- First Steps in Terminal
- Navigating the File System
- Special Characters
- Managing Files (this post)
- Symbolic Links
We already know how to navigate and read the file system with
Now we want to actually do something to the files.
Create an Empty File
Sometimes it can be useful to quickly create an empty file. You can use the touch command to do this.
$ touch emptyfile
If you use the
touch command on a file that already exists it will update the file’s modification date and change nothing else.
macOS (and other Unix-like operation systems) sometimes uses the existence of a file in a certain directory as a flag for configuration.
For example, when a file named
.hushlogin exists at the root of a user’s home directory, the ‘Last Login: …’ message when you open a new shell (terminal window) is suppressed.
$ touch ~/.hushlogin
will create this file and subsequent new Terminal windows will not show this message. To return to showing the message, you will have to delete the file.
To delete a file use the
rm (remove) command:
$ rm document.txt
You have to use special care with the
In the Finder, deleted files are moved to the Trash, which is actually the invisible directory
~/.Trash. There the file will remain until the user chooses ‘Empty Trash’. Only then is the file removed from disk.
The command line has no such safety net.
When you delete a file (or directory) with the
rm command it is gone. You have to be especially careful with files with special characters. If a filename has a space in it, and you run the
rm command without escaping or quotes, then you will get an error or even worse, might delete the wrong file.
$ rm My Important Document.txt
Will delete the three files
Document.txt, if they exist. If they do not exist it will show errors.
Use escape sequences or quotation marks to protect from spaces and other special characters in and directory names:
$ rm 'My Important Document.txt'
Tab-completion will also protect from improperly typed or escaped file names. If the tab-completion will not work, even though you believe you have the right file or path then something went awry and you have to step back and verify your working directory and paths.
To delete the
.hushlogin file we created above, you use
$ rm ~/.hushlogin
Once the file is removed, new terminal windows will show the ’Last Login: …" message again.
You can add the
-i option to the
rm command which will ask for confirmation before actually deleting a file.
$ rm -i ~/.hushlogin remove /Users/armin/.hushlogin? y
To create a new empty directory (or folder) you use the
$ mkdir scratchspace
you can give the
mkdir command multiple arguments when you want or need to create multiple directories at once
$ mkdir folder1 folder2 folder3
When you create a nested directories, all the directories in between already have to exist:
$ mkdir LevelA $ mkdir LevelA/LevelB/LevelC mkdir: LevelA/LevelB: No such file or directory
When you need to create nested directory hierarchies like this, you can use
$ mkdir -p LevelA/LevelB/LevelC
This will create all three folders at once, if they do not already exist.
Moving and Renaming
You can move a file or directory using the
mv command. The
mv command needs two arguments: the source and the destination.
$ touch testfile $ mkdir testdir $ mv testfile testdir $ ls testdir testfile
mv command reads as ‘move the file
testfile to the directory
testdir’. To move it back to the current working directory you can use the ‘
.’ short cut.
$ mv testdir/testfile .
mv command can also rename a file:
$ mv testfile samplefile
Moving and renaming is considered the same in the shell.
Warning: When a file already exists in the destination, mv will mercilessly overwrite the destination file. There is no way to retrieve an overwritten file.
You have to take care to type the proper paths in the shell. It is a very unforgiving environment.
mv a bit safer add the
-i option which will prompt to confirm when it will overwrite a file:
Warning: when you use
mvto move between volumes, the source file will be removed after it is moved to the destination. This is different from the behavior in Finder, where the default drag action between volumes is copy.
On macOS and other operating systems it is common to denote the file type with an extension. The extension is a standard alphanumeric code separated from the rest of the file’s name by a dot or period. E.g.
bash, the filename extension is part of the filename. There is no special treatment for the extension.
On macOS, however, Finder usually hides the file extension from the user. You can control the display of the file extension in the ‘Advanced’ tab of Finder Preferences. You can also control this setting for each individual file in its Info panel.
Finder will also warn when you attempt to change the file extension, since it might change which application is used to open a file. (You can also disable this in the Finder Preferences.)
bash has no such warning mechanism.
$ mv hello.txt hello.md
Note: A feature specific to macOS is that some directories will have filename extensions and Finder will display them as if they were files, not folders. These folders are called ‘packages’ or ‘bundles.’ The most common example are applications with the
Packages and bundles are used to hide complex file and data structures from users. Another example is the ‘Photos Library’ (or ‘iPhotos Library’ on older systems) which hides a big and complex folder structure.
You can choose ‘Show Package Contents’ from the context menu in Finder to drill down further into the internal structure of a package or bundle.
bashand other shells are not really aware of packages or bundles and treat them like normal directories.
You can read more detail on Bundles and Packages on the Apple Developer Page.
Note to the Note: the name ‘packages’ is also used for package installer files (with the
.pkgextension). These are different uses of the same word.
The command to copy is
cp. It follows similar syntax as the
$ cp source destination
So you can copy the
samplefile we created earlier:
$ cp samplefile newsamplefile
You can also copy to a directory:
$ cp samplefile testdir
cpcommand will mercilessly overwrite existing files with the same name!
When you run
cp again it will overwrite the existing copy:
$ cp samplefile testdir
As with the
rm command overwritten files are lost. There is no way to retrieve overwritten files.
-i option shows a prompt to confirm whenever a file will be overwritten:
$ cp -i samplefile testdir overwrite testdir/samplefile? (y/n [n]) n not overwritten
When you try to copy a directory, you will get an error message:
$ cp testdir newdir cp: testdir is a directory (not copied).
Since the command to copy a file or directory would look exactly the same,
cp expects an extra option to be certain you know what you are doing. The
-R option (for recursive) will tell
cp to recursively copy all files and sub-directories (and their contents) of a folder.
$ cp -R testdir newdir
This will create a copy of
testdir and all its contents with the name
Warning: the option for recursive copying is
R). There is a legacy option
r) which seems to do the same thing. However, there is a difference in behavior mentioned in the
Historic versions of the `cp` utility had a `-r` option. This implementation supports that option; however, its use is strongly discouraged, as it does not correctly copy special files, symbolic links, or fifo's. If the destination directory already exists the way you write the path of the source directory will influence the behavior of cp.
When the path to the source does not end with a
cp will create a copy of the directory in the destination directory:
$ mkdir dirA $ cp -R testdir dirA $ ls dirA testdir
When the path of the source directory ends with a
cp will copy all the contents of the source directory to the destination folder:
$ ls testdir samplefile $ mkdir dirB $ cp -R testdir dirB $ ls dirB samplefile
Warning: when you use tab-completion to complete paths to directories the
/is always appended! You will need to consider whether you want to keep the trailing
You can add more source arguments to a
cp command, the last argument will be the destination:
$ cp -R samplefile otherfile hello.txt bigfolder
Note: In early versions of Unix wildcard substitution was the responsibility of a program called
glob, short for ‘global command.’ Because of this the action of replacing wildcards with actual paths and filenames was and still is called globbing.
When you have to address or manage many files at once, it can be slow, tedious and ineffective to address each file individually.
bash provides wildcard characters to make that easier.
There are two commonly used wildcard characters:
The asterisk or star
* will match zero or more characters. It can be placed anywhere in a path.
The question mark
? will match any character, but there has to be a character.
By default filenames that start with a period ‘
.’ are not matched, unless you specifically start the string with a dot
It is important to keep in mind that
bash will build a list of filenames that match the wildcards and substitute this list in place of the name with the wildcard(s) before executing the command.
When you enter
$ cd ~ $ ls D*
The D* will be replaced with the list of filenames that match (
Desktop Documents Downloads) and then executed:
$ ls Desktop Documents Downloads
This can lead to some unforeseen consequences. For example say you are in a folder with some files and directories:
$ ls -F dirA/ dirB/ dirC/ file1 file2 file3
And you run
$ cp file? dir?
The wildcards will be expanded to
$ cp file1 file2 file3 dirA dirB dirC
Which means that the three files as well as
dirB will be copied into
dirC, since treats the last argument as the destination and all previous arguments will be copied.
You can use wildcards in paths, so
/Users/*/ will expand into all directories in the
/Users/*/Desktop will expand into a list of all users’
Desktop folders. Note that the first list contains
/Users/Shared while the second does not contain
/Users/Shared/Desktop, because that directory does not exist!
Warning: Wildcards can be extremely useful, but also very dangerous. They have to be handled with utmost caution, especially with potentially destructive commands such as
You can always test the result of wildcard expansion with the echo command:
$ echo /Users/*/ /Users/Guest/ /Users/Shared/ /Users/armin/ $ echo /Users/*/Desktop /Users/Guest/Desktop /Users/armin/Desktop
You can also hit the escape key twice and bash will show the expansion, if there are any:
$ echo /Users/*<esc><esc> Guest/ Shared/ armin/
bash has a third globbing or wildcard character, but it is a bit more complex. You can provide a list of possible characters between square brackets.
rat, but not
Since shell commands are case-sensitive, you may have to provide both cases, if you want to match:
No matter how many characters are in the square brackets, they will match to exactly one character:
We have been creating and copying a lot of files. It is time to clean up. We already know the
rm command to remove files. However, when you try to use
rm to delete a directory you get:
$ rm newdir rm: newdir: is a directory
There is a command
rmdir which is the destructive equivalent of
rmdir can only remove empty directories:
$ rmdir newdir rmdir: newdir: Directory not empty
You can use the
* wildcard to delete all files in
$ rm newdir/*
*wildcard will not expand to filenames starting with a period. You may have to explicitly delete dot files as well:
$ touch newdir/.dotfile $ rm newdir/* $ rmdir newdir rmdir: newdir: Directory not empty $ rm newdir/.* rm: "." and ".." may not be removed $ rmdir newdir
This will work as long there are only files or empty directories in
newdir. When the directory you want to delete contains an entire hierarchy of files and directories, then this approach will be cumbersome.
For this the
rm command has the
-R option which will recursively delete all contents and subdirectories.
$ rm -R testdir
Since there is no way to recover a file deleted by
rm you should always use this command with care, especially when using the
You can add the
-i option when using
-R as well, but then you will be prompted for every single file and subdirectory, which can be very tedious and counter-productive.
Note: unlike the
-Roption for the
rmcommand are synonyms. However, for consistency’s sake and to build muscle memory. I would recommend making a habit of using the
-Rsyntax for both commands.