From: Alex Dowad <alexinbeijing@gmail.com>
Date: Sun, 18 Oct 2020 15:51:59 +0000 (+0200)
Subject: Add test suite for ARMSCII-8 encoding
X-Git-Url: https://granicus.if.org/sourcecode?a=commitdiff_plain;h=ff953f254c3f55c67e2de8a003887876d3b05420;p=php

Add test suite for ARMSCII-8 encoding
---

diff --git a/ext/mbstring/tests/armscii8_encoding.phpt b/ext/mbstring/tests/armscii8_encoding.phpt
new file mode 100644
index 0000000000..b7e653d58b
--- /dev/null
+++ b/ext/mbstring/tests/armscii8_encoding.phpt
@@ -0,0 +1,33 @@
+--TEST--
+Exhaustive test of verification and conversion of ARMSCII-8 text
+--SKIPIF--
+<?php
+extension_loaded('mbstring') or die('skip mbstring not available');
+if (getenv("SKIP_SLOW_TESTS")) die("skip slow test");
+?>
+--FILE--
+<?php
+include('encoding_tests.inc');
+srand(111); // Make results consistent
+mb_substitute_character(0x25); // '%'
+
+readConversionTable(__DIR__ . '/data/ARMSCII-8.txt', $toUnicode, $fromUnicode);
+$irreversible = ["\x28", "\x29", "\x2C", "\x2D", "\x2E"];
+
+findInvalidChars($toUnicode, $invalid, $truncated);
+testAllValidChars($toUnicode, 'ARMSCII-8', 'UTF-16BE', false);
+foreach ($irreversible as $char)
+  unset($toUnicode[$char]);
+testAllValidChars($toUnicode, 'ARMSCII-8', 'UTF-16BE');
+testAllInvalidChars($invalid, $toUnicode, 'ARMSCII-8', 'UTF-16BE', "\x00%");
+testTruncatedChars($truncated, 'ARMSCII-8', 'UTF-16BE', "\x00%");
+echo "Tested ARMSCII-8 -> UTF-16BE\n";
+
+findInvalidChars($fromUnicode, $invalid, $truncated, map(range(0,0xFF), 2));
+testAllInvalidChars($invalid, $fromUnicode, 'UTF-16BE', 'ARMSCII-8', '%');
+testTruncatedChars($truncated, 'UTF-16BE', 'ARMSCII-8', '%');
+echo "Tested UTF-16BE -> ARMSCII-8\n";
+?>
+--EXPECT--
+Tested ARMSCII-8 -> UTF-16BE
+Tested UTF-16BE -> ARMSCII-8
diff --git a/ext/mbstring/tests/data/ARMSCII-8.txt b/ext/mbstring/tests/data/ARMSCII-8.txt
new file mode 100644
index 0000000000..1854fddc13
--- /dev/null
+++ b/ext/mbstring/tests/data/ARMSCII-8.txt
@@ -0,0 +1,255 @@
+# Derived from armscii-8(7) man page
+0x0	0x0
+0x1	0x1
+0x2	0x2
+0x3	0x3
+0x4	0x4
+0x5	0x5
+0x6	0x6
+0x7	0x7
+0x8	0x8
+0x9	0x9
+0xA	0xA
+0xB	0xB
+0xC	0xC
+0xD	0xD
+0xE	0xE
+0xF	0xF
+0x10	0x10
+0x11	0x11
+0x12	0x12
+0x13	0x13
+0x14	0x14
+0x15	0x15
+0x16	0x16
+0x17	0x17
+0x18	0x18
+0x19	0x19
+0x1A	0x1A
+0x1B	0x1B
+0x1C	0x1C
+0x1D	0x1D
+0x1E	0x1E
+0x1F	0x1F
+0x20	0x20
+0x21	0x21
+0x22	0x22
+0x23	0x23
+0x24	0x24
+0x25	0x25
+0x26	0x26
+0x27	0x27
+0x28	0x28
+0x29	0x29
+0x2A	0x2A
+0x2B	0x2B
+0x2C	0x2C
+0x2D	0x2D
+0x2E	0x2E
+0x2F	0x2F
+0x30	0x30
+0x31	0x31
+0x32	0x32
+0x33	0x33
+0x34	0x34
+0x35	0x35
+0x36	0x36
+0x37	0x37
+0x38	0x38
+0x39	0x39
+0x3A	0x3A
+0x3B	0x3B
+0x3C	0x3C
+0x3D	0x3D
+0x3E	0x3E
+0x3F	0x3F
+0x40	0x40
+0x41	0x41
+0x42	0x42
+0x43	0x43
+0x44	0x44
+0x45	0x45
+0x46	0x46
+0x47	0x47
+0x48	0x48
+0x49	0x49
+0x4A	0x4A
+0x4B	0x4B
+0x4C	0x4C
+0x4D	0x4D
+0x4E	0x4E
+0x4F	0x4F
+0x50	0x50
+0x51	0x51
+0x52	0x52
+0x53	0x53
+0x54	0x54
+0x55	0x55
+0x56	0x56
+0x57	0x57
+0x58	0x58
+0x59	0x59
+0x5A	0x5A
+0x5B	0x5B
+0x5C	0x5C
+0x5D	0x5D
+0x5E	0x5E
+0x5F	0x5F
+0x60	0x60
+0x61	0x61
+0x62	0x62
+0x63	0x63
+0x64	0x64
+0x65	0x65
+0x66	0x66
+0x67	0x67
+0x68	0x68
+0x69	0x69
+0x6A	0x6A
+0x6B	0x6B
+0x6C	0x6C
+0x6D	0x6D
+0x6E	0x6E
+0x6F	0x6F
+0x70	0x70
+0x71	0x71
+0x72	0x72
+0x73	0x73
+0x74	0x74
+0x75	0x75
+0x76	0x76
+0x77	0x77
+0x78	0x78
+0x79	0x79
+0x7A	0x7A
+0x7B	0x7B
+0x7C	0x7C
+0x7D	0x7D
+0x7E	0x7E
+0x7F	0x7F
+0x80	0x80
+0x81	0x81
+0x82	0x82
+0x83	0x83
+0x84	0x84
+0x85	0x85
+0x86	0x86
+0x87	0x87
+0x88	0x88
+0x89	0x89
+0x8A	0x8A
+0x8B	0x8B
+0x8C	0x8C
+0x8D	0x8D
+0x8E	0x8E
+0x8F	0x8F
+0x90	0x90
+0x91	0x91
+0x92	0x92
+0x93	0x93
+0x94	0x94
+0x95	0x95
+0x96	0x96
+0x97	0x97
+0x98	0x98
+0x99	0x99
+0x9A	0x9A
+0x9B	0x9B
+0x9C	0x9C
+0x9D	0x9D
+0x9E	0x9E
+0x9F	0x9F
+0xA0	0x00A0 # NO-BREAK SPACE
+0xA2	0x0587 # SMALL LIGATURE ECH YIWN
+0xA3	0x0589 # ARMENIAN FULL STOP
+0xA4	0x0029 # RIGHT PARENTHESIS
+0xA5	0x0028 # LEFT PARENTHESIS
+0xA6	0x00BB # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
+0xA7	0x00AB # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
+0xA8	0x2014 # EM DASH
+0xA9	0x002E # FULL STOP
+0xAA	0x055D # ARMENIAN COMMA
+0xAB	0x002C # COMMA
+0xAC	0x002D # HYPHEN-MINUS
+0xAD	0x058A # ARMENIAN HYPHEN
+0xAE	0x2026 # HORIZONTAL ELLIPSIS
+0xAF	0x055C # ARMENIAN EXCLAMATION MARK
+0xB0	0x055B # ARMENIAN EMPHASIS MARK
+0xB1	0x055E # ARMENIAN QUESTION MARK
+0xB2	0x0531
+0xB3	0x0561
+0xB4	0x0532
+0xB5	0x0562
+0xB6	0x0533
+0xB7	0x0563
+0xB8	0x0534
+0xB9	0x0564
+0xBA	0x0535
+0xBB	0x0565
+0xBC	0x0536
+0xBD	0x0566
+0xBE	0x0537
+0xBF	0x0567
+0xC0	0x0538
+0xC1	0x0568
+0xC2	0x0539
+0xC3	0x0569
+0xC4	0x053A
+0xC5	0x056A
+0xC6	0x053B
+0xC7	0x056B
+0xC8	0x053C
+0xC9	0x056C
+0xCA	0x053D
+0xCB	0x056D
+0xCC	0x053E
+0xCD	0x056E
+0xCE	0x053F
+0xCF	0x056F
+0xD0	0x0540
+0xD1	0x0570
+0xD2	0x0541
+0xD3	0x0571
+0xD4	0x0542
+0xD5	0x0572
+0xD6	0x0543
+0xD7	0x0573
+0xD8	0x0544
+0xD9	0x0574
+0xDA	0x0545
+0xDB	0x0575
+0xDC	0x0546
+0xDD	0x0576
+0xDE	0x0547
+0xDF	0x0577
+0xE0	0x0548
+0xE1	0x0578
+0xE2	0x0549
+0xE3	0x0579
+0xE4	0x054A
+0xE5	0x057A
+0xE6	0x054B
+0xE7	0x057B
+0xE8	0x054C
+0xE9	0x057C
+0xEA	0x054D
+0xEB	0x057D
+0xEC	0x054E
+0xED	0x057E
+0xEE	0x054F
+0xEF	0x057F
+0xF0	0x0550
+0xF1	0x0580
+0xF2	0x0551
+0xF3	0x0581
+0xF4	0x0552
+0xF5	0x0582
+0xF6	0x0553
+0xF7	0x0583
+0xF8	0x0554
+0xF9	0x0584
+0xFA	0x0555
+0xFB	0x0585
+0xFC	0x0556
+0xFD	0x0586
+0xFE	0x055A