Shortcuts on this page
r m x toggle line displays
j k next/prev highlighted chunk
0 (zero) top of page
1 (one) first highlighted chunk
1"""
2 pygments.lexers.julia
3 ~~~~~~~~~~~~~~~~~~~~~
5 Lexers for the Julia language.
7 :copyright: Copyright 2006-2025 by the Pygments team, see AUTHORS.
8 :license: BSD, see LICENSE for details.
9"""
11from pygments.lexer import Lexer, RegexLexer, bygroups, do_insertions, \
12 words, include
13from pygments.token import Text, Comment, Operator, Keyword, Name, String, \
14 Number, Punctuation, Generic, Whitespace
15from pygments.util import shebang_matches
16from pygments.lexers._julia_builtins import OPERATORS_LIST, DOTTED_OPERATORS_LIST, \
17 KEYWORD_LIST, BUILTIN_LIST, LITERAL_LIST
19__all__ = ['JuliaLexer', 'JuliaConsoleLexer']
21# see https://docs.julialang.org/en/v1/manual/variables/#Allowed-Variable-Names
22allowed_variable = \
23 '(?:[a-zA-Z_\u00A1-\U0010ffff][a-zA-Z_0-9!\u00A1-\U0010ffff]*)'
24# see https://github.com/JuliaLang/julia/blob/master/src/flisp/julia_opsuffs.h
25operator_suffixes = r'[²³¹ʰʲʳʷʸˡˢˣᴬᴮᴰᴱᴳᴴᴵᴶᴷᴸᴹᴺᴼᴾᴿᵀᵁᵂᵃᵇᵈᵉᵍᵏᵐᵒᵖᵗᵘᵛᵝᵞᵟᵠᵡᵢᵣᵤᵥᵦᵧᵨᵩᵪᶜᶠᶥᶦᶫᶰᶸᶻᶿ′″‴‵‶‷⁗⁰ⁱ⁴⁵⁶⁷⁸⁹⁺⁻⁼⁽⁾ⁿ₀₁₂₃₄₅₆₇₈₉₊₋₌₍₎ₐₑₒₓₕₖₗₘₙₚₛₜⱼⱽ]*'
27class JuliaLexer(RegexLexer):
28 """
29 For Julia source code.
30 """
32 name = 'Julia'
33 url = 'https://julialang.org/'
34 aliases = ['julia', 'jl']
35 filenames = ['*.jl']
36 mimetypes = ['text/x-julia', 'application/x-julia']
37 version_added = '1.6'
39 tokens = {
40 'root': [
41 (r'\n', Whitespace),
42 (r'[^\S\n]+', Whitespace),
43 (r'#=', Comment.Multiline, "blockcomment"),
44 (r'#.*$', Comment),
45 (r'[\[\](),;]', Punctuation),
47 # symbols
48 # intercept range expressions first
49 (r'(' + allowed_variable + r')(\s*)(:)(' + allowed_variable + ')',
50 bygroups(Name, Whitespace, Operator, Name)),
51 # then match :name which does not follow closing brackets, digits, or the
52 # ::, <:, and :> operators
53 (r'(?<![\]):<>\d.])(:' + allowed_variable + ')', String.Symbol),
55 # type assertions - excludes expressions like ::typeof(sin) and ::avec[1]
56 (r'(?<=::)(\s*)(' + allowed_variable + r')\b(?![(\[])',
57 bygroups(Whitespace, Keyword.Type)),
58 # type comparisons
59 # - MyType <: A or MyType >: A
60 ('(' + allowed_variable + r')(\s*)([<>]:)(\s*)(' + allowed_variable + r')\b(?![(\[])',
61 bygroups(Keyword.Type, Whitespace, Operator, Whitespace, Keyword.Type)),
62 # - <: B or >: B
63 (r'([<>]:)(\s*)(' + allowed_variable + r')\b(?![(\[])',
64 bygroups(Operator, Whitespace, Keyword.Type)),
65 # - A <: or A >:
66 (r'\b(' + allowed_variable + r')(\s*)([<>]:)',
67 bygroups(Keyword.Type, Whitespace, Operator)),
69 # operators
70 # Suffixes aren't actually allowed on all operators, but we'll ignore that
71 # since those cases are invalid Julia code.
72 (words([*OPERATORS_LIST, *DOTTED_OPERATORS_LIST],
73 suffix=operator_suffixes), Operator),
74 (words(['.' + o for o in DOTTED_OPERATORS_LIST],
75 suffix=operator_suffixes), Operator),
76 (words(['...', '..']), Operator),
78 # NOTE
79 # Patterns below work only for definition sites and thus hardly reliable.
80 #
81 # functions
82 # (r'(function)(\s+)(' + allowed_variable + ')',
83 # bygroups(Keyword, Text, Name.Function)),
85 # chars
86 (r"'(\\.|\\[0-7]{1,3}|\\x[a-fA-F0-9]{1,3}|\\u[a-fA-F0-9]{1,4}|"
87 r"\\U[a-fA-F0-9]{1,6}|[^\\\'\n])'", String.Char),
89 # try to match trailing transpose
90 (r'(?<=[.\w)\]])(\'' + operator_suffixes + ')+', Operator),
92 # raw strings
93 (r'(raw)(""")', bygroups(String.Affix, String), 'tqrawstring'),
94 (r'(raw)(")', bygroups(String.Affix, String), 'rawstring'),
95 # regular expressions
96 (r'(r)(""")', bygroups(String.Affix, String.Regex), 'tqregex'),
97 (r'(r)(")', bygroups(String.Affix, String.Regex), 'regex'),
98 # other strings
99 (r'(' + allowed_variable + ')?(""")',
100 bygroups(String.Affix, String), 'tqstring'),
101 (r'(' + allowed_variable + ')?(")',
102 bygroups(String.Affix, String), 'string'),
104 # backticks
105 (r'(' + allowed_variable + ')?(```)',
106 bygroups(String.Affix, String.Backtick), 'tqcommand'),
107 (r'(' + allowed_variable + ')?(`)',
108 bygroups(String.Affix, String.Backtick), 'command'),
110 # type names
111 # - names that begin a curly expression
112 ('(' + allowed_variable + r')(\{)',
113 bygroups(Keyword.Type, Punctuation), 'curly'),
114 # - names as part of bare 'where'
115 (r'(where)(\s+)(' + allowed_variable + ')',
116 bygroups(Keyword, Whitespace, Keyword.Type)),
117 # - curly expressions in general
118 (r'(\{)', Punctuation, 'curly'),
119 # - names as part of type declaration
120 (r'(abstract|primitive)([ \t]+)(type\b)([\s()]+)(' +
121 allowed_variable + r')',
122 bygroups(Keyword, Whitespace, Keyword, Text, Keyword.Type)),
123 (r'(mutable(?=[ \t]))?([ \t]+)?(struct\b)([\s()]+)(' +
124 allowed_variable + r')',
125 bygroups(Keyword, Whitespace, Keyword, Text, Keyword.Type)),
127 # macros
128 (r'@' + allowed_variable, Name.Decorator),
129 (words([*OPERATORS_LIST, '..', '.', *DOTTED_OPERATORS_LIST],
130 prefix='@', suffix=operator_suffixes), Name.Decorator),
132 # keywords
133 (words(KEYWORD_LIST, suffix=r'\b'), Keyword),
134 # builtin types
135 (words(BUILTIN_LIST, suffix=r'\b'), Keyword.Type),
136 # builtin literals
137 (words(LITERAL_LIST, suffix=r'\b'), Name.Builtin),
139 # names
140 (allowed_variable, Name),
142 # numbers
143 (r'(\d+((_\d+)+)?\.(?!\.)(\d+((_\d+)+)?)?|\.\d+((_\d+)+)?)([eEf][+-]?[0-9]+)?', Number.Float),
144 (r'\d+((_\d+)+)?[eEf][+-]?[0-9]+', Number.Float),
145 (r'0x[a-fA-F0-9]+((_[a-fA-F0-9]+)+)?(\.([a-fA-F0-9]+((_[a-fA-F0-9]+)+)?)?)?p[+-]?\d+', Number.Float),
146 (r'0b[01]+((_[01]+)+)?', Number.Bin),
147 (r'0o[0-7]+((_[0-7]+)+)?', Number.Oct),
148 (r'0x[a-fA-F0-9]+((_[a-fA-F0-9]+)+)?', Number.Hex),
149 (r'\d+((_\d+)+)?', Number.Integer),
151 # single dot operator matched last to permit e.g. ".1" as a float
152 (words(['.']), Operator),
153 ],
155 "blockcomment": [
156 (r'[^=#]', Comment.Multiline),
157 (r'#=', Comment.Multiline, '#push'),
158 (r'=#', Comment.Multiline, '#pop'),
159 (r'[=#]', Comment.Multiline),
160 ],
162 'curly': [
163 (r'\{', Punctuation, '#push'),
164 (r'\}', Punctuation, '#pop'),
165 (allowed_variable, Keyword.Type),
166 include('root'),
167 ],
169 'tqrawstring': [
170 (r'"""', String, '#pop'),
171 (r'([^"]|"[^"][^"])+', String),
172 ],
173 'rawstring': [
174 (r'"', String, '#pop'),
175 (r'\\"', String.Escape),
176 (r'([^"\\]|\\[^"])+', String),
177 ],
179 # Interpolation is defined as "$" followed by the shortest full
180 # expression, which is something we can't parse. Include the most
181 # common cases here: $word, and $(paren'd expr).
182 'interp': [
183 (r'\$' + allowed_variable, String.Interpol),
184 (r'(\$)(\()', bygroups(String.Interpol, Punctuation), 'in-intp'),
185 ],
186 'in-intp': [
187 (r'\(', Punctuation, '#push'),
188 (r'\)', Punctuation, '#pop'),
189 include('root'),
190 ],
192 'string': [
193 (r'(")(' + allowed_variable + r'|\d+)?',
194 bygroups(String, String.Affix), '#pop'),
195 # FIXME: This escape pattern is not perfect.
196 (r'\\([\\"\'$nrbtfav]|(x|u|U)[a-fA-F0-9]+|\d+)', String.Escape),
197 include('interp'),
198 # @printf and @sprintf formats
199 (r'%[-#0 +]*([0-9]+|[*])?(\.([0-9]+|[*]))?[hlL]?[E-GXc-giorsux%]',
200 String.Interpol),
201 (r'[^"$%\\]+', String),
202 (r'.', String),
203 ],
204 'tqstring': [
205 (r'(""")(' + allowed_variable + r'|\d+)?',
206 bygroups(String, String.Affix), '#pop'),
207 (r'\\([\\"\'$nrbtfav]|(x|u|U)[a-fA-F0-9]+|\d+)', String.Escape),
208 include('interp'),
209 (r'[^"$%\\]+', String),
210 (r'.', String),
211 ],
213 'regex': [
214 (r'(")([imsxa]*)?', bygroups(String.Regex, String.Affix), '#pop'),
215 (r'\\"', String.Regex),
216 (r'[^\\"]+', String.Regex),
217 ],
219 'tqregex': [
220 (r'(""")([imsxa]*)?', bygroups(String.Regex, String.Affix), '#pop'),
221 (r'[^"]+', String.Regex),
222 ],
224 'command': [
225 (r'(`)(' + allowed_variable + r'|\d+)?',
226 bygroups(String.Backtick, String.Affix), '#pop'),
227 (r'\\[`$]', String.Escape),
228 include('interp'),
229 (r'[^\\`$]+', String.Backtick),
230 (r'.', String.Backtick),
231 ],
232 'tqcommand': [
233 (r'(```)(' + allowed_variable + r'|\d+)?',
234 bygroups(String.Backtick, String.Affix), '#pop'),
235 (r'\\\$', String.Escape),
236 include('interp'),
237 (r'[^\\`$]+', String.Backtick),
238 (r'.', String.Backtick),
239 ],
240 }
242 def analyse_text(text):
243 return shebang_matches(text, r'julia')
246class JuliaConsoleLexer(Lexer):
247 """
248 For Julia console sessions. Modeled after MatlabSessionLexer.
249 """
250 name = 'Julia console'
251 aliases = ['jlcon', 'julia-repl']
252 url = 'https://julialang.org/'
253 version_added = '1.6'
254 _example = "jlcon/console"
256 def get_tokens_unprocessed(self, text):
257 jllexer = JuliaLexer(**self.options)
258 start = 0
259 curcode = ''
260 insertions = []
261 output = False
262 error = False
264 for line in text.splitlines(keepends=True):
265 if line.startswith('julia>'):
266 insertions.append((len(curcode), [(0, Generic.Prompt, line[:6])]))
267 curcode += line[6:]
268 output = False
269 error = False
270 elif line.startswith('help?>') or line.startswith('shell>'):
271 yield start, Generic.Prompt, line[:6]
272 yield start + 6, Text, line[6:]
273 output = False
274 error = False
275 elif line.startswith(' ') and not output:
276 insertions.append((len(curcode), [(0, Whitespace, line[:6])]))
277 curcode += line[6:]
278 else:
279 if curcode:
280 yield from do_insertions(
281 insertions, jllexer.get_tokens_unprocessed(curcode))
282 curcode = ''
283 insertions = []
284 if line.startswith('ERROR: ') or error:
285 yield start, Generic.Error, line
286 error = True
287 else:
288 yield start, Generic.Output, line
289 output = True
290 start += len(line)
292 if curcode:
293 yield from do_insertions(
294 insertions, jllexer.get_tokens_unprocessed(curcode))