1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
package Torello.HTML;

import java.util.*;
import java.util.regex.*;
import java.util.stream.*;

import Torello.Java.*;


/**
 * Easy utilities for escaping and un-escaping HTML characters such as {@code  }, and even
 * code-point based Emoji's.
 * 
 * <EMBED CLASS='external-html' DATA-FILE-ID=ESCAPE>
 */
@Torello.JavaDoc.StaticFunctional
public final class Escape
{
    private Escape() { }


    // ********************************************************************************************
    // ********************************************************************************************
    // Internal Fields, used by this class only
    // ********************************************************************************************
    // ********************************************************************************************


    /**
     * Regular Expression for characters represented in HTML as
     * <CODE>&amp;#x[Hexadecimal-Code];</CODE>
     */
    private static final Pattern HEX_CODE = Pattern.compile("&#x([A-F,a-f,\\d]{1,8});");

    /**
     * Regular Expression for characters represented in HTML as <CODE>&amp;#[Decimal-Code];</CODE>
     */
    private static final Pattern DEC_CODE = Pattern.compile("&#(\\d{1,8});");

    /**
     * Regular Expression (approximate, not exact) for hard-coded escape sequences such as
     * <CODE>"&amp;amp;"</CODE>
     * 
     * <BR /><BR />This is <I>"approximate"</I> - because it does not actually look the sequence
     * up in the hash table.  This means, of course, that not everything which matches this Regular
     * Expression Pattern is actually an escaped HTML ASCII/UniCode character.
     * 
     * <BR /><BR /><B CLASS=JDDescLabel>For Example:</B>
     * 
     * <BR /><CODE>&amp;NotACode;</CODE> will match this Regular-Expression, but it is not an
     * actual HTML Escape-sequence.  For that, one needs to consult the internal
     * {@code 'htmlEscSeq'} or {@code 'htmlEscChars'} tables themselves.
     * 
     * @see #htmlEscChars
     * @see #htmlEscSeq
     */
    private static final Pattern TEXT_CODE = Pattern.compile("&[A-Z,a-z,0-9]{1,8};");

    @SuppressWarnings("rawtypes")
    private static final Vector data = LFEC.readObjectFromFile_JAR
        (Escape.class, "data-files/Escape.htdat", true, Vector.class);

    /** 
     * This {@code Hashtable} contains all of the HTML escape characters which are represented by
     * a short Text-{@code String}.  The file listed above contains that list.
     * 
     * @see HTML_ESC_CHARS
     */
    @SuppressWarnings("unchecked")
    private static final Hashtable<String, Character> htmlEscChars = 
        (Hashtable<String, Character>) data.elementAt(0);

    /**
     * This {@code Hashtable} is the reverse of the previous table.  It allows a user to look up
     * the escape sequence, given a particular ASCII {@code char}.
     * 
     * @see HTML_ESC_CHARS
     * @see #htmlEscChars
     */
    @SuppressWarnings("unchecked")
    private static final Hashtable<Character, String> htmlEscSeq =
        (Hashtable<Character, String>) data.elementAt(1);


    // ********************************************************************************************
    // ********************************************************************************************
    // Some debug, and "View Data" methods
    // ********************************************************************************************
    // ********************************************************************************************


    /**
     * Print's the HTML Escape Character lookup table to {@code System.out}.
     * This is useful for debugging.
     * 
     * <BR /><BR /><B CLASS=JDDescLabel>View Escape-Codes:</B>
     * 
     * <BR />The JAR Data-File List included within the page attached (below) is a complete list of
     * all <B><CODE>text-String</B> HTML Escape Sequences </CODE> that are known to this class.  
     * This list, does not include any <CODE>Code Point, Hex</CODE> or <CODE>Decimal Number</CODE>
     * sequences.
     *
     * <BR /><BR /><B><CODE><A HREF="doc-files/EscapeCodes.html">
     * All HTML Escape Sequences</A></CODE></B>
     */
    public static void printHTMLEsc()
    {
        Enumeration<String> e = htmlEscChars.keys();

        while (e.hasMoreElements())
        {
            String tag = e.nextElement();
            System.out.println("&" + tag + "; ==> " + htmlEscChars.get(tag));
        }
    }


    // ********************************************************************************************
    // ********************************************************************************************
    // Main Part of the class
    // ********************************************************************************************
    // ********************************************************************************************


    /**
     * Converts a single {@code String} from an HTML-escape sequence into the appropriate
     * character.
     * 
     * <BR /><BR />
     * <CODE>&amp;[escape-sequence];</CODE> ==&gt; actual ASCII or UniCode character.
     *
     * @param escHTML An HTML escape sequence.
     * 
     * @return the {@code ASCII} or {@code Unicode} character represented by this escape sequence.
     * 
     * <BR /><BR />This method will return {@code '0'} if the input it does not represent a valid
     * HTML Escape sequence.
     */
    public static char escHTMLToChar(String escHTML)
    {
        if (! escHTML.startsWith("&") || ! escHTML.endsWith(";")) return (char) 0;

        String  s = escHTML.substring(1, escHTML.length() - 1);

        // Temporary Variable.
        int     i = 0;

        // Since the EMOJI Escape Sequences use Code Point, they cannot, generally be
        // converted into a single Character.  Skip them.

        if (HEX_CODE.matcher(s).find())
        {
            if ((i = Integer.parseInt(s.substring(2), 16)) < Character.MAX_VALUE)
                return (char) i;
            else
                return 0;
        }

        // Again, deal with Emoji's here...  Parse the integer, and make sure it is a
        // character in the standard UNICODE range.

        if (DEC_CODE.matcher(s).find()) 
        {
            if ((i = Integer.parseInt(s.substring(1))) < Character.MAX_VALUE)
                return (char) i;
            else
                return 0;
        }

        // Now check if the provided Escape String is listed in the htmlEscChars Hashtable.
        Character c = htmlEscChars.get(s);

        // If the character was found in the table that lists all escape sequence characters,
        // then return it.  Otherwise just return ASCII zero.

        return (c != null) ? c.charValue() : 0;
    }

    /**
     * Will generate a {@code String} whereby any &amp; all <B STYLE='color: red;'><I>Hexadecimal
     * Escape Sequences</I></B> have been removed and subsequently replaced with their actual
     * ASCII/UniCode un-escaped characters!
     * 
     * <BR /><BR /><B CLASS=JDDescLabel>Hexadecimal HTML Escape-Sequence Examples:</B>
     * 
     * <BR /><TABLE CLASS=JDBriefTable>
     * <TR><TH>Substring from Input:</TH><TH>Web-Browser Converts To:</TH></TR>
     * <TR><TD><CODE>&amp;#xAA;</CODE></TD><TD><CODE>'&#xAA;'</CODE> within a browser</TD></TR>
     * <TR><TD><CODE>&amp;#x67;</CODE></TD><TD><CODE>'&#x67;'</CODE> within a browser</TD></TR>
     * <TR><TD><CODE>&amp;#x84;</CODE></TD><TD><CODE>'&#x84;'</CODE> within a browser</TD></TR>
     * </TABLE>
     * 
     * <BR />This method might be thought of as similar to the older C/C++ {@code 'Ord()'}
     * function, except it is for HTML.
     * 
     * @param str any {@code String} that contains an HTML Escape Sequence
     * &amp;#x[HEXADECIMAL VALUE];
     * 
     * @return a {@code String}, with all of the hexadecimal escape sequences removed and replaced
     * with their equivalent ASCII or UniCode Characters.
     * 
     * @see #replaceAll_DEC(String str)
     * @see StrReplace#r(String, String[], char[])
     */
    public static String replaceAll_HEX(String str)
    {
        // This is the RegEx Matcher from the top.  It matches string's that look like: &#x\d+;
        Matcher m = HEX_CODE.matcher(str);

        // Save the escape-string regex search matches in a TreeMap.  We need to use a
        // TreeMap because it is much easier to check if a particular escape sequence has already
        // been found.  It is easier to find duplicates with TreeMap's.

        TreeMap<String, Character> escMap = new TreeMap<>();

        while (m.find())
        {
            // Use Base-16 Integer-Parse
            int i = Integer.valueOf(m.group(1), 16);

            // Do not un-escape EMOJI's... It makes a mess - they are sequences of characters
            // not single characters.

            if (i > Character.MAX_VALUE) continue;

            // Retrieve the Text Information about the HTML Escape Sequence
            String text = m.group();

            // Check if it is a valid HTML 5 Escape Sequence.
            if (! escMap.containsKey(text)) escMap.put(text, Character.valueOf((char) i));
        }
        
        // Build the matchStr's and replaceChar's arrays.  These are just the KEY's and
        // the VALUE's of the TreeMap<String, Character> which was just built.
        // NOTE: A TreeMap is used *RATHER THAN* two parallel arrays in order to avoid keeping
        //       duplicates when the replacement occurs.

        String[]    matchStrs       = escMap.keySet().toArray(new String[escMap.size()]);
        char[]      replaceChars    = new char[escMap.size()];

        // Lookup each "ReplaceChar" in the TreeMap, and put it in the output "replaceChars"
        // array.  The class StrReplace will replace all the escape squences with the actual
        // characters.

        for (int i=0; i < matchStrs.length; i++) replaceChars[i] = escMap.get(matchStrs[i]);

        return StrReplace.r(str, matchStrs, replaceChars);
    }

    /**
     * This method functions the same as {@code replaceAll_HEX(String)} - except it replaces only
     * HTML Escape sequences that are represented using decimal (base-10) values.
     * {@code 'replaceAll_HEX(...)'} works on hexadecimal (base-16) values.
     * 
     * <BR /><BR /><B CLASS=JDDescLabel>Base-10 HTML Escape-Sequence Examples:</B>
     * 
     * <BR /><TABLE CLASS=JDBriefTable>
     * <TR><TH>Substring from Input:</TH><TH>Web-Browser Converts To:</TH></TR>
     * <TR><TD><CODE>&amp;#48;</CODE></TD><TD><CODE>'&#48;'</CODE> in your browser</TD></TR>
     * <TR><TD><CODE>&amp;#64;</CODE></TD><TD><CODE>'&#64;'</CODE> in your browser</TD></TR>
     * <TR><TD><CODE>&amp;#123;</CODE></TD><TD><CODE>'&#123;'</CODE> in your browser</TD></TR>
     * <TR><TD><CODE>&amp;#125;</CODE></TD><TD><CODE>'&#125;'</CODE> in your browser</TD></TR>
     * </TABLE>
     * 
     * <BR /><B CLASS=JDDescLabel>Base-10 &amp; Base-16 Escape-Sequence Difference:</B>
     * 
     * <BR /><UL CLASS=JDUL>
     * <LI> <CODE>&amp;#x[hex base-16 value];</CODE>  There is an {@code 'x'} as the third character
     *      in  the {@code String}
     * </LI>
     * <LI> <CODE>&amp;#[decimal base-10 value];</CODE>  There is no {@code 'x'} in the
     *      escape-sequence  {@code String!}
     * </LI>
     * </UL>
     * 
     * <BR />This short example delineates the difference between an HTML escape-sequence that
     * employs {@code Base-10} numbers, and one using {@code Base-16} (Hexadecimal) numbers.
     * 
     * @param str any {@code String} that contains the HTML Escape Sequence 
     * <CODE>&amp;#[DECIMAL VALUE];</CODE>.
     * 
     * @return a {@code String}, with all of the decimal escape sequences removed and replaced with
     * ASCII UniCode Characters.
     * 
     * <BR /><BR />If this parameter does not contain such a sequence, then this method will return
     * the same input-{@code String} reference as its return value.  
     * 
     * @see #replaceAll_HEX(String str)
     * @see StrReplace#r(String, String[], char[])
     */
    public static String replaceAll_DEC(String str)
    {
        // This is the RegEx Matcher from the top.  It matches string's that look like: &#\d+;
        Matcher m = DEC_CODE.matcher(str);

        // Save the escape-string regex search matches in a TreeMap.  We need to use a
        // TreeMap because it is much easier to check if a particular escape sequence has already
        // been found.  It is easier to find duplicates with TreeMap's.

        TreeMap<String, Character> escMap = new TreeMap<>();

        while (m.find())
        {
            // Use Base-10 Integer-Parse
            int i = Integer.valueOf(m.group(1));

            // Do not un-escape EMOJI's... It makes a mess - they are sequences of characters
            // not single characters.

            if (i > Character.MAX_VALUE) continue;

            // Retrieve the Text Information about the HTML Escape Sequence
            String text = m.group();

            // Check if it is a valid HTML 5 Escape Sequence.
            if (! escMap.containsKey(text)) escMap.put(text, Character.valueOf((char) i));
        }
        
        // Build the matchStr's and replaceChar's arrays.  These are just the KEY's and
        // the VALUE's of the TreeMap<String, Character> which was just built.
        // NOTE: A TreeMap is used *RATHER THAN* two parallel arrays in order to avoid keeping
        //       duplicates when the replacement occurs.

        String[]    matchStrs       = escMap.keySet().toArray(new String[escMap.size()]);
        char[]      replaceChars    = new char[escMap.size()];

        // Lookup each "ReplaceChar" in the TreeMap, and put it in the output "replaceChars"
        // array.  The class StrReplace will replace all the escape sequences with the actual
        // characters.

        for (int i=0; i < matchStrs.length; i++) replaceChars[i] = escMap.get(matchStrs[i]);

        return StrReplace.r(str, matchStrs, replaceChars);
    }

    /**
     * <EMBED CLASS='external-html' DATA-FILE-ID=ESCAPE_ALL_TEXT>
     * 
     * @param str any {@code String} that contains HTML Escape Sequences that need to be converted
     * to their ASCII-UniCode character representations.
     * 
     * @return a {@code String}, with all of the decimal escape sequences removed and replaced with
     * ASCII UniCode Characters.
     * 
     * @see #replaceAll_HEX(String str)
     * @see StrReplace#r(String, boolean, String[], Torello.Java.Function.ToCharIntTFunc)
     * 
     * @throws IllegalStateException
     */
    public static String replaceAll_TEXT(String str)
    {
        // We only need to find which escape sequences are in this string.
        // use a TreeSet<String> to list them.  It will

        Matcher                 m        = TEXT_CODE.matcher(str);
        TreeMap<String, String> escMap   = new TreeMap<>();

        while (m.find())
        {
            // Retrieve the Text Information about the HTML Escape Sequence
            String text     = m.group();
            String sequence = text.substring(1, text.length() - 1);

            // Check if it is a valid HTML 5 Escape Sequence.
            if ((! escMap.containsKey(text)) && htmlEscChars.containsKey(sequence))
                escMap.put(text, sequence);
        }
        
        // Convert the TreeSet to a String[] array... and use StrReplace
        String[] escArr = new String[escMap.size()];

        return StrReplace.r(
            str, false, escMap.keySet().toArray(escArr),
            (int i, String sequence) -> htmlEscChars.get(escMap.get(sequence))
        );
    }

    /**
     * Calls all of the HTML Escape Sequence convert/replace {@code String} functions at once.
     * 
     * @param s This may be any Java {@code String} which may (or may not) contain HTML Escape
     * sequences.
     * 
     * @return a new {@code String} where all HTML escape-sequence substrings have been replaced 
     * with their natural character representations.
     * 
     * @see #replaceAll_DEC(String)
     * @see #replaceAll_HEX(String)
     * @see #replaceAll_TEXT(String)
     */
    @Deprecated
    public static String replaceAll(String s)
    { return replaceAll_HEX(replaceAll_DEC(replaceAll_TEXT(s))); }

    /**
     * <EMBED CLASS='external-html' DATA-FILE-ID=ESCAPE_REPLACE>
     * 
     * @param s This may be any Java {@code String} which may (or may not) contain HTML Escape
     * sequences.
     * 
     * @return a new {@code String} where all HTML escape-sequence substrings have been replaced 
     * with their natural character representations.
     */
    public static String replace(String s)
    {
        // The primary optimization is to do this the "C" way (As in The C Programming Language)
        // The String to Escape is converted to a character array, and the characters are shifted
        // as the Escape Sequences are replaced.  This is all done "in place" without creating
        // new substring's in memory.

        char[] c = s.toCharArray();

        // These two pointers are kept as the "Source Character" - as in the next character to
        // "Read" ... and the "Destination Character" - as in the next location to write.

        int sourcePos   = 0;
        int destPos     = 0;

        while (sourcePos < c.length)

            // All Escape Sequences begin with the Ampersand Symbol.  If the next character
            // does not begin with the Ampersand, we should skip and move on.  Copy the next source
            // character to the next destination location, and continue the loop.

            if (c[sourcePos] != '&')
            { c[destPos++]=c[sourcePos++];  continue; }
    
            // Here, an Ampersand has been found.  Now check if the character immediately 
            // following the Ampersand is a Pound Sign.  If it is a Pound Sign, that implies
            // this escape sequence is simply going to be a number.

            else if ((sourcePos < (c.length-1)) && (c[sourcePos + 1] == '#'))
            {
                int     evaluatingPos   = sourcePos + 1;
                boolean isHex           = false;

                // If the Character after the Pound Sign is an 'X', it means that the number
                // that has been escaped is a Base 16 (Hexadecimal) number.
                // IMPORTANT: Check to see that the Ampersand wasn't the last char in the String

                if (evaluatingPos + 1 < c.length)
                    if (c[evaluatingPos + 1] == 'x')
                    { isHex = true; evaluatingPos++; }

                // Keep skipping the numbers, until a non-digit character is identified.
                while ((++evaluatingPos < c.length) && Character.isDigit(c[evaluatingPos]));

                // If the character immediately after the last digit isn't a ';' (Semicolon),
                // then this entire thing is NOT an escaped HTML character.  In this case, make
                // sure to copy the next source-character to the next destination location in the
                // char[] array...  Then continue the loop to the next 'char' (after Ampersand)

                if ((evaluatingPos == c.length) || (c[evaluatingPos] != ';'))
                    { c[destPos++]=c[sourcePos++];  continue; }

                int escapedChar;

                try
                { 
                    // Make sure to convert 16-bit numbers using the 16-bit radix using the
                    // standard java parse integer way.

                    escapedChar = isHex
                        ? Integer.parseInt(s.substring(sourcePos + 3, evaluatingPos), 16)
                        : Integer.parseInt(s.substring(sourcePos + 2, evaluatingPos));
                }

                // If for whatever reason java was unable to parse the digits in the escape
                // sequence, then copy the next source-character to the next destination-location
                // and move on in the loop.

                catch (NumberFormatException e)
                    { c[destPos++]=c[sourcePos++];  continue; }

                // If the character was an Emoji, then it would be a number greater than
                // 2^16.  Emoji's use Code Points - which are multiple characters used up
                // together.  Their escape sequences are always characters larger than 65,535.
                // If so, just copy the next source-character to the next destination location, and
                // move on in the loop.

                if (escapedChar > Character.MAX_VALUE)
                    { c[destPos++]=c[sourcePos++];  continue; }

                // Replace the next "Destination Location" with the (un) escaped char.
                c[destPos++] = (char) escapedChar;

                // Skip the entire HTML Escape Sequence by skipping to the location after the
                // position where the "evaluation" (all this processing) was occurring.  This
                // just happens to be the next-character immediately after the semi-colon

                sourcePos = evaluatingPos + 1;  // will be pointing at the ';' (semicolon)
            }

            // An Ampersand was just found, but it was not followed by a '#' (Pound Sign).  This
            // means that it is not a "numbered" (to invent a term) HTML Escape Sequence.  Instead
            // we shall check if there is a valid Escape-String (before the next semi-colon) that
            // can be identified in the Hashtable 'htmlEscChars'

            else if (sourcePos < (c.length - 1))
            {
                // We need to create a 'temp variable' and it will be called "evaluating position"
                int evaluatingPos = sourcePos;

                // All text (non "Numbered") HTML Escape String's are comprised of letter or digits
                while ((++evaluatingPos < c.length) && Character.isLetterOrDigit(c[evaluatingPos]));

                // If the character immediately after the last letter or digit is not a semi-colon,
                // then there is no way this is an HTML Escape Sequence.  Copy the next source to
                // the next destination location, and continue with the loop.

                if ((evaluatingPos == c.length) || (c[evaluatingPos] != ';'))
                    { c[destPos++]=c[sourcePos++];  continue; }

                // Get the replacement character from the lookup table.
                Character replacement = htmlEscChars.get(s.substring(sourcePos + 1, evaluatingPos));

                // The lookup table will return null if there this was not a valid escape sequence.
                // If this was not a valid sequence, just copy the next character from the source
                // location, and move on in the loop.

                if (replacement == null)
                    { c[destPos++]=c[sourcePos++];  continue; }

                c[destPos++]    = replacement;
                sourcePos       = evaluatingPos + 1;
            }

            else
                { c[destPos++]=c[sourcePos++];  continue; }

        return new String(c, 0, destPos);    
    }

    /**
     * <EMBED CLASS='external-html' DATA-FILE-ID=ESCAPE_CHAR>
     * 
     * @param c Any Java Character.  Note that the Java <B>Primitive Type</B> {@code 'char'}
     * is a 16-bit type.  This parameter equates to the <B>UNICODE</B> Characters
     * {@code 0x0000} up to {@code 0xFFFF}.
     * 
     * @param use16BitEscapeSequence If the user would like the returned, escaped, {@code String}
     * to use <B>Base 16</B> for the escaped digits, pass {@code TRUE} to this parameter.  If the
     * user would like to retrieve an escaped {@code String} that uses standard <B>Base 10</B>
     * digits, then pass {@code FALSE} to this parameter.
     * 
     * @return The passed character parameter {@code 'c'} will be converted to an HTML Escape
     * Sequence.  For instance if the character <CODE>'&#6211;'</CODE>, which is the Chinese
     * Character for <I>I, Me, Myself</I> were passed to this method, then the {@code String}
     * {@code "&#25105;"} would be returned.
     * 
     * <BR /><BR />If the parameter {@code 'use16BitEscapeSequence'} had been passed {@code TRUE},
     * then this method would, instead, return the {@code String "&#x6211;"}.
     */
    public static String escChar(char c, boolean use16BitEscapeSequence)
    {
        return use16BitEscapeSequence
            ? "&#" + ((int) c) + ";"
            : "&#x" + Integer.toHexString((int) c).toUpperCase() + ";";
    }

    /**
     * <EMBED CLASS='external-html' DATA-FILE-ID=ESCAPE_CODE_PT>
     * 
     * @param codePoint This will take any integer.  It will be interpreted as a {@code UNICODE}
     * {@code code point}.  
     * 
     * <BR /><BR /><B STYLE="color:red;">NOTE:</B> Java uses <B>16-bit</B> values for it's
     * primitive {@code 'char'} type.  This is also the "first plane" of the <B>UNICODE Space</B>
     * and actually referred to as the <B>Basic Multi Lingual Plane</B>.  Any value passed to this
     * method that is lower than {@code 65,535} would receive the same escape-{@code String} that
     * it would from a call to the method {@link #escChar(char, boolean)}.
     * 
     * @param use16BitEscapeSequence If the user would like the returned, escaped, {@code String}
     * to use <B>Base 16</B> for the escaped digits, pass {@code TRUE} to this parameter.  If the
     * user would like to retrieve an escaped {@code String} that uses standard <B>Base 10</B>
     * digits, then pass {@code FALSE} to this parameter.
     * 
     * @return The {@code code point} will be converted to an HTML Escape Sequence, as a 
     * {@code java.lang.String}.  For instance if the {@code code point} for "the snowman" glyph
     * (character &#x2603;), which happens to be represented by a {@code code point} that is below
     * {@code 65,535} (and, incidentally, does "fit" into a single Java {@code 'char'}) - this
     * method would return the {@code String "&#9731;"}. 
     * 
     * <BR /><BR />If the parameter {@code 'use16BitEscapeSequence'} had been passed {@code TRUE},
     * then this method would, instead, return the {@code String "&#x2603;"}.
     * 
     * @throws IllegalArgumentException Java has a method for determining whether any integer is a
     * valid {@code code point}.  Not all of the integers "fit" into the 17 Unicode "planes".  
     * Note that each of the planes in {@code 'Unicode Space'} contain {@code 65,535}
     * (or {@code 2^16}) characters.
     */
    public static String escCodePoint(int codePoint, boolean use16BitEscapeSequence)
    {
        if (! Character.isValidCodePoint(codePoint)) throw new IllegalArgumentException(
            "The integer you have passed to this method [" + codePoint + "] was deemed an " +
            "invalid Code Point after a call to: [java.lang.Character.isValidCodePoint(int)].  " +
            "Therefore this method is unable to provide an HTML Escape Sequence."
        );

        return use16BitEscapeSequence
            ? "&#" + codePoint + ";"
            : "&#x" + Integer.toHexString(codePoint).toUpperCase() + ";";
    }
    
    /**
     * <EMBED CLASS='external-html' DATA-FILE-ID=ESCAPE_HAS_HTML>
     *
     * @param c Any <B>ASCII</B> or <B>UNICODE</B> Character
     * 
     * @return {@code TRUE} if there is a {@code String} escape sequence for this character, and
     * {@code FALSE} otherwise.
     * 
     * @see #htmlEsc(char)
     */
    public static boolean hasHTMLEsc(char c)
    { return htmlEscSeq.get(Character.valueOf(c)) != null; }

    /**
     * <EMBED CLASS='external-html' DATA-FILE-ID=ESCAPE_HTML_ESC>
     *
     * @param c Any <B>ASCII</B> or <B>UNICODE</B> Character
     * 
     * @return The {@code String} that is used by web-browsers to escape this ASCII / Uni-Code
     * character - <I>if there is one saved</I> in the <B>internal</B> <CODE>Lookup Table</CODE>.
     * If the character provided does not have an associated {@code HTML Escape String}, then
     * 'null' is returned.
     * 
     * <BR /><BR /><B>NOTE:</B> The entire escape-{@code String} is not provided, just the
     * inner-characters.  The leading {@code '&'} (Ampersand) and the trailing {@code ';'} 
     * (Semi-Colon) are not appended to the returned {@code String}.
     * 
     * @see #hasHTMLEsc(char)
     */
    public static String htmlEsc(char c)
    { return htmlEscSeq.get(Character.valueOf(c)); }
}