# -*- coding: utf-8 -*-
"""
    pygments.lexers.functional
    ~~~~~~~~~~~~~~~~~~~~~~~~~~

    Lexers for functional languages.

    :copyright: 2006-2007 by Georg Brandl, Marek Kubica,
                Adam Blinkinsop <blinks@acm.org>.
    :license: BSD, see LICENSE for more details.
"""

import re
try:
    set
except NameError:
    from sets import Set as set

from pygments.lexer import RegexLexer, bygroups, using, this, include
from pygments.token import Text, Comment, Operator, Keyword, Name, \
     String, Number, Punctuation


__all__ = ['SchemeLexer', 'HaskellLexer', 'OcamlLexer']


class SchemeLexer(RegexLexer):
    """
    A Scheme lexer, parsing a stream and outputting the tokens
    needed to highlight scheme code.
    This lexer could be most probably easily subclassed to parse
    other LISP-Dialects like Common Lisp, Emacs Lisp or AutoLisp.

    This parser is checked with pastes from the LISP pastebin
    at http://paste.lisp.org/ to cover as much syntax as possible.

    It supports the full Scheme syntax as defined in R5RS.

    *New in Pygments 0.6.*
    """
    name = 'Scheme'
    aliases = ['scheme', 'scm']
    filenames = ['*.scm']
    mimetypes = ['text/x-scheme', 'application/x-scheme']

    # list of known keywords and builtins taken form vim 6.4 scheme.vim
    # syntax file.
    keywords = [
        'lambda', 'define', 'if', 'else', 'cond', 'and', 'or', 'case', 'let',
        'let*', 'letrec', 'begin', 'do', 'delay', 'set!', '=>', 'quote',
        'quasiquote', 'unquote', 'unquote-splicing', 'define-syntax',
        'let-syntax', 'letrec-syntax', 'syntax-rules'
    ]
    builtins = [
        '*', '+', '-', '/', '<', '<=', '=', '>', '>=', 'abs', 'acos', 'angle',
        'append', 'apply', 'asin', 'assoc', 'assq', 'assv', 'atan',
        'boolean?', 'caaaar', 'caaadr', 'caaar', 'caadar', 'caaddr', 'caadr',
        'caar', 'cadaar', 'cadadr', 'cadar', 'caddar', 'cadddr', 'caddr',
        'cadr', 'call-with-current-continuation', 'call-with-input-file',
        'call-with-output-file', 'call-with-values', 'call/cc', 'car',
        'cdaaar', 'cdaadr', 'cdaar', 'cdadar', 'cdaddr', 'cdadr', 'cdar',
        'cddaar', 'cddadr', 'cddar', 'cdddar', 'cddddr', 'cdddr', 'cddr',
        'cdr', 'ceiling', 'char->integer', 'char-alphabetic?', 'char-ci<=?',
        'char-ci<?', 'char-ci=?', 'char-ci>=?', 'char-ci>?', 'char-downcase',
        'char-lower-case?', 'char-numeric?', 'char-ready?', 'char-upcase',
        'char-upper-case?', 'char-whitespace?', 'char<=?', 'char<?', 'char=?',
        'char>=?', 'char>?', 'char?', 'close-input-port', 'close-output-port',
        'complex?', 'cons', 'cos', 'current-input-port', 'current-output-port',
        'denominator', 'display', 'dynamic-wind', 'eof-object?', 'eq?',
        'equal?', 'eqv?', 'eval', 'even?', 'exact->inexact', 'exact?', 'exp',
        'expt', 'floor', 'for-each', 'force', 'gcd', 'imag-part',
        'inexact->exact', 'inexact?', 'input-port?', 'integer->char',
        'integer?', 'interaction-environment', 'lcm', 'length', 'list',
        'list->string', 'list->vector', 'list-ref', 'list-tail', 'list?',
        'load', 'log', 'magnitude', 'make-polar', 'make-rectangular',
        'make-string', 'make-vector', 'map', 'max', 'member', 'memq', 'memv',
        'min', 'modulo', 'negative?', 'newline', 'not', 'null-environment',
        'null?', 'number->string', 'number?', 'numerator', 'odd?',
        'open-input-file', 'open-output-file', 'output-port?', 'pair?',
        'peek-char', 'port?', 'positive?', 'procedure?', 'quotient',
        'rational?', 'rationalize', 'read', 'read-char', 'real-part', 'real?',
        'remainder', 'reverse', 'round', 'scheme-report-environment',
        'set-car!', 'set-cdr!', 'sin', 'sqrt', 'string', 'string->list',
        'string->number', 'string->symbol', 'string-append', 'string-ci<=?',
        'string-ci<?', 'string-ci=?', 'string-ci>=?', 'string-ci>?',
        'string-copy', 'string-fill!', 'string-length', 'string-ref',
        'string-set!', 'string<=?', 'string<?', 'string=?', 'string>=?',
        'string>?', 'string?', 'substring', 'symbol->string', 'symbol?',
        'tan', 'transcript-off', 'transcript-on', 'truncate', 'values',
        'vector', 'vector->list', 'vector-fill!', 'vector-length',
        'vector-ref', 'vector-set!', 'vector?', 'with-input-from-file',
        'with-output-to-file', 'write', 'write-char', 'zero?'
    ]

    # valid names for identifiers
    # well, names can only not consist fully of numbers
    # but this should be good enough for now
    valid_name = r'[a-zA-Z0-9!$%&*+,/:<=>?@^_~-]+'

    tokens = {
        'root' : [
            # the comments - always starting with semicolon
            # and going to the end of the line
            (r';.*$', Comment.Single),

            # whitespaces - usually not relevant
            (r'\s+', Text),

            # numbers
            (r'-?\d+\.\d+', Number.Float),
            (r'-?\d+', Number.Integer),
            # support for uncommon kinds of numbers -
            # have to figure out what the characters mean
            #(r'(#e|#i|#b|#o|#d|#x)[\d.]+', Number),

            # strings, symbols and characters
            (r'"(\\\\|\\"|[^"])*"', String),
            (r"'" + valid_name, String.Symbol),
            (r"#\\([()/'\".'_!§$%& ?=+-]{1}|[a-zA-Z0-9]+)", String.Char),

            # constants
            (r'(#t|#f)', Name.Constant),

            # special operators
            (r"('|#|`|,@|,|\.)", Operator),

            # highlight the keywords
            ('(%s)' % '|'.join([
                re.escape(entry) + ' ' for entry in keywords]),
                Keyword
            ),

            # first variable in a quoted string like
            # '(this is syntactic sugar)
            (r"(?<='\()" + valid_name, Name.Variable),
            (r"(?<=#\()" + valid_name, Name.Variable),

            # highlight the builtins
            ("(?<=\()(%s)" % '|'.join([
                re.escape(entry) + ' ' for entry in builtins]),
                Name.Builtin
            ),

            # the remaining functions
            (r'(?<=\()' + valid_name, Name.Function),
            # find the remaining variables
            (valid_name, Name.Variable),

            # the famous parentheses!
            (r'(\(|\))', Punctuation),
        ],
    }


class HaskellLexer(RegexLexer):
    """
    A Haskell lexer based on the lexemes defined in the Haskell 98 Report.

    *New in Pygments 0.8.*
    """
    name = 'Haskell'
    aliases = ['haskell', 'hs']
    filenames = ['*.hs']

    reserved = ['case','class','data','default','deriving','do','else',
                'if','in','infix[lr]?','instance',
                'let','newtype','of','then','type','where','_']
    ascii = ['NUL','SOH','[SE]TX','EOT','ENQ','ACK',
             'BEL','BS','HT','LF','VT','FF','CR','S[OI]','DLE',
             'DC[1-4]','NAK','SYN','ETB','CAN',
             'EM','SUB','ESC','[FGRU]S','SP','DEL']

    tokens = {
        'root': [
            # Whitespace:
            (r'\s+', Text),
            (r'--.*$', Comment.Single),
            (r'{-', Comment.Multiline, 'comment'),
            # Lexemes:
            #  Identifiers
            (r'\bimport\b', Keyword.Reserved, 'import'),
            (r'\bmodule\b', Keyword.Reserved, 'module'),
            (r'\berror\b', Name.Exception),
            (r'\b(%s)\b' % '|'.join(reserved), Keyword.Reserved),
            (r'^[_a-z][\w\']*', Name.Function),
            (r'[_a-z][\w\']*', Name),
            (r'[A-Z][\w\']*', Keyword.Type),
            #  Operators
            (r'\\(?![:!#$%&*+.\\/<=>?@^|~-]+)', Name.Function), # lambda operator
            (r'[:!#$%&*+.\\/<=>?@^|~-]+', Operator),
            #  Numbers
            (r'\d+[eE][+-]?\d+', Number.Float),
            (r'\d+\.\d+([eE][+-]?\d+)?', Number.Float),
            (r'0[oO][0-7]+', Number.Oct),
            (r'0[xX][\da-fA-F]+', Number.Hex),
            (r'\d+', Number.Integer),
            #  Character/String Literals
            (r"'", String.Char, 'character'),
            (r'"', String, 'string'),
            #  Special
            (r'\[\]', Keyword.Type),
            (r'\(\)', Name.Builtin),
            (r'[][(),;`{}]', Punctuation),
        ],
        'import': [
            # Import statements
            (r'\s+', Text),
            # after "funclist" state
            (r'\)', Punctuation, '#pop'),
            (r'qualified\b', Keyword),
            # import X as Y
            (r'([A-Z][a-zA-Z0-9_.]*)(\s+)(as)(\s+)([A-Z][a-zA-Z0-9_.]*)',
             bygroups(Name.Namespace, Text, Keyword, Text, Name), '#pop'),
            # import X hiding (functions)
            (r'([A-Z][a-zA-Z0-9_.]*)(\s+)(hiding)(\s+)(\()',
             bygroups(Name.Namespace, Text, Keyword, Text, Punctuation), 'funclist'),
            # import X (functions)
            (r'([A-Z][a-zA-Z0-9_.]*)(\s+)(\()',
             bygroups(Name.Namespace, Text, Punctuation), 'funclist'),
            # import X
            (r'[a-zA-Z0-9_.]+', Name.Namespace, '#pop'),
        ],
        'module': [
            (r'\s+', Text),
            (r'([A-Z][a-zA-Z0-9_.]*)(\s+)(\()',
             bygroups(Name.Namespace, Text, Punctuation), 'funclist'),
            (r'[A-Z][a-zA-Z0-9_.]*', Name.Namespace, '#pop'),
        ],
        'funclist': [
            (r'\s+', Text),
            (r'[A-Z][a-zA-Z0-9_]*', Keyword.Type),
            (r'[a-zA-Z0-9_]+', Name.Function),
            (r',', Punctuation),
            (r'[:!#$%&*+.\\/<=>?@^|~-]+', Operator),
            # (HACK, but it makes sense to push two instances, believe me)
            (r'\(', Punctuation, ('funclist', 'funclist')),
            (r'\)', Punctuation, '#pop:2'),
        ],
        'comment': [
            # Multiline Comments
            (r'[^-{}]', Comment.Multiline),
            (r'{-', Comment.Multiline, '#push'),
            (r'-}', Comment.Multiline, '#pop'),
            (r'[-{}]', Comment.Multiline),
        ],
        'character': [
            # Allows multi-chars, incorrectly.
            (r"[^\']", String.Char),
            (r"\\", String.Escape, 'escape'),
            ("'", String.Char, '#pop'),
        ],
        'string': [
            (r'[^\\"]', String),
            (r"\\", String.Escape, 'escape'),
            ('"', String, '#pop'),
        ],
        'escape': [
            ('[abfnrtv\\"\'&]', String.Escape, '#pop'),
            ('\\^[][A-Z@\\^_]', String.Escape, '#pop'),
            ('|'.join(ascii), String.Escape, '#pop'),
            (r'o[0-7]+', String.Escape, '#pop'),
            (r'x[\da-fA-F]+', String.Escape, '#pop'),
            (r'\d+', String.Escape, '#pop'),
        ],
    }


class OcamlLexer(RegexLexer):
    """
    For the OCaml language.

    *New in Pygments 0.7.*
    """

    name = 'OCaml'
    aliases = ['ocaml']
    filenames = ['*.ml', '*.mli', '*.mll', '*.mly']
    mimetypes = ['text/x-ocaml']

    keywords = [
      'as', 'assert', 'begin', 'class', 'constraint', 'do', 'done',
      'downto', 'else', 'end', 'exception', 'external', 'false',
      'for', 'fun', 'function', 'functor', 'if', 'in', 'include',
      'inherit', 'initializer', 'lazy', 'let', 'match', 'method',
      'module', 'mutable', 'new', 'object', 'of', 'open', 'private',
      'raise', 'rec', 'sig', 'struct', 'then', 'to', 'true', 'try',
      'type', 'val', 'virtual', 'when', 'while', 'with'
    ]
    keyopts = [
      '!=','#','&','&&','\(','\)','\*','\+',',','-',
      '-\.','->','\.','\.\.',':','::',':=',':>',';',';;','<',
      '<-','=','>','>]','>}','\?','\?\?','\[','\[<','\[>','\[\|',
      ']','_','`','{','{<','\|','\|]','}','~'
    ]

    operators = r'[!$%&*+\./:<=>?@^|~-]'
    word_operators = ['and', 'asr', 'land', 'lor', 'lsl', 'lxor', 'mod', 'or']
    prefix_syms = r'[!?~]'
    infix_syms = r'[=<>@^|&+\*/$%-]'
    primitives = ['unit', 'int', 'float', 'bool', 'string', 'char', 'list', 'array']

    tokens = {
        'escape-sequence': [
            (r'\\[\"\'ntbr]', String.Escape),
            (r'\\[0-9]{3}', String.Escape),
            (r'\\x[0-9a-fA-F]{2}', String.Escape),
        ],
        'root': [
            (r'\s+', Text),
            (r'false|true|\(\)|\[\]', Name.Builtin.Pseudo),
            (r'\b([A-Z][A-Za-z0-9_\']*)(?=\s*\.)',
             Name.Namespace, 'dotted'),
            (r'\b([A-Z][A-Za-z0-9_\']*)', Name.Class),
            (r'\(\*', Comment, 'comment'),
            (r'\b(%s)\b' % '|'.join(keywords), Keyword),
            (r'(%s)' % '|'.join(keyopts), Operator),
            (r'(%s|%s)?%s' % (infix_syms, prefix_syms, operators), Operator),
            (r'\b(%s)\b' % '|'.join(word_operators), Operator.Word),
            (r'\b(%s)\b' % '|'.join(primitives), Keyword.Type),

            (r"[^\W\d][\w']*", Name),

            (r'\d[\d_]*', Number.Integer),
            (r'0[xX][\da-fA-F][\da-fA-F_]*', Number.Hex),
            (r'0[oO][0-7][0-7_]*', Number.Oct),
            (r'0[bB][01][01_]*', Number.Binary),
            (r'-?\d[\d_]*(.[\d_]*)?([eE][+\-]?\d[\d_]*)', Number.Float),

            (r"'(?:(\\[\\\"'ntbr ])|(\\[0-9]{3})|(\\x[0-9a-fA-F]{2}))'",
             String.Char),
            (r"'.'", String.Char),
            (r"'", Keyword), # a stray quote is another syntax element

            (r'"', String.Double, 'string'),

            (r'[~?][a-z][\w\']*:', Name.Variable),
        ],
        'comment': [
            (r'[^(*)]', Comment),
            (r'\(\*', Comment, '#push'),
            (r'\*\)', Comment, '#pop'),
            (r'[(*)]', Comment),
        ],
        'string': [
            (r'[^\\"]', String.Double),
            include('escape-sequence'),
            (r'\\\n', String.Double),
            (r'"', String.Double, '#pop'),
        ],
        'dotted': [
            (r'\s+', Text),
            (r'\.', Punctuation),
            (r'[A-Z][A-Za-z0-9_\']*(?=\s*\.)', Name.Namespace),
            (r'[A-Z][A-Za-z0-9_\']*', Name.Class, '#pop'),
            (r'[a-z][a-z0-9_\']*', Name, '#pop'),
        ],
    }