qemu/scripts/qapi/common.py

219 lines
6.6 KiB
Python
Raw Normal View History

#
# QAPI helper library
#
# Copyright IBM, Corp. 2011
# Copyright (c) 2013-2018 Red Hat Inc.
#
# Authors:
# Anthony Liguori <aliguori@us.ibm.com>
qapi.py: Restructure lexer and parser The parser has a rather unorthodox structure: Until EOF: Read a section: Generator function get_expr() yields one section after the other, as a string. An unindented, non-empty line that isn't a comment starts a new section. Lexing: Split section into a list of tokens (strings), with help of generator function tokenize(). Parsing: Parse the first expression from the list of tokens, with parse(), throw away any remaining tokens. In parse_schema(): record value of an enum, union or struct key (if any) in the appropriate global table, append expression to the list of expressions. Return list of expressions. Known issues: (1) Indentation is significant, unlike in real JSON. (2) Neither lexer nor parser have any idea of source positions. Error reporting is hard, let's go shopping. (3) The one error we bother to detect, we "report" via raise. (4) The lexer silently ignores invalid characters. (5) If everything in a section gets ignored, the parser crashes. (6) The lexer treats a string containing a structural character exactly like the structural character. (7) Tokens trailing the first expression in a section are silently ignored. (8) The parser accepts any token in place of a colon. (9) The parser treats comma as optional. (10) parse() crashes on unexpected EOF. (11) parse_schema() crashes when a section's expression isn't a JSON object. Replace this piece of original art by a thoroughly unoriginal design. Takes care of (1), (2), (5), (6) and (7), and lays the groundwork for addressing the others. Generated source files remain unchanged. Signed-off-by: Markus Armbruster <armbru@redhat.com> Reviewed-by: Eric Blake <eblake@redhat.com> Message-id: 1374939721-7876-4-git-send-email-armbru@redhat.com Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
2013-07-27 19:41:55 +04:00
# Markus Armbruster <armbru@redhat.com>
#
# This work is licensed under the terms of the GNU GPL, version 2.
# See the COPYING file in the top-level directory.
import re
from typing import Match, Optional, Sequence
#: Magic string that gets removed along with all space to its right.
EATSPACE = '\033EATSPACE.'
POINTER_SUFFIX = ' *' + EATSPACE
def camel_to_upper(value: str) -> str:
"""
Converts CamelCase to CAMEL_CASE.
Examples::
ENUMName -> ENUM_NAME
EnumName1 -> ENUM_NAME1
ENUM_NAME -> ENUM_NAME
ENUM_NAME1 -> ENUM_NAME1
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()
def c_enum_const(type_name: str,
const_name: str,
prefix: Optional[str] = None) -> str:
"""
Generate a C enumeration constant name.
:param type_name: The name of the enumeration.
: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
qapi: Change munging of CamelCase enum values When munging enum values, the fact that we were passing the entire prefix + value through camel_to_upper() meant that enum values spelled with CamelCase could be turned into CAMEL_CASE. However, this provides a potential collision (both OneTwo and One-Two would munge into ONE_TWO) for enum types, when the same two names are valid side-by-side as QAPI member names. By changing the generation of enum constants to always be prefix + '_' + c_name(value, False).upper(), and ensuring that there are no case collisions (in the next patches), we no longer have to worry about names that would be distinct as QAPI members but collide as variant tag names, without having to think about what munging the heuristics in camel_to_upper() will actually perform on an enum value. Making the change will affect enums that did not follow coding conventions, using 'CamelCase' rather than desired 'lower-case'. Thankfully, there are only two culprits: InputButton and ErrorClass. We already tweaked ErrorClass to make it an alias of QapiErrorClass, where only the alias needs changing rather than the whole tree. So the bulk of this change is modifying INPUT_BUTTON_WHEEL_UP to the new INPUT_BUTTON_WHEELUP (and likewise for WHEELDOWN). That part of this commit may later need reverting if we rename the enum constants from 'WheelUp' to 'wheel-up' as part of moving x-input-send-event to a stable interface; but at least we have documentation bread crumbs in place to remind us (commit 513e7cd), and it matches the fact that SDL constants are also spelled SDL_BUTTON_WHEELUP. Suggested by: Markus Armbruster <armbru@redhat.com> Signed-off-by: Eric Blake <eblake@redhat.com> Message-Id: <1447836791-369-27-git-send-email-eblake@redhat.com> [Commit message tweaked] Signed-off-by: Markus Armbruster <armbru@redhat.com>
2015-11-18 11:53:01 +03:00
return camel_to_upper(type_name) + '_' + c_name(const_name, False).upper()
def c_name(name: str, protect: bool = True) -> str:
"""
Map ``name`` to a valid C identifier.
Used for converting 'name' from a 'name':'type' qapi definition
into a generated struct member, as well as converting type names
into substrings of a generated C function name.
'__a.b_c' -> '__a_b_c', 'x-foo' -> 'x_foo'
protect=True: 'int' -> 'q_int'; protect=False: 'int' -> 'int'
:param name: The name to map.
:param protect: If true, avoid returning certain ticklish identifiers
(like C keywords) by prepending ``q_``.
"""
# ANSI X3J11/88-090, 3.1.1
c89_words = set(['auto', 'break', 'case', 'char', 'const', 'continue',
'default', 'do', 'double', 'else', 'enum', 'extern',
'float', 'for', 'goto', 'if', 'int', 'long', 'register',
'return', 'short', 'signed', 'sizeof', 'static',
'struct', 'switch', 'typedef', 'union', 'unsigned',
'void', 'volatile', 'while'])
# ISO/IEC 9899:1999, 6.4.1
c99_words = set(['inline', 'restrict', '_Bool', '_Complex', '_Imaginary'])
# ISO/IEC 9899:2011, 6.4.1
c11_words = set(['_Alignas', '_Alignof', '_Atomic', '_Generic',
'_Noreturn', '_Static_assert', '_Thread_local'])
# GCC http://gcc.gnu.org/onlinedocs/gcc-4.7.1/gcc/C-Extensions.html
# excluding _.*
gcc_words = set(['asm', 'typeof'])
# C++ ISO/IEC 14882:2003 2.11
cpp_words = set(['bool', 'catch', 'class', 'const_cast', 'delete',
'dynamic_cast', 'explicit', 'false', 'friend', 'mutable',
'namespace', 'new', 'operator', 'private', 'protected',
'public', 'reinterpret_cast', 'static_cast', 'template',
'this', 'throw', 'true', 'try', 'typeid', 'typename',
'using', 'virtual', 'wchar_t',
# alternative representations
'and', 'and_eq', 'bitand', 'bitor', 'compl', 'not',
'not_eq', 'or', 'or_eq', 'xor', 'xor_eq'])
# namespace pollution:
polluted_words = set(['unix', 'errno', 'mips', 'sparc', 'i386'])
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
class Indentation:
"""
Indentation level management.
:param initial: Initial number of spaces, default 0.
"""
def __init__(self, initial: int = 0) -> None:
self._level = initial
def __int__(self) -> int:
return self._level
def __repr__(self) -> str:
return "{}({:d})".format(type(self).__name__, self._level)
def __str__(self) -> str:
"""Return the current indentation as a string of spaces."""
return ' ' * self._level
def __bool__(self) -> bool:
"""True when there is a non-zero indentation."""
return bool(self._level)
def increase(self, amount: int = 4) -> None:
"""Increase the indentation level by ``amount``, default 4."""
self._level += amount
def decrease(self, amount: int = 4) -> None:
"""Decrease the indentation level by ``amount``, default 4."""
if self._level < amount:
raise ArithmeticError(
f"Can't remove {amount:d} spaces from {self!r}")
self._level -= amount
#: Global, current indent level for code generation.
indent = Indentation()
def cgen(code: str, **kwds: object) -> str:
"""
Generate ``code`` with ``kwds`` interpolated.
Obey `indent`, and strip `EATSPACE`.
"""
raw = code % kwds
if indent:
raw = re.sub(r'^(?!(#|$))', str(indent), raw, flags=re.MULTILINE)
return re.sub(re.escape(EATSPACE) + r' *', '', raw)
def mcgen(code: str, **kwds: object) -> str:
if code[0] == '\n':
code = code[1:]
return cgen(code, **kwds)
def c_fname(filename: str) -> str:
return re.sub(r'[^A-Za-z0-9_]', '_', filename)
def guardstart(name: str) -> str:
return mcgen('''
#ifndef %(name)s
#define %(name)s
''',
name=c_fname(name).upper())
def guardend(name: str) -> str:
return mcgen('''
#endif /* %(name)s */
''',
name=c_fname(name).upper())
def gen_if(ifcond: Sequence[str]) -> str:
ret = ''
for ifc in ifcond:
ret += mcgen('''
#if %(cond)s
''', cond=ifc)
return ret
def gen_endif(ifcond: Sequence[str]) -> str:
ret = ''
for ifc in reversed(ifcond):
ret += mcgen('''
#endif /* %(cond)s */
''', cond=ifc)
return ret
def must_match(pattern: str, string: str) -> Match[str]:
match = re.match(pattern, string)
assert match is not None
return match