wikiscript-parser 0.0.1

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: 4cc732979e1e25604b1cdbe22b32257cb6a45f81
+  data.tar.gz: 6f0c638ffff2721893648fd14c806ccda48c129a
+SHA512:
+  metadata.gz: 5be2b8eb71b3cd149ee292dd95309f959661092ebbf17a50633a195fa879178c4a087ae3af503bc6fe322e9d113d0f347f9e5e14272f30e296e973dd9494658b
+  data.tar.gz: b2401e1c920ae981e20b77b8399b8e03791cf38901440fc9e35a584c4bcf68d6c633b10315168d68e4a30806ccb4fa6c9b923d152274217dd6d586f992424a3f

data/CHANGELOG.md

@@ -0,0 +1,3 @@
+### 0.0.1 / 2020-11-30
+
+* Everything is new. First release.

data/Manifest.txt

@@ -0,0 +1,8 @@
+CHANGELOG.md
+Manifest.txt
+README.md
+Rakefile
+lib/wikiscript-parser.rb
+lib/wikiscript-parser/parser.rb
+lib/wikiscript-parser/version.rb
+lib/wikiscript/parser.rb

data/README.md

@@ -0,0 +1,31 @@
+# wikiscript-parser - wikitext/script parser (builds abstract syntax tree 'n' more )
+
+* home  :: [github.com/wikiscript/wikiscript](https://github.com/wikiscript/wikiscript)
+* bugs  :: [github.com/wikiscript/wikiscript/issues](https://github.com/wikiscript/wikiscript/issues)
+* gem   :: [rubygems.org/gems/wikiscript-parser](https://rubygems.org/gems/wikiscript-parser)
+* rdoc  :: [rubydoc.info/gems/wikiscript-parser](http://rubydoc.info/gems/wikiscript-parser)
+
+
+
+## Usage
+
+
+to be done
+
+
+
+## Install
+
+Use
+
+    gem install wikiscript-parser
+
+or add to your Gemfile
+
+    gem 'wikiscript-parser'
+
+
+## License
+
+The `wikiscript` scripts are dedicated to the public domain.
+Use it as you please with no restrictions whatsoever.

data/Rakefile

@@ -0,0 +1,29 @@
+require 'hoe'
+require './lib/wikiscript-parser/version.rb'
+
+Hoe.spec 'wikiscript-parser' do
+
+  self.version = Wikiscript::Module::Parser::VERSION
+
+  self.summary = "wikiscript-parser - wikitext/script parser (builds abstract syntax tree 'n' more)"
+  self.description = summary
+
+  self.urls = { home: 'https://github.com/wikiscript/wikiscript' }
+
+  self.author = 'Gerald Bauer'
+  self.email  = 'opensport@googlegroups.com'
+
+  # switch extension to .markdown for gihub formatting
+  self.readme_file  = 'README.md'
+  self.history_file = 'CHANGELOG.md'
+
+  self.extra_deps = [
+    ['wikitree' ],
+  ]
+
+  self.licenses = ['Public Domain']
+
+  self.spec_extras = {
+    required_ruby_version: '>= 2.2.2'
+  }
+end

data/lib/wikiscript-parser.rb

@@ -0,0 +1,25 @@
+## stdlibs
+require 'strscan'
+
+
+## 3rd party gems/libs
+require 'wikitree'
+
+# our own code
+require 'wikiscript-parser/version' # let it always go first
+require 'wikiscript-parser/parser'
+
+
+
+
+####
+# convenience all-in-one parse helper - add - why? why not?
+module Wikiscript
+  def self.parse( text )
+     Parser.new( text ).parse
+  end
+end
+
+
+
+puts Wikiscript::Module::Parser.banner

data/lib/wikiscript-parser/parser.rb

@@ -0,0 +1,205 @@
+module Wikiscript
+
+
+class Parser
+  ####
+  # convenience all-in-one parse helper
+  def self.parse( text )
+    new( text ).parse
+  end
+
+
+  def initialize( text )
+    @text = text
+  end
+
+  def parse
+    parse_lines( @text )
+  end
+
+
+
+
+  def skip_whitespaces( input )  ## incl. multiple newlines
+    return 0   if input.eos?
+
+    input.scan( /[ \t\r\n]*/ )
+  end
+
+  #
+  # Whereas MediaWiki variable names are all uppercase,
+  # template names have the same basic features and limitations as all page names:
+  # they are case-sensitive (except for the first character);
+  # underscores are parsed as spaces;
+  # and they cannot contain any of these characters: # < > [ ] | { }.
+  # This is because those are reserved for wiki markup and HTML.
+
+  TEMPLATE_BEGIN_RE = /\{\{/  ## e.g  {{
+  TEMPLATE_END_RE   = /\}\}/  ## e.g. }}
+
+  ## todo/fix: check how to add # too!!!
+  ##  todo: check what chars to escape in character class
+  ##  change to something line [^|<>\[\]{}]+ ]
+  TEMPLATE_NAME_RE = /[a-z0-9 _-]+/i
+
+
+
+  def parse_template( input )
+    input.scan( TEMPLATE_BEGIN_RE ) ## e.g.{{
+    skip_whitespaces( input )
+
+    name = input.scan( TEMPLATE_NAME_RE )
+    name = name.strip  ## strip trailing spaces?
+    puts "==> (begin) template >#{name}<"
+    skip_whitespaces( input )
+
+    params = []
+    loop do
+       if input.check( TEMPLATE_END_RE ) ## e.g. }}
+         input.scan( TEMPLATE_END_RE )
+         puts "<== (end) template >#{name}<"
+         ## puts "  params:"
+         ## pp params
+         return Wikitree::Template.new( name, params )
+       elsif input.check( /\|/ )  ## e.g. |
+         puts "      param #{params.size+1} (#{name}):"
+         param_name, param_value = parse_param( input )
+         params << [param_name, param_value]
+       else
+         puts "!! SYNTAX ERROR: expected closing }} or para | in template:"
+         puts input.peek( 100 )
+         exit 1
+       end
+    end
+  end
+
+
+
+  def parse_param( input )
+    input.scan( /\|/ )
+    skip_whitespaces( input )
+
+    name  = nil
+    value = []    # note: value is an array of ast nodes!!!
+
+    ## check for named param e.g. hello=
+    ##  otherwise assume content
+    if input.check( /[a-z0-9 _-]+(?==)/i )  ## note: use positive lookhead (=)
+      name = input.scan( /[a-z0-9 _-]+/i )
+      name = name.strip  ## strip trailing spaces?
+      puts "        param name >#{name}<"
+      input.scan( /=/ )
+      skip_whitespaces( input )
+
+      if input.check( /\|/ ) ||
+         input.check( /\}/ )  ## add/allow }} too? - why? why not?
+        ## allow empty value!!!
+        puts "!! WARN: empty value for param >#{name}<"
+      else
+        value = parse_param_value( input )  ## get keyed param value
+        puts "        param value >#{value}<"
+      end
+    else
+      if input.check( /\|/ ) ||   ## add/allow }} too? - why? why not?
+         input.check( /\}/ )
+        ## allow empty value here too - why? why not?
+        puts "!! WARN: empty value for (unnamed/positioned) param"
+      else
+        value = parse_param_value( input )  ## get (unnamed) param value
+        puts "        param value >#{value}<"
+      end
+    end
+    [name, value]
+  end
+
+
+  def parse_param_value( input ) ## todo: change to parse_param_value_nodes or such - why? why not??
+    # puts "     [debug] parse_param_value >#{input.peek(10)}...<"
+
+    values = []  ## todo - change/rename to nodes??
+    loop do
+      values << parse_node( input )
+      skip_whitespaces( input )
+
+      ## puts "      [debug] peek >#{input.peek(10)}...<"
+      if input.check( /\|/ ) || input.check( /\}\}/ )
+        ## puts "        [debug] break param_value"
+        break
+      end
+
+      if input.eos?
+        puts "!! SYNTAX ERROR: unexpected end of string in param value; expected ending w/ | or }}"
+        exit 1
+      end
+    end
+
+    values
+  end
+
+
+  def parse_link( input )    ## todo/fix: change to parse_page - why? why not?
+    input.scan( /\[\[/ )
+
+    ## page name
+    name     = input.scan( /[^|\]]+/ ).strip
+    alt_name = if input.check( /\|/ )  ## optional alternate/display name
+                  input.scan( /\|/ )  ## eat up |
+                  input.scan( /[^\]]+/ ).strip
+               else
+                  nil
+               end
+
+    input.scan( /\]\]/ )  ## eatup ]]
+    skip_whitespaces( input )
+
+    if alt_name
+      puts " @page<#{name} | #{alt_name}>"
+    else
+      puts " @page<#{name}>"
+    end
+
+    Wikitree::Page.new( name, alt_name )
+  end
+
+
+  def parse_node( input )
+    ## puts "  [debug] parse >#{input.peek(10)}...<"
+    if input.check( TEMPLATE_BEGIN_RE )
+      parse_template( input )
+    elsif input.check( /\[\[/ )
+      parse_link( input )
+    elsif input.check( /[^|{}\[\]]+/ )    ## check for rawtext run for now
+      run = input.scan( /[^|{}\[\]]+/ ).strip
+      # puts "   text run=>#{run}<"
+      Wikitree::Text.new( run )
+    else
+      puts " !! SYNTAX ERROR: unknown content type:"
+      puts input.peek( 100 )
+      exit 1
+    end
+  end
+
+
+  def parse_lines( text )
+    ## note: remove all html comments for now - why? why not?
+    ## <!-- Area rank should match .. -->
+    text = text.gsub( /<!--.+?-->/m ) do |m|  ## note: use .+? (non-greedy match)
+                                         puts " removing comment >#{m}<"
+                                         ''
+                                       end
+
+    input = StringScanner.new( text )
+
+    nodes = []
+    loop do
+      skip_whitespaces( input )
+      break if input.eos?
+
+      nodes << parse_node( input )
+   end
+   nodes
+  end
+end # class Parser
+
+
+end # module Wikiscript

data/lib/wikiscript-parser/version.rb

@@ -0,0 +1,17 @@
+
+module Wikiscript
+module Module
+module Parser
+  VERSION = '0.0.1'
+
+   def self.banner
+     "wikiscript-parser/#{VERSION} on Ruby #{RUBY_VERSION} (#{RUBY_RELEASE_DATE}) [#{RUBY_PLATFORM}] in (#{root})"
+   end
+
+   def self.root
+     File.expand_path( File.dirname(File.dirname(File.dirname(__FILE__))) )
+   end
+
+end # module Parser
+end # module Module
+end # module Wikiscript

data/lib/wikiscript/parser.rb

@@ -0,0 +1,5 @@
+# note: allow require 'wikiscript/parser' too
+#        (in addition to require 'wikiscript-parser')
+
+require_relative '../wikiscript-parser'
+

metadata

@@ -0,0 +1,106 @@
+--- !ruby/object:Gem::Specification
+name: wikiscript-parser
+version: !ruby/object:Gem::Version
+  version: 0.0.1
+platform: ruby
+authors:
+- Gerald Bauer
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2020-11-30 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: wikitree
+  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: rdoc
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '4.0'
+    - - "<"
+      - !ruby/object:Gem::Version
+        version: '7'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '4.0'
+    - - "<"
+      - !ruby/object:Gem::Version
+        version: '7'
+- !ruby/object:Gem::Dependency
+  name: hoe
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.22'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.22'
+description: wikiscript-parser - wikitext/script parser (builds abstract syntax tree
+  'n' more)
+email: opensport@googlegroups.com
+executables: []
+extensions: []
+extra_rdoc_files:
+- CHANGELOG.md
+- Manifest.txt
+- README.md
+files:
+- CHANGELOG.md
+- Manifest.txt
+- README.md
+- Rakefile
+- lib/wikiscript-parser.rb
+- lib/wikiscript-parser/parser.rb
+- lib/wikiscript-parser/version.rb
+- lib/wikiscript/parser.rb
+homepage: https://github.com/wikiscript/wikiscript
+licenses:
+- Public Domain
+metadata: {}
+post_install_message: 
+rdoc_options:
+- "--main"
+- README.md
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: 2.2.2
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project: 
+rubygems_version: 2.5.2
+signing_key: 
+specification_version: 4
+summary: wikiscript-parser - wikitext/script parser (builds abstract syntax tree 'n'
+  more)
+test_files: []