问题：
我需要从这个JavaScript中自动提取所有名称属性 （分别针对供应商大型和供应商小型）
/*
Simple OpenID Plugin
http://code.google.com/p/openid-selector/
This code is licensed under the New BSD License.
*/
var providers_large = {
google : {
name : 'Google',
url : 'https://www.google.com/accounts/o8/id'
},
yahoo : {
name : 'Yahoo',
url : 'http://me.yahoo.com/'
},
aol : {
name : 'AOL',
label : 'Enter your AOL screenname.',
url : 'http://openid.aol.com/{username}'
},
myopenid : {
name : 'MyOpenID',
label : 'Enter your MyOpenID username.',
url : 'http://{username}.myopenid.com/'
},
openid : {
name : 'OpenID',
label : 'Enter your OpenID.',
url : null
}
};
var providers_small = {
livejournal : {
name : 'LiveJournal',
label : 'Enter your Livejournal username.',
url : 'http://{username}.livejournal.com/'
},
/* flickr: {
name: 'Flickr',
label: 'Enter your Flickr username.',
url: 'http://flickr.com/{username}/'
}, */
/* technorati: {
name: 'Technorati',
label: 'Enter your Technorati username.',
url: 'http://technorati.com/people/technorati/{username}/'
}, */
wordpress : {
name : 'Wordpress',
label : 'Enter your Wordpress.com username.',
url : 'http://{username}.wordpress.com/'
},
blogger : {
name : 'Blogger',
label : 'Your Blogger account',
url : 'http://{username}.blogspot.com/'
},
verisign : {
name : 'Verisign',
label : 'Your Verisign username',
url : 'http://{username}.pip.verisignlabs.com/'
},
/* vidoop: {
name: 'Vidoop',
label: 'Your Vidoop username',
url: 'http://{username}.myvidoop.com/'
}, */
/* launchpad: {
name: 'Launchpad',
label: 'Your Launchpad username',
url: 'https://launchpad.net/~{username}'
}, */
claimid : {
name : 'ClaimID',
label : 'Your ClaimID username',
url : 'http://claimid.com/{username}'
},
clickpass : {
name : 'ClickPass',
label : 'Enter your ClickPass username',
url : 'http://clickpass.com/public/{username}'
},
google_profile : {
name : 'Google Profile',
label : 'Enter your Google Profile username',
url : 'http://www.google.com/profiles/{username}'
}
};
openid.locale = 'en';
openid.sprite = 'en'; // reused in german& japan localization
openid.demo_text = 'In client demo mode. Normally would have submitted OpenID:';
openid.signin_text = 'Sign-In';
openid.image_title = 'log in with {provider}';
所以我需要： A）删除所有C-Style注释 和B）获取[providers_large，providers_small]的所有名称值（删除注释后）
到目前为止，我已经尝试使用正则表达式来删除C风格的注释（并且失败了） 和正则表达式来获取大括号（和失败的）之间的所有内容
我随后尝试将其作为JSON读取， 但这当然失败了“无效的json primitve what”
这是我使用的stackoverflow-sites 这是我到目前为止尝试的例子
using System;
using System.Collections.Generic;
using System.Linq;
using System.Text;
namespace ConsoleExperiments
{
public class Program
{
// http://stackoverflow.com/questions/2538279/strip-out-c-style-multi-line-comments
// NOT working
static string RemoveCstyleComments(string strInput)
{
string strPattern = @"/[*][\w\d\s]+[*]/";
//strPattern = @"/\*.*?\*/";
strPattern = "/\\*.*?\\*/";
string strOutput = System.Text.RegularExpressions.Regex.Replace(strInput, strPattern, string.Empty, System.Text.RegularExpressions.RegexOptions.Multiline);
Console.WriteLine(strOutput);
return strOutput;
}
// http://stackoverflow.com/questions/413071/regex-to-get-string-between-curly-braces-i-want-whats-between-the-curly-brace
// http://stackoverflow.com/questions/5337166/regular-expression-get-string-between-curly-braces
// http://stackoverflow.com/questions/1904617/regex-for-removing-curly-brackets-with-nested-curly-brackets
// http://stackoverflow.com/questions/378415/how-do-i-extract-a-string-of-text-that-lies-between-two-brackets-using-net
static string GetCurlyValues(string strInput)
{
string strPattern = "/{(.*?)}/";
strPattern = "/{([^}]*)}/";
strPattern = @"\{(\s*?.*?)*?\}";
strPattern = @"(?<=\{).*(?=\})";
strPattern = "{(.*{(.*)}.*)}";
strPattern = "{{([^}]*)}}";
strPattern = "{{({?}?[^{}])*}}";
strPattern = @"\(([^)]*)\)";
System.Text.RegularExpressions.Regex rex = new System.Text.RegularExpressions.Regex(strPattern, System.Text.RegularExpressions.RegexOptions.Multiline);
System.Text.RegularExpressions.Match mMatch = rex.Match(strInput);
foreach (System.Text.RegularExpressions.Group g in mMatch.Groups)
{
Console.WriteLine("Group: " + g.Value);
foreach (System.Text.RegularExpressions.Capture c in g.Captures)
{
Console.WriteLine("Capture: " + c.Value);
}
}
return "";
}
static void ReadFile()
{
try
{
string strFilePath = @"TestFile.txt";
if (System.IO.File.Exists(strFilePath))
{
// Create an instance of StreamReader to read from a file.
// The using statement also closes the StreamReader.
using (System.IO.StreamReader sr = new System.IO.StreamReader(strFilePath))
{
string line;
// Read and display lines from the file until the end of
// the file is reached.
while ((line = sr.ReadLine()) != null)
{
Console.WriteLine(line);
} // Whend
sr.Close();
} // End Using
} // End if (System.IO.File.Exists(strFilePath))
else
Console.WriteLine("File \"" + strFilePath + "\" does not exist.");
} // End Try
catch (Exception e)
{
// Let the user know what went wrong.
Console.WriteLine("The file could not be read:");
Console.WriteLine(e.Message);
} // End Catch
} // End Sub
public class cProvider
{
public string name = "abc";
public string label ="def";
public string url ="url";
}
public class cProviders_large
{
public List<cProvider> foo = new List<cProvider>();
}
static void Main(string[] args)
{
string strContent = System.IO.File.ReadAllText(@"D:\UserName\Downloads\openid-selector-1.3\openid-selector\js\openid-en - Kopie.js.txt");
Console.WriteLine(strContent);
//RemoveCstyleComments(strContent);
//GetCurlyValues(strContent);
System.Web.Script.Serialization.JavaScriptSerializer js = new System.Web.Script.Serialization.JavaScriptSerializer();
//object obj = js.DeserializeObject(strContent);
cProviders_large xx = new cProviders_large();
cProvider ap = new cProvider();
xx.foo.Add(ap);
xx.foo.Add(ap);
string res = js.Serialize(xx);
Console.WriteLine(res);
Console.WriteLine(Environment.NewLine);
Console.WriteLine(" --- Press any key to continue --- ");
Console.ReadKey();
} // End Sub Main
} // End Class Program
} // End namespace ConsoleExperiments
任何比我更了解正则表达式的人能为我提供必要的正则表达式吗？ 现在，看起来每次文件更改时我都会手工完成， 我真的很讨厌这个...
修改 在旁注中，v8包装器使用C ++ .NET，因此在Linux上不起作用，尽管v8引擎在Linux上运行良好。
所以我坚持通过JSON转换解决问题。
答案 0 :(得分：4)
您可以使用javascript engine：
using System;
using System.IO;
using Noesis.Javascript;
class Program
{
static void Main()
{
var context = new JavascriptContext();
context.SetParameter("openid", new object());
context.Run(File.ReadAllText("test.js"));
dynamic providers_large = context.GetParameter("providers_large");
foreach (var provider in providers_large)
{
Console.WriteLine(
"name: {0}, url: {1}",
provider.Value["name"],
provider.Value["url"]
);
}
}
}
在我的控制台上打印以下内容：
name: Google, url: https://www.google.com/accounts/o8/id
name: Yahoo, url: http://me.yahoo.com/
name: AOL, url: http://openid.aol.com/{username}
name: MyOpenID, url: http://{username}.myopenid.com/
name: OpenID, url:
答案 1 :(得分：0)
为此考虑JavaScriptSerializer，提供json反序列化，如果删除变量和注释，它应该能够创建对象图。
答案 2 :(得分：0)
所以这是通过转换为JSON和反序列化的锻炼：
static string RemoveCstyleComments(string strInput)
{
string strPattern = @"/[*][\w\d\s]+[*]/";
//strPattern = @"/\*.*?\*/"; // Doesn't work
//strPattern = "/\\*.*?\\*/"; // Doesn't work
//strPattern = @"/\*([^*]|[\r\n]|(\*+([^*/]|[\r\n])))*\*+/ "; // Doesn't work
//strPattern = @"/\*([^*]|[\r\n]|(\*+([^*/]|[\r\n])))*\*+/ "; // Doesn't work
// http://stackoverflow.com/questions/462843/improving-fixing-a-regex-for-c-style-block-comments
strPattern = @"/\*(?>(?:(?>[^*]+)|\*(?!/))*)\*/"; // Works !
string strOutput = System.Text.RegularExpressions.Regex.Replace(strInput, strPattern, string.Empty, System.Text.RegularExpressions.RegexOptions.Multiline);
Console.WriteLine(strOutput);
return strOutput;
} // End Function RemoveCstyleComments
static string ReplaceVariables(string strInput)
{
string strPattern = @"var\s+providers_large(\s+)?=(\s+)?{(\s+)?";
strInput = System.Text.RegularExpressions.Regex.Replace(strInput, strPattern, "\"providers_large\" : {" + Environment.NewLine, System.Text.RegularExpressions.RegexOptions.Multiline);
strPattern = @"(\s+)?var\s+providers_small(\s+)?=(\s+)?{(\s+)?";
strInput = System.Text.RegularExpressions.Regex.Replace(strInput, strPattern, ", \"providers_small\" : {" + Environment.NewLine, System.Text.RegularExpressions.RegexOptions.Multiline);
strPattern = @"}(\s+)?;(\s+)?";
strInput = System.Text.RegularExpressions.Regex.Replace(strInput, strPattern, "}" + Environment.NewLine, System.Text.RegularExpressions.RegexOptions.Multiline);
strPattern = @"$(\s+)?(\w+)(\s+)?:(\s+)?{";
strInput = System.Text.RegularExpressions.Regex.Replace(strInput, strPattern, "\"$2\" : {", System.Text.RegularExpressions.RegexOptions.Multiline);
strPattern = @"name(\s+)?:(\s+)?'";
strInput = System.Text.RegularExpressions.Regex.Replace(strInput, strPattern, "\"name\" : '", System.Text.RegularExpressions.RegexOptions.Multiline);
strPattern = @"url(\s+)?:(\s+)?'";
strInput = System.Text.RegularExpressions.Regex.Replace(strInput, strPattern, "\"url\" : '", System.Text.RegularExpressions.RegexOptions.Multiline);
strPattern = @"label(\s+)?:(\s+)?'";
strInput = System.Text.RegularExpressions.Regex.Replace(strInput, strPattern, "\"label\" : '", System.Text.RegularExpressions.RegexOptions.Multiline);
strInput = strInput.Replace("'", "\"");
strPattern = "openid\\.locale.*";
//strInput = System.Text.RegularExpressions.Regex.Replace(strInput, strPattern, "", System.Text.RegularExpressions.RegexOptions.Multiline);
strInput = System.Text.RegularExpressions.Regex.Replace(strInput, strPattern, "", System.Text.RegularExpressions.RegexOptions.Singleline);
strPattern = null;
/*
string[] astrTrailingComments = {
@"openid\.locale"
,@"openid\.sprite"
,@"openid\.demo_text"
,@"openid\.signin_text"
,@"openid\.image_title"
};
foreach (string strThisPattern in astrTrailingComments)
{
strInput = System.Text.RegularExpressions.Regex.Replace(strInput, strThisPattern + ".+", "", System.Text.RegularExpressions.RegexOptions.Multiline);
} // Next strThisPattern
*/
strInput = "{" + strInput + "}";
//Console.WriteLine(strInput);
return strInput;
} // End Function ReplaceVariables
static System.Collections.Specialized.NameValueCollection TrySerialize(string strInput)
{
strInput = RemoveCstyleComments(strInput);
strInput = ReplaceVariables(strInput);
System.Collections.Specialized.NameValueCollection nvc = new System.Collections.Specialized.NameValueCollection(StringComparer.OrdinalIgnoreCase);
System.Web.Script.Serialization.JavaScriptSerializer js = new System.Web.Script.Serialization.JavaScriptSerializer();
dynamic objScript = js.DeserializeObject(strInput);
js = null;
foreach (dynamic kvp in objScript)
{
dynamic dictValues = kvp.Value;
//Console.WriteLine(Environment.NewLine);
//Console.WriteLine(Environment.NewLine);
//Console.WriteLine(kvp.Key);
//Console.WriteLine(Environment.NewLine);
foreach (string strMemberVariable in dictValues.Keys)
{
if(StringComparer.OrdinalIgnoreCase.Equals(kvp.Key,"providers_small"))
{
nvc.Add("providers_small", strMemberVariable);
}
if(StringComparer.OrdinalIgnoreCase.Equals(kvp.Key,"providers_large"))
{
nvc.Add("providers_large", strMemberVariable);
}
//Console.WriteLine(strMemberVariable + ":");
dynamic MemberVariable = dictValues[strMemberVariable];
//Console.WriteLine(MemberVariable.GetType().ToString());
foreach (string strProperty in MemberVariable.Keys)
{
//Console.WriteLine(strValue);
dynamic objPropertyValue = MemberVariable[strProperty];
//if (objPropertyValue != null)
//Console.WriteLine(" - " + (strProperty + ":").PadRight(8, ' ') + objPropertyValue.ToString());
} // Next strProperty
} // Next strMemberVariable
} // Next kvp
// Console.WriteLine("providers large: ");
// Console.WriteLine(nvc["providers_large"]);
// Console.WriteLine(Environment.NewLine);
// Console.WriteLine("providers small: ");
// Console.WriteLine(nvc["providers_small"]);
return nvc;
} // End Function TrySerialize
public static void GetProviders()
{
string strContent = System.IO.File.ReadAllText(@"D:\UserName\Downloads\openid-selector-1.3\openid-selector\js\openid-en.js");
strContent = System.IO.File.ReadAllText(@"D:\UserName\Downloads\openid-selector-1.3\openid-selector\js\openid-ru.js");
//Console.WriteLine(strContent);
//JavaScriptEngineTest(strContent);
//GetCurlyValues(strContent);
System.Collections.Specialized.NameValueCollection nvc = TrySerialize(strContent);
Console.WriteLine(Environment.NewLine);
Console.WriteLine("providers large: ");
foreach (string strValue in nvc.GetValues("providers_large"))
{
Console.WriteLine(" " + strValue);
} // Next strValue
//System.Runtime.Serialization.Json.DataContractJsonSerializer dcjs = new System.Runtime.Serialization.Json.DataContractJsonSerializer();
// The above is bullshit in unadulterated filth. ==> Use System.Web.Extensions instead
Console.WriteLine(Environment.NewLine);
Console.WriteLine("providers small: ");
foreach (string strValue in nvc.GetValues("providers_small"))
{
Console.WriteLine(" " + strValue);
} // Next strValue
} // End Sub GetProviders