[PATCH 08/28] qapi: Support flat unions tag values with leading digit

[Markus Armbruster]

Flat union tag values get checked twice: as enum member name, and as
union branch name.  The former accepts leading digits, the latter
doesn't.  The restriction feels arbitrary.  Skip the latter check.

This can expose c_name() to input it can't handle: a name starting
with a digit.  Improve it to return a valid C identifier for any
input.

Signed-off-by: Markus Armbruster <armbru@redhat.com>
---
 scripts/qapi/common.py | 8 ++++----
 scripts/qapi/expr.py   | 4 +++-
 2 files changed, 7 insertions(+), 5 deletions(-)

diff --git a/scripts/qapi/common.py b/scripts/qapi/common.py
index 11b86beeab..cbd3fd81d3 100644
--- a/scripts/qapi/common.py
+++ b/scripts/qapi/common.py
@@ -18,7 +18,6 @@
 #: Magic string that gets removed along with all space to its right.
 EATSPACE = '\033EATSPACE.'
 POINTER_SUFFIX = ' *' + EATSPACE
-_C_NAME_TRANS = str.maketrans('.-', '__')
 
 
 def camel_to_upper(value: str) -> str:
@@ -109,9 +108,10 @@ def c_name(name: str, protect: bool = True) -> str:
                      'not_eq', 'or', 'or_eq', 'xor', 'xor_eq'])
     # namespace pollution:
     polluted_words = set(['unix', 'errno', 'mips', 'sparc', 'i386'])
-    name = name.translate(_C_NAME_TRANS)
-    if protect and (name in c89_words | c99_words | c11_words | gcc_words
-                    | cpp_words | polluted_words):
+    name = re.sub(r'[^A-Za-z0-9_]', '_', name)
+    if protect and (name in (c89_words | c99_words | c11_words | gcc_words
+                             | cpp_words | polluted_words)
+                    or name[0].isdigit()):
         return 'q_' + name
     return name
 
diff --git a/scripts/qapi/expr.py b/scripts/qapi/expr.py
index cf09fa9fd3..507550c340 100644
--- a/scripts/qapi/expr.py
+++ b/scripts/qapi/expr.py
@@ -246,7 +246,9 @@ def check_union(expr, info):
 
     for (key, value) in members.items():
         source = "'data' member '%s'" % key
-        check_name_str(key, info, source)
+        if discriminator is None:
+            check_name_str(key, info, source)
+        # else: name is in discriminator enum, which gets checked
         check_keys(value, info, source, ['type'], ['if'])
         check_if(value, info, source)
         check_type(value['type'], info, source, allow_array=not base)
-- 
2.26.3