class SiSU_JSON_Munge::Trans
Public Class Methods
new(md)
click to toggle source
# File lib/sisu/json_shared.rb, line 77 def initialize(md) @md=md @sys=SiSU_Env::SystemCall.new @dir=SiSU_Env::InfoEnv.new(@md.fns) if @md.sem_tag @ab ||=semantic_tags.default end end
Public Instance Methods
char_enc()
click to toggle source
# File lib/sisu/json_shared.rb, line 125 def char_enc #character encode def utf8(dob='') if @sys.locale =~/utf-?8/i # instead ucs for utf8 # String#encode Iñtërnâtiônàlizætiøn str=if defined? dob.obj then dob.obj elsif dob.is_a?(String) then dob end if str #¿ÀÁÂÃÄÅÆÇÈÉÊËÌÍÎÏÐÑÒÓÔÕÖØÙÚÛÜÞßàáâãäåæçèéêëìíîïðñòóôõöøùúûü #¢£¥§©ª«®°±²³µ¶¹º»¼½¾×÷ str=str.gsub(/</um,'<'). # '<' # < gsub(/>/um,'>'). # '>' # > gsub(/¢/um,'¢'). # '¢' # ¢ gsub(/£/um,'£'). # '£' # £ gsub(/¥/um,'¥'). # '¥' # ¥ gsub(/§/um,'§'). # '§' # § gsub(/©/um,'©'). # '©' # © gsub(/ª/um,'ª'). # 'ª' # ª gsub(/«/um,'«'). # '«' # « gsub(/®/um,'®'). # '®' # ® gsub(/°/um,'°'). # '°' # ° gsub(/±/um,'±'). # '±' # ± gsub(/²/um,'²'). # '²' # ² gsub(/³/um,'³'). # '³' # ³ gsub(/µ/um,'µ'). # 'µ' # µ gsub(/¶/um,'¶'). # '¶' # ¶ gsub(/¹/um,'¹'). # '¹' # ¹ gsub(/º/um,'º'). # 'º' # º gsub(/»/um,'»'). # '»' # » gsub(/¼/um,'¼'). # '¼' # ¼ gsub(/½/um,'½'). # '½' # ½ gsub(/¾/um,'¾'). # '¾' # ¾ gsub(/×/um,'×'). # '×' # × gsub(/÷/um,'÷'). # '÷' # ÷ gsub(/¿/um,'¿'). # '¿' # ¿ gsub(/À/um,'À'). # 'À' # À gsub(/Á/um,'Á'). # 'Á' # Á gsub(/Â/um,'Â'). # 'Â' #  gsub(/Ã/um,'Ã'). # 'Ã' # à gsub(/Ä/um,'Ä'). # 'Ä' # Ä gsub(/Å/um,'Å'). # 'Å' # Å gsub(/Æ/um,'Æ'). # 'Æ' # Æ gsub(/Ç/um,'Ç'). # 'Ç' # Ç gsub(/È/um,'È'). # 'È' # È gsub(/É/um,'É'). # 'É' # É gsub(/Ê/um,'Ê'). # 'Ê' # Ê gsub(/Ë/um,'Ë'). # 'Ë' # Ë gsub(/Ì/um,'Ì'). # 'Ì' # Ì gsub(/Í/um,'Í'). # 'Í' # Í gsub(/Î/um,'Î'). # 'Î' # Î gsub(/Ï/um,'Ï'). # 'Ï' # Ï gsub(/Ð/um,'Ð'). # 'Ð' # Ð gsub(/Ñ/um,'Ñ'). # 'Ñ' # Ñ gsub(/Ò/um,'Ò'). # 'Ò' # Ò gsub(/Ó/um,'Ó'). # 'Ó' # Ó gsub(/Ô/um,'Ô'). # 'Ô' # Ô gsub(/Õ/um,'Õ'). # 'Õ' # Õ gsub(/Ö/um,'Ö'). # 'Ö' # Ö gsub(/Ø/um,'Ø'). # 'Ø' # Ø gsub(/Ù/um,'Ù'). # 'Ù' # Ù gsub(/Ú/um,'Ú'). # 'Ú' # Ú gsub(/Û/um,'Û'). # 'Û' # Û gsub(/Ü/um,'Ü'). # 'Ü' # Ü gsub(/Ý/um,'Ý'). # 'Ý' # Ý gsub(/Þ/um,'Þ'). # 'Þ' # Þ gsub(/ß/um,'ß'). # 'ß' # ß gsub(/à/um,'à'). # 'à' # à gsub(/á/um,'á'). # 'á' # á gsub(/â/um,'â'). # 'â' # â gsub(/ã/um,'ã'). # 'ã' # ã gsub(/ä/um,'ä'). # 'ä' # ä gsub(/å/um,'å'). # 'å' # å gsub(/æ/um,'æ'). # 'æ' # æ gsub(/ç/um,'ç'). # 'ç' # ç gsub(/è/um,'è'). # 'è' # è gsub(/é/um,'é'). # '´' # é gsub(/ê/um,'ê'). # 'ˆ' # ê gsub(/ë/um,'ë'). # 'ë' # ë gsub(/ì/um,'ì'). # 'ì' # ì gsub(/í/um,'í'). # '´' # í gsub(/î/um,'î'). # 'î' # î gsub(/ï/um,'ï'). # 'ï' # ï gsub(/ð/um,'ð'). # 'ð' # ð gsub(/ñ/um,'ñ'). # 'ñ' # ñ gsub(/ò/um,'ò'). # 'ò' # ò gsub(/ó/um,'ó'). # 'ó' # ó gsub(/ô/um,'ô'). # 'ô' # ô gsub(/õ/um,'õ'). # 'õ' # õ gsub(/ö/um,'ö'). # 'ö' # ö gsub(/ø/um,'ø'). # 'ø' # ø gsub(/ù/um,'ú'). # 'ù' # ú gsub(/ú/um,'û'). # 'ú' # û gsub(/û/um,'ü'). # 'û' # ü gsub(/ü/um,'ý'). # 'ü' # ý gsub(/þ/um,'þ'). # 'þ' # þ gsub(/ÿ/um,'ÿ'). # 'ÿ' # ÿ gsub(/‘/um,'‘'). # '‘' # ‘ gsub(/’/um,'’'). # '’' # ’ gsub(/“/um,'“'). # “ # “ gsub(/”/um,'”'). # ” # ” gsub(/–/um,'–'). # – # – gsub(/—/um,'—'). # — # — gsub(/∝/um,'∝'). # ∝ # ∝ gsub(/∞/um,'∞'). # ∞ # ∞ gsub(/™/um,'™'). # ™ # ™ gsub(/✠/um,'✠'). # ✗ # ✠ gsub(/ /um,' '). # space identify gsub(/ /um,' ') # space identify end dob=if defined? dob.obj dob.obj=str dob elsif dob.is_a?(String) str end dob end end def html(dob='') if @sys.locale =~/utf-?8/i # instead ucs for utf8 # String#encode Iñtërnâtiônàlizætiøn dob.obj=dob.obj.gsub(/ /u,' '). # space identify gsub(/ /u,' ') # space identify end end self end
clean(str)
click to toggle source
# File lib/sisu/json_shared.rb, line 349 def clean(str) str=str.gsub(/#{Mx[:gl_o]}(#[0-9]{3})#{Mx[:gl_c]}/u,'&\1;'). gsub(/#{Mx[:gl_o]}#([a-z]{2,4})#{Mx[:gl_c]}/u,'&\1;') end
default()
click to toggle source
# File lib/sisu/json_shared.rb, line 86 def default { pub: 'publication', conv: 'convention', vol: 'volume', pg: 'page', cty: 'city', org: 'organization', uni: 'university', dept: 'department', fac: 'faculty', inst: 'institute', co: 'company', com: 'company', conv: 'convention', dt: 'date', y: 'year', m: 'month', d: 'day', ti: 'title', au: 'author', ed: 'editor', #editor? v: 'version', #edition n: 'name', fn: 'firstname', mn: 'middlename', ln: 'lastname', in: 'initials', qt: 'quote', ct: 'cite', ref: 'reference', ab: 'abreviation', def: 'define', desc: 'description', trans: 'translate', } end
html(dob='')
click to toggle source
# File lib/sisu/json_shared.rb, line 242 def html(dob='') if @sys.locale =~/utf-?8/i # instead ucs for utf8 # String#encode Iñtërnâtiônàlizætiøn dob.obj=dob.obj.gsub(/ /u,' '). # space identify gsub(/ /u,' ') # space identify end end
markup(dob='')
click to toggle source
# File lib/sisu/json_shared.rb, line 260 def markup(dob='') wordlist=dob.obj.scan(/&[#0-9a-z]+;|\S+|\n/) #\n needed for tables, check though added 2005w17 dob.obj=tidywords(wordlist).join(' ').strip unless dob.is==:table dob.obj=dob.obj.gsub(/#{Mx[:br_line]}/u,'<br>'). gsub(/#{Mx[:br_paragraph]}/u,'<br>'). gsub(/#{Mx[:br_line]}|#{Mx[:br_nl]}/,'<br>') end dob.obj=dob.obj.gsub(/#{Mx[:mk_o]}:name#\S+?#{Mx[:mk_c]}/,''). gsub(/#{Mx[:mk_o]}#([a-zA-Z]+)#{Mx[:mk_c]}/,'&\1;'). gsub(/#{Mx[:mk_o]}(#[0-9]+)#{Mx[:mk_c]}/,'&\1;'). gsub(/(^|#{Mx[:gl_c]}|\s+)<\s+/,'\1< ').gsub(/\s+>(\s+|$)/,' >\1'). #gsub(/#{Mx[:fa_emphasis_o]}(.+?)#{Mx[:fa_emphasis_c]}/,'<em>\1</em>'). #reinstate gsub(/#{Mx[:fa_bold_o]}(.+?)#{Mx[:fa_bold_c]}/m,'<b>\1</b>'). gsub(/#{Mx[:fa_italics_o]}(.+?)#{Mx[:fa_italics_c]}/m,'<i>\1</i>'). gsub(/#{Mx[:fa_underscore_o]}(.+?)#{Mx[:fa_underscore_c]}/,'<u>\1</u>'). gsub(/#{Mx[:fa_superscript_o]}(.+?)#{Mx[:fa_superscript_c]}/,'<sup>\1</sup>'). gsub(/#{Mx[:fa_subscript_o]}(.+?)#{Mx[:fa_subscript_c]}/,'<sub>\1</sub>'). gsub(/#{Mx[:fa_insert_o]}(.+?)#{Mx[:fa_insert_c]}/,'<ins>\1</ins>'). gsub(/#{Mx[:fa_cite_o]}(.+?)#{Mx[:fa_cite_c]}/,'<cite>\1</cite>'). gsub(/#{Mx[:fa_strike_o]}(.+?)#{Mx[:fa_strike_c]}/,'<del>\1</del>'). gsub(/#{Mx[:fa_monospace_o]}(.+?)#{Mx[:fa_monospace_c]}/,'<tt>\1</tt>'). gsub(/<:pb>\s*/,''). #Fix gsub(/<+[-~]#>+/,'') if dob.is !=:code #embeds a red-bullet image --> dob.obj=dob.obj.gsub(/#{Mx[:fa_bold_o]}(.+?)#{Mx[:fa_bold_c]}/,'<b>\1</b>'). gsub(/#{Mx[:fa_italics_o]}(.+?)#{Mx[:fa_italics_c]}/,'<i>\1</i>'). gsub(/#{Mx[:fa_underscore_o]}(.+?)#{Mx[:fa_underscore_c]}/,'<u>\1</u>'). gsub(/#{Mx[:fa_strike_o]}(.+?)#{Mx[:fa_strike_c]}/,'<del>\1</del>') dob.obj=dob.obj.gsub(/#{Mx[:br_line]}|#{Mx[:br_nl]}/,'<br>') unless dob.is==:table dob.obj=dob.obj.gsub(/#{Mx[:br_page]}\s*/,''). gsub(/#{Mx[:br_page_new]}\s*/,''). gsub(/#{Mx[:br_page_line]}\s*/,''). gsub(/#{Mx[:pa_non_object_no_heading]}|#{Mx[:pa_non_object_dummy_heading]}/,''). gsub(/<[-~]#>/,''). gsub(/href="#{Xx[:segment]}/m,'href="'). gsub(/#{Mx[:lnk_o]}([^#{Mx[:lnk_o]}#{Mx[:lnk_c]}#{Mx[:rel_o]}#{Mx[:rel_c]}]+?)#{Mx[:lnk_c]}#{Mx[:rel_o]}(\.\.\/\S+?)#{Mx[:rel_c]}/, '<link xmlns:xl="http://www.w3.org/1999/xlink" xl:type="simple" xl:href="\2">\1</link>'). gsub(/#{Mx[:lnk_o]}([^#{Mx[:lnk_o]}#{Mx[:lnk_c]}#{Mx[:rel_o]}#{Mx[:rel_c]}]+?)#{Mx[:lnk_c]}#{Mx[:rel_o]}:(\S+?)#{Mx[:rel_c]}/, '<link xmlns:xl="http://www.w3.org/1999/xlink" xl:type="simple" xl:href="../\2">\1</link>'). gsub(/#{Mx[:lnk_o]}(.+?)#{Mx[:lnk_c]}#{Mx[:rel_o]}(\S+?)#{Mx[:rel_c]}/, '<link xmlns:xl="http://www.w3.org/1999/xlink" xl:type="simple" xl:href="#\2">\1</link>'). gsub(/(?:^|[^_\\])#{Mx[:lnk_o]}[ ]*(\S+?\.(?:jpg|png|gif))[ ]+(\d+)x(\d+)(\s+[^}]+)?#{Mx[:lnk_c]}#{Mx[:url_o]}(\S+?)#{Mx[:url_c]}/, %{<image xmlns:xl="http://www.w3.org/1999/xlink" xl:type="simple" xl:actuate="onLoad" xl:show="embed" xl:href="#{@md.file.output_path.xml.rel_image}/\\1" width="\\2" height="\\3" />[\\1] \\4}). gsub(/(?:^|[^_\\])#{Mx[:lnk_o]}[ ]*(\S+?\.(?:jpg|png|gif))([ ]+[^}]+)?#{Mx[:lnk_c]}#{Mx[:url_o]}(\S+?)#{Mx[:url_c]}/, %{<image xmlns:xl="http://www.w3.org/1999/xlink" xl:type="simple" xl:actuate="onLoad" xl:show="embed" xl:href="#{@md.file.output_path.xml.rel_image}/\\1"/>\\1}). gsub(/(?:^|[^_\\])#{Mx[:lnk_o]}[ ]*(\S+?\.(?:jpg|png|gif))[ ]+(\d+)x(\d+)(\s+[^}]+)?#{Mx[:lnk_c]}image/, %{<image xmlns:xl="http://www.w3.org/1999/xlink" xl:type="simple" xl:actuate="onLoad" xl:show="embed" xl:href="#{@md.file.output_path.xml.rel_image}/\\1" width="\\2" height="\\3" />[\\1] \\4}). gsub(/(?:^|[^_\\])#{Mx[:lnk_o]}[ ]*(\S+?\.(?:jpg|png|gif))([ ]+[^}]+)?#{Mx[:lnk_c]}image/, %{<image xmlns:xl="http://www.w3.org/1999/xlink" xl:type="simple" xl:actuate="onLoad" xl:show="embed" xl:href="#{@md.file.output_path.xml.rel_image}/\\1"/>\\1}). gsub(/#{Mx[:lnk_o]}(.+?)#{Mx[:lnk_c]}#{Mx[:url_o]}(\S+?)#{Mx[:url_c]}/, '<link xmlns:xl="http://www.w3.org/1999/xlink" xl:type="simple" xl:href="\2">\1</link>'). #watch, compare html_tune gsub(/#{Mx[:url_o]}(\S+?)#{Mx[:url_c]}/, %{#{the_url_decoration.xml_open}<link xmlns:xl="http://www.w3.org/1999/xlink" xl:type="simple" xl:href="\\1">\\1</link>#{the_url_decoration.xml_close}}). gsub(/#{Mx[:url_o]}_(\S+?)#{Mx[:url_c]}/, '<link xmlns:xl="http://www.w3.org/1999/xlink" xl:type="simple" xl:href="\1">\1</link>') #escaped urls not linked, deal with later else dob.obj=dob.obj.gsub(/</m,'<').gsub(/>/m,'>') end if dob.of==:block dob.obj=dob.obj.gsub(/#{Mx[:gl_bullet]}/,'● ') end dob.obj=dob.obj.gsub(/#{Mx[:url_o]}([a-zA-Z0-9._-]+\@\S+?\.[a-zA-Z0-9._-]+)#{Mx[:url_c]}/, %{#{the_url_decoration.xml_open}\\1#{the_url_decoration.xml_close}}). gsub(/#{Dx[:url_o]}/,"#{Dx[:url_o_xml]}"). gsub(/#{Dx[:url_c]}/,"#{Dx[:url_c_xml]}"). gsub(/ |#{Mx[:nbsp]}/m,' '). gsub(/;&([^#]|(?:[^gl][^t]|[^a][^m][^p]|[^n][^b][^s][^p])[^;])/,';&\1') # pattern not to match dob end
markup_block(dob='')
click to toggle source
# File lib/sisu/json_shared.rb, line 421 def markup_block(dob='') dob.obj=dob.obj.gsub(/</,'<').gsub(/>/,'>'). gsub(/<:?br(?:\s+\/)?>/,'<br>'). gsub(/<(link xmlns:xl=".+?")>/,'<\1>'). gsub(/<(\/link)>/,'<\1>'). gsub(/<(\/?en)>/,'<\1>') dob end
markup_docbook(dob='')
click to toggle source
# File lib/sisu/json_shared.rb, line 377 def markup_docbook(dob='') # work on, initially a copy of fictionbook! if dob.is !=:code dob.obj=dob.obj.gsub(/#{Mx[:en_a_o]}(\d+)\s*(.+?)#{Mx[:en_a_c]}/m,'<footnote><para><!-- fn\1 -->\2</para></footnote>'). gsub(/\\\\/,'</para><para>'). gsub(/&/,'&'). #sort gsub(/#{Mx[:mk_o]}#([a-zA-Z]+)#{Mx[:mk_c]}/,'&\1;'). gsub(/(^|#{Mx[:gl_c]}|\s)&\s+/,'\1& '). #sort gsub(/#{Mx[:mk_o]}(#[0-9]+)#{Mx[:mk_c]}/,'&\1;') dob.obj=dob.obj.gsub(/#{Mx[:br_line]}|#{Mx[:br_nl]}/,'<br>') unless dob.is==:table dob.obj=dob.obj.gsub(/#{Mx[:fa_bold_o]}(.+?)#{Mx[:fa_bold_c]}/,'<b>\1</b>'). gsub(/#{Mx[:fa_italics_o]}(.+?)#{Mx[:fa_italics_c]}/,'<i>\1</i>'). gsub(/#{Mx[:fa_underscore_o]}(.+?)#{Mx[:fa_underscore_c]}/,'<u>\1</u>'). gsub(/#{Mx[:fa_superscript_o]}(.+?)#{Mx[:fa_superscript_c]}/,'<sup>\1</sup>'). gsub(/#{Mx[:fa_subscript_o]}(.+?)#{Mx[:fa_subscript_c]}/,'<sub>\1</sub>'). gsub(/#{Mx[:fa_insert_o]}(.+?)#{Mx[:fa_insert_c]}/,'<ins>\1</ins>'). gsub(/#{Mx[:fa_cite_o]}(.+?)#{Mx[:fa_cite_c]}/,'<cite>\1</cite>'). gsub(/#{Mx[:fa_strike_o]}(.+?)#{Mx[:fa_strike_c]}/,'<del>\1</del>'). gsub(/#{Mx[:fa_monospace_o]}(.+?)#{Mx[:fa_monospace_c]}/,'<tt>\1</tt>'). # tt, kbd gsub(/#{Mx[:lnk_o]}\s*(\S+?)\.(png|jpg|gif).+?#{Mx[:lnk_c]}(?:#{Mx[:url_o]}\S+?#{Mx[:url_c]}|#{Mx[:rel_o]}\S+?#{Mx[:rel_c]}|image)/m, %{#{Xx[:split]}:spaces0:<figure id="fig-\\1">\n:spaces1:<title></title>\n:spaces1:<graphic fileref="../../_sisu/image/\\1.\\2" align="center" width="50%"></graphic>\n:spaces0:</figure>#{Xx[:split]}}). # common image location, else use ./images gsub(/#{Mx[:lnk_o]}(.+?)#{Mx[:lnk_c]}#{Mx[:url_o]}(.+?)#{Mx[:url_c]}/, '<ulink url="\2">\1</ulink>'). gsub(/#{Mx[:url_o]}(.+?)#{Mx[:url_c]}/, '<ulink url="\1">\1</ulink>'). gsub(/#{Mx[:mk_o]}:name#(\S+?)#{Mx[:mk_c]}/,'<a name="\1"></a>'). gsub(/#{Mx[:gl_bullet]}/m,'● '). # not available gsub(/#{Mx[:nbsp]}/,' '). # not available gsub(/<(p|br)>/,'<\1 />') dob.obj=clean(dob.obj) elsif dob.is == :code dob.obj=dob.obj.gsub(/&/m,'&'). #sort gsub(/</,'<').gsub(/>/,'>') else # p dob.is ?? end dob end
markup_fictionbook(str='',is='')
click to toggle source
# File lib/sisu/json_shared.rb, line 353 def markup_fictionbook(str='',is='') str=str.gsub(/#{Mx[:en_a_o]}([\d+*]+).+?#{Mx[:en_a_c]}/m,'<a xl:href="#footnote\1" type="note">[\1]</a>'). gsub(/&/,'&'). #sort gsub(/#{Mx[:mk_o]}#([a-zA-Z]+)#{Mx[:mk_c]}/,'&\1;'). gsub(/(^|#{Mx[:gl_c]}|\s)&\s+/,'\1& '). #sort gsub(/#{Mx[:mk_o]}(#[0-9]+)#{Mx[:mk_c]}/,'&\1;') str=str.gsub(/#{Mx[:br_line]}|#{Mx[:br_nl]}/,'<br>') unless is==:table str=str.gsub(/#{Mx[:fa_bold_o]}(.+?)#{Mx[:fa_bold_c]}/,'<b>\1</b>'). gsub(/#{Mx[:fa_italics_o]}(.+?)#{Mx[:fa_italics_c]}/,'<i>\1</i>'). gsub(/#{Mx[:fa_underscore_o]}(.+?)#{Mx[:fa_underscore_c]}/,'<u>\1</u>'). gsub(/#{Mx[:fa_superscript_o]}(.+?)#{Mx[:fa_superscript_c]}/,'<sup>\1</sup>'). gsub(/#{Mx[:fa_subscript_o]}(.+?)#{Mx[:fa_subscript_c]}/,'<sub>\1</sub>'). gsub(/#{Mx[:fa_insert_o]}(.+?)#{Mx[:fa_insert_c]}/,'<ins>\1</ins>'). gsub(/#{Mx[:fa_cite_o]}(.+?)#{Mx[:fa_cite_c]}/,'<cite>\1</cite>'). gsub(/#{Mx[:fa_strike_o]}(.+?)#{Mx[:fa_strike_c]}/,'<del>\1</del>'). gsub(/#{Mx[:fa_monospace_o]}(.+?)#{Mx[:fa_monospace_c]}/,'<tt>\1</tt>'). # tt, kbd gsub(/#{Mx[:lnk_o]}\s*(\S+?\.(?:png|jpg|gif)).+?#{Mx[:lnk_c]}(?:#{Mx[:url_o]}\S+?#{Mx[:url_c]}|#{Mx[:rel_o]}\S+?#{Mx[:rel_c]}|image)/m,'<image xl:href="#\1" />'). gsub(/#{Mx[:url_o]}(.+?)#{Mx[:url_c]}/,"#{Dx[:url_o]}\\1#{Dx[:url_c]}"). gsub(/#{Mx[:mk_o]}:name#(\S+?)#{Mx[:mk_c]}/,'<a name="\1"></a>'). gsub(/#{Mx[:gl_bullet]}/m,'● '). # not available gsub(/#{Mx[:nbsp]}/,' '). # not available gsub(/<(p|br)>/,'<\1 />') clean(str) end
markup_group(dob='')
click to toggle source
# File lib/sisu/json_shared.rb, line 413 def markup_group(dob='') dob.obj=dob.obj.gsub(/</,'<').gsub(/>/,'>'). gsub(/<:?br(?:\s+\/)?>/,'<br>'). gsub(/<(link xmlns:xl=".+?")>/,'<\1>'). gsub(/<(\/link)>/,'<\1>'). gsub(/<(\/?en)>/,'<\1>') dob end
markup_light(dob='')
click to toggle source
# File lib/sisu/json_shared.rb, line 331 def markup_light(dob='') dob.obj=dob.obj.gsub(/\/\{(.+?)\}\//,'<i>\1</i>'). gsub(/[*!]\{(.+?)\}[*!]/,'<b>\1</b>'). gsub(/_\{(.+?)\}_/,'<u>\1</u>'). gsub(/-\{(.+?)\}-/,'<del>\1</del>'). gsub(/<br(\s*\/)?>/,'<br>'). gsub(/<:pb>\s*/,''). gsub(/<[-~]#>/,''). gsub(/(^|#{Mx[:gl_c]}|\s)&\s+/,'\1& '). #sort gsub(/&([^;]{1,5})/,'&\1'). #sort, rough estimate, revisit #WATCH found in node not sax gsub(/(?:^|[^_\\])#{Mx[:lnk_o]}(\S+?\.(?:png|jpg|gif))[ ]+.+?#{Mx[:lnk_c]}(?:#{Mx[:url_o]}\S+?#{Mx[:url_c]}|image)/, "<image.path>#{@md.file.output_path.xml.rel_image}\/\\1</image.path>"). gsub(/ |#{Mx[:nbsp]}/,' '). gsub(/;&([^#]|(?:[^gl][^t]|[^a][^m][^p]|[^n][^b][^s][^p])[^;])/,';&\1') # pattern not to match wordlist=dob.obj.scan(/&[#0-9a-z]+;|\S+|\n/) #\n needed for tables, check though added 2005w17 dob.obj=tidywords(wordlist).join(' ').strip dob end
tidywords(wordlist)
click to toggle source
# File lib/sisu/json_shared.rb, line 250 def tidywords(wordlist) wordlist_new=[] wordlist.each do |x| #imperfect solution will not catch all possible cases x=x.gsub(/&/,'&') unless x =~/&\S+;/ x=x.gsub(/&([A-Z])/,'&\1') wordlist_new << x end wordlist_new end
utf8(dob='')
click to toggle source
# File lib/sisu/json_shared.rb, line 126 def utf8(dob='') if @sys.locale =~/utf-?8/i # instead ucs for utf8 # String#encode Iñtërnâtiônàlizætiøn str=if defined? dob.obj then dob.obj elsif dob.is_a?(String) then dob end if str #¿ÀÁÂÃÄÅÆÇÈÉÊËÌÍÎÏÐÑÒÓÔÕÖØÙÚÛÜÞßàáâãäåæçèéêëìíîïðñòóôõöøùúûü #¢£¥§©ª«®°±²³µ¶¹º»¼½¾×÷ str=str.gsub(/</um,'<'). # '<' # < gsub(/>/um,'>'). # '>' # > gsub(/¢/um,'¢'). # '¢' # ¢ gsub(/£/um,'£'). # '£' # £ gsub(/¥/um,'¥'). # '¥' # ¥ gsub(/§/um,'§'). # '§' # § gsub(/©/um,'©'). # '©' # © gsub(/ª/um,'ª'). # 'ª' # ª gsub(/«/um,'«'). # '«' # « gsub(/®/um,'®'). # '®' # ® gsub(/°/um,'°'). # '°' # ° gsub(/±/um,'±'). # '±' # ± gsub(/²/um,'²'). # '²' # ² gsub(/³/um,'³'). # '³' # ³ gsub(/µ/um,'µ'). # 'µ' # µ gsub(/¶/um,'¶'). # '¶' # ¶ gsub(/¹/um,'¹'). # '¹' # ¹ gsub(/º/um,'º'). # 'º' # º gsub(/»/um,'»'). # '»' # » gsub(/¼/um,'¼'). # '¼' # ¼ gsub(/½/um,'½'). # '½' # ½ gsub(/¾/um,'¾'). # '¾' # ¾ gsub(/×/um,'×'). # '×' # × gsub(/÷/um,'÷'). # '÷' # ÷ gsub(/¿/um,'¿'). # '¿' # ¿ gsub(/À/um,'À'). # 'À' # À gsub(/Á/um,'Á'). # 'Á' # Á gsub(/Â/um,'Â'). # 'Â' #  gsub(/Ã/um,'Ã'). # 'Ã' # à gsub(/Ä/um,'Ä'). # 'Ä' # Ä gsub(/Å/um,'Å'). # 'Å' # Å gsub(/Æ/um,'Æ'). # 'Æ' # Æ gsub(/Ç/um,'Ç'). # 'Ç' # Ç gsub(/È/um,'È'). # 'È' # È gsub(/É/um,'É'). # 'É' # É gsub(/Ê/um,'Ê'). # 'Ê' # Ê gsub(/Ë/um,'Ë'). # 'Ë' # Ë gsub(/Ì/um,'Ì'). # 'Ì' # Ì gsub(/Í/um,'Í'). # 'Í' # Í gsub(/Î/um,'Î'). # 'Î' # Î gsub(/Ï/um,'Ï'). # 'Ï' # Ï gsub(/Ð/um,'Ð'). # 'Ð' # Ð gsub(/Ñ/um,'Ñ'). # 'Ñ' # Ñ gsub(/Ò/um,'Ò'). # 'Ò' # Ò gsub(/Ó/um,'Ó'). # 'Ó' # Ó gsub(/Ô/um,'Ô'). # 'Ô' # Ô gsub(/Õ/um,'Õ'). # 'Õ' # Õ gsub(/Ö/um,'Ö'). # 'Ö' # Ö gsub(/Ø/um,'Ø'). # 'Ø' # Ø gsub(/Ù/um,'Ù'). # 'Ù' # Ù gsub(/Ú/um,'Ú'). # 'Ú' # Ú gsub(/Û/um,'Û'). # 'Û' # Û gsub(/Ü/um,'Ü'). # 'Ü' # Ü gsub(/Ý/um,'Ý'). # 'Ý' # Ý gsub(/Þ/um,'Þ'). # 'Þ' # Þ gsub(/ß/um,'ß'). # 'ß' # ß gsub(/à/um,'à'). # 'à' # à gsub(/á/um,'á'). # 'á' # á gsub(/â/um,'â'). # 'â' # â gsub(/ã/um,'ã'). # 'ã' # ã gsub(/ä/um,'ä'). # 'ä' # ä gsub(/å/um,'å'). # 'å' # å gsub(/æ/um,'æ'). # 'æ' # æ gsub(/ç/um,'ç'). # 'ç' # ç gsub(/è/um,'è'). # 'è' # è gsub(/é/um,'é'). # '´' # é gsub(/ê/um,'ê'). # 'ˆ' # ê gsub(/ë/um,'ë'). # 'ë' # ë gsub(/ì/um,'ì'). # 'ì' # ì gsub(/í/um,'í'). # '´' # í gsub(/î/um,'î'). # 'î' # î gsub(/ï/um,'ï'). # 'ï' # ï gsub(/ð/um,'ð'). # 'ð' # ð gsub(/ñ/um,'ñ'). # 'ñ' # ñ gsub(/ò/um,'ò'). # 'ò' # ò gsub(/ó/um,'ó'). # 'ó' # ó gsub(/ô/um,'ô'). # 'ô' # ô gsub(/õ/um,'õ'). # 'õ' # õ gsub(/ö/um,'ö'). # 'ö' # ö gsub(/ø/um,'ø'). # 'ø' # ø gsub(/ù/um,'ú'). # 'ù' # ú gsub(/ú/um,'û'). # 'ú' # û gsub(/û/um,'ü'). # 'û' # ü gsub(/ü/um,'ý'). # 'ü' # ý gsub(/þ/um,'þ'). # 'þ' # þ gsub(/ÿ/um,'ÿ'). # 'ÿ' # ÿ gsub(/‘/um,'‘'). # '‘' # ‘ gsub(/’/um,'’'). # '’' # ’ gsub(/“/um,'“'). # “ # “ gsub(/”/um,'”'). # ” # ” gsub(/–/um,'–'). # – # – gsub(/—/um,'—'). # — # — gsub(/∝/um,'∝'). # ∝ # ∝ gsub(/∞/um,'∞'). # ∞ # ∞ gsub(/™/um,'™'). # ™ # ™ gsub(/✠/um,'✠'). # ✗ # ✠ gsub(/ /um,' '). # space identify gsub(/ /um,' ') # space identify end dob=if defined? dob.obj dob.obj=str dob elsif dob.is_a?(String) str end dob end end
xml_sem_block_paired(matched)
click to toggle source
# File lib/sisu/json_shared.rb, line 429 def xml_sem_block_paired(matched) # colon depth: many, recurs matched=matched.gsub(/\b(au):\{(.+?)\}:\1\b/m, %{<sem:#{@ab[:au]} depth="many">\\2</sem:#{@ab[:au]}>}). gsub(/\b(vol):\{(.+?)\}:\1\b/m, %{<sem:#{@ab[:vol]} depth="many">\\2</sem:#{@ab[:vol]}>}). gsub(/\b(pub):\{(.+?)\}:\1\b/m, %{<sem:#{@ab[:pub]} depth="many">\\2</sem:#{@ab[:pub]}>}). gsub(/\b(ref):\{(.+?)\}:\1\b/m, %{<sem:#{@ab[:ref]} depth="many">\\2</sem:#{@ab[:ref]}>}). gsub(/\b(desc):\{(.+?)\}:\1\b/m,%{<sem:#{@ab[:desc]} depth="many">\\2</sem:#{@ab[:desc]}>}). gsub(/\b(conv):\{(.+?)\}:\1\b/m,%{<sem:#{@ab[:conv]} depth="many">\\2</sem:#{@ab[:conv]}>}). gsub(/\b(ct):\{(.+?)\}:\1\b/m, %{<sem:#{@ab[:ct]} depth="many">\\2</sem:#{@ab[:ct]}>}). gsub(/\b(cty):\{(.+?)\}:\1\b/m, %{<sem:#{@ab[:cty]} depth="many">\\2</sem:#{@ab[:cty]}>}). gsub(/\b(org):\{(.+?)\}:\1\b/m, %{<sem:#{@ab[:org]} depth="many">\\2</sem:#{@ab[:org]}>}). gsub(/\b(dt):\{(.+?)\}:\1\b/m, %{<sem:#{@ab[:dt]} depth="many">\\2</sem:#{@ab[:dt]}>}). gsub(/\b(n):\{(.+?)\}:\1\b/m, %{<sem:#{@ab[:n]} depth="many">\\2</sem:#{@ab[:n]}>}). gsub(/([a-z]+(?:[_:.][a-z]+)*)(?::\{(.+?)\}:\1)/m,'<sem:\1 depth="many">\2</sem:\1>') end