paru 0.4.2.4 → 1.0.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 90995074101bc9a2a14e72b9e32e319ab836cf545568927f8f554939e8a7f50e
-  data.tar.gz: 2f2d91f0e45c27cae4df32267a0a98511ccfbcf28cec29f1ed0b9318de9ee5c2
+  metadata.gz: d31c824836527183bdaa118455039dcb428dfaf24b48fda1415ddc09d39cb1c0
+  data.tar.gz: 7ce8dbcb28c40c56821352df0168952535e14682d744a039ab8e281cde529aeb
 SHA512:
-  metadata.gz: 02ec89f731646faf0e0731b0fc903a5ffa6145a75b24ba01a45d13670b33709e23ee86ba571abcf813f0d9201ccdb4fccf40cc619c393832770c72c7b67b35cf
-  data.tar.gz: 4e168c11e2209cee4d108db0be97f0c24e5dcc7a59da1fe5643654b7879ad43eb33929ac33dbe1cfd10b19cde9a196b812009495b0700c0df5b7656e09b9525e
+  metadata.gz: 9866df62f18f6f929546dcd6b697b4ed8dfc6cc9c2a3a4f9d2f0623a2f79e4fff524aaf4558c185e24527987474a7e737b4ce288662e2169a6e417f7bd931de5
+  data.tar.gz: 8e18948789ae07df6ee6ee0d97c33fef28db223a5dc3e37872dc443baede147ed06858c2c980b71b367b8d64da3e770b3bd608ccfefd393972a6c5937d08b998

data/lib/paru/filter/caption.rb

@@ -61,6 +61,9 @@ module Paru
                 ]
             end
 
+            # Create an AST representation of this Node
+            #
+            # @return [Hash]
             def to_ast()
               ast_contents()
             end

data/lib/paru/filter/cell.rb

@@ -64,6 +64,9 @@ module Paru
                 ]
             end
 
+            # Create an AST representation of this Node
+            #
+            # @return [Hash]
             def to_ast()
               ast_contents()
             end

data/lib/paru/filter/int_value.rb

@@ -31,6 +31,9 @@ module Paru
             @value = value
           end
 
+          # Create an AST representation of this Node
+          #
+          # @return [Hash]
           def to_ast()
             @value
           end

data/lib/paru/filter/metadata.rb

@@ -49,7 +49,7 @@ module Paru
                     if yaml_string.empty?
                         contents = {}
                     else
-                        contents = YAML.load yaml_string, permitted_classes: [Date]
+                        contents = YAML.safe_load yaml_string, permitted_classes: [Date]
                     end
 
                     if not contents

data/lib/paru/filter/row.rb

@@ -61,6 +61,9 @@ module Paru
                 ]
             end
 
+            # Create an AST representation of this Node
+            #
+            # @return [Hash]
             def to_ast()
               ast_contents()
             end

data/lib/paru/filter/table_body.rb

@@ -72,6 +72,9 @@ module Paru
                 ]
             end
 
+            # Create an AST representation of this Node
+            #
+            # @return [Hash]
             def to_ast()
               ast_contents()
             end

data/lib/paru/filter/table_end.rb

@@ -58,6 +58,9 @@ module Paru
                 ]
             end
 
+            # Create an AST representation of this Node
+            #
+            # @return [Hash]
             def to_ast()
               ast_contents()
             end

data/lib/paru/filter.rb

@@ -1,5 +1,5 @@
 #--
-# Copyright 2015, 2016, 2017 Huub de Beer <Huub@heerdebeer.org>
+# Copyright 2015, 2016, 2017, 2022 Huub de Beer <Huub@heerdebeer.org>
 #
 # This file is part of Paru
 #
@@ -284,6 +284,11 @@ module Paru
                 end
             end
 
+            @ran_before = false
+            @ran_after = false
+            instance_eval(&block) # run filter with before block
+            @ran_before = true
+
             @current_node = @document
 
             nodes_to_filter.each do |node|
@@ -299,6 +304,9 @@ module Paru
                 instance_eval(&block) # run the actual filter code
             end
 
+            @ran_after = true
+            instance_eval(&block) # run filter with after block
+
             write_document
         end
 
@@ -308,8 +316,26 @@ module Paru
         # @param selector [String] a selector string 
         # @yield [Node] the current node if it matches the selector
         def with(selector)
-            @selectors[selector] = Selector.new selector unless @selectors.has_key? selector
-            yield @current_node if @selectors[selector].matches? @current_node, @filtered_nodes
+            if @ran_before and !@ran_after
+              @selectors[selector] = Selector.new selector unless @selectors.has_key? selector
+              yield @current_node if @selectors[selector].matches? @current_node, @filtered_nodes
+            end
+        end
+
+        # Before running the filter on all nodes, the +document+ is passed to
+        # the block to this +before+ method. This method is run exactly once.
+        #
+        # @yield [Document] the document
+        def before()
+          yield @document unless @ran_before
+        end
+
+        # After running the filter on all nodes, the +document+ is passed to
+        # the block to this +after+ method. This method is run exactly once.
+        #
+        # @yield [Document] the document
+        def after()
+          yield @document if @ran_after
         end
 
         # Stop processing the document any further and output it as it is now.
@@ -324,7 +350,6 @@ module Paru
             exit true
         end
 
-
         private
 
         # The Document node from JSON formatted pandoc document structure

data/lib/paru/info.rb

@@ -0,0 +1,90 @@
+#--
+# Copyright 2022 Huub de Beer <Huub@heerdebeer.org>
+#
+# This file is part of Paru
+#
+# Paru is free software: you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# Paru is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# 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 "error.rb"
+
+module Paru
+  # Information about pandoc
+  #
+  # @!attribute version
+  #   @return [Array<Integer>] Pandoc's version, like [2, 18, 1]
+  #
+  # @!attribute data_dir
+  #   @return [String] Pandoc's default data directory
+  #
+  # @!attribute scripting_engine
+  #   @return [String] Pandoc's internal scripting engine, like "Lua 5.4"
+  class Info
+    attr_reader :version, :data_dir, :scripting_engine
+
+    # Create a new Info object
+    #
+    # @param path [String] the path to pandoc. Defaults to 'pandoc', i.e.,
+    # assumes it's on the environment's path.
+    def initialize(path = "pandoc")
+      begin
+        # Get pandoc's version information
+        version_string = ''
+        IO.popen("#{path} --version", 'r+') do |p|
+          p.close_write
+          version_string << p.read
+        end
+
+        # Extract the version as an array of integers, like SemVer.
+        @version = version_string
+          .match(/pandoc.* (\d+\.\d+.*)$/)[1]
+          .split(".")
+          .map {|s| s.to_i}
+
+        # Extract the data directory
+        @data_dir = version_string.match(/User data directory: (.+)$/)[1]
+
+        # Extract scripting engine
+        @scripting_engine = version_string.match(/Scripting engine: (.+)$/)[1]
+      rescue StandardError => err
+        warn "Error extracting pandoc's information: #{err.message}"
+        warn "Using made up values instead."
+
+        @version = @version || [2, 18]
+        @data_dir = @data_dir || "."
+        @scripting_engine = @scripting_engine || "Lua 5.4"
+      end
+    end
+
+    # Get pandoc's info by key like a Hash for backwards compatability.
+    #
+    # @deprecated Use Info's getters instead.
+    # 
+    # @param key [String|Symbol] the key for the information to look up.
+    # Info only supports keys 'version' and 'data_dir'.
+    # @return [Any] Information associated with the key.
+    # @raise [Error] for an unknown key.
+    def [](key)
+      case key
+      when "verion", :version
+        version
+      when "data_dir", :data_dir
+        data_dir
+      when "scripting_engine", :scripting_engine
+        scripting_engine
+      else
+        throw Error.new "Info does not know key '#{key}'"
+      end
+    end
+  end
+end

data/lib/paru/pandoc.rb

@@ -1,5 +1,5 @@
 #--
-# Copyright 2015, 2016, 2017 Huub de Beer <Huub@heerdebeer.org>
+# Copyright 2015, 2016, 2017, 2022 Huub de Beer <Huub@heerdebeer.org>
 #
 # This file is part of Paru
 #
@@ -21,6 +21,7 @@ require "shellwords"
 require "yaml"
 
 require_relative "error.rb"
+require_relative "info.rb"
 
 module Paru
     # Pandoc is a wrapper around the pandoc document converter. See
@@ -92,8 +93,7 @@ module Paru
         # directory. This method is typically used in scripts that use Paru to
         # automate the use of pandoc.
         #
-        # @return [Hash{:version => Array<Integer>, :data_dir => String}] Pandoc's
-        #   version, such as "[2.10.1]" and the data directory, such as "/home/huub/.pandoc".
+        # @return [Info] Pandoc's version, such as "[2.10.1]" and the data directory, such as "/home/huub/.pandoc".
         def self.info()
             @@info
         end
@@ -216,63 +216,20 @@ module Paru
                             "pandoc"
                         end
 
-        begin
-            version_string = ''
-            IO.popen("#{@@pandoc_exec} --version", 'r+') do |p|
-                p.close_write
-                version_string << p.read
-            end
-        rescue StandardError => err
-            throw Error.new "Unable to run pandoc via command '#{@@pandoc_exec} --version': #{err.message}"
-        end
-
-        version = version_string
-                    .match(/pandoc.* (\d+\.\d+.*)$/)[1]
-                    .split(".")
-                    .map {|s| s.to_i}
-        major_version = version[0]
-
-        # Pandoc version 2.7 introduced a new default data dir to comply
-        # with XDG Base Directory Specification
-
-        xdg_data_dir, old_data_dir = version_string.match(/User data directory: (.+)$/)[1].split(" or ")
-
-        if File.directory? xdg_data_dir then
-            data_dir = xdg_data_dir
-        elsif not old_data_dir.nil? and File.directory? old_data_dir then
-            # The new-style data directory does not exist, but the
-            # old-style does, so use the old-style data directory for
-            # backwards compatibility
-            data_dir = old_data_dir
-        else
-            # Neither data directory exists, default to the new default
-            data_dir = xdg_data_dir
-        end
-
-        @@info = {
-            :version => version,
-            :data_dir => data_dir
-        }
-
-        # Load the options for the appropriate major version of pandoc
-        if not [1, 2].include? major_version 
-            throw Error.new "Unknown major pandoc version: '#{major_version}'. Expected the major version to be '1' or '2'. Please check the pandoc path: '#{@@pandoc_exec}'."
-            # defaults to version 1
-            major_version = 2
-        end
+        @@info = Info.new(@@pandoc_exec)
 
         # For each pandoc command line option a method is defined as follows:
-        OPTIONS = YAML.load_file File.join(__dir__, "pandoc_options_version_#{major_version}.yaml")
+        OPTIONS = YAML.load_file File.join(__dir__, "pandoc_options.yaml")
 
-        OPTIONS.keys.each do |option|
+        OPTIONS.each_pair do |option, default|
             if OPTIONS[option].is_a? Array then
 
                 # option can be set multiple times, for example adding multiple css
                 # files
 
-                default = OPTIONS[option][0]
-
                 define_method(option) do |value = default|
+                    value = [] if value.nil?
+
                     if @options[option].nil? then
                         @options[option] = []
                     end
@@ -291,6 +248,8 @@ module Paru
 
                 default = OPTIONS[option]
                 define_method(option) do |value = default|
+                    value = default if value.nil?
+
                     @options[option] = value
                     self
                 end

data/lib/paru/{pandoc_options_version_2.yaml → pandoc_options.yaml}

@@ -58,13 +58,14 @@ tab_stop:                   4
 track_changes:              "accept"
 extract_media:              ""
 abbreviations:              ""
+trace:                      true
 #####
 # General writing options:
 #####
-sandbox:                    false
 standalone:                 true
 template:                   ""
 variable:                   [""]
+sandbox:                    true
 print_default_template:     ""
 print_default_data_file:    ""
 eol:                        "native"
@@ -84,7 +85,7 @@ include_before_body:        [""]
 include_after_body:         [""]
 resource_path:              ""
 request_header:             ""
-no_check_certificate:       false
+no_check_certificate:       true
 #####
 # Options affecting specific writers
 #####
@@ -94,7 +95,7 @@ ascii:                      true
 reference_links:            true
 reference_location:         "block"
 markdown_headings:          "atx"
-atx_headers:                false
+atx_headers:                true
 top_level_division:         "section"
 number_sections:            true
 number_offset:              2
@@ -137,4 +138,3 @@ gladtex:                    true
 #####
 dump_args:                  true
 ignore_args:                true
-trace:                      true

data/lib/paru/selector.rb

@@ -1,5 +1,5 @@
 #--
-# Copyright 2015, 2016, 2017 Huub de Beer <Huub@heerdebeer.org>
+# Copyright 2015, 2016, 2017, 2022 Huub de Beer <Huub@heerdebeer.org>
 #
 # This file is part of Paru
 #
@@ -32,6 +32,12 @@ module Paru
     # that selector expression or not.
     class Selector
 
+        # Pseudo selector to select any inline and block node
+        ANY_SELECTOR = "*"
+
+        # All pseudo selectors
+        PSEUDO_SELECTORS = [ANY_SELECTOR]
+
         # Create a new Selector based on the selector string
         #
         # @param selector [String] the selector string
@@ -51,9 +57,14 @@ module Paru
         # @return [Boolean] True if the node in the context of the
         #   filtered_nodes is selected by this Selector
         def matches? node, filtered_nodes
-            node.type == @type and 
-                @classes.all? {|c| node.has_class? c } and    
-                @relations.all? {|r| r.matches? node, filtered_nodes}
+            case @type 
+            when ANY_SELECTOR
+              Paru::PANDOC_TYPES.include? node.type
+            else
+              node.type == @type and 
+                  @classes.all? {|c| node.has_class? c } and    
+                  @relations.all? {|r| r.matches? node, filtered_nodes}
+            end
         end
 
         private 
@@ -61,7 +72,7 @@ module Paru
         S = /\s*/
         # Improved CSS class selector taken from https://stackoverflow.com/questions/448981/which-characters-are-valid-in-css-class-names-selectors/449000#449000
         CLASS = /(\.-?[_a-zA-Z]+[_a-zA-Z0-9-]*)/
-        TYPE = /(?<type>(?<name>[A-Z][a-zA-Z]*)(?<classes>#{CLASS}*))/
+        TYPE = /(?<type>(?<name>[A-Z][a-zA-Z]*|\*)(?<classes>#{CLASS}*))/
         OTHER_TYPE = /(?<other_type>(?<other_name>[A-Z][a-zA-Z]*)(?<other_classes>#{CLASS}*))/
         OPERATOR = /(?<operator>\+|-|>)/
         DISTANCE = /(?<distance>[1-9][0-9]*)/
@@ -87,7 +98,7 @@ module Paru
 
         # Is type actually a Pandoc AST node type?
         def is_pandoc_type(type)
-            Paru::PANDOC_TYPES.include? type
+          Paru::PANDOC_TYPES.concat(PSEUDO_SELECTORS).include? type
         end
 
         def expect(parts, part)

data/lib/paru.rb

@@ -1,5 +1,5 @@
 #--
-# Copyright 2015, 2016, 2017, 2018, 2019, 2020 Huub de Beer <Huub@heerdebeer.org>
+# Copyright 2015, 2016, 2017, 2018, 2019, 2020, 2022 Huub de Beer <Huub@heerdebeer.org>
 #
 # This file is part of Paru
 #
@@ -17,6 +17,6 @@
 # Paru.  If not, see <http://www.gnu.org/licenses/>.
 #++
 module Paru
-    # Paru's current version
-    VERSION = [0, 4, 2, 4]
+  # Paru's current version
+  VERSION = [1, 0, 0].freeze
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: paru
 version: !ruby/object:Gem::Version
-  version: 0.4.2.4
+  version: 1.0.0
 platform: ruby
 authors:
 - Huub de Beer
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2021-11-04 00:00:00.000000000 Z
+date: 2022-05-29 00:00:00.000000000 Z
 dependencies: []
 description: Control pandoc with Ruby and write pandoc filters in Ruby
 email: Huub@heerdebeer.org
@@ -93,10 +93,10 @@ files:
 - lib/paru/filter/value.rb
 - lib/paru/filter/version.rb
 - lib/paru/filter_error.rb
+- lib/paru/info.rb
 - lib/paru/pandoc.rb
 - lib/paru/pandoc2yaml.rb
-- lib/paru/pandoc_options_version_1.yaml
-- lib/paru/pandoc_options_version_2.yaml
+- lib/paru/pandoc_options.yaml
 - lib/paru/selector.rb
 homepage: https://heerdebeer.org/Software/markdown/paru/
 licenses:
@@ -110,14 +110,14 @@ required_ruby_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
-      version: 2.6.8
+      version: 2.7.6
 required_rubygems_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.2.22
+rubygems_version: 3.2.3
 signing_key: 
 specification_version: 4
 summary: Paru is a ruby wrapper around pandoc

data/lib/paru/pandoc_options_version_1.yaml

@@ -1,112 +0,0 @@
-#--
-# Copyright 2015, 2016, 2017 Huub de Beer <Huub@heerdebeer.org>
-#
-# This file is part of Paru
-#
-# Paru is free software: you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation, either version 3 of the License, or
-# (at your option) any later version.
-#
-# Paru is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with Paru.  If not, see <http://www.gnu.org/licenses/>.
-# See http://pandoc.org/README.html for an overview of all options
-#++
-# Options for pandoc version 1.x, in order of occurrence in the pandoc manual.
-# General options
-from:                     ""
-read:                     ""
-to:                       ""
-write:                    ""
-output:                   ""
-data_dir:                 ""
-list_input_formats:       true
-list_output_formats:      true
-list_extensions:          true
-list_highlight_languages: true
-list_highlight_styles:    true
-version:                  true
-# Reader options
-parse_raw:                true
-smart:                    true
-old_dashes:               true
-base_header_level:        1
-indented_code_classes:    ""
-default_image_extension:  ""
-file_scope:               true
-filter:                   [""]
-metadata:                 [""]
-normalize:                true
-preserve_tabs:            true
-tab_stop:                 4
-track_changes:            "accept"
-extract_media:            true
-# General writer options
-standalone:               true
-template:                 ""
-variable:                 [""]
-print_default_template:   ""
-print_default_data_file:  ""
-dpi:                      96
-wrap:                     "auto"
-no_wrap:                  true
-columns:                  78
-toc:                      true
-table_of_contents:        true
-toc_depth:                3
-no_highlight:             true
-highlight_style:          "pygments"
-include_in_header:        [""]
-include_before_body:      [""]
-include_after_body:       [""]
-# Options affecting specific writers
-self_contained:           true
-html_q_tags:              true
-ascii:                    true
-reference_links:          true
-reference_location:       "document"
-atx_headers:              true
-chapters:                 true
-top_level_division:       "section"
-number_sections:          true
-number_offset:            "0"
-no_tex_ligatures:         true
-listings:                 true
-incremental:              true
-slide_level:              1
-section_divs:             true
-email_obfuscation:        "none"
-id_prefix:                ""
-title_prefix:             ""
-css:                      [""]
-reference_odt:            ""
-reference_docx:           ""
-epub_stylesheet:          "epub.css"
-epub_cover_image:         ""
-epub_metadata:            ""
-epub_embed_font:          ""
-epub_chapter_level:       1
-latex_engine:             "pdflatex"
-latex_engine_opt:         [""]
-# Citation rendering
-bibliography:             ""
-csl:                      ""
-citation_abbreviations:   ""
-natbib:                   true
-biblatex:                 true
-# Math rendering in HTML
-latexmathml:              ""
-mathml:                   ""
-jsmath:                   ""
-mathjax:                  ""
-gladtex:                  true
-mimetex:                  ""
-webtex:                   ""
-katex:                    ""
-katex_stylesheet:         ""
-#--