Point parser diagnostics at the offending name (#7742)

When the unquoted-identifier parser finishes, require that the next char
is a real word-boundary (not another identifier char and not another
'-'). Otherwise the caller wrote something like `pubKeyHash-305478r71`,
`foo-bar` or `foo-123-456`: the '-NNN' we just consumed as the numeric
unique-suffix is not actually terminal, and the prefix interpretation
would silently mis-parse. Consume the remainder of the extended
identifier so the diagnostic can cite the full bad text, then raise a
new `InvalidIdentifier` custom parser error with a caret on the start
of the identifier and an actionable hint to quote it with backticks.

For the original Scalus 0.16.0 HTLC reproducer this changes the error
from `htlc.uplc:448:39: unexpected '(' expecting ')'` (on a lambda 8+
chars past the real site) to `htlc.uplc:447:41: Invalid identifier
'pubKeyHash-305478r71'` — on the offending name itself.

The three negative goldens added in the previous commit are updated to
the new message; all 3886 tests across plutus-core/untyped-plutus-core/
plutus-ir pass unchanged.

Author: Unisay

plutus-core/changelog.d/20260424_182803_yuriy.lazaryev_issue_7742_uplc_parser_large_case.md

@@ -0,0 +1,12 @@
+### Changed
+
+- The UPLC/PLC/PIR textual parser now rejects unquoted identifiers that
+  contain a `-` anywhere other than as the terminal numeric unique-suffix
+  separator (e.g. `pubKeyHash-305478r71`, `foo-bar`, `foo-123-456`) with
+  a dedicated `InvalidIdentifier` diagnostic that points directly at the
+  offending name and shows the full bad text. Previously the same inputs
+  silently mis-parsed — the prefix was taken as a name plus unique-suffix
+  and the remainder was picked up as an adjacent term — which surfaced as
+  a confusing "unexpected '(' expecting ')'" message far from the real
+  site (see #7742). To use such a string as a name verbatim, wrap it in
+  backticks: `` `pubKeyHash-305478r71` ``.

plutus-core/plutus-core/src/PlutusCore/Error.hs

@@ -52,6 +52,12 @@ data ParserError
   = BuiltinTypeNotAStar !T.Text !SourcePos
   | UnknownBuiltinFunction !T.Text !SourcePos ![T.Text]
   | InvalidBuiltinConstant !T.Text !T.Text !SourcePos
+  | {-| An unquoted identifier that violates the grammar: a '-' appeared
+    anywhere other than as the separator of a terminal numeric unique-suffix
+    (e.g. @pubKeyHash-305478r71@, @foo-bar@, @foo-123-456@). The 'Text'
+    carries the full offending text as it appeared in the source, so the
+    user sees their own name back in the diagnostic. -}
+    InvalidIdentifier !T.Text !SourcePos
   deriving stock (Eq, Ord, Generic)
   deriving anyclass (NFData)
 
@@ -192,6 +198,18 @@ instance Pretty ParserError where
       <+> squotes (pretty s)
       <+> "at"
       <+> pretty loc
+  pretty (InvalidIdentifier txt loc) =
+    "Invalid identifier"
+      <+> squotes (pretty txt)
+      <+> "at"
+      <+> pretty loc
+      <> "."
+      <> hardline
+      <> "A '-' inside a name is the numeric unique-suffix separator and must be"
+      <+> "followed only by digits and a word boundary."
+      <> hardline
+      <> "To use this text as a name verbatim, quote it with backticks:"
+      <+> pretty ("`" <> txt <> "`")
 
 instance ShowErrorComponent ParserError where
   showErrorComponent = show . pretty

plutus-core/plutus-core/src/PlutusCore/Parser/ParserCommon.hs

@@ -13,6 +13,7 @@ import Control.Monad.Except
 import Control.Monad.Reader (ReaderT, ask, local, runReaderT)
 import Control.Monad.State (StateT, evalStateT)
 import Data.Map qualified as M
+import Data.Set qualified as Set
 import Data.Text (Text)
 import Data.Text qualified as Text
 import Text.Megaparsec hiding (ParseError, State, parse, some)
@@ -217,9 +218,33 @@ name = try $ parseUnquoted <|> parseQuoted
   where
     parseUnquoted :: Parser Name
     parseUnquoted = do
+      startOffset <- getOffset
+      startPos <- getSourcePos'
       _ <- lookAhead (satisfy isIdentifierStartingChar)
+      inputBefore <- getInput
       str <- takeWhileP (Just "identifier-unquoted") isIdentifierChar
-      Name str <$> uniqueSuffix str
+      u <- uniqueSuffix str
+      {- The parsed prefix is only a valid identifier if the next character is
+      a real word-boundary. If instead we see more identifier chars or another
+      '-', the user wrote something like `foo-bar` or `pubKeyHash-305478r71` —
+      the '-NNN' run we just treated as a unique-suffix was actually part of
+      their intended name (or they have a stray '-' at all). Fail with a
+      custom diagnostic that points at the whole offending identifier. -}
+      mBad <- optional (lookAhead (satisfy isNameExtensionChar))
+      case mBad of
+        Nothing -> pure (Name str u)
+        Just _ -> do
+          -- Consume the remainder so the reported text covers the full name.
+          _ <- takeWhileP Nothing isNameExtensionChar
+          inputAfter <- getInput
+          let consumed = Text.length inputBefore - Text.length inputAfter
+              fullText = Text.take consumed inputBefore
+          parseError $
+            FancyError startOffset $
+              Set.singleton (ErrorCustom (InvalidIdentifier fullText startPos))
+
+    isNameExtensionChar :: Char -> Bool
+    isNameExtensionChar c = isIdentifierChar c || c == '-'
 
     parseQuoted :: Parser Name
     parseQuoted = do

plutus-core/untyped-plutus-core/test/Parser/Golden/invalid-identifier-double-unique.golden

@@ -1,6 +1,7 @@
-test:1:28:
+test:1:21:
   |
 1 | (program 1.1.0 (lam foo-123-456 foo-123-456))
-  |                            ^
-unexpected '-'
-expecting '`', digit, opening bracket '[', or opening parenthesis '('
+  |                     ^
+Invalid identifier 'foo-123-456' at test:1:21.
+A '-' inside a name is the numeric unique-suffix separator and must be followed only by digits and a word boundary.
+To use this text as a name verbatim, quote it with backticks: `foo-123-456`

plutus-core/untyped-plutus-core/test/Parser/Golden/invalid-identifier-hyphen-letters.golden

@@ -1,6 +1,7 @@
-test:1:42:
+test:1:21:
   |
 1 | (program 1.1.0 (lam pubKeyHash-305478r71 (lam x x)))
-  |                                          ^
-unexpected '('
-expecting closing parenthesis ')'
+  |                     ^
+Invalid identifier 'pubKeyHash-305478r71' at test:1:21.
+A '-' inside a name is the numeric unique-suffix separator and must be followed only by digits and a word boundary.
+To use this text as a name verbatim, quote it with backticks: `pubKeyHash-305478r71`

plutus-core/untyped-plutus-core/test/Parser/Golden/invalid-identifier-hyphen-word.golden

@@ -1,6 +1,7 @@
-test:1:24:
+test:1:21:
   |
 1 | (program 1.1.0 (lam foo-bar foo-bar))
-  |                        ^
-unexpected '-'
-expecting '`', identifier-unquoted, opening bracket '[', or opening parenthesis '('
+  |                     ^
+Invalid identifier 'foo-bar' at test:1:21.
+A '-' inside a name is the numeric unique-suffix separator and must be followed only by digits and a word boundary.
+To use this text as a name verbatim, quote it with backticks: `foo-bar`