ignore full range of specified characters0.12.8

Fix for issue #55, incorporating pull request #11 both by Harguroicha Hsu

4 files changed, 32 insertions, 3 deletions

diff --git a/README.rst b/README.rst
index 57071da..b381532 100644
--- a/README.rst
+++ b/README.rst
@@ -18,6 +18,10 @@ ChangeLog
 
 ::
 
+  0.12.8 (2016-09-xx):
+     - To be ignored Unicode characters were not properly regex matched
+       (no specific tests, PR by Haraguroicha Hsu)
+
   0.12.7 (2016-09-03):
      - fixing issue 54 empty lines with spaces (reported by Alex Harvey)
 
diff --git a/__init__.py b/__init__.py
index ff4b33c..728eee9 100644
--- a/__init__.py
+++ b/__init__.py
@@ -9,7 +9,7 @@ from __future__ import absolute_import
 
 _package_data = dict(
     full_package_name="ruamel.yaml",
-    version_info=(0, 12, 7),
+    version_info=(0, 12, 8),
     author="Anthon van der Neut",
     author_email="a.van.der.neut@ruamel.eu",
     description="ruamel.yaml is a YAML parser/emitter that supports roundtrip preservation of comments, seq/map flow style, and map key order",  # NOQA
diff --git a/_test/test_comments.py b/_test/test_comments.py
index 63895cc..0e52031 100644
--- a/_test/test_comments.py
+++ b/_test/test_comments.py
@@ -494,7 +494,7 @@ class TestCommentedMapMerge:
 
 class TestEmptyLines:
     # prompted by issue 46 from Alex Harvey
-    def Xtest_issue_46(self):
+    def test_issue_46(self):
         yaml_str = dedent("""\
         ---
         # Please add key/value pairs in alphabetical order
@@ -591,3 +591,23 @@ class TestEmptyLines:
             stripped += line.rstrip() + '\n'
             print(line + '$')
         assert stripped == y
+
+
+class TestUnicodeComments:
+    def test_issue_55(self):  # reported by Haraguroicha Hsu
+        round_trip("""\
+        name: TEST
+        description: test using
+        author: Harguroicha
+        sql:
+          command: |-
+            select name from testtbl where no = :no
+
+          ci-test:
+          - :no: 04043709 # 小花
+          - :no: 05161690 # 茶
+          - :no: 05293147 # 〇𤋥川
+          - :no: 05338777 # 〇〇啓
+          - :no: 05273867 # 〇
+          - :no: 05205786 # 〇𤦌
+        """)
diff --git a/reader.py b/reader.py
index 1257f52..fe6f505 100644
--- a/reader.py
+++ b/reader.py
@@ -145,7 +145,12 @@ class Reader(object):
         self.update(1)
 
     NON_PRINTABLE = re.compile(
-        u'[^\x09\x0A\x0D\x20-\x7E\x85\xA0-\uD7FF\uE000-\uFFFD\U00010000-\U0010FFFF]')
+        u'[^\x09\x0A\x0D\x20-\x7E\x85'
+        u'\xA0-\uD7FF'
+        u'\uE000-\uFFFD'
+        u'\U00010000-\U0010FFFF'
+        u']'
+    )
 
     def check_printable(self, data):
         match = self.NON_PRINTABLE.search(data)