Rollup merge of rust-lang#69387 - petrochenkov:idprint, r=Mark-Simulacrum

Deduplicate identifier printing a bit

rust-lang#67010 introduced a couple more subtly different ways to print an identifier.
This PR attempts to restore the order.

The most basic identifier printing interface is `Formatter`-based now, so `String`s are not allocated unless required.

r? @Mark-Simulacrum

Author: Dylan-DPC

src/librustc_ast_pretty/pprust.rs

@@ -3,7 +3,7 @@ use crate::pp::{self, Breaks};
 
 use rustc_span::edition::Edition;
 use rustc_span::source_map::{SourceMap, Spanned};
-use rustc_span::symbol::{kw, sym};
+use rustc_span::symbol::{kw, sym, IdentPrinter};
 use rustc_span::{BytePos, FileName, Span};
 use syntax::ast::{self, BlockCheckMode, PatKind, RangeEnd, RangeSyntax};
 use syntax::ast::{Attribute, GenericArg, MacArgs};
@@ -196,40 +196,6 @@ pub fn literal_to_string(lit: token::Lit) -> String {
     out
 }
 
-/// Print an ident from AST, `$crate` is converted into its respective crate name.
-pub fn ast_ident_to_string(ident: ast::Ident, is_raw: bool) -> String {
-    ident_to_string(ident.name, is_raw, Some(ident.span))
-}
-
-// AST pretty-printer is used as a fallback for turning AST structures into token streams for
-// proc macros. Additionally, proc macros may stringify their input and expect it survive the
-// stringification (especially true for proc macro derives written between Rust 1.15 and 1.30).
-// So we need to somehow pretty-print `$crate` in a way preserving at least some of its
-// hygiene data, most importantly name of the crate it refers to.
-// As a result we print `$crate` as `crate` if it refers to the local crate
-// and as `::other_crate_name` if it refers to some other crate.
-// Note, that this is only done if the ident token is printed from inside of AST pretty-pringing,
-// but not otherwise. Pretty-printing is the only way for proc macros to discover token contents,
-// so we should not perform this lossy conversion if the top level call to the pretty-printer was
-// done for a token stream or a single token.
-fn ident_to_string(name: ast::Name, is_raw: bool, convert_dollar_crate: Option<Span>) -> String {
-    if is_raw {
-        format!("r#{}", name)
-    } else {
-        if name == kw::DollarCrate {
-            if let Some(span) = convert_dollar_crate {
-                let converted = span.ctxt().dollar_crate_name();
-                return if converted.is_path_segment_keyword() {
-                    converted.to_string()
-                } else {
-                    format!("::{}", converted)
-                };
-            }
-        }
-        name.to_string()
-    }
-}
-
 /// Print the token kind precisely, without converting `$crate` into its respective crate name.
 pub fn token_kind_to_string(tok: &TokenKind) -> String {
     token_kind_to_string_ext(tok, None)
@@ -280,7 +246,7 @@ fn token_kind_to_string_ext(tok: &TokenKind, convert_dollar_crate: Option<Span>)
         token::Literal(lit) => literal_to_string(lit),
 
         /* Name components */
-        token::Ident(s, is_raw) => ident_to_string(s, is_raw, convert_dollar_crate),
+        token::Ident(s, is_raw) => IdentPrinter::new(s, is_raw, convert_dollar_crate).to_string(),
         token::Lifetime(s) => s.to_string(),
 
         /* Other */
@@ -315,7 +281,7 @@ pub fn nonterminal_to_string(nt: &Nonterminal) -> String {
         token::NtBlock(ref e) => block_to_string(e),
         token::NtStmt(ref e) => stmt_to_string(e),
         token::NtPat(ref e) => pat_to_string(e),
-        token::NtIdent(e, is_raw) => ast_ident_to_string(e, is_raw),
+        token::NtIdent(e, is_raw) => IdentPrinter::for_ast_ident(e, is_raw).to_string(),
         token::NtLifetime(e) => e.to_string(),
         token::NtLiteral(ref e) => expr_to_string(e),
         token::NtTT(ref tree) => tt_to_string(tree.clone()),
@@ -819,7 +785,7 @@ impl<'a> PrintState<'a> for State<'a> {
     }
 
     fn print_ident(&mut self, ident: ast::Ident) {
-        self.s.word(ast_ident_to_string(ident, ident.is_raw_guess()));
+        self.s.word(IdentPrinter::for_ast_ident(ident, ident.is_raw_guess()).to_string());
         self.ann.post(self, AnnNode::Ident(&ident))
     }
 

src/librustc_hir/print.rs

@@ -1,8 +1,8 @@
 use rustc_ast_pretty::pp::Breaks::{Consistent, Inconsistent};
 use rustc_ast_pretty::pp::{self, Breaks};
-use rustc_ast_pretty::pprust::{self, Comments, PrintState};
+use rustc_ast_pretty::pprust::{Comments, PrintState};
 use rustc_span::source_map::{SourceMap, Spanned};
-use rustc_span::symbol::kw;
+use rustc_span::symbol::{kw, IdentPrinter};
 use rustc_span::{self, BytePos, FileName};
 use rustc_target::spec::abi::Abi;
 use syntax::ast;
@@ -126,7 +126,7 @@ impl<'a> PrintState<'a> for State<'a> {
     }
 
     fn print_ident(&mut self, ident: ast::Ident) {
-        self.s.word(pprust::ast_ident_to_string(ident, ident.is_raw_guess()));
+        self.s.word(IdentPrinter::for_ast_ident(ident, ident.is_raw_guess()).to_string());
         self.ann.post(self, AnnNode::Name(&ident.name))
     }
 

src/librustc_span/symbol.rs

@@ -893,19 +893,17 @@ impl Hash for Ident {
 
 impl fmt::Debug for Ident {
     fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
-        if self.is_raw_guess() {
-            write!(f, "r#")?;
-        }
-        write!(f, "{}{:?}", self.name, self.span.ctxt())
+        fmt::Display::fmt(self, f)?;
+        fmt::Debug::fmt(&self.span.ctxt(), f)
     }
 }
 
+/// This implementation is supposed to be used in error messages, so it's expected to be identical
+/// to printing the original identifier token written in source code (`token_to_string`),
+/// except that AST identifiers don't keep the rawness flag, so we have to guess it.
 impl fmt::Display for Ident {
     fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
-        if self.is_raw_guess() {
-            write!(f, "r#")?;
-        }
-        fmt::Display::fmt(&self.name, f)
+        fmt::Display::fmt(&IdentPrinter::new(self.name, self.is_raw_guess(), None), f)
     }
 }
 
@@ -929,6 +927,59 @@ impl UseSpecializedDecodable for Ident {
     }
 }
 
+/// This is the most general way to print identifiers.
+/// AST pretty-printer is used as a fallback for turning AST structures into token streams for
+/// proc macros. Additionally, proc macros may stringify their input and expect it survive the
+/// stringification (especially true for proc macro derives written between Rust 1.15 and 1.30).
+/// So we need to somehow pretty-print `$crate` in a way preserving at least some of its
+/// hygiene data, most importantly name of the crate it refers to.
+/// As a result we print `$crate` as `crate` if it refers to the local crate
+/// and as `::other_crate_name` if it refers to some other crate.
+/// Note, that this is only done if the ident token is printed from inside of AST pretty-pringing,
+/// but not otherwise. Pretty-printing is the only way for proc macros to discover token contents,
+/// so we should not perform this lossy conversion if the top level call to the pretty-printer was
+/// done for a token stream or a single token.
+pub struct IdentPrinter {
+    symbol: Symbol,
+    is_raw: bool,
+    /// Span used for retrieving the crate name to which `$crate` refers to,
+    /// if this field is `None` then the `$crate` conversion doesn't happen.
+    convert_dollar_crate: Option<Span>,
+}
+
+impl IdentPrinter {
+    /// The most general `IdentPrinter` constructor. Do not use this.
+    pub fn new(symbol: Symbol, is_raw: bool, convert_dollar_crate: Option<Span>) -> IdentPrinter {
+        IdentPrinter { symbol, is_raw, convert_dollar_crate }
+    }
+
+    /// This implementation is supposed to be used when printing identifiers
+    /// as a part of pretty-printing for larger AST pieces.
+    /// Do not use this either.
+    pub fn for_ast_ident(ident: Ident, is_raw: bool) -> IdentPrinter {
+        IdentPrinter::new(ident.name, is_raw, Some(ident.span))
+    }
+}
+
+impl fmt::Display for IdentPrinter {
+    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
+        if self.is_raw {
+            f.write_str("r#")?;
+        } else {
+            if self.symbol == kw::DollarCrate {
+                if let Some(span) = self.convert_dollar_crate {
+                    let converted = span.ctxt().dollar_crate_name();
+                    if !converted.is_path_segment_keyword() {
+                        f.write_str("::")?;
+                    }
+                    return fmt::Display::fmt(&converted, f);
+                }
+            }
+        }
+        fmt::Display::fmt(&self.symbol, f)
+    }
+}
+
 /// An interned string.
 ///
 /// Internally, a `Symbol` is implemented as an index, and all operations