/** Return the number of countries recognized by the GeoIP database. */
int
geoip_get_n_countries(void)
{
if (!geoip_countries)
init_geoip_countries();
return (int) smartlist_len(geoip_countries);
}
/** Add an entry to the GeoIP table, parsing it from <b>line</b>. The
* format is as for geoip_load_file(). */
/*private*/ int
geoip_parse_entry(const char *line)
{
unsigned int low, high;
char b[3];
if (!geoip_countries)
init_geoip_countries();
if (!geoip_entries)
geoip_entries = smartlist_new();
while (TOR_ISSPACE(*line))
++line;
if (*line == '#')
return 0;
if (tor_sscanf(line,"%u,%u,%2s", &low, &high, b) == 3) {
geoip_add_entry(low, high, b);
return 0;
} else if (tor_sscanf(line,"\"%u\",\"%u\",\"%2s\",", &low, &high, b) == 3) {
geoip_add_entry(low, high, b);
return 0;
} else {
log_warn(LD_GENERAL, "Unable to parse line from GEOIP file: %s",
escaped(line));
return -1;
}
}
/** Clear the GeoIP database and reload it from the file
* <b>filename</b>. Return 0 on success, -1 on failure.
*
* Recognized line formats are:
* INTIPLOW,INTIPHIGH,CC
* and
* "INTIPLOW","INTIPHIGH","CC","CC3","COUNTRY NAME"
* where INTIPLOW and INTIPHIGH are IPv4 addresses encoded as 4-byte unsigned
* integers, and CC is a country code.
*
* It also recognizes, and skips over, blank lines and lines that start
* with '#' (comments).
*/
int
geoip_load_file(const char *filename, const or_options_t *options)
{
FILE *f;
const char *msg = "";
int severity = options_need_geoip_info(options, &msg) ? LOG_WARN : LOG_INFO;
crypto_digest_t *geoip_digest_env = NULL;
clear_geoip_db();
if (!(f = tor_fopen_cloexec(filename, "r"))) {
log_fn(severity, LD_GENERAL, "Failed to open GEOIP file %s. %s",
filename, msg);
return -1;
}
if (!geoip_countries)
init_geoip_countries();
if (geoip_entries) {
SMARTLIST_FOREACH(geoip_entries, geoip_entry_t *, e, tor_free(e));
smartlist_free(geoip_entries);
}
geoip_entries = smartlist_new();
geoip_digest_env = crypto_digest_new();
log_notice(LD_GENERAL, "Parsing GEOIP file %s.", filename);
while (!feof(f)) {
char buf[512];
if (fgets(buf, (int)sizeof(buf), f) == NULL)
break;
crypto_digest_add_bytes(geoip_digest_env, buf, strlen(buf));
/* FFFF track full country name. */
geoip_parse_entry(buf);
}
/*XXXX abort and return -1 if no entries/illformed?*/
fclose(f);
smartlist_sort(geoip_entries, geoip_compare_entries_);
/* Okay, now we need to maybe change our mind about what is in which
* country. */
refresh_all_country_info();
/* Remember file digest so that we can include it in our extra-info
* descriptors. */
crypto_digest_get_digest(geoip_digest_env, geoip_digest, DIGEST_LEN);
crypto_digest_free(geoip_digest_env);
return 0;
}
/** Clear appropriate GeoIP database, based on <b>family</b>, and
* reload it from the file <b>filename</b>. Return 0 on success, -1 on
* failure.
*
* Recognized line formats for IPv4 are:
* INTIPLOW,INTIPHIGH,CC
* and
* "INTIPLOW","INTIPHIGH","CC","CC3","COUNTRY NAME"
* where INTIPLOW and INTIPHIGH are IPv4 addresses encoded as 4-byte unsigned
* integers, and CC is a country code.
*
* Recognized line format for IPv6 is:
* IPV6LOW,IPV6HIGH,CC
* where IPV6LOW and IPV6HIGH are IPv6 addresses and CC is a country code.
*
* It also recognizes, and skips over, blank lines and lines that start
* with '#' (comments).
*/
int
geoip_load_file(sa_family_t family, const char *filename)
{
FILE *f;
const char *msg = "";
const or_options_t *options = get_options();
int severity = options_need_geoip_info(options, &msg) ? LOG_WARN : LOG_INFO;
crypto_digest_t *geoip_digest_env = NULL;
tor_assert(family == AF_INET || family == AF_INET6);
if (!(f = tor_fopen_cloexec(filename, "r"))) {
log_fn(severity, LD_GENERAL, "Failed to open GEOIP file %s. %s",
filename, msg);
return -1;
}
if (!geoip_countries)
init_geoip_countries();
if (family == AF_INET) {
if (geoip_ipv4_entries) {
SMARTLIST_FOREACH(geoip_ipv4_entries, geoip_ipv4_entry_t *, e,
tor_free(e));
smartlist_free(geoip_ipv4_entries);
}
geoip_ipv4_entries = smartlist_new();
} else { /* AF_INET6 */
if (geoip_ipv6_entries) {
SMARTLIST_FOREACH(geoip_ipv6_entries, geoip_ipv6_entry_t *, e,
tor_free(e));
smartlist_free(geoip_ipv6_entries);
}
geoip_ipv6_entries = smartlist_new();
}
geoip_digest_env = crypto_digest_new();
log_notice(LD_GENERAL, "Parsing GEOIP %s file %s.",
(family == AF_INET) ? "IPv4" : "IPv6", filename);
while (!feof(f)) {
char buf[512];
if (fgets(buf, (int)sizeof(buf), f) == NULL)
break;
crypto_digest_add_bytes(geoip_digest_env, buf, strlen(buf));
/* FFFF track full country name. */
geoip_parse_entry(buf, family);
}
/*XXXX abort and return -1 if no entries/illformed?*/
fclose(f);
/* Sort list and remember file digests so that we can include it in
* our extra-info descriptors. */
if (family == AF_INET) {
smartlist_sort(geoip_ipv4_entries, geoip_ipv4_compare_entries_);
/* Okay, now we need to maybe change our mind about what is in
* which country. We do this for IPv4 only since that's what we
* store in node->country. */
refresh_all_country_info();
crypto_digest_get_digest(geoip_digest_env, geoip_digest, DIGEST_LEN);
} else {
/* AF_INET6 */
smartlist_sort(geoip_ipv6_entries, geoip_ipv6_compare_entries_);
crypto_digest_get_digest(geoip_digest_env, geoip6_digest, DIGEST_LEN);
}
crypto_digest_free(geoip_digest_env);
return 0;
}
/** Add an entry to the GeoIP table indicated by <b>family</b>,
* parsing it from <b>line</b>. The format is as for geoip_load_file(). */
/*private*/ int
geoip_parse_entry(const char *line, sa_family_t family)
{
tor_addr_t low_addr, high_addr;
char c[3];
char *country = NULL;
if (!geoip_countries)
init_geoip_countries();
if (family == AF_INET) {
if (!geoip_ipv4_entries)
geoip_ipv4_entries = smartlist_new();
} else if (family == AF_INET6) {
if (!geoip_ipv6_entries)
geoip_ipv6_entries = smartlist_new();
} else {
log_warn(LD_GENERAL, "Unsupported family: %d", family);
return -1;
}
while (TOR_ISSPACE(*line))
++line;
if (*line == '#')
return 0;
if (family == AF_INET) {
unsigned int low, high;
if (tor_sscanf(line,"%u,%u,%2s", &low, &high, c) == 3 ||
tor_sscanf(line,"\"%u\",\"%u\",\"%2s\",", &low, &high, c) == 3) {
tor_addr_from_ipv4h(&low_addr, low);
tor_addr_from_ipv4h(&high_addr, high);
} else
goto fail;
country = c;
} else { /* AF_INET6 */
char buf[512];
char *low_str, *high_str;
struct in6_addr low, high;
char *strtok_state;
strlcpy(buf, line, sizeof(buf));
low_str = tor_strtok_r(buf, ",", &strtok_state);
if (!low_str)
goto fail;
high_str = tor_strtok_r(NULL, ",", &strtok_state);
if (!high_str)
goto fail;
country = tor_strtok_r(NULL, "\n", &strtok_state);
if (!country)
goto fail;
if (strlen(country) != 2)
goto fail;
if (tor_inet_pton(AF_INET6, low_str, &low) <= 0)
goto fail;
tor_addr_from_in6(&low_addr, &low);
if (tor_inet_pton(AF_INET6, high_str, &high) <= 0)
goto fail;
tor_addr_from_in6(&high_addr, &high);
}
geoip_add_entry(&low_addr, &high_addr, country);
return 0;
fail:
log_warn(LD_GENERAL, "Unable to parse line from GEOIP %s file: %s",
family == AF_INET ? "IPv4" : "IPv6", escaped(line));
return -1;
}
