qapi: Smarter camel_to_upper() to reduce need for 'prefix'

camel_to_upper() converts its argument from camel case to upper case
with '_' between words.  Used for generated enumeration constant
prefixes.

When some of the words are spelled all caps, where exactly to insert
'_' is guesswork.  camel_to_upper()'s guesses are bad enough in places
to make people override them with a 'prefix' in the schema.

Rewrite it to guess better:

1. Insert '_' after a non-upper case character followed by an upper
   case character:

       OneTwo -> ONE_TWO
       One2Three -> ONE2_THREE

2. Insert '_' before the last upper case character followed by a
   non-upper case character:

       ACRONYMWord -> ACRONYM_Word

   Except at the beginning (as in OneTwo above), or when there is
   already one:

       AbCd -> AB_CD

This changes the default enumeration constant prefix for a number of
enums.  Generated enumeration constants change only where the default
is not overridden with 'prefix'.

The following enumerations without a 'prefix' change:

    enum                            old camel_to_upper()
                                    new camel_to_upper()
    ------------------------------------------------------------------
    DisplayGLMode                   DISPLAYGL_MODE
                                    DISPLAY_GL_MODE
    EbpfProgramID                   EBPF_PROGRAMID
                                    EBPF_PROGRAM_ID
    HmatLBDataType                  HMATLB_DATA_TYPE
                                    HMAT_LB_DATA_TYPE
    HmatLBMemoryHierarchy           HMATLB_MEMORY_HIERARCHY
                                    HMAT_LB_MEMORY_HIERARCHY
    MultiFDCompression              MULTIFD_COMPRESSION
                                    MULTI_FD_COMPRESSION
    OffAutoPCIBAR                   OFF_AUTOPCIBAR
                                    OFF_AUTO_PCIBAR
    QCryptoBlockFormat              Q_CRYPTO_BLOCK_FORMAT
                                    QCRYPTO_BLOCK_FORMAT
    QCryptoBlockLUKSKeyslotState    Q_CRYPTO_BLOCKLUKS_KEYSLOT_STATE
                                    QCRYPTO_BLOCK_LUKS_KEYSLOT_STATE
    QKeyCode                        Q_KEY_CODE
                                    QKEY_CODE
    XDbgBlockGraphNodeType          X_DBG_BLOCK_GRAPH_NODE_TYPE
                                    XDBG_BLOCK_GRAPH_NODE_TYPE
    TestUnionEnumA                  TEST_UNION_ENUMA
                                    TEST_UNION_ENUM_A

Add a 'prefix' so generated code doesn't change now.  Subsequent
commits will remove most of them again.  Two will remain:
MULTIFD_COMPRESSION, because migration code generally spells "multifd"
that way, and Q_KEY_CODE, because that one is baked into
subprojects/keycodemapdb/tools/keymap-gen.

The following enumerations with a 'prefix' change so that the prefix
is now superfluous:

    enum                            old camel_to_upper()
                                    new camel_to_upper() [equal to prefix]
    ------------------------------------------------------------------
    BlkdebugIOType                  BLKDEBUGIO_TYPE
                                    BLKDEBUG_IO_TYPE
    QCryptoTLSCredsEndpoint         Q_CRYPTOTLS_CREDS_ENDPOINT
                                    QCRYPTO_TLS_CREDS_ENDPOINT
    QCryptoSecretFormat             Q_CRYPTO_SECRET_FORMAT
                                    QCRYPTO_SECRET_FORMAT
    QCryptoCipherMode               Q_CRYPTO_CIPHER_MODE
                                    QCRYPTO_CIPHER_MODE
    QCryptodevBackendType           Q_CRYPTODEV_BACKEND_TYPE
                                    QCRYPTODEV_BACKEND_TYPE
    QType [builtin]                 Q_TYPE
                                    QTYPE

Drop these prefixes.

The following enumerations with a 'prefix' change without making the
'prefix' superfluous:

    enum                            old camel_to_upper()
                                    new camel_to_upper() [equal to prefix]
                                    prefix
    ------------------------------------------------------------------
    CpuS390Entitlement              CPUS390_ENTITLEMENT
                                    CPU_S390_ENTITLEMENT
                                    S390_CPU_ENTITLEMENT
    CpuS390Polarization             CPUS390_POLARIZATION
                                    CPU_S390_POLARIZATION
                                    S390_CPU_POLARIZATION
    CpuS390State                    CPUS390_STATE
                                    CPU_S390_STATE
                                    S390_CPU_STATE
    QAuthZListFormat                Q_AUTHZ_LIST_FORMAT
                                    QAUTH_Z_LIST_FORMAT
                                    QAUTHZ_LIST_FORMAT
    QAuthZListPolicy                Q_AUTHZ_LIST_POLICY
                                    QAUTH_Z_LIST_POLICY
                                    QAUTHZ_LIST_POLICY
    QCryptoAkCipherAlgorithm        Q_CRYPTO_AK_CIPHER_ALGORITHM
                                    QCRYPTO_AK_CIPHER_ALGORITHM
                                    QCRYPTO_AKCIPHER_ALG
    QCryptoAkCipherKeyType          Q_CRYPTO_AK_CIPHER_KEY_TYPE
                                    QCRYPTO_AK_CIPHER_KEY_TYPE
                                    QCRYPTO_AKCIPHER_KEY_TYPE
    QCryptoCipherAlgorithm          Q_CRYPTO_CIPHER_ALGORITHM
                                    QCRYPTO_CIPHER_ALGORITHM
                                    QCRYPTO_CIPHER_ALG
    QCryptoHashAlgorithm            Q_CRYPTO_HASH_ALGORITHM
                                    QCRYPTO_HASH_ALGORITHM
                                    QCRYPTO_HASH_ALG
    QCryptoIVGenAlgorithm           Q_CRYPTOIV_GEN_ALGORITHM
                                    QCRYPTO_IV_GEN_ALGORITHM
                                    QCRYPTO_IVGEN_ALG
    QCryptoRSAPaddingAlgorithm      Q_CRYPTORSA_PADDING_ALGORITHM
                                    QCRYPTO_RSA_PADDING_ALGORITHM
                                    QCRYPTO_RSA_PADDING_ALG
    QCryptodevBackendAlgType        Q_CRYPTODEV_BACKEND_ALG_TYPE
                                    QCRYPTODEV_BACKEND_ALG_TYPE
                                    QCRYPTODEV_BACKEND_ALG
    QCryptodevBackendServiceType    Q_CRYPTODEV_BACKEND_SERVICE_TYPE
                                    QCRYPTODEV_BACKEND_SERVICE_TYPE
                                    QCRYPTODEV_BACKEND_SERVICE

Subsequent commits will tweak things to remove most of these prefixes.
Only QAUTHZ_LIST_FORMAT and QAUTHZ_LIST_POLICY will remain.

Signed-off-by: Markus Armbruster <armbru@redhat.com>
Reviewed-by: Daniel P. Berrangé <berrange@redhat.com>
Message-ID: <20240904111836.3273842-2-armbru@redhat.com>

2 files changed, 26 insertions, 20 deletions

diff --git a/scripts/qapi/common.py b/scripts/qapi/common.py
index 737b059e62..d7c8aa3365 100644
--- a/scripts/qapi/common.py
+++ b/scripts/qapi/common.py
@@ -40,22 +40,28 @@ def camel_to_upper(value: str) -> str:
         ENUM_Name2 -> ENUM_NAME2
         ENUM24_Name -> ENUM24_NAME
     """
-    c_fun_str = c_name(value, False)
-    if value.isupper():
-        return c_fun_str
-
-    new_name = ''
-    length = len(c_fun_str)
-    for i in range(length):
-        char = c_fun_str[i]
-        # When char is upper case and no '_' appears before, do more checks
-        if char.isupper() and (i > 0) and c_fun_str[i - 1] != '_':
-            if i < length - 1 and c_fun_str[i + 1].islower():
-                new_name += '_'
-            elif c_fun_str[i - 1].isdigit():
-                new_name += '_'
-        new_name += char
-    return new_name.lstrip('_').upper()
+    ret = value[0]
+    upc = value[0].isupper()
+
+    # Copy remainder of ``value`` to ``ret`` with '_' inserted
+    for ch in value[1:]:
+        if ch.isupper() == upc:
+            pass
+        elif upc:
+            # ``ret`` ends in upper case, next char isn't: insert '_'
+            # before the last upper case char unless there is one
+            # already, or it's at the beginning
+            if len(ret) > 2 and ret[-2].isalnum():
+                ret = ret[:-1] + '_' + ret[-1]
+        else:
+            # ``ret`` doesn't end in upper case, next char is: insert
+            # '_' before it
+            if ret[-1].isalnum():
+                ret += '_'
+        ret += ch
+        upc = ch.isupper()
+
+    return c_name(ret.upper()).lstrip('_')
 
 
 def c_enum_const(type_name: str,
@@ -68,9 +74,9 @@ def c_enum_const(type_name: str,
     :param const_name: The name of this constant.
     :param prefix: Optional, prefix that overrides the type_name.
     """
-    if prefix is not None:
-        type_name = prefix
-    return camel_to_upper(type_name) + '_' + c_name(const_name, False).upper()
+    if prefix is None:
+        prefix = camel_to_upper(type_name)
+    return prefix + '_' + c_name(const_name, False).upper()
 
 
 def c_name(name: str, protect: bool = True) -> str:
diff --git a/scripts/qapi/schema.py b/scripts/qapi/schema.py
index d65c35f6ee..e97c978d38 100644
--- a/scripts/qapi/schema.py
+++ b/scripts/qapi/schema.py
@@ -1249,7 +1249,7 @@ class QAPISchema:
             [{'name': n} for n in qtypes], None)
 
         self._def_definition(QAPISchemaEnumType(
-            'QType', None, None, None, None, qtype_values, 'QTYPE'))
+            'QType', None, None, None, None, qtype_values, None))
 
     def _make_features(
         self,