implement 'parse_unicode_escapes()'

CHANGELOG.md

@@ -1,5 +1,7 @@
 # Changelog
 
+## Unreleased
+
 ## 1.8.6 - 2019-06-14
 ### Additions
 - Support for

gallery_dl/text.py

@@ -174,6 +174,17 @@ def extract_from(txt, pos=0, default=""):
     return extr
 
 
+def parse_unicode_escapes(txt):
+    """Convert JSON Unicode escapes in 'txt' into actual characters"""
+    if "\\u" in txt:
+        return re.sub(r"\\u([0-9a-fA-F]{4})", _hex_to_char, txt)
+    return txt
+
+
+def _hex_to_char(match):
+    return chr(int(match.group(1), 16))
+
+
 def parse_bytes(value, default=0, suffixes="bkmgtp"):
     """Convert a bytes-amount ("500k", "2.5M", ...) to int"""
     try:

gallery_dl/version.py

@@ -6,4 +6,4 @@
 # it under the terms of the GNU General Public License version 2 as
 # published by the Free Software Foundation.
 
-__version__ = "1.8.6"
+__version__ = "1.8.7-dev"

test/test_text.py

@@ -271,6 +271,18 @@ class TestText(unittest.TestCase):
         self.assertEqual(e("[", "]"), "END")
         self.assertEqual(e("[", "]"), "END")
 
+    def test_parse_unicode_escapes(self, f=text.parse_unicode_escapes):
+        self.assertEqual(f(""), "")
+        self.assertEqual(f("foobar"), "foobar")
+        self.assertEqual(f("foo’bar"), "foo’bar")
+        self.assertEqual(f("foo\\u2019bar"), "foo’bar")
+        self.assertEqual(f("foo\\u201bar"), "foo‛ar")
+        self.assertEqual(f("foo\\u201zar"), "foo\\u201zar")
+        self.assertEqual(
+            f("\\u2018foo\\u2019\\u2020bar\\u00ff"),
+            "‘foo’†barÿ",
+        )
+
     def test_parse_bytes(self, f=text.parse_bytes):
         self.assertEqual(f("0"), 0)
         self.assertEqual(f("50"), 50)