Distinguish the two kinds of token range.

When collecting tokens there are two kinds of range:
- a range relative to the parser's full token stream (which we get when
  we are parsing);
- a range relative to a single AST node's token stream (which we use
  within `LazyAttrTokenStreamImpl` when replacing tokens).

These are currently both represented with `Range<u32>` and it's easy to
mix them up -- until now I hadn't properly understood the difference.

This commit introduces `ParserRange` and `NodeRange` to distinguish
them. This also requires splitting `ReplaceRange` in two, giving the new
types `ParserReplacement` and `NodeReplacement`. (These latter two names
reduce the overloading of the word "range".)

The commit also rewrites some comments to be clearer.

The end result is a little more verbose, but much clearer.

compiler/rustc_parse/src/parser/attr.rs

@@ -8,7 +8,7 @@ use rustc_span::{sym, BytePos, Span};
 use thin_vec::ThinVec;
 use tracing::debug;
 
-use super::{AttrWrapper, Capturing, FnParseMode, ForceCollect, Parser, PathStyle};
+use super::{AttrWrapper, Capturing, FnParseMode, ForceCollect, Parser, ParserRange, PathStyle};
 use crate::{errors, fluent_generated as fluent, maybe_whole};
 
 // Public for rustfmt usage
@@ -307,8 +307,8 @@ impl<'a> Parser<'a> {
                 // inner attribute, for possible later processing in a `LazyAttrTokenStream`.
                 if let Capturing::Yes = self.capture_state.capturing {
                     let end_pos = self.num_bump_calls;
-                    let range = start_pos..end_pos;
-                    self.capture_state.inner_attr_ranges.insert(attr.id, range);
+                    let parser_range = ParserRange(start_pos..end_pos);
+                    self.capture_state.inner_attr_parser_ranges.insert(attr.id, parser_range);
                 }
                 attrs.push(attr);
             } else {