From 3dfed88a2a2ef90471e4e658c7c2ba82a99e4447 Mon Sep 17 00:00:00 2001 From: CyMule Date: Wed, 7 Jan 2026 10:39:15 -0500 Subject: [PATCH] perf: upgrade pdfminer-six to 20260107 Fixes ~15-18% performance regression introduced in 20251230 where f-strings were evaluated eagerly even when logging was disabled. See: https://github.com/pdfminer/pdfminer.six/issues/1233 Fix: https://github.com/pdfminer/pdfminer.six/pull/1234 --- CHANGELOG.md | 5 +++++ requirements/extra-pdf-image.txt | 2 +- unstructured/__version__.py | 2 +- 3 files changed, 7 insertions(+), 2 deletions(-) diff --git a/CHANGELOG.md b/CHANGELOG.md index f51e422e02..aae973d8ed 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -1,3 +1,8 @@ +## 0.18.27-dev5 + +### Enhancement +- Upgrade pdfminer-six to 20260107 to fix ~15-18% performance regression from eager f-string evaluation + ## 0.18.27-dev4 ### Fixes diff --git a/requirements/extra-pdf-image.txt b/requirements/extra-pdf-image.txt index 1ccfed216d..047a52cde2 100644 --- a/requirements/extra-pdf-image.txt +++ b/requirements/extra-pdf-image.txt @@ -146,7 +146,7 @@ pandas==2.3.3 # via unstructured-inference pdf2image==1.17.0 # via -r extra-pdf-image.in -pdfminer-six==20251230 +pdfminer-six==20260107 # via # -r extra-pdf-image.in # unstructured-inference diff --git a/unstructured/__version__.py b/unstructured/__version__.py index cd393308d2..c72d9a6020 100644 --- a/unstructured/__version__.py +++ b/unstructured/__version__.py @@ -1 +1 @@ -__version__ = "0.18.27-dev4" # pragma: no cover +__version__ = "0.18.27-dev5" # pragma: no cover