--- a/src/json.c Sun Jan 26 12:24:49 2025 +0100
+++ b/src/json.c Sun Jan 26 13:20:05 2025 +0100
@@ -353,8 +353,8 @@
return CX_JSON_INCOMPLETE_DATA;
}
-// converts a unicode (up to U+FFFF) codepoint to utf8
-static int codepoint_to_utf8(uint32_t codepoint, char *output_buf) {
+// converts a Unicode codepoint to utf8
+static unsigned codepoint_to_utf8(uint32_t codepoint, char *output_buf) {
if (codepoint <= 0x7F) {
*output_buf = (char)codepoint;
return 1;
@@ -375,7 +375,7 @@
return 4;
}
- return 0;
+ return 0; // LCOV_EXCL_LINE
}
// converts a utf16 surrogate pair to utf8
@@ -398,6 +398,8 @@
u = false;
if (c == 'n') {
c = '\n';
+ } else if (c == '"') {
+ c = '"';
} else if (c == 't') {
c = '\t';
} else if (c == 'r') {
@@ -411,48 +413,54 @@
} else if (c == 'b') {
c = '\b';
} else if (c == 'u') {
- if (i+4 < str.length - 1) {
- cxstring codepoint_str = { str.ptr + i + 1, 4};
- uint32_t codepoint;
- if (!cx_strtou32_lc(codepoint_str, &codepoint, 16, "")) {
- char utf8buf[4];
- int utf8len = 0;
- if (codepoint >= 0xD800 && codepoint <= 0xDFFF) {
+ if (i + 4 < str.length - 1) {
+ cxstring ustr1 = { str.ptr + i + 1, 4};
+ uint16_t utf16a, utf16b;
+ char utf8buf[4];
+ unsigned utf8len = 0;
+ if (!cx_strtou16_lc(ustr1, &utf16a, 16, "")) {
+ uint32_t codepoint;
+ if (utf16a >= 0xD800 && utf16a <= 0xDFFF) {
// character is encoded as a surrogate pair
// get next 6 bytes
if (i + 10 < str.length - 1) {
- char *surrogate2 = str.ptr+i+5;
- if (surrogate2[0] == '\\' && surrogate2[1] == 'u') {
- cxstring c2_str = { surrogate2 + 2, 4 };
- uint32_t c2;
- if (!cx_strtou32_lc(c2_str, &c2, 16, "")) {
- codepoint = utf16pair_to_codepoint((uint16_t)codepoint, c2);
+ if (*(str.ptr+i+5) == '\\' && *(str.ptr+i+6) == 'u') {
+ cxstring ustr2 = { str.ptr+i+7, 4 };
+ if (!cx_strtou16_lc(ustr2, &utf16b, 16, "")
+ && utf16b >= 0xDC00 && utf16b <= 0xDFFF) {
+ codepoint = utf16pair_to_codepoint(utf16a, utf16b);
utf8len = codepoint_to_utf8(codepoint, utf8buf);
- i += 6;
+ i += 10;
}
}
}
} else {
// character is in the Basic Multilingual Plane
// and encoded as a single utf16 char
+ codepoint = utf16a;
utf8len = codepoint_to_utf8(codepoint, utf8buf);
+ i += 4;
}
- if(utf8len > 0) {
- // add all bytes from utf8buf expect the last char
- // to the result
- utf8len--;
- c = utf8buf[utf8len];
- for(int x=0;x<utf8len;x++) {
- result.ptr[result.length++] = utf8buf[x];
- }
+ }
+ if(utf8len > 0) {
+ // add all bytes from utf8buf except the last char
+ // to the result (last char will be added below)
+ utf8len--;
+ c = utf8buf[utf8len];
+ for (unsigned x = 0; x < utf8len; x++) {
+ result.ptr[result.length++] = utf8buf[x];
}
- i += 4;
+ } else {
+ // decoding failed, ignore the entire sequence
+ result.ptr[result.length++] = '\\';
}
}
+ } else {
+ // TODO: discuss the behavior for unrecognized escape sequences
+ // most parsers throw an error here - we just ignore it
+ result.ptr[result.length++] = '\\';
}
-
- // TODO: discuss the behavior for unrecognized escape sequences
- // most parsers throw an error here
+
result.ptr[result.length++] = c;
} else {
if (c == '\\') {