bare-buffer 2.5.4 → 2.5.6

package/vendor/libutf/src/utf8/length-from-latin1.c

@@ -0,0 +1,32 @@
+#include <stddef.h>
+
+#include "../../include/utf.h"
+
+/**
+ * Modified from https://github.com/simdutf/simdutf
+ *
+ * Copyright 2020 The simdutf authors
+ *
+ * Licensed under the Apache License, Version 2.0 (the "License");
+ * you may not use this file except in compliance with the License.
+ * You may obtain a copy of the License at
+ *
+ *     http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+size_t
+utf8_length_from_latin1 (const latin1_t *data, size_t len) {
+  size_t counter = len;
+
+  for (size_t i = 0; i < len; i++) {
+    counter += data[i] >> 7;
+  }
+
+  return counter;
+}

package/vendor/libutf/src/{utf16/utf8-length.c → utf8/length-from-utf16.c}

@@ -1,9 +1,8 @@
-#include <stdbool.h>
 #include <stddef.h>
 #include <stdint.h>
 
 #include "../../include/utf.h"
-#include "../../include/utf/endianness.h"
+#include "../endianness.h"
 
 /**
  * Modified from https://github.com/simdutf/simdutf

package/vendor/libutf/src/utf8/length-from-utf32.c

@@ -0,0 +1,35 @@
+#include <stddef.h>
+
+#include "../../include/utf.h"
+
+/**
+ * Modified from https://github.com/simdutf/simdutf
+ *
+ * Copyright 2020 The simdutf authors
+ *
+ * Licensed under the Apache License, Version 2.0 (the "License");
+ * you may not use this file except in compliance with the License.
+ * You may obtain a copy of the License at
+ *
+ *     http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+size_t
+utf8_length_from_utf32 (const utf32_t *data, size_t len) {
+  size_t counter = 0;
+
+  for (size_t i = 0; i < len; i++) {
+    counter++;
+    counter += data[i] > 0x7f;
+    counter += data[i] > 0x7ff;
+    counter += data[i] > 0xffff;
+  }
+
+  return counter;
+}

package/vendor/libutf/src/utf8/string.c

@@ -1,3 +1,4 @@
+#include <stdbool.h>
 #include <stddef.h>
 
 #include "../../include/utf.h"
@@ -25,7 +26,7 @@ extern void
 utf8_string_clear (utf8_string_t *string);
 
 extern bool
-utf8_string_empty (utf8_string_t *string);
+utf8_string_empty (const utf8_string_t *string);
 
 extern bool
 utf8_string_view_empty (const utf8_string_view_t view);

package/vendor/libutf/src/utf8/validate.c

@@ -26,7 +26,6 @@
 bool
 utf8_validate (const utf8_t *data, size_t len) {
   uint64_t pos = 0;
-  uint32_t code_point;
   uint8_t word;
 
   while (pos < len) {
@@ -42,13 +41,11 @@ utf8_validate (const utf8_t *data, size_t len) {
         continue;
       }
     }
-
     word = data[pos];
     while (word < 0b10000000) {
       if (++pos == len) return true;
       word = data[pos];
     }
-
     if ((word & 0b11100000) == 0b11000000) {
       next_pos = pos + 2;
       if (next_pos > len) {
@@ -57,7 +54,8 @@ utf8_validate (const utf8_t *data, size_t len) {
       if ((data[pos + 1] & 0b11000000) != 0b10000000) {
         return false;
       }
-      code_point = (word & 0b00011111) << 6 | (data[pos + 1] & 0b00111111);
+      uint32_t code_point = ((word & 0b00011111) << 6) |
+                            (data[pos + 1] & 0b00111111);
       if ((code_point < 0x80) || (0x7ff < code_point)) {
         return false;
       }
@@ -72,9 +70,9 @@ utf8_validate (const utf8_t *data, size_t len) {
       if ((data[pos + 2] & 0b11000000) != 0b10000000) {
         return false;
       }
-      code_point = (word & 0b00001111) << 12 |
-                   (data[pos + 1] & 0b00111111) << 6 |
-                   (data[pos + 2] & 0b00111111);
+      uint32_t code_point = ((word & 0b00001111) << 12) |
+                            ((data[pos + 1] & 0b00111111) << 6) |
+                            (data[pos + 2] & 0b00111111);
       if ((code_point < 0x800) || (0xffff < code_point) || (0xd7ff < code_point && code_point < 0xe000)) {
         return false;
       }
@@ -92,8 +90,10 @@ utf8_validate (const utf8_t *data, size_t len) {
       if ((data[pos + 3] & 0b11000000) != 0b10000000) {
         return false;
       }
-      code_point = (word & 0b00000111) << 18 | (data[pos + 1] & 0b00111111) << 12 |
-                   (data[pos + 2] & 0b00111111) << 6 | (data[pos + 3] & 0b00111111);
+      uint32_t code_point = ((word & 0b00000111) << 18) |
+                            ((data[pos + 1] & 0b00111111) << 12) |
+                            ((data[pos + 2] & 0b00111111) << 6) |
+                            (data[pos + 3] & 0b00111111);
       if (code_point <= 0xffff || 0x10ffff < code_point) {
         return false;
       }