Computing desk
< November 16	<< Oct \| November \| Dec >>	November 18 >

Welcome to the Wikipedia Computing Reference Desk Archives
The page you are currently viewing is an archive page. While you can leave answers for any questions shown below, please ask new questions on one of the current reference desk pages.

November 17

Laptop

Whenever I close my laptop, the computer will do the same thing that happens when hitting the "print screen" button, namely copy an image of the screen to the clipboard. Does this also happen on your laptop? GeoffreyT2000 (talk) 02:28, 17 November 2015 (UTC)[reply]

no. Vespine (talk) 02:33, 17 November 2015 (UTC)[reply]

Could be something physically hitting the Print Screen button. StuRat (talk) 06:14, 17 November 2015 (UTC)[reply]

Laptops usually have a setting for what to do when the laptop is closed, such as "turn off the screen" or "log off". It is possible someone changed that to "print screen" just to be annoying. 209.149.115.177 (talk) 14:52, 17 November 2015 (UTC)[reply]

@GeoffreyT2000 and 209.149.115.177: That may be possible, but might require a registry 'hack'. My Win 7 Toshiba laptop only gives the selections of: Do nothing, Hibernate, Sleep and Shutdown. No user selectables, though it may be there in BIOS. 220 of ^Borg 08:18, 20 November 2015 (UTC)[reply]

Detecting that a folder contains unreachable files or folders due to deep nesting

Windows has a limit of 255 characters imits for path names according to [1]. It's fairly easy when copying or renaming folders, to get in a situation where some of your data is unreachable by ordinary means because this limit has been exceeded. The previously quoted source says robocopy can bypass this limitation. Another trick is to use the subst command from a windows shell to create an alias for a reachable folder with unreachable sub-folders, and access the nested material using the alias.

My question: Is it possible to test beforehand whether a folder contains sub-folders or files with names that exceed the name length? I ask because I would like to avoid starting time-consuming tasks that are bound to fail and possibly mess things up (zip + move). --NorwegianBlue^talk 13:08, 17 November 2015 (UTC)[reply]

Best bet would be writing a Python or PowerShell (or whatever language you're comfortable with) script to recurse through all the folders in a tree and keep track of the max path length as you go. This thread has a Visual Basic (ugh) script for doing this.

The other option is to move the files elsewhere before you begin said task, to shorten the length of the paths; depending on what you're doing this for, though, that may not be possible. FrameDrag (talk) 14:42, 17 November 2015 (UTC)[reply]

The claim that Windows limits path names to 255 characters is not correct or authoritative. Microsoft's documentation, Naming Files, Paths, and Namespaces, explains that maximum path length is file-system-dependent. Certain programmatic functions in the Windows API are limited to use strings of length MAX_PATH, which is 260 characters; but most built-in utilities (including Explorer and the command prompt) are able to use extended path names, with lengths of about 32,000 characters. This has been true of all Windows operating systems for about 20 years - including Windows NT, Windows 95, and Windows CE - so unless you're using a very old system like Windows 3.1, or Windows for Workgroups, or some other ancient software, you do not need to limit path names based on the MAX_PATH limitation. When you write C or C++ code to the Windows API, if you choose to use legacy path functions, you need to be aware of these limits; but you can always use newer APIs to access the file system. If you aren't writing C or C++, (or otherwise directly linking the Windows API), you should probably ignore the "260 character" limit completely, because it doesn't apply. The shell and the individual file system may have different limitations, but this MAX_PATH is not one of them.

Nimur (talk) 16:23, 17 November 2015 (UTC)[reply]

You've misunderstood the documentation. Almost all Windows programs are limited to 260-character paths (259 + trailing NUL), including .NET programs, and there's no sign of that changing in the future. -- BenRG (talk) 18:27, 17 November 2015 (UTC)[reply]

"The Windows API has many functions that also have Unicode versions to permit an extended-length path for a maximum total path length of 32,767 characters." Maximum Path Length Limitation. I think you are conflating two different limitations: limits that are intentionally imposed by specific programs, and limits that are enforced by the operating system itself. Nimur (talk) 20:51, 17 November 2015 (UTC)[reply]

Maybe you misunderstood the quoted sentence to mean that any program that uses the Unicode API supports long paths. That's not the case. Long paths are only supported in a \\?\ prefixed form which doesn't follow the usual Win32 rules (for example the . and .. pseudo-directories aren't supported). Some software will work if you pass it a \\?\ path and it doesn't inspect it too closely, but software that understands and reliably supports long paths is rare. It is indeed a limit of "specific programs", not the kernel, but the "specific programs" include almost every program that has ever been written for 32-bit or 64-bit Windows.

(Cygwin 1.7+ is a notable exception; you can probably safely use long paths in a pure Cygwin environment.) -- BenRG (talk) 00:06, 18 November 2015 (UTC)[reply]

I'm not exactly sure where you got that by reading that MSDN page, I got a completely different read out of it. It says that normal X:\ path names are limited to 260 characters (X:\ + path + NUL terminator), and that \\?\ path names are (probably) limited to the file system limit. It also says that the filesystem itself and the shell are separate, and that it's possible to create perfectly valid things that the shell can't interpret correctly. It's also worth noting that the question wasn't about the char limit... FrameDrag (talk) 20:21, 17 November 2015 (UTC)[reply]

Thanks for your replies! I did some experimenting based on the assumption that Nimur's assertion was correct, before reading the discussion. Here's what I found:

It was possible to create and traverse hierarchies that are deeper than 260 characters with explorer (Windows 7). I created the hierarchy by unzipping a deep hierarchy twice (i.e. nested within itself).
However, there was some weirdness when I crossed the 260 character limit. For one thing, when I tried to text-copy (ctr-C) a folder name presented in the explorer address bar, it changed to old DOS 8-character long-name represesentation when I clicked the address bar, thus preserving a path name shorter than 260 characters, like so:

T:\AD-HER~1\HENVEN~1\2012-0~2\TAKKTI~1\XYZ-TE~1\Brukere\N\nblue\MINEDO~1\MI\HENVEN~1\2012-0~2\Takk til Kristoffer, med nye versjoner\Ny mappe

The full version of the path name in this case would have had 385 characters.

When trying to create new files or folders (in a directory that was beyond the limit) by right-clicking, nothing appeared to happen. However, when I pressed F5, it turned out that the folder or file had been created with the default name, but the gui hadn't been updated.
In cmd.exe, chdir with an argument longer than the 260-character limit failed. If I went step-by-step to the deepest "legal" directory, I could show the next level with "dir", but I couldn't chdir to a directory which gave a path name longer than the limit. I could, however, access the directory via explorer and start a shell with shift-click. But then, the path name was shown as above (T:\AD-HER~1\... etc).
dir /b /s failed with an error message when it reached a folder that was nested too deeply.
When I right-clicked the root folder and selected "properties", only the files that were below the limit appeared to be counted, ditto for the disk space used.
7-zip (current stable version, which is from 2010) was able to successfully compress the entire hierarchy, preserving full-size names at each level, and to decompress it without error messages and with no obvious errors.
I also did an experiment that turned out to provide an answer to my original question. I tried to compress the folder to a zip-file using the built-in Windows mechanism (right clicking and selecting "send to compressed folder"). And voilá - an immediate error message reporting the first file name that was too long. So the question is answered, at least for Windows-7. Unfortunately, the problem that prompted the question occured on an XP machine that needs to be maintained (don't ask)....

-NorwegianBlue^talk 22:29, 17 November 2015 (UTC)[reply]

Resolved

@NorwegianBlue: - I'd be interested (as a smug Linux rubbernecker) whether the failures you got with chdir and dir in cmd.exe also happen if you run them in Powershell. I would hazard that they do not. -- Finlay McWalterᚠTalk 22:39, 17 November 2015 (UTC)[reply]

For what it's worth, TCC/LE, a freeware almost-compatible replacement for cmd.exe, appears to support long paths. PowerShell 2.0 appears not to, but it's rather old. I can't find any clear information about newer PowerShell versions online. -- BenRG (talk) 00:06, 18 November 2015 (UTC)[reply]

(Also, chdir is never going to work because the Win32 "current directory" is just a string that's prepended to partial paths by the Win32 parsing code that \\?\ bypasses. Windows just doesn't support long current directories.) -- BenRG (talk) 00:25, 18 November 2015 (UTC)[reply]

@Finlay McWalter: - As BenRG predicted, powershell 2.0 failed in a similar (and slightly worse) manner than cmd.exe did. From the most deeply nested reachable directory, cmd.exe was able to list the files and folders of the next level. Powershell, however, only echoed the name of the current directory. --NorwegianBlue^talk 07:30, 18 November 2015 (UTC)[reply]

Scanner won't open

My Epson scanner won't open when I click the icon on my computer. I can turn it on but that's it. What could be the problem?--Jeanne Boleyn (talk) 13:24, 17 November 2015 (UTC)[reply]

In technical terms, your scanner is f*cked. Try reinstalling it. If that doesn't work try installing it on a different computer. if that doesn't work, chuck it out. Vespine (talk) 21:51, 17 November 2015 (UTC)[reply]

You can always try unplugging it and plugging it in again. Rebooting the computer may overcome trouble too. Graeme Bartlett (talk) 22:36, 17 November 2015 (UTC)[reply]

Moving data from one secondary SSD to a larger one

I've just purchased a 500GB SSD and I'd like to copy the data from my 240GB SSD (drive letter D currently) to it. Normally I'd just add the drive in but I've actually run out of SATA ports on my motherboard so an upgrade will have to do. Will anything bad happen if I just plug both drives in (unplugging another one temoprarily) and just copy all the data across, then unplug the original and give the new drive the drive letter D? I have installed programs but no OS installed to the drive. 81.138.15.171 (talk) 17:03, 17 November 2015 (UTC)[reply]

Nothing bad should happen (standard disclaimers apply), but if you want to be certain a kit like this (many different ones available, search around for the one that suits you best) makes cloning a disk almost painless. WegianWarrior (talk) 18:45, 17 November 2015 (UTC)[reply]

The installed programs may not appreciate being transferred between drives because of registry issues, and you might have to reinstall them, depending on how the program identifies where it is in the registry. Won't know that until you try it, unfortunately. Also, make sure you turn off your computer before swapping the drives. SATA does support hot-swap in the specification but it depends on your SATA controller as to if it's actually supported. Drive cloning as mentioned above would be a mostly one-click process, but still might have the registry problems. Keyword in all this is 'might.' It also might go completely fine without any problems whatsoever. Obligatory make-sure-to-backup-important-data message here. FrameDrag (talk) 20:27, 17 November 2015 (UTC)[reply]

Another alternative for Windows 7 and above is to back up your existing SSD to another drive with enough free space, swap SSDs, format, and restore. Alternatively, SATA controller add-in cards are dirt cheap. I recently put this $20 card in a PC that didn't have enough sata ports and it works fine. --Guy Macon (talk) 21:40, 17 November 2015 (UTC)[reply]

Transfering the whole windows from the 240 GB to the EMPTY 500 GB SSD requeres to delete all data on the 500 GB target device. Connect the two drives to the computer. Boot a linux live CD. Use gParted to indentify the drives only. Use dd (Unix) to copy the 240 GB to the 500 GB SSD. Shutdown after complete to reload partition tables on next boot up. Booting windows, remove the 240 GB drive before! In the disk mananger, fomerly called windisk select the remaining space and the system parition by holding the CTRL-key rightclick and choose expand. Theres no reboot neccessary but you need the rights of the windows administrator. When having more custom partitions on the drive, reboot liunx, use gparted, to move and expand the partitions. When booting windows, keep the old SSD far away from the system. You might have to register your windows copy again. Note DD is a commandline tool. Aware to copy accidently the target to the source, deleting all your data! --Hans Haase (有问题吗) 11:46, 21 November 2015 (UTC)[reply]

I would just use Clonezilla. I've used it many times and have never had problems. It will copy everything from the 240 GB drive to the 500 GB drive and clear anything off the 500 GB drive for you. The drive letters will stay the same. The only thing you'll have to do after running it is expand the partition to fill up the rest of the space on the 500 GB drive in the Windows Disk Management console. You just plug both drives into your motherboard, boot from the Clonezilla ISO, and follow the prompts.—Best Dog Ever (talk) 11:58, 21 November 2015 (UTC)[reply]

Linux hard disk questions

Because of circumstances beyond my control, I no longer have the right to use the Windows drive that was in the computer my company gave me. I can keep the actual computer though, so I have physically removed the drive. Fedora 20 Linux boots up happily without it, but I still see "Windows Boot Manager" in the boot menu even though the computer is now 100% Bill-free. How do I get rid of it?

This has also given me an empty drive bay. Assuming I buy another hard drive, can I somehow have one partition, or one mount point, span both drives, part of one and the total of another, or part of one and part of another? I think I must have asked this question earlier but I have forgot the answers. JIP | Talk 18:08, 17 November 2015 (UTC)[reply]

The issue will be what boot manager you are running. If it is grub2 (F20 default), you can see the grub.conf file usually in /boot/grub2/grun.conf. It looks like a mess, but it is rather easy to find each kernel that it will load. You can delete the one you don't want. I know that there are tools to edit the grub.conf file, but I don't use them, so I cannot explain how to use them. As for spanning multiple disks, that is what LVM is used for. Again, this is default for F20. Both disks become a volume that you, the user, sees as a single drive. My suggestion is to backup all the files you really want to keep. Then, put in a second drive. Then, install the latest Fedora from disk and tell it to completely format and reuse all drive space. You'll quickly end up with a single logical volume over two disks and the boot manager will be cleaned up. 209.149.115.177 (talk) 18:37, 17 November 2015 (UTC)[reply]

I think that when I fill up my current drive, I can buy another two drives and keep the old one as a backup. I can then install the latest Fedora release on the new drives and use LVM on them. Is it possible to have LVM only use part of one drive and the whole of another? How is it controlled which files end up on which drive if they're the same logical partition? Or will the files themselves be spread out across the drives, with part of a file lying on one drive and part on another? What happens if I remove one drive? Can I still access the remaining drive's files or will the whole LVM system fail? If I migrate the drives themselves to another computer, is it enough to plug them both in somewhere? Do I have to boot the computer from the LVM drives for LVM to work or will it somehow automatically work even if I boot from a normal singular drive? JIP | Talk 19:13, 17 November 2015 (UTC)[reply]

LVM merges partitions into single logical volume. You don't really have much control over where files go (there are advanced LVM settings, but I don't play with them). So, you can partition a single drive into two partitions and only use one of those partitions in a logical volume. The cool thing about LVM is that you can remove and add partitions whenever you like. I had a disk that was reporting too many bad sectors. I removed it from the LVM (which took time, but automatically removed all data from the failing drive). Then, I added a new drive to the LVM. My file system was, from my point of view, the same (technically bigger). I also solved a problem we had using LVM. We had a JBOD with 24TB of disk space in it. We kept getting file corruption. After a hell of a lot of research, I highly suspected the size of the disks. It reported as a single 24TB partition. So, I broke it into 6 4TB partitions on the JBOD side. I didn't lose much data storage - just a very minor amount for the partition overhead. Then, on the server side, I merged the 6 partitions into a single logical volume. After a year of monthly (or more often) file corruption, we ran for the next two years without a single corrupt file. The users still saw the 24TB "disk", which was actually a volume of 6 partitions. 209.149.115.177 (talk) 19:45, 17 November 2015 (UTC)[reply]

So, as I understand it, LVM divides files between the drives but doesn't actually spread out individual files, and I don't get to choose what files go where. But I didn't really see a reply to my other questions. Is an LVM drive or partition only accessible through LVM, or can it be mounted as a standard drive or partition and whatever files there are can be accessed? Do LVM drives or partitions automatically know they're under LVM and so all I have to do is to plug them in and they're accessible through LVM? How do I actually add or remove a drive in LVM? Does a drive under LVM obey the normal file system structure or does LVM have its own file system? Is an LVM drive accessible if I don't plug in all of the drives under LVM? In particular, I want to know whether an LVM drive can be accessed without LVM, and whether installing LVM drives to a new system is as simple as just plugging the drives in. JIP | Talk 20:15, 17 November 2015 (UTC)[reply]

LVM is part of Fedora. You may already be using it. Run "sudo lvdisplay" to see what logical volumes you have. I only have one drive in my computer I'm using right now, but it has a logical volume wrapping the single user partition on that drive. The volume is what the OS sees as a "drive". You can format the volume with whatever filesystem you like. It is just a drive. All in all, it is another level of abstraction. You have the physical disk. Above that, you have partitions. Each partition is a separate "drive" even though they are all one physical disk. Volumes treat multiple partitions as single drives. To get technical, it gets down to block mapping. Block 82 of my logical volume will be mapped to, say Block 129 of one of the partitions in the volume. But, that partition is part of a physical drive. Block 129 of the partition may be block 2031 on the physical drive. You (and your files) don't know about the indirection. They just know about the volume because the filesystem resides on the volume. So, assume you are using something simple like a file allocation table based filesystem. You have a file allocated to blocks 153 to 187. Those are logical volume blocks. You don't control which partition owns those blocks or what block they are on the partition. You can do advanced settings, but I don't mess with that. As for messing with volumes, you use the lv* commands (I'm sure there's a GUI also). There is lvcreate, lvdisplay, lvextend, lvremove, lvresize -- just off the top of my head. I'm sure there are more lv commands. In the end, you won't notice you are using logical volumes until you decide to mess with the volumes. Otherwise, they are just drives built into the Fedora's file management system. 209.149.115.177 (talk) 20:49, 17 November 2015 (UTC)[reply]

I'm finally getting my head around all this. So LVM is not about actually storing the files, but about accessing them? The files get stored as normal files under normal file systems, but LVM is just there to let me access all of them via a single mount point? JIP | Talk 21:07, 17 November 2015 (UTC)[reply]

That is mostly correct. When you merge a partition into an volume, the partition will be formatted by the logical volume manager to be part of the volume. You can't take a drive out of a logical volume and slap it into another computer. It no longer is independent. It is a dedicated part of a volume. This is very similar to RAID. If a partition is part of a RAID 5 volume, you cannot take a single drive out of it and use it elsewhere. So, it is not like taking a bunch of independent drives that work fine by themselves and putting them under one mount point. It is merging the filesystem of a bunch of drives so they are dependent on one another. As such, they become a single mount point. 75.139.70.50 (talk) 23:30, 17 November 2015 (UTC)[reply]

So I have to have both drives plugged in for them to be usable. If I migrate the drives to a new system, is it enough to just plug them both in, providing the host system supports LVM, or do I have to actually boot from the LVM drives or do some magical LVM configuration first? JIP | Talk 18:40, 18 November 2015 (UTC)[reply]

A logical volume expects to have all partitions at all times. You can move it to another machine. You unmount it (obviously). Then, you mark it inactive and export it. That will make the partitions movable. Once it is on a new machine, you import the partitions, mark the logical volume active, and mount it. The pertinent commands to read up on are vgchange (to make groups active/inactive) and vgexport/vgimport. 75.139.70.50 (talk) 16:53, 19 November 2015 (UTC)[reply]

I'm fairly sure I use grub2, because it's the F20 default. I don't remember choosing any alternative boot manager. I have a /boot/grub2 directory but there is no grub.conf file there. locate grub.conf didn't find it either. JIP | Talk 19:16, 17 November 2015 (UTC)[reply]

Mine is in /boot/grub2/grub.cfg - I think I typo'd with grub.conf earlier. 209.149.115.177 (talk) 19:45, 17 November 2015 (UTC)[reply]

Mine is in /boot/efi/EFI/fedora/grub.cfg; it depends on whether your machine uses UEFI or not. --70.49.170.168 (talk) 19:50, 17 November 2015 (UTC)[reply]

I did find /boot/efi/EFI/fedora/grub.cfg, and there is a line in it for "Windows Boot Manager". But at the last moment, I chickened out from editing the file. If I make any errors, could it cause grub2 to fail and make my system unbootable, and therefore pretty much unusable? JIP | Talk 20:26, 17 November 2015 (UTC)[reply]

I don't use a GUI or special "helpers". I Googled and "grubby" appears to a tool Fedora has to alter the grub.cfg file without manually editing it. 75.139.70.50 (talk) 23:30, 17 November 2015 (UTC)[reply]

Open alternatives to Kindle

As I understand it Kindle is very snoopy and DRMy. Is there an alternative? Or can I jail-break a Kindle?
All the best: Rich Farmbrough, 20:53, 17 November 2015 (UTC).[reply]

Defective by Design's list of DRM-free ebook suppliers is here. -- Finlay McWalterᚠTalk 23:18, 17 November 2015 (UTC)[reply]

Kindle is a tablet. There are many tablets on the market that aren't locked down by Amazon. Many are cheaper than a Kindle. If you are talking about the Kindle Reader app. You can get many books in PDF form and read them with any PDF reader you like. If you are talking about Kindle books, there are programs that you can use to convert those to PDF documents. It isn't the easiest thing to do, but it exists. 75.139.70.50 (talk) 23:32, 17 November 2015 (UTC)[reply]

Try one of the Kobo eReaders. Instructions for Building The Kobo Reader Sources are here. --Guy Macon (talk) 00:07, 18 November 2015 (UTC)[reply]

Fairly sure the OP is referring to the Amazon Kindle eReader devices, which aren't tablets under most common definitions. And there aren't that many eink/epaper or eink/epaper like devices any more (well there never was but they more common than tablets at one time). There is however more than the Kindle. Kobo is the most obvious example, but there's also the Nook, a bunch of Hanvon devices and others. The Mobiread forums [2] and wiki [3] are a good source of information for such devices. There are even some with Android, but I'm not sure if it's really a good choice. Amazon does seem to be going down the route of Apple, and making it difficult for users to get full control over their devices, e.g. [4] [5].

Note however, depending on precisely which version you're looking at (including ad supported or not), where you live and whether Amazon is having one of their regular specials, you'll probably find most of these devices are at best comparable in price to Amazon devices, not cheaper.

PDF is a fairly bad format for most fiction eBooks since it's designed for fixed-layout which is unnecessary and means the book generally only works well on certain screen sizes. Likewise the ability to change font size etc (a big advantage with ebooks) is limited. PDF should only really be used for ebooks when fixed-layout is needed such as with text books, picture books, journal articles etc, although even there there are alternatives for fixed layout.

EPUB which is an ISO standard is probably the only common standard ebook format that's somewhat open and used by pretty much everyone other than Amazon. (The latest versions also support fixed-layout and may be where picture books and possibly text books will move. Although as I understand it epub 3 is very complicated format, hence why it's taken so long for even the full featured commercial rendering engine.)

However most ebooks in ePub format from commercial sources have DRM. In some countries you can legally remove this DRM if you own a licence for the book. OTOH in some countries such as the US with DMCA or similar laws with anti-circumvention clauses, you're potentially breaking the law (as in criminal matter rather than a civil matter between you and the copyright owner) if you do so for most purposes regardless of what licence you have (enabling the book to work with text to speech tools may be one exception in the US, but I'm not certain).

If you're able to remove the DRM, it's relatively easy on a computer for a number of DRM formats. This BTW includes the DRM Amazon uses in the Kindle books. Also I believe Apple FairPlay DRM (never done it myself but what I've read suggests it's possible). And perhaps the key one is Adobe Digital Editions DRM which many epub vendors including I believe Google Play, Barnes & Noble and Kobo support for transferring to other ereaders (their own devices sometimes use different DRM).

While the popular library management application Calibre refuses to official support DRM-removal in any way, there are plugins that can be added that after set-up mean you can basically just import the book like normal (not sure about Apple). Calibre BTW also has fairly good automatic conversion between ebook formats. It can even often fix ebooks which are unnecessarily PDFs (or otherwise fixed layout) although your best bet is to avoid them. (Calibre can also handle TXT, saved HTML, RTF, DOC, older formats like LIT, actually pretty much anything you're likely to encounter. Albeit with the possibility some formatting may be lost, or you may get some weird stuff on particularly poorly made sources.) So with some minor technical competence, actually dealing with DRMed ebooks isn't generally that different from non DRMed ones. And likewise you may not have to care whether your books are from Amazon or someone else, which may not match your device. (If you're in the US, this may be an advantage because from what I've read Amazon often has the cheapest ebooks, although as mentioned if you're in the US the DMCA may cause problems.)

Note that most commercially sourced PDF eBooks are DRM protected too, so it's not like getting PDFs allays DRM concerns. Also most ereaders including Amazon's do support DRM free ebooks in the formats they support for DRMed ebooks, if you get them from somewhere (be it originally like that or with the DRM removed). Obviously with Amazon their lack of support for epub means conversions may be necessary (although as mentioned is generally easy). However the Kindle devices are popular enough that MOBI and KF8 books are also very common. E.g. Humble Bundle DRM-free fiction ebooks generally provide both Mobi and EPUB, and possibly PDF [6] [7].

BTW, if you do have a tablet, there are plenty of ereader apps on both Android and Apple Store, and even Windows Store, which support proper ebook formats like epub or Mobi (probably both if they aren't vendor apps). Likewise on most laptop/desktop OSes. So there's never any real reason to use a fixed layout format like PDF for ebooks, where it isn't needed by the book.

Nil Einne (talk) 12:45, 18 November 2015 (UTC)[reply]

While there is some perception that the Kindle is closed, that's not quite true. Sure, it only supports DRMed books from Amazon. But it does understand formats like PDF (which sucks for eBooks) and mobi, which is basically the same as (one version of) Amazon's AMZ. Open source calibre (software) can convert many other formats, including EPUB, and you can put books onto the Kindle via USB, either directly (it mounts as a USB disk) or via calibre. So if you don't want to use Amazon, you can put it into Airplane mode (or just never join a WiFi network) and treat it as an unconnected device for all non-DRMed books, including most of Project Gutenberg and many many commercial ebooks. --Stephan Schulz (talk) 19:09, 20 November 2015 (UTC)[reply]