Question

我有一些XML，我试图用C中的Expat处理.XML可以用Java解析，所以我没有理由相信它是错误的。此外，我所拥有的C代码将解析我手动插入的字符串文字 - 但它无法解析我的XML文件。

这是代码（我添加的内容 - 如果上帝希望我们使用调试器，他就不会给我们printf）：

static void XMLCALL
starthandler(void *data, const XML_Char *name, const XML_Char **attr)
{
int i;
if (strcmp(name, "file") == 0) {
    for (i = 0; attr[i]; i += 2) {
        if (strcmp(attr[i], "path") == 0) {
            printf("File is at %s\n", attr[i + 1]);
        }
    }
}
}       

int main(int argc, char *argv[])
{
FILE* inXML;
ssize_t read;
char* line;
size_t len = 0;

XML_Parser p_ctrl = XML_ParserCreate("UTF-8");
if (!p_ctrl) {
    fprintf(stderr, "Could not create parser\n");
    exit(-1);
}

XML_SetStartElementHandler(p_ctrl, starthandler);
inXML = fopen(argv[1], "r");
if (inXML == NULL) {
    fprintf(stderr, "Could not open %s\n", argv[1]);
    XML_ParserFree(p_ctrl);
    exit(-1);
}

while ((read = getline(&line, &len, inXML)) != -1) {
    printf("Line is %s", line);
    enum XML_Status status = XML_Parse(p_ctrl, line, len, 0);
    if (status == 0) {
        enum XML_Error errcde = XML_GetErrorCode(p_ctrl);
        printf("ERROR: %s\n", XML_ErrorString(errcde));
        printf("Error at column number %lu\n",    XML_GetCurrentColumnNumber(p_ctrl));
        printf("Error at line number %lu\n", XML_GetCurrentLineNumber(p_ctrl));
    }
    free(line);
    line = NULL;
    len = 0;
}

XML_ParserFree(p_ctrl);
fclose(inXML);
return 0;
}

这是我试图解析的XML文件：

<?xml version="1.0" encoding="UTF-8" standalone="no"?>
<!DOCTYPE threadrecordml [
<!ELEMENT threadrecordml (file)*>
<!ATTLIST threadrecordml version CDATA #FIXED "0.1">
<!ATTLIST threadrecordml xmlns CDATA #FIXED "http://cartesianproduct.wordpress.com">
<!ELEMENT file EMPTY>
<!ATTLIST file thread CDATA #REQUIRED>
<!ATTLIST file path CDATA #REQUIRED>
]>
<threadrecordml xmlns="http://cartesianproduct.wordpress.com">
<file thread="1" path="tester_1.xml" />
<file thread="3" path="tester_3.xml" />
<file thread="2" path="tester_2.xml" />
<file thread="4" path="tester_4.xml" />
<file thread="5" path="tester_5.xml" />
<file thread="6" path="tester_6.xml" />
<file thread="7" path="tester_7.xml" />
<file thread="8" path="tester_8.xml" />
<file thread="9" path="tester_9.xml" />
<file thread="10" path="tester_10.xml" />
<file thread="11" path="tester_11.xml" />
<file thread="12" path="tester_12.xml" />
<file thread="13" path="tester_13.xml" />
<file thread="14" path="tester_14.xml" />
<file thread="15" path="tester_15.xml" />
<file thread="16" path="tester_16.xml" />
<file thread="17" path="tester_17.xml" />
<file thread="18" path="tester_18.xml" />
</threadrecordml>

这是输出样本......

adrianm@imola:/n/staffstore/adrianm/optGenC$ ./optgenc ../tester_control.xml 
Line is <?xml version="1.0" encoding="UTF-8" standalone="no"?>
ERROR: not well-formed (invalid token)
Error at column number 0
Error at line number 2
Line is <!DOCTYPE threadrecordml [
ERROR: not well-formed (invalid token)
Error at column number 0
Error at line number 3
Line is <!ELEMENT threadrecordml (file)*>
ERROR: not well-formed (invalid token)
Error at column number 0
Error at line number 4
Line is <!ATTLIST threadrecordml version CDATA #FIXED "0.1">
ERROR: not well-formed (invalid token)
Error at column number 0

（适用于所有行）

如果我“欺骗”并在阅读后添加此行...

line = "<file thread=\"1\" path=\"tester.xml\" />";

该行将被解析（当然代码因其他原因而中断）。

因此，从磁盘文件中读取似乎会出现一些错误...这可能被读为16位吗？但是将解析器的编码更改为NULL或UTF-16似乎没有任何区别。

有人可以提供解释吗？（如果它有任何区别我在64位OSX和Linux机器上运行此代码并遇到同样的问题）

Answer 1

答案是getline（...）在换行符之后添加一个空字符，然后将其传递给解析器，但当然它不是有效的XML，因此它会导致失败 - 因为它在换行符之后，这被记录为第2行，依此类推。

这样做可以解决问题：

do {
    len = fread(data, 1, sizeof(data), inXML);
    done = len < sizeof(data);

    if (XML_Parse(p_ctrl, data, len, 0) == 0) {
        enum XML_Error errcde = XML_GetErrorCode(p_ctrl);
        printf("ERROR: %s\n", XML_ErrorString(errcde));
        printf("Error at column number %lu\n", XML_GetCurrentColumnNumber(p_ctrl));
        printf("Error at line number %lu\n", XML_GetCurrentLineNumber(p_ctrl));
    }
} while(!done);

Expat（C） - （几乎）每行的“无效令牌”

1 个答案: