/* This code is originally from http://www.cl.cam.ac.uk/~mgk25/ucs/ */
struct interval {
- int first;
- int last;
+ ucs_char_t first;
+ ucs_char_t last;
};
size_t display_mode_esc_sequence_len(const char *s)
if (ucs < table[0].first || ucs > table[max].last)
return 0;
while (max >= min) {
- mid = (min + max) / 2;
+ mid = min + (max - min) / 2;
if (ucs > table[mid].last)
min = mid + 1;
else if (ucs < table[mid].first)
{
/*
* Sorted list of non-overlapping intervals of non-spacing characters,
- * generated by
- * "uniset +cat=Me +cat=Mn +cat=Cf -00AD +1160-11FF +200B c".
*/
- static const struct interval combining[] = {
- { 0x0300, 0x036F }, { 0x0483, 0x0489 }, { 0x0591, 0x05BD },
- { 0x05BF, 0x05BF }, { 0x05C1, 0x05C2 }, { 0x05C4, 0x05C5 },
- { 0x05C7, 0x05C7 }, { 0x0600, 0x0604 }, { 0x0610, 0x061A },
- { 0x064B, 0x065F }, { 0x0670, 0x0670 }, { 0x06D6, 0x06E4 },
- { 0x06E7, 0x06E8 }, { 0x06EA, 0x06ED }, { 0x070F, 0x070F },
- { 0x0711, 0x0711 }, { 0x0730, 0x074A }, { 0x07A6, 0x07B0 },
- { 0x0901, 0x0902 }, { 0x093C, 0x093C }, { 0x0941, 0x0948 },
- { 0x094D, 0x094D }, { 0x0951, 0x0954 }, { 0x0962, 0x0963 },
- { 0x0981, 0x0981 }, { 0x09BC, 0x09BC }, { 0x09C1, 0x09C4 },
- { 0x09CD, 0x09CD }, { 0x09E2, 0x09E3 }, { 0x0A01, 0x0A02 },
- { 0x0A3C, 0x0A3C }, { 0x0A41, 0x0A42 }, { 0x0A47, 0x0A48 },
- { 0x0A4B, 0x0A4D }, { 0x0A70, 0x0A71 }, { 0x0A81, 0x0A82 },
- { 0x0ABC, 0x0ABC }, { 0x0AC1, 0x0AC5 }, { 0x0AC7, 0x0AC8 },
- { 0x0ACD, 0x0ACD }, { 0x0AE2, 0x0AE3 }, { 0x0B01, 0x0B01 },
- { 0x0B3C, 0x0B3C }, { 0x0B3F, 0x0B3F }, { 0x0B41, 0x0B43 },
- { 0x0B4D, 0x0B4D }, { 0x0B56, 0x0B56 }, { 0x0B82, 0x0B82 },
- { 0x0BC0, 0x0BC0 }, { 0x0BCD, 0x0BCD }, { 0x0C3E, 0x0C40 },
- { 0x0C46, 0x0C48 }, { 0x0C4A, 0x0C4D }, { 0x0C55, 0x0C56 },
- { 0x0CBC, 0x0CBC }, { 0x0CBF, 0x0CBF }, { 0x0CC6, 0x0CC6 },
- { 0x0CCC, 0x0CCD }, { 0x0D41, 0x0D43 }, { 0x0D4D, 0x0D4D },
- { 0x0DCA, 0x0DCA }, { 0x0DD2, 0x0DD4 }, { 0x0DD6, 0x0DD6 },
- { 0x0E31, 0x0E31 }, { 0x0E34, 0x0E3A }, { 0x0E47, 0x0E4E },
- { 0x0EB1, 0x0EB1 }, { 0x0EB4, 0x0EB9 }, { 0x0EBB, 0x0EBC },
- { 0x0EC8, 0x0ECD }, { 0x0F18, 0x0F19 }, { 0x0F35, 0x0F35 },
- { 0x0F37, 0x0F37 }, { 0x0F39, 0x0F39 }, { 0x0F71, 0x0F7E },
- { 0x0F80, 0x0F84 }, { 0x0F86, 0x0F87 }, { 0x0F90, 0x0F97 },
- { 0x0F99, 0x0FBC }, { 0x0FC6, 0x0FC6 }, { 0x102D, 0x1030 },
- { 0x1032, 0x1032 }, { 0x1036, 0x1037 }, { 0x1039, 0x1039 },
- { 0x1058, 0x1059 }, { 0x1160, 0x11FF }, { 0x1712, 0x1714 },
- { 0x1732, 0x1734 }, { 0x1752, 0x1753 }, { 0x1772, 0x1773 },
- { 0x17B4, 0x17B5 }, { 0x17B7, 0x17BD }, { 0x17C6, 0x17C6 },
- { 0x17C9, 0x17D3 }, { 0x17DD, 0x17DD }, { 0x180B, 0x180D },
- { 0x18A9, 0x18A9 }, { 0x1920, 0x1922 }, { 0x1927, 0x1928 },
- { 0x1932, 0x1932 }, { 0x1939, 0x193B }, { 0x200B, 0x200F },
- { 0x202A, 0x202E }, { 0x2060, 0x2063 }, { 0x206A, 0x206F },
- { 0x20D0, 0x20EA }, { 0x302A, 0x302F }, { 0x3099, 0x309A },
- { 0xFB1E, 0xFB1E }, { 0xFE00, 0xFE0F }, { 0xFE20, 0xFE23 },
- { 0xFEFF, 0xFEFF }, { 0xFFF9, 0xFFFB }, { 0x1D167, 0x1D169 },
- { 0x1D173, 0x1D182 }, { 0x1D185, 0x1D18B },
- { 0x1D1AA, 0x1D1AD }, { 0xE0001, 0xE0001 },
- { 0xE0020, 0xE007F }, { 0xE0100, 0xE01EF }
- };
+#include "unicode-width.h"
/* test for 8-bit control characters */
if (ch == 0)
return -1;
/* binary search in table of non-spacing characters */
- if (bisearch(ch, combining, sizeof(combining)
+ if (bisearch(ch, zero_width, sizeof(zero_width)
/ sizeof(struct interval) - 1))
return 0;
- /*
- * If we arrive here, ch is neither a combining nor a C0/C1
- * control character.
- */
+ /* binary search in table of double width characters */
+ if (bisearch(ch, double_width, sizeof(double_width)
+ / sizeof(struct interval) - 1))
+ return 2;
- return 1 +
- (ch >= 0x1100 &&
- /* Hangul Jamo init. consonants */
- (ch <= 0x115f ||
- ch == 0x2329 || ch == 0x232a ||
- /* CJK ... Yi */
- (ch >= 0x2e80 && ch <= 0xa4cf &&
- ch != 0x303f) ||
- /* Hangul Syllables */
- (ch >= 0xac00 && ch <= 0xd7a3) ||
- /* CJK Compatibility Ideographs */
- (ch >= 0xf900 && ch <= 0xfaff) ||
- /* CJK Compatibility Forms */
- (ch >= 0xfe30 && ch <= 0xfe6f) ||
- /* Fullwidth Forms */
- (ch >= 0xff00 && ch <= 0xff60) ||
- (ch >= 0xffe0 && ch <= 0xffe6) ||
- (ch >= 0x20000 && ch <= 0x2fffd) ||
- (ch >= 0x30000 && ch <= 0x3fffd)));
+ return 1;
}
/*
return 1;
}
-static void strbuf_addchars(struct strbuf *sb, int c, size_t n)
-{
- strbuf_grow(sb, n);
- memset(sb->buf + sb->len, c, n);
- strbuf_setlen(sb, sb->len + n);
-}
-
static void strbuf_add_indented_text(struct strbuf *buf, const char *text,
int indent, int indent2)
{
dst += n;
}
+ if (src >= end)
+ break;
+
old = src;
n = utf8_width((const char**)&src, NULL);
if (!src) /* broken utf-8, do nothing */
- return;
+ goto out;
if (n && w >= pos && w < pos + width) {
if (subst) {
memcpy(dst, subst, subst_len);
}
strbuf_setlen(&sb_dst, dst - sb_dst.buf);
strbuf_swap(sb_src, &sb_dst);
+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);
}
while (1) {
size_t cnt = iconv(conv, &cp, &insz, &outpos, &outsz);
- if (cnt == -1) {
+ if (cnt == (size_t) -1) {
size_t sofar;
if (errno != E2BIG) {
free(out);
return out;
}
+static const char *fallback_encoding(const char *name)
+{
+ /*
+ * Some platforms do not have the variously spelled variants of
+ * UTF-8, so let's fall back to trying the most official
+ * spelling. We do so only as a fallback in case the platform
+ * does understand the user's spelling, but not our official
+ * one.
+ */
+ if (is_encoding_utf8(name))
+ return "UTF-8";
+
+ /*
+ * Even though latin-1 is still seen in e-mail
+ * headers, some platforms only install ISO-8859-1.
+ */
+ if (!strcasecmp(name, "latin-1"))
+ return "ISO-8859-1";
+
+ return name;
+}
+
char *reencode_string_len(const char *in, int insz,
const char *out_encoding, const char *in_encoding,
int *outsz)
conv = iconv_open(out_encoding, in_encoding);
if (conv == (iconv_t) -1) {
- /*
- * Some platforms do not have the variously spelled variants of
- * UTF-8, so let's fall back to trying the most official
- * spelling. We do so only as a fallback in case the platform
- * does understand the user's spelling, but not our official
- * one.
- */
- if (is_encoding_utf8(in_encoding))
- in_encoding = "UTF-8";
- if (is_encoding_utf8(out_encoding))
- out_encoding = "UTF-8";
+ in_encoding = fallback_encoding(in_encoding);
+ out_encoding = fallback_encoding(out_encoding);
+
conv = iconv_open(out_encoding, in_encoding);
if (conv == (iconv_t) -1)
return NULL;
}
#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[] = {'\xFE', '\xFF'};
+static const char utf16_le_bom[] = {'\xFF', '\xFE'};
+static const char utf32_be_bom[] = {'\0', '\0', '\xFE', '\xFF'};
+static const char utf32_le_bom[] = {'\xFF', '\xFE', '\0', '\0'};
+
+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`.
}
}
-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;
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)
+{
+ if (len < strlen(utf8_bom) ||
+ memcmp(*text, utf8_bom, strlen(utf8_bom)))
+ return 0;
+ *text += strlen(utf8_bom);
+ return 1;
+}
+
+void strbuf_utf8_align(struct strbuf *buf, align_type position, unsigned int width,
+ const char *s)
+{
+ int slen = strlen(s);
+ int display_len = utf8_strnwidth(s, slen, 0);
+ int utf8_compensation = slen - display_len;
+
+ if (display_len >= width) {
+ strbuf_addstr(buf, s);
+ return;
+ }
+
+ if (position == ALIGN_LEFT)
+ strbuf_addf(buf, "%-*s", width + utf8_compensation, s);
+ else if (position == ALIGN_MIDDLE) {
+ int left = (width - display_len) / 2;
+ strbuf_addf(buf, "%*s%-*s", left, "", width - left + utf8_compensation, s);
+ } else if (position == ALIGN_RIGHT)
+ strbuf_addf(buf, "%*s", width + utf8_compensation, s);
+}