diff options
Diffstat (limited to 'pygments/lexers/basic.py')
| -rw-r--r-- | pygments/lexers/basic.py | 165 |
1 files changed, 162 insertions, 3 deletions
diff --git a/pygments/lexers/basic.py b/pygments/lexers/basic.py index e6545ee6..1aa3274c 100644 --- a/pygments/lexers/basic.py +++ b/pygments/lexers/basic.py @@ -12,11 +12,14 @@ 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', 'BBCBasicLexer'] + class BlitzMaxLexer(RegexLexer): @@ -498,3 +501,159 @@ 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 + (r'\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), + (r'.+(\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 + ], + } + + +class BBCBasicLexer(RegexLexer): + """ + BBC Basic was supplied on the BBC Micro, and later Acorn RISC OS. + It is also used by BBC Basic For Windows. + + .. versionadded:: 2.4 + """ + base_keywords = ['OTHERWISE', 'AND', 'DIV', 'EOR', 'MOD', 'OR', 'ERROR', + 'LINE', 'OFF', 'STEP', 'SPC', 'TAB', 'ELSE', 'THEN', + 'OPENIN', 'PTR', 'PAGE', 'TIME', 'LOMEM', 'HIMEM', 'ABS', + 'ACS', 'ADVAL', 'ASC', 'ASN', 'ATN', 'BGET', 'COS', 'COUNT', + 'DEG', 'ERL', 'ERR', 'EVAL', 'EXP', 'EXT', 'FALSE', 'FN', + 'GET', 'INKEY', 'INSTR', 'INT', 'LEN', 'LN', 'LOG', 'NOT', + 'OPENUP', 'OPENOUT', 'PI', 'POINT', 'POS', 'RAD', 'RND', + 'SGN', 'SIN', 'SQR', 'TAN', 'TO', 'TRUE', 'USR', 'VAL', + 'VPOS', 'CHR$', 'GET$', 'INKEY$', 'LEFT$', 'MID$', + 'RIGHT$', 'STR$', 'STRING$', 'EOF', 'PTR', 'PAGE', 'TIME', + 'LOMEM', 'HIMEM', 'SOUND', 'BPUT', 'CALL', 'CHAIN', 'CLEAR', + 'CLOSE', 'CLG', 'CLS', 'DATA', 'DEF', 'DIM', 'DRAW', 'END', + 'ENDPROC', 'ENVELOPE', 'FOR', 'GOSUB', 'GOTO', 'GCOL', 'IF', + 'INPUT', 'LET', 'LOCAL', 'MODE', 'MOVE', 'NEXT', 'ON', + 'VDU', 'PLOT', 'PRINT', 'PROC', 'READ', 'REM', 'REPEAT', + 'REPORT', 'RESTORE', 'RETURN', 'RUN', 'STOP', 'COLOUR', + 'TRACE', 'UNTIL', 'WIDTH', 'OSCLI'] + + basic5_keywords = ['WHEN', 'OF', 'ENDCASE', 'ENDIF', 'ENDWHILE', 'CASE', + 'CIRCLE', 'FILL', 'ORIGIN', 'POINT', 'RECTANGLE', 'SWAP', + 'WHILE', 'WAIT', 'MOUSE', 'QUIT', 'SYS', 'INSTALL', + 'LIBRARY', 'TINT', 'ELLIPSE', 'BEATS', 'TEMPO', 'VOICES', + 'VOICE', 'STEREO', 'OVERLAY', 'APPEND', 'AUTO', 'CRUNCH', + 'DELETE', 'EDIT', 'HELP', 'LIST', 'LOAD', 'LVAR', 'NEW', + 'OLD', 'RENUMBER', 'SAVE', 'TEXTLOAD', 'TEXTSAVE', + 'TWIN', 'TWINO', 'INSTALL', 'SUM', 'BEAT'] + + + name = 'BBC Basic' + aliases = ['bbcbasic'] + filenames = ['*.bbc'] + + tokens = { + 'root': [ + (r"[0-9]+", Name.Label), + (r"(\*)([^\n]*)", + bygroups(Keyword.Pseudo, Comment.Special)), + (r"", Whitespace, 'code'), + ], + + 'code': [ + (r"(REM)([^\n]*)", + bygroups(Keyword.Declaration, Comment.Single)), + (r'\n', Whitespace, 'root'), + (r'\s+', Whitespace), + (r':', Comment.Preproc), + + # Some special cases to make functions come out nicer + (r'(DEF)(\s*)(FN|PROC)([A-Za-z_@][\w@]*)', + bygroups(Keyword.Declaration, Whitespace, Keyword.Declaration, Name.Function)), + (r'(FN|PROC)([A-Za-z_@][\w@]*)', + bygroups(Keyword, Name.Function)), + + (r'(GOTO|GOSUB|THEN|RESTORE)(\s*)(\d+)', + bygroups(Keyword, Whitespace, Name.Label)), + + (r'(TRUE|FALSE)', Keyword.Constant), + (r'(PAGE|LOMEM|HIMEM|TIME|WIDTH|ERL|ERR|REPORT\$|POS|VPOS|VOICES)', Keyword.Pseudo), + + (words(base_keywords), Keyword), + (words(basic5_keywords), Keyword), + + ('"', String.Double, 'string'), + + ('%[01]{1,32}', Number.Bin), + ('&[0-9a-f]{1,8}', Number.Hex), + + (r'[+-]?[0-9]+\.[0-9]*(E[+-]?[0-9]+)?', Number.Float), + (r'[+-]?\.[0-9]+(E[+-]?[0-9]+)?', Number.Float), + (r'[+-]?[0-9]+E[+-]?[0-9]+', Number.Float), + (r'[+-]?\d+', Number.Integer), + + (r'([A-Za-z_@][\w@]*[%$]?)', Name.Variable), + (r'([+\-]=|[$!|?+\-*/%^=><();]|>=|<=|<>|<<|>>|>>>|,)', Operator), + ], + 'string': [ + (r'[^"\n]+', String.Double), + (r'"', String.Double, '#pop'), + (r'\n', Error, 'root'), # Unterminated string + ], + } + + def analyse_text(text): + if text.startswith('10REM >') or text.startswith('REM >'): + return 0.9 |