summaryrefslogtreecommitdiff
path: root/compiler/rustc_parse_format
diff options
context:
space:
mode:
authorNilstrieb <48135649+Nilstrieb@users.noreply.github.com>2023-01-05 20:17:30 +0100
committerNilstrieb <48135649+Nilstrieb@users.noreply.github.com>2023-03-14 13:16:52 +0000
commit729185338f1726f60ea2dc282fe6bbf0eb84cb17 (patch)
treee84828d0610ea806f017a1ba76014199c180e8f0 /compiler/rustc_parse_format
parent0058748944abb3282aba0e0a74823c6411703565 (diff)
downloadrust-729185338f1726f60ea2dc282fe6bbf0eb84cb17.tar.gz
Properly allow macro expanded `format_args` invocations to uses captures
Originally, this was kinda half-allowed. There were some primitive checks in place that looked at the span to see whether the input was likely a literal. These "source literal" checks are needed because the spans created during `format_args` parsing only make sense when it is indeed a literal that was written in the source code directly. This is orthogonal to the restriction that the first argument must be a "direct literal", not being exanpanded from macros. This restriction was imposed by [RFC 2795] on the basis of being too confusing. But this was only concerned with the argument of the invocation being a literal, not whether it was a source literal (maybe in spirit it meant it being a source literal, this is not clear to me). Since the original check only really cared about source literals (which is good enough to deny the `format_args!(concat!())` example), macros expanding to `format_args` invocations were able to use implicit captures if they spanned the string in a way that lead back to a source string. The "source literal" checks were not strict enough and caused ICEs in certain cases (see # 106191 (the space is intended to avoid spammy backreferences)). So I tightened it up in # 106195 to really only work if it's a direct source literal. This caused the `indoc` crate to break. `indoc` transformed the source literal by removing whitespace, which made it not a "source literal" anymore (which is required to fix the ICE). But since `indoc` spanned the literal in ways that made the old check think that it's a literal, it was able to use implicit captures (which is useful and nice for the users of `indoc`). This commit properly seperates the previously introduced concepts of "source literal" and "direct literal" and therefore allows `indoc` invocations, which don't create "source literals" to use implicit captures again. [RFC 2795]: https://rust-lang.github.io/rfcs/2795-format-args-implicit-identifiers.html#macro-hygiene
Diffstat (limited to 'compiler/rustc_parse_format')
-rw-r--r--compiler/rustc_parse_format/src/lib.rs18
1 files changed, 10 insertions, 8 deletions
diff --git a/compiler/rustc_parse_format/src/lib.rs b/compiler/rustc_parse_format/src/lib.rs
index 8a3cedfee79..d67239efa80 100644
--- a/compiler/rustc_parse_format/src/lib.rs
+++ b/compiler/rustc_parse_format/src/lib.rs
@@ -234,8 +234,10 @@ pub struct Parser<'a> {
last_opening_brace: Option<InnerSpan>,
/// Whether the source string is comes from `println!` as opposed to `format!` or `print!`
append_newline: bool,
- /// Whether this formatting string is a literal or it comes from a macro.
- pub is_literal: bool,
+ /// Whether this formatting string was written directly in the source. This controls whether we
+ /// can use spans to refer into it and give better error messages.
+ /// N.B: This does _not_ control whether implicit argument captures can be used.
+ pub is_source_literal: bool,
/// Start position of the current line.
cur_line_start: usize,
/// Start and end byte offset of every line of the format string. Excludes
@@ -262,7 +264,7 @@ impl<'a> Iterator for Parser<'a> {
} else {
let arg = self.argument(lbrace_end);
if let Some(rbrace_pos) = self.must_consume('}') {
- if self.is_literal {
+ if self.is_source_literal {
let lbrace_byte_pos = self.to_span_index(pos);
let rbrace_byte_pos = self.to_span_index(rbrace_pos);
@@ -302,7 +304,7 @@ impl<'a> Iterator for Parser<'a> {
_ => Some(String(self.string(pos))),
}
} else {
- if self.is_literal {
+ if self.is_source_literal {
let span = self.span(self.cur_line_start, self.input.len());
if self.line_spans.last() != Some(&span) {
self.line_spans.push(span);
@@ -323,7 +325,7 @@ impl<'a> Parser<'a> {
mode: ParseMode,
) -> Parser<'a> {
let input_string_kind = find_width_map_from_snippet(snippet, style);
- let (width_map, is_literal) = match input_string_kind {
+ let (width_map, is_source_literal) = match input_string_kind {
InputStringKind::Literal { width_mappings } => (width_mappings, true),
InputStringKind::NotALiteral => (Vec::new(), false),
};
@@ -339,7 +341,7 @@ impl<'a> Parser<'a> {
width_map,
last_opening_brace: None,
append_newline,
- is_literal,
+ is_source_literal,
cur_line_start: 0,
line_spans: vec![],
}
@@ -532,13 +534,13 @@ impl<'a> Parser<'a> {
'{' | '}' => {
return &self.input[start..pos];
}
- '\n' if self.is_literal => {
+ '\n' if self.is_source_literal => {
self.line_spans.push(self.span(self.cur_line_start, pos));
self.cur_line_start = pos + 1;
self.cur.next();
}
_ => {
- if self.is_literal && pos == self.cur_line_start && c.is_whitespace() {
+ if self.is_source_literal && pos == self.cur_line_start && c.is_whitespace() {
self.cur_line_start = pos + c.len_utf8();
}
self.cur.next();