Skip to main content



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


Tied objects

Changes for 0.17 - 2024-03-29

  • Adds get_meta to return the objects definition
  • Adds Rope::Monkey which takes the monkey patch approach to achieve autoloading, each for their own.


Call a subroutine on destruction of a variable.

Changes for 0.09 - 2024-03-29T19:04:01+01:00

  • Further fix on older perls


Tied objects

Changes for 0.16 - 2024-03-29

  • Fix before, around and after to only work on readonly functions (properties that have a value as a code ref), to prevent unexpected behaviour.


Tied objects

Changes for 0.15 - 2024-03-29

  • Adds get_initialised function which can be called on Rope to retrieve an already initialised object by index.
  • Adds before, around and after keywords which can be chained and work for all properties/functions, not traditional subs currently because they are effectively 'hidden' to Rope.



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]



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 

And here is a small example from the YAML config template that someone uses as a reference.
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]



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]










Perl.social Code of Conduct


I've posted this on reddit and wanted a discussion here too for those not on reddit for whatever reason:

reddit.com/r/perl/comments/1bl…

The gist though is that I've gotten another request for a proper CoC/ToS that would be acceptable to the community since i've been negligent in doing so. I've decided that a slightly modified version from the mastodon CoC might be a good starting point and I'll post that content in a reply to this so that it doesn't flood everyone's feeds with a giant wall of text immediately.

in reply to Ryan Voots

COC/TOS

Borrowing many things from the Mastodon CoC as a astarting point (github.com/mastodon/mastodon/b…).

I am removing a few things from it, not because I don't think they're good ideas or anything but also because I want to limit the scope
of the initial discussion and the amount of work for myself as I'm still currently the only moderator but once the community there gets larger
or it changes that I'm not the only one maintaining things, we will hold another discussion about everything.

I've changed a few things also, specifically to add stronger language that any moderators
MUST document why an action was taken. This doesn't necessarily mean that I believe
that those reasons must be immediately given to an affected user, but that they must
be available when requested. Specifically I'm thinking of not informing in the context
of bots, spam, illegal or otherwise legally actionable content (i.e. something that's going to get me a subpeona or court case).

Other proposed ideas:
1) Some kind of regular discussion, maybe annually? on ToS/CoC type things
1a) The idea being that we require a regular discussion of anything that's
happened over the last time period to avoid it being possible for something
happening being "swept under the rug" or "falling through the cracks" because
it didn't get the proper time given to it previously. How this should be done
I have no good recommendations for, likely creating a group on perl.social to
host the conversation each time?
2) ?

Contributor Covenant Code of Conduct

Our Pledge


We as members, contributors, and leaders pledge to make participation in our
community a harassment-free experience for everyone, regardless of age, body
size, visible or invisible disability, ethnicity, sex characteristics, gender
identity and expression, level of experience, education, socio-economic status,
nationality, personal appearance, race, caste, color, religion, or sexual
identity and orientation.

We pledge to act and interact in ways that contribute to an open, welcoming,
diverse, inclusive, and healthy community.

Privacy


I reserve the right to collect email or other identifiable contact information,
and it will never be shared to an outside party without consent except in the case
of it being required by some legal process. If at any time perl.social becomes
a larger organization and there is a desire to change this, I will require the
removal of all such information until explicit consent is given again with such
a new policy. I don't know if there's a way I can make this legally enforcable
but I see it as something I do not own and therefore cannot ethically give it to
another party in that kind of scenario.

Both perl.social and I are located in the USA, and therefore I believe are not
directly subject to the GDPR, but as there are similar laws in other jurisdictions
even within the USA, and I basically agree with the ideas involved, I will do
whatever is reasonable feasible to follow them.

Our Standards


Examples of behavior that contributes to a positive environment for our
community include:

  • Being respectful of differing opinions, viewpoints, and experiences
  • Giving and gracefully accepting constructive feedback
  • Accepting responsibility and apologizing to those affected by our mistakes,
    and learning from the experience
  • Focusing on what is best not just for us as individuals, but for the overall
    community

Examples of unacceptable behavior include:

  • The use of public and/or unwanted sexualized language or imagery,
    and sexual attention or advances of any kind. Consenting adults in private
    should be acceptable.
  • Trolling, insulting or derogatory comments, and personal or political attacks
  • Public or private harassment
  • Publishing others' private information, such as a physical or email address,
    without their explicit permission
  • Other conduct which could reasonably be considered inappropriate in a
    professional setting


Enforcement Responsibilities


Community leaders are responsible for clarifying and enforcing our standards of
acceptable behavior and will take appropriate and fair corrective action in
response to any behavior that they deem inappropriate, threatening, offensive,
or harmful.

Community leaders have the right and responsibility to remove, edit, or reject
comments, commits, code, wiki edits, issues, and other contributions that are
not aligned to this Code of Conduct, and MUST communicate reasons for moderation
decisions.

Scope


This Code of Conduct applies within all community spaces, and also applies when
an individual is officially representing the community in public spaces.
Examples of representing our community include using an official e-mail address,
posting via an official social media account, or acting as an appointed
representative at an online or offline event.

Enforcement


Instances of abusive, harassing, or otherwise unacceptable behavior may be
reported to the community leaders responsible for enforcement at
[hello@joinmastodon.org](mailto:hello@joinmastodon.org).
All complaints will be reviewed and investigated promptly and fairly.

All community leaders are obligated to respect the privacy and security of the
reporter of any incident.

Enforcement Guidelines


Community leaders will follow these Community Impact Guidelines in determining
the consequences for any action they deem in violation of this Code of Conduct:

1. Correction


Community Impact: Use of inappropriate language or other behavior deemed
unprofessional or unwelcome in the community.

Consequence: A private, written warning from community leaders, providing
clarity around the nature of the violation and an explanation of why the
behavior was inappropriate. A public apology may be requested.

2. Warning


Community Impact: A violation through a single incident or series of
actions.

Consequence: A warning with consequences for continued behavior. No
interaction with the people involved, including unsolicited interaction with
those enforcing the Code of Conduct, for a specified period of time. This
includes avoiding interactions in community spaces as well as external channels
like social media. Violating these terms may lead to a temporary or permanent
ban.

3. Temporary Ban


Community Impact: A serious violation of community standards, including
sustained inappropriate behavior.

Consequence: A temporary ban from any sort of interaction or public
communication with the community for a specified period of time. No public or
private interaction with the people involved, including unsolicited interaction
with those enforcing the Code of Conduct, is allowed during this period.
Violating these terms may lead to a permanent ban.

4. Permanent Ban


Community Impact: Demonstrating a pattern of violation of community
standards, including sustained inappropriate behavior, harassment of an
individual, or aggression toward or disparagement of classes of individuals.

Consequence: A permanent ban from any sort of public interaction within the
community.

Attribution


This Code of Conduct is adapted from the Contributor Covenant,
version 2.1, available at
contributor-covenant.org/versi…contributor-covenant.org/versi….

And from the Mastodon code of conduct available at github.com/mastodon/mastodon/b…

Community Impact Guidelines were inspired by
Mozilla's code of conduct enforcement ladder.

For answers to common questions about this code of conduct, see the FAQ at
contributor-covenant.org/faqcontributor-covenant.org/faq. Translations are available at
contributor-covenant.org/trans…contributor-covenant.org/trans….



So hear me out...


This idea is stupid. But on Star Trek (VOY, TNG, and DS9 at least), they measured their data as "quads". ( memory-alpha.fandom.com/wiki/Q… ). This was never defined because it's just Sci-Fi and doesn't need a real definition. But... what if they're quad-floats aka 128bit floating point values. This would mean then that all the storage could be done as LLM or other neural network style models, and vector embeddings and such. Given what we've got today with transformer style models for doing translation, chat, etc. If you had ultrapowerful computers that could do these calculations with such gigantic precision then you'd be able to store very accurate data and transform it back and forth from vector embeddings and other fancy structures. It'd enable very powerful searches, and the kind of analysis we're trying to use LLMs for and see them use in the shows when talking to the computers. This would also explain a lot about the universal translators from ENG onward, and could even help make sense of Darmok and Jalad at Tenagra. And then Voyager even has bio-neural circuitry for doing things faster, some kind of organic analog computing doing stuff "at the edge". Using weights and embeddings to do things with them and have them react by programming them with a machine learning model at each node could easily explain how that could work too.

This idea honestly feels too stupid to be real but it could explain so much.



Perl.social server upgrades


So if anyone noticed things being a bit unstable recently it looks like the server was hitting the OOM killer sometimes and caused some odd behavior. In response to this I've added more ram to the VPS running perl.social so this shouldn't happen anymore and it'll also probably mean things run faster now too since more things will sit in the caches.


perlbot and related status


to stave off any rumors, i just had a hardware failure in my main server of some kind (likely motherboard failure) and I can't fucking fix it right now. I'm about to go out of town and won't be back for a little more than a week. there is literally nothing i can do right now, perlbot and all the related stuff will be down for that time while i get back from vacation and then spend gobs of money fixing the thing.