Archive file support

List mode #5

CMakeLists.txt

@@ -23,6 +23,7 @@ if (WITH_SIST2)
             src/parsing/text.h src/parsing/text.c
             src/index/web.c src/index/web.h
             src/web/serve.c src/web/serve.h
+            src/web/auth_basic.h src/web/auth_basic.c
             src/index/elastic.c src/index/elastic.h
             src/util.c src/util.h
             src/ctx.h src/types.h src/parsing/font.c src/parsing/font.h
@@ -40,7 +41,7 @@ if (WITH_SIST2)
 
             # utf8.h
             utf8.h/utf8.h
-    )
+            src/parsing/arc.c src/parsing/arc.h)
 endif ()
 
 if (WITH_SIST2_SCAN)
@@ -73,7 +74,7 @@ if (WITH_SIST2_SCAN)
 
             # utf8.h
             utf8.h/utf8.h
-    )
+            src/parsing/arc.c src/parsing/arc.h)
 endif ()
 
 find_package(PkgConfig REQUIRED)
@@ -122,10 +123,10 @@ if (WITH_SIST2)
 
     target_compile_options(sist2
             PRIVATE
-#            -Ofast
+            -Ofast
 #                    -march=native
-#            -fno-stack-protector
+            -fno-stack-protector
-#            -fomit-frame-pointer
+            -fomit-frame-pointer
             )
 
     TARGET_LINK_LIBRARIES(
@@ -156,9 +157,10 @@ if (WITH_SIST2)
             m
             bz2
             magic
-            harfbuzz
+            ${PROJECT_SOURCE_DIR}/lib/libharfbuzz.a
-            openjp2
+            ${PROJECT_SOURCE_DIR}/lib/libopenjp2.a
             freetype
+            archive
     )
 
 endif ()
@@ -227,6 +229,11 @@ if (WITH_SIST2_SCAN)
             ${PROJECT_SOURCE_DIR}/lib/libharfbuzz.a
             ${PROJECT_SOURCE_DIR}/lib/libopenjp2.a
             freetype
+
+            ${PROJECT_SOURCE_DIR}/lib/libarchive.a
+            ${PROJECT_SOURCE_DIR}/lib/liblz4.a
+            ${PROJECT_SOURCE_DIR}/lib/liblzma.a
+            ${PROJECT_SOURCE_DIR}/lib/libzstd.a
     )
 endif ()
 

Docker/build.sh

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

README.md

@@ -15,9 +15,11 @@ sist2 (Simple incremental search tool)
 * Generates thumbnails\*
 * Incremental scanning
 * Automatic tagging from file attributes via [user scripts](scripting/README.md)
+* Recursive scan inside archive files \*\*
 
 
-\* See [format support](#format-support)
+\* See [format support](#format-support)    
+\** See [Archive files](#archive-files)
 
 ## Getting Started
 
@@ -33,8 +35,6 @@ sist2 (Simple incremental search tool)
 
 ## Example usage
 
-![demo](demo.gif)
-
 See help page `sist2 --help` for more details.
 
 **Scan a directory**
@@ -91,9 +91,25 @@ pdf,xps,cbz,fb2,epub | MuPDF | yes | yes, `png` | title |
 `image/*` | ffmpeg | - | yes, `jpeg` | `EXIF:Artist`, `EXIF:ImageDescription` |
 ttf,ttc,cff,woff,fnt,otf | Freetype2 | - | yes, `bmp` | Name & style |
 `text/plain` | *(none)* | yes | no | - |
-docx, xlsx, pptx |  | *planned* | no | *planned* |
+tar, zip, rar, 7z, ar ...  | Libarchive | yes\* | - | no |
+docx, xlsx, pptx |  | yes | no | *planned* |
 
+\* *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)
+scan is also supported.
 
+**Limitations**:
+* Parsing media files with formats that require
+*seek* (e.g. `.gif`, `.mp4` w/ fragmented metadata etc.) is not supported.
+* 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.
+
+To check if a media file can be parsed without *seek*, execute `cat file.mp4 | ffprobe -`
+ 
 
 
 ## Build from source
@@ -122,4 +138,4 @@ binaries.
     ./scripts/get_static_libs.sh
     cmake .
     make
-    ```
+    ```

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
@@ -410,4 +410,9 @@ text/PGP,
 audio/x-hx-aac-adts,
 application/x-chrome-extension,
 image/heic, heic
-image/x-gem,
+image/x-gem,
+application/x-lzma, lzma
+application/warc, warc
+application/x-lz4, lz4
+application/x-lzip, lz
+application/x-lzop, lzo

scripts/get_static_libs.sh

@@ -67,5 +67,39 @@ make -j 4
 cd ..
 mv libmagic/src/.libs/libmagic.a .
 
+# libarchive
+git clone https://github.com/libarchive/libarchive
+cd libarchive/build
+./autogen.sh
+cd ..
+./configure --without-nettle --without-expat --without-xml2 --without-openssl
+make -j 4
+cd ..
+mv libarchive/.libs/libarchive.a .
+
+# lz4
+git clone https://github.com/lz4/lz4
+cd lz4
+make -j 4
+cd ..
+mv lz4/lib/liblz4.a .
+
+# lzma
+wget https://newcontinuum.dl.sourceforge.net/project/lzmautils/xz-5.2.3.tar.gz
+tar -xzf xz-5.2.3.tar.gz
+rm xz-5.2.3.tar.gz
+cd xz-5.2.3
+./autogen.sh
+./configure
+make -j 4
+cd ..
+mv xz-5.2.3/src/liblzma/.libs/liblzma.a .
+
+# zstd
+git clone https://github.com/facebook/zstd
+cd zstd
+make -j 4
+cd ..
+mv zstd/lib/libzstd.a .
 
 cd ..

scripts/mime.py

@@ -34,6 +34,28 @@ font = (
     "font/woff2"
 )
 
+# Archive "formats"
+archive = (
+    "application/x-tar",
+    "application/zip",
+    "application/x-rar",
+    "application/x-arc",
+    "application/x-warc",
+    "application/x-7z-compressed",
+)
+
+# Archive "filters"
+arc_filter = (
+    "application/gzip",
+    "application/x-bzip2",
+    "application/x-xz",
+    "application/x-zstd",
+    "application/x-lzma",
+    "application/x-lz4",
+    "application/x-lzip",
+    "application/x-lzop",
+)
+
 cnt = 1
 
 
@@ -48,6 +70,10 @@ def mime_id(mime):
         mime_id += " | 0x40000000"
     elif mime in font:
         mime_id += " | 0x20000000"
+    elif mime in archive:
+        mime_id += " | 0x10000000"
+    elif mime in arc_filter:
+        mime_id += " | 0x08000000"
     elif mime == "application/x-empty":
         return "1"
     return mime_id

src/cli.c

@@ -1,12 +1,13 @@
 #include "cli.h"
 
 #define DEFAULT_OUTPUT "index.sist2/"
-#define DEFAULT_CONTENT_SIZE 4096
+#define DEFAULT_CONTENT_SIZE 32768
 #define DEFAULT_QUALITY 5
 #define DEFAULT_SIZE 500
 #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 +15,39 @@
 
 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 +79,13 @@ 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) {
+    } else if (args->size > 0 && args->size < 32) {
-        fprintf(stderr, "Invalid size: %d\n", args->size);
+        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 +108,12 @@ 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);
     }
@@ -87,10 +121,24 @@ int scan_args_validate(scan_args_t *args, int argc, const char **argv) {
     if (args->rewrite_url == NULL) {
         args->rewrite_url = DEFAULT_REWRITE_URL;
     }
+
+    if (args->archive == NULL || strcmp(args->archive, "recurse") == 0) {
+        args->archive_mode = ARC_MODE_RECURSE;
+    } else if (strcmp(args->archive, "list") == 0) {
+        args->archive_mode = ARC_MODE_LIST;
+    } else if (strcmp(args->archive, "shallow") == 0) {
+        args->archive_mode = ARC_MODE_SHALLOW;
+    } else if (strcmp(args->archive, "skip") == 0) {
+        args->archive_mode = ARC_MODE_SKIP;
+    } else {
+        fprintf(stderr, "Archive mode must be one of (skip, list, shallow, recurse), got '%s'", args->archive);
+        return 1;
+    }
     return 0;
 }
 
 #ifndef SIST_SCAN_ONLY
+
 int index_args_validate(index_args_t *args, int argc, const char **argv) {
 
     if (argc < 2) {
@@ -104,6 +152,7 @@ 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) {
@@ -126,10 +175,20 @@ int index_args_validate(index_args_t *args, int argc, const char **argv) {
         }
 
         args->script = malloc(info.st_size + 1);
-        read(fd, args->script, info.st_size);
+        res = read(fd, args->script, info.st_size);
+        if (res == -1) {
+            fprintf(stderr, "Error reading script file '%s': %s\n", args->script_path, strerror(errno));
+            return 1;
+        }
+
         *(args->script + info.st_size) = '\0';
         close(fd);
     }
+
+    if (args->batch_size == 0) {
+        args->batch_size = DEFAULT_BATCH_SIZE;
+    }
+
     return 0;
 }
 
@@ -152,6 +211,12 @@ int web_args_validate(web_args_t *args, int argc, const char **argv) {
         args->port = DEFAULT_PORT;
     }
 
+    if (args->credentials != NULL) {
+        args->b64credentials = onion_base64_encode(args->credentials, (int) strlen(args->credentials));
+        //Remove trailing newline
+        *(args->b64credentials + strlen(args->b64credentials) - 1) = '\0';
+    }
+
     args->index_count = argc - 1;
     args->indices = argv + 1;
 
@@ -174,5 +239,6 @@ web_args_t *web_args_create() {
     web_args_t *args = calloc(sizeof(web_args_t), 1);
     return args;
 }
+
 #endif
 

src/cli.h

@@ -12,10 +12,14 @@ typedef struct scan_args {
     char *output;
     char *rewrite_url;
     char *name;
+    int depth;
     char *path;
+    char *archive;
+    archive_mode_t archive_mode;
 } 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 +29,7 @@ typedef struct index_args {
     const char *script_path;
     char *script;
     int print;
+    int batch_size;
     int force_reset;
 } index_args_t;
 
@@ -32,12 +37,17 @@ typedef struct web_args {
     char *es_url;
     char *bind;
     char *port;
+    char *credentials;
+    char *b64credentials;
     int index_count;
     const char **indices;
 } 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 +15,8 @@ struct {
     int threads;
     int content_size;
     float tn_qscale;
+    int depth;
+    archive_mode_t archive_mode;
 
     size_t stat_tn_size;
     size_t stat_index_size;
@@ -29,11 +31,13 @@ struct {
 #ifndef SIST_SCAN_ONLY
 struct {
     char *es_url;
+    int batch_size;
 } IndexCtx;
 
 struct {
     char *es_url;
     int index_count;
+    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;
@@ -131,6 +130,12 @@ void elastic_flush() {
     char bulk_url[4096];
     snprintf(bulk_url, 4096, "%s/sist2/_bulk", Indexer->es_url);
     response_t *r = web_post(bulk_url, buf, "Content-Type: application/x-ndjson");
+
+    if (r->status_code == 0) {
+        fprintf(stderr, "Could not connect to %s, make sure that elasticsearch is running!\n", IndexCtx.es_url);
+        exit(1);
+    }
+
     printf("Indexed %3d documents (%zukB) <%d>\n", count, buf_cur / 1024, r->status_code);
 
     cJSON *ret_json = cJSON_Parse(r->body);
@@ -167,7 +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];
@@ -111,6 +111,8 @@ char *get_meta_key_text(enum metakey meta_key) {
             return "title";
         case MetaFontName:
             return "font_name";
+        case MetaParent:
+            return "parent";
         default:
             return NULL;
     }
@@ -119,13 +121,13 @@ 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 +160,16 @@ 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() {
+void thread_cleanup() {
-    close(IndexFd);
+    close(index_fd);
 }
 
 void read_index(const char *path, const char index_id[UUID_STR_LEN], index_func func) {
@@ -244,6 +249,7 @@ void read_index(const char *path, const char index_id[UUID_STR_LEN], index_func
                 case MetaAlbumArtist:
                 case MetaGenre:
                 case MetaFontName:
+                case MetaParent:
                 case MetaTitle: {
                     buf.cur = 0;
                     while ((c = getc(file)) != 0) {

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

@@ -1,7 +1,8 @@
 #include "walk.h"
 #include "src/ctx.h"
 
-parse_job_t *create_parse_job(const char *filepath, const struct stat *info, int base) {
+__always_inline
+parse_job_t *create_fs_parse_job(const char *filepath, const struct stat *info, int base) {
     int len = (int) strlen(filepath);
     parse_job_t *job = malloc(sizeof(parse_job_t) + len);
 
@@ -14,14 +15,22 @@ parse_job_t *create_parse_job(const char *filepath, const struct stat *info, int
         job->ext = len;
     }
 
-    memcpy(&(job->info), info, sizeof(struct stat));
+    job->info = *info;
+
+    memset(job->parent, 0, 16);
+
+    job->vfile.filepath = job->filepath;
+    job->vfile.read = fs_read;
+    job->vfile.close = fs_close;
+    job->vfile.fd = -1;
+    job->vfile.is_fs_file = TRUE;
 
     return job;
 }
 
 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);
+        parse_job_t *job = create_fs_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 = "1.1.5";
+static const char *const Version = "1.1.10";
 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("threads\t\t\t%d\n", ScanCtx.threads);
-    printf("tn_qscale\t%.1f/31.0\n", ScanCtx.tn_qscale);
+    printf("tn_qscale\t\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);
+    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\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 +65,8 @@ 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;
+    ScanCtx.archive_mode = args->archive_mode;
     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 +106,7 @@ 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 +139,11 @@ 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);
@@ -175,6 +191,7 @@ void sist2_web(web_args_t *args) {
 
     WebCtx.es_url = args->es_url;
     WebCtx.index_count = args->index_count;
+    WebCtx.b64credentials = args->b64credentials;
 
     for (int i = 0; i < args->index_count; i++) {
         char *abs_path = abspath(args->indices[i]);
@@ -196,6 +213,7 @@ void sist2_web(web_args_t *args) {
 
     serve(args->bind, args->port);
 }
+
 #endif
 
 
@@ -204,14 +222,14 @@ 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(),
@@ -222,28 +240,36 @@ 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=32768"),
             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"),
+            OPT_STRING(0, "archive", &scan_args->archive, "Archive file mode (skip|list|shallow|recurse). "
+                                                          "skip: Don't parse, list: only get file names as text, "
+                                                          "shallow: Don't parse archives inside archives. DEFAULT: recurse"),
 
-            #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"),
-            #endif
+            OPT_STRING(0, "auth", &web_args->credentials, "Basic auth in user:password format"),
+#endif
 
             OPT_END(),
     };
@@ -258,10 +284,10 @@ 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);
@@ -276,7 +302,7 @@ 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);
@@ -294,12 +320,20 @@ 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/arc.c

@@ -0,0 +1,152 @@
+#include "arc.h"
+#include "src/ctx.h"
+
+#define ARC_BUF_SIZE 8192
+
+int should_parse_filtered_file(const char *filepath, int ext) {
+    char tmp[PATH_MAX * 2];
+
+    if (ext == 0) {
+        return FALSE;
+    }
+
+    memcpy(tmp, filepath, ext - 1);
+    *(tmp + ext - 1) = '\0';
+
+    char *idx = strrchr(tmp, '.');
+
+    if (idx == NULL) {
+        return FALSE;
+    }
+
+    if (strcmp(idx, ".tar") == 0) {
+        return TRUE;
+    }
+
+    return FALSE;
+}
+
+int arc_read(struct vfile *f, void *buf, size_t size) {
+    return archive_read_data(f->arc, buf, size);
+}
+
+typedef struct arc_data {
+    vfile_t *f;
+    char buf[ARC_BUF_SIZE];
+} arc_data_f;
+
+int vfile_open_callback(struct archive *a, void *user_data) {
+    arc_data_f *data = user_data;
+
+    if (data->f->is_fs_file && data->f->fd == -1) {
+        data->f->fd = open(data->f->filepath, O_RDONLY);
+    }
+
+    return ARCHIVE_OK;
+}
+
+long vfile_read_callback(struct archive *a, void *user_data, const void **buf) {
+    arc_data_f *data = user_data;
+
+    *buf = data->buf;
+    return data->f->read(data->f, data->buf, ARC_BUF_SIZE);
+}
+
+int vfile_close_callback(struct archive *a, void *user_data) {
+    arc_data_f *data = user_data;
+
+    if (data->f->close != NULL) {
+        data->f->close(data->f);
+    }
+
+    return ARCHIVE_OK;
+}
+
+void parse_archive(vfile_t *f, document_t *doc) {
+
+    struct archive *a;
+    struct archive_entry *entry;
+
+    a = archive_read_new();
+
+    archive_read_support_filter_all(a);
+    archive_read_support_format_all(a);
+
+    arc_data_f data;
+    data.f = f;
+
+    int ret = 0;
+    if (data.f->is_fs_file) {
+        ret = archive_read_open_filename(a, doc->filepath, ARC_BUF_SIZE);
+    } else if (ScanCtx.archive_mode == ARC_MODE_RECURSE) {
+        ret = archive_read_open(
+                a, &data,
+                vfile_open_callback,
+                vfile_read_callback,
+                vfile_close_callback
+        );
+    } else {
+        archive_read_free(a);
+        return;
+    }
+
+    if (ret != ARCHIVE_OK) {
+        fprintf(stderr, "OPEN[%d]:%s %s\n", ret, archive_error_string(a), doc->filepath);
+        archive_read_free(a);
+        return;
+    }
+
+    if (ScanCtx.archive_mode == ARC_MODE_LIST) {
+
+        dyn_buffer_t buf = dyn_buffer_create();
+
+        while (archive_read_next_header(a, &entry) == ARCHIVE_OK) {
+            if (S_ISREG(archive_entry_stat(entry)->st_mode)) {
+
+                char *path = (char *) archive_entry_pathname(entry);
+
+                dyn_buffer_append_string(&buf, path);
+                dyn_buffer_write_char(&buf, '\n');
+            }
+        }
+        dyn_buffer_write_char(&buf, '\0');
+
+        meta_line_t *meta_list = malloc(sizeof(meta_line_t) + buf.cur);
+        meta_list->key = MetaContent;
+        strcpy(meta_list->strval, buf.buf);
+        APPEND_META(doc, meta_list);
+        dyn_buffer_destroy(&buf);
+
+    } else {
+
+        parse_job_t *sub_job = malloc(sizeof(parse_job_t) + PATH_MAX * 2);
+
+        sub_job->vfile.close = NULL;
+        sub_job->vfile.read = arc_read;
+        sub_job->vfile.arc = a;
+        sub_job->vfile.filepath = sub_job->filepath;
+        sub_job->vfile.is_fs_file = FALSE;
+        memcpy(sub_job->parent, doc->uuid, sizeof(uuid_t));
+
+        while (archive_read_next_header(a, &entry) == ARCHIVE_OK) {
+            sub_job->info = *archive_entry_stat(entry);
+            if (S_ISREG(sub_job->info.st_mode)) {
+                sprintf(sub_job->filepath, "%s#/%s", f->filepath, archive_entry_pathname(entry));
+                sub_job->base = (int) (strrchr(sub_job->filepath, '/') - sub_job->filepath) + 1;
+
+                char *p = strrchr(sub_job->filepath, '.');
+                if (p != NULL) {
+                    sub_job->ext = (int) (p - sub_job->filepath + 1);
+                } else {
+                    sub_job->ext = (int) strlen(sub_job->filepath);
+                }
+
+                parse(sub_job);
+            }
+        }
+
+        free(sub_job);
+    }
+
+    archive_read_free(a);
+}

src/parsing/arc.h

@@ -0,0 +1,12 @@
+#ifndef SIST2_ARC_H
+#define SIST2_ARC_H
+
+#include "src/sist.h"
+
+int should_parse_filtered_file(const char *filepath, int ext);
+
+void parse_archive(vfile_t *f, document_t *doc);
+
+int arc_read(struct vfile * f, void *buf, size_t size);
+
+#endif

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) {
+    if (ft_lib == NULL) {
-        FT_Init_FreeType(&library);
+        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

@@ -2,6 +2,7 @@
 #include "src/ctx.h"
 
 #define MIN_SIZE 32
+#define AVIO_BUF_SIZE 8192
 
 __always_inline
 AVCodecContext *alloc_jpeg_encoder(int dstW, int dstH, float qscale) {
@@ -89,9 +90,9 @@ AVFrame *read_frame(AVFormatContext *pFormatCtx, AVCodecContext *decoder, int st
             int read_frame_ret = av_read_frame(pFormatCtx, &avPacket);
 
             if (read_frame_ret != 0) {
-                if (read_frame_ret != AVERROR_EOF) {
+//                if (read_frame_ret != AVERROR_EOF) {
-                    fprintf(stderr, "Error reading frame: %d\n", read_frame_ret);
+//                    fprintf(stderr, "Error reading frame: %d\n", read_frame_ret);
-                }
+//                }
                 av_frame_free(&frame);
                 av_packet_unref(&avPacket);
                 return NULL;
@@ -188,22 +189,11 @@ void append_video_meta(AVFormatContext *pFormatCtx, AVFrame *frame, document_t *
     }
 }
 
-void parse_media(const char *filepath, document_t *doc) {
+void parse_media(AVFormatContext *pFormatCtx, document_t *doc) {
 
     int video_stream = -1;
     int audio_stream = -1;
 
-    AVFormatContext *pFormatCtx = avformat_alloc_context();
-    if (pFormatCtx == NULL) {
-        fprintf(stderr, "Could not allocate AVFormatContext! %s \n", filepath);
-        return;
-    }
-    int res = avformat_open_input(&pFormatCtx, filepath, NULL, NULL);
-    if (res < 0) {
-        fprintf(stderr, "media error: %s %s\n", filepath, av_err2str(res));
-        return;
-    }
-
     avformat_find_stream_info(pFormatCtx, NULL);
 
     for (int i = (int) pFormatCtx->nb_streams - 1; i >= 0; i--) {
@@ -242,7 +232,7 @@ 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) {
@@ -314,3 +304,58 @@ void parse_media(const char *filepath, document_t *doc) {
     avformat_free_context(pFormatCtx);
 }
 
+void parse_media_filename(const char *filepath, document_t *doc) {
+
+    AVFormatContext *pFormatCtx = avformat_alloc_context();
+    if (pFormatCtx == NULL) {
+        fprintf(stderr, "Could not allocate AVFormatContext! %s \n", filepath);
+        return;
+    }
+    int res = avformat_open_input(&pFormatCtx, filepath, NULL, NULL);
+    if (res < 0) {
+        fprintf(stderr, "media error: %s %s\n", filepath, av_err2str(res));
+        return;
+    }
+
+    parse_media(pFormatCtx, doc);
+}
+
+
+int vfile_read(void *ptr, uint8_t *buf, int buf_size) {
+    struct vfile *f = ptr;
+
+    int ret = f->read(f, buf, buf_size);
+
+    if (ret == 0) {
+        return AVERROR_EOF;
+    }
+    return ret;
+}
+
+void parse_media_vfile(struct vfile *f, document_t *doc) {
+
+    AVFormatContext *pFormatCtx = avformat_alloc_context();
+    if (pFormatCtx == NULL) {
+        fprintf(stderr, "Could not allocate AVFormatContext! %s \n", f->filepath);
+        return;
+    }
+
+    unsigned char *buffer = (unsigned char *) av_malloc(AVIO_BUF_SIZE);
+    AVIOContext *io_ctx = avio_alloc_context(buffer, AVIO_BUF_SIZE, 0, f, vfile_read, NULL, NULL);
+
+    pFormatCtx->pb = io_ctx;
+    pFormatCtx->flags |= AVFMT_FLAG_CUSTOM_IO;
+
+    int res = avformat_open_input(&pFormatCtx, "", NULL, NULL);
+    if (res == -5) {
+        // Tried to parse media that requires seek
+        return;
+    } else if(res < 0) {
+        fprintf(stderr, "media error: %s %s\n", f->filepath, av_err2str(res));
+        return;
+    }
+
+    parse_media(pFormatCtx, doc);
+    av_free(io_ctx);
+}
+

src/parsing/media.h

@@ -7,6 +7,8 @@
 #define MIN_VIDEO_SIZE 1024 * 64
 #define MIN_IMAGE_SIZE 1024 * 2
 
-void parse_media(const char * filepath, document_t *doc);
+void parse_media_filename(const char * filepath, document_t *doc);
+
+void parse_media_vfile(struct vfile *f, document_t *doc);
 
 #endif

src/parsing/mime.h

@@ -8,7 +8,7 @@
 #define MIME_EMPTY 1
 
 #define DONT_PARSE 0x80000000
-#define SHOULD_PARSE(mime_id) (mime_id & DONT_PARSE) != DONT_PARSE
+#define SHOULD_PARSE(mime_id) (mime_id & DONT_PARSE) != DONT_PARSE && mime_id != 0
 
 #define PDF_MASK 0x40000000
 #define IS_PDF(mime_id) (mime_id & PDF_MASK) == PDF_MASK
@@ -16,6 +16,12 @@
 #define FONT_MASK 0x20000000
 #define IS_FONT(mime_id) (mime_id & FONT_MASK) == FONT_MASK
 
+#define ARC_MASK 0x10000000
+#define IS_ARC(mime_id) (mime_id & ARC_MASK) == ARC_MASK
+
+#define ARC_FILTER_MASK 0x08000000
+#define IS_ARC_FILTER(mime_id) (mime_id & ARC_FILTER_MASK) == ARC_FILTER_MASK
+
 enum major_mime {
     MimeInvalid = 0,
     MimeModel = 1,

src/parsing/mime_generated.c

@@ -20,7 +20,7 @@ enum mime {
     application_freeloader=655372,
     application_futuresplash=655373,
     application_groupwise=655374,
-    application_gzip=655375,
+    application_gzip=655375 | 0x08000000,
     application_hta=655376,
     application_i_deas=655377,
     application_iges=655378,
@@ -82,342 +82,346 @@ enum mime {
     application_vnd_xara=655434,
     application_vocaltec_media_desc=655435,
     application_vocaltec_media_file=655436,
-    application_winhelp=655437,
+    application_warc=655437,
-    application_wordperfect=655438,
+    application_winhelp=655438,
-    application_wordperfect6_0=655439,
+    application_wordperfect=655439,
-    application_wordperfect6_1=655440,
+    application_wordperfect6_0=655440,
-    application_x_123=655441,
+    application_wordperfect6_1=655441,
-    application_x_7z_compressed=655442,
+    application_x_123=655442,
-    application_x_aim=655443,
+    application_x_7z_compressed=655443 | 0x10000000,
-    application_x_apple_diskimage=655444,
+    application_x_aim=655444,
-    application_x_arc=655445,
+    application_x_apple_diskimage=655445,
-    application_x_archive=655446,
+    application_x_arc=655446 | 0x10000000,
-    application_x_atari_7800_rom=655447,
+    application_x_archive=655447,
-    application_x_authorware_bin=655448,
+    application_x_atari_7800_rom=655448,
-    application_x_authorware_map=655449,
+    application_x_authorware_bin=655449,
-    application_x_authorware_seg=655450,
+    application_x_authorware_map=655450,
-    application_x_avira_qua=655451,
+    application_x_authorware_seg=655451,
-    application_x_bcpio=655452,
+    application_x_avira_qua=655452,
-    application_x_bittorrent=655453,
+    application_x_bcpio=655453,
-    application_x_bsh=655454,
+    application_x_bittorrent=655454,
-    application_x_bytecode_python=655455,
+    application_x_bsh=655455,
-    application_x_bzip=655456,
+    application_x_bytecode_python=655456,
-    application_x_bzip2=655457,
+    application_x_bzip=655457,
-    application_x_cbr=655458,
+    application_x_bzip2=655458 | 0x08000000,
-    application_x_cbz=655459 | 0x40000000,
+    application_x_cbr=655459,
-    application_x_cdlink=655460,
+    application_x_cbz=655460 | 0x40000000,
-    application_x_chat=655461,
+    application_x_cdlink=655461,
-    application_x_chrome_extension=655462,
+    application_x_chat=655462,
-    application_x_cocoa=655463,
+    application_x_chrome_extension=655463,
-    application_x_conference=655464,
+    application_x_cocoa=655464,
-    application_x_coredump=655465,
+    application_x_conference=655465,
-    application_x_cpio=655466,
+    application_x_coredump=655466,
-    application_x_dbf=655467,
+    application_x_cpio=655467,
-    application_x_dbt=655468,
+    application_x_dbf=655468,
-    application_x_debian_package=655469,
+    application_x_dbt=655469,
-    application_x_deepv=655470,
+    application_x_debian_package=655470,
-    application_x_director=655471,
+    application_x_deepv=655471,
-    application_x_dmp=655472,
+    application_x_director=655472,
-    application_x_dosdriver=655473,
+    application_x_dmp=655473,
-    application_x_dosexec=655474,
+    application_x_dosdriver=655474,
-    application_x_dvi=655475,
+    application_x_dosexec=655475,
-    application_x_elc=655476,
+    application_x_dvi=655476,
+    application_x_elc=655477,
     application_x_empty=1,
-    application_x_envoy=655478,
+    application_x_envoy=655479,
-    application_x_esrehber=655479,
+    application_x_esrehber=655480,
-    application_x_excel=655480,
+    application_x_excel=655481,
-    application_x_executable=655481,
+    application_x_executable=655482,
-    application_x_font_gdos=655482,
+    application_x_font_gdos=655483,
-    application_x_font_pf2=655483,
+    application_x_font_pf2=655484,
-    application_x_font_pfm=655484,
+    application_x_font_pfm=655485,
-    application_x_font_sfn=655485,
+    application_x_font_sfn=655486,
-    application_x_font_ttf=655486 | 0x20000000,
+    application_x_font_ttf=655487 | 0x20000000,
-    application_x_freelance=655487,
+    application_x_freelance=655488,
-    application_x_gamecube_rom=655488,
+    application_x_gamecube_rom=655489,
-    application_x_gdbm=655489,
+    application_x_gdbm=655490,
-    application_x_gettext_translation=655490,
+    application_x_gettext_translation=655491,
-    application_x_git=655491,
+    application_x_git=655492,
-    application_x_gsp=655492,
+    application_x_gsp=655493,
-    application_x_gss=655493,
+    application_x_gss=655494,
-    application_x_gtar=655494,
+    application_x_gtar=655495,
-    application_x_gzip=655495,
+    application_x_gzip=655496,
-    application_x_hdf=655496,
+    application_x_hdf=655497,
-    application_x_helpfile=655497,
+    application_x_helpfile=655498,
-    application_x_httpd_imap=655498,
+    application_x_httpd_imap=655499,
-    application_x_ima=655499,
+    application_x_ima=655500,
-    application_x_innosetup=655500,
+    application_x_innosetup=655501,
-    application_x_internett_signup=655501,
+    application_x_internett_signup=655502,
-    application_x_inventor=655502,
+    application_x_inventor=655503,
-    application_x_ip2=655503,
+    application_x_ip2=655504,
-    application_x_java_applet=655504,
+    application_x_java_applet=655505,
-    application_x_java_commerce=655505,
+    application_x_java_commerce=655506,
-    application_x_java_image=655506,
+    application_x_java_image=655507,
-    application_x_java_jmod=655507,
+    application_x_java_jmod=655508,
-    application_x_java_keystore=655508,
+    application_x_java_keystore=655509,
-    application_x_kdelnk=655509,
+    application_x_kdelnk=655510,
-    application_x_koan=655510,
+    application_x_koan=655511,
-    application_x_latex=655511,
+    application_x_latex=655512,
-    application_x_livescreen=655512,
+    application_x_livescreen=655513,
-    application_x_lotus=655513,
+    application_x_lotus=655514,
-    application_x_lz4=655514,
+    application_x_lz4=655515 | 0x08000000,
-    application_x_lz4_json=655515,
+    application_x_lz4_json=655516,
-    application_x_lzh=655516,
+    application_x_lzh=655517,
-    application_x_lzh_compressed=655517,
+    application_x_lzh_compressed=655518,
-    application_x_lzx=655518,
+    application_x_lzip=655519 | 0x08000000,
-    application_x_mach_binary=655519,
+    application_x_lzma=655520 | 0x08000000,
-    application_x_mach_executable=655520,
+    application_x_lzop=655521 | 0x08000000,
-    application_x_magic_cap_package_1_0=655521,
+    application_x_lzx=655522,
-    application_x_mathcad=655522,
+    application_x_mach_binary=655523,
-    application_x_maxis_dbpf=655523,
+    application_x_mach_executable=655524,
-    application_x_meme=655524,
+    application_x_magic_cap_package_1_0=655525,
-    application_x_midi=655525,
+    application_x_mathcad=655526,
-    application_x_mif=655526,
+    application_x_maxis_dbpf=655527,
-    application_x_mix_transfer=655527,
+    application_x_meme=655528,
-    application_x_mobipocket_ebook=655528,
+    application_x_midi=655529,
-    application_x_ms_compress_szdd=655529,
+    application_x_mif=655530,
-    application_x_ms_pdb=655530,
+    application_x_mix_transfer=655531,
-    application_x_ms_reader=655531,
+    application_x_mobipocket_ebook=655532,
-    application_x_msaccess=655532,
+    application_x_ms_compress_szdd=655533,
-    application_x_navi_animation=655533,
+    application_x_ms_pdb=655534,
-    application_x_navidoc=655534,
+    application_x_ms_reader=655535,
-    application_x_navimap=655535,
+    application_x_msaccess=655536,
-    application_x_navistyle=655536,
+    application_x_navi_animation=655537,
-    application_x_nes_rom=655537,
+    application_x_navidoc=655538,
-    application_x_netcdf=655538,
+    application_x_navimap=655539,
-    application_x_newton_compatible_pkg=655539,
+    application_x_navistyle=655540,
-    application_x_nintendo_ds_rom=655540,
+    application_x_nes_rom=655541,
-    application_x_object=655541,
+    application_x_netcdf=655542,
-    application_x_omc=655542,
+    application_x_newton_compatible_pkg=655543,
-    application_x_omcdatamaker=655543,
+    application_x_nintendo_ds_rom=655544,
-    application_x_omcregerator=655544,
+    application_x_object=655545,
-    application_x_pagemaker=655545,
+    application_x_omc=655546,
-    application_x_pcl=655546,
+    application_x_omcdatamaker=655547,
-    application_x_pgp_keyring=655547,
+    application_x_omcregerator=655548,
-    application_x_pixclscript=655548,
+    application_x_pagemaker=655549,
-    application_x_pkcs7_certreqresp=655549,
+    application_x_pcl=655550,
-    application_x_pkcs7_signature=655550,
+    application_x_pgp_keyring=655551,
-    application_x_project=655551,
+    application_x_pixclscript=655552,
-    application_x_qpro=655552,
+    application_x_pkcs7_certreqresp=655553,
-    application_x_rar=655553,
+    application_x_pkcs7_signature=655554,
-    application_x_rpm=655554,
+    application_x_project=655555,
-    application_x_sdp=655555,
+    application_x_qpro=655556,
-    application_x_sea=655556,
+    application_x_rar=655557 | 0x10000000,
-    application_x_seelogo=655557,
+    application_x_rpm=655558,
-    application_x_setupscript=655558,
+    application_x_sdp=655559,
-    application_x_shar=655559,
+    application_x_sea=655560,
-    application_x_sharedlib=655560,
+    application_x_seelogo=655561,
-    application_x_shockwave_flash=655561,
+    application_x_setupscript=655562,
-    application_x_snappy_framed=655562,
+    application_x_shar=655563,
-    application_x_sprite=655563,
+    application_x_sharedlib=655564,
-    application_x_sqlite3=655564,
+    application_x_shockwave_flash=655565,
-    application_x_sv4cpio=655565,
+    application_x_snappy_framed=655566,
-    application_x_sv4crc=655566,
+    application_x_sprite=655567,
-    application_x_tar=655567,
+    application_x_sqlite3=655568,
-    application_x_tbook=655568,
+    application_x_sv4cpio=655569,
-    application_x_terminfo=655569,
+    application_x_sv4crc=655570,
-    application_x_terminfo2=655570,
+    application_x_tar=655571 | 0x10000000,
-    application_x_tex_tfm=655571,
+    application_x_tbook=655572,
-    application_x_texinfo=655572,
+    application_x_terminfo=655573,
-    application_x_ustar=655573,
+    application_x_terminfo2=655574,
-    application_x_visio=655574,
+    application_x_tex_tfm=655575,
-    application_x_vnd_audioexplosion_mzz=655575,
+    application_x_texinfo=655576,
-    application_x_vnd_ls_xpix=655576,
+    application_x_ustar=655577,
-    application_x_vrml=655577,
+    application_x_visio=655578,
-    application_x_wais_source=655578,
+    application_x_vnd_audioexplosion_mzz=655579,
-    application_x_wine_extension_ini=655579,
+    application_x_vnd_ls_xpix=655580,
-    application_x_wintalk=655580,
+    application_x_vrml=655581,
-    application_x_world=655581,
+    application_x_wais_source=655582,
-    application_x_wri=655582,
+    application_x_wine_extension_ini=655583,
-    application_x_x509_ca_cert=655583,
+    application_x_wintalk=655584,
-    application_x_xz=655584,
+    application_x_world=655585,
-    application_x_zip=655585,
+    application_x_wri=655586,
-    application_x_zstd=655586,
+    application_x_x509_ca_cert=655587,
-    application_xml=655587,
+    application_x_xz=655588 | 0x08000000,
-    application_zip=655588,
+    application_x_zip=655589,
-    application_zlib=655589,
+    application_x_zstd=655590 | 0x08000000,
-    audio_it=458982,
+    application_xml=655591,
-    audio_make=458983,
+    application_zip=655592 | 0x10000000,
-    audio_mid=458984,
+    application_zlib=655593,
-    audio_midi=458985,
+    audio_it=458986,
-    audio_mp4=458986,
+    audio_make=458987,
-    audio_mpeg=458987,
+    audio_mid=458988,
-    audio_ogg=458988,
+    audio_midi=458989,
-    audio_s3m=458989,
+    audio_mp4=458990,
-    audio_tsp_audio=458990,
+    audio_mpeg=458991,
-    audio_tsplayer=458991,
+    audio_ogg=458992,
-    audio_vnd_qcelp=458992,
+    audio_s3m=458993,
-    audio_voxware=458993,
+    audio_tsp_audio=458994,
-    audio_x_aiff=458994,
+    audio_tsplayer=458995,
-    audio_x_flac=458995,
+    audio_vnd_qcelp=458996,
-    audio_x_gsm=458996,
+    audio_voxware=458997,
-    audio_x_hx_aac_adts=458997,
+    audio_x_aiff=458998,
-    audio_x_jam=458998,
+    audio_x_flac=458999,
-    audio_x_liveaudio=458999,
+    audio_x_gsm=459000,
-    audio_x_m4a=459000,
+    audio_x_hx_aac_adts=459001,
-    audio_x_midi=459001,
+    audio_x_jam=459002,
-    audio_x_mod=459002,
+    audio_x_liveaudio=459003,
-    audio_x_mp4a_latm=459003,
+    audio_x_m4a=459004,
-    audio_x_mpeg_3=459004,
+    audio_x_midi=459005,
-    audio_x_mpequrl=459005,
+    audio_x_mod=459006,
-    audio_x_nspaudio=459006,
+    audio_x_mp4a_latm=459007,
-    audio_x_pn_realaudio=459007,
+    audio_x_mpeg_3=459008,
-    audio_x_psid=459008,
+    audio_x_mpequrl=459009,
-    audio_x_realaudio=459009,
+    audio_x_nspaudio=459010,
-    audio_x_twinvq=459010,
+    audio_x_pn_realaudio=459011,
-    audio_x_twinvq_plugin=459011,
+    audio_x_psid=459012,
-    audio_x_voc=459012,
+    audio_x_realaudio=459013,
-    audio_x_wav=459013,
+    audio_x_twinvq=459014,
-    audio_xm=459014,
+    audio_x_twinvq_plugin=459015,
-    font_otf=327943 | 0x20000000,
+    audio_x_voc=459016,
-    font_sfnt=327944 | 0x20000000,
+    audio_x_wav=459017,
-    font_woff=327945 | 0x20000000,
+    audio_xm=459018,
-    font_woff2=327946 | 0x20000000,
+    font_otf=327947 | 0x20000000,
-    image_cmu_raster=524555,
+    font_sfnt=327948 | 0x20000000,
-    image_fif=524556,
+    font_woff=327949 | 0x20000000,
-    image_florian=524557,
+    font_woff2=327950 | 0x20000000,
-    image_g3fax=524558,
+    image_cmu_raster=524559,
-    image_gif=524559,
+    image_fif=524560,
-    image_heic=524560,
+    image_florian=524561,
-    image_ief=524561,
+    image_g3fax=524562,
-    image_jpeg=524562,
+    image_gif=524563,
-    image_jutvision=524563,
+    image_heic=524564,
-    image_naplps=524564,
+    image_ief=524565,
-    image_pict=524565,
+    image_jpeg=524566,
-    image_png=524566,
+    image_jutvision=524567,
-    image_svg=524567 | 0x80000000,
+    image_naplps=524568,
-    image_svg_xml=524568 | 0x80000000,
+    image_pict=524569,
-    image_tiff=524569,
+    image_png=524570,
-    image_vnd_adobe_photoshop=524570 | 0x80000000,
+    image_svg=524571 | 0x80000000,
-    image_vnd_djvu=524571 | 0x80000000,
+    image_svg_xml=524572 | 0x80000000,
-    image_vnd_fpx=524572,
+    image_tiff=524573,
-    image_vnd_microsoft_icon=524573,
+    image_vnd_adobe_photoshop=524574 | 0x80000000,
-    image_vnd_rn_realflash=524574,
+    image_vnd_djvu=524575 | 0x80000000,
-    image_vnd_rn_realpix=524575,
+    image_vnd_fpx=524576,
-    image_vnd_wap_wbmp=524576,
+    image_vnd_microsoft_icon=524577,
-    image_vnd_xiff=524577,
+    image_vnd_rn_realflash=524578,
-    image_webp=524578,
+    image_vnd_rn_realpix=524579,
-    image_wmf=524579,
+    image_vnd_wap_wbmp=524580,
-    image_x_3ds=524580,
+    image_vnd_xiff=524581,
-    image_x_cmu_raster=524581,
+    image_webp=524582,
-    image_x_cur=524582,
+    image_wmf=524583,
-    image_x_dwg=524583,
+    image_x_3ds=524584,
-    image_x_eps=524584,
+    image_x_cmu_raster=524585,
-    image_x_exr=524585,
+    image_x_cur=524586,
-    image_x_gem=524586,
+    image_x_dwg=524587,
-    image_x_icns=524587,
+    image_x_eps=524588,
-    image_x_icon=524588 | 0x80000000,
+    image_x_exr=524589,
-    image_x_jg=524589,
+    image_x_gem=524590,
-    image_x_jps=524590,
+    image_x_icns=524591,
-    image_x_ms_bmp=524591,
+    image_x_icon=524592 | 0x80000000,
-    image_x_niff=524592,
+    image_x_jg=524593,
-    image_x_pcx=524593,
+    image_x_jps=524594,
-    image_x_pict=524594,
+    image_x_ms_bmp=524595,
-    image_x_portable_bitmap=524595,
+    image_x_niff=524596,
-    image_x_portable_graymap=524596,
+    image_x_pcx=524597,
-    image_x_portable_pixmap=524597,
+    image_x_pict=524598,
-    image_x_quicktime=524598,
+    image_x_portable_bitmap=524599,
-    image_x_rgb=524599,
+    image_x_portable_graymap=524600,
-    image_x_tga=524600,
+    image_x_portable_pixmap=524601,
-    image_x_tiff=524601,
+    image_x_quicktime=524602,
-    image_x_win_bitmap=524602,
+    image_x_rgb=524603,
-    image_x_xcf=524603 | 0x80000000,
+    image_x_tga=524604,
-    image_x_xpixmap=524604 | 0x80000000,
+    image_x_tiff=524605,
-    image_x_xwindowdump=524605,
+    image_x_win_bitmap=524606,
-    message_news=196926,
+    image_x_xcf=524607 | 0x80000000,
-    message_rfc822=196927,
+    image_x_xpixmap=524608 | 0x80000000,
-    model_vnd_dwf=65856,
+    image_x_xwindowdump=524609,
-    model_vnd_gdl=65857,
+    message_news=196930,
-    model_vnd_gs_gdl=65858,
+    message_rfc822=196931,
-    model_vrml=65859,
+    model_vnd_dwf=65860,
-    model_x_pov=65860,
+    model_vnd_gdl=65861,
-    text_PGP=590149,
+    model_vnd_gs_gdl=65862,
-    text_asp=590150,
+    model_vrml=65863,
-    text_css=590151,
+    model_x_pov=65864,
-    text_html=590152,
+    text_PGP=590153,
-    text_javascript=590153,
+    text_asp=590154,
-    text_mcf=590154,
+    text_css=590155,
-    text_pascal=590155,
+    text_html=590156,
-    text_plain=590156,
+    text_javascript=590157,
-    text_richtext=590157,
+    text_mcf=590158,
-    text_rtf=590158,
+    text_pascal=590159,
-    text_scriplet=590159,
+    text_plain=590160,
-    text_tab_separated_values=590160,
+    text_richtext=590161,
-    text_troff=590161,
+    text_rtf=590162,
-    text_uri_list=590162,
+    text_scriplet=590163,
-    text_vnd_abc=590163,
+    text_tab_separated_values=590164,
-    text_vnd_fmi_flexstor=590164,
+    text_troff=590165,
-    text_vnd_wap_wml=590165,
+    text_uri_list=590166,
-    text_vnd_wap_wmlscript=590166,
+    text_vnd_abc=590167,
-    text_webviewhtml=590167,
+    text_vnd_fmi_flexstor=590168,
-    text_x_Algol68=590168,
+    text_vnd_wap_wml=590169,
-    text_x_asm=590169,
+    text_vnd_wap_wmlscript=590170,
-    text_x_audiosoft_intra=590170,
+    text_webviewhtml=590171,
-    text_x_awk=590171,
+    text_x_Algol68=590172,
-    text_x_bcpl=590172,
+    text_x_asm=590173,
-    text_x_c=590173,
+    text_x_audiosoft_intra=590174,
-    text_x_c__=590174,
+    text_x_awk=590175,
-    text_x_component=590175,
+    text_x_bcpl=590176,
-    text_x_diff=590176,
+    text_x_c=590177,
-    text_x_fortran=590177,
+    text_x_c__=590178,
-    text_x_java=590178,
+    text_x_component=590179,
-    text_x_la_asf=590179,
+    text_x_diff=590180,
-    text_x_lisp=590180,
+    text_x_fortran=590181,
-    text_x_m=590181,
+    text_x_java=590182,
-    text_x_m4=590182,
+    text_x_la_asf=590183,
-    text_x_makefile=590183,
+    text_x_lisp=590184,
-    text_x_ms_regedit=590184,
+    text_x_m=590185,
-    text_x_msdos_batch=590185,
+    text_x_m4=590186,
-    text_x_objective_c=590186,
+    text_x_makefile=590187,
-    text_x_pascal=590187,
+    text_x_ms_regedit=590188,
-    text_x_perl=590188,
+    text_x_msdos_batch=590189,
-    text_x_php=590189,
+    text_x_objective_c=590190,
-    text_x_po=590190,
+    text_x_pascal=590191,
-    text_x_python=590191,
+    text_x_perl=590192,
-    text_x_ruby=590192,
+    text_x_php=590193,
-    text_x_sass=590193,
+    text_x_po=590194,
-    text_x_scss=590194,
+    text_x_python=590195,
-    text_x_server_parsed_html=590195,
+    text_x_ruby=590196,
-    text_x_setext=590196,
+    text_x_sass=590197,
-    text_x_sgml=590197,
+    text_x_scss=590198,
-    text_x_shellscript=590198,
+    text_x_server_parsed_html=590199,
-    text_x_speech=590199,
+    text_x_setext=590200,
-    text_x_tcl=590200,
+    text_x_sgml=590201,
-    text_x_tex=590201,
+    text_x_shellscript=590202,
-    text_x_uil=590202,
+    text_x_speech=590203,
-    text_x_uuencode=590203,
+    text_x_tcl=590204,
-    text_x_vcalendar=590204,
+    text_x_tex=590205,
-    text_x_vcard=590205,
+    text_x_uil=590206,
-    text_xml=590206,
+    text_x_uuencode=590207,
-    video_MP2T=393599,
+    text_x_vcalendar=590208,
-    video_animaflex=393600,
+    text_x_vcard=590209,
-    video_avi=393601,
+    text_xml=590210,
-    video_avs_video=393602,
+    video_MP2T=393603,
-    video_mp4=393603,
+    video_animaflex=393604,
-    video_mpeg=393604,
+    video_avi=393605,
-    video_quicktime=393605,
+    video_avs_video=393606,
-    video_vdo=393606,
+    video_mp4=393607,
-    video_vivo=393607,
+    video_mpeg=393608,
-    video_vnd_rn_realvideo=393608,
+    video_quicktime=393609,
-    video_vosaic=393609,
+    video_vdo=393610,
-    video_webm=393610,
+    video_vivo=393611,
-    video_x_amt_demorun=393611,
+    video_vnd_rn_realvideo=393612,
-    video_x_amt_showrun=393612,
+    video_vosaic=393613,
-    video_x_atomic3d_feature=393613,
+    video_webm=393614,
-    video_x_dl=393614,
+    video_x_amt_demorun=393615,
-    video_x_dv=393615,
+    video_x_amt_showrun=393616,
-    video_x_fli=393616,
+    video_x_atomic3d_feature=393617,
-    video_x_flv=393617,
+    video_x_dl=393618,
-    video_x_isvideo=393618,
+    video_x_dv=393619,
-    video_x_jng=393619 | 0x80000000,
+    video_x_fli=393620,
-    video_x_m4v=393620,
+    video_x_flv=393621,
-    video_x_matroska=393621,
+    video_x_isvideo=393622,
-    video_x_mng=393622,
+    video_x_jng=393623 | 0x80000000,
-    video_x_motion_jpeg=393623,
+    video_x_m4v=393624,
-    video_x_ms_asf=393624,
+    video_x_matroska=393625,
-    video_x_msvideo=393625,
+    video_x_mng=393626,
-    video_x_qtc=393626,
+    video_x_motion_jpeg=393627,
-    video_x_sgi_movie=393627,
+    video_x_ms_asf=393628,
-    x_epoc_x_sisx_app=721308,
+    video_x_msvideo=393629,
+    video_x_qtc=393630,
+    video_x_sgi_movie=393631,
+    x_epoc_x_sisx_app=721312,
 };
 char *mime_get_mime_text(unsigned int mime_id) {switch (mime_id) {
 case application_arj: return "application/arj";
@@ -832,6 +836,10 @@ case audio_x_hx_aac_adts: return "audio/x-hx-aac-adts";
 case application_x_chrome_extension: return "application/x-chrome-extension";
 case image_heic: return "image/heic";
 case image_x_gem: return "image/x-gem";
+case application_x_lzma: return "application/x-lzma";
+case application_warc: return "application/warc";
+case application_x_lzip: return "application/x-lzip";
+case application_x_lzop: return "application/x-lzop";
 default: return NULL;}}
 GHashTable *mime_get_ext_table() {GHashTable *ext_table = g_hash_table_new(g_str_hash, g_str_equal);
 g_hash_table_insert(ext_table, "arj", (gpointer)application_arj);
@@ -1182,6 +1190,9 @@ 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);
@@ -1334,6 +1345,10 @@ g_hash_table_insert(ext_table, "z", (gpointer)application_zlib);
 g_hash_table_insert(ext_table, "pf2", (gpointer)application_x_font_pf2);
 g_hash_table_insert(ext_table, "jmod", (gpointer)application_x_java_jmod);
 g_hash_table_insert(ext_table, "heic", (gpointer)image_heic);
+g_hash_table_insert(ext_table, "lzma", (gpointer)application_x_lzma);
+g_hash_table_insert(ext_table, "warc", (gpointer)application_warc);
+g_hash_table_insert(ext_table, "lz", (gpointer)application_x_lzip);
+g_hash_table_insert(ext_table, "lzo", (gpointer)application_x_lzop);
 return ext_table;}
 GHashTable *mime_get_mime_table() {GHashTable *mime_table = g_hash_table_new(g_str_hash, g_str_equal);
 g_hash_table_insert(mime_table, "application/arj", (gpointer)application_arj);
@@ -1748,5 +1763,9 @@ g_hash_table_insert(mime_table, "audio/x-hx-aac-adts", (gpointer)audio_x_hx_aac_
 g_hash_table_insert(mime_table, "application/x-chrome-extension", (gpointer)application_x_chrome_extension);
 g_hash_table_insert(mime_table, "image/heic", (gpointer)image_heic);
 g_hash_table_insert(mime_table, "image/x-gem", (gpointer)image_x_gem);
+g_hash_table_insert(mime_table, "application/x-lzma", (gpointer)application_x_lzma);
+g_hash_table_insert(mime_table, "application/warc", (gpointer)application_warc);
+g_hash_table_insert(mime_table, "application/x-lzip", (gpointer)application_x_lzip);
+g_hash_table_insert(mime_table, "application/x-lzop", (gpointer)application_x_lzop);
 return mime_table;}
 #endif

src/parsing/parse.c

@@ -1,9 +1,32 @@
+#include <src/ctx.h>
 #include "src/sist.h"
 #include "src/ctx.h"
 
 __thread magic_t Magic = NULL;
 
-void *read_all(parse_job_t *job, const char *buf, int bytes_read, int *fd) {
+int fs_read(struct vfile *f, void *buf, size_t size) {
+
+    if (f->fd == -1) {
+        f->fd = open(f->filepath, O_RDONLY);
+        if (f->fd == -1) {
+            perror("open");
+            printf("%s\n", f->filepath);
+            return -1;
+        }
+    }
+
+    return read(f->fd, buf, size);
+}
+
+#define CLOSE_FILE(f) if (f.close != NULL) {f.close(&f);};
+
+void fs_close(struct vfile *f) {
+    if (f->fd != -1) {
+        close(f->fd);
+    }
+}
+
+void *read_all(parse_job_t *job, const char *buf, int bytes_read) {
 
     void *full_buf;
 
@@ -11,17 +34,10 @@ void *read_all(parse_job_t *job, const char *buf, int bytes_read, int *fd) {
         full_buf = malloc(job->info.st_size);
         memcpy(full_buf, buf, job->info.st_size);
     } else {
-        if (*fd == -1) {
-            *fd = open(job->filepath, O_RDONLY);
-            if (*fd == -1) {
-                perror("open");
-                printf("%s\n", job->filepath);
-                return NULL;
-            }
-        }
         full_buf = malloc(job->info.st_size);
         memcpy(full_buf, buf, bytes_read);
-        int ret = read(*fd, full_buf + bytes_read, job->info.st_size - bytes_read);
+
+        int ret = job->vfile.read(&job->vfile, full_buf + bytes_read, job->info.st_size - bytes_read);
         if (ret == -1) {
             perror("read");
             return NULL;
@@ -36,15 +52,14 @@ void parse(void *arg) {
     parse_job_t *job = arg;
     document_t doc;
 
-    if (incremental_get(ScanCtx.original_table, job->info.st_ino) == job->info.st_mtim.tv_sec) {
+    int inc_ts = incremental_get(ScanCtx.original_table, job->info.st_ino);
+    if (inc_ts != 0 && inc_ts == job->info.st_mtim.tv_sec) {
         incremental_mark_file_for_copy(ScanCtx.copy_table, job->info.st_ino);
-        free(job);
         return;
     }
 
     if (Magic == NULL) {
         Magic = magic_open(MAGIC_MIME_TYPE);
-        magic_load(Magic, NULL);
     }
 
     doc.filepath = job->filepath;
@@ -66,24 +81,13 @@ void parse(void *arg) {
         doc.mime = mime_get_mime_by_ext(ScanCtx.ext_table, job->filepath + job->ext);
     }
 
-    int fd = -1;
     int bytes_read = 0;
 
     if (doc.mime == 0) {
         // Get mime type with libmagic
-        fd = open(job->filepath, O_RDONLY);
+        bytes_read = job->vfile.read(&job->vfile, buf, PARSE_BUF_SIZE);
-        if (fd == -1) {
-            perror("open");
-            free(job);
-            return;
-        }
-
-        bytes_read = read(fd, buf, PARSE_BUF_SIZE);
-
         if (bytes_read == -1) {
-            perror("read");
+            CLOSE_FILE(job->vfile)
-            close(fd);
-            free(job);
             return;
         }
 
@@ -101,11 +105,16 @@ void parse(void *arg) {
     if (!(SHOULD_PARSE(doc.mime))) {
 
     } else if ((mmime == MimeVideo && doc.size >= MIN_VIDEO_SIZE) ||
-    (mmime == MimeImage && doc.size >= MIN_IMAGE_SIZE) || mmime == MimeAudio) {
+               (mmime == MimeImage && doc.size >= MIN_IMAGE_SIZE) || mmime == MimeAudio) {
-        parse_media(job->filepath, &doc);
+
+        if (job->vfile.is_fs_file) {
+            parse_media_filename(job->filepath, &doc);
+        } else {
+            parse_media_vfile(&job->vfile, &doc);
+        }
 
     } else if (IS_PDF(doc.mime)) {
-        void *pdf_buf = read_all(job, (char *) buf, bytes_read, &fd);
+        void *pdf_buf = read_all(job, (char *) buf, bytes_read);
         parse_pdf(pdf_buf, doc.size, &doc);
 
         if (pdf_buf != buf && pdf_buf != NULL) {
@@ -113,22 +122,35 @@ void parse(void *arg) {
         }
 
     } else if (mmime == MimeText && ScanCtx.content_size > 0) {
-        parse_text(bytes_read, &fd, (char *) buf, &doc);
+        parse_text(bytes_read, &job->vfile, (char *) buf, &doc);
 
     } else if (IS_FONT(doc.mime)) {
-        void *font_buf = read_all(job, (char *) buf, bytes_read, &fd);
+        void *font_buf = read_all(job, (char *) buf, bytes_read);
         parse_font(font_buf, doc.size, &doc);
 
         if (font_buf != buf && font_buf != NULL) {
             free(font_buf);
         }
+    } else if (
+            ScanCtx.archive_mode != ARC_MODE_SKIP && (
+                    IS_ARC(doc.mime) ||
+                    (IS_ARC_FILTER(doc.mime) && should_parse_filtered_file(doc.filepath, doc.ext))
+            )) {
+        parse_archive(&job->vfile, &doc);
+    }
+
+    //Parent meta
+    if (!uuid_is_null(job->parent)) {
+        char tmp[UUID_STR_LEN];
+        uuid_unparse(job->parent, tmp);
+
+        meta_line_t *meta_parent = malloc(sizeof(meta_line_t) + UUID_STR_LEN + 1);
+        meta_parent->key = MetaParent;
+        strcpy(meta_parent->strval, tmp);
+        APPEND_META((&doc), meta_parent)
     }
 
     write_document(&doc);
 
-    if (fd != -1) {
+    CLOSE_FILE(job->vfile)
-        close(fd);
-    }
-
-    free(job);
 }

src/parsing/parse.h

@@ -5,6 +5,9 @@
 
 #define PARSE_BUF_SIZE 4096
 
+int fs_read(struct vfile *f, void *buf, size_t size);
+void fs_close(struct vfile *f);
+
 void parse(void *arg);
 
 #endif

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};
+    if (ScanCtx.content_size > 0) {
-    text_buffer_t text_buf = text_buffer_create(ScanCtx.content_size);
+        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_stext_block *block = stext->first_block;
-        fz_device *dev = fz_new_stext_device(ctx, stext, &opts);
+            while (block != NULL) {
-
+                int ret = read_stext_block(block, &text_buf);
-        fz_var(err);
+                if (ret == TEXT_BUF_FULL) {
-        fz_try(ctx)
+                    break;
-            fz_run_page(ctx, page, dev, fz_identity, NULL);
+                }
-        fz_always(ctx)
+                block = block->next;
-        {
+            }
-            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_page(ctx, page);
-            fz_drop_document(ctx, fzdoc);
-            fz_drop_context(ctx);
-            return;
-        }
 
-        fz_stext_block *block = stext->first_block;
+            if (text_buf.dyn_buffer.cur >= text_buf.dyn_buffer.size) {
-        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);
+        text_buffer_terminate_string(&text_buf);
-        fz_drop_page(ctx, page);
 
-        if (text_buf.dyn_buffer.cur >= text_buf.dyn_buffer.size) {
+        meta_line_t *meta_content = malloc(sizeof(meta_line_t) + text_buf.dyn_buffer.cur);
-            break;
+        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/parsing/text.c

@@ -1,7 +1,7 @@
 #include "text.h"
 #include "src/ctx.h"
 
-void parse_text(int bytes_read, int *fd, char *buf, document_t *doc) {
+void parse_text(int bytes_read, struct vfile *f, char *buf, document_t *doc) {
 
     char *intermediate_buf;
     int intermediate_buf_len;
@@ -13,10 +13,6 @@ void parse_text(int bytes_read, int *fd, char *buf, document_t *doc) {
         memcpy(intermediate_buf, buf, to_copy);
 
     } else {
-        if (*fd == -1) {
-            *fd = open(doc->filepath, O_RDONLY);
-        }
-
         int to_read = MIN(ScanCtx.content_size, doc->size) - bytes_read;
 
         intermediate_buf = malloc(to_read + bytes_read);
@@ -25,7 +21,7 @@ void parse_text(int bytes_read, int *fd, char *buf, document_t *doc) {
             memcpy(intermediate_buf, buf, bytes_read);
         }
 
-        read(*fd, intermediate_buf + bytes_read, to_read);
+        f->read(f, intermediate_buf + bytes_read, to_read);
     }
     text_buffer_t tex = text_buffer_create(ScanCtx.content_size);
     text_buffer_append_string(&tex, intermediate_buf, intermediate_buf_len);

src/parsing/text.h

@@ -3,6 +3,6 @@
 
 #include "src/sist.h"
 
-void parse_text(int bytes_read, int *fd, char *buf, document_t *doc);
+void parse_text(int bytes_read, struct vfile *f, char *buf, document_t *doc);
 
 #endif

src/sist.h

@@ -26,12 +26,17 @@
 #include <pthread.h>
 #include <sys/stat.h>
 #include <wordexp.h>
+#include "ft2build.h"
+#include "freetype/freetype.h"
+#include <archive.h>
+#include <archive_entry.h>
 
 #ifndef SIST_SCAN_ONLY
 #include <onion/onion.h>
 #include <onion/handler.h>
 #include <onion/block.h>
 #include <onion/shortcuts.h>
+#include <onion/codecs.h>
 #include <curl/curl.h>
 #endif
 
@@ -49,6 +54,7 @@
 #include "parsing/pdf.h"
 #include "parsing/media.h"
 #include "parsing/font.h"
+#include "parsing/arc.h"
 #include "cli.h"
 #include "utf8.h/utf8.h"
 
@@ -56,6 +62,7 @@
 #include "src/index/elastic.h"
 #include "index/web.h"
 #include "web/serve.h"
+#include "web/auth_basic.h"
 #endif
 
 ;

src/tpool.c

@@ -114,12 +114,19 @@ 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->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 +149,15 @@ 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;
+            usleep(500000);
-            break;
+            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 +180,8 @@ 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 +221,6 @@ 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(&pool->threads[i], NULL, tpool_worker, pool);
-        pthread_create(&thread, NULL, tpool_worker, pool);
-        pthread_detach(thread);
     }
 }

src/types.h

@@ -9,6 +9,12 @@
 #define IS_META_LONG(key) (key & META_LONG_MASK) == META_LONG_MASK
 #define IS_META_STR(meta) (meta->key & META_STR_MASK) == META_STR_MASK
 
+#define ARC_MODE_SKIP 0
+#define ARC_MODE_LIST 1
+#define ARC_MODE_SHALLOW 2
+#define ARC_MODE_RECURSE 3
+typedef int archive_mode_t;
+
 // This is written to file as a 8bit char!
 enum metakey {
     MetaContent = 1 | META_STR_MASK,
@@ -24,6 +30,7 @@ enum metakey {
     MetaGenre = 11 | META_STR_MASK,
     MetaTitle = 12 | META_STR_MASK,
     MetaFontName = 13 | META_STR_MASK,
+    MetaParent = 14 | META_STR_MASK,
 };
 
 typedef struct index_descriptor {
@@ -63,13 +70,39 @@ typedef struct document {
     short ext;
     meta_line_t *meta_head;
     meta_line_t *meta_tail;
+    struct document *child_head;
+    struct document *child_tail;
     char *filepath;
 } document_t;
 
+typedef struct vfile vfile_t;
+
+typedef int (*read_func_t)(struct vfile *, void *buf, size_t size);
+
+typedef int (*seek_func_t)(struct vfile *, size_t size, int whence);
+
+typedef void (*close_func_t)(struct vfile *);
+
+typedef struct vfile {
+
+    union {
+        int fd;
+        struct archive *arc;
+    };
+
+    int is_fs_file;
+    char *filepath;
+
+    read_func_t read;
+    close_func_t close;
+} vfile_t;
+
 typedef struct parse_job_t {
     int base;
     int ext;
     struct stat info;
+    struct vfile vfile;
+    uuid_t parent;
     char filepath[1];
 } parse_job_t;
 

src/util.c

@@ -46,6 +46,10 @@ void dyn_buffer_write_str(dyn_buffer_t *buf, char *str) {
     dyn_buffer_write_char(buf, '\0');
 }
 
+void dyn_buffer_append_string(dyn_buffer_t *buf, char *str) {
+    dyn_buffer_write(buf, str, strlen(str));
+}
+
 void dyn_buffer_write_int(dyn_buffer_t *buf, int d) {
     grow_buffer_small(buf);
 

src/util.h

@@ -47,6 +47,8 @@ void dyn_buffer_write_char(dyn_buffer_t *buf, char c);
 
 void dyn_buffer_write_str(dyn_buffer_t *buf, char *str);
 
+void dyn_buffer_append_string(dyn_buffer_t *buf, char *str);
+
 void dyn_buffer_write_int(dyn_buffer_t *buf, int d);
 
 void dyn_buffer_write_short(dyn_buffer_t *buf, short s);

src/web/auth_basic.c

@@ -0,0 +1,59 @@
+#include "auth_basic.h"
+
+#define UNAUTHORIZED_TEXT "Unauthorized"
+
+typedef struct auth_basic_data {
+    onion_handler *inside;
+    const char *b64credentials;
+} auth_basic_data_t;
+
+
+int authenticate(const char *expected, const char *credentials) {
+
+    if (expected == NULL) {
+        return TRUE;
+    }
+
+    if (credentials && strncmp(credentials, "Basic ", 6) == 0) {
+        if (strcmp((credentials + 6), expected) == 0) {
+            return TRUE;
+        }
+    }
+
+    return FALSE;
+}
+
+int auth_basic_handler(auth_basic_data_t *d,
+                       onion_request *req,
+                       onion_response *res) {
+
+    const char *credentials = onion_request_get_header(req, "Authorization");
+
+    if (authenticate(d->b64credentials, credentials)) {
+        return onion_handler_handle(d->inside, req, res);
+    }
+
+    onion_response_set_header(res, "WWW-Authenticate", "Basic realm=\"sist2\"");
+    onion_response_set_code(res, HTTP_UNAUTHORIZED);
+    onion_response_write(res, UNAUTHORIZED_TEXT, sizeof(UNAUTHORIZED_TEXT));
+    onion_response_set_length(res, sizeof(UNAUTHORIZED_TEXT));
+
+    return OCS_PROCESSED;
+}
+
+void auth_basic_free(auth_basic_data_t *data) {
+    onion_handler_free(data->inside);
+    free(data);
+}
+
+onion_handler *auth_basic(const char *b64credentials, onion_handler *inside_level) {
+
+    auth_basic_data_t *privdata = malloc(sizeof(auth_basic_data_t));
+
+    privdata->b64credentials = b64credentials;
+    privdata->inside = inside_level;
+
+    return onion_handler_new((onion_handler_handler) auth_basic_handler, privdata,
+                             (onion_handler_private_data_free) auth_basic_free);
+}
+

src/web/auth_basic.h

@@ -0,0 +1,4 @@
+#include "src/sist.h"
+
+
+onion_handler *auth_basic(const char *b64credentials, onion_handler *inside_level);

src/web/serve.c

@@ -245,6 +245,8 @@ int search(void *p, onion_request *req, onion_response *res) {
 
     if (r->status_code == 200) {
         onion_response_write(res, r->body, r->size);
+    } else {
+        onion_response_set_code(res, HTTP_INTERNAL_ERROR);
     }
 
     free_response(r);
@@ -358,12 +360,24 @@ int file(void *p, onion_request *req, onion_response *res) {
         return OCS_PROCESSED;
     }
 
-    cJSON *doc = elastic_get_document(arg_uuid);
+    char *next = arg_uuid;
-    cJSON *source = cJSON_GetObjectItem(doc, "_source");
+    cJSON *doc = NULL;
-    cJSON *index_id = cJSON_GetObjectItem(source, "index");
+    cJSON *index_id = NULL;
-    if (index_id == NULL) {
+    cJSON *source = NULL;
-        cJSON_Delete(doc);
+
-        return OCS_NOT_PROCESSED;
+    while (true) {
+        doc = elastic_get_document(next);
+        source = cJSON_GetObjectItem(doc, "_source");
+        index_id = cJSON_GetObjectItem(source, "index");
+        if (index_id == NULL) {
+            cJSON_Delete(doc);
+            return OCS_NOT_PROCESSED;
+        }
+        cJSON *parent = cJSON_GetObjectItem(source, "parent");
+        if (parent == NULL) {
+            break;
+        }
+        next = parent->valuestring;
     }
 
     index_t *idx = get_index_by_id(index_id->valuestring);
@@ -391,9 +405,11 @@ void serve(const char *hostname, const char *port) {
     onion_set_hostname(o, hostname);
     onion_set_port(o, port);
 
-    onion_url *urls = onion_root_url(o);
+    onion_url *urls = onion_url_new();
 
     // Static paths
+    onion_set_root_handler(o, auth_basic(WebCtx.b64credentials, onion_url_to_handler(urls)));
+
     onion_url_add(urls, "", search_index);
     onion_url_add(urls, "css", style);
     onion_url_add(urls, "js", javascript);
@@ -410,6 +426,7 @@ void serve(const char *hostname, const char *port) {
     onion_url_add(urls, "^f/([a-fA-F0-9]{8}-[a-fA-F0-9]{4}-[a-fA-F0-9]{4}-[a-fA-F0-9]{4}-[a-fA-F0-9]{12})$", file);
     onion_url_add(urls, "i", index_info);
 
+
     printf("Starting web server @ http://%s:%s\n", hostname, port);
 
     onion_listen(o);

web/css/dark.css

@@ -23,6 +23,29 @@ body {
     border: none;
 }
 
+.sub-document {
+    background: #37474F;
+}
+
+.sub-document .text-muted {
+    color: #8a949c !important;
+}
+
+
+.list-group-item {
+    background: #212121;
+    color: #e0e0e0;
+
+    border-top: 1px solid #424242;
+    border-bottom: none;
+    border-left: none;
+    border-right: none;
+}
+
+.list-group-item:first-child {
+    border-top: none;
+}
+
 .navbar-brand {
     font-size: 1.75rem;
     padding: 0;
@@ -93,6 +116,7 @@ body {
     white-space: nowrap;
     text-overflow: ellipsis;
     overflow: hidden;
+    color: #00BCD4;
 }
 
 .badge {
@@ -115,6 +139,15 @@ body {
     height: auto;
 }
 
+.fit-sm {
+    display: block;
+    max-width: 64px;
+    max-height: 64px;
+    margin: 0 auto 0;
+    width: auto;
+    height: auto;
+}
+
 .audio-fit {
     height: 39px;
     vertical-align: bottom;
@@ -158,6 +191,8 @@ mark {
     border: 1px solid #616161;
     border-radius: 4px;
     margin: 3px;
+    white-space: normal;
+    color: rgb(224, 224, 224);
 }
 
 .irs-single, .irs-from, .irs-to {
@@ -239,6 +274,7 @@ option {
     padding: 0.5rem;
     background: #212121;
     color: #eee;
+    margin-top: 1em;
 }
 
 .btn-xs {
@@ -279,8 +315,46 @@ option {
     margin-top: 0.5rem;
 }
 
-@media (min-width: 800px) {
+@media (max-width: 800px) {
-    .nav {
+    #treeTabs {
-        min-width: 800px;
+        flex-basis: inherit;
+        flex-grow: inherit;
     }
 }
+
+.list-group {
+    margin-top: 1em;
+}
+
+.list-group-item {
+    padding: .25rem 0.5rem;
+}
+
+.wrapper-sm {
+    min-width: 64px;
+}
+
+.media-expanded {
+    display: inherit;
+}
+
+.media-expanded .fit {
+    max-height: 250px;
+}
+
+@media (max-width: 600px) {
+    .media-expanded .fit {
+        max-height: none;
+    }
+
+    .tagline {
+        display: none;
+    }
+}
+
+.version {
+    color: #00BCD4;
+    margin-left: -18px;
+    margin-top: -14px;
+    font-size: 11px;
+}

web/css/light.css

@@ -2,7 +2,9 @@
     outline: 0;
 }
 
-body {overflow-y:scroll;}
+body {
+    overflow-y: scroll;
+}
 
 .progress {
     margin-top: 1em;
@@ -10,15 +12,23 @@ body {overflow-y:scroll;}
 
 .card {
     margin-top: 1em;
-    box-shadow: 0 .125rem .25rem rgba(0,0,0,.075) !important;
+    box-shadow: 0 .125rem .25rem rgba(0, 0, 0, .075) !important;
 }
+
+.sub-document {
+    background: #AB47BC1F;
+}
+
 .navbar-brand {
     font-size: 1.75rem;
     padding: 0;
 }
+
 .navbar {
-    background: #F7F7F7; border-bottom: solid 1px #dfdfdf;
+    background: #F7F7F7;
+    border-bottom: solid 1px #dfdfdf;
 }
+
 .document {
     padding: 0.5rem;
 }
@@ -93,6 +103,15 @@ body {overflow-y:scroll;}
     height: auto;
 }
 
+.fit-sm {
+    display: block;
+    max-width: 64px;
+    max-height: 64px;
+    margin: 0 auto 0;
+    width: auto;
+    height: auto;
+}
+
 .audio-fit {
     height: 39px;
     vertical-align: bottom;
@@ -107,16 +126,17 @@ body {overflow-y:scroll;}
 }
 
 @media (min-width: 1500px) {
-    .container  {
+    .container {
         max-width: 1440px;
     }
+
     .card-columns {
         column-count: 5;
     }
 }
 
 @media (min-width: 1800px) {
-    .container  {
+    .container {
         max-width: 1550px;
     }
 }
@@ -128,13 +148,15 @@ mark {
 }
 
 .content-div {
-    font-family: SFMono-Regular,Menlo,Monaco,Consolas,"Liberation Mono","Courier New",monospace;
+    font-family: SFMono-Regular, Menlo, Monaco, Consolas, "Liberation Mono", "Courier New", monospace;
     font-size: 13px;
     padding: 1em;
     background-color: #f5f5f5;
     border: 1px solid #ccc;
     border-radius: 4px;
     margin: 3px;
+    white-space: normal;
+    color: #000;
 }
 
 .irs-single, .irs-from, .irs-to {
@@ -154,8 +176,7 @@ mark {
     margin-bottom: 1em;
 }
 
-.inspire-tree .selected > .wholerow, .inspire-tree .selected > .title-wrap:hover + .wholerow
+.inspire-tree .selected > .wholerow, .inspire-tree .selected > .title-wrap:hover + .wholerow {
-{
     background: none;
 }
 
@@ -171,6 +192,7 @@ mark {
     line-height: 1rem;
     padding: 0.5rem;
     background: #f8f9fa;
+    margin-top: 1em;
 }
 
 .btn-xs {
@@ -183,8 +205,46 @@ mark {
     margin-top: 0.5rem;
 }
 
-@media (min-width: 800px) {
+@media (max-width: 800px) {
-    .nav {
+    #treeTabs {
-        min-width: 800px;
+        flex-basis: inherit;
+        flex-grow: inherit;
     }
 }
+
+.list-group {
+    margin-top: 1em;
+}
+
+.list-group-item {
+    padding: .25rem 0.5rem;
+}
+
+.wrapper-sm {
+    min-width: 64px;
+}
+
+.media-expanded {
+    display: inherit;
+}
+
+.media-expanded .fit {
+    max-height: 250px;
+}
+
+@media (max-width: 600px) {
+    .media-expanded .fit {
+        max-height: none;
+    }
+
+    .tagline {
+        display: none;
+    }
+}
+
+.version {
+    color: #007bff;
+    margin-left: -18px;
+    margin-top: -14px;
+    font-size: 11px;
+}

web/js/dom.js

@@ -75,18 +75,84 @@ function shouldPlayVideo(hit) {
     return videoc !== "hevc" && videoc !== "mpeg2video" && videoc !== "wmv3";
 }
 
-function makePlaceholder(w, h) {
+function makePlaceholder(w, h, small) {
-    const calc = w > h
+    let calc;
-        ? (175 / w / h) >= 272
+    if (small) {
-            ? (175 * w / h)
+        calc = w > h
-            : 175
+            ? (64 / w / h) >= 100
-        : 175;
+                ? (64 * w / h)
+                : 64
+            : 64;
+    } else {
+        calc = w > h
+            ? (175 / w / h) >= 272
+                ? (175 * w / h)
+                : 175
+            : 175;
+    }
 
     const el = document.createElement("div");
     el.setAttribute("style", `height: ${calc}px`);
     return el;
 }
 
+function makeTitle(hit) {
+    let title = document.createElement("div");
+    title.setAttribute("class", "file-title");
+    let extension = hit["_source"].hasOwnProperty("extension") && hit["_source"]["extension"] !== "" ? "." + hit["_source"]["extension"] : "";
+
+    applyNameToTitle(hit, title, extension);
+
+    title.setAttribute("title", hit["_source"]["path"] + "/" + hit["_source"]["name"] + extension);
+    return title;
+}
+
+function getTags(hit, mimeCategory) {
+
+    let tags = [];
+    switch (mimeCategory) {
+        case "video":
+        case "image":
+            if (hit["_source"].hasOwnProperty("videoc")) {
+                const formatTag = document.createElement("span");
+                formatTag.setAttribute("class", "badge badge-pill badge-video");
+                formatTag.appendChild(document.createTextNode(hit["_source"]["videoc"].replace(" ", "")));
+                tags.push(formatTag);
+            }
+            break;
+        case "audio": {
+            if (hit["_source"].hasOwnProperty("audioc")) {
+                let formatTag = document.createElement("span");
+                formatTag.setAttribute("class", "badge badge-pill badge-audio");
+                formatTag.appendChild(document.createTextNode(hit["_source"]["audioc"]));
+                tags.push(formatTag);
+            }
+        }
+            break;
+    }
+    // User tags
+    if (hit["_source"].hasOwnProperty("tag")) {
+        hit["_source"]["tag"].forEach(tag => {
+            const userTag = document.createElement("span");
+            userTag.setAttribute("class", "badge badge-pill badge-user");
+
+            const tokens = tag.split("#");
+
+            if (tokens.length > 1) {
+                const bg = "#" + tokens[1];
+                const fg = lum(tokens[1]) > 40 ? "#000" : "#fff";
+                userTag.setAttribute("style", `background-color: ${bg}; color: ${fg}`);
+            }
+
+            const name = tokens[0].split(".")[tokens[0].split(".").length - 1];
+            userTag.appendChild(document.createTextNode(name));
+            tags.push(userTag);
+        })
+    }
+
+    return tags
+}
+
 /**
  *
  * @param hit
@@ -99,27 +165,25 @@ function createDocCard(hit) {
     let docCardBody = document.createElement("div");
     docCardBody.setAttribute("class", "card-body document");
 
+    //Title
+    let title = makeTitle(hit);
+    let isSubDocument = false;
+
     let link = document.createElement("a");
     link.setAttribute("href", "f/" + hit["_id"]);
     link.setAttribute("target", "_blank");
+    link.appendChild(title);
 
-    //Title
+    if (hit["_source"].hasOwnProperty("parent")) {
-    let title = document.createElement("p");
+        docCard.classList.add("sub-document");
-    title.setAttribute("class", "file-title");
+        isSubDocument = true;
-    let extension = hit["_source"].hasOwnProperty("extension") && hit["_source"]["extension"] !== "" ? "." + hit["_source"]["extension"] : "";
+    }
-
-    applyNameToTitle(hit, title, extension);
-
-    title.setAttribute("title", hit["_source"]["path"] + "/" + hit["_source"]["name"] + extension);
-    docCard.appendChild(title);
 
     let tagContainer = document.createElement("div");
     tagContainer.setAttribute("class", "card-text");
 
     if (hit["_source"].hasOwnProperty("mime") && hit["_source"]["mime"] !== null) {
 
-        let tags = [];
-        let thumbnail = null;
         let thumbnailOverlay = null;
         let imgWrapper = document.createElement("div");
         imgWrapper.setAttribute("style", "position: relative");
@@ -127,47 +191,7 @@ function createDocCard(hit) {
         let mimeCategory = hit["_source"]["mime"].split("/")[0];
 
         //Thumbnail
-        if (mimeCategory === "video" && shouldPlayVideo(hit)) {
+        let thumbnail = makeThumbnail(mimeCategory, hit, imgWrapper, false);
-            thumbnail = document.createElement("video");
-            addVidSrc("f/" + hit["_id"], hit["_source"]["mime"], thumbnail);
-
-            const placeholder = makePlaceholder(hit["_source"]["width"], hit["_source"]["height"]);
-            imgWrapper.appendChild(placeholder);
-
-            thumbnail.setAttribute("class", "fit");
-            thumbnail.setAttribute("controls", "");
-            thumbnail.setAttribute("preload", "none");
-            thumbnail.setAttribute("poster", `t/${hit["_source"]["index"]}/${hit["_id"]}`);
-            thumbnail.addEventListener("dblclick", function () {
-                thumbnail.webkitRequestFullScreen();
-            });
-            const poster = new Image();
-            poster.src = thumbnail.getAttribute('poster');
-            poster.addEventListener("load", function () {
-                placeholder.remove();
-                imgWrapper.appendChild(thumbnail);
-            });
-        } else if ((hit["_source"].hasOwnProperty("width") && hit["_source"]["width"] > 20 && hit["_source"]["height"] > 20)
-            || hit["_source"]["mime"] === "application/pdf"
-            || hit["_source"]["mime"] === "application/epub+zip"
-            || hit["_source"]["mime"] === "application/x-cbz"
-            || hit["_source"].hasOwnProperty("font_name")
-        ) {
-            thumbnail = document.createElement("img");
-            thumbnail.setAttribute("class", "card-img-top fit");
-            thumbnail.setAttribute("src", `t/${hit["_source"]["index"]}/${hit["_id"]}`);
-
-            const placeholder = makePlaceholder(hit["_source"]["width"], hit["_source"]["height"]);
-            imgWrapper.appendChild(placeholder);
-
-            thumbnail.addEventListener("error", () => {
-                imgWrapper.remove();
-            });
-            thumbnail.addEventListener("load", () => {
-                placeholder.remove();
-                imgWrapper.appendChild(thumbnail);
-            });
-        }
 
         //Thumbnail overlay
         switch (mimeCategory) {
@@ -177,15 +201,17 @@ function createDocCard(hit) {
                 thumbnailOverlay.setAttribute("class", "card-img-overlay");
 
                 //Resolution
-                let resolutionBadge = document.createElement("span");
+                if (hit["_source"].hasOwnProperty("width") && hit["_source"]["width"] > 32 && hit["_source"]["height"] > 32) {
-                resolutionBadge.setAttribute("class", "badge badge-resolution");
+                    let resolutionBadge = document.createElement("span");
-                if (hit["_source"].hasOwnProperty("width")) {
+                    resolutionBadge.setAttribute("class", "badge badge-resolution");
-                    resolutionBadge.appendChild(document.createTextNode(hit["_source"]["width"] + "x" + hit["_source"]["height"]));
+                    if (hit["_source"].hasOwnProperty("width")) {
+                        resolutionBadge.appendChild(document.createTextNode(hit["_source"]["width"] + "x" + hit["_source"]["height"]));
+                    }
+                    thumbnailOverlay.appendChild(resolutionBadge);
                 }
-                thumbnailOverlay.appendChild(resolutionBadge);
 
                 // Hover
-                if (thumbnail && hit["_source"]["videoc"] === "gif") {
+                if (thumbnail && hit["_source"]["videoc"] === "gif" && !isSubDocument) {
                     gifOver(thumbnail, hit);
                 }
                 break;
@@ -202,26 +228,10 @@ function createDocCard(hit) {
                 }
         }
 
-        //Tags
+        // Tags
-        switch (mimeCategory) {
+        let tags = getTags(hit, mimeCategory);
-            case "video":
+        for (let i = 0; i < tags.length; i++) {
-            case "image":
+            tagContainer.appendChild(tags[i]);
-                if (hit["_source"].hasOwnProperty("videoc")) {
-                    const formatTag = document.createElement("span");
-                    formatTag.setAttribute("class", "badge badge-pill badge-video");
-                    formatTag.appendChild(document.createTextNode(hit["_source"]["videoc"].replace(" ", "")));
-                    tags.push(formatTag);
-                }
-                break;
-            case "audio": {
-                if (hit["_source"].hasOwnProperty("audioc")) {
-                    let formatTag = document.createElement("span");
-                    formatTag.setAttribute("class", "badge badge-pill badge-audio");
-                    formatTag.appendChild(document.createTextNode(hit["_source"]["audioc"]));
-                    tags.push(formatTag);
-                }
-            }
-                break;
         }
 
         //Content
@@ -238,7 +248,7 @@ function createDocCard(hit) {
         }
 
         //Audio
-        if (mimeCategory === "audio" && hit["_source"].hasOwnProperty("audioc")) {
+        if (mimeCategory === "audio" && hit["_source"].hasOwnProperty("audioc") && !isSubDocument) {
 
             let audio = document.createElement("audio");
             audio.setAttribute("preload", "none");
@@ -253,30 +263,6 @@ function createDocCard(hit) {
         if (thumbnailOverlay !== null) {
             imgWrapper.appendChild(thumbnailOverlay);
         }
-
-        // User tags
-        if (hit["_source"].hasOwnProperty("tag")) {
-            hit["_source"]["tag"].forEach(tag => {
-                const userTag = document.createElement("span");
-                userTag.setAttribute("class", "badge badge-pill badge-user");
-
-                const tokens = tag.split("#");
-
-                if (tokens.length > 1) {
-                    const bg = "#" + tokens[1];
-                    const fg = lum(tokens[1]) > 40 ? "#000" : "#fff";
-                    userTag.setAttribute("style", `background-color: ${bg}; color: ${fg}`);
-                }
-
-                const name = tokens[0].split(".")[tokens[0].split(".").length - 1];
-                userTag.appendChild(document.createTextNode(name));
-                tags.push(userTag);
-            })
-        }
-
-        for (let i = 0; i < tags.length; i++) {
-            tagContainer.appendChild(tags[i]);
-        }
     }
 
     //Size tag
@@ -288,12 +274,146 @@ function createDocCard(hit) {
     docCardBody.appendChild(link);
     docCard.appendChild(docCardBody);
 
-    link.appendChild(title);
     docCardBody.appendChild(tagContainer);
 
     return docCard;
 }
 
+function makeThumbnail(mimeCategory, hit, imgWrapper, small) {
+    let thumbnail;
+    let isSubDocument = hit["_source"].hasOwnProperty("parent");
+
+    if (mimeCategory === "video" && shouldPlayVideo(hit) && !isSubDocument) {
+        thumbnail = document.createElement("video");
+        addVidSrc("f/" + hit["_id"], hit["_source"]["mime"], thumbnail);
+
+        const placeholder = makePlaceholder(hit["_source"]["width"], hit["_source"]["height"], small);
+        imgWrapper.appendChild(placeholder);
+
+        if (small) {
+            thumbnail.setAttribute("class", "fit-sm");
+        } else {
+            thumbnail.setAttribute("class", "fit");
+        }
+        if (small) {
+            thumbnail.style.cursor = "pointer";
+            thumbnail.title = "Enlarge";
+            thumbnail.addEventListener("click", function () {
+                imgWrapper.classList.remove("wrapper-sm", "mr-1");
+                imgWrapper.parentElement.classList.add("media-expanded");
+                thumbnail.setAttribute("class", "fit");
+                thumbnail.setAttribute("controls", "");
+            });
+        } else {
+            thumbnail.setAttribute("controls", "");
+        }
+        thumbnail.setAttribute("preload", "none");
+        thumbnail.setAttribute("poster", `t/${hit["_source"]["index"]}/${hit["_id"]}`);
+        thumbnail.addEventListener("dblclick", function () {
+            thumbnail.setAttribute("controls", "");
+            if (thumbnail.webkitRequestFullScreen) {
+                thumbnail.webkitRequestFullScreen();
+            } else {
+                thumbnail.requestFullscreen();
+            }
+        });
+        const poster = new Image();
+        poster.src = thumbnail.getAttribute('poster');
+        poster.addEventListener("load", function () {
+            placeholder.remove();
+            imgWrapper.appendChild(thumbnail);
+        });
+    } else if ((hit["_source"].hasOwnProperty("width") && hit["_source"]["width"] > 32 && hit["_source"]["height"] > 32)
+        || hit["_source"]["mime"] === "application/pdf"
+        || hit["_source"]["mime"] === "application/epub+zip"
+        || hit["_source"]["mime"] === "application/x-cbz"
+        || hit["_source"].hasOwnProperty("font_name")
+    ) {
+        thumbnail = document.createElement("img");
+        if (small) {
+            thumbnail.setAttribute("class", "fit-sm");
+        } else {
+            thumbnail.setAttribute("class", "card-img-top fit");
+        }
+        thumbnail.setAttribute("src", `t/${hit["_source"]["index"]}/${hit["_id"]}`);
+
+        const placeholder = makePlaceholder(hit["_source"]["width"], hit["_source"]["height"], small);
+        imgWrapper.appendChild(placeholder);
+
+        thumbnail.addEventListener("error", () => {
+            imgWrapper.remove();
+        });
+        thumbnail.addEventListener("load", () => {
+            placeholder.remove();
+            imgWrapper.appendChild(thumbnail);
+        });
+    }
+
+    return thumbnail;
+}
+
+function createDocLine(hit) {
+
+    const mime = hit["_source"]["mime"];
+    let mimeCategory = mime ? mime.split("/")[0] : null;
+    let tags = getTags(hit, mimeCategory);
+
+    let imgWrapper = document.createElement("div");
+    imgWrapper.setAttribute("class", "align-self-start mr-1 wrapper-sm");
+
+    let media = document.createElement("div");
+    media.setAttribute("class", "media");
+
+    const line = document.createElement("div");
+    line.setAttribute("class", "list-group-item flex-column align-items-start");
+
+
+    const title = makeTitle(hit);
+
+    let link = document.createElement("a");
+    link.setAttribute("href", "f/" + hit["_id"]);
+    link.setAttribute("target", "_blank");
+    link.appendChild(title);
+
+    const titleDiv = document.createElement("div");
+    titleDiv.setAttribute("class", "file-title");
+    titleDiv.appendChild(link);
+
+    line.appendChild(media);
+
+    let thumbnail = makeThumbnail(mimeCategory, hit, imgWrapper, true);
+    if (thumbnail) {
+        media.appendChild(imgWrapper);
+    }
+    media.appendChild(titleDiv);
+
+    // Content
+    let contentHl = getContentHighlight(hit);
+    if (contentHl !== undefined) {
+        const contentDiv = document.createElement("div");
+        contentDiv.setAttribute("class", "content-div");
+        contentDiv.insertAdjacentHTML('afterbegin', contentHl);
+        titleDiv.appendChild(contentDiv);
+    }
+
+    let tagContainer = document.createElement("div");
+    tagContainer.setAttribute("class", "");
+
+    for (let i = 0; i < tags.length; i++) {
+        tagContainer.appendChild(tags[i]);
+    }
+
+    //Size tag
+    let sizeTag = document.createElement("small");
+    sizeTag.appendChild(document.createTextNode(humanFileSize(hit["_source"]["size"])));
+    sizeTag.setAttribute("class", "text-muted");
+    tagContainer.appendChild(sizeTag);
+
+    titleDiv.appendChild(tagContainer);
+
+    return line;
+}
+
 function makePreloader() {
     const elem = document.createElement("div");
     elem.setAttribute("class", "progress");
@@ -318,18 +438,53 @@ function makePageIndicator(searchResult) {
 function makeStatsCard(searchResult) {
 
     let statsCard = document.createElement("div");
-    statsCard.setAttribute("class", "card");
+    statsCard.setAttribute("class", "card stat");
     let statsCardBody = document.createElement("div");
     statsCardBody.setAttribute("class", "card-body");
 
-    let stat = document.createElement("p");
+    const resultMode = document.createElement("div");
+    resultMode.setAttribute("class", "btn-group btn-group-toggle");
+    resultMode.setAttribute("data-toggle", "buttons");
+    resultMode.style.cssFloat = "right";
+
+    const listMode = document.createElement("label");
+    listMode.setAttribute("class", "btn btn-primary");
+    listMode.appendChild(document.createTextNode("List"));
+
+    const gridMode = document.createElement("label");
+    gridMode.setAttribute("class", "btn btn-primary");
+    gridMode.appendChild(document.createTextNode("Grid"));
+
+    resultMode.appendChild(gridMode);
+    resultMode.appendChild(listMode);
+
+    if (mode === "grid") {
+        gridMode.classList.add("active")
+    } else {
+        listMode.classList.add("active")
+    }
+
+    gridMode.addEventListener("click", () => {
+        mode = "grid";
+        localStorage.setItem("mode", mode);
+        searchDebounced();
+    });
+    listMode.addEventListener("click", () => {
+        mode = "list";
+        localStorage.setItem("mode", mode);
+        searchDebounced();
+    });
+
+    let stat = document.createElement("span");
     const totalHits = searchResult["hits"]["total"].hasOwnProperty("value")
         ? searchResult["hits"]["total"]["value"] : searchResult["hits"]["total"];
     stat.appendChild(document.createTextNode(totalHits + " results in " + searchResult["took"] + "ms"));
+
     statsCardBody.appendChild(stat);
+    statsCardBody.appendChild(resultMode);
 
     if (totalHits !== 0) {
-        let sizeStat = document.createElement("span");
+        let sizeStat = document.createElement("div");
         sizeStat.appendChild(document.createTextNode(humanFileSize(searchResult["aggregations"]["total_size"]["value"])));
         statsCardBody.appendChild(sizeStat);
     }
@@ -341,7 +496,11 @@ function makeStatsCard(searchResult) {
 
 function makeResultContainer() {
     let resultContainer = document.createElement("div");
-    resultContainer.setAttribute("class", "card-columns");
 
+    if (mode === "grid") {
+        resultContainer.setAttribute("class", "card-columns");
+    } else {
+        resultContainer.setAttribute("class", "list-group");
+    }
     return resultContainer;
 }

web/js/search.js

@@ -12,6 +12,13 @@ let coolingDown = false;
 let searchBusy = true;
 let selectedIndices = [];
 
+let mode;
+if (localStorage.getItem("mode") === null) {
+    mode = "grid";
+} else {
+    mode = localStorage.getItem("mode")
+}
+
 jQuery["jsonPost"] = function (url, data) {
     return jQuery.ajax({
         url: url,
@@ -211,7 +218,12 @@ new autoComplete({
 
 function insertHits(resultContainer, hits) {
     for (let i = 0; i < hits.length; i++) {
-        resultContainer.appendChild(createDocCard(hits[i]));
+
+        if (mode === "grid") {
+            resultContainer.appendChild(createDocCard(hits[i]));
+        } else {
+            resultContainer.appendChild(createDocLine(hits[i]));
+        }
         docCount++;
     }
 }
@@ -345,6 +357,7 @@ function search() {
             post_tags: ["</mark>"],
             fields: {
                 content: {},
+                // "content.nGram": {},
                 name: {},
                 "name.nGram": {},
                 font_name: {},

web/js/util.js

@@ -3,7 +3,7 @@
  */
 function humanFileSize(bytes) {
     if (bytes === 0) {
-        return "? B"
+        return "0 B"
     }
 
     let thresh = 1000;

web/search.html

@@ -11,6 +11,7 @@
 
 <nav class="navbar navbar-expand-lg">
     <a class="navbar-brand" href="/">sist2</a>
+    <span class="badge badge-pill version">v1.1.10</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>
@@ -41,7 +42,7 @@
                     <select class="custom-select" id="indices" multiple size="6"></select>
                 </div>
 
-                <div class="col">
+                <div class="col" id="treeTabs">
                     <ul class="nav nav-tabs" role="tablist">
                         <li class="nav-item">
                             <a class="nav-link active" data-toggle="tab" href="#mime" role="tab" aria-controls="home" aria-selected="true">Mime Types</a>