Module:DecodeEncode/sandbox - Revision history

Gonnym: simplify code

2023-03-21T15:03:22Z

simplify code

← Previous revision		Revision as of 15:03, 21 March 2023
Line 23:		Line 23:

	function p.decode( frame )		function p.decode( frame )
	local s		local s = frame.args['s'] or ''
	local subset_only		local subset_only = _getBoolean(frame.args['subset_only'] or false)

	s = frame.args['s'] or ''
	subset_only = _getBoolean(frame.args['subset_only'] or false)

	return p._decode( s, subset_only )		return p._decode( s, subset_only )
Line 33:		Line 30:

	function p._decode( s, subset_only )		function p._decode( s, subset_only )
	local ret = nil;

	-- U+2009 THIN SPACE: workaround for bug: HTML entity   is decoded incorrect. Entity   gets decoded properly		-- U+2009 THIN SPACE: workaround for bug: HTML entity   is decoded incorrect. Entity   gets decoded properly
	s = mw.ustring.gsub( s, ' ', ' ' )		s = mw.ustring.gsub( s, ' ', ' ' )
Line 40:		Line 35:
	s = mw.ustring.gsub( s, 'ε', '&epsi;' )		s = mw.ustring.gsub( s, 'ε', '&epsi;' )

	ret = mw.text.decode( s, not subset_only )		local ret = mw.text.decode( s, not subset_only )

	return ret		return ret
Line 46:		Line 41:

	function p.encode( frame )		function p.encode( frame )
	local s		local s = frame.args['s'] or ''
	local charset		local charset = frame.args['charset']

	s = frame.args['s'] or ''
	charset = frame.args['charset']

	return p._encode( s, charset )		return p._encode( s, charset )

2023-03-21T14:25:02Z

← Previous revision		Revision as of 14:25, 21 March 2023
Line 2:		Line 2:
	local p = {}		local p = {}

	function _getBoolean( boolean_str )		local function _getBoolean( boolean_str )
	-- from: module:String; adapted		-- from: module:String; adapted
	-- requires an explicit true		-- requires an explicit true

2023-03-21T14:23:35Z

require('strict')

2023-02-07T18:33:26Z

phab:T328840, commented in

← Previous revision		Revision as of 18:33, 7 February 2023
Line 36:		Line 36:
	-- U+2009 THIN SPACE: workaround for bug: HTML entity   is decoded incorrect. Entity   gets decoded properly		-- U+2009 THIN SPACE: workaround for bug: HTML entity   is decoded incorrect. Entity   gets decoded properly
	s = mw.ustring.gsub( s, ' ', ' ' )		s = mw.ustring.gsub( s, ' ', ' ' )
	-- U+03B5 ε GREEK SMALL LETTER EPSILON: workaround for bug (phab:~~...~~): HTML entity ε is decoded incorrect for gsub(). Entity &epsi; gets decoded properly		-- U+03B5 ε GREEK SMALL LETTER EPSILON: workaround for bug (phab:T328840): HTML entity ε is decoded incorrect for gsub(). Entity &epsi; gets decoded properly
	s = mw.ustring.gsub( s, 'ε', '&epsi;' )		s = mw.ustring.gsub( s, 'ε', '&epsi;' )

2023-02-04T11:11:56Z

← Previous revision		Revision as of 11:11, 4 February 2023
Line 33:		Line 33:
	function p._decode( s, subset_only )		function p._decode( s, subset_only )
	local ret = nil;		local ret = nil;


	-- U+2009 THIN SPACE: workaround for bug: HTML entity   is decoded incorrect. Entity   gets decoded properly		-- U+2009 THIN SPACE: workaround for bug: HTML entity   is decoded incorrect. Entity   gets decoded properly
	s = mw.ustring.gsub( s, ' ', ' ' )		s = mw.ustring.gsub( s, ' ', ' ' )

2023-02-04T11:11:14Z

← Previous revision		Revision as of 11:11, 4 February 2023
Line 34:		Line 34:
	local ret = nil;		local ret = nil;

	-- U+2009 THIN SPACE: workaround for bug: HTML entity   is decoded incorrect.   gets decoded properly		-- U+2009 THIN SPACE: workaround for bug: HTML entity   is decoded incorrect. Entity   gets decoded properly
	s = mw.ustring.gsub( s, ' ', ' ' )		s = mw.ustring.gsub( s, ' ', ' ' )
	-- U+03B5 ε GREEK SMALL LETTER EPSILON: workaround for bug (phab:...): HTML entity ε is decoded incorrect for gsub(). &epsi; gets decoded properly		-- U+03B5 ε GREEK SMALL LETTER EPSILON: workaround for bug (phab:...): HTML entity ε is decoded incorrect for gsub(). Entity &epsi; gets decoded properly
	s = mw.ustring.gsub( s, 'ε', '&epsi;' )		s = mw.ustring.gsub( s, 'ε', '&epsi;' )

	ret = mw.text.decode( s, not subset_only )		ret = mw.text.decode( s, not subset_only )

2023-02-04T10:16:27Z

← Previous revision		Revision as of 10:16, 4 February 2023
Line 33:		Line 33:
	function p._decode( s, subset_only )		function p._decode( s, subset_only )
	local ret = nil;		local ret = nil;


	~~s = mw.ustring.gsub( s, ' ', ' ' )~~ -- U+2009 THIN SPACE: workaround for bug: HTML entity   is decoded incorrect;   gets decoded properly		-- U+2009 THIN SPACE: workaround for bug: HTML entity   is decoded incorrect.   gets decoded properly
	s = mw.ustring.gsub( s, '&~~epsilon~~;', '&~~epsi~~;' ) -- U+03B5 ε GREEK SMALL LETTER EPSILON: workaround for bug: HTML entity ε is decoded incorrect for gsub(); &epsi; gets decoded properly ~~(phab:..)~~		s = mw.ustring.gsub( s, ' ', ' ' )
			-- U+03B5 ε GREEK SMALL LETTER EPSILON: workaround for bug (phab:...): HTML entity ε is decoded incorrect for gsub(). &epsi; gets decoded properly
			s = mw.ustring.gsub( s, 'ε', '&epsi;' )

	ret = mw.text.decode( s, not subset_only )		ret = mw.text.decode( s, not subset_only )

2023-02-04T10:15:01Z

← Previous revision		Revision as of 10:15, 4 February 2023
Line 34:		Line 34:
	local ret = nil;		local ret = nil;

	s = mw.ustring.gsub( s, ' ', ' ' ) -- U+2009 THIN SPACE: workaround for bug: HTML entity   is decoded incorrect ~~for gsub()~~;   gets decoded properly		s = mw.ustring.gsub( s, ' ', ' ' ) -- U+2009 THIN SPACE: workaround for bug: HTML entity   is decoded incorrect;   gets decoded properly
	s = mw.ustring.gsub( s, 'ε', '&epsi;' ) -- U+03B5 ε GREEK SMALL LETTER EPSILON: workaround for bug: HTML entity ε is decoded incorrect for gsub(); &epsi; gets decoded properly		s = mw.ustring.gsub( s, 'ε', '&epsi;' ) -- U+03B5 ε GREEK SMALL LETTER EPSILON: workaround for bug: HTML entity ε is decoded incorrect for gsub(); &epsi; gets decoded properly (phab:..)

	ret = mw.text.decode( s, not subset_only )		ret = mw.text.decode( s, not subset_only )

2023-02-04T10:13:53Z

← Previous revision		Revision as of 10:13, 4 February 2023
Line 34:		Line 34:
	local ret = nil;		local ret = nil;

	s = mw.ustring.gsub( s, ' ', ' ' ) -- U+2009 THIN SPACE: ~~Workaround~~ for bug: &~~ThinSpace~~; ~~gets properly~~ decoded in ~~decode,~~ ~~but~~ &~~thinsp~~; ~~doesn't.~~		s = mw.ustring.gsub( s, ' ', ' ' ) -- U+2009 THIN SPACE: workaround for bug: HTML entity   is decoded incorrect for gsub();   gets decoded properly
	s = mw.ustring.gsub( s, 'ε', '&epsi;' ) -- U+03B5 ε GREEK SMALL LETTER EPSILON: workaround for bug: HTML entity &~~epsi~~; ~~gets properly~~ decoded, ~~but~~ &~~epsilon~~; ~~doesn't.~~		s = mw.ustring.gsub( s, 'ε', '&epsi;' ) -- U+03B5 ε GREEK SMALL LETTER EPSILON: workaround for bug: HTML entity ε is decoded incorrect for gsub(); &epsi; gets decoded properly


	ret = mw.text.decode( s, not subset_only )		ret = mw.text.decode( s, not subset_only )

2023-02-04T10:08:32Z

-- U+03B5 ε GREEK SMALL LETTER EPSILON: workaround for bug: HTML entity ε gets properly decoded, but ε doesn't.

← Previous revision		Revision as of 10:08, 4 February 2023
Line 34:		Line 34:
	local ret = nil;		local ret = nil;

	s = mw.ustring.gsub( s, ' ', ' ' ) -- Workaround for bug:   gets properly decoded in decode, but   doesn't.		s = mw.ustring.gsub( s, ' ', ' ' ) -- U+2009 THIN SPACE: Workaround for bug:   gets properly decoded in decode, but   doesn't.
			s = mw.ustring.gsub( s, 'ε', '&epsi;' ) -- U+03B5 ε GREEK SMALL LETTER EPSILON: workaround for bug: HTML entity &epsi; gets properly decoded, but ε doesn't.


	ret = mw.text.decode( s, not subset_only )		ret = mw.text.decode( s, not subset_only )