Added help_docs feature.

pr_agent/git_providers/bitbucket_provider.py

@@ -67,6 +67,33 @@ class BitbucketProvider(GitProvider):
         except Exception:
             return ""
 
+    def get_git_repo_url(self, pr_url: str=None) -> str: #bitbucket does not support issue url, so ignore param
+        try:
+            parsed_url = urlparse(self.pr_url)
+            return f"{parsed_url.scheme}://{parsed_url.netloc}/{self.workspace_slug}/{self.repo_slug}.git"
+        except Exception as e:
+            get_logger().exception(f"url is not a valid merge requests url: {self.pr_url}")
+            return ""
+
+    def get_canonical_url_parts(self, repo_git_url:str=None, desired_branch:str=None) -> Tuple[str, str]:
+        scheme_and_netloc = None
+        if repo_git_url:
+            parsed_git_url = urlparse(repo_git_url)
+            scheme_and_netloc = parsed_git_url.scheme + "://" + parsed_git_url.netloc
+            repo_path = parsed_git_url.path.split('.git')[0][1:] #/<workspace>/<repo>.git -> <workspace>/<repo>
+            if repo_path.count('/') != 1:
+                get_logger().error(f"repo_git_url is not a valid git repo url: {repo_git_url}")
+                return ("", "")
+            workspace_name, project_name = repo_path.split('/')
+        else:
+            parsed_pr_url = urlparse(self.pr_url)
+            scheme_and_netloc = parsed_pr_url.scheme + "://" + parsed_pr_url.netloc
+            workspace_name, project_name = (self.workspace_slug, self.repo_slug)
+        prefix = f"{scheme_and_netloc}/{workspace_name}/{project_name}/src/{desired_branch}"
+        suffix = "" #None
+        return (prefix, suffix)
+
+
     def publish_code_suggestions(self, code_suggestions: list) -> bool:
         """
         Publishes code suggestions as comments on the PR.

pr_agent/git_providers/bitbucket_server_provider.py

@@ -138,6 +138,31 @@ class BitbucketServerProvider(GitProvider):
             return False
         return True
 
+    def get_git_repo_url(self, pr_url: str=None) -> str: #bitbucket server does not support issue url, so ignore param
+        try:
+            parsed_url = urlparse(self.pr_url)
+            return f"{parsed_url.scheme}://{parsed_url.netloc}/scm/{self.workspace_slug.lower()}/{self.repo_slug.lower()}.git"
+        except Exception as e:
+            get_logger().exception(f"url is not a valid merge requests url: {self.pr_url}")
+            return ""
+
+    def get_canonical_url_parts(self, repo_git_url:str=None, desired_branch:str=None) -> Tuple[str, str]:
+        workspace_name = None
+        project_name = None
+        if not repo_git_url:
+            workspace_name = self.workspace_slug
+            project_name = self.repo_slug
+        else:
+            repo_path = repo_git_url.split('.git')[0].split('scm/')[-1]
+            if repo_path.count('/') == 1:  # Has to have the form <workspace>/<repo>
+                workspace_name, project_name = repo_path.split('/')
+        if not workspace_name or not project_name:
+            get_logger().error(f"workspace_name or project_name not found in context, either git url: {repo_git_url} or uninitialized workspace/project.")
+            return ("", "")
+        prefix = f"{self.bitbucket_server_url}/projects/{workspace_name}/repos/{project_name}/browse"
+        suffix = f"?at=refs%2Fheads%2F{desired_branch}"
+        return (prefix, suffix)
+
     def set_pr(self, pr_url: str):
         self.workspace_slug, self.repo_slug, self.pr_num = self._parse_pr_url(pr_url)
         self.pr = self._get_pr()

pr_agent/git_providers/git_provider.py

@@ -1,6 +1,6 @@
 from abc import ABC, abstractmethod
 # enum EDIT_TYPE (ADDED, DELETED, MODIFIED, RENAMED)
-from typing import Optional
+from typing import Optional, Tuple
 
 from pr_agent.algo.types import FilePatchInfo
 from pr_agent.algo.utils import Range, process_description
@@ -14,6 +14,19 @@ class GitProvider(ABC):
     def is_supported(self, capability: str) -> bool:
         pass
 
+    #Given a url (issues or PR/MR) - get the .git repo url to which they belong. Needs to be implemented by the provider.
+    def get_git_repo_url(self, issues_or_pr_url: str) -> str:
+        get_logger().warning("Not implemented! Returning empty url")
+        return ""
+
+    # Given a git repo url, return prefix and suffix of the provider in order to view a given file belonging to that repo. Needs to be implemented by the provider.
+    # For example: For a git: https://git_provider.com/MY_PROJECT/MY_REPO.git then it should return ('https://git_provider.com/projects/MY_PROJECT/repos/MY_REPO', '?=<SOME HEADER>')
+    # so that to properly view the file: docs/readme.md -> <PREFIX>/docs/readme.md<SUFFIX> -> https://git_provider.com/projects/MY_PROJECT/repos/MY_REPO/docs/readme.md?=<SOME HEADER>)
+    def get_canonical_url_parts(self, repo_git_url:str, desired_branch:str) -> Tuple[str, str]:
+        get_logger().warning("Not implemented! Returning empty prefix and suffix")
+        return ("", "")
+
+
     @abstractmethod
     def get_files(self) -> list:
         pass

pr_agent/git_providers/github_provider.py

@@ -63,6 +63,53 @@ class GithubProvider(GitProvider):
     def is_supported(self, capability: str) -> bool:
         return True
 
+    def _get_owner_and_repo_path(self, given_url: str) -> str:
+        try:
+            repo_path = None
+            if 'issues' in given_url:
+                repo_path, _ = self._parse_issue_url(given_url)
+            elif 'pull' in given_url:
+                repo_path, _ = self._parse_pr_url(given_url)
+            elif given_url.endswith('.git'):
+                parsed_url = urlparse(given_url)
+                repo_path = (parsed_url.path.split('.git')[0])[1:] # /<owner>/<repo>.git -> <owner>/<repo>
+            if not repo_path:
+                get_logger().error(f"url is neither an issues url nor a pr url nor a valid git url: {given_url}. Returning empty result.")
+                return ""
+            return repo_path
+        except Exception as e:
+            get_logger().exception(f"unable to parse url: {given_url}. Returning empty result.")
+            return ""
+
+    def get_git_repo_url(self, issues_or_pr_url: str) -> str:
+        repo_path = self._get_owner_and_repo_path(issues_or_pr_url)
+        return f"{issues_or_pr_url.split(repo_path)[0]}{repo_path}.git"
+
+    def get_canonical_url_parts(self, repo_git_url:str, desired_branch:str) -> Tuple[str, str]:
+        owner = None
+        repo = None
+        scheme_and_netloc = None
+
+        if repo_git_url: #If user provided an external git url, which may be different than what this provider was initialized with, we cannot use self.repo
+            repo_path = self._get_owner_and_repo_path(repo_git_url)
+            parsed_git_url = urlparse(repo_git_url)
+            scheme_and_netloc = parsed_git_url.scheme + "://" + parsed_git_url.netloc
+            if repo_path.count('/') == 1: #Has to have the form <owner>/<repo>
+                owner, repo = repo_path.split('/')
+            else:
+                get_logger().error(f"Invalid repo_path: {repo_path} from repo_git_url: {repo_git_url}")
+                return ("", "")
+        if (not owner or not repo) and self.repo: #"else" - User did not provide an external git url, use self.repo object:
+            owner, repo = self.repo.split('/')
+            scheme_and_netloc = self.base_url_html
+        if not any([scheme_and_netloc, owner, repo]): #"else": Not invoked from a PR context,but no provided git url for context
+            get_logger().error(f"Unable to get canonical url parts since missing context (PR or explicit git url)")
+            return ("", "")
+
+        prefix = f"{scheme_and_netloc}/{owner}/{repo}/blob/{desired_branch}"
+        suffix = ""  # github does not add a suffix
+        return (prefix, suffix)
+
     def get_pr_url(self) -> str:
         return self.pr.html_url
 

pr_agent/git_providers/gitlab_provider.py

@@ -57,6 +57,38 @@ class GitLabProvider(GitProvider):
             return False
         return True
 
+    def _get_project_path_from_pr_or_issue_url(self, pr_or_issue_url: str) -> str:
+        repo_project_path = None
+        if 'issues' in pr_or_issue_url:
+            #replace 'issues' with 'merge_requests', since gitlab provider does not support issue urls, just to get the git repo url:
+            pr_or_issue_url = pr_or_issue_url.replace('issues', 'merge_requests')
+        if 'merge_requests' in pr_or_issue_url:
+            repo_project_path, _ = self._parse_merge_request_url(pr_or_issue_url)
+        if not repo_project_path:
+            get_logger().error(f"url is not a valid merge requests url: {pr_or_issue_url}")
+            return ""
+        return repo_project_path
+
+    def get_git_repo_url(self, issues_or_pr_url: str) -> str:
+        provider_url = issues_or_pr_url
+        repo_path = self._get_project_path_from_pr_or_issue_url(issues_or_pr_url)
+        if not repo_path:
+            return ""
+        return f"{provider_url.split(repo_path)[0]}{repo_path}.git"
+
+    def get_canonical_url_parts(self, repo_git_url:str=None, desired_branch:str=None) -> Tuple[str, str]:
+        repo_path = ""
+        if not repo_git_url and not self.pr_url:
+            get_logger().error("Cannot get canonical URL parts: missing either context PR URL or a repo GIT URL")
+            return ("", "")
+        if not repo_git_url: #Use PR url as context
+            repo_path = self._get_project_path_from_pr_or_issue_url(self.pr_url)
+        else: #Use repo git url
+            repo_path = repo_git_url.split('.git')[0].split('.com/')[-1]
+        prefix = f"{self.gitlab_url}/{repo_path}/-/blob/{desired_branch}"
+        suffix = "?ref_type=heads"  # gitlab cloud adds this suffix. gitlab server does not, but it is harmless.
+        return (prefix, suffix)
+
     @property
     def pr(self):
         '''The GitLab terminology is merge request (MR) instead of pull request (PR)'''