Build fix

Correct typos in example

.github/ISSUE_TEMPLATE/issue-template.md

@@ -9,7 +9,9 @@ assignees: ''
 
 sist2 version:
 
-Platform (please indicate if you're using Docker):
+Platform (Linux or Docker):
+
+Elasticsearch version:
 
 Command with arguments:  `ex: "scan ~/Documents -o ./i2 --threads 3 -q 1.0`
 

CMakeLists.txt

@@ -30,7 +30,7 @@ add_executable(
         third-party/argparse/argparse.h third-party/argparse/argparse.c
 
         src/cli.c src/cli.h
-        src/stats.c src/stats.h)
+        src/stats.c src/stats.h src/ctx.c)
 
 target_link_directories(sist2 PRIVATE BEFORE ${_VCPKG_INSTALLED_DIR}/${VCPKG_TARGET_TRIPLET}/lib/)
 set(CMAKE_FIND_LIBRARY_SUFFIXES .a .lib)

README.md

@@ -18,7 +18,7 @@ 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)
+* Automatic tagging from file attributes via [user scripts](docs/scripting.md)
 * Recursive scan inside archive files \*\*
 * OCR support with tesseract \*\*\*
 * Stats page & disk utilisation visualization
@@ -53,7 +53,7 @@ sist2 (Simple incremental search tool)
     1. *(or)* Download a [development snapshot](https://files.simon987.net/artifacts/Sist2/Build/) *(Not recommended!)*
     1. *(or)* `docker pull simon987/sist2:latest`
 
-1. See [Usage guide](DOCS/USAGE.md)
+1. See [Usage guide](docs/USAGE.md)
    
 
 \* *Windows users*: **sist2** runs under [WSL](https://en.wikipedia.org/wiki/Windows_Subsystem_for_Linux)    
@@ -61,7 +61,7 @@ sist2 (Simple incremental search tool)
 
 ## Example usage
 
-See [Usage guide](DOCS/USAGE.md) for more details
+See [Usage guide](docs/USAGE.md) for more details
 
 1. Scan a directory: `sist2 scan ~/Documents -o ./docs_idx`
 1. Push index to Elasticsearch: `sist2 index ./docs_idx`
@@ -91,14 +91,12 @@ they were directly in the file system. Recursive (archives inside archives)
 scan is also supported.
 
 **Limitations**:
-* Parsing media files with formats that require
-*seek* (e.g. `.gif`, `.mp4` w/ fragmented metadata etc.) is not supported.
+* Support for parsing media files with formats that require *seek* (e.g. `.gif`, `.mp4` w/ fragmented metadata etc.) 
+  is limitted (see `--mem-buffer` option)
 * Archive files are scanned sequentially, by a single thread. On systems where
 **sist2** is not I/O bound, scans might be faster when larger archives are split
  into smaller parts.
  
-To check if a media file can be parsed without *seek*, execute `cat file.mp4 | ffprobe -`
- 
  
 ### OCR
 
@@ -130,6 +128,6 @@ binaries (GCC 7+ required).
 2. Build
     ```bash
     git clone --recursive https://github.com/simon987/sist2/
-    cmake -D <VCPKG_ROOT>/scripts/buildsystems/vcpkg.cmake .
+    cmake -DCMAKE_TOOLCHAIN_FILE=<VCPKG_ROOT>/scripts/buildsystems/vcpkg.cmake .
     make
     ```

docs/USAGE.md

@@ -14,11 +14,13 @@
     * [examples](#web-examples)
     * [rewrite_url](#rewrite_url)
     * [link to specific indices](#link-to-specific-indices)
+* [exec-script](#exec-script)
 
 ```
 Usage: sist2 scan [OPTION]... PATH
    or: sist2 index [OPTION]... INDEX
    or: sist2 web [OPTION]... INDEX...
+   or: sist2 exec-script [OPTION]... INDEX
 Lightning-fast file system indexer and search tool.
 
     -h, --help                    show this help message and exit
@@ -40,6 +42,8 @@ Scan options
     --ocr=<str>                   Tesseract language (use tesseract --list-langs to see which are installed on your machine)
     -e, --exclude=<str>           Files that match this regex will not be scanned
     --fast                        Only index file names & mime type
+    --treemap-threshold=<str>     Relative size threshold for treemap (see USAGE.md). DEFAULT: 0.0005
+    --mem-buffer=<int>            Maximum memory buffer size per thread in MB for files inside archives (see USAGE.md). DEFAULT: 2000
 
 Index options
     --es-url=<str>                Elasticsearch url with port. DEFAULT=http://localhost:9200
@@ -48,13 +52,14 @@ Index options
     --batch-size=<int>            Index batch size. DEFAULT: 100
     -f, --force-reset             Reset Elasticsearch mappings and settings. (You must use this option the first time you use the index command)
 
-
 Web options
     --es-url=<str>                Elasticsearch url. DEFAULT=http://localhost:9200
     --bind=<str>                  Listen on this address. DEFAULT=localhost:4090
     --auth=<str>                  Basic auth in user:password format
-Made by simon987 <me@simon987.net>. Released under GPL-3.0
 
+Exec-script options
+    --script-file=<str>           Path to user script.
+Made by simon987 <me@simon987.net>. Released under GPL-3.0
 ```
 
 ## Scan
@@ -102,6 +107,11 @@ Made by simon987 <me@simon987.net>. Released under GPL-3.0
     In effect, smaller `treemap-threshold` values will yield a more detailed 
     (but also a more cluttered and harder to read) visualization. 
     
+* `--mem-buffer` Maximum memory buffer size in MB (per thread) for files inside archives. Media files 
+    larger than this number will be read sequentially and no *seek* operations will be supported.
+
+    To check if a media file can be parsed without *seek*, execute `cat file.mp4 | ffprobe -`
+
 ### Scan examples
 
 Simple scan
@@ -226,7 +236,7 @@ it is currently unsupported and has no guaranties of back/forward compatibility.
  * `-p, --print` 
     Print index in JSON format to stdout.
  * `--script-file` 
-    Path to user script. See [Scripting](scripting/README.md).
+    Path to user script. See [Scripting](scripting.md).
  * `--batch-size=<int>` 
     Index batch size. Indexing is generally faster with larger batches, but payloads that
     are too large will fail and additional overhead for retrying with smaller sizes may slow
@@ -286,3 +296,7 @@ Both the `root` and `rewrite_url` fields are safe to manually modify from the
 To link to specific indices, you can add a list of comma-separated index name to 
 the URL: `?i=<name>,<name>`. By default, indices with `"(nsfw)"` in their name are
 not displayed.
+
+## exec-script
+
+The `exec-script` command is used to execute a user script for an index that has already been imported to Elasticsearch with the `index` command. Note that the documents will not be reset to their default state before each execution as the `index` command does: if you make undesired changes to the documents by accident, you will need to run `index` again to revert to the original state.

docs/scripting.md

@@ -39,7 +39,7 @@ it adds the `genre.<genre>` tag.
 ArrayList tags = ctx._source.tag = new ArrayList();
 
 if (ctx._source?.genre != null) {
-    tags.add("genre." + ctx._source.genre.toLowerCase())
+    tags.add("genre." + ctx._source.genre.toLowerCase());
 }
 ```
 
@@ -67,7 +67,7 @@ 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))
+    tags.add("year." + m.group(1));
 }
 ```
 
@@ -111,16 +111,6 @@ if (ctx._source.path != "") {
 }
 ```
 
-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]);
-}
-```
-
 Parse `EXIF:F Number` tag
 ```Java
 if (ctx._source?.exif_fnumber != null) {

schema/mappings.json

@@ -10,6 +10,7 @@
     "path": {
       "type": "text",
       "analyzer": "path_analyzer",
+      "copy_to": "suggest-path",
       "fielddata": true,
       "fields": {
         "nGram": {
@@ -22,6 +23,10 @@
         }
       }
     },
+    "suggest-path": {
+      "type": "completion",
+      "analyzer": "case_insensitive_kw_analyzer"
+    },
     "mime": {
       "type": "keyword"
     },

scripts/mime.csv

@@ -13,7 +13,7 @@ application/epub+zip, epub
 application/freeloader, frl
 application/futuresplash, spl
 application/groupwise, vew
-application/gzip, gz
+application/gzip, gz|tgz
 application/hta, hta
 application/i-deas, unv
 application/iges, iges|igs
@@ -111,7 +111,7 @@ application/x-dbf, dbf
 application/x-dbt,
 application/x-debian-package, deb
 application/x-deepv, deepv
-application/x-director, dcr|dir|dxr
+application/x-director, dir|dxr
 application/x-dmp, dmp
 application/x-dosdriver,
 application/x-dosexec, dll
@@ -429,4 +429,22 @@ video/x-qtc, qtc
 video/x-sgi-movie, movie|mv
 x-epoc/x-sisx-app,
 application/x-zstd-dictionary,
-application/vnd.ms-outlook,
+application/vnd.ms-outlook, msg
+image/x-olympus-orf, orf
+image/x-nikon-nef, nef
+image/x-fuji-raf, raf
+image/x-panasonic-raw, rw2|raw
+image/x-adobe-dng, dng
+image/x-canon-cr2, cr2
+image/x-canon-crw, crw
+image/x-dcraw,
+image/x-kodak-dcr, dcr
+image/x-kodak-k25, k25
+image/x-kodak-kdc, kdc
+image/x-minolta-mrw, mrw
+image/x-pentax-pef, pef
+image/x-sigma-x3f, xf3
+image/x-sony-arw, arw
+image/x-sony-sr2, sr2
+image/x-sony-srf, srf
+image/x-epson-erf, erf

scripts/mime.py

@@ -73,6 +73,29 @@ markup = (
     "text/x-sgml"
 )
 
+raw = (
+    "image/x-olympus-orf",
+    "image/x-nikon-nef",
+    "image/x-fuji-raf",
+    "image/x-panasonic-raw",
+    "image/x-adobe-dng",
+    "image/x-canon-cr2",
+    "image/x-canon-crw",
+    "image/x-dcraw",
+    "image/x-kodak-dcr",
+    "image/x-kodak-k25",
+    "image/x-kodak-kdc",
+    "image/x-minolta-mrw",
+    "image/x-pentax-pef",
+    "image/x-sigma-x3f",
+    "image/x-sony-arw",
+    "image/x-sony-sr2",
+    "image/x-sony-srf",
+    "image/x-minolta-mrw",
+    "image/x-pentax-pef",
+    "image/x-epson-erf",
+)
+
 cnt = 1
 
 
@@ -97,6 +120,8 @@ def mime_id(mime):
         mime_id += " | 0x02000000"
     elif mime in markup:
         mime_id += " | 0x01000000"
+    elif mime in raw:
+        mime_id += " | 0x00800000"
     elif mime == "application/x-empty":
         return "1"
     return mime_id

src/cli.c

@@ -14,7 +14,9 @@
 #define DEFAULT_LISTEN_ADDRESS "localhost:4090"
 #define DEFAULT_TREEMAP_THRESHOLD 0.0005
 
-const char* TESS_DATAPATHS[] = {
+#define DEFAULT_MAX_MEM_BUFFER 2000
+
+const char *TESS_DATAPATHS[] = {
         "/usr/share/tessdata/",
         "/usr/share/tesseract-ocr/tessdata/",
         "./",
@@ -30,6 +32,11 @@ scan_args_t *scan_args_create() {
     return args;
 }
 
+exec_args_t *exec_args_create() {
+    exec_args_t *args = calloc(sizeof(exec_args_t), 1);
+    return args;
+}
+
 void scan_args_destroy(scan_args_t *args) {
     if (args->name != NULL) {
         free(args->name);
@@ -53,6 +60,10 @@ void web_args_destroy(web_args_t *args) {
     free(args);
 }
 
+void exec_args_destroy(exec_args_t *args) {
+    free(args);
+}
+
 int scan_args_validate(scan_args_t *args, int argc, const char **argv) {
     if (argc < 2) {
         fprintf(stderr, "Required positional argument: PATH.\n");
@@ -113,7 +124,7 @@ int scan_args_validate(scan_args_t *args, int argc, const char **argv) {
         return 1;
     }
 
-    if (args->depth < 0) {
+    if (args->depth <= 0) {
         args->depth = G_MAXINT32;
     } else {
         args->depth += 1;
@@ -145,7 +156,7 @@ int scan_args_validate(scan_args_t *args, int argc, const char **argv) {
 
         char filename[128];
         sprintf(filename, "%s.traineddata", args->tesseract_lang);
-        const char * path = find_file_in_paths(TESS_DATAPATHS, filename);
+        const char *path = find_file_in_paths(TESS_DATAPATHS, filename);
         if (path == NULL) {
             LOG_FATAL("cli.c", "Could not find tesseract language file!");
         }
@@ -187,6 +198,10 @@ int scan_args_validate(scan_args_t *args, int argc, const char **argv) {
         args->treemap_threshold = atof(args->treemap_threshold_str);
     }
 
+    if (args->max_memory_buffer == 0) {
+        args->max_memory_buffer = DEFAULT_MAX_MEM_BUFFER;
+    }
+
     LOG_DEBUGF("cli.c", "arg quality=%f", args->quality)
     LOG_DEBUGF("cli.c", "arg size=%d", args->size)
     LOG_DEBUGF("cli.c", "arg content_size=%d", args->content_size)
@@ -203,6 +218,35 @@ int scan_args_validate(scan_args_t *args, int argc, const char **argv) {
     LOG_DEBUGF("cli.c", "arg exclude=%s", args->exclude_regex)
     LOG_DEBUGF("cli.c", "arg fast=%d", args->fast)
     LOG_DEBUGF("cli.c", "arg treemap_threshold=%f", args->treemap_threshold)
+    LOG_DEBUGF("cli.c", "arg max_memory_buffer=%d", args->max_memory_buffer)
+
+    return 0;
+}
+
+int load_script(const char *script_path, char **dst) {
+    struct stat info;
+    int res = stat(script_path, &info);
+
+    if (res == -1) {
+        fprintf(stderr, "Error opening script file '%s': %s\n", script_path, strerror(errno));
+        return 1;
+    }
+
+    int fd = open(script_path, O_RDONLY);
+    if (fd == -1) {
+        fprintf(stderr, "Error opening script file '%s': %s\n", script_path, strerror(errno));
+        return 1;
+    }
+
+    *dst = malloc(info.st_size + 1);
+    res = read(fd, *dst, info.st_size);
+    if (res < 0) {
+        fprintf(stderr, "Error reading script file '%s': %s\n", script_path, strerror(errno));
+        return 1;
+    }
+
+    *(*dst + info.st_size) = '\0';
+    close(fd);
 
     return 0;
 }
@@ -230,29 +274,9 @@ int index_args_validate(index_args_t *args, int argc, const char **argv) {
     }
 
     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));
+        if (load_script(args->script_path, &args->script) != 0) {
             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 < 0) {
-            fprintf(stderr, "Error reading script file '%s': %s\n", args->script_path, strerror(errno));
-            return 1;
-        }
-
-        *(args->script + info.st_size) = '\0';
-        close(fd);
     }
 
     if (args->batch_size == 0) {
@@ -288,7 +312,7 @@ int web_args_validate(web_args_t *args, int argc, const char **argv) {
     }
 
     if (args->credentials != NULL) {
-        char * ptr = strstr(args->credentials, ":");
+        char *ptr = strstr(args->credentials, ":");
         if (ptr == NULL) {
             fprintf(stderr, "Invalid --auth format, see usage\n");
             return 1;
@@ -341,3 +365,30 @@ web_args_t *web_args_create() {
     return args;
 }
 
+int exec_args_validate(exec_args_t *args, int argc, const char **argv) {
+
+    char *index_path = abspath(argv[1]);
+    if (index_path == NULL) {
+        fprintf(stderr, "File not found: %s\n", argv[1]);
+        return 1;
+    } else {
+        args->index_path = argv[1];
+        free(index_path);
+    }
+
+    if (args->es_url == NULL) {
+        args->es_url = DEFAULT_ES_URL;
+    }
+
+    if (args->script_path == NULL) {
+        LOG_FATAL("cli.c", "--script-file argument is required");
+    }
+
+    if (load_script(args->script_path, &args->script) != 0) {
+        return 1;
+    }
+
+    LOG_DEBUGF("cli.c", "arg script_path=%s", args->script_path)
+    LOG_DEBUGF("cli.c", "arg script=%s", args->script)
+    return 0;
+}

src/cli.h

@@ -24,6 +24,7 @@ typedef struct scan_args {
     int fast;
     const char* treemap_threshold_str;
     double treemap_threshold;
+    int max_memory_buffer;
 } scan_args_t;
 
 scan_args_t *scan_args_create();
@@ -53,6 +54,13 @@ typedef struct web_args {
     const char **indices;
 } web_args_t;
 
+typedef struct exec_args {
+    char *es_url;
+    const char *index_path;
+    const char *script_path;
+    char *script;
+} exec_args_t;
+
 index_args_t *index_args_create();
 
 void index_args_destroy(index_args_t *args);
@@ -65,4 +73,10 @@ int index_args_validate(index_args_t *args, int argc, const char **argv);
 
 int web_args_validate(web_args_t *args, int argc, const char **argv);
 
+exec_args_t *exec_args_create();
+
+void exec_args_destroy(exec_args_t *args);
+
+int exec_args_validate(exec_args_t *args, int argc, const char **argv);
+
 #endif

src/ctx.c

@@ -0,0 +1,6 @@
+#include "ctx.h"
+
+ScanCtx_t ScanCtx;
+WebCtx_t WebCtx;
+IndexCtx_t IndexCtx;
+LogCtx_t LogCtx;

src/ctx.h

@@ -12,12 +12,12 @@
 #include "libscan/ooxml/ooxml.h"
 #include "libscan/text/text.h"
 #include "libscan/mobi/scan_mobi.h"
+#include "libscan/raw/raw.h"
 
 #include <glib.h>
 #include <pcre.h>
 
-//TODO Move to individual scan ctx
-struct {
+typedef struct {
     struct index_t index;
 
     GHashTable *mime_table;
@@ -46,27 +46,33 @@ struct {
     scan_ooxml_ctx_t ooxml_ctx;
     scan_text_ctx_t text_ctx;
     scan_mobi_ctx_t mobi_ctx;
-} ScanCtx;
+    scan_raw_ctx_t raw_ctx;
+} ScanCtx_t;
 
-struct {
+typedef struct {
     int verbose;
     int very_verbose;
     int no_color;
-} LogCtx;
+} LogCtx_t;
 
-struct {
+typedef struct {
     char *es_url;
     int batch_size;
-} IndexCtx;
+} IndexCtx_t;
 
-struct {
+typedef struct {
     char *es_url;
     int index_count;
     char *auth_user;
     char *auth_pass;
     int auth_enabled;
-    struct index_t indices[16];
-} WebCtx;
+    struct index_t indices[64];
+} WebCtx_t;
+
+extern ScanCtx_t ScanCtx;
+extern WebCtx_t WebCtx;
+extern IndexCtx_t IndexCtx;
+extern LogCtx_t LogCtx;
 
 
 #endif

src/index/elastic.c

@@ -53,6 +53,10 @@ void index_json(cJSON *document, const char uuid_str[UUID_STR_LEN]) {
 
 void execute_update_script(const char *script, const char index_id[UUID_STR_LEN]) {
 
+    if (Indexer == NULL) {
+        Indexer = create_indexer(IndexCtx.es_url);
+    }
+
     cJSON *body = cJSON_CreateObject();
     cJSON *script_obj = cJSON_AddObjectToObject(body, "script");
     cJSON_AddStringToObject(script_obj, "lang", "painless");
@@ -202,9 +206,8 @@ void delete_queue(int max) {
         Indexer->line_head = tmp->next;
         if (Indexer->line_head == NULL) {
             Indexer->line_tail = NULL;
-        } else {
-            free(tmp);
         }
+        free(tmp);
         Indexer->queued -= 1;
     }
 }
@@ -265,6 +268,7 @@ void destroy_indexer(char *script, char index_id[UUID_STR_LEN]) {
 
     if (script != NULL) {
         execute_update_script(script, index_id);
+        free(script);
     }
 
     snprintf(url, sizeof(url), "%s/sist2/_refresh", IndexCtx.es_url);

src/index/elastic.h

@@ -32,4 +32,6 @@ cJSON *elastic_get_document(const char *uuid_str);
 
 char *elastic_get_status();
 
+void execute_update_script(const char *script, const char index_id[UUID_STR_LEN]);
+
 #endif

src/main.c

@@ -2,7 +2,6 @@
 #include "ctx.h"
 
 #include <third-party/argparse/argparse.h>
-#include <glib.h>
 #include <locale.h>
 
 #include "cli.h"
@@ -22,11 +21,12 @@
 #define EPILOG "Made by simon987 <me@simon987.net>. Released under GPL-3.0"
 
 
-static const char *const Version = "2.3.0";
+static const char *const Version = "2.5.0";
 static const char *const usage[] = {
         "sist2 scan [OPTION]... PATH",
         "sist2 index [OPTION]... INDEX",
         "sist2 web [OPTION]... INDEX...",
+        "sist2 exec-script [OPTION]... INDEX",
         NULL,
 };
 
@@ -127,6 +127,7 @@ void initialize_scan_context(scan_args_t *args) {
     ScanCtx.media_ctx.log = _log;
     ScanCtx.media_ctx.logf = _logf;
     ScanCtx.media_ctx.store = _store;
+    ScanCtx.media_ctx.max_media_buffer = (long) args->max_memory_buffer * 1024 * 1024;
     init_media();
 
     // OOXML
@@ -153,6 +154,13 @@ void initialize_scan_context(scan_args_t *args) {
     strncpy(ScanCtx.index.desc.rewrite_url, args->rewrite_url, sizeof(ScanCtx.index.desc.rewrite_url));
     ScanCtx.index.desc.root_len = (short) strlen(ScanCtx.index.desc.root);
     ScanCtx.fast = args->fast;
+
+    // Raw
+    ScanCtx.raw_ctx.tn_qscale = args->quality;
+    ScanCtx.raw_ctx.tn_size = args->size;
+    ScanCtx.raw_ctx.log = _log;
+    ScanCtx.raw_ctx.logf = _logf;
+    ScanCtx.raw_ctx.store = _store;
 }
 
 
@@ -286,6 +294,22 @@ void sist2_index(index_args_t *args) {
     }
 }
 
+void sist2_exec_script(exec_args_t *args) {
+
+    LogCtx.verbose = TRUE;
+
+    char descriptor_path[PATH_MAX];
+    snprintf(descriptor_path, PATH_MAX, "%s/descriptor.json", args->index_path);
+    index_descriptor_t desc = read_index_descriptor(descriptor_path);
+
+    IndexCtx.es_url = args->es_url;
+
+    LOG_DEBUGF("main.c", "descriptor version %s (%s)", desc.version, desc.type)
+
+    execute_update_script(args->script, desc.uuid);
+    free(args->script);
+}
+
 void sist2_web(web_args_t *args) {
 
     WebCtx.es_url = args->es_url;
@@ -322,10 +346,12 @@ int main(int argc, const char *argv[]) {
     scan_args_t *scan_args = scan_args_create();
     index_args_t *index_args = index_args_create();
     web_args_t *web_args = web_args_create();
+    exec_args_t *exec_args = exec_args_create();
 
     int arg_version = 0;
 
     char *common_es_url = NULL;
+    char *common_script_path = NULL;
 
     struct argparse_option options[] = {
             OPT_HELP(),
@@ -358,11 +384,14 @@ int main(int argc, const char *argv[]) {
             OPT_BOOLEAN(0, "fast", &scan_args->fast, "Only index file names & mime type"),
             OPT_STRING(0, "treemap-threshold", &scan_args->treemap_threshold_str, "Relative size threshold for treemap "
                                                                                   "(see USAGE.md). DEFAULT: 0.0005"),
+            OPT_INTEGER(0, "mem-buffer", &scan_args->max_memory_buffer,
+                        "Maximum memory buffer size per thread in MB for files inside archives "
+                        "(see USAGE.md). DEFAULT: 2000"),
 
             OPT_GROUP("Index options"),
             OPT_STRING(0, "es-url", &common_es_url, "Elasticsearch url with port. 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_STRING(0, "script-file", &common_script_path, "Path to user script."),
             OPT_INTEGER(0, "batch-size", &index_args->batch_size, "Index batch size. DEFAULT: 100"),
             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)"),
@@ -372,6 +401,9 @@ int main(int argc, const char *argv[]) {
             OPT_STRING(0, "bind", &web_args->listen_address, "Listen on this address. DEFAULT=localhost:4090"),
             OPT_STRING(0, "auth", &web_args->credentials, "Basic auth in user:password format"),
 
+            OPT_GROUP("Exec-script options"),
+            OPT_STRING(0, "script-file", &common_script_path, "Path to user script."),
+
             OPT_END(),
     };
 
@@ -391,6 +423,8 @@ int main(int argc, const char *argv[]) {
 
     web_args->es_url = common_es_url;
     index_args->es_url = common_es_url;
+    index_args->script_path = common_script_path;
+    exec_args->script_path = common_script_path;
 
     if (argc == 0) {
         argparse_usage(&argparse);
@@ -419,6 +453,14 @@ int main(int argc, const char *argv[]) {
         }
         sist2_web(web_args);
 
+    }  else if (strcmp(argv[0], "exec-script") == 0) {
+
+        int err = exec_args_validate(exec_args, argc, argv);
+        if (err != 0) {
+            goto end;
+        }
+        sist2_exec_script(exec_args);
+
     } else {
         fprintf(stderr, "Invalid command: '%s'\n", argv[0]);
         argparse_usage(&argparse);
@@ -430,6 +472,7 @@ int main(int argc, const char *argv[]) {
     scan_args_destroy(scan_args);
     index_args_destroy(index_args);
     web_args_destroy(web_args);
+    exec_args_destroy(exec_args);
 
     return 0;
 }

src/parsing/mime.h

@@ -3,7 +3,7 @@
 
 #include "../sist.h"
 
-#define MAJOR_MIME(mime_id) (mime_id & 0x00FF0000) >> 16
+#define MAJOR_MIME(mime_id) (mime_id & 0x000F0000) >> 16
 
 #define MIME_EMPTY 1
 
@@ -31,6 +31,9 @@
 #define MARKUP_MASK 0x01000000
 #define IS_MARKUP(mime_id) (mime_id & MARKUP_MASK) == MARKUP_MASK
 
+#define RAW_MASK 0x00800000
+#define IS_RAW(mime_id) (mime_id & RAW_MASK) == RAW_MASK
+
 enum major_mime {
     MimeInvalid = 0,
     MimeModel = 1,

src/parsing/mime_generated.c

@@ -315,127 +315,145 @@ enum mime {
     image_webp=524595,
     image_wmf=524596,
     image_x_3ds=524597,
-    image_x_award_bioslogo=524598,
-    image_x_cmu_raster=524599,
-    image_x_cur=524600,
-    image_x_dwg=524601,
-    image_x_eps=524602,
-    image_x_exr=524603,
-    image_x_gem=524604,
-    image_x_icns=524605,
-    image_x_icon=524606 | 0x80000000,
-    image_x_jg=524607,
-    image_x_jps=524608,
-    image_x_ms_bmp=524609,
-    image_x_niff=524610,
-    image_x_pcx=524611,
-    image_x_pict=524612,
-    image_x_portable_bitmap=524613,
-    image_x_portable_graymap=524614,
-    image_x_portable_pixmap=524615,
-    image_x_quicktime=524616,
-    image_x_rgb=524617,
-    image_x_tga=524618,
-    image_x_tiff=524619,
-    image_x_win_bitmap=524620,
-    image_x_xcf=524621 | 0x80000000,
-    image_x_xpixmap=524622 | 0x80000000,
-    image_x_xwindowdump=524623,
-    message_news=196944,
-    message_rfc822=196945,
-    model_vnd_dwf=65874,
-    model_vnd_gdl=65875,
-    model_vnd_gs_gdl=65876,
-    model_vrml=65877,
-    model_x_pov=65878,
-    text_PGP=590167,
-    text_asp=590168,
-    text_css=590169,
-    text_html=590170 | 0x01000000,
-    text_javascript=590171,
-    text_mcf=590172,
-    text_pascal=590173,
-    text_plain=590174,
-    text_richtext=590175,
-    text_rtf=590176,
-    text_scriplet=590177,
-    text_tab_separated_values=590178,
-    text_troff=590179,
-    text_uri_list=590180,
-    text_vnd_abc=590181,
-    text_vnd_fmi_flexstor=590182,
-    text_vnd_wap_wml=590183,
-    text_vnd_wap_wmlscript=590184,
-    text_webviewhtml=590185,
-    text_x_Algol68=590186,
-    text_x_asm=590187,
-    text_x_audiosoft_intra=590188,
-    text_x_awk=590189,
-    text_x_bcpl=590190,
-    text_x_c=590191,
-    text_x_c__=590192,
-    text_x_component=590193,
-    text_x_diff=590194,
-    text_x_fortran=590195,
-    text_x_java=590196,
-    text_x_la_asf=590197,
-    text_x_lisp=590198,
-    text_x_m=590199,
-    text_x_m4=590200,
-    text_x_makefile=590201,
-    text_x_ms_regedit=590202,
-    text_x_msdos_batch=590203,
-    text_x_objective_c=590204,
-    text_x_pascal=590205,
-    text_x_perl=590206,
-    text_x_php=590207,
-    text_x_po=590208,
-    text_x_python=590209,
-    text_x_ruby=590210,
-    text_x_sass=590211,
-    text_x_scss=590212,
-    text_x_server_parsed_html=590213,
-    text_x_setext=590214,
-    text_x_sgml=590215 | 0x01000000,
-    text_x_shellscript=590216,
-    text_x_speech=590217,
-    text_x_tcl=590218,
-    text_x_tex=590219,
-    text_x_uil=590220,
-    text_x_uuencode=590221,
-    text_x_vcalendar=590222,
-    text_x_vcard=590223,
-    text_xml=590224 | 0x01000000,
-    video_MP2T=393617,
-    video_animaflex=393618,
-    video_avi=393619,
-    video_avs_video=393620,
-    video_mp4=393621,
-    video_mpeg=393622,
-    video_quicktime=393623,
-    video_vdo=393624,
-    video_vivo=393625,
-    video_vnd_rn_realvideo=393626,
-    video_vosaic=393627,
-    video_webm=393628,
-    video_x_amt_demorun=393629,
-    video_x_amt_showrun=393630,
-    video_x_atomic3d_feature=393631,
-    video_x_dl=393632,
-    video_x_dv=393633,
-    video_x_fli=393634,
-    video_x_flv=393635,
-    video_x_isvideo=393636,
-    video_x_jng=393637 | 0x80000000,
-    video_x_m4v=393638,
-    video_x_matroska=393639,
-    video_x_mng=393640,
-    video_x_motion_jpeg=393641,
-    video_x_ms_asf=393642,
-    video_x_msvideo=393643,
-    video_x_qtc=393644,
-    video_x_sgi_movie=393645,
-    x_epoc_x_sisx_app=721326,
+    image_x_adobe_dng=524598 | 0x00800000,
+    image_x_award_bioslogo=524599,
+    image_x_canon_cr2=524600 | 0x00800000,
+    image_x_canon_crw=524601 | 0x00800000,
+    image_x_cmu_raster=524602,
+    image_x_cur=524603,
+    image_x_dcraw=524604 | 0x00800000,
+    image_x_dwg=524605,
+    image_x_eps=524606,
+    image_x_epson_erf=524607 | 0x00800000,
+    image_x_exr=524608,
+    image_x_fuji_raf=524609 | 0x00800000,
+    image_x_gem=524610,
+    image_x_icns=524611,
+    image_x_icon=524612 | 0x80000000,
+    image_x_jg=524613,
+    image_x_jps=524614,
+    image_x_kodak_dcr=524615 | 0x00800000,
+    image_x_kodak_k25=524616 | 0x00800000,
+    image_x_kodak_kdc=524617 | 0x00800000,
+    image_x_minolta_mrw=524618 | 0x00800000,
+    image_x_ms_bmp=524619,
+    image_x_niff=524620,
+    image_x_nikon_nef=524621 | 0x00800000,
+    image_x_olympus_orf=524622 | 0x00800000,
+    image_x_panasonic_raw=524623 | 0x00800000,
+    image_x_pcx=524624,
+    image_x_pentax_pef=524625 | 0x00800000,
+    image_x_pict=524626,
+    image_x_portable_bitmap=524627,
+    image_x_portable_graymap=524628,
+    image_x_portable_pixmap=524629,
+    image_x_quicktime=524630,
+    image_x_rgb=524631,
+    image_x_sigma_x3f=524632 | 0x00800000,
+    image_x_sony_arw=524633 | 0x00800000,
+    image_x_sony_sr2=524634 | 0x00800000,
+    image_x_sony_srf=524635 | 0x00800000,
+    image_x_tga=524636,
+    image_x_tiff=524637,
+    image_x_win_bitmap=524638,
+    image_x_xcf=524639 | 0x80000000,
+    image_x_xpixmap=524640 | 0x80000000,
+    image_x_xwindowdump=524641,
+    message_news=196962,
+    message_rfc822=196963,
+    model_vnd_dwf=65892,
+    model_vnd_gdl=65893,
+    model_vnd_gs_gdl=65894,
+    model_vrml=65895,
+    model_x_pov=65896,
+    text_PGP=590185,
+    text_asp=590186,
+    text_css=590187,
+    text_html=590188 | 0x01000000,
+    text_javascript=590189,
+    text_mcf=590190,
+    text_pascal=590191,
+    text_plain=590192,
+    text_richtext=590193,
+    text_rtf=590194,
+    text_scriplet=590195,
+    text_tab_separated_values=590196,
+    text_troff=590197,
+    text_uri_list=590198,
+    text_vnd_abc=590199,
+    text_vnd_fmi_flexstor=590200,
+    text_vnd_wap_wml=590201,
+    text_vnd_wap_wmlscript=590202,
+    text_webviewhtml=590203,
+    text_x_Algol68=590204,
+    text_x_asm=590205,
+    text_x_audiosoft_intra=590206,
+    text_x_awk=590207,
+    text_x_bcpl=590208,
+    text_x_c=590209,
+    text_x_c__=590210,
+    text_x_component=590211,
+    text_x_diff=590212,
+    text_x_fortran=590213,
+    text_x_java=590214,
+    text_x_la_asf=590215,
+    text_x_lisp=590216,
+    text_x_m=590217,
+    text_x_m4=590218,
+    text_x_makefile=590219,
+    text_x_ms_regedit=590220,
+    text_x_msdos_batch=590221,
+    text_x_objective_c=590222,
+    text_x_pascal=590223,
+    text_x_perl=590224,
+    text_x_php=590225,
+    text_x_po=590226,
+    text_x_python=590227,
+    text_x_ruby=590228,
+    text_x_sass=590229,
+    text_x_scss=590230,
+    text_x_server_parsed_html=590231,
+    text_x_setext=590232,
+    text_x_sgml=590233 | 0x01000000,
+    text_x_shellscript=590234,
+    text_x_speech=590235,
+    text_x_tcl=590236,
+    text_x_tex=590237,
+    text_x_uil=590238,
+    text_x_uuencode=590239,
+    text_x_vcalendar=590240,
+    text_x_vcard=590241,
+    text_xml=590242 | 0x01000000,
+    video_MP2T=393635,
+    video_animaflex=393636,
+    video_avi=393637,
+    video_avs_video=393638,
+    video_mp4=393639,
+    video_mpeg=393640,
+    video_quicktime=393641,
+    video_vdo=393642,
+    video_vivo=393643,
+    video_vnd_rn_realvideo=393644,
+    video_vosaic=393645,
+    video_webm=393646,
+    video_x_amt_demorun=393647,
+    video_x_amt_showrun=393648,
+    video_x_atomic3d_feature=393649,
+    video_x_dl=393650,
+    video_x_dv=393651,
+    video_x_fli=393652,
+    video_x_flv=393653,
+    video_x_isvideo=393654,
+    video_x_jng=393655 | 0x80000000,
+    video_x_m4v=393656,
+    video_x_matroska=393657,
+    video_x_mng=393658,
+    video_x_motion_jpeg=393659,
+    video_x_ms_asf=393660,
+    video_x_msvideo=393661,
+    video_x_qtc=393662,
+    video_x_sgi_movie=393663,
+    x_epoc_x_sisx_app=721344,
 };
 char *mime_get_mime_text(unsigned int mime_id) {switch (mime_id) {
 case application_arj: return "application/arj";
@@ -868,6 +886,24 @@ case video_x_sgi_movie: return "video/x-sgi-movie";
 case x_epoc_x_sisx_app: return "x-epoc/x-sisx-app";
 case application_x_zstd_dictionary: return "application/x-zstd-dictionary";
 case application_vnd_ms_outlook: return "application/vnd.ms-outlook";
+case image_x_olympus_orf: return "image/x-olympus-orf";
+case image_x_nikon_nef: return "image/x-nikon-nef";
+case image_x_fuji_raf: return "image/x-fuji-raf";
+case image_x_panasonic_raw: return "image/x-panasonic-raw";
+case image_x_adobe_dng: return "image/x-adobe-dng";
+case image_x_canon_cr2: return "image/x-canon-cr2";
+case image_x_canon_crw: return "image/x-canon-crw";
+case image_x_dcraw: return "image/x-dcraw";
+case image_x_kodak_dcr: return "image/x-kodak-dcr";
+case image_x_kodak_k25: return "image/x-kodak-k25";
+case image_x_kodak_kdc: return "image/x-kodak-kdc";
+case image_x_minolta_mrw: return "image/x-minolta-mrw";
+case image_x_pentax_pef: return "image/x-pentax-pef";
+case image_x_sigma_x3f: return "image/x-sigma-x3f";
+case image_x_sony_arw: return "image/x-sony-arw";
+case image_x_sony_sr2: return "image/x-sony-sr2";
+case image_x_sony_srf: return "image/x-sony-srf";
+case image_x_epson_erf: return "image/x-epson-erf";
 default: return NULL;}}
 GHashTable *mime_get_ext_table() {GHashTable *ext_table = g_hash_table_new(g_str_hash, g_str_equal);
 g_hash_table_insert(ext_table, "arj", (gpointer)application_arj);
@@ -885,6 +921,7 @@ g_hash_table_insert(ext_table, "frl", (gpointer)application_freeloader);
 g_hash_table_insert(ext_table, "spl", (gpointer)application_futuresplash);
 g_hash_table_insert(ext_table, "vew", (gpointer)application_groupwise);
 g_hash_table_insert(ext_table, "gz", (gpointer)application_gzip);
+g_hash_table_insert(ext_table, "tgz", (gpointer)application_gzip);
 g_hash_table_insert(ext_table, "hta", (gpointer)application_hta);
 g_hash_table_insert(ext_table, "unv", (gpointer)application_i_deas);
 g_hash_table_insert(ext_table, "iges", (gpointer)application_iges);
@@ -999,7 +1036,6 @@ g_hash_table_insert(ext_table, "cpio", (gpointer)application_x_cpio);
 g_hash_table_insert(ext_table, "dbf", (gpointer)application_x_dbf);
 g_hash_table_insert(ext_table, "deb", (gpointer)application_x_debian_package);
 g_hash_table_insert(ext_table, "deepv", (gpointer)application_x_deepv);
-g_hash_table_insert(ext_table, "dcr", (gpointer)application_x_director);
 g_hash_table_insert(ext_table, "dir", (gpointer)application_x_director);
 g_hash_table_insert(ext_table, "dxr", (gpointer)application_x_director);
 g_hash_table_insert(ext_table, "dmp", (gpointer)application_x_dmp);
@@ -1387,6 +1423,25 @@ g_hash_table_insert(ext_table, "divx", (gpointer)video_x_msvideo);
 g_hash_table_insert(ext_table, "qtc", (gpointer)video_x_qtc);
 g_hash_table_insert(ext_table, "movie", (gpointer)video_x_sgi_movie);
 g_hash_table_insert(ext_table, "mv", (gpointer)video_x_sgi_movie);
+g_hash_table_insert(ext_table, "msg", (gpointer)application_vnd_ms_outlook);
+g_hash_table_insert(ext_table, "orf", (gpointer)image_x_olympus_orf);
+g_hash_table_insert(ext_table, "nef", (gpointer)image_x_nikon_nef);
+g_hash_table_insert(ext_table, "raf", (gpointer)image_x_fuji_raf);
+g_hash_table_insert(ext_table, "rw2", (gpointer)image_x_panasonic_raw);
+g_hash_table_insert(ext_table, "raw", (gpointer)image_x_panasonic_raw);
+g_hash_table_insert(ext_table, "dng", (gpointer)image_x_adobe_dng);
+g_hash_table_insert(ext_table, "cr2", (gpointer)image_x_canon_cr2);
+g_hash_table_insert(ext_table, "crw", (gpointer)image_x_canon_crw);
+g_hash_table_insert(ext_table, "dcr", (gpointer)image_x_kodak_dcr);
+g_hash_table_insert(ext_table, "k25", (gpointer)image_x_kodak_k25);
+g_hash_table_insert(ext_table, "kdc", (gpointer)image_x_kodak_kdc);
+g_hash_table_insert(ext_table, "mrw", (gpointer)image_x_minolta_mrw);
+g_hash_table_insert(ext_table, "pef", (gpointer)image_x_pentax_pef);
+g_hash_table_insert(ext_table, "xf3", (gpointer)image_x_sigma_x3f);
+g_hash_table_insert(ext_table, "arw", (gpointer)image_x_sony_arw);
+g_hash_table_insert(ext_table, "sr2", (gpointer)image_x_sony_sr2);
+g_hash_table_insert(ext_table, "srf", (gpointer)image_x_sony_srf);
+g_hash_table_insert(ext_table, "erf", (gpointer)image_x_epson_erf);
 return ext_table;}
 GHashTable *mime_get_mime_table() {GHashTable *mime_table = g_hash_table_new(g_str_hash, g_str_equal);
 g_hash_table_insert(mime_table, "application/arj", (gpointer)application_arj);
@@ -1819,5 +1874,23 @@ g_hash_table_insert(mime_table, "video/x-sgi-movie", (gpointer)video_x_sgi_movie
 g_hash_table_insert(mime_table, "x-epoc/x-sisx-app", (gpointer)x_epoc_x_sisx_app);
 g_hash_table_insert(mime_table, "application/x-zstd-dictionary", (gpointer)application_x_zstd_dictionary);
 g_hash_table_insert(mime_table, "application/vnd.ms-outlook", (gpointer)application_vnd_ms_outlook);
+g_hash_table_insert(mime_table, "image/x-olympus-orf", (gpointer)image_x_olympus_orf);
+g_hash_table_insert(mime_table, "image/x-nikon-nef", (gpointer)image_x_nikon_nef);
+g_hash_table_insert(mime_table, "image/x-fuji-raf", (gpointer)image_x_fuji_raf);
+g_hash_table_insert(mime_table, "image/x-panasonic-raw", (gpointer)image_x_panasonic_raw);
+g_hash_table_insert(mime_table, "image/x-adobe-dng", (gpointer)image_x_adobe_dng);
+g_hash_table_insert(mime_table, "image/x-canon-cr2", (gpointer)image_x_canon_cr2);
+g_hash_table_insert(mime_table, "image/x-canon-crw", (gpointer)image_x_canon_crw);
+g_hash_table_insert(mime_table, "image/x-dcraw", (gpointer)image_x_dcraw);
+g_hash_table_insert(mime_table, "image/x-kodak-dcr", (gpointer)image_x_kodak_dcr);
+g_hash_table_insert(mime_table, "image/x-kodak-k25", (gpointer)image_x_kodak_k25);
+g_hash_table_insert(mime_table, "image/x-kodak-kdc", (gpointer)image_x_kodak_kdc);
+g_hash_table_insert(mime_table, "image/x-minolta-mrw", (gpointer)image_x_minolta_mrw);
+g_hash_table_insert(mime_table, "image/x-pentax-pef", (gpointer)image_x_pentax_pef);
+g_hash_table_insert(mime_table, "image/x-sigma-x3f", (gpointer)image_x_sigma_x3f);
+g_hash_table_insert(mime_table, "image/x-sony-arw", (gpointer)image_x_sony_arw);
+g_hash_table_insert(mime_table, "image/x-sony-sr2", (gpointer)image_x_sony_sr2);
+g_hash_table_insert(mime_table, "image/x-sony-srf", (gpointer)image_x_sony_srf);
+g_hash_table_insert(mime_table, "image/x-epson-erf", (gpointer)image_x_epson_erf);
 return mime_table;}
 #endif

src/parsing/parse.c

@@ -78,6 +78,11 @@ void parse(void *arg) {
 
     if (doc.mime == 0 && !ScanCtx.fast) {
         // Get mime type with libmagic
+        if (!job->vfile.is_fs_file) {
+            LOG_WARNING(job->filepath, "Guessing mime type with libmagic inside archive files is not currently supported");
+            goto abort;
+        }
+
         bytes_read = job->vfile.read(&job->vfile, buf, MAGIC_BUF_SIZE);
         if (bytes_read < 0) {
 
@@ -114,6 +119,8 @@ void parse(void *arg) {
 
     if (!(SHOULD_PARSE(doc.mime))) {
 
+    } else if (IS_RAW(doc.mime)) {
+        parse_raw(&ScanCtx.raw_ctx, &job->vfile, &doc);
     } else if ((mmime == MimeVideo && doc.size >= MIN_VIDEO_SIZE) ||
                (mmime == MimeImage && doc.size >= MIN_IMAGE_SIZE) || mmime == MimeAudio) {
 
@@ -147,14 +154,13 @@ void parse(void *arg) {
         parse_mobi(&ScanCtx.mobi_ctx, &job->vfile, &doc);
     }
 
+    abort:
+
     //Parent meta
     if (!uuid_is_null(job->parent)) {
-        char tmp[UUID_STR_LEN];
-        uuid_unparse(job->parent, tmp);
-
         meta_line_t *meta_parent = malloc(sizeof(meta_line_t) + UUID_STR_LEN + 1);
         meta_parent->key = MetaParent;
-        strcpy(meta_parent->str_val, tmp);
+        uuid_unparse(job->parent, meta_parent->str_val);
         APPEND_META((&doc), meta_parent)
     }
 

src/static/css/autocomplete.min.css

@@ -0,0 +1,4 @@
+.autocomplete-suggestions { text-align: left; cursor: default; border: 1px solid #ccc; border-top: 0; background: #fff; box-shadow: -1px 1px 3px rgba(0,0,0,.1); position: absolute; display: none; z-index: 9999; max-height: 254px; overflow: hidden; overflow-y: auto; box-sizing: border-box; }
+.autocomplete-suggestion { position: relative; padding: 0 .6em; line-height: 23px; white-space: nowrap; overflow: hidden; text-overflow: ellipsis; font-size: 1.02em; color: #333; }
+.autocomplete-suggestion b { font-weight: normal; color: #1f8dd6; }
+.autocomplete-suggestion.selected { background: #f0f0f0; }

src/static/css/dark.css

@@ -266,6 +266,7 @@ mark {
     margin: 3px;
     white-space: normal;
     color: rgb(224, 224, 224);
+    overflow: hidden;
 }
 
 .irs-single, .irs-from, .irs-to {

src/static/css/light.css

@@ -205,6 +205,7 @@ mark {
     margin: 3px;
     white-space: normal;
     color: #000;
+    overflow: hidden;
 }
 
 .irs-single, .irs-from, .irs-to {

src/static/js/dom.js

@@ -27,18 +27,12 @@ function gifOver(thumbnail, hit) {
 }
 
 function getContentHighlight(hit) {
-    const re = RegExp(/<mark>/g);
-
-    const sortByMathCount = (a, b) => {
-        return b.match(re).length - a.match(re).length;
-    };
-
     if (hit.hasOwnProperty("highlight")) {
         if (hit["highlight"].hasOwnProperty("content")) {
-            return hit["highlight"]["content"].sort(sortByMathCount)[0];
+            return hit["highlight"]["content"][0];
 
         } else if (hit["highlight"].hasOwnProperty("content.nGram")) {
-            return hit["highlight"]["content.nGram"].sort(sortByMathCount)[0];
+            return hit["highlight"]["content.nGram"][0];
         }
     }
 
@@ -77,6 +71,7 @@ function shouldPlayVideo(hit) {
 
     return mime &&
         mime.startsWith("video/") &&
+        !("parent" in hit["_source"]) &&
         hit["_source"]["extension"] !== "mkv" &&
         hit["_source"]["extension"] !== "avi" &&
         videoc !== "hevc" &&
@@ -92,6 +87,7 @@ function shouldDisplayRawImage(hit) {
         hit["_source"]["mime"] &&
         !hit["_source"]["parent"] &&
         hit["_source"]["videoc"] !== "tiff" &&
+        hit["_source"]["videoc"] !== "raw" &&
         hit["_source"]["videoc"] !== "ppm";
 }
 

src/static/js/search.js

@@ -74,6 +74,41 @@ function showEsError() {
 
 window.onload = () => {
     CONF.load();
+    new autoComplete({
+        selector: '#pathBar',
+        minChars: 1,
+        delay: 400,
+        renderItem: function (item) {
+            return '<div class="autocomplete-suggestion" data-val="' + item + '">' + item + '</div>';
+        },
+        source: async function (term, suggest) {
+
+            if (!CONF.options.suggestPath) {
+                return []
+            }
+
+            term = term.toLowerCase();
+
+            const choices = await getPathChoices();
+
+            let matches = [];
+            for (let i = 0; i < choices.length; i++) {
+                if (~choices[i].toLowerCase().indexOf(term)) {
+                    matches.push(choices[i]);
+                }
+            }
+            suggest(matches.sort());
+        },
+        onSelect: function () {
+            searchDebounced();
+        }
+    });
+    searchBar.addEventListener("keyup", searchDebounced);
+    pathBar.addEventListener("keyup", e => {
+        if (e.key === "Enter") {
+            searchDebounced();
+        }
+    });
 };
 
 function toggleFuzzy() {
@@ -105,10 +140,7 @@ $.jsonPost("i").then(resp => {
 });
 
 function getDocumentInfo(id) {
-    return $.getJSON("d/" + id).fail(e => {
-        console.log(e);
-        showEsError();
-    })
+    return $.getJSON("d/" + id).fail(showEsError)
 }
 
 function handleTreeClick(tree) {
@@ -218,12 +250,13 @@ function addTag(map, tag, id, count) {
     let child = {
         id: id,
         text: tags.length !== 1 ? tags[0] : `${tags[0]} (${count})`,
+        name: tags[0],
         children: []
     };
 
     let found = false;
     map.forEach(node => {
-        if (node.text === child.text) {
+        if (node.name === child.name) {
             found = true;
             if (tags.length !== 1) {
                 addTag(node.children, tags.slice(1).join("."), id, count);
@@ -332,24 +365,24 @@ function search(after = null) {
 
     let path = pathBar.value.replace(/\/$/, "").toLowerCase(); //remove trailing slashes
     if (path !== "") {
-        filters.push([{term: {path: path}}])
+        filters.push({term: {path: path}})
     }
     let mimeTypes = getSelectedNodes(mimeTree);
     if (!mimeTypes.includes("any")) {
-        filters.push([{terms: {"mime": mimeTypes}}]);
+        filters.push({terms: {"mime": mimeTypes}});
     }
 
     let tags = getSelectedNodes(tagTree);
     if (!tags.includes("any")) {
-        filters.push([{terms: {"tag": tags}}]);
+        filters.push({terms: {"tag": tags}});
     }
 
     if (date_min && date_max) {
-        filters.push([{range: {mtime: {gte: date_min, lte: date_max}}}])
+        filters.push({range: {mtime: {gte: date_min, lte: date_max}}})
     } else if (date_min) {
-        filters.push([{range: {mtime: {gte: date_min}}}])
+        filters.push({range: {mtime: {gte: date_min}}})
     } else if (date_max) {
-        filters.push([{range: {mtime: {lte: date_max}}}])
+        filters.push({range: {mtime: {lte: date_max}}})
     }
 
     let q = {
@@ -385,6 +418,9 @@ function search(after = null) {
         q.highlight = {
             pre_tags: ["<mark>"],
             post_tags: ["</mark>"],
+            fragment_size: CONF.options.fragmentSize,
+            number_of_fragments: 1,
+            order: "score",
             fields: {
                 content: {},
                 // "content.nGram": {},
@@ -441,8 +477,6 @@ let searchDebounced = _.debounce(function () {
     search()
 }, 500);
 
-searchBar.addEventListener("keyup", searchDebounced);
-pathBar.addEventListener("keyup", searchDebounced);
 
 //Size slider
 $("#sizeSlider").ionRangeSlider({
@@ -607,7 +641,8 @@ function createPathTree(target) {
     let pathTree = new InspireTree({
         data: function (node, resolve, reject) {
             return getNextDepth(node);
-        }
+        },
+        sort: "text"
     });
 
     selectedIndices.forEach(index => {
@@ -627,3 +662,19 @@ function createPathTree(target) {
     pathTree.on("node.click", handlePathTreeClick(pathTree));
 }
 
+function getPathChoices() {
+    return new Promise(getPaths => {
+        $.jsonPost("es", {
+            suggest: {
+                path: {
+                    prefix: pathBar.value,
+                    completion: {
+                        field: "suggest-path",
+                        skip_duplicates: true,
+                        size: 10000
+                    }
+                }
+            }
+        }).then(resp => getPaths(resp["suggest"]["path"][0]["options"].map(opt => opt["_source"]["path"])));
+    })
+}

src/static/js/util.js

@@ -100,6 +100,8 @@ const _defaults = {
     treemapGroupingDepth: 3,
     treemapColor: "PuBuGn",
     treemapSize: "large",
+    suggestPath: true,
+    fragmentSize: 100
 };
 
 function loadSettings() {
@@ -114,6 +116,8 @@ function loadSettings() {
     $("#settingTreemapColor").val(CONF.options.treemapColor);
     $("#settingTreemapSize").val(CONF.options.treemapSize);
     $("#settingTreemapType").val(CONF.options.treemapType);
+    $("#settingSuggestPath").prop("checked", CONF.options.suggestPath);
+    $("#settingFragmentSize").val(CONF.options.fragmentSize);
 }
 
 function Settings() {
@@ -155,6 +159,8 @@ function updateSettings() {
     CONF.options.treemapColor = $("#settingTreemapColor").val();
     CONF.options.treemapSize = $("#settingTreemapSize").val();
     CONF.options.treemapType = $("#settingTreemapType").val();
+    CONF.options.suggestPath = $("#settingSuggestPath").prop("checked");
+    CONF.options.fragmentSize = $("#settingFragmentSize").val();
     CONF.save();
 
     if (typeof searchDebounced !== "undefined") {

src/static/search.html

@@ -11,7 +11,7 @@
 
 <nav class="navbar navbar-expand-lg">
     <a class="navbar-brand" href="/">sist2</a>
-    <span class="badge badge-pill version">2.3.0</span>
+    <span class="badge badge-pill version">2.5.0</span>
     <span class="tagline">Lightning-fast file system indexer and search tool </span>
     <a class="btn ml-auto" href="/stats">Stats</a>
     <button class="btn" type="button" data-toggle="modal" data-target="#settings" onclick="loadSettings()">Settings</button>
@@ -192,6 +192,17 @@
                         <label class="custom-control-label" for="settingSearchInPath">Enable matching query against document path</label>
                     </div>
 
+                    <div class="custom-control custom-checkbox">
+                        <input type="checkbox" class="custom-control-input" id="settingSuggestPath">
+                        <label class="custom-control-label" for="settingSuggestPath">Enable auto-complete in path filter bar</label>
+                    </div>
+
+                    <br/>
+                    <div class="form-group">
+                        <input type="number" class="form-control" id="settingFragmentSize">
+                        <label for="settingFragmentSize">Highlight context size in characters</label>
+                    </div>
+
                     <label for="settingDisplay">Display</label>
                     <select id="settingDisplay" class="form-control form-control-sm">
                         <option value="grid">Grid</option>

src/static/stats.html

@@ -10,7 +10,7 @@
 
 <nav class="navbar navbar-expand-lg">
     <a class="navbar-brand" href="/">sist2</a>
-    <span class="badge badge-pill version">2.3.0</span>
+    <span class="badge badge-pill version">2.5.0</span>
     <span class="tagline">Lightning-fast file system indexer and search tool </span>
     <a style="margin-left: auto" class="btn" href="/">Back</a>
     <button class="btn" type="button" data-toggle="modal" data-target="#settings"
@@ -77,6 +77,17 @@
                         path</label>
                 </div>
 
+                <div class="custom-control custom-checkbox">
+                    <input type="checkbox" class="custom-control-input" id="settingSuggestPath">
+                    <label class="custom-control-label" for="settingSuggestPath">Enable auto-complete in path filter bar</label>
+                </div>
+
+                <br/>
+                <div class="form-group">
+                    <input type="number" class="form-control" id="settingFragmentSize">
+                    <label for="settingFragmentSize">Highlight context size in characters</label>
+                </div>
+
                 <label for="settingDisplay">Display</label>
                 <select id="settingDisplay" class="form-control form-control-sm">
                     <option value="grid">Grid</option>

src/stats.c

@@ -24,6 +24,10 @@ typedef struct {
 
 void fill_tables(cJSON *document, UNUSED(const char uuid_str[UUID_STR_LEN])) {
 
+    if (cJSON_GetObjectItem(document, "parent") != NULL) {
+        return;
+    }
+
     const char *json_path = cJSON_GetObjectItem(document, "path")->valuestring;
     char *path = malloc(strlen(json_path) + 1);
     strcpy(path, json_path);
@@ -167,7 +171,7 @@ int merge_up(double thresh) {
 
     int size = g_hash_table_size(FlatTree);
 
-    LOG_DEBUGF("stats.h", "Merge up iteration (%d merged, %d in tree)", count, size)
+    LOG_DEBUGF("stats.c", "Merge up iteration (%d merged, %d in tree)", count, size)
     return count;
 }
 
@@ -184,9 +188,9 @@ void csv_escape(char *dst, const char *str) {
         return;
     }
 
-    while (*ptr++ != 0) {
-        char c = *ptr;
-
+    *out++ = '"';
+    char c;
+    while ((c = *ptr++) != 0) {
         if (c == '"') {
             *out++ = '"';
             *out++ = '"';
@@ -194,6 +198,8 @@ void csv_escape(char *dst, const char *str) {
             *out++ = c;
         }
     }
+    *out++ = '"';
+    *out = '\0';
 }
 
 int open_or_exit(const char *path) {

src/util.c

@@ -26,10 +26,11 @@ dyn_buffer_t url_escape(char *str) {
 }
 
 char *abspath(const char *path) {
-    wordexp_t w;
-    wordexp(path, &w, 0);
 
-    char *abs = realpath(w.we_wordv[0], NULL);
+    char *expanded = expandpath(path);
+
+    char *abs = realpath(expanded, NULL);
+    free(expanded);
     if (abs == NULL) {
         return NULL;
     }
@@ -38,16 +39,46 @@ char *abspath(const char *path) {
         strcat(abs, "/");
     }
 
-    wordfree(&w);
     return abs;
 }
 
-char *expandpath(const char *path) {
-    wordexp_t w;
-    wordexp(path, &w, 0);
+void shell_escape(char *dst, const char *src) {
+    const char *ptr = src;
+    char *out = dst;
+    while ((*ptr)) {
+        char c = *ptr++;
 
-    char *expanded = malloc(strlen(w.we_wordv[0]) + 2);
-    strcpy(expanded, w.we_wordv[0]);
+        if (c == '&' || c == '\n' || c == '|' || c == ';' || c == '<' ||
+            c == '>' || c == '(' || c == ')' || c == '{' || c == '}') {
+            *out++ = '\\';
+        }
+        *out++ = c;
+    }
+    *out = 0;
+}
+
+char *expandpath(const char *path) {
+    char tmp[PATH_MAX * 2];
+
+    shell_escape(tmp, path);
+
+    wordexp_t w;
+    wordexp(tmp, &w, 0);
+
+    if (w.we_wordv == NULL) {
+        return NULL;
+    }
+
+    *tmp = '\0';
+    for (int i = 0; i < w.we_wordc; i++) {
+        strcat(tmp, w.we_wordv[i]);
+        if (i != w.we_wordc - 1) {
+            strcat(tmp, " ");
+        }
+    }
+
+    char *expanded = malloc(strlen(tmp) + 2);
+    strcpy(expanded, tmp);
     strcat(expanded, "/");
 
     wordfree(&w);
@@ -152,7 +183,7 @@ void str_escape(char *dst, const char *str) {
                     break;
                 }
 
-                cur += sprintf(cur, "%c%02X", ESCAPE_CHAR, (unsigned char)tmp[i]);
+                cur += sprintf(cur, "%c%02X", ESCAPE_CHAR, (unsigned char) tmp[i]);
             }
             continue;
         }
@@ -198,12 +229,12 @@ void str_unescape(char *dst, const char *str) {
             char next = *ptr;
 
             if (next == ESCAPE_CHAR) {
-                *cur++ = (char)c;
+                *cur++ = (char) c;
                 ptr += 1;
             } else {
                 tmp[0] = *(ptr);
                 tmp[1] = *(ptr + 1);
-                *cur++ = (char)strtol(tmp, NULL, 16);
+                *cur++ = (char) strtol(tmp, NULL, 16);
                 ptr += 2;
             }
         } else {

src/web/serve.c

@@ -68,6 +68,7 @@ void stats(struct mg_connection *nc) {
 void stats_files(struct mg_connection *nc, struct http_message *hm, struct mg_str *path) {
 
     if (path->len != UUID_STR_LEN + 4) {
+        mg_http_send_error(nc, 404, NULL);
         nc->flags |= MG_F_SEND_AND_CLOSE;
         return;
     }
@@ -78,6 +79,7 @@ void stats_files(struct mg_connection *nc, struct http_message *hm, struct mg_st
 
     index_t *index = get_index_by_id(arg_uuid);
     if (index == NULL) {
+        mg_http_send_error(nc, 404, NULL);
         nc->flags |= MG_F_SEND_AND_CLOSE;
         return;
     }
@@ -173,6 +175,7 @@ void thumbnail(struct mg_connection *nc, struct http_message *hm, struct mg_str
 
     if (path->len != UUID_STR_LEN * 2 + 2) {
         LOG_DEBUGF("serve.c", "Invalid thumbnail path: %.*s", (int) path->len, path->p)
+        mg_http_send_error(nc, 404, NULL);
         nc->flags |= MG_F_SEND_AND_CLOSE;
         return;
     }
@@ -189,6 +192,7 @@ void thumbnail(struct mg_connection *nc, struct http_message *hm, struct mg_str
     int ret = uuid_parse(arg_uuid, uuid);
     if (ret != 0) {
         LOG_DEBUGF("serve.c", "Invalid thumbnail UUID: %s", arg_uuid)
+        mg_http_send_error(nc, 404, NULL);
         nc->flags |= MG_F_SEND_AND_CLOSE;
         return;
     }
@@ -196,6 +200,7 @@ void thumbnail(struct mg_connection *nc, struct http_message *hm, struct mg_str
     store_t *store = get_store(arg_index);
     if (store == NULL) {
         LOG_DEBUGF("serve.c", "Could not get store for index: %s", arg_index)
+        mg_http_send_error(nc, 404, NULL);
         nc->flags |= MG_F_SEND_AND_CLOSE;
         return;
     }
@@ -214,6 +219,7 @@ void search(struct mg_connection *nc, struct http_message *hm) {
 
     if (hm->body.len == 0) {
         LOG_DEBUG("serve.c", "Client sent empty body, ignoring request")
+        mg_http_send_error(nc, 500, NULL);
         nc->flags |= MG_F_SEND_AND_CLOSE;
         return;
     }
@@ -314,6 +320,7 @@ void document_info(struct mg_connection *nc, struct http_message *hm, struct mg_
 
     if (path->len != UUID_STR_LEN + 2) {
         LOG_DEBUGF("serve.c", "Invalid document_info path: %.*s", (int) path->len, path->p)
+        mg_http_send_error(nc, 404, NULL);
         nc->flags |= MG_F_SEND_AND_CLOSE;
         return;
     }
@@ -328,6 +335,7 @@ void document_info(struct mg_connection *nc, struct http_message *hm, struct mg_
     cJSON *index_id = cJSON_GetObjectItem(source, "index");
     if (index_id == NULL) {
         cJSON_Delete(doc);
+        mg_http_send_error(nc, 404, NULL);
         nc->flags |= MG_F_SEND_AND_CLOSE;
         return;
     }
@@ -335,6 +343,7 @@ void document_info(struct mg_connection *nc, struct http_message *hm, struct mg_
     index_t *idx = get_index_by_id(index_id->valuestring);
     if (idx == NULL) {
         cJSON_Delete(doc);
+        mg_http_send_error(nc, 404, NULL);
         nc->flags |= MG_F_SEND_AND_CLOSE;
         return;
     }
@@ -352,6 +361,7 @@ void file(struct mg_connection *nc, struct http_message *hm, struct mg_str *path
 
     if (path->len != UUID_STR_LEN + 2) {
         LOG_DEBUGF("serve.c", "Invalid file path: %.*s", (int) path->len, path->p)
+        mg_http_send_error(nc, 404, NULL);
         nc->flags |= MG_F_SEND_AND_CLOSE;
         return;
     }
@@ -371,6 +381,7 @@ void file(struct mg_connection *nc, struct http_message *hm, struct mg_str *path
         index_id = cJSON_GetObjectItem(source, "index");
         if (index_id == NULL) {
             cJSON_Delete(doc);
+            mg_http_send_error(nc, 404, NULL);
             nc->flags |= MG_F_SEND_AND_CLOSE;
             return;
         }
@@ -386,6 +397,7 @@ void file(struct mg_connection *nc, struct http_message *hm, struct mg_str *path
     if (idx == NULL) {
         cJSON_Delete(doc);
         nc->flags |= MG_F_SEND_AND_CLOSE;
+        mg_http_send_error(nc, 404, NULL);
         return;
     }
 
@@ -423,6 +435,7 @@ static void ev_router(struct mg_connection *nc, int ev, void *p) {
         struct http_message *hm = (struct http_message *) p;
 
         if (mg_parse_uri(hm->uri, &scheme, &user_info, &host, &port, &path, &query, &fragment) != 0) {
+            mg_http_send_error(nc, 400, NULL);
             nc->flags |= MG_F_SEND_AND_CLOSE;
             return;
         }
@@ -469,6 +482,7 @@ static void ev_router(struct mg_connection *nc, int ev, void *p) {
         } else if (has_prefix(&path, &((struct mg_str) MG_MK_STR("/d/")))) {
             document_info(nc, hm, &path);
         } else {
+            mg_http_send_error(nc, 404, NULL);
             nc->flags |= MG_F_SEND_AND_CLOSE;
         }
 
@@ -499,7 +513,7 @@ static void ev_router(struct mg_connection *nc, int ev, void *p) {
                         free(json_str);
                         free(tmp);
                     }
-                    //todo return error code
+                    mg_http_send_error(nc, 500, NULL);
                 }
 
                 free_response(r);