This is an archive of past discussions. Do not edit the contents of this page. If you wish to start a new discussion or revive an old one, please do so on the current talk page.

The title makes me wonder if this might have something we could use, but I can't figure out how to get it to work, or even what it does: User:Dr Brains/ListPages.js.

The doc is no longer around, and didn't leave any instructions behind.

What does it do, and how does it work?    — The Transhumanist   23:45, 4 July 2018 (UTC)

Looks like it was intended to get all articles in a category, including all subcategories, and then find each article's interwiki target on the French Wikipedia, and produce a table of articles and their French equivalent. But it is using outdated/deprecated techniques, which would be why you can't get it to work. - Evad37 [talk] 05:31, 6 July 2018 (UTC)

Thank you. I'll cross this one off my list.    — The Transhumanist   07:58, 8 July 2018 (UTC)

A tool to get all articles in a subcategory, including all subcategories, and list them in that structure, would be quite useful. · · · Peter (Southwood) ^(talk): 08:36, 14 July 2018 (UTC)

You can use wp:PETSCAN to do that (and a whole lot more) - Evad37 [talk] 11:29, 14 July 2018 (UTC)

Thank you for updating editors on this. I know it doesn't currently apply to manually maintained portals, but I just wanted to say that I'm going to try and convert the intros for the 30 or so portals I maintain. It's worked on two so far, with a bit of tweaking. Thank you to those who worked out how to do it! Bermicourt (talk) 20:06, 10 July 2018 (UTC)

Bermicourt, We will generally not make this sort of change to a manually maintained portal out of deference to the maintainer, who has taken on the task of doing the maintensnce and any upgrades themself. If you have any trouble doing the upgrades, leave a note somewhere and we will try to help sort it out. We encourage maintainers to use the automated tools whenever there are no good reasons not to do so, because it is less work in the long run, and there is less risk of content forking when using transcluded excerpts. Cheers, · · · Peter (Southwood) ^(talk): 07:02, 14 July 2018 (UTC)

Pbsouthwood. Thanks, very happy with that. I'm generally a fan of automated tools; I created one to cycle through articles/images of the month when transferred a portal from German Wikipedia but realised I wasn't going to get the support they have there to create new articles and images every month. So I set them up with an annual cycle of 12 articles/images. Clearly the frequency and cycle period are changeable. Cheers. Bermicourt (talk) 07:13, 14 July 2018 (UTC)

P.S. I think it's good, though, that you aren't forcing the changes on portals that are manually maintained as you will retain the goodwill of those maintainers. :) Bermicourt (talk) 07:14, 14 July 2018 (UTC)

That is the intention. If anyone wants to use the new toolkit we are willing to assist, if they don't, they are more than welcome to do it a different way as long as it works. We will convert portals with no known maintainer (most of them it seems), and if someone pops up and claims to be the maintainer then they can revert and carry on from there, as long as they actually do the maintenance they volunteer for. If they don't, someone may tag for deletion as unmaintained/out of date/whatever, and then we consider the portal open for conversion. The enthusiasm and support for automation here is amazing. We want people to join us when they think our way is better, and if they think they have a better way, to develop it so we can join them if it works. Cheers, · · · Peter (Southwood) ^(talk): 08:23, 14 July 2018 (UTC)

Someone from the project edited my test portal with the summary "Rename Picture slideshow section to "Selected pictures", because it doesn't show up as a slideshow on mobile devices" -- does anyone know what the failure mode on the slideshow is for mobile devices? (I don't own one, so can't check.) I was assuming that I'd have to convert the slideshow to the random subpages model before going live on this one, but I've been putting it off as I like the functionality. Espresso Addict (talk) 08:24, 12 July 2018 (UTC)

The gallery shows up as a standard gallery instead of a slideshow. You can check the mobile version on a desktop device by going to the en.m.wikipedia.org version of the page, e.g. https://en.m.wikipedia.org/wiki/Portal:Sacramento - Evad37 [talk] 09:11, 12 July 2018 (UTC)

See also Wikipedia talk:WikiProject Portals/Design § Slideshows and the mobile skin - Evad37 [talk] 09:13, 12 July 2018 (UTC)

Thanks; I didn't know I could look at the mobile version like that, handy! Espresso Addict (talk) 09:32, 12 July 2018 (UTC)

Somebody somewhere is working on a new mobile main page for Wikivoyage, and if I remember correctly it will have a carousel functionality much like the slideshows. I heard about this at Wikimania, I think, but can't remember the details, though I have a feeling it is a Mediawiki extension. When it is running we should take a look. · · · Peter (Southwood) ^(talk): 18:11, 31 July 2018 (UTC)

Bit of a problem on Portal:Reptiles, 7 boxes relying on automatic presentation of content are now saying "The time allocated for running scripts has expired." Sincerely, InsaneHacker (💬) 09:12, 15 July 2018 (UTC)

@InsaneHacker: I am currently unable to reproduce the issue. None of the templates on that page are currently misbehaving AFAICT. If the problem is still occurring for you, please open the HTML page source and look for a comment block similar to the one mentioned here, then post it here so we can find the culprit. — AfroThundr ^{(u · t · c)} 16:11, 15 July 2018 (UTC)

The problem is not occurring for me either anymore. Perhaps the backend was having some issues this morning. Sincerely, InsaneHacker (💬) 16:26, 15 July 2018 (UTC)

I have also seen the problem in the last 24 hours (can't remember exactly where or when) but it seems to work now. Certes (talk) 18:01, 15 July 2018 (UTC)

@InsaneHacker, AfroThundr3007730, and Certes: It seems to happen when a super large pic is being displayed. I was running into this phenomenon with the panoramic pics being added to the intro sections, and found that it went away when I found smaller-sized pics (under 2 megabytes) to display instead. Some of the pics in slideshows might be huge, but would only cause the problem when they are displayed, making the problem intermittent. That's where I would look next. If you purge the page, and the problem goes away, it was probably a large pic in the slideshow.    — The Transhumanist   03:51, 18 July 2018 (UTC)

"Time allocated" errors occurred when a caption's text was duplicated earlier in the infobox, e.g. in Melbourne. I fixed that bug here. Of course, other problems may produce the same error text. I'm away from home for a week so would rather not attempt module edits currently. Certes (talk) 19:50, 18 July 2018 (UTC)

Hi, in the automation of the introduction section to portals we are loosing images or maps, as these are usually in the infoboxes and so the template replacement does not extract the image or map for the portal. Is there a way of overriding this to enable an image or map to be placed in the introduction or should the automated process be extended to include detail from the infobox? Keith D (talk) 18:48, 15 July 2018 (UTC)

This is template being used Template:Transclude lead excerpt. The image parameter is files=. It however doesn't include images in infoboxes. --Emir of Wikipedia (talk) 19:11, 15 July 2018 (UTC)

The template attempts to include images from infoboxes. Is there a particular portal where it's not managing to do that? Certes (talk) 19:38, 15 July 2018 (UTC)

The documentation says "Note that images within infoboxes etc. are not available." Emir of Wikipedia (talk) 21:15, 15 July 2018 (UTC)

Thanks for spotting that. The documentation was outdated; I've fixed it. It is still possible for an article to display an image in an unusual way which the template fails to detect. Perhaps the infobox in the relevant article uses such a technique. Certes (talk) 21:37, 15 July 2018 (UTC)

I was looking at Portal:Lincolnshire which had a map before conversion and nothing after. Though the image used for the map is not in the infobox on the Lincolnshire article but a map is there that could be used. Maybe a |file= parameter is needed to code in an image which is not from the article. Keith D (talk) 00:31, 17 July 2018 (UTC)

It used to use Portal:Lincolnshire/intro/2 (or, randomly, the flag in /1), which in turn uses Portal:Lincolnshire/intro/layout. That's probably best done manually, by adding a File: to the main portal page, rather than by coaxing the excerpt to include an image that's not actually in the article. Certes (talk) 01:00, 17 July 2018 (UTC)

As an alternative, you can add thumbnail pics to the top of the box, and they will be floated next to the text as usual. You can also add a panorama, which will display before the text. For examples of panorama insertion, see Portal:Seattle, Portal:Munich, and Portal:Miami. For the panorama insertion task, see Wikipedia:WikiProject Portals#Add a panorama or skyline to a geographic portal.    — The Transhumanist   04:06, 18 July 2018 (UTC)

@Keith D and Emir of Wikipedia: Evad and Certes have been improving the image detection capability of the transclusion templates. For details, and to report an image that is getting missed, go to Wikipedia talk:WikiProject Portals/Design#Template:Transclude lead excerpt.    — The Transhumanist   05:00, 18 July 2018 (UTC)

It was just a case of me reading out dated documentation but thanks for reminding me about the other page. Emir of Wikipedia (talk) 18:29, 18 July 2018 (UTC)

How do you submit a new portal image so that it links to the actual portal rather than that ugly blue icon visible on newly created portals? Thanks. Senegambianamestudy (talk) 15:53, 19 July 2018 (UTC)

Senegambianamestudy, please link to an example. I have no idea what you mean. Cheers, · · · Peter (Southwood) ^(talk): 16:04, 19 July 2018 (UTC)

Portal:Alieu Ebrima Cham Joof. Thanks. Senegambianamestudy (talk) 16:07, 19 July 2018 (UTC)

@Peter (Southwood) Thanks. Senegambianamestudy (talk) 21:28, 19 July 2018 (UTC)

@Senegambianamestudy: See Template:Portal#Image.    — The Transhumanist   23:15, 19 July 2018 (UTC)

Thank you. Senegambianamestudy (talk) —Preceding undated comment added 23:19, 19 July 2018 (UTC)

There seems to be a problem with the 'in the news' section on a number of portals, in particular:

• Portal:Abu Dhabi
• Portal:Android
• Portal:Australian roads
• Portal:Bangladesh
• Portal:Bangladesh/Bangladesh news
• Portal:Bangladesh/Old
• Portal:Bengal
• Portal:Bengal/Bengal news
• Portal:Berkshire
• Portal:Buckinghamshire
• Portal:Gilgit-Baltistan
• Portal:Gilgit-Baltistan/In the news
• Portal:Hampshire
• Portal:India
• Portal:India/News
• Portal:Iraq
• Portal:New South Wales
• Portal:Poland/Events/archive
• Portal:SAARC
• Portal:SAARC/South Asia news
• Portal:Sacramento
• Portal:Salem, Oregon
• Portal:Scotland
• Portal:Surrey
• Portal:Sydney
• Portal:Telephones
• Portal:UK railways
• Portal:UK railways/Trains news
• Portal:Virginia Woolf

I fixed it by disabling the template in one, Portal:24, before noticing there are a many more. I don’t know if this can be fixed in the template, to not generate errors if there’s no data. Or if it should just be removed on the assumption that news articles on e.g. Virginia Woolf are not going to appear often enough for it to be worthwhile.--JohnBlackburne^words_deeds 14:59, 28 July 2018 (UTC)

@JohnClackburne: It appears to choke when days= is set to any number higher than 40. Something must have changed at the source.    — The Transhumanist   05:29, 29 July 2018 (UTC)

 Done I tested each of the above news sections for 40 days. Those that came up empty ("No recent news items"), I removed. Those that displayed news, I configured to 40 days. We'll be looking into news solutions soon.    — The Transhumanist   18:32, 30 July 2018 (UTC)

@The Transhumanist: This bug in the module has now been fixed, so values as high as one or maybe two years can be used again (with the actual limit dependent on how much Lua is used in the rest of the portal). - Evad37 [talk] 18:40, 30 July 2018 (UTC)

Evad37, How is the amount of Lua used in the rest of the portal significant, and how does one find out how much Lua is used? · · · Peter (Southwood) ^(talk): 05:46, 31 July 2018 (UTC)

There is a per-page limit 10 seconds for all Lua processing on a page. If you preview a page, then at the bottom (below the edit box) there is a collapsed section "Parser profiling data" which when clicked on expands to shows a bunch of technical measurements and limits, including Lua time usage. - Evad37 [talk] 06:12, 31 July 2018 (UTC)

In addition to that, the same information can be found in the generated HTML source near the bottom of the page. Just look for a comment block starting with NewPP limit report. I find this very useful for capturing those stats for a specific instance of a page (e.g. when random transclusion is used, so the page is constantly changing). — AfroThundr ^{(u · t · c)} 07:28, 31 July 2018 (UTC)

Thanks for the explanations, most helpful. 10 seconds seems quite a lot of processing time for a page, specially if that is just the Lua. Are there any tips for minimising it for us non-technical people who just use the templates? · · · Peter (Southwood) ^(talk): 09:56, 31 July 2018 (UTC)

It sounds a lot to me too. Has anyone done any profiling to see which activity is eating up the time? If that yields no useful information, we could restrict the number of days in getItems() with while daysAgo < maxDays and os.clock() < 8 (8 being a number of seconds which may need tweaking). Certes (talk) 11:29, 31 July 2018 (UTC)

Hi , I have some news here .

Firstly , I have added panoramas to Portal:Calgary , Portal:Moscow , Portal:New Orleans and Portal:Brisbane .

But something is wrong with Portal:Melbourne , please can somebody check on it ? Kpgjhpjm 12:42, 16 July 2018 (UTC)

It's getting the "The time allocated for running scripts has expired." message on ((Transclude lead excerpt|Melbourne)). Purging didn't help. Melbourne is a long article. I'll see whether we can handle large pages more efficiently. Certes (talk) 15:03, 16 July 2018 (UTC)

@Kpgjhpjm:  Fixed. The caption text for Melbourne's map also appears earlier in the infobox as alt text, which confused the parser into an infinite loop. Sorry for the inconvenience; thanks for the report and for adding the attractive images. Certes (talk) 16:04, 16 July 2018 (UTC)

@Certes: Added panorama to the Portal along with Seattle and Houston portals . Kpgjhpjm 16:33, 16 July 2018 (UTC)

In Portal:Kurdistan, one of the images in the slideshow has a broken caption (you need to scroll through them to see it). Seems it can’t handle a caption which invokes a module. The bug is present in the page even when it’s not displaying the image, which suggests it’s loading all those images but not displaying them which could be quite expensive. It’s not making it any faster it seems as there’s a distinct delay when you cycle though them.--JohnBlackburne^words_deeds 23:40, 1 August 2018 (UTC)

Loading all of the listed (or linked) article segments is a limitation of the random excerpt and random slideshow template series. Loading a particular file or excerpt on demand would most likely require client-side javascript, which is beyond the scope of these templates. The problematic image in question is from Kurdistan § Syrian Civil War and the caption makes use of several templates and a module invocation. The wikitext looks like this:

[[File:Syrian, Iraqi, and Lebanese insurgencies.png|thumb|240px|Military situation on ((#invoke:Iraq_Syria_map_date|date)):<br />((legend|#e2d974|Controlled by [[Kurdish Supreme Committee|Syrian Kurds]]))((legend|#d7e074|Controlled by [[Peshmerga|Iraqi Kurds]]))((legend|#b4b2ae|Controlled by the [[Islamic State of Iraq and the Levant|Islamic State in Iraq and Syria]] (ISIL, ISIS, IS)))]]

I'm not sure how this should be fixed. If the template just strips the module, part of the caption will be missing. @Evad37: thoughts? — AfroThundr ^{(u · t · c)} 05:38, 2 August 2018 (UTC)

I just fixed all uses of it in portal space by adding captions to each one (though I cheated on the Scotland portal, just adding hard spaces as captions, as there were so many.)

The weird thing is, they didn't need captions until today. Those pictures worked fine without captions yesterday.

Even though there aren't any errors being thrown currenty, the bug is still there. Though I probably wouldn't have taken the time to add all those informative captions if the bug wasn't there. :)    — The Transhumanist   23:07, 1 August 2018 (UTC)

Yes, I spotted that too. I've spent most of the day assembling a range of panorama images to add to Portal: Scotland. Testing them without captions, all previewed fine. So I added them all, saved and lo and behold, on checking later suddenly there were no panorama images, just a Lua error message. After much head scratching I came to the same conclusion as you, The Transhumanist, so I have now reluctantly added captions. (I didn't spot that you'd added the hard spaces - that might be a preferred option for me, because I find the captions unneccessary). It would be good if the template / module author could fix it so that they are optional again. Cactus.man ✍ 00:20, 2 August 2018 (UTC)

@Transhumanist and Cactus.man: Fixed — FR ⁺ 09:21, 2 August 2018 (UTC)

I am getting this error on Portal:Underwater diving. It is a big portal with lots of automated random excerpts in the various box sections. It was OK until I converted to ((Transclude excerpts as random slideshow)), and now there are quite a lot of templates that are not processed. It may be that I am just trying to go beyond what is reasonable in the current system, but maybe there is a way to tweak it. · · · Peter (Southwood) ^(talk): 13:03, 31 July 2018 (UTC)

NewPP limit report
Parsed by mw1267
Cached time: 20180731124327
Cache expiry: 3600
Dynamic content: true
CPU time usage: 7.432 seconds
Real time usage: 8.992 seconds
Preprocessor visited node count: 57510/1000000
Preprocessor generated node count: 0/1500000
Post‐expand include size: 2097152/2097152 bytes
Template argument size: 730052/2097152 bytes
Highest expansion depth: 20/40
Expensive parser function count: 5/500
Unstrip recursion depth: 0/20
Unstrip post‐expand size: 847828/5000000 bytes
Number of Wikibase entities loaded: 0/400
Lua time usage: 5.436/10.000 seconds
Lua memory usage: 24.74 MB/50 MB
-->
<!--
Transclusion expansion time report (%,ms,calls,template)
100.00% 7770.505      1 -total
 70.96% 5513.587     17 Template:Transclude_excerpts_as_random_slideshow
 11.65%  905.506     18 Template:Navbox
  8.15%  632.955    188 Template:Ship
  6.23%  484.163     25 Template:Columns-list
  6.01%  466.894     18 Template:Collapsible_list
  5.84%  453.648      1 Template:Random_slideshow
  5.25%  407.665      1 Template:Recreational_dive_sites
  3.63%  281.695     78 Template:SS
  3.21%  249.269     77 Template:Imbox
-->

The Post-expand include size, whatever that is, seems to have hit the limit. Everything else in the top group 'looks' OK, but I am guessing · · · Peter (Southwood) ^(talk): 13:26, 31 July 2018 (UTC)

(edit conflict) Yep, I was about to comment on that. I noticed the behavior started to happen after you converted all the sections to use ((transclude excerpts as random slideshow)). Here are the reports on either side of that edit:

<!-- 
NewPP limit report
Parsed by mw1269
Cached time: 20180731134219
Cache expiry: 21600
Dynamic content: true
CPU time usage: 4.168 seconds
Real time usage: 4.959 seconds
Preprocessor visited node count: 44913/1000000
Preprocessor generated node count: 0/1500000
Post‐expand include size: 1626840/2097152 bytes
Template argument size: 613695/2097152 bytes
Highest expansion depth: 20/40
Expensive parser function count: 2/500
Unstrip recursion depth: 0/20
Unstrip post‐expand size: 329317/5000000 bytes
Number of Wikibase entities loaded: 0/400
Lua time usage: 2.485/10.000 seconds
Lua memory usage: 10.12 MB/50 MB
-->
<!--
Transclusion expansion time report (%,ms,calls,template)
100.00% 3926.903      1 -total
 23.55%  924.782      2 Template:Transclude_list_item_excerpts_as_random_slideshow
 14.80%  581.262     18 Template:Navbox
 12.83%  503.821      1 Template:Random_slideshow
 12.78%  501.922    188 Template:Ship
 12.68%  497.807     25 Template:Columns-list
 12.62%  495.462     18 Template:Collapsible_list
 10.73%  421.306      1 Template:Transclude_excerpts_as_random_slideshow
  8.07%  316.848      1 Template:Transclude_selected_current_events
  6.37%  250.167      1 Template:Recreational_dive_sites
-->

<!-- 
NewPP limit report
Parsed by mw1270
Cached time: 20180731134334
Cache expiry: 3600
Dynamic content: true
CPU time usage: 8.872 seconds
Real time usage: 10.533 seconds
Preprocessor visited node count: 62453/1000000
Preprocessor generated node count: 0/1500000
Post‐expand include size: 2097152/2097152 bytes
Template argument size: 749109/2097152 bytes
Highest expansion depth: 24/40
Expensive parser function count: 6/500
Unstrip recursion depth: 0/20
Unstrip post‐expand size: 948199/5000000 bytes
Number of Wikibase entities loaded: 0/400
Lua time usage: 6.596/10.000 seconds
Lua memory usage: 22.04 MB/50 MB
-->
<!--
Transclusion expansion time report (%,ms,calls,template)
100.00% 9156.232      1 -total
 60.90% 5576.263     17 Template:Transclude_excerpts_as_random_slideshow
 11.53% 1056.080     18 Template:Navbox
 10.75%  983.928      2 Template:Transclude_list_item_excerpts_as_random_slideshow
  7.76%  710.863    188 Template:Ship
  5.30%  485.315      1 Template:Random_slideshow
  5.30%  484.931      1 Template:Recreational_dive_sites
  5.12%  469.243     25 Template:Columns-list
  5.06%  462.950     18 Template:Collapsible_list
  3.46%  317.051     78 Template:SS
-->

You can see that even before that conversion you were at 77% of the limit. Add in several more instances of the not-exactly-lightweight slideshow templates, and there you are. I don't have exact numbers for this, but I'll wager that page weighs in at over 3MB right now. Perhaps we can find ways to make these templates a little lighter, so we don't have to restrict their use too much. — AfroThundr ^{(u · t · c)} 13:48, 31 July 2018 (UTC)

At least we're not hitting the Lua timeout, so the modules themselves aren't too heavy. @Evad37 and Certes: Do you guys know of a good way to pin down what exactly about the transclusion templates is causing this? Is it just too many transcluded templates in the excerpts? Is there anything we can do to reduce the impact, or are we just going to have to limit the amount of times these templates are used? — AfroThundr ^{(u · t · c)} 13:56, 31 July 2018 (UTC)

(Thinking out loud) It would be awesome if there was some sort of introspection capability, so we could find out where the limit is getting hit from. It could be another problem article with some odd template usage again, or maybe it's just the sheer number of instances being used concurrently. Would it be possible to build a test template that instead of displaying the excerpt, showed some stats about how heavy that particular transclusion is, maybe even do the same with a whole list? Something like that would make finding the issue trivial, I think. — AfroThundr ^{(u · t · c)} 14:05, 31 July 2018 (UTC)

(ec) Does the page size include the actual .jpgs? If so then that's clearly the cause of hitting the page size limit: the first image alone is 492 kB. Can we use smaller versions? I think the modules themselves are "heavy" (including the code I've written). Even if the load on the server is just about within the limit (which it may not be once we fix the size limit and generate the full page), 10.533 seconds is longer than many people are prepared to wait for a page to load. Certes (talk) 14:11, 31 July 2018 (UTC)

Oh no, the images wouldn't be included in this, we'd have soo many broken articles if that were the case. It's just for tracking the "overhead" of generating the HTML from the wikitext source. The images will only ever be a URI. The browser will still load them separately, so they don't count source-wise. Part of the 10 second load time is because the parser is actually waiting on the expansion to finish (and probably times out due to hitting the include size). Reducing the page below the include size would make the rendering phase quicker again. The ~5 second time from before the break is not bad for a template-heavy page like a portal. — AfroThundr ^{(u · t · c)} 14:22, 31 July 2018 (UTC)

Thanks for the clarification. It's ok to give ((Transclude random excerpt)) hundreds of article parameters because each call only transcludes and expands one of the articles. ((Transclude excerpts as random slideshow)) works differently: it needs to read all of the articles, ready to flip between them if the reader clicks the previous/next arrows. The diving portal now looks wonderful but it's reading in 365 articles and expanding 365 leads. That has to be expensive, but I'm not sure how we achieve such great results more cheaply. Certes (talk) 14:52, 31 July 2018 (UTC)

Each instance of ((Transclude excerpts as random slideshow)) will limit itself to only actually reading/using 50 excerpts by default, and a lower limit can be set with the |limit= parameter. - Evad37 [talk] 15:04, 31 July 2018 (UTC)

I will try limiting to 25. It will be a rare reader who ever gets that far, and if they do, they can purge the page for a new selection, or use the index above to go through the lot. If anyone ever does this I would be astonished. · · · Peter (Southwood) ^(talk): 16:58, 31 July 2018 (UTC)

I tried 25 and it was still too large. I've just limited the large lists to 20 and that works (1,945,881/2,097,152 bytes). Certes (talk) 17:13, 31 July 2018 (UTC)

And that explains my edit conflict! I came to the same conclusion, 20 works fine. I just added it to the whole lot in case things grow over time. Still cutting it a bit fine, as many of the transcluded excerpts are rather small and will grow, but as long as I know how to fix it is manageable, and we now know roughly what the upper limit might look like. Cheers, · · · Peter (Southwood) ^(talk): 17:50, 31 July 2018 (UTC)

This limitation is a thing to bear in mind when designing a portal wizard. In a few years the limit may go up, as things do. · · · Peter (Southwood) ^(talk): 17:59, 31 July 2018 (UTC)

10 seconds is a fairly long time to wait if you are accustomed to fast internet. For me it sometimes take that long to save an edit, and not necessarily a big one. That will also get faster as the years pass. · · · Peter (Southwood) ^(talk): 18:04, 31 July 2018 (UTC)

I don't suppose there is a way to bypass the full expansion, and load the content of the excerpts (or images) one at a time as and when they are selected, as I assume the images are loaded into Mediaviewer? · · · Peter (Southwood) ^(talk): 18:35, 31 July 2018 (UTC)

I believe dynamically loading excerpts like that would require client-side JavaScript, so probably not something we'd be able to do with templates alone. — AfroThundr ^{(u · t · c)} 19:20, 31 July 2018 (UTC)

I notice that portal is now clocking in at a hair under the include limit (currently 96%).

<!-- 
NewPP limit report
Parsed by mw1266
Cached time: 20180731184805
Cache expiry: 3600
Dynamic content: true
CPU time usage: 6.572 seconds
Real time usage: 7.913 seconds
Preprocessor visited node count: 51801/1000000
Preprocessor generated node count: 0/1500000
Post‐expand include size: 2013571/2097152 bytes
Template argument size: 662620/2097152 bytes
Highest expansion depth: 20/40
Expensive parser function count: 5/500
Unstrip recursion depth: 0/20
Unstrip post‐expand size: 758943/5000000 bytes
Number of Wikibase entities loaded: 0/400
Lua time usage: 4.526/10.000 seconds
Lua memory usage: 22.32 MB/50 MB
-->
<!--
Transclusion expansion time report (%,ms,calls,template)
100.00% 6430.083      1 -total
 69.78% 4486.731     18 Template:Transclude_excerpts_as_random_slideshow
  9.63%  619.190     18 Template:Navbox
  7.94%  510.635    188 Template:Ship
  7.14%  459.012     25 Template:Columns-list
  6.88%  442.563     18 Template:Collapsible_list
  6.37%  409.448      1 Template:Random_slideshow
  4.20%  270.270      1 Template:Recreational_dive_sites
  3.34%  214.923     78 Template:SS
  2.64%  169.726      1 Template:Transclude_list_item_excerpts_as_random_slideshow
-->

So 7.9s to load the page (not counting the time to load images, etc.) and 4.5s of Lua time. A bit on the heavy side, but manageable, assuming nothing else is added to it.

On another note, how feasible would it be to whip up a JS widget to yank these blocks out of the page content and display it for the user? Just curious. — AfroThundr ^{(u · t · c)} 19:20, 31 July 2018 (UTC)

@AfroThundr3007730: I didn't understand your question. You want a user script to do what?    — The Transhumanist   04:20, 12 August 2018 (UTC)

I was referring to a toolbox button that will give you the template and Lua stats for a page in a popup when clicked. Not that searching the HTML source directly is difficult or anything. Just thinking it would be handy for checking on the heavier portals. — AfroThundr ^{(u · t · c)} 06:52, 12 August 2018 (UTC)

Firstly, can I say that I am in awe of the absolutely amazing work done by so many keen editors here over the last few months. Naming no names, you all know who you are.

Anyway, I thought I'd drop by and start to pick up tips to manually improve Portal:Alps, and add in some of the new automated features being developed. Amongst all the complex challenges and solutions being discussed here, I actually found it quite hard to wade through and to pick out helpful links to where the good bits are already deployed and working fine. I finally managed to understand enough to try out a few of them in my sandbox - and I'd welcome feedback, especially from Bermicourt. But first I had to resort to read back through some of the really informative newsletter updates left on my talk page by The Transhumanist. I then pasted the most up-to-date instructions and links into the bottom of my mockup as a form of reference tool for myself. Only then could I understand enough to create a working demo.

So I was wondering, could we have some form of really obvious, high-profile 'shop window' on the Project page to help show off some of the updated Portals that demonstrate how well each one of these elements work? It would be great to see examples of individual elements, different column layouts and so forth, and maybe even some 'before and after' links. As well as helping people like me to see current developments in action, and to manually modify an existing Portal, I suggest it could be a useful section to keep updated whilst we're in transition, especially to show the 'non-believers' how great things are becoming. My apologies if I've missed something that's already been created - maybe it just isn't easy to find. Cheers all, Nick Moyes (talk) 14:27, 17 August 2018 (UTC)

@Nick Moyes: The easiest way to start, is to put ((subst:box portal skeleton)) on the blank page, and press ↵ Enter.

For Portal:Alps, it looks like this: https://en.wikipedia.org/w/index.php?title=Portal:Alps&oldid=855407361

Then you fill in the blanks.

Or, you can copy any of the new portals. Most of their code is templatized, some even with magic words. So when you save it on a new page, it will conform to the subject in the title of the page, except for customizations, like the panorama, sections using ((Transclude random excerpt)), manual search terms in the Did you know and In the news sections. Pretty easy to spot when you view the page.

Most of the new tools are covered and put into perspective on Wikipedia:WikiProject Portals/Design.

The most extensive portals are based on outlines, using the ((Transclude list item excerpts as random slideshow)) and its section parameter. So using this model requires building an outline first. See Portal:Monaco (which is partially built on this model), and Portal:Lithuania (which is built almost entirely on this model).

As for shop windows, the portals themselves are just that. Look at the new or revamped portals, and see what features you like. Then pull those right out of the page source.

I hope the above tips help. "Shop windows" are provided below...    — The Transhumanist   08:01, 18 August 2018 (UTC)

Portals using ((Transclude random excerpt))

Portals using ((Transclude list item excerpt))

Portals using ((Transclude list item excerpts as random slideshow))

I am currently searching article space for links to www.1911encyclopedia.org a long dead website which I am replacing with links to wikisource using the template ((cite EB1911)).

I used AWB to create the list and I included portals in it as they are visible to readers. The portal Portal:Crusades has shown up with two links:#

• Portal:Crusades/Bio Archive
• Portal:Crusades/Selected biography/10

The reason for this is that the portal includes very old copies of various Wikipedia articles. In this case an old copy of John Hunyadi.

Someone who cares needs to remove the page "Selected Biographies" or the sub-pages of "Selected biography" (or turn them in to redirects to the current articles), or whatever, but old version of articles ought not to exist in portal space as they are indirectly visible to readers via links to portal space). -- PBS (talk) 19:48, 21 August 2018 (UTC)

@The Transhumanist: I see that you've worked on this portal recently and no one has held their hand up as its manual maintainer. Is it a good candidate for a makeover, replacing the old text by ((Transclude lead excerpt)) etc.? Certes (talk) 20:20, 21 August 2018 (UTC)

@Certes and Evad37: That was part of an AWB run during which I upgraded the image sections with slideshows for a couple hundred portals. After the conversion, each one was manually checked and tweeked (if needed). There are about 1300 to go. :)

All the portals that don't have maintainers are in need of further upgrading. So far, the intro sections on all but about 70 portals without maintainers have been upgraded, as have all their Associated Wikimedia sections. Underway are upgrades to their Selected images sections, their categories sections, and adding banner-shaped images (such as panoramas) to their intros.

All these portals will be completely overhauled eventually, especially if other AWBers join in. Doing most of the upgrades myself will take many months, because I'm about to switch back over to programming (which itself could speed things up, in the mid-term, but there are no guarantees in software development). :)

I ran into an issue while converting Selected image sections. There is a treasure trove of excellent images with captions in the subpages of many portals. "Upgrading" those by rebuilding them from scratch, or supplanting their image slideshows, would be a downgrade. Some have up to a hundred image subpages. I started skipping portals that had rich collections. It would be nice to gather those up automatically into a gallery section of a portal, and then the gallery section could be accessed via ((Transclude files as random slideshow)), using its section parameter feature.

Thoughts (on how to build a tool to gather images and captions from subpages automatically, and deposit them into a section of a portal basepage)?    — The Transhumanist   00:12, 22 August 2018 (UTC)

I am working on a system to create portals from outline lists, and use a gallery at the end of the outline list as a repository for selectable images. At the same time I am creating short descriptions and using them to annotate outline lists, which will also serve as a source for index lists. All useful for navigating a topic. An example of this integrated syatem can be seen at Portal:Underwater diving and Outline of underwater diving. A tool for gathering images and captions would go well with this approach, as the images can be stored in the outline list and transcluded into the portal without an additional subpage. When there is no outline list yet, a subpage would be a reasonable temporary measure, but there may be other ideas around, and if preferred, they could be stored directly on the portal page - it would just become a bit larger. Cheers, · · · Peter (Southwood) ^(talk): 16:31, 22 August 2018 (UTC)

For what it's worth, I think that time spent on automating portal maintenance and construction by our best tool writers is the best use of their time for this project. Those of us with lesser skills in this field can usefully test the tools and brainstorm improvements, and gradually upgrade the portals on the side, as a way of testing the tools. · · · Peter (Southwood) ^(talk): 16:43, 22 August 2018 (UTC)

Hello. Is there any tool to transclude wikitables? For example the Portal:Chess has an outdated table with the top 20 FIDE rating, which could be transcluded from FIDE world rankings.Guilherme Burn (talk) 12:08, 23 August 2018 (UTC)

You could use mw:Extension:Labeled Section Transclusion, if you're happy to add section tags around the table in the article. Certes (talk) 12:20, 23 August 2018 (UTC)

Great @Certes: worked perfectly. Please, see the result Portal:Chess. Only ((Transclude random excerpt)) that is not working very well. But I think the problem is in the articles that have been transcluded.Guilherme Burn (talk) 13:59, 23 August 2018 (UTC)

The table looks good. What's going wrong with ((Transclude random excerpt))? The portal looks fine to me, but perhaps the pages that break it are not being randomly selected at the moment. Certes (talk) 14:36, 23 August 2018 (UTC)

See edits by Plantdrew here: [1]. I previously raised this  on their talk page, asking them not to trim relevant portals. There was no response from them, and they did at the time move on to doing taxobox cleanup... but now they are back to mass-removal of portals. Sometimes with misleading edit summaries like [2],[3] - Evad37 [talk] 09:31, 6 September 2018 (UTC)

@Evad37: I would revert them citing unexplained deletion of content. Dreamy Jazz 🎷 ^{talk to me | my contributions} 15:39, 6 September 2018 (UTC)

Yes best revert.....the editor should not orphan a portal in this manner....if the portal is fucked it should go through the deletion nomination process. Disruptive runaround to say the least.--Moxy (talk) 01:24, 7 September 2018 (UTC)

I see portals being deleted (not surprising given the recent discussions), but is anything being done thereafter to remove the deleted portals from article pages? Is there a script or bot or something? I noticed Portal:Prisons was speedily deleted a few months back, and would rather not manually pull it off every page where it now shows as a redlink. Suggestions welcome. UnitedStatesian (talk) 23:19, 9 September 2018 (UTC)

@UnitedStatesian: Portals are being deleted but generally not by members of this project, who usually prefer to improve such portals to a condition where they can be kept. Tagging a page for deletion is always quicker and more interesting than cleaning up the resulting mess of dead links, and the latter doesn't always happen. Thanks for pointing out the problem. It does look as if we've been left to manually pull it off every page where it now shows as a redlink. I'll see what I can do to help tomorrow. Certes (talk) 00:00, 10 September 2018 (UTC)

An alternative to deleting the links is to divert them to somewhere like Portal:Criminal justice instead. Any opinions? Certes (talk) 00:12, 10 September 2018 (UTC)

I like that idea. No need to edit all of the including articles, and it allows for the re-creation of the portal at a later date, assuming it has the content to stand on its own. — AfroThundr ^{(u · t · c)} 02:20, 10 September 2018 (UTC)

I was thinking of editing the included articles but I agree that a redirect would save time and reduce the scope for errors, so I've created one. It appears as Prisons portal or similar in the articles, which may be considered slightly misleading, but there are plenty of other redirects in portal space. Certes (talk) 10:01, 10 September 2018 (UTC)

Hello. In an attempt to improve the Portal:Pornography, I moved it to Portal:Erotica and Pornography. But now I'm having trouble displaying the images using the template ((Random portal component)). Is there a way to point to old subpages? I believed that all would be moved. If anyone can also help me in the portal layout. Thanks. Guilherme Burn (talk) 20:36, 10 September 2018 (UTC)

I would recommend converting the portal to a single page format, as it is the new standard and had advantages for maintenance. I will see what I can do to help. · · · Peter (Southwood) ^(talk): 09:14, 11 September 2018 (UTC)

I have made a start. Follow the example to fill in the file names etc. · · · Peter (Southwood) ^(talk): 10:43, 11 September 2018 (UTC)

For reasons which are not clear to me yet, both slideshows are only showing 3 images. · · · Peter (Southwood) ^(talk): 11:19, 11 September 2018 (UTC)

Using "|File=Foo|File=Bar" just overwrites the File parameter; the template and module see only the last value. I've changed File= to the File: namespace prefix, making the parameters unnamed, which seems to work. Certes (talk) 11:28, 11 September 2018 (UTC)

Thanks @Pbsouthwood:. I also only see benefits in single page format. But dynamic image templates are still showing a lot of bugs. They do not display properly on mobile devices, they do not display the option to view everything in a gallery, and now this problem with the 3 images.For now I will list the images and subtitles to avoid being lost. @Certes: I didn't understand, could you give me an example, please? Guilherme Burn (talk) 11:41, 11 September 2018 (UTC)

@Guilherme Burn: I made this edit, changing File= to File: on several rows. File=Foo would create a parameter called File, allowing the template to use the syntax (({File))} to retrieve the value Foo. I don't think this template looks for a parameter called File. Even if it does, the several File= entries would overwrite each other and the template would only receive the last one. I think what was intended was File:, to indicate that the image is in the File namespace. Certes (talk) 11:51, 11 September 2018 (UTC)

Its working, which is the important bit. Thanks Certes.

@Guilherme Burn:, I wouldn't worry about losing the images and subtitles. Once they are in the template they are pretty much there for the lifetime of Wikipedia. There are already ways to manage mobile display, but not as a slideshow, and that may also change. · · · Peter (Southwood) ^(talk): 12:11, 11 September 2018 (UTC)

@Pbsouthwood: I add all "selected images" using Notepad++ to extract the data from the original page. But they are not all being displayed in the template, especially the last ones of the list.Guilherme Burn (talk) 16:55, 12 September 2018 (UTC)

@Guilherme Burn:, I removed a pair of comment tags and cleaned up a bit. The template does not like empty file parameters. I think they all display now. I assume you intend to put the captions back too.

Do you intend to rescue the did-you-know subpages too? · · · Peter (Southwood) ^(talk): 20:03, 12 September 2018 (UTC)

OK thank you. Yes, as soon as there's a time, I'll retrieve the subtitles as well. No, the did-you-know subpages are over the years with no update. And I believe they are expendable.Guilherme Burn (talk) 22:47, 12 September 2018 (UTC)

Ping me when you are done and I will finish cleanup of redundant subpages. · · · Peter (Southwood) ^(talk): 05:29, 13 September 2018 (UTC)

 finish @Pbsouthwood: I moved all the necessary subpages.Guilherme Burn (talk) 15:20, 18 September 2018 (UTC)

Thanks, I will delete them. Cheers, · · · Peter (Southwood) ^(talk): 15:38, 18 September 2018 (UTC)

I noticed above some concern about stubs appearing in portals. Keep in mind that our lua gurus have built-into the transclusion modules a stub filter, so that articles tagged as stubs are not displayed in portal slideshows. Just an FYI. ;) (Remember to show your appreciation to these guys, for the amazing features they have enabled in portals).    — The Transhumanist   23:33, 26 September 2018 (UTC)

@The Transhumanist: I have moved this off-topic post out of the "Time for some portal creation criteria?" section, to this new separate section. The other is a discussion about creation criteria; please stay on topic, and do not spam it with technical announcements. Thanks. --BrownHairedGirl (talk) • (contribs) 00:56, 27 September 2018 (UTC)

It was in answer to specific points made in the discussion itself, and therefore, I've reinserted it as a specific reply, back into the discussion. I'd appreciate it if you'd leave my on-topic posts alone.    — The Transhumanist   06:24, 27 September 2018 (UTC)

That is a useful feature, Kudos to our coders. It is in my opinion relevant to the discussion above, but not obviously so to someone who is not part of the project. · · · Peter (Southwood) ^(talk): 07:57, 27 September 2018 (UTC)

Discussions are taking place as to whether the portals listed below are suitable for inclusion in Wikipedia according to Wikipedia's policies and guidelines or whether they should be deleted.

The portals will be discussed at WP:MFD in each respective deletion discussion until a consensus is reached, and anyone is welcome to contribute to the discussions. The nomination may explain the policies and guidelines which are of concern. The discussion focuses on high-quality evidence and our policies and guidelines. North America¹⁰⁰⁰ 21:41, 27 September 2018 (UTC)

One concept we have discussed, toward which we are approaching fairly quickly, is the capability to provide a button that generates a portal at the time you press the button. No stored page required. Pbsouthwood referred to them as "quantum portals". My guess is that this isn't more than a few years away, maybe as little as one. To allow editor contributions, we would need to have a parameter page though, or some other way of storing editor input. Like if you wanted to add pictures to an image slideshow. And differences in style could be handled on a settings page somewhere, like on the preferences page, including randomizing styles. I wonder, where would the bar be for quantum portals?    — The Transhumanist   21:36, 27 September 2018 (UTC)

The current external pressure may force some accelerated development. I was hoping for a less forced development process where more options could be explored, but reality is, and we must live with it. We might already have the tools to do it, but not as well as I was hoping for.

I would expect the bar for quantum portals to be reasonable. It must be appropriate to an automated process. The existence of a suitable navbox will allow a reasonable quantum portal to be autogenerated from a template. If the creation criteria are specified carefully it will help with refining the main template. Some of the box section templates will probably need tweaking. They probably need that tweaking anyway. · · · Peter (Southwood) ^(talk): 07:07, 28 September 2018 (UTC)

At this stage, I would guess that the existence of a navbox might be sufficient. A quantum portal would only be rendered for someone who is interested enough to press the button. On the other hand, I currently support the notion that for every navbox there should be an equivalent category (until I am shown reason why this would be a bad thing). However, navboxes are easy to use as portal frames, and categories are not, so I would be inclined to leave the category out of the quantum portal criteria if only for this reason. For semi-automated portals I would be quite happy to see a requirement for an equivalent category, if only because it would encourage their creation. There might be some conflicts where navboxes and categories are named inconveniently, and I have seen cases where the navbox could have been named better. · · · Peter (Southwood) ^(talk): 09:51, 28 September 2018 (UTC)

Let's build a list of missing portals that are needed. What subjects would you like to see a portal on?    — The Transhumanist   00:02, 27 September 2018 (UTC)

• Let's leave that aside until we have had an RFC to establish consenus on the scope and other thresholds for creating portals.

Less bot-like portal creation, please ... and a lot more consenus-buiding on purpose, utility and scope. --BrownHairedGirl (talk) • (contribs) 01:11, 27 September 2018 (UTC)

 

Note that there is already a standing consensus on portal creation: no limitations on scope. In other words, there is no established consensus to limit the scope of portals. Portal creation has been allowed at all scope levels since 2004. The low threshold is established in speedy deletion criteria. Portals are currently covered by the same notability requirements as articles. In order to set new limitations requires establishing a new consensus. Present your reasoning on establishing a new consensus and we will all happily consider it. In the meantime, the consensus currently in place, stands.

 

As for your suggestion that we cease operations, there is no consensus for that. The items in the above list are all level 2 vital topics, with very wide scope, and each of them score high up on the portal rating scale for importance. Also, by finding out what others want, we can get your feedback on their portal suggestions. I for one, would really like to know what you think of the above topics as potential portals. Sincerely,    — The Transhumanist   08:01, 27 September 2018 (UTC)

I would agree that a level 2 vital topic is adequate justification for a portal, provided that there is sufficient material to create one. I would not argue against a level 3 vital topics either, also provided we have the articles. Whether a poorly populated portal is an inducement to expanding a topic is debatable. I do not have an opinion on that as I have no evidence either way.

Regarding "bot-like portal creation": A large part of the thrust of portal R&D is to make portal creation and maintenence as low effort as possible. Without prejudice regarding just how fast and how many portals should be created, even which portals should be created or deleted, "bot-like portal creation" is actually evidence of success in reaching our goals. · · · Peter (Southwood) ^(talk): 08:14, 27 September 2018 (UTC)

Note that underwater topics are not included at any level in the vital article system. The underwater portals are some of the best portals we have. And they show that vital levels are not adequate as a filter. Many topics with many subtopics are not on the "vital" lists. The vital lists were created to plan featured status. The vast majority of Wikipedia will never reach featured status, but that doesn't mean navigation tools are not needed for them as well. The portal format is a general purpose navigation format, just as all the other navigation systems are. There is no reason to limit portal's use to subjects with more topics than a portal can handle efficiently.

BHG wants portals limited for use on subjects with thousands or more subtopics. That is far more subtopics than make a portal useful. On the old style of portal where a single excerpt is displayed upon each visit, it would take thousands of visits (or page purges) to browse through the portal's articles. On the new design, if you put thousands of topics in a slideshow, assuming the servers would handle that, nobody would ever get to the end of the slideshow, let alone a tenth of the way through it. (Note that the servers limit lua to 10 seconds to do their thing, limiting how much you can put in a portal's slideshows, and pushing a portal to 10 seconds is long time to wait for page load). Slideshows are most useful for from a handful of excerpts to maybe around seventy-five or thereabouts. After that, at least for me, they get less convenient and make clicking forward or backward to a particular entry more cumbersome. Like if you want to go back and read an entry you've already looked at -- if there are several hundred or more entries in the slideshow, that's potentially a lot of clicking to get back to that entry, and you might miss it.    — The Transhumanist   09:46, 27 September 2018 (UTC)

Underwater diving is a level 4 vital topic in "life", but your point is valid nonetheless. Vital topics probably all should have portals, but that should not exclude other topics which can have portals

From personal experience, a portal that is too big will crash the rendering system. If kept trivial enough it is not a problem, but when one tries to make it comprehensive it just gets too big and either overruns the allocated space, or runs out of time. Splitting into sub-portals helps. I don't know how large they can be without being a problem, but do know that automation pushes the size up, so the less maintenance, the smaller they need to be, so the more there will be. Swings and roundabouts. I favour more in number, smaller, more comprehensive, more focused and automatically updating portals at the bottom end, with wider scope but less detailed portals higher up the tree.· · · Peter (Southwood) ^(talk): 13:11, 27 September 2018 (UTC)

Until someone comes up with a better metric, I think that a navbox is a good visual clue. If the topic needs more than one navbox, there should probably be more than one portal. If the navbox is sparse, there may not be enough for a portal yet. I would like to see a single (approximately) eponymous category tree in every portal.

That was a lot to read (and probably belongs on a subpage). Perhaps we should now adopt the top-down approach suggested above. Create the most urgently needed 100 or so missing portals that almost everyone agrees would benefit Wikipedia and would clearly survive MfD. We can do that in a bot-like way as long as we notify relevant Wikiprojects who may wish to hand-craft some individuality into them. At that point we should pause and decide how much further to go. There may be a case for continuing further down the tree, but we should certainly avoid mass-producing skeleton portals for towns no one here has ever heard of. Certes (talk) 11:36, 27 September 2018 (UTC)

If the projects want to fine tune, it is better if they do it after the portal has been constructed, as that way they are less likely to inadvertently make them a maintenance problem. I would suggest create first, then inform the project, so they have a sturdy frame to build on if they want to. · · · Peter (Southwood) ^(talk): 13:11, 27 September 2018 (UTC)

Agreed. Certes (talk) 13:28, 27 September 2018 (UTC)

By request, I have been methodically adding links to portals (e.g. Alicia Keys), adding a footer where necessary (e.g. Boston Red Sox). I've edited templates beginning with A and B but paused as some of the targets are being proposed for MfD in alphabetical order. Any comments? Certes (talk) 11:36, 27 September 2018 (UTC)

Pause or continue as you prefer. MfD is not a reason not to improve the subject, and an improved portal is more likely to survive. Put in as much work as you think is worthwhile, so assess the portal and fix it if you care enough. Some will go, most will probably survive, and those which are deleted can be recreated when better building materials are available. Just my 2c · · · Peter (Southwood) ^(talk): 13:11, 27 September 2018 (UTC)

To clarify: in this task I'm not improving the content of the portals themselves, merely editing templates etc. to add wikilinks which lead to portals. Certes (talk) 13:28, 27 September 2018 (UTC)

I see, It becomes a bit of a guess which portals will make it and which won't, At present the changes are correct. If the portal is deleted, someone will have to revert if they get round to it before the portal is recreated. I would look at the navbox and edit it according to whether I thought the portal was justified or not. So use your judgement, but don't lose any sleep about getting some wrong. · · · Peter (Southwood) ^(talk): 14:07, 27 September 2018 (UTC)

@The Transhumanist: you write Note that there is already a standing consensus on portal creation: no limitations on scope. In other words, there is no established consensus to limit the scope of portals.

Those are actually two different statements in one para.

The first sentence asserts that a positive consensus has been reached not to limit he scope of portals. The second sentence says no consensus has been established.

One of them may be true, or neither may be true, but logically they cannot both be true. please clarify which you believe to be true. --BrownHairedGirl (talk) • (contribs) 19:24, 27 September 2018 (UTC)

The second statement asserts that there is no consensus to limit the scope of portals, not that there is no consensus.

If there is consensus to not limit scope there is no consensus to limit scope. Seems logical to me. · · · Peter (Southwood) ^(talk): 20:21, 27 September 2018 (UTC)

Not so, Pbsouthwood. The first sentence in The Transhumanist's statenent announces that there is a specific agreement that there should be no limit. The second one says no consenus has been reached. Those are different statements, and I want to know which one is being actually asserted.

So... if there has been a specific consensus reached that no limit will be applied, that will be the first sentence above. In that case, please can someone link to that discussion so that we can assess how broad and how fresh the consensus is.

If there is no link, the sentence one is false and sentence two applies. --BrownHairedGirl (talk) • (contribs) 21:28, 27 September 2018 (UTC)

I disagree, but this is a red herring. Lets get back to something constructive, like the proposed criteria. · · · Peter (Southwood) ^(talk): 08:09, 28 September 2018 (UTC)

@Pbsouthwood: Peter, it's not a red herring. Lack of clarity around community consensus is at the root of this mess, so clarity of language matters. And since there is no link to a discussion which reached, the answer is that no consenus has been reached on limits other the stable text at WP:PORTAL.

But we clearly are not going to agree, so let's focus on creating an RFC. --BrownHairedGirl (talk) • (contribs) 00:59, 30 September 2018 (UTC)

All of BrownHairedGirl's requests and suggestions fall in line with the stance she presented during the RFC proposal to delete all portals and the portal namespace:

*Support. Whatever the theoretical benefits of portals, the reality is that most of them are woefully under-maintained, and v little used. This been the case for years, so all the talk of "keep and improve them" is dreaming: there simply are not enough editors with a sustained interest in doing so, Worse, given the viewing figures, anyone advocating widespread improvement is unintentionally encouraging editors to waste their time. That would actively damage Wikipedia by diverting effort away from actually improving en.wp
I say this with some sadness because I recently spent a day or two making Template talk:YearInCountryPortalBox to automatically add portal links to thousands of country-by-year cats; but as I built it and viewed more portals, I became more and more convinced that my concerns were well-founded.
My ideal solution would be too keep about 20 major portals(art/science/etc plus continents), and delete the rest. But given the unhelpful binary nature of this proposal, I'd prefer outright deletion to either keeping them all or to having 1500 MfD debates. --BrownHairedGirl (talk) • (contribs) 04:38, 19 April 2018 (UTC)

This, and all of her postings since, show an extreme bias against portals, and seek to limit, filter, or delete them. Beware.    — The Transhumanist   09:57, 27 September 2018 (UTC)

Deal with the specific criticism in each case. There may be good and bad. Rebut the bad, politely, with logic and evidence, and learn from the good. The opposition may also have good ideas, or inspire them through rational debate. · · · Peter (Southwood) ^(talk): 13:20, 27 September 2018 (UTC)

I have made no secret of my position, and it hasn't changed. I have also posted several times to remind members of this project that there were ~150 editors who posted at the RFC to support either deletion of all portals, or a major cull. So my view is not an "extreme bias"; on the contrary it is an evidence-based assessment shared by many other editors.

Despite that strong support for a cull, this project seems decided to remark on a massive spree of creating hundreds of new portals, and several project members have explicitly rejected calls for a moratorium while a consensus is formed. This rapid push in the opposite direction to widespread community concern runs directly counter to the principles of consenus-buidling, so I am finding it hard to sustain the hope that dialogue here serves any purpose . I hope that my pessimism is misfounded. --BrownHairedGirl (talk) • (contribs) 20:07, 27 September 2018 (UTC)

I think BrownHairedGirl's concerns about the explosion of new portals may be a helpful warning shot across the bows. I would hate to see the deletion debate opened up again after all the progress that has been made. I wonder whether it might make sense to throttle back for now on the creation of new portals that won't necessarily have a human maintainer and to focus more on improving the existing ones. Otherwise we risk attracting unnecessary flak and undoing everyone's hard work. Having seen how easy it now is to generate a new portal, I do think portals should meet a set of minimum criteria as part of their launch process. Someone suggested that we didn't want "German bureaucracy", but I would say, whether we think Germans are bureaucratic or not, the de.wiki process and criteria are straightforward and something similar could be tailored to meet our needs. For BrownHairedGirl - please continue to contribute to the dialogue. We editors won't always agree, but "iron sharpens iron" provided we stay constructive. Hope that helps. Bermicourt (talk) 20:24, 27 September 2018 (UTC)

Thanks, @Bermicourt.

I do want to have a dialogue here. But sadly my experience so far has been that most of the project's contributors have been unconstructive, and unwilling to actually engage in dialogue. There has been a lot of restatement of position, a lot of verbosity of the technology, a lot of misleading assertions about consensus, but no sign until now of a willingness to accept that the enthusiasm of proj members for the creation of new portals does not at the moment have explicit community-wide consensus. The Transhumanist has been particularly averse even to the notion that they might supply a post-facto justification for the creation of a portal, averse to the holding of deletion discussions, and averse to any scope criteria at all. There is limit to how much energy I am willing to put into trying to communicate through the fog.

So if I am to continue to work collaboratively towards an RFC, I need to know which editors are actually prepared to work with me to formulate a neutrally-framed RFC on criteria for portal creation, to put all options on the table.

That can only work if editors a) accept that others may legitimately have very different views to their own, and b) that they are prepared to focus on defining options rather than on arguing the case for against them or diverting the discussion into technical commentary.

Any takers for a focused exercise in formulating options? --BrownHairedGirl (talk) • (contribs) 21:19, 27 September 2018 (UTC)

I'm willing to help work on setting a 'bar' if others are - see my response above - but will not be around much this weekend, so bear with me! Bermicourt (talk) 21:39, 27 September 2018 (UTC)

I haven't answered BHG's questions on most of the MfDs yet — there are eighteen of them — and I haven't had a chance to get back and see how she responded to the scope-related answer(s) that I did post. I'm still sifting through the various threads on this entire issue trying to catch up. Though I am working on, or about to work on, five responses, not all necessarily in this order:

The first is that there are MfDs in play right now. In order to give those the best chance of surviving those nominations, those portals need to be completed. Right now, the participants are arguing over incomplete portal starts. Portal stubs. I am disappointed that nobody has jumped into them to work on them. That is one of the main ways to save a page from deletion. Like the Wikipedia:Article Rescue Squadron. Many of the points concerning whether portals of their scope should be retained are being covered in their respective MfDs, and may play an important part in the wider criteria discussions. Another very strong reason for me to work on those first, because it will force me to think about the issues in context, at the front lines, where user meets portal. So, those MfDs are my highest priority right now. The discussions here can wait 3 days or so. We have plenty of time to hash this out after the MfDs have run their course.

One of my other responses will be rather technical, dealing with the utility and limitations of the Selected articles frames of portals — the core feature of portals — including those for the subpage-based older model of portals, and of the new design paradigm. And, with the supplemental features that add further content not generally found on any other type of page on Wikipedia. And the other features too. The main issue I will be focused on in this response, is what scope portals are ideal for navigating, and I will be very specific as to why, and will show specific examples of portal components in my explanation. A supplemental issue here I will also be addressing is the scope of the entire portal system, and the system-level benefits that portals as a whole, can provide.

Another of the responses will deal with the ramifications of various levels of creation criteria upon the existing set of portals, especially the set of portals that existed at the time the RfC was posted. How many of the portals will qualify for deletion under various scope criteria? This will require that I delve into the set, and quantify the portals of various scopes. I could sure use your help on this one.

Another of my concerns is that BHG is rehashing the RfC all over again, and presenting the minority position as if it were community consensus. So, I am working on another response, that will analyze the consensus established in the RfC, and deal with BHG's various statements of position.

Then there is the issue of portal perspective, probably the most important issue of all. Looking at the value of portals from various angles. Most of the debates so far have dealt with "oh, we should have a portal on this one, rather than this one, because they have x number of topics." In this response, I will be looking at the user's experience while they are on the root article page, and exploring what impact having a portal button on that page might have on the user. What are the benefits of the individual leaves of this tree we are building to the user of any particular subject? In this response I will also be touching upon the irrelevance of comparing page visit counts with the counts of pages served by external search engines, and looking at how many hits can be deemed significant to pages that receive only internal traffic in relation to their cost in development time and effort. But, I'll be handling that issue mostly in one of the other responses.

There is a lot of territory to cover here, and each response will probably amount to a wall of text in their own right, so, please, bear with me. Thank you.    — The Transhumanist   23:36, 27 September 2018 (UTC)

Sorry, TTH. Another wall of text is disruptive again.

Do try to focus, and save the wall for the RFC. (Tho even there, you would do much better to summarise concisely and link to walls of text elesewhere if you think anyone may want ti read them)

What we need now is a question and a few options to frame as an RFC, to establish whether there is a broad community consensus to amend the long-standing guidance at WP:PORTAL that portals should be about broad subject areas, which are likely to attract large numbers of interested readers and portal maintainers. You clearly have strong views on that. I and others have different strong views. RFC is where those differences are resolved.

In the meantime, I have reverted your unilateral rewriting of the scope of an entire namespace (the edit summary "update" was so misleadingly vague that it looks sneaky; see WP:SUMMARYNO). Such a major step requires a broad and stable community consensus. --BrownHairedGirl (talk) • (contribs) 00:18, 28 September 2018 (UTC)

I don't particularly find a wall of text to be disruptive. That's just how some discussions go around here. We like to thoroughly discuss the various aspects of a topic, especially one with far-reaching consequences such as this one. Best to cover all the bases than leave something out that might not have been considered yet. — AfroThundr ^{(u · t · c)} 14:23, 30 September 2018 (UTC)