UI fix, disable thumbnail option, batch index size option

CMakeLists.txt

@@ -157,8 +157,8 @@ if (WITH_SIST2)
             m
             bz2
             magic
-            harfbuzz
-            openjp2
+            ${PROJECT_SOURCE_DIR}/lib/libharfbuzz.a
+            ${PROJECT_SOURCE_DIR}/lib/libopenjp2.a
             freetype
     )
 

Docker/build.sh

@@ -1,3 +1,4 @@
+rm ./sist2
 cp ../sist2 .
 
 version=$(./sist2 --version)

mime.csv

@@ -252,7 +252,7 @@ text/html, acgi|htm|html|htmls|htx|shtml
 text/javascript, js
 text/mcf, mcf
 text/pascal, pas
-text/plain, com|cmd|conf|def|g|idc|list|lst|mar|sdml|text|txt|md|groovy|license|properties|desktop|ini|rst|cmake|ipynb|readme|less|lo|go|yml|d|cs|hpp|srt
+text/plain, com|cmd|conf|def|g|idc|list|lst|mar|sdml|text|txt|md|groovy|license|properties|desktop|ini|rst|cmake|ipynb|readme|less|lo|go|yml|d|cs|hpp|srt|nfo|sfv|m3u
 text/richtext, rt|rtf|rtx
 text/rtf,
 text/scriplet, wsc

src/cli.c

@@ -7,6 +7,7 @@
 #define DEFAULT_REWRITE_URL ""
 
 #define DEFAULT_ES_URL "http://localhost:9200"
+#define DEFAULT_BATCH_SIZE 100
 
 #define DEFAULT_BIND_ADDR "localhost"
 #define DEFAULT_PORT "4090"
@@ -14,9 +15,37 @@
 
 scan_args_t *scan_args_create() {
     scan_args_t *args = calloc(sizeof(scan_args_t), 1);
+
+    args->depth = -1;
+
     return args;
 }
 
+void scan_args_destroy(scan_args_t *args) {
+    if (args->name != NULL) {
+        free(args->name);
+    }
+    if (args->path != NULL) {
+        free(args->path);
+    }
+    if (args->output != NULL) {
+        free(args->output);
+    }
+    free(args);
+}
+
+#ifndef SIST_SCAN_ONLY
+void index_args_destroy(index_args_t *args) {
+    //todo
+    free(args);
+}
+
+void web_args_destroy(web_args_t *args) {
+    //todo
+    free(args);
+}
+#endif
+
 int scan_args_validate(scan_args_t *args, int argc, const char **argv) {
     if (argc < 2) {
         fprintf(stderr, "Required positional argument: PATH.\n");
@@ -48,16 +77,13 @@ int scan_args_validate(scan_args_t *args, int argc, const char **argv) {
 
     if (args->size == 0) {
         args->size = DEFAULT_SIZE;
-    } else if (args->size <= 0) {
-        fprintf(stderr, "Invalid size: %d\n", args->size);
+    } else if (args->size > 0 && args->size < 32) {
+        printf("Invalid size: %d\n", args->content_size);
         return 1;
     }
 
     if (args->content_size == 0) {
         args->content_size = DEFAULT_CONTENT_SIZE;
-    } else if (args->content_size <= 0) {
-        fprintf(stderr, "Invalid content-size: %d\n", args->content_size);
-        return 1;
     }
 
     if (args->threads == 0) {
@@ -80,6 +106,12 @@ int scan_args_validate(scan_args_t *args, int argc, const char **argv) {
         return 1;
     }
 
+    if (args->depth < 0) {
+        args->depth = G_MAXINT32;
+    } else {
+        args->depth += 1;
+    }
+
     if (args->name == NULL) {
         args->name = g_path_get_basename(args->output);
     }
@@ -104,6 +136,7 @@ int index_args_validate(index_args_t *args, int argc, const char **argv) {
         return 1;
     } else {
         args->index_path = argv[1];
+        free(index_path);
     }
 
     if (args->es_url == NULL) {
@@ -135,6 +168,11 @@ int index_args_validate(index_args_t *args, int argc, const char **argv) {
         *(args->script + info.st_size) = '\0';
         close(fd);
     }
+
+    if (args->batch_size == 0) {
+        args->batch_size = DEFAULT_BATCH_SIZE;
+    }
+
     return 0;
 }
 

src/cli.h

@@ -12,10 +12,12 @@ typedef struct scan_args {
     char *output;
     char *rewrite_url;
     char *name;
+    int depth;
     char *path;
 } scan_args_t;
 
 scan_args_t *scan_args_create();
+void scan_args_destroy(scan_args_t *args);
 int scan_args_validate(scan_args_t *args, int argc, const char **argv);
 
 #ifndef SIST_SCAN_ONLY
@@ -25,6 +27,7 @@ typedef struct index_args {
     const char *script_path;
     char *script;
     int print;
+    int batch_size;
     int force_reset;
 } index_args_t;
 
@@ -39,7 +42,10 @@ typedef struct web_args {
 } web_args_t;
 
 index_args_t *index_args_create();
+void index_args_destroy(index_args_t *args);
+
 web_args_t *web_args_create();
+void web_args_destroy(web_args_t *args);
 
 int index_args_validate(index_args_t *args, int argc, const char **argv);
 int web_args_validate(web_args_t *args, int argc, const char **argv);

src/ctx.h

@@ -15,6 +15,7 @@ struct {
     int threads;
     int content_size;
     float tn_qscale;
+    int depth;
 
     size_t stat_tn_size;
     size_t stat_index_size;
@@ -29,12 +30,13 @@ struct {
 #ifndef SIST_SCAN_ONLY
 struct {
     char *es_url;
+    int batch_size;
 } IndexCtx;
 
 struct {
     char *es_url;
     int index_count;
-    char* b64credentials;
+    char *b64credentials;
     struct index_t indices[16];
 } WebCtx;
 #endif

src/index/elastic.c

@@ -9,7 +9,6 @@
 
 #include "static_generated.c"
 
-#define BULK_INDEX_SIZE 100
 
 typedef struct es_indexer {
     int queued;
@@ -173,7 +172,7 @@ void elastic_index_line(es_bulk_line_t *line) {
 
     Indexer->queued += 1;
 
-    if (Indexer->queued >= BULK_INDEX_SIZE) {
+    if (Indexer->queued >= IndexCtx.batch_size) {
         elastic_flush();
     }
 }

src/io/serialize.c

@@ -1,7 +1,7 @@
 #include "src/ctx.h"
 #include "serialize.h"
 
-static __thread int IndexFd = -1;
+static __thread int index_fd = -1;
 
 typedef struct {
     unsigned char uuid[16];
@@ -119,13 +119,13 @@ char *get_meta_key_text(enum metakey meta_key) {
 
 void write_document(document_t *doc) {
 
-    if (IndexFd == -1) {
+    if (index_fd == -1) {
         char dstfile[PATH_MAX];
         pthread_t self = pthread_self();
         snprintf(dstfile, PATH_MAX, "%s_index_%lu", ScanCtx.index.path, self);
-        IndexFd = open(dstfile, O_CREAT | O_WRONLY | O_APPEND, S_IRUSR | S_IWUSR);
+        index_fd = open(dstfile, O_CREAT | O_WRONLY | O_APPEND, S_IRUSR | S_IWUSR);
 
-        if (IndexFd == -1) {
+        if (index_fd == -1) {
             perror("open");
         }
     }
@@ -158,13 +158,16 @@ void write_document(document_t *doc) {
     }
     dyn_buffer_write_char(&buf, '\n');
 
-    write(IndexFd, buf.buf, buf.cur);
+    int res = write(index_fd, buf.buf, buf.cur);
+    if (res == -1) {
+        perror("write");
+    }
     ScanCtx.stat_index_size += buf.cur;
     dyn_buffer_destroy(&buf);
 }
 
-void serializer_cleanup() {
-    close(IndexFd);
+void thread_cleanup() {
+    close(index_fd);
 }
 
 void read_index(const char *path, const char index_id[UUID_STR_LEN], index_func func) {

src/io/serialize.h

@@ -18,7 +18,7 @@ void incremental_read(GHashTable *table, const char *filepath);
 /**
  * Must be called after write_document
  */
-void serializer_cleanup();
+void thread_cleanup();
 
 void write_index_descriptor(char *path, index_descriptor_t *desc);
 

src/io/walk.c

@@ -20,7 +20,7 @@ parse_job_t *create_parse_job(const char *filepath, const struct stat *info, int
 }
 
 int handle_entry(const char *filepath, const struct stat *info, int typeflag, struct FTW *ftw) {
-    if (typeflag == FTW_F && S_ISREG(info->st_mode)) {
+    if (ftw->level <= ScanCtx.depth && typeflag == FTW_F && S_ISREG(info->st_mode)) {
         parse_job_t *job = create_parse_job(filepath, info, ftw->base);
         tpool_add_work(ScanCtx.pool, parse, job);
     }

src/main.c

@@ -10,7 +10,7 @@
 #define EPILOG "Made by simon987 <me@simon987.net>. Released under GPL-3.0"
 
 
-static const char *const Version = "1.1.7";
+static const char *const Version = "1.1.9";
 static const char *const usage[] = {
         "sist2 scan [OPTION]... PATH",
         "sist2 index [OPTION]... INDEX",
@@ -19,9 +19,9 @@ static const char *const usage[] = {
 };
 
 void global_init() {
-    #ifndef SIST_SCAN_ONLY
+#ifndef SIST_SCAN_ONLY
     curl_global_init(CURL_GLOBAL_NOTHING);
-    #endif
+#endif
     av_log_set_level(AV_LOG_QUIET);
 }
 
@@ -41,10 +41,22 @@ void init_dir(const char *dirpath) {
 void scan_print_header() {
     printf("sist2 V%s\n", Version);
     printf("---------------------\n");
-    printf("threads\t\t%d\n", ScanCtx.threads);
-    printf("tn_qscale\t%.1f/31.0\n", ScanCtx.tn_qscale);
-    printf("tn_size\t\t%dpx\n", ScanCtx.tn_size);
-    printf("output\t\t%s\n", ScanCtx.index.path);
+    printf("threads\t\t\t%d\n", ScanCtx.threads);
+    printf("tn_qscale\t\t%.1f/31.0\n", ScanCtx.tn_qscale);
+
+    if (ScanCtx.tn_size > 0) {
+        printf("tn_size\t\t\t%dpx\n", ScanCtx.tn_size);
+    } else {
+        printf("tn_size\t\t\tdisabled\n");
+    }
+
+    if (ScanCtx.content_size > 0) {
+        printf("content_size\t%d B\n", ScanCtx.content_size);
+    } else {
+        printf("content_size\t\t\tdisabled\n");
+    }
+
+    printf("output\t\t\t%s\n", ScanCtx.index.path);
 }
 
 void sist2_scan(scan_args_t *args) {
@@ -53,6 +65,7 @@ void sist2_scan(scan_args_t *args) {
     ScanCtx.tn_size = args->size;
     ScanCtx.content_size = args->content_size;
     ScanCtx.threads = args->threads;
+    ScanCtx.depth = args->depth;
     strncpy(ScanCtx.index.path, args->output, sizeof(ScanCtx.index.path));
     strncpy(ScanCtx.index.desc.name, args->name, sizeof(ScanCtx.index.desc.name));
     strncpy(ScanCtx.index.desc.root, args->path, sizeof(ScanCtx.index.desc.root));
@@ -92,7 +105,7 @@ void sist2_scan(scan_args_t *args) {
         printf("Loaded %d items in to mtime table.", g_hash_table_size(ScanCtx.original_table));
     }
 
-    ScanCtx.pool = tpool_create(args->threads, serializer_cleanup);
+    ScanCtx.pool = tpool_create(args->threads, thread_cleanup);
     tpool_start(ScanCtx.pool);
     walk_directory_tree(ScanCtx.index.desc.root);
     tpool_wait(ScanCtx.pool);
@@ -125,9 +138,11 @@ void sist2_scan(scan_args_t *args) {
 }
 
 #ifndef SIST_SCAN_ONLY
+
 void sist2_index(index_args_t *args) {
 
     IndexCtx.es_url = args->es_url;
+    IndexCtx.batch_size = args->batch_size;
 
     if (!args->print) {
         elastic_init(args->force_reset);
@@ -197,6 +212,7 @@ void sist2_web(web_args_t *args) {
 
     serve(args->bind, args->port);
 }
+
 #endif
 
 
@@ -205,14 +221,14 @@ int main(int argc, const char *argv[]) {
     global_init();
 
     scan_args_t *scan_args = scan_args_create();
-    #ifndef SIST_SCAN_ONLY
+#ifndef SIST_SCAN_ONLY
     index_args_t *index_args = index_args_create();
     web_args_t *web_args = web_args_create();
-    #endif
+#endif
 
     int arg_version = 0;
 
-    char * common_es_url = NULL;
+    char *common_es_url = NULL;
 
     struct argparse_option options[] = {
             OPT_HELP(),
@@ -223,29 +239,33 @@ int main(int argc, const char *argv[]) {
             OPT_INTEGER('t', "threads", &scan_args->threads, "Number of threads. DEFAULT=1"),
             OPT_FLOAT('q', "quality", &scan_args->quality,
                       "Thumbnail quality, on a scale of 1.0 to 31.0, 1.0 being the best. DEFAULT=5"),
-            OPT_INTEGER(0, "size", &scan_args->size, "Thumbnail size, in pixels. DEFAULT=500"),
+            OPT_INTEGER(0, "size", &scan_args->size,
+                        "Thumbnail size, in pixels. Use negative value to disable. DEFAULT=500"),
             OPT_INTEGER(0, "content-size", &scan_args->content_size,
-                        "Number of bytes to be extracted from text documents. DEFAULT=4096"),
+                        "Number of bytes to be extracted from text documents. Use negative value to disable. DEFAULT=4096"),
             OPT_STRING(0, "incremental", &scan_args->incremental,
                        "Reuse an existing index and only scan modified files."),
             OPT_STRING('o', "output", &scan_args->output, "Output directory. DEFAULT=index.sist2/"),
             OPT_STRING(0, "rewrite-url", &scan_args->rewrite_url, "Serve files from this url instead of from disk."),
             OPT_STRING(0, "name", &scan_args->name, "Index display name. DEFAULT: (name of the directory)"),
+            OPT_INTEGER(0, "depth", &scan_args->depth, "Scan up to DEPTH subdirectories deep. "
+                                                       "Use 0 to only scan files in PATH. DEFAULT: -1"),
 
-            #ifndef SIST_SCAN_ONLY
+#ifndef SIST_SCAN_ONLY
             OPT_GROUP("Index options"),
             OPT_STRING(0, "es-url", &common_es_url, "Elasticsearch url. DEFAULT=http://localhost:9200"),
             OPT_BOOLEAN('p', "print", &index_args->print, "Just print JSON documents to stdout."),
             OPT_STRING(0, "script-file", &index_args->script_path, "Path to user script."),
+            OPT_INTEGER(0, "batch-size", &index_args->batch_size, "Index batch size. DEFAULT: 100"),
             OPT_BOOLEAN('f', "force-reset", &index_args->force_reset, "Reset Elasticsearch mappings and settings. "
-                                                              "(You must use this option the first time you use the index command)"),
+                                                                      "(You must use this option the first time you use the index command)"),
 
             OPT_GROUP("Web options"),
             OPT_STRING(0, "es-url", &common_es_url, "Elasticsearch url. DEFAULT=http://localhost:9200"),
             OPT_STRING(0, "bind", &web_args->bind, "Listen on this address. DEFAULT=localhost"),
             OPT_STRING(0, "port", &web_args->port, "Listen on this port. DEFAULT=4090"),
             OPT_STRING(0, "auth", &web_args->credentials, "Basic auth in user:password format"),
-            #endif
+#endif
 
             OPT_END(),
     };
@@ -260,10 +280,10 @@ int main(int argc, const char *argv[]) {
         exit(0);
     }
 
-    #ifndef SIST_SCAN_ONLY
+#ifndef SIST_SCAN_ONLY
     web_args->es_url = common_es_url;
     index_args->es_url = common_es_url;
-    #endif
+#endif
 
     if (argc == 0) {
         argparse_usage(&argparse);
@@ -278,7 +298,7 @@ int main(int argc, const char *argv[]) {
 
     }
 
-    #ifndef SIST_SCAN_ONLY
+#ifndef SIST_SCAN_ONLY
     else if (strcmp(argv[0], "index") == 0) {
 
         int err = index_args_validate(index_args, argc, argv);
@@ -296,12 +316,20 @@ int main(int argc, const char *argv[]) {
         sist2_web(web_args);
 
     }
-    #endif
+#endif
     else {
         fprintf(stderr, "Invalid command: '%s'\n", argv[0]);
         argparse_usage(&argparse);
         return 1;
     }
     printf("\n");
+
+    scan_args_destroy(scan_args);
+
+#ifndef SIST_SCAN_ONLY
+    index_args_destroy(index_args);
+    web_args_destroy(web_args);
+#endif
+
     return 0;
 }

src/parsing/font.c

@@ -1,11 +1,9 @@
 #include "font.h"
 
-#include "ft2build.h"
-#include "freetype/freetype.h"
 
 #include "src/ctx.h"
 
-__thread FT_Library library = NULL;
+__thread FT_Library ft_lib = NULL;
 
 
 typedef struct text_dimensions {
@@ -139,15 +137,15 @@ void bmp_format(dyn_buffer_t *buf, text_dimensions_t dimensions, const unsigned
 }
 
 void parse_font(const char *buf, size_t buf_len, document_t *doc) {
-    if (library == NULL) {
-        FT_Init_FreeType(&library);
+    if (ft_lib == NULL) {
+        FT_Init_FreeType(&ft_lib);
     }
     if (buf == NULL) {
         return;
     }
 
     FT_Face face;
-    FT_Error err = FT_New_Memory_Face(library, (unsigned char *) buf, buf_len, 0, &face);
+    FT_Error err = FT_New_Memory_Face(ft_lib, (unsigned char *) buf, buf_len, 0, &face);
     if (err != 0) {
         return;
     }
@@ -169,6 +167,10 @@ void parse_font(const char *buf, size_t buf_len, document_t *doc) {
     strcpy(meta_name->strval, font_name);
     APPEND_META(doc, meta_name)
 
+    if (ScanCtx.tn_size <= 0) {
+        return;
+    }
+
     int pixel = 64;
     int num_chars = (int) strlen(font_name);
 

src/parsing/media.c

@@ -242,7 +242,7 @@ void parse_media(const char *filepath, document_t *doc) {
         }
     }
 
-    if (video_stream != -1) {
+    if (video_stream != -1 && ScanCtx.tn_size > 0) {
         AVStream *stream = pFormatCtx->streams[video_stream];
 
         if (stream->codecpar->width <= MIN_SIZE || stream->codecpar->height <= MIN_SIZE) {

src/parsing/mime_generated.c

@@ -1182,6 +1182,9 @@ g_hash_table_insert(ext_table, "d", (gpointer)text_plain);
 g_hash_table_insert(ext_table, "cs", (gpointer)text_plain);
 g_hash_table_insert(ext_table, "hpp", (gpointer)text_plain);
 g_hash_table_insert(ext_table, "srt", (gpointer)text_plain);
+g_hash_table_insert(ext_table, "nfo", (gpointer)text_plain);
+g_hash_table_insert(ext_table, "sfv", (gpointer)text_plain);
+g_hash_table_insert(ext_table, "m3u", (gpointer)text_plain);
 g_hash_table_insert(ext_table, "rt", (gpointer)text_richtext);
 g_hash_table_insert(ext_table, "rtf", (gpointer)text_richtext);
 g_hash_table_insert(ext_table, "rtx", (gpointer)text_richtext);

src/parsing/parse.c

@@ -44,7 +44,6 @@ void parse(void *arg) {
 
     if (Magic == NULL) {
         Magic = magic_open(MAGIC_MIME_TYPE);
-        magic_load(Magic, NULL);
     }
 
     doc.filepath = job->filepath;

src/parsing/pdf.c

@@ -177,7 +177,17 @@ void parse_pdf(void *buf, size_t buf_len, document_t *doc) {
         return;
     }
 
-    fz_page *cover = render_cover(ctx, doc, fzdoc);
+    fz_page *cover = NULL;
+    if (ScanCtx.tn_size > 0) {
+        cover = render_cover(ctx, doc, fzdoc);
+    } else {
+        fz_var(cover);
+        fz_try(ctx)
+            cover = fz_load_page(ctx, fzdoc, 0);
+        fz_catch(ctx)
+            cover = NULL;
+    }
+
     if (cover == NULL) {
         fz_drop_stream(ctx, stream);
         fz_drop_document(ctx, fzdoc);
@@ -185,79 +195,81 @@ void parse_pdf(void *buf, size_t buf_len, document_t *doc) {
         return;
     }
 
-    fz_stext_options opts = {0};
-    text_buffer_t text_buf = text_buffer_create(ScanCtx.content_size);
+    if (ScanCtx.content_size > 0) {
+        fz_stext_options opts = {0};
+        text_buffer_t text_buf = text_buffer_create(ScanCtx.content_size);
+
+        for (int current_page = 0; current_page < page_count; current_page++) {
+            fz_page *page = NULL;
+            if (current_page == 0) {
+                page = cover;
+            } else {
+                fz_var(err);
+                fz_try(ctx)
+                            page = fz_load_page(ctx, fzdoc, current_page);
+                fz_catch(ctx)
+                    err = ctx->error.errcode;
+                if (err != 0) {
+                    text_buffer_destroy(&text_buf);
+                    fz_drop_page(ctx, page);
+                    fz_drop_stream(ctx, stream);
+                    fz_drop_document(ctx, fzdoc);
+                    fz_drop_context(ctx);
+                    return;
+                }
+            }
+
+            fz_stext_page *stext = fz_new_stext_page(ctx, fz_bound_page(ctx, page));
+            fz_device *dev = fz_new_stext_device(ctx, stext, &opts);
 
-    for (int current_page = 0; current_page < page_count; current_page++) {
-        fz_page *page = NULL;
-        if (current_page == 0) {
-            page = cover;
-        } else {
             fz_var(err);
             fz_try(ctx)
-                page = fz_load_page(ctx, fzdoc, current_page);
+                        fz_run_page(ctx, page, dev, fz_identity, NULL);
+            fz_always(ctx)
+                {
+                    fz_close_device(ctx, dev);
+                    fz_drop_device(ctx, dev);
+                }
             fz_catch(ctx)
                 err = ctx->error.errcode;
+
             if (err != 0) {
                 text_buffer_destroy(&text_buf);
                 fz_drop_page(ctx, page);
+                fz_drop_stext_page(ctx, stext);
                 fz_drop_stream(ctx, stream);
                 fz_drop_document(ctx, fzdoc);
                 fz_drop_context(ctx);
                 return;
             }
-        }
 
-        fz_stext_page *stext = fz_new_stext_page(ctx, fz_bound_page(ctx, page));
-        fz_device *dev = fz_new_stext_device(ctx, stext, &opts);
-
-        fz_var(err);
-        fz_try(ctx)
-            fz_run_page(ctx, page, dev, fz_identity, NULL);
-        fz_always(ctx)
-        {
-            fz_close_device(ctx, dev);
-            fz_drop_device(ctx, dev);
-        }
-        fz_catch(ctx)
-            err = ctx->error.errcode;
-
-        if (err != 0) {
-            text_buffer_destroy(&text_buf);
-            fz_drop_page(ctx, page);
+            fz_stext_block *block = stext->first_block;
+            while (block != NULL) {
+                int ret = read_stext_block(block, &text_buf);
+                if (ret == TEXT_BUF_FULL) {
+                    break;
+                }
+                block = block->next;
+            }
             fz_drop_stext_page(ctx, stext);
-            fz_drop_stream(ctx, stream);
-            fz_drop_document(ctx, fzdoc);
-            fz_drop_context(ctx);
-            return;
-        }
+            fz_drop_page(ctx, page);
 
-        fz_stext_block *block = stext->first_block;
-        while (block != NULL) {
-            int ret = read_stext_block(block, &text_buf);
-            if (ret == TEXT_BUF_FULL) {
+            if (text_buf.dyn_buffer.cur >= text_buf.dyn_buffer.size) {
                 break;
             }
-            block = block->next;
         }
-        fz_drop_stext_page(ctx, stext);
-        fz_drop_page(ctx, page);
+        text_buffer_terminate_string(&text_buf);
 
-        if (text_buf.dyn_buffer.cur >= text_buf.dyn_buffer.size) {
-            break;
-        }
+        meta_line_t *meta_content = malloc(sizeof(meta_line_t) + text_buf.dyn_buffer.cur);
+        meta_content->key = MetaContent;
+        memcpy(meta_content->strval, text_buf.dyn_buffer.buf, text_buf.dyn_buffer.cur);
+        APPEND_META(doc, meta_content)
+
+        text_buffer_destroy(&text_buf);
     }
-    text_buffer_terminate_string(&text_buf);
-
-    meta_line_t *meta_content = malloc(sizeof(meta_line_t) + text_buf.dyn_buffer.cur);
-    meta_content->key = MetaContent;
-    memcpy(meta_content->strval, text_buf.dyn_buffer.buf, text_buf.dyn_buffer.cur);
-    APPEND_META(doc, meta_content)
 
     fz_drop_stream(ctx, stream);
     fz_drop_document(ctx, fzdoc);
     fz_drop_context(ctx);
-
-    text_buffer_destroy(&text_buf);
 }
 

src/sist.h

@@ -26,6 +26,8 @@
 #include <pthread.h>
 #include <sys/stat.h>
 #include <wordexp.h>
+#include "ft2build.h"
+#include "freetype/freetype.h"
 
 #ifndef SIST_SCAN_ONLY
 #include <onion/onion.h>

src/tpool.c

@@ -114,12 +114,18 @@ static void *tpool_worker(void *arg) {
         pthread_mutex_unlock(&(pool->work_mutex));
 
         if (work != NULL) {
+            if (pool->stop) {
+                break;
+            }
+
             work->func(work->arg);
             free(work);
         }
 
         pthread_mutex_lock(&(pool->work_mutex));
-        pool->done_cnt++;
+        if (work != NULL) {
+            pool->done_cnt++;
+        }
 
         progress_bar_print((double) pool->done_cnt / pool->work_cnt, ScanCtx.stat_tn_size, ScanCtx.stat_index_size);
 
@@ -142,11 +148,15 @@ void tpool_wait(tpool_t *pool) {
         if (pool->done_cnt < pool->work_cnt) {
             pthread_cond_wait(&(pool->working_cond), &(pool->work_mutex));
         } else {
-            pool->stop = 1;
-            break;
+            usleep(500000);
+            if (pool->done_cnt == pool->work_cnt) {
+                pool->stop = 1;
+                usleep(1000000);
+                break;
+            }
         }
-        progress_bar_print(100.0, ScanCtx.stat_tn_size, ScanCtx.stat_index_size);
     }
+    progress_bar_print(1.0, ScanCtx.stat_tn_size, ScanCtx.stat_index_size);
     pthread_mutex_unlock(&(pool->work_mutex));
 }
 
@@ -169,7 +179,8 @@ void tpool_destroy(tpool_t *pool) {
     for (size_t i = 0; i < pool->thread_cnt; i++) {
         pthread_t thread = pool->threads[i];
         if (thread != 0) {
-            pthread_cancel(thread);
+            void *_;
+            pthread_join(thread, &_);
         }
     }
 
@@ -209,8 +220,6 @@ tpool_t *tpool_create(size_t thread_cnt, void cleanup_func()) {
 void tpool_start(tpool_t *pool) {
 
     for (size_t i = 0; i < pool->thread_cnt; i++) {
-        pthread_t thread = pool->threads[i];
-        pthread_create(&thread, NULL, tpool_worker, pool);
-        pthread_detach(thread);
+        pthread_create(&pool->threads[i], NULL, tpool_worker, pool);
     }
 }

src/web/auth_basic.c

@@ -1,4 +1,4 @@
-#import "auth_basic.h"
+#include "auth_basic.h"
 
 #define UNAUTHORIZED_TEXT "Unauthorized"
 

web/js/dom.js

@@ -345,7 +345,8 @@ function makeThumbnail(mimeCategory, hit, imgWrapper, small) {
 
 function createDocLine(hit) {
 
-    let mimeCategory = hit["_source"]["mime"].split("/")[0];
+    const mime = hit["_source"]["mime"];
+    let mimeCategory = mime ? mime.split("/")[0] : null;
     let tags = getTags(hit, mimeCategory);
 
     let imgWrapper = document.createElement("div");

web/js/search.js

@@ -357,6 +357,7 @@ function search() {
             post_tags: ["</mark>"],
             fields: {
                 content: {},
+                // "content.nGram": {},
                 name: {},
                 "name.nGram": {},
                 font_name: {},

web/search.html

@@ -11,7 +11,7 @@
 
 <nav class="navbar navbar-expand-lg">
     <a class="navbar-brand" href="/">sist2</a>
-    <span class="badge badge-pill version">v1.1.7</span>
+    <span class="badge badge-pill version">v1.1.9</span>
     <span class="tagline">Lightning-fast file system indexer and search tool </span>
     <a style="margin-left: auto" id="theme" class="btn" title="Toggle theme" href="/">Theme</a>
 </nav>