summaryrefslogtreecommitdiff
path: root/utf8.c
diff options
context:
space:
mode:
Diffstat (limited to 'utf8.c')
-rw-r--r--utf8.c123
1 files changed, 109 insertions, 14 deletions
diff --git a/utf8.c b/utf8.c
index 4419055b48..d55e20c641 100644
--- a/utf8.c
+++ b/utf8.c
@@ -401,18 +401,40 @@ out:
strbuf_release(&sb_dst);
}
+/*
+ * Returns true (1) if the src encoding name matches the dst encoding
+ * name directly or one of its alternative names. E.g. UTF-16BE is the
+ * same as UTF16BE.
+ */
+static int same_utf_encoding(const char *src, const char *dst)
+{
+ if (istarts_with(src, "utf") && istarts_with(dst, "utf")) {
+ /* src[3] or dst[3] might be '\0' */
+ int i = (src[3] == '-' ? 4 : 3);
+ int j = (dst[3] == '-' ? 4 : 3);
+ return !strcasecmp(src+i, dst+j);
+ }
+ return 0;
+}
+
int is_encoding_utf8(const char *name)
{
if (!name)
return 1;
- if (!strcasecmp(name, "utf-8") || !strcasecmp(name, "utf8"))
+ if (same_utf_encoding("utf-8", name))
return 1;
return 0;
}
int same_encoding(const char *src, const char *dst)
{
- if (is_encoding_utf8(src) && is_encoding_utf8(dst))
+ static const char utf8[] = "UTF-8";
+
+ if (!src)
+ src = utf8;
+ if (!dst)
+ dst = utf8;
+ if (same_utf_encoding(src, dst))
return 1;
return !strcasecmp(src, dst);
}
@@ -538,6 +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`.
@@ -620,28 +681,33 @@ static ucs_char_t next_hfs_char(const char **in)
}
}
-int is_hfs_dotgit(const char *path)
+static int is_hfs_dot_generic(const char *path,
+ const char *needle, size_t needle_len)
{
ucs_char_t c;
c = next_hfs_char(&path);
if (c != '.')
return 0;
- c = next_hfs_char(&path);
/*
* there's a great deal of other case-folding that occurs
- * in HFS+, but this is enough to catch anything that will
- * convert to ".git"
+ * in HFS+, but this is enough to catch our fairly vanilla
+ * hard-coded needles.
*/
- if (c != 'g' && c != 'G')
- return 0;
- c = next_hfs_char(&path);
- if (c != 'i' && c != 'I')
- return 0;
- c = next_hfs_char(&path);
- if (c != 't' && c != 'T')
- return 0;
+ for (; needle_len > 0; needle++, needle_len--) {
+ c = next_hfs_char(&path);
+
+ /*
+ * We know our needles contain only ASCII, so we clamp here to
+ * make the results of tolower() sane.
+ */
+ if (c > 127)
+ return 0;
+ if (tolower(c) != *needle)
+ return 0;
+ }
+
c = next_hfs_char(&path);
if (c && !is_dir_sep(c))
return 0;
@@ -649,6 +715,35 @@ int is_hfs_dotgit(const char *path)
return 1;
}
+/*
+ * Inline wrapper to make sure the compiler resolves strlen() on literals at
+ * compile time.
+ */
+static inline int is_hfs_dot_str(const char *path, const char *needle)
+{
+ return is_hfs_dot_generic(path, needle, strlen(needle));
+}
+
+int is_hfs_dotgit(const char *path)
+{
+ return is_hfs_dot_str(path, "git");
+}
+
+int is_hfs_dotgitmodules(const char *path)
+{
+ return is_hfs_dot_str(path, "gitmodules");
+}
+
+int is_hfs_dotgitignore(const char *path)
+{
+ return is_hfs_dot_str(path, "gitignore");
+}
+
+int is_hfs_dotgitattributes(const char *path)
+{
+ return is_hfs_dot_str(path, "gitattributes");
+}
+
const char utf8_bom[] = "\357\273\277";
int skip_utf8_bom(char **text, size_t len)