diff options
author | ser <ser@b2dd03c8-39d4-4d8f-98ff-823fe69b080e> | 2006-12-01 02:20:08 +0000 |
---|---|---|
committer | ser <ser@b2dd03c8-39d4-4d8f-98ff-823fe69b080e> | 2006-12-01 02:20:08 +0000 |
commit | f114b85d89cf98cf4a11731615df77e50901d0c1 (patch) | |
tree | 5d0fe1b4da60aaa23cde90cbd793e2584b7762a4 /lib/rexml/text.rb | |
parent | d2205c869eb959e6ddb8b08c4ab7318d30ea62af (diff) |
* Cross-patch from Ruby CVS; mostly Nabu edits.
* Fixes ticket:68.
***** Note that this is an API change!!! *****
NOTE that this involves an API change! Entity declarations in the doctype now
generate events that carry two, not one, arguments.
* Implements ticket:15, using gwrite's suggestion. This allows Element to be
subclassed.
* Fixed namespaces handling in XPath and element.
***** Note that this is an API change!!! *****
Element.namespaces() now returns a hash of namespace mappings which are
relevant for that node.
* Fixes a bug in multiple decodings
* The changeset 1230:1231 was bad. The default behavior is *not* to use the
native REXML encodings by default, but rather to use ICONV by default. I'll
have to think of a better way of managing translations, but the REXML codecs
are (a) less reliable than ICONV, but more importantly (b) slower. The real
solution is to use ICONV by default, but allow users to specify that they
want to use the pure Ruby codecs.
* Fixes ticket:61 (xpath_parser)
* Fixes ticket:63 (UTF-16; UNILE decoding was bad)
* Improves parsing error messages a little
* Adds the ability to override the encoding detection in Source construction
* Fixes an edge case in Functions::string, where document nodes weren't
correctly converted
* Fixes Functions::string() for Element and Document nodes
* Fixes some problems in entity handling
* Addresses ticket:66
* Fixes ticket:71
* Addresses ticket:78
NOTE: that this also fixes what is technically another bug in REXML. REXML's
XPath parser used to allow exponential notation in numbers. The XPath spec
is specific about what a number is, and scientific notation is not included.
Therefore, this has been fixed.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/branches/ruby_1_8@11315 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
Diffstat (limited to 'lib/rexml/text.rb')
-rw-r--r-- | lib/rexml/text.rb | 47 |
1 files changed, 24 insertions, 23 deletions
diff --git a/lib/rexml/text.rb b/lib/rexml/text.rb index 55bc9f50f8..3de9170623 100644 --- a/lib/rexml/text.rb +++ b/lib/rexml/text.rb @@ -42,6 +42,7 @@ module REXML # Use this field if you have entities defined for some text, and you don't # want REXML to escape that text in output. # Text.new( "<&", false, nil, false ) #-> "<&" + # Text.new( "<&", false, nil, false ) #-> "&lt;&amp;" # Text.new( "<&", false, nil, true ) #-> Parse exception # Text.new( "<&", false, nil, true ) #-> "<&" # # Assume that the entity "s" is defined to be "sean" @@ -172,17 +173,6 @@ module REXML end @unnormalized = Text::unnormalize( @string, doctype ) end - - def wrap(string, width, addnewline=false) - # Recursivly wrap string at width. - return string if string.length <= width - place = string.rindex(' ', width) # Position in string with last ' ' before cutoff - if addnewline then - return "\n" + string[0,place] + "\n" + wrap(string[place+1..-1], width) - else - return string[0,place] + "\n" + wrap(string[place+1..-1], width) - end - end # Sets the contents of this text node. This expects the text to be # unnormalized. It returns self. @@ -198,17 +188,28 @@ module REXML @raw = false end - def indent_text(string, level=1, style="\t", indentfirstline=true) - return string if level < 0 - new_string = '' - string.each { |line| - indent_string = style * level - new_line = (indent_string + line).sub(/[\s]+$/,'') - new_string << new_line - } - new_string.strip! unless indentfirstline - return new_string + def wrap(string, width, addnewline=false) + # Recursivly wrap string at width. + return string if string.length <= width + place = string.rindex(' ', width) # Position in string with last ' ' before cutoff + if addnewline then + return "\n" + string[0,place] + "\n" + wrap(string[place+1..-1], width) + else + return string[0,place] + "\n" + wrap(string[place+1..-1], width) + end end + + def indent_text(string, level=1, style="\t", indentfirstline=true) + return string if level < 0 + new_string = '' + string.each { |line| + indent_string = style * level + new_line = (indent_string + line).sub(/[\s]+$/,'') + new_string << new_line + } + new_string.strip! unless indentfirstline + return new_string + end def write( writer, indent=-1, transitive=false, ie_hack=false ) s = to_s() @@ -286,9 +287,10 @@ module REXML def Text::normalize( input, doctype=nil, entity_filter=nil ) copy = input # Doing it like this rather than in a loop improves the speed + #copy = copy.gsub( EREFERENCE, '&' ) + copy = copy.gsub( "&", "&" ) if doctype # Replace all ampersands that aren't part of an entity - copy = copy.gsub( EREFERENCE, '&' ) doctype.entities.each_value do |entity| copy = copy.gsub( entity.value, "&#{entity.name};" ) if entity.value and @@ -296,7 +298,6 @@ module REXML end else # Replace all ampersands that aren't part of an entity - copy = copy.gsub( EREFERENCE, '&' ) DocType::DEFAULT_ENTITIES.each_value do |entity| copy = copy.gsub(entity.value, "&#{entity.name};" ) end |