update

Author: kostya

CHANGELOG.md

@@ -1,5 +1,9 @@
+## 3.3.0
+* update liblexbor to latest
+* add usage `Lexbor.new` instead of `Lexbor::Parser.new`
+
 ## 3.2.0
-* updat liblexbor to latest
+* update liblexbor to latest
 
 ## 3.1.3
 * fix usage in interpreter

README.md

@@ -34,7 +34,7 @@ html = <<-HTML
   </html>
 HTML
 
-lexbor = Lexbor::Parser.new(html)
+lexbor = Lexbor.new(html)
 
 lexbor.nodes(:div).each do |node|
   id = node["id"]?
@@ -76,7 +76,7 @@ html = <<-HTML
   </html>
 HTML
 
-lexbor = Lexbor::Parser.new(html)
+lexbor = Lexbor.new(html)
 
 p lexbor.css("#t2 tr td:first-child").map(&.inner_text).to_a
 # => ["123", "foo", "bar", "xyz"]

examples/basic1.cr

@@ -13,7 +13,7 @@ html = <<-HTML
   </html>
 HTML
 
-lexbor = Lexbor::Parser.new(html)
+lexbor = Lexbor.new(html)
 
 lexbor.nodes(:div).each do |node|
   id = node["id"]?

examples/create_html.cr

@@ -2,7 +2,7 @@
 
 require "../src/lexbor"
 
-doc = Lexbor::Parser.new ""
+doc = Lexbor.new ""
 body = doc.body!
 
 div = doc.create_node(:div)

examples/css_selectors1.cr

@@ -16,7 +16,7 @@ html = <<-HTML
   </html>
 HTML
 
-lexbor = Lexbor::Parser.new(html)
+lexbor = Lexbor.new(html)
 
 p lexbor.css("#t2 tr td:first-child").map(&.inner_text).to_a
 # => ["123", "foo", "bar", "xyz"]

examples/css_selectors2.cr

@@ -15,30 +15,30 @@ html = <<-PAGE
   </div>
 PAGE
 
-parser = Lexbor::Parser.new(html)
+lexbor = Lexbor.new(html)
 
 # select all p nodes which id like `*p*`
-p parser.css("p[id*=p]").map(&.attribute_by("id")).to_a # => ["p1", "p2", "p3", "p4", "p5", "p6"]
+p lexbor.css("p[id*=p]").map(&.attribute_by("id")).to_a # => ["p1", "p2", "p3", "p4", "p5", "p6"]
 
 # select all nodes with class "jo"
-p parser.css("p.jo").map(&.attribute_by("id")).to_a # => ["p2", "p4", "p6"]
-p parser.css(".jo").map(&.attribute_by("id")).to_a  # => ["p2", "p4", "p6"]
+p lexbor.css("p.jo").map(&.attribute_by("id")).to_a # => ["p2", "p4", "p6"]
+p lexbor.css(".jo").map(&.attribute_by("id")).to_a  # => ["p2", "p4", "p6"]
 
 # select odd child tag inside div, which not contain a
-p parser.css("div > :nth-child(2n+1):not(:has(a))").map(&.attribute_by("id")).to_a # => ["p1", "p4", "p6"]
+p lexbor.css("div > :nth-child(2n+1):not(:has(a))").map(&.attribute_by("id")).to_a # => ["p1", "p4", "p6"]
 
 # all elements with class=jo inside last div tag
-p parser.css("div").to_a.last.css(".jo").map(&.attribute_by("id")).to_a # => ["p4", "p6"]
+p lexbor.css("div").to_a.last.css(".jo").map(&.attribute_by("id")).to_a # => ["p4", "p6"]
 
 # a element with href ends like .png
-p parser.css(%q{a[href$=".png"]}).map(&.attribute_by("id")).to_a # => ["a2"]
+p lexbor.css(%q{a[href$=".png"]}).map(&.attribute_by("id")).to_a # => ["a2"]
 
 # find all a tags inside <p id=p3>, which href contain `html`
-p parser.css(%q{p[id=p3] > a[href*="html"]}).map(&.attribute_by("id")).to_a # => ["a1"]
+p lexbor.css(%q{p[id=p3] > a[href*="html"]}).map(&.attribute_by("id")).to_a # => ["a1"]
 
 # find all a tags inside <p id=p3>, which href contain `html` or ends_with `.png`
-p parser.css(%q{p[id=p3] > a:is([href *= "html"], [href $= ".png"])}).map(&.attribute_by("id")).to_a # => ["a1", "a2"]
+p lexbor.css(%q{p[id=p3] > a:is([href *= "html"], [href $= ".png"])}).map(&.attribute_by("id")).to_a # => ["a1", "a2"]
 
 # create filter and use it in many places, this is faster, than create it many times
 filter = Lexbor::CssFilter.new(".jo")
-p parser.css(filter).map(&.attribute_by("id")).to_a # => ["p2", "p4", "p6"]
+p lexbor.css(filter).map(&.attribute_by("id")).to_a # => ["p2", "p4", "p6"]

examples/links.cr

@@ -35,7 +35,7 @@ def good_texts_iterator(iterator)
     .reject(&.empty?)
 end
 
-Lexbor::Parser.new(str).nodes(:a).each do |node|
+Lexbor.new(str).nodes(:a).each do |node|
   anchor = node.inner_text(deep: true)
   href = node.attribute_by("href")
   before = good_texts_iterator(node.left_iterator).first?

examples/print_html.cr

@@ -26,7 +26,7 @@ formatting = (ARGV[1]? != "0")
 remove_whitespaces = (ARGV[2]? != "0")
 remove_comments = (ARGV[3]? != "0")
 
-lexbor = Lexbor::Parser.new(str)
+lexbor = Lexbor.new(str)
 
 if remove_comments
   nodes = lexbor.nodes(:_em_comment).to_a # important to materialize array with to_a, before removing

examples/print_tree.cr

@@ -13,8 +13,7 @@ str = if filename = ARGV[0]?
         "<html><Div><span class='test'>HTML</span></div></html>"
       end
 
-parser = Lexbor::Parser.new(str)
-walk(parser.root!)
+walk(Lexbor.new(str).root!)
 
 # Output:
 # Lexbor::Node(:html)

examples/texts.cr

@@ -30,17 +30,16 @@ struct Lexbor::Node
   end
 end
 
-def words(parser)
-  parser
+def words(doc)
+  doc
     .nodes(:_text)                         # iterate through all TEXT nodes
     .select(&.parents.all?(&.displayble?)) # select only which parents are visible good tag
     .map(&.tag_text)                       # mapping node text
     .reject(&.blank?)                      # reject blanked texts
     .map(&.strip.gsub(/\s{2,}/, " "))      # remove extra spaces
 end
 
-parser = Lexbor::Parser.new(str)
-puts words(parser).join(" | ")
+puts words(Lexbor.new(str)).join(" | ")
 
 # Output:
 #   Название: | Что я сделал? | Ответил: | Чудище-Змей | на | 21 Октябрь 2005, 18:11 |

examples/usage.cr

@@ -5,7 +5,7 @@ require "../src/lexbor"
 puts Lexbor.version
 
 page = "<html><div class=aaa>bla</div></html>"
-lexbor = Lexbor::Parser.new(page)
+lexbor = Lexbor.new(page)
 
 # html node
 lexbor.root  # (.html) Lexbor::Node?

spec/css_selectors_spec.cr

@@ -5,7 +5,7 @@ describe Lexbor do
     html = "<div><p id=p1><p id=p2><p id=p3><a>link</a><p id=p4><p id=p5><p id=p6></div>"
     selector = "div > :nth-child(2n+1):not(:has(a))"
 
-    parser = Lexbor::Parser.new(html)
+    parser = Lexbor.new(html)
     finder = Lexbor::CssFilter.new(selector)
     nodes = finder.search_from(parser.html!).to_a
 
@@ -23,7 +23,7 @@ describe Lexbor do
   it "css for root! node" do
     html = "<div><p id=p1><p id=p2 class=jo><p id=p3><a>link</a><span id=bla><p id=p4 class=jo><p id=p5 class=bu><p id=p6 class=jo></span></div>"
 
-    parser = Lexbor::Parser.new(html)
+    parser = Lexbor.new(html)
     nodes = parser.root!.css("div > :nth-child(2n+1):not(:has(a))").to_a
 
     nodes.size.should eq 2
@@ -40,21 +40,21 @@ describe Lexbor do
   it "another rule" do
     html = "<div><p id=p1><p id=p2 class=jo><p id=p3><a>link</a><span id=bla><p id=p4 class=jo><p id=p5 class=bu><p id=p6 class=jo></span></div>"
 
-    parser = Lexbor::Parser.new(html)
+    parser = Lexbor.new(html)
     parser.root!.css(".jo").to_a.map(&.attribute_by("id")).should eq %w(p2 p4 p6)
   end
 
   it "another rule for parser itself" do
     html = "<div><p id=p1><p id=p2 class=jo><p id=p3><a>link</a><span id=bla><p id=p4 class=jo><p id=p5 class=bu><p id=p6 class=jo></span></div>"
 
-    parser = Lexbor::Parser.new(html)
+    parser = Lexbor.new(html)
     parser.css(".jo").to_a.map(&.attribute_by("id")).should eq %w(p2 p4 p6)
   end
 
   it "work for another scope node" do
     html = "<div><p id=p1><p id=p2 class=jo><p id=p3><a>link</a><div id=bla><p id=p4 class=jo><p id=p5 class=bu><p id=p6 class=jo></div></div>"
 
-    parser = Lexbor::Parser.new(html)
+    parser = Lexbor.new(html)
     parser.nodes(:div).to_a.last.css(".jo").to_a.map(&.attribute_by("id")).should eq %w(p4 p6)
     parser.nodes(:div).to_a.first.css(".jo").to_a.map(&.attribute_by("id")).should eq %w(p2 p4 p6)
   end
@@ -63,7 +63,7 @@ describe Lexbor do
     it "for parser" do
       html = "<div><p id=p1><p id=p2 class=jo><p id=p3><a>link</a><span id=bla><p id=p4 class=jo><p id=p5 class=bu><p id=p6 class=jo></span></div>"
 
-      parser = Lexbor::Parser.new(html)
+      parser = Lexbor.new(html)
       finder = Lexbor::CssFilter.new(".jo")
 
       10.times do
@@ -76,7 +76,7 @@ describe Lexbor do
     it "for parser" do
       html = "<div><p id=p1><p id=p2 class=jo><p id=p3><a>link</a><span id=bla><p id=p4 class=jo><p id=p5 class=bu><p id=p6 class=jo></span></div>"
 
-      parser = Lexbor::Parser.new(html)
+      parser = Lexbor.new(html)
       finder = Lexbor::CssFilter.new(".jo")
 
       10.times do
@@ -87,7 +87,7 @@ describe Lexbor do
     it "for root node" do
       html = "<div><p id=p1><p id=p2 class=jo><p id=p3><a>link</a><span id=bla><p id=p4 class=jo><p id=p5 class=bu><p id=p6 class=jo></span></div>"
 
-      parser = Lexbor::Parser.new(html)
+      parser = Lexbor.new(html)
       finder = Lexbor::CssFilter.new(".jo")
 
       10.times do
@@ -99,7 +99,7 @@ describe Lexbor do
   it "should raise on empty selector" do
     html = "<div><p id=p1><p id=p2 class=jo><p id=p3><a>link</a><span id=bla><p id=p4 class=jo><p id=p5 class=bu><p id=p6 class=jo></span></div>"
 
-    parser = Lexbor::Parser.new(html)
+    parser = Lexbor.new(html)
     expect_raises(Lexbor::LibError, "Failed to css_selectors_parse for") do
       finder = Lexbor::CssFilter.new("")
       parser.css(finder).to_a.size.should eq 0
@@ -122,7 +122,7 @@ describe Lexbor do
       </div>
     PAGE
 
-    parser = Lexbor::Parser.new(html)
+    parser = Lexbor.new(html)
 
     # select all p nodes which id like `*p*`
     parser.css("p[id*=p]").map(&.attribute_by("id")).to_a.should eq ["p1", "p2", "p3", "p4", "p5", "p6"]
@@ -166,7 +166,7 @@ describe Lexbor do
       </body></html>
     PAGE
 
-    parser = Lexbor::Parser.new(html)
+    parser = Lexbor.new(html)
     parser.css("#t2 tr td:first-child").map(&.inner_text).to_a.should eq ["123", "foo", "bar", "xyz"]
     parser.css("#t2 tr td:first-child").map(&.to_html).to_a.should eq ["<td>123</td>", "<td>foo</td>", "<td>bar</td>", "<td>xyz</td>"]
 
@@ -179,7 +179,7 @@ describe Lexbor do
 
   it "not sigfaulting on more than 1024 elements" do
     str = "<html>" + "<div class=A>ooo</div>" * 20000 + "</html>"
-    parser = Lexbor::Parser.new(str)
+    parser = Lexbor.new(str)
 
     c = 0
     x = 0
@@ -192,12 +192,12 @@ describe Lexbor do
   end
 
   it "bug in css" do
-    parser = Lexbor::Parser.new(%q{<div class="asfjjjj">bla</div>})
+    parser = Lexbor.new(%q{<div class="asfjjjj">bla</div>})
     parser.css("div.jjjj").to_a.size.should eq 0
   end
 
   it "css with yield" do
-    parser = Lexbor::Parser.new(%q{<div class="jjjj">bla</div>})
+    parser = Lexbor.new(%q{<div class="jjjj">bla</div>})
     parser.css("div.jjjj") { |col| col.to_a.size }.should eq 1
   end
 end

spec/integration_spec.cr

@@ -64,7 +64,7 @@ def parser_links
     </html>
   HTML
 
-  Lexbor::Parser.new(str)
+  Lexbor.new(str)
 end
 
 describe "integration" do

spec/iterators_spec.cr

@@ -21,7 +21,7 @@ def parser(**args)
     </html>
   HTML
 
-  parser = Lexbor::Parser.new(str, **args)
+  parser = Lexbor.new(str, **args)
   parser
 end
 
@@ -168,7 +168,7 @@ describe "iterators" do
   end
 
   # it "Collection befave like array, when multiple times call size, empty? and others..." do
-  #   parser = Lexbor::Parser.new(%q{<head><title>Title</title></head>})
+  #   parser = Lexbor.new(%q{<head><title>Title</title></head>})
   #   iter = parser.css("title")
 
   #   iter.size.should eq 1

spec/lexbor_spec.cr

@@ -2,7 +2,7 @@ require "./spec_helper"
 
 describe Lexbor do
   it "parser work" do
-    parser = Lexbor::Parser.new("<html>BLA</html>")
+    parser = Lexbor.new("<html>BLA</html>")
 
     parser.root!.tag_name.should eq "html"
     parser.root!.child!.tag_name.should eq "head"