c - Expat (C) - "invalid token"(几乎)每一行

Question

我有一些 XML 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格式错误的。此外，我拥有的 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(我添加了一些东西——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>

这是输出示例...

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

(对于所有行)

如果我“作弊”并在读取后添加这一行...

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

该行将被解析(代码当然会因其他原因中断)。

所以在从磁盘文件读取时似乎发生了一些损坏...这可能是作为 16 位读取的吗？但是将解析器的编码更改为 NULL 或 UTF-16 似乎没有任何区别。

谁能解释一下？ (如果有什么不同的话，我已经在 64 位 OSX 和 Linux 机器上运行了这段代码并且遇到了同样的问题)

Answer 1

答案是 getline(...) 在换行符后添加一个空字符，然后将其传递给解析器，但当然它不是有效的 XML，所以它会导致失败 - 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);