Archive file support

List mode #5

.gitmodules

@@ -16,3 +16,18 @@
 [submodule "lmdb"]
 	path = lmdb
 	url = https://github.com/LMDB/lmdb
+[submodule "utf8.h"]
+	path = utf8.h
+	url = https://github.com/sheredom/utf8.h
+[submodule "lib/openjpeg"]
+	path = lib/openjpeg
+	url = https://github.com/uclouvain/openjpeg
+[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
@@ -37,7 +38,10 @@ if (WITH_SIST2)
             lmdb/libraries/liblmdb/lmdb.h lmdb/libraries/liblmdb/mdb.c
             lmdb/libraries/liblmdb/midl.h lmdb/libraries/liblmdb/midl.c
             src/cli.c src/cli.h
-    )
+
+            # utf8.h
+            utf8.h/utf8.h
+            src/parsing/arc.c src/parsing/arc.h)
 endif ()
 
 if (WITH_SIST2_SCAN)
@@ -67,7 +71,10 @@ if (WITH_SIST2_SCAN)
             lmdb/libraries/liblmdb/lmdb.h lmdb/libraries/liblmdb/mdb.c
             lmdb/libraries/liblmdb/midl.h lmdb/libraries/liblmdb/midl.c
             src/cli.c src/cli.h
-    )
+
+            # utf8.h
+            utf8.h/utf8.h
+            src/parsing/arc.c src/parsing/arc.h)
 endif ()
 
 find_package(PkgConfig REQUIRED)
@@ -116,8 +123,8 @@ if (WITH_SIST2)
 
     target_compile_options(sist2
             PRIVATE
-            -O3
-            #        -march=native
+            -Ofast
+#                    -march=native
             -fno-stack-protector
             -fomit-frame-pointer
             )
@@ -150,6 +157,10 @@ if (WITH_SIST2)
             m
             bz2
             magic
+            ${PROJECT_SOURCE_DIR}/lib/libharfbuzz.a
+            ${PROJECT_SOURCE_DIR}/lib/libopenjp2.a
+            freetype
+            archive
     )
 
 endif ()
@@ -187,7 +198,7 @@ if (WITH_SIST2_SCAN)
     )
     target_compile_options(sist2_scan
             PRIVATE
-            -O3
+            -Ofast
             #        -march=native
             -fno-stack-protector
             -fomit-frame-pointer
@@ -215,6 +226,14 @@ if (WITH_SIST2_SCAN)
 
             pthread
             m
+            ${PROJECT_SOURCE_DIR}/lib/libharfbuzz.a
+            ${PROJECT_SOURCE_DIR}/lib/libopenjp2.a
+            freetype
+
+            ${PROJECT_SOURCE_DIR}/lib/libarchive.a
+            ${PROJECT_SOURCE_DIR}/lib/liblz4.a
+            ${PROJECT_SOURCE_DIR}/lib/liblzma.a
+            ${PROJECT_SOURCE_DIR}/lib/libzstd.a
     )
 endif ()
 

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 +1,9 @@
+rm ./sist2
+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

@@ -9,29 +9,32 @@ sist2 (Simple incremental search tool)
 
 ## Features
 
-* Fast, low memory usage
+* Fast, low memory usage, multi-threaded
 * Portable (all its features are packaged in a single executable)
 * Extracts text from common file types\*
 * Generates thumbnails\*
 * Incremental scanning
+* Automatic tagging from file attributes via [user scripts](scripting/README.md)
+* Recursive scan inside archive files \*\*
 
 
-\* See [format support](#format-support)
+\* See [format support](#format-support)    
+\** See [Archive files](#archive-files)
 
 ## 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
 
-![demo](demo.gif)
-
 See help page `sist2 --help` for more details.
 
 **Scan a directory**
@@ -52,19 +55,61 @@ 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` | *planned* |
-`audio/*` | libav | - | yes, `jpeg` | ID3 tags |
-`video/*` | libav | - | yes, `jpeg` | *planned* |
-`image/*` | libav | - | yes, `jpeg` | *planned* |
+pdf,xps,cbz,fb2,epub | MuPDF | yes | yes, `png` | title |
+`audio/*` | ffmpeg | - | yes, `jpeg` | ID3 tags |
+`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* |
+tar, zip, rar, 7z, ar ...  | Libarchive | yes\* | - | no |
+docx, xlsx, pptx |  | yes | no | *planned* |
 
+\* *See [Archive files](#archive-files)*
+ 
+### Archive files
+**sist2** will scan files stored into archive files (zip, tar, 7z...) as if
+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.
+* 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 -`
+ 
 
 
 ## Build from source
@@ -79,17 +124,18 @@ binaries.
     apt install git cmake pkg-config libglib2.0-dev\
         libssl-dev uuid-dev libavformat-dev libswscale-dev \
         python3 libmagic-dev libfreetype6-dev libcurl-dev \
-        libbz2-dev yasm
+        libbz2-dev yasm libharfbuzz-dev ragel
    ```
     *(FreeBSD)*
     ```bash
-   pkg install cmake gcc yasm gmake bash ffmpeg e2fsprogs-uuid
+   pkg install cmake gcc yasm gmake bash ffmpeg e2fsprogs-uuid\
+        autotools ragel
    ```
-  __ 
+
 2. Build
     ```bash
     git clone --recurse-submodules https://github.com/simon987/sist2
     ./scripts/get_static_libs.sh
     cmake .
     make
-    ```
+    ```

mime.csv

@@ -252,8 +252,9 @@ text/html, acgi|htm|html|htmls|htx|shtml
 text/javascript, js
 text/mcf, mcf
 text/pascal, pas
-text/plain, com|cmd|conf|def|g|idc|list|lst|mar|sdml|text|txt|md|groovy|license|properties|desktop|ini|rst|cmake|ipynb|readme|less|lo|go|yml|d|cs|hpp|srt
+text/plain, com|cmd|conf|def|g|idc|list|lst|mar|sdml|text|txt|md|groovy|license|properties|desktop|ini|rst|cmake|ipynb|readme|less|lo|go|yml|d|cs|hpp|srt|nfo|sfv|m3u
 text/richtext, rt|rtf|rtx
+text/rtf,
 text/scriplet, wsc
 text/x-awk, awk
 !video/x-jng, jng
@@ -263,7 +264,7 @@ image/x-xwindowdump, xwd
 !image/vnd.adobe.photoshop, psd
 text/tab-separated-values, tsv
 text/troff, man|me|ms|roff|t|tr
-text/uri-list, uni|unis|uri|uris
+text/uri-list, uji|unis|uri|uris
 text/vnd.abc, abc
 text/vnd.fmi.flexstor, flx
 text/vnd.wap.wmlscript, wmls
@@ -360,3 +361,58 @@ application/x-wine-extension-ini,
 application/x-cbz, cbz
 application/x-cbr, cbr
 application/x-ms-compress-szdd, fon
+application/x-atari-7800-rom, a78
+application/x-nes-rom, nes
+application/x-font-pfm, pfm
+application/x-gettext-translation,
+image/wmf,
+application/pgp-keys,
+image/x-3ds, 3ds
+application/x-lz4, lz4
+application/vnd.openxmlformats-officedocument.presentationml.presentation, pptx
+application/vnd.oasis.opendocument.presentation, odp
+application/x-msaccess, accdb
+application/vnd.oasis.opendocument.spreadsheet, ods
+audio/x-aiff, aiff|aif
+text/x-ms-regedit, reg
+application/x-gamecube-rom,
+application/x-nintendo-ds-rom,
+text/x-objective-c,
+application/x-font-gdos,
+application/x-apple-diskimage,
+application/x-zstd, zst
+video/x-m4v, m4v
+message/news,
+application/vnd.symbian.install,
+application/x-lzh-compressed,
+application/x-dosdriver,
+application/vnd.tcpdump.pcap, pcap
+x-epoc/x-sisx-app,
+application/x-avira-qua,
+video/MP2T,
+application/x-snappy-framed,
+application/x-lz4+json, jsonlz4
+application/x-dmp, dmp
+application/zlib, z
+application/x-pgp-keyring,
+application/x-gdbm,
+application/x-font-pf2, pf2
+application/x-zip,
+application/x-coredump,
+application/x-java-jmod, jmod
+application/x-terminfo,
+application/x-terminfo2,
+application/x-arc,
+application/vnd.lotus-1-2-3,
+image/x-win-bitmap,
+application/x-maxis-dbpf,
+text/PGP,
+audio/x-hx-aac-adts,
+application/x-chrome-extension,
+image/heic, heic
+image/x-gem,
+application/x-lzma, lzma
+application/warc, warc
+application/x-lz4, lz4
+application/x-lzip, lz
+application/x-lzop, lzo

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

@@ -2,12 +2,28 @@
 cd lib
 
 cd mupdf
-HAVE_X11=no HAVE_GLUT=no make -j 4
+USE_SYSTEM_HARFBUZZ=yes USE_SYSTEM_OPENJPEG=yes HAVE_X11=no HAVE_GLUT=no make -j 4
 cd ..
 
 mv mupdf/build/release/libmupdf.a .
 mv mupdf/build/release/libmupdf-third.a .
 
+# openjp2
+cd openjpeg
+#cmake . -DCMAKE_BUILD_TYPE=Release -DCMAKE_C_FLAGS="-O3 -march=native -DNDEBUG"
+cmake . -DCMAKE_BUILD_TYPE=Release -DCMAKE_C_FLAGS="-O3"
+make -j 4
+cd ..
+mv openjpeg/bin/libopenjp2.a .
+
+# harfbuzz
+cd harfbuzz
+./autogen.sh
+./configure --disable-shared --enable-static
+make -j 4
+cd ..
+mv harfbuzz/src/.libs/libharfbuzz.a .
+
 # ffmpeg
 cd ffmpeg
 ./configure --disable-shared --enable-static --disable-ffmpeg --disable-ffplay \
@@ -38,14 +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
@@ -53,5 +67,39 @@ make -j 4
 cd ..
 mv libmagic/src/.libs/libmagic.a .
 
+# libarchive
+git clone https://github.com/libarchive/libarchive
+cd libarchive/build
+./autogen.sh
+cd ..
+./configure --without-nettle --without-expat --without-xml2 --without-openssl
+make -j 4
+cd ..
+mv libarchive/.libs/libarchive.a .
+
+# lz4
+git clone https://github.com/lz4/lz4
+cd lz4
+make -j 4
+cd ..
+mv lz4/lib/liblz4.a .
+
+# lzma
+wget https://newcontinuum.dl.sourceforge.net/project/lzmautils/xz-5.2.3.tar.gz
+tar -xzf xz-5.2.3.tar.gz
+rm xz-5.2.3.tar.gz
+cd xz-5.2.3
+./autogen.sh
+./configure
+make -j 4
+cd ..
+mv xz-5.2.3/src/liblzma/.libs/liblzma.a .
+
+# zstd
+git clone https://github.com/facebook/zstd
+cd zstd
+make -j 4
+cd ..
+mv zstd/lib/libzstd.a .
 
 cd ..

scripts/get_static_libs_freebsd.sh

@@ -9,6 +9,22 @@ cd ..
 mv mupdf/build/release/libmupdf.a .
 mv mupdf/build/release/libmupdf-third.a .
 
+# openjp2
+cd openjpeg
+#cmake . -DCMAKE_BUILD_TYPE=Release -DCMAKE_C_FLAGS="-O3 -march=native -DNDEBUG"
+cmake . -DCMAKE_BUILD_TYPE=Release -DCMAKE_C_FLAGS="-O3"
+gmake -j 4
+cd ..
+mv openjpeg/bin/libopenjp2.a .
+
+# harfbuzz
+cd harfbuzz
+./autogen.sh
+./configure --disable-shared --enable-static
+gmake -j 4
+cd ..
+mv harfbuzz/src/.libs/libharfbuzz.a .
+
 # ffmpeg
 cd ffmpeg
 ./configure --disable-shared --enable-static --disable-ffmpeg --disable-ffplay \
@@ -26,14 +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

scripts/mime.py

@@ -12,7 +12,8 @@ major_mime = {
     "audio": 7,
     "image": 8,
     "text": 9,
-    "application": 10
+    "application": 10,
+    "x-epoc": 11,
 }
 
 pdf = (
@@ -33,6 +34,28 @@ font = (
     "font/woff2"
 )
 
+# Archive "formats"
+archive = (
+    "application/x-tar",
+    "application/zip",
+    "application/x-rar",
+    "application/x-arc",
+    "application/x-warc",
+    "application/x-7z-compressed",
+)
+
+# Archive "filters"
+arc_filter = (
+    "application/gzip",
+    "application/x-bzip2",
+    "application/x-xz",
+    "application/x-zstd",
+    "application/x-lzma",
+    "application/x-lz4",
+    "application/x-lzip",
+    "application/x-lzop",
+)
+
 cnt = 1
 
 
@@ -47,6 +70,10 @@ def mime_id(mime):
         mime_id += " | 0x40000000"
     elif mime in font:
         mime_id += " | 0x20000000"
+    elif mime in archive:
+        mime_id += " | 0x10000000"
+    elif mime in arc_filter:
+        mime_id += " | 0x08000000"
     elif mime == "application/x-empty":
         return "1"
     return mime_id

src/cli.c

@@ -1,12 +1,13 @@
 #include "cli.h"
 
 #define DEFAULT_OUTPUT "index.sist2/"
-#define DEFAULT_CONTENT_SIZE 4096
-#define DEFAULT_QUALITY 15
-#define DEFAULT_SIZE 200
+#define DEFAULT_CONTENT_SIZE 32768
+#define DEFAULT_QUALITY 5
+#define DEFAULT_SIZE 500
 #define DEFAULT_REWRITE_URL ""
 
 #define DEFAULT_ES_URL "http://localhost:9200"
+#define DEFAULT_BATCH_SIZE 100
 
 #define DEFAULT_BIND_ADDR "localhost"
 #define DEFAULT_PORT "4090"
@@ -14,9 +15,39 @@
 
 scan_args_t *scan_args_create() {
     scan_args_t *args = calloc(sizeof(scan_args_t), 1);
+
+    args->depth = -1;
+
     return args;
 }
 
+void scan_args_destroy(scan_args_t *args) {
+    if (args->name != NULL) {
+        free(args->name);
+    }
+    if (args->path != NULL) {
+        free(args->path);
+    }
+    if (args->output != NULL) {
+        free(args->output);
+    }
+    free(args);
+}
+
+#ifndef SIST_SCAN_ONLY
+
+void index_args_destroy(index_args_t *args) {
+    //todo
+    free(args);
+}
+
+void web_args_destroy(web_args_t *args) {
+    //todo
+    free(args);
+}
+
+#endif
+
 int scan_args_validate(scan_args_t *args, int argc, const char **argv) {
     if (argc < 2) {
         fprintf(stderr, "Required positional argument: PATH.\n");
@@ -25,7 +56,7 @@ 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 +65,7 @@ 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;
         }
     }
@@ -48,16 +79,13 @@ int scan_args_validate(scan_args_t *args, int argc, const char **argv) {
 
     if (args->size == 0) {
         args->size = DEFAULT_SIZE;
-    } else if (args->size <= 0) {
-        fprintf(stderr, "Invalid size: %d\n", args->size);
+    } else if (args->size > 0 && args->size < 32) {
+        printf("Invalid size: %d\n", args->content_size);
         return 1;
     }
 
     if (args->content_size == 0) {
         args->content_size = DEFAULT_CONTENT_SIZE;
-    } else if (args->content_size <= 0) {
-        fprintf(stderr, "Invalid content-size: %d\n", args->content_size);
-        return 1;
     }
 
     if (args->threads == 0) {
@@ -80,6 +108,12 @@ int scan_args_validate(scan_args_t *args, int argc, const char **argv) {
         return 1;
     }
 
+    if (args->depth < 0) {
+        args->depth = G_MAXINT32;
+    } else {
+        args->depth += 1;
+    }
+
     if (args->name == NULL) {
         args->name = g_path_get_basename(args->output);
     }
@@ -87,10 +121,24 @@ int scan_args_validate(scan_args_t *args, int argc, const char **argv) {
     if (args->rewrite_url == NULL) {
         args->rewrite_url = DEFAULT_REWRITE_URL;
     }
+
+    if (args->archive == NULL || strcmp(args->archive, "recurse") == 0) {
+        args->archive_mode = ARC_MODE_RECURSE;
+    } else if (strcmp(args->archive, "list") == 0) {
+        args->archive_mode = ARC_MODE_LIST;
+    } else if (strcmp(args->archive, "shallow") == 0) {
+        args->archive_mode = ARC_MODE_SHALLOW;
+    } else if (strcmp(args->archive, "skip") == 0) {
+        args->archive_mode = ARC_MODE_SKIP;
+    } else {
+        fprintf(stderr, "Archive mode must be one of (skip, list, shallow, recurse), got '%s'", args->archive);
+        return 1;
+    }
     return 0;
 }
 
 #ifndef SIST_SCAN_ONLY
+
 int index_args_validate(index_args_t *args, int argc, const char **argv) {
 
     if (argc < 2) {
@@ -100,15 +148,47 @@ 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];
+        free(index_path);
     }
 
     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);
+    }
+
+    if (args->batch_size == 0) {
+        args->batch_size = DEFAULT_BATCH_SIZE;
+    }
+
     return 0;
 }
 
@@ -131,13 +211,19 @@ 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;
         }
     }
@@ -153,5 +239,6 @@ web_args_t *web_args_create() {
     web_args_t *args = calloc(sizeof(web_args_t), 1);
     return args;
 }
+
 #endif
 

src/cli.h

@@ -12,17 +12,24 @@ typedef struct scan_args {
     char *output;
     char *rewrite_url;
     char *name;
+    int depth;
     char *path;
+    char *archive;
+    archive_mode_t archive_mode;
 } scan_args_t;
 
 scan_args_t *scan_args_create();
+void scan_args_destroy(scan_args_t *args);
 int scan_args_validate(scan_args_t *args, int argc, const char **argv);
 
 #ifndef SIST_SCAN_ONLY
 typedef struct index_args {
     char *es_url;
     const char *index_path;
+    const char *script_path;
+    char *script;
     int print;
+    int batch_size;
     int force_reset;
 } index_args_t;
 
@@ -30,12 +37,17 @@ typedef struct web_args {
     char *es_url;
     char *bind;
     char *port;
+    char *credentials;
+    char *b64credentials;
     int index_count;
     const char **indices;
 } web_args_t;
 
 index_args_t *index_args_create();
+void index_args_destroy(index_args_t *args);
+
 web_args_t *web_args_create();
+void web_args_destroy(web_args_t *args);
 
 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);

src/ctx.h

@@ -15,6 +15,8 @@ struct {
     int threads;
     int content_size;
     float tn_qscale;
+    int depth;
+    archive_mode_t archive_mode;
 
     size_t stat_tn_size;
     size_t stat_index_size;
@@ -29,11 +31,13 @@ struct {
 #ifndef SIST_SCAN_ONLY
 struct {
     char *es_url;
+    int batch_size;
 } IndexCtx;
 
 struct {
     char *es_url;
     int index_count;
+    char *b64credentials;
     struct index_t indices[16];
 } WebCtx;
 #endif

src/index/elastic.c

@@ -6,11 +6,9 @@
 #include <stdio.h>
 #include <string.h>
 #include <cJSON/cJSON.h>
-#include <src/ctx.h>
 
 #include "static_generated.c"
 
-#define BULK_INDEX_SIZE 100
 
 typedef struct es_indexer {
     int queued;
@@ -54,6 +52,40 @@ 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) {
@@ -98,16 +130,30 @@ 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);
     if (cJSON_GetObjectItem(ret_json, "errors")->valueint != 0) {
-        fprintf(stderr, "%s\n", r->body);
+        cJSON *err;
+        cJSON_ArrayForEach(err, cJSON_GetObjectItem(ret_json, "items")) {
+            if (cJSON_GetObjectItem(cJSON_GetObjectItem(err, "index"), "status")->valueint != 201) {
+                char* str = cJSON_Print(err);
+                fprintf(stderr, "%s\n", str);
+                cJSON_free(str);
+            }
+        }
     }
 
     cJSON_Delete(ret_json);
 
     free_response(r);
+    free(buf);
 }
 
 void elastic_index_line(es_bulk_line_t *line) {
@@ -126,15 +172,14 @@ void elastic_index_line(es_bulk_line_t *line) {
 
     Indexer->queued += 1;
 
-    if (Indexer->queued >= BULK_INDEX_SIZE) {
+    if (Indexer->queued >= IndexCtx.batch_size) {
         elastic_flush();
     }
 }
 
 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));
@@ -147,7 +192,7 @@ 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];
 
@@ -156,6 +201,15 @@ 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

@@ -1,7 +1,7 @@
 #include "src/ctx.h"
 #include "serialize.h"
 
-static __thread int IndexFd = -1;
+static __thread int index_fd = -1;
 
 typedef struct {
     unsigned char uuid[16];
@@ -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';
@@ -66,7 +72,7 @@ index_descriptor_t read_index_descriptor(char *path) {
     strcpy(descriptor.root, cJSON_GetObjectItem(json, "root")->valuestring);
     strcpy(descriptor.name, cJSON_GetObjectItem(json, "name")->valuestring);
     strcpy(descriptor.rewrite_url, cJSON_GetObjectItem(json, "rewrite_url")->valuestring);
-    descriptor.root_len = (short)strlen(descriptor.root);
+    descriptor.root_len = (short) strlen(descriptor.root);
     strcpy(descriptor.version, cJSON_GetObjectItem(json, "version")->valuestring);
     strcpy(descriptor.uuid, cJSON_GetObjectItem(json, "uuid")->valuestring);
 
@@ -105,6 +111,8 @@ char *get_meta_key_text(enum metakey meta_key) {
             return "title";
         case MetaFontName:
             return "font_name";
+        case MetaParent:
+            return "parent";
         default:
             return NULL;
     }
@@ -113,13 +121,13 @@ char *get_meta_key_text(enum metakey meta_key) {
 
 void write_document(document_t *doc) {
 
-    if (IndexFd == -1) {
+    if (index_fd == -1) {
         char dstfile[PATH_MAX];
         pthread_t self = pthread_self();
         snprintf(dstfile, PATH_MAX, "%s_index_%lu", ScanCtx.index.path, self);
-        IndexFd = open(dstfile, O_CREAT | O_WRONLY | O_APPEND, S_IRUSR | S_IWUSR);
+        index_fd = open(dstfile, O_CREAT | O_WRONLY | O_APPEND, S_IRUSR | S_IWUSR);
 
-        if (IndexFd == -1) {
+        if (index_fd == -1) {
             perror("open");
         }
     }
@@ -152,13 +160,16 @@ void write_document(document_t *doc) {
     }
     dyn_buffer_write_char(&buf, '\n');
 
-    write(IndexFd, buf.buf, buf.cur);
+    int res = write(index_fd, buf.buf, buf.cur);
+    if (res == -1) {
+        perror("write");
+    }
     ScanCtx.stat_index_size += buf.cur;
     dyn_buffer_destroy(&buf);
 }
 
-void serializer_cleanup() {
-    close(IndexFd);
+void thread_cleanup() {
+    close(index_fd);
 }
 
 void read_index(const char *path, const char index_id[UUID_STR_LEN], index_func func) {
@@ -181,7 +192,7 @@ void read_index(const char *path, const char index_id[UUID_STR_LEN], index_func
         uuid_unparse(line.uuid, uuid_str);
 
         cJSON_AddStringToObject(document, "mime", mime_get_mime_text(line.mime));
-        cJSON_AddNumberToObject(document, "size", (double)line.size);
+        cJSON_AddNumberToObject(document, "size", (double) line.size);
         cJSON_AddNumberToObject(document, "mtime", line.mtime);
 
         int c;
@@ -208,14 +219,19 @@ void read_index(const char *path, const char index_id[UUID_STR_LEN], index_func
         while (key != '\n') {
             switch (key) {
                 case MetaWidth:
-                case MetaHeight:
-                case MetaMediaDuration:
-                case MetaMediaBitrate: {
+                case MetaHeight: {
                     int value;
                     fread(&value, sizeof(int), 1, file);
                     cJSON_AddNumberToObject(document, get_meta_key_text(key), value);
                     break;
                 }
+                case MetaMediaDuration:
+                case MetaMediaBitrate: {
+                    long value;
+                    fread(&value, sizeof(long), 1, file);
+                    cJSON_AddNumberToObject(document, get_meta_key_text(key), value);
+                    break;
+                }
                 case MetaMediaAudioCodec:
                 case MetaMediaVideoCodec: {
                     int value;
@@ -233,10 +249,11 @@ void read_index(const char *path, const char index_id[UUID_STR_LEN], index_func
                 case MetaAlbumArtist:
                 case MetaGenre:
                 case MetaFontName:
+                case MetaParent:
                 case MetaTitle: {
                     buf.cur = 0;
                     while ((c = getc(file)) != 0) {
-                        if (!(SHOULD_IGNORE_CHAR(c)) || c == ' ') {
+                        if (SHOULD_KEEP_CHAR(c) || c == ' ') {
                             dyn_buffer_write_char(&buf, (char) c);
                         }
                     }
@@ -244,14 +261,18 @@ void read_index(const char *path, const char index_id[UUID_STR_LEN], index_func
                     cJSON_AddStringToObject(document, get_meta_key_text(key), buf.buf);
                     break;
                 }
+                default:
+                    fprintf(stderr, "Invalid meta key (corrupt index): %x\n", key);
+                    break;
             }
 
             key = getc(file);
         }
 
         func(document, uuid_str);
-        cJSON_free(document);
+        cJSON_Delete(document);
     }
+    dyn_buffer_destroy(&buf);
     fclose(file);
 }
 

src/io/serialize.h

@@ -18,7 +18,7 @@ void incremental_read(GHashTable *table, const char *filepath);
 /**
  * Must be called after write_document
  */
-void serializer_cleanup();
+void thread_cleanup();
 
 void write_index_descriptor(char *path, index_descriptor_t *desc);
 

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/io/walk.c

@@ -1,28 +1,36 @@
 #include "walk.h"
 #include "src/ctx.h"
 
-parse_job_t *create_parse_job(const char *filepath, const struct stat *info, int base) {
+__always_inline
+parse_job_t *create_fs_parse_job(const char *filepath, const struct stat *info, int base) {
     int len = (int) strlen(filepath);
-
     parse_job_t *job = malloc(sizeof(parse_job_t) + len);
 
-    memcpy(&(job->filepath), filepath, len + 1);
+    strcpy(job->filepath, filepath);
     job->base = base;
     char *p = strrchr(filepath + base, '.');
     if (p != NULL) {
-        job->ext = (int)(p - filepath + 1);
+        job->ext = (int) (p - filepath + 1);
     } else {
         job->ext = len;
     }
 
-    memcpy(&(job->info), info, sizeof(struct stat));
+    job->info = *info;
+
+    memset(job->parent, 0, 16);
+
+    job->vfile.filepath = job->filepath;
+    job->vfile.read = fs_read;
+    job->vfile.close = fs_close;
+    job->vfile.fd = -1;
+    job->vfile.is_fs_file = TRUE;
 
     return job;
 }
 
 int handle_entry(const char *filepath, const struct stat *info, int typeflag, struct FTW *ftw) {
-    if (typeflag == FTW_F && S_ISREG(info->st_mode)) {
-        parse_job_t *job = create_parse_job(filepath, info, ftw->base);
+    if (ftw->level <= ScanCtx.depth && typeflag == FTW_F && S_ISREG(info->st_mode)) {
+        parse_job_t *job = create_fs_parse_job(filepath, info, ftw->base);
         tpool_add_work(ScanCtx.pool, parse, job);
     }
 

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 = "1.0.11";
+static const char *const Version = "1.1.10";
 static const char *const usage[] = {
         "sist2 scan [OPTION]... PATH",
         "sist2 index [OPTION]... INDEX",
@@ -19,9 +19,9 @@ static const char *const usage[] = {
 };
 
 void global_init() {
-    #ifndef SIST_SCAN_ONLY
+#ifndef SIST_SCAN_ONLY
     curl_global_init(CURL_GLOBAL_NOTHING);
-    #endif
+#endif
     av_log_set_level(AV_LOG_QUIET);
 }
 
@@ -41,10 +41,22 @@ void init_dir(const char *dirpath) {
 void scan_print_header() {
     printf("sist2 V%s\n", Version);
     printf("---------------------\n");
-    printf("threads\t\t%d\n", ScanCtx.threads);
-    printf("tn_qscale\t%.1f/31.0\n", ScanCtx.tn_qscale);
-    printf("tn_size\t\t%dpx\n", ScanCtx.tn_size);
-    printf("output\t\t%s\n", ScanCtx.index.path);
+    printf("threads\t\t\t%d\n", ScanCtx.threads);
+    printf("tn_qscale\t\t%.1f/31.0\n", ScanCtx.tn_qscale);
+
+    if (ScanCtx.tn_size > 0) {
+        printf("tn_size\t\t\t%dpx\n", ScanCtx.tn_size);
+    } else {
+        printf("tn_size\t\t\tdisabled\n");
+    }
+
+    if (ScanCtx.content_size > 0) {
+        printf("content_size\t\t%d B\n", ScanCtx.content_size);
+    } else {
+        printf("content_size\t\t\tdisabled\n");
+    }
+
+    printf("output\t\t\t%s\n", ScanCtx.index.path);
 }
 
 void sist2_scan(scan_args_t *args) {
@@ -52,11 +64,12 @@ void sist2_scan(scan_args_t *args) {
     ScanCtx.tn_qscale = args->quality;
     ScanCtx.tn_size = args->size;
     ScanCtx.content_size = args->content_size;
-    ScanCtx.pool = tpool_create(args->threads, serializer_cleanup);
     ScanCtx.threads = args->threads;
+    ScanCtx.depth = args->depth;
+    ScanCtx.archive_mode = args->archive_mode;
     strncpy(ScanCtx.index.path, args->output, sizeof(ScanCtx.index.path));
     strncpy(ScanCtx.index.desc.name, args->name, sizeof(ScanCtx.index.desc.name));
-    strcpy(ScanCtx.index.desc.root, args->path);
+    strncpy(ScanCtx.index.desc.root, args->path, sizeof(ScanCtx.index.desc.root));
     ScanCtx.index.desc.root_len = (short) strlen(ScanCtx.index.desc.root);
 
     init_dir(ScanCtx.index.path);
@@ -93,6 +106,8 @@ void sist2_scan(scan_args_t *args) {
         printf("Loaded %d items in to mtime table.", g_hash_table_size(ScanCtx.original_table));
     }
 
+    ScanCtx.pool = tpool_create(args->threads, thread_cleanup);
+    tpool_start(ScanCtx.pool);
     walk_directory_tree(ScanCtx.index.desc.root);
     tpool_wait(ScanCtx.pool);
     tpool_destroy(ScanCtx.pool);
@@ -124,9 +139,11 @@ void sist2_scan(scan_args_t *args) {
 }
 
 #ifndef SIST_SCAN_ONLY
+
 void sist2_index(index_args_t *args) {
 
     IndexCtx.es_url = args->es_url;
+    IndexCtx.batch_size = args->batch_size;
 
     if (!args->print) {
         elastic_init(args->force_reset);
@@ -162,10 +179,11 @@ 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);
     }
 }
 
@@ -173,6 +191,7 @@ 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]);
@@ -194,6 +213,7 @@ void sist2_web(web_args_t *args) {
 
     serve(args->bind, args->port);
 }
+
 #endif
 
 
@@ -202,41 +222,54 @@ int main(int argc, const char *argv[]) {
     global_init();
 
     scan_args_t *scan_args = scan_args_create();
-    #ifndef SIST_SCAN_ONLY
+#ifndef SIST_SCAN_ONLY
     index_args_t *index_args = index_args_create();
     web_args_t *web_args = web_args_create();
-    #endif
+#endif
 
-    char * common_es_url = NULL;
+    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. Use negative value to disable. DEFAULT=500"),
             OPT_INTEGER(0, "content-size", &scan_args->content_size,
-                        "Number of bytes to be extracted from text documents. DEFAULT=4096"),
+                        "Number of bytes to be extracted from text documents. Use negative value to disable. DEFAULT=32768"),
             OPT_STRING(0, "incremental", &scan_args->incremental,
                        "Reuse an existing index and only scan modified files."),
             OPT_STRING('o', "output", &scan_args->output, "Output directory. DEFAULT=index.sist2/"),
             OPT_STRING(0, "rewrite-url", &scan_args->rewrite_url, "Serve files from this url instead of from disk."),
             OPT_STRING(0, "name", &scan_args->name, "Index display name. DEFAULT: (name of the directory)"),
+            OPT_INTEGER(0, "depth", &scan_args->depth, "Scan up to DEPTH subdirectories deep. "
+                                                       "Use 0 to only scan files in PATH. DEFAULT: -1"),
+            OPT_STRING(0, "archive", &scan_args->archive, "Archive file mode (skip|list|shallow|recurse). "
+                                                          "skip: Don't parse, list: only get file names as text, "
+                                                          "shallow: Don't parse archives inside archives. DEFAULT: recurse"),
 
-            #ifndef SIST_SCAN_ONLY
+#ifndef SIST_SCAN_ONLY
             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_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)"),
+                                                                      "(You must use this option the first time you use the index command)"),
 
             OPT_GROUP("Web options"),
             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"),
-            #endif
+            OPT_STRING(0, "auth", &web_args->credentials, "Basic auth in user:password format"),
+#endif
 
             OPT_END(),
     };
@@ -246,10 +279,15 @@ int main(int argc, const char *argv[]) {
     argparse_describe(&argparse, DESCRIPTION, EPILOG);
     argc = argparse_parse(&argparse, argc, argv);
 
-    #ifndef SIST_SCAN_ONLY
+    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;
-    #endif
+#endif
 
     if (argc == 0) {
         argparse_usage(&argparse);
@@ -264,7 +302,7 @@ int main(int argc, const char *argv[]) {
 
     }
 
-    #ifndef SIST_SCAN_ONLY
+#ifndef SIST_SCAN_ONLY
     else if (strcmp(argv[0], "index") == 0) {
 
         int err = index_args_validate(index_args, argc, argv);
@@ -282,12 +320,20 @@ int main(int argc, const char *argv[]) {
         sist2_web(web_args);
 
     }
-    #endif
+#endif
     else {
         fprintf(stderr, "Invalid command: '%s'\n", argv[0]);
         argparse_usage(&argparse);
         return 1;
     }
     printf("\n");
+
+    scan_args_destroy(scan_args);
+
+#ifndef SIST_SCAN_ONLY
+    index_args_destroy(index_args);
+    web_args_destroy(web_args);
+#endif
+
     return 0;
 }

src/parsing/arc.c

@@ -0,0 +1,152 @@
+#include "arc.h"
+#include "src/ctx.h"
+
+#define ARC_BUF_SIZE 8192
+
+int should_parse_filtered_file(const char *filepath, int ext) {
+    char tmp[PATH_MAX * 2];
+
+    if (ext == 0) {
+        return FALSE;
+    }
+
+    memcpy(tmp, filepath, ext - 1);
+    *(tmp + ext - 1) = '\0';
+
+    char *idx = strrchr(tmp, '.');
+
+    if (idx == NULL) {
+        return FALSE;
+    }
+
+    if (strcmp(idx, ".tar") == 0) {
+        return TRUE;
+    }
+
+    return FALSE;
+}
+
+int arc_read(struct vfile *f, void *buf, size_t size) {
+    return archive_read_data(f->arc, buf, size);
+}
+
+typedef struct arc_data {
+    vfile_t *f;
+    char buf[ARC_BUF_SIZE];
+} arc_data_f;
+
+int vfile_open_callback(struct archive *a, void *user_data) {
+    arc_data_f *data = user_data;
+
+    if (data->f->is_fs_file && data->f->fd == -1) {
+        data->f->fd = open(data->f->filepath, O_RDONLY);
+    }
+
+    return ARCHIVE_OK;
+}
+
+long vfile_read_callback(struct archive *a, void *user_data, const void **buf) {
+    arc_data_f *data = user_data;
+
+    *buf = data->buf;
+    return data->f->read(data->f, data->buf, ARC_BUF_SIZE);
+}
+
+int vfile_close_callback(struct archive *a, void *user_data) {
+    arc_data_f *data = user_data;
+
+    if (data->f->close != NULL) {
+        data->f->close(data->f);
+    }
+
+    return ARCHIVE_OK;
+}
+
+void parse_archive(vfile_t *f, document_t *doc) {
+
+    struct archive *a;
+    struct archive_entry *entry;
+
+    a = archive_read_new();
+
+    archive_read_support_filter_all(a);
+    archive_read_support_format_all(a);
+
+    arc_data_f data;
+    data.f = f;
+
+    int ret = 0;
+    if (data.f->is_fs_file) {
+        ret = archive_read_open_filename(a, doc->filepath, ARC_BUF_SIZE);
+    } else if (ScanCtx.archive_mode == ARC_MODE_RECURSE) {
+        ret = archive_read_open(
+                a, &data,
+                vfile_open_callback,
+                vfile_read_callback,
+                vfile_close_callback
+        );
+    } else {
+        archive_read_free(a);
+        return;
+    }
+
+    if (ret != ARCHIVE_OK) {
+        fprintf(stderr, "OPEN[%d]:%s %s\n", ret, archive_error_string(a), doc->filepath);
+        archive_read_free(a);
+        return;
+    }
+
+    if (ScanCtx.archive_mode == ARC_MODE_LIST) {
+
+        dyn_buffer_t buf = dyn_buffer_create();
+
+        while (archive_read_next_header(a, &entry) == ARCHIVE_OK) {
+            if (S_ISREG(archive_entry_stat(entry)->st_mode)) {
+
+                char *path = (char *) archive_entry_pathname(entry);
+
+                dyn_buffer_append_string(&buf, path);
+                dyn_buffer_write_char(&buf, '\n');
+            }
+        }
+        dyn_buffer_write_char(&buf, '\0');
+
+        meta_line_t *meta_list = malloc(sizeof(meta_line_t) + buf.cur);
+        meta_list->key = MetaContent;
+        strcpy(meta_list->strval, buf.buf);
+        APPEND_META(doc, meta_list);
+        dyn_buffer_destroy(&buf);
+
+    } else {
+
+        parse_job_t *sub_job = malloc(sizeof(parse_job_t) + PATH_MAX * 2);
+
+        sub_job->vfile.close = NULL;
+        sub_job->vfile.read = arc_read;
+        sub_job->vfile.arc = a;
+        sub_job->vfile.filepath = sub_job->filepath;
+        sub_job->vfile.is_fs_file = FALSE;
+        memcpy(sub_job->parent, doc->uuid, sizeof(uuid_t));
+
+        while (archive_read_next_header(a, &entry) == ARCHIVE_OK) {
+            sub_job->info = *archive_entry_stat(entry);
+            if (S_ISREG(sub_job->info.st_mode)) {
+                sprintf(sub_job->filepath, "%s#/%s", f->filepath, archive_entry_pathname(entry));
+                sub_job->base = (int) (strrchr(sub_job->filepath, '/') - sub_job->filepath) + 1;
+
+                char *p = strrchr(sub_job->filepath, '.');
+                if (p != NULL) {
+                    sub_job->ext = (int) (p - sub_job->filepath + 1);
+                } else {
+                    sub_job->ext = (int) strlen(sub_job->filepath);
+                }
+
+                parse(sub_job);
+            }
+        }
+
+        free(sub_job);
+    }
+
+    archive_read_free(a);
+}

src/parsing/arc.h

@@ -0,0 +1,12 @@
+#ifndef SIST2_ARC_H
+#define SIST2_ARC_H
+
+#include "src/sist.h"
+
+int should_parse_filtered_file(const char *filepath, int ext);
+
+void parse_archive(vfile_t *f, document_t *doc);
+
+int arc_read(struct vfile * f, void *buf, size_t size);
+
+#endif

src/parsing/font.c

@@ -1,11 +1,9 @@
 #include "font.h"
 
-#include "ft2build.h"
-#include "freetype/freetype.h"
 
 #include "src/ctx.h"
 
-__thread FT_Library library = NULL;
+__thread FT_Library ft_lib = NULL;
 
 
 typedef struct text_dimensions {
@@ -15,12 +13,12 @@ typedef struct text_dimensions {
 } text_dimensions_t;
 
 typedef struct glyph {
-    unsigned int top;
-    unsigned int height;
-    unsigned int width;
-    unsigned int descent;
-    unsigned int ascent;
-    unsigned int advance_width;
+    int top;
+    int height;
+    int width;
+    int descent;
+    int ascent;
+    int advance_width;
     unsigned char *pixmap;
 } glyph_t;
 
@@ -39,10 +37,10 @@ glyph_t ft_glyph_to_glyph(FT_GlyphSlot slot) {
 
     glyph.pixmap = slot->bitmap.buffer;
 
-    glyph.width = slot->bitmap.width;
-    glyph.height = slot->bitmap.rows;
+    glyph.width = (int) slot->bitmap.width;
+    glyph.height = (int) slot->bitmap.rows;
     glyph.top = slot->bitmap_top;
-    glyph.advance_width = slot->advance.x / 64;
+    glyph.advance_width = (int) slot->advance.x / 64;
 
     glyph.descent = MAX(0, glyph.height - glyph.top);
     glyph.ascent = MAX(0, MAX(glyph.top, glyph.height) - glyph.descent);
@@ -50,10 +48,6 @@ glyph_t ft_glyph_to_glyph(FT_GlyphSlot slot) {
     return glyph;
 }
 
-__always_inline
-glyph_t get_glyph(char character, FT_Face face) {
-}
-
 text_dimensions_t text_dimension(char *text, FT_Face face) {
     text_dimensions_t dimensions;
 
@@ -62,7 +56,7 @@ text_dimensions_t text_dimension(char *text, FT_Face face) {
     int num_chars = (int) strlen(text);
 
     unsigned int max_ascent = 0;
-    unsigned int max_descent = 0;
+    int max_descent = 0;
 
     char pc = 0;
     for (int i = 0; i < num_chars; i++) {
@@ -72,7 +66,7 @@ text_dimensions_t text_dimension(char *text, FT_Face face) {
         glyph_t glyph = ft_glyph_to_glyph(face->glyph);
 
         max_descent = MAX(max_descent, glyph.descent);
-        max_ascent = MAX(max_ascent, glyph.ascent);
+        max_ascent = MAX(max_ascent, MAX(glyph.height, glyph.ascent));
 
         int kerning_x = kerning_offset(c, pc, face);
         dimensions.width += MAX(glyph.advance_width, glyph.width) + kerning_x;
@@ -143,12 +137,15 @@ void bmp_format(dyn_buffer_t *buf, text_dimensions_t dimensions, const unsigned
 }
 
 void parse_font(const char *buf, size_t buf_len, document_t *doc) {
-    if (library == NULL) {
-        FT_Init_FreeType(&library);
+    if (ft_lib == NULL) {
+        FT_Init_FreeType(&ft_lib);
+    }
+    if (buf == NULL) {
+        return;
     }
 
     FT_Face face;
-    FT_Error err = FT_New_Memory_Face(library, (unsigned char *) buf, buf_len, 0, &face);
+    FT_Error err = FT_New_Memory_Face(ft_lib, (unsigned char *) buf, buf_len, 0, &face);
     if (err != 0) {
         return;
     }
@@ -170,6 +167,10 @@ void parse_font(const char *buf, size_t buf_len, document_t *doc) {
     strcpy(meta_name->strval, font_name);
     APPEND_META(doc, meta_name)
 
+    if (ScanCtx.tn_size <= 0) {
+        return;
+    }
+
     int pixel = 64;
     int num_chars = (int) strlen(font_name);
 
@@ -190,11 +191,18 @@ void parse_font(const char *buf, size_t buf_len, document_t *doc) {
 
         err = FT_Load_Char(face, c, FT_LOAD_NO_HINTING | FT_LOAD_RENDER);
         if (err != 0) {
-            continue;
+            c = c >= 'a' && c <= 'z' ? c - 32 : c + 32;
+            err = FT_Load_Char(face, c, FT_LOAD_NO_HINTING | FT_LOAD_RENDER);
+            if (err != 0) {
+                continue;
+            }
         }
         glyph_t glyph = ft_glyph_to_glyph(face->glyph);
 
         pen.x += kerning_offset(c, pc, face);
+        if (pen.x <= 0) {
+            pen.x = ABS(glyph.advance_width - glyph.width);
+        }
         pen.y = dimensions.height - glyph.ascent - dimensions.baseline;
 
         draw_glyph(&glyph, pen.x, pen.y, dimensions, bitmap);

src/parsing/media.c

@@ -1,6 +1,10 @@
 #include "src/sist.h"
 #include "src/ctx.h"
 
+#define MIN_SIZE 32
+#define AVIO_BUF_SIZE 8192
+
+__always_inline
 AVCodecContext *alloc_jpeg_encoder(int dstW, int dstH, float qscale) {
 
     AVCodec *jpeg_codec = avcodec_find_encoder(AV_CODEC_ID_MJPEG);
@@ -22,8 +26,8 @@ AVCodecContext *alloc_jpeg_encoder(int dstW, int dstH, float qscale) {
     return jpeg;
 }
 
+__always_inline
 AVFrame *scale_frame(const AVCodecContext *decoder, const AVFrame *frame, int size) {
-    AVFrame *scaled_frame = av_frame_alloc();
 
     int dstW;
     int dstH;
@@ -41,16 +45,22 @@ AVFrame *scale_frame(const AVCodecContext *decoder, const AVFrame *frame, int si
         }
     }
 
+    if (dstW <= MIN_SIZE || dstH <= MIN_SIZE) {
+        return NULL;
+    }
+
+    AVFrame *scaled_frame = av_frame_alloc();
+
     struct SwsContext *ctx = sws_getContext(
             decoder->width, decoder->height, decoder->pix_fmt,
             dstW, dstH, AV_PIX_FMT_YUVJ420P,
             SWS_FAST_BILINEAR, 0, 0, 0
     );
 
-    int dst_buf_len = avpicture_get_size(AV_PIX_FMT_YUVJ420P, dstW, dstH);
+    int dst_buf_len = av_image_get_buffer_size(AV_PIX_FMT_YUV420P, dstW, dstH, 1);
     uint8_t *dst_buf = (uint8_t *) av_malloc(dst_buf_len);
 
-    avpicture_fill((AVPicture *) scaled_frame, dst_buf, AV_PIX_FMT_YUVJ420P, dstW, dstH);
+    av_image_fill_arrays(scaled_frame->data, scaled_frame->linesize, dst_buf, AV_PIX_FMT_YUV420P, dstW, dstH, 1);
 
     sws_scale(ctx,
               (const uint8_t *const *) frame->data, frame->linesize,
@@ -80,9 +90,9 @@ AVFrame *read_frame(AVFormatContext *pFormatCtx, AVCodecContext *decoder, int st
             int read_frame_ret = av_read_frame(pFormatCtx, &avPacket);
 
             if (read_frame_ret != 0) {
-                if (read_frame_ret != AVERROR_EOF) {
-                    fprintf(stderr, "Error reading frame: %s\n", av_err2str(read_frame_ret));
-                }
+//                if (read_frame_ret != AVERROR_EOF) {
+//                    fprintf(stderr, "Error reading frame: %d\n", read_frame_ret);
+//                }
                 av_frame_free(&frame);
                 av_packet_unref(&avPacket);
                 return NULL;
@@ -107,63 +117,83 @@ AVFrame *read_frame(AVFormatContext *pFormatCtx, AVCodecContext *decoder, int st
     return frame;
 }
 
+#define APPEND_TAG_META(doc, tag_, keyname) \
+    text_buffer_t tex = text_buffer_create(-1); \
+    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); \
+    APPEND_META(doc, meta_tag) \
+    text_buffer_destroy(&tex);
+
+__always_inline
 void append_audio_meta(AVFormatContext *pFormatCtx, document_t *doc) {
 
     AVDictionaryEntry *tag = NULL;
     while ((tag = av_dict_get(pFormatCtx->metadata, "", tag, AV_DICT_IGNORE_SUFFIX))) {
-        char *key = tag->key;
-        for (; *key; ++key) *key = (char) tolower(*key);
+        char key[32];
+        strncpy(key, tag->key, sizeof(key));
 
-        if (strcmp(tag->key, "artist") == 0) {
-            size_t len = strlen(tag->value);
-            meta_line_t *meta_tag = malloc(sizeof(meta_line_t) + len);
-            meta_tag->key = MetaArtist;
-            memcpy(meta_tag->strval, tag->value, len);
-            APPEND_META(doc, meta_tag)
-        } else if (strcmp(tag->key, "genre") == 0) {
-            size_t len = strlen(tag->value);
-            meta_line_t *meta_tag = malloc(sizeof(meta_line_t) + len);
-            meta_tag->key = MetaGenre;
-            memcpy(meta_tag->strval, tag->value, len);
-            APPEND_META(doc, meta_tag)
-        } else if (strcmp(tag->key, "title") == 0) {
-            size_t len = strlen(tag->value);
-            meta_line_t *meta_tag = malloc(sizeof(meta_line_t) + len);
-            meta_tag->key = MetaTitle;
-            memcpy(meta_tag->strval, tag->value, len);
-            APPEND_META(doc, meta_tag)
-        } else if (strcmp(tag->key, "album_artist") == 0) {
-            size_t len = strlen(tag->value);
-            meta_line_t *meta_tag = malloc(sizeof(meta_line_t) + len);
-            meta_tag->key = MetaAlbumArtist;
-            memcpy(meta_tag->strval, tag->value, len);
-            APPEND_META(doc, meta_tag)
-        } else if (strcmp(tag->key, "album") == 0) {
-            size_t len = strlen(tag->value);
-            meta_line_t *meta_tag = malloc(sizeof(meta_line_t) + len);
-            meta_tag->key = MetaAlbum;
-            memcpy(meta_tag->strval, tag->value, len);
-            APPEND_META(doc, meta_tag)
+        char *ptr = key;
+        for (; *ptr; ++ptr) *ptr = (char) tolower(*ptr);
+
+        if (strcmp(key, "artist") == 0) {
+            APPEND_TAG_META(doc, tag, MetaArtist)
+        } else if (strcmp(key, "genre") == 0) {
+            APPEND_TAG_META(doc, tag, MetaGenre)
+        } else if (strcmp(key, "title") == 0) {
+            APPEND_TAG_META(doc, tag, MetaTitle)
+        } else if (strcmp(key, "album_artist") == 0) {
+            APPEND_TAG_META(doc, tag, MetaAlbumArtist)
+        } else if (strcmp(key, "album") == 0) {
+            APPEND_TAG_META(doc, tag, MetaAlbum)
         }
     }
 }
 
-void parse_media(const char *filepath, document_t *doc) {
+__always_inline
+void append_video_meta(AVFormatContext *pFormatCtx, AVFrame *frame, document_t *doc, int include_audio_tags, int is_video) {
+
+    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)
+    }
+
+    AVDictionaryEntry *tag = NULL;
+    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)
+            }
+        }
+    }
+}
+
+void parse_media(AVFormatContext *pFormatCtx, document_t *doc) {
 
     int video_stream = -1;
     int audio_stream = -1;
 
-    AVFormatContext *pFormatCtx = avformat_alloc_context();
-    if (pFormatCtx == NULL) {
-        fprintf(stderr, "Could not allocate AVFormatContext! %s \n", filepath);
-        return;
-    }
-    int res = avformat_open_input(&pFormatCtx, filepath, NULL, NULL);
-    if (res < 0) {
-        printf("ERR%s %s\n", filepath, av_err2str(res));
-        return;
-    }
-
     avformat_find_stream_info(pFormatCtx, NULL);
 
     for (int i = (int) pFormatCtx->nb_streams - 1; i >= 0; i--) {
@@ -202,23 +232,10 @@ void parse_media(const char *filepath, document_t *doc) {
         }
     }
 
-    if (video_stream != -1) {
+    if (video_stream != -1 && ScanCtx.tn_size > 0) {
         AVStream *stream = pFormatCtx->streams[video_stream];
 
-        if (stream->nb_frames > 1) {
-            //This is a video (not a still image)
-            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->intval = pFormatCtx->bit_rate;
-            APPEND_META(doc, meta_bitrate)
-        }
-
-        if (stream->codecpar->width <= 20 || stream->codecpar->height <= 20) {
+        if (stream->codecpar->width <= MIN_SIZE || stream->codecpar->height <= MIN_SIZE) {
             avformat_close_input(&pFormatCtx);
             avformat_free_context(pFormatCtx);
             return;
@@ -250,9 +267,19 @@ 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);
 
+        if (scaled_frame == NULL) {
+            av_frame_free(&frame);
+            avcodec_free_context(&decoder);
+            avformat_close_input(&pFormatCtx);
+            avformat_free_context(pFormatCtx);
+            return;
+        }
+
         // Encode frame to jpeg
         AVCodecContext *jpeg_encoder = alloc_jpeg_encoder(scaled_frame->width, scaled_frame->height, ScanCtx.tn_qscale);
         avcodec_send_frame(jpeg_encoder, scaled_frame);
@@ -262,7 +289,8 @@ void parse_media(const char *filepath, document_t *doc) {
         avcodec_receive_packet(jpeg_encoder, &jpeg_packet);
 
         // Save thumbnail
-        store_write(ScanCtx.index.store, (char *) doc->uuid, sizeof(doc->uuid), (char *) jpeg_packet.data, jpeg_packet.size);
+        store_write(ScanCtx.index.store, (char *) doc->uuid, sizeof(doc->uuid), (char *) jpeg_packet.data,
+                    jpeg_packet.size);
 
         av_packet_unref(&jpeg_packet);
         av_frame_free(&frame);
@@ -276,3 +304,58 @@ void parse_media(const char *filepath, document_t *doc) {
     avformat_free_context(pFormatCtx);
 }
 
+void parse_media_filename(const char *filepath, document_t *doc) {
+
+    AVFormatContext *pFormatCtx = avformat_alloc_context();
+    if (pFormatCtx == NULL) {
+        fprintf(stderr, "Could not allocate AVFormatContext! %s \n", filepath);
+        return;
+    }
+    int res = avformat_open_input(&pFormatCtx, filepath, NULL, NULL);
+    if (res < 0) {
+        fprintf(stderr, "media error: %s %s\n", filepath, av_err2str(res));
+        return;
+    }
+
+    parse_media(pFormatCtx, doc);
+}
+
+
+int vfile_read(void *ptr, uint8_t *buf, int buf_size) {
+    struct vfile *f = ptr;
+
+    int ret = f->read(f, buf, buf_size);
+
+    if (ret == 0) {
+        return AVERROR_EOF;
+    }
+    return ret;
+}
+
+void parse_media_vfile(struct vfile *f, document_t *doc) {
+
+    AVFormatContext *pFormatCtx = avformat_alloc_context();
+    if (pFormatCtx == NULL) {
+        fprintf(stderr, "Could not allocate AVFormatContext! %s \n", f->filepath);
+        return;
+    }
+
+    unsigned char *buffer = (unsigned char *) av_malloc(AVIO_BUF_SIZE);
+    AVIOContext *io_ctx = avio_alloc_context(buffer, AVIO_BUF_SIZE, 0, f, vfile_read, NULL, NULL);
+
+    pFormatCtx->pb = io_ctx;
+    pFormatCtx->flags |= AVFMT_FLAG_CUSTOM_IO;
+
+    int res = avformat_open_input(&pFormatCtx, "", NULL, NULL);
+    if (res == -5) {
+        // Tried to parse media that requires seek
+        return;
+    } else if(res < 0) {
+        fprintf(stderr, "media error: %s %s\n", f->filepath, av_err2str(res));
+        return;
+    }
+
+    parse_media(pFormatCtx, doc);
+    av_free(io_ctx);
+}
+

src/parsing/media.h

@@ -5,7 +5,10 @@
 #include "src/sist.h"
 
 #define MIN_VIDEO_SIZE 1024 * 64
+#define MIN_IMAGE_SIZE 1024 * 2
 
-void parse_media(const char * filepath, document_t *doc);
+void parse_media_filename(const char * filepath, document_t *doc);
+
+void parse_media_vfile(struct vfile *f, document_t *doc);
 
 #endif

src/parsing/mime.c

@@ -1,10 +1,12 @@
 #include "mime.h"
 
 unsigned int mime_get_mime_by_ext(GHashTable *ext_table, const char * ext) {
-    char lower[64];
+    char lower[8];
     char *p = lower;
-    while ((*ext)) {
+    int cnt = 0;
+    while ((*ext) != '\0' && cnt + 1 < sizeof(lower)) {
         *p++ = (char)tolower(*ext++);
+        cnt++;
     }
     *p = '\0';
     return (size_t) g_hash_table_lookup(ext_table, lower);

src/parsing/mime.h

@@ -8,7 +8,7 @@
 #define MIME_EMPTY 1
 
 #define DONT_PARSE 0x80000000
-#define SHOULD_PARSE(mime_id) (mime_id & DONT_PARSE) != DONT_PARSE
+#define SHOULD_PARSE(mime_id) (mime_id & DONT_PARSE) != DONT_PARSE && mime_id != 0
 
 #define PDF_MASK 0x40000000
 #define IS_PDF(mime_id) (mime_id & PDF_MASK) == PDF_MASK
@@ -16,6 +16,12 @@
 #define FONT_MASK 0x20000000
 #define IS_FONT(mime_id) (mime_id & FONT_MASK) == FONT_MASK
 
+#define ARC_MASK 0x10000000
+#define IS_ARC(mime_id) (mime_id & ARC_MASK) == ARC_MASK
+
+#define ARC_FILTER_MASK 0x08000000
+#define IS_ARC_FILTER(mime_id) (mime_id & ARC_FILTER_MASK) == ARC_FILTER_MASK
+
 enum major_mime {
     MimeInvalid = 0,
     MimeModel = 1,

src/parsing/mime_generated.c

@@ -20,7 +20,7 @@ enum mime {
     application_freeloader=655372,
     application_futuresplash=655373,
     application_groupwise=655374,
-    application_gzip=655375,
+    application_gzip=655375 | 0x08000000,
     application_hta=655376,
     application_i_deas=655377,
     application_iges=655378,
@@ -39,334 +39,389 @@ enum mime {
     application_oda=655391,
     application_ogg=655392,
     application_pdf=655393 | 0x40000000,
-    application_pgp_signature=655394,
-    application_pkcs7_signature=655395,
-    application_pkix_cert=655396,
-    application_postscript=655397,
-    application_pro_eng=655398,
-    application_ringing_tones=655399,
-    application_smil=655400,
-    application_solids=655401,
-    application_sounder=655402,
-    application_step=655403,
-    application_streamingmedia=655404,
-    application_vda=655405,
-    application_vnd_fdf=655406,
-    application_vnd_font_fontforge_sfd=655407,
-    application_vnd_hp_hpgl=655408,
-    application_vnd_iccprofile=655409,
-    application_vnd_ms_cab_compressed=655410,
-    application_vnd_ms_excel=655411,
-    application_vnd_ms_fontobject=655412,
-    application_vnd_ms_opentype=655413 | 0x20000000,
-    application_vnd_ms_pki_certstore=655414,
-    application_vnd_ms_pki_pko=655415,
-    application_vnd_ms_pki_seccat=655416,
-    application_vnd_ms_powerpoint=655417,
-    application_vnd_ms_project=655418,
-    application_vnd_oasis_opendocument_base=655419,
-    application_vnd_oasis_opendocument_formula=655420,
-    application_vnd_oasis_opendocument_graphics=655421,
-    application_vnd_oasis_opendocument_text=655422,
-    application_vnd_openxmlformats_officedocument_spreadsheetml_sheet=655423,
-    application_vnd_openxmlformats_officedocument_wordprocessingml_document=655424,
-    application_vnd_wap_wmlc=655425,
-    application_vnd_wap_wmlscriptc=655426,
-    application_vnd_xara=655427,
-    application_vocaltec_media_desc=655428,
-    application_vocaltec_media_file=655429,
-    application_winhelp=655430,
-    application_wordperfect=655431,
-    application_wordperfect6_0=655432,
-    application_wordperfect6_1=655433,
-    application_x_123=655434,
-    application_x_7z_compressed=655435,
-    application_x_aim=655436,
-    application_x_archive=655437,
-    application_x_authorware_bin=655438,
-    application_x_authorware_map=655439,
-    application_x_authorware_seg=655440,
-    application_x_bcpio=655441,
-    application_x_bittorrent=655442,
-    application_x_bsh=655443,
-    application_x_bytecode_python=655444,
-    application_x_bzip=655445,
-    application_x_bzip2=655446,
-    application_x_cbr=655447,
-    application_x_cbz=655448 | 0x40000000,
-    application_x_cdlink=655449,
-    application_x_chat=655450,
-    application_x_cocoa=655451,
-    application_x_conference=655452,
-    application_x_cpio=655453,
-    application_x_dbf=655454,
-    application_x_dbt=655455,
-    application_x_debian_package=655456,
-    application_x_deepv=655457,
-    application_x_director=655458,
-    application_x_dosexec=655459,
-    application_x_dvi=655460,
-    application_x_elc=655461,
+    application_pgp_keys=655394,
+    application_pgp_signature=655395,
+    application_pkcs7_signature=655396,
+    application_pkix_cert=655397,
+    application_postscript=655398,
+    application_pro_eng=655399,
+    application_ringing_tones=655400,
+    application_smil=655401,
+    application_solids=655402,
+    application_sounder=655403,
+    application_step=655404,
+    application_streamingmedia=655405,
+    application_vda=655406,
+    application_vnd_fdf=655407,
+    application_vnd_font_fontforge_sfd=655408,
+    application_vnd_hp_hpgl=655409,
+    application_vnd_iccprofile=655410,
+    application_vnd_lotus_1_2_3=655411,
+    application_vnd_ms_cab_compressed=655412,
+    application_vnd_ms_excel=655413,
+    application_vnd_ms_fontobject=655414,
+    application_vnd_ms_opentype=655415 | 0x20000000,
+    application_vnd_ms_pki_certstore=655416,
+    application_vnd_ms_pki_pko=655417,
+    application_vnd_ms_pki_seccat=655418,
+    application_vnd_ms_powerpoint=655419,
+    application_vnd_ms_project=655420,
+    application_vnd_oasis_opendocument_base=655421,
+    application_vnd_oasis_opendocument_formula=655422,
+    application_vnd_oasis_opendocument_graphics=655423,
+    application_vnd_oasis_opendocument_presentation=655424,
+    application_vnd_oasis_opendocument_spreadsheet=655425,
+    application_vnd_oasis_opendocument_text=655426,
+    application_vnd_openxmlformats_officedocument_presentationml_presentation=655427,
+    application_vnd_openxmlformats_officedocument_spreadsheetml_sheet=655428,
+    application_vnd_openxmlformats_officedocument_wordprocessingml_document=655429,
+    application_vnd_symbian_install=655430,
+    application_vnd_tcpdump_pcap=655431,
+    application_vnd_wap_wmlc=655432,
+    application_vnd_wap_wmlscriptc=655433,
+    application_vnd_xara=655434,
+    application_vocaltec_media_desc=655435,
+    application_vocaltec_media_file=655436,
+    application_warc=655437,
+    application_winhelp=655438,
+    application_wordperfect=655439,
+    application_wordperfect6_0=655440,
+    application_wordperfect6_1=655441,
+    application_x_123=655442,
+    application_x_7z_compressed=655443 | 0x10000000,
+    application_x_aim=655444,
+    application_x_apple_diskimage=655445,
+    application_x_arc=655446 | 0x10000000,
+    application_x_archive=655447,
+    application_x_atari_7800_rom=655448,
+    application_x_authorware_bin=655449,
+    application_x_authorware_map=655450,
+    application_x_authorware_seg=655451,
+    application_x_avira_qua=655452,
+    application_x_bcpio=655453,
+    application_x_bittorrent=655454,
+    application_x_bsh=655455,
+    application_x_bytecode_python=655456,
+    application_x_bzip=655457,
+    application_x_bzip2=655458 | 0x08000000,
+    application_x_cbr=655459,
+    application_x_cbz=655460 | 0x40000000,
+    application_x_cdlink=655461,
+    application_x_chat=655462,
+    application_x_chrome_extension=655463,
+    application_x_cocoa=655464,
+    application_x_conference=655465,
+    application_x_coredump=655466,
+    application_x_cpio=655467,
+    application_x_dbf=655468,
+    application_x_dbt=655469,
+    application_x_debian_package=655470,
+    application_x_deepv=655471,
+    application_x_director=655472,
+    application_x_dmp=655473,
+    application_x_dosdriver=655474,
+    application_x_dosexec=655475,
+    application_x_dvi=655476,
+    application_x_elc=655477,
     application_x_empty=1,
-    application_x_envoy=655463,
-    application_x_esrehber=655464,
-    application_x_excel=655465,
-    application_x_executable=655466,
-    application_x_font_sfn=655467,
-    application_x_font_ttf=655468 | 0x20000000,
-    application_x_freelance=655469,
-    application_x_git=655470,
-    application_x_gsp=655471,
-    application_x_gss=655472,
-    application_x_gtar=655473,
-    application_x_gzip=655474,
-    application_x_hdf=655475,
-    application_x_helpfile=655476,
-    application_x_httpd_imap=655477,
-    application_x_ima=655478,
-    application_x_innosetup=655479,
-    application_x_internett_signup=655480,
-    application_x_inventor=655481,
-    application_x_ip2=655482,
-    application_x_java_applet=655483,
-    application_x_java_commerce=655484,
-    application_x_java_image=655485,
-    application_x_java_keystore=655486,
-    application_x_kdelnk=655487,
-    application_x_koan=655488,
-    application_x_latex=655489,
-    application_x_livescreen=655490,
-    application_x_lotus=655491,
-    application_x_lzh=655492,
-    application_x_lzx=655493,
-    application_x_mach_binary=655494,
-    application_x_mach_executable=655495,
-    application_x_magic_cap_package_1_0=655496,
-    application_x_mathcad=655497,
-    application_x_meme=655498,
-    application_x_midi=655499,
-    application_x_mif=655500,
-    application_x_mix_transfer=655501,
-    application_x_mobipocket_ebook=655502,
-    application_x_ms_compress_szdd=655503,
-    application_x_ms_pdb=655504,
-    application_x_ms_reader=655505,
-    application_x_navi_animation=655506,
-    application_x_navidoc=655507,
-    application_x_navimap=655508,
-    application_x_navistyle=655509,
-    application_x_netcdf=655510,
-    application_x_newton_compatible_pkg=655511,
-    application_x_object=655512,
-    application_x_omc=655513,
-    application_x_omcdatamaker=655514,
-    application_x_omcregerator=655515,
-    application_x_pagemaker=655516,
-    application_x_pcl=655517,
-    application_x_pixclscript=655518,
-    application_x_pkcs7_certreqresp=655519,
-    application_x_pkcs7_signature=655520,
-    application_x_project=655521,
-    application_x_qpro=655522,
-    application_x_rar=655523,
-    application_x_rpm=655524,
-    application_x_sdp=655525,
-    application_x_sea=655526,
-    application_x_seelogo=655527,
-    application_x_setupscript=655528,
-    application_x_shar=655529,
-    application_x_sharedlib=655530,
-    application_x_shockwave_flash=655531,
-    application_x_sprite=655532,
-    application_x_sqlite3=655533,
-    application_x_sv4cpio=655534,
-    application_x_sv4crc=655535,
-    application_x_tar=655536,
-    application_x_tbook=655537,
-    application_x_tex_tfm=655538,
-    application_x_texinfo=655539,
-    application_x_ustar=655540,
-    application_x_visio=655541,
-    application_x_vnd_audioexplosion_mzz=655542,
-    application_x_vnd_ls_xpix=655543,
-    application_x_vrml=655544,
-    application_x_wais_source=655545,
-    application_x_wine_extension_ini=655546,
-    application_x_wintalk=655547,
-    application_x_world=655548,
-    application_x_wri=655549,
-    application_x_x509_ca_cert=655550,
-    application_x_xz=655551,
-    application_xml=655552,
-    application_zip=655553,
-    audio_it=458946,
-    audio_make=458947,
-    audio_mid=458948,
-    audio_midi=458949,
-    audio_mp4=458950,
-    audio_mpeg=458951,
-    audio_ogg=458952,
-    audio_s3m=458953,
-    audio_tsp_audio=458954,
-    audio_tsplayer=458955,
-    audio_vnd_qcelp=458956,
-    audio_voxware=458957,
-    audio_x_flac=458958,
-    audio_x_gsm=458959,
-    audio_x_jam=458960,
-    audio_x_liveaudio=458961,
-    audio_x_m4a=458962,
-    audio_x_midi=458963,
-    audio_x_mod=458964,
-    audio_x_mp4a_latm=458965,
-    audio_x_mpeg_3=458966,
-    audio_x_mpequrl=458967,
-    audio_x_nspaudio=458968,
-    audio_x_pn_realaudio=458969,
-    audio_x_psid=458970,
-    audio_x_realaudio=458971,
-    audio_x_twinvq=458972,
-    audio_x_twinvq_plugin=458973,
-    audio_x_voc=458974,
-    audio_x_wav=458975,
-    audio_xm=458976,
-    font_otf=327905 | 0x20000000,
-    font_sfnt=327906 | 0x20000000,
-    font_woff=327907 | 0x20000000,
-    font_woff2=327908 | 0x20000000,
-    image_cmu_raster=524517,
-    image_fif=524518,
-    image_florian=524519,
-    image_g3fax=524520,
-    image_gif=524521,
-    image_ief=524522,
-    image_jpeg=524523,
-    image_jutvision=524524,
-    image_naplps=524525,
-    image_pict=524526,
-    image_png=524527,
-    image_svg=524528 | 0x80000000,
-    image_svg_xml=524529 | 0x80000000,
-    image_tiff=524530,
-    image_vnd_adobe_photoshop=524531 | 0x80000000,
-    image_vnd_djvu=524532 | 0x80000000,
-    image_vnd_fpx=524533,
-    image_vnd_microsoft_icon=524534,
-    image_vnd_rn_realflash=524535,
-    image_vnd_rn_realpix=524536,
-    image_vnd_wap_wbmp=524537,
-    image_vnd_xiff=524538,
-    image_webp=524539,
-    image_x_cmu_raster=524540,
-    image_x_cur=524541,
-    image_x_dwg=524542,
-    image_x_eps=524543,
-    image_x_exr=524544,
-    image_x_icns=524545,
-    image_x_icon=524546 | 0x80000000,
-    image_x_jg=524547,
-    image_x_jps=524548,
-    image_x_ms_bmp=524549,
-    image_x_niff=524550,
-    image_x_pcx=524551,
-    image_x_pict=524552,
-    image_x_portable_bitmap=524553,
-    image_x_portable_graymap=524554,
-    image_x_portable_pixmap=524555,
-    image_x_quicktime=524556,
-    image_x_rgb=524557,
-    image_x_tga=524558,
-    image_x_tiff=524559,
-    image_x_xcf=524560 | 0x80000000,
-    image_x_xpixmap=524561 | 0x80000000,
-    image_x_xwindowdump=524562,
-    message_rfc822=196883,
-    model_vnd_dwf=65812,
-    model_vnd_gdl=65813,
-    model_vnd_gs_gdl=65814,
-    model_vrml=65815,
-    model_x_pov=65816,
-    text_asp=590105,
-    text_css=590106,
-    text_html=590107,
-    text_javascript=590108,
-    text_mcf=590109,
-    text_pascal=590110,
-    text_plain=590111,
-    text_richtext=590112,
-    text_scriplet=590113,
-    text_tab_separated_values=590114,
-    text_troff=590115,
-    text_uri_list=590116,
-    text_vnd_abc=590117,
-    text_vnd_fmi_flexstor=590118,
-    text_vnd_wap_wml=590119,
-    text_vnd_wap_wmlscript=590120,
-    text_webviewhtml=590121,
-    text_x_Algol68=590122,
-    text_x_asm=590123,
-    text_x_audiosoft_intra=590124,
-    text_x_awk=590125,
-    text_x_bcpl=590126,
-    text_x_c=590127,
-    text_x_c__=590128,
-    text_x_component=590129,
-    text_x_diff=590130,
-    text_x_fortran=590131,
-    text_x_java=590132,
-    text_x_la_asf=590133,
-    text_x_lisp=590134,
-    text_x_m=590135,
-    text_x_m4=590136,
-    text_x_makefile=590137,
-    text_x_msdos_batch=590138,
-    text_x_pascal=590139,
-    text_x_perl=590140,
-    text_x_php=590141,
-    text_x_po=590142,
-    text_x_python=590143,
-    text_x_ruby=590144,
-    text_x_sass=590145,
-    text_x_scss=590146,
-    text_x_server_parsed_html=590147,
-    text_x_setext=590148,
-    text_x_sgml=590149,
-    text_x_shellscript=590150,
-    text_x_speech=590151,
-    text_x_tcl=590152,
-    text_x_tex=590153,
-    text_x_uil=590154,
-    text_x_uuencode=590155,
-    text_x_vcalendar=590156,
-    text_x_vcard=590157,
-    text_xml=590158,
-    video_animaflex=393551,
-    video_avi=393552,
-    video_avs_video=393553,
-    video_mp4=393554,
-    video_mpeg=393555,
-    video_quicktime=393556,
-    video_vdo=393557,
-    video_vivo=393558,
-    video_vnd_rn_realvideo=393559,
-    video_vosaic=393560,
-    video_webm=393561,
-    video_x_amt_demorun=393562,
-    video_x_amt_showrun=393563,
-    video_x_atomic3d_feature=393564,
-    video_x_dl=393565,
-    video_x_dv=393566,
-    video_x_fli=393567,
-    video_x_flv=393568,
-    video_x_isvideo=393569,
-    video_x_jng=393570 | 0x80000000,
-    video_x_matroska=393571,
-    video_x_mng=393572,
-    video_x_motion_jpeg=393573,
-    video_x_ms_asf=393574,
-    video_x_msvideo=393575,
-    video_x_qtc=393576,
-    video_x_sgi_movie=393577,
+    application_x_envoy=655479,
+    application_x_esrehber=655480,
+    application_x_excel=655481,
+    application_x_executable=655482,
+    application_x_font_gdos=655483,
+    application_x_font_pf2=655484,
+    application_x_font_pfm=655485,
+    application_x_font_sfn=655486,
+    application_x_font_ttf=655487 | 0x20000000,
+    application_x_freelance=655488,
+    application_x_gamecube_rom=655489,
+    application_x_gdbm=655490,
+    application_x_gettext_translation=655491,
+    application_x_git=655492,
+    application_x_gsp=655493,
+    application_x_gss=655494,
+    application_x_gtar=655495,
+    application_x_gzip=655496,
+    application_x_hdf=655497,
+    application_x_helpfile=655498,
+    application_x_httpd_imap=655499,
+    application_x_ima=655500,
+    application_x_innosetup=655501,
+    application_x_internett_signup=655502,
+    application_x_inventor=655503,
+    application_x_ip2=655504,
+    application_x_java_applet=655505,
+    application_x_java_commerce=655506,
+    application_x_java_image=655507,
+    application_x_java_jmod=655508,
+    application_x_java_keystore=655509,
+    application_x_kdelnk=655510,
+    application_x_koan=655511,
+    application_x_latex=655512,
+    application_x_livescreen=655513,
+    application_x_lotus=655514,
+    application_x_lz4=655515 | 0x08000000,
+    application_x_lz4_json=655516,
+    application_x_lzh=655517,
+    application_x_lzh_compressed=655518,
+    application_x_lzip=655519 | 0x08000000,
+    application_x_lzma=655520 | 0x08000000,
+    application_x_lzop=655521 | 0x08000000,
+    application_x_lzx=655522,
+    application_x_mach_binary=655523,
+    application_x_mach_executable=655524,
+    application_x_magic_cap_package_1_0=655525,
+    application_x_mathcad=655526,
+    application_x_maxis_dbpf=655527,
+    application_x_meme=655528,
+    application_x_midi=655529,
+    application_x_mif=655530,
+    application_x_mix_transfer=655531,
+    application_x_mobipocket_ebook=655532,
+    application_x_ms_compress_szdd=655533,
+    application_x_ms_pdb=655534,
+    application_x_ms_reader=655535,
+    application_x_msaccess=655536,
+    application_x_navi_animation=655537,
+    application_x_navidoc=655538,
+    application_x_navimap=655539,
+    application_x_navistyle=655540,
+    application_x_nes_rom=655541,
+    application_x_netcdf=655542,
+    application_x_newton_compatible_pkg=655543,
+    application_x_nintendo_ds_rom=655544,
+    application_x_object=655545,
+    application_x_omc=655546,
+    application_x_omcdatamaker=655547,
+    application_x_omcregerator=655548,
+    application_x_pagemaker=655549,
+    application_x_pcl=655550,
+    application_x_pgp_keyring=655551,
+    application_x_pixclscript=655552,
+    application_x_pkcs7_certreqresp=655553,
+    application_x_pkcs7_signature=655554,
+    application_x_project=655555,
+    application_x_qpro=655556,
+    application_x_rar=655557 | 0x10000000,
+    application_x_rpm=655558,
+    application_x_sdp=655559,
+    application_x_sea=655560,
+    application_x_seelogo=655561,
+    application_x_setupscript=655562,
+    application_x_shar=655563,
+    application_x_sharedlib=655564,
+    application_x_shockwave_flash=655565,
+    application_x_snappy_framed=655566,
+    application_x_sprite=655567,
+    application_x_sqlite3=655568,
+    application_x_sv4cpio=655569,
+    application_x_sv4crc=655570,
+    application_x_tar=655571 | 0x10000000,
+    application_x_tbook=655572,
+    application_x_terminfo=655573,
+    application_x_terminfo2=655574,
+    application_x_tex_tfm=655575,
+    application_x_texinfo=655576,
+    application_x_ustar=655577,
+    application_x_visio=655578,
+    application_x_vnd_audioexplosion_mzz=655579,
+    application_x_vnd_ls_xpix=655580,
+    application_x_vrml=655581,
+    application_x_wais_source=655582,
+    application_x_wine_extension_ini=655583,
+    application_x_wintalk=655584,
+    application_x_world=655585,
+    application_x_wri=655586,
+    application_x_x509_ca_cert=655587,
+    application_x_xz=655588 | 0x08000000,
+    application_x_zip=655589,
+    application_x_zstd=655590 | 0x08000000,
+    application_xml=655591,
+    application_zip=655592 | 0x10000000,
+    application_zlib=655593,
+    audio_it=458986,
+    audio_make=458987,
+    audio_mid=458988,
+    audio_midi=458989,
+    audio_mp4=458990,
+    audio_mpeg=458991,
+    audio_ogg=458992,
+    audio_s3m=458993,
+    audio_tsp_audio=458994,
+    audio_tsplayer=458995,
+    audio_vnd_qcelp=458996,
+    audio_voxware=458997,
+    audio_x_aiff=458998,
+    audio_x_flac=458999,
+    audio_x_gsm=459000,
+    audio_x_hx_aac_adts=459001,
+    audio_x_jam=459002,
+    audio_x_liveaudio=459003,
+    audio_x_m4a=459004,
+    audio_x_midi=459005,
+    audio_x_mod=459006,
+    audio_x_mp4a_latm=459007,
+    audio_x_mpeg_3=459008,
+    audio_x_mpequrl=459009,
+    audio_x_nspaudio=459010,
+    audio_x_pn_realaudio=459011,
+    audio_x_psid=459012,
+    audio_x_realaudio=459013,
+    audio_x_twinvq=459014,
+    audio_x_twinvq_plugin=459015,
+    audio_x_voc=459016,
+    audio_x_wav=459017,
+    audio_xm=459018,
+    font_otf=327947 | 0x20000000,
+    font_sfnt=327948 | 0x20000000,
+    font_woff=327949 | 0x20000000,
+    font_woff2=327950 | 0x20000000,
+    image_cmu_raster=524559,
+    image_fif=524560,
+    image_florian=524561,
+    image_g3fax=524562,
+    image_gif=524563,
+    image_heic=524564,
+    image_ief=524565,
+    image_jpeg=524566,
+    image_jutvision=524567,
+    image_naplps=524568,
+    image_pict=524569,
+    image_png=524570,
+    image_svg=524571 | 0x80000000,
+    image_svg_xml=524572 | 0x80000000,
+    image_tiff=524573,
+    image_vnd_adobe_photoshop=524574 | 0x80000000,
+    image_vnd_djvu=524575 | 0x80000000,
+    image_vnd_fpx=524576,
+    image_vnd_microsoft_icon=524577,
+    image_vnd_rn_realflash=524578,
+    image_vnd_rn_realpix=524579,
+    image_vnd_wap_wbmp=524580,
+    image_vnd_xiff=524581,
+    image_webp=524582,
+    image_wmf=524583,
+    image_x_3ds=524584,
+    image_x_cmu_raster=524585,
+    image_x_cur=524586,
+    image_x_dwg=524587,
+    image_x_eps=524588,
+    image_x_exr=524589,
+    image_x_gem=524590,
+    image_x_icns=524591,
+    image_x_icon=524592 | 0x80000000,
+    image_x_jg=524593,
+    image_x_jps=524594,
+    image_x_ms_bmp=524595,
+    image_x_niff=524596,
+    image_x_pcx=524597,
+    image_x_pict=524598,
+    image_x_portable_bitmap=524599,
+    image_x_portable_graymap=524600,
+    image_x_portable_pixmap=524601,
+    image_x_quicktime=524602,
+    image_x_rgb=524603,
+    image_x_tga=524604,
+    image_x_tiff=524605,
+    image_x_win_bitmap=524606,
+    image_x_xcf=524607 | 0x80000000,
+    image_x_xpixmap=524608 | 0x80000000,
+    image_x_xwindowdump=524609,
+    message_news=196930,
+    message_rfc822=196931,
+    model_vnd_dwf=65860,
+    model_vnd_gdl=65861,
+    model_vnd_gs_gdl=65862,
+    model_vrml=65863,
+    model_x_pov=65864,
+    text_PGP=590153,
+    text_asp=590154,
+    text_css=590155,
+    text_html=590156,
+    text_javascript=590157,
+    text_mcf=590158,
+    text_pascal=590159,
+    text_plain=590160,
+    text_richtext=590161,
+    text_rtf=590162,
+    text_scriplet=590163,
+    text_tab_separated_values=590164,
+    text_troff=590165,
+    text_uri_list=590166,
+    text_vnd_abc=590167,
+    text_vnd_fmi_flexstor=590168,
+    text_vnd_wap_wml=590169,
+    text_vnd_wap_wmlscript=590170,
+    text_webviewhtml=590171,
+    text_x_Algol68=590172,
+    text_x_asm=590173,
+    text_x_audiosoft_intra=590174,
+    text_x_awk=590175,
+    text_x_bcpl=590176,
+    text_x_c=590177,
+    text_x_c__=590178,
+    text_x_component=590179,
+    text_x_diff=590180,
+    text_x_fortran=590181,
+    text_x_java=590182,
+    text_x_la_asf=590183,
+    text_x_lisp=590184,
+    text_x_m=590185,
+    text_x_m4=590186,
+    text_x_makefile=590187,
+    text_x_ms_regedit=590188,
+    text_x_msdos_batch=590189,
+    text_x_objective_c=590190,
+    text_x_pascal=590191,
+    text_x_perl=590192,
+    text_x_php=590193,
+    text_x_po=590194,
+    text_x_python=590195,
+    text_x_ruby=590196,
+    text_x_sass=590197,
+    text_x_scss=590198,
+    text_x_server_parsed_html=590199,
+    text_x_setext=590200,
+    text_x_sgml=590201,
+    text_x_shellscript=590202,
+    text_x_speech=590203,
+    text_x_tcl=590204,
+    text_x_tex=590205,
+    text_x_uil=590206,
+    text_x_uuencode=590207,
+    text_x_vcalendar=590208,
+    text_x_vcard=590209,
+    text_xml=590210,
+    video_MP2T=393603,
+    video_animaflex=393604,
+    video_avi=393605,
+    video_avs_video=393606,
+    video_mp4=393607,
+    video_mpeg=393608,
+    video_quicktime=393609,
+    video_vdo=393610,
+    video_vivo=393611,
+    video_vnd_rn_realvideo=393612,
+    video_vosaic=393613,
+    video_webm=393614,
+    video_x_amt_demorun=393615,
+    video_x_amt_showrun=393616,
+    video_x_atomic3d_feature=393617,
+    video_x_dl=393618,
+    video_x_dv=393619,
+    video_x_fli=393620,
+    video_x_flv=393621,
+    video_x_isvideo=393622,
+    video_x_jng=393623 | 0x80000000,
+    video_x_m4v=393624,
+    video_x_matroska=393625,
+    video_x_mng=393626,
+    video_x_motion_jpeg=393627,
+    video_x_ms_asf=393628,
+    video_x_msvideo=393629,
+    video_x_qtc=393630,
+    video_x_sgi_movie=393631,
+    x_epoc_x_sisx_app=721312,
 };
 char *mime_get_mime_text(unsigned int mime_id) {switch (mime_id) {
 case application_arj: return "application/arj";
@@ -625,6 +680,7 @@ case text_mcf: return "text/mcf";
 case text_pascal: return "text/pascal";
 case text_plain: return "text/plain";
 case text_richtext: return "text/richtext";
+case text_rtf: return "text/rtf";
 case text_scriplet: return "text/scriplet";
 case text_x_awk: return "text/x-awk";
 case video_x_jng: return "video/x-jng";
@@ -730,6 +786,60 @@ case application_x_wine_extension_ini: return "application/x-wine-extension-ini"
 case application_x_cbz: return "application/x-cbz";
 case application_x_cbr: return "application/x-cbr";
 case application_x_ms_compress_szdd: return "application/x-ms-compress-szdd";
+case application_x_atari_7800_rom: return "application/x-atari-7800-rom";
+case application_x_nes_rom: return "application/x-nes-rom";
+case application_x_font_pfm: return "application/x-font-pfm";
+case application_x_gettext_translation: return "application/x-gettext-translation";
+case image_wmf: return "image/wmf";
+case application_pgp_keys: return "application/pgp-keys";
+case image_x_3ds: return "image/x-3ds";
+case application_x_lz4: return "application/x-lz4";
+case application_vnd_openxmlformats_officedocument_presentationml_presentation: return "application/vnd.openxmlformats-officedocument.presentationml.presentation";
+case application_vnd_oasis_opendocument_presentation: return "application/vnd.oasis.opendocument.presentation";
+case application_x_msaccess: return "application/x-msaccess";
+case application_vnd_oasis_opendocument_spreadsheet: return "application/vnd.oasis.opendocument.spreadsheet";
+case audio_x_aiff: return "audio/x-aiff";
+case text_x_ms_regedit: return "text/x-ms-regedit";
+case application_x_gamecube_rom: return "application/x-gamecube-rom";
+case application_x_nintendo_ds_rom: return "application/x-nintendo-ds-rom";
+case text_x_objective_c: return "text/x-objective-c";
+case application_x_font_gdos: return "application/x-font-gdos";
+case application_x_apple_diskimage: return "application/x-apple-diskimage";
+case application_x_zstd: return "application/x-zstd";
+case video_x_m4v: return "video/x-m4v";
+case message_news: return "message/news";
+case application_vnd_symbian_install: return "application/vnd.symbian.install";
+case application_x_lzh_compressed: return "application/x-lzh-compressed";
+case application_x_dosdriver: return "application/x-dosdriver";
+case application_vnd_tcpdump_pcap: return "application/vnd.tcpdump.pcap";
+case x_epoc_x_sisx_app: return "x-epoc/x-sisx-app";
+case application_x_avira_qua: return "application/x-avira-qua";
+case video_MP2T: return "video/MP2T";
+case application_x_snappy_framed: return "application/x-snappy-framed";
+case application_x_lz4_json: return "application/x-lz4+json";
+case application_x_dmp: return "application/x-dmp";
+case application_zlib: return "application/zlib";
+case application_x_pgp_keyring: return "application/x-pgp-keyring";
+case application_x_gdbm: return "application/x-gdbm";
+case application_x_font_pf2: return "application/x-font-pf2";
+case application_x_zip: return "application/x-zip";
+case application_x_coredump: return "application/x-coredump";
+case application_x_java_jmod: return "application/x-java-jmod";
+case application_x_terminfo: return "application/x-terminfo";
+case application_x_terminfo2: return "application/x-terminfo2";
+case application_x_arc: return "application/x-arc";
+case application_vnd_lotus_1_2_3: return "application/vnd.lotus-1-2-3";
+case image_x_win_bitmap: return "image/x-win-bitmap";
+case application_x_maxis_dbpf: return "application/x-maxis-dbpf";
+case text_PGP: return "text/PGP";
+case audio_x_hx_aac_adts: return "audio/x-hx-aac-adts";
+case application_x_chrome_extension: return "application/x-chrome-extension";
+case image_heic: return "image/heic";
+case image_x_gem: return "image/x-gem";
+case application_x_lzma: return "application/x-lzma";
+case application_warc: return "application/warc";
+case application_x_lzip: return "application/x-lzip";
+case application_x_lzop: return "application/x-lzop";
 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);
@@ -1080,6 +1190,9 @@ g_hash_table_insert(ext_table, "d", (gpointer)text_plain);
 g_hash_table_insert(ext_table, "cs", (gpointer)text_plain);
 g_hash_table_insert(ext_table, "hpp", (gpointer)text_plain);
 g_hash_table_insert(ext_table, "srt", (gpointer)text_plain);
+g_hash_table_insert(ext_table, "nfo", (gpointer)text_plain);
+g_hash_table_insert(ext_table, "sfv", (gpointer)text_plain);
+g_hash_table_insert(ext_table, "m3u", (gpointer)text_plain);
 g_hash_table_insert(ext_table, "rt", (gpointer)text_richtext);
 g_hash_table_insert(ext_table, "rtf", (gpointer)text_richtext);
 g_hash_table_insert(ext_table, "rtx", (gpointer)text_richtext);
@@ -1097,7 +1210,7 @@ g_hash_table_insert(ext_table, "ms", (gpointer)text_troff);
 g_hash_table_insert(ext_table, "roff", (gpointer)text_troff);
 g_hash_table_insert(ext_table, "t", (gpointer)text_troff);
 g_hash_table_insert(ext_table, "tr", (gpointer)text_troff);
-g_hash_table_insert(ext_table, "uni", (gpointer)text_uri_list);
+g_hash_table_insert(ext_table, "uji", (gpointer)text_uri_list);
 g_hash_table_insert(ext_table, "unis", (gpointer)text_uri_list);
 g_hash_table_insert(ext_table, "uri", (gpointer)text_uri_list);
 g_hash_table_insert(ext_table, "uris", (gpointer)text_uri_list);
@@ -1211,6 +1324,31 @@ g_hash_table_insert(ext_table, "hlp", (gpointer)application_winhelp);
 g_hash_table_insert(ext_table, "cbz", (gpointer)application_x_cbz);
 g_hash_table_insert(ext_table, "cbr", (gpointer)application_x_cbr);
 g_hash_table_insert(ext_table, "fon", (gpointer)application_x_ms_compress_szdd);
+g_hash_table_insert(ext_table, "a78", (gpointer)application_x_atari_7800_rom);
+g_hash_table_insert(ext_table, "nes", (gpointer)application_x_nes_rom);
+g_hash_table_insert(ext_table, "pfm", (gpointer)application_x_font_pfm);
+g_hash_table_insert(ext_table, "3ds", (gpointer)image_x_3ds);
+g_hash_table_insert(ext_table, "lz4", (gpointer)application_x_lz4);
+g_hash_table_insert(ext_table, "pptx", (gpointer)application_vnd_openxmlformats_officedocument_presentationml_presentation);
+g_hash_table_insert(ext_table, "odp", (gpointer)application_vnd_oasis_opendocument_presentation);
+g_hash_table_insert(ext_table, "accdb", (gpointer)application_x_msaccess);
+g_hash_table_insert(ext_table, "ods", (gpointer)application_vnd_oasis_opendocument_spreadsheet);
+g_hash_table_insert(ext_table, "aiff", (gpointer)audio_x_aiff);
+g_hash_table_insert(ext_table, "aif", (gpointer)audio_x_aiff);
+g_hash_table_insert(ext_table, "reg", (gpointer)text_x_ms_regedit);
+g_hash_table_insert(ext_table, "zst", (gpointer)application_x_zstd);
+g_hash_table_insert(ext_table, "m4v", (gpointer)video_x_m4v);
+g_hash_table_insert(ext_table, "pcap", (gpointer)application_vnd_tcpdump_pcap);
+g_hash_table_insert(ext_table, "jsonlz4", (gpointer)application_x_lz4_json);
+g_hash_table_insert(ext_table, "dmp", (gpointer)application_x_dmp);
+g_hash_table_insert(ext_table, "z", (gpointer)application_zlib);
+g_hash_table_insert(ext_table, "pf2", (gpointer)application_x_font_pf2);
+g_hash_table_insert(ext_table, "jmod", (gpointer)application_x_java_jmod);
+g_hash_table_insert(ext_table, "heic", (gpointer)image_heic);
+g_hash_table_insert(ext_table, "lzma", (gpointer)application_x_lzma);
+g_hash_table_insert(ext_table, "warc", (gpointer)application_warc);
+g_hash_table_insert(ext_table, "lz", (gpointer)application_x_lzip);
+g_hash_table_insert(ext_table, "lzo", (gpointer)application_x_lzop);
 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);
@@ -1469,6 +1607,7 @@ g_hash_table_insert(mime_table, "text/mcf", (gpointer)text_mcf);
 g_hash_table_insert(mime_table, "text/pascal", (gpointer)text_pascal);
 g_hash_table_insert(mime_table, "text/plain", (gpointer)text_plain);
 g_hash_table_insert(mime_table, "text/richtext", (gpointer)text_richtext);
+g_hash_table_insert(mime_table, "text/rtf", (gpointer)text_rtf);
 g_hash_table_insert(mime_table, "text/scriplet", (gpointer)text_scriplet);
 g_hash_table_insert(mime_table, "text/x-awk", (gpointer)text_x_awk);
 g_hash_table_insert(mime_table, "video/x-jng", (gpointer)video_x_jng);
@@ -1574,5 +1713,59 @@ g_hash_table_insert(mime_table, "application/x-wine-extension-ini", (gpointer)ap
 g_hash_table_insert(mime_table, "application/x-cbz", (gpointer)application_x_cbz);
 g_hash_table_insert(mime_table, "application/x-cbr", (gpointer)application_x_cbr);
 g_hash_table_insert(mime_table, "application/x-ms-compress-szdd", (gpointer)application_x_ms_compress_szdd);
+g_hash_table_insert(mime_table, "application/x-atari-7800-rom", (gpointer)application_x_atari_7800_rom);
+g_hash_table_insert(mime_table, "application/x-nes-rom", (gpointer)application_x_nes_rom);
+g_hash_table_insert(mime_table, "application/x-font-pfm", (gpointer)application_x_font_pfm);
+g_hash_table_insert(mime_table, "application/x-gettext-translation", (gpointer)application_x_gettext_translation);
+g_hash_table_insert(mime_table, "image/wmf", (gpointer)image_wmf);
+g_hash_table_insert(mime_table, "application/pgp-keys", (gpointer)application_pgp_keys);
+g_hash_table_insert(mime_table, "image/x-3ds", (gpointer)image_x_3ds);
+g_hash_table_insert(mime_table, "application/x-lz4", (gpointer)application_x_lz4);
+g_hash_table_insert(mime_table, "application/vnd.openxmlformats-officedocument.presentationml.presentation", (gpointer)application_vnd_openxmlformats_officedocument_presentationml_presentation);
+g_hash_table_insert(mime_table, "application/vnd.oasis.opendocument.presentation", (gpointer)application_vnd_oasis_opendocument_presentation);
+g_hash_table_insert(mime_table, "application/x-msaccess", (gpointer)application_x_msaccess);
+g_hash_table_insert(mime_table, "application/vnd.oasis.opendocument.spreadsheet", (gpointer)application_vnd_oasis_opendocument_spreadsheet);
+g_hash_table_insert(mime_table, "audio/x-aiff", (gpointer)audio_x_aiff);
+g_hash_table_insert(mime_table, "text/x-ms-regedit", (gpointer)text_x_ms_regedit);
+g_hash_table_insert(mime_table, "application/x-gamecube-rom", (gpointer)application_x_gamecube_rom);
+g_hash_table_insert(mime_table, "application/x-nintendo-ds-rom", (gpointer)application_x_nintendo_ds_rom);
+g_hash_table_insert(mime_table, "text/x-objective-c", (gpointer)text_x_objective_c);
+g_hash_table_insert(mime_table, "application/x-font-gdos", (gpointer)application_x_font_gdos);
+g_hash_table_insert(mime_table, "application/x-apple-diskimage", (gpointer)application_x_apple_diskimage);
+g_hash_table_insert(mime_table, "application/x-zstd", (gpointer)application_x_zstd);
+g_hash_table_insert(mime_table, "video/x-m4v", (gpointer)video_x_m4v);
+g_hash_table_insert(mime_table, "message/news", (gpointer)message_news);
+g_hash_table_insert(mime_table, "application/vnd.symbian.install", (gpointer)application_vnd_symbian_install);
+g_hash_table_insert(mime_table, "application/x-lzh-compressed", (gpointer)application_x_lzh_compressed);
+g_hash_table_insert(mime_table, "application/x-dosdriver", (gpointer)application_x_dosdriver);
+g_hash_table_insert(mime_table, "application/vnd.tcpdump.pcap", (gpointer)application_vnd_tcpdump_pcap);
+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-avira-qua", (gpointer)application_x_avira_qua);
+g_hash_table_insert(mime_table, "video/MP2T", (gpointer)video_MP2T);
+g_hash_table_insert(mime_table, "application/x-snappy-framed", (gpointer)application_x_snappy_framed);
+g_hash_table_insert(mime_table, "application/x-lz4+json", (gpointer)application_x_lz4_json);
+g_hash_table_insert(mime_table, "application/x-dmp", (gpointer)application_x_dmp);
+g_hash_table_insert(mime_table, "application/zlib", (gpointer)application_zlib);
+g_hash_table_insert(mime_table, "application/x-pgp-keyring", (gpointer)application_x_pgp_keyring);
+g_hash_table_insert(mime_table, "application/x-gdbm", (gpointer)application_x_gdbm);
+g_hash_table_insert(mime_table, "application/x-font-pf2", (gpointer)application_x_font_pf2);
+g_hash_table_insert(mime_table, "application/x-zip", (gpointer)application_x_zip);
+g_hash_table_insert(mime_table, "application/x-coredump", (gpointer)application_x_coredump);
+g_hash_table_insert(mime_table, "application/x-java-jmod", (gpointer)application_x_java_jmod);
+g_hash_table_insert(mime_table, "application/x-terminfo", (gpointer)application_x_terminfo);
+g_hash_table_insert(mime_table, "application/x-terminfo2", (gpointer)application_x_terminfo2);
+g_hash_table_insert(mime_table, "application/x-arc", (gpointer)application_x_arc);
+g_hash_table_insert(mime_table, "application/vnd.lotus-1-2-3", (gpointer)application_vnd_lotus_1_2_3);
+g_hash_table_insert(mime_table, "image/x-win-bitmap", (gpointer)image_x_win_bitmap);
+g_hash_table_insert(mime_table, "application/x-maxis-dbpf", (gpointer)application_x_maxis_dbpf);
+g_hash_table_insert(mime_table, "text/PGP", (gpointer)text_PGP);
+g_hash_table_insert(mime_table, "audio/x-hx-aac-adts", (gpointer)audio_x_hx_aac_adts);
+g_hash_table_insert(mime_table, "application/x-chrome-extension", (gpointer)application_x_chrome_extension);
+g_hash_table_insert(mime_table, "image/heic", (gpointer)image_heic);
+g_hash_table_insert(mime_table, "image/x-gem", (gpointer)image_x_gem);
+g_hash_table_insert(mime_table, "application/x-lzma", (gpointer)application_x_lzma);
+g_hash_table_insert(mime_table, "application/warc", (gpointer)application_warc);
+g_hash_table_insert(mime_table, "application/x-lzip", (gpointer)application_x_lzip);
+g_hash_table_insert(mime_table, "application/x-lzop", (gpointer)application_x_lzop);
 return mime_table;}
 #endif

src/parsing/parse.c

@@ -1,9 +1,32 @@
+#include <src/ctx.h>
 #include "src/sist.h"
 #include "src/ctx.h"
 
-__thread magic_t Magic;
+__thread magic_t Magic = NULL;
 
-void *read_all(parse_job_t *job, const char *buf, int bytes_read, int *fd) {
+int fs_read(struct vfile *f, void *buf, size_t size) {
+
+    if (f->fd == -1) {
+        f->fd = open(f->filepath, O_RDONLY);
+        if (f->fd == -1) {
+            perror("open");
+            printf("%s\n", f->filepath);
+            return -1;
+        }
+    }
+
+    return read(f->fd, buf, size);
+}
+
+#define CLOSE_FILE(f) if (f.close != NULL) {f.close(&f);};
+
+void fs_close(struct vfile *f) {
+    if (f->fd != -1) {
+        close(f->fd);
+    }
+}
+
+void *read_all(parse_job_t *job, const char *buf, int bytes_read) {
 
     void *full_buf;
 
@@ -11,20 +34,13 @@ void *read_all(parse_job_t *job, const char *buf, int bytes_read, int *fd) {
         full_buf = malloc(job->info.st_size);
         memcpy(full_buf, buf, job->info.st_size);
     } else {
-        if (*fd == -1) {
-            *fd = open(job->filepath, O_RDONLY);
-            if (*fd == -1) {
-                perror("open");
-                printf("%s\n", job->filepath);
-                free(job);
-                return NULL;
-            }
-        }
         full_buf = malloc(job->info.st_size);
         memcpy(full_buf, buf, bytes_read);
-        int ret = read(*fd, full_buf + bytes_read, job->info.st_size - bytes_read);
+
+        int ret = job->vfile.read(&job->vfile, full_buf + bytes_read, job->info.st_size - bytes_read);
         if (ret == -1) {
             perror("read");
+            return NULL;
         }
     }
 
@@ -36,15 +52,14 @@ void parse(void *arg) {
     parse_job_t *job = arg;
     document_t doc;
 
-    if (incremental_get(ScanCtx.original_table, job->info.st_ino) == job->info.st_mtim.tv_sec) {
+    int inc_ts = incremental_get(ScanCtx.original_table, job->info.st_ino);
+    if (inc_ts != 0 && inc_ts == job->info.st_mtim.tv_sec) {
         incremental_mark_file_for_copy(ScanCtx.copy_table, job->info.st_ino);
-        free(job);
         return;
     }
 
     if (Magic == NULL) {
         Magic = magic_open(MAGIC_MIME_TYPE);
-        magic_load(Magic, NULL);
     }
 
     doc.filepath = job->filepath;
@@ -62,29 +77,25 @@ void parse(void *arg) {
 
     if (job->info.st_size == 0) {
         doc.mime = MIME_EMPTY;
-    } else if (*(job->filepath + job->ext) != '\0') {
+    } else if (*(job->filepath + job->ext) != '\0' && (job->ext - job->base != 1)) {
         doc.mime = mime_get_mime_by_ext(ScanCtx.ext_table, job->filepath + job->ext);
     }
 
-    int fd = -1;
     int bytes_read = 0;
 
     if (doc.mime == 0) {
         // Get mime type with libmagic
-        fd = open(job->filepath, O_RDONLY);
-        if (fd == -1) {
-            perror("open");
-            free(job);
+        bytes_read = job->vfile.read(&job->vfile, buf, PARSE_BUF_SIZE);
+        if (bytes_read == -1) {
+            CLOSE_FILE(job->vfile)
             return;
         }
 
-        bytes_read = read(fd, buf, PARSE_BUF_SIZE);
-
         const char *magic_mime_str = magic_buffer(Magic, buf, bytes_read);
         if (magic_mime_str != NULL) {
             doc.mime = mime_get_mime_by_string(ScanCtx.mime_table, magic_mime_str);
             if (doc.mime == 0) {
-                fprintf(stderr, "Couldn't find mime %s, %s!\n", magic_mime_str, job->filepath + job->base);
+                fprintf(stderr, "Couldn't find mime %s, %s\n", magic_mime_str, job->filepath + job->base);
             }
         }
     }
@@ -93,34 +104,53 @@ void parse(void *arg) {
 
     if (!(SHOULD_PARSE(doc.mime))) {
 
-    } else if ((mmime == MimeVideo && doc.size >= MIN_VIDEO_SIZE) || mmime == MimeAudio || mmime == MimeImage) {
-        parse_media(job->filepath, &doc);
+    } else if ((mmime == MimeVideo && doc.size >= MIN_VIDEO_SIZE) ||
+               (mmime == MimeImage && doc.size >= MIN_IMAGE_SIZE) || mmime == MimeAudio) {
+
+        if (job->vfile.is_fs_file) {
+            parse_media_filename(job->filepath, &doc);
+        } else {
+            parse_media_vfile(&job->vfile, &doc);
+        }
 
     } else if (IS_PDF(doc.mime)) {
-        void *pdf_buf = read_all(job, (char *) buf, bytes_read, &fd);
+        void *pdf_buf = read_all(job, (char *) buf, bytes_read);
         parse_pdf(pdf_buf, doc.size, &doc);
 
-        if (pdf_buf != buf) {
+        if (pdf_buf != buf && pdf_buf != NULL) {
             free(pdf_buf);
         }
 
     } else if (mmime == MimeText && ScanCtx.content_size > 0) {
-        parse_text(bytes_read, &fd, (char *) buf, &doc);
+        parse_text(bytes_read, &job->vfile, (char *) buf, &doc);
 
     } else if (IS_FONT(doc.mime)) {
-        void *font_buf = read_all(job, (char *) buf, bytes_read, &fd);
+        void *font_buf = read_all(job, (char *) buf, bytes_read);
         parse_font(font_buf, doc.size, &doc);
 
-        if (font_buf != buf) {
+        if (font_buf != buf && font_buf != NULL) {
             free(font_buf);
         }
+    } else if (
+            ScanCtx.archive_mode != ARC_MODE_SKIP && (
+                    IS_ARC(doc.mime) ||
+                    (IS_ARC_FILTER(doc.mime) && should_parse_filtered_file(doc.filepath, doc.ext))
+            )) {
+        parse_archive(&job->vfile, &doc);
+    }
+
+    //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->strval, tmp);
+        APPEND_META((&doc), meta_parent)
     }
 
     write_document(&doc);
 
-    if (fd != -1) {
-        close(fd);
-    }
-
-    free(job);
+    CLOSE_FILE(job->vfile)
 }

src/parsing/parse.h

@@ -5,6 +5,9 @@
 
 #define PARSE_BUF_SIZE 4096
 
+int fs_read(struct vfile *f, void *buf, size_t size);
+void fs_close(struct vfile *f);
+
 void parse(void *arg);
 
 #endif

src/parsing/pdf.c

@@ -1,10 +1,22 @@
-#include <src/ctx.h>
 #include "pdf.h"
 #include "src/ctx.h"
 
 fz_page *render_cover(fz_context *ctx, document_t *doc, fz_document *fzdoc) {
 
-    fz_page *cover = fz_load_page(ctx, fzdoc, 0);
+    int err = 0;
+    fz_page *cover = NULL;
+
+    fz_var(cover);
+    fz_try(ctx)
+        cover = fz_load_page(ctx, fzdoc, 0);
+    fz_catch(ctx)
+        err = 1;
+
+    if (err != 0) {
+        fz_drop_page(ctx, cover);
+        return NULL;
+    }
+
     fz_rect bounds = fz_bound_page(ctx, cover);
 
     float scale;
@@ -24,24 +36,49 @@ fz_page *render_cover(fz_context *ctx, document_t *doc, fz_document *fzdoc) {
     fz_clear_pixmap_with_value(ctx, pixmap, 0xFF);
     fz_device *dev = fz_new_draw_device(ctx, m, pixmap);
 
-    pthread_mutex_lock(&ScanCtx.mupdf_mu);
+    fz_var(err);
     fz_try(ctx)
+    {
+        pthread_mutex_lock(&ScanCtx.mupdf_mu);
         fz_run_page(ctx, cover, dev, fz_identity, NULL);
+    }
     fz_always(ctx)
+    {
+        fz_close_device(ctx, dev);
+        fz_drop_device(ctx, dev);
         pthread_mutex_unlock(&ScanCtx.mupdf_mu);
+    }
     fz_catch(ctx)
-        fz_rethrow(ctx);
+        err = ctx->error.errcode;
 
-    fz_drop_device(ctx, dev);
+    if (err != 0) {
+        fz_drop_page(ctx, cover);
+        fz_drop_pixmap(ctx, pixmap);
+        return NULL;
+    }
 
-    fz_buffer *fzbuf = fz_new_buffer_from_pixmap_as_png(ctx, pixmap, fz_default_color_params);
-    unsigned char *tn_buf;
-    size_t tn_len = fz_buffer_storage(ctx, fzbuf, &tn_buf);
+    fz_buffer *fzbuf = NULL;
+    fz_var(fzbuf);
+    fz_var(err);
 
-    store_write(ScanCtx.index.store, (char *) doc->uuid, sizeof(doc->uuid), (char *) tn_buf, tn_len);
+    fz_try(ctx)
+        fzbuf = fz_new_buffer_from_pixmap_as_png(ctx, pixmap, fz_default_color_params);
+    fz_catch(ctx)
+        err = ctx->error.errcode;
+
+    if (err == 0) {
+        unsigned char *tn_buf;
+        size_t tn_len = fz_buffer_storage(ctx, fzbuf, &tn_buf);
+        store_write(ScanCtx.index.store, (char *) doc->uuid, sizeof(doc->uuid), (char *) tn_buf, tn_len);
+    }
 
-    fz_drop_pixmap(ctx, pixmap);
     fz_drop_buffer(ctx, fzbuf);
+    fz_drop_pixmap(ctx, pixmap);
+
+    if (err != 0) {
+        fz_drop_page(ctx, cover);
+        return NULL;
+    }
 
     return cover;
 }
@@ -49,113 +86,190 @@ fz_page *render_cover(fz_context *ctx, document_t *doc, fz_document *fzdoc) {
 void fz_noop_callback(__attribute__((unused)) void *user, __attribute__((unused)) const char *message) {}
 
 
+void init_ctx(fz_context *ctx) {
+    fz_disable_icc(ctx);
+    fz_register_document_handlers(ctx);
+    ctx->warn.print = fz_noop_callback;
+    ctx->error.print = fz_noop_callback;
+}
+
+int read_stext_block(fz_stext_block *block, text_buffer_t *tex) {
+    if (block->type != FZ_STEXT_BLOCK_TEXT) {
+        return 0;
+    }
+
+    fz_stext_line *line = block->u.t.first_line;
+    while (line != NULL) {
+        fz_stext_char *c = line->first_char;
+        while (c != NULL) {
+            if (text_buffer_append_char(tex, c->c) == TEXT_BUF_FULL) {
+                return TEXT_BUF_FULL;
+            }
+            c = c->next;
+        }
+        line = line->next;
+    }
+    return 0;
+}
+
 void parse_pdf(void *buf, size_t buf_len, document_t *doc) {
 
+    if (buf == NULL) {
+        return;
+    }
+
     static int mu_is_initialized = 0;
     if (!mu_is_initialized) {
         pthread_mutex_init(&ScanCtx.mupdf_mu, NULL);
         mu_is_initialized = 1;
     }
     fz_context *ctx = fz_new_context(NULL, NULL, FZ_STORE_UNLIMITED);
-    fz_stream *stream = NULL;
-    fz_document *fzdoc = NULL;
 
-    fz_var(stream);
+    init_ctx(ctx);
+
+    int err = 0;
+
+    fz_document *fzdoc = NULL;
+    fz_stream *stream = NULL;
     fz_var(fzdoc);
+    fz_var(stream);
+    fz_var(err);
 
     fz_try(ctx)
     {
-        fz_disable_icc(ctx);
-        fz_register_document_handlers(ctx);
-
-        //disable warnings
-        ctx->warn.print = fz_noop_callback;
-        ctx->error.print = fz_noop_callback;
-
         stream = fz_open_memory(ctx, buf, buf_len);
         fzdoc = fz_open_document_with_stream(ctx, mime_get_mime_text(doc->mime), stream);
+    }
+    fz_catch(ctx)
+        err = ctx->error.errcode;
 
-        char title[4096] = {'\0',};
+    if (err) {
+        fz_drop_stream(ctx, stream);
+        fz_drop_document(ctx, fzdoc);
+        fz_drop_context(ctx);
+        return;
+    }
+
+    char title[4096] = {'\0',};
+    fz_try(ctx)
         fz_lookup_metadata(ctx, fzdoc, FZ_META_INFO_TITLE, title, sizeof(title));
-        printf("Title: %s\n", title); //todo rmv
+    fz_catch(ctx)
+        ;
 
-        if (strlen(title) > 0) {
-            meta_line_t *meta_content = malloc(sizeof(meta_line_t) + strlen(title) + 1);
-            meta_content->key = MetaTitle;
-            strcpy(meta_content->strval, title);
-            APPEND_META(doc, meta_content)
-        }
+    if (strlen(title) > 0) {
+        meta_line_t *meta_content = malloc(sizeof(meta_line_t) + strlen(title));
+        meta_content->key = MetaTitle;
+        strcpy(meta_content->strval, title);
+        APPEND_META(doc, meta_content)
+    }
 
-        int page_count = fz_count_pages(ctx, fzdoc);
+    int page_count = -1;
+    fz_var(err);
+    fz_try(ctx)
+        page_count = fz_count_pages(ctx, fzdoc);
+    fz_catch(ctx)
+        err = ctx->error.errcode;
 
-        fz_page *cover = render_cover(ctx, doc, fzdoc);
+    if (err) {
+        fz_drop_stream(ctx, stream);
+        fz_drop_document(ctx, fzdoc);
+        fz_drop_context(ctx);
+        return;
+    }
 
-        fz_stext_options opts;
+    fz_page *cover = NULL;
+    if (ScanCtx.tn_size > 0) {
+        cover = render_cover(ctx, doc, fzdoc);
+    } else {
+        fz_var(cover);
+        fz_try(ctx)
+            cover = fz_load_page(ctx, fzdoc, 0);
+        fz_catch(ctx)
+            cover = NULL;
+    }
 
+    if (cover == NULL) {
+        fz_drop_stream(ctx, stream);
+        fz_drop_document(ctx, fzdoc);
+        fz_drop_context(ctx);
+        return;
+    }
+
+    if (ScanCtx.content_size > 0) {
+        fz_stext_options opts = {0};
         text_buffer_t text_buf = text_buffer_create(ScanCtx.content_size);
 
         for (int current_page = 0; current_page < page_count; current_page++) {
-            fz_page *page; if (current_page == 0) {
+            fz_page *page = NULL;
+            if (current_page == 0) {
                 page = cover;
             } else {
-                page = fz_load_page(ctx, fzdoc, current_page);
+                fz_var(err);
+                fz_try(ctx)
+                            page = fz_load_page(ctx, fzdoc, current_page);
+                fz_catch(ctx)
+                    err = ctx->error.errcode;
+                if (err != 0) {
+                    text_buffer_destroy(&text_buf);
+                    fz_drop_page(ctx, page);
+                    fz_drop_stream(ctx, stream);
+                    fz_drop_document(ctx, fzdoc);
+                    fz_drop_context(ctx);
+                    return;
+                }
             }
 
             fz_stext_page *stext = fz_new_stext_page(ctx, fz_bound_page(ctx, page));
             fz_device *dev = fz_new_stext_device(ctx, stext, &opts);
 
-            pthread_mutex_lock(&ScanCtx.mupdf_mu);
+            fz_var(err);
             fz_try(ctx)
-                fz_run_page_contents(ctx, page, dev, fz_identity, NULL);
+                        fz_run_page(ctx, page, dev, fz_identity, NULL);
             fz_always(ctx)
-                pthread_mutex_unlock(&ScanCtx.mupdf_mu);
+                {
+                    fz_close_device(ctx, dev);
+                    fz_drop_device(ctx, dev);
+                }
             fz_catch(ctx)
-                fz_rethrow(ctx);
+                err = ctx->error.errcode;
 
-            fz_drop_device(ctx, dev);
+            if (err != 0) {
+                text_buffer_destroy(&text_buf);
+                fz_drop_page(ctx, page);
+                fz_drop_stext_page(ctx, stext);
+                fz_drop_stream(ctx, stream);
+                fz_drop_document(ctx, fzdoc);
+                fz_drop_context(ctx);
+                return;
+            }
 
             fz_stext_block *block = stext->first_block;
             while (block != NULL) {
-
-                if (block->type != FZ_STEXT_BLOCK_TEXT) {
-                    block = block->next;
-                    continue;
-                }
-
-                fz_stext_line *line = block->u.t.first_line;
-                while (line != NULL) {
-                    fz_stext_char *c = line->first_char;
-                    while (c != NULL) {
-                        if (text_buffer_append_char(&text_buf, c->c) == TEXT_BUF_FULL) {
-                            fz_drop_page(ctx, page);
-                            fz_drop_stext_page(ctx, stext);
-                            goto write_loop_end;
-                        }
-                        c = c->next;
-                    }
-                    line = line->next;
+                int ret = read_stext_block(block, &text_buf);
+                if (ret == TEXT_BUF_FULL) {
+                    break;
                 }
                 block = block->next;
             }
-            fz_drop_page(ctx, page);
             fz_drop_stext_page(ctx, stext);
+            fz_drop_page(ctx, page);
+
+            if (text_buf.dyn_buffer.cur >= text_buf.dyn_buffer.size) {
+                break;
+            }
         }
-        write_loop_end:;
         text_buffer_terminate_string(&text_buf);
 
         meta_line_t *meta_content = malloc(sizeof(meta_line_t) + text_buf.dyn_buffer.cur);
         meta_content->key = MetaContent;
         memcpy(meta_content->strval, text_buf.dyn_buffer.buf, text_buf.dyn_buffer.cur);
-        text_buffer_destroy(&text_buf);
         APPEND_META(doc, meta_content)
+
+        text_buffer_destroy(&text_buf);
     }
-    fz_always(ctx)
-    {
-        fz_drop_stream(ctx, stream);
-        fz_drop_document(ctx, fzdoc);
-        fz_drop_context(ctx);
-    } fz_catch(ctx) {
-        fprintf(stderr, "Error %s %s\n", doc->filepath, ctx->error.message);
-    }
+
+    fz_drop_stream(ctx, stream);
+    fz_drop_document(ctx, fzdoc);
+    fz_drop_context(ctx);
 }
 

src/parsing/text.c

@@ -1,7 +1,7 @@
 #include "text.h"
 #include "src/ctx.h"
 
-void parse_text(int bytes_read, int *fd, char *buf, document_t *doc) {
+void parse_text(int bytes_read, struct vfile *f, char *buf, document_t *doc) {
 
     char *intermediate_buf;
     int intermediate_buf_len;
@@ -13,10 +13,6 @@ void parse_text(int bytes_read, int *fd, char *buf, document_t *doc) {
         memcpy(intermediate_buf, buf, to_copy);
 
     } else {
-        if (*fd == -1) {
-            *fd = open(doc->filepath, O_RDONLY);
-        }
-
         int to_read = MIN(ScanCtx.content_size, doc->size) - bytes_read;
 
         intermediate_buf = malloc(to_read + bytes_read);
@@ -25,19 +21,16 @@ void parse_text(int bytes_read, int *fd, char *buf, document_t *doc) {
             memcpy(intermediate_buf, buf, bytes_read);
         }
 
-        read(*fd, intermediate_buf + bytes_read, to_read);
+        f->read(f, intermediate_buf + bytes_read, to_read);
     }
+    text_buffer_t tex = text_buffer_create(ScanCtx.content_size);
+    text_buffer_append_string(&tex, intermediate_buf, intermediate_buf_len);
 
-    text_buffer_t text_buf = text_buffer_create(ScanCtx.content_size);
-    for (int i = 0; i < intermediate_buf_len; i++) {
-        text_buffer_append_char(&text_buf, *(intermediate_buf + i));
-    }
-    text_buffer_terminate_string(&text_buf);
-
-    meta_line_t *meta = malloc(sizeof(meta_line_t) + text_buf.dyn_buffer.cur);
+    meta_line_t *meta = malloc(sizeof(meta_line_t) + tex.dyn_buffer.cur);
     meta->key = MetaContent;
-    strcpy(meta->strval, text_buf.dyn_buffer.buf);
-    text_buffer_destroy(&text_buf);
-    free(intermediate_buf);
+    strcpy(meta->strval, tex.dyn_buffer.buf);
     APPEND_META(doc, meta)
+
+    free(intermediate_buf);
+    text_buffer_destroy(&tex);
 }

src/parsing/text.h

@@ -3,6 +3,6 @@
 
 #include "src/sist.h"
 
-void parse_text(int bytes_read, int *fd, char *buf, document_t *doc);
+void parse_text(int bytes_read, struct vfile *f, char *buf, document_t *doc);
 
 #endif

src/sist.h

@@ -16,6 +16,7 @@
 #include <libswscale/swscale.h>
 #include <libswresample/swresample.h>
 #include <libavcodec/avcodec.h>
+#include <libavutil/imgutils.h>
 #include <ctype.h>
 #include <mupdf/fitz.h>
 #include <mupdf/pdf.h>
@@ -25,12 +26,17 @@
 #include <pthread.h>
 #include <sys/stat.h>
 #include <wordexp.h>
+#include "ft2build.h"
+#include "freetype/freetype.h"
+#include <archive.h>
+#include <archive_entry.h>
 
 #ifndef SIST_SCAN_ONLY
 #include <onion/onion.h>
 #include <onion/handler.h>
 #include <onion/block.h>
 #include <onion/shortcuts.h>
+#include <onion/codecs.h>
 #include <curl/curl.h>
 #endif
 
@@ -48,12 +54,15 @@
 #include "parsing/pdf.h"
 #include "parsing/media.h"
 #include "parsing/font.h"
+#include "parsing/arc.h"
 #include "cli.h"
+#include "utf8.h/utf8.h"
 
 #ifndef SIST_SCAN_ONLY
 #include "src/index/elastic.h"
 #include "index/web.h"
 #include "web/serve.h"
+#include "web/auth_basic.h"
 #endif
 
 ;

src/tpool.c

@@ -25,6 +25,7 @@ typedef struct tpool {
     int done_cnt;
 
     int stop;
+
     void (*cleanup_func)();
 } tpool_t;
 
@@ -100,7 +101,7 @@ static void *tpool_worker(void *arg) {
     tpool_t *pool = arg;
 
     while (1) {
-        pthread_mutex_lock(&(pool->work_mutex));
+        pthread_mutex_lock(&pool->work_mutex);
         if (pool->stop) {
             break;
         }
@@ -113,14 +114,21 @@ static void *tpool_worker(void *arg) {
         pthread_mutex_unlock(&(pool->work_mutex));
 
         if (work != NULL) {
+            if (pool->stop) {
+                break;
+            }
+
             work->func(work->arg);
+            free(work->arg);
             free(work);
         }
 
         pthread_mutex_lock(&(pool->work_mutex));
-        pool->done_cnt++;
+        if (work != NULL) {
+            pool->done_cnt++;
+        }
 
-        progress_bar_print((double)pool->done_cnt / pool->work_cnt, ScanCtx.stat_tn_size, ScanCtx.stat_index_size);
+        progress_bar_print((double) pool->done_cnt / pool->work_cnt, ScanCtx.stat_tn_size, ScanCtx.stat_index_size);
 
         if (pool->work_head == NULL) {
             pthread_cond_signal(&(pool->working_cond));
@@ -141,11 +149,15 @@ void tpool_wait(tpool_t *pool) {
         if (pool->done_cnt < pool->work_cnt) {
             pthread_cond_wait(&(pool->working_cond), &(pool->work_mutex));
         } else {
-            pool->stop = 1;
-            break;
+            usleep(500000);
+            if (pool->done_cnt == pool->work_cnt) {
+                pool->stop = 1;
+                usleep(1000000);
+                break;
+            }
         }
-        progress_bar_print(100.0, ScanCtx.stat_tn_size, ScanCtx.stat_index_size);
     }
+    progress_bar_print(1.0, ScanCtx.stat_tn_size, ScanCtx.stat_index_size);
     pthread_mutex_unlock(&(pool->work_mutex));
 }
 
@@ -168,7 +180,8 @@ void tpool_destroy(tpool_t *pool) {
     for (size_t i = 0; i < pool->thread_cnt; i++) {
         pthread_t thread = pool->threads[i];
         if (thread != 0) {
-            pthread_cancel(thread);
+            void *_;
+            pthread_join(thread, &_);
         }
     }
 
@@ -188,11 +201,11 @@ tpool_t *tpool_create(size_t thread_cnt, void cleanup_func()) {
 
     tpool_t *pool = malloc(sizeof(tpool_t));
     pool->thread_cnt = thread_cnt;
-    pool->work_cnt =0;
-    pool->done_cnt =0;
+    pool->work_cnt = 0;
+    pool->done_cnt = 0;
     pool->stop = 0;
     pool->cleanup_func = cleanup_func;
-    pool->threads = malloc(sizeof(pthread_t) * thread_cnt);
+    pool->threads = calloc(sizeof(pthread_t), thread_cnt);
 
     pthread_mutex_init(&(pool->work_mutex), NULL);
 
@@ -202,11 +215,12 @@ tpool_t *tpool_create(size_t thread_cnt, void cleanup_func()) {
     pool->work_head = NULL;
     pool->work_tail = NULL;
 
-    for (size_t i = 0; i < thread_cnt; i++) {
-        pthread_t thread = pool->threads[i];
-        pthread_create(&thread, NULL, tpool_worker, pool);
-        pthread_detach(thread);
-    }
-
     return pool;
 }
+
+void tpool_start(tpool_t *pool) {
+
+    for (size_t i = 0; i < pool->thread_cnt; i++) {
+        pthread_create(&pool->threads[i], NULL, tpool_worker, pool);
+    }
+}

src/tpool.h

@@ -9,6 +9,7 @@ typedef struct tpool tpool_t;
 typedef void (*thread_func_t)(void *arg);
 
 tpool_t *tpool_create(size_t num, void (*cleanup_func)());
+void tpool_start(tpool_t *pool);
 void tpool_destroy(tpool_t *tm);
 
 int tpool_add_work(tpool_t *pool, thread_func_t func, void *arg);

src/types.h

@@ -9,6 +9,12 @@
 #define IS_META_LONG(key) (key & META_LONG_MASK) == META_LONG_MASK
 #define IS_META_STR(meta) (meta->key & META_STR_MASK) == META_STR_MASK
 
+#define ARC_MODE_SKIP 0
+#define ARC_MODE_LIST 1
+#define ARC_MODE_SHALLOW 2
+#define ARC_MODE_RECURSE 3
+typedef int archive_mode_t;
+
 // This is written to file as a 8bit char!
 enum metakey {
     MetaContent = 1 | META_STR_MASK,
@@ -24,6 +30,7 @@ enum metakey {
     MetaGenre = 11 | META_STR_MASK,
     MetaTitle = 12 | META_STR_MASK,
     MetaFontName = 13 | META_STR_MASK,
+    MetaParent = 14 | META_STR_MASK,
 };
 
 typedef struct index_descriptor {
@@ -63,13 +70,39 @@ typedef struct document {
     short ext;
     meta_line_t *meta_head;
     meta_line_t *meta_tail;
+    struct document *child_head;
+    struct document *child_tail;
     char *filepath;
 } document_t;
 
+typedef struct vfile vfile_t;
+
+typedef int (*read_func_t)(struct vfile *, void *buf, size_t size);
+
+typedef int (*seek_func_t)(struct vfile *, size_t size, int whence);
+
+typedef void (*close_func_t)(struct vfile *);
+
+typedef struct vfile {
+
+    union {
+        int fd;
+        struct archive *arc;
+    };
+
+    int is_fs_file;
+    char *filepath;
+
+    read_func_t read;
+    close_func_t close;
+} vfile_t;
+
 typedef struct parse_job_t {
     int base;
     int ext;
     struct stat info;
+    struct vfile vfile;
+    uuid_t parent;
     char filepath[1];
 } parse_job_t;
 

src/util.c

@@ -46,6 +46,10 @@ void dyn_buffer_write_str(dyn_buffer_t *buf, char *str) {
     dyn_buffer_write_char(buf, '\0');
 }
 
+void dyn_buffer_append_string(dyn_buffer_t *buf, char *str) {
+    dyn_buffer_write(buf, str, strlen(str));
+}
+
 void dyn_buffer_write_int(dyn_buffer_t *buf, int d) {
     grow_buffer_small(buf);
 
@@ -89,6 +93,85 @@ void text_buffer_terminate_string(text_buffer_t *buf) {
     dyn_buffer_write_char(&buf->dyn_buffer, '\0');
 }
 
+__always_inline
+int utf8_validchr(const char *s) {
+    if (0x00 == (0x80 & *s)) {
+        return TRUE;
+    } else if (0xf0 == (0xf8 & *s)) {
+        if ((0x80 != (0xc0 & s[1])) || (0x80 != (0xc0 & s[2])) ||
+            (0x80 != (0xc0 & s[3]))) {
+            return FALSE;
+        }
+
+        if (0x80 == (0xc0 & s[4])) {
+            return FALSE;
+        }
+
+        if ((0 == (0x07 & s[0])) && (0 == (0x30 & s[1]))) {
+            return FALSE;
+        }
+    } else if (0xe0 == (0xf0 & *s)) {
+        if ((0x80 != (0xc0 & s[1])) || (0x80 != (0xc0 & s[2]))) {
+            return FALSE;
+        }
+
+        if (0x80 == (0xc0 & s[3])) {
+            return FALSE;
+        }
+
+        if ((0 == (0x0f & s[0])) && (0 == (0x20 & s[1]))) {
+            return FALSE;
+        }
+    } else if (0xc0 == (0xe0 & *s)) {
+        if (0x80 != (0xc0 & s[1])) {
+            return FALSE;
+        }
+
+        if (0x80 == (0xc0 & s[2])) {
+            return FALSE;
+        }
+
+        if (0 == (0x1e & s[0])) {
+            return FALSE;
+        }
+    } else {
+        return FALSE;
+    }
+
+    return TRUE;
+}
+
+int text_buffer_append_string(text_buffer_t *buf, char *str, size_t len) {
+
+    utf8_int32_t c;
+    if (str == NULL || len < 1 ||
+        (0xf0 == (0xf8 & str[0]) && len < 4) ||
+        (0xe0 == (0xf0 & str[0]) && len < 3) ||
+        (0xc0 == (0xe0 & str[0]) && len == 1) ||
+        *(str) == 0) {
+        text_buffer_terminate_string(buf);
+        return 0;
+    }
+
+    for (void *v = utf8codepoint(str, &c); c != '\0' && ((char *) v - str + 4) < len; v = utf8codepoint(v, &c)) {
+        if (utf8_validchr(v)) {
+            text_buffer_append_char(buf, c);
+        }
+    }
+    text_buffer_terminate_string(buf);
+    return 0;
+}
+
+int text_buffer_append_string0(text_buffer_t *buf, char *str) {
+    utf8_int32_t c;
+    for (void *v = utf8codepoint(str, &c); c != '\0'; v = utf8codepoint(v, &c)) {
+        if (utf8_validchr(v)) {
+            text_buffer_append_char(buf, c);
+        }
+    }
+    text_buffer_terminate_string(buf);
+}
+
 int text_buffer_append_char(text_buffer_t *buf, int c) {
 
     if (SHOULD_IGNORE_CHAR(c)) {
@@ -96,15 +179,31 @@ int text_buffer_append_char(text_buffer_t *buf, int c) {
             dyn_buffer_write_char(&buf->dyn_buffer, ' ');
             buf->last_char_was_whitespace = TRUE;
 
-            if (buf->dyn_buffer.cur >= buf->max_size) {
+            if (buf->max_size > 0 && buf->dyn_buffer.cur >= buf->max_size) {
                 return TEXT_BUF_FULL;
             }
         }
     } else {
         buf->last_char_was_whitespace = FALSE;
-        dyn_buffer_write_char(&buf->dyn_buffer, (char) c);
+        grow_buffer_small(&buf->dyn_buffer);
 
-        if (buf->dyn_buffer.cur >= buf->max_size) {
+        if (0 == ((utf8_int32_t) 0xffffff80 & c)) {
+            *(buf->dyn_buffer.buf + buf->dyn_buffer.cur++) = (char) c;
+        } else if (0 == ((utf8_int32_t) 0xfffff800 & c)) {
+            *(buf->dyn_buffer.buf + buf->dyn_buffer.cur++) = 0xc0 | (char) (c >> 6);
+            *(buf->dyn_buffer.buf + buf->dyn_buffer.cur++) = 0x80 | (char) (c & 0x3f);
+        } else if (0 == ((utf8_int32_t) 0xffff0000 & c)) {
+            *(buf->dyn_buffer.buf + buf->dyn_buffer.cur++) = 0xe0 | (char) (c >> 12);
+            *(buf->dyn_buffer.buf + buf->dyn_buffer.cur++) = 0x80 | (char) ((c >> 6) & 0x3f);
+            *(buf->dyn_buffer.buf + buf->dyn_buffer.cur++) = 0x80 | (char) (c & 0x3f);
+        } else {
+            *(buf->dyn_buffer.buf + buf->dyn_buffer.cur++) = 0xf0 | (char) (c >> 18);
+            *(buf->dyn_buffer.buf + buf->dyn_buffer.cur++) = 0x80 | (char) ((c >> 12) & 0x3f);
+            *(buf->dyn_buffer.buf + buf->dyn_buffer.cur++) = 0x80 | (char) ((c >> 6) & 0x3f);
+            *(buf->dyn_buffer.buf + buf->dyn_buffer.cur++) = 0x80 | (char) (c & 0x3f);
+        }
+
+        if (buf->max_size > 0 && buf->dyn_buffer.cur >= buf->max_size) {
             return TEXT_BUF_FULL;
         }
     }
@@ -136,7 +235,7 @@ dyn_buffer_t url_escape(char *str) {
 
     dyn_buffer_t text = dyn_buffer_create();
 
-    char * ptr = str;
+    char *ptr = str;
     while (*ptr) {
         if (*ptr == '#') {
             dyn_buffer_write(&text, "%23", 3);
@@ -169,7 +268,7 @@ char *expandpath(const char *path) {
     wordexp_t w;
     wordexp(path, &w, 0);
 
-    char * expanded = malloc(strlen(w.we_wordv[0]) + 2);
+    char *expanded = malloc(strlen(w.we_wordv[0]) + 2);
     strcpy(expanded, w.we_wordv[0]);
     strcat(expanded, "/");
 

src/util.h

@@ -5,7 +5,10 @@
 
 #define TEXT_BUF_FULL -1
 #define INITIAL_BUF_SIZE 1024 * 16
-#define SHOULD_IGNORE_CHAR(c) c < '0' || c > 'z'
+
+#define SHOULD_IGNORE_CHAR(c) !(SHOULD_KEEP_CHAR(c))
+#define SHOULD_KEEP_CHAR(c) (c >= (int)'!')
+
 
 typedef struct dyn_buffer {
     char *buf;
@@ -21,8 +24,10 @@ typedef struct text_buffer {
     dyn_buffer_t dyn_buffer;
 } text_buffer_t;
 
-char *abspath(const char * path);
+char *abspath(const char *path);
+
 char *expandpath(const char *path);
+
 dyn_buffer_t url_escape(char *str);
 
 void progress_bar_print(double percentage, size_t tn_size, size_t index_size);
@@ -42,6 +47,8 @@ void dyn_buffer_write_char(dyn_buffer_t *buf, char c);
 
 void dyn_buffer_write_str(dyn_buffer_t *buf, char *str);
 
+void dyn_buffer_append_string(dyn_buffer_t *buf, char *str);
+
 void dyn_buffer_write_int(dyn_buffer_t *buf, int d);
 
 void dyn_buffer_write_short(dyn_buffer_t *buf, short s);
@@ -56,13 +63,16 @@ text_buffer_t text_buffer_create(int max_size);
 
 void text_buffer_terminate_string(text_buffer_t *buf);
 
+int text_buffer_append_string(text_buffer_t *buf, char *str, size_t len);
+int text_buffer_append_string0(text_buffer_t *buf, char *str);
+
 int text_buffer_append_char(text_buffer_t *buf, int c);
 
 void incremental_put(GHashTable *table, unsigned long inode_no, int mtime);
 
 int incremental_get(GHashTable *table, unsigned long inode_no);
+
 int incremental_mark_file_for_copy(GHashTable *table, unsigned long inode_no);
 
 
-
 #endif

src/web/auth_basic.c

@@ -0,0 +1,59 @@
+#include "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);
@@ -358,12 +360,24 @@ int file(void *p, onion_request *req, onion_response *res) {
         return OCS_PROCESSED;
     }
 
-    cJSON *doc = elastic_get_document(arg_uuid);
-    cJSON *source = cJSON_GetObjectItem(doc, "_source");
-    cJSON *index_id = cJSON_GetObjectItem(source, "index");
-    if (index_id == NULL) {
-        cJSON_Delete(doc);
-        return OCS_NOT_PROCESSED;
+    char *next = arg_uuid;
+    cJSON *doc = NULL;
+    cJSON *index_id = NULL;
+    cJSON *source = NULL;
+
+    while (true) {
+        doc = elastic_get_document(next);
+        source = cJSON_GetObjectItem(doc, "_source");
+        index_id = cJSON_GetObjectItem(source, "index");
+        if (index_id == NULL) {
+            cJSON_Delete(doc);
+            return OCS_NOT_PROCESSED;
+        }
+        cJSON *parent = cJSON_GetObjectItem(source, "parent");
+        if (parent == NULL) {
+            break;
+        }
+        next = parent->valuestring;
     }
 
     index_t *idx = get_index_by_id(index_id->valuestring);
@@ -391,9 +405,11 @@ 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 +426,7 @@ 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;
 }
@@ -15,6 +19,31 @@ body {
     margin-top: 1em;
     background: #212121;
     color: #e0e0e0;
+    border-radius: 1px;
+    border: none;
+}
+
+.sub-document {
+    background: #37474F;
+}
+
+.sub-document .text-muted {
+    color: #8a949c !important;
+}
+
+
+.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 {
@@ -87,12 +116,18 @@ 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;
@@ -104,6 +139,15 @@ 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;
@@ -147,6 +191,8 @@ mark {
     border: 1px solid #616161;
     border-radius: 4px;
     margin: 3px;
+    white-space: normal;
+    color: rgb(224, 224, 224);
 }
 
 .irs-single, .irs-from, .irs-to {
@@ -162,6 +208,7 @@ mark {
     margin-top: 1em;
     margin-bottom: 1em;
 }
+
 .custom-select {
     overflow: auto;
     background-color: #37474F;
@@ -227,6 +274,7 @@ option {
     padding: 0.5rem;
     background: #212121;
     color: #eee;
+    margin-top: 1em;
 }
 
 .btn-xs {
@@ -237,4 +285,76 @@ 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;
@@ -6,14 +12,23 @@ body {overflow-y:scroll;}
 
 .card {
     margin-top: 1em;
+    box-shadow: 0 .125rem .25rem rgba(0, 0, 0, .075) !important;
 }
+
+.sub-document {
+    background: #AB47BC1F;
+}
+
 .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;
 }
@@ -46,6 +61,11 @@ body {overflow-y:scroll;}
     background-color: #FFC107;
 }
 
+.badge-user {
+    color: #212529;
+    background-color: #e0e0e0;
+}
+
 .badge-text {
     color: #FFFFFF;
     background-color: #FAAB3C;
@@ -83,6 +103,15 @@ 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;
@@ -97,16 +126,17 @@ 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;
     }
 }
@@ -118,13 +148,15 @@ 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 {
@@ -144,8 +176,7 @@ 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;
 }
 
@@ -160,11 +191,60 @@ mark {
 .page-indicator {
     line-height: 1rem;
     padding: 0.5rem;
-    background: #212121;
+    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
@@ -82,32 +160,30 @@ function shouldPlayVideo(hit) {
  */
 function createDocCard(hit) {
     let docCard = document.createElement("div");
-    docCard.setAttribute("class", "card shadow-sm");
+    docCard.setAttribute("class", "card");
 
     let docCardBody = document.createElement("div");
     docCardBody.setAttribute("class", "card-body document");
 
+    //Title
+    let title = makeTitle(hit);
+    let isSubDocument = false;
+
     let link = document.createElement("a");
     link.setAttribute("href", "f/" + hit["_id"]);
     link.setAttribute("target", "_blank");
+    link.appendChild(title);
 
-    //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);
+    if (hit["_source"].hasOwnProperty("parent")) {
+        docCard.classList.add("sub-document");
+        isSubDocument = true;
+    }
 
     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");
@@ -115,28 +191,7 @@ 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"]}`);
-        }
+        let thumbnail = makeThumbnail(mimeCategory, hit, imgWrapper, false);
 
         //Thumbnail overlay
         switch (mimeCategory) {
@@ -146,15 +201,17 @@ function createDocCard(hit) {
                 thumbnailOverlay.setAttribute("class", "card-img-overlay");
 
                 //Resolution
-                let resolutionBadge = document.createElement("span");
-                resolutionBadge.setAttribute("class", "badge badge-resolution");
-                if (hit["_source"].hasOwnProperty("width")) {
-                    resolutionBadge.appendChild(document.createTextNode(hit["_source"]["width"] + "x" + hit["_source"]["height"]));
+                if (hit["_source"].hasOwnProperty("width") && hit["_source"]["width"] > 32 && hit["_source"]["height"] > 32) {
+                    let resolutionBadge = document.createElement("span");
+                    resolutionBadge.setAttribute("class", "badge badge-resolution");
+                    if (hit["_source"].hasOwnProperty("width")) {
+                        resolutionBadge.appendChild(document.createTextNode(hit["_source"]["width"] + "x" + hit["_source"]["height"]));
+                    }
+                    thumbnailOverlay.appendChild(resolutionBadge);
                 }
-                thumbnailOverlay.appendChild(resolutionBadge);
 
                 // Hover
-                if (thumbnail && hit["_source"]["videoc"] === "gif") {
+                if (thumbnail && hit["_source"]["videoc"] === "gif" && !isSubDocument) {
                     gifOver(thumbnail, hit);
                 }
                 break;
@@ -164,51 +221,34 @@ 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);
         }
 
         //Audio
-        if (mimeCategory === "audio" && hit["_source"].hasOwnProperty("audioc")) {
+        if (mimeCategory === "audio" && hit["_source"].hasOwnProperty("audioc") && !isSubDocument) {
 
             let audio = document.createElement("audio");
             audio.setAttribute("preload", "none");
@@ -223,10 +263,6 @@ function createDocCard(hit) {
         if (thumbnailOverlay !== null) {
             imgWrapper.appendChild(thumbnailOverlay);
         }
-
-        for (let i = 0; i < tags.length; i++) {
-            tagContainer.appendChild(tags[i]);
-        }
     }
 
     //Size tag
@@ -238,12 +274,146 @@ function createDocCard(hit) {
     docCardBody.appendChild(link);
     docCard.appendChild(docCardBody);
 
-    link.appendChild(title);
     docCardBody.appendChild(tagContainer);
 
     return docCard;
 }
 
+function makeThumbnail(mimeCategory, hit, imgWrapper, small) {
+    let thumbnail;
+    let isSubDocument = hit["_source"].hasOwnProperty("parent");
+
+    if (mimeCategory === "video" && shouldPlayVideo(hit) && !isSubDocument) {
+        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) {
+
+    const mime = hit["_source"]["mime"];
+    let mimeCategory = mime ? mime.split("/")[0] : null;
+    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");
@@ -257,7 +427,7 @@ function makePreloader() {
 
 function makePageIndicator(searchResult) {
     let pageIndicator = document.createElement("div");
-    pageIndicator.setAttribute("class", "page-indicator shadow-sm font-weight-light");
+    pageIndicator.setAttribute("class", "page-indicator font-weight-light");
     const totalHits = searchResult["hits"]["total"].hasOwnProperty("value")
         ? searchResult["hits"]["total"]["value"] : searchResult["hits"]["total"];
     pageIndicator.appendChild(document.createTextNode(docCount + " / " + totalHits));
@@ -268,18 +438,53 @@ 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);
     }
@@ -291,7 +496,11 @@ 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,
@@ -23,7 +32,7 @@ jQuery["jsonPost"] = function (url, data) {
 
 window.onload = () => {
     $("#theme").on("click", () => {
-        if (document.cookie.length === 0) {
+        if (!document.cookie.includes("sist")) {
             document.cookie = "sist=dark";
         } else {
             document.cookie = "sist=; Max-Age=-99999999;";
@@ -32,7 +41,7 @@ window.onload = () => {
     })
 };
 
-function toggleSearchBar() {
+function toggleFuzzy() {
     searchDebounced();
 }
 
@@ -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: {
@@ -85,38 +111,90 @@ $.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,
-    delay: 75,
+    delay: 400,
     renderItem: function (item) {
         return '<div class="autocomplete-suggestion" data-val="' + item + '">' + item + '</div>';
     },
@@ -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() {
@@ -218,21 +301,37 @@ function search() {
 
     let query = searchBar.value;
     let empty = query === "";
-    let condition = $("#barToggle").prop("checked") && !empty ? "must" : "should";
+    let condition = empty ? "should" : "must";
     let filters = [
         {range: {size: {gte: size_min, lte: size_max}}},
         {terms: {index: selectedIndices}}
     ];
+    let fields = [
+        "name^8",
+        "content^3",
+        "album^8", "artist^8", "title^8", "genre^2", "album_artist^8",
+        "font_name^6"
+    ];
+
+    if ($("#fuzzyToggle").prop("checked")) {
+        fields.push("content.nGram");
+        fields.push("name.nGram^3");
+    }
 
     let path = pathBar.value.replace(/\/$/, "").toLowerCase(); //remove trailing slashes
     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"]
@@ -243,12 +342,7 @@ function search() {
                     multi_match: {
                         query: query,
                         type: "most_fields",
-                        fields: [
-                            "name^8", "name.nGram^3", "content^3",
-                            "content.nGram",
-                            "album^8", "artist^8", "title^8", "genre^2", "album_artist^8",
-                            "font_name^6"
-                        ],
+                        fields: fields,
                         operator: "and"
                     }
                 },
@@ -263,9 +357,10 @@ function search() {
             post_tags: ["</mark>"],
             fields: {
                 content: {},
+                // "content.nGram": {},
                 name: {},
                 "name.nGram": {},
-                // font_name: {},
+                font_name: {},
             }
         },
         aggs: {
@@ -279,14 +374,6 @@ function search() {
         //Search stats
         searchResults.appendChild(makeStatsCard(searchResult));
 
-        //Autocomplete
-        if (searchResult.hasOwnProperty("suggest") && searchResult["suggest"].hasOwnProperty("path")) {
-            pathAutoComplete = [];
-            for (let i = 0; i < searchResult["suggest"]["path"][0]["options"].length; i++) {
-                pathAutoComplete.push(searchResult["suggest"]["path"][0]["options"][i].text)
-            }
-        }
-
         //Setup page
         let resultContainer = makeResultContainer();
         searchResults.appendChild(resultContainer);
@@ -298,7 +385,6 @@ function search() {
     });
 }
 
-let pathAutoComplete = [];
 let size_min = 0;
 let size_max = 10000000000000;
 
@@ -306,8 +392,8 @@ let searchDebounced = _.debounce(function () {
     coolingDown = false;
     search()
 }, 500);
+
 searchBar.addEventListener("keyup", searchDebounced);
-document.getElementById("pathBar").addEventListener("keyup", searchDebounced);
 
 //Size slider
 $("#sizeSlider").ionRangeSlider({
@@ -358,15 +444,18 @@ updateIndices();
 //Suggest
 function getPathChoices() {
     return new Promise(getPaths => {
-
-        let xhttp = new XMLHttpRequest();
-        xhttp.onreadystatechange = function () {
-            if (this.readyState === 4 && this.status === 200) {
-                getPaths(JSON.parse(xhttp.responseText))
+        $.jsonPost("es", {
+            suggest: {
+                path: {
+                    prefix: pathBar.value,
+                    completion: {
+                        field: "suggest-path",
+                        skip_duplicates: true,
+                        size: 10000
+                    }
+                }
             }
-        };
-        xhttp.open("GET", "suggest?prefix=" + pathBar.value, true);
-        xhttp.send();
-    });
+        }).then(resp => getPaths(resp["suggest"]["path"][0]["options"].map(opt => opt["_source"]["path"])));
+    })
 }
 

web/js/util.js

@@ -3,7 +3,7 @@
  */
 function humanFileSize(bytes) {
     if (bytes === 0) {
-        return "? B"
+        return "0 B"
     }
 
     let thresh = 1000;
@@ -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">v1.1.10</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>
@@ -24,9 +25,9 @@
             <div class="input-group">
                 <div class="input-group-prepend">
                     <div class="input-group-text">
-                        <span onclick="document.getElementById('barToggle').click()">Must match&nbsp</span>
-                        <input title="Toggle between 'Should' and 'Must' match mode" type="checkbox" id="barToggle"
-                               onclick="toggleSearchBar()" checked>
+                        <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>
                 </div>
                 <input id="searchBar" type="search" class="form-control" placeholder="Search">
@@ -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>