polytexnic 0.5.0 → 0.6.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: c16ad8d5728f4ac2d87b81744b76c4a854e26d88
-  data.tar.gz: 5859a31e6722957809d2fd080c5170a05be7b5e1
+  metadata.gz: d8e7de21594c8b7389b2644e15ea5cf098edff39
+  data.tar.gz: 49867ac88a23d41ddf48903ada6f0269dd84d940
 SHA512:
-  metadata.gz: 12e8c475ee247533ce1dcf0b1db8ad7cf3806a2cf81cf5726b935fbc0d23ac60ccc1998e7e38c5a234911be9ff370abdac44f6782caf5b5f1f28a3608240f3b2
-  data.tar.gz: 54b074f7a0df5e183cf333a52ceb5d4fa1b7addc3085c5b082da3c15f693a7afe03fba5295a8b140b85d48dfece737a8e74d258a021420935d497301007e584c
+  metadata.gz: 0c58db6f0f1661a51c11c216c624960f4d9f405eaf2b201f88e810c9276c94e30539b322100c71cd9c36163480f43229d271fcb2520ffdd715889451db977ef7
+  data.tar.gz: 015ba8b5a3034d4b2765b509d2fa9a58f1fc8f5f4a897c0a2724b7048e4f912deec4cd18c0d4635a5c5b98ab95c356be1c79ded81802f839fb804ad7650b7d47

data/lib/polytexnic/literal.rb

@@ -1,5 +1,6 @@
 module Polytexnic
   module Literal
+    extend self
 
     # Matches the line for syntax highlighting.
     # %= lang:<language>
@@ -21,6 +22,22 @@ module Polytexnic
       output.join("\n")
     end
 
+    # Returns supported math environments.
+    # Note that the custom AMS-TeX environments are supported
+    # in addition to the LaTeX defaults.
+    def math_environments
+      %w[align align*
+         eqnarray eqnarray* equation equation*
+         gather gather* gathered
+         multline multline*
+        ]
+    end
+
+    # Returns a list of all literal types.
+    def literal_types
+      %w[verbatim Vertatim code metadcode] + math_environments
+    end
+
     # Handles environments that should be passed through the pipeline intact.
     # The includes verbatim environments ('verbatim', 'Verbatim') and all the
     # equation environments handled by MathJax ('equation', 'align', etc.).
@@ -40,7 +57,7 @@ module Polytexnic
     # and even then I've failed to get it to work. Thus, it shall for now
     # follow the "ball of mud" pattern. (The only saving grace is that it's
     # very thoroughly tested.)
-    def cache_literal_environments(lines, output, format)
+    def cache_literal_environments(lines, output, format, cache = nil)
       latex = (format == :latex)
       language = nil
       in_verbatim = false
@@ -241,18 +258,9 @@ module Polytexnic
   end
 end
 
-# Returns supported math environments.
-# Note that the custom AMS-TeX environments are supported
-# in addition to the LaTeX defaults.
-def math_environments
-  %w[align align*
-     eqnarray eqnarray* equation equation*
-     gather gather* gathered
-     multline multline*
-    ]
-end
 
 class String
+  include Polytexnic::Literal
 
   # Returns true if self matches \begin{...} where ... is a literal environment.
   # Note: Support for the 'metacode' environment exists solely to allow
@@ -294,6 +302,8 @@ class String
 
     # Returns a regex matching valid math environments.
     def math_environment_regex
-      math_environments.map { |s| Regexp.escape(s) }.join('|')
+      Polytexnic::Literal.math_environments.map do |s|
+        Regexp.escape(s)
+      end.join('|')
     end
 end

data/lib/polytexnic/preprocessors/polytex.rb

@@ -2,6 +2,7 @@
 module Polytexnic
   module Preprocessor
     module Polytex
+      include Polytexnic::Literal
 
       # Converts Markdown to PolyTeX.
       # We adopt a unified approach: rather than convert "Markdown" (I use
@@ -23,17 +24,83 @@ module Polytexnic
       # marketing term.</rant>
       def to_polytex
         require 'Kramdown'
+        cache = {}
+        math_cache = {}
         cleaned_markdown = cache_code_environments
         cleaned_markdown.tap do |markdown|
           convert_code_inclusion(markdown)
+          cache_latex_literal(markdown, cache)
+          cache_raw_latex(markdown, cache)
+          cache_math(markdown, math_cache)
         end
-        math_cache = cache_math(cleaned_markdown)
         # Override the header ordering, which starts with 'section' by default.
         lh = 'chapter,section,subsection,subsubsection,paragraph,subparagraph'
         kramdown = Kramdown::Document.new(cleaned_markdown, latex_headers: lh)
         @source = restore_inclusion(restore_math(kramdown.to_latex, math_cache))
+        restore_raw_latex(@source, cache)
+      end
+
+      # Adds support for <<(path/to/code) inclusion.
+      # Yes, this is a bit of a hack, but it works.
+      def convert_code_inclusion(text)
+        text.gsub!(/^\s*<<(\(.*?\))/) { "<!-- inclusion= <<#{$1}-->" }
+      end
+      def restore_inclusion(text)
+        text.gsub(/% <!-- inclusion= (.*?)-->/) { "%= #{$1}" }
+      end
+
+      # Caches literal LaTeX environments.
+      def cache_latex_literal(markdown, cache)
+        Polytexnic::Literal.literal_types.each do |literal|
+          regex = /(\\begin\{#{Regexp.escape(literal)}\}
+                  .*?
+                  \\end\{#{Regexp.escape(literal)}\})
+                  /xm
+          markdown.gsub!(regex) do
+            key = digest($1)
+            cache[key] = $1
+            key
+          end
+        end
+      end
+
+      # Caches raw LaTeX commands to be passed through the pipeline.
+      def cache_raw_latex(markdown, cache)
+        command_regex = /(
+                          ~\\ref\{.*?\}     # reference with a tie
+                          |
+                          ~\\eqref\{.*?\}   # eq reference with a tie
+                          |
+                          \\\w+\{.*?\}      # command with one arg
+                          |
+                          \\\w+             # normal command
+                          |
+                          \\[ %&$#@]        # space or special character
+                          )
+                        /x
+        markdown.gsub!(command_regex) do
+          key = digest($1)
+          cache[key] = $1
+          key
+        end
+      end
+
+      # Restores raw LaTeX from the cache
+      def restore_raw_latex(text, cache)
+        cache.each do |key, value|
+          if value == '\&'
+            # Bizarrely, the default code doesn't work for '\&'.
+            # I actually suspect it may be a bug in Ruby. This hacks around it.
+            text.gsub!(key, value.sub(/\\/, '\\\\\\'))
+          else
+            text.gsub!(key, value)
+          end
+        end
       end
 
+      # Caches Markdown code environments.
+      # Included are indented environments, Leanpub-style indented environments,
+      # and GitHub-style code fencing.
       def cache_code_environments
         output = []
         lines = @source.split("\n")
@@ -72,7 +139,7 @@ module Polytexnic
         output.join("\n")
       end
 
-      # Caches Leanpub-style math.
+      # Caches math.
       # Leanpub uses the notation {$$}...{/$$} for both inline and block math,
       # with the only difference being the presences of newlines:
       #     {$$} x^2 {/$$}  % inline
@@ -80,21 +147,19 @@ module Polytexnic
       #     {$$}
       #     x^2             % block
       #     {/$$}
-      # I personally hate this notation and convention, but anyone who really
-      # cares should just use PolyTeX instead of Markdown.
-      def cache_math(text)
-        cache = {}
-        text.gsub!(/\{\$\$\}\n(.*?)\n\{\/\$\$\}/) do
-          key = digest($1)
-          cache[[:block, key]] = $1
+      # I personally hate this notation and convention, so we also support
+      # LaTeX-style \( x \) and \[ x^2 - 2 = 0 \] notation.
+      def cache_math(text, cache)
+        text.gsub!(/(?:\{\$\$\}\n(.*?)\n\{\/\$\$\}|\\\[(.*?)\\\])/) do
+          key = digest($1 || $2)
+          cache[[:block, key]] = $1 || $2
           key
         end
-        text.gsub!(/\{\$\$\}(.*?)\{\/\$\$\}/) do
-          key = digest($1)
-          cache[[:inline, key]] = $1
+        text.gsub!(/(?:\{\$\$\}(.*?)\{\/\$\$\}|\\\((.*?)\\\))/) do
+          key = digest($1 || $2)
+          cache[[:inline, key]] = $1 || $2
           key
         end
-        cache
       end
 
       # Restores the Markdown math.
@@ -115,13 +180,5 @@ module Polytexnic
         text
       end
     end
-
-    # Adds support for <<(path/to/code) inclusion.
-    def convert_code_inclusion(text)
-      text.gsub!(/^\s*<<(\(.*?\))/) { "<!-- inclusion= <<#{$1}-->" }
-    end
-    def restore_inclusion(text)
-      text.gsub(/% <!-- inclusion= (.*?)-->/) { "%= #{$1}" }
-    end
   end
 end

data/lib/polytexnic/version.rb

@@ -1,3 +1,3 @@
 module Polytexnic
-  VERSION = "0.5.0"
+  VERSION = "0.6.0"
 end

data/spec/markdown_to_polytex_spec.rb

@@ -87,6 +87,78 @@ That is it.  You can keep writing your text after the footnote content.
       end
     end
 
+    context "with LaTeX containing" do
+
+      context "a normal command" do
+        let(:source) { 'This is a command: \foobar' }
+        it { should include source }
+      end
+
+      context "backslash space" do
+        let(:source) { 'Dr.\ No' }
+        it { should include source }
+      end
+
+      context "escaped special characters" do
+        let(:source) { '\% \& \$ \# \@ \_' }
+        it { should include source }
+      end
+
+      context "a label and cross-reference" do
+        let(:source) do <<-'EOS'
+# Chapter One
+\label{cha:one}
+
+Chapter~\ref{cha:one}
+          EOS
+        end
+        it { should include '\label{cha:one}' }
+        it { should include 'Chapter~\ref{cha:one}' }
+      end
+
+      context "an inline equation" do
+        let(:source) { '\( x \) is a variable' }
+        it { should include source }
+      end
+
+      context "a centered equation" do
+        let(:source) { '\[ x^2 - 2 = 0 \] is an equation' }
+        it { should resemble source }
+      end
+
+      context "an equation environment" do
+        let(:source) do <<-'EOS'
+foo
+
+\begin{equation}
+\label{eq:phi}
+\phi = \frac{1+\sqrt{5}}{2}
+\end{equation}
+
+bar
+          EOS
+        end
+        it { should resemble source }
+      end
+
+      context "a codelisting environment" do
+        let(:source) do <<-'EOS'
+\begin{codelisting}
+\codecaption{Lorem ipsum.}
+\label{code:lorem}
+```ruby
+def foo; "bar"; end
+```
+\end{codelisting}
+          EOS
+        end
+        it { should resemble '\begin{codelisting}' }
+        it { should resemble '\codecaption{Lorem ipsum.}' }
+        it { should resemble '\label{code:lorem}' }
+        it { should resemble '\end{codelisting}' }
+      end
+    end
+
     describe "source code" do
       context "without highlighting" do
         let(:source) do <<-EOS

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: polytexnic
 version: !ruby/object:Gem::Version
-  version: 0.5.0
+  version: 0.6.0
 platform: ruby
 authors:
 - Michael Hartl
@@ -9,7 +9,7 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2013-11-13 00:00:00.000000000 Z
+date: 2013-11-14 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: nokogiri