summaryrefslogtreecommitdiff
path: root/lib/unicase/u-prefix-context.h
diff options
context:
space:
mode:
Diffstat (limited to 'lib/unicase/u-prefix-context.h')
-rw-r--r--lib/unicase/u-prefix-context.h101
1 files changed, 101 insertions, 0 deletions
diff --git a/lib/unicase/u-prefix-context.h b/lib/unicase/u-prefix-context.h
new file mode 100644
index 00000000..b30ed6b1
--- /dev/null
+++ b/lib/unicase/u-prefix-context.h
@@ -0,0 +1,101 @@
+/* Case-mapping context of prefix UTF-8/UTF-16/UTF-32 string.
+ Copyright (C) 2009-2018 Free Software Foundation, Inc.
+ Written by Bruno Haible <bruno@clisp.org>, 2009.
+
+ This program is free software: you can redistribute it and/or
+ modify it under the terms of either:
+
+ * the GNU Lesser General Public License as published by the Free
+ Software Foundation; either version 3 of the License, or (at your
+ option) any later version.
+
+ or
+
+ * the GNU General Public License as published by the Free
+ Software Foundation; either version 2 of the License, or (at your
+ option) any later version.
+
+ or both in parallel, as here.
+ This program is distributed in the hope that it will be useful,
+ but WITHOUT ANY WARRANTY; without even the implied warranty of
+ MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ Lesser General Public License for more details.
+
+ You should have received a copy of the GNU Lesser General Public License
+ along with this program. If not, see <https://www.gnu.org/licenses/>. */
+
+casing_prefix_context_t
+FUNC1 (const UNIT *s, size_t n)
+{
+ return FUNC2 (s, n, unicase_empty_prefix_context);
+}
+
+casing_prefix_context_t
+FUNC2 (const UNIT *s, size_t n, casing_prefix_context_t a_context)
+{
+#if 0
+ /* Forward iteration. Slow for long strings. */
+ casing_prefix_context_t context = a_context;
+ const UNIT *s_end = s + n;
+
+ while (s < s_end)
+ {
+ ucs4_t uc;
+ int count = U_MBTOUC_UNSAFE (&uc, s, s_end - s);
+
+ if (!uc_is_case_ignorable (uc))
+ context.last_char_except_ignorable = uc;
+
+ {
+ int ccc = uc_combining_class (uc);
+ if (ccc == UC_CCC_A || ccc == UC_CCC_NR)
+ context.last_char_normal_or_above = uc;
+ }
+
+ s += count;
+ }
+
+ return context;
+#else
+ /* Iterate backwards, only as far as needed. */
+ casing_prefix_context_t context;
+ ucs4_t last_char_except_ignorable = (ucs4_t)(-1);
+ ucs4_t last_char_normal_or_above = (ucs4_t)(-1);
+ const UNIT *p = s + n;
+
+ for (;;)
+ {
+ ucs4_t uc;
+ p = U_PREV (&uc, p, s);
+ if (p == NULL)
+ break;
+
+ if (last_char_except_ignorable == (ucs4_t)(-1))
+ {
+ if (!uc_is_case_ignorable (uc))
+ last_char_except_ignorable = uc;
+ }
+
+ if (last_char_normal_or_above == (ucs4_t)(-1))
+ {
+ int ccc = uc_combining_class (uc);
+ if (ccc == UC_CCC_A || ccc == UC_CCC_NR)
+ last_char_normal_or_above = uc;
+ }
+
+ if (last_char_except_ignorable != (ucs4_t)(-1)
+ && last_char_normal_or_above != (ucs4_t)(-1))
+ break;
+ }
+ context.last_char_except_ignorable =
+ (last_char_except_ignorable != (ucs4_t)(-1)
+ ? last_char_except_ignorable
+ : a_context.last_char_except_ignorable);
+ context.last_char_normal_or_above =
+ (last_char_normal_or_above != (ucs4_t)(-1)
+ ? last_char_normal_or_above
+ : a_context.last_char_normal_or_above);
+
+ return context;
+#endif
+}