#!/usr/bin/env python

# Tool for canonical RISC-V architecture string.
# Copyright (C) 2011-2021 Free Software Foundation, Inc.
# Contributed by Andrew Waterman (andrew@sifive.com).
#
# This file is part of GCC.
#
# GCC is free software; you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation; either version 3, or (at your option)
# any later version.
#
# GCC is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
# GNU General Public License for more details.
#
# You should have received a copy of the GNU General Public License
# along with GCC; see the file COPYING3.  If not see
# <http://www.gnu.org/licenses/>.


from __future__ import print_function
import sys
import collections
import itertools
from functools import reduce


CANONICAL_ORDER = "mafdgqlcbjtpvn"
LONG_EXT_PREFIXES = ['z', 's', 'h', 'x']

#
# IMPLIED_EXT(ext) -> implied extension list.
#
IMPLIED_EXT = {
  "d" : ["f"],
}

def arch_canonicalize(arch):
  # TODO: Support extension version.
  new_arch = ""
  if arch[:5] in ['rv32e', 'rv32i', 'rv32g', 'rv64i', 'rv64g']:
    # TODO: We should expand g to imad_zifencei once we support newer spec.
    new_arch = arch[:5].replace("g", "imafd")
  else:
    raise Exception("Unexpected arch: `%s`" % arch[:5])

  # Find any Z, S, H or X
  long_ext_prefixes_idx = map(lambda x: arch.find(x), LONG_EXT_PREFIXES)

  # Filter out any non-existent index.
  long_ext_prefixes_idx = list(filter(lambda x: x != -1, long_ext_prefixes_idx))
  if long_ext_prefixes_idx:
    first_long_ext_idx = min(long_ext_prefixes_idx)
    long_exts = arch[first_long_ext_idx:].split("_")
    std_exts = list(arch[5:first_long_ext_idx])
  else:
    long_exts = []
    std_exts = list(arch[5:])

  #
  # Handle implied extensions.
  #
  for ext in std_exts + long_exts:
    if ext in IMPLIED_EXT:
      implied_exts = IMPLIED_EXT[ext]
      for implied_ext in implied_exts:
        if implied_ext not in std_exts + long_exts:
          long_exts.append(implied_ext)

  # Single letter extension might appear in the long_exts list,
  # becasue we just append extensions list to the arch string.
  std_exts += list(filter(lambda x:len(x) == 1, long_exts))

  def longext_sort (exts):
    if not exts.startswith("zxm") and exts.startswith("z"):
      # If "Z" extensions are named, they should be ordered first by CANONICAL.
      if exts[1] not in CANONICAL_ORDER:
        raise Exception("Unsupported extension `%s`" % exts)
      canonical_sort = CANONICAL_ORDER.index(exts[1])
    else:
      canonical_sort = -1
    return (exts.startswith("x"), exts.startswith("zxm"),
            LONG_EXT_PREFIXES.index(exts[0]), canonical_sort, exts[1:])

  # Multi-letter extension must be in lexicographic order.
  long_exts = list(sorted(filter(lambda x:len(x) != 1, long_exts),
                          key=longext_sort))

  # Put extensions in canonical order.
  for ext in CANONICAL_ORDER:
    if ext in std_exts:
      new_arch += ext

  # Check every extension is processed.
  for ext in std_exts:
    if ext == '_':
      continue
    if ext not in CANONICAL_ORDER:
      raise Exception("Unsupported extension `%s`" % ext)

  # Concat rest of the multi-char extensions.
  if long_exts:
    new_arch += "_" + "_".join(long_exts)
  return new_arch

if len(sys.argv) < 2:
  print ("Usage: %s <arch_str> [<arch_str>*]" % sys.argv)
  sys.exit(1)

for arg in sys.argv[1:]:
  print (arch_canonicalize(arg))