Update CI scripts, Dockerfiles, enable arm64 build again

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/
-      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)
 
@@ -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)* `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)
-   
-
-\* *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) |
-raw, rw2, dng, cr2, crw, dcr, k25, kdc, mrw, pef, xf3, arw, sr2, srf, erf  | LibRaw | - | yes | Common EXIF tags |
+`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, 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
- into smaller parts.
- 
- 
+  **sist2** is not I/O bound, scans might be faster when larger archives are split 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
-package manager (`apt install tesseract-ocr-eng`) or directly [from Github](https://github.com/tesseract-ocr/tesseract/wiki/Data-Files).
+`--ocr <lang>` option. Download the language data files with your package manager (`apt install tesseract-ocr-eng`) or
+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
-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
    ```
+   
+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
-cp /usr/lib/x86_64-linux-gnu/libasan.so.2.0.0 libasan.so.2
-mv sist2_debug sist2-x64-linux-debug
-tar -czf sist2-x64-linux-debug.tar.gz sist2-x64-linux-debug libasan.so.2
+make -j  $(nproc)
+mv sist2_debug sist2-x64-linux-debug

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

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"
     },

scripts/reset.sh

@@ -0,0 +1,6 @@
+#!/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

src/ctx.h

@@ -40,6 +40,8 @@ typedef struct {
     pcre_extra *exclude_extra;
     int fast;
 
+    GHashTable *dbg_current_files;
+
     scan_arc_ctx_t arc_ctx;
     scan_comic_ctx_t comic_ctx;
     scan_ebook_ctx_t ebook_ctx;

src/io/serialize.c

@@ -15,9 +15,13 @@ typedef struct {
     char has_parent;
 } line_t;
 
+#define META_NEXT 0xFFFF
+
 void skip_meta(FILE *file) {
-    enum metakey key = getc(file);
-    while (key != '\n') {
+    enum metakey key = 0;
+    fread(&key, sizeof(uint16_t), 1, file);
+
+    while (key != META_NEXT) {
         if (IS_META_INT(key)) {
             fseek(file, sizeof(int), SEEK_CUR);
         } else if (IS_META_LONG(key)) {
@@ -26,7 +30,7 @@ void skip_meta(FILE *file) {
             while ((getc(file))) {}
         }
 
-        key = getc(file);
+        fread(&key, sizeof(uint16_t), 1, file);
     }
 }
 
@@ -66,7 +70,7 @@ index_descriptor_t read_index_descriptor(char *path) {
     }
 
     char *buf = malloc(info.st_size + 1);
-    int ret = read(fd, buf, info.st_size);
+    size_t ret = read(fd, buf, info.st_size);
     if (ret == -1) {
         LOG_FATALF("serialize.c", "Could not read index descriptor: %s", strerror(errno));
     }
@@ -152,8 +156,20 @@ char *get_meta_key_text(enum metakey meta_key) {
             return "thumbnail";
         case MetaPages:
             return "pages";
+        case MetaExifGpsLongitudeRef:
+            return "exif_gps_longitude_ref";
+        case MetaExifGpsLongitudeDMS:
+            return "exif_gps_longitude_dms";
+        case MetaExifGpsLongitudeDec:
+            return "exif_gps_longitude_dec";
+        case MetaExifGpsLatitudeRef:
+            return "exif_gps_latitude_ref";
+        case MetaExifGpsLatitudeDMS:
+            return "exif_gps_latitude_dms";
+        case MetaExifGpsLatitudeDec:
+            return "exif_gps_latitude_dec";
         default:
-            return NULL;
+        LOG_FATALF("serialize.c", "FIXME: Unknown meta key: %d", meta_key)
     }
 }
 
@@ -183,7 +199,7 @@ void write_document(document_t *doc) {
 
     meta_line_t *meta = doc->meta_head;
     while (meta != NULL) {
-        dyn_buffer_write_char(&buf, meta->key);
+        dyn_buffer_write_short(&buf, (uint16_t) meta->key);
 
         if (IS_META_INT(meta->key)) {
             dyn_buffer_write_int(&buf, meta->int_val);
@@ -197,7 +213,7 @@ void write_document(document_t *doc) {
         meta = meta->next;
         free(tmp);
     }
-    dyn_buffer_write_char(&buf, '\n');
+    dyn_buffer_write_short(&buf, META_NEXT);
 
     int res = write(index_fd, buf.buf, buf.cur);
     if (res == -1) {
@@ -221,7 +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;
         }
@@ -268,9 +284,10 @@ void read_index_bin(const char *path, const char *index_id, index_func func) {
             cJSON_AddStringToObject(document, "path", "");
         }
 
-        enum metakey key = getc(file);
-        size_t ret = 0;
-        while (key != '\n') {
+        enum metakey key = 0;
+        fread(&key, sizeof(uint16_t), 1, file);
+        size_t ret;
+        while (key != META_NEXT) {
             switch (key) {
                 case MetaPages:
                 case MetaWidth:
@@ -308,6 +325,12 @@ void read_index_bin(const char *path, const char *index_id, index_func func) {
                 case MetaAuthor:
                 case MetaModifiedBy:
                 case MetaThumbnail:
+                case MetaExifGpsLongitudeDMS:
+                case MetaExifGpsLongitudeDec:
+                case MetaExifGpsLongitudeRef:
+                case MetaExifGpsLatitudeDMS:
+                case MetaExifGpsLatitudeDec:
+                case MetaExifGpsLatitudeRef:
                 case MetaTitle: {
                     buf.cur = 0;
                     while ((c = getc(file)) != 0) {
@@ -323,7 +346,7 @@ void read_index_bin(const char *path, const char *index_id, index_func func) {
                 LOG_FATALF("serialize.c", "Invalid meta key (corrupt index): %x", key)
             }
 
-            key = getc(file);
+            fread(&key, sizeof(uint16_t), 1, file);
         }
 
         cJSON *meta_obj = NULL;
@@ -458,7 +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);
@@ -508,11 +531,11 @@ void incremental_copy(store_t *store, store_t *dst_store, const char *filepath,
                 free(buf);
             }
 
-            enum metakey key;
+            enum metakey key = 0;
             while (1) {
-                key = getc(file);
-                fwrite(&key, sizeof(char), 1, dst_file);
-                if (key == '\n') {
+                fread(&key, sizeof(uint16_t), 1, file);
+                fwrite(&key, sizeof(uint16_t), 1, dst_file);
+                if (key == META_NEXT) {
                     break;
                 }
 

src/io/store.c

@@ -4,6 +4,7 @@
 store_t *store_create(char *path, size_t chunk_size) {
 
     store_t *store = malloc(sizeof(struct store_t));
+#if (SIST_FAKE_STORE != 1)
     store->chunk_size = chunk_size;
     pthread_rwlock_init(&store->lock, NULL);
 
@@ -28,15 +29,18 @@ store_t *store_create(char *path, size_t chunk_size) {
     mdb_txn_begin(store->env, NULL, 0, &txn);
     mdb_dbi_open(txn, NULL, 0, &store->dbi);
     mdb_txn_commit(txn);
+#endif
 
     return store;
 }
 
 void store_destroy(store_t *store) {
 
+#if (SIST_FAKE_STORE != 1)
     pthread_rwlock_destroy(&store->lock);
     mdb_close(store->env, store->dbi);
     mdb_env_close(store->env);
+#endif
     free(store);
 }
 
@@ -56,6 +60,8 @@ void store_write(store_t *store, char *key, size_t key_len, char *buf, size_t bu
         }
     }
 
+#if (SIST_FAKE_STORE != 1)
+
     MDB_val mdb_key;
     mdb_key.mv_data = key;
     mdb_key.mv_size = key_len;
@@ -92,10 +98,13 @@ void store_write(store_t *store, char *key, size_t key_len, char *buf, size_t bu
     if (put_ret != 0) {
         LOG_ERROR("store.c", mdb_strerror(put_ret))
     }
+#endif
 }
 
 char *store_read(store_t *store, char *key, size_t key_len, size_t *ret_vallen) {
     char *buf = NULL;
+
+#if (SIST_FAKE_STORE != 1)
     MDB_val mdb_key;
     mdb_key.mv_data = key;
     mdb_key.mv_size = key_len;
@@ -116,6 +125,7 @@ char *store_read(store_t *store, char *key, size_t key_len, size_t *ret_vallen)
     }
 
     mdb_txn_abort(txn);
+#endif
     return buf;
 }
 

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 = "2.9.1";
+static const char *const Version = "2.10.1";
 static const char *const usage[] = {
         "sist2 scan [OPTION]... PATH",
         "sist2 index [OPTION]... INDEX",
@@ -30,6 +30,69 @@ static const char *const usage[] = {
         NULL,
 };
 
+#include<signal.h>
+#include<unistd.h>
+
+static __sighandler_t sigsegv_handler = NULL;
+static __sighandler_t sigabrt_handler = NULL;
+
+void sig_handler(int signum) {
+
+    LogCtx.verbose = 1;
+    LogCtx.very_verbose = 1;
+
+    LOG_ERROR("*SIGNAL HANDLER*", "=============================================\n\n");
+    LOG_ERRORF("*SIGNAL HANDLER*", "Uh oh! Caught fatal signal: %s", strsignal(signum));
+
+    GHashTableIter iter;
+    g_hash_table_iter_init(&iter, ScanCtx.dbg_current_files);
+
+    void *key;
+    void *value;
+    while (g_hash_table_iter_next(&iter, &key, &value)) {
+        parse_job_t *job = value;
+
+        if (isatty(STDERR_FILENO)) {
+            LOG_DEBUGF(
+                    "*SIGNAL HANDLER*",
+                    "Thread \033[%dm[%04llX]\033[0m was working on job '%s'",
+                    31 + ((unsigned int) key) % 7, key, job->filepath
+            );
+        } else {
+            LOG_DEBUGF(
+                    "*SIGNAL HANDLER*",
+                    "THREAD [%04llX] was working on job %s",
+                    key, job->filepath
+            );
+        }
+    }
+
+    tpool_dump_debug_info(ScanCtx.pool);
+
+    LOG_INFO(
+            "*SIGNAL HANDLER*",
+            "Please consider creating a bug report at https://github.com/simon987/sist2/issues !"
+    )
+    LOG_INFO(
+            "*SIGNAL HANDLER*",
+            "sist2 is an open source project and relies on the collaboration of its users to diagnose and fix bugs"
+    )
+
+#ifndef SIST_DEBUG
+    LOG_WARNING(
+            "*SIGNAL HANDLER*",
+            "You are running sist2 in release mode! Please consider downloading the debug binary from the Github "
+            "releases page to provide additionnal information when submitting a bug report."
+    )
+#endif
+
+    if (signum == SIGSEGV && sigsegv_handler != NULL) {
+        sigsegv_handler(signum);
+    } else if (signum == SIGABRT && sigabrt_handler != NULL) {
+        sigabrt_handler(signum);
+    }
+}
+
 void init_dir(const char *dirpath) {
     char path[PATH_MAX];
     snprintf(path, PATH_MAX, "%sdescriptor.json", dirpath);
@@ -105,6 +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);
+
     // Comic
     ScanCtx.comic_ctx.log = _log;
     ScanCtx.comic_ctx.logf = _logf;
@@ -405,6 +470,9 @@ void sist2_web(web_args_t *args) {
 
 
 int main(int argc, const char *argv[]) {
+    sigsegv_handler = signal(SIGSEGV, sig_handler);
+    sigabrt_handler = signal(SIGABRT, sig_handler);
+
     setlocale(LC_ALL, "");
 
     scan_args_t *scan_args = scan_args_create();

src/parsing/parse.c

@@ -41,11 +41,18 @@ void fs_reset(struct vfile *f) {
 
 #define IS_GIT_OBJ (strlen(doc.filepath + doc.base) == 38 && (strstr(doc.filepath, "objects") != NULL))
 
+void set_dbg_current_file(parse_job_t *job) {
+    unsigned long long pid = (unsigned long long) pthread_self();
+    g_hash_table_replace(ScanCtx.dbg_current_files, GINT_TO_POINTER(pid), job);
+}
+
 void parse(void *arg) {
 
     parse_job_t *job = arg;
     document_t doc;
 
+    set_dbg_current_file(job);
+
     doc.filepath = job->filepath;
     doc.ext = (short) job->ext;
     doc.base = (short) job->base;

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/search.js

@@ -511,8 +511,8 @@ function search(after = null) {
         searchResults.appendChild(preload);
     }
 
-    let query = searchBar.value;
-    let empty = query === "";
+    let searchBarValue = searchBar.value;
+    let empty = searchBarValue === "";
     let condition = empty ? "should" : "must";
     let filters = [
         {range: {size: {gte: size_min, lte: size_max}}},
@@ -561,19 +561,32 @@ function search(after = null) {
         filters.push({range: {mtime: {lte: date_max}}})
     }
 
+    let query;
+    if (CONF.options.queryMode === "simple") {
+        query = {
+            simple_query_string: {
+                query: searchBarValue,
+                fields: fields,
+                default_operator: "and"
+            }
+        }
+    } else {
+        query = {
+            query_string: {
+                query: searchBarValue,
+                default_field: "name",
+                default_operator: "and"
+            }
+        }
+    }
+
     let q = {
         "_source": {
             excludes: ["content", "_tie"]
         },
         query: {
             bool: {
-                [condition]: {
-                    simple_query_string: {
-                        query: query,
-                        fields: fields,
-                        default_operator: "and"
-                    }
-                },
+                [condition]: query,
                 filter: filters
             }
         },
@@ -611,7 +624,9 @@ function search(after = null) {
         }
     }
 
-    $.jsonPost("es", q).then(searchResult => {
+    const showError = CONF.options.queryMode === "advanced";
+
+    $.jsonPost("es", q, showError).then(searchResult => {
         let hits = searchResult["hits"]["hits"];
         if (hits) {
             lastDoc = hits[hits.length - 1];
@@ -645,7 +660,25 @@ function search(after = null) {
         reachedEnd = hits.length !== SIZE;
         insertHits(resultContainer, hits);
         searchBusy = false;
-    });
+    }).fail(() => {
+        searchBusy = false;
+        if (!after) {
+            preload.remove();
+        }
+
+        console.log("QUERY:")
+        console.log(q)
+        $.toast({
+            heading: "Query error",
+            text: "Could not parse or execute query, please check the Advanced search documentation. " +
+                "See server logs for more information.",
+            stack: false,
+            bgColor: "#FF8F00",
+            textColor: "#FFF3E0",
+            position: 'bottom-right',
+            hideAfter: false
+        });
+    })
 }
 
 

src/static/js/util.js

@@ -70,7 +70,7 @@ function strUnescape(str) {
 
     for (let i = 0; i < str.length; i++) {
         const c = str[i];
-        const next = str[i+1];
+        const next = str[i + 1];
 
         if (c === ']') {
             if (next === ']') {
@@ -102,7 +102,8 @@ const _defaults = {
     treemapSize: "large",
     suggestPath: true,
     fragmentSize: 100,
-    columns: 5
+    columns: 5,
+    queryMode: "simple"
 };
 
 function loadSettings() {
@@ -120,6 +121,7 @@ function loadSettings() {
     $("#settingSuggestPath").prop("checked", CONF.options.suggestPath);
     $("#settingFragmentSize").val(CONF.options.fragmentSize);
     $("#settingColumns").val(CONF.options.columns);
+    $("#settingQueryMode").val(CONF.options.queryMode);
 }
 
 function Settings() {
@@ -127,6 +129,7 @@ function Settings() {
 
     this._onUpdate = function () {
         $("#fuzzyToggle").prop("checked", this.options.fuzzy);
+        $("#searchBar").attr("placeholder", this.options.queryMode === "simple" ? "Search" : "Advanced search");
         updateColumnStyle();
     };
 
@@ -165,6 +168,7 @@ function updateSettings() {
     CONF.options.suggestPath = $("#settingSuggestPath").prop("checked");
     CONF.options.fragmentSize = $("#settingFragmentSize").val();
     CONF.options.columns = $("#settingColumns").val();
+    CONF.options.queryMode = $("#settingQueryMode").val();
     CONF.save();
 
     if (typeof searchDebounced !== "undefined") {
@@ -187,14 +191,16 @@ function updateSettings() {
     });
 }
 
-jQuery["jsonPost"] = function (url, data) {
+jQuery["jsonPost"] = function (url, data, showError = true) {
     return jQuery.ajax({
         url: url,
         type: "post",
         data: JSON.stringify(data),
         contentType: "application/json"
     }).fail(err => {
-        showEsError();
+        if (showError) {
+            showEsError();
+        }
         console.log(err);
     });
 };
@@ -212,7 +218,7 @@ function updateColumnStyle() {
     const style = document.getElementById("style");
     if (style) {
         style.innerHTML =
-        `
+            `
 @media screen and (min-width: 1500px) {
     .container {
             max-width: 1440px;
@@ -229,4 +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">2.9.1</span>
+    <span class="badge badge-pill version">2.10.1</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
@@ -120,6 +120,8 @@
                 </div>
                 <div class="modal-body">
 
+                    <h2>Simple search</h2>
+
                     <table class="table">
                         <tbody>
                         <tr>
@@ -168,6 +170,12 @@
                     <p>For more information, see <a target="_blank"
                                                     href="//www.elastic.co/guide/en/elasticsearch/reference/current/query-dsl-simple-query-string-query.html">Elasticsearch
                         documentation</a></p>
+
+                    <h2>Advanced search</h2>
+                    <p>For documentation about the advanced search mode, see <a target="_blank"
+                                                                                href="//www.elastic.co/guide/en/elasticsearch/reference/current/query-dsl-query-string-query.html#query-string-syntax">Elasticsearch
+                        documentation</a></p>
+
                 </div>
             </div>
         </div>
@@ -207,10 +215,16 @@
 
                     <br/>
                     <div class="form-group">
-                        <input type="number" class="form-control" id="settingFragmentSize">
                         <label for="settingFragmentSize">Highlight context size in characters</label>
+                        <input type="number" class="form-control" id="settingFragmentSize">
                     </div>
 
+                    <label for="settingQueryMode">Search mode</label>
+                    <select id="settingQueryMode" class="form-control form-control-sm">
+                        <option value="simple">Simple</option>
+                        <option value="advanced">Advanced</option>
+                    </select>
+
                     <label for="settingDisplay">Display</label>
                     <select id="settingDisplay" class="form-control form-control-sm">
                         <option value="grid">Grid</option>

src/static/stats.html

@@ -10,7 +10,7 @@
 
 <nav class="navbar navbar-expand-lg">
     <a class="navbar-brand" href="/">sist2</a>
-    <span class="badge badge-pill version">2.9.1</span>
+    <span class="badge badge-pill version">2.10.1</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"
@@ -84,10 +84,16 @@
 
                 <br/>
                 <div class="form-group">
-                    <input type="number" class="form-control" id="settingFragmentSize">
                     <label for="settingFragmentSize">Highlight context size in characters</label>
+                    <input type="number" class="form-control" id="settingFragmentSize">
                 </div>
 
+                <label for="settingQueryMode">Search mode</label>
+                <select id="settingQueryMode" class="form-control form-control-sm">
+                    <option value="simple">Simple</option>
+                    <option value="advanced">Advanced</option>
+                </select>
+
                 <label for="settingDisplay">Display</label>
                 <select id="settingDisplay" class="form-control form-control-sm">
                     <option value="grid">Grid</option>

src/tpool.c

@@ -52,6 +52,13 @@ static tpool_work_t *tpool_work_create(thread_func_t func, void *arg) {
     return work;
 }
 
+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->stop = %d", pool->stop)
+}
+
 /**
  * Pop work object from thread pool
  */
@@ -83,7 +90,7 @@ int tpool_add_work(tpool_t *pool, thread_func_t func, void *arg) {
     }
 
     while ((pool->work_cnt - pool->done_cnt) >= MAX_QUEUE_SIZE) {
-        usleep(100000);
+        usleep(10000);
     }
 
     pthread_mutex_lock(&(pool->work_mutex));
@@ -150,6 +157,7 @@ static void *tpool_worker(void *arg) {
     if (pool->cleanup_func != NULL) {
         LOG_INFO("tpool.c", "Executing cleanup function")
         pool->cleanup_func();
+        LOG_DEBUG("tpool.c", "Done executing cleanup function")
     }
 
     pthread_cond_signal(&(pool->working_cond));

src/tpool.h

@@ -10,10 +10,12 @@ typedef void (*thread_func_t)(void *arg);
 
 tpool_t *tpool_create(size_t num, void (*cleanup_func)(), int free_arg);
 void tpool_start(tpool_t *pool);
-void tpool_destroy(tpool_t *tm);
+void tpool_destroy(tpool_t *pool);
 
 int tpool_add_work(tpool_t *pool, thread_func_t func, void *arg);
-void tpool_wait(tpool_t *tm);
+void tpool_wait(tpool_t *pool);
+
+void tpool_dump_debug_info(tpool_t *pool);
 
 #endif
 

src/web/serve.c

@@ -95,7 +95,7 @@ void stats_files(struct mg_connection *nc, struct mg_http_message *hm) {
     }
 
     char disposition[8192];
-    snprintf(disposition, sizeof(disposition), "Content-Disposition: inline; filename=\"%s\"", file);
+    snprintf(disposition, sizeof(disposition), "Content-Disposition: inline; filename=\"%s\"\r\n", file);
 
     char full_path[PATH_MAX];
     strcpy(full_path, index->path);
@@ -245,10 +245,10 @@ void serve_file_from_disk(cJSON *json, index_t *idx, struct mg_connection *nc, s
     LOG_DEBUGF("serve.c", "Serving file from disk: %s", full_path)
 
     char disposition[8192];
-    snprintf(disposition, sizeof(disposition), "Content-Disposition: inline; filename=\"%s%s%s\"",
+    snprintf(disposition, sizeof(disposition), "Content-Disposition: inline; filename=\"%s%s%s\"\r\n",
              name, strlen(ext) == 0 ? "" : ".", ext);
 
-    mg_http_serve_file(nc, hm, full_path, mime, "");
+    mg_http_serve_file(nc, hm, full_path, mime, disposition);
 }
 
 void index_info(struct mg_connection *nc) {
@@ -571,7 +571,7 @@ static void ev_router(struct mg_connection *nc, int ev, void *ev_data, UNUSED(vo
             file(nc, hm);
         } else if (mg_http_match_uri(hm, "/t/*/*")) {
             thumbnail(nc, hm);
-        } else if (mg_http_match_uri(hm, "/s/*")) {
+        } else if (mg_http_match_uri(hm, "/s/*/*")) {
             stats_files(nc, hm);
         } else if (mg_http_match_uri(hm, "/tag/*")) {
             if (WebCtx.tag_auth_enabled == TRUE && !validate_auth(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)
-    sist2("scan", path, "-o", "i", *args)
-    return iter(sist2_index_to_dict("i"))
+    shutil.rmtree("test_i", ignore_errors=True)
+    sist2("scan", path, "-o", "test_i", *args)
+    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)
-    sist2("scan", path, "-o", "i_inc", "--incremental", "i", *args)
-    return iter(sist2_index_to_dict("i_inc"))
+    shutil.rmtree("test_i_inc", ignore_errors=True)
+    sist2("scan", path, "-o", "test_i_inc", "--incremental", "test_i", *args)
+    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():