From ea4fb7fa0d71718fdb8d2038fd470046a5f4051c Mon Sep 17 00:00:00 2001
From: simon <me@simon987.net>
Date: Sat, 9 Nov 2019 12:00:07 -0500
Subject: [PATCH] Bug fixes

---
 src/main.c          |  2 +-
 src/parsing/font.c  |  3 +++
 src/parsing/parse.c |  6 +++---
 src/parsing/pdf.c   |  4 ++++
 src/util.c          | 16 +++++++++++++---
 5 files changed, 24 insertions(+), 7 deletions(-)

diff --git a/src/main.c b/src/main.c
index 490ed06..632a3b4 100644
--- a/src/main.c
+++ b/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",
diff --git a/src/parsing/font.c b/src/parsing/font.c
index 7049831..d2f61dc 100644
--- a/src/parsing/font.c
+++ b/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);
diff --git a/src/parsing/parse.c b/src/parsing/parse.c
index 315993a..571cb81 100644
--- a/src/parsing/parse.c
+++ b/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);
         }
     }
diff --git a/src/parsing/pdf.c b/src/parsing/pdf.c
index 4d0e2a1..7b3b112 100644
--- a/src/parsing/pdf.c
+++ b/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);
diff --git a/src/util.c b/src/util.c
index 0197656..5749309 100644
--- a/src/util.c
+++ b/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) {