feat(playwright): add papersize argument

Author: bayangan1991

README.md

@@ -14,17 +14,18 @@ This can be done via a function_url, apigateway or lambda invoke.
 
 Event payload body.
 
-|Field | Type| Description|
-|---|---|---|
-| **javascript (princexml)**   |  boolean (False) | Enables [princeXML's javascript execution](https://www.princexml.com/doc/javascript/). This will not render react but can be used for formatting. |
-| **check_license**  |   boolean (False) | Send this field to receive a check on remaining license usage |
-| **document_content** | string | Embed the html content in the payload. There will be AWS payload size limitations.|
-| **document_url**| url | Fetch the html content from `document_url` to disk before rendering.|
-| **browser_url** | url | Browser the `browser_url` with `playwright` before rendering with `renderer`|
-| **browser_headers**| Mapping[str,str] | Add additional headers to playwright before visiting `browser_url`|
-| **renderer**| `princexml` or `playwright`| Renderer to render the html with |
-| **bucket_name**| string | Output the resulting pdf to `s3://{bucket_name}/{uuid}.pdf`. The lambda will require permission to upload to the bucket. The response will include `bucket`, `key`, `presigned_url`|
-| **presigned_url**| url | Output the resulting pdf to the presigned url. Generate the presigned url with `put_object`. See Output for more information.|
+| Field                      | Type                        | Description                                                                                                                                                                         |
+|----------------------------|-----------------------------|-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+| **javascript (princexml)** | boolean (False)             | Enables [princeXML's javascript execution](https://www.princexml.com/doc/javascript/). This will not render react but can be used for formatting.                                   |
+| **check_license**          | boolean (False)             | Send this field to receive a check on remaining license usage                                                                                                                       |
+| **document_content**       | string                      | Embed the html content in the payload. There will be AWS payload size limitations.                                                                                                  |
+| **document_url**           | url                         | Fetch the html content from `document_url` to disk before rendering.                                                                                                                |
+| **browser_url**            | url                         | Browser the `browser_url` with `playwright` before rendering with `renderer`                                                                                                        |
+| **browser_headers**        | Mapping[str,str]            | Add additional headers to playwright before visiting `browser_url`                                                                                                                  |
+| **browser_papersize**      | `A4` or `letter`            | Size of the page when creating PDF with playwright                                                                                                                                  |                                                                                                                                                                           |
+| **renderer**               | `princexml` or `playwright` | Renderer to render the html with                                                                                                                                                    |
+| **bucket_name**            | string                      | Output the resulting pdf to `s3://{bucket_name}/{uuid}.pdf`. The lambda will require permission to upload to the bucket. The response will include `bucket`, `key`, `presigned_url` |
+| **presigned_url**          | url                         | Output the resulting pdf to the presigned url. Generate the presigned url with `put_object`. See Output for more information.                                                       |
 
 ### Input
 

lambda_function.py

@@ -39,6 +39,11 @@ class Renderers(str, enum.Enum):
     princexml = "princexml"
 
 
+class Papersize(str, enum.Enum):
+    A4 = "A4"
+    Letter = "letter"
+
+
 class Payload(pydantic.BaseModel):
     # NOTE: When updating this model, also update the equivalent documentation
     # General Parameters
@@ -53,6 +58,7 @@ class Payload(pydantic.BaseModel):
     ## Browse the document in a browser before rendering
     browser_url: str | None = None
     browser_headers: dict = pydantic.Field(default_factory=dict)
+    browser_papersize: Papersize = Papersize.A4
     renderer: Renderers = Renderers.princexml
 
     # Output parameters
@@ -151,9 +157,11 @@ def _playwright_visit_page(browser_url: str, headers: dict) -> Iterator[playwrig
         yield page
 
 
-def playwright_page_to_pdf(browser_url: str, headers: dict, output_filepath: str) -> None:
+def playwright_page_to_pdf(
+    browser_url: str, headers: dict, output_filepath: str, papersize: Papersize = Papersize.A4
+) -> None:
     with _playwright_visit_page(browser_url, headers) as page:
-        page.pdf(path=output_filepath, format="A4")
+        page.pdf(path=output_filepath, format=papersize)
 
 
 def playwright_page_to_html_string(browser_url: str, headers: dict) -> str:
@@ -175,6 +183,7 @@ def pdf_from_document_content(payload: Payload, output_filepath: str) -> None:
                 f"file://{temporary_html_file.name}",
                 payload.browser_headers,
                 output_filepath,
+                payload.browser_papersize,
             )
 
 
@@ -197,6 +206,7 @@ def pdf_from_document_url(payload: Payload, output_filepath: str) -> None:
                 f"file://{temporary_html_file.name}",
                 payload.browser_headers,
                 output_filepath,
+                payload.browser_papersize,
             )
 
 
@@ -212,7 +222,12 @@ def pdf_from_browser_url(payload: Payload, output_filepath: str) -> None:
             output_filepath,
         )
     else:
-        playwright_page_to_pdf(payload.browser_url, payload.browser_headers, output_filepath)
+        playwright_page_to_pdf(
+            payload.browser_url,
+            payload.browser_headers,
+            output_filepath,
+            payload.browser_papersize,
+        )
 
 
 def execute(cmd: list[str]) -> None:

tests/test_lambda_e2e.py

@@ -54,8 +54,9 @@ def test_check_license_returns_a_license_payload() -> None:
 
 
 @pytest.mark.parametrize("renderer", ["princexml", "playwright"])
+@pytest.mark.parametrize("browser_papersize", ["A4", "letter"])
 class TestRenderers:
-    def test_generating_pdf_from_document_url(self, renderer: str):
+    def test_generating_pdf_from_document_url(self, renderer: str, browser_papersize: str):
         s3_client = get_s3_client()
 
         key = gen_temp_key()
@@ -67,24 +68,24 @@ def test_generating_pdf_from_document_url(self, renderer: str):
         )
 
         status_code, _, pdf_body = call_lamdba(
-            {"document_url": document_url, "renderer": renderer},
+            {"document_url": document_url, "renderer": renderer, "browser_papersize": browser_papersize},
         )
 
         assert b"Z" in pdf_body
         assert status_code == 200
 
-    def test_generating_pdf_from_document_content(self, renderer: str):
+    def test_generating_pdf_from_document_content(self, renderer: str, browser_papersize: str):
         """Send an embedded html document and receive the pdf bytes for it"""
         status_code, _, pdf_body = call_lamdba(
-            {"document_content": "<h1>Z</h1>", "renderer": renderer},
+            {"document_content": "<h1>Z</h1>", "renderer": renderer, "browser_papersize": browser_papersize},
         )
 
         assert b"Z" in pdf_body
         assert status_code == 200
 
-    def test_generating_pdf_from_browser_url(self, renderer: str):
+    def test_generating_pdf_from_browser_url(self, renderer: str, browser_papersize: str):
         status_code, _, pdf_body = call_lamdba(
-            {"browser_url": "http://google.com", "renderer": renderer},
+            {"browser_url": "http://google.com", "renderer": renderer, "browser_papersize": browser_papersize},
         )
 
         assert b"Z" in pdf_body