RubyGems - rexleparser - Versions diffs - 0.9.9 → 1.0.0 - Mend

rexleparser 0.9.9 → 1.0.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.

Files changed (6) hide show

checksums.yaml CHANGED Viewed

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 3059b4fd1544e6c16167934dbc60e77c82c0bf57674e0d99e71c39b96909efb1
-  data.tar.gz: 6f3377d006cd852abe4b88881a320207579d138fbadf5e8aa830a3d4ca24d598
+  metadata.gz: a6291ec758a59d1737240656c502a96250c5fe6cdd230a452c220ba34c17f091
+  data.tar.gz: c9edbdc47b4e728598407ddd23da8d5622ed699069061742497d3017477e25bc
 SHA512:
-  metadata.gz: f2ddf0f05e84df521185a1606aa98b6a745902e2d35235d2ff6948e430ced3cfa2772aa1944191b00c8a045b16c58be884ce0a2f5dcdc7ec2e4e7cc078c5caa6
-  data.tar.gz: 8ef7aae9fc024a71d8ab79254f6ca7abb6d301ebd02696e15ea5138ab68074b2f57ebd8166a4f4421c61d24db2f94101654d753bf4af800ef593ae44c99d06ff
+  metadata.gz: 2665fb624f0b3fee4e4304c304c093900685e6708bfc62209fa54a0f0108e7e195844285fa7a677a91d83f0ee72c306ca8f785052cd7d6c51dba3ab1ea3950b9
+  data.tar.gz: 8c7d22a214d798f867d670c300d2b61c2235a17c437823ac7f5978dcb3c80015d3887dfc2f7f22b421d58d6b3b321eaa327ac931cb0448c06c1d1f71f70640ae

checksums.yaml.gz.sig CHANGED Viewed

Binary file

data/lib/rexleparser.rb CHANGED Viewed

@@ -7,20 +7,20 @@
 class Attributes < Hash
   class Value < String
     def initialize(value)
       #jr2020-04-30 super(value.gsub("'", '&apos;'))
       super(value)
     end
     def <(val2)
       self.to_f < val2.to_f
-    end
+    end
     def >(val2)
       self.to_f > val2.to_f
     end
     def inspect()
       super().gsub('&lt;','<',).gsub('&gt;','>').gsub('&pos;',"'")
     end
@@ -28,207 +28,256 @@ class Attributes < Hash
     def to_s(unescape: true)
       unescape ? self.gsub('&amp;','&').gsub('&pos;',"'") : self
     end
-  end
+  end
   def initialize(h={})
     super().merge! h
   end
   def []=(k,v)
     super(k, k != :class ? Value.new(v) : v)
   end
+  def delete(key=nil)
+    if key then
+      super(key)
+    else
+      keys.each {|key| super(key)}
+    end
+  end
   def merge(h)
-    h2 = h.inject({}) do |r, kv|
+    h2 = h.inject({}) do |r, kv|
       k, raw_v = kv
       v = raw_v.is_a?(String) ? Value.new(raw_v) : raw_v
-      r.merge(k => v)
+      r.merge(k => v)
     end
     super(h2)
   end
 end
 class RexleParserException < Exception
 end
 class RexleParser
-  attr_reader :instructions, :doctype, :to_a
-  def initialize(raw_s)
+  attr_reader :stack
-    super()
-    s = raw_s.clone.strip
-    return if s.empty?
+  def initialize(raws, debug: false)
+    s = raws.strip
+    @debug = debug
+    @a = []
+    @stack = []
     raw_xml, raw_instrctns = if s.lines.first =~ /<?xml/ then
-      s.split(/(?=\?>\s*<\w)/,2).reverse
+      s.split(/(?<=\?>)/,2).reverse
     else
       s
     end
+    puts 'raw_xml: ' + raw_xml.inspect if @debug
     @instructions = raw_instrctns ? \
                               raw_instrctns.scan(/<\?([\w-]+) ([^\?]+)/) : []
     @doctype = s.slice!(/<!DOCTYPE html>\n?/) if s.lines.first =~ /<\!DOCTYPE/
-    @to_a = reverse(parse_node(raw_xml.strip.reverse))
+    # scancom is run twice because we 1st check for comment tags and then cdata tags
+    @a = parse(scancom(scancom(raw_xml), type: :cdata)).flatten(1)
   end
-  private
-  def scan_next(r, tagname)
-    j = tagname
-    if r[0] == '>' then
-      # end tag match
-      tag = r[/^>[^<]+</]
-      if tag[1][/[ \w"']/] and  tag[-2] != '/'  then
-        # is it the end tag to match the start tag?
-        tag = r.slice!(/^>[^<]+</)
-        end_tag = tag[/^>[^>]*#{j}<$/]
-        if end_tag then
-          j = nil
-          return   [:end_tag, end_tag]
-        elsif tag[/^>[^>]*\w+<$/] then
-          # broken tag found
-          broken_tag = tag
-          return [:child, [nil, [], broken_tag]] if broken_tag
-        else
-          text, newtag =  tag.sub('>',';tg&').split(/>/,2)
-          if newtag then
-            tag = newtag
-            r.prepend '>' + tag
-          end
-          return [:child, text]
-        end
-      elsif r[0,3] == '>--' then   # comment tag found
+  def to_a()
+    @a
+  end
-        r.slice!(0,3)
-        i = r =~ /(\-\-!<)/
-        s = r.slice!(0,i)
-        r.slice!(0,4)
+  private
+  def ehead(raws)
+    s = raws.lstrip
+    puts '_s: ' + s.inspect if @debug
+    # fetch the element head
+    tag = s =~ /<[^>]+\/?>/
+    s2 = s[tag+1..-1]
+    tagb = s2 =~ />/
+    return unless tag
+    len = tagb+1-tag
+    if @debug then
+      puts 'ehead()/detail: ' + [tag, tagb, len, s[tag,len+1]].inspect
+    end
-        tagname, content = ['-!',s]
+    [s[tag,len+1], s[len+1..-1]]
-        return [:child, [">#{tagname}<", [content], ">#{tagname}/<"]]
+  end
-      elsif r[0,3] == '>]]' then   # CDATA tag found
+  def get_attributes(raw_attributes)
+    r1 = /([\w\-:\(\)]+\='[^']*)'/
+    r2 = /([\w\-:\(\)]+\="[^"]*)"/
+    r =  raw_attributes.scan(/#{r1}|#{r2}/).map(&:compact)\
+                                  .flatten.inject(Attributes.new) do |r, x|
+      attr_name, raw_val = x.split(/=/,2)
+      val = attr_name != 'class' ? raw_val[1..-1] : raw_val[1..-1].split
+      r.merge(attr_name.to_sym => val)
+    end
-        r.slice!(0,3)
-        i = r =~ /(\[ATADC\[!<)/
-        s = r.slice!(0,i)
-        r.slice!(0,9)
+    return r
+  end
-        tagname, content = ['[!',s]
+  def parse(raws, a=[], cur=nil)
-        return [:child, [">#{tagname}<", [content], ">#{tagname}/<"]]
+    s = raws #.lstrip
+    if @debug then
+      puts '.parse() s: ' + s.inspect[0..600]
+      puts '.parse() a: ' + a.inspect[0..699]
+      puts '.parse() cur: ' + cur.inspect[0..799]
+    end
-      elsif tag[/>\/|\/<$/] or tag[/^>.*[\w!]+\/<$/] then
+    # if self-closing tag
+    if s =~ /^<[^<]+\/>/ then
-        return [:newnode]
+      tag = s[/^<[^<]+\/>/]
+      puts 'parse() self-closing/tag: ' + tag.inspect  if @debug
+      tail = $'
+      if @debug then
+        puts 'parse() self-closing tag found'
+        puts 'parse()/tail: ' + tail.inspect
+      end
+      a2 = parsetag(tag)
+      puts '_a: ' + a.inspect if @debug
+      cur ? a.last << a2 : a << a2
+      parse(tail, a, cur)
+    # is it the head?
+    elsif (s =~ /^<[^\/>]+>/) == 0 then
+      puts 'parse()/head found' if @debug
+      tag, tail = ehead(s)
+      if @debug then
+        puts 'parse() tag: ' + tag.inspect
+        puts 'parse() tail: ' + tail.inspect
+      end
+      # add it to the list
+      a2 = parsetag(tag)
+      puts '_cur: ' + cur.inspect  if @debug
+      if cur then
+        cur << a2
+        cur2 = cur.last
       else
+        a << a2
+        cur2 = a.last
+      end
-        r.sub!('>',';tg&')
-        i = r =~ />(?:[\-\/"'\w]|\]\])/ # collect until a tag is found or a CDATA element
-        text = r.slice!(0,i)
-        return [:child, text] if text
-      end # end of tag match
-    else
-      # it's a text value
-      i = r =~ />(?:[\-\/"'\w]|\]\])/ # collect until a tag is found or a CDATA element
-      text = r.slice!(0,i)
-      return [:child, text] if text
-    end
-  end
+      puts '_a: ' + a.inspect  if @debug
-  def parse_node(r, j=nil)
+      # add it to the stack
+      @stack.push cur2
-    return unless r.length > 0
-    tag = r.slice!(/^>[^<]+</) if (r =~ /^>[^<]+</) == 0
-    tagname = tag[/([\w!:]+)\/?<$/,1]
+      parse(tail, a, cur2)
+    elsif (s =~ /^[^<]/) == 0
-    # self closing tag?
-    if tag[/^>\/.*#{tagname}<$/m] then
-      return [">/#{tagname}<", [], "#{tag.sub(/>\//,'>')}"]
-    end
+      puts 'parse() we have text!'  if @debug
+      text = raws[/[^<]+/m] #
+      remaining = $'
+      if @debug then
+        puts 'parse() text: ' + text.inspect
+        puts 'cur tag: ' + cur[0].inspect
+      end
+      cur << if cur[0][0] == '!' then
+        text.gsub('&lt;','<').gsub('&gt;','>').gsub('&amp;','&')
+      else
+        text.gsub(/>/,'&gt;').gsub(/</, '&lt;')
+      end
-    start_tag, children, end_tag = tag, [], nil
+      puts 'remaining: ' + remaining.inspect  if @debug
+      parse(remaining, a, cur) if remaining.length > 0
+    # is it a closing tag?
+    elsif s =~ /^\s?<\/\w+>/m
+      tail = s[/^\s*<\/\w+>(.*)/m,1]
+      if @debug then
+        puts 'parse()/closing tag ' + s[/^\s*<\/\w+>/].inspect
+        puts '>a: ' + a.inspect
+      end
+      @stack.pop
+      #a << []
+      parse(tail, a, @stack.last)
+    elsif s.empty? and @stack.length > 0
+      puts 'parse() no end tag!'  if @debug
-    unless start_tag[1..-3][/\w+$/] then
-      raise RexleParserException, 'invalid closing tag found ' + \
-                start_tag.reverse + '; context: ' + r[0..120].reverse.inspect
     end
-    until end_tag do
-      key, res = scan_next r, tagname
-      case key
-      when :end_tag
-        end_tag = res
-        r2 = [start_tag, children, end_tag]
-        end_tag = nil
-        return r2
-      when :child
-        children << res
-      when :newnode
-        children << parse_node(r, tagname)
-      else
-        break
-      end
-    end
+    return a
-    [start_tag,  children, end_tag]
   end
-  def get_attributes(raw_attributes)
-    r1 = /([\w\-:\(\)]+\='[^']*)'/
-    r2 = /([\w\-:\(\)]+\="[^"]*)"/
-    r =  raw_attributes.scan(/#{r1}|#{r2}/).map(&:compact)\
-                                  .flatten.inject(Attributes.new) do |r, x|
-      attr_name, raw_val = x.split(/=/,2)
-      val = attr_name != 'class' ? raw_val[1..-1] : raw_val[1..-1].split
-      r.merge(attr_name.to_sym => val)
+  # we parse the tag because it contains more than just the name it often contains attributes
+  #
+  def parsetag(s)
+    puts 'parsetag:' + s.inspect  if @debug
+    rawtagname, rawattr = s[1..-2].sub(/\/$/,'').match(/^(\w+) *(.*)/)\
+      .values_at(1,2)
+    tagname = case rawtagname.to_sym
+    when :_comment
+      '!-'
+    when :_cdata
+      '!['
+    else
+      rawtagname
     end
-    return r
+    [tagname, get_attributes(rawattr)]
   end
-  def reverse(raw_obj)
+  def scancom(s, type=:comment)
-    return unless raw_obj
-    obj = raw_obj.clone
-    return obj.reverse! if obj.is_a? String
+    tag1 = ['<!--', '-->', 'comment', '<!--']
+    tag2 = ['<![CDATA[', '\]\]>', 'cdata', '\<!\[CDATA\[']
+    tag = type == :comment ? tag1 : tag2
-    tag = obj.pop.reverse
+    #puts 'tag: ' + tag.inspect
+    istart = s =~ /#{tag[3]}/
+    return s unless istart
-    children = obj[-1]
+    iend = s =~ /#{tag[1]}/
+    comment ="<_%s>%s</_%s>" % [tag[2], s[istart+tag[0].length.. iend-1].gsub('&','&amp;').gsub('<','&lt;').gsub('>','&gt;'), tag[2]]
-    r = children.reverse.map {|x| reverse(x)}
+    if @debug then
+      puts 'comment: ' + comment.inspect
+      # construct the new string
+      puts 'istart: ' + istart.inspect
+    end
+    s3 = s[0,istart].to_s + comment + s[iend+3..-1]
+    scancom(s3, type)
-    return [tag[/[!\-\w:\[]+/], 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: 0.9.9
+  version: 1.0.0
 platform: ruby
 authors:
 - James Robertson
@@ -10,32 +10,33 @@ bindir: bin
 cert_chain:
 - |
   -----BEGIN CERTIFICATE-----
-  MIIEXjCCAsagAwIBAgIBATANBgkqhkiG9w0BAQsFADAsMSowKAYDVQQDDCFnZW1t
-  YXN0ZXIvREM9amFtZXNyb2JlcnRzb24vREM9ZXUwHhcNMjEwNDAxMTI1NDA1WhcN
-  MjIwNDAxMTI1NDA1WjAsMSowKAYDVQQDDCFnZW1tYXN0ZXIvREM9amFtZXNyb2Jl
-  cnRzb24vREM9ZXUwggGiMA0GCSqGSIb3DQEBAQUAA4IBjwAwggGKAoIBgQC9tf0T
-  BYEECADFGYQisEHfQBwZtTbhsjWGAsDG1CCEg+Zje9gQIwCPVPUYtEiZkmPtb2en
-  YQ0gdCvrSdaxyeP+O7UnN2sR/Rb0G/4Nx3gzY5e+k1PeZ+YEHhehzF/CjpxCpief
-  Mhi2HgToCQ71U1iyUT3Squb3CBA6vwLJI6MMh71GWU01aqrMT/l9W3vN54SAZ5i7
-  Ud9nVF4JsMXwHyzikv5MH6WwIOzMhqKMUxaAeeGAlFN3u2G2DGW+7fd9/z5zpD6S
-  XJEvqjllf5fetAk77Lvw7hPfK0gHJHwTva7k87K704pYgKvi8bAwcnhk/aHXgyON
-  D42nLpNYipRRVTXiNXxo9svPTSDGsee5e0prmpC/U9bD2T4SxCrM7VvfVWXbhhEX
-  47iZDeo2KllKmocjA02vfqtbaQXEATi3fSz/pdRpCr1g/Rd/JdAjRnxHgUu1q1TU
-  JU99/sfjaxBGvbL+C20cfMgdXdPrkGPNsiEDqfxK5IIBfaob8cp6jzKNDosCAwEA
-  AaOBijCBhzAJBgNVHRMEAjAAMAsGA1UdDwQEAwIEsDAdBgNVHQ4EFgQUgG4OM1TJ
-  YfZh1FAIhnVN+TXDs64wJgYDVR0RBB8wHYEbZ2VtbWFzdGVyQGphbWVzcm9iZXJ0
-  c29uLmV1MCYGA1UdEgQfMB2BG2dlbW1hc3RlckBqYW1lc3JvYmVydHNvbi5ldTAN
-  BgkqhkiG9w0BAQsFAAOCAYEACka8bLaU+wG55T9M2lqOrmXMsKpHQ5xtmSQk29OJ
-  4FUZ4aJEhTYxzJosvMNpauZVyrk+KyF/8uuGz5CfG/aPbOboB9+EIsmIcvRZ696M
-  BUXc6OuHE8SL0C9yuB9PloIZy2nxrRENFSV5xxyMS04bcaQjKCqtKw69+QT6lbra
-  iAU2EIebKyy0UIbrJSBIDKfig9KMEUrXvFUR4hu0lWpeT1bwq4sYeIeZNcg3v/y3
-  EbV3QK7AumvKgYvaz7iTu+9FKWT7AqIOH9wuPNPeXDLgyuKhLjdMaugz0wy6RYhT
-  Q8tgppTgSzQP8XwMg3xsaM+gWHbRLy8tO+3dkWTPN1m0xETWlSWFCiyi6oq8G4wC
-  t4pClPXscWrfmQa/u189WCF/O5BbsElrKQqx0vjq73l2apKjN9xViJi4LrEsZTuz
-  cF/nszU+U7PJ1WnQ+W7QTqoViru4N0S9bwi3YV5F5NPPeVnnrtmC2yruRfgTCI4b
-  3nEas0DJDZbQSkPP1mVcybEA
+  MIIEljCCAv6gAwIBAgIBATANBgkqhkiG9w0BAQsFADBIMRIwEAYDVQQDDAlnZW1t
+  YXN0ZXIxHjAcBgoJkiaJk/IsZAEZFg5qYW1lc3JvYmVydHNvbjESMBAGCgmSJomT
+  8ixkARkWAmV1MB4XDTIzMDMwNzEyNDM0MVoXDTI0MDMwNjEyNDM0MVowSDESMBAG
+  A1UEAwwJZ2VtbWFzdGVyMR4wHAYKCZImiZPyLGQBGRYOamFtZXNyb2JlcnRzb24x
+  EjAQBgoJkiaJk/IsZAEZFgJldTCCAaIwDQYJKoZIhvcNAQEBBQADggGPADCCAYoC
+  ggGBAMXdVvebuQa1+janwRx6yjABUKs2WSd6ns81LBol0KgH8Lmjj5CdIJHK/IFZ
+  pcjvbJCSNJS9eREO4RnHkJTUpYE6xgTboCsSMdTpJU3MK2Y+PHXQu5YJHBQQBWSe
+  LORpuKuhQuhU+oQgxnuszksIO1UBU+Xh0D5dntbWpiFBGPzTctoBTtJqBdClZwXc
+  s1mAmXhAkeK2hmT0Rw/IY2CqZAMeMbrVZBaqazYvqXvfDisRPMMZVZMz9al3w6IE
+  L9E4tDbU1sExjUgVGB+BIV6SIG5kYrOzpDKnZXhvPbmUR08iZeTe0IpUIFMIYPIy
+  kPJxO45OaxLwnabV+jC38P2CV4Pbx6dij/M/mWisD/az4kzmw1kGUMGJiPIn/XRX
+  mLOOxuCQxHDts+7tvD+/wTtSIxklsvVKz49QH1ybNrOdoYQuB8qNnLPFzKFr+5SC
+  ojuaJ45mf/Uv3Orps8LXj8WmOBvbJWC1/Lglhy+hhGV/7gh1EKVMpx6AwKcJ1+85
+  R19PMQIDAQABo4GKMIGHMAkGA1UdEwQCMAAwCwYDVR0PBAQDAgSwMB0GA1UdDgQW
+  BBQiPSrne0dHxLynj/1izBmEwv/lkTAmBgNVHREEHzAdgRtnZW1tYXN0ZXJAamFt
+  ZXNyb2JlcnRzb24uZXUwJgYDVR0SBB8wHYEbZ2VtbWFzdGVyQGphbWVzcm9iZXJ0
+  c29uLmV1MA0GCSqGSIb3DQEBCwUAA4IBgQBWIQG28MQXuVSHsAw/rQuaE1FpOmz0
+  AXWhHK1oDWxkoPTBIoLil2M2PI3htcBBRLUzyli9XFvqjzuO+J8LpWqs2iddxjXP
+  3xtUg0h+0urVRk00xwsnPLppwT7VxvycQifN31En8rMEzd24V5FKkn90brdokVQC
+  5aL/9LD3S5k3t4AyUcGeOFuU+k87lEz8bzKk2wjOjzpgxjNyqeK6h0iFeA94rhnp
+  HPaebr7ytgAR3dKU/Zr/gmZdQroli86LaOqGK1AJQ9E1RFBKwKluNa27dR3VyqBA
+  VG1Z/9QNxm0ivqKr7samwkNUGiql+s4CPZndbJD/hmDDdmCtYf1mywCAUOh+DrfU
+  iKwWhO5Qmo/RUOvr0a4KtP5i0N7qY1LFMSCpfCRTS9zTlfTIjs1ipAnWhLcqp5Js
+  NMSYHad41dFYLrVyE7mdZdIVlFqIdG+V1x7iY+zPpg7FS/8EUnK5zUxMC0YoLeK2
+  hcHycb1NL9Ujb7onXEop5Dobym6xO6V+yBY=
   -----END CERTIFICATE-----
-date: 2022-01-15 00:00:00.000000000 Z
+date: 2023-03-07 00:00:00.000000000 Z
 dependencies: []
 description:
 email: digital.robertson@gmail.com
@@ -63,8 +64,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubyforge_project:
-rubygems_version: 2.7.10
+rubygems_version: 3.4.6
 signing_key:
 specification_version: 4
 summary: Rexleparser is an XML parser used by the Rexle gem

metadata.gz.sig CHANGED Viewed

@@ -1,3 +1,3 @@
-��0�J��g%r��3���ֺ�<�
-�6�I���db
-�6إ�wth
+,����<�a��1�����$n�]��ᆧAWεp����J���z{�0aM��p�٥tP�u���,k���l�ygܖ|8��P�t"}����ej
++֢��PJ{ݍ��}ׄ��vj�	�a�m,�G��]��ӡ�	���h&r����C*�r��3I=�i��O�ɂ�7�]~��?����CH��Z��j���*�9���ե�ӱM��R+��a����n�3ͣJ��Lm�,��mU&���2>@G���a�OQ�0�b�&��%�.��
+|d�!lDO#�3{�oV��+�(��7<j��pc�"�z���֤�ϗ'�m�si�0�}��y��eP1�:���Dcյ���6=�R,�s�{�7�d}�jj�h�f�j��