Sync with v1.9.5

diff --git a/utf8.c b/utf8.c
index 536a9c83e1bbde516df22288d6156160b12a62ce..a89704017a0997fd93ba14f198eb3e199d0f4274 100644 (file)
--- a/utf8.c
+++ b/utf8.c
@@ -5,8 +5,8 @@
 /* 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)
@@ -528,7 +528,7 @@ char *reencode_string_iconv(const char *in, size_t insz, iconv_t conv, int *outs
        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);
@@ -627,3 +627,67 @@ int mbs_chrlen(const char **text, size_t *remainder_p, const char *encoding)
 
        return chrlen;
 }
+
+/*
+ * Pick the next char from the stream, folding as an HFS+ filename comparison
+ * would. Note that this is _not_ complete by any means. It's just enough
+ * to make is_hfs_dotgit() work, and should not be used otherwise.
+ */
+static ucs_char_t next_hfs_char(const char **in)
+{
+       while (1) {
+               ucs_char_t out = pick_one_utf8_char(in, NULL);
+               /*
+                * check for malformed utf8. Technically this
+                * gets converted to a percent-sequence, but
+                * returning 0 is good enough for is_hfs_dotgit
+                * to realize it cannot be .git
+                */
+               if (!*in)
+                       return 0;
+
+               /* these code points are ignored completely */
+               switch (out) {
+               case 0x200c: /* ZERO WIDTH NON-JOINER */
+               case 0x200d: /* ZERO WIDTH JOINER */
+               case 0x200e: /* LEFT-TO-RIGHT MARK */
+               case 0x200f: /* RIGHT-TO-LEFT MARK */
+               case 0x202a: /* LEFT-TO-RIGHT EMBEDDING */
+               case 0x202b: /* RIGHT-TO-LEFT EMBEDDING */
+               case 0x202c: /* POP DIRECTIONAL FORMATTING */
+               case 0x202d: /* LEFT-TO-RIGHT OVERRIDE */
+               case 0x202e: /* RIGHT-TO-LEFT OVERRIDE */
+               case 0x206a: /* INHIBIT SYMMETRIC SWAPPING */
+               case 0x206b: /* ACTIVATE SYMMETRIC SWAPPING */
+               case 0x206c: /* INHIBIT ARABIC FORM SHAPING */
+               case 0x206d: /* ACTIVATE ARABIC FORM SHAPING */
+               case 0x206e: /* NATIONAL DIGIT SHAPES */
+               case 0x206f: /* NOMINAL DIGIT SHAPES */
+               case 0xfeff: /* ZERO WIDTH NO-BREAK SPACE */
+                       continue;
+               }
+
+               /*
+                * there's a great deal of other case-folding that occurs,
+                * but this is enough to catch anything that will convert
+                * to ".git"
+                */
+               return tolower(out);
+       }
+}
+
+int is_hfs_dotgit(const char *path)
+{
+       ucs_char_t c;
+
+       if (next_hfs_char(&path) != '.' ||
+           next_hfs_char(&path) != 'g' ||
+           next_hfs_char(&path) != 'i' ||
+           next_hfs_char(&path) != 't')
+               return 0;
+       c = next_hfs_char(&path);
+       if (c && !is_dir_sep(c))
+               return 0;
+
+       return 1;
+}