TST: Add test for arab text (#1127)

py-pdf · Jul 17, 2022 · 0b693e1 · 0b693e1
1 parent ae0ff49
commit 0b693e1
Show file tree

Hide file tree

Showing 2 changed files with 11 additions and 4 deletions.
diff --git a/sample-files b/sample-files
diff --git a/tests/test_page.py b/tests/test_page.py
@@ -2,6 +2,7 @@
 import os
 from copy import deepcopy
 from io import BytesIO
+from pathlib import Path
 
 import pytest
 
@@ -16,11 +17,11 @@
 TESTS_ROOT = os.path.abspath(os.path.dirname(__file__))
 PROJECT_ROOT = os.path.dirname(TESTS_ROOT)
 RESOURCE_ROOT = os.path.join(PROJECT_ROOT, "resources")
-EXTERNAL_ROOT = os.path.join(PROJECT_ROOT, "sample-files")
+EXTERNAL_ROOT = Path(PROJECT_ROOT) / "sample-files"
 
 
 def get_all_sample_files():
-    with open(os.path.join(EXTERNAL_ROOT, "files.json")) as fp:
+    with open(EXTERNAL_ROOT / "files.json") as fp:
         data = fp.read()
     meta = json.loads(data)
     return meta
@@ -37,7 +38,7 @@ def get_all_sample_files():
 )
 @pytest.mark.filterwarnings("ignore::PyPDF2.errors.PdfReadWarning")
 def test_read(meta):
-    pdf_path = os.path.join(EXTERNAL_ROOT, meta["path"])
+    pdf_path = EXTERNAL_ROOT / meta["path"]
     reader = PdfReader(pdf_path)
     reader.pages[0]
     assert len(reader.pages) == meta["pages"]
@@ -342,3 +343,9 @@ def test_empyt_password_1088():
     stream = BytesIO(get_pdf_from_url(url, name=name))
     reader = PdfReader(stream)
     len(reader.pages)
+
+
+@pytest.mark.xfail(reason="#1088 / #1126")
+def test_arab_text_extraction():
+    reader = PdfReader(EXTERNAL_ROOT / "015-arabic/habibi.pdf")
+    assert reader.pages[0].extract_text() == "habibi حَبيبي"
+37 −0		015-arabic/README.md
+ −		015-arabic/habibi-oneline-cmap.pdf
+9 −0		015-arabic/habibi.html
+ −		015-arabic/habibi.pdf
+18 −0		files.json