Make redbean StoreAsset() work better

- Better UBSAN error messages
- POSIX Advisory Locks polyfills
- Move redbean manual to /.help.txt
- System call memory safety in ASAN mode
- Character classification now does UNICODE
This commit is contained in:
Justine Tunney 2021-05-14 05:36:58 -07:00
parent 919b6fec10
commit 690be544da
228 changed files with 3653 additions and 3015 deletions

View file

@ -16,11 +16,23 @@
TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR
PERFORMANCE OF THIS SOFTWARE.
*/
#include "libc/bits/likely.h"
#include "libc/str/thompike.h"
#include "libc/str/utf16.h"
#include "libc/x/x.h"
#include "net/http/escape.h"
static const char kEscapeLiteral[128] = {
9, 9, 9, 9, 9, 9, 9, 9, 9, 1, 2, 9, 4, 3, 9, 9, // 0x00
9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, // 0x10
0, 0, 7, 0, 0, 0, 9, 8, 0, 0, 0, 0, 0, 0, 0, 6, // 0x20
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 9, 9, 9, 0, // 0x30
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, // 0x40
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 5, 0, 0, 0, // 0x50
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, // 0x60
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 9, // 0x70
};
/**
* Escapes UTF-8 data for JavaScript or JSON string literal.
*
@ -66,141 +78,51 @@ char *EscapeJsStringLiteral(const char *p, size_t n, size_t *z) {
}
}
}
switch (x) {
case ' ':
case '!':
case '#':
case '$':
case '%':
case '(':
case ')':
case '*':
case '+':
case ',':
case '-':
case '.':
case '0':
case '1':
case '2':
case '3':
case '4':
case '5':
case '6':
case '7':
case '8':
case '9':
case ':':
case ';':
case '?':
case '@':
case 'A':
case 'B':
case 'C':
case 'D':
case 'E':
case 'F':
case 'G':
case 'H':
case 'I':
case 'J':
case 'K':
case 'L':
case 'M':
case 'N':
case 'O':
case 'P':
case 'Q':
case 'R':
case 'S':
case 'T':
case 'U':
case 'V':
case 'W':
case 'X':
case 'Y':
case 'Z':
case '[':
case ']':
case '^':
case '_':
case '`':
case 'a':
case 'b':
case 'c':
case 'd':
case 'e':
case 'f':
case 'g':
case 'h':
case 'i':
case 'j':
case 'k':
case 'l':
case 'm':
case 'n':
case 'o':
case 'p':
case 'q':
case 'r':
case 's':
case 't':
case 'u':
case 'v':
case 'w':
case 'x':
case 'y':
case 'z':
case '{':
case '|':
case '}':
case '~':
switch (0 <= x && x <= 127 ? kEscapeLiteral[x] : 9) {
case 0:
*q++ = x;
break;
case '\t':
case 1:
q[0] = '\\';
q[1] = 't';
q += 2;
break;
case '\n':
case 2:
q[0] = '\\';
q[1] = 'n';
q += 2;
break;
case '\r':
case 3:
q[0] = '\\';
q[1] = 'r';
q += 2;
break;
case '\f':
case 4:
q[0] = '\\';
q[1] = 'f';
q += 2;
break;
case '\\':
case 5:
q[0] = '\\';
q[1] = '\\';
q += 2;
break;
case '/':
case 6:
q[0] = '\\';
q[1] = '/';
q += 2;
break;
case '"':
case 7:
q[0] = '\\';
q[1] = '"';
q += 2;
break;
case '\'':
case 8:
q[0] = '\\';
q[1] = '\'';
q += 2;
break;
case '<':
case '>':
case '&':
case '=':
default:
case 9:
w = EncodeUtf16(x);
do {
q[0] = '\\';
@ -212,6 +134,8 @@ char *EscapeJsStringLiteral(const char *p, size_t n, size_t *z) {
q += 6;
} while ((w >>= 16));
break;
default:
unreachable;
}
}
if (z) *z = q - r;

View file

@ -1,24 +0,0 @@
%{
#include "libc/str/str.h"
#include "net/http/uri.h"
#define GPERF_DOWNCASE
%}
%compare-strncmp
%ignore-case
%language=ANSI-C
%pic
%readonly-tables
%struct-type
struct UriSchemeSlot { unsigned char name; unsigned char code; };
%%
http,kUriSchemeHttp
https,kUriSchemeHttps
file,kUriSchemeFile
data,kUriSchemeData
zip,kUriSchemeZip
sip,kUriSchemeSip
sips,kUriSchemeSips
tel,kUriSchemeTel
ssh,kUriSchemeSsh
gs,kUriSchemeGs
s3,kUriSchemeS3

View file

@ -1,213 +0,0 @@
/* ANSI-C code produced by gperf version 3.0.4 */
/* Command-line: gperf net/http/geturischeme.gperf */
/* Computed positions: -k'1-2' */
#if !((' ' == 32) && ('!' == 33) && ('"' == 34) && ('#' == 35) \
&& ('%' == 37) && ('&' == 38) && ('\'' == 39) && ('(' == 40) \
&& (')' == 41) && ('*' == 42) && ('+' == 43) && (',' == 44) \
&& ('-' == 45) && ('.' == 46) && ('/' == 47) && ('0' == 48) \
&& ('1' == 49) && ('2' == 50) && ('3' == 51) && ('4' == 52) \
&& ('5' == 53) && ('6' == 54) && ('7' == 55) && ('8' == 56) \
&& ('9' == 57) && (':' == 58) && (';' == 59) && ('<' == 60) \
&& ('=' == 61) && ('>' == 62) && ('?' == 63) && ('A' == 65) \
&& ('B' == 66) && ('C' == 67) && ('D' == 68) && ('E' == 69) \
&& ('F' == 70) && ('G' == 71) && ('H' == 72) && ('I' == 73) \
&& ('J' == 74) && ('K' == 75) && ('L' == 76) && ('M' == 77) \
&& ('N' == 78) && ('O' == 79) && ('P' == 80) && ('Q' == 81) \
&& ('R' == 82) && ('S' == 83) && ('T' == 84) && ('U' == 85) \
&& ('V' == 86) && ('W' == 87) && ('X' == 88) && ('Y' == 89) \
&& ('Z' == 90) && ('[' == 91) && ('\\' == 92) && (']' == 93) \
&& ('^' == 94) && ('_' == 95) && ('a' == 97) && ('b' == 98) \
&& ('c' == 99) && ('d' == 100) && ('e' == 101) && ('f' == 102) \
&& ('g' == 103) && ('h' == 104) && ('i' == 105) && ('j' == 106) \
&& ('k' == 107) && ('l' == 108) && ('m' == 109) && ('n' == 110) \
&& ('o' == 111) && ('p' == 112) && ('q' == 113) && ('r' == 114) \
&& ('s' == 115) && ('t' == 116) && ('u' == 117) && ('v' == 118) \
&& ('w' == 119) && ('x' == 120) && ('y' == 121) && ('z' == 122) \
&& ('{' == 123) && ('|' == 124) && ('}' == 125) && ('~' == 126))
/* The character set is not based on ISO-646. */
#error "gperf generated tables don't work with this execution character set. Please report a bug to <bug-gnu-gperf@gnu.org>."
#endif
#line 1 "net/http/geturischeme.gperf"
#include "libc/str/str.h"
#include "net/http/uri.h"
#define GPERF_DOWNCASE
#line 12 "net/http/geturischeme.gperf"
struct UriSchemeSlot { unsigned char name; unsigned char code; };
#define TOTAL_KEYWORDS 11
#define MIN_WORD_LENGTH 2
#define MAX_WORD_LENGTH 5
#define MIN_HASH_VALUE 2
#define MAX_HASH_VALUE 19
/* maximum key range = 18, duplicates = 0 */
#ifndef GPERF_DOWNCASE
#define GPERF_DOWNCASE 1
static unsigned char gperf_downcase[256] =
{
0, 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, 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, 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
};
#endif
#ifndef GPERF_CASE_STRNCMP
#define GPERF_CASE_STRNCMP 1
static int
gperf_case_strncmp (register const char *s1, register const char *s2, register unsigned int n)
{
for (; n > 0;)
{
unsigned char c1 = gperf_downcase[(unsigned char)*s1++];
unsigned char c2 = gperf_downcase[(unsigned char)*s2++];
if (c1 != 0 && c1 == c2)
{
n--;
continue;
}
return (int)c1 - (int)c2;
}
return 0;
}
#endif
#ifdef __GNUC__
__inline
#else
#ifdef __cplusplus
inline
#endif
#endif
static unsigned int
hash (register const char *str, register unsigned int len)
{
static const unsigned char asso_values[] =
{
20, 20, 20, 20, 20, 20, 20, 20, 20, 20,
20, 20, 20, 20, 20, 20, 20, 20, 20, 20,
20, 20, 20, 20, 20, 20, 20, 20, 20, 20,
20, 20, 20, 20, 20, 20, 20, 20, 20, 20,
20, 20, 20, 20, 20, 20, 20, 20, 20, 20,
20, 5, 20, 20, 20, 20, 20, 20, 20, 20,
20, 20, 20, 20, 20, 10, 20, 20, 5, 15,
5, 0, 0, 5, 20, 20, 20, 20, 20, 20,
20, 20, 20, 0, 0, 20, 20, 20, 20, 20,
5, 20, 20, 20, 20, 20, 20, 10, 20, 20,
5, 15, 5, 0, 0, 5, 20, 20, 20, 20,
20, 20, 20, 20, 20, 0, 0, 20, 20, 20,
20, 20, 5, 20, 20, 20, 20, 20, 20, 20,
20, 20, 20, 20, 20, 20, 20, 20, 20, 20,
20, 20, 20, 20, 20, 20, 20, 20, 20, 20,
20, 20, 20, 20, 20, 20, 20, 20, 20, 20,
20, 20, 20, 20, 20, 20, 20, 20, 20, 20,
20, 20, 20, 20, 20, 20, 20, 20, 20, 20,
20, 20, 20, 20, 20, 20, 20, 20, 20, 20,
20, 20, 20, 20, 20, 20, 20, 20, 20, 20,
20, 20, 20, 20, 20, 20, 20, 20, 20, 20,
20, 20, 20, 20, 20, 20, 20, 20, 20, 20,
20, 20, 20, 20, 20, 20, 20, 20, 20, 20,
20, 20, 20, 20, 20, 20, 20, 20, 20, 20,
20, 20, 20, 20, 20, 20, 20, 20, 20, 20,
20, 20, 20, 20, 20, 20
};
return len + asso_values[(unsigned char)str[1]] + asso_values[(unsigned char)str[0]];
}
struct stringpool_t
{
char stringpool_str2[sizeof("gs")];
char stringpool_str3[sizeof("ssh")];
char stringpool_str4[sizeof("http")];
char stringpool_str5[sizeof("https")];
char stringpool_str7[sizeof("s3")];
char stringpool_str8[sizeof("sip")];
char stringpool_str9[sizeof("sips")];
char stringpool_str13[sizeof("zip")];
char stringpool_str14[sizeof("file")];
char stringpool_str18[sizeof("tel")];
char stringpool_str19[sizeof("data")];
};
static const struct stringpool_t stringpool_contents =
{
"gs",
"ssh",
"http",
"https",
"s3",
"sip",
"sips",
"zip",
"file",
"tel",
"data"
};
#define stringpool ((const char *) &stringpool_contents)
const struct UriSchemeSlot *
in_word_set (register const char *str, register unsigned int len)
{
static const struct UriSchemeSlot wordlist[] =
{
{-1}, {-1},
#line 23 "net/http/geturischeme.gperf"
{(int)(long)&((struct stringpool_t *)0)->stringpool_str2,kUriSchemeGs},
#line 22 "net/http/geturischeme.gperf"
{(int)(long)&((struct stringpool_t *)0)->stringpool_str3,kUriSchemeSsh},
#line 14 "net/http/geturischeme.gperf"
{(int)(long)&((struct stringpool_t *)0)->stringpool_str4,kUriSchemeHttp},
#line 15 "net/http/geturischeme.gperf"
{(int)(long)&((struct stringpool_t *)0)->stringpool_str5,kUriSchemeHttps},
{-1},
#line 24 "net/http/geturischeme.gperf"
{(int)(long)&((struct stringpool_t *)0)->stringpool_str7,kUriSchemeS3},
#line 19 "net/http/geturischeme.gperf"
{(int)(long)&((struct stringpool_t *)0)->stringpool_str8,kUriSchemeSip},
#line 20 "net/http/geturischeme.gperf"
{(int)(long)&((struct stringpool_t *)0)->stringpool_str9,kUriSchemeSips},
{-1}, {-1}, {-1},
#line 18 "net/http/geturischeme.gperf"
{(int)(long)&((struct stringpool_t *)0)->stringpool_str13,kUriSchemeZip},
#line 16 "net/http/geturischeme.gperf"
{(int)(long)&((struct stringpool_t *)0)->stringpool_str14,kUriSchemeFile},
{-1}, {-1}, {-1},
#line 21 "net/http/geturischeme.gperf"
{(int)(long)&((struct stringpool_t *)0)->stringpool_str18,kUriSchemeTel},
#line 17 "net/http/geturischeme.gperf"
{(int)(long)&((struct stringpool_t *)0)->stringpool_str19,kUriSchemeData}
};
if (len <= MAX_WORD_LENGTH && len >= MIN_WORD_LENGTH)
{
register int key = hash (str, len);
if (key <= MAX_HASH_VALUE && key >= 0)
{
register int o = wordlist[key].name;
if (o >= 0)
{
register const char *s = o + stringpool;
if ((((unsigned char)*str ^ (unsigned char)*s) & ~32) == 0 && !gperf_case_strncmp (str, s, len) && s[len] == '\0')
return &wordlist[key];
}
}
}
return 0;
}

View file

@ -24,21 +24,21 @@
#include "net/http/url.h"
struct UrlParser {
int i;
unsigned i;
int c;
const char *data;
int size;
bool isform;
bool islatin1;
bool isopaque;
size_t size;
char isform;
char islatin1;
char isopaque;
char *p;
char *q;
};
static void EmitLatin1(struct UrlParser *u, int c) {
u->p[0] = 0300 | c >> 6;
u->p[1] = 0200 | c & 077;
u->p += 2;
static void EmitLatin1(char **p, int c) {
(*p)[0] = 0300 | c >> 6;
(*p)[1] = 0200 | c & 077;
*p += 2;
}
static bool EmitKey(struct UrlParser *u, struct UrlParams *h) {
@ -115,16 +115,18 @@ static bool ParseScheme(struct UrlParser *u, struct Url *h) {
ParseEscape(u);
return false;
} else if (u->c >= 0200 && u->islatin1) {
EmitLatin1(u, u->c);
EmitLatin1(&u->p, u->c);
return false;
} else {
*u->p++ = u->c;
if (u->i == 1) {
if (!isalpha(u->c)) {
if (!(('A' <= u->c && u->c <= 'Z') || ('a' <= u->c && u->c <= 'z'))) {
return false;
}
} else {
if (!isalnum(u->c) && u->c != '+' && u->c != '-' && u->c != '.') {
if (!(('0' <= u->c && u->c <= '9') || ('A' <= u->c && u->c <= 'Z') ||
('a' <= u->c && u->c <= 'z') || u->c == '+' || u->c == '-' ||
u->c == '.')) {
return false;
}
}
@ -134,17 +136,17 @@ static bool ParseScheme(struct UrlParser *u, struct Url *h) {
}
static void ParseAuthority(struct UrlParser *u, struct Url *h) {
int t = 0;
unsigned t = 1;
const char *c = NULL;
while (u->i < u->size) {
u->c = u->data[u->i++] & 0xff;
if (u->c == '/' || u->c == '#' || u->c == '?') {
break;
} else if (u->c == '[') {
t = -1;
} else if (u->c == ']') {
t = 0;
} else if (u->c == ':' && t >= 0) {
} else if (u->c == ']') {
t = 1;
} else if (u->c == ':' && t > 0) {
*u->p++ = ':';
c = u->p;
++t;
@ -155,7 +157,7 @@ static void ParseAuthority(struct UrlParser *u, struct Url *h) {
h->pass.p = c;
h->pass.n = u->p - c;
c = NULL;
t = 0;
t = 1;
} else {
h->user.p = u->q;
h->user.n = u->p - u->q;
@ -164,12 +166,12 @@ static void ParseAuthority(struct UrlParser *u, struct Url *h) {
} else if (u->c == '%') {
ParseEscape(u);
} else if (u->c >= 0200 && u->islatin1) {
EmitLatin1(u, u->c);
EmitLatin1(&u->p, u->c);
} else {
*u->p++ = u->c;
}
}
if (t == 1) {
if (t == 2) {
h->host.p = u->q;
h->host.n = c - 1 - u->q;
h->port.p = c;
@ -195,7 +197,7 @@ static void ParsePath(struct UrlParser *u, struct UrlView *h) {
} else if (u->c == '%') {
ParseEscape(u);
} else if (u->c >= 0200 && u->islatin1) {
EmitLatin1(u, u->c);
EmitLatin1(&u->p, u->c);
} else {
*u->p++ = u->c;
}
@ -226,7 +228,7 @@ static void ParseQuery(struct UrlParser *u, struct UrlParams *h) {
*u->p++ = '=';
}
} else if (u->c >= 0200 && u->islatin1) {
EmitLatin1(u, u->c);
EmitLatin1(&u->p, u->c);
} else {
*u->p++ = u->c;
}
@ -240,7 +242,7 @@ static void ParseFragment(struct UrlParser *u, struct UrlView *h) {
if (u->c == '%') {
ParseEscape(u);
} else if (u->c >= 0200 && u->islatin1) {
EmitLatin1(u, u->c);
EmitLatin1(&u->p, u->c);
} else {
*u->p++ = u->c;
}
@ -258,8 +260,8 @@ static char *ParseUrlImpl(const char *data, size_t size, struct Url *h,
u.i = 0;
u.c = 0;
u.isform = false;
u.islatin1 = latin1;
u.isopaque = false;
u.islatin1 = latin1;
u.data = data;
u.size = size;
memset(h, 0, sizeof(*h));