fix issue 54: space on empty lines break roundtrip0.12.7

4 files changed, 51 insertions, 3 deletions

diff --git a/README.rst b/README.rst
index 49799c6..57071da 100644
--- a/README.rst
+++ b/README.rst
@@ -18,6 +18,9 @@ ChangeLog
 
 ::
 
+  0.12.7 (2016-09-03):
+     - fixing issue 54 empty lines with spaces (reported by Alex Harvey)
+
   0.12.6 (2016-09-03):
      - fixing issue 46 empty lines between top-level keys were gobbled (but
        not between sequence elements, nor between keys in netsted mappings
diff --git a/__init__.py b/__init__.py
index e880d11..ff4b33c 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, 6),
+    version_info=(0, 12, 7),
     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 4bdaed1..63895cc 100644
--- a/_test/test_comments.py
+++ b/_test/test_comments.py
@@ -569,3 +569,25 @@ class TestEmptyLines:
 
           - 3
         """)
+
+    def test_line_with_only_spaces(self):
+        # issue 54
+        yaml_str = "---\n\na: 'x'\n \nb: y\n"
+        d = round_trip_load(yaml_str, preserve_quotes=True)
+        y = round_trip_dump(d, explicit_start=True)
+        stripped = ""
+        for line in yaml_str.splitlines():
+            stripped += line.rstrip() + '\n'
+            print(line + '$')
+        assert stripped == y
+
+    def test_some_eol_spaces(self):
+        # spaces after tokens and on empty lines
+        yaml_str = '---  \n  \na: "x"  \n   \nb: y  \n'
+        d = round_trip_load(yaml_str, preserve_quotes=True)
+        y = round_trip_dump(d, explicit_start=True)
+        stripped = ""
+        for line in yaml_str.splitlines():
+            stripped += line.rstrip() + '\n'
+            print(line + '$')
+        assert stripped == y
diff --git a/scanner.py b/scanner.py
index 5d50e27..ab78d51 100644
--- a/scanner.py
+++ b/scanner.py
@@ -1643,6 +1643,7 @@ class RoundTripScanner(Scanner):
                     self.allow_simple_key = True
                 return comment, start_mark, end_mark
             if self.scan_line_break():
+                start_mark = self.get_mark()
                 if not self.flow_level:
                     self.allow_simple_key = True
                 ch = self.peek()
@@ -1650,14 +1651,36 @@ class RoundTripScanner(Scanner):
                     start_mark = self.get_mark()
                     comment = ''
                     while ch:
-                        ch = self.scan_line_break()
+                        ch = self.scan_line_break(empty_line=True)
                         comment += ch
-                    # print('ch', repr(comment))
                     end_mark = self.get_mark()
                     return comment, start_mark, end_mark
             else:
                 found = True
 
+    def scan_line_break(self, empty_line=False):
+        # Transforms:
+        #   '\r\n'      :   '\n'
+        #   '\r'        :   '\n'
+        #   '\n'        :   '\n'
+        #   '\x85'      :   '\n'
+        #   '\u2028'    :   '\u2028'
+        #   '\u2029     :   '\u2029'
+        #   default     :   ''
+        ch = self.peek()
+        if ch in u'\r\n\x85':
+            if self.prefix(2) == u'\r\n':
+                self.forward(2)
+            else:
+                self.forward()
+            return u'\n'
+        elif ch in u'\u2028\u2029':
+            self.forward()
+            return ch
+        elif empty_line and ch in '\t ':
+            return ch
+        return u''
+
 # try:
 #     import psyco
 #     psyco.bind(Scanner)