update docker image version in readme

v2.10.1

.dockerignore

@@ -20,4 +20,6 @@ third-party/libscan/libscan-test-files/
 **/ext_ffmpeg
 **/ext_libmobi
 **/scan_a_test
-Dockerfile
+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/
+      context: ./
-      dockerfile: ./Docker/Dockerfile
+      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 update && apt install -y curl
-RUN apt install -y libglib2.0-0 libcurl4 libmagic1 libharfbuzz-bin libopenjp2-7 libarchive13 liblzma5 libzstd1 liblz4-1 \
- curl libtiff5 libpng16-16 libpcre3
 
 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)
 
@@ -25,14 +25,12 @@ sist2 (Simple incremental search tool)
 * OCR support with tesseract \*\*\*
 * Stats page & disk utilisation visualization
 
-
 \* See [format support](#format-support)    
 \*\* See [Archive files](#archive-files)    
-\*\*\* See [OCR](#ocr)    
+\*\*\* See [OCR](#ocr)
 
 ![stats](docs/stats.png)
 
-
 ## Getting Started
 
 1. Have an Elasticsearch (>= 6.X.X) instance running
@@ -52,14 +50,12 @@ 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)* Download a [development snapshot](https://files.simon987.net/.gate/sist2/simon987_sist2/) *(Not recommended!)*
-    1. *(or)* `docker pull simon987/sist2:latest`
+    1. *(or)* `docker pull simon987/sist2:2.10.3-x64-linux`
 
 1. See [Usage guide](docs/USAGE.md)
-   
-
-\* *Windows users*: **sist2** runs under [WSL](https://en.wikipedia.org/wiki/Windows_Subsystem_for_Linux)    
 
+\* *Windows users*: **sist2** runs under [WSL](https://en.wikipedia.org/wiki/Windows_Subsystem_for_Linux)
 
 ## Example usage
 
@@ -69,17 +65,16 @@ See [Usage guide](docs/USAGE.md) for more details
 1. Push index to Elasticsearch: `sist2 index ./docs_idx`
 1. Start web interface: `sist2 web ./docs_idx`
 
-
 ## 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 | - |
 `audio/*` | ffmpeg | - | yes | ID3 tags |
 `video/*` | ffmpeg | - | yes | title, comment, artist |
-`image/*` | ffmpeg | - | yes | [Common EXIF tags](https://github.com/simon987/sist2/blob/efdde2734eca9b14a54f84568863b7ffd59bdba3/src/parsing/media.c#L190) |
+`image/*` | ffmpeg | - | yes | [Common EXIF tags](https://github.com/simon987/sist2/blob/efdde2734eca9b14a54f84568863b7ffd59bdba3/src/parsing/media.c#L190), GPS tags |
-raw, rw2, dng, cr2, crw, dcr, k25, kdc, mrw, pef, xf3, arw, sr2, srf, erf  | LibRaw | - | yes | Common EXIF tags |
+raw, rw2, dng, cr2, crw, dcr, k25, kdc, mrw, pef, xf3, arw, sr2, srf, erf  | LibRaw | - | yes | Common EXIF tags, GPS tags |
 ttf,ttc,cff,woff,fnt,otf | Freetype2 | - | yes, `bmp` | Name & style |
 `text/plain` | *(none)* | yes | no | - |
 html, xml | *(none)* | yes | no | - |
@@ -89,48 +84,67 @@ doc (MS Word 97-2003) | antiword | yes | yes | author, title |
 mobi, azw, azw3 | libmobi | yes | no | author, title |
 
 \* *See [Archive files](#archive-files)*
- 
+
 ### Archive files
-**sist2** will scan files stored into archive files (zip, tar, 7z...) as if
+
-they were directly in the file system. Recursive (archives inside archives)
+**sist2** will scan files stored into archive files (zip, tar, 7z...) as if they were directly in the file system.
+Recursive (archives inside archives)
 scan is also supported.
 
 **Limitations**:
-* Support for parsing media files with formats that require *seek* (e.g. `.gif`, `.mp4` w/ fragmented metadata etc.) 
+
+* Support for parsing media files with formats that require *seek* (e.g. `.gif`, `.mp4` w/ fragmented metadata etc.)
   is limitted (see `--mem-buffer` option)
 * Archive files are scanned sequentially, by a single thread. On systems where
-**sist2** is not I/O bound, scans might be faster when larger archives are split
+  **sist2** is not I/O bound, scans might be faster when larger archives are split into smaller parts.
- into smaller parts.
+
- 
- 
 ### OCR
 
 You can enable OCR support for pdf,xps,fb2,epub file types with the
-`--ocr <lang>` option. Download the language data files with your
+`--ocr <lang>` option. Download the language data files with your package manager (`apt install tesseract-ocr-eng`) or
-package manager (`apt install tesseract-ocr-eng`) or directly [from Github](https://github.com/tesseract-ocr/tesseract/wiki/Data-Files).
+directly [from Github](https://github.com/tesseract-ocr/tesseract/wiki/Data-Files).
 
-The `simon987/sist2` image comes with common languages 
+The `simon987/sist2` image comes with common languages
 (hin, jpn, eng, fra, rus, spa) pre-installed.
 
 Examples
+
 ```bash
 sist2 scan --ocr jpn ~/Books/Manga/
 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
+You can compile **sist2** by yourself if you don't want to use the pre-compiled binaries
-binaries (GCC 7+ required).
+
+### 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
    ```
+   
+1. Apply vcpkg patches, as per [sist2-build](https://github.com/simon987/sist2-build) Dockerfile
 
-2. Build
+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
+make -j  $(nproc)
-cp /usr/lib/x86_64-linux-gnu/libasan.so.2.0.0 libasan.so.2
+mv sist2_debug sist2-x64-linux-debug
-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 
+\* *It can take a few seconds to take effect in new search queries.*
-    to be reloaded for the tags tab to update*
 
 
 ### Automatic tagging

schema/mappings.json

@@ -105,10 +105,10 @@
       "analyzer": "my_nGram",
       "type": "text"
     },
-    "_keyword.*":  {
+    "_keyword.*": {
       "type": "keyword"
     },
-    "_text.*":  {
+    "_text.*": {
       "analyzer": "content_analyzer",
       "type": "text",
       "fields": {
@@ -165,6 +165,30 @@
     "exif_user_comment": {
       "type": "text"
     },
+    "exif_gps_longitude_ref": {
+      "type": "keyword",
+      "index": false
+    },
+    "exif_gps_longitude_dms": {
+      "type": "keyword",
+      "index": false
+    },
+    "exif_gps_longitude_dec": {
+      "type": "keyword",
+      "index": false
+    },
+    "exif_gps_latitude_ref": {
+      "type": "keyword",
+      "index": false
+    },
+    "exif_gps_latitude_dms": {
+      "type": "keyword",
+      "index": false
+    },
+    "exif_gps_latitude_dec": {
+      "type": "keyword",
+      "index": false
+    },
     "author": {
       "type": "text"
     },

src/cli.c

@@ -232,6 +232,7 @@ int scan_args_validate(scan_args_t *args, int argc, const char **argv) {
     LOG_DEBUGF("cli.c", "arg tesseract_path=%s", args->tesseract_path)
     LOG_DEBUGF("cli.c", "arg exclude=%s", args->exclude_regex)
     LOG_DEBUGF("cli.c", "arg fast=%d", args->fast)
+    LOG_DEBUGF("cli.c", "arg fast_epub=%d", args->fast_epub)
     LOG_DEBUGF("cli.c", "arg treemap_threshold=%f", args->treemap_threshold)
     LOG_DEBUGF("cli.c", "arg max_memory_buffer=%d", args->max_memory_buffer)
 

src/cli.h

@@ -27,6 +27,7 @@ typedef struct scan_args {
     double treemap_threshold;
     int max_memory_buffer;
     int read_subtitles;
+    int fast_epub;
 } scan_args_t;
 
 scan_args_t *scan_args_create();

src/ctx.h

@@ -41,6 +41,12 @@ typedef struct {
     int fast;
 
     GHashTable *dbg_current_files;
+    pthread_mutex_t dbg_current_files_mu;
+
+    int dbg_failed_files_count;
+    int dbg_skipped_files_count;
+    int dbg_excluded_files_count;
+    pthread_mutex_t dbg_file_counts_mu;
 
     scan_arc_ctx_t arc_ctx;
     scan_comic_ctx_t comic_ctx;

src/io/serialize.c

@@ -18,7 +18,7 @@ typedef struct {
 #define META_NEXT 0xFFFF
 
 void skip_meta(FILE *file) {
-    enum metakey key;
+    enum metakey key = 0;
     fread(&key, sizeof(uint16_t), 1, file);
 
     while (key != META_NEXT) {
@@ -237,7 +237,7 @@ void read_index_bin(const char *path, const char *index_id, index_func func) {
     FILE *file = fopen(path, "rb");
     while (TRUE) {
         buf.cur = 0;
-        size_t _ = fread((void *) &line, 1, sizeof(line_t), file);
+        size_t _ = fread((void *) &line, sizeof(line_t), 1, file);
         if (feof(file)) {
             break;
         }
@@ -284,8 +284,8 @@ void read_index_bin(const char *path, const char *index_id, index_func func) {
             cJSON_AddStringToObject(document, "path", "");
         }
 
-        enum metakey key;
+        enum metakey key = 0;
-        fread(&key, sizeof(short), 1, file);
+        fread(&key, sizeof(uint16_t), 1, file);
         size_t ret;
         while (key != META_NEXT) {
             switch (key) {
@@ -481,7 +481,7 @@ void incremental_read(GHashTable *table, const char *filepath) {
 
         incremental_put(table, line.path_md5, line.mtime);
 
-        while ((getc(file))) {}
+        while ((getc(file)) != 0) {}
         skip_meta(file);
     }
     fclose(file);
@@ -531,7 +531,7 @@ void incremental_copy(store_t *store, store_t *dst_store, const char *filepath,
                 free(buf);
             }
 
-            enum metakey key;
+            enum metakey key = 0;
             while (1) {
                 fread(&key, sizeof(uint16_t), 1, file);
                 fwrite(&key, sizeof(uint16_t), 1, dst_file);

src/io/walk.c

@@ -41,6 +41,10 @@ int handle_entry(const char *filepath, const struct stat *info, int typeflag, st
 
         if (ScanCtx.exclude != NULL && EXCLUDED(filepath)) {
             LOG_DEBUGF("walk.c", "Excluded: %s", filepath)
+
+            pthread_mutex_lock(&ScanCtx.dbg_file_counts_mu);
+            ScanCtx.dbg_excluded_files_count += 1;
+            pthread_mutex_unlock(&ScanCtx.dbg_file_counts_mu);
             return 0;
         }
 
@@ -51,6 +55,8 @@ int handle_entry(const char *filepath, const struct stat *info, int typeflag, st
     return 0;
 }
 
+#define MAX_FILE_DESCRIPTORS 64
+
 int walk_directory_tree(const char *dirpath) {
-    return nftw(dirpath, handle_entry, 15, FTW_PHYS);
+    return nftw(dirpath, handle_entry, MAX_FILE_DESCRIPTORS, FTW_PHYS | FTW_DEPTH);
 }

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 = "2.10.3";
 static const char *const usage[] = {
         "sist2 scan [OPTION]... PATH",
         "sist2 index [OPTION]... INDEX",
@@ -168,7 +168,10 @@ 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);
+
+    pthread_mutex_init(&ScanCtx.dbg_file_counts_mu, NULL);
 
     // Comic
     ScanCtx.comic_ctx.log = _log;
@@ -188,6 +191,7 @@ void initialize_scan_context(scan_args_t *args) {
     ScanCtx.ebook_ctx.log = _log;
     ScanCtx.ebook_ctx.logf = _logf;
     ScanCtx.ebook_ctx.store = _store;
+    ScanCtx.ebook_ctx.fast_epub_parse = args->fast_epub;
 
     // Font
     ScanCtx.font_ctx.enable_tn = args->size > 0;
@@ -248,6 +252,37 @@ void initialize_scan_context(scan_args_t *args) {
 }
 
 
+void load_incremental_index(const scan_args_t *args) {
+    ScanCtx.original_table = incremental_get_table();
+    ScanCtx.copy_table = incremental_get_table();
+
+    DIR *dir = opendir(args->incremental);
+    if (dir == NULL) {
+        LOG_FATALF("main.c", "Could not open original index for incremental scan: %s", strerror(errno))
+    }
+
+    char descriptor_path[PATH_MAX];
+    snprintf(descriptor_path, PATH_MAX, "%s/descriptor.json", args->incremental);
+    index_descriptor_t original_desc = read_index_descriptor(descriptor_path);
+
+    if (strcmp(original_desc.version, Version) != 0) {
+        LOG_FATALF("main.c", "Version mismatch! Index is %s but executable is %s/%s", original_desc.version,
+                   Version, INDEX_VERSION_EXTERNAL)
+    }
+
+    struct dirent *de;
+    while ((de = readdir(dir)) != NULL) {
+        if (strncmp(de->d_name, "_index_", sizeof("_index_") - 1) == 0) {
+            char file_path[PATH_MAX];
+            snprintf(file_path, PATH_MAX, "%s%s", args->incremental, de->d_name);
+            incremental_read(ScanCtx.original_table, file_path);
+        }
+    }
+    closedir(dir);
+
+    LOG_INFOF("main.c", "Loaded %d items in to mtime table.", g_hash_table_size(ScanCtx.original_table))
+}
+
 void sist2_scan(scan_args_t *args) {
 
     ScanCtx.mime_table = mime_get_mime_table();
@@ -269,42 +304,22 @@ void sist2_scan(scan_args_t *args) {
     scan_print_header();
 
     if (args->incremental != NULL) {
-        ScanCtx.original_table = incremental_get_table();
+        load_incremental_index(args);
-        ScanCtx.copy_table = incremental_get_table();
-
-        DIR *dir = opendir(args->incremental);
-        if (dir == NULL) {
-            LOG_FATALF("main.c", "Could not open original index for incremental scan: %s", strerror(errno))
-        }
-
-        char descriptor_path[PATH_MAX];
-        snprintf(descriptor_path, PATH_MAX, "%s/descriptor.json", args->incremental);
-        index_descriptor_t original_desc = read_index_descriptor(descriptor_path);
-
-        if (strcmp(original_desc.version, Version) != 0) {
-            LOG_FATALF("main.c", "Version mismatch! Index is %s but executable is %s/%s", original_desc.version,
-                       Version, INDEX_VERSION_EXTERNAL)
-        }
-
-        struct dirent *de;
-        while ((de = readdir(dir)) != NULL) {
-            if (strncmp(de->d_name, "_index_", sizeof("_index_") - 1) == 0) {
-                char file_path[PATH_MAX];
-                snprintf(file_path, PATH_MAX, "%s%s", args->incremental, de->d_name);
-                incremental_read(ScanCtx.original_table, file_path);
-            }
-        }
-        closedir(dir);
-
-        LOG_INFOF("main.c", "Loaded %d items in to mtime table.", g_hash_table_size(ScanCtx.original_table))
     }
 
     ScanCtx.pool = tpool_create(args->threads, thread_cleanup, TRUE);
     tpool_start(ScanCtx.pool);
-    walk_directory_tree(ScanCtx.index.desc.root);
+    int walk_ret = walk_directory_tree(ScanCtx.index.desc.root);
+    if (walk_ret == -1) {
+        LOG_FATALF("main.c", "walk_directory_tree() failed! %s (%d)", strerror(errno), errno)
+    }
     tpool_wait(ScanCtx.pool);
     tpool_destroy(ScanCtx.pool);
 
+    LOG_DEBUGF("main.c", "Skipped files: %d", ScanCtx.dbg_skipped_files_count)
+    LOG_DEBUGF("main.c", "Excluded files: %d", ScanCtx.dbg_excluded_files_count)
+    LOG_DEBUGF("main.c", "Failed files: %d", ScanCtx.dbg_failed_files_count)
+
     if (args->incremental != NULL) {
         char dst_path[PATH_MAX];
         snprintf(store_path, PATH_MAX, "%sthumbs", args->incremental);
@@ -426,6 +441,7 @@ void sist2_exec_script(exec_args_t *args) {
     index_descriptor_t desc = read_index_descriptor(descriptor_path);
 
     IndexCtx.es_url = args->es_url;
+    IndexCtx.es_index = args->es_index;
 
     LOG_DEBUGF("main.c", "descriptor version %s (%s)", desc.version, desc.type)
 
@@ -526,6 +542,7 @@ int main(int argc, const char *argv[]) {
                         "Maximum memory buffer size per thread in MB for files inside archives "
                         "(see USAGE.md). DEFAULT: 2000"),
             OPT_BOOLEAN(0, "read-subtitles", &scan_args->read_subtitles, "Read subtitles from media files."),
+            OPT_BOOLEAN(0, "fast-epub", &scan_args->fast_epub, "Faster but less accurate EPUB parsing (no thumbnails, metadata)"),
 
             OPT_GROUP("Index options"),
             OPT_INTEGER('t', "threads", &common_threads, "Number of threads. DEFAULT=1"),

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) {
@@ -69,6 +71,11 @@ void parse(void *arg) {
     int inc_ts = incremental_get(ScanCtx.original_table, doc.path_md5);
     if (inc_ts != 0 && inc_ts == job->vfile.info.st_mtim.tv_sec) {
         incremental_mark_file_for_copy(ScanCtx.copy_table, doc.path_md5);
+
+        pthread_mutex_lock(&ScanCtx.dbg_file_counts_mu);
+        ScanCtx.dbg_skipped_files_count += 1;
+        pthread_mutex_unlock(&ScanCtx.dbg_file_counts_mu);
+
         return;
     }
 
@@ -110,6 +117,10 @@ void parse(void *arg) {
             }
 
             CLOSE_FILE(job->vfile)
+
+            pthread_mutex_lock(&ScanCtx.dbg_file_counts_mu);
+            ScanCtx.dbg_failed_files_count += 1;
+            pthread_mutex_unlock(&ScanCtx.dbg_file_counts_mu);
             return;
         }
 

src/static/js/dom.js

@@ -192,6 +192,19 @@ function makeUserTag(tag, hit) {
     return userTag;
 }
 
+function makeGpsMetaRow(tbody, latitude, longitude) {
+    tbody.append($("<tr>")
+        .append($("<td>").text("Exif GPS"))
+        .append($("<td>")
+            .append($("<a>")
+                .text(`${latitude}, ${longitude}`)
+                .attr("href", `https://maps.google.com/?q=${latitude},${longitude}&ll=${latitude},${longitude}&t=k&z=17`)
+                .attr("target", "_blank")
+            )
+        )
+    );
+}
+
 function infoButtonCb(hit) {
     return () => {
         getDocumentInfo(hit["_id"]).then(doc => {
@@ -229,13 +242,25 @@ function infoButtonCb(hit) {
                     .text(new Date(doc["mtime"] * 1000).toISOString().split(".")[0].replace("T", " "))
                     .attr("title", doc["mtime"]))
             );
+
+            // Exif GPS
+            if ("exif_gps_longitude_dec" in doc) {
+                makeGpsMetaRow(tbody, doc["exif_gps_latitude_dec"], doc["exif_gps_longitude_dec"])
+            } else if ("exif_gps_longitude_dms" in doc) {
+                makeGpsMetaRow(
+                    tbody,
+                    dmsToDecimal(doc["exif_gps_latitude_dms"], doc["exif_gps_latitude_ref"]),
+                    dmsToDecimal(doc["exif_gps_longitude_dms"], doc["exif_gps_longitude_ref"]),
+                )
+            }
+
             const displayFields = new Set([
                 "mime", "size", "path", "title", "width", "height", "duration", "audioc", "videoc",
                 "bitrate", "artist", "album", "album_artist", "genre", "title", "font_name", "tag", "author",
                 "modified_by", "pages"
             ]);
             Object.keys(doc)
-                .filter(key => key.startsWith("_keyword.") || key.startsWith("_text.") || displayFields.has(key) || key.startsWith("exif_"))
+                .filter(key => key.startsWith("_keyword.") || key.startsWith("_text.") || displayFields.has(key) || (key.startsWith("exif_") && !key.includes("gps")))
                 .forEach(key => {
                     tbody.append($("<tr>")
                         .append($("<td>").text(key))
@@ -352,7 +377,7 @@ function createDocCard(hit) {
             audio.setAttribute("src", "f/" + hit["_id"]);
             audio.addEventListener("play", () => {
                 // Pause all currently playing audio tags
-                $("audio").each(function(){
+                $("audio").each(function () {
                     if (this !== audio) {
                         this.pause();
                     }

src/static/js/util.js

@@ -235,4 +235,14 @@ function updateColumnStyle() {
 }
         `
     }
+}
+
+function dmsToDecimal(dms, ref) {
+    const tokens = dms.split(",")
+
+    const d = Number(tokens[0].trim().split(":")[0]) / Number(tokens[0].trim().split(":")[1])
+    const m = Number(tokens[1].trim().split(":")[0]) / Number(tokens[1].trim().split(":")[1])
+    const s = Number(tokens[2].trim().split(":")[0]) / Number(tokens[2].trim().split(":")[1])
+
+    return (d + (m / 60) + (s / 3600)) * (ref === "S" || ref === "W" ? -1 : 1)
 }

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">2.10.3</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">2.10.3</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/tpool.c

@@ -27,6 +27,7 @@ typedef struct tpool {
     int thread_cnt;
     int work_cnt;
     int done_cnt;
+    int busy_cnt;
 
     int free_arg;
     int stop;
@@ -56,6 +57,7 @@ void tpool_dump_debug_info(tpool_t *pool) {
     LOG_DEBUGF("tpool.c", "pool->thread_cnt = %d", pool->thread_cnt)
     LOG_DEBUGF("tpool.c", "pool->work_cnt = %d", pool->work_cnt)
     LOG_DEBUGF("tpool.c", "pool->done_cnt = %d", pool->done_cnt)
+    LOG_DEBUGF("tpool.c", "pool->busy_cnt = %d", pool->busy_cnt)
     LOG_DEBUGF("tpool.c", "pool->stop = %d", pool->stop)
 }
 
@@ -127,6 +129,10 @@ static void *tpool_worker(void *arg) {
         }
 
         tpool_work_t *work = tpool_work_get(pool);
+        if (work != NULL) {
+            pool->busy_cnt += 1;
+        }
+
         pthread_mutex_unlock(&(pool->work_mutex));
 
         if (work != NULL) {
@@ -143,6 +149,7 @@ static void *tpool_worker(void *arg) {
 
         pthread_mutex_lock(&(pool->work_mutex));
         if (work != NULL) {
+            pool->busy_cnt -= 1;
             pool->done_cnt++;
         }
 
@@ -168,14 +175,14 @@ static void *tpool_worker(void *arg) {
 void tpool_wait(tpool_t *pool) {
     LOG_INFO("tpool.c", "Waiting for worker threads to finish")
     pthread_mutex_lock(&(pool->work_mutex));
-    while (1) {
+    while (TRUE) {
         if (pool->done_cnt < pool->work_cnt) {
             pthread_cond_wait(&(pool->working_cond), &(pool->work_mutex));
         } else {
-            usleep(500000);
+            LOG_INFOF("tpool.c", "Received head=NULL signal, busy_cnt=%d", pool->busy_cnt);
-            if (pool->done_cnt == pool->work_cnt) {
+
-                pool->stop = 1;
+            if (pool->done_cnt == pool->work_cnt && pool->busy_cnt == 0) {
-                usleep(1000000);
+                pool->stop = TRUE;
                 break;
             }
         }
@@ -195,12 +202,16 @@ void tpool_destroy(tpool_t *pool) {
 
     pthread_mutex_lock(&(pool->work_mutex));
     tpool_work_t *work = pool->work_head;
+    int count = 0;
     while (work != NULL) {
         tpool_work_t *tmp = work->next;
         free(work);
         work = tmp;
+        count += 1;
     }
 
+    LOG_DEBUGF("tpool.c", "Destroyed %d jobs", count);
+
     pthread_cond_broadcast(&(pool->has_work_cond));
     pthread_mutex_unlock(&(pool->work_mutex));
 
@@ -226,13 +237,14 @@ void tpool_destroy(tpool_t *pool) {
  * Create a thread pool
  * @param thread_cnt Worker threads count
  */
-tpool_t *tpool_create(size_t thread_cnt, void cleanup_func(), int free_arg) {
+tpool_t *tpool_create(int thread_cnt, void cleanup_func(), int free_arg) {
 
     tpool_t *pool = malloc(sizeof(tpool_t));
     pool->thread_cnt = thread_cnt;
     pool->work_cnt = 0;
     pool->done_cnt = 0;
-    pool->stop = 0;
+    pool->busy_cnt = 0;
+    pool->stop = FALSE;
     pool->free_arg = free_arg;
     pool->cleanup_func = cleanup_func;
     pool->threads = calloc(sizeof(pthread_t), thread_cnt);

src/tpool.h

@@ -8,7 +8,7 @@ typedef struct tpool tpool_t;
 
 typedef void (*thread_func_t)(void *arg);
 
-tpool_t *tpool_create(size_t num, void (*cleanup_func)(), int free_arg);
+tpool_t *tpool_create(int num, void (*cleanup_func)(), int free_arg);
 void tpool_start(tpool_t *pool);
 void tpool_destroy(tpool_t *pool);
 

src/web/serve.c

@@ -178,6 +178,9 @@ void thumbnail(struct mg_connection *nc, struct mg_http_message *hm) {
         send_response_line(nc, 200, data_len, "Content-Type: image/jpeg");
         mg_send(nc, data, data_len);
         free(data);
+    } else {
+        mg_http_reply(nc, 404, "Content-Type: text/plain;charset=utf-8\r\n", "Not found");
+        return;
     }
 }
 
@@ -220,7 +223,10 @@ 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 +537,7 @@ 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 +550,6 @@ 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 +580,6 @@ 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);

tests/test_scan.py

@@ -17,17 +17,19 @@ def copy_files(files):
 
 
 def sist2(*args):
+    print("./sist2 " + " ".join(args))
+
     return subprocess.check_output(
-        args=["./sist2_debug", *args],
+        args=["./sist2", *args],
     )
 
 
 def sist2_index(files, *args):
     path = copy_files(files)
 
-    shutil.rmtree("i", ignore_errors=True)
+    shutil.rmtree("test_i", ignore_errors=True)
-    sist2("scan", path, "-o", "i", *args)
+    sist2("scan", path, "-o", "test_i", *args)
-    return iter(sist2_index_to_dict("i"))
+    return iter(sist2_index_to_dict("test_i"))
 
 
 def sist2_incremental_index(files, func=None, *args):
@@ -36,14 +38,14 @@ def sist2_incremental_index(files, func=None, *args):
     if func:
         func(path)
 
-    shutil.rmtree("i_inc", ignore_errors=True)
+    shutil.rmtree("test_i_inc", ignore_errors=True)
-    sist2("scan", path, "-o", "i_inc", "--incremental", "i", *args)
+    sist2("scan", path, "-o", "test_i_inc", "--incremental", "test_i", *args)
-    return iter(sist2_index_to_dict("i_inc"))
+    return iter(sist2_index_to_dict("test_i_inc"))
 
 
 def sist2_index_to_dict(index):
     res = subprocess.check_output(
-        args=["./sist2_debug", "index", "--print", index],
+        args=["./sist2", "index", "--print", index],
     )
 
     for line in res.splitlines():