Merge d0ec304f7b5610d79be2f84cc461f796f1322012 into 7873ef003d7b09e8a3eb4bb4c7ef4473deac30a2

.drone.yml

@@ -7,11 +7,36 @@ platform:
   arch: amd64
 
 steps:
+  - name: submodules
+    image: alpine/git
+    commands:
+      - git submodule update --init --recursive
+  - name: docker
+    image: plugins/docker
+    depends_on:
+      - submodules
+    settings:
+      username:
+        from_secret: DOCKER_USER
+      password:
+        from_secret: DOCKER_PASSWORD
+      repo: sist2app/sist2
+      context: ./
+      dockerfile: ./Dockerfile
+      auto_tag: true
+      auto_tag_suffix: x64-linux
+      when:
+        event:
+          - tag
   - name: build
-    image: simon987/sist2-build
+    image: sist2app/sist2-build
+    depends_on:
+    - submodules
     commands:
       - ./scripts/build.sh
   - name: scp files
+    depends_on:
+      - build
     image: appleboy/drone-scp
     settings:
       host:
@@ -22,26 +47,11 @@ steps:
         from_secret: SSH_USER
       key:
         from_secret: SSH_KEY
-      target: /files/sist2/${DRONE_REPO_OWNER}_${DRONE_REPO_NAME}/${DRONE_BRANCH}_${DRONE_BUILD_NUMBER}_${DRONE_COMMIT}/
+      target: ~/files/sist2/${DRONE_REPO_OWNER}_${DRONE_REPO_NAME}/${DRONE_BRANCH}_${DRONE_BUILD_NUMBER}_${DRONE_COMMIT}/
       source:
         - ./VERSION
         - ./sist2-x64-linux
         - ./sist2-x64-linux-debug
-  - name: docker
-    image: plugins/docker
-    settings:
-      username:
-        from_secret: DOCKER_USER
-      password:
-        from_secret: DOCKER_PASSWORD
-      repo: simon987/sist2
-      context: ./
-      dockerfile: ./Dockerfile
-      auto_tag: true
-      auto_tag_suffix: x64-linux
-      when:
-        event:
-          - tag
 
 ---
 kind: pipeline
@@ -52,11 +62,36 @@ platform:
   arch: arm64
 
 steps:
+  - name: submodules
+    image: alpine/git
+    commands:
+      - git submodule update --init --recursive
+  - name: docker
+    image: plugins/docker
+    depends_on:
+      - submodules
+    settings:
+      username:
+        from_secret: DOCKER_USER
+      password:
+        from_secret: DOCKER_PASSWORD
+      repo: sist2app/sist2
+      context: ./
+      dockerfile: ./Dockerfile.arm64
+      auto_tag: true
+      auto_tag_suffix: arm64-linux
+      when:
+        event:
+          - tag
   - name: build
-    image: simon987/sist2-build-arm64
+    image: sist2app/sist2-build-arm64
+    depends_on:
+      - submodules
     commands:
       - ./scripts/build_arm64.sh
   - name: scp files
+    depends_on:
+      - build
     image: appleboy/drone-scp
     settings:
       host:
@@ -67,22 +102,7 @@ steps:
         from_secret: SSH_USER
       key:
         from_secret: SSH_KEY
-      target: /files/sist2/${DRONE_REPO_OWNER}_${DRONE_REPO_NAME}/arm_${DRONE_BRANCH}_${DRONE_BUILD_NUMBER}_${DRONE_COMMIT}/
+      target: ~/files/sist2/${DRONE_REPO_OWNER}_${DRONE_REPO_NAME}/arm_${DRONE_BRANCH}_${DRONE_BUILD_NUMBER}_${DRONE_COMMIT}/
       source:
         - ./sist2-arm64-linux
         - ./sist2-arm64-linux-debug
-  - name: docker
-    image: plugins/docker
-    settings:
-      username:
-        from_secret: DOCKER_USER
-      password:
-        from_secret: DOCKER_PASSWORD
-      repo: simon987/sist2
-      context: ./
-      dockerfile: ./Dockerfile.arm64
-      auto_tag: true
-      auto_tag_suffix: arm64-linux
-      when:
-        event:
-          - tag

CMakeLists.txt

@@ -147,6 +147,7 @@ add_dependencies(
 target_link_libraries(
         sist2
 
+        m
         z
         argparse
         unofficial::mongoose::mongoose

Dockerfile

@@ -1,5 +1,4 @@
-FROM simon987/sist2-build as build
-MAINTAINER simon987 <me@simon987.net>
+FROM sist2app/sist2-build as build
 
 WORKDIR /build/
 

Dockerfile.arm64

@@ -1,5 +1,4 @@
-FROM simon987/sist2-build-arm64 as build
-MAINTAINER simon987 <me@simon987.net>
+FROM sist2app/sist2-build-arm64 as build
 
 WORKDIR /build/
 

docs/USAGE.md

@@ -189,7 +189,7 @@ Since v3.2.0, User scripts can be used to generate _embeddings_ (vector of float
 
 In theory, embeddings can be created for any type of documents (image, text, audio etc.).
 
-For example, the [clip](https://github.com/simon987/sist2-script-clip) User Script, generates 512-d embeddings of images
+For example, the [clip](https://github.com/sist2app/sist2-script-clip) User Script, generates 512-d embeddings of images
 (videos are also supported using the thumbnails generated by sist2). When the user enters a query in the "Embeddings Search"
 textbox, the query's embedding is generated in their browser, leveraging the ONNX web runtime.
 

scripts/build.sh

@@ -2,8 +2,6 @@
 
 VCPKG_ROOT="/vcpkg"
 
-git submodule update --init --recursive
-
 (
   cd sist2-vue/
   npm install

scripts/magic_static.py

@@ -1,8 +1,5 @@
 
-try:
-    with open("/usr/lib/file/magic.mgc", "rb") as f:
-        data = f.read()
-except:
-    data = bytes([])
+with open("/usr/lib/file/magic.mgc", "rb") as f:
+    data = f.read()
 
 print("char magic_database_buffer[%d] = {%s};" % (len(data), ",".join(str(int(b)) for b in data)))

sist2-admin/frontend/src/App.vue

@@ -4,7 +4,7 @@
         <b-container class="pt-4">
             <b-alert show dismissible variant="info">
                 This is a beta version of sist2-admin. Please submit bug reports, usability issues and feature requests
-                to the <a href="https://github.com/simon987/sist2/issues/new/choose" target="_blank">issue tracker on
+                to the <a href="https://github.com/sist2app/sist2/issues/new/choose" target="_blank">issue tracker on
                 Github</a>. Thank you!
             </b-alert>
             <router-view v-if="$store.state.sist2AdminInfo"/>

sist2-admin/requirements.txt

@@ -4,4 +4,4 @@ uvicorn
 websockets
 pycron
 GitPython
-git+https://github.com/simon987/sist2-python.git
+git+https://github.com/sist2app/sist2-python.git

sist2-admin/sist2_admin/script.py

@@ -96,7 +96,7 @@ SCRIPT_TEMPLATES = {
     "CLIP - Generate embeddings to predict the most relevant image based on the text prompt": lambda name: UserScript(
         name=name,
         type=ScriptType.GIT,
-        git_repository="https://github.com/simon987/sist2-script-clip",
+        git_repository="https://github.com/sist2app/sist2-script-clip",
         extra_args="--num-tags=1 --tags-file=general.txt --color=#dcd7ff"
     ),
     "Whisper - Speech to text with OpenAI Whisper": lambda name: UserScript(

sist2-vue/src/components/NavBar.vue

@@ -9,7 +9,7 @@
 
     <span class="badge badge-pill version" v-if="$store && $store.state.sist2Info">
       v{{ sist2Version() }}<span v-if="isDebug()">-dbg</span><span v-if="isLegacy() && !hideLegacy()">-<a
-        href="https://github.com/simon987/sist2/blob/master/docs/USAGE.md#elasticsearch"
+        href="https://github.com/sist2app/sist2/blob/master/docs/USAGE.md#elasticsearch"
         target="_blank">legacyES</a></span><span v-if="$store.state.uiSqliteMode">-SQLite</span>
     </span>
 

sist2-vue/src/i18n/messages.js

@@ -138,7 +138,7 @@ export default {
         },
         debug: "Debug information",
         debugDescription: "Information useful for debugging. If you encounter bugs or have suggestions for" +
-            " new features, please submit a new issue <a href='https://github.com/simon987/sist2/issues/new/choose'>here</a>.",
+            " new features, please submit a new issue <a href='https://github.com/sist2app/sist2/issues/new/choose'>here</a>.",
         tagline: "Tagline",
         toast: {
             esConnErrTitle: "Elasticsearch connection error",
@@ -318,7 +318,7 @@ export default {
         },
         debug: "Debug Informationen",
         debugDescription: "Informationen für das Debugging. Wenn du Bugs gefunden oder Anregungen für " +
-            "neue Features hast, poste sie bitte <a href='https://github.com/simon987/sist2/issues/new/choose'>hier</a>.",
+            "neue Features hast, poste sie bitte <a href='https://github.com/sist2app/sist2/issues/new/choose'>hier</a>.",
         tagline: "Tagline",
         toast: {
             esConnErrTitle: "Elasticsearch Verbindungsfehler",
@@ -494,7 +494,7 @@ export default {
         debug: "Information de débogage",
         debugDescription: "Informations utiles pour le débogage\n" +
             "Si vous rencontrez des bogues ou si vous avez des suggestions pour de nouvelles fonctionnalités," +
-            " veuillez soumettre un nouvel Issue <a href='https://github.com/simon987/sist2/issues/new/choose'>ici</a>.",
+            " veuillez soumettre un nouvel Issue <a href='https://github.com/sist2app/sist2/issues/new/choose'>ici</a>.",
         tagline: "Tagline",
         toast: {
             esConnErrTitle: "Erreur de connexion Elasticsearch",
@@ -668,7 +668,7 @@ export default {
         },
         debug: "调试信息",
         debugDescription: "对调试除错有用的信息。 若您遇到bug或者想建议新功能，请提交新Issue到" +
-            "<a href='https://github.com/simon987/sist2/issues/new/choose'>这里</a>.",
+            "<a href='https://github.com/sist2app/sist2/issues/new/choose'>这里</a>.",
         tagline: "标签栏",
         toast: {
             esConnErrTitle: "Elasticsearch连接错误",
@@ -846,7 +846,7 @@ export default {
         },
         debug: "Informacje dla programistów",
         debugDescription: "Informacje przydatne do znajdowania błędów w oprogramowaniu. Jeśli napotkasz błąd lub masz" +
-            " propozycje zmian, zgłoś to proszę <a href='https://github.com/simon987/sist2/issues/new/choose'>tutaj</a>.",
+            " propozycje zmian, zgłoś to proszę <a href='https://github.com/sist2app/sist2/issues/new/choose'>tutaj</a>.",
         tagline: "Slogan",
         toast: {
             esConnErrTitle: "Problem z połączeniem z Elasticsearch",

sist2-vue/src/store/index.js

@@ -58,7 +58,7 @@ export default new Vuex.Store({
         optVidPreviewInterval: 700,
         optSimpleLightbox: true,
         optShowTagPickerFilter: true,
-        optMlRepositories: "https://raw.githubusercontent.com/simon987/sist2-ner-models/main/repo.json",
+        optMlRepositories: "https://raw.githubusercontent.com/sist2app/sist2-ner-models/main/repo.json",
         optAutoAnalyze: false,
         optMlDefaultModel: null,
 

src/database/database.c

@@ -478,8 +478,7 @@ index_descriptor_t *database_read_index_descriptor(database_t *db) {
 database_iterator_t *database_create_delete_list_iterator(database_t *db) {
 
     sqlite3_stmt *stmt;
-    sqlite3_prepare_v2(db->db, "SELECT doc.id FROM delete_list "
-                               "INNER JOIN document doc ON doc.ROWID = delete_list.id;", -1, &stmt, NULL);
+    sqlite3_prepare_v2(db->db, "SELECT id FROM delete_list", -1, &stmt, NULL);
 
     database_iterator_t *iter = malloc(sizeof(database_iterator_t));
 

src/parsing/parse.c

@@ -161,7 +161,8 @@ void parse(parse_job_t *job) {
         return;
     }
 
-    if (database_mark_document(ProcData.index_db, doc->filepath + ScanCtx.index.desc.root_len, doc->mtime)) {
+    int document_exists = database_mark_document(ProcData.index_db, doc->filepath + ScanCtx.index.desc.root_len, doc->mtime);
+    if (document_exists) {
         CLOSE_FILE(job->vfile)
         free(doc);
         return;

src/sist.h

@@ -61,7 +61,7 @@ static const int VersionPatch = 2;
 #define SIST_PLATFORM unknown
 #endif
 
-#define EXPECTED_MONGOOSE_VERSION "7.13"
+#define EXPECTED_MONGOOSE_VERSION "7.16"
 
 #define Q(x) #x
 #define QUOTE(x) Q(x)

src/web/serve.c

@@ -50,13 +50,13 @@ void get_embedding(struct mg_connection *nc, struct mg_http_message *hm) {
 
     sist_id_t sid;
 
-    if (hm->uri.len != SIST_SID_LEN + 2 + 4 || !parse_sid(&sid, hm->uri.ptr + 3)) {
-        LOG_DEBUGF("serve.c", "Invalid embedding path: %.*s", (int) hm->uri.len, hm->uri.ptr);
+    if (hm->uri.len != SIST_SID_LEN + 2 + 4 || !parse_sid(&sid, hm->uri.buf + 3)) {
+        LOG_DEBUGF("serve.c", "Invalid embedding path: %.*s", (int) hm->uri.len, hm->uri.buf);
         HTTP_REPLY_NOT_FOUND
         return;
     }
 
-    int model_id = (int) strtol(hm->uri.ptr + SIST_SID_LEN + 3, NULL, 10);
+    int model_id = (int) strtol(hm->uri.buf + SIST_SID_LEN + 3, NULL, 10);
 
     database_t *db = web_get_database(sid.index_id);
     if (db == NULL) {
@@ -86,11 +86,11 @@ void stats_files(struct mg_connection *nc, struct mg_http_message *hm) {
     char index_id_str[9];
     char arg_stat_type[5];
 
-    memcpy(index_id_str, hm->uri.ptr + 3, 8);
+    memcpy(index_id_str, hm->uri.buf + 3, 8);
     *(index_id_str + 8) = '\0';
     int index_id = (int) strtol(index_id_str, NULL, 16);
 
-    memcpy(arg_stat_type, hm->uri.ptr + 3 + 9, 4);
+    memcpy(arg_stat_type, hm->uri.buf + 3 + 9, 4);
     *(arg_stat_type + sizeof(arg_stat_type) - 1) = '\0';
 
     database_stat_type_d stat_type = database_get_stat_type_by_mnemonic(arg_stat_type);
@@ -135,19 +135,19 @@ void serve_chunk_vendors_js(struct mg_connection *nc, struct mg_http_message *hm
     }
 }
 
-void serve_favicon_ico(struct mg_connection *nc, struct mg_http_message *hm) {
+void serve_favicon_ico(struct mg_connection *nc, UNUSED(struct mg_http_message *hm)) {
     web_serve_asset_favicon_ico(nc);
 }
 
-void serve_style_css(struct mg_connection *nc, struct mg_http_message *hm) {
+void serve_style_css(struct mg_connection *nc, UNUSED(struct mg_http_message *hm)) {
     web_serve_asset_style_css(nc);
 }
 
-void serve_chunk_vendors_css(struct mg_connection *nc, struct mg_http_message *hm) {
+void serve_chunk_vendors_css(struct mg_connection *nc, UNUSED(struct mg_http_message *hm)) {
     web_serve_asset_chunk_vendors_css(nc);
 }
 
-void serve_thumbnail(struct mg_connection *nc, struct mg_http_message *hm, int index_id,
+void serve_thumbnail(struct mg_connection *nc, UNUSED(struct mg_http_message *hm), int index_id,
                      int doc_id, int arg_num) {
 
     database_t *db = web_get_database(index_id);
@@ -179,13 +179,13 @@ void serve_thumbnail(struct mg_connection *nc, struct mg_http_message *hm, int i
 void thumbnail_with_num(struct mg_connection *nc, struct mg_http_message *hm) {
     sist_id_t sid;
 
-    if (hm->uri.len != SIST_SID_LEN + 2 + 4 || !parse_sid(&sid, hm->uri.ptr + 3)) {
-        LOG_DEBUGF("serve.c", "Invalid thumbnail path: %.*s", (int) hm->uri.len, hm->uri.ptr);
+    if (hm->uri.len != SIST_SID_LEN + 2 + 4 || !parse_sid(&sid, hm->uri.buf + 3)) {
+        LOG_DEBUGF("serve.c", "Invalid thumbnail path: %.*s", (int) hm->uri.len, hm->uri.buf);
         HTTP_REPLY_NOT_FOUND
         return;
     }
 
-    int num = (int) strtol(hm->uri.ptr + SIST_SID_LEN + 3, NULL, 10);
+    int num = (int) strtol(hm->uri.buf + SIST_SID_LEN + 3, NULL, 10);
 
     serve_thumbnail(nc, hm, sid.index_id, sid.doc_id, num);
 }
@@ -193,8 +193,8 @@ void thumbnail_with_num(struct mg_connection *nc, struct mg_http_message *hm) {
 void thumbnail(struct mg_connection *nc, struct mg_http_message *hm) {
     sist_id_t sid;
 
-    if (hm->uri.len != 20 || !parse_sid(&sid, hm->uri.ptr + 3)) {
-        LOG_DEBUGF("serve.c", "Invalid thumbnail path: %.*s", (int) hm->uri.len, hm->uri.ptr);
+    if (hm->uri.len != 20 || !parse_sid(&sid, hm->uri.buf + 3)) {
+        LOG_DEBUGF("serve.c", "Invalid thumbnail path: %.*s", (int) hm->uri.len, hm->uri.buf);
         HTTP_REPLY_NOT_FOUND
         return;
     }
@@ -210,7 +210,7 @@ void search(struct mg_connection *nc, struct mg_http_message *hm) {
     }
 
     char *body = malloc(hm->body.len + 1);
-    memcpy(body, hm->body.ptr, hm->body.len);
+    memcpy(body, hm->body.buf, hm->body.len);
     *(body + hm->body.len) = '\0';
 
     char url[4096];
@@ -416,8 +416,8 @@ cJSON *get_root_document_by_id(int index_id, int doc_id) {
 void file(struct mg_connection *nc, struct mg_http_message *hm) {
     sist_id_t sid;
 
-    if (hm->uri.len != 20 || !parse_sid(&sid, hm->uri.ptr + 3)) {
-        LOG_DEBUGF("serve.c", "Invalid file path: %.*s", (int) hm->uri.len, hm->uri.ptr);
+    if (hm->uri.len != 20 || !parse_sid(&sid, hm->uri.buf + 3)) {
+        LOG_DEBUGF("serve.c", "Invalid file path: %.*s", (int) hm->uri.len, hm->uri.buf);
         HTTP_REPLY_NOT_FOUND
         return;
     }
@@ -528,14 +528,14 @@ subreq_ctx_t *elastic_write_tag(const char *sid, const tag_req_t *req) {
 
 void tag(struct mg_connection *nc, struct mg_http_message *hm) {
     sist_id_t sid;
-    if (hm->uri.len != 22 || !parse_sid(&sid, hm->uri.ptr + 5)) {
-        LOG_DEBUGF("serve.c", "Invalid tag path: %.*s", (int) hm->uri.len, hm->uri.ptr);
+    if (hm->uri.len != 22 || !parse_sid(&sid, hm->uri.buf + 5)) {
+        LOG_DEBUGF("serve.c", "Invalid tag path: %.*s", (int) hm->uri.len, hm->uri.buf);
         HTTP_REPLY_NOT_FOUND
         return;
     }
 
     char *body = malloc(hm->body.len + 1);
-    memcpy(body, hm->body.ptr, hm->body.len);
+    memcpy(body, hm->body.buf, hm->body.len);
     *(body + hm->body.len) = '\0';
     cJSON *json = cJSON_Parse(body);
     free(body);
@@ -612,7 +612,7 @@ int check_auth0(struct mg_http_message *hm) {
     }
 
     token_str = malloc(token.len + 1);
-    strncpy(token_str, token.ptr, token.len);
+    strncpy(token_str, token.buf, token.len);
     *(token_str + token.len) = '\0';
 
     int res = auth0_verify_jwt(
@@ -642,13 +642,15 @@ static void ev_router(struct mg_connection *nc, int ev, void *ev_data) {
         }
 
         char uri[256];
-        memcpy(uri, hm->uri.ptr, hm->uri.len);
+        memcpy(uri, hm->uri.buf, hm->uri.len);
         *(uri + hm->uri.len) = '\0';
         LOG_DEBUGF("serve.c", "<%s> GET %s",
                    web_address_to_string(&(nc->rem)),
                    uri
         );
 
+#define mg_http_match_uri(hm, pattern) mg_match((hm)->uri, mg_str(pattern), NULL)
+
         if (mg_http_match_uri(hm, "/")) {
             serve_index_html(nc, hm);
             return;

src/web/web_fts.c

@@ -420,8 +420,8 @@ void fts_get_document(struct mg_connection *nc, struct mg_http_message *hm) {
 
     sist_id_t sid;
 
-    if (hm->uri.len != 24 || !parse_sid(&sid, hm->uri.ptr + 7)) {
-        LOG_DEBUGF("serve.c", "Invalid /fts/d/ path: %.*s", (int) hm->uri.len, hm->uri.ptr);
+    if (hm->uri.len != 24 || !parse_sid(&sid, hm->uri.buf + 7)) {
+        LOG_DEBUGF("serve.c", "Invalid /fts/d/ path: %.*s", (int) hm->uri.len, hm->uri.buf);
         HTTP_REPLY_NOT_FOUND
         return;
     }

src/web/web_util.c

@@ -73,7 +73,7 @@ cJSON *web_get_json_body(struct mg_http_message *hm) {
     }
 
     char *body = malloc(hm->body.len + 1);
-    memcpy(body, hm->body.ptr, hm->body.len);
+    memcpy(body, hm->body.buf, hm->body.len);
     *(body + hm->body.len) = '\0';
     cJSON *json = cJSON_Parse(body);
     free(body);
@@ -87,7 +87,7 @@ char *web_get_string_body(struct mg_http_message *hm) {
     }
 
     char *body = malloc(hm->body.len + 1);
-    memcpy(body, hm->body.ptr, hm->body.len);
+    memcpy(body, hm->body.buf, hm->body.len);
     *(body + hm->body.len) = '\0';
 
     return body;