This file is indexed.

/usr/include/d/std/uri.d is in libphobos2-ldc-dev 1:0.17.1-1ubuntu1.

This file is owned by root:root, with mode 0o644.

The actual contents of the file can be viewed below.

  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
// Written in the D programming language.

/**
 * Encode and decode Uniform Resource Identifiers (URIs).
 * URIs are used in internet transfer protocols.
 * Valid URI characters consist of letters, digits,
 * and the characters $(B ;/?:@&=+$,-_.!~*'())
 * Reserved URI characters are $(B ;/?:@&=+$,)
 * Escape sequences consist of $(B %) followed by two hex digits.
 *
 * See_Also:
 *  $(LINK2 http://www.ietf.org/rfc/rfc3986.txt, RFC 3986)<br>
 *  $(LINK2 http://en.wikipedia.org/wiki/Uniform_resource_identifier, Wikipedia)
 * Macros:
 *  WIKI = Phobos/StdUri
 *
 * Copyright: Copyright Digital Mars 2000 - 2009.
 * License:   $(WEB www.boost.org/LICENSE_1_0.txt, Boost License 1.0).
 * Authors:   $(WEB digitalmars.com, Walter Bright)
 * Source:    $(PHOBOSSRC std/_uri.d)
 */
/*          Copyright Digital Mars 2000 - 2009.
 * Distributed under the Boost Software License, Version 1.0.
 *    (See accompanying file LICENSE_1_0.txt or copy at
 *          http://www.boost.org/LICENSE_1_0.txt)
 */
module std.uri;

//debug=uri;        // uncomment to turn on debugging writefln's
debug(uri) private import std.stdio;

/* ====================== URI Functions ================ */

private import std.ascii;
private import core.stdc.stdlib;
private import std.utf;
private import std.traits : isSomeChar;
import core.exception : OutOfMemoryError;
import std.exception : assumeUnique;

/** This Exception is thrown if something goes wrong when encoding or
decoding a URI.
*/
class URIException : Exception
{
    import std.array : empty;
    @safe pure nothrow this(string msg, string file = __FILE__,
        size_t line = __LINE__, Throwable next = null)
    {
        super("URI Exception" ~ (!msg.empty ? ": " ~ msg : ""), file, line,
            next);
    }
}

private enum
{
    URI_Alpha = 1,
    URI_Reserved = 2,
    URI_Mark = 4,
    URI_Digit = 8,
    URI_Hash = 0x10,        // '#'
}

immutable char[16] hex2ascii = "0123456789ABCDEF";

__gshared ubyte[128] uri_flags;       // indexed by character

shared static this()
{
    // Initialize uri_flags[]
    static void helper(immutable char[] p, uint flags)
    {
        for (int i = 0; i < p.length; i++)
            uri_flags[p[i]] |= flags;
    }

    uri_flags['#'] |= URI_Hash;

    for (int i = 'A'; i <= 'Z'; i++)
    {
        uri_flags[i] |= URI_Alpha;
        uri_flags[i + 0x20] |= URI_Alpha;   // lowercase letters
    }
    helper("0123456789", URI_Digit);
    helper(";/?:@&=+$,", URI_Reserved);
    helper("-_.!~*'()",  URI_Mark);
}


private string URI_Encode(dstring string, uint unescapedSet)
{
    uint j;
    uint k;
    dchar V;
    dchar C;

    // result buffer
    char[50] buffer = void;
    char* R;
    uint Rlen;
    uint Rsize; // alloc'd size

    auto len = string.length;

    R = buffer.ptr;
    Rsize = buffer.length;
    Rlen = 0;

    for (k = 0; k != len; k++)
    {
        C = string[k];
        // if (C in unescapedSet)
        if (C < uri_flags.length && uri_flags[C] & unescapedSet)
        {
            if (Rlen == Rsize)
            {
                char* R2;

                Rsize *= 2;
                if (Rsize > 1024) {
                    R2 = (new char[Rsize]).ptr;
                }
                else
                {
                    R2 = cast(char *)alloca(Rsize * char.sizeof);
                    if (!R2)
                        throw new OutOfMemoryError("Alloca failure");
                }
                R2[0..Rlen] = R[0..Rlen];
                R = R2;
            }
            R[Rlen] = cast(char)C;
            Rlen++;
        }
        else
        {
            char[6] Octet;
            uint L;

            V = C;

            // Transform V into octets
            if (V <= 0x7F)
            {
                Octet[0] = cast(char) V;
                L = 1;
            }
            else if (V <= 0x7FF)
            {
                Octet[0] = cast(char)(0xC0 | (V >> 6));
                Octet[1] = cast(char)(0x80 | (V & 0x3F));
                L = 2;
            }
            else if (V <= 0xFFFF)
            {
                Octet[0] = cast(char)(0xE0 | (V >> 12));
                Octet[1] = cast(char)(0x80 | ((V >> 6) & 0x3F));
                Octet[2] = cast(char)(0x80 | (V & 0x3F));
                L = 3;
            }
            else if (V <= 0x1FFFFF)
            {
                Octet[0] = cast(char)(0xF0 | (V >> 18));
                Octet[1] = cast(char)(0x80 | ((V >> 12) & 0x3F));
                Octet[2] = cast(char)(0x80 | ((V >> 6) & 0x3F));
                Octet[3] = cast(char)(0x80 | (V & 0x3F));
                L = 4;
            }
            /+
            else if (V <= 0x3FFFFFF)
            {
                Octet[0] = cast(char)(0xF8 | (V >> 24));
                Octet[1] = cast(char)(0x80 | ((V >> 18) & 0x3F));
                Octet[2] = cast(char)(0x80 | ((V >> 12) & 0x3F));
                Octet[3] = cast(char)(0x80 | ((V >> 6) & 0x3F));
                Octet[4] = cast(char)(0x80 | (V & 0x3F));
                L = 5;
            }
            else if (V <= 0x7FFFFFFF)
            {
                Octet[0] = cast(char)(0xFC | (V >> 30));
                Octet[1] = cast(char)(0x80 | ((V >> 24) & 0x3F));
                Octet[2] = cast(char)(0x80 | ((V >> 18) & 0x3F));
                Octet[3] = cast(char)(0x80 | ((V >> 12) & 0x3F));
                Octet[4] = cast(char)(0x80 | ((V >> 6) & 0x3F));
                Octet[5] = cast(char)(0x80 | (V & 0x3F));
                L = 6;
            }
            +/
            else
            {
                throw new URIException("Undefined UTF-32 code point");
            }

            if (Rlen + L * 3 > Rsize)
            {
                char *R2;

                Rsize = 2 * (Rlen + L * 3);
                if (Rsize > 1024) {
                    R2 = (new char[Rsize]).ptr;
                }
                else
                {
                    R2 = cast(char *)alloca(Rsize * char.sizeof);
                    if (!R2)
                        throw new OutOfMemoryError("Alloca failure");
                }
                R2[0..Rlen] = R[0..Rlen];
                R = R2;
            }

            for (j = 0; j < L; j++)
            {
                R[Rlen] = '%';
                R[Rlen + 1] = hex2ascii[Octet[j] >> 4];
                R[Rlen + 2] = hex2ascii[Octet[j] & 15];

                Rlen += 3;
            }
        }
    }

    return R[0..Rlen].idup;
}

uint ascii2hex(dchar c)
{
    return (c <= '9') ? c - '0' :
        (c <= 'F') ? c - 'A' + 10 :
        c - 'a' + 10;
}

private dstring URI_Decode(Char)(in Char[] uri, uint reservedSet) if (isSomeChar!Char)
{
    uint j;
    uint k;
    uint V;
    dchar C;

    // Result array, allocated on stack
    dchar* R;
    uint Rlen;

    auto len = uri.length;
    auto s = uri.ptr;

    // Preallocate result buffer R guaranteed to be large enough for result
    auto Rsize = len;
    if (Rsize > 1024 / dchar.sizeof) {
        R = (new dchar[Rsize]).ptr;
    }
    else
    {
        R = cast(dchar *)alloca(Rsize * dchar.sizeof);
        if (!R)
            throw new OutOfMemoryError("Alloca failure");
    }
    Rlen = 0;

    for (k = 0; k != len; k++)
    {
        char B;
        uint start;

        C = s[k];
        if (C != '%')
        {
            R[Rlen] = C;
            Rlen++;
            continue;
        }
        start = k;
        if (k + 2 >= len)
            throw new URIException("Unexpected end of URI");
        if (!isHexDigit(s[k + 1]) || !isHexDigit(s[k + 2]))
            throw new URIException("Expected two hexadecimal digits after '%'");
        B = cast(char)((ascii2hex(s[k + 1]) << 4) + ascii2hex(s[k + 2]));
        k += 2;
        if ((B & 0x80) == 0)
        {
            C = B;
        }
        else
        {
            uint n;

            for (n = 1; ; n++)
            {
                if (n > 4)
                    throw new URIException("UTF-32 code point size too large");
                if (((B << n) & 0x80) == 0)
                {
                    if (n == 1)
                        throw new URIException("UTF-32 code point size too small");
                    break;
                }
            }

            // Pick off (7 - n) significant bits of B from first byte of octet
            V = B & ((1 << (7 - n)) - 1);   // (!!!)

            if (k + (3 * (n - 1)) >= len)
                throw new URIException("UTF-32 unaligned String");
            for (j = 1; j != n; j++)
            {
                k++;
                if (s[k] != '%')
                    throw new URIException("Expected: '%'");
                if (!isHexDigit(s[k + 1]) || !isHexDigit(s[k + 2]))
                    throw new URIException("Expected two hexadecimal digits after '%'");
                B = cast(char)((ascii2hex(s[k + 1]) << 4) + ascii2hex(s[k + 2]));
                if ((B & 0xC0) != 0x80)
                    throw new URIException("Incorrect UTF-32 multi-byte sequence");
                k += 2;
                V = (V << 6) | (B & 0x3F);
            }
            if (V > 0x10FFFF)
                throw new URIException("Unknown UTF-32 code point");
            C = V;
        }
        if (C < uri_flags.length && uri_flags[C] & reservedSet)
        {
            // R ~= s[start .. k + 1];
            int width = (k + 1) - start;
            for (int ii = 0; ii < width; ii++)
                R[Rlen + ii] = s[start + ii];
            Rlen += width;
        }
        else
        {
            R[Rlen] = C;
            Rlen++;
        }
    }
    assert(Rlen <= Rsize);  // enforce our preallocation size guarantee

    // Copy array on stack to array in memory
    return R[0..Rlen].idup;
}

/*************************************
 * Decodes the URI string encodedURI into a UTF-8 string and returns it.
 * Escape sequences that resolve to reserved URI characters are not replaced.
 * Escape sequences that resolve to the '#' character are not replaced.
 */

string decode(Char)(in Char[] encodedURI) if (isSomeChar!Char)
{
    auto s = URI_Decode(encodedURI, URI_Reserved | URI_Hash);
    return std.utf.toUTF8(s);
}

/*******************************
 * Decodes the URI string encodedURI into a UTF-8 string and returns it. All
 * escape sequences are decoded.
 */

string decodeComponent(Char)(in Char[] encodedURIComponent) if (isSomeChar!Char)
{
    auto s = URI_Decode(encodedURIComponent, 0);
    return std.utf.toUTF8(s);
}

/*****************************
 * Encodes the UTF-8 string uri into a URI and returns that URI. Any character
 * not a valid URI character is escaped. The '#' character is not escaped.
 */

string encode(Char)(in Char[] uri) if (isSomeChar!Char)
{
    auto s = std.utf.toUTF32(uri);
    return URI_Encode(s, URI_Reserved | URI_Hash | URI_Alpha | URI_Digit | URI_Mark);
}

/********************************
 * Encodes the UTF-8 string uriComponent into a URI and returns that URI.
 * Any character not a letter, digit, or one of -_.!~*'() is escaped.
 */

string encodeComponent(Char)(in Char[] uriComponent) if (isSomeChar!Char)
{
    auto s = std.utf.toUTF32(uriComponent);
    return URI_Encode(s, URI_Alpha | URI_Digit | URI_Mark);
}

/***************************
 * Does string s[] start with a URL?
 * Returns:
 *  -1   it does not
 *  len  it does, and s[0..len] is the slice of s[] that is that URL
 */

size_t uriLength(Char)(in Char[] s) if (isSomeChar!Char)
{
    /* Must start with one of:
     *  http://
     *  https://
     *  www.
     */
    import std.uni : icmp;

    size_t i;

    if (s.length <= 4)
        return -1;

    if (s.length > 7 && icmp(s[0 .. 7], "http://") == 0) {
        i = 7;
    }
    else
    {
        if (s.length > 8 && icmp(s[0 .. 8], "https://") == 0)
            i = 8;
        else
            return -1;
    }
    //    if (icmp(s[0 .. 4], "www.") == 0)
    //  i = 4;

    size_t lastdot;
    for (; i < s.length; i++)
    {
        auto c = s[i];
        if (isAlphaNum(c))
            continue;
        if (c == '-' || c == '_' || c == '?' ||
                c == '=' || c == '%' || c == '&' ||
                c == '/' || c == '+' || c == '#' ||
                c == '~' || c == '$')
            continue;
        if (c == '.')
        {
            lastdot = i;
            continue;
        }
        break;
    }
    //if (!lastdot || (i - lastdot != 3 && i - lastdot != 4))
    if (!lastdot)
        return -1;

    return i;
}

///
unittest
{
    string s1 = "http://www.digitalmars.com/~fred/fredsRX.html#foo end!";
    assert (uriLength(s1) == 49);
    string s2 = "no uri here";
    assert (uriLength(s2) == -1);
}


/***************************
 * Does string s[] start with an email address?
 * Returns:
 *  -1    it does not
 *  len   it does, and s[0..i] is the slice of s[] that is that email address
 * References:
 *  RFC2822
 */
size_t emailLength(Char)(in Char[] s) if (isSomeChar!Char)
{
    size_t i;

    if (!isAlpha(s[0]))
        return -1;

    for (i = 1; 1; i++)
    {
        if (i == s.length)
            return -1;
        auto c = s[i];
        if (isAlphaNum(c))
            continue;
        if (c == '-' || c == '_' || c == '.')
            continue;
        if (c != '@')
            return -1;
        i++;
        break;
    }

    /* Now do the part past the '@'
     */
    size_t lastdot;
    for (; i < s.length; i++)
    {
        auto c = s[i];
        if (isAlphaNum(c))
            continue;
        if (c == '-' || c == '_')
            continue;
        if (c == '.')
        {
            lastdot = i;
            continue;
        }
        break;
    }
    if (!lastdot || (i - lastdot != 3 && i - lastdot != 4))
        return -1;

    return i;
}

///
unittest
{
    string s1 = "my.e-mail@www.example-domain.com with garbage added";
    assert (emailLength(s1) == 32);
    string s2 = "no email address here";
    assert (emailLength(s2) == -1);
}


unittest
{
    debug(uri) writeln("uri.encodeURI.unittest");

    string source = "http://www.digitalmars.com/~fred/fred's RX.html#foo";
    string target = "http://www.digitalmars.com/~fred/fred's%20RX.html#foo";

    auto result = encode(source);
    debug(uri) writefln("result = '%s'", result);
    assert(result == target);
    result = decode(target);
    debug(uri) writefln("result = '%s'", result);
    assert(result == source);

    result = encode(decode("%E3%81%82%E3%81%82"));
    assert(result == "%E3%81%82%E3%81%82");

    result = encodeComponent("c++");
    assert(result == "c%2B%2B");

    auto str = new char[10_000_000];
    str[] = 'A';
    result = encodeComponent(str);
    foreach (char c; result)
        assert(c == 'A');

    result = decode("%41%42%43");
    debug(uri) writeln(result);

    import std.typetuple : TypeTuple;
    foreach (StringType; TypeTuple!(char[], wchar[], dchar[], string, wstring, dstring))
    {
        import std.conv : to;
        StringType decoded1 = source.to!StringType;
        string encoded1 = encode(decoded1);
        assert(decoded1 == source.to!StringType); // check that `decoded1` wasn't changed
        assert(encoded1 == target);
        assert(decoded1 == decode(encoded1).to!StringType);

        StringType encoded2 = target.to!StringType;
        string decoded2 = decode(encoded2);
        assert(encoded2 == target.to!StringType); // check that `encoded2` wasn't changed
        assert(decoded2 == source);
        assert(encoded2 == encode(decoded2).to!StringType);
    }
}