blogc: added utf8 validation

7 files changed, 226 insertions, 0 deletions

diff --git a/.gitignore b/.gitignore
index e0ac2c9..95eeff6 100644
--- a/.gitignore
+++ b/.gitignore
@@ -57,6 +57,7 @@ blogc*.html
 /tests/check_renderer
 /tests/check_source_parser
 /tests/check_template_parser
+/tests/check_utf8
 /tests/check_utils
 
 # tarballs
diff --git a/Makefile.am b/Makefile.am
index 11dde62..2582881 100644
--- a/Makefile.am
+++ b/Makefile.am
@@ -41,6 +41,7 @@ noinst_HEADERS = \
 	src/renderer.h \
 	src/source-parser.h \
 	src/template-parser.h \
+	src/utf8.h \
 	src/utils.h \
 	$(NULL)
 
@@ -94,6 +95,7 @@ libblogc_la_LIBADD = \
 
 
 libblogc_utils_la_SOURCES = \
+	src/utf8.c \
 	src/utils.c \
 	$(NULL)
 
@@ -277,6 +279,7 @@ check_PROGRAMS += \
 	tests/check_renderer \
 	tests/check_source_parser \
 	tests/check_template_parser \
+	tests/check_utf8 \
 	tests/check_utils \
 	$(NULL)
 
@@ -408,6 +411,23 @@ tests_check_template_parser_LDADD = \
 	libblogc_utils.la \
 	$(NULL)
 
+tests_check_utf8_SOURCES = \
+	tests/check_utf8.c \
+	$(NULL)
+
+tests_check_utf8_CFLAGS = \
+	$(CMOCKA_CFLAGS) \
+	$(NULL)
+
+tests_check_utf8_LDFLAGS = \
+	-no-install \
+	$(NULL)
+
+tests_check_utf8_LDADD = \
+	$(CMOCKA_LIBS) \
+	libblogc_utils.la \
+	$(NULL)
+
 tests_check_utils_SOURCES = \
 	tests/check_utils.c \
 	$(NULL)
diff --git a/src/blogc.c b/src/blogc.c
index 40a5918..4606740 100644
--- a/src/blogc.c
+++ b/src/blogc.c
@@ -30,6 +30,7 @@
 #include "loader.h"
 #include "renderer.h"
 #include "error.h"
+#include "utf8.h"
 #include "utils.h"
 
 #ifndef PACKAGE_VERSION
@@ -125,6 +126,11 @@ main(int argc, char **argv)
     sb_trie_insert(config, "BLOGC_VERSION", sb_strdup(PACKAGE_VERSION));
 
     for (unsigned int i = 1; i < argc; i++) {
+        if (!blogc_utf8_validate((uint8_t*) argv[i], strlen(argv[i]))) {
+            fprintf(stderr, "blogc: error: command-line argument is not utf8-"
+                "encoded: %s\n", argv[i]);
+            goto cleanup;
+        }
         tmp = NULL;
         if (argv[i][0] == '-') {
             switch (argv[i][1]) {
diff --git a/src/file.c b/src/file.c
index f784d93..7171f31 100644
--- a/src/file.c
+++ b/src/file.c
@@ -16,6 +16,7 @@
 #include <string.h>
 #include "file.h"
 #include "error.h"
+#include "utf8.h"
 #include "utils.h"
 
 // this would belong to loader.c, but we need it in a separated file to be
@@ -47,6 +48,14 @@ blogc_file_get_contents(const char *path, size_t *len, blogc_error_t **err)
         sb_string_append_len(str, buffer, read_len);
     }
     fclose(fp);
+
+    if (!blogc_utf8_validate_str(str)) {
+        *err = blogc_error_new_printf(BLOGC_ERROR_LOADER,
+            "File content is not valid UTF-8: %s", path);
+        sb_string_free(str, true);
+        return NULL;
+    }
+
     return sb_string_free(str, false);
 }
 
diff --git a/src/utf8.c b/src/utf8.c
new file mode 100644
index 0000000..deea46d
--- /dev/null
+++ b/src/utf8.c
@@ -0,0 +1,88 @@
+/*
+ * blogc: A blog compiler.
+ * Copyright (c) 2008-2010 Bjoern Hoehrmann <bjoern@hoehrmann.de>
+ * Copyright (c) 2016 Rafael G. Martins <rafael@rafaelmartins.eng.br>
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to
+ * deal in the Software without restriction, including without limitation the
+ * rights to use, copy, modify, merge, publish, distribute, sublicense, and/or
+ * sell copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+ * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
+ * IN THE SOFTWARE.
+ */
+
+// Based on Bjoern Hoehrmann's algorithm.
+// See http://bjoern.hoehrmann.de/utf-8/decoder/dfa/ for details.
+
+#include <stdbool.h>
+#include <inttypes.h>
+#include "utils.h"
+
+#define UTF8_ACCEPT 0
+#define UTF8_REJECT 12
+
+
+static const uint8_t utf8d[] = {
+    // The first part of the table maps bytes to character classes that
+    // to reduce the size of the transition table and create bitmasks.
+     0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,  0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
+     0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,  0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
+     0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,  0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
+     0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,  0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
+     1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,  9,9,9,9,9,9,9,9,9,9,9,9,9,9,9,9,
+     7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,  7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,
+     8,8,2,2,2,2,2,2,2,2,2,2,2,2,2,2,  2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,
+    10,3,3,3,3,3,3,3,3,3,3,3,3,4,3,3, 11,6,6,6,5,8,8,8,8,8,8,8,8,8,8,8,
+
+    // The second part is a transition table that maps a combination
+    // of a state of the automaton and a character class to a state.
+     0,12,24,36,60,96,84,12,12,12,48,72, 12,12,12,12,12,12,12,12,12,12,12,12,
+    12, 0,12,12,12,12,12, 0,12, 0,12,12, 12,24,12,12,12,12,12,24,12,24,12,12,
+    12,12,12,12,12,12,12,24,12,12,12,12, 12,24,12,12,12,12,12,12,12,24,12,12,
+    12,12,12,12,12,12,12,36,12,36,12,12, 12,36,12,12,12,12,12,36,12,36,12,12,
+    12,36,12,12,12,12,12,12,12,12,12,12,
+};
+
+
+static uint32_t inline
+decode(uint32_t* state, uint32_t* codep, uint32_t byte) {
+    uint32_t type = utf8d[byte];
+
+    *codep = (*state != UTF8_ACCEPT) ?
+        (byte & 0x3fu) | (*codep << 6) :
+        (0xff >> type) & (byte);
+
+    *state = utf8d[256 + *state + type];
+    return *state;
+}
+
+
+bool
+blogc_utf8_validate(const uint8_t *str, size_t len)
+{
+    uint32_t codepoint;
+    uint32_t state = 0;
+
+    for (size_t i = 0; i < len; i++)
+        decode(&state, &codepoint, str[i]);
+
+    return state == UTF8_ACCEPT;
+}
+
+
+bool
+blogc_utf8_validate_str(sb_string_t *str)
+{
+    return blogc_utf8_validate((uint8_t*) str->str, str->len);
+}
diff --git a/src/utf8.h b/src/utf8.h
new file mode 100644
index 0000000..837d02f
--- /dev/null
+++ b/src/utf8.h
@@ -0,0 +1,19 @@
+/*
+ * blogc: A blog compiler.
+ * Copyright (C) 2015-2016 Rafael G. Martins <rafael@rafaelmartins.eng.br>
+ *
+ * This program can be distributed under the terms of the BSD License.
+ * See the file LICENSE.
+ */
+
+#ifndef _UTF_8_H
+#define _UTF_8_H
+
+#include <inttypes.h>
+#include <stdbool.h>
+#include "utils.h"
+
+bool blogc_utf8_validate(const uint8_t *str, size_t len);
+bool blogc_utf8_validate_str(sb_string_t *str);
+
+#endif /* _UTF_8_H */
diff --git a/tests/check_utf8.c b/tests/check_utf8.c
new file mode 100644
index 0000000..b0dec4e
--- /dev/null
+++ b/tests/check_utf8.c
@@ -0,0 +1,83 @@
+/*
+ * blogc: A blog compiler.
+ * Copyright (C) 2015-2016 Rafael G. Martins <rafael@rafaelmartins.eng.br>
+ *
+ * This program can be distributed under the terms of the BSD License.
+ * See the file LICENSE.
+ */
+
+#ifdef HAVE_CONFIG_H
+#include <config.h>
+#endif /* HAVE_CONFIG_H */
+
+#include <stdarg.h>
+#include <stddef.h>
+#include <setjmp.h>
+#include <cmocka.h>
+#include <string.h>
+#include "../src/utf8.h"
+#include "../src/utils.h"
+
+
+static void
+test_utf8_valid(void **state)
+{
+    const char *c = "<a href=\"{{ BASE_URL }}/page/{{ PREVIOUS_PAGE }}/\">"
+        "\xc2\xab Newer posts</a>";
+    assert_true(blogc_utf8_validate((uint8_t*) c, strlen(c)));
+    const uint8_t d[3] = {0xe2, 0x82, 0xac};
+    assert_true(blogc_utf8_validate(d, 3));
+}
+
+
+static void
+test_utf8_invalid(void **state)
+{
+    const uint8_t c[4] = {0xff, 0xfe, 0xac, 0x20};  // utf-16
+    assert_false(blogc_utf8_validate(c, 4));
+    const uint8_t d[8] = {0xff, 0xfe, 0x00, 0x00, 0xac, 0x20, 0x00, 0x00};  // utf-32
+    assert_false(blogc_utf8_validate(d, 8));
+}
+
+
+static void
+test_utf8_valid_str(void **state)
+{
+    sb_string_t *s = sb_string_new();
+    sb_string_append(s,
+        "<a href=\"{{ BASE_URL }}/page/{{ PREVIOUS_PAGE }}/\">\xc2\xab Newer "
+        "posts</a>");
+    assert_true(blogc_utf8_validate_str(s));
+    sb_string_free(s, true);
+    s = sb_string_new();
+    sb_string_append(s, "\xe2\x82\xac");
+    assert_true(blogc_utf8_validate_str(s));
+    sb_string_free(s, true);
+}
+
+
+static void
+test_utf8_invalid_str(void **state)
+{
+    sb_string_t *s = sb_string_new();
+    sb_string_append(s, "\xff\xfe\xac\x20");  // utf-16
+    assert_false(blogc_utf8_validate_str(s));
+    sb_string_free(s, true);
+    s = sb_string_new();
+    sb_string_append(s, "\xff\xfe\x00\x00\xac\x20\x00\x00");  // utf-32
+    assert_false(blogc_utf8_validate_str(s));
+    sb_string_free(s, true);
+}
+
+
+int
+main(void)
+{
+    const UnitTest tests[] = {
+        unit_test(test_utf8_valid),
+        unit_test(test_utf8_invalid),
+        unit_test(test_utf8_valid_str),
+        unit_test(test_utf8_invalid_str),
+    };
+    return run_tests(tests);
+}