scriptis/lix
0
0
Fork 0
forked from lix-project/lix
Code Pull requests Activity

Merge "lix-doc: update dependencies and refactor" into main

Browse source
This commit is contained in:
Lunaphied 2024-07-10 17:47:27 +00:00 committed by Gerrit Code Review
parent f0c751d4d6 41963df4a5
commit 014410cbf0
6 changed files with 395 additions and 247 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

114
lix-doc/Cargo.lock generated
View file

@ -9,13 +9,10 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "d468802bab17cbc0cc575e9b053f41e72aa36bfa6b7f55e3529ffa43161b97fa" checksum = "d468802bab17cbc0cc575e9b053f41e72aa36bfa6b7f55e3529ffa43161b97fa"
[[package]] [[package]]
name = "cbitset" name = "countme"
version = "0.2.0" version = "3.0.1"
source = "registry+https://github.com/rust-lang/crates.io-index" source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "29b6ad25ae296159fb0da12b970b2fe179b234584d7cd294c891e2bbb284466b" checksum = "7704b5fdd17b18ae31c4c1da5a2e0305a2bf17b5249300a9ee9ed7b72114c636"
dependencies = [
"num-traits",
]
[[package]] [[package]]
name = "dissimilar" name = "dissimilar"
@ -33,19 +30,26 @@ dependencies = [
"once_cell", "once_cell",
] ]
[[package]]
name = "hashbrown"
version = "0.14.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "e5274423e17b7c9fc20b6e7e208532f9b19825d82dfd615708b70edd83df41f1"
[[package]] [[package]]
name = "lix-doc" name = "lix-doc"
version = "0.0.1" version = "0.0.1"
dependencies = [ dependencies = [
"expect-test", "expect-test",
"rnix", "rnix",
"rowan",
] ]
[[package]] [[package]]
name = "num-traits" name = "memoffset"
version = "0.2.18" version = "0.9.1"
source = "registry+https://github.com/rust-lang/crates.io-index" source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "da0df0e5185db44f69b44f26786fe401b6c293d1907744beaa7fa62b2e5a517a" checksum = "488016bfae457b036d996092f6cb448677611ce4449e970ceaf42695203f218a"
dependencies = [ dependencies = [
"autocfg", "autocfg",
] ]
@ -56,44 +60,26 @@ version = "1.19.0"
source = "registry+https://github.com/rust-lang/crates.io-index" source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "3fdb12b2476b595f9358c5161aa467c2438859caa136dec86c26fdd2efe17b92" checksum = "3fdb12b2476b595f9358c5161aa467c2438859caa136dec86c26fdd2efe17b92"
[[package]]
name = "proc-macro2"
version = "1.0.79"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "e835ff2298f5721608eb1a980ecaee1aef2c132bf95ecc026a11b7bf3c01c02e"
dependencies = [
"unicode-ident",
]
[[package]]
name = "quote"
version = "1.0.35"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "291ec9ab5efd934aaf503a6466c5d5251535d108ee747472c3977cc5acc868ef"
dependencies = [
"proc-macro2",
]
[[package]] [[package]]
name = "rnix" name = "rnix"
version = "0.8.1" version = "0.11.0"
source = "registry+https://github.com/rust-lang/crates.io-index" source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "0a9b645f0edba447dbfc6473dd22999f46a1d00ab39e777a2713a1cf34a1597b" checksum = "bb35cedbeb70e0ccabef2a31bcff0aebd114f19566086300b8f42c725fc2cb5f"
dependencies = [ dependencies = [
"cbitset",
"rowan", "rowan",
] ]
[[package]] [[package]]
name = "rowan" name = "rowan"
version = "0.9.1" version = "0.15.15"
source = "registry+https://github.com/rust-lang/crates.io-index" source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "1ea7cadf87a9d8432e85cb4eb86bd2e765ace60c24ef86e79084dcae5d1c5a19" checksum = "32a58fa8a7ccff2aec4f39cc45bf5f985cec7125ab271cf681c279fd00192b49"
dependencies = [ dependencies = [
"countme",
"hashbrown",
"memoffset",
"rustc-hash", "rustc-hash",
"smol_str", "text-size",
"text_unit",
"thin-dst",
] ]
[[package]] [[package]]
@ -103,59 +89,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "08d43f7aa6b08d49f382cde6a7982047c3426db949b1424bc4b7ec9ae12c6ce2" checksum = "08d43f7aa6b08d49f382cde6a7982047c3426db949b1424bc4b7ec9ae12c6ce2"
[[package]] [[package]]
name = "serde" name = "text-size"
version = "1.0.197" version = "1.1.1"
source = "registry+https://github.com/rust-lang/crates.io-index" source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "3fb1c873e1b9b056a4dc4c0c198b24c3ffa059243875552b2bd0933b1aee4ce2" checksum = "f18aa187839b2bdb1ad2fa35ead8c4c2976b64e4363c386d45ac0f7ee85c9233"
dependencies = [
"serde_derive",
]
[[package]]
name = "serde_derive"
version = "1.0.197"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "7eb0b34b42edc17f6b7cac84a52a1c5f0e1bb2227e997ca9011ea3dd34e8610b"
dependencies = [
"proc-macro2",
"quote",
"syn",
]
[[package]]
name = "smol_str"
version = "0.1.24"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "fad6c857cbab2627dcf01ec85a623ca4e7dcb5691cbaa3d7fb7653671f0d09c9"
dependencies = [
"serde",
]
[[package]]
name = "syn"
version = "2.0.53"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "7383cd0e49fff4b6b90ca5670bfd3e9d6a733b3f90c686605aa7eec8c4996032"
dependencies = [
"proc-macro2",
"quote",
"unicode-ident",
]
[[package]]
name = "text_unit"
version = "0.1.10"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "20431e104bfecc1a40872578dbc390e10290a0e9c35fffe3ce6f73c15a9dbfc2"
[[package]]
name = "thin-dst"
version = "1.1.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "db3c46be180f1af9673ebb27bc1235396f61ef6965b3fe0dbb2e624deb604f0e"
[[package]]
name = "unicode-ident"
version = "1.0.12"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "3354b9ac3fae1ff6755cb6db53683adb661634f67557942dea4facebec0fee4b"

6
lix-doc/Cargo.toml
View file

@ -1,6 +1,6 @@
[package] [package]
description = "Nix function documentation tool, stripped down into a library" description = "Nix function documentation tool, stripped down into a library"
edition = "2018" edition = "2021"
name = "lix-doc" name = "lix-doc"
version = "0.0.1" version = "0.0.1"
license = "BSD-2-Clause OR MIT" license = "BSD-2-Clause OR MIT"
@ -12,7 +12,9 @@ repository = "https://github.com/lf-/nix-doc"
crate_type = ["staticlib"] crate_type = ["staticlib"]
[dependencies] [dependencies]
rnix = "0.8.0" rnix = "0.11.0"
# Necessary because rnix fails to export a critical trait (Rowan's AstNode).
rowan = "0.15.0"
[dev-dependencies] [dev-dependencies]
expect-test = "1.1.0" expect-test = "1.1.0"

431
lix-doc/src/lib.rs
View file

@ -1,5 +1,5 @@
// SPDX-FileCopyrightText: 2024 Jade Lovelace // SPDX-FileCopyrightText: 2024 Jade Lovelace
// // SPDX-FileCopyrightText: 2024 Lunaphied
// SPDX-License-Identifier: BSD-2-Clause OR MIT // SPDX-License-Identifier: BSD-2-Clause OR MIT
//! library components of nix-doc //! library components of nix-doc
@ -7,13 +7,16 @@ pub mod pprint;
use crate::pprint::pprint_args; use crate::pprint::pprint_args;
use rnix::types::{Lambda, TypedNode}; use rnix::ast::{self, Lambda};
use rnix::SyntaxKind::*; use rnix::{NodeOrToken, SyntaxKind};
use rnix::{NodeOrToken, SyntaxNode, TextUnit, WalkEvent}; use rnix::SyntaxNode;
// Needed because rnix fucked up and didn't reexport this, oops.
use rowan::ast::AstNode;
use std::ffi::{CStr, CString}; use std::ffi::{CStr, CString};
use std::fs; use std::fs;
use std::iter;
use std::os::raw::c_char; use std::os::raw::c_char;
use std::panic; use std::panic;
@ -23,66 +26,104 @@ use std::{fmt::Display, str};
pub type Result<T> = std::result::Result<T, Box<dyn std::error::Error>>; pub type Result<T> = std::result::Result<T, Box<dyn std::error::Error>>;
const DOC_INDENT: usize = 3;
struct SearchResult { struct SearchResult {
/// Name of the function /// Name of the function
identifier: String, identifier: String,
/// Dedented documentation comments /// Dedented documentation comment
doc: String, doc: String,
/// Parameter block for the function /// Parameter block for the function
param_block: String, param_block: String,
} }
fn find_pos(file: &str, line: usize, col: usize) -> usize {
let mut lines = 1;
let mut line_start = 0;
let mut it = file.chars().enumerate().peekable();
while let Some((count, ch)) = it.next() {
if ch == '\n' || ch == '\r' {
lines += 1;
let addend = if ch == '\r' && it.peek().map(|x| x.1) == Some('\n') {
it.next();
1
} else {
0
};
line_start = count + addend;
}
let col_diff = ((count as i32) - (line_start as i32)).abs() as usize;
if lines == line && col_diff == col {
return count;
}
}
unreachable!();
}
impl SearchResult { impl SearchResult {
fn format<P: Display>(&self, filename: P, line: usize) -> String { fn format<P: Display>(&self, filename: P, line: usize) -> String {
format!( format!(
"**Synopsis:** `{}` = {}\n\n{}\n\n# {}", "**Synopsis:** `{}` = {}\n\n{}\n\n# {}",
self.identifier.as_str(), self.identifier.as_str(),
self.param_block, self.param_block,
indented(&self.doc, DOC_INDENT), self.doc,
format!("{}:{}", filename, line).as_str(), format!("{}:{}", filename, line).as_str(),
) )
} }
} }
/// Emits a string `s` indented by `indent` spaces /// Converts Nix compatible line endings (Nix accepts `\r`, `\n`, *and* `\r\n` as endings), to
fn indented(s: &str, indent: usize) -> String { /// standard `\n` endings for use within Rust land.
let indent_s = iter::repeat(' ').take(indent).collect::<String>(); fn convert_endings(s: &str) -> String {
s.split('\n') let mut out = String::with_capacity(s.len());
.map(|line| indent_s.clone() + line) let mut it = s.chars().peekable();
.collect::<Vec<_>>()
.join("\n") while let Some(ch) = it.next() {
if ch == '\n' || ch == '\r' {
out.push('\n');
if ch == '\r' && it.peek().map(|&c| c == '\n').unwrap_or(false) {
// Consume `\n` in `\r\n`.
it.next();
}
} else {
out.push(ch);
}
}
out
}
/// Converts the position information from Lix itself into an character index into the file itself.
/// Expects an input string that's already had it's line endings normalized.
///
/// Note that this returns a *byte* offset, not a character offset.
fn find_pos(s: &str, line: usize, col: usize) -> usize {
// Nix line positions are 1-indexed.
let mut lines = 1;
for (byte_pos, ch) in s.char_indices() {
// If we find a newline, increase the line count.
if ch == '\n' {
lines += 1;
}
// We've arrived at the correct line.
if lines == line {
// Column position is 1-indexed, and it's a *byte* offset, because Nix doesn't actually
// support UTF-8. Rust does though, so we need to convert to a proper byte index to
// match rnix. Lix also doesn't consider the line endings part of the column offset so
// we implicitly add one to advance to the character *after* that.
return byte_pos + col;
}
}
// If things never match that should be literally impossible.
unreachable!();
}
/// Represents a forwarded token from rnix's AST over to lix-doc.
#[derive(Debug, Clone)]
enum DocToken {
Comment(String),
Whitespace(String),
}
/// Determine if a given token string contains more than two newlines, this is used to determine when
/// we hit blank lines between comments indicating a contextually unrelated comment.
fn has_empty_line(tok: &DocToken) -> bool {
// It's either solely whitespace with two newlines inside somewhere, or it's
// contained inside a comment token and we don't want to count that as empty.
if let DocToken::Whitespace(s) = tok {
s.chars().filter(|&c| c == '\n').take(2).count() == 2
} else {
false
}
} }
/// Cleans up a single line, erasing prefix single line comments but preserving indentation /// Cleans up a single line, erasing prefix single line comments but preserving indentation
fn cleanup_single_line<'a>(s: &'a str) -> &'a str { // NOTE: We have a bit of a conflict of interest problem here due to the inconsistent format of
// doc comments. Some doc comments will use a series of single line comments that may then contain `*`
// characters to represent a list. Some will be multiline comments that don't prefix individual lines
// with `*`, only using them for lists directly, and some will prefix lines with `*` as a leading
// character to mark the block. There's no way to disambiguate all three, but we do our best to
// make the common case pretty.
fn cleanup_single_line(s: &str) -> &str {
let mut cmt_new_start = 0; let mut cmt_new_start = 0;
let mut iter = s.char_indices().peekable(); let mut iter = s.char_indices().peekable();
while let Some((idx, ch)) = iter.next() { while let Some((idx, ch)) = iter.next() {
@ -90,7 +131,9 @@ fn cleanup_single_line<'a>(s: &'a str) -> &'a str {
let (_, next_ch) = iter.peek().unwrap_or(&(0, '\n')); let (_, next_ch) = iter.peek().unwrap_or(&(0, '\n'));
// if we find a character, save the byte position after it as our new string start // if we find a character, save the byte position after it as our new string start
if ch == '#' || (ch == '*' && next_ch.is_whitespace()) { // This has special handling for `>` because some Nixpkgs documentation has `*>` right
// after the start of their doc comments, and we want to strip the `*` still.
if ch == '#' || (ch == '*' && (*next_ch == '>' || next_ch.is_whitespace())) {
cmt_new_start = idx + 1; cmt_new_start = idx + 1;
break; break;
} }
@ -103,15 +146,12 @@ fn cleanup_single_line<'a>(s: &'a str) -> &'a str {
&s[cmt_new_start..] &s[cmt_new_start..]
} }
/// Erases indents in comments. This is *almost* a normal dedent function, but it starts by looking /// Erases indents in comments based on the indentation of the first line.
/// at the second line if it can.
fn dedent_comment(s: &str) -> String { fn dedent_comment(s: &str) -> String {
let mut whitespaces = 0; let mut whitespaces = 0;
let mut lines = s.lines();
let first = lines.next();
// scan for whitespace // scan for whitespace
for line in lines.chain(first) { for line in s.lines() {
let line_whitespace = line.chars().take_while(|ch| ch.is_whitespace()).count(); let line_whitespace = line.chars().take_while(|ch| ch.is_whitespace()).count();
if line_whitespace != line.len() { if line_whitespace != line.len() {
@ -121,16 +161,6 @@ fn dedent_comment(s: &str) -> String {
} }
} }
// maybe the first considered line we found was indented further, so let's look for more lines
// that might have a shorter indent. In the case of one line, do nothing.
for line in s.lines().skip(1) {
let line_whitespace = line.chars().take_while(|ch| ch.is_whitespace()).count();
if line_whitespace != line.len() {
whitespaces = line_whitespace.min(whitespaces);
}
}
// delete up to `whitespaces` whitespace characters from each line and reconstitute the string // delete up to `whitespaces` whitespace characters from each line and reconstitute the string
let mut out = String::new(); let mut out = String::new();
for line in s.lines() { for line in s.lines() {
@ -143,69 +173,163 @@ fn dedent_comment(s: &str) -> String {
out out
} }
/// Deletes whitespace and leading comment characters /// Takes a series of comment and whitespace strings and output a clean single block of text to use
/// as the output documentation comment block.
/// ///
/// Oversight we are choosing to ignore: if you put # characters at the beginning of lines in a /// This function expects to be given the tokens in reverse order (proceeding upwards from the
/// multiline comment, they will be deleted. /// first comment above the definitions), this allows us to properly enforce the below conditions.
fn cleanup_comments<S: AsRef<str>, I: DoubleEndedIterator<Item = S>>(comment: &mut I) -> String { /// The output from this function will be reordered and ready for display.
///
/// The two types of documentation comments we expect are:
///
/// - A single multiline comment not whitespace separated from the start.
/// - A series of back to back single line comments not separated by whitespace.
///
/// Any other combination will be filtered out.
///
/// Once an empty line is encountered, we know no more valid documentation comments remain and stop.
fn cleanup_comments<I: Iterator<Item = DocToken>>(tokens: &mut I) -> String {
// Keep track of when we've found a single line and multiline comment, we use this to
// only process a single multiline or back to back single lines.
let mut found_single_line = false;
// Comments that have survived our filtering phase and should be cleaned up.
let mut valid = vec![];
// Filter out comments that don't meet the characteristics of documentation comments.
for tok in tokens {
if has_empty_line(&tok) {
// Take tokens until we hit whitespace containing an empty line.
break;
}
// Only care about comments from this point on.
if let DocToken::Comment(comment) = tok {
// Now determine if it's a single line comment.
let is_single_line = comment.starts_with('#');
// We've found a single line comment if we've found one before or we just found one.
found_single_line |= is_single_line;
// What we do next is only special when we hit a multiline comment.
if !is_single_line {
// If we've hit a multiline comment as our first comment, take that one alone.
if !found_single_line {
// Otherwise we've hit a multiline comment immediately and this is our
// one and only doc comment to worry about.
valid.push(comment);
}
// Otherwise we've hit a multiline comment after single line comments, in either
// case this means we're done processing comments.
break;
}
// Otherwise this is a new single line comment to push to the stack.
valid.push(comment);
}
}
// Cleanup comments for user consumption.
dedent_comment( dedent_comment(
&comment &valid
.into_iter()
.rev() .rev()
.map(|small_comment| { .map(|small_comment| {
small_comment small_comment
.as_ref() // Trim off start of multiline comments.
// space before multiline start
.trim_start()
// multiline starts
.trim_start_matches("/*") .trim_start_matches("/*")
// trailing so we can grab multiline end // Trim off end of multiline comments.
.trim_end()
// multiline ends
.trim_end_matches("*/") .trim_end_matches("*/")
// extra space that was in the multiline // Trim off any internal whitespace that's trapped inside comments themselves.
.trim() .trim()
// Split comments by newlines to extract lines of multiline comments.
.split('\n') .split('\n')
// erase single line comments and such // Cleanup single line comments and a few more tweaks for multiline comments.
.map(cleanup_single_line) .map(cleanup_single_line)
.collect::<Vec<_>>() .collect::<Vec<_>>()
// Reconstruct the multiline comment's whitespace.
.join("\n") .join("\n")
}) })
.collect::<Vec<_>>() .collect::<Vec<_>>()
.join("\n"), // We've found that when multiple back to back single line comments are used in Nixpkgs,
// they make more sense to represent as if someone inserted line breaks into the Markdown
// properly, so we join them with linebreaks that markdown will pass through.
.join("\n\n"),
) )
} }
/// Get the docs for a specific function /// Get the docs for a specific function.
// TODO: Improve error reporting?
pub fn get_function_docs(filename: &str, line: usize, col: usize) -> Option<String> { pub fn get_function_docs(filename: &str, line: usize, col: usize) -> Option<String> {
let content = fs::read(filename).ok()?; let content = fs::read(filename).ok()?;
let decoded = str::from_utf8(&content).ok()?; let decoded = convert_endings(str::from_utf8(&content).ok()?);
let pos = find_pos(&decoded, line, col); let pos = find_pos(&decoded, line, col);
let rowan_pos = TextUnit::from_usize(pos); let rowan_pos = rnix::TextSize::from(pos as u32);
let tree = rnix::parse(decoded);
// The minimum length of a lambda is 4 characters and thus the range we're looking for must be
// at least 4 characters long `_: 3` being an example of a minimal length lambda.
let rowan_range = rnix::TextRange::at(rowan_pos, 4.into());
// Parse the file using rnix.
let root = rnix::Root::parse(&decoded).ok().ok()?;
// Extract the inner expression that represents the Root node and extract the top level expression.
let expr = root.expr()?;
// There are two cases we have to be able to handle
// 1. A straightforward definition with an attrset binding to a lambda that's defined inline.
// 2. A lambda defined in a standalone file where the attrset binding imports that file directly.
// The latter case will not be able to find the binding so we must be able to handle not finding it.
// Find the deepest node or token that covers the position given by Lix.
let covering = expr.syntax().covering_element(rowan_range);
// Climb up until we find the lambda node that contains that token.
let mut lambda = None; let mut lambda = None;
for node in tree.node().preorder() { for ancestor in covering.ancestors() {
match node { if ancestor.kind() == SyntaxKind::NODE_LAMBDA {
WalkEvent::Enter(n) => { lambda = Some(ancestor);
if n.text_range().start() >= rowan_pos && n.kind() == NODE_LAMBDA {
lambda = Lambda::cast(n);
break; break;
} }
} }
WalkEvent::Leave(_) => (),
// There is literally always a lambda or something has gone very very wrong.
let lambda =
ast::Lambda::cast(
lambda.expect("no lambda found; what.")
) .expect("not a rnix::ast::Lambda; what.");
// Search up, hopefully to find the binding so we can get the identifier name.
// TODO: Just provide this directly from the C++ code to make it possible to always have the correct identifier.
let mut binding = None;
for ancestor in lambda.syntax().ancestors() {
if ancestor.kind() == SyntaxKind::NODE_ATTRPATH_VALUE {
binding = Some(ancestor);
} }
} }
let lambda = lambda?;
let res = visit_lambda("func".to_string(), &lambda); // Convert the binding to an identifier if it was found, otherwise use a placeholder.
Some(res.format(filename, line)) let identifier;
identifier = match binding.clone() {
Some(binding) => ast::AttrpathValue::cast(binding)
.expect("not an rnix::ast::AttrpathValue; what")
.attrpath()
.expect("AttrpathValue has no attrpath; what.")
.to_string(),
_ => "<unknown binding>".to_string(),
};
// Find all the comments on the binding or the lambda if we have to fall back.
let comment_node = binding.as_ref().unwrap_or(lambda.syntax());
let comment = find_comment(comment_node).unwrap_or_else(String::new);
// And display them properly for the markdown function in Lix.
Some(visit_lambda(identifier, comment, &lambda).format(filename, line))
} }
fn visit_lambda(name: String, lambda: &Lambda) -> SearchResult { fn visit_lambda(name: String, comment: String, lambda: &Lambda) -> SearchResult {
// grab the arguments // grab the arguments
let param_block = pprint_args(&lambda); let param_block = pprint_args(lambda);
// find the doc comment
let comment = find_comment(lambda.node().clone()).unwrap_or_else(|| "".to_string());
SearchResult { SearchResult {
identifier: name, identifier: name,
@ -214,39 +338,47 @@ fn visit_lambda(name: String, lambda: &Lambda) -> SearchResult {
} }
} }
fn find_comment(node: SyntaxNode) -> Option<String> { fn find_comment(node: &SyntaxNode) -> Option<String> {
let mut node = NodeOrToken::Node(node); let mut it = node
let mut comments = Vec::new(); .siblings_with_tokens(rowan::Direction::Prev)
loop { // Skip ourselves as we're always the first token returned.
loop { .skip(1)
if let Some(new) = node.prev_sibling_or_token() { .peekable();
node = new;
break; // Consume up to one whitespace token before the first comment. There might not always be
} else { // whitespace such as the (rather unusual) case of `/* meow */x = a: 3`.
node = NodeOrToken::Node(node.parent()?); if matches!(it.peek(), Some(NodeOrToken::Token(token)) if token.kind() == SyntaxKind::TOKEN_WHITESPACE) {
} it.next();
} }
match node.kind() { let comments = it.map_while(|element| match element {
TOKEN_COMMENT => match &node { NodeOrToken::Token(token) => {
NodeOrToken::Token(token) => comments.push(token.text().clone()), match token.kind() {
NodeOrToken::Node(_) => unreachable!(), // Map the tokens we're interested in to our internal token type.
}, SyntaxKind::TOKEN_COMMENT => Some(DocToken::Comment(token.text().to_owned())),
// This stuff is found as part of `the-fn = f: ...` SyntaxKind::TOKEN_WHITESPACE => {
// here: ^^^^^^^^ Some(DocToken::Whitespace(token.text().to_owned()))
NODE_KEY | TOKEN_ASSIGN => (), }
t if t.is_trivia() => (), // If we hit a different token type, we know we've gone past relevant comments
_ => break, // and should stop.
_ => None,
} }
} }
let doc = cleanup_comments(&mut comments.iter().map(|c| c.as_str())); // If we hit a node entry we've definitely gone past comments that would be related to
Some(doc).filter(|it| !it.is_empty()) // this node and we should retreat.
_ => None,
});
// For the curious, `into_iter()` here consumes the binding producing an owned value allowing us to avoid
// making the original binding mutable, we don't reuse it later so this is a cute way to handle it, though
// there's probably a better way we just can't remember.
Some(cleanup_comments(&mut comments.into_iter())).filter(|c| !c.is_empty())
} }
/// Get the docs for a function in the given file path at the given file position and return it as /// Get the docs for a function in the given file path at the given file position and return it as
/// a C string pointer /// a C string pointer
#[no_mangle] #[no_mangle]
pub extern "C" fn nd_get_function_docs( pub extern "C" fn lixdoc_get_function_docs(
filename: *const c_char, filename: *const c_char,
line: usize, line: usize,
col: usize, col: usize,
@ -269,9 +401,9 @@ pub extern "C" fn nd_get_function_docs(
.unwrap_or(ptr::null()) .unwrap_or(ptr::null())
} }
/// Call this to free a string from nd_get_function_docs /// Call this to free a string from `lixdoc_get_function_docs`.
#[no_mangle] #[no_mangle]
pub extern "C" fn nd_free_string(s: *const c_char) { pub extern "C" fn lixdoc_free_string(s: *const c_char) {
unsafe { unsafe {
// cast note: this cast is turning something that was cast to const // cast note: this cast is turning something that was cast to const
// back to mut // back to mut
@ -283,35 +415,57 @@ pub extern "C" fn nd_free_string(s: *const c_char) {
mod tests { mod tests {
use super::*; use super::*;
#[test]
fn test_line_conversion() {
let fakefile = "abc\rdef\r\nghi";
assert_eq!(convert_endings(fakefile), "abc\ndef\nghi");
}
#[test] #[test]
fn test_bytepos() { fn test_bytepos() {
let fakefile = "abc\ndef\nghi"; let fakefile = "abc\ndef\nghi";
assert_eq!(find_pos(fakefile, 2, 2), 5); assert_eq!(find_pos(fakefile, 2, 2), 5);
} }
#[test]
fn test_bytepos_unusual() {
let fakefile = convert_endings("abc\rdef\r\nghi");
assert_eq!(find_pos(&fakefile, 2, 2), 5);
assert_eq!(find_pos(&fakefile, 3, 2), 9);
}
/// This test is to check that we correctly resolve byte positions even when inconsistent with
/// character positions.
#[test] #[test]
fn test_bytepos_cursed() { fn test_bytepos_cursed() {
let fakefile = "abc\rdef\r\nghi"; let fakefile = "hello\nwórld";
assert_eq!(find_pos(fakefile, 2, 2), 5); // Try to find the position of the `r` after world, which will be wrong if we don't handle
assert_eq!(find_pos(fakefile, 3, 2), 10); // UTF-8 properly.
let pos = find_pos(&fakefile, 2, 4);
dbg!(&fakefile[pos..]);
assert_eq!(pos, 9)
} }
#[test] #[test]
fn test_comment_stripping() { fn test_comment_stripping() {
let ex1 = ["/* blah blah blah\n foooo baaar\n blah */"]; let ex1 = [DocToken::Comment(
"/* blah blah blah\n foooo baaar\n blah */".to_string(),
)];
assert_eq!( assert_eq!(
cleanup_comments(&mut ex1.iter()), cleanup_comments(&mut ex1.into_iter()),
"blah blah blah\n foooo baaar\nblah" "blah blah blah\n foooo baaar\n blah"
); );
let ex2 = ["# a1", "# a2", "# aa"]; let ex2 = ["# a1", "# a2", "# aa"]
assert_eq!(cleanup_comments(&mut ex2.iter()), "aa\n a2\na1"); .into_iter()
.map(|s| DocToken::Comment(s.to_string()));
assert_eq!(cleanup_comments(&mut ex2.into_iter()), "aa\n\n a2\n\na1");
} }
#[test] #[test]
fn test_dedent() { fn test_dedent() {
let ex1 = "a\n b\n c\n d"; let ex1 = "a\n b\n c\n d";
assert_eq!(dedent_comment(ex1), "a\nb\nc\n d"); assert_eq!(dedent_comment(ex1), ex1);
let ex2 = "a\nb\nc"; let ex2 = "a\nb\nc";
assert_eq!(dedent_comment(ex2), ex2); assert_eq!(dedent_comment(ex2), ex2);
let ex3 = " a\n b\n\n c"; let ex3 = " a\n b\n\n c";
@ -335,4 +489,31 @@ mod tests {
let ex1 = " **Foo**:"; let ex1 = " **Foo**:";
assert_eq!(cleanup_single_line(ex1), ex1); assert_eq!(cleanup_single_line(ex1), ex1);
} }
// TODO: Next CL
//#[test]
//fn comment_test_complex() {
// let testcase = r#"
// rec {
// /*
// Hello
// 23
// This is a comment.
// this is another comment.
// and this is a third comment.
// Way
// go
// */
// meow = { g }: {a, b ? 4, ...}: g: c: 5;
// # And another comment.
// cat = 34;
// # inner layer.
// "inner-layer" = outer: meow;
// }
// "#;
// // Need to find the location of the lambda, we do a quick hack.
// let location = dbg!(testcase.find("{ g }").unwrap() as u32);
//
// //get_function_docs(filename, line, col)
//}
} }

61
lix-doc/src/pprint.rs
View file

@ -1,38 +1,61 @@
// SPDX-FileCopyrightText: 2024 Jade Lovelace // SPDX-FileCopyrightText: 2024 Jade Lovelace
// // SPDX-FileCopyrightText: 2024 Lunaphied
// SPDX-License-Identifier: BSD-2-Clause OR MIT // SPDX-License-Identifier: BSD-2-Clause OR MIT
use rnix::types::{Lambda, TypedNode}; use rnix::ast::{Expr, Lambda};
use rnix::SyntaxKind::*; use rowan::ast::AstNode;
/// Pretty-prints the arguments to a function /// Pretty-prints the arguments to a function
pub fn pprint_args(lambda: &Lambda) -> String { pub fn pprint_args(lambda: &Lambda) -> String {
// TODO: handle docs directly on NODE_IDENT args (uncommon case) // TODO: handle docs directly on NODE_IDENT args (uncommon case)
let mut lambda = lambda.clone(); let mut lambda = lambda.clone();
let mut depth = 0;
let mut out = String::new(); let mut out = String::new();
loop { loop {
let arg = lambda.arg().unwrap(); let arg = lambda.param().unwrap();
match arg.kind() { for child in arg.syntax().children_with_tokens() {
NODE_IDENT => { //dbg!(child.kind());
out += &format!("*{}*", &arg.to_string()); match child {
rowan::NodeOrToken::Node(node) => {
out.push_str(&node.text().to_string());
if node.kind() == rnix::SyntaxKind::NODE_PAT_ENTRY {
out.push_str(&",\n");
}
}
rowan::NodeOrToken::Token(token) => {
use rnix::SyntaxKind::{
TOKEN_COMMENT, TOKEN_ELLIPSIS, TOKEN_L_BRACE, TOKEN_QUESTION, TOKEN_R_BRACE,
};
match token.kind() {
TOKEN_COMMENT | TOKEN_ELLIPSIS | TOKEN_QUESTION | TOKEN_L_BRACE
| TOKEN_R_BRACE => {
//dbg!(&token);
out.push_str(&token.text().to_string());
if token.kind() == TOKEN_COMMENT {
out.push('\n');
}
}
_ => {}
}
//out.push_str(&token.text().to_string());
}
}
}
out.push_str(": "); out.push_str(": ");
let body = lambda.body().unwrap(); let body = lambda.body().unwrap();
if body.kind() == NODE_LAMBDA { if let Expr::Lambda(inner) = body {
lambda = Lambda::cast(body).unwrap(); lambda = inner;
// If we recurse we want the next line of recursion to be indented and on a new line.
out.push('\n');
for _ in 0..=depth {
out.push('\t');
}
depth += 1;
} else { } else {
// If we don't find an inner lambda we're done with argument handling.
break; break;
} }
} }
NODE_PATTERN => {
out += &format!("*{}*", &arg.to_string());
out.push_str(": ");
break;
}
t => {
unreachable!("unhandled arg type {:?}", t);
}
}
}
out.push_str("..."); out.push_str("...");
out out

8
package.nix
View file

@ -474,6 +474,14 @@ stdenv.mkDerivation (finalAttrs: {
# Load-bearing order. Must come before clang-unwrapped below, but after clang_tools above. # Load-bearing order. Must come before clang-unwrapped below, but after clang_tools above.
stdenv.cc stdenv.cc
] ]
++ [
pkgs.rust-analyzer
pkgs.cargo
pkgs.rustc
pkgs.rustfmt
pkgs.rustPlatform.rustLibSrc
pkgs.rustPlatform.rustcSrc
]
++ lib.optionals stdenv.cc.isClang [ ++ lib.optionals stdenv.cc.isClang [
# Required for clang-tidy checks. # Required for clang-tidy checks.
llvmPackages.llvm llvmPackages.llvm

10
src/libcmd/repl.cc
View file

@ -40,24 +40,24 @@
#include <gc/gc_cpp.h> #include <gc/gc_cpp.h>
#endif #endif
// XXX: These are for nix-doc features and will be removed in a future rewrite where this functionality is integrated more natively. // XXX: These are for lix-doc features and will be removed in a future rewrite where this functionality is integrated more natively.
extern "C" { extern "C" {
char const *nd_get_function_docs(char const *filename, size_t line, size_t col); char const *lixdoc_get_function_docs(char const *filename, size_t line, size_t col);
void nd_free_string(char const *str); void lixdoc_free_string(char const *str);
} }
namespace nix { namespace nix {
/** Wrapper around std::unique_ptr with a custom deleter for strings from nix-doc **/ /** Wrapper around std::unique_ptr with a custom deleter for strings from nix-doc **/
using NdString = std::unique_ptr<const char, decltype(&nd_free_string)>; using NdString = std::unique_ptr<const char, decltype(&lixdoc_free_string)>;
/** /**
* Fetch a string representing the doc comment using nix-doc and wrap it in an RAII wrapper. * Fetch a string representing the doc comment using nix-doc and wrap it in an RAII wrapper.
*/ */
NdString lambdaDocsForPos(SourcePath const path, nix::Pos const &pos) { NdString lambdaDocsForPos(SourcePath const path, nix::Pos const &pos) {
std::string const file = path.to_string(); std::string const file = path.to_string();
return NdString{nd_get_function_docs(file.c_str(), pos.line, pos.column), &nd_free_string}; return NdString{lixdoc_get_function_docs(file.c_str(), pos.line, pos.column), &lixdoc_free_string};
} }
/** /**