fix for issue #58, endless loop in token scanning

4 files changed, 32 insertions, 1 deletions

diff --git a/README.rst b/README.rst
index 15a10b2..9101755 100644
--- a/README.rst
+++ b/README.rst
@@ -18,6 +18,10 @@ ChangeLog
 
 ::
 
+  0.12.11 (2016-09-06):
+   - Fix issue 58 endless loop in scanning tokens (reported by 
+     Christopher Lambert)
+
   0.12.10 (2016-09-05):
    - Make previous fix depend on unicode char width (32 bit unicode support
      is a problem on MacOS reported by David Tagatac)
diff --git a/__init__.py b/__init__.py
index 69a0d81..eb634fb 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, 10),
+    version_info=(0, 12, 11, "dev"),
     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 4014509..b858fbc 100644
--- a/_test/test_comments.py
+++ b/_test/test_comments.py
@@ -592,6 +592,29 @@ class TestEmptyLines:
             print(line + '$')
         assert stripped == y
 
+    def test_issue_54_not_ok(self):
+        yaml_str = dedent("""\
+        toplevel:
+
+            # some comment
+            sublevel: 300
+        """)
+        d = round_trip_load(yaml_str)
+        print(d.ca)
+        y = round_trip_dump(d, indent=4)
+        print(y.replace('\n', '$\n'))
+        assert yaml_str == y
+
+    def test_issue_54_ok(self):
+        yaml_str = dedent("""\
+        toplevel:
+            # some comment
+            sublevel: 300
+        """)
+        d = round_trip_load(yaml_str)
+        y = round_trip_dump(d, indent=4)
+        assert yaml_str == y
+
 
 class TestUnicodeComments:
     @pytest.mark.skipif(ruamel.yaml.reader.Reader.UNICODE_SIZE < 4,
diff --git a/scanner.py b/scanner.py
index ab78d51..f37e656 100644
--- a/scanner.py
+++ b/scanner.py
@@ -1653,6 +1653,9 @@ class RoundTripScanner(Scanner):
                     while ch:
                         ch = self.scan_line_break(empty_line=True)
                         comment += ch
+                    if self.peek() == '#':  # empty line followed by indented real cmment
+                        comment = comment.rsplit('\n', 1)[0] + '\n'
+                    print('comment', repr(comment), self.peek() == '#')
                     end_mark = self.get_mark()
                     return comment, start_mark, end_mark
             else:
@@ -1678,6 +1681,7 @@ class RoundTripScanner(Scanner):
             self.forward()
             return ch
         elif empty_line and ch in '\t ':
+            self.forward()
             return ch
         return u''