feature/azure devops integration

.gitignore

@@ -19,4 +19,5 @@ venv
 .*.sw?
 
 
-.env
+.env
+.DS_Store

app/data_sources/azuredevops.py

@@ -0,0 +1,117 @@
+import datetime
+import logging
+from typing import Dict, List
+import requests
+import base64
+import urllib.parse
+
+from azure.devops.connection import Connection
+from msrest.authentication import BasicAuthentication
+
+from data_source_api.base_data_source import BaseDataSource, ConfigField, HTMLInputType
+from data_source_api.basic_document import DocumentType, BasicDocument
+from data_source_api.exception import InvalidDataSourceConfig
+from index_queue import IndexQueue
+from pydantic import BaseModel
+from parsers.html import html_to_text
+from data_source_api.utils import parse_with_workers
+
+logger = logging.getLogger(__name__)
+
+class DevOpsConfig(BaseModel):
+    organization_url: str
+    access_token: str
+    project_name: str
+    query_id: str
+
+class AzuredevopsDataSource(BaseDataSource):
+    @staticmethod
+    def get_config_fields() -> List[ConfigField]:
+        return [
+            ConfigField(label="AzureDevOps organization URL", placeholder="https://dev.azure.com/org", name="organization_url"),
+            ConfigField(label="Personal Access Token", name="access_token", type=HTMLInputType.PASSWORD),
+            ConfigField(label="Project Name", name="project_name"),
+            ConfigField(label="Query ID", name="query_id"),
+        ]
+
+    @staticmethod
+    def validate_config(config: Dict) -> None:
+        try:
+            devops_config = DevOpsConfig(**config)
+            credentials = BasicAuthentication('', devops_config.access_token)
+            connection = Connection(base_url=devops_config.organization_url, creds=credentials)
+            core_client = connection.clients.get_core_client()
+            core_client.get_projects()
+        except Exception as e:
+            raise InvalidDataSourceConfig from e
+
+    def __init__(self, *args, **kwargs):
+        super().__init__(*args, **kwargs)
+        devops_config = DevOpsConfig(**self._config)
+        self._query_id = devops_config.query_id.strip()
+        self._access_token = devops_config.access_token.strip()
+        self._project_name = devops_config.project_name.strip()
+        self._organization_url = devops_config.organization_url.strip()
+        credentials = BasicAuthentication('', self._access_token)
+        connection = Connection(base_url=self._organization_url, creds=credentials)
+        self._work_item_tracking_client = connection.clients.get_work_item_tracking_client()
+
+    def _parse_documents_worker(self, raw_docs: List[Dict]):
+        logging.info(f'Worker parsing {len(raw_docs)} documents')
+
+        parsed_docs = []
+        total_fed = 0
+        for item in raw_docs:
+            for raw_page in item['comments']:
+                create_date = datetime.datetime.strptime(raw_page['createdDate'], "%Y-%m-%dT%H:%M:%S.%fZ")
+                if create_date < self._last_index_time:
+                    continue
+                author = raw_page['createdBy']['displayName']
+                workitem_id = raw_page['workItemId']
+                title = str(raw_page['workItemId']) + ' - ' + raw_page['createdBy']['displayName']
+                html_content = raw_page['text']
+                plain_text = html_to_text(html_content)
+                author_image_url = raw_page['createdBy']['_links']['avatar']['href']
+                url = f"{self._organization_url}/{urllib.parse.quote(self._project_name)}/_workitems/edit/{raw_page['workItemId']}".strip()
+
+                parsed_docs.append(BasicDocument(
+                    id=workitem_id,
+                    data_source_id=self._data_source_id,
+                    author=author,
+                    author_image_url=author_image_url,
+                    content=plain_text,
+                    type=DocumentType.COMMENT,
+                    title=title,
+                    timestamp=create_date,
+                    location=self._project_name,
+                    url=url
+                ))
+
+                if len(parsed_docs) >= 50:
+                    total_fed += len(parsed_docs)
+                    IndexQueue.get_instance().put(docs=parsed_docs)
+                    parsed_docs = []
+
+        IndexQueue.get_instance().put(docs=parsed_docs)
+        total_fed += len(parsed_docs)
+        if total_fed > 0:
+            logging.info(f'Worker fed {total_fed} documents')
+
+
+    def _list_work_item_comments(self, work_item_url) -> List[Dict]:
+        authorization = str(base64.b64encode(bytes(':'+self._access_token, 'ascii')), 'ascii')
+        headers = {
+            'Accept': 'application/json',
+            'Authorization': 'Basic '+authorization
+        }
+        return requests.get(url=work_item_url + '/comments', headers=headers).json()
+
+    def _feed_new_documents(self) -> None:
+        logger.info('Feeding new Azure DevOps Work Items')
+        raw_docs = []
+        work_item_results = self._work_item_tracking_client.query_by_id(self._query_id)
+        for work_item in work_item_results.work_items:
+            result = self._list_work_item_comments(work_item.url)
+            if result['totalCount'] > 0:
+                raw_docs.append(result)
+        parse_with_workers(self._parse_documents_worker, raw_docs)

app/requirements.txt

@@ -22,3 +22,4 @@ python-pptx
 alembic
 rocketchat-API
 mattermostdriver
+azure-devops

docs/data-sources/azuredevops/azuredevops.md

@@ -0,0 +1,16 @@
+# Setting up Azure DevOps Data Source
+Please note this will only index Work Items returned by your Query
+
+1. Navigate to the settings menu in the top-right hand corner of the screen and select Personal Access Tokens.
+![Settings](./Settings.png)
+2. Click on the new option.
+![NewButton](./NewButton.png)
+1. Complete the form, and set the expiration date to custom. Select the furthest expiration date possible. Make sure to only provide read only permissions.
+![TokenForm](./TokenForm.png)
+1. Hit Create and copy the token from the next window.
+2. Navigate to your Project and go to Boards > Queries. Select your query from the list.
+![QuerySelect](./QuerySelect.png)
+1. Copy the Query ID from the URL in the address bar.
+![AddressBar](./AddressBar.png)
+1. Go to Gerev and input all of the data into the fields.
+![Gerev](./Gerev.png)

ui/src/components/data-source-panel.tsx

@@ -297,6 +297,21 @@ export default class DataSourcePanel extends React.Component<DataSourcePanelProp
                                     <p>Note that the url must begin with either http:// or https://</p>
                                  </span>
                               )}
+
+                              {
+                                 this.state.selectedDataSource.value === 'azuredevops' && (
+                                    <span className="flex flex-col leading-9  text-xl text-white">
+                                       <span>1. {'Go to your Azure DevOps -> top-right Person with the Gear -> Personal Access Token'}</span>
+                                       <span>2. {'Fill out the details, and set your expiration date'}</span>
+                                       <span>3. {"Make sure Read under Work Items is checked and save your token"}</span>
+                                       <span>4. {"Copy the token and paste it here"}</span>
+                                       <span>5. {"Add your Project Name here"}</span>
+                                       <span>6. {"Navigate to Your Project then Boards > Queries"}</span>
+                                       <span>7. {"Select the query that you want from the list and get the id from the end of the URL"}</span>
+                                       <span>ex. {"https://dev.azure.com/{org}/{project}/_queries/query/{query_id}/"}</span>
+                                    </span>
+                                 )
+                              }
                            </div>
 
                            <div className="flex flex-row flex-wrap items-end mt-4">