pygments.rb 1.1.2 → 2.0.0

data/vendor/pygments-main/pygments/lexers/make.py

@@ -5,7 +5,7 @@
 
     Lexers for Makefiles and similar.
 
-    :copyright: Copyright 2006-2015 by the Pygments team, see AUTHORS.
+    :copyright: Copyright 2006-2020 by the Pygments team, see AUTHORS.
     :license: BSD, see LICENSE for details.
 """
 
@@ -57,8 +57,7 @@ class MakefileLexer(Lexer):
                 ins.append((len(done), [(0, Comment, line)]))
             else:
                 done += line
-        for item in do_insertions(ins, lex.get_tokens_unprocessed(done)):
-            yield item
+        yield from do_insertions(ins, lex.get_tokens_unprocessed(done))
 
     def analyse_text(text):
         # Many makefiles have $(BIG_CAPS) style variables
@@ -102,8 +101,8 @@ class BaseMakefileLexer(RegexLexer):
             (r'\$\(', Keyword, 'expansion'),
         ],
         'expansion': [
-            (r'[^$a-zA-Z_()]+', Text),
-            (r'[a-zA-Z_]+', Name.Variable),
+            (r'[^\w$().-]+', Text),
+            (r'[\w.-]+', Name.Variable),
             (r'\$', Keyword),
             (r'\(', Keyword, '#push'),
             (r'\)', Keyword, '#pop'),
@@ -196,7 +195,12 @@ class CMakeLexer(RegexLexer):
     }
 
     def analyse_text(text):
-        exp = r'^ *CMAKE_MINIMUM_REQUIRED *\( *VERSION *\d(\.\d)* *( FATAL_ERROR)? *\) *$'
+        exp = (
+            r'^[ \t]*CMAKE_MINIMUM_REQUIRED[ \t]*'
+            r'\([ \t]*VERSION[ \t]*\d+(\.\d+)*[ \t]*'
+            r'([ \t]FATAL_ERROR)?[ \t]*\)[ \t]*'
+            r'(#[^\n]*)?$'
+       )
         if re.search(exp, text, flags=re.MULTILINE | re.IGNORECASE):
             return 0.8
         return 0.0

data/vendor/pygments-main/pygments/lexers/markup.py

@@ -5,7 +5,7 @@
 
     Lexers for non-HTML markup languages.
 
-    :copyright: Copyright 2006-2015 by the Pygments team, see AUTHORS.
+    :copyright: Copyright 2006-2020 by the Pygments team, see AUTHORS.
     :license: BSD, see LICENSE for details.
 """
 
@@ -24,7 +24,7 @@ from pygments.util import get_bool_opt, ClassNotFound
 __all__ = ['BBCodeLexer', 'MoinWikiLexer', 'RstLexer', 'TexLexer', 'GroffLexer',
            'MozPreprocHashLexer', 'MozPreprocPercentLexer',
            'MozPreprocXulLexer', 'MozPreprocJavascriptLexer',
-           'MozPreprocCssLexer', 'MarkdownLexer']
+           'MozPreprocCssLexer', 'MarkdownLexer', 'TiddlyWiki5Lexer']
 
 
 class BBCodeLexer(RegexLexer):
@@ -165,12 +165,11 @@ class RstLexer(RegexLexer):
                 code += line[indention_size:]
             else:
                 code += line
-        for item in do_insertions(ins, lexer.get_tokens_unprocessed(code)):
-            yield item
+        yield from do_insertions(ins, lexer.get_tokens_unprocessed(code))
 
     # from docutils.parsers.rst.states
-    closers = u'\'")]}>\u2019\u201d\xbb!?'
-    unicode_delimiters = u'\u2010\u2011\u2012\u2013\u2014\u00a0'
+    closers = '\'")]}>\u2019\u201d\xbb!?'
+    unicode_delimiters = '\u2010\u2011\u2012\u2013\u2014\u00a0'
     end_string_suffix = (r'((?=$)|(?=[-/:.,; \n\x00%s%s]))'
                          % (re.escape(unicode_delimiters),
                             re.escape(closers)))
@@ -204,7 +203,7 @@ class RstLexer(RegexLexer):
              bygroups(Text, Operator, using(this, state='inline'))),
             # Sourcecode directives
             (r'^( *\.\.)(\s*)((?:source)?code(?:-block)?)(::)([ \t]*)([^\n]+)'
-             r'(\n[ \t]*\n)([ \t]+)(.*)(\n)((?:(?:\8.*|)\n)+)',
+             r'(\n[ \t]*\n)([ \t]+)(.*)(\n)((?:(?:\8.*)?\n)+)',
              _handle_sourcecode),
             # A directive
             (r'^( *\.\.)(\s*)([\w:-]+?)(::)(?:([ \t]*)(.*))',
@@ -222,15 +221,14 @@ class RstLexer(RegexLexer):
                       Punctuation, Text, using(this, state='inline'))),
             # Comments
             (r'^ *\.\..*(\n( +.*\n|\n)+)?', Comment.Preproc),
-            # Field list
-            (r'^( *)(:[a-zA-Z-]+:)(\s*)$', bygroups(Text, Name.Class, Text)),
-            (r'^( *)(:.*?:)([ \t]+)(.*?)$',
-             bygroups(Text, Name.Class, Text, Name.Function)),
+            # Field list marker
+            (r'^( *)(:(?:\\\\|\\:|[^:\n])+:(?=\s))([ \t]*)',
+             bygroups(Text, Name.Class, Text)),
             # Definition list
             (r'^(\S.*(?<!::)\n)((?:(?: +.*)\n)+)',
              bygroups(using(this, state='inline'), using(this, state='inline'))),
             # Code blocks
-            (r'(::)(\n[ \t]*\n)([ \t]+)(.*)(\n)((?:(?:\3.*|)\n)+)',
+            (r'(::)(\n[ \t]*\n)([ \t]+)(.*)(\n)((?:(?:\3.*)?\n)+)',
              bygroups(String.Escape, Text, String, String, Text, String)),
             include('inline'),
         ],
@@ -463,8 +461,7 @@ class MozPreprocXulLexer(DelegatingLexer):
     mimetypes = []
 
     def __init__(self, **options):
-        super(MozPreprocXulLexer, self).__init__(
-            XmlLexer, MozPreprocHashLexer, **options)
+        super().__init__(XmlLexer, MozPreprocHashLexer, **options)
 
 
 class MozPreprocJavascriptLexer(DelegatingLexer):
@@ -480,8 +477,7 @@ class MozPreprocJavascriptLexer(DelegatingLexer):
     mimetypes = []
 
     def __init__(self, **options):
-        super(MozPreprocJavascriptLexer, self).__init__(
-            JavascriptLexer, MozPreprocHashLexer, **options)
+        super().__init__(JavascriptLexer, MozPreprocHashLexer, **options)
 
 
 class MozPreprocCssLexer(DelegatingLexer):
@@ -497,8 +493,7 @@ class MozPreprocCssLexer(DelegatingLexer):
     mimetypes = []
 
     def __init__(self, **options):
-        super(MozPreprocCssLexer, self).__init__(
-            CssLexer, MozPreprocPercentLexer, **options)
+        super().__init__(CssLexer, MozPreprocPercentLexer, **options)
 
 
 class MarkdownLexer(RegexLexer):
@@ -509,7 +504,7 @@ class MarkdownLexer(RegexLexer):
     """
     name = 'markdown'
     aliases = ['md']
-    filenames = ['*.md']
+    filenames = ['*.md', '*.markdown']
     mimetypes = ["text/x-markdown"]
     flags = re.MULTILINE
 
@@ -520,9 +515,9 @@ class MarkdownLexer(RegexLexer):
         from pygments.lexers import get_lexer_by_name
 
         # section header
-        yield match.start(1), String        , match.group(1)
-        yield match.start(2), String        , match.group(2)
-        yield match.start(3), Text          , match.group(3)
+        yield match.start(1), String.Backtick, match.group(1)
+        yield match.start(2), String.Backtick, match.group(2)
+        yield match.start(3), Text           , match.group(3)
 
         # lookup lexer if wanted and existing
         lexer = None
@@ -536,57 +531,232 @@ class MarkdownLexer(RegexLexer):
         # no lexer for this language. handle it like it was a code block
         if lexer is None:
             yield match.start(4), String, code
-            return
-
-        for item in do_insertions([], lexer.get_tokens_unprocessed(code)):
-            yield item
+        else:
+            yield from do_insertions([], lexer.get_tokens_unprocessed(code))
 
-        yield match.start(5), String        , match.group(5)
+        yield match.start(5), String.Backtick, match.group(5)
 
     tokens = {
         'root': [
-            # heading with pound prefix
-            (r'^(#)([^#].+\n)', bygroups(Generic.Heading, Text)),
-            (r'^(#{2,6})(.+\n)', bygroups(Generic.Subheading, Text)),
+            # heading with '#' prefix (atx-style)
+            (r'(^#[^#].+)(\n)', bygroups(Generic.Heading, Text)),
+            # subheading with '#' prefix (atx-style)
+            (r'(^#{2,6}[^#].+)(\n)', bygroups(Generic.Subheading, Text)),
+            # heading with '=' underlines (Setext-style)
+            (r'^(.+)(\n)(=+)(\n)', bygroups(Generic.Heading, Text, Generic.Heading, Text)),
+            # subheading with '-' underlines (Setext-style)
+            (r'^(.+)(\n)(-+)(\n)', bygroups(Generic.Subheading, Text, Generic.Subheading, Text)),
             # task list
             (r'^(\s*)([*-] )(\[[ xX]\])( .+\n)',
             bygroups(Text, Keyword, Keyword, using(this, state='inline'))),
-            # bulleted lists
+            # bulleted list
             (r'^(\s*)([*-])(\s)(.+\n)',
             bygroups(Text, Keyword, Text, using(this, state='inline'))),
-            # numbered lists
+            # numbered list
             (r'^(\s*)([0-9]+\.)( .+\n)',
             bygroups(Text, Keyword, using(this, state='inline'))),
             # quote
             (r'^(\s*>\s)(.+\n)', bygroups(Keyword, Generic.Emph)),
+            # code block fenced by 3 backticks
+            (r'^(\s*```\n(.+\n)+\s*```$)', String.Backtick),
+            # code block with language
+            (r'^(\s*```)(\w+)(\n)([\w\W]*?)(^\s*```$)', _handle_codeblock),
+            # code block indented with 4 spaces or 1 tab
+            (r'(\n\n)((\ {4}|\t)(.+\n)+)', bygroups(Text, String.Backtick)),
+
+            include('inline'),
+        ],
+        'inline': [
+            # escape
+            (r'\\.', Text),
+            # inline code
+            (r'([^`])(`[^`\n]+`)', bygroups(Text, String.Backtick)),
+            # warning: the following rules eat outer tags.
+            # eg. **foo _bar_ baz** => foo and baz are not recognized as bold
+            # bold fenced by '**'
+            (r'(\*\*[^* \n][^*\n]*\*\*)', bygroups(Generic.Strong)),
+            # # bold fenced by '__'
+            (r'(\_\_[^_ \n][^_\n]*\_\_)', bygroups(Generic.Strong)),
+            # italics fenced by '*'
+            (r'(\*[^* \n][^*\n]*\*)', bygroups(Generic.Emph)),
+            # italics fenced by '_'
+            (r'(\_[^_ \n][^_\n]*\_)', bygroups(Generic.Emph)),
+            # strikethrough
+            (r'([^~]*)(~~[^~]+~~)', bygroups(Text, Generic.Deleted)),
+            # mentions and topics (twitter and github stuff)
+            (r'[@#][\w/:]+', Name.Entity),
+            # (image?) links eg: ![Image of Yaktocat](https://octodex.github.com/images/yaktocat.png)
+            (r'(!?\[)([^]]+)(\])(\()([^)]+)(\))',
+             bygroups(Text, Name.Tag, Text, Text, Name.Attribute, Text)),
+            # reference-style links, e.g.:
+            #   [an example][id]
+            #   [id]: http://example.com/
+            (r'(\[)([^]]+)(\])(\[)([^]]*)(\])',
+             bygroups(Text, Name.Tag, Text, Text, Name.Label, Text)),
+            (r'^(\s*\[)([^]]*)(\]:\s*)(.+)',
+             bygroups(Text, Name.Label, Text, Name.Attribute)),
+
+            # general text, must come last!
+            (r'[^\\\s]+', Text),
+            (r'.', Text),
+        ],
+    }
+
+    def __init__(self, **options):
+        self.handlecodeblocks = get_bool_opt(options, 'handlecodeblocks', True)
+        RegexLexer.__init__(self, **options)
+
+
+class TiddlyWiki5Lexer(RegexLexer):
+    """
+    For `TiddlyWiki5 <https://tiddlywiki.com/#TiddlerFiles>`_ markup.
+
+    .. versionadded:: 2.7
+    """
+    name = 'tiddler'
+    aliases = ['tid']
+    filenames = ['*.tid']
+    mimetypes = ["text/vnd.tiddlywiki"]
+    flags = re.MULTILINE
+
+    def _handle_codeblock(self, match):
+        """
+        match args: 1:backticks, 2:lang_name, 3:newline, 4:code, 5:backticks
+        """
+        from pygments.lexers import get_lexer_by_name
+
+        # section header
+        yield match.start(1), String, match.group(1)
+        yield match.start(2), String, match.group(2)
+        yield match.start(3), Text,   match.group(3)
+
+        # lookup lexer if wanted and existing
+        lexer = None
+        if self.handlecodeblocks:
+            try:
+                lexer = get_lexer_by_name(match.group(2).strip())
+            except ClassNotFound:
+                pass
+        code = match.group(4)
+
+        # no lexer for this language. handle it like it was a code block
+        if lexer is None:
+            yield match.start(4), String, code
+            return
+
+        yield from do_insertions([], lexer.get_tokens_unprocessed(code))
+
+        yield match.start(5), String, match.group(5)
+
+    def _handle_cssblock(self, match):
+        """
+        match args: 1:style tag 2:newline, 3:code, 4:closing style tag
+        """
+        from pygments.lexers import get_lexer_by_name
+
+        # section header
+        yield match.start(1), String, match.group(1)
+        yield match.start(2), String, match.group(2)
+
+        lexer = None
+        if self.handlecodeblocks:
+            try:
+                lexer = get_lexer_by_name('css')
+            except ClassNotFound:
+                pass
+        code = match.group(3)
+
+        # no lexer for this language. handle it like it was a code block
+        if lexer is None:
+            yield match.start(3), String, code
+            return
+
+        yield from do_insertions([], lexer.get_tokens_unprocessed(code))
+
+        yield match.start(4), String, match.group(4)
+
+    tokens = {
+        'root': [
+            # title in metadata section
+            (r'^(title)(:\s)(.+\n)', bygroups(Keyword, Text, Generic.Heading)),
+            # headings
+            (r'^(!)([^!].+\n)', bygroups(Generic.Heading, Text)),
+            (r'^(!{2,6})(.+\n)', bygroups(Generic.Subheading, Text)),
+            # bulleted or numbered lists or single-line block quotes
+            # (can be mixed)
+            (r'^(\s*)([*#>]+)(\s*)(.+\n)',
+             bygroups(Text, Keyword, Text, using(this, state='inline'))),
+            # multi-line block quotes
+            (r'^(<<<.*\n)([\w\W]*?)(^<<<.*$)', bygroups(String, Text, String)),
+            # table header
+            (r'^(\|.*?\|h)$', bygroups(Generic.Strong)),
+            # table footer or caption
+            (r'^(\|.*?\|[cf])$', bygroups(Generic.Emph)),
+            # table class
+            (r'^(\|.*?\|k)$', bygroups(Name.Tag)),
+            # definitions
+            (r'^(;.*)$', bygroups(Generic.Strong)),
             # text block
             (r'^(```\n)([\w\W]*?)(^```$)', bygroups(String, Text, String)),
             # code block with language
             (r'^(```)(\w+)(\n)([\w\W]*?)(^```$)', _handle_codeblock),
+            # CSS style block
+            (r'^(<style>)(\n)([\w\W]*?)(^</style>$)', _handle_cssblock),
 
+            include('keywords'),
             include('inline'),
         ],
+        'keywords': [
+            (words((
+                '\\define', '\\end', 'caption', 'created', 'modified', 'tags',
+                'title', 'type'), prefix=r'^', suffix=r'\b'),
+             Keyword),
+        ],
         'inline': [
             # escape
             (r'\\.', Text),
+            # created or modified date
+            (r'\d{17}', Number.Integer),
             # italics
-            (r'(\s)([*_][^*_]+[*_])(\W|\n)', bygroups(Text, Generic.Emph, Text)),
+            (r'(\s)(//[^/]+//)((?=\W|\n))',
+             bygroups(Text, Generic.Emph, Text)),
+            # superscript
+            (r'(\s)(\^\^[^\^]+\^\^)', bygroups(Text, Generic.Emph)),
+            # subscript
+            (r'(\s)(,,[^,]+,,)', bygroups(Text, Generic.Emph)),
+            # underscore
+            (r'(\s)(__[^_]+__)', bygroups(Text, Generic.Strong)),
             # bold
-            # warning: the following rule eats internal tags. eg. **foo _bar_ baz** bar is not italics
-            (r'(\s)((\*\*|__).*\3)((?=\W|\n))', bygroups(Text, Generic.Strong, None, Text)),
-            # "proper way" (r'(\s)([*_]{2}[^*_]+[*_]{2})((?=\W|\n))', bygroups(Text, Generic.Strong, Text)),
+            (r"(\s)(''[^']+'')((?=\W|\n))",
+             bygroups(Text, Generic.Strong, Text)),
             # strikethrough
-            (r'(\s)(~~[^~]+~~)((?=\W|\n))', bygroups(Text, Generic.Deleted, Text)),
+            (r'(\s)(~~[^~]+~~)((?=\W|\n))',
+             bygroups(Text, Generic.Deleted, Text)),
+            # TiddlyWiki variables
+            (r'<<[^>]+>>', Name.Tag),
+            (r'\$\$[^$]+\$\$', Name.Tag),
+            (r'\$\([^)]+\)\$', Name.Tag),
+            # TiddlyWiki style or class
+            (r'^@@.*$', Name.Tag),
+            # HTML tags
+            (r'</?[^>]+>', Name.Tag),
             # inline code
             (r'`[^`]+`', String.Backtick),
-            # mentions and topics (twitter and github stuff)
-            (r'[@#][\w/:]+', Name.Entity),
-            # (image?) links eg: ![Image of Yaktocat](https://octodex.github.com/images/yaktocat.png)
-            (r'(!?\[)([^]]+)(\])(\()([^)]+)(\))', bygroups(Text, Name.Tag, Text, Text, Name.Attribute, Text)),
+            # HTML escaped symbols
+            (r'&\S*?;', String.Regex),
+            # Wiki links
+            (r'(\[{2})([^]\|]+)(\]{2})', bygroups(Text, Name.Tag, Text)),
+            # External links
+            (r'(\[{2})([^]\|]+)(\|)([^]\|]+)(\]{2})',
+            bygroups(Text, Name.Tag, Text, Name.Attribute, Text)),
+            # Transclusion
+            (r'(\{{2})([^}]+)(\}{2})', bygroups(Text, Name.Tag, Text)),
+            # URLs
+            (r'(\b.?.?tps?://[^\s"]+)', bygroups(Name.Attribute)),
 
             # general text, must come last!
-            (r'[^\\\s]+', Text),
-            (r'.', Text),
+            (r'[\w]+', Text),
+            (r'.', Text)
         ],
     }
 

data/vendor/pygments-main/pygments/lexers/math.py

@@ -5,7 +5,7 @@
 
     Just export lexers that were contained in this module.
 
-    :copyright: Copyright 2006-2015 by the Pygments team, see AUTHORS.
+    :copyright: Copyright 2006-2020 by the Pygments team, see AUTHORS.
     :license: BSD, see LICENSE for details.
 """
 

data/vendor/pygments-main/pygments/lexers/matlab.py

@@ -5,13 +5,14 @@
 
     Lexers for Matlab and related languages.
 
-    :copyright: Copyright 2006-2015 by the Pygments team, see AUTHORS.
+    :copyright: Copyright 2006-2020 by the Pygments team, see AUTHORS.
     :license: BSD, see LICENSE for details.
 """
 
 import re
 
-from pygments.lexer import Lexer, RegexLexer, bygroups, words, do_insertions
+from pygments.lexer import Lexer, RegexLexer, bygroups, default, words, \
+    do_insertions
 from pygments.token import Text, Comment, Operator, Keyword, Name, String, \
     Number, Punctuation, Generic, Whitespace
 
@@ -45,33 +46,35 @@ class MatlabLexer(RegexLexer):
     # specfun: Special Math functions
     # elmat: Elementary matrices and matrix manipulation
     #
-    # taken from Matlab version 7.4.0.336 (R2007a)
+    # taken from Matlab version 9.4 (R2018a)
     #
     elfun = ("sin", "sind", "sinh", "asin", "asind", "asinh", "cos", "cosd", "cosh",
              "acos", "acosd", "acosh", "tan", "tand", "tanh", "atan", "atand", "atan2",
-             "atanh", "sec", "secd", "sech", "asec", "asecd", "asech", "csc", "cscd",
+             "atan2d", "atanh", "sec", "secd", "sech", "asec", "asecd", "asech", "csc", "cscd",
              "csch", "acsc", "acscd", "acsch", "cot", "cotd", "coth", "acot", "acotd",
-             "acoth", "hypot", "exp", "expm1", "log", "log1p", "log10", "log2", "pow2",
+             "acoth", "hypot", "deg2rad", "rad2deg", "exp", "expm1", "log", "log1p", "log10", "log2", "pow2",
              "realpow", "reallog", "realsqrt", "sqrt", "nthroot", "nextpow2", "abs",
              "angle", "complex", "conj", "imag", "real", "unwrap", "isreal", "cplxpair",
              "fix", "floor", "ceil", "round", "mod", "rem", "sign")
     specfun = ("airy", "besselj", "bessely", "besselh", "besseli", "besselk", "beta",
-               "betainc", "betaln", "ellipj", "ellipke", "erf", "erfc", "erfcx",
-               "erfinv", "expint", "gamma", "gammainc", "gammaln", "psi", "legendre",
+               "betainc", "betaincinv", "betaln", "ellipj", "ellipke", "erf", "erfc", "erfcx",
+               "erfinv", "erfcinv", "expint", "gamma", "gammainc", "gammaincinv", "gammaln", "psi", "legendre",
                "cross", "dot", "factor", "isprime", "primes", "gcd", "lcm", "rat",
                "rats", "perms", "nchoosek", "factorial", "cart2sph", "cart2pol",
                "pol2cart", "sph2cart", "hsv2rgb", "rgb2hsv")
-    elmat = ("zeros", "ones", "eye", "repmat", "rand", "randn", "linspace", "logspace",
+    elmat = ("zeros", "ones", "eye", "repmat", "repelem", "linspace", "logspace",
              "freqspace", "meshgrid", "accumarray", "size", "length", "ndims", "numel",
-             "disp", "isempty", "isequal", "isequalwithequalnans", "cat", "reshape",
-             "diag", "blkdiag", "tril", "triu", "fliplr", "flipud", "flipdim", "rot90",
+             "disp", "isempty", "isequal", "isequaln", "cat", "reshape",
+             "diag", "blkdiag", "tril", "triu", "fliplr", "flipud", "flip", "rot90",
              "find", "end", "sub2ind", "ind2sub", "bsxfun", "ndgrid", "permute",
              "ipermute", "shiftdim", "circshift", "squeeze", "isscalar", "isvector",
-             "ans", "eps", "realmax", "realmin", "pi", "i", "inf", "nan", "isnan",
-             "isinf", "isfinite", "j", "why", "compan", "gallery", "hadamard", "hankel",
+             "isrow", "iscolumn", "ismatrix", "eps", "realmax", "realmin", "intmax", "intmin", "flintmax", "pi", "i", "inf", "nan", "isnan",
+             "isinf", "isfinite", "j", "true", "false", "compan", "gallery", "hadamard", "hankel",
              "hilb", "invhilb", "magic", "pascal", "rosser", "toeplitz", "vander",
              "wilkinson")
 
+    _operators = r'-|==|~=|<=|>=|<|>|&&|&|~|\|\|?|\.\*|\*|\+|\.\^|\.\\|\./|/|\\'
+
     tokens = {
         'root': [
             # line starting with '!' is sent as a system command.  not sure what
@@ -79,25 +82,40 @@ class MatlabLexer(RegexLexer):
             (r'^!.*', String.Other),
             (r'%\{\s*\n', Comment.Multiline, 'blockcomment'),
             (r'%.*$', Comment),
-            (r'^\s*function', Keyword, 'deffunc'),
-
-            # from 'iskeyword' on version 7.11 (R2010):
-            (words((
-                'break', 'case', 'catch', 'classdef', 'continue', 'else', 'elseif',
-                'end', 'enumerated', 'events', 'for', 'function', 'global', 'if',
-                'methods', 'otherwise', 'parfor', 'persistent', 'properties',
-                'return', 'spmd', 'switch', 'try', 'while'), suffix=r'\b'),
+            (r'^\s*function\b', Keyword, 'deffunc'),
+
+            # from 'iskeyword' on version 9.4 (R2018a):
+            # Check that there is no preceding dot, as keywords are valid field
+            # names.
+            (words(('break', 'case', 'catch', 'classdef', 'continue', 'else',
+                    'elseif', 'end', 'for', 'function',
+                    'global', 'if', 'otherwise', 'parfor',
+                    'persistent', 'return', 'spmd', 'switch',
+                    'try', 'while'),
+                   prefix=r'(?<!\.)', suffix=r'\b'),
              Keyword),
 
             ("(" + "|".join(elfun + specfun + elmat) + r')\b',  Name.Builtin),
 
             # line continuation with following comment:
-            (r'\.\.\..*$', Comment),
+            (r'(\.\.\.)(.*)$', bygroups(Keyword, Comment)),
+
+            # command form:
+            # "How MATLAB Recognizes Command Syntax" specifies that an operator
+            # is recognized if it is either surrounded by spaces or by no
+            # spaces on both sides; only the former case matters for us.  (This
+            # allows distinguishing `cd ./foo` from `cd ./ foo`.)
+            (r'(?:^|(?<=;))(\s*)(\w+)(\s+)(?!=|\(|(?:%s)\s+)' % _operators,
+             bygroups(Text, Name, Text), 'commandargs'),
 
             # operators:
-            (r'-|==|~=|<|>|<=|>=|&&|&|~|\|\|?', Operator),
-            # operators requiring escape for re:
-            (r'\.\*|\*|\+|\.\^|\.\\|\.\/|\/|\\', Operator),
+            (_operators, Operator),
+
+            # numbers (must come before punctuation to handle `.5`; cannot use
+            # `\b` due to e.g. `5. + .5`).
+            (r'(?<!\w)((\d+\.\d*)|(\d*\.\d+))([eEf][+-]?\d+)?(?!\w)', Number.Float),
+            (r'\b\d+[eEf][+-]?[0-9]+\b', Number.Float),
+            (r'\b\d+\b', Number.Integer),
 
             # punctuation:
             (r'\[|\]|\(|\)|\{|\}|:|@|\.|,', Punctuation),
@@ -107,17 +125,12 @@ class MatlabLexer(RegexLexer):
             # (not great, but handles common cases...)
             (r'(?<=[\w)\].])\'+', Operator),
 
-            (r'(\d+\.\d*|\d*\.\d+)([eEf][+-]?[0-9]+)?', Number.Float),
-            (r'\d+[eEf][+-]?[0-9]+', Number.Float),
-            (r'\d+', Number.Integer),
+            (r'"(""|[^"])*"', String),
 
             (r'(?<![\w)\].])\'', String, 'string'),
             (r'[a-zA-Z_]\w*', Name),
             (r'.', Text),
         ],
-        'string': [
-            (r'[^\']*\'', String, '#pop')
-        ],
         'blockcomment': [
             (r'^\s*%\}', Comment.Multiline, '#pop'),
             (r'^.*\n', Comment.Multiline),
@@ -131,12 +144,36 @@ class MatlabLexer(RegexLexer):
             # function with no args
             (r'(\s*)([a-zA-Z_]\w*)', bygroups(Text, Name.Function), '#pop'),
         ],
+        'string': [
+            (r"[^']*'", String, '#pop'),
+        ],
+        'commandargs': [
+            # If an equal sign or other operator is encountered, this
+            # isn't a command. It might be a variable assignment or
+            # comparison operation with multiple spaces before the
+            # equal sign or operator
+            (r"=", Punctuation, '#pop'),
+            (_operators, Operator, '#pop'),
+            (r"[ \t]+", Text),
+            ("'[^']*'", String),
+            (r"[^';\s]+", String),
+            (";", Punctuation, '#pop'),
+            default('#pop'),
+        ]
     }
 
     def analyse_text(text):
-        if re.match('^\s*%', text, re.M):  # comment
+        # function declaration.
+        first_non_comment = next((line for line in text.splitlines()
+                                  if not re.match(r'^\s*%', text)), '').strip()
+        if (first_non_comment.startswith('function')
+                and '{' not in first_non_comment):
+            return 1.
+        # comment
+        elif re.search(r'^\s*%', text, re.M):
             return 0.2
-        elif re.match('^!\w+', text, re.M):  # system cmd
+        # system cmd
+        elif re.search(r'^!\w+', text, re.M):
             return 0.2
 
 
@@ -158,6 +195,7 @@ class MatlabSessionLexer(Lexer):
 
         curcode = ''
         insertions = []
+        continuation = False
 
         for match in line_re.finditer(text):
             line = match.group()
@@ -180,21 +218,36 @@ class MatlabSessionLexer(Lexer):
                 # line = "\n" + line
                 token = (0, Generic.Traceback, line)
                 insertions.append((idx, [token]))
-
+            elif continuation:
+                # line_start is the length of the most recent prompt symbol
+                line_start = len(insertions[-1][-1][-1])
+                # Set leading spaces with the length of the prompt to be a generic prompt
+                # This keeps code aligned when prompts are removed, say with some Javascript
+                if line.startswith(' '*line_start):
+                    insertions.append((len(curcode),
+                                    [(0, Generic.Prompt, line[:line_start])]))
+                    curcode += line[line_start:]
+                else:
+                    curcode += line
             else:
                 if curcode:
-                    for item in do_insertions(
-                            insertions, mlexer.get_tokens_unprocessed(curcode)):
-                        yield item
+                    yield from do_insertions(
+                        insertions, mlexer.get_tokens_unprocessed(curcode))
                     curcode = ''
                     insertions = []
 
                 yield match.start(), Generic.Output, line
 
+            # Does not allow continuation if a comment is included after the ellipses.
+            # Continues any line that ends with ..., even comments (lines that start with %)
+            if line.strip().endswith('...'):
+                continuation = True
+            else:
+                continuation = False
+
         if curcode:  # or item:
-            for item in do_insertions(
-                    insertions, mlexer.get_tokens_unprocessed(curcode)):
-                yield item
+            yield from do_insertions(
+                insertions, mlexer.get_tokens_unprocessed(curcode))
 
 
 class OctaveLexer(RegexLexer):
@@ -536,7 +589,7 @@ class OctaveLexer(RegexLexer):
         'root': [
             # We should look into multiline comments
             (r'[%#].*$', Comment),
-            (r'^\s*function', Keyword, 'deffunc'),
+            (r'^\s*function\b', Keyword, 'deffunc'),
 
             # from 'iskeyword' on hg changeset 8cc154f45e37
             (words((
@@ -594,6 +647,10 @@ class OctaveLexer(RegexLexer):
         ],
     }
 
+    def analyse_text(text):
+        """Octave is quite hard to spot, and it looks like Matlab as well."""
+        return 0
+
 
 class ScilabLexer(RegexLexer):
     """
@@ -609,7 +666,7 @@ class ScilabLexer(RegexLexer):
     tokens = {
         'root': [
             (r'//.*?$', Comment.Single),
-            (r'^\s*function', Keyword, 'deffunc'),
+            (r'^\s*function\b', Keyword, 'deffunc'),
 
             (words((
                 '__FILE__', '__LINE__', 'break', 'case', 'catch', 'classdef', 'continue', 'do', 'else',