User scripts, bug fixes, docker image

CMakeLists.txt

@@ -122,10 +122,10 @@ if (WITH_SIST2)
 
     target_compile_options(sist2
             PRIVATE
-            -Ofast
+#            -Ofast
 #                    -march=native
-            -fno-stack-protector
-            -fomit-frame-pointer
+#            -fno-stack-protector
+#            -fomit-frame-pointer
             )
 
     TARGET_LINK_LIBRARIES(

Docker/Dockerfile

@@ -0,0 +1,9 @@
+FROM ubuntu:19.10
+MAINTAINER simon987 <me@simon987.net>
+
+RUN apt update
+RUN apt install -y libglib2.0-0 libcurl4 libmagic1 libharfbuzz-bin libopenjp2-7
+
+ADD sist2 /root/sist2
+
+ENTRYPOINT ["/root/sist2"]

Docker/build.sh

@@ -0,0 +1,8 @@
+cp ../sist2 .
+
+version=$(./sist2 --version)
+
+echo "Version ${version}"
+docker build . -t simon987/sist2:${version} -t simon987/sist2:latest
+docker push simon987/sist2:${version}
+docker push simon987/sist2:latest

README.md

@@ -14,18 +14,21 @@ sist2 (Simple incremental search tool)
 * Extracts text from common file types\*
 * Generates thumbnails\*
 * Incremental scanning
+* Automatic tagging from file attributes via [user scripts](scripting/README.md)
 
 
 \* See [format support](#format-support)
 
 ## Getting Started
 
 1. Have an [Elasticsearch](https://www.elastic.co/downloads/elasticsearch) instance running
-1. Download the [latest sist2 release](https://github.com/simon987/sist2/releases)
+1. 
+    1. Download the [latest sist2 release](https://github.com/simon987/sist2/releases) *
+    1. *(or)* `docker pull simon987/sist2:latest`
+
 
-*Windows users*: `sist2` runs under [WSL](https://en.wikipedia.org/wiki/Windows_Subsystem_for_Linux)
-
-*Mac users*: See [#1](https://github.com/simon987/sist2/issues/1)
+\* *Windows users*: **sist2** runs under [WSL](https://en.wikipedia.org/wiki/Windows_Subsystem_for_Linux)    
+\* *Mac users*: See [#1](https://github.com/simon987/sist2/issues/1)
 
 
 ## Example usage
@@ -52,6 +55,32 @@ sist2 index --print ./my_idx > raw_documents.ndjson
 sist2 web --bind 0.0.0.0 --port 4321 ./my_idx1 ./my_idx2 ./my_idx3
 ```
 
+### Use sist2 with docker
+
+**scan**
+```bash
+docker run -it \
+    -v /path/to/files/:/files \
+    -v $PWD/out/:/out \
+    simon987/sist2 scan -t 4 /files -o /out/my_idx1
+```
+**index**
+```bash
+docker run -it --network host\
+    -v $PWD/out/:/out \
+    simon987/sist2 index /out/my_idx1
+```
+
+**web**
+```bash
+docker run --rm --network host -d --name sist2\
+    -v $PWD/out/my_idx:/idx \
+    -v $PWD/my/files:/files
+    simon987/sist2 web --bind 0.0.0.0 /idx
+docker stop sist2
+```
+
+
 ## Format support
 
 File type | Library | Content | Thumbnail | Metadata

schema/mappings.json

@@ -80,6 +80,9 @@
           "analyzer": "my_nGram"
         }
       }
+    },
+    "tag": {
+      "type": "keyword"
     }
   }
 }

scripting/README.md

@@ -0,0 +1,117 @@
+## User scripts
+
+*This document is under construction, more in-depth guide coming soon*
+
+During the `index` step, you can use the `--script-file <script>` option to
+modify documents or add user tags. This option is mainly used to
+implement automatic tagging based on file attributes.
+
+The scripting language used 
+([Painless Scripting Language](https://www.elastic.co/guide/en/elasticsearch/painless/7.4/index.html)) 
+is very similar to Java, but you should be able to create user scripts
+without programming experience at all if you're somewhat familiar with
+regex.
+
+This is the base structure of the documents we're working with:
+```json
+{
+  "_id": "e171405c-fdb5-4feb-bb32-82637bc32084",
+  "_index": "sist2",
+  "_type": "_doc",
+  "_source": {
+    "index": "206b3050-e821-421a-891d-12fcf6c2db0d",
+    "mime": "application/json",
+    "size": 1799,
+    "mtime": 1545443685,
+    "extension": "md",
+    "name": "README",
+    "path": "sist2/scripting",
+    "content": "..."
+  }
+}
+```
+
+**Example script**
+
+This script checks if the `genre` attribute exists, if it does
+it adds the `genre.<genre>` tag. 
+```Java
+ArrayList tags = ctx._source.tag = new ArrayList();
+
+if (ctx._source?.genre != null) {
+    tags.add("genre." + ctx._source.genre.toLowerCase())
+}
+```
+
+You can use `.` to create a hierarchical tag tree:
+
+![scripting/genre_example](genre_example.png)
+
+
+To use regular expressions, you need to add this line in `/etc/elasticsearch/elasticsearch.yml`
+```yaml
+script.painless.regex.enabled: true
+```
+Or, if you're using docker add `-e "script.painless.regex.enabled=true"`
+
+### Examples
+
+If `(20XX)` is in the file name, add the `year.<year>` tag:
+```Java
+ArrayList tags = ctx._source.tag = new ArrayList();
+
+Matcher m = /[\(\.+](20[0-9]{2})[\)\.+]/.matcher(ctx._source.name);
+if (m.find()) {
+    tags.add("year." + m.group(1))
+}
+```
+
+Use default *Calibre* folder structure to infer author.
+```Java
+ArrayList tags = ctx._source.tag = new ArrayList();
+
+// We expect the book path to look like this:
+//  /path/to/Calibre Library/Author/Title/Title - Author.pdf
+
+if (ctx._source.name.contains("-") && ctx._source.extension == "pdf") {
+    String[] names = ctx._source.name.splitOnToken('-');
+    tags.add("author." + names[1].strip());
+}
+```
+
+If the file matches a specific pattern `AAAA-000 fName1 lName1, <fName2 lName2>...`, add the `actress.<actress>` and 
+`studio.<studio>` tag:
+```Java
+ArrayList tags = ctx._source.tag = new ArrayList();
+
+Matcher m = /([A-Z]{4})-[0-9]{3} (.*)/.matcher(ctx._source.name);
+if (m.find()) {
+    tags.add("studio." + m.group(1));
+
+    // Take the matched group (.*), and add a tag for
+    //  each name, separated by comma
+    for (String name : m.group(2).splitOnToken(',')) {
+        tags.add("actress." + name);
+    }
+}
+```
+
+Set the name of the last folder (`/path/to/<studio>/file.mp4`) to `studio.<studio>` tag
+```Java
+ArrayList tags = ctx._source.tag = new ArrayList();
+
+if (ctx._source.path != "") {
+    String[] names = ctx._source.path.splitOnToken('/');
+    tags.add("studio." + names[names.length-1]);
+}
+```
+
+Set the name of the last folder (`/path/to/<studio>/file.mp4`) to `studio.<studio>` tag
+```Java
+ArrayList tags = ctx._source.tag = new ArrayList();
+
+if (ctx._source.path != "") {
+    String[] names = ctx._source.path.splitOnToken('/');
+    tags.add("studio." + names[names.length-1]);
+}
+```

src/cli.c

@@ -2,8 +2,8 @@
 
 #define DEFAULT_OUTPUT "index.sist2/"
 #define DEFAULT_CONTENT_SIZE 4096
-#define DEFAULT_QUALITY 15
-#define DEFAULT_SIZE 200
+#define DEFAULT_QUALITY 5
+#define DEFAULT_SIZE 500
 #define DEFAULT_REWRITE_URL ""
 
 #define DEFAULT_ES_URL "http://localhost:9200"
@@ -25,7 +25,7 @@ int scan_args_validate(scan_args_t *args, int argc, const char **argv) {
 
     char *abs_path = abspath(argv[1]);
     if (abs_path == NULL) {
-        fprintf(stderr, "File not found: %s", argv[1]);
+        fprintf(stderr, "File not found: %s\n", argv[1]);
         return 1;
     } else {
         args->path = abs_path;
@@ -34,7 +34,7 @@ int scan_args_validate(scan_args_t *args, int argc, const char **argv) {
     if (args->incremental != NULL) {
         abs_path = abspath(args->incremental);
         if (abs_path == NULL) {
-            fprintf(stderr, "File not found: %s", args->incremental);
+            fprintf(stderr, "File not found: %s\n", args->incremental);
             return 1;
         }
     }
@@ -100,7 +100,7 @@ int index_args_validate(index_args_t *args, int argc, const char **argv) {
 
     char *index_path = abspath(argv[1]);
     if (index_path == NULL) {
-        fprintf(stderr, "File not found: %s", argv[1]);
+        fprintf(stderr, "File not found: %s\n", argv[1]);
         return 1;
     } else {
         args->index_path = argv[1];
@@ -109,6 +109,27 @@ int index_args_validate(index_args_t *args, int argc, const char **argv) {
     if (args->es_url == NULL) {
         args->es_url = DEFAULT_ES_URL;
     }
+
+    if (args->script_path != NULL) {
+        struct stat info;
+        int res = stat(args->script_path, &info);
+
+        if (res == -1) {
+            fprintf(stderr, "Error opening script file '%s': %s\n", args->script_path, strerror(errno));
+            return 1;
+        }
+
+        int fd = open(args->script_path, O_RDONLY);
+        if (fd == -1) {
+            fprintf(stderr, "Error opening script file '%s': %s\n", args->script_path, strerror(errno));
+            return 1;
+        }
+
+        args->script = malloc(info.st_size + 1);
+        read(fd, args->script, info.st_size);
+        *(args->script + info.st_size) = '\0';
+        close(fd);
+    }
     return 0;
 }
 
@@ -137,7 +158,7 @@ int web_args_validate(web_args_t *args, int argc, const char **argv) {
     for (int i = 0; i < args->index_count; i++) {
         char *abs_path = abspath(args->indices[i]);
         if (abs_path == NULL) {
-            fprintf(stderr, "File not found: %s", abs_path);
+            fprintf(stderr, "File not found: %s\n", abs_path);
             return 1;
         }
     }

src/cli.h

@@ -22,6 +22,8 @@ int scan_args_validate(scan_args_t *args, int argc, const char **argv);
 typedef struct index_args {
     char *es_url;
     const char *index_path;
+    const char *script_path;
+    char *script;
     int print;
     int force_reset;
 } index_args_t;

src/index/elastic.c

@@ -6,7 +6,6 @@
 #include <stdio.h>
 #include <string.h>
 #include <cJSON/cJSON.h>
-#include <src/ctx.h>
 
 #include "static_generated.c"
 
@@ -54,6 +53,40 @@ void index_json(cJSON *document, const char uuid_str[UUID_STR_LEN]) {
     elastic_index_line(bulk_line);
 }
 
+void execute_update_script(const char *script, const char index_id[UUID_STR_LEN]) {
+
+    cJSON *body = cJSON_CreateObject();
+    cJSON *script_obj = cJSON_AddObjectToObject(body, "script");
+    cJSON_AddStringToObject(script_obj, "lang", "painless");
+    cJSON_AddStringToObject(script_obj, "source", script);
+
+    cJSON *query = cJSON_AddObjectToObject(body, "query");
+    cJSON *term_obj = cJSON_AddObjectToObject(query, "term");
+    cJSON_AddStringToObject(term_obj, "index", index_id);
+
+    char * str = cJSON_Print(body);
+
+    char bulk_url[4096];
+    snprintf(bulk_url, 4096, "%s/sist2/_update_by_query?pretty", Indexer->es_url);
+    response_t *r = web_post(bulk_url, str, "Content-Type: application/json");
+    printf("Executed user script <%d>\n", r->status_code);
+    cJSON *resp = cJSON_Parse(r->body);
+
+    cJSON_free(str);
+    cJSON_Delete(body);
+    free_response(r);
+
+    cJSON *error = cJSON_GetObjectItem(resp, "error");
+    if (error != NULL) {
+        char *error_str = cJSON_Print(error);
+
+        fprintf(stderr, "User script error: \n%s\n", error_str);
+        cJSON_free(error_str);
+    }
+
+    cJSON_Delete(resp);
+}
+
 void elastic_flush() {
 
     if (Indexer == NULL) {
@@ -115,6 +148,7 @@ void elastic_flush() {
     cJSON_Delete(ret_json);
 
     free_response(r);
+    free(buf);
 }
 
 void elastic_index_line(es_bulk_line_t *line) {
@@ -140,8 +174,7 @@ void elastic_index_line(es_bulk_line_t *line) {
 
 es_indexer_t *create_indexer(const char *url) {
 
-    size_t url_len = strlen(url);
-    char *es_url = malloc(url_len);
+    char *es_url = malloc(strlen(url) + 1);
     strcpy(es_url, url);
 
     es_indexer_t *indexer = malloc(sizeof(es_indexer_t));
@@ -154,7 +187,7 @@ es_indexer_t *create_indexer(const char *url) {
     return indexer;
 }
 
-void destroy_indexer() {
+void destroy_indexer(char * script, char index_id[UUID_STR_LEN]) {
 
     char url[4096];
 
@@ -163,6 +196,15 @@ void destroy_indexer() {
     printf("Refresh index <%d>\n", r->status_code);
     free_response(r);
 
+    if (script != NULL) {
+        execute_update_script(script, index_id);
+    }
+
+    snprintf(url, sizeof(url), "%s/sist2/_refresh", IndexCtx.es_url);
+    r = web_post(url, "", NULL);
+    printf("Refresh index <%d>\n", r->status_code);
+    free_response(r);
+
     snprintf(url, sizeof(url), "%s/sist2/_forcemerge", IndexCtx.es_url);
     r = web_post(url, "", NULL);
     printf("Merge index <%d>\n", r->status_code);