3 ��XQ� � @ sr d Z ddlZddlmZmZ ddlmZmZ ddlm Z m Z mZmZm Z mZmZmZmZ dgZG dd� de�ZdS )z� pygments.lexers.modula2 ~~~~~~~~~~~~~~~~~~~~~~~ Multi-Dialect Lexer for Modula-2. :copyright: Copyright 2006-2017 by the Pygments team, see AUTHORS. :license: BSD, see LICENSE for details. � N)� RegexLexer�include)�get_bool_opt�get_list_opt) �Text�Comment�Operator�Keyword�Name�String�Number�Punctuation�Error�Modula2Lexerc K @ s` e Zd ZdZdZddgZddgZdgZej ej B Zdefd efgd e jfde jfde jfd e jfde jfde jfde jfde jfgdefgdejfdejfgdejfdejfdejfgdejfdejfdejfgdefdefgdefdefdefd efd!efd"efd#efd$efd%efd&efg d'efd(efd)efd*efd+efd,efd-efd.efd/efg d0efd1efd2efd3efd4efd5efd6efgd7efd8efd9efgd:e jfd;e jfd<e jfgd=e jfd>e jfged?�ed@�edA�edB�edC�edD�edE�edF�edG�edH�edI�edJ�edK�g dL�Z�d`Z�daZ�dbZ �dcZ!�ddZ"�deZ#�dfZ$�dgZ%�dhZ&�diZ'�djZ(�dkZ)�dlZ*�dmZ+�dnZ,�doZ-�dpZ.�dqZ/f Z0f Z1�drZ2f Z3�dsZ4�dtZ5f Z6f Z7f Z8�duZ9�dvZ:�dwZ;�dxZ<�dyZ=�dzZ>�d{Z?�d|Z@�d}ZAf ZBf ZCf ZDf ZEf ZF�d~ZG�dZH�d�ZI�d�ZJ�d�ZK�d�ZL�d�ZM�d�ZNf e!fe%fe)fe-fe%fe!fe%fe%f�dV� ZOee"e&e*fee"fee&fee*fee*e.fee&e1fee"e4fee&e7fee&e:f�dV� ZPee#e'e+fee#fee'fee+fee+e/fee'e2fee#e5fee'e8fee'e;f�dV� ZQe e$e(e,fe e$fe e(fe e,fe e,e0fe e(e3fe e$e6fe e(e9fe e(e<f�dV� ZRf f f eGfeGff f f f �dV� ZSf e=feBfeHeIeGfeHeIfeBfe=feBfeBf�dV� ZTf e>feCfeJfeJfeCfe>feCfeCf�dV� ZUf e?feDfeKfeKfeDfe?feDfeDf�dV� ZVf e@feEfeLfeLfeEfe@feEfeEf�dV� ZWf eAfeFfeMfeMfeFfeAfeFfeFf�dV� ZX�dW�dX� ZY�dY�dZ� ZZ�d[�d\� Z[�d]�d^� Z\�d_S (� r a� For `Modula-2 <http://www.modula2.org/>`_ source code. The Modula-2 lexer supports several dialects. By default, it operates in fallback mode, recognising the *combined* literals, punctuation symbols and operators of all supported dialects, and the *combined* reserved words and builtins of PIM Modula-2, ISO Modula-2 and Modula-2 R10, while not differentiating between library defined identifiers. To select a specific dialect, a dialect option may be passed or a dialect tag may be embedded into a source file. Dialect Options: `m2pim` Select PIM Modula-2 dialect. `m2iso` Select ISO Modula-2 dialect. `m2r10` Select Modula-2 R10 dialect. `objm2` Select Objective Modula-2 dialect. The PIM and ISO dialect options may be qualified with a language extension. Language Extensions: `+aglet` Select Aglet Modula-2 extensions, available with m2iso. `+gm2` Select GNU Modula-2 extensions, available with m2pim. `+p1` Select p1 Modula-2 extensions, available with m2iso. `+xds` Select XDS Modula-2 extensions, available with m2iso. Passing a Dialect Option via Unix Commandline Interface Dialect options may be passed to the lexer using the `dialect` key. Only one such option should be passed. If multiple dialect options are passed, the first valid option is used, any subsequent options are ignored. Examples: `$ pygmentize -O full,dialect=m2iso -f html -o /path/to/output /path/to/input` Use ISO dialect to render input to HTML output `$ pygmentize -O full,dialect=m2iso+p1 -f rtf -o /path/to/output /path/to/input` Use ISO dialect with p1 extensions to render input to RTF output Embedding a Dialect Option within a source file A dialect option may be embedded in a source file in form of a dialect tag, a specially formatted comment that specifies a dialect option. Dialect Tag EBNF:: dialectTag : OpeningCommentDelim Prefix dialectOption ClosingCommentDelim ; dialectOption : 'm2pim' | 'm2iso' | 'm2r10' | 'objm2' | 'm2iso+aglet' | 'm2pim+gm2' | 'm2iso+p1' | 'm2iso+xds' ; Prefix : '!' ; OpeningCommentDelim : '(*' ; ClosingCommentDelim : '*)' ; No whitespace is permitted between the tokens of a dialect tag. In the event that a source file contains multiple dialect tags, the first tag that contains a valid dialect option will be used and any subsequent dialect tags will be ignored. Ideally, a dialect tag should be placed at the beginning of a source file. An embedded dialect tag overrides a dialect option set via command line. Examples: ``(*!m2r10*) DEFINITION MODULE Foobar; ...`` Use Modula2 R10 dialect to render this source file. ``(*!m2pim+gm2*) DEFINITION MODULE Bazbam; ...`` Use PIM dialect with GNU extensions to render this source file. Algol Publication Mode: In Algol publication mode, source text is rendered for publication of algorithms in scientific papers and academic texts, following the format of the Revised Algol-60 Language Report. It is activated by passing one of two corresponding styles as an option: `algol` render reserved words lowercase underline boldface and builtins lowercase boldface italic `algol_nu` render reserved words lowercase boldface (no underlining) and builtins lowercase boldface italic The lexer automatically performs the required lowercase conversion when this mode is activated. Example: ``$ pygmentize -O full,style=algol -f latex -o /path/to/output /path/to/input`` Render input file in Algol publication mode to LaTeX output. Rendering Mode of First Class ADT Identifiers: The rendering of standard library first class ADT identifiers is controlled by option flag "treat_stdlib_adts_as_builtins". When this option is turned on, standard library ADT identifiers are rendered as builtins. When it is turned off, they are rendered as ordinary library identifiers. `treat_stdlib_adts_as_builtins` (default: On) The option is useful for dialects that support ADTs as first class objects and provide ADTs in the standard library that would otherwise be built-in. At present, only Modula-2 R10 supports library ADTs as first class objects and therefore, no ADT identifiers are defined for any other dialects. Example: ``$ pygmentize -O full,dialect=m2r10,treat_stdlib_adts_as_builtins=Off ...`` Render standard library ADTs as ordinary library types. .. versionadded:: 1.3 .. versionchanged:: 2.1 Added multi-dialect support. zModula-2Zmodula2�m2z*.defz*.modztext/x-modula2z\n+z\s+z\(\*!m2pim\*\)z\(\*!m2iso\*\)z\(\*!m2r10\*\)z\(\*!objm2\*\)z\(\*!m2iso\+aglet\*\)z\(\*!m2pim\+gm2\*\)z\(\*!m2iso\+p1\*\)z\(\*!m2iso\+xds\*\)z([a-zA-Z_$][\w$]*)z0b[01]+(\'[01]+)*z0[ux][0-9A-F]+(\'[0-9A-F]+)*z>[0-9]+(\'[0-9]+)*\.[0-9]+(\'[0-9]+)*[eE][+-]?[0-9]+(\'[0-9]+)*z$[0-9]+(\'[0-9]+)*\.[0-9]+(\'[0-9]+)*z[0-9]+(\'[0-9]+)*z[0-7]+Bz[0-7]+Cz [0-9A-F]+Hz'(\\\\|\\'|[^'])*'z"(\\\\|\\"|[^"])*"z\*\.z\+>�<>z<=z>=�==�::z:=z\+\+�--z[+-]z[*/]z\\z[=#<>]z\^�@�&�~�`z\.\.�<<�>>�->z\|#�##z\|\*z[()\[\]{},.:;|]�!z\?z^//.*?\nz\(\*([^$].*?)\*\)z/\*(.*?)\*/z <\*.*?\*>z \(\*\$.*?\*\)� whitespace�dialecttags�pragmas�comments�identifiers�suffixed_number_literals�prefixed_number_literals�plain_number_literals�string_literals�digraph_punctuation�digraph_operators�unigraph_punctuation�unigraph_operators)r r r"