Jira source connector: add status filter and option to download attachments to issues (#616)

Author: Paul-Cornell

snippets/general-shared-text/jira-api-placeholders.mdx

@@ -6,4 +6,6 @@
 - `<project-id>`: The ID of a target project in Jira to access.
 - `<board-id>`: The ID of a target board in Jira to access.
 - `<issue-id>`: The ID of a target issue in Jira to access.
-- Set `cloud` to `true` to specify using Jira Cloud or `false` to specify using Jira Data Center. The default is to use Jira Data Center.
+- `<status>`: The name of a status to filter Jira issues by.
+- Set `download_attachments` to `true` to download attachments from Jira issues. The default is `false`.
+- Set `cloud` to `true` to specify using Jira Cloud or `false` to specify using Jira Data Center. The default is to use Jira Data Center.

snippets/general-shared-text/jira-cli-api.mdx

@@ -32,5 +32,8 @@ Also, to process specific projects, boards, or issues, use:
 - `--projects` with a comma-delimited list of target project IDs (CLI) or `project` with an array of target project IDs (Python).
 - `--boards` with a comma-delmited list of target board IDs (CLI) or `boards` with an array of target board IDs (Python).
 - `--issues` with a comma-delimited list of target issue IDs (CLI) or `issues` with an array of target issue IDs (Python).
+- `--status-filter` with a comma-delimited list of statuses to filter Jira issues by (CLI) or `status_filter` with an array of statuses to filter Jira issues by (Python).
+- `--download-attachments` (CLI) or `download_attachments=True` (Python) to download attachments from Jira issues.
+- `--no-download-attachments` (CLI) or `download_attachments=False` (Python) to not download attachments from Jira issues. This is the default behavior.
 - `--cloud` (CLI) or `cloud=True` (Python) to specify using Jira Cloud. The default is to use Jira Data Center.
-- `--no-cloud` (CLI) or `cloud=False` (Python) to specify using Jira Data Center. This is the default behavior.
+- `--no-cloud` (CLI) or `cloud=False` (Python) to specify using Jira Data Center. This is the default behavior.

snippets/general-shared-text/jira-platform.mdx

@@ -9,4 +9,7 @@ Fill in the following fields:
 - **Cloud**: Check this box if you are using Jira Cloud. The default is unchecked to use Jira Data Center.
 - **Projects**: A comma-separated list of IDs of the target projects in Jira to access.
 - **Boards**: A comma-separated list of IDs of the target boards in Jira to access.
-- **Issues**: A comma-separated list of IDs of the target issues in Jira to access.
+- **Issues**: A comma-separated list of IDs of the target issues in Jira to access.
+- **Status Filter**: A comma-separated list of statuses to filter Jira issues by.
+- **Issues**: A comma-separated list of IDs of the target issues in Jira to access.
+- **Download Attachments**: If checked, download attachments from Jira issues. By default, attachments are not downloaded.

snippets/source_connectors/jira.sh.mdx

@@ -12,6 +12,11 @@ unstructured-ingest \
     --cloud \ # For Jira Cloud.
     --no-cloud \ # For Jira Data Center (default).
     --output-dir $LOCAL_FILE_OUTPUT_DIR \
+    --projects <project-id>,<project-id> \
+    --boards <board-id>,<board-id> \
+    --issues <issue-id>,<issue-id> \
+    --status-filters <status>,<status> \
+    --download-attachments \
     --chunking-strategy by_title \
     --embedding-provider huggingface \
     --partition-by-api \

snippets/source_connectors/jira.v2.py.mdx

@@ -20,24 +20,31 @@ if __name__ == "__main__":
     Pipeline.from_configs(
         context=ProcessorConfig(),
         indexer_config=JiraIndexerConfig(
-            # projects=[
-            #     "project-id",
-            #     "project-id"
-            # ],
-            # boards=[
-            #     "board-id",
-            #     "board-id"
-            # ],
-            # issues=[
-            #     "issue-id",
-            #     "issue-id"
-            # ]
+            projects=[
+                "<project-id>",
+                "<project-id>"
+            ],
+            boards=[
+                "<board-id>",
+                "<board-id>"
+            ],
+            issues=[
+                "<issue-id>",
+                "<issue-id>"
+            ],
+            status_filter=[
+                "<status>",
+                "<status>"
+            ]
+        ),
+        downloader_config=JiraDownloaderConfig(
+            download_dir=os.getenv("LOCAL_FILE_DOWNLOAD_DIR"),
+            download_attachments=True
         ),
-        downloader_config=JiraDownloaderConfig(download_dir=os.getenv("LOCAL_FILE_DOWNLOAD_DIR")),
         source_connection_config=JiraConnectionConfig(
             access_config=JiraAccessConfig(
                 password=os.getenv("JIRA_PASSWORD_OR_API_TOKEN"), # Password or API token authentication.
-                # token=os.getenv("JIRA_PERSONAL_ACCES_TOKEN") # Personal access token authentication only.
+                # token=os.getenv("JIRA_PERSONAL_ACCESS_TOKEN") # Personal access token authentication only.
             ),
             url=os.getenv("JIRA_URL"),
             username=os.getenv("JIRA_USERNAME"), # For password or API token authentication.

snippets/source_connectors/jira_rest_create.mdx

@@ -30,6 +30,11 @@ curl --request 'POST' --location \
             "<issue-id>",
             "<issue-id>"
         ],
+        "status_filters": [
+            "<status>",
+            "<status>"
+        ],
+        "download_attachments": <true|false>,
         "cloud": <true|false>
     }
 }'

snippets/source_connectors/jira_sdk.mdx

@@ -37,6 +37,11 @@ with UnstructuredClient(api_key_auth=os.getenv("UNSTRUCTURED_API_KEY")) as clien
                         "<issue-id>",
                         "<issue-id>"
                     ],
+                    status_filters=[
+                        "<status>",
+                        "<status>"
+                    ],
+                    download_attachments=<True|False>,
                     cloud=<True|False>
                 )
             )