uri-whatwg_parser 0.1.2 → 0.1.3

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 57eb48896a4f467a9b2f4d5a9b195a8df8a3b1f707d680711e777b1226d5471a
-  data.tar.gz: 90e1c4a439d6309ac14c7f8e46ace4128c8f8469d275e29b9afa06b60d1e8ac9
+  metadata.gz: d94a0f3f96af7620d7592bb1c0b215b52bfcb7e19c2be83177407a67ae8eaa79
+  data.tar.gz: 14cd125a49fc9b61eb5f70621cfc8685e0cb9b309f048f5528e6c6a37d389eaf
 SHA512:
-  metadata.gz: dd95276e9e4df35db76eb196c46b72f1300d777c45161dcf58d3253e477db846d7662cd9f0e837fcc37a3ddd047700c024ecc5c1adeed83c24a478026b188936
-  data.tar.gz: 3cb8ee2b663bb4938bd099106874bed736aa709a38ff4b435803c8ff1752f229a4d8cd83ffb920fc1e29f5ebfc1815f5796105a6f54bb99d241f4b5adb605efa
+  metadata.gz: 31e07e1a13f149e0188cd7701e2e0828fa66b078004b30bbe55ae1a34989cb68cf4190a0283d6969b718f90712a1cbf61f1efee095ab5847ea6771caf3936661
+  data.tar.gz: 3e251062ddd86971a0829f83fb27f0b1da05016544b95516f859ce66cb6bd35d61abea75dd1bf693d663de47853c82e7ff326d771f4924a3827fe38c8f5a3df4

data/CHANGELOG.md

@@ -0,0 +1,15 @@
+## 0.1.3
+
+* Improve performance of parsing
+
+## 0.1.2
+
+* Correctly compress IPv6 host
+
+## 0.1.1
+
+* Support `base` option
+
+## 0.1.0
+
+* Initial release

data/lib/uri/whatwg_parser/host_parser.rb

@@ -156,11 +156,11 @@ class URI::WhatwgParser
     end
 
     def include_forbidden_domain_code_point?(str)
-      str.chars.intersect?(FORBIDDEN_DOMAIN_CODE_POINT)
+      FORBIDDEN_DOMAIN_CODE_POINT.any? {|c| str.include?(c) }
     end
 
     def include_forbidden_host_code_point?(str)
-      str.chars.intersect?(FORBIDDEN_HOST_CODE_POINT)
+      FORBIDDEN_HOST_CODE_POINT.any? {|c| str.include?(c) }
     end
   end
 end

data/lib/uri/whatwg_parser/parser_helper.rb

@@ -2,8 +2,9 @@
 
 class URI::WhatwgParser
   module ParserHelper
-    C0_CONTROL = (0..0x1f).to_a
-    C0_CONTROL_PERCENT_ENCODE_SET = C0_CONTROL.map(&:chr)
+    C0_CONTROL_PERCENT_ENCODE_SET = (0..0x1f).map(&:chr)
+    ASCII_ALPHA = ("a".."z").to_a + ("A".."Z").to_a
+    ASCII_DIGIT = ("0".."9").to_a
 
     def ascii_alpha?(c)
       ASCII_ALPHA.include?(c)

data/lib/uri/whatwg_parser/version.rb

@@ -2,6 +2,6 @@
 
 module URI
   class WhatwgParser
-    VERSION = "0.1.2"
+    VERSION = "0.1.3"
   end
 end

data/lib/uri/whatwg_parser.rb

@@ -1,6 +1,5 @@
 # frozen_string_literal: true
 
-require "strscan"
 require "uri"
 require_relative "whatwg_parser/error"
 require_relative "whatwg_parser/version"
@@ -12,8 +11,6 @@ module URI
     include ParserHelper
 
     SPECIAL_SCHEME = { "ftp" => 21, "file" => nil, "http" => 80, "https" => 443, "ws" => 80, "wss" => 443 }
-    ASCII_ALPHA = ("a".."z").to_a + ("A".."Z").to_a
-    ASCII_DIGIT = ("0".."9").to_a
 
     FRAGMENT_PERCENT_ENCODE_SET = C0_CONTROL_PERCENT_ENCODE_SET + [" ", "\"", "<", ">", "`"]
     QUERY_PERCENT_ENCODE_SET = C0_CONTROL_PERCENT_ENCODE_SET + [" ", "\"", "#", "<", ">"]
@@ -51,31 +48,25 @@ module URI
         reset
       end
 
-      uri = uri.dup
-      uri.gsub!(/\A[\u0000-\u0020]*/, "")
-      uri.gsub!(/[\u0000-\u0020]*\z/, "")
-      uri.delete!("\t")
-      uri.delete!("\n")
-      uri.delete!("\r")
+      @uri = uri.dup
+      @uri.sub!(/\A[\u0000-\u0020]*/, "")
+      @uri.sub!(/[\u0000-\u0020]*\z/, "")
+      @uri.delete!("\t")
+      @uri.delete!("\n")
+      @uri.delete!("\r")
 
       raise ParseError, "uri can't be empty" if uri.empty? && @base.nil?
 
-      @scanner = StringScanner.new(uri)
+      @pos = 0
 
-      loop do
-        c = @scanner.getch
-        send("on_#{@state}", c)
-
-        if @force_continue
-          @force_continue = false
-          next
-        end
-
-        break if c.nil? && @scanner.eos?
+      while @pos <= @uri.length
+        c = @uri[@pos]
+        send(@state, c)
+        @pos += 1
       end
 
       @parse_result[:userinfo] = "#{@username}:#{@password}" if !@username.nil? || !@password.nil?
-      @parse_result[:path] = "/#{@paths.join("/")}" if !@paths.empty?
+      @parse_result[:path] = "/#{@paths.join("/")}" if @paths && !@paths.empty?
 
       @parse_result.values
     end
@@ -95,12 +86,11 @@ module URI
     private
 
     def reset
-      @scanner = nil
       @buffer = +""
       @at_sign_seen = nil
       @password_token_seen = nil
       @inside_brackets = nil
-      @paths = []
+      @paths = nil
       @username = nil
       @password = nil
       @parse_result = { scheme: nil, userinfo: nil, host: nil, port: nil, registry: nil, path: nil, opaque: nil, query: nil, fragment: nil }
@@ -108,21 +98,17 @@ module URI
       @state = :scheme_start_state
     end
 
-    def on_scheme_start_state(c)
+    def scheme_start_state(c)
       if ascii_alpha?(c)
         @buffer += c.downcase
         @state = :scheme_state
       else
-        if c.nil?
-          @force_continue = true
-        else
-          @scanner.pos -= c.bytesize
-        end
+        @pos -= 1
         @state = :no_scheme_state
       end
     end
 
-    def on_scheme_state(c)
+    def scheme_state(c)
       if ascii_alphanumerica?(c) || ["+", "-", "."].include?(c)
         @buffer += c.downcase
       elsif c == ":"
@@ -135,58 +121,58 @@ module URI
           @state = :special_relative_or_authority_state
         elsif special_url?
           @state = :special_authority_slashes_state
-        elsif @scanner.rest.start_with?("/")
+        elsif rest.start_with?("/")
           @state = :path_or_authority_state
-          @scanner.pos += c.bytesize
+          @pos += 1
         else
-          @parse_result[:path] = ""
+          @parse_result[:path] = nil
           @state = :opaque_path_state
         end
       else
         @buffer = +""
-        decrease_pos(c)
+        @pos -= 1
         @state = :no_scheme_state
       end
     end
 
-    def on_no_scheme_state(c)
+    def no_scheme_state(c)
       raise ParseError, "scheme is missing" if @base.nil? || !@base[:opaque].nil? && c != "#"
 
       if !@base[:opaque].nil? && c == "#"
         @parse_result[:scheme] = @base[:scheme]
         @parse_result[:path] = @base[:path]
         @parse_result[:query] = @base[:query]
-        @parse_result[:fragment] = ""
+        @parse_result[:fragment] = nil
         @state = :fragment_state
       elsif @base[:scheme] != "file"
         @state = :relative_state
-        decrease_pos(c)
+        @pos -= 1
       else
         @state = :file_state
-        decrease_pos(c)
+        @pos -= 1
       end
     end
 
-    def on_special_relative_or_authority_state(c)
-      if c == "/" && @scanner.rest.start_with?("/")
+    def special_relative_or_authority_state(c)
+      if c == "/" && rest.start_with?("/")
         @state = :special_authority_ignore_slashes_state
-        decrease_pos(c)
+        @pos -= 1
       else
         @state = :relative_state
-        decrease_pos(c)
+        @pos -= 1
       end
     end
 
-    def on_path_or_authority_state(c)
+    def path_or_authority_state(c)
       if c == "/"
         @state = :authority_state
       else
         @state = :path_state
-        decrease_pos(c)
+        @pos -= 1
       end
     end
 
-    def on_relative_state(c)
+    def relative_state(c)
       @parse_result[:scheme] = @base[:scheme]
       if c == "/"
         @state = :relative_slash_state
@@ -200,21 +186,21 @@ module URI
         @parse_result[:query] = @base[:query]
 
         if c == "?"
-          @parse_result[:query] = ""
+          @parse_result[:query] = nil
           @state = :query_state
         elsif c == "#"
-          @parse_result[:fragment] = ""
+          @parse_result[:fragment] = nil
           @state = :fragment_state
         elsif !c.nil?
           @parse_result[:query] = nil
           shorten_url_path
           @state = :path_state
-          @scanner.pos -= c.bytesize
+          @pos -= 1
         end
       end
     end
 
-    def on_relative_slash_state(c)
+    def relative_slash_state(c)
       if special_url? && (c == "/" || c == "\\")
         @state = :special_authority_ignore_slashes_state
       elsif c == "/"
@@ -224,28 +210,28 @@ module URI
         @parse_result[:host] = @base[:host]
         @parse_result[:port] = @base[:port]
         @state = :path_state
-        decrease_pos(c)
+        @pos -= 1
       end
     end
 
-    def on_special_authority_slashes_state(c)
-      if c == "/" && @scanner.rest.start_with?("/")
+    def special_authority_slashes_state(c)
+      if c == "/" && rest.start_with?("/")
         @state = :special_authority_ignore_slashes_state
-        @scanner.pos += c.bytesize
+        @pos += 1
       else
         @state = :special_authority_ignore_slashes_state
-        decrease_pos(c)
+        @pos -= 1
       end
     end
 
-    def on_special_authority_ignore_slashes_state(c)
+    def special_authority_ignore_slashes_state(c)
       if c != "/" && c != "\\"
         @state = :authority_state
-        decrease_pos(c)
+        @pos -= 1
       end
     end
 
-    def on_authority_state(c)
+    def authority_state(c)
       if c == "@"
         @buffer.prepend("%40") if @at_sign_seen
         @at_sign_seen = true
@@ -267,12 +253,8 @@ module URI
         @buffer = +""
       elsif c.nil? || ["/", "?", "#"].include?(c) || (special_url? && c == "\\")
         raise ParseError, "host is missing" if @at_sign_seen && @buffer.empty?
-        if c.nil?
-          @force_continue = true
-          @scanner.pos -= @buffer.bytesize
-        else
-          @scanner.pos -= (@buffer.bytesize + c.bytesize.to_i)
-        end
+
+        @pos -= (@buffer.size + 1)
         @buffer = +""
         @state = :host_state
       else
@@ -280,7 +262,7 @@ module URI
       end
     end
 
-    def on_host_state(c)
+    def host_state(c)
       if c == ":" && !@inside_brackets
         raise ParseError, "host is missing" if @buffer.empty?
 
@@ -288,7 +270,7 @@ module URI
         @buffer = +""
         @state = :port_state
       elsif c.nil? || ["/", "?", "#"].include?(c) || (special_url? && c == "\\")
-        decrease_pos(c)
+        @pos -= 1
         if special_url? && @buffer.empty?
           raise ParseError, "host is missing"
         else
@@ -303,7 +285,7 @@ module URI
       end
     end
 
-    def on_port_state(c)
+    def port_state(c)
       if ascii_digit?(c)
         @buffer += c
       elsif c.nil? || ["/", "?", "#"].include?(c) || (special_url? && c == "\\")
@@ -320,15 +302,15 @@ module URI
         end
 
         @state = :path_start_state
-        decrease_pos(c)
+        @pos -= 1
       else
         raise ParseError, "port is invalid value"
       end
     end
 
-    def on_file_state(c)
+    def file_state(c)
       @parse_result[:scheme] = "file"
-      @parse_result[:host] = ""
+      @parse_result[:host] = nil
 
       if c == "/" || c == "\\"
         @state = :file_slash_state
@@ -336,50 +318,50 @@ module URI
         @parse_result[:host] = @base[:host]
         @parse_result[:query] = @base[:query]
         if c == "?"
-          @parse_result[:query] = ""
+          @parse_result[:query] = nil
           @state = :query_state
         elsif c == "#"
-          @parse_result[:fragment] = ""
+          @parse_result[:fragment] = nil
           @state = :fragment_state
         elsif !c.nil?
           @parse_result[:query] = nil
-          if !starts_with_windows_drive_letter?(@scanner.rest)
+          if !starts_with_windows_drive_letter?(rest)
             shorten_url_path
           else
-            @paths = []
+            @paths = nil
           end
           @state = :path_state
-          decrease_pos(c)
+          @pos -= 1
         end
       else
         @state = :path_state
-        decrease_pos(c)
+        @pos -= 1
       end
     end
 
-    def on_file_slash_state(c)
+    def file_slash_state(c)
       if c == "/" || c == "\\"
         @state = :file_host_state
       else
         if !@base.nil? && @base[:scheme] == "file"
           @parse_result[:host] = @base[:host]
-          if !starts_with_windows_drive_letter?(@scanner.rest) && normalized_windows_drive_letter?(@base_paths[0])
+          if !starts_with_windows_drive_letter?(rest) && @base_paths && normalized_windows_drive_letter?(@base_paths[0])
             @paths[0] += @base_paths[0]
           end
         end
         @state = :path_state
-        decrease_pos(c)
+        @pos -= 1
       end
     end
 
-    def on_file_host_state(c)
+    def file_host_state(c)
       if c.nil? || c == "/" || c == "\\" || c == "?" || c == "#"
-        @scanner.pos -= c.bytesize unless c.nil?
+        @pos -= 1
 
         if windows_drive_letter?(@buffer)
           @state = :path_state
         elsif @buffer.empty?
-          @parse_result[:host] = ""
+          @parse_result[:host] = nil
           @state = :path_start_state
         else
           host = @host_parser.parse(@buffer, !special_url?)
@@ -395,23 +377,23 @@ module URI
       @buffer += c unless c.nil?
     end
 
-    def on_path_start_state(c)
-      return if c.nil?
-
+    def path_start_state(c)
       if special_url?
-        @scanner.pos -= c.bytesize if c != "/" && c != "\\"
+        @pos -= 1 if c != "/" && c != "\\"
         @state = :path_state
       elsif c == "?"
         @state = :query_state
       elsif c == "#"
         @state = :fragment_state
       elsif c != nil
-        @scanner.pos -= c.bytesize if c != "/"
+        @pos -= 1 if c != "/"
         @state = :path_state
       end
     end
 
-    def on_path_state(c)
+    def path_state(c)
+      @paths ||= []
+
       if (c.nil? || c == "/") || (special_url? && c == "\/") || (c == "?" || c == "#")
 
         if double_dot_path_segments?(@buffer)
@@ -431,10 +413,10 @@ module URI
         @buffer = +""
 
         if c == "?"
-          @parse_result[:query] = ""
+          @parse_result[:query] = nil
           @state = :query_state
         elsif c == "#"
-          @parse_result[:frament] = ""
+          @parse_result[:frament] = nil
           @state = :fragment_state
         end
       else
@@ -442,15 +424,15 @@ module URI
       end
     end
 
-    def on_opaque_path_state(c)
+    def opaque_path_state(c)
       if c == "?"
-        @parse_result[:query] = ""
+        @parse_result[:query] = nil
         @state = :query_state
       elsif c == "#"
-        @parse_result[:fragment] = ""
+        @parse_result[:fragment] = nil
         @state = :fragment_state
       elsif c == " "
-        if @scanner.rest.start_with?("?") || @scanner.rest.start_with?("#")
+        if rest.start_with?("?") || rest.start_with?("#")
           @parse_result[:path] = @parse_result[:path].to_s + "%20"
         else
           @parse_result[:path] = @parse_result[:path].to_s + " "
@@ -460,7 +442,7 @@ module URI
       end
     end
 
-    def on_query_state(c)
+    def query_state(c)
       if c.nil? || c == "#"
         query_percent_encode_set = special_url? ? SPECIAL_QUERY_PERCENT_ENCODE_SET : QUERY_PERCENT_ENCODE_SET
         @parse_result[:query] = @buffer.chars.map { |c| percent_encode(c, query_percent_encode_set) }.join
@@ -471,19 +453,11 @@ module URI
       end
     end
 
-    def on_fragment_state(c)
+    def fragment_state(c)
       return if c.nil?
       @parse_result[:fragment] = @parse_result[:fragment].to_s + percent_encode(c, FRAGMENT_PERCENT_ENCODE_SET)
     end
 
-    def c0_control_or_space?(c)
-      c0_control? || c == " "
-    end
-
-    def c0_control?(c)
-      C0_CONTROL.include?(c.ord)
-    end
-
     def windows_drive_letter?(str)
       WINDOWS_DRIVE_LETTER.match?(str)
     end
@@ -497,7 +471,7 @@ module URI
     end
 
     def special_url?
-      SPECIAL_SCHEME.keys.include?(@parse_result[:scheme])
+      SPECIAL_SCHEME.key?(@parse_result[:scheme])
     end
 
     def single_dot_path_segments?(c)
@@ -515,12 +489,8 @@ module URI
       @parse_result[:path]&.chomp!
     end
 
-    def decrease_pos(c)
-      if c.nil?
-        @force_continue = true
-      else
-        @scanner.pos -= c.bytesize
-      end
+    def rest
+      @uri[@pos+1..]
     end
   end
 end

metadata

@@ -1,28 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: uri-whatwg_parser
 version: !ruby/object:Gem::Version
-  version: 0.1.2
+  version: 0.1.3
 platform: ruby
 authors:
 - Yuji Yaginuma
 bindir: exe
 cert_chain: []
-date: 2025-05-12 00:00:00.000000000 Z
+date: 2025-05-25 00:00:00.000000000 Z
 dependencies:
-- !ruby/object:Gem::Dependency
-  name: strscan
-  requirement: !ruby/object:Gem::Requirement
-    requirements:
-    - - ">="
-      - !ruby/object:Gem::Version
-        version: '0'
-  type: :runtime
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    requirements:
-    - - ">="
-      - !ruby/object:Gem::Version
-        version: '0'
 - !ruby/object:Gem::Dependency
   name: uri
   requirement: !ruby/object:Gem::Requirement
@@ -71,6 +57,7 @@ executables: []
 extensions: []
 extra_rdoc_files: []
 files:
+- CHANGELOG.md
 - LICENSE.txt
 - README.md
 - Rakefile