Fix performance of countPages in thumbnail lambda (#2616)

quiltdata · Jan 18, 2022 · e8ff056 · e8ff056
1 parent c6e6d64
commit e8ff056
Show file tree

Hide file tree

Showing 2 changed files with 8 additions and 15 deletions.
diff --git a/docs/CHANGELOG.md b/docs/CHANGELOG.md
@@ -20,6 +20,7 @@
 ## Catalog, Lambdas
 * [Changed] pkgselect: make directly invocable, always use execution role ([#2560](https://github.com/quiltdata/quilt/pull/2560))
 * [Changed] Move package listing / querying to GraphQL ([#2552](https://github.com/quiltdata/quilt/pull/2552))
+* [Changed] Fix performance of `countPages` in thumbnail lambda ([#2616](https://github.com/quiltdata/quilt/pull/2616)).
 * [Fixed] Improve upload performance and stability, fix some hashing-related errors ([#2532](https://github.com/quiltdata/quilt/pull/2532))
 * [Added] Echarts renderer ([#2382](https://github.com/quiltdata/quilt/pull/2382))
 * [Added] Set height for `quilt_summarize.json` files ([#2474](https://github.com/quiltdata/quilt/pull/2474))

diff --git a/lambdas/thumbnail/index.py b/lambdas/thumbnail/index.py
@@ -16,6 +16,7 @@
 
 import imageio
 import numpy as np
+import pdf2image
 import requests
 from aicsimageio import AICSImage, readers
 from pdf2image import convert_from_bytes
@@ -276,24 +277,15 @@ def lambda_handler(request):
     if input_ == "pdf":
         set_pdf_env()
         try:
-            kwargs = {
-                # respect width but not necessarily height to preserve aspect ratio
-                "size": (size[0], None),
-                "fmt": "JPEG",
-            }
-            if not count_pages:
-                kwargs["first_page"] = page
-                kwargs["last_page"] = page
-
             pages = convert_from_bytes(
                 resp.content,
-                **kwargs,
+                # respect width but not necessarily height to preserve aspect ratio
+                size=(size[0], None),
+                fmt="JPEG",
+                first_page=page,
+                last_page=page,
             )
-            num_pages = len(pages)
             preview = pages[0]
-            if count_pages:
-                # shift 1-index to 0-index
-                preview = pages[page - 1]
         except (
                 IndexError,
                 PDFInfoNotInstalledError,
@@ -308,7 +300,7 @@ def lambda_handler(request):
             'thumbnail_size': preview.size,
         }
         if count_pages:
-            info['page_count'] = num_pages
+            info['page_count'] = pdf2image.pdfinfo_from_bytes(resp.content)["Pages"]
 
         thumbnail_bytes = BytesIO()
         preview.save(thumbnail_bytes, thumbnail_format)