libmxml数据结构(源码分析)

  libmxml是一个开源、小巧的C语言xml库。这里简单分析一下它是用什么样的数据结构来保存分析过的xml文档。

  mxml关键的结构体mxml_node_t是这样的实现的:

struct mxml_node_s            /**** An XML node. @private@ ****/
{
  mxml_type_t        type;        /* Node type */
  struct mxml_node_s    *next;        /* Next node under same parent */
  struct mxml_node_s    *prev;        /* Previous node under same parent */
  struct mxml_node_s    *parent;    /* Parent node */
  struct mxml_node_s    *child;        /* First child node */
  struct mxml_node_s    *last_child;    /* Last child node */
  mxml_value_t        value;        /* Node value */
  int            ref_count;    /* Use count */
  void            *user_data;    /* User data */
};

typedef struct mxml_node_s mxml_node_t;    /**** An XML node. ****/

  

   它使用左孩子右兄弟的树形结构来描述xml报文:即下层节点登记在child链表,兄弟节点登记在next链表。 如果某个节点下面有N个子节点,则child指向第一个子节点,该子节点的next指向下一个同父节点的子节点。  比较特殊的是,mxml把xml节点值也认为是一个子节点。例如<group>value</group>, 其中value(type是MXML_OPAQUE)是一个独立的子节点,挂载在group节点(type是MXML_ELEMENT)下面。  另外,空白符(空格,回车换行,制表符)和注释,虽然对xml报文无实质意义,但mxml还是把它们做为一个节点存储起来。

  由于mxml只是使用简单的链表存储xml元素,所以元素节点个数比较多时,mxml查找元素效率是比较低的。所以libmxml提供了一个索引查找的函数,它需要先遍历xml元素树,生成一个排序过的数组,加快查找速度。

   为了方便大家理解,我写了一个函数打印xml结构体。

 

void printNode(mxml_node_t *node, int nNodeSn, int level)
{
    static int currNodeSn = 0;
    if (node == NULL)
    {
        return;
    }

    ++currNodeSn; //每遇到一个新节点 则将节点序号递增,做为本节点序号
    printf("[%- 3d -> %- 3d] ", currNodeSn, nNodeSn);

    switch (node->type)
    {
    case MXML_ELEMENT:
        {
            int i;
            printf("level %d MXML_ELEMENT [%s]", level, node->value.element.name);
            for (i = 0; i < node->value.element.num_attrs; ++i)
            {
                printf(" %s=%s", node->value.element.attrs[i].name, node->value.element.attrs[i].value);
            }
            printf("\n");
        }
        break;
    case MXML_INTEGER:
        printf("level %d MXML_INTEGER %d\n", level, node->value.integer);
        break;
    case MXML_OPAQUE:
        printf("level %d MXML_OPAQUE [%s]\n", level, node->value.opaque);
        break;
    case MXML_REAL:
        printf("level %d MXML_REAL %lf\n", level, node->value.real);
        break;
    case MXML_TEXT:
        printf("level %d MXML_TEXT [%s]\n", level, node->value.text.string);
        break;
    case MXML_CUSTOM:
        printf("level %d MXML_CUSTOM\n", level);
        break;
    default:
        printf("unknown node type %d\n", node->type);
    }

    //深度优先遍历
    if (node->child)
    {
        //访问子节点时把本节点序号做为父节点序号 层级加1
        printNode(node->child, currNodeSn, level + 1);
    }

    if (node->next)
    {
        //访问兄弟节点,直接传父节点序号即可 层级也不用加1
        printNode(node->next, nNodeSn, level);
    }
}

  运行示例如下:

  xml源如下:

<?xml version="1.0" encoding="GBK" ?>
<group>
    <option>122334 我们
        <string>我们</string>45677
        <keyword type="opaque">InputSlot</keyword>
        <default type="opaque">Auto</default>
        <text>Media Source</text>
        <order type="real">10.000000</order>
        <choice>
            <keyword type="opaque">Auto</keyword>
            <text>Auto Tray Selection</text>
            <code type="opaque" />
        </choice>
        <choice>
            <keyword type="opaque">Upper</keyword>
            <text>Tray 1</text>
            <code type="opaque">&lt;&lt;/MediaPosition 0&gt;&gt;setpagedevice</code>
        </choice>
        <choice>
            <keyword type="opaque">Lower</keyword>
            <text>Tray 2</text>
            <code type="opaque">&lt;&lt;/MediaPosition 1&gt;&gt;setpagedevice</code>
        </choice>
    </option> 我 12334545 050504550
    <integer>123</integer>
    <string>Now is the time for all good men to come to the aid of their
country.</string>
    <!-- this is a comment -->
    <![CDATA[this is CDATA 0123456789ABCDEF]]>
</group>

  用我这个printNode分析结果如下:

说明:[ 1  ->  0 ],代表本节点序号是1,其父节点序号是0,level 0代表本节点是最顶层节点。

[ 1  ->  0 ] level 0 MXML_ELEMENT [?xml version="1.0" encoding="GBK" ?]
[ 2  ->  1 ] level 1 MXML_OPAQUE [
]
[ 3  ->  1 ] level 1 MXML_ELEMENT [group]
[ 4  ->  3 ] level 2 MXML_OPAQUE [
        ]
[ 5  ->  3 ] level 2 MXML_ELEMENT [option]
[ 6  ->  5 ] level 3 MXML_OPAQUE [122334 我们
                ]
[ 7  ->  5 ] level 3 MXML_ELEMENT [string]
[ 8  ->  7 ] level 4 MXML_OPAQUE [我们]
[ 9  ->  5 ] level 3 MXML_OPAQUE [45677
                ]
[ 10 ->  5 ] level 3 MXML_ELEMENT [keyword] type=opaque
[ 11 ->  10] level 4 MXML_OPAQUE [InputSlot]
[ 12 ->  5 ] level 3 MXML_OPAQUE [
                ]
[ 13 ->  5 ] level 3 MXML_ELEMENT [default] type=opaque
[ 14 ->  13] level 4 MXML_OPAQUE [Auto]
[ 15 ->  5 ] level 3 MXML_OPAQUE [
                ]
[ 16 ->  5 ] level 3 MXML_ELEMENT [text]
[ 17 ->  16] level 4 MXML_OPAQUE [Media Source]
[ 18 ->  5 ] level 3 MXML_OPAQUE [
                ]
[ 19 ->  5 ] level 3 MXML_ELEMENT [order] type=real
[ 20 ->  19] level 4 MXML_OPAQUE [10.000000]
[ 21 ->  5 ] level 3 MXML_OPAQUE [
                ]
[ 22 ->  5 ] level 3 MXML_ELEMENT [choice]
[ 23 ->  22] level 4 MXML_OPAQUE [
                        ]
[ 24 ->  22] level 4 MXML_ELEMENT [keyword] type=opaque
[ 25 ->  24] level 5 MXML_OPAQUE [Auto]
[ 26 ->  22] level 4 MXML_OPAQUE [
                        ]
[ 27 ->  22] level 4 MXML_ELEMENT [text]
[ 28 ->  27] level 5 MXML_OPAQUE [Auto Tray Selection]
[ 29 ->  22] level 4 MXML_OPAQUE [
                        ]
[ 30 ->  22] level 4 MXML_ELEMENT [code] type=opaque
[ 31 ->  22] level 4 MXML_OPAQUE [
                ]
[ 32 ->  5 ] level 3 MXML_OPAQUE [
                ]
[ 33 ->  5 ] level 3 MXML_ELEMENT [choice]
[ 34 ->  33] level 4 MXML_OPAQUE [
                        ]
[ 35 ->  33] level 4 MXML_ELEMENT [keyword] type=opaque
[ 36 ->  35] level 5 MXML_OPAQUE [Upper]
[ 37 ->  33] level 4 MXML_OPAQUE [
                        ]
[ 38 ->  33] level 4 MXML_ELEMENT [text]
[ 39 ->  38] level 5 MXML_OPAQUE [Tray 1]
[ 40 ->  33] level 4 MXML_OPAQUE [
                        ]
[ 41 ->  33] level 4 MXML_ELEMENT [code] type=opaque
[ 42 ->  41] level 5 MXML_OPAQUE [<</MediaPosition 0>>setpagedevice]
[ 43 ->  33] level 4 MXML_OPAQUE [
                ]
[ 44 ->  5 ] level 3 MXML_OPAQUE [
                ]
[ 45 ->  5 ] level 3 MXML_ELEMENT [choice]
[ 46 ->  45] level 4 MXML_OPAQUE [
                        ]
[ 47 ->  45] level 4 MXML_ELEMENT [keyword] type=opaque
[ 48 ->  47] level 5 MXML_OPAQUE [Lower]
[ 49 ->  45] level 4 MXML_OPAQUE [
                        ]
[ 50 ->  45] level 4 MXML_ELEMENT [text]
[ 51 ->  50] level 5 MXML_OPAQUE [Tray 2]
[ 52 ->  45] level 4 MXML_OPAQUE [
                        ]
[ 53 ->  45] level 4 MXML_ELEMENT [code] type=opaque
[ 54 ->  53] level 5 MXML_OPAQUE [<</MediaPosition 1>>setpagedevice]
[ 55 ->  45] level 4 MXML_OPAQUE [
                ]
[ 56 ->  5 ] level 3 MXML_OPAQUE [
        ]
[ 57 ->  3 ] level 2 MXML_OPAQUE [ 我12334545 050504550
        ]
[ 58 ->  3 ] level 2 MXML_ELEMENT [integer]
[ 59 ->  58] level 3 MXML_OPAQUE [123]
[ 60 ->  3 ] level 2 MXML_OPAQUE [
        ]
[ 61 ->  3 ] level 2 MXML_ELEMENT [string]
[ 62 ->  61] level 3 MXML_OPAQUE [Now is the time for all good men to come to the aid of their
country.]
[ 63 ->  3 ] level 2 MXML_OPAQUE [
        ]
[ 64 ->  3 ] level 2 MXML_ELEMENT [!-- this is a comment --]
[ 65 ->  3 ] level 2 MXML_OPAQUE [
        ]
[ 66 ->  3 ] level 2 MXML_ELEMENT [![CDATA[this is CDATA 0123456789ABCDEF]]]
[ 67 ->  3 ] level 2 MXML_OPAQUE [
]

 

   

转载于:https://www.cnblogs.com/kingstarer/p/10659709.html

  • 0
    点赞
  • 0
    收藏
    觉得还不错? 一键收藏
  • 0
    评论
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值