Any new developments in webperl ?

https://webperl.zero-g.net/

submitted by /u/ReplacementSlight413
[link] [comments]

Mo timezone utilities.

Changes for 0.01 - 2024-04-03T18:33:24+02:00

• First version.

Mo language utilities.

Changes for 0.06 - 2024-04-03T17:32:05+02:00

• Fix EXAMPLES in doc.
• Fix SYNOPSIS section in doc.

Easily load and access DBIx::Class functionality in Mojolicious apps

Changes for 0.01 - 2024-04-03T09:11:05-05:00

• initial release

Greple module for text search and substitution

Changes for 2.33_9901 - 2024-04-03T13:14:26Z

• introduce --macos option
• implement --exdictdir option by builtin
• update share/macos.dict

Greetings monks, question about reorganizing a Perl module, and if the following is a good approach:

The module is 7300 lines in one file and has 106 subs. I'll call it Cat.pm, its mostly called as an object like Cat->new(); but could be called like Cat->black() or Cat::Black::meow

To simplify maintaining this file I am thinking I can make a new sub directory in the same folder as the file call it Cat/ and move the 105 of the 106 subs to about 12 or 15 new .pm's in the new folder.

I plan later to rewrite one or more of those as XS modules. Cat/Tabby_XS.pm etc.

Then in Cat.pm I would just have use Cat::Black; use Cat::White; use Cat:;tabby; ...etc in Cat.pm

The only sub I'd keep in Cat.pm is sub new which looks like this:

sub new { #Object Interface #http://www.perl.com/pub/1999/09/refererents.html my $type = shift; my $self = {}; $self->{dbh} = shift; bless $self, $type; $self; } 

submitted by /u/bug_splat
[link] [comments]

Decide whether to allow a client to run this script

Changes for 0.05 - 2024-04-02T16:26:14Z

• Calling new on an object now returns a clone rather than setting the defaults in the new object

Easily format content into PDF/PS/DVI with LaTeX templates.

Changes for 0.05 - 2024-04-02

• Enhanced the ability to pass parameters to the Text::Xslate template engine and created a test file to test setting the search paths for included templates. Method 'templater_parameters()' has been removed. Now, parameters to Text::Xslate template engine can only be passed during construction of LaTeX::Easy::Templates. Test files under "xt/" are now included in the distribution, they were omitted in previous releases. Test files above 300 have been restructured and renamed. Enhanced documentation.

A health check for your code

Changes for v1.9.0 - 2024-04-02T19:56:08Z

• No changes found

Audit CPAN distributions for known vulnerabilities

Changes for 20240401.001 - 2024-04-01T11:50:11Z

• data update for 2024-04-01
• fix data issue for Mojolicious report (briandfoy/cpan-security-advisory#149) (Timothy Legge)

cat-v command implementation

Changes for 0.9901 - 2024-04-01T10:20:20Z

• organized docs directory

PDF DateTime Parser and Formatter.

Changes for 0.01 - 2024-04-01T11:22:08+02:00

• First version.

Dist::Zilla Mixed Up

Changes for 0.1.24 - 2024-03-30T07:51:11Z

• Update copyright year
• Add a zild/no-check setting

Shamelessly copied Tk::Tree widget

Changes for 0.02

• Configured Left and Right key to open and close branches. Corrected documentation.

Tied objects

Changes for 0.20 - 2024-03-30

• Adds clear_meta and set_meta on Rope so that you can manipulate an Objects meta definition
• Extends CONFIGURE PROPERTIES with predicates and clearers

create diffs between HTTP requests

Changes for 0.07 - 2024-03-30

• Switch tests from YAML to YAML::PP This is mainly to avoid YAML::Syck being loaded, which can't handle some of our YAML (?!)

This isn't directly perl-related, but it's a good reminder that as the bus-factor of our projects dwindle down to 0, the danger of a dependency attack goes up.

Obligatory XKCD

The story is still unfolding, and I've just been reading it from the HN post

In this case, it appears that the maintainer of xz-utils, who has been maintaining it since 2009 and mentioned online that they don't really have the capacity for it anymore finally had a motivated helper show up to assist with the work 2.5 years ago. That motivated helper now appears to either be a long-con state actor, or a compromised account.

liblzma is used by libsystemd. Redhat and Debian patch ssh to use libsystemd. The startup code of libxz detects when it is loaded into sshd during initialization and replaces a core auth function of sshd with its own copy. The malicious code comes from compressed compiled code within one of the libxz unit test files that gets sneakily injected into the build during the ./configure script. The person who discovered it only found it due to valgrind errors and a slower startup time for ssh, which are mistakes a more sophisticated attacker might not have made.

Oh, and of course the question on everyone's mind, you're probably not affected yet because the latest liblzma is only used in pre-release distros right now. But check if you have xz 5.6 or later. However, the author has been contributing to xz for 2.5 years so who knows if this is the first attack or not...

submitted by /u/nrdvana
[link] [comments]

Dependency

^xkcd

Libdeflate compression library

Changes for 0.08 - 2024-03-30

• Check compiler when installing and exit if version is too low
• Include a missing file

Sah schemas related to ArrayData

Changes for 0.005 - 2024-02-16

• Rename module/dist Sah-Schema{s,Bundle}-ArrayData following rename of Sah-Schema{s,Bundle} (for visual clarity and consistency with naming of other bundles).

Interface to the Qhull convex hull, Delauny triangulation, Voronoi diagram software suite

Changes for 0.06 - 2024-03-29T17:56:08-04:00

• BUG FIX

automate the Chrome browser

Changes for 0.73 - 2024-03-29

• Tests should not hang when run as root now
• Sandbox is automatically disabled when running as root

Multi column file system explorer

Changes for 0.01 - 2024-03-01T10:42:59Z

• original version; created by h2xs 1.23 with options -X Tk::FileBrowser

Hi all,

I have most difficulties to make my LWP::UserAgent to use TLS 1.2/1.3

I tried :

my $ua = new LWP::UserAgent( 'ssl_opts' => { SSL_version => 'TLSv12:!SSLv2:!SSLv3:!TLSv1:!TLSv11', } );

but no success .....

also tried :

$ENV{https_version}=3;

perl v5.32 is not that old, I am very surprised I can't establish connecting to TLS 1.2/1.3 server

Is it a known problem with openSSL version used to compile v5.32 ? if so, can I upgrade the SSL libs only ? or is there an option to pass on to force TLS 1.2/1.3 ?

Windows 10 - strawberry v5.32.1 MSWin32-x64-multi-thread

Thank you very much !

​

submitted by /u/lowpowerdesign
[link] [comments]

Read environment variables from .env file

Changes for 0.012 - 2024-03-29T18:05:10+02:00

• Fix lib and test code to use Cwd::abs_path with File::Spec->catdir|catfile.

Class for conversion between percent number to star visualization

Changes for 0.03 - 2024-03-29T16:01:21+01:00

• Add missing dot in doc.
• Improve doc for constructor.
• Move bugtracker to Github.
• Move valid tests to top.
• Rewrite check of error to Mo::utils.

I have a bunch of YAML config files (using YAML::XS) which are multidimensional, and the values can be HASH, ARRAY, or SCALAR. Right now, I have a kind of a template YAML that defines the layout that someone can use as a reference to write a config file. The keys and layout are the same, except instead of having values it has two keys: 1) required (boolean) and 2) type (ARRAY, HASH, STR, etc). What I would like is for a sub to just verify the tree and spit out an error on which key is the problem, but I'm getting kind of lost on trying to loop both trees together.

Here is a small example from a part of a YAML config.

split: level: 3 filter: directories: delete: - \/main.assets$ keep: - S2589004224001688 files: keep: - issue.xml - main.xml - main.pdf 

split: required: True type: HASH group: required: False type: HASH by: required: True type: STR count: required: True type: STR level: required: True type: INT filter: required: False type: HASH directories: required: False type: HASH delete: required: False type: ARRAY keep: required: False type: ARRAY files: required: False type: HASH delete: required: False type: ARRAY keep: required: False type: ARRAY 

submitted by /u/sirhalos
[link] [comments]

A Latemp Utility Module.

Changes for 0.12.0 - 2024-03-29

• Deprecate.
• Add deprecation note.

Audit CPAN distributions for known vulnerabilities

Changes for 20240329.002 - 2024-03-29T12:08:01Z

• Data update for 2024-03-29

create diffs between HTTP requests

Changes for 0.06 - 2024-03-29

• Use "stable" instead of "experimental"

Some fun with chatgpt (note that you can get the same information with a rudimentary search across various research databases followed by statistical analysis of the tags)

When reading the chat bot response note that

legacy systems include many/most of the research tools in many fields many of the legacy systems are heavily dependent on bash for gluing their individual components many of these legacy systems include a noninsignificant amount for web programming Python / R etc just glue over code written in C and Fortran, ie they just provide an API

Prompt: can you suggest a few application areas for perl as glue in scientific component based software engineering?

Perl can be effectively used as "glue" in scientific component-based software engineering due to its strong text manipulation capabilities, mature ecosystem, and ability to interface with various systems and languages. Here are a few application areas where Perl can excel as a glue language:

1. Bioinformatics Pipelines

Perl has been traditionally strong in bioinformatics, where it is used to connect different software components for tasks like DNA sequence analysis, protein structure prediction, and genetic data processing. It can orchestrate workflows that involve calling various tools, parsing their output, and preparing it for the next step in the analysis pipeline.

2. Data Transformation and Integration

In scientific computing, there is often a need to transform data between different formats or integrate data from various sources. Perl can serve as a glue language to script these transformations and integrations, handling formats like CSV, JSON, XML, and proprietary binary formats commonly used in scientific instruments.

3. System Administration for Research Computing

Perl can automate and manage tasks in research computing environments, such as scheduling jobs on a compute cluster, monitoring resource usage, and managing file systems. It can glue together various system components, ensuring they work seamlessly to support scientific computation.

4. Legacy Scientific Software Integration

Many scientific research fields have legacy software components written in Perl or that provide Perl interfaces. Perl can be used to integrate these components with newer systems, preserving the value of previous investments in software development.

5. Automated Reporting and Visualization

Perl can be used to generate automated reports and visualizations from scientific data. By gluing together data extraction, analysis, and reporting tools, Perl scripts can produce regular, up-to-date reports or visualizations of ongoing scientific research or experiments.

Limitations to Consider

While Perl is useful in these areas, it's essential to consider its limitations. The ecosystem around Perl, particularly in scientific computing, may not be as vibrant as it once was, with many new developments occurring in other languages like Python. Therefore, while Perl remains a powerful tool for certain tasks, its role in new scientific software projects might be more limited compared to its peak usage times.

In conclusion, Perl's role as glue in scientific component-based software engineering is well established, particularly in areas where text processing and legacy system integration are paramount. However, the choice to use Perl should be balanced with considerations about the current and future needs of the project, as well as the availability of skills and community support.

submitted by /u/ReplacementSlight413
[link] [comments]

Class library for rapid development

Changes for 1.215 - 2024-03-28

• Quiq::Confluence::Client
• Quiq::Database::Connection
• Quiq::Hash
• Quiq::Path
• Quiq::PhotoStorage
• Quiq::Url

Raspberry Pi GPIO Perl Modules

Changes for 0.92

• Build failures in 0.91 distribution

Simplified abstracted chained DBI subclass

Changes for 1.15 - 2024-03-28T12:26:27-07:00

• Carp SQL parsing errors
• Ignore reserved words SQL parse errors when not specifying an explicit dialect
• Add abstract() method
• Move parsed query cache to the connection object (instead of global)

Generate complete SQL from Perl data structures

Changes for 1.09 - 2024-03-28T12:22:27-07:00

• Slightly better handling of columns in get()

Tied objects

Changes for 0.11 - 2024-03-28

• Ensure any passed index takes precedents over the auto generated index

create diffs between HTTP requests

Changes for 0.05 - 2024-03-28

• We use the postderef feature also in tests
• Use features of URI in a backwards compatible way