Add procfile lexer (#1808)

* add Procfile Lexer

* add unit tests for ProcfileLexer

* add Procfile lexer author

* Document Procfile as supported language

* add Procfile.output file

* merge Profile files; update output file

* Add versionadded info

* Fix typo (processus -> processes)

* detect Integer only

* split Text from Whitespace

AUTHORS

@@ -32,7 +32,7 @@ Other contributors, listed alphabetically, are:
 * Sébastien Bigaret -- QVT Operational lexer
 * Jarrett Billingsley -- MiniD lexer
 * Adam Blinkinsop -- Haskell, Redcode lexers
-* Stéphane Blondon -- SGF and Sieve lexers
+* Stéphane Blondon -- Procfile, SGF and Sieve lexers
 * Frits van Bommel -- assembler lexers
 * Pierre Bourdon -- bugfixes
 * Martijn Braam -- Kernel log lexer, BARE lexer

doc/languages.rst

@@ -264,6 +264,7 @@ Other markup
 * `OMG IDL <https://www.omg.org/spec/IDL/About-IDL/>`_
 * `PEG <https://bford.info/packrat/>`_
 * POV-Ray scenes
+* `Procfile <https://devcenter.heroku.com/articles/procfile#procfile-format>`_
 * `PromQL <https://prometheus.io/docs/prometheus/latest/querying/basics/>`_
 * `Puppet <https://puppet.com/>`_
 * QML

pygments/lexers/_mapping.py

@@ -357,6 +357,7 @@
     'PowerShellLexer': ('pygments.lexers.shell', 'PowerShell', ('powershell', 'posh', 'ps1', 'psm1'), ('*.ps1', '*.psm1'), ('text/x-powershell',)),
     'PowerShellSessionLexer': ('pygments.lexers.shell', 'PowerShell Session', ('ps1con',), (), ()),
     'PraatLexer': ('pygments.lexers.praat', 'Praat', ('praat',), ('*.praat', '*.proc', '*.psc'), ()),
+    'ProcfileLexer': ('pygments.lexers.procfile', 'Procfile', ('procfile',), ('Procfile',), ()),
     'PrologLexer': ('pygments.lexers.prolog', 'Prolog', ('prolog',), ('*.ecl', '*.prolog', '*.pro', '*.pl'), ('text/x-prolog',)),
     'PromQLLexer': ('pygments.lexers.promql', 'PromQL', ('promql',), ('*.promql',), ()),
     'PropertiesLexer': ('pygments.lexers.configs', 'Properties', ('properties', 'jproperties'), ('*.properties',), ('text/x-java-properties',)),

pygments/lexers/procfile.py

@@ -0,0 +1,43 @@
+"""
+    pygments.lexers.procfile
+    ~~~~~~~~~~~~~~~~~~~~~~~~
+
+    Lexer for Procfile file format.
+
+    :copyright: Copyright 2006-2021 by the Pygments team, see AUTHORS.
+    :license: BSD, see LICENSE for details.
+"""
+
+from pygments.lexer import RegexLexer, bygroups
+from pygments.token import Name, Number, String, Text, Punctuation
+
+__all__ = ["ProcfileLexer"]
+
+
+class ProcfileLexer(RegexLexer):
+    """
+    Lexer for Procfile file format.
+
+    The format is used to run processes on Heroku or is used by Foreman or
+    Honcho tools.
+    For more information about the definition of the format, see:
+    https://devcenter.heroku.com/articles/procfile#procfile-format
+
+    .. versionadded:: 2.10
+    """
+    name = 'Procfile'
+    aliases = ['procfile']
+    filenames = ['Procfile']
+
+    tokens = {
+        'root': [
+            (r'^([a-z]+)(:)', bygroups(Name.Label, Punctuation)),
+            (r'\s+', Text.Whitespace),
+            (r'"[^"]*"', String),
+            (r"'[^']*'", String),
+            (r'[0-9]+', Number.Integer),
+            (r'\$[a-zA-Z_][\w]*', Name.Variable),
+            (r'(\w+)(=)(\w+)', bygroups(Name.Variable, Punctuation, String)),
+            (r'([\w\-\./]+)', Text),
+        ],
+    }

tests/examplefiles/procfile/Procfile

@@ -0,0 +1,3 @@
+db: runzeo -C zeoserver.config
+web: bundle exec rails server -p $PORT
+stuff: env FLASK_ENV=development run -p 9 --stuff 'foobar'

tests/test_procfile.py

@@ -0,0 +1,40 @@
+# -*- coding: utf-8 -*-
+"""
+    Basic ProcfileLexer Test
+    ~~~~~~~~~~~~~~~~~~~~
+
+    :copyright: Copyright 2006-2020 by the Pygments team, see AUTHORS.
+    :license: BSD, see LICENSE for details.
+"""
+
+import pytest
+
+from pygments.token import Name, Punctuation, Text
+from pygments.lexers.procfile import ProcfileLexer
+
+
+@pytest.fixture(scope='module')
+def lexer():
+    yield ProcfileLexer()
+
+
+def test_basic_line(lexer):
+    text = 'task: executable --options'
+
+    tokens = lexer.get_tokens(text)
+
+    for index, token in enumerate(tokens):
+        if index == 0:
+            assert token == (Name.Label, 'task')
+        elif index == 1:
+            assert token == (Punctuation, ':')
+        else:
+            assert token[0] in (Text, Text.Whitespace)
+
+
+def test_environment_variable(lexer):
+    text = '$XDG_SESSION_PATH'
+
+    token = list(lexer.get_tokens(text))[0]
+
+    assert token == (Name.Variable, text)