Merge d0ec304f7b5610d79be2f84cc461f796f1322012 into d800effad9dfbdd5fa00b6f012eba99095448f21

Update README.md

README.md

@@ -1,5 +1,5 @@
-![GitHub](https://img.shields.io/github/license/simon987/sist2.svg)
+![GitHub](https://img.shields.io/github/license/sist2app/sist2.svg)
-[![CodeFactor](https://www.codefactor.io/repository/github/simon987/sist2/badge?s=05daa325188aac4eae32c786f3d9cf4e0593f822)](https://www.codefactor.io/repository/github/simon987/sist2)
+[![CodeFactor](https://www.codefactor.io/repository/github/sist2app/sist2/badge?s=05daa325188aac4eae32c786f3d9cf4e0593f822)](https://www.codefactor.io/repository/github/sist2app/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/)
@@ -38,26 +38,22 @@ sist2 (Simple incremental search tool)
 ### Using Docker Compose *(Windows/Linux/Mac)*
 
 ```yaml
-version: "3"
-
 services:
   elasticsearch:
     image: elasticsearch:7.17.9
     restart: unless-stopped
     volumes:
-      # This directory must have 1000:1000 permissions (or update PUID & PGID below)
+      # This directory must have 1000:1000 permissions
       - /data/sist2-es-data/:/usr/share/elasticsearch/data
     environment:
       - "discovery.type=single-node"
       - "ES_JAVA_OPTS=-Xms2g -Xmx2g"
-      - "PUID=1000"
-      - "PGID=1000"
   sist2-admin:
-    image: simon987/sist2:3.4.2-x64-linux
+    image: sist2app/sist2:x64-linux
     restart: unless-stopped
     volumes:
       - /data/sist2-admin-data/:/sist2-admin/
-      - /:/host
+      - /<path to index>/:/host
     ports:
       - 4090:4090
       # NOTE: Don't expose this port publicly!
@@ -81,7 +77,7 @@ Navigate to http://localhost:8080/ to configure sist2-admin.
             ```
     * **SQLite**: No installation required
 
-2. Download the [latest sist2 release](https://github.com/simon987/sist2/releases).
+2. Download the [latest sist2 release](https://github.com/sist2app/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.
 
@@ -100,20 +96,20 @@ Example usage:
 | File type                                                                 | Library                                                                      | Content  | Thumbnail   | Metadata                                                                                                                               |
 |:--------------------------------------------------------------------------|:-----------------------------------------------------------------------------|:---------|:------------|:---------------------------------------------------------------------------------------------------------------------------------------|
 | pdf,xps,fb2,epub                                                          | MuPDF                                                                        | text+ocr | yes         | author, title                                                                                                                          |
-| cbz,cbr                                                                   | [libscan](https://github.com/simon987/sist2/tree/master/third-party/libscan) | -        | yes         | -                                                                                                                                      |
+| cbz,cbr                                                                   | [libscan](https://github.com/sist2app/sist2/tree/master/third-party/libscan) | -        | yes         | -                                                                                                                                      |
 | `audio/*`                                                                 | ffmpeg                                                                       | -        | yes         | ID3 tags                                                                                                                               |
 | `video/*`                                                                 | ffmpeg                                                                       | -        | yes         | title, comment, artist                                                                                                                 |
-| `image/*`                                                                 | ffmpeg                                                                       | ocr      | yes         | [Common EXIF tags](https://github.com/simon987/sist2/blob/efdde2734eca9b14a54f84568863b7ffd59bdba3/src/parsing/media.c#L190), GPS tags |
+| `image/*`                                                                 | ffmpeg                                                                       | ocr      | yes         | [Common EXIF tags](https://github.com/sist2app/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                                                                       | no       | yes         | Common EXIF tags, GPS tags                                                                                                             |
 | ttf,ttc,cff,woff,fnt,otf                                                  | Freetype2                                                                    | -        | yes, `bmp`  | Name & style                                                                                                                           |
-| `text/plain`                                                              | [libscan](https://github.com/simon987/sist2/tree/master/third-party/libscan) | yes      | no          | -                                                                                                                                      |
+| `text/plain`                                                              | [libscan](https://github.com/sist2app/sist2/tree/master/third-party/libscan) | yes      | no          | -                                                                                                                                      |
-| html, xml                                                                 | [libscan](https://github.com/simon987/sist2/tree/master/third-party/libscan) | yes      | no          | -                                                                                                                                      |
+| html, xml                                                                 | [libscan](https://github.com/sist2app/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                                                                                                            |
+| docx, xlsx, pptx                                                          | [libscan](https://github.com/sist2app/sist2/tree/master/third-party/libscan) | yes      | if embedded | creator, modified_by, 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      | -           | -                                                                                                                                      |
+| json, jsonl, ndjson                                                       | [libscan](https://github.com/sist2app/sist2/tree/master/third-party/libscan) | yes      | -           | -                                                                                                                                      |
 
 \* *See [Archive files](#archive-files)*
 
@@ -137,7 +133,7 @@ You can enable OCR support for ebook (pdf,xps,fb2,epub) or image file types with
 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 `sist2app/sist2` image comes with common languages
 (hin, jpn, eng, fra, rus, spa, chi_sim, deu, pol) pre-installed.
 
 You can use the `+` separator to specify multiple languages. The language
@@ -177,13 +173,13 @@ sist2 v3.0.4+ supports named-entity recognition (NER). Simply add a supported re
 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.
+See [sist2app/sist2-ner-models](https://github.com/sist2app/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 |
+| [sist2app/sist2-ner-models](https://raw.githubusercontent.com/sist2app/sist2-ner-models/main/repo.json) | [sist2app](https://github.com/sist2app) | General |
 
 <details>
   <summary>Screenshot</summary>
@@ -199,7 +195,7 @@ You can compile **sist2** by yourself if you don't want to use the pre-compiled
 ### Using docker
 
 ```bash
-git clone --recursive https://github.com/simon987/sist2/
+git clone --recursive https://github.com/sist2app/sist2/
 cd sist2
 docker build . -t my-sist2-image
 # Copy sist2 executable from docker image
@@ -214,7 +210,7 @@ docker run --rm --entrypoint cat my-sist2-image /root/sist2 > sist2-x64-linux
    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
    ```
 
-2. Install vcpkg using my fork: https://github.com/simon987/vcpkg
+2. Install vcpkg using my fork: https://github.com/sist2app/vcpkg
 3. Install vcpkg dependencies
 
     ```bash
@@ -223,7 +219,7 @@ docker run --rm --entrypoint cat my-sist2-image /root/sist2 > sist2-x64-linux
 
 4. Build
     ```bash
-    git clone --recursive https://github.com/simon987/sist2/
+    git clone --recursive https://github.com/sist2app/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 .

docker-compose.yml

@@ -5,20 +5,18 @@ services:
     image: elasticsearch:7.17.9
     container_name: sist2-es
     volumes:
-      # This directory must have 1000:1000 permissions (or update PUID & PGID below)
+      # This directory must have 1000:1000 permissions
       - /data/sist2-es-data/:/usr/share/elasticsearch/data
     environment:
       - "discovery.type=single-node"
       - "ES_JAVA_OPTS=-Xms2g -Xmx2g"
-      - "PUID=1000"
-      - "PGID=1000"
   sist2-admin:
     build:
       context: .
     container_name: sist2-admin
     volumes:
       - /data/sist2-admin-data/:/sist2-admin/
-      - /:/host
+      - /<path to index>/:/host
     ports:
       - 4090:4090
       # NOTE: Don't export this port publicly!

scripts/magic_static.py

@@ -1,5 +1,16 @@
 
-with open("/usr/lib/file/magic.mgc", "rb") as f:
+MAGIC_PATHS = [
-    data = f.read()
+    "/vcpkg/installed/x64-linux/share/libmagic/misc/magic.mgc",
+    "/work/vcpkg/installed/x64-linux/share/libmagic/misc/magic.mgc",
+    "/usr/lib/file/magic.mgc"
+]
+
+for path in MAGIC_PATHS:
+    try:
+        with open(path, "rb") as f:
+            data = f.read()
+        break
+    except:
+        continue
 
 print("char magic_database_buffer[%d] = {%s};" % (len(data), ",".join(str(int(b)) for b in data)))

sist2-vue/src/Sist2Api.js

@@ -309,7 +309,7 @@ class Sist2Api {
     }
 
     getTagsSqlite() {
-        return axios.get(`${this.baseUrl}/fts/tags`)
+        return axios.get(`${this.baseUrl}fts/tags`)
             .then(resp => {
                 return resp.data.map(tag => this._createEsTag(tag.tag, tag.count))
             });
@@ -566,7 +566,7 @@ class Sist2Api {
     }
 
     getDocumentSqlite(sid) {
-        return axios.get(`${this.baseUrl}/fts/d/${sid}`)
+        return axios.get(`${this.baseUrl}fts/d/${sid}`)
             .then(resp => ({
                 _source: resp.data
             }));
@@ -589,7 +589,7 @@ class Sist2Api {
     }
 
     getTagSuggestionsSqlite(prefix) {
-        return axios.post(`${this.baseUrl}/fts/suggestTags`, prefix)
+        return axios.post(`${this.baseUrl}fts/suggestTags`, prefix)
             .then(resp => (resp.data));
     }
 
@@ -620,7 +620,7 @@ class Sist2Api {
     }
 
     getEmbeddings(sid, modelId) {
-        return axios.post(`${this.baseUrl}/e/${sid}/${modelId.toString().padStart(3, '0')}`)
+        return axios.post(`${this.baseUrl}e/${sid}/${modelId.toString().padStart(3, '0')}`)
             .then(resp => (resp.data));
     }
 }

sist2-vue/src/Sist2ElasticsearchQuery.js

@@ -117,11 +117,11 @@ class Sist2ElasticsearchQuery {
             }
 
             if (dateMin && dateMax) {
-                filters.push({range: {mtime: {gte: dateMin, lte: dateMax}}})
+                filters.push({range: {mtime: {gte: dateMin, lte: dateMax, format: "epoch_second"}}})
             } else if (dateMin) {
-                filters.push({range: {mtime: {gte: dateMin}}})
+                filters.push({range: {mtime: {gte: dateMin, format: "epoch_second"}}})
             } else if (dateMax) {
-                filters.push({range: {mtime: {lte: dateMax}}})
+                filters.push({range: {mtime: {lte: dateMax, format: "epoch_second"}}})
             }
 
             const path = pathText.replace(/\/$/, "").toLowerCase(); //remove trailing slashes

src/cli.c

@@ -25,6 +25,7 @@ const char *TESS_DATAPATHS[] = {
         "/usr/share/tessdata/",
         "/usr/share/tesseract-ocr/tessdata/",
         "/usr/share/tesseract-ocr/4.00/tessdata/",
+        "/usr/share/tesseract-ocr/5/tessdata/",
         "./",
         NULL
 };

src/sist.h

@@ -55,7 +55,7 @@
 static const char *const Version = VERSION;
 static const int VersionMajor = 3;
 static const int VersionMinor = 4;
-static const int VersionPatch = 2;
+static const int VersionPatch = 3;
 
 #ifndef SIST_PLATFORM
 #define SIST_PLATFORM unknown

third-party/libscan/libscan/ebook/ebook.c

@@ -175,9 +175,19 @@ int render_cover(scan_ebook_ctx_t *ctx, fz_context *fzctx, document_t *doc, fz_d
     return TRUE;
 }
 
+#define IS_IGNORED_MESSAGE(message)           \
+    (                                          \
+        strstr(message, "invalid glyph index") \
+        || strstr(message, "... repeated")     \
+    )                                          \
+
 void fz_err_callback(void *user, const char *message) {
     document_t *doc = (document_t *) user;
 
+    if (IS_IGNORED_MESSAGE(message)) {
+        return;
+    }
+
     const scan_ebook_ctx_t *ctx = &thread_ctx;
     CTX_LOG_WARNINGF(doc->filepath, "FZ: %s", message);
 }
@@ -185,6 +195,10 @@ void fz_err_callback(void *user, const char *message) {
 void fz_warn_callback(void *user, const char *message) {
     document_t *doc = (document_t *) user;
 
+    if (IS_IGNORED_MESSAGE(message)) {
+        return;
+    }
+
     const scan_ebook_ctx_t *ctx = &thread_ctx;
     CTX_LOG_DEBUGF(doc->filepath, "FZ: %s", message);
 }

third-party/libscan/libscan/media/media.c

@@ -223,14 +223,10 @@ read_frame(scan_media_ctx_t *ctx, AVFormatContext *pFormatCtx, AVCodecContext *d
 
 void append_tag_meta_if_not_exists(scan_media_ctx_t *ctx, document_t *doc, AVDictionaryEntry *tag, enum metakey key) {
 
-    meta_line_t *meta = doc->meta_head;
+    if (meta_contains_key(doc->meta_head, key)) {
-    while (meta != NULL) {
+        CTX_LOG_DEBUGF(doc->filepath, "Ignoring duplicate tag: '%02x=%s'",
-        if (meta->key == key) {
+                       key, tag->value);
-            CTX_LOG_DEBUGF(doc->filepath, "Ignoring duplicate tag: '%02x=%s' and '%02x=%s'",
+        return;
-                           key, meta->str_val, key, tag->value);
-            return;
-        }
-        meta = meta->next;
     }
 
     text_buffer_t tex = text_buffer_create(-1);
@@ -445,7 +441,7 @@ int decode_frame_and_save_thumbnail(scan_media_ctx_t *ctx, AVFormatContext *pFor
         return SAVE_THUMBNAIL_FAILED;
     }
 
-    if (ctx->tesseract_lang != NULL && thumbnail_index == 0) {
+    if (ctx->tesseract_lang != NULL && thumbnail_index == 0 && !meta_contains_key(doc->meta_head, MetaContent)) {
         ocr_image(ctx, doc, decoder, frame_and_packet->frame);
     }
 

third-party/libscan/libscan/util.h

@@ -392,4 +392,18 @@ static parse_job_t *create_parse_job(const char *filepath, int mtime, size_t st_
     return job;
 }
 
+
+static int meta_contains_key (meta_line_t *meta_head, enum metakey key) {
+
+    meta_line_t *meta = meta_head;
+    while (meta != NULL) {
+        if (meta->key == key) {
+            return TRUE;
+        }
+        meta = meta->next;
+    }
+
+    return FALSE;
+}
+
 #endif