itchyny
e001deb4cf
The UTF-8 BOM was stripped only at the start of the parser stream, but jq feeds all input files into a single parser, so a BOM at the start of the second and later files reached the parser as content and failed with a confusing "Invalid numeric literal" error. Strip it in the file readers instead, at the start of each input file including stdin, and in jv_load_file. This also strips the BOM for raw input, so -R and --rawfile no longer yield a leading U+FEFF, and a BOM at the start of a -f program file or an imported module is now accepted rather than reported as a syntax error. In exchange, "\uFEFF1" | fromjson is now a parse error, since a U+FEFF inside a string is content rather than an encoding marker, and the dedicated "Malformed BOM" error is gone.
96 lines
2.6 KiB
C
96 lines
2.6 KiB
C
#include <sys/stat.h>
|
|
|
|
#include <errno.h>
|
|
#include <fcntl.h>
|
|
#include <stdio.h>
|
|
#include <stdlib.h>
|
|
#include <string.h>
|
|
#include <unistd.h>
|
|
#include "jv.h"
|
|
#include "jv_unicode.h"
|
|
|
|
jv jv_load_file(const char* filename, int raw) {
|
|
struct stat sb;
|
|
int fd = open(filename, O_RDONLY);
|
|
if (fd == -1) {
|
|
return jv_invalid_with_msg(jv_string_fmt("Could not open %s: %s",
|
|
filename,
|
|
strerror(errno)));
|
|
}
|
|
if (fstat(fd, &sb) == -1 || S_ISDIR(sb.st_mode)) {
|
|
close(fd);
|
|
return jv_invalid_with_msg(jv_string_fmt("Could not open %s: %s",
|
|
filename,
|
|
"It's a directory"));
|
|
}
|
|
FILE* file = fdopen(fd, "r");
|
|
struct jv_parser* parser = NULL;
|
|
jv data;
|
|
if (!file) {
|
|
close(fd);
|
|
return jv_invalid_with_msg(jv_string_fmt("Could not open %s: %s",
|
|
filename,
|
|
strerror(errno)));
|
|
}
|
|
if (raw) {
|
|
data = jv_string("");
|
|
} else {
|
|
data = jv_array();
|
|
parser = jv_parser_new(0);
|
|
}
|
|
|
|
// To avoid mangling UTF-8 multi-byte sequences that cross the end of our read
|
|
// buffer, we need to be able to read the remainder of a sequence and add that
|
|
// before appending.
|
|
char buf[4096 + 4];
|
|
int at_file_start = 1;
|
|
while (!feof(file) && !ferror(file)) {
|
|
size_t n = fread(buf, 1, sizeof(buf) - 4, file);
|
|
if (n == 0)
|
|
continue;
|
|
|
|
char *end = buf + n;
|
|
int len = 0;
|
|
if (jvp_utf8_backtrack(end - 1, buf, &len) && len > 0 &&
|
|
!feof(file) && !ferror(file)) {
|
|
n += fread(end, 1, len, file);
|
|
}
|
|
|
|
char *p = buf;
|
|
if (at_file_start) {
|
|
// Strip UTF-8 BOM at the start of the file
|
|
if (n >= 3 && !memcmp(buf, "\xEF\xBB\xBF", 3)) {
|
|
p += 3;
|
|
n -= 3;
|
|
}
|
|
at_file_start = 0;
|
|
}
|
|
|
|
if (raw) {
|
|
data = jv_string_append_buf(data, p, n);
|
|
if (!jv_is_valid(data))
|
|
break;
|
|
} else {
|
|
jv_parser_set_buf(parser, p, n, !feof(file));
|
|
jv value;
|
|
while (jv_is_valid((value = jv_parser_next(parser))))
|
|
data = jv_array_append(data, value);
|
|
if (jv_invalid_has_msg(jv_copy(value))) {
|
|
jv_free(data);
|
|
data = value;
|
|
break;
|
|
}
|
|
jv_free(value);
|
|
}
|
|
}
|
|
if (!raw)
|
|
jv_parser_free(parser);
|
|
int badread = ferror(file);
|
|
if (fclose(file) != 0 || badread) {
|
|
jv_free(data);
|
|
return jv_invalid_with_msg(jv_string_fmt("Error reading from %s",
|
|
filename));
|
|
}
|
|
return data;
|
|
}
|