我们正尝试使用以下C＃代码将JSON转换为XML：
Object httpConn = Dts.Connections["HTTP"].AcquireConnection(null);
HttpClientConnection myConnection = new HttpClientConnection(httpConn);
myConnection.ServerURL = string.Format(("http://xxxx.com/jjjj"),"userid","password");
byte[] webdata = myConnection.DownloadData();
String result_data = Convert.ToBase64String(webdata);
XmlDocument xd = new XmlDocument();
XmlDictionaryReader xr = JsonReaderWriterFactory.CreateJsonReader(webdata, XmlDictionaryReaderQuotas.Max);
xr.Read();
xd.LoadXml(xr.ReadOuterXml());
xd.Save("\\Server\\ZZZZ\\Downloads\\Data.xml");
示例json是：
[
{
"id" : 21953,
"mainReqIdentity" : "xxxx",
"itemName" : "xxxx",
"kanbanPhase" : "xxxx",
"kanbanStatus" : "xxxx",
"backlogItemType" : "xxxx",
"identityDomain" : "xxxx",
"fromDatetime" : "2016-08-05 17:52:34",
"teams" : [],
"releases" : [{
"id" : 1229,
"release_name" : "xxxx",
"release_connection_type" : "xxxx"
}
],
"fpReleases" : [],
"sources" : [{
"sourceName" : "xxxx",
"sourceRecordUrl" : "xxxx",
"sourceRecordIdentity" : "xxxx"
}
],
"productNumbers" : [],
"tags" : [],
"productComponents" : [],
"ranPlatforms" : [],
"subReleases" : [],
"requirementAreaId" : "xxxx",
"requirementArea" : "xxxx",
"toBeHandledAtxxxx" : "xxxx"
}, {
"id" : 22014,
"mainReqIdentity" : "xxxx",
"itemName" : "xxxx",
"kanbanPhase" : "xxxx",
"kanbanStatus" : "xxxx",
"backlogItemType" : "xxxx",
"identityDomain" : "xxxx",
"fromDatetime" : "2016-08-05 17:52:34",
"teams" : [],
"releases" : [{
"id" : "xxxx",
"release_name" : "xxxx",
"release_connection_type" : "xxxx"
}
],
"fpReleases" : [],
"sources" : [{
"sourceName" : "xxxx",
"sourceRecordUrl" : "xxxx",
"sourceRecordIdentity" : "xxxx"
}
],
"productNumbers" : [],
"tags" : [],
"productComponents" : [],
"ranPlatforms" : [],
"subReleases" : [],
"requirementAreaId" : "xxxx",
"requirementArea" : "xxxx",
"f0Date" : "2015-10-01",
"f1Date" : "2015-10-01",
"f2Date" : "2016-02-01",
"f4Date" : "2016-03-31",
"fgDate" : "2016-04-29",
"toBeHandledAtxxxx" : "xxxx"
}
]
转换后，XML看起来像：
<root type="array">
<id type="number">21286</id>
<mainReqIdentity type="string">xxxxxx</mainReqIdentity>
<itemName type="string">xxxxxx</itemName>
<kanbanPhase type="string">xxxxxx</kanbanPhase>
<kanbanStatus type="string">xxxxxx</kanbanStatus>
<kanbanNote type="string">xxxxxx</kanbanNote>
<backlogItemType type="string">xxxxxx</backlogItemType>
<identityDomain type="string">xxxxxx</identityDomain>
<fromDatetime type="string">2016-08-23 17:01:52</fromDatetime>
<teams type="array">
<item type="object">
<team_name type="string">xxxxxx</team_name>
<preliminary type="boolean">xxxxxx</preliminary>
</item>
</teams>
<releases type="array">
<item type="object">
<id type="number">xxxxxx</id>
<release_name type="string">xxxxxx</release_name>
<release_connection_type type="string">xxxxxx</release_connection_type>
</item>
</releases>
<fpReleases type="array">
</fpReleases>
<sources type="array">
<item type="object">
<sourceName type="string">xxxxxx</sourceName>
<sourceRecordUrl type="string">xxxxxx</sourceRecordUrl>
</item>
</sources>
<productNumbers type="array">
</productNumbers>
<tags type="array">
</tags>
<productComponents type="array">
</productComponents>
<ranPlatforms type="array">
</ranPlatforms>
<subReleases type="array">
</subReleases>
<requirementAreaId type="number">xxxxxx</requirementAreaId>
<requirementArea type="string">xxxxxx</requirementArea>
<itemContact type="string">xxxxxx</itemContact>
<toBeHandledAtxxx type="string">xxxxxx</toBeHandledAtxxx>
</item>
<item type="object">
<id type="number">xxxxxx</id>
<mainReqIdentity type="string">xxxxxx</mainReqIdentity>
<itemName type="string">xxxxxx</itemName>
<kanbanPhase type="string">xxxxxx</kanbanPhase>
<kanbanStatus type="string">xxxxxx</kanbanStatus>
<kanbanNote type="string">xxxxxx</kanbanNote>
<backlogItemType type="string">xxxxxx</backlogItemType>
<identityDomain type="string">xxxxxx</identityDomain>
<fromDatetime type="string">2016-08-23 17:01:52</fromDatetime>
<teams type="array">
<item type="object">
<team_name type="string">xxxxxx</team_name>
<preliminary type="boolean">xxxxxx</preliminary>
</item>
</teams>
<releases type="array">
<item type="object">
<id type="number">xxxxxx</id>
<release_name type="string">xxxxxx</release_name>
<release_connection_type type="string">xxxxxx</release_connection_type>
</item>
</releases>
<fpReleases type="array">
</fpReleases>
<sources type="array">
<item type="object">
<sourceName type="string">xxxxxx</sourceName>
<sourceRecordUrl type="string">xxxxxx</sourceRecordUrl>
</item>
</sources>
<productNumbers type="array">
</productNumbers>
<tags type="array">
</tags>
<productComponents type="array">
</productComponents>
<ranPlatforms type="array">
</ranPlatforms>
<subReleases type="array">
</subReleases>
<requirementAreaId type="number">xxxxxx</requirementAreaId>
<requirementArea type="string">xxxxxx</requirementArea>
<oaResultReference type="string">xxxxxx</oaResultReference>
<itemContact type="string">xxxxxx</itemContact>
<f0Date type="string">2014-10-17</f0Date>
<f1Date type="string">2015-01-16</f1Date>
<f2Date type="string">2015-02-13</f2Date>
<f4Date type="string">2015-06-12</f4Date>
<faDate type="string">2015-06-12</faDate>
<fgDate type="string">2015-06-12</fgDate>
<toBeHandledAtxxx type="string">xxxxxx</toBeHandledAtxxx>
</item>
</root>
如果您在每个节点之前观察，则会创建 项类型 。我的问题是如何避免从C＃类创建它们。
答案 0 :(得分：2)
JsonReaderWriterFactory中描述了"type"使用的XML和JSON之间的对应关系。特别是：
由于XML不具有数组原语的概念，因此JSON数组被映射到两个XML级别，其中内部元素的[本地名称]将是＆＃34; item＆＃34;。
将属性XmlDocument添加到每个元素。如文档中所述，此属性用于在映射的XML中保留JSON类型（字符串，数字，布尔值，对象，数组或null）。
如果此映射不能满足您的需求，您可以在存储XML之前使用某些适当的API（例如Mapping Between JSON and XML或XSLT transformation修改）自定义生成的XML。
例如，LINQ to XML，取代.Net 3.5中的XDocument xd;
using (var xr = JsonReaderWriterFactory.CreateJsonReader(webdata, XmlDictionaryReaderQuotas.Max))
{
xd = XDocument.Load(xr);
}
API的API，允许在内存中轻松修改XML。首先，将您的JSON加载到LINQ to XML，如下所示：
foreach (var arrayElement in xd.Root.Descendants().Where(e => (string)e.Attribute("type") == "array").ToList())
{
// Get all child nodes of the array container node.
var nodes = arrayElement.Nodes().ToList();
bool anyChildren = false;
// Change names of child elements from <item> to the name of the container node, <releases> or whatever.
foreach (var element in nodes.OfType<XElement>())
{
anyChildren = true;
element.Name = arrayElement.Name;
}
if (anyChildren)
{
// Remove all its child nodes.
nodes.Remove();
// Add formerly child nodes right after the container node.
arrayElement.AddAfterSelf(nodes);
// Remove the container node itself.
arrayElement.Remove();
}
}
现在，如果你想＆＃34; un-nest＆＃34;来自其外部容器元素的数组项，您可以按如下方式执行 - 除了根元素的情况。如果XML文档的XDocument对应于JSON数组，则其项目不能冒出来，因为这样做会违反每个XML文档必须具有root element的规则。话虽如此，以下应该有效：
"type"（对于嵌套的JSON数组，可能需要进一步自定义此代码。）
接下来，如果您要删除foreach (var element in xd.Descendants().Where(e => e.Attribute("type") != null))
element.Attributes("type").Remove();
属性，可以使用以下代码：
xd.Save("\\Server\\ZZZZ\\Downloads\\Data.xml");
最后，要保存文档，请执行以下操作：
<root>
<item>
<id>21953</id>
<mainReqIdentity>xxxx</mainReqIdentity>
<itemName>xxxx</itemName>
<kanbanPhase>xxxx</kanbanPhase>
<kanbanStatus>xxxx</kanbanStatus>
<backlogItemType>xxxx</backlogItemType>
<identityDomain>xxxx</identityDomain>
<fromDatetime>2016-08-05 17:52:34</fromDatetime>
<teams></teams>
<releases>
<id>1229</id>
<release_name>xxxx</release_name>
<release_connection_type>xxxx</release_connection_type>
</releases>
<fpReleases></fpReleases>
<sources>
<sourceName>xxxx</sourceName>
<sourceRecordUrl>xxxx</sourceRecordUrl>
<sourceRecordIdentity>xxxx</sourceRecordIdentity>
</sources>
<productNumbers></productNumbers>
<tags></tags>
<productComponents></productComponents>
<ranPlatforms></ranPlatforms>
<subReleases></subReleases>
<requirementAreaId>xxxx</requirementAreaId>
<requirementArea>xxxx</requirementArea>
<toBeHandledAtxxxx>xxxx</toBeHandledAtxxxx>
</item>
<item>
<id>22014</id>
<mainReqIdentity>xxxx</mainReqIdentity>
<itemName>xxxx</itemName>
<kanbanPhase>xxxx</kanbanPhase>
<kanbanStatus>xxxx</kanbanStatus>
<backlogItemType>xxxx</backlogItemType>
<identityDomain>xxxx</identityDomain>
<fromDatetime>2016-08-05 17:52:34</fromDatetime>
<teams></teams>
<releases>
<id>xxxx</id>
<release_name>xxxx</release_name>
<release_connection_type>xxxx</release_connection_type>
</releases>
<fpReleases></fpReleases>
<sources>
<sourceName>xxxx</sourceName>
<sourceRecordUrl>xxxx</sourceRecordUrl>
<sourceRecordIdentity>xxxx</sourceRecordIdentity>
</sources>
<productNumbers></productNumbers>
<tags></tags>
<productComponents></productComponents>
<ranPlatforms></ranPlatforms>
<subReleases></subReleases>
<requirementAreaId>xxxx</requirementAreaId>
<requirementArea>xxxx</requirementArea>
<f0Date>2015-10-01</f0Date>
<f1Date>2015-10-01</f1Date>
<f2Date>2016-02-01</f2Date>
<f4Date>2016-03-31</f4Date>
<fgDate>2016-04-29</fgDate>
<toBeHandledAtxxxx>xxxx</toBeHandledAtxxxx>
</item>
</root>
链接这两个转换的结果是：
1 import gensim
2 import nltk
3 from gensim.models import word2vec
4 from nltk.corpus import stopwords
5 from nltk.corpus import wordnet
6 import logging
7 import re
8 import itertools
9 import glob
10 from collections import defaultdict
11 import csv
12 from nltk.stem.wordnet import WordNetLemmatizer
13 import os
14 import os.path
15
16 stopwords = nltk.corpus.stopwords.words('english')
17
18 path = "/home/mona/computer_vision/imgur/tiny_comments/*.txt"
19 files = glob.glob(path)
20 csv_file_complete = open("tiny_graph.csv", "wb")
21 stat_csv_file = open("tiny_stat.csv", "r")
22 csv_reader = csv.reader(stat_csv_file)
23 lemmatizer = WordNetLemmatizer()
24 list_of_rows = []
25
26 with open('swear_words_uniq.txt') as swear_words_file:
27 swear_words = swear_words_file.read()
28 swear_words = re.sub("[^a-zA-Z]", ' ', swear_words).lower().split()
29 swear_words_file.close()
30
31
32 for file1, file2 in itertools.combinations(files, 2):
33 with open(file1) as f1:
34 f1_text = f1.read()
35 f1_text = re.sub(r'^https?:\/\/.*[\r\n]*', '',f1_text, flags=re.MULTILINE)
36 f1_words = re.sub("[^a-zA-Z]", ' ', f1_text).lower().split()
37 lemmatized_f1_words = [str(lemmatizer.lemmatize(w, wordnet.VERB)) for w in f1_words if w not in stopwords]
38 cleaned_f1_words = [w for w in lemmatized_f1_words if w not in swear_words and len(w) > 2]
39 f1.close()
40 with open(file2) as f2:
41 f2_text = f2.read()
42 f2_words = re.sub("[^a-zA-Z]", ' ', f2_text).lower().split()
43 lemmatized_f2_words = [str(lemmatizer.lemmatize(w, wordnet.VERB)) for w in f2_words if w not in stopwords]
44 cleaned_f2_words = [w for w in lemmatized_f2_words if w not in swear_words and len(w) > 2]
45 f2.close()
46 f1_head, f1_tail = os.path.split(file1)
47 f2_head, f2_tail = os.path.split(file2)
48 tail_to_numbers = {ftail: fnum for fnum, ftail in csv_reader}
49 stat_csv_file.seek(0)
50 try:
51 file1_file_number = tail_to_numbers[f1_tail]
52 file2_file_number = tail_to_numbers[f2_tail]
53 except KeyError as e:
54 print(e)
55 continue
56 else:
57 row_complete = [file1_file_number.strip(), file2_file_number.strip()]
58 list_of_rows.append(row_complete)
59 print(len(list_of_rows))
60 a_complete = csv.writer(csv_file_complete, delimiter=',')
61 for row in list_of_rows:
62 print(row)
63 a_complete.writerow(row)
64
65 csv_file_complete.close()