From 54fbcd7f89f97ac091493b3211e091d696fffe13 Mon Sep 17 00:00:00 2001
From: pubpub-zz <4083478+pubpub-zz@users.noreply.github.com>
Date: Fri, 21 Jun 2024 21:04:44 +0200
Subject: [PATCH 1/2] ENH: accepts ETen-B5 and UniCNS-UTF16 encodings

closes #2356
---
 pypdf/_cmap.py | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/pypdf/_cmap.py b/pypdf/_cmap.py
index c77a849bc..9ff3c62d3 100644
--- a/pypdf/_cmap.py
+++ b/pypdf/_cmap.py
@@ -121,10 +121,15 @@ def build_char_map_from_dict(
     "/GBK-EUC-V": "gbk",  # TBC
     "/GBK2K-H": "gb18030",
     "/GBK2K-V": "gb18030",
+    "/ETen-B5-H": "cp950",
+    "/ETen-B5-V": "cp950",
+    "/ETenms-B5-H": "cp950",
+    "/ETenms-B5-V": "cp950",
+    "/UniCNS-UTF16-H": "utf-16-be",  # TBC
+    "/UniCNS-UTF16-V": "utf-16-be",  # TBC
     # UCS2 in code
 }
 
-
 # manually extracted from http://mirrors.ctan.org/fonts/adobe/afm/Adobe-Core35_AFMs-229.tar.gz
 _default_fonts_space_width: Dict[str, int] = {
     "/Courier": 600,

From fdbf37c57d9cd2be0ad48ab9ff0bdd12163c2a7d Mon Sep 17 00:00:00 2001
From: pubpub-zz <4083478+pubpub-zz@users.noreply.github.com>
Date: Sat, 22 Jun 2024 12:09:53 +0200
Subject: [PATCH 2/2] from comments

---
 pypdf/_cmap.py     | 16 ++++++++--------
 tests/test_cmap.py |  7 +++++++
 2 files changed, 15 insertions(+), 8 deletions(-)

diff --git a/pypdf/_cmap.py b/pypdf/_cmap.py
index 9ff3c62d3..9a2d10a61 100644
--- a/pypdf/_cmap.py
+++ b/pypdf/_cmap.py
@@ -113,20 +113,20 @@ def build_char_map_from_dict(
 _predefined_cmap: Dict[str, str] = {
     "/Identity-H": "utf-16-be",
     "/Identity-V": "utf-16-be",
-    "/GB-EUC-H": "gbk",  # TBC
-    "/GB-EUC-V": "gbk",  # TBC
-    "/GBpc-EUC-H": "gb2312",  # TBC
-    "/GBpc-EUC-V": "gb2312",  # TBC
-    "/GBK-EUC-H": "gbk",  # TBC
-    "/GBK-EUC-V": "gbk",  # TBC
+    "/GB-EUC-H": "gbk",
+    "/GB-EUC-V": "gbk",
+    "/GBpc-EUC-H": "gb2312",
+    "/GBpc-EUC-V": "gb2312",
+    "/GBK-EUC-H": "gbk",
+    "/GBK-EUC-V": "gbk",
     "/GBK2K-H": "gb18030",
     "/GBK2K-V": "gb18030",
     "/ETen-B5-H": "cp950",
     "/ETen-B5-V": "cp950",
     "/ETenms-B5-H": "cp950",
     "/ETenms-B5-V": "cp950",
-    "/UniCNS-UTF16-H": "utf-16-be",  # TBC
-    "/UniCNS-UTF16-V": "utf-16-be",  # TBC
+    "/UniCNS-UTF16-H": "utf-16-be",
+    "/UniCNS-UTF16-V": "utf-16-be",
     # UCS2 in code
 }
 
diff --git a/tests/test_cmap.py b/tests/test_cmap.py
index b00ba6abb..9dcfb252d 100644
--- a/tests/test_cmap.py
+++ b/tests/test_cmap.py
@@ -199,3 +199,10 @@ def test_ignoring_non_put_entries():
     """Issue #2290"""
     reader = PdfReader(BytesIO(get_data_from_url(name="iss2290.pdf")))
     reader.pages[0].extract_text()
+
+
+@pytest.mark.enable_socket()
+def test_eten_b5():
+    """Issue #2356"""
+    reader = PdfReader(BytesIO(get_data_from_url(name="iss2290.pdf")))
+    reader.pages[0].extract_text().startswith("1/7 \n富邦新終身壽險")