From 0b392c1094f388de7cf75a561a123114995d6748 Mon Sep 17 00:00:00 2001
From: Mike West <mike@mikewest.org>
Date: Wed, 20 Oct 2010 14:34:09 +0200
Subject: [PATCH] Attempt to autodetect file language

`pygmentize` 1.0+ has an `-N` option that attempts to match a file (via
the extension) to a language lexer.  If `pygmentize` is installed, we'll
run it with this option to get a language.

If no language is detected, `pygmentize -N` returns `text`.  In that case,
we'll first look for a user-provided language to use as a fallback.  If no
language was provided, highlight using `ruby` as a reasonable default.

Closes issue #19.
---
 lib/rocco.rb       | 43 ++++++++++++++++++++++++++++++++++++++-----
 test/rocco_test.rb | 24 ++++++++++++++++++++++++
 2 files changed, 62 insertions(+), 5 deletions(-)

diff --git a/lib/rocco.rb b/lib/rocco.rb
index 467f9ef..ea0293e 100644
--- a/lib/rocco.rb
+++ b/lib/rocco.rb
@@ -61,10 +61,18 @@ end
 
 # `Rocco.new` takes a source `filename`, an optional list of source filenames
 # for other documentation sources, an `options` hash, and an optional `block`.
-# The `options` hash respects two members: `:language`, which specifies which
-# Pygments lexer to use; and `:comment_chars`, which specifies the comment
-# characters of the target language. The options default to `'ruby'` and `'#'`,
-# respectively.
+# The `options` hash respects three members:
+#
+# *    `:language`: specifies which Pygments lexer to use if one can't be
+#      auto-detected from the filename.  _Defaults to `ruby`_.
+# 
+# *    `:comment_chars`, which specifies the comment characters of the
+#      target language. _Defaults to `#`_.
+#
+# *    `:template_file`, which specifies a external template file to use
+#      when rendering the final, highlighted file via Mustache.  _Defaults
+#      to `nil` (that is, Mustache will use `./lib/rocco/layout.mustache`)_.
+#
 # When `block` is given, it must read the contents of the file using whatever
 # means necessary and return it as a string. With no `block`, the file is read
 # to retrieve data.
@@ -88,12 +96,37 @@ class Rocco
     @sources = sources
     @comment_pattern = Regexp.new("^\\s*#{@options[:comment_chars]}\s?")
     @template_file = @options[:template_file]
+
+    @options[:language] = detect_language()
     @sections = highlight(split(parse(@data)))
   end
 
+  # Returns `true` if `pygmentize` is available locally, `false` otherwise.
+  def pygmentize?
+    # Memoize the result, we'll call this a few times
+    @pygmentize ||= ENV['PATH'].split(':').any? { |dir| executable?("#{dir}/pygmentize") }
+  end
+
+  # If `pygmentize` is available, we can use it to autodetect a file's
+  # language based on its filename.  Filenames without extensions, or with
+  # extensions that `pygmentize` doesn't understand will return `text`.  In
+  # that case, we'll fallback to the user-provided `:language` option.
+  def detect_language
+    default = @options[:language]
+    if pygmentize?
+        lang = %x[pygmentize -N #{@file}].strip!
+        ( !lang || lang == "text" ) ? default : lang
+    else
+        default
+    end
+  end
+
   # The filename as given to `Rocco.new`.
   attr_reader :file
 
+  # The merged options array
+  attr_reader :options
+
   # A list of two-tuples representing each *section* of the source file. Each
   # item in the list has the form: `[docs_html, code_html]`, where both
   # elements are strings containing the documentation and source code HTML,
@@ -173,7 +206,7 @@ class Rocco
     # `pygmentize(1)` or <http://pygments.appspot.com>
     code_stream = code_blocks.join("\n\n#{@options[:comment_chars]} DIVIDER\n\n")
 
-    if ENV['PATH'].split(':').any? { |dir| executable?("#{dir}/pygmentize") }
+    if pygmentize? 
       code_html = highlight_pygmentize(code_stream)
     else 
       code_html = highlight_webservice(code_stream)
diff --git a/test/rocco_test.rb b/test/rocco_test.rb
index 58c0820..5d9d23d 100644
--- a/test/rocco_test.rb
+++ b/test/rocco_test.rb
@@ -82,6 +82,30 @@ class RoccoBasicTests < Test::Unit::TestCase
 
 end
 
+class RoccoLanguageDetection < Test::Unit::TestCase
+    def test_basic_detection
+        r = Rocco.new( 'filename.py' ) { "" }
+        if r.pygmentize?
+          assert_equal "python", r.detect_language(), "`detect_language()` should return the correct language"
+          assert_equal "python", r.options[:language], "`@options[:language]` should be set to the correct language"
+        end
+    end
+    def test_fallback_default
+        r = Rocco.new( 'filename.an_extension_with_no_meaning_whatsoever' ) { "" }
+        if r.pygmentize?
+          assert_equal "ruby", r.detect_language(), "`detect_language()` should return `ruby` when nothing else is detected"
+          assert_equal "ruby", r.options[:language], "`@options[:language]` should be set to `ruby` when nothing else is detected"
+        end
+    end
+    def test_fallback_user
+        r = Rocco.new( 'filename.an_extension_with_no_meaning_whatsoever', '', { :language => "c" } ) { "" }
+        if r.pygmentize?
+          assert_equal "c", r.detect_language(), "`detect_language()` should return the user's setting when nothing else is detected"
+          assert_equal "c", r.options[:language], "`@options[:language]` should be set to the user's setting when nothing else is detected"
+        end
+    end
+end
+
 class RoccoIssueTests < Test::Unit::TestCase
     def test_issue07_incorrect_parsing_in_c_mode
         # Precursor to issue #13 below, Rocco incorrectly parsed C/C++