Added lexer for VBScript.

6 files changed, 474 insertions, 4 deletions

diff --git a/AUTHORS b/AUTHORS
index 66377ead..915a747d 100644
--- a/AUTHORS
+++ b/AUTHORS
@@ -7,7 +7,8 @@ Other contributors, listed alphabetically, are:
 
 * Sam Aaron -- Ioke lexer
 * Ali Afshar -- image formatter
-* Thomas Aglassinger -- Easytrieve, JCL, Rexx and Transact-SQL lexers
+* Thomas Aglassinger -- Easytrieve, JCL, Rexx, Transact-SQL and VBScript
+  lexers
 * Muthiah Annamalai -- Ezhil lexer
 * Kumar Appaiah -- Debian control lexer
 * Andreas Amann -- AppleScript lexer
diff --git a/pygments/lexers/_mapping.py b/pygments/lexers/_mapping.py
index a6097b1c..882ec292 100644
--- a/pygments/lexers/_mapping.py
+++ b/pygments/lexers/_mapping.py
@@ -422,6 +422,7 @@ LEXERS = {
     'TypoScriptHtmlDataLexer': ('pygments.lexers.typoscript', 'TypoScriptHtmlData', ('typoscripthtmldata',), (), ()),
     'TypoScriptLexer': ('pygments.lexers.typoscript', 'TypoScript', ('typoscript',), ('*.ts', '*.txt'), ('text/x-typoscript',)),
     'UrbiscriptLexer': ('pygments.lexers.urbi', 'UrbiScript', ('urbiscript',), ('*.u',), ('application/x-urbiscript',)),
+    'VBScriptLexer': ('pygments.lexers.basic', 'VBScript', (), ('*.vbs', '*.VBS'), ()),
     'VCLLexer': ('pygments.lexers.varnish', 'VCL', ('vcl',), ('*.vcl',), ('text/x-vclsrc',)),
     'VCLSnippetLexer': ('pygments.lexers.varnish', 'VCLSnippets', ('vclsnippets', 'vclsnippet'), (), ('text/x-vclsnippet',)),
     'VCTreeStatusLexer': ('pygments.lexers.console', 'VCTreeStatus', ('vctreestatus',), (), ()),
diff --git a/pygments/lexers/_vbscript_builtins.py b/pygments/lexers/_vbscript_builtins.py
new file mode 100644
index 00000000..493e5c7c
--- /dev/null
+++ b/pygments/lexers/_vbscript_builtins.py
@@ -0,0 +1,275 @@
+# -*- coding: utf-8 -*-
+"""
+    pygments.lexers._vbscript_builtins
+    ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+    These are manually translated lists from
+    http://www.indusoft.com/pdf/VBScript%20Reference.pdf.
+
+    :copyright: Copyright 2006-2015 by the Pygments team, see AUTHORS.
+    :license: BSD, see LICENSE for details.
+"""
+KEYWORDS = [
+    # dim: special rule
+    'call',
+    'case',
+    'class',
+    # const: special rule
+    'do',
+    'each',
+    'else',
+    'elseif',
+    'end',
+    'erase',
+    'execute',
+    'function',
+    'exit',
+    'for',
+    'function',
+    'GetRef',
+    'global',
+    'if',
+    'let',
+    'loop',
+    'next',
+    'new',
+    # option: special rule
+    'private',
+    'public',
+    'redim',
+    'select',
+    'set',
+    'sub',
+    'then',
+    'wend',
+    'while',
+    'with',
+]
+
+BUILTIN_FUNCTIONS = [
+    'Abs',
+    'Array',
+    'Asc',
+    'Atn',
+    'CBool',
+    'CByte',
+    'CCur',
+    'CDate',
+    'CDbl',
+    'Chr',
+    'CInt',
+    'CLng',
+    'Cos',
+    'CreateObject',
+    'CSng',
+    'CStr',
+    'Date',
+    'DateAdd',
+    'DateDiff',
+    'DatePart',
+    'DateSerial',
+    'DateValue',
+    'Day',
+    'Eval',
+    'Exp',
+    'Filter',
+    'Fix',
+    'FormatCurrency',
+    'FormatDateTime',
+    'FormatNumber',
+    'FormatPercent',
+    'GetObject',
+    'GetLocale',
+    'Hex',
+    'Hour',
+    'InStr',
+    'inStrRev',
+    'Int',
+    'IsArray',
+    'IsDate',
+    'IsEmpty',
+    'IsNull',
+    'IsNumeric',
+    'IsObject',
+    'Join',
+    'LBound',
+    'LCase',
+    'Left',
+    'Len',
+    'LoadPicture',
+    'Log',
+    'LTrim',
+    'Mid',
+    'Minute',
+    'Month',
+    'MonthName',
+    'MsgBox',
+    'Now',
+    'Oct',
+    'Randomize',
+    'RegExp',
+    'Replace',
+    'RGB',
+    'Right',
+    'Rnd',
+    'Round',
+    'RTrim',
+    'ScriptEngine',
+    'ScriptEngineBuildVersion',
+    'ScriptEngineMajorVersion',
+    'ScriptEngineMinorVersion',
+    'Second',
+    'SetLocale',
+    'Sgn',
+    'Space',
+    'Split',
+    'Sqr',
+    'StrComp',
+    'String',
+    'StrReverse',
+    'Tan',
+    'Time',
+    'Timer',
+    'TimeSerial',
+    'TimeValue',
+    'Trim',
+    'TypeName',
+    'UBound',
+    'UCase',
+    'VarType',
+    'Weekday',
+    'WeekdayName',
+    'Year',
+]
+
+BUILTIN_VARIABLES = [
+    'Debug',
+    'Dictionary',
+    'Drive',
+    'Drives',
+    'Err',
+    'File',
+    'Files',
+    'FileSystemObject',
+    'Folder',
+    'Folders',
+    'Match',
+    'Matches',
+    'RegExp',
+    'Submatches',
+    'TextStream',
+]
+
+OPERATORS = [
+    '+',
+    '-',
+    '*',
+    '/',
+    '\\',
+    '^',
+    '|',
+    '<',
+    '<=',
+    '>',
+    '>=',
+    '=',
+    '<>',
+    '&',
+    '$',
+]
+
+OPERATOR_WORDS = [
+    'mod',
+    'and',
+    'or',
+    'xor',
+    'eqv',
+    'imp',
+    'is',
+    'not',
+]
+
+BUILTIN_CONSTANTS = [
+    'vbAbort',
+    'vbAbortRetryIgnore',
+    'vbApplicationModal',
+    'vbArray',
+    'vbBinaryCompare',
+    'vbBlack',
+    'vbBlue',
+    'vbBoole',
+    'vbByte',
+    'vbCancel',
+    'vbCr',
+    'vbCritical',
+    'vbCrLf',
+    'vbCurrency',
+    'vbCyan',
+    'vbDataObject',
+    'vbDate',
+    'vbDefaultButton1',
+    'vbDefaultButton2',
+    'vbDefaultButton3',
+    'vbDefaultButton4',
+    'vbDouble',
+    'vbEmpty',
+    'vbError',
+    'vbExclamation',
+    'vbFalse',
+    'vbFirstFullWeek',
+    'vbFirstJan1',
+    'vbFormFeed',
+    'vbFriday',
+    'vbGeneralDate',
+    'vbGreen',
+    'vbIgnore',
+    'vbInformation',
+    'vbInteger',
+    'vbLf',
+    'vbLong',
+    'vbLongDate',
+    'vbLongTime',
+    'vbMagenta',
+    'vbMonday',
+    'vbMsgBoxHelpButton',
+    'vbMsgBoxRight',
+    'vbMsgBoxRtlReading',
+    'vbMsgBoxSetForeground',
+    'vbNewLine',
+    'vbNo',
+    'vbNull',
+    'vbNullChar',
+    'vbNullString',
+    'vbObject',
+    'vbObjectError',
+    'vbOK',
+    'vbOKCancel',
+    'vbOKOnly',
+    'vbQuestion',
+    'vbRed',
+    'vbRetry',
+    'vbRetryCancel',
+    'vbSaturday',
+    'vbShortDate',
+    'vbShortTime',
+    'vbSingle',
+    'vbString',
+    'vbSunday',
+    'vbSystemModal',
+    'vbTab',
+    'vbTextCompare',
+    'vbThursday',
+    'vbTrue',
+    'vbTuesday',
+    'vbUseDefault',
+    'vbUseSystem',
+    'vbUseSystem',
+    'vbVariant',
+    'vbVerticalTab',
+    'vbWednesday',
+    'vbWhite',
+    'vbYellow',
+    'vbYes',
+    'vbYesNo',
+    'vbYesNoCancel',
+]
\ No newline at end of file
diff --git a/pygments/lexers/basic.py b/pygments/lexers/basic.py
index a73ad8b4..09d9bfb9 100644
--- a/pygments/lexers/basic.py
+++ b/pygments/lexers/basic.py
@@ -12,11 +12,13 @@
 import re
 
 from pygments.lexer import RegexLexer, bygroups, default, words, include
-from pygments.token import Text, Comment, Operator, Keyword, Name, String, \
-    Number, Punctuation
+from pygments.token import Comment, Error, Keyword, Name, Number, \
+    Punctuation, Operator, String, Text, Whitespace
+from pygments.lexers import _vbscript_builtins
+
 
 __all__ = ['BlitzBasicLexer', 'BlitzMaxLexer', 'MonkeyLexer', 'CbmBasicV2Lexer',
-           'QBasicLexer']
+           'QBasicLexer', 'VBScriptLexer']
 
 
 class BlitzMaxLexer(RegexLexer):
@@ -498,3 +500,65 @@ class QBasicLexer(RegexLexer):
     def analyse_text(text):
         if '$DYNAMIC' in text or '$STATIC' in text:
             return 0.9
+
+
+class VBScriptLexer(RegexLexer):
+    """
+    VBScript is scripting language that is modeled on Visual Basic.
+
+    .. versionadded:: 2.2
+    """
+    name = 'VBScript'
+    aliases = []
+    filenames = ['*.vbs', '*.VBS']
+    flags = re.IGNORECASE
+
+    tokens = {
+        'root': [
+            (r"'[^\n]*", Comment.Single),
+            (r'\s+', Whitespace),
+            ('"', String.Double, 'string'),
+            ('&h[0-9a-f]+', Number.Hex),
+            # Float variant 1, for example: 1., 1.e2, 1.2e3
+            (r'[0-9]+\.[0-9]*(e[+-]?[0-9]+)?', Number.Float),
+            (r'\.[0-9]+(e[+-]?[0-9]+)?', Number.Float),  # Float variant 2, for example: .1, .1e2
+            (r'[0-9]+e[+-]?[0-9]+', Number.Float),  # Float variant 3, for example: 123e45
+            ('\d+', Number.Integer),
+            ('#.+#', String),  # date or time value
+            (r'(dim)(\s+)([a-z_][a-z0-9_]*)',
+             bygroups(Keyword.Declaration, Whitespace, Name.Variable), 'dim_more'),
+            (r'(function|sub)(\s+)([a-z_][a-z0-9_]*)',
+             bygroups(Keyword.Declaration, Whitespace, Name.Function)),
+            (r'(class)(\s+)([a-z_][a-z0-9_]*)', bygroups(Keyword.Declaration, Whitespace, Name.Class)),
+            (r'(const)(\s+)([a-z_][a-z0-9_]*)', bygroups(Keyword.Declaration, Whitespace, Name.Constant)),
+            (r'(end)(\s+)(class|function|if|property|sub|with)', bygroups(Keyword, Whitespace, Keyword)),
+            (r'(on)(\s+)(error)(\s+)(goto)(\s+)(0)',
+             bygroups(Keyword, Whitespace, Keyword, Whitespace, Keyword, Whitespace, Number.Integer)),
+            (r'(on)(\s+)(error)(\s+)(resume)(\s+)(next)',
+             bygroups(Keyword, Whitespace, Keyword, Whitespace, Keyword, Whitespace, Keyword)),
+            (r'(option)(\s+)(explicit)', bygroups(Keyword, Whitespace, Keyword)),
+            (r'(property)(\s+)(get|let|set)(\s+)([a-z_][a-z0-9_]*)',
+             bygroups(Keyword.Declaration, Whitespace, Keyword.Declaration, Whitespace, Name.Property)),
+            (r'rem\s.*[^\n]*', Comment.Single),
+            (words(_vbscript_builtins.KEYWORDS, suffix=r'\b'), Keyword),
+            (words(_vbscript_builtins.OPERATORS), Operator),
+            (words(_vbscript_builtins.OPERATOR_WORDS, suffix=r'\b'), Operator.Word),
+            (words(_vbscript_builtins.BUILTIN_CONSTANTS, suffix=r'\b'), Name.Constant),
+            (words(_vbscript_builtins.BUILTIN_FUNCTIONS, suffix=r'\b'), Name.Builtin),
+            (words(_vbscript_builtins.BUILTIN_VARIABLES, suffix=r'\b'), Name.Builtin),
+            (r'[a-z_][a-z0-9_]*', Name),
+            (r'\b_\n', Operator),
+            (words(r'(),.:'), Punctuation),
+            ('.+(\n)?', Error)
+        ],
+        'dim_more': [
+            (r'(\s*)(,)(\s*)([a-z_][a-z0-9]*)', bygroups(Whitespace, Punctuation, Whitespace, Name.Variable)),
+            default('#pop'),
+        ],
+        'string': [
+            (r'[^"\n]+', String.Double),
+            (r'\"\"', String.Double),
+            (r'"', String.Double, '#pop'),
+            (r'\n', Error, '#pop'),  # Unterminated string
+        ],
+    }
\ No newline at end of file
diff --git a/tests/examplefiles/example.vbs b/tests/examplefiles/example.vbs
new file mode 100644
index 00000000..d962b73d
--- /dev/null
+++ b/tests/examplefiles/example.vbs
@@ -0,0 +1,55 @@
+rem VBScript examples
+
+' Various constants of different types
+const someText = "some " & """text"""
+const someInt = 123
+const someHex = &h3110c0d3
+const someFloat = 123.45e-67
+const someDate = #1/2/2016#
+const someTime = #12:34:56 AM#
+const someBool = vbTrue  ' -1
+
+' Do some math.
+radius = 1.e2
+area = radius ^ 2 * 3.1315
+a = 17 : b = 23
+c = sqr(a ^2 + b ^ 2)
+
+' Write 10 files.
+For i = 1 to 10
+    createFile( i )
+Next
+
+Public Sub createFile(a)
+    Dim fso, TargetFile
+    TargetPath = "C:\some_" & a & ".tmp"
+    Set fso = CreateObject("Scripting.FileSystemObject")
+    Set TargetFile = fso.CreateTextFile(TargetPath)
+    TargetFile.WriteLine("Hello " & vbCrLf & "world!")
+    TargetFile.Close
+End Sub
+
+' Define a class with a property.
+Class Customer
+    Private m_CustomerName
+
+    Private Sub Class_Initialize
+        m_CustomerName = ""
+    End Sub
+
+    ' CustomerName property.
+    Public Property Get CustomerName
+        CustomerName = m_CustomerName
+    End Property
+
+    Public Property Let CustomerName(custname)
+        m_CustomerName = custname
+    End Property
+End Class
+
+' Special constructs
+Option Explicit
+On Error Resume Next
+On Error Goto 0
+
+' Comment without terminating CR/LF.
\ No newline at end of file
diff --git a/tests/test_basic.py b/tests/test_basic.py
new file mode 100644
index 00000000..03d10cd2
--- /dev/null
+++ b/tests/test_basic.py
@@ -0,0 +1,74 @@
+# -*- coding: utf-8 -*-
+"""
+    Pygments Basic lexers tests
+    ~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+    :copyright: Copyright 2006-2016 by the Pygments team, see AUTHORS.
+    :license: BSD, see LICENSE for details.
+"""
+import unittest
+
+from pygments.lexers.basic import VBScriptLexer
+from pygments.token import Error, Name, Number, Punctuation, String, Whitespace
+
+
+class VBScriptLexerTest(unittest.TestCase):
+
+    def setUp(self):
+        self.lexer = VBScriptLexer()
+
+    def _assert_are_tokens_of_type(self, examples, expected_token_type):
+        for test_number, example in enumerate(examples.split(), 1):
+            token_count = 0
+            for token_type, token_value in self.lexer.get_tokens(example):
+                if token_type != Whitespace:
+                    token_count += 1
+                    self.assertEqual(
+                        token_type, expected_token_type,
+                        'token_type #%d for %s is be %s but must be %s' %
+                        (test_number, token_value, token_type, expected_token_type))
+            self.assertEqual(
+                token_count, 1,
+                '%s must yield exactly 1 token instead of %d' %
+                (example, token_count))
+
+    def _assert_tokens_match(self, text, expected_tokens_without_trailing_newline):
+        actual_tokens = tuple(self.lexer.get_tokens(text))
+        if (len(actual_tokens) >= 1) and (actual_tokens[-1] == (Whitespace, '\n')):
+            actual_tokens = tuple(actual_tokens[:-1])
+        self.assertEqual(
+            expected_tokens_without_trailing_newline, actual_tokens,
+            'text must yield expected tokens: %s' % text)
+
+    def test_can_lex_float(self):
+        self._assert_are_tokens_of_type(
+            '1. 1.e1 .1 1.2 1.2e3 1.2e+3 1.2e-3 1e2', Number.Float)
+        self._assert_tokens_match(
+            '1e2.1e2',
+            ((Number.Float, '1e2'), (Number.Float, '.1e2'))
+        )
+
+    def test_can_reject_almost_float(self):
+        self._assert_tokens_match(
+            '.e1',
+            ((Punctuation, '.'), (Name, 'e1')))
+
+    def test_can_lex_integer(self):
+        self._assert_are_tokens_of_type(
+            '1 23 456', Number.Integer)
+
+    def test_can_lex_names(self):
+        self._assert_are_tokens_of_type(
+            u'thingy thingy123 _thingy _123', Name)
+
+    def test_can_recover_after_unterminated_string(self):
+        self._assert_tokens_match(
+            '"x\nx',
+            ((String.Double, '"'), (String.Double, 'x'), (Error, '\n'), (Name, 'x'))
+        )
+
+    def test_can_recover_from_invalid_character(self):
+        self._assert_tokens_match(
+            'a;bc\nd',
+            ((Name, 'a'), (Error, ';bc\n'), (Name, 'd'))
+        )