UI fix, disable thumbnail option, batch index size option

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"
@@ -33,6 +34,7 @@ void scan_args_destroy(scan_args_t *args) {
     free(args);
 }
 
+#ifndef SIST_SCAN_ONLY
 void index_args_destroy(index_args_t *args) {
     //todo
     free(args);
@@ -42,6 +44,7 @@ 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) {
@@ -74,16 +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) {
@@ -168,6 +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

@@ -27,6 +27,7 @@ typedef struct index_args {
     const char *script_path;
     char *script;
     int print;
+    int batch_size;
     int force_reset;
 } index_args_t;
 

src/ctx.h

@@ -30,6 +30,7 @@ struct {
 #ifndef SIST_SCAN_ONLY
 struct {
     char *es_url;
+    int batch_size;
 } IndexCtx;
 
 struct {

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/main.c

@@ -10,7 +10,7 @@
 #define EPILOG "Made by simon987 <me@simon987.net>. Released under GPL-3.0"
 
 
-static const char *const Version = "1.1.8";
+static const char *const Version = "1.1.9";
 static const char *const usage[] = {
         "sist2 scan [OPTION]... PATH",
         "sist2 index [OPTION]... INDEX",
@@ -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) {
@@ -130,6 +142,7 @@ void sist2_scan(scan_args_t *args) {
 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);
@@ -226,9 +239,10 @@ 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/"),
@@ -242,6 +256,7 @@ int main(int argc, const char *argv[]) {
             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)"),
 

src/parsing/font.c

@@ -167,6 +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/parse.c

@@ -97,33 +97,31 @@ void parse(void *arg) {
 
     int mmime = MAJOR_MIME(doc.mime);
 
-    parse_text(bytes_read, &fd, (char *) buf, &doc);
+    if (!(SHOULD_PARSE(doc.mime))) {
 
-//    if (!(SHOULD_PARSE(doc.mime))) {
-//
-//    } else if ((mmime == MimeVideo && doc.size >= MIN_VIDEO_SIZE) ||
-//    (mmime == MimeImage && doc.size >= MIN_IMAGE_SIZE) || mmime == MimeAudio) {
-//        parse_media(job->filepath, &doc);
-//
-//    } else if (IS_PDF(doc.mime)) {
-//        void *pdf_buf = read_all(job, (char *) buf, bytes_read, &fd);
-//        parse_pdf(pdf_buf, doc.size, &doc);
-//
-//        if (pdf_buf != buf && pdf_buf != NULL) {
-//            free(pdf_buf);
-//        }
-//
-//    } else if (mmime == MimeText && ScanCtx.content_size > 0) {
-//        parse_text(bytes_read, &fd, (char *) buf, &doc);
-//
-//    } else if (IS_FONT(doc.mime)) {
-//        void *font_buf = read_all(job, (char *) buf, bytes_read, &fd);
-//        parse_font(font_buf, doc.size, &doc);
-//
-//        if (font_buf != buf && font_buf != NULL) {
-//            free(font_buf);
-//        }
-//    }
+    } else if ((mmime == MimeVideo && doc.size >= MIN_VIDEO_SIZE) ||
+    (mmime == MimeImage && doc.size >= MIN_IMAGE_SIZE) || mmime == MimeAudio) {
+        parse_media(job->filepath, &doc);
+
+    } else if (IS_PDF(doc.mime)) {
+        void *pdf_buf = read_all(job, (char *) buf, bytes_read, &fd);
+        parse_pdf(pdf_buf, doc.size, &doc);
+
+        if (pdf_buf != buf && pdf_buf != NULL) {
+            free(pdf_buf);
+        }
+
+    } else if (mmime == MimeText && ScanCtx.content_size > 0) {
+        parse_text(bytes_read, &fd, (char *) buf, &doc);
+
+    } else if (IS_FONT(doc.mime)) {
+        void *font_buf = read_all(job, (char *) buf, bytes_read, &fd);
+        parse_font(font_buf, doc.size, &doc);
+
+        if (font_buf != buf && font_buf != NULL) {
+            free(font_buf);
+        }
+    }
 
     write_document(&doc);
 

src/parsing/pdf.c

@@ -1,4 +1,3 @@
-#include <src/ctx.h>
 #include "pdf.h"
 #include "src/ctx.h"
 
@@ -178,7 +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);