Add tests for u8upper()

3 files changed, 108 insertions, 0 deletions

diff --git a/test/data/UppercaseTest b/test/data/UppercaseTest
new file mode 100644
index 0000000..76612ac
--- /dev/null
+++ b/test/data/UppercaseTest
@@ -0,0 +1,23 @@
+# Empty input
+;;
+
+# Latin alphabet
+Lorem ipsum dolor sit amet, consectetur adipiscing elit.;LOREM IPSUM DOLOR SIT AMET, CONSECTETUR ADIPISCING ELIT.;
+
+# Greek alphabet
+Δεν υπάρχει κανείς που να αγαπάει τον ίδιο τον πόνο;ΔΕΝ ΥΠΆΡΧΕΙ ΚΑΝΕΊΣ ΠΟΥ ΝΑ ΑΓΑΠΆΕΙ ΤΟΝ ΊΔΙΟ ΤΟΝ ΠΌΝΟ;
+
+# Cyrillic alphabet
+Слава Україні проти російської агресії!;СЛАВА УКРАЇНІ ПРОТИ РОСІЙСЬКОЇ АГРЕСІЇ!;
+
+# Capital ‘ß’ with CF_ẞ, and ‘SS’ otherwise
+Was ich nicht weiß, macht mich nicht heiß;WAS ICH NICHT WEISS, MACHT MICH NICHT HEISS;
+Was ich nicht weiß, macht mich nicht heiß;WAS ICH NICHT WEIẞ, MACHT MICH NICHT HEIẞ;ẞ
+
+# Uppercase ‘i’ to ‘İ’ in Azeri/Turkish
+istanbul’luyum;ISTANBUL’LUYUM;
+istanbul’luyum;İSTANBUL’LUYUM;AZ
+
+# Remove U+0307 COMBINING DOT ABOVE in Lithuanian
+ràsti, mèsti, ki̇̀lo;RÀSTI, MÈSTI, Kİ̀LO;
+ràsti, mèsti, ki̇̀lo;RÀSTI, MÈSTI, KÌLO;LT
diff --git a/test/gen-test-data b/test/gen-test-data
index b9932ae..2f9e5a2 100755
--- a/test/gen-test-data
+++ b/test/gen-test-data
@@ -12,5 +12,6 @@ download()
 download 'auxiliary/GraphemeBreakTest.txt'
 download 'auxiliary/WordBreakTest.txt'
 
+grep '^[^#]'                         data/UppercaseTest     >upper.in
 sed -En 's/\s+//g; s/÷?#.*//g; /./p' data/GraphemeBreakTest >gnext.in
 sed -En 's/\s+//g; s/÷?#.*//g; /./p' data/WordBreakTest     >wnext.in
diff --git a/test/upper-test.c b/test/upper-test.c
new file mode 100644
index 0000000..6881e0c
--- /dev/null
+++ b/test/upper-test.c
@@ -0,0 +1,84 @@
+#define _GNU_SOURCE
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+
+#include <alloc.h>
+#include <errors.h>
+#include <macros.h>
+#include <mbstring.h>
+#include <unicode/string.h>
+
+#define TESTFILE "upper.in"
+
+static bool test(const char8_t *, int);
+
+int
+main(int, char **argv)
+{
+	int rv;
+	size_t n;
+	ssize_t nr;
+	char *line;
+	FILE *fp;
+
+	rv = EXIT_SUCCESS;
+	line = nullptr;
+	mlib_setprogname(argv[0]);
+
+	if ((fp = fopen(TESTFILE, "r")) == nullptr)
+		err("fopen: %s:", TESTFILE);
+
+	for (int id = 1; (nr = getline(&line, &n, fp)) > 0; id++) {
+		if (line[nr - 1] == '\n')
+			line[--nr] = '\0';
+
+		if (!test(line, id))
+			rv = EXIT_FAILURE;
+	}
+	if (ferror(fp))
+		err("getline: %s:", TESTFILE);
+
+	free(line);
+	fclose(fp);
+	return rv;
+}
+
+bool
+test(const char8_t *line, int id)
+{
+	struct u8view before, after, flags;
+	before.p = line;
+	after.p = strchr(line, ';') + 1;
+	before.len = after.p - before.p - 1;
+	flags.p = strchr(after.p, ';') + 1;
+	after.len = flags.p - after.p - 1;
+	flags.len = strlen(flags.p);
+
+	enum caseflags cf = 0;
+	if (u8eq(U8_ARGS(flags), U8_ARGS(U8("ẞ"))))
+		cf |= CF_ẞ;
+	else if (u8eq(U8_ARGS(flags), U8_ARGS(U8("AZ"))))
+		cf |= CF_LANG_AZ;
+	else if (u8eq(U8_ARGS(flags), U8_ARGS(U8("LT"))))
+		cf |= CF_LANG_LT;
+
+	char8_t *buf = bufalloc(nullptr, 1, after.len);
+	size_t ret = u8upper(buf, after.len, U8_ARGS(before), cf);
+
+	if (ret != after.len) {
+		warn("case %d: expected uppercased length of %zu but got %zu "
+		     "(flags=‘%.*s’)",
+		     id, after.len, ret, U8_PRI_ARGS(flags));
+		return false;
+	}
+
+	if (!memeq(buf, after.p, after.len)) {
+		warn("case %d: expected ‘%.*s’ but got ‘%.*s’ (flags=‘%.*s’)", id,
+		     U8_PRI_ARGS(after), (int)after.len, buf, U8_PRI_ARGS(flags));
+		return false;
+	}
+
+	free(buf);
+	return true;
+}