Merged in taboege/pygments-main (pull request #803)

Add Perl 6 to the language list

9 files changed, 356 insertions, 19 deletions

diff --git a/pygments/lexers/_mapping.py b/pygments/lexers/_mapping.py
index 331dadf3..f8207e70 100644
--- a/pygments/lexers/_mapping.py
+++ b/pygments/lexers/_mapping.py
@@ -428,8 +428,9 @@ LEXERS = {
     'TypeScriptLexer': ('pygments.lexers.javascript', 'TypeScript', ('ts', 'typescript'), ('*.ts', '*.tsx'), ('text/x-typescript',)),
     'TypoScriptCssDataLexer': ('pygments.lexers.typoscript', 'TypoScriptCssData', ('typoscriptcssdata',), (), ()),
     'TypoScriptHtmlDataLexer': ('pygments.lexers.typoscript', 'TypoScriptHtmlData', ('typoscripthtmldata',), (), ()),
-    'TypoScriptLexer': ('pygments.lexers.typoscript', 'TypoScript', ('typoscript',), ('*.ts', '*.txt'), ('text/x-typoscript',)),
+    'TypoScriptLexer': ('pygments.lexers.typoscript', 'TypoScript', ('typoscript',), ('*.typoscript',), ('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..7d514790
--- /dev/null
+++ b/pygments/lexers/_vbscript_builtins.py
@@ -0,0 +1,279 @@
+# -*- 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 = [
+    'ByRef',
+    'ByVal',
+    # 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 = [
+    'False',
+    'True',
+    '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 e6545ee6..f5f0498e 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:: 2.4
+    """
+    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/pygments/lexers/javascript.py b/pygments/lexers/javascript.py
index 87c4af2d..0507375f 100644
--- a/pygments/lexers/javascript.py
+++ b/pygments/lexers/javascript.py
@@ -538,12 +538,6 @@ class TypeScriptLexer(RegexLexer):
         ],
     }
 
-    def analyse_text(text):
-        if re.search(r'^(import.+(from\s+)?["\']|'
-                     r'(export\s*)?(interface|class|function)\s+)',
-                     text, re.MULTILINE):
-            return 1.0
-
 
 class LassoLexer(RegexLexer):
     """
diff --git a/pygments/lexers/lisp.py b/pygments/lexers/lisp.py
index ba3fd403..3bfc83a6 100644
--- a/pygments/lexers/lisp.py
+++ b/pygments/lexers/lisp.py
@@ -1400,7 +1400,7 @@ class RacketLexer(RegexLexer):
 
 class NewLispLexer(RegexLexer):
     """
-    For `newLISP. <www.newlisp.org>`_ source code (version 10.3.0).
+    For `newLISP. <http://www.newlisp.org/>`_ source code (version 10.3.0).
 
     .. versionadded:: 1.5
     """
diff --git a/pygments/lexers/php.py b/pygments/lexers/php.py
index f959fb1f..440d9d81 100644
--- a/pygments/lexers/php.py
+++ b/pygments/lexers/php.py
@@ -15,7 +15,8 @@ from pygments.lexer import RegexLexer, include, bygroups, default, using, \
     this, words
 from pygments.token import Text, Comment, Operator, Keyword, Name, String, \
     Number, Punctuation, Other
-from pygments.util import get_bool_opt, get_list_opt, iteritems
+from pygments.util import get_bool_opt, get_list_opt, iteritems, \
+    shebang_matches
 
 __all__ = ['ZephirLexer', 'PhpLexer']
 
@@ -261,6 +262,8 @@ class PhpLexer(RegexLexer):
             yield index, token, value
 
     def analyse_text(text):
+        if shebang_matches(text, r'php'):
+            return True
         rv = 0.0
         if re.search(r'<\?(?!xml)', text):
             rv += 0.3
diff --git a/pygments/lexers/r.py b/pygments/lexers/r.py
index 0829ae6e..66d6402c 100644
--- a/pygments/lexers/r.py
+++ b/pygments/lexers/r.py
@@ -161,7 +161,7 @@ class RdLexer(RegexLexer):
     This is a very minimal implementation, highlighting little more
     than the macros. A description of Rd syntax is found in `Writing R
     Extensions <http://cran.r-project.org/doc/manuals/R-exts.html>`_
-    and `Parsing Rd files <developer.r-project.org/parseRd.pdf>`_.
+    and `Parsing Rd files <http://developer.r-project.org/parseRd.pdf>`_.
 
     .. versionadded:: 1.6
     """
diff --git a/pygments/lexers/shell.py b/pygments/lexers/shell.py
index 86d8c37a..31bc7e94 100644
--- a/pygments/lexers/shell.py
+++ b/pygments/lexers/shell.py
@@ -76,7 +76,7 @@ class BashLexer(RegexLexer):
             (r'&&|\|\|', Operator),
         ],
         'data': [
-            (r'(?s)\$?"(\\\\|\\[0-7]+|\\.|[^"\\$])*"', String.Double),
+            (r'(?s)\$?"(\\.|[^"\\$])*"', String.Double),
             (r'"', String.Double, 'string'),
             (r"(?s)\$'(\\\\|\\[0-7]+|\\.|[^'\\])*'", String.Single),
             (r"(?s)'.*?'", String.Single),
diff --git a/pygments/lexers/typoscript.py b/pygments/lexers/typoscript.py
index 6e1c3155..f75a6f02 100644
--- a/pygments/lexers/typoscript.py
+++ b/pygments/lexers/typoscript.py
@@ -108,7 +108,7 @@ class TypoScriptLexer(RegexLexer):
 
     name = 'TypoScript'
     aliases = ['typoscript']
-    filenames = ['*.ts', '*.txt']
+    filenames = ['*.typoscript']
     mimetypes = ['text/x-typoscript']
 
     flags = re.DOTALL | re.MULTILINE
@@ -220,7 +220,3 @@ class TypoScriptLexer(RegexLexer):
             (r'[\w"\-!/&;]+', Text),
         ],
     }
-
-    def analyse_text(text):
-        if '<INCLUDE_TYPOSCRIPT:' in text:
-            return 1.0