ExternalVendorCode/tippecanoe
1
0
Fork 0
mirror of https://github.com/mapbox/tippecanoe.git synced 2025-02-01 08:47:57 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

Handle surrogate pairs in JSON strings

Browse Source
This commit is contained in:
Eric Fischer 2017-10-10 14:03:33 -07:00
parent cc734c8709
commit 621cf72e5a
1 changed files with 79 additions and 21 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

102
jsonpull/jsonpull.c
View File

@ -569,12 +569,84 @@ again:
struct string val;
string_init(&val);
int surrogate = -1;
while ((c = read_wrap(j)) != EOF) {
if (c == '"') {
if (surrogate >= 0) {
string_append(&val, 0xE0 | (surrogate >> 12));
string_append(&val, 0x80 | ((surrogate >> 6) & 0x3F));
string_append(&val, 0x80 | (surrogate & 0x3F));
surrogate = -1;
}
break;
} else if (c == '\\') {
c = read_wrap(j);
if (c == 'u') {
char hex[5] = "aaaa";
int i;
for (i = 0; i < 4; i++) {
hex[i] = read_wrap(j);
if (hex[i] < '0' || (hex[i] > '9' && hex[i] < 'A') || (hex[i] > 'F' && hex[i] < 'a') || hex[i] > 'f') {
j->error = "Invalid \\u hex character";
string_free(&val);
return NULL;
}
}
unsigned long ch = strtoul(hex, NULL, 16);
if (ch >= 0xd800 && ch <= 0xdbff) {
if (surrogate < 0) {
surrogate = ch;
} else {
// Impossible surrogate, so output the first half,
// keep what might be a legitimate new first half.
string_append(&val, 0xE0 | (surrogate >> 12));
string_append(&val, 0x80 | ((surrogate >> 6) & 0x3F));
string_append(&val, 0x80 | (surrogate & 0x3F));
surrogate = ch;
}
continue;
} else if (ch >= 0xdc00 && c <= 0xdfff) {
if (surrogate >= 0) {
long c1 = surrogate - 0xd800;
long c2 = ch - 0xdc00;
ch = ((c1 << 10) | c2) + 0x010000;
surrogate = -1;
}
}
if (surrogate >= 0) {
string_append(&val, 0xE0 | (surrogate >> 12));
string_append(&val, 0x80 | ((surrogate >> 6) & 0x3F));
string_append(&val, 0x80 | (surrogate & 0x3F));
surrogate = -1;
}
if (ch <= 0x7F) {
string_append(&val, ch);
} else if (ch <= 0x7FF) {
string_append(&val, 0xC0 | (ch >> 6));
string_append(&val, 0x80 | (ch & 0x3F));
} else if (ch < 0xFFFF) {
string_append(&val, 0xE0 | (ch >> 12));
string_append(&val, 0x80 | ((ch >> 6) & 0x3F));
string_append(&val, 0x80 | (ch & 0x3F));
} else {
string_append(&val, 0xF0 | (ch >> 18));
string_append(&val, 0x80 | ((ch >> 12) & 0x3F));
string_append(&val, 0x80 | ((ch >> 6) & 0x3F));
string_append(&val, 0x80 | (ch & 0x3F));
}
} else {
if (surrogate >= 0) {
string_append(&val, 0xE0 | (surrogate >> 12));
string_append(&val, 0x80 | ((surrogate >> 6) & 0x3F));
string_append(&val, 0x80 | (surrogate & 0x3F));
surrogate = -1;
}
if (c == '"') {
string_append(&val, '"');
} else if (c == '\\') {
@ -591,38 +663,24 @@ again:
string_append(&val, '\r');
} else if (c == 't') {
string_append(&val, '\t');
} else if (c == 'u') {
char hex[5] = "aaaa";
int i;
for (i = 0; i < 4; i++) {
hex[i] = read_wrap(j);
if (hex[i] < '0' || (hex[i] > '9' && hex[i] < 'A') || (hex[i] > 'F' && hex[i] < 'a') || hex[i] > 'f') {
j->error = "Invalid \\u hex character";
string_free(&val);
return NULL;
}
}
unsigned long ch = strtoul(hex, NULL, 16);
if (ch <= 0x7F) {
string_append(&val, ch);
} else if (ch <= 0x7FF) {
string_append(&val, 0xC0 | (ch >> 6));
string_append(&val, 0x80 | (ch & 0x3F));
} else {
string_append(&val, 0xE0 | (ch >> 12));
string_append(&val, 0x80 | ((ch >> 6) & 0x3F));
string_append(&val, 0x80 | (ch & 0x3F));
}
} else {
j->error = "Found backslash followed by unknown character";
string_free(&val);
return NULL;
}
}
} else if (c < ' ') {
j->error = "Found control character in string";
string_free(&val);
return NULL;
} else {
if (surrogate >= 0) {
string_append(&val, 0xE0 | (surrogate >> 12));
string_append(&val, 0x80 | ((surrogate >> 6) & 0x3F));
string_append(&val, 0x80 | (surrogate & 0x3F));
surrogate = -1;
}
string_append(&val, c);
}
}