I have a text file that contains over 200 records of the following format:
@INPROCEEDINGS{Rajan-Sullivan03,
author = {Hridesh Rajan and Kevin J. Sullivan},
title = {{{Eos}: Instance-Level Aspects for Integrated System Design}},
booktitle = {ESEC/FSE 2003},
year = {2003},
pages = {297--306},
month = sep,
isbn = {1-58113-743-5},
location = {Helsinki, FN},
owner = {Administrator},
timestamp = {2009.03.08}
}
@INPROCEEDINGS{ras-mor-models-06,
author = {Awais Rashid and Ana Moreira},
title = {Domain Models Are {NOT} Aspect Free},
booktitle = {MoDELS},
year = {2006},
editor = {Oscar Nierstrasz and Jon Whittle and David Harel and Gianna Reggio},
volume = {4199},
series = {Lecture Notes in Computer Science},
pages = {155--169},
publisher = {Springer},
bibdate = {2006-12-07},
bibsource = {DBLP, http://dblp.uni-trier.de/db/conf/models/models2006.html#RashidM06},
isbn = {3-540-45772-0},
owner = {aljasser},
timestamp = {2008.09.16},
url = {http://dx.doi.org/10.1007/11880240_12}
}
Basically a records starts with @ and ends with a }, so what i tried to do is start with @ and end with }\\n} but didn't work, it will only match the first record and the other one because there is no new line after it.
string pattern = @"(^@)([\s\S]*)(}$\n}(\n))";
and when i tried to fix it by making it, it matched everything as one match
string pattern = @"(^@)([\s\S]*)(}$\n}(\n*))";
I have tried until i reached the following pattern but it's not working, please if you can fix it or maybe give a more efficient one plus a little explanation on it's done.
Here is my code:
string pattern = @"(^@)([\s\S]*)(}$\n}(\n))";
Regex regex = new Regex(pattern,RegexOptions.Multiline);
var matches = regex.Matches(bibFileContent).Cast<Match>().Select(m => m.Value).ToList();
If you use the Matches method, you need this kind of patterns, that deal with balanced curly brackets:
string pattern = @"@[A-Z]+{(?>[^{}]+|(?<open>{)|(?<-open>}))*(?(open)(?!))}";
Regex regex = new Regex(pattern);
or to ensure that all results are well-formed (in a brackets point of view) :
string pattern = @"\G[^{}]*(@[A-Z]+{(?>[^{}]+|(?<open>{)|(?<-open>}))*(?(open)(?!))})";
These two patterns use named captures as a counter. When an opening bracket is met the counter is incremented, when a closing bracket is met the counter is decremented. (?(open)(?!))
is a conditional test that makes the pattern fail if the counter isn't null.
If chuncks do not contain the @
character, it will be more handy to use the Regex.Split(input, pattern)
method:
string[] result = Regex.Split(input, @"[^}]*(?=@)");
If chuncks can contain the @
character, you can make it more robust with a more descriptive lookahead:
string[] result = Regex.Split(input, @"[^}]*(?=@[A-Z]+{)");
or
string[] result = Regex.Split(input, @"\s*(?=@[A-Z]+{)");
I think the problem is that your input does not finish by \\n so your second record is not matched. You should put an alternation with $
This will get in group 1 the records:
@(.*?)^}(?:[\r\n]+|$)
Notice you have to use the m
and s
modifiers
Use this code:
Regex regex = new Regex(pattern, RegexOptions.Multiline | RegexOptions.Singleline);
MatchCollection mc = regex.Matches(bibFileContent);
List<String> results = new List<String>();
foreach (Group m in mc[0].Groups)
{
results.Add(m.Value);
}
You could use a simple regex like this:
(@[^@]+)
The idea is to match content that starts with @ and doesn't have another @. Btw, if you just want to match the pattern instead of capturing it just remove the capturin group:
@[^@]+
This looks like a candidate for balanced groups.
# @"(?m)^[^\S\r\n]*@[^{}]+(?:\{(?>[^{}]+|\{(?<Depth>)|\}(?<-Depth>))*(?(Depth)(?!))\})"
(?m)
^ [^\S\r\n]*
@ [^{}]+
(?:
\{ # Match opening {
(?> # Then either match (possessively):
[^{}]+ # Anything (but only if we're not at the start of { or } )
| # or
\{ # { (and increase the braces counter)
(?<Depth> )
| # or
\} # } (and decrease the braces counter).
(?<-Depth> )
)* # Repeat as needed.
(?(Depth) # Assert that the braces counter is at zero.
(?!) # Fail if it isn't
)
\} # Then match a closing }.
)
Code sample
Regex FghRx = new Regex( @"(?m)^[^\S\r\n]*@[^{}]+(?:\{(?>[^{}]+|\{(?<Depth>)|\}(?<-Depth>))*(?(Depth)(?!))\})" );
string FghData =
@"
@INPROCEEDINGS{Rajan-Sullivan03,
author = {Hridesh Rajan and Kevin J. Sullivan},
title = {{{Eos}: Instance-Level Aspects for Integrated System Design}},
booktitle = {ESEC/FSE 2003},
year = {2003},
pages = {297--306},
month = sep,
isbn = {1-58113-743-5},
location = {Helsinki, FN},
owner = {Administrator},
timestamp = {2009.03.08}
}
@INPROCEEDINGS{ras-mor-models-06,
author = {Awais Rashid and Ana Moreira},
title = {Domain Models Are {NOT} Aspect Free},
booktitle = {MoDELS},
year = {2006},
editor = {Oscar Nierstrasz and Jon Whittle and David Harel and Gianna Reggio},
volume = {4199},
series = {Lecture Notes in Computer Science},
pages = {155--169},
publisher = {Springer},
bibdate = {2006-12-07},
bibsource = {DBLP, http://dblp.uni-trier.de/db/conf/models/models2006.html#RashidM06},
isbn = {3-540-45772-0},
owner = {aljasser},
timestamp = {2008.09.16},
url = {http://dx.doi.org/10.1007/11880240_12}
}
";
Match FghMatch = FghRx.Match(FghData);
while (FghMatch.Success)
{
Console.WriteLine("New Record\n------------------------");
Console.WriteLine("{0}", FghMatch.Groups[0].Value);
FghMatch = FghMatch.NextMatch();
Console.WriteLine("");
}
Output
New Record
------------------------
@INPROCEEDINGS{Rajan-Sullivan03,
author = {Hridesh Rajan and Kevin J. Sullivan},
title = {{{Eos}: Instance-Level Aspects for Integrated System Design}},
booktitle = {ESEC/FSE 2003},
year = {2003},
pages = {297--306},
month = sep,
isbn = {1-58113-743-5},
location = {Helsinki, FN},
owner = {Administrator},
timestamp = {2009.03.08}
}
New Record
------------------------
@INPROCEEDINGS{ras-mor-models-06,
author = {Awais Rashid and Ana Moreira},
title = {Domain Models Are {NOT} Aspect Free},
booktitle = {MoDELS},
year = {2006},
editor = {Oscar Nierstrasz and Jon Whittle and David Harel and Gianna Reggio},
volume = {4199},
series = {Lecture Notes in Computer Science},
pages = {155--169},
publisher = {Springer},
bibdate = {2006-12-07},
bibsource = {DBLP, http://dblp.uni-trier.de/db/conf/models/models2006.html#RashidM06},
isbn = {3-540-45772-0},
owner = {aljasser},
timestamp = {2008.09.16},
url = {http://dx.doi.org/10.1007/11880240_12}
}
The technical post webpages of this site follow the CC BY-SA 4.0 protocol. If you need to reprint, please indicate the site URL or the original address.Any question please contact:yoyou2525@163.com.