Switch from CSV to YAML

requirements/ci-3.11.txt

@@ -69,6 +69,8 @@ pytest-timeout==2.1.0
     # via -r requirements/ci.in
 pytest-xdist==3.3.1
     # via -r requirements/ci.in
+pyyaml==6.0.1
+    # via -r requirements/ci.in
 ruff==0.0.290
     # via -r requirements/ci.in
 typeguard==4.1.2

requirements/ci.in

@@ -17,3 +17,4 @@ pytest-cov
 typeguard
 types-dataclasses
 types-Pillow
+pyyaml

requirements/ci.txt

@@ -83,6 +83,8 @@ pytest-timeout==2.1.0
     # via -r requirements/ci.in
 pytest-xdist==3.0.2
     # via -r requirements/ci.in
+pyyaml==6.0.1
+    # via -r requirements/ci.in
 six==1.16.0
     # via flake8-print
 tomli==1.2.3

tests/__init__.py

@@ -1,11 +1,12 @@
 import concurrent.futures
-import csv
 import ssl
 import urllib.request
 from pathlib import Path
 from typing import Dict, List, Optional
 from urllib.error import HTTPError
 
+import yaml
+
 from pypdf.generic import DictionaryObject, IndirectObject
 
 
@@ -113,15 +114,10 @@ def is_sublist(child_list, parent_list):
     return is_sublist(child_list, parent_list[1:])
 
 
-def read_csv_to_list_of_dicts(file_path: Path) -> List[Dict[str, str]]:
-    data_list = []
-
-    with open(file_path, newline="", encoding="utf-8") as file:
-        reader = csv.DictReader(file)
-
-        data_list = list(reader)
-
-    return data_list
+def read_yaml_to_list_of_dicts(yaml_file: Path) -> List[Dict[str, str]]:
+    with open(yaml_file) as yaml_input:
+        data = yaml.safe_load(yaml_input)
+    return data
 
 
 def download_test_pdfs():
@@ -130,7 +126,7 @@ def download_test_pdfs():
 
     This is especially important to avoid pytest timeouts.
     """
-    pdfs = read_csv_to_list_of_dicts(Path(__file__).parent / "example_files.csv")
+    pdfs = read_yaml_to_list_of_dicts(Path(__file__).parent / "example_files.yaml")
 
     with concurrent.futures.ThreadPoolExecutor(max_workers=20) as executor:
         futures = [
@@ -141,7 +137,7 @@ def download_test_pdfs():
 
 
 def test_csv_consistency():
-    pdfs = read_csv_to_list_of_dicts(Path(__file__).parent / "example_files.csv")
+    pdfs = read_yaml_to_list_of_dicts(Path(__file__).parent / "example_files.csv")
     # Ensure the names are unique
     assert len(pdfs) == len({pdf["name"] for pdf in pdfs})
 

tests/example_files.yaml

@@ -0,0 +1,24 @@
+- local_filename: 2201.00214.pdf
+  url: https://arxiv.org/pdf/2201.00214.pdf
+- local_filename: ASurveyofImageClassificationBasedTechniques.pdf
+  url: https://raw.githubusercontent.com/xyegithub/myBlog/12127c712ac2008782616c743224b187a4069477/posts/c94b2364/paper_pdfs/ImageClassification/2007%2CASurveyofImageClassificationBasedTechniques.pdf
+- local_filename: Giacalone.pdf
+  url: https://github.com/yxj-HGNwmb5kdp8ewr/yxj-HGNwmb5kdp8ewr.github.io/raw/master/files/Giacalone%20Llobell%20Jaeger%20(2022)%20Food%20Qual%20Prefer.pdf
+- local_filename: iss1718.pdf
+  url: https://github.com/py-pdf/pypdf/files/10983477/Ballinasloe_WS.pdf
+- local_filename: iss2077.pdf
+  url: https://github.com/py-pdf/pypdf/files/12309492/example_134.pdf
+- local_filename: pdf_font_garbled.pdf
+  url: https://github.com/py-pdf/pypdf/files/11219022/pdf_font_garbled.pdf
+- local_filename: The%20lean%20times%20in%20the%20Peruvian%20economy.pdf
+  url: https://github.com/alexanderquispe/1REI05/raw/main/reports/report_1/The%20lean%20times%20in%20the%20Peruvian%20economy.pdf
+- local_filename: tika-908104.pdf
+  url: https://corpora.tika.apache.org/base/docs/govdocs1/908/908104.pdf
+- local_filename: tika-923406.pdf
+  url: https://corpora.tika.apache.org/base/docs/govdocs1/923/923406.pdf
+- local_filename: tika-955562.pdf
+  url: https://corpora.tika.apache.org/base/docs/govdocs1/955/955562.pdf
+- local_filename: tika-959173.pdf
+  url: https://corpora.tika.apache.org/base/docs/govdocs1/959/959173.pdf
+- local_filename: waarom-meisjes-het-beter-doen-op-HAVO-en-VWO-ROA.pdf
+  url: https://github.com/py-pdf/pypdf/files/10773829/waarom-meisjes-het-beter-doen-op-HAVO-en-VWO-ROA.pdf