From 44bd4b5eda29a59f5f02dd8ceb2eef39d21d924d Mon Sep 17 00:00:00 2001
From: Mike Gerber <mike.gerber@sbb.spk-berlin.de>
Date: Tue, 2 Jan 2024 20:38:40 +0100
Subject: [PATCH 1/2] =?UTF-8?q?=E2=9A=99=20pre-commit:=20Update=20hooks?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 .pre-commit-config.yaml | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml
index d0ae66d..4f3562a 100644
--- a/.pre-commit-config.yaml
+++ b/.pre-commit-config.yaml
@@ -11,26 +11,26 @@ repos:
     -   id: check-ast
 
 -   repo: https://github.com/psf/black
-    rev: 23.10.0
+    rev: 23.12.1
     hooks:
     -   id: black
 
 -   repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.1.1
+    rev: v0.1.10
     hooks:
     -   args:
-        - --fix
-        - --exit-non-zero-on-fix
+        -   --fix
+        -   --exit-non-zero-on-fix
         id: ruff
 
 -   repo: https://github.com/pre-commit/mirrors-mypy
-    rev: v1.6.1
+    rev: v1.8.0
     hooks:
     -   additional_dependencies:
-        - types-setuptools
+        -   types-setuptools
         id: mypy
 
 -   repo: https://gitlab.com/vojko.pribudic/pre-commit-update
-    rev: v0.1.0
+    rev: v0.1.1
     hooks:
     -   id: pre-commit-update

From c1681551af19922c8fa4164ea76cccdde832c708 Mon Sep 17 00:00:00 2001
From: Mike Gerber <mike.gerber@sbb.spk-berlin.de>
Date: Wed, 3 Jan 2024 19:21:53 +0100
Subject: [PATCH 2/2] =?UTF-8?q?=F0=9F=90=9B=20Fix=20generating=20word=20di?=
 =?UTF-8?q?fferences?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 src/dinglehopper/cli.py | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/src/dinglehopper/cli.py b/src/dinglehopper/cli.py
index e542697..99403ba 100644
--- a/src/dinglehopper/cli.py
+++ b/src/dinglehopper/cli.py
@@ -122,9 +122,11 @@ def process(
 
     gt_text = extract(gt, textequiv_level=textequiv_level)
     ocr_text = extract(ocr, textequiv_level=textequiv_level)
-    gt_words = words_normalized(gt_text)
-    ocr_words = words_normalized(ocr_text)
+    gt_words: list = list(words_normalized(gt_text))
+    ocr_words: list = list(words_normalized(ocr_text))
 
+    assert isinstance(gt_text, ExtractedText)
+    assert isinstance(ocr_text, ExtractedText)
     cer, n_characters = character_error_rate_n(gt_text, ocr_text)
     char_diff_report, diff_c = gen_diff_report(
         gt_text,
@@ -136,6 +138,10 @@ def process(
         differences=differences,
     )
 
+    # {gt,ocr}_words must not be a generator, so we don't drain it for the differences
+    # report.
+    assert isinstance(gt_words, list)
+    assert isinstance(ocr_words, list)
     wer, n_words = word_error_rate_n(gt_words, ocr_words)
     word_diff_report, diff_w = gen_diff_report(
         gt_words,