Skip to content

Adding support to Unicode characters over codepoint 0xffff #63

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
sigmavirus24 merged 5 commits into from
Aug 8, 2017
Merged

Adding support to Unicode characters over codepoint 0xffff #63

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
a06c1f6
A change to a message
peterkmurphy May 6, 2017
cf1c86c
First attack at pyyaml does not support literals in unicode over code…
peterkmurphy May 8, 2017
c60232d
Added emoticon test data files (which will probably break testing)
peterkmurphy May 9, 2017
c67d8df
Suspicious 'expected an exception' messages trimmed
peterkmurphy May 9, 2017
94c3f07
Reverting README to old copy
peterkmurphy May 9, 2017
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Prev Previous commit
Next Next commit
First attack at pyyaml does not support literals in unicode over code… 
…point 0xffff #25
  • Loading branch information
@peterkmurphy
peterkmurphy committed May 8, 2017
commit cf1c86cb86db74206085e6f83e4586ddc7db9ac2
10 changes: 7 additions & 3 deletions lib/yaml/emitter.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,9 +8,13 @@

__all__ = ['Emitter', 'EmitterError']

import sys

from error import YAMLError
from events import *

has_ucs4 = sys.maxunicode > 0xffff

class EmitterError(YAMLError):
pass

Expand Down Expand Up @@ -674,7 +678,7 @@ def analyze_scalar(self, scalar):
# Check for indicators.
if index == 0:
# Leading indicators are special characters.
if ch in u'#,[]{}&*!|>\'\"%@`':
if ch in u'#,[]{}&*!|>\'\"%@`':

@adamchainz adamchainz May 10, 2017

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

trimming trailing whitespace is bad form as it's diff noise

flow_indicators = True
block_indicators = True
if ch in u'?:':
Expand All @@ -701,7 +705,8 @@ def analyze_scalar(self, scalar):
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':
or u'\uE000' <= ch <= u'\uFFFD'
or ((not has_ucs4) or (u'\U00010000' <= ch < u'\U0010ffff'))) and ch != u'\uFEFF':
unicode_characters = True
if not self.allow_unicode:
special_characters = True
Expand Down Expand Up @@ -1137,4 +1142,3 @@ def write_plain(self, text, split=True):
spaces = (ch == u' ')
breaks = (ch in u'\n\x85\u2028\u2029')
end += 1

10 changes: 7 additions & 3 deletions lib/yaml/reader.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -19,7 +19,9 @@

from error import YAMLError, Mark

import codecs, re
import codecs, re, sys

has_ucs4 = sys.maxunicode > 0xffff

class ReaderError(YAMLError):

Expand Down Expand Up @@ -134,7 +136,10 @@ def determine_encoding(self):
self.encoding = 'utf-8'
self.update(1)

NON_PRINTABLE = re.compile(u'[^\x09\x0A\x0D\x20-\x7E\x85\xA0-\uD7FF\uE000-\uFFFD]')
if has_ucs4:
NON_PRINTABLE = re.compile(u'[^\x09\x0A\x0D\x20-\x7E\x85\xA0-\uD7FF\uE000-\uFFFD\U00010000-\U0010ffff]')
else:
NON_PRINTABLE = re.compile(u'[^\x09\x0A\x0D\x20-\x7E\x85\xA0-\uD7FF\uE000-\uFFFD]')
def check_printable(self, data):
match = self.NON_PRINTABLE.search(data)
if match:
Expand Down Expand Up @@ -187,4 +192,3 @@ def update_raw(self, size=1024):
# psyco.bind(Reader)
#except ImportError:
# pass

6 changes: 3 additions & 3 deletions lib3/yaml/emitter.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -671,7 +671,7 @@ def analyze_scalar(self, scalar):
# Check for indicators.
if index == 0:
# Leading indicators are special characters.
if ch in '#,[]{}&*!|>\'\"%@`':
if ch in '#,[]{}&*!|>\'\"%@`':
flow_indicators = True
block_indicators = True
if ch in '?:':
Expand All @@ -698,7 +698,8 @@ def analyze_scalar(self, scalar):
line_breaks = True
if not (ch == '\n' or '\x20' <= ch <= '\x7E'):
if (ch == '\x85' or '\xA0' <= ch <= '\uD7FF'
or '\uE000' <= ch <= '\uFFFD') and ch != '\uFEFF':
or '\uE000' <= ch <= '\uFFFD'
or '\U00010000' <= ch < '\U0010ffff') and ch != '\uFEFF':
unicode_characters = True
if not self.allow_unicode:
special_characters = True
Expand Down Expand Up @@ -1134,4 +1135,3 @@ def write_plain(self, text, split=True):
spaces = (ch == ' ')
breaks = (ch in '\n\x85\u2028\u2029')
end += 1

3 changes: 1 addition & 2 deletions lib3/yaml/reader.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -134,7 +134,7 @@ def determine_encoding(self):
self.encoding = 'utf-8'
self.update(1)

NON_PRINTABLE = re.compile('[^\x09\x0A\x0D\x20-\x7E\x85\xA0-\uD7FF\uE000-\uFFFD]')
NON_PRINTABLE = re.compile('[^\x09\x0A\x0D\x20-\x7E\x85\xA0-\uD7FF\uE000-\uFFFD\U00010000-\U0010ffff]')
def check_printable(self, data):
match = self.NON_PRINTABLE.search(data)
if match:
Expand Down Expand Up @@ -189,4 +189,3 @@ def update_raw(self, size=4096):
# psyco.bind(Reader)
#except ImportError:
# pass