Fixed arabic extraction test file and white space

py-pdf · Feb 2, 2023 · 25fa0d3 · 25fa0d3
1 parent 56d9a1a
commit 25fa0d3
Show file tree

Hide file tree

Showing 2 changed files with 9 additions and 5 deletions.
diff --git a/pypdf/_page.py b/pypdf/_page.py
@@ -1691,7 +1691,8 @@ def process_operation(operator: bytes, operands: List) -> None:
                                     )
                                 text = ""
                         elif (
-                            abs(delta_y) < f * 0.3
+                            rtl_dir == False
+                            and abs(delta_y) < f * 0.3
                             and abs(delta_x) > current_spacewidth() * f * 15
                         ):
                             if (output + text)[-1] != " ":

diff --git a/tests/test_page.py b/tests/test_page.py
@@ -832,11 +832,14 @@ def test_empyt_password_1088():
     reader = PdfReader(stream)
     len(reader.pages)
 
-
-@pytest.mark.xfail(reason="#1088 / #1126")
+@pytest.mark.external
+# @pytest.mark.xfail(reason="#1088 / #1126")
 def test_arab_text_extraction():
-    reader = PdfReader(SAMPLE_ROOT / "015-arabic/habibi.pdf")
-    assert reader.pages[0].extract_text() == "habibi حَبيبي"
+    # previous habibi.pdf not used anymore and can be deleted
+    url = "https://github.com/py-pdf/pypdf/files/10567398/habibi-fixed.pdf"
+    name = "habibi-fixed-020220231036.pdf"
+    reader = PdfReader(BytesIO(get_pdf_from_url(url, name=name)))
+    assert reader.pages[0].extract_text() == "habibi ﺣَﺒﯿﺒﻲ"
 
 
 @pytest.mark.samples