magic_parser 0.0.1.pre

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA256:
+  metadata.gz: e9d21d03735ffbd01e28a9874bc023341feff0e43ab69ec7f2189b186a88f2fe
+  data.tar.gz: 70d0b3b839fa244618a252d97225fe8badbf16d82f36b17ec47ad59182872126
+SHA512:
+  metadata.gz: 4531eaabb7f3b066f0038c3a2b6779a531f244bf028a9cb04128ebbbf09ab9b5a15c5901eacd500e6cde9bfe8e2d1213db611953055df129f475c9d61c222746
+  data.tar.gz: ee3b60402f7d64c9daaaf9437f8c1985db6c574dcd6412f114156cc3edc6ff3bfc89e4943e1a8ef0cc2e118e6d2d9e5ddeca83fcf3823e263c3504b8225a41d3

data/lib/basic/basic.rb

@@ -0,0 +1,224 @@
+require 'date'
+require 'bigdecimal'
+require 'bigdecimal/util'
+
+def assert cond, msg = 'Error!'
+	if !cond then raise msg end
+end
+
+def error msg = 'Error!'
+	assert false, msg
+end
+
+def check_args var, type
+	if var.class != Array then var = [var] end
+	if type.class != Array then type = [type] end
+
+	assert (var.length == type.length), 'array lengths must match'
+
+	ctr = 0
+	while ctr < var.length
+		var[ctr].assert_type type[ctr]
+		ctr += 1
+	end
+end
+
+class Integer
+  def factorial_recursive
+    self <= 1 ? 1 : self * (self - 1).factorial
+  end
+
+  def factorial_iterative
+    f = 1; for i in 1..self; f *= i; end; f
+  end
+
+  alias :factorial :factorial_iterative
+  alias :fact :factorial
+end
+
+class Object
+	def assert_type clas, msg = nil
+		msg ||= "Bad type: expected #{clas}, got #{self.class}"
+		if !clas.kind_of? Array then clas = [clas] end
+		clas.each { |c|
+			if self.kind_of?( c ) then return; end
+		}
+		assert false, "Bad type: expected #{clas}, got #{self.class}"
+	end
+
+	def stringable?
+		respond_to? 'to_s'
+	end
+end
+
+class String
+	def pad size, char
+		size -= length
+		if size > 0 then replace self+(char*size) end
+	end
+
+	def addslashes
+		gsub(/['"\\\x0]/,'\\\\\0')
+	end
+
+	def addslashes!
+		replace addslashes
+	end
+
+	def write filename = nil
+		write_file( filename ){ self }
+	end
+end
+
+def write_file filename = nil
+	file = filename ? File.open( filename, 'w' ) : Tempfile.new( filename )
+
+	file.print yield
+	file.close
+end
+
+class Array
+	def find
+		ctr = 0
+		each { |e|
+			if yield( e )
+				return ctr
+			end
+		}
+
+		nil
+	end
+
+	def prep_insert table
+		set = []
+
+		each { |line|
+			set = "( #{line.join ','} )"
+		}
+
+		set = "insert into #{table} values ( #{set.join ','} ),"
+	end
+
+	def assert_all_types clas, msg = nil
+		each { |x|
+			x.assert_type clas, msg
+		}
+	end
+
+	def contains? *elements
+		elements.each { |element|
+			if !include?( element ) then return false end
+		}
+		true
+	end
+
+	# buggy Ruby is supposed to do this already...
+	def to_s
+		collect { |x|
+			x.to_s
+		}.join
+	end
+end
+
+class Stack < Array
+	def push x
+	end
+
+	def pop
+	end
+end
+
+#class Queue < Array
+#	def nxt
+#	end
+
+#	def add x
+#	end
+#end
+
+class Hash
+	def defaults defs
+		defs.assert_type Hash
+
+		keyset = keys
+		defs.each { |k, v|
+			if !keyset.include? k then self[k] = v end
+		}
+	end
+
+	def prep_insert table
+		set = []
+
+		each { |k, v|
+			set = "( #{k}, #{v} )"
+		}
+
+		set = "insert into #{table} values ( #{set.join ','} ),"
+	end
+
+	def select *items
+		r = {}
+
+		items.each { |item|
+			r[item] = self[item]
+		}
+
+		r
+	end
+
+	def create_path *path
+		entry = self
+		endcap = path.pop
+		final = path.pop
+
+		path.each { |e|
+			if !entry[e] then entry[e] = {} end
+			entry = entry[e]
+		}
+
+		if !entry[final] then entry[final] = endcap end
+	end
+
+	def required *elements
+		elements.each { |element|
+			assert has_key?( element ), "required key missing: #{element}"
+		}
+	end
+end
+
+class Value
+	attr_accessor :value
+
+	def initialize v = 0
+		set v
+	end
+
+	def set x
+		x.assert_type Numeric
+		@value = Float.new x
+	end
+
+	def to_i
+		@value.to_i
+	end
+
+	def to_f
+		@value
+	end
+end
+
+class Date
+	def american sep = '/'
+		"%02d#{sep}%02d#{sep}%02d" % [month, day, year]
+	end
+end
+
+class Time
+	def Time.stamp
+		n = Time.now
+		"%d%02d%02d-%02d%02d%02d" % [n.year, n.month, n.day, n.hour, n.min, n.sec]
+	end
+end
+
+class FileName < String
+end

data/lib/magic_parser.rb

@@ -0,0 +1,218 @@
+=begin
+parser = {
+	'name' => [/pattern/, {subparser}
+	...
+	]
+}
+
+# token
+parsed
+	text, name, [breakdown]
+=end
+
+require 'basic/basic'
+
+class Token < Array
+	attr_accessor :text, :name
+
+	def initialize n = nil, t = nil
+		check_args [n, t], [[String, NilClass], [String, NilClass]]
+
+		@name, @text, @@tab = n, t, 0
+
+		update
+	end
+
+	def print_verbose
+		print true
+	end
+
+	def print verbose = false
+		out = ''
+
+		if name || verbose
+			val = @@tab
+			if !verbose then val -= 1 end
+			out += "\t" * val
+			out += "#{name} |#{text}|\n"
+		end
+
+		@@tab += 1
+		each { |s|
+			out += s.print verbose
+		}
+		@@tab -= 1
+
+		out
+	end
+
+	def to_s
+		update
+	end
+
+	def update
+		if length == 0
+			return text
+		end
+
+		text = ''
+
+		each { |t|
+			text += t.update
+		}
+
+		text
+	end
+
+	def write filename = nil
+		write_file( filename ){ to_s }
+	end
+end
+
+class Rule
+	attr_reader :name, :subrule, :pattern
+
+	def initialize n, pa = /.*/, s = {}
+		check_args [n, pa], [String, Regexp]
+
+		@pattern = pa
+		@name = n
+
+		if block_given?
+			s = yield
+		end
+		s.assert_type Hash
+
+		@subrule = RuleSet.new( s )
+	end
+
+	def to_s
+		out = "Rule: #{name}, pattern: #{pattern}, subrules: #{subrule.length}\n"
+		subrule.each { |name, s|
+			out += s.to_s
+		}
+		out
+	end
+
+	def apply token
+		token.assert_type Token
+
+		result = token.dup.clear
+
+		if token.length == 0
+			token << Token.new( nil, token.text )
+		end
+
+		token.each { |subtoken|
+			if subtoken.name
+				result << subtoken
+			else
+				cursor = 0
+				subtoken.text.encode!('UTF-8', 'binary', invalid: :replace, undef: :replace, replace: '')
+				r = subtoken.text.scan pattern
+
+				r.each { |match|
+					if match.kind_of? Array
+						match = match[0]
+					end
+
+					offset = subtoken.text.index match, cursor
+					if offset != cursor
+						text = subtoken.text.slice(cursor .. offset-1)
+						result << Token.new( nil, text )
+						cursor = offset
+					end
+
+					offset = cursor + match.length
+					text = subtoken.text.slice(cursor .. offset-1)
+					new_subtoken = Token.new( name, text )
+
+					if subrule
+						new_subtoken = subrule.apply( new_subtoken )
+					end
+
+					result << new_subtoken
+					cursor = offset
+				}
+
+				if cursor < subtoken.text.length
+					text = subtoken.text.slice(cursor .. -1)
+					result << Token.new( nil, text )
+				end
+			end
+		}
+
+		result
+	end
+end
+
+class RuleSet < Hash
+	def initialize rules = {}
+		if block_given?
+			rules = yield
+		end
+
+		rules.assert_type Hash
+
+		rules.each { |name, rule|
+			pattern, subrule = rule
+			if !subrule
+				subrule = {}
+		  end
+			self[name] = Rule.new( name, pattern, subrule )
+		}
+	end
+
+	def to_s
+		out = ''
+		each { |name, rule|
+			out += "#{rule}\n"
+		}
+		out
+	end
+
+	def apply token
+		if token.kind_of? String
+			token = Token.new( token )
+		end
+
+		token.assert_type Token
+
+		each { |name, rule|
+			token = rule.apply token
+		}
+
+		token
+	end
+
+	def parse text: '', file: nil
+		Parser.parse text, file
+	end
+
+	def RuleSet.parse text: '', file: nil
+		check_args [text, file], [String, [String, NilClass]]
+
+		if file
+			text = File.read( file )
+		end
+
+		apply Token.new( nil, text.force_encoding('UTF-8') )
+	end
+end
+
+class Parser < RuleSet
+end
+
+class Document < Token
+	@@parser = nil
+
+	def initialize text: '', file: nil
+		check_args [text, file], [String, [String, NilClass]]
+
+		assert @@parser, 'Parser must be assigned'
+
+		result = @@parser.parse( text: text, file: file )
+		concat result
+		super result.name, result.text
+	end
+end

data/readme.md

@@ -0,0 +1,175 @@
+parser
+======
+
+The parser gem provides an easy way to do most simple parsing of text files. The grammar for a file format is written as a hierarchy of regular expression/tag pairs. Here is an example taken from the definition of xml:
+
+xml.rb
+
+require 'magic_parser'
+
+class XMLParser < Parser
+	def initialize
+		# XML definition
+		attr_value_w_space = "([\\'\"]?\\s*[\\w\\-\\.\/: ]+\\s*[\\'\"]?)"
+		attr_value_no_space = "(\\s*[\\w\\-\\.\/:]+\\s*)"
+		attr_name = "([\\w:-]+)"
+		tag_name = attr_name
+		attr_value = "(#{attr_value_w_space}|#{attr_value_no_space})"
+		attribute = "#{attr_name}\\s*\\=\\s*#{attr_value}"
+
+		super() { {
+			'tag' => [ /\s*(\<\??\s*#{tag_name}(\s*#{attribute}\s*)*\/?\s*\??\>)\s*/, {
+				'name' => /\<\??\s*#{tag_name}/,
+				'attribute' => [ /\s*(#{attribute})\s*/, {
+					'name' => /(#{attr_name})\s*\=/,
+					'value' => /\=\s*#{attr_value}/
+				}]
+			}],
+			'close_tag' => [ /\s*(\<\s*\/#{tag_name}\s*\>)\s*/, {
+				'name' => /\<\s*\/#{tag_name}/
+			}],
+			'content' => /\s*(\w.*)/
+		} }
+	end
+end
+
+class XML < Document
+	@@parser = XMLParser.new
+end
+
+With this you can parse a simple bit of text:
+
+text = '<?xml version="1.0" encoding="UTF-8"?>'
+
+xml = XML.new( text: text )
+
+or an entire file. For a file called data.xml:
+
+<?xml version="1.0" encoding="UTF-8"?>
+<catalog>
+  <cd>
+    <title>Empire Burlesque</title>
+    <artist>Bob Dylan</artist>
+    <country>USA</country>
+    <company>Columbia</company>
+    <price>10.90</price>
+    <year>1985</year>
+  </cd>
+</catalog>
+
+your code can look like:
+
+require 'xml'
+
+catalog = XML.new 'data.xml'
+catalog.print
+
+which will output:
+
+tag, |<?xml version="1.0" encoding="UTF-8"?>|
+	name, |xml|
+	attribute, |version="1.0"|
+		name, |version|
+		value, |"1.0"|
+	attribute, |encoding="UTF-8"|
+		name, |encoding|
+		value, |"UTF-8"|
+tag, |<catalog>|
+	name, |catalog|
+tag, |<cd>|
+	name, |cd|
+tag, |<title>|
+	name, |title|
+content, |Empire Burlesque|
+close_tag, |</title>|
+	name, |title|
+tag, |<artist>|
+	name, |artist|
+content, |Bob Dylan|
+close_tag, |</artist>|
+	name, |artist|
+tag, |<country>|
+	name, |country|
+content, |USA|
+close_tag, |</country>|
+	name, |country|
+tag, |<company>|
+	name, |company|
+content, |Columbia|
+close_tag, |</company>|
+	name, |company|
+tag, |<price>|
+	name, |price|
+content, |10.90|
+close_tag, |</price>|
+	name, |price|
+tag, |<year>|
+	name, |year|
+content, |1985|
+close_tag, |</year>|
+	name, |year|
+close_tag, |</cd>|
+	name, |cd|
+close_tag, |</catalog>|
+	name, |catalog|
+
+The Token class is an Array of Tokens and has 'name' and 'text' attributes. A Document is a kind of Token. You can iterate through the parsed file examining and editing tags and content. Given the prior code:
+
+# print a list of titles and artists
+catalog.each {|title|
+	puts title.name
+	puts title.text
+
+	index = 0
+	title.each {|field|
+		if field.name == 'tag' && field[0].name == 'artist'
+			# this should be the artist name
+			puts title[index+1].text
+		end
+		index += 1
+	}
+}
+
+It is important to note that in definitions order matters! The most specific cases must be matched before the more general ones.
+
+Features
+--------
+- definitions are entirely based on regular expressions
+- definitions are stored as hash trees, so they can build on each other (e.g. HTML can be defined as an extension of XML)
+
+Future Expansion
+----------------
+
+This will be the basis for further projects such as an xslt processor. A logical next step will be to add XPath features.
+
+Installation
+------------
+
+Install parser by running:
+
+	sudo gem install magic_parser
+
+Contribute
+----------
+
+- Issue Tracker: github.com/$project/$project/issues
+- Source Code: github.com/$project/$project
+
+Support
+-------
+
+If you are having issues, please let us know.
+We have a mailing list located at: project@google-groups.com
+
+License
+-------
+
+(The MIT License)
+
+Copyright � Paul Amirian
+
+Permission is hereby granted, free of charge, to any person obtaining a copy of this software and associated documentation files (the 'Software'), to deal in the Software without restriction, including without limitation the rights to use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies of the Software, and to permit persons to whom the Software is furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED 'AS IS', WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

data/test/xml/xml.rb

@@ -0,0 +1,31 @@
+require 'magic_parser'
+
+class XMLParser < Parser
+	def initialize
+		# XML definition
+		attr_value_w_space = "([\\'\"]?\\s*[\\w\\-\\.\/: ]+\\s*[\\'\"]?)"
+		attr_value_no_space = "(\\s*[\\w\\-\\.\/:]+\\s*)"
+		attr_name = "([\\w:-]+)"
+		tag_name = attr_name
+		attr_value = "(#{attr_value_w_space}|#{attr_value_no_space})"
+		attribute = "#{attr_name}\\s*\\=\\s*#{attr_value}"
+
+		super() { {
+			'tag' => [ /\s*(\<\??\s*#{tag_name}(\s*#{attribute}\s*)*\/?\s*\??\>)\s*/, {
+				'name' => /\<\??\s*#{tag_name}/,
+				'attribute' => [ /\s*(#{attribute})\s*/, {
+					'name' => /(#{attr_name})\s*\=/,
+					'value' => /\=\s*#{attr_value}/
+				}]
+			}],
+			'close_tag' => [ /\s*(\<\s*\/#{tag_name}\s*\>)\s*/, {
+				'name' => /\<\s*\/#{tag_name}/
+			}],
+			'content' => /\s*(\w.*)/
+		} }
+	end
+end
+
+class XML < Document
+	@@parser = XMLParser.new
+end

data/test/xml/xml_test.rb

@@ -0,0 +1,14 @@
+#! /usr/bin/ruby
+
+$: << '.'
+
+require 'xml'
+
+text = '<?xml version="1.0" encoding="UTF-8"?>'
+
+#xml = XML.new( text: text )
+#xml = XML.new( file: 'form.xsl' )
+xml = XML.new( file: 'data.xml' )
+
+puts xml.print 
+# puts xml.to_s

metadata

@@ -0,0 +1,47 @@
+--- !ruby/object:Gem::Specification
+name: magic_parser
+version: !ruby/object:Gem::Version
+  version: 0.0.1.pre
+platform: ruby
+authors:
+- Digital Magic
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2019-04-11 00:00:00.000000000 Z
+dependencies: []
+description: 
+email: 
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- lib/basic/basic.rb
+- lib/magic_parser.rb
+- readme.md
+- test/xml/xml.rb
+- test/xml/xml_test.rb
+homepage: 
+licenses:
+- MIT
+metadata: {}
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">"
+    - !ruby/object:Gem::Version
+      version: 1.3.1
+requirements: []
+rubygems_version: 3.0.1
+signing_key: 
+specification_version: 4
+summary: regex-based parser
+test_files: []