#!/usr/bin/env python
"""
crackfortran --- read fortran (77,90) code and extract declaration information.

Copyright 1999-2004 Pearu Peterson all rights reserved,
Pearu Peterson <pearu@ioc.ee>
Permission to use, modify, and distribute this software is given under the
terms of the NumPy License.

NO WARRANTY IS EXPRESSED OR IMPLIED.  USE AT YOUR OWN RISK.
$Date: 2005/09/27 07:13:49 $
Pearu Peterson


Usage of crackfortran:
======================
Command line keys: -quiet,-verbose,-fix,-f77,-f90,-show,-h <pyffilename>
                   -m <module name for f77 routines>,--ignore-contains
Functions: crackfortran, crack2fortran
The following Fortran statements/constructions are supported
(or will be if needed):
   block data,byte,call,character,common,complex,contains,data,
   dimension,double complex,double precision,end,external,function,
   implicit,integer,intent,interface,intrinsic,
   logical,module,optional,parameter,private,public,
   program,real,(sequence?),subroutine,type,use,virtual,
   include,pythonmodule
Note: 'virtual' is mapped to 'dimension'.
Note: 'implicit integer (z) static (z)' is 'implicit static (z)' (this is minor bug).
Note: code after 'contains' will be ignored until its scope ends.
Note: 'common' statement is extended: dimensions are moved to variable definitions
Note: f2py directive: <commentchar>f2py<line> is read as <line>
Note: pythonmodule is introduced to represent Python module

Usage:
  `postlist=crackfortran(files)`
  `postlist` contains declaration information read from the list of files `files`.
  `crack2fortran(postlist)` returns a fortran code to be saved to pyf-file

  `postlist` has the following structure:
 *** it is a list of dictionaries containing `blocks':
     B = {'block','body','vars','parent_block'[,'name','prefix','args','result',
          'implicit','externals','interfaced','common','sortvars',
          'commonvars','note']}
     B['block'] = 'interface' | 'function' | 'subroutine' | 'module' |
                  'program' | 'block data' | 'type' | 'pythonmodule'
     B['body'] --- list containing `subblocks' with the same structure as `blocks'
     B['parent_block'] --- dictionary of a parent block:
                             C['body'][<index>]['parent_block'] is C
     B['vars'] --- dictionary of variable definitions
     B['sortvars'] --- dictionary of variable definitions sorted by dependence (independent first)
     B['name'] --- name of the block (not if B['block']=='interface')
     B['prefix'] --- prefix string (only if B['block']=='function')
     B['args'] --- list of argument names if B['block']== 'function' | 'subroutine'
     B['result'] --- name of the return value (only if B['block']=='function')
     B['implicit'] --- dictionary {'a':<variable definition>,'b':...} | None
     B['externals'] --- list of variables being external
     B['interfaced'] --- list of variables being external and defined
     B['common'] --- dictionary of common blocks (list of objects)
     B['commonvars'] --- list of variables used in common blocks (dimensions are moved to variable definitions)
     B['from'] --- string showing the 'parents' of the current block
     B['use'] --- dictionary of modules used in current block:
         {<modulename>:{['only':<0|1>],['map':{<local_name1>:<use_name1>,...}]}}
     B['note'] --- list of LaTeX comments on the block
     B['f2pyenhancements'] --- optional dictionary
          {'threadsafe':'','fortranname':<name>,
           'callstatement':<C-expr>|<multi-line block>,
           'callprotoargument':<C-expr-list>,
           'usercode':<multi-line block>|<list of multi-line blocks>,
           'pymethoddef:<multi-line block>'
           }
     B['entry'] --- dictionary {entryname:argslist,..}
     B['varnames'] --- list of variable names given in the order of reading the
                       Fortran code, useful for derived types.
     B['saved_interface'] --- a string of scanned routine signature, defines explicit interface
 *** Variable definition is a dictionary
     D = B['vars'][<variable name>] =
     {'typespec'[,'attrspec','kindselector','charselector','=','typename']}
     D['typespec'] = 'byte' | 'character' | 'complex' | 'double complex' |
                     'double precision' | 'integer' | 'logical' | 'real' | 'type'
     D['attrspec'] --- list of attributes (e.g. 'dimension(<arrayspec>)',
                       'external','intent(in|out|inout|hide|c|callback|cache|aligned4|aligned8|aligned16)',
                       'optional','required', etc)
     K = D['kindselector'] = {['*','kind']} (only if D['typespec'] =
                         'complex' | 'integer' | 'logical' | 'real' )
     C = D['charselector'] = {['*','len','kind']}
                             (only if D['typespec']=='character')
     D['='] --- initialization expression string
     D['typename'] --- name of the type if D['typespec']=='type'
     D['dimension'] --- list of dimension bounds
     D['intent'] --- list of intent specifications
     D['depend'] --- list of variable names on which current variable depends on
     D['check'] --- list of C-expressions; if C-expr returns zero, exception is raised
     D['note'] --- list of LaTeX comments on the variable
 *** Meaning of kind/char selectors (few examples):
     D['typespec>']*K['*']
     D['typespec'](kind=K['kind'])
     character*C['*']
     character(len=C['len'],kind=C['kind'])
     (see also fortran type declaration statement formats below)

Fortran 90 type declaration statement format (F77 is subset of F90)
====================================================================
(Main source: IBM XL Fortran 5.1 Language Reference Manual)
type declaration = <typespec> [[<attrspec>]::] <entitydecl>
<typespec> = byte                          |
             character[<charselector>]     |
             complex[<kindselector>]       |
             double complex                |
             double precision              |
             integer[<kindselector>]       |
             logical[<kindselector>]       |
             real[<kindselector>]          |
             type(<typename>)
<charselector> = * <charlen>               |
             ([len=]<len>[,[kind=]<kind>]) |
             (kind=<kind>[,len=<len>])
<kindselector> = * <intlen>                |
             ([kind=]<kind>)
<attrspec> = comma separated list of attributes.
             Only the following attributes are used in
             building up the interface:
                external
                (parameter --- affects '=' key)
                optional
                intent
             Other attributes are ignored.
<intentspec> = in | out | inout
<arrayspec> = comma separated list of dimension bounds.
<entitydecl> = <name> [[*<charlen>][(<arrayspec>)] | [(<arrayspec>)]*<charlen>]
                      [/<init_expr>/ | =<init_expr>] [,<entitydecl>]

In addition, the following attributes are used: check,depend,note

TODO:
    * Apply 'parameter' attribute (e.g. 'integer parameter :: i=2' 'real x(i)'
                                   -> 'real x(2)')
    The above may be solved by creating appropriate preprocessor program, for example.

"""
from __future__ import division, absolute_import, print_function

import sys
import string
import fileinput
import re
import os
import copy
import platform

from . import __version__

# The eviroment provided by auxfuncs.py is needed for some calls to eval.
# As the needed functions cannot be determined by static inspection of the
# code, it is safest to use import * pending a major refactoring of f2py.
from .auxfuncs import *


f2py_version = __version__.version

# Global flags:
strictf77 = 1          # Ignore `!' comments unless line[0]=='!'
sourcecodeform = 'fix'  # 'fix','free'
quiet = 0              # Be verbose if 0 (Obsolete: not used any more)
verbose = 1            # Be quiet if 0, extra verbose if > 1.
tabchar = 4 * ' '
pyffilename = ''
f77modulename = ''
skipemptyends = 0      # for old F77 programs without 'program' statement
ignorecontains = 1
dolowercase = 1
debug = []

# Global variables
beginpattern = ''
currentfilename = ''
expectbegin = 1
f90modulevars = {}
filepositiontext = ''
gotnextfile = 1
groupcache = None
groupcounter = 0
grouplist = {groupcounter: []}
groupname = ''
include_paths = []
neededmodule = -1
onlyfuncs = []
previous_context = None
skipblocksuntil = -1
skipfuncs = []
skipfunctions = []
usermodules = []


def reset_global_f2py_vars():
    global groupcounter, grouplist, neededmodule, expectbegin
    global skipblocksuntil, usermodules, f90modulevars, gotnextfile
    global filepositiontext, currentfilename, skipfunctions, skipfuncs
    global onlyfuncs, include_paths, previous_context
    global strictf77, sourcecodeform, quiet, verbose, tabchar, pyffilename
    global f77modulename, skipemptyends, ignorecontains, dolowercase, debug

    # flags
    strictf77 = 1
    sourcecodeform = 'fix'
    quiet = 0
    verbose = 1
    tabchar = 4 * ' '
    pyffilename = ''
    f77modulename = ''
    skipemptyends = 0
    ignorecontains = 1
    dolowercase = 1
    debug = []
    # variables
    groupcounter = 0
    grouplist = {groupcounter: []}
    neededmodule = -1
    expectbegin = 1
    skipblocksuntil = -1
    usermodules = []
    f90modulevars = {}
    gotnextfile = 1
    filepositiontext = ''
    currentfilename = ''
    skipfunctions = []
    skipfuncs = []
    onlyfuncs = []
    include_paths = []
    previous_context = None


def outmess(line, flag=1):
    global filepositiontext

    if not verbose:
        return
    if not quiet:
        if flag:
            sys.stdout.write(filepositiontext)
        sys.stdout.write(line)

re._MAXCACHE = 50
defaultimplicitrules = {}
for c in "abcdefghopqrstuvwxyz$_":
    defaultimplicitrules[c] = {'typespec': 'real'}
for c in "ijklmn":
    defaultimplicitrules[c] = {'typespec': 'integer'}
del c
badnames = {}
invbadnames = {}
for n in ['int', 'double', 'float', 'char', 'short', 'long', 'void', 'case', 'while',
          'return', 'signed', 'unsigned', 'if', 'for', 'typedef', 'sizeof', 'union',
          'struct', 'static', 'register', 'new', 'break', 'do', 'goto', 'switch',
          'continue', 'else', 'inline', 'extern', 'delete', 'const', 'auto',
          'len', 'rank', 'shape', 'index', 'slen', 'size', '_i',
          'max', 'min',
          'flen', 'fshape',
          'string', 'complex_double', 'float_double', 'stdin', 'stderr', 'stdout',
          'type', 'default']:
    badnames[n] = n + '_bn'
    invbadnames[n + '_bn'] = n


def rmbadname1(name):
    if name in badnames:
        errmess('rmbadname1: Replacing "%s" with "%s".\n' %
                (name, badnames[name]))
        return badnames[name]
    return name


def rmbadname(names):
    return [rmbadname1(_m) for _m in names]


def undo_rmbadname1(name):
    if name in invbadnames:
        errmess('undo_rmbadname1: Replacing "%s" with "%s".\n'
                % (name, invbadnames[name]))
        return invbadnames[name]
    return name


def undo_rmbadname(names):
    return [undo_rmbadname1(_m) for _m in names]


def getextension(name):
    i = name.rfind('.')
    if i == -1:
        return ''
    if '\\' in name[i:]:
        return ''
    if '/' in name[i:]:
        return ''
    return name[i + 1:]

is_f_file = re.compile(r'.*[.](for|ftn|f77|f)\Z', re.I).match
_has_f_header = re.compile(r'-[*]-\s*fortran\s*-[*]-', re.I).search
_has_f90_header = re.compile(r'-[*]-\s*f90\s*-[*]-', re.I).search
_has_fix_header = re.compile(r'-[*]-\s*fix\s*-[*]-', re.I).search
_free_f90_start = re.compile(r'[^c*]\s*[^\s\d\t]', re.I).match


def is_free_format(file):
    """Check if file is in free format Fortran."""
    # f90 allows both fixed and free format, assuming fixed unless
    # signs of free format are detected.
    result = 0
    with open(file, 'r') as f:
        line = f.readline()
        n = 15  # the number of non-comment lines to scan for hints
        if _has_f_header(line):
            n = 0
        elif _has_f90_header(line):
            n = 0
            result = 1
        while n > 0 and line:
            if line[0] != '!' and line.strip():
                n -= 1
                if (line[0] != '\t' and _free_f90_start(line[:5])) or line[-2:-1] == '&':
                    result = 1
                    break
            line = f.readline()
    return result


# Read fortran (77,90) code
def readfortrancode(ffile, dowithline=show, istop=1):
    """
    Read fortran codes from files and
     1) Get rid of comments, line continuations, and empty lines; lower cases.
     2) Call dowithline(line) on every line.
     3) Recursively call itself when statement \"include '<filename>'\" is met.
    """
    global gotnextfile, filepositiontext, currentfilename, sourcecodeform, strictf77
    global beginpattern, quiet, verbose, dolowercase, include_paths

    if not istop:
        saveglobals = gotnextfile, filepositiontext, currentfilename, sourcecodeform, strictf77,\
            beginpattern, quiet, verbose, dolowercase
    if ffile == []:
        return
    localdolowercase = dolowercase