Extract file extension: Difference between revisions
m →{{header|Lua}}: (shortened) |
m →{{header|REXX}}: changed/added comments and whitespace, changed indentations. |
||
Line 857: | Line 857: | ||
=={{header|REXX}}== |
=={{header|REXX}}== |
||
Using this paraphrased Rosetta Code task's definition that: |
|||
⚫ | |||
a legal file extension ''only'' consists of mixed-case Latin letters and/or decimal digits. |
|||
⚫ | |||
⚫ | |||
parse arg fID /*obtain any optional arguments from CL*/ |
|||
@.= /*define default value for the @ array.*/ |
|||
parse arg fID /*obtain any optional arguments from CL*/ |
|||
if fID\=='' then @.1 = fID /*use the filename from the C.L. */ |
|||
⚫ | |||
@.1 = 'picture.jpg' |
@.1 = 'picture.jpg' |
||
@.2 = 'http://mywebsite.com/pictures/image.png' |
@.2 = 'http://mywebsite.com/pictures/image.png' |
||
Line 871: | Line 873: | ||
end |
end |
||
do j=1 while @.j\==''; x= /*process (all of) the file name(s). */ |
do j=1 while @.j\==''; x= /*process (all of) the file name(s). */ |
||
p=lastpos(.,@.j) /*find the last position of a period. */ |
p=lastpos(.,@.j) /*find the last position of a period. */ |
||
if p\==0 then x=substr(@.j,p+1) /*Found a dot? Then get stuff after it*/ |
if p\==0 then x=substr(@.j, p+1) /*Found a dot? Then get stuff after it*/ |
||
if \datatype(x,'A') then x= /*is it upper/lowercase letters|digits?*/ |
if \datatype(x, 'A') then x= /*is it upper/lowercase letters|digits?*/ |
||
if x=='' then x=" [null]" /*use a better name for a "null". */ |
if x=='' then x= " [null]" /*use a better name for a "null". */ |
||
else x=. || x /*prefix the extension with a period. */ |
else x= . || x /*prefix the extension with a period. */ |
||
say 'file |
say 'file extension=' left(x, 20) "for file name=" @.j |
||
⚫ | |||
end /*j*/ |
|||
⚫ | |||
⚫ | |||
⚫ | |||
<pre> |
<pre> |
||
file |
file extension= .jpg for file name= picture.jpg |
||
file |
file extension= .png for file name= http://mywebsite.com/pictures/image.png |
||
file |
file extension= .longextension for file name= myuniquefile.longextension |
||
file |
file extension= [null] for file name= IAmAFileWithoutExtension |
||
file |
file extension= [null] for file name= /path/to.my/file |
||
file |
file extension= [null] for file name= file.odd_one |
||
</pre> |
</pre> |
||
Revision as of 23:24, 22 April 2016
Write a program that takes one string argument representing the path to a file and returns the file's extension, or the null string if the file path has no extension. An extension appears after the last period in the file name and consists of one or more letters or numbers.
Show here the action of your routine on the following examples:
- picture.jpg returns .jpg
- http://mywebsite.com/picture/image.png returns .png
- myuniquefile.longextension returns .longextension
- IAmAFileWithoutExtension returns an empty string ""
- /path/to.my/file returns an empty string as the period is in the directory name rather than the file
- file.odd_one returns an empty string as an extension (by this definition), cannot contain an underscore.
ALGOL 68
<lang algol68># extracts a file-extension from the end of a pathname. The file extension is #
- defined as a dot followed by one or more letters or digits #
OP EXTENSION = ( STRING pathname )STRING:
IF LWB pathname >= UPB pathname THEN # the pathname has 0 or 1 characters and so has no extension # "" ELIF NOT isalnum( pathname[ UPB pathname ] ) THEN # the final character is not a letter or digit - no extension # "" ELSE # could have an extension # INT pos := UPB pathname; WHILE pos > LWB pathname AND isalnum( pathname[ pos ] ) DO pos -:= 1 OD; IF pathname[ pos ] = "." THEN # the character before the letters and digits was a "." # pathname[ pos : ] ELSE # no "." before the letters and digits - no extension # "" FI FI ; # EXTENSION #
- test the EXTENSION operator #
PROC test extension = ( STRING pathname, STRING expected extension )VOID:
BEGIN STRING extension = EXTENSION pathname; write( ( ( pathname + " got extension: (" + extension + ") " + IF extension = expected extension THEN "" ELSE "NOT" FI + " as expected" ) , newline ) ) END ; # text extension #
main: ( test extension( "picture.jpg", ".jpg" )
- test extension( "http://mywebsite.com/picture/image.png", ".png" )
- test extension( "myuniquefile.longextension", ".longextension" )
- test extension( "IAmAFileWithoutExtension", "" )
- test extension( "/path/to.my/file", "" )
- test extension( "file.odd_one", "" )
)</lang>
- Output:
picture.jpg got extension: (.jpg) as expected http://mywebsite.com/picture/image.png got extension: (.png) as expected myuniquefile.longextension got extension: (.longextension) as expected IAmAFileWithoutExtension got extension: () as expected /path/to.my/file got extension: () as expected file.odd_one got extension: () as expected
ALGOL W
<lang algolw>begin
% extracts a file-extension from the end of a pathname. % % The file extension is defined as a dot followed by one or more letters % % or digits. As Algol W only has fixed length strings we limit the % % extension to 32 characters and the pathname to 256 (the longest string % % allowed by Algol W) % string(32) procedure extension( string(256) value pathname ) ; begin
integer pathPos;
% position to the previous character in the pathname % procedure prev ; pathPos := pathPos - 1; % get the character as pathPos from pathname % string(1) procedure ch ; pathname( pathPos // 1 ); % checks for a letter or digit - assumes the letters are contiguous % % in the character set - not true for EBCDIC % logical procedure isLetterOrDigit( string(1) value c ) ; ( c <= "z" and c >= "a" ) or ( c <= "Z" and c >= "A" ) or ( c <= "9" and c >= "0" ) ;
% find the length of the pathname with trailing blanks removed % pathPos := 255; while pathPos >= 0 and ch = " " do prev;
% extract the extension if possible % if pathPos <= 0 then "" % no extension: 0 or 1 character pathname % else if not isLetterOrDigit( ch ) then "" % no extension: last character not a letter/digit % else begin while pathPos > 0 and isLetterOrDigit( ch ) do prev; if ch not = "." then "" % no extension: letters/digits not preceeded by "." % else begin % have an extension % string(32) ext; ext := " "; % algol W substring lengths must be compile-time constants % % hence the loop to copy the extension characters % for charPos := 0 until 31 do begin if pathPos <= 255 then begin ext( charPos // 1 ) := pathname( pathPos // 1 ); pathPos := pathPos + 1 end end for_charPos ; ext end end
end extension ;
% test the extension procedure % procedure testExtension( string(256) value pathname ; string(32) value expectedExtension ) ; begin string(32) ext; ext := extension( pathname ); write( pathname( 0 // 40 ) , " -> (" , ext( 0 // 16 ) , ") " , if ext = expectedExtension then "" else "NOT" , " as expected" ) end ; % text extension % testExtension( "picture.jpg", ".jpg" ); testExtension( "http://mywebsite.com/picture/image.png", ".png" ); testExtension( "myuniquefile.longextension", ".longextension" ); testExtension( "IAmAFileWithoutExtension", "" ); testExtension( "/path/to.my/file", "" ); testExtension( "file.odd_one", "" );
end.</lang>
- Output:
picture.jpg -> (.jpg ) as expected http://mywebsite.com/picture/image.png -> (.png ) as expected myuniquefile.longextension -> (.longextension ) as expected IAmAFileWithoutExtension -> ( ) as expected /path/to.my/file -> ( ) as expected file.odd_one -> ( ) as expected
AWK
<lang AWK>
- syntax: GAWK -f EXTRACT_FILE_EXTENSION.AWK
BEGIN {
arr[++i] = "picture.jpg" arr[++i] = "http://mywebsite.com/picture/image.png" arr[++i] = "myuniquefile.longextension" arr[++i] = "IAmAFileWithoutExtension" arr[++i] = "/path/to.my/file" arr[++i] = "file.odd_one" for (j=1; j<=i; j++) { printf("%-40s '%s'\n",arr[j],extract_ext(arr[j])) } exit(0)
} function extract_ext(fn, sep1,sep2,tmp) {
while (fn ~ (sep1 = ":|\\\\|\\/")) { # ":" or "\" or "/" fn = substr(fn,match(fn,sep1)+1) } while (fn ~ (sep2 = "\\.")) { # "." fn = substr(fn,match(fn,sep2)+1) tmp = 1 } if (fn ~ /_/ || tmp == 0) { return("") } return(fn)
} </lang>
Output:
picture.jpg 'jpg' http://mywebsite.com/picture/image.png 'png' myuniquefile.longextension 'longextension' IAmAFileWithoutExtension '' /path/to.my/file '' file.odd_one ''
C
<lang C>
- include <assert.h>
- include <ctype.h>
- include <string.h>
- include <stdio.h>
/* Returns a pointer to the extension of 'string'. If no extension is found,
* then returns a pointer to the null-terminator of 'string'. */
char* file_ext(const char *string) {
assert(string != NULL); char *ext = strrchr(string, '.');
if (ext == NULL) return (char*) string + strlen(string);
for (char *iter = ext + 1; *iter != '\0'; iter++) { if (!isalnum(*iter)) return (char*) string + strlen(string); }
return ext + 1;
}
int main(void) {
const char *strings[] = { "picture.jpg", "http://mywebsite.con/picture/image.png", "myuniquefile.longextension", "IAmAFileWithoutExtension", "/path/to.my/file", "file.odd_one" };
for (int i = 0; i < sizeof(strings) / sizeof(strings[0]); ++i) { printf("'%s' - '%s'\n", strings[i], file_ext(strings[i])); }
} </lang>
- Output:
'picture.jpg' - 'jpg' 'http://mywebsite.con/picture/image.png' - 'png' 'myuniquefile.longextension' - 'longextension' 'IAmAFileWithoutExtension' - '' '/path/to.my/file' - '' 'file.odd_one' - ''
C++
<lang cpp>#include <string>
- include <algorithm>
- include <iostream>
- include <vector>
std::string findExtension ( const std::string & filename ) {
auto position = filename.find_last_of ( '.' ) ; if ( position == std::string::npos ) return "" ; else { std::string extension ( filename.substr( position ) ) ; position = extension.find( '_' ) ; auto pos2 = extension.find( '/' ) ; if (( position != std::string::npos ) || ( pos2 != std::string::npos ))
return "" ;
else
return extension ;
}
}
int main( ) {
std::vector<std::string> filenames {"picture.jpg" , "http://mywebsite.com/picture/image.png" , "myuniquefile.longextension" , "IAmAFileWithoutExtension" , "/path/to.my/file" , "file.odd_one" } ; std::vector<std::string> extensions( filenames.size( ) ) ; std::transform( filenames.begin( ) , filenames.end( ) , extensions.begin( ) , findExtension ) ; for ( int i = 0 ; i < filenames.size( ) ; i++ ) std::cout << filenames[i] << " has extension : " << extensions[i] << " !\n" ; return 0 ;
} </lang>
- Output:
picture.jpg has extension : .jpg ! http://mywebsite.com/picture/image.png has extension : .png ! myuniquefile.longextension has extension : .longextension ! IAmAFileWithoutExtension has extension : ! /path/to.my/file has extension : ! file.odd_one has extension : !
C#
<lang C#> public static string ExtractExtension(string str) {
string s = str; string temp = ""; string result = ""; bool isDotFound = false;
for (int i = s.Length -1; i >= 0; i--) { if(s[i].Equals('.')) { temp += s[i]; isDotFound = true; break; } else { temp += s[i]; } }
if(!isDotFound) { result = ""; } else { for (int j = temp.Length - 1; j >= 0; j--) { result += temp[j]; } }
return result;
} </lang>
Emacs Lisp
<lang Lisp>(file-name-extension "foo.txt") => "txt"</lang>
No extension is distinguished from empty extension but an (or ... "")
can give ""
for both if desired
<lang Lisp>(file-name-extension "foo.") => "" (file-name-extension "foo") => nil</lang>
An Emacs backup ~
or .~NUM~
are not part of the extension, but otherwise any characters are allowed.
<lang Lisp>(file-name-extension "foo.txt~") => "txt" (file-name-extension "foo.txt.~1.234~") => "txt"</lang>
Forth
<lang forth>: invalid? ( c -- f )
toupper dup [char] A [char] Z 1+ within swap [char] 0 [char] 9 1+ within or 0= ;
- extension ( addr1 u1 -- addr2 u2 )
dup 0= if exit then 2dup over + begin 1- 2dup <= while dup c@ invalid? until then \ no '.' found 2dup - 0> if 2drop dup /string exit then \ invalid char dup c@ [char] . <> if 2drop dup /string exit then swap - \ '.' is last char 2dup 1+ = if drop dup then /string ;
- type.quoted ( addr u -- )
[char] ' emit type [char] ' emit ;
- test ( addr u -- )
2dup type.quoted ." => " extension type.quoted cr ;
- tests
s" picture.jpg" test s" http://mywebsite.com/picture/image.png" test s" myuniquefile.longextension" test s" IAmAFileWithoutExtension" test s" /path/to.my/file" test s" file.odd_one" test s" IDontHaveAnExtension." test ;</lang>
- Output:
cr tests 'picture.jpg' => '.jpg' 'http://mywebsite.com/picture/image.png' => '.png' 'myuniquefile.longextension' => '.longextension' 'IAmAFileWithoutExtension' => '' '/path/to.my/file' => '' 'file.odd_one' => '' 'IDontHaveAnExtension.' => '' ok
Go
<lang go>package main
import ( "fmt" "path" )
// An exact copy of `path.Ext` from Go 1.4.2 for reference: func Ext(path string) string { for i := len(path) - 1; i >= 0 && path[i] != '/'; i-- { if path[i] == '.' { return path[i:] } } return "" }
// A variation that handles the extra non-standard requirement // that extensions shall only "consists of one or more letters or numbers". // // Note, instead of direct comparison with '0-9a-zA-Z' we could instead use: // case !unicode.IsLetter(rune(b)) && !unicode.IsNumber(rune(b)): // return "" // even though this operates on bytes instead of Unicode code points (runes), // it is still correct given the details of UTF-8 encoding. func ext(path string) string { for i := len(path) - 1; i >= 0; i-- { switch b := path[i]; { case b == '.': return path[i:] case '0' <= b && b <= '9': case 'a' <= b && b <= 'z': case 'A' <= b && b <= 'Z': default: return "" } } return "" }
func main() { tests := []string{ "picture.jpg", "http://mywebsite.com/picture/image.png", "myuniquefile.longextension", "IAmAFileWithoutExtension", "/path/to.my/file", "file.odd_one", // Extra, with unicode "café.png", "file.resumé", // with unicode combining characters "cafe\u0301.png", "file.resume\u0301", } for _, str := range tests { std := path.Ext(str) custom := ext(str) fmt.Printf("%38s\t→ %-8q", str, custom) if custom != std { fmt.Printf("(Standard: %q)", std) } fmt.Println() } }</lang>
- Output:
picture.jpg → ".jpg" http://mywebsite.com/picture/image.png → ".png" myuniquefile.longextension → ".longextension" IAmAFileWithoutExtension → "" /path/to.my/file → "" file.odd_one → "" (Standard: ".odd_one") café.png → ".png" file.resumé → "" (Standard: ".resumé") café.png → ".png" file.resumé → "" (Standard: ".resumé")
Haskell
<lang Haskell>module FileExtension
where
myextension :: String -> String myextension s
|not $ elem '.' s = "" |elem '/' extension || elem '_' extension = "" |otherwise = '.' : extension where
extension = reverse ( takeWhile ( /= '.' ) $ reverse s ) </lang>
- Output:
map myextension ["picture.jpg" , "http://mywebsite.com/picture/image.png" , "myuniquefile.longextension" , "IAmAFileWithoutExtension" , "/path/to.my/file" , "file.odd_one"] [".jpg",".png",".longextension","","",""]
J
Implementation:
<lang J>require'regex' ext=: '[.][a-zA-Z0-9]+$'&rxmatch ;@rxfrom ]</lang>
Obviously most of the work here is done by the regex implementation (pcre, if that matters - and this particular kind of expression tends to be a bit more concise expressed in perl than in J...).
Perhaps of interest is that this is an example of a J fork - here we have three verbs separated by spaces. Unlike a unix system fork (which spins up child process which is an almost exact clone of the currently running process), a J fork is three independently defined verbs. The two verbs on the edge get the fork's argument and the verb in the middle combines those two results.
The left verb uses rxmatch to find the beginning position of the match and its length. The right verb is the identity function. The middle verb extracts the desired characters from the original argument. (For a non-match, the length of the "match" is zero so the empty string is extracted.)
Alternative non-regex Implementation
<lang J>ext=: #~ [: +./\ e.&'.' *. [: -. [: +./\. -.@e.&('.',AlphaNum_j_)</lang>
Task examples:
<lang J> ext 'picture.jpg' .jpg
ext 'http://mywebsite.com/picture/image.png'
.png
Examples=: 'picture.jpg';'http://mywebsite.com/picture/image.png';'myuniquefile.longextension';'IAmAFileWithoutExtension';'/path/to.my/file';'file.odd_one' ext each Examples
┌────┬────┬──────────────┬┬┬┐ │.jpg│.png│.longextension││││ └────┴────┴──────────────┴┴┴┘</lang>
Java
<lang java>public class Test {
public static void main(String[] args) { String[] filenames = {"picture.jpg", "http://mywebsite.con/picture/image.png", "myuniquefile.longextension", "IAmAFileWithoutExtension", "/path/to.my/file", "file.odd_one"};
for (String filename : filenames) { String ext = "null"; int idx = filename.lastIndexOf('.'); if (idx != -1) { String tmp = filename.substring(idx); if (tmp.matches("\\.[a-zA-Z0-9]+")) { ext = tmp; } } System.out.println(filename + " -> " + ext); } }
}</lang>
picture.jpg -> .jpg http://mywebsite.con/picture/image.png -> .png myuniquefile.longextension -> .longextension IAmAFileWithoutExtension -> null /path/to.my/file -> null file.odd_one -> null
jq
Pending resolution of the inconsistency in the task description as of this writing, the following definitions exclude the delimiting period.
In the first section, a version intended for jq version 1.4 is presented. A simpler definition using "match", a regex feature of subsequent versions of jq, is then given.
<lang jq>def file_extension:
def alphanumeric: explode | unique | reduce .[] as $i (true; if . then $i | (97 <= . and . <= 122) or (65 <= . and . <= 90) or (48 <= . and . <= 57) else false end ); rindex(".") as $ix | if $ix then .[1+$ix:] as $ext | if $ext|alphanumeric then $ext # or ".\($ext)" if the period is wanted else "" end else "" end;</lang>
<lang jq>def file_extension:
match( "\\.([a-zA-Z0-9]*$)" ) // false | if . then .captures[0].string else "" end ;</lang>
Examples:
Using either version above gives the same results. <lang jq>"picture.jpg", "myuniquefile.longextension", "http://mywebsite.com/picture/image.png", "myuniquefile.longextension", "IAmAFileWithoutExtension", "/path/to.my/file", "file.odd_one" | "\(.) has extension: \"\(file_extension)\""</lang>
- Output:
<lang sh>$ jq -r -n -f Extract_file_extension.jq picture.jpg has extension: "jpg" myuniquefile.longextension has extension: "longextension" http://mywebsite.com/picture/image.png has extension: "png" myuniquefile.longextension has extension: "longextension" IAmAFileWithoutExtension has extension: "" /path/to.my/file has extension: "" file.odd_one has extension: ""</lang>
Lua
<lang Lua>-- Lua pattern docs at http://www.lua.org/manual/5.1/manual.html#5.4.1 function fileExt (filename) return filename:match("(%.%w+)$") or "" end
local testCases = {
"picture.jpg", "http://mywebsite.com/picture/image.png", "myuniquefile.longextension", "IAmAFileWithoutExtension", "/path/to.my/file", "file.odd_one"
} for _, example in pairs(testCases) do
print(example .. ' -> "' .. fileExt(example) .. '"')
end</lang>
- Output:
picture.jpg -> ".jpg" http://mywebsite.com/picture/image.png -> ".png" myuniquefile.longextension -> ".longextension" IAmAFileWithoutExtension -> "" /path/to.my/file -> "" file.odd_one -> ""
Oforth
If extension is not valid, returns null, not "". Easy to change if "" is required.
<lang Oforth>: fileExt(s) { | i |
s lastIndexOf('.') dup ->i ifNull: [ null return ] s extract(i 1+, s size) conform(#isAlpha) ifFalse: [ null return ] s extract(i, s size)
} </lang>
- Output:
fileExt("picture.jpg") println fileExt("http://mywebsite.com/picture/image.png") println fileExt("myuniquefile.longextension") println fileExt("IAmAFileWithoutExtension") println fileExt("/path/to.my/file") println fileExt("file.odd_one") println
Perl
<lang Perl>#!/usr/bin/perl use strict ; use warnings ;
sub extension {
my $filename = shift ; if ( $filename !~ /\./ ) { return "" ; } else { my @parts = split ( /\./ , $filename ) ; my $extension = $parts[ -1 ] ; if ( $extension =~ /[\/_]/ ) {
return "" ;
} else {
return ".$extension" ;
} }
}
map { print ("file name: $_ , extension : " . extension( $_ ) . "\n" ) }
( "picture.jpg" , "http://mywebsite.com/picture/image.png" , "myuniquefile.longextension" , "IAmAFileWithoutExtension" , "/path/to.my/file" , "file.odd_one" ) ;
</lang>
- Output:
file name: picture.jpg , extension : .jpg file name: http://mywebsite.com/picture/image.png , extension : .png file name: myuniquefile.longextension , extension : .longextension file name: IAmAFileWithoutExtension , extension : file name: /path/to.my/file , extension : file name: file.odd_one , extension :
Perl 6
<lang perl6>sub extension ( Str $filename --> Str ) {
given $filename.split(/\./)[*-1] { when $filename { "" } when / <[\/_]> / { "" } default { "." ~ $_ } }
}
say "$_ -> ", extension($_).perl for (
'mywebsite.com/picture/image.png', 'http://mywebsite.com/picture/image.png', 'myuniquefile.longextension', 'IAmAFileWithoutExtension', '/path/to.my/file', 'file.odd_one',
)</lang>
- Output:
mywebsite.com/picture/image.png -> ".png" http://mywebsite.com/picture/image.png -> ".png" myuniquefile.longextension -> ".longextension" IAmAFileWithoutExtension -> "" /path/to.my/file -> "" file.odd_one -> ""
Phix
<lang Phix>function getExtension(string filename)
for i=length(filename) to 1 by -1 do integer ch = filename[i] if ch='.' then return filename[i..$] end if if find(ch,"\\/_") then exit end if end for return ""
end function
constant tests = {"mywebsite.com/picture/image.png",
"http://mywebsite.com/picture/image.png", "myuniquefile.longextension", "IAmAFileWithoutExtension", "/path/to.my/file", "file.odd_one"}
for i=1 to length(tests) do
printf(1,"%s ==> %s\n",{tests[i],getExtension(tests[i])})
end for</lang>
- Output:
mywebsite.com/picture/image.png ==> .png http://mywebsite.com/picture/image.png ==> .png myuniquefile.longextension ==> .longextension IAmAFileWithoutExtension ==> /path/to.my/file ==> file.odd_one ==>
PowerShell
<lang PowerShell> function extension($file){
$ext = [System.IO.Path]::GetExtension($file) if (-not [String]::IsNullOrEmpty($ext)) { if($ext.IndexOf("_") -ne -1) {$ext = ""} } $ext
} extension "picture.jpg" extension "http://mywebsite.com/picture/image.png" extension "myuniquefile.longextension" extension "IAmAFileWithoutExtension" extension "/path/to.my/file" extension "file.odd_one" </lang> Output:
.jpg .png .longextension
Python
Uses os.path.splitext and the extended tests from the Go example above.
<lang python>Python 3.5.0a1 (v3.5.0a1:5d4b6a57d5fd, Feb 7 2015, 17:58:38) [MSC v.1900 32 bit (Intel)] on win32 Type "copyright", "credits" or "license()" for more information. >>> import os >>> tests = ["picture.jpg", "http://mywebsite.com/picture/image.png", "myuniquefile.longextension", "IAmAFileWithoutExtension", "/path/to.my/file", "file.odd_one", # Extra, with unicode "café.png", "file.resumé", # with unicode combining characters "cafe\u0301.png", "file.resume\u0301"] >>> for path in tests:
print("Path: %r -> Extension: %r" % (path, os.path.splitext(path)[-1]))
Path: 'picture.jpg' -> Extension: '.jpg'
Path: 'http://mywebsite.com/picture/image.png' -> Extension: '.png'
Path: 'myuniquefile.longextension' -> Extension: '.longextension'
Path: 'IAmAFileWithoutExtension' -> Extension:
Path: '/path/to.my/file' -> Extension:
Path: 'file.odd_one' -> Extension: '.odd_one'
Path: 'café.png' -> Extension: '.png'
Path: 'file.resumé' -> Extension: '.resumé'
Path: 'café.png' -> Extension: '.png'
Path: 'file.resumé' -> Extension: '.resumé'
>>> </lang>
Racket
<lang Racket>#lang racket
- Note that for a real implementation, Racket has a
- `filename-extension` in its standard library, but don't use it here
- since it requires a proper name (fails on ""), returns a byte-string,
- and handles path values so might run into problems with unicode
- string inputs.
(define (string-extension x)
(cadr (regexp-match #px"(\\.alnum:+|)$" x)))
(define (string-extension/unicode x)
(cadr (regexp-match #px"(\\.(?:\\p{L}|\\p{N}|\\p{M})+|)$" x)))
(define examples '("picture.jpg"
"http://mywebsite.com/picture/image.png" "myuniquefile.longextension" "IAmAFileWithoutExtension" "/path/to.my/file" "file.odd_one" "" ;; Extra, with unicode "café.png" "file.resumé" ;; with unicode combining characters "cafe\u0301.png" "file.resume\u0301"))
(printf "Official task:\n") (for ([x (in-list examples)])
(printf "~s ==> ~s\n" x (string-extension x)))
(printf "\nWith unicode support:\n") (for ([x (in-list examples)])
(printf "~s ==> ~s\n" x (string-extension/unicode x)))
</lang>
- Output:
Official task: "picture.jpg" ==> ".jpg" "http://mywebsite.com/picture/image.png" ==> ".png" "myuniquefile.longextension" ==> ".longextension" "IAmAFileWithoutExtension" ==> "" "/path/to.my/file" ==> "" "file.odd_one" ==> "" "" ==> "" "café.png" ==> ".png" "file.resumé" ==> "" "café.png" ==> ".png" "file.resumé" ==> "" With unicode support: "picture.jpg" ==> ".jpg" "http://mywebsite.com/picture/image.png" ==> ".png" "myuniquefile.longextension" ==> ".longextension" "IAmAFileWithoutExtension" ==> "" "/path/to.my/file" ==> "" "file.odd_one" ==> "" "" ==> "" "café.png" ==> ".png" "file.resumé" ==> ".resumé" "café.png" ==> ".png" "file.resumé" ==> ".resumé"
REXX
Using this paraphrased Rosetta Code task's definition that:
a legal file extension only consists of mixed-case Latin letters and/or decimal digits. <lang rexx>/*REXX pgm extracts the file extension (defined above from the RC task) from a file name*/ @.= /*define default value for the @ array.*/ parse arg fID /*obtain any optional arguments from CL*/ if fID\== then @.1 = fID /*use the filename from the C.L. */
else do /*No filename given? Then use defaults.*/ @.1 = 'picture.jpg' @.2 = 'http://mywebsite.com/pictures/image.png' @.3 = 'myuniquefile.longextension' @.4 = 'IAmAFileWithoutExtension' @.5 = '/path/to.my/file' @.6 = 'file.odd_one' end
do j=1 while @.j\==; x= /*process (all of) the file name(s). */ p=lastpos(.,@.j) /*find the last position of a period. */ if p\==0 then x=substr(@.j, p+1) /*Found a dot? Then get stuff after it*/ if \datatype(x, 'A') then x= /*is it upper/lowercase letters|digits?*/ if x== then x= " [null]" /*use a better name for a "null". */ else x= . || x /*prefix the extension with a period. */ say 'file extension=' left(x, 20) "for file name=" @.j end /*j*/ /*stick a fork in it, we're all done. */</lang>
output when using the default (internal) inputs:
file extension= .jpg for file name= picture.jpg file extension= .png for file name= http://mywebsite.com/pictures/image.png file extension= .longextension for file name= myuniquefile.longextension file extension= [null] for file name= IAmAFileWithoutExtension file extension= [null] for file name= /path/to.my/file file extension= [null] for file name= file.odd_one
sed
<lang sed>s:.*\.:.: s:\(^[^.]\|.*[/_]\).*::</lang> or <lang bash>sed -re 's:.*\.:.:' -e 's:(^[^.]|.*[/_]).*::'</lang>
- Output:
.jpg .png .longextension IAmAFileWithoutExtension
Sidef
<lang ruby>func extension (filename) {
given(filename.split('.').last) { when(filename) { "" } when(/[\/_]/) { "" } default { "." + _ } }
}
['mywebsite.com/picture/image.png',
'http://mywebsite.com/picture/image.png', 'myuniquefile.longextension', 'IAmAFileWithoutExtension', '/path/to.my/file', 'file.odd_one',
].each {|f| say "#{f} -> #{extension(f).dump}" }</lang>
- Output:
mywebsite.com/picture/image.png -> ".png" http://mywebsite.com/picture/image.png -> ".png" myuniquefile.longextension -> ".longextension" IAmAFileWithoutExtension -> "" /path/to.my/file -> "" file.odd_one -> ""
Tcl
Tcl's built in file extension command already almost knows how to do this, except it accepts any character after the dot. Just for fun, we'll enhance the builtin with a new subcommand with the limitation specified for this problem.
<lang Tcl>proc assert {expr} { ;# for "static" assertions that throw nice errors
if {![uplevel 1 [list expr $expr]]} { set msg "{$expr}" catch {append msg " {[uplevel 1 [list subst -noc $expr]]}"} tailcall throw {ASSERT ERROR} $msg }
}
proc file_ext {file} {
set res "" regexp {(\.[a-z0-9]+)$} $file -> res return $res
}
set map [namespace ensemble configure file -map] dict set map ext ::file_ext namespace ensemble configure file -map $map
- and a test:
foreach {file ext} {
picture.jpg .jpg http://mywebsite.com/picture/image.png .png myuniquefile.longextension .longextension IAmAFileWithoutExtension "" /path/to.my/file "" file.odd_one ""
} {
set res "" assert {[file ext $file] eq $ext}
}</lang>
VBScript
<lang vb> Function GetExtension(s) If InStr(s,"/") Then arr_s = Split(s,"/") fname = arr_s(UBound(arr_s)) ElseIf InStr(s,"\") Then arr_s = Split(s,"\") fname = arr_s(UBound(arr_s)) Else fname = s End If GetExtension = "" If InStr(fname,".") Then arr_x = Split(fname,".") If InStr(1,arr_x(UBound(arr_x)),"_") = 0 Then GetExtension = "." & arr_x(UBound(arr_x)) End If End If End Function
'Testing the function arr_t = Array("picture.jpg","http://mywebsite.com/picture/image.png",_ "myuniquefile.longextension","IAmAFileWithoutExtension",_ "/path/to.my/file","file.odd_one") For i = 0 To UBound(arr_t) WScript.StdOut.WriteLine arr_t(i) & " -> " & GetExtension(arr_t(i)) Next </lang>
- Output:
picture.jpg -> .jpg http://mywebsite.com/picture/image.png -> .png myuniquefile.longextension -> .longextension IAmAFileWithoutExtension -> '' /path/to.my/file -> '' file.odd_one -> ''
zkl
The File object has a method splitFileName that does just that, returning a list of the parts. The method knows about the OS it was compiled on (Unix, Windows). <lang zkl>T("picture.jpg","http://mywebsite.com/picture/image.png",
"myuniquefile.longextension","IAmAFileWithoutExtension", "/path/to.my/file","file.odd_one").apply(File.splitFileName).println();</lang>
- Output:
L(L("","","picture",".jpg"), L("","http://mywebsite.com/picture/","image",".png"), L("","","myuniquefile",".longextension"), L("","","IAmAFileWithoutExtension",""), L("","/path/to.my/","file",""), L("","","file",".odd_one"))
The last one is an odd duck so some code is in order: <lang zkl>fcn exonly(fileName){
var re=RegExp(0'|\.[a-zA-Z0-9]+$|); ext:=File.splitFileName(fileName)[-1]; if(not re.matches(ext)) return(""); ext
}</lang> <lang zkl>T("picture.jpg","http://mywebsite.com/picture/image.png",
"myuniquefile.longextension","IAmAFileWithoutExtension", "/path/to.my/file","file.odd_one").apply(exonly).println();</lang>
- Output:
L(".jpg",".png",".longextension","","","")