From 11907e10c73883e5dcdaba11a093ef01c7ee2de8 Mon Sep 17 00:00:00 2001
From: Ralph Amissah <ralph@amissah.com>
Date: Sun, 27 Jan 2013 16:26:29 -0500
Subject: v4: check xml representation of characters (& < > in particular)
---
lib/sisu/v4/epub_format.rb | 63 ++++++++++++++----------
lib/sisu/v4/shared_metadata.rb | 109 +++++------------------------------------
2 files changed, 47 insertions(+), 125 deletions(-)
(limited to 'lib')
diff --git a/lib/sisu/v4/epub_format.rb b/lib/sisu/v4/epub_format.rb
index 84d32000..dd3273d0 100644
--- a/lib/sisu/v4/epub_format.rb
+++ b/lib/sisu/v4/epub_format.rb
@@ -1217,6 +1217,18 @@ module SiSU_EPUB_Format
WOK
end
end
+ module SanitizeXML
+ def self.xml(x)
+ if x.is_a?(String)
+ x.gsub(/&/,'&').
+ gsub(/</,'<').gsub(/>/,'>').
+ #gsub(/</,'<').gsub(/>/,'>').
+ gsub(/\\\\/,'<br />').
+ gsub(/<br(?: \/)?>/,'<br />')
+ else x
+ end
+ end
+ end
class HeadInformation
include SiSU_Viz
attr_reader :md,:rdf,:vz
@@ -1347,10 +1359,12 @@ output_epub_cont_seg.close
end
def head
depth=@md.lvs[1] + @md.lvs[2] + @md.lvs[3] + @md.lvs[4]
+ title=SanitizeXML.xml(@md.title.full)
+ author=SanitizeXML.xml(@md.author)
<<-WOK
<!-- four required metadata items (for all NCX documents,
(including the relaxed constraints of OPS 2.0) -->
- <title>#{@md.title.full} by #{@md.author}</title>
+ <title>#{title} by #{author}</title>
<link href="css/xhtml.css" rel="stylesheet" type="text/css" id="main-css" />
<meta name="dtb:uid" content="urn:uuid:#{@md.dgst[1]}" />
<!-- <meta name="epub-creator" content="#{@md.publisher}" /> -->
@@ -1365,16 +1379,18 @@ output_epub_cont_seg.close
WOK
end
def doc_title
+ txt=SanitizeXML.xml(@md.title.full)
<<-WOK
<docTitle>
- <text>#{@md.title.full}</text>
+ <text>#{txt}</text>
</docTitle>
WOK
end
def doc_author
+ txt=SanitizeXML.xml(@md.author)
<<-WOK
<docAuthor>
- <text>#{@md.author}</text>
+ <text>#{txt}</text>
</docAuthor>
WOK
end
@@ -1466,12 +1482,10 @@ output_epub_cont_seg.close
m=(m.empty?) \
? (surname + other_names)
: (m + '; ' + surname + ', ' + other_names)
- m=m.gsub(/</,'<').gsub(/>/,'>').
- gsub(/<br(?: \/)?>/,';')
+ m=SanitizeXML.xml(m)
end
x=@md.creator.author.dup
- x=x.gsub(/</,'<').gsub(/>/,'>').
- gsub(/<br(?: \/)?>/,'<br />')
+ x=SanitizeXML.xml(x)
%{\n <dc:creator opf:file-as="#{m}" opf:role="aut">#{x}</dc:creator>}
else ''
end
@@ -1488,12 +1502,10 @@ output_epub_cont_seg.close
m=(m.empty?) \
? (surname + other_names)
: (m + '; ' + surname + ', ' + other_names)
- m=m.gsub(/</,'<').gsub(/>/,'>').
- gsub(/<br(?: \/)?>/,';')
+ m=SanitizeXML.xml(m)
end
x=@md.creator.editor.dup
- x=x.gsub(/</,'<').gsub(/>/,'>').
- gsub(/<br(?: \/)?>/,'<br />')
+ x=SanitizeXML.xml(x)
%{\n <dc:creator opf:file-as="#{m}" opf:role="edt">#{x}</dc:creator>}
else ''
end
@@ -1510,12 +1522,10 @@ output_epub_cont_seg.close
m=(m.empty?) \
? (surname + other_names)
: (m + '; ' + surname + ', ' + other_names)
- m=m.gsub(/</,'<').gsub(/>/,'>').
- gsub(/<br(?: \/)?>/,';')
+ m=SanitizeXML.xml(m)
end
x=@md.creator.translator.dup
- x=x.gsub(/</,'<').gsub(/>/,'>').
- gsub(/<br(?: \/)?>/,'<br />')
+ x=SanitizeXML.xml(x)
%{\n <dc:creator opf:file-as="#{m}" opf:role="trl">#{x}</dc:creator>}
else ''
end
@@ -1532,28 +1542,24 @@ output_epub_cont_seg.close
m=(m.empty?) \
? (surname + other_names)
: (m + '; ' + surname + ', ' + other_names)
- m=m.gsub(/</,'<').gsub(/>/,'>').
- gsub(/<br(?: \/)?>/,';')
+ m=SanitizeXML.xml(m)
end
x=@md.creator.illustrator.dup
- x=x.gsub(/</,'<').gsub(/>/,'>').
- gsub(/<br(?: \/)?>/,'<br />')
+ x=SanitizeXML.xml(x)
%{\n <dc:creator opf:file-as="#{m}" opf:role="ill">#{x}</dc:creator>}
else ''
end
date_published=if defined? @md.date.published \
and @md.date.published =~/\S+/
x=@md.date.published.dup
- x=x.gsub(/</,'<').gsub(/>/,'>').
- gsub(/<br(?: \/)?>/,'<br />')
+ x=SanitizeXML.xml(x)
%{\n <dc:date opf:event="published">#{x}</dc:date>}
else ''
end
subject=if defined? @md.classify.subject \
and @md.classify.subject =~/\S+/
x=@md.classify.subject.dup
- x=x.gsub(/</,'<').gsub(/>/,'>').
- gsub(/<br(?: \/)?>/,'<br />')
+ x=SanitizeXML.xml(x)
%{\n <dc:subject>#{x}</dc:subject>}
else ''
end
@@ -1565,7 +1571,7 @@ output_epub_cont_seg.close
end
rights=if defined? @md.rights.all \
and @md.rights.all =~/\S+/
- rights=@md.rights.all.gsub(/<br>/,'<br />')
+ rights=SanitizeXML.xml(@md.rights.all)
%{\n <dc:rights>#{rights}</dc:rights>}
else ''
end
@@ -1750,9 +1756,8 @@ output_epub_cont_seg.close
end
def rights
def all
- rghts=@md.rights.all.gsub(/<br>/,'<br />')
- rghts=rghts.gsub(/^\s*Copyright\s+\(C\)/,'Copyright <sup>©</sup> ')
- %{<p class="small_left">Rights: #{rghts}</p>}
+ rights=SanitizeXML.xml(@md.rights.all)
+ %{<p class="small_left">Rights: #{rights}</p>}
end
self
end
@@ -2068,15 +2073,19 @@ output_epub_cont_seg.close
#{@vz.table_close}}
end
def toc_head_copy_at
+ @txt=SanitizeXML.xml(@txt)
%{<p class="center">#{@txt}</p>\n}
end
def center
+ @txt=SanitizeXML.xml(@txt)
%{<p class="center">#{@txt}</p>\n}
end
def bold
+ @txt=SanitizeXML.xml(@txt)
%{<p class="bold">#{@txt}</p>\n}
end
def center_bold
+ @txt=SanitizeXML.xml(@txt)
%{<p class="centerbold">#{@txt}</p>\n}
end
end
diff --git a/lib/sisu/v4/shared_metadata.rb b/lib/sisu/v4/shared_metadata.rb
index 44c7243e..8b660208 100644
--- a/lib/sisu/v4/shared_metadata.rb
+++ b/lib/sisu/v4/shared_metadata.rb
@@ -725,107 +725,19 @@ module SiSU_Metadata
end
def char_enc(str)
@s=str
+ def amp
+ if @s \
+ and @s.is_a?(String)
+ @s=@s.gsub(/&/u,'&')
+ end
+ @s
+ end
def utf8
if @s \
and @s.is_a?(String)
@s=@s.gsub(/<br(?: \/)?>/u,Mx[:br_paragraph]).
- gsub(/</um,'<'). # '<' # <
- 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' # 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' # 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,'<').gsub(/>/um,'>').
+ #gsub(/</um,'<').gsub(/>/um,'>').
gsub(/ /um,' '). # space identify
gsub(/ /um,' '). # space identify
gsub(/#{Mx[:br_paragraph]}/u,'<br />')
@@ -888,7 +800,8 @@ WOK
end
def xhtml_display
def meta_para
- inf_xml=char_enc(@inf).utf8
+ inf_xml=char_enc(@inf).amp
+ inf_xml=char_enc(inf_xml).utf8
%{<p class="norm">
<b>#{@tag}</b>: #{inf_xml}
</p>}
--
cgit v1.2.3