From a3d876e3764b6aa25d0d42ac452acc55a999b746 Mon Sep 17 00:00:00 2001 From: Thomas Voss Date: Mon, 11 Sep 2023 07:25:03 +0200 Subject: Remove backup files --- src/prj/mmv/index.gsp.bak | 645 ---------------------------------------------- 1 file changed, 645 deletions(-) delete mode 100644 src/prj/mmv/index.gsp.bak (limited to 'src/prj/mmv') diff --git a/src/prj/mmv/index.gsp.bak b/src/prj/mmv/index.gsp.bak deleted file mode 100644 index 3c2fd97..0000000 --- a/src/prj/mmv/index.gsp.bak +++ /dev/null @@ -1,645 +0,0 @@ -html lang="en" { - head { m4_include(head.gsp) } - body { - header { - div { - h1 {-Moving Files the Right Way} - m4_include(nav.gsp) - } - - figure .quote { - blockquote { - p {= - I think the OpenBSD crowd is a bunch of masturbating monkeys, in - that they make such a big deal about concentrating on security to - the point where they pretty much admit that nothing else matters to - them. - } - } - figcaption {-Linus Torvalds} - } - } - - main { - p { - em {- - You can find the @code{-mmv} git repository over at - @a - href="https://git.sr.ht/~mango/mmv" - target="_blank" - {-sourcehut} - or - @a - href="https://github.com/Mango0x45/mmv" - target="_blank" - {-GitHub}. - } - } - - p {- - NOTE: As of the - @a href="https://git.sr.ht/~mango/mmv/refs/v1.2.0" {-v1.2.0} - release there is now also the @code{-mcp} utility. It behaves the same - as the @code{-mmv} utility but it copies files instead of moving them. - It also doesn’t support the ‘@code{--n}’ flag as it doesn’t need to deal - with backups. - } - - h2 {-Table of Contents} - - ul { - li {a href="#prologue" {-Prologue}} - li {a href="#moving" {-Advanced Moving and Pitfalls}} - li {a href="#mapping" {-Name Mapping with @code{-mmv}}} - li {a href="#newlines" {-Filenames with Embedded Newlines}} - ul { - li {a href="0-flag" {-The Simple Case}} - li {a href="#e-flag" {-Encoding Newlines}} - } - li {a href="#i-flag" {-Individual Execution}} - li {a href="#safety" {-Safety}} - li {a href="#examples" {-Examples}} - } - - h2 #prologue {-Prologue} - p {- - File moving and renaming is one of the most common tasks we undertake on - the command-line. We basically always do this with the @code{-mv} - utility, and it gets the job done most of the time. Want to rename one - file? Use @code{-mv}! Want to move a bunch of files into a directory? - Use @code{-mv}! How could mv ever go wrong? Well I’m glad you asked! - } - - h2 #moving {-Advanced Moving and Pitfalls} - p {- - Let’s start off nice and simple. You just inherited a C project that - uses the sacrilegious - @a - href="https://en.wikipedia.org/wiki/Camel_case" - target="_blank" - {-camelCase} - naming convention for its files: - } - - figure { - pre { m4_fmt_code(ls-files.sh.gsp) } - } - - p {- - This deeply upsets you, as it upsets me. So you decide you want to - switch all these files to use - @a - href="https://en.wikipedia.org/wiki/Snake_case" - target="_blank" - {-snake_case}, - like a normal person. Well how would you do this? You use @code{-mv}! - This is what you might end up doing: - } - - figure { - pre { m4_fmt_code(manual-mv.sh.gsp) } - } - - p {- - Well… it works I guess, but it’s a pretty shitty way of renaming these - files. Luckily we only had 5, but what if this was a much larger - project with many more files to rename? Things would get tedious. So - instead we can use a pipeline for this: - } - - figure { - pre { m4_fmt_code(camel-to-snake-naïve.sh.gsp) } - } - - aside { - p {- - The given example assumes your @code{-sed} implementation supports - ‘@code{-\\L}’ which is a non-standard m4_abbr(GNU) extension. - } - } - - p {- - That works and it gets the job done, but it’s not really ideal is - it? There are a couple of issues with this. - } - - ol { - li { - p {- - You’re writing more complicated code. This has the obvious drawback - of potentially being more error-prone, but also risks taking more - time to write than you’d like as you might have forgotten if - @code{-xargs} actually has an ‘@code{--L}’ option or not (which - would require reading the - @a - href="https://www.man7.org/linux/man-pages/man1/xargs.1.html" - target="_blank" - { - code {-xargs(1)} - } - manual). - } - } - li { - p {- - If you try to rename the file @em{-foo} to @em{-bar} but @em{-bar} - already exists, you end up deleting a file you may not have wanted - to. - } - } - li { - p {- - In a similar vein to the previous point, you need to be very careful - about schemes like renaming the file @em{-a} to @em{-b} and @em{-b} - to @em{-c}. You run the risk of turning @em{-a} into @em{-c} and - losing the file @em{-b} entirely. - } - } - li { - p {- - Moving symbolic links is its own whole can of worms. If a symlink - points to a relative location then you need to make sure you keep - pointing to the right place. If the symlink is absolute however - then you can leave it untouched. But what if the symlink points to - a file that you’re moving as part of your batch move operation? Now - you need to handle that too. - } - } - } - - h2 #mapping {-Name Mapping with @code{-mmv}} - - p {- - What is @code{-mmv}? It’s the solution to all your problems, that’s - what it is! @code{-mmv} takes as its argument(s) a utility and that - utilities arguments and uses that to create a mapping between old and - new filenames — similar to the @code{-map()} function found in many - programming languages. I think to best convey how the tool functions, I - should provide an example. Let’s try to do the same thing we did - previously where we tried to turn camelCase files to snake_case, but - using @code{-mmv}: - } - - figure { - pre { m4_fmt_code(camel-to-snake-smart.sh.gsp) } - } - - p {-Let me break down how this works.} - - p {- - @code{-mmv} starts by reading a series of filenames separated by - newlines from the standard input. Yes, sometimes filenames have - newlines in them and yes there is a way to handle them but I shall get - to that later. The filenames that @code{-mmv} reads from the standard - input will be referred to as the @em{-input files}. Once all the input - files have been read, the utility specified by the arguments is spawned; - in this case that would be @code{-sed} with the argument - @code{-'s/[A-Z]/\\L_&/g'}. The input files are then piped into - @code{-sed} the exact same way that they would have been if we ran the - above commands without @code{-mmv}, and the output of @code{-sed} then - forms what will be referred to as the @em{-output files}. Once a - complete list of output files is accumulated, each input file gets - renamed to its corresponding output file. - } - - p {- - Let’s look at a simpler example. Say we want to rename 2 files in the - current directory to use lowercase letters, we could use the following - command: - } - - figure { - pre { m4_fmt_code(mmv-tr.sh.gsp) } - } - - p {- - In the above example @code{-mmv} reads 2 lines from standard input, - those being @em{-LICENSE} and @em{-README}. Those are our 2 input files - now. The @code{-tr} utility is then spawned and the input files are - piped into it. We can simulate this in the shell: - } - - figure { - pre { m4_fmt_code(tr.sh.gsp) } - } - - p {- - As you can see above, @code{-tr} has produced 2 lines of output; these - are our 2 output files. Since we now have our 2 input files and 2 - output files, @code{-mmv} can go ahead and rename the files. In this - case it will rename @em{-LICENSE} to @em{-license} and @em{-README} to - @em{-readme}. For some examples, check the @a href="#examples" - {-examples} section of this page down below. - } - - h2 #newlines {-Filenames with Embedded Newlines} - - p {- - People are retarded, and as a result we have filenames with newlines in - them. All it would have taken to solve this issue for everyone was for - literally @strong{-anybody} during the early UNIX days to go “@em{-hey, - this is a bad idea!}”, but alas, we must deal with this. Newlines are - of course not the only special characters filenames can contain, but - they are the single most infuriating to deal with; the UNIX utilities - all being line-oriented really doesn’t work well with these files. - } - - p {- - So how does @code{-mmv} deal with special characters, and newlines in - particular? Well it does so by providing the user with the @code{--0} - and @code{--e} flags: - } - - dl { - dt { code{--0} } - dd { - p {- - Tell @code{-mmv} to expect its input to not be separated by newlines - (‘@code{-\\n}’), but by NUL bytes (‘@code{-\\0}’). NUL bytes are - the only characters not allowed in filenames besides forward - slashes, so they are an obvious choice for an alternative separator. - } - } - dt { code{--e} } - dd { - p {- - Encode newlines in filenames before passing them to the provided - utility. Newline characters are replaced by the literal string - ‘@code{-\\n}’ and backslashes by the literal string ‘@code{-\\\\}’. - After processing, the resulting output is decoded again. - } - p {- - If combined with the @code{--0} flag, then while input will be read - assuming a NUL-byte input-seperator, the encoded input files will be - written to the spawned process newline-seperated. - } - } - } - - h3 id="0-flag" {-The Simple Case} - - p {- - In order to better understand these flags and how they work let’s go - though another example. We have 2 files — one with and one without an - embedded newline — and our goal is to simply reverse these filenames. - In this example I am going to be displaying newlines in filenames with - the “@code{-$'\\n'}” syntax as this is how my shell displays embedded - newlines. - } - - p {- - We can start by just trying to naïvely pass these 2 files to @code{-mmv} - and use @code{-rev} to reverse the names, but this doesn’t work: - } - - figure { - pre { m4_fmt_code(mmv-rev.sh.gsp) } - } - - p {- - The reason this doesn’t work is because due to the line-oriented nature - of @code{-ls} and @code{-rev}, we are actually trying to rename the - files @em{-foo}, @em{-bar}, and @em{-baz} to the new filenames - @em{-zab}, @em{-rab}, and @em{-oof}. As can be seen in the following - diagram, the embedded newline is causing our input to be ambiguous and - @code{-mmv} can’t reliably proceed anymore @x-ref{-1}: - } - - figure { - object data="conflict.svg" type="image/svg+xml" {-} - } - - aside { - p data-ref="1" {- - The reason you get a cryptic “file not found” error message is because - @code{-mmv} tries to assert that all the input files actually exist - before doing anything. Since “foo” isn’t a real file, we error out. - } - } - - p {- - The first thing we need to do in order to proceed is to pass the - @code{--0} flag to @code{-mmv}. This will tell @code{-mmv} that we want - to use the NUL-byte as our input separator and not the newline. We also - need @code{-ls} to actually provide us with the filenames delimited by - NUL-bytes. Luckily m4_abbr(GNU) @code{-ls} gives us the @code{---zero} - flag to do just that: - } - - figure { - pre { m4_fmt_code(mmv-rev-zero.sh.gsp) } - } - - p {- - So we’re getting places, but we aren’t quite there yet. The issue we’re - getting now is that @code{-mmv} recieved 2 input files from the standard - input, but @code{-rev} produced 3 output files. Why is that? Well - let’s try our hand at a little bit of command-line debugging with - @code{-sed}: - } - - figure { - pre { m4_fmt_code(sed-debugging.sh.gsp) } - } - - p {- - If you aren’t quite sure what the above is doing, here’s a quick - summary: - } - - ul { - li {- - The @code{--U} flag given to @code{-ls} tells it not to sort our - output. This is purely just to keep this example clear to the reader. - } - li {- - The @code{--n} flag given to @code{-sed} tells it not to print the - input line automatically at the end of the provided script. - } - li {- - The @code{-l} command in @code{-sed} prints the current input in a - “visually unambiguous form”. - } - } - - p {- - In the @code{-sed} output, we can see that @samp{-$} represents the end - of a line, and @samp{-\\000} represents the NUL-byte. All looks good - here, we have two inputs seperated by NUL-bytes. Now let’s try to throw - in @code{-rev}: - } - - figure { - pre { m4_fmt_code(sed-debugging-rev.sh.gsp) } - } - - p {- - Well wouldn’t you know it? Since @code{-rev} @em{-also} works with - newline-seperated input, it reversed out NUL-byte seperators and now - gives us 3 outputs. Luckily the folks over at @em{-util-linux} provided - us with the @code{--0} flag here too, so that we can properly handle - NUL-delimited input. Combining all of this together we get a final - working product: - } - - figure { - pre { m4_fmt_code(reverse-embedded-newline.sh.gsp) } - } - - h3 #e-flag {-Encoding Newlines} - - p {- - Sometimes we want to rename a bunch of files, but the command we want to - use doesn’t support NUL-bytes as nicely as we would like. In these - cases, you may want to consider encoding your newline characters into - the literal string ‘@code{-\\n}’ and then passing your input - newline-seperated to your given command with the @code{--e} flag. - } - - p {- - For a real-world example, perhaps you want to edit some filenames in - vim, or whatever other editor you use. Well we can do this incredibly - easily with the @code{-vipe} utility from the - @a href="https://joeyh.name/code/moreutils/" {-moreutils} - collection. The @code{-vipe} command simply reads input from the - standard input, opens it up in your editor, and then prints the - resulting output to the standard output; perfect for @code{-mmv}! We do - not really want to deal with NUL-bytes in our text-editor though, so - let’s just encode our newlines: - } - - figure { - pre { m4_fmt_code(vipe.sh.gsp) } - } - - aside { - p {- - Notice how you still need to pass the @code{--0} flag to @code{-mmv} - know that our inputfiles may have embedded newlines. - } - } - - p {- - When running the above code example, you will see the following in your - editor: - } - - figure { - pre { m4_fmt_code(vim.gsp) } - } - - p {- - After you exit your editor, @code{-mmv} will decode all occurances of - ‘@code{-\\n}’ back into a newline, and all occurances of ‘@code{-\\\\}’ - back into a backslash: - } - - figure { - object data="e-flag.svg" type="image/svg+xml" {-} - } - - h2 #i-flag {-Individual Execution} - p {- - The previous examples are great and all, but what do you do if your - mapping command doesn’t have the concept of an input seperator at all? - This is where the @code{--i} flag comes into play. With the @code{--i} - flag we can get @code{-mmv} to execute our mapping command for every - input filename. This means that as long as we can work with a complete - buffer, we don’t need to worry about seperators. - } - - p {- - To be honest, I cannot really think of any situation where you might - actually need to do this. If you can think of one, please @a - href="mailto:mail@thomasvoss.com" {-email me} and I’ll update the - example on this page. Regardless, let’s imagine that we wanted to - rename some files so that their filenames are replaced with their - filename - @a - href="https://en.wikipedia.org/wiki/SHA-1" - target="_blank" - {-m4_abbr(SHA)-1 hash}. - On Linux we have the @code{-sha1sum} program which reads input from the - standard input and outputs the m4_abbr(SHA)-1 hash. This is how we - would use it with @code{-mmv}: - } - - figure { - pre { m4_fmt_code(sha1sum-long-example.sh.gsp) } - } - - p {- - Another approach is to invoke @code{-mmv} twice: - } - - figure { - pre { m4_fmt_code(sha1sum-short-example.sh.gsp) } - } - - p {- - If you are confused about why we need to make a call to @code{-awk}, - it’s because the @code{-sha1sum} program outputs 2 columns of data. The - first column is our hash and the second column is the filename where the - to-be-hashed data was read from. We don’t want the second column. - } - - p {- - Unlike in previous examples where one process was spawned to map all our - filenames, with the @code{--i} flag we are spawning a new instance for - each filename. If you struggle to visualize this, perhaps the following - diagrams help: - } - - figure { - figcaption {-Invoking @code{-mmv} without @code{--i}} - object data="without-i-flag.svg" type="image/svg+xml" {-} - } - - figure { - figcaption {-Invoking @code{-mmv} with @code{--i}} - object data="with-i-flag.svg" type="image/svg+xml" {-} - } - - h2 #safety {-Safety} - p {- - When compared to the standard @code{-for f in *; do mv $f …; done} or - @code{-ls | … | xargs -L2 mv} constructs, @code{-mmv} is significantly - more safe to use. These are some of the safety features that are built - into the tool: - } - - ol { - li {- - If the number of input- and output files differs, execution is aborted - before making any changes. - } - li {- - If an input file is renamed to the name of another input file, the - second input file is not lost (i.e. you can rename @em{-a} to @em{-b} - and @em{-b} to @em{-a} with no problem). - } - li {- - All input files must be unique and all output files must be unique. - Otherwise execution is aborted before making any changes. - } - li {- - In the case that something goes wrong during execution (perhaps you - tried to move a file to a non-existant directory, or a syscall - failed), a backup of your input files is saved automatically by - @code{-mmv} for recovery. - } - } - - p {- - Due to the way @code{-mmv} handles #2, when things do go wrong you may - find that all of your input files have disappeared. Don’t worry though, - @code{-mmv} takes a backup of your code before doing anything. If you - run @code{-mmv} with the @code{--v} option for verbose output, you’ll - notice it backing up your stuff in the @code{-$XDG_CACHE_DIR} directory: - } - - figure { - pre { m4_fmt_code(mmv-verbose.sh.gsp) } - } - - p {- - Upon successful execution the @code{-$XDG_CACHE_DIR/mmv/TIMESTAMP} - directory will be automatically removed, but it remains when things go - wrong so that you can recover any missing data. The names of the - backup-subdirectories in the @code{-$XDG_CACHE_DIR/mmv} directory are - timestamps of when the directories were created. This should make it - easier for you to figure out which directory you need to recover if you - happen to have multiple of these. - } - - h2 #examples {-Examples} - - aside { - p {- - All of these examples are ripped straight from the @code{-mmv(1)} - manual page. If you installed @code{-mmv} through a package manager or - via @code{-make install} then you should have the manual installed on - your system. - } - } - - p {-Swap the files @em{-foo} and @em{-bar}:} - figure { - pre { m4_fmt_code(examples/swap.sh.gsp) } - } - - p {- - Rename all files in the current directory to use hyphens (‘-’) instead - of spaces: - } - figure { - pre { m4_fmt_code(examples/hyphens.sh.gsp) } - } - - p {- - Rename a given list of movies to use lowercase letters and hyphens - instead of uppercase letters and spaces, and number them so that they’re - properly ordered in globs (e.g. rename @em{-The Return of the King.mp4} - to @em{-02-the-return-of-the-king.mp4}): - } - figure { - pre { m4_fmt_code(examples/number.sh.gsp) } - } - - p {- - Rename files interactively in your editor while encoding newline into - the literal string ‘@code{-\\n}’, making use of - @code { - a - href="https://linux.die.net/man/1/vipe" - target="_blank" - {-vipe(1)} - } - from @em{-moreutils}: - } - figure { - pre { m4_fmt_code(examples/vipe.sh.gsp) } - } - - p {- - Rename all C source code- and header files in a git repository - to use snake_case instead of camelCase using - the m4_abbr(GNU) - @code { - a - href="https://www.man7.org/linux/man-pages/man1/sed.1.html" - target="_blank" - {-sed(1)} - } - ‘@code{-\\n}’ extension: - } - figure { - pre { m4_fmt_code(examples/camel-to-snake.sh.gsp) } - } - - p {- - Lowercase all filenames within a directory hierarchy which may contain - newline characters: - } - figure { - pre { m4_fmt_code(examples/lowercase.sh.gsp) } - } - - p {- - Map filenames which may contain newlines in the current directory with - the command ‘@code{-cmd}’, which itself does not support nul-byte - separated entries. This only works assuming your mapping doesn’t - require any context outside of the given input filename (for example, - you would not be able to number your files as this requires knowledge of - the input files position in the input list): - } - figure { - pre { m4_fmt_code(examples/i-flag.sh.gsp) } - } - } - - hr{} - - footer { m4_footer } - } -} -- cgit v1.2.3