Smalltalk › Frameworks & Tools › Moose

C# importer ?

_‹ Previous Topic Next Topic _›

Classic

List

Threaded

13 messages Options

Johan Fabry

C# importer ?

Hi all,

And now it looks like I will need to analyze a part of our own code, written in C#. Is there a parser for C# in Moose and if so, how extensive/solid is it?

TIA
--
Johan Fabry, Senior Software Engineer.
[hidden email] | Email too brief? Here's why! http://emailcharter.org

_______________________________________________
Moose-dev mailing list
[hidden email]
https://www.list.inf.unibe.ch/listinfo/moose-dev

Usman Bhatti

Re: C# importer ?

Hi John,

Sorry for the late reply.

I worked on a C# (MSIL) importer a few years back while I was working in Inria.

This parser was based on Mono project and a library Mono.Cecil that provides API to access MSIL.

The importer I wrote was able to extract the basic information required to create FAMIX model (Classes, Namespaces, methods, attributes, invocations, accesses, params).

I think it might also have started to extract Generics but that part might not be complete. I didn't rewrite FAME/FAMIX for C# but used a library to transform FAME/FAMIX in Java to C#.

That meant that I could reuse the meta-model + MSE import/export from existing code.

But I haven't been able to work on it since 6 years now. But if you are interested, you may have a look here at the code here:

https://scm.gforge.inria.fr/anonscm/svn/verveinesharp/

One day when I get some time I would like to replace Mono.Cecil with Microsoft's parser that has been opensourced since.

HTH,

regards.

Usman

On Thu, Apr 12, 2018 at 12:09 PM, Johan Fabry <[hidden email]> wrote:

Hi all,

And now it looks like I will need to analyze a part of our own code, written in C#. Is there a parser for C# in Moose and if so, how extensive/solid is it?

TIA
--
Johan Fabry, Senior Software Engineer.
[hidden email] | Email too brief? Here's why! http://emailcharter.org

_______________________________________________
Moose-dev mailing list
[hidden email]
https://www.list.inf.unibe.ch/listinfo/moose-dev

_______________________________________________
Moose-dev mailing list
[hidden email]
https://www.list.inf.unibe.ch/listinfo/moose-dev

Johan Fabry

Re: C# importer ?

Hi Usman,

Thanks for the reply! In the mean time I have been looking at using Roslyn: the .NET reflection API's, to make a XML dump of the structure of the code. I am almost there so I will keep going this route.

Now I can write a basic class structure with simple call information, and it's only 160 LOC of C# code. But the thing is that parsing is not enough, I also want the semantic analysis that gives type information (argument types, receiver type) and I don’t want to write that myself. Roslyn is supposed to give me that as well so I am investigating that now.

Johan Fabry, Senior Software Engineer.

[hidden email] | Email too brief? Here's why! http://emailcharter.org

From: Moose-dev [mailto:[hidden email]] On Behalf Of Usman Bhatti
Sent: Monday, April 16, 2018 9:59 AM
To: Moose-related development <[hidden email]>
Subject: [Moose-dev] Re: C# importer ?

Hi John,

Sorry for the late reply.

I worked on a C# (MSIL) importer a few years back while I was working in Inria.

This parser was based on Mono project and a library Mono.Cecil that provides API to access MSIL.

The importer I wrote was able to extract the basic information required to create FAMIX model (Classes, Namespaces, methods, attributes, invocations, accesses, params).

I think it might also have started to extract Generics but that part might not be complete. I didn't rewrite FAME/FAMIX for C# but used a library to transform FAME/FAMIX in Java to C#.

That meant that I could reuse the meta-model + MSE import/export from existing code.

But I haven't been able to work on it since 6 years now. But if you are interested, you may have a look here at the code here:

https://scm.gforge.inria.fr/anonscm/svn/verveinesharp/

One day when I get some time I would like to replace Mono.Cecil with Microsoft's parser that has been opensourced since.

HTH,

regards.

Usman

On Thu, Apr 12, 2018 at 12:09 PM, Johan Fabry <[hidden email]> wrote:

Hi all,

And now it looks like I will need to analyze a part of our own code, written in C#. Is there a parser for C# in Moose and if so, how extensive/solid is it?

TIA
--
Johan Fabry, Senior Software Engineer.
[hidden email] | Email too brief? Here's why! http://emailcharter.org

_______________________________________________
Moose-dev mailing list
[hidden email]
https://www.list.inf.unibe.ch/listinfo/moose-dev

_______________________________________________
Moose-dev mailing list
[hidden email]
https://www.list.inf.unibe.ch/listinfo/moose-dev

Usman Bhatti

Re: C# importer ?

On Mon, Apr 16, 2018 at 10:07 AM, Johan Fabry <[hidden email]> wrote:

Hi Usman,

Thanks for the reply! In the mean time I have been looking at using Roslyn: the .NET reflection API's, to make a XML dump of the structure of the code. I am almost there so I will keep going this route.

Excellent!

Now I can write a basic class structure with simple call information, and it's only 160 LOC of C# code. But the thing is that parsing is not enough, I also want the semantic analysis that gives type information (argument types, receiver type) and I don’t want to write that myself. Roslyn is supposed to give me that as well so I am investigating that now.

I hope it does.

Now, Mono.Cecil also does name resolution but sometimes I encountered limitations with it hence I would also support that you go for a solution provided by MS.

regards.

Usman

--

Johan Fabry, Senior Software Engineer.

[hidden email] | Email too brief? Here's why! http://emailcharter.org

From: Moose-dev [mailto:[hidden email]] On Behalf Of Usman Bhatti
Sent: Monday, April 16, 2018 9:59 AM
To: Moose-related development <[hidden email]>
Subject: [Moose-dev] Re: C# importer ?

Hi John,

Sorry for the late reply.

I worked on a C# (MSIL) importer a few years back while I was working in Inria.

This parser was based on Mono project and a library Mono.Cecil that provides API to access MSIL.

The importer I wrote was able to extract the basic information required to create FAMIX model (Classes, Namespaces, methods, attributes, invocations, accesses, params).

I think it might also have started to extract Generics but that part might not be complete. I didn't rewrite FAME/FAMIX for C# but used a library to transform FAME/FAMIX in Java to C#.

That meant that I could reuse the meta-model + MSE import/export from existing code.

But I haven't been able to work on it since 6 years now. But if you are interested, you may have a look here at the code here:

https://scm.gforge.inria.fr/anonscm/svn/verveinesharp/

One day when I get some time I would like to replace Mono.Cecil with Microsoft's parser that has been opensourced since.

HTH,

regards.

Usman

On Thu, Apr 12, 2018 at 12:09 PM, Johan Fabry <[hidden email]> wrote:

Hi all,

And now it looks like I will need to analyze a part of our own code, written in C#. Is there a parser for C# in Moose and if so, how extensive/solid is it?

TIA
--
Johan Fabry, Senior Software Engineer.
[hidden email] | Email too brief? Here's why! http://emailcharter.org

_______________________________________________
Moose-dev mailing list
[hidden email]
https://www.list.inf.unibe.ch/listinfo/moose-dev

_______________________________________________
Moose-dev mailing list
[hidden email]
https://www.list.inf.unibe.ch/listinfo/moose-dev

_______________________________________________
Moose-dev mailing list
[hidden email]
https://www.list.inf.unibe.ch/listinfo/moose-dev

Thomas Haug

Re: C# importer ?

Hi Johan,

you might take a look at my famix generator for IL code:

http://sharpmetrics.net/index.php/famix-generator

At the moment I am using Microsoft CCI but I have also begun to use Roslyn to generate Famix models.

During the upcoming weeks I will release a new version of the generator and my other tool (also change the license to that everything can be also used for commerical use).

Cheers

Thomas

Von: "Usman Bhatti" <[hidden email]>
An: "Moose-related development" <[hidden email]>
Gesendet: Montag, 16. April 2018 10:21:46
Betreff: [Moose-dev] Re: C# importer ?

On Mon, Apr 16, 2018 at 10:07 AM, Johan Fabry <[hidden email]> wrote:

Hi Usman,

Thanks for the reply! In the mean time I have been looking at using Roslyn: the .NET reflection API's, to make a XML dump of the structure of the code. I am almost there so I will keep going this route.

Excellent!

Now I can write a basic class structure with simple call information, and it's only 160 LOC of C# code. But the thing is that parsing is not enough, I also want the semantic analysis that gives type information (argument types, receiver type) and I don’t want to write that myself. Roslyn is supposed to give me that as well so I am investigating that now.

I hope it does.

Now, Mono.Cecil also does name resolution but sometimes I encountered limitations with it hence I would also support that you go for a solution provided by MS.

regards.

Usman

--

Johan Fabry, Senior Software Engineer.

[hidden email] | Email too brief? Here's why! http://emailcharter.org

From: Moose-dev [mailto:[hidden email]] On Behalf Of Usman Bhatti
Sent: Monday, April 16, 2018 9:59 AM
To: Moose-related development <[hidden email]>
Subject: [Moose-dev] Re: C# importer ?

Hi John,

Sorry for the late reply.

I worked on a C# (MSIL) importer a few years back while I was working in Inria.

This parser was based on Mono project and a library Mono.Cecil that provides API to access MSIL.

The importer I wrote was able to extract the basic information required to create FAMIX model (Classes, Namespaces, methods, attributes, invocations, accesses, params).

I think it might also have started to extract Generics but that part might not be complete. I didn't rewrite FAME/FAMIX for C# but used a library to transform FAME/FAMIX in Java to C#.

That meant that I could reuse the meta-model + MSE import/export from existing code.

But I haven't been able to work on it since 6 years now. But if you are interested, you may have a look here at the code here:

https://scm.gforge.inria.fr/anonscm/svn/verveinesharp/

One day when I get some time I would like to replace Mono.Cecil with Microsoft's parser that has been opensourced since.

HTH,

regards.

Usman

On Thu, Apr 12, 2018 at 12:09 PM, Johan Fabry <[hidden email]> wrote:

Hi all,

And now it looks like I will need to analyze a part of our own code, written in C#. Is there a parser for C# in Moose and if so, how extensive/solid is it?

TIA
--
Johan Fabry, Senior Software Engineer.
[hidden email] | Email too brief? Here's why! http://emailcharter.org

_______________________________________________
Moose-dev mailing list
[hidden email]
https://www.list.inf.unibe.ch/listinfo/moose-dev

_______________________________________________
Moose-dev mailing list
[hidden email]
https://www.list.inf.unibe.ch/listinfo/moose-dev

_______________________________________________
Moose-dev mailing list
[hidden email]
https://www.list.inf.unibe.ch/listinfo/moose-dev

Stéphane Ducasse

Re: C# importer ?

Thanks Thomas.

Our objectives now is to put all the importer under MIT license.

Stef

On 16 May 2018, at 17:59, Thomas Haug <[hidden email]> wrote:

Hi Johan,

you might take a look at my famix generator for IL code:
http://sharpmetrics.net/index.php/famix-generator

At the moment I am using Microsoft CCI but I have also begun to use Roslyn to generate Famix models.
During the upcoming weeks I will release a new version of the generator and my other tool (also change the license to that everything can be also used for commerical use).

Cheers
Thomas

Von: "Usman Bhatti" <[hidden email]>
An: "Moose-related development" <[hidden email]>
Gesendet: Montag, 16. April 2018 10:21:46
Betreff: [Moose-dev] Re: C# importer ?

On Mon, Apr 16, 2018 at 10:07 AM, Johan Fabry <[hidden email]> wrote:

Hi Usman,

Thanks for the reply! In the mean time I have been looking at using Roslyn: the .NET reflection API's, to make a XML dump of the structure of the code. I am almost there so I will keep going this route.

Excellent!

Now I can write a basic class structure with simple call information, and it's only 160 LOC of C# code. But the thing is that parsing is not enough, I also want the semantic analysis that gives type information (argument types, receiver type) and I don’t want to write that myself. Roslyn is supposed to give me that as well so I am investigating that now.

I hope it does.
Now, Mono.Cecil also does name resolution but sometimes I encountered limitations with it hence I would also support that you go for a solution provided by MS.

regards.
Usman

--
Johan Fabry, Senior Software Engineer.
[hidden email] | Email too brief? Here's why! http://emailcharter.org

From: Moose-dev [mailto:[hidden email]] On Behalf Of Usman Bhatti
Sent: Monday, April 16, 2018 9:59 AM
To: Moose-related development <[hidden email]>
Subject: [Moose-dev] Re: C# importer ?

Hi John,

Sorry for the late reply.

I worked on a C# (MSIL) importer a few years back while I was working in Inria.

This parser was based on Mono project and a library Mono.Cecil that provides API to access MSIL.

The importer I wrote was able to extract the basic information required to create FAMIX model (Classes, Namespaces, methods, attributes, invocations, accesses, params).

I think it might also have started to extract Generics but that part might not be complete. I didn't rewrite FAME/FAMIX for C# but used a library to transform FAME/FAMIX in Java to C#.

That meant that I could reuse the meta-model + MSE import/export from existing code.

But I haven't been able to work on it since 6 years now. But if you are interested, you may have a look here at the code here:

https://scm.gforge.inria.fr/anonscm/svn/verveinesharp/

One day when I get some time I would like to replace Mono.Cecil with Microsoft's parser that has been opensourced since.

HTH,

regards.

Usman

On Thu, Apr 12, 2018 at 12:09 PM, Johan Fabry <[hidden email]> wrote:

Hi all,

And now it looks like I will need to analyze a part of our own code, written in C#. Is there a parser for C# in Moose and if so, how extensive/solid is it?

TIA
--
Johan Fabry, Senior Software Engineer.
[hidden email] | Email too brief? Here's why! http://emailcharter.org

_______________________________________________
Moose-dev mailing list
[hidden email]
https://www.list.inf.unibe.ch/listinfo/moose-dev

_______________________________________________
Moose-dev mailing list
[hidden email]
https://www.list.inf.unibe.ch/listinfo/moose-dev

_______________________________________________
Moose-dev mailing list
[hidden email]
https://www.list.inf.unibe.ch/listinfo/moose-dev

--------------------------------------------

Stéphane Ducasse

http://stephane.ducasse.free.fr

http://www.synectique.eu / http://www.pharo.org

03 59 35 87 52

Assistant: Julie Jonas

FAX 03 59 57 78 50

TEL 03 59 35 86 16

S. Ducasse - Inria

40, avenue Halley,

Parc Scientifique de la Haute Borne, Bât.A, Park Plaza

Villeneuve d'Ascq 59650

France

_______________________________________________
Moose-dev mailing list
[hidden email]
https://www.list.inf.unibe.ch/listinfo/moose-dev

Thomas Haug

Re: C# importer ?

Hi Stef,

thanks for the info.

My famix generator is using a "proprietary" model to generate the FAMIX file.

My IL "analysis engine", which based on Microsoft CCI to create the "proprietary" is not really in a shape to be open sourced (I fear I would ruine my professional career if somebody sees how badly it is implemented ;-). Yes I am not proud but it does the job and it was build in my rare spare time).

But I could offer to open source the famix generator and place it under the MIT license as an intermediate step. The long term goal for me would be to switch to Roslyn and have a sound implementation which can also be open sourced.

The question to you is if such a (half-hearted) solution would be ok for you?

If so then I would put the code into my github repo

Cheers

Thomas

Von: "Stéphane Ducasse" <[hidden email]>
An: "Moose-related development" <[hidden email]>
Gesendet: Mittwoch, 16. Mai 2018 20:17:20
Betreff: [Moose-dev] Re: C# importer ?

Thanks Thomas.

Our objectives now is to put all the importer under MIT license.

Stef

On 16 May 2018, at 17:59, Thomas Haug <[hidden email]> wrote:

Hi Johan,

you might take a look at my famix generator for IL code:
http://sharpmetrics.net/index.php/famix-generator

At the moment I am using Microsoft CCI but I have also begun to use Roslyn to generate Famix models.
During the upcoming weeks I will release a new version of the generator and my other tool (also change the license to that everything can be also used for commerical use).

Cheers
Thomas

Von: "Usman Bhatti" <[hidden email]>
An: "Moose-related development" <[hidden email]>
Gesendet: Montag, 16. April 2018 10:21:46
Betreff: [Moose-dev] Re: C# importer ?

On Mon, Apr 16, 2018 at 10:07 AM, Johan Fabry <[hidden email]> wrote:

Hi Usman,

Thanks for the reply! In the mean time I have been looking at using Roslyn: the .NET reflection API's, to make a XML dump of the structure of the code. I am almost there so I will keep going this route.

Excellent!

Now I can write a basic class structure with simple call information, and it's only 160 LOC of C# code. But the thing is that parsing is not enough, I also want the semantic analysis that gives type information (argument types, receiver type) and I don’t want to write that myself. Roslyn is supposed to give me that as well so I am investigating that now.

I hope it does.
Now, Mono.Cecil also does name resolution but sometimes I encountered limitations with it hence I would also support that you go for a solution provided by MS.

regards.
Usman

--
Johan Fabry, Senior Software Engineer.
[hidden email] | Email too brief? Here's why! http://emailcharter.org

From: Moose-dev [mailto:[hidden email]] On Behalf Of Usman Bhatti
Sent: Monday, April 16, 2018 9:59 AM
To: Moose-related development <[hidden email]>
Subject: [Moose-dev] Re: C# importer ?

Hi John,

Sorry for the late reply.

I worked on a C# (MSIL) importer a few years back while I was working in Inria.

This parser was based on Mono project and a library Mono.Cecil that provides API to access MSIL.

The importer I wrote was able to extract the basic information required to create FAMIX model (Classes, Namespaces, methods, attributes, invocations, accesses, params).

I think it might also have started to extract Generics but that part might not be complete. I didn't rewrite FAME/FAMIX for C# but used a library to transform FAME/FAMIX in Java to C#.

That meant that I could reuse the meta-model + MSE import/export from existing code.

But I haven't been able to work on it since 6 years now. But if you are interested, you may have a look here at the code here:

https://scm.gforge.inria.fr/anonscm/svn/verveinesharp/

One day when I get some time I would like to replace Mono.Cecil with Microsoft's parser that has been opensourced since.

HTH,

regards.

Usman

On Thu, Apr 12, 2018 at 12:09 PM, Johan Fabry <[hidden email]> wrote:

Hi all,

And now it looks like I will need to analyze a part of our own code, written in C#. Is there a parser for C# in Moose and if so, how extensive/solid is it?

TIA
--
Johan Fabry, Senior Software Engineer.
[hidden email] | Email too brief? Here's why! http://emailcharter.org

_______________________________________________
Moose-dev mailing list
[hidden email]
https://www.list.inf.unibe.ch/listinfo/moose-dev

_______________________________________________
Moose-dev mailing list
[hidden email]
https://www.list.inf.unibe.ch/listinfo/moose-dev

_______________________________________________
Moose-dev mailing list
[hidden email]
https://www.list.inf.unibe.ch/listinfo/moose-dev

--------------------------------------------

Stéphane Ducasse

http://stephane.ducasse.free.fr

http://www.synectique.eu / http://www.pharo.org

03 59 35 87 52

Assistant: Julie Jonas

FAX 03 59 57 78 50

TEL 03 59 35 86 16

S. Ducasse - Inria

40, avenue Halley,

Parc Scientifique de la Haute Borne, Bât.A, Park Plaza

Villeneuve d'Ascq 59650

France

_______________________________________________
Moose-dev mailing list
[hidden email]
https://www.list.inf.unibe.ch/listinfo/moose-dev

Stéphane Ducasse

Re: C# importer ?

Hi thomas

Do the best that you can.

Now you see if you open-source a badly implemented solution (and say to the guys that it is in bad shape then we know it), people in need may even do a pass on it.

This is not like certain tools full of getClass.equal() everywhere that pretend that this is the correct design :) They believe that they know object-oriented programming.

We are waiting that Synectique situation clarifies (it will probably die) and from that day we will open-source everything we did.

The C++, C importers are already open-source and we should structure the moose git repo.

Stef

Hi Stef,
thanks for the info.

My famix generator is using a "proprietary" model to generate the FAMIX file.
My IL "analysis engine", which based on Microsoft CCI to create the "proprietary" is not really in a shape to be open sourced (I fear I would ruine my professional career if somebody sees how badly it is implemented ;-). Yes I am not proud but it does the job and it was build in my rare spare time).

But I could offer to open source the famix generator and place it under the MIT license as an intermediate step. The long term goal for me would be to switch to Roslyn and have a sound implementation which can also be open sourced.

The question to you is if such a (half-hearted) solution would be ok for you?
If so then I would put the code into my github repo

Cheers
Thomas

Von: "Stéphane Ducasse" <[hidden email]>
An: "Moose-related development" <[hidden email]>
Gesendet: Mittwoch, 16. Mai 2018 20:17:20
Betreff: [Moose-dev] Re: C# importer ?

Thanks Thomas.
Our objectives now is to put all the importer under MIT license.

Stef

On 16 May 2018, at 17:59, Thomas Haug <[hidden email]> wrote:

Hi Johan,

you might take a look at my famix generator for IL code:
http://sharpmetrics.net/index.php/famix-generator

At the moment I am using Microsoft CCI but I have also begun to use Roslyn to generate Famix models.
During the upcoming weeks I will release a new version of the generator and my other tool (also change the license to that everything can be also used for commerical use).

Cheers
Thomas

Von: "Usman Bhatti" <[hidden email]>
An: "Moose-related development" <[hidden email]>
Gesendet: Montag, 16. April 2018 10:21:46
Betreff: [Moose-dev] Re: C# importer ?

On Mon, Apr 16, 2018 at 10:07 AM, Johan Fabry <[hidden email]> wrote:

Hi Usman,

Thanks for the reply! In the mean time I have been looking at using Roslyn: the .NET reflection API's, to make a XML dump of the structure of the code. I am almost there so I will keep going this route.

Excellent!

Now I can write a basic class structure with simple call information, and it's only 160 LOC of C# code. But the thing is that parsing is not enough, I also want the semantic analysis that gives type information (argument types, receiver type) and I don’t want to write that myself. Roslyn is supposed to give me that as well so I am investigating that now.

I hope it does.
Now, Mono.Cecil also does name resolution but sometimes I encountered limitations with it hence I would also support that you go for a solution provided by MS.

regards.
Usman

--
Johan Fabry, Senior Software Engineer.
[hidden email] | Email too brief? Here's why! http://emailcharter.org

From: Moose-dev [mailto:[hidden email]] On Behalf Of Usman Bhatti
Sent: Monday, April 16, 2018 9:59 AM
To: Moose-related development <[hidden email]>
Subject: [Moose-dev] Re: C# importer ?

Hi John,

Sorry for the late reply.

I worked on a C# (MSIL) importer a few years back while I was working in Inria.

This parser was based on Mono project and a library Mono.Cecil that provides API to access MSIL.

The importer I wrote was able to extract the basic information required to create FAMIX model (Classes, Namespaces, methods, attributes, invocations, accesses, params).

I think it might also have started to extract Generics but that part might not be complete. I didn't rewrite FAME/FAMIX for C# but used a library to transform FAME/FAMIX in Java to C#.

That meant that I could reuse the meta-model + MSE import/export from existing code.

But I haven't been able to work on it since 6 years now. But if you are interested, you may have a look here at the code here:

https://scm.gforge.inria.fr/anonscm/svn/verveinesharp/

One day when I get some time I would like to replace Mono.Cecil with Microsoft's parser that has been opensourced since.

HTH,

regards.

Usman

On Thu, Apr 12, 2018 at 12:09 PM, Johan Fabry <[hidden email]> wrote:

Hi all,

And now it looks like I will need to analyze a part of our own code, written in C#. Is there a parser for C# in Moose and if so, how extensive/solid is it?

TIA
--
Johan Fabry, Senior Software Engineer.
[hidden email] | Email too brief? Here's why! http://emailcharter.org

_______________________________________________
Moose-dev mailing list
[hidden email]
https://www.list.inf.unibe.ch/listinfo/moose-dev

_______________________________________________
Moose-dev mailing list
[hidden email]
https://www.list.inf.unibe.ch/listinfo/moose-dev

_______________________________________________
Moose-dev mailing list
[hidden email]
https://www.list.inf.unibe.ch/listinfo/moose-dev

--------------------------------------------
Stéphane Ducasse
http://stephane.ducasse.free.fr
http://www.synectique.eu / http://www.pharo.org
03 59 35 87 52
Assistant: Julie Jonas
FAX 03 59 57 78 50
TEL 03 59 35 86 16
S. Ducasse - Inria
40, avenue Halley,
Parc Scientifique de la Haute Borne, Bât.A, Park Plaza
Villeneuve d'Ascq 59650
France

_______________________________________________
Moose-dev mailing list
[hidden email]
https://www.list.inf.unibe.ch/listinfo/moose-dev
_______________________________________________
Moose-dev mailing list
[hidden email]
https://www.list.inf.unibe.ch/listinfo/moose-dev

--------------------------------------------

Stéphane Ducasse

http://stephane.ducasse.free.fr

http://www.synectique.eu / http://www.pharo.org

03 59 35 87 52

Assistant: Julie Jonas

FAX 03 59 57 78 50

TEL 03 59 35 86 16

S. Ducasse - Inria

40, avenue Halley,

Parc Scientifique de la Haute Borne, Bât.A, Park Plaza

Villeneuve d'Ascq 59650

France

_______________________________________________
Moose-dev mailing list
[hidden email]
https://www.list.inf.unibe.ch/listinfo/moose-dev

Johan Fabry

Re: C# importer ?

In reply to this post by Thomas Haug

Hi Thomas,

Thanks for your mail! In the mean time I hacked together a simple export using Roslyn and it more or less did what I needed.

So I don't have any immediate need but I will certainly keep it in mind in the future!

Johan Fabry, Senior Software Engineer.

[hidden email] | Email too brief? Here's why! http://emailcharter.org

From: Thomas Haug [mailto:[hidden email]]
Sent: Wednesday, May 16, 2018 6:00 PM
To: Johan Fabry <[hidden email]>
Cc: Moose-related development <[hidden email]>
Subject: Re: [Moose-dev] Re: C# importer ?

Hi Johan,

you might take a look at my famix generator for IL code:

http://sharpmetrics.net/index.php/famix-generator

At the moment I am using Microsoft CCI but I have also begun to use Roslyn to generate Famix models.

During the upcoming weeks I will release a new version of the generator and my other tool (also change the license to that everything can be also used for commerical use).

Cheers

Thomas

Von: "Usman Bhatti" <[hidden email]>
An: "Moose-related development" <[hidden email]>
Gesendet: Montag, 16. April 2018 10:21:46
Betreff: [Moose-dev] Re: C# importer ?

On Mon, Apr 16, 2018 at 10:07 AM, Johan Fabry <[hidden email]> wrote:

Hi Usman,

Thanks for the reply! In the mean time I have been looking at using Roslyn: the .NET reflection API's, to make a XML dump of the structure of the code. I am almost there so I will keep going this route.

Excellent!

Now I can write a basic class structure with simple call information, and it's only 160 LOC of C# code. But the thing is that parsing is not enough, I also want the semantic analysis that gives type information (argument types, receiver type) and I don’t want to write that myself. Roslyn is supposed to give me that as well so I am investigating that now.

I hope it does.

Now, Mono.Cecil also does name resolution but sometimes I encountered limitations with it hence I would also support that you go for a solution provided by MS.

regards.

Usman

--

Johan Fabry, Senior Software Engineer.

[hidden email] | Email too brief? Here's why! http://emailcharter.org

From: Moose-dev [mailto:[hidden email]] On Behalf Of Usman Bhatti
Sent: Monday, April 16, 2018 9:59 AM
To: Moose-related development <[hidden email]>
Subject: [Moose-dev] Re: C# importer ?

Hi John,

Sorry for the late reply.

I worked on a C# (MSIL) importer a few years back while I was working in Inria.

This parser was based on Mono project and a library Mono.Cecil that provides API to access MSIL.

The importer I wrote was able to extract the basic information required to create FAMIX model (Classes, Namespaces, methods, attributes, invocations, accesses, params).

I think it might also have started to extract Generics but that part might not be complete. I didn't rewrite FAME/FAMIX for C# but used a library to transform FAME/FAMIX in Java to C#.

That meant that I could reuse the meta-model + MSE import/export from existing code.

But I haven't been able to work on it since 6 years now. But if you are interested, you may have a look here at the code here:

https://scm.gforge.inria.fr/anonscm/svn/verveinesharp/

One day when I get some time I would like to replace Mono.Cecil with Microsoft's parser that has been opensourced since.

HTH,

regards.

Usman

On Thu, Apr 12, 2018 at 12:09 PM, Johan Fabry <[hidden email]> wrote:

Hi all,

And now it looks like I will need to analyze a part of our own code, written in C#. Is there a parser for C# in Moose and if so, how extensive/solid is it?

TIA
--
Johan Fabry, Senior Software Engineer.
[hidden email] | Email too brief? Here's why! http://emailcharter.org

_______________________________________________
Moose-dev mailing list
[hidden email]
https://www.list.inf.unibe.ch/listinfo/moose-dev

_______________________________________________
Moose-dev mailing list
[hidden email]
https://www.list.inf.unibe.ch/listinfo/moose-dev

_______________________________________________
Moose-dev mailing list
[hidden email]
https://www.list.inf.unibe.ch/listinfo/moose-dev

Johan Fabry

Re: C# importer ?

In reply to this post by Stéphane Ducasse

I agree with Stef, do not be afraid to put it out there.

Nobody else knows your exact situation and hence the decisions you had to make to get to a certain design or implementation. Nobody is perfect. Worse things have been released but are still useful.

<rant>Look for example at the design of Roslyn. That thing is so hard to use and it's so unclear why things go wrong when they do. Yet it's supposed to be built by people who know very well what they are doing. Good luck if you want to use it and get it to work 100%. I still have some cases where it cannot give me receiver type information even though it is trivial to deduce (and visual studio does it without problems).</rant>

Johan Fabry, Senior Software Engineer.

[hidden email] | Email too brief? Here's why! http://emailcharter.org

From: Moose-dev [mailto:[hidden email]] On Behalf Of Stéphane Ducasse
Sent: Wednesday, May 16, 2018 10:20 PM
To: Moose-related development <[hidden email]>
Subject: [Moose-dev] Re: C# importer ?

Hi thomas

Do the best that you can.

Now you see if you open-source a badly implemented solution (and say to the guys that it is in bad shape then we know it), people in need may even do a pass on it.

This is not like certain tools full of getClass.equal() everywhere that pretend that this is the correct design :) They believe that they know object-oriented programming.

We are waiting that Synectique situation clarifies (it will probably die) and from that day we will open-source everything we did.

The C++, C importers are already open-source and we should structure the moose git repo.

Stef

Hi Stef,

thanks for the info.

My famix generator is using a "proprietary" model to generate the FAMIX file.

My IL "analysis engine", which based on Microsoft CCI to create the "proprietary" is not really in a shape to be open sourced (I fear I would ruine my professional career if somebody sees how badly it is implemented ;-). Yes I am not proud but it does the job and it was build in my rare spare time).

But I could offer to open source the famix generator and place it under the MIT license as an intermediate step. The long term goal for me would be to switch to Roslyn and have a sound implementation which can also be open sourced.

The question to you is if such a (half-hearted) solution would be ok for you?

If so then I would put the code into my github repo

Cheers

Thomas

Von: "Stéphane Ducasse" <[hidden email]>
An: "Moose-related development" <[hidden email]>
Gesendet: Mittwoch, 16. Mai 2018 20:17:20
Betreff: [Moose-dev] Re: C# importer ?

Thanks Thomas.

Our objectives now is to put all the importer under MIT license.

Stef

On 16 May 2018, at 17:59, Thomas Haug <[hidden email]> wrote:

Hi Johan,

you might take a look at my famix generator for IL code:

http://sharpmetrics.net/index.php/famix-generator

At the moment I am using Microsoft CCI but I have also begun to use Roslyn to generate Famix models.

During the upcoming weeks I will release a new version of the generator and my other tool (also change the license to that everything can be also used for commerical use).

Cheers

Thomas

Von: "Usman Bhatti" <[hidden email]>
An: "Moose-related development" <[hidden email]>
Gesendet: Montag, 16. April 2018 10:21:46
Betreff: [Moose-dev] Re: C# importer ?

On Mon, Apr 16, 2018 at 10:07 AM, Johan Fabry <[hidden email]> wrote:

Hi Usman,

Thanks for the reply! In the mean time I have been looking at using Roslyn: the .NET reflection API's, to make a XML dump of the structure of the code. I am almost there so I will keep going this route.

Excellent!

Now I can write a basic class structure with simple call information, and it's only 160 LOC of C# code. But the thing is that parsing is not enough, I also want the semantic analysis that gives type information (argument types, receiver type) and I don’t want to write that myself. Roslyn is supposed to give me that as well so I am investigating that now.

I hope it does.

Now, Mono.Cecil also does name resolution but sometimes I encountered limitations with it hence I would also support that you go for a solution provided by MS.

regards.

Usman

--

Johan Fabry, Senior Software Engineer.

[hidden email] | Email too brief? Here's why! http://emailcharter.org

From: Moose-dev [mailto:[hidden email]] On Behalf Of Usman Bhatti
Sent: Monday, April 16, 2018 9:59 AM
To: Moose-related development <[hidden email]>
Subject: [Moose-dev] Re: C# importer ?

Hi John,

Sorry for the late reply.

I worked on a C# (MSIL) importer a few years back while I was working in Inria.

This parser was based on Mono project and a library Mono.Cecil that provides API to access MSIL.

The importer I wrote was able to extract the basic information required to create FAMIX model (Classes, Namespaces, methods, attributes, invocations, accesses, params).

I think it might also have started to extract Generics but that part might not be complete. I didn't rewrite FAME/FAMIX for C# but used a library to transform FAME/FAMIX in Java to C#.

That meant that I could reuse the meta-model + MSE import/export from existing code.

But I haven't been able to work on it since 6 years now. But if you are interested, you may have a look here at the code here:

https://scm.gforge.inria.fr/anonscm/svn/verveinesharp/

One day when I get some time I would like to replace Mono.Cecil with Microsoft's parser that has been opensourced since.

HTH,

regards.

Usman

On Thu, Apr 12, 2018 at 12:09 PM, Johan Fabry <[hidden email]> wrote:

Hi all,

And now it looks like I will need to analyze a part of our own code, written in C#. Is there a parser for C# in Moose and if so, how extensive/solid is it?

TIA
--
Johan Fabry, Senior Software Engineer.
[hidden email] | Email too brief? Here's why! http://emailcharter.org

_______________________________________________
Moose-dev mailing list
[hidden email]
https://www.list.inf.unibe.ch/listinfo/moose-dev

_______________________________________________
Moose-dev mailing list
[hidden email]
https://www.list.inf.unibe.ch/listinfo/moose-dev

_______________________________________________
Moose-dev mailing list
[hidden email]
https://www.list.inf.unibe.ch/listinfo/moose-dev

--------------------------------------------

Stéphane Ducasse

http://stephane.ducasse.free.fr

http://www.synectique.eu / http://www.pharo.org

03 59 35 87 52

Assistant: Julie Jonas

FAX 03 59 57 78 50

TEL 03 59 35 86 16

S. Ducasse - Inria

40, avenue Halley,

Parc Scientifique de la Haute Borne, Bât.A, Park Plaza

Villeneuve d'Ascq 59650

France

_______________________________________________
Moose-dev mailing list
[hidden email]
https://www.list.inf.unibe.ch/listinfo/moose-dev

_______________________________________________
Moose-dev mailing list
[hidden email]
https://www.list.inf.unibe.ch/listinfo/moose-dev

--------------------------------------------

Stéphane Ducasse

http://stephane.ducasse.free.fr

http://www.synectique.eu / http://www.pharo.org

03 59 35 87 52

Assistant: Julie Jonas

FAX 03 59 57 78 50

TEL 03 59 35 86 16

S. Ducasse - Inria

40, avenue Halley,

Parc Scientifique de la Haute Borne, Bât.A, Park Plaza

Villeneuve d'Ascq 59650

France

_______________________________________________
Moose-dev mailing list
[hidden email]
https://www.list.inf.unibe.ch/listinfo/moose-dev

Nicolas Anquetil

Re: C# importer ?

In reply to this post by Stéphane Ducasse

Hi,

And to add my voice to that of steph and Johan, I am not particularly proud of the C/C++ importer, yet I opened it and some people tried to use it recently.

I am not sure they succedded, so it might be a bad example, but there is always hope that somebody will have time to improve it at some point

nicolas

On 16/05/2018 22:19, Stéphane Ducasse wrote:

Hi thomas

Do the best that you can.
Now you see if you open-source a badly implemented solution (and say to the guys that it is in bad shape then we know it), people in need may even do a pass on it.

This is not like certain tools full of getClass.equal() everywhere that pretend that this is the correct design :) They believe that they know object-oriented programming.

We are waiting that Synectique situation clarifies (it will probably die) and from that day we will open-source everything we did.

The C++, C importers are already open-source and we should structure the moose git repo.

Stef

Hi Stef,

thanks for the info.

My famix generator is using a "proprietary" model to generate the FAMIX file.

My IL "analysis engine", which based on Microsoft CCI to create the "proprietary" is not really in a shape to be open sourced (I fear I would ruine my professional career if somebody sees how badly it is implemented ;-). Yes I am not proud but it does the job and it was build in my rare spare time).

But I could offer to open source the famix generator and place it under the MIT license as an intermediate step. The long term goal for me would be to switch to Roslyn and have a sound implementation which can also be open sourced.

The question to you is if such a (half-hearted) solution would be ok for you?

If so then I would put the code into my github repo

Cheers

Thomas

Von: "Stéphane Ducasse" <[hidden email]>
An: "Moose-related development" <[hidden email]>
Gesendet: Mittwoch, 16. Mai 2018 20:17:20
Betreff: [Moose-dev] Re: C# importer ?

Thanks Thomas.
Our objectives now is to put all the importer under MIT license.

Stef

On 16 May 2018, at 17:59, Thomas Haug <[hidden email]> wrote:

Hi Johan,

you might take a look at my famix generator for IL code:

http://sharpmetrics.net/index.php/famix-generator

At the moment I am using Microsoft CCI but I have also begun to use Roslyn to generate Famix models.

During the upcoming weeks I will release a new version of the generator and my other tool (also change the license to that everything can be also used for commerical use).

Cheers

Thomas

Von: "Usman Bhatti" <[hidden email]>
An: "Moose-related development" <[hidden email]>
Gesendet: Montag, 16. April 2018 10:21:46
Betreff: [Moose-dev] Re: C# importer ?

On Mon, Apr 16, 2018 at 10:07 AM, Johan Fabry <[hidden email]> wrote:

Hi Usman,

Thanks for the reply! In the mean time I have been looking at using Roslyn: the .NET reflection API's, to make a XML dump of the structure of the code. I am almost there so I will keep going this route.

Excellent!

Now I can write a basic class structure with simple call information, and it's only 160 LOC of C# code. But the thing is that parsing is not enough, I also want the semantic analysis that gives type information (argument types, receiver type) and I don’t want to write that myself. Roslyn is supposed to give me that as well so I am investigating that now.

I hope it does.

Now, Mono.Cecil also does name resolution but sometimes I encountered limitations with it hence I would also support that you go for a solution provided by MS.

regards.

Usman

--

Johan Fabry, Senior Software Engineer.

[hidden email] | Email too brief? Here's why! http://emailcharter.org

From: Moose-dev [mailto:[hidden email]] On Behalf Of Usman Bhatti
Sent: Monday, April 16, 2018 9:59 AM
To: Moose-related development <[hidden email]>
Subject: [Moose-dev] Re: C# importer ?

Hi John,

Sorry for the late reply.

I worked on a C# (MSIL) importer a few years back while I was working in Inria.

This parser was based on Mono project and a library Mono.Cecil that provides API to access MSIL.

The importer I wrote was able to extract the basic information required to create FAMIX model (Classes, Namespaces, methods, attributes, invocations, accesses, params).

I think it might also have started to extract Generics but that part might not be complete. I didn't rewrite FAME/FAMIX for C# but used a library to transform FAME/FAMIX in Java to C#.

That meant that I could reuse the meta-model + MSE import/export from existing code.

But I haven't been able to work on it since 6 years now. But if you are interested, you may have a look here at the code here:

https://scm.gforge.inria.fr/anonscm/svn/verveinesharp/

One day when I get some time I would like to replace Mono.Cecil with Microsoft's parser that has been opensourced since.

HTH,

regards.

Usman

On Thu, Apr 12, 2018 at 12:09 PM, Johan Fabry <[hidden email]> wrote:

Hi all,

And now it looks like I will need to analyze a part of our own code, written in C#. Is there a parser for C# in Moose and if so, how extensive/solid is it?

TIA
--
Johan Fabry, Senior Software Engineer.
[hidden email] | Email too brief? Here's why! http://emailcharter.org

_______________________________________________
Moose-dev mailing list
[hidden email]
https://www.list.inf.unibe.ch/listinfo/moose-dev

_______________________________________________
Moose-dev mailing list
[hidden email]
https://www.list.inf.unibe.ch/listinfo/moose-dev

_______________________________________________
Moose-dev mailing list
[hidden email]
https://www.list.inf.unibe.ch/listinfo/moose-dev

--------------------------------------------

Stéphane Ducasse

http://stephane.ducasse.free.fr

http://www.synectique.eu / http://www.pharo.org

03 59 35 87 52

Assistant: Julie Jonas

FAX 03 59 57 78 50

TEL 03 59 35 86 16

S. Ducasse - Inria

40, avenue Halley,

Parc Scientifique de la Haute Borne, Bât.A, Park Plaza

Villeneuve d'Ascq 59650

France

_______________________________________________
Moose-dev mailing list
[hidden email]
https://www.list.inf.unibe.ch/listinfo/moose-dev

_______________________________________________
Moose-dev mailing list
[hidden email]
https://www.list.inf.unibe.ch/listinfo/moose-dev

--------------------------------------------

Stéphane Ducasse

http://stephane.ducasse.free.fr

http://www.synectique.eu / http://www.pharo.org

03 59 35 87 52

Assistant: Julie Jonas

FAX 03 59 57 78 50

TEL 03 59 35 86 16

S. Ducasse - Inria

40, avenue Halley,

Parc Scientifique de la Haute Borne, Bât.A, Park Plaza

Villeneuve d'Ascq 59650

France
_______________________________________________
Moose-dev mailing list
[hidden email]
https://www.list.inf.unibe.ch/listinfo/moose-dev

-- 
Nicolas Anquetil
RMod team -- Inria Lille

_______________________________________________
Moose-dev mailing list
[hidden email]
https://www.list.inf.unibe.ch/listinfo/moose-dev

smallglt

Re: C# importer ?

In response to earlier replies from Stephane, Nicholas, and any others, on
the subject of using Moose with C/C++ using VerveineC-Cpp and/or Famix-C:

My immediate stumbling block using Moose on C/C++ code is the scarcity of
examples of how to actually start using them, once the requisite tools are
installed--Famix-C as part of installing Moose, or VerveineC-Cpp separately
installed using the instructions from the Github project.

Such an example should at minimum illustrate, starting with tools (including
installation instructions for tools like VerveineC-Cpp that aren't
integrated into the Moose distribution) and a set of source files, what a
neophyte like me would need to do, to get the source code "loaded" into
Moose.

If I and others were able to start using these tools, we might also (in the
more or less distant future) become able to help in some way with their
development.

Hoping for help, while hoping to be helpful,

Galen

--
Sent from: http://forum.world.st/Moose-f1310756.html
_______________________________________________
Moose-dev mailing list
[hidden email]
https://www.list.inf.unibe.ch/listinfo/moose-dev

Fuhrmanator

Re: C# importer ?

In reply to this post by Nicolas Anquetil

Hello - reading this discussion, I'm reminded of the book "Team Geek" (1) and the part about the "Genius Myth".

Most programmers are afraid to share work they’ve only just started, because it means peers will see their mistakes and know the author of the code is not a genius.

The authors (who were key SVN developers) even mention that in 2008 users were asking for strange SVN features so users could "hide branches" of code, or "erase history",etc., because they were embarassed of their work. According to the authors, it's all very normal to have this insecurity. Some people may judge, but I don't equate one's self-worth with the quality of that person's code. I encourage you to put the code out there, especially if someone's asking for it.

Cheers,

Christopher

1. Fitzpatrick, Brian W.; Collins-Sussman, Ben. Team Geek: A Software Developer's Guide to Working Well with Others (pp. 4-5). O'Reilly Media. Kindle Edition.

On Thu, May 17, 2018 at 4:03 AM, Nicolas Anquetil <[hidden email]> wrote:

Hi,

And to add my voice to that of steph and Johan, I am not particularly proud of the C/C++ importer, yet I opened it and some people tried to use it recently.

I am not sure they succedded, so it might be a bad example, but there is always hope that somebody will have time to improve it at some point

nicolas
On 16/05/2018 22:19, Stéphane Ducasse wrote:
Hi thomas

Do the best that you can.
Now you see if you open-source a badly implemented solution (and say to the guys that it is in bad shape then we know it), people in need may even do a pass on it.

This is not like certain tools full of getClass.equal() everywhere that pretend that this is the correct design :) They believe that they know object-oriented programming.

We are waiting that Synectique situation clarifies (it will probably die) and from that day we will open-source everything we did.

The C++, C importers are already open-source and we should structure the moose git repo.

Stef

Hi Stef,

thanks for the info.

My famix generator is using a "proprietary" model to generate the FAMIX file.

My IL "analysis engine", which based on Microsoft CCI to create the "proprietary" is not really in a shape to be open sourced (I fear I would ruine my professional career if somebody sees how badly it is implemented ;-). Yes I am not proud but it does the job and it was build in my rare spare time).

But I could offer to open source the famix generator and place it under the MIT license as an intermediate step. The long term goal for me would be to switch to Roslyn and have a sound implementation which can also be open sourced.

The question to you is if such a (half-hearted) solution would be ok for you?

If so then I would put the code into my github repo

Cheers

Thomas

Von: "Stéphane Ducasse" <[hidden email]>
An: "Moose-related development" <[hidden email]>
Gesendet: Mittwoch, 16. Mai 2018 20:17:20
Betreff: [Moose-dev] Re: C# importer ?

Thanks Thomas.
Our objectives now is to put all the importer under MIT license.

Stef

On 16 May 2018, at 17:59, Thomas Haug <[hidden email]> wrote:

Hi Johan,

you might take a look at my famix generator for IL code:

http://sharpmetrics.net/index.php/famix-generator

At the moment I am using Microsoft CCI but I have also begun to use Roslyn to generate Famix models.

During the upcoming weeks I will release a new version of the generator and my other tool (also change the license to that everything can be also used for commerical use).

Cheers

Thomas

Von: "Usman Bhatti" <[hidden email]>
An: "Moose-related development" <[hidden email]>
Gesendet: Montag, 16. April 2018 10:21:46
Betreff: [Moose-dev] Re: C# importer ?

On Mon, Apr 16, 2018 at 10:07 AM, Johan Fabry <[hidden email]> wrote:

Hi Usman,

Thanks for the reply! In the mean time I have been looking at using Roslyn: the .NET reflection API's, to make a XML dump of the structure of the code. I am almost there so I will keep going this route.

Excellent!

Now I can write a basic class structure with simple call information, and it's only 160 LOC of C# code. But the thing is that parsing is not enough, I also want the semantic analysis that gives type information (argument types, receiver type) and I don’t want to write that myself. Roslyn is supposed to give me that as well so I am investigating that now.

I hope it does.

Now, Mono.Cecil also does name resolution but sometimes I encountered limitations with it hence I would also support that you go for a solution provided by MS.

regards.

Usman

--

Johan Fabry, Senior Software Engineer.

[hidden email] | Email too brief? Here's why! http://emailcharter.org

From: Moose-dev [mailto:[hidden email]] On Behalf Of Usman Bhatti
Sent: Monday, April 16, 2018 9:59 AM
To: Moose-related development <[hidden email]>
Subject: [Moose-dev] Re: C# importer ?

Hi John,

Sorry for the late reply.

I worked on a C# (MSIL) importer a few years back while I was working in Inria.

This parser was based on Mono project and a library Mono.Cecil that provides API to access MSIL.

The importer I wrote was able to extract the basic information required to create FAMIX model (Classes, Namespaces, methods, attributes, invocations, accesses, params).

I think it might also have started to extract Generics but that part might not be complete. I didn't rewrite FAME/FAMIX for C# but used a library to transform FAME/FAMIX in Java to C#.

That meant that I could reuse the meta-model + MSE import/export from existing code.

But I haven't been able to work on it since 6 years now. But if you are interested, you may have a look here at the code here:

https://scm.gforge.inria.fr/anonscm/svn/verveinesharp/

One day when I get some time I would like to replace Mono.Cecil with Microsoft's parser that has been opensourced since.

HTH,

regards.

Usman

On Thu, Apr 12, 2018 at 12:09 PM, Johan Fabry <[hidden email]> wrote:

Hi all,

And now it looks like I will need to analyze a part of our own code, written in C#. Is there a parser for C# in Moose and if so, how extensive/solid is it?

TIA
--
Johan Fabry, Senior Software Engineer.
[hidden email] | Email too brief? Here's why! http://emailcharter.org

_______________________________________________
Moose-dev mailing list
[hidden email]
https://www.list.inf.unibe.ch/listinfo/moose-dev

_______________________________________________
Moose-dev mailing list
[hidden email]
https://www.list.inf.unibe.ch/listinfo/moose-dev

_______________________________________________
Moose-dev mailing list
[hidden email]
https://www.list.inf.unibe.ch/listinfo/moose-dev

--------------------------------------------

Stéphane Ducasse

http://stephane.ducasse.free.fr

http://www.synectique.eu / http://www.pharo.org

03 59 35 87 52

Assistant: Julie Jonas

FAX 03 59 57 78 50

TEL 03 59 35 86 16

S. Ducasse - Inria

40, avenue Halley,

Parc Scientifique de la Haute Borne, Bât.A, Park Plaza

Villeneuve d'Ascq 59650

France

_______________________________________________
Moose-dev mailing list
[hidden email]
https://www.list.inf.unibe.ch/listinfo/moose-dev

_______________________________________________
Moose-dev mailing list
[hidden email]
https://www.list.inf.unibe.ch/listinfo/moose-dev

--------------------------------------------

Stéphane Ducasse

http://stephane.ducasse.free.fr

http://www.synectique.eu / http://www.pharo.org

03 59 35 87 52

Assistant: Julie Jonas

FAX 03 59 57 78 50

TEL 03 59 35 86 16

S. Ducasse - Inria

40, avenue Halley,

Parc Scientifique de la Haute Borne, Bât.A, Park Plaza

Villeneuve d'Ascq 59650

France
_______________________________________________
Moose-dev mailing list
[hidden email]
https://www.list.inf.unibe.ch/listinfo/moose-dev
-- Nicolas Anquetil RMod team -- Inria Lille
_______________________________________________
Moose-dev mailing list
[hidden email]
https://www.list.inf.unibe.ch/listinfo/moose-dev

_______________________________________________
Moose-dev mailing list
[hidden email]
https://www.list.inf.unibe.ch/listinfo/moose-dev