GH-98831: Identify instructions that don't use oparg (#100957)

For these the instr_format field uses IX instead of IB.
Register instructions use IX, IB, IBBX, IBBB, etc.

Also: Include the closing '}' in Block.tokens, for completeness

2 files changed, 13 insertions, 3 deletions

diff --git a/Tools/cases_generator/generate_cases.py b/Tools/cases_generator/generate_cases.py
index 608df6b..4bd99b7 100644
--- a/Tools/cases_generator/generate_cases.py
+++ b/Tools/cases_generator/generate_cases.py
@@ -168,9 +168,14 @@ class Instruction:
                 break
         self.unmoved_names = frozenset(unmoved_names)
         if self.register:
-            fmt = "IBBB"
+            num_regs = len(self.input_effects) + len(self.output_effects)
+            num_dummies = (num_regs // 2) * 2 + 1 - num_regs
+            fmt = "I" + "B"*num_regs + "X"*num_dummies
         else:
-            fmt = "IB"
+            if variable_used(inst.block, "oparg"):
+                fmt = "IB"
+            else:
+                fmt = "IX"
         cache = "C"
         for ce in self.cache_effects:
             for _ in range(ce.size):
@@ -894,6 +899,11 @@ def always_exits(lines: list[str]) -> bool:
     )
 
 
+def variable_used(block: parser.Block, name: str) -> bool:
+    """Determine whether a variable with a given name is used in a block."""
+    return any(token.kind == "IDENTIFIER" and token.text == name for token in block.tokens)
+
+
 def main():
     """Parse command line, parse input, analyze, write output."""
     args = arg_parser.parse_args()  # Prints message and sys.exit(2) on error
diff --git a/Tools/cases_generator/parser.py b/Tools/cases_generator/parser.py
index 4885394..fad0cb9 100644
--- a/Tools/cases_generator/parser.py
+++ b/Tools/cases_generator/parser.py
@@ -338,13 +338,13 @@ class Parser(PLexer):
         tokens: list[lx.Token] = []
         level = 0
         while tkn := self.next(raw=True):
+            tokens.append(tkn)
             if tkn.kind in (lx.LBRACE, lx.LPAREN, lx.LBRACKET):
                 level += 1
             elif tkn.kind in (lx.RBRACE, lx.RPAREN, lx.RBRACKET):
                 level -= 1
                 if level <= 0:
                     break
-            tokens.append(tkn)
         return tokens