diff --git a/.github/dependabot.yml b/.github/dependabot.yml new file mode 100644 index 00000000..b18fd293 --- /dev/null +++ b/.github/dependabot.yml @@ -0,0 +1,6 @@ +version: 2 +updates: + - package-ecosystem: 'github-actions' + directory: '/' + schedule: + interval: 'weekly' diff --git a/.github/workflows/benchmark.yml b/.github/workflows/benchmark.yml new file mode 100644 index 00000000..52349b44 --- /dev/null +++ b/.github/workflows/benchmark.yml @@ -0,0 +1,29 @@ +name: Benchmark + +on: + - push + - pull_request + +jobs: + benchmark: + name: "Benchmark: Ruby ${{ matrix.ruby-version }}: ${{ matrix.runs-on }}" + strategy: + fail-fast: false + matrix: + ruby-version: + - '3.3' + runs-on: + - ubuntu-latest + runs-on: ${{ matrix.runs-on }} + steps: + - uses: actions/checkout@v4 + - uses: ruby/setup-ruby@v1 + with: + ruby-version: ${{ matrix.ruby-version }} + - name: Install dependencies + run: | + bundle install + gem install rexml -v 3.2.6 + - name: Benchmark + run: | + rake benchmark diff --git a/.github/workflows/release.yml b/.github/workflows/release.yml new file mode 100644 index 00000000..20ff87e7 --- /dev/null +++ b/.github/workflows/release.yml @@ -0,0 +1,30 @@ +name: Release +on: + push: + tags: + - "*" +jobs: + github: + name: GitHub + runs-on: ubuntu-latest + timeout-minutes: 10 + steps: + - uses: actions/checkout@v4 + - name: Extract release note + run: | + ruby \ + -e 'print("## REXML "); \ + puts(ARGF.read.split(/^## /)[1]. \ + gsub(/ {.+?}/, ""). \ + gsub(/\[(.+?)\]\[.+?\]/) {$1})' \ + NEWS.md > release-note.md + - name: Upload to release + run: | + title=$(head -n1 release-note.md | sed -e 's/^## //') + tail -n +2 release-note.md > release-note-without-version.md + gh release create ${GITHUB_REF_NAME} \ + --discussion-category Announcements \ + --notes-file release-note-without-version.md \ + --title "${title}" + env: + GH_TOKEN: ${{ github.token }} diff --git a/.github/workflows/test.yml b/.github/workflows/test.yml index 65a3bffd..fd26b9ab 100644 --- a/.github/workflows/test.yml +++ b/.github/workflows/test.yml @@ -3,7 +3,14 @@ on: - push - pull_request jobs: + ruby-versions: + uses: ruby/actions/.github/workflows/ruby_versions.yml@master + with: + engine: cruby-jruby + min_version: 2.5 + inplace: + needs: ruby-versions name: "Inplace: ${{ matrix.ruby-version }} on ${{ matrix.runs-on }}" runs-on: ${{ matrix.runs-on }} strategy: @@ -13,16 +20,14 @@ jobs: - ubuntu-latest - macos-latest - windows-latest - ruby-version: - - "2.5" - - "2.6" - - "2.7" - - jruby + ruby-version: ${{ fromJson(needs.ruby-versions.outputs.versions) }} + exclude: + - {runs-on: macos-latest, ruby-version: 2.5} # include: # - runs-on: ubuntu-latest # ruby-version: truffleruby steps: - - uses: actions/checkout@v2 + - uses: actions/checkout@v4 - uses: ruby/setup-ruby@v1 with: ruby-version: ${{ matrix.ruby-version }} @@ -30,6 +35,18 @@ jobs: - name: Test run: bundle exec rake test + frozen-string-literal: + name: frozen-string-literal + runs-on: ubuntu-latest + steps: + - uses: actions/checkout@v4 + - uses: ruby/setup-ruby@v1 + with: + ruby-version: ruby + bundler-cache: true + - name: Test + run: bundle exec rake test RUBYOPT="--enable-frozen-string-literal" + gem: name: "Gem: ${{ matrix.ruby-version }} on ${{ matrix.runs-on }}" runs-on: ${{ matrix.runs-on }} @@ -44,13 +61,17 @@ jobs: - "3.0" - head steps: - - uses: actions/checkout@v2 + - uses: actions/checkout@v4 - uses: ruby/setup-ruby@v1 with: ruby-version: ${{ matrix.ruby-version }} - name: Install as gem + env: + BUNDLE_PATH__SYSTEM: "true" + BUNDLE_WITHOUT: "benchmark:development" run: | rake install + bundle install - name: Test run: | ruby -run -e mkdir -- tmp @@ -62,7 +83,7 @@ jobs: name: "Document" runs-on: ubuntu-latest steps: - - uses: actions/checkout@v2 + - uses: actions/checkout@v4 - uses: ruby/setup-ruby@v1 with: ruby-version: 2.7 @@ -72,7 +93,7 @@ jobs: - name: Build document run: | bundle exec rake warning:error rdoc - - uses: actions/checkout@v2 + - uses: actions/checkout@v4 if: | github.event_name == 'push' with: diff --git a/Gemfile b/Gemfile index 54da2c0c..67f21dfb 100644 --- a/Gemfile +++ b/Gemfile @@ -4,3 +4,17 @@ git_source(:github) {|repo_name| "https://github.com/#{repo_name}" } # Specify your gem's dependencies in rexml.gemspec gemspec + +group :development do + gem "bundler" + gem "rake" +end + +group :benchmark do + gem "benchmark_driver" +end + +group :test do + gem "test-unit" + gem "test-unit-ruby-core" +end diff --git a/NEWS.md b/NEWS.md index 84bbde2d..013409e6 100644 --- a/NEWS.md +++ b/NEWS.md @@ -1,15 +1,179 @@ # News +## 3.2.8 - 2024-05-16 {#version-3-2-8} + +### Fixes + + * Suppressed a warning + +## 3.2.7 - 2024-05-16 {#version-3-2-7} + +### Improvements + + * Improve parse performance by using `StringScanner`. + + * GH-106 + * GH-107 + * GH-108 + * GH-109 + * GH-112 + * GH-113 + * GH-114 + * GH-115 + * GH-116 + * GH-117 + * GH-118 + * GH-119 + * GH-121 + + * Patch by NAITOH Jun. + + * Improved parse performance when an attribute has many `<`s. + + * GH-124 + +### Fixes + + * XPath: Fixed a bug of `normalize_space(array)`. + + * GH-110 + * GH-111 + + * Patch by flatisland. + + * XPath: Fixed a bug that wrong position is used with nested path. + + * GH-110 + * GH-122 + + * Reported by jcavalieri. + * Patch by NAITOH Jun. + + * Fixed a bug that an exception message can't be generated for + invalid encoding XML. + + * GH-29 + * GH-123 + + * Reported by DuKewu. + * Patch by NAITOH Jun. + +### Thanks + + * NAITOH Jun + * flatisland + * jcavalieri + * DuKewu + + +## 3.2.6 - 2023-07-27 {#version-3-2-6} + +### Improvements + + * Required Ruby 2.5 or later explicitly. + [GH-69][gh-69] + [Patch by Ivo Anjo] + + * Added documentation for maintenance cycle. + [GH-71][gh-71] + [Patch by Ivo Anjo] + + * Added tutorial. + [GH-77][gh-77] + [GH-78][gh-78] + [Patch by Burdette Lamar] + + * Improved performance and memory usage. + [GH-94][gh-94] + [Patch by fatkodima] + + * `REXML::Parsers::XPathParser#abbreviate`: Added support for + function arguments. + [GH-95][gh-95] + [Reported by pulver] + + * `REXML::Parsers::XPathParser#abbreviate`: Added support for string + literal that contains double-quote. + [GH-96][gh-96] + [Patch by pulver] + + * `REXML::Parsers::XPathParser#abbreviate`: Added missing `/` to + `:descendant_or_self/:self/:parent`. + [GH-97][gh-97] + [Reported by pulver] + + * `REXML::Parsers::XPathParser#abbreviate`: Added support for more patterns. + [GH-97][gh-97] + [Reported by pulver] + +### Fixes + + * Fixed a typo in NEWS. + [GH-72][gh-72] + [Patch by Spencer Goodman] + + * Fixed a typo in NEWS. + [GH-75][gh-75] + [Patch by Andrew Bromwich] + + * Fixed documents. + [GH-87][gh-87] + [Patch by Alexander Ilyin] + + * Fixed a bug that `Attriute` convert `'` and `'` even when + `attribute_quote: :quote` is used. + [GH-92][gh-92] + [Reported by Edouard Brière] + + * Fixed links in tutorial. + [GH-99][gh-99] + [Patch by gemmaro] + + +### Thanks + + * Ivo Anjo + + * Spencer Goodman + + * Andrew Bromwich + + * Burdette Lamar + + * Alexander Ilyin + + * Edouard Brière + + * fatkodima + + * pulver + + * gemmaro + +[gh-69]:https://github.com/ruby/rexml/issues/69 +[gh-71]:https://github.com/ruby/rexml/issues/71 +[gh-72]:https://github.com/ruby/rexml/issues/72 +[gh-75]:https://github.com/ruby/rexml/issues/75 +[gh-77]:https://github.com/ruby/rexml/issues/77 +[gh-87]:https://github.com/ruby/rexml/issues/87 +[gh-92]:https://github.com/ruby/rexml/issues/92 +[gh-94]:https://github.com/ruby/rexml/issues/94 +[gh-95]:https://github.com/ruby/rexml/issues/95 +[gh-96]:https://github.com/ruby/rexml/issues/96 +[gh-97]:https://github.com/ruby/rexml/issues/97 +[gh-98]:https://github.com/ruby/rexml/issues/98 +[gh-99]:https://github.com/ruby/rexml/issues/99 + ## 3.2.5 - 2021-04-05 {#version-3-2-5} ### Improvements * Add more validations to XPath parser. - * `require "rexml/docuemnt"` by default. + * `require "rexml/document"` by default. [GitHub#36][Patch by Koichi ITO] - * Don't add `#dcloe` method to core classes globally. + * Don't add `#dclone` method to core classes globally. [GitHub#37][Patch by Akira Matsuda] * Add more documentations. diff --git a/README.md b/README.md index 27da0e49..e8ab5082 100644 --- a/README.md +++ b/README.md @@ -6,7 +6,7 @@ REXML supports both tree and stream document parsing. Stream parsing is faster ( ## API -See the {API documentation}[https://ruby.github.io/rexml/] +See the [API documentation](https://ruby.github.io/rexml/). ## Usage @@ -33,6 +33,15 @@ doc = Document.new string So parsing a string is just as easy as parsing a file. +## Support + +REXML support follows the same maintenance cycle as Ruby releases, as shown on . + +If you are running on an end-of-life Ruby, do not expect modern REXML releases to be compatible with it; in fact, it's recommended that you DO NOT use this gem, and instead use the REXML version that came bundled with your end-of-life Ruby version. + +The `required_ruby_version` on the gemspec is kept updated on a [best-effort basis](https://github.com/ruby/rexml/pull/70) by the community. +Up to version 3.2.5, this information was not set. That version [is known broken with at least Ruby < 2.3](https://github.com/ruby/rexml/issues/69). + ## Development After checking out the repo, run `rake test` to run the tests. diff --git a/Rakefile b/Rakefile index 7143e754..76a56296 100644 --- a/Rakefile +++ b/Rakefile @@ -28,3 +28,42 @@ RDoc::Task.new do |rdoc| end load "#{__dir__}/tasks/tocs.rake" + +benchmark_tasks = [] +namespace :benchmark do + Dir.glob("benchmark/*.yaml").sort.each do |yaml| + name = File.basename(yaml, ".*") + env = { + "RUBYLIB" => nil, + "BUNDLER_ORIG_RUBYLIB" => nil, + } + command_line = [ + RbConfig.ruby, "-v", "-S", "benchmark-driver", File.expand_path(yaml), + ] + + desc "Run #{name} benchmark" + task name do + puts("```") + sh(env, *command_line) + puts("```") + end + benchmark_tasks << "benchmark:#{name}" + + case name + when /\Aparse/ + namespace name do + desc "Run #{name} benchmark: small" + task :small do + puts("```") + sh(env.merge("N_ELEMENTS" => "500", "N_ATTRIBUTES" => "1"), + *command_line) + puts("```") + end + benchmark_tasks << "benchmark:#{name}:small" + end + end + end +end + +desc "Run all benchmarks" +task :benchmark => benchmark_tasks diff --git a/benchmark/parse.yaml b/benchmark/parse.yaml new file mode 100644 index 00000000..e7066fcb --- /dev/null +++ b/benchmark/parse.yaml @@ -0,0 +1,57 @@ +loop_count: 100 +contexts: + - gems: + rexml: 3.2.6 + require: false + prelude: require 'rexml' + - name: master + prelude: | + $LOAD_PATH.unshift(File.expand_path("lib")) + require 'rexml' + - name: 3.2.6(YJIT) + gems: + rexml: 3.2.6 + require: false + prelude: | + require 'rexml' + RubyVM::YJIT.enable + - name: master(YJIT) + prelude: | + $LOAD_PATH.unshift(File.expand_path("lib")) + require 'rexml' + RubyVM::YJIT.enable + +prelude: | + require 'rexml/document' + require 'rexml/parsers/sax2parser' + require 'rexml/parsers/pullparser' + require 'rexml/parsers/streamparser' + require 'rexml/streamlistener' + + n_elements = Integer(ENV.fetch("N_ELEMENTS", "5000"), 10) + n_attributes = Integer(ENV.fetch("N_ATTRIBUTES", "2"), 10) + + def build_xml(n_elements, n_attributes) + xml = '' + n_elements.times do |i| + xml << '' + end + xml << '' + end + xml = build_xml(n_elements, n_attributes) + + class Listener + include REXML::StreamListener + end + +benchmark: + 'dom' : REXML::Document.new(xml).elements.each("root/child") {|_|} + 'sax' : REXML::Parsers::SAX2Parser.new(xml).parse + 'pull' : | + parser = REXML::Parsers::PullParser.new(xml) + while parser.has_next? + parser.pull + end + 'stream' : REXML::Parsers::StreamParser.new(xml, Listener.new).parse diff --git a/doc/rexml/tasks/rdoc/element.rdoc b/doc/rexml/tasks/rdoc/element.rdoc index f229275f..4b3609b0 100644 --- a/doc/rexml/tasks/rdoc/element.rdoc +++ b/doc/rexml/tasks/rdoc/element.rdoc @@ -369,7 +369,7 @@ to retrieve the first text node in a specified element: Use method {Element#has_text?}[../../../../REXML/Element.html#method-i-has_text-3F] -to determine whethe the element has text: +to determine whether the element has text: e = REXML::Element.new('foo') e.has_text? # => false @@ -486,7 +486,7 @@ to remove a specific namespace from the element: Use method {Element#namespace}[../../../../REXML/Element.html#method-i-namespace] -to retrieve a speficic namespace URI for the element: +to retrieve a specific namespace URI for the element: xml_string = <<-EOT diff --git a/doc/rexml/tutorial.rdoc b/doc/rexml/tutorial.rdoc new file mode 100644 index 00000000..c85a70d0 --- /dev/null +++ b/doc/rexml/tutorial.rdoc @@ -0,0 +1,1358 @@ += \REXML Tutorial + +== Why \REXML? + +- Ruby's \REXML library is part of the Ruby distribution, + so using it requires no gem installations. +- \REXML is fully maintained. +- \REXML is mature, having been in use for long years. + +== To Include, or Not to Include? + +REXML is a module. +To use it, you must require it: + + require 'rexml' # => true + +If you do not also include it, you must fully qualify references to REXML: + + REXML::Document # => REXML::Document + +If you also include the module, you may optionally omit REXML::: + + include REXML + Document # => REXML::Document + REXML::Document # => REXML::Document + +== Preliminaries + +All examples here assume that the following code has been executed: + + require 'rexml' + include REXML + +The source XML for many examples here is from file +{books.xml}[https://www.w3schools.com/xml/books.xml] at w3schools.com. +You may find it convenient to open that page in a new tab +(Ctrl-click in some browsers). + +Note that your browser may display the XML with modified whitespace +and without the XML declaration, which in this case is: + + + +For convenience, we capture the XML into a string variable: + + require 'open-uri' + source_string = URI.open('https://www.w3schools.com/xml/books.xml').read + +And into a file: + + File.write('source_file.xml', source_string) + +Throughout these examples, variable +doc+ will hold only the document +derived from these sources: + + doc = Document.new(source_string) + +== Parsing \XML \Source + +=== Parsing a Document + +Use method REXML::Document::new to parse XML source. + +The source may be a string: + + doc = Document.new(source_string) + +Or an \IO stream: + + doc = File.open('source_file.xml', 'r') do |io| + Document.new(io) + end + +Method URI.open returns a StringIO object, +so the source can be from a web page: + + require 'open-uri' + io = URI.open("https://www.w3schools.com/xml/books.xml") + io.class # => StringIO + doc = Document.new(io) + +For any of these sources, the returned object is an REXML::Document: + + doc # => ... + doc.class # => REXML::Document + +Note: 'UNDEFINED' is the "name" displayed for a document, +even though doc.name returns an empty string "". + +A parsed document may produce \REXML objects of many classes, +but the two that are likely to be of greatest interest are +REXML::Document and REXML::Element. +These two classes are covered in great detail in this tutorial. + +=== Context (Parsing Options) + +The context for parsing a document is a hash that influences +the way the XML is read and stored. + +The context entries are: + +- +:respect_whitespace+: controls treatment of whitespace. +- +:compress_whitespace+: determines whether whitespace is compressed. +- +:ignore_whitespace_nodes+: determines whether whitespace-only nodes are to be ignored. +- +:raw+: controls treatment of special characters and entities. + +See {Element Context}[../context_rdoc.html]. + +== Exploring the Document + +An REXML::Document object represents an XML document. + +The object inherits from its ancestor classes: + +- REXML::Child (includes module REXML::Node) + - REXML::Parent (includes module {Enumerable}[rdoc-ref:Enumerable]). + - REXML::Element (includes module REXML::Namespace). + - REXML::Document + +This section covers only those properties and methods that are unique to a document +(that is, not inherited or included). + +=== Document Properties + +A document has several properties (other than its children); + +- Document type. +- Node type. +- Name. +- Document. +- XPath + +[Document Type] + + A document may have a document type: + + my_xml = '' + my_doc = Document.new(my_xml) + doc_type = my_doc.doctype + doc_type.class # => REXML::DocType + doc_type.to_s # => "" + +[Node Type] + + A document also has a node type (always +:document+): + + doc.node_type # => :document + +[Name] + + A document has a name (always an empty string): + + doc.name # => "" + +[Document] + + \Method REXML::Document#document returns +self+: + + doc.document == doc # => true + + An object of a different class (\REXML::Element or \REXML::Child) + may have a document, which is the document to which the object belongs; + if so, that document will be an \REXML::Document object. + + doc.root.document.class # => REXML::Document + +[XPath] + + \method REXML::Element#xpath returns the string xpath to the element, + relative to its most distant ancestor: + + doc.root.class # => REXML::Element + doc.root.xpath # => "/bookstore" + doc.root.texts.first # => "\n\n" + doc.root.texts.first.xpath # => "/bookstore/text()" + + If there is no ancestor, returns the expanded name of the element: + + Element.new('foo').xpath # => "foo" + +=== Document Children + +A document may have children of these types: + +- XML declaration. +- Root element. +- Text. +- Processing instructions. +- Comments. +- CDATA. + +[XML Declaration] + + A document may an XML declaration, which is stored as an REXML::XMLDecl object: + + doc.xml_decl # => + doc.xml_decl.class # => REXML::XMLDecl + + Document.new('').xml_decl # => + + my_xml = '"' + my_doc = Document.new(my_xml) + xml_decl = my_doc.xml_decl + xml_decl.to_s # => "" + + The version, encoding, and stand-alone values may be retrieved separately: + + my_doc.version # => "1.0" + my_doc.encoding # => "UTF-8" + my_doc.stand_alone? # => "yes" + +[Root Element] + + A document may have a single element child, called the _root_ _element_, + which is stored as an REXML::Element object; + it may be retrieved with method +root+: + + doc.root # => ... + doc.root.class # => REXML::Element + + Document.new('').root # => nil + +[Text] + + A document may have text passages, each of which is stored + as an REXML::Text object: + + doc.texts.each {|t| p [t.class, t] } + + Output: + + [REXML::Text, "\n"] + +[Processing Instructions] + + A document may have processing instructions, which are stored + as REXML::Instruction objects: + + + + Output: + + [REXML::Instruction, ] + [REXML::Instruction, ] + +[Comments] + + A document may have comments, which are stored + as REXML::Comment objects: + + my_xml = <<-EOT + + + EOT + my_doc = Document.new(my_xml) + my_doc.comments.each {|c| p [c.class, c] } + + Output: + + [REXML::Comment, # ... , @string="foo">] + [REXML::Comment, # ... , @string="bar">] + +[CDATA] + + A document may have CDATA entries, which are stored + as REXML::CData objects: + + my_xml = <<-EOT + + + EOT + my_doc = Document.new(my_xml) + my_doc.cdatas.each {|cd| p [cd.class, cd] } + + Output: + + [REXML::CData, "foo"] + [REXML::CData, "bar"] + +The payload of a document is a tree of nodes, descending from the root element: + + doc.root.children.each do |child| + p [child, child.class] + end + +Output: + + [REXML::Text, "\n\n"] + [REXML::Element, ... ] + [REXML::Text, "\n\n"] + [REXML::Element, ... ] + [REXML::Text, "\n\n"] + [REXML::Element, ... ] + [REXML::Text, "\n\n"] + [REXML::Element, ... ] + [REXML::Text, "\n\n"] + +== Exploring an Element + +An REXML::Element object represents an XML element. + +The object inherits from its ancestor classes: + +- REXML::Child (includes module REXML::Node) + - REXML::Parent (includes module {Enumerable}[rdoc-ref:Enumerable]). + - REXML::Element (includes module REXML::Namespace). + +This section covers methods: + +- Defined in REXML::Element itself. +- Inherited from REXML::Parent and REXML::Child. +- Included from REXML::Node. + +=== Inside the Element + +[Brief String Representation] + + Use method REXML::Element#inspect to retrieve a brief string representation. + + doc.root.inspect # => " ... " + + The ellipsis (...) indicates that the element has children. + When there are no children, the ellipsis is omitted: + + Element.new('foo').inspect # => "" + + If the element has attributes, those are also included: + + doc.root.elements.first.inspect # => " ... " + +[Extended String Representation] + + Use inherited method REXML::Child.bytes to retrieve an extended + string representation. + + doc.root.bytes # => "\n\n\n Everyday Italian\n Giada De Laurentiis\n 2005\n 30.00\n\n\n\n Harry Potter\n J K. Rowling\n 2005\n 29.99\n\n\n\n XQuery Kick Start\n James McGovern\n Per Bothner\n Kurt Cagle\n James Linn\n Vaidyanathan Nagarajan\n 2003\n 49.99\n\n\n\n Learning XML\n Erik T. Ray\n 2003\n 39.95\n\n\n" + +[Node Type] + + Use method REXML::Element#node_type to retrieve the node type (always +:element+): + + doc.root.node_type # => :element + +[Raw Mode] + + Use method REXML::Element#raw to retrieve whether (+true+ or +nil+) + raw mode is set. + + doc.root.raw # => nil + +[Context] + + Use method REXML::Element#context to retrieve the context hash + (see {Element Context}[../context_rdoc.html]): + + doc.root.context # => {} + +=== Relationships + +An element may have: + +- Ancestors. +- Siblings. +- Children. + +==== Ancestors + +[Containing Document] + + Use method REXML::Element#document to retrieve the containing document, if any: + + ele = doc.root.elements.first # => ... + ele.document # => ... + ele = Element.new('foo') # => + ele.document # => nil + +[Root Element] + + Use method REXML::Element#root to retrieve the root element: + + ele = doc.root.elements.first # => ... + ele.root # => ... + ele = Element.new('foo') # => + ele.root # => + +[Root Node] + + Use method REXML::Element#root_node to retrieve the most distant ancestor, + which is the containing document, if any, otherwise the root element: + + ele = doc.root.elements.first # => ... + ele.root_node # => ... + ele = Element.new('foo') # => + ele.root_node # => + +[Parent] + + Use inherited method REXML::Child#parent to retrieve the parent + + ele = doc.root # => ... + ele.parent # => ... + ele = doc.root.elements.first # => ... + ele.parent # => ... + + Use included method REXML::Node#index_in_parent to retrieve the index + of the element among all of its parents children (not just the element children). + Note that while the index for doc.root.elements[n] is 1-based, + the returned index is 0-based. + + doc.root.children # => + # ["\n\n", + # ... , + # "\n\n", + # ... , + # "\n\n", + # ... , + # "\n\n", + # ... , + # "\n\n"] + ele = doc.root.elements[1] # => ... + ele.index_in_parent # => 2 + ele = doc.root.elements[2] # => ... + ele.index_in_parent# => 4 + +==== Siblings + +[Next Element] + + Use method REXML::Element#next_element to retrieve the first following + sibling that is itself an element (+nil+ if there is none): + + ele = doc.root.elements[1] + while ele do + p [ele.class, ele] + ele = ele.next_element + end + p ele + + Output: + + [REXML::Element, ... ] + [REXML::Element, ... ] + [REXML::Element, ... ] + [REXML::Element, ... ] + +[Previous Element] + + Use method REXML::Element#previous_element to retrieve the first preceding + sibling that is itself an element (+nil+ if there is none): + + ele = doc.root.elements[4] + while ele do + p [ele.class, ele] + ele = ele.previous_element + end + p ele + + Output: + + [REXML::Element, ... ] + [REXML::Element, ... ] + [REXML::Element, ... ] + [REXML::Element, ... ] + +[Next Node] + + Use included method REXML::Node.next_sibling_node + (or its alias next_sibling) to retrieve the first following node + regardless of its class: + + node = doc.root.children[0] + while node do + p [node.class, node] + node = node.next_sibling + end + p node + + Output: + + [REXML::Text, "\n\n"] + [REXML::Element, ... ] + [REXML::Text, "\n\n"] + [REXML::Element, ... ] + [REXML::Text, "\n\n"] + [REXML::Element, ... ] + [REXML::Text, "\n\n"] + [REXML::Element, ... ] + [REXML::Text, "\n\n"] + +[Previous Node] + + Use included method REXML::Node.previous_sibling_node + (or its alias previous_sibling) to retrieve the first preceding node + regardless of its class: + + node = doc.root.children[-1] + while node do + p [node.class, node] + node = node.previous_sibling + end + p node + + Output: + + [REXML::Text, "\n\n"] + [REXML::Element, ... ] + [REXML::Text, "\n\n"] + [REXML::Element, ... ] + [REXML::Text, "\n\n"] + [REXML::Element, ... ] + [REXML::Text, "\n\n"] + [REXML::Element, ... ] + [REXML::Text, "\n\n"] + +==== Children + +[Child Count] + + Use inherited method REXML::Parent.size to retrieve the count + of nodes (of all types) in the element: + + doc.root.size # => 9 + +[Child Nodes] + + Use inherited method REXML::Parent.children to retrieve an array + of the child nodes (of all types): + + doc.root.children # => + # ["\n\n", + # ... , + # "\n\n", + # ... , + # "\n\n", + # ... , + # "\n\n", + # ... , + # "\n\n"] + +[Child at Index] + + Use method REXML::Element#[] to retrieve the child at a given numerical index, + or +nil+ if there is no such child: + + doc.root[0] # => "\n\n" + doc.root[1] # => ... + doc.root[7] # => ... + doc.root[8] # => "\n\n" + + doc.root[-1] # => "\n\n" + doc.root[-2] # => ... + + doc.root[50] # => nil + +[Index of Child] + + Use method REXML::Parent#index to retrieve the zero-based child index + of the given object, or #size - 1 if there is no such child: + + ele = doc.root # => ... + ele.index(ele[0]) # => 0 + ele.index(ele[1]) # => 1 + ele.index(ele[7]) # => 7 + ele.index(ele[8]) # => 8 + + ele.index(ele[-1]) # => 8 + ele.index(ele[-2]) # => 7 + + ele.index(ele[50]) # => 8 + +[Element Children] + + Use method REXML::Element#has_elements? to retrieve whether the element + has element children: + + doc.root.has_elements? # => true + REXML::Element.new('foo').has_elements? # => false + + Use method REXML::Element#elements to retrieve the REXML::Elements object + containing the element children: + + eles = doc.root.elements + eles # => # ... > + eles.size # => 4 + eles.each {|e| p [e.class], e } + + Output: + + [ ... , + ... , + ... , + ... + ] + +Note that while in this example, all the element children of the root element are +elements of the same name, 'book', that is not true of all documents; +a root element (or any other element) may have any mixture of child elements. + +[CDATA Children] + + Use method REXML::Element#cdatas to retrieve a frozen array of CDATA children: + + my_xml = <<-EOT + + + + + EOT + my_doc = REXML::Document.new(my_xml) + cdatas my_doc.root.cdatas + cdatas.frozen? # => true + cdatas.map {|cd| cd.class } # => [REXML::CData, REXML::CData] + +[Comment Children] + + Use method REXML::Element#comments to retrieve a frozen array of comment children: + + my_xml = <<-EOT + + + + + EOT + my_doc = REXML::Document.new(my_xml) + comments = my_doc.root.comments + comments.frozen? # => true + comments.map {|c| c.class } # => [REXML::Comment, REXML::Comment] + comments.map {|c| c.to_s } # => ["foo", "bar"] + +[Processing Instruction Children] + + Use method REXML::Element#instructions to retrieve a frozen array + of processing instruction children: + + my_xml = <<-EOT + + + + + EOT + my_doc = REXML::Document.new(my_xml) + instrs = my_doc.root.instructions + instrs.frozen? # => true + instrs.map {|i| i.class } # => [REXML::Instruction, REXML::Instruction] + instrs.map {|i| i.to_s } # => ["", ""] + +[Text Children] + + Use method REXML::Element#has_text? to retrieve whether the element + has text children: + + doc.root.has_text? # => true + REXML::Element.new('foo').has_text? # => false + + Use method REXML::Element#texts to retrieve a frozen array of text children: + + my_xml = 'textmore' + my_doc = REXML::Document.new(my_xml) + texts = my_doc.root.texts + texts.frozen? # => true + texts.map {|t| t.class } # => [REXML::Text, REXML::Text] + texts.map {|t| t.to_s } # => ["text", "more"] + +[Parenthood] + + Use inherited method REXML::Parent.parent? to retrieve whether the element is a parent; + always returns +true+; only REXML::Child#parent returns +false+. + + doc.root.parent? # => true + +=== Element Attributes + +Use method REXML::Element#has_attributes? to return whether the element +has attributes: + + ele = doc.root # => ... + ele.has_attributes? # => false + ele = ele.elements.first # => ... + ele.has_attributes? # => true + +Use method REXML::Element#attributes to return the hash +containing the attributes for the element. +Each hash key is a string attribute name; +each hash value is an REXML::Attribute object. + + ele = doc.root # => ... + attrs = ele.attributes # => {} + + ele = ele.elements.first # => ... + attrs = ele.attributes # => {"category"=>category='cooking'} + attrs.size # => 1 + attr_name = attrs.keys.first # => "category" + attr_name.class # => String + attr_value = attrs.values.first # => category='cooking' + attr_value.class # => REXML::Attribute + +Use method REXML::Element#[] to retrieve the string value for a given attribute, +which may be given as either a string or a symbol: + + ele = doc.root.elements.first # => ... + attr_value = ele['category'] # => "cooking" + attr_value.class # => String + ele['nosuch'] # => nil + +Use method REXML::Element#attribute to retrieve the value of a named attribute: + + my_xml = "" + my_doc = REXML::Document.new(my_xml) + my_doc.root.attribute("x") # => x='x' + my_doc.root.attribute("x", "a") # => a:x='a:x' + +== Whitespace + +Use method REXML::Element#ignore_whitespace_nodes to determine whether +whitespace nodes were ignored when the XML was parsed; +returns +true+ if so, +nil+ otherwise. + +Use method REXML::Element#whitespace to determine whether whitespace +is respected for the element; returns +true+ if so, +false+ otherwise. + +== Namespaces + +Use method REXML::Element#namespace to retrieve the string namespace URI +for the element, which may derive from one of its ancestors: + + xml_string = <<-EOT + + + + + + + EOT + d = Document.new(xml_string) + b = d.elements['//b'] + b.namespace # => "1" + b.namespace('y') # => "2" + b.namespace('nosuch') # => nil + +Use method REXML::Element#namespaces to retrieve a hash of all defined namespaces +in the element and its ancestors: + + xml_string = <<-EOT + + + + + + + EOT + d = Document.new(xml_string) + d.elements['//a'].namespaces # => {"x"=>"1", "y"=>"2"} + d.elements['//b'].namespaces # => {"x"=>"1", "y"=>"2"} + d.elements['//c'].namespaces # => {"x"=>"1", "y"=>"2", "z"=>"3"} + +Use method REXML::Element#prefixes to retrieve an array of the string prefixes (names) +of all defined namespaces in the element and its ancestors: + + xml_string = <<-EOT + + + + + + + EOT + d = Document.new(xml_string, {compress_whitespace: :all}) + d.elements['//a'].prefixes # => ["x", "y"] + d.elements['//b'].prefixes # => ["x", "y"] + d.elements['//c'].prefixes # => ["x", "y", "z"] + +== Traversing + +You can use certain methods to traverse children of the element. +Each child that meets given criteria is yielded to the given block. + +[Traverse All Children] + + Use inherited method REXML::Parent#each (or its alias #each_child) to traverse + all children of the element: + + doc.root.each {|child| p [child.class, child] } + + Output: + + [REXML::Text, "\n\n"] + [REXML::Element, ... ] + [REXML::Text, "\n\n"] + [REXML::Element, ... ] + [REXML::Text, "\n\n"] + [REXML::Element, ... ] + [REXML::Text, "\n\n"] + [REXML::Element, ... ] + [REXML::Text, "\n\n"] + +[Traverse Element Children] + + Use method REXML::Element#each_element to traverse only the element children + of the element: + + doc.root.each_element {|e| p [e.class, e] } + + Output: + + [REXML::Element, ... ] + [REXML::Element, ... ] + [REXML::Element, ... ] + [REXML::Element, ... ] + +[Traverse Element Children with Attribute] + + Use method REXML::Element#each_element_with_attribute with the single argument + +attr_name+ to traverse each element child that has the given attribute: + + my_doc = Document.new '' + my_doc.root.each_element_with_attribute('id') {|e| p [e.class, e] } + + Output: + + [REXML::Element, ] + [REXML::Element, ] + [REXML::Element, ] + + Use the same method with a second argument +value+ to traverse + each element child element that has the given attribute and value: + + my_doc.root.each_element_with_attribute('id', '1') {|e| p [e.class, e] } + + Output: + + [REXML::Element, ] + [REXML::Element, ] + + Use the same method with a third argument +max+ to traverse + no more than the given number of element children: + + my_doc.root.each_element_with_attribute('id', '1', 1) {|e| p [e.class, e] } + + Output: + + [REXML::Element, ] + + Use the same method with a fourth argument +xpath+ to traverse + only those element children that match the given xpath: + + my_doc.root.each_element_with_attribute('id', '1', 2, '//d') {|e| p [e.class, e] } + + Output: + + [REXML::Element, ] + +[Traverse Element Children with Text] + + Use method REXML::Element#each_element_with_text with no arguments + to traverse those element children that have text: + + my_doc = Document.new 'bbd' + my_doc.root.each_element_with_text {|e| p [e.class, e] } + + Output: + + [REXML::Element, ... ] + [REXML::Element, ... ] + [REXML::Element, ... ] + + Use the same method with the single argument +text+ to traverse + those element children that have exactly that text: + + my_doc.root.each_element_with_text('b') {|e| p [e.class, e] } + + Output: + + [REXML::Element, ... ] + [REXML::Element, ... ] + + Use the same method with additional second argument +max+ to traverse + no more than the given number of element children: + + my_doc.root.each_element_with_text('b', 1) {|e| p [e.class, e] } + + Output: + + [REXML::Element, ... ] + + Use the same method with additional third argument +xpath+ to traverse + only those element children that also match the given xpath: + + my_doc.root.each_element_with_text('b', 2, '//c') {|e| p [e.class, e] } + + Output: + + [REXML::Element, ... ] + +[Traverse Element Children's Indexes] + + Use inherited method REXML::Parent#each_index to traverse all children's indexes + (not just those of element children): + + doc.root.each_index {|i| print i } + + Output: + + 012345678 + +[Traverse Children Recursively] + + Use included method REXML::Node#each_recursive to traverse all children recursively: + + doc.root.each_recursive {|child| p [child.class, child] } + + Output: + + [REXML::Element, ... ] + [REXML::Element, ... </>] + [REXML::Element, <author> ... </>] + [REXML::Element, <year> ... </>] + [REXML::Element, <price> ... </>] + [REXML::Element, <book category='children'> ... </>] + [REXML::Element, <title lang='en'> ... </>] + [REXML::Element, <author> ... </>] + [REXML::Element, <year> ... </>] + [REXML::Element, <price> ... </>] + [REXML::Element, <book category='web'> ... </>] + [REXML::Element, <title lang='en'> ... </>] + [REXML::Element, <author> ... </>] + [REXML::Element, <author> ... </>] + [REXML::Element, <author> ... </>] + [REXML::Element, <author> ... </>] + [REXML::Element, <author> ... </>] + [REXML::Element, <year> ... </>] + [REXML::Element, <price> ... </>] + [REXML::Element, <book category='web' cover='paperback'> ... </>] + [REXML::Element, <title lang='en'> ... </>] + [REXML::Element, <author> ... </>] + [REXML::Element, <year> ... </>] + [REXML::Element, <price> ... </>] + +== Searching + +You can use certain methods to search among the descendants of an element. + +Use method REXML::Element#get_elements to retrieve all element children of the element +that match the given +xpath+: + + xml_string = <<-EOT + <root> + <a level='1'> + <a level='2'/> + </a> + </root> + EOT + d = Document.new(xml_string) + d.root.get_elements('//a') # => [<a level='1'> ... </>, <a level='2'/>] + +Use method REXML::Element#get_text with no argument to retrieve the first text node +in the first child: + + my_doc = Document.new "<p>some text <b>this is bold!</b> more text</p>" + text_node = my_doc.root.get_text + text_node.class # => REXML::Text + text_node.to_s # => "some text " + +Use the same method with argument +xpath+ to retrieve the first text node +in the first child that matches the xpath: + + my_doc.root.get_text(1) # => "this is bold!" + +Use method REXML::Element#text with no argument to retrieve the text +from the first text node in the first child: + + my_doc = Document.new "<p>some text <b>this is bold!</b> more text</p>" + text_node = my_doc.root.text + text_node.class # => String + text_node # => "some text " + +Use the same method with argument +xpath+ to retrieve the text from the first text node +in the first child that matches the xpath: + + my_doc.root.text(1) # => "this is bold!" + +Use included method REXML::Node#find_first_recursive +to retrieve the first descendant element +for which the given block returns a truthy value, or +nil+ if none: + + doc.root.find_first_recursive do |ele| + ele.name == 'price' + end # => <price> ... </> + doc.root.find_first_recursive do |ele| + ele.name == 'nosuch' + end # => nil + +== Editing + +=== Editing a Document + +[Creating a Document] + + Create a new document with method REXML::Document::new: + + doc = Document.new(source_string) + empty_doc = REXML::Document.new + +[Adding to the Document] + + Add an XML declaration with method REXML::Document#add + and an argument of type REXML::XMLDecl: + + my_doc = Document.new + my_doc.xml_decl.to_s # => "" + my_doc.add(XMLDecl.new('2.0')) + my_doc.xml_decl.to_s # => "<?xml version='2.0'?>" + + Add a document type with method REXML::Document#add + and an argument of type REXML::DocType: + + my_doc = Document.new + my_doc.doctype.to_s # => "" + my_doc.add(DocType.new('foo')) + my_doc.doctype.to_s # => "<!DOCTYPE foo>" + + Add a node of any other REXML type with method REXML::Document#add and an argument + that is not of type REXML::XMLDecl or REXML::DocType: + + my_doc = Document.new + my_doc.add(Element.new('foo')) + my_doc.to_s # => "<foo/>" + + Add an existing element as the root element with method REXML::Document#add_element: + + ele = Element.new('foo') + my_doc = Document.new + my_doc.add_element(ele) + my_doc.root # => <foo/> + + Create and add an element as the root element with method REXML::Document#add_element: + + my_doc = Document.new + my_doc.add_element('foo') + my_doc.root # => <foo/> + +=== Editing an Element + +==== Creating an Element + +Create a new element with method REXML::Element::new: + + ele = Element.new('foo') # => <foo/> + +==== Setting Element Properties + +Set the context for an element with method REXML::Element#context= +(see {Element Context}[../context_rdoc.html]): + + ele.context # => nil + ele.context = {ignore_whitespace_nodes: :all} + ele.context # => {:ignore_whitespace_nodes=>:all} + +Set the parent for an element with inherited method REXML::Child#parent= + + ele.parent # => nil + ele.parent = Element.new('bar') + ele.parent # => <bar/> + +Set the text for an element with method REXML::Element#text=: + + ele.text # => nil + ele.text = 'bar' + ele.text # => "bar" + +==== Adding to an Element + +Add a node as the last child with inherited method REXML::Parent#add (or its alias #push): + + ele = Element.new('foo') # => <foo/> + ele.push(Text.new('bar')) + ele.push(Element.new('baz')) + ele.children # => ["bar", <baz/>] + +Add a node as the first child with inherited method REXML::Parent#unshift: + + ele = Element.new('foo') # => <foo/> + ele.unshift(Element.new('bar')) + ele.unshift(Text.new('baz')) + ele.children # => ["bar", <baz/>] + +Add an element as the last child with method REXML::Element#add_element: + + ele = Element.new('foo') # => <foo/> + ele.add_element('bar') + ele.add_element(Element.new('baz')) + ele.children # => [<bar/>, <baz/>] + +Add a text node as the last child with method REXML::Element#add_text: + + ele = Element.new('foo') # => <foo/> + ele.add_text('bar') + ele.add_text(Text.new('baz')) + ele.children # => ["bar", "baz"] + +Insert a node before a given node with method REXML::Parent#insert_before: + + ele = Element.new('foo') # => <foo/> + ele.add_text('bar') + ele.add_text(Text.new('baz')) + ele.children # => ["bar", "baz"] + target = ele[1] # => "baz" + ele.insert_before(target, Text.new('bat')) + ele.children # => ["bar", "bat", "baz"] + +Insert a node after a given node with method REXML::Parent#insert_after: + + ele = Element.new('foo') # => <foo/> + ele.add_text('bar') + ele.add_text(Text.new('baz')) + ele.children # => ["bar", "baz"] + target = ele[0] # => "bar" + ele.insert_after(target, Text.new('bat')) + ele.children # => ["bar", "bat", "baz"] + +Add an attribute with method REXML::Element#add_attribute: + + ele = Element.new('foo') # => <foo/> + ele.add_attribute('bar', 'baz') + ele.add_attribute(Attribute.new('bat', 'bam')) + ele.attributes # => {"bar"=>bar='baz', "bat"=>bat='bam'} + +Add multiple attributes with method REXML::Element#add_attributes: + + ele = Element.new('foo') # => <foo/> + ele.add_attributes({'bar' => 'baz', 'bat' => 'bam'}) + ele.add_attributes([['ban', 'bap'], ['bah', 'bad']]) + ele.attributes # => {"bar"=>bar='baz', "bat"=>bat='bam', "ban"=>ban='bap', "bah"=>bah='bad'} + +Add a namespace with method REXML::Element#add_namespace: + + ele = Element.new('foo') # => <foo/> + ele.add_namespace('bar') + ele.add_namespace('baz', 'bat') + ele.namespaces # => {"xmlns"=>"bar", "baz"=>"bat"} + +==== Deleting from an Element + +Delete a specific child object with inherited method REXML::Parent#delete: + + ele = Element.new('foo') # => <foo/> + ele.add_element('bar') + ele.add_text('baz') + ele.children # => [<bar/>, "baz"] + target = ele[1] # => "baz" + ele.delete(target) # => "baz" + ele.children # => [<bar/>] + target = ele[0] # => <baz/> + ele.delete(target) # => <baz/> + ele.children # => [] + +Delete a child at a specific index with inherited method REXML::Parent#delete_at: + + ele = Element.new('foo') # => <foo/> + ele.add_element('bar') + ele.add_text('baz') + ele.children # => [<bar/>, "baz"] + ele.delete_at(1) + ele.children # => [<bar/>] + ele.delete_at(0) + ele.children # => [] + +Delete all children meeting a specified criterion with inherited method +REXML::Parent#delete_if: + + ele = Element.new('foo') # => <foo/> + ele.add_element('bar') + ele.add_text('baz') + ele.add_element('bat') + ele.add_text('bam') + ele.children # => [<bar/>, "baz", <bat/>, "bam"] + ele.delete_if {|child| child.instance_of?(Text) } + ele.children # => [<bar/>, <bat/>] + +Delete an element at a specific 1-based index with method REXML::Element#delete_element: + + ele = Element.new('foo') # => <foo/> + ele.add_element('bar') + ele.add_text('baz') + ele.add_element('bat') + ele.add_text('bam') + ele.children # => [<bar/>, "baz", <bat/>, "bam"] + ele.delete_element(2) # => <bat/> + ele.children # => [<bar/>, "baz", "bam"] + ele.delete_element(1) # => <bar/> + ele.children # => ["baz", "bam"] + +Delete a specific element with the same method: + + ele = Element.new('foo') # => <foo/> + ele.add_element('bar') + ele.add_text('baz') + ele.add_element('bat') + ele.add_text('bam') + ele.children # => [<bar/>, "baz", <bat/>, "bam"] + target = ele.elements[2] # => <bat/> + ele.delete_element(target) # => <bat/> + ele.children # => [<bar/>, "baz", "bam"] + +Delete an element matching an xpath using the same method: + + ele = Element.new('foo') # => <foo/> + ele.add_element('bar') + ele.add_text('baz') + ele.add_element('bat') + ele.add_text('bam') + ele.children # => [<bar/>, "baz", <bat/>, "bam"] + ele.delete_element('./bat') # => <bat/> + ele.children # => [<bar/>, "baz", "bam"] + ele.delete_element('./bar') # => <bar/> + ele.children # => ["baz", "bam"] + +Delete an attribute by name with method REXML::Element#delete_attribute: + + ele = Element.new('foo') # => <foo/> + ele.add_attributes({'bar' => 'baz', 'bam' => 'bat'}) + ele.attributes # => {"bar"=>bar='baz', "bam"=>bam='bat'} + ele.delete_attribute('bam') + ele.attributes # => {"bar"=>bar='baz'} + +Delete a namespace with method REXML::Element#delete_namespace: + + ele = Element.new('foo') # => <foo/> + ele.add_namespace('bar') + ele.add_namespace('baz', 'bat') + ele.namespaces # => {"xmlns"=>"bar", "baz"=>"bat"} + ele.delete_namespace('xmlns') + ele.namespaces # => {} # => {"baz"=>"bat"} + ele.delete_namespace('baz') + ele.namespaces # => {} # => {} + +Remove an element from its parent with inherited method REXML::Child#remove: + + ele = Element.new('foo') # => <foo/> + parent = Element.new('bar') # => <bar/> + parent.add_element(ele) # => <foo/> + parent.children.size # => 1 + ele.remove # => <foo/> + parent.children.size # => 0 + +==== Replacing Nodes + +Replace the node at a given 0-based index with inherited method REXML::Parent#[]=: + + ele = Element.new('foo') # => <foo/> + ele.add_element('bar') + ele.add_text('baz') + ele.add_element('bat') + ele.add_text('bam') + ele.children # => [<bar/>, "baz", <bat/>, "bam"] + ele[2] = Text.new('bad') # => "bad" + ele.children # => [<bar/>, "baz", "bad", "bam"] + +Replace a given node with another node with inherited method REXML::Parent#replace_child: + + ele = Element.new('foo') # => <foo/> + ele.add_element('bar') + ele.add_text('baz') + ele.add_element('bat') + ele.add_text('bam') + ele.children # => [<bar/>, "baz", <bat/>, "bam"] + target = ele[2] # => <bat/> + ele.replace_child(target, Text.new('bah')) + ele.children # => [<bar/>, "baz", "bah", "bam"] + +Replace +self+ with a given node with inherited method REXML::Child#replace_with: + + ele = Element.new('foo') # => <foo/> + ele.add_element('bar') + ele.add_text('baz') + ele.add_element('bat') + ele.add_text('bam') + ele.children # => [<bar/>, "baz", <bat/>, "bam"] + target = ele[2] # => <bat/> + target.replace_with(Text.new('bah')) + ele.children # => [<bar/>, "baz", "bah", "bam"] + +=== Cloning + +Create a shallow clone of an element with method REXML::Element#clone. +The clone contains the name and attributes, but not the parent or children: + + ele = Element.new('foo') + ele.add_attributes({'bar' => 0, 'baz' => 1}) + ele.clone # => <foo bar='0' baz='1'/> + +Create a shallow clone of a document with method REXML::Document#clone. +The XML declaration is copied; the document type and root element are not cloned: + + my_xml = '<?xml version="1.0" encoding="UTF-8"?><!DOCTYPE foo><root/>' + my_doc = Document.new(my_xml) + clone_doc = my_doc.clone + + my_doc.xml_decl # => <?xml ... ?> + clone_doc.xml_decl # => <?xml ... ?> + + my_doc.doctype.to_s # => "<?xml version='1.0' encoding='UTF-8'?>" + clone_doc.doctype.to_s # => "" + + my_doc.root # => <root/> + clone_doc.root # => nil + +Create a deep clone of an element with inherited method REXML::Parent#deep_clone. +All nodes and attributes are copied: + + doc.to_s.size # => 825 + clone = doc.deep_clone + clone.to_s.size # => 825 + +== Writing the Document + +Write a document to an \IO stream (defaults to <tt>$stdout</tt>) +with method REXML::Document#write: + + doc.write + +Output: + + <?xml version='1.0' encoding='UTF-8'?> + <bookstore> + + <book category='cooking'> + <title lang='en'>Everyday Italian + Giada De Laurentiis + 2005 + 30.00 + + + + Harry Potter + J K. Rowling + 2005 + 29.99 + + + + XQuery Kick Start + James McGovern + Per Bothner + Kurt Cagle + James Linn + Vaidyanathan Nagarajan + 2003 + 49.99 + + + + Learning XML + Erik T. Ray + 2003 + 39.95 + + + diff --git a/lib/rexml/attribute.rb b/lib/rexml/attribute.rb index 8933a013..11893a95 100644 --- a/lib/rexml/attribute.rb +++ b/lib/rexml/attribute.rb @@ -1,4 +1,4 @@ -# frozen_string_literal: false +# frozen_string_literal: true require_relative "namespace" require_relative 'text' @@ -13,9 +13,6 @@ class Attribute # The element to which this attribute belongs attr_reader :element - # The normalized value of this attribute. That is, the attribute with - # entities intact. - attr_writer :normalized PATTERN = /\s*(#{NAME_STR})\s*=\s*(["'])(.*?)\2/um NEEDS_A_SECOND_CHECK = /(<|&((#{Entity::NAME});|(#0*((?:\d+)|(?:x[a-fA-F0-9]+)));)?)/um @@ -122,10 +119,13 @@ def hash # b = Attribute.new( "ns:x", "y" ) # b.to_string # -> "ns:x='y'" def to_string + value = to_s if @element and @element.context and @element.context[:attribute_quote] == :quote - %Q^#@expanded_name="#{to_s().gsub(/"/, '"')}"^ + value = value.gsub('"', '"') if value.include?('"') + %Q^#@expanded_name="#{value}"^ else - "#@expanded_name='#{to_s().gsub(/'/, ''')}'" + value = value.gsub("'", ''') if value.include?("'") + "#@expanded_name='#{value}'" end end @@ -141,7 +141,6 @@ def to_s return @normalized if @normalized @normalized = Text::normalize( @unnormalized, doctype ) - @unnormalized = nil @normalized end @@ -150,10 +149,16 @@ def to_s def value return @unnormalized if @unnormalized @unnormalized = Text::unnormalize( @normalized, doctype ) - @normalized = nil @unnormalized end + # The normalized value of this attribute. That is, the attribute with + # entities intact. + def normalized=(new_normalized) + @normalized = new_normalized + @unnormalized = nil + end + # Returns a copy of this attribute def clone Attribute.new self @@ -190,7 +195,7 @@ def node_type end def inspect - rv = "" + rv = +"" write( rv ) rv end diff --git a/lib/rexml/document.rb b/lib/rexml/document.rb index 2edeb987..b1caa020 100644 --- a/lib/rexml/document.rb +++ b/lib/rexml/document.rb @@ -69,7 +69,7 @@ class Document < Element # d.to_s # => "FooBar" # # When argument +document+ is given, it must be an existing - # document object, whose context and attributes (but not chidren) + # document object, whose context and attributes (but not children) # are cloned into the new document: # # d = REXML::Document.new(xml_string) diff --git a/lib/rexml/element.rb b/lib/rexml/element.rb index 4c21dbd5..bf913a82 100644 --- a/lib/rexml/element.rb +++ b/lib/rexml/element.rb @@ -989,7 +989,7 @@ def previous_element # :call-seq: # has_text? -> true or false # - # Returns +true if the element has one or more text noded, + # Returns +true+ if the element has one or more text noded, # +false+ otherwise: # # d = REXML::Document.new 'text' @@ -1006,7 +1006,7 @@ def has_text? # text(xpath = nil) -> text_string or nil # # Returns the text string from the first text node child - # in a specified element, if it exists, # +nil+ otherwise. + # in a specified element, if it exists, +nil+ otherwise. # # With no argument, returns the text from the first text node in +self+: # @@ -1014,7 +1014,7 @@ def has_text? # d.root.text.class # => String # d.root.text # => "some text " # - # With argument +xpath+, returns text from the the first text node + # With argument +xpath+, returns text from the first text node # in the element that matches +xpath+: # # d.root.text(1) # => "this is bold!" diff --git a/lib/rexml/entity.rb b/lib/rexml/entity.rb index 89a9e84c..573db691 100644 --- a/lib/rexml/entity.rb +++ b/lib/rexml/entity.rb @@ -132,24 +132,34 @@ def to_s # then: # doctype.entity('yada').value #-> "nanoo bar nanoo" def value - if @value - matches = @value.scan(PEREFERENCE_RE) - rv = @value.clone - if @parent - sum = 0 - matches.each do |entity_reference| - entity_value = @parent.entity( entity_reference[0] ) - if sum + entity_value.bytesize > Security.entity_expansion_text_limit - raise "entity expansion has grown too large" - else - sum += entity_value.bytesize - end - rv.gsub!( /%#{entity_reference.join};/um, entity_value ) + @resolved_value ||= resolve_value + end + + def parent=(other) + @resolved_value = nil + super + end + + private + def resolve_value + return nil if @value.nil? + return @value unless @value.match?(PEREFERENCE_RE) + + matches = @value.scan(PEREFERENCE_RE) + rv = @value.clone + if @parent + sum = 0 + matches.each do |entity_reference| + entity_value = @parent.entity( entity_reference[0] ) + if sum + entity_value.bytesize > Security.entity_expansion_text_limit + raise "entity expansion has grown too large" + else + sum += entity_value.bytesize end + rv.gsub!( /%#{entity_reference.join};/um, entity_value ) end - return rv end - nil + rv end end diff --git a/lib/rexml/formatters/pretty.rb b/lib/rexml/formatters/pretty.rb index 562ef946..a1198b7a 100644 --- a/lib/rexml/formatters/pretty.rb +++ b/lib/rexml/formatters/pretty.rb @@ -1,4 +1,4 @@ -# frozen_string_literal: false +# frozen_string_literal: true require_relative 'default' module REXML @@ -58,7 +58,7 @@ def write_element(node, output) skip = false if compact if node.children.inject(true) {|s,c| s & c.kind_of?(Text)} - string = "" + string = +"" old_level = @level @level = 0 node.children.each { |child| write( child, string ) } diff --git a/lib/rexml/functions.rb b/lib/rexml/functions.rb index 77926bf2..4c114616 100644 --- a/lib/rexml/functions.rb +++ b/lib/rexml/functions.rb @@ -262,11 +262,10 @@ def Functions::string_length( string ) string(string).length end - # UNTESTED def Functions::normalize_space( string=nil ) string = string(@@context[:node]) if string.nil? if string.kind_of? Array - string.collect{|x| string.to_s.strip.gsub(/\s+/um, ' ') if string} + string.collect{|x| x.to_s.strip.gsub(/\s+/um, ' ') if x} else string.to_s.strip.gsub(/\s+/um, ' ') end diff --git a/lib/rexml/namespace.rb b/lib/rexml/namespace.rb index 924edf95..2e67252a 100644 --- a/lib/rexml/namespace.rb +++ b/lib/rexml/namespace.rb @@ -1,4 +1,4 @@ -# frozen_string_literal: false +# frozen_string_literal: true require_relative 'xmltokens' @@ -10,13 +10,17 @@ module Namespace # The expanded name of the object, valid if name is set attr_accessor :prefix include XMLTokens + NAME_WITHOUT_NAMESPACE = /\A#{NCNAME_STR}\z/ NAMESPLIT = /^(?:(#{NCNAME_STR}):)?(#{NCNAME_STR})/u # Sets the name and the expanded name def name=( name ) @expanded_name = name - case name - when NAMESPLIT + if name.match?(NAME_WITHOUT_NAMESPACE) + @prefix = "" + @namespace = "" + @name = name + elsif name =~ NAMESPLIT if $1 @prefix = $1 else @@ -24,7 +28,7 @@ def name=( name ) @namespace = "" end @name = $2 - when "" + elsif name == "" @prefix = nil @namespace = nil @name = nil diff --git a/lib/rexml/parseexception.rb b/lib/rexml/parseexception.rb index 7b16cd1a..e57d05fd 100644 --- a/lib/rexml/parseexception.rb +++ b/lib/rexml/parseexception.rb @@ -29,6 +29,7 @@ def to_s err << "\nLine: #{line}\n" err << "Position: #{position}\n" err << "Last 80 unconsumed characters:\n" + err.force_encoding("ASCII-8BIT") err << @source.buffer[0..80].force_encoding("ASCII-8BIT").gsub(/\n/, ' ') end diff --git a/lib/rexml/parsers/baseparser.rb b/lib/rexml/parsers/baseparser.rb index 305b1207..d09237c5 100644 --- a/lib/rexml/parsers/baseparser.rb +++ b/lib/rexml/parsers/baseparser.rb @@ -1,4 +1,4 @@ -# frozen_string_literal: false +# frozen_string_literal: true require_relative '../parseexception' require_relative '../undefinednamespaceexception' require_relative '../source' @@ -96,7 +96,7 @@ class BaseParser ENTITYDEF = "(?:#{ENTITYVALUE}|(?:#{EXTERNALID}(#{NDATADECL})?))" PEDECL = "" GEDECL = "" - ENTITYDECL = /\s*(?:#{GEDECL})|(?:#{PEDECL})/um + ENTITYDECL = /\s*(?:#{GEDECL})|\s*(?:#{PEDECL})/um NOTATIONDECL_START = /\A\s* [/'/, "'", "'", /'/] } + module Private + INSTRUCTION_END = /#{NAME}(\s+.*?)?\?>/um + TAG_PATTERN = /((?>#{QNAME_STR}))\s*/um + CLOSE_PATTERN = /(#{QNAME_STR})\s*>/um + ATTLISTDECL_END = /\s+#{NAME}(?:#{ATTDEF})*\s*>/um + NAME_PATTERN = /\s*#{NAME}/um + GEDECL_PATTERN = "\\s+#{NAME}\\s+#{ENTITYDEF}\\s*>" + PEDECL_PATTERN = "\\s+(%)\\s+#{NAME}\\s+#{PEDEF}\\s*>" + ENTITYDECL_PATTERN = /(?:#{GEDECL_PATTERN})|(?:#{PEDECL_PATTERN})/um + end + private_constant :Private + include Private + def initialize( source ) self.stream = source @listeners = [] @@ -196,181 +209,180 @@ def pull_event return @stack.shift if @stack.size > 0 #STDERR.puts @source.encoding #STDERR.puts "BUFFER = #{@source.buffer.inspect}" + + @source.ensure_buffer if @document_status == nil - word = @source.match( /\A((?:\s+)|(?:<[^>]*>))/um ) - word = word[1] unless word.nil? - #STDERR.puts "WORD = #{word.inspect}" - case word - when COMMENT_START - return [ :comment, @source.match( COMMENT_PATTERN, true )[1] ] - when XMLDECL_START - #STDERR.puts "XMLDECL" - results = @source.match( XMLDECL_PATTERN, true )[1] - version = VERSION.match( results ) - version = version[1] unless version.nil? - encoding = ENCODING.match(results) - encoding = encoding[1] unless encoding.nil? - if need_source_encoding_update?(encoding) - @source.encoding = encoding - end - if encoding.nil? and /\AUTF-16(?:BE|LE)\z/i =~ @source.encoding - encoding = "UTF-16" - end - standalone = STANDALONE.match(results) - standalone = standalone[1] unless standalone.nil? - return [ :xmldecl, version, encoding, standalone ] - when INSTRUCTION_START - return process_instruction - when DOCTYPE_START - base_error_message = "Malformed DOCTYPE" - @source.match(DOCTYPE_START, true) - @nsstack.unshift(curr_ns=Set.new) - name = parse_name(base_error_message) - if @source.match(/\A\s*\[/um, true) - id = [nil, nil, nil] - @document_status = :in_doctype - elsif @source.match(/\A\s*>/um, true) - id = [nil, nil, nil] - @document_status = :after_doctype - else - id = parse_id(base_error_message, - accept_external_id: true, - accept_public_id: false) - if id[0] == "SYSTEM" - # For backward compatibility - id[1], id[2] = id[2], nil + start_position = @source.position + if @source.match("/um, true)[1] ] + elsif @source.match("DOCTYPE", true) + base_error_message = "Malformed DOCTYPE" + unless @source.match(/\s+/um, true) + if @source.match(">") + message = "#{base_error_message}: name is missing" + else + message = "#{base_error_message}: invalid name" + end + @source.position = start_position + raise REXML::ParseException.new(message, @source) end - if @source.match(/\A\s*\[/um, true) + @nsstack.unshift(curr_ns=Set.new) + name = parse_name(base_error_message) + if @source.match(/\s*\[/um, true) + id = [nil, nil, nil] @document_status = :in_doctype - elsif @source.match(/\A\s*>/um, true) + elsif @source.match(/\s*>/um, true) + id = [nil, nil, nil] @document_status = :after_doctype + @source.ensure_buffer else - message = "#{base_error_message}: garbage after external ID" - raise REXML::ParseException.new(message, @source) + id = parse_id(base_error_message, + accept_external_id: true, + accept_public_id: false) + if id[0] == "SYSTEM" + # For backward compatibility + id[1], id[2] = id[2], nil + end + if @source.match(/\s*\[/um, true) + @document_status = :in_doctype + elsif @source.match(/\s*>/um, true) + @document_status = :after_doctype + @source.ensure_buffer + else + message = "#{base_error_message}: garbage after external ID" + raise REXML::ParseException.new(message, @source) + end end - end - args = [:start_doctype, name, *id] - if @document_status == :after_doctype - @source.match(/\A\s*/um, true) - @stack << [ :end_doctype ] - end - return args - when /\A\s+/ - else - @document_status = :after_doctype - if @source.encoding == "UTF-8" - @source.buffer.force_encoding(::Encoding::UTF_8) + args = [:start_doctype, name, *id] + if @document_status == :after_doctype + @source.match(/\s*/um, true) + @stack << [ :end_doctype ] + end + return args + else + message = "Invalid XML" + raise REXML::ParseException.new(message, @source) end end end if @document_status == :in_doctype - md = @source.match(/\A\s*(.*?>)/um) - case md[1] - when SYSTEMENTITY - match = @source.match( SYSTEMENTITY, true )[1] - return [ :externalentity, match ] - - when ELEMENTDECL_START - return [ :elementdecl, @source.match( ELEMENTDECL_PATTERN, true )[1] ] - - when ENTITY_START - match = @source.match( ENTITYDECL, true ).to_a.compact - match[0] = :entitydecl - ref = false - if match[1] == '%' - ref = true - match.delete_at 1 - end - # Now we have to sort out what kind of entity reference this is - if match[2] == 'SYSTEM' - # External reference - match[3] = match[3][1..-2] # PUBID - match.delete_at(4) if match.size > 4 # Chop out NDATA decl - # match is [ :entity, name, SYSTEM, pubid(, ndata)? ] - elsif match[2] == 'PUBLIC' - # External reference - match[3] = match[3][1..-2] # PUBID - match[4] = match[4][1..-2] # HREF - match.delete_at(5) if match.size > 5 # Chop out NDATA decl - # match is [ :entity, name, PUBLIC, pubid, href(, ndata)? ] - else - match[2] = match[2][1..-2] - match.pop if match.size == 4 - # match is [ :entity, name, value ] - end - match << '%' if ref - return match - when ATTLISTDECL_START - md = @source.match( ATTLISTDECL_PATTERN, true ) - raise REXML::ParseException.new( "Bad ATTLIST declaration!", @source ) if md.nil? - element = md[1] - contents = md[0] - - pairs = {} - values = md[0].scan( ATTDEF_RE ) - values.each do |attdef| - unless attdef[3] == "#IMPLIED" - attdef.compact! - val = attdef[3] - val = attdef[4] if val == "#FIXED " - pairs[attdef[0]] = val - if attdef[0] =~ /^xmlns:(.*)/ - @nsstack[0] << $1 - end + @source.match(/\s*/um, true) # skip spaces + start_position = @source.position + if @source.match("/um, true) + raise REXML::ParseException.new( "Bad ELEMENT declaration!", @source ) if md.nil? + return [ :elementdecl, "/um) - message = "#{base_error_message}: name is missing" + # Now we have to sort out what kind of entity reference this is + if match[2] == 'SYSTEM' + # External reference + match[3] = match[3][1..-2] # PUBID + match.delete_at(4) if match.size > 4 # Chop out NDATA decl + # match is [ :entity, name, SYSTEM, pubid(, ndata)? ] + elsif match[2] == 'PUBLIC' + # External reference + match[3] = match[3][1..-2] # PUBID + match[4] = match[4][1..-2] # HREF + match.delete_at(5) if match.size > 5 # Chop out NDATA decl + # match is [ :entity, name, PUBLIC, pubid, href(, ndata)? ] else - message = "#{base_error_message}: invalid declaration name" + match[2] = match[2][1..-2] + match.pop if match.size == 4 + # match is [ :entity, name, value ] end - raise REXML::ParseException.new(message, @source) - end - name = parse_name(base_error_message) - id = parse_id(base_error_message, - accept_external_id: true, - accept_public_id: true) - unless @source.match(/\A\s*>/um, true) - message = "#{base_error_message}: garbage before end >" - raise REXML::ParseException.new(message, @source) + match << '%' if ref + return match + elsif @source.match("ATTLIST", true) + md = @source.match(ATTLISTDECL_END, true) + raise REXML::ParseException.new( "Bad ATTLIST declaration!", @source ) if md.nil? + element = md[1] + contents = md[0] + + pairs = {} + values = md[0].scan( ATTDEF_RE ) + values.each do |attdef| + unless attdef[3] == "#IMPLIED" + attdef.compact! + val = attdef[3] + val = attdef[4] if val == "#FIXED " + pairs[attdef[0]] = val + if attdef[0] =~ /^xmlns:(.*)/ + @nsstack[0] << $1 + end + end + end + return [ :attlistdecl, element, pairs, contents ] + elsif @source.match("NOTATION", true) + base_error_message = "Malformed notation declaration" + unless @source.match(/\s+/um, true) + if @source.match(">") + message = "#{base_error_message}: name is missing" + else + message = "#{base_error_message}: invalid name" + end + @source.position = start_position + raise REXML::ParseException.new(message, @source) + end + name = parse_name(base_error_message) + id = parse_id(base_error_message, + accept_external_id: true, + accept_public_id: true) + unless @source.match(/\s*>/um, true) + message = "#{base_error_message}: garbage before end >" + raise REXML::ParseException.new(message, @source) + end + return [:notationdecl, name, *id] + elsif md = @source.match(/--(.*?)-->/um, true) + case md[1] + when /--/, /-\z/ + raise REXML::ParseException.new("Malformed comment", @source) + end + return [ :comment, md[1] ] if md end - return [:notationdecl, name, *id] - when DOCTYPE_END + elsif match = @source.match(/(%.*?;)\s*/um, true) + return [ :externalentity, match[1] ] + elsif @source.match(/\]\s*>/um, true) @document_status = :after_doctype - @source.match( DOCTYPE_END, true ) return [ :end_doctype ] end end if @document_status == :after_doctype - @source.match(/\A\s*/um, true) + @source.match(/\s*/um, true) end begin - @source.read if @source.buffer.size<2 - if @source.buffer[0] == ?< - if @source.buffer[1] == ?/ + start_position = @source.position + if @source.match("<", true) + if @source.match("/", true) @nsstack.shift last_tag = @tags.pop - md = @source.match( CLOSE_MATCH, true ) + md = @source.match(CLOSE_PATTERN, true) if md and !last_tag message = "Unexpected top-level end tag (got '#{md[1]}')" raise REXML::ParseException.new(message, @source) end if md.nil? or last_tag != md[1] message = "Missing end tag for '#{last_tag}'" - message << " (got '#{md[1]}')" if md + message += " (got '#{md[1]}')" if md + @source.position = start_position if md.nil? raise REXML::ParseException.new(message, @source) end return [ :end_element, last_tag ] - elsif @source.buffer[1] == ?! - md = @source.match(/\A(\s*[^>]*>)/um) + elsif @source.match("!", true) + md = @source.match(/([^>]*>)/um) #STDERR.puts "SOURCE BUFFER = #{source.buffer}, #{source.buffer.size}" raise REXML::ParseException.new("Malformed node", @source) unless md - if md[0][2] == ?- - md = @source.match( COMMENT_PATTERN, true ) + if md[0][0] == ?- + md = @source.match(/--(.*?)-->/um, true) case md[1] when /--/, /-\z/ @@ -379,19 +391,21 @@ def pull_event return [ :comment, md[1] ] if md else - md = @source.match( CDATA_PATTERN, true ) + md = @source.match(/\[CDATA\[(.*?)\]\]>/um, true) return [ :cdata, md[1] ] if md end raise REXML::ParseException.new( "Declarations can only occur "+ "in the doctype declaration.", @source) - elsif @source.buffer[1] == ?? - return process_instruction + elsif @source.match("?", true) + return process_instruction(start_position) else # Get the next tag - md = @source.match(TAG_MATCH, true) + md = @source.match(TAG_PATTERN, true) unless md + @source.position = start_position raise REXML::ParseException.new("malformed XML: missing tag start", @source) end + tag = md[1] @document_status = :in_element prefixes = Set.new prefixes << md[2] if md[2] @@ -405,23 +419,17 @@ def pull_event end if closed - @closed = md[1] + @closed = tag @nsstack.shift else - @tags.push( md[1] ) + @tags.push( tag ) end - return [ :start_element, md[1], attributes ] + return [ :start_element, tag, attributes ] end else - md = @source.match( TEXT_PATTERN, true ) - if md[0].length == 0 - @source.match( /(\s+)/, true ) - end - #STDERR.puts "GOT #{md[1].inspect}" unless md[0].length == 0 - #return [ :text, "" ] if md[0].length == 0 - # unnormalized = Text::unnormalize( md[1], self ) - # return PullEvent.new( :text, md[1], unnormalized ) - return [ :text, md[1] ] + md = @source.match(/([^<]*)/um, true) + text = md[1] + return [ :text, text ] end rescue REXML::UndefinedNamespaceException raise @@ -463,8 +471,7 @@ def normalize( input, entities=nil, entity_filter=nil ) # Unescapes all possible entities def unnormalize( string, entities=nil, filter=nil ) - rv = string.clone - rv.gsub!( /\r\n?/, "\n" ) + rv = string.gsub( /\r\n?/, "\n" ) matches = rv.scan( REFERENCE_RE ) return rv if matches.size == 0 rv.gsub!( /�*((?:\d+)|(?:x[a-fA-F0-9]+));/ ) { @@ -499,9 +506,9 @@ def need_source_encoding_update?(xml_declaration_encoding) end def parse_name(base_error_message) - md = @source.match(/\A\s*#{NAME}/um, true) + md = @source.match(NAME_PATTERN, true) unless md - if @source.match(/\A\s*\S/um) + if @source.match(/\s*\S/um) message = "#{base_error_message}: invalid name" else message = "#{base_error_message}: name is missing" @@ -577,97 +584,89 @@ def parse_id_invalid_details(accept_external_id:, end end - def process_instruction - match_data = @source.match(INSTRUCTION_PATTERN, true) + def process_instruction(start_position) + match_data = @source.match(INSTRUCTION_END, true) unless match_data message = "Invalid processing instruction node" + @source.position = start_position raise REXML::ParseException.new(message, @source) end + if @document_status.nil? and match_data[1] == "xml" + content = match_data[2] + version = VERSION.match(content) + version = version[1] unless version.nil? + encoding = ENCODING.match(content) + encoding = encoding[1] unless encoding.nil? + if need_source_encoding_update?(encoding) + @source.encoding = encoding + end + if encoding.nil? and /\AUTF-16(?:BE|LE)\z/i =~ @source.encoding + encoding = "UTF-16" + end + standalone = STANDALONE.match(content) + standalone = standalone[1] unless standalone.nil? + return [ :xmldecl, version, encoding, standalone ] + end [:processing_instruction, match_data[1], match_data[2]] end def parse_attributes(prefixes, curr_ns) attributes = {} closed = false - match_data = @source.match(/^(.*?)(\/)?>/um, true) - if match_data.nil? - message = "Start tag isn't ended" - raise REXML::ParseException.new(message, @source) - end - - raw_attributes = match_data[1] - closed = !match_data[2].nil? - return attributes, closed if raw_attributes.nil? - return attributes, closed if raw_attributes.empty? - - scanner = StringScanner.new(raw_attributes) - until scanner.eos? - if scanner.scan(/\s+/) - break if scanner.eos? - end - - pos = scanner.pos - loop do - break if scanner.scan(ATTRIBUTE_PATTERN) - unless scanner.scan(QNAME) - message = "Invalid attribute name: <#{scanner.rest}>" - raise REXML::ParseException.new(message, @source) - end - name = scanner[0] - unless scanner.scan(/\s*=\s*/um) + while true + if @source.match(">", true) + return attributes, closed + elsif @source.match("/>", true) + closed = true + return attributes, closed + elsif match = @source.match(QNAME, true) + name = match[1] + prefix = match[2] + local_part = match[3] + + unless @source.match(/\s*=\s*/um, true) message = "Missing attribute equal: <#{name}>" raise REXML::ParseException.new(message, @source) end - quote = scanner.scan(/['"]/) - unless quote + unless match = @source.match(/(['"])/, true) message = "Missing attribute value start quote: <#{name}>" raise REXML::ParseException.new(message, @source) end - unless scanner.scan(/.*#{Regexp.escape(quote)}/um) - match_data = @source.match(/^(.*?)(\/)?>/um, true) - if match_data - scanner << "/" if closed - scanner << ">" - scanner << match_data[1] - scanner.pos = pos - closed = !match_data[2].nil? - next - end - message = - "Missing attribute value end quote: <#{name}>: <#{quote}>" + quote = match[1] + value = @source.read_until(quote) + unless value.chomp!(quote) + message = "Missing attribute value end quote: <#{name}>: <#{quote}>" raise REXML::ParseException.new(message, @source) end - end - name = scanner[1] - prefix = scanner[2] - local_part = scanner[3] - # quote = scanner[4] - value = scanner[5] - if prefix == "xmlns" - if local_part == "xml" - if value != "http://www.w3.org/XML/1998/namespace" - msg = "The 'xml' prefix must not be bound to any other namespace "+ + @source.match(/\s*/um, true) + if prefix == "xmlns" + if local_part == "xml" + if value != "http://www.w3.org/XML/1998/namespace" + msg = "The 'xml' prefix must not be bound to any other namespace "+ + "(http://www.w3.org/TR/REC-xml-names/#ns-decl)" + raise REXML::ParseException.new( msg, @source, self ) + end + elsif local_part == "xmlns" + msg = "The 'xmlns' prefix must not be declared "+ "(http://www.w3.org/TR/REC-xml-names/#ns-decl)" - raise REXML::ParseException.new( msg, @source, self ) + raise REXML::ParseException.new( msg, @source, self) end - elsif local_part == "xmlns" - msg = "The 'xmlns' prefix must not be declared "+ - "(http://www.w3.org/TR/REC-xml-names/#ns-decl)" - raise REXML::ParseException.new( msg, @source, self) + curr_ns << local_part + elsif prefix + prefixes << prefix unless prefix == "xml" end - curr_ns << local_part - elsif prefix - prefixes << prefix unless prefix == "xml" - end - if attributes.has_key?(name) - msg = "Duplicate attribute #{name.inspect}" - raise REXML::ParseException.new(msg, @source, self) - end + if attributes[name] + msg = "Duplicate attribute #{name.inspect}" + raise REXML::ParseException.new(msg, @source, self) + end - attributes[name] = value + attributes[name] = value + else + message = "Invalid attribute name: <#{@source.buffer.split(%r{[/>\s]}).first}>" + raise REXML::ParseException.new(message, @source) + end end - return attributes, closed end end end diff --git a/lib/rexml/parsers/xpathparser.rb b/lib/rexml/parsers/xpathparser.rb index d92678fe..bd3b6856 100644 --- a/lib/rexml/parsers/xpathparser.rb +++ b/lib/rexml/parsers/xpathparser.rb @@ -1,4 +1,5 @@ # frozen_string_literal: false + require_relative '../namespace' require_relative '../xmltokens' @@ -38,108 +39,143 @@ def predicate path parsed end - def abbreviate( path ) - path = path.kind_of?(String) ? parse( path ) : path - string = "" - document = false - while path.size > 0 - op = path.shift + def abbreviate(path_or_parsed) + if path_or_parsed.kind_of?(String) + parsed = parse(path_or_parsed) + else + parsed = path_or_parsed + end + components = [] + component = nil + while parsed.size > 0 + op = parsed.shift case op when :node + component << "node()" when :attribute - string << "/" if string.size > 0 - string << "@" + component = "@" + components << component when :child - string << "/" if string.size > 0 + component = "" + components << component when :descendant_or_self - string << "/" + next_op = parsed[0] + if next_op == :node + parsed.shift + component = "" + components << component + else + component = "descendant-or-self::" + components << component + end when :self - string << "." + next_op = parsed[0] + if next_op == :node + parsed.shift + components << "." + else + component = "self::" + components << component + end when :parent - string << ".." + next_op = parsed[0] + if next_op == :node + parsed.shift + components << ".." + else + component = "parent::" + components << component + end when :any - string << "*" + component << "*" when :text - string << "text()" + component << "text()" when :following, :following_sibling, :ancestor, :ancestor_or_self, :descendant, :namespace, :preceding, :preceding_sibling - string << "/" unless string.size == 0 - string << op.to_s.tr("_", "-") - string << "::" + component = op.to_s.tr("_", "-") << "::" + components << component when :qname - prefix = path.shift - name = path.shift - string << prefix+":" if prefix.size > 0 - string << name + prefix = parsed.shift + name = parsed.shift + component << prefix+":" if prefix.size > 0 + component << name when :predicate - string << '[' - string << predicate_to_string( path.shift ) {|x| abbreviate( x ) } - string << ']' + component << '[' + component << predicate_to_path(parsed.shift) {|x| abbreviate(x)} + component << ']' when :document - document = true + components << "" when :function - string << path.shift - string << "( " - string << predicate_to_string( path.shift[0] ) {|x| abbreviate( x )} - string << " )" + component << parsed.shift + component << "( " + component << predicate_to_path(parsed.shift[0]) {|x| abbreviate(x)} + component << " )" when :literal - string << %Q{ "#{path.shift}" } + component << quote_literal(parsed.shift) else - string << "/" unless string.size == 0 - string << "UNKNOWN(" - string << op.inspect - string << ")" + component << "UNKNOWN(" + component << op.inspect + component << ")" end end - string = "/"+string if document - return string + case components + when [""] + "/" + when ["", ""] + "//" + else + components.join("/") + end end - def expand( path ) - path = path.kind_of?(String) ? parse( path ) : path - string = "" + def expand(path_or_parsed) + if path_or_parsed.kind_of?(String) + parsed = parse(path_or_parsed) + else + parsed = path_or_parsed + end + path = "" document = false - while path.size > 0 - op = path.shift + while parsed.size > 0 + op = parsed.shift case op when :node - string << "node()" + path << "node()" when :attribute, :child, :following, :following_sibling, :ancestor, :ancestor_or_self, :descendant, :descendant_or_self, :namespace, :preceding, :preceding_sibling, :self, :parent - string << "/" unless string.size == 0 - string << op.to_s.tr("_", "-") - string << "::" + path << "/" unless path.size == 0 + path << op.to_s.tr("_", "-") + path << "::" when :any - string << "*" + path << "*" when :qname - prefix = path.shift - name = path.shift - string << prefix+":" if prefix.size > 0 - string << name + prefix = parsed.shift + name = parsed.shift + path << prefix+":" if prefix.size > 0 + path << name when :predicate - string << '[' - string << predicate_to_string( path.shift ) { |x| expand(x) } - string << ']' + path << '[' + path << predicate_to_path( parsed.shift ) { |x| expand(x) } + path << ']' when :document document = true else - string << "/" unless string.size == 0 - string << "UNKNOWN(" - string << op.inspect - string << ")" + path << "UNKNOWN(" + path << op.inspect + path << ")" end end - string = "/"+string if document - return string + path = "/"+path if document + path end - def predicate_to_string( path, &block ) - string = "" - case path[0] + def predicate_to_path(parsed, &block) + path = "" + case parsed[0] when :and, :or, :mult, :plus, :minus, :neq, :eq, :lt, :gt, :lteq, :gteq, :div, :mod, :union - op = path.shift + op = parsed.shift case op when :eq op = "=" @@ -156,36 +192,50 @@ def predicate_to_string( path, &block ) when :union op = "|" end - left = predicate_to_string( path.shift, &block ) - right = predicate_to_string( path.shift, &block ) - string << " " - string << left - string << " " - string << op.to_s - string << " " - string << right - string << " " + left = predicate_to_path( parsed.shift, &block ) + right = predicate_to_path( parsed.shift, &block ) + path << left + path << " " + path << op.to_s + path << " " + path << right when :function - path.shift - name = path.shift - string << name - string << "( " - string << predicate_to_string( path.shift, &block ) - string << " )" + parsed.shift + name = parsed.shift + path << name + path << "(" + parsed.shift.each_with_index do |argument, i| + path << ", " if i > 0 + path << predicate_to_path(argument, &block) + end + path << ")" when :literal - path.shift - string << " " - string << path.shift.inspect - string << " " + parsed.shift + path << quote_literal(parsed.shift) else - string << " " - string << yield( path ) - string << " " + path << yield( parsed ) end - return string.squeeze(" ") + return path.squeeze(" ") end + # For backward compatibility + alias_method :preciate_to_string, :predicate_to_path private + def quote_literal( literal ) + case literal + when String + # XPath 1.0 does not support escape characters. + # Assumes literal does not contain both single and double quotes. + if literal.include?("'") + "\"#{literal}\"" + else + "'#{literal}'" + end + else + literal.inspect + end + end + #LocationPath # | RelativeLocationPath # | '/' RelativeLocationPath? diff --git a/lib/rexml/rexml.rb b/lib/rexml/rexml.rb index 8a01f0e1..191932b8 100644 --- a/lib/rexml/rexml.rb +++ b/lib/rexml/rexml.rb @@ -26,10 +26,12 @@ # - REXML::Document. # - REXML::Element. # +# There's also an {REXML tutorial}[doc/rexml/tutorial_rdoc.html]. +# module REXML COPYRIGHT = "Copyright © 2001-2008 Sean Russell " DATE = "2008/019" - VERSION = "3.2.5" + VERSION = "3.2.8" REVISION = "" Copyright = COPYRIGHT diff --git a/lib/rexml/source.rb b/lib/rexml/source.rb index 90b370b9..0f3c5011 100644 --- a/lib/rexml/source.rb +++ b/lib/rexml/source.rb @@ -30,8 +30,6 @@ def SourceFactory::create_from(arg) # objects and provides consumption of text class Source include Encoding - # The current buffer (what we're going to read next) - attr_reader :buffer # The line number of the last consumed text attr_reader :line attr_reader :encoding @@ -41,7 +39,8 @@ class Source # @param encoding if non-null, sets the encoding of the source to this # value, overriding all encoding detection def initialize(arg, encoding=nil) - @orig = @buffer = arg + @orig = arg + @scanner = StringScanner.new(@orig) if encoding self.encoding = encoding else @@ -50,6 +49,14 @@ def initialize(arg, encoding=nil) @line = 0 end + # The current buffer (what we're going to read next) + def buffer + @scanner.rest + end + + def buffer_encoding=(encoding) + @scanner.string.force_encoding(encoding) + end # Inherited from Encoding # Overridden to support optimized en/decoding @@ -58,98 +65,72 @@ def encoding=(enc) encoding_updated end - # Scans the source for a given pattern. Note, that this is not your - # usual scan() method. For one thing, the pattern argument has some - # requirements; for another, the source can be consumed. You can easily - # confuse this method. Originally, the patterns were easier - # to construct and this method more robust, because this method - # generated search regexps on the fly; however, this was - # computationally expensive and slowed down the entire REXML package - # considerably, since this is by far the most commonly called method. - # @param pattern must be a Regexp, and must be in the form of - # /^\s*(#{your pattern, with no groups})(.*)/. The first group - # will be returned; the second group is used if the consume flag is - # set. - # @param consume if true, the pattern returned will be consumed, leaving - # everything after it in the Source. - # @return the pattern, if found, or nil if the Source is empty or the - # pattern is not found. - def scan(pattern, cons=false) - return nil if @buffer.nil? - rv = @buffer.scan(pattern) - @buffer = $' if cons and rv.size>0 - rv + def read(term = nil) end - def read + def read_until(term) + @scanner.scan_until(Regexp.union(term)) or @scanner.rest end - def consume( pattern ) - @buffer = $' if pattern.match( @buffer ) + def ensure_buffer end - def match_to( char, pattern ) - return pattern.match(@buffer) + def match(pattern, cons=false) + if cons + @scanner.scan(pattern).nil? ? nil : @scanner + else + @scanner.check(pattern).nil? ? nil : @scanner + end end - def match_to_consume( char, pattern ) - md = pattern.match(@buffer) - @buffer = $' - return md + def position + @scanner.pos end - def match(pattern, cons=false) - md = pattern.match(@buffer) - @buffer = $' if cons and md - return md + def position=(pos) + @scanner.pos = pos end # @return true if the Source is exhausted def empty? - @buffer == "" - end - - def position - @orig.index( @buffer ) + @scanner.eos? end # @return the current line in the source def current_line lines = @orig.split - res = lines.grep @buffer[0..30] + res = lines.grep @scanner.rest[0..30] res = res[-1] if res.kind_of? Array lines.index( res ) if res end private + def detect_encoding - buffer_encoding = @buffer.encoding + scanner_encoding = @scanner.rest.encoding detected_encoding = "UTF-8" begin - @buffer.force_encoding("ASCII-8BIT") - if @buffer[0, 2] == "\xfe\xff" - @buffer[0, 2] = "" + @scanner.string.force_encoding("ASCII-8BIT") + if @scanner.scan(/\xfe\xff/n) detected_encoding = "UTF-16BE" - elsif @buffer[0, 2] == "\xff\xfe" - @buffer[0, 2] = "" + elsif @scanner.scan(/\xff\xfe/n) detected_encoding = "UTF-16LE" - elsif @buffer[0, 3] == "\xef\xbb\xbf" - @buffer[0, 3] = "" + elsif @scanner.scan(/\xef\xbb\xbf/n) detected_encoding = "UTF-8" end ensure - @buffer.force_encoding(buffer_encoding) + @scanner.string.force_encoding(scanner_encoding) end self.encoding = detected_encoding end def encoding_updated if @encoding != 'UTF-8' - @buffer = decode(@buffer) + @scanner.string = decode(@scanner.rest) @to_utf = true else @to_utf = false - @buffer.force_encoding ::Encoding::UTF_8 + @scanner.string.force_encoding(::Encoding::UTF_8) end end end @@ -172,7 +153,7 @@ def initialize(arg, block_size=500, encoding=nil) end if !@to_utf and - @buffer.respond_to?(:force_encoding) and + @orig.respond_to?(:force_encoding) and @source.respond_to?(:external_encoding) and @source.external_encoding != ::Encoding::UTF_8 @force_utf8 = true @@ -181,65 +162,57 @@ def initialize(arg, block_size=500, encoding=nil) end end - def scan(pattern, cons=false) - rv = super - # You'll notice that this next section is very similar to the same - # section in match(), but just a liiittle different. This is - # because it is a touch faster to do it this way with scan() - # than the way match() does it; enough faster to warrant duplicating - # some code - if rv.size == 0 - until @buffer =~ pattern or @source.nil? - begin - @buffer << readline - rescue Iconv::IllegalSequence - raise - rescue - @source = nil - end - end - rv = super + def read(term = nil) + begin + @scanner << readline(term) + true + rescue Exception, NameError + @source = nil + false end - rv.taint if RUBY_VERSION < '2.7' - rv end - def read + def read_until(term) + pattern = Regexp.union(term) begin - @buffer << readline - rescue Exception, NameError - @source = nil + until str = @scanner.scan_until(pattern) + @scanner << readline(term) + end + rescue EOFError + @scanner.rest + else + read if @scanner.eos? and !@source.eof? + str end end - def consume( pattern ) - match( pattern, true ) + def ensure_buffer + read if @scanner.eos? && @source end + # Note: When specifying a string for 'pattern', it must not include '>' except in the following formats: + # - ">" + # - "XXX>" (X is any string excluding '>') def match( pattern, cons=false ) - rv = pattern.match(@buffer) - @buffer = $' if cons and rv - while !rv and @source - begin - @buffer << readline - rv = pattern.match(@buffer) - @buffer = $' if cons and rv - rescue - @source = nil + while true + if cons + md = @scanner.scan(pattern) + else + md = @scanner.check(pattern) end + break if md + return nil if pattern.is_a?(String) + return nil if @source.nil? + return nil unless read end - rv.taint if RUBY_VERSION < '2.7' - rv + + md.nil? ? nil : @scanner end def empty? super and ( @source.nil? || @source.eof? ) end - def position - @er_source.pos rescue 0 - end - # @return the current line in the source def current_line begin @@ -263,8 +236,8 @@ def current_line end private - def readline - str = @source.readline(@line_break) + def readline(term = nil) + str = @source.readline(term || @line_break) if @pending_buffer if str.nil? str = @pending_buffer @@ -290,7 +263,7 @@ def encoding_updated @source.set_encoding(@encoding, @encoding) end @line_break = encode(">") - @pending_buffer, @buffer = @buffer, "" + @pending_buffer, @scanner.string = @scanner.rest, "" @pending_buffer.force_encoding(@encoding) super end diff --git a/lib/rexml/text.rb b/lib/rexml/text.rb index 050b09c9..b47bad3b 100644 --- a/lib/rexml/text.rb +++ b/lib/rexml/text.rb @@ -1,4 +1,4 @@ -# frozen_string_literal: false +# frozen_string_literal: true require_relative 'security' require_relative 'entity' require_relative 'doctype' @@ -131,7 +131,7 @@ def parent= parent def Text.check string, pattern, doctype # illegal anywhere - if string !~ VALID_XML_CHARS + if !string.match?(VALID_XML_CHARS) if String.method_defined? :encode string.chars.each do |c| case c.ord @@ -371,7 +371,7 @@ def Text::normalize( input, doctype=nil, entity_filter=nil ) copy = input.to_s # Doing it like this rather than in a loop improves the speed #copy = copy.gsub( EREFERENCE, '&' ) - copy = copy.gsub( "&", "&" ) + copy = copy.gsub( "&", "&" ) if copy.include?("&") if doctype # Replace all ampersands that aren't part of an entity doctype.entities.each_value do |entity| @@ -382,7 +382,9 @@ def Text::normalize( input, doctype=nil, entity_filter=nil ) else # Replace all ampersands that aren't part of an entity DocType::DEFAULT_ENTITIES.each_value do |entity| - copy = copy.gsub(entity.value, "&#{entity.name};" ) + if copy.include?(entity.value) + copy = copy.gsub(entity.value, "&#{entity.name};" ) + end end end copy diff --git a/lib/rexml/xpath_parser.rb b/lib/rexml/xpath_parser.rb index d8b88e7a..5eb1e5a9 100644 --- a/lib/rexml/xpath_parser.rb +++ b/lib/rexml/xpath_parser.rb @@ -590,6 +590,7 @@ def filter_nodeset(nodeset) def evaluate_predicate(expression, nodesets) enter(:predicate, expression, nodesets) if @debug + new_nodeset_count = 0 new_nodesets = nodesets.collect do |nodeset| new_nodeset = [] subcontext = { :size => nodeset.size } @@ -606,17 +607,20 @@ def evaluate_predicate(expression, nodesets) result = result[0] if result.kind_of? Array and result.length == 1 if result.kind_of? Numeric if result == node.position - new_nodeset << XPathNode.new(node, position: new_nodeset.size + 1) + new_nodeset_count += 1 + new_nodeset << XPathNode.new(node, position: new_nodeset_count) end elsif result.instance_of? Array if result.size > 0 and result.inject(false) {|k,s| s or k} if result.size > 0 - new_nodeset << XPathNode.new(node, position: new_nodeset.size + 1) + new_nodeset_count += 1 + new_nodeset << XPathNode.new(node, position: new_nodeset_count) end end else if result - new_nodeset << XPathNode.new(node, position: new_nodeset.size + 1) + new_nodeset_count += 1 + new_nodeset << XPathNode.new(node, position: new_nodeset_count) end end end diff --git a/rexml.gemspec b/rexml.gemspec index 620a8981..97eac657 100644 --- a/rexml.gemspec +++ b/rexml.gemspec @@ -52,10 +52,8 @@ Gem::Specification.new do |spec| spec.files = files spec.rdoc_options.concat(["--main", "README.md"]) spec.extra_rdoc_files = rdoc_files - spec.bindir = "exe" - spec.executables = spec.files.grep(%r{^exe/}) { |f| File.basename(f) } - spec.add_development_dependency "bundler" - spec.add_development_dependency "rake" - spec.add_development_dependency "test-unit" + spec.required_ruby_version = '>= 2.5.0' + + spec.add_runtime_dependency("strscan", ">= 3.0.9") end diff --git a/test/data/much_ado.xml b/test/data/much_ado.xml index f008fadb..0040088c 100644 --- a/test/data/much_ado.xml +++ b/test/data/much_ado.xml @@ -4735,7 +4735,7 @@ CLAUDIO, BENEDICK, HERO, BEATRICE, and Attendants But they shall find, awaked in such a kind, Both strength of limb and policy of mind, Ability in means and choice of friends, -To quit me of them throughly. +To quit me of them thoroughly. diff --git a/test/data/ofbiz-issues-full-177.xml b/test/data/ofbiz-issues-full-177.xml index bfff771d..e1f7bdfd 100644 --- a/test/data/ofbiz-issues-full-177.xml +++ b/test/data/ofbiz-issues-full-177.xml @@ -152,8 +152,8 @@ - - + + diff --git a/test/data/test/tests.xml b/test/data/test/tests.xml index cf03b42b..fd415679 100644 --- a/test/data/test/tests.xml +++ b/test/data/test/tests.xml @@ -299,7 +299,7 @@ - + web-app web-app web-app @@ -318,7 +318,7 @@ - + web-app web-app web-app diff --git a/test/data/tutorial.xml b/test/data/tutorial.xml index bf5783d0..9c4639b9 100644 --- a/test/data/tutorial.xml +++ b/test/data/tutorial.xml @@ -286,7 +286,7 @@ el1 << Text.new(" cruel world") strings.

I can't emphasize this enough, because people do have problems with - this. REXML can't possibly alway guess correctly how your text is + this. REXML can't possibly always guess correctly how your text is encoded, so it always assumes the text is UTF-8. It also does not warn you when you try to add text which isn't properly encoded, for the same reason. You must make sure that you are adding UTF-8 text. diff --git a/test/formatter/test_default.rb b/test/formatter/test_default.rb index 321d8180..aa403dbe 100644 --- a/test/formatter/test_default.rb +++ b/test/formatter/test_default.rb @@ -2,7 +2,7 @@ module REXMLTests class DefaultFormatterTest < Test::Unit::TestCase def format(node) formatter = REXML::Formatters::Default.new - output = "" + output = +"" formatter.write(node, output) output end diff --git a/test/functions/test_base.rb b/test/functions/test_base.rb index 74dc1a31..daa38156 100644 --- a/test/functions/test_base.rb +++ b/test/functions/test_base.rb @@ -229,8 +229,30 @@ def test_normalize_space assert_equal( [REXML::Comment.new("COMMENT A")], m ) end + def test_normalize_space_strings + source = <<-XML +breakfast boosts\t\t + +concentration +Coffee beans + aroma + + + + Dessert + \t\t after dinner + XML + normalized_texts = REXML::XPath.each(REXML::Document.new(source), "normalize-space(//text())").to_a + assert_equal([ + "breakfast boosts concentration", + "Coffee beans aroma", + "Dessert after dinner", + ], + normalized_texts) + end + def test_string_nil_without_context - doc = REXML::Document.new(<<-XML) + doc = REXML::Document.new(<<~XML) diff --git a/test/parse/test_document_type_declaration.rb b/test/parse/test_document_type_declaration.rb index 55713909..8faa0b78 100644 --- a/test/parse/test_document_type_declaration.rb +++ b/test/parse/test_document_type_declaration.rb @@ -36,6 +36,21 @@ def test_garbage_plus_before_name_at_line_start + r SYSTEM "urn:x-rexml:test" [ ]> DETAIL end + + def test_no_name + exception = assert_raise(REXML::ParseException) do + parse(<<-DOCTYPE) + + DOCTYPE + end + assert_equal(<<-DETAIL.chomp, exception.to_s) +Malformed DOCTYPE: name is missing +Line: 3 +Position: 17 +Last 80 unconsumed characters: + + DETAIL + end end class TestExternalID < self diff --git a/test/parse/test_element.rb b/test/parse/test_element.rb index 9f172a28..14d0703a 100644 --- a/test/parse/test_element.rb +++ b/test/parse/test_element.rb @@ -41,9 +41,22 @@ def test_empty_namespace_attribute_name assert_equal(<<-DETAIL.chomp, exception.to_s) Invalid attribute name: <:a=""> Line: 1 -Position: 9 +Position: 13 Last 80 unconsumed characters: +:a=""> + DETAIL + end + def test_empty_namespace_attribute_name_with_utf8_character + exception = assert_raise(REXML::ParseException) do + parse("") # U+200B ZERO WIDTH SPACE + end + assert_equal(<<-DETAIL.chomp.force_encoding("ASCII-8BIT"), exception.to_s) +Invalid attribute name: <:\xE2\x80\x8B> +Line: 1 +Position: 8 +Last 80 unconsumed characters: +:\xE2\x80\x8B> DETAIL end diff --git a/test/parse/test_entity_declaration.rb b/test/parse/test_entity_declaration.rb new file mode 100644 index 00000000..e15deec6 --- /dev/null +++ b/test/parse/test_entity_declaration.rb @@ -0,0 +1,36 @@ +# frozen_string_literal: false +require 'test/unit' +require 'rexml/document' + +module REXMLTests + class TestParseEntityDeclaration < Test::Unit::TestCase + private + def xml(internal_subset) + <<-XML + + + XML + end + + def parse(internal_subset) + REXML::Document.new(xml(internal_subset)).doctype + end + + def test_empty + exception = assert_raise(REXML::ParseException) do + parse(<<-INTERNAL_SUBSET) + + INTERNAL_SUBSET + end + assert_equal(<<-DETAIL.chomp, exception.to_s) +Malformed notation declaration: name is missing +Line: 5 +Position: 72 +Last 80 unconsumed characters: + ]> + DETAIL + end + end +end diff --git a/test/parse/test_notation_declaration.rb b/test/parse/test_notation_declaration.rb index 19a0536d..9e81b6a4 100644 --- a/test/parse/test_notation_declaration.rb +++ b/test/parse/test_notation_declaration.rb @@ -35,7 +35,7 @@ def test_no_name Line: 5 Position: 72 Last 80 unconsumed characters: - ]> + ]> DETAIL end diff --git a/test/parser/test_xpath.rb b/test/parser/test_xpath.rb new file mode 100644 index 00000000..9143d25c --- /dev/null +++ b/test/parser/test_xpath.rb @@ -0,0 +1,115 @@ +# frozen_string_literal: false + +require "test/unit" +require "rexml/parsers/xpathparser" + +module REXMLTests + class TestXPathParser < Test::Unit::TestCase + sub_test_case("#abbreviate") do + def abbreviate(xpath) + parser = REXML::Parsers::XPathParser.new + parser.abbreviate(xpath) + end + + def test_document + assert_equal("/", + abbreviate("/")) + end + + def test_descendant_or_self_only + assert_equal("//", + abbreviate("/descendant-or-self::node()/")) + end + + def test_descendant_or_self_absolute + assert_equal("//a/b", + abbreviate("/descendant-or-self::node()/a/b")) + end + + def test_descendant_or_self_relative + assert_equal("a//b", + abbreviate("a/descendant-or-self::node()/b")) + end + + def test_descendant_or_self_not_node + assert_equal("/descendant-or-self::text()", + abbreviate("/descendant-or-self::text()")) + end + + def test_self_absolute + assert_equal("/a/./b", + abbreviate("/a/self::node()/b")) + end + + def test_self_relative + assert_equal("a/./b", + abbreviate("a/self::node()/b")) + end + + def test_self_not_node + assert_equal("/self::text()", + abbreviate("/self::text()")) + end + + def test_parent_absolute + assert_equal("/a/../b", + abbreviate("/a/parent::node()/b")) + end + + def test_parent_relative + assert_equal("a/../b", + abbreviate("a/parent::node()/b")) + end + + def test_parent_not_node + assert_equal("/a/parent::text()", + abbreviate("/a/parent::text()")) + end + + def test_any_absolute + assert_equal("/*/a", + abbreviate("/*/a")) + end + + def test_any_relative + assert_equal("a/*/b", + abbreviate("a/*/b")) + end + + def test_following_sibling_absolute + assert_equal("/following-sibling::a/b", + abbreviate("/following-sibling::a/b")) + end + + def test_following_sibling_relative + assert_equal("a/following-sibling::b/c", + abbreviate("a/following-sibling::b/c")) + end + + def test_predicate_index + assert_equal("a[5]/b", + abbreviate("a[5]/b")) + end + + def test_attribute_relative + assert_equal("a/@b", + abbreviate("a/attribute::b")) + end + + def test_filter_attribute + assert_equal("a/b[@i = 1]/c", + abbreviate("a/b[attribute::i=1]/c")) + end + + def test_filter_string_single_quote + assert_equal("a/b[@name = \"single ' quote\"]/c", + abbreviate("a/b[attribute::name=\"single ' quote\"]/c")) + end + + def test_filter_string_double_quote + assert_equal("a/b[@name = 'double \" quote']/c", + abbreviate("a/b[attribute::name='double \" quote']/c")) + end + end + end +end diff --git a/test/test_attributes.rb b/test/test_attributes.rb index 91fc68a5..09fde442 100644 --- a/test/test_attributes.rb +++ b/test/test_attributes.rb @@ -178,18 +178,27 @@ def test_amp_and_lf_attributes attr_test('name','value with LF & ampersand') end - def test_quoting + def test_quote_root d = Document.new(%q{}) assert_equal( %q{}, d.to_s ) d.root.context[:attribute_quote] = :quote assert_equal( %q{}, d.to_s ) + end + def test_quote_sub_element d = Document.new(%q{}) assert_equal( %q{}, d.to_s ) d.root.context[:attribute_quote] = :quote assert_equal( %q{}, d.to_s ) end + def test_quote_to_s_value + doc = Document.new(%q{}, {attribute_quote: :quote}) + assert_equal(%q{}, doc.to_s) + assert_equal("'", doc.root.attribute("a").value) + assert_equal(%q{}, doc.to_s) + end + def test_ticket_127 doc = Document.new doc.add_element 'a', { 'v' => 'x & y' } diff --git a/test/test_contrib.rb b/test/test_contrib.rb index f3ad0b6c..23ee35b1 100644 --- a/test/test_contrib.rb +++ b/test/test_contrib.rb @@ -80,7 +80,7 @@ def test_bad_doctype_Tobias # Peter Verhage def test_namespace_Peter - source = <<-EOF + source = <<~EOF @@ -377,7 +377,7 @@ def test_various_xpath end def test_entities_Holden_Glova - document = <<-EOL + document = <<~EOL diff --git a/test/test_core.rb b/test/test_core.rb index fd3af8c2..44e2e7ea 100644 --- a/test/test_core.rb +++ b/test/test_core.rb @@ -15,7 +15,7 @@ class Tester < Test::Unit::TestCase include Helper::Fixture include REXML def setup - @xsa_source = <<-EOL + @xsa_source = <<~EOL