2003-06-09 21:31:01 -04:00
|
|
|
require "rexml/element"
|
|
|
|
require "rexml/xmldecl"
|
|
|
|
require "rexml/source"
|
|
|
|
require "rexml/comment"
|
|
|
|
require "rexml/doctype"
|
|
|
|
require "rexml/instruction"
|
|
|
|
require "rexml/rexml"
|
|
|
|
require "rexml/parseexception"
|
|
|
|
require "rexml/output"
|
|
|
|
require "rexml/parsers/baseparser"
|
|
|
|
require "rexml/parsers/streamparser"
|
2004-06-09 22:01:04 -04:00
|
|
|
require "rexml/parsers/treeparser"
|
2003-06-09 21:31:01 -04:00
|
|
|
|
|
|
|
module REXML
|
|
|
|
# Represents a full XML document, including PIs, a doctype, etc. A
|
|
|
|
# Document has a single child that can be accessed by root().
|
|
|
|
# Note that if you want to have an XML declaration written for a document
|
|
|
|
# you create, you must add one; REXML documents do not write a default
|
2008-10-01 09:46:53 -04:00
|
|
|
# declaration for you. See |DECLARATION| and |write|.
|
|
|
|
class Document < Element
|
|
|
|
# A convenient default XML declaration. If you want an XML declaration,
|
|
|
|
# the easiest way to add one is mydoc << Document::DECLARATION
|
2003-12-08 21:41:33 -05:00
|
|
|
# +DEPRECATED+
|
|
|
|
# Use: mydoc << XMLDecl.default
|
2008-10-01 09:46:53 -04:00
|
|
|
DECLARATION = XMLDecl.default
|
|
|
|
|
|
|
|
# Constructor
|
|
|
|
# @param source if supplied, must be a Document, String, or IO.
|
|
|
|
# Documents have their context and Element attributes cloned.
|
|
|
|
# Strings are expected to be valid XML documents. IOs are expected
|
|
|
|
# to be sources of valid XML documents.
|
|
|
|
# @param context if supplied, contains the context of the document;
|
|
|
|
# this should be a Hash.
|
|
|
|
def initialize( source = nil, context = {} )
|
2008-09-01 09:41:38 -04:00
|
|
|
@entity_expansion_count = 0
|
2008-10-01 09:46:53 -04:00
|
|
|
super()
|
|
|
|
@context = context
|
|
|
|
return if source.nil?
|
|
|
|
if source.kind_of? Document
|
|
|
|
@context = source.context
|
|
|
|
super source
|
|
|
|
else
|
|
|
|
build( source )
|
|
|
|
end
|
|
|
|
end
|
2003-06-09 21:31:01 -04:00
|
|
|
|
|
|
|
def node_type
|
|
|
|
:document
|
|
|
|
end
|
|
|
|
|
2008-10-01 09:46:53 -04:00
|
|
|
# Should be obvious
|
|
|
|
def clone
|
|
|
|
Document.new self
|
|
|
|
end
|
Short summary:
This is a version bump to REXML 3.1.4 for Ruby HEAD. This change log is
identical to the log for the 1.8 branch.
It includes numerous bug fixes and is a pretty big patch, but is nonetheless
a minor revision bump, since the API hasn't changed.
For more information, see:
http:/www.germane-software.com/projects/rexml/milestone/3.1.4
For all tickets, see:
http://www.germane-software.com/projects/rexml/ticket/#
Where '#' is replaced with the ticket number.
Changelog:
* Fixed the documentation WRT the raw mode of text nodes (ticket #4)
* Fixes roundup ticket #43: substring-after bug.
* Fixed ticket #44, Element#xpath
* Patch submitted by an anonymous doner to allow parsing of Tempfiles. I was
hoping that, by now, that whole Source thing would have been changed to use
duck typing and avoid this sort of ticket... but in the meantime, the patch
has been applied.
* Fixes ticket:30, XPath default namespace bug. The fix was provided
by Lucas Nussbaum.
* Aliases #size to #length, as per zdennis's request.
* Fixes typo from previous commit
* Fixes ticket #32, preceding-sibling fails attempting delete_if on nil nodeset
* Merges a user-contributed patch for ticket #40
* Adds a forgotten-to-commit unit test for ticket #32
* Changes Date, Version, and Copyright to upper case, to avoid conflicts with
the Date class. All of the other changes in the altered files are because
Subversion doesn't allow block-level commits, like it should. English cased
Version and Copyright are aliased to the upper case versions, for partial
backward compatability.
* Resolves ticket #34, SAX parser change makes it impossible to parse IO feeds.
* Moves parser.source.position() to parser.position()
* Fixes ticket:48, repeated writes munging text content
* Fixes ticket:46, adding methods for accessing notation DTD information.
* Encodes some characters and removes a brokes link in the documentation
* Deals with carriage returns after XML declarations
* Improved doctype handling
* Whitespace handling changes
* Applies a patch by David Tardon, which (incidentally) fixes ticket:50
* Closes #26, allowing anything that walks like an IO to be a source.
* Ticket #31 - One unescape too many
This wasn't really a bug, per se... "value" always returns
a normalized string, and "value" is the method used to get
the text() of an element. However, entities have no meaning
in CDATA sections, so there's no justification for value
to be normalizing the content of CData objects. This behavior
has therefore been changed.
* Ticket #45 -- Now parses notation declarations in DTDs properly.
* Resolves ticket #49, Document.parse_stream returns ArgumentError
* Adds documentation to clarify how XMLDecl works, to avoid invalid bug reports.
* Addresses ticket #10, fixing the StreamParser API for DTDs.
* Fixes ticket #42, XPath node-set function 'name' fails with relative node
set parameter
* Good patch by Aaron to fix ticket #53: REXML ignoring unbalanced tags
at the end of a document.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@10092 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
2006-04-15 00:11:04 -04:00
|
|
|
|
2008-10-01 09:46:53 -04:00
|
|
|
# According to the XML spec, a root node has no expanded name
|
|
|
|
def expanded_name
|
|
|
|
''
|
|
|
|
#d = doc_type
|
|
|
|
#d ? d.name : "UNDEFINED"
|
|
|
|
end
|
Short summary:
This is a version bump to REXML 3.1.4 for Ruby HEAD. This change log is
identical to the log for the 1.8 branch.
It includes numerous bug fixes and is a pretty big patch, but is nonetheless
a minor revision bump, since the API hasn't changed.
For more information, see:
http:/www.germane-software.com/projects/rexml/milestone/3.1.4
For all tickets, see:
http://www.germane-software.com/projects/rexml/ticket/#
Where '#' is replaced with the ticket number.
Changelog:
* Fixed the documentation WRT the raw mode of text nodes (ticket #4)
* Fixes roundup ticket #43: substring-after bug.
* Fixed ticket #44, Element#xpath
* Patch submitted by an anonymous doner to allow parsing of Tempfiles. I was
hoping that, by now, that whole Source thing would have been changed to use
duck typing and avoid this sort of ticket... but in the meantime, the patch
has been applied.
* Fixes ticket:30, XPath default namespace bug. The fix was provided
by Lucas Nussbaum.
* Aliases #size to #length, as per zdennis's request.
* Fixes typo from previous commit
* Fixes ticket #32, preceding-sibling fails attempting delete_if on nil nodeset
* Merges a user-contributed patch for ticket #40
* Adds a forgotten-to-commit unit test for ticket #32
* Changes Date, Version, and Copyright to upper case, to avoid conflicts with
the Date class. All of the other changes in the altered files are because
Subversion doesn't allow block-level commits, like it should. English cased
Version and Copyright are aliased to the upper case versions, for partial
backward compatability.
* Resolves ticket #34, SAX parser change makes it impossible to parse IO feeds.
* Moves parser.source.position() to parser.position()
* Fixes ticket:48, repeated writes munging text content
* Fixes ticket:46, adding methods for accessing notation DTD information.
* Encodes some characters and removes a brokes link in the documentation
* Deals with carriage returns after XML declarations
* Improved doctype handling
* Whitespace handling changes
* Applies a patch by David Tardon, which (incidentally) fixes ticket:50
* Closes #26, allowing anything that walks like an IO to be a source.
* Ticket #31 - One unescape too many
This wasn't really a bug, per se... "value" always returns
a normalized string, and "value" is the method used to get
the text() of an element. However, entities have no meaning
in CDATA sections, so there's no justification for value
to be normalizing the content of CData objects. This behavior
has therefore been changed.
* Ticket #45 -- Now parses notation declarations in DTDs properly.
* Resolves ticket #49, Document.parse_stream returns ArgumentError
* Adds documentation to clarify how XMLDecl works, to avoid invalid bug reports.
* Addresses ticket #10, fixing the StreamParser API for DTDs.
* Fixes ticket #42, XPath node-set function 'name' fails with relative node
set parameter
* Good patch by Aaron to fix ticket #53: REXML ignoring unbalanced tags
at the end of a document.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@10092 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
2006-04-15 00:11:04 -04:00
|
|
|
|
2008-10-01 09:46:53 -04:00
|
|
|
alias :name :expanded_name
|
Short summary:
This is a version bump to REXML 3.1.4 for Ruby HEAD. This change log is
identical to the log for the 1.8 branch.
It includes numerous bug fixes and is a pretty big patch, but is nonetheless
a minor revision bump, since the API hasn't changed.
For more information, see:
http:/www.germane-software.com/projects/rexml/milestone/3.1.4
For all tickets, see:
http://www.germane-software.com/projects/rexml/ticket/#
Where '#' is replaced with the ticket number.
Changelog:
* Fixed the documentation WRT the raw mode of text nodes (ticket #4)
* Fixes roundup ticket #43: substring-after bug.
* Fixed ticket #44, Element#xpath
* Patch submitted by an anonymous doner to allow parsing of Tempfiles. I was
hoping that, by now, that whole Source thing would have been changed to use
duck typing and avoid this sort of ticket... but in the meantime, the patch
has been applied.
* Fixes ticket:30, XPath default namespace bug. The fix was provided
by Lucas Nussbaum.
* Aliases #size to #length, as per zdennis's request.
* Fixes typo from previous commit
* Fixes ticket #32, preceding-sibling fails attempting delete_if on nil nodeset
* Merges a user-contributed patch for ticket #40
* Adds a forgotten-to-commit unit test for ticket #32
* Changes Date, Version, and Copyright to upper case, to avoid conflicts with
the Date class. All of the other changes in the altered files are because
Subversion doesn't allow block-level commits, like it should. English cased
Version and Copyright are aliased to the upper case versions, for partial
backward compatability.
* Resolves ticket #34, SAX parser change makes it impossible to parse IO feeds.
* Moves parser.source.position() to parser.position()
* Fixes ticket:48, repeated writes munging text content
* Fixes ticket:46, adding methods for accessing notation DTD information.
* Encodes some characters and removes a brokes link in the documentation
* Deals with carriage returns after XML declarations
* Improved doctype handling
* Whitespace handling changes
* Applies a patch by David Tardon, which (incidentally) fixes ticket:50
* Closes #26, allowing anything that walks like an IO to be a source.
* Ticket #31 - One unescape too many
This wasn't really a bug, per se... "value" always returns
a normalized string, and "value" is the method used to get
the text() of an element. However, entities have no meaning
in CDATA sections, so there's no justification for value
to be normalizing the content of CData objects. This behavior
has therefore been changed.
* Ticket #45 -- Now parses notation declarations in DTDs properly.
* Resolves ticket #49, Document.parse_stream returns ArgumentError
* Adds documentation to clarify how XMLDecl works, to avoid invalid bug reports.
* Addresses ticket #10, fixing the StreamParser API for DTDs.
* Fixes ticket #42, XPath node-set function 'name' fails with relative node
set parameter
* Good patch by Aaron to fix ticket #53: REXML ignoring unbalanced tags
at the end of a document.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@10092 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
2006-04-15 00:11:04 -04:00
|
|
|
|
2008-10-01 09:46:53 -04:00
|
|
|
# We override this, because XMLDecls and DocTypes must go at the start
|
|
|
|
# of the document
|
|
|
|
def add( child )
|
|
|
|
if child.kind_of? XMLDecl
|
|
|
|
@children.unshift child
|
2007-10-01 21:45:55 -04:00
|
|
|
child.parent = self
|
2008-10-01 09:46:53 -04:00
|
|
|
elsif child.kind_of? DocType
|
Short summary:
This is a version bump to REXML 3.1.4 for Ruby HEAD. This change log is
identical to the log for the 1.8 branch.
It includes numerous bug fixes and is a pretty big patch, but is nonetheless
a minor revision bump, since the API hasn't changed.
For more information, see:
http:/www.germane-software.com/projects/rexml/milestone/3.1.4
For all tickets, see:
http://www.germane-software.com/projects/rexml/ticket/#
Where '#' is replaced with the ticket number.
Changelog:
* Fixed the documentation WRT the raw mode of text nodes (ticket #4)
* Fixes roundup ticket #43: substring-after bug.
* Fixed ticket #44, Element#xpath
* Patch submitted by an anonymous doner to allow parsing of Tempfiles. I was
hoping that, by now, that whole Source thing would have been changed to use
duck typing and avoid this sort of ticket... but in the meantime, the patch
has been applied.
* Fixes ticket:30, XPath default namespace bug. The fix was provided
by Lucas Nussbaum.
* Aliases #size to #length, as per zdennis's request.
* Fixes typo from previous commit
* Fixes ticket #32, preceding-sibling fails attempting delete_if on nil nodeset
* Merges a user-contributed patch for ticket #40
* Adds a forgotten-to-commit unit test for ticket #32
* Changes Date, Version, and Copyright to upper case, to avoid conflicts with
the Date class. All of the other changes in the altered files are because
Subversion doesn't allow block-level commits, like it should. English cased
Version and Copyright are aliased to the upper case versions, for partial
backward compatability.
* Resolves ticket #34, SAX parser change makes it impossible to parse IO feeds.
* Moves parser.source.position() to parser.position()
* Fixes ticket:48, repeated writes munging text content
* Fixes ticket:46, adding methods for accessing notation DTD information.
* Encodes some characters and removes a brokes link in the documentation
* Deals with carriage returns after XML declarations
* Improved doctype handling
* Whitespace handling changes
* Applies a patch by David Tardon, which (incidentally) fixes ticket:50
* Closes #26, allowing anything that walks like an IO to be a source.
* Ticket #31 - One unescape too many
This wasn't really a bug, per se... "value" always returns
a normalized string, and "value" is the method used to get
the text() of an element. However, entities have no meaning
in CDATA sections, so there's no justification for value
to be normalizing the content of CData objects. This behavior
has therefore been changed.
* Ticket #45 -- Now parses notation declarations in DTDs properly.
* Resolves ticket #49, Document.parse_stream returns ArgumentError
* Adds documentation to clarify how XMLDecl works, to avoid invalid bug reports.
* Addresses ticket #10, fixing the StreamParser API for DTDs.
* Fixes ticket #42, XPath node-set function 'name' fails with relative node
set parameter
* Good patch by Aaron to fix ticket #53: REXML ignoring unbalanced tags
at the end of a document.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@10092 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
2006-04-15 00:11:04 -04:00
|
|
|
# Find first Element or DocType node and insert the decl right
|
|
|
|
# before it. If there is no such node, just insert the child at the
|
|
|
|
# end. If there is a child and it is an DocType, then replace it.
|
|
|
|
insert_before_index = 0
|
|
|
|
@children.find { |x|
|
|
|
|
insert_before_index += 1
|
|
|
|
x.kind_of?(Element) || x.kind_of?(DocType)
|
|
|
|
}
|
|
|
|
if @children[ insert_before_index ] # Not null = not end of list
|
|
|
|
if @children[ insert_before_index ].kind_of DocType
|
|
|
|
@children[ insert_before_index ] = child
|
|
|
|
else
|
|
|
|
@children[ index_before_index-1, 0 ] = child
|
|
|
|
end
|
|
|
|
else # Insert at end of list
|
|
|
|
@children[insert_before_index] = child
|
Merged in development from the main REXML repository.
* Fixed bug #34, typo in xpath_parser.
* Previous fix, (include? -> includes?) was incorrect.
* Added another test for encoding
* Started AnyName support in RelaxNG
* Added Element#Attributes#to_a, so that it does something intelligent.
This was needed by XPath, for '@*'
* Fixed XPath so that @* works.
* Added xmlgrep to the bin/ directory. A little tool allowing you to grep
for XPaths in an XML document.
* Fixed a CDATA pretty-printing bug. (#39)
* Fixed a buffering bug in Source.rb that affected the SAX parser
This bug was related to how REXML determines the encoding of a file, and
evinced itself by hanging on input when using the SAX parser.
* The unit test for the previous patch. Forgot to commit it.
* Minor pretty printing fix.
* Applied Curt Sampson's optimization improvements
* Issue #9; 3.1.3: The SAX parser was not denormalizing entity references
in incoming text. All declared internal entities, as well as numeric
entities, should now be denormalized. There was a related bug in that the
SAX parser was actually double-encoding entities; this is also fixed.
* bin/* programs should now be executable. Setting bin apps to executable
* Issue 14; 3.1.3: DTD events are now all being passed by StreamParser
Some of the DTD events were not being passed through by the stream parser.
* #26: Element#add_element(nil) now raises an error Changed XPath searches so
that if a non-Hash is passed, an error is raised Fixed a spurrious undefined
method error in encoding. #29: XPath ordering bug fixed by Mark Williams.
Incidentally, Mark supplied a superlative bug report, including a full unit
test. Then he went ahead and fixed the bug. It doesn't get any better than
this, folks.
* Fixed a broken link. Thanks to Dick Davies for pointing it out. Added
functions courtesy of Michael Neumann <mneumann@xxxx.de>.
Example code to follow.
* Added Michael's sample code. Merged the changes in from branches/xpath_V
* Fixed preceding:: and following:: axis Fixed the ordering bug that Martin
Fowler reported.
* Uncommented some code commented for testing Applied Nobu's changes to the
Encoding infrastructure, which should fix potential threading issues.
* Added more tests, and the missing syncenumerator class. Fixed the
inheritance bug in the pull parser that James Britt found. Indentation
changes, and changed some exceptions to runtime
exceptions.
* Changes by Matz, mostly of indent -> indent_level, to avoid
function/variable naming conflicts
* Tabs -> spaces (whitespace)
Note the addition of syncenumerator.rb. This is a stopgap, until I can work on
the class enough to get it accepted as a replacement for the SyncEnumerator
that comes with the Generator class. My version is orders of magnitude faster
than the Generator SyncEnumerator, but is currently missing a couple of
features of the original. Eventually, I expect this class to migrate to
another part of the source tree.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@8483 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
2005-05-18 22:58:11 -04:00
|
|
|
end
|
2008-10-01 09:46:53 -04:00
|
|
|
child.parent = self
|
|
|
|
else
|
|
|
|
rv = super
|
|
|
|
raise "attempted adding second root element to document" if @elements.size > 1
|
|
|
|
rv
|
|
|
|
end
|
|
|
|
end
|
|
|
|
alias :<< :add
|
|
|
|
|
|
|
|
def add_element(arg=nil, arg2=nil)
|
|
|
|
rv = super
|
|
|
|
raise "attempted adding second root element to document" if @elements.size > 1
|
|
|
|
rv
|
|
|
|
end
|
|
|
|
|
|
|
|
# @return the root Element of the document, or nil if this document
|
|
|
|
# has no children.
|
|
|
|
def root
|
Merged in development from the main REXML repository.
* Fixed bug #34, typo in xpath_parser.
* Previous fix, (include? -> includes?) was incorrect.
* Added another test for encoding
* Started AnyName support in RelaxNG
* Added Element#Attributes#to_a, so that it does something intelligent.
This was needed by XPath, for '@*'
* Fixed XPath so that @* works.
* Added xmlgrep to the bin/ directory. A little tool allowing you to grep
for XPaths in an XML document.
* Fixed a CDATA pretty-printing bug. (#39)
* Fixed a buffering bug in Source.rb that affected the SAX parser
This bug was related to how REXML determines the encoding of a file, and
evinced itself by hanging on input when using the SAX parser.
* The unit test for the previous patch. Forgot to commit it.
* Minor pretty printing fix.
* Applied Curt Sampson's optimization improvements
* Issue #9; 3.1.3: The SAX parser was not denormalizing entity references
in incoming text. All declared internal entities, as well as numeric
entities, should now be denormalized. There was a related bug in that the
SAX parser was actually double-encoding entities; this is also fixed.
* bin/* programs should now be executable. Setting bin apps to executable
* Issue 14; 3.1.3: DTD events are now all being passed by StreamParser
Some of the DTD events were not being passed through by the stream parser.
* #26: Element#add_element(nil) now raises an error Changed XPath searches so
that if a non-Hash is passed, an error is raised Fixed a spurrious undefined
method error in encoding. #29: XPath ordering bug fixed by Mark Williams.
Incidentally, Mark supplied a superlative bug report, including a full unit
test. Then he went ahead and fixed the bug. It doesn't get any better than
this, folks.
* Fixed a broken link. Thanks to Dick Davies for pointing it out. Added
functions courtesy of Michael Neumann <mneumann@xxxx.de>.
Example code to follow.
* Added Michael's sample code. Merged the changes in from branches/xpath_V
* Fixed preceding:: and following:: axis Fixed the ordering bug that Martin
Fowler reported.
* Uncommented some code commented for testing Applied Nobu's changes to the
Encoding infrastructure, which should fix potential threading issues.
* Added more tests, and the missing syncenumerator class. Fixed the
inheritance bug in the pull parser that James Britt found. Indentation
changes, and changed some exceptions to runtime
exceptions.
* Changes by Matz, mostly of indent -> indent_level, to avoid
function/variable naming conflicts
* Tabs -> spaces (whitespace)
Note the addition of syncenumerator.rb. This is a stopgap, until I can work on
the class enough to get it accepted as a replacement for the SyncEnumerator
that comes with the Generator class. My version is orders of magnitude faster
than the Generator SyncEnumerator, but is currently missing a couple of
features of the original. Eventually, I expect this class to migrate to
another part of the source tree.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@8483 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
2005-05-18 22:58:11 -04:00
|
|
|
elements[1]
|
|
|
|
#self
|
|
|
|
#@children.find { |item| item.kind_of? Element }
|
2008-10-01 09:46:53 -04:00
|
|
|
end
|
|
|
|
|
|
|
|
# @return the DocType child of the document, if one exists,
|
|
|
|
# and nil otherwise.
|
|
|
|
def doctype
|
|
|
|
@children.find { |item| item.kind_of? DocType }
|
|
|
|
end
|
|
|
|
|
|
|
|
# @return the XMLDecl of this document; if no XMLDecl has been
|
|
|
|
# set, the default declaration is returned.
|
|
|
|
def xml_decl
|
|
|
|
rv = @children[0]
|
2003-12-08 21:41:33 -05:00
|
|
|
return rv if rv.kind_of? XMLDecl
|
|
|
|
rv = @children.unshift(XMLDecl.default)[0]
|
2008-10-01 09:46:53 -04:00
|
|
|
end
|
|
|
|
|
|
|
|
# @return the XMLDecl version of this document as a String.
|
|
|
|
# If no XMLDecl has been set, returns the default version.
|
|
|
|
def version
|
|
|
|
xml_decl().version
|
|
|
|
end
|
|
|
|
|
|
|
|
# @return the XMLDecl encoding of this document as a String.
|
|
|
|
# If no XMLDecl has been set, returns the default encoding.
|
|
|
|
def encoding
|
|
|
|
xml_decl().encoding
|
|
|
|
end
|
|
|
|
|
|
|
|
# @return the XMLDecl standalone value of this document as a String.
|
|
|
|
# If no XMLDecl has been set, returns the default setting.
|
|
|
|
def stand_alone?
|
|
|
|
xml_decl().stand_alone?
|
|
|
|
end
|
Short summary:
This is a version bump to REXML 3.1.4 for Ruby HEAD. This change log is
identical to the log for the 1.8 branch.
It includes numerous bug fixes and is a pretty big patch, but is nonetheless
a minor revision bump, since the API hasn't changed.
For more information, see:
http:/www.germane-software.com/projects/rexml/milestone/3.1.4
For all tickets, see:
http://www.germane-software.com/projects/rexml/ticket/#
Where '#' is replaced with the ticket number.
Changelog:
* Fixed the documentation WRT the raw mode of text nodes (ticket #4)
* Fixes roundup ticket #43: substring-after bug.
* Fixed ticket #44, Element#xpath
* Patch submitted by an anonymous doner to allow parsing of Tempfiles. I was
hoping that, by now, that whole Source thing would have been changed to use
duck typing and avoid this sort of ticket... but in the meantime, the patch
has been applied.
* Fixes ticket:30, XPath default namespace bug. The fix was provided
by Lucas Nussbaum.
* Aliases #size to #length, as per zdennis's request.
* Fixes typo from previous commit
* Fixes ticket #32, preceding-sibling fails attempting delete_if on nil nodeset
* Merges a user-contributed patch for ticket #40
* Adds a forgotten-to-commit unit test for ticket #32
* Changes Date, Version, and Copyright to upper case, to avoid conflicts with
the Date class. All of the other changes in the altered files are because
Subversion doesn't allow block-level commits, like it should. English cased
Version and Copyright are aliased to the upper case versions, for partial
backward compatability.
* Resolves ticket #34, SAX parser change makes it impossible to parse IO feeds.
* Moves parser.source.position() to parser.position()
* Fixes ticket:48, repeated writes munging text content
* Fixes ticket:46, adding methods for accessing notation DTD information.
* Encodes some characters and removes a brokes link in the documentation
* Deals with carriage returns after XML declarations
* Improved doctype handling
* Whitespace handling changes
* Applies a patch by David Tardon, which (incidentally) fixes ticket:50
* Closes #26, allowing anything that walks like an IO to be a source.
* Ticket #31 - One unescape too many
This wasn't really a bug, per se... "value" always returns
a normalized string, and "value" is the method used to get
the text() of an element. However, entities have no meaning
in CDATA sections, so there's no justification for value
to be normalizing the content of CData objects. This behavior
has therefore been changed.
* Ticket #45 -- Now parses notation declarations in DTDs properly.
* Resolves ticket #49, Document.parse_stream returns ArgumentError
* Adds documentation to clarify how XMLDecl works, to avoid invalid bug reports.
* Addresses ticket #10, fixing the StreamParser API for DTDs.
* Fixes ticket #42, XPath node-set function 'name' fails with relative node
set parameter
* Good patch by Aaron to fix ticket #53: REXML ignoring unbalanced tags
at the end of a document.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@10092 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
2006-04-15 00:11:04 -04:00
|
|
|
|
2007-10-01 21:45:19 -04:00
|
|
|
# Write the XML tree out, optionally with indent. This writes out the
|
|
|
|
# entire XML document, including XML declarations, doctype declarations,
|
|
|
|
# and processing instructions (if any are given).
|
|
|
|
#
|
|
|
|
# A controversial point is whether Document should always write the XML
|
|
|
|
# declaration (<?xml version='1.0'?>) whether or not one is given by the
|
|
|
|
# user (or source document). REXML does not write one if one was not
|
2008-06-04 05:37:38 -04:00
|
|
|
# specified, because it adds unnecessary bandwidth to applications such
|
2007-10-01 21:45:19 -04:00
|
|
|
# as XML-RPC.
|
Merges upstream changes for REXML v3.1.7
http://www.germane-software.com/repos/rexml/tags/3.1.7
r1278@bean: ser | 2007-06-07 00:53:06 -0400
Fixed a double-encoding bug. This was a regression, related
to ticket:48.
r1292@bean: ser | 2007-07-25 08:19:36 -0400
r1279@bean: ser | 2007-06-09 23:19:02 -0400
Fixes ticket:89 -- encoding CP-1252 was broken. ISO-8859-15 had the same
problem.
Also in this patch is a fix to merge.rb (unused, but it should at least
contain no errors), and a unit test for ticket:88.
r1293@bean: ser | 2007-07-25 08:19:37 -0400
r1281@bean: ser | 2007-07-24 11:08:48 -0400
Addresses ticket:85
This is a major rewrite of the XML formatting code. The XML writers have all
been extracted out of the classes and put into their own class containers.
This makes writing parsers easier, and cleaner.
There are three formatters, which correspond to the previous three XML writing
modes:
REXML::Formatters::Default
Prints the XML document exactly as it was parsed
REXML::Formatters::Pretty
Pretty prints the XML document, destroying whitespace in the document
REXML::Formatters::Transitive
Pretty prints the XML document, preserving whitespace
All of the write() functions have been deprecated (some are still used, but
these will also go away) except the write() function on Document, which is left
for convenience. To pretty print an XML document the canonical way:
formatter = REXML::Formatters::Pretty.new( 5 ) # indent by 5 spaces
formatter.write( document, output )
r1294@bean: ser | 2007-07-25 08:19:38 -0400
r1283@bean: ser | 2007-07-24 19:53:30 -0400
This goes with the previous commit.
r1295@bean: ser | 2007-07-25 08:19:39 -0400
r1285@bean: ser | 2007-07-24 20:02:07 -0400
And THIS goes with the previous two patches. Dammit.
r1296@bean: ser | 2007-07-25 08:19:40 -0400
r1287@bean: ser | 2007-07-24 20:12:25 -0400
Applied patch from Jeff Barczewski. Note that this changes what the values of
the name and IDs are from the previous behavior -- the values no longer include
the quotes. This is the correct behavior, so I'm leaving it in, but it is not
backwards compatible. Also fixes the serializer so that it outputs the doctype
in a correct format (needed as a result of this change).
r1297@bean: ser | 2007-07-25 08:38:38 -0400
Version update
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@12844 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
2007-07-25 08:47:23 -04:00
|
|
|
#
|
2007-10-01 21:45:19 -04:00
|
|
|
# See also the classes in the rexml/formatters package for the proper way
|
|
|
|
# to change the default formatting of XML output
|
Merges upstream changes for REXML v3.1.7
http://www.germane-software.com/repos/rexml/tags/3.1.7
r1278@bean: ser | 2007-06-07 00:53:06 -0400
Fixed a double-encoding bug. This was a regression, related
to ticket:48.
r1292@bean: ser | 2007-07-25 08:19:36 -0400
r1279@bean: ser | 2007-06-09 23:19:02 -0400
Fixes ticket:89 -- encoding CP-1252 was broken. ISO-8859-15 had the same
problem.
Also in this patch is a fix to merge.rb (unused, but it should at least
contain no errors), and a unit test for ticket:88.
r1293@bean: ser | 2007-07-25 08:19:37 -0400
r1281@bean: ser | 2007-07-24 11:08:48 -0400
Addresses ticket:85
This is a major rewrite of the XML formatting code. The XML writers have all
been extracted out of the classes and put into their own class containers.
This makes writing parsers easier, and cleaner.
There are three formatters, which correspond to the previous three XML writing
modes:
REXML::Formatters::Default
Prints the XML document exactly as it was parsed
REXML::Formatters::Pretty
Pretty prints the XML document, destroying whitespace in the document
REXML::Formatters::Transitive
Pretty prints the XML document, preserving whitespace
All of the write() functions have been deprecated (some are still used, but
these will also go away) except the write() function on Document, which is left
for convenience. To pretty print an XML document the canonical way:
formatter = REXML::Formatters::Pretty.new( 5 ) # indent by 5 spaces
formatter.write( document, output )
r1294@bean: ser | 2007-07-25 08:19:38 -0400
r1283@bean: ser | 2007-07-24 19:53:30 -0400
This goes with the previous commit.
r1295@bean: ser | 2007-07-25 08:19:39 -0400
r1285@bean: ser | 2007-07-24 20:02:07 -0400
And THIS goes with the previous two patches. Dammit.
r1296@bean: ser | 2007-07-25 08:19:40 -0400
r1287@bean: ser | 2007-07-24 20:12:25 -0400
Applied patch from Jeff Barczewski. Note that this changes what the values of
the name and IDs are from the previous behavior -- the values no longer include
the quotes. This is the correct behavior, so I'm leaving it in, but it is not
backwards compatible. Also fixes the serializer so that it outputs the doctype
in a correct format (needed as a result of this change).
r1297@bean: ser | 2007-07-25 08:38:38 -0400
Version update
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@12844 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
2007-07-25 08:47:23 -04:00
|
|
|
#
|
|
|
|
# _Examples_
|
|
|
|
# Document.new("<a><b/></a>").serialize
|
|
|
|
#
|
|
|
|
# output_string = ""
|
|
|
|
# tr = Transitive.new( output_string )
|
|
|
|
# Document.new("<a><b/></a>").serialize( tr )
|
|
|
|
#
|
2007-10-01 21:45:19 -04:00
|
|
|
# output::
|
|
|
|
# output an object which supports '<< string'; this is where the
|
|
|
|
# document will be written.
|
|
|
|
# indent::
|
|
|
|
# An integer. If -1, no indenting will be used; otherwise, the
|
|
|
|
# indentation will be twice this number of spaces, and children will be
|
|
|
|
# indented an additional amount. For a value of 3, every item will be
|
Merged from REXML main repository:
Fixes ticket:68.
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.
Two unrelated changes, because subversion is retarded and doesn't do
block-level commits:
1) Fixed a typo bug in previous change for ticket:15
2) 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 know
that this will piss some people off, but defaulting to the pure Ruby version
isn't the correct solution, and it breaks other encodings, so I've reverted it.
* Fixes ticket:61 (xpath_parser)
* Fixes ticket:63 (UTF-16; UNILE decoding was bad)
* Cleans up some tests, removing opportunities for test corruption
* 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.
Cross-ported a fix for ticket:88 from CVS.
Fixes ticket:80
Documentation cleanup. Ticket:84
Applied Kou's fix for an un-trac'ed bug.
------------------------------------------------------------------------
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@11548 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
2007-01-19 22:56:02 -05:00
|
|
|
# indented 3 more levels, or 6 more spaces (2 * 3). Defaults to -1
|
2008-06-05 07:22:32 -04:00
|
|
|
# transitive::
|
2007-10-01 21:45:19 -04:00
|
|
|
# If transitive is true and indent is >= 0, then the output will be
|
|
|
|
# pretty-printed in such a way that the added whitespace does not affect
|
|
|
|
# the absolute *value* of the document -- that is, it leaves the value
|
|
|
|
# and number of Text nodes in the document unchanged.
|
|
|
|
# ie_hack::
|
|
|
|
# Internet Explorer is the worst piece of crap to have ever been
|
|
|
|
# written, with the possible exception of Windows itself. Since IE is
|
|
|
|
# unable to parse proper XML, we have to provide a hack to generate XML
|
|
|
|
# that IE's limited abilities can handle. This hack inserts a space
|
|
|
|
# before the /> on empty tags. Defaults to false
|
2007-10-12 11:19:28 -04:00
|
|
|
def write( output=$stdout, indent=-1, transitive=false, ie_hack=false )
|
Merges upstream changes for REXML v3.1.7
http://www.germane-software.com/repos/rexml/tags/3.1.7
r1278@bean: ser | 2007-06-07 00:53:06 -0400
Fixed a double-encoding bug. This was a regression, related
to ticket:48.
r1292@bean: ser | 2007-07-25 08:19:36 -0400
r1279@bean: ser | 2007-06-09 23:19:02 -0400
Fixes ticket:89 -- encoding CP-1252 was broken. ISO-8859-15 had the same
problem.
Also in this patch is a fix to merge.rb (unused, but it should at least
contain no errors), and a unit test for ticket:88.
r1293@bean: ser | 2007-07-25 08:19:37 -0400
r1281@bean: ser | 2007-07-24 11:08:48 -0400
Addresses ticket:85
This is a major rewrite of the XML formatting code. The XML writers have all
been extracted out of the classes and put into their own class containers.
This makes writing parsers easier, and cleaner.
There are three formatters, which correspond to the previous three XML writing
modes:
REXML::Formatters::Default
Prints the XML document exactly as it was parsed
REXML::Formatters::Pretty
Pretty prints the XML document, destroying whitespace in the document
REXML::Formatters::Transitive
Pretty prints the XML document, preserving whitespace
All of the write() functions have been deprecated (some are still used, but
these will also go away) except the write() function on Document, which is left
for convenience. To pretty print an XML document the canonical way:
formatter = REXML::Formatters::Pretty.new( 5 ) # indent by 5 spaces
formatter.write( document, output )
r1294@bean: ser | 2007-07-25 08:19:38 -0400
r1283@bean: ser | 2007-07-24 19:53:30 -0400
This goes with the previous commit.
r1295@bean: ser | 2007-07-25 08:19:39 -0400
r1285@bean: ser | 2007-07-24 20:02:07 -0400
And THIS goes with the previous two patches. Dammit.
r1296@bean: ser | 2007-07-25 08:19:40 -0400
r1287@bean: ser | 2007-07-24 20:12:25 -0400
Applied patch from Jeff Barczewski. Note that this changes what the values of
the name and IDs are from the previous behavior -- the values no longer include
the quotes. This is the correct behavior, so I'm leaving it in, but it is not
backwards compatible. Also fixes the serializer so that it outputs the doctype
in a correct format (needed as a result of this change).
r1297@bean: ser | 2007-07-25 08:38:38 -0400
Version update
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@12844 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
2007-07-25 08:47:23 -04:00
|
|
|
if xml_decl.encoding != "UTF-8" && !output.kind_of?(Output)
|
|
|
|
output = Output.new( output, xml_decl.encoding )
|
|
|
|
end
|
|
|
|
formatter = if indent > -1
|
2008-06-05 07:22:32 -04:00
|
|
|
if transitive
|
Merges upstream changes for REXML v3.1.7
http://www.germane-software.com/repos/rexml/tags/3.1.7
r1278@bean: ser | 2007-06-07 00:53:06 -0400
Fixed a double-encoding bug. This was a regression, related
to ticket:48.
r1292@bean: ser | 2007-07-25 08:19:36 -0400
r1279@bean: ser | 2007-06-09 23:19:02 -0400
Fixes ticket:89 -- encoding CP-1252 was broken. ISO-8859-15 had the same
problem.
Also in this patch is a fix to merge.rb (unused, but it should at least
contain no errors), and a unit test for ticket:88.
r1293@bean: ser | 2007-07-25 08:19:37 -0400
r1281@bean: ser | 2007-07-24 11:08:48 -0400
Addresses ticket:85
This is a major rewrite of the XML formatting code. The XML writers have all
been extracted out of the classes and put into their own class containers.
This makes writing parsers easier, and cleaner.
There are three formatters, which correspond to the previous three XML writing
modes:
REXML::Formatters::Default
Prints the XML document exactly as it was parsed
REXML::Formatters::Pretty
Pretty prints the XML document, destroying whitespace in the document
REXML::Formatters::Transitive
Pretty prints the XML document, preserving whitespace
All of the write() functions have been deprecated (some are still used, but
these will also go away) except the write() function on Document, which is left
for convenience. To pretty print an XML document the canonical way:
formatter = REXML::Formatters::Pretty.new( 5 ) # indent by 5 spaces
formatter.write( document, output )
r1294@bean: ser | 2007-07-25 08:19:38 -0400
r1283@bean: ser | 2007-07-24 19:53:30 -0400
This goes with the previous commit.
r1295@bean: ser | 2007-07-25 08:19:39 -0400
r1285@bean: ser | 2007-07-24 20:02:07 -0400
And THIS goes with the previous two patches. Dammit.
r1296@bean: ser | 2007-07-25 08:19:40 -0400
r1287@bean: ser | 2007-07-24 20:12:25 -0400
Applied patch from Jeff Barczewski. Note that this changes what the values of
the name and IDs are from the previous behavior -- the values no longer include
the quotes. This is the correct behavior, so I'm leaving it in, but it is not
backwards compatible. Also fixes the serializer so that it outputs the doctype
in a correct format (needed as a result of this change).
r1297@bean: ser | 2007-07-25 08:38:38 -0400
Version update
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@12844 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
2007-07-25 08:47:23 -04:00
|
|
|
REXML::Formatters::Transitive.new( indent, ie_hack )
|
|
|
|
else
|
|
|
|
REXML::Formatters::Pretty.new( indent, ie_hack )
|
|
|
|
end
|
|
|
|
else
|
|
|
|
REXML::Formatters::Default.new( ie_hack )
|
2004-07-18 10:04:03 -04:00
|
|
|
end
|
Merges upstream changes for REXML v3.1.7
http://www.germane-software.com/repos/rexml/tags/3.1.7
r1278@bean: ser | 2007-06-07 00:53:06 -0400
Fixed a double-encoding bug. This was a regression, related
to ticket:48.
r1292@bean: ser | 2007-07-25 08:19:36 -0400
r1279@bean: ser | 2007-06-09 23:19:02 -0400
Fixes ticket:89 -- encoding CP-1252 was broken. ISO-8859-15 had the same
problem.
Also in this patch is a fix to merge.rb (unused, but it should at least
contain no errors), and a unit test for ticket:88.
r1293@bean: ser | 2007-07-25 08:19:37 -0400
r1281@bean: ser | 2007-07-24 11:08:48 -0400
Addresses ticket:85
This is a major rewrite of the XML formatting code. The XML writers have all
been extracted out of the classes and put into their own class containers.
This makes writing parsers easier, and cleaner.
There are three formatters, which correspond to the previous three XML writing
modes:
REXML::Formatters::Default
Prints the XML document exactly as it was parsed
REXML::Formatters::Pretty
Pretty prints the XML document, destroying whitespace in the document
REXML::Formatters::Transitive
Pretty prints the XML document, preserving whitespace
All of the write() functions have been deprecated (some are still used, but
these will also go away) except the write() function on Document, which is left
for convenience. To pretty print an XML document the canonical way:
formatter = REXML::Formatters::Pretty.new( 5 ) # indent by 5 spaces
formatter.write( document, output )
r1294@bean: ser | 2007-07-25 08:19:38 -0400
r1283@bean: ser | 2007-07-24 19:53:30 -0400
This goes with the previous commit.
r1295@bean: ser | 2007-07-25 08:19:39 -0400
r1285@bean: ser | 2007-07-24 20:02:07 -0400
And THIS goes with the previous two patches. Dammit.
r1296@bean: ser | 2007-07-25 08:19:40 -0400
r1287@bean: ser | 2007-07-24 20:12:25 -0400
Applied patch from Jeff Barczewski. Note that this changes what the values of
the name and IDs are from the previous behavior -- the values no longer include
the quotes. This is the correct behavior, so I'm leaving it in, but it is not
backwards compatible. Also fixes the serializer so that it outputs the doctype
in a correct format (needed as a result of this change).
r1297@bean: ser | 2007-07-25 08:38:38 -0400
Version update
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@12844 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
2007-07-25 08:47:23 -04:00
|
|
|
formatter.write( self, output )
|
2008-10-01 09:46:53 -04:00
|
|
|
end
|
2003-06-09 21:31:01 -04:00
|
|
|
|
2008-10-01 09:46:53 -04:00
|
|
|
|
|
|
|
def Document::parse_stream( source, listener )
|
|
|
|
Parsers::StreamParser.new( source, listener ).parse
|
|
|
|
end
|
2003-06-09 21:31:01 -04:00
|
|
|
|
2008-09-01 09:41:38 -04:00
|
|
|
@@entity_expansion_limit = 10_000
|
|
|
|
|
2008-09-12 22:16:05 -04:00
|
|
|
# Set the entity expansion limit. By default the limit is set to 10000.
|
2008-09-01 09:41:38 -04:00
|
|
|
def Document::entity_expansion_limit=( val )
|
|
|
|
@@entity_expansion_limit = val
|
|
|
|
end
|
|
|
|
|
2008-09-12 22:16:05 -04:00
|
|
|
# Get the entity expansion limit. By default the limit is set to 10000.
|
2008-09-01 09:41:38 -04:00
|
|
|
def Document::entity_expansion_limit
|
|
|
|
return @@entity_expansion_limit
|
|
|
|
end
|
|
|
|
|
|
|
|
attr_reader :entity_expansion_count
|
|
|
|
|
|
|
|
def record_entity_expansion
|
|
|
|
@entity_expansion_count += 1
|
|
|
|
if @entity_expansion_count > @@entity_expansion_limit
|
|
|
|
raise "number of entity expansions exceeded, processing aborted."
|
|
|
|
end
|
|
|
|
end
|
|
|
|
|
2008-10-01 09:46:53 -04:00
|
|
|
private
|
|
|
|
def build( source )
|
2004-06-09 22:01:04 -04:00
|
|
|
Parsers::TreeParser.new( source, self ).parse
|
2008-10-01 09:46:53 -04:00
|
|
|
end
|
|
|
|
end
|
2003-06-09 21:31:01 -04:00
|
|
|
end
|