This is an automated email from the git hooks/post-receive script. js pushed a commit to tag PEVANS in repository libparser-mgc-perl.
commit 02da7f9e45ba2af967ae1b71575be62763da3bba Author: Paul Evans <leon...@leonerd.org.uk> Date: Sat Dec 11 19:46:20 2010 +0000 Import of PEVANS/Parser-MGC-0.01 from CPAN. gitpan-cpan-distribution: Parser-MGC gitpan-cpan-version: 0.01 gitpan-cpan-path: PEVANS/Parser-MGC-0.01.tar.gz gitpan-cpan-author: PEVANS gitpan-cpan-maturity: released --- Build.PL | 19 ++ Changes | 4 + LICENSE | 377 ++++++++++++++++++++++++++++++++ MANIFEST | 24 +++ META.yml | 21 ++ Makefile.PL | 14 ++ README | 194 +++++++++++++++++ lib/Parser/MGC.pm | 614 +++++++++++++++++++++++++++++++++++++++++++++++++++++ t/00use.t | 3 + t/01base.t | 36 ++++ t/02expect.t | 31 +++ t/03where.t | 47 ++++ t/04comment.t | 32 +++ t/10token_int.t | 26 +++ t/11token_string.t | 32 +++ t/12token_ident.t | 38 ++++ t/13token_kw.t | 28 +++ t/20maybe.t | 32 +++ t/21scope_of.t | 28 +++ t/22list_of.t | 25 +++ t/23sequence_of.t | 24 +++ t/24one_of.t | 33 +++ t/30commit.t | 39 ++++ t/99pod.t | 8 + 24 files changed, 1729 insertions(+) diff --git a/Build.PL b/Build.PL new file mode 100644 index 0000000..f98f30d --- /dev/null +++ b/Build.PL @@ -0,0 +1,19 @@ +use strict; +use warnings; + +use Module::Build; + +my $build = Module::Build->new( + module_name => 'Parser::MGC', + requires => { + }, + build_requires => { + 'Test::More' => 0, + }, + license => 'perl', + create_makefile_pl => 'traditional', + create_license => 1, + create_readme => 1, +); + +$build->create_build_script; diff --git a/Changes b/Changes new file mode 100644 index 0000000..086fef5 --- /dev/null +++ b/Changes @@ -0,0 +1,4 @@ +Revision history for Parser-MGC + +0.01 First version, released on an unsuspecting world. + diff --git a/LICENSE b/LICENSE new file mode 100644 index 0000000..bed175a --- /dev/null +++ b/LICENSE @@ -0,0 +1,377 @@ +This software is copyright (c) 2010 by Paul Evans <leon...@leonerd.org.uk>. + +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) 2010 by Paul Evans <leon...@leonerd.org.uk>. + +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. + 59 Temple Place, Suite 330, Boston, MA 02111-1307, 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. + + <one line to give the program's name and a brief idea of what it does.> + Copyright (C) 19yy <name of author> + + 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., 59 Temple Place, Suite 330, Boston, MA 02111-1307, 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. + + <signature of Ty Coon>, 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) 2010 by Paul Evans <leon...@leonerd.org.uk>. + +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 + diff --git a/MANIFEST b/MANIFEST new file mode 100644 index 0000000..ace5273 --- /dev/null +++ b/MANIFEST @@ -0,0 +1,24 @@ +Build.PL +Changes +lib/Parser/MGC.pm +LICENSE +Makefile.PL +MANIFEST This list of files +META.yml +README +t/00use.t +t/01base.t +t/02expect.t +t/03where.t +t/04comment.t +t/10token_int.t +t/11token_string.t +t/12token_ident.t +t/13token_kw.t +t/20maybe.t +t/21scope_of.t +t/22list_of.t +t/23sequence_of.t +t/24one_of.t +t/30commit.t +t/99pod.t diff --git a/META.yml b/META.yml new file mode 100644 index 0000000..4f0c13c --- /dev/null +++ b/META.yml @@ -0,0 +1,21 @@ +--- +abstract: 'build simple recursive-descent parsers' +author: + - 'Paul Evans <leon...@leonerd.org.uk>' +build_requires: + Test::More: 0 +configure_requires: + Module::Build: 0.36 +generated_by: 'Module::Build version 0.3607' +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: 0.01 +resources: + license: http://dev.perl.org/licenses/ +version: 0.01 diff --git a/Makefile.PL b/Makefile.PL new file mode 100644 index 0000000..1c06b3a --- /dev/null +++ b/Makefile.PL @@ -0,0 +1,14 @@ +# Note: this file was auto-generated by Module::Build::Compat version 0.3607 +use ExtUtils::MakeMaker; +WriteMakefile +( + 'NAME' => 'Parser::MGC', + 'VERSION_FROM' => 'lib/Parser/MGC.pm', + 'PREREQ_PM' => { + 'Test::More' => 0 + }, + 'INSTALLDIRS' => 'site', + 'EXE_FILES' => [], + 'PL_FILES' => {} + ) +; diff --git a/README b/README new file mode 100644 index 0000000..c1ac37f --- /dev/null +++ b/README @@ -0,0 +1,194 @@ +NAME + "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->one_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 atomically + extract a grammatical token from the string. It also provides wrapping + methods that can be used to build up a possibly-recursive grammar + structure. Each method, both token and structural, atomically either + consumes a prefix of the string and returns its result, or fails and + consumes nothing. + +CONSTRUCTOR + $parser = Parser::MGC->new( %args ) + Returns a new instance of a "Parser::MGC" object. This must be called on + a subclass that provides a "parse" method. + + Takes the following named arguments + + 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 + +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. + + * 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 + $result = $parser->from_string( $str ) + Parse the given literal string and return the result from the "parse" + method. + + $result = $parser->from_file( $file ) + Parse the given file, which may be a pathname in a string, or an opened + IO handle, and return the result from the "parse" method. + + ( $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. + + $parser->fail( $message ) + Aborts the current parse attempt with the given message string. The + failure message will include the current line and column position, and + will include the line of input that failed. + + $eos = $parser->at_eos + Returns true if the input string is at the end of the string. + +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. + + $ret = $parser->maybe( $code ) + Attempts to execute the given $code reference in scalar context, passing + in no arguments, and returning what it returned. If the code fails to + parse by calling the "fail" method then none of the input string will be + consumed; the current parsing position will be restored. "undef" will be + returned in this case. + + This may be considered to be similar to the "?" regexp qualifier. + + $ret = $parser->scope_of( $start, $code, $stop ) + Expects to find the $start pattern, then attempts to execute the given + $code reference, then expects to find the $stop pattern. Returns + whatever the code reference returned. + + 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 return + "undef". + + $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. + + 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. + + $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. + + $ret = $parser->one_of( @codes ) + Expects that one of the given code references can parse something from + the input, returning what it returned. Each code reference may indicate + a failure to parse by calling the "fail" method. + + This may be considered to be similar to the "|" regexp operator for + forming alternations of possible parse trees. + + $parser->commit + Calling this method will cancel the backtracking behaviour of the + innermost "maybe" or "one_of" structure forming method. That is, if + later code then calls "fail", the exception will be propagated out of + "maybe", and no further code blocks will be attempted by "one_of". + + Typically this will be called once the grammatical structure of an + alternation has been determined, ensuring that any further failures are + raised as real exceptions, rather than by attempting other alternatives. + + TODO: Code example with commit inside one_of + +TOKEN PARSING METHODS + The following methods attempt to consume some part of the input string, + to be used as part of the parsing process. + + As a convenience for parsing, each of these methods will return undef if + the string is already at the end (if "at_eos" returns true). + + $parser->expect( $string ) + $parser->expect( qr/pattern/ ) + Expects to find a literal string or regexp pattern match, and consumes + it. This method does not return a useful value. + + $int = $parser->token_int + Expects to find an integer in decimal, octal or hexadecimal notation, + and consumes it. + + $str = $parser->token_string + Expects to find a quoted string, and consumes it. The string should be + quoted using """ or "'" quote marks. + + $ident = $parser->token_ident + Expects to find an identifier, and consumes it. + + $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. + +TODO + * Unescaping of string constants; customisable + + * Easy ability for subclasses to define more token types + +AUTHOR + Paul Evans <leon...@leonerd.org.uk> + diff --git a/lib/Parser/MGC.pm b/lib/Parser/MGC.pm new file mode 100644 index 0000000..1bd12d0 --- /dev/null +++ b/lib/Parser/MGC.pm @@ -0,0 +1,614 @@ +# 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 -- leon...@leonerd.org.uk + +package Parser::MGC; + +use strict; +use warnings; + +our $VERSION = '0.01'; + +use Carp; + +use File::Slurp qw( slurp ); + +=head1 NAME + +C<Parser::MGC> - 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->one_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<m//gc> regexps used to implement +the token parsing behaviour. + +It provides a number of token-parsing methods, which each atomically extract a +grammatical token from the string. It also provides wrapping methods that can +be used to build up a possibly-recursive grammar structure. Each method, both +token and structural, atomically either consumes a prefix of the string and +returns its result, or fails and consumes nothing. + +=cut + +=head1 CONSTRUCTOR + +=cut + +=head2 $parser = Parser::MGC->new( %args ) + +Returns a new instance of a C<Parser::MGC> object. This must be called on a +subclass that provides a C<parse> method. + +Takes the following named arguments + +=over 8 + +=item patterns => HASH + +Keys in this hash should map to quoted regexp (C<qr//>) references, to +override the default patterns used to match tokens. See C<PATTERNS> below + +=back + +=cut + +=head1 PATTERNS + +The following pattern names are recognised. They may be passed to the +constructor in the C<patterns> hash, or provided as a class method under the +name C<pattern_I<name>>. + +=over 4 + +=item * ws + +Pattern used to skip whitespace between tokens. Defaults to C</[\s\n\t]+/> + +=item * comment + +Pattern used to skip comments between tokens. Undefined by default. + +=item * ident + +Pattern used to parse an identifier by C<token_ident>. Defaults to +C</[[:alpha:]_]\w*/> + +=item * string_delim + +Pattern used to delimit a string by C<token_string>. Defaults to C</["']/>. + +=back + +=cut + +my @patterns = qw( + ws + comment + ident + string_delim +); + +use constant { + pattern_ws => qr/[\s\n\t]+/, + pattern_comment => undef, + pattern_ident => qr/[[:alpha:]_]\w*/, + pattern_string_delim => qr/["']/, +}; + +sub new +{ + my $class = shift; + my %args = @_; + + $class->can( "parse" ) or + croak "Expected to be a subclass that can ->parse"; + + my $self = bless { + patterns => {}, + }, $class; + + $self->{patterns}{$_} = $args{patterns}{$_} || $self->${\"pattern_$_"} for @patterns; + + return $self; +} + +=head1 METHODS + +=cut + +=head2 $result = $parser->from_string( $str ) + +Parse the given literal string and return the result from the C<parse> method. + +=cut + +sub from_string +{ + my $self = shift; + my ( $str ) = @_; + + $self->{str} = $str; + + pos $self->{str} = 0; + + my $result = $self->parse; + + $self->at_eos or + $self->fail( "Expected end of input" ); + + return $result; +} + +=head2 $result = $parser->from_file( $file ) + +Parse the given file, which may be a pathname in a string, or an opened IO +handle, and return the result from the C<parse> method. + +=cut + +sub from_file +{ + my $self = shift; + my ( $filename ) = @_; + + $self->{filename} = $filename; + + $self->from_string( scalar(slurp $filename) ); +} + +=head2 ( $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 = 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 $parser->fail( $message ) + +Aborts the current parse attempt with the given message string. The failure +message will include the current line and column position, and will include +the line of input that failed. + +=cut + +sub fail +{ + my $self = shift; + my ( $message ) = @_; + + my ( $lineno, $col, $line ) = $self->where; + + die Parser::MGC::Failure->new( $message, $self->where ); +} + +=head2 $eos = $parser->at_eos + +Returns true if the input string is at the end of the string. + +=cut + +sub at_eos +{ + my $self = shift; + + $self->skip_ws; + + my $pos = pos $self->{str}; + + return 1 if defined $pos and $pos >= length $self->{str}; + + return 0 unless defined $self->{endofscope}; + + # No /g so we won't actually alter pos() + my $at_eos = $self->{str} =~ m/\G$self->{endofscope}/; + + return $at_eos; +} + +=head1 STRUCTURE-FORMING METHODS + +The following methods may be used to build a grammatical structure out of the +defined basic token-parsing methods. Each takes at least one code reference, +which will be passed the actual C<$parser> object as its first argument. + +=cut + +=head2 $ret = $parser->maybe( $code ) + +Attempts to execute the given C<$code> reference in scalar context, passing in +no arguments, and returning what it returned. If the code fails to parse by +calling the C<fail> method then none of the input string will be consumed; the +current parsing position will be restored. C<undef> will be returned in this +case. + +This may be considered to be similar to the C<?> regexp qualifier. + +=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 = $code->( $self ); 1 } and return $ret; + my $e = $@; + + pos($self->{str}) = $pos; + + die $e if $committed or not eval { $e->isa( "Parser::MGC::Failure" ) }; + return undef; +} + +=head2 $ret = $parser->scope_of( $start, $code, $stop ) + +Expects to find the C<$start> pattern, then attempts to execute the given +C<$code> reference, then expects to find the C<$stop> pattern. Returns +whatever the code reference returned. + +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 return +C<undef>. + +=cut + +sub scope_of +{ + my $self = shift; + my ( $start, $code, $stop ) = @_; + + ref $stop or $stop = qr/\Q$stop/; + + $self->expect( $start ); + local $self->{endofscope} = $stop; + + my $ret = $code->( $self ); + + $self->expect( $stop ); + + return $ret; +} + +=head2 $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>. + +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. + +=cut + +sub list_of +{ + my $self = shift; + my ( $sep, $code ) = @_; + + ref $sep or $sep = qr/\Q$sep/; + + my @ret; + + while( !$self->at_eos ) { + push @ret, scalar $code->( $self ); + + $self->skip_ws; + $self->{str} =~ m/\G$sep/gc or last; + } + + return \@ret; +} + +=head2 $ret = $parser->sequence_of( $code ) + +A shortcut for calling C<list_of> with an empty string as separator; expects +to find at least one instance of something parsed by C<$code>, separated only +by skipped whitespace. + +This may be considered to be similar to the C<+> or C<*> regexp qualifiers. + +=cut + +sub sequence_of +{ + my $self = shift; + my ( $code ) = @_; + + return $self->list_of( "", $code ); +} + +=head2 $ret = $parser->one_of( @codes ) + +Expects that one of the given code references can parse something from the +input, returning what it returned. Each code reference may indicate a failure +to parse by calling the C<fail> method. + +This may be considered to be similar to the C<|> regexp operator for forming +alternations of possible parse trees. + +=cut + +sub one_of +{ + my $self = shift; + + while( @_ ) { + my $pos = pos $self->{str}; + + my $committed = 0; + local $self->{committer} = sub { $committed++ }; + + my $ret; + $ret = eval { shift->( $self ) } and return $ret; + my $e = $@; + + pos( $self->{str} ) = $pos; + + die $e if $committed or not eval { $e->isa( "Parser::MGC::Failure" ) }; + } + + $self->fail( "Found nothing parseable" ); +} + +=head2 $parser->commit + +Calling this method will cancel the backtracking behaviour of the innermost +C<maybe> or C<one_of> structure forming method. That is, if later code then +calls C<fail>, the exception will be propagated out of C<maybe>, and no +further code blocks will be attempted by C<one_of>. + +Typically this will be called once the grammatical structure of an +alternation has been determined, ensuring that any further failures are raised +as real exceptions, rather than by attempting other alternatives. + + TODO: Code example with commit inside one_of + +=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. + +As a convenience for parsing, each of these methods will return undef if the +string is already at the end (if C<at_eos> returns true). + +=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 ); +} + +=head2 $parser->expect( $string ) + +=head2 $parser->expect( qr/pattern/ ) + +Expects to find a literal string or regexp pattern match, and consumes it. +This method does not return a useful value. + +=cut + +sub expect +{ + my $self = shift; + my ( $expect ) = @_; + + ref $expect or $expect = qr/\Q$expect/; + + $self->skip_ws; + $self->{str} =~ m/\G$expect/gc or + $self->fail( "Expected $expect" ); +} + +=head2 $int = $parser->token_int + +Expects to find an integer in decimal, octal or hexadecimal notation, and +consumes it. + +=cut + +sub token_int +{ + my $self = shift; + + return undef if $self->at_eos; + + $self->{str} =~ m/\G(0x[[:xdigit:]]+|[[:digit:]]+)/gc or + $self->fail( "Expected integer" ); + + my $int = $1; + + return oct $int if $int =~ m/^0/; + return $int; +} + +=head2 $str = $parser->token_string + +Expects to find a quoted string, and consumes it. The string should be quoted +using C<"> or C<'> quote marks. + +=cut + +sub token_string +{ + my $self = shift; + + return undef if $self->at_eos; + + my $pos = pos $self->{str}; + + $self->{str} =~ m/\G($self->{patterns}{string_delim})/gc or + $self->fail( "Expected string delimiter" ); + + my $delim = $1; + + $self->{str} =~ m/\G((?:\\.|[^\\])*)$delim/gc or + pos($self->{str}) = $pos, $self->fail( "Expected contents of string" ); + + my $string = $1; + + # TODO: Unescape stuff like \\ and \n and whatnot + + return $string; +} + +=head2 $ident = $parser->token_ident + +Expects to find an identifier, and consumes it. + +=cut + +sub token_ident +{ + my $self = shift; + + return undef if $self->at_eos; + + $self->{str} =~ m/\G($self->{patterns}{ident})/gc or + $self->fail( "Expected identifier" ); + + return $1; +} + +=head2 $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 linenum col text )} = @_; + return $self; +} + +use overload '""' => "STRING"; +sub STRING +{ + my $self = shift; + + return "$self->{message} on line $self->{linenum} at:\n" . + "$self->{text}\n" . + ( " " x $self->{col} . "^" ) . "\n"; +} + +# Keep perl happy; keep Britain tidy +1; + +__END__ + +=head1 TODO + +=over 4 + +=item * + +Unescaping of string constants; customisable + +=item * + +Easy ability for subclasses to define more token types + +=back + +=head1 AUTHOR + +Paul Evans <leon...@leonerd.org.uk> diff --git a/t/00use.t b/t/00use.t new file mode 100644 index 0000000..d2dc1c4 --- /dev/null +++ b/t/00use.t @@ -0,0 +1,3 @@ +use Test::More tests => 1; + +use_ok( "Parser::MGC" ); diff --git a/t/01base.t b/t/01base.t new file mode 100644 index 0000000..6efca79 --- /dev/null +++ b/t/01base.t @@ -0,0 +1,36 @@ +#!/usr/bin/perl -w + +use strict; + +use Test::More tests => 4; + +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)' ); + +__DATA__ +4 5 6 diff --git a/t/02expect.t b/t/02expect.t new file mode 100644 index 0000000..df8049b --- /dev/null +++ b/t/02expect.t @@ -0,0 +1,31 @@ +#!/usr/bin/perl -w + +use strict; + +use Test::More tests => 3; + +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( !eval { $parser->from_string( "goodbye world" ) }, '"goodbye world" fails' ); +is( $@, + qq[Expected (?-xism:hello) on line 1 at:\n] . + qq[goodbye world\n] . + qq[^\n], + 'Exception from "goodbye world" failure' ); diff --git a/t/03where.t b/t/03where.t new file mode 100644 index 0000000..a955bd2 --- /dev/null +++ b/t/03where.t @@ -0,0 +1,47 @@ +#!/usr/bin/perl -w + +use strict; + +use Test::More tests => 6; + +my @positions; + +package TestParser; +use base qw( Parser::MGC ); + +sub parse +{ + my $self = shift; + + main::is_deeply( [ $self->where ], + $positions[0], + '->where before parsing' ); + + $self->expect( "hello" ); + main::is_deeply( [ $self->where ], + $positions[1], + '->where during parsing' ); + + $self->expect( qr/world/ ); + main::is_deeply( [ $self->where ], + $positions[2], + '->where after parsing' ); + + return 1; +} + +package main; + +my $parser = TestParser->new; + +@positions = ( + [ 1, 0, "hello world" ], + [ 1, 5, "hello world" ], + [ 1, 11, "hello world" ], ); +$parser->from_string( "hello world" ); + +@positions = ( + [ 1, 0, "hello" ], + [ 1, 5, "hello" ], + [ 2, 5, "world" ], ); +$parser->from_string( "hello\nworld" ); diff --git a/t/04comment.t b/t/04comment.t new file mode 100644 index 0000000..a95f780 --- /dev/null +++ b/t/04comment.t @@ -0,0 +1,32 @@ +#!/usr/bin/perl -w + +use strict; + +use Test::More tests => 4; + +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' ); diff --git a/t/10token_int.t b/t/10token_int.t new file mode 100644 index 0000000..e5cc0ce --- /dev/null +++ b/t/10token_int.t @@ -0,0 +1,26 @@ +#!/usr/bin/perl -w + +use strict; + +use Test::More tests => 5; + +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( "hello" ) }, '"hello" fails' ); diff --git a/t/11token_string.t b/t/11token_string.t new file mode 100644 index 0000000..8c164c1 --- /dev/null +++ b/t/11token_string.t @@ -0,0 +1,32 @@ +#!/usr/bin/perl -w + +use strict; + +use Test::More tests => 6; + +package TestParser; +use base qw( Parser::MGC ); + +sub parse +{ + my $self = shift; + + return $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( $parser->from_string( q['foo "bar"'] ), 'foo "bar"', 'Single quoted string containing double substr' ); + +$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' ); diff --git a/t/12token_ident.t b/t/12token_ident.t new file mode 100644 index 0000000..4785131 --- /dev/null +++ b/t/12token_ident.t @@ -0,0 +1,38 @@ +#!/usr/bin/perl -w + +use strict; + +use Test::More tests => 6; + +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 identifier 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' ); diff --git a/t/13token_kw.t b/t/13token_kw.t new file mode 100644 index 0000000..d534245 --- /dev/null +++ b/t/13token_kw.t @@ -0,0 +1,28 @@ +#!/usr/bin/perl -w + +use strict; + +use Test::More tests => 3; + +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' ); diff --git a/t/20maybe.t b/t/20maybe.t new file mode 100644 index 0000000..e58235f --- /dev/null +++ b/t/20maybe.t @@ -0,0 +1,32 @@ +#!/usr/bin/perl -w + +use strict; + +use Test::More tests => 4; + +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 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' ); diff --git a/t/21scope_of.t b/t/21scope_of.t new file mode 100644 index 0000000..fcb7da9 --- /dev/null +++ b/t/21scope_of.t @@ -0,0 +1,28 @@ +#!/usr/bin/perl -w + +use strict; + +use Test::More tests => 3; + +package TestParser; +use base qw( Parser::MGC ); + +sub parse +{ + my $self = shift; + + $self->scope_of( + "(", + sub { return $self->token_int }, + ")" + ); +} + +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"' ); diff --git a/t/22list_of.t b/t/22list_of.t new file mode 100644 index 0000000..d3a48be --- /dev/null +++ b/t/22list_of.t @@ -0,0 +1,25 @@ +#!/usr/bin/perl -w + +use strict; + +use Test::More tests => 3; + +package TestParser; +use base qw( Parser::MGC ); + +sub parse +{ + my $self = shift; + + $self->list_of( ",", sub { + return $self->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"' ); diff --git a/t/23sequence_of.t b/t/23sequence_of.t new file mode 100644 index 0000000..e91a6e4 --- /dev/null +++ b/t/23sequence_of.t @@ -0,0 +1,24 @@ +#!/usr/bin/perl -w + +use strict; + +use Test::More tests => 2; + +package TestParser; +use base qw( Parser::MGC ); + +sub parse +{ + my $self = shift; + + $self->sequence_of( sub { + return $self->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"' ); diff --git a/t/24one_of.t b/t/24one_of.t new file mode 100644 index 0000000..665e291 --- /dev/null +++ b/t/24one_of.t @@ -0,0 +1,33 @@ +#!/usr/bin/perl -w + +use strict; + +use Test::More tests => 6; + +package TestParser; +use base qw( Parser::MGC ); + +sub parse +{ + my $self = shift; + + $self->one_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 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' ); diff --git a/t/30commit.t b/t/30commit.t new file mode 100644 index 0000000..b9080bb --- /dev/null +++ b/t/30commit.t @@ -0,0 +1,39 @@ +#!/usr/bin/perl -w + +use strict; + +use Test::More tests => 4; + +package TestParser; +use base qw( Parser::MGC ); + +sub parse +{ + my $self = shift; + + $self->one_of( + sub { $self->token_int }, + sub { + $self->scope_of( "(", + sub { + $self->commit; + $self->token_string; + }, + ")" ); + } + ); +} + +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' ); diff --git a/t/99pod.t b/t/99pod.t new file mode 100644 index 0000000..339b17d --- /dev/null +++ b/t/99pod.t @@ -0,0 +1,8 @@ +#!/usr/bin/perl -w + +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(); -- Alioth's /usr/local/bin/git-commit-notice on /srv/git.debian.org/git/pkg-perl/packages/libparser-mgc-perl.git _______________________________________________ Pkg-perl-cvs-commits mailing list Pkg-perl-cvs-commits@lists.alioth.debian.org http://lists.alioth.debian.org/cgi-bin/mailman/listinfo/pkg-perl-cvs-commits