Bump version

v2.10.1

.dockerignore

@@ -21,3 +21,5 @@ third-party/libscan/libscan-test-files/
 **/ext_libmobi
 **/scan_a_test
 Dockerfile
+*.idx/
+VERSION

.drone.yml

@@ -8,7 +8,7 @@ platform:
 
 steps:
   - name: build
-    image: simon987/ubuntu_ci
+    image: simon987/sist2-build
     commands:
       - ./ci/build.sh
   - name: docker
@@ -19,8 +19,8 @@ steps:
       password:
         from_secret: DOCKER_PASSWORD
       repo: simon987/sist2
-      context: ./Docker/
-      dockerfile: ./Docker/Dockerfile
+      context: ./
+      dockerfile: ./Dockerfile
       auto_tag: true
       auto_tag_suffix: x64-linux
       when:
@@ -41,7 +41,7 @@ steps:
       source:
         - ./VERSION
         - ./sist2-x64-linux
-        - ./sist2-x64-linux-debug.tar.gz
+        - ./sist2-x64-linux-debug
 
 ---
 kind: pipeline
@@ -53,7 +53,7 @@ platform:
 
 steps:
   - name: build
-    image: simon987/ubuntu_ci_arm
+    image: simon987/sist2-build-arm64
     commands:
       - ./ci/build_arm64.sh
   - name: scp files

.github/ISSUE_TEMPLATE/bug_report.md

@@ -0,0 +1,40 @@
+---
+name: "🐞 Bug Report"
+about: Submit a bug report 
+title: ''
+labels: bug
+assignees: ''
+
+---
+
+**Device Information (please complete the following information):**
+ - OS: `[e.g., Ubuntu 20.04, WSL2]`
+ - Deployment: `[Linux, Linux ARM64 or Docker]`
+ - Browser *(if relevant)*: `[e.g., chrome, safari]`
+ - SIST2 Version: `[e.g., v2.9.0]`
+ - Elasticsearch Version *(if relevant)* : ``
+
+**Command with arguments** 
+<!-- `ex: "scan ~/Documents -o ./i2 --threads 3 -q 1.0` -->
+
+**Describe the bug**
+<!-- A clear and concise description of what the bug is. -->
+
+**Steps To Reproduce**
+Please be specific!
+1. Go to '...'
+2. Click on '....'
+3. etc.
+
+**Expected behavior**
+<!-- A clear and concise description of what you expected to happen. -->
+
+**Actual Behavior**
+<!-- A clear and concise description of what actually happens. -->
+
+**Screenshots**
+<!-- If applicable, add screenshots to help explain your problem. -->
+
+**Additional context**
+<!-- Add any other context about the problem here. If applicable, please include why you think the bug is occurring and/or troubleshooting you have already performed. -->
+<!-- If the issue is related to the `scan` module, please attach the files necessary to reproduce the error or email them to me[at]simon987.net. -->

.github/ISSUE_TEMPLATE/config.yml

@@ -0,0 +1,5 @@
+blank_issues_enabled: false
+contact_links:
+  - name: SIST2 Documentation
+    url: https://github.com/simon987/sist2/blob/master/docs/USAGE.md
+    about: Check out the SIST2 documentation for answers to common questions

.github/ISSUE_TEMPLATE/feature_request.md

@@ -0,0 +1,18 @@
+---
+name: "🚀 Feature Request"
+about: Suggest an idea for SIST2
+title: ''
+assignees: ''
+
+---
+**Which SIST2 component is your Feature Request related to?**
+<!-- e.g., Scan, Index, or Web? -->
+
+**Is your feature request related to a problem? Please describe.**
+<!-- A clear and concise description of what the problem is. e.g., "I'm always frustrated when [...]" -->
+
+**What would you like to see happen?**
+<!-- A clear and concise description of what you want to happen. -->
+
+**Additional context**
+<!-- Add any other context or screenshots about the feature request here. -->

.gitignore

@@ -16,3 +16,5 @@ bundle.js
 vgcore.*
 build/
 third-party/
+*.idx/
+VERSION

Dockerfile

@@ -9,9 +9,7 @@ RUN strip sist2
 
 FROM ubuntu:20.10
 
-RUN apt update
-RUN apt install -y libglib2.0-0 libcurl4 libmagic1 libharfbuzz-bin libopenjp2-7 libarchive13 liblzma5 libzstd1 liblz4-1 \
- curl libtiff5 libpng16-16 libpcre3
+RUN apt update && apt install -y curl
 
 RUN mkdir -p /usr/share/tessdata && \
     cd /usr/share/tessdata/ && \

Dockerfile.arm64

@@ -1 +1,28 @@
-# TODO
+FROM simon987/sist2-build-arm64 as build
+MAINTAINER simon987 <me@simon987.net>
+
+WORKDIR /build/
+ADD . /build/
+RUN cmake -DSIST_DEBUG=off -DBUILD_TESTS=off -DCMAKE_TOOLCHAIN_FILE=/vcpkg/scripts/buildsystems/vcpkg.cmake .
+RUN make -j$(nproc)
+RUN strip sist2
+
+FROM ubuntu:20.10
+
+RUN apt update && apt install -y curl
+
+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
+
+COPY --from=build /build/sist2 /root/sist2
+
+ENV LANG C.UTF-8
+ENV LC_ALL C.UTF-8
+
+ENTRYPOINT ["/root/sist2"]

README.md

@@ -1,6 +1,6 @@
 ![GitHub](https://img.shields.io/github/license/simon987/sist2.svg)
 [![CodeFactor](https://www.codefactor.io/repository/github/simon987/sist2/badge?s=05daa325188aac4eae32c786f3d9cf4e0593f822)](https://www.codefactor.io/repository/github/simon987/sist2)
-[![Development snapshots](https://ci.simon987.net/api/badges/simon987/sist2/status.svg)](https://files.simon987.net/sist2/simon987_sist2/)
+[![Development snapshots](https://ci.simon987.net/api/badges/simon987/sist2/status.svg)](https://files.simon987.net/.gate/sist2/simon987_sist2/)
 
 **Demo**: [sist2.simon987.net](https://sist2.simon987.net/?i=Demo%20files)
 
@@ -50,8 +50,8 @@ sist2 (Simple incremental search tool)
         ```
 1. Download sist2 executable
     1. Download the [latest sist2 release](https://github.com/simon987/sist2/releases) *
-    1. *(or)* Download a [development snapshot](https://files.simon987.net/sist2/simon987_sist2/) *(Not recommended!)*
-    1. *(or)* `docker pull simon987/sist2:latest`
+    1. *(or)* Download a [development snapshot](https://files.simon987.net/.gate/sist2/simon987_sist2/) *(Not recommended!)*
+    1. *(or)* `docker pull simon987/sist2:2.10.1-x64-linux`
 
 1. See [Usage guide](docs/USAGE.md)
 
@@ -67,7 +67,7 @@ See [Usage guide](docs/USAGE.md) for more details
 
 ## Format support
 
-File type | Library | Content | Thumbnail | Metadata
+File type | Library | Content | Thumbnail | Metadata
 :---|:---|:---|:---|:---
 pdf,xps,fb2,epub | MuPDF | text+ocr | yes | author, title |
 cbz,cbr | *(none)* | - | yes | - |
@@ -116,15 +116,35 @@ sist2 scan --ocr eng ~/Books/Textbooks/
 
 ## Build from source
 
-You can compile **sist2** by yourself if you don't want to use the pre-compiled binaries (GCC 7+ required).
+You can compile **sist2** by yourself if you don't want to use the pre-compiled binaries
+
+### With docker (recommended)
+
+```bash
+git clone --recursive https://github.com/simon987/sist2/
+cd sist2
+docker build . -f ./Dockerfile -t my-sist2-image
+docker run --rm my-sist2-image cat /root/sist2 > sist2-x64-linux
+```
+
+### On a linux computer
 
 1. Install compile-time dependencies
 
    ```bash
-   vcpkg install lmdb cjson glib libarchive[core,bzip2,libxml2,lz4,lzma,lzo] pthread tesseract libxml2 ffmpeg zstd gtest mongoose libmagic libraw curl[core,ssl] jbig2dec brotli libmupdf
+   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
    ```
    
-2. Build
+1. Apply vcpkg patches, as per [sist2-build](https://github.com/simon987/sist2-build) Dockerfile
+
+1. 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 libuuid libmagic libraw jasper lcms gumbo
+    ```
+
+1. Build
     ```bash
     git clone --recursive https://github.com/simon987/sist2/
     cmake -DSIST_DEBUG=off -DCMAKE_TOOLCHAIN_FILE=<VCPKG_ROOT>/scripts/buildsystems/vcpkg.cmake .

ci/build.sh

@@ -2,21 +2,18 @@
 
 VCPKG_ROOT="/vcpkg"
 
-rm *.gz
+rm *.gz &>/dev/null
 
 git submodule update --init --recursive
 
 rm -rf CMakeFiles CMakeCache.txt
 cmake -DSIST_DEBUG=off -DCMAKE_TOOLCHAIN_FILE="${VCPKG_ROOT}/scripts/buildsystems/vcpkg.cmake" .
-make -j 33
+make -j $(nproc)
 strip sist2
 ./sist2 -v > VERSION
-cp sist2 Docker/
 mv sist2 sist2-x64-linux
 
 rm -rf CMakeFiles CMakeCache.txt
 cmake -DSIST_DEBUG=on -DCMAKE_TOOLCHAIN_FILE="${VCPKG_ROOT}/scripts/buildsystems/vcpkg.cmake" .
-make -j 33
-cp /usr/lib/x86_64-linux-gnu/libasan.so.2.0.0 libasan.so.2
+make -j  $(nproc)
 mv sist2_debug sist2-x64-linux-debug
-tar -czf sist2-x64-linux-debug.tar.gz sist2-x64-linux-debug libasan.so.2

ci/build_arm64.sh

@@ -2,12 +2,12 @@
 
 VCPKG_ROOT="/vcpkg"
 
-rm *.gz
+rm *.gz &>/dev/null
 
 git submodule update --init --recursive
 
 rm -rf CMakeFiles CMakeCache.txt
 cmake -DSIST_DEBUG=off -DCMAKE_TOOLCHAIN_FILE="${VCPKG_ROOT}/scripts/buildsystems/vcpkg.cmake" .
-make -j 4
+make -j $(nproc)
 strip sist2
 mv sist2 sist2-arm64-linux

docs/USAGE.md

@@ -357,8 +357,7 @@ You can safely copy the `/tags/` database to another index.
 See [Automatic tagging](#automatic-tagging) for information about tag 
  hierarchies and tag colors.
 
-\* *It can take a few seconds to take effect in new search queries, and the page needs 
-    to be reloaded for the tags tab to update*
+\* *It can take a few seconds to take effect in new search queries.*
 
 
 ### Automatic tagging

src/ctx.h

@@ -41,6 +41,7 @@ typedef struct {
     int fast;
 
     GHashTable *dbg_current_files;
+    pthread_mutex_t dbg_current_files_mu;
 
     scan_arc_ctx_t arc_ctx;
     scan_comic_ctx_t comic_ctx;

src/main.c

@@ -21,7 +21,7 @@
 #define EPILOG "Made by simon987 <me@simon987.net>. Released under GPL-3.0"
 
 
-static const char *const Version = "2.10.1";
+static const char *const Version = "2.10.2";
 static const char *const usage[] = {
         "sist2 scan [OPTION]... PATH",
         "sist2 index [OPTION]... INDEX",
@@ -168,7 +168,8 @@ void initialize_scan_context(scan_args_t *args) {
         ScanCtx.arc_ctx.passphrase[0] = 0;
     }
 
-    ScanCtx.dbg_current_files = g_hash_table_new(g_int64_hash, g_int64_equal);
+    ScanCtx.dbg_current_files = g_hash_table_new_full(g_int64_hash, g_int64_equal, NULL, NULL);
+    pthread_mutex_init(&ScanCtx.dbg_current_files_mu, NULL);
 
     // Comic
     ScanCtx.comic_ctx.log = _log;

src/parsing/parse.c

@@ -43,7 +43,9 @@ void fs_reset(struct vfile *f) {
 
 void set_dbg_current_file(parse_job_t *job) {
     unsigned long long pid = (unsigned long long) pthread_self();
+    pthread_mutex_lock(&ScanCtx.dbg_current_files_mu);
     g_hash_table_replace(ScanCtx.dbg_current_files, GINT_TO_POINTER(pid), job);
+    pthread_mutex_unlock(&ScanCtx.dbg_current_files_mu);
 }
 
 void parse(void *arg) {

src/static/search.html

@@ -12,7 +12,7 @@
 
 <nav class="navbar navbar-expand-lg">
     <a class="navbar-brand" href="/">sist2</a>
-    <span class="badge badge-pill version">2.10.1</span>
+    <span class="badge badge-pill version">2.10.2</span>
     <span class="tagline">Lightning-fast file system indexer and search tool </span>
     <a class="btn ml-auto" href="stats">Stats</a>
     <button class="btn" type="button" data-toggle="modal" data-target="#settings" onclick="loadSettings()">Settings

src/static/stats.html

@@ -10,7 +10,7 @@
 
 <nav class="navbar navbar-expand-lg">
     <a class="navbar-brand" href="/">sist2</a>
-    <span class="badge badge-pill version">2.10.1</span>
+    <span class="badge badge-pill version">2.10.2</span>
     <span class="tagline">Lightning-fast file system indexer and search tool </span>
     <a style="margin-left: auto" class="btn" href="/">Back</a>
     <button class="btn" type="button" data-toggle="modal" data-target="#settings"

src/web/serve.c

@@ -220,7 +220,10 @@ void serve_file_from_url(cJSON *json, index_t *idx, struct mg_connection *nc) {
     dyn_buffer_t encoded = url_escape(url);
     dyn_buffer_write_char(&encoded, '\0');
 
-    mg_http_reply(nc, 308, "Location: %s", encoded.buf);
+    char location_header[8192];
+    snprintf(location_header, sizeof(location_header), "Location: %s\r\n", encoded.buf);
+
+    mg_http_reply(nc, 308, location_header, "");
     dyn_buffer_destroy(&encoded);
 }
 
@@ -531,7 +534,7 @@ int validate_auth(struct mg_connection *nc, struct mg_http_message *hm) {
 
     mg_http_creds(hm, user, sizeof(user), pass, sizeof(pass));
     if (strcmp(user, WebCtx.auth_user) != 0 || strcmp(pass, WebCtx.auth_pass) != 0) {
-        mg_http_reply(nc, 401, "WWW-Authenticate: Basic realm=\"sist2\"", "");
+        mg_http_reply(nc, 401, "WWW-Authenticate: Basic realm=\"sist2\"\r\n", "");
         return FALSE;
     }
     return TRUE;
@@ -544,7 +547,6 @@ static void ev_router(struct mg_connection *nc, int ev, void *ev_data, UNUSED(vo
 
         if (WebCtx.auth_enabled == TRUE) {
             if (!validate_auth(nc, hm)) {
-                nc->is_closing = 1;
                 return;
             }
         }
@@ -575,7 +577,6 @@ static void ev_router(struct mg_connection *nc, int ev, void *ev_data, UNUSED(vo
             stats_files(nc, hm);
         } else if (mg_http_match_uri(hm, "/tag/*")) {
             if (WebCtx.tag_auth_enabled == TRUE && !validate_auth(nc, hm)) {
-                nc->is_closing = 1;
                 return;
             }
             tag(nc, hm);