Support guessing lexer by filename

TODO.md

@@ -5,5 +5,6 @@
 * ✅ Implement styles
 * ✅ Implement formatters
 * ✅ Implement CLI
-* Implement lexer loader that respects aliases, etc
+* ✅ Implement lexer loader that respects aliases
-* Implement language guessing for file names
+* ✅ Implement lexer loader by file extension
+* Implement lexer loader by mime type

src/lexer.cr

@@ -1,3 +1,5 @@
+require "./constants/lexers"
+
 module Tartrazine
   class LexerFiles
     extend BakedFileSystem
@@ -6,19 +8,33 @@ module Tartrazine
   end
 
   # Get the lexer object for a language name
-  # FIXME: support aliases, paths, mimetypes, etc
+  # FIXME: support mimetypes
-  def self.lexer(name : String) : Lexer
+  def self.lexer(name : String? = nil, filename : String? = nil) : Lexer
-    Lexer.from_xml(LexerFiles.get("/#{name}.xml").gets_to_end)
+    if name.nil? && filename.nil?
+      lexer_file_name = LEXERS_BY_NAME["plaintext"]
+    elsif name && name != "autodetect"
+      lexer_file_name = LEXERS_BY_NAME[name.downcase]
+    else
+      # Guess by filename
+      candidates = Set(String).new
+      LEXERS_BY_FILENAME.each do |k, v|
+        candidates += v.to_set if File.match?(k, File.basename(filename.to_s))
+      end
+      case candidates.size
+      when 0
+        lexer_file_name = LEXERS_BY_NAME["plaintext"]
+      when 1
+        lexer_file_name = candidates.first
+      else
+        raise Exception.new("Multiple lexers match the filename: #{candidates.to_a.join(", ")}")
+      end
+    end
+    Lexer.from_xml(LexerFiles.get("/#{lexer_file_name}.xml").gets_to_end)
   end
 
   # Return a list of all lexers
-  # FIXME: support aliases
   def self.lexers : Array(String)
-    lexers = Set(String).new
+    LEXERS_BY_NAME.keys.sort!
-    LexerFiles.files.each do |file|
-      lexers << file.path.split("/").last.split(".").first
-    end
-    lexers.to_a.sort!
   end
 
   # This implements a lexer for Pygments RegexLexers as expressed

src/main.cr

@@ -18,7 +18,7 @@ Usage:
 Options:
   -f <formatter>      Format to use (html, terminal, json)
   -t <theme>          Theme to use, see --list-themes [default: default-dark]
-  -l <lexer>          Lexer (language) to use, see --list-lexers [default: plaintext]
+  -l <lexer>          Lexer (language) to use, see --list-lexers [default: autodetect]
   -o <output>         Output file. Default is stdout.
   --standalone        Generate a standalone HTML file, which includes
                       all style information. If not given, it will generate just
@@ -77,7 +77,7 @@ if options["-f"]
     exit 0
   end
 
-  lexer = Tartrazine.lexer(options["-l"].as(String))
+  lexer = Tartrazine.lexer(name: options["-l"].as(String), filename: options["FILE"].as(String))
 
   input = File.open(options["FILE"].as(String)).gets_to_end
   output = formatter.format(input, lexer, theme)