Searching code based on learned programming construct patterns and NLP similarity

Patent metadata

Field	Value
Publication number	US-9946786-B2
Application number	US-201615067997-A
Country	US
Kind code	B2
Filing date	Mar 11, 2016
Priority date	Mar 23, 2015
Publication date	Apr 17, 2018
Grant date	Apr 17, 2018

Abstract

An approach is provided to ingest software source code files into a question/answering (QA) system. During ingestion, source code blocks are classified to identify one or more constructs in the blocks as being domain-specific. Relationships between the blocks are then mapped. Software compliance regulations are ingested into the QA system. Using the QA system, a source code file is analyzed for compliance to the software compliance regulations. The analysis identifies code sections within the source code file as being domain-specific and subject to the ingested set of software compliance regulations.

First claim

The invention claimed is:

1. A method implemented by an information handling system that includes a memory having executable instructions stored thereon and a processor, where the processor executes the instructions to perform the method steps, the method steps comprising:
building a domain-specific knowledge base of a domain by ingesting a plurality of source code files into the domain-specific knowledge base utilized by a question/answering (QA) system, wherein the ingesting further comprises:
ingesting a set of software compliance regulations corresponding to the domain into the domain-specific knowledge base;
selecting one of the plurality of source code files that includes a plurality of source code sections;
classifying one of the plurality of source code sections as a domain-specific source code section; and
classifying a construct in the domain-specific source code section as a domain-specific construct;
retrieving a new source code file that comprises a plurality of new source code sections, wherein a selected one of the plurality of new source code sections includes a new construct;
generating a natural language question based on the new construct; and
processing, by the QA system, the natural language question using the domain-specific knowledge base, wherein the processing further comprises:
matching the new construct to the domain-specific construct;
determining, in response to the matching, that the selected source code section is subject to the ingested set of software compliance regulations; and
generating an answer, in response the determining, that indicates the new source code section is subject to the set of software compliance regulations.

2. The method of claim 1 further comprising:
identifying one or more domain-specific relationships between the plurality of new code sections of the new source code file; and
using the QA system, analyzing compliance of the new source code file by further determining whether the identified one or more domain-specific relationships are subject to the ingested set of software compliance regulations.

3. The method of claim 1 further comprising:
formulating a different natural language question pertaining to the new source code file being domain specific and subject to the ingested set of software compliance regulations;
submitting the different natural language question to the QA system; and
receiving a response from the QA system that indicates whether the new source code file is subject to the ingested set of software compliance regulations.

4. The method of claim 1 further comprising:
receiving, from the QA system, a confidence value corresponding to the answer; and in response to the confidence value exceeding a threshold,
generating a report that indicates the new source code section is subject to the ingested set of software compliance regulations.

5. The method of claim 4 further comprising:
including the set of software compliance regulations in the report.

Assignees

• IBM

Inventors

• Allen Corville O
• Freed Andrew R
• Price Dana L

Classifications

• G06F11/3688

  for test execution, e.g. scheduling of test suites · CPC title

• G06F8/71

  Version control (security arrangements therefor G06F21/57); Configuration management · CPC title

• G06F8/36 Primary

  Software reuse · CPC title

• G06F16/3344

  using natural language analysis · CPC title

• G06F8/433

  Dependency analysis; Data or control flow analysis · CPC title