Update readme

README.md

@@ -25,14 +25,12 @@ sist2 (Simple incremental search tool)
 * OCR support with tesseract \*\*\*
 * Stats page & disk utilisation visualization
 
-
 \* See [format support](#format-support)    
 \*\* See [Archive files](#archive-files)    
-\*\*\* See [OCR](#ocr)    
+\*\*\* See [OCR](#ocr)
 
 ![stats](docs/stats.png)
 
-
 ## Getting Started
 
 1. Have an Elasticsearch (>= 6.X.X) instance running
@@ -56,10 +54,8 @@ sist2 (Simple incremental search tool)
     1. *(or)* `docker pull simon987/sist2:latest`
 
 1. See [Usage guide](docs/USAGE.md)
-   
-
-\* *Windows users*: **sist2** runs under [WSL](https://en.wikipedia.org/wiki/Windows_Subsystem_for_Linux)    
 
+\* *Windows users*: **sist2** runs under [WSL](https://en.wikipedia.org/wiki/Windows_Subsystem_for_Linux)
 
 ## Example usage
 
@@ -69,7 +65,6 @@ See [Usage guide](docs/USAGE.md) for more details
 1. Push index to Elasticsearch: `sist2 index ./docs_idx`
 1. Start web interface: `sist2 web ./docs_idx`
 
-
 ## Format support
 
 File type | Library | Content | Thumbnail | Metadata
@@ -78,8 +73,8 @@ pdf,xps,fb2,epub | MuPDF | text+ocr | yes | author, title |
 cbz,cbr | *(none)* | - | yes | - |
 `audio/*` | ffmpeg | - | yes | ID3 tags |
 `video/*` | ffmpeg | - | yes | title, comment, artist |
-`image/*` | ffmpeg | - | yes | [Common EXIF tags](https://github.com/simon987/sist2/blob/efdde2734eca9b14a54f84568863b7ffd59bdba3/src/parsing/media.c#L190) |
-raw, rw2, dng, cr2, crw, dcr, k25, kdc, mrw, pef, xf3, arw, sr2, srf, erf  | LibRaw | - | yes | Common EXIF tags |
+`image/*` | ffmpeg | - | yes | [Common EXIF tags](https://github.com/simon987/sist2/blob/efdde2734eca9b14a54f84568863b7ffd59bdba3/src/parsing/media.c#L190), GPS tags |
+raw, rw2, dng, cr2, crw, dcr, k25, kdc, mrw, pef, xf3, arw, sr2, srf, erf  | LibRaw | - | yes | Common EXIF tags, GPS tags |
 ttf,ttc,cff,woff,fnt,otf | Freetype2 | - | yes, `bmp` | Name & style |
 `text/plain` | *(none)* | yes | no | - |
 html, xml | *(none)* | yes | no | - |
@@ -89,40 +84,39 @@ doc (MS Word 97-2003) | antiword | yes | yes | author, title |
 mobi, azw, azw3 | libmobi | yes | no | author, title |
 
 \* *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)
+
+**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**:
-* Support for parsing media files with formats that require *seek* (e.g. `.gif`, `.mp4` w/ fragmented metadata etc.) 
+
+* Support for parsing media files with formats that require *seek* (e.g. `.gif`, `.mp4` w/ fragmented metadata etc.)
   is limitted (see `--mem-buffer` option)
 * 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.
- 
- 
+  **sist2** is not I/O bound, scans might be faster when larger archives are split into smaller parts.
+
 ### OCR
 
 You can enable OCR support for pdf,xps,fb2,epub file types with the
-`--ocr <lang>` option. Download the language data files with your
-package manager (`apt install tesseract-ocr-eng`) or directly [from Github](https://github.com/tesseract-ocr/tesseract/wiki/Data-Files).
+`--ocr <lang>` option. Download the language data files with your package manager (`apt install tesseract-ocr-eng`) or
+directly [from Github](https://github.com/tesseract-ocr/tesseract/wiki/Data-Files).
 
-The `simon987/sist2` image comes with common languages 
+The `simon987/sist2` image comes with common languages
 (hin, jpn, eng, fra, rus, spa) pre-installed.
 
 Examples
+
 ```bash
 sist2 scan --ocr jpn ~/Books/Manga/
 sist2 scan --ocr eng ~/Books/Textbooks/
 ```
 
-
 ## Build from source
 
-You can compile **sist2** by yourself if you don't want to use the pre-compiled
-binaries (GCC 7+ required).
+You can compile **sist2** by yourself if you don't want to use the pre-compiled binaries (GCC 7+ required).
 
 1. Install compile-time dependencies
 

schema/mappings.json

@@ -105,10 +105,10 @@
       "analyzer": "my_nGram",
       "type": "text"
     },
-    "_keyword.*":  {
+    "_keyword.*": {
       "type": "keyword"
     },
-    "_text.*":  {
+    "_text.*": {
       "analyzer": "content_analyzer",
       "type": "text",
       "fields": {
@@ -165,6 +165,30 @@
     "exif_user_comment": {
       "type": "text"
     },
+    "exif_gps_longitude_ref": {
+      "type": "keyword",
+      "index": false
+    },
+    "exif_gps_longitude_dms": {
+      "type": "keyword",
+      "index": false
+    },
+    "exif_gps_longitude_dec": {
+      "type": "keyword",
+      "index": false
+    },
+    "exif_gps_latitude_ref": {
+      "type": "keyword",
+      "index": false
+    },
+    "exif_gps_latitude_dms": {
+      "type": "keyword",
+      "index": false
+    },
+    "exif_gps_latitude_dec": {
+      "type": "keyword",
+      "index": false
+    },
     "author": {
       "type": "text"
     },

src/io/serialize.c

@@ -18,7 +18,7 @@ typedef struct {
 #define META_NEXT 0xFFFF
 
 void skip_meta(FILE *file) {
-    enum metakey key;
+    enum metakey key = 0;
     fread(&key, sizeof(uint16_t), 1, file);
 
     while (key != META_NEXT) {
@@ -237,7 +237,7 @@ void read_index_bin(const char *path, const char *index_id, index_func func) {
     FILE *file = fopen(path, "rb");
     while (TRUE) {
         buf.cur = 0;
-        size_t _ = fread((void *) &line, 1, sizeof(line_t), file);
+        size_t _ = fread((void *) &line, sizeof(line_t), 1, file);
         if (feof(file)) {
             break;
         }
@@ -284,8 +284,8 @@ void read_index_bin(const char *path, const char *index_id, index_func func) {
             cJSON_AddStringToObject(document, "path", "");
         }
 
-        enum metakey key;
-        fread(&key, sizeof(short), 1, file);
+        enum metakey key = 0;
+        fread(&key, sizeof(uint16_t), 1, file);
         size_t ret;
         while (key != META_NEXT) {
             switch (key) {
@@ -481,7 +481,7 @@ void incremental_read(GHashTable *table, const char *filepath) {
 
         incremental_put(table, line.path_md5, line.mtime);
 
-        while ((getc(file))) {}
+        while ((getc(file)) != 0) {}
         skip_meta(file);
     }
     fclose(file);
@@ -531,7 +531,7 @@ void incremental_copy(store_t *store, store_t *dst_store, const char *filepath,
                 free(buf);
             }
 
-            enum metakey key;
+            enum metakey key = 0;
             while (1) {
                 fread(&key, sizeof(uint16_t), 1, file);
                 fwrite(&key, sizeof(uint16_t), 1, dst_file);

src/static/js/dom.js

@@ -192,6 +192,19 @@ function makeUserTag(tag, hit) {
     return userTag;
 }
 
+function makeGpsMetaRow(tbody, latitude, longitude) {
+    tbody.append($("<tr>")
+        .append($("<td>").text("Exif GPS"))
+        .append($("<td>")
+            .append($("<a>")
+                .text(`${latitude}, ${longitude}`)
+                .attr("href", `https://maps.google.com/?q=${latitude},${longitude}&ll=${latitude},${longitude}&t=k&z=17`)
+                .attr("target", "_blank")
+            )
+        )
+    );
+}
+
 function infoButtonCb(hit) {
     return () => {
         getDocumentInfo(hit["_id"]).then(doc => {
@@ -229,13 +242,25 @@ function infoButtonCb(hit) {
                     .text(new Date(doc["mtime"] * 1000).toISOString().split(".")[0].replace("T", " "))
                     .attr("title", doc["mtime"]))
             );
+
+            // Exif GPS
+            if ("exif_gps_longitude_dec" in doc) {
+                makeGpsMetaRow(tbody, doc["exif_gps_latitude_dec"], doc["exif_gps_longitude_dec"])
+            } else if ("exif_gps_longitude_dms" in doc) {
+                makeGpsMetaRow(
+                    tbody,
+                    dmsToDecimal(doc["exif_gps_latitude_dms"], doc["exif_gps_latitude_ref"]),
+                    dmsToDecimal(doc["exif_gps_longitude_dms"], doc["exif_gps_longitude_ref"]),
+                )
+            }
+
             const displayFields = new Set([
                 "mime", "size", "path", "title", "width", "height", "duration", "audioc", "videoc",
                 "bitrate", "artist", "album", "album_artist", "genre", "title", "font_name", "tag", "author",
                 "modified_by", "pages"
             ]);
             Object.keys(doc)
-                .filter(key => key.startsWith("_keyword.") || key.startsWith("_text.") || displayFields.has(key) || key.startsWith("exif_"))
+                .filter(key => key.startsWith("_keyword.") || key.startsWith("_text.") || displayFields.has(key) || (key.startsWith("exif_") && !key.includes("gps")))
                 .forEach(key => {
                     tbody.append($("<tr>")
                         .append($("<td>").text(key))
@@ -352,7 +377,7 @@ function createDocCard(hit) {
             audio.setAttribute("src", "f/" + hit["_id"]);
             audio.addEventListener("play", () => {
                 // Pause all currently playing audio tags
-                $("audio").each(function(){
+                $("audio").each(function () {
                     if (this !== audio) {
                         this.pause();
                     }

src/static/js/util.js

@@ -235,4 +235,14 @@ function updateColumnStyle() {
 }
         `
     }
+}
+
+function dmsToDecimal(dms, ref) {
+    const tokens = dms.split(",")
+
+    const d = Number(tokens[0].trim().split(":")[0]) / Number(tokens[0].trim().split(":")[1])
+    const m = Number(tokens[1].trim().split(":")[0]) / Number(tokens[1].trim().split(":")[1])
+    const s = Number(tokens[2].trim().split(":")[0]) / Number(tokens[2].trim().split(":")[1])
+
+    return (d + (m / 60) + (s / 3600)) * (ref === "S" || ref === "W" ? -1 : 1)
 }

tests/test_scan.py

@@ -17,17 +17,19 @@ def copy_files(files):
 
 
 def sist2(*args):
+    print("./sist2 " + " ".join(args))
+
     return subprocess.check_output(
-        args=["./sist2_debug", *args],
+        args=["./sist2", *args],
     )
 
 
 def sist2_index(files, *args):
     path = copy_files(files)
 
-    shutil.rmtree("i", ignore_errors=True)
-    sist2("scan", path, "-o", "i", *args)
-    return iter(sist2_index_to_dict("i"))
+    shutil.rmtree("test_i", ignore_errors=True)
+    sist2("scan", path, "-o", "test_i", *args)
+    return iter(sist2_index_to_dict("test_i"))
 
 
 def sist2_incremental_index(files, func=None, *args):
@@ -36,14 +38,14 @@ def sist2_incremental_index(files, func=None, *args):
     if func:
         func(path)
 
-    shutil.rmtree("i_inc", ignore_errors=True)
-    sist2("scan", path, "-o", "i_inc", "--incremental", "i", *args)
-    return iter(sist2_index_to_dict("i_inc"))
+    shutil.rmtree("test_i_inc", ignore_errors=True)
+    sist2("scan", path, "-o", "test_i_inc", "--incremental", "test_i", *args)
+    return iter(sist2_index_to_dict("test_i_inc"))
 
 
 def sist2_index_to_dict(index):
     res = subprocess.check_output(
-        args=["./sist2_debug", "index", "--print", index],
+        args=["./sist2", "index", "--print", index],
     )
 
     for line in res.splitlines():

third-party/libscan

@@ -1 +1 @@
-Subproject commit 598e748214fe0656d536e40bb9e056c058504d85
+Subproject commit 9be4f02851107edac65894a1fdde16a80cad43ac