Unstructured-IO · ahmetmeleq · Sep 6, 2023 · Aug 28, 2023 · Aug 28, 2023 · Aug 29, 2023
diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml
@@ -277,6 +277,8 @@ jobs:
         DROPBOX_REFRESH_TOKEN: ${{ secrets.DROPBOX_REFRESH_TOKEN }}
         GCP_INGEST_SERVICE_KEY: ${{ secrets.GCP_INGEST_SERVICE_KEY }}
         GH_READ_ONLY_ACCESS_TOKEN: ${{ secrets.GH_READ_ONLY_ACCESS_TOKEN }}
+        JIRA_INGEST_API_TOKEN: ${{ secrets.JIRA_INGEST_API_TOKEN }}
+        JIRA_INGEST_USER_EMAIL: ${{ secrets.JIRA_INGEST_USER_EMAIL }}
         MS_CLIENT_CRED: ${{ secrets.MS_CLIENT_CRED }}
         MS_CLIENT_ID: ${{ secrets.MS_CLIENT_ID }}
         MS_TENANT_ID: ${{ secrets.MS_TENANT_ID }}
@@ -314,6 +316,7 @@ jobs:
         make install-ingest-google-drive
         make install-ingest-github
         make install-ingest-gitlab
+        make install-ingest-jira
         make install-ingest-onedrive
         make install-ingest-outlook
         make install-ingest-salesforce

diff --git a/.github/workflows/ingest-test-fixtures-update-pr.yml b/.github/workflows/ingest-test-fixtures-update-pr.yml
@@ -68,6 +68,8 @@ jobs:
           DROPBOX_REFRESH_TOKEN: ${{ secrets.DROPBOX_REFRESH_TOKEN }}
           GCP_INGEST_SERVICE_KEY: ${{ secrets.GCP_INGEST_SERVICE_KEY }}
           GH_READ_ONLY_ACCESS_TOKEN: ${{ secrets.GH_READ_ONLY_ACCESS_TOKEN }}
+          JIRA_INGEST_API_TOKEN: ${{ secrets.JIRA_INGEST_API_TOKEN }}
+          JIRA_INGEST_USER_EMAIL: ${{ secrets.JIRA_INGEST_USER_EMAIL }}
           MS_CLIENT_CRED: ${{ secrets.MS_CLIENT_CRED }}
           MS_CLIENT_ID: ${{ secrets.MS_CLIENT_ID }}
           MS_TENANT_ID: ${{ secrets.MS_TENANT_ID }}
@@ -105,6 +107,7 @@ jobs:
           make install-ingest-google-drive
           make install-ingest-github
           make install-ingest-gitlab
+          make install-ingest-jira
           make install-ingest-onedrive
           make install-ingest-outlook
           make install-ingest-salesforce

diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -1,14 +1,17 @@
-## 0.10.13-dev1
+## 0.10.13-dev2
 
 ### Enhancements
 
 * Updated documentation: Added back support doc types for partitioning, more Python codes in the API page,  RAG definition, and use case.
 
+### Features
+
+* Add Jira Connector to be able to pull issues from a Jira organization
+
 ### Fixes
 
 * Ingest error handling to properly raise errors when wrapped
 
-
 ## 0.10.12
 
 ### Enhancements

diff --git a/Makefile b/Makefile
@@ -192,6 +192,10 @@ install-ingest-notion:
 install-ingest-salesforce:
 	python3 -m pip install -r requirements/ingest-salesforce.txt
 
+.PHONY: install-ingest-jira
+install-ingest-jira:
+	python3 -m pip install -r requirements/ingest-jira.txt
+
 .PHONY: install-unstructured-inference
 install-unstructured-inference:
 	python3 -m pip install -r requirements/local-inference.txt

diff --git a/docs/source/upstream_connectors/confluence.rst b/docs/source/upstream_connectors/confluence.rst
@@ -1,6 +1,6 @@
 Confluence
 ==========
-Connect Confluence to your preprocessing pipeline, and batch process all your documents using ``unstructured-ingest`` to store structured outputs locally on your filesystem. 
+Connect Confluence to your preprocessing pipeline, and batch process all your documents using ``unstructured-ingest`` to store structured outputs locally on your filesystem.
 
 First you'll need to install the Confluence dependencies as shown here.
 
@@ -34,7 +34,7 @@ Run Locally
 
         command = [
           "unstructured-ingest",
-          "confluence"
+          "confluence",
           "--metadata-exclude", "filename,file_directory,metadata.data_source.date_processed",
           "--url", "https://unstructured-ingest-test.atlassian.net",
           "--user-email", "[email protected]",
@@ -58,7 +58,7 @@ Run Locally
 Run via the API
 ---------------
 
-You can also use upstream connectors with the ``unstructured`` API. For this you'll need to use the ``--partition-by-api`` flag and pass in your API key with ``--api-key``. 
+You can also use upstream connectors with the ``unstructured`` API. For this you'll need to use the ``--partition-by-api`` flag and pass in your API key with ``--api-key``.
 
 .. tabs::
 
@@ -85,7 +85,7 @@ You can also use upstream connectors with the ``unstructured`` API. For this you
 
         command = [
           "unstructured-ingest",
-          "confluence"
+          "confluence",
           "--metadata-exclude", "filename,file_directory,metadata.data_source.date_processed",
           "--url", "https://unstructured-ingest-test.atlassian.net",
           "--user-email", "[email protected]",
@@ -112,4 +112,4 @@ Additionaly, you will need to pass the ``--partition-endpoint`` if you're runnin
 
 For a full list of the options the CLI accepts check ``unstructured-ingest confluence --help``.
 
-NOTE: Keep in mind that you will need to have all the appropriate extras and dependencies for the file types of the documents contained in your data storage platform if you're running this locally. You can find more information about this in the `installation guide <https://unstructured-io.github.io/unstructured/installing.html>`_.
+NOTE: Keep in mind that you will need to have all the appropriate extras and dependencies for the file types of the documents contained in your data storage platform if you're running this locally. You can find more information about this in the `installation guide <https://unstructured-io.github.io/unstructured/installing.html>`_.
diff --git a/docs/source/upstream_connectors/discord.rst b/docs/source/upstream_connectors/discord.rst
@@ -1,6 +1,6 @@
 Discord
 ==========
-Connect Discord to your preprocessing pipeline, and batch process all your documents using ``unstructured-ingest`` to store structured outputs locally on your filesystem. 
+Connect Discord to your preprocessing pipeline, and batch process all your documents using ``unstructured-ingest`` to store structured outputs locally on your filesystem.
 
 First you'll need to install the Discord dependencies as shown here.
 
@@ -34,7 +34,7 @@ Run Locally
 
         command = [
           "unstructured-ingest",
-            "discord"
+            "discord",
             "--channels", "12345678",
             "--token", "$DISCORD_TOKEN",
             "--download-dir", "discord-ingest-download",
@@ -58,7 +58,7 @@ Run Locally
 Run via the API
 ---------------
 
-You can also use upstream connectors with the ``unstructured`` API. For this you'll need to use the ``--partition-by-api`` flag and pass in your API key with ``--api-key``. 
+You can also use upstream connectors with the ``unstructured`` API. For this you'll need to use the ``--partition-by-api`` flag and pass in your API key with ``--api-key``.
 
 .. tabs::
 
@@ -73,7 +73,7 @@ You can also use upstream connectors with the ``unstructured`` API. For this you
           --download-dir discord-ingest-download \
           --structured-output-dir discord-example \
           --preserve-downloads \
-          --verbose \ 
+          --verbose \
           --partition-by-api \
           --api-key "<UNSTRUCTURED-API-KEY>"
 
@@ -85,7 +85,7 @@ You can also use upstream connectors with the ``unstructured`` API. For this you
 
         command = [
           "unstructured-ingest",
-          "discord"
+          "discord",
           "--channels", "12345678",
           "--token", "$DISCORD_TOKEN",
           "--download-dir", "discord-ingest-download",
@@ -112,4 +112,4 @@ Additionaly, you will need to pass the ``--partition-endpoint`` if you're runnin
 
 For a full list of the options the CLI accepts check ``unstructured-ingest discord --help``.
 
-NOTE: Keep in mind that you will need to have all the appropriate extras and dependencies for the file types of the documents contained in your data storage platform if you're running this locally. You can find more information about this in the `installation guide <https://unstructured-io.github.io/unstructured/installing.html>`_.
+NOTE: Keep in mind that you will need to have all the appropriate extras and dependencies for the file types of the documents contained in your data storage platform if you're running this locally. You can find more information about this in the `installation guide <https://unstructured-io.github.io/unstructured/installing.html>`_.
diff --git a/docs/source/upstream_connectors/jira.rst b/docs/source/upstream_connectors/jira.rst
@@ -0,0 +1,115 @@
+Jira
+==========
+Connect Jira to your preprocessing pipeline, and batch process all your documents using ``unstructured-ingest`` to store structured outputs locally on your filesystem.
+
+First you'll need to install the Jira dependencies as shown here.
+
+.. code:: shell
+
+  pip install "unstructured[jira]"
+
+Run Locally
+-----------
+
+.. tabs::
+
+   .. tab:: Shell
+
+      .. code:: shell
+
+        unstructured-ingest \
+          jira \
+          --metadata-exclude filename,file_directory,metadata.data_source.date_processed \
+          --url https://unstructured-jira-connector-test.atlassian.net \
+          --user-email [email protected] \
+          --api-token ABCDE1234ABDE1234ABCDE1234 \
+          --structured-output-dir jira-ingest-output \
+          --num-processes 2
+
+   .. tab:: Python
+
+      .. code:: python
+
+        import subprocess
+
+        command = [
+            "unstructured-ingest",
+            "jira",
+            "--metadata-exclude", "filename,file_directory,metadata.data_source.date_processed",
+            "--url", "https://unstructured-jira-connector-test.atlassian.net",
+            "--user-email", "[email protected]",
+            "--api-token", "ABCDE1234ABDE1234ABCDE1234",
+            "--structured-output-dir", "jira-ingest-output",
+            "--num-processes", "2",
+        ]
+
+        # Run the command
+        process = subprocess.Popen(command, stdout=subprocess.PIPE)
+        output, error = process.communicate()
+
+        # Print output
+        if process.returncode == 0:
+            print('Command executed successfully. Output:')
+            print(output.decode())
+        else:
+            print('Command failed. Error:')
+            print(error.decode())
+
+Run via the API
+---------------
+
+You can also use upstream connectors with the ``unstructured`` API. For this you'll need to use the ``--partition-by-api`` flag and pass in your API key with ``--api-key``.
+
+.. tabs::
+
+   .. tab:: Shell
+
+      .. code:: shell
+
+        unstructured-ingest \
+          jira \
+          --metadata-exclude filename,file_directory,metadata.data_source.date_processed \
+          --url https://unstructured-jira-connector-test.atlassian.net \
+          --user-email [email protected] \
+          --api-token ABCDE1234ABDE1234ABCDE1234 \
+          --structured-output-dir jira-ingest-output \
+          --num-processes 2 \
+          --partition-by-api \
+          --api-key "<UNSTRUCTURED-API-KEY>"
+
+   .. tab:: Python
+
+      .. code:: python
+
+        import subprocess
+
+        command = [
+          "unstructured-ingest",
+          "jira",
+          "--metadata-exclude", "filename,file_directory,metadata.data_source.date_processed",
+          "--url", "https://unstructured-jira-connector-test.atlassian.net",
+          "--user-email", "[email protected]",
+          "--api-token", "ABCDE1234ABDE1234ABCDE1234",
+          "--structured-output-dir", "jira-ingest-output",
+          "--num-processes", "2",
+          "--partition-by-api",
+          "--api-key", "<UNSTRUCTURED-API-KEY>",
+        ]
+
+        # Run the command
+        process = subprocess.Popen(command, stdout=subprocess.PIPE)
+        output, error = process.communicate()
+
+        # Print output
+        if process.returncode == 0:
+            print('Command executed successfully. Output:')
+            print(output.decode())
+        else:
+            print('Command failed. Error:')
+            print(error.decode())
+
+Additionaly, you will need to pass the ``--partition-endpoint`` if you're running the API locally. You can find more information about the ``unstructured`` API `here <https://github.com/Unstructured-IO/unstructured-api>`_.
+
+For a full list of the options the CLI accepts check ``unstructured-ingest jira --help``.
+
+NOTE: Keep in mind that you will need to have all the appropriate extras and dependencies for the file types of the documents contained in your data storage platform if you're running this locally. You can find more information about this in the `installation guide <https://unstructured-io.github.io/unstructured/installing.html>`_.
diff --git a/examples/ingest/jira/ingest.sh b/examples/ingest/jira/ingest.sh
@@ -0,0 +1,41 @@
+#!/usr/bin/env bash
+
+# Processes all the issues in all projects within a jira domain, using the `unstructured` library.
+
+# Structured outputs are stored in jira-ingest-output
+SCRIPT_DIR=$(dirname "$(realpath "$0")")
+cd "$SCRIPT_DIR"/../../.. || exit 1
+
+# Required arguments:
+# --url
+#   --> Atlassian (Jira) domain URL
+# --api-token
+#   --> Api token to authenticate into Atlassian (Jira).
+#       Check https://support.atlassian.com/atlassian-account/docs/manage-api-tokens-for-your-atlassian-account/ for more info.
+# --user-email
+#   --> User email for the domain, such as [email protected]
+
+# Optional arguments:
+# --list-of-projects
+#     --> Space separated project ids or keys
+# --list-of-boards
+#     --> Space separated board ids or keys
+# --list-of-issues
+#     --> Space separated issue ids or keys
+
+# Note: When any of the optional arguments are provided, connector will ingest only those components, and nothing else.
+#       When none of the optional arguments are provided, all issues in all projects will be ingested.
+
+
+PYTHONPATH=. ./unstructured/ingest/main.py \
+        jira \
+        --metadata-exclude filename,file_directory,metadata.data_source.date_processed \
+        --url https://unstructured-jira-connector-test.atlassian.net \
+        --user-email "$JIRA_USER_EMAIL" \
+        --api-token "$JIRA_API_TOKEN" \
+        --structured-output-dir jira-ingest-output \
+        --num-processes 2 \
+        --reprocess
+        # --list-of-projects <your project keys/ids here (space separated)> \
+        # --list-of-boards <your board keys/ids here (space separated)> \
+        # --list-of-issues <your issue keys/ids here (space separated)> \
diff --git a/requirements/ingest-jira.in b/requirements/ingest-jira.in
@@ -0,0 +1,3 @@
+-c constraints.in
+-c base.txt
+atlassian-python-api
diff --git a/requirements/ingest-jira.txt b/requirements/ingest-jira.txt
@@ -0,0 +1,43 @@
+#
+# This file is autogenerated by pip-compile with Python 3.10
+# by the following command:
+#
+#    pip-compile requirements/ingest-jira.in
+#
+atlassian-python-api==3.41.1
+    # via -r requirements/ingest-jira.in
+certifi==2023.7.22
+    # via
+    #   -c requirements/base.txt
+    #   -c requirements/constraints.in
+    #   requests
+charset-normalizer==3.2.0
+    # via
+    #   -c requirements/base.txt
+    #   requests
+deprecated==1.2.14
+    # via atlassian-python-api
+idna==3.4
+    # via
+    #   -c requirements/base.txt
+    #   requests
+oauthlib==3.2.2
+    # via
+    #   atlassian-python-api
+    #   requests-oauthlib
+requests==2.31.0
+    # via
+    #   -c requirements/base.txt
+    #   atlassian-python-api
+    #   requests-oauthlib
+requests-oauthlib==1.3.1
+    # via atlassian-python-api
+six==1.16.0
+    # via atlassian-python-api
+urllib3==1.26.16
+    # via
+    #   -c requirements/base.txt
+    #   -c requirements/constraints.in
+    #   requests
+wrapt==1.15.0
+    # via deprecated
diff --git a/setup.py b/setup.py
@@ -149,6 +149,7 @@ def load_requirements(file_list: Optional[Union[str, List[str]]] = None) -> List
         "sharepoint": load_requirements("requirements/ingest-sharepoint.in"),
         "delta-table": load_requirements("requirements/ingest-delta-table.in"),
         "salesforce": load_requirements("requirements/ingest-salesforce.in"),
+        "jira": load_requirements("requirements/ingest-jira.in"),
         # Legacy extra requirements
         "huggingface": load_requirements("requirements/huggingface.in"),
         "local-inference": all_doc_reqs,