Update xhtml2pdf

digitalfabrik · Feb 24, 2023 · 988cd16 · 988cd16
1 parent ea9b69d
commit 988cd16
Show file tree

Hide file tree

Showing 11 changed files with 18 additions and 20 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -1,6 +1,8 @@
 UNRELEASED
 ----------
 
+* [ [#1498](https://github.com/digitalfabrik/integreat-cms/issues/1498) ] Fix PDF errors on specific pages in Arabic & Farsi
+
 
 2023.2.2
 --------

diff --git a/pyproject.toml b/pyproject.toml
@@ -70,7 +70,7 @@ dependencies = [
     "rules",
     "six",
     "webauthn",
-    "xhtml2pdf==0.2.8",
+    "xhtml2pdf",
 ]
 
 [project.optional-dependencies]
@@ -157,10 +157,10 @@ pinned = [
     "pydantic==1.10.5",
     "Pygments==2.14.0",
     "pyHanko==0.17.0",
-    "pyhanko-certvalidator==0.20.0",
+    "pyhanko-certvalidator==0.20.1",
     "pyOpenSSL==23.0.0",
     "pyotp==2.8.0",
-    "PyPDF3==1.0.6",
+    "pypdf==3.4.1",
     "pypng==0.20220715.0",
     "pyrsistent==0.19.3",
     "python-bidi==0.4.2",
@@ -180,7 +180,6 @@ pinned = [
     "stack-data==0.6.2",
     "svglib==1.5.1",
     "tinycss2==1.2.1",
-    "tqdm==4.64.1",
     "traitlets==5.9.0",
     "typing_extensions==4.5.0",
     "tzdata==2022.7",
@@ -190,7 +189,7 @@ pinned = [
     "wcwidth==0.2.6",
     "webauthn==1.7.2",
     "webencodings==0.5.1",
-    "xhtml2pdf==0.2.8",
+    "xhtml2pdf==0.2.9",
     "yarl==1.8.2",
 ]
 

diff --git a/tests/pdf/files/28814d44dd/Integreat - Ukrainisch - Ласкаво просимо в Аугсбург.pdf b/tests/pdf/files/28814d44dd/Integreat - Ukrainisch - Ласкаво просимо в Аугсбург.pdf
diff --git a/tests/pdf/files/3b02f5ea5b/Integreat - Arabisch - معلومات الوصول.pdf b/tests/pdf/files/3b02f5ea5b/Integreat - Arabisch - معلومات الوصول.pdf
diff --git a/tests/pdf/files/52d22a85dc/Integreat - Amharisch - እንኳን ደህና መጡ.pdf b/tests/pdf/files/52d22a85dc/Integreat - Amharisch - እንኳን ደህና መጡ.pdf
diff --git a/tests/pdf/files/6262976c99/Integreat - Deutsch - Willkommen.pdf b/tests/pdf/files/6262976c99/Integreat - Deutsch - Willkommen.pdf
diff --git a/tests/pdf/files/92ff67bd01/Integreat - Deutsch - Augsburg.pdf b/tests/pdf/files/92ff67bd01/Integreat - Deutsch - Augsburg.pdf
diff --git a/tests/pdf/files/ba6f45d0ab/Integreat - Griechisch - Καλώς ήλθατε στο Augsburg.pdf b/tests/pdf/files/ba6f45d0ab/Integreat - Griechisch - Καλώς ήλθατε στο Augsburg.pdf
diff --git a/tests/pdf/files/cdff964723/Integreat - German - Willkommen.pdf b/tests/pdf/files/cdff964723/Integreat - German - Willkommen.pdf
diff --git a/tests/pdf/files/e155c5e38b/Integreat - Englisch - Welcome.pdf b/tests/pdf/files/e155c5e38b/Integreat - Englisch - Welcome.pdf
diff --git a/tests/pdf/test_pdf_export.py b/tests/pdf/test_pdf_export.py
@@ -3,7 +3,7 @@
 from urllib.parse import urlencode, quote
 
 import pytest
-import PyPDF3
+import pypdf
 
 from django.urls import reverse
 
@@ -107,25 +107,22 @@ def test_pdf_export(
         print(response.headers)
         assert response.headers.get("Content-Type") == "application/pdf"
         # Compare file content
-        result_pdf = PyPDF3.PdfFileReader(
-            io.BytesIO(b"".join(response.streaming_content))
-        )
+        result_pdf = pypdf.PdfReader(io.BytesIO(b"".join(response.streaming_content)))
         # pylint: disable=consider-using-with
-        expected_pdf = PyPDF3.PdfFileReader(
+        expected_pdf = pypdf.PdfReader(
             open(f"tests/pdf/files/{expected_filename}", "rb")
         )
         # Assert that both documents have same number of pages
-        assert result_pdf.numPages == expected_pdf.numPages
+        assert len(result_pdf.pages) == len(expected_pdf.pages)
         # Assert that the content is identical
-        for page_number in range(result_pdf.numPages):
-            result_page = result_pdf.getPage(page_number)
-            expected_page = expected_pdf.getPage(page_number)
-            assert result_page.artBox == expected_page.artBox
-            assert result_page.bleedBox == expected_page.bleedBox
-            assert result_page.cropBox == expected_page.cropBox
-            assert result_page.mediaBox == expected_page.mediaBox
-            assert result_page.extractText() == expected_page.extractText()
-            assert result_page.getContents() == expected_page.getContents()
+        for page_number, result_page in enumerate(result_pdf.pages):
+            expected_page = expected_pdf.pages[page_number]
+            assert result_page.artbox == expected_page.artbox
+            assert result_page.bleedbox == expected_page.bleedbox
+            assert result_page.cropbox == expected_page.cropbox
+            assert result_page.mediabox == expected_page.mediabox
+            assert result_page.extract_text() == expected_page.extract_text()
+            assert result_page.get_contents() == expected_page.get_contents()
 
 
 # pylint: disable=unused-argument,too-many-locals