RubyGems - rexleparser - Versions diffs - 0.4.19 → 0.5.0 - Mend

rexleparser 0.4.19 → 0.5.0

Files changed (6) hide show

checksums.yaml CHANGED Viewed

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 9cef0695d2e3117b683c543e54f66740d174f9e9
-  data.tar.gz: 5faa7ee7f21ec164bfa8e49f88ca9fad4ad7c415
+  metadata.gz: 4fd9dcc1abbf7f2b61bd3d2f86d4e304d14b7356
+  data.tar.gz: ded2e477c2d4f6a634d33fe89a598946366ee9ee
 SHA512:
-  metadata.gz: 06f2ad8866f62ddac3dc4c2db0b4d19b89a607f170645460d34ca3bab4e2cc206555fab7843f6b8a92a0d8239e156e4d12e4bdb2cc2e9fc9b6fb4ca93539397a
-  data.tar.gz: 2b5772c4220d2b8cb0a6cc52a10ded34a6726b25cf316429021232ff5fa863d43d478458622d2f3b42878f507cffb49a3d09c984e5d39c9bb3c8780d5a2b5ee0
+  metadata.gz: 5bf24ad6b143d2e89cf8b25b2352b89df9246ed97c59cb48e14b0231348a7750619e9fe3cfc0894220c4f1a980237be3aa5635f704ff84bafb368df102fead72
+  data.tar.gz: 70209b2013bafa24af4667d76647e413caed13b8c66b0fdd8d27ea71d032328ad850e44ac027493bc26029d9602d5a3fdfc2d0082ed3215cdba5e54459281eb5

checksums.yaml.gz.sig CHANGED Viewed

Binary file

data/lib/rexleparser.rb CHANGED Viewed

@@ -5,154 +5,109 @@
 class RexleParser
-  attr_reader :instructions, :doctype
+  attr_reader :instructions, :doctype, :to_a
   def initialize(raw_s)
     super()
     s = raw_s.clone
     @instructions = s.scan(/<\?([\w-]+) ([^>]+)\?>/)
     @doctype = s.slice!(/<!DOCTYPE html>\n?/)
-    @a = scan_element(s.strip.gsub(/<\?[^>]+>/,'').split(//))
-  end
-  def to_a()  @a end
-  def to_s()
-    name, value, attributes, *remaining = @a
-   [value.strip, scan_a(remaining)].flatten.join(' ')
+    s2 = s.gsub('<![CDATA[','<!cdata>').gsub(']]>','</!cdata>')
+    @to_a = reverse(parse(s2.strip.gsub(/<\?[^>]+>/,'').reverse))
   end
   private
-  def scan_a(a)
-    a.inject([]) do |r, x|
-      name, value, attributes, *remaining = x
-      text_remaining = scan_a remaining if remaining
-      r << value.strip << text_remaining if value
-    end
-  end
-  def scan_element(a)
-    a.shift until a[0] == '<' and a[1] != '/' or a.length < 1
-    return unless a.length > 1
-    a.shift
+  def scan_next(r, tagname)
-    # CDATA ?
-    if a[0..1].join == '![' then
+    j = tagname
-      name = '!['
-      8.times{ a.shift }
-      value = ''
-      value << a.shift until a[0..2].join == ']]>' or a.length <= 1
-      a.slice!(0,3)
-      return [name, value, {}]
-    elsif a[0..2].join == '!--' then
-      name = '!-'
-      #<![CDATA[
-      #<!--
-      3.times{ a.shift }
-      value = ''
-      value << a.shift until a[0..2].join == '-->' or a.length <= 1
-      a.slice!(0,3)
-      return [name, value, {}]
-    else
+    if (r =~ /^>/) == 0 then
+      # end tag match
+      tag = r[/^>[^<]+</]
-      name = ''
-      name << a.shift
-      name << a.shift while a[0] != ' ' and a[0] != '>' and a[0] != '/'
+      if tag[/^>.*[^\/]<$/] then
-      return unless name
+        # is it the end tag to match the start tag?
+        tag = r.slice!(/^>[^<]+</)
+        end_tag = tag[/^>[^>]*#{j}<$/]
-      # find the closing tag
-      i = a.index('>')
-      raw_values = ''
+        if end_tag then
+          j = nil
+          return   [:end_tag, end_tag]
+        elsif tag[/^>[^>]*\w+<$/] then
+          # broken tag found
+          broken_tag = tag
+          return [:child, [nil, [], broken_tag]] if broken_tag
+        else
-      # is it a self closing tag?
-      if a[i-1] == '/' then
+          text, tag =  tag.sub('>',';tg&').split(/>/,2)
+          r.prepend '>' + tag
+          return [:child, text]
+        end
-        raw_values << a.shift until (a[0] + a[1..-1].join.strip[0]) == '/>'
-        a.shift(2)
+      else
-        after_text = []
-        after_text << a.shift until a[0] == '<' or a.length <= 1
-        #a.shift until a[0] == '<' or a.length < 1
-        raw_values.strip!
+        # it's a start tag?
+        return [:newnode] if tag[/^>.*[\w!]+\/<$/]
-        attributes = raw_values.length > 0 ? get_attributes(raw_values) : {}
-        element = [name, nil, attributes]
+      end # end of tag match
-        return element if after_text.empty?
-        return [element, after_text.join]
+    else
-      else
+      # it's a text value
+      text = r.slice!(/[^>]+/)
+      return [:child, text] if text
+    end
+  end
-        raw_values << a.shift until a[0] == '<'
+  def parse(r, j=nil)
-        if raw_values[1..-1].length > 0 then
-          value, attributes = get_value_and_attribs(raw_values)
-        end
+    tag = r.slice!(/^>[^<]+</) if (r =~ /^>[^<]+</) == 0
-        element = [name, value, attributes || {}]
-        tag = a[0, name.length + 3].join
-        return unless a.length > 0
-        children = tag == ("</%s>" % name) ? false : true
-        if children == true then
+    if tag[0,3] == '>--' then
-          xa = scan_elements(a, element) until (a[0, name.length + 3].join \
-                                         == "</%s>" % [name]) or a.length < 2
+      i = r =~ /<--/
+      tag += r.slice!(0,i+5)
+      # it's a comment tag
+      tagname = '-!'
+      return [">#{tagname}<", [tag[/>--(.*)--!</,1]], ">#{tagname}/<"]
+    end
+    tagname = tag[/([\w!]+)\/?<$/,1]
-          xa.shift until xa[0] == '>' or xa.length <= 1
-          xa.shift
-          after_text = []
-          after_text << xa.shift until xa[0] == '<' or xa.length <= 1
-          return after_text.length >= 1 ? [element, after_text.join] : element
+    # self closing tag?
+    if tag[/^>\/.*#{tagname}<$/] then
+      return [">/#{tagname}<", [], "#{tag.sub(/>\//,'>')}"]
+    end
-        else
+    start_tag, children, end_tag = tag, [], nil
-          #check for its end tag
-          a.slice!(0, name.length + 3) if a[0, name.length + 3].join \
-                                                  == "</%s>" % name
-          after_text = []
-          after_text << a.shift until a[0] == '<' or a.length <= 1
+    until end_tag do
-          return after_text.length >= 1 ? [element, after_text.join] : element
+      key, res = scan_next r, tagname
-        end
+      case key
+      when :end_tag
+        end_tag = res
+        return [start_tag, children, end_tag]
+      when :child
+        children << res
+      when :newnode
+        children << parse(r, tagname)
       end
     end
-  end
-  def scan_elements(a, element)
-    r = scan_element(a)
-    if r and r[0].is_a?(Array) then
-      element = r.inject(element) {|r,x|  r << x} if r
-    elsif r
-      element << r
-    end
-    return a
-  end
-  def get_value_and_attribs(raw_values)
-    match_found = raw_values.match(/([^>]*)>(.*)/m)
-    if match_found then
-      raw_attributes, value = match_found.captures
-      attributes = get_attributes(raw_attributes)
-    end
-    [value.gsub('>','&gt;').gsub('<','&lt;'), attributes]
+    [start_tag,  children, end_tag]
   end
   def get_attributes(raw_attributes)
@@ -169,4 +124,27 @@ class RexleParser
     return r
   end
+  def reverse(raw_obj)
+    obj = raw_obj.clone
+    return obj.reverse! if obj.is_a? String
+    tag = obj.pop.reverse.sub('!cdata','!-')
+    children = obj[-1]
+    if children.last.is_a?(String) then
+      ltext ||= ''
+      ltext << children.pop.reverse
+    end
+    ltext << children.pop.reverse if children.last.is_a?(String)
+    r = children.reverse.map do |x|
+      reverse(x)
+    end
+    return [tag[/[!\-\w\[]+/], ltext, get_attributes(tag), *r]
+  end
 end

data.tar.gz.sig CHANGED Viewed

Binary file

metadata CHANGED Viewed

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: rexleparser
 version: !ruby/object:Gem::Version
-  version: 0.4.19
+  version: 0.5.0
 platform: ruby
 authors:
 - James Robertson
@@ -31,7 +31,7 @@ cert_chain:
   CkjTMLaPwIQI6dsbG4bVJ7/XzL7c8niqJSF7M0yr1+2kUrWFUZMBMrUUxgZxSkjL
   Cgd76bp2zjiyCw==
   -----END CERTIFICATE-----
-date: 2014-11-20 00:00:00.000000000 Z
+date: 2015-01-25 00:00:00.000000000 Z
 dependencies: []
 description:
 email: james@r0bertson.co.uk

metadata.gz.sig CHANGED Viewed

Binary file