Merge pull request #255 from pzarfos/issue_138_codecommit_describe

Enhancement of AWS CodeCommit support in PR-Agent

INSTALL.md

@@ -309,7 +309,9 @@ Example IAM permissions to that user to allow access to CodeCommit:
                 "codecommit:Get*",
                 "codecommit:List*",
                 "codecommit:PostComment*",
-                "codecommit:PutCommentReaction"
+                "codecommit:PutCommentReaction",
+                "codecommit:UpdatePullRequestDescription",
+                "codecommit:UpdatePullRequestTitle"                
             ],
             "Resource": "*"
         }

README.md

@@ -80,7 +80,7 @@ CodiumAI `PR-Agent` is an open-source tool aiming to help developers review pull
 | TOOLS | Review                                      |   :white_check_mark:    |   :white_check_mark:    |   :white_check_mark:       |   :white_check_mark:    |
 |       | ⮑ Inline review                             |   :white_check_mark:    |   :white_check_mark:    |           |          |
 |       | Ask                                         |   :white_check_mark:    |   :white_check_mark:    |   :white_check_mark:          |
-|       | Auto-Description                            |   :white_check_mark:    |   :white_check_mark:    |           |          |
+|       | Auto-Description                            |   :white_check_mark:    |   :white_check_mark:    |           |   :white_check_mark:    |
 |       | Improve Code                                |   :white_check_mark:    |   :white_check_mark:    |           |          |
 |       | ⮑ Extended                             |   :white_check_mark:    |   :white_check_mark:    |           |          |
 |       | Reflect and Review                          |   :white_check_mark:    |                         |           |          |

pr_agent/git_providers/codecommit_client.py

@@ -64,7 +64,7 @@ class CodeCommitClient:
         """
         Get the differences between two commits in CodeCommit.
 
-        Parameters:
+        Args:
         - repo_name: Name of the repository
         - destination_commit: Commit hash you want to merge into (the "before" hash) (usually on the main or master branch)
         - source_commit: Commit hash of the code you are adding (the "after" branch)
@@ -73,8 +73,8 @@ class CodeCommitClient:
         - List of CodeCommitDifferencesResponse objects
 
         Boto3 Documentation:
-        aws codecommit get-differences
+        - aws codecommit get-differences
-        https://boto3.amazonaws.com/v1/documentation/api/latest/reference/services/codecommit/client/get_differences.html
+        - https://boto3.amazonaws.com/v1/documentation/api/latest/reference/services/codecommit/client/get_differences.html
         """
         if self.boto_client is None:
             self._connect_boto_client()
@@ -101,7 +101,7 @@ class CodeCommitClient:
         """
         Retrieve a file from CodeCommit.
 
-        Parameters:
+        Args:
         - repo_name: Name of the repository
         - file_path: Path to the file you are retrieving
         - sha_hash: Commit hash of the file you are retrieving
@@ -110,8 +110,8 @@ class CodeCommitClient:
         - File contents
 
         Boto3 Documentation:
-        aws codecommit get_file
+        - aws codecommit get_file
-        https://boto3.amazonaws.com/v1/documentation/api/latest/reference/services/codecommit/client/get_file.html
+        - https://boto3.amazonaws.com/v1/documentation/api/latest/reference/services/codecommit/client/get_file.html
         """
         if not file_path:
             return ""
@@ -137,15 +137,15 @@ class CodeCommitClient:
         """
         Get a information about a CodeCommit PR.
 
-        Parameters:
+        Args:
         - pr_number: The PR number you are requesting
 
         Returns:
         - CodeCommitPullRequestResponse object
 
         Boto3 Documentation:
-        aws codecommit get_pull_request
+        - aws codecommit get_pull_request
-        https://boto3.amazonaws.com/v1/documentation/api/latest/reference/services/codecommit/client/get_pull_request.html
+        - https://boto3.amazonaws.com/v1/documentation/api/latest/reference/services/codecommit/client/get_pull_request.html
         """
         if self.boto_client is None:
             self._connect_boto_client()
@@ -164,11 +164,48 @@ class CodeCommitClient:
 
         return CodeCommitPullRequestResponse(response.get("pullRequest", {}))
 
+    def publish_description(self, pr_number: int, pr_title: str, pr_body: str):
+        """
+        Set the title and description on a pull request
+
+        Args:
+        - pr_number: the AWS CodeCommit pull request number
+        - pr_title: title of the pull request
+        - pr_body: body of the pull request
+
+        Returns:
+        - None
+
+        Boto3 Documentation:
+        - aws codecommit update_pull_request_title
+        - https://boto3.amazonaws.com/v1/documentation/api/latest/reference/services/codecommit/client/update_pull_request_title.html
+        - aws codecommit update_pull_request_description
+        - https://boto3.amazonaws.com/v1/documentation/api/latest/reference/services/codecommit/client/update_pull_request_description.html
+        """
+        if self.boto_client is None:
+            self._connect_boto_client()
+
+        try:
+            self.boto_client.update_pull_request_title(pullRequestId=str(pr_number), title=pr_title)
+            self.boto_client.update_pull_request_description(pullRequestId=str(pr_number), description=pr_body)
+        except botocore.exceptions.ClientError as e:
+            if e.response["Error"]["Code"] == 'PullRequestDoesNotExistException':
+                raise ValueError(f"PR number does not exist: {pr_number}") from e
+            if e.response["Error"]["Code"] == 'InvalidTitleException':
+                raise ValueError(f"Invalid title for PR number: {pr_number}") from e
+            if e.response["Error"]["Code"] == 'InvalidDescriptionException':
+                raise ValueError(f"Invalid description for PR number: {pr_number}") from e
+            if e.response["Error"]["Code"] == 'PullRequestAlreadyClosedException':
+                raise ValueError(f"PR is already closed: PR number: {pr_number}") from e
+            raise ValueError(f"Boto3 client error calling publish_description") from e
+        except Exception as e:
+            raise ValueError(f"Error calling publish_description") from e
+
     def publish_comment(self, repo_name: str, pr_number: int, destination_commit: str, source_commit: str, comment: str):
         """
         Publish a comment to a pull request
 
-        Parameters:
+        Args:
         - repo_name: name of the repository
         - pr_number: number of the pull request
         - destination_commit: The commit hash you want to merge into (the "before" hash) (usually on the main or master branch)
@@ -179,8 +216,8 @@ class CodeCommitClient:
         - None
 
         Boto3 Documentation:
-        aws codecommit post_comment_for_pull_request
+        - aws codecommit post_comment_for_pull_request
-        https://boto3.amazonaws.com/v1/documentation/api/latest/reference/services/codecommit/client/post_comment_for_pull_request.html
+        - https://boto3.amazonaws.com/v1/documentation/api/latest/reference/services/codecommit/client/post_comment_for_pull_request.html
         """
         if self.boto_client is None:
             self._connect_boto_client()

pr_agent/git_providers/codecommit_provider.py

@@ -1,5 +1,6 @@
 import logging
 import os
+import re
 from collections import Counter
 from typing import List, Optional, Tuple
 from urllib.parse import urlparse
@@ -153,17 +154,27 @@ class CodeCommitProvider(GitProvider):
         return self.diff_files
 
     def publish_description(self, pr_title: str, pr_body: str):
-        return ""  # not implemented yet
+        try:
+            self.codecommit_client.publish_description(
+                pr_number=self.pr_num,
+                pr_title=pr_title,
+                pr_body=CodeCommitProvider._add_additional_newlines(pr_body),
+            )
+        except Exception as e:
+            raise ValueError(f"CodeCommit Cannot publish description for PR: {self.pr_num}") from e    
 
     def publish_comment(self, pr_comment: str, is_temporary: bool = False):
         if is_temporary:
             logging.info(pr_comment)
             return
 
+        pr_comment = CodeCommitProvider._remove_markdown_html(pr_comment)
+        pr_comment = CodeCommitProvider._add_additional_newlines(pr_comment)
+
         try:
             self.codecommit_client.publish_comment(
                 repo_name=self.repo_name,
-                pr_number=str(self.pr_num),
+                pr_number=self.pr_num,
                 destination_commit=self.pr.destination_commit,
                 source_commit=self.pr.source_commit,
                 comment=pr_comment,
@@ -200,7 +211,7 @@ class CodeCommitProvider(GitProvider):
         Returns a dictionary of languages, containing the percentage of each language used in the PR.
 
         Returns:
-            dict: A dictionary where each key is a language name and the corresponding value is the percentage of that language in the PR.
+        - dict: A dictionary where each key is a language name and the corresponding value is the percentage of that language in the PR.
         """
         commit_files = self.get_files()
         filenames = [ item.filename for item in commit_files ]
@@ -251,11 +262,20 @@ class CodeCommitProvider(GitProvider):
 
     @staticmethod
     def _parse_pr_url(pr_url: str) -> Tuple[str, int]:
+        """
+        Parse the CodeCommit PR URL and return the repository name and PR number.
+
+        Args:
+        - pr_url: the full AWS CodeCommit pull request URL
+
+        Returns:
+        - Tuple[str, int]: A tuple containing the repository name and PR number.
+        """
         # Example PR URL:
         # https://us-east-1.console.aws.amazon.com/codesuite/codecommit/repositories/__MY_REPO__/pull-requests/123456"
         parsed_url = urlparse(pr_url)
 
-        if "us-east-1.console.aws.amazon.com" not in parsed_url.netloc:
+        if not CodeCommitProvider._is_valid_codecommit_hostname(parsed_url.netloc):
             raise ValueError(f"The provided URL is not a valid CodeCommit URL: {pr_url}")
 
         path_parts = parsed_url.path.strip("/").split("/")
@@ -278,6 +298,22 @@ class CodeCommitProvider(GitProvider):
 
         return repo_name, pr_number
 
+    @staticmethod
+    def _is_valid_codecommit_hostname(hostname: str) -> bool:
+        """
+        Check if the provided hostname is a valid AWS CodeCommit hostname.
+
+        This is not an exhaustive check of AWS region names, 
+        but instead uses a regex to check for matching AWS region patterns.
+
+        Args:
+        - hostname: the hostname to check
+
+        Returns:
+        - bool: True if the hostname is valid, False otherwise.
+        """
+        return re.match(r"^[a-z]{2}-(gov-)?[a-z]+-\d\.console\.aws\.amazon\.com$", hostname) is not None
+
     def _get_pr(self):
         response = self.codecommit_client.get_pr(self.pr_num)
 
@@ -306,13 +342,52 @@ class CodeCommitProvider(GitProvider):
         return ""  # not implemented yet
 
     @staticmethod
-    def _get_edit_type(codecommit_change_type):
+    def _add_additional_newlines(body: str) -> str:
+        """
+        Replace single newlines in a PR body with double newlines.
+
+        CodeCommit Markdown does not seem to render as well as GitHub Markdown,
+        so we add additional newlines to the PR body to make it more readable in CodeCommit.
+
+        Args:
+        - body: the PR body
+
+        Returns:
+        - str: the PR body with the double newlines added
+        """
+        return re.sub(r'(?<!\n)\n(?!\n)', '\n\n', body)
+
+    @staticmethod
+    def _remove_markdown_html(comment: str) -> str:
+        """
+        Remove the HTML tags from a PR comment.
+
+        CodeCommit Markdown does not seem to render as well as GitHub Markdown,
+        so we remove the HTML tags from the PR comment to make it more readable in CodeCommit.
+
+        Args:
+        - comment: the PR comment
+
+        Returns:
+        - str: the PR comment with the HTML tags removed
+        """
+        comment = comment.replace("<details>", "")
+        comment = comment.replace("</details>", "")
+        comment = comment.replace("<summary>", "")
+        comment = comment.replace("</summary>", "")
+        return comment
+
+    @staticmethod
+    def _get_edit_type(codecommit_change_type: str):
         """
         Convert the CodeCommit change type string to the EDIT_TYPE enum.
         The CodeCommit change type string is returned from the get_differences SDK method.
 
+        Args:
+        - codecommit_change_type: the CodeCommit change type string
+
         Returns:
-            An EDIT_TYPE enum representing the modified, added, deleted, or renamed file in the PR diff.
+        - An EDIT_TYPE enum representing the modified, added, deleted, or renamed file in the PR diff.
         """
         t = codecommit_change_type.upper()
         edit_type = None
@@ -333,6 +408,12 @@ class CodeCommitProvider(GitProvider):
         The returned extensions will include the dot "." prefix,
         to accommodate for the dots in the existing language_extension_map settings.
         Filenames with no extension will return an empty string for the extension.
+
+        Args:
+        - filenames: a list of filenames
+
+        Returns:
+        - list: A list of file extensions, including the dot "." prefix.
         """
         extensions = []
         for filename in filenames:
@@ -349,6 +430,12 @@ class CodeCommitProvider(GitProvider):
         Return a dictionary containing the programming language name (as the key),
         and the percentage that language is used (as the value),
         given a list of file extensions.
+
+        Args:
+        - extensions: a list of file extensions
+
+        Returns:
+        - dict: A dictionary where each key is a language name and the corresponding value is the percentage of that language in the PR.
         """
         total_files = len(extensions)
         if total_files == 0:

tests/unittest/test_codecommit_provider.py

@@ -26,11 +26,48 @@ class TestCodeCommitFile:
 
 class TestCodeCommitProvider:
     def test_parse_pr_url(self):
+        # Test that the _parse_pr_url() function can extract the repo name and PR number from a CodeCommit URL
         url = "https://us-east-1.console.aws.amazon.com/codesuite/codecommit/repositories/my_test_repo/pull-requests/321"
         repo_name, pr_number = CodeCommitProvider._parse_pr_url(url)
         assert repo_name == "my_test_repo"
         assert pr_number == 321
 
+    def test_is_valid_codecommit_hostname(self):
+        # Test the various AWS regions
+        assert CodeCommitProvider._is_valid_codecommit_hostname("af-south-1.console.aws.amazon.com")
+        assert CodeCommitProvider._is_valid_codecommit_hostname("ap-east-1.console.aws.amazon.com")
+        assert CodeCommitProvider._is_valid_codecommit_hostname("ap-northeast-1.console.aws.amazon.com")
+        assert CodeCommitProvider._is_valid_codecommit_hostname("ap-northeast-2.console.aws.amazon.com")
+        assert CodeCommitProvider._is_valid_codecommit_hostname("ap-northeast-3.console.aws.amazon.com")
+        assert CodeCommitProvider._is_valid_codecommit_hostname("ap-south-1.console.aws.amazon.com")
+        assert CodeCommitProvider._is_valid_codecommit_hostname("ap-south-2.console.aws.amazon.com")
+        assert CodeCommitProvider._is_valid_codecommit_hostname("ap-southeast-1.console.aws.amazon.com")
+        assert CodeCommitProvider._is_valid_codecommit_hostname("ap-southeast-2.console.aws.amazon.com")
+        assert CodeCommitProvider._is_valid_codecommit_hostname("ap-southeast-3.console.aws.amazon.com")
+        assert CodeCommitProvider._is_valid_codecommit_hostname("ap-southeast-4.console.aws.amazon.com")
+        assert CodeCommitProvider._is_valid_codecommit_hostname("ca-central-1.console.aws.amazon.com")
+        assert CodeCommitProvider._is_valid_codecommit_hostname("eu-central-1.console.aws.amazon.com")
+        assert CodeCommitProvider._is_valid_codecommit_hostname("eu-central-2.console.aws.amazon.com")
+        assert CodeCommitProvider._is_valid_codecommit_hostname("eu-north-1.console.aws.amazon.com")
+        assert CodeCommitProvider._is_valid_codecommit_hostname("eu-south-1.console.aws.amazon.com")
+        assert CodeCommitProvider._is_valid_codecommit_hostname("eu-south-2.console.aws.amazon.com")
+        assert CodeCommitProvider._is_valid_codecommit_hostname("eu-west-1.console.aws.amazon.com")
+        assert CodeCommitProvider._is_valid_codecommit_hostname("eu-west-2.console.aws.amazon.com")
+        assert CodeCommitProvider._is_valid_codecommit_hostname("eu-west-3.console.aws.amazon.com")
+        assert CodeCommitProvider._is_valid_codecommit_hostname("il-central-1.console.aws.amazon.com")
+        assert CodeCommitProvider._is_valid_codecommit_hostname("me-central-1.console.aws.amazon.com")
+        assert CodeCommitProvider._is_valid_codecommit_hostname("me-south-1.console.aws.amazon.com")
+        assert CodeCommitProvider._is_valid_codecommit_hostname("sa-east-1.console.aws.amazon.com")
+        assert CodeCommitProvider._is_valid_codecommit_hostname("us-east-1.console.aws.amazon.com")
+        assert CodeCommitProvider._is_valid_codecommit_hostname("us-east-2.console.aws.amazon.com")
+        assert CodeCommitProvider._is_valid_codecommit_hostname("us-gov-east-1.console.aws.amazon.com")
+        assert CodeCommitProvider._is_valid_codecommit_hostname("us-gov-west-1.console.aws.amazon.com")
+        assert CodeCommitProvider._is_valid_codecommit_hostname("us-west-1.console.aws.amazon.com")
+        assert CodeCommitProvider._is_valid_codecommit_hostname("us-west-2.console.aws.amazon.com")
+        # Test non-AWS regions
+        assert not CodeCommitProvider._is_valid_codecommit_hostname("no-such-region.console.aws.amazon.com")
+        assert not CodeCommitProvider._is_valid_codecommit_hostname("console.aws.amazon.com")
+
     # Test that an error is raised when an invalid CodeCommit URL is provided to the set_pr() method of the CodeCommitProvider class.
     # Generated by CodiumAI
     def test_invalid_codecommit_url(self):
@@ -106,6 +143,7 @@ class TestCodeCommitProvider:
         assert percentages == {}
 
     def test_get_edit_type(self):
+        # Test that the _get_edit_type() function can convert a CodeCommit letter to an EDIT_TYPE enum
         assert CodeCommitProvider._get_edit_type("A") == EDIT_TYPE.ADDED
         assert CodeCommitProvider._get_edit_type("D") == EDIT_TYPE.DELETED
         assert CodeCommitProvider._get_edit_type("M") == EDIT_TYPE.MODIFIED
@@ -117,3 +155,18 @@ class TestCodeCommitProvider:
         assert CodeCommitProvider._get_edit_type("r") == EDIT_TYPE.RENAMED
 
         assert CodeCommitProvider._get_edit_type("X") is None
+
+    def test_add_additional_newlines(self):
+        # a short string to test adding double newlines
+        input = "abc\ndef\n\n___\nghi\njkl\nmno\n\npqr\n"
+        expect = "abc\n\ndef\n\n___\n\nghi\n\njkl\n\nmno\n\npqr\n\n"
+        assert CodeCommitProvider._add_additional_newlines(input) == expect
+        # a test example from a real PR
+        input = "## PR Type:\nEnhancement\n\n___\n## PR Description:\nThis PR introduces a new feature to the script, allowing users to filter servers by name.\n\n___\n## PR Main Files Walkthrough:\n`foo`: The foo script has been updated to include a new command line option `-f` or `--filter`.\n`bar`: The bar script has been updated to list stopped servers.\n"
+        expect = "## PR Type:\n\nEnhancement\n\n___\n\n## PR Description:\n\nThis PR introduces a new feature to the script, allowing users to filter servers by name.\n\n___\n\n## PR Main Files Walkthrough:\n\n`foo`: The foo script has been updated to include a new command line option `-f` or `--filter`.\n\n`bar`: The bar script has been updated to list stopped servers.\n\n"
+        assert CodeCommitProvider._add_additional_newlines(input) == expect
+
+    def test_remove_markdown_html(self):
+        input = "## PR Feedback\n<details><summary>Code feedback:</summary>\nfile foo\n</summary>\n"
+        expect = "## PR Feedback\nCode feedback:\nfile foo\n\n"
+        assert CodeCommitProvider._remove_markdown_html(input) == expect