Added Smithy Lexer (#1878) (#1879)

* Added Smithy Lexer (#1878)

* Added Smithy Lexer
* Added Smithy Lexer auhtor
* Documented Smithy as a supported language
* Added Smithy test file and output

* Updated Smithy Lexer

* Added Standard file heading with copyright and license
* Used `words` method for optimization, instead of bare regex
* Specified whitespace punctuation in root
* Updated aliases to only contain lowercase names to pass `test_basic_api` tests
* Updated regexes lightly to fit regexlint rules (removing duplicate characters in group `-`)
* Fixed regexes with errors in regexlint rules (Escaping brackets, gaps in capture groups)

* Ran mapping script to fix build check

* Ran mapping to update after changing aliases in previous commit

AUTHORS

@@ -227,6 +227,7 @@ Other contributors, listed alphabetically, are:
 * Matthias Vallentin -- Bro lexer
 * Benoît Vinot -- AMPL lexer
 * Linh Vu Hong -- RSL lexer
+* Immanuel Washington -- Smithy lexer
 * Nathan Weizenbaum -- Haml and Sass lexers
 * Nathan Whetsell -- Csound lexers
 * Dietmar Winkler -- Modelica lexer

doc/languages.rst

@@ -280,6 +280,7 @@ Other markup
 * Scdoc
 * Sieve
 * Singularity
+* `Smithy <https://awslabs.github.io/smithy/>`_
 * SPARQL
 * SQL, also MySQL, SQLite
 * Squid configuration

pygments/lexers/_mapping.py

@@ -431,6 +431,7 @@
     'SmalltalkLexer': ('pygments.lexers.smalltalk', 'Smalltalk', ('smalltalk', 'squeak', 'st'), ('*.st',), ('text/x-smalltalk',)),
     'SmartGameFormatLexer': ('pygments.lexers.sgf', 'SmartGameFormat', ('sgf',), ('*.sgf',), ()),
     'SmartyLexer': ('pygments.lexers.templates', 'Smarty', ('smarty',), ('*.tpl',), ('application/x-smarty',)),
+    'SmithyLexer': ('pygments.lexers.smithy', 'Smithy', ('smithy',), ('*.smithy',), ()),
     'SnobolLexer': ('pygments.lexers.snobol', 'Snobol', ('snobol',), ('*.snobol',), ('text/x-snobol',)),
     'SnowballLexer': ('pygments.lexers.dsls', 'Snowball', ('snowball',), ('*.sbl',), ()),
     'SolidityLexer': ('pygments.lexers.solidity', 'Solidity', ('solidity',), ('*.sol',), ()),

pygments/lexers/smithy.py

@@ -0,0 +1,79 @@
+"""
+    pygments.lexers.smithy
+    ~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+    Lexers for the Smithy IDL.
+
+    :copyright: Copyright 2006-2021 by the Pygments team, see AUTHORS.
+    :license: BSD, see LICENSE for details.
+"""
+
+import re
+
+from pygments.lexer import RegexLexer, bygroups, words
+from pygments.token import Text, Comment, Keyword, Name, String, \
+    Number, Whitespace, Punctuation
+
+__all__ = ['SmithyLexer']
+
+
+class SmithyLexer(RegexLexer):
+    """
+    For Smithy IDL
+
+    .. versionadded:: 2.10
+    """
+    name = 'Smithy'
+    filenames = ['*.smithy']
+    aliases = ['smithy']
+
+    flags = re.MULTILINE | re.UNICODE
+    unquoted = r'[A-Za-z0-9_\.#$-]+'
+    identifier = r"[A-Za-z0-9_\.#$-]+"
+
+    simple_shapes = (
+        'use', 'byte', 'short', 'integer', 'long', 'float', 'document',
+        'double', 'bigInteger', 'bigDecimal', 'boolean', 'blob', 'string',
+        'timestamp',
+    )
+
+    aggregate_shapes = (
+       'apply', 'list', 'map', 'set', 'structure', 'union', 'resource',
+       'operation', 'service', 'trait'
+    )
+
+    tokens = {
+        'root': [
+            (r'///.*$', Comment.Multiline),
+            (r'//.*$', Comment),
+            (r'@[0-9a-zA-Z\.#-]*', Name.Decorator),
+            (r'(=)', Name.Decorator),
+            (r'^(\$version)(:)(.+)',
+                bygroups(Keyword.Declaration, Name.Decorator, Name.Class)),
+            (r'^(namespace)(\s+' + identifier + r')\b',
+                bygroups(Keyword.Declaration, Name.Class)),
+            (words(simple_shapes,
+                   prefix=r'^', suffix=r'(\s+' + identifier + r')\b'),
+                bygroups(Keyword.Declaration, Name.Class)),
+            (words(aggregate_shapes,
+                   prefix=r'^', suffix=r'(\s+' + identifier + r')'),
+                bygroups(Keyword.Declaration, Name.Class)),
+            (r'^(metadata)(\s+.+)(\s*)(=)',
+                bygroups(Keyword.Declaration, Name.Class, Whitespace, Name.Decorator)),
+            (r"(true|false|null)", Keyword.Constant),
+            (r"(-?(?:0|[1-9]\d*)(?:\.\d+)?(?:[eE][+-]?\d+)?)", Number),
+            (identifier + ":", Name.Label),
+            (identifier, Name.Variable.Class),
+            (r'\[', Text, "#push"),
+            (r'\]', Text, "#pop"),
+            (r'\(', Text, "#push"),
+            (r'\)', Text, "#pop"),
+            (r'\{', Text, "#push"),
+            (r'\}', Text, "#pop"),
+            (r'"{3}(\\\\|\n|\\")*"{3}', String.Doc),
+            (r'"(\\\\|\n|\\"|[^"])*"', String.Double),
+            (r"'(\\\\|\n|\\'|[^'])*'", String.Single),
+            (r'[:,]+', Punctuation),
+            (r'\s+', Whitespace),
+        ]
+    }