Expat（C） - 「無效令牌」（幾乎）每行

Question

我有一些XML我想用C中的Expat進行處理.XML可以用Java解析，所以我沒有理由相信它是畸形的。此外，我所擁有的C代碼將解析我手動插入的字符串 - 但它無法解析我的XML文件。

這是代碼（用的東西，我已經添加了 - 如果上帝想讓我們用調試器，他不會給我們的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; 
} 

這是我試圖解析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> 

這是輸出的樣品...

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 

（對於所有的行）

如果我「欺騙」，並在讀取後添加此行...

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

該生產線將被解析（當然的代碼，然後打破其他原因）。

因此，從磁盤文件中讀取似乎會發生一些變化......這是否被讀爲16位？但將解析器的編碼更改爲NULL或UTF-16似乎沒有任何區別。

任何人都可以提供解釋嗎？ （如果它有什麼區別，我已經在64位OSX和Linux機器上運行這個代碼，並且有同樣的問題）

Answer 1

答案是getline（...）在換行符後面添加一個空字符，這是然後傳遞給解析器，但它當然不是有效的XML，因此導致失敗 - 並且在換行符後面，這被記錄爲在第2行等。

這樣做解決了這個問題：

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);