From dbf7718aee8d98ac59577ff54e5b6ebf13eefaba Mon Sep 17 00:00:00 2001
From: benoit74 <benoit74@users.noreply.github.com>
Date: Mon, 29 Jul 2024 14:00:18 +0000
Subject: [PATCH] fixup! Drop disallowed control characters and strip blank
 characters

---
 CHANGELOG.md                     |  1 +
 src/zimscraperlib/zim/creator.py | 22 +++++++++-------------
 2 files changed, 10 insertions(+), 13 deletions(-)

diff --git a/CHANGELOG.md b/CHANGELOG.md
index e770241d..182f53c4 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -10,6 +10,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 ### Added
 
 - Add utility function to compute ZIM Tags #164, including deduplication #156
+- Metadata does not automatically drops control characters #159
 
 ### Fixed
 
diff --git a/src/zimscraperlib/zim/creator.py b/src/zimscraperlib/zim/creator.py
index 97478a88..9198980a 100644
--- a/src/zimscraperlib/zim/creator.py
+++ b/src/zimscraperlib/zim/creator.py
@@ -67,7 +67,7 @@
 )
 
 # All control characters are disallowed in str metadata except \n, \r and \t
-CONTROL_CHARACTERS_REGEX = regex.compile(r"(?![\n\t\r])\p{C}")
+UNWANTED_CONTROL_CHARACTERS_REGEX = regex.compile(r"(?![\n\t\r])\p{C}")
 
 
 def mimetype_for(
@@ -256,10 +256,9 @@ def add_metadata(
     ):
         # drop control characters before passing them to libzim
         if isinstance(content, str):
-            if CONTROL_CHARACTERS_REGEX.search(content):
-                content = CONTROL_CHARACTERS_REGEX.sub("", content).strip(" \r\n\t")
-            else:
-                content = content.strip(" \r\n\t")
+            content = UNWANTED_CONTROL_CHARACTERS_REGEX.sub("", content).strip(
+                " \r\n\t"
+            )
         if not self.disable_metadata_checks:
             self.validate_metadata(name, content)
         if name == "Date" and isinstance(content, (datetime.date, datetime.datetime)):
@@ -314,16 +313,13 @@ def config_metadata(
             }
         )
         self._metadata.update(extras)
-        for k, v in self._metadata.items():
+        for metadata_key, metadata_value in self._metadata.items():
             # drop control characters so that proper value is stored in memory and
             # logged in DEBUG mode ; also strip blank characters
-            if isinstance(v, str):
-                if CONTROL_CHARACTERS_REGEX.search(v):
-                    self._metadata[k] = CONTROL_CHARACTERS_REGEX.sub("", v).strip(
-                        " \r\n\t"
-                    )
-                else:
-                    self._metadata[k] = v.strip(" \r\n\t")
+            if isinstance(metadata_value, str):
+                self._metadata[metadata_key] = UNWANTED_CONTROL_CHARACTERS_REGEX.sub(
+                    "", metadata_value
+                ).strip(" \r\n\t")
         return self
 
     def config_dev_metadata(self, **extras: str):