Hash :
6685df9c
Author :
Date :
2024-01-16T15:09:33
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
# Coverage
This file is just a collection of tests designed to activate code in MD4C
which may otherwise be hard to hit. It's to improve our test coverage.
## `md_is_unicode_whitespace__()`
Unicode whitespace (here U+2000) forms a word boundary so these cannot be
resolved as emphasis span because there is no closer mark.
```````````````````````````````` example
*foo *bar
.
<p>*foo *bar</p>
````````````````````````````````
## `md_is_unicode_punct__()`
Ditto for Unicode punctuation (here U+00A1).
```````````````````````````````` example
*foo¡*bar
.
<p>*foo¡*bar</p>
````````````````````````````````
## `md_get_unicode_fold_info()`
```````````````````````````````` example
[Příliš žluťoučký kůň úpěl ďábelské ódy.]
[PŘÍLIŠ ŽLUŤOUČKÝ KŮŇ ÚPĚL ĎÁBELSKÉ ÓDY.]: /url
.
<p><a href="/url">Příliš žluťoučký kůň úpěl ďábelské ódy.</a></p>
````````````````````````````````
## `md_decode_utf8__()` and `md_decode_utf8_before__()`
```````````````````````````````` example
á*Á (U+00E1, i.e. two byte UTF-8 sequence)
* (U+2000, i.e. three byte UTF-8 sequence)
.
<p>á*Á (U+00E1, i.e. two byte UTF-8 sequence)
* (U+2000, i.e. three byte UTF-8 sequence)</p>
````````````````````````````````
## `md_is_link_destination_A()`
```````````````````````````````` example
[link](</url\.with\.escape>)
.
<p><a href="/url.with.escape">link</a></p>
````````````````````````````````
## `md_link_label_eq()`
```````````````````````````````` example
[foo bar]
[foo bar]: /url
.
<p><a href="/url">foo bar</a></p>
````````````````````````````````
## `md_is_inline_link_spec()`
```````````````````````````````` example
> [link](/url 'foo
> bar')
.
<blockquote>
<p><a href="/url" title="foo
bar">link</a></p>
</blockquote>
````````````````````````````````
## `md_build_ref_def_hashtable()`
All link labels in the following example all have the same FNV1a hash (after
normalization of the label, which means after converting to a vector of Unicode
codepoints and lowercase folding).
So the example triggers quite complex code paths which are not otherwise easily
tested.
```````````````````````````````` example
[foo]: /foo
[qnptgbh]: /qnptgbh
[abgbrwcv]: /abgbrwcv
[abgbrwcv]: /abgbrwcv2
[abgbrwcv]: /abgbrwcv3
[abgbrwcv]: /abgbrwcv4
[alqadfgn]: /alqadfgn
[foo]
[qnptgbh]
[abgbrwcv]
[alqadfgn]
[axgydtdu]
.
<p><a href="/foo">foo</a>
<a href="/qnptgbh">qnptgbh</a>
<a href="/abgbrwcv">abgbrwcv</a>
<a href="/alqadfgn">alqadfgn</a>
[axgydtdu]</p>
````````````````````````````````
For the sake of completeness, the following C program was used to find the hash
collisions by brute force:
~~~
#include <stdio.h>
#include <string.h>
static unsigned etalon;
#define MD_FNV1A_BASE 2166136261
#define MD_FNV1A_PRIME 16777619
static inline unsigned
fnv1a(unsigned base, const void* data, size_t n)
{
const unsigned char* buf = (const unsigned char*) data;
unsigned hash = base;
size_t i;
for(i = 0; i < n; i++) {
hash ^= buf[i];
hash *= MD_FNV1A_PRIME;
}
return hash;
}
static unsigned
unicode_hash(const char* data, size_t n)
{
unsigned value;
unsigned hash = MD_FNV1A_BASE;
int i;
for(i = 0; i < n; i++) {
value = data[i];
hash = fnv1a(hash, &value, sizeof(unsigned));
}
return hash;
}
static void
recurse(char* buffer, size_t off, size_t len)
{
int ch;
if(off < len - 1) {
for(ch = 'a'; ch <= 'z'; ch++) {
buffer[off] = ch;
recurse(buffer, off+1, len);
}
} else {
for(ch = 'a'; ch <= 'z'; ch++) {
buffer[off] = ch;
if(unicode_hash(buffer, len) == etalon) {
printf("Dup: %.*s\n", (int)len, buffer);
}
}
}
}
int
main(int argc, char** argv)
{
char buffer[32];
int len;
if(argc < 2)
etalon = unicode_hash("foo", 3);
else
etalon = unicode_hash(argv[1], strlen(argv[1]));
for(len = 1; len <= sizeof(buffer); len++)
recurse(buffer, 0, len);
return 0;
}
~~~