Graph-Based Code Completion
Download as PPT, PDF1 like416 views
This document presents a graph-based pattern-oriented approach to context-sensitive source code completion. It builds a graph-based model of code, extracts features, and matches patterns in the model to suggestions from a code editing context. An evaluation of the approach on 24 real-world systems achieved 95% precision, 92% recall, and 93% F-score. The author observes that semantic relationships could help improve pattern matching compared to the current syntactic approach.
Graph-Based Code Completion
- 1. Graph-Based Pattern-Oriented, ContextSensitive Source Code Completion Nguyen, T.T. ; Nguyen, H.A. ; Tamrawi, A. ; Nguyen, H.V. ; Al-Kofahi, J. ; Nguyen, T.N. Presented By: Mohammad Masudur Rahman
- 2. Contents Code Completion Thesis Statement Motivating Example Terminologies Methodology Empirical Evaluation & Results My Observation & Future Thoughts 2
- 3. Code Completion 3 Built-in feature of modern all IDEs Speed up development Longer Identifier names for program comprehension Less overhead for developers Mostly single variable, method supports- API packages Template based support – control structure, event handling and others
- 4. Thesis Statement Novel approach with graph-based code completion Graph based feature extracting, searching, ranking of API usage pattern, matching with editing context of current code. Empirical evaluation shows correctness and usefulness- 95% precision, 92% recall, 93% f-score over 24 real world systems 4
- 5. Motivating Example (Single-line) 5 Fig 1: Current State of Code Completion (Eclipse 3.6)
- 6. Motivating Example (Multi-line) 6 Fig 2: SWT Usage Example
- 7. Motivating Example (Query) Fig 3: SWT Query Example 7
- 8. Terminologies GRAPACC API Usage Pattern Groum Based Model Context-sensitive Weight 8
- 9. GRAPACC Graph-Based Pattern-Oriented Context-Sensitive Code 9 Completion
- 10. API Usage Pattern 10 Fig 4: SWT API Usage
- 11. Groum Based Model 11 Fig 5: Groum Conversion
- 12. Context-Sensitive Weight 1 w f (q) = (d + 1) Wf (q)=Context-sensitive weight of feature q q= feature of Query, Q d=distance to the closest token in Groum Model 12
- 13. Methodology Query Processing and Feature Extraction Pattern Managing, Searching and Ranking Pattern Oriented Code Completion 13
- 14. Query Processing and Feature Extraction Tokenizing Partial Parsing Groum Building Feature Extracting and Weighting 14
- 15. Tokenizing, Partial Parsing Lexical analysis Preserves keywords related to control structure, rest are removed elsewhere but saved Eclipse java parser PPA tool returns AST (Abstract Syntax Tree) Unresolved nodes assigned ‘Unknown Type’ 15
- 16. Groum Building Groum from AST Unresolved nodes are discarded but considered as tokens Query converted to the following Groum 16 Fig 6: Groum of Query
- 17. Feature Extraction & Weighting Groum nodes mapped to tokens in tokenization step Feature extracted from Groum for path, L<=3 3 factors contribute to feature weight Structured based factor (size) Structured based factor (centrality) User based factor 17
- 18. Feature Extraction & Weighting ws(q)= size based weight for feature, q of Query, Q (w(q)=1+size(q); 1<= size(q)<=3) wc(q)= Centrality based weight for feature, q of Query, Q (wc(q)=n / s, n=no of neighbors, s=size) (wf(q)=1/(d+1)), distance between focus node and the closest token in feature path Groum Model 18
- 19. Feature Extraction & Weighting 19 w(q)= total weight for feature, q of Query, Q ws(q)= size based weight for feature, q of Query, Q wc(q)= Centrality based weight for feature, q of Query, Q wf(q)= used based weight for feature, q of Query, Q
- 20. Pattern Managing, Searching and Ranking Pr(P) is popularity of pattern P = frequency of Pattern P Weight of feature p in Pattern P using inverse indexing Np,P=occurrence 20 of feature p in P, NP=total no of features in P Np=No of patterns containing p, N=total no of pattern in database
- 21. Pattern Managing, Searching and Ranking 21 For each feature p, L(p), a list of patterns from which p can be extracted p for pattern feature, q for query feature Now sim(p,q)>∂,then p is added to F, set of mapped features for q For each pєF, top n ranked patterns from L(p) is added to C, candidate patterns for relevance computation Now for each P in C, compute fit(P,Q)
- 22. Feature Similarity is a name-based similarity between two features given that feature is a collection of labels and has the form Of X.Y.Z where X=package name Y=class name Z=method name 22
- 23. Name-based Similarity (nsim) = 23 wsim(X, X’) is word-based similarity X, X’ are broken down and two sequence of words L(x) and L(y) Similarity computed as Lo/Lm Lo is length of LCS, Lm is average length of two sequences
- 25. Pattern Matching SM(P,Q)=total weight of Matched feature pair Fit (P, Q)=Relevance degree between P and Q 25 Pr(P)=Popularity of Pattern P
- 26. Pattern Oriented Code Completion Matched pattern is selected and corresponding node in Groum is matched The missing nodes are fulfilled with code 26
- 27. Empirical Evaluation Precision Recall F-score java.io, java.util :API used as library 28 real world open-source systems 4 for training, 24 for testing 27
- 29. My Observation Planning to use semantic web technology Data and control dependency relationship can be improved using semantic relationship like conceptual similarity Matching of pattern is complex and errorprone, semantic score can be beneficial 29