paru 0.2.5c → 0.2.5f

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: e39519f32865af110131f673e16b6e4a99f567d0
-  data.tar.gz: bfc70e18a105a8488cc4ba06b2f3cc393e7bb9b6
+  metadata.gz: 9d36825678ac43efb4419d37a42033055a161fe8
+  data.tar.gz: c639c47e276492541231e67cc3a683b4b68cc3eb
 SHA512:
-  metadata.gz: d1169e0f995d1722251fcfbb0107c386aaf6d5f0df98ead73fac6adf64276bf7715e1f4003c512186cd41d228a38f007fa26cc18cb62c033f3c69e863a570268
-  data.tar.gz: 12f8bbb1532f99347ac624b56215b2932bf56db09ac2d4a8f3583601fe5aadbc2df071ba4b183b07d1165c3e29f3e111743c677854cc967677341e62c24bcb44
+  metadata.gz: 6384ccf86bd98e102fe068f6ceee9221a54758396f96e1f3787b16d8474530d6f683df255f845de565ffd98f80cea11a6df8b11155eccd758471758845291558
+  data.tar.gz: 2220576d8c4c53fd8dfe0dd9bf5855ed82f55064ca9c87d3810dafdd418f15c7280ac54ef6b407015096319e9cb3aa00c783af5b8ccd9b90ed14df4a2c6dc150

data/bin/do-pandoc.rb

@@ -2,9 +2,7 @@
 require "yaml"
 require 'optparse'
 require "paru/pandoc"
-require_relative "./pandoc2yaml.rb"
-
-include Pandoc2Yaml
+require "paru/pandoc2yaml"
 
 parser = OptionParser.new do |opts|
   opts.banner = "do-pandoc.rb runs pandoc on an input file using the pandoc configuration specified in that input file."
@@ -44,7 +42,9 @@ if !File.readable? document
   warn "Cannot read file: #{input_document}"
   exit
 end
-metadata = YAML.load Pandoc2Yaml.extract_metadata(document)
+
+yaml = Paru::Pandoc2Yaml.extract_metadata(document)
+metadata = YAML.load yaml
 
 if metadata.has_key? "pandoc" then
   begin
@@ -65,5 +65,5 @@ if metadata.has_key? "pandoc" then
     warn "Something went wrong while using pandoc:\n\n#{e.message}"
   end
 else
-    warn "Unsure what to do: no pandoc options in #{input}"
+    warn "Unsure what to do: no pandoc options in #{input_document}"
 end

data/bin/pandoc2yaml.rb

@@ -9,86 +9,51 @@
 #  pandoc2yaml.rb input_file
 #
 ##
-module Pandoc2Yaml
-  require "json"
-  require "paru/pandoc"
+require "json"
+require 'optparse'
+require 'paru/pandoc2yaml'
 
-  # Paru converters:
-  # Note. When converting metadata back to the pandoc markdown format, you have
-  # to use the option "standalone", otherwise the metadata is skipped
-  PANDOC_2_JSON = Paru::Pandoc.new {from "markdown"; to "json"}
-  JSON_2_PANDOC = Paru::Pandoc.new {from "json"; to "markdown"; standalone}
-
-  # When converting a pandoc document to JSON, or vice versa, the JSON object
-  # has the following three properties:
-  VERSION = "pandoc-api-version"
-  META = "meta"
-  BLOCKS = "blocks"
-
-  def extract_metadata input_document
-    json = JSON.parse(PANDOC_2_JSON << File.read(input_document))
-    yaml = ""
-
-    version, metadata = json.values_at(VERSION, META)
-
-    if not metadata.empty? then
-      metadata_document = {
-        VERSION => version, 
-        META => metadata, 
-        BLOCKS => []
-      }
-
-      yaml = JSON_2_PANDOC << JSON.generate(metadata_document)
-    end
-
-    yaml
-  end
-end
-
-if __FILE__ == $0
-  include Pandoc2Yaml
-  require 'optparse'
-
-  parser = OptionParser.new do |opts|
+parser = OptionParser.new do |opts|
     opts.banner = "pandoc2yaml.rb mines a pandoc markdown file for its YAML metadata"
     opts.banner << "\n\nUsage: pandoc2yaml.rb some-pandoc-markdownfile.md"
     opts.separator ""
     opts.separator "Common options"
 
     opts.on_tail("-h", "--help", "Show this message") do
-      puts opts
-      exit
+        puts opts
+        exit
     end
 
     opts.on("-v", "--version", "Show version") do 
-      puts "pandoc2yaml.rb is part of paru version 0.2.3"
-      exit
+        puts "pandoc2yaml.rb is part of paru version 0.2.3"
+        exit
     end
-  end
+end
 
-  parser.parse! ARGV
+parser.parse! ARGV
 
-  input_document = ARGV.pop
+input_document = ARGV.pop
 
-  if ARGV.size != 0 then
+if ARGV.size != 0 or input_document.nil? or input_document.empty? then
     warn "Expecting exactly one argument: the pandoc file to strip for metadata"
     puts ""
     puts parser
     exit
-  end
+end
 
-  document = File.expand_path input_document
-  if not File.exist? document
+document = File.expand_path input_document
+if not File.exist? document
     warn "Cannot find file: #{input_document}"
     exit
-  end
+end
 
-  if !File.readable? document
+if !File.readable? document
     warn "Cannot read file: #{input_document}"
     exit
-  end
-
-  output_metadata = Pandoc2Yaml.extract_metadata document
-  
-  puts output_metadata
 end
+
+yaml = Paru::Pandoc2Yaml.extract_metadata(document)
+
+yaml = "---\n..." if yaml.empty?
+
+puts yaml

data/lib/paru.rb

@@ -17,10 +17,6 @@
 # Paru.  If not, see <http://www.gnu.org/licenses/>.
 #++
 module Paru
-    require "paru/pandoc"
-    require "paru/error"
-    require "paru/filter"
-
     # Paru's current version
-    VERSION = [0, 2, 4, 4]
+    VERSION = [0, 2, 4, 9]
 end

data/lib/paru/error.rb

@@ -16,9 +16,7 @@
 # You should have received a copy of the GNU General Public License
 # along with Paru.  If not, see <http://www.gnu.org/licenses/>.
 #++
-
 module Paru
-
     # An error class to use as a basis for paru specific errors.
     class Error < RuntimeError
     end

data/lib/paru/filter.rb

@@ -16,11 +16,11 @@
 # You should have received a copy of the GNU General Public License
 # along with Paru.  If not, see <http://www.gnu.org/licenses/>.
 #++
-module Paru
-
-    require_relative "./selector"
-    require_relative "filter/document"
+require_relative "./selector.rb"
+require_relative "./filter/document.rb"
+require_relative "./filter/metadata.rb"
 
+module Paru
     # Paru filter is a wrapper around pandoc's JSON api, which is based on
     # {pandoc-types}[https://hackage.haskell.org/package/pandoc-types-1.17.0.4/docs/Text-Pandoc-Definition.html].
     # Pandoc treats block elements and inline elements differently. 
@@ -54,6 +54,7 @@ module Paru
         "SmallCaps",
         "Quoted",
         "Cite",
+        "Code",
         "Space",
         "SoftBreak",
         "LineBreak",
@@ -104,8 +105,8 @@ module Paru
     #
     #     ![Figure 2. My second image](img/rabbit.jpeg)
     #
-    # The method {PandocFilter::Node#inner_markdown} and its counterpart
-    # {PandocFilter::Node#outer_markdown} are a great way to manipulate the
+    # The method {PandocFilter::InnerMarkdown#inner_markdown} and its counterpart
+    # {PandocFilter::Node#markdown} are a great way to manipulate the
     # contents of a selected {PandocFilter::Node}. No messing about creating
     # and filling {PandocFilter::Node}s, you can just use pandoc's own
     # markdown format!
@@ -169,8 +170,8 @@ module Paru
     #
     # == Manipulating nodes: Removing horizontal lines
     #
-    # Although the {PandocFilter::Node#inner_markdown} and
-    # {PandocFilter::Node#outer_markdown} work in most situations, sometimes
+    # Although the {PandocFilter::InnerMarkdown#inner_markdown} and
+    # {PandocFilter::Node#markdown} work in most situations, sometimes
     # direct manipulation of the pandoc document AST is useful. These
     # {PandocFilter::ASTManipulation} methods are mixed in
     # {PandocFilter::Node} and can be used on any node in your filter. For
@@ -181,9 +182,7 @@ module Paru
     #
     # Note that you could have arrived at the same effect by using:
     #
-    #     rule.outer_markdown = ""
-    #
-    # 
+    #     rule.markdown = ""
     #
     # == Manipulating metadata: 
     #
@@ -196,8 +195,14 @@ module Paru
     #
     # {include:file:examples/filters/add_today.rb}
     #
+    # In a filter, the +metadata+ property is a Ruby Hash of Strings, Numbers,
+    # Booleans, Arrays, and Hashes. You can manipulate it like any other Ruby
+    # Hash.
+    #
     class Filter
 
+        attr_reader :metadata, :document
+
         # Create a new Filter instance. For convenience, {run} creates a new
         # {Filter} and runs it immediately. Use this constructor if you want
         # to run a filter on different input and output streams that STDIN and
@@ -210,6 +215,7 @@ module Paru
         def initialize(input = $stdin, output = $stdout)
             @input = input
             @output = output
+            @running = false
         end
 
         # Run the filter specified by block. This is a convenience method that
@@ -228,15 +234,6 @@ module Paru
             Filter.new($stdin, $stdout).filter(&block)
         end
 
-        # The Document node from JSON formatted pandoc document structure
-        # on STDIN that is being filtered
-        #
-        # @return [Document] create a new Document node from a pandoc AST from
-        #   JSON from STDIN
-        def document()
-            PandocFilter::Document.from_JSON @input.read
-        end
-
         # Create a filter using +block+. In the block you specify
         # selectors and actions to be performed on selected nodes. In the
         # example below, the selector is "Image", which selects all image
@@ -257,18 +254,23 @@ module Paru
         #       end
         #   end
         #
-        #   # do something with output.string
         def filter(&block)
             @selectors = Hash.new
             @filtered_nodes = []
-            @doc = document
+            @document = read_document
+
+            @metadata = PandocFilter::Metadata.new @document.meta
 
-            @doc.each_depth_first do |node|
+            @running = true
+            @document.each_depth_first do |node|
                 @filtered_nodes.push node
                 instance_eval(&block)
+                break unless @running
             end
+            @running = false
 
-            @output.write @doc.to_JSON
+            @document.meta = @metadata.to_meta
+            @output.write @document.to_JSON
         end
 
         # +current_node+ points to the node that is *now* being processed while
@@ -289,13 +291,27 @@ module Paru
             yield current_node if @selectors[selector].matches? current_node, @filtered_nodes
         end
 
-        # While running a filter you can access the document's metadata through
-        # the +metadata+ method.
-        #
-        # @return [Meta] the filtered document's metadata
-        def metadata()
-            @doc.meta
+        # Stop processing the document any further and output it as it is now.
+        # This is a great timesaver for filters that only act on a small
+        # number of nodes in a large document, or when you only want to set
+        # the metadata.
+        def stop!()
+           @running = false 
         end
 
+        private
+
+        # The Document node from JSON formatted pandoc document structure
+        # on STDIN that is being filtered
+        #
+        # @return [Document] create a new Document node from a pandoc AST from
+        #   JSON from STDIN
+        def read_document()
+            PandocFilter::Document.from_JSON @input.read
+        end
+    end
+    
+    # FilterError is thrown when there is an error during filtering
+    class FilterError < Error
     end
 end

data/lib/paru/filter/ast_manipulation.rb

@@ -18,7 +18,6 @@
 #++
 module Paru
     module PandocFilter
-
         # ASTManipulation is a mixin for Node with some standard tree
         # manipulation methods such as inserting or removing nodes, replacing
         # nodes, and so on.

data/lib/paru/filter/attr.rb

@@ -18,7 +18,6 @@
 #++
 module Paru
     module PandocFilter
-
         # Attr represents an attribute object for a node. It contains of an id, a
         # list of class names and a list of key-value pairs. 
         #

data/lib/paru/filter/block.rb

@@ -16,10 +16,10 @@
 # You should have received a copy of the GNU General Public License
 # along with Paru.  If not, see <http://www.gnu.org/licenses/>.
 #++
+require_relative "./node.rb"
+
 module Paru
     module PandocFilter
-        require_relative "./node"
-        
         # A Block level node.
         # @see https://hackage.haskell.org/package/pandoc-types-1.17.0.5/docs/Text-Pandoc-Definition.html#t:Block
         class Block < Node

data/lib/paru/filter/block_quote.rb

@@ -16,10 +16,10 @@
 # You should have received a copy of the GNU General Public License
 # along with Paru.  If not, see <http://www.gnu.org/licenses/>.
 #++
+require_relative "./block.rb"
+
 module Paru
     module PandocFilter
-        require_relative "./block"
-
         # A BlockQuote node. Contains a list of Blocks
         class BlockQuote < Block
             # Has this node a block?

data/lib/paru/filter/bullet_list.rb

@@ -16,10 +16,10 @@
 # You should have received a copy of the GNU General Public License
 # along with Paru.  If not, see <http://www.gnu.org/licenses/>.
 #++
+require_relative "./list.rb"
+
 module Paru
     module PandocFilter
-        require_relative "./list"
-
         # BulletList, contains a list of list of Block nodes.
         class BulletList < List
         end

data/lib/paru/filter/citation.rb

@@ -16,10 +16,10 @@
 # You should have received a copy of the GNU General Public License
 # along with Paru.  If not, see <http://www.gnu.org/licenses/>.
 #--
+require_relative "./inline.rb"
+    
 module Paru
     module PandocFilter
-        require_relative "./inline"
-    
         # A Citation consists of an id, a prefix, a suffix, a mode, a note
         # number, and integer hash. All of which are optional.
         #

data/lib/paru/filter/cite.rb

@@ -16,10 +16,11 @@
 # You should have received a copy of the GNU General Public License
 # along with Paru.  If not, see <http://www.gnu.org/licenses/>.
 #++
+require_relative "./inline.rb"
+require_relative "./citation.rb"
+
 module Paru
     module PandocFilter
-        require_relative "./inline"
-
         # A Cite node, consisting of a list of Citation nodes, and a list of
         # Inline nodes
         #
@@ -32,12 +33,12 @@ module Paru
             #
             # @param contents [Array] an array containing a list of citations
             #   and a list of inline nodes
-            def initialize contents
+            def initialize(contents)
+                super contents[1]
                 @citations = []
                 contents[0].each do |citation|
                     @citations.push Citation.new(citation)
                 end
-                super contents[1]
             end
 
             # Create an AST representation of this Cite node.
@@ -47,6 +48,9 @@ module Paru
                     super
                 ]
             end
+
+            undef_method :inner_markdown
+            undef_method :inner_markdown=
         end
     end
 end

data/lib/paru/filter/code.rb

@@ -16,11 +16,11 @@
 # You should have received a copy of the GNU General Public License
 # along with Paru.  If not, see <http://www.gnu.org/licenses/>.
 #++
+require_relative "./inline.rb"
+require_relative "./attr.rb"
+
 module Paru
     module PandocFilter
-        require_relative "./inline"
-        require_relative "./attr"
-
         # A Code node, with an attribute object and the code itself as a
         # string.
         #
@@ -61,6 +61,14 @@ module Paru
             def has_inline?()
                 false
             end
+            
+            # Get the markdown representation of this Node, including the Node
+            # itself.
+            #
+            # @return [String] the outer markdown representation of this Node
+            def markdown()
+                super.strip
+            end
         end
     end
 end