Template talk:Infobox Australian place

See also: Blank infobox page | Documentation page | Discussion page | Examples page

Core policies for this box

KISS

Keep this box as simple as possible.

Scope

Make sure you remember that this box is used on more than 12,900 pages, of 7 different types.[1] Whatever you do needs to be applicable to a good number of those pages.

Discussion/Community

Its very important to discuss everything that's going to change. And before you suggest something, look in the archives, it may have been suggested before.

Accepted value: "township"

The present accepted values – city, town, lga – don't cover Australia's many smaller places with higher population than a locality. I recommend including "township" in the accepted values.

Two random examples are William Creek -- permanent population <20 but a significant settlement nevertheless -- and Wanbi, South Australia, with a similar population, described as "a town and locality" when it is neither, really. They are both townships. Comments? SCHolar44 (talk) 13:13, 7 July 2024 (UTC)

I'm not sure about the township as, at least in WA, it doesn't seem to be an official description for a bounded location. I do however agree that another description below town is needed. Currently, "| type = town" will automatically place the article in the relevant town category, e.g. William Creek in Category:Towns in South Australia, which seems wrong for a lot of really small places as they just don't qualify as towns. Locality doesn't even exist as an option right now. Something below town would be useful! Calistemon (talk) 12:10, 8 July 2024 (UTC)

Town means a population centre, they can be small or large in terms of population, or even be ghost towns so we don't really need a distinction between a city, a town, a township, villages, hamlets etc. Certainly QLD has dropped all of those distinctions. We have the population field to show the size of a town in that regard. A locality has a boundary while a town has a centre point, or it's not an either-or. Indeed it is very common for a placename to be both a small rural town that sits within a locality of the same name. Suburbs are localities (being bounded) but the term suburb tends to used when they are in an urban area, but are otherwise interchangeable. What is wrong with the "type" is the inability to reflect that the topic of the article is both a population centre (town) and locality/suburb. One of the things to be aware of that if that if we change the "type" values, any tools that use that field need to rewritten, so it's not something to do lightly. Kerry (talk) 12:22, 9 July 2024 (UTC)

Indeed, some parts of wikipedia have 'human settlements' and 'populated places'... In WA (and Tasmania), the establishment of places occurred after townsites were surveyed and gazetted, but they never really became towns as such, and in effect over time have been localities. I just throw this in, as I think that many 'towns' in Australia may have been surveyed, and gazetted, but never really became 'towns' - they are more suitably known as localities. JarrahTree 08:05, 23 July 2024 (UTC)

For all purposes, the gazetted towns in WA are still there, parallel/inside the localities. If you go to Slipmap, select Localities (LGATE-234) and Townsites (LGATE-248) under Borders, you will see that the latter often exists within the former. Just take Kirup as an example, you will see that there is actually two marked out entities, the larger locality and the smaller townsite. Calistemon (talk) 08:24, 23 July 2024 (UTC)

Indeed, many of these abandoned towns are still officially gazetted. and for Queensland at least, the digitised newspapers on Trove will reveal the first sale of town lots, etc, which is nice to add to the article's history section and if you look at your state's geospatial information system, those grids of streets and land parcels still exist but the imagery shows nothing there except farmland etc. When a place is both a town and locality, you generally have two sets of coords as the town coords are generally of a point that is perceived to be the town centre (in a human sense) while the centre of a locality is usually a mathematically computed centroid based on the boundaries (and has no human meaning). Similarly they may have two census figures, one reflecting the town and one reflecting the locality. This is why it would be be useful if the infobox had a way to indicate that the article deals with both a town and a locality (since for the vast majority of them, there is no benefit to having 2 articles, except where the locality/suburb is but one of many suburbs (usually the historic centre suburb) of the town of the same name. Kerry (talk) 01:59, 24 July 2024 (UTC)

Lacking terminology to convey the size of a [here insert name of a very small type of human settlement] obfuscates the understanding of readers who don't know that Queensland has dropped all such distinctions, i.e. the vast majority. Their understanding is more likely to be closer to, as per SOED:

• a built-up area with a name, defined boundaries, and local government, that is larger than a village and generally smaller than a city
• the central part of a neighbourhood, with its business or shopping area
• densely populated areas, especially as contrasted with the country or suburbs.

The scale is nowhere near the scale we're talking about. At least one term below "town" is needed. On reflection, "populated place" that JarrahTree mentions seems to provide the maximum flexibility. It's descriptive and avoids being entangled in the nomenclature of any particular jurisdiction. SCHolar44 (talk) 23:30, 23 July 2024 (UTC)

It is lack of emoji symbols use, where an facetious, irony or cynical flag against the terms mentioned should have been made. Strongly disagree with the suggested usage of the term.JarrahTree 01:02, 24 July 2024 (UTC)

If the place was or is gazetted as something called "township", "village" or whayever, then I don't see any issue with calling it that in the lede and citing it accordingly. But we are discussing the type field of the infobox, which reading the documentation doesn't seem to make any great difference to anything (apart from the colour of the infobox). The documentation suggests the type might be used to recommend or control the selection of parameters used in the infobox, but my experience of writing thousands of place articles is that you can have any params you want no matter what the type is. If anyone knows of anything beyond the colour that is affected by the type, say so. The reason I would like to be able to specify that a place is both a town and locality in the type of the infobox, would be to allow two sets of coords (one for each, appropriately labelled) and two sets of census population (one for each, appropriately labelled). The type in the infobox can be different to the type in the lede. Kerry (talk) 04:40, 24 July 2024 (UTC)

In view of what Kerry and Calistemon have said about the specifics of a locality and town being separate entities on wikidata, the dual entities and the capacity of the infobox to carry such a multiplicty, is far more pressing than bothering about terminology. I strongly support any investigation into the possibility of an infobox parameter that can be designed for the two items of info to be included. JarrahTree 06:47, 24 July 2024 (UTC)

Information

In response to Kerry's request for details on how the template responds to |type=:

• |type= sets the short description of the article (eg: 'Town in /state/', or maybe 'Suburb of /city/ in /state/', etc.) - which is shown in the WP search suggestions
• |type= sets the infobox background colour - for the header and the labels column
• if |type=lga, the default is not to show a location map
  • for all other |type= values, the location map shows the Australian state map with the place as a point location
  • these can be over-ridden if a specific location map is forced (using |alternative_location_map=, |force_national_map= or |use_lga_map=)
• if population is sourced from wikidata (because |pop= is not supplied):
  • |type=town or |type=city will show the UCL (urban centre) population
    • if |type=town and no UCL population is found, SAL (locality) and / or ILOC (indigenous location) populations will be shown
  • |type=suburb will show the SAL (locality) population
  • |type=lga or |type=region will show the LGA population
• if |type=protected
  • if |iucn_category= is supplied, will show an IUCN banner
  • |nearest_town_or_city= will be shown if supplied
  • is supposed to get some different response when displaying coordinates (though it doesn't seem to make any actual difference)
  • |visitation_num= and |visitation_year= will be shown if supplied
  • will show a link to a list article of protected areas in the state
• if |type=lga
  • |mayor= will be shown if supplied
• if |type=cadastral
  • |hundred=, |former_hundred= and |division= will be shown if supplied
• |type= sets the heading on the places-near sub-table (eg: 'Towns around ...')
• |type= sets the categories the article is included in:
  • for |type=town: [[Category:Towns in /state/]]
  • for |type=suburb: [[Category:Surburbs of /city/]]
  • for |type=lga and if |est= is supplied: [[Category:Populated places established in /year/]]
• |type= also influences tracking categories, which I won't detail here

Opinion
I agree the template needs a type for small settled places (usually they will be too small for the ABS to define a UCL, which means usually under 200 people). My suggestion is 'settlement'. The Macquarie Dictionary has as one of its definitions of settlement: 'a small village or collection of houses, especiallty in a sparsely populated area'. If there is an ABS SAL (locality) in the linked Wikidata, that population should be shown (appropriately labelled), if not there will be no ABS population figure available.

Kerry, I'm not convinced of the value of two sets of coords for 'town' and 'locality': on a small-scale map (the default location map is of a whole state) they would likely just be two very-close points, while on a large-scale map point locations for what are both actually areas don't mean much - it would be more meaningful to show the actual boundaries of the 'urban' and 'locality' areas (admittedly a big mapping or data-import task). (BTW, the coordinates shown top-right of the article will be for the last {{coords}} call with display=title.)

As JarrahTree suggests, there needs to be a way of recognising that a 'place' can be both a town and a locality. Why not |type=townandlocality, which would show population figures for both the UCL and the SAL, provided they are both in the linked Wikidata item.

If displayed populations (etc.) are to depend on |type= values, we need 'terminology' for them. If we are not going to 'bother with terminology', then automatic populations will need to be presented for all entity types in the wikidata, regardless of |type=. Or is the suggestion a new parameter of 'ignoretypeforwikidatapopulation'? (That name is not a genuinely suggested one, but you get my drift I hope.) Innesw (talk) 12:29, 13 August 2024 (UTC)

Thanks for the thorough response. I hope there is further conversation.JarrahTree 13:00, 13 August 2024 (UTC)

Proposal for new values for |type=

Note: in the following 'locality' is used in the sense of a whole named postal-address area (= an ABS SAL), not a point location that happens to have a name.

• |type=locality
  • in general an alias for |type=suburb, but intended for rural localities. Therefore it would show a Wikidata population figure for (only) the ABS SAL.
  • the differences from |type=suburb would be in the article short description ('A locality in /state/'), the heading for the Places Near sub-table ('Localities around /place/'), the background colour and the categories
  • background colour:  #f9de9d 
• |type=townandlocality
  • for when a place name is used for both a town and the locality surrounding that town
  • would show Wikidata population figures for both the UCL and the SAL, suitably labelled
  • would create an article short description of 'A town and a locality in /state/'
  • the Places Near sub-table would have the heading 'Localities around /place/', and should contain the adjacent localities
  • background colour:  #f1f1b7 
• |type=settlement
  • for a settled place too small to be a town
  • it is assumed there won't be an ABS UCL for the settlement itself (otherwise |type=town would be valid). What should be done if a locality of the same name exists needs discussion.
  • background colour:  #d7f9da 

I am aware these changes would require changes elsewhere, especially to Module:PopulationFromWikidata, but the technical details can be sorted out later if the principles of the above changes are accepted. Innesw (talk) 11:50, 12 September 2024 (UTC)

Excellent suggestion! Cheers, Simon – SCHolar44 🇦🇺 💬 at 05:28, 16 October 2024 (UTC)

Short description not returned by annotated link template

Annotated link for Broughton Island (New South Wales) returns – 'island in Australia' and notice "Pages displaying wikidata descriptions as a fallback", but there is a short description, 'Protected area in New South Wales, Australia' generated by the infobox ({{Infobox Australian place}}), which the Annotated link template apparently does not find. I don't know if this is a unique occurrence or a general problem. Cheers, · · · Peter Southwood ^(talk): 07:22, 21 August 2024 (UTC)

For anyone interested, the issue raised has resulted in a discussion at Template_Talk:Annotated link#Failure to return SD from infobox? Innesw (talk) 12:20, 22 August 2024 (UTC)

No flag, coat of arms section?

Recently I discovered that, for instance, Melbourne doesn't have its flag or coat of arms in the infobox. And it turns out that this infobox lacks these sections. Why is that? I argue it's high time these sections should be returned or added. Even if a official flag (like the one of Sydney) is not used by the council, it still is official and should be displayed in the article until it is revoked by the city or replaced. Ivario (talk) 12:25, 9 September 2024 (UTC)

I think you will find that you can add a coat of arms. See the City of Rockingham article which has one using the Image2 parameter. Calistemon (talk) 12:55, 9 September 2024 (UTC)

Referring to population in the body text

The introduction of <!--Leave blank to draw the latest automatically from Wikidata--> against "|pop=" in the infobox was a great move forward. However, there remains a problem in many (most??) articles in which the population is discussed additionally in the body text. The last sentence in the lead in Mallala, South Australia is an example.

Whereas in the past, population figures simply got out of date (but were consistent in their "wrongness" in both the infobox and the body text), now when an automatic update has been made it will not be matched in the body text, and the inconsistency will be noticeable. For people who are Wikipeda-naive, it will lessen the authority of the product. It would be really good if a template could be devised to pick up the population figure against "|pop=" in the infobox and display it in the body text.

This is way beyond my pay grade to implement. How could this be done? / who should be asked? Cheers, Simon – SCHolar44 🇦🇺 💬 at 05:28, 16 October 2024 (UTC)

Its a very good question. I have used a template for this purpose for the localities lists in the LGA articles. You could possibly go like this example:

At the most recent Australian census, Pingrup had a population of 231 (SAL 2021).

Would this work for you? Calistemon (talk) 08:04, 16 October 2024 (UTC)

It certainly does, Calistemon. Brilliant! Thanks indeed.

Could this be tweaked to cover the (frequent) situation in which it's beneficial to indicate how many are in the township compared with how many are outliers? I would like to say:

In the most recent Australian census, the wider Mallala locality, including the town, had a population of 1,042 (SAL 2021)[1] and the population of the town alone was 887 (UCL 2021).[2]

References

1. Australian Bureau of Statistics (28 June 2022). "Mallala (suburb and locality)". Australian Census 2021 QuickStats. Retrieved 28 June 2022.

2. Australian Bureau of Statistics (28 June 2022). "Mallala (urban centre and locality)". Australian Census 2021.

But I can't get beyond this:

In the most recent Australian census, the wider Mallala locality, including the town, had a population of 1,042 (SAL 2021) and the population of the town alone was

• 887 (UCL 2021)
• 1,042 (SAL 2021)

References

Is this do-able, or is it a little beyond? I wait with bated breath.  :-)

Cheers, Simon – SCHolar44 🇦🇺 💬 at 23:12, 16 October 2024 (UTC)

bated breath indeed - https://pageviews.wmcloud.org/?project=en.wikipedia.org&platform=all-access&agent=user&redirects=0&range=latest-90&pages=Template_talk:Infobox_Australian_place

the editors who have very specifically dealt with the issues relating to the mechanics of the internals of some aspects that you touched upon are no-where to be seen, a serious health warning should be given, without adequate breathing assistance, you're cactus JarrahTree 23:55, 16 October 2024 (UTC)

Umm, not quite cactus. As it happens I've been working on changes to Module:PopulationFromWikidata for some time now, including an option to get a single, specific-ABS-geography population figure when required. My ducks are not all in the required row yet (ie: I haven't finished my own testing), but should be within the week, when I'll be able to provide a link to a new version to try out. It should solve @SCHolar44's problem. Innesw (talk) 04:12, 17 October 2024 (UTC)

The problem with discussion here is the very low apparent watchers, and I was facilitating humour towards the editors whom I have met in real life - 99of9, and Canley - who have worked in the area, as well as the WMAU funded project to facilitate the change of the other year. That aside, as it is a community wide issue (Oz) and not just any particular individual's problem. The requirement of a lua/wikidata/ABS literate person(s) is something that the average editor would not even begin to comprehend, whether the packaging, let alone the contents... So good to see some quacking, however muted or distant in time or space.JarrahTree 04:26, 17 October 2024 (UTC)

Actually this conversation should be noted at or moved to the scene of the issue so to speak - https://en.wikipedia.org/wiki/Module_talk:PopulationFromWikidata JarrahTree 04:31, 17 October 2024 (UTC)

Thank you for letting me know, Innesw. :-) Having just unbated my breath (thanks, JarrahTree), I will bate again! My main doubt concerns whether the "town only" population can be extracted from the Wikidata on its own, just as the "town+area" can. We'll see ... Cheers, Simon – SCHolar44 🇦🇺 💬 at 07:06, 17 October 2024 (UTC)

In short, yes the "town-only" and "town+area" pops could be extracted on their own. It's just that the current version of Module:PopulationFromWikidata doesn't allow you to do it with the control you require. (Making it available could be a while away yet - don't hold your bated breath too long, you'll turn blue!) Innesw (talk) 11:26, 17 October 2024 (UTC)

One thing to consider in all of this is whether it is currently acceptable to call Wikidata from within article prose. Infoboxes are OK, as long as the data is reliably sourced, but at Wikipedia:Wikidata#Appropriate usage in articles, the most recent RFC on Wikidata in article prose appears to date from 2013(!), and it forbids using Wikidata information in article prose. There may be a later RFC that is not linked, or I may not be reading the Wikipedia:Wikidata page thoroughly enough. – Jonesey95 (talk) 17:18, 17 October 2024 (UTC)

Thanks @Jonesey95, I wasn't aware of that RfC, and (after some research, but I, like you, would stand corrected) it seems you're right, it doesn't appear that any of the later discussions have re-addressed (let alone changed the consensus on) the WD-data-in-article-text issue. I have two responses:

• the wiki-lawyer in me thinks "the current consensus is against it, we should not be facilitating editors doing it"
• the pragmatist thinks "we have a series of reasons why that doesn't make sense in this case":
  • that RfC was during the infancy of WD, things have changed
  • the WD data we are using is (almost certainly) already in the infobox, what's the problem with re-stating it in the text?
  • that data is pretty unimpeachable - ABS is source, fully referenced, exact land unit and point-in-time it applies to is known
  • it's only a number, not subject to the problems raised in some of the later discussions (like changing the classification of a book as/not-as a novel in a contentious case)
  • the whole point of the module - supported by WMAU - was to ensure quoted population figures were automatically up-to-date, so editors did not have to work through lots of articles to update them after each census. The project also did seem to envisage in-text use at the time.

Innesw (talk) 12:05, 18 October 2024 (UTC)

I had all of the same thoughts. I won't stop you; I just wanted to ensure that you were all being thoughtful about this process. – Jonesey95 (talk) 12:54, 18 October 2024 (UTC)

Very well put, both of you! It is always such a relief to see sensible discussion, as for 2013, that is a very long and very disassociated location in time from this point - a day in the life of wikipedia is long enough... JarrahTree 00:32, 19 October 2024 (UTC)

I love it. Data should come from Wikidata where possible, and not just population data but also geographic coordinates, official URLs and names, student and staff numbers over time, financial information, and so on. For many reasons, including consistency across Wikipedia languages.

However, it has to be easy to get correct, and it has to comply with the MOS, so in this case it has to render as “... of 231.^[1]” Note the [1] after punctuation and absence of “(SAL 2021)”. Bib of Bob (talk) 03:08, 19 October 2024 (UTC)

Here is another option: I discounted this solution earlier, but here is another way to source the latest population data from Wikidata, using Template:Wikidata:

At the most recent Australian census, Pingrup had a population of 264.

As shown above, it can place the punctuation in the right place. The reason I didn't suggest it earlier was that it sources the first available data, not the latest one, in this case, 2016, not 2021. I suspect, to make this work, the rank of the older values has to be changed on Wikidata. If so, when the next Census comes around, the rank for every 2021 value has to be changed, quite a bit of work. Unless there is another work around. Calistemon (talk) 06:00, 19 October 2024 (UTC)

I gave it a go at another item. To display the current value, the current value has to be set to Preferred rank on Wikidata. It doesn't seem to like the way the reference is formatted on Wikidata, the citation template doesn't seem to be able to handle the "Australian Statistical Geography 2021 ID". Not a winner, I fear! Calistemon (talk) 06:27, 19 October 2024 (UTC)

I will take this as my cue to show what my revised version of the module can do in this respect. I was going to ask about the formatting of in-text values, and currently it does not take into account Bib of Bob's suggestions.

Mallala is a town in South Australia. It has a population of 887 (UCL 2021). The surrounding whole locality has a population of 1,042 (SAL 2021).

• There is no dependance here on Wikidata Preferred rank or order - it's the latest data by year
• I'm quite happy to remove the abbreviations (UCL/SAL etc.), particularly as the expansions appear in the reference anyway, but I wonder if it's worth keeping the year
• I can add a |punc= to put the '.' (or whatever is specified) before the reference number
• note that the geography for which the population is returned needs to be specified, in the examples |geog=ucl and |geog=sal
• the function called is currently SinglePopulation, but I wonder if LatestPopulation would be better
• eventually a template {{Single/LatestPopulationFromWikidata}} could be put in place, rather than require editors to bother with #invoke

Innesw (talk) 23:37, 19 October 2024 (UTC)

I have now renamed the function SinglePopulation to LatestPopulation, and added:

• |year=, which if set to 'yes' will show the year after the population figure. The default is not to show the year.
• |punc=, which will put the value of the parameter between the rest of the output and the reference number. Usually this would be |punc=..

The first case in the following example shows |year= in use, the second shows |punc= in use.

Mallala is a town in South Australia. It has a population of 887 (2021). The whole locality has a population of 1,042.

Innesw (talk) 09:49, 22 October 2024 (UTC)

Can we set this up so we can create our own templates and draw on the components we want? QLD articles are very consistent in their format so to introduce a different format would look awful.

But before we do anything, can we get a lot of other problems fixed. There are many problems with drawing the data from Wikidata as I have seen in QLD data. So many, that I no longer use Wikidata. For example it provides a numeric value cited against the quickststats website, BUT the webpage says "no or low popularion" not the number. Which fails verification!!! Kerry (talk) 09:40, 30 October 2024 (UTC)

Kerry, taking your issues in reverse order:

• the discrepancy between values in Wikidata and Quickstats is a known issue (see here, the bottom item in that section), but it's not something we at WP can really fix. The census data in Wikidata is from the ABS datapacks, and has actual numbers for the low-population places, but there is no way of providing a reference into the datapacks. The ABS Quickstats say "no or low population" for the same places, but Quickstats is the only place a reference can be made to, and (as far as I know) there is no way to query the Quickstats values electronically so they could be uploaded to Wikidata. The discrepancy really needs to be taken up with the ABS, and hopefully fixed for the 2026 census.
• there are other issues with Module:PopulationFromWikidata, and most of them I believe I have fixed in this rework of the module. The original was really only written with output for the infobox in mind, the rework also formats output for in-text population figures, as per above example for Mallala. Is there anything else you require in that regard?
• once the re-worked module is properly tested and consensus-approved, and becomes the active version, then yes new templates could be written to get the data with whatever components are reqested. Innesw (talk) 03:50, 1 November 2024 (UTC)

I'm familiar with the data pack. I used the data pack myself for doing the census data for Queensland, but for any place with a low population, I always cross-checked with quickstats and put "no or low" if that it is what quickstats said. That way, I could cite quickstats, because it would always verify the census data I'd added. However, if that's not the case, then the fundamental rule of "cite it where you saw it" must apply and the data pack must be cited. Otherwise it fails verification. However, citing the data pack isn't very reader-friendly so can we automate it to do a cross-check as I did. I automated most of my roll-out using AutoWikiBrowser but it would flag to me if it was a low enough population to be potentially different on quickstats and I manually corrected those, which was a little tedious, but means I can cite quickstats AND be verifiable. I had a talk with someone from the ABS about this a while back to get a sense of when "no or low" is used (as it is clearly not a simple "under/over" a threshold value). The guy said that generally any population under 100 for a reportable area would be reviewed by an experienced statistician to determine the re-identification risk (which is where people reading the census data, particularly people from that area, can work out information about other people in their area, which should not occur due to the privacy we are promised). That would be used to decide what detailed information was suppressed through to suppressing all information (which I guess produces "no or low"). So if we make the low values from the data pack through Wikipedia, then we are contributing to re-identification risk. Having said that, I find the ABS idea that publishing the low-value data in one form (quickstats) is risky but publishing the same data in a data pack is somehow safe confusing (surely if there is a risk, you don't publish it in any form?). But, given the ABS thought there was a risk in disclosing the datapack values, I was not willing to put low values from the data pack onto Wikipedia (I feel we need act responsibly and I think this should extend to Wikidata too). My observation is "no or low" tends to kick in at populations under 30, but, it evidently depends on other factors. Having now seen a lot of cases (when doing the QLD census roll-out), my sense is that the number of households is a major influence. Many households with an overall low population seem to be considered not a risk (the actual value was shown) but the same low population in fewer households produced "no or low". Now, with the benefit of hindsight perhaps I should have webscraped quickstats as part of the AWB process to automate that, but, by the time I thought about it, I was well into the task and decided to continue with the manual inspection of low population places (and fix as appropriate, which was basically just some pastes of "no or low population" to replace the value from the datapack which occurred in 3 places: infobox, lede, and Demographics section). If I was starting over, I would look at automating the check. So, could we do the same thing with the module, double-check against quickstats and return "low or no" as appropriate. Then citing quickstats becomes verifiable where the current strategy is not verifiable (fundamental pillar of Wikipedia). It would not be a bad idea to include a double-check that it is the right place name (e.g. using LGA). For example, Happy Valley on Fraser Island (as it called in the 2021 census) is not a census district but the module cheerfully supplies the population for Happy Valley in Mount Isa. Now I spotted that one (I think I could fix it in Wikidata). But there is a lot of stuff that can go wrong with census data and I think we do have to act responsibly. We know that places with the same population in different censuses get their citations mixed-up using the module and various other errors. I don't know if there are things you have looked at in the revision you mention, but, having reported this all at length and getting no action on fixing anything, I decided to do the whole of QLD manually. I'd rather not have to do that again so I would really like us to get the Wikidata and Wikipedia to match quickstats, which I suspect we can do by combining the data pack with webscraping for low-value populations, even if we do have to produce a list of "not sure, please do it manually" if we detect circumstances that suggest corner cases. Kerry (talk) 06:24, 1 November 2024 (UTC)

As far as I can tell the module can't query quickstats to catch a "no or low" value there: a module in WP cannot access external web data, I assume because it could then put that (unverified) data straight into article text. (Somebody correct me if I'm wrong here.) Therefore the module has no choice but to trust wikidata.

That leaves (a) getting the ABS to publish consistent data - what's the chances?, and (b) running through the datapacks to identify suspicious cases, checking quickstats, and fixing the wikidata. (Done carefully it could be fully automated, but the quickstats check will be data-intensive, what with its maps and everything.) Another problem is that wikidata population (P1082) is supposed to be constrained to a numeric quantity >= zero - "no or low" (or any string) isn't a valid value. I think, in the event of "no or low", we should probably set the population number to zero, and add a flag to the population claim. The module could then catch that flag and output appropriate text. (access restriction status (P7228)='fully restricted access' may be appropriate here, but I'm not sure of that. We may have to create a wikidata property for the purpose.)

I wasn't aware of the 'places with the same population in different censuses get their citations mixed-up using the module' issue. Can you point me to more detail? Ditto the 'various other errors' - if they are issues with the module, they may already be dealt with in the revision. Innesw (talk) 20:48, 3 November 2024 (UTC)

It was discussed earlier in this Talk page, now at Template talk:Infobox Australian place/Archive 9#Strange census behaviour on Gootchie, Queensland Kerry (talk) 09:12, 8 November 2024 (UTC)

In fact I had read that, but dismissed it as a wikidata issue. It's been fixed in Gootchie (Q55453404), I presume manually, but it still exists in Banksiadale (Q4856763) - which at this stage is good, because it will allow me to test dealing with it. It will be possible for the module to identify that there are two point in time (P585) qualifiers in the claim, find the latest one, and return with the correct reference. Working on it ... Innesw (talk) 00:12, 10 November 2024 (UTC)

Another issue that came up was density which does not appear infoboxes using the module. We can't put "no or low" into the infobox population field as it expects a number so I have been forced to put 0, so we need to allow that field to not have a number (and not attempt to calculate a density unless it is a number). Kerry (talk) 09:16, 8 November 2024 (UTC)

Along with my revision of Module:PopulationFromWikidata, I've also revised Template:Infobox_Australian_place (first stage revision here), which catches non-numeric |pop= or |area= and does not output a calculated density. But a calculated density will only work if both pop and area are entered manually into the infobox. If |pop= is blank, so the population uses the Wikidata module, density needs to be suppressed completely. The problem is that we have no idea whether the land unit the area (either in |area= in the infobox, or maybe one in wikidata) is for is the same as that for the population figure - therefore any calculated density could be wildly innacurate. Innesw (talk) 00:12, 10 November 2024 (UTC)