EXIF metadata for images

README.md

@@ -9,7 +9,7 @@ sist2 (Simple incremental search tool)
 
 ## Features
 
-* Fast, low memory usage
+* Fast, low memory usage, multi-threaded
 * Portable (all its features are packaged in a single executable)
 * Extracts text from common file types\*
 * Generates thumbnails\*
@@ -56,10 +56,10 @@ sist2 web --bind 0.0.0.0 --port 4321 ./my_idx1 ./my_idx2 ./my_idx3
 
 File type | Library | Content | Thumbnail | Metadata
 :---|:---|:---|:---|:---
-pdf,xps,cbz,cbr,fb2,epub | MuPDF | yes | yes, `png` | title |
-`audio/*` | libav | - | yes, `jpeg` | ID3 tags |
-`video/*` | libav | - | yes, `jpeg` | title, comment |
-`image/*` | libav | - | yes, `jpeg` | *planned* |
+pdf,xps,cbz,fb2,epub | MuPDF | yes | yes, `png` | title |
+`audio/*` | ffmpeg | - | yes, `jpeg` | ID3 tags |
+`video/*` | ffmpeg | - | yes, `jpeg` | title, comment, artist |
+`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* |
@@ -79,11 +79,12 @@ binaries.
     apt install git cmake pkg-config libglib2.0-dev\
         libssl-dev uuid-dev libavformat-dev libswscale-dev \
         python3 libmagic-dev libfreetype6-dev libcurl-dev \
-        libbz2-dev yasm
+        libbz2-dev yasm libharfbuzz-dev ragel
    ```
     *(FreeBSD)*
     ```bash
-   pkg install cmake gcc yasm gmake bash ffmpeg e2fsprogs-uuid
+   pkg install cmake gcc yasm gmake bash ffmpeg e2fsprogs-uuid\
+        autotools ragel
    ```
 
 2. Build

src/io/serialize.c

@@ -66,7 +66,7 @@ index_descriptor_t read_index_descriptor(char *path) {
     strcpy(descriptor.root, cJSON_GetObjectItem(json, "root")->valuestring);
     strcpy(descriptor.name, cJSON_GetObjectItem(json, "name")->valuestring);
     strcpy(descriptor.rewrite_url, cJSON_GetObjectItem(json, "rewrite_url")->valuestring);
-    descriptor.root_len = (short)strlen(descriptor.root);
+    descriptor.root_len = (short) strlen(descriptor.root);
     strcpy(descriptor.version, cJSON_GetObjectItem(json, "version")->valuestring);
     strcpy(descriptor.uuid, cJSON_GetObjectItem(json, "uuid")->valuestring);
 
@@ -181,7 +181,7 @@ void read_index(const char *path, const char index_id[UUID_STR_LEN], index_func
         uuid_unparse(line.uuid, uuid_str);
 
         cJSON_AddStringToObject(document, "mime", mime_get_mime_text(line.mime));
-        cJSON_AddNumberToObject(document, "size", (double)line.size);
+        cJSON_AddNumberToObject(document, "size", (double) line.size);
         cJSON_AddNumberToObject(document, "mtime", line.mtime);
 
         int c;
@@ -208,14 +208,19 @@ void read_index(const char *path, const char index_id[UUID_STR_LEN], index_func
         while (key != '\n') {
             switch (key) {
                 case MetaWidth:
-                case MetaHeight:
-                case MetaMediaDuration:
-                case MetaMediaBitrate: {
+                case MetaHeight: {
                     int value;
                     fread(&value, sizeof(int), 1, file);
                     cJSON_AddNumberToObject(document, get_meta_key_text(key), value);
                     break;
                 }
+                case MetaMediaDuration:
+                case MetaMediaBitrate: {
+                    long value;
+                    fread(&value, sizeof(long), 1, file);
+                    cJSON_AddNumberToObject(document, get_meta_key_text(key), value);
+                    break;
+                }
                 case MetaMediaAudioCodec:
                 case MetaMediaVideoCodec: {
                     int value;
@@ -245,7 +250,7 @@ void read_index(const char *path, const char index_id[UUID_STR_LEN], index_func
                     break;
                 }
                 default:
-                    fprintf(stderr, "Invalid meta key (corrupt index): %x", key);
+                    fprintf(stderr, "Invalid meta key (corrupt index): %x\n", key);
                     break;
             }
 

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 = "1.1.0";
+static const char *const Version = "1.1.3";
 static const char *const usage[] = {
         "sist2 scan [OPTION]... PATH",
         "sist2 index [OPTION]... INDEX",

src/parsing/font.c

@@ -142,6 +142,9 @@ void parse_font(const char *buf, size_t buf_len, document_t *doc) {
     if (library == NULL) {
         FT_Init_FreeType(&library);
     }
+    if (buf == NULL) {
+        return;
+    }
 
     FT_Face face;
     FT_Error err = FT_New_Memory_Face(library, (unsigned char *) buf, buf_len, 0, &face);

src/parsing/media.c

@@ -116,9 +116,9 @@ AVFrame *read_frame(AVFormatContext *pFormatCtx, AVCodecContext *decoder, int st
     return frame;
 }
 
-#define APPEND_TAG_META(doc, tag, keyname) \
+#define APPEND_TAG_META(doc, tag_, keyname) \
     text_buffer_t tex = text_buffer_create(-1); \
-    text_buffer_append_string0(&tex, tag->value); \
+    text_buffer_append_string0(&tex, tag_->value); \
     meta_line_t *meta_tag = malloc(sizeof(meta_line_t) + tex.dyn_buffer.cur); \
     meta_tag->key = keyname; \
     strcpy(meta_tag->strval, tex.dyn_buffer.buf); \
@@ -151,30 +151,39 @@ void append_audio_meta(AVFormatContext *pFormatCtx, document_t *doc) {
 }
 
 __always_inline
-void append_video_meta(AVFormatContext *pFormatCtx, document_t *doc, int include_audio_tags) {
+void append_video_meta(AVFormatContext *pFormatCtx, AVFrame *frame, document_t *doc, int include_audio_tags, int is_video) {
 
-    meta_line_t *meta_duration = malloc(sizeof(meta_line_t));
-    meta_duration->key = MetaMediaDuration;
-    meta_duration->longval = pFormatCtx->duration / AV_TIME_BASE;
-    APPEND_META(doc, meta_duration)
+    if (is_video) {
+        meta_line_t *meta_duration = malloc(sizeof(meta_line_t));
+        meta_duration->key = MetaMediaDuration;
+        meta_duration->longval = pFormatCtx->duration / AV_TIME_BASE;
+        APPEND_META(doc, meta_duration)
 
-    meta_line_t *meta_bitrate = malloc(sizeof(meta_line_t));
-    meta_bitrate->key = MetaMediaBitrate;
-    meta_bitrate->longval = pFormatCtx->bit_rate;
-    APPEND_META(doc, meta_bitrate)
+        meta_line_t *meta_bitrate = malloc(sizeof(meta_line_t));
+        meta_bitrate->key = MetaMediaBitrate;
+        meta_bitrate->longval = pFormatCtx->bit_rate;
+        APPEND_META(doc, meta_bitrate)
+    }
 
     AVDictionaryEntry *tag = NULL;
-    while ((tag = av_dict_get(pFormatCtx->metadata, "", tag, AV_DICT_IGNORE_SUFFIX))) {
-        char key[32];
-        strncpy(key, tag->key, sizeof(key));
-
-        char *ptr = key;
-        for (; *ptr; ++ptr) *ptr = (char) tolower(*ptr);
-
-        if (strcmp(key, "title") == 0 && include_audio_tags) {
-            APPEND_TAG_META(doc, tag, MetaTitle)
-        } else if (strcmp(key, "comment") == 0) {
-            APPEND_TAG_META(doc, tag, MetaContent)
+    if (is_video) {
+        while ((tag = av_dict_get(pFormatCtx->metadata, "", tag, AV_DICT_IGNORE_SUFFIX))) {
+            if (include_audio_tags && strcmp(tag->key, "title") == 0) {
+                APPEND_TAG_META(doc, tag, MetaTitle)
+            } else if (strcmp(tag->key, "comment") == 0) {
+                APPEND_TAG_META(doc, tag, MetaContent)
+            } else if (include_audio_tags && strcmp(tag->key, "artist") == 0) {
+                APPEND_TAG_META(doc, tag, MetaArtist)
+            }
+        }
+    } else {
+        // EXIF metadata
+        while ((tag = av_dict_get(frame->metadata, "", tag, AV_DICT_IGNORE_SUFFIX))) {
+            if (include_audio_tags && strcmp(tag->key, "Artist") == 0) {
+                APPEND_TAG_META(doc, tag, MetaArtist)
+            } else if (strcmp(tag->key, "ImageDescription") == 0) {
+                APPEND_TAG_META(doc, tag, MetaContent)
+            }
         }
     }
 }
@@ -236,11 +245,6 @@ void parse_media(const char *filepath, document_t *doc) {
     if (video_stream != -1) {
         AVStream *stream = pFormatCtx->streams[video_stream];
 
-        if (stream->nb_frames > 1) {
-            //This is a video (not a still image)
-            append_video_meta(pFormatCtx, doc, audio_stream == -1);
-        }
-
         if (stream->codecpar->width <= MIN_SIZE || stream->codecpar->height <= MIN_SIZE) {
             avformat_close_input(&pFormatCtx);
             avformat_free_context(pFormatCtx);
@@ -273,6 +277,8 @@ void parse_media(const char *filepath, document_t *doc) {
             return;
         }
 
+        append_video_meta(pFormatCtx, frame, doc, audio_stream == -1, stream->nb_frames > 1);
+
         // Scale frame
         AVFrame *scaled_frame = scale_frame(decoder, frame, ScanCtx.tn_size);
 

src/parsing/parse.c

@@ -16,7 +16,6 @@ void *read_all(parse_job_t *job, const char *buf, int bytes_read, int *fd) {
             if (*fd == -1) {
                 perror("open");
                 printf("%s\n", job->filepath);
-                free(job);
                 return NULL;
             }
         }
@@ -25,6 +24,7 @@ void *read_all(parse_job_t *job, const char *buf, int bytes_read, int *fd) {
         int ret = read(*fd, full_buf + bytes_read, job->info.st_size - bytes_read);
         if (ret == -1) {
             perror("read");
+            return NULL;
         }
     }
 
@@ -108,7 +108,7 @@ void parse(void *arg) {
         void *pdf_buf = read_all(job, (char *) buf, bytes_read, &fd);
         parse_pdf(pdf_buf, doc.size, &doc);
 
-        if (pdf_buf != buf) {
+        if (pdf_buf != buf && pdf_buf != NULL) {
             free(pdf_buf);
         }
 
@@ -119,7 +119,7 @@ void parse(void *arg) {
         void *font_buf = read_all(job, (char *) buf, bytes_read, &fd);
         parse_font(font_buf, doc.size, &doc);
 
-        if (font_buf != buf) {
+        if (font_buf != buf && font_buf != NULL) {
             free(font_buf);
         }
     }

src/parsing/pdf.c

@@ -114,6 +114,10 @@ int read_stext_block(fz_stext_block *block, text_buffer_t *tex) {
 
 void parse_pdf(void *buf, size_t buf_len, document_t *doc) {
 
+    if (buf == NULL) {
+        return;
+    }
+
     static int mu_is_initialized = 0;
     if (!mu_is_initialized) {
         pthread_mutex_init(&ScanCtx.mupdf_mu, NULL);

src/util.c

@@ -90,7 +90,7 @@ void text_buffer_terminate_string(text_buffer_t *buf) {
 }
 
 __always_inline
-int utf8_validchr(const char* s) {
+int utf8_validchr(const char *s) {
     if (0x00 == (0x80 & *s)) {
         return TRUE;
     } else if (0xf0 == (0xf8 & *s)) {
@@ -130,7 +130,7 @@ int utf8_validchr(const char* s) {
         if (0 == (0x1e & s[0])) {
             return FALSE;
         }
-    } else  {
+    } else {
         return FALSE;
     }
 
@@ -140,12 +140,22 @@ int utf8_validchr(const char* s) {
 int text_buffer_append_string(text_buffer_t *buf, char *str, size_t len) {
 
     utf8_int32_t c;
-    for (void *v = utf8codepoint(str, &c); c != '\0' && ((char*)v - str + 4) < len; v = utf8codepoint(v, &c)) {
+    if (str == NULL || len < 1 ||
+        (0xf0 == (0xf8 & str[0]) && len < 4) ||
+        (0xe0 == (0xf0 & str[0]) && len < 3) ||
+        (0xc0 == (0xe0 & str[0]) && len == 1) ||
+        *(str) == 0) {
+        text_buffer_terminate_string(buf);
+        return 0;
+    }
+
+    for (void *v = utf8codepoint(str, &c); c != '\0' && ((char *) v - str + 4) < len; v = utf8codepoint(v, &c)) {
         if (utf8_validchr(v)) {
             text_buffer_append_char(buf, c);
         }
     }
     text_buffer_terminate_string(buf);
+    return 0;
 }
 
 int text_buffer_append_string0(text_buffer_t *buf, char *str) {

web/js/dom.js

@@ -136,6 +136,9 @@ function createDocCard(hit) {
             thumbnail = document.createElement("img");
             thumbnail.setAttribute("class", "card-img-top fit");
             thumbnail.setAttribute("src", `t/${hit["_source"]["index"]}/${hit["_id"]}`);
+            thumbnail.addEventListener("error", () => {
+                imgWrapper.remove();
+            });
         }
 
         //Thumbnail overlay

web/js/search.js

@@ -32,7 +32,7 @@ window.onload = () => {
     })
 };
 
-function toggleSearchBar() {
+function toggleFuzzy() {
     searchDebounced();
 }
 
@@ -218,11 +218,22 @@ function search() {
 
     let query = searchBar.value;
     let empty = query === "";
-    let condition = $("#barToggle").prop("checked") && !empty ? "must" : "should";
+    let condition = empty ? "should" : "must";
     let filters = [
         {range: {size: {gte: size_min, lte: size_max}}},
         {terms: {index: selectedIndices}}
     ];
+    let fields = [
+        "name^8",
+        "content^3",
+        "album^8", "artist^8", "title^8", "genre^2", "album_artist^8",
+        "font_name^6"
+    ];
+
+    if ($("#fuzzyToggle").prop("checked")) {
+        fields.push("content.nGram");
+        fields.push("name.nGram^3");
+    }
 
     let path = pathBar.value.replace(/\/$/, "").toLowerCase(); //remove trailing slashes
     if (path !== "") {
@@ -243,12 +254,7 @@ function search() {
                     multi_match: {
                         query: query,
                         type: "most_fields",
-                        fields: [
-                            "name^8", "name.nGram^3", "content^3",
-                            "content.nGram",
-                            "album^8", "artist^8", "title^8", "genre^2", "album_artist^8",
-                            "font_name^6"
-                        ],
+                        fields: fields,
                         operator: "and"
                     }
                 },
@@ -265,7 +271,7 @@ function search() {
                 content: {},
                 name: {},
                 "name.nGram": {},
-                // font_name: {},
+                font_name: {},
             }
         },
         aggs: {

web/search.html

@@ -24,9 +24,9 @@
             <div class="input-group">
                 <div class="input-group-prepend">
                     <div class="input-group-text">
-                        <span onclick="document.getElementById('barToggle').click()">Must match&nbsp</span>
-                        <input title="Toggle between 'Should' and 'Must' match mode" type="checkbox" id="barToggle"
-                               onclick="toggleSearchBar()" checked>
+                        <span onclick="document.getElementById('fuzzyToggle').click()">Fuzzy&nbsp</span>
+                        <input title="Toggle fuzzy searching" type="checkbox" id="fuzzyToggle"
+                               onclick="toggleFuzzy()" checked>
                     </div>
                 </div>
                 <input id="searchBar" type="search" class="form-control" placeholder="Search">