plurimath 0.8.11 → 0.8.13

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 2125384d29ad98d919d7fd71cebaf3e5fdc6ffc1aa8df386f3b63f20754ae6bb
-  data.tar.gz: 64a002bc99ed60eada7e7a59df1f0bfa083eaa4427efdb0ec2fbe615db33f851
+  metadata.gz: cd471ff00338f1235d74433502b5589c0b95287f196c0088be89cbc91e65a456
+  data.tar.gz: 3f30ce7bd235c3e9c07768240ffafea84e93f63c0da3ae442b2687ad7b2b7f95
 SHA512:
-  metadata.gz: a88aae5ca0beb6e36de8f3e025241cb291cb2d8c44faeeb2325ea4a2276ca6c93b32176484d7698a6818cf5f05e76f3a8b0fad829ed657f417a7fda183726ba9
-  data.tar.gz: fb521143940cab36ef15320d65aad971e56e150776229809fa9bdd1014847ac36cfef09fc55f2e182338ee2e1e2a6d13f086eb0a285d01e51b847df1c07cbe53
+  metadata.gz: 83007b138c9c86561350991289d7007d42b7aa24859f8039c961c7e2434f1f1b381d3e4f85f897bc3c5c1b1f4d22cb4ddf7257bb9f136a0c465695995ba72690
+  data.tar.gz: 6b019a7ed611f78e28c0e62473b4e8ee0780568de8b304fed12f9957fde6aebc7f88f30c4656ddd6500f7ef298462616d5fba6fd6d2e9fc3b03f24be1ef8fde4

data/README.adoc

@@ -61,16 +61,91 @@ Or install it yourself with:
 $ gem install plurimath
 ----
 
-== Usage
+== Command Line Interface (CLI) usage
+
+=== General
+
+Plurimath provides a Command Line Interface (CLI) tool for converting between
+different math formats.
+
+NOTE: Before continuing please ensure you have the gem installed.
+
+To convert math equations between formats, use the following command followed by
+appropriate options.
+
+[source,bash]
+----
+plurimath convert [options]
+----
+
+Options available are:
+
+`-i`, `--input <INPUT>`::
+Specifies the input math equation. Should be provided within double quotes.
+
+`-f`, `--input-format <FORMAT>`::
+Specifies the input format of the equation. Defaults to `asciimath`.
+
+`-p`, `--file-path <FILE_PATH>`::
+Reads input from a file instead of the command line input. Use this for larger
+inputs or when input contains special characters.
+
+`-t`, `--output-format <FORMAT>`::
+Specifies the output format type. Defaults to `mathml`.
+
+`-m`, `--math-rendering`::
+Renders the converted equation as a math zone display tree. Boolean option
+(`true`, `false`).
+
+`-d`, `--display-style`::
+Specifies the DisplayStyle for OMML and MathML outputs only. Boolean option
+(`true`, `false`).
+
+`-s`, `--split-on-linebreak`::
+Splits MathML and OMML output into multiple equations. Boolean option (`true`,
+`false`).
+
+
+=== Convert an AsciiMath equation to MathML
+
+[source,bash]
+----
+plurimath convert -i "sqrt(x^2 + y^2)" -f asciimath -t mathml
+----
+
+=== Convert an OMML equation to MathML with DisplayStyle
+
+[source,bash]
+----
+plurimath convert -i "equation" -f omml -t mathml -d true
+----
+
+=== Convert equations from a file and output as UnicodeMath
+
+[source,bash]
+----
+plurimath convert -e <file_path> -t unicodemath
+----
+
+For more detailed information and additional options, use:
+
+[source,bash]
+----
+plurimath help convert
+----
+
+
+== Ruby API
+
 
 The central data model in Plurimath is the `Plurimath::Formula` class, which
 allows you to transform any math representation language into any other
 representation language.
 
 
-=== Conversion Examples
+=== Conversion examples
 
-==== AsciiMath Formula Example
+==== AsciiMath Formula example
 
 [source,ruby]
 ----
@@ -78,7 +153,7 @@ asciimath = "sin(1)"
 formula = Plurimath::Math.parse(asciimath, :asciimath)
 ----
 
-==== MathML Formula Example
+==== MathML Formula example
 
 [source,ruby]
 ----
@@ -93,7 +168,7 @@ MATHML
 formula = Plurimath::Math.parse(mathml, :mathml)
 ----
 
-==== LaTeX Formula Example
+==== LaTeX Formula example
 
 [source,ruby]
 ----
@@ -101,7 +176,7 @@ latex = "\\sin{1}"
 formula = Plurimath::Math.parse(latex, :latex)
 ----
 
-==== UnicodeMath Formula Example
+==== UnicodeMath Formula example
 
 [source,ruby]
 ----
@@ -109,7 +184,7 @@ unicodemath = "sin(1)"
 formula = Plurimath::Math.parse(unicodemath, :unicodemath)
 ----
 
-==== OMML Formula Example
+==== OMML Formula example
 
 [source,ruby]
 ----
@@ -137,13 +212,14 @@ OMML
 formula = Plurimath::Math.parse(omml, :omml)
 ----
 
-=== Converting to Other Formats
+
+=== Converting to other formats
 
 Once you have a `Plurimath::Math::Formula` object, you can convert it to
 AsciiMath, MathML, LaTeX, UnicodeMath, or OMML by calling the respective
 conversion function on the `Formula` object.
 
-==== AsciiMath Output Conversion
+==== AsciiMath output conversion
 
 [source,ruby]
 ----
@@ -157,7 +233,7 @@ that LaTeX does. During conversion from LaTeX to AsciiMath, if a symbol is not
 supported in AsciiMath, the LaTeX symbol will be returned.
 
 
-==== LaTeX Output Conversion
+==== LaTeX output conversion
 
 [source,ruby]
 ----
@@ -165,7 +241,7 @@ formula.to_latex
 # => "\\sin1"
 ----
 
-==== MathML Output Conversion
+==== MathML output conversion
 
 [source,ruby]
 ----
@@ -173,7 +249,7 @@ formula.to_mathml
 # => "<math xmlns='http://www.w3.org/1998/Math/MathML'><mstyle displaystyle='true'><mi>sin</mi><mn>1</mn></mstyle></math>"
 ----
 
-==== UnicodeMath Output Conversion
+==== UnicodeMath output conversion
 
 [source,ruby]
 ----
@@ -181,7 +257,7 @@ formula.to_unicodemath
 # => "sin(1)"
 ----
 
-==== OMML Output Conversion
+==== OMML output conversion
 
 [source,ruby]
 ----
@@ -189,7 +265,8 @@ formula.to_omml
 # => "<m:oMathPara xmlns:m=\"http://schemas.openxmlformats.org/officeDocument/2006/math\"><m:oMath><m:f><m:fPr><m:ctrlPr /></m:fPr><m:num><m:r><m:t>sin</m:t></m:r></m:num><m:den><m:r><m:t>1</m:t></m:r></m:den></m:f></m:oMath></m:oMathPara>"
 ----
 
-== Handling Complex Mathematical Expressions
+
+==== Complex mathematical expressions
 
 Plurimath is capable of handling complex mathematical expressions with nested
 functions and operators.
@@ -197,9 +274,7 @@ functions and operators.
 This feature is particularly useful for application that requires consistent and
 accurate conversion of intricate mathematical content.
 
-=== Example of a Complex Expression
-
-Consider the following complex LaTeX expression:
+Example. Consider the following complex LaTeX expression:
 
 [source,latex]
 ----
@@ -232,13 +307,14 @@ omml = formula.to_omml
 
 
 
+== Math parse trees
 
-== Displaying the Math Parse Tree
+=== General
 
 Plurimath allows you to display the math parse tree both as `Formula` objects
 and in the math language of expression.
 
-=== Displaying as Formula Objects
+=== Displaying as Formula objects
 
 You can display the parse tree as `Formula` objects to understand the structure
 of the parsed mathematical expression.
@@ -246,14 +322,11 @@ of the parsed mathematical expression.
 [source,ruby]
 ----
 formula = Plurimath::Math.parse("sin(1)", :asciimath)
-formula.to_display(:asciimath)
-# |_ Math zone
-#   |_ "sin(1)"
-#      |_ "sin" function apply
-#         |_ "1" argument
+formula.to_display(:formula)
+# ...
 ----
 
-=== Displaying in the Math Language of Expression
+=== Displaying in the math language of expression
 
 You can also display the parse tree in the math language of expression to see
 how the expression is represented in that language.
@@ -261,11 +334,25 @@ how the expression is represented in that language.
 [source,ruby]
 ----
 formula = Plurimath::Math.parse("sin(1)", :asciimath)
+formula.to_display(:asciimath)
+# |_ Math zone
+#   |_ "sin(1)"
+#      |_ "sin" function apply
+#         |_ "1" argument
+
 formula.to_display(:latex)
 # |_ Math zone
 #   |_ "\\sin1"
 #      |_ "sin" function apply
 #         |_ "1" argument
+
+formula.to_display(:mathml)
+# |_ Math zone
+#   |_ "<math xmlns="http://www.w3.org/1998/Math/MathML" display="block"><mstyle displaystyle="true"><mrow><mi>sin</mi><mrow><mo>(</mo><mn>1</mn><mo>)</mo></mrow></mrow></mstyle></math>"
+#      |_ "<mrow><mi>sin</mi><mrow><mo>(</mo><mn>1</mn><mo>)</mo></mrow></mrow>" function apply
+#         |_ "sin" function name
+#         |_ "<mrow><mo>(</mo><mn>1</mn><mo>)</mo></mrow>" argument
+#            |_ "<mtext>1</mtext>" text
 ----
 
 // == Integration
@@ -311,11 +398,11 @@ h = 6.62607015 xx 10^(-34) "unitsml(kg*m^2*s^(-1))"
 
 ==== Step-by-Step Customization
 
-. **Parse the UnitsML Expression**
-. **Customize and Convert to AsciiMath**
-. **Customize and Convert to MathML**
-. **Customize and Convert to UnicodeMath**
-. **Customize and Convert to OMML**
+. Parse the UnitsML Expression
+. Customize and Convert to AsciiMath
+. Customize and Convert to MathML
+. Customize and Convert to UnicodeMath
+. Customize and Convert to OMML
 
 ==== Parse the UnitsML Expression
 
@@ -341,7 +428,7 @@ puts asciimath
 # Output: 'h = 6.62607015 xx 10^(-34) "unitsml(kg*m^2*s^(-1))"'
 ----
 
-==== Customize and Convert to MathML
+==== Customize and convert to MathML
 
 To customize the MathML output, you can use additional attributes and options:
 
@@ -353,7 +440,7 @@ puts mathml
 # Output: "<math xmlns='http://www.w3.org/1998/Math/MathML'><mrow><mi>h</mi><mo>=</mo><mn>6.62607015</mn><mo>×</mo><msup><mn>10</mn><mrow><mo>−</mo><mn>34</mn></mrow></msup><mtext>kg·m²·s⁻¹</mtext></mrow></math>"
 ----
 
-==== Customize and Convert to UnicodeMath
+==== Customize and convert to UnicodeMath
 
 Similarly, customize the UnicodeMath output:
 
@@ -365,7 +452,7 @@ puts unicodemath
 # Output: 'h = 6.62607015 × 10^(−34) kg·m²·s⁻¹'
 ----
 
-==== Customize and Convert to OMML
+==== Customize and convert to OMML
 
 For OMML output, you can customize the XML structure:
 
@@ -377,7 +464,7 @@ puts omml
 # Output: "<m:oMathPara xmlns:m='http://schemas.openxmlformats.org/officeDocument/2006/math'><m:oMath><m:r><m:t>h</m:t></m:r><m:r><m:t>=</m:t></m:r><m:r><m:t>6.62607015</m:t></m:r><m:r><m:t>×</m:t></m:r><m:sSup><m:sSupPr><m:ctrlPr /></m:sSupPr><m:e><m:r><m:t>10</m:t></m:r></m:e><m:sup><m:r><m:t>−34</m:t></m:r></m:sup></m:sSup><m:r><m:t>kg·m²·s⁻¹</m:t></m:r></m:oMath></m:oMathPara>"
 ----
 
-=== Complete Example Code with Customization
+=== Complete example code with customization
 
 Here's the complete code for parsing, converting, and customizing the UnitsML
 expression between different formats:
@@ -434,7 +521,7 @@ as a text string of `"__{symbol-name}"`. Plurimath can recognize it, but other
 renderers or processors would treat it as a single symbol, which is accurate.
 
 
-=== Example of Compatibility Wrapper
+=== Usage of the compatibility wrapper
 
 For a symbol like `backepsilon`.
 
@@ -466,12 +553,13 @@ In MathML:
 <mi>∍</mi>
 ----
 
-== XML Engines
 
-**Plurimath** supports two XML engines:
+== XML engines
+
+Plurimath supports two XML engines:
 
+. **Ox**: (default) A fast XML parser
 . **Oga**: A pure Ruby XML parser
-. **Ox**: A fast XML parser
 
 By default, **Ox** is used.
 
@@ -479,12 +567,13 @@ To switch to **Oga**, use the following syntax:
 
 [source,ruby]
 ----
-require "plurimath/xml_engines/oga" = load files related to Oga
-Plurimath.xml_engine = Plurimath::XmlEngine::Oga = set Oga as Plurimath XML engine
+require "plurimath/xml_engines/oga"
+Plurimath.xml_engine = Plurimath::XmlEngine::Oga
 ----
 
 You can switch back to **Ox** similarly.
 
+
 === Supported content
 
 === General

data/exe/plurimath

@@ -0,0 +1,4 @@
+#!/usr/bin/env ruby
+require "plurimath/cli"
+
+Plurimath::Cli.start(ARGV)

data/lib/plurimath/asciimath/constants.rb

@@ -102,17 +102,9 @@ module Plurimath
           @@symbols ||= Utility.symbols_hash(:asciimath).keys.concat(parens_symbols)
         end
 
-        def wrapper_symbols
-          symbols_array.grep(/__{/)
-        end
-
         def parens_symbols
           Utility.parens_hash(:asciimath).keys.delete_if { |sym| SKIP_INPUT_PARENS.include?(sym) }
         end
-
-        def absent_symbols
-          wrapper_symbols.concat(parens_symbols)
-        end
       end
     end
   end

data/lib/plurimath/asciimath/parse.rb

@@ -5,7 +5,7 @@ module Plurimath
   class Asciimath
     class Parse < Parslet::Parser
       rule(:td)     { expression.as(:td) }
-      rule(:base)   { arr_to_expression(Constants.absent_symbols, :symbol).absent? >> str("_") }
+      rule(:base)   { str("__|").absent? >> str("_") }
       rule(:power)  { str("^") }
       rule(:space)  { match(/\s+/) }
       rule(:comma)  { (str(",") >> space?) }

data/lib/plurimath/cli.rb

@@ -0,0 +1,84 @@
+# frozen_string_literal: true
+
+require "thor"
+
+module Plurimath
+  self.autoload :Math, "plurimath/math"
+
+  class Cli < Thor
+    desc "convert", "Convert between math formats"
+
+    option :input,
+           aliases: "-i",
+           desc: "Input value should be in quoted string"
+
+    option :input_format,
+           aliases: "-f",
+           default: "asciimath",
+           desc: "Input format should be in quoted string => \"asciimath\""
+
+    option :file_path,
+           aliases: "-p",
+           desc: "Reads input from a file instead of the command line input. Use this for larger inputs or when input contains special characters.",
+           force: :boolean
+
+    option :output_format,
+           aliases: "-t",
+           default: "mathml",
+           desc: "Convert to language type, Output format should be in quoted string"
+
+    option :math_rendering,
+           aliases: "-m",
+           force: :boolean,
+           default: 'false',
+           desc: "Render converted equation as math zone display tree, Boolean only"
+
+    option :display_style,
+           aliases: "-d",
+           desc: "DisplayStyle is only supported for OMML and MathML conversion, Boolean only",
+           force: :boolean
+
+    option :split_on_linebreak,
+           aliases: "-s",
+           desc: "Splits only MathML and OMML equations into multiple equations, Boolean only",
+           force: :boolean
+
+    def convert
+      input          = options[:input]
+      input_string   = options[:file_path] ? File.read(options[:file_path]) : input
+      warn_and_exit("missing generator argument --input or --file-input") unless input_string
+
+      input_format   = options[:input_format]
+      output_format  = options[:output_format]
+      formula        = Plurimath::Math.parse(input_string, input_format)
+      return puts formula.to_display(output_format.to_sym) if YAML.safe_load(options[:math_rendering])
+
+      display_style  = options[:display_style]
+      split          = options[:split_on_linebreak]
+      style          = display_style.to_s.empty? ? "true" : display_style
+      output_text = case output_format
+                    when "unicodemath"
+                      formula.to_unicodemath
+                    when "asciimath"
+                      formula.to_asciimath
+                    when "mathml"
+                      formula.to_mathml(display_style: style, split_on_linebreak: split)
+                    when "latex"
+                      formula.to_latex
+                    when "omml"
+                      formula.to_omml(display_style: style, split_on_linebreak: split)
+                    else
+                      warn_and_exit("Invalid output format: #{output_format}")
+                    end
+
+      puts output_text
+    end
+
+    no_commands do
+      def warn_and_exit(message)
+        warn(message)
+        exit 1
+      end
+    end
+  end
+end

data/lib/plurimath/latex/constants.rb

@@ -236,10 +236,6 @@ module Plurimath
           reverse_sort_hash(@@parens)
         end
 
-        def wrapper_symbols
-          symbols_hash.keys.grep(/__{/)
-        end
-
         private
 
         def symbols_hash

data/lib/plurimath/latex/parse.rb

@@ -4,7 +4,7 @@ require "parslet"
 module Plurimath
   class Latex
     class Parse < Parslet::Parser
-      rule(:base)          { arr_to_expression(Constants.wrapper_symbols, :symbols).absent? >> str("_") }
+      rule(:base)          { str("_") }
       rule(:power)         { str("^") }
       rule(:slash)         { str("\\") }
       rule(:under_over)    { slash >> underover_classes }
@@ -207,7 +207,7 @@ module Plurimath
         when :operant
           (first_value.as(:operant) | (slashed_value(first_value, :symbols)))
         when :symbols
-          expr.to_s.start_with?("__{") ? first_value.as(name) : slashed_value(first_value, :symbols)
+          slashed_value(first_value, :symbols)
         when :unary
           unary_rules(first_value)
         when :fonts

data/lib/plurimath/latex/parser.rb

@@ -8,17 +8,10 @@ module Plurimath
     class Parser
       attr_accessor :text
 
+      TEXT_REGEX = %r(\\(?:mbox|text){[^}]+})
+
       def initialize(text)
-        enti = HTMLEntities.new
-        text = enti.encode(enti.decode(text), :hexadecimal)
-        text = text
-          .gsub(/((?<!\\) )|\n+/, "")
-          .gsub(/\\\\ /, "\\\\\\\\")
-          .gsub(/&#x26;/, "&")
-          .gsub(/&#x22;/, "\"")
-          .gsub(/(?<!\\\\)\\&#xa;/, "\\ ")
-          .gsub(/&#xa;/, "")
-        @text = text
+        @text = pre_processing(text)
       end
 
       def parse
@@ -28,6 +21,26 @@ module Plurimath
 
         Math::Formula.new(formula)
       end
+
+      private
+
+      def pre_processing(text)
+        text_functions = text.scan(TEXT_REGEX)
+        enti = HTMLEntities.new
+        text = enti.encode(enti.decode(text), :hexadecimal)
+        text = gsub_space_and_unicodes(text)
+        text.gsub(TEXT_REGEX) { |str| text_functions.shift }
+      end
+
+      def gsub_space_and_unicodes(text)
+        text
+          .gsub(/((?<!\\) )|\n+/, "")
+          .gsub(/\\\\ /, "\\\\\\\\")
+          .gsub(/&#x26;/, "&")
+          .gsub(/&#x22;/, "\"")
+          .gsub(/(?<!\\\\)\\&#xa;/, "\\ ")
+          .gsub(/&#xa;/, "")
+      end
     end
   end
 end

data/lib/plurimath/math/core.rb

@@ -116,6 +116,16 @@ module Plurimath
         options[:array] << field&.to_omml_math_zone(hashed[:function_spacing], hashed[:last], hashed[:indent], display_style: display_style)
       end
 
+      def unicodemath_fields_to_print(field, options = {})
+        return if field.nil?
+
+        hashed = common_math_zone_conversion(field, options)
+        options[:array] << "#{hashed[:spacing]}|_ \"#{field&.to_unicodemath}\"#{hashed[:field_name]}\n"
+        return unless Utility.validate_math_zone(field, lang: :unicodemath)
+
+        options[:array] << field&.to_unicodemath_math_zone(hashed[:function_spacing], hashed[:last], hashed[:indent])
+      end
+
       def dump_mathml(field, intent = false)
         dump_ox_nodes(field.to_mathml_without_math_tag(intent)).gsub(/\n\s*/, "")
       end

data/lib/plurimath/math/formula.rb

@@ -10,6 +10,7 @@ module Plurimath
         latex
         mathml
         asciimath
+        unicodemath
       ].freeze
       POWER_BASE_CLASSES = %w[powerbase power base].freeze
       DERIVATIVE_CONSTS = [
@@ -165,6 +166,8 @@ module Plurimath
                       "  |_ \"#{to_mathml.gsub(/\n\s*/, "")}\"\n#{to_mathml_math_zone("     ").join}"
                     when :omml
                       "  |_ \"#{to_omml.gsub(/\n\s*/, "")}\"\n#{to_omml_math_zone("     ", display_style: displaystyle).join}"
+                    when :unicodemath
+                      "  |_ \"#{to_unicodemath}\"\n#{to_unicodemath_math_zone("     ").join}"
                     end
         <<~MATHZONE.sub(/\n$/, "")
         |_ Math zone
@@ -200,6 +203,13 @@ module Plurimath
         end
       end
 
+      def to_unicodemath_math_zone(spacing = "", last = false, indent = true)
+        filtered_values(value, lang: :unicodemath).map.with_index(1) do |object, index|
+          last = index == @values.length
+          object.to_unicodemath_math_zone(new_space(spacing, indent), last, indent)
+        end
+      end
+
       def extract_class_name_from_text
         return unless value.length < 2 && value.first.is_a?(Function::Text)
 

data/lib/plurimath/math/function/binary_function.rb

@@ -100,6 +100,15 @@ module Plurimath
           new_arr
         end
 
+        def to_unicodemath_math_zone(spacing, last = false, _)
+          parameters = self.class::FUNCTION
+          new_spacing = gsub_spacing(spacing, last)
+          new_arr = ["#{spacing}\"#{to_unicodemath}\" #{parameters[:name]}\n"]
+          unicodemath_fields_to_print(parameter_one, { spacing: new_spacing, field_name: parameters[:first_value], additional_space: "|  |_ " , array: new_arr })
+          unicodemath_fields_to_print(parameter_two, { spacing: new_spacing, field_name: parameters[:second_value], additional_space: "   |_ " , array: new_arr })
+          new_arr
+        end
+
         protected
 
         def latex_wrapped(field)