fix for elasticsearch

schema/settings.json

@@ -1,6 +1,6 @@
 {
   "index": {
-    "refresh_interval": "-1",
+    "refresh_interval": "30s",
     "codec": "best_compression"
   },
   "analysis": {
@@ -24,13 +24,15 @@
       "my_nGram": {
         "tokenizer": "my_nGram_tokenizer",
         "filter": [
-          "lowercase"
+          "lowercase",
+          "asciifolding"
         ]
       },
       "content_analyzer": {
         "tokenizer": "standard",
         "filter": [
-          "lowercase"
+          "lowercase",
+          "asciifolding"
         ]
       }
     }

src/index/elastic.c

@@ -70,7 +70,8 @@ void elastic_flush() {
 
     while (line != NULL) {
         char action_str[512];
-        snprintf(action_str, 512, "{\"index\":{\"_id\": \"%s\", \"_type\":\"_doc\"}}", line->uuid_str);
+        snprintf(action_str, 512,
+                "{\"index\":{\"_id\":\"%s\", \"_type\":\"_doc\", \"_index\":\"sist2\"}}\n", line->uuid_str);
         size_t action_str_len = strlen(action_str);
 
         size_t line_len = strlen(line->line);
@@ -98,6 +99,14 @@ void elastic_flush() {
     snprintf(bulk_url, 4096, "%s/sist2/_bulk", Indexer->es_url);
     response_t *r = web_post(bulk_url, buf, "Content-Type: application/x-ndjson");
     printf("Indexed %3d documents (%zukB) <%d>\n", count, buf_cur / 1024, r->status_code);
+
+    cJSON *ret_json = cJSON_Parse(r->body);
+    if (cJSON_GetObjectItem(ret_json, "errors")->valueint != 0) {
+        fprintf(stderr, "%s\n", r->body);
+    }
+
+    cJSON_Delete(ret_json);
+
     free_response(r);
 }
 
@@ -187,7 +196,7 @@ void elastic_init(int force_reset) {
         printf("Update settings <%d>\n", r->status_code);
         free_response(r);
 
-        snprintf(url, 4096, "%s/sist2/_mappings/_doc", IndexCtx.es_url);
+        snprintf(url, 4096, "%s/sist2/_mappings/_doc?include_type_name=true", IndexCtx.es_url);
         r = web_put(url, mappings_json, "Content-Type: application/json");
         printf("Update mappings <%d>\n", r->status_code);
         free_response(r);

src/io/serialize.c

@@ -232,7 +232,9 @@ void read_index(const char *path, const char index_id[UUID_STR_LEN], index_func
                 case MetaTitle: {
                     buf.cur = 0;
                     while ((c = getc(file)) != 0) {
-                        dyn_buffer_write_char(&buf, (char) c);
+                        if (!(SHOULD_IGNORE_CHAR(c) || c == ' ')) {
+                            dyn_buffer_write_char(&buf, (char) c);
+                        }
                     }
                     dyn_buffer_write_char(&buf, '\0');
                     cJSON_AddStringToObject(document, get_meta_key_text(key), buf.buf);

src/main.c

@@ -5,7 +5,7 @@
 #define EPILOG "Made by simon987 <me@simon987.net>. Released under GPL-3.0"
 
 
-static const char *const Version = "1.0.1";
+static const char *const Version = "1.0.2";
 static const char *const usage[] = {
         "sist2 scan [OPTION]... PATH",
         "sist2 index [OPTION]... INDEX",