allow output of supplimentary unicode characters0.15.17

6 files changed, 34 insertions, 6 deletions

diff --git a/CHANGES b/CHANGES
index daa6d2e..a0f3f3d 100644
--- a/CHANGES
+++ b/CHANGES
@@ -1,3 +1,8 @@
+[0, 15, 17]: 2017-07-03
+  - support for Unicode supplementary Plane **output** with allow_unicode
+    (input was already supported, triggered by
+    `this <https://stackoverflow.com/a/44875714/1307905>`_ Stack Overflow Q&A)
+
 [0, 15, 16]: 2017-07-01
   - minor typing issues (reported and fix provided by
     `Manvendra Singh <https://bitbucket.org/manu-chroma/>`_)
diff --git a/README.rst b/README.rst
index 2358958..174f8f0 100644
--- a/README.rst
+++ b/README.rst
@@ -32,6 +32,11 @@ ChangeLog
 
 .. should insert NEXT: at the beginning of line for next key
 
+0.15.17 (2017-07-03):
+  - support for Unicode supplementary Plane **output**
+    (input was already supported, triggered by
+    `this <https://stackoverflow.com/a/44875714/1307905>`_ Stack Overflow Q&A)
+
 0.15.16 (2017-07-01):
   - minor typing issues (reported and fix provided by
     `Manvendra Singh <https://bitbucket.org/manu-chroma/>`_
diff --git a/__init__.py b/__init__.py
index 012f49a..b803bbe 100644
--- a/__init__.py
+++ b/__init__.py
@@ -7,8 +7,8 @@ if False:  # MYPY
 
 _package_data = dict(
     full_package_name='ruamel.yaml',
-    version_info=(0, 15, 16),
-    __version__='0.15.16',
+    version_info=(0, 15, 17),
+    __version__='0.15.17',
     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/_doc/api.rst b/_doc/api.rst
index 30ee195..c98193c 100644
--- a/_doc/api.rst
+++ b/_doc/api.rst
@@ -76,6 +76,7 @@ all functionality of the old interface will be available via
 Loading
 -------
 
+
 Duplicate keys
 ++++++++++++++
 
@@ -96,7 +97,19 @@ In the old API this is a warning starting with 0.15.2 and an error in
 Dumping
 -------
 
+Controls
+++++++++
+
+On your `YAML()` instance you can set attributes e.g with::
+
+  yaml = YAML(typ='safe', pure=True)
+  yaml.allow_unicode = False
+
+new attributes available are:
 
+`_supplementary`
+   defaults to `True` if Unicode chars larger than 2 bytes. Set to `False` to
+   enforce output of the `\U0001f601` ( presumes `allow_unicode` is `True`
 
 Transparent usage of new and old API
 ------------------------------------
diff --git a/_doc/conf.py b/_doc/conf.py
index e1b1eea..94f85e5 100644
--- a/_doc/conf.py
+++ b/_doc/conf.py
@@ -46,7 +46,7 @@ master_doc = 'index'
 
 # General information about the project.
 project = u'yaml'
-copyright = u'2016, Anthon van der Neut, Ruamel bvba'
+copyright = u'2017, Anthon van der Neut, Ruamel bvba'
 author = u'Anthon van der Neut'
 
 # The version info for the project you're documenting, acts as replacement for
@@ -58,7 +58,7 @@ try:
     # The short X.Y version.
     version = '.'.join(version_info[:2])
     # The full version, including alpha/beta/rc tags.
-    release = __version__
+    version = release = __version__
 except:
     version = release = 'dev'
 
@@ -123,7 +123,7 @@ html_theme = 'default'
 
 # The name for this set of Sphinx documents.  If None, it defaults to
 # "<project> v<release> documentation".
-# html_title = None
+html_title = "python YAML package documentation"
 
 # A shorter title for the navigation bar.  Default is the same as html_title.
 # html_short_title = None
diff --git a/emitter.py b/emitter.py
index bedcf60..e9388bc 100644
--- a/emitter.py
+++ b/emitter.py
@@ -10,6 +10,7 @@ from __future__ import print_function
 # sequence ::= SEQUENCE-START node* SEQUENCE-END
 # mapping ::= MAPPING-START (node node)* MAPPING-END
 
+import sys
 from ruamel.yaml.error import YAMLError, YAMLStreamError
 from ruamel.yaml.events import *                                     # NOQA
 from ruamel.yaml.compat import utf8, text_type, PY2, nprint, dbg, DBG_EVENT, \
@@ -106,6 +107,8 @@ class Emitter(object):
         # Formatting details.
         self.canonical = canonical
         self.allow_unicode = allow_unicode
+        # set to False to get "\Uxxxxxxxx" for non-basic unicode like emojis
+        self.unicode_supplementary = sys.maxunicode > 0xffff
         self.block_seq_indent = block_seq_indent if block_seq_indent else 0
         self.top_level_colon_align = top_level_colon_align
         self.best_indent = 2
@@ -860,7 +863,9 @@ class Emitter(object):
                 line_breaks = True
             if not (ch == u'\n' or u'\x20' <= ch <= u'\x7E'):
                 if (ch == u'\x85' or u'\xA0' <= ch <= u'\uD7FF' or
-                        u'\uE000' <= ch <= u'\uFFFD') and ch != u'\uFEFF':
+                        u'\uE000' <= ch <= u'\uFFFD' or
+                        (self.unicode_supplementary and
+                         (u'\U00010000' <= ch <= u'\U0010FFFF'))) and ch != u'\uFEFF':
                     # unicode_characters = True
                     if not self.allow_unicode:
                         special_characters = True