Start working on the scanner.

For now, all that is implemented is some functionality which imports UTF-8 into the
memory managed by aplwc, after checking that the data is in fact valid UTF-8.

FossilOrigin-Name: c861e88777d8180cb7b37c11fc7016a900f9d5821a7e3c8e8aab54118d2fca94

2 files changed, 68 insertions, 1 deletions

diff --git a/tests/aplwc_errstr.c b/tests/aplwc_errstr.c
index 0efb777..8014c1e 100644
--- a/tests/aplwc_errstr.c
+++ b/tests/aplwc_errstr.c
@@ -35,7 +35,7 @@ main(void)
 	if(err == NULL)
 		return 1;
 
-	for(ret = 0; ret < APLWC_RC_LAST; ret++){
+	for(ret = 0; ret <= APLWC_RC_LAST; ret++){
 		err = aplwc_errstr_rc(ret);
 		if(err == NULL)
 			return 1;
diff --git a/tests/aplwc_utf8.c b/tests/aplwc_utf8.c
new file mode 100644
index 0000000..b97b978
--- /dev/null
+++ b/tests/aplwc_utf8.c
@@ -0,0 +1,67 @@
+#include <aplwc.h>
+
+uint8_t bad1[] = {0xff,0};
+uint8_t bad2[] = {0x80,0};
+uint8_t bad3[] = {0xc0,0x80,0};
+uint8_t bad4[] = {0xc0,0x40,0};
+uint8_t bad5[] = {0xe0,0x80,0x80,0};
+uint8_t bad6[] = {0xc0,0};
+uint8_t bad7[] = {0xF0,0x80,0x80,0x80,0};
+
+uint8_t good1[] = {0x61,0x70,0x6c,0x77,0x63,0};
+uint8_t good2[] = {0x41,0xe2,0x89,0xa2,0xce,0x91,0x2e,0};
+uint8_t good3[] = {0xed,0x95,0x9c,0xea,0xb5,0xad,0xec,0x96,0xb4,0};
+uint8_t good4[] = {0xe6,0x97,0xa5,0xe6,0x9c,0xac,0xe8,0xaa,0x9e,0};
+uint8_t good5[] = {0xef,0xbb,0xbf,0xf0,0xa3,0x8e,0xb4,0};
+
+int
+main(void)
+{
+	uint8_t data[APLWC_MIN_MEM+64000];
+	struct aplwc *aplwc;
+	struct aplwc_line *line;
+	enum aplwc_rc ret;
+	size_t i;
+
+	uint8_t *bad_tests[] = {
+		bad1,
+		bad2,
+		bad3,
+		bad4,
+		bad5,
+		bad6,
+		bad7
+	};
+
+	uint8_t *good_tests[] = {
+		good1,
+		good2,
+		good3,
+		good4,
+		good5
+	};
+
+	ret = aplwc_new(&aplwc, data, sizeof(data));
+	if(ret)
+		return 1;
+
+	for(i = 0; i < (sizeof(bad_tests)/sizeof(*bad_tests)); i++){
+		line = aplwc_read(aplwc, (char *)bad_tests[i]);
+		if(line != NULL)
+			return 1;
+		if(aplwc_last_error(aplwc) != APLWC_INVALID_UTF8)
+			return 1;
+		aplwc_free_line(line);
+	}
+
+	for(i = 0; i < (sizeof(good_tests)/sizeof(*good_tests)); i++){
+		line = aplwc_read(aplwc, (char *)good_tests[i]);
+		if((line == NULL) && (aplwc_last_error(aplwc) == APLWC_INVALID_UTF8))
+			return 1;
+		aplwc_free_line(line);
+	}
+
+	aplwc_destroy(aplwc);
+
+	return 0;
+}