diff --git a/etc/example.conf b/etc/example.conf
index b118ab9c..356944ef 100644
--- a/etc/example.conf
+++ b/etc/example.conf
@@ -103,6 +103,13 @@ archive_only_mydomains=0
 ; minimum word length in mail body to index
 min_word_len=1
 
+; whether to enable CJK (=Chinese, Japanese, and Korean) "characters".
+; the text piler can see with CJK languages may have extremely long
+; sequences without any whitespace. To prevent the parser to drop
+; these very long sequences, enable (1) this feature. By default it's
+; disabled (0).
+enable_cjk=0
+
 ; if piler detects this line in the mail header, then it will assume
 ; the message is a spam. You should include your own antispam solution's
 ; specific line.
diff --git a/src/cfg.c b/src/cfg.c
index 04fe0608..02878e13 100644
--- a/src/cfg.c
+++ b/src/cfg.c
@@ -68,6 +68,7 @@ struct _parse_rule config_parse_rules[] =
    { "clamd_socket", "string", (void*) string_parser, offsetof(struct __config, clamd_socket), CLAMD_SOCKET, MAXVAL-1},
    { "debug", "integer", (void*) int_parser, offsetof(struct __config, debug), "0", sizeof(int)},
    { "default_retention_days", "integer", (void*) int_parser, offsetof(struct __config, default_retention_days), "2557", sizeof(int)},
+   { "enable_cjk", "integer", (void*) int_parser, offsetof(struct __config, enable_cjk), "0", sizeof(int)},
    { "encrypt_messages", "integer", (void*) int_parser, offsetof(struct __config, encrypt_messages), "1", sizeof(int)},
    { "extra_to_field", "string", (void*) string_parser, offsetof(struct __config, extra_to_field), "", MAXVAL-1},
    { "hostid", "string", (void*) string_parser, offsetof(struct __config, hostid), HOSTID, MAXVAL-1},
diff --git a/src/cfg.h b/src/cfg.h
index 2a989e16..537f744e 100644
--- a/src/cfg.h
+++ b/src/cfg.h
@@ -84,6 +84,8 @@ struct __config {
 
    int tweak_sent_time_offset;
 
+   int enable_cjk;
+
    int debug;
 };
 
diff --git a/src/config.h b/src/config.h
index 31b1009c..65ea457e 100644
--- a/src/config.h
+++ b/src/config.h
@@ -14,7 +14,7 @@
 
 #define VERSION "0.1.25-master-branch"
 
-#define BUILD 851
+#define BUILD 852
 
 #define HOSTID "mailarchiver"
 
diff --git a/src/parser.c b/src/parser.c
index c7529cbf..aad91b1e 100644
--- a/src/parser.c
+++ b/src/parser.c
@@ -604,7 +604,7 @@ int parse_line(char *buf, struct _state *state, struct session_data *sdata, int
 
       if(strncasecmp(puf, "http://", 7) == 0 || strncasecmp(puf, "https://", 8) == 0) fixURL(puf);
 
-      if(state->is_header == 0 && strncmp(puf, "__URL__", 7) && (puf[0] == ' ' || strlen(puf) > MAX_WORD_LEN || isHexNumber(puf)) ) continue;
+      if(state->is_header == 0 && strncmp(puf, "__URL__", 7) && (puf[0] == ' ' || (strlen(puf) > MAX_WORD_LEN && cfg->enable_cjk == 0) || isHexNumber(puf)) ) continue;
 
 
       len = strlen(puf);