1"""
2 pygments.lexers.dylan
3 ~~~~~~~~~~~~~~~~~~~~~
4
5 Lexers for the Dylan language.
6
7 :copyright: Copyright 2006-2025 by the Pygments team, see AUTHORS.
8 :license: BSD, see LICENSE for details.
9"""
10
11import re
12
13from pygments.lexer import Lexer, RegexLexer, bygroups, do_insertions, \
14 default, line_re
15from pygments.token import Comment, Operator, Keyword, Name, String, \
16 Number, Punctuation, Generic, Literal, Whitespace
17
18__all__ = ['DylanLexer', 'DylanConsoleLexer', 'DylanLidLexer']
19
20
21class DylanLexer(RegexLexer):
22 """
23 For the Dylan language.
24 """
25
26 name = 'Dylan'
27 url = 'http://www.opendylan.org/'
28 aliases = ['dylan']
29 filenames = ['*.dylan', '*.dyl', '*.intr']
30 mimetypes = ['text/x-dylan']
31 version_added = '0.7'
32
33 flags = re.IGNORECASE
34
35 builtins = {
36 'subclass', 'abstract', 'block', 'concrete', 'constant', 'class',
37 'compiler-open', 'compiler-sideways', 'domain', 'dynamic',
38 'each-subclass', 'exception', 'exclude', 'function', 'generic',
39 'handler', 'inherited', 'inline', 'inline-only', 'instance',
40 'interface', 'import', 'keyword', 'library', 'macro', 'method',
41 'module', 'open', 'primary', 'required', 'sealed', 'sideways',
42 'singleton', 'slot', 'thread', 'variable', 'virtual'}
43
44 keywords = {
45 'above', 'afterwards', 'begin', 'below', 'by', 'case', 'cleanup',
46 'create', 'define', 'else', 'elseif', 'end', 'export', 'finally',
47 'for', 'from', 'if', 'in', 'let', 'local', 'otherwise', 'rename',
48 'select', 'signal', 'then', 'to', 'unless', 'until', 'use', 'when',
49 'while'}
50
51 operators = {
52 '~', '+', '-', '*', '|', '^', '=', '==', '~=', '~==', '<', '<=',
53 '>', '>=', '&', '|'}
54
55 functions = {
56 'abort', 'abs', 'add', 'add!', 'add-method', 'add-new', 'add-new!',
57 'all-superclasses', 'always', 'any?', 'applicable-method?', 'apply',
58 'aref', 'aref-setter', 'as', 'as-lowercase', 'as-lowercase!',
59 'as-uppercase', 'as-uppercase!', 'ash', 'backward-iteration-protocol',
60 'break', 'ceiling', 'ceiling/', 'cerror', 'check-type', 'choose',
61 'choose-by', 'complement', 'compose', 'concatenate', 'concatenate-as',
62 'condition-format-arguments', 'condition-format-string', 'conjoin',
63 'copy-sequence', 'curry', 'default-handler', 'dimension', 'dimensions',
64 'direct-subclasses', 'direct-superclasses', 'disjoin', 'do',
65 'do-handlers', 'element', 'element-setter', 'empty?', 'error', 'even?',
66 'every?', 'false-or', 'fill!', 'find-key', 'find-method', 'first',
67 'first-setter', 'floor', 'floor/', 'forward-iteration-protocol',
68 'function-arguments', 'function-return-values',
69 'function-specializers', 'gcd', 'generic-function-mandatory-keywords',
70 'generic-function-methods', 'head', 'head-setter', 'identity',
71 'initialize', 'instance?', 'integral?', 'intersection',
72 'key-sequence', 'key-test', 'last', 'last-setter', 'lcm', 'limited',
73 'list', 'logand', 'logbit?', 'logior', 'lognot', 'logxor', 'make',
74 'map', 'map-as', 'map-into', 'max', 'member?', 'merge-hash-codes',
75 'min', 'modulo', 'negative', 'negative?', 'next-method',
76 'object-class', 'object-hash', 'odd?', 'one-of', 'pair', 'pop',
77 'pop-last', 'positive?', 'push', 'push-last', 'range', 'rank',
78 'rcurry', 'reduce', 'reduce1', 'remainder', 'remove', 'remove!',
79 'remove-duplicates', 'remove-duplicates!', 'remove-key!',
80 'remove-method', 'replace-elements!', 'replace-subsequence!',
81 'restart-query', 'return-allowed?', 'return-description',
82 'return-query', 'reverse', 'reverse!', 'round', 'round/',
83 'row-major-index', 'second', 'second-setter', 'shallow-copy',
84 'signal', 'singleton', 'size', 'size-setter', 'slot-initialized?',
85 'sort', 'sort!', 'sorted-applicable-methods', 'subsequence-position',
86 'subtype?', 'table-protocol', 'tail', 'tail-setter', 'third',
87 'third-setter', 'truncate', 'truncate/', 'type-error-expected-type',
88 'type-error-value', 'type-for-copy', 'type-union', 'union', 'values',
89 'vector', 'zero?'}
90
91 valid_name = '\\\\?[\\w!&*<>|^$%@\\-+~?/=]+'
92
93 def get_tokens_unprocessed(self, text):
94 for index, token, value in RegexLexer.get_tokens_unprocessed(self, text):
95 if token is Name:
96 lowercase_value = value.lower()
97 if lowercase_value in self.builtins:
98 yield index, Name.Builtin, value
99 continue
100 if lowercase_value in self.keywords:
101 yield index, Keyword, value
102 continue
103 if lowercase_value in self.functions:
104 yield index, Name.Builtin, value
105 continue
106 if lowercase_value in self.operators:
107 yield index, Operator, value
108 continue
109 yield index, token, value
110
111 tokens = {
112 'root': [
113 # Whitespace
114 (r'\s+', Whitespace),
115
116 # single line comment
117 (r'//.*?\n', Comment.Single),
118
119 # lid header
120 (r'([a-z0-9-]+)(:)([ \t]*)(.*(?:\n[ \t].+)*)',
121 bygroups(Name.Attribute, Operator, Whitespace, String)),
122
123 default('code') # no header match, switch to code
124 ],
125 'code': [
126 # Whitespace
127 (r'\s+', Whitespace),
128
129 # single line comment
130 (r'(//.*?)(\n)', bygroups(Comment.Single, Whitespace)),
131
132 # multi-line comment
133 (r'/\*', Comment.Multiline, 'comment'),
134
135 # strings and characters
136 (r'"', String, 'string'),
137 (r"'(\\.|\\[0-7]{1,3}|\\x[a-f0-9]{1,2}|[^\\\'\n])'", String.Char),
138
139 # binary integer
140 (r'#b[01]+', Number.Bin),
141
142 # octal integer
143 (r'#o[0-7]+', Number.Oct),
144
145 # floating point
146 (r'[-+]?(\d*\.\d+(e[-+]?\d+)?|\d+(\.\d*)?e[-+]?\d+)', Number.Float),
147
148 # decimal integer
149 (r'[-+]?\d+', Number.Integer),
150
151 # hex integer
152 (r'#x[0-9a-f]+', Number.Hex),
153
154 # Macro parameters
155 (r'(\?' + valid_name + ')(:)'
156 r'(token|name|variable|expression|body|case-body|\*)',
157 bygroups(Name.Tag, Operator, Name.Builtin)),
158 (r'(\?)(:)(token|name|variable|expression|body|case-body|\*)',
159 bygroups(Name.Tag, Operator, Name.Builtin)),
160 (r'\?' + valid_name, Name.Tag),
161
162 # Punctuation
163 (r'(=>|::|#\(|#\[|##|\?\?|\?=|\?|[(){}\[\],.;])', Punctuation),
164
165 # Most operators are picked up as names and then re-flagged.
166 # This one isn't valid in a name though, so we pick it up now.
167 (r':=', Operator),
168
169 # Pick up #t / #f before we match other stuff with #.
170 (r'#[tf]', Literal),
171
172 # #"foo" style keywords
173 (r'#"', String.Symbol, 'keyword'),
174
175 # #rest, #key, #all-keys, etc.
176 (r'#[a-z0-9-]+', Keyword),
177
178 # required-init-keyword: style keywords.
179 (valid_name + ':', Keyword),
180
181 # class names
182 ('<' + valid_name + '>', Name.Class),
183
184 # define variable forms.
185 (r'\*' + valid_name + r'\*', Name.Variable.Global),
186
187 # define constant forms.
188 (r'\$' + valid_name, Name.Constant),
189
190 # everything else. We re-flag some of these in the method above.
191 (valid_name, Name),
192 ],
193 'comment': [
194 (r'[^*/]+', Comment.Multiline),
195 (r'/\*', Comment.Multiline, '#push'),
196 (r'\*/', Comment.Multiline, '#pop'),
197 (r'[*/]', Comment.Multiline)
198 ],
199 'keyword': [
200 (r'"', String.Symbol, '#pop'),
201 (r'[^\\"]+', String.Symbol), # all other characters
202 ],
203 'string': [
204 (r'"', String, '#pop'),
205 (r'\\([\\abfnrtv"\']|x[a-f0-9]{2,4}|[0-7]{1,3})', String.Escape),
206 (r'[^\\"\n]+', String), # all other characters
207 (r'\\\n', String), # line continuation
208 (r'\\', String), # stray backslash
209 ]
210 }
211
212
213class DylanLidLexer(RegexLexer):
214 """
215 For Dylan LID (Library Interchange Definition) files.
216 """
217
218 name = 'DylanLID'
219 aliases = ['dylan-lid', 'lid']
220 filenames = ['*.lid', '*.hdp']
221 mimetypes = ['text/x-dylan-lid']
222 url = 'http://www.opendylan.org/'
223 version_added = '1.6'
224 flags = re.IGNORECASE
225
226 tokens = {
227 'root': [
228 # Whitespace
229 (r'\s+', Whitespace),
230
231 # single line comment
232 (r'(//.*?)(\n)', bygroups(Comment.Single, Whitespace)),
233
234 # lid header
235 (r'(.*?)(:)([ \t]*)(.*(?:\n[ \t].+)*)',
236 bygroups(Name.Attribute, Operator, Whitespace, String)),
237 ]
238 }
239
240
241class DylanConsoleLexer(Lexer):
242 """
243 For Dylan interactive console output.
244
245 This is based on a copy of the ``RubyConsoleLexer``.
246 """
247 name = 'Dylan session'
248 aliases = ['dylan-console', 'dylan-repl']
249 filenames = ['*.dylan-console']
250 mimetypes = ['text/x-dylan-console']
251 url = 'http://www.opendylan.org/'
252 version_added = '1.6'
253 _example = 'dylan-console/console.dylan-console'
254
255 _prompt_re = re.compile(r'\?| ')
256
257 def get_tokens_unprocessed(self, text):
258 dylexer = DylanLexer(**self.options)
259
260 curcode = ''
261 insertions = []
262 for match in line_re.finditer(text):
263 line = match.group()
264 m = self._prompt_re.match(line)
265 if m is not None:
266 end = m.end()
267 insertions.append((len(curcode),
268 [(0, Generic.Prompt, line[:end])]))
269 curcode += line[end:]
270 else:
271 if curcode:
272 yield from do_insertions(insertions,
273 dylexer.get_tokens_unprocessed(curcode))
274 curcode = ''
275 insertions = []
276 yield match.start(), Generic.Output, line
277 if curcode:
278 yield from do_insertions(insertions,
279 dylexer.get_tokens_unprocessed(curcode))