Parser-MGC-0.16000755001750001750 013035213443 12017 5ustar00leoleo000000000000Parser-MGC-0.16/Build.PL000444001750001750 100713035213443 13446 0ustar00leoleo000000000000use strict; use warnings; use Module::Build; my $build = Module::Build->new( module_name => 'Parser::MGC', requires => { 'File::Slurp::Tiny' => 0, 'Scalar::Util' => 0, }, test_requires => { 'File::Temp' => 0, 'Test::More' => '0.88', # done_testing }, configure_requires => { 'Module::Build' => '0.4004', # test_requires }, license => 'perl', create_makefile_pl => 'traditional', create_license => 1, create_readme => 1, ); $build->create_build_script; Parser-MGC-0.16/Changes000444001750001750 742013035213443 13452 0ustar00leoleo000000000000Revision history for Parser-MGC 0.16 2017/01/10 16:39:02 [CHANGES] * Added ->take method * Added ->committed_scope_of method * Added a simple Bencode example 0.15 2015/12/03 16:56:19 [CHANGES] * Allow method names as well as CODE references to structure-forming methods * Added worked run-through example documentation and explanation of the expression evaluator parser example * Further expanded Parser::MGC::Tutorial 0.14 2015/08/31 15:29:36 [CHANGES] * Many documentation improvements: + More detailed explanation of backtracking behaviour and the use of the ->commit method + Trailing delimiter does not upset ->list_of + Added an as-yet incomplete Parser::MGC::Tutorial * Use Scalar::Util::blessed() to avoid the eval { ->isa } antipattern * Have long-deprecated ->one_of print a deprecation warning 0.13 2015/06/25 19:05:10 [CHANGES] * Use File::Slurp::Tiny instead of File::Slurp 0.12 2013/09/01 01:30:13 [CHANGES] * Ensure that ->expect / ->maybe_expect with optional capture groups don't yield warnings (thanks BP Jonsson) * Allow setting binmode for ->from_file * Slightly neater examples/parse-xml.pl 0.11 CHANGES: * Allow different toplevel parse methods to the constructor * Added another example showing parsing XML - only a minimal example; do not use this as real code. :) 0.10 CHANGES: * Added ->maybe_expect, for higher performance parsers 0.09 CHANGES: * Added ->pos accessor and ->fail_from to throw failures from other locations * Added ->token_number as a convenience for int or float 0.08 CHANGES: * Give ->list_of and ->sequence_of proper failure-handling semantics * Added ->generic_token * Defer conversion of pos into line/col/text until string-formatting a failure exception - improves performance of backtracking * Make token_float tuneable 0.07 CHANGES: * Allow ->expect to return subgroup captures in list context * Documentation improvements BUGFIXES: * Use Data::Dumper rather than Data::Dump in examples, as the latter is not core; no point pulling in non-core deps simply for examples 0.06 CHANGES: * Renamed ->one_of to ->any_of * Added ->substring_before * Allow ->scope_of to not take a start pattern * Recognise the usual set of character escapes in ->token_string * Added more example scripts to demonstrate: + the use ->substring_before to parse POD-like notation + accumulator variables instead of structural return * Unit-test the example scripts 0.05 CHANGES: * Added ->scope_level * Added ->from_reader as a new potential source of string input 0.04 CHANGES: * Added ->token_float * Optionally parse 0o... ad octal integers BUGFIXES: * Match strings non-greedily * Correct exception printing when line indent includes tabs (thanks to Khisanth/#perl) 0.03 CHANGES: * Expanded documentation, more examples BUGFIXES: * Regexp quoting fix for perl >= 5.13.6 * Declare dependency on File::Slurp 0.02 CHANGES: * ->expect now returns the consumed string * ->token_int recognises negative integers * ->token_* raises a failure at end-of-scope, rather than returning undef BUGFIXES: * 'use overload fallback' to keep Test::More 0.96 happy 0.01 First version, released on an unsuspecting world. Parser-MGC-0.16/LICENSE000444001750001750 4376213035213443 13215 0ustar00leoleo000000000000This software is copyright (c) 2017 by Paul Evans . This is free software; you can redistribute it and/or modify it under the same terms as the Perl 5 programming language system itself. Terms of the Perl programming language system itself a) the GNU General Public License as published by the Free Software Foundation; either version 1, or (at your option) any later version, or b) the "Artistic License" --- The GNU General Public License, Version 1, February 1989 --- This software is Copyright (c) 2017 by Paul Evans . This is free software, licensed under: The GNU General Public License, Version 1, February 1989 GNU GENERAL PUBLIC LICENSE Version 1, February 1989 Copyright (C) 1989 Free Software Foundation, Inc. 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA Everyone is permitted to copy and distribute verbatim copies of this license document, but changing it is not allowed. Preamble The license agreements of most software companies try to keep users at the mercy of those companies. By contrast, our General Public License is intended to guarantee your freedom to share and change free software--to make sure the software is free for all its users. The General Public License applies to the Free Software Foundation's software and to any other program whose authors commit to using it. You can use it for your programs, too. When we speak of free software, we are referring to freedom, not price. Specifically, the General Public License is designed to make sure that you have the freedom to give away or sell copies of free software, that you receive source code or can get it if you want it, that you can change the software or use pieces of it in new free programs; and that you know you can do these things. To protect your rights, we need to make restrictions that forbid anyone to deny you these rights or to ask you to surrender the rights. These restrictions translate to certain responsibilities for you if you distribute copies of the software, or if you modify it. For example, if you distribute copies of a such a program, whether gratis or for a fee, you must give the recipients all the rights that you have. You must make sure that they, too, receive or can get the source code. And you must tell them their rights. We protect your rights with two steps: (1) copyright the software, and (2) offer you this license which gives you legal permission to copy, distribute and/or modify the software. Also, for each author's protection and ours, we want to make certain that everyone understands that there is no warranty for this free software. If the software is modified by someone else and passed on, we want its recipients to know that what they have is not the original, so that any problems introduced by others will not reflect on the original authors' reputations. The precise terms and conditions for copying, distribution and modification follow. GNU GENERAL PUBLIC LICENSE TERMS AND CONDITIONS FOR COPYING, DISTRIBUTION AND MODIFICATION 0. This License Agreement applies to any program or other work which contains a notice placed by the copyright holder saying it may be distributed under the terms of this General Public License. The "Program", below, refers to any such program or work, and a "work based on the Program" means either the Program or any work containing the Program or a portion of it, either verbatim or with modifications. Each licensee is addressed as "you". 1. You may copy and distribute verbatim copies of the Program's source code as you receive it, in any medium, provided that you conspicuously and appropriately publish on each copy an appropriate copyright notice and disclaimer of warranty; keep intact all the notices that refer to this General Public License and to the absence of any warranty; and give any other recipients of the Program a copy of this General Public License along with the Program. You may charge a fee for the physical act of transferring a copy. 2. You may modify your copy or copies of the Program or any portion of it, and copy and distribute such modifications under the terms of Paragraph 1 above, provided that you also do the following: a) cause the modified files to carry prominent notices stating that you changed the files and the date of any change; and b) cause the whole of any work that you distribute or publish, that in whole or in part contains the Program or any part thereof, either with or without modifications, to be licensed at no charge to all third parties under the terms of this General Public License (except that you may choose to grant warranty protection to some or all third parties, at your option). c) If the modified program normally reads commands interactively when run, you must cause it, when started running for such interactive use in the simplest and most usual way, to print or display an announcement including an appropriate copyright notice and a notice that there is no warranty (or else, saying that you provide a warranty) and that users may redistribute the program under these conditions, and telling the user how to view a copy of this General Public License. d) You may charge a fee for the physical act of transferring a copy, and you may at your option offer warranty protection in exchange for a fee. Mere aggregation of another independent work with the Program (or its derivative) on a volume of a storage or distribution medium does not bring the other work under the scope of these terms. 3. You may copy and distribute the Program (or a portion or derivative of it, under Paragraph 2) in object code or executable form under the terms of Paragraphs 1 and 2 above provided that you also do one of the following: a) accompany it with the complete corresponding machine-readable source code, which must be distributed under the terms of Paragraphs 1 and 2 above; or, b) accompany it with a written offer, valid for at least three years, to give any third party free (except for a nominal charge for the cost of distribution) a complete machine-readable copy of the corresponding source code, to be distributed under the terms of Paragraphs 1 and 2 above; or, c) accompany it with the information you received as to where the corresponding source code may be obtained. (This alternative is allowed only for noncommercial distribution and only if you received the program in object code or executable form alone.) Source code for a work means the preferred form of the work for making modifications to it. For an executable file, complete source code means all the source code for all modules it contains; but, as a special exception, it need not include source code for modules which are standard libraries that accompany the operating system on which the executable file runs, or for standard header files or definitions files that accompany that operating system. 4. You may not copy, modify, sublicense, distribute or transfer the Program except as expressly provided under this General Public License. Any attempt otherwise to copy, modify, sublicense, distribute or transfer the Program is void, and will automatically terminate your rights to use the Program under this License. However, parties who have received copies, or rights to use copies, from you under this General Public License will not have their licenses terminated so long as such parties remain in full compliance. 5. By copying, distributing or modifying the Program (or any work based on the Program) you indicate your acceptance of this license to do so, and all its terms and conditions. 6. Each time you redistribute the Program (or any work based on the Program), the recipient automatically receives a license from the original licensor to copy, distribute or modify the Program subject to these terms and conditions. You may not impose any further restrictions on the recipients' exercise of the rights granted herein. 7. The Free Software Foundation may publish revised and/or new versions of the General Public License from time to time. Such new versions will be similar in spirit to the present version, but may differ in detail to address new problems or concerns. Each version is given a distinguishing version number. If the Program specifies a version number of the license which applies to it and "any later version", you have the option of following the terms and conditions either of that version or of any later version published by the Free Software Foundation. If the Program does not specify a version number of the license, you may choose any version ever published by the Free Software Foundation. 8. If you wish to incorporate parts of the Program into other free programs whose distribution conditions are different, write to the author to ask for permission. For software which is copyrighted by the Free Software Foundation, write to the Free Software Foundation; we sometimes make exceptions for this. Our decision will be guided by the two goals of preserving the free status of all derivatives of our free software and of promoting the sharing and reuse of software generally. NO WARRANTY 9. BECAUSE THE PROGRAM IS LICENSED FREE OF CHARGE, THERE IS NO WARRANTY FOR THE PROGRAM, TO THE EXTENT PERMITTED BY APPLICABLE LAW. EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE. THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE PROGRAM IS WITH YOU. SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF ALL NECESSARY SERVICING, REPAIR OR CORRECTION. 10. IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MAY MODIFY AND/OR REDISTRIBUTE THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES, INCLUDING ANY GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING OUT OF THE USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED TO LOSS OF DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER PROGRAMS), EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF SUCH DAMAGES. END OF TERMS AND CONDITIONS Appendix: How to Apply These Terms to Your New Programs If you develop a new program, and you want it to be of the greatest possible use to humanity, the best way to achieve this is to make it free software which everyone can redistribute and change under these terms. To do so, attach the following notices to the program. It is safest to attach them to the start of each source file to most effectively convey the exclusion of warranty; and each file should have at least the "copyright" line and a pointer to where the full notice is found. Copyright (C) 19yy This program is free software; you can redistribute it and/or modify it under the terms of the GNU General Public License as published by the Free Software Foundation; either version 1, or (at your option) any later version. This program is distributed in the hope that it will be useful, but WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for more details. You should have received a copy of the GNU General Public License along with this program; if not, write to the Free Software Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston MA 02110-1301 USA Also add information on how to contact you by electronic and paper mail. If the program is interactive, make it output a short notice like this when it starts in an interactive mode: Gnomovision version 69, Copyright (C) 19xx name of author Gnomovision comes with ABSOLUTELY NO WARRANTY; for details type `show w'. This is free software, and you are welcome to redistribute it under certain conditions; type `show c' for details. The hypothetical commands `show w' and `show c' should show the appropriate parts of the General Public License. Of course, the commands you use may be called something other than `show w' and `show c'; they could even be mouse-clicks or menu items--whatever suits your program. You should also get your employer (if you work as a programmer) or your school, if any, to sign a "copyright disclaimer" for the program, if necessary. Here a sample; alter the names: Yoyodyne, Inc., hereby disclaims all copyright interest in the program `Gnomovision' (a program to direct compilers to make passes at assemblers) written by James Hacker. , 1 April 1989 Ty Coon, President of Vice That's all there is to it! --- The Artistic License 1.0 --- This software is Copyright (c) 2017 by Paul Evans . This is free software, licensed under: The Artistic License 1.0 The Artistic License Preamble The intent of this document is to state the conditions under which a Package may be copied, such that the Copyright Holder maintains some semblance of artistic control over the development of the package, while giving the users of the package the right to use and distribute the Package in a more-or-less customary fashion, plus the right to make reasonable modifications. Definitions: - "Package" refers to the collection of files distributed by the Copyright Holder, and derivatives of that collection of files created through textual modification. - "Standard Version" refers to such a Package if it has not been modified, or has been modified in accordance with the wishes of the Copyright Holder. - "Copyright Holder" is whoever is named in the copyright or copyrights for the package. - "You" is you, if you're thinking about copying or distributing this Package. - "Reasonable copying fee" is whatever you can justify on the basis of media cost, duplication charges, time of people involved, and so on. (You will not be required to justify it to the Copyright Holder, but only to the computing community at large as a market that must bear the fee.) - "Freely Available" means that no fee is charged for the item itself, though there may be fees involved in handling the item. It also means that recipients of the item may redistribute it under the same conditions they received it. 1. You may make and give away verbatim copies of the source form of the Standard Version of this Package without restriction, provided that you duplicate all of the original copyright notices and associated disclaimers. 2. You may apply bug fixes, portability fixes and other modifications derived from the Public Domain or from the Copyright Holder. A Package modified in such a way shall still be considered the Standard Version. 3. You may otherwise modify your copy of this Package in any way, provided that you insert a prominent notice in each changed file stating how and when you changed that file, and provided that you do at least ONE of the following: a) place your modifications in the Public Domain or otherwise make them Freely Available, such as by posting said modifications to Usenet or an equivalent medium, or placing the modifications on a major archive site such as ftp.uu.net, or by allowing the Copyright Holder to include your modifications in the Standard Version of the Package. b) use the modified Package only within your corporation or organization. c) rename any non-standard executables so the names do not conflict with standard executables, which must also be provided, and provide a separate manual page for each non-standard executable that clearly documents how it differs from the Standard Version. d) make other distribution arrangements with the Copyright Holder. 4. You may distribute the programs of this Package in object code or executable form, provided that you do at least ONE of the following: a) distribute a Standard Version of the executables and library files, together with instructions (in the manual page or equivalent) on where to get the Standard Version. b) accompany the distribution with the machine-readable source of the Package with your modifications. c) accompany any non-standard executables with their corresponding Standard Version executables, giving the non-standard executables non-standard names, and clearly documenting the differences in manual pages (or equivalent), together with instructions on where to get the Standard Version. d) make other distribution arrangements with the Copyright Holder. 5. You may charge a reasonable copying fee for any distribution of this Package. You may charge any fee you choose for support of this Package. You may not charge a fee for this Package itself. However, you may distribute this Package in aggregate with other (possibly commercial) programs as part of a larger (possibly commercial) software distribution provided that you do not advertise this Package as a product of your own. 6. The scripts and library files supplied as input to or produced as output from the programs of this Package do not automatically fall under the copyright of this Package, but belong to whomever generated them, and may be sold commercially, and may be aggregated with this Package. 7. C or perl subroutines supplied by you and linked into this Package shall not be considered part of this Package. 8. The name of the Copyright Holder may not be used to endorse or promote products derived from this software without specific prior written permission. 9. THIS PACKAGE IS PROVIDED "AS IS" AND WITHOUT ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, WITHOUT LIMITATION, THE IMPLIED WARRANTIES OF MERCHANTIBILITY AND FITNESS FOR A PARTICULAR PURPOSE. The End Parser-MGC-0.16/MANIFEST000444001750001750 150013035213443 13301 0ustar00leoleo000000000000Build.PL Changes examples/eval-expr.pl examples/LICENSE examples/parse-bencode.pl examples/parse-dict.pl examples/parse-perlstr.pl examples/parse-pod.pl examples/parse-xml.pl examples/synopsis.pl lib/Parser/MGC.pm lib/Parser/MGC/Examples/EvaluateExpression.pm lib/Parser/MGC/Tutorial.pod LICENSE Makefile.PL MANIFEST This list of files META.json META.yml README t/00use.t t/01base.t t/02expect.t t/03reader.t t/04where.t t/05comment.t t/06take.t t/07generic_token.t t/08substring.t t/10token_int.t t/11token_float.t t/12token_number.t t/13token_string.t t/14token_ident.t t/15token_kw.t t/20maybe.t t/21scope_of.t t/22list_of.t t/23sequence_of.t t/24any_of.t t/30commit.t t/31scope_level.t t/32committed_scope_of.t t/32exception.t t/90ex_bencode.t t/90ex_dict.t t/90ex_expr.t t/90ex_pod.t t/90ex_synopsis.t t/90ex_xml.t t/99pod.t Parser-MGC-0.16/META.json000444001750001750 231513035213443 13576 0ustar00leoleo000000000000{ "abstract" : "build simple recursive-descent parsers", "author" : [ "Paul Evans " ], "dynamic_config" : 1, "generated_by" : "Module::Build version 0.422", "license" : [ "perl_5" ], "meta-spec" : { "url" : "http://search.cpan.org/perldoc?CPAN::Meta::Spec", "version" : "2" }, "name" : "Parser-MGC", "prereqs" : { "configure" : { "requires" : { "Module::Build" : "0.4004" } }, "runtime" : { "requires" : { "File::Slurp::Tiny" : "0", "Scalar::Util" : "0" } }, "test" : { "requires" : { "File::Temp" : "0", "Test::More" : "0.88" } } }, "provides" : { "Parser::MGC" : { "file" : "lib/Parser/MGC.pm", "version" : "0.16" }, "Parser::MGC::Examples::EvaluateExpression" : { "file" : "lib/Parser/MGC/Examples/EvaluateExpression.pm" } }, "release_status" : "stable", "resources" : { "license" : [ "http://dev.perl.org/licenses/" ] }, "version" : "0.16", "x_serialization_backend" : "JSON::PP version 2.27400" } Parser-MGC-0.16/META.yml000444001750001750 142113035213443 13423 0ustar00leoleo000000000000--- abstract: 'build simple recursive-descent parsers' author: - 'Paul Evans ' build_requires: File::Temp: '0' Test::More: '0.88' configure_requires: Module::Build: '0.4004' dynamic_config: 1 generated_by: 'Module::Build version 0.422, CPAN::Meta::Converter version 2.150005' license: perl meta-spec: url: http://module-build.sourceforge.net/META-spec-v1.4.html version: '1.4' name: Parser-MGC provides: Parser::MGC: file: lib/Parser/MGC.pm version: '0.16' Parser::MGC::Examples::EvaluateExpression: file: lib/Parser/MGC/Examples/EvaluateExpression.pm requires: File::Slurp::Tiny: '0' Scalar::Util: '0' resources: license: http://dev.perl.org/licenses/ version: '0.16' x_serialization_backend: 'CPAN::Meta::YAML version 0.018' Parser-MGC-0.16/Makefile.PL000444001750001750 57413035213443 14114 0ustar00leoleo000000000000# Note: this file was auto-generated by Module::Build::Compat version 0.4220 use ExtUtils::MakeMaker; WriteMakefile ( 'NAME' => 'Parser::MGC', 'VERSION_FROM' => 'lib/Parser/MGC.pm', 'PREREQ_PM' => { 'File::Slurp::Tiny' => 0, 'Scalar::Util' => 0 }, 'INSTALLDIRS' => 'site', 'EXE_FILES' => [], 'PL_FILES' => {} ) ; Parser-MGC-0.16/README000444001750001750 5103113035213443 13054 0ustar00leoleo000000000000NAME Parser::MGC - build simple recursive-descent parsers SYNOPSIS package My::Grammar::Parser use base qw( Parser::MGC ); sub parse { my $self = shift; $self->sequence_of( sub { $self->any_of( sub { $self->token_int }, sub { $self->token_string }, sub { \$self->token_ident }, sub { $self->scope_of( "(", \&parse, ")" ) } ); } ); } my $parser = My::Grammar::Parser->new; my $tree = $parser->from_file( $ARGV[0] ); ... DESCRIPTION This base class provides a low-level framework for building recursive-descent parsers that consume a given input string from left to right, returning a parse structure. It takes its name from the m//gc regexps used to implement the token parsing behaviour. It provides a number of token-parsing methods, which each extract a grammatical token from the string. It also provides wrapping methods that can be used to build up a possibly-recursive grammar structure, by applying a structure around other parts of parsing code. Backtracking Each method, both token and structural, atomically either consumes a prefix of the string and returns its result, or fails and consumes nothing. This makes it simple to implement grammars that require backtracking. Several structure-forming methods have some form of "optional" behaviour; they can optionally consume some amount of input or take some particular choice, but if the code invoked inside that subsequently fails, the structure can backtrack and take some different behaviour. This is usually what is required when testing whether the structure of the input string matches some part of the grammar that is optional, or has multiple choices. However, once the choice of grammar has been made, it is often useful to be able to fix on that one choice, thus making subsequent failures propagate up rather than taking that alternative behaviour. Control of this backtracking is given by the commit method; and careful use of this method is one of the key advantages that Parser::MGC has over more simple parsing using single regexps alone. CONSTRUCTOR new $parser = Parser::MGC->new( %args ) Returns a new instance of a Parser::MGC object. This must be called on a subclass that provides method of the name provided as toplevel, by default called parse. Takes the following named arguments toplevel => STRING Name of the toplevel method to use to start the parse from. If not supplied, will try to use a method called parse. patterns => HASH Keys in this hash should map to quoted regexp (qr//) references, to override the default patterns used to match tokens. See PATTERNS below accept_0o_oct => BOOL If true, the token_int method will also accept integers with a 0o prefix as octal. PATTERNS The following pattern names are recognised. They may be passed to the constructor in the patterns hash, or provided as a class method under the name pattern_name. * ws Pattern used to skip whitespace between tokens. Defaults to /[\s\n\t]+/ * comment Pattern used to skip comments between tokens. Undefined by default. * int Pattern used to parse an integer by token_int. Defaults to /-?(?:0x[[:xdigit:]]+|[[:digit:]]+)/. If accept_0o_oct is given, then this will be expanded to match /0o[0-7]+/ as well. * float Pattern used to parse a floating-point number by token_float. Defaults to /-?(?:\d*\.\d+|\d+\.)(?:e-?\d+)?|-?\d+e-?\d+/i. * ident Pattern used to parse an identifier by token_ident. Defaults to /[[:alpha:]_]\w*/ * string_delim Pattern used to delimit a string by token_string. Defaults to /["']/. METHODS from_string $result = $parser->from_string( $str ) Parse the given literal string and return the result from the toplevel method. from_file $result = $parser->from_file( $file, %opts ) Parse the given file, which may be a pathname in a string, or an opened IO handle, and return the result from the toplevel method. The following options are recognised: binmode => STRING If set, applies the given binmode to the filehandle before reading. Typically this can be used to set the encoding of the file. $parser->from_file( $file, binmode => ":encoding(UTF-8)" ) from_reader $result = $parser->from_reader( \&reader ) Since version 0.05. Parse the input which is read by the reader function. This function will be called in scalar context to generate portions of string to parse, being passed the $parser object. The function should return undef when it has no more string to return. $reader->( $parser ) Note that because it is not generally possible to detect exactly when more input may be required due to failed regexp parsing, the reader function is only invoked during searching for skippable whitespace. This makes it suitable for reading lines of a file in the common case where lines are considered as skippable whitespace, or for reading lines of input interractively from a user. It cannot be used in all cases (for example, reading fixed-size buffers from a file) because two successive invocations may split a single token across the buffer boundaries, and cause parse failures. pos $pos = $parser->pos Since version 0.09. Returns the current parse position, as a character offset from the beginning of the file or string. take $str = $parser->take( $len ) Since version 0.16. Returns the next $len characters directly from the input, prior to any whitespace or comment skipping. This does not take account of any pending end-of-scope marker that may be pending. It is intended for use by parsers of partially-binary protocols, or other situations in which it would be incorrect for the end-of-scope marker to take effect at this time. where ( $lineno, $col, $text ) = $parser->where Returns the current parse position, as a line and column number, and the entire current line of text. The first line is numbered 1, and the first column is numbered 0. fail fail_from $parser->fail( $message ) $parser->fail_from( $pos, $message ) fail_from since version 0.09. Aborts the current parse attempt with the given message string. The failure message will include the line and column position, and the line of input that failed at the current parse position (fail), or a position earlier obtained using the pos method (fail_from). This failure will propagate up to the inner-most structure parsing method that has not been committed; or will cause the entire parser to fail if there are no further options to take. at_eos $eos = $parser->at_eos Returns true if the input string is at the end of the string. scope_level $level = $parser->scope_level Since version 0.05. Returns the number of nested scope_of calls that have been made. STRUCTURE-FORMING METHODS The following methods may be used to build a grammatical structure out of the defined basic token-parsing methods. Each takes at least one code reference, which will be passed the actual $parser object as its first argument. maybe $ret = $parser->maybe( $code ) Attempts to execute the given $code in scalar context, and returns what it returned, accepting that it might fail. $code may either be a CODE reference or a method name given as a string. If the code fails (either by calling fail itself, or by propagating a failure from another method it invoked) before it has invoked commit, then none of the input string will be consumed; the current parsing position will be restored. undef will be returned in this case. If it calls commit then any subsequent failure will be propagated to the caller, rather than returning undef. This may be considered to be similar to the ? regexp qualifier. sub parse_declaration { my $self = shift; [ $self->parse_type, $self->token_ident, $self->maybe( sub { $self->expect( "=" ); $self->parse_expression } ), ]; } scope_of $ret = $parser->scope_of( $start, $code, $stop ) Expects to find the $start pattern, then attempts to execute the given $code, then expects to find the $stop pattern. Returns whatever the code returned. $code may either be a CODE reference of a method name given as a string. While the code is being executed, the $stop pattern will be used by the token parsing methods as an end-of-scope marker; causing them to raise a failure if called at the end of a scope. sub parse_block { my $self = shift; $self->scope_of( "{", sub { $self->parse_statements }, "}" ); } If the $start pattern is undefined, it is presumed the caller has already checked for this. This is useful when the stop pattern needs to be calculated based on the start pattern. sub parse_bracketed { my $self = shift; my $delim = $self->expect( qr/[\(\[\<\{]/ ); $delim =~ tr/([<{/)]>}/; $self->scope_of( undef, sub { $self->parse_body }, $delim ); } This method does not have any optional parts to it; any failures are immediately propagated to the caller. committed_scope_of $ret = $parser->committed_scope_of( $start, $code, $stop ) Since version 0.16. A variant of "scope_of" that calls "commit" after a successful match of the start pattern. This is usually what you want if using scope_of from within an any_of choice, if no other alternative following this one could possibly match if the start pattern has. list_of $ret = $parser->list_of( $sep, $code ) Expects to find a list of instances of something parsed by $code, separated by the $sep pattern. Returns an ARRAY ref containing a list of the return values from the $code. A single trailing delimiter is allowed, and does not affect the return value. $code may either be a CODE reference or a method name given as a string. This method does not consider it an error if the returned list is empty; that is, that the scope ended before any item instances were parsed from it. sub parse_numbers { my $self = shift; $self->list_of( ",", sub { $self->token_int } ); } If the code fails (either by invoking fail itself, or by propagating a failure from another method it invoked) before it has invoked commit on a particular item, then the item is aborted and the parsing position will be restored to the beginning of that failed item. The list of results from previous successful attempts will be returned. If it calls commit within an item then any subsequent failure for that item will cause the entire list_of to fail, propagating that to the caller. sequence_of $ret = $parser->sequence_of( $code ) A shortcut for calling list_of with an empty string as separator; expects to find at least one instance of something parsed by $code, separated only by skipped whitespace. This may be considered to be similar to the + or * regexp qualifiers. sub parse_statements { my $self = shift; $self->sequence_of( sub { $self->parse_statement } ); } The interaction of failures in the code and the commit method is identical to that of list_of. any_of $ret = $parser->any_of( @codes ) Since version 0.06. Expects that one of the given code instances can parse something from the input, returning what it returned. Each code instance may indicate a failure to parse by calling the fail method or otherwise propagating a failure. Each code instance may either be a CODE reference or a method name given as a string. This may be considered to be similar to the | regexp operator for forming alternations of possible parse trees. sub parse_statement { my $self = shift; $self->any_of( sub { $self->parse_declaration; $self->expect(";") }, sub { $self->parse_expression; $self->expect(";") }, sub { $self->parse_block }, ); } If the code for a given choice fails (either by invoking fail itself, or by propagating a failure from another method it invoked) before it has invoked commit itself, then the parsing position restored and the next choice will be attempted. If it calls commit then any subsequent failure for that choice will cause the entire any_of to fail, propagating that to the caller and no further choices will be attmepted. commit $parser->commit Calling this method will cancel the backtracking behaviour of the innermost maybe, list_of, sequence_of, or any_of structure forming method. That is, if later code then calls fail, the exception will be propagated out of maybe, no further list items will be attempted by list_of or sequence_of, and no further code blocks will be attempted by any_of. Typically this will be called once the grammatical structure alter has been determined, ensuring that any further failures are raised as real exceptions, rather than by attempting other alternatives. sub parse_statement { my $self = shift; $self->any_of( ... sub { $self->scope_of( "{", sub { $self->commit; $self->parse_statements; }, "}" ), }, ); } Though in this common pattern, "committed_scope_of" may be used instead. TOKEN PARSING METHODS The following methods attempt to consume some part of the input string, to be used as part of the parsing process. expect $str = $parser->expect( $literal ) $str = $parser->expect( qr/pattern/ ) @groups = $parser->expect( qr/pattern/ ) Expects to find a literal string or regexp pattern match, and consumes it. In scalar context, this method returns the string that was captured. In list context it returns the matching substring and the contents of any subgroups contained in the pattern. This method will raise a parse error (by calling fail) if the regexp fails to match. Note that if the pattern could match an empty string (such as for example qr/\d*/), the pattern will always match, even if it has to match an empty string. This method will not consider a failure if the regexp matches with zero-width. maybe_expect $str = $parser->maybe_expect( ... ) @groups = $parser->maybe_expect( ... ) Since version 0.10. A convenient shortcut equivalent to calling expect within maybe, but implemented more efficiently, avoiding the exception-handling set up by maybe. Returns undef or an empty list if the match fails. substring_before $str = $parser->substring_before( $literal ) $str = $parser->substring_before( qr/pattern/ ) Since version 0.06. Expects to possibly find a literal string or regexp pattern match. If it finds such, consume all the input text before but excluding this match, and return it. If it fails to find a match before the end of the current scope, consumes all the input text until the end of scope and return it. This method does not consume the part of input that matches, only the text before it. It is not considered a failure if the substring before this match is empty. If a non-empty match is required, use the fail method: sub token_nonempty_part { my $self = shift; my $str = $parser->substring_before( "," ); length $str or $self->fail( "Expected a string fragment before ," ); return $str; } Note that unlike most of the other token parsing methods, this method does not consume either leading or trailing whitespace around the substring. It is expected that this method would be used as part a parser to read quoted strings, or similar cases where whitespace should be preserved. generic_token $val = $parser->generic_token( $name, $re, $convert ) Since version 0.08. Expects to find a token matching the precompiled regexp $re. If provided, the $convert CODE reference can be used to convert the string into a more convenient form. $name is used in the failure message if the pattern fails to match. If provided, the $convert function will be passed the parser and the matching substring; the value it returns is returned from generic_token. $convert->( $parser, $substr ) If not provided, the substring will be returned as it stands. This method is mostly provided for subclasses to define their own token types. For example: sub token_hex { my $self = shift; $self->generic_token( hex => qr/[0-9A-F]{2}h/, sub { hex $_[1] } ); } token_int $int = $parser->token_int Expects to find an integer in decimal, octal or hexadecimal notation, and consumes it. Negative integers, preceeded by -, are also recognised. token_float $float = $parser->token_float Since version 0.04. Expects to find a number expressed in floating-point notation; a sequence of digits possibly prefixed by -, possibly containing a decimal point, possibly followed by an exponent specified by e followed by an integer. The numerical value is then returned. token_number $number = $parser->token_number Since version 0.09. Expects to find a number expressed in either of the above forms. token_string $str = $parser->token_string Expects to find a quoted string, and consumes it. The string should be quoted using " or ' quote marks. The content of the quoted string can contain character escapes similar to those accepted by C or Perl. Specifically, the following forms are recognised: \a Bell ("alert") \b Backspace \e Escape \f Form feed \n Newline \r Return \t Horizontal Tab \0, \012 Octal character \x34, \x{5678} Hexadecimal character C's \v for vertical tab is not supported as it is rarely used in practice and it collides with Perl's \v regexp escape. Perl's \c for forming other control characters is also not supported. token_ident $ident = $parser->token_ident Expects to find an identifier, and consumes it. token_kw $keyword = $parser->token_kw( @keywords ) Expects to find a keyword, and consumes it. A keyword is defined as an identifier which is exactly one of the literal values passed in. EXAMPLES Accumulating Results Using Variables Although the structure-forming methods all return a value, obtained from their nested parsing code, it can sometimes be more convenient to use a variable to accumulate a result in instead. For example, consider the following parser method, designed to parse a set of name: "value" assignments, such as might be found in a configuration file, or YAML/JSON-style mapping value. sub parse_dict { my $self = shift; my %ret; $self->list_of( ",", sub { my $key = $self->token_ident; exists $ret{$key} and $self->fail( "Already have a mapping for '$key'" ); $self->expect( ":" ); $ret{$key} = $self->parse_value; } ); return \%ret } Instead of using the return value from list_of, this method accumulates values in the %ret hash, eventually returning a reference to it as its result. Because of this, it can perform some error checking while it parses; namely, rejecting duplicate keys. TODO * Make unescaping of string constants more customisable. Possibly consider instead a parse_string_generic using a loop over substring_before. * Easy ability for subclasses to define more token types as methods. Perhaps provide a class method such as __PACKAGE__->has_token( hex => qr/[0-9A-F]+/i, sub { hex $_[1] } ); * Investigate how well from_reader can cope with buffer splitting across other tokens than simply skippable whitespace AUTHOR Paul Evans Parser-MGC-0.16/examples000755001750001750 013035213443 13635 5ustar00leoleo000000000000Parser-MGC-0.16/examples/LICENSE000444001750001750 233013035213443 14775 0ustar00leoleo000000000000The following licence applies to the example scripts in this directory ---------------------------------------------------------------------- The MIT License Copyright (c) 2011 Paul Evans Permission is hereby granted, free of charge, to any person obtaining a copy of this software and associated documentation files (the "Software"), to deal in the Software without restriction, including without limitation the rights to use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies of the Software, and to permit persons to whom the Software is furnished to do so, subject to the following conditions: The above copyright notice and this permission notice shall be included in all copies or substantial portions of the Software. THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE. Parser-MGC-0.16/examples/eval-expr.pl000444001750001750 235613035213443 16240 0ustar00leoleo000000000000#!/usr/bin/perl use strict; use warnings; package ExprParser; use base qw( Parser::MGC ); # An expression is a list of terms, joined by + or - operators sub parse { my $self = shift; my $val = $self->parse_term; 1 while $self->any_of( sub { $self->expect( "+" ); $self->commit; $val += $self->parse_term; 1 }, sub { $self->expect( "-" ); $self->commit; $val -= $self->parse_term; 1 }, sub { 0 }, ); return $val; } # A term is a list of factors, joined by * or - operators sub parse_term { my $self = shift; my $val = $self->parse_factor; 1 while $self->any_of( sub { $self->expect( "*" ); $self->commit; $val *= $self->parse_factor; 1 }, sub { $self->expect( "/" ); $self->commit; $val /= $self->parse_factor; 1 }, sub { 0 }, ); return $val; } # A factor is either a parenthesized expression, or an integer sub parse_factor { my $self = shift; $self->any_of( sub { $self->committed_scope_of( "(", 'parse', ")" ) }, sub { $self->token_int }, ); } if( !caller ) { my $parser = __PACKAGE__->new; while( defined( my $line = ) ) { my $ret = eval { $parser->from_string( $line ) }; print $@ and next if $@; print "$ret\n"; } } 1; Parser-MGC-0.16/examples/parse-bencode.pl000444001750001750 232613035213443 17041 0ustar00leoleo000000000000#!/usr/bin/perl use strict; use warnings; package BencodeParser; use base qw( Parser::MGC ); # See also # https://en.wikipedia.org/wiki/Bencode sub parse { my $self = shift; $self->any_of( sub { $self->parse_int }, sub { $self->parse_bytestring }, sub { $self->parse_list }, sub { $self->parse_dict }, ); } sub parse_int { my $self = shift; $self->expect( 'i' ); my $value = $self->expect( qr/-?\d+/ ); $self->expect( 'e' ); return $value; } sub parse_bytestring { my $self = shift; my $len = $self->expect( qr/\d+/ ); $self->expect( ':' ); return $self->take( $len ); } sub parse_list { my $self = shift; $self->committed_scope_of( 'l', sub { $self->sequence_of( sub { $self->parse } ) }, 'e' ); } sub parse_dict { my $self = shift; my $kvlist = $self->committed_scope_of( 'd', sub { $self->sequence_of( sub { $self->parse } ) }, 'e' ); return { @$kvlist }; } use Data::Dumper; if( !caller ) { my $parser = __PACKAGE__->new; while( defined( my $line = ) ) { my $ret = eval { $parser->from_string( $line ) }; print $@ and next if $@; print Dumper( $ret ); } } 1; Parser-MGC-0.16/examples/parse-dict.pl000444001750001750 134313035213443 16363 0ustar00leoleo000000000000#!/usr/bin/perl use strict; use warnings; package DictParser; use base qw( Parser::MGC ); sub parse { my $self = shift; $self->any_of( sub { $self->token_int }, sub { $self->token_string }, sub { $self->committed_scope_of( "{", 'parse_dict', "}" ) }, ); } sub parse_dict { my $self = shift; my %ret; $self->list_of( ",", sub { my $key = $self->token_ident; $self->expect( ":" ); $ret{$key} = $self->parse; } ); return \%ret } use Data::Dumper; if( !caller ) { my $parser = __PACKAGE__->new; while( defined( my $line = ) ) { my $ret = eval { $parser->from_string( $line ) }; print $@ and next if $@; print Dumper( $ret ); } } 1; Parser-MGC-0.16/examples/parse-perlstr.pl000555001750001750 651413035213443 17143 0ustar00leoleo000000000000#!/usr/bin/perl use strict; use warnings; use base qw( Parser::MGC ); my %unescape = ( q(') => q('), q(") => q("), "\\" => "\\", n => "\n", r => "\r", ); my $escapes = join "|", map quotemeta, keys %unescape; $escapes = qr/$escapes/; sub parse { my $self = shift; $self->any_of( # qq() strings sub { $self->scope_of( q("), sub { $self->parse_qq_body( q(") ) }, q(") ) }, sub { $self->expect( 'qq' ); my $start = $self->expect( qr/./ ); $self->commit; if( ( my $stop = $start ) =~ tr/([<{/)]>}/ ) { $self->scope_of( undef, sub { $self->parse_qq_body( $start, $stop ) }, $stop ) } else { $self->scope_of( undef, sub { $self->parse_qq_body( $start ) }, $stop ) } }, # q() strings sub { $self->scope_of( q('), sub { $self->parse_q_body( q(') ) }, q(') ) }, sub { $self->expect( 'q' ); my $start = $self->expect( qr/./ ); $self->commit; if( ( my $stop = $start ) =~ tr/([<{/)]>}/ ) { $self->scope_of( undef, sub { $self->parse_q_body( $start, $stop ) }, $stop ) } else { $self->scope_of( undef, sub { $self->parse_q_body( $start ) }, $stop ) } }, ); } sub parse_q_body { my $self = shift; my ( $start, $stop ) = @_; my @bodies = ( sub { $self->expect( "\\" ); $self->commit; $self->expect( qr/['"\\]/ ) }, sub { $self->substring_before( qr/[\\\Q$start\E]/ ) }, ); $stop and unshift @bodies, sub { $self->expect( $start ); $self->commit; my $inner; $self->scope_of( undef, sub { $inner = $self->parse_q_body( $start, $stop ) }, $stop ); "$start$inner$stop" }; my $parts = $self->sequence_of( sub { $self->any_of( @bodies ) } ); return join "", @$parts; } sub parse_qq_body { my $self = shift; my ( $start, $stop ) = @_; my @parts; my @bodies = ( sub { $self->expect( "\\" ); $self->commit; push @parts, $self->one_of( sub { $unescape{ $self->expect( $escapes ) } }, sub { $self->expect( "x" ); chr oct( "0x" . $self->expect( qr/[0-9A-Fa-f]+/ ) ) }, sub { chr oct "0" . $self->expect( qr/[0-7]+/ ) }, ); }, sub { $self->expect( '$' ); push @parts, [ interpolate => $self->token_ident ] }, # TODO: This isn't very accurate sub { $self->substring_before( qr/[\\\$\Q$start\E]/ ) }, ); $stop and unshift @bodies, sub { $self->expect( $start ); $self->commit; my $inner; $self->scope_of( undef, sub { $inner = $self->parse_qq_body( $start, $stop ) }, $stop ); push @parts, $start, @$inner, $stop; }; $self->sequence_of( sub { $self->any_of( @bodies ) } ); # Coaless plain strings for( my $i = 1; $i < @parts; $i++ ) { last; # debug next if ref $parts[$i-1] or ref $parts[$i]; $parts[$i-1] .= splice @parts, $i, 1; redo; } return \@parts; } use Data::Dumper; if( !caller ) { my $parser = __PACKAGE__->new; while( defined( my $line = ) ) { my $ret = eval { $parser->from_string( $line ) }; print $@ and next if $@; print Dumper( $ret ); } } 1; Parser-MGC-0.16/examples/parse-pod.pl000444001750001750 126213035213443 16222 0ustar00leoleo000000000000#!/usr/bin/perl use strict; use warnings; package PodParser; use base qw( Parser::MGC ); sub parse { my $self = shift; $self->sequence_of( sub { $self->any_of( sub { my ( undef, $tag, $delim ) = $self->expect( qr/([A-Z])(<+)/ ); $self->commit; +{ $tag => $self->scope_of( undef, \&parse, ">" x length $delim ) }; }, sub { $self->substring_before( qr/[A-Z]new; while( defined( my $line = ) ) { my $ret = eval { $parser->from_string( $line ) }; print $@ and next if $@; print Dumper( $ret ); } } 1; Parser-MGC-0.16/examples/parse-xml.pl000444001750001750 542213035213443 16242 0ustar00leoleo000000000000#!/usr/bin/perl use strict; use warnings; # DO NOT RELY ON THIS AS A REAL XML PARSER! # It is not intended to be used actually as an XML parser, simply to stand as # an example of how you might use Parser::MGC to parse an XML-like syntax # There are a great many things it doesn't do correctly; it lacks at least the # following features: # Entities # Processing instructions # Comments # CDATA package XmlParser; use base qw( Parser::MGC ); sub parse { my $self = shift; my $rootnode = $self->parse_node; $rootnode->kind eq "element" or die "Expected XML root node"; $rootnode->name eq "xml" or die "Expected XML root node"; return [ $rootnode->children ]; } sub parse_node { my $self = shift; # A "node" is either an XML element subtree or plaintext $self->any_of( 'parse_plaintext', 'parse_element' ); } sub parse_plaintext { my $self = shift; my $str = $self->substring_before( '<' ); $self->fail( "No plaintext" ) unless length $str; return XmlParser::Node::Plain->new( $str ); } sub parse_element { my $self = shift; my $tag = $self->parse_tag; $self->commit; return XmlParser::Node::Element->new( $tag->{name}, $tag->{attrs} ) if $tag->{selfclose}; my $childlist = $self->sequence_of( 'parse_node' ); $self->parse_close_tag->{name} eq $tag->{name} or $self->fail( "Expected $tag->{name} to be closed" ); return XmlParser::Node::Element->new( $tag->{name}, $tag->{attrs}, @$childlist ); } sub parse_tag { my $self = shift; $self->expect( '<' ); my $tagname = $self->token_ident; my $attrs = $self->sequence_of( 'parse_tag_attr' ); my $selfclose = $self->maybe_expect( '/' ); $self->expect( '>' ); return { name => $tagname, attrs => { map { ( $_->[0], $_->[1] ) } @$attrs }, selfclose => $selfclose, }; } sub parse_close_tag { my $self = shift; $self->expect( 'token_ident; $self->expect( '>' ); return { name => $tagname }; } sub parse_tag_attr { my $self = shift; my $attrname = $self->token_ident; $self->expect( '=' ); return [ $attrname => $self->parse_tag_attr_value ]; } sub parse_tag_attr_value { my $self = shift; # TODO: This sucks return $self->token_string; } use Data::Dumper; if( !caller ) { my $parser = __PACKAGE__->new; my $ret = $parser->from_file( \*STDIN ); print Dumper( $ret ); } package XmlParser::Node; sub new { my $class = shift; bless [ @_ ], $class } package XmlParser::Node::Plain; use base qw( XmlParser::Node ); sub kind { "plain" } sub text { shift->[0] } package XmlParser::Node::Element; use base qw( XmlParser::Node ); sub kind { "element" } sub name { shift->[0] } sub attrs { shift->[1] } sub children { my $self = shift; @{$self}[2..$#$self] } 1; Parser-MGC-0.16/examples/synopsis.pl000444001750001750 102013035213443 16207 0ustar00leoleo000000000000use strict; use warnings; package LispParser; use base qw( Parser::MGC ); use constant pattern_ident => qr{[[:alnum:]+*/._:-]+}; sub parse { my $self = shift; $self->sequence_of( sub { $self->any_of( sub { $self->token_int }, sub { $self->token_string }, sub { \$self->token_ident }, sub { $self->scope_of( "(", \&parse, ")" ) } ); } ); } use Data::Dumper; if( !caller ) { my $parser = __PACKAGE__->new; print Dumper( $parser->from_file( $ARGV[0] ) ); } 1; Parser-MGC-0.16/lib000755001750001750 013035213443 12565 5ustar00leoleo000000000000Parser-MGC-0.16/lib/Parser000755001750001750 013035213443 14021 5ustar00leoleo000000000000Parser-MGC-0.16/lib/Parser/MGC.pm000444001750001750 7575213035213443 15162 0ustar00leoleo000000000000# You may distribute under the terms of either the GNU General Public License # or the Artistic License (the same terms as Perl itself) # # (C) Paul Evans, 2010-2017 -- leonerd@leonerd.org.uk package Parser::MGC; use strict; use warnings; our $VERSION = '0.16'; use Carp; use File::Slurp::Tiny qw( read_file ); use Scalar::Util qw( blessed ); =head1 NAME C - build simple recursive-descent parsers =head1 SYNOPSIS package My::Grammar::Parser use base qw( Parser::MGC ); sub parse { my $self = shift; $self->sequence_of( sub { $self->any_of( sub { $self->token_int }, sub { $self->token_string }, sub { \$self->token_ident }, sub { $self->scope_of( "(", \&parse, ")" ) } ); } ); } my $parser = My::Grammar::Parser->new; my $tree = $parser->from_file( $ARGV[0] ); ... =head1 DESCRIPTION This base class provides a low-level framework for building recursive-descent parsers that consume a given input string from left to right, returning a parse structure. It takes its name from the C regexps used to implement the token parsing behaviour. It provides a number of token-parsing methods, which each extract a grammatical token from the string. It also provides wrapping methods that can be used to build up a possibly-recursive grammar structure, by applying a structure around other parts of parsing code. =head2 Backtracking Each method, both token and structural, atomically either consumes a prefix of the string and returns its result, or fails and consumes nothing. This makes it simple to implement grammars that require backtracking. Several structure-forming methods have some form of "optional" behaviour; they can optionally consume some amount of input or take some particular choice, but if the code invoked inside that subsequently fails, the structure can backtrack and take some different behaviour. This is usually what is required when testing whether the structure of the input string matches some part of the grammar that is optional, or has multiple choices. However, once the choice of grammar has been made, it is often useful to be able to fix on that one choice, thus making subsequent failures propagate up rather than taking that alternative behaviour. Control of this backtracking is given by the C method; and careful use of this method is one of the key advantages that C has over more simple parsing using single regexps alone. =cut =head1 CONSTRUCTOR =cut =head2 new $parser = Parser::MGC->new( %args ) Returns a new instance of a C object. This must be called on a subclass that provides method of the name provided as C, by default called C. Takes the following named arguments =over 8 =item toplevel => STRING Name of the toplevel method to use to start the parse from. If not supplied, will try to use a method called C. =item patterns => HASH Keys in this hash should map to quoted regexp (C) references, to override the default patterns used to match tokens. See C below =item accept_0o_oct => BOOL If true, the C method will also accept integers with a C<0o> prefix as octal. =back =cut =head1 PATTERNS The following pattern names are recognised. They may be passed to the constructor in the C hash, or provided as a class method under the name C>. =over 4 =item * ws Pattern used to skip whitespace between tokens. Defaults to C =item * comment Pattern used to skip comments between tokens. Undefined by default. =item * int Pattern used to parse an integer by C. Defaults to C. If C is given, then this will be expanded to match C as well. =item * float Pattern used to parse a floating-point number by C. Defaults to C. =item * ident Pattern used to parse an identifier by C. Defaults to C =item * string_delim Pattern used to delimit a string by C. Defaults to C. =back =cut my @patterns = qw( ws comment int float ident string_delim ); use constant pattern_ws => qr/[\s\n\t]+/; use constant pattern_comment => undef; use constant pattern_int => qr/-?(?:0x[[:xdigit:]]+|[[:digit:]]+)/; use constant pattern_float => qr/-?(?:\d*\.\d+|\d+\.)(?:e-?\d+)?|-?\d+e-?\d+/i; use constant pattern_ident => qr/[[:alpha:]_]\w*/; use constant pattern_string_delim => qr/["']/; sub new { my $class = shift; my %args = @_; my $toplevel = $args{toplevel} || "parse"; $class->can( $toplevel ) or croak "Expected to be a subclass that can ->$toplevel"; my $self = bless { toplevel => $toplevel, patterns => {}, scope_level => 0, }, $class; $self->{patterns}{$_} = $args{patterns}{$_} || $self->${\"pattern_$_"} for @patterns; if( $args{accept_0o_oct} ) { $self->{patterns}{int} = qr/0o[0-7]+|$self->{patterns}{int}/; } return $self; } =head1 METHODS =cut =head2 from_string $result = $parser->from_string( $str ) Parse the given literal string and return the result from the toplevel method. =cut sub from_string { my $self = shift; my ( $str ) = @_; $self->{str} = $str; pos $self->{str} = 0; my $toplevel = $self->{toplevel}; my $result = $self->$toplevel; $self->at_eos or $self->fail( "Expected end of input" ); return $result; } =head2 from_file $result = $parser->from_file( $file, %opts ) Parse the given file, which may be a pathname in a string, or an opened IO handle, and return the result from the toplevel method. The following options are recognised: =over 8 =item binmode => STRING If set, applies the given binmode to the filehandle before reading. Typically this can be used to set the encoding of the file. $parser->from_file( $file, binmode => ":encoding(UTF-8)" ) =back =cut sub from_file { my $self = shift; my ( $file, %opts ) = @_; $self->{filename} = $file; $self->from_string( ref $file ? do { local $/; binmode $file, $opts{binmode} if $opts{binmode}; <$file> } : ( read_file $file, binmode => $opts{binmode} ) ); } =head2 from_reader $result = $parser->from_reader( \&reader ) I Parse the input which is read by the C function. This function will be called in scalar context to generate portions of string to parse, being passed the C<$parser> object. The function should return C when it has no more string to return. $reader->( $parser ) Note that because it is not generally possible to detect exactly when more input may be required due to failed regexp parsing, the reader function is only invoked during searching for skippable whitespace. This makes it suitable for reading lines of a file in the common case where lines are considered as skippable whitespace, or for reading lines of input interractively from a user. It cannot be used in all cases (for example, reading fixed-size buffers from a file) because two successive invocations may split a single token across the buffer boundaries, and cause parse failures. =cut sub from_reader { my $self = shift; my ( $reader ) = @_; local $self->{reader} = $reader; $self->{str} = ""; pos $self->{str} = 0; my $result = $self->parse; $self->at_eos or $self->fail( "Expected end of input" ); return $result; } =head2 pos $pos = $parser->pos I Returns the current parse position, as a character offset from the beginning of the file or string. =cut sub pos { my $self = shift; return pos $self->{str}; } =head2 take $str = $parser->take( $len ) I Returns the next C<$len> characters directly from the input, prior to any whitespace or comment skipping. This does I take account of any pending end-of-scope marker that may be pending. It is intended for use by parsers of partially-binary protocols, or other situations in which it would be incorrect for the end-of-scope marker to take effect at this time. =cut sub take { my $self = shift; my ( $len ) = @_; my $start = pos( $self->{str} ); pos( $self->{str} ) += $len; return substr( $self->{str}, $start, $len ); } =head2 where ( $lineno, $col, $text ) = $parser->where Returns the current parse position, as a line and column number, and the entire current line of text. The first line is numbered 1, and the first column is numbered 0. =cut sub where { my $self = shift; my ( $pos ) = @_; defined $pos or $pos = pos $self->{str}; my $str = $self->{str}; my $sol = $pos; $sol-- if $sol > 0 and substr( $str, $sol, 1 ) =~ m/^[\r\n]$/; $sol-- while $sol > 0 and substr( $str, $sol-1, 1 ) !~ m/^[\r\n]$/; my $eol = $pos; $eol++ while $eol < length($str) and substr( $str, $eol, 1 ) !~ m/^[\r\n]$/; my $line = substr( $str, $sol, $eol - $sol ); my $col = $pos - $sol; my $lineno = ( () = substr( $str, 0, $pos ) =~ m/\n/g ) + 1; return ( $lineno, $col, $line ); } =head2 fail =head2 fail_from $parser->fail( $message ) $parser->fail_from( $pos, $message ) I since version 0.09.> Aborts the current parse attempt with the given message string. The failure message will include the line and column position, and the line of input that failed at the current parse position (C), or a position earlier obtained using the C method (C). This failure will propagate up to the inner-most structure parsing method that has not been committed; or will cause the entire parser to fail if there are no further options to take. =cut sub fail { my $self = shift; my ( $message ) = @_; $self->fail_from( $self->pos, $message ); } sub fail_from { my $self = shift; my ( $pos, $message ) = @_; die Parser::MGC::Failure->new( $message, $self, $pos ); } sub _isa_failure { blessed $_[0] and $_[0]->isa( "Parser::MGC::Failure" ) } =head2 at_eos $eos = $parser->at_eos Returns true if the input string is at the end of the string. =cut sub at_eos { my $self = shift; # Save pos() before skipping ws so we don't break the substring_before method my $pos = pos $self->{str}; $self->skip_ws; my $at_eos; if( pos( $self->{str} ) >= length $self->{str} ) { $at_eos = 1; } elsif( defined $self->{endofscope} ) { $at_eos = $self->{str} =~ m/\G$self->{endofscope}/; } else { $at_eos = 0; } pos( $self->{str} ) = $pos; return $at_eos; } =head2 scope_level $level = $parser->scope_level I Returns the number of nested C calls that have been made. =cut sub scope_level { my $self = shift; return $self->{scope_level}; } =head1 STRUCTURE-FORMING METHODS The following methods may be used to build a grammatical structure out of the defined basic token-parsing methods. Each takes at least one code reference, which will be passed the actual C<$parser> object as its first argument. =cut =head2 maybe $ret = $parser->maybe( $code ) Attempts to execute the given C<$code> in scalar context, and returns what it returned, accepting that it might fail. C<$code> may either be a CODE reference or a method name given as a string. If the code fails (either by calling C itself, or by propagating a failure from another method it invoked) before it has invoked C, then none of the input string will be consumed; the current parsing position will be restored. C will be returned in this case. If it calls C then any subsequent failure will be propagated to the caller, rather than returning C. This may be considered to be similar to the C regexp qualifier. sub parse_declaration { my $self = shift; [ $self->parse_type, $self->token_ident, $self->maybe( sub { $self->expect( "=" ); $self->parse_expression } ), ]; } =cut sub maybe { my $self = shift; my ( $code ) = @_; my $pos = pos $self->{str}; my $committed = 0; local $self->{committer} = sub { $committed++ }; my $ret; eval { $ret = $self->$code; 1 } and return $ret; my $e = $@; pos($self->{str}) = $pos; die $e if $committed or not _isa_failure( $e ); return undef; } =head2 scope_of $ret = $parser->scope_of( $start, $code, $stop ) Expects to find the C<$start> pattern, then attempts to execute the given C<$code>, then expects to find the C<$stop> pattern. Returns whatever the code returned. C<$code> may either be a CODE reference of a method name given as a string. While the code is being executed, the C<$stop> pattern will be used by the token parsing methods as an end-of-scope marker; causing them to raise a failure if called at the end of a scope. sub parse_block { my $self = shift; $self->scope_of( "{", sub { $self->parse_statements }, "}" ); } If the C<$start> pattern is undefined, it is presumed the caller has already checked for this. This is useful when the stop pattern needs to be calculated based on the start pattern. sub parse_bracketed { my $self = shift; my $delim = $self->expect( qr/[\(\[\<\{]/ ); $delim =~ tr/([<{/)]>}/; $self->scope_of( undef, sub { $self->parse_body }, $delim ); } This method does not have any optional parts to it; any failures are immediately propagated to the caller. =cut sub scope_of { my $self = shift; $self->_scope_of( 0, @_ ); } sub _scope_of { my $self = shift; my ( $commit_if_started, $start, $code, $stop ) = @_; ref $stop or $stop = qr/\Q$stop/; $self->expect( $start ) if defined $start; $self->commit if $commit_if_started; local $self->{endofscope} = $stop; local $self->{scope_level} = $self->{scope_level} + 1; my $ret = $self->$code; $self->expect( $stop ); return $ret; } =head2 committed_scope_of $ret = $parser->committed_scope_of( $start, $code, $stop ) I A variant of L that calls L after a successful match of the start pattern. This is usually what you want if using C from within an C choice, if no other alternative following this one could possibly match if the start pattern has. =cut sub committed_scope_of { my $self = shift; $self->_scope_of( 1, @_ ); } =head2 list_of $ret = $parser->list_of( $sep, $code ) Expects to find a list of instances of something parsed by C<$code>, separated by the C<$sep> pattern. Returns an ARRAY ref containing a list of the return values from the C<$code>. A single trailing delimiter is allowed, and does not affect the return value. C<$code> may either be a CODE reference or a method name given as a string. This method does not consider it an error if the returned list is empty; that is, that the scope ended before any item instances were parsed from it. sub parse_numbers { my $self = shift; $self->list_of( ",", sub { $self->token_int } ); } If the code fails (either by invoking C itself, or by propagating a failure from another method it invoked) before it has invoked C on a particular item, then the item is aborted and the parsing position will be restored to the beginning of that failed item. The list of results from previous successful attempts will be returned. If it calls C within an item then any subsequent failure for that item will cause the entire C to fail, propagating that to the caller. =cut sub list_of { my $self = shift; my ( $sep, $code ) = @_; ref $sep or $sep = qr/\Q$sep/ if defined $sep; my $committed; local $self->{committer} = sub { $committed++ }; my @ret; while( !$self->at_eos ) { $committed = 0; my $pos = pos $self->{str}; eval { push @ret, $self->$code; 1 } and next; my $e = $@; pos($self->{str}) = $pos; die $e if $committed or not _isa_failure( $e ); last; } continue { if( defined $sep ) { $self->skip_ws; $self->{str} =~ m/\G$sep/gc or last; } } return \@ret; } =head2 sequence_of $ret = $parser->sequence_of( $code ) A shortcut for calling C with an empty string as separator; expects to find at least one instance of something parsed by C<$code>, separated only by skipped whitespace. This may be considered to be similar to the C<+> or C<*> regexp qualifiers. sub parse_statements { my $self = shift; $self->sequence_of( sub { $self->parse_statement } ); } The interaction of failures in the code and the C method is identical to that of C. =cut sub sequence_of { my $self = shift; my ( $code ) = @_; $self->list_of( undef, $code ); } =head2 any_of $ret = $parser->any_of( @codes ) I Expects that one of the given code instances can parse something from the input, returning what it returned. Each code instance may indicate a failure to parse by calling the C method or otherwise propagating a failure. Each code instance may either be a CODE reference or a method name given as a string. This may be considered to be similar to the C<|> regexp operator for forming alternations of possible parse trees. sub parse_statement { my $self = shift; $self->any_of( sub { $self->parse_declaration; $self->expect(";") }, sub { $self->parse_expression; $self->expect(";") }, sub { $self->parse_block }, ); } If the code for a given choice fails (either by invoking C itself, or by propagating a failure from another method it invoked) before it has invoked C itself, then the parsing position restored and the next choice will be attempted. If it calls C then any subsequent failure for that choice will cause the entire C to fail, propagating that to the caller and no further choices will be attmepted. =cut sub any_of { my $self = shift; while( @_ ) { my $code = shift; my $pos = pos $self->{str}; my $committed = 0; local $self->{committer} = sub { $committed++ }; my $ret; eval { $ret = $self->$code; 1 } and return $ret; my $e = $@; pos( $self->{str} ) = $pos; die $e if $committed or not _isa_failure( $e ); } $self->fail( "Found nothing parseable" ); } sub one_of { croak "Parser::MGC->one_of is deprecated; use ->any_of instead"; } =head2 commit $parser->commit Calling this method will cancel the backtracking behaviour of the innermost C, C, C, or C structure forming method. That is, if later code then calls C, the exception will be propagated out of C, no further list items will be attempted by C or C, and no further code blocks will be attempted by C. Typically this will be called once the grammatical structure alter has been determined, ensuring that any further failures are raised as real exceptions, rather than by attempting other alternatives. sub parse_statement { my $self = shift; $self->any_of( ... sub { $self->scope_of( "{", sub { $self->commit; $self->parse_statements; }, "}" ), }, ); } Though in this common pattern, L may be used instead. =cut sub commit { my $self = shift; if( $self->{committer} ) { $self->{committer}->(); } else { croak "Cannot commit except within a backtrack-able structure"; } } =head1 TOKEN PARSING METHODS The following methods attempt to consume some part of the input string, to be used as part of the parsing process. =cut sub skip_ws { my $self = shift; my $ws = $self->{patterns}{ws}; my $c = $self->{patterns}{comment}; { 1 while $self->{str} =~ m/\G$ws/gc or ( $c and $self->{str} =~ m/\G$c/gc ); return if pos( $self->{str} ) < length $self->{str}; return unless $self->{reader}; my $more = $self->{reader}->( $self ); if( defined $more ) { my $pos = pos( $self->{str} ); $self->{str} .= $more; pos( $self->{str} ) = $pos; redo; } undef $self->{reader}; return; } } =head2 expect $str = $parser->expect( $literal ) $str = $parser->expect( qr/pattern/ ) @groups = $parser->expect( qr/pattern/ ) Expects to find a literal string or regexp pattern match, and consumes it. In scalar context, this method returns the string that was captured. In list context it returns the matching substring and the contents of any subgroups contained in the pattern. This method will raise a parse error (by calling C) if the regexp fails to match. Note that if the pattern could match an empty string (such as for example C), the pattern will always match, even if it has to match an empty string. This method will not consider a failure if the regexp matches with zero-width. =head2 maybe_expect $str = $parser->maybe_expect( ... ) @groups = $parser->maybe_expect( ... ) I A convenient shortcut equivalent to calling C within C, but implemented more efficiently, avoiding the exception-handling set up by C. Returns C or an empty list if the match fails. =cut sub maybe_expect { my $self = shift; my ( $expect ) = @_; ref $expect or $expect = qr/\Q$expect/; $self->skip_ws; $self->{str} =~ m/\G$expect/gc or return; return substr( $self->{str}, $-[0], $+[0]-$-[0] ) if !wantarray; return map { defined $-[$_] ? substr( $self->{str}, $-[$_], $+[$_]-$-[$_] ) : undef } 0 .. $#+; } sub expect { my $self = shift; my ( $expect ) = @_; ref $expect or $expect = qr/\Q$expect/; if( wantarray ) { my @ret = $self->maybe_expect( $expect ) or $self->fail( "Expected $expect" ); return @ret; } else { defined( my $ret = $self->maybe_expect( $expect ) ) or $self->fail( "Expected $expect" ); return $ret; } } =head2 substring_before $str = $parser->substring_before( $literal ) $str = $parser->substring_before( qr/pattern/ ) I Expects to possibly find a literal string or regexp pattern match. If it finds such, consume all the input text before but excluding this match, and return it. If it fails to find a match before the end of the current scope, consumes all the input text until the end of scope and return it. This method does not consume the part of input that matches, only the text before it. It is not considered a failure if the substring before this match is empty. If a non-empty match is required, use the C method: sub token_nonempty_part { my $self = shift; my $str = $parser->substring_before( "," ); length $str or $self->fail( "Expected a string fragment before ," ); return $str; } Note that unlike most of the other token parsing methods, this method does not consume either leading or trailing whitespace around the substring. It is expected that this method would be used as part a parser to read quoted strings, or similar cases where whitespace should be preserved. =cut sub substring_before { my $self = shift; my ( $expect ) = @_; ref $expect or $expect = qr/\Q$expect/; my $endre = ( defined $self->{endofscope} ) ? qr/$expect|$self->{endofscope}/ : $expect; # NO skip_ws my $start = pos $self->{str}; my $end; if( $self->{str} =~ m/\G(?s:.*?)($endre)/ ) { $end = $-[1]; } else { $end = length $self->{str}; } return $self->take( $end - $start ); } =head2 generic_token $val = $parser->generic_token( $name, $re, $convert ) I Expects to find a token matching the precompiled regexp C<$re>. If provided, the C<$convert> CODE reference can be used to convert the string into a more convenient form. C<$name> is used in the failure message if the pattern fails to match. If provided, the C<$convert> function will be passed the parser and the matching substring; the value it returns is returned from C. $convert->( $parser, $substr ) If not provided, the substring will be returned as it stands. This method is mostly provided for subclasses to define their own token types. For example: sub token_hex { my $self = shift; $self->generic_token( hex => qr/[0-9A-F]{2}h/, sub { hex $_[1] } ); } =cut sub generic_token { my $self = shift; my ( $name, $re, $convert ) = @_; $self->fail( "Expected $name" ) if $self->at_eos; $self->skip_ws; $self->{str} =~ m/\G$re/gc or $self->fail( "Expected $name" ); my $match = substr( $self->{str}, $-[0], $+[0] - $-[0] ); return $convert ? $convert->( $self, $match ) : $match; } sub _token_generic { my $self = shift; my %args = @_; my $name = $args{name}; my $re = $args{pattern} ? $self->{patterns}{ $args{pattern} } : $args{re}; my $convert = $args{convert}; $self->generic_token( $name, $re, $convert ); } =head2 token_int $int = $parser->token_int Expects to find an integer in decimal, octal or hexadecimal notation, and consumes it. Negative integers, preceeded by C<->, are also recognised. =cut sub token_int { my $self = shift; $self->_token_generic( name => "int", pattern => "int", convert => sub { my $int = $_[1]; my $sign = ( $int =~ s/^-// ) ? -1 : 1; $int =~ s/^0o/0/; return $sign * oct $int if $int =~ m/^0/; return $sign * $int; }, ); } =head2 token_float $float = $parser->token_float I Expects to find a number expressed in floating-point notation; a sequence of digits possibly prefixed by C<->, possibly containing a decimal point, possibly followed by an exponent specified by C followed by an integer. The numerical value is then returned. =cut sub token_float { my $self = shift; $self->_token_generic( name => "float", pattern => "float", convert => sub { $_[1] + 0 }, ); } =head2 token_number $number = $parser->token_number I Expects to find a number expressed in either of the above forms. =cut sub token_number { my $self = shift; $self->any_of( \&token_float, \&token_int ); } =head2 token_string $str = $parser->token_string Expects to find a quoted string, and consumes it. The string should be quoted using C<"> or C<'> quote marks. The content of the quoted string can contain character escapes similar to those accepted by C or Perl. Specifically, the following forms are recognised: \a Bell ("alert") \b Backspace \e Escape \f Form feed \n Newline \r Return \t Horizontal Tab \0, \012 Octal character \x34, \x{5678} Hexadecimal character C's C<\v> for vertical tab is not supported as it is rarely used in practice and it collides with Perl's C<\v> regexp escape. Perl's C<\c> for forming other control characters is also not supported. =cut my %escapes = ( a => "\a", b => "\b", e => "\e", f => "\f", n => "\n", r => "\r", t => "\t", ); sub token_string { my $self = shift; $self->fail( "Expected string" ) if $self->at_eos; my $pos = pos $self->{str}; $self->skip_ws; $self->{str} =~ m/\G($self->{patterns}{string_delim})/gc or $self->fail( "Expected string delimiter" ); my $delim = $1; $self->{str} =~ m/ \G( (?: \\[0-7]{1,3} # octal escape |\\x[0-9A-F]{2} # 2-digit hex escape |\\x\{[0-9A-F]+\} # {}-delimited hex escape |\\. # symbolic escape |[^\\$delim]+ # plain chunk )*? )$delim/gcix or pos($self->{str}) = $pos, $self->fail( "Expected contents of string" ); my $string = $1; $string =~ s<\\(?:([0-7]{1,3})|x([0-9A-F]{2})|x\{([0-9A-F]+)\}|(.))> [defined $1 ? chr oct $1 : defined $2 ? chr hex $2 : defined $3 ? chr hex $3 : exists $escapes{$4} ? $escapes{$4} : $4]egi; return $string; } =head2 token_ident $ident = $parser->token_ident Expects to find an identifier, and consumes it. =cut sub token_ident { my $self = shift; $self->_token_generic( name => "ident", pattern => "ident", ); } =head2 token_kw $keyword = $parser->token_kw( @keywords ) Expects to find a keyword, and consumes it. A keyword is defined as an identifier which is exactly one of the literal values passed in. =cut sub token_kw { my $self = shift; my @acceptable = @_; $self->skip_ws; my $pos = pos $self->{str}; defined( my $kw = $self->token_ident ) or return undef; grep { $_ eq $kw } @acceptable or pos($self->{str}) = $pos, $self->fail( "Expected any of ".join( ", ", @acceptable ) ); return $kw; } package # hide from indexer Parser::MGC::Failure; sub new { my $class = shift; my $self = bless {}, $class; @{$self}{qw( message parser pos )} = @_; return $self; } use overload '""' => "STRING"; sub STRING { my $self = shift; my $parser = $self->{parser}; my ( $linenum, $col, $text ) = $parser->where( $self->{pos} ); # Column number only counts characters. There may be tabs in there. # Rather than trying to calculate the visual column number, just print the # indentation as it stands. my $indent = substr( $text, 0, $col ); $indent =~ s/[^ \t]/ /g; # blank out all the non-whitespace my $filename = $parser->{filename}; my $in_file = ( defined $filename and !ref $filename ) ? "in $filename " : ""; return "$self->{message} ${in_file}on line $linenum at:\n" . "$text\n" . "$indent^\n"; } # Provide fallback operators for cmp, eq, etc... use overload fallback => 1; =head1 EXAMPLES =head2 Accumulating Results Using Variables Although the structure-forming methods all return a value, obtained from their nested parsing code, it can sometimes be more convenient to use a variable to accumulate a result in instead. For example, consider the following parser method, designed to parse a set of C assignments, such as might be found in a configuration file, or YAML/JSON-style mapping value. sub parse_dict { my $self = shift; my %ret; $self->list_of( ",", sub { my $key = $self->token_ident; exists $ret{$key} and $self->fail( "Already have a mapping for '$key'" ); $self->expect( ":" ); $ret{$key} = $self->parse_value; } ); return \%ret } Instead of using the return value from C, this method accumulates values in the C<%ret> hash, eventually returning a reference to it as its result. Because of this, it can perform some error checking while it parses; namely, rejecting duplicate keys. =head1 TODO =over 4 =item * Make unescaping of string constants more customisable. Possibly consider instead a C using a loop over C. =item * Easy ability for subclasses to define more token types as methods. Perhaps provide a class method such as __PACKAGE__->has_token( hex => qr/[0-9A-F]+/i, sub { hex $_[1] } ); =item * Investigate how well C can cope with buffer splitting across other tokens than simply skippable whitespace =back =head1 AUTHOR Paul Evans =cut 0x55AA; Parser-MGC-0.16/lib/Parser/MGC000755001750001750 013035213443 14427 5ustar00leoleo000000000000Parser-MGC-0.16/lib/Parser/MGC/Tutorial.pod000444001750001750 2222113035213443 17112 0ustar00leoleo000000000000=head1 NAME Parser::MGC::Tutorial =head1 INTRODUCTION L is an abstract base class that provides useful features to assist writing a parser. A parser written using this module will be a subclass of C, which provides a C method. For example, the following trivial parser accepts only input content matching the given regexp. package ExampleParser; use base qw( Parser::MGC ); sub parse { my $self = shift; $self->expect( qr/hello world/i ); return 1; } A program using this parser constructs an instance of it, and uses this instance to parse content. Content is passed either as string value to the C method, or from a named file or filehandle to the C method. use feature qw( say ); use ExampleParser; my $parser = ExampleParser->new; say $parser->from_string( "Hello World" ); When run, this program outputs the return value of the C method, which itself is the value returned by the C method. $ perl tut01.pl 1 Content can also be provided by C instead: use feature qw( say ); use ExampleParser; my $parser = ExampleParser->new; say $parser->from_file( \*STDIN ); =head2 Returning Values Of course, a parser that simply returns 1 to say it matches may not be all that useful. Almost always when a parser is being used to match some input, it is because some values or structure are needed from this input, which should be returned to the caller. The C method attempts to match the next part of the input string with the given regexp, and returns the matching substring. A subsequent C call will continue parsing where the previous one finished. C will automatically skip over whitespace between these calls, so most grammars that are whitespace-insensitive should not need to worry about this explicitly. By using two C calls, a parser can first examine that some given literal is present, and then return a matched substring from the input. sub parse { my $self = shift; $self->expect( qr/hello/i ); my $name = $self->expect( qr/\w+/ ); return $name; } Z<> say $parser->from_string( "Hello World" ); Z<> $ perl tut02.pl World Token methods make this easier by providing convenient shortcuts to commonly-used matching patterns. sub parse { my $self = shift; $self->expect( qr/hello/i ); return $self->token_ident; } If instead we pass in a value that does not match the regexp, an exception is thrown, including details of how the parse failed. say $parser->from_string( "Hello, world!" ); Z<> $ perl tut03.pl Expected (?i-xsm:hello world) on line 1 at: Hello, world! ^ A typical use of a parser is to form an Abstract Syntax Tree (AST) from a given input. In this case it is likely that the return value from the parse method will be some object the application can use to inspect the syntax. sub parse { my $self = shift; my $num = $self->token_number; return MyGrammar::Expression::Number->new( $num ); } =head2 Indicating Failure While the basic methods such as C and the varions token methods will indicate a failure automatically, there may be cases in the grammar that more logic is required by the parser. If this logic wishes to indicate a failure in the input and cause back-tracking to occur, it can use the C method. sub parse { my $self = shift; my $num = $self->token_number; $num >= 0 or $self->fail( "Expected a non-negative number" ); return $num; } =head1 STRUCTURE So far we've managed to parse simple patterns that could have been specified with a simple regular expression. Any parser for a nontrivial grammar will need other abilities as well; it will need to be able to choose from a list of alternatives, to be able to repeat patterns, and to form nested scopes to match other content within. C provides a set of methods that take one or more C references that perform some parsing step, and form a higher-level construction out of them. These can be used to build more complex parsers out of simple ones. It is this recursive structure that gives C its main power over simple one-shot regexp matching. Any nontrivial grammar is likely to be formed from multiple named rules. It is natural therefore to split the parser for such a grammar into methods whose names reflect the structure of the grammar to be parsed. Each of the structure-forming methods which takes C references invokes each by passing in the parser object itself as the first argument. This makes it simple to invoke sub-rules by passing references to method subs themselves, because the parser object will already be passed as the invocant. The following examples will build together into a parser for a simple C-like expression language. =head2 Optional Rules The simplest of the structure-forming methods, C, attempts to run the parser step it is given and if it succeeds, returns the value returned by that step. If it fails by throwing an exception, then the C call simply returns C and resets the current parse position back to where it was before it started. This allows writing a grammar that includes an optional element, similar to the C quantifier in a regular expression. sub parse_type { my $self = shift; my $storage = $self->maybe( sub { $self->token_kw(qw( static auto typedef )); } ); return MyGrammar::Type->new( $self->parse_ident, $storage ); } =head2 Repeated Rules The next structure-forming method, C, attempts to run the parser step it is given multiple times until it fails, and returns an C reference collecting up all the return values from each iteration that succeeded. By itself, C can never fail; if the body never matches then it just yields an empty array and consumes nothing from the input. This allows writing a grammar that includes a repeating element, similar to the C<*> quantifier in a regular expression. sub parse_statements { my $self = shift; my $statements = $self->sequence_of( sub { $self->parse_statement; } ); return MyGrammar::Statements->new( $statements ); } Often it is the case that the grammar requires at least one item to be present, and should not accept an empty parse of zero elements. This can be achieved in code by testing the size of the returned array, and using the C method. This could be considered similar to the C<+> quantifier in a regular expression. sub parse_statements { my $self = shift; my $statements = $self->sequence_of( sub { $self->parse_statement; } ); @$statements > 0 or $self->fail( "Expected at least one statement" ); return MyGrammar::Statements->new( $statements ); } Another case that often happens it that the grammar requires some simple separation pattern between each parsed item, such as a comma. The C method helps here because it automatically handles those separating patterns between the items, returning a reference to an array containing only the actual parsed items without the separators. sub parse_expression_list { my $self = shift; my $exprs = $self->list_of( ",", sub { $self->parse_expression; } ); return MyGrammar::ExpressionList->new( $exprs ); } =head2 Alternate Rules To handle a choice of multiple different alternatives in the grammar, the C method takes an ordered list of parser steps, and attempts to invoke each in turn. It yields as its result the result of the first one of these that didn't fail. This allows writing a grammar that allows a choice of multiple different rules at some point, similar to the C<|> alternation in a regular expression. sub parse_statement { my $self = shift; $self->any_of( sub { $self->parse_declaration }, sub { $self->parse_expression; $self->expect( ';' ); }, sub { $self->parse_block_statement }, ); } =head2 Scoping Rules The final structure-forming method has no direct analogy to a regular expression, though usually similar structures can be found. To handle the case where some nested structure has to be handled between opening and closing markers, the C method can be used. It takes three arguments, being the opening marker, a parser step to handle the contents of the body, and the closing marker. It expects to find each of these in sequence, and returns the value that the inner parsing step returned. However, what makes it more intersting is that during execution of the inner parsing step, the basic token functions all take into account the closing marker. No token function will return a result if the stream now looks like the scope closing marker. Instead, they'll all fail claiming to be at the end of the scope. This makes it much simpler to parse, for example, lists of values surrounded by braces. sub parse_array_initialiser { my $self = shift; $self->scope_of( "{", sub { $self->parse_expression_list }, "}" ); } During execution of the inner call to C, any occurance in the stream of the C<}> marker will appear to be the end of the stream, causing the inner call to stop at hopefully the right place (barring other syntax errors), and terminating correctly. Parser-MGC-0.16/lib/Parser/MGC/Examples000755001750001750 013035213443 16205 5ustar00leoleo000000000000Parser-MGC-0.16/lib/Parser/MGC/Examples/EvaluateExpression.pm000444001750001750 3307313035213443 22554 0ustar00leoleo000000000000package Parser::MGC::Examples::EvaluateExpression; =head1 NAME C - an example parser to evaluate simple numerical expressions =head1 DESCRIPTION This evaluator-parser takes simple mathematical expressions involving the four basic arithmetic operators (+, -, *, /) applied to integers, and returns the numerical result. It handles operator precedence, with * and / having a higher level than + and -, and copes with parentheses. Operator precedence is implemented by using two different parsing functions to handle the two different precedence levels. =cut =head2 Boilerplate We start off by declaring a package and subclassing L. package ExprParser; use base qw( Parser::MGC ); use strict; use warnings; =head2 parse The topmost parsing function, C, handles the outermost level of operator precedence, the + and - operators. It first parses a single term from the input by callling C to obtain its value. It then uses the C structure-forming method to look for either a + or - operator which would indicate another term will follow it. If it finds either of these, it parses the next term from after the operator by another call to C and then adds or subtracts the value of it from the running total. The C call itself is used as the conditional expression of a C loop, to ensure it gets called multiple times. Whenever another term has been parsed, the body function returns a true value, to indicate that the while loop should be invoked again. Only when there are no more + or - operators, indicating no more terms, does the body return false, causing the while loop to stop. This continues until there are no more + or - operators, when the overall total value is returned to the caller. =cut =pod sub parse { my $self = shift; my $val = $self->parse_term 1 while $self->any_of( sub { $self->expect( "+" ); $val += $self->parse_term; 1 }, sub { $self->expect( "-" ); $val -= $self->parse_term; 1 }, sub { 0 }, ); return $val; } =cut =pod This function recognises input matching the following EBNF grammar: EXPR = TERM { ( '+' | '-' ) TERM }; =cut =head2 parse_term Called by C, the next function is C which has a similar structure. This function implements the next level of operator precedence, of the * and / operators. In a similar fashion to the previous function, this one parses a single factor from the input by calling C, and then looks for * or / operators, multiplying or dividing the value by the next factor it expects to find after those. This continues until there are no more * or / operators, when the overall product is returned. =cut =pod sub parse_term { my $self = shift; my $val = $self->parse_factor; 1 while $self->any_of( sub { $self->expect( "*" ); $val *= $self->parse_factor; 1 }, sub { $self->expect( "/" ); $val /= $self->parse_factor; 1 }, sub { 0 }, ); return $val; } =cut =pod This function recognises input matching the following EBNF grammar: TERM = FACTOR { ( '*' | '/' ) FACTOR }; =cut =head2 parse_factor Finally, the innermost C function is called by C to parse out the actual numerical values. This is also the point at which the grammar can recurse, recognising a parenthesized expression. It uses an C with two alternative function bodies, to cover these two cases. The first case, to handle a parenthesized sub-expression, consists of a call to C. This call would expect to find a C<(> symbol to indicate the parenthesized expression. If it finds one, it will recurse back to the toplevel C method to obtain its value, then expects the final C<)> symbol. The value of this factor is then the value of the sub-expression contained within the parentheses. If the first case fails, because it does not find that leading C<(> symbol, the second case is attempted instead. This handles an actual integer constant. This case is simply a call to the C method of the underlying class, which recognises various string forms of integer constants, returning their numerical value. =cut =pod sub parse_factor { my $self = shift; $self->any_of( sub { $self->scope_of( "(", sub { $self->parse }, ")" ) }, sub { $self->token_int }, ); } =cut =pod This function recognises input matching the following EBNF grammar: FACTOR = '(' EXPR ')' | integer =cut =head1 EXAMPLES OF OPERATION =head2 A single integer The simplest form of operation of this parser is when it is given a single integer value as its input; for example C<"15">. INPUT: 15 POSITION: ^ The outermost call to C will call C, which in turn calls C. INPUT: 15 POSITION ^ CALLS: parse => parse_term => parse_factor The C inside C will first attempt to find a parenthesized sub-expression by using C, but this will fail because it does not start with an open parenthesis symbol. The C will then attempt the second case, calling C which will succeed at obtaining an integer value from the input stream, consuming it by advancing the stream position. The value of 15 is then returned by C back to C where it is stored in the C<$val> lexical. INPUT: 15 POSITION: ^ CALLS: parse => parse_term -- $val = 15 At this point, the C inside C will attempt to find a * or / operator, but both will fail because there is none, causing the final alternative function to be invoked, which stops the C loop executing. The value of 15 is then returned to the outer caller, C. A similar process happens there, where it fails to find a + or - operator, and thus the final value of 15 is returned as the result of the entire parsing operation. INPUT: 15 OUTPUT: 15 =head2 A simple sum of two integers Next lets consider a case that actually requires some real parsing, such as an expression requesting the sum of two values; C<"6 + 9">. INPUT: 6 + 9 POSITION: ^ This parsing operation starts the same as the previous; with C calling C which in turn calls C. INPUT: 6 + 9 POSITION: ^ CALLS: parse => parse_term => parse_factor As before, the C inside C first attempts and fails to find a parenthesized sub-expression and so tries C instead. As before this obtains an integer value from the stream and advances the position. This value is again returned to C. As before, the C attempts but fails to find a * or / operator so the value gets returned to C to be stored in C<$val>. INPUT: 6 + 9 POSITION: ^ CALLS: parse -- $val = 6 This time, the C in the outer C method attempts to find a + operator and succeeds, because there is one at the next position in the stream. This causes the first case to continue, making another call to C. INPUT: 6 + 9 POSITION: ^ CALLS: parse -- $val = 6 => parse_term This call to C proceeds much like the first, eventually returning the value 9 by consuming it from the input stream. This value is added to C<$val> by the code inside the C call. INPUT: 6 + 9 POSITION: ^ CALLS: parse -- $val = 15 C then calls C a second time, which attempts to find another operator. This time there is none, so it returns false, which stops the C loop and the value is returned as the final result of the operation. INPUT: 6 + 9 OUTPUT: 15 =head2 Operator precedence The two kinds of operators (+ and - vs * and /) are split across two different method calls to allow them to implement precedence; to say that some of the operators bind more tightly than others. Those operators that are implemented in more inwardly-nested functions bind tighter than the ones implemented further out. To see this in operation consider an expression that mixes the two kinds of operators, such as C<"15 - 2 * 3"> INPUT: 15 - 2 * 3 POSITION: ^ The parsing operation starts by calling down from C all the way to C which extracts the first integer, 15, from the stream and returns it all the way up to C as before: INPUT: 15 - 2 * 3 POSITION: ^ CALLS: parse -- $val = 15 As before, the C function looks for a * or - operator by its C test, and finds this time the - operator, which then causes it to call C to parse its value: INPUT: 15 - 2 * 3 POSITION: ^ CALLS: parse -- $val = 15 => parse_term Again, C starts by calling C which extracts the next integer from the stream and returns it. C temporarily stores that in its own C<$val> lexical (which remember, is a lexical variable local to that call, so is distinct from the one in C). INPUT: 15 - 2 * 3 POSITION: ^ CALLS: parse -- $val = 15 => parse_term -- $val = 2 This time, when C attempts its own C test to look for a * or / operator, it manages to find one. By a process similar to the way that the outer C method forms a sum of terms, C forms a product of factors by calling down to C and accumulating the result. Here it will call C again, which returns the value 3. This gets multiplied into C<$var>. INPUT: 15 - 2 * 3 POSITION: ^ CALLS: parse -- $val = 15 => parse_term -- $val = 6 C will try again to look for a * or / operator, but this time fails to find one, and so returns its final result, 6, back to C, which then subtracts it from its own C<$val>. INPUT: 15 - 2 * 3 POSITION: ^ CALLS: parse -- $val = 9 The outer C call similarly fails to find any more + or - operators and so returns the final result of the parsing operation. INPUT: 15 - 2 * 3 OUTPUT: 9 By implementing the * and / operators separately in a different piece of logic inside the one that implements the + and - operators, we have ensured that they operate more greedily. That is, that they bind tighter, consuming their values first, before the outer + and - operators. This is the way that operator precedence is implemented. =head2 Parentheses This grammar, like many others, provides a way for expressions to override the usual operator precedence by supplying a sub-expression in parentheses. The expression inside those parentheses is parsed in the usual way, and then its result stands in place of the entire parenthesized part, overriding whatever rules might have governed the order between those operators inside it and those outside. In this parser we implement this as a recursive call, where one possibility of the innermost part (the C function or the C EBNF rule) is to recurse back to the outermost thing, inside parentheses. This example examines what happens to the input string C<"(15 - 2) * 3">. INPUT: (15 - 2) * 3 POSITION: ^ As with all the other examples the parsing operation starts by C calling C which calls C. This time, the first case within the C in C does successfully manage to find an open parenthesis, so consumes it. It then stores the close parenthesis pattern as the end-of-scope marker, and makes a recursive call back to the parse method again. INPUT: (15 - 2) * 3 POSITION: ^ CALLS: parse => parse_term => parse_factor => parse EOS = ")" The operation of the inner call to C proceeds much like the first few examples, calling down through C to C to obtain the 15. INPUT: (15 - 2) * 3 POSITION: ^ CALLS: parse => parse_term => parse_factor => parse -- $val = 15 EOS = ")" Similar to previous examples, this then finds the - operator, and parses another term to subtract from it. INPUT: (15 - 2) * 3 POSITION: ^ CALLS: parse => parse_term => parse_factor => parse -- $val = 13 EOS = ")" At this point, the C test in the inner call to C tries again to look for a + or - operator, and this time fails because it believes it is at the end of the input. It isn't really at the end of the string, of course, but it believes it to be at the end because of the "end-of-scope" pattern that the call to C established. This pretends that the input has finished whenever the next part of the input matches the end-of-scope pattern. Because this inner call to C now believes it has got to the end of its input, it returns its final answer back to the caller, which in this case was the C call that C made. As the C call returns, it consumes the input matching the end-of-scope pattern. This return value is then stored by C. INPUT: (15 - 2) * 3 POSITION: ^ CALLS: parse => parse_term -- $val = 13 At this point, C proceeds as before, finding and extracting the * operator and calling C a second time, multiplying them together and returning that to the outer C call. INPUT: (15 - 2) * 3 POSITION: ^ CALLS: parse -- $val = 39 At this point C fails to extract any more operators because it is at the (real) end of input, so returns the final answer. INPUT: (15 - 2) * 3 OUTPUT: 39 Parser-MGC-0.16/t000755001750001750 013035213443 12262 5ustar00leoleo000000000000Parser-MGC-0.16/t/00use.t000444001750001750 14513035213443 13520 0ustar00leoleo000000000000#!/usr/bin/perl use strict; use warnings; use Test::More; use_ok( "Parser::MGC" ); done_testing; Parser-MGC-0.16/t/01base.t000444001750001750 117113035213443 13657 0ustar00leoleo000000000000#!/usr/bin/perl use strict; use warnings; use Test::More; package TestParser; use base qw( Parser::MGC ); sub parse { my $self = shift; # Some slight cheating here pos( $self->{str} ) = length( $self->{str} ); return [ split ' ', $self->{str} ]; } package main; my $parser = TestParser->new; isa_ok( $parser, "TestParser", '$parser' ); isa_ok( $parser, "Parser::MGC", '$parser' ); my $tokens = $parser->from_string( "1 2 3" ); is_deeply( $tokens, [ 1, 2, 3 ], '->from_string' ); $tokens = $parser->from_file( \*DATA ); is_deeply( $tokens, [ 4, 5, 6 ], '->from_file(\*DATA)' ); done_testing; __DATA__ 4 5 6 Parser-MGC-0.16/t/02expect.t000444001750001750 370413035213443 14242 0ustar00leoleo000000000000#!/usr/bin/perl use strict; use warnings; use Test::More; package TestParser; use base qw( Parser::MGC ); sub parse_hello { my $self = shift; [ $self->expect( "hello" ), $self->expect( qr/world/ ) ]; } sub parse_hex { my $self = shift; return hex +( $self->expect( qr/0x([0-9A-F]+)/i ) )[1]; } sub parse_foo_or_bar { my $self = shift; return $self->maybe_expect( qr/foo/i ) || $self->maybe_expect( qr/bar/i ); } sub parse_numrange { my $self = shift; return [ ( $self->maybe_expect( qr/(\d+)(?:-(\d+))?/ ) )[1,2] ]; } package main; my $parser = TestParser->new( toplevel => "parse_hello" ); is_deeply( $parser->from_string( "hello world" ), [ "hello", "world" ], '"hello world"' ); is_deeply( $parser->from_string( " hello world " ), [ "hello", "world" ], '" hello world "' ); # Perl 5.13.6 changed the regexp form # Accept both old and new-style stringification my $modifiers = (qr/foobar/ =~ /\Q(?^/) ? '^' : '-xism'; ok( !eval { $parser->from_string( "goodbye world" ) }, '"goodbye world" fails' ); is( $@, qq[Expected (?$modifiers:hello) on line 1 at:\n] . qq[goodbye world\n] . qq[^\n], 'Exception from "goodbye world" failure' ); $parser = TestParser->new( toplevel => "parse_hex" ); is( $parser->from_string( "0x123" ), 0x123, "Hex parser captures substring" ); $parser = TestParser->new( toplevel => "parse_foo_or_bar" ); is( $parser->from_string( "Foo" ), "Foo", "FooBar parser first case" ); is( $parser->from_string( "Bar" ), "Bar", "FooBar parser first case" ); $parser = TestParser->new( toplevel => "parse_numrange" ); is_deeply( $parser->from_string( "123-456" ), [ 123, 456 ], "Number range parser complete" ); { my $warnings = ""; local $SIG{__WARN__} = sub { $warnings .= join "", @_ }; is_deeply( $parser->from_string( "789" ), [ 789, undef ], "Number range parser lacking max" ); is( $warnings, "", "Number range lacking max yields no warnings" ); } done_testing; Parser-MGC-0.16/t/03reader.t000444001750001750 101513035213443 14206 0ustar00leoleo000000000000#!/usr/bin/perl use strict; use warnings; use Test::More; package TestParser; use base qw( Parser::MGC ); sub parse { my $self = shift; my @tokens; push @tokens, $self->expect( qr/[a-z]+/ ) while !$self->at_eos; return \@tokens; } package main; my $parser = TestParser->new; my @strings = ( "here is a list ", "of some more ", "tokens" ); is_deeply( $parser->from_reader( sub { return shift @strings } ), [qw( here is a list of some more tokens )], 'tokens from reader' ); done_testing; Parser-MGC-0.16/t/04where.t000444001750001750 215113035213443 14061 0ustar00leoleo000000000000#!/usr/bin/perl use strict; use warnings; use Test::More; my @positions; my @wheres; package TestParser; use base qw( Parser::MGC ); sub parse { my $self = shift; main::is( $self->pos, $positions[0], '->pos before parsing' ); main::is_deeply( [ $self->where ], $wheres[0], '->where before parsing' ); $self->expect( "hello" ); main::is( $self->pos, $positions[1], '->pos during parsing' ); main::is_deeply( [ $self->where ], $wheres[1], '->where during parsing' ); $self->expect( qr/world/ ); main::is( $self->pos, $positions[2], '->pos after parsing' ); main::is_deeply( [ $self->where ], $wheres[2], '->where after parsing' ); return 1; } package main; my $parser = TestParser->new; @positions = ( 0, 5, 11 ); @wheres = ( [ 1, 0, "hello world" ], [ 1, 5, "hello world" ], [ 1, 11, "hello world" ], ); $parser->from_string( "hello world" ); @positions = ( 0, 5, 11 ); @wheres = ( [ 1, 0, "hello" ], [ 1, 5, "hello" ], [ 2, 5, "world" ], ); $parser->from_string( "hello\nworld" ); done_testing; Parser-MGC-0.16/t/05comment.t000444001750001750 124613035213443 14416 0ustar00leoleo000000000000#!/usr/bin/perl use strict; use warnings; use Test::More; package TestParser; use base qw( Parser::MGC ); sub parse { my $self = shift; $self->expect( "hello" ); $self->expect( qr/world/ ); return 1; } package main; my $parser = TestParser->new; ok( $parser->from_string( "hello world" ), '"hello world"' ); ok( $parser->from_string( "hello\nworld" ), '"hello\nworld"' ); ok( !eval { $parser->from_string( "hello\n# Comment\nworld" ) }, '"hello world" with comment fails' ); $parser = TestParser->new( patterns => { comment => qr/#.*\n/ }, ); ok( $parser->from_string( "hello\n# Comment\nworld" ), '"hello world" with comment passes' ); done_testing; Parser-MGC-0.16/t/06take.t000444001750001750 71313035213443 13657 0ustar00leoleo000000000000#!/usr/bin/perl use strict; use warnings; use Test::More; package TestParser; use base qw( Parser::MGC ); sub parse { my $self = shift; # Some gut-wrenching to make the test pass [ $self->take( 5 ), $self->take( 5 ), $self->take( length( $self->{str} ) - pos( $self->{str} ) ) ] } package main; my $parser = TestParser->new; is_deeply( $parser->from_string( "Hello There" ), [ "Hello", " Ther", "e" ], '"Hello There"' ); done_testing; Parser-MGC-0.16/t/07generic_token.t000444001750001750 115513035213443 15571 0ustar00leoleo000000000000#!/usr/bin/perl use strict; use warnings; use Test::More; package TestParser; use base qw( Parser::MGC ); my $re; my $convert; sub parse { my $self = shift; return $self->generic_token( token => $re, $convert ); } package main; my $parser = TestParser->new; $re = qr/[A-Z]+/; is( $parser->from_string( "HELLO" ), "HELLO", 'Simple RE' ); ok( !eval { $parser->from_string( "hello" ) }, 'Simple RE fails' ); $re = qr/[A-Z]+/i; is( $parser->from_string( "Hello" ), "Hello", 'RE with flags' ); $convert = sub { lc $_[1] }; is( $parser->from_string( "Hello" ), "hello", 'Conversion function' ); done_testing; Parser-MGC-0.16/t/08substring.t000444001750001750 70613035213443 14757 0ustar00leoleo000000000000#!/usr/bin/perl use strict; use warnings; use Test::More; package TestParser; use base qw( Parser::MGC ); sub parse { my $self = shift; [ $self->substring_before( "!" ), $self->expect( "!" ) ]; } package main; my $parser = TestParser->new; is_deeply( $parser->from_string( "Hello, world!" ), [ "Hello, world", "!" ], '"Hello, world!"' ); is_deeply( $parser->from_string( "!" ), [ "", "!" ], '"Hello, world!"' ); done_testing; Parser-MGC-0.16/t/10token_int.t000444001750001750 142613035213443 14742 0ustar00leoleo000000000000#!/usr/bin/perl use strict; use warnings; use Test::More; package TestParser; use base qw( Parser::MGC ); sub parse { my $self = shift; return $self->token_int; } package main; my $parser = TestParser->new; is( $parser->from_string( "123" ), 123, 'Decimal integer' ); is( $parser->from_string( "0" ), 0, 'Zero' ); is( $parser->from_string( "0x20" ), 32, 'Hexadecimal integer' ); is( $parser->from_string( "010" ), 8, 'Octal integer' ); ok( !eval { $parser->from_string( "0o20" ) }, '0o prefix fails' ); is( $parser->from_string( "-4" ), -4, 'Negative decimal' ); ok( !eval { $parser->from_string( "hello" ) }, '"hello" fails' ); $parser = TestParser->new( accept_0o_oct => 1 ); is( $parser->from_string( "0o20" ), 16, 'Octal integer with 0o prefix' ); done_testing; Parser-MGC-0.16/t/11token_float.t000444001750001750 257213035213443 15261 0ustar00leoleo000000000000#!/usr/bin/perl use strict; use warnings; use Test::More; package TestParser; use base qw( Parser::MGC ); sub parse { my $self = shift; return $self->token_float; } package main; my $parser = TestParser->new; # We're going to be testing floating point values. sub approx { my ( $got, $exp, $name ) = @_; ok( abs( $got - $exp ) < 1E-12, $name ) or diag( "Expected approximately $exp, got $got" ); } approx( $parser->from_string( "123.0" ), 123, 'Decimal integer' ); approx( $parser->from_string( "0.0" ), 0, 'Zero' ); approx( $parser->from_string( "12." ), 12, 'Trailing DP' ); approx( $parser->from_string( ".34" ), 0.34, 'Leading DP' ); approx( $parser->from_string( "8.9" ), 8.9, 'Infix DP' ); approx( $parser->from_string( "-4.0" ), -4, 'Negative decimal' ); approx( $parser->from_string( "1E0" ), 1, 'Scientific without DP' ); approx( $parser->from_string( "2.0E0" ), 2, 'Scientific with DP' ); approx( $parser->from_string( "3.E0" ), 3, 'Scientific with trailing DP' ); approx( $parser->from_string( ".4E1" ), 4, 'Scientific with leading DP' ); approx( $parser->from_string( "50E-1" ), 5, 'Scientific with negative exponent without DP' ); approx( $parser->from_string( "60.0E-1" ), 6, 'Scientific with DP with negative exponent' ); approx( $parser->from_string( "1e0" ), 1, 'Scientific with lowercase e' ); done_testing; Parser-MGC-0.16/t/12token_number.t000444001750001750 157513035213443 15447 0ustar00leoleo000000000000#!/usr/bin/perl use strict; use warnings; use Test::More; package TestParser; use base qw( Parser::MGC ); sub parse { my $self = shift; return $self->token_number; } package main; my $parser = TestParser->new; # We're going to be testing floating point values. sub approx { my ( $got, $exp, $name ) = @_; ok( abs( $got - $exp ) < 1E-12, $name ) or diag( "Expected approximately $exp, got $got" ); } is( $parser->from_string( "123" ), 123, 'Decimal integer' ); approx( $parser->from_string( "123.0" ), 123, 'Decimal integer' ); approx( $parser->from_string( "0.0" ), 0, 'Zero' ); approx( $parser->from_string( "12." ), 12, 'Trailing DP' ); approx( $parser->from_string( ".34" ), 0.34, 'Leading DP' ); approx( $parser->from_string( "8.9" ), 8.9, 'Infix DP' ); ok( !eval { $parser->from_string( "hello" ) }, '"hello" fails' ); done_testing; Parser-MGC-0.16/t/13token_string.t000444001750001750 411613035213443 15460 0ustar00leoleo000000000000#!/usr/bin/perl use strict; use warnings; use Test::More; package TestParser; use base qw( Parser::MGC ); sub parse { my $self = shift; return $self->token_string; } package StringPairParser; use base qw( Parser::MGC ); sub parse { my $self = shift; return [ $self->token_string, $self->token_string ]; } package main; my $parser = TestParser->new; is( $parser->from_string( q['single'] ), "single", 'Single quoted string' ); is( $parser->from_string( q["double"] ), "double", 'Double quoted string' ); is( $parser->from_string( q["foo 'bar'"] ), "foo 'bar'", 'Double quoted string containing single substr' ); is( $parser->from_string( q['foo "bar"'] ), 'foo "bar"', 'Single quoted string containing double substr' ); is( $parser->from_string( q["tab \t"] ), "tab \t", '\t' ); is( $parser->from_string( q["newline \n"] ), "newline \n", '\n' ); is( $parser->from_string( q["return \r"] ), "return \r", '\r' ); is( $parser->from_string( q["form feed \f"] ), "form feed \f", '\f' ); is( $parser->from_string( q["backspace \b"] ), "backspace \b", '\b' ); is( $parser->from_string( q["bell \a"] ), "bell \a", '\a' ); is( $parser->from_string( q["escape \e"] ), "escape \e", '\e' ); # ord('A') == 65 == 0101 == 0x41 # TODO: This is ASCII dependent. If anyone on EBCDIC cares, do let me know... is( $parser->from_string( q["null \0"] ), "null \0", 'Octal null' ); is( $parser->from_string( q["octal \101BC"] ), "octal ABC", 'Octal' ); is( $parser->from_string( q["hex \x41BC"] ), "hex ABC", 'Hexadecimal' ); is( $parser->from_string( q["unihex \x{263a}"] ), "unihex \x{263a}", 'Unicode hex' ); $parser = TestParser->new( patterns => { string_delim => qr/"/ } ); is( $parser->from_string( q["double"] ), "double", 'Double quoted string still passes' ); ok( !eval { $parser->from_string( q['single'] ) }, 'Single quoted string now fails' ); $parser = StringPairParser->new; is_deeply( $parser->from_string( q["foo" "bar"] ), [ "foo", "bar" ], 'String-matching pattern is non-greedy' ); done_testing; Parser-MGC-0.16/t/14token_ident.t000444001750001750 147313035213443 15261 0ustar00leoleo000000000000#!/usr/bin/perl use strict; use warnings; use Test::More; package TestParser; use base qw( Parser::MGC ); sub parse { my $self = shift; return $self->token_ident; } package main; my $parser = TestParser->new; is( $parser->from_string( "foo" ), "foo", 'Identifier' ); is( $parser->from_string( "x" ), "x", 'Single-letter identifier' ); ok( !eval { $parser->from_string( "123" ) }, '"123" fails' ); is( $@, qq[Expected ident on line 1 at:\n] . qq[123\n] . qq[^\n], 'Exception from "123" failure' ); ok( !eval { $parser->from_string( "some-ident" ) }, '"some-ident" fails on default identifier' ); $parser = TestParser->new( patterns => { ident => qr/[[:alpha:]_][\w-]+/ }, ); is( $parser->from_string( "some-ident" ), "some-ident", '"some-ident" passes with new token pattern' ); done_testing; Parser-MGC-0.16/t/15token_kw.t000444001750001750 76413035213443 14562 0ustar00leoleo000000000000#!/usr/bin/perl use strict; use warnings; use Test::More; package TestParser; use base qw( Parser::MGC ); sub parse { my $self = shift; return $self->token_kw( qw( foo bar ) ); } package main; my $parser = TestParser->new; is( $parser->from_string( "foo" ), "foo", 'Keyword' ); ok( !eval { $parser->from_string( "splot" ) }, '"splot" fails' ); is( $@, qq[Expected any of foo, bar on line 1 at:\n] . qq[splot\n] . qq[^\n], 'Exception from "splot" failure' ); done_testing; Parser-MGC-0.16/t/20maybe.t000444001750001750 146313035213443 14047 0ustar00leoleo000000000000#!/usr/bin/perl use strict; use warnings; use Test::More; my $die; package TestParser; use base qw( Parser::MGC ); sub parse { my $self = shift; $self->maybe( sub { die $die if $die; $self->token_ident; } ) || $self->token_int; } package TestParser2; use base qw( Parser::MGC ); sub parse { my $self = shift; $self->maybe( 'token_ident' ) || $self->token_int; } package main; my $parser = TestParser->new; is( $parser->from_string( "hello" ), "hello", '"hello"' ); is( $parser->from_string( "123" ), 123, '"123"' ); $die = "Now have to fail\n"; ok( !eval { $parser->from_string( "456" ) }, '"456" with $die fails' ); is( $@, "Now have to fail\n", 'Exception from failure' ); is( TestParser2->new->from_string( "hello" ), "hello", '"hello" as method name' ); done_testing; Parser-MGC-0.16/t/21scope_of.t000444001750001750 216013035213443 14543 0ustar00leoleo000000000000#!/usr/bin/perl use strict; use warnings; use Test::More; package TestParser; use base qw( Parser::MGC ); sub parse { my $self = shift; $self->scope_of( "(", sub { return $self->token_int }, ")" ); } package TestParser2; use base qw( Parser::MGC ); sub parse { my $self = shift; $self->scope_of( "(", 'token_int', ")" ); } package DynamicDelimParser; use base qw( Parser::MGC ); sub parse { my $self = shift; my $delim = $self->expect( qr/[\(\[]/ ); $delim =~ tr/([/)]/; $self->scope_of( undef, sub { return $self->token_int }, $delim, ); } package main; my $parser = TestParser->new; is( $parser->from_string( "(123)" ), 123, '"(123)"' ); ok( !eval { $parser->from_string( "(abc)" ) }, '"(abc)"' ); ok( !eval { $parser->from_string( "456" ) }, '"456"' ); is( TestParser2->new->from_string( "(67)" ), 67, '"(67)" as method name' ); $parser = DynamicDelimParser->new; is( $parser->from_string( "(45)" ), 45, '"(45)"' ); is( $parser->from_string( "[45]" ), 45, '"[45]"' ); ok( !eval { $parser->from_string( "(45]" ) }, '"(45]" fails' ); done_testing; Parser-MGC-0.16/t/22list_of.t000444001750001750 143513035213443 14412 0ustar00leoleo000000000000#!/usr/bin/perl use strict; use warnings; use Test::More; package TestParser; use base qw( Parser::MGC ); sub parse { my $self = shift; $self->list_of( ",", sub { return $self->token_int; } ); } package TestParser2; use base qw( Parser::MGC ); sub parse { my $self = shift; $self->list_of( ",", 'token_int' ); } package main; my $parser = TestParser->new; is_deeply( $parser->from_string( "123" ), [ 123 ], '"123"' ); is_deeply( $parser->from_string( "4,5,6" ), [ 4, 5, 6 ], '"4,5,6"' ); is_deeply( $parser->from_string( "7, 8" ), [ 7, 8 ], '"7, 8"' ); # Trailing delimiter is_deeply( $parser->from_string( "10,11,12," ), [ 10, 11, 12 ], '"10,11,12,"' ); is_deeply( TestParser2->new->from_string( "13,14" ), [ 13, 14 ], '"13,14" as method name' ); done_testing; Parser-MGC-0.16/t/23sequence_of.t000444001750001750 205513035213443 15247 0ustar00leoleo000000000000#!/usr/bin/perl use strict; use warnings; use Test::More; package TestParser; use base qw( Parser::MGC ); sub parse { my $self = shift; $self->sequence_of( sub { return $self->token_int; } ); } package IntThenStringParser; use base qw( Parser::MGC ); sub parse { my $self = shift; [ $self->sequence_of( sub { return $self->token_int; } ), $self->sequence_of( sub { return $self->token_string; } ), ]; } package main; my $parser = TestParser->new; is_deeply( $parser->from_string( "123" ), [ 123 ], '"123"' ); is_deeply( $parser->from_string( "4 5 6" ), [ 4, 5, 6 ], '"4 5 6"' ); is_deeply( $parser->from_string( "" ), [], '""' ); $parser = IntThenStringParser->new; is_deeply( $parser->from_string( "10 20 'ab' 'cd'" ), [ [ 10, 20 ], [ 'ab', 'cd' ] ], q("10 20 'ab' 'cd'") ); is_deeply( $parser->from_string( "10 20" ), [ [ 10, 20 ], [] ], q("10 20") ); is_deeply( $parser->from_string( "'ab' 'cd'" ), [ [], [ 'ab', 'cd' ] ], q("'ab' 'cd'") ); done_testing; Parser-MGC-0.16/t/24any_of.t000444001750001750 210313035213443 14221 0ustar00leoleo000000000000#!/usr/bin/perl use strict; use warnings; use Test::More; package TestParser; use base qw( Parser::MGC ); sub parse { my $self = shift; $self->any_of( sub { [ int => $self->token_int ] }, sub { [ str => $self->token_string ] }, sub { [ ident => $self->token_ident ] }, sub { $self->expect( "@" ); die "Here I fail\n" }, ); } package TestParser2; use base qw( Parser::MGC ); sub parse { my $self = shift; $self->any_of( 'parse_int', 'fail' ); } sub parse_int { [ int => shift->token_int ] } package main; my $parser = TestParser->new; is_deeply( $parser->from_string( "123" ), [ int => 123 ], '"123"' ); is_deeply( $parser->from_string( q["hi"] ), [ str => "hi" ], '"hi"' ); is_deeply( $parser->from_string( "foobar" ), [ ident => "foobar" ], '"foobar"' ); ok( !eval { $parser->from_string( "@" ) }, '"@" fails' ); is( $@, "Here I fail\n", 'Exception from "@" failure' ); ok( !eval { $parser->from_string( "+" ) }, '"+" fails' ); is_deeply( TestParser2->new->from_string( "456" ), [ int => 456 ], '"456" as method name' ); done_testing; Parser-MGC-0.16/t/30commit.t000444001750001750 251713035213443 14244 0ustar00leoleo000000000000#!/usr/bin/perl use strict; use warnings; use Test::More; package TestParser; use base qw( Parser::MGC ); sub parse { my $self = shift; $self->any_of( sub { $self->token_int }, sub { $self->scope_of( "(", sub { $self->commit; $self->token_string; }, ")" ); } ); } package IntStringPairsParser; use base qw( Parser::MGC ); sub parse { my $self = shift; $self->sequence_of( sub { my $int = $self->token_int; $self->commit; my $str = $self->token_string; [ $int, $str ]; } ); } package main; my $parser = TestParser->new; is( $parser->from_string( "123" ), 123, '"123"' ); is( $parser->from_string( '("hi")' ), "hi", '("hi")' ); ok( !eval { $parser->from_string( "(456)" ) }, '"(456)" fails' ); is( $@, qq[Expected string delimiter on line 1 at:\n]. qq[(456)\n]. qq[ ^\n], 'Exception from "(456)" failure' ); $parser = IntStringPairsParser->new; is_deeply( $parser->from_string( "1 'one' 2 'two'" ), [ [ 1, "one" ], [ 2, "two" ] ], "1 'one' 2 'two'" ); ok( !eval { $parser->from_string( "1 'one' 2" ) }, "1 'one' 2 fails" ); is( $@, qq[Expected string on line 1 at:\n]. qq[1 'one' 2\n]. qq[ ^\n], 'Exception from 1 \'one\' 2 failure' ); done_testing; Parser-MGC-0.16/t/31scope_level.t000444001750001750 120113035213443 15242 0ustar00leoleo000000000000#!/usr/bin/perl use strict; use warnings; use Test::More; package TestParser; use base qw( Parser::MGC ); sub parse { my $self = shift; $self->sequence_of( sub { $self->any_of( sub { $self->expect( qr/[a-z]+/ ) . "/" . $self->scope_level }, sub { $self->scope_of( "(", \&parse, ")" ) }, ); }, ); } package main; my $parser = TestParser->new; is_deeply( $parser->from_string( "a" ), [ "a/0" ], 'a' ); is_deeply( $parser->from_string( "(b)" ), [ [ "b/1" ] ], '(b)' ); is_deeply( $parser->from_string( "c (d) e" ), [ "c/0", [ "d/1" ], "e/0" ], 'c (d) e' ); done_testing; Parser-MGC-0.16/t/32committed_scope_of.t000444001750001750 112613035213443 16613 0ustar00leoleo000000000000#!/usr/bin/perl use strict; use warnings; use Test::More; my $fallback; package TestParser; use base qw( Parser::MGC ); sub parse { my $self = shift; $self->any_of( sub { $self->committed_scope_of( "(", sub { return $self->token_int }, ")", ); }, sub { $fallback++ }, ); } package main; my $parser = TestParser->new; is( $parser->from_string( "(123)" ), 123, '"(123)"' ); ok( !eval { $parser->from_string( "(abc)" ) }, '"(abc)"' ); ok( !$fallback, '"(abc) does not invoke fallback case' ); done_testing; Parser-MGC-0.16/t/32exception.t000444001750001750 243413035213443 14752 0ustar00leoleo000000000000#!/usr/bin/perl use strict; use warnings; use Test::More; use File::Temp qw( tempfile ); package TestParser; use base qw( Parser::MGC ); sub parse { my $self = shift; return $self->token_int; } package main; my $parser = TestParser->new; isa_ok( $parser, "TestParser", '$parser' ); isa_ok( $parser, "Parser::MGC", '$parser' ); my $value = $parser->from_string( "\t123" ); is( $value, 123, '->from_string' ); ok( !eval { $parser->from_string( "\t123." ) }, 'Trailing input on string fails' ); is( $@, qq[Expected end of input on line 1 at:\n]. qq[\t123.\n]. qq[\t ^\n], 'Exception from trailing input on string' ); ok( !eval { $parser->from_file( \*DATA ) }, 'Trailing input on glob filehandle fails' ); is( $@, qq[Expected end of input on line 1 at:\n]. qq[ 123.\n]. qq[ ^\n], 'Exception from trailing input on glob filehandle' ); my ( $fh, $filename ) = tempfile( "tmpfile.XXXXXX", UNLINK => 1 ); END { defined $filename and unlink $filename } print $fh " 123.\n"; close $fh; ok( !eval { $parser->from_file( $filename ) }, 'Trailing input on named file fails' ); is( $@, qq[Expected end of input in $filename on line 1 at:\n]. qq[ 123.\n]. qq[ ^\n], 'Exception from trailing input on named file' ); done_testing; __DATA__ 123. Parser-MGC-0.16/t/90ex_bencode.t000444001750001750 74513035213443 15036 0ustar00leoleo000000000000#!/usr/bin/perl use strict; use warnings; use Test::More; use lib "."; require "examples/parse-bencode.pl"; my $parser = BencodeParser->new; sub test { my ( $str, $expect, $name ) = @_; is_deeply( $parser->from_string( $str ), $expect, $name ); } test q[i10e], 10, "Integer"; test q[5:hello], "hello", "String"; test q[li1ei2ei3ee], [ 1, 2, 3 ], "List"; test q[d3:onei1e3:twoi2ee], { one => 1, two => 2 }, "Dict"; done_testing; Parser-MGC-0.16/t/90ex_dict.t000444001750001750 103013035213443 14366 0ustar00leoleo000000000000#!/usr/bin/perl use strict; use warnings; use Test::More; use lib "."; require "examples/parse-dict.pl"; my $parser = DictParser->new; sub test { my ( $str, $expect, $name ) = @_; is_deeply( $parser->from_string( $str ), $expect, $name ); } test q[123], 123, "Number"; test q["Hello"], "Hello", "String"; test q[{one: 1, two: 2}], { one => 1, two => 2 }, "Flat dict"; test q[{numbers: {three: 3, four: 4}}], { numbers => { three => 3, four => 4 } }, "Nested dict"; done_testing; Parser-MGC-0.16/t/90ex_expr.t000444001750001750 61713035213443 14413 0ustar00leoleo000000000000#!/usr/bin/perl use strict; use warnings; use Test::More; use lib "."; require "examples/eval-expr.pl"; my $parser = ExprParser->new; while( ) { chomp; my ( $str, $expect ) = split m/=/; is( $parser->from_string( $str ), $expect, $str ); } done_testing; __DATA__ 1+2=3 1 + 2 =3 1+2+3=6 10-4=6 10-2-2=6 3*4=12 3*4*5=60 20/4=5 20/5/2=2 3+4*5=23 4*5+3=23 (3+4)*5=35 4*(5+3)=32 Parser-MGC-0.16/t/90ex_pod.t000444001750001750 131113035213443 14227 0ustar00leoleo000000000000#!/usr/bin/perl use strict; use warnings; use Test::More; use lib "."; require "examples/parse-pod.pl"; my $parser = PodParser->new; sub test { my ( $str, $expect, $name ) = @_; is_deeply( $parser->from_string( $str ), $expect, $name ); } test "Plain text", [ "Plain text" ], "plain"; test "B", [ { B => [ "bold" ] } ], "B<>"; test "Text with I text", [ "Text with ", { I => [ "italic" ] }, " text" ], "I<> surrounded"; test "Nested B>", [ "Nested ", { B => [ { I => [ "tags" ] } ] } ], "Nested"; test "Double C<< Class->method >> tags", [ "Double ", { C => [ " Class->method " ] }, " tags" ], "Double tags"; done_testing; Parser-MGC-0.16/t/90ex_synopsis.t000444001750001750 61213035213443 15317 0ustar00leoleo000000000000#!/usr/bin/perl use strict; use warnings; use Test::More; use lib "."; require "examples/synopsis.pl"; my $parser = LispParser->new; sub test { my ( $str, $expect ) = @_; is_deeply( $parser->from_string( $str ), [ $expect ], qq("$str") ); } test "123", 123; test "'hello'", 'hello'; test "(123 456)", [ 123, 456 ]; test "(+ 1 (* 2 3))", [ \'+', 1, [ \'*', 2, 3 ] ]; done_testing; Parser-MGC-0.16/t/90ex_xml.t000444001750001750 205213035213443 14250 0ustar00leoleo000000000000#!/usr/bin/perl use strict; use warnings; use Test::More tests => 5; use lib "."; require "examples/parse-xml.pl"; my $parser = XmlParser->new; sub plain { bless [ @_ ], "XmlParser::Node::Plain" } sub elem { bless [ @_ ], "XmlParser::Node::Element" } sub test { my ( $str, $expect, $name ) = @_; is_deeply( $parser->from_string( $str ), $expect, $name ); } test q[Hello world], [ plain("Hello world") ], "Plaintext"; test q[Hello world], [ elem(message => {}, plain("Hello world")) ], "Single node"; test q[Helloworld], [ elem(first => {}, plain("Hello")), elem(second => {}, plain("world")) ], "Two nodes"; test q[Hello world], [ elem(first => {}, plain("Hello")), plain(" "), elem(second => {}, plain("world")) ], "Two nodes with whitespace"; test q[], [ elem(node => { a1 => "v1", a2 => "v2" }) ], "Node with attrs"; done_testing; Parser-MGC-0.16/t/99pod.t000444001750001750 25713035213443 13534 0ustar00leoleo000000000000#!/usr/bin/perl use strict; use warnings; use Test::More; eval "use Test::Pod 1.00"; plan skip_all => "Test::Pod 1.00 required for testing POD" if $@; all_pod_files_ok();