From 641804fe85f3e6d66e5f77998b6e2d6fb0f0031e Mon Sep 17 00:00:00 2001
From: pubpub-zz <4083478+pubpub-zz@users.noreply.github.com>
Date: Tue, 14 Jun 2022 22:29:15 +0200
Subject: [PATCH 1/4] ROB : utf-16-be' codec can't decode (...) #988

the data bytes are not matching encoding expectation
---
 PyPDF2/_page.py | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/PyPDF2/_page.py b/PyPDF2/_page.py
index 031aa1471..92886a95a 100644
--- a/PyPDF2/_page.py
+++ b/PyPDF2/_page.py
@@ -1218,7 +1218,13 @@ def process_operation(operator: bytes, operands: List) -> None:
                     else operands[0]
                 )
                 if isinstance(cmap[0], str):
-                    t = tt.decode(cmap[0], "surrogatepass")  # apply str encoding
+                    try:
+                        t = tt.decode(cmap[0], "surrogatepass")  # apply str encoding
+                    except:  # the data does not match the expectation, we use the alternative ; text extraction may not be good
+                        t = tt.decode(
+                            "utf-16-be" if cmap[0] == "charmap" else "charmap",
+                            "surrogatepass",
+                        )  # apply str encoding
                 else:  # apply dict encoding
                     t = "".join(
                         [

From 7eaf7543d483f73145c13a3bf82ab0214f51f275 Mon Sep 17 00:00:00 2001
From: pubpub-zz <4083478+pubpub-zz@users.noreply.github.com>
Date: Tue, 14 Jun 2022 22:39:47 +0200
Subject: [PATCH 2/4] flake8

---
 PyPDF2/_page.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/PyPDF2/_page.py b/PyPDF2/_page.py
index 92886a95a..bd24fbe28 100644
--- a/PyPDF2/_page.py
+++ b/PyPDF2/_page.py
@@ -1220,7 +1220,7 @@ def process_operation(operator: bytes, operands: List) -> None:
                 if isinstance(cmap[0], str):
                     try:
                         t = tt.decode(cmap[0], "surrogatepass")  # apply str encoding
-                    except:  # the data does not match the expectation, we use the alternative ; text extraction may not be good
+                    except Exception:  # the data does not match the expectation, we use the alternative ; text extraction may not be good
                         t = tt.decode(
                             "utf-16-be" if cmap[0] == "charmap" else "charmap",
                             "surrogatepass",

From e4d8d68c9c953c477b77db0f91d5cb8b83ed38fe Mon Sep 17 00:00:00 2001
From: pubpub-zz <4083478+pubpub-zz@users.noreply.github.com>
Date: Tue, 14 Jun 2022 22:40:41 +0200
Subject: [PATCH 3/4] fix assertion error #960

---
 PyPDF2/_cmap.py | 1 -
 1 file changed, 1 deletion(-)

diff --git a/PyPDF2/_cmap.py b/PyPDF2/_cmap.py
index bb9c477a1..430f3d68f 100644
--- a/PyPDF2/_cmap.py
+++ b/PyPDF2/_cmap.py
@@ -222,7 +222,6 @@ def parse_to_unicode(
                     ] = unhexlify(sq).decode("utf-16-be", "surrogatepass")
                     int_entry.append(a)
                     a += 1
-                    assert a > b
             else:
                 c = int(lst[2], 16)
                 fmt2 = b"%%0%dX" % len(lst[2])

From 6a33f1109d5fbdbdeb4a88baf595ceb38f2f4bb8 Mon Sep 17 00:00:00 2001
From: pubpub-zz <4083478+pubpub-zz@users.noreply.github.com>
Date: Wed, 15 Jun 2022 20:10:15 +0200
Subject: [PATCH 4/4] extend test tika

---
 tests/__init__.py       | 2 ++
 tests/test_workflows.py | 5 +++++
 2 files changed, 7 insertions(+)

diff --git a/tests/__init__.py b/tests/__init__.py
index 637a97714..6aee556d8 100644
--- a/tests/__init__.py
+++ b/tests/__init__.py
@@ -1,4 +1,5 @@
 import os
+import ssl
 import urllib.request
 
 
@@ -21,6 +22,7 @@ def get_pdf_from_url(url: str, name: str) -> bytes:
         os.mkdir(cache_dir)
     cache_path = os.path.join(cache_dir, name)
     if not os.path.exists(cache_path):
+        ssl._create_default_https_context = ssl._create_unverified_context
         with urllib.request.urlopen(url) as response, open(
             cache_path, "wb"
         ) as out_file:
diff --git a/tests/test_workflows.py b/tests/test_workflows.py
index b928b858a..c5f8ebf20 100644
--- a/tests/test_workflows.py
+++ b/tests/test_workflows.py
@@ -162,6 +162,11 @@ def test_rotate_45():
             [0, 1, 34, 35, 36, 118, 119, 120, 121],
         ),
         (True, "https://github.com/py-pdf/PyPDF2/files/8884493/998167.pdf", [0]),
+        (
+            True,
+            "https://corpora.tika.apache.org/base/docs/govdocs1/971/971703.pdf",
+            [0, 1, 5, 8, 14],
+        ),
     ],
 )
 def test_extract_textbench(enable, url, pages, print_result=False):