Add test for UTF16LE string support

Issue #941

1 files changed, 32 insertions, 0 deletions

diff --git a/qt5/tests/check_utf_conversion.cpp b/qt5/tests/check_utf_conversion.cpp
index f28829f4..1f04c2a5 100644
--- a/qt5/tests/check_utf_conversion.cpp
+++ b/qt5/tests/check_utf_conversion.cpp
@@ -4,6 +4,7 @@
 #include <poppler-private.h>
 
 #include <cstring>
+#include <cstdint> // for uint16_t
 
 #include "GlobalParams.h"
 #include "UnicodeTypeTable.h"
@@ -18,6 +19,7 @@ private slots:
     void testUTF_data();
     void testUTF();
     void testUnicodeToAscii7();
+    void testUnicodeLittleEndian();
 };
 
 static bool compare(const char *a, const char *b)
@@ -143,5 +145,35 @@ void TestUTFConversion::testUnicodeToAscii7()
     free(out_ascii_idx);
 }
 
+void TestUTFConversion::testUnicodeLittleEndian()
+{
+    uint16_t UTF16LE_hi[4] { 0xFFFE, 0x4800, 0x4900, 0x2100 }; // UTF16-LE "HI!"
+    GooString GooUTF16LE(reinterpret_cast<const char *>(UTF16LE_hi), 4 * 2);
+
+    uint16_t UTF16BE_hi[4] { 0xFEFF, 0x0048, 0x0049, 0x0021 }; // UTF16-BE "HI!"
+    GooString GooUTF16BE(reinterpret_cast<const char *>(UTF16BE_hi), 4 * 2);
+
+    // Let's assert both GooString's are different
+    Q_ASSERT(GooUTF16LE.cmp(&GooUTF16BE) != 0);
+
+    Unicode *UCS4fromLE, *UCS4fromBE;
+    const int len1 = TextStringToUCS4(&GooUTF16LE, &UCS4fromLE);
+    const int len2 = TextStringToUCS4(&GooUTF16BE, &UCS4fromBE);
+
+    // 3 as TextStringToUCS4() removes the two leading Byte Order Mark (BOM) code points
+    Q_ASSERT(len1 == len2);
+    Q_ASSERT(len1 == 3);
+
+    // Check that now after conversion, UCS4fromLE and UCS4fromBE are now the same
+    for (int i = 0; i < len1; i++) {
+        Q_ASSERT(UCS4fromLE[i] == UCS4fromBE[i]);
+    }
+
+    // Do some final verifications, checking the strings to be "HI!"
+    QVERIFY(*UCS4fromLE == *UCS4fromBE);
+    QVERIFY(compare(UCS4fromLE, "HI!", 3));
+    QVERIFY(compare(UCS4fromBE, "HI!", 3));
+}
+
 QTEST_GUILESS_MAIN(TestUTFConversion)
 #include "check_utf_conversion.moc"