Bug fixes

README.md

@@ -79,7 +79,7 @@ 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 libharfbuzz-dev
+        libbz2-dev yasm libharfbuzz-dev ragel
    ```
     *(FreeBSD)*
     ```bash

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 = "1.1.1";
+static const char *const Version = "1.1.2";
 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/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/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: [
+                        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"
-                        ],
                         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>
+                        <span onclick="document.getElementById('fuzzyToggle').click()">Fuzzy&nbsp</span>
-                        <input title="Toggle between 'Should' and 'Must' match mode" type="checkbox" id="barToggle"
+                        <input title="Toggle fuzzy searching" type="checkbox" id="fuzzyToggle"
-                               onclick="toggleSearchBar()" checked>
+                               onclick="toggleFuzzy()" checked>
                     </div>
                 </div>
                 <input id="searchBar" type="search" class="form-control" placeholder="Search">