Strip block comments
You are encouraged to solve this task according to the task description, using any language you may know.
A block comment begins with a beginning delimiter and ends with a ending delimiter, including the delimiters. These delimiters are often multi-character sequences.
Task: Strip block comments from program text (of a programming language much like classic C). Your demos should at least handle simple, non-nested and multiline block comment delimiters. The beginning delimiter is the two-character sequence “/*” and the ending delimiter is “*/”.
Sample text for stripping:
/**
* Some comments
* longer comments here that we can parse.
*
* Rahoo
*/
function subroutine() {
a = /* inline comment */ b + c ;
}
/*/ <-- tricky comments */
/**
* Another comment.
*/
function something() {
}
Extra credit: Ensure that the stripping code is not hard-coded to the particular delimiters described above, but instead allows the caller to specify them. (If your language supports them, optional parameters may be useful for this.)
C.f: Strip comments from a string
Ada
strip.adb: <lang Ada>with Ada.Strings.Fixed; with Ada.Strings.Unbounded; with Ada.Text_IO; with Ada.Command_Line;
procedure Strip is
use Ada.Strings.Unbounded;
procedure Print_Usage is
begin
Ada.Text_IO.Put_Line ("Usage:");
Ada.Text_IO.New_Line;
Ada.Text_IO.Put_Line (" strip <file> [<opening> [<closing>]]");
Ada.Text_IO.New_Line;
Ada.Text_IO.Put_Line (" file: file to strip");
Ada.Text_IO.Put_Line (" opening: string for opening comment");
Ada.Text_IO.Put_Line (" closing: string for closing comment");
Ada.Text_IO.New_Line;
end Print_Usage;
Opening_Pattern : Unbounded_String := To_Unbounded_String ("/*");
Closing_Pattern : Unbounded_String := To_Unbounded_String ("*/");
Inside_Comment : Boolean := False;
function Strip_Comments (From : String) return String is
use Ada.Strings.Fixed;
Opening_Index : Natural;
Closing_Index : Natural;
Start_Index : Natural := From'First;
begin
if Inside_Comment then
Start_Index :=
Index (Source => From, Pattern => To_String (Closing_Pattern));
if Start_Index < From'First then
return "";
end if;
Inside_Comment := False;
Start_Index := Start_Index + Length (Closing_Pattern);
end if;
Opening_Index :=
Index
(Source => From,
Pattern => To_String (Opening_Pattern),
From => Start_Index);
if Opening_Index < From'First then
return From (Start_Index .. From'Last);
else
Closing_Index :=
Index
(Source => From,
Pattern => To_String (Closing_Pattern),
From => Opening_Index + Length (Opening_Pattern));
if Closing_Index > 0 then
return From (Start_Index .. Opening_Index - 1) &
Strip_Comments
(From (
Closing_Index + Length (Closing_Pattern) .. From'Last));
else
Inside_Comment := True;
return From (Start_Index .. Opening_Index - 1);
end if;
end if;
end Strip_Comments;
File : Ada.Text_IO.File_Type;
begin
if Ada.Command_Line.Argument_Count < 1
or else Ada.Command_Line.Argument_Count > 3
then
Print_Usage;
return;
end if;
if Ada.Command_Line.Argument_Count > 1 then
Opening_Pattern := To_Unbounded_String (Ada.Command_Line.Argument (2));
if Ada.Command_Line.Argument_Count > 2 then
Closing_Pattern :=
To_Unbounded_String (Ada.Command_Line.Argument (3));
else
Closing_Pattern := Opening_Pattern;
end if;
end if;
Ada.Text_IO.Open
(File => File,
Mode => Ada.Text_IO.In_File,
Name => Ada.Command_Line.Argument (1));
while not Ada.Text_IO.End_Of_File (File => File) loop
declare
Line : constant String := Ada.Text_IO.Get_Line (File);
begin
Ada.Text_IO.Put_Line (Strip_Comments (Line));
end;
end loop;
Ada.Text_IO.Close (File => File);
end Strip;</lang> output:
function subroutine() {
a = b + c ;
}
function something() {
}
C
<lang C>#include <stdio.h>
- include <string.h>
- include <stdlib.h>
char *ca = "/*", *cb = "*/"; int al = 2, bl = 2;
char *loadfile(char *s) {
FILE *f = fopen(s, "rb"); int l;
if (f != NULL) {
fseek(f, 0, SEEK_END); l = ftell(f); s = malloc(l+1); rewind(f); if (s) fread(s, 1, l, f); fclose(f);
} return s;
}
void stripcomments(char *s) {
char *a, *b; int len = strlen(s) + 1;
while ((a = strstr(s, ca)) != NULL) {
b = strstr(a+al, cb); if (b == NULL) break; b += bl; memmove(a, b, len-(b-a));
}
}
int main(int argc, char **argv) {
char *s = "input.txt";
if (argc >= 2)
s = argv[1];
s = loadfile(s);
if (argc == 4) {
al = strlen(ca = argv[2]); bl = strlen(cb = argv[3]);
} stripcomments(s); puts(s); free(s); return 0;
}</lang>
- Usage
Specify an input file via the first command line argument, and optionally specify comment opening and closing delimiters with the next two args, or defaults of /* and */ are assumed.
- Output
function subroutine() {
a = b + c ;
}
function something() {
}
C++
<lang cpp>#include <string>
- include <iostream>
- include <iterator>
- include <fstream>
- include <boost/regex.hpp>
int main( ) {
std::ifstream codeFile( "samplecode.txt" ) ;
if ( codeFile ) {
boost::regex commentre( "/\\*.*?\\*/" ) ;//comment start and end, and as few characters in between as possible
std::string my_erase( "" ) ; //erase them
std::string stripped ;
std::string code( (std::istreambuf_iterator<char>( codeFile ) ) ,
std::istreambuf_iterator<char>( ) ) ;
codeFile.close( ) ;
stripped = boost::regex_replace( code , commentre , my_erase ) ;
std::cout << "Code unstripped:\n" << stripped << std::endl ;
return 0 ;
}
else {
std::cout << "Could not find code file!" << std::endl ;
return 1 ;
}
}</lang> Output:
Code unstripped:
function subroutine() {
a = b + c ;
}
function something() {
}
C#
<lang Csharp>using System;
class Program
{
private static string BlockCommentStrip(string commentStart, string commentEnd, string sampleText)
{
while (sampleText.IndexOf(commentStart) > -1 && sampleText.IndexOf(commentEnd, sampleText.IndexOf(commentStart) + commentStart.Length) > -1)
{
int start = sampleText.IndexOf(commentStart);
int end = sampleText.IndexOf(commentEnd, start + commentStart.Length);
sampleText = sampleText.Remove(
start,
(end + commentEnd.Length) - start
);
}
return sampleText;
}
}</lang>
Clojure
<lang Clojure>(defn comment-strip [txt & args]
(let [args (conj {:delim ["/*" "*/"]} (apply hash-map args)) ; This is the standard way of doing keyword/optional arguments in Clojure
[opener closer] (:delim args)]
(loop [out "", txt txt, delim-count 0] ; delim-count is needed to handle nested comments
(let [[hdtxt resttxt] (split-at (count opener) txt)] ; This splits "/* blah blah */" into hdtxt="/*" and restxt="blah blah */"
(printf "hdtxt=%8s resttxt=%8s out=%8s txt=%16s delim-count=%s\n" (apply str hdtxt) (apply str resttxt) out (apply str txt) delim-count) (cond (empty? hdtxt) (str out (apply str txt)) (= (apply str hdtxt) opener) (recur out resttxt (inc delim-count)) (= (apply str hdtxt) closer) (recur out resttxt (dec delim-count)) (= delim-count 0)(recur (str out (first txt)) (rest txt) delim-count) true (recur out (rest txt) delim-count))))))</lang>
user> (comment-strip "This /* is */ some /* /* /* */ funny */ */ text") hdtxt= Th resttxt=is /* is */ some /* /* /* */ funny */ */ text out= txt=This /* is */ some /* /* /* */ funny */ */ text delim-count=0 hdtxt= hi resttxt=s /* is */ some /* /* /* */ funny */ */ text out= T txt=his /* is */ some /* /* /* */ funny */ */ text delim-count=0 hdtxt= is resttxt= /* is */ some /* /* /* */ funny */ */ text out= Th txt=is /* is */ some /* /* /* */ funny */ */ text delim-count=0 hdtxt= s resttxt=/* is */ some /* /* /* */ funny */ */ text out= Thi txt=s /* is */ some /* /* /* */ funny */ */ text delim-count=0 hdtxt= / resttxt=* is */ some /* /* /* */ funny */ */ text out= This txt= /* is */ some /* /* /* */ funny */ */ text delim-count=0 hdtxt= /* resttxt= is */ some /* /* /* */ funny */ */ text out= This txt=/* is */ some /* /* /* */ funny */ */ text delim-count=0 hdtxt= i resttxt=s */ some /* /* /* */ funny */ */ text out= This txt= is */ some /* /* /* */ funny */ */ text delim-count=1 hdtxt= is resttxt= */ some /* /* /* */ funny */ */ text out= This txt=is */ some /* /* /* */ funny */ */ text delim-count=1 hdtxt= s resttxt=*/ some /* /* /* */ funny */ */ text out= This txt=s */ some /* /* /* */ funny */ */ text delim-count=1 hdtxt= * resttxt=/ some /* /* /* */ funny */ */ text out= This txt= */ some /* /* /* */ funny */ */ text delim-count=1 hdtxt= */ resttxt= some /* /* /* */ funny */ */ text out= This txt=*/ some /* /* /* */ funny */ */ text delim-count=1 hdtxt= s resttxt=ome /* /* /* */ funny */ */ text out= This txt= some /* /* /* */ funny */ */ text delim-count=0 hdtxt= so resttxt=me /* /* /* */ funny */ */ text out= This txt=some /* /* /* */ funny */ */ text delim-count=0 hdtxt= om resttxt=e /* /* /* */ funny */ */ text out= This s txt=ome /* /* /* */ funny */ */ text delim-count=0 hdtxt= me resttxt= /* /* /* */ funny */ */ text out=This so txt=me /* /* /* */ funny */ */ text delim-count=0 hdtxt= e resttxt=/* /* /* */ funny */ */ text out=This som txt=e /* /* /* */ funny */ */ text delim-count=0 hdtxt= / resttxt=* /* /* */ funny */ */ text out=This some txt= /* /* /* */ funny */ */ text delim-count=0 hdtxt= /* resttxt= /* /* */ funny */ */ text out=This some txt=/* /* /* */ funny */ */ text delim-count=0 hdtxt= / resttxt=* /* */ funny */ */ text out=This some txt= /* /* */ funny */ */ text delim-count=1 hdtxt= /* resttxt= /* */ funny */ */ text out=This some txt=/* /* */ funny */ */ text delim-count=1 hdtxt= / resttxt=* */ funny */ */ text out=This some txt= /* */ funny */ */ text delim-count=2 hdtxt= /* resttxt= */ funny */ */ text out=This some txt=/* */ funny */ */ text delim-count=2 hdtxt= * resttxt=/ funny */ */ text out=This some txt= */ funny */ */ text delim-count=3 hdtxt= */ resttxt= funny */ */ text out=This some txt=*/ funny */ */ text delim-count=3 hdtxt= f resttxt=unny */ */ text out=This some txt= funny */ */ text delim-count=2 hdtxt= fu resttxt=nny */ */ text out=This some txt=funny */ */ text delim-count=2 hdtxt= un resttxt=ny */ */ text out=This some txt= unny */ */ text delim-count=2 hdtxt= nn resttxt=y */ */ text out=This some txt= nny */ */ text delim-count=2 hdtxt= ny resttxt= */ */ text out=This some txt= ny */ */ text delim-count=2 hdtxt= y resttxt=*/ */ text out=This some txt= y */ */ text delim-count=2 hdtxt= * resttxt=/ */ text out=This some txt= */ */ text delim-count=2 hdtxt= */ resttxt= */ text out=This some txt= */ */ text delim-count=2 hdtxt= * resttxt= / text out=This some txt= */ text delim-count=1 hdtxt= */ resttxt= text out=This some txt= */ text delim-count=1 hdtxt= t resttxt= ext out=This some txt= text delim-count=0 hdtxt= te resttxt= xt out=This some txt= text delim-count=0 hdtxt= ex resttxt= t out=This some t txt= ext delim-count=0 hdtxt= xt resttxt= out=This some te txt= xt delim-count=0 hdtxt= t resttxt= out=This some tex txt= t delim-count=0 hdtxt= resttxt= out=This some text txt= delim-count=0 "This some text"
D
<lang d>import std.stdio ; import std.regexp, std.algorithm ;
string[] sepComment(string s, string cpat[] ...) {
assert(cpat.length == 2,
"sepComment : 2 pattern arguments for comment begin & end") ;
string[] res = new string[](2) ;
int p = 0, q = 0 /* cursors */, ic = 0 ; // inside comment?
int[] plen = new int[](2) ; // this's for handling /*/
bool advCursor() {
auto m = std.regexp.search(s[p..$], cpat[ic]) ;
if(m is null) return false ;
plen[ic] = max(0, plen[ic], m[0].length) ;
q = p + m.pre.length ; // got comment head
if(ic) { q += m[0].length ; } // or comment tail
if(std.regexp.find(m[0], "\n|\r") != -1) // special adjust for \n\r
q-- ;
return true ;
}
while(true) {
if(!advCursor()) break ;
res[ic] ~= s[p..q] ; // save slice of result
if( ic && (q - p < plen[0] + plen[1])) { // this handle /*/ pattern
p = q ;
if(!advCursor()) break ;
res[ic] ~= s[p..q] ; // save result again
}
p = q ; // advance cursor
ic = 1 - ic ; // toggle search type
}
if(ic)
throw new Exception("Mismatched Comment") ;
res[ic] ~= s[p..$] ; // save rest(non-comment)
return res ;
}
void main() {
string s = ` /**
* Some comments
* longer comments here that we can parse.
*
* Rahoo
*/
function subroutine() {
a = /* inline comment */ b + c ;
}
/*/ <-- tricky comments */
/**
* Another comment.
*/
function something() {
}` ;
writefln("==original:\n%s", s) ;
auto t = sepComment(s, `/\*`, `\*/`) ;
writefln("==comment stripped:\n%s\n==stripped comment:\n%s", t[0], t[1]) ;
s = "apples, pears # and bananas
apples, pears ; and bananas " ; // test for line comment
writefln("==original:\n%s", s) ;
t = sepComment(s, `#|;`, `[\n\r]|$`) ;
writefln("==comment stripped:\n%s\n==stripped comment:\n%s", t[0], t[1]) ;
}</lang> part of output:
==comment stripped:
function subroutine() {
a = b + c ;
}
function something() {
}
==stripped comment:
/**
* Some comments
* longer comments here that we can parse.
*
* Rahoo
*//* inline comment *//*/ <-- tricky comments *//**
* Another comment.
*/
Go
For the extra credit: No optional parameters in Go, but documented below is an efficient technique for letting the caller specify the delimiters. <lang go>package main
import (
"fmt" "strings"
)
// idiomatic to name a function newX that allocates an object, initializes it, // and returns it ready to use. the object in this case is a closure. func newStripper(start, end string) func(string) string {
// default to c-style block comments
if start == "" || end == "" {
start, end = "/*", "*/"
}
// closes on variables start, end.
return func(source string) string {
for {
cs := strings.Index(source, start)
if cs < 0 {
break
}
ce := strings.Index(source[cs+2:], end)
if ce < 0 {
break
}
source = source[:cs] + source[cs+ce+4:]
}
return source
}
}
func main() {
// idiomatic is that zero values indicate to use meaningful defaults
stripC := newStripper("", "")
// strip function now defined and can be called any number of times
// without respecifying delimiters
fmt.Println(stripC(` /**
* Some comments
* longer comments here that we can parse.
*
* Rahoo
*/
function subroutine() {
a = /* inline comment */ b + c ;
}
/*/ <-- tricky comments */
/**
* Another comment.
*/
function something() {
}`))
}</lang>
Groovy
<lang groovy>def code = """
/**
* Some comments
* longer comments here that we can parse.
*
* Rahoo
*/
function subroutine() {
a = /* inline comment */ b + c ;
}
/*/ <-- tricky comments */
/**
* Another comment.
*/
function something() {
}
"""
println ((code =~ "(?:/\\*(?:[^*]|(?:\\*+[^*/]))*\\*+/)|(?://.*)").replaceAll())</lang>
Haskell
Comment delimiters can be changed by calling stripComments with different start and end parameters. <lang Haskell>import Data.List
stripComments :: String -> String -> String -> String stripComments start end = notComment
where notComment :: String -> String
notComment "" = ""
notComment xs
| start `isPrefixOf` xs = inComment $ drop (length start) xs
| otherwise = head xs:(notComment $ tail xs)
inComment :: String -> String
inComment "" = ""
inComment xs
| end `isPrefixOf` xs = notComment $ drop (length end) xs
| otherwise = inComment $ tail xs
main = interact (stripComments "/*" "*/")</lang> Output:
function subroutine() {
a = b + c ;
}
function something() {
}
Icon and Unicon
If one is willing to concede that the program file will fit in memory, then the following code works: <lang Icon>procedure main()
every (unstripped := "") ||:= !&input || "\n" # Load file as one string write(stripBlockComment(unstripped,"/*","*/"))
end
procedure stripBlockComment(s1,s2,s3) #: strip comments between s2-s3 from s1
result := ""
s1 ? {
while result ||:= tab(find(s2)) do {
move(*s2)
tab(find(s3)|0) # or end of string
move(*s3)
}
return result || tab(0)
}
end</lang> Otherwise, the following handles an arbitrary length input: <lang Icon>procedure main()
every writes(stripBlockComment(!&input,"/*","*/"))
end
procedure stripBlockComment(s,s2,s3)
static inC # non-null when inside comment
(s||"\n") ? while not pos(0) do {
if /inC then
if inC := 1(tab(find(s2))\1, move(*s2)) then suspend inC
else return tab(0)
else if (tab(find(s3))\1,move(*s3)) then inC := &null
else fail
}
end</lang>
J
<lang j>strip=:#~1 0 _1*./@:(|."0 1)2>4{"1(5;(0,"0~".;._2]0 :0);'/*'i.a.)&;:
1 0 0 0 2 0 2 3 2 0 2 2
)</lang> Example data: <lang j>example=: 0 :0
/**
* Some comments
* longer comments here that we can parse.
*
* Rahoo
*/
function subroutine() {
a = /* inline comment */ b + c ;
}
/*/ <-- tricky comments */
/**
* Another comment.
*/
function something() {
}
)</lang> Example use: <lang j> strip example
function subroutine() {
a = b + c ;
}
function something() {
}</lang>
Here is a version which allows the delimiters to be passed as an optional left argument as a pair of strings: <lang j>stripp=:3 :0
('/*';'*/') stripp y
'open close'=. x marks=. (+./(-i._1+#open,close)|."0 1 open E. y) - close E.&.|. y y #~ -. (+._1&|.) (1 <. 0 >. +)/\.&.|. marks
)</lang>
Java
<lang java>import java.io.*;
public class StripBlockComments{
public static String readFile(String filename) {
BufferedReader reader = new BufferedReader(new FileReader(filename)); try { StringBuilder fileContents = new StringBuilder(); char[] buffer = new char[4096]; while (reader.read(buffer, 0, 4096) > 0) { fileContents.append(buffer); } return fileContents.toString(); } finally { reader.close(); }
}
public static String stripComments(String beginToken, String endToken,
String input) { StringBuilder output = new StringBuilder(); while (true) { int begin = input.indexOf(beginToken); int end = input.indexOf(endToken, begin+beginToken.length()); if (begin == -1 || end == -1) { output.append(input); return output.toString(); } output.append(input.substring(0, begin)); input = input.substring(end + endToken.length()); }
}
public static void main(String[] args) {
if (args.length < 3) { System.out.println("Usage: BeginToken EndToken FileToProcess"); System.exit(1); }
String begin = args[0]; String end = args[1]; String input = args[2];
try { System.out.println(stripComments(begin, end, readFile(input))); } catch (Exception e) { e.printStackTrace(); System.exit(1); }
}
}</lang>
Liberty BASIC
<lang lb>global CRLF$ CRLF$ =chr$( 13) +chr$( 10)
sample$ =" /**"+CRLF$+_ " * Some comments"+CRLF$+_ " * longer comments here that we can parse."+CRLF$+_ " *"+CRLF$+_ " * Rahoo "+CRLF$+_ " */"+CRLF$+_ " function subroutine() {"+CRLF$+_ " a = /* inline comment */ b + c ;"+CRLF$+_ " }"+CRLF$+_ " /*/ <-- tricky comments */"+CRLF$+_ ""+CRLF$+_ " /**"+CRLF$+_ " * Another comment."+CRLF$+_ " */"+CRLF$+_ " function something() {"+CRLF$+_ " }"+CRLF$
startDelim$ ="/*" finishDelim$ ="*/"
print "________________________________" print sample$ print "________________________________" print blockStripped$( sample$, startDelim$, finishDelim$) print "________________________________"
end
function blockStripped$( in$, s$, f$)
for i =1 to len( in$) -len( s$)
if mid$( in$, i, len( s$)) =s$ then
i =i +len( s$)
do
if mid$( in$, i, 2) =CRLF$ then blockStripped$ =blockStripped$ +CRLF$
i =i +1
loop until ( mid$( in$, i, len( f$)) =f$) or ( i =len( in$) -len( f$))
i =i +len( f$) -1
else
blockStripped$ =blockStripped$ +mid$( in$, i, 1)
end if
next i
end function</lang>
function subroutine() {
a = b + c ;
}
function something() {
}
Lua
It is assumed, that the code is in the file "Text1.txt". <lang lua>filename = "Text1.txt"
fp = io.open( filename, "r" ) str = fp:read( "*all" ) fp:close()
stripped = string.gsub( str, "/%*.-%*/", "" ) print( stripped )</lang>
Mathematica
<lang Mathematica>StringReplace[a,"/*"~~Shortest[___]~~"*/" -> ""]
->
function subroutine() {
a = b + c ;
}
function something() {
}</lang>
MATLAB / Octave
<lang Matlab>function str = stripblockcomment(str,startmarker,endmarker)
while(1)
ix1 = strfind(str, startmarker);
if isempty(ix1) return; end;
ix2 = strfind(str(ix1+length(startmarker):end),endmarker);
if isempty(ix2)
str = str(1:ix1(1)-1);
return;
else
str = [str(1:ix1(1)-1),str(ix1(1)+ix2(1)+length(endmarker)+1:end)];
end;
end;
end;</lang> Output:
>>t = ' /**\n * Some comments\n * longer comments here that we can parse.\n *\n * Rahoo \n */\n function subroutine() {\n a = /* inline comment */ b + c ;\n }\n /*/ <-- tricky comments */\n\n /**\n * Another comment.\n */\n function something() {\n }\n'
>>printf(t);
>>printf('=============\n');
>>printf(stripblockcomment(t));
/**
* Some comments
* longer comments here that we can parse.
*
* Rahoo
*/
function subroutine() {
a = /* inline comment */ b + c ;
}
/*/ <-- tricky comments */
/**
* Another comment.
*/
function something() {
}
===============
function subroutine() {
a = b + c ;
}
function something() {
}
Perl
<lang Perl>#!/usr/bin/perl -w use strict ; use warnings ;
open( FH , "<" , "samplecode.txt" ) or die "Can't open file!$!\n" ; my $code = "" ; {
local $/ ; $code = <FH> ; #slurp mode
} close FH ; $code =~ s,/\*.*?\*/,,sg ; print $code . "\n" ;</lang> Output:
function subroutine() {
a = b + c ;
}
function something() {
}
Perl 6
<lang perl6>sample().split(/ '/*' .+? '*/' /).print;
sub sample { ' /**
* Some comments
* longer comments here that we can parse.
*
* Rahoo
*/
function subroutine() {
a = /* inline comment */ b + c ;
}
/*/ <-- tricky comments */
/**
* Another comment.
*/
function something() {
}
'}</lang> Output:
function subroutine() {
a = b + c ;
}
function something() {
}
PicoLisp
<lang PicoLisp>(in "sample.txt"
(while (echo "/*")
(out "/dev/null" (echo "*/")) ) )</lang>
Output:
function subroutine() {
a = b + c ;
}
function something() {
}
PL/I
<lang PL/I>/* A program to remove comments from text. */ strip: procedure options (main); /* 8/1/2011 */
declare text character (80) varying; declare (j, k) fixed binary;
on endfile (sysin) stop;
do forever;
get edit (text) (L);
do until (k = 0);
k = index(text, '/*');
if k > 0 then /* we have a start of comment. */
do;
/* Look for end of comment. */
j = index(text, '*/', k+2);
if j > 0 then
do;
text = substr(text, 1, k-1) ||
substr(text, j+2, length(text)-(j+2)+1);
end;
else
do; /* The comment continues onto the next line. */
put skip list ( substr(text, 1, k-1) );
more: get edit (text) (L);
j = index(text, '*/');
if j = 0 then do; put skip; go to more; end;
text = substr(text, j+2, length(text) - (j+2) + 1);
end;
end;
end;
put skip list (text);
end;
end strip;</lang>
PureBasic
Solution using regular expressions. A procedure to stripBlocks() procedure is defined that will strip comments between any two delimeters. <lang PureBasic>Procedure.s escapeChars(text.s)
Static specialChars.s = "[\^$.|?*+()"
Protected output.s, nextChar.s, i, countChar = Len(text)
For i = 1 To countChar
nextChar = Mid(text, i, 1)
If FindString(specialChars, nextChar, 1)
output + "\" + nextChar
Else
output + nextChar
EndIf
Next
ProcedureReturn output
EndProcedure
Procedure.s stripBlocks(text.s, first.s, last.s)
Protected delimter_1.s = escapeChars(first), delimter_2.s = escapeChars(last) Protected expNum = CreateRegularExpression(#PB_Any, delimter_1 + ".*?" + delimter_2, #PB_RegularExpression_DotAll) Protected output.s = ReplaceRegularExpression(expNum, text, "") FreeRegularExpression(expNum) ProcedureReturn output
EndProcedure
Define source.s source.s = " /**" + #CRLF$ source.s + " * Some comments" + #CRLF$ source.s + " * longer comments here that we can parse." + #CRLF$ source.s + " *" + #CRLF$ source.s + " * Rahoo " + #CRLF$ source.s + " */" + #CRLF$ source.s + " function subroutine() {" + #CRLF$ source.s + " a = /* inline comment */ b + c ;" + #CRLF$ source.s + " }" + #CRLF$ source.s + " /*/ <-- tricky comments */" + #CRLF$ source.s + "" + #CRLF$ source.s + " /**" + #CRLF$ source.s + " * Another comment." + #CRLF$ source.s + " */" + #CRLF$ source.s + " function something() {" + #CRLF$ source.s + " }" + #CRLF$
If OpenConsole()
PrintN("--- source ---")
PrintN(source)
PrintN("--- source with block comments between '/*' and '*/' removed ---")
PrintN(stripBlocks(source, "/*", "*/"))
PrintN("--- source with block comments between '*' and '*' removed ---")
PrintN(stripBlocks(source, "*", "*"))
Print(#CRLF$ + #CRLF$ + "Press ENTER to exit"): Input()
CloseConsole()
EndIf</lang> Sample output:
--- source ---
/**
* Some comments
* longer comments here that we can parse.
*
* Rahoo
*/
function subroutine() {
a = /* inline comment */ b + c ;
}
/*/ <-- tricky comments */
/**
* Another comment.
*/
function something() {
}
--- source with block comments between '/*' and '*/' removed ---
function subroutine() {
a = b + c ;
}
function something() {
}
--- source with block comments between '*' and '*' removed ---
/
longer comments here that we can parse.
Rahoo
inline comment / <-- tricky comments Another comment.
*/
function something() {
}
Python
The code has comment delimeters as an argument and will also strip nested block comments. <lang python>def _commentstripper(txt, delim):
'Strips first nest of block comments'
deliml, delimr = delim
out =
if deliml in txt:
indx = txt.index(deliml)
out += txt[:indx]
txt = txt[indx+len(deliml):]
txt = _commentstripper(txt, delim)
assert delimr in txt, 'Cannot find closing comment delimiter in ' + txt
indx = txt.index(delimr)
out += txt[(indx+len(delimr)):]
else:
out = txt
return out
def commentstripper(txt, delim=('/*', '*/')):
'Strips nests of block comments'
deliml, delimr = delim
while deliml in txt:
txt = _commentstripper(txt, delim)
return txt</lang>
- Tests and sample output
<lang python>def test():
print('\nNON-NESTED BLOCK COMMENT EXAMPLE:')
sample = /**
* Some comments
* longer comments here that we can parse.
*
* Rahoo
*/
function subroutine() {
a = /* inline comment */ b + c ;
}
/*/ <-- tricky comments */
/**
* Another comment.
*/
function something() {
}
print(commentstripper(sample))
print('\nNESTED BLOCK COMMENT EXAMPLE:')
sample = /**
* Some comments
* longer comments here that we can parse.
*
* Rahoo
*//*
function subroutine() {
a = /* inline comment */ b + c ;
}
/*/ <-- tricky comments */
*/
/**
* Another comment.
*/
function something() {
}
print(commentstripper(sample))
if __name__ == '__main__':
test()</lang>
NON-NESTED BLOCK COMMENT EXAMPLE:
function subroutine() {
a = b + c ;
}
function something() {
}
NESTED BLOCK COMMENT EXAMPLE:
function something() {
}
Ruby
<lang ruby>def remove_comments!(str, comment_start='/*', comment_end='*/')
while start_idx = str.index(comment_start) end_idx = str.index(comment_end, start_idx + comment_start.length) + comment_end.length - 1 str[start_idx .. end_idx] = "" end str
end
def remove_comments(str, comment_start='/*', comment_end='*/')
remove_comments!(str.dup, comment_start, comment_end)
end
example = <<END_OF_STRING
/**
* Some comments
* longer comments here that we can parse.
*
* Rahoo
*/
function subroutine() {
a = /* inline comment */ b + c ;
}
/*/ <-- tricky comments */
/**
* Another comment.
*/
function something() {
}
END_OF_STRING
puts remove_comments example</lang> outputs
function subroutine() {
a = b + c ;
}
function something() {
}
Seed7
The function replace2 can be used to replace unnested comments.
<lang seed7>$ include "seed7_05.s7i";
const proc: main is func
local
const string: stri is "\
\ /**\n\
\ * Some comments\n\
\ * longer comments here that we can parse.\n\
\ *\n\
\ * Rahoo\n\
\ */\n\
\ function subroutine() {\n\
\ a = /* inline comment */ b + c ;\n\
\ }\n\
\ /*/ <-- tricky comments */\n\
\\n\
\ /**\n\
\ * Another comment.\n\
\ */\n\
\ function something() {\n\
\ }";
begin
writeln(replace2(stri, "/*", "*/", " "));
end func;</lang>
Output:
function subroutine() {
a = b + c ;
}
function something() {
}
Tcl
<lang tcl>proc stripBlockComment {string {openDelimiter "/*"} {closeDelimiter "*/"}} {
# Convert the delimiters to REs by backslashing all non-alnum characters
set openAsRE [regsub -all {\W} $openDelimiter {\\&}]
set closeAsRE [regsub -all {\W} $closeDelimiter {\\&}]
# Now remove the blocks using a dynamic non-greedy regular expression regsub -all "$openAsRE.*?$closeAsRE" $string ""
}</lang> Demonstration code: <lang tcl>puts [stripBlockComment " /**
* Some comments
* longer comments here that we can parse.
*
* Rahoo
*/
function subroutine() {
a = /* inline comment */ b + c ;
}
/*/ <-- tricky comments */
/**
* Another comment.
*/
function something() {
}
"]</lang> Output:
function subroutine() {
a = b + c ;
}
function something() {
}