Test long UTF-16 CDATA (more than internal buffer size)

diff --git a/expat/tests/chardata.h b/expat/tests/chardata.h
index e8dc4ce22c42a8e994c9265c1bc412dbabde6885..0db4b999b58bb9e4c9474faea1da8c3e36dbdf44 100644 (file)
--- a/expat/tests/chardata.h
+++ b/expat/tests/chardata.h
@@ -18,7 +18,7 @@ extern "C" {
 
 typedef struct {
     int count;                          /* # of chars, < 0 if not set */
-    XML_Char data[1024];
+    XML_Char data[2048];
 } CharData;
 
 

diff --git a/expat/tests/runtests.c b/expat/tests/runtests.c
index 53466cc3a58e41e40654e68e654391db49f9e744..22a51ad281ef20bb39a63b868e0df16475cdd4c4 100644 (file)
--- a/expat/tests/runtests.c
+++ b/expat/tests/runtests.c
@@ -1685,6 +1685,79 @@ START_TEST(test_good_cdata_utf16)
 }
 END_TEST
 
+/* Test UTF16 conversion of a long cdata string */
+
+/* 16 characters: handy macro to reduce visual clutter */
+#define A_TO_P_IN_UTF16 "\0A\0B\0C\0D\0E\0F\0G\0H\0I\0J\0K\0L\0M\0N\0O\0P"
+
+START_TEST(test_long_cdata_utf16)
+{
+    /* Test data is:
+     * <?xlm version='1.0' encoding='utf-16'?>
+     * <a><![CDATA[
+     * ABCDEFGHIJKLMNOP
+     * ]]></a>
+     */
+    const char text[] =
+        "\0<\0?\0x\0m\0l\0 "
+        "\0v\0e\0r\0s\0i\0o\0n\0=\0'\0\x31\0.\0\x30\0'\0 "
+        "\0e\0n\0c\0o\0d\0i\0n\0g\0=\0'\0u\0t\0f\0-\0\x31\0\x36\0'\0?\0>"
+        "\0<\0a\0>\0<\0!\0[\0C\0D\0A\0T\0A\0["
+        /* 64 characters per line */
+        A_TO_P_IN_UTF16  A_TO_P_IN_UTF16  A_TO_P_IN_UTF16  A_TO_P_IN_UTF16
+        A_TO_P_IN_UTF16  A_TO_P_IN_UTF16  A_TO_P_IN_UTF16  A_TO_P_IN_UTF16
+        A_TO_P_IN_UTF16  A_TO_P_IN_UTF16  A_TO_P_IN_UTF16  A_TO_P_IN_UTF16
+        A_TO_P_IN_UTF16  A_TO_P_IN_UTF16  A_TO_P_IN_UTF16  A_TO_P_IN_UTF16
+        A_TO_P_IN_UTF16  A_TO_P_IN_UTF16  A_TO_P_IN_UTF16  A_TO_P_IN_UTF16
+        A_TO_P_IN_UTF16  A_TO_P_IN_UTF16  A_TO_P_IN_UTF16  A_TO_P_IN_UTF16
+        A_TO_P_IN_UTF16  A_TO_P_IN_UTF16  A_TO_P_IN_UTF16  A_TO_P_IN_UTF16
+        A_TO_P_IN_UTF16  A_TO_P_IN_UTF16  A_TO_P_IN_UTF16  A_TO_P_IN_UTF16
+        A_TO_P_IN_UTF16  A_TO_P_IN_UTF16  A_TO_P_IN_UTF16  A_TO_P_IN_UTF16
+        A_TO_P_IN_UTF16  A_TO_P_IN_UTF16  A_TO_P_IN_UTF16  A_TO_P_IN_UTF16
+        A_TO_P_IN_UTF16  A_TO_P_IN_UTF16  A_TO_P_IN_UTF16  A_TO_P_IN_UTF16
+        A_TO_P_IN_UTF16  A_TO_P_IN_UTF16  A_TO_P_IN_UTF16  A_TO_P_IN_UTF16
+        A_TO_P_IN_UTF16  A_TO_P_IN_UTF16  A_TO_P_IN_UTF16  A_TO_P_IN_UTF16
+        A_TO_P_IN_UTF16  A_TO_P_IN_UTF16  A_TO_P_IN_UTF16  A_TO_P_IN_UTF16
+        A_TO_P_IN_UTF16  A_TO_P_IN_UTF16  A_TO_P_IN_UTF16  A_TO_P_IN_UTF16
+        A_TO_P_IN_UTF16  A_TO_P_IN_UTF16  A_TO_P_IN_UTF16  A_TO_P_IN_UTF16
+        A_TO_P_IN_UTF16
+        "\0]\0]\0>\0<\0/\0a\0>";
+    const char *expected =
+        "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+        "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+        "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+        "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+        "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+        "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+        "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+        "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+        "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+        "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+        "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+        "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+        "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+        "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+        "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+        "ABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOPABCDEFGHIJKLMNOP"
+        "ABCDEFGHIJKLMNOP";
+    CharData storage;
+    void *buffer;
+
+    CharData_Init(&storage);
+    XML_SetUserData(parser, &storage);
+    XML_SetCharacterDataHandler(parser, accumulate_characters);
+    buffer = XML_GetBuffer(parser, sizeof(text) - 1);
+    if (buffer == NULL)
+        fail("Could not allocate parse buffer");
+    memcpy(buffer, text, sizeof(text) - 1);
+    if (XML_ParseBuffer(parser,
+                        sizeof(text) - 1,
+                        XML_TRUE) == XML_STATUS_ERROR)
+        xml_failure(parser);
+    CharData_CheckXMLChars(&storage, expected);
+}
+END_TEST
+
 START_TEST(test_bad_cdata)
 {
     struct CaseData {
@@ -5133,6 +5206,7 @@ make_suite(void)
     tcase_add_test(tc_basic, test_repeated_stop_parser_between_char_data_calls);
     tcase_add_test(tc_basic, test_good_cdata_ascii);
     tcase_add_test(tc_basic, test_good_cdata_utf16);
+    tcase_add_test(tc_basic, test_long_cdata_utf16);
     tcase_add_test(tc_basic, test_bad_cdata);
     tcase_add_test(tc_basic, test_memory_allocation);
     tcase_add_test(tc_basic, test_default_current);