranges defined by upstream org-mode's :standard-properties match the slices in Organic's StandardProperties.
///
/// This does **not** handle plain text because plain text is a special case.
pub(crate) fn assert_bounds<'s, S: StandardProperties<'s> + ?Sized>(
    original_document: &'s str,
    emacs: &'s Token<'s>,
    rust: &'s S,
) -> Result<(), Box<dyn std::error::Error>> {
    let standard_properties = get_emacs_standard_properties(emacs)?; // 1-based
    let (begin, end) = (
        standard_properties
            .begin
            .ok_or("Token should have a begin.")?,
        standard_properties.end.ok_or("Token should have an end.")?,
    );
    let (rust_begin, rust_end) = get_rust_byte_offsets(original_document, rust); // 0-based
    let rust_begin_char_offset = (&original_document[..rust_begin]).chars().count() + 1; // 1-based
    let rust_end_char_offset =
        rust_begin_char_offset + (&original_document[rust_begin..rust_end]).chars().count(); // 1-based
    if rust_begin_char_offset != begin || rust_end_char_offset != end {
        Err(format!("Rust bounds (in chars) ({rust_begin}, {rust_end}) do not match emacs bounds ({emacs_begin}, {emacs_end})", rust_begin = rust_begin_char_offset, rust_end = rust_end_char_offset, emacs_begin=begin, emacs_end=end))?;
    }

    Ok(())
}

struct EmacsStandardProperties {
    begin: Option<usize>,
    #[allow(dead_code)]
    post_affiliated: Option<usize>,
    #[allow(dead_code)]
    contents_begin: Option<usize>,
    #[allow(dead_code)]
    contents_end: Option<usize>,
    end: Option<usize>,
    #[allow(dead_code)]
    post_blank: Option<usize>,
}

fn get_emacs_standard_properties<'s>(
    emacs: &'s Token<'s>,
) -> Result<EmacsStandardProperties, Box<dyn std::error::Error>> {
    let children = emacs.as_list()?;
    let attributes_child = children
        .iter()
        .nth(1)
        .ok_or("Should have an attributes child.")?;
    let attributes_map = attributes_child.as_map()?;
    let standard_properties = attributes_map.get(":standard-properties");
    Ok(if standard_properties.is_some() {
        let mut std_props = standard_properties
            .expect("if statement proves its Some")
            .as_vector()?
            .into_iter();
        let begin = maybe_token_to_usize(std_props.next())?;
        let post_affiliated = maybe_token_to_usize(std_props.next())?;
        let contents_begin = maybe_token_to_usize(std_props.next())?;
        let contents_end = maybe_token_to_usize(std_props.next())?;
        let end = maybe_token_to_usize(std_props.next())?;
        let post_blank = maybe_token_to_usize(std_props.next())?;
        EmacsStandardProperties {
            begin,
            post_affiliated,
            contents_begin,
            contents_end,
            end,
            post_blank,
        }
    } else {
        let begin = maybe_token_to_usize(attributes_map.get(":begin").map(|token| *token))?;
        let end = maybe_token_to_usize(attributes_map.get(":end").map(|token| *token))?;
        let contents_begin =
            maybe_token_to_usize(attributes_map.get(":contents-begin").map(|token| *token))?;
        let contents_end =
            maybe_token_to_usize(attributes_map.get(":contents-end").map(|token| *token))?;
        let post_blank =
            maybe_token_to_usize(attributes_map.get(":post-blank").map(|token| *token))?;
        let post_affiliated =
            maybe_token_to_usize(attributes_map.get(":post-affiliated").map(|token| *token))?;
        EmacsStandardProperties {
            begin,
            post_affiliated,
            contents_begin,
            contents_end,
            end,
            post_blank,
        }
    })
}

fn maybe_token_to_usize(
    token: Option<&Token<'_>>,
) -> Result<Option<usize>, Box<dyn std::error::Error>> {
    Ok(token
        .map(|token| token.as_atom())
        .map_or(Ok(None), |r| r.map(Some))?
        .map(|val| {
            if val == "nil" {
                None
            } else {
                Some(val.parse::<usize>())
            }
        })
        .flatten() // Outer option is whether or not the param exists, inner option is whether or not it is nil
        .map_or(Ok(None), |r| r.map(Some))?)
}

/// Get a named property from the emacs token.
///
/// Returns Ok(None) if value is nil.
///
/// Returns error if the attribute is not specified on the token at all.
pub(crate) fn get_property<'s, 'x>(
    emacs: &'s Token<'s>,
    key: &'x str,
) -> Result<Option<&'s Token<'s>>, Box<dyn std::error::Error>> {
    let children = emacs.as_list()?;
    let attributes_child = children
        .iter()
        .nth(1)
        .ok_or("Should have an attributes child.")?;
    let attributes_map = attributes_child.as_map()?;
    let prop = attributes_map
        .get(key)
        .ok_or(format!("Missing {} attribute.", key))?;
    match prop.as_atom() {
        Ok("nil") => return Ok(None),
        _ => {}
    };
    Ok(Some(*prop))
}

/// Get a named property containing an unquoted atom from the emacs token.
///
/// Returns None if key is not found.
pub(crate) fn get_property_unquoted_atom<'s, 'x>(
    emacs: &'s Token<'s>,
    key: &'x str,
) -> Result<Option<&'s str>, Box<dyn std::error::Error>> {
    Ok(get_property(emacs, key)?
        .map(Token::as_atom)
        .map_or(Ok(None), |r| r.map(Some))?)
}

/// Get a named property containing an quoted string from the emacs token.
///
/// Returns None if key is not found.
pub(crate) fn get_property_quoted_string<'s, 'x>(
    emacs: &'s Token<'s>,
    key: &'x str,
) -> Result<Option<String>, Box<dyn std::error::Error>> {
    Ok(get_property(emacs, key)?
        .map(Token::as_atom)
        .map_or(Ok(None), |r| r.map(Some))?
        .map(unquote)
        .map_or(Ok(None), |r| r.map(Some))?)
}