XXXX redacted: Difference between revisions
m
→{{header|Wren}}: Minor tidy
m (→{{header|Phix}}: added utf32_length()) |
m (→{{header|Wren}}: Minor tidy) |
||
| (32 intermediate revisions by 14 users not shown) | |||
Line 60:
Redact '👨👩👦' [w] 🧑 👨 🧔 X
{{Template:Strings}}
<br><br>
=={{header|Ada}}==
<syntaxhighlight lang="ada">
-- Redact text
-- J. Carter 2023 Apr
with Ada.Characters.Handling;
with Ada.Containers.Vectors;
with Ada.Strings.Fixed;
with Ada.Strings.Unbounded;
with Ada.Text_IO;
procedure Redact is
use Ada.Strings.Unbounded;
package Field_Lists is new Ada.Containers.Vectors (Index_Type => Positive, Element_Type => Unbounded_String);
function Parsed (Line : String) return Field_Lists.Vector;
-- Presumes that Line consists of fields speparated by 1 or more spaces (' ')
-- Returns a list of the parsed fields
function Redact (Word : in Field_Lists.Vector;
Pattern : in String;
Whole_Word : in Boolean;
Case_Sensitive : in Boolean;
Overkill : in Boolean)
return String;
-- Redacts the words or parts of words in Word containing Pattern
-- If Whole_Word, the entire word must match Pattern, and Overkill is ignored
-- Case_Sensitive determines whether or not the match is case sensitive
-- Overkill means the entire word is redacted even if only a part matches
function Parsed (Line : String) return Field_Lists.Vector is
Result : Field_Lists.Vector;
Start : Natural := Line'First;
Stop : Natural;
begin -- Parsed
All_Fields : loop
Start := Ada.Strings.Fixed.Index_Non_Blank (Line (Start .. Line'Last) );
exit All_Fields when Start = 0;
Stop := Ada.Strings.Fixed.Index (Line (Start .. Line'Last), " ");
if Stop = 0 then
Stop := Line'Last + 1;
end if;
Result.Append (New_Item => To_Unbounded_String (Line (Start .. Stop - 1) ) );
Start := Stop + 1;
end loop All_Fields;
return Result;
end Parsed;
function Redact (Word : in Field_Lists.Vector;
Pattern : in String;
Whole_Word : in Boolean;
Case_Sensitive : in Boolean;
Overkill : in Boolean)
return String is
subtype Lower is Character range 'a' .. 'z';
subtype Upper is Character range 'A' .. 'Z';
Pat : constant String := (if Case_Sensitive then Pattern else Ada.Characters.Handling.To_Lower (Pattern) );
Result : Unbounded_String;
Start : Positive; -- Start of a word, ignoring initial punctuation
Stop : Positive; -- End of a word, ignoring terminal punctuation
First : Natural; -- Start of partial match
Last : Natural; -- End of partial match
begin -- Redact
All_Words : for I in 1 .. Word.Last_Index loop
One_Word : declare
Raw : String := To_String (Word.Element (I) );
Woid : String := (if Case_Sensitive then Raw else Ada.Characters.Handling.To_Lower (Raw) );
begin -- One_Word
Start := Woid'First; -- Ignore initial punctuation
Find_Start : loop
exit Find_Start when Woid (Start) in Lower | Upper;
Start := Start + 1;
end loop Find_Start;
Stop := Woid'Last; -- Ignore terminal punctuation
Find_Stop : loop
exit Find_Stop when Woid (Stop) in Lower | Upper;
Stop := Stop - 1;
end loop Find_Stop;
if Whole_Word then
if Woid (Start .. Stop) = Pat then
Raw (Start .. Stop) := (Start .. Stop => 'X');
end if;
else
Last := Start - 1;
All_Matches : loop -- Multiple matches are possible within a single word
First := Ada.Strings.Fixed.Index (Woid (Last + 1 .. Stop), Pat);
exit All_Matches when First = 0;
Last := (if Overkill then Stop else First + Pattern'Length - 1);
if Overkill then
First := Start;
end if;
Raw (First .. Last) := (First .. Last => 'X');
end loop All_Matches;
end if;
Append (Source => Result, New_Item => Raw & (if I = Word.Last_Index then "" else " ") );
end One_Word;
end loop All_Words;
return To_String (Result);
end Redact;
subtype Pattern_String is String (1 .. 3);
type Pattern_List is array (1 .. 2) of Pattern_String;
Pattern : constant Pattern_List := ("Tom", "tom");
Line : constant String := "Tom? Toms bottom tomato is in his stomach while playing the " & '"' & "Tom-tom" & '"' &
" brand tom-toms. That's so tom.";
Word : constant Field_Lists.Vector := Parsed (Line);
begin -- Redact
All_Patterns : for Pat of Pattern loop
Ada.Text_IO.Put_Line (Item => "Pattern: " & Pat);
Wholeness : for Whole in Boolean loop
Sensitivity : for Sense in Boolean loop
if Whole then
Ada.Text_IO.Put_Line (Item => 'W' & (if Sense then 'S' else 'I') & "N: " & Redact (Word, Pat, Whole, Sense, False) );
else
Overkill : for Over in Boolean loop
Ada.Text_IO.Put_Line (Item => (if Whole then 'W' else 'P') &
(if Sense then 'S' else 'I') &
(if Over then 'O' else 'N') & ": " &
Redact (Word, Pat, Whole, Sense, Over) );
end loop Overkill;
end if;
end loop Sensitivity;
end loop Wholeness;
end loop All_Patterns;
end Redact;
</syntaxhighlight>
{{out}}
<pre>
Pattern: Tom
PIN: XXX? XXXs botXXX XXXato is in his sXXXach while playing the "XXX-XXX" brand XXX-XXXs. That's so XXX.
PIO: XXX? XXXX XXXXXX XXXXXX is in his XXXXXXX while playing the "XXXXXXX" brand XXXXXXXX. That's so XXX.
PSN: XXX? XXXs bottom tomato is in his stomach while playing the "XXX-tom" brand tom-toms. That's so tom.
PSO: XXX? XXXX bottom tomato is in his stomach while playing the "XXXXXXX" brand tom-toms. That's so tom.
WIN: XXX? Toms bottom tomato is in his stomach while playing the "Tom-tom" brand tom-toms. That's so XXX.
WSN: XXX? Toms bottom tomato is in his stomach while playing the "Tom-tom" brand tom-toms. That's so tom.
Pattern: tom
PIN: XXX? XXXs botXXX XXXato is in his sXXXach while playing the "XXX-XXX" brand XXX-XXXs. That's so XXX.
PIO: XXX? XXXX XXXXXX XXXXXX is in his XXXXXXX while playing the "XXXXXXX" brand XXXXXXXX. That's so XXX.
PSN: Tom? Toms botXXX XXXato is in his sXXXach while playing the "Tom-XXX" brand XXX-XXXs. That's so XXX.
PSO: Tom? Toms XXXXXX XXXXXX is in his XXXXXXX while playing the "XXXXXXX" brand XXXXXXXX. That's so XXX.
WIN: XXX? Toms bottom tomato is in his stomach while playing the "Tom-tom" brand tom-toms. That's so XXX.
WSN: Tom? Toms bottom tomato is in his stomach while playing the "Tom-tom" brand tom-toms. That's so XXX.
</pre>
=={{header|AppleScript}}==
===ASObjC===
This uses ASObjC to access macOS's Foundation framework's regex and text-replacement methods. The methods support [https://unicode-org.github.io/icu/userguide/strings/regexp.html ICU]-compatible regular expressions.
<syntaxhighlight lang="applescript">use AppleScript version "2.4" -- OS X 10.10 (Yosemite) or later
use framework "Foundation"
use scripting additions
on redact(theText, redactionTargets, options)
set |⌘| to current application
-- Set up a regex search pattern for the target or list of targets supplied.
-- Since it has to be able to match grapheme characters which may be combinations of
-- others in the same string, include catches for "Zero Width Joiner" characters.
set targets to |⌘|'s class "NSMutableArray"'s arrayWithArray:(redactionTargets as list)
repeat with thisTarget in targets
set thisTarget's contents to (|⌘|'s class "NSRegularExpression"'s escapedPatternForString:(thisTarget))
end repeat
set targetPattern to "(?<!\\u200d)(?:" & (targets's componentsJoinedByString:("|")) & ")(?!\\u200d)"
-- If necessary, modify the pattern according to the requested options. Only "w", "o", "i", and "s" need attention.
if (options contains "w") then
-- Don't match where preceded or followed by either a hyphen or anything which isn't punctuation or white space.
set targetPattern to "(?<![-[^[:punct:]\\s]])" & targetPattern & "(?![-[^[:punct:]\\s]])"
else if (options contains "o") then
-- Include any preceding or following run of hyphens and/or non-(punctuation or white-space).
set targetPattern to "[-[^[:punct:]\\s]]*" & targetPattern & "[-[^[:punct:]\\s]]*+"
end if
-- Default to case-insensitivity as in vanilla AppleScript unless otherwise indicated by option or AS 'considering' attribute.
if ((options contains "i") or ((options does not contain "s") and ("i" = "I"))) then ¬
set targetPattern to "(?i)" & targetPattern
-- Locate all the matches in the text.
set mutableText to |⌘|'s class "NSMutableString"'s stringWithString:(theText)
set regexObject to |⌘|'s class "NSRegularExpression"'s regularExpressionWithPattern:(targetPattern) ¬
options:(0) |error|:(missing value)
set matchObjects to regexObject's matchesInString:(mutableText) options:(0) range:({0, mutableText's |length|()})
set matchRanges to matchObjects's valueForKey:("range")
-- Replace each character or grapheme in the matched ranges with "X".
set regexSearch to |⌘|'s NSRegularExpressionSearch
repeat with i from (count matchRanges) to 1 by -1
tell mutableText to replaceOccurrencesOfString:(".(?:\\u200d.)*+") withString:("X") ¬
options:(regexSearch) range:(item i of matchRanges)
end repeat
return mutableText as text
end redact
-- Test code:
set theText to "Tom? Toms bottom tomato is in his stomach while playing the \"Tom-tom\" brand tom-toms. That's so tom."
set output to {}
repeat with redactionTarget in {"Tom", "tom"}
set end of output to "Redact " & redactionTarget & ":"
repeat with options in {"[w|s|n]", "[w|i|n]", "[p|s|n]", "[p|i|n]", "[p|s|o]", "[p|i|o]"}
set end of output to options & ": " & redact(theText, redactionTarget, options)
end repeat
set end of output to ""
end repeat
set astid to AppleScript's text item delimiters
set AppleScript's text item delimiters to linefeed
set output to output as text
set AppleScript's text item delimiters to astid
return output</syntaxhighlight>
{{output}}
<syntaxhighlight lang="applescript">"Redact Tom:
[w|s|n]: XXX? Toms bottom tomato is in his stomach while playing the \"Tom-tom\" brand tom-toms. That's so tom.
[w|i|n]: XXX? Toms bottom tomato is in his stomach while playing the \"Tom-tom\" brand tom-toms. That's so XXX.
[p|s|n]: XXX? XXXs bottom tomato is in his stomach while playing the \"XXX-tom\" brand tom-toms. That's so tom.
[p|i|n]: XXX? XXXs botXXX XXXato is in his sXXXach while playing the \"XXX-XXX\" brand XXX-XXXs. That's so XXX.
[p|s|o]: XXX? XXXX bottom tomato is in his stomach while playing the \"XXXXXXX\" brand tom-toms. That's so tom.
[p|i|o]: XXX? XXXX XXXXXX XXXXXX is in his XXXXXXX while playing the \"XXXXXXX\" brand XXXXXXXX. That's so XXX.
Redact tom:
[w|s|n]: Tom? Toms bottom tomato is in his stomach while playing the \"Tom-tom\" brand tom-toms. That's so XXX.
[w|i|n]: XXX? Toms bottom tomato is in his stomach while playing the \"Tom-tom\" brand tom-toms. That's so XXX.
[p|s|n]: Tom? Toms botXXX XXXato is in his sXXXach while playing the \"Tom-XXX\" brand XXX-XXXs. That's so XXX.
[p|i|n]: XXX? XXXs botXXX XXXato is in his sXXXach while playing the \"XXX-XXX\" brand XXX-XXXs. That's so XXX.
[p|s|o]: Tom? Toms XXXXXX XXXXXX is in his XXXXXXX while playing the \"XXXXXXX\" brand XXXXXXXX. That's so XXX.
[p|i|o]: XXX? XXXX XXXXXX XXXXXX is in his XXXXXXX while playing the \"XXXXXXX\" brand XXXXXXXX. That's so XXX.
"</syntaxhighlight>
Or with the grapheme text:
<syntaxhighlight lang="applescript">set graphemeText to "🧑 👨 🧔 👨👩👦"
set output to {}
repeat with redactionTarget in {"👨", "👨👩👦"}
set end of output to "Redact " & redactionTarget & ":"
set end of output to "[w]: " & redact(graphemeText, redactionTarget, "[w]")
set end of output to ""
end repeat
set astid to AppleScript's text item delimiters
set AppleScript's text item delimiters to linefeed
set output to output as text
set AppleScript's text item delimiters to astid
return output</syntaxhighlight>
{{output}}
<syntaxhighlight lang="applescript">"Redact 👨:
[w]: 🧑 X 🧔 👨👩👦
Redact 👨👩👦:
[w]: 🧑 👨 🧔 X
"</syntaxhighlight>
===Vanilla (core language only)===
The above uses ASObjC to take advantage of the Foundation framework's regex functions. But the core AppleScript language is itself perfectly capable of performing the task, albeit with somewhat more code. A fairly recent macOS version's needed for the grapheme characters to be recognised and handled satisfactorily (macOS 10.14's fine), but with plain text, the code below works on any system since Mac OS X 10.5. On macOS 10.14, it's about twice as fast as the ASObjC.
Test code and output as above.
<syntaxhighlight lang="applescript">on redact(theText, redactionTargets, options)
(* Script object containing the basic process. *)
script default
property textItems : missing value
property outputText : theText
-- Replace every instance of each of the passed redaction targets with an "X" sequence of the same length.
on redact()
set astid to AppleScript's text item delimiters
repeat with thisTarget in (redactionTargets as list)
set AppleScript's text item delimiters to thisTarget's contents
set my textItems to my outputText's text items
applyOption()
set AppleScript's text item delimiters to getXs(count thisTarget)
set my outputText to my textItems as text
end repeat
set astid to AppleScript's text item delimiters
end redact
on applyOption()
end applyOption
on getXs(targetLength)
set Xs to ""
repeat targetLength times
set Xs to Xs & "X"
end repeat
return Xs
end getXs
end script
(* Child script objects with their own applyOption() handlers for word-match and overkill. *)
script wordMatch
property parent : default
property newTextItems : missing value
-- Derive new text items from those just extracted with the current delimiter, losing any delimitation within words.
on applyOption()
set my newTextItems to {}
set i to 1
repeat with j from 2 to (count my textItems)
set precedingExtract to text from text item i to text item (j - 1) of my outputText -- Substring from the text.
set thisTextItem to item j of my textItems -- Text item from the list.
if not ¬
((precedingExtract ends with "-") or ¬
(((count precedingExtract's words) > 0) and (precedingExtract ends with precedingExtract's last word)) or ¬
(thisTextItem begins with "-") or ¬
(((count thisTextItem's words) > 0) and (thisTextItem begins with thisTextItem's first word))) then
set end of my newTextItems to precedingExtract
set i to j
end if
end repeat
set end of my newTextItems to text from text item i to text item j of my outputText
set my textItems to my newTextItems
end applyOption
end script
script overkill
property parent : default
-- Where the extracted text items are delimited within words, replace the word stumps' characters with "X"s.
on applyOption()
repeat with i from 2 to (count my textItems)
set precedingTextItem to item (i - 1) of my textItems
if ((count precedingTextItem's words) > 0) then
set lastword to precedingTextItem's last word
if ((precedingTextItem ends with lastword) or (precedingTextItem ends with (lastword & "-"))) then
set editLength to (count text from last word to end of precedingTextItem)
set Xs to getXs(editLength)
if ((count precedingTextItem) > editLength) then ¬
set Xs to text 1 thru -(editLength + 1) of precedingTextItem & Xs
set item (i - 1) of my textItems to Xs
end if
else if ((precedingTextItem is "-") and (i > 2)) then -- Hyphen between two target instances.
set item (i - 1) of my textItems to "X"
end if
set thisTextItem to item i of my textItems
if ((count thisTextItem's words) > 0) then
set firstWord to thisTextItem's first word
if ((thisTextItem begins with firstWord) or (thisTextItem begins with ("-" & firstWord))) then
set editLength to (count text 1 thru first word of thisTextItem)
set Xs to getXs(editLength)
if ((count thisTextItem) > editLength) then set Xs to Xs & text (editLength + 1) thru end of thisTextItem
set item i of my textItems to Xs
end if
end if
end repeat
end applyOption
end script
(* Outer handler code. *)
-- Select the script object to use as the redactor.
if (options contains "w") then
set redactor to wordMatch
else if (options contains "o") then
set redactor to overkill
else
set redactor to default
end if
-- Invoke it with the necessary text comparison attributes imposed.
if ((options contains "i") or ((options does not contain "s") and ("i" = "I"))) then
considering white space and punctuation but ignoring case
tell redactor to redact()
end considering
else
considering white space, punctuation and case
tell redactor to redact()
end considering
end if
return redactor's outputText
end redact</syntaxhighlight>
=={{header|AutoHotkey}}==
No Complex Unicode!
<syntaxhighlight lang="autohotkey">str = Tom? Toms bottom tomato is in his stomach while playing the "Tom-tom" brand tom-toms. That's so tom.
words := ["Tom", "tom"]
opts := ["wsn", "win", "psn", "pin", "pso", "pio"]
for i, word in words
{
result .= "Redact '" word "'`n"
for j, opt in opts
result .= opt "`t" redact(str, word, opt) "`n"
result .= "`n"
}
MsgBox, 262144, , % result
return
redact(str, word, opt){
if InStr(opt, "w") ; Whole word
a := "(^|[^-])\K\b", z := "\b(?!-)"
if InStr(opt, "o") ; Overkill
a .= "\b[\w\-]*", z := "[\w\-]*\b" z
if InStr(opt, "i") ; Case insensitive
i := "i)"
ndle := i a "\Q" word "\E" z
while pos := RegExMatch(str, ndle, mtch, A_Index=1?1:pos+StrLen(mtch))
{
rplc := ""
loop % StrLen(mtch)
rplc .= "X"
str := RegExReplace(str, ndle, rplc,, 1)
}
return str
}</syntaxhighlight>
{{out}}
<pre>Redact 'Tom'
wsn XXX? Toms bottom tomato is in his stomach while playing the "Tom-tom" brand tom-toms. That's so tom.
win XXX? Toms bottom tomato is in his stomach while playing the "Tom-tom" brand tom-toms. That's so XXX.
psn XXX? XXXs bottom tomato is in his stomach while playing the "XXX-tom" brand tom-toms. That's so tom.
pin XXX? XXXs botXXX XXXato is in his sXXXach while playing the "XXX-XXX" brand XXX-XXXs. That's so XXX.
pso XXX? XXXX bottom tomato is in his stomach while playing the "XXXXXXX" brand tom-toms. That's so tom.
pio XXX? XXXX XXXXXX XXXXXX is in his XXXXXXX while playing the "XXXXXXX" brand XXXXXXXX. That's so XXX.
Redact 'tom'
wsn Tom? Toms bottom tomato is in his stomach while playing the "Tom-tom" brand tom-toms. That's so XXX.
win XXX? Toms bottom tomato is in his stomach while playing the "Tom-tom" brand tom-toms. That's so XXX.
psn Tom? Toms botXXX XXXato is in his sXXXach while playing the "Tom-XXX" brand XXX-XXXs. That's so XXX.
pin XXX? XXXs botXXX XXXato is in his sXXXach while playing the "XXX-XXX" brand XXX-XXXs. That's so XXX.
pso Tom? Toms XXXXXX XXXXXX is in his XXXXXXX while playing the "XXXXXXX" brand XXXXXXXX. That's so XXX.
pio XXX? XXXX XXXXXX XXXXXX is in his XXXXXXX while playing the "XXXXXXX" brand XXXXXXXX. That's so XXX.</pre>
=={{header|C}}==
This is a very basic ASCII-only implementation, no Unicode or regular expressions.
<syntaxhighlight lang="c">#include <ctype.h>
#include <stdbool.h>
#include <stdio.h>
#include <string.h>
typedef enum {
whole_word = 1,
overkill = 2,
case_insensitive = 4
} redact_options;
bool is_word_char(char ch) {
return ch == '-' || isalpha((unsigned char)ch);
}
// Performs in-place redaction of the target with the specified options.
void redact(char* text, const char* target, redact_options options) {
size_t target_length = strlen(target);
if (target_length == 0)
return;
char* start = text;
char* end = text + strlen(text);
while (start < end) {
// NB: strcasestr is a non-standard extension. It's similar to the
// standard strstr function, but case-insensitive.
char* str = (options & case_insensitive) ? strcasestr(start, target)
: strstr(start, target);
if (str == NULL)
break;
char* word_start = str;
char* word_end = str + target_length;
if (options & (overkill | whole_word)) {
while (word_start > start && is_word_char(*(word_start - 1)))
--word_start;
while (word_end < end && is_word_char(*word_end))
++word_end;
}
if (!(options & whole_word) ||
(word_start == str && word_end == str + target_length))
memset(word_start, 'X', word_end - word_start);
start = word_end;
}
}
void do_basic_test(const char* target, redact_options options) {
char text[] = "Tom? Toms bottom tomato is in his stomach while playing the "
"\"Tom-tom\" brand tom-toms. That's so tom.";
redact(text, target, options);
printf("[%c|%c|%c]: %s\n", (options & whole_word) ? 'w' : 'p',
(options & case_insensitive) ? 'i' : 's',
(options & overkill) ? 'o' : 'n', text);
}
void do_basic_tests(const char* target) {
printf("Redact '%s':\n", target);
do_basic_test(target, whole_word);
do_basic_test(target, whole_word | case_insensitive);
do_basic_test(target, 0);
do_basic_test(target, case_insensitive);
do_basic_test(target, overkill);
do_basic_test(target, case_insensitive | overkill);
}
int main() {
do_basic_tests("Tom");
printf("\n");
do_basic_tests("tom");
return 0;
}</syntaxhighlight>
{{out}}
<pre>
Redact 'Tom':
[w|s|n]: XXX? Toms bottom tomato is in his stomach while playing the "Tom-tom" brand tom-toms. That's so tom.
[w|i|n]: XXX? Toms bottom tomato is in his stomach while playing the "Tom-tom" brand tom-toms. That's so XXX.
[p|s|n]: XXX? XXXs bottom tomato is in his stomach while playing the "XXX-tom" brand tom-toms. That's so tom.
[p|i|n]: XXX? XXXs botXXX XXXato is in his sXXXach while playing the "XXX-XXX" brand XXX-XXXs. That's so XXX.
[p|s|o]: XXX? XXXX bottom tomato is in his stomach while playing the "XXXXXXX" brand tom-toms. That's so tom.
[p|i|o]: XXX? XXXX XXXXXX XXXXXX is in his XXXXXXX while playing the "XXXXXXX" brand XXXXXXXX. That's so XXX.
Redact 'tom':
[w|s|n]: Tom? Toms bottom tomato is in his stomach while playing the "Tom-tom" brand tom-toms. That's so XXX.
[w|i|n]: XXX? Toms bottom tomato is in his stomach while playing the "Tom-tom" brand tom-toms. That's so XXX.
[p|s|n]: Tom? Toms botXXX XXXato is in his sXXXach while playing the "Tom-XXX" brand XXX-XXXs. That's so XXX.
[p|i|n]: XXX? XXXs botXXX XXXato is in his sXXXach while playing the "XXX-XXX" brand XXX-XXXs. That's so XXX.
[p|s|o]: Tom? Toms XXXXXX XXXXXX is in his XXXXXXX while playing the "XXXXXXX" brand XXXXXXXX. That's so XXX.
[p|i|o]: XXX? XXXX XXXXXX XXXXXX is in his XXXXXXX while playing the "XXXXXXX" brand XXXXXXXX. That's so XXX.
</pre>
=={{header|C++}}==
{{trans|D}}
<syntaxhighlight lang="cpp">#include <iostream>
using namespace std;
string redact(const string &source, const string &word, bool partial, bool insensitive, bool overkill) {
string temp = source;
auto different = [insensitive](char s, char w) {
if (insensitive) {
return toupper(s) != toupper(w);
} else {
return s != w;
}
};
auto isWordChar = [](char c) {
return c == '-' || isalpha(c);
};
for (size_t i = 0; i < temp.length() - word.length() + 1; i++) {
bool match = true;
for (size_t j = 0; j < word.length(); j++) {
if (different(temp[i + j], word[j])) {
match = false;
break;
}
}
if (match) {
auto beg = i;
auto end = i + word.length();
if (!partial) {
if (beg > 0 && isWordChar(temp[beg - 1])) {
continue;
}
if (end < temp.length() && isWordChar(temp[end])) {
continue;
}
}
if (overkill) {
while (beg > 0 && isWordChar(temp[beg - 1])) {
beg--;
}
while (end < temp.length() && isWordChar(temp[end])) {
end++;
}
}
for (size_t k = beg; k < end; k++) {
temp[k] = 'X';
}
}
}
return temp;
}
void example(const string &source, const string &word) {
std::cout << "Redact " << word << '\n';
std::cout << "[w|s|n] " << redact(source, word, false, false, false) << '\n';
std::cout << "[w|i|n] " << redact(source, word, false, true, false) << '\n';
std::cout << "[p|s|n] " << redact(source, word, true, false, false) << '\n';
std::cout << "[p|i|n] " << redact(source, word, true, true, false) << '\n';
std::cout << "[p|s|o] " << redact(source, word, true, false, true) << '\n';
std::cout << "[p|i|o] " << redact(source, word, true, true, true) << '\n';
std::cout << '\n';
}
int main() {
string text = "Tom? Toms bottom tomato is in his stomach while playing the \"Tom-tom\" brand tom-toms. That's so tom";
example(text, "Tom");
example(text, "tom");
return 0;
}</syntaxhighlight>
{{out}}
<pre>Redact Tom
[w|s|n] XXX? Toms bottom tomato is in his stomach while playing the "Tom-tom" brand tom-toms. That's so tom
[w|i|n] XXX? Toms bottom tomato is in his stomach while playing the "Tom-tom" brand tom-toms. That's so XXX
[p|s|n] XXX? XXXs bottom tomato is in his stomach while playing the "XXX-tom" brand tom-toms. That's so tom
[p|i|n] XXX? XXXs botXXX XXXato is in his sXXXach while playing the "XXX-XXX" brand XXX-XXXs. That's so XXX
[p|s|o] XXX? XXXX bottom tomato is in his stomach while playing the "XXXXXXX" brand tom-toms. That's so tom
[p|i|o] XXX? XXXX XXXXXX XXXXXX is in his XXXXXXX while playing the "XXXXXXX" brand XXXXXXXX. That's so XXX
Redact tom
[w|s|n] Tom? Toms bottom tomato is in his stomach while playing the "Tom-tom" brand tom-toms. That's so XXX
[w|i|n] XXX? Toms bottom tomato is in his stomach while playing the "Tom-tom" brand tom-toms. That's so XXX
[p|s|n] Tom? Toms botXXX XXXato is in his sXXXach while playing the "Tom-XXX" brand XXX-XXXs. That's so XXX
[p|i|n] XXX? XXXs botXXX XXXato is in his sXXXach while playing the "XXX-XXX" brand XXX-XXXs. That's so XXX
[p|s|o] Tom? Toms XXXXXX XXXXXX is in his XXXXXXX while playing the "XXXXXXX" brand XXXXXXXX. That's so XXX
[p|i|o] XXX? XXXX XXXXXX XXXXXX is in his XXXXXXX while playing the "XXXXXXX" brand XXXXXXXX. That's so XXX</pre>
=={{header|D}}==
<syntaxhighlight lang="d">import std.stdio;
import std.uni;
string redact(string source, string word, bool partial = false, bool insensitive = false, bool overkill = false) {
bool different(char s, char w) {
if (insensitive) {
return s.toUpper != w.toUpper;
} else {
return s != w;
}
}
bool isWordChar(char c) {
return c == '-' || c.isAlpha;
}
auto temp = source.dup;
foreach (i; 0 .. temp.length - word.length + 1) {
bool match = true;
foreach (j; 0 .. word.length) {
if (different(temp[i + j], word[j])) {
match = false;
break;
}
}
if (match) {
auto beg = i;
auto end = i + word.length;
if (!partial) {
if (beg > 0 && isWordChar(temp[beg - 1])) {
// writeln("b boundary ", temp[beg - 1]);
continue;
}
if (end < temp.length && isWordChar(temp[end])) {
// writeln("e boundary ", temp[end]);
continue;
}
}
if (overkill) {
while (beg > 0 && isWordChar(temp[beg - 1])) {
beg--;
}
while (end < temp.length - 1 && isWordChar(temp[end])) {
end++;
}
}
temp[beg .. end] = 'X';
}
}
return temp.idup;
}
void example(string source, string word) {
writeln("Redact ", word);
writeln("[w|s|n] ", redact(source, word, false, false, false));
writeln("[w|i|n] ", redact(source, word, false, true, false));
writeln("[p|s|n] ", redact(source, word, true, false, false));
writeln("[p|i|n] ", redact(source, word, true, true, false));
writeln("[p|s|o] ", redact(source, word, true, false, true));
writeln("[p|i|o] ", redact(source, word, true, true, true));
writeln;
}
void main(string[] args) {
string text = `Tom? Toms bottom tomato is in his stomach while playing the "Tom-tom" brand tom-toms. That's so tom`;
example(text, "Tom");
example(text, "tom");
}</syntaxhighlight>
{{out}}
<pre>Redact Tom
[w|s|n] XXX? Toms bottom tomato is in his stomach while playing the "Tom-tom" brand tom-toms. That's so tom
[w|i|n] XXX? Toms bottom tomato is in his stomach while playing the "Tom-tom" brand tom-toms. That's so XXX
[p|s|n] XXX? XXXs bottom tomato is in his stomach while playing the "XXX-tom" brand tom-toms. That's so tom
[p|i|n] XXX? XXXs botXXX XXXato is in his sXXXach while playing the "XXX-XXX" brand XXX-XXXs. That's so XXX
[p|s|o] XXX? XXXX bottom tomato is in his stomach while playing the "XXXXXXX" brand tom-toms. That's so tom
[p|i|o] XXX? XXXX XXXXXX XXXXXX is in his XXXXXXX while playing the "XXXXXXX" brand XXXXXXXX. That's so XXX
Redact tom
[w|s|n] Tom? Toms bottom tomato is in his stomach while playing the "Tom-tom" brand tom-toms. That's so XXX
[w|i|n] XXX? Toms bottom tomato is in his stomach while playing the "Tom-tom" brand tom-toms. That's so XXX
[p|s|n] Tom? Toms botXXX XXXato is in his sXXXach while playing the "Tom-XXX" brand XXX-XXXs. That's so XXX
[p|i|n] XXX? XXXs botXXX XXXato is in his sXXXach while playing the "XXX-XXX" brand XXX-XXXs. That's so XXX
[p|s|o] Tom? Toms XXXXXX XXXXXX is in his XXXXXXX while playing the "XXXXXXX" brand XXXXXXXX. That's so XXX
[p|i|o] XXX? XXXX XXXXXX XXXXXX is in his XXXXXXX while playing the "XXXXXXX" brand XXXXXXXX. That's so XXX</pre>
=={{header|FutureBasic}}==
<syntaxhighlight lang="futurebasic">
include "NSLog.incl"
local fn Redact( string as CFStringRef, target as CFStringRef, whole as BOOL, icase as BOOL, over as BOOL ) as CFStringRef
ErrorRef err = NULL
CFStringRef w = @"p", i = @"s", o = @"n", result = NULL
NSRegularExpressionOptions options = 0
CFStringRef pattern = fn RegularExpressionEscapedPattern( target )
if whole == YES
pattern = fn StringWithFormat( @"%@%@%@", @"(?<![-[^[:punct:]\\s]])", pattern, @"(?![-[^[:punct:]\\s]])" )
w = @"w"
end if
if over == YES
pattern = fn StringWithFormat( @"%@%@%@", @"[-[^[:punct:]\\s]]*", pattern, @"[-[^[:punct:]\\s]]*+" )
o = @"o"
end if
if icase == YES Then options = NSRegularExpressionCaseInsensitive : i = @"i"
RegularExpressionRef regex = fn RegularExpressionWithPattern( pattern, options, @err )
if err then NSLog( @"%@", fn ErrorLocalizedDescription( err ) )
CFMutableStringRef mutStr = fn MutableStringWithString( string )
CFArrayRef matches = fn RegularExpressionMatches( regex, mutStr, 0, fn CFRangeMake( 0, len( mutStr ) ) )
long x, count = len(matches)
for x = 0 to count - 1
CFRange matchRange = fn ValueRange( fn ObjectValueForKey( matches[x], @"range" ) )
MutableStringReplaceOccurrencesOfString( mutStr, @".(?:\\u200d.)*+", @"X", NSRegularExpressionSearch, matchRange )
next
result = fn StringWithFormat( @"[%@|%@|%@] %@", w, i, o, mutStr )
end fn = result
CFStringRef tomTest
tomTest = @"Tom? Toms bottom tomato is in his stomach while playing the \"Tom-tom\" brand tom-toms. That's so tom."
NSLog( @"Test string:\n%@\n\nRedact 'Tom':", tomTest )
NSLog( @"%@", fn Redact( tomTest, @"Tom", YES, NO, NO ) )
NSLog( @"%@", fn Redact( tomTest, @"Tom", YES, YES, NO ) )
NSLog( @"%@", fn Redact( tomTest, @"Tom", NO, NO, NO ) )
NSLog( @"%@", fn Redact( tomTest, @"Tom", NO, YES, NO ) )
NSLog( @"%@", fn Redact( tomTest, @"Tom", NO, NO, YES ) )
NSLog( @"%@", fn Redact( tomTest, @"Tom", NO, YES, YES ) )
NSLog( @"\nRedact 'tom':" )
NSLog( @"%@", fn Redact( tomTest, @"tom", YES, NO, NO ) )
NSLog( @"%@", fn Redact( tomTest, @"tom", YES, YES, NO ) )
NSLog( @"%@", fn Redact( tomTest, @"tom", NO, NO, NO ) )
NSLog( @"%@", fn Redact( tomTest, @"tom", NO, YES, NO ) )
NSLog( @"%@", fn Redact( tomTest, @"tom", NO, NO, YES ) )
NSLog( @"%@", fn Redact( tomTest, @"tom", NO, YES, YES ) )
NSLogSetFont( fn FontWithName( @"Menlo", 18.0 ) )
NSLog( @"\n 🧑 👨 🧔 👨👩👦" )
NSLog( @"Redact '👨': %@", fn Redact( @"🧑 👨 🧔 👨👩👦", @"👨", YES, YES, YES ) )
NSLog( @"Redact '👨👩👦': %@", fn Redact( @"🧑 👨 🧔 👨👩👦", @"👨👩👦", YES, YES, YES ) )
HandleEvents
</syntaxhighlight>
{{output}}
<pre>
Test string:
Tom? Toms bottom tomato is in his stomach while playing the "Tom-tom" brand tom-toms. That's so tom.
Redact 'Tom':
[w|s|n] XXX? Toms bottom tomato is in his stomach while playing the "Tom-tom" brand tom-toms. That's so tom.
[w|i|n] XXX? Toms bottom tomato is in his stomach while playing the "Tom-tom" brand tom-toms. That's so XXX.
[p|s|n] XXX? XXXs bottom tomato is in his stomach while playing the "XXX-tom" brand tom-toms. That's so tom.
[p|i|n] XXX? XXXs botXXX XXXato is in his sXXXach while playing the "XXX-XXX" brand XXX-XXXs. That's so XXX.
[p|s|o] XXX? XXXX bottom tomato is in his stomach while playing the "XXXXXXX" brand tom-toms. That's so tom.
[p|i|o] XXX? XXXX XXXXXX XXXXXX is in his XXXXXXX while playing the "XXXXXXX" brand XXXXXXXX. That's so XXX.
Redact 'tom':
[w|s|n] Tom? Toms bottom tomato is in his stomach while playing the "Tom-tom" brand tom-toms. That's so XXX.
[w|i|n] XXX? Toms bottom tomato is in his stomach while playing the "Tom-tom" brand tom-toms. That's so XXX.
[p|s|n] Tom? Toms botXXX XXXato is in his sXXXach while playing the "Tom-XXX" brand XXX-XXXs. That's so XXX.
[p|i|n] XXX? XXXs botXXX XXXato is in his sXXXach while playing the "XXX-XXX" brand XXX-XXXs. That's so XXX.
[p|s|o] Tom? Toms XXXXXX XXXXXX is in his XXXXXXX while playing the "XXXXXXX" brand XXXXXXXX. That's so XXX.
[p|i|o] XXX? XXXX XXXXXX XXXXXX is in his XXXXXXX while playing the "XXXXXXX" brand XXXXXXXX. That's so XXX.
🧑 👨 🧔 👨👩👦
Redact '👨': [w|i|o] 🧑 X 🧔 👨👩👦
Redact '👨👩👦': [w|i|o] 🧑 👨 🧔 X
</pre>
Line 69 ⟶ 871:
To get the number of 'X's right where a ZWJ emoji or other character combination is being replaced, a third party library function is used which counts the number of graphemes in a string, as required by the task.
<
import (
Line 158 ⟶ 960:
allOpts = []string{"[p]", "[p|o]"}
printResults(text, allOpts, allWords)
}</
{{out}}
Line 248 ⟶ 1,050:
The solution must kludge a check with the variable "multichar" to properly substitute "X" instead of "XXXX" with the last example.
Otherwise Julia (v 1.4) interprets one 184-bit Unicode extended emoji character as four Unicode characters.
<
regex = insens ? Regex("^$pattern\$", "i") : Regex("^$pattern\$")
return replace(word, regex => pattern in multichars ? "X" : "X"^length(pattern))
Line 303 ⟶ 1,105:
println()
end
</
<pre>
Line 330 ⟶ 1,132:
</pre>
=={{header|
Note: The syntax-highlighter used here for Lua appears to be confused by the nested quote styles, but the syntax is valid as written.
<syntaxhighlight lang="lua">function redact(text, targ, opts)
local part, case, ovrk = opts:find("p")~=nil, opts:find("s")~=nil, opts:find("o")~=nil
local oknp = ovrk or not part
local patt = oknp and "([%w%-]+)" or "(%w+)"
local ci = case and function(s) return s end or function(s) return s:lower() end
local matches = function(s,w) return part and ci(s):find(ci(w))~=nil or ci(s)==ci(w) end
local replace = function(s,w) return oknp and string.rep("X",#s) or ci(s):gsub(ci(w), string.rep("X",#w)) end
return text:gsub(patt, function(word) return matches(word,targ) and replace(word,targ) or word end)
end
text = [[Tom? Toms bottom tomato is in his stomach while playing the "Tom-tom" brand tom-toms. That's so tom.]]
targlist, optslist = { "Tom", "tom" }, { "[w|s|n]", "[w|i|n]", "[p|s|n]", "[p|i|n]", "[p|s|o]", "[p|i|o]" }
print("Redact '"..targ.."':")
for _,opts in ipairs(optslist) do
print(opts .. " "
end
end</syntaxhighlight>
{{out}}
<pre>Redact 'Tom':
[w|s|n] XXX? Toms bottom tomato is in his stomach while playing the "Tom-tom" brand tom-toms. That's so tom.
[w|i|n] XXX? Toms bottom tomato is in his stomach while playing the "Tom-tom" brand tom-toms. That's so XXX.
[p|s|n] XXX? XXXs bottom tomato is in his stomach while playing the "XXX-tom" brand tom-toms. That's so tom.
[p|i|n] XXX? XXXs botXXX XXXato is in his sXXXach while playing the "XXX-XXX" brand XXX-XXXs. That's so XXX.
[p|s|o] XXX? XXXX bottom tomato is in his stomach while playing the "XXXXXXX" brand tom-toms. That's so tom.
[p|i|o] XXX? XXXX XXXXXX XXXXXX is in his XXXXXXX while playing the "XXXXXXX" brand XXXXXXXX. That's so XXX.
Redact 'tom':
[w|s|n] Tom? Toms bottom tomato is in his stomach while playing the "Tom-tom" brand tom-toms. That's so XXX.
[w|i|n] XXX? Toms bottom tomato is in his stomach while playing the "Tom-tom" brand tom-toms. That's so XXX.
[p|s|n] Tom? Toms botXXX XXXato is in his sXXXach while playing the "Tom-XXX" brand XXX-XXXs. That's so XXX.
[p|i|n] XXX? XXXs botXXX XXXato is in his sXXXach while playing the "XXX-XXX" brand XXX-XXXs. That's so XXX.
[p|s|o] Tom? Toms XXXXXX XXXXXX is in his XXXXXXX while playing the "XXXXXXX" brand XXXXXXXX. That's so XXX.
[p|i|o] XXX? XXXX XXXXXX XXXXXX is in his XXXXXXX while playing the "XXXXXXX" brand XXXXXXXX. That's so XXX.</pre>
=={{header|Perl}}==
{{trans|Raku}}
<syntaxhighlight lang="perl">use strict;
use warnings;
Tom? Toms bottom tomato is in his stomach while playing the "Tom-tom" brand tom-toms. That's so tom.
'Tis very tomish, don't you think?
END
sub redact {
my($str, $redact, %opt) = @_;
my $insensitive = $opt{'i'} or 0;
my $partial = $opt{'p'} or 0;
my $overkill = $opt{'o'} or 0;
my $rx =
$insensitive ?
$partial ?
$overkill ? qr/ \b{wb} ((?i)[-\w_]* [\w*']* $redact [-'\w]* \S*?) \b{wb} /x
: qr/ ((?i)$redact) /x
: qr/ \b{wb}(?<!-) ((?i)$redact) (?!-)\b{wb} /x
:
$partial ?
$overkill ? qr/ \b{wb} ([-\w]* [\w*']* $redact [-'\w]* \S*?) \b{wb} /x
: qr/ ($redact) /x
: qr/ \b{wb}(?<!-) ($redact) (?!-)\b{wb} /x
;
$str =~ s/($rx)/'X' x length $1/gre;
}
for my $redact (<Tom tom t>) {
print "\nRedact '$redact':\n";
for (['[w|s|n]', {}],
['[w|i|n]', {i=>1}],
['[p|s|n]', {p=>1}],
['[p|i|n]', {p=>1, i=>1}],
['[p|s|o]', {p=>1, o=>1}],
['[p|i|o]', {p=>1, i=>1, o=>1}]
) {
my($option, $opts) = @$_;
no strict 'refs';
printf "%s %s\n", $option, redact($test, $redact, %$opts)
}
}</syntaxhighlight>
{{out}}
<pre style="height:40ex;overflow:scroll;">Redact 'Tom':
[w|s|n] XXX? Toms bottom tomato is in his stomach while playing the "Tom-tom" brand tom-toms. That's so tom.
'Tis very tomish, don't you think?
[w|i|n] XXX? Toms bottom tomato is in his stomach while playing the "Tom-tom" brand tom-toms. That's so XXX.
'Tis very tomish, don't you think?
[p|s|n] XXX? XXXs bottom tomato is in his stomach while playing the "XXX-tom" brand tom-toms. That's so tom.
'Tis very tomish, don't you think?
[p|i|n] XXX? XXXs botXXX XXXato is in his sXXXach while playing the "XXX-XXX" brand XXX-XXXs. That's so XXX.
'Tis very XXXish, don't you think?
[p|s|o] XXX? XXXX bottom tomato is in his stomach while playing the "XXXXXXX" brand tom-toms. That's so tom.
'Tis very tomish, don't you think?
[p|i|o] XXX? XXXX XXXXXX XXXXXX is in his XXXXXXX while playing the "XXXXXXX" brand XXXXXXXX. That's so XXX.
'Tis very XXXXXX, don't you think?
Redact 'tom':
[w|s|n] Tom? Toms bottom tomato is in his stomach while playing the "Tom-tom" brand tom-toms. That's so XXX.
'Tis very tomish, don't you think?
[w|i|n] XXX? Toms bottom tomato is in his stomach while playing the "Tom-tom" brand tom-toms. That's so XXX.
'Tis very tomish, don't you think?
[p|s|n] Tom? Toms botXXX XXXato is in his sXXXach while playing the "Tom-XXX" brand XXX-XXXs. That's so XXX.
'Tis very XXXish, don't you think?
[p|i|n] XXX? XXXs botXXX XXXato is in his sXXXach while playing the "XXX-XXX" brand XXX-XXXs. That's so XXX.
'Tis very XXXish, don't you think?
[p|s|o] Tom? Toms XXXXXX XXXXXX is in his XXXXXXX while playing the "XXXXXXX" brand XXXXXXXX. That's so XXX.
'Tis very XXXXXX, don't you think?
[p|i|o] XXX? XXXX XXXXXX XXXXXX is in his XXXXXXX while playing the "XXXXXXX" brand XXXXXXXX. That's so XXX.
'Tis very XXXXXX, don't you think?
Redact 't':
[w|s|n] Tom? Toms bottom tomato is in his stomach while playing the "Tom-tom" brand tom-toms. That's so tom.
'Tis very tomish, don't you think?
[w|i|n] Tom? Toms bottom tomato is in his stomach while playing the "Tom-tom" brand tom-toms. That's so tom.
'Tis very tomish, don't you think?
[p|s|n] Tom? Toms boXXom XomaXo is in his sXomach while playing Xhe "Tom-Xom" brand Xom-Xoms. ThaX's so Xom.
'Tis very Xomish, don'X you Xhink?
[p|i|n] Xom? Xoms boXXom XomaXo is in his sXomach while playing Xhe "Xom-Xom" brand Xom-Xoms. XhaX's so Xom.
'Xis very Xomish, don'X you Xhink?
[p|s|o] Tom? Toms XXXXXX XXXXXX is in his XXXXXXX while playing XXX "XXXXXXX" brand XXXXXXXX. XXXXXX so XXX.
'Tis very XXXXXX, XXXXX you XXXXX?
[p|i|o] XXX? XXXX XXXXXX XXXXXX is in his XXXXXXX while playing XXX "XXXXXXX" brand XXXXXXXX. XXXXXX so XXX.
XXXX very XXXXXX, XXXXX you XXXXX?</pre>
=={{header|Phix}}==
{{libheader|Phix/online}}
You can run this online [http://phix.x10.mx/p2js/redact.htm here]. Note the windows console makes a complete mockery of those unicode characters.<br>
Written on the assumption that overkill implies partial (see talk page).<br>
utf32_length() fashioned after [[Reverse_a_string#Phix]] with added ZWJ - I do not expect it to be entirely complete.
<!--<syntaxhighlight lang="phix">(phixonline)-->
<span style="color: #008080;">enum</span> <span style="color: #000000;">WHOLE</span><span style="color: #0000FF;">,</span><span style="color: #000000;">PARTIAL</span><span style="color: #0000FF;">,</span><span style="color: #000000;">OVERKILL</span><span style="color: #0000FF;">,</span><span style="color: #000000;">INSENSITIVE</span>
<span style="color: #008080;">constant</span> <span style="color: #000000;">spunc</span> <span style="color: #0000FF;">=</span> <span style="color: #008000;">" \r\n.?\""</span> <span style="color: #000080;font-style:italic;">-- spaces and punctuation</span>
<span style="color: #008080;">function</span> <span style="color: #000000;">utf32_length</span><span style="color: #0000FF;">(</span><span style="color: #004080;">sequence</span> <span style="color: #000000;">utf32</span><span style="color: #0000FF;">)</span>
<span style="color: #004080;">integer</span> <span style="color: #000000;">l</span> <span style="color: #0000FF;">=</span> <span style="color: #7060A8;">length</span><span style="color: #0000FF;">(</span><span style="color: #000000;">utf32</span><span style="color: #0000FF;">)</span>
<span style="color: #008080;">for</span> <span style="color: #000000;">i</span><span style="color: #0000FF;">=</span><span style="color: #000000;">1</span> <span style="color: #008080;">to</span> <span style="color: #000000;">l</span> <span style="color: #008080;">do</span>
<span style="color: #004080;">integer</span> <span style="color: #000000;">ch</span> <span style="color: #0000FF;">=</span> <span style="color: #000000;">utf32</span><span style="color: #0000FF;">[</span><span style="color: #000000;">i</span><span style="color: #0000FF;">]</span>
<span style="color: #008080;">if</span> <span style="color: #0000FF;">(</span><span style="color: #000000;">ch</span><span style="color: #0000FF;">>=</span><span style="color: #000000;">0x300</span> <span style="color: #008080;">and</span> <span style="color: #000000;">ch</span><span style="color: #0000FF;"><=</span><span style="color: #000000;">0x36f</span><span style="color: #0000FF;">)</span>
<span style="color: #008080;">or</span> <span style="color: #0000FF;">(</span><span style="color: #000000;">ch</span><span style="color: #0000FF;">>=</span><span style="color: #000000;">0x1dc0</span> <span style="color: #008080;">and</span> <span style="color: #000000;">ch</span><span style="color: #0000FF;"><=</span><span style="color: #000000;">0x1dff</span><span style="color: #0000FF;">)</span>
<span style="color: #008080;">or</span> <span style="color: #0000FF;">(</span><span style="color: #000000;">ch</span><span style="color: #0000FF;">>=</span><span style="color: #000000;">0x20d0</span> <span style="color: #008080;">and</span> <span style="color: #000000;">ch</span><span style="color: #0000FF;"><=</span><span style="color: #000000;">0x20ff</span><span style="color: #0000FF;">)</span>
<span style="color: #008080;">or</span> <span style="color: #0000FF;">(</span><span style="color: #000000;">ch</span><span style="color: #0000FF;">>=</span><span style="color: #000000;">0xfe20</span> <span style="color: #008080;">and</span> <span style="color: #000000;">ch</span><span style="color: #0000FF;"><=</span><span style="color: #000000;">0xfe2f</span><span style="color: #0000FF;">)</span> <span style="color: #008080;">then</span>
<span style="color: #000000;">l</span> <span style="color: #0000FF;">-=</span> <span style="color: #000000;">1</span>
<span style="color: #008080;">elsif</span> <span style="color: #000000;">ch</span><span style="color: #0000FF;">=</span><span style="color: #000000;">0x200D</span> <span style="color: #008080;">then</span> <span style="color: #000080;font-style:italic;">-- ZERO WIDTH JOINER</span>
<span style="color: #000000;">l</span> <span style="color: #0000FF;">-=</span> <span style="color: #000000;">2</span>
<span style="color: #008080;">end</span> <span style="color: #008080;">if</span>
<span style="color: #008080;">end</span> <span style="color: #008080;">for</span>
<span style="color: #008080;">return</span> <span style="color: #000000;">l</span>
<span style="color: #008080;">end</span> <span style="color: #008080;">function</span>
<span style="color: #008080;">function</span> <span style="color: #000000;">redact</span><span style="color: #0000FF;">(</span><span style="color: #004080;">string</span> <span style="color: #000000;">text</span><span style="color: #0000FF;">,</span> <span style="color: #000000;">word</span><span style="color: #0000FF;">,</span> <span style="color: #004080;">integer</span> <span style="color: #000000;">options</span><span style="color: #0000FF;">)</span>
<span style="color: #004080;">sequence</span> <span style="color: #000000;">t_utf32</span> <span style="color: #0000FF;">=</span> <span style="color: #7060A8;">utf8_to_utf32</span><span style="color: #0000FF;">(</span><span style="color: #000000;">text</span><span style="color: #0000FF;">),</span>
<span style="color: #000000;">l_utf32</span> <span style="color: #0000FF;">=</span> <span style="color: #000000;">t_utf32</span><span style="color: #0000FF;">,</span>
<span style="color: #000000;">w_utf32</span> <span style="color: #0000FF;">=</span> <span style="color: #7060A8;">utf8_to_utf32</span><span style="color: #0000FF;">(</span><span style="color: #000000;">word</span><span style="color: #0000FF;">)</span>
<span style="color: #004080;">string</span> <span style="color: #000000;">opt</span> <span style="color: #0000FF;">=</span> <span style="color: #008000;">"[?|s]"</span>
<span style="color: #008080;">if</span> <span style="color: #000000;">options</span><span style="color: #0000FF;">></span><span style="color: #000000;">INSENSITIVE</span> <span style="color: #008080;">then</span>
<span style="color: #000000;">options</span> <span style="color: #0000FF;">-=</span> <span style="color: #000000;">INSENSITIVE</span>
<span style="color: #000000;">opt</span><span style="color: #0000FF;">[</span><span style="color: #000000;">4</span><span style="color: #0000FF;">]</span> <span style="color: #0000FF;">=</span> <span style="color: #008000;">'i'</span>
<span style="color: #000000;">l_utf32</span> <span style="color: #0000FF;">=</span> <span style="color: #7060A8;">lower</span><span style="color: #0000FF;">(</span><span style="color: #000000;">t_utf32</span><span style="color: #0000FF;">)</span>
<span style="color: #000000;">w_utf32</span> <span style="color: #0000FF;">=</span> <span style="color: #7060A8;">lower</span><span style="color: #0000FF;">(</span><span style="color: #000000;">w_utf32</span><span style="color: #0000FF;">)</span>
<span style="color: #008080;">end</span> <span style="color: #008080;">if</span>
<span style="color: #000000;">opt</span><span style="color: #0000FF;">[</span><span style="color: #000000;">2</span><span style="color: #0000FF;">]</span> <span style="color: #0000FF;">=</span> <span style="color: #008000;">"wpo"</span><span style="color: #0000FF;">[</span><span style="color: #000000;">options</span><span style="color: #0000FF;">]</span>
<span style="color: #004080;">integer</span> <span style="color: #000000;">idx</span> <span style="color: #0000FF;">=</span> <span style="color: #000000;">1</span>
<span style="color: #008080;">while</span> <span style="color: #004600;">true</span> <span style="color: #008080;">do</span>
<span style="color: #000000;">idx</span> <span style="color: #0000FF;">=</span> <span style="color: #7060A8;">match</span><span style="color: #0000FF;">(</span><span style="color: #000000;">w_utf32</span><span style="color: #0000FF;">,</span><span style="color: #000000;">l_utf32</span><span style="color: #0000FF;">,</span><span style="color: #000000;">idx</span><span style="color: #0000FF;">)</span>
<span style="color: #008080;">if</span> <span style="color: #000000;">idx</span><span style="color: #0000FF;">=</span><span style="color: #000000;">0</span> <span style="color: #008080;">then</span> <span style="color: #008080;">exit</span> <span style="color: #008080;">end</span> <span style="color: #008080;">if</span>
<span style="color: #004080;">integer</span> <span style="color: #000000;">edx</span> <span style="color: #0000FF;">=</span> <span style="color: #000000;">idx</span><span style="color: #0000FF;">+</span><span style="color: #7060A8;">length</span><span style="color: #0000FF;">(</span><span style="color: #000000;">w_utf32</span><span style="color: #0000FF;">)-</span><span style="color: #000000;">1</span>
<span style="color: #008080;">if</span> <span style="color: #000000;">options</span><span style="color: #0000FF;">=</span><span style="color: #000000;">WHOLE</span> <span style="color: #008080;">then</span>
<span style="color: #008080;">if</span> <span style="color: #0000FF;">(</span><span style="color: #000000;">idx</span><span style="color: #0000FF;">=</span><span style="color: #000000;">1</span> <span style="color: #008080;">or</span> <span style="color: #7060A8;">find</span><span style="color: #0000FF;">(</span><span style="color: #000000;">l_utf32</span><span style="color: #0000FF;">[</span><span style="color: #000000;">idx</span><span style="color: #0000FF;">-</span><span style="color: #000000;">1</span><span style="color: #0000FF;">],</span><span style="color: #000000;">spunc</span><span style="color: #0000FF;">))</span>
<span style="color: #008080;">and</span> <span style="color: #0000FF;">(</span><span style="color: #000000;">edx</span><span style="color: #0000FF;">=</span><span style="color: #7060A8;">length</span><span style="color: #0000FF;">(</span><span style="color: #000000;">l_utf32</span><span style="color: #0000FF;">)</span> <span style="color: #008080;">or</span> <span style="color: #7060A8;">find</span><span style="color: #0000FF;">(</span><span style="color: #000000;">l_utf32</span><span style="color: #0000FF;">[</span><span style="color: #000000;">edx</span><span style="color: #0000FF;">+</span><span style="color: #000000;">1</span><span style="color: #0000FF;">],</span><span style="color: #000000;">spunc</span><span style="color: #0000FF;">))</span> <span style="color: #008080;">then</span>
<span style="color: #000000;">t_utf32</span><span style="color: #0000FF;">[</span><span style="color: #000000;">idx</span><span style="color: #0000FF;">..</span><span style="color: #000000;">edx</span><span style="color: #0000FF;">]</span> <span style="color: #0000FF;">=</span> <span style="color: #7060A8;">repeat</span><span style="color: #0000FF;">(</span><span style="color: #008000;">'X'</span><span style="color: #0000FF;">,</span><span style="color: #000000;">utf32_length</span><span style="color: #0000FF;">(</span><span style="color: #000000;">t_utf32</span><span style="color: #0000FF;">[</span><span style="color: #000000;">idx</span><span style="color: #0000FF;">..</span><span style="color: #000000;">edx</span><span style="color: #0000FF;">]))</span>
<span style="color: #008080;">end</span> <span style="color: #008080;">if</span>
<span style="color: #008080;">elsif</span> <span style="color: #000000;">options</span><span style="color: #0000FF;">=</span><span style="color: #000000;">PARTIAL</span>
<span style="color: #008080;">or</span> <span style="color: #000000;">options</span><span style="color: #0000FF;">=</span><span style="color: #000000;">OVERKILL</span> <span style="color: #008080;">then</span>
<span style="color: #008080;">if</span> <span style="color: #000000;">options</span><span style="color: #0000FF;">=</span><span style="color: #000000;">OVERKILL</span> <span style="color: #008080;">then</span>
<span style="color: #008080;">while</span> <span style="color: #000000;">idx</span><span style="color: #0000FF;">></span><span style="color: #000000;">1</span> <span style="color: #008080;">and</span> <span style="color: #008080;">not</span> <span style="color: #7060A8;">find</span><span style="color: #0000FF;">(</span><span style="color: #000000;">l_utf32</span><span style="color: #0000FF;">[</span><span style="color: #000000;">idx</span><span style="color: #0000FF;">-</span><span style="color: #000000;">1</span><span style="color: #0000FF;">],</span><span style="color: #000000;">spunc</span><span style="color: #0000FF;">)</span> <span style="color: #008080;">do</span> <span style="color: #000000;">idx</span> <span style="color: #0000FF;">-=</span> <span style="color: #000000;">1</span> <span style="color: #008080;">end</span> <span style="color: #008080;">while</span>
<span style="color: #008080;">while</span> <span style="color: #000000;">edx</span><span style="color: #0000FF;"><</span><span style="color: #7060A8;">length</span><span style="color: #0000FF;">(</span><span style="color: #000000;">l_utf32</span><span style="color: #0000FF;">)</span> <span style="color: #008080;">and</span> <span style="color: #008080;">not</span> <span style="color: #7060A8;">find</span><span style="color: #0000FF;">(</span><span style="color: #000000;">l_utf32</span><span style="color: #0000FF;">[</span><span style="color: #000000;">edx</span><span style="color: #0000FF;">+</span><span style="color: #000000;">1</span><span style="color: #0000FF;">],</span><span style="color: #000000;">spunc</span><span style="color: #0000FF;">)</span> <span style="color: #008080;">do</span> <span style="color: #000000;">edx</span> <span style="color: #0000FF;">+=</span> <span style="color: #000000;">1</span> <span style="color: #008080;">end</span> <span style="color: #008080;">while</span>
<span style="color: #008080;">end</span> <span style="color: #008080;">if</span>
<span style="color: #000000;">t_utf32</span><span style="color: #0000FF;">[</span><span style="color: #000000;">idx</span><span style="color: #0000FF;">..</span><span style="color: #000000;">edx</span><span style="color: #0000FF;">]</span> <span style="color: #0000FF;">=</span> <span style="color: #7060A8;">repeat</span><span style="color: #0000FF;">(</span><span style="color: #008000;">'X'</span><span style="color: #0000FF;">,</span><span style="color: #000000;">utf32_length</span><span style="color: #0000FF;">(</span><span style="color: #000000;">t_utf32</span><span style="color: #0000FF;">[</span><span style="color: #000000;">idx</span><span style="color: #0000FF;">..</span><span style="color: #000000;">edx</span><span style="color: #0000FF;">]))</span>
<span style="color: #008080;">end</span> <span style="color: #008080;">if</span>
<span style="color: #000000;">idx</span> <span style="color: #0000FF;">=</span> <span style="color: #000000;">edx</span><span style="color: #0000FF;">+</span><span style="color: #000000;">1</span>
<span style="color: #008080;">end</span> <span style="color: #008080;">while</span>
<span style="color: #000000;">text</span> <span style="color: #0000FF;">=</span> <span style="color: #7060A8;">utf32_to_utf8</span><span style="color: #0000FF;">(</span><span style="color: #000000;">t_utf32</span><span style="color: #0000FF;">)</span>
<span style="color: #008080;">return</span> <span style="color: #0000FF;">{</span><span style="color: #000000;">opt</span><span style="color: #0000FF;">,</span><span style="color: #000000;">text</span><span style="color: #0000FF;">}</span>
<span style="color: #008080;">end</span> <span style="color: #008080;">function</span>
<span style="color: #008080;">constant</span> <span style="color: #000000;">test</span> <span style="color: #0000FF;">=</span> <span style="color: #008000;">`
Tom? Toms bottom tomato is in his stomach while playing the "Tom-tom" brand tom-toms. That's so tom.`</span><span style="color: #0000FF;">,</span>
<span style="color: #000000;">tests</span> <span style="color: #0000FF;">=</span> <span style="color: #0000FF;">{</span><span style="color: #008000;">"Tom"</span><span style="color: #0000FF;">,</span><span style="color: #008000;">"tom"</span><span style="color: #0000FF;">,</span><span style="color: #008000;">"t"</span><span style="color: #0000FF;">}</span>
<span style="color: #008080;">for</span> <span style="color: #000000;">t</span><span style="color: #0000FF;">=</span><span style="color: #000000;">1</span> <span style="color: #008080;">to</span> <span style="color: #7060A8;">length</span><span style="color: #0000FF;">(</span><span style="color: #000000;">tests</span><span style="color: #0000FF;">)</span> <span style="color: #008080;">do</span>
<span style="color: #7060A8;">printf</span><span style="color: #0000FF;">(</span><span style="color: #000000;">1</span><span style="color: #0000FF;">,</span><span style="color: #008000;">"Redact %s:\n"</span><span style="color: #0000FF;">,{</span><span style="color: #000000;">tests</span><span style="color: #0000FF;">[</span><span style="color: #000000;">t</span><span style="color: #0000FF;">]})</span>
<span style="color: #008080;">for</span> <span style="color: #000000;">o</span><span style="color: #0000FF;">=</span><span style="color: #000000;">WHOLE</span> <span style="color: #008080;">to</span> <span style="color: #000000;">OVERKILL</span> <span style="color: #008080;">do</span>
<span style="color: #7060A8;">printf</span><span style="color: #0000FF;">(</span><span style="color: #000000;">1</span><span style="color: #0000FF;">,</span><span style="color: #008000;">"%s:%s\n"</span><span style="color: #0000FF;">,</span><span style="color: #000000;">redact</span><span style="color: #0000FF;">(</span><span style="color: #000000;">test</span><span style="color: #0000FF;">,</span><span style="color: #000000;">tests</span><span style="color: #0000FF;">[</span><span style="color: #000000;">t</span><span style="color: #0000FF;">],</span><span style="color: #000000;">o</span><span style="color: #0000FF;">))</span>
<span style="color: #7060A8;">printf</span><span style="color: #0000FF;">(</span><span style="color: #000000;">1</span><span style="color: #0000FF;">,</span><span style="color: #008000;">"%s:%s\n"</span><span style="color: #0000FF;">,</span><span style="color: #000000;">redact</span><span style="color: #0000FF;">(</span><span style="color: #000000;">test</span><span style="color: #0000FF;">,</span><span style="color: #000000;">tests</span><span style="color: #0000FF;">[</span><span style="color: #000000;">t</span><span style="color: #0000FF;">],</span><span style="color: #000000;">o</span><span style="color: #0000FF;">+</span><span style="color: #000000;">INSENSITIVE</span><span style="color: #0000FF;">))</span>
<span style="color: #008080;">end</span> <span style="color: #008080;">for</span>
<span style="color: #008080;">end</span> <span style="color: #008080;">for</span>
<span style="color: #008080;">constant</span> <span style="color: #000000;">ut</span> <span style="color: #0000FF;">=</span> <span style="color: #008000;">"🧑 👨 🧔 👨👩👦"</span><span style="color: #0000FF;">,</span>
<span style="color: #000000;">fmt</span> <span style="color: #0000FF;">=</span> <span style="color: #008000;">"""
%s
Redact 👨 %s %s
Redact 👨👩👦 %s %s
"""</span>
<span style="color: #7060A8;">printf</span><span style="color: #0000FF;">(</span><span style="color: #000000;">1</span><span style="color: #0000FF;">,</span><span style="color: #000000;">fmt</span><span style="color: #0000FF;">,{</span><span style="color: #000000;">ut</span><span style="color: #0000FF;">}&</span><span style="color: #000000;">redact</span><span style="color: #0000FF;">(</span><span style="color: #000000;">ut</span><span style="color: #0000FF;">,</span><span style="color: #008000;">"👨"</span><span style="color: #0000FF;">,</span><span style="color: #000000;">WHOLE</span><span style="color: #0000FF;">)&</span><span style="color: #000000;">redact</span><span style="color: #0000FF;">(</span><span style="color: #000000;">ut</span><span style="color: #0000FF;">,</span><span style="color: #008000;">"👨👩👦"</span><span style="color: #0000FF;">,</span><span style="color: #000000;">WHOLE</span><span style="color: #0000FF;">))</span>
<!--</syntaxhighlight>-->
{{out}}
w/p/o means whole/partial/overkill word, s/i means case sensitive/insensitive.
<pre>
Redact Tom:
Line 430 ⟶ 1,377:
[o|s]:Tom? Toms XXXXXX XXXXXX is in his XXXXXXX while playing XXX "XXXXXXX" brand XXXXXXXX. XXXXXX so XXX.
[o|i]:XXX? XXXX XXXXXX XXXXXX is in his XXXXXXX while playing XXX "XXXXXXX" brand XXXXXXXX. XXXXXX so XXX.
🧑 👨 🧔 👨👩👦
Redact 👨 [w|s] 🧑 XX 🧔 👨👩👦
Redact 👨👩👦 [w|s] 🧑 👨 🧔 XXXX
</pre>
Line 440 ⟶ 1,387:
{{works with|Rakudo|2020.02}}
<syntaxhighlight lang="raku"
my $rx =
$insensitive ??
Line 502 ⟶ 1,449:
printf "%20s %s\n", "Redact '👨' [p|o]", $emoji.&redact('👨', :p, :o);
printf "%20s %s\n", "Redact '👨👩👦' [p|o]", $emoji.&redact('👨👩👦', :p, :o);
}</
{{out}}
<pre style="height:40ex;overflow:scroll;">Redact 'Tom':
Line 572 ⟶ 1,519:
Redact '👨' [p|o] Argentina🧑🇦🇹 XXXXXXXX Germany🧔🇩🇪 Netherlands👨👩👦🇳🇱
Redact '👨👩👦' [p|o] Argentina🧑🇦🇹 France👨🇫🇷 Germany🧔🇩🇪 XXXXXXXXXXXXX
</pre>
=={{header|REXX}}==
REXX doesn't have ''regular expressions'', so I had to roll-my-own parsing.
<syntaxhighlight lang="rexx">/*REXX program redacts a string (using Xs) from a text, depending upon specified options*/
zDefault= 'Tom? Toms bottom tomato is in his stomach while playing the "Tom-tom"' ,
"brand tom-toms. That's so tom."
parse arg x '~' z /*obtain optional arguments from the CL*/
if x=='' | x=="," then x= 'Tom tom t' /*Not specified? Then use the default.*/
if z= '' | z= "," then z= zDefault /* " " " " " " */
options= 'w│s│n w│i│n p│s│n p│i│n p│s│o p│i│o' /*most glyphs can be used instead of │ */
call build /*build some stemmed arrays for REDACT.*/
do j=1 for words(x); q= word(x, j) /*process each of the needle strings.*/
if j==1 then say 'haystack' z /*show a title if this is the 1at time.*/
say; say 'needle: ' q
do k=1 for words(options); useOpt= word(options, k)
say ' ['useOpt"]" redact(useOpt, q)
end /*k*/
end /*j*/
exit 0 /*stick a fork in it, we're all done. */
/*──────────────────────────────────────────────────────────────────────────────────────*/
build: #= words(z); ?= '█'; !.=
do i=1 for #; n= word(z, i); n= elide(n, 'HEAD',1 )
n= elide(n, 'TAIL',,,-1)
@.0.i= n; upper n; @.1.i= n
end /*k*/; return
/*──────────────────────────────────────────────────────────────────────────────────────*/
elide: parse arg $, hot, LO, HI, inc; L= length($); inc= word(inc 1, 1)
if LO=='' then LO=L; if HI=='' then HI= L
do k=LO for HI by inc; _= substr($, k, 1)
if datatype(_, 'M') then leave; !.hot.i= !.hot.i || _
if inc==1 then $= substr($, 2) /*hot ≡ Heads Or Tails*/
else $= left($, length($) - 1)
end /*k*/; return $ /*elides punctuation. */
/*──────────────────────────────────────────────────────────────────────────────────────*/
opt: parse arg wop; oU= option; upper oU wop; return pos(wop, oU) \== 0
/*──────────────────────────────────────────────────────────────────────────────────────*/
redact: parse arg option,qq; nz=; lu= 0; ww= opt('w'); pp= \ww; ii= opt('i'); oo= opt('o')
qu= qq; upper qu; Lqq= length(qq); if ii then do; upper qq; lu= 1; end
do r=1 for #; a= @.lu.r; na= @.0.r; La= length(a)
if ww then if a==qq then na= copies(?, Lqq)
if pp then do 1; _= pos(qq, a); if _==0 then leave
nn= na; if ii then upper nn
do La; _= pos(qq, nn); if _==0 then leave
na= overlay(?, na, _, Lqq, ?);
nn= na; if ii then upper nn
end /*La*/
end /*1*/
if oo then if pos(?, na)\==0 then na= copies(?, length(na) )
nz= nz !.head.r || na || !.tail.r
end /*r*/
return strip( translate(nz, 'X', ?) )</syntaxhighlight>
{{out|output|text= when using the default inputs:}}
<pre>
haystack Tom? Toms bottom tomato is in his stomach while playing the "Tom-tom" brand tom-toms. That's so tom.
needle: Tom
[w│s│n] XXX? Toms bottom tomato is in his stomach while playing the "Tom-tom" brand tom-toms. That's so tom.
[w│i│n] XXX? Toms bottom tomato is in his stomach while playing the "Tom-tom" brand tom-toms. That's so XXX.
[p│s│n] XXX? XXXs bottom tomato is in his stomach while playing the "XXX-tom" brand tom-toms. That's so tom.
[p│i│n] XXX? XXXs botXXX XXXato is in his sXXXach while playing the "XXX-XXX" brand XXX-XXXs. That's so XXX.
[p│s│o] XXX? XXXX bottom tomato is in his stomach while playing the "XXXXXXX" brand tom-toms. That's so tom.
[p│i│o] XXX? XXXX XXXXXX XXXXXX is in his XXXXXXX while playing the "XXXXXXX" brand XXXXXXXX. That's so XXX.
needle: tom
[w│s│n] Tom? Toms bottom tomato is in his stomach while playing the "Tom-tom" brand tom-toms. That's so XXX.
[w│i│n] XXX? Toms bottom tomato is in his stomach while playing the "Tom-tom" brand tom-toms. That's so XXX.
[p│s│n] Tom? Toms botXXX XXXato is in his sXXXach while playing the "Tom-XXX" brand XXX-XXXs. That's so XXX.
[p│i│n] XXX? XXXs botXXX XXXato is in his sXXXach while playing the "XXX-XXX" brand XXX-XXXs. That's so XXX.
[p│s│o] Tom? Toms XXXXXX XXXXXX is in his XXXXXXX while playing the "XXXXXXX" brand XXXXXXXX. That's so XXX.
[p│i│o] XXX? XXXX XXXXXX XXXXXX is in his XXXXXXX while playing the "XXXXXXX" brand XXXXXXXX. That's so XXX.
needle: t
[w│s│n] Tom? Toms bottom tomato is in his stomach while playing the "Tom-tom" brand tom-toms. That's so tom.
[w│i│n] Tom? Toms bottom tomato is in his stomach while playing the "Tom-tom" brand tom-toms. That's so tom.
[p│s│n] Tom? Toms boXXom XomaXo is in his sXomach while playing Xhe "Tom-Xom" brand Xom-Xoms. ThaX's so Xom.
[p│i│n] Xom? Xoms boXXom XomaXo is in his sXomach while playing Xhe "Xom-Xom" brand Xom-Xoms. XhaX's so Xom.
[p│s│o] Tom? Toms XXXXXX XXXXXX is in his XXXXXXX while playing XXX "XXXXXXX" brand XXXXXXXX. XXXXXX so XXX.
[p│i│o] XXX? XXXX XXXXXX XXXXXX is in his XXXXXXX while playing XXX "XXXXXXX" brand XXXXXXXX. XXXXXX so XXX.
</pre>
=={{header|RPL}}==
≪ DUP2 SWAP 1 DUP SUB POS SIGN DEPTH
→ text seps wip stack <span style="color:grey">@ wip is a flag for a word in progress</span>
≪ wip NOT 1 +
1 text SIZE '''FOR''' j
text j DUP SUB
'''IF''' seps OVER POS wip XOR '''THEN''' + '''ELSE''' 1 wip - 'wip' STO '''END'''
'''NEXT'''
DEPTH stack - 3 + →LIST
≫ ≫ '<span style="color:blue">→TKN</span>' STO <span style="color:grey">@ ( "string" → { wordpos "word" "sep" "word" .. } )</span>
≪ ""
1 3 PICK SIZE '''FOR''' c
OVER c DUP SUB NUM
R→B #20h OR B→R CHR +
'''NEXT''' SWAP DROP
≫ '<span style="color:blue">LOWER</span>' STO
≪ → text pos rep
≪ pos 1 > text 1 pos 1 - SUB "" IFTE
rep +
text pos rep SIZE + OVER SIZE SUB +
≫ ≫ '<span style="color:blue">REPL</span>' STO <span style="color:grey">@ mimics HP-48+ instruction only for strings</span>
≪ DUP2 <span style="color:blue">LOWER</span> SWAP <span style="color:blue">LOWER</span> "" → token word lord loken xxx
≪ xxx 1 7 FS? 9 FS? OR token word IFTE SIZE '''START''' "X" + '''NEXT'''
'''IF''' 7 FC? 9 FC? AND '''THEN'''
'xxx' STO 1 SF loken token
'''DO'''
8 FC? OVER word POS 4 PICK lord POS IFTE
'''IF''' DUP NOT '''THEN''' DROP 1 CF '''ELSE'''
'''IF''' 8 FS? '''THEN''' ROT OVER xxx <span style="color:blue">REPL</span> SWAP '''END'''
xxx <span style="color:blue">REPL</span>
'''END'''
'''UNTIL''' 1 FC? '''END'''
SWAP DROP
'''END'''
≫ ≫ '<span style="color:blue">XREPL</span>' STO <span style="color:grey">@ ( "word" "rd" → "woXX" | "XXXX" ) </span>
≪ DUP 1 GET OVER SIZE '''FOR''' t
DUP t GET <span style="color:blue">LOWER</span>
t SWAP PUT
2 '''STEP'''
≫ '<span style="color:blue">LOTKN</span>' STO <span style="color:grey">@ ( { "TOKENS" } → { "tokens" } ) </span>
≪ 7 9 '''FOR''' f f CF '''NEXT'''
'''IF''' DUP 1 DUP SUB "W" == '''THEN''' 7 SF '''END'''
'''IF''' DUP 2 DUP SUB "I" == '''THEN''' 8 SF '''END'''
'''IF''' 3 DUP SUB "O" == '''THEN''' 9 SF '''END'''
'''IF''' 8 FS? '''THEN''' <span style="color:blue">LOWER</span> '''END'''
SWAP " ,.?'≪≫" <span style="color:blue">→TKN</span> DUP <span style="color:blue">LOTKN</span>
→ word tokens lokens
≪ "" tokens 1 GET
DUP 2 MOD ROT ROT
tokens SIZE '''FOR''' w
8 FS? 'lokens' 'tokens' IFTE w GET
'''IF''' 3 PICK w 2 MOD == '''THEN'''
tokens w GET SWAP
'''IF''' word 7 FS? ≪ == ≫ ≪ POS ≫ IFTE '''THEN''' word <span style="color:blue">XREPL</span> '''END'''
'''END'''
+
'''NEXT'''
≫ ≫ '<span style="color:blue">RDACT</span>' STO <span style="color:grey">@ ( "text" "word" "PAR" → "text" ) </span>
≪ "Tom? Toms bottom tomato is in his stomach while playing the ≪Tom-tom≫ brand tom-toms. That's so tom."
{ "WSN" "WIN" "PSN" "PIN" "PSO" "PIO" } → sentence cases
≪ { }
1 6 '''FOR''' k
sentence "Tom" cases k GET <span style="color:blue">RDACT</span> + '''NEXT'''
1 6 '''FOR''' k
sentence "tom" cases k GET <span style="color:blue">RDACT</span> + '''NEXT'''
≫ ≫ '<span style="color:blue">TASK</span>' STO
{{out}}
<pre>
1: { "XXX? Toms bottom tomato is in his stomach while playing the ≪Tom-tom≫ brand tom-toms. That's so tom."
"XXX? Toms bottom tomato is in his stomach while playing the ≪Tom-tom≫ brand tom-toms. That's so XXX."
"XXX? XXXs bottom tomato is in his stomach while playing the ≪XXX-tom≫ brand tom-toms. That's so tom."
"XXX? XXXs botXXX XXXato is in his sXXXach while playing the ≪XXX-XXX≫ brand XXX-XXXs. That's so XXX."
"XXX? XXXX bottom tomato is in his stomach while playing the ≪XXXXXXX≫ brand tom-toms. That's so tom."
"XXX? XXXX XXXXXX XXXXXX is in his XXXXXXX while playing the ≪XXXXXXX≫ brand XXXXXXXX. That's so XXX."
"Tom? Toms bottom tomato is in his stomach while playing the ≪Tom-tom≫ brand tom-toms. That's so XXX."
"XXX? Toms bottom tomato is in his stomach while playing the ≪Tom-tom≫ brand tom-toms. That's so XXX."
"Tom? Toms botXXX XXXato is in his sXXXach while playing the ≪Tom-XXX≫ brand XXX-XXXs. That's so XXX."
"XXX? XXXs botXXX XXXato is in his sXXXach while playing the ≪XXX-XXX≫ brand XXX-XXXs. That's so XXX."
"Tom? Toms XXXXXX XXXXXX is in his XXXXXXX while playing the ≪XXXXXXX≫ brand XXXXXXXX. That's so XXX."
"XXX? XXXX XXXXXX XXXXXX is in his XXXXXXX while playing the ≪XXXXXXX≫ brand XXXXXXXX. That's so XXX." }
</pre>
=={{header|Swift}}==
{{trans|AppleScript}}
<syntaxhighlight lang="swift">import Foundation
struct RedactionOptions: OptionSet {
let rawValue: Int
static let wholeWord = RedactionOptions(rawValue: 1 << 0)
static let overKill = RedactionOptions(rawValue: 1 << 1)
static let caseInsensitive = RedactionOptions(rawValue: 1 << 2)
}
func redact(text: String, target: String, options: RedactionOptions) throws -> String {
// Set up a regex search pattern for the specified target.
// Since it has to be able to match grapheme characters which may
// be combinations of others in the same string, include catches
// for "Zero Width Joiner" characters.
var pattern = "(?<!\\u200d)" + NSRegularExpression.escapedPattern(for: target) + "(?!\\u200d)"
if options.contains(.wholeWord) {
// Don't match where preceded or followed by either a hyphen
// or anything which isn't punctuation or white space.
pattern = "(?<![-[^[:punct:]\\s]])" + pattern + "(?![-[^[:punct:]\\s]])"
} else if options.contains(.overKill) {
// Include any preceding or following run of hyphens and/or
// non-(punctuation or white-space).
pattern = "[-[^[:punct:]\\s]]*" + pattern + "[-[^[:punct:]\\s]]*+"
}
// Default to case-sensitivity.
if options.contains(.caseInsensitive) {
pattern = "(?i)" + pattern
}
let regex = try NSRegularExpression(pattern: pattern)
let mutableText = NSMutableString(string: text)
// Locate all the matches in the text and replace each character
// or grapheme in the matched ranges with "X".
for match in regex.matches(in: text, range: NSRange(text.startIndex..., in: text)) {
mutableText.replaceOccurrences(of: ".(?:\\u200d.)*+", with: "X",
options: .regularExpression, range: match.range)
}
return mutableText as String
}
func optionString(options: RedactionOptions) -> String {
var result = options.contains(.wholeWord) ? "w" : "p"
result.append("|")
result.append(options.contains(.caseInsensitive) ? "i" : "s")
result.append("|")
result.append(options.contains(.overKill) ? "o" : "n")
return result
}
func doBasicTest(target: String, options: RedactionOptions) {
let text = "Tom? Toms bottom tomato is in his stomach while playing the \"Tom-tom\" brand tom-toms. That's so tom."
do {
try print("[\(optionString(options: options))]: \(redact(text: text, target: target, options: options))")
} catch {
print(error.localizedDescription)
}
}
func doBasicTests(target: String) {
print("Redact '\(target)':")
doBasicTest(target: target, options: .wholeWord)
doBasicTest(target: target, options: [.wholeWord, .caseInsensitive])
doBasicTest(target: target, options: [])
doBasicTest(target: target, options: .caseInsensitive)
doBasicTest(target: target, options: .overKill)
doBasicTest(target: target, options: [.overKill, .caseInsensitive])
}
func doExtraTest(target: String) {
let text = "🧑 👨 🧔 👨👩👦"
do {
try print("Redact '\(target)':\n[w]: \(redact(text: text, target: target, options: .wholeWord))")
} catch {
print(error.localizedDescription)
}
}
doBasicTests(target: "Tom")
print()
doBasicTests(target: "tom")
print()
doExtraTest(target: "👨")
print()
doExtraTest(target: "👨👩👦")</syntaxhighlight>
{{out}}
<pre>
Redact 'Tom':
[w|s|n]: XXX? Toms bottom tomato is in his stomach while playing the "Tom-tom" brand tom-toms. That's so tom.
[w|i|n]: XXX? Toms bottom tomato is in his stomach while playing the "Tom-tom" brand tom-toms. That's so XXX.
[p|s|n]: XXX? XXXs bottom tomato is in his stomach while playing the "XXX-tom" brand tom-toms. That's so tom.
[p|i|n]: XXX? XXXs botXXX XXXato is in his sXXXach while playing the "XXX-XXX" brand XXX-XXXs. That's so XXX.
[p|s|o]: XXX? XXXX bottom tomato is in his stomach while playing the "XXXXXXX" brand tom-toms. That's so tom.
[p|i|o]: XXX? XXXX XXXXXX XXXXXX is in his XXXXXXX while playing the "XXXXXXX" brand XXXXXXXX. That's so XXX.
Redact 'tom':
[w|s|n]: Tom? Toms bottom tomato is in his stomach while playing the "Tom-tom" brand tom-toms. That's so XXX.
[w|i|n]: XXX? Toms bottom tomato is in his stomach while playing the "Tom-tom" brand tom-toms. That's so XXX.
[p|s|n]: Tom? Toms botXXX XXXato is in his sXXXach while playing the "Tom-XXX" brand XXX-XXXs. That's so XXX.
[p|i|n]: XXX? XXXs botXXX XXXato is in his sXXXach while playing the "XXX-XXX" brand XXX-XXXs. That's so XXX.
[p|s|o]: Tom? Toms XXXXXX XXXXXX is in his XXXXXXX while playing the "XXXXXXX" brand XXXXXXXX. That's so XXX.
[p|i|o]: XXX? XXXX XXXXXX XXXXXX is in his XXXXXXX while playing the "XXXXXXX" brand XXXXXXXX. That's so XXX.
Redact '👨':
[w]: 🧑 X 🧔 👨👩👦
Redact '👨👩👦':
[w]: 🧑 👨 🧔 X
</pre>
=={{header|Tailspin}}==
This is using the normal definition of words, i.e. emoji do not form words or word boundaries, so the stretch assignment must be matched as a partial match. This solution parses the flags inline and takes the secret to be redacted as a parameter to illustrate both options, although in a production solution I would imagine one might pass both the same way.
<syntaxhighlight lang="tailspin">
composer redact&{secret:}
@: { fill: '', leftBound: '\b{g}', rightBound: '\b{g}', case: '' };
(<flags> <WS>*) [ <redact|keep>* ] -> '$...;'
rule flags: <='['> <word|partial> <='|'> <insensitive|sensitive> <='|'> <overkill|normal> <=']'>
rule word: (<='w'> -> ..|@:{leftBound: '(?<!-)\b', rightBound: '\b(?!\-)'};)
rule partial: <='p'>
rule insensitive: (<='i'> -> ..|@:{case: '(?i)'};)
rule sensitive: <='s'>
rule overkill: (<='o'> -> ..|@:{leftBound: '(?<!\-)\b', rightBound: '\b(?!\-)', fill: '[\w\-]*'};)
rule normal: <='n'>
rule redact: <'(?uU)$@.case;$@.leftBound;$@.fill;$secret;$@.fill;$@.rightBound;'> -> [$... -> 'X'] -> '$...;'
rule keep: <~redact>
end redact
def target: 'Tom? Toms bottom tomato is in his stomach while playing the "Tom-tom" brand tom-toms. That''s so tom.';
def options: ['[w|s|n]', '[w|i|n]', '[p|s|n]', '[p|i|n]', '[p|s|o]', '[p|i|o]'];
'Redacting Tom:
' -> !OUT::write
$options... -> \('$;: ' -> !OUT::write '$; $target;' -> redact&{secret: 'Tom'} -> '$;
' -> !OUT::write \) -> !VOID
'
Redacting tom:
' -> !OUT::write
$options... -> \('$;: ' -> !OUT::write '$; $target;' -> redact&{secret: 'tom'} -> '$;
' -> !OUT::write \) -> !VOID
'🧑 👨 🧔 👨👩👦' -> '[p|s|n] $;' -> redact&{secret: '👨'} -> '
$;
' -> !OUT::write
'🧑 👨 🧔 👨👩👦' -> '[p|s|n] $;' -> redact&{secret: '👨👩👦'} -> '
$;
' -> !OUT::write
</syntaxhighlight>
{{out}}
<pre>
Redacting Tom:
[w|s|n]: XXX? Toms bottom tomato is in his stomach while playing the "Tom-tom" brand tom-toms. That's so tom.
[w|i|n]: XXX? Toms bottom tomato is in his stomach while playing the "Tom-tom" brand tom-toms. That's so XXX.
[p|s|n]: XXX? XXXs bottom tomato is in his stomach while playing the "XXX-tom" brand tom-toms. That's so tom.
[p|i|n]: XXX? XXXs botXXX XXXato is in his sXXXach while playing the "XXX-XXX" brand XXX-XXXs. That's so XXX.
[p|s|o]: XXX? XXXX bottom tomato is in his stomach while playing the "XXXXXXX" brand tom-toms. That's so tom.
[p|i|o]: XXX? XXXX XXXXXX XXXXXX is in his XXXXXXX while playing the "XXXXXXX" brand XXXXXXXX. That's so XXX.
Redacting tom:
[w|s|n]: Tom? Toms bottom tomato is in his stomach while playing the "Tom-tom" brand tom-toms. That's so XXX.
[w|i|n]: XXX? Toms bottom tomato is in his stomach while playing the "Tom-tom" brand tom-toms. That's so XXX.
[p|s|n]: Tom? Toms botXXX XXXato is in his sXXXach while playing the "Tom-XXX" brand XXX-XXXs. That's so XXX.
[p|i|n]: XXX? XXXs botXXX XXXato is in his sXXXach while playing the "XXX-XXX" brand XXX-XXXs. That's so XXX.
[p|s|o]: Tom? Toms XXXXXX XXXXXX is in his XXXXXXX while playing the "XXXXXXX" brand XXXXXXXX. That's so XXX.
[p|i|o]: XXX? XXXX XXXXXX XXXXXX is in his XXXXXXX while playing the "XXXXXXX" brand XXXXXXXX. That's so XXX.
🧑 X 🧔 👨👩👦
🧑 👨 🧔 X
</pre>
=={{header|Wren}}==
{{trans|Go}}
{{libheader|Wren-pattern}}
{{libheader|Wren-str}}
{{libheader|Wren-upc}}
<syntaxhighlight lang="wren">import "./pattern" for Pattern
import "./str" for Str
import "./upc" for Graphemes
var join = Fn.new { |words, seps|
var lw = words.count
var ls = seps.count
if (lw != ls + 1) {
Fiber.abort("Mismatch between number of words and separators.")
}
var sb = ""
for (i in 0...ls) {
sb = sb + words[i]
sb = sb + seps[i]
}
sb = sb + words[lw-1]
return sb
}
var redact = Fn.new { |text, word, opts|
var partial = opts.contains("p")
var overkill = opts.contains("o")
var insensitive = opts.contains("i")
var i = " \t\n\r!\"#$\%&()*+,./:;<=>?@[\\]^`{|}~" // all punctuation except -'_
var p = Pattern.new("+1/i", 0, i)
var matches = p.findAll(text)
var seps = Pattern.matchesText(matches)
var words = p.splitAll(text)
var expr = insensitive ? Str.lower(word) : word
var p2 = Pattern.new(expr)
for (i in 0...words.count) {
var w = words[i]
var wl = insensitive ? Str.lower(w) : w
var m = p2.find(wl)
if (m && wl.indexOf(m.text + "\u200d") == -1 && wl.indexOf("\u200d" + m.text) == -1) {
if (overkill) {
words[i] = "X" * Graphemes.clusterCount(w)
} else if (!partial) {
if (wl == m.text) words[i] = "X" * Graphemes.clusterCount(w)
} else if (partial) {
var repl = "X" * Graphemes.clusterCount(word)
words[i] = p2.replaceAll(wl, repl)
}
}
}
System.print("%(opts) %(join.call(words, seps))\n")
}
var printResults = Fn.new { |text, allOpts, allWords|
System.print("Text: %(text)\n")
for (word in allWords) {
System.print("Redact '%(word)':")
for (opts in allOpts) redact.call(text, word, opts)
}
System.print()
}
var text = "Tom? Toms bottom tomato is in his stomach while playing the \"Tom-tom\" brand tom-toms. That's so tom.
'Tis very tomish, don't you think?"
var allOpts = ["[w|s|n]", "[w|i|n]", "[p|s|n]", "[p|i|n]", "[p|s|o]", "[p|i|o]"]
var allWords = ["Tom", "tom", "t"]
printResults.call(text, allOpts, allWords)
text = "🧑 👨 🧔 👨👩👦"
allOpts = ["[w]"]
allWords = ["👨", "👨👩👦"]
printResults.call(text, allOpts, allWords)
text = "Argentina🧑🇦🇹 France👨🇫🇷 Germany🧔🇩🇪 Netherlands👨👩👦🇳🇱"
allOpts = ["[p]", "[p|o]"]
printResults.call(text, allOpts, allWords)</syntaxhighlight>
{{out}}
<pre>
Text: Tom? Toms bottom tomato is in his stomach while playing the "Tom-tom" brand tom-toms. That's so tom.
'Tis very tomish, don't you think?
Redact 'Tom':
[w|s|n] XXX? Toms bottom tomato is in his stomach while playing the "Tom-tom" brand tom-toms. That's so tom.
'Tis very tomish, don't you think?
[w|i|n] XXX? Toms bottom tomato is in his stomach while playing the "Tom-tom" brand tom-toms. That's so XXX.
'Tis very tomish, don't you think?
[p|s|n] XXX? XXXs bottom tomato is in his stomach while playing the "XXX-tom" brand tom-toms. That's so tom.
'Tis very tomish, don't you think?
[p|i|n] XXX? XXXs botXXX XXXato is in his sXXXach while playing the "XXX-XXX" brand XXX-XXXs. That's so XXX.
'Tis very XXXish, don't you think?
[p|s|o] XXX? XXXX bottom tomato is in his stomach while playing the "XXXXXXX" brand tom-toms. That's so tom.
'Tis very tomish, don't you think?
[p|i|o] XXX? XXXX XXXXXX XXXXXX is in his XXXXXXX while playing the "XXXXXXX" brand XXXXXXXX. That's so XXX.
'Tis very XXXXXX, don't you think?
Redact 'tom':
[w|s|n] Tom? Toms bottom tomato is in his stomach while playing the "Tom-tom" brand tom-toms. That's so XXX.
'Tis very tomish, don't you think?
[w|i|n] XXX? Toms bottom tomato is in his stomach while playing the "Tom-tom" brand tom-toms. That's so XXX.
'Tis very tomish, don't you think?
[p|s|n] Tom? Toms botXXX XXXato is in his sXXXach while playing the "Tom-XXX" brand XXX-XXXs. That's so XXX.
'Tis very XXXish, don't you think?
[p|i|n] XXX? XXXs botXXX XXXato is in his sXXXach while playing the "XXX-XXX" brand XXX-XXXs. That's so XXX.
'Tis very XXXish, don't you think?
[p|s|o] Tom? Toms XXXXXX XXXXXX is in his XXXXXXX while playing the "XXXXXXX" brand XXXXXXXX. That's so XXX.
'Tis very XXXXXX, don't you think?
[p|i|o] XXX? XXXX XXXXXX XXXXXX is in his XXXXXXX while playing the "XXXXXXX" brand XXXXXXXX. That's so XXX.
'Tis very XXXXXX, don't you think?
Redact 't':
[w|s|n] Tom? Toms bottom tomato is in his stomach while playing the "Tom-tom" brand tom-toms. That's so tom.
'Tis very tomish, don't you think?
[w|i|n] Tom? Toms bottom tomato is in his stomach while playing the "Tom-tom" brand tom-toms. That's so tom.
'Tis very tomish, don't you think?
[p|s|n] Tom? Toms boXXom XomaXo is in his sXomach while playing Xhe "Tom-Xom" brand Xom-Xoms. ThaX's so Xom.
'Tis very Xomish, don'X you Xhink?
[p|i|n] Xom? Xoms boXXom XomaXo is in his sXomach while playing Xhe "Xom-Xom" brand Xom-Xoms. XhaX's so Xom.
'Xis very Xomish, don'X you Xhink?
[p|s|o] Tom? Toms XXXXXX XXXXXX is in his XXXXXXX while playing XXX "XXXXXXX" brand XXXXXXXX. XXXXXX so XXX.
'Tis very XXXXXX, XXXXX you XXXXX?
[p|i|o] XXX? XXXX XXXXXX XXXXXX is in his XXXXXXX while playing XXX "XXXXXXX" brand XXXXXXXX. XXXXXX so XXX.
XXXX very XXXXXX, XXXXX you XXXXX?
Text: 🧑 👨 🧔 👨👩👦
Redact '👨':
[w] 🧑 X 🧔 👨👩👦
Redact '👨👩👦':
[w] 🧑 👨 🧔 X
Text: Argentina🧑🇦🇹 France👨🇫🇷 Germany🧔🇩🇪 Netherlands👨👩👦🇳🇱
Redact '👨':
[p] Argentina🧑🇦🇹 FranceX🇫🇷 Germany🧔🇩🇪 Netherlands👨👩👦🇳🇱
[p|o] Argentina🧑🇦🇹 XXXXXXXX Germany🧔🇩🇪 Netherlands👨👩👦🇳🇱
Redact '👨👩👦':
[p] Argentina🧑🇦🇹 France👨🇫🇷 Germany🧔🇩🇪 NetherlandsX🇳🇱
[p|o] Argentina🧑🇦🇹 France👨🇫🇷 Germany🧔🇩🇪 XXXXXXXXXXXXX
</pre>
| |||