Make graphviz dependency optional

CONTRIBUTING.rst

@@ -856,13 +856,13 @@ arangodb, asana, async, atlas, atlassian.jira, aws, azure, cassandra, celery, cg
 cncf.kubernetes, cohere, common.io, common.sql, crypto, databricks, datadog, dbt.cloud,
 deprecated_api, devel, devel_all, devel_ci, devel_hadoop, dingding, discord, doc, doc_gen, docker,
 druid, elasticsearch, exasol, fab, facebook, ftp, gcp, gcp_api, github, github_enterprise, google,
-google_auth, grpc, hashicorp, hdfs, hive, http, imap, influxdb, jdbc, jenkins, kerberos, kubernetes,
-ldap, leveldb, microsoft.azure, microsoft.mssql, microsoft.psrp, microsoft.winrm, mongo, mssql,
-mysql, neo4j, odbc, openai, openfaas, openlineage, opensearch, opsgenie, oracle, otel, pagerduty,
-pandas, papermill, password, pgvector, pinecone, pinot, postgres, presto, rabbitmq, redis, s3, s3fs,
-salesforce, samba, saml, segment, sendgrid, sentry, sftp, singularity, slack, smtp, snowflake,
-spark, sqlite, ssh, statsd, tableau, tabular, telegram, trino, vertica, virtualenv, weaviate,
-webhdfs, winrm, yandex, zendesk
+google_auth, graphviz, grpc, hashicorp, hdfs, hive, http, imap, influxdb, jdbc, jenkins, kerberos,
+kubernetes, ldap, leveldb, microsoft.azure, microsoft.mssql, microsoft.psrp, microsoft.winrm, mongo,
+mssql, mysql, neo4j, odbc, openai, openfaas, openlineage, opensearch, opsgenie, oracle, otel,
+pagerduty, pandas, papermill, password, pgvector, pinecone, pinot, postgres, presto, rabbitmq,
+redis, s3, s3fs, salesforce, samba, saml, segment, sendgrid, sentry, sftp, singularity, slack, smtp,
+snowflake, spark, sqlite, ssh, statsd, tableau, tabular, telegram, trino, vertica, virtualenv,
+weaviate, webhdfs, winrm, yandex, zendesk
   .. END EXTRAS HERE
 
 Provider packages

Dockerfile

@@ -35,7 +35,7 @@
 #                        much smaller.
 #
 # Use the same builder frontend version for everyone
-ARG AIRFLOW_EXTRAS="aiobotocore,amazon,async,celery,cncf.kubernetes,common.io,docker,elasticsearch,ftp,google,google_auth,grpc,hashicorp,http,ldap,microsoft.azure,mysql,odbc,openlineage,pandas,postgres,redis,sendgrid,sftp,slack,snowflake,ssh,statsd,virtualenv"
+ARG AIRFLOW_EXTRAS="aiobotocore,amazon,async,celery,cncf.kubernetes,common.io,docker,elasticsearch,ftp,google,google_auth,graphviz,grpc,hashicorp,http,ldap,microsoft.azure,mysql,odbc,openlineage,pandas,postgres,redis,sendgrid,sftp,slack,snowflake,ssh,statsd,virtualenv"
 ARG ADDITIONAL_AIRFLOW_EXTRAS=""
 ARG ADDITIONAL_PYTHON_DEPS=""
 

INSTALL

@@ -101,13 +101,13 @@ arangodb, asana, async, atlas, atlassian.jira, aws, azure, cassandra, celery, cg
 cncf.kubernetes, cohere, common.io, common.sql, crypto, databricks, datadog, dbt.cloud,
 deprecated_api, devel, devel_all, devel_ci, devel_hadoop, dingding, discord, doc, doc_gen, docker,
 druid, elasticsearch, exasol, fab, facebook, ftp, gcp, gcp_api, github, github_enterprise, google,
-google_auth, grpc, hashicorp, hdfs, hive, http, imap, influxdb, jdbc, jenkins, kerberos, kubernetes,
-ldap, leveldb, microsoft.azure, microsoft.mssql, microsoft.psrp, microsoft.winrm, mongo, mssql,
-mysql, neo4j, odbc, openai, openfaas, openlineage, opensearch, opsgenie, oracle, otel, pagerduty,
-pandas, papermill, password, pgvector, pinecone, pinot, postgres, presto, rabbitmq, redis, s3, s3fs,
-salesforce, samba, saml, segment, sendgrid, sentry, sftp, singularity, slack, smtp, snowflake,
-spark, sqlite, ssh, statsd, tableau, tabular, telegram, trino, vertica, virtualenv, weaviate,
-webhdfs, winrm, yandex, zendesk
+google_auth, graphviz, grpc, hashicorp, hdfs, hive, http, imap, influxdb, jdbc, jenkins, kerberos,
+kubernetes, ldap, leveldb, microsoft.azure, microsoft.mssql, microsoft.psrp, microsoft.winrm, mongo,
+mssql, mysql, neo4j, odbc, openai, openfaas, openlineage, opensearch, opsgenie, oracle, otel,
+pagerduty, pandas, papermill, password, pgvector, pinecone, pinot, postgres, presto, rabbitmq,
+redis, s3, s3fs, salesforce, samba, saml, segment, sendgrid, sentry, sftp, singularity, slack, smtp,
+snowflake, spark, sqlite, ssh, statsd, tableau, tabular, telegram, trino, vertica, virtualenv,
+weaviate, webhdfs, winrm, yandex, zendesk
 # END EXTRAS HERE
 
 # For installing Airflow in development environments - see CONTRIBUTING.rst

airflow/utils/dot_renderer.py

@@ -19,9 +19,14 @@
 """Renderer DAG (tasks and dependencies) to the graphviz object."""
 from __future__ import annotations
 
+import warnings
 from typing import TYPE_CHECKING, Any
 
-import graphviz
+try:
+    import graphviz
+except ImportError:
+    warnings.warn("Could not import graphviz. Rendering graph to the graphical format will not be possible.")
+    graphviz = None
 
 from airflow.exceptions import AirflowException
 from airflow.models.baseoperator import BaseOperator
@@ -151,6 +156,10 @@ def render_dag_dependencies(deps: dict[str, list[DagDependency]]) -> graphviz.Di
     :param deps: List of DAG dependencies
     :return: Graphviz object
     """
+    if not graphviz:
+        raise AirflowException(
+            "Could not import graphviz. Install the graphviz python package to fix this error."
+        )
     dot = graphviz.Digraph(graph_attr={"rankdir": "LR"})
 
     for dag, dependencies in deps.items():
@@ -179,6 +188,10 @@ def render_dag(dag: DAG, tis: list[TaskInstance] | None = None) -> graphviz.Digr
     :param tis: List of task instances
     :return: Graphviz object
     """
+    if not graphviz:
+        raise AirflowException(
+            "Could not import graphviz. Install the graphviz python package to fix this error."
+        )
     dot = graphviz.Digraph(
         dag.dag_id,
         graph_attr={

dev/breeze/src/airflow_breeze/global_constants.py

@@ -432,6 +432,7 @@ def get_airflow_extras():
     "ftp",
     "google",
     "google_auth",
+    "graphviz",
     "grpc",
     "hashicorp",
     "http",

docs/apache-airflow/extra-packages-ref.rst

@@ -52,6 +52,8 @@ python dependencies for the provided package.
 +---------------------+-----------------------------------------------------+----------------------------------------------------------------------------+
 | google_auth         | ``pip install 'apache-airflow[google_auth]'``       | Google auth backend                                                        |
 +---------------------+-----------------------------------------------------+----------------------------------------------------------------------------+
+| graphviz            | ``pip install 'apache-airflow[graphviz]'``          | Graphviz renderer for converting DAG to graphical output                   |
++---------------------+-----------------------------------------------------+----------------------------------------------------------------------------+
 | kerberos            | ``pip install 'apache-airflow[kerberos]'``          | Kerberos integration for Kerberized services (Hadoop, Presto, Trino)       |
 +---------------------+-----------------------------------------------------+----------------------------------------------------------------------------+
 | ldap                | ``pip install 'apache-airflow[ldap]'``              | LDAP authentication for users                                              |

docs/docker-stack/build-arg-ref.rst

@@ -91,6 +91,7 @@ List of default extras in the production Dockerfile:
 * ftp
 * google
 * google_auth
+* graphviz
 * grpc
 * hashicorp
 * http

docs/spelling_wordlist.txt

@@ -687,6 +687,7 @@ googleapiclient
 GoogleDisplayVideo
 gpu
 gpus
+graphviz
 greenlet
 Groupalia
 groupId

images/breeze/output_prod-image_build.txt

@@ -1 +1 @@
-aa383b195f2991035d5333a6f37bebaa
+f7a753d66923772bfb6250d5b87d1f51

newsfragments/36647.significant.rst

@@ -0,0 +1,23 @@
+Graphviz dependency is now an optional one, not required one.
+
+The ``graphviz`` dependency has been problematic as Airflow required dependency - especially for
+ARM-based installations. Graphviz packages require binary graphviz libraries - which is already a
+limitation, but they also require to install graphviz Python bindings to be build and installed.
+This does not work for older Linux installation but - more importantly - when you try to install
+Graphviz libraries for Python 3.8, 3.9 for ARM M1 MacBooks, the packages fail to install because
+Python bindings compilation for M1 can only work for Python 3.10+.
+
+This is not a breaking change technically - the CLIs to render the DAGs is still there and IF you
+already have graphviz installed, it will continue working as it did before. The only problem when it
+does not work is where you do not have graphviz installed it will raise an error and inform that you need it.
+
+Graphviz will remain to be installed for most users:
+
+* the Airflow Image will still contain graphviz library, because
+  it is added there as extra
+* when previous version of Airflow has been installed already, then
+  graphviz library is already installed there and Airflow will
+  continue working as it did
+
+The only change will be a new installation of new version of Airflow from the scratch, where graphviz will
+need to be specified as extra or installed separately in order to enable DAG rendering option.

setup.cfg

@@ -107,7 +107,6 @@ install_requires =
     flask-wtf>=0.15
     fsspec>=2023.10.0
     google-re2>=1.0
-    graphviz>=0.12
     gunicorn>=20.1.0
     httpx
     importlib_metadata>=1.7;python_version<"3.9"

setup.py

@@ -318,12 +318,14 @@ def write_version(filename: str = str(AIRFLOW_SOURCES_ROOT / "airflow" / "git_ve
 ]
 doc_gen = [
     "eralchemy2",
+    "graphviz>=0.12",
 ]
 flask_appbuilder_oauth = [
     "authlib>=1.0.0",
     # The version here should be upgraded at the same time as flask-appbuilder in setup.cfg
     "flask-appbuilder[oauth]==4.3.10",
 ]
+graphviz = ["graphviz>=0.12"]
 kerberos = [
     "pykerberos>=1.1.13",
     "requests_kerberos>=0.10.0",
@@ -593,6 +595,7 @@ def get_unique_dependency_list(req_list_iterable: Iterable[list[str]]):
     "deprecated_api": deprecated_api,
     "github_enterprise": flask_appbuilder_oauth,
     "google_auth": flask_appbuilder_oauth,
+    "graphviz": graphviz,
     "kerberos": kerberos,
     "ldap": ldap,
     "leveldb": leveldb,