Merge branch 'ma/http-walker-no-partial'

diff --git a/utf8.c b/utf8.c
index 40f4b142d6983cb134992ffffa07413b75a6cece..0fcc6487e3d8b4a4af81c92148fb4edb9574f524 100644 (file)
--- a/utf8.c
+++ b/utf8.c
@@ -81,7 +81,7 @@ static int git_wcwidth(ucs_char_t ch)
        /*
         * Sorted list of non-overlapping intervals of non-spacing characters,
         */
-#include "unicode_width.h"
+#include "unicode-width.h"
 
        /* test for 8-bit control characters */
        if (ch == 0)
@@ -560,6 +560,45 @@ char *reencode_string_len(const char *in, int insz,
 }
 #endif
 
+static int has_bom_prefix(const char *data, size_t len,
+                         const char *bom, size_t bom_len)
+{
+       return data && bom && (len >= bom_len) && !memcmp(data, bom, bom_len);
+}
+
+static const char utf16_be_bom[] = {0xFE, 0xFF};
+static const char utf16_le_bom[] = {0xFF, 0xFE};
+static const char utf32_be_bom[] = {0x00, 0x00, 0xFE, 0xFF};
+static const char utf32_le_bom[] = {0xFF, 0xFE, 0x00, 0x00};
+
+int has_prohibited_utf_bom(const char *enc, const char *data, size_t len)
+{
+       return (
+         (same_utf_encoding("UTF-16BE", enc) ||
+          same_utf_encoding("UTF-16LE", enc)) &&
+         (has_bom_prefix(data, len, utf16_be_bom, sizeof(utf16_be_bom)) ||
+          has_bom_prefix(data, len, utf16_le_bom, sizeof(utf16_le_bom)))
+       ) || (
+         (same_utf_encoding("UTF-32BE",  enc) ||
+          same_utf_encoding("UTF-32LE", enc)) &&
+         (has_bom_prefix(data, len, utf32_be_bom, sizeof(utf32_be_bom)) ||
+          has_bom_prefix(data, len, utf32_le_bom, sizeof(utf32_le_bom)))
+       );
+}
+
+int is_missing_required_utf_bom(const char *enc, const char *data, size_t len)
+{
+       return (
+          (same_utf_encoding(enc, "UTF-16")) &&
+          !(has_bom_prefix(data, len, utf16_be_bom, sizeof(utf16_be_bom)) ||
+            has_bom_prefix(data, len, utf16_le_bom, sizeof(utf16_le_bom)))
+       ) || (
+          (same_utf_encoding(enc, "UTF-32")) &&
+          !(has_bom_prefix(data, len, utf32_be_bom, sizeof(utf32_be_bom)) ||
+            has_bom_prefix(data, len, utf32_le_bom, sizeof(utf32_le_bom)))
+       );
+}
+
 /*
  * Returns first character length in bytes for multi-byte `text` according to
  * `encoding`.