This commit is contained in:
Ingy döt Net 2013-04-10 21:29:02 -07:00
parent 764da6cbbb
commit db842d013d
19005 changed files with 197040 additions and 7 deletions

View file

@ -0,0 +1,9 @@
It is often necessary to split a string into pieces based on several different (potentially multi-character) separator strings, while still retaining the information about which separators were present in the input. This is particularly useful when doing small parsing tasks. The task is to write code to demonstrate this.
The function (or procedure or method, as appropriate) should take an input string and an ordered collection of separators. The order of the separators is significant: The delimiter order represents priority in matching, with the first defined delimiter having the highest priority. In cases where there would be an ambiguity as to which separator to use at a particular point (e.g., because one separator is a prefix of another) the separator with the highest priority should be used. Delimiters can be reused and the output from the function should be an ordered sequence of substrings.
Test your code using the input string “<code>a!===b=!=c</code>” and the separators “<code>==</code>”, “<code>!=</code>” and “<code>=</code>”.
For these inputs the string should be parsed as <code>"a" (!=) "" (==) "b" (=) "" (!=) "c"</code>, where matched delimiters are shown in parentheses, and separated strings are quoted, so our resulting output is <code>"a", empty string, "b", empty string, "c"</code>. Note that the quotation marks are shown for clarity and do not form part of the output.
'''Extra Credit:''' provide information that indicates which separator was matched at each separation point and where in the input string that separator was matched.

View file

@ -0,0 +1,81 @@
with Ada.Containers.Indefinite_Doubly_Linked_Lists;
with Ada.Text_IO;
procedure Multisplit is
package String_Lists is new Ada.Containers.Indefinite_Doubly_Linked_Lists
(Element_Type => String);
use type String_Lists.Cursor;
function Split
(Source : String;
Separators : String_Lists.List)
return String_Lists.List
is
Result : String_Lists.List;
Next_Position : Natural := Source'First;
Prev_Position : Natural := Source'First;
Separator_Position : String_Lists.Cursor;
Separator_Length : Natural;
Changed : Boolean;
begin
loop
Changed := False;
Separator_Position := Separators.First;
while Separator_Position /= String_Lists.No_Element loop
Separator_Length :=
String_Lists.Element (Separator_Position)'Length;
if Next_Position + Separator_Length - 1 <= Source'Last
and then Source
(Next_Position .. Next_Position + Separator_Length - 1) =
String_Lists.Element (Separator_Position)
then
if Next_Position > Prev_Position then
Result.Append
(Source (Prev_Position .. Next_Position - 1));
end if;
Result.Append (String_Lists.Element (Separator_Position));
Next_Position := Next_Position + Separator_Length;
Prev_Position := Next_Position;
Changed := True;
exit;
end if;
Separator_Position := String_Lists.Next (Separator_Position);
end loop;
if not Changed then
Next_Position := Next_Position + 1;
end if;
if Next_Position > Source'Last then
Result.Append (Source (Prev_Position .. Source'Last));
exit;
end if;
end loop;
return Result;
end Split;
Test_Input : constant String := "a!===b=!=c";
Test_Separators : String_Lists.List;
Test_Result : String_Lists.List;
Pos : String_Lists.Cursor;
begin
Test_Separators.Append ("==");
Test_Separators.Append ("!=");
Test_Separators.Append ("=");
Test_Result := Split (Test_Input, Test_Separators);
Pos := Test_Result.First;
while Pos /= String_Lists.No_Element loop
Ada.Text_IO.Put (" " & String_Lists.Element (Pos));
Pos := String_Lists.Next (Pos);
end loop;
Ada.Text_IO.New_Line;
-- other order of separators
Test_Separators.Clear;
Test_Separators.Append ("=");
Test_Separators.Append ("!=");
Test_Separators.Append ("==");
Test_Result := Split (Test_Input, Test_Separators);
Pos := Test_Result.First;
while Pos /= String_Lists.No_Element loop
Ada.Text_IO.Put (" " & String_Lists.Element (Pos));
Pos := String_Lists.Next (Pos);
end loop;
end Multisplit;

View file

@ -0,0 +1,24 @@
DIM sep$(2)
sep$() = "==", "!=", "="
PRINT "String splits into:"
PRINT FNmultisplit("a!===b=!=c", sep$(), FALSE)
PRINT "For extra credit:"
PRINT FNmultisplit("a!===b=!=c", sep$(), TRUE)
END
DEF FNmultisplit(s$, d$(), info%)
LOCAL d%, i%, j%, m%, p%, o$
p% = 1
REPEAT
m% = LEN(s$)
FOR i% = 0 TO DIM(d$(),1)
d% = INSTR(s$, d$(i%), p%)
IF d% IF d% < m% m% = d% : j% = i%
NEXT
IF m% < LEN(s$) THEN
o$ += """" + MID$(s$, p%, m%-p%) + """"
IF info% o$ += " (" + d$(j%) + ") " ELSE o$ += ", "
p% = m% + LEN(d$(j%))
ENDIF
UNTIL m% = LEN(s$)
= o$ + """" + MID$(s$, p%) + """"

View file

@ -0,0 +1,18 @@
( ( oneOf
= operator
. !arg:%?operator ?arg
& ( @(!sjt:!operator ?arg)&(!operator.!arg)
| oneOf$!arg
)
)
& "a!===b=!=c":?unparsed
& "==" "!=" "=":?operators
& whl
' ( @( !unparsed
: ?nonOp [%(oneOf$!operators:(?operator.?unparsed))
)
& put$(!nonOp str$("{" !operator "} "))
)
& put$!unparsed
& put$\n
);

View file

@ -0,0 +1,19 @@
#include <iostream>
#include <boost/tokenizer.hpp>
#include <string>
int main( ) {
std::string str( "a!===b=!=c" ) , output ;
typedef boost::tokenizer<boost::char_separator<char> > tokenizer ;
boost::char_separator<char> separator ( "==" , "!=" ) , sep ( "!" ) ;
tokenizer mytok( str , separator ) ;
tokenizer::iterator tok_iter = mytok.begin( ) ;
for ( ; tok_iter != mytok.end( ) ; ++tok_iter )
output.append( *tok_iter ) ;
tokenizer nexttok ( output , sep ) ;
for ( tok_iter = nexttok.begin( ) ; tok_iter != nexttok.end( ) ;
++tok_iter )
std::cout << *tok_iter << " " ;
std::cout << '\n' ;
return 0 ;
}

View file

@ -0,0 +1,57 @@
using System;
using System.Collections.Generic;
using System.Linq;
using System.Text;
namespace Multisplit
{
internal static class Program
{
private static void Main(string[] args)
{
foreach (var s in "a!===b=!=c".Multisplit(true, "==", "!=", "=")) // Split the string and return the separators.
{
Console.Write(s); // Write the returned substrings and separators to the console.
}
Console.WriteLine();
}
private static IEnumerable<string> Multisplit(this string s, bool returnSeparators = false,
params string[] delimiters)
{
var currentString = new StringBuilder(); /* Initiate the StringBuilder. This will hold the current string to return
* once we find a separator. */
int index = 0; // Initiate the index counter at 0. This tells us our current position in the string to read.
while (index < s.Length) // Loop through the string.
{
// This will get the highest priority separator found at the current index, or null if there are none.
string foundDelimiter =
(from delimiter in delimiters
where s.Length >= index + delimiter.Length &&
s.Substring(index, delimiter.Length) == delimiter
select delimiter).FirstOrDefault();
if (foundDelimiter != null)
{
yield return currentString.ToString(); // Return the current string.
if (returnSeparators) // Return the separator, if the user specified to do so.
yield return
string.Format("{{\"{0}\", ({1}, {2})}}",
foundDelimiter,
index, index + foundDelimiter.Length);
currentString.Clear(); // Clear the current string.
index += foundDelimiter.Length; // Move the index past the current separator.
}
else
{
currentString.Append(s[index++]); // Add the character at this index to the current string.
}
}
if (currentString.Length > 0)
yield return currentString.ToString(); // If we have anything left over, return it.
}
}
}

View file

@ -0,0 +1,24 @@
#include <stdio.h>
#include <string.h>
void parse_sep(const char *str, const char *const *pat, int len)
{
int i, slen;
while (*str != '\0') {
for (i = 0; i < len || !putchar(*(str++)); i++) {
slen = strlen(pat[i]);
if (strncmp(str, pat[i], slen)) continue;
printf("{%.*s}", slen, str);
str += slen;
break;
}
}
}
int main()
{
const char *seps[] = { "==", "!=", "=" };
parse_sep("a!===b=!=c", seps, 3);
return 0;
}

View file

@ -0,0 +1 @@
a{!=}{==}b{=}{!=}c

View file

@ -0,0 +1,30 @@
multi_split = (text, separators) ->
# Split text up, using separators to break up text and discarding
# separators.
#
# Returns an array of strings, which can include empty strings when
# separators are found either adjacent to each other or at the
# beginning/end of the text.
#
# Separators have precedence, according to their order in the array,
# and each separator should be at least one character long.
result = []
i = 0
s = ''
while i < text.length
found = false
for separator in separators
if text.substring(i, i + separator.length) == separator
found = true
i += separator.length
result.push s
s = ''
break
if !found
s += text[i]
i += 1
result.push s
result
console.log multi_split 'a!===b=!=c', ['==', '!=', '='] # [ 'a', '', 'b', '', 'c' ]
console.log multi_split '', ['whatever'] # [ '' ]

View file

@ -0,0 +1,38 @@
import std.stdio, std.array, std.algorithm;
string[] multiSplit(in string s, in string[] divisors)
/*pure nothrow*/ {
string[] result;
auto rest = s.idup;
while (true) {
bool done = true;
string delim;
{
string best;
foreach (div; divisors) {
const maybe = find(rest, div);
if (maybe.length > best.length) {
best = maybe;
delim = div;
done = false;
}
}
}
result.length++;
if (done) {
result[$ - 1] = rest.idup;
return result;
} else {
const t = findSplit(rest, delim);
result[$ - 1] = t[0].idup;
rest = t[2];
}
}
}
void main() {
immutable s = "a!===b=!=c";
immutable divs = ["==", "!=", "="];
writeln(multiSplit(s, divs).join(" {} "));
}

View file

@ -0,0 +1,26 @@
package main
import (
"fmt"
"strings"
)
func ms(txt string, sep []string) (ans []string) {
for txt > "" {
sepMatch := ""
posMatch := len(txt)
for _, s := range sep {
if p := strings.Index(txt, s); p >= 0 && p < posMatch {
sepMatch = s
posMatch = p
}
}
ans = append(ans, txt[:posMatch])
txt = txt[posMatch+len(sepMatch):]
}
return
}
func main() {
fmt.Printf("%q\n", ms("a!===b=!=c", []string{"==", "!=", "="}))
}

View file

@ -0,0 +1,21 @@
procedure main()
s := "a!===b=!=c"
# just list the tokens
every writes(multisplit(s,["==", "!=", "="])," ") | write()
# list tokens and indices
every ((p := "") ||:= t := multisplit(s,sep := ["==", "!=", "="])) | break write() do
if t == !sep then writes(t," (",*p+1-*t,") ") else writes(t," ")
end
procedure multisplit(s,L)
s ? while not pos(0) do {
t := =!L | 1( arb(), match(!L)|pos(0) )
suspend t
}
end
procedure arb()
suspend .&subject[.&pos:&pos <- &pos to *&subject + 1]
end

View file

@ -0,0 +1,12 @@
multisplit=:4 :0
'sep begin'=.|:t=. y /:~&.:(|."1)@;@(i.@#@[ ,.L:0"0 I.@E.L:0) x
end=. begin + sep { #@>y
last=.next=.0
r=.2 0$0
while.next<#begin do.
r=.r,.(last}.x{.~next{begin);next{t
last=.next{end
next=.1 i.~(begin>next{begin)*.begin>:last
end.
r=.r,.'';~last}.x
)

View file

@ -0,0 +1,19 @@
S=:'a!===b=!=c'
S multisplit '==';'!=';'='
┌───┬───┬───┬───┬─┐
│a │ │b │ │c│
├───┼───┼───┼───┼─┤
│1 1│0 3│2 6│1 7│ │
└───┴───┴───┴───┴─┘
S multisplit '=';'!=';'=='
┌───┬───┬───┬───┬───┬─┐
│a │ │ │b │ │c│
├───┼───┼───┼───┼───┼─┤
│1 1│0 3│0 4│0 6│1 7│ │
└───┴───┴───┴───┴───┴─┘
'X123Y' multisplit '1';'12';'123';'23';'3'
┌───┬───┬─┐
│X │ │Y│
├───┼───┼─┤
│0 1│3 2│ │
└───┴───┴─┘

View file

@ -0,0 +1,8 @@
RegExp.escape = function(text) {
return text.replace(/[-[\]{}()*+?.,\\^$|#\s]/g, "\\$&");
}
multisplit = function(string, seps) {
var sep_regex = RegExp(_.map(seps, function(sep) { return RegExp.escape(sep); }).join('|'));
return string.split(sep_regex);
}

View file

@ -0,0 +1 @@
StringSplit["a!===b=!=c", {"==", "!=", "="}]

View file

@ -0,0 +1,11 @@
#!/usr/bin/perl -w
use strict ;
sub multisplit {
my ( $string , $pattern ) = @_ ;
split( /($pattern)/, $string, -1 ) ;
}
my $phrase = "a!===b=!=c" ;
my $pattern = "==|!=|=" ;
print "$_ ," foreach multisplit( $phrase , $pattern ) ;
print "\n" ;

View file

@ -0,0 +1,19 @@
(de multisplit (Str Sep)
(setq Sep (mapcar chop Sep))
(make
(for (S (chop Str) S)
(let L
(make
(loop
(T (find head Sep (circ S))
(link
(list
(- (length Str) (length S))
(pack (cut (length @) 'S)) ) ) )
(link (pop 'S))
(NIL S (link NIL)) ) )
(link (pack (cdr (rot L))))
(and (car L) (link @)) ) ) ) )
(println (multisplit "a!===b=!=c" '("==" "!=" "=")))
(println (multisplit "a!===b=!=c" '("=" "!=" "==")))

View file

@ -0,0 +1,40 @@
multisplit(_LSep, '') -->
{!},
[].
multisplit(LSep, T) -->
{next_sep(LSep, T, [], Token, Sep, T1)},
( {Token \= '' },[Token], {!}; []),
( {Sep \= '' },[Sep], {!}; []),
multisplit(LSep, T1).
next_sep([], T, Lst, Token, Sep, T1) :-
% if we can't find any separator, the game is over
( Lst = [] ->
Token = T, Sep = '', T1 = '';
% we sort the list to get nearest longest separator
predsort(my_sort, Lst, [(_,_, Sep)|_]),
atomic_list_concat([Token|_], Sep, T),
atom_concat(Token, Sep, Tmp),
atom_concat(Tmp, T1, T)).
next_sep([HSep|TSep], T, Lst, Token, Sep, T1) :-
sub_atom(T, Before, Len, _, HSep),
next_sep(TSep, T, [(Before, Len,HSep) | Lst], Token, Sep, T1).
next_sep([_HSep|TSep], T, Lst, Token, Sep, T1) :-
next_sep(TSep, T, Lst, Token, Sep, T1).
my_sort(<, (N1, _, _), (N2, _, _)) :-
N1 < N2.
my_sort(>, (N1, _, _), (N2, _, _)) :-
N1 > N2.
my_sort(>, (N, N1, _), (N, N2, _)) :-
N1 < N2.
my_sort(<, (N, N1, _), (N, N2, _)) :-
N1 > N2.

View file

@ -0,0 +1,15 @@
>>> import re
>>> def ms2(txt="a!===b=!=c", sep=["==", "!=", "="]):
if not txt or not sep:
return []
ans = m = []
for m in re.finditer('(.*?)(?:' + '|'.join('('+re.escape(s)+')' for s in sep) + ')', txt):
ans += [m.group(1), (m.lastindex-2, m.start(m.lastindex))]
if m and txt[m.end(m.lastindex):]:
ans += [txt[m.end(m.lastindex):]]
return ans
>>> ms2()
['a', (1, 1), '', (0, 3), 'b', (2, 6), '', (1, 7), 'c']
>>> ms2(txt="a!===b=!=c", sep=["=", "!=", "=="])
['a', (1, 1), '', (0, 3), '', (0, 4), 'b', (0, 6), '', (1, 7), 'c']

View file

@ -0,0 +1,24 @@
>>> def ms(txt="a!===b=!=c", sep=["==", "!=", "="]):
if not txt or not sep:
return []
size = [len(s) for s in sep]
ans, pos0 = [], 0
def getfinds():
return [(-txt.find(s, pos0), -sepnum, size[sepnum])
for sepnum, s in enumerate(sep)
if s in txt[pos0:]]
finds = getfinds()
while finds:
pos, snum, sz = max(finds)
pos, snum = -pos, -snum
ans += [ txt[pos0:pos], [snum, pos] ]
pos0 = pos+sz
finds = getfinds()
if txt[pos0:]: ans += [ txt[pos0:] ]
return ans
>>> ms()
['a', [1, 1], '', [0, 3], 'b', [2, 6], '', [1, 7], 'c']
>>> ms(txt="a!===b=!=c", sep=["=", "!=", "=="])
['a', [1, 1], '', [0, 3], '', [0, 4], 'b', [0, 6], '', [1, 7], 'c']

View file

@ -0,0 +1,67 @@
def min_pos(List):
return List.index(min(List))
def find_all(S, Sub, Start = 0, End = -1, IsOverlapped = 0):
Res = []
if End == -1:
End = len(S)
if IsOverlapped:
DeltaPos = 1
else:
DeltaPos = len(Sub)
Pos = Start
while True:
Pos = S.find(Sub, Pos, End)
if Pos == -1:
break
Res.append(Pos)
Pos += DeltaPos
return Res
def multisplit(S, SepList):
SepPosListList = []
SLen = len(S)
SepNumList = []
ListCount = 0
for i, Sep in enumerate(SepList):
SepPosList = find_all(S, Sep, 0, SLen, IsOverlapped = 1)
if SepPosList != []:
SepNumList.append(i)
SepPosListList.append(SepPosList)
ListCount += 1
if ListCount == 0:
return [S]
MinPosList = []
for i in range(ListCount):
MinPosList.append(SepPosListList[i][0])
SepEnd = 0
MinPosPos = min_pos(MinPosList)
Res = []
while True:
Res.append( S[SepEnd : MinPosList[MinPosPos]] )
Res.append([SepNumList[MinPosPos], MinPosList[MinPosPos]])
SepEnd = MinPosList[MinPosPos] + len(SepList[SepNumList[MinPosPos]])
while True:
MinPosPos = min_pos(MinPosList)
if MinPosList[MinPosPos] < SepEnd:
del SepPosListList[MinPosPos][0]
if len(SepPosListList[MinPosPos]) == 0:
del SepPosListList[MinPosPos]
del MinPosList[MinPosPos]
del SepNumList[MinPosPos]
ListCount -= 1
if ListCount == 0:
break
else:
MinPosList[MinPosPos] = SepPosListList[MinPosPos][0]
else:
break
if ListCount == 0:
break
Res.append(S[SepEnd:])
return Res
S = "a!===b=!=c"
multisplit(S, ["==", "!=", "="]) # output: ['a', [1, 1], '', [0, 3], 'b', [2, 6], '', [1, 7], 'c']
multisplit(S, ["=", "!=", "=="]) # output: ['a', [1, 1], '', [0, 3], '', [0, 4], 'b', [0, 6], '', [1, 7], 'c']

View file

@ -0,0 +1,26 @@
/*REXX program to split a string based on different separator strings. */
parse arg ? /*get string from command line. */
if ?=='' then ? = 'a!===b=!=c' /*None specified? Use default.*/
say 'old string='? /*echo the old string to screen. */
zz = '0'x /*null char, can be most anything*/
seps = '== != =' /*a list of seperaters to be used*/
do j=1 for words(seps) /*parse string with all the seps.*/
sep=word(seps,j) /*pick a separater to use now. */
do k=1 for length(sep) /*parse for various sep versions.*/
sep=strip(insert(zz,sep,k),,zz) /*allow imbedded "nulls" in sep. */
?=changestr(sep,?,zz) /* ··· but not trailing "nulls". */
do until ?==??; ??=? /*keep changing until no more chg*/
?=changestr(zz || zz, ?, zz) /*reduce replicated "nulls". */
end /*until···*/
sep=changestr(zz, sep, '') /*remove true nulls from the sep.*/
end /*k*/
end /*j*/
showNull = ' {} ' /*one last change, allow the ... */
?=changestr(zz,?,showNull) /*showing of "null" characters. */
say 'new string='? /*now, show and tell time. */
/*stick a fork in it, we're done.*/

View file

@ -0,0 +1,14 @@
text = 'a!===b=!=c'
separators = ['==', '!=', '=']
def multisplit_simple(text, separators)
sep_regex = Regexp.new(separators.collect {|sep| Regexp.escape(sep)}.join('|'))
text.split(sep_regex)
end
p multisplit_simple(text, separators)
["a", "", "b", "", "c"]
=> nil
p multisplit_simple(text, ['=', '!=', '=='])
["a", "", "", "b", "", "c"]
=> nil

View file

@ -0,0 +1,18 @@
def multisplit(text, separators)
sep_regex = Regexp.new(separators.collect {|sep| Regexp.escape(sep)}.join('|'))
separator_info = []
pieces = []
i = prev = 0
while i = text.index(sep_regex, i)
separator = Regexp.last_match(0)
pieces << text[prev .. i-1]
separator_info << [separator, i]
i = i + separator.length
prev = i
end
pieces << text[prev .. -1]
[pieces, separator_info]
end
p multisplit(text, separators)
# => [["a", "", "b", "", "c"], [["!=", 1], ["==", 3], ["=", 6], ["!=", 7]]]

View file

@ -0,0 +1,7 @@
def multisplit_rejoin(info)
str = info[0].zip(info[1])[0..-2].inject("") {|str, (piece, (sep, idx))| str << piece << sep}
str << info[0].last
end
p multisplit_rejoin(multisplit(text, separators)) == text
# => true

View file

@ -0,0 +1,16 @@
import scala.annotation.tailrec
def multiSplit(str:String, sep:Seq[String])={
def findSep(index:Int)=sep find (str startsWith (_, index))
@tailrec def nextSep(index:Int):(Int,Int)=
if(index>str.size) (index, 0) else findSep(index) match {
case Some(sep) => (index, sep.size)
case _ => nextSep(index + 1)
}
def getParts(start:Int, pos:(Int,Int)):List[String]={
val part=str slice (start, pos._1)
if(pos._2==0) List(part) else part :: getParts(pos._1+pos._2, nextSep(pos._1+pos._2))
}
getParts(0, nextSep(0))
}
println(multiSplit("a!===b=!=c", Seq("!=", "==", "=")))

View file

@ -0,0 +1,5 @@
proc simplemultisplit {text sep} {
set map {}; foreach s $sep {lappend map $s "\uffff"}
return [split [string map $map $text] "\uffff"]
}
puts [simplemultisplit "a!===b=!=c" {"==" "!=" "="}]

View file

@ -0,0 +1,14 @@
proc multisplit {text sep} {
foreach s $sep {lappend sr [regsub -all {\W} $s {\\&}]}
set sepRE [join $sr "|"]
set pieces {}
set match {}
set start 0
while {[regexp -indices -start $start -- $sepRE $text found]} {
lassign $found x y
lappend pieces [string range $text $start [expr {$x-1}]]
lappend match [lsearch -exact $sep [string range $text {*}$found]] $x
set start [expr {$y + 1}]
}
return [list [lappend pieces [string range $text $start end]] $match]
}

View file

@ -0,0 +1,5 @@
set input "a!===b=!=c"
set matchers {"==" "!=" "="}
lassign [multisplit $input $matchers] substrings matchinfo
puts $substrings
puts $matchinfo