List mode tweak

List mode #5

.gitmodules

@@ -25,3 +25,9 @@
 [submodule "lib/harfbuzz"]
 	path = lib/harfbuzz
 	url = https://github.com/harfbuzz/harfbuzz
+[submodule "lib/libmagic"]
+	path = lib/libmagic
+	url = https://github.com/threatstack/libmagic
+[submodule "lib/bzip2-1.0.6"]
+	path = lib/bzip2-1.0.6
+	url = https://github.com/enthought/bzip2-1.0.6

CMakeLists.txt

@@ -23,6 +23,7 @@ if (WITH_SIST2)
             src/parsing/text.h src/parsing/text.c
             src/index/web.c src/index/web.h
             src/web/serve.c src/web/serve.h
+            src/web/auth_basic.h src/web/auth_basic.c
             src/index/elastic.c src/index/elastic.h
             src/util.c src/util.h
             src/ctx.h src/types.h src/parsing/font.c src/parsing/font.h

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

@@ -14,6 +14,7 @@ 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)
@@ -21,11 +22,13 @@ sist2 (Simple incremental search tool)
 ## 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
@@ -52,14 +55,40 @@ 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
 :---|:---|:---|:---|:---
-pdf,xps,cbz,cbr,fb2,epub | MuPDF | yes | yes, `png` | title |
+pdf,xps,cbz,fb2,epub | MuPDF | yes | yes, `png` | title |
 `audio/*` | ffmpeg | - | yes, `jpeg` | ID3 tags |
-`video/*` | ffmpeg | - | yes, `jpeg` | title, comment |
-`image/*` | ffmpeg | - | yes, `jpeg` | *planned* |
+`video/*` | ffmpeg | - | yes, `jpeg` | title, comment, artist |
+`image/*` | ffmpeg | - | yes, `jpeg` | `EXIF:Artist`, `EXIF:ImageDescription` |
 ttf,ttc,cff,woff,fnt,otf | Freetype2 | - | yes, `bmp` | Name & style |
 `text/plain` | *(none)* | yes | no | - |
 docx, xlsx, pptx |  | *planned* | no | *planned* |

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]);
+}
+```

scripts/get_static_libs.sh

@@ -54,14 +54,12 @@ cd ../..
 mv onion/build/src/onion/libonion_static.a .
 
 #bzip2
-git clone https://github.com/enthought/bzip2-1.0.6
 cd bzip2-1.0.6
 make -j 4
 cd ..
 mv bzip2-1.0.6/libbz2.a .
 
 # magic
-git clone https://github.com/threatstack/libmagic
 cd libmagic
 ./autogen.sh
 ./configure --enable-static --disable-shared

scripts/get_static_libs_freebsd.sh

@@ -42,14 +42,12 @@ mv ffmpeg/libswresample/libswresample.a .
 mv ffmpeg/libswscale/libswscale.a .
 
 #bzip2
-git clone https://github.com/enthought/bzip2-1.0.6
 cd bzip2-1.0.6
 make -j 4
 cd ..
 mv bzip2-1.0.6/libbz2.a .
 
 # magic
-git clone https://github.com/threatstack/libmagic
 cd libmagic
 ./autogen.sh
 ./configure --enable-static --disable-shared

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 +109,32 @@ 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);
+        res = read(fd, args->script, info.st_size);
+        if (res == -1) {
+            fprintf(stderr, "Error reading script file '%s': %s\n", args->script_path, strerror(errno));
+            return 1;
+        }
+
+        *(args->script + info.st_size) = '\0';
+        close(fd);
+    }
     return 0;
 }
 
@@ -131,13 +157,19 @@ int web_args_validate(web_args_t *args, int argc, const char **argv) {
         args->port = DEFAULT_PORT;
     }
 
+    if (args->credentials != NULL) {
+        args->b64credentials = onion_base64_encode(args->credentials, (int)strlen(args->credentials));
+        //Remove trailing newline
+        *(args->b64credentials + strlen(args->b64credentials) - 1) = '\0';
+    }
+
     args->index_count = argc - 1;
     args->indices = argv + 1;
 
     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;
@@ -30,6 +32,8 @@ typedef struct web_args {
     char *es_url;
     char *bind;
     char *port;
+    char *credentials;
+    char *b64credentials;
     int index_count;
     const char **indices;
 } web_args_t;

src/ctx.h

@@ -34,6 +34,7 @@ struct {
 struct {
     char *es_url;
     int index_count;
+    char* b64credentials;
     struct index_t indices[16];
 } WebCtx;
 #endif

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) {
@@ -98,6 +131,12 @@ void elastic_flush() {
     char bulk_url[4096];
     snprintf(bulk_url, 4096, "%s/sist2/_bulk", Indexer->es_url);
     response_t *r = web_post(bulk_url, buf, "Content-Type: application/x-ndjson");
+
+    if (r->status_code == 0) {
+        fprintf(stderr, "Could not connect to %s, make sure that elasticsearch is running!\n", IndexCtx.es_url);
+        exit(1);
+    }
+
     printf("Indexed %3d documents (%zukB) <%d>\n", count, buf_cur / 1024, r->status_code);
 
     cJSON *ret_json = cJSON_Parse(r->body);
@@ -115,6 +154,7 @@ void elastic_flush() {
     cJSON_Delete(ret_json);
 
     free_response(r);
+    free(buf);
 }
 
 void elastic_index_line(es_bulk_line_t *line) {
@@ -140,8 +180,7 @@ 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 +193,7 @@ 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 +202,15 @@ 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);

src/index/elastic.h

@@ -24,7 +24,7 @@ void index_json(cJSON *document, const char uuid_str[UUID_STR_LEN]);
 
 es_indexer_t *create_indexer(const char* es_url);
 
-void destroy_indexer();
+void destroy_indexer(char *script, char index_id[UUID_STR_LEN]);
 
 void elastic_init(int force_reset);
 

src/io/serialize.c

@@ -54,6 +54,12 @@ index_descriptor_t read_index_descriptor(char *path) {
     struct stat info;
     stat(path, &info);
     int fd = open(path, O_RDONLY);
+
+    if (fd == -1) {
+        fprintf(stderr, "Invalid/corrupt index (Could not find descriptor)\n");
+        exit(1);
+    }
+
     char *buf = malloc(info.st_size + 1);
     read(fd, buf, info.st_size);
     *(buf + info.st_size) = '\0';
@@ -258,8 +264,9 @@ void read_index(const char *path, const char index_id[UUID_STR_LEN], index_func
         }
 
         func(document, uuid_str);
-        cJSON_free(document);
+        cJSON_Delete(document);
     }
+    dyn_buffer_destroy(&buf);
     fclose(file);
 }
 

src/io/store.c

@@ -15,7 +15,7 @@ store_t *store_create(char *path) {
     );
 
     if (open_ret != 0) {
-        fprintf(stderr, "Error while opening store: %s", mdb_strerror(open_ret));
+        fprintf(stderr, "Error while opening store: %s (%s)\n", mdb_strerror(open_ret), path);
         exit(1);
     }
 

src/main.c

@@ -10,7 +10,7 @@
 #define EPILOG "Made by simon987 <me@simon987.net>. Released under GPL-3.0"
 
 
-static const char *const Version = "1.1.2";
+static const char *const Version = "1.1.7";
 static const char *const usage[] = {
         "sist2 scan [OPTION]... PATH",
         "sist2 index [OPTION]... INDEX",
@@ -163,10 +163,11 @@ void sist2_index(index_args_t *args) {
             read_index(file_path, desc.uuid, f);
         }
     }
+    closedir(dir);
 
     if (!args->print) {
         elastic_flush();
-        destroy_indexer();
+        destroy_indexer(args->script, desc.uuid);
     }
 }
 
@@ -174,6 +175,7 @@ void sist2_web(web_args_t *args) {
 
     WebCtx.es_url = args->es_url;
     WebCtx.index_count = args->index_count;
+    WebCtx.b64credentials = args->b64credentials;
 
     for (int i = 0; i < args->index_count; i++) {
         char *abs_path = abspath(args->indices[i]);
@@ -208,16 +210,20 @@ int main(int argc, const char *argv[]) {
     web_args_t *web_args = web_args_create();
     #endif
 
+    int arg_version = 0;
+
     char * common_es_url = NULL;
 
     struct argparse_option options[] = {
             OPT_HELP(),
 
+            OPT_BOOLEAN('v', "version", &arg_version, "Show version and exit"),
+
             OPT_GROUP("Scan options"),
             OPT_INTEGER('t', "threads", &scan_args->threads, "Number of threads. DEFAULT=1"),
             OPT_FLOAT('q', "quality", &scan_args->quality,
-                      "Thumbnail quality, on a scale of 1.0 to 31.0, 1.0 being the best. DEFAULT=15"),
-            OPT_INTEGER(0, "size", &scan_args->size, "Thumbnail size, in pixels. DEFAULT=200"),
+                      "Thumbnail quality, on a scale of 1.0 to 31.0, 1.0 being the best. DEFAULT=5"),
+            OPT_INTEGER(0, "size", &scan_args->size, "Thumbnail size, in pixels. DEFAULT=500"),
             OPT_INTEGER(0, "content-size", &scan_args->content_size,
                         "Number of bytes to be extracted from text documents. DEFAULT=4096"),
             OPT_STRING(0, "incremental", &scan_args->incremental,
@@ -230,6 +236,7 @@ int main(int argc, const char *argv[]) {
             OPT_GROUP("Index options"),
             OPT_STRING(0, "es-url", &common_es_url, "Elasticsearch url. DEFAULT=http://localhost:9200"),
             OPT_BOOLEAN('p', "print", &index_args->print, "Just print JSON documents to stdout."),
+            OPT_STRING(0, "script-file", &index_args->script_path, "Path to user script."),
             OPT_BOOLEAN('f', "force-reset", &index_args->force_reset, "Reset Elasticsearch mappings and settings. "
                                                               "(You must use this option the first time you use the index command)"),
 
@@ -237,6 +244,7 @@ int main(int argc, const char *argv[]) {
             OPT_STRING(0, "es-url", &common_es_url, "Elasticsearch url. DEFAULT=http://localhost:9200"),
             OPT_STRING(0, "bind", &web_args->bind, "Listen on this address. DEFAULT=localhost"),
             OPT_STRING(0, "port", &web_args->port, "Listen on this port. DEFAULT=4090"),
+            OPT_STRING(0, "auth", &web_args->credentials, "Basic auth in user:password format"),
             #endif
 
             OPT_END(),
@@ -247,6 +255,11 @@ int main(int argc, const char *argv[]) {
     argparse_describe(&argparse, DESCRIPTION, EPILOG);
     argc = argparse_parse(&argparse, argc, argv);
 
+    if (arg_version) {
+        printf(Version);
+        exit(0);
+    }
+
     #ifndef SIST_SCAN_ONLY
     web_args->es_url = common_es_url;
     index_args->es_url = common_es_url;

src/parsing/media.c

@@ -116,9 +116,9 @@ AVFrame *read_frame(AVFormatContext *pFormatCtx, AVCodecContext *decoder, int st
     return frame;
 }
 
-#define APPEND_TAG_META(doc, tag, keyname) \
+#define APPEND_TAG_META(doc, tag_, keyname) \
     text_buffer_t tex = text_buffer_create(-1); \
-    text_buffer_append_string0(&tex, tag->value); \
+    text_buffer_append_string0(&tex, tag_->value); \
     meta_line_t *meta_tag = malloc(sizeof(meta_line_t) + tex.dyn_buffer.cur); \
     meta_tag->key = keyname; \
     strcpy(meta_tag->strval, tex.dyn_buffer.buf); \
@@ -151,30 +151,39 @@ void append_audio_meta(AVFormatContext *pFormatCtx, document_t *doc) {
 }
 
 __always_inline
-void append_video_meta(AVFormatContext *pFormatCtx, document_t *doc, int include_audio_tags) {
+void append_video_meta(AVFormatContext *pFormatCtx, AVFrame *frame, document_t *doc, int include_audio_tags, int is_video) {
 
-    meta_line_t *meta_duration = malloc(sizeof(meta_line_t));
-    meta_duration->key = MetaMediaDuration;
-    meta_duration->longval = pFormatCtx->duration / AV_TIME_BASE;
-    APPEND_META(doc, meta_duration)
+    if (is_video) {
+        meta_line_t *meta_duration = malloc(sizeof(meta_line_t));
+        meta_duration->key = MetaMediaDuration;
+        meta_duration->longval = pFormatCtx->duration / AV_TIME_BASE;
+        APPEND_META(doc, meta_duration)
 
-    meta_line_t *meta_bitrate = malloc(sizeof(meta_line_t));
-    meta_bitrate->key = MetaMediaBitrate;
-    meta_bitrate->longval = pFormatCtx->bit_rate;
-    APPEND_META(doc, meta_bitrate)
+        meta_line_t *meta_bitrate = malloc(sizeof(meta_line_t));
+        meta_bitrate->key = MetaMediaBitrate;
+        meta_bitrate->longval = pFormatCtx->bit_rate;
+        APPEND_META(doc, meta_bitrate)
+    }
 
     AVDictionaryEntry *tag = NULL;
-    while ((tag = av_dict_get(pFormatCtx->metadata, "", tag, AV_DICT_IGNORE_SUFFIX))) {
-        char key[32];
-        strncpy(key, tag->key, sizeof(key));
-
-        char *ptr = key;
-        for (; *ptr; ++ptr) *ptr = (char) tolower(*ptr);
-
-        if (strcmp(key, "title") == 0 && include_audio_tags) {
-            APPEND_TAG_META(doc, tag, MetaTitle)
-        } else if (strcmp(key, "comment") == 0) {
-            APPEND_TAG_META(doc, tag, MetaContent)
+    if (is_video) {
+        while ((tag = av_dict_get(pFormatCtx->metadata, "", tag, AV_DICT_IGNORE_SUFFIX))) {
+            if (include_audio_tags && strcmp(tag->key, "title") == 0) {
+                APPEND_TAG_META(doc, tag, MetaTitle)
+            } else if (strcmp(tag->key, "comment") == 0) {
+                APPEND_TAG_META(doc, tag, MetaContent)
+            } else if (include_audio_tags && strcmp(tag->key, "artist") == 0) {
+                APPEND_TAG_META(doc, tag, MetaArtist)
+            }
+        }
+    } else {
+        // EXIF metadata
+        while ((tag = av_dict_get(frame->metadata, "", tag, AV_DICT_IGNORE_SUFFIX))) {
+            if (include_audio_tags && strcmp(tag->key, "Artist") == 0) {
+                APPEND_TAG_META(doc, tag, MetaArtist)
+            } else if (strcmp(tag->key, "ImageDescription") == 0) {
+                APPEND_TAG_META(doc, tag, MetaContent)
+            }
         }
     }
 }
@@ -236,11 +245,6 @@ void parse_media(const char *filepath, document_t *doc) {
     if (video_stream != -1) {
         AVStream *stream = pFormatCtx->streams[video_stream];
 
-        if (stream->nb_frames > 1) {
-            //This is a video (not a still image)
-            append_video_meta(pFormatCtx, doc, audio_stream == -1);
-        }
-
         if (stream->codecpar->width <= MIN_SIZE || stream->codecpar->height <= MIN_SIZE) {
             avformat_close_input(&pFormatCtx);
             avformat_free_context(pFormatCtx);
@@ -273,6 +277,8 @@ void parse_media(const char *filepath, document_t *doc) {
             return;
         }
 
+        append_video_meta(pFormatCtx, frame, doc, audio_stream == -1, stream->nb_frames > 1);
+
         // Scale frame
         AVFrame *scaled_frame = scale_frame(decoder, frame, ScanCtx.tn_size);
 

src/sist.h

@@ -32,6 +32,7 @@
 #include <onion/handler.h>
 #include <onion/block.h>
 #include <onion/shortcuts.h>
+#include <onion/codecs.h>
 #include <curl/curl.h>
 #endif
 
@@ -56,6 +57,7 @@
 #include "src/index/elastic.h"
 #include "index/web.h"
 #include "web/serve.h"
+#include "web/auth_basic.h"
 #endif
 
 ;

src/web/auth_basic.c

@@ -0,0 +1,59 @@
+#import "auth_basic.h"
+
+#define UNAUTHORIZED_TEXT "Unauthorized"
+
+typedef struct auth_basic_data {
+    onion_handler *inside;
+    const char *b64credentials;
+} auth_basic_data_t;
+
+
+int authenticate(const char *expected, const char *credentials) {
+
+    if (expected == NULL) {
+        return TRUE;
+    }
+
+    if (credentials && strncmp(credentials, "Basic ", 6) == 0) {
+        if (strcmp((credentials + 6), expected) == 0) {
+            return TRUE;
+        }
+    }
+
+    return FALSE;
+}
+
+int auth_basic_handler(auth_basic_data_t *d,
+                       onion_request *req,
+                       onion_response *res) {
+
+    const char *credentials = onion_request_get_header(req, "Authorization");
+
+    if (authenticate(d->b64credentials, credentials)) {
+        return onion_handler_handle(d->inside, req, res);
+    }
+
+    onion_response_set_header(res, "WWW-Authenticate", "Basic realm=\"sist2\"");
+    onion_response_set_code(res, HTTP_UNAUTHORIZED);
+    onion_response_write(res, UNAUTHORIZED_TEXT, sizeof(UNAUTHORIZED_TEXT));
+    onion_response_set_length(res, sizeof(UNAUTHORIZED_TEXT));
+
+    return OCS_PROCESSED;
+}
+
+void auth_basic_free(auth_basic_data_t *data) {
+    onion_handler_free(data->inside);
+    free(data);
+}
+
+onion_handler *auth_basic(const char *b64credentials, onion_handler *inside_level) {
+
+    auth_basic_data_t *privdata = malloc(sizeof(auth_basic_data_t));
+
+    privdata->b64credentials = b64credentials;
+    privdata->inside = inside_level;
+
+    return onion_handler_new((onion_handler_handler) auth_basic_handler, privdata,
+                             (onion_handler_private_data_free) auth_basic_free);
+}
+

src/web/auth_basic.h

@@ -0,0 +1,4 @@
+#include "src/sist.h"
+
+
+onion_handler *auth_basic(const char *b64credentials, onion_handler *inside_level);

src/web/serve.c

@@ -245,6 +245,8 @@ int search(void *p, onion_request *req, onion_response *res) {
 
     if (r->status_code == 200) {
         onion_response_write(res, r->body, r->size);
+    } else {
+        onion_response_set_code(res, HTTP_INTERNAL_ERROR);
     }
 
     free_response(r);
@@ -391,9 +393,11 @@ void serve(const char *hostname, const char *port) {
     onion_set_hostname(o, hostname);
     onion_set_port(o, port);
 
-    onion_url *urls = onion_root_url(o);
+    onion_url *urls = onion_url_new();
 
     // Static paths
+    onion_set_root_handler(o, auth_basic(WebCtx.b64credentials, onion_url_to_handler(urls)));
+
     onion_url_add(urls, "", search_index);
     onion_url_add(urls, "css", style);
     onion_url_add(urls, "js", javascript);
@@ -410,6 +414,7 @@ void serve(const char *hostname, const char *port) {
     onion_url_add(urls, "^f/([a-fA-F0-9]{8}-[a-fA-F0-9]{4}-[a-fA-F0-9]{4}-[a-fA-F0-9]{4}-[a-fA-F0-9]{12})$", file);
     onion_url_add(urls, "i", index_info);
 
+
     printf("Starting web server @ http://%s:%s\n", hostname, port);
 
     onion_listen(o);

web/css/dark.css

@@ -1,3 +1,7 @@
+*:focus {
+    outline: 0;
+}
+
 a {
     color: #00BCD4;
 }
@@ -19,6 +23,20 @@ body {
     border: none;
 }
 
+.list-group-item {
+    background: #212121;
+    color: #e0e0e0;
+
+    border-top: 1px solid #424242;
+    border-bottom: none;
+    border-left: none;
+    border-right: none;
+}
+
+.list-group-item:first-child {
+    border-top: none;
+}
+
 .navbar-brand {
     font-size: 1.75rem;
     padding: 0;
@@ -89,12 +107,18 @@ body {
     white-space: nowrap;
     text-overflow: ellipsis;
     overflow: hidden;
+    color: #00BCD4;
 }
 
 .badge {
     margin-right: 3px;
 }
 
+.badge-user {
+    color: #212529;
+    background-color: #e0e0e0;
+}
+
 .fit {
     display: block;
     min-width: 64px;
@@ -106,6 +130,15 @@ body {
     height: auto;
 }
 
+.fit-sm {
+    display: block;
+    max-width: 64px;
+    max-height: 64px;
+    margin: 0 auto 0;
+    width: auto;
+    height: auto;
+}
+
 .audio-fit {
     height: 39px;
     vertical-align: bottom;
@@ -149,6 +182,8 @@ mark {
     border: 1px solid #616161;
     border-radius: 4px;
     margin: 3px;
+    white-space: normal;
+    color: rgb(224, 224, 224);
 }
 
 .irs-single, .irs-from, .irs-to {
@@ -164,6 +199,7 @@ mark {
     margin-top: 1em;
     margin-bottom: 1em;
 }
+
 .custom-select {
     overflow: auto;
     background-color: #37474F;
@@ -229,6 +265,7 @@ option {
     padding: 0.5rem;
     background: #212121;
     color: #eee;
+    margin-top: 1em;
 }
 
 .btn-xs {
@@ -239,4 +276,76 @@ option {
 
 .btn {
     color: #eee;
-}
+}
+
+.nav-tabs .nav-link {
+    color: #e0e0e0;
+}
+
+.nav-tabs .nav-item.show .nav-link, .nav-tabs .nav-link.active {
+    background-color: #212121;
+    border-color: #616161 #616161 #212121;
+    color: #e0e0e0;
+}
+
+.nav-tabs .nav-link:focus, .nav-tabs .nav-link:focus {
+    border-color: #616161 #616161 #212121;
+    color: #e0e0e0;
+}
+
+.nav-tabs .nav-link:focus, .nav-tabs .nav-link:hover {
+    border-color: #e0e0e0 #e0e0e0 #212121;
+    color: #e0e0e0;
+}
+
+.nav-tabs {
+    border-bottom: #616161;
+}
+
+.nav {
+    margin-top: 0.5rem;
+}
+
+@media (max-width: 800px) {
+    #treeTabs {
+        flex-basis: inherit;
+        flex-grow: inherit;
+    }
+}
+
+.list-group {
+    margin-top: 1em;
+}
+
+.list-group-item {
+    padding: .25rem 0.5rem;
+}
+
+.wrapper-sm {
+    min-width: 64px;
+}
+
+.media-expanded {
+    display: inherit;
+}
+
+.media-expanded .fit {
+    max-height: 250px;
+}
+
+@media (max-width: 600px) {
+    .media-expanded .fit {
+        max-height: none;
+    }
+
+    .tagline {
+        display: none;
+    }
+}
+
+.version {
+    color: #00BCD4;
+    margin-left: -18px;
+    margin-top: -14px;
+    font-size: 11px;
+}

web/css/light.css

@@ -1,4 +1,10 @@
-body {overflow-y:scroll;}
+*:focus {
+    outline: 0;
+}
+
+body {
+    overflow-y: scroll;
+}
 
 .progress {
     margin-top: 1em;
@@ -6,15 +12,19 @@ body {overflow-y:scroll;}
 
 .card {
     margin-top: 1em;
-    box-shadow: 0 .125rem .25rem rgba(0,0,0,.075) !important;
+    box-shadow: 0 .125rem .25rem rgba(0, 0, 0, .075) !important;
 }
+
 .navbar-brand {
     font-size: 1.75rem;
     padding: 0;
 }
+
 .navbar {
-    background: #F7F7F7; border-bottom: solid 1px #dfdfdf;
+    background: #F7F7F7;
+    border-bottom: solid 1px #dfdfdf;
 }
+
 .document {
     padding: 0.5rem;
 }
@@ -47,6 +57,11 @@ body {overflow-y:scroll;}
     background-color: #FFC107;
 }
 
+.badge-user {
+    color: #212529;
+    background-color: #e0e0e0;
+}
+
 .badge-text {
     color: #FFFFFF;
     background-color: #FAAB3C;
@@ -84,6 +99,15 @@ body {overflow-y:scroll;}
     height: auto;
 }
 
+.fit-sm {
+    display: block;
+    max-width: 64px;
+    max-height: 64px;
+    margin: 0 auto 0;
+    width: auto;
+    height: auto;
+}
+
 .audio-fit {
     height: 39px;
     vertical-align: bottom;
@@ -98,16 +122,17 @@ body {overflow-y:scroll;}
 }
 
 @media (min-width: 1500px) {
-    .container  {
+    .container {
         max-width: 1440px;
     }
+
     .card-columns {
         column-count: 5;
     }
 }
 
 @media (min-width: 1800px) {
-    .container  {
+    .container {
         max-width: 1550px;
     }
 }
@@ -119,13 +144,15 @@ mark {
 }
 
 .content-div {
-    font-family: SFMono-Regular,Menlo,Monaco,Consolas,"Liberation Mono","Courier New",monospace;
+    font-family: SFMono-Regular, Menlo, Monaco, Consolas, "Liberation Mono", "Courier New", monospace;
     font-size: 13px;
     padding: 1em;
     background-color: #f5f5f5;
     border: 1px solid #ccc;
     border-radius: 4px;
     margin: 3px;
+    white-space: normal;
+    color: #000;
 }
 
 .irs-single, .irs-from, .irs-to {
@@ -145,8 +172,7 @@ mark {
     margin-bottom: 1em;
 }
 
-.inspire-tree .selected > .wholerow, .inspire-tree .selected > .title-wrap:hover + .wholerow
-{
+.inspire-tree .selected > .wholerow, .inspire-tree .selected > .title-wrap:hover + .wholerow {
     background: none;
 }
 
@@ -162,10 +188,59 @@ mark {
     line-height: 1rem;
     padding: 0.5rem;
     background: #f8f9fa;
+    margin-top: 1em;
 }
 
 .btn-xs {
     padding: .1rem .3rem;
     font-size: .875rem;
     border-radius: .2rem;
-}
+}
+
+.nav {
+    margin-top: 0.5rem;
+}
+
+@media (max-width: 800px) {
+    #treeTabs {
+        flex-basis: inherit;
+        flex-grow: inherit;
+    }
+}
+
+.list-group {
+    margin-top: 1em;
+}
+
+.list-group-item {
+    padding: .25rem 0.5rem;
+}
+
+.wrapper-sm {
+    min-width: 64px;
+}
+
+.media-expanded {
+    display: inherit;
+}
+
+.media-expanded .fit {
+    max-height: 250px;
+}
+
+@media (max-width: 600px) {
+    .media-expanded .fit {
+        max-height: none;
+    }
+
+    .tagline {
+        display: none;
+    }
+}
+
+.version {
+    color: #007bff;
+    margin-left: -18px;
+    margin-top: -14px;
+    font-size: 11px;
+}

web/js/dom.js

@@ -75,6 +75,84 @@ function shouldPlayVideo(hit) {
     return videoc !== "hevc" && videoc !== "mpeg2video" && videoc !== "wmv3";
 }
 
+function makePlaceholder(w, h, small) {
+    let calc;
+    if (small) {
+        calc = w > h
+            ? (64 / w / h) >= 100
+                ? (64 * w / h)
+                : 64
+            : 64;
+    } else {
+        calc = w > h
+            ? (175 / w / h) >= 272
+                ? (175 * w / h)
+                : 175
+            : 175;
+    }
+
+    const el = document.createElement("div");
+    el.setAttribute("style", `height: ${calc}px`);
+    return el;
+}
+
+function makeTitle(hit) {
+    let title = document.createElement("div");
+    title.setAttribute("class", "file-title");
+    let extension = hit["_source"].hasOwnProperty("extension") && hit["_source"]["extension"] !== "" ? "." + hit["_source"]["extension"] : "";
+
+    applyNameToTitle(hit, title, extension);
+
+    title.setAttribute("title", hit["_source"]["path"] + "/" + hit["_source"]["name"] + extension);
+    return title;
+}
+
+function getTags(hit, mimeCategory) {
+
+    let tags = [];
+    switch (mimeCategory) {
+        case "video":
+        case "image":
+            if (hit["_source"].hasOwnProperty("videoc")) {
+                const formatTag = document.createElement("span");
+                formatTag.setAttribute("class", "badge badge-pill badge-video");
+                formatTag.appendChild(document.createTextNode(hit["_source"]["videoc"].replace(" ", "")));
+                tags.push(formatTag);
+            }
+            break;
+        case "audio": {
+            if (hit["_source"].hasOwnProperty("audioc")) {
+                let formatTag = document.createElement("span");
+                formatTag.setAttribute("class", "badge badge-pill badge-audio");
+                formatTag.appendChild(document.createTextNode(hit["_source"]["audioc"]));
+                tags.push(formatTag);
+            }
+        }
+            break;
+    }
+    // User tags
+    if (hit["_source"].hasOwnProperty("tag")) {
+        hit["_source"]["tag"].forEach(tag => {
+            const userTag = document.createElement("span");
+            userTag.setAttribute("class", "badge badge-pill badge-user");
+
+            const tokens = tag.split("#");
+
+            if (tokens.length > 1) {
+                const bg = "#" + tokens[1];
+                const fg = lum(tokens[1]) > 40 ? "#000" : "#fff";
+                userTag.setAttribute("style", `background-color: ${bg}; color: ${fg}`);
+            }
+
+            const name = tokens[0].split(".")[tokens[0].split(".").length - 1];
+            userTag.appendChild(document.createTextNode(name));
+            tags.push(userTag);
+        })
+    }
+
+    return tags
+}
+
 /**
  *
  * @param hit
@@ -92,22 +170,13 @@ function createDocCard(hit) {
     link.setAttribute("target", "_blank");
 
     //Title
-    let title = document.createElement("p");
-    title.setAttribute("class", "file-title");
-    let extension = hit["_source"].hasOwnProperty("extension") && hit["_source"]["extension"] !== "" ? "." + hit["_source"]["extension"] : "";
-
-    applyNameToTitle(hit, title, extension);
-
-    title.setAttribute("title", hit["_source"]["path"] + "/" + hit["_source"]["name"] + extension);
-    docCard.appendChild(title);
+    let title = makeTitle(hit);
 
     let tagContainer = document.createElement("div");
     tagContainer.setAttribute("class", "card-text");
 
     if (hit["_source"].hasOwnProperty("mime") && hit["_source"]["mime"] !== null) {
 
-        let tags = [];
-        let thumbnail = null;
         let thumbnailOverlay = null;
         let imgWrapper = document.createElement("div");
         imgWrapper.setAttribute("style", "position: relative");
@@ -115,31 +184,7 @@ function createDocCard(hit) {
         let mimeCategory = hit["_source"]["mime"].split("/")[0];
 
         //Thumbnail
-        if (mimeCategory === "video" && shouldPlayVideo(hit)) {
-            thumbnail = document.createElement("video");
-            addVidSrc("f/" + hit["_id"], hit["_source"]["mime"], thumbnail);
-
-            thumbnail.setAttribute("class", "fit");
-            thumbnail.setAttribute("loop", "");
-            thumbnail.setAttribute("controls", "");
-            thumbnail.setAttribute("preload", "none");
-            thumbnail.setAttribute("poster", `t/${hit["_source"]["index"]}/${hit["_id"]}`);
-            thumbnail.addEventListener("dblclick", function () {
-                thumbnail.webkitRequestFullScreen();
-            });
-        } else if ((hit["_source"].hasOwnProperty("width") && hit["_source"]["width"] > 20 && hit["_source"]["height"] > 20)
-            || hit["_source"]["mime"] === "application/pdf"
-            || hit["_source"]["mime"] === "application/epub+zip"
-            || hit["_source"]["mime"] === "application/x-cbz"
-            || hit["_source"].hasOwnProperty("font_name")
-        ) {
-            thumbnail = document.createElement("img");
-            thumbnail.setAttribute("class", "card-img-top fit");
-            thumbnail.setAttribute("src", `t/${hit["_source"]["index"]}/${hit["_id"]}`);
-            thumbnail.addEventListener("error", () => {
-                imgWrapper.remove();
-            });
-        }
+        let thumbnail = makeThumbnail(mimeCategory, hit, imgWrapper, false);
 
         //Thumbnail overlay
         switch (mimeCategory) {
@@ -167,46 +212,29 @@ function createDocCard(hit) {
                 if (hit["_source"].hasOwnProperty("duration")) {
                     thumbnailOverlay = document.createElement("div");
                     thumbnailOverlay.setAttribute("class", "card-img-overlay");
-                    let durationBadge = document.createElement("span");
+                    const durationBadge = document.createElement("span");
                     durationBadge.setAttribute("class", "badge badge-resolution");
                     durationBadge.appendChild(document.createTextNode(humanTime(hit["_source"]["duration"])));
                     thumbnailOverlay.appendChild(durationBadge);
                 }
         }
 
-        //Tags
-        switch (mimeCategory) {
-            case "video":
-            case "image":
-                if (hit["_source"].hasOwnProperty("videoc")) {
-                    let formatTag = document.createElement("span");
-                    formatTag.setAttribute("class", "badge badge-pill badge-video");
-                    formatTag.appendChild(document.createTextNode(hit["_source"]["videoc"].replace(" ", "")));
-                    tags.push(formatTag);
-                }
-                break;
-            case "audio": {
-                if (hit["_source"].hasOwnProperty("audioc")) {
-                    let formatTag = document.createElement("span");
-                    formatTag.setAttribute("class", "badge badge-pill badge-audio");
-                    formatTag.appendChild(document.createTextNode(hit["_source"]["audioc"]));
-                    tags.push(formatTag);
-                }
-            }
-                break;
+        // Tags
+        let tags = getTags(hit, mimeCategory);
+        for (let i = 0; i < tags.length; i++) {
+            tagContainer.appendChild(tags[i]);
         }
 
         //Content
         let contentHl = getContentHighlight(hit);
         if (contentHl !== undefined) {
-            let contentDiv = document.createElement("div");
+            const contentDiv = document.createElement("div");
             contentDiv.setAttribute("class", "content-div");
             contentDiv.insertAdjacentHTML('afterbegin', contentHl);
             docCard.appendChild(contentDiv);
         }
 
         if (thumbnail !== null) {
-            imgWrapper.appendChild(thumbnail);
             docCard.appendChild(imgWrapper);
         }
 
@@ -226,10 +254,6 @@ function createDocCard(hit) {
         if (thumbnailOverlay !== null) {
             imgWrapper.appendChild(thumbnailOverlay);
         }
-
-        for (let i = 0; i < tags.length; i++) {
-            tagContainer.appendChild(tags[i]);
-        }
     }
 
     //Size tag
@@ -247,6 +271,139 @@ function createDocCard(hit) {
     return docCard;
 }
 
+function makeThumbnail(mimeCategory, hit, imgWrapper, small) {
+    let thumbnail;
+
+    if (mimeCategory === "video" && shouldPlayVideo(hit)) {
+        thumbnail = document.createElement("video");
+        addVidSrc("f/" + hit["_id"], hit["_source"]["mime"], thumbnail);
+
+        const placeholder = makePlaceholder(hit["_source"]["width"], hit["_source"]["height"], small);
+        imgWrapper.appendChild(placeholder);
+
+        if (small) {
+            thumbnail.setAttribute("class", "fit-sm");
+        } else {
+            thumbnail.setAttribute("class", "fit");
+        }
+        if (small) {
+            thumbnail.style.cursor = "pointer";
+            thumbnail.title = "Enlarge";
+            thumbnail.addEventListener("click", function () {
+                imgWrapper.classList.remove("wrapper-sm", "mr-1");
+                imgWrapper.parentElement.classList.add("media-expanded");
+                thumbnail.setAttribute("class", "fit");
+                thumbnail.setAttribute("controls", "");
+            });
+        } else {
+            thumbnail.setAttribute("controls", "");
+        }
+        thumbnail.setAttribute("preload", "none");
+        thumbnail.setAttribute("poster", `t/${hit["_source"]["index"]}/${hit["_id"]}`);
+        thumbnail.addEventListener("dblclick", function () {
+            thumbnail.setAttribute("controls", "");
+            if (thumbnail.webkitRequestFullScreen) {
+                thumbnail.webkitRequestFullScreen();
+            } else {
+                thumbnail.requestFullscreen();
+            }
+        });
+        const poster = new Image();
+        poster.src = thumbnail.getAttribute('poster');
+        poster.addEventListener("load", function () {
+            placeholder.remove();
+            imgWrapper.appendChild(thumbnail);
+        });
+    } else if ((hit["_source"].hasOwnProperty("width") && hit["_source"]["width"] > 32 && hit["_source"]["height"] > 32)
+        || hit["_source"]["mime"] === "application/pdf"
+        || hit["_source"]["mime"] === "application/epub+zip"
+        || hit["_source"]["mime"] === "application/x-cbz"
+        || hit["_source"].hasOwnProperty("font_name")
+    ) {
+        thumbnail = document.createElement("img");
+        if (small) {
+            thumbnail.setAttribute("class", "fit-sm");
+        } else {
+            thumbnail.setAttribute("class", "card-img-top fit");
+        }
+        thumbnail.setAttribute("src", `t/${hit["_source"]["index"]}/${hit["_id"]}`);
+
+        const placeholder = makePlaceholder(hit["_source"]["width"], hit["_source"]["height"], small);
+        imgWrapper.appendChild(placeholder);
+
+        thumbnail.addEventListener("error", () => {
+            imgWrapper.remove();
+        });
+        thumbnail.addEventListener("load", () => {
+            placeholder.remove();
+            imgWrapper.appendChild(thumbnail);
+        });
+    }
+
+    return thumbnail;
+}
+
+function createDocLine(hit) {
+
+    let mimeCategory = hit["_source"]["mime"].split("/")[0];
+    let tags = getTags(hit, mimeCategory);
+
+    let imgWrapper = document.createElement("div");
+    imgWrapper.setAttribute("class", "align-self-start mr-1 wrapper-sm");
+
+    let media = document.createElement("div");
+    media.setAttribute("class", "media");
+
+    const line = document.createElement("div");
+    line.setAttribute("class", "list-group-item flex-column align-items-start");
+
+
+    const title = makeTitle(hit);
+
+    let link = document.createElement("a");
+    link.setAttribute("href", "f/" + hit["_id"]);
+    link.setAttribute("target", "_blank");
+    link.appendChild(title);
+
+    const titleDiv = document.createElement("div");
+    titleDiv.setAttribute("class", "file-title");
+    titleDiv.appendChild(link);
+
+    line.appendChild(media);
+
+    let thumbnail = makeThumbnail(mimeCategory, hit, imgWrapper, true);
+    if (thumbnail) {
+        media.appendChild(imgWrapper);
+    }
+    media.appendChild(titleDiv);
+
+    // Content
+    let contentHl = getContentHighlight(hit);
+    if (contentHl !== undefined) {
+        const contentDiv = document.createElement("div");
+        contentDiv.setAttribute("class", "content-div");
+        contentDiv.insertAdjacentHTML('afterbegin', contentHl);
+        titleDiv.appendChild(contentDiv);
+    }
+
+    let tagContainer = document.createElement("div");
+    tagContainer.setAttribute("class", "");
+
+    for (let i = 0; i < tags.length; i++) {
+        tagContainer.appendChild(tags[i]);
+    }
+
+    //Size tag
+    let sizeTag = document.createElement("small");
+    sizeTag.appendChild(document.createTextNode(humanFileSize(hit["_source"]["size"])));
+    sizeTag.setAttribute("class", "text-muted");
+    tagContainer.appendChild(sizeTag);
+
+    titleDiv.appendChild(tagContainer);
+
+    return line;
+}
+
 function makePreloader() {
     const elem = document.createElement("div");
     elem.setAttribute("class", "progress");
@@ -271,18 +428,53 @@ function makePageIndicator(searchResult) {
 function makeStatsCard(searchResult) {
 
     let statsCard = document.createElement("div");
-    statsCard.setAttribute("class", "card");
+    statsCard.setAttribute("class", "card stat");
     let statsCardBody = document.createElement("div");
     statsCardBody.setAttribute("class", "card-body");
 
-    let stat = document.createElement("p");
+    const resultMode = document.createElement("div");
+    resultMode.setAttribute("class", "btn-group btn-group-toggle");
+    resultMode.setAttribute("data-toggle", "buttons");
+    resultMode.style.cssFloat = "right";
+
+    const listMode = document.createElement("label");
+    listMode.setAttribute("class", "btn btn-primary");
+    listMode.appendChild(document.createTextNode("List"));
+
+    const gridMode = document.createElement("label");
+    gridMode.setAttribute("class", "btn btn-primary");
+    gridMode.appendChild(document.createTextNode("Grid"));
+
+    resultMode.appendChild(gridMode);
+    resultMode.appendChild(listMode);
+
+    if (mode === "grid") {
+        gridMode.classList.add("active")
+    } else {
+        listMode.classList.add("active")
+    }
+
+    gridMode.addEventListener("click", () => {
+        mode = "grid";
+        localStorage.setItem("mode", mode);
+        searchDebounced();
+    });
+    listMode.addEventListener("click", () => {
+        mode = "list";
+        localStorage.setItem("mode", mode);
+        searchDebounced();
+    });
+
+    let stat = document.createElement("span");
     const totalHits = searchResult["hits"]["total"].hasOwnProperty("value")
         ? searchResult["hits"]["total"]["value"] : searchResult["hits"]["total"];
     stat.appendChild(document.createTextNode(totalHits + " results in " + searchResult["took"] + "ms"));
+
     statsCardBody.appendChild(stat);
+    statsCardBody.appendChild(resultMode);
 
     if (totalHits !== 0) {
-        let sizeStat = document.createElement("span");
+        let sizeStat = document.createElement("div");
         sizeStat.appendChild(document.createTextNode(humanFileSize(searchResult["aggregations"]["total_size"]["value"])));
         statsCardBody.appendChild(sizeStat);
     }
@@ -294,7 +486,11 @@ function makeStatsCard(searchResult) {
 
 function makeResultContainer() {
     let resultContainer = document.createElement("div");
-    resultContainer.setAttribute("class", "card-columns");
 
+    if (mode === "grid") {
+        resultContainer.setAttribute("class", "card-columns");
+    } else {
+        resultContainer.setAttribute("class", "list-group");
+    }
     return resultContainer;
 }

web/js/search.js

@@ -1,6 +1,8 @@
 const SIZE = 40;
 let mimeMap = [];
-let tree;
+let tagMap = [];
+let mimeTree;
+let tagTree;
 
 let searchBar = document.getElementById("searchBar");
 let pathBar = document.getElementById("pathBar");
@@ -10,6 +12,13 @@ let coolingDown = false;
 let searchBusy = true;
 let selectedIndices = [];
 
+let mode;
+if (localStorage.getItem("mode") === null) {
+    mode = "grid";
+} else {
+    mode = localStorage.getItem("mode")
+}
+
 jQuery["jsonPost"] = function (url, data) {
     return jQuery.ajax({
         url: url,
@@ -49,6 +58,23 @@ $.jsonPost("i").then(resp => {
     });
 });
 
+function handleTreeClick (tree) {
+    return (event, node, handler) => {
+        event.preventTreeDefault();
+
+        if (node.id === "any") {
+            if (!node.itree.state.checked) {
+                tree.deselect();
+            }
+        } else {
+            tree.node("any").deselect();
+        }
+
+        handler();
+        searchDebounced();
+    }
+}
+
 $.jsonPost("es", {
     aggs: {
         mimeTypes: {
@@ -85,34 +111,86 @@ $.jsonPost("es", {
     });
     mimeMap.push({"text": "All", "id": "any"});
 
-    tree = new InspireTree({
+    mimeTree = new InspireTree({
         selection: {
             mode: 'checkbox'
         },
         data: mimeMap
     });
-    new InspireTreeDOM(tree, {
-        target: '.tree'
+    new InspireTreeDOM(mimeTree, {
+        target: '#mimeTree'
     });
-    tree.on("node.click", function (event, node, handler) {
-        event.preventTreeDefault();
+    mimeTree.on("node.click", handleTreeClick(mimeTree));
+    mimeTree.select();
+    mimeTree.node("any").deselect();
+});
 
-        if (node.id === "any") {
-            if (!node.itree.state.checked) {
-                tree.deselect();
+function leafTag(tag) {
+    const tokens = tag.split(".");
+    return tokens[tokens.length-1]
+}
+
+// Tags tree
+$.jsonPost("es", {
+    aggs: {
+        tags: {
+            terms: {
+                field: "tag",
+                size: 10000
             }
-        } else {
-            tree.node("any").deselect();
         }
-
-        handler();
-        searchDebounced();
+    },
+    size: 0,
+}).then(resp => {
+    resp["aggregations"]["tags"]["buckets"]
+        .sort((a, b) => a["key"].localeCompare(b["key"]))
+        .forEach(bucket => {
+        addTag(tagMap, bucket["key"], bucket["key"], bucket["doc_count"])
     });
-    tree.select();
-    tree.node("any").deselect();
+
+    tagMap.push({"text": "All", "id": "any"});
+    tagTree = new InspireTree({
+        selection: {
+            mode: 'checkbox'
+        },
+        data: tagMap
+    });
+    new InspireTreeDOM(tagTree, {
+        target: '#tagTree'
+    });
+    tagTree.on("node.click", handleTreeClick(tagTree));
+    tagTree.node("any").select();
     searchBusy = false;
 });
 
+function addTag(map, tag, id, count) {
+    let tags = tag.split("#")[0].split(".");
+
+    let child = {
+        id: id,
+        text: tags.length !== 1 ? tags[0] : `${tags[0]} (${count})`,
+        children: []
+    };
+
+    let found = false;
+    map.forEach(node => {
+        if (node.text === child.text) {
+            found = true;
+            if (tags.length !== 1) {
+                addTag(node.children, tags.slice(1).join("."), id, count);
+            }
+        }
+    });
+    if (!found) {
+        if (tags.length !== 1) {
+            addTag(child.children, tags.slice(1).join("."), id, count);
+            map.push(child);
+        } else {
+            map.push(child);
+        }
+    }
+}
+
 new autoComplete({
     selector: '#pathBar',
     minChars: 1,
@@ -140,7 +218,12 @@ new autoComplete({
 
 function insertHits(resultContainer, hits) {
     for (let i = 0; i < hits.length; i++) {
-        resultContainer.appendChild(createDocCard(hits[i]));
+
+        if (mode === "grid") {
+            resultContainer.appendChild(createDocCard(hits[i]));
+        } else {
+            resultContainer.appendChild(createDocLine(hits[i]));
+        }
         docCount++;
     }
 }
@@ -181,8 +264,8 @@ function doScroll() {
         })
 }
 
-function getSelectedMimeTypes() {
-    let mimeTypes = [];
+function getSelectedNodes(tree) {
+    let selectedNodes = [];
 
     let selected = tree.selected();
 
@@ -194,11 +277,11 @@ function getSelectedMimeTypes() {
 
         //Only get children
         if (selected[i].text.indexOf("(") !== -1) {
-            mimeTypes.push(selected[i].id);
+            selectedNodes.push(selected[i].id);
         }
     }
 
-    return mimeTypes
+    return selectedNodes
 }
 
 function search() {
@@ -239,11 +322,16 @@ function search() {
     if (path !== "") {
         filters.push([{term: {path: path}}])
     }
-    let mimeTypes = getSelectedMimeTypes();
+    let mimeTypes = getSelectedNodes(mimeTree);
     if (!mimeTypes.includes("any")) {
         filters.push([{terms: {"mime": mimeTypes}}]);
     }
 
+    let tags = getSelectedNodes(tagTree);
+    if (!tags.includes("any")) {
+        filters.push([{terms: {"tag": tags}}]);
+    }
+
     $.jsonPost("es?scroll=1", {
         "_source": {
             excludes: ["content"]

web/js/util.js

@@ -43,9 +43,9 @@ function humanTime(sec_num) {
 
 function debounce(func, wait) {
     let timeout;
-    return function() {
+    return function () {
         let context = this, args = arguments;
-        let later = function() {
+        let later = function () {
             timeout = null;
             func.apply(context, args);
         };
@@ -54,3 +54,13 @@ function debounce(func, wait) {
         func.apply(context, args);
     };
 }
+
+function lum(c) {
+    c = c.substring(1);
+    let rgb = parseInt(c, 16);
+    let r = (rgb >> 16) & 0xff;
+    let g = (rgb >> 8) & 0xff;
+    let b = (rgb >> 0) & 0xff;
+
+    return 0.2126 * r + 0.7152 * g + 0.0722 * b;
+}

web/search.html

@@ -11,6 +11,7 @@
 
 <nav class="navbar navbar-expand-lg">
     <a class="navbar-brand" href="/">sist2</a>
+    <span class="badge badge-pill version">v1.1.7</span>
     <span class="tagline">Lightning-fast file system indexer and search tool </span>
     <a style="margin-left: auto" id="theme" class="btn" title="Toggle theme" href="/">Theme</a>
 </nav>
@@ -24,7 +25,7 @@
             <div class="input-group">
                 <div class="input-group-prepend">
                     <div class="input-group-text">
-                        <span onclick="document.getElementById('fuzzyToggle').click()">Fuzzy&nbsp</span>
+                        <span title="Toggle fuzzy searching"  onclick="document.getElementById('fuzzyToggle').click()">Fuzzy&nbsp</span>
                         <input title="Toggle fuzzy searching" type="checkbox" id="fuzzyToggle"
                                onclick="toggleFuzzy()" checked>
                     </div>
@@ -41,11 +42,25 @@
                     <select class="custom-select" id="indices" multiple size="6"></select>
                 </div>
 
-                <div class="col">
-                    <label>Mime types</label>
-
-                    <div class="tree"></div>
+                <div class="col" id="treeTabs">
+                    <ul class="nav nav-tabs" role="tablist">
+                        <li class="nav-item">
+                            <a class="nav-link active" data-toggle="tab" href="#mime" role="tab" aria-controls="home" aria-selected="true">Mime Types</a>
+                        </li>
+                        <li class="nav-item">
+                            <a class="nav-link" data-toggle="tab" href="#tag" role="tab" aria-controls="profile" aria-selected="false" title="User-defined tags">Tags</a>
+                        </li>
+                    </ul>
+                    <div class="tab-content" id="myTabContent">
+                        <div class="tab-pane fade show active" id="mime" role="tabpanel" aria-labelledby="home-tab">
+                            <div id="mimeTree" class="tree"></div>
+                        </div>
+                        <div class="tab-pane fade" id="tag" role="tabpanel" aria-labelledby="profile-tab">
+                            <div id="tagTree" class="tree"></div>
+                        </div>
+                    </div>
                 </div>
+
             </div>
         </div>
     </div>