aboutsummaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
Diffstat
-rw-r--r--Makefile12
-rw-r--r--convert-to-lycian.c18
-rw-r--r--convert-to-lydian.c18
-rw-r--r--convert-to-subscript.c18
-rw-r--r--convert-to-superscript.c18
-rw-r--r--libcharconv.h128
-rw-r--r--libcharconv_latin.c31
-rw-r--r--libcharconv_lycian.c63
-rw-r--r--libcharconv_lydian.c62
-rw-r--r--libcharconv_subscript.c29
-rw-r--r--libcharconv_superscript.c34
11 files changed, 429 insertions, 2 deletions
diff --git a/Makefile b/Makefile
index 2c58556..54016f9 100644
--- a/Makefile
+++ b/Makefile
@@ -44,7 +44,11 @@ BIN =\
convert-to-buhid\
convert-to-replacement\
convert-to-bracketed\
- convert-to-variation-selectors
+ convert-to-variation-selectors\
+ convert-to-superscript\
+ convert-to-subscript\
+ convert-to-lydian\
+ convert-to-lycian
LIBOBJ =\
libcharconv_decode_utf8_.o\
@@ -76,7 +80,11 @@ LIBOBJ =\
libcharconv_buhid.o\
libcharconv_replacement.o\
libcharconv_bracketed.o\
- libcharconv_variation_selectors.o
+ libcharconv_variation_selectors.o\
+ libcharconv_superscript.o\
+ libcharconv_subscript.o\
+ libcharconv_lydian.o\
+ libcharconv_lycian.o
LOBJ = $(LIBOBJ:.o=.lo)
diff --git a/convert-to-lycian.c b/convert-to-lycian.c
new file mode 100644
index 0000000..23caae1
--- /dev/null
+++ b/convert-to-lycian.c
@@ -0,0 +1,18 @@
+/* See LICENSE file for copyright and license details. */
+#include "common.h"
+
+USAGE("");
+
+
+int
+main(int argc, char *argv[])
+{
+ ARGBEGIN {
+ default:
+ usage();
+ } ARGEND;
+ if (argc)
+ usage();
+
+ return convert(&libcharconv_lycian);
+}
diff --git a/convert-to-lydian.c b/convert-to-lydian.c
new file mode 100644
index 0000000..989def7
--- /dev/null
+++ b/convert-to-lydian.c
@@ -0,0 +1,18 @@
+/* See LICENSE file for copyright and license details. */
+#include "common.h"
+
+USAGE("");
+
+
+int
+main(int argc, char *argv[])
+{
+ ARGBEGIN {
+ default:
+ usage();
+ } ARGEND;
+ if (argc)
+ usage();
+
+ return convert(&libcharconv_lydian);
+}
diff --git a/convert-to-subscript.c b/convert-to-subscript.c
new file mode 100644
index 0000000..6f39c92
--- /dev/null
+++ b/convert-to-subscript.c
@@ -0,0 +1,18 @@
+/* See LICENSE file for copyright and license details. */
+#include "common.h"
+
+USAGE("");
+
+
+int
+main(int argc, char *argv[])
+{
+ ARGBEGIN {
+ default:
+ usage();
+ } ARGEND;
+ if (argc)
+ usage();
+
+ return convert(&libcharconv_subscript);
+}
diff --git a/convert-to-superscript.c b/convert-to-superscript.c
new file mode 100644
index 0000000..62037ec
--- /dev/null
+++ b/convert-to-superscript.c
@@ -0,0 +1,18 @@
+/* See LICENSE file for copyright and license details. */
+#include "common.h"
+
+USAGE("");
+
+
+int
+main(int argc, char *argv[])
+{
+ ARGBEGIN {
+ default:
+ usage();
+ } ARGEND;
+ if (argc)
+ usage();
+
+ return convert(&libcharconv_superscript);
+}
diff --git a/libcharconv.h b/libcharconv.h
index 969d95d..9eab393 100644
--- a/libcharconv.h
+++ b/libcharconv.h
@@ -965,4 +965,132 @@ enum libcharconv_result libcharconv_bracketed(const char *s, size_t slen, size_t
enum libcharconv_result libcharconv_variation_selectors(const char *s, size_t slen, size_t *n, uint_least32_t *cp, size_t *ncp);
+/**
+ * Convert to superscript
+ *
+ * @param s Text to convert
+ * @param slen The number of bytes available in `s`
+ * @param n Output parameter for the number of consumed bytes
+ * @param cp Output buffer for the codepoints
+ * @param ncp Input parameter for the number of codepoints that
+ * fit in `cp`, and output parameter for the number
+ * of output codepoints (if it exceeds the original
+ * value of `ncp`, a larger buffer is needed)
+ * @return LIBCHARCONV_NO_CONVERT:
+ * `*n` is the number of bytes from the beginning
+ * of `s` that cannot be converted
+ * LIBCHARCONV_CONVERTED:
+ * `*n` is the number of bytes from the beginning
+ * of `s` that was converted to a codepoint which
+ * is stored in `*cp`
+ * LIBCHARCONV_INDETERMINATE:
+ * If all text has been input, no more can be
+ * converted, otherwise more of the text most
+ * be made available before the function can
+ * determine whether the beginning of `s` can be
+ * converted or what it should be converted to
+ * LIBCHARCONV_CONVERT_IF_END:
+ * As LIBCHARCONV_CONVERTED the entire text has
+ * been input, as LIBCHARCONV_INDETERMINATE
+ * otherwise
+ */
+enum libcharconv_result libcharconv_superscript(const char *s, size_t slen, size_t *n, uint_least32_t *cp, size_t *ncp);
+
+
+/**
+ * Convert to subscript
+ *
+ * @param s Text to convert
+ * @param slen The number of bytes available in `s`
+ * @param n Output parameter for the number of consumed bytes
+ * @param cp Output buffer for the codepoints
+ * @param ncp Input parameter for the number of codepoints that
+ * fit in `cp`, and output parameter for the number
+ * of output codepoints (if it exceeds the original
+ * value of `ncp`, a larger buffer is needed)
+ * @return LIBCHARCONV_NO_CONVERT:
+ * `*n` is the number of bytes from the beginning
+ * of `s` that cannot be converted
+ * LIBCHARCONV_CONVERTED:
+ * `*n` is the number of bytes from the beginning
+ * of `s` that was converted to a codepoint which
+ * is stored in `*cp`
+ * LIBCHARCONV_INDETERMINATE:
+ * If all text has been input, no more can be
+ * converted, otherwise more of the text most
+ * be made available before the function can
+ * determine whether the beginning of `s` can be
+ * converted or what it should be converted to
+ * LIBCHARCONV_CONVERT_IF_END:
+ * As LIBCHARCONV_CONVERTED the entire text has
+ * been input, as LIBCHARCONV_INDETERMINATE
+ * otherwise
+ */
+enum libcharconv_result libcharconv_subscript(const char *s, size_t slen, size_t *n, uint_least32_t *cp, size_t *ncp);
+
+
+/**
+ * Preforms convertion from Latin to Lydian
+ *
+ * @param s Text to convert
+ * @param slen The number of bytes available in `s`
+ * @param n Output parameter for the number of consumed bytes
+ * @param cp Output buffer for the codepoints
+ * @param ncp Input parameter for the number of codepoints that
+ * fit in `cp`, and output parameter for the number
+ * of output codepoints (if it exceeds the original
+ * value of `ncp`, a larger buffer is needed)
+ * @return LIBCHARCONV_NO_CONVERT:
+ * `*n` is the number of bytes from the beginning
+ * of `s` that cannot be converted
+ * LIBCHARCONV_CONVERTED:
+ * `*n` is the number of bytes from the beginning
+ * of `s` that was converted to a codepoint which
+ * is stored in `*cp`
+ * LIBCHARCONV_INDETERMINATE:
+ * If all text has been input, no more can be
+ * converted, otherwise more of the text most
+ * be made available before the function can
+ * determine whether the beginning of `s` can be
+ * converted or what it should be converted to
+ * LIBCHARCONV_CONVERT_IF_END:
+ * As LIBCHARCONV_CONVERTED the entire text has
+ * been input, as LIBCHARCONV_INDETERMINATE
+ * otherwise
+ */
+enum libcharconv_result libcharconv_lydian(const char *s, size_t slen, size_t *n, uint_least32_t *cp, size_t *ncp);
+
+
+/**
+ * Preforms convertion from Latin to Lycian
+ *
+ * @param s Text to convert
+ * @param slen The number of bytes available in `s`
+ * @param n Output parameter for the number of consumed bytes
+ * @param cp Output buffer for the codepoints
+ * @param ncp Input parameter for the number of codepoints that
+ * fit in `cp`, and output parameter for the number
+ * of output codepoints (if it exceeds the original
+ * value of `ncp`, a larger buffer is needed)
+ * @return LIBCHARCONV_NO_CONVERT:
+ * `*n` is the number of bytes from the beginning
+ * of `s` that cannot be converted
+ * LIBCHARCONV_CONVERTED:
+ * `*n` is the number of bytes from the beginning
+ * of `s` that was converted to a codepoint which
+ * is stored in `*cp`
+ * LIBCHARCONV_INDETERMINATE:
+ * If all text has been input, no more can be
+ * converted, otherwise more of the text most
+ * be made available before the function can
+ * determine whether the beginning of `s` can be
+ * converted or what it should be converted to
+ * LIBCHARCONV_CONVERT_IF_END:
+ * As LIBCHARCONV_CONVERTED the entire text has
+ * been input, as LIBCHARCONV_INDETERMINATE
+ * otherwise
+ */
+enum libcharconv_result libcharconv_lycian(const char *s, size_t slen, size_t *n, uint_least32_t *cp, size_t *ncp);
+
+
#endif
diff --git a/libcharconv_latin.c b/libcharconv_latin.c
index d3c1817..60a2fb5 100644
--- a/libcharconv_latin.c
+++ b/libcharconv_latin.c
@@ -299,6 +299,34 @@ libcharconv_latin(const char *s, size_t slen, size_t *n, uint_least32_t *cp, siz
goto conv3;
}
+ } else if (UINT32_C(0x2070) <= c && c <= UINT32_C(0x2079)) {
+ /* superscript */
+ c -= (uint_least32_t)UINT32_C(0x2070) - (uint_least32_t)'0';
+ goto conv;
+ } else if (UINT32_C(0x00B2) <= c && c <= UINT32_C(0x00B3)) {
+ /* superscript */
+ c -= (uint_least32_t)UINT32_C(0x00B2) - (uint_least32_t)'2';
+ goto conv;
+ } else if (c == UINT32_C(0x00B9)) {
+ /* superscript */
+ c -= (uint_least32_t)UINT32_C(0x00B9) - (uint_least32_t)'1';
+ goto conv;
+
+ } else if (UINT32_C(0x2080) <= c && c <= UINT32_C(0x2089)) {
+ /* subscript */
+ c -= (uint_least32_t)UINT32_C(0x2080) - (uint_least32_t)'0';
+ goto conv;
+
+ } else if (UINT32_C(0x10920) <= c && c <= UINT32_C(0x10939)) {
+ /* lydian */
+ c = (uint_least32_t)"abgdeviyklmnorStufqsTAELNc"[c - UINT32_C(0x10920)];
+ goto conv;
+
+ } else if (UINT32_C(0x10280) <= c && c <= UINT32_C(0x1029C)) {
+ /* lycian */
+ c = (uint_least32_t)"aebBgdiwzDjkqlmnMNupKrstTAEhx"[c - UINT32_C(0x10280)];
+ goto conv;
+
} else {
switch (c) {
/* shogi */
@@ -428,6 +456,9 @@ libcharconv_latin(const char *s, size_t slen, size_t *n, uint_least32_t *cp, siz
c = (uint_least32_t)'?';
goto conv;
+ /* lydian */
+ case UINT32_C(0x1093F): c = (uint_least32_t)'"'; goto conv;
+
default:
no_match:
*n += clen;
diff --git a/libcharconv_lycian.c b/libcharconv_lycian.c
new file mode 100644
index 0000000..7998ecb
--- /dev/null
+++ b/libcharconv_lycian.c
@@ -0,0 +1,63 @@
+/* See LICENSE file for copyright and license details. */
+#include "lib-common.h"
+
+
+static struct {
+ unsigned char cp_low;
+ char latin;
+} lycian[] = {
+ {0x80, 'a'},
+ {0x82, 'b'},
+ {0x85, 'd'},
+ {0x81, 'e'},
+ {0x84, 'g'},
+ {0x9B, 'h'},
+ {0x86, 'i'},
+ {0x8A, 'j'},
+ {0x8B, 'k'},
+ {0x8D, 'l'},
+ {0x8E, 'm'},
+ {0x8F, 'n'},
+ {0x93, 'p'},
+ {0x8C, 'q'},
+ {0x95, 'r'},
+ {0x96, 's'},
+ {0x97, 't'},
+ {0x92, 'u'},
+ {0x87, 'w'},
+ {0x9C, 'x'},
+ {0x88, 'z'},
+ {0x99, 'A'},
+ {0x83, 'B'},
+ {0x89, 'D'},
+ {0x9A, 'E'},
+ {0x94, 'K'},
+ {0x90, 'M'},
+ {0x91, 'N'},
+ {0x98, 'T'}
+};
+
+
+enum libcharconv_result
+libcharconv_lycian(const char *s, size_t slen, size_t *n, uint_least32_t *cp, size_t *ncp)
+{
+ size_t i;
+ *n = 0;
+ for (; slen--; s++) {
+ for (i = 0u; i < sizeof(lycian) / sizeof(*lycian); i++)
+ if (*s == lycian[i].latin)
+ goto conv;
+ *n += 1u;
+ }
+no_conv:
+ return LIBCHARCONV_NO_CONVERT;
+
+conv:
+ if (*n)
+ goto no_conv;
+ if (*ncp)
+ *cp = (uint_least32_t)(UINT32_C(0x10200) | lycian[i].cp_low);
+ *n += 1u;
+ *ncp = 1u;
+ return LIBCHARCONV_CONVERTED;
+}
diff --git a/libcharconv_lydian.c b/libcharconv_lydian.c
new file mode 100644
index 0000000..a3427fa
--- /dev/null
+++ b/libcharconv_lydian.c
@@ -0,0 +1,62 @@
+/* See LICENSE file for copyright and license details. */
+#include "lib-common.h"
+
+
+static struct {
+ unsigned char cp_low;
+ char latin;
+} lydian[] = {
+ {0x20, 'a'},
+ {0x21, 'b'},
+ {0x39, 'c'},
+ {0x23, 'd'},
+ {0x24, 'e'},
+ {0x31, 'f'},
+ {0x22, 'g'},
+ {0x26, 'i'},
+ {0x28, 'k'},
+ {0x29, 'l'},
+ {0x2A, 'm'},
+ {0x2B, 'n'},
+ {0x2C, 'o'},
+ {0x32, 'q'},
+ {0x2D, 'r'},
+ {0x33, 's'},
+ {0x2F, 't'},
+ {0x30, 'u'},
+ {0x25, 'v'},
+ {0x27, 'y'},
+ {0x35, 'A'},
+ {0x36, 'E'},
+ {0x37, 'L'},
+ {0x38, 'N'},
+ {0x2E, 'S'},
+ {0x34, 'T'},
+ {0x3F, '\"'},
+ {0x3F, '\''}
+};
+
+
+enum libcharconv_result
+libcharconv_lydian(const char *s, size_t slen, size_t *n, uint_least32_t *cp, size_t *ncp)
+{
+ size_t i;
+ *n = 0;
+ for (; slen--; s++) {
+ for (i = 0u; i < sizeof(lydian) / sizeof(*lydian); i++)
+ if (*s == lydian[i].latin)
+ goto conv;
+ *n += 1u;
+ }
+no_conv:
+ return LIBCHARCONV_NO_CONVERT;
+
+conv:
+ if (*n)
+ goto no_conv;
+ if (*ncp)
+ *cp = (uint_least32_t)(UINT32_C(0x10900) | lydian[i].cp_low);
+ *n += 1u;
+ *ncp = 1u;
+ return LIBCHARCONV_CONVERTED;
+}
diff --git a/libcharconv_subscript.c b/libcharconv_subscript.c
new file mode 100644
index 0000000..35a3a72
--- /dev/null
+++ b/libcharconv_subscript.c
@@ -0,0 +1,29 @@
+/* See LICENSE file for copyright and license details. */
+#include "lib-common.h"
+
+
+enum libcharconv_result
+libcharconv_subscript(const char *s, size_t slen, size_t *n, uint_least32_t *cp, size_t *ncp)
+{
+ uint_least32_t c;
+ *n = 0;
+ for (; slen--; s++) {
+ if ('0' <= *s && *s <= '9') {
+ c = (uint_least32_t)(UINT32_C(0x2080) + (unsigned)(*s - '0'));
+ goto conv;
+ } else {
+ *n += 1u;
+ }
+ }
+no_conv:
+ return LIBCHARCONV_NO_CONVERT;
+
+conv:
+ if (*n)
+ goto no_conv;
+ if (*ncp)
+ *cp = c;
+ *n += 1u;
+ *ncp = 1u;
+ return LIBCHARCONV_CONVERTED;
+}
diff --git a/libcharconv_superscript.c b/libcharconv_superscript.c
new file mode 100644
index 0000000..d15f490
--- /dev/null
+++ b/libcharconv_superscript.c
@@ -0,0 +1,34 @@
+/* See LICENSE file for copyright and license details. */
+#include "lib-common.h"
+
+
+enum libcharconv_result
+libcharconv_superscript(const char *s, size_t slen, size_t *n, uint_least32_t *cp, size_t *ncp)
+{
+ uint_least32_t c;
+ *n = 0;
+ for (; slen--; s++) {
+ if (*s == '1') {
+ c = (uint_least32_t)UINT32_C(0x00B9);
+ } else if ('2' <= *s && *s <= '3') {
+ c = (uint_least32_t)(UINT32_C(0x00B2) + (unsigned)(*s - '2'));
+ } else if ('0' <= *s && *s <= '9') {
+ c = (uint_least32_t)(UINT32_C(0x2070) + (unsigned)(*s - '0'));
+ } else {
+ *n += 1u;
+ continue;
+ }
+ goto conv;
+ }
+no_conv:
+ return LIBCHARCONV_NO_CONVERT;
+
+conv:
+ if (*n)
+ goto no_conv;
+ if (*ncp)
+ *cp = c;
+ *n += 1u;
+ *ncp = 1u;
+ return LIBCHARCONV_CONVERTED;
+}
generated by cgit v1.2.3-70-g09d2 (git 2.51.0) at 2026-02-20 21:47:10 +0000