Add control character representations

Signed-off-by: Mattias Andrée <m@maandree.se>

1 files changed, 65 insertions, 0 deletions

diff --git a/libcharconv_control_character_representations.c b/libcharconv_control_character_representations.c
new file mode 100644
index 0000000..57c1c93
--- /dev/null
+++ b/libcharconv_control_character_representations.c
@@ -0,0 +1,65 @@
+/* See LICENSE file for copyright and license details. */
+#include "lib-common.h"
+#include <string.h>
+
+
+static const char *texts[] = {
+	"NUL", "SOH", "STX", "ETX", "EOT", "ENQ", "ACK", "BEL",
+	"BS",  "HT",  "LF", " VT",  "FF",  "CR",  "SS",  "SI",
+	"DLE", "DC1", "DC2", "DC3", "DC4", "NAK", "SYN", "ETB",
+	"CAN", "EM",  "SUB", "ESC", "FS",  "GS",  "RS",  "US",
+	"SP",  "DEL"
+};
+
+
+enum libcharconv_result
+libcharconv_control_character_representations(const char *s, size_t slen, size_t *n, uint_least32_t *cp, size_t *ncp)
+{
+	size_t i, len, found, found_len;
+	int indeterminate;
+	*n = 0;
+	for (; slen; s++, slen--, ++*n) {
+		if (*(const unsigned char *)s <= ' ') {
+			found = *(const unsigned char *)s;
+			goto conv_byte;
+		} else if (*(const unsigned char *)s == 0x7Fu) {
+			found = 0x21u;
+			goto conv_byte;
+		}
+		indeterminate = 0;
+		found = SIZE_MAX;
+		found_len = 0u;
+		for (i = 0u; i < sizeof(texts) / sizeof(*texts); i++) {
+			len = strlen(texts[i]);
+			if (strncmp(s, texts[i], len < slen ? len : slen))
+				continue;
+			if (slen < len) {
+				indeterminate = 1;
+				continue;
+			}
+			if (len > found_len) {
+				found = i;
+				found_len = len;
+			}
+		}
+		if (found_len)
+			goto conv;
+		if (*n)
+			goto no_conv;
+		if (indeterminate)
+			return LIBCHARCONV_INDETERMINATE;
+	}
+no_conv:
+	return LIBCHARCONV_NO_CONVERT;
+
+conv_byte:
+	found_len = 1u;
+conv:
+	if (*n)
+		goto no_conv;
+	if (*ncp)
+		*cp = (uint_least32_t)UINT32_C(0x2400) | (uint_least32_t)found;
+	*n += found_len;
+	*ncp = 1u;
+	return indeterminate ? LIBCHARCONV_CONVERT_IF_END : LIBCHARCONV_CONVERTED;
+}