Data-TableReader-0.022000755001750001750 015234670244 16264 5ustar00silverdirksilverdirk000000000000README100644001750001750 62615234670244 17211 0ustar00silverdirksilverdirk000000000000Data-TableReader-0.022This archive contains the distribution Data-TableReader, version 0.022: Locate and read records from human-edited data tables (Excel, CSV) This software is copyright (c) 2026 by Michael Conrad. This is free software; you can redistribute it and/or modify it under the same terms as the Perl 5 programming language system itself. This README file was generated by Dist::Zilla::Plugin::Readme v6.036. Changes100644001750001750 1347115234670244 17666 0ustar00silverdirksilverdirk000000000000Data-TableReader-0.022Version 0.022 - 2026-08-05 - Support various web framework Upload objects being used as ->input - Use content_type if available in preference to file extension or content heuristics. - Differentiate between real_file_name and client_file_name, and ignore the file extension of real_file_name if client_file_name exists. (e.g. things broke when Catalyst changed the file extension to .upload) These show as new attributes on the Decoder. - Much improved detection and handling of charset for CSV, TSV, and HTML - Properly handle consequences of writes to the ->fields(...) attribute by clearing other attributes. - Fix several col_map lifecycle bugs: preserve the caller's original array, restore the supplied map after clearing search results, re-resolve it after fields change, and avoid reusing a previous search result during subsequent find_table calls. - Fix bug when using ->seek on a record iterator which had reached EOF or was in the middle of counting blank lines. - Fix ability to use ->all on a record iterator where record objects could stringify to a false value. - More API validation and better error messages in a variety of edge cases. - Stop logging at 'notice' level since it isn't supported by all common logger objects. - Fix numerous documentation mistakes, including callback argument list of on_partial_match and on_unknown_columns. - Additionally pass the %candidate structure to on_unknown_columns callback. Version 0.021 - 2024-05-02 - Use ->table_search_results->{...}{row} instead of {row_idx} - Allow initializing TableReader 'fields' attribute with Field objects (had only been allowing strings and hashrefs) - Decoder::Mock now correctly handles empty tables (no rows) Version 0.020 - 2024-04-30 - Rename on_validation_fail -> on_validation_error The action codes are the same, but the callback has different arguments. Old callbacks applied using the attribute name 'on_validation_fail' will continue to work. - New iterator attribute 'dataset_idx', for keeping track of which dataset you're on. - Unimplemented Iterator->seek now dies as per the documentation. (no built-in iterator lacked support for seek, so unlikely to matter) Version 0.015 - 2024-04-27 - Better support for fields sharing name, with Field->addr (refaddr) and TableReader->field_by_addr - Decoder iterators now have ->row attribute - Spreadsheet decoder ->position includes sheet number and now uses 1-based row number (as originally intended) - Results of find_table are stored in table_search_results for better inspection and reporting on a failure. This allows detection messages to be associated with a row, and various conflicts to be associated with a column (without parsing message text). - On a failed find_table, user can inspect the attempts in table_search_results->{candidates} and select one to be ->{found}, and then proceed to create the iterator. - col_map is now a full attribute and can be specified in the constructor. find_table starts with the user-supplied value and tries to fill in any 'undef' values in that array. - New settings on_partial_match, on_ambiguous_columns, and modified official values of on_unknown_columns. These provide better control over what counts as an error and whether to continue the search. Version 0.014 - 2024-03-25 - Fix compatibility with newest Spreadsheet::ParseXLSX Version 0.013 - 2024-03-22 - Fix bug in unit tests causing failure when MRO::Compat not installed Version 0.012 - 2024-03-07 - Field now has 'coerce' attribute which can be a coderef, or enable Type::Tiny coercion. - TableReader 'input' attribute can now be an arrayref, as a shorthand for the 'Mock' decoder. - Improved unit tests Version 0.011 - 2019-06-27 - Allow per-field 'trim' value to be a regex or coderef - Change dist version-munger to Dist::Zilla::Plugin::OurPkgVersion - Exclude ::Decoder::HTML files from getting shipped with main dist Version 0.010 - 2019-01-02 - Fix several bugs related to multi-line headers - Also allow 'input' to be a Spreadsheet::ParseExcel::Workbook - Auto-detection support for ::Decoder::HTML companion module Version 0.008 - 2018-11-28 - 'input' attribute may now be a Spreadsheet::ParseExcel::Worksheet - When specifying 'decoder' attribute as an arrayref or hashref, the CLASS argument is now optional, allowing auto-detection while still supplying extre optional attributes for the decoder. - Wrokaround for Libre Office row-max bug - New Decoder::XLSX attribute 'xls_formatter', useful for casting local datetimes to a known time zone. - Prevent loading Text::CSV_XS if its version is too old. Version 0.007 - 2018-03-15 - Fix various bugs in detect_input_format relevant to CSV files - Enhanced debug-level logging during the table search algorighm Version 0.006 - 2018-03-08 - Auto-detect CSV Unicode format by looking for BOM, unless handle already has an IO layer to specify encoding. - Improved logging, and logging API. 'log' attribute is no longer public on Decoder objects. Version 0.005 - 2017-11-26 - Remove 'filters' feature since it adds overhead and not much value - Fix bug when creating multiple parallel record iterators - Sanitize data headers written in logging messages Version 0.004 - 2017-11-26 - Re-add Text::CSV as a hard dependency since it's small and I need a recent version for all the tests to pass. Version 0.003 - 2017-11-25 - Remove hard dependencies on CSV and Excel parsers - Use new "Mock" decoder for format-independent test cases - Fix handling of $TableReader->log to match API description - Fix bugs to be compatible back to 5.8.9 Version 0.002 - 2017-11-24 - Fixed 'filters' feature - Iterators of decoders are now created on each call, rather than cached - Many documentation improvements Version 0.001 - 2017-11-24 - Initial public version LICENSE100644001750001750 4630715234670244 17404 0ustar00silverdirksilverdirk000000000000Data-TableReader-0.022This software is copyright (c) 2026 by Michael Conrad. 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) 2026 by Michael Conrad. 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. 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, see . 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 Moe Ghoul, President of Vice That's all there is to it! --- The Perl Artistic License 1.0 --- This software is Copyright (c) 2026 by Michael Conrad. This is free software, licensed under: The Perl 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 as specified below. "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 uunet.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) give non-standard executables non-standard names, and clearly document 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. You may embed this Package's interpreter within an executable of yours (by linking); this shall be construed as a mere form of aggregation, provided that the complete Standard Version of the interpreter is so embedded. 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 whoever generated them, and may be sold commercially, and may be aggregated with this Package. If such scripts or library files are aggregated with this Package via the so-called "undump" or "unexec" methods of producing a binary executable image, then distribution of such an image shall neither be construed as a distribution of this Package nor shall it fall under the restrictions of Paragraphs 3 and 4, provided that you do not represent such an executable image as a Standard Version of this Package. 7. C subroutines (or comparably compiled subroutines in other languages) supplied by you and linked into this Package in order to emulate subroutines and variables of the language defined by this Package shall not be considered part of this Package, but are the equivalent of input as in Paragraph 6, provided these subroutines do not change the language in any way that would cause it to fail the regression tests for the language. 8. Aggregation of this Package with a commercial distribution is always permitted provided that the use of this Package is embedded; that is, when no overt attempt is made to make this Package's interfaces visible to the end user of the commercial distribution. Such use shall not be construed as a distribution of this Package. 9. The name of the Copyright Holder may not be used to endorse or promote products derived from this software without specific prior written permission. 10. THIS PACKAGE IS PROVIDED "AS IS" AND WITHOUT ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, WITHOUT LIMITATION, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE. The End dist.ini100644001750001750 277515234670244 20024 0ustar00silverdirksilverdirk000000000000Data-TableReader-0.022name = Data-TableReader abstract = Locate and read records from human-edited data tables (Excel, CSV) author = Michael Conrad license = Perl_5 copyright_holder = Michael Conrad [MetaResources] homepage = https://github.com/nrdvana/perl-Data-TableReader bugtracker.web = https://github.com/nrdvana/perl-Data-TableReader/issues repository.web = https://github.com/nrdvana/perl-Data-TableReader repository.url = https://github.com/nrdvana/perl-Data-TableReader.git repository.type = git [@Git] [Git::Contributors] [Git::GatherDir] exclude_match = ^t/tmp exclude_match = ^Decoder-.* include_untracked = 0 [Encoding] encoding = bytes match = ^t/data/ [Git::NextVersion] [OurPkgVersion] [PodWeaver] [PodSyntaxTests] [Test::Pod::Coverage::Configurable] also_private=BUILD [MakeMaker] [License] [Readme] ; authordep Pod::Weaver::Section::Contributors ; authordep Pod::Elemental::Transformer::List [AutoPrereqs] skip = MRO::Compat skip = Types::Standard [Prereqs] Text::CSV = 1.95 [Prereqs / RuntimeRecommends] Text::CSV_XS = 1.06 Spreadsheet::ParseExcel = 0 Spreadsheet::ParseXLSX = 0 Data::TableReader::Decoder::HTML = 0 [Prereqs / TestRequires] Log::Any::Adapter::TAP = 0 [Prereqs / TestRecommends] Spreadsheet::ParseXLSX = 0 [Prereqs / DevelopRequires] Pod::Weaver::Section::Contributors = 0 Pod::Elemental::Transformer::List = 0 [DynamicPrereqs] -condition = "$]" < '5.010' -body = requires('MRO::Compat'); [Manifest] [MetaYAML] [MetaJSON] [UploadToCPAN] MANIFEST100644001750001750 174515234670244 17505 0ustar00silverdirksilverdirk000000000000Data-TableReader-0.022# This file was automatically generated by Dist::Zilla::Plugin::Manifest v6.036. Changes LICENSE MANIFEST META.json META.yml Makefile.PL README README.md SciTEDirectory.properties dist.ini lib/Data/TableReader.pm lib/Data/TableReader/Decoder.pm lib/Data/TableReader/Decoder/CSV.pm lib/Data/TableReader/Decoder/IdiotCSV.pm lib/Data/TableReader/Decoder/Mock.pm lib/Data/TableReader/Decoder/Spreadsheet.pm lib/Data/TableReader/Decoder/TSV.pm lib/Data/TableReader/Decoder/XLS.pm lib/Data/TableReader/Decoder/XLSX.pm lib/Data/TableReader/Field.pm lib/Data/TableReader/Iterator.pm t/01-env-check.t t/05-field.t t/09-decoder-mock.t t/10-decoder-csv.t t/11-decoder-tsv.t t/12-decoder-idiot-csv.t t/15-decoder-xls.t t/30-detect-input-format.t t/35-record-iterator.t t/40-locate-table.t t/41-user-supplied-colmap.t t/42-user-overrides-found-header.t t/50-validation.t t/51-typetiny-validation.t t/data/AddressAuxData.xls t/data/AddressAuxData.xlsx weaver.ini xt/author/pod-coverage.t xt/author/pod-syntax.t META.yml100644001750001750 260715234670244 17623 0ustar00silverdirksilverdirk000000000000Data-TableReader-0.022--- abstract: 'Locate and read records from human-edited data tables (Excel, CSV)' author: - 'Michael Conrad ' build_requires: File::Spec::Functions: '0' Log::Any::Adapter: '0' Log::Any::Adapter::TAP: '0' Test::More: '0' configure_requires: ExtUtils::MakeMaker: '0' dynamic_config: 1 generated_by: 'Dist::Zilla version 6.036, CPAN::Meta::Converter version 2.150010' license: perl meta-spec: url: http://module-build.sourceforge.net/META-spec-v1.4.html version: '1.4' name: Data-TableReader recommends: Data::TableReader::Decoder::HTML: '0' Spreadsheet::ParseExcel: '0' Spreadsheet::ParseXLSX: '0' Text::CSV_XS: '1.06' requires: Carp: '0' Encode: '0' IO::Handle: '0' List::Util: '0' Log::Any: '0' Module::Runtime: '0' Moo: '2' Scalar::Util: '0' Text::CSV: '1.95' namespace::clean: '0' overload: '0' strict: '0' warnings: '0' resources: bugtracker: https://github.com/nrdvana/perl-Data-TableReader/issues homepage: https://github.com/nrdvana/perl-Data-TableReader repository: https://github.com/nrdvana/perl-Data-TableReader.git version: '0.022' x_contributors: - 'Christian Walde ' - 'Étienne Mollier ' - 'Michael Conrad ' x_generated_by_perl: v5.40.0 x_serialization_backend: 'YAML::Tiny version 1.74' x_spdx_expression: 'Artistic-1.0-Perl OR GPL-1.0-or-later' README.md100644001750001750 71115234670244 17603 0ustar00silverdirksilverdirk000000000000Data-TableReader-0.022# Data::TableReader This perl module helps take un-sanitized tabular data sources and verify that they match your expected schema, and then iterate the records. You can install the latest stable release of this module from CPAN: cpanm Data::TableReader or build and install this source code with the Dist::Zilla tool: dzil build cpanm ./Data-TableReader-$VERSION The source is found at http://github.com/nrdvana/perl-Data-TableReader META.json100644001750001750 521315234670244 17767 0ustar00silverdirksilverdirk000000000000Data-TableReader-0.022{ "abstract" : "Locate and read records from human-edited data tables (Excel, CSV)", "author" : [ "Michael Conrad " ], "dynamic_config" : 1, "generated_by" : "Dist::Zilla version 6.036, CPAN::Meta::Converter version 2.150010", "license" : [ "perl_5" ], "meta-spec" : { "url" : "http://search.cpan.org/perldoc?CPAN::Meta::Spec", "version" : 2 }, "name" : "Data-TableReader", "prereqs" : { "configure" : { "requires" : { "ExtUtils::MakeMaker" : "0" } }, "develop" : { "requires" : { "Pod::Coverage::TrustPod" : "0", "Pod::Elemental::Transformer::List" : "0", "Pod::Weaver::Section::Contributors" : "0", "Test::More" : "0.88", "Test::Pod" : "1.41", "Test::Pod::Coverage" : "1.08" } }, "runtime" : { "recommends" : { "Data::TableReader::Decoder::HTML" : "0", "Spreadsheet::ParseExcel" : "0", "Spreadsheet::ParseXLSX" : "0", "Text::CSV_XS" : "1.06" }, "requires" : { "Carp" : "0", "Encode" : "0", "IO::Handle" : "0", "List::Util" : "0", "Log::Any" : "0", "Module::Runtime" : "0", "Moo" : "2", "Scalar::Util" : "0", "Text::CSV" : "1.95", "namespace::clean" : "0", "overload" : "0", "strict" : "0", "warnings" : "0" } }, "test" : { "recommends" : { "Spreadsheet::ParseXLSX" : "0" }, "requires" : { "File::Spec::Functions" : "0", "Log::Any::Adapter" : "0", "Log::Any::Adapter::TAP" : "0", "Test::More" : "0" } } }, "release_status" : "stable", "resources" : { "bugtracker" : { "web" : "https://github.com/nrdvana/perl-Data-TableReader/issues" }, "homepage" : "https://github.com/nrdvana/perl-Data-TableReader", "repository" : { "type" : "git", "url" : "https://github.com/nrdvana/perl-Data-TableReader.git", "web" : "https://github.com/nrdvana/perl-Data-TableReader" } }, "version" : "0.022", "x_contributors" : [ "Christian Walde ", "\u00c9tienne Mollier ", "Michael Conrad " ], "x_generated_by_perl" : "v5.40.0", "x_serialization_backend" : "Cpanel::JSON::XS version 4.38", "x_spdx_expression" : "Artistic-1.0-Perl OR GPL-1.0-or-later" } weaver.ini100644001750001750 57015234670244 20321 0ustar00silverdirksilverdirk000000000000Data-TableReader-0.022[@CorePrep] [-SingleEncoding] [Name] [Version] [Region / prelude] [Generic / SYNOPSIS] [Generic / DESCRIPTION] [Generic / OVERVIEW] [Collect / ATTRIBUTES] command = attr [Collect / METHODS] command = method [Collect / FUNCTIONS] command = func [Leftovers] [Region / postlude] [Generic / Thanks] [Authors] [-Transformer] transformer = List [Contributors] [Legal] Makefile.PL100644001750001750 537515234670244 20331 0ustar00silverdirksilverdirk000000000000Data-TableReader-0.022# This file was automatically generated by Dist::Zilla::Plugin::MakeMaker v6.036. use strict; use warnings; use ExtUtils::MakeMaker; my %WriteMakefileArgs = ( "ABSTRACT" => "Locate and read records from human-edited data tables (Excel, CSV)", "AUTHOR" => "Michael Conrad ", "CONFIGURE_REQUIRES" => { "ExtUtils::MakeMaker" => 0 }, "DISTNAME" => "Data-TableReader", "LICENSE" => "perl", "NAME" => "Data::TableReader", "PREREQ_PM" => { "Carp" => 0, "Encode" => 0, "IO::Handle" => 0, "List::Util" => 0, "Log::Any" => 0, "Module::Runtime" => 0, "Moo" => 2, "Scalar::Util" => 0, "Text::CSV" => "1.95", "namespace::clean" => 0, "overload" => 0, "strict" => 0, "warnings" => 0 }, "TEST_REQUIRES" => { "File::Spec::Functions" => 0, "Log::Any::Adapter" => 0, "Log::Any::Adapter::TAP" => 0, "Test::More" => 0 }, "VERSION" => "0.022", "test" => { "TESTS" => "t/*.t" } ); my %FallbackPrereqs = ( "Carp" => 0, "Encode" => 0, "File::Spec::Functions" => 0, "IO::Handle" => 0, "List::Util" => 0, "Log::Any" => 0, "Log::Any::Adapter" => 0, "Log::Any::Adapter::TAP" => 0, "Module::Runtime" => 0, "Moo" => 2, "Scalar::Util" => 0, "Test::More" => 0, "Text::CSV" => "1.95", "namespace::clean" => 0, "overload" => 0, "strict" => 0, "warnings" => 0 ); # inserted by Dist::Zilla::Plugin::DynamicPrereqs 0.040 if ("$]" < '5.010') { requires('MRO::Compat'); } unless ( eval { ExtUtils::MakeMaker->VERSION(6.63_03) } ) { delete $WriteMakefileArgs{TEST_REQUIRES}; delete $WriteMakefileArgs{BUILD_REQUIRES}; $WriteMakefileArgs{PREREQ_PM} = \%FallbackPrereqs; } delete $WriteMakefileArgs{CONFIGURE_REQUIRES} unless eval { ExtUtils::MakeMaker->VERSION(6.52) }; WriteMakefile(%WriteMakefileArgs); # inserted by Dist::Zilla::Plugin::DynamicPrereqs 0.040 sub _add_prereq { my ($mm_key, $module, $version_or_range) = @_; $version_or_range ||= 0; warn "$module already exists in $mm_key (at version $WriteMakefileArgs{$mm_key}{$module}) -- need to do a sane metamerge!" if exists $WriteMakefileArgs{$mm_key}{$module} and $WriteMakefileArgs{$mm_key}{$module} ne '0' and $WriteMakefileArgs{$mm_key}{$module} ne $version_or_range; warn "$module already exists in FallbackPrereqs (at version $FallbackPrereqs{$module}) -- need to do a sane metamerge!" if exists $FallbackPrereqs{$module} and $FallbackPrereqs{$module} ne '0' and $FallbackPrereqs{$module} ne $version_or_range; $WriteMakefileArgs{$mm_key}{$module} = $FallbackPrereqs{$module} = $version_or_range; return; } sub requires { goto &runtime_requires } sub runtime_requires { my ($module, $version_or_range) = @_; _add_prereq(PREREQ_PM => $module, $version_or_range); } t000755001750001750 015234670244 16450 5ustar00silverdirksilverdirk000000000000Data-TableReader-0.02205-field.t100644001750001750 452515234670244 20310 0ustar00silverdirksilverdirk000000000000Data-TableReader-0.022/t#! /usr/bin/env perl use strict; use warnings; use Test::More; use_ok( 'Data::TableReader::Field' ) or BAIL_OUT; subtest header_regex => sub { my @tests= ({ name => 'name', header => undef, match => [ 'name', ' nAMe', '^%name&*^%^' ], nomatch => [ 'na me', 'names', 'surname', 'first name' ], },{ name => 'first_name', header => undef, match => [ 'first name', 'FirstName', ' First_Name', 'First.Name' ], nomatch => [ 'first_nam', 'first.*', 'name', 'first name 0' ], },{ name => 'first_name', header => 'first_name', match => [ 'first_name', ' first_name', 'first_name#"$:^' ], nomatch => [ 'first name', 'first.name', 'first _name', 'FirstName' ], },{ name => 'zip5', match => [ 'zip5', 'zip 5', 'zip_5', 'ZIP-5' ], nomatch => [ 'zip' ], },{ name => 'ZipCode', match => [ 'ZipCode', 'zip code', 'zip.code', 'ZIP CODE', '--ZIP CODE--' ], nomatch => [ 'ZipCode(5)' ], },{ name => 'ZipCode', header => "Zip\nCode", match => ["Zip\nCode", "zip \n code"], nomatch => [ 'zipcode' ], }); plan tests => scalar @tests; for my $t (@tests) { subtest "name=$t->{name} header=".($t->{header}||'') => sub { plan tests => 1 + @{$t->{match}} + @{$t->{nomatch}}; my $field= new_ok( 'Data::TableReader::Field', [ name => $t->{name}, header => $t->{header} ], 'field' ); like( $_, $field->header_regex, "match $_" ) for @{ $t->{match} }; unlike( $_, $field->header_regex, "nomatch $_" ) for @{ $t->{nomatch} }; }; } }; subtest trim => sub { my @tests= ({ name => 'true', trim => 1, input => [ 'x', ' x', 'x ', ' x ', ' ' ], expected => [ 'x', 'x', 'x', 'x', '' ], },{ name => 'regex', trim => qr/^\s*N\/A\s*$|^\s*NULL\s*$|^\s+|\s+$/i, input => [ 'x', ' x', 'x ', ' x ', 'N/A', ' N/A ', ' Null ' ], expected => [ 'x', 'x', 'x', 'x', '', '', '' ], },{ name => 'coderef', trim => sub { s/\s+/_/g; }, input => [ 'x x', ' x' ], expected => [ 'x_x', '_x' ], }); plan tests => scalar @tests; for my $t (@tests) { subtest "name=$t->{name}" => sub { plan tests => 1 + @{$t->{input}}; my $field= new_ok( 'Data::TableReader::Field', [ name => $t->{name}, trim => $t->{trim} ], 'field' ); for (0.. $#{$t->{input}}) { my ($in, $expected)= ( $t->{input}[$_], $t->{expected}[$_] ); $field->trim_coderef->() for my $out= $in; is( $out, $expected, $in ); } }; } }; done_testing; 01-env-check.t100644001750001750 61515234670244 21040 0ustar00silverdirksilverdirk000000000000Data-TableReader-0.022/t#! /usr/bin/env perl use strict; use warnings; use Test::More tests => 1; diag "Checking optional modules"; for (qw( Text::CSV Text::CSV_XS Archive::Zip Spreadsheet::XLSX Spreadsheet::ParseXLSX Spreadsheet::ParseExcel Type::Tiny Types::Standard )) { if (eval "require $_") { diag "Have $_ ".$_->VERSION; } else { diag "No $_"; } } pass('This is just for CPAN testers reports'); 50-validation.t100644001750001750 735615234670244 21364 0ustar00silverdirksilverdirk000000000000Data-TableReader-0.022/t#! /usr/bin/env perl use strict; use warnings; use Test::More; use File::Spec::Functions 'catfile'; use Log::Any '$log'; use Log::Any::Adapter 'TAP', filter => 'none'; use_ok( 'Data::TableReader' ) or BAIL_OUT; sub is_alpha { defined $_[0] and $_[0] =~ /^[a-z]+$/? undef : 'not alpha' } sub is_num { defined $_[0] and $_[0] =~ /^[0-9]+$/? undef : 'not numeric' } # Find fields in the exact order they are present in the file subtest validation_die => sub { my @log; my $tr= new_ok( 'Data::TableReader', [ input => [ ['X'], ['abc'], ['123'], ['def'] ], fields => [{ name => 'X', type => \&is_alpha }], log => \@log ], 'TableReader' ); my $i= $tr->iterator; is_deeply( eval { $i->() }, { X => 'abc' }, 'valid row' ); like( do { local $@; eval { $i->() }; my $e= $@ }, qr/not alpha/, 'invalid row' ); is_deeply( eval { $i->() }, { X => 'def' }, 'valid row' ); is( $i->(), undef, 'eof' ); }; subtest validation_next => sub { open(my $csv, '<', \"X\n1\n2\n\n15\nX\nY\nZ\n16\n") or die; my $tr= new_ok( 'Data::TableReader', [ input => [ ['X'], ['1'], ['2'], [''], ['15'], ['X'], ['Y'], ['Z'], ['16'] ], fields => [{ name => 'X', type => \&is_num }], on_validation_fail => 'next', log => \my @log ], 'TableReader' ); is_deeply( $tr->iterator->all, [ { X => 1 }, { X => 2 }, { X => 15 }, { X => 16 } ], 'only numeric values' ) or note explain \@log; }; subtest validation_use => sub { my @log; my $tr= new_ok( 'Data::TableReader', [ input => [ ['X'], ['1'], ['2'], ['x'], ['15'] ], fields => [{ name => 'X', type => \&is_num }], on_validation_fail => 'use', log => \@log ], 'TableReader' ); is_deeply( $tr->iterator->all, [ { X => 1 }, { X => 2 }, { X => 'x' }, { X => 15 } ], 'keep all values' ); is( scalar(grep { $_->[0] eq 'warn' } @log), 1, 'one warning' ); like( $log[0][1], qr/not numeric/, 'warn about non-numeric' ); }; subtest validation_custom => sub { my @log; my $tr= new_ok( 'Data::TableReader', [ input => [ ['X'], ['1'], ['2'], ['x'], ['15'] ], fields => [{ name => 'X', type => \&is_num }], on_validation_fail => sub { my ($reader, $failures, $values, $context)= @_; for (@$failures) { my ($field, $value_index, $message)= @$_; if ($field->name eq 'X') { $values->[$value_index]= 0; $_= undef; } } @$failures= grep defined, @$failures; return 'use'; }, log => \@log ], 'TableReader' ); is_deeply( $tr->iterator->all, [ { X => 1 }, { X => 2 }, { X => 0 }, { X => 15 } ], 'keep munged value' ); is_deeply( \@log, [], 'no warnings' ) or note explain @log; }; subtest validation_new_api => sub { my @log; my $tr= new_ok( 'Data::TableReader', [ input => [ ['X', 'X', 'Y'], [1,1,1], ['2','3'], ['x',5], ['15'] ], fields => [ { name => 'X', type => \&is_num, array => 1 }, { name => 'y', type => \&is_num } ], on_validation_error => sub { my ($reader, $failures, $record, $data_iter)= @_; for (@$failures) { my ($field, $value_ref, $message, $path)= @$_; if ($field->name eq 'X') { $$value_ref= 0; $_= undef; } elsif ($field->name eq 'y') { $$value_ref= -1; $_= undef; } } @$failures= grep defined, @$failures; return 'use'; }, log => \@log ], 'TableReader' ); is_deeply( [ map +($_? $_->name : undef), @{$tr->col_map} ], [ 'X', 'X', 'y' ], 'col_map' ); is_deeply( $tr->iterator->all, [ { X => [1,1], y => 1 }, { X => [2,3], y => -1 }, { X => [0,5], y => -1 }, { X => [15,0], y => -1 } ], 'keep munged value' ); is_deeply( \@log, [], 'no warnings' ) or note explain @log; }; done_testing; sub open_data { my $name= shift; my $t_dir= __FILE__; $t_dir =~ s,[^\/]+$,,; $name= catfile($t_dir, 'data', $name); open(my $fh, "<:raw", $name) or die "open($name): $!"; return $fh; } 10-decoder-csv.t100644001750001750 1150115234670244 21427 0ustar00silverdirksilverdirk000000000000Data-TableReader-0.022/t#! /usr/bin/env perl use strict; use warnings; use Test::More; use Log::Any '$log'; use Log::Any::Adapter 'TAP'; use Data::TableReader::Decoder::CSV; my $csvmod; plan skip_all => 'Need a CSV parser for this test' unless eval { $csvmod= Data::TableReader::Decoder::CSV->default_csv_module }; note "CSV decoder is ".$csvmod." version ".$csvmod->VERSION; my $log_fn= sub { $log->can($_[0])->($log, $_[1]) }; sub test_basic { my $input= ascii(); open my $input_fh, '<', \$input or die; my $d= new_ok( 'Data::TableReader::Decoder::CSV', [ file_name => '', file_handle => $input_fh, _log => $log_fn ], 'CSV decoder' ); ok( my $iter= $d->iterator, 'got iterator' ); is_deeply( $iter->(), [ 'a', 'b', 'c', 'd' ], 'first row' ); is( $iter->row, 1, 'row=1' ); is( $iter->dataset_idx, 0, 'dataset_idx=0' ); is_deeply( $iter->(), [ '1', '2', '3', '4' ], 'second row' ); is( $iter->row, 2, 'row=2' ); is_deeply( $iter->(), undef, 'no third row' ); is( $iter->row, 2, 'row=2' ); is( $iter->dataset_idx, 0, 'dataset_idx=0' ); ok( $iter->seek(0), 'rewind' ); is( $iter->row, 0, 'row=0' ); is_deeply( $iter->(), [ 'a', 'b', 'c', 'd' ], 'first row again' ); is( $iter->row, 1, 'row=1' ); is_deeply( $iter->([2,1]), [ '3', '2' ], 'slice from second row' ); ok( !$iter->next_dataset, 'no next dataset' ); is( $iter->dataset_idx, 0, 'dataset_idx=0' ); } sub test_multi_iterator { my $input= ascii(); open my $input_fh, '<', \$input or die; my $d= new_ok( 'Data::TableReader::Decoder::CSV', [ file_name => '', file_handle => $input_fh, _log => $log_fn ], 'CSV decoder' ); ok( my $iter= $d->iterator, 'create first iterator' ); # This might be supported in the future, but for now ensure it dies like( do { local $@; eval { $d->iterator }; my $e= $@ }, qr/multiple iterator/i, 'error for multiple iterators' ); undef $iter; # release old iterator, freeing up the file handle to create a new one ok( $iter= $d->iterator, 'new iterator' ); is_deeply( $iter->(), [ 'a', 'b', 'c', 'd' ], 'first row again' ); } sub test_utf_bom { for my $input_fn (qw( utf8_bom utf16_le_bom utf16_be_bom utf8_nobom deceptive_utf8_nobom )) { subtest "seekable $input_fn" => sub { my $input= main->$input_fn; open my $input_fh, '<', \$input or die; my $d= new_ok( 'Data::TableReader::Decoder::CSV', [ file_name => '', file_handle => $input_fh, _log => $log_fn ], "CSV decoder for $input_fn" ); ok( my $iter= $d->iterator, 'got iterator' ); like( $iter->()[0], qr/^\x{FFFD}?test$/, 'first row' ); is_deeply( $iter->(), [ "\x{8A66}\x{3057}", 1, 2, 3 ], 'second row' ); is_deeply( $iter->(), [ "\x{27000}" ], 'third row' ); is_deeply( $iter->(), undef, 'no fourth row' ); ok( $iter->seek(0), 'rewind' ); # workaround for a perl bug! the input string gets corrupted substr($input,0,8)= substr(main->$input_fn,0,8); like( $iter->()[0], qr/^\x{FFFD}?test$/, 'first row' ); is_deeply( $iter->([0,3]), [ "\x{8A66}\x{3057}", 3 ], 'slice from second row' ); ok( !$iter->next_dataset, 'no next dataset' ); }; subtest "nonseekable $input_fn" => sub { my $input= main->$input_fn; pipe(my ($input_fh, $out_fh)) or die "pipe: $!"; print $out_fh $input or die "print(pipe_out): $!"; close $out_fh or die "close: $!"; my $d= new_ok( 'Data::TableReader::Decoder::CSV', [ file_name => '', file_handle => $input_fh, _log => $log_fn ], "CSV decoder for $input_fn" ); if ($input_fn =~ /deceptive/) { # Some inputs on non-seekable file handles will result in this exception. # This is expected. like( do { local $@; eval { $d->iterator }; my $e= $@ }, qr/seek/, 'can\'t seek exception' ); } else { ok( my $iter= $d->iterator, 'got iterator' ); like( $iter->()[0], qr/^\x{FFFD}?test$/, 'first row' ); is_deeply( $iter->(), [ "\x{8A66}\x{3057}", 1, 2, 3 ], 'second row' ); is_deeply( $iter->(), [ "\x{27000}" ], 'third row' ); is_deeply( $iter->(), undef, 'no fourth row' ); ok( !$iter->next_dataset, 'no next dataset' ); } }; } } subtest basic => \&test_basic; subtest multi_iter => \&test_multi_iterator; subtest utf_bom => \&test_utf_bom; done_testing; sub ascii { return < 'Need a CSV parser for this test' unless eval { Data::TableReader::Decoder::TSV->default_csv_module }; my $input= < '', file_handle => $input_fh, _log => sub {} ], 'TSV decoder' ); ok( my $iter= $d->iterator, 'got iterator' ); is_deeply( $iter->(), [ 'a', 'b', 'c', 'd' ], 'first row' ); is( $iter->row, 1, 'row=1' ); is( $iter->dataset_idx, 0, 'dataset_idx=0' ); is_deeply( $iter->(), [ '1', '2', '3', '4' ], 'second row' ); is_deeply( $iter->(), undef, 'no third row' ); is( $iter->row, 2, 'row=2' ); ok( $iter->seek(0), 'rewind' ); is_deeply( $iter->(), [ 'a', 'b', 'c', 'd' ], 'first row again' ); is( $iter->row, 1, 'row=1' ); is_deeply( $iter->([2,1]), [ '3', '2' ], 'slice from second row' ); ok( !$iter->next_dataset, 'no next dataset' ); is( $iter->dataset_idx, 0, 'dataset_idx=0' ); done_testing; 15-decoder-xls.t100644001750001750 552115234670244 21434 0ustar00silverdirksilverdirk000000000000Data-TableReader-0.022/t#! /usr/bin/env perl use strict; use warnings; use Test::More; use File::Spec::Functions 'catfile'; use Data::TableReader::Decoder::XLSX; use Data::TableReader::Decoder::XLS; use Data::TableReader; SKIP: { skip "Need an XLS parser", 1 unless eval { Data::TableReader::Decoder::XLS->default_xls_module }; subtest XLS => sub { my $xls= new_ok( 'Data::TableReader::Decoder::XLS', [ file_name => '', file_handle => open_data('AddressAuxData.xls'), _log => sub {} ], 'XLS decoder' ); run_test($xls); run_test_w_sheet($xls); }; } SKIP: { skip "Need an XLSX parser", 1 unless eval { Data::TableReader::Decoder::XLSX->default_xlsx_module }; subtest XLSX => sub { my $xlsx= new_ok( 'Data::TableReader::Decoder::XLSX', [ file_name => '', file_handle => open_data('AddressAuxData.xlsx'), _log => sub {} ], 'XLSX decoder' ); run_test($xlsx); run_test_w_sheet($xlsx); }; } done_testing; # Both worksheets have the same data, so just repeat the tests sub run_test { my ($decoder, $skip_second)= @_; ok( my $iter= $decoder->iterator, 'got iterator' ); ok( my $iter2= $decoder->iterator, 'second parallel iterator' ); is_deeply( $iter->(), [ 'Name', 'Address', 'City', 'State', 'Zip' ], 'row 1' ); is( $iter->row, 1, 'iter1 row=1' ); is( $iter2->row, 0, 'iter2 row=0' ); is_deeply( $iter2->(), [ 'Name', 'Address', 'City', 'State', 'Zip' ], 'row 1 from iterator 2' ); is_deeply( $iter->(), [ 'Someone', '123 Long St', 'Somewhere', 'OH', 45678 ], 'row 2' ); ok( my $pos= $iter->tell, 'tell position' ); is_deeply( $iter->(), [ ('') x 5 ], 'row 3 blank' ); is_deeply( $iter->(), [ 'Another', '01 Main St', 'Elsewhere', 'OH', 45678 ], 'row 4' ); is( $iter->row, 4, 'iter1 row=4' ); is_deeply( $iter->(), undef, 'no row 5' ); is( $iter->dataset_idx, 0, 'dataset_idx=0' ); return if $skip_second; ok( $iter->next_dataset, 'next dataset (worksheet)' ); is( $iter->dataset_idx, 1, 'dataset_idx=1' ); is_deeply( $iter->(), [ 'Zip Codes', '', '', '', 'Cities', '', '', '', 'State Postal Codes', '', '' ], 'sheet 2, first row' ); ok( $iter->seek($pos), 'seek back to previous sheet' ); is( $iter->dataset_idx, 0, 'dataset_idx=0' ); is_deeply( $iter->(), [ ('') x 5 ], 'row 3 blank' ); is_deeply( $iter->(), [ 'Another', '01 Main St', 'Elsewhere', 'OH', 45678 ], 'row 4' ); is_deeply( $iter->(), undef, 'no row 5' ); ok( $iter->next_dataset, 'next dataset (worksheet)' ); is( $iter->dataset_idx, 1, 'dataset_idx=1' ); ok( !$iter->next_dataset, 'no more worksheets' ); is( $iter->dataset_idx, 1, 'dataset_idx=1' ); } sub run_test_w_sheet { my ($decoder) = @_; run_test(Data::TableReader->new(input => $decoder->_sheets->[0], fields => [])->decoder, "skip_second"); return; } sub open_data { my $name= shift; my $t_dir= __FILE__; $t_dir =~ s,[^\/\\]+$,,; $name= catfile($t_dir, 'data', $name); open(my $fh, "<:raw", $name) or die "open($name): $!"; return $fh; } 09-decoder-mock.t100644001750001750 520015234670244 21554 0ustar00silverdirksilverdirk000000000000Data-TableReader-0.022/t#! /usr/bin/env perl use strict; use warnings; use Test::More; use Log::Any '$log'; use Log::Any::Adapter 'TAP'; use Data::TableReader::Decoder::Mock; my $log_fn= sub { $log->can($_[0])->($log, $_[1]) }; sub table1 { [ [ 'a', 'b', 'c' ], [ 1, 2, 3 ], [ 4, 5, 6 ] ] }; sub table2 { [ [ 'x', 'y', 'z' ], [ 9, 8, 7 ], [ 6, 5, 4 ] ] }; subtest one_table => sub { my $expected= table1; my $d= new_ok( 'Data::TableReader::Decoder::Mock', [ table => table1, _log => $log_fn, file_name => undef, file_handle => undef ], 'new decoder' ); ok( my $iter= $d->iterator, 'got iterator' ); is( $iter->row, 0, 'row=0' ); is( $iter->dataset_idx, 0, 'dataset_idx=0' ); is_deeply( $iter->(), $expected->[0], 'first row' ); is( $iter->row, 1, 'row=1' ); is( $iter->dataset_idx, 0, 'dataset_idx=0' ); is_deeply( $iter->(), $expected->[1], 'second row' ); is( $iter->row, 2, 'row=2' ); is( $iter->dataset_idx, 0, 'dataset_idx=0' ); is_deeply( $iter->(), $expected->[2], 'third row' ); is( $iter->row, 3, 'row=3' ); is_deeply( $iter->(), undef, 'no fourth row' ); is( $iter->row, 3, 'row=3' ); is( $iter->dataset_idx, 0, 'dataset_idx=0' ); ok( $iter->seek(0), 'rewind' ); is( $iter->row, 0, 'row=0' ); is_deeply( $iter->(), $expected->[0], 'first row again' ); is( $iter->row, 1, 'row=1' ); is_deeply( $iter->([2,1]), [ '3', '2' ], 'slice from second row' ); ok( !$iter->next_dataset, 'no next dataset' ); is( $iter->dataset_idx, 0, 'dataset_idx=0' ); }; subtest empty_table => sub { my $datasets= [ [], [] ]; my $d= new_ok( 'Data::TableReader::Decoder::Mock', [ datasets => $datasets, _log => $log_fn, file_name => undef, file_handle => undef ], 'new decoder' ); ok( my $iter= $d->iterator, 'iterator' ); is( $iter->row, 0, 'row=0' ); is( $iter->dataset_idx, 0, 'dataset_idx=0' ); is( $iter->(), undef, 'eof' ); is( $iter->row, 0, 'row=0' ); ok( $iter->next_dataset, 'next_dataset' ); is( $iter->row, 0, 'row=0' ); is( $iter->dataset_idx, 1, 'dataset_idx=1' ); is( $iter->(), undef, 'eof' ); is( $iter->row, 0, 'row=0' ); ok( !$iter->next_dataset, 'no next_dataset' ); is_deeply( $datasets, [ [], [] ], 'backing data unchanged' ); }; subtest no_datasets => sub { my $datasets= []; my $d= new_ok( 'Data::TableReader::Decoder::Mock', [ datasets => $datasets, _log => $log_fn, file_name => undef, file_handle => undef ], 'new decoder' ); ok( my $iter= $d->iterator, 'iterator' ); is( $iter->row, 0, 'row=0' ); is( $iter->dataset_idx, 0, 'dataset_idx=0' ); is( $iter->(), undef, 'eof' ); is( $iter->row, 0, 'row=0' ); ok( !$iter->next_dataset, 'no next_dataset' ); is_deeply( $datasets, [], 'backing data unchanged' ); }; done_testing; 40-locate-table.t100644001750001750 3675115234670244 21606 0ustar00silverdirksilverdirk000000000000Data-TableReader-0.022/t#! /usr/bin/env perl use strict; use warnings; use Test::More; use File::Spec::Functions 'catfile'; use Log::Any '$log'; use Log::Any::Adapter 'TAP', filter => 'warn'; use Scalar::Util 'refaddr'; use_ok( 'Data::TableReader' ) or BAIL_OUT; # Find fields in the exact order they are present in the file sub mock_data { [ [ [ qw( Name Address City State Zip ) ], [ 'Someone', '123 Long St', 'Somewhere', 'OH', '45678' ], [ ('')x5 ], [ 'Another', '01 Main St', 'Elsewhere', 'OH', '45678' ], ], [ [ 'Zip Codes','', '', '','Cities', '','','', 'State Postal Codes','','' ], [ 'Zip', 'Lat','Lon', '','with population > 1,000,000','','','', 'State','PostCode','Country'], [ '45001', '39.138752','-84.709618', '','City', 'State', 'Population','', 'Alberta','AB','CA'], [ '45002', '39.182833','-84.723477', '','New York City','New York', '8,550,405','', 'Alaska','AK','US' ], [ '45003', '39.588296','-84.786326', '','Los Angeles', 'California','3,971,883','', 'Alabama','AL','US' ], [ '','','', '','Chicago', 'Illinois', '2,720,546','', 'Arkansas','AR','US' ], [ '','','', '','Houston', 'Texas', '2,296,224','', 'American Samoa','AS','US' ], ] ] } subtest basic => sub { my $ex= new_ok( 'Data::TableReader', [ input => mock_data(), fields => [ { name => 'name' }, { name => 'address' }, { name => 'city' }, { name => 'state' }, { name => 'zip' }, ], log => \my @messages, ], 'TableReader' ); ok( $ex->find_table, 'found table' ) or diag explain \@messages; is_deeply( $ex->col_map, $ex->fields, 'col map' ); is_deeply( $ex->field_map, { name => 0, address => 1, city => 2, state => 3, zip => 4 }, 'field map' ); is( $ex->table_search_results->{found}, $ex->table_search_results->{candidates}[0], 'search results' ); is( $ex->table_search_results->{found}{row_idx}, 0, 'found row_idx' ); is( $ex->table_search_results->{found}{dataset_idx}, 0, 'found dataset_idx' ); ok( my $i= $ex->iterator, 'iterator' ); is_deeply( $i->(), { name => 'Someone', address => '123 Long St', city => 'Somewhere', state => 'OH', zip => '45678' }, 'first row' ); is_deeply( $i->(), { name => 'Another', address => '01 Main St', city => 'Elsewhere', state => 'OH', zip => '45678' }, 'third row' ); is( $i->(), undef, 'eof' ); }; subtest find_on_second_sheet => sub { my $ex= new_ok( 'Data::TableReader', [ input => mock_data(), fields => [ { name => 'postcode' }, { name => 'country' }, { name => 'state' }, ], log => \my @messages, ], 'TableReader' ); ok( $ex->find_table, 'found table' ) or diag explain \@messages; ok( my $i= $ex->iterator, 'iterator' ); is_deeply( $i->(), { state => 'Alberta', postcode => 'AB', country => 'CA' }, 'row 1' ); is_deeply( $i->(), { state => 'Alaska', postcode => 'AK', country => 'US' }, 'row 2' ); is_deeply( $i->(), { state => 'Alabama', postcode => 'AL', country => 'US' }, 'row 3' ); is_deeply( $i->(), { state => 'Arkansas',postcode => 'AR', country => 'US' }, 'row 4' ); is_deeply( $i->(), { state => 'American Samoa', postcode => 'AS', country => 'US' }, 'row 5' ); is( $i->(), undef, 'eof' ); }; subtest find_required => sub { my $ex= new_ok( 'Data::TableReader', [ input => [ [qw( q w e r t y )], [qw( q w e r t a s d )], ], fields => [ { name => 'q', required => 1 }, { name => 'w', required => 1 }, { name => 'a', required => 0 }, { name => 'b', required => 0 }, { name => 'y', required => 0 }, { name => 's', required => 1 }, ], log => \my @messages, ], 'TableReader' ); ok( $ex->find_table, 'found table' ) or diag explain \@messages; is_deeply( $ex->field_map, { q => 0, w => 1, a => 5, s => 6 }, 'field_map' ); is_deeply( $ex->iterator->all(), [], 'immediate eof' ); }; subtest multiline_header => sub { my $ex= new_ok( 'Data::TableReader', [ input => [ [qw( a b c )], [qw( d e f )], [qw( g b c )], [qw( A B C )], ], fields => [ { name => 'a', header => "d g" }, { name => 'b', header => "b\ne\nb" }, { name => 'c', header => qr/f\nc$/ }, ], log => \my @messages, ], 'TableReader' ); is( $ex->header_row_combine, 3, 'header_row_combine' ); ok( $ex->find_table, 'found table' ) or diag explain \@messages; is_deeply( $ex->field_map, { a => 0, b => 1, c => 2 }, 'field_map' ); is_deeply( $ex->iterator->all(), [{a=>'A',b=>'B',c=>'C'}], 'found row' ); }; subtest multi_column => sub { my $ex= new_ok( 'Data::TableReader', [ input => [ [qw( a b a c a d )], [qw( 1 2 3 4 5 6 )], ], fields => [ { name => 'a', header => qr/a|c/, array => 1 }, { name => 'd' }, ], log => \my @messages, ], 'TableReader' ); ok( $ex->find_table, 'found table' ) or diag explain \@messages; is_deeply( $ex->field_map, { a => [0,2,3,4], d => 5 }, 'field_map' ); is_deeply( $ex->iterator->all(), [{a => [1,3,4,5], d => 6}], 'rows' ); }; subtest array_at_end => sub { my $ex= new_ok( 'Data::TableReader', [ input => [ [qw( a b c ),'','','','',''], [qw( 1 2 3 4 5 6 7 8 9 )], [qw( 1 2 3 4 5 6 7 8 9 10 11 12 13 )], [qw( 1 2 3 4 )], ], fields => [ 'a', { name => 'c', array => 1 }, { name => 'c', array => 1, header => '', follows => 'c' }, ], log => \my @messages, ], 'TableReader' ); ok( $ex->find_table, 'found table' ) or diag explain \@messages; is_deeply( $ex->field_map, { a => 0, c => [2,3,4,5,6,7] }, 'field_map' ); my $i= $ex->iterator; is_deeply( $i->(), { a => 1, c => [3,4,5,6,7,8] }, 'row1' ); is_deeply( $i->(), { a => 1, c => [3,4,5,6,7,8] }, 'row1' ); is_deeply( $i->(), { a => 1, c => [3,4,undef,undef,undef,undef] }, 'row1' ); is( $i->(), undef, 'eof' ); }; subtest multiple_arrays => sub { my $ex= new_ok( 'Data::TableReader', [ input => [ [qw( a b b b c d d d e )], [qw( 1 2 3 4 5 6 7 8 9 )], ], fields => [ 'a', { name => 'b', array => 1 }, 'c', { name => 'd', array => 1 }, 'e', ], log => \my @messages, ], 'TableReader' ); ok( $ex->find_table, 'found table' ) or diag explain \@messages; is_deeply( $ex->field_map, { a => 0, b => [1,2,3], c => 4, d => [5,6,7], e => 8 }, 'field_map' ); my $i= $ex->iterator; is_deeply( $i->(), { a => 1, b => [2,3,4], c => 5, d => [6,7,8], e => 9 }, 'row1' ); is( $i->(), undef, 'eof' ); }; subtest discontinuous_array => sub { my $ex= new_ok( 'Data::TableReader', [ input => [ [qw( a b b b c b b e )], [qw( 1 2 3 4 5 6 7 8 )], ], fields => [ 'a', { name => 'b', array => 1 }, 'c', 'e', ], log => \my @messages, ], 'TableReader' ); ok( $ex->find_table, 'found table' ) or diag explain \@messages; is_deeply( $ex->field_map, { a => 0, b => [1,2,3,5,6], c => 4, e => 7 }, 'field_map' ); my $i= $ex->iterator; is_deeply( $i->(), { a => 1, b => [2,3,4,6,7], c => 5, e => 8 }, 'row1' ); is( $i->(), undef, 'eof' ); }; subtest complex_follows => sub { my $ex= new_ok( 'Data::TableReader', [ input => [ ['name', 'start coords','','','','end coords','','','',''], ['', 'x', 'y', 'w', 'h', 'x','y','w','h'], ['foo', '1', '1', '6', '6', '2','2','8','8'], ], fields => [ 'name', { name => 'start_x', header => qr/start.*\nx/ }, { name => 'start_y', header => 'y', follows => 'start_x' }, { name => 'end_x', header => qr/end.*\nx/ }, { name => 'end_y', header => 'y', follows => 'end_x' } ], log => \my @messages, ], 'TableReader' ); ok( $ex->find_table, 'found table' ) or diag explain \@messages; is_deeply( $ex->field_map, { name => 0, start_x => 1, start_y => 2, end_x => 5, end_y => 6 }, 'field_map' ); my $i= $ex->iterator; is_deeply( $i->(), { name => 'foo', start_x => 1, start_y => 1, end_x => 2, end_y => 2 }, 'row1' ); is( $i->(), undef, 'eof' ); }; subtest col_map_lazy_search => sub { my $ex= new_ok( 'Data::TableReader', [ input => [ [qw( a b c )], ], fields => [qw( a b c )], log => \my @messages, ], 'TableReader' ); ok( !$ex->has_table_search_results, 'search has not run yet' ); ok( !$ex->has_col_map, 'no col_map yet' ); is_deeply( $ex->col_map, $ex->fields, 'reading col_map lazily detects the table', ); ok( $ex->has_table_search_results, 'lazy read populated search results' ); ok( $ex->has_col_map, 'derived col_map now exists' ); }; subtest supplied_col_map_survives_search_clear => sub { my $base_map= [ undef, 'b', undef ]; my $ex= new_ok( 'Data::TableReader', [ input => [ [qw( a b c )], ], fields => [qw( a b c )], col_map => $base_map, log => \my @messages, ], 'TableReader' ); ok( $ex->find_table, 'found table' ) or diag explain \@messages; is_deeply( [ map defined()? $_->name : undef, @{$ex->col_map} ], [qw( a b c )], 'effective col_map includes detected fields', ); $ex->clear_table_search_results; is_deeply( [ map defined()? $_->name : undef, @{$ex->col_map} ], [ undef, 'b', undef ], 'clearing search results restores supplied col_map', ); ok( !$ex->has_table_search_results, 'reading a supplied col_map does not rerun table search', ); }; subtest col_map_setter_does_not_modify_caller => sub { my $ex= new_ok( 'Data::TableReader', [ input => [ [qw( a b )], ], fields => [qw( a b )], log => \my @messages, ], 'TableReader' ); my $map= [ 'a', undef ]; $ex->col_map($map); is_deeply( $map, [ 'a', undef ], 'col_map setter does not modify caller array', ); ok( ref($ex->col_map->[0]), 'stored col_map resolves names to Field objects', ); $map->[1]= 'changed'; is( $ex->col_map->[1], undef, 'modifying caller array does not modify stored col_map', ); }; subtest col_map_re_resolves_after_fields_change => sub { my $ex= new_ok( 'Data::TableReader', [ input => [ [qw( a )], ], fields => [qw( a )], col_map => [ 'a' ], log => \my @messages, ], 'TableReader' ); my $old_field= $ex->col_map->[0]; $ex->fields([ 'a' ]); my $new_field= $ex->col_map->[0]; is( $new_field, $ex->fields->[0], 'col_map resolves to the replacement Field object', ); isnt( refaddr($new_field), refaddr($old_field), 'col_map does not retain stale Field object', ); }; subtest repeated_find_uses_supplied_col_map => sub { my $ex= new_ok( 'Data::TableReader', [ input => [ [qw( a b )], ], fields => [qw( a b )], static_field_order => 1, log => \my @messages, ], 'TableReader' ); ok( $ex->find_table, 'initial search succeeds' ) or diag explain \@messages; is_deeply( [ map $_->name, @{$ex->col_map} ], [qw( a b )], 'initial derived map', ); $ex->col_map([qw( b a )]); @messages= (); ok( !$ex->find_table, 'second search uses newly supplied map, not previous result', ); like( join("\n", map $_->[1], @messages), qr/Header at column 1 does not look like field b/, 'failure describes supplied map mismatch', ); }; subtest headerless_requires_static_order => sub { my $ex= new_ok( 'Data::TableReader', [ input => [ [qw( 1 2 )], ], fields => [qw( a b )], header_row_at => undef, static_field_order => 0, log => \my @messages, ], 'TableReader' ); my ($result, $exception); { local $@; eval { $result= $ex->find_table; 1; } or $exception= $@; } is( $exception, undef, 'find_table does not die' ); ok( !$result, 'find_table reports failure' ); is( $ex->table_search_results->{fatal}, "You must enable 'static_field_order' if there is no header row", 'failure reason is retained in search results', ); }; subtest headerless_with_static_order => sub { my $ex= new_ok( 'Data::TableReader', [ input => [ [qw( 1 2 )], ], fields => [qw( a b )], header_row_at => undef, static_field_order => 1, log => \my @messages, ], 'TableReader' ); ok( $ex->find_table, 'headerless table accepted in static mode' ) or diag explain \@messages; is_deeply( [ map $_->name, @{$ex->col_map} ], [qw( a b )], 'fields become the headerless col_map', ); is( $ex->table_search_results->{found}{row_idx}, -1, 'headerless result uses row_idx -1', ); is( $ex->table_search_results->{found}{row}, undef, 'headerless result has no header row number', ); }; subtest static_header_error_uses_one_based_column => sub { my $ex= new_ok( 'Data::TableReader', [ input => [ [qw( a wrong )], ], fields => [qw( a b )], static_field_order => 1, log => \my @messages, ], 'TableReader' ); ok( !$ex->find_table, 'header mismatch fails search' ); my $candidate= $ex->table_search_results->{candidates}[0]; like( join("\n", map $_->[1], @{$candidate->{messages}}), qr/Header at column 2 does not look like field b/, 'static mismatch reports a one-based column number', ); }; subtest undefined_header_cells => sub { my $ex= new_ok( 'Data::TableReader', [ input => [ [ undef, 'a' ], ], fields => [ 'a' ], on_unknown_columns => 'warn', log => \my @messages, ], 'TableReader' ); my ($result, $exception); { local $@; eval { $result= $ex->find_table; 1; } or $exception= $@; } is( $exception, undef, 'undefined header cell does not die' ); ok( $result, 'table is still detected' ); is_deeply( $ex->field_map, { a => 1 }, 'defined header is mapped normally', ); like( join("\n", map $_->[1], @messages), qr/Ignoring unknown columns: /, 'undefined header is formatted safely', ); }; subtest on_partial_match_callback_arguments => sub { my @callback_args; my $ex= new_ok( 'Data::TableReader', [ input => [ [ 'a', 'not-b' ], [ 'a', 'b' ], ], fields => [ { name => 'a', required => 1 }, { name => 'b', required => 1 }, ], on_partial_match => sub { @callback_args= @_; return 'next'; }, log => \my @messages, ], 'TableReader' ); ok( $ex->find_table, 'search continues after partial match' ) or diag explain \@messages; is( $callback_args[0], $ex, 'callback receives reader' ); is( ref($callback_args[1]), 'HASH', 'callback receives candidate hashref', ); is( $callback_args[1]{row}, 1, 'candidate describes partial row', ); is_deeply( $callback_args[2], [ 'a', 'not-b' ], 'callback receives header row arrayref', ); is( $ex->table_search_results->{found}{row}, 2, 'second row is selected', ); }; subtest on_unknown_columns_callback_arguments => sub { my @callback_args; my $ex= new_ok( 'Data::TableReader', [ input => [ [qw( a extra )], ], fields => [ 'a' ], on_unknown_columns => sub { @callback_args= @_; return 'warn'; }, log => \my @messages, ], 'TableReader' ); ok( $ex->find_table, 'callback permits unknown column' ) or diag explain \@messages; is( $callback_args[0], $ex, 'callback receives reader' ); is_deeply( $callback_args[1], [qw( a extra )], 'callback receives headers arrayref', ); is_deeply( $callback_args[2], [1], 'callback receives unmatched indices arrayref', ); is( ref($callback_args[3]), 'HASH', 'callback receives candidate hashref', ); is( $callback_args[3]{row}, 1, 'candidate contains row information', ); }; subtest empty_fields_fail_at_find_table => sub { my $ex= new_ok( 'Data::TableReader', [ input => [ [qw( a b )], ], fields => [], log => \my @messages, ], 'TableReader' ); my ($result, $exception); { local $@; eval { $result= $ex->find_table; 1; } or $exception= $@; } like( $exception, qr/No fields/, 'empty fields cause an exception' ); ok( !$ex->has_table_search_results, 'empty fields do not identify a table' ); is( $ex->header_row_combine, 0, 'empty fields produce zero header rows to combine', ); }; done_testing; 35-record-iterator.t100644001750001750 1436015234670244 22353 0ustar00silverdirksilverdirk000000000000Data-TableReader-0.022/t#! /usr/bin/env perl use strict; use warnings; use Test::More; use Log::Any '$log'; use Log::Any::Adapter 'TAP'; use_ok( 'Data::TableReader' ) or BAIL_OUT; subtest trim_options => sub { my $re= new_ok( 'Data::TableReader', [ input => [ [ [qw( trim retrim codetrim notrim )], [ ' abc ', ' abc ', ' abc ', ' abc ' ], ], ], fields => [ { name => 'notrim', trim => 0 }, { name => 'trim', trim => 1 }, { name => 'retrim', trim => qr/a/ }, { name => 'codetrim', trim => sub { s/b//ig } }, ], log => $log ], 'TableReader' ); ok( $re->find_table, 'find_table' ) or die "Can't continue without table"; ok( my $i= $re->iterator, 'create iterator' ); is( $i->dataset_idx, 0, 'dataset_idx=0' ); is( $i->row, 1, 'row=1' ); is_deeply( $i->all, [ { trim => 'abc', retrim => ' bc ', codetrim => ' ac ', notrim => ' abc ' } ], 'values' ); is( $i->row, 2, 'row=2' ); }; subtest multiple_iterator => sub { my $re= new_ok( 'Data::TableReader', [ input => [ [ [qw( a b c )], [qw( 1 2 3 )], ] ], fields => ['a','b','c'], log => $log ], 'TableReader' ); ok( $re->find_table, 'find_table' ) or die "Can't continue without table"; ok( my $i= $re->iterator, 'create iterator' ); Scalar::Util::weaken( my $wref= $i ); undef $i; is( $wref, undef, 'first iterator garbage collected' ); ok( my $i2= $re->iterator, 'second interator' ); ok( my $i3= $re->iterator, 'third iterator' ); is( $i2->row, 1, 'i2 row=1' ); is( $i3->row, 1, 'i3 row=1' ); is_deeply( $i2->all, [ { a => 1, b => 2, c => 3 } ], 'read rows from i2' ); is( $i3->row, 1, 'i3 row=1' ); is_deeply( $i3->all, [ { a => 1, b => 2, c => 3 } ], 'read rows from i3' ); }; subtest record_class_array => sub { my $re= new_ok( 'Data::TableReader', [ input => [ [ [qw( c b a b )], [qw( 1 2 3 4 )], [qw( 5 6 7 ),''], ] ], fields => [ 'a', Data::TableReader::Field->new(name => 'b', array => 1), 'c', { name => 'd', required => 0 }, ], record_class => 'ARRAY', log => \my @messages, ], 'TableReader' ); ok( $re->find_table, 'find_table' ) or note explain \@messages; ok( my $i= $re->iterator, 'create iterator' ); is_deeply( $i->(), [ 3, [2,4], 1, undef ], 'row 1' ); is_deeply( $i->(), [ 7, [6, undef], 5, undef ], 'row 2' ); is( $i->(), undef, 'eof' ); }; subtest iterator_all_keeps_false_objects => sub { { package Local::FalseRecord; use overload 'bool' => sub { 0 }, fallback => 1; sub new { my ($class, $data)= @_; return bless $data, $class; } } my $re= new_ok( 'Data::TableReader', [ input => [ [ [qw( a )], [1], [2], ] ], fields => ['a'], record_class => 'Local::FalseRecord', log => $log, ], 'TableReader' ); ok( $re->find_table, 'find_table' ) or die "Can't continue without table"; my $records= $re->iterator->all; is( scalar @$records, 2, 'all returns false-overloaded records' ); isa_ok( $records->[0], 'Local::FalseRecord' ); isa_ok( $records->[1], 'Local::FalseRecord' ); is( $records->[0]{a}, 1, 'first record value' ); is( $records->[1]{a}, 2, 'second record value' ); }; subtest iterator_tell_seek => sub { my $re= new_ok( 'Data::TableReader', [ input => [ [ [qw( a b )], [qw( 1 2 )], [qw( 3 4 )], [qw( 5 6 )], ] ], fields => [qw( a b )], log => $log, ], 'TableReader' ); ok( $re->find_table, 'find_table' ) or die "Can't continue without table"; ok( my $i= $re->iterator, 'create iterator' ); is_deeply( $i->(), { a => 1, b => 2 }, 'read first row' ); my $state= $i->tell; is( ref $state, 'ARRAY', 'tell returns arrayref' ); is( scalar @$state, 4, 'tell returns complete iterator state' ); is_deeply( $i->(), { a => 3, b => 4 }, 'read second row' ); is( $i->seek($state), $i, 'seek returns iterator' ); is_deeply( $i->(), { a => 3, b => 4 }, 'seek restores position before second row', ); is_deeply( $i->(), { a => 5, b => 6 }, 'continues after restored row' ); is( $i->(), undef, 'eof' ); }; subtest iterator_seek_after_eof => sub { my $re= new_ok( 'Data::TableReader', [ input => [ [ [qw( a )], [1], [2], ] ], fields => ['a'], log => $log, ], 'TableReader' ); ok( $re->find_table, 'find_table' ) or die "Can't continue without table"; ok( my $i= $re->iterator, 'create iterator' ); my $start= $i->tell; is_deeply( $i->(), { a => 1 }, 'first row' ); is_deeply( $i->(), { a => 2 }, 'second row' ); is( $i->(), undef, 'reached eof' ); is( $i->(), undef, 'eof remains stable' ); $i->seek($start); is_deeply( $i->(), { a => 1 }, 'seek after eof resets closure eof state', ); is_deeply( $i->(), { a => 2 }, 'second row after rewind' ); is( $i->(), undef, 'eof after rewind' ); }; subtest iterator_seek_preserves_blank_row_state => sub { my $re= new_ok( 'Data::TableReader', [ input => [ [ [qw( a )], [1], [''], [''], [2], ] ], fields => ['a'], on_blank_row => 'next', log => \my @messages, ], 'TableReader' ); ok( $re->find_table, 'find_table' ) or die "Can't continue without table"; ok( my $i= $re->iterator, 'create iterator' ); is_deeply( $i->(), { a => 1 }, 'first row' ); my $before_blanks= $i->tell; is_deeply( $i->(), { a => 2 }, 'blank rows skipped before second row' ); like( join("\n", map $_->[1], @messages), qr/Skipping blank rows from 3 until 4/, 'blank row warning emitted', ); @messages= (); $i->seek($before_blanks); is_deeply( $i->(), { a => 2 }, 'seek restores blank-row tracking state', ); like( join("\n", map $_->[1], @messages), qr/Skipping blank rows from 3 until 4/, 'blank row warning is correct after seek', ); }; subtest iterator_seek_rejects_invalid_state => sub { my $re= new_ok( 'Data::TableReader', [ input => [ [ [qw( a )], [1], ] ], fields => ['a'], log => $log, ], 'TableReader' ); ok( $re->find_table, 'find_table' ) or die "Can't continue without table"; my $i= $re->iterator; for my $bad_state ( undef, 'not an arrayref', [], [1], [1, 2, 3], [1, 2, 3, 4, 5], ) { my $ok= eval { $i->seek($bad_state); 1; }; ok( !$ok, 'invalid seek state rejected' ); like( $@, qr/Expected arrayref of 4 elements/, 'useful invalid-state error', ); } }; done_testing; author000755001750001750 015234670244 20142 5ustar00silverdirksilverdirk000000000000Data-TableReader-0.022/xtpod-syntax.t100644001750001750 25215234670244 22554 0ustar00silverdirksilverdirk000000000000Data-TableReader-0.022/xt/author#!perl # This file was automatically generated by Dist::Zilla::Plugin::PodSyntaxTests. use strict; use warnings; use Test::More; use Test::Pod 1.41; all_pod_files_ok(); Data000755001750001750 015234670244 17624 5ustar00silverdirksilverdirk000000000000Data-TableReader-0.022/libTableReader.pm100644001750001750 17762015234670244 22551 0ustar00silverdirksilverdirk000000000000Data-TableReader-0.022/lib/Datapackage Data::TableReader; use Moo 2; use Carp; use Scalar::Util qw( blessed refaddr ); use List::Util 'max'; use Module::Runtime 'require_module'; use Data::TableReader::Field; use Data::TableReader::Iterator; use Encode (); use namespace::clean; # ABSTRACT: Extract records from "dirty" tabular data sources our $VERSION = '0.022'; # VERSION has input => ( is => 'rw', required => 1 ); has _file_handle => ( is => 'lazy' ); has _real_file_name => ( is => 'rw', lazy => 1, builder => 1 ); has _client_file_name => ( is => 'rw', lazy => 1, builder => 1 ); has _decoder_arg => ( is => 'rw', init_arg => 'decoder' ); has decoder => ( is => 'lazy', init_arg => undef ); has fields => ( is => 'rw', required => 1, coerce => \&_coerce_field_list, trigger => \&_update_fields ); sub field_list { @{ shift->fields } } has field_by_name => ( is => 'lazy', clearer => 1 ); has field_by_addr => ( is => 'lazy', clearer => 1 ); has record_class => ( is => 'rw', required => 1, default => sub { 'HASH' } ); has static_field_order => ( is => 'rw' ); # force order of columns has header_row_at => ( is => 'rw', default => sub { [1,10] } ); # row of header, or range to scan has header_row_combine => ( is => 'rw', lazy => 1, builder => 1, clearer => 1 ); has table_search_results=> ( is => 'rw', lazy => 1, builder => 1, clearer => 1, predicate => 1 ); has col_map => ( is => 'rw', reader => '_get_col_map', writer => '_set_col_map' ); has on_partial_match => ( is => 'rw', default => sub { 'next' } ); has on_ambiguous_columns=> ( is => 'rw', default => sub { 'error' } ); has on_unknown_columns => ( is => 'rw', default => sub { 'warn' } ); has on_blank_row => ( is => 'rw', default => sub { 'next' } ); has on_validation_error => ( is => 'rw', default => sub { 'die' } ); has log => ( is => 'rw', trigger => sub { shift->_clear_log } ); sub _update_fields { my $self= shift; # clear derived attributes $self->clear_field_by_name; $self->clear_field_by_addr; $self->clear_header_row_combine; $self->clear_table_search_results; } sub BUILD { my ($self, $args)= @_; # Back-compat for previous API if (defined (my $act= $args->{on_validation_fail})) { croak "on_validation_fail (back-compat alias) conflicts with on_validation_error" if defined $args->{on_validation_error}; $self->on_validation_fail($act); } } sub on_validation_fail { my $self= shift; if (@_) { my $act= shift; #warn "on_validation_fail is deprecated (see on_validation_error)"; # adapt for the old API $act= _wrap_on_validation_fail($act) if ref $act eq 'CODE'; return $self->on_validation_error($act); } return $self->on_validation_error; } # Modifies array to replace name with field ref sub _resolve_colmap_names { my ($self, $col_map)= @_; for (grep defined, @$col_map) { my $name= ref $_ && ref($_)->can('name')? $_->name : "$_"; defined(my $f= $self->field_by_name->{$name}) or croak("col_map specifies non-existent field '$name'"); $_= $f; } $col_map; } # Only consider it a "client"-facing filename if we have a definite method that # tells us this is true. sub _build__client_file_name { my $self= shift; my $i= $self->input; if (my $cls= blessed($i)) { # All major framework upload objects have this attribute in common return $i->filename if $i->can('filename') && $cls =~ /::Upload/; } return undef; } sub _build__real_file_name { my $self= shift; my $i= $self->input; if (my $cls= blessed($i)) { return $i->filename if $cls->isa('File::Temp'); # Path::Tiny, Class::Path::File, etc. require overload; return "$i" if $cls =~ /File|Path/ && overload::Method($i, q{""}); # Support for Catalyst::Request::Upload, Dancer::Request::Upload, # and Dancer2::Core::Request::Upload, all of which have 'tempname'. return '' . $i->tempname if $i->can('tempname') && defined $i->tempname; # Mojo::Upload needs to refer to the asset if ($cls->isa('Mojo::Upload')) { $i= $i->asset; $cls= blessed($i); } return '' . $i->path if ($cls->isa('Plack::Request::Upload') || $cls->isa('Mojo::Asset::File')) && defined $i->path; } # plain scalars default to being the filename return ref $i? undef : $i; } # Open 'input' if it isn't already a file handle sub _build__file_handle { my $self= shift; my $i= $self->input; if (ref $i) { my $cls= blessed($i) || ''; return $i if ref $i eq 'GLOB' # file handle or $cls && $i->can('read') && $i->can('eof'); # IO::Handle-ish object # When supplied a spreadsheet object, no handle is needed return undef if ref $i eq 'ARRAY' or $cls && ($i->can('get_cell') || $i->can('worksheets')); # Support web framework upload objects if ($cls =~ /::Upload/) { # Support for Catalyst::Request::Upload, Dancer::Request::Upload, # and Dancer2::Core::Request::Upload, all of which have 'tempname'. if ($i->can('tempname') && defined $i->tempname) { $i= '' . $i->tempname; $cls= ''; } # Support Mojo::Upload elsif ($cls->isa('Mojo::Upload')) { $i= $i->asset; # change input to the Mojo::Asset $cls= blessed($i); } # Support for Plack::Request::Upload elsif ($cls->isa('Plack::Request::Upload')) { $i= '' . $i->path; $cls= ''; } } # Support for Mojo::Asset if ($cls && $cls->isa('Mojo::Asset')) { return $i->handle if $cls->isa('Mojo::Asset::File'); my $str= $i->slurp; $i= \$str; } } open(my $fh, '<', $i) or croak "open($i): $!"; binmode $fh; # This attempt to open $i was more permissive than the rules that build _real_file_name, # so if open() succeeded, update that attribute with the thing we successfully opened. # ...unless it was a scalar-ref. $self->_real_file_name($i) unless ref $i; return $fh; } # Create ::Decoder instance either from user-supplied args, or by detecting input format sub _build_decoder { my $self= shift; my $decoder_arg= $self->_decoder_arg; my $decoder_ref= ref $decoder_arg; my ($class, @args); if (!$decoder_arg) { ($class, @args)= $self->detect_input_format; croak "Can't determine file format" unless defined $class; $self->_log->('trace', "Detected input format as %s", $class); } elsif (!$decoder_ref) { $class= $decoder_arg; } elsif ($decoder_ref eq "HASH" or $decoder_ref eq "ARRAY") { ($class, @args)= $decoder_ref eq "ARRAY"? @$decoder_arg : do { my %tmp= %$decoder_arg; (delete($tmp{CLASS}), %tmp); }; if(!$class) { my ($input_class, @input_args)= $self->detect_input_format; croak "decoder class not specified in arguments, and unable to identify decoder class from input" unless $input_class; ($class, @args)= ($input_class, @input_args, @args); } } elsif ($decoder_ref->can('iterator')) { return $decoder_arg; } else { croak "Can't create decoder from $decoder_ref"; } $class= "Data::TableReader::Decoder::$class" unless $class =~ /::/; require_module($class); $self->_log->('trace', 'Creating decoder %s on input %s', $class, $self->input); return $class->new( file_handle => $self->_file_handle, real_file_name => $self->_real_file_name, client_file_name => $self->_client_file_name, _log => $self->_log, @args ); } # User supplies any old perl data, but this field should always be an arrayref of ::Field sub _coerce_field_list { my ($list)= @_; defined $list and ref $list eq 'ARRAY' or croak "'fields' must be an arrayref"; my @list= @$list; # clone it, to make sure we don't unexpectedly alter the caller's data for (@list) { if (!ref $_) { $_= Data::TableReader::Field->new({ name => $_ }); } elsif (ref $_ eq 'HASH') { my %args= %$_; # "isa" alias for the 'type' attribute $args{type}= delete $args{isa} if defined $args{isa} && !defined $args{type}; $_= Data::TableReader::Field->new(\%args) } else { croak "Can't coerce '$_' to a Field object" unless blessed($_) && $_->isa('Data::TableReader::Field'); } } return \@list; } sub _build_field_by_name { my $self= shift; # reverse list so first field of a name takes precedence return { map +( $_->name => $_ ), reverse @{ $self->fields } } } sub _build_field_by_addr { my $self= shift; return { map +( refaddr $_ => $_ ), @{ $self->fields } } } sub _build_header_row_combine { my $self= shift; # If headers contain "\n", we need to collect multiple cells per column # Find the maximum number of \n contained in any regex. max 0, map { 1+(()= ($_->header_regex =~ /\\n|\n/g)) } $self->field_list; } # 'log' can be a variety of things, but '_log' will always be a coderef has _log => ( is => 'lazy', clearer => 1 ); sub _build__log { _log_fn(shift->log); } sub _log_fn { my $dest= shift; !$dest? sub { my ($level, $msg, @args)= @_; return unless $level eq 'warn' or $level eq 'error'; $msg= sprintf($msg, @args) if @args; warn $msg."\n"; } : ref($dest) eq 'CODE'? sub { my ($level, $msg, @args)= @_; $msg= sprintf($msg, @args) if @args; $dest->($level, $msg); } : ref $dest eq 'ARRAY'? sub { my ($level, $msg, @args)= @_; return unless $level eq 'warn' or $level eq 'error'; $msg= sprintf($msg, @args) if @args; push @$dest, [ $level, $msg ]; } : ref($dest)->can('info')? sub { my ($level, $msg, @args)= @_; my $is_level= $dest->can('is_'.$level) or croak "Logger object lacks required 'is_$level' method"; # If it can("is_$level"), probably no sense wasting time checking for can($level) $dest->$level( @args? sprintf($msg, @args) : $msg ) if $is_level->($dest); } : croak "Don't know how to log to $dest"; } # Routine to lazily load first block of file sub _get_content_head { my ($self, $hints)= @_; unless (exists $hints->{content_head}) { my $fh= $self->_file_handle; if (!defined $fh) { # Decoder will be using something other than a file handle anyway $hints->{content_head}= undef; } # Need to be able to seek. elsif (seek($fh, 0, 1)) { my $fpos= tell $fh; defined read($fh, my $buf, 4096) or croak "read: $!"; defined seek($fh, $fpos, 0) or croak "seek: $!"; $hints->{content_head}= $buf; } elsif ($fh->can('ungets')) { defined read($fh, my $buf, 4096) or croak "read: $!"; $fh->ungets($buf); $hints->{content_head}= $buf; } else { $self->_log->('info',"Can't fully detect input format because handle is not seekable." ." Consider fully buffering the file, or using FileHandle::Unget"); $hints->{content_head}= undef; } } $hints->{content_head}; } sub _get_content_head_text { my ($self, $hints)= @_; unless (exists $hints->{content_head_text}) { my $text; if (defined $self->_get_content_head($hints)) { $self->detect_input_charset($hints) unless defined $hints->{charset}; $text= substr($hints->{content_head}, $hints->{content_ofs}||0); $text= Encode::decode($hints->{charset}, $text) if defined $hints->{charset}; } $hints->{content_head_text}= $text; } $hints->{content_head_text}; } our @_decoder_classes; our %_decoder_mime_types= ( 'text/csv' => 'CSV', 'text/tab-separated-values' => 'TSV', 'application/vnd.ms-excel' => 'XLS', 'application/vnd.openxmlformats-officedocument.spreadsheetml.sheet' => 'XLSX', # common nonstandard mime types, according to AI 'application/csv' => 'CSV', 'application/x-csv' => 'CSV', 'text/x-csv' => 'CSV', 'text/comma-separated-values' => 'CSV', 'text/x-comma-separated-values' => 'CSV', 'text/tsv' => 'TSV', 'application/tab-separated-values' => 'TSV', 'application/x-tsv' => 'TSV', 'text/x-tsv' => 'TSV', 'application/msexcel' => 'XLS', 'application/x-msexcel' => 'XLS', 'application/excel' => 'XLS', 'application/x-excel' => 'XLS', 'application/vnd.ms-office' => 'XLS', 'application/x-dos_ms_excel' => 'XLS', 'application/xlsx' => 'XLSX', 'application/x-xlsx' => 'XLSX', ); sub detect_input_format { my $self= shift; my $hints= @_ == 1 && ref $_[0] eq 'HASH'? $_[0] : { filename => $_[0], content_head => $_[1] }; my $input= $self->input; # this and all related routines want a lowercase content type $hints->{content_type}= lc($hints->{content_type}) if defined $hints->{content_type}; # As convenience to spreadsheet users, let input be a parsed workbook/worksheet object. return ('XLSX', sheet => $input) if ref($input) && ref($input)->can('get_cell'); return ('XLSX', workbook => $input) if ref($input) && ref($input)->can('worksheets'); # Convenience for passing already-parsed data as an array of arrays if (ref($input) eq 'ARRAY') { # if user supplied single table of data, wrap it in an array to make an array of tables. $input= [ $input ] if @$input && ref($input->[0]) eq 'ARRAY' && @{$input->[0]} && ref($input->[0][0]) ne 'ARRAY'; return ('Mock', datasets => $input); } my ($headers, $ct, $charset)= @{$hints}{qw( http_headers content_type charset )}; # Support for web framework upload objects if (!$headers && blessed($input) && $input->can('headers')) { # Catalyst and Plack have ->headers => HTTP::Headers, though in plack the ->headers is # not documented.... # Dancer & Dancer2 have ->headers => HASH # Mojo has ->headers => Mojo::Headers $headers= $input->headers; } # the full content-type header, where the user-supplied '$ct' may only be the portion before ';' my $full_ct= defined $ct && $ct =~ /;/ ? $ct : undef; if (!defined $full_ct && $headers) { # Dancer uses hashref of headers, case-normalized if (ref $headers eq 'HASH') { my $ct_key= defined $headers->{'Content-Type'}? 'Content-Type' : (grep /^content[-_]type\z/i, keys %$headers)[0]; $full_ct= $headers->{$ct_key} if $ct_key; } # HTTP::Headers object or Mojo::Headers object elsif (blessed($headers) && $headers->can('header')) { $full_ct= $headers->header('Content-Type'); } $full_ct= lc($full_ct) if defined $full_ct; } # Extract charset and content type from full content-type header. # But, don't if the user supplied a content-type value and it doesn't match the HTTP header. if (defined $full_ct && $full_ct =~ /^\s*([^;\s]+)/ && (!defined $ct || $ct eq $full_ct || $ct eq $1)) { $ct= $1; if (!defined $charset && $full_ct =~ /;\s*charset\s*=\s*(?:"((?:[^"\\]|\\.)*)"|([^;\s]+))/i) { # Could remove the '\\' escapes, but any value that has escapes will be an invalid # charset anyway. $charset= defined $1? $1 : $2; } } if (defined $charset) { if (my $enc= Encode::find_encoding($charset)) { $charset= $enc->name; } else { $self->_log->('warn', "Unknown character encoding '$charset'"); undef $charset; } } # Trust the content type if (defined $ct && length $ct) { my $class= $_decoder_mime_types{$ct}; if ($class) { my @args; ($class, @args)= @$class if ref $class eq 'ARRAY'; if ($class eq 'CSV' || $class eq 'TSV' || $class eq 'HTML') { # Use the MIME declared charset to read the stream. If the content type wasn't # declared, it is up to the module to detect something appropriate. push @args, encoding => $charset if defined $charset; } return ($class, @args); } else { $self->_log->('warn', "Unknown content type '$ct'"); } } @{$hints}{qw( http_headers content_type charset )}= ($headers, $ct, $charset); # Consult any registered decoders first for my $cls (grep $_->can('detect_input_format'), @_decoder_classes) { my @answer= $cls->detect_input_format($self, $hints); return @answer if @answer; } # Lacking a content-type, fall back to probing the contents of the file. my $content_head= $self->_get_content_head($hints); # Excel is obvious so check it first. This handles cases where an excel file is # erroneously named ".csv" and silliness like that. if (defined $content_head) { return ( 'XLSX' ) if $content_head =~ /^PK(\x03\x04|\x05\x06|\x07\x08)/; return ( 'XLS' ) if $content_head =~ /^\xD0\xCF\x11\xE0/; } # Remaining options are CSV, TSV, and HTML. Trust the file extension, because TSV with # commas can be very similar to CSV with tabs in the data, and some crazy person might store # an HTML document as the first element of a CSV file. # Detect filename if not supplied $hints->{filename}= $self->_client_file_name unless defined $hints->{filename}; $hints->{filename}= $self->_real_file_name unless defined $hints->{filename}; if (defined $hints->{filename} && $hints->{filename} =~ /\.( csv (?{"CSV"}) | tsv (?{"TSV"}) | html? (?{"HTML"}) )\z/xi) { return ($^R, defined $charset? (encoding => $charset) : ()); } # Try to decide between CSV or TSV or HTML based on content alone. # To do this, we also have to guess the content-type if it wasn't supplied. if (defined $content_head && length $content_head) { $self->_log->('debug',"Probing file format because no known filename suffix"); } else { my $reason= defined $content_head? "empty file" : "unseekable file handle"; $self->_log->('debug',"Can't probe $reason"); return (); } $charset= $self->detect_input_charset($hints) unless defined $charset; my $text= $self->_get_content_head_text($hints); # HTML is pretty obvious. Look for either or return ( 'HTML', defined $charset? (encoding => $charset) : ()) if $text =~ /^<(?:!DOCTYPE\s+)?HTML\b/i; # Else guess between CSV and TSV my ($probably_csv, $probably_tsv)= (0,0); ++$probably_csv if $text =~ /^("(?:[^"]|"")*"|[^,"]+),/; # first field appears terminated with comma ++$probably_tsv if $text =~ /^("(?:[^"]|"")*"|[^\t"]+)\t/; # first field appears terminated with tab my $comma_count= () = ($text =~ /,/g); my $tab_count= () = ($text =~ /\t/g); my $eol_count= () = ($text =~ /\n/g); ++$probably_csv if $comma_count >= $eol_count and $comma_count > $tab_count; ++$probably_tsv if $tab_count >= $eol_count and $tab_count > $comma_count; $self->_log->('debug', 'probe results: comma_count=%d tab_count=%d eol_count=%d probably_csv=%d probably_tsv=%d', $comma_count, $tab_count, $eol_count, $probably_csv, $probably_tsv); my $class= $probably_csv && $probably_csv > $probably_tsv? 'CSV' : $probably_tsv && $probably_tsv > $probably_csv? 'TSV' : undef; return () unless $class; return ($class, $charset? (encoding => $charset) : ()); } sub detect_input_charset { my ($self, $hints)= @_; # Need to have the content_head available unless (defined $self->_get_content_head($hints)) { # Use existence of the hint key as a flag for whether this has been called yet # though it doesn't change the behavior of this method. $hints->{charset}= undef unless exists $hints->{charset}; return undef; } my ($charset, $ofs)= (undef, $hints->{content_ofs}); # Check for explicit byte-order-mark pos($hints->{content_head})= $ofs || 0; if ($hints->{content_head} =~ /\G(?: \xFF\xFE\x00\x00 (?{"UTF-32LE"}) | \x00\x00\xFE\xFF (?{"UTF-32BE"}) | \xFF\xFE (?{"UTF-16LE"}) | \xFE\xFF (?{"UTF-16BE"}) | \xEF\xBB\xBF (?{"utf-8-strict"}) )/xgc) { $charset= $^R; $ofs= $+[0]; } if (!$charset) { # Other heuristics: a CSV or TSV likely begin with a line of headers, # and the headers are likely ascii identifier strings even if the data # contains lots of non-english. Also HTML and JSON begin with at least # 2 ascii chars. if ($hints->{content_head} =~ /\G(?: (?:[\t\n\x20-\x7E]\0\0\0){2} (?{"UTF-32LE"}) # ascii char x2 | (?:\0\0\0[\t\n\x20-\x7E]){2} (?{"UTF-32BE"}) # ascii char x2 | (?:[\t\n\x20-\x7E]\0){2} (?{"UTF-16LE"}) # ascii char x2 | (?:\0[\t\n\x20-\x7E]){2} (?{"UTF-16BE"}) # ascii char x2 )/gc) { $charset= $^R; } # any buffer that has NULs in it is likely 16/32 encoded. Look for a newline. elsif ($hints->{content_head} =~ /\G.*?\0/) { $charset= $hints->{content_head} =~ /\G(....)*?\n\0\0\0/gcs? 'UTF-32LE' : $hints->{content_head} =~ /\G(....)*?\0\0\0\n/gcs? 'UTF-32BE' : $hints->{content_head} =~ /\G(..)*?\n\0/gcs? 'UTF-16LE' : $hints->{content_head} =~ /\G(..)*?\0\n/gcs? 'UTF-16BE' : undef; } } ($hints->{charset}, $hints->{content_ofs})= ($charset, $ofs) if defined $charset; return $charset; } sub _build_table_search_results { my $self= shift; my $result= $self->_find_table($self->decoder->iterator); # When called during lazy-build, not finding the table is fatal if (!$result->{found}) { my $err= $result->{fatal} || "Can't locate valid header"; $self->_log->('error', $err); croak $err; } $result; } # The col_map attribute has some awkward back-compat. It originally triggered a lazy-build # of ->find_table and stored the result. Users could inspect and modify it afterward. # Then I added the ability to pass it to the constructor, and start from that initial value # to build the col_map for the table_search_results. I probably should have used a new # attribute name like 'base_col_map' or something, but didn't. The user-assigned value is now # the only thing stored in the attribute, not the built value, but the accessor returns the # built value if one exists before falling back to the stored value. sub col_map { my $self= shift; my $ret; if (@_) { if (@_ == 1 && !defined $_[0]) { $self->_set_col_map($ret= undef); } else { @_ == 1 && ref $_[0] eq 'ARRAY' or croak 'Expected arrayref'; $ret= [ @{$_[0]} ]; $self->_resolve_colmap_names($ret); $self->_set_col_map($ret); } } else { my $supplied= $self->_get_col_map; # lazy-build search results, like original API $self->table_search_results unless defined $supplied; $ret= ($self->has_table_search_results && $self->table_search_results->{found})? $self->table_search_results->{found}{col_map} # supplied col_map might be using strings or stale/foreign field objects : $supplied? $self->_resolve_colmap_names($supplied) : undef; } return $ret; } # Accessor is documented to return true if an initial col_map was supplied, # or if a col_map has been derived by find_table. sub has_col_map { my $self= shift; defined $self->_get_col_map or $self->has_table_search_results && $self->table_search_results->{found} } # Accessor for only the user-supplied list, but resolved to field objects sub _supplied_col_map { my $self= shift; my $supplied= $self->_get_col_map; defined $supplied? $self->_resolve_colmap_names($supplied) : undef; } sub find_table { my $self= shift; $self->clear_table_search_results; my $result= $self->_find_table($self->decoder->iterator); $self->table_search_results($result); return defined $result->{found}; } sub field_map { _field_map(shift->col_map) } sub _field_map { my $col_map= shift; my %fmap; for my $i (0 .. $#$col_map) { next unless defined $col_map->[$i]; if ($col_map->[$i]->array) { push @{ $fmap{$col_map->[$i]->name} }, $i; } else { $fmap{$col_map->[$i]->name}= $i; } } return \%fmap; } sub _find_table { my ($self, $data_iter)= @_; my @fields= $self->field_list; my $header_at= $self->header_row_at; my %result; # It is not an error to construct a TableReader with no fields, but they must be assigned # before we can attempt detecting a table. croak "No fields were defined" unless @fields; # Special case for the file not having any headers in it. # If header_row_at is undef, then there is no header. # Ensure static_field_order, then set up columns. if (!defined $header_at) { unless ($self->static_field_order) { $result{fatal}= "You must enable 'static_field_order' if there is no header row"; return \%result; } my $col_map= [ @{ $self->_supplied_col_map || \@fields } ]; $result{found}= { row_idx => -1, row => undef, dataset_idx => 0, col_map => $col_map, messages => [], first_record_pos => $data_iter->tell, _data_iter => $data_iter, }; $result{candidates}= [ $result{found} ]; return \%result; } my $dataset_idx= 0; dataset: do { # If headers contain "\n", we need to collect multiple cells per column my $row_accum= $self->header_row_combine; my ($start, $end)= ref $header_at? @$header_at : ( $header_at, $header_at ); my @rows; # If header_row_at doesn't start at 1, seek forward if ($start > 1) { $self->_log->('trace', 'Skipping to row %s', $start); push @rows, $data_iter->() for 1..$start-1; } # Scan through the rows of the dataset up to the end of header_row_at, accumulating rows so that # multi-line regexes can match. for my $row ($start .. $end) { my %attempt= ( row_idx => $row-1, row => $row, dataset_idx => $dataset_idx, messages => [] ); my $vals= $data_iter->(); if (!$vals) { # if undef, we reached end of dataset $self->_log->('trace', 'EOF'); last; } if ($row_accum > 1) { push @rows, $vals; shift @rows while @rows > $row_accum; $vals= [ map { my $c= $_; join("\n", map $_->[$c], @rows) } 0 .. $#{$rows[-1]} ]; $attempt{context}= $row_accum.' rows ending at '.$data_iter->position; } else { $attempt{context}= $data_iter->position; } $self->_log->('trace', 'Checking for headers on %s', $attempt{context}); # Now fill-in the col_map my $found= $self->static_field_order? # If static field order, look for headers in sequence $self->_match_headers_static($vals, \%attempt) # else search for each header : $self->_match_headers_dynamic($vals, \%attempt); $attempt{first_record_pos}= $data_iter->tell; $self->_log->(@$_) for @{$attempt{messages}}; push @{$result{candidates}}, \%attempt; if ($found) { $result{found}= \%attempt; $result{found}{_data_iter}= $data_iter; $self->_log->(info => 'Found header at '.$attempt{context}); return \%result; } else { # Back-compat: if attempt ends with 'fatal' message, stop looking for header last dataset if delete $attempt{fatal}; # Was this a partial match? See if any col_map entries were added vs. what user already gave us. my $initial_colmap_count= !$self->_get_col_map? 0 : scalar(grep defined, @{$self->_get_col_map}); if ($initial_colmap_count < scalar(grep defined, @{$attempt{col_map}})) { # Handling of partial match determined by on_partial_match setting my $act= $self->on_partial_match; $act= $act->($self, \%attempt, $vals) if ref $act eq 'CODE'; last dataset if $act eq 'last'; } } $self->_log->('debug', '%s: No match', $attempt{context}); } $self->_log->('error','No row in dataset matched full header requirements'); ++$dataset_idx; } while ($data_iter->next_dataset); return \%result; } # This mode assumes all headers match exactly as prescribed in the fields list or user-supplied col_map sub _match_headers_static { my ($self, $header, $attempt)= @_; my @col_map= @{ $self->_supplied_col_map || $self->fields }; $attempt->{col_map}= \@col_map; for my $i (0 .. $#col_map) { next unless defined $col_map[$i]; next if defined $header->[$i] && $header->[$i] =~ $col_map[$i]->header_regex; # Field header doesn't match. Start over on next row. push @{$attempt->{messages}}, [ error => "Header at column ".($i+1)." does not look like field ".$col_map[$i]->name ]; return 0; } # found a match for every mapped field $self->_log->('debug','%s: Found!', $attempt->{context}); return 1; } sub _match_headers_dynamic { my ($self, $header, $attempt)= @_; my $context= $attempt->{context}; my $fields= $self->fields; # Colmap starts empty unless user supplied one my $user_colmap= $self->_supplied_col_map || []; my @colmap= map +(defined $_? [ $_ ] : undef), @$user_colmap; $attempt->{col_map}= \@colmap; # Search every cell of the header, except ones specified by the user my @col_search_idx= grep !defined $user_colmap->[$_], 0 .. $#$header; # Divide remaining fields (not specified by user) into list that can only occur following # another field, or the ones that can occur anywhere. my %seen= map +(refaddr $_ => 1 ), grep defined, @$user_colmap; my (@follows_fields, @free_fields); defined $seen{refaddr $_} or push @{($_->follows_list? \@follows_fields : \@free_fields)}, $_ for @$fields; undef %seen; # Sort required fields to front, to fail faster on non-matching rows # But otherwise preserve field order in case it matters for priority of matching @free_fields= ( (grep $_->required, @free_fields), (grep !$_->required, @free_fields) ); # For each freely-located field (free = lacking placement requirements) scan every un-used # column for a match. Record all matches, for later analysis of ambiguity. # But, stop as soon as a required column is missing; it helps speed up the search for the # header. my $ambiguous_log_level= $self->on_ambiguous_columns eq 'error'? 'error' : 'warn'; my %fieldname_cols; for my $f (@free_fields) { my $hr= $f->header_regex; push @{$attempt->{messages}}, [ trace => "looking for $hr" ]; my @found_idx= grep +(defined $header->[$_] && $header->[$_] =~ $hr), @col_search_idx; push @{$attempt->{messages}}, [ debug => "found ".$f->name." header at col [".join(',', map $_+1, @found_idx).']' ]; for my $idx (@found_idx) { # If another field of the same name matches a column, the first gets priority. # ignore the duplicate. if ($fieldname_cols{$f->name}{$idx}) { push @{$attempt->{messages}}, [ debug => "Ignored; column $idx is already claimed by a field named ".$f->name ]; } else { push @{$colmap[$idx]}, $f; #$col_fieldnames{$idx}{$f->name}= 1; $fieldname_cols{$f->name}{$idx}= $f; } } # Flag missing required fields if (!@found_idx && $f->required) { push @{$attempt->{missing_required}}, $f; push @{$attempt->{messages}}, [ error => 'No match for required field '.$f->name ]; # Missing required fields probably means this isn't the header row, or the input is # garbage, so might as well stop here before generating a bunch of analysis. last; } } # Now, check for any of the 'follows' fields, some of which might also be 'required'. if (@follows_fields && !$attempt->{missing_required}) { my %following; my %found; for my $idx (0 .. $#$header) { if ($colmap[$idx] && 1 == @{$colmap[$idx]}) { %following= ( $colmap[$idx][0]->name => $colmap[$idx][0] ); } else { my $val= $header->[$idx]; for my $f (@follows_fields) { next unless grep $following{$_}, $f->follows_list; next unless defined $val && $val =~ $f->header_regex; # If another field of the same name matches a column, the first gets priority. # ignore the duplicate. if ($fieldname_cols{$f->name}{$idx}) { push @{$attempt->{messages}}, [ debug => "Ignored; column $idx is already claimed by a field named ".$f->name ]; } else { push @{$colmap[$idx]}, $f; $fieldname_cols{$f->name}{$idx}= $f; $found{refaddr $f}= 1; } } # If successfully matched exactly one field, add it to the 'following' set. if ($colmap[$idx] && @{$colmap[$idx]} == 1) { $following{$colmap[$idx][0]->name}= $colmap[$idx][0]; } # Else if no matches, or ambiguous, so reset the following set else { %following= (); } } } # Check if any of the 'follows' fields were required if (my @unfound= grep +($_->required && !$found{refaddr $_}), @follows_fields) { push @{$attempt->{missing_required}}, @unfound; push @{$attempt->{messages}}, [ error => sprintf('No match for required %s [%s]', (@unfound > 1? 'fields':'field'), join(', ', map $_->name, sort @unfound)) ]; } } # Make the list of columns which didn't match anything before starting to munge things # related to ambiguities. my @unmatched= grep !defined $colmap[$_], 0 .. $#$header; $attempt->{unmatched}= \@unmatched if @unmatched; # Ambiguity check: each field *name* may only be located in one column, unless # the field(s) are flagged as being arrays. my %ambiguous_fields; for my $name (sort keys %fieldname_cols) { my $cols= $fieldname_cols{$name}; next unless keys %$cols > 1; next unless grep !$_->array, values %$cols; push @{$attempt->{messages}}, [ $ambiguous_log_level => sprintf "Found field '%s' at multiple columns: %s", $name, join(', ', map 1+$_, sort { $a <=> $b } keys %$cols) ]; $ambiguous_fields{$name}= $cols; } $attempt->{ambiguous_fields}= \%ambiguous_fields if keys %ambiguous_fields; # Ambiguity check: there must be only one field claiming each column # If it's OK, resolve the arrayref down to its single member. for my $idx (0 .. $#colmap) { next unless defined $colmap[$idx]; if (@{$colmap[$idx]} == 1) { # only claimed by one field my $f= $colmap[$idx][0]; # but if that one field is ambiguous, discard it $colmap[$idx]= $ambiguous_fields{$f->name}? undef : $f; } else { push @{$attempt->{messages}}, [ $ambiguous_log_level => sprintf "Column %d claimed by multiple fields: %s", $idx+1, join(', ', sort map $_->name, @{$colmap[$idx]}) ]; $attempt->{ambiguous_columns}{$idx}= $colmap[$idx]; $colmap[$idx]= undef; } } # Need to have found at least one column (even if none required) unless (grep defined, @colmap) { push @{$attempt->{messages}}, [ error => ($attempt->{ambiguous_columns} || $attempt->{ambiguous_fields}) ? 'All matching headers were ambiguous' : 'No field headers matched' ]; return 0; } return 0 if $attempt->{missing_required} or $self->on_ambiguous_columns ne 'warn' && ($attempt->{ambiguous_columns} || $attempt->{ambiguous_fields}); # Now, if there are any un-claimed columns, handle per 'on_unknown_columns' setting. if (@unmatched) { my $act= $self->on_unknown_columns; my $unknown_list= join(', ', map $self->_fmt_header_text($header->[$_]), @unmatched); $act= $act->($self, $header, \@unmatched, $attempt) if ref $act eq 'CODE'; if ($act eq 'warn' || $act eq 'use') { # 'use' is back-compat, 'warn' is official now. push @{$attempt->{messages}}, [ warn => 'Ignoring unknown columns: '.$unknown_list ]; } elsif ($act eq 'error' || $act eq 'next') { # 'next' is back-compat, 'error' is official now. push @{$attempt->{messages}}, [ error => 'Would match except for unknown columns: '.$unknown_list ]; return 0; } else { push @{$attempt->{messages}}, [ error => $act eq 'die'? "${context}Header row includes unknown columns: $unknown_list" : "Invalid action '$act' for 'on_unknown_columns'" ]; $attempt->{fatal}= 1; return 0; } } return 1; } # Make header string readable for log messages sub _fmt_header_text { shift if ref $_[0]; # ignore $self, but still a method in case someone wants to subclass it my $x= shift; return '' unless defined $x; $x =~ s/ ( [^[:print:]] ) / sprintf("\\x%02X", ord $1 ) /gex; qq{"$x"}; } # format the colmap into a string sub _colmap_progress_str { my ($colmap, $headers)= @_; join(' ', map { $colmap->{$_}? $_.'='.$colmap->{$_}->name : $_.':'._fmt_header_text($headers->[$_]) } 0 .. $#$headers) } sub iterator { my $self= shift; my $fields= $self->fields; $self->table_search_results->{found} or croak "table_search_results does not contain 'found'"; # Creating the record iterator consumes the data source's iterator. # The first time after detecting the table, we continue with the same iterator. # Every time after that we need to create a new data iterator and seek to the # first record under the header. my $data_iter= delete $self->table_search_results->{found}{_data_iter}; unless ($data_iter) { $data_iter= $self->decoder->iterator; $data_iter->seek($self->table_search_results->{found}{first_record_pos}); } # The goal for this iterator is to perform as little work as possible on each iteration, # while making all the features possible, but avoiding building custom perl code with 'eval'. # To that end, most of the operations get vectorized and stored in array variables that # get closed-over by the iterator function. # # The iterator algorithm goes like this: # # - Collect a slice of the next row from the Decoder, selecting only the columns we need. # i.e. @row_slice= @decoder_row[@slice_idx]; # - Run trim functions on each value that needs trimmed. # i.e. $row_slice[$i]= $trim[$i]->($row_slice[$i]) if defined $row_slice[$i] # - Apply "blank" value to any value that is zero length # i.e. $row_slice[$i]= $blank_value[$i] unless length $row_slice[$i] # - Special handling if the entire row is blank # - If user wanted validation, do type checks on each relevant value # i.e. $type->validate($row_slice[$i]) # - Assemble array-valued fields into a single arrayref value # i.e. $row_slice[$from]= [ splice(@row_slice, $from, $to, undef) ]; # - If user wanted an array matching the Field order, alter @row_slice to match # - else if user wanted a hashref, build one, # - If validations failed, run user callback # - if user wanted an object, construct one my $col_map= $self->table_search_results->{found}{col_map}; my $field_map= _field_map($col_map); my @input_slice; # list of column idx to retrieve from input my @output_slice; # list of column idx to store in output, for record_class=>'ARRAY' my @output_keys; # list of hash key names where values get stored my @array_ranges; # list of value indices that get bundled into an arrayref my @blank_val; # blank value per each fetched column my @trim; # list of trim functions and the value indices they should be applied to my @type_check; # list of validation coderefs that should be applied my $class; # optional object class to construct for the resulting rows my ($n_blank, $first_blank, $eof); my $sub= sub { my (@failed, $out, $vals); again: # Pull the specific slice of the next row that we need $vals= !$eof && $data_iter->(\@input_slice) or ++$eof && return undef; # Apply 'trim' to any column whose field requested it for my $t (@trim) { defined and $t->[0]->() for @{$vals}[@{$t->[1]}]; } # Apply 'blank value' to every column which is zero length $n_blank= 0; (defined $vals->[$_] and length $vals->[$_]) or (++$n_blank, $vals->[$_]= $blank_val[$_]) for 0..$#$vals; # If all are blank, then handle according to $on_blank_row setting if ($n_blank == @$vals) { $first_blank ||= $data_iter->row; goto again; } elsif ($first_blank) { # At the end of a series of blank rows, run the callback to decide what to do unless ($self->_handle_blank_row($data_iter, $data_iter->row - $first_blank)) { $eof= 1; return undef; } $first_blank= undef; } # Check type constraints, if any @failed= (); push @failed, $_->($vals) for @type_check; # Combine each set of array-valued fields into an arrayref $vals->[$_->[0]]= [ splice @$vals, $_->[0], $_->[1], undef ] for @array_ranges; # Generate the output structure $out= @output_keys? do { my %out; @out{@output_keys}= @$vals; \%out } : @output_slice? do { my @out; $#out= $#$fields; @out[@output_slice]= @$vals; \@out } : $vals; # Handle any validation errors detected above if (@failed) { $self->_handle_validation_error(\@failed, $out, $data_iter) or goto again; } # Construct a class, if requested, else return hashref return $class? $class->new($out) : $out; }; # User wants arrayref output, with one element per field? if ($self->record_class eq 'ARRAY') { # If two fields share a name, only the first one gets the value(s). my %remaining= %$field_map; my $need_output_slice= 0; for my $field_idx (0 .. $#$fields) { my $f= $fields->[$field_idx]; my $src= delete $remaining{$f->name}; # If this field has a source, add it to the input slice and output slice if (defined $src) { push @output_slice, $field_idx if $need_output_slice; push @input_slice, $src; } # output_slice isn't needed until the first field that doesn't have a source elsif (!$need_output_slice) { $need_output_slice= 1; @output_slice= ( 0 .. $field_idx-1 ); } } } else { # For any other record_class, we are building a hashref # Only set the 'class' variable if we also need to construct an object. $class= $self->record_class unless 'HASH' eq $self->record_class; @input_slice= values %$field_map; @output_keys= keys %$field_map; } my %trimmer; for (my ($i, $out_ofs, $array_start, $array_lim)= (0,0); $i <= $#input_slice; $i++) { my $col_idx= $input_slice[$i]; if (ref $col_idx eq 'ARRAY') { $array_start= $i; $array_lim= $array_start + @$col_idx; splice(@input_slice, $i, 1, @$col_idx); push @array_ranges, [ $i+$out_ofs, scalar @$col_idx ]; $col_idx= $col_idx->[0]; } elsif (defined $array_lim) { if ($i >= $array_lim) { $array_start= $array_lim= undef; } else { --$out_ofs; # each iteration within an array increases the offset } } my $field= $col_map->[$col_idx]; # Handling for ->trim feature if (my $t= $field->trim_coderef) { $trimmer{refaddr $t} ||= [ $t, [] ]; push @{ $trimmer{refaddr $t}[1] }, $i; } # Handling for ->blank feature push @blank_val, $field->blank; # Handling for ->type and ->coerce features if ($field->type) { # @path is needed to show the on_validation_fail callback where to find the value in # the output. First element of @path is either ->{$name} or ->[$idx] depending whether # the output is an array or hashref. Second element only happens if that field's value # is an arrayref. my $output_idx= $i + $out_ofs; my @path= ( @output_keys? $output_keys[$output_idx] : @output_slice? $output_slice[$output_idx] : $output_idx ); push @path, ($i - $array_start) if defined $array_start; push @type_check, $self->_make_validation_check_coderef($field, $i, \@path); } } @trim= values %trimmer; return Data::TableReader::_RecIter->new( $sub, { data_iter => $data_iter, reader => $self, n_blank => \$n_blank, first_blank => \$first_blank, eof => \$eof, }, ); } sub _make_validation_check_coderef { my ($self, $field, $vals_idx, $out_path)= @_; my $t= $field->type; my $c= $field->coerce; my $t_can_validate= blessed($t) && $t->can('validate'); # If type object has method 'coerce' but does not have method 'has_coercions', just run it. # But, if has_coercions is false, then there's no point in running it. my $t_can_coerce= blessed($t) && ($t->can('has_coercions')? $t->has_coercions : $t->can('coerce')); # There are 5 possibilities for the callback: # type is a coderef, and coerce is false ref $t eq 'CODE'? ( !$c? sub { my $e= $t->($_[0][$vals_idx]); defined $e? ([ $field, undef, $e, $out_path ]) : () } # type is a coderef, and coerce is a coderef : ref $c eq 'CODE'? sub { my $e= $t->($_[0][$vals_idx]); if (defined $e) { my $tmp= $c->($_[0][$vals_idx]); ($_[0][$vals_idx], $e)= ($tmp) unless defined $t->($tmp); } defined $e? ([ $field, undef, $e, $out_path ]) : () } : croak("Can't coerce field ".$field->name.": ->type is coderef and ->coerce is not a coderef") ) # type is a Type::Tiny, and coerce is a coderef : $t_can_validate? ( ref $c eq 'CODE'? sub { my $e= $t->validate($_[0][$vals_idx]); if (defined $e) { my $tmp= $c->($_[0][$vals_idx]); ($_[0][$vals_idx], $e)= ($tmp) unless defined $t->validate($tmp); } defined $e? ([ $field, undef, $e, $out_path ]) : () } # type is a Type::Tiny, and coerce is requested and is available from the type object : $c && $t_can_coerce? sub { my $e= $t->validate($_[0][$vals_idx]); if (defined $e) { my $tmp= $t->coerce($_[0][$vals_idx]); ($_[0][$vals_idx], $e)= ($tmp) unless defined $t->validate($tmp); } defined $e? ([ $field, undef, $e, $out_path ]) : () } # type is a Type::Tiny, and coerce is not requested or not available : sub { my $e= $t->validate($_[0][$vals_idx]); defined $e? ([ $field, undef, $e, $out_path ]) : () } ) : croak "Invalid type constraint $t on field ".$field->name; } sub _handle_blank_row { my ($self, $data_iter, $count)= @_; my $last= $data_iter->row - 1; my $first= $last - $count + 1; my $act= $self->on_blank_row; $act= $act->($self, $first, $last) if ref $act eq 'CODE'; if ($act eq 'next') { $self->_log->('warn', $first == $last? ( 'Skipping blank row at %s', $first ) : ('Skipping blank rows from %s until %s', $first, $last ) ); return 1; } if ($act eq 'last') { $self->_log->('warn', 'Ending at blank row %s', $first); return 0; } if ($act eq 'die') { my $msg= "Encountered blank rows at $first..$last"; $self->_log->('error', $msg); croak $msg; } croak "Invalid value for 'on_blank_row': \"$act\""; } sub _handle_validation_error { my ($self, $failures, $output, $data_iter)= @_; my $act= $self->on_validation_error; if (ref $act eq 'CODE') { # Fill in the second element (ref to $output) for each failure for (@$failures) { my $path= $_->[3]; my $ref= ref $output eq 'HASH'? \$output->{$path->[0]} : \$output->[$path->[0]]; $ref= \(${$ref}->[$path->[1]]) if @$path > 1; $_->[1]= $ref; } $act= $act->($self, $failures, $output, $data_iter); } my $errors= join(', ', map $_->[0]->name.': '.$_->[2], @$failures); if ($act eq 'next') { $self->_log->('warn', "%s: Skipped for data errors: %s", $data_iter->position, $errors) if $errors; return 0; } if ($act eq 'use') { $self->_log->('warn', "%s: Possible data errors: %s", $data_iter->position, $errors) if $errors; return 1; } if ($act eq 'die') { my $msg= $data_iter->position.": Invalid record: $errors"; $self->_log->('error', $msg); croak $msg; } croak "Invalid value for 'on_validation_error': \"$act\""; } # This is back-compat for the previous callback API which was an attribute named 'on_validation_fail' sub _wrap_on_validation_fail { my $orig_cb= shift; return sub { my ($self, $failures, $output, $data_iter)= @_; # Old API gave the user a value index rather than a ref to the value my @value_refs= map $_->[1], @$failures; my @values= map $$_, @value_refs; $failures->[$_][1]= $_ for 0 .. $#$failures; my $act= $orig_cb->($self, $failures, \@values, $data_iter->position.': '); # if they changed any values, write them back to the refs. ${$value_refs[$_]}= $values[$_] for 0 .. $#value_refs; return $act; }; } BEGIN { @Data::TableReader::_RecIter::ISA= ( 'Data::TableReader::Iterator' ) } sub Data::TableReader::_RecIter::all { my $self= shift; my (@rec, $x); push @rec, $x while defined($x= $self->()); return \@rec; } sub Data::TableReader::_RecIter::dataset_idx { shift->_fields->{data_iter}->dataset_idx(@_); } sub Data::TableReader::_RecIter::row { shift->_fields->{data_iter}->row(@_); } sub Data::TableReader::_RecIter::position { shift->_fields->{data_iter}->position(@_); } sub Data::TableReader::_RecIter::progress { shift->_fields->{data_iter}->progress(@_); } sub Data::TableReader::_RecIter::tell { my $fields= shift->_fields; my $dec_pos= $fields->{data_iter}->tell; return [ $dec_pos, ${$fields->{eof}}, ${$fields->{first_blank}}, ${$fields->{n_blank}} ]; } sub Data::TableReader::_RecIter::seek { my ($self, $state)= @_; my $fields= $self->_fields; ref $state eq 'ARRAY' && @$state == 4 or croak "Expected arrayref of 4 elements, as returned by ->tell"; my ($dec_pos, $eof, $first_blank, $n_blank)= @$state; $fields->{data_iter}->seek($dec_pos); ${$fields->{eof}}= $eof; ${$fields->{first_blank}}= $first_blank; ${$fields->{n_blank}}= $n_blank; return $self; } sub Data::TableReader::_RecIter::next_dataset { shift->_fields->{reader}->_log ->('warn',"Searching for subsequent table headers is not supported yet"); return 0; } 1; __END__ =pod =encoding UTF-8 =head1 NAME Data::TableReader - Extract records from "dirty" tabular data sources =head1 VERSION version 0.022 =head1 SYNOPSIS # Find a row in the Excel file containing the headers # "address", "city", "state", "zip" (in any order) # and then convert each row under that into a hashref of those fields. my $records= Data::TableReader->new( input => 'path/to/file.xlsx', fields => [qw( address city state zip )], ) ->iterator->all; but there are plenty of options to choose from... my $tr= Data::TableReader->new( # path or file handle # let it auto-detect the format (but can override that if we need) input => 'path/to/file.csv', # We want these fields to exist in the file (identified by headers) fields => [ { name => 'address', header => qr/street|address/i }, 'city', 'state', # can validate with Type::Tiny classes { name => 'zip', header => qr/zip\b|postal/i, type => US_Zipcode }, ], # Our data provider is horrible; just ignore any nonsense we encounter on_blank_row => 'next', on_validation_error => 'next', # Capture warnings and show to user who uploaded file log => \(my @messages) ); my $records= $tr->iterator->all; ... $http_response->body( encode_json({ messages => \@messages }) ); =head1 DESCRIPTION This module is designed to take "loose" or "dirty" tabular data sources (such as Excel, CSV, TSV, or HTML) which may have been edited by non-technical humans and extract the data into sanitized records, while also verifying that the data file contains roughly the schema you were expecting. It is primarily intended for making automated imports of data from non-automated or unstable sources, and providing human-readable feedback about the validity of the data file. =head1 ATTRIBUTES =head2 input This can be a file name, L instance, file handle, arrayref, or L object. If you supply a file handle, it must be seekable in order to auto-detect the file format, I you may specify the decoder directly to avoid auto-detection. Arrayrefs are passed to the L<'Mock' decoder|Data::TableReader::Decoder::Mock> which just returns the data as-is. =head2 decoder This is either an instance of L, or a class name, or a partial class name to be appended as C<"Data::TableReader::Decoder::$name"> or an arrayref or hashref of arguments to build the decoder. In an arrayref the first argument can be undef, and in a hashref the CLASS argument can be missing or undef. In those cases it will be detected from the input attribute and any default arguments combined with (and if necessary trumped by) the extra arguments in the arrayref or hashref. Examples: 'CSV' # becomes Data::TableReader::Decoder::CSV->new() [ 'CSV', sep_char => "|" ] # becomes Data::TableReader::Decoder::CSV->new(sep_char => "|") { CLASS => 'CSV', sep_char => "|" } # becomes Data::TableReader::Decoder::CSV->new({ sep_char => "|" }) =head2 fields An arrayref of L objects which this module should search for within the tables (worksheets etc.) of L. If an element of this array is a hashref or string, it will be coerced to an instance of L, with plain strings becoming the C attribute. See L for how names are automatically converted to the header-matching regex. There are some convenience accessors for the fields: =over =item field_list List access for C<< @{ $reader->fields } >> =item field_by_name Map of C<< { $field->name => $field } >>. If you have multiple fields of the same name (allowed, but not recommended) the value is the first per the order of C. =item field_by_addr Map of C<< { refaddr($field) => $field } >>. =back If you need to, you can supply an empty list of fields and then update the attribute later. (Be sure to write via the accessor rather than modify the arrayref.) This can be useful if you want to use the input detection features before sorting out the details of which fields to use. =head2 record_class Default is the special value C<'HASH'> for un-blessed hashref records. The special value C<'ARRAY'> will result in arrayrefs with fields in the same order they were specified in the L specification. Setting it to anything else will return records created with C<< $record_class->new(\%fields); >> =head2 static_field_order Boolean, whether the L must be found in columns in the exact order that they were specified. Default is false. =head2 header_row_at Row number, or range of row numbers where the header must be found. (All row numbers in this module are 1-based, to match end-user expectations.) The default is C<[1,10]> to limit header scanning to the first 10 rows. As a special case, if you are reading a source which lacks headers and you trust the source to deliver the columns in the right order, you can set this to undef if you also set C<< static_field_order => 1 >>. =head2 col_map This is an arrayref, one element per column of input data, listing which field was detected to come from that column. If you specify this to the constructor, L will respect any defined element of the array, but still search for matching headers in the undefined columns. After a successful L, the C accessor refers to the same array as C<< ->table_search_results->{found}{col_map} >>. If you call C, the C accessor returns to the previous value. For backward compatibility, if you did not specify this attribute to the constructor and try accessing it before calling L, it automatically calls L for you (and dies if it fails). =head2 has_col_map Returns true if you assigned an initial value to col_map, or if a value was determined by table_search_results. =head2 table_search_results This is the output of the most recent L operation. { candidates => [ { dataset_idx => $n, row => $n, col_map => [ $field_or_undef, $field_or_undef, ... ], missing_required => \@fields, ambiguous_columns => { $col_idx => \@fields, ... }, ambiguous_fields => { $field_name => { $col_idx => $field }, ... }, unmatched => \@col_idx, messages => [], }, ... ], found => $ref_to_candidate, # undef if find_table failed } The fields describing problems (C, C, C, and C) are not present unless they contain data. All C<@fields> are refs to the actual Field objects. C has one element per element of the header row. If C is populated, the analysis of ambiguity may be incomplete, because missing required columns abort the search for the header. All C<"_idx"> values are 0-based, but the errors in C use 1-based descriptions. =head2 has_table_search_results, clear_table_search_results Predicate and clearer for lazy-built table_search_results. =head2 on_partial_match on_partial_match => 'next' # keep searching for a better line of headers on_partial_match => 'last' # return failure from ->find_table on_partial_match => sub { my ($reader, $candidate, $header_row)= @_; return $action; # one of the above values } During L, if a row is found that matches at least one header, but fails to match all the requirements (required columns, unknown or ambiguous columns if those are configured as an error) you can either keep searching for a better header row, or stop here. The default is 'next', to keep searching, but this may result in a lot of noise. The 'last' setting allows you to stop after a likely header row. If you supply a coderef, you receive the "candidate" info described in L. =head2 on_ambiguous_columns on_ambiguous_columns => 'warn' # warn, and omit from the match on_ambiguous_columns => 'error' # fail the header match for this row During L, when matching a field's header pattern vs. the columns of a row, if the pattern could match more than one cell it is an error. You might want to handle it in various ways: =over =item C<'warn'> If a Field matches multiple columns (and isn't an array field) omit the field from the col_map entirely. If a column matches multiple fields, leave the col_map blank for this column. Both generate warnings, but the header match can still proceed to a successful result. =item C<'error'> (default) Any ambiguities (field matching multiple columns, multiple fields matching a column) cause the match of the header on this row to fail. Further attempts at finding the header depend on the L setting. =back =head2 on_unknown_columns on_unknown_columns => 'warn' # warn, and then accept these headers on_unknown_columns => 'error' # fail the header match for this row on_unknown_columns => sub { my ($reader, $headers, $unmatched, $candidate)= @_; # @headers is an array of the header of each column # @unmatched is an array of which @header indices are unmatched # %candidate is the structure from ->table_search_results->{candidates} ...; return $opt; # one of the above values } This determines handling for columns that aren't associated with any field. The "required" columns must all be found before it considers this setting, but once it has found everything it needs to make this a candidate, you might or might not care about the leftover columns. =over =item C<'warn'> (default) You don't care if there are extra columns, just log warnings about them and proceed extracting from this table. =item C<'error'> Extra columns mean that you didn't find the table you wanted. Log the near-miss, and keep searching additional rows or additional tables, according to L. =item C You can add your own logic to handle this. Inspect the headers however you like, and then return one of the above values. =back =head2 on_blank_row on_blank_row => 'next' # warn, and then skip the row(s) on_blank_row => 'last' # warn, and stop iterating the table on_blank_row => 'die' # fatal error on_blank_row => sub { my ($reader, $first_blank_rownum, $last_blank_rownum)= @_; ...; return $opt; # one of the above values } This determines what happens when you've found the table, are extracting records, and encounter a series of blank rows (defined as a row with no printable characters in any field) followed by non-blank rows. If you use the callback, it suppresses the default warning, since you can generate your own. The default is C<'next'>. =head2 on_validation_error on_validation_error => 'next' # warn, and then skip the record on_validation_error => 'use' # warn, and then use the record anyway on_validation_error => 'die' # fatal error on_validation_error => sub { my ($tablereader, $failures, $record, $data_iterator)= @_; # $record is the assembled hashref (unblessed) or arrayref of fields # $data_iterator is the Decoder's row iterator, useful for context for (@$failures) { my ($field, $value_ref, $message, $path)= @$_; ... # $field is a Data::TableReader::Field # $$value_ref is the string that failed validation # $message is the error returned from the validation function # $path is the element (and maybe sub-element) of $record # i.e. $value_ref= \$record->{$path->[0]}[$path->[1]] # You may modify $$value_ref or $record to alter the output } # Clear the failures array to suppress warnings, if you actually corrected # the validation problems. @$failures= (); # return one of the above constants to tell the iterator what to do next return $opt; } This determines what happens when you've found the table, are extracting records, and one row fails its validation. In addition to deciding an option, the callback gives you a chance to alter the record before C<'use'>ing it. The default is 'die'. =head2 log If undefined (the default) all log messages above 'info' will be emitted with C. If set to an object, it should support an API of: trace, is_trace debug, is_debug info, is_info warn, is_warn error, is_error such as L and many other perl logging modules use. You can also set it to a coderef such as: my @messages; sub { my ($level, $message)= @_; push @messages, [ $level, $message ] if grep { $level eq $_ } qw( info warn error ); }; for a simple way to capture the messages without involving a logging module. And for extra convenience, you can set it to an arrayref which will receive any message that would otherwise have gone to 'warn' or 'error'. =head1 METHODS =head2 detect_input_format my ($decoder_class, @args)= $tr->detect_input_format(\%hints); my ($decoder_class, @args)= $tr->detect_input_format( $filename, $head_of_file ); This is used internally to detect the format of a file, but you can call it manually if you like. The following hints can be supplied as a hashref: { http_headers => ..., # hashref or various objects representing HTTP headers content_type => ..., # a MIME content-type, optional charset charset => ..., # a character set, as seen in charset=X on a MIME type filename => ..., # filename, using file extension to guess content-type content_head => ..., # the first block(s) of the file, to probe magic numbers content_ofs => ..., # a byte offset from which the input file should be read } Missing hints will be pulled from L if possible, updating the supplied hashref. The two-argument form was the previous calling convention, and doesn't provide a way to retrieve the generated hint values. The return value is the best guess of module name and constructor arguments that should be used to parse the file. However, this doesn't guarantee such module actually exists or is installed; it might just echo the file extension back to you. (which could be useful if you write your own Decoder subclass with that name) On failure, it returns an empty list. =head2 detect_input_charset my $charset= $tr->detect_input_charset(\%hints); This is used internally to detect the text encoding of a file, but you can call it manually if you like. The following hints can be supplied as a hashref: { charset => ..., # a character set, as seen in charset=X on a MIME type content_head => ..., # the first block(s) of the file content_ofs => ..., # byte offset from which detection should start } Missing hints will be pulled from L if possible, modifying the supplied hashref. The return value is the best guess of C based on the content. If the content can't be read, or isn't conclusive, this returns C. If successful, the C is stored into C<< $hints->{charset} >> overwriting any previous value, though it doesn't clear a previously set C hint on failure. If the content started with a byte-order-mark (BOM) the length of the BOM will be added to C<< $hints->{content_ofs} >>. Note that this means you shouldn't call C twice without resetting C inbetween. =head2 find_table if ($tr->find_table) { ... } Search through the input for the beginning of the records, identified by a header row matching the various constraints defined in L. If L is C, then this does nothing and assumes success. Returns a boolean of whether it succeeded. This method does I C on failure like L does, on the assumption that you want to handle them gracefully. All diagnostics about the search are logged via L, but also reported in L. =head2 field_map Build a hashref of C<< { $field_name => $col_idx_or_arrayref } >> for the current L. If the field is defined as an array field, the value will be an arrayref (even if only found in one column). Otherwise, the value is a simple scalar of the column index. =head2 iterator my $iter= $tr->iterator; while (my $rec= $iter->()) { ... } Create an iterator. If the table has not been located, then find it and C if it can't be found. Depending on the decoder and input filehandle, you might only be able to have one instance of the iterator at a time. The iterator derives from L but also has a method "all" which returns all records in an arrayref. my $records= $tr->iterator->all; =head1 THANKS Portions of this software were funded by L and L. =head1 AUTHOR Michael Conrad =head1 CONTRIBUTORS =for stopwords Christian Walde Étienne Mollier Michael Conrad =over 4 =item * Christian Walde =item * Étienne Mollier =item * Michael Conrad =back =head1 COPYRIGHT AND LICENSE This software is copyright (c) 2026 by Michael Conrad. This is free software; you can redistribute it and/or modify it under the same terms as the Perl 5 programming language system itself. =cut 12-decoder-idiot-csv.t100644001750001750 162015234670244 22520 0ustar00silverdirksilverdirk000000000000Data-TableReader-0.022/t#! /usr/bin/env perl use strict; use warnings; use Test::More; use Data::TableReader::Decoder::IdiotCSV; plan skip_all => 'Need a CSV parser for this test' unless eval { Data::TableReader::Decoder::IdiotCSV->default_csv_module }; my $input= <<'END'; "First Name","Last Name","Email" "Joseph "Joe","Smith",""Smith, Joe" " END open my $input_fh, '<', \$input or die; my $d= new_ok( 'Data::TableReader::Decoder::IdiotCSV', [ file_name => '', file_handle => $input_fh, _log => sub {} ], 'IdiotCSV decoder' ); ok( my $iter= $d->iterator, 'got iterator' ); is( $iter->dataset_idx, 0, 'dataset_idx=0' ); is_deeply( $iter->(), [ 'First Name', 'Last Name', 'Email' ], 'first row' ); is_deeply( $iter->(), [ 'Joseph "Joe', 'Smith', '"Smith, Joe" ' ], 'second row' ); is_deeply( $iter->(), undef, 'no third row' ); is( $iter->dataset_idx, 0, 'dataset_idx=0' ); done_testing; pod-coverage.t100644001750001750 200515234670244 23037 0ustar00silverdirksilverdirk000000000000Data-TableReader-0.022/xt/author#!perl # This file was automatically generated by Dist::Zilla::Plugin::Test::Pod::Coverage::Configurable 0.07. use Test::Pod::Coverage 1.08; use Test::More 0.88; BEGIN { if ( $] <= 5.008008 ) { plan skip_all => 'These tests require Pod::Coverage::TrustPod, which only works with Perl 5.8.9+'; } } use Pod::Coverage::TrustPod; my %skip = map { $_ => 1 } qw( ); my @modules; for my $module ( all_modules() ) { next if $skip{$module}; push @modules, $module; } plan skip_all => 'All the modules we found were excluded from POD coverage test.' unless @modules; plan tests => scalar @modules; my %trustme = (); my @also_private = ( qr/^BUILD$/u ); for my $module ( sort @modules ) { pod_coverage_ok( $module, { coverage_class => 'Pod::Coverage::TrustPod', also_private => \@also_private, trustme => $trustme{$module} || [], }, "pod coverage for $module" ); } done_testing(); SciTEDirectory.properties100644001750001750 11015234670244 23267 0ustar00silverdirksilverdirk000000000000Data-TableReader-0.022tabsize=3 indent.size=3 use.tabs=1 tab.indents=1 backspace.unindents=1 data000755001750001750 015234670244 17361 5ustar00silverdirksilverdirk000000000000Data-TableReader-0.022/tAddressAuxData.xls100754001750001750 2000015234670244 23120 0ustar00silverdirksilverdirk000000000000Data-TableReader-0.022/t/dataࡱ;   Root Entry  !"#$%&'()*+,-./0123456789:<?@ABDEFGH  \pCalc Ba==@ 8@"1Calibri1Arial1Arial1Arial1Calibri GENERAL #,##0                + ) , *    "8   ` Addressesq Aux DataTbZ 3  @@  1)NameAddressCityStateZipSomeone 123 Long St SomewhereOHAnother 01 Main St Elsewhere Zip CodesCitiesState Postal CodesLatLonwith population > 1,000,000PostCodeCountry PopulationAlbertaABCA New York CityNew YorkAlaskaAKUS Los Angeles CaliforniaAlabamaALChicagoIllinoisArkansasARHoustonTexasAmerican SamoaAS)cc   d-C6?_% *+&ffffff?'ffffff?(?)?"d,, ` `? ` `?U} } e }  }             ~     ~ PH0(  >@gg   d-C6?_% *+&ffffff?'ffffff?(?)?"d,, ` `? ` `?U} } }                        ~ & #‘C@ʩaj-U        ~ *]gC@ yrM.U  ~       ~ ./HMC@I*S2U  ~ l      ! "~  #  $   % &~ & '  (   PH 0(  >@gg  FMicrosoft Excel 97-TabelleBiff8Oh+'0  px mconrad1@T*@@?tA(=@a՜.+,D՜.+,\H AppVersion DocSecurityHyperlinksChangedLinksUpToDate ScaleCrop ShareDoc12.0000 Root EntryF@WorkbookCompObj;IOle =SummaryInformation(><DocumentSummaryInformation8Cd30-detect-input-format.t100644001750001750 2115215234670244 23131 0ustar00silverdirksilverdirk000000000000Data-TableReader-0.022/t#! /usr/bin/env perl use strict; use warnings; use Test::More; use Encode qw( encode ); use_ok( 'Data::TableReader' ) or BAIL_OUT; =head1 DESCRIPTION This collection of tests verify that the detect_input_format method calculates the right decoder arguments from a wide variety of input objects and with a variety of hints. =cut { # Mock of HTTP::Headers package Local::HTTPHeaders; sub new { my ($class, %headers)= @_; bless \%headers, $class; } sub header { my ($self, $name)= @_; return $self->{$name}; } } { # Mock of various web framework ::Upload objects package Local::Upload; sub new { my ($class, %args)= @_; bless \%args, $class; } sub headers { $_[0]{headers}; } } my %bom= ( 'UTF-8' => "\xEF\xBB\xBF", 'UTF-16LE' => "\xFF\xFE", 'UTF-16BE' => "\xFE\xFF", 'UTF-32LE' => "\xFF\xFE\x00\x00", 'UTF-32BE' => "\x00\x00\xFE\xFF", ); sub encode_with_bom { my ($encoding, $text)= @_; return $bom{$encoding} . encode($encoding, $text); } sub unused_input { my $x; \$x; } my $csv= <<'CSV'; name,description alpha,first beta,second CSV my $tsv= <<'TSV'; name description alpha first beta second TSV my @tests= ( { name => 'CSV from content type', hints => { content_type => 'text/csv', content_head => $csv, }, expected => [ 'CSV' ], }, { name => 'CSV content type with explicit charset', hints => { content_type => 'text/csv', charset => 'UTF-8', content_head => $csv, }, expected => [ 'CSV', encoding => 'utf-8-strict' ], }, { name => 'CSV content type contains charset', hints => { content_type => 'text/csv; charset=UTF-8', content_head => $csv, }, expected => [ 'CSV', encoding => 'utf-8-strict' ], }, { name => 'quoted charset in content type', hints => { content_type => 'text/csv; charset="ISO-8859-1"', content_head => $csv, }, expected => [ 'CSV', encoding => 'iso-8859-1' ], }, { name => 'explicit charset overrides HTTP charset', hints => { content_type => 'text/csv', charset => 'UTF-8', http_headers => { 'Content-Type' => 'text/csv; charset=ISO-8859-1', }, content_head => $csv, }, expected => [ 'CSV', encoding => 'utf-8-strict' ], }, { name => 'content type from hash headers', hints => { http_headers => { 'Content-Type' => 'text/csv; charset=UTF-8', }, content_head => $csv, }, expected => [ 'CSV', encoding => 'utf-8-strict' ], }, { name => 'case-insensitive hash header name', hints => { http_headers => { 'content_type' => 'text/tab-separated-values; charset=UTF-8', }, content_head => $tsv, }, expected => [ 'TSV', encoding => 'utf-8-strict' ], }, { name => 'content type from HTTP::Headers-like object', hints => { http_headers => Local::HTTPHeaders->new( 'Content-Type' => 'text/csv; charset=UTF-8', ), content_head => $csv, }, expected => [ 'CSV', encoding => 'utf-8-strict' ], }, { name => 'headers obtained from upload object', input => Local::Upload->new( headers => Local::HTTPHeaders->new( 'Content-Type' => 'text/tab-separated-values; charset=UTF-8', ), ), hints => { content_head => $tsv, }, expected => [ 'TSV', encoding => 'utf-8-strict' ], }, { name => 'explicit content type does not inherit charset from mismatched header', hints => { content_type => 'text/csv', http_headers => { 'Content-Type' => 'text/plain; charset=UTF-16LE', }, content_head => $csv, }, expected => [ 'CSV' ], }, { name => 'TSV from content type', hints => { content_type => 'text/tab-separated-values', content_head => $tsv, }, expected => [ 'TSV' ], }, { name => 'XLS from content type', hints => { content_type => 'application/vnd.ms-excel', content_head => '', }, expected => [ 'XLS' ], }, { name => 'XLSX from content type', hints => { content_type => 'application/vnd.openxmlformats-officedocument.spreadsheetml.sheet', content_head => '', }, expected => [ 'XLSX' ], }, { name => 'CSV from filename', hints => { filename => 'sample.csv', charset => 'UTF-8', content_head => $csv, }, expected => [ 'CSV', encoding => 'utf-8-strict' ], }, { name => 'TSV from filename', hints => { filename => 'sample.tsv', charset => 'UTF-16LE', content_head => encode('UTF-16LE', $tsv), }, expected => [ 'TSV', encoding => 'UTF-16LE' ], }, { name => 'HTM suffix normalizes to HTML', hints => { filename => 'sample.htm', content_head => '', }, expected => [ 'HTML' ], }, { name => 'XLS magic takes priority over CSV filename', hints => { filename => 'wrong.csv', content_head => "\xD0\xCF\x11\xE0\xA1\xB1\x1A\xE1", }, expected => [ 'XLS' ], }, { name => 'XLSX magic takes priority over CSV filename', hints => { filename => 'wrong.csv', content_head => "PK\x03\x04more bytes", }, expected => [ 'XLSX' ], }, { name => 'HTML UTF-8 without BOM', hints => { content_head => '', }, expected => [ 'HTML' ], }, { name => 'HTML UTF-8 with BOM', hints => { content_head => encode_with_bom( 'UTF-8', '' ), }, expected => [ 'HTML', encoding => 'utf-8-strict' ], }, { name => 'HTML UTF-16LE with BOM', hints => { content_head => encode_with_bom( 'UTF-16LE', '', ), }, expected => [ 'HTML', encoding => 'UTF-16LE' ], }, { name => 'HTML UTF-16BE with BOM', hints => { content_head => encode_with_bom( 'UTF-16BE', '', ), }, expected => [ 'HTML', encoding => 'UTF-16BE' ], }, { name => 'HTML UTF-32LE with BOM', hints => { content_head => encode_with_bom( 'UTF-32LE', '', ), }, expected => [ 'HTML', encoding => 'UTF-32LE' ], }, { name => 'HTML UTF-32BE with BOM', hints => { content_head => encode_with_bom( 'UTF-32BE', '', ), }, expected => [ 'HTML', encoding => 'UTF-32BE' ], }, { name => 'CSV probe in UTF-8', hints => { content_head => $csv, }, expected => [ 'CSV' ], }, { name => 'TSV probe in UTF-8', hints => { content_head => $tsv, }, expected => [ 'TSV' ], }, { name => 'CSV probe using supplied UTF-16LE', hints => { charset => 'UTF-16LE', content_head => encode('UTF-16LE', $csv), }, expected => [ 'CSV', encoding => 'UTF-16LE' ], }, { name => 'TSV probe using supplied UTF-32BE', hints => { charset => 'UTF-32BE', content_head => encode('UTF-32BE', $tsv), }, expected => [ 'TSV', encoding => 'UTF-32BE' ], }, { name => 'CSV probe detects UTF-16LE BOM', hints => { content_head => encode_with_bom('UTF-16LE', $csv), }, expected => [ 'CSV', encoding => 'UTF-16LE' ], }, { name => 'TSV probe detects UTF-16BE BOM', hints => { content_head => encode_with_bom('UTF-16BE', $tsv), }, expected => [ 'TSV', encoding => 'UTF-16BE' ], }, { name => 'CSV probe detects UTF-32LE without BOM', hints => { content_head => encode('UTF-32LE', $csv), }, expected => [ 'CSV', encoding => 'UTF-32LE' ], }, { name => 'TSV probe detects UTF-32BE without BOM', hints => { content_head => encode('UTF-32BE', $tsv), }, expected => [ 'TSV', encoding => 'UTF-32BE' ], }, { name => 'unknown content type falls through to probe', hints => { content_type => 'application/octet-stream', content_head => $csv, }, expected => [ 'CSV' ], }, { name => 'unknown charset is ignored', hints => { content_type => 'text/csv', charset => 'surely-not-an-encoding', content_head => $csv, }, expected => [ 'CSV' ], }, { name => 'nonsense is not detected', hints => { content_head => 'this is not tabular data', }, expected => [], }, { name => 'ambiguous equal comma and tab evidence is not detected', hints => { content_head => "one,two\tthree\n", }, expected => [], }, { name => 'empty content without filename is not detected', hints => { content_head => '', }, expected => [], }, ); for my $t (@tests) { subtest $t->{name} => sub { my $tr= new_ok( 'Data::TableReader', [ input => $t->{input} || unused_input(), fields => [], log => sub { note "$_[0] $_[1]" }, ], 'reader', ); my (@got, $error); { local $@; eval { @got= $tr->detect_input_format($t->{hints}); 1; } or $error= $@; } if (exists $t->{error}) { like( $error || '', $t->{error}, 'throws expected exception', ); } else { is( $error, undef, 'does not throw', ); is_deeply( \@got, $t->{expected}, 'detected decoder and arguments', ); } }; } done_testing; 51-typetiny-validation.t100644001750001750 375715234670244 23251 0ustar00silverdirksilverdirk000000000000Data-TableReader-0.022/t#! /usr/bin/env perl use strict; use warnings; use Test::More; use File::Spec::Functions 'catfile'; use Log::Any '$log'; use Log::Any::Adapter 'TAP', filter => 'warn'; use Data::TableReader; plan skip_all => 'Requires Types::Standard to be installed' unless eval { require Types::Standard }; my $camelcase= Types::Standard::Str() ->where(sub { /^[A-Z][a-z]*([0-9]|[A-Z][a-z]*)*\Z/ }) ->plus_coercions(Types::Standard::Str() => sub { (my $x= $_[0]) =~ s/_([a-z0-9])/uc($1)/ge; $x =~ s/^([a-z])/uc($1)/e; $x; }); subtest trim_validate_coerce => sub { my $tr= new_ok( 'Data::TableReader', [ input => [ [ 'id', 'name ', 'description' ], [ '1 ', ' test', '' ], [ '2', 'Test_2', 'Some details' ], [ '3', 'test_three ', ' yada yada' ], [ '4', "can't coerce", '' ], [ ' ', 'cant_coerce_id', '' ], ], fields => [ { name => 'id', trim => 1, type => Types::Standard::Int() }, { name => 'name', trim => 1, type => $camelcase, coerce => 1 }, { name => 'description', trim => 1, type => Types::Standard::Maybe([Types::Standard::Str()]) }, ], on_validation_error => sub { my ($reader, $failures, $record, $data_iter)= @_; for (@$failures) { my ($field, $value_ref, $message)= @$_; $$value_ref= [ $$value_ref, $message ]; } return 'use'; }, log => $log, ], 'TableReader' ); my $i= $tr->iterator; is_deeply( $i->all, [ { id => 1, name => 'Test', description => undef }, { id => 2, name => 'Test2', description => 'Some details' }, { id => 3, name => 'TestThree', description => 'yada yada' }, { id => 4, name => [ "can't coerce", q{Value "can't coerce" did not pass type constraint} ], description => undef }, { id => [ undef, q{Undef did not pass type constraint "Int"} ], name => 'CantCoerceId', description => undef }, ], 'valid row' ); }; done_testing; AddressAuxData.xlsx100754001750001750 1560515234670244 23327 0ustar00silverdirksilverdirk000000000000Data-TableReader-0.022/t/dataPK3tK _rels/.relsN0 {*5@LH!4$năD Îq~bLn,0&K^UY&c}qy/6͢~8GRoC*rOJAʤ{tJ MKcd=@r]Uw2dYqgVMmk5nIz>3W"!vJL|8 e ye} 0HM!ӷ!阘rpbͼ0gt{M#}HL3_JZPK4PK3tKdocProps/custom.xmlMo >EýBUkm5;ė;Ԓ@ݚe}tz4ٔK? ?9Q183~nvW4Ty*!2j&p9PX43P56P#4XSn6v%tykd.H;6%9qڰ<_YfY_!op)BOb .qmOrݓUh2w<َb2޵dY1RS^oGZHP:-G%'Hd#{"HE\j1)MV*.'Vba0 ^,85c ieE\_N!{w buO!FINjEx;kb}U/Msj桸YsoPHl!!$%5%l:cz5^TiFzߵI7A@ۭG"zB|~ x8~t8-u9TPKtClPK3tKxl/_rels/workbook.xml.relsj0 } $c8A[Q6o?-Rv(;@j^x@U0؍a0{ujq'/fq\Ą!f+A'v@]学%#vhUvaǾn{1ȉr3Ҁb.2o৕>?dn.:o 'e,2F^PKpPK3tKxl/sharedStrings.xmlmKo0| N$!(Ie*bt3$<8 !<3y9郳F27:*B }o~1lG$}ھX%WOǓ݀(͏p:ƾ1"t4 qY+.LV7?'\?J5u1ت"xm1g[wfva*0 W[^8 N9.+uڰ)s.n$S ivoB<՛Aa,pZ珪zUֳ,&rň}$"rru^--Krrr=#=څɀ51x#['FP\=xɿ,LIJ04Һ 2ZRCPK3)ZPK3tKxl/worksheets/sheet2.xmlXMs8p>05!@Ij٩ڛVmyei6IS$z~z?Ɵu&-\nhJVQxbB[vc}x:N dX o'j C][GR(.l(:l`"d$'%(g67=h~ 2AG bFOFv~D!9N/F`8E/!m+$N\[m!pSmܿodns'qkB)8 -Ba g:t {B'tF{^_ b ~I3XDD?"QG- ŏF(B/v̞G];vaZ7ѣ7ӢX-Awmh9sYؠH'g-c0sⴁ7O\,:HR $%ɝ̺p@k**_/ %d@>$tw<%dmN V:)P6JG)j`4$=ӑp*[(#o(Ŭ^4+b;siA̔~GwI)"Kg[[ ָ VaDpyzpKXͅ/^$ݘiioO̶.3\>2GǮ( ? 1i Yߗm~~)'o Z7MĒr ܩ=7-6Њ^4.VJ[]esM]!MO4Mal§~2=V3 PKK\PK3tKxl/worksheets/sheet1.xmlVMo8t_ÒN uN@oDYD(RKRv_CRɇbr8|3|Cϊ:',$l3u0xNq~{3u ,?g.erɕ[*UzJ\!95fRpQ!Sqd-0ͦz'^s-­x/ -Ϛ 3eAHA$tKQ8 /< D%oYWO ݲ^z2'A\܏]=ÿ` Qp3e,P$$ U5N?MP,xoXBP=B=}FQ9.PCNqOp4 yCl0i߿?\j! ?5Vz]՗6i\_WϜB^#},\m6wpn:?S)X fJh?c*$"pvik($y/%O_̯T/%}^r妳d|p|ߏ4I76¯![uEƱ0]Ŀa܂GW ~FM` h7e"Kώ0fTŹ7zwm~Ier8/4Y?/N:#x뱙zo=S[G{xMOP '#ɈbD#4`8YI~3I$IS`t6W\F7m;u&oՂ0:%41;^ll䂼r݀pc1x0P$.xV q$gv `FuҨAq:-BSX+@ "Ғɵl t l';$ٮB D@5XlF]=P=dyqr@t 8@Œ:'｡IQ@2.9u]ߝ._zܶ9pcZDk`0PKg6 PK3tK xl/styles.xmlXn }W vdjf4UUJ=ۨ, mү۱ukiK58\=>LO9XHY}"v:ywTňro|d+ `Tqd}^`{.rtS,F4r \w0lOr%ALp@bm<ҝXKxqyq}:? u&ԩr~*Z #GTSx&< Y' Qm9d&!!CnseZ<uBwdžlslkea&PyW R 6 PէB=o)~ րyg\zԙ=XC &( " X >ʼnĂ)/CucR[榢G$w5"yLXЫhj 7$Z @,kW+r(Gu ȸ L`2"BB]s, P1`c"aqXLv7tkFqX3ʣ@'ӺZPKrPK3tK[Content_Types].xmlŔOK@alۃ$AYi4mMi+( -%dR;f[ؤ tJۺbgrZXeF` oZEza/H̊ [-E||kZ~ %e_xCNRN.3E*Dt@6Cbo{5'dH@ eK`8>ص~~wnט1K xv H7Gt^??0r`ܵp'tค]: #=G%OPKvgrC\PK3tK4 _rels/.relsPK3tK?1C@'docProps/custom.xmlPK3tK@"gdocProps/app.xmlPK3tKtCldocProps/core.xmlPK3tKpJxl/_rels/workbook.xml.relsPK3tK3)Zlxl/sharedStrings.xmlPK3tKK\9xl/worksheets/sheet2.xmlPK3tKg6  xl/worksheets/sheet1.xmlPK3tKnW;V xl/styles.xmlPK3tKrxl/workbook.xmlPK3tKvgrC\%[Content_Types].xmlPK 41-user-supplied-colmap.t100644001750001750 630115234670244 23271 0ustar00silverdirksilverdirk000000000000Data-TableReader-0.022/t#! /usr/bin/env perl use strict; use warnings; use Test::More; use File::Spec::Functions 'catfile'; use Log::Any '$log'; use Log::Any::Adapter 'TAP', filter => 'warn'; use_ok( 'Data::TableReader' ) or BAIL_OUT; # Find columns when the first is known to be the ID subtest one_overridden_col => sub { my $ex= new_ok( 'Data::TableReader', [ fields => [ { name => 'prod_num' }, { name => 'description' }, { name => 'weight' }, ], input => [ [ 'Product', 'Description', 'Weight' ], [ 'ABC-DE-F', 'Precision cut widget', 1.25 ], [ 'ABC-DE-G', 'Widget with feature X', 4.5 ], ], col_map => [ 'prod_num' ], log => \my @messages, ], 'TableReader' ); ok( $ex->find_table, 'found table' ) or note explain \@messages; is_deeply( $ex->col_map, $ex->fields, 'col map' ); is_deeply( $ex->field_map, { prod_num => 0, description => 1, weight => 2 }, 'field map' ); ok( my $i= $ex->iterator, 'iterator' ); is_deeply( $i->(), { prod_num => 'ABC-DE-F', description => 'Precision cut widget', weight => 1.25 }, 'row2' ); is_deeply( $i->(), { prod_num => 'ABC-DE-G', description => 'Widget with feature X', weight => 4.5 }, 'row3' ); is( $i->(), undef, 'eof' ); }; # Specify all columns in the colmap subtest all_overridden_col => sub { my $ex= new_ok( 'Data::TableReader', [ fields => [ { name => 'prod_num' }, { name => 'a1' }, { name => 'a2' }, ], input => [ [ 'Product', 'Description', 'Weight' ], [ 'ABC-DE-F', 'Precision cut widget', 1.25 ], [ 'ABC-DE-G', 'Widget with feature X', 4.5 ], ], col_map => [ 'prod_num', 'a1', 'a2' ], log => \my @messages, ], 'TableReader' ); ok( $ex->find_table, 'found table' ) or note explain \@messages; is_deeply( $ex->col_map, $ex->fields, 'col map' ); is_deeply( $ex->field_map, { prod_num => 0, a1 => 1, a2 => 2 }, 'field map' ); ok( my $i= $ex->iterator, 'iterator' ); is_deeply( $i->(), { prod_num => 'ABC-DE-F', a1 => 'Precision cut widget', a2 => 1.25 }, 'row2' ); is_deeply( $i->(), { prod_num => 'ABC-DE-G', a1 => 'Widget with feature X', a2 => 4.5 }, 'row3' ); is( $i->(), undef, 'eof' ); }; # Specify some columns in the colmap, but the others don't match anything, and # need to just decide to use the first row in the header_row_at list for lack # of a better indication. subtest only_match_overridden => sub { my $ex= new_ok( 'Data::TableReader', [ fields => [ { name => 'prod_num' }, { name => 'a1' }, { name => 'a2', required => 0 }, ], input => [ [ 'Description about the file' ], [ 'Product', 'Description', 'Weight' ], [ 'ABC-DE-F', 'Precision cut widget', 1.25 ], [ 'ABC-DE-G', 'Widget with feature X', 4.5 ], ], header_row_at => 2, col_map => [ 'prod_num', undef, 'a1' ], log => \my @messages, ], 'TableReader' ); ok( $ex->find_table, 'found table' ) or note explain \@messages; is_deeply( $ex->col_map, [ $ex->fields->[0], undef, $ex->fields->[1] ], 'col map' ); is_deeply( $ex->field_map, { prod_num => 0, a1 => 2 }, 'field map' ); ok( my $i= $ex->iterator, 'iterator' ); is_deeply( $i->(), { prod_num => 'ABC-DE-F', a1 => 1.25 }, 'row2' ); is_deeply( $i->(), { prod_num => 'ABC-DE-G', a1 => 4.5 }, 'row3' ); is( $i->(), undef, 'eof' ); }; done_testing; TableReader000755001750001750 015234670244 21776 5ustar00silverdirksilverdirk000000000000Data-TableReader-0.022/lib/DataField.pm100644001750001750 2154315234670244 23544 0ustar00silverdirksilverdirk000000000000Data-TableReader-0.022/lib/Data/TableReaderpackage Data::TableReader::Field; use Moo 2; use Carp; use namespace::clean; # ABSTRACT: Field specification for Data::TableReader our $VERSION = '0.022'; # VERSION has name => ( is => 'ro', required => 1 ); *addr= \&Scalar::Util::refaddr; has header => ( is => 'ro' ); has required => ( is => 'ro', default => sub { 1 } ); has trim => ( is => 'ro', default => sub { 1 } ); has blank => ( is => 'ro' ); # default is undef has type => ( is => 'ro', isa => sub { ref $_[0] eq 'CODE' or $_[0]->can('validate') } ); has coerce => ( is => 'ro', isa => sub { ref $_[0] eq 'CODE' or !ref $_[0] } ); has array => ( is => 'ro' ); has follows => ( is => 'ro' ); sub follows_list { my $f= shift->follows; ref $f? @$f : defined $f? ( $f ) : () } sub BUILD { my $self= shift; if ($self->coerce) { croak "To coerce field ".$self->name.", either 'coerce' must be a coderef or 'type' must have a ->coerce method" unless ref $self->coerce eq 'CODE' or (defined $self->type && ref($self->type)->can('coerce')); } } has header_regex => ( is => 'lazy' ); sub _build_header_regex { my $self= shift; my $h= $self->header; unless (defined $h) { $h= $self->name; $h =~ s/([[:lower:]])([[:upper:]])/$1 $2/g; # split words on camelCase $h =~ s/([[:alpha:]])([[:digit:]])/$1 $2/g; # or digit $h =~ s/([[:digit:]])([[:alpha:]])/$1 $2/g; $h =~ s/_/ /g; # then split on underscore } return $h if ref($h) eq 'Regexp'; my $pattern= join "[\\W_]*", map { $_ eq "\n"? '\n' : "\Q$_\E" } grep { defined && length } split /(\n)|\s+|(\W)/, $h; # capture newline or non-word, except for other whitespace return qr/^[\W_]*$pattern[\W_]*$/im; } has trim_coderef => ( is => 'lazy' ); sub _default_trim_coderef { $_ =~ s/\s+$//; $_ =~ s/^\s+//; } sub _build_trim_coderef { my $t= shift->trim; return undef unless $t; return \&_default_trim_coderef if !ref $t; return $t if ref $t eq 'CODE'; return sub { s/$t//g; } if ref $t eq 'Regexp'; croak("Can't convert ".ref($t)." to a coderef"); } 1; __END__ =pod =encoding UTF-8 =head1 NAME Data::TableReader::Field - Field specification for Data::TableReader =head1 VERSION version 0.022 =head1 DESCRIPTION This class describes aspects of one of the fields you want to find in your spreadsheet. =head1 ATTRIBUTES =head2 name Required. Used for the hashref key if you pull records as hashes, and used in diagnostic messages. =head2 addr Convenience for C<< refaddr($field) >>. This should be used any time you use the field as a key in a hashref, if there is any chance your names aren't distinct. =head2 header A string or regex describing the column header you want to find in the spreadsheet. If you specify a regex, it is used directly. If you specify a string, it becomes the regex matching any string with the same words (\w+) and non-whitespace (\S+) characters in the same order, case insensitive, surrounded by any amount of non-alphanumeric garbage (C<[\W_]*>). When no header is specified, the L is used as a string after first breaking it into words on underscore or camel-case or numeric boundaries. This deserves some examples: Name Implied Default Header "zipcode" "zipcode" "ZipCode" "Zip Code" "Zip_Code" "zip Code" "zip5" "zip 5" Header Regex Could Match... "ZipCode" /^[\W_]*ZipCode[\W_]*$/i "zipcode:" "zip_code" /^[\W_]*zip_code[\W_]*$/i "--ZIP_CODE--" "zip code" /^[\W_]*zip[\W_]*code[\W_]*$/i "ZIP\nCODE " "zip-code" /^[\W_]*zip[\W_]*-[\W_]*code[\W_]*$/i "ZIP-CODE:" qr/Zip.*Code/ /Zip.*Code/ "Post(Zip)Code" If this default matching doesn't meet your needs or paranoia level, then you should always specify your own header regexes. (If your data actually doesn't have any header at all and you want to brazenly assume the columns match the fields, see reader attribute L) =head2 required Whether or not this field must be found in order to detect a table. Defaults is B. Note this does B require the field of a row to contain data in order to read a record from the table; it just requires a column to exist. =head2 trim # remove leading/trailing whitespace trim => 1 # remove leading/trailing whitespace but also remove "N/A" and "NULL" trim => qr( ^ \s* N/A \s* $ | ^ \s* NULL \s* $ | ^ \s+ | \s+ $ )xi # custom search/replace in a coderef trim => sub { s/[\0-\1F\7F]+/ /g; s/^\s+//; s/\s+$//; }; If set to a non-reference, this is treated as a boolean of whether to remove leading and trailing whitespace. If set to a coderef, the coderef will be called for each value with C<$_> set to the current value; it should modify C<$_> as appropriate (return value is ignored). It can also be set to a regular expression of all the patterns to remove, as per C<< s/$regexp//g >>. Default is B<1>, which is equivalent to a regular expression of C<< qr/(^\s+)|(\s+$)/ >>. =head2 blank The value to extract when the spreadsheet cell is an empty string or undef. (after any processing done by L) Default is C. Another common value would be C<"">. =head2 type A L type (or any object or class with a C method) or a coderef which returns a validation error message (undef if it is valid). use Types::Standard; ... type => Maybe[Int] # or without Type::Tiny type => sub { $_[0] =~ /^\w+/? undef : "word-characters only" }, This is an optional feature and there is no default. The behavior of a validation failure depends on the options to TableReader. =head2 coerce If C validation fails, this gives you a second chance at fixing the field. Set this to a true value to call C<< $field->type->coerce >> on the value, or set it to a coderef of the form C<< $coerced_value= $coerce->($value) >>. Type validation will be attempted a second time on the coerced value, and if successful it replaces the original value. If it fails, the original value remains in the record (and you can handle it how you like in the L callback|Data::TableReader/on_validation_error>. If you want to apply a coercion before the first type validation is attempted, you can put that logic into the L attribute. =head2 array Boolean of whether this field can be found multiple times in one table. Default is B. If true, the value of the field will always be an arrayref (even if only one column matched). =head2 follows Name (or arrayref of names) of a field which this field must follow, in a first-to-last ordering of the columns. This field must occur immediately after the named field(s), or after another field which also has a C restriction and follows the named field(s). The purpose of this attribute is to resolve ambiguous columns. Suppose you expect columns with the following headers: Father | | | | Mother | | | FirstName | LastName | Tel. | Email | FirstName | LastName | Tel. | Email You can use C to identify the first column, but after FirstName the rest are ambiguous. But, TableReader can figure it out if you say: { name => 'father_first', header => qr/Father\nFirstName/ }, { name => 'father_last', header => 'LastName', follows => 'father_first' }, { name => 'father_tel', header => 'Tel.', follows => 'father_first' }, { name => 'father_email', header => 'Email', follows => 'father_first' }, .. and so on. Note how C<'father_first'> is used for each as the C name; this way if any non-required fields (like maybe C) are completely removed from the file, TableReader will still be able to find C and C. You can also use this to accumulate an array of columns that lack headers: Scores | | | | | | | OtherData 12% | 35% | 42% | 18% | 65% | 99% | 55% | xyz { name => 'scores', array => 1, trim => 1 }, { name => 'scores', array => 1, trim => 1, header => '', follows => 'scores' }, The second field definition has an empty header, which would normally make it rather ambiguous and potentially capture blank-header columns that might not be part of the array. But, because it must follow a column named 'scores' there's no ambiguity; you get exactly any column starting from the header C<'Scores'> until a column of any other header. =head2 follows_list Convenience accessor for C<< @{ ->follows } >>, useful because C might be either a scalar or arrayref. =head2 header_regex L, coerced to a regex if it wasn't already =head1 AUTHOR Michael Conrad =head1 COPYRIGHT AND LICENSE This software is copyright (c) 2026 by Michael Conrad. This is free software; you can redistribute it and/or modify it under the same terms as the Perl 5 programming language system itself. =cut Decoder.pm100644001750001750 560715234670244 24051 0ustar00silverdirksilverdirk000000000000Data-TableReader-0.022/lib/Data/TableReaderpackage Data::TableReader::Decoder; use Moo 2; # ABSTRACT: Base class for table decoders our $VERSION = '0.022'; # VERSION has file_handle => ( is => 'ro', required => 1 ); has real_file_name => ( is => 'rw' ); has client_file_name => ( is => 'rw' ); *file_name= *real_file_name; # back-compat has _log => ( is => 'ro', required => 1 ); *log= *_log; # back-compat, but deprecated since it doesn't match ->log on TableReader sub BUILD { my ($self, $args)= @_; # Previous attribute name was 'file_name' $self->real_file_name($args->{file_name}) if defined $args->{file_name} && !defined $self->real_file_name; } sub _first_sufficient_module { my ($name, $modules, $req_versions)= @_; require Module::Runtime; for my $mod (@$modules) { my ($pkg, $ver)= ref $mod eq 'ARRAY'? @$mod : ( $mod, 0 ); next unless eval { Module::Runtime::use_module($pkg, $ver) }; # Special case for Excel modules that use Archive::Zip and don't declare proper # version requirements for it: # https://github.com/MichaelDaum/spreadsheet-parsexlsx/pull/12 if ($pkg =~ /XLSX/ && !eval { Module::Runtime::use_module('Archive::Zip', 1.34) }) { Carp::carp("Your version of Archive::Zip is not new enough to make use of $pkg"); next; } return $pkg } require Carp; Carp::croak "No $name available (or of sufficient version); install one of: " .join(', ', map +(ref $_ eq 'ARRAY'? "$_->[0] >= $_->[1]" : $_), @$modules); } 1; __END__ =pod =encoding UTF-8 =head1 NAME Data::TableReader::Decoder - Base class for table decoders =head1 VERSION version 0.022 =head1 DESCRIPTION This is an abstract base class describing the API for decoders. A decoder's job is to iterate table rows of a file containing tabular data. If a file provides multiple tables of data (such as worksheets, or tags) then the decode should also support the "next_dataset" method. =head1 ATTRIBUTES =head2 file_handle This is what the iterator should parse. Streams should work, but for best results use a seekable file handle. =head2 real_file_name Indicates real filename of C, or C if that can't be determined. =head2 client_file_name Indicates a client-side file name which should be used in client-facing log messages. =head1 METHODS =head2 iterator This must be implemented by the subclass, to return an instance of L. The iterator should return an arrayref each time it is called, and accept one optional argument of a "slice" needed from the record. All decoder iterators return arrayrefs, so the slice should be an arrayref of column indicies equivalent to the perl syntax @row[@$slice] =head1 AUTHOR Michael Conrad =head1 COPYRIGHT AND LICENSE This software is copyright (c) 2026 by Michael Conrad. This is free software; you can redistribute it and/or modify it under the same terms as the Perl 5 programming language system itself. =cut Iterator.pm100644001750001750 650215234670244 24270 0ustar00silverdirksilverdirk000000000000Data-TableReader-0.022/lib/Data/TableReaderpackage Data::TableReader::Iterator; use strict; use warnings; use Carp; use Scalar::Util 'refaddr'; # ABSTRACT: Base class for iterators (blessed coderefs) our $VERSION = '0.022'; # VERSION our %_iterator_fields; sub new { my ($class, $sub, $fields)= @_; ref $sub eq 'CODE' and ref $fields eq 'HASH' or croak "Expected new(CODEREF, HASHREF)"; $_iterator_fields{refaddr $sub}= $fields; return bless $sub, $class; } sub _fields { $_iterator_fields{refaddr shift}; } sub DESTROY { delete $_iterator_fields{refaddr shift}; } sub progress { undef; } sub row { croak "Unimplemented"; } sub dataset_idx { 0 } sub tell { undef; } sub seek { croak "Unimplemented"; } sub next_dataset { undef; } 1; __END__ =pod =encoding UTF-8 =head1 NAME Data::TableReader::Iterator - Base class for iterators (blessed coderefs) =head1 VERSION version 0.022 =head1 SYNOPSIS my $iter= $record_reader->iterator; while (my $rec= $iter->()) { ... my $position= $iter->tell; print "Marking position $position"; # position stringifies to human-readable ... $iter->seek($position); } if ($iter->next_dataset) { # iterate some more while ($rec= $iter->()) { ... printf "Have processed %3d %% of the file", $iter->progress*100; } } =head1 DESCRIPTION This is the abstract base class for iterators used in Data::TableReader, which are blessed coderefs that return records on each call. The coderef should support a single argument of a "slice" to extract from the record, in case not all of the record is needed. =head1 ATTRIBUTES =head2 position Return a human-readable string describing the current location within the source file. This will be something like C<"$filename row $row"> or C<"$filename $worksheet:$cell_id">. =head2 row A numeric 1-based row number for the current position of the current dataset. This is not affected by which row the header was found on. =head2 dataset_idx A numeric 0-based dataset number. For Decoders which only support a single dataset, this is always C<0>. =head2 progress An estimate of how much of the data has already been returned. If the stream is not seekable this may return undef. =head1 METHODS =head2 new $iter= Data::TableReader::Iterator->new( \&coderef, \%fields ); The iterator is a blessed coderef. The first argument is the coderef to be blessed, and the second argument is the magic hashref of fields to be made available as C<< $iter->_fields >>. =head2 tell If seeking is supported, this will return some value that can be passed to seek to come back to this point in the stream. This value will always be true. If seeking is not supported this will return undef. =head2 seek $iter->seek($pos); Seek to a point previously reported by L. If seeking is not supported this will die. If C<$pos> is any false value it means to seek to the start of the stream. =head2 next_dataset If a file format supports more than one tabular group of data, this method allows you to jump to the next. Returns true if it moved to a new dataset, and false at the end of iteration. =head1 AUTHOR Michael Conrad =head1 COPYRIGHT AND LICENSE This software is copyright (c) 2026 by Michael Conrad. This is free software; you can redistribute it and/or modify it under the same terms as the Perl 5 programming language system itself. =cut 42-user-overrides-found-header.t100644001750001750 252615234670244 24542 0ustar00silverdirksilverdirk000000000000Data-TableReader-0.022/t#! /usr/bin/env perl use strict; use warnings; use Test::More; use File::Spec::Functions 'catfile'; use Log::Any '$log'; use Log::Any::Adapter 'TAP', filter => 'warn'; use_ok( 'Data::TableReader' ) or BAIL_OUT; # In this scenario, the user asks to find the best header, but then runs their own logic to # choose a header row they like better. The table Iterator should run with whatever candicdate # they put in ->table_search_results->{found} my $tr= new_ok( 'Data::TableReader', [ fields => [ { name => 'prod_num' }, { name => 'description', required => 0 }, { name => 'weight', required => 0 }, ], input => [ [ qw( a b c ) ], [ qw( d e f ) ], [ qw( g h i ) ], ], col_map => [ 'prod_num' ], on_unknown_columns => 'error', # causes it to scan all rows log => \my @messages, ], 'TableReader' ); ok( !$tr->find_table, 'didn\'t find table' ) or note explain \@messages; is( scalar @{$tr->table_search_results->{candidates}}, 3, '3 candidates' ); ok( !defined $tr->table_search_results->{found}, 'not found' ); $tr->table_search_results->{found}= $tr->table_search_results->{candidates}[1]; # override col_map $tr->table_search_results->{found}{col_map}[2]= $tr->fields->[2]; my $i= $tr->iterator; is_deeply( $i->(), { prod_num => 'g', weight => 'i' }, 'row2 is header, row3 is data' ); is( $i->(), undef, 'eof' ); done_testing; Decoder000755001750001750 015234670244 23343 5ustar00silverdirksilverdirk000000000000Data-TableReader-0.022/lib/Data/TableReaderCSV.pm100644001750001750 2010015234670244 24505 0ustar00silverdirksilverdirk000000000000Data-TableReader-0.022/lib/Data/TableReader/Decoderpackage Data::TableReader::Decoder::CSV; use Moo 2; use Carp; use IO::Handle; extends 'Data::TableReader::Decoder'; # ABSTRACT: Access rows of a comma-delimited text file our $VERSION = '0.022'; # VERSION our @csv_probe_modules= ( ['Text::CSV_XS' => 1.06], ['Text::CSV' => 1.91] ); our $default_csv_module; sub default_csv_module { $default_csv_module ||= Data::TableReader::Decoder::_first_sufficient_module('CSV parser', \@csv_probe_modules); } has _parser_args => ( is => 'ro', init_arg => 'parser' ); has parser => ( is => 'lazy', init_arg => undef ); sub _build_parser { my $self= shift; my $args= $self->_parser_args || {}; return $args if ref($args)->can('getline'); return $self->default_csv_module->new({ binary => 1, allow_loose_quotes => 1, auto_diag => 2, %$args }); } has autodetect_encoding => ( is => 'rw', default => sub { 1 } ); sub BUILD { my ($self, $args)= @_; $self->encoding($args->{encoding}) if defined $args->{encoding}; } sub encoding { my ($self, $enc)= @_; my $fh= $self->file_handle; if (defined $enc) { # protect against binmode string injection croak "invalid/unknown encoding '$enc'" unless Encode::find_encoding($enc); binmode($fh, ":encoding($enc)"); return $enc; } my @layers= PerlIO::get_layers($fh); if (($enc)= grep { /^encoding|^utf/i } @layers) { # extract encoding name return 'UTF-8' if $enc eq 'utf8'; return uc($1) if $enc =~ /encoding\(([^)]+)\)/; return uc($enc); # could throw a parse error, but this is probably more useful behavior } # fh_start_pos will be set if we have already checked for BOM if ($self->autodetect_encoding && !defined $self->_fh_start_pos) { $self->_fh_start_pos(tell $fh or 0); if (($enc= $self->_autodetect_bom($fh))) { binmode($fh, ":encoding($enc)"); # re-mark the start after the BOM $self->_fh_start_pos(tell $fh or 0); return $enc; } } return ''; } has _fh_start_pos => ( is => 'rw' ); has _iterator => ( is => 'rw', weak_ref => 1 ); has _row_ref => ( is => 'rw' ); sub iterator { my $self= shift; croak "Multiple iterators on CSV stream not supported yet" if $self->_iterator; my $parser= $self->parser; my $fh= $self->file_handle; my $row_ref= $self->_row_ref; # Keeping this object is just an indication of whether an iterator has been used yet if (!$row_ref) { $self->_row_ref($row_ref= \(my $row= 0)); # trigger BOM detection if needed my $enc= $self->encoding; $self->_log->('debug', "encoding is ".($enc||'maybe utf8')); # ensure _fh_start_pos is set $self->_fh_start_pos(tell $fh or 0); } elsif ($$row_ref) { $self->_log->('debug', 'Seeking back to start of input'); seek($fh, $self->_fh_start_pos, 0) or die "Can't seek back to start of stream"; $$row_ref= 0; } my $i= Data::TableReader::Decoder::CSV::_Iter->new( sub { my $r= $parser->getline($fh) or return undef; ++$$row_ref; @$r= @{$r}[ @{$_[0]} ] if $_[0]; # optional slice argument return $r; }, { row => $row_ref, fh => $fh, origin => $self->_fh_start_pos, } ); $self->_iterator($i); return $i; } # This design is simplified from File::BOM in that it ignores UTF-32 # and in any "normal" case it can read from a pipe with only one # character to push back, avoiding the need to tie the file handle. # It also checks for whether layers have already been enabled. # It also avoids seeking to the start of the file handle, in case # the user deliberately seeked to a position. sub _autodetect_bom { my ($self, $fh)= @_; my $fpos= tell($fh); local $!; read($fh, my $buf, 1) || return; if ($buf eq "\xFF" || $buf eq "\xFE" || $buf eq "\xEF") { if (read($fh, $buf, 1, 1)) { if ($buf eq "\xFF\xFE") { return 'UTF-16LE'; } elsif ($buf eq "\xFE\xFF") { return 'UTF-16BE'; } elsif ($buf eq "\xEF\xBB" and read($fh, $buf, 1, 2) and $buf eq "\xEF\xBB\xBF") { return 'UTF-8'; } } } # It wasn't a BOM. Try to undo our read. $self->_log->('debug', 'No BOM in stream, seeking back to start'); if (length $buf == 1) { $fh->ungetc(ord $buf); } elsif (!seek($fh, $fpos, 0)) { # Can't seek if ($fh->can('ungets')) { # support for FileHandle::Unget $fh->ungets($buf); } else { croak "Can't seek input handle after BOM detection; You should set an encoding manually, buffer the entire input, or use FileHandle::Unget"; } } return; } # If you need to subclass this iterator, don't. Just implement your own. # i.e. I'm not declaring this implementation stable, yet. use Data::TableReader::Iterator; BEGIN { @Data::TableReader::Decoder::CSV::_Iter::ISA= ('Data::TableReader::Iterator'); } sub Data::TableReader::Decoder::CSV::_Iter::position { my $f= shift->_fields; 'row '.${ $f->{row} }; } sub Data::TableReader::Decoder::CSV::_Iter::row { ${ shift->_fields->{row} } } sub Data::TableReader::Decoder::CSV::_Iter::progress { my $f= shift->_fields; # lazy-build the file size, using seek unless (exists $f->{file_size}) { my $pos= tell $f->{fh}; if (defined $pos and $pos >= 0 and seek($f->{fh}, 0, 2)) { $f->{file_size}= tell($f->{fh}); seek($f->{fh}, $pos, 0) or die "seek: $!"; } else { $f->{file_size}= undef; } } return $f->{file_size}? (tell $f->{fh})/$f->{file_size} : undef; } sub Data::TableReader::Decoder::CSV::_Iter::tell { my $f= shift->_fields; my $pos= tell($f->{fh}); return undef unless defined $pos && $pos >= 0; return [ $pos, ${$f->{row}} ]; } sub Data::TableReader::Decoder::CSV::_Iter::seek { my ($self, $to)= @_; my $f= $self->_fields; seek($f->{fh}, ($to? $to->[0] : $f->{origin}), 0) or croak("seek failed: $!"); ${ $f->{row} }= $to? $to->[1] : 0; 1; } 1; __END__ =pod =encoding UTF-8 =head1 NAME Data::TableReader::Decoder::CSV - Access rows of a comma-delimited text file =head1 VERSION version 0.022 =head1 DESCRIPTION This decoder wraps an instance of either L or L. You may pass your own options via the L attribute, which will override the defaults of this module on a per-field basis. This module defaults to: parser => { binary => 1, allow_loose_quotes => 1, auto_diag => 2, } This module makes an attempt at automatic unicode support: =over =item * If the stream has a PerlIO encoding() on it, no additional decoding is done. =item * If the stream has a BOM (byte-order mark) for UTF-8 or UTF-16, it adds that encoding with C. =item * Else, it lets the parser decide. The default Text::CSV parser will automatically upgrade UTF-8 sequences that it finds. (and, you can't disable this without also disabling unicode received from IO layers, which seems like a bug...) =back Because auto-detection might need to read multiple bytes, it is possible that for non-seekable streams (like pipes, stdin, etc) this may result in an exception. Only un-seekable streams beginning with C<"\xEF">, C<"\xFE">, or C<"\xFF"> will have this problem. You can solve this by supplying an encoding layer on the file handle (avoiding detection), setting L to false, buffering the entire input in a scalar and creating a file handle from that (making it seekable), or using a file handle that supports "ungets" like L. =head1 ATTRIBUTES =head2 parser An instance of L or L or compatible, or arguments to pass to the constructor. Constructor arguments are passed to CSV_XS if it is installed, else CSV. =head2 autodetect_encoding Whether to look for a byte-order mark on the input. =head2 encoding If autodetection is enabled, this will first check for a byte-order mark on the input. Else, or afterward, it will return whatever encoding PerlIO layer is configured on the file handle. Setting this attribute will change the PerlIO layer on the file handle, possibly skipping detection. =head2 iterator my $iterator= $decoder->iterator; Return an L which returns each row of the table as an arrayref. =head1 AUTHOR Michael Conrad =head1 COPYRIGHT AND LICENSE This software is copyright (c) 2026 by Michael Conrad. This is free software; you can redistribute it and/or modify it under the same terms as the Perl 5 programming language system itself. =cut TSV.pm100644001750001750 221215234670244 24512 0ustar00silverdirksilverdirk000000000000Data-TableReader-0.022/lib/Data/TableReader/Decoderpackage Data::TableReader::Decoder::TSV; use Moo 2; use Carp; use Log::Any '$log'; # ABSTRACT: Access rows of a tab-delimited text file our $VERSION = '0.022'; # VERSION extends 'Data::TableReader::Decoder::CSV'; sub _build_parser { my $args= shift->_parser_args || {}; Data::TableReader::Decoder::CSV->default_csv_module->new({ binary => 1, allow_loose_quotes => 1, auto_diag => 2, sep_char => "\t", escape_char => undef, %$args, }); } 1; __END__ =pod =encoding UTF-8 =head1 NAME Data::TableReader::Decoder::TSV - Access rows of a tab-delimited text file =head1 VERSION version 0.022 =head1 DESCRIPTION This module is a simple subclass of L which supplies these defaults for the parser: parser => { binary => 1, allow_loose_quotes => 1, sep_char => "\t", escape_char => undef, auto_diag => 2, } =head1 AUTHOR Michael Conrad =head1 COPYRIGHT AND LICENSE This software is copyright (c) 2026 by Michael Conrad. This is free software; you can redistribute it and/or modify it under the same terms as the Perl 5 programming language system itself. =cut XLS.pm100644001750001750 327315234670244 24514 0ustar00silverdirksilverdirk000000000000Data-TableReader-0.022/lib/Data/TableReader/Decoderpackage Data::TableReader::Decoder::XLS; use Moo 2; use Carp; extends 'Data::TableReader::Decoder::Spreadsheet'; our @xls_probe_modules= ( [ 'Spreadsheet::ParseExcel', '0.66' ] ); our $default_xls_module; sub default_xls_module { $default_xls_module ||= Data::TableReader::Decoder::_first_sufficient_module('XLS parser', \@xls_probe_modules); } # ABSTRACT: Access sheets/rows of a Microsoft Excel '97 workbook our $VERSION = '0.022'; # VERSION sub _build_workbook { my $self= shift; my $wbook; my $f= $self->file_handle; if (ref $f and ref($f)->can('worksheets')) { $wbook= $f; } else { $wbook= $self->default_xls_module->new->parse($f, $self->xls_formatter); } defined $wbook or croak "Can't parse file '".$self->file_name."'"; return $wbook; } 1; __END__ =pod =encoding UTF-8 =head1 NAME Data::TableReader::Decoder::XLS - Access sheets/rows of a Microsoft Excel '97 workbook =head1 VERSION version 0.022 =head1 DESCRIPTION See L. This subclass simply parses the input using an instance of L. =head1 CLASS METHODS =head2 default_xls_module Initializes C<@Data::TableReader::Decoder::XLS::default_xls_module> to the first available module in the list of C<@Data::TableReader::Decoder::XLS::xls_probe_modules> and returns the cached value every time afterward. Those variables can be modified as needed, if you have other XLS modules available. =head1 AUTHOR Michael Conrad =head1 COPYRIGHT AND LICENSE This software is copyright (c) 2026 by Michael Conrad. This is free software; you can redistribute it and/or modify it under the same terms as the Perl 5 programming language system itself. =cut Mock.pm100644001750001750 1040715234670244 24754 0ustar00silverdirksilverdirk000000000000Data-TableReader-0.022/lib/Data/TableReader/Decoderpackage Data::TableReader::Decoder::Mock; use Moo 2; use Carp 'croak'; use IO::Handle; require MRO::Compat if $] < '5.010'; extends 'Data::TableReader::Decoder'; # ABSTRACT: Decoder that returns supplied data without decoding anything our $VERSION = '0.022'; # VERSION sub BUILDARGS { my $args= $_[0]->next::method(@_[1..$#_]); # back-compat with earlier versions $args->{datasets}= delete $args->{data} if defined $args->{data}; # allow simple way for user to specify a single table $args->{datasets}= [ delete $args->{table} ] if defined $args->{table}; $args; } has datasets => ( is => 'rw', isa => \&_arrayref_3_deep ); *data= *datasets; sub _arrayref_3_deep { ref $_[0] eq 'ARRAY' or return 'Not an arrayref'; return undef unless @{$_[0]}; ref $_[0][0] eq 'ARRAY' or return 'Not an arrayref of tables'; return undef unless @{$_[0][0]}; ref $_[0][0][0] eq 'ARRAY' or return 'Not an arrayref of tables of rows'; return undef unless @{$_[0][0][0]}; ref $_[0][0][0][0] ne 'ARRAY' or return 'Expected plain cell value at ->[$dataset][$table][$cell] depth of arrayrefs'; undef; } sub iterator { my $self= shift; my $data= $self->datasets; my $table= $data->[0]; my $rowmax= $table? $#$table : -1; my $row= -1; Data::TableReader::Decoder::Mock::_Iter->new( sub { my $slice= shift; return undef unless $row < $rowmax; my $datarow= $table->[++$row]; return [ @{$datarow}[@$slice] ] if $slice; return $datarow; }, { data => $data, table_idx => 0, table_ref => \$table, row_ref => \$row, rowmax_ref => \$rowmax, origin => [ 0, $row ], } ); } # If you need to subclass this iterator, don't. Just implement your own. # i.e. I'm not declaring this implementation stable, yet. use Data::TableReader::Iterator; BEGIN { @Data::TableReader::Decoder::Mock::_Iter::ISA= ('Data::TableReader::Iterator'); } sub Data::TableReader::Decoder::Mock::_Iter::position { my $f= shift->_fields; 'row '.(1 + ${ $f->{row_ref} }); } sub Data::TableReader::Decoder::Mock::_Iter::row { 1 + ${ shift->_fields->{row_ref} }; } sub Data::TableReader::Decoder::Mock::_Iter::dataset_idx { shift->_fields->{table_idx} } sub Data::TableReader::Decoder::Mock::_Iter::progress { my $f= shift->_fields; return ${ $f->{row_ref} } / (${ $f->{rowmax_ref} } || 1); } sub Data::TableReader::Decoder::Mock::_Iter::tell { my $f= shift->_fields; return [ $f->{table_idx}, ${$f->{row_ref}} ]; } sub Data::TableReader::Decoder::Mock::_Iter::seek { my ($self, $to)= @_; my $f= $self->_fields; $to ||= $f->{origin}; my ($table_idx, $row)= @$to; my $table= $f->{data}[$table_idx]; my $rowmax= $table? $#$table : -1; $row= -1 unless defined $row; $f->{table_idx}= $table_idx; ${$f->{table_ref}}= $table; ${$f->{row_ref}}= $row; ${$f->{rowmax_ref}}= $rowmax; 1; } sub Data::TableReader::Decoder::Mock::_Iter::next_dataset { my $self= shift; my $f= $self->_fields; return defined $f->{data}[ $f->{table_idx}+1 ] && $self->seek([ $f->{table_idx}+1 ]); } 1; __END__ =pod =encoding UTF-8 =head1 NAME Data::TableReader::Decoder::Mock - Decoder that returns supplied data without decoding anything =head1 VERSION version 0.022 =head1 SYNOPSIS decoder => { CLASS => 'Mock', datasets => [ [ # Data Set 0 [ 1, 2, 3, 4, 5 ], ... ], [ # Data Set 1 [ 1, 2, 3, 4, 5 ], ... ], ] } or decoder => { CLASS => 'Mock', table => [ [ 1, 2, 3, 4, 5 ], ... ], } This doesn't actually decode anything; it just returns verbatim rows of data from arrayrefs that you supply. You can provide one or multiple tables. The 'table' constructor parameter is an alias for C<< datasets[0] >>. =head1 ATTRIBUTES See attributes from parent class: L. =head2 datasets The verbatim data which will be returned by the iterator. This can be an array of tables, or one table itself. A table must be composed of arrayrefs, and the cells of the table cannot themselves be arrayrefs. =head1 AUTHOR Michael Conrad =head1 COPYRIGHT AND LICENSE This software is copyright (c) 2026 by Michael Conrad. This is free software; you can redistribute it and/or modify it under the same terms as the Perl 5 programming language system itself. =cut XLSX.pm100644001750001750 360415234670244 24642 0ustar00silverdirksilverdirk000000000000Data-TableReader-0.022/lib/Data/TableReader/Decoderpackage Data::TableReader::Decoder::XLSX; use Moo 2; use Carp; extends 'Data::TableReader::Decoder::Spreadsheet'; our @xlsx_probe_modules= ( [ 'Spreadsheet::ParseXLSX', '0.30' ], 'Spreadsheet::XLSX' ); our $default_xlsx_module; sub default_xlsx_module { $default_xlsx_module ||= Data::TableReader::Decoder::_first_sufficient_module('XLSX parser', \@xlsx_probe_modules); } # ABSTRACT: Access sheets/rows of a modern Microsoft Excel workbook our $VERSION = '0.022'; # VERSION sub _build_workbook { my $self= shift; my $wbook; my $f= $self->file_handle; if (ref $f and ref($f)->can('worksheets')) { $wbook= $f; } else { my $class= $self->default_xlsx_module; # Spreadsheet::XLSX has an incompatible constructor if ($class->isa('Spreadsheet::XLSX')) { $wbook= $class->new($f); } else { $wbook= $class->new->parse($f, $self->xls_formatter); } } defined $wbook or croak "Can't parse file '".$self->file_name."'"; return $wbook; } 1; __END__ =pod =encoding UTF-8 =head1 NAME Data::TableReader::Decoder::XLSX - Access sheets/rows of a modern Microsoft Excel workbook =head1 VERSION version 0.022 =head1 DESCRIPTION See L. This subclass simply parses the input using an instance of L. =head1 CLASS METHODS =head2 default_xlsx_module Initializes C<@Data::TableReader::Decoder::XLSX::default_xlsx_module> to the first available module in the list of C<@Data::TableReader::Decoder::XLSX::xlsx_probe_modules> and returns the cached value every time afterward. Those variables can be modified as needed, if you have other XLSX modules available. =head1 AUTHOR Michael Conrad =head1 COPYRIGHT AND LICENSE This software is copyright (c) 2026 by Michael Conrad. This is free software; you can redistribute it and/or modify it under the same terms as the Perl 5 programming language system itself. =cut IdiotCSV.pm100644001750001750 417115234670244 25470 0ustar00silverdirksilverdirk000000000000Data-TableReader-0.022/lib/Data/TableReader/Decoderpackage Data::TableReader::Decoder::IdiotCSV; use Moo 2; use Carp; use Log::Any '$log'; extends 'Data::TableReader::Decoder::CSV'; # ABSTRACT: Access rows of a badly formatted comma-delimited text file our $VERSION = '0.022'; # VERSION sub _build_parser { my $args= shift->_parser_args || {}; Data::TableReader::Decoder::CSV->default_csv_module->new({ binary => 1, allow_loose_quotes => 1, allow_whitespace => 1, auto_diag => 1, escape_char => undef, %$args, }); } 1; __END__ =pod =encoding UTF-8 =head1 NAME Data::TableReader::Decoder::IdiotCSV - Access rows of a badly formatted comma-delimited text file =head1 VERSION version 0.022 =head1 DESCRIPTION This decoder is like L<::Decoder::CSV|Data::TableReader::Decoder::CSV>, but can additionally parse the garbage resulting from those special people who write "CSV Export" code that looks like print join(",", map qq{"$_"}, @record)."\n"; (or rather, the equivalent code in Visual Basic or PHP which is what they're probably using) regardless of their data containing quote characters or newlines, resulting in garbage like: "First Name","Last Name","email" "Joseph "Joe","Smith",""Smith, Joe" " This can actually be processed by (recent versions of) the L module with the following configuration: { binary => 1, allow_loose_quotes => 1, allow_whitespace => 1, escape_char => undef, } And so this module is simply a subclass of L which provides those defaults to the parser. How does the parsing work though? Well, some guesswork and patterns. It's not super reliable, and you should always complain loudly to whoever generated that data, unless they're a much larger company than you and would never listen, or went out of business a while back, in which case you can justify using this module in production. =head1 AUTHOR Michael Conrad =head1 COPYRIGHT AND LICENSE This software is copyright (c) 2026 by Michael Conrad. This is free software; you can redistribute it and/or modify it under the same terms as the Perl 5 programming language system itself. =cut Spreadsheet.pm100644001750001750 1265115234670244 26335 0ustar00silverdirksilverdirk000000000000Data-TableReader-0.022/lib/Data/TableReader/Decoderpackage Data::TableReader::Decoder::Spreadsheet; use Moo 2; use Carp 'croak'; use IO::Handle; extends 'Data::TableReader::Decoder'; # ABSTRACT: Base class for implementing spreadsheet decoders our $VERSION = '0.022'; # VERSION has workbook => ( is => 'lazy' ); has sheet => ( is => 'ro' ); has xls_formatter => ( is => 'rw' ); # Arrayref of all sheets we can search has _sheets => ( is => 'lazy' ); sub _build__sheets { my $self= shift; # If we have ->sheet and it is a worksheet object, then no need to do anything else if ($self->sheet && ref($self->sheet) && ref($self->sheet)->can('get_cell')) { return [ $self->sheet ]; } # Else we need to scan sheets from the excel file. Make sure we have the file my @sheets= $self->workbook->worksheets; @sheets or croak "No worksheets in file?"; if (defined $self->sheet) { if (ref($self->sheet) eq 'Regexp') { @sheets= grep { $_->get_name =~ $self->sheet } @sheets; } elsif (ref($self->sheet) eq 'CODE') { @sheets= grep { $self->sheet->($_) } @sheets; } elsif (!ref $self->sheet) { @sheets= grep { $_->get_name eq $self->sheet } @sheets; } else { croak "Unknown type of sheet specification: ".$self->sheet; } } return \@sheets; } sub _oo_rowmax_fix { # openoffice saves bogus rowmax, try and fix my ($s, $rowmax)= @_; my $final_row_max= ($s and ref $s->{Cells} eq "ARRAY" and $#{$s->{Cells}} < $rowmax) # ? $#{$s->{Cells}} : $rowmax; return $final_row_max; } sub iterator { my $self= shift; my $sheets= $self->_sheets; my $sheet= $sheets->[0]; my ($colmin, $colmax)= $sheet? $sheet->col_range() : (0,-1); my ($rowmin, $rowmax)= $sheet? $sheet->row_range() : (0,-1); $rowmax= _oo_rowmax_fix $sheet, $rowmax; my $row= $rowmin-1; Data::TableReader::Decoder::Spreadsheet::_Iter->new( sub { my $slice= shift; return undef unless $row < $rowmax; ++$row; my $x; if ($slice) { return [ map { $x= ($x= $sheet->get_cell($row, $_)) && $x->value; defined $x? $x : '' } @$slice ]; } else { return [ map { $x= ($x= $sheet->get_cell($row, $_)) && $x->value; defined $x? $x : '' } 0 .. $colmax ]; } }, { sheets => $sheets, sheet_idx => 0, sheet_ref => \$sheet, row_ref => \$row, colmax_ref => \$colmax, rowmax_ref => \$rowmax, origin => [ $sheet, $row ], } ); } # If you need to subclass this iterator, don't. Just implement your own. # i.e. I'm not declaring this implementation stable, yet. use Data::TableReader::Iterator; BEGIN { @Data::TableReader::Decoder::Spreadsheet::_Iter::ISA= ('Data::TableReader::Iterator'); } sub Data::TableReader::Decoder::Spreadsheet::_Iter::position { my $f= shift->_fields; ($f->{sheet_idx} > 0? 'sheet '.($f->{sheet_idx}+1).' ' : '') .'row '.(1+${ $f->{row_ref} }); } sub Data::TableReader::Decoder::Spreadsheet::_Iter::row { 1 + ${ shift->_fields->{row_ref} }; } sub Data::TableReader::Decoder::Spreadsheet::_Iter::dataset_idx { shift->_fields->{sheet_idx}; } sub Data::TableReader::Decoder::Spreadsheet::_Iter::progress { my $f= shift->_fields; return ${ $f->{row_ref} } / (${ $f->{rowmax_ref} } || 1); } sub Data::TableReader::Decoder::Spreadsheet::_Iter::tell { my $f= shift->_fields; return [ $f->{sheet_idx}, ${$f->{row_ref}} ]; } sub Data::TableReader::Decoder::Spreadsheet::_Iter::seek { my ($self, $to)= @_; my $f= $self->_fields; $to ||= $f->{origin}; my ($sheet_idx, $row)= @$to; my $sheet= $f->{sheets}[$sheet_idx]; my ($colmin, $colmax)= $sheet? $sheet->col_range() : (0,-1); my ($rowmin, $rowmax)= $sheet? $sheet->row_range() : (0,-1); $rowmax= _oo_rowmax_fix $sheet, $rowmax; $row= $rowmin-1 unless defined $row; $f->{sheet_idx}= $sheet_idx; ${$f->{sheet_ref}}= $sheet; ${$f->{row_ref}}= $row; ${$f->{colmax_ref}}= $colmax; ${$f->{rowmax_ref}}= $rowmax; 1; } sub Data::TableReader::Decoder::Spreadsheet::_Iter::next_dataset { my $self= shift; my $f= $self->_fields; return defined $f->{sheets}[ $f->{sheet_idx}+1 ] && $self->seek([ $f->{sheet_idx}+1 ]); } 1; __END__ =pod =encoding UTF-8 =head1 NAME Data::TableReader::Decoder::Spreadsheet - Base class for implementing spreadsheet decoders =head1 VERSION version 0.022 =head1 DESCRIPTION This is a base class for any file format that exposes a spreadsheet API compatible with L. =head1 ATTRIBUTES See attributes from parent class: L. =head2 workbook This is an instance of L, L, or L (which all happen to have the same API). Subclasses can lazy-build this from the C. =head2 sheet This is either a sheet name, a regex for matching a sheet name, or a parser's worksheet object. It is also optional; if not set, all sheets will be iterated. =head2 xls_formatter An optional object that is passed to Excel parsers L and L. It governs how raw data in cells is formatted into values depending on the type of the cell. The parsers create one of their own if none is provided, usually L. Note that it does not work for Spreadsheet::XLSX, which hardcodes the formatter as Spreadsheet::XLSX::Fmt2007. =head1 AUTHOR Michael Conrad =head1 COPYRIGHT AND LICENSE This software is copyright (c) 2026 by Michael Conrad. This is free software; you can redistribute it and/or modify it under the same terms as the Perl 5 programming language system itself. =cut