Collaborative peer to peer edition: Avoiding conflicts is better than solving conflicts

Collaborative edition is achieved by distinct sites that work independently on (a copy of) a shared document. Conflicts may arise during this process and must be solved by the collaborative editor. In pure Peer to Peer collaborative editing, no centralization nor locks nor time-stamps are used which make conflict resolution difficult. We propose an algorithm which relies on the notion or semantics dependence and avoids the need of any integration transformation to solve conflicts. Furthermore, it doesn't use any history file recording operations performed since starting the edition process. We show how to define editing operations for semi-structured documents i.e. XML-like trees, that are enriched with informations derived for free from the editing process. Then we define the semantics dependence relation required by the algorithm and we present preliminary results obtained by a prototype implementation.