1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101

// Copyright (C) 2009 Google Inc.
//
// Licensed under the Apache License, Version 2.0 (the "License");
// you may not use this file except in compliance with the License.
// You may obtain a copy of the License at
//
//      http://www.apache.org/licenses/LICENSE-2.0
//
// Unless required by applicable law or agreed to in writing, software
// distributed under the License is distributed on an "AS IS" BASIS,
// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
// See the License for the specific language governing permissions and
// limitations under the License.



/**
 * @fileoverview
 * Registers a language handler for Haskell.
 *
 *
 * To use, include prettify.js and this file in your HTML page.
 * Then put your code in an HTML tag like
 *      <pre class="prettyprint lang-hs">(my lisp code)</pre>
 * The lang-cl class identifies the language as common lisp.
 * This file supports the following language extensions:
 *     lang-cl - Common Lisp
 *     lang-el - Emacs Lisp
 *     lang-lisp - Lisp
 *     lang-scm - Scheme
 *
 *
 * I used http://www.informatik.uni-freiburg.de/~thiemann/haskell/haskell98-report-html/syntax-iso.html
 * as the basis, but ignore the way the ncomment production nests since this
 * makes the lexical grammar irregular.  It might be possible to support
 * ncomments using the lookbehind filter.
 *
 *
 * @author mikesamuel@gmail.com
 */

PR['registerLangHandler'](
    PR['createSimpleLexer'](
        [
         // Whitespace
         // whitechar    ->    newline | vertab | space | tab | uniWhite
         // newline      ->    return linefeed | return | linefeed | formfeed
         [PR['PR_PLAIN'],       /^[\t\n\x0B\x0C\r ]+/, null, '\t\n\x0B\x0C\r '],
         // Single line double and single-quoted strings.
         // char         ->    ' (graphic<' | \> | space | escape<\&>) '
         // string       ->    " {graphic<" | \> | space | escape | gap}"
         // escape       ->    \ ( charesc | ascii | decimal | o octal
         //                        | x hexadecimal )
         // charesc      ->    a | b | f | n | r | t | v | \ | " | ' | &
         [PR['PR_STRING'],      /^\"(?:[^\"\\\n\x0C\r]|\\[\s\S])*(?:\"|$)/,
          null, '"'],
         [PR['PR_STRING'],      /^\'(?:[^\'\\\n\x0C\r]|\\[^&])\'?/,
          null, "'"],
         // decimal      ->    digit{digit}
         // octal        ->    octit{octit}
         // hexadecimal  ->    hexit{hexit}
         // integer      ->    decimal
         //               |    0o octal | 0O octal
         //               |    0x hexadecimal | 0X hexadecimal
         // float        ->    decimal . decimal [exponent]
         //               |    decimal exponent
         // exponent     ->    (e | E) [+ | -] decimal
         [PR['PR_LITERAL'],
          /^(?:0o[0-7]+|0x[\da-f]+|\d+(?:\.\d+)?(?:e[+\-]?\d+)?)/i,
          null, '0123456789']
        ],
        [
         // Haskell does not have a regular lexical grammar due to the nested
         // ncomment.
         // comment      ->    dashes [ any<symbol> {any}] newline
         // ncomment     ->    opencom ANYseq {ncomment ANYseq}closecom
         // dashes       ->    '--' {'-'}
         // opencom      ->    '{-'
         // closecom     ->    '-}'
         [PR['PR_COMMENT'],     /^(?:(?:--+(?:[^\r\n\x0C]*)?)|(?:\{-(?:[^-]|-+[^-\}])*-\}))/],
         // reservedid   ->    case | class | data | default | deriving | do
         //               |    else | if | import | in | infix | infixl | infixr
         //               |    instance | let | module | newtype | of | then
         //               |    type | where | _
         [PR['PR_KEYWORD'],     /^(?:case|class|data|default|deriving|do|else|if|import|in|infix|infixl|infixr|instance|let|module|newtype|of|then|type|where|_)(?=[^a-zA-Z0-9\']|$)/, null],
         // qvarid       ->    [ modid . ] varid
         // qconid       ->    [ modid . ] conid
         // varid        ->    (small {small | large | digit | ' })<reservedid>
         // conid        ->    large {small | large | digit | ' }
         // modid        ->    conid
         // small        ->    ascSmall | uniSmall | _
         // ascSmall     ->    a | b | ... | z
         // uniSmall     ->    any Unicode lowercase letter
         // large        ->    ascLarge | uniLarge
         // ascLarge     ->    A | B | ... | Z
         // uniLarge     ->    any uppercase or titlecase Unicode letter
         [PR['PR_PLAIN'],  /^(?:[A-Z][\w\']*\.)*[a-zA-Z][\w\']*/],
         // matches the symbol production
         [PR['PR_PUNCTUATION'], /^[^\t\n\x0B\x0C\r a-zA-Z0-9\'\"]+/]
        ]),
    ['hs']);