From fe73ab908a9899150f8cf6fd0a31432c04d4b439 Mon Sep 17 00:00:00 2001
From: Shirshanka Das <shirshanka@apache.org>
Date: Thu, 8 Sep 2022 00:38:10 -0700
Subject: [PATCH] docs(ingest): improve doc gen, docs for snowflake, looker
 (#5867)

---
 .../docs/sources/looker/looker.md             | 23 -----
 .../docs/sources/looker/looker_pre.md         | 62 ++++++++++++
 .../docs/sources/looker/lookml.md             | 13 ---
 .../docs/sources/looker/lookml_post.md        | 11 +++
 .../docs/sources/looker/lookml_pre.md         | 84 ++++++++++++++++
 .../docs/sources/looker/lookml_recipe.yml     |  5 +-
 .../docs/sources/snowflake/README.md          | 29 +++++-
 ...nowflake-beta.md => snowflake-beta_pre.md} |  0
 .../snowflake/snowflake-beta_recipe.yml       | 13 +--
 ...wflake-usage.md => snowflake-usage_pre.md} |  0
 metadata-ingestion/scripts/docgen.py          | 96 ++++++++++++++++---
 .../src/datahub/ingestion/api/decorators.py   |  3 +-
 .../source/snowflake/snowflake_v2.py          |  2 +-
 13 files changed, 276 insertions(+), 65 deletions(-)
 delete mode 100644 metadata-ingestion/docs/sources/looker/looker.md
 create mode 100644 metadata-ingestion/docs/sources/looker/looker_pre.md
 delete mode 100644 metadata-ingestion/docs/sources/looker/lookml.md
 create mode 100644 metadata-ingestion/docs/sources/looker/lookml_post.md
 create mode 100644 metadata-ingestion/docs/sources/looker/lookml_pre.md
 rename metadata-ingestion/docs/sources/snowflake/{snowflake-beta.md => snowflake-beta_pre.md} (100%)
 rename metadata-ingestion/docs/sources/snowflake/{snowflake-usage.md => snowflake-usage_pre.md} (100%)

diff --git a/metadata-ingestion/docs/sources/looker/looker.md b/metadata-ingestion/docs/sources/looker/looker.md
deleted file mode 100644
index 769d3341dca13f..00000000000000
--- a/metadata-ingestion/docs/sources/looker/looker.md
+++ /dev/null
@@ -1,23 +0,0 @@
-#### Configuration Notes
-
-See the [Looker authentication docs](https://docs.looker.com/reference/api-and-integration/api-auth#authentication_with_an_sdk) for the steps to create a client ID and secret. 
-You need to provide the following permissions for ingestion to work correctly. 
-```
-access_data
-explore
-manage_models
-see_datagroups
-see_lookml
-see_lookml_dashboards
-see_looks
-see_pdts
-see_queries
-see_schedules
-see_sql
-see_system_activity
-see_user_dashboards
-see_users
-```
-Here is an example permission set after configuration. 
-![Looker DataHub Permission Set](./looker_datahub_permission_set.png)
-
diff --git a/metadata-ingestion/docs/sources/looker/looker_pre.md b/metadata-ingestion/docs/sources/looker/looker_pre.md
new file mode 100644
index 00000000000000..762b4d0f5af48e
--- /dev/null
+++ b/metadata-ingestion/docs/sources/looker/looker_pre.md
@@ -0,0 +1,62 @@
+### Pre-Requisites
+
+#### Set up the right permissions
+You need to provide the following permissions for ingestion to work correctly. 
+```
+access_data
+explore
+manage_models
+see_datagroups
+see_lookml
+see_lookml_dashboards
+see_looks
+see_pdts
+see_queries
+see_schedules
+see_sql
+see_system_activity
+see_user_dashboards
+see_users
+```
+Here is an example permission set after configuration. 
+![Looker DataHub Permission Set](./looker_datahub_permission_set.png)
+
+#### Get an API key
+
+You need to get an API key for the account with the above privileges to perform ingestion. See the [Looker authentication docs](https://docs.looker.com/reference/api-and-integration/api-auth#authentication_with_an_sdk) for the steps to create a client ID and secret.
+
+
+### Ingestion through UI
+
+The following video shows you how to get started with ingesting Looker metadata through the UI. 
+
+:::note
+
+You will need to run `lookml` ingestion through the CLI after you have ingested Looker metadata through the UI. Otherwise you will not be able to see Looker Views and their lineage to your warehouse tables. 
+
+::: 
+
+<div
+  style={{
+    position: "relative",
+    paddingBottom: "57.692307692307686%",
+    height: 0
+  }}
+>
+  <iframe
+    src="https://www.loom.com/embed/b8b9654e02714d20a44122cc1bffc1bb"
+    frameBorder={0}
+    webkitallowfullscreen=""
+    mozallowfullscreen=""
+    allowFullScreen=""
+    style={{
+      position: "absolute",
+      top: 0,
+      left: 0,
+      width: "100%",
+      height: "100%"
+    }}
+  />
+</div>
+
+
diff --git a/metadata-ingestion/docs/sources/looker/lookml.md b/metadata-ingestion/docs/sources/looker/lookml.md
deleted file mode 100644
index 996f5f68550f38..00000000000000
--- a/metadata-ingestion/docs/sources/looker/lookml.md
+++ /dev/null
@@ -1,13 +0,0 @@
-#### Configuration Notes
-
-See the [Looker authentication docs](https://docs.looker.com/reference/api-and-integration/api-auth#authentication_with_an_sdk) for the steps to create a client ID and secret.
-You need to ensure that the API key is attached to a user that has Admin privileges. If that is not possible, read the configuration section to provide an offline specification of the `connection_to_platform_map` and the `project_name`.
-
-:::note
-The integration can use an SQL parser to try to parse the tables the views depends on. 
-:::
-This parsing is disabled by default,
-but can be enabled by setting `parse_table_names_from_sql: True`.  The default parser is based on the [`sqllineage`](https://pypi.org/project/sqllineage/) package.
-As this package doesn't officially support all the SQL dialects that Looker supports, the result might not be correct. You can, however, implement a
-custom parser and take it into use by setting the `sql_parser` configuration value. A custom SQL parser must inherit from `datahub.utilities.sql_parser.SQLParser`
-and must be made available to Datahub by ,for example, installing it. The configuration then needs to be set to `module_name.ClassName` of the parser.
diff --git a/metadata-ingestion/docs/sources/looker/lookml_post.md b/metadata-ingestion/docs/sources/looker/lookml_post.md
new file mode 100644
index 00000000000000..f5c84774b62e45
--- /dev/null
+++ b/metadata-ingestion/docs/sources/looker/lookml_post.md
@@ -0,0 +1,11 @@
+#### Configuration Notes
+
+:::note
+
+The integration can use an SQL parser to try to parse the tables the views depends on. 
+
+:::
+
+This parsing is disabled by default, but can be enabled by setting `parse_table_names_from_sql: True`.  The default parser is based on the [`sqllineage`](https://pypi.org/project/sqllineage/) package.
+As this package doesn't officially support all the SQL dialects that Looker supports, the result might not be correct. You can, however, implement a custom parser and take it into use by setting the `sql_parser` configuration value. A custom SQL parser must inherit from `datahub.utilities.sql_parser.SQLParser`
+and must be made available to Datahub by ,for example, installing it. The configuration then needs to be set to `module_name.ClassName` of the parser.
diff --git a/metadata-ingestion/docs/sources/looker/lookml_pre.md b/metadata-ingestion/docs/sources/looker/lookml_pre.md
new file mode 100644
index 00000000000000..c5c6b80d669071
--- /dev/null
+++ b/metadata-ingestion/docs/sources/looker/lookml_pre.md
@@ -0,0 +1,84 @@
+### Pre-requisites
+
+#### [Optional] Create an API key
+
+See the [Looker authentication docs](https://docs.looker.com/reference/api-and-integration/api-auth#authentication_with_an_sdk) for the steps to create a client ID and secret.
+You need to ensure that the API key is attached to a user that has Admin privileges. 
+
+If that is not possible, read the configuration section and provide an offline specification of the `connection_to_platform_map` and the `project_name`.
+
+### Ingestion through UI
+
+Ingestion using lookml connector is not supported through the UI.
+However, you can set up ingestion using a GitHub Action to push metadata whenever your main lookml repo changes.
+
+#### Sample GitHub Action
+
+Drop this file into your `.github/workflows` directory inside your Looker github repo.
+
+```
+name: lookml metadata upload
+on:
+  push:
+    branches:
+      - main
+    paths-ignore:
+      - "docs/**"
+      - "**.md"
+  pull_request:
+    branches:
+      - main
+    paths-ignore:
+      - "docs/**"
+      - "**.md"
+  release:
+    types: [published, edited]
+  workflow_dispatch:
+    
+
+jobs:
+  lookml-metadata-upload:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v2
+      - uses: actions/setup-python@v4
+        with:
+          python-version: '3.9'
+      - name: Run LookML ingestion
+        run: |
+          pip install 'acryl-datahub[lookml,datahub-rest]'
+          cat << EOF > lookml_ingestion.yml
+          # LookML ingestion configuration
+          source:
+            type: "lookml"
+            config:
+              base_folder: ${{ github.workspace }}
+              parse_table_names_from_sql: true
+              github_info:
+                repo: ${{ github.repository }}
+                branch: ${{ github.ref }}
+              # Options
+              #connection_to_platform_map:
+              #  acryl-snow: snowflake
+                  #platform: snowflake
+                  #default_db: DEMO_PIPELINE
+              api:
+                client_id: ${LOOKER_CLIENT_ID}
+                client_secret: ${LOOKER_CLIENT_SECRET}
+                base_url: ${LOOKER_BASE_URL}
+          sink:
+            type: datahub-rest
+            config:
+              server: ${DATAHUB_GMS_HOST}
+              token: ${DATAHUB_TOKEN}
+          EOF
+          datahub ingest -c lookml_ingestion.yml
+        env:
+          DATAHUB_GMS_HOST: ${{ secrets.DATAHUB_GMS_HOST }}
+          DATAHUB_TOKEN: ${{ secrets.DATAHUB_TOKEN }}
+          LOOKER_BASE_URL: https://acryl.cloud.looker.com  # <--- replace with your Looker base URL
+          LOOKER_CLIENT_ID: ${{ secrets.LOOKER_CLIENT_ID }}
+          LOOKER_CLIENT_SECRET: ${{ secrets.LOOKER_CLIENT_SECRET }}
+```
+
+If you want to ingest lookml using the **datahub** cli directly, read on for instructions and configuration details.
\ No newline at end of file
diff --git a/metadata-ingestion/docs/sources/looker/lookml_recipe.yml b/metadata-ingestion/docs/sources/looker/lookml_recipe.yml
index 57e6aef18b2594..2a89a44328edee 100644
--- a/metadata-ingestion/docs/sources/looker/lookml_recipe.yml
+++ b/metadata-ingestion/docs/sources/looker/lookml_recipe.yml
@@ -31,6 +31,7 @@ source:
 
     # Optional additional github information. Used to add github links on the dataset's entity page.
     github_info:
-       repo: org/repo-name
+      repo: org/repo-name
+# Default sink is datahub-rest and doesn't need to be configured
+# See https://datahubproject.io/docs/metadata-ingestion/sink_docs/datahub for customization options
 
-# sink configs
diff --git a/metadata-ingestion/docs/sources/snowflake/README.md b/metadata-ingestion/docs/sources/snowflake/README.md
index eb65620a9c2b60..5b528ee066baa0 100644
--- a/metadata-ingestion/docs/sources/snowflake/README.md
+++ b/metadata-ingestion/docs/sources/snowflake/README.md
@@ -1,4 +1,29 @@
-To get all metadata from Snowflake you need to use two plugins `snowflake` and `snowflake-usage`. Both of them are described in this page. These will require 2 separate recipes.
+Ingesting metadata from Snowflake requires either using the **snowflake-beta** module with just one recipe (recommended) or the two separate modules **snowflake** and **snowflake-usage** (soon to be deprecated) with two separate recipes. 
 
+All three modules are described on this page. 
 
-We encourage you to try out new `snowflake-beta` plugin as alternative to running both `snowflake` and `snowflake-usage` plugins and share feedback. `snowflake-beta` is much faster than `snowflake` for extracting metadata .
\ No newline at end of file
+We encourage you to try out the new **snowflake-beta** plugin as alternative to running both **snowflake** and **snowflake-usage** plugins and share feedback. `snowflake-beta` is much faster than `snowflake` for extracting metadata.
+
+## Snowflake Ingestion through the UI
+
+The following video shows you how to ingest Snowflake metadata through the UI.
+
+<div style={{ position: "relative", paddingBottom: "56.25%", height: 0 }}>
+  <iframe
+    src="https://www.loom.com/embed/15d0401caa1c4aa483afef1d351760db"
+    frameBorder={0}
+    webkitallowfullscreen=""
+    mozallowfullscreen=""
+    allowFullScreen=""
+    style={{
+      position: "absolute",
+      top: 0,
+      left: 0,
+      width: "100%",
+      height: "100%"
+    }}
+  />
+</div>
+
+
+Read on if you are interested in ingesting Snowflake metadata using the **datahub** cli, or want to learn about all the configuration parameters that are supported by the connectors.
\ No newline at end of file
diff --git a/metadata-ingestion/docs/sources/snowflake/snowflake-beta.md b/metadata-ingestion/docs/sources/snowflake/snowflake-beta_pre.md
similarity index 100%
rename from metadata-ingestion/docs/sources/snowflake/snowflake-beta.md
rename to metadata-ingestion/docs/sources/snowflake/snowflake-beta_pre.md
diff --git a/metadata-ingestion/docs/sources/snowflake/snowflake-beta_recipe.yml b/metadata-ingestion/docs/sources/snowflake/snowflake-beta_recipe.yml
index 817707eb7210df..10d95bdb0e7f69 100644
--- a/metadata-ingestion/docs/sources/snowflake/snowflake-beta_recipe.yml
+++ b/metadata-ingestion/docs/sources/snowflake/snowflake-beta_recipe.yml
@@ -1,12 +1,11 @@
 source:
   type: snowflake-beta
   config:
-
     # This option is recommended to be used for the first time to ingest all lineage
     ignore_start_time_lineage: true
     # This is an alternative option to specify the start_time for lineage
     # if you don't want to look back since beginning
-    start_time: '2022-03-01T00:00:00Z'
+    start_time: "2022-03-01T00:00:00Z"
 
     # Coordinates
     account_id: "abc48144"
@@ -35,9 +34,7 @@ source:
       profile_table_level_only: true
     profile_pattern:
       allow:
-        - 'ACCOUNTING_DB.*.*'
-        - 'MARKETING_DB.*.*'
-
-
-sink:
-# sink configs
\ No newline at end of file
+        - "ACCOUNTING_DB.*.*"
+        - "MARKETING_DB.*.*"
+# Default sink is datahub-rest and doesn't need to be configured
+# See https://datahubproject.io/docs/metadata-ingestion/sink_docs/datahub for customization options
diff --git a/metadata-ingestion/docs/sources/snowflake/snowflake-usage.md b/metadata-ingestion/docs/sources/snowflake/snowflake-usage_pre.md
similarity index 100%
rename from metadata-ingestion/docs/sources/snowflake/snowflake-usage.md
rename to metadata-ingestion/docs/sources/snowflake/snowflake-usage_pre.md
diff --git a/metadata-ingestion/scripts/docgen.py b/metadata-ingestion/scripts/docgen.py
index 53e3733d760a3c..917e5341def4e5 100644
--- a/metadata-ingestion/scripts/docgen.py
+++ b/metadata-ingestion/scripts/docgen.py
@@ -26,19 +26,25 @@
 @dataclass
 class FieldRow:
     path: str
+    parent: Optional[str]
     type_name: str
     required: bool
     default: str
     description: str
     inner_fields: List["FieldRow"] = Field(default_factory=list)
 
-    @staticmethod
-    def get_checkbox(enabled: bool) -> str:
-        return "✅" if enabled else ""
+    def get_checkbox(self) -> str:
+        if self.required:
+            if not self.parent:  # None and empty string both count
+                return "✅"
+            else:
+                return f"❓ (required if {self.parent} is set)"
+        else:
+            return ""
 
     def to_md_line(self) -> str:
         return (
-            f"| {self.path} | {self.get_checkbox(self.required)} | {self.type_name} | {self.description} | {self.default} |\n"
+            f"| {self.path} | {self.get_checkbox()} | {self.type_name} | {self.description} | {self.default} |\n"
             + "".join([inner_field.to_md_line() for inner_field in self.inner_fields])
         )
 
@@ -129,6 +135,7 @@ def gen_md_table(
         md_str.append(
             FieldRow(
                 path=get_prefixed_name(field_prefix, None),
+                parent=field_prefix,
                 type_name="Enum",
                 required=field_dict.get("required") or False,
                 description=f"one of {','.join(field_dict['enum'])}",
@@ -150,6 +157,7 @@ def gen_md_table(
                     if "enum" in def_dict:
                         row = FieldRow(
                             path=get_prefixed_name(field_prefix, field_name),
+                            parent=field_prefix,
                             type_name=f"enum({reference.split('/')[-1]})",
                             description=get_enum_description(
                                 value.get("description"), def_dict["enum"]
@@ -162,6 +170,7 @@ def gen_md_table(
                         # object reference
                         row = FieldRow(
                             path=get_prefixed_name(field_prefix, field_name),
+                            parent=field_prefix,
                             type_name=f"{reference.split('/')[-1]} (see below for fields)",
                             description=value.get("description") or "",
                             default=str(value.get("default", "")),
@@ -188,6 +197,7 @@ def gen_md_table(
                 md_str.append(
                     FieldRow(
                         path=get_prefixed_name(field_prefix, field_name),
+                        parent=field_prefix,
                         type_name="Enum",
                         description=f"one of {','.join(def_dict['enum'])}",
                         required=required_field,
@@ -210,6 +220,7 @@ def gen_md_table(
 
                         row = FieldRow(
                             path=get_prefixed_name(field_prefix, field_name),
+                            parent=field_prefix,
                             type_name=f"Dict[str, {value_ref.split('/')[-1]}]",
                             description=value.get("description") or "",
                             default=str(value.get("default", "")),
@@ -229,6 +240,7 @@ def gen_md_table(
                         md_str.append(
                             FieldRow(
                                 path=get_prefixed_name(field_prefix, field_name),
+                                parent=field_prefix,
                                 type_name=f"Dict[str,{value_type}]"
                                 if value_type
                                 else "Dict",
@@ -241,6 +253,7 @@ def gen_md_table(
                     object_definition = value["$ref"]
                     row = FieldRow(
                         path=get_prefixed_name(field_prefix, field_name),
+                        parent=field_prefix,
                         type_name=f"{object_definition.split('/')[-1]} (see below for fields)",
                         description=value.get("description") or "",
                         default=str(value.get("default", "")),
@@ -266,6 +279,7 @@ def gen_md_table(
                 md_str.append(
                     FieldRow(
                         path=get_prefixed_name(field_prefix, field_name),
+                        parent=field_prefix,
                         type_name=f"Array of {items_type}",
                         description=value.get("description") or "",
                         default=str(value.get("default", "None")),
@@ -278,6 +292,7 @@ def gen_md_table(
                 md_str.append(
                     FieldRow(
                         path=get_prefixed_name(field_prefix, field_name),
+                        parent=field_prefix,
                         type_name=value["type"],
                         description=value.get("description") or "",
                         default=str(value.get("default", "None")),
@@ -292,6 +307,7 @@ def gen_md_table(
                 )
                 row = FieldRow(
                     path=get_prefixed_name(field_prefix, field_name),
+                    parent=field_prefix,
                     type_name=f"{object_definition.split('/')[-1]} (see below for fields)",
                     description=value.get("description") or "",
                     default=str(value.get("default", "")),
@@ -313,6 +329,7 @@ def gen_md_table(
                 md_str.append(
                     FieldRow(
                         path=get_prefixed_name(field_prefix, field_name),
+                        parent=field_prefix,
                         type_name="Generic dict",
                         description=value.get("description", ""),
                         default=str(value.get("default", "None")),
@@ -481,11 +498,37 @@ def generate(
                             final_markdown,
                         )
                     else:
-                        create_or_update(
-                            source_documentation,
-                            [platform_name, "plugins", file_name, "custom_docs"],
-                            final_markdown,
-                        )
+                        if "_" in file_name:
+                            plugin_doc_parts = file_name.split("_")
+                            if len(plugin_doc_parts) != 2 or plugin_doc_parts[
+                                1
+                            ] not in ["pre", "post"]:
+                                raise Exception(
+                                    f"{file_name} needs to be of the form <plugin>_pre.md or <plugin>_post.md"
+                                )
+
+                            docs_key_name = f"custom_docs_{plugin_doc_parts[1]}"
+                            create_or_update(
+                                source_documentation,
+                                [
+                                    platform_name,
+                                    "plugins",
+                                    plugin_doc_parts[0],
+                                    docs_key_name,
+                                ],
+                                final_markdown,
+                            )
+                        else:
+                            create_or_update(
+                                source_documentation,
+                                [
+                                    platform_name,
+                                    "plugins",
+                                    file_name,
+                                    "custom_docs_post",
+                                ],
+                                final_markdown,
+                            )
             else:
                 yml_match = re.search("/docs/sources/(.*)/(.*)_recipe.yml", path)
                 if yml_match:
@@ -543,6 +586,14 @@ def generate(
                 if hasattr(source_type, "get_platform_id"):
                     platform_id = source_type.get_platform_id()
 
+                if hasattr(source_type, "get_platform_doc_order"):
+                    platform_doc_order = source_type.get_platform_doc_order()
+                    create_or_update(
+                        source_documentation,
+                        [platform_id, "plugins", plugin_name, "doc_order"],
+                        platform_doc_order,
+                    )
+
                 source_documentation[platform_id] = (
                     source_documentation.get(platform_id) or {}
                 )
@@ -637,6 +688,7 @@ def generate(
             warning_msg = f"Failed to find source classes for platform {platform_id}. Did you remember to annotate your source class with @platform_name({platform_id})?"
             logger.error(warning_msg)
             metrics["source_platforms"]["warnings"].append(warning_msg)
+            continue
 
         with open(platform_doc_file, "w") as f:
             if "name" in platform_docs:
@@ -658,7 +710,12 @@ def generate(
 
                 #                f.write("| Source Module | Documentation |\n")
                 #                f.write("| ------ | ---- |\n")
-                for plugin in sorted(platform_docs["plugins"]):
+                for plugin, plugin_docs in sorted(
+                    platform_docs["plugins"].items(),
+                    key=lambda x: str(x[1].get("doc_order"))
+                    if x[1].get("doc_order")
+                    else x[0],
+                ):
                     f.write("<tr>\n")
                     f.write(f"<td>\n\n`{plugin}`\n\n</td>\n")
                     f.write(
@@ -671,8 +728,14 @@ def generate(
                 f.write("</table>\n\n")
             # insert platform level custom docs before plugin section
             f.write(platform_docs.get("custom_docs") or "")
-            for plugin in sorted(platform_docs["plugins"]):
-                plugin_docs = platform_docs["plugins"][plugin]
+            # all_plugins = platform_docs["plugins"].keys()
+
+            for plugin, plugin_docs in sorted(
+                platform_docs["plugins"].items(),
+                key=lambda x: str(x[1].get("doc_order"))
+                if x[1].get("doc_order")
+                else x[0],
+            ):
                 f.write(f"\n\n## Module `{plugin}`\n")
                 if "support_status" in plugin_docs:
                     f.write(
@@ -692,8 +755,11 @@ def generate(
                     f.write("\n")
 
                 f.write(f"{plugin_docs.get('source_doc') or ''}\n")
+                # Insert custom pre section
+                f.write(plugin_docs.get("custom_docs_pre", ""))
+                f.write("\n### CLI based Ingestion\n")
                 if "extra_deps" in plugin_docs:
-                    f.write("### Install the Plugin\n")
+                    f.write("\n#### Install the Plugin\n")
                     if plugin_docs["extra_deps"] != []:
                         f.write("```shell\n")
                         f.write(f"pip install 'acryl-datahub[{plugin}]'\n")
@@ -703,7 +769,7 @@ def generate(
                             f"The `{plugin}` source works out of the box with `acryl-datahub`.\n"
                         )
                 if "recipe" in plugin_docs:
-                    f.write("\n### Quickstart Recipe\n")
+                    f.write("\n### Starter Recipe\n")
                     f.write(
                         "Check out the following recipe to get started with ingestion! See [below](#config-details) for full configuration options.\n\n\n"
                     )
@@ -740,7 +806,7 @@ def generate(
 </Tabs>\n\n"""
                     )
                 # insert custom plugin docs after config details
-                f.write(plugin_docs.get("custom_docs", ""))
+                f.write(plugin_docs.get("custom_docs_post", ""))
                 if "classname" in plugin_docs:
                     f.write("\n### Code Coordinates\n")
                     f.write(f"- Class Name: `{plugin_docs['classname']}`\n")
diff --git a/metadata-ingestion/src/datahub/ingestion/api/decorators.py b/metadata-ingestion/src/datahub/ingestion/api/decorators.py
index 8cf1cc3f0dca60..5a06957ab97989 100644
--- a/metadata-ingestion/src/datahub/ingestion/api/decorators.py
+++ b/metadata-ingestion/src/datahub/ingestion/api/decorators.py
@@ -28,7 +28,7 @@ def wrapper(cls: Type) -> Type:
 
 
 def platform_name(
-    platform_name: str, id: Optional[str] = None
+    platform_name: str, id: Optional[str] = None, doc_order: Optional[int] = None
 ) -> Callable[[Type], Type]:
     """Adds a get_platform_name method to the decorated class"""
 
@@ -39,6 +39,7 @@ def wrapper(cls: Type) -> Type:
             "get_platform_id",
             lambda: id or platform_name.lower().replace(" ", "-"),
         )
+        setattr(cls, "get_platform_doc_order", lambda: doc_order or None)
 
         return cls
 
diff --git a/metadata-ingestion/src/datahub/ingestion/source/snowflake/snowflake_v2.py b/metadata-ingestion/src/datahub/ingestion/source/snowflake/snowflake_v2.py
index dd5cac8dceb029..69ab76d437f97e 100644
--- a/metadata-ingestion/src/datahub/ingestion/source/snowflake/snowflake_v2.py
+++ b/metadata-ingestion/src/datahub/ingestion/source/snowflake/snowflake_v2.py
@@ -148,7 +148,7 @@
 }
 
 
-@platform_name("Snowflake")
+@platform_name("Snowflake", doc_order=1)
 @config_class(SnowflakeV2Config)
 @support_status(SupportStatus.INCUBATING)
 @capability(SourceCapability.PLATFORM_INSTANCE, "Enabled by default")