updates

SQLite search backend

.devcontainer/Dockerfile

@@ -0,0 +1,9 @@
+FROM simon987/sist2-build
+
+RUN curl -fsSL https://deb.nodesource.com/setup_16.x | bash
+RUN apt update -y; apt install -y nodejs && rm -rf /var/lib/apt/lists/*
+
+ENV DEBIAN_FRONTEND=noninteractive
+ENV LANG C.UTF-8
+ENV LC_ALL C.UTF-8
+

.devcontainer/devcontainer.json

@@ -0,0 +1,16 @@
+{
+  "name": "sist2-dev",
+  "dockerComposeFile": [
+    "docker-compose.yml"
+  ],
+  "service": "sist2-dev",
+  "customizations": {
+    "vscode": {
+      "extensions": [
+        "ms-vscode.cpptools-extension-pack"
+      ]
+    }
+  },
+  "remoteUser": "root",
+  "workspaceFolder": "/app/"
+}

.devcontainer/docker-compose.yml

@@ -0,0 +1,8 @@
+version: "3"
+
+services:
+  sist2-dev:
+    build: .
+    command: sleep infinity
+    volumes:
+      - ../:/app

.dockerignore

@@ -8,13 +8,13 @@ Testing/
 **/cmake_install.cmake
 **/CMakeCache.txt
 **/CMakeFiles/
+.cmake
 LICENSE
 Makefile
 **/*.md
 **/*.cbp
 VERSION
 **/node_modules/
-.git/
 sist2-*-linux-debug
 sist2-*-linux
 sist2_debug
@@ -29,3 +29,12 @@ sist2
 **/core
 *.a
 tmp_scan/
+Dockerfile
+Dockerfile.arm64
+docker-compose.yml
+state.db
+*-journal
+build/
+__pycache__/
+sist2-vue/dist
+sist2-admin/frontend/dist

.gitattributes

@@ -1,3 +0,0 @@
-CMakeModules/* linguist-vendored
-**/*_generated.c linguist-vendored
-**/*_generated.h linguist-vendored

.gitignore

@@ -10,6 +10,9 @@ Makefile
 LOG
 sist2*
 !sist2-vue/
+!sist2-admin
+!sist2_admin
+!sist2.py
 *.sist2/
 bundle*.css
 bundle.js
@@ -26,3 +29,20 @@ test_i_inc
 node_modules/
 .cmake/
 i_inc/
+state.db
+*.pyc
+!sist2-admin/frontend/dist
+*.js.map
+sist2-vue/dist
+sist2-admin/frontend/dist
+.ninja_deps
+.ninja_log
+build.ninja
+src/web/static_generated.c
+src/magic_generated.c
+src/index/static_generated.c
+*.sist2
+*-shm
+*-journal
+.vscode
+*.fts

.gitmodules

@@ -10,3 +10,6 @@
 [submodule "third-party/libscan/third-party/libmobi"]
 	path = third-party/libscan/third-party/libmobi
 	url = https://github.com/bfabiszewski/libmobi
+[submodule "third-party/libscan/libscan-test-files"]
+	path = third-party/libscan/libscan-test-files
+	url = https://github.com/simon987/libscan-test-files

CMakeLists.txt

@@ -1,11 +1,11 @@
 cmake_minimum_required(VERSION 3.7)
-set(CMAKE_C_STANDARD 11)
 
-project(sist2 C)
+project(sist2)
+set(CMAKE_C_STANDARD 11)
 
 option(SIST_DEBUG "Build a debug executable" on)
 option(SIST_FAST "Enable more optimisation flags" off)
-option(SIST_FAKE_STORE "Disable IO operations of LMDB stores for debugging purposes" 0)
+option(SIST_DEBUG_INFO "Turn on debug information in web interface" on)
 
 add_compile_definitions(
         "SIST_PLATFORM=${SIST_PLATFORM}"
@@ -15,50 +15,67 @@ if (SIST_DEBUG)
     add_compile_definitions(
             "SIST_DEBUG=${SIST_DEBUG}"
     )
-endif()
+    set(VCPKG_BUILD_TYPE debug)
+else ()
+    set(VCPKG_BUILD_TYPE release)
+endif ()
+
+if (SIST_DEBUG_INFO)
+    add_compile_definitions(
+            "SIST_DEBUG_INFO=${SIST_DEBUG_INFO}"
+    )
+endif ()
+
 
 add_subdirectory(third-party/libscan)
 set(ARGPARSE_SHARED off)
 add_subdirectory(third-party/argparse)
 
-add_executable(sist2
+add_executable(
+        sist2
+        # argparse
+        third-party/argparse/argparse.h third-party/argparse/argparse.c
+
         src/main.c
         src/sist.h
         src/io/walk.h src/io/walk.c
-        src/io/store.h src/io/store.c
         src/tpool.h src/tpool.c
         src/parsing/parse.h src/parsing/parse.c
+        src/parsing/magic_util.c src/parsing/magic_util.h
         src/io/serialize.h src/io/serialize.c
         src/parsing/mime.h src/parsing/mime.c src/parsing/mime_generated.c
         src/index/web.c src/index/web.h
         src/web/serve.c src/web/serve.h
+        src/web/web_util.c src/web/web_util.h
         src/index/elastic.c src/index/elastic.h
         src/util.c src/util.h
-        src/ctx.h src/types.h
+        src/ctx.c src/ctx.h
+        src/types.h
         src/log.c src/log.h
         src/cli.c src/cli.h
-        src/stats.c src/stats.h src/ctx.c
         src/parsing/sidecar.c src/parsing/sidecar.h
+        src/database/database.c src/database/database.h
+        src/parsing/fs_util.h
 
-        # argparse
-        third-party/argparse/argparse.h third-party/argparse/argparse.c
-        )
+        src/auth0/auth0_c_api.h src/auth0/auth0_c_api.cpp
+
+        src/database/database_stats.c
+        src/database/database_schema.c
+        src/database/database_fts.c
+        src/web/web_fts.c
+)
+set_target_properties(sist2 PROPERTIES LINKER_LANGUAGE C)
 
 target_link_directories(sist2 PRIVATE BEFORE ${_VCPKG_INSTALLED_DIR}/${VCPKG_TARGET_TRIPLET}/lib/)
 set(CMAKE_FIND_LIBRARY_SUFFIXES .a .lib)
 
 find_package(PkgConfig REQUIRED)
 
-pkg_search_module(GLIB REQUIRED glib-2.0)
-
-find_package(lmdb CONFIG REQUIRED)
 find_package(cJSON CONFIG REQUIRED)
 find_package(unofficial-mongoose CONFIG REQUIRED)
 find_package(CURL CONFIG REQUIRED)
-find_library(MAGIC_LIB
-        NAMES libmagic.so.1 magic
-        PATHS /usr/lib/x86_64-linux-gnu/ /usr/lib/aarch64-linux-gnu/
-)
+find_library(MAGIC_LIB NAMES libmagic.a REQUIRED)
+find_package(unofficial-sqlite3 CONFIG REQUIRED)
 
 
 target_include_directories(
@@ -67,7 +84,6 @@ target_include_directories(
         ${CMAKE_SOURCE_DIR}/third-party/utf8.h/
         ${CMAKE_SOURCE_DIR}/third-party/libscan/
         ${CMAKE_SOURCE_DIR}/
-        ${GLIB_INCLUDE_DIRS}
 )
 
 target_compile_options(
@@ -85,7 +101,7 @@ if (SIST_DEBUG)
             -fno-omit-frame-pointer
             -fsanitize=address
             -fno-inline
-#            -O2
+            #            -O2
     )
     target_link_options(
             sist2
@@ -115,8 +131,10 @@ else ()
             PRIVATE
 
             -Ofast
+#            -g
             -fno-stack-protector
             -fomit-frame-pointer
+            -w
     )
 endif ()
 
@@ -130,20 +148,16 @@ target_link_libraries(
         sist2
 
         z
-        lmdb
-        cjson
         argparse
-        ${GLIB_LDFLAGS}
         unofficial::mongoose::mongoose
         CURL::libcurl
 
         pthread
 
-        c
-
         scan
 
         ${MAGIC_LIB}
+        unofficial::sqlite3::sqlite3
 )
 
 add_custom_target(

Dockerfile

@@ -1,28 +1,58 @@
 FROM simon987/sist2-build as build
 MAINTAINER simon987 <me@simon987.net>
 
+ENV DEBIAN_FRONTEND=noninteractive
+
+RUN curl -fsSL https://deb.nodesource.com/setup_16.x | bash
+RUN apt update -y; apt install -y nodejs && rm -rf /var/lib/apt/lists/*
+
 WORKDIR /build/
-COPY . .
-RUN cmake -DSIST_PLATFORM=x64_linux -DSIST_DEBUG=off -DBUILD_TESTS=off -DCMAKE_TOOLCHAIN_FILE=/vcpkg/scripts/buildsystems/vcpkg.cmake .
-RUN make -j$(nproc)
-RUN strip sist2 || mv sist2_debug sist2
 
-FROM --platform="linux/amd64" ubuntu:21.10
+COPY scripts scripts
+COPY schema schema
+COPY CMakeLists.txt .
+COPY third-party third-party
+COPY src src
+COPY sist2-vue sist2-vue
+COPY sist2-admin sist2-admin
 
-RUN apt update && apt install -y curl libasan5 libmagic1 && rm -rf /var/lib/apt/lists/*
+RUN cd sist2-vue/ && npm install && npm run build
+RUN cd sist2-admin/frontend/ && npm install && npm run build
 
-RUN mkdir -p /usr/share/tessdata && \
-    cd /usr/share/tessdata/ && \
-    curl -o /usr/share/tessdata/hin.traineddata https://raw.githubusercontent.com/tesseract-ocr/tessdata/master/hin.traineddata &&\
-    curl -o /usr/share/tessdata/jpn.traineddata https://raw.githubusercontent.com/tesseract-ocr/tessdata/master/jpn.traineddata &&\
-    curl -o /usr/share/tessdata/eng.traineddata https://raw.githubusercontent.com/tesseract-ocr/tessdata/master/eng.traineddata &&\
-    curl -o /usr/share/tessdata/fra.traineddata https://raw.githubusercontent.com/tesseract-ocr/tessdata/master/fra.traineddata &&\
-    curl -o /usr/share/tessdata/rus.traineddata https://raw.githubusercontent.com/tesseract-ocr/tessdata/master/rus.traineddata &&\
-    curl -o /usr/share/tessdata/spa.traineddata https://raw.githubusercontent.com/tesseract-ocr/tessdata/master/spa.traineddata
+RUN mkdir build && cd build && cmake -DSIST_PLATFORM=x64_linux_docker -DSIST_DEBUG_INFO=on -DSIST_DEBUG=off -DBUILD_TESTS=off -DCMAKE_TOOLCHAIN_FILE=/vcpkg/scripts/buildsystems/vcpkg.cmake ..
+RUN cd build && make -j$(nproc)
+RUN strip build/sist2 || mv build/sist2_debug build/sist2
+
+FROM --platform="linux/amd64" ubuntu@sha256:965fbcae990b0467ed5657caceaec165018ef44a4d2d46c7cdea80a9dff0d1ea
 
-ENTRYPOINT ["/root/sist2"]
 
 ENV LANG C.UTF-8
 ENV LC_ALL C.UTF-8
 
-COPY --from=build /build/sist2 /root/sist2
+ENTRYPOINT ["/root/sist2"]
+
+RUN apt update && DEBIAN_FRONTEND=noninteractive apt install -y curl libasan5 libmagic1 python3  \
+    python3-pip git tesseract-ocr && rm -rf /var/lib/apt/lists/*
+
+RUN mkdir -p /usr/share/tessdata && \
+    cd /usr/share/tessdata/ && \
+    curl -o /usr/share/tesseract-ocr/4.00/tessdata/hin.traineddata https://raw.githubusercontent.com/tesseract-ocr/tessdata/master/hin.traineddata &&\
+    curl -o /usr/share/tesseract-ocr/4.00/tessdata/jpn.traineddata https://raw.githubusercontent.com/tesseract-ocr/tessdata/master/jpn.traineddata &&\
+    curl -o /usr/share/tesseract-ocr/4.00/tessdata/eng.traineddata https://raw.githubusercontent.com/tesseract-ocr/tessdata/master/eng.traineddata &&\
+    curl -o /usr/share/tesseract-ocr/4.00/tessdata/fra.traineddata https://raw.githubusercontent.com/tesseract-ocr/tessdata/master/fra.traineddata &&\
+    curl -o /usr/share/tesseract-ocr/4.00/tessdata/rus.traineddata https://raw.githubusercontent.com/tesseract-ocr/tessdata/master/rus.traineddata &&\
+    curl -o /usr/share/tesseract-ocr/4.00/tessdata/osd.traineddata https://raw.githubusercontent.com/tesseract-ocr/tessdata/master/osd.traineddata &&\
+    curl -o /usr/share/tesseract-ocr/4.00/tessdata/spa.traineddata https://raw.githubusercontent.com/tesseract-ocr/tessdata/master/spa.traineddata &&\
+    curl -o /usr/share/tesseract-ocr/4.00/tessdata/deu.traineddata https://raw.githubusercontent.com/tesseract-ocr/tessdata/master/deu.traineddata &&\
+    curl -o /usr/share/tesseract-ocr/4.00/tessdata/equ.traineddata https://raw.githubusercontent.com/tesseract-ocr/tessdata/master/equ.traineddata &&\
+    curl -o /usr/share/tesseract-ocr/4.00/tessdata/pol.traineddata https://raw.githubusercontent.com/tesseract-ocr/tessdata/master/pol.traineddata &&\
+    curl -o /usr/share/tesseract-ocr/4.00/tessdata/chi_sim.traineddata https://raw.githubusercontent.com/tesseract-ocr/tessdata/master/chi_sim.traineddata
+
+# sist2
+COPY --from=build /build/build/sist2 /root/sist2
+
+# sist2-admin
+WORKDIR /root/sist2-admin
+COPY sist2-admin/requirements.txt /root/sist2-admin/
+RUN python3 -m pip install --no-cache -r /root/sist2-admin/requirements.txt
+COPY --from=build /build/sist2-admin/ /root/sist2-admin/

Dockerfile.arm64

@@ -3,26 +3,39 @@ MAINTAINER simon987 <me@simon987.net>
 
 WORKDIR /build/
 ADD . /build/
-RUN cmake -DSIST_PLATFORM=arm64_linux -DSIST_DEBUG=off -DBUILD_TESTS=off -DCMAKE_TOOLCHAIN_FILE=/vcpkg/scripts/buildsystems/vcpkg.cmake .
-RUN make -j$(nproc)
-RUN strip sist2
+RUN mkdir build && cd build && cmake -DSIST_PLATFORM=arm64_linux_docker -DSIST_DEBUG_INFO=on -DSIST_DEBUG=off -DBUILD_TESTS=off -DCMAKE_TOOLCHAIN_FILE=/vcpkg/scripts/buildsystems/vcpkg.cmake ..
+RUN cd build && make -j$(nproc)
+RUN strip build/sist2 || mv build/sist2_debug build/sist2
 
-FROM --platform="linux/arm64/v8" ubuntu:21.10
+FROM --platform=linux/arm64/v8 ubuntu@sha256:537da24818633b45fcb65e5285a68c3ec1f3db25f5ae5476a7757bc8dfae92a3
 
-RUN apt update && apt install -y curl libasan5 && rm -rf /var/lib/apt/lists/*
-
-RUN mkdir -p /usr/share/tessdata && \
-    cd /usr/share/tessdata/ && \
-    curl -o /usr/share/tessdata/hin.traineddata https://raw.githubusercontent.com/tesseract-ocr/tessdata/master/hin.traineddata &&\
-    curl -o /usr/share/tessdata/jpn.traineddata https://raw.githubusercontent.com/tesseract-ocr/tessdata/master/jpn.traineddata &&\
-    curl -o /usr/share/tessdata/eng.traineddata https://raw.githubusercontent.com/tesseract-ocr/tessdata/master/eng.traineddata &&\
-    curl -o /usr/share/tessdata/fra.traineddata https://raw.githubusercontent.com/tesseract-ocr/tessdata/master/fra.traineddata &&\
-    curl -o /usr/share/tessdata/rus.traineddata https://raw.githubusercontent.com/tesseract-ocr/tessdata/master/rus.traineddata &&\
-    curl -o /usr/share/tessdata/spa.traineddata https://raw.githubusercontent.com/tesseract-ocr/tessdata/master/spa.traineddata
+WORKDIR /root
 
 ENV LANG C.UTF-8
 ENV LC_ALL C.UTF-8
 
 ENTRYPOINT ["/root/sist2"]
 
-COPY --from=build /build/sist2 /root/sist2
+RUN apt update && apt install -y curl libasan5 libmagic1 tesseract-ocr python3-pip python3 git && rm -rf /var/lib/apt/lists/*
+
+RUN mkdir -p /usr/share/tessdata && \
+    cd /usr/share/tessdata/ && \
+    curl -o /usr/share/tesseract-ocr/4.00/tessdata/hin.traineddata https://raw.githubusercontent.com/tesseract-ocr/tessdata/master/hin.traineddata &&\
+    curl -o /usr/share/tesseract-ocr/4.00/tessdata/jpn.traineddata https://raw.githubusercontent.com/tesseract-ocr/tessdata/master/jpn.traineddata &&\
+    curl -o /usr/share/tesseract-ocr/4.00/tessdata/eng.traineddata https://raw.githubusercontent.com/tesseract-ocr/tessdata/master/eng.traineddata &&\
+    curl -o /usr/share/tesseract-ocr/4.00/tessdata/fra.traineddata https://raw.githubusercontent.com/tesseract-ocr/tessdata/master/fra.traineddata &&\
+    curl -o /usr/share/tesseract-ocr/4.00/tessdata/rus.traineddata https://raw.githubusercontent.com/tesseract-ocr/tessdata/master/rus.traineddata &&\
+    curl -o /usr/share/tesseract-ocr/4.00/tessdata/osd.traineddata https://raw.githubusercontent.com/tesseract-ocr/tessdata/master/osd.traineddata &&\
+    curl -o /usr/share/tesseract-ocr/4.00/tessdata/spa.traineddata https://raw.githubusercontent.com/tesseract-ocr/tessdata/master/spa.traineddata &&\
+    curl -o /usr/share/tesseract-ocr/4.00/tessdata/deu.traineddata https://raw.githubusercontent.com/tesseract-ocr/tessdata/master/deu.traineddata &&\
+    curl -o /usr/share/tesseract-ocr/4.00/tessdata/equ.traineddata https://raw.githubusercontent.com/tesseract-ocr/tessdata/master/equ.traineddata &&\
+    curl -o /usr/share/tesseract-ocr/4.00/tessdata/pol.traineddata https://raw.githubusercontent.com/tesseract-ocr/tessdata/master/pol.traineddata &&\
+    curl -o /usr/share/tesseract-ocr/4.00/tessdata/chi_sim.traineddata https://raw.githubusercontent.com/tesseract-ocr/tessdata/master/chi_sim.traineddata
+
+# sist2
+COPY --from=build /build/build/sist2 /root/sist2
+
+# sist2-admin
+COPY sist2-admin/requirements.txt sist2-admin/
+RUN python3 -m pip install --no-cache -r sist2-admin/requirements.txt
+COPY --from=build /build/sist2-admin/ sist2-admin/

README.md

@@ -10,13 +10,13 @@ sist2 (Simple incremental search tool)
 
 *Warning: sist2 is in early development*
 
-![search panel](docs/sist2.png)
+![search panel](docs/sist2.gif)
 
 ## Features
 
 * Fast, low memory usage, multi-threaded
+* Manage & schedule scan jobs with simple web interface (Docker only)
 * Mobile-friendly Web interface
-* Portable (all its features are packaged in a single executable)
 * Extracts text and metadata from common file types \*
 * Generates thumbnails \*
 * Incremental scanning
@@ -24,47 +24,64 @@ sist2 (Simple incremental search tool)
 * Recursive scan inside archive files \*\*
 * OCR support with tesseract \*\*\*
 * Stats page & disk utilisation visualization
+* Named-entity recognition (client-side) \*\*\*\*
 
 \* See [format support](#format-support)    
 \*\* See [Archive files](#archive-files)    
 \*\*\* See [OCR](#ocr)    
-
-![stats](docs/stats.png)
+\*\*\*\* See [Named-Entity Recognition](#NER)
 
 ## Getting Started
 
-1. Have an Elasticsearch (>= 6.8.X, ideally >=7.14.0) instance running
-    1. Download [from official website](https://www.elastic.co/downloads/elasticsearch)
-    1. *(or)* Run using docker:
-        ```bash
-        docker run -d -p 9200:9200 -e "discovery.type=single-node" elasticsearch:7.14.0
-        ```
-    1. *(or)* Run using docker-compose:
-        ```yaml
+### Using Docker Compose *(Windows/Linux/Mac)*
+
+```yaml
+version: "3"
+
+services:
   elasticsearch:
-            image: docker.elastic.co/elasticsearch/elasticsearch:7.14.0
+    image: elasticsearch:7.17.9
+    restart: unless-stopped
     environment:
-              - discovery.type=single-node
-              - "ES_JAVA_OPTS=-Xms1G -Xmx2G"
+      - "discovery.type=single-node"
+      - "ES_JAVA_OPTS=-Xms2g -Xmx2g"
+  sist2-admin:
+    image: simon987/sist2:3.1.0-x64-linux
+    restart: unless-stopped
+    volumes:
+      - ./sist2-admin-data/:/sist2-admin/
+      - /:/host
+    ports:
+      - 4090:4090 # sist2
+      - 8080:8080 # sist2-admin
+    working_dir: /root/sist2-admin/
+    entrypoint: python3 /root/sist2-admin/sist2_admin/app.py
+```
+
+Navigate to http://localhost:8080/ to configure sist2-admin.
+
+### Using the executable file *(Linux/WSL only)*
+
+1. Choose search backend (See [comparison](#search-backends)):
+    * **Elasticsearch**: have an Elasticsearch (version >= 6.8.X, ideally >=7.14.0) instance running
+        1. Download [from official website](https://www.elastic.co/downloads/elasticsearch)
+        2. *(or)* Run using docker:
+            ```bash
+            docker run -d -p 9200:9200 -e "discovery.type=single-node" elasticsearch:7.17.9
             ```
-1. Download sist2 executable
-    1. Download the [latest sist2 release](https://github.com/simon987/sist2/releases). 
-Select the file corresponding to your CPU architecture and mark the binary as executable with `chmod +x` *
-    2. *(or)* Download a [development snapshot](https://files.simon987.net/.gate/sist2/simon987_sist2/) *(Not
-       recommended!)*
-    3. *(or)* `docker pull simon987/sist2:2.12.1-x64-linux`
+    * **SQLite**: No installation required
 
-1. See [Usage guide](docs/USAGE.md)
+2. Download the [latest sist2 release](https://github.com/simon987/sist2/releases).
+   Select the file corresponding to your CPU architecture and mark the binary as executable with `chmod +x`.
+3. See [usage guide](docs/USAGE.md) for command line usage.
 
-\* *Windows users*: **sist2** runs under [WSL](https://en.wikipedia.org/wiki/Windows_Subsystem_for_Linux)
+Example usage:
 
-## Example usage
-
-See [Usage guide](docs/USAGE.md) for more details
-
-1. Scan a directory: `sist2 scan ~/Documents -o ./docs_idx`
-1. Push index to Elasticsearch: `sist2 index ./docs_idx`
-1. Start web interface: `sist2 web ./docs_idx`
+1. Scan a directory: `sist2 scan ~/Documents --output ./documents.sist2`
+2. Prepare search index:
+    * **Elasticsearch**: `sist2 index --es-url http://localhost:9200 ./documents.sist2`
+    * **SQLite**: `sist2 index --search-index ./search.sist2 ./documents.sist2`
+3. Start web interface: `sist2 web ./documents.sist2`
 
 ## Format support
 
@@ -81,8 +98,8 @@ See [Usage guide](docs/USAGE.md) for more details
 | html, xml                                                                 | [libscan](https://github.com/simon987/sist2/tree/master/third-party/libscan) | yes      | no          | -                                                                                                                                      |
 | tar, zip, rar, 7z, ar ...                                                 | Libarchive                                                                   | yes\*    | -           | no                                                                                                                                     |
 | docx, xlsx, pptx                                                          | [libscan](https://github.com/simon987/sist2/tree/master/third-party/libscan) | yes      | if embedded | creator, modified_by, title                                                                                                            |
-| doc (MS Word 97-2003)                                                     | antiword                                                                     | yes      | yes         | author, title                                                                                                                          |
-| mobi, azw, azw3                                                           | libmobi                                                                      | yes      | no          | author, title                                                                                                                          |
+| doc (MS Word 97-2003)                                                     | antiword                                                                     | yes      | no          | author, title                                                                                                                          |
+| mobi, azw, azw3                                                           | libmobi                                                                      | yes      | yes         | author, title                                                                                                                          |
 | wpd (WordPerfect)                                                         | libwpd                                                                       | yes      | no          | *planned*                                                                                                                              |
 | json, jsonl, ndjson                                                       | [libscan](https://github.com/simon987/sist2/tree/master/third-party/libscan) | yes      | -           | -                                                                                                                                      |
 
@@ -109,7 +126,7 @@ Download the language data files with your package manager (`apt install tessera
 directly [from Github](https://github.com/tesseract-ocr/tesseract/wiki/Data-Files).
 
 The `simon987/sist2` image comes with common languages
-(hin, jpn, eng, fra, rus, spa) pre-installed.
+(hin, jpn, eng, fra, rus, spa, chi_sim, deu, pol) pre-installed.
 
 You can use the `+` separator to specify multiple languages. The language
 name must be identical to the `*.traineddata` file installed on your system
@@ -123,39 +140,80 @@ sist2 scan --ocr-images --ocr-lang eng ~/Images/Screenshots/
 sist2 scan --ocr-ebooks --ocr-images --ocr-lang eng+chi_sim ~/Chinese-Bilingual/
 ```
 
+### Search backends
+
+sist2 v3.0.7+ supports SQLite search backend. The SQLite search backend has
+fewer features and generally comparable query performance for medium-size
+indices, but it uses much less memory and is easier to set up.
+
+|                                              |                  SQLite                  |                                                             Elasticsearch                                                             |
+|----------------------------------------------|:----------------------------------------:|:-------------------------------------------------------------------------------------------------------------------------------------:|
+| Requires separate search engine installation |                                          |                                                                   ✓                                                                   |
+| Memory footprint                             |                  ~20MB                   |                                                                >500MB                                                                 |
+| Query syntax                                 | [fts5](https://www.sqlite.org/fts5.html) | [query_string](https://www.elastic.co/guide/en/elasticsearch/reference/current/query-dsl-query-string-query.html#query-string-syntax) |
+| Fuzzy search                                 |                                          |                                                                   ✓                                                                   |
+| Media Types tree real-time updating          |                                          |                                                                   ✓                                                                   |
+| Search in file `path`                        |                                          |                                                                   ✓                                                                   |
+| Manual tagging                               |                    ✓                     |                                                                   ✓                                                                   |
+| User scripts                                 |                                          |                                                                   ✓                                                                   |
+| Media Type breakdown for search results      |                                          |                                                                   ✓                                                                   |
+
+### NER
+
+sist2 v3.0.4+ supports named-entity recognition (NER). Simply add a supported repository URL to
+**Configuration** > **Machine learning options** > **Model repositories**
+to enable it.
+
+The text processing is done in your browser, no data is sent to any third-party services.
+See [simon987/sist2-ner-models](https://github.com/simon987/sist2-ner-models) for more details.
+
+#### List of available repositories:
+
+| URL                                                                                                     | Maintainer                              | Purpose |
+|---------------------------------------------------------------------------------------------------------|-----------------------------------------|---------|
+| [simon987/sist2-ner-models](https://raw.githubusercontent.com/simon987/sist2-ner-models/main/repo.json) | [simon987](https://github.com/simon987) | General |
+
+<details>
+  <summary>Screenshot</summary>
+
+![ner](docs/ner.png)
+
+</details>
+
 ## Build from source
 
 You can compile **sist2** by yourself if you don't want to use the pre-compiled binaries
 
-### With docker (recommended)
+### Using docker
 
 ```bash
 git clone --recursive https://github.com/simon987/sist2/
 cd sist2
-docker build . -f ./Dockerfile -t my-sist2-image
+docker build . -t my-sist2-image
+# Copy sist2 executable from docker image
 docker run --rm --entrypoint cat my-sist2-image /root/sist2 > sist2-x64-linux
 ```
 
-### On a linux computer
+### Using a linux computer
 
 1. Install compile-time dependencies
 
    ```bash
-   apt install gcc g++ python3 yasm ragel automake autotools-dev wget libtool libssl-dev curl zip unzip tar xorg-dev libglu1-mesa-dev libxcursor-dev libxml2-dev libxinerama-dev gettext nasm git
+   apt install gcc g++ python3 yasm ragel automake autotools-dev wget libtool libssl-dev curl zip unzip tar xorg-dev libglu1-mesa-dev libxcursor-dev libxml2-dev libxinerama-dev gettext nasm git nodejs
    ```
 
-1. Apply vcpkg patches, as per [sist2-build](https://github.com/simon987/sist2-build) Dockerfile
-
-1. Install vcpkg dependencies
+2. Install vcpkg using my fork: https://github.com/simon987/vcpkg
+3. Install vcpkg dependencies
 
     ```bash
-    vcpkg install curl[core,openssl]
-    vcpkg install lmdb cjson glib brotli libarchive[core,bzip2,libxml2,lz4,lzma,lzo] pthread tesseract libxml2 libmupdf gtest mongoose libmagic libraw jasper lcms gumbo
+    vcpkg install curl[core,openssl] sqlite3[core,fts5] cpp-jwt pcre cjson brotli libarchive[core,bzip2,libxml2,lz4,lzma,lzo] pthread tesseract libxml2 libmupdf gtest mongoose libmagic libraw gumbo ffmpeg[core,avcodec,avformat,swscale,swresample,webp]
     ```
 
-1. Build
+4. Build
     ```bash
     git clone --recursive https://github.com/simon987/sist2/
+    (cd sist2-vue; npm install; npm run build)
+    (cd sist2-admin/frontend; npm install; npm run build)
     cmake -DSIST_DEBUG=off -DCMAKE_TOOLCHAIN_FILE=<VCPKG_ROOT>/scripts/buildsystems/vcpkg.cmake .
     make
     ```

contrib/systemd/sist2-update-files.sh

@@ -12,7 +12,7 @@ REWRITE_URL=""
 sist2 scan \
   --threads 14 \
   --mem-throttle 32768 \
-  --quality 1.0 \
+  --thumbnail-quality 2 \
   --name $NAME \
   --ocr-lang=eng+chi_sim \
   --ocr-ebooks \

contrib/systemd/sist2-update-nextcloud.sh

@@ -12,7 +12,7 @@ REWRITE_URL=""
 sist2 scan \
   --threads 14 \
   --mem-throttle 32768 \
-  --quality 1.0 \
+  --thumbnail-quality 2 \
   --name $NAME \
   --ocr-lang=eng+chi_sim \
   --ocr-ebooks \

docker-compose.yml

@@ -0,0 +1,24 @@
+version: "3"
+
+services:
+  elasticsearch:
+    image: elasticsearch:7.17.9
+    container_name: sist2-es
+    environment:
+      - "discovery.type=single-node"
+      - "ES_JAVA_OPTS=-Xms2g -Xmx2g"
+  sist2-admin:
+    build:
+      context: .
+    container_name: sist2-admin
+    volumes:
+      - /mnt/array/sist2-admin-data/:/sist2-admin/
+      - /:/host
+    ports:
+      - 4090:4090
+      # NOTE: Don't export this port publicly!
+      - 8080:8080
+    working_dir: /root/sist2-admin/
+    entrypoint: python3
+    command:
+      - /root/sist2-admin/sist2_admin/app.py

docs/USAGE.md

@@ -1,154 +1,97 @@
 # Usage
 
-*More examples (specifically with docker/compose) are in progress*
-
-* [scan](#scan)
-    * [options](#scan-options)
-    * [examples](#scan-examples)
-    * [index format](#index-format)
-* [index](#index)
-    * [options](#index-options)
-    * [examples](#index-examples)
-* [web](#web)
-    * [options](#web-options)
-    * [examples](#web-examples)
-    * [rewrite_url](#rewrite_url)
-* [elasticsearch](#elasticsearch)
-* [exec-script](#exec-script)
-* [tagging](#tagging)
-* [sidecar files](#sidecar-files)
-
 ```
 Usage: sist2 scan [OPTION]... PATH
    or: sist2 index [OPTION]... INDEX
+   or: sist2 sqlite-index [OPTION]... INDEX
    or: sist2 web [OPTION]... INDEX...
    or: sist2 exec-script [OPTION]... INDEX
+
 Lightning-fast file system indexer and search tool.
 
     -h, --help                        show this help message and exit
-    -v, --version                     Show version and exit
-    --verbose                         Turn on logging
-    --very-verbose                    Turn on debug messages
+    -v, --version                     Print version and exit.
+    --verbose                         Turn on logging.
+    --very-verbose                    Turn on debug messages.
+    --json-logs                       Output logs in JSON format.
 
 Scan options
-    -t, --threads=<int>               Number of threads. DEFAULT=1
-    --mem-throttle=<int>              Total memory threshold in MiB for scan throttling. DEFAULT=0
-    -q, --thumbnail-quality=<flt>     Thumbnail quality, on a scale of 1.0 to 31.0, 1.0 being the best. DEFAULT=1
-    --thumbnail-size=<int>            Thumbnail size, in pixels. DEFAULT=500
-    --thumbnail-count=<int>           Number of thumbnails to generate. Set a value > 1 to create video previews, set to 0 to disable thumbnails. DEFAULT=1
-    --content-size=<int>              Number of bytes to be extracted from text documents. Set to 0 to disable. DEFAULT=32768
-    --incremental=<str>               Reuse an existing index and only scan modified files.
-    -o, --output=<str>                Output directory. DEFAULT=index.sist2/
+    -t, --threads=<int>               Number of threads. DEFAULT: 1
+    -q, --thumbnail-quality=<int>     Thumbnail quality, on a scale of 0 to 100, 100 being the best. DEFAULT: 50
+    --thumbnail-size=<int>            Thumbnail size, in pixels. DEFAULT: 552
+    --thumbnail-count=<int>           Number of thumbnails to generate. Set a value > 1 to create video previews, set to 0 to disable thumbnails. DEFAULT: 1
+    --content-size=<int>              Number of bytes to be extracted from text documents. Set to 0 to disable. DEFAULT: 32768
+    -o, --output=<str>                Output index file path. DEFAULT: index.sist2
+    --incremental                     If the output file path exists, only scan new or modified files.
+    --optimize-index                  Defragment index file after scan to reduce its file size.
     --rewrite-url=<str>               Serve files from this url instead of from disk.
-    --name=<str>                      Index display name. DEFAULT: (name of the directory)
+    --name=<str>                      Index display name. DEFAULT: index
     --depth=<int>                     Scan up to DEPTH subdirectories deep. Use 0 to only scan files in PATH. DEFAULT: -1
-    --archive=<str>                   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
+    --archive=<str>                   Archive file mode (skip|list|shallow|recurse). skip: don't scan, list: only save file names as text, shallow: don't scan archives inside archives. DEFAULT: recurse
     --archive-passphrase=<str>        Passphrase for encrypted archive files
     --ocr-lang=<str>                  Tesseract language (use 'tesseract --list-langs' to see which are installed on your machine)
     --ocr-images                      Enable OCR'ing of image files.
     --ocr-ebooks                      Enable OCR'ing of ebook files.
-    -e, --exclude=<str>               Files that match this regex will not be scanned
-    --fast                            Only index file names & mime type
+    -e, --exclude=<str>               Files that match this regex will not be scanned.
+    --fast                            Only index file names & mime type.
     --treemap-threshold=<str>         Relative size threshold for treemap (see USAGE.md). DEFAULT: 0.0005
     --mem-buffer=<int>                Maximum memory buffer size per thread in MiB for files inside archives (see USAGE.md). DEFAULT: 2000
     --read-subtitles                  Read subtitles from media files.
-    --fast-epub                       Faster but less accurate EPUB parsing (no thumbnails, metadata)
+    --fast-epub                       Faster but less accurate EPUB parsing (no thumbnails, metadata).
     --checksums                       Calculate file checksums when scanning.
     --list-file=<str>                 Specify a list of newline-delimited paths to be scanned instead of normal directory traversal. Use '-' to read from stdin.
 
 Index options
-    -t, --threads=<int>               Number of threads. DEFAULT=1
-    --es-url=<str>                    Elasticsearch url with port. DEFAULT=http://localhost:9200
-    --es-index=<str>                  Elasticsearch index name. DEFAULT=sist2
-    -p, --print                       Just print JSON documents to stdout.
-    --incremental-index               Conduct incremental indexing, assumes that the old index is already digested by Elasticsearch.
+    -t, --threads=<int>               Number of threads. DEFAULT: 1
+    --es-url=<str>                    Elasticsearch url with port. DEFAULT: http://localhost:9200
+    --es-insecure-ssl                 Do not verify SSL connections to Elasticsearch.
+    --es-index=<str>                  Elasticsearch index name. DEFAULT: sist2
+    -p, --print                       Print JSON documents to stdout instead of indexing to elasticsearch.
+    --incremental-index               Conduct incremental indexing. Assumes that the old index is already ingested in Elasticsearch.
     --script-file=<str>               Path to user script.
     --mappings-file=<str>             Path to Elasticsearch mappings.
     --settings-file=<str>             Path to Elasticsearch settings.
     --async-script                    Execute user script asynchronously.
-    --batch-size=<int>                Index batch size. DEFAULT: 100
-    -f, --force-reset                 Reset Elasticsearch mappings and settings. (You must use this option the first time you use the index command)
+    --batch-size=<int>                Index batch size. DEFAULT: 70
+    -f, --force-reset                 Reset Elasticsearch mappings and settings.
+
+sqlite-index options
+    --search-index=<str>              Path to search index. Will be created if it does not exist yet.
 
 Web options
-    --es-url=<str>                    Elasticsearch url. DEFAULT=http://localhost:9200
-    --es-index=<str>                  Elasticsearch index name. DEFAULT=sist2
-    --bind=<str>                      Listen on this address. DEFAULT=localhost:4090
+    --es-url=<str>                    Elasticsearch url. DEFAULT: http://localhost:9200
+    --es-insecure-ssl                 Do not verify SSL connections to Elasticsearch.
+    --search-index=<str>              Path to SQLite search index.
+    --es-index=<str>                  Elasticsearch index name. DEFAULT: sist2
+    --bind=<str>                      Listen for connections on this address. DEFAULT: localhost:4090
     --auth=<str>                      Basic auth in user:password format
+    --auth0-audience=<str>            API audience/identifier
+    --auth0-domain=<str>              Application domain
+    --auth0-client-id=<str>           Application client ID
+    --auth0-public-key-file=<str>     Path to Auth0 public key file extracted from <domain>/pem
     --tag-auth=<str>                  Basic auth in user:password format for tagging
     --tagline=<str>                   Tagline in navbar
     --dev                             Serve html & js files from disk (for development)
     --lang=<str>                      Default UI language. Can be changed by the user
 
 Exec-script options
-    --es-url=<str>                    Elasticsearch url. DEFAULT=http://localhost:9200
-    --es-index=<str>                  Elasticsearch index name. DEFAULT=sist2
+    --es-url=<str>                    Elasticsearch url. DEFAULT: http://localhost:9200
+    --es-insecure-ssl                 Do not verify SSL connections to Elasticsearch.
+    --es-index=<str>                  Elasticsearch index name. DEFAULT: sist2
     --script-file=<str>               Path to user script.
     --async-script                    Execute user script asynchronously.
+
 Made by simon987 <me@simon987.net>. Released under GPL-3.0
 ```
 
-## Scan
+#### Thumbnail database size estimation
 
-### Scan options
+See chart below for rough estimate of thumbnail size vs. thumbnail size & quality arguments:
 
-* `-t, --threads` 
-      Number of threads for file parsing. **Do not set a number higher than `$(nproc)` or `$(Get-CimInstance Win32_ComputerSystem).NumberOfLogicalProcessors` in Windows!**
-* `--mem-throttle`
-    Total memory threshold in MiB for scan throttling. Worker threads will not start a new parse job
-    until the total memory usage of sist2 is below this threshold. Set to 0 to disable. DEFAULT=0
-* `-q, --thumbnail-quality` 
-    Thumbnail quality, on a scale of 1.0 to 31.0, 1.0 being the best.
-* `--thumbnail-size` 
-    Thumbnail size in pixels.
-* `--thumbnail-count`
-    Maximum number of thumbnails to generate. When set to a value >= 2, thumbnails for video previews
-    will be generated. The actual number of thumbnails generated depends on the length of the video (maximum 1 image 
-    every ~7s). Set to 0 to completely disable thumbnails.
-* `--content-size` 
-    Number of bytes of text to be extracted from the content of files (plain text, PDFs etc.).
-    Repeated whitespace and special characters do not count toward this limit.
-    Set to 0 to completely disable content parsing.
-* `--incremental`
-    Specify an existing index. Information about files in this index that were not modified (based on *mtime* attribute)
-    will be copied to the new index and will not be parsed again.
-* `-o, --output` Output directory. 
-* `--rewrite-url` Set the `rewrite_url` option for the web module (See [rewrite_url](#rewrite_url)) 
-* `--name` Set the `name` option for the web module
-* `--depth` Maximum scan dept. Set to 0 only scan files directly in the root directory, set to -1 for infinite depth
-* `--archive` Archive file mode.
-    * skip: Don't parse
-    * list: Only get file names as text
-    * shallow: Don't parse archives inside archives.
-    * recurse: Scan archives recursively (default)
-* `--ocr-lang`, `--ocr-ebooks`, `--ocr-images` See [OCR](../README.md#OCR)
-* `-e, --exclude` Regex pattern to exclude files. A file is excluded if the pattern matches any 
-    part of the full absolute path.
+For example, `--thumbnail-size=500`, `--thumbnail-quality=50` for a directory with 8 million images will create a thumbnail database 
+that is about `8000000 * 11.8kB = 94.4GB`.
 
-    Examples: 
-    * `-e ".*\.ttf"`: Ignore ttf files
-    * `-e ".*\.(ttf|rar)"`: Ignore ttf and rar files
-    * `-e "^/mnt/backups/"`: Ignore all files in the `/mnt/backups/` directory
-    * `-e "^/mnt/Data[12]/"`: Ignore all files in the `/mnt/Data1/` and `/mnt/Data2/` directory
-    * `-e "(^/usr/)|(^/var/)|(^/media/DRIVE-A/tmp/)|(^/media/DRIVE-B/Trash/)"` Exclude the
-     `/usr`, `/var`, `/media/DRIVE-A/tmp`, `/media/DRIVE-B/Trash` directories
-* `--fast` Only index file names and mime type
-* `--treemap-threshold` Directories smaller than (`treemap-threshold` * `<total size of the index>`)
-    will not be considered for the disk utilisation visualization; their size will be added to
-    the parent directory. If the parent directory is still smaller than the threshold, it will also be "merged upwards"
-    and so on.
-    
-    In effect, smaller `treemap-threshold` values will yield a more detailed 
-    (but also a more cluttered and harder to read) visualization. 
-    
-* `--mem-buffer` Maximum memory buffer size in MiB (per thread) for files inside archives. Media files 
-    larger than this number will be read sequentially and no *seek* operations will be supported.
-
-    To check if a media file can be parsed without *seek*, execute `cat file.mp4 | ffprobe -`
-* `--read-subtitles` When enabled, will attempt to read the subtitles stream from media files.
-* `--fast-epub` Much faster but less accurate EPUB parsing. When enabled, sist2 will use a simple HTML parser to read epub files instead of the MuPDF library. No thumbnails are generated and author/title metadata are not parsed.
-* `--checksums` Calculate file checksums (SHA1) when scanning files. This option does not cause any additional read 
-  operations. Checksums are not calculated for all file types, unless the file is inside an archive. When enabled, duplicate
-  files are hidden in the web UI (this behaviour can be toggled in the Configuration page).
+![thumbnail_size](thumbnail_size.png)
 
 ### Scan examples
 
@@ -157,131 +100,70 @@ Simple scan
 sist2 scan ~/Documents
 
 sist2 scan \
-    --threads 4 --content-size 16000000 --quality 1.0 --archive shallow \
+    --threads 4 --content-size 16000000 --thumbnail-quality 2 --archive shallow \
     --name "My Documents" --rewrite-url "http://nas.domain.local/My Documents/" \
-    ~/Documents -o ./documents.idx/
+    ~/Documents -o ./documents.sist2
 ```
 
 Incremental scan
-```
-sist2 scan --incremental ./orig_idx/ -o ./updated_idx/ ~/Documents
-```
 
-### Index format
-
-A typical `ndjson` type index structure looks like this:
-```
-documents.idx/
-├── descriptor.json
-├── _index_main.ndjson.zst
-├── treemap.csv
-├── agg_mime.csv
-├── agg_date.csv
-├── add_size.csv
-├── thumbs/
-|   ├── data.mdb
-|   └── lock.mdb
-├── tags/
-|   ├── data.mdb
-|   └── lock.mdb
-└── meta/
-    ├── data.mdb
-    └── lock.mdb
-```
-
-The `_index_*.ndjson.zst` files contain the document data in JSON format, in a compressed newline-delemited file.
-
-The `thumbs/` folder is a [LMDB](https://en.wikipedia.org/wiki/Lightning_Memory-Mapped_Database)
-database containing the thumbnails.
-
-The `descriptor.json` file contains general information about the index. The 
-following fields are safe to modify manually: `root`, `name`, [rewrite_url](#rewrite_url) and `timestamp`.
-
-The `.csv` are pre-computed aggregations necessary for the stats page.
-
-*thumbs/*:
-
-LMDB key-value store. Keys are **binary** 16-byte md5 hash* (`_id` field)
-and values are raw image bytes.
-
-*\* Hash is calculated from the full path of the file, including the extension, relative to the index root*
-
-
-## Index
-### Index options
- * `--es-url` 
- Elasticsearch url and port. If you are using docker, make sure that both containers are on the
- same network.
- * `--es-index` 
-    Elasticsearch index name. DEFAULT=sist2
- * `-p, --print` 
-    Print index in JSON format to stdout.
- * `--incremental-index`
-   Conduct incremental indexing. Assumes that the old index is already ingested in Elasticsearch.
-   Only the new changes since the last scan will be sent.
- * `--script-file` 
-    Path to user script. See [Scripting](scripting.md).
- * `--mappings-file`
-    Path to custom Elasticsearch mappings. If none is specified, [the bundled mappings](https://github.com/simon987/sist2/tree/master/schema) will be used.
- * `--settings-file`
-    Path to custom Elasticsearch settings. *(See above)*
- * `--async-script` 
-    Use `wait_for_completion=false` elasticsearch option while executing user script.
-     (See [Elasticsearch documentation](https://www.elastic.co/guide/en/elasticsearch/reference/current/tasks.html))
- * `--batch-size=<int>` 
-    Index batch size. Indexing is generally faster with larger batches, but payloads that
-    are too large will fail and additional overhead for retrying with smaller sizes may slow
-    down the process.
- * `-f, --force-reset` 
-    Reset Elasticsearch mappings and settings.
- * `-t, --threads` Number of threads to use. Ideally, choose a number equal to the number of logical cores of the machine hosting Elasticsearch.
-    
-### Index examples
-
-**Push to elasticsearch**
+If the index file does not exist, `--incremental` has no effect.
 ```bash
-sist2 index --force-reset --batch-size 1000 --es-url http://localhost:9200 ./my_index/
-sist2 index ./my_index/
+sist scan ~/Documents -o ./documents.sist2
+sist scan ~/Documents -o ./documents.sist2 --incremental
+# or
+sist scan ~/Documents -o ./documents.sist2 --incremental
+sist scan ~/Documents -o ./documents.sist2 --incremental
+```
+
+### Index documents to Elasticsearch search backend
+
+```bash
+sist2 index --force-reset --batch-size 1000 --es-url http://localhost:9200 ./my_index.sist2
+sist2 index ./my_index.sist2
+```
+
+#### Index documents to SQLite search backend
+```bash
+# The search index will be created if it does not exist already
+sist2 sqlite-index ./index1.sist2 --search-index search.sist2
+sist2 sqlite-index ./index2.sist2 --search-index search.sist2
 ```
 
 **Save index in JSON format**
 ```bash
-sist2 index --print ./my_index/ > my_index.ndjson
+sist2 index --print ./my_index.sist2 > my_index.ndjson
 ```
 
 **Inspect contents of an index**
 ```bash
-sist2 index --print ./my_index/ | jq | less
+sist2 index --print ./my_index.sist2 | jq | less
 ```
 
 ## Web
 
-### Web options
- * `--es-url=<str>` Elasticsearch url.
- * `--es-index` 
-    Elasticsearch index name. DEFAULT=sist2
- * `--bind=<str>` Listen on this address.
- * `--auth=<str>` Basic auth in user:password format
- * `--tag-auth=<str>` Basic auth in user:password format. Works the same way as the 
-    `--auth` argument, but authentication is only applied the `/tag/` endpoint.
- * `--tagline=<str>` When specified, will replace the default tagline in the navbar.
- * `--dev` Serve html & js files from disk (for development, used to modify frontend files without having to recompile)
- * `--lang=<str>` Set the default web UI language (See #180 for a list of supported languages, default
-   is `en`). The user can change the language in the configuration page
-
 ### Web examples
 
-**Single index**
+**Single index (Elasticsearch backend)**
 ```bash
-sist2 web --auth admin:hunter2 --bind 0.0.0.0:8888 my_index
+sist2 web --auth admin:hunter2 --bind 0.0.0.0:8888 my_index.sist2
 ```
 
-**Multiple indices**
+**Multiple indices (Elasticsearch backend)**
 ```bash
 # Indices will be displayed in this order in the web interface
-sist2 web index1 index2 index3 index4
+sist2 web index1.sist2 index2.sist2 index3.sist2 index4.sist2
 ```
 
+**SQLite search backend**
+```bash
+sist2 web --search-index search.sist2 index1.sist2
+```
+
+#### Auth0 authentication
+
+See [auth0.md](auth0.md)
+
 ### rewrite_url
 
 When the `rewrite_url` field is not empty, the web module ignores the `root`
@@ -363,8 +245,8 @@ The sidecar file must have exactly the same file path and the `.s2meta` suffix.
 ```
 
 ```
-sist2 scan ~/Documents -o ./docs.idx
-sist2 index ./docs.idx
+sist2 scan ~/Documents -o ./docs.sist2
+sist2 index ./docs.sist2
 ```
 
 *NOTE*: It is technically possible to overwrite the `tag` value using sidecar files, however,

docs/auth0.md

@@ -0,0 +1,19 @@
+
+# Authentication with Auth0
+
+1. Create a new Auth0 application (Single page app)
+2. Create a new Auth0 API:
+   1. Choose `RS256` signing algorithm
+   2. Set identifier (audience) to `https://sist2`
+3. Download the Auth0 certificate from https://<domain>.auth0.com/pem (you can find the domain Applications->Basic information)
+4. Extract the public key from the certificate using `openssl x509 -pubkey -noout -in cert.pem > pubkey.txt`
+5. Start the sist2 web server
+
+Example options:
+```bash
+sist2 web \
+  --auth0-client-id XXX \
+  --auth0-audience https://sist2 \
+  --auth0-domain YYY.auth0.com \
+  --auth0-public-key-file /ZZZ/pubkey.txt
+```

schema/mappings.json

@@ -67,7 +67,8 @@
       "index": false
     },
     "mtime": {
-      "type": "integer"
+      "type": "date",
+      "format": "epoch_millis"
     },
     "size": {
       "type": "long"

scripts/before_build.sh

@@ -1,10 +1,13 @@
 #!/usr/bin/env bash
 
-rm -rf index.sist2/
+(
+  cd ..
+  rm -rf index.sist2
 
-python3 scripts/mime.py > src/parsing/mime_generated.c
-python3 scripts/serve_static.py > src/web/static_generated.c
-python3 scripts/index_static.py > src/index/static_generated.c
-python3 scripts/magic_static.py > src/magic_generated.c
+  python3 scripts/mime.py > src/parsing/mime_generated.c
+  python3 scripts/serve_static.py > src/web/static_generated.c
+  python3 scripts/index_static.py > src/index/static_generated.c
+  python3 scripts/magic_static.py > src/magic_generated.c
 
-printf "static const char *const Sist2CommitHash = \"%s\";\n" $(git rev-parse HEAD) > src/git_hash.h
+  printf "static const char *const Sist2CommitHash = \"%s\";\n" $(git rev-parse HEAD) > src/git_hash.h
+)

scripts/build.sh

@@ -4,14 +4,20 @@ VCPKG_ROOT="/vcpkg"
 
 git submodule update --init --recursive
 
-rm -rf CMakeFiles CMakeCache.txt
-cmake -DSIST_PLATFORM=x64_linux -DSIST_DEBUG=off -DBUILD_TESTS=off -DCMAKE_TOOLCHAIN_FILE="${VCPKG_ROOT}/scripts/buildsystems/vcpkg.cmake" .
-make -j $(nproc)
-strip sist2
-./sist2 -v > VERSION
-mv sist2 sist2-x64-linux
+mkdir build
+(
+  cd build
+  cmake -DSIST_PLATFORM=x64_linux -DSIST_DEBUG_INFO=on -DSIST_DEBUG=off -DBUILD_TESTS=off -DCMAKE_TOOLCHAIN_FILE="${VCPKG_ROOT}/scripts/buildsystems/vcpkg.cmake" ..
+  make -j $(nproc)
+  strip sist2
+  ./sist2 -v > VERSION
+)
+mv build/sist2 sist2-x64-linux
 
-rm -rf CMakeFiles CMakeCache.txt
-cmake -DSIST_PLATFORM=x64_linux -DSIST_DEBUG=on -DBUILD_TESTS=off -DCMAKE_TOOLCHAIN_FILE="${VCPKG_ROOT}/scripts/buildsystems/vcpkg.cmake" .
-make -j  $(nproc)
-mv sist2_debug sist2-x64-linux-debug
+(
+  cd build
+  rm -rf CMakeFiles CMakeCache.txt
+  cmake -DSIST_PLATFORM=x64_linux -DSIST_DEBUG_INFO=on -DSIST_DEBUG=on -DBUILD_TESTS=off -DCMAKE_TOOLCHAIN_FILE="${VCPKG_ROOT}/scripts/buildsystems/vcpkg.cmake" ..
+  make -j  $(nproc)
+)
+mv build/sist2_debug sist2-x64-linux-debug

scripts/build_arm64.sh

@@ -4,14 +4,19 @@ VCPKG_ROOT="/vcpkg"
 
 git submodule update --init --recursive
 
-rm -rf CMakeFiles CMakeCache.txt
-cmake -DSIST_PLATFORM=arm64_linux -DSIST_DEBUG=off -DBUILD_TESTS=off -DCMAKE_TOOLCHAIN_FILE="${VCPKG_ROOT}/scripts/buildsystems/vcpkg.cmake" .
-make -j $(nproc)
-strip sist2
-mv sist2 sist2-arm64-linux
+mkdir build
+(
+  cd build
+  cmake -DSIST_PLATFORM=arm64_linux -DSIST_DEBUG_INFO=on -DSIST_DEBUG=off -DBUILD_TESTS=off -DCMAKE_TOOLCHAIN_FILE="${VCPKG_ROOT}/scripts/buildsystems/vcpkg.cmake" ..
+  make -j $(nproc)
+  strip sist2
+)
+mv build/sist2 sist2-arm64-linux
 
 rm -rf CMakeFiles CMakeCache.txt
-cmake -DSIST_PLATFORM=arm64_linux -DSIST_DEBUG=on -DBUILD_TESTS=off -DCMAKE_TOOLCHAIN_FILE="${VCPKG_ROOT}/scripts/buildsystems/vcpkg.cmake" .
-make -j $(nproc)
-strip sist2
-mv sist2_debug sist2-arm64-linux-debug
+(
+  cd build
+  cmake -DSIST_PLATFORM=arm64_linux -DSIST_DEBUG_INFO=on -DSIST_DEBUG=on -DBUILD_TESTS=off -DCMAKE_TOOLCHAIN_FILE="${VCPKG_ROOT}/scripts/buildsystems/vcpkg.cmake" ..
+  make -j $(nproc)
+)
+mv build/sist2_debug sist2-arm64-linux-debug

scripts/mime.csv

@@ -1,3 +1,4 @@
+application/x-matlab-data,mat
 application/arj, arj
 application/base64, mme
 application/binhex, hqx
@@ -29,7 +30,7 @@ application/mime, aps
 application/mspowerpoint, ppz
 application/msword, doc|dot|w6w|wiz|word
 application/netmc, mcp
-application/octet-stream, bin|dump|gpg
+application/octet-stream, bin|dump|gpg|pack|idx
 application/oda, oda
 application/ogg, ogv
 application/pdf, pdf
@@ -243,7 +244,7 @@ audio/make, funk|my|pfunk
 audio/midi, kar
 audio/mid, rmi
 audio/mp4, m4b
-audio/mpeg, m2a|mpa
+audio/mpeg, m2a|mpa|mpga
 audio/ogg, ogg
 audio/s3m, s3m
 audio/tsp-audio, tsi
@@ -346,6 +347,8 @@ text/mcf, mcf
 text/pascal, pas
 text/PGP,
 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|csv|eml|make|log|markdown|yaml
+text/x-script.python, pyx
+text/csv,
 application/vnd.coffeescript, coffee
 text/richtext, rt|rtf|rtx
 text/rtf,
@@ -382,7 +385,7 @@ text/x-pascal, p
 text/x-perl, pl
 text/x-php, php
 text/x-po, po
-text/x-python, py
+text/x-python, py|pyi
 text/x-ruby, rb
 text/x-sass, sass
 text/x-scss, scss

scripts/mime.py

@@ -1,3 +1,5 @@
+import zlib
+
 mimes = {}
 noparse = set()
 ext_in_hash = set()
@@ -135,24 +137,40 @@ def clean(t):
     return t.replace("/", "_").replace(".", "_").replace("+", "_").replace("-", "_")
 
 
+def crc(s):
+    return zlib.crc32(s.encode()) & 0xffffffff
+
+
 with open("scripts/mime.csv") as f:
     for l in f:
         mime, ext_list = l.split(",")
         if l.startswith("!"):
             mime = mime[1:]
             noparse.add(mime)
-        ext = [x.strip() for x in ext_list.split("|")]
+        ext = [x.strip() for x in ext_list.split("|") if x.strip() != ""]
         mimes[mime] = ext
 
+    seen_crc = set()
+    for ext in mimes.values():
+        for e in ext:
+            if crc(e) in seen_crc:
+                raise Exception("CRC32 collision")
+            seen_crc.add(crc(e))
+
+    seen_crc = set()
+    for mime in mimes.keys():
+        if crc(mime) in seen_crc:
+            raise Exception("CRC32 collision")
+        seen_crc.add(crc(mime))
+
     print("// **Generated by mime.py**")
     print("#ifndef MIME_GENERATED_C")
     print("#define MIME_GENERATED_C")
-    print("#include <glib.h>\n")
     print("#include <stdlib.h>\n")
     # Enum
     print("enum mime {")
     for mime, ext in sorted(mimes.items()):
-        print("    " + clean(mime) + "=" + mime_id(mime) + ",")
+        print(f"{clean(mime)}={mime_id(mime)},")
     print("};")
 
     # Enum -> string
@@ -163,20 +181,20 @@ with open("scripts/mime.csv") as f:
     print("default: return NULL;}}")
 
     # Ext -> Enum
-    print("GHashTable *mime_get_ext_table() {"
-          "GHashTable *ext_table = g_hash_table_new(g_str_hash, g_str_equal);")
+    print("unsigned int mime_extension_lookup(unsigned long extension_crc32) {"
+          "switch (extension_crc32) {")
     for mime, ext in mimes.items():
-        for e in [e for e in ext if e]:
-            print("g_hash_table_insert(ext_table, \"" + e + "\", (gpointer)" + clean(mime) + ");")
-            if e in ext_in_hash:
-                raise Exception("extension already in hash: " + e)
-            ext_in_hash.add(e)
-    print("return ext_table;}")
+        if len(ext) > 0:
+            for e in ext:
+                print(f"case {crc(e)}:", end="")
+            print(f"return {clean(mime)};")
+    print("default: return 0;}}")
 
     # string -> Enum
-    print("GHashTable *mime_get_mime_table() {"
-          "GHashTable *mime_table = g_hash_table_new(g_str_hash, g_str_equal);")
-    for mime, ext in mimes.items():
-        print("g_hash_table_insert(mime_table, \"" + mime + "\", (gpointer)" + clean(mime) + ");")
-    print("return mime_table;}")
+    print("unsigned int mime_name_lookup(unsigned long mime_crc32) {"
+          "switch (mime_crc32) {")
+    for mime in mimes.keys():
+        print(f"case {crc(mime)}: return {clean(mime)};")
+
+    print("default: return 0;}}")
     print("#endif")

scripts/reset.sh

@@ -1,6 +0,0 @@
-#!/usr/bin/env bash
-
-make clean
-rm -rf CMakeFiles/ CMakeCache.txt Makefile \
-  third-party/libscan/CMakeFiles third-party/libscan/CMakeCache.txt third-party/libscan/third-party/ext_ffmpeg \
-  third-party/libscan/third-party/ext_libmobi third-party/libscan/Makefile

scripts/sqlite_extension.c

@@ -0,0 +1,84 @@
+#include <sqlite3ext.h>
+#include <string.h>
+#include <stdlib.h>
+
+SQLITE_EXTENSION_INIT1
+
+static int sep_rfind(const char *str) {
+    for (int i = (int) strlen(str); i >= 0; i--) {
+        if (str[i] == '/') {
+            return i;
+        }
+    }
+    return -1;
+}
+
+void path_parent_func(sqlite3_context *ctx, int argc, sqlite3_value **argv) {
+    if (argc != 1 || sqlite3_value_type(argv[0]) != SQLITE_TEXT) {
+        sqlite3_result_error(ctx, "Invalid parameters", -1);
+    }
+
+    const char *value = (const char *) sqlite3_value_text(argv[0]);
+
+    int stop = sep_rfind(value);
+    if (stop == -1) {
+        sqlite3_result_null(ctx);
+        return;
+    }
+    char parent[4096 * 3];
+    strncpy(parent, value, stop);
+
+    sqlite3_result_text(ctx, parent, stop, SQLITE_TRANSIENT);
+}
+
+void random_func(sqlite3_context *ctx, int argc, sqlite3_value **argv) {
+    if (argc != 1 || sqlite3_value_type(argv[0]) != SQLITE_INTEGER) {
+        sqlite3_result_error(ctx, "Invalid parameters", -1);
+    }
+
+    char state_buf[32] = {0,};
+    struct random_data buf;
+    int result;
+
+    long seed = sqlite3_value_int64(argv[0]);
+
+    initstate_r((int) seed, state_buf, sizeof(state_buf), &buf);
+
+    random_r(&buf, &result);
+
+    sqlite3_result_int(ctx, result);
+}
+
+
+int sqlite3_extension_init(
+        sqlite3 *db,
+        char **pzErrMsg,
+        const sqlite3_api_routines *pApi
+) {
+    SQLITE_EXTENSION_INIT2(pApi);
+
+
+    sqlite3_create_function(
+            db,
+            "path_parent",
+            1,
+            SQLITE_UTF8,
+            NULL,
+            path_parent_func,
+            NULL,
+            NULL
+    );
+
+    sqlite3_create_function(
+            db,
+            "random_seeded",
+            1,
+            SQLITE_UTF8,
+            NULL,
+            random_func,
+            NULL,
+            NULL
+    );
+
+    return SQLITE_OK;
+}

scripts/sqlite_extension_compile.sh

@@ -0,0 +1 @@
+gcc -I/mnt/work/vcpkg/installed/x64-linux/include -g -fPIC -shared sqlite_extension.c -o sist2funcs.so

scripts/start_dev_es.sh

@@ -1,3 +1,3 @@
 docker run --rm -it --name "sist2-dev-es"\
        	-p 9200:9200 -e "discovery.type=single-node" \
-	-e "ES_JAVA_OPTS=-Xms8g -Xmx8g" elasticsearch:7.14.0
+	-e "ES_JAVA_OPTS=-Xms8g -Xmx8g" elasticsearch:7.17.9

scripts/start_dev_es_8.sh

@@ -1,3 +1,3 @@
 docker run --rm -it --name "sist2-dev-es"\
        	-p 9200:9200 -p 9300:9300 -e "discovery.type=single-node" \
-	-e "ES_JAVA_OPTS=-Xms8g -Xmx8g" elasticsearch:8.1.2
+	-e "ES_JAVA_OPTS=-Xms8g -Xmx8g" elasticsearch:8.7.0

sist2-admin/frontend/babel.config.js

@@ -0,0 +1,5 @@
+module.exports = {
+  presets: [
+    '@vue/cli-plugin-babel/preset'
+  ]
+}

sist2-admin/frontend/package.json

@@ -0,0 +1,49 @@
+{
+  "name": "sist2-admin-vue",
+  "version": "0.1.0",
+  "private": true,
+  "scripts": {
+    "serve": "vue-cli-service serve",
+    "build": "vue-cli-service build",
+    "watch": "vue-cli-service build --watch"
+  },
+  "dependencies": {
+    "axios": "^0.27.2",
+    "bootstrap-vue": "^2.21.2",
+    "core-js": "^3.6.5",
+    "moment": "^2.29.3",
+    "socket.io-client": "^4.5.1",
+    "vue": "^2.6.14",
+    "vue-i18n": "^8.24.4",
+    "vue-router": "^3.5.4",
+    "vuex": "^3.4.0"
+  },
+  "devDependencies": {
+    "@vue/cli-plugin-babel": "~5.0.8",
+    "@vue/cli-plugin-router": "~5.0.8",
+    "@vue/cli-plugin-vuex": "~5.0.8",
+    "@vue/cli-service": "~5.0.8",
+    "babel-eslint": "^10.1.0",
+    "bootstrap": "^4.5.2",
+    "vue-template-compiler": "^2.6.11"
+  },
+  "eslintConfig": {
+    "root": true,
+    "env": {
+      "node": true
+    },
+    "extends": [
+      "plugin:vue/essential",
+      "eslint:recommended"
+    ],
+    "parserOptions": {
+      "parser": "babel-eslint"
+    },
+    "rules": {}
+  },
+  "browserslist": [
+    "> 1%",
+    "last 2 versions",
+    "not dead"
+  ]
+}

sist2-admin/frontend/public/index.html

@@ -0,0 +1,17 @@
+<!DOCTYPE html>
+<html lang="">
+  <head>
+    <meta charset="utf-8">
+    <meta http-equiv="X-UA-Compatible" content="IE=edge">
+    <meta name="viewport" content="width=device-width,initial-scale=1.0">
+    <link rel="icon" href="<%= BASE_URL %>serve_favicon_ico.ico">
+    <title>sist2-admin</title>
+  </head>
+  <body>
+    <noscript>
+      <strong>We're sorry but <%= htmlWebpackPlugin.options.title %> doesn't work properly without JavaScript enabled. Please enable it to continue.</strong>
+    </noscript>
+    <div id="app"></div>
+    <!-- built files will be auto injected -->
+  </body>
+</html>

sist2-admin/frontend/src/App.vue

@@ -0,0 +1,98 @@
+<template>
+  <div id="app">
+    <NavBar></NavBar>
+    <b-container class="pt-4">
+      <b-alert show dismissible variant="info">
+        This is a beta version of sist2-admin. Please submit bug reports, usability issues and feature requests
+        to the <a href="https://github.com/simon987/sist2/issues/new/choose" target="_blank">issue tracker on Github</a>. Thank you!
+      </b-alert>
+      <router-view/>
+    </b-container>
+  </div>
+</template>
+
+<script>
+import NavBar from "@/components/NavBar";
+import Sist2AdminApi from "@/Sist2AdminApi";
+
+export default {
+  components: {NavBar},
+  data() {
+    return {
+      socket: null
+    }
+  },
+  mounted() {
+    Sist2AdminApi.getSist2AdminInfo()
+        .then(resp => this.$store.commit("setSist2AdminInfo", resp.data));
+    this.$store.dispatch("loadBrowserSettings");
+    this.connectNotifications();
+    // this.socket.onclose = this.connectNotifications;
+  },
+  methods: {
+    connectNotifications() {
+      this.socket = new WebSocket(`ws://${window.location.host}/notifications`);
+      this.socket.onopen = () => {
+        this.socket.send("Hello from client");
+      }
+
+      this.socket.onmessage = e => {
+        const notification = JSON.parse(e.data);
+        if (notification.message) {
+          notification.messageString = this.$t(notification.message).toString();
+        }
+
+        this.$store.dispatch("notify", notification)
+      }
+    }
+  }
+}
+</script>
+
+<style>
+html, body {
+  height: 100%;
+}
+
+#app {
+  /*font-family: Avenir, Helvetica, Arial, sans-serif;*/
+  -webkit-font-smoothing: antialiased;
+  -moz-osx-font-smoothing: grayscale;
+  /*text-align: center;*/
+  color: #2c3e50;
+  padding-bottom: 1em;
+  min-height: 100%;
+}
+
+.info-icon {
+  width: 1rem;
+  margin-right: 0.2rem;
+  cursor: pointer;
+  line-height: 1rem;
+  height: 1rem;
+  background-image: url(data:image/svg+xml;base64,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);
+  filter: brightness(45%);
+  display: block;
+}
+
+.tabs {
+  margin-top: 10px;
+}
+
+.modal-title {
+  text-overflow: ellipsis;
+  overflow: hidden;
+  white-space: nowrap;
+}
+
+@media screen and (min-width: 1500px) {
+  .container {
+    max-width: 1440px;
+  }
+}
+
+label {
+  margin-top: 0.5rem;
+  margin-bottom: 0;
+}
+</style>

sist2-admin/frontend/src/Sist2AdminApi.js

@@ -0,0 +1,117 @@
+import axios from "axios";
+
+class Sist2AdminApi {
+
+    constructor() {
+        this.baseUrl = window.location.protocol + "//" + window.location.host;
+    }
+
+    getJobs() {
+        return axios.get(`${this.baseUrl}/api/job/`);
+    }
+
+    getFrontends() {
+        return axios.get(`${this.baseUrl}/api/frontend/`);
+    }
+
+    getTasks() {
+        return axios.get(`${this.baseUrl}/api/task/`);
+    }
+
+    killTask(taskId) {
+        return axios.post(`${this.baseUrl}/api/task/${taskId}/kill`)
+    }
+
+    getTaskHistory() {
+        return axios.get(`${this.baseUrl}/api/task/history`);
+    }
+
+    /**
+     * @param {string} name
+     */
+    getJob(name) {
+        return axios.get(`${this.baseUrl}/api/job/${name}`);
+    }
+
+    /**
+     * @param {string} name
+     */
+    getFrontend(name) {
+        return axios.get(`${this.baseUrl}/api/frontend/${name}`);
+    }
+
+    /**
+     * @param {string} name
+     */
+    startFrontend(name) {
+        return axios.post(`${this.baseUrl}/api/frontend/${name}/start`);
+    }
+
+    /**
+     * @param {string} name
+     */
+    stopFrontend(name) {
+        return axios.post(`${this.baseUrl}/api/frontend/${name}/stop`);
+    }
+
+    /**
+     * @param {string} name
+     * @param job
+     */
+    updateJob(name, job) {
+        return axios.put(`${this.baseUrl}/api/job/${name}`, job);
+    }
+
+    /**
+     * @param {string} name
+     * @param frontend
+     */
+    updateFrontend(name, frontend) {
+        return axios.put(`${this.baseUrl}/api/frontend/${name}`, frontend);
+    }
+
+    /**
+     * @param {string} name
+     */
+    runJob(name) {
+        return axios.get(`${this.baseUrl}/api/job/${name}/run`);
+    }
+
+    /**
+     * @param {string} name
+     */
+    deleteJob(name) {
+        return axios.delete(`${this.baseUrl}/api/job/${name}`);
+    }
+
+    /**
+     * @param {string} name
+     */
+    deleteFrontend(name) {
+        return axios.delete(`${this.baseUrl}/api/frontend/${name}`);
+    }
+
+    /**
+     * @param {string} name
+     */
+    createJob(name) {
+        return axios.post(`${this.baseUrl}/api/job/${name}`);
+    }
+
+    /**
+     * @param {string} name
+     */
+    createFrontend(name) {
+        return axios.post(`${this.baseUrl}/api/frontend/${name}`);
+    }
+
+    pingEs(url, insecure) {
+        return axios.get(`${this.baseUrl}/api/ping_es`, {params: {url, insecure}});
+    }
+
+    getSist2AdminInfo() {
+        return axios.get(`${this.baseUrl}/api/`);
+    }
+}
+
+export default new Sist2AdminApi()

sist2-admin/frontend/src/components/FrontendListItem.vue

@@ -0,0 +1,31 @@
+<template>
+  <b-list-group-item action :to="`/frontend/${frontend.name}`">
+
+    <div class="d-flex w-100 justify-content-between">
+      <h5 class="mb-1" style="display: block">
+        {{ frontend.name }}
+        <b-badge variant="light">{{ formatBindAddress(frontend.web_options.bind) }}</b-badge>
+      </h5>
+
+      <div>
+        <b-badge v-if="frontend.running" variant="success">{{$t("online")}}</b-badge>
+        <b-badge v-else variant="secondary">{{$t("offline")}}</b-badge>
+      </div>
+    </div>
+
+  </b-list-group-item>
+</template>
+
+<script>
+import {formatBindAddress} from "@/util";
+
+export default {
+  name: "FrontendListItem",
+  props: ["frontend"],
+  data() {
+    return {
+      formatBindAddress
+    }
+  }
+}
+</script>

sist2-admin/frontend/src/components/IndexOptions.vue

@@ -0,0 +1,64 @@
+<template>
+  <div>
+    <label>{{ $t("indexOptions.threads") }}</label>
+    <b-form-input v-model="options.threads" type="number" min="1" @change="update()"></b-form-input>
+
+    <label>{{ $t("webOptions.esUrl") }}</label>
+    <b-alert :variant="esTestOk ? 'success' : 'danger'" :show="showEsTestAlert" class="mt-1">
+      {{ esTestMessage }}
+    </b-alert>
+    <b-input-group>
+      <b-form-input v-model="options.es_url" @change="update()"></b-form-input>
+      <b-input-group-append>
+        <b-button variant="outline-primary" @click="testEs()">{{ $t("test") }}</b-button>
+      </b-input-group-append>
+    </b-input-group>
+
+    <label>{{ $t("indexOptions.esIndex") }}</label>
+    <b-form-input v-model="options.es_index" @change="update()"></b-form-input>
+
+    <br>
+    <b-form-checkbox v-model="options.es_insecure_ssl" :disabled="!options.es_url.startsWith('https')" @change="update()">
+      {{ $t("webOptions.esInsecure") }}
+    </b-form-checkbox>
+
+    <label>{{ $t("indexOptions.batchSize") }}</label>
+    <b-form-input v-model="options.batch_size" type="number" min="1" @change="update()"></b-form-input>
+
+    <label>{{ $t("indexOptions.script") }}</label>
+    <b-form-textarea v-model="options.script" rows="6" @change="update()"></b-form-textarea>
+  </div>
+
+</template>
+
+<script>
+import sist2AdminApi from "@/Sist2AdminApi";
+
+export default {
+  name: "IndexOptions",
+  props: ["options"],
+  data() {
+    return {
+      showEsTestAlert: false,
+      esTestOk: false,
+      esTestMessage: "",
+    }
+  },
+  methods: {
+    update() {
+      this.$emit("change", this.options);
+    },
+    testEs() {
+      sist2AdminApi.pingEs(this.options.es_url, this.options.es_insecure_ssl).then((resp) => {
+        this.showEsTestAlert = true;
+        this.esTestOk = resp.data.ok;
+        this.esTestMessage = resp.data.message;
+      });
+    }
+  },
+}
+</script>
+
+<style scoped>
+
+</style>

sist2-admin/frontend/src/components/JobCheckboxGroup.vue

@@ -0,0 +1,42 @@
+<template>
+  <div>
+    <h5>{{ $t("selectJobs") }}</h5>
+    <b-progress v-if="loading" striped animated value="100"></b-progress>
+    <b-form-group v-else>
+      <b-form-checkbox-group
+          v-if="jobs.length > 0"
+          :checked="frontend.jobs"
+          @input="frontend.jobs = $event; $emit('input')"
+      >
+        <div v-for="job in jobs" :key="job.name">
+          <b-form-checkbox :disabled="job.status !== 'indexed'" :value="job.name">[{{ job.name }}]</b-form-checkbox>
+          <br/>
+        </div>
+      </b-form-checkbox-group>
+      <div v-else>
+        <span class="text-muted">{{ $t('jobOptions.noJobAvailable') }}</span>
+        &nbsp;<router-link to="/">{{$t("create")}}</router-link>
+      </div>
+    </b-form-group>
+  </div>
+</template>
+
+<script>
+import Sist2AdminApi from "@/Sist2AdminApi";
+
+export default {
+  name: "JobCheckboxGroup",
+  props: ["frontend"],
+  mounted() {
+    Sist2AdminApi.getJobs().then(resp => {
+      this.jobs = resp.data;
+      this.loading = false;
+    });
+  },
+  data() {
+    return {
+      loading: true,
+    }
+  }
+}
+</script>

sist2-admin/frontend/src/components/JobListItem.vue

@@ -0,0 +1,56 @@
+<template>
+  <b-list-group-item class="flex-column align-items-start" action :to="`job/${job.name}`">
+
+    <div class="d-flex w-100 justify-content-between">
+      <div>
+        <h5 class="mb-1">
+          {{ job.name }}
+        </h5>
+      </div>
+      <div>
+        <b-row>
+          <b-col>
+            <small v-if="job.last_index_date">
+              {{ $t("scanned") }} {{ formatLastIndexDate(job.last_index_date) }}</small>
+            <div v-else>&nbsp;</div>
+          </b-col>
+        </b-row>
+        <b-row v-if="job.schedule_enabled">
+          <b-col>
+            <small><code>{{job.cron_expression }}</code></small>
+          </b-col>
+        </b-row>
+        <b-row v-else>
+          <b-col>
+            &nbsp;
+          </b-col>
+        </b-row>
+
+      </div>
+    </div>
+
+  </b-list-group-item>
+</template>
+
+<script>
+import moment from "moment";
+
+export default {
+  name: "JobListItem",
+  props: ["job"],
+  methods: {
+    formatLastIndexDate(dateString) {
+      if (dateString === null) {
+        return "";
+      }
+
+      const date = Date.parse(dateString);
+      return moment(date).fromNow();
+    }
+  }
+}
+</script>
+
+<style scoped>
+
+</style>

sist2-admin/frontend/src/components/JobOptions.vue

@@ -0,0 +1,57 @@
+<template>
+  <div>
+    <b-form-checkbox :checked="desktopNotificationsEnabled" @change="updateNotifications($event)">
+      {{ $t("jobOptions.desktopNotifications") }}
+    </b-form-checkbox>
+
+    <b-form-checkbox v-model="job.schedule_enabled" @change="update()">
+      {{ $t("jobOptions.scheduleEnabled") }}
+    </b-form-checkbox>
+
+    <label>{{ $t("jobOptions.cron") }}</label>
+    <b-form-input class="text-monospace" :state="cronValid" v-model="job.cron_expression" :disabled="!job.schedule_enabled" @change="update()"></b-form-input>
+  </div>
+</template>
+
+<script>
+
+export default {
+  name: "JobOptions",
+  props: ["job"],
+  data() {
+    return {
+      cronValid: undefined
+    }
+  },
+  computed: {
+    desktopNotificationsEnabled() {
+      return this.$store.state.jobDesktopNotificationMap[this.job.name];
+    }
+  },
+    mounted() {
+      this.cronValid = this.checkCron(this.job.cron_expression)
+    },
+    methods: {
+      checkCron(expression) {
+          return /((((\d+,)+\d+|(\d+([/-])\d+)|\d+|\*) ?){5,7})/.test(expression);
+      },
+    updateNotifications(value) {
+      this.$store.dispatch("setJobDesktopNotification", {
+        job: this.job.name,
+        enabled: value
+      });
+    },
+    update() {
+      if (this.job.schedule_enabled) {
+        this.cronValid = this.checkCron(this.job.cron_expression);
+      } else {
+        this.cronValid = undefined;
+      }
+
+      if (this.cronValid !== false) {
+        this.$emit("change", this.job);
+      }
+    },
+  },
+}
+</script>

sist2-admin/frontend/src/components/NavBar.vue

@@ -0,0 +1,69 @@
+<template>
+  <b-navbar>
+    <b-navbar-brand to="/">
+      <Sist2Icon></Sist2Icon>
+    </b-navbar-brand>
+
+    <b-button class="ml-auto" to="/task" variant="link">{{ $t("tasks") }}</b-button>
+  </b-navbar>
+</template>
+
+<script>
+import Sist2Icon from "@/components/icons/Sist2Icon";
+
+export default {
+  name: "NavBar",
+  components: {Sist2Icon},
+  methods: {
+    tagline() {
+      return this.$store.state.sist2Info.tagline;
+    },
+    sist2Version() {
+      return this.$store.state.sist2Info.version;
+    },
+    isDebug() {
+      return this.$store.state.sist2Info.debug;
+    },
+    isLegacy() {
+      return this.$store.state.sist2Info.esVersionLegacy;
+    },
+    hideLegacy() {
+      return this.$store.state.optHideLegacy;
+    }
+  }
+}
+</script>
+
+<style scoped>
+.navbar {
+  box-shadow: 0 0.125rem 0.25rem rgb(0 0 0 / 8%) !important;
+  border-radius: 0;
+}
+
+.theme-black .navbar {
+  background: #546b7a30;
+  border-bottom: none;
+}
+
+.navbar-brand {
+  color: #222 !important;
+  font-size: 1.75rem;
+  padding: 0;
+}
+
+.navbar-brand:hover {
+  color: #000 !important;
+}
+
+.version {
+  color: #222 !important;
+  margin-left: -18px;
+  margin-top: -14px;
+  font-size: 11px;
+  font-family: monospace;
+}
+
+.btn-link {
+  color: #222;
+}
+</style>

sist2-admin/frontend/src/components/ScanOptions.vue

@@ -0,0 +1,109 @@
+<template>
+  <div>
+    <label>{{ $t("scanOptions.path") }}</label>
+    <b-form-input v-model="options.path" @change="update()"></b-form-input>
+
+    <label>{{ $t("scanOptions.threads") }}</label>
+    <b-form-input type="number" min="1" v-model="options.threads" @change="update()"></b-form-input>
+
+    <label>{{ $t("scanOptions.thumbnailQuality") }}</label>
+    <b-form-input type="number" min="0" max="100" v-model="options.thumbnail_quality" @change="update()"></b-form-input>
+
+    <label>{{ $t("scanOptions.thumbnailCount") }}</label>
+    <b-form-input type="number" min="0" max="1000" v-model="options.thumbnail_count" @change="update()"></b-form-input>
+
+    <label>{{ $t("scanOptions.thumbnailSize") }}</label>
+    <b-form-input type="number" min="100" v-model="options.thumbnail_size" @change="update()"></b-form-input>
+
+    <label>{{ $t("scanOptions.contentSize") }}</label>
+    <b-form-input type="number" min="0" v-model="options.content_size" @change="update()"></b-form-input>
+
+    <label>{{ $t("scanOptions.rewriteUrl") }}</label>
+    <b-form-input v-model="options.rewrite_url" @change="update()"></b-form-input>
+
+    <label>{{ $t("scanOptions.depth") }}</label>
+    <b-form-input type="number" min="0" v-model="options.depth" @change="update()"></b-form-input>
+
+    <label>{{ $t("scanOptions.archive") }}</label>
+    <b-form-select :options="['skip', 'list', 'shallow', 'recurse']" v-model="options.archive"
+                   @change="update()"></b-form-select>
+
+    <label>{{ $t("scanOptions.archivePassphrase") }}</label>
+    <b-form-input v-model="options.archive_passphrase" @change="update()"></b-form-input>
+
+    <label>{{ $t("scanOptions.ocrLang") }}</label>
+    <b-alert variant="danger" show v-if="selectedOcrLangs.length === 0 && !disableOcrLang">{{ $t("scanOptions.ocrLangAlert") }}</b-alert>
+    <b-checkbox-group :disabled="disableOcrLang" v-model="selectedOcrLangs" @input="onOcrLangChange">
+      <b-checkbox v-for="lang in ocrLangs" :key="lang" :value="lang">{{ lang }}</b-checkbox>
+    </b-checkbox-group>
+
+    <!--    <b-form-input readonly v-model="options.ocr_lang" @change="update()"></b-form-input>-->
+
+    <div style="height: 10px"></div>
+
+    <b-form-checkbox v-model="options.ocr_images" @change="update()">
+      {{ $t("scanOptions.ocrImages") }}
+    </b-form-checkbox>
+
+    <b-form-checkbox v-model="options.ocr_ebooks" @change="update()">
+      {{ $t("scanOptions.ocrEbooks") }}
+    </b-form-checkbox>
+
+    <label>{{ $t("scanOptions.exclude") }}</label>
+    <b-form-input v-model="options.exclude" @change="update()"
+                  :placeholder="$t('scanOptions.excludePlaceholder')"></b-form-input>
+
+    <div style="height: 10px"></div>
+
+    <b-form-checkbox v-model="options.fast" @change="update()">
+      {{ $t("scanOptions.fast") }}
+    </b-form-checkbox>
+
+    <b-form-checkbox v-model="options.checksums" @change="update()">
+      {{ $t("scanOptions.checksums") }}
+    </b-form-checkbox>
+
+    <b-form-checkbox v-model="options.read_subtitles" @change="update()">
+      {{ $t("scanOptions.readSubtitles") }}
+    </b-form-checkbox>
+
+    <b-form-checkbox v-model="options.optimize_index" @change="update()">
+        {{ $t("scanOptions.optimizeIndex") }}
+    </b-form-checkbox>
+
+    <label>{{ $t("scanOptions.treemapThreshold") }}</label>
+    <b-form-input type="number" min="0" v-model="options.treemap_threshold" @change="update()"></b-form-input>
+  </div>
+</template>
+
+<script>
+
+export default {
+  name: "ScanOptions",
+  props: ["options"],
+  data() {
+    return {
+      disableOcrLang: false,
+      selectedOcrLangs: []
+    }
+  },
+  computed: {
+    ocrLangs() {
+      return this.$store.state.sist2AdminInfo?.tesseract_langs || [];
+    }
+  },
+  methods: {
+    onOcrLangChange() {
+      this.options.ocr_lang = this.selectedOcrLangs.join("+");
+    },
+    update() {
+      this.disableOcrLang = this.options.ocr_images === false && this.options.ocr_ebooks === false;
+      this.$emit("change", this.options);
+    },
+  },
+  mounted() {
+    this.disableOcrLang = this.options.ocr_images === false && this.options.ocr_ebooks === false;
+    this.selectedOcrLangs = this.options.ocr_lang ? this.options.ocr_lang.split("+") : [];
+  }
+}
+</script>

sist2-admin/frontend/src/components/TaskListItem.vue

@@ -0,0 +1,57 @@
+<template>
+  <b-list-group-item>
+    <b-row style="height: 50px">
+      <b-col><h5>{{ task.display_name }}</h5></b-col>
+      <b-col class="shrink">
+        <router-link class="btn btn-link" :to="`/log/${task.id}`">{{ $t("logs") }}</router-link>
+      </b-col>
+      <b-col class="shrink">
+        <b-btn variant="link" @click="killTask(task.id)">{{ $t("kill") }}</b-btn>
+      </b-col>
+    </b-row>
+
+    <b-row>
+      <b-col>
+        <b-progress :max="task.progress.count">
+          <b-progress-bar :value="task.progress.done" :label-html="label" :striped="!task.progress.waiting"/>
+        </b-progress>
+      </b-col>
+    </b-row>
+
+  </b-list-group-item>
+</template>
+
+<script>
+import sist2AdminApi from "@/Sist2AdminApi";
+
+export default {
+  name: "TaskListItem",
+  props: ["task"],
+  computed: {
+    label() {
+
+      const count = this.task.progress.count;
+      const done = this.task.progress.done;
+
+      return `<span>${done}/${count}</span>`
+    }
+  },
+  methods: {
+    killTask(taskId) {
+      sist2AdminApi.killTask(taskId).then(() => {
+        this.$bvToast.toast(this.$t("killConfirmation"), {
+          title: this.$t("killConfirmationTitle"),
+          variant: "success",
+          toaster: "b-toaster-bottom-right"
+        });
+      });
+    }
+  }
+}
+</script>
+
+<style scoped>
+.shrink {
+  flex-grow: inherit;
+}
+</style>

sist2-admin/frontend/src/components/WebOptions.vue

@@ -0,0 +1,91 @@
+<template>
+  <div>
+    <label>{{ $t("webOptions.esUrl") }}</label>
+    <b-alert :variant="esTestOk ? 'success' : 'danger'" :show="showEsTestAlert" class="mt-1">
+      {{ esTestMessage }}
+    </b-alert>
+
+    <b-input-group>
+      <b-form-input v-model="options.es_url" @change="update()"></b-form-input>
+      <b-input-group-append>
+        <b-button variant="outline-primary" @click="testEs()">{{ $t("test") }}</b-button>
+      </b-input-group-append>
+    </b-input-group>
+
+    <b-form-checkbox v-model="options.es_insecure_ssl" :disabled="!this.options.es_url.startsWith('https')" @change="update()">
+      {{ $t("webOptions.esInsecure") }}
+    </b-form-checkbox>
+
+    <label>{{ $t("webOptions.esIndex") }}</label>
+    <b-form-input v-model="options.es_index" @change="update()"></b-form-input>
+
+    <label>{{ $t("webOptions.lang") }}</label>
+    <b-form-select v-model="options.lang" :options="['en', 'fr', 'zh-CN']" @change="update()"></b-form-select>
+
+    <label>{{ $t("webOptions.bind") }}</label>
+    <b-form-input v-model="options.bind" @change="update()"></b-form-input>
+
+    <label>{{ $t("webOptions.tagline") }}</label>
+    <b-form-textarea v-model="options.tagline" @change="update()"></b-form-textarea>
+
+    <label>{{ $t("webOptions.auth") }}</label>
+    <b-form-input v-model="options.auth" @change="update()"></b-form-input>
+
+    <label>{{ $t("webOptions.tagAuth") }}</label>
+    <b-form-input v-model="options.tag_auth" @change="update()"></b-form-input>
+
+    <br>
+    <h5>Auth0 options</h5>
+    <label>{{ $t("webOptions.auth0Audience") }}</label>
+    <b-form-input v-model="options.auth0_audience" @change="update()"></b-form-input>
+
+    <label>{{ $t("webOptions.auth0Domain") }}</label>
+    <b-form-input v-model="options.auth0_domain" @change="update()"></b-form-input>
+
+    <label>{{ $t("webOptions.auth0ClientId") }}</label>
+    <b-form-input v-model="options.auth0_client_id" @change="update()"></b-form-input>
+
+    <label>{{ $t("webOptions.auth0PublicKey") }}</label>
+    <b-textarea rows="10" v-model="options.auth0_public_key" @change="update()"></b-textarea>
+
+
+
+  </div>
+</template>
+
+<script>
+
+import sist2AdminApi from "@/Sist2AdminApi";
+
+export default {
+  name: "WebOptions",
+  props: ["options", "frontendName"],
+  data() {
+    return {
+      showEsTestAlert: false,
+      esTestOk: false,
+      esTestMessage: "",
+    }
+  },
+  methods: {
+    update() {
+      if (!this.options.es_url.startsWith("https")) {
+        this.options.es_insecure_ssl = false;
+      }
+
+      this.$emit("change", this.options);
+    },
+    testEs() {
+      sist2AdminApi.pingEs(this.options.es_url, this.options.es_insecure_ssl).then((resp) => {
+        this.showEsTestAlert = true;
+        this.esTestOk = resp.data.ok;
+        this.esTestMessage = resp.data.message;
+      });
+    }
+  }
+}
+</script>
+
+<style scoped>
+
+</style>

sist2-admin/frontend/src/components/icons/Sist2Icon.vue

@@ -0,0 +1,40 @@
+<template>
+  <svg
+      xmlns="http://www.w3.org/2000/svg"
+      width="27.868069mm"
+      height="7.6446671mm"
+      viewBox="0 0 27.868069 7.6446671"
+  >
+    <g transform="translate(-4.5018313,-4.1849793)">
+      <g
+          style="fill: currentColor;fill-opacity:1;stroke:none;stroke-width:0.26458332">
+        <path
+            d="m 6.3153296,11.829646 q -0.7717014,0 -1.8134983,-0.337619 v -0.916395 q 1.0128581,0.511252 1.803852,0.511252 0.5643067,0 0.901926,-0.236334 0.3376194,-0.236333 0.3376194,-0.63183 0,-0.3424428 -0.2845649,-0.5498376 Q 6.980922,9.4566645 6.3635609,9.3264399 L 5.9921796,9.2492698 Q 5.2301245,9.0949295 4.8732126,8.7428407 4.5211238,8.3859288 4.5211238,7.7733908 q 0,-0.7765245 0.5305447,-1.1961372 0.5305447,-0.4196126 1.5096409,-0.4196126 0.829579,0 1.6061036,0.3183268 V 7.3441319 Q 7.4101809,6.9004036 6.5854251,6.9004036 q -1.1671984,0 -1.1671984,0.7958171 0,0.2604492 0.1012858,0.4147895 0.1012858,0.1495171 0.3858507,0.2556261 0.2845649,0.1012858 0.8392253,0.2122179 l 0.3569119,0.067524 q 1.3408312,0.2652724 1.3408312,1.4614098 0,0.80064 -0.5691298,1.263661 -0.5691298,0.458197 -1.5578722,0.458197 z"
+            style="stroke-width:0.26458332"
+        />
+        <path
+            d="m 11.943927,5.3087694 q -0.144694,0 -0.144694,-0.144694 V 4.3296733 q 0,-0.144694 0.144694,-0.144694 h 0.694531 q 0.144694,0 0.144694,0.144694 v 0.8344021 q 0,0.144694 -0.144694,0.144694 z M 13.5645,11.728361 q -0.795817,0 -1.234722,-0.511253 -0.434082,-0.516075 -0.434082,-1.4469398 V 6.9823969 H 10.714028 V 6.2878656 h 2.069124 v 3.4823026 q 0,0.5884228 0.221864,0.8971028 0.221865,0.308681 0.6463,0.308681 h 1.036974 v 0.752409 z"
+            style="stroke-width:0.26458332"
+        />
+        <path
+            d="m 18.209178,11.829646 q -0.771701,0 -1.813498,-0.337619 v -0.916395 q 1.012858,0.511252 1.803852,0.511252 0.564306,0 0.901926,-0.236334 0.337619,-0.236333 0.337619,-0.63183 0,-0.3424428 -0.284565,-0.5498376 Q 18.87477,9.4566645 18.257409,9.3264399 l -0.371381,-0.07717 Q 17.123973,9.0949295 16.767061,8.7428407 16.414972,8.3859288 16.414972,7.7733908 q 0,-0.7765245 0.530545,-1.1961372 0.530545,-0.4196126 1.509641,-0.4196126 0.829579,0 1.606103,0.3183268 v 0.8681641 q -0.757232,-0.4437283 -1.581988,-0.4437283 -1.167198,0 -1.167198,0.7958171 0,0.2604492 0.101286,0.4147895 0.101286,0.1495171 0.385851,0.2556261 0.284565,0.1012858 0.839225,0.2122179 l 0.356912,0.067524 q 1.340831,0.2652724 1.340831,1.4614098 0,0.80064 -0.56913,1.263661 -0.56913,0.458197 -1.557872,0.458197 z"
+            style="stroke-width:0.26458332"
+        />
+        <path
+            d="m 25.207545,11.709068 q -0.993565,0 -1.408355,-0.40032 -0.409966,-0.405143 -0.409966,-1.3794164 V 6.9775737 H 21.947107 V 6.2878656 h 1.442117 V 4.8746874 l 0.887457,-0.3858507 v 1.7990289 h 2.016069 v 0.6897081 h -2.016069 v 2.9517579 q 0,0.5932454 0.226687,0.8344024 0.226687,0.236333 0.790994,0.236333 h 0.998388 v 0.709001 z"
+            style="stroke-width:0.26458332"
+        />
+        <path
+            d="m 27.995317,11.043476 q 0,-0.178456 0.120578,-0.299035 0.274919,-0.289388 0.651123,-0.684885 0.376205,-0.4003199 0.805464,-0.8681638 0.327973,-0.356912 0.491959,-0.5353679 0.16881,-0.1832791 0.255626,-0.2845649 0.09164,-0.1012858 0.178456,-0.2073948 0.255626,-0.3086805 0.405144,-0.5257215 0.15434,-0.2170411 0.250803,-0.4292589 0.168809,-0.3762045 0.168809,-0.7524089 0,-0.5980686 -0.352089,-0.935688 -0.356911,-0.3424425 -0.979096,-0.3424425 -0.863341,0 -1.938899,0.6414768 V 4.8361023 q 0.491959,-0.2363335 0.979096,-0.3569119 0.47749,-0.1205783 0.945334,-0.1205783 0.501606,0 0.940511,0.1350477 0.438905,0.1350478 0.766878,0.4244358 0.289388,0.2556261 0.463021,0.6270074 0.173633,0.3665582 0.173633,0.829579 0,0.4726671 -0.212218,0.9501574 -0.106109,0.2411567 -0.274919,0.4726671 -0.163986,0.2266873 -0.424435,0.540191 Q 31.270225,8.501684 31.077299,8.718725 30.884374,8.9357661 30.628748,9.2106847 30.445469,9.4084332 30.286305,9.5675966 30.131965,9.72676 29.958332,9.9003928 29.7847,10.069203 29.558012,10.300713 29.336148,10.5274 29.012998,10.869843 h 3.356901 v 0.819932 h -4.374582 z"
+            style="stroke-width:0.26458332"
+        />
+      </g>
+    </g>
+  </svg>
+</template>
+
+<script>
+export default {
+  name: "Sist2Icon"
+}
+</script>

sist2-admin/frontend/src/i18n/messages.js

@@ -0,0 +1,114 @@
+export default {
+    en: {
+        start: "Start",
+        stop: "Stop",
+        go: "Go",
+        online: "online",
+        offline: "offline",
+        delete: "Delete",
+        runNow: "Index now",
+        create: "Create",
+        test: "Test",
+
+        jobTitle: "job configuration",
+        tasks: "Tasks",
+        runningTasks: "Running tasks",
+        frontends: "Frontends",
+        jobDisabled: "There is no valid index for this job",
+        status: "Status",
+
+        taskHistory: "Task history",
+        taskName: "Task name",
+        taskStarted: "Started",
+        taskDuration: "Duration",
+        taskStatus: "Status",
+        logs: "Logs",
+        kill: "Kill",
+        killConfirmation: "SIGTERM signal sent to sist2 process",
+        killConfirmationTitle: "Confirmation",
+        follow: "Follow",
+        wholeFile: "Whole file",
+        logLevel: "Log level",
+        logMode: "Follow mode",
+        logFile: "Reading log file",
+
+        jobs: "Jobs",
+        newJobName: "New job name",
+        newJobHelp: "Create a new job to get started!",
+        newFrontendName: "New frontend name",
+        scanned: "last scan",
+        autoStart: "Start automatically",
+
+        runJobConfirmationTitle: "Task queued",
+        runJobConfirmation: "Check the Tasks page to monitor the status.",
+
+        extraQueryArgs: "Extra query arguments when launching from sist2-admin",
+        customUrl: "Custom URL when launching from sist2-admin",
+
+        selectJobs: "Select jobs",
+        webOptions: {
+            title: "Web options",
+            esUrl: "Elasticsearch URL",
+            esIndex: "Elasticsearch index name",
+            esInsecure: "Do not verify SSL connections to Elasticsearch.",
+            lang: "UI Language",
+            bind: "Listen address",
+            tagline: "Tagline in navbar",
+            auth: "Basic auth in user:password format",
+            tagAuth: "Basic auth in user:password format for tagging",
+            auth0Audience: "Auth0 audience",
+            auth0Domain: "Auth0 domain",
+            auth0ClientId: "Auth0 client ID",
+            auth0PublicKey: "Auth0 public key",
+        },
+        scanOptions: {
+            title: "Scanning options",
+            path: "Path",
+            threads: "Number of threads",
+            memThrottle: "Total memory threshold in MiB for scan throttling",
+            thumbnailQuality: "Thumbnail quality, on a scale of 0 to 100, 100 being the best",
+            thumbnailCount: "Number of thumbnails to generate. Set a value > 1 to create video previews, set to 0 to disable thumbnails.",
+            thumbnailSize: "Thumbnail size, in pixels",
+            contentSize: "Number of bytes to be extracted from text documents. Set to 0 to disable",
+            rewriteUrl: "Serve files from this url instead of from disk",
+            depth: "Scan up to this many subdirectories deep",
+            archive: "Archive file mode",
+            archivePassphrase: "Passphrase for encrypted archive files",
+            ocrLang: "Tesseract language",
+            ocrLangAlert: "You must select at least one language",
+            ocrEbooks: "Enable OCR'ing of ebook files",
+            ocrImages: "Enable OCR'ing of image files",
+            exclude: "Files that match this regex will not be scanned",
+            excludePlaceholder: "Exclude",
+            fast: "Only index file names & mime type",
+            checksums: "Calculate file checksums when scanning",
+            readSubtitles: "Read subtitles from media files",
+            memBuffer: "Maximum memory buffer size per thread in MiB for files inside archives",
+            treemapThreshold: "Relative size threshold for treemap",
+            optimizeIndex: "Defragment index file after scan to reduce its file size."
+        },
+        indexOptions: {
+            title: "Indexing options",
+            threads: "Number of threads",
+            esUrl: "Elasticsearch URL",
+            esIndex: "Elasticsearch index name",
+            esInsecure: "Do not verify SSL connections to Elasticsearch.",
+            batchSize: "Index batch size",
+            script: "User script"
+        },
+        jobOptions: {
+            title: "Job options",
+            cron: "Job schedule",
+            scheduleEnabled: "Enable scheduled re-scan",
+            noJobAvailable: "No jobs available.",
+            desktopNotifications: "Desktop notifications"
+        },
+        frontendOptions: {
+            title: "Frontend options",
+            noJobSelectedWarning: "You must select at least one job to start this frontend"
+        },
+        notifications: {
+            indexCompleted: "Task completed for [$JOB$]"
+        }
+    }
+}

sist2-admin/frontend/src/main.js

@@ -0,0 +1,31 @@
+import Vue from 'vue'
+
+import { BootstrapVue, IconsPlugin } from 'bootstrap-vue'
+
+import "bootstrap/dist/css/bootstrap.min.css"
+import "bootstrap-vue/dist/bootstrap-vue.min.css"
+
+Vue.use(BootstrapVue);
+Vue.use(IconsPlugin);
+
+import App from './App.vue';
+import router from './router';
+import store from './store';
+import VueI18n from "vue-i18n";
+import messages from "@/i18n/messages";
+
+Vue.use(VueI18n);
+
+const i18n = new VueI18n({
+  locale: "en",
+  messages: messages
+});
+
+Vue.config.productionTip = false
+
+new Vue({
+  router,
+  store,
+  i18n,
+  render: h => h(App)
+}).$mount('#app')

sist2-admin/frontend/src/router/index.js

@@ -0,0 +1,45 @@
+import Vue from 'vue'
+import VueRouter from 'vue-router'
+import Home from '../views/Home.vue'
+import Job from "@/views/Job";
+import Tasks from "@/views/Tasks";
+import Frontend from "@/views/Frontend";
+import Tail from "@/views/Tail";
+
+Vue.use(VueRouter);
+
+const routes = [
+  {
+    path: "/",
+    name: "Home",
+    component: Home
+  },
+  {
+    path: "/job/:name",
+    name: "Job",
+    component: Job
+  },
+  {
+    path: "/task/",
+    name: "Tasks",
+    component: Tasks
+  },
+  {
+    path: "/frontend/:name",
+    name: "Frontend",
+    component: Frontend
+  },
+  {
+    path: "/log/:taskId",
+    name: "Tail",
+    component: Tail
+  },
+]
+
+const router = new VueRouter({
+  mode: "hash",
+  base: process.env.BASE_URL,
+  routes
+})
+
+export default router

sist2-admin/frontend/src/store/index.js

@@ -0,0 +1,63 @@
+import Vue from "vue";
+import Vuex from "vuex";
+
+Vue.use(Vuex);
+
+function saveBrowserSettings(state) {
+    const settings = {
+        jobDesktopNotificationMap: state.jobDesktopNotificationMap
+    };
+    localStorage.setItem("sist2-admin-settings", JSON.stringify(settings));
+
+    console.log("SAVED");
+    console.log(settings);
+}
+
+export default new Vuex.Store({
+    state: {
+        sist2AdminInfo: null,
+        jobDesktopNotificationMap: {}
+    },
+    mutations: {
+        setSist2AdminInfo: (state, payload) => state.sist2AdminInfo = payload,
+        setJobDesktopNotificationMap: (state, payload) => state.jobDesktopNotificationMap = payload,
+    },
+    actions: {
+        notify: async ({state}, notification) => {
+
+            if (!state.jobDesktopNotificationMap[notification.job]) {
+                console.log("pass");
+                return;
+            }
+
+            new Notification(notification.messageString.replace("$JOB$", notification.job));
+        },
+        setJobDesktopNotification: async ({state}, {job, enabled}) => {
+
+            if (enabled === true) {
+                const permission = await Notification.requestPermission()
+
+                if (permission !== "granted") {
+                    return false;
+                }
+            }
+
+            state.jobDesktopNotificationMap[job] = enabled;
+            saveBrowserSettings(state);
+
+            return true;
+        },
+        loadBrowserSettings({commit}) {
+            const settingString = localStorage.getItem("sist2-admin-settings");
+
+            if (!settingString) {
+                return;
+            }
+
+            const settings = JSON.parse(settingString);
+
+            commit("setJobDesktopNotificationMap", settings["jobDesktopNotificationMap"]);
+        }
+    },
+    modules: {}
+})

sist2-admin/frontend/src/util.js

@@ -0,0 +1,8 @@
+
+export function formatBindAddress(address) {
+    if (address.startsWith("0.0.0.0")) {
+        return address.slice("0.0.0.0".length)
+    }
+
+    return address
+}

sist2-admin/frontend/src/views/Frontend.vue

@@ -0,0 +1,129 @@
+<template>
+  <b-card>
+    <b-card-title>
+      {{ name }}
+      <small style="vertical-align: top">
+        <b-badge v-if="!loading && frontend.running" variant="success">{{ $t("online") }}</b-badge>
+        <b-badge v-else-if="!loading" variant="secondary">{{ $t("offline") }}</b-badge>
+      </small>
+    </b-card-title>
+
+    <div class="mb-3" v-if="!loading">
+      <b-button class="mr-1" :disabled="frontend.running || !valid" variant="success" @click="start()">{{
+          $t("start")
+        }}
+      </b-button>
+      <b-button class="mr-1" :disabled="!frontend.running" variant="danger" @click="stop()">{{
+          $t("stop")
+        }}
+      </b-button>
+      <b-button class="mr-1" :disabled="!frontend.running" variant="primary" :href="frontendUrl" target="_blank">
+        {{ $t("go") }}
+      </b-button>
+      <b-button variant="danger" @click="deleteFrontend()">{{ $t("delete") }}</b-button>
+    </div>
+
+
+    <b-progress v-if="loading" striped animated value="100"></b-progress>
+    <b-card-body v-else>
+
+      <h4>{{ $t("frontendOptions.title") }}</h4>
+      <b-card>
+        <b-form-checkbox v-model="frontend.auto_start" @change="update()">
+          {{ $t("autoStart") }}
+        </b-form-checkbox>
+
+        <label>{{ $t("extraQueryArgs") }}</label>
+        <b-form-input v-model="frontend.extra_query_args" @change="update()"></b-form-input>
+
+        <label>{{ $t("customUrl") }}</label>
+        <b-form-input v-model="frontend.custom_url" @change="update()" placeholder="http://"></b-form-input>
+
+        <br/>
+
+        <b-alert v-if="!valid" variant="warning" show>{{ $t("frontendOptions.noJobSelectedWarning") }}</b-alert>
+
+        <JobCheckboxGroup :frontend="frontend" @input="update()"></JobCheckboxGroup>
+      </b-card>
+
+      <br/>
+
+      <h4>{{ $t("webOptions.title") }}</h4>
+      <b-card>
+        <WebOptions :options="frontend.web_options" :frontend-name="$route.params.name" @change="update()"></WebOptions>
+      </b-card>
+    </b-card-body>
+
+  </b-card>
+</template>
+
+<script>
+
+import Sist2AdminApi from "@/Sist2AdminApi";
+import JobCheckboxGroup from "@/components/JobCheckboxGroup";
+import WebOptions from "@/components/WebOptions";
+
+export default {
+  name: 'Frontend',
+  components: {JobCheckboxGroup, WebOptions},
+  data() {
+    return {
+      loading: true,
+      frontend: null,
+    }
+  },
+  computed: {
+    valid() {
+      return !this.loading && this.frontend.jobs.length > 0;
+    },
+    frontendUrl() {
+      if (this.frontend.custom_url) {
+        return this.frontend.custom_url + this.args;
+      }
+
+      if (this.frontend.web_options.bind.startsWith("0.0.0.0")) {
+        return window.location.protocol + "//" + window.location.hostname + ":" + this.port + this.args;
+      }
+
+      return window.location.protocol + "//" + this.frontend.web_options.bind + this.args;
+    },
+    name() {
+      return this.$route.params.name;
+    },
+    port() {
+      return this.frontend.web_options.bind.split(":")[1]
+    },
+    args() {
+      const args = this.frontend.extra_query_args;
+      if (args !== "") {
+        return "#" + (args.startsWith("?") ? (args) : ("?" + args));
+      }
+      return "";
+    }
+  },
+  mounted() {
+    Sist2AdminApi.getFrontend(this.name).then(resp => {
+      this.frontend = resp.data;
+      this.loading = false;
+    });
+  },
+  methods: {
+    start() {
+      this.frontend.running = true;
+      Sist2AdminApi.startFrontend(this.name)
+    },
+    stop() {
+      this.frontend.running = false;
+      Sist2AdminApi.stopFrontend(this.name)
+    },
+    deleteFrontend() {
+      Sist2AdminApi.deleteFrontend(this.name).then(() => {
+        this.$router.push("/frontends");
+      });
+    },
+    update() {
+      Sist2AdminApi.updateFrontend(this.name, this.frontend);
+    },
+  }
+}
+</script>

sist2-admin/frontend/src/views/Home.vue

@@ -0,0 +1,122 @@
+<template>
+  <div>
+    <b-card>
+      <b-card-title>{{ $t("jobs") }}</b-card-title>
+      <b-row>
+        <b-col>
+          <b-input id="new-job" v-model="newJobName" :placeholder="$t('newJobName')"></b-input>
+          <b-popover
+              :show.sync="showHelp"
+              target="new-job"
+              placement="top"
+              triggers="manual"
+              variant="primary"
+              :content="$t('newJobHelp')"
+          ></b-popover>
+        </b-col>
+        <b-col>
+          <b-button variant="primary" @click="createJob()" :disabled="!jobNameValid(newJobName)">{{ $t("create") }}
+          </b-button>
+        </b-col>
+      </b-row>
+
+      <hr/>
+
+      <b-progress v-if="jobsLoading" striped animated value="100"></b-progress>
+      <b-list-group v-else>
+        <JobListItem v-for="job in jobs" :key="job.name" :job="job"></JobListItem>
+      </b-list-group>
+    </b-card>
+
+    <br/>
+
+    <b-card>
+
+      <b-card-title>{{ $t("frontends") }}</b-card-title>
+
+      <b-row>
+        <b-col>
+          <b-input v-model="newFrontendName" :placeholder="$t('newFrontendName')"></b-input>
+        </b-col>
+        <b-col>
+          <b-button variant="primary" @click="createFrontend()" :disabled="!frontendNameValid(newFrontendName)">
+            {{ $t("create") }}
+          </b-button>
+        </b-col>
+      </b-row>
+
+      <hr/>
+
+      <b-progress v-if="frontendsLoading" striped animated value="100"></b-progress>
+      <b-list-group v-else>
+        <FrontendListItem v-for="frontend in frontends"
+                          :key="frontend.name" :frontend="frontend"></FrontendListItem>
+      </b-list-group>
+
+    </b-card>
+  </div>
+</template>
+
+<script>
+import JobListItem from "@/components/JobListItem";
+import {formatBindAddress} from "@/util";
+import Sist2AdminApi from "@/Sist2AdminApi";
+import FrontendListItem from "@/components/FrontendListItem";
+
+export default {
+  name: "Jobs",
+  components: {JobListItem, FrontendListItem},
+  data() {
+    return {
+      jobsLoading: true,
+      newJobName: "",
+      jobs: [],
+
+      frontendsLoading: true,
+      frontends: [],
+      formatBindAddress,
+      newFrontendName: "",
+
+      showHelp: false
+    }
+  },
+  mounted() {
+    this.loading = true;
+    this.reload();
+  },
+  methods: {
+    jobNameValid(name) {
+      if (this.jobs.some(job => job.name === name)) {
+        return false;
+      }
+
+      return /^[a-zA-Z0-9-_,.; ]+$/.test(name);
+    },
+    frontendNameValid(name) {
+      if (this.frontends.some(job => job.name === name)) {
+        return false;
+      }
+
+      return /^[a-zA-Z0-9-_,.; ]+$/.test(name);
+    },
+    reload() {
+      Sist2AdminApi.getJobs().then(resp => {
+        this.jobs = resp.data;
+        this.jobsLoading = false;
+
+        this.showHelp = this.jobs.length === 0;
+      });
+      Sist2AdminApi.getFrontends().then(resp => {
+        this.frontends = resp.data;
+        this.frontendsLoading = false;
+      });
+    },
+    createJob() {
+      Sist2AdminApi.createJob(this.newJobName).then(this.reload);
+    },
+    createFrontend() {
+      Sist2AdminApi.createFrontend(this.newFrontendName).then(this.reload)
+    }
+  }
+}
+</script>

sist2-admin/frontend/src/views/Job.vue

@@ -0,0 +1,92 @@
+<template>
+  <b-card>
+    <b-card-title>
+      [{{ getName() }}]
+      {{ $t("jobTitle") }}
+    </b-card-title>
+
+    <div class="mb-3">
+      <b-button class="mr-1" variant="primary" @click="runJob()">{{ $t("runNow") }}</b-button>
+      <b-button variant="danger" @click="deleteJob()">{{ $t("delete") }}</b-button>
+    </div>
+
+    <div v-if="job">
+      {{ $t("status") }}: <code>{{ job.status }}</code>
+    </div>
+
+    <b-progress v-if="loading" striped animated value="100"></b-progress>
+    <b-card-body v-else>
+
+      <h4>{{ $t("jobOptions.title") }}</h4>
+      <b-card>
+        <JobOptions :job="job" @change="update"></JobOptions>
+      </b-card>
+
+      <br/>
+
+      <h4>{{ $t("scanOptions.title") }}</h4>
+      <b-card>
+        <ScanOptions :options="job.scan_options" @change="update()"></ScanOptions>
+      </b-card>
+
+      <br/>
+
+      <h4>{{ $t("indexOptions.title") }}</h4>
+      <b-card>
+        <IndexOptions :options="job.index_options" @change="update()"></IndexOptions>
+      </b-card>
+
+    </b-card-body>
+
+  </b-card>
+</template>
+
+<script>
+import ScanOptions from "@/components/ScanOptions";
+import Sist2AdminApi from "@/Sist2AdminApi";
+import IndexOptions from "@/components/IndexOptions";
+import JobOptions from "@/components/JobOptions";
+
+export default {
+  name: "Job",
+  components: {
+    IndexOptions,
+    ScanOptions,
+    JobOptions
+  },
+  data() {
+    return {
+      loading: true,
+      job: null
+    }
+  },
+  methods: {
+    getName() {
+      return this.$route.params.name;
+    },
+    update() {
+      Sist2AdminApi.updateJob(this.getName(), this.job);
+    },
+    runJob() {
+      Sist2AdminApi.runJob(this.getName()).then(() => {
+        this.$bvToast.toast(this.$t("runJobConfirmation"), {
+          title: this.$t("runJobConfirmationTitle"),
+          variant: "success",
+          toaster: "b-toaster-bottom-right"
+        });
+      });
+    },
+    deleteJob() {
+      Sist2AdminApi.deleteJob(this.getName()).then(() => {
+        this.$router.push("/");
+      })
+    }
+  },
+  mounted() {
+    Sist2AdminApi.getJob(this.getName()).then(resp => {
+      this.loading = false;
+      this.job = resp.data;
+    })
+  }
+}
+</script>

sist2-admin/frontend/src/views/Tail.vue

@@ -0,0 +1,168 @@
+<template>
+  <b-card>
+    <b-card-body>
+
+      <h4 class="mb-3">{{ taskId }} {{ $t("logs") }}</h4>
+
+      <div v-if="$store.state.sist2AdminInfo">
+        {{ $t("logFile") }}
+        <code>{{ $store.state.sist2AdminInfo.logs_folder }}/sist2-{{ taskId }}.log</code>
+        <br/>
+        <br/>
+      </div>
+
+      <b-row>
+        <b-col>
+          <span>{{ $t("logLevel") }}</span>
+          <b-select :options="levels.slice(0, -1)" v-model="logLevel" @input="connect()"></b-select>
+        </b-col>
+        <b-col>
+          <span>{{ $t("logMode") }}</span>
+          <b-select :options="modeOptions" v-model="mode" @input="connect()"></b-select>
+        </b-col>
+      </b-row>
+
+      <div id="log-tail-output" class="mt-3 ml-1"></div>
+
+    </b-card-body>
+  </b-card>
+</template>
+
+<script>
+
+export default {
+  name: "Tail",
+  data() {
+    return {
+      logLevel: "DEBUG",
+      levels: ["DEBUG", "INFO", "WARNING", "ERROR", "ADMIN", "FATAL"],
+      socket: null,
+      mode: "follow",
+      modeOptions: [
+        {
+          "text": this.$t('follow'),
+          "value": "follow"
+        },
+        {
+          "text": this.$t('wholeFile'),
+          "value": "wholeFile"
+        }
+      ]
+    }
+  },
+  computed: {
+    taskId: function () {
+      return this.$route.params.taskId;
+    }
+  },
+  methods: {
+    connect() {
+      let lineCount = 0;
+      const outputElem = document.getElementById("log-tail-output")
+      outputElem.replaceChildren();
+      if (this.socket !== null) {
+        this.socket.close();
+      }
+
+      const n = this.mode === "follow" ? 32 : 9999999999;
+      this.socket = new WebSocket(`ws://${window.location.host}/log/${this.taskId}?n=${n}`);
+      this.socket.onopen = () => {
+        this.socket.send("Hello from client");
+      }
+
+      this.socket.onmessage = e => {
+        let message;
+        try {
+          message = JSON.parse(e.data);
+        } catch {
+          console.error(e.data)
+          return;
+        }
+
+        if ("ping" in message) {
+          return;
+        }
+
+        if (message.level === undefined) {
+
+          if ("stderr" in message) {
+            message.level = "ERROR";
+            message.message = message["stderr"];
+          } else {
+            message.level = "ADMIN";
+            message.message = message["sist2-admin"];
+          }
+          message.datetime = ""
+          message.filepath = ""
+        }
+
+        if (this.levels.indexOf(message.level) < this.levels.indexOf(this.logLevel)) {
+          return;
+        }
+
+        const logLine = `${message.datetime} [${message.level} ${message.filepath}] ${message.message}`;
+
+        const span = document.createElement("span");
+        span.setAttribute("class", message.level);
+        span.appendChild(document.createTextNode(logLine));
+
+        outputElem.appendChild(span);
+        lineCount += 1;
+
+        if (this.mode === "follow" && lineCount >= n) {
+          outputElem.firstChild.remove();
+        }
+      }
+    }
+  },
+  mounted() {
+    this.connect()
+  }
+}
+
+</script>
+
+<style>
+#log-tail-output span {
+  display: block;
+}
+
+span.DEBUG {
+  color: #9E9E9E;
+}
+
+span.WARNING {
+  color: #FFB300;
+}
+
+span.INFO {
+  color: #039BE5;
+}
+
+span.ERROR {
+  color: #F4511E;
+}
+
+span.FATAL {
+  color: #F4511E;
+}
+
+span.ADMIN {
+  color: #ee05ff;
+}
+
+
+#log-tail-output {
+  font-size: 13px;
+  font-family: monospace;
+
+  padding: 6px;
+  background-color: #f5f5f5;
+  border: 1px solid #ccc;
+  border-radius: 4px;
+  margin: 3px;
+  white-space: pre;
+  color: #000;
+  overflow: hidden;
+}
+</style>

sist2-admin/frontend/src/views/Tasks.vue

@@ -0,0 +1,150 @@
+<template>
+  <div>
+
+    <b-card v-if="tasks.length > 0">
+      <h2>{{ $t("runningTasks") }}</h2>
+      <b-list-group>
+        <TaskListItem v-for="task in tasks" :key="task.id" :task="task"></TaskListItem>
+      </b-list-group>
+    </b-card>
+
+    <b-card class="mt-4">
+
+      <b-card-title>{{ $t("taskHistory") }}</b-card-title>
+
+      <br/>
+
+      <b-table
+          id="task-history"
+          :items="historyItems"
+          :fields="historyFields"
+          :current-page="historyCurrentPage"
+          :tbody-tr-class="rowClass"
+          :per-page="10"
+      >
+        <template #cell(logs)="data">
+          <router-link :to="`/log/${data.item.logs}`">{{ $t("logs") }}</router-link>
+        </template>
+
+      </b-table>
+
+      <b-pagination limit="20" v-model="historyCurrentPage" :total-rows="historyItems.length"
+                    :per-page="10"></b-pagination>
+
+    </b-card>
+  </div>
+</template>
+
+<script>
+import TaskListItem from "@/components/TaskListItem";
+import Sist2AdminApi from "@/Sist2AdminApi";
+import moment from "moment";
+
+const DAY = 3600 * 24;
+const HOUR = 3600;
+const MINUTE = 60;
+
+function humanDuration(sec_num) {
+  sec_num = sec_num / 1000;
+  const days = Math.floor(sec_num / DAY);
+  sec_num -= days * DAY;
+  const hours = Math.floor(sec_num / HOUR);
+  sec_num -= hours * HOUR;
+  const minutes = Math.floor(sec_num / MINUTE);
+  sec_num -= minutes * MINUTE;
+  const seconds = Math.floor(sec_num);
+
+  if (days > 0) {
+    return `${days} days ${hours}h ${minutes}m ${seconds}s`;
+  }
+
+  if (hours > 0) {
+    return `${hours}h ${minutes}m ${seconds}s`;
+  }
+
+  if (minutes > 0) {
+    return `${minutes}m ${seconds}s`;
+  }
+
+  if (seconds > 0) {
+    return `${seconds}s`;
+  }
+
+  return "<0s";
+}
+
+export default {
+  name: 'Tasks',
+  components: {TaskListItem},
+  data() {
+    return {
+      loading: true,
+      tasks: [],
+      taskHistory: [],
+      timerId: null,
+      historyFields: [
+        {key: "name", label: this.$t("taskName")},
+        {key: "time", label: this.$t("taskStarted")},
+        {key: "duration", label: this.$t("taskDuration")},
+        {key: "status", label: this.$t("taskStatus")},
+        {key: "logs", label: this.$t("logs")},
+      ],
+      historyCurrentPage: 1,
+      historyItems: []
+    }
+  },
+  props: {
+    msg: String
+  },
+  mounted() {
+    this.loading = true;
+    this.update().then(() => this.loading = false);
+
+    this.timerId = window.setInterval(this.update, 1000);
+    this.updateHistory();
+  },
+  destroyed() {
+    if (this.timerId) {
+      window.clearInterval(this.timerId);
+    }
+  },
+  methods: {
+    rowClass(row) {
+      if (row.status === "failed") {
+        return "table-danger";
+      }
+      return null;
+    },
+    updateHistory() {
+      Sist2AdminApi.getTaskHistory().then(resp => {
+        this.historyItems = resp.data.map(row => ({
+          id: row.id,
+          name: row.name,
+          duration: this.taskDuration(row),
+          time: moment(row.started).format("dd, MMM Do YYYY, HH:mm:ss"),
+          logs: row.id,
+          status: row.return_code === 0 ? "ok" : "failed"
+        }));
+      });
+    },
+    update() {
+      return Sist2AdminApi.getTasks().then(resp => {
+        this.tasks = resp.data;
+      })
+    },
+    taskDuration(task) {
+      const start = moment.utc(task.started);
+      const end = moment.utc(task.ended);
+
+      return humanDuration(end.diff(start))
+    }
+  }
+}
+</script>
+
+<style scoped>
+#task-history {
+  font-family: monospace;
+  font-size: 12px;
+}
+</style>

sist2-admin/frontend/vue.config.js

@@ -0,0 +1,5 @@
+module.exports = {
+    publicPath: "",
+    filenameHashing: false,
+    productionSourceMap: false,
+};

sist2-admin/requirements.txt

@@ -0,0 +1,5 @@
+fastapi
+git+https://github.com/simon987/hexlib.git
+uvicorn
+websockets
+pycron

sist2-admin/sist2_admin/app.py

@@ -0,0 +1,390 @@
+import asyncio
+import os
+import signal
+from datetime import datetime
+from urllib.parse import urlparse
+
+import requests
+import uvicorn
+from fastapi import FastAPI, HTTPException
+from hexlib.db import PersistentState
+from requests import ConnectionError
+from requests.exceptions import SSLError
+from starlette.middleware.cors import CORSMiddleware
+from starlette.responses import RedirectResponse
+from starlette.staticfiles import StaticFiles
+from starlette.websockets import WebSocket
+from websockets.exceptions import ConnectionClosed
+
+import cron
+from config import LOG_FOLDER, logger, WEBSERVER_PORT, DATA_FOLDER, SIST2_BINARY
+from jobs import Sist2Job, Sist2ScanTask, TaskQueue, Sist2IndexTask, JobStatus
+from notifications import Subscribe, Notifications
+from sist2 import Sist2
+from state import migrate_v1_to_v2, RUNNING_FRONTENDS, TESSERACT_LANGS, DB_SCHEMA_VERSION
+from web import Sist2Frontend
+
+sist2 = Sist2(SIST2_BINARY, DATA_FOLDER)
+db = PersistentState(dbfile=os.path.join(DATA_FOLDER, "state.db"))
+notifications = Notifications()
+task_queue = TaskQueue(sist2, db, notifications)
+
+app = FastAPI()
+
+app.add_middleware(
+    CORSMiddleware,
+    allow_credentials=True,
+    allow_origins=["*"],
+    allow_methods=["*"],
+    allow_headers=["*"],
+)
+
+app.mount("/ui/", StaticFiles(directory="./frontend/dist", html=True), name="static")
+
+
+@app.get("/")
+async def home():
+    return RedirectResponse("ui")
+
+
+@app.get("/api")
+async def api():
+    return {
+        "tesseract_langs": TESSERACT_LANGS,
+        "logs_folder": LOG_FOLDER
+    }
+
+
+@app.get("/api/job/{name:str}")
+async def get_job(name: str):
+    job = db["jobs"][name]
+    if not job:
+        raise HTTPException(status_code=404)
+    return job
+
+
+@app.get("/api/frontend/{name:str}")
+async def get_frontend(name: str):
+    frontend = db["frontends"][name]
+    frontend: Sist2Frontend
+    if frontend:
+        frontend.running = frontend.name in RUNNING_FRONTENDS
+        return frontend
+    raise HTTPException(status_code=404)
+
+
+@app.get("/api/job/")
+async def get_jobs():
+    return list(db["jobs"])
+
+
+@app.put("/api/job/{name:str}")
+async def update_job(name: str, new_job: Sist2Job):
+    # TODO: Check etag
+
+    new_job.last_modified = datetime.now()
+    job = db["jobs"][name]
+    if not job:
+        raise HTTPException(status_code=404)
+
+    args_that_trigger_full_scan = [
+        "path",
+        "thumbnail_count",
+        "thumbnail_quality",
+        "thumbnail_size",
+        "content_size",
+        "depth",
+        "archive",
+        "archive_passphrase",
+        "ocr_lang",
+        "ocr_images",
+        "ocr_ebooks",
+        "fast",
+        "checksums",
+        "read_subtitles",
+    ]
+    for arg in args_that_trigger_full_scan:
+        if getattr(new_job.scan_options, arg) != getattr(job.scan_options, arg):
+            new_job.do_full_scan = True
+
+    db["jobs"][name] = new_job
+
+
+@app.put("/api/frontend/{name:str}")
+async def update_frontend(name: str, frontend: Sist2Frontend):
+    db["frontends"][name] = frontend
+
+    # TODO: Check etag
+
+    return "ok"
+
+
+@app.get("/api/task/")
+async def get_tasks():
+    return list(map(lambda t: t.json(), task_queue.tasks()))
+
+
+@app.get("/api/task/history")
+async def task_history():
+    return list(db["task_done"].sql("ORDER BY started DESC"))
+
+
+@app.post("/api/task/{task_id:str}/kill")
+async def kill_job(task_id: str):
+    return task_queue.kill_task(task_id)
+
+
+def _run_job(job: Sist2Job):
+    job.last_modified = datetime.now()
+    if job.status == JobStatus("created"):
+        job.status = JobStatus("started")
+    db["jobs"][job.name] = job
+
+    scan_task = Sist2ScanTask(job, f"Scan [{job.name}]")
+    index_task = Sist2IndexTask(job, f"Index [{job.name}]", depends_on=scan_task)
+
+    task_queue.submit(scan_task)
+    task_queue.submit(index_task)
+
+
+@app.get("/api/job/{name:str}/run")
+async def run_job(name: str):
+    job = db["jobs"][name]
+    if not job:
+        raise HTTPException(status_code=404)
+
+    _run_job(job)
+
+    return "ok"
+
+
+@app.delete("/api/job/{name:str}")
+async def delete_job(name: str):
+    job = db["jobs"][name]
+    if job:
+        del db["jobs"][name]
+    else:
+        raise HTTPException(status_code=404)
+
+
+@app.delete("/api/frontend/{name:str}")
+async def delete_frontend(name: str):
+    if name in RUNNING_FRONTENDS:
+        os.kill(RUNNING_FRONTENDS[name], signal.SIGTERM)
+        del RUNNING_FRONTENDS[name]
+
+    frontend = db["frontends"][name]
+    if frontend:
+        del db["frontends"][name]
+    else:
+        raise HTTPException(status_code=404)
+
+
+@app.post("/api/job/{name:str}")
+async def create_job(name: str):
+    if db["jobs"][name]:
+        raise ValueError("Job with the same name already exists")
+
+    job = Sist2Job.create_default(name)
+    db["jobs"][name] = job
+
+    return job
+
+
+@app.post("/api/frontend/{name:str}")
+async def create_frontend(name: str):
+    if db["frontends"][name]:
+        raise ValueError("Frontend with the same name already exists")
+
+    frontend = Sist2Frontend.create_default(name)
+    db["frontends"][name] = frontend
+
+    return frontend
+
+
+@app.get("/api/ping_es")
+async def ping_es(url: str, insecure: bool):
+    return check_es_version(url, insecure)
+
+
+def check_es_version(es_url: str, insecure: bool):
+    try:
+        url = urlparse(es_url)
+        if url.username:
+            auth = (url.username, url.password)
+            es_url = f"{url.scheme}://{url.hostname}:{url.port}"
+        else:
+            auth = None
+        r = requests.get(es_url, verify=insecure, auth=auth)
+    except SSLError:
+        return {
+            "ok": False,
+            "message": "Invalid SSL certificate"
+        }
+    except ConnectionError as e:
+        return {
+            "ok": False,
+            "message": "Connection refused"
+        }
+    except ValueError as e:
+        return {
+            "ok": False,
+            "message": str(e)
+        }
+
+    if r.status_code == 401:
+        return {
+            "ok": False,
+            "message": "Authentication failure"
+        }
+
+    try:
+        return {
+            "ok": True,
+            "message": "Elasticsearch version " + r.json()["version"]["number"]
+        }
+    except:
+        return {
+            "ok": False,
+            "message": "Could not read version"
+        }
+
+
+def start_frontend_(frontend: Sist2Frontend):
+    frontend.web_options.indices = list(map(lambda j: db["jobs"][j].index_path, frontend.jobs))
+
+    pid = sist2.web(frontend.web_options, frontend.name)
+    RUNNING_FRONTENDS[frontend.name] = pid
+
+
+@app.post("/api/frontend/{name:str}/start")
+async def start_frontend(name: str):
+    frontend = db["frontends"][name]
+    if not frontend:
+        raise HTTPException(status_code=404)
+
+    start_frontend_(frontend)
+
+
+@app.post("/api/frontend/{name:str}/stop")
+async def stop_frontend(name: str):
+    if name in RUNNING_FRONTENDS:
+        os.kill(RUNNING_FRONTENDS[name], signal.SIGTERM)
+        del RUNNING_FRONTENDS[name]
+
+
+@app.get("/api/frontend/")
+async def get_frontends():
+    res = []
+    for frontend in db["frontends"]:
+        frontend: Sist2Frontend
+        frontend.running = frontend.name in RUNNING_FRONTENDS
+        res.append(frontend)
+    return res
+
+
+def tail(filepath: str, n: int):
+    with open(filepath) as file:
+
+        reached_eof = False
+        buffer = []
+
+        line = ""
+        while True:
+            tmp = file.readline()
+            if tmp:
+                line += tmp
+
+                if line.endswith("\n"):
+
+                    if reached_eof:
+                        yield line
+                    else:
+                        if len(buffer) > n:
+                            buffer.pop(0)
+                        buffer.append(line)
+                line = ""
+            else:
+                if not reached_eof:
+                    reached_eof = True
+                    yield from buffer
+                yield None
+
+
+@app.websocket("/notifications")
+async def ws_tail_log(websocket: WebSocket):
+    await websocket.accept()
+
+    try:
+        await websocket.receive_text()
+
+        async with Subscribe(notifications) as ob:
+            async for notification in ob.notifications():
+                await websocket.send_json(notification)
+                print(notification)
+
+    except ConnectionClosed:
+        return
+
+
+@app.websocket("/log/{task_id}")
+async def ws_tail_log(websocket: WebSocket, task_id: str, n: int):
+    log_file = os.path.join(LOG_FOLDER, f"sist2-{task_id}.log")
+
+    await websocket.accept()
+
+    try:
+        await websocket.receive_text()
+    except ConnectionClosed:
+        return
+
+    while True:
+        for line in tail(log_file, n):
+
+            try:
+                if line:
+                    await websocket.send_text(line)
+                else:
+                    await websocket.send_json({"ping": ""})
+                    await asyncio.sleep(0.1)
+            except ConnectionClosed:
+                return
+
+
+def main():
+    uvicorn.run(app, port=WEBSERVER_PORT, host="0.0.0.0")
+
+
+def initialize_db():
+    db["sist2_admin"]["info"] = {"version": DB_SCHEMA_VERSION}
+
+    frontend = Sist2Frontend.create_default("default")
+    db["frontends"]["default"] = frontend
+
+    logger.info("Initialized database.")
+
+
+def start_frontends():
+    for frontend in db["frontends"]:
+        frontend: Sist2Frontend
+        if frontend.auto_start and len(frontend.jobs) > 0:
+            start_frontend_(frontend)
+
+
+if __name__ == '__main__':
+
+    if not db["sist2_admin"]["info"]:
+        initialize_db()
+    if db["sist2_admin"]["info"]["version"] == "1":
+        logger.info("Migrating to v2 database schema")
+        migrate_v1_to_v2(db)
+    if db["sist2_admin"]["info"]["version"] == "2":
+        logger.error("Cannot migrate database from v2 to v3. Delete state.db to proceed.")
+        exit(-1)
+
+    start_frontends()
+    cron.initialize(db, _run_job)
+
+    logger.info("Started sist2-admin. Hello!")
+
+    main()

sist2-admin/sist2_admin/config.py

@@ -0,0 +1,30 @@
+import os
+import logging
+import sys
+from logging import StreamHandler
+from logging.handlers import RotatingFileHandler
+
+MAX_LOG_SIZE = 1 * 1024 * 1024
+
+SIST2_BINARY = os.environ.get("SIST2_BINARY", "/root/sist2")
+DATA_FOLDER = os.environ.get("DATA_FOLDER", "/sist2-admin/")
+LOG_FOLDER = os.path.join(DATA_FOLDER, "logs")
+WEBSERVER_PORT = 8080
+
+os.makedirs(LOG_FOLDER, exist_ok=True)
+os.makedirs(DATA_FOLDER, exist_ok=True)
+
+logger = logging.Logger("sist2-admin")
+
+_log_file = os.path.join(LOG_FOLDER, "sist2-admin.log")
+_log_fmt = "%(asctime)s [%(levelname)s] %(message)s"
+_log_formatter = logging.Formatter(_log_fmt, datefmt='%Y-%m-%d %H:%M:%S')
+
+console_handler = StreamHandler(sys.stdout)
+console_handler.setFormatter(_log_formatter)
+
+file_handler = RotatingFileHandler(_log_file, mode="a", maxBytes=MAX_LOG_SIZE, backupCount=1)
+file_handler.setFormatter(_log_formatter)
+
+logger.addHandler(console_handler)
+logger.addHandler(file_handler)

sist2-admin/sist2_admin/cron.py

@@ -0,0 +1,33 @@
+from threading import Thread
+
+import pycron
+import time
+
+from hexlib.db import PersistentState
+
+from config import logger
+from jobs import Sist2Job
+
+
+def _check_schedule(db: PersistentState, run_job):
+    for job in db["jobs"]:
+        job: Sist2Job
+
+        if job.schedule_enabled:
+            if pycron.is_now(job.cron_expression):
+                logger.info(f"Submit scan task to queue for [{job.name}]")
+                run_job(job)
+
+
+def _cron_thread(db, run_job):
+    time.sleep(60 - (time.time() % 60))
+    start = time.time()
+
+    while True:
+        _check_schedule(db, run_job)
+        time.sleep(60 - ((time.time() - start) % 60))
+
+
+def initialize(db, run_job):
+    t = Thread(target=_cron_thread, args=(db, run_job), daemon=True, name="timer")
+    t.start()

sist2-admin/sist2_admin/jobs.py

@@ -0,0 +1,317 @@
+import json
+import logging
+import os.path
+import signal
+import uuid
+from datetime import datetime
+from enum import Enum
+from logging import FileHandler
+from threading import Lock, Thread
+from time import sleep
+from uuid import uuid4, UUID
+
+from hexlib.db import PersistentState
+from pydantic import BaseModel
+
+from config import logger, LOG_FOLDER
+from notifications import Notifications
+from sist2 import ScanOptions, IndexOptions, Sist2
+from state import RUNNING_FRONTENDS
+from web import Sist2Frontend
+
+
+class JobStatus(Enum):
+    CREATED = "created"
+    STARTED = "started"
+    INDEXED = "indexed"
+    FAILED = "failed"
+
+
+class Sist2Job(BaseModel):
+    name: str
+    scan_options: ScanOptions
+    index_options: IndexOptions
+
+    cron_expression: str
+    schedule_enabled: bool = False
+
+    previous_index: str = None
+    index_path: str = None
+    previous_index_path: str = None
+    last_index_date: datetime = None
+    status: JobStatus = JobStatus("created")
+    last_modified: datetime
+    etag: str = None
+    do_full_scan: bool = False
+
+    def __init__(self, **kwargs):
+        super().__init__(**kwargs)
+
+    @staticmethod
+    def create_default(name: str):
+        return Sist2Job(
+            name=name,
+            scan_options=ScanOptions(path="/"),
+            index_options=IndexOptions(),
+            last_modified=datetime.now(),
+            cron_expression="0 0 * * *"
+        )
+
+    # @validator("etag", always=True)
+    # def validate_etag(cls, value, values):
+    #     s = values["name"] + values["scan_options"].json() + values["index_options"].json() + values["cron_expression"]
+    #     return md5(s.encode()).hexdigest()
+
+
+class Sist2TaskProgress:
+
+    def __init__(self, done: int = 0, count: int = 0, index_size: int = 0, tn_size: int = 0, waiting: bool = False):
+        self.done = done
+        self.count = count
+        self.index_size = index_size
+        self.store_size = tn_size
+        self.waiting = waiting
+
+    def percent(self):
+        return (self.done / self.count) if self.count else 0
+
+
+class Sist2Task:
+
+    def __init__(self, job: Sist2Job, display_name: str, depends_on: uuid.UUID = None):
+        self.job = job
+        self.display_name = display_name
+
+        self.progress = Sist2TaskProgress()
+        self.id = uuid4()
+        self.pid = None
+        self.started = None
+        self.ended = None
+        self.depends_on = depends_on
+
+        self._logger = logging.Logger(name=f"{self.id}")
+        self._logger.addHandler(FileHandler(os.path.join(LOG_FOLDER, f"sist2-{self.id}.log")))
+
+    def json(self):
+        return {
+            "id": self.id,
+            "job": self.job,
+            "display_name": self.display_name,
+            "progress": self.progress,
+            "started": self.started,
+            "ended": self.ended,
+            "depends_on": self.depends_on,
+        }
+
+    def log_callback(self, log_json):
+
+        if "progress" in log_json:
+            self.progress = Sist2TaskProgress(**log_json["progress"])
+        elif self._logger:
+            self._logger.info(json.dumps(log_json))
+
+    def run(self, sist2: Sist2, db: PersistentState):
+        self.started = datetime.now()
+
+        logger.info(f"Started task {self.display_name}")
+
+
+class Sist2ScanTask(Sist2Task):
+
+    def run(self, sist2: Sist2, db: PersistentState):
+        super().run(sist2, db)
+
+        self.job.scan_options.name = self.job.name
+
+        if self.job.index_path is not None and not self.job.do_full_scan:
+            self.job.scan_options.output = self.job.index_path
+        else:
+            self.job.scan_options.output = None
+
+        def set_pid(pid):
+            self.pid = pid
+
+        return_code = sist2.scan(self.job.scan_options, logs_cb=self.log_callback, set_pid_cb=set_pid)
+        self.ended = datetime.now()
+
+        if return_code != 0:
+            self._logger.error(json.dumps({"sist2-admin": f"Process returned non-zero exit code ({return_code})"}))
+            logger.info(f"Task {self.display_name} failed ({return_code})")
+        else:
+            self.job.index_path = self.job.scan_options.output
+            self.job.last_index_date = datetime.now()
+            self.job.do_full_scan = False
+            db["jobs"][self.job.name] = self.job
+            self._logger.info(json.dumps({"sist2-admin": f"Save last_index_date={self.job.last_index_date}"}))
+
+        logger.info(f"Completed {self.display_name} ({return_code=})")
+
+        # Remove old index
+        if return_code == 0:
+            if self.job.previous_index_path is not None and self.job.previous_index_path != self.job.index_path:
+                self._logger.info(json.dumps({"sist2-admin": f"Remove {self.job.previous_index_path=}"}))
+                try:
+                    os.remove(self.job.previous_index_path)
+                except FileNotFoundError:
+                    pass
+
+            self.job.previous_index_path = self.job.index_path
+            db["jobs"][self.job.name] = self.job
+
+        return return_code
+
+
+class Sist2IndexTask(Sist2Task):
+
+    def __init__(self, job: Sist2Job, display_name: str, depends_on: Sist2Task):
+        super().__init__(job, display_name, depends_on=depends_on.id)
+
+    def run(self, sist2: Sist2, db: PersistentState):
+        super().run(sist2, db)
+
+        self.job.index_options.path = self.job.scan_options.output
+
+        return_code = sist2.index(self.job.index_options, logs_cb=self.log_callback)
+        self.ended = datetime.now()
+
+        duration = self.ended - self.started
+
+        ok = return_code == 0
+
+        if ok:
+            self.restart_running_frontends(db, sist2)
+
+        # Update status
+        self.job.status = JobStatus("indexed") if ok else JobStatus("failed")
+        self.job.previous_index_path = self.job.index_path
+        db["jobs"][self.job.name] = self.job
+
+        self._logger.info(json.dumps({"sist2-admin": f"Sist2Scan task finished {return_code=}, {duration=}"}))
+
+        logger.info(f"Completed {self.display_name} ({return_code=})")
+
+        return return_code
+
+    def restart_running_frontends(self, db: PersistentState, sist2: Sist2):
+        for frontend_name, pid in RUNNING_FRONTENDS.items():
+            frontend = db["frontends"][frontend_name]
+            frontend: Sist2Frontend
+
+            try:
+                os.kill(pid, signal.SIGTERM)
+            except ProcessLookupError:
+                pass
+            try:
+                os.wait()
+            except ChildProcessError:
+                pass
+
+            frontend.web_options.indices = map(lambda j: db["jobs"][j].index_path, frontend.jobs)
+
+            pid = sist2.web(frontend.web_options, frontend.name)
+            RUNNING_FRONTENDS[frontend_name] = pid
+
+            self._logger.info(json.dumps({"sist2-admin": f"Restart frontend {pid=} {frontend_name=}"}))
+
+
+class TaskQueue:
+    def __init__(self, sist2: Sist2, db: PersistentState, notifications: Notifications):
+        self._lock = Lock()
+
+        self._sist2 = sist2
+        self._db = db
+        self._notifications = notifications
+
+        self._tasks = {}
+        self._queue = []
+        self._sem = 0
+
+        self._thread = Thread(target=self._check_new_task, daemon=True)
+        self._thread.start()
+
+    def _tasks_failed(self):
+        done = set()
+
+        for row in self._db["task_done"].sql("WHERE return_code != 0"):
+            done.add(uuid.UUID(row["id"]))
+
+        return done
+
+    def _tasks_done(self):
+
+        done = set()
+
+        for row in self._db["task_done"]:
+            done.add(uuid.UUID(row["id"]))
+
+        return done
+
+    def _check_new_task(self):
+        while True:
+            with self._lock:
+                for task in list(self._queue):
+                    task: Sist2Task
+
+                    if self._sem >= 1:
+                        break
+
+                    if not task.depends_on or task.depends_on in self._tasks_done():
+                        self._queue.remove(task)
+
+                        if task.depends_on in self._tasks_failed():
+                            # The task which we depend on failed, continue
+                            continue
+
+                        self._sem += 1
+
+                        t = Thread(target=self._run_task, args=(task,))
+
+                        self._tasks[task.id] = {
+                            "task": task,
+                            "thread": t,
+                        }
+
+                        t.start()
+                    break
+            sleep(1)
+
+    def tasks(self):
+        return list(map(lambda t: t["task"], self._tasks.values()))
+
+    def kill_task(self, task_id):
+
+        task = self._tasks.get(UUID(task_id))
+
+        if task:
+            pid = task["task"].pid
+            logger.info(f"Killing task {task_id} (pid={pid})")
+            os.kill(pid, signal.SIGTERM)
+            return True
+
+        return False
+
+    def _run_task(self, task: Sist2Task):
+        task_result = task.run(self._sist2, self._db)
+
+        with self._lock:
+            del self._tasks[task.id]
+            self._sem -= 1
+
+            self._db["task_done"][task.id] = {
+                "ended": task.ended,
+                "started": task.started,
+                "name": task.display_name,
+                "return_code": task_result
+            }
+        if isinstance(task, Sist2IndexTask):
+            self._notifications.notify({
+                "message": "notifications.indexCompleted",
+                "job": task.job.name
+            })
+
+    def submit(self, task: Sist2Task):
+
+        logger.info(f"Submitted task to queue {task.display_name}")
+
+        with self._lock:
+            self._queue.append(task)

sist2-admin/sist2_admin/notifications.py

@@ -0,0 +1,40 @@
+import asyncio
+from typing import List
+
+
+class Notifications:
+    def __init__(self):
+        self._subscribers: List[Subscribe] = []
+
+    def subscribe(self, ob):
+        self._subscribers.append(ob)
+
+    def unsubscribe(self, ob):
+        self._subscribers.remove(ob)
+
+    def notify(self, notification: dict):
+        for ob in self._subscribers:
+            ob.notify(notification)
+
+
+class Subscribe:
+    def __init__(self, notifications: Notifications):
+        self._queue = []
+        self._notifications = notifications
+
+    async def __aenter__(self):
+        self._notifications.subscribe(self)
+        return self
+
+    async def __aexit__(self, exc_type, exc_val, exc_tb):
+        self._notifications.unsubscribe(self)
+
+    def notify(self, notification: dict):
+        self._queue.append(notification)
+
+    async def notifications(self):
+        while True:
+            try:
+                yield self._queue.pop(0)
+            except IndexError:
+                await asyncio.sleep(0.1)

sist2-admin/sist2_admin/sist2.py

@@ -0,0 +1,323 @@
+import datetime
+import json
+import logging
+import os.path
+from datetime import datetime
+from io import TextIOWrapper
+from logging import FileHandler
+from subprocess import Popen, PIPE
+from tempfile import NamedTemporaryFile
+from threading import Thread
+from typing import List
+
+from pydantic import BaseModel
+
+from config import logger, LOG_FOLDER
+
+
+class Sist2Version:
+    def __init__(self, version: str):
+        self._version = version
+
+        self.major, self.minor, self.patch = [int(x) for x in version.split(".")]
+
+    def __str__(self):
+        return f"{self.major}.{self.minor}.{self.patch}"
+
+
+class WebOptions(BaseModel):
+    indices: List[str] = []
+    es_url: str = "http://elasticsearch:9200"
+    es_insecure_ssl: bool = False
+    es_index: str = "sist2"
+    bind: str = "0.0.0.0:4090"
+    auth: str = None
+    tag_auth: str = None
+    tagline: str = "Lightning-fast file system indexer and search tool"
+    dev: bool = False
+    lang: str = "en"
+    auth0_audience: str = None
+    auth0_domain: str = None
+    auth0_client_id: str = None
+    auth0_public_key: str = None
+    auth0_public_key_file: str = None
+
+    def __init__(self, **kwargs):
+        super().__init__(**kwargs)
+
+    def args(self):
+        args = ["web", f"--es-url={self.es_url}", f"--es-index={self.es_index}", f"--bind={self.bind}",
+                f"--tagline={self.tagline}", f"--lang={self.lang}"]
+
+        if self.auth0_audience:
+            args.append(f"--auth0-audience={self.auth0_audience}")
+        if self.auth0_domain:
+            args.append(f"--auth0-domain={self.auth0_domain}")
+        if self.auth0_client_id:
+            args.append(f"--auth0-client-id={self.auth0_client_id}")
+        if self.auth0_public_key_file:
+            args.append(f"--auth0-public-key-file={self.auth0_public_key_file}")
+        if self.es_insecure_ssl:
+            args.append(f"--es-insecure-ssl")
+        if self.auth:
+            args.append(f"--auth={self.auth}")
+        if self.tag_auth:
+            args.append(f"--tag-auth={self.tag_auth}")
+        if self.dev:
+            args.append(f"--dev")
+
+        args.extend(self.indices)
+
+        return args
+
+
+class IndexOptions(BaseModel):
+    path: str = None
+    threads: int = 1
+    es_url: str = "http://elasticsearch:9200"
+    es_insecure_ssl: bool = False
+    es_index: str = "sist2"
+    incremental_index: bool = True
+    script: str = ""
+    script_file: str = None
+    batch_size: int = 70
+
+    def __init__(self, **kwargs):
+        super().__init__(**kwargs)
+
+    def args(self):
+
+        args = ["index", self.path, f"--threads={self.threads}", f"--es-url={self.es_url}",
+                f"--es-index={self.es_index}", f"--batch-size={self.batch_size}"]
+
+        if self.script_file:
+            args.append(f"--script-file={self.script_file}")
+        if self.es_insecure_ssl:
+            args.append(f"--es-insecure-ssl")
+        if self.incremental_index:
+            args.append(f"--incremental-index")
+
+        return args
+
+
+ARCHIVE_SKIP = "skip"
+ARCHIVE_LIST = "list"
+ARCHIVE_SHALLOW = "shallow"
+ARCHIVE_RECURSE = "recurse"
+
+
+class ScanOptions(BaseModel):
+    path: str
+    threads: int = 1
+    thumbnail_quality: int = 50
+    thumbnail_size: int = 552
+    thumbnail_count: int = 1
+    content_size: int = 32768
+    depth: int = -1
+    archive: str = ARCHIVE_RECURSE
+    archive_passphrase: str = None
+    ocr_lang: str = None
+    ocr_images: bool = False
+    ocr_ebooks: bool = False
+    exclude: str = None
+    fast: bool = False
+    treemap_threshold: float = 0.0005
+    mem_buffer: int = 2000
+    read_subtitles: bool = False
+    fast_epub: bool = False
+    checksums: bool = False
+    incremental: bool = True
+    optimize_index: bool = False
+    output: str = None
+    name: str = None
+    rewrite_url: str = None
+    list_file: str = None
+
+    def __init__(self, **kwargs):
+        super().__init__(**kwargs)
+
+    def args(self):
+        args = ["scan", self.path, f"--threads={self.threads}", f"--thumbnail-quality={self.thumbnail_quality}",
+                f"--thumbnail-count={self.thumbnail_count}", f"--thumbnail-size={self.thumbnail_size}",
+                f"--content-size={self.content_size}", f"--output={self.output}", f"--depth={self.depth}",
+                f"--archive={self.archive}", f"--mem-buffer={self.mem_buffer}"]
+
+        if self.incremental:
+            args.append(f"--incremental")
+        if self.optimize_index:
+            args.append(f"--optimize-index")
+        if self.rewrite_url:
+            args.append(f"--rewrite-url={self.rewrite_url}")
+        if self.name:
+            args.append(f"--name={self.name}")
+        if self.archive_passphrase:
+            args.append(f"--archive-passphrase={self.archive_passphrase}")
+        if self.ocr_lang:
+            args.append(f"--ocr-lang={self.ocr_lang}")
+        if self.ocr_ebooks:
+            args.append(f"--ocr-ebooks")
+        if self.ocr_images:
+            args.append(f"--ocr-images")
+        if self.exclude:
+            args.append(f"--exclude={self.exclude}")
+        if self.fast:
+            args.append(f"--fast")
+        if self.treemap_threshold:
+            args.append(f"--treemap-threshold={self.treemap_threshold}")
+        if self.read_subtitles:
+            args.append(f"--read-subtitles")
+        if self.fast_epub:
+            args.append(f"--fast-epub")
+        if self.checksums:
+            args.append(f"--checksums")
+        if self.list_file:
+            args.append(f"--list_file={self.list_file}")
+
+        return args
+
+
+class Sist2Index:
+    def __init__(self, path):
+        self.path = path
+
+        with open(os.path.join(path, "descriptor.json")) as f:
+            self._descriptor = json.load(f)
+
+    def to_json(self):
+        return {
+            "path": self.path,
+            "version": self.version(),
+            "timestamp": self.timestamp(),
+            "name": self.name()
+        }
+
+    def version(self) -> Sist2Version:
+        return Sist2Version(self._descriptor["version"])
+
+    def timestamp(self) -> datetime:
+        return datetime.fromtimestamp(self._descriptor["timestamp"])
+
+    def name(self) -> str:
+        return self._descriptor["name"]
+
+
+class Sist2:
+
+    def __init__(self, bin_path: str, data_directory: str):
+        self._bin_path = bin_path
+        self._data_dir = data_directory
+
+    def index(self, options: IndexOptions, logs_cb):
+
+        if options.script:
+            with NamedTemporaryFile("w", prefix="sist2-admin", suffix=".painless", delete=False) as f:
+                f.write(options.script)
+            options.script_file = f.name
+        else:
+            options.script_file = None
+
+        args = [
+            self._bin_path,
+            *options.args(),
+            "--json-logs",
+            "--very-verbose"
+        ]
+        proc = Popen(args, stdout=PIPE, stderr=PIPE)
+
+        t_stderr = Thread(target=self._consume_logs_stderr, args=(logs_cb, proc))
+        t_stderr.start()
+
+        self._consume_logs_stdout(logs_cb, proc)
+
+        t_stderr.join()
+
+        return proc.returncode
+
+    def scan(self, options: ScanOptions, logs_cb, set_pid_cb):
+
+        if options.output is None:
+            options.output = os.path.join(
+                self._data_dir,
+                f"scan-{options.name.replace('/', '_')}-{datetime.now()}.sist2"
+            )
+
+        args = [
+            self._bin_path,
+            *options.args(),
+            "--json-logs",
+            "--very-verbose"
+        ]
+
+        logs_cb({"sist2-admin": f"Starting sist2 command with args {args}"})
+
+        proc = Popen(args, stdout=PIPE, stderr=PIPE)
+
+        set_pid_cb(proc.pid)
+
+        t_stderr = Thread(target=self._consume_logs_stderr, args=(logs_cb, proc))
+        t_stderr.start()
+
+        self._consume_logs_stdout(logs_cb, proc)
+
+        t_stderr.join()
+
+        return proc.returncode
+
+    @staticmethod
+    def _consume_logs_stderr(logs_cb, proc):
+        pipe_wrapper = TextIOWrapper(proc.stderr, encoding="utf8", errors="ignore")
+        try:
+            for line in pipe_wrapper:
+                if line.strip() == "":
+                    continue
+                logs_cb({"stderr": line})
+        finally:
+            proc.wait()
+            pipe_wrapper.close()
+
+    @staticmethod
+    def _consume_logs_stdout(logs_cb, proc):
+        pipe_wrapper = TextIOWrapper(proc.stdout, encoding="utf8", errors="ignore")
+        for line in pipe_wrapper:
+            try:
+                if line.strip() == "":
+                    continue
+                log_object = json.loads(line)
+                logs_cb(log_object)
+            except Exception as e:
+                try:
+                    logs_cb({"sist2-admin": f"Could not decode log line: {line}; {e}"})
+                except NameError:
+                    pass
+
+    def web(self, options: WebOptions, name: str):
+
+        if options.auth0_public_key:
+            with NamedTemporaryFile("w", prefix="sist2-admin", suffix=".txt", delete=False) as f:
+                f.write(options.auth0_public_key)
+            options.auth0_public_key_file = f.name
+        else:
+            options.auth0_public_key_file = None
+
+        args = [
+            self._bin_path,
+            *options.args()
+        ]
+
+        web_logger = logging.Logger(name=f"sist2-frontend-{name}")
+        web_logger.addHandler(FileHandler(os.path.join(LOG_FOLDER, f"frontend-{name}.log")))
+
+        def logs_cb(message):
+            web_logger.info(json.dumps(message))
+
+        logger.info(f"Starting frontend {' '.join(args)}")
+
+        proc = Popen(args, stdout=PIPE, stderr=PIPE)
+
+        t_stderr = Thread(target=self._consume_logs_stderr, args=(logs_cb, proc))
+        t_stderr.start()
+
+        t_stdout = Thread(target=self._consume_logs_stdout, args=(logs_cb, proc))
+        t_stdout.start()
+
+        return proc.pid

sist2-admin/sist2_admin/state.py

@@ -0,0 +1,79 @@
+from typing import Dict
+import shutil
+
+from hexlib.db import Table, PersistentState
+import pickle
+
+from tesseract import get_tesseract_langs
+
+RUNNING_FRONTENDS: Dict[str, int] = {}
+
+TESSERACT_LANGS = get_tesseract_langs()
+
+DB_SCHEMA_VERSION = "3"
+
+from pydantic import BaseModel
+
+
+def _serialize(item):
+    if isinstance(item, BaseModel):
+        return pickle.dumps(item)
+    if isinstance(item, bytes):
+        raise Exception("FIXME: bytes in PickleTable")
+    return item
+
+
+def _deserialize(item):
+    if isinstance(item, bytes):
+        return pickle.loads(item)
+    return item
+
+
+class PickleTable(Table):
+
+    def __getitem__(self, item):
+        row = super().__getitem__(item)
+        if row:
+            return dict((k, _deserialize(v)) for k, v in row.items())
+        return row
+
+    def __setitem__(self, key, value):
+        value = dict((k, _serialize(v)) for k, v in value.items())
+        super().__setitem__(key, value)
+
+    def __iter__(self):
+        for row in super().__iter__():
+            yield dict((k, _deserialize(v)) for k, v in row.items())
+
+    def sql(self, where_clause, *params):
+        for row in super().sql(where_clause, *params):
+            yield dict((k, _deserialize(v)) for k, v in row.items())
+
+
+def migrate_v1_to_v2(db: PersistentState):
+
+    shutil.copy(db.dbfile, db.dbfile + "-before-migrate-v2.bak")
+
+    # Frontends
+    db._table_factory = PickleTable
+    frontends = [row["frontend"] for row in db["frontends"]]
+    del db["frontends"]
+
+    db._table_factory = Table
+    for frontend in frontends:
+        db["frontends"][frontend.name] = frontend
+    list(db["frontends"])
+
+    # Jobs
+    db._table_factory = PickleTable
+    jobs = [row["job"] for row in db["jobs"]]
+    del db["jobs"]
+
+    db._table_factory = Table
+    for job in jobs:
+        db["jobs"][job.name] = job
+    list(db["jobs"])
+
+    db["sist2_admin"]["info"] = {
+        "version": "2"
+    }

sist2-admin/sist2_admin/tesseract.py

@@ -0,0 +1,14 @@
+import subprocess
+
+
+def get_tesseract_langs():
+
+    res = subprocess.check_output([
+        "tesseract",
+        "--list-langs"
+    ]).decode()
+
+    languages = res.split("\n")[1:]
+
+    return list(filter(lambda lang: lang and lang != "osd", languages))
+

sist2-admin/sist2_admin/web.py

@@ -0,0 +1,28 @@
+import os.path
+from typing import List
+
+from pydantic import BaseModel
+
+from sist2 import WebOptions
+
+
+class Sist2Frontend(BaseModel):
+    name: str
+    jobs: List[str]
+    web_options: WebOptions
+    running: bool = False
+
+    auto_start: bool = False
+    extra_query_args: str = ""
+    custom_url: str = None
+
+    def get_log_path(self, log_folder: str):
+        return os.path.join(log_folder, f"frontend-{self.name}.log")
+
+    @staticmethod
+    def create_default(name: str):
+        return Sist2Frontend(
+            name=name,
+            web_options=WebOptions(),
+            jobs=[]
+        )

sist2-vue/dist/index.html

@@ -1,3 +0,0 @@
-<!DOCTYPE html><html lang="en"><head><meta charset="utf-8"><meta http-equiv="X-UA-Compatible" content="IE=edge"><meta name="viewport" content="width=device-width,initial-scale=1,maximum-scale=1,user-scalable=no"><title>sist2</title><link href="css/chunk-vendors.css" rel="preload" as="style"><link href="css/index.css" rel="preload" as="style"><link href="js/chunk-vendors.js" rel="preload" as="script"><link href="js/index.js" rel="preload" as="script"><link href="css/chunk-vendors.css" rel="stylesheet"><link href="css/index.css" rel="stylesheet"></head><body><noscript><style>body {
-            height: initial;
-        }</style><div style="text-align: center; margin-top: 100px"><strong>We're sorry but sist2 doesn't work properly without JavaScript enabled. Please enable it to continue.</strong><br><strong>Nous sommes désolés mais sist2 ne fonctionne pas correctement si JavaScript est activé. Veuillez l'activer pour continuer.</strong></div></noscript><div id="app"></div><script src="js/chunk-vendors.js"></script><script src="js/index.js"></script></body></html>

sist2-vue/package.json

@@ -7,14 +7,16 @@
     "build": "vue-cli-service build --mode production"
   },
   "dependencies": {
+    "@auth0/auth0-spa-js": "^2.0.2",
     "@egjs/vue-infinitegrid": "3.3.0",
+    "@tensorflow/tfjs": "^4.4.0",
     "axios": "^0.25.0",
     "bootstrap-vue": "^2.21.2",
     "core-js": "^3.6.5",
-    "d3": "^5.16.0",
+    "d3": "^7.8.4",
     "date-fns": "^2.21.3",
     "dom-to-image": "^2.6.0",
-    "fslightbox-vue": "file:../../../mnt/Hatchery/main/projects/sist2/fslightbox-vue-pro-1.3.1.tgz",
+    "fslightbox-vue": "fslightbox-vue.tgz",
     "nouislider": "^15.2.0",
     "underscore": "^1.13.1",
     "vue": "^2.6.12",
@@ -26,12 +28,12 @@
     "vuex": "^3.4.0"
   },
   "devDependencies": {
-    "@babel/polyfill": "^7.11.5",
-    "@vue/cli-plugin-babel": "~4.5.0",
-    "@vue/cli-plugin-router": "~4.5.0",
-    "@vue/cli-plugin-typescript": "~4.5.0",
-    "@vue/cli-plugin-vuex": "~4.5.0",
-    "@vue/cli-service": "~4.5.0",
+    "@babel/polyfill": "^7.12.1",
+    "@vue/cli-plugin-babel": "~5.0.8",
+    "@vue/cli-plugin-router": "~5.0.8",
+    "@vue/cli-plugin-typescript": "^5.0.8",
+    "@vue/cli-plugin-vuex": "~5.0.8",
+    "@vue/cli-service": "^5.0.8",
     "@vue/test-utils": "^1.0.3",
     "bootstrap": "^4.5.2",
     "inspire-tree": "^4.3.1",

sist2-vue/public/index.html

@@ -19,12 +19,6 @@
             We're sorry but <%= htmlWebpackPlugin.options.title %> doesn't work properly without JavaScript enabled.
             Please enable it to continue.
         </strong>
-        <br/>
-        <strong>
-            Nous sommes désolés mais <%= htmlWebpackPlugin.options.title %> ne fonctionne pas correctement
-            si JavaScript est activé.
-            Veuillez l'activer pour continuer.
-        </strong>
     </div>
 </noscript>
 <div id="app"></div>

sist2-vue/src/App.vue

@@ -1,19 +1,36 @@
 <template>
-  <div id="app" :class="getClass()">
+    <div id="app" :class="getClass()" v-if="!authLoading">
         <NavBar></NavBar>
         <router-view v-if="!configLoading"/>
     </div>
+    <div class="loading-page" v-else>
+        <div class="loading-spinners">
+            <b-spinner type="grow" variant="primary"></b-spinner>
+            <b-spinner type="grow" variant="primary"></b-spinner>
+            <b-spinner type="grow" variant="primary"></b-spinner>
+        </div>
+        <div class="loading-text">
+            Loading • Chargement • 装载 • Wird geladen • Ładowanie
+        </div>
+    </div>
 </template>
 
 <script>
 import NavBar from "@/components/NavBar";
-import {mapGetters} from "vuex";
+import {mapActions, mapGetters, mapMutations} from "vuex";
+import Sist2Api from "@/Sist2Api";
+import ModelsRepo from "@/ml/modelsRepo";
+import {setupAuth0} from "@/main";
+import Sist2ElasticsearchQuery from "@/Sist2ElasticsearchQuery";
+import Sist2SqliteQuery from "@/Sist2SqliteQuery";
 
 export default {
     components: {NavBar},
     data() {
         return {
-      configLoading: false
+            configLoading: false,
+            authLoading: true,
+            sist2InfoLoading: true
         }
     },
     computed: {
@@ -22,6 +39,17 @@ export default {
     mounted() {
         this.$store.dispatch("loadConfiguration").then(() => {
             this.$root.$i18n.locale = this.$store.state.optLang;
+            ModelsRepo.init(this.$store.getters.mlRepositoryList).catch(err => {
+                this.$bvToast.toast(
+                    this.$t("ml.repoFetchError"),
+                    {
+                        title: this.$t("ml.repoFetchErrorTitle"),
+                        noAutoHide: true,
+                        toaster: "b-toaster-bottom-right",
+                        headerClass: "toast-header-warning",
+                        bodyClass: "toast-body-warning",
+                    });
+            });
         });
 
         this.$store.subscribe((mutation) => {
@@ -30,9 +58,50 @@ export default {
                 this.configLoading = true;
                 window.setTimeout(() => this.configLoading = false, 10);
             }
+
+            if (mutation.type === "setAuth0Token") {
+                this.authLoading = false;
+            }
+        });
+
+        Sist2Api.getSist2Info().then(data => {
+
+            if (data.auth0Enabled) {
+                this.authLoading = true;
+                setupAuth0(data.auth0Domain, data.auth0ClientId, data.auth0Audience)
+
+                this.$auth.$watch("loading", loading => {
+                    if (loading === false) {
+
+                        if (!this.$auth.isAuthenticated) {
+                            this.$auth.loginWithRedirect();
+                            return;
+                        }
+
+                        // Remove "code" param
+                        window.history.replaceState({}, "", "/" + window.location.hash);
+
+                        this.$store.dispatch("loadAuth0Token");
+                    }
+                });
+            } else {
+                this.authLoading = false;
+            }
+
+            this.setSist2Info(data);
+            this.setIndices(data.indices)
+
+            if (Sist2Api.backend() === "sqlite") {
+                Sist2Api.init(Sist2SqliteQuery.searchQuery);
+                this.$store.commit("setUiSqliteMode", true);
+            } else {
+                Sist2Api.init(Sist2ElasticsearchQuery.searchQuery);
+            }
         });
     },
     methods: {
+        ...mapActions(["setSist2Info",]),
+        ...mapMutations(["setIndices",]),
         getClass() {
             return {
                 "theme-light": this.optTheme === "light",
@@ -314,4 +383,22 @@ mark {
 .pointer {
     cursor: pointer;
 }
+
+.loading-page {
+    display: flex;
+    justify-content: center;
+    align-items: center;
+    flex-direction: column;
+    height: 100%;
+    gap: 15px
+}
+
+.loading-spinners {
+    display: flex;
+    gap: 10px;
+}
+
+.loading-text {
+    text-align: center;
+}
 </style>

sist2-vue/src/Sist2Api.ts

@@ -1,5 +1,7 @@
 import axios from "axios";
 import {ext, strUnescape, lum} from "./util";
+import Sist2Query from "@/Sist2ElasticsearchQuery";
+import store from "@/store";
 
 export interface EsTag {
     id: string
@@ -61,6 +63,7 @@ export interface EsHit {
         isAudio: boolean
         hasThumbnail: boolean
         hasVidPreview: boolean
+        imageAspectRatio: number
         /** Number of thumbnails available */
         tnNum: number
     }
@@ -98,12 +101,22 @@ export interface EsResult {
 
 class Sist2Api {
 
-    private baseUrl: string
+    private readonly baseUrl: string
+    private sist2Info: any
+    private queryfunc: () => EsResult;
 
     constructor(baseUrl: string) {
         this.baseUrl = baseUrl;
     }
 
+    init(queryFunc: () => EsResult) {
+        this.queryfunc = queryFunc;
+    }
+
+    backend() {
+        return this.sist2Info.searchBackend;
+    }
+
     getSist2Info(): Promise<any> {
         return axios.get(`${this.baseUrl}i`).then(resp => {
             const indices = resp.data.indices as Index[];
@@ -118,6 +131,8 @@ class Sist2Api {
                 } as Index;
             });
 
+            this.sist2Info = resp.data;
+
             return resp.data;
         })
     }
@@ -155,6 +170,9 @@ class Sist2Api {
                     && hit._source.videoc !== "raw" && hit._source.videoc !== "ppm") {
                     hit._props.isPlayableImage = true;
                 }
+                if ("width" in hit._source && "height" in hit._source) {
+                    hit._props.imageAspectRatio = hit._source.width / hit._source.height;
+                }
                 break;
             case "video":
                 if ("videoc" in hit._source) {
@@ -187,30 +205,6 @@ class Sist2Api {
     setHitTags(hit: EsHit): void {
         const tags = [] as Tag[];
 
-        const mimeCategory = hit._source.mime == null ? null : hit._source.mime.split("/")[0];
-
-        switch (mimeCategory) {
-            case "image":
-            case "video":
-                if ("videoc" in hit._source && hit._source.videoc) {
-                    tags.push({
-                        style: "video",
-                        text: hit._source.videoc.replace(" ", ""),
-                        userTag: false
-                    } as Tag);
-                }
-                break
-            case "audio":
-                if ("audioc" in hit._source && hit._source.audioc) {
-                    tags.push({
-                        style: "audio",
-                        text: hit._source.audioc,
-                        userTag: false
-                    } as Tag);
-                }
-                break;
-        }
-
         // User tags
         if ("tag" in hit._source) {
             hit._source.tag.forEach(tag => {
@@ -239,6 +233,14 @@ class Sist2Api {
         } as Tag;
     }
 
+    search(): Promise<EsResult> {
+        if (this.backend() == "sqlite") {
+            return this.ftsQuery(this.queryfunc())
+        } else {
+            return this.esQuery(this.queryfunc());
+        }
+    }
+
     esQuery(query: any): Promise<EsResult> {
         return axios.post(`${this.baseUrl}es`, query).then(resp => {
             const res = resp.data as EsResult;
@@ -257,7 +259,30 @@ class Sist2Api {
         });
     }
 
-    getMimeTypes(query = undefined) {
+    ftsQuery(query: any): Promise<EsResult> {
+        return axios.post(`${this.baseUrl}fts/search`, query).then(resp => {
+            const res = resp.data as any;
+
+            if (res.hits.hits) {
+                res.hits.hits.forEach(hit => {
+                    hit["_source"]["name"] = strUnescape(hit["_source"]["name"]);
+                    hit["_source"]["path"] = strUnescape(hit["_source"]["path"]);
+
+                    this.setHitProps(hit);
+                    this.setHitTags(hit);
+
+                    if ("highlight" in hit) {
+                        hit["highlight"]["name"] = [hit["highlight"]["name"]];
+                        hit["highlight"]["content"] = [hit["highlight"]["content"]];
+                    }
+                });
+            }
+
+            return res;
+        });
+    }
+
+    private getMimeTypesEs(query) {
         const AGGS = {
             mimeTypes: {
                 terms: {
@@ -278,19 +303,42 @@ class Sist2Api {
         }
 
         return this.esQuery(query).then(resp => {
-            const mimeMap: any[] = [];
-            const buckets = resp["aggregations"]["mimeTypes"]["buckets"];
+            return resp["aggregations"]["mimeTypes"]["buckets"].map(bucket => ({
+                mime: bucket.key,
+                count: bucket.doc_count
+            }));
 
-            buckets.sort((a: any, b: any) => a.key > b.key).forEach((bucket: any) => {
-                const tmp = bucket["key"].split("/");
+        });
+    }
+
+    private getMimeTypesSqlite(): Promise<[{ mime: string, count: number }]> {
+        return axios.get(`${this.baseUrl}fts/mimetypes`)
+            .then(resp => {
+                return resp.data;
+            });
+    }
+
+    async getMimeTypes(query = undefined) {
+        let buckets;
+
+        if (this.backend() == "sqlite") {
+            buckets = await this.getMimeTypesSqlite();
+        } else {
+            buckets = await this.getMimeTypesEs(query);
+        }
+
+        const mimeMap: any[] = [];
+
+        buckets.sort((a: any, b: any) => a.mime > b.mime).forEach((bucket: any) => {
+            const tmp = bucket.mime.split("/");
             const category = tmp[0];
             const mime = tmp[1];
 
             let category_exists = false;
 
             const child = {
-                    "id": bucket["key"],
-                    "text": `${mime} (${bucket["doc_count"]})`
+                "id": bucket.mime,
+                "text": `${mime} (${bucket.count})`
             };
 
             mimeMap.forEach(node => {
@@ -313,13 +361,12 @@ class Sist2Api {
         mimeMap.sort((a, b) => a.id.localeCompare(b.id))
 
         return {buckets, mimeMap};
-        });
     }
 
     _createEsTag(tag: string, count: number): EsTag {
         const tokens = tag.split(".");
 
-        if (/.*\.#[0-9a-f]{6}/.test(tag)) {
+        if (/.*\.#[0-9a-fA-F]{6}/.test(tag)) {
             return {
                 id: tokens.slice(0, -1).join("."),
                 color: tokens.pop(),
@@ -336,25 +383,42 @@ class Sist2Api {
         };
     }
 
-    getTags() {
+    private getTagsEs() {
         return this.esQuery({
             aggs: {
                 tags: {
                     terms: {
                         field: "tag",
-                        size: 10000
+                        size: 65535
                     }
                 }
             },
             size: 0,
         }).then(resp => {
-            const seen = new Set();
-
-            const tags = resp["aggregations"]["tags"]["buckets"]
+            return resp["aggregations"]["tags"]["buckets"]
                 .sort((a: any, b: any) => a["key"].localeCompare(b["key"]))
                 .map((bucket: any) => this._createEsTag(bucket["key"], bucket["doc_count"]));
+        });
+    }
+
+    private getTagsSqlite() {
+        return axios.get(`${this.baseUrl}/fts/tags`)
+            .then(resp => {
+                return resp.data.map(tag => this._createEsTag(tag.tag, tag.count))
+            });
+    }
+
+    async getTags(): Promise<EsTag[]> {
+        let tags;
+        if (this.backend() == "sqlite") {
+            tags = await this.getTagsSqlite();
+        } else {
+            tags = await this.getTagsEs();
+        }
 
         // Remove duplicates (same tag with different color)
+        const seen = new Set();
+
         return tags.filter((t: EsTag) => {
             if (seen.has(t.id)) {
                 return false;
@@ -362,7 +426,6 @@ class Sist2Api {
             seen.add(t.id);
             return true;
         });
-        });
     }
 
     saveTag(tag: string, hit: EsHit) {
@@ -381,20 +444,263 @@ class Sist2Api {
         });
     }
 
-    getTreemapCsvUrl(indexId: string) {
-        return `${this.baseUrl}s/${indexId}/1`;
+    searchPaths(indexId, minDepth, maxDepth, prefix = null) {
+        if (this.backend() == "sqlite") {
+            return this.searchPathsSqlite(indexId, minDepth, minDepth, prefix);
+        } else {
+            return this.searchPathsEs(indexId, minDepth, maxDepth, prefix);
+        }
     }
 
-    getMimeCsvUrl(indexId: string) {
-        return `${this.baseUrl}s/${indexId}/2`;
+    private searchPathsSqlite(indexId, minDepth, maxDepth, prefix) {
+        return axios.post(`${this.baseUrl}fts/paths`, {
+            indexId, minDepth, maxDepth, prefix
+        }).then(resp => {
+            return resp.data;
+        });
     }
 
-    getSizeCsv(indexId: string) {
-        return `${this.baseUrl}s/${indexId}/3`;
+    private searchPathsEs(indexId, minDepth, maxDepth, prefix): Promise<[{ path: string, count: number }]> {
+
+        const query = {
+            query: {
+                bool: {
+                    filter: [
+                        {term: {index: indexId}},
+                        {range: {_depth: {gte: minDepth, lte: maxDepth}}},
+                    ]
+                }
+            },
+            aggs: {
+                paths: {
+                    terms: {
+                        field: "path",
+                        size: 10000
+                    }
+                }
+            },
+            size: 0
+        };
+
+        if (prefix != null) {
+            query["query"]["bool"]["must"] = {
+                prefix: {
+                    path: prefix,
+                }
+            };
         }
 
-    getDateCsv(indexId: string) {
-        return `${this.baseUrl}s/${indexId}/4`;
+        return this.esQuery(query).then(resp => {
+            const buckets = resp["aggregations"]["paths"]["buckets"];
+
+            if (!buckets) {
+                return [];
+            }
+
+            return buckets
+                .map(bucket => ({
+                    path: bucket.key,
+                    count: bucket.doc_count
+                }));
+        });
+    }
+
+    private getDateRangeSqlite() {
+        return axios.get(`${this.baseUrl}fts/dateRange`)
+            .then(resp => ({
+                min: resp.data.dateMin,
+                max: resp.data.dateMax,
+            }));
+    }
+
+    getDateRange(): Promise<{ min: number, max: number }> {
+        if (this.backend() == "sqlite") {
+            return this.getDateRangeSqlite();
+        } else {
+            return this.getDateRangeEs();
+        }
+    }
+
+    private getDateRangeEs() {
+        return this.esQuery({
+            // TODO: filter current selected indices
+            aggs: {
+                dateMin: {min: {field: "mtime"}},
+                dateMax: {max: {field: "mtime"}},
+            },
+            size: 0
+        }).then(res => {
+            const range = {
+                min: res.aggregations.dateMin.value,
+                max: res.aggregations.dateMax.value,
+            }
+
+            if (range.min == null) {
+                range.min = 0;
+                range.max = 1;
+            } else if (range.min == range.max) {
+                range.max += 1;
+            }
+
+            return range;
+        });
+    }
+
+    private getPathSuggestionsSqlite(text: string) {
+        return axios.post(`${this.baseUrl}fts/paths`, {
+            prefix: text,
+            minDepth: 1,
+            maxDepth: 10000
+        }).then(resp => {
+            return resp.data.map(bucket => bucket.path);
+        })
+    }
+
+    private getPathSuggestionsEs(text) {
+        return this.esQuery({
+            suggest: {
+                path: {
+                    prefix: text,
+                    completion: {
+                        field: "suggest-path",
+                        skip_duplicates: true,
+                        size: 10000
+                    }
+                }
+            }
+        }).then(resp => {
+            return resp["suggest"]["path"][0]["options"]
+                .map(opt => opt["_source"]["path"]);
+        });
+    }
+
+    getPathSuggestions(text: string): Promise<string[]> {
+        if (this.backend() == "sqlite") {
+            return this.getPathSuggestionsSqlite(text);
+        } else {
+            return this.getPathSuggestionsEs(text)
+        }
+    }
+
+    getTreemapStat(indexId: string) {
+        return `${this.baseUrl}s/${indexId}/TMAP`;
+    }
+
+    getMimeStat(indexId: string) {
+        return `${this.baseUrl}s/${indexId}/MAGG`;
+    }
+
+    getSizeStat(indexId: string) {
+        return `${this.baseUrl}s/${indexId}/SAGG`;
+    }
+
+    getDateStat(indexId: string) {
+        return `${this.baseUrl}s/${indexId}/DAGG`;
+    }
+
+    private getDocumentEs(docId: string, highlight: boolean, fuzzy: boolean) {
+        const query = Sist2Query.searchQuery();
+
+        if (highlight) {
+            const fields = fuzzy
+                ? {"content.nGram": {}}
+                : {content: {}};
+
+            query.highlight = {
+                pre_tags: ["<mark>"],
+                post_tags: ["</mark>"],
+                number_of_fragments: 0,
+                fields,
+            };
+
+            if (!store.state.sist2Info.esVersionLegacy) {
+                query.highlight.max_analyzed_offset = 999_999;
+            }
+        }
+
+        if ("function_score" in query.query) {
+            query.query = query.query.function_score.query;
+        }
+
+        if (!("must" in query.query.bool)) {
+            query.query.bool.must = [];
+        } else if (!Array.isArray(query.query.bool.must)) {
+            query.query.bool.must = [query.query.bool.must];
+        }
+
+        query.query.bool.must.push({match: {_id: docId}});
+
+        delete query["sort"];
+        delete query["aggs"];
+        delete query["search_after"];
+        delete query.query["function_score"];
+
+        query._source = {
+            includes: ["content", "name", "path", "extension"]
+        }
+
+        query.size = 1;
+
+        return this.esQuery(query).then(resp => {
+            if (resp.hits.hits.length === 1) {
+                return resp.hits.hits[0];
+            }
+            return null;
+        });
+    }
+
+    private getDocumentSqlite(docId: string): Promise<EsHit> {
+        return axios.get(`${this.baseUrl}/fts/d/${docId}`)
+            .then(resp => ({
+                _source: resp.data
+            } as EsHit));
+    }
+
+    getDocument(docId: string, highlight: boolean, fuzzy: boolean): Promise<EsHit | null> {
+        if (this.backend() == "sqlite") {
+            return this.getDocumentSqlite(docId);
+        } else {
+            return this.getDocumentEs(docId, highlight, fuzzy);
+        }
+    }
+
+    getTagSuggestions(prefix: string): Promise<string[]> {
+        if (this.backend() == "sqlite") {
+            return this.getTagSuggestionsSqlite(prefix);
+        } else {
+            return this.getTagSuggestionsEs(prefix);
+        }
+    }
+
+    private getTagSuggestionsSqlite(prefix): Promise<string[]> {
+        return axios.post(`${this.baseUrl}/fts/suggestTags`, prefix)
+            .then(resp => (resp.data));
+    }
+
+    private getTagSuggestionsEs(prefix): Promise<string[]> {
+        return this.esQuery({
+            suggest: {
+                tag: {
+                    prefix: prefix,
+                    completion: {
+                        field: "suggest-tag",
+                        skip_duplicates: true,
+                        size: 10000
+                    }
+                }
+            }
+        }).then(resp => {
+            const result = [];
+            resp["suggest"]["tag"][0]["options"].map(opt => opt["_source"]["tag"]).forEach(tags => {
+                tags.forEach(tag => {
+                    const t = tag.slice(0, -8);
+                    if (!result.find(x => x.slice(0, -8) === t)) {
+                        result.push(tag);
+                    }
+                });
+            });
+            return result;
+        });
     }
 }
 

sist2-vue/src/Sist2ElasticsearchQuery.ts

@@ -60,14 +60,7 @@ const SORT_MODES = {
     }
 } as any;
 
-interface SortMode {
-    text: string
-    mode: any[]
-    key: (hit: EsHit) => any
-}
-
-
-class Sist2Query {
+class Sist2ElasticsearchQuery {
 
     searchQuery(blankSearch: boolean = false): any {
 
@@ -177,14 +170,16 @@ class Sist2Query {
                 }
             },
             sort: SORT_MODES[getters.sortMode].mode,
-            aggs:
-                {
-                    total_size: {"sum": {"field": "size"}},
-                    total_count: {"value_count": {"field": "size"}}
-                },
             size: size,
         } as any;
 
+        if (!after) {
+            q.aggs = {
+                total_size: {"sum": {"field": "size"}},
+                total_count: {"value_count": {"field": "size"}}
+            };
+        }
+
         if (!empty && !blankSearch) {
             q.query.bool.must = query;
         }
@@ -249,4 +244,5 @@ class Sist2Query {
     }
 }
 
-export default new Sist2Query();
+
+export default new Sist2ElasticsearchQuery();

sist2-vue/src/Sist2SqliteQuery.ts

@@ -0,0 +1,111 @@
+import store from "./store";
+import {EsHit, Index} from "@/Sist2Api";
+
+const SORT_MODES = {
+    score: {
+        "sort": "score",
+    },
+    random: {
+        "sort": "random"
+    },
+    dateAsc: {
+        "sort": "mtime"
+    },
+    dateDesc: {
+        "sort": "mtime",
+        "sortAsc": false
+    },
+    sizeAsc: {
+        "sort": "size",
+    },
+    sizeDesc: {
+        "sort": "size",
+        "sortAsc": false
+    },
+    nameAsc: {
+        "sort": "name",
+    },
+    nameDesc: {
+        "sort": "name",
+        "sortAsc": false
+    }
+} as any;
+
+interface SortMode {
+    text: string
+    mode: any[]
+    key: (hit: EsHit) => any
+}
+
+
+class Sist2ElasticsearchQuery {
+
+    searchQuery(): any {
+
+        const getters = store.getters;
+
+        const searchText = getters.searchText;
+        const pathText = getters.pathText;
+        const sizeMin = getters.sizeMin;
+        const sizeMax = getters.sizeMax;
+        const dateMin = getters.dateMin;
+        const dateMax = getters.dateMax;
+        const size = getters.size;
+        const after = getters.lastDoc;
+        const selectedIndexIds = getters.selectedIndices.map((idx: Index) => idx.id)
+        const selectedMimeTypes = getters.selectedMimeTypes;
+        const selectedTags = getters.selectedTags;
+
+        const q = {
+            "pageSize": size
+        }
+
+        Object.assign(q, SORT_MODES[getters.sortMode]);
+
+        if (!after) {
+            q["fetchAggregations"] = true;
+        }
+        if (searchText) {
+            q["query"] = searchText;
+        }
+        if (pathText) {
+            q["path"] = pathText.endsWith("/") ? pathText.slice(0, -1) : pathText;
+        }
+        if (sizeMin) {
+            q["sizeMin"] = sizeMin;
+        }
+        if (sizeMax) {
+            q["sizeMax"] = sizeMax;
+        }
+        if (dateMin) {
+            q["dateMin"] = dateMin;
+        }
+        if (dateMax) {
+            q["dateMax"] = dateMax;
+        }
+        if (after) {
+            q["after"] = after.sort;
+        }
+        if (selectedIndexIds.length > 0) {
+            q["indexIds"] = selectedIndexIds;
+        }
+        if (selectedMimeTypes.length > 0) {
+            q["mimeTypes"] = selectedMimeTypes;
+        }
+        if (selectedTags.length > 0) {
+            q["tags"] = selectedTags
+        }
+        if (getters.sortMode == "random") {
+            q["seed"] = getters.seed;
+        }
+        if (getters.optHighlight) {
+            q["highlight"] = true;
+            q["highlightContextSize"] = Number(getters.optFragmentSize);
+        }
+
+        return q;
+    }
+}
+
+
+export default new Sist2ElasticsearchQuery();

sist2-vue/src/components/AnalyzedContentSpan.vue

@@ -0,0 +1,21 @@
+<template>
+    <span :style="getStyle()">{{span.text}}</span>
+</template>
+
+<script>
+
+
+import ModelsRepo from "@/ml/modelsRepo";
+
+export default {
+    name: "AnalyzedContentSpan",
+    props: ["span", "text"],
+    methods: {
+        getStyle() {
+            return ModelsRepo.data[this.$store.getters.mlModel.name].labelStyles[this.span.label];
+        }
+    }
+}
+</script>
+
+<style scoped></style>

sist2-vue/src/components/AnalyzedContentSpanContainer.vue

@@ -0,0 +1,75 @@
+<template>
+    <div>
+        <b-card class="mb-2">
+            <AnalyzedContentSpan v-for="span of legend" :key="span.id" :span="span"
+                                 class="mr-2"></AnalyzedContentSpan>
+        </b-card>
+        <div class="content-div">
+            <AnalyzedContentSpan v-for="span of mergedSpans" :key="span.id" :span="span"></AnalyzedContentSpan>
+        </div>
+    </div>
+</template>
+
+<script>
+
+
+import AnalyzedContentSpan from "@/components/AnalyzedContentSpan.vue";
+import ModelsRepo from "@/ml/modelsRepo";
+
+export default {
+    name: "AnalyzedContentSpanContainer",
+    components: {AnalyzedContentSpan},
+    props: ["spans", "text"],
+    computed: {
+        legend() {
+            return Object.entries(ModelsRepo.data[this.$store.state.mlModel.name].legend)
+                .map(([label, name]) => ({
+                    text: name,
+                    id: label,
+                    label: label
+                }));
+        },
+        mergedSpans() {
+            const spans = this.spans;
+
+            const merged = [];
+
+            let lastLabel = null;
+            let fixSpace = false;
+            for (let i = 0; i < spans.length; i++) {
+
+                if (spans[i].label !== lastLabel) {
+                    let start = spans[i].wordIndex;
+                    const nextSpan = spans.slice(i + 1).find(s => s.label !== spans[i].label)
+                    let end = nextSpan ? nextSpan.wordIndex : undefined;
+
+                    if (end !== undefined && this.text[end - 1] === " ") {
+                        end -= 1;
+                        fixSpace = true;
+                    }
+
+                    merged.push({
+                        text: this.text.slice(start, end),
+                        label: spans[i].label,
+                        id: spans[i].wordIndex
+                    });
+
+                    if (fixSpace) {
+                        merged.push({
+                            text: " ",
+                            label: "O",
+                            id: end
+                        });
+                        fixSpace = false;
+                    }
+                    lastLabel = spans[i].label;
+                }
+            }
+
+            return merged;
+        },
+    },
+}
+</script>
+
+<style scoped></style>

sist2-vue/src/components/D3DateHistogram.vue

@@ -120,7 +120,7 @@ export default {
     update(indexId) {
       const svg = d3.select("#date-histogram");
 
-      d3.csv(Sist2Api.getDateCsv(indexId)).then(tabularData => {
+      d3.json(Sist2Api.getDateStat(indexId)).then(tabularData => {
         dateHistogram(tabularData.slice(), svg, this.$t("d3.dateHistogram"));
       });
     }

sist2-vue/src/components/D3MimeBarCount.vue

@@ -91,7 +91,7 @@ export default {
       const mimeSvgCount = d3.select("#agg-mime-count");
       const fillOpacity = this.$store.state.optTheme === "black" ? 0.9 : 0.6;
 
-      d3.csv(Sist2Api.getMimeCsvUrl(indexId)).then(tabularData => {
+      d3.json(Sist2Api.getMimeStat(indexId)).then(tabularData => {
         mimeBarCount(tabularData.slice(), mimeSvgCount, fillOpacity, this.$t("d3.mimeCount"));
       });
     }

sist2-vue/src/components/D3MimeBarSize.vue

@@ -90,7 +90,7 @@ export default {
       const mimeSvgSize = d3.select("#agg-mime-size");
       const fillOpacity = this.$store.state.optTheme === "black" ? 0.9 : 0.6;
 
-      d3.csv(Sist2Api.getMimeCsvUrl(indexId)).then(tabularData => {
+      d3.json(Sist2Api.getMimeStat(indexId)).then(tabularData => {
         mimeBarSize(tabularData.slice(), mimeSvgSize, fillOpacity, this.$t("d3.mimeSize"));
       });
     }

sist2-vue/src/components/D3SizeHistogram.vue

@@ -117,7 +117,7 @@ export default {
     update(indexId) {
       const svg = d3.select("#size-histogram");
 
-      d3.csv(Sist2Api.getSizeCsv(indexId)).then(tabularData => {
+      d3.json(Sist2Api.getSizeStat(indexId)).then(tabularData => {
         sizeHistogram(tabularData.slice(), svg, this.$t("d3.sizeHistogram"));
       });
     }

sist2-vue/src/components/D3Treemap.vue

@@ -240,7 +240,7 @@ export default {
           .style("overflow", "visible")
           .style("font", "10px sans-serif");
 
-      d3.csv(Sist2Api.getTreemapCsvUrl(indexId)).then(tabularData => {
+      d3.json(Sist2Api.getTreemapStat(indexId)).then(tabularData => {
         tabularData.forEach(row => {
           row.taxonomy = row.path.split("/");
           row.size = Number(row.size);

sist2-vue/src/components/DebugInfo.vue

@@ -1,14 +1,18 @@
 <template>
-  <b-card class="mb-4 mt-4">
-    <b-card-title><DebugIcon class="mr-1"></DebugIcon>{{ $t("debug") }}</b-card-title>
+    <b-card v-if="$store.state.sist2Info.showDebugInfo" class="mb-4 mt-4">
+        <b-card-title>
+            <DebugIcon class="mr-1"></DebugIcon>
+            {{ $t("debug") }}
+        </b-card-title>
         <p v-html="$t('debugDescription')"></p>
 
         <b-card-body>
 
             <b-table :items="tableItems" small borderless responsive="md" thead-class="hidden" class="mb-0"></b-table>
 
-      <hr />
-      <IndexDebugInfo v-for="idx of $store.state.sist2Info.indices" :key="idx.id" :index="idx" class="mt-2"></IndexDebugInfo>
+            <hr/>
+            <IndexDebugInfo v-for="idx of $store.state.sist2Info.indices" :key="idx.id" :index="idx"
+                            class="mt-2"></IndexDebugInfo>
         </b-card-body>
     </b-card>
 </template>
@@ -16,13 +20,17 @@
 <script>
 import IndexDebugInfo from "@/components/IndexDebugInfo";
 import DebugIcon from "@/components/icons/DebugIcon";
+import {mapGetters} from "vuex";
 
 export default {
     name: "DebugInfo.vue",
     components: {DebugIcon, IndexDebugInfo},
     computed: {
+        ...mapGetters([
+            "uiSqliteMode",
+        ]),
         tableItems() {
-      return [
+            const items = [
                 {key: "version", value: this.$store.state.sist2Info.version},
                 {key: "platform", value: this.$store.state.sist2Info.platform},
                 {key: "debugBinary", value: this.$store.state.sist2Info.debug},
@@ -31,10 +39,17 @@ export default {
                 {key: "tagline", value: this.$store.state.sist2Info.tagline},
                 {key: "dev", value: this.$store.state.sist2Info.dev},
                 {key: "mongooseVersion", value: this.$store.state.sist2Info.mongooseVersion},
+            ];
+
+            if (!this.uiSqliteMode) {
+                items.push(
                     {key: "esVersion", value: this.$store.state.sist2Info.esVersion},
                     {key: "esVersionSupported", value: this.$store.state.sist2Info.esVersionSupported},
-        {key: "esVersionLegacy", value: this.$store.state.sist2Info.esVersionLegacy},
-      ]
+                    {key: "esVersionLegacy", value: this.$store.state.sist2Info.esVersionLegacy}
+                );
+            }
+
+            return items;
         }
     }
 }

sist2-vue/src/components/DocCard.vue

@@ -16,7 +16,7 @@
             <!-- Audio player-->
             <audio v-if="doc._props.isAudio" ref="audio" preload="none" class="audio-fit fit" controls
                    :type="doc._source.mime"
-             :src="`f/${doc._id}`"
+                   :src="`f/${doc._source.index}/${doc._id}`"
                    @play="onAudioPlay()"></audio>
 
             <b-card-body class="padding-03">
@@ -27,6 +27,11 @@
                     <DocFileTitle :doc="doc"></DocFileTitle>
                 </div>
 
+                <!-- Featured line -->
+                <div style="display: flex">
+                    <FeaturedFieldsLine :doc="doc"></FeaturedFieldsLine>
+                </div>
+
                 <!-- Tags -->
                 <div class="card-text">
                     <TagContainer :hit="doc"></TagContainer>
@@ -43,10 +48,11 @@ import DocFileTitle from "@/components/DocFileTitle.vue";
 import DocInfoModal from "@/components/DocInfoModal.vue";
 import ContentDiv from "@/components/ContentDiv.vue";
 import FullThumbnail from "@/components/FullThumbnail";
+import FeaturedFieldsLine from "@/components/FeaturedFieldsLine";
 
 
 export default {
-  components: {FullThumbnail, ContentDiv, DocInfoModal, DocFileTitle, TagContainer},
+    components: {FeaturedFieldsLine, FullThumbnail, ContentDiv, DocInfoModal, DocFileTitle, TagContainer},
     props: ["doc", "width"],
     data() {
         return {
@@ -70,7 +76,7 @@ export default {
             await this.$store.dispatch("showLightbox");
         },
         onAudioPlay() {
-      document.getElementsByTagName("audio").forEach((el) => {
+            Array.prototype.slice.call(document.getElementsByTagName("audio")).forEach((el) => {
                 if (el !== this.$refs["audio"]) {
                     el.pause();
                 }

sist2-vue/src/components/DocFileTitle.vue

@@ -1,5 +1,5 @@
 <template>
-  <a :href="`f/${doc._id}`" class="file-title-anchor" target="_blank">
+  <a :href="`f/${doc._source.index}/${doc._id}`" class="file-title-anchor" target="_blank">
     <div class="file-title" :title="doc._source.path + '/' + doc._source.name + ext(doc)"
          v-html="fileName() + ext(doc)"></div>
   </a>

sist2-vue/src/components/DocListItem.vue

@@ -17,7 +17,7 @@
           </div>
 
           <img v-if="doc._props.isPlayableImage || doc._props.isPlayableVideo"
-               :src="(doc._props.isGif && hover) ? `f/${doc._id}` : `t/${doc._source.index}/${doc._id}`"
+               :src="(doc._props.isGif && hover) ? `f/${doc._source.index}/${doc._id}` : `t/${doc._source.index}/${doc._id}`"
                alt=""
                class="pointer fit-sm" @click="onThumbnailClick()">
           <img v-else :src="`t/${doc._source.index}/${doc._id}`" alt=""
@@ -50,6 +50,11 @@
           <span v-if="doc._source.author && doc._source.pages" class="mx-1">-</span>
           <span v-if="doc._source.author">{{ doc._source.author }}</span>
         </div>
+
+        <!-- Featured line -->
+        <div style="display: flex">
+          <FeaturedFieldsLine :doc="doc"></FeaturedFieldsLine>
+        </div>
       </div>
     </div>
   </b-list-group-item>
@@ -61,10 +66,11 @@ import DocFileTitle from "@/components/DocFileTitle";
 import DocInfoModal from "@/components/DocInfoModal";
 import ContentDiv from "@/components/ContentDiv";
 import FileIcon from "@/components/icons/FileIcon";
+import FeaturedFieldsLine from "@/components/FeaturedFieldsLine";
 
 export default {
   name: "DocListItem",
-  components: {FileIcon, ContentDiv, DocInfoModal, DocFileTitle, TagContainer},
+  components: {FileIcon, ContentDiv, DocInfoModal, DocFileTitle, TagContainer, FeaturedFieldsLine},
   props: ["doc"],
   data() {
     return {

sist2-vue/src/components/FeaturedFieldsLine.vue

@@ -0,0 +1,46 @@
+<template>
+    <div class="featured-line" v-html="featuredLineHtml"></div>
+</template>
+
+<script>
+import {humanDate, humanFileSize} from "@/util";
+
+function scopedEval(context, expr) {
+    const evaluator = Function.apply(null, [...Object.keys(context), "expr", "return eval(expr)"]);
+    return evaluator.apply(null, [...Object.values(context), expr]);
+}
+
+
+export default {
+    name: "FeaturedFieldsLine",
+    props: ["doc"],
+    computed: {
+        featuredLineHtml() {
+            if (this.$store.getters.optFeaturedFields === undefined) {
+                return "";
+            }
+
+            const scope = {doc: this.doc._source, humanDate: humanDate, humanFileSize: humanFileSize};
+
+            return this.$store.getters.optFeaturedFields
+                .replaceAll(/\$\{([^}]*)}/g, (match, g1) => {
+                    return scopedEval(scope, g1);
+                });
+        }
+    }
+}
+</script>
+
+<style scoped>
+
+.featured-line {
+    font-size: 90%;
+    font-family: 'Source Sans Pro', 'Helvetica Neue', Arial, sans-serif;
+    color: #424242;
+    padding-left: 2px;
+}
+
+.theme-black .featured-line {
+    color: #bebebe;
+}
+</style>

sist2-vue/src/components/FullThumbnail.vue

@@ -6,13 +6,13 @@
     </div>
 
     <div
-        v-if="doc._props.isImage && !hover && doc._props.tnW / doc._props.tnH < 5"
+        v-if="doc._props.isImage && doc._props.imageAspectRatio < 5"
         class="card-img-overlay"
         :class="{'small-badge': smallBadge}">
       <span class="badge badge-resolution">{{ `${doc._source.width}x${doc._source.height}` }}</span>
     </div>
 
-    <div v-if="(doc._props.isVideo || doc._props.isGif) && doc._source.duration > 0 && !hover"
+    <div v-if="(doc._props.isVideo || doc._props.isGif) && doc._source.duration > 0"
          class="card-img-overlay"
          :class="{'small-badge': smallBadge}">
       <span class="badge badge-resolution">{{ humanTime(doc._source.duration) }}</span>
@@ -63,17 +63,20 @@ export default {
   },
   computed: {
     tnSrc() {
-      const doc = this.doc;
-      const props = doc._props;
-      if (props.isGif && this.hover) {
-        return `f/${doc._id}`;
-      }
-      return (this.currentThumbnailNum === 0)
-          ? `t/${doc._source.index}/${doc._id}`
-          : `t/${doc._source.index}/${doc._id}${String(this.currentThumbnailNum).padStart(4, "0")}`;
+      return this.getThumbnailSrc(this.currentThumbnailNum);
     },
   },
   methods: {
+    getThumbnailSrc(thumbnailNum) {
+      const doc = this.doc;
+      const props = doc._props;
+      if (props.isGif && this.hover) {
+        return `f/${doc._source.index}/${doc._id}`;
+      }
+      return (this.currentThumbnailNum === 0)
+          ? `t/${doc._source.index}/${doc._id}`
+          : `t/${doc._source.index}/${doc._id}/${String(thumbnailNum).padStart(4, "0")}`;
+    },
     humanTime: humanTime,
     onThumbnailClick() {
       this.$emit("onThumbnailClick");
@@ -86,9 +89,14 @@ export default {
     },
     onTnEnter() {
       this.hover = true;
+      const start = Date.now()
       if (this.doc._props.hasVidPreview) {
+        let img = new Image();
+        img.src = this.getThumbnailSrc(this.currentThumbnailNum + 1);
+        img.onload = () => {
           this.currentThumbnailNum += 1;
-        this.scheduleNextTnNum();
+          this.scheduleNextTnNum(Date.now() - start);
+        }
       }
     },
     onTnLeave() {
@@ -99,17 +107,23 @@ export default {
         this.timeoutId = null;
       }
     },
-    scheduleNextTnNum() {
-      const INTERVAL = this.$store.state.optVidPreviewInterval ?? 700;
+    scheduleNextTnNum(offset = 0) {
+      const INTERVAL = (this.$store.state.optVidPreviewInterval ?? 700) - offset;
       this.timeoutId = window.setTimeout(() => {
+        const start = Date.now();
         if (!this.hover) {
           return;
         }
-        this.scheduleNextTnNum();
         if (this.currentThumbnailNum === this.doc._props.tnNum - 1) {
           this.currentThumbnailNum = 0;
+          this.scheduleNextTnNum();
         } else {
+          let img = new Image();
+          img.src = this.getThumbnailSrc(this.currentThumbnailNum + 1);
+          img.onload = () => {
             this.currentThumbnailNum += 1;
+            this.scheduleNextTnNum(Date.now() - start);
+          }
         }
       }, INTERVAL);
     },
@@ -152,17 +166,18 @@ export default {
 }
 
 .badge-resolution {
-  color: #212529;
-  background-color: #FFC107;
+  color: #c6c6c6;
+  background-color: #272727CC;
+  padding: 2px 3px;
 }
 
 .card-img-overlay {
   pointer-events: none;
-  padding: 0.75rem;
-  bottom: unset;
-  top: 0;
+  padding: 2px 6px;
+  bottom: 4px;
+  top: unset;
   left: unset;
-  right: unset;
+  right: 0;
 }
 
 .small-badge {

sist2-vue/src/components/LazyContentDiv.vue

@@ -1,80 +1,103 @@
 <template>
     <Preloader v-if="loading"></Preloader>
-  <div v-else-if="content" class="content-div" v-html="content"></div>
+    <div v-else-if="content">
+        <b-form inline class="my-2" v-if="ModelsRepo.getOptions().length > 0">
+            <b-checkbox class="ml-auto mr-2" :checked="optAutoAnalyze"
+                        @input="setOptAutoAnalyze($event); $store.dispatch('updateConfiguration')">
+                {{ $t("ml.auto") }}
+            </b-checkbox>
+            <b-button :disabled="mlPredictionsLoading || mlLoading" @click="mlAnalyze" variant="primary"
+            >{{ $t("ml.analyzeText") }}
+            </b-button>
+            <b-select :disabled="mlPredictionsLoading || mlLoading" class="ml-2" v-model="mlModel">
+                <b-select-option :value="opt.value" v-for="opt of ModelsRepo.getOptions()">{{ opt.text }}
+                </b-select-option>
+            </b-select>
+        </b-form>
+
+        <b-progress v-if="mlLoading" variant="warning" show-progress :max="1" class="mb-3"
+        >
+            <b-progress-bar :value="modelLoadingProgress">
+                <strong>{{ ((modelLoadingProgress * modelSize) / (1024 * 1024)).toFixed(1) }}MB / {{
+                    (modelSize / (1024 * 1024)).toFixed(1)
+                    }}MB</strong>
+            </b-progress-bar>
+        </b-progress>
+
+        <b-progress v-if="mlPredictionsLoading" variant="primary" :value="modelPredictionProgress"
+                    :max="content.length" class="mb-3"></b-progress>
+
+        <AnalyzedContentSpansContainer v-if="analyzedContentSpans.length > 0"
+                                       :spans="analyzedContentSpans" :text="rawContent"></AnalyzedContentSpansContainer>
+        <div v-else class="content-div" v-html="content"></div>
+    </div>
 </template>
 
 <script>
 import Sist2Api from "@/Sist2Api";
 import Preloader from "@/components/Preloader";
-import Sist2Query from "@/Sist2Query";
+import Sist2Query from "@/Sist2ElasticsearchQuery";
 import store from "@/store";
+import BertNerModel from "@/ml/BertNerModel";
+import AnalyzedContentSpansContainer from "@/components/AnalyzedContentSpanContainer.vue";
+import ModelsRepo from "@/ml/modelsRepo";
+import {mapGetters, mapMutations} from "vuex";
 
 export default {
     name: "LazyContentDiv",
-  components: {Preloader},
+    components: {AnalyzedContentSpansContainer, Preloader},
     props: ["docId"],
     data() {
         return {
+            ModelsRepo,
             content: "",
-      loading: true
+            rawContent: "",
+            loading: true,
+            modelLoadingProgress: 0,
+            modelPredictionProgress: 0,
+            mlPredictionsLoading: false,
+            mlLoading: false,
+            mlModel: null,
+            analyzedContentSpans: []
         }
     },
     mounted() {
-    const query = Sist2Query.searchQuery();
 
-    if (this.$store.state.optHighlight) {
-
-      const fields = this.$store.state.fuzzy
-          ? {"content.nGram": {}}
-          : {content: {}};
-
-      query.highlight = {
-        pre_tags: ["<mark>"],
-        post_tags: ["</mark>"],
-        number_of_fragments: 0,
-        fields,
-      };
-
-      if (!store.state.sist2Info.esVersionLegacy) {
-        query.highlight.max_analyzed_offset = 999_999;
-      }
-    }
-
-    if ("function_score" in query.query) {
-      query.query = query.query.function_score.query;
-    }
-
-    if (!("must" in query.query.bool)) {
-      query.query.bool.must = [];
-    } else if (!Array.isArray(query.query.bool.must)) {
-      query.query.bool.must = [query.query.bool.must];
-    }
-
-    query.query.bool.must.push({match: {_id: this.docId}});
-
-    delete query["sort"];
-    delete query["aggs"];
-    delete query["search_after"];
-    delete query.query["function_score"];
-
-    query._source = {
-      includes: ["content", "name", "path", "extension"]
-    }
-
-    query.size = 1;
-
-    Sist2Api.esQuery(query).then(resp => {
-      this.loading = false;
-      if (resp.hits.hits.length === 1) {
-        this.content = this.getContent(resp.hits.hits[0]);
+        if (this.$store.getters.optMlDefaultModel) {
+            this.mlModel = this.$store.getters.optMlDefaultModel
         } else {
-        console.log("FIXME: could not get content")
-        console.log(resp)
+            this.mlModel = ModelsRepo.getDefaultModel();
+        }
+
+        Sist2Api
+            .getDocument(this.docId, this.$store.state.optHighlight, this.$store.state.fuzzy)
+            .then(doc => {
+                this.loading = false;
+
+                if (doc) {
+                    this.content = this.getContent(doc)
+                }
+
+                if (this.optAutoAnalyze) {
+                    this.mlAnalyze();
                 }
             });
     },
+    computed: {
+        ...mapGetters(["optAutoAnalyze"]),
+        modelSize() {
+            const modelData = ModelsRepo.data[this.mlModel];
+            if (!modelData) {
+                return 0;
+            }
+            return modelData.size;
+        }
+    },
     methods: {
+        ...mapMutations(["setOptAutoAnalyze"]),
         getContent(doc) {
+            this.rawContent = doc._source.content;
+
             if (!doc.highlight) {
                 return doc._source.content;
             }
@@ -85,10 +108,60 @@ export default {
             if (doc.highlight.content) {
                 return doc.highlight.content[0];
             }
+        },
+        async getMlModel() {
+            if (this.$store.getters.mlModel.name !== this.mlModel) {
+                this.mlLoading = true;
+                this.modelLoadingProgress = 0;
+                const modelInfo = ModelsRepo.data[this.mlModel];
+
+                const model = new BertNerModel(
+                    modelInfo.vocabUrl,
+                    modelInfo.modelUrl,
+                    modelInfo.id2label,
+                )
+
+                await model.init(progress => this.modelLoadingProgress = progress);
+                this.$store.commit("setMlModel", {model, name: this.mlModel});
+
+                this.mlLoading = false;
+                return model
+            }
+
+            return this.$store.getters.mlModel.model;
+        },
+        async mlAnalyze() {
+            if (!this.content) {
+                return;
+            }
+
+            const modelInfo = ModelsRepo.data[this.mlModel];
+            if (modelInfo === undefined) {
+                return;
+            }
+
+            this.$store.commit("setOptMlDefaultModel", this.mlModel);
+            await this.$store.dispatch("updateConfiguration");
+
+            const model = await this.getMlModel();
+
+            this.analyzedContentSpans = [];
+
+            this.mlPredictionsLoading = true;
+
+            await model.predict(this.rawContent, results => {
+                results.forEach(result => result.label = modelInfo.humanLabels[result.label]);
+                this.analyzedContentSpans.push(...results);
+                this.modelPredictionProgress = results[results.length - 1].wordIndex;
+            });
+            this.mlPredictionsLoading = false;
         }
     }
 }
 </script>
 
-<style scoped>
+<style>
+.progress-bar {
+    transition: none;
+}
 </style>

sist2-vue/src/components/Lightbox.vue

@@ -160,9 +160,13 @@ export default {
     },
     onSlideChange() {
       // Pause all videos when changing slide
-      document.getElementsByTagName("video").forEach((el) => {
+      const videos = document.getElementsByTagName("video");
+      if (videos.length === 0) {
+        return
+      }
+      for (let el of videos) {
         el.pause();
-      });
+      }
     },
   }
 

sist2-vue/src/components/MimePicker.vue

@@ -9,7 +9,7 @@ import InspireTreeDOM from "inspire-tree-dom";
 import "inspire-tree-dom/dist/inspire-tree-light.min.css";
 import {getSelectedTreeNodes, getTreeNodeAttributes} from "@/util";
 import Sist2Api from "@/Sist2Api";
-import Sist2Query from "@/Sist2Query";
+import Sist2Query from "@/Sist2ElasticsearchQuery";
 
 export default {
   name: "MimePicker",

sist2-vue/src/components/NavBar.vue

@@ -9,13 +9,15 @@
 
     <span class="badge badge-pill version" v-if="$store && $store.state.sist2Info">
       v{{ sist2Version() }}<span v-if="isDebug()">-dbg</span><span v-if="isLegacy() && !hideLegacy()">-<a
-        href="https://github.com/simon987/sist2/blob/master/docs/USAGE.md#elasticsearch" target="_blank">legacyES</a></span>
+        href="https://github.com/simon987/sist2/blob/master/docs/USAGE.md#elasticsearch"
+        target="_blank">legacyES</a></span><span v-if="$store.state.uiSqliteMode">-SQLite</span>
     </span>
 
     <span v-if="$store && $store.state.sist2Info" class="tagline" v-html="tagline()"></span>
 
     <b-button class="ml-auto" to="stats" variant="link">{{ $t("stats") }}</b-button>
     <b-button to="config" variant="link">{{ $t("config") }}</b-button>
+    <b-button v-if="$auth && $auth.isAuthenticated" variant="link" @click="onLogoutClick()">logout</b-button>
   </b-navbar>
 </template>
 
@@ -40,6 +42,9 @@ export default {
     },
     hideLegacy() {
       return this.$store.state.optHideLegacy;
+    },
+    onLogoutClick() {
+      this.$auth.logout();
     }
   }
 }
@@ -60,7 +65,6 @@ export default {
   color: #222 !important;
   font-size: 1.75rem;
   padding: 0;
-  font-family: Hack;
 }
 
 .navbar-brand:hover {