Linguist 2.4.0

Add Handlebars

Rakefile

@@ -3,9 +3,7 @@ require 'rake/testtask'
 
 task :default => :test
 
-Rake::TestTask.new do |t|
-  t.warning = true
-end
+Rake::TestTask.new
 
 task :samples do
   require 'linguist/samples'

github-linguist.gemspec

@@ -1,6 +1,6 @@
 Gem::Specification.new do |s|
   s.name    = 'github-linguist'
-  s.version = '2.3.0'
+  s.version = '2.4.0'
   s.summary = "GitHub Language detection"
 
   s.authors = "GitHub"
@@ -11,7 +11,8 @@ Gem::Specification.new do |s|
   s.add_dependency 'charlock_holmes', '~> 0.6.6'
   s.add_dependency 'escape_utils',    '~> 0.2.3'
   s.add_dependency 'mime-types',      '~> 1.19'
-  s.add_dependency 'pygments.rb',     '>= 0.2.13'
+  s.add_dependency 'pygments.rb',     '>= 0.3.0'
+  s.add_development_dependency 'mocha'
   s.add_development_dependency 'json'
   s.add_development_dependency 'rake'
   s.add_development_dependency 'yajl-ruby'

lib/linguist/blob_helper.rb

@@ -160,7 +160,7 @@ module Linguist
     #
     # Return true or false
     def safe_to_colorize?
-      text? && !large? && !high_ratio_of_long_lines?
+      !large? && text? && !high_ratio_of_long_lines?
     end
 
     # Internal: Does the blob have a ratio of long lines?
@@ -204,7 +204,31 @@ module Linguist
     #
     # Returns an Array of lines
     def lines
-      @lines ||= (viewable? && data) ? data.split("\n", -1) : []
+      @lines ||=
+        if viewable? && data
+          data.split(line_split_character, -1)
+        else
+          []
+        end
+    end
+
+    # Character used to split lines. This is almost always "\n" except when Mac
+    # Format is detected in which case it's "\r".
+    #
+    # Returns a split pattern string.
+    def line_split_character
+      @line_split_character ||= (mac_format?? "\r" : "\n")
+    end
+
+    # Public: Is the data in ** Mac Format **. This format uses \r (0x0d) characters
+    # for line ends and does not include a \n (0x0a).
+    #
+    # Returns true when mac format is detected.
+    def mac_format?
+      return if !viewable?
+      if pos = data[0, 4096].index("\r")
+        data[pos + 1] != ?\n
+      end
     end
 
     # Public: Get number of lines of code
@@ -250,7 +274,9 @@ module Linguist
     #
     # Return true or false
     def indexable?
-      if binary?
+      if size > 100 * 1024
+        false
+      elsif binary?
         false
       elsif extname == '.txt'
         true
@@ -260,8 +286,6 @@ module Linguist
         false
       elsif generated?
         false
-      elsif size > 100 * 1024
-        false
       else
         true
       end
@@ -278,7 +302,7 @@ module Linguist
       if defined?(@data) && @data.is_a?(String)
         data = @data
       else
-        data = lambda { binary_mime_type? ? "" : self.data }
+        data = lambda { (binary_mime_type? || binary?) ? "" : self.data }
       end
 
       @language = Language.detect(name.to_s, data, mode)

lib/linguist/language.rb

@@ -84,7 +84,9 @@ module Linguist
 
       if possible_languages.length > 1
         data = data.call() if data.respond_to?(:call)
-        if result = Classifier.classify(Samples::DATA, data, possible_languages.map(&:name)).first
+        if data.nil? || data == ""
+          nil
+        elsif result = Classifier.classify(Samples::DATA, data, possible_languages.map(&:name)).first
           Language[result[0]]
         end
       else
@@ -220,6 +222,7 @@ module Linguist
         raise(ArgumentError, "#{@name} is missing lexer")
 
       @ace_mode = attributes[:ace_mode]
+      @wrap = attributes[:wrap] || false
 
       # Set legacy search term
       @search_term = attributes[:search_term] || default_alias_name
@@ -310,6 +313,11 @@ module Linguist
     # Returns a String name or nil
     attr_reader :ace_mode
 
+    # Public: Should language lines be wrapped
+    #
+    # Returns true or false
+    attr_reader :wrap
+
     # Public: Get extensions
     #
     # Examples
@@ -460,6 +468,7 @@ module Linguist
       :aliases           => options['aliases'],
       :lexer             => options['lexer'],
       :ace_mode          => options['ace_mode'],
+      :wrap              => options['wrap'],
       :group_name        => options['group'],
       :searchable        => options.key?('searchable') ? options['searchable'] : true,
       :search_term       => options['search_term'],

lib/linguist/languages.yml

@@ -10,6 +10,7 @@
 # aliases           - An Array of additional aliases (implicitly
 #                     includes name.downcase)
 # ace_mode          - A String name of Ace Mode (if available)
+# wrap              - Boolean wrap to enable line wrapping (default: false)
 # extension         - An Array of associated extensions
 # primary_extension - A String for the main extension associated with
 #                     the language. Must be unique. Used when a Language is picked
@@ -62,6 +63,12 @@ Ada:
   - .adb
   - .ads
 
+ApacheConf:
+  type: markup
+  aliases:
+  - apache
+  primary_extension: .apacheconf
+
 Apex:
   type: programming
   lexer: Text only
@@ -179,8 +186,10 @@ C++:
   - cpp
   primary_extension: .cpp
   extensions:
+  - .C
   - .c++
   - .cxx
+  - .H
   - .h++
   - .hh
   - .hxx
@@ -243,6 +252,7 @@ CoffeeScript:
   color: "#244776"
   aliases:
   - coffee
+  - coffee-script
   primary_extension: .coffee
   extensions:
   - ._coffee
@@ -367,6 +377,14 @@ Ecere Projects:
   extensions:
   - .epj
 
+Ecl:
+  type: programming
+  color: "#8a1267"
+  primary_extension: .ecl
+  lexer: ECL
+  extensions:
+  - .eclxml
+
 Eiffel:
   type: programming
   lexer: Text only
@@ -383,6 +401,12 @@ Elixir:
   - .ex
   - .exs
 
+Elm:
+  type: programming
+  lexer: Haskell
+  group: Haskell
+  primary_extension: .elm
+
 Emacs Lisp:
   type: programming
   lexer: Scheme
@@ -536,6 +560,8 @@ Groovy Server Pages:
 HTML:
   type: markup
   ace_mode: html
+  aliases:
+  - xhtml
   primary_extension: .html
   extensions:
   - .htm
@@ -554,6 +580,8 @@ HTML+ERB:
   type: markup
   group: HTML
   lexer: RHTML
+  aliases:
+  - erb
   primary_extension: .erb
   extensions:
   - .erb
@@ -566,22 +594,20 @@ HTML+PHP:
   extensions:
   - .phtml
 
-HaXe:
-  type: programming
-  lexer: haXe
-  ace_mode: haxe
-  color: "#346d51"
-  primary_extension: .hx
-  extensions:
-  - .hx
-  - .hxml
-  - .mtt
+HTTP:
+  type: data
+  primary_extension: .http
 
 Haml:
   group: HTML
   type: markup
   primary_extension: .haml
 
+Handlebars:
+  type: markup
+  lexer: Text only
+  primary_extension: .handlebars
+
 Haskell:
   type: programming
   color: "#29b544"
@@ -590,6 +616,15 @@ Haskell:
   - .hs
   - .hsc
 
+Haxe:
+  type: programming
+  lexer: haXe
+  ace_mode: haxe
+  color: "#346d51"
+  primary_extension: .hx
+  extensions:
+  - .hxsl
+
 INI:
   type: data
   extensions:
@@ -714,6 +749,8 @@ Lua:
   - .nse
 
 Makefile:
+  aliases:
+  - make
   extensions:
   - .mak
   - .mk
@@ -733,6 +770,7 @@ Markdown:
   type: markup
   lexer: Text only
   ace_mode: markdown
+  wrap: true
   primary_extension: .md
   extensions:
   - .markdown
@@ -788,6 +826,11 @@ Nemerle:
   color: "#0d3c6e"
   primary_extension: .n
 
+Nginx:
+  type: markup
+  lexer: Nginx configuration file
+  primary_extension: .nginxconf
+
 Nimrod:
   type: programming
   color: "#37775b"
@@ -833,6 +876,9 @@ ObjDump:
 Objective-C:
   type: programming
   color: "#438eff"
+  aliases:
+  - obj-c
+  - objc
   primary_extension: .m
   extensions:
   - .mm
@@ -840,6 +886,8 @@ Objective-C:
 Objective-J:
   type: programming
   color: "#ff0c5a"
+  aliases:
+  - obj-j
   primary_extension: .j
   extensions:
   - .j
@@ -1114,10 +1162,6 @@ Shell:
   - bash
   - zsh
   primary_extension: .sh
-  filenames:
-  - .zsh
-  - bashrc
-  - zshrc
 
 Smalltalk:
   type: programming
@@ -1162,6 +1206,8 @@ Tcsh:
 TeX:
   type: markup
   ace_mode: latex
+  aliases:
+  - latex
   primary_extension: .tex
   extensions:
   - .aux
@@ -1180,6 +1226,7 @@ Textile:
   type: markup
   lexer: Text only
   ace_mode: textile
+  wrap: true
   primary_extension: .textile
   extensions:
   - .textile
@@ -1250,6 +1297,11 @@ Visual Basic:
 XML:
   type: markup
   ace_mode: xml
+  aliases:
+  - rss
+  - xsd
+  - xsl
+  - wsdl
   primary_extension: .xml
   extensions:
   - .glade
@@ -1295,6 +1347,8 @@ XSLT:
 
 YAML:
   type: markup
+  aliases:
+  - yml
   primary_extension: .yml
   extensions:
   - .yaml
@@ -1324,6 +1378,7 @@ ooc:
 
 reStructuredText:
   type: markup
+  wrap: true
   search_term: rst
   aliases:
   - rst

lib/linguist/samples.rb

@@ -76,12 +76,14 @@ module Linguist
           db['extnames'][language_name] ||= []
           if !db['extnames'][language_name].include?(sample[:extname])
             db['extnames'][language_name] << sample[:extname]
+            db['extnames'][language_name].sort!
           end
         end
 
         if sample[:filename]
           db['filenames'][language_name] ||= []
           db['filenames'][language_name] << sample[:filename]
+          db['filenames'][language_name].sort!
         end
 
         data = File.read(sample[:path])

lib/linguist/tokenizer.rb

@@ -16,6 +16,9 @@ module Linguist
       new.extract_tokens(data)
     end
 
+    # Read up to 100KB
+    BYTE_LIMIT = 100_000
+
     # Start state on token, ignore anything till the next newline
     SINGLE_LINE_COMMENTS = [
       '//', # C
@@ -55,6 +58,8 @@ module Linguist
 
       tokens = []
       until s.eos?
+        break if s.pos >= BYTE_LIMIT
+
         if token = s.scan(/^#!.+$/)
           if name = extract_shebang(token)
             tokens << "SHEBANG#!#{name}"
@@ -133,7 +138,7 @@ module Linguist
           s.scan(/\s+/)
           script = s.scan(/\S+/)
         end
-        script = script[/[^\d]+/, 0]
+        script = script[/[^\d]+/, 0] if script
         return script
       end
 

samples/ApacheConf/filenames/.htaccess

@@ -0,0 +1,26 @@
+ServerSignature Off
+RewriteCond %{REQUEST_METHOD} ^(HEAD|TRACE|DELETE|TRACK) [NC,OR]
+RewriteCond %{THE_REQUEST} (\\r|\\n|%0A|%0D) [NC,OR]
+
+RewriteCond %{HTTP_REFERER} (<|>|’|%0A|%0D|%27|%3C|%3E|%00) [NC,OR]
+RewriteCond %{HTTP_COOKIE} (<|>|’|%0A|%0D|%27|%3C|%3E|%00) [NC,OR]
+RewriteCond %{REQUEST_URI} ^/(,|;|:|<|>|”>|”<|/|\\\.\.\\).{0,9999} [NC,OR]
+
+RewriteCond %{HTTP_USER_AGENT} ^$ [OR]
+RewriteCond %{HTTP_USER_AGENT} ^(java|curl|wget) [NC,OR]
+RewriteCond %{HTTP_USER_AGENT} (winhttp|HTTrack|clshttp|archiver|loader|email|harvest|extract|grab|miner) [NC,OR]
+RewriteCond %{HTTP_USER_AGENT} (libwww-perl|curl|wget|python|nikto|scan) [NC,OR]
+RewriteCond %{HTTP_USER_AGENT} (<|>|’|%0A|%0D|%27|%3C|%3E|%00) [NC,OR]
+
+#Block mySQL injects
+RewriteCond %{QUERY_STRING} (;|<|>|’|”|\)|%0A|%0D|%22|%27|%3C|%3E|%00).*(/\*|union|select|insert|cast|set|declare|drop|update|md5|benchmark) [NC,OR]
+
+RewriteCond %{QUERY_STRING} \.\./\.\. [OR]
+
+RewriteCond %{QUERY_STRING} (localhost|loopback|127\.0\.0\.1) [NC,OR]
+RewriteCond %{QUERY_STRING} \.[a-z0-9] [NC,OR]
+RewriteCond %{QUERY_STRING} (<|>|’|%0A|%0D|%27|%3C|%3E|%00) [NC]
+# Note: The final RewriteCond must NOT use the [OR] flag.
+
+# Return 403 Forbidden error.
+RewriteRule .* index.php [F]

samples/ApacheConf/filenames/apache2.conf

@@ -0,0 +1,470 @@
+# This is the main Apache HTTP server configuration file.  It contains the
+# configuration directives that give the server its instructions.
+# See <URL:http://httpd.apache.org/docs/2.2> for detailed information.
+# In particular, see
+# <URL:http://httpd.apache.org/docs/2.2/mod/directives.html>
+# for a discussion of each configuration directive.
+#
+# Do NOT simply read the instructions in here without understanding
+# what they do.  They're here only as hints or reminders.  If you are unsure
+# consult the online docs. You have been warned.
+#
+# Configuration and logfile names: If the filenames you specify for many
+# of the server's control files begin with "/" (or "drive:/" for Win32), the
+# server will use that explicit path.  If the filenames do *not* begin
+# with "/", the value of ServerRoot is prepended -- so "/var/log/apache2/foo.log"
+# with ServerRoot set to "" will be interpreted by the
+# server as "//var/log/apache2/foo.log".
+
+#
+# ServerRoot: The top of the directory tree under which the server's
+# configuration, error, and log files are kept.
+#
+# Do not add a slash at the end of the directory path.  If you point
+# ServerRoot at a non-local disk, be sure to point the LockFile directive
+# at a local disk.  If you wish to share the same ServerRoot for multiple
+# httpd daemons, you will need to change at least LockFile and PidFile.
+#
+ServerRoot ""
+
+#
+# Listen: Allows you to bind Apache to specific IP addresses and/or
+# ports, instead of the default. See also the <VirtualHost>
+# directive.
+#
+# Change this to Listen on specific IP addresses as shown below to
+# prevent Apache from glomming onto all bound IP addresses.
+#
+#Listen 12.34.56.78:80
+Listen 80
+
+#
+# Dynamic Shared Object (DSO) Support
+#
+# To be able to use the functionality of a module which was built as a DSO you
+# have to place corresponding `LoadModule' lines at this location so the
+# directives contained in it are actually available _before_ they are used.
+# Statically compiled modules (those listed by `httpd -l') do not need
+# to be loaded here.
+#
+# Example:
+# LoadModule foo_module modules/mod_foo.so
+#
+LoadModule authn_file_module /usr/lib/apache2/modules/mod_authn_file.so
+LoadModule authn_dbm_module /usr/lib/apache2/modules/mod_authn_dbm.so
+LoadModule authn_anon_module /usr/lib/apache2/modules/mod_authn_anon.so
+LoadModule authn_dbd_module /usr/lib/apache2/modules/mod_authn_dbd.so
+LoadModule authn_default_module /usr/lib/apache2/modules/mod_authn_default.so
+LoadModule authn_alias_module /usr/lib/apache2/modules/mod_authn_alias.so
+LoadModule authz_host_module /usr/lib/apache2/modules/mod_authz_host.so
+LoadModule authz_groupfile_module /usr/lib/apache2/modules/mod_authz_groupfile.so
+LoadModule authz_user_module /usr/lib/apache2/modules/mod_authz_user.so
+LoadModule authz_dbm_module /usr/lib/apache2/modules/mod_authz_dbm.so
+LoadModule authz_owner_module /usr/lib/apache2/modules/mod_authz_owner.so
+LoadModule authnz_ldap_module /usr/lib/apache2/modules/mod_authnz_ldap.so
+LoadModule authz_default_module /usr/lib/apache2/modules/mod_authz_default.so
+LoadModule auth_basic_module /usr/lib/apache2/modules/mod_auth_basic.so
+LoadModule auth_digest_module /usr/lib/apache2/modules/mod_auth_digest.so
+LoadModule file_cache_module /usr/lib/apache2/modules/mod_file_cache.so
+LoadModule cache_module /usr/lib/apache2/modules/mod_cache.so
+LoadModule disk_cache_module /usr/lib/apache2/modules/mod_disk_cache.so
+LoadModule mem_cache_module /usr/lib/apache2/modules/mod_mem_cache.so
+LoadModule dbd_module /usr/lib/apache2/modules/mod_dbd.so
+LoadModule dumpio_module /usr/lib/apache2/modules/mod_dumpio.so
+LoadModule ext_filter_module /usr/lib/apache2/modules/mod_ext_filter.so
+LoadModule include_module /usr/lib/apache2/modules/mod_include.so
+LoadModule filter_module /usr/lib/apache2/modules/mod_filter.so
+LoadModule charset_lite_module /usr/lib/apache2/modules/mod_charset_lite.so
+LoadModule deflate_module /usr/lib/apache2/modules/mod_deflate.so
+LoadModule ldap_module /usr/lib/apache2/modules/mod_ldap.so
+LoadModule log_forensic_module /usr/lib/apache2/modules/mod_log_forensic.so
+LoadModule env_module /usr/lib/apache2/modules/mod_env.so
+LoadModule mime_magic_module /usr/lib/apache2/modules/mod_mime_magic.so
+LoadModule cern_meta_module /usr/lib/apache2/modules/mod_cern_meta.so
+LoadModule expires_module /usr/lib/apache2/modules/mod_expires.so
+LoadModule headers_module /usr/lib/apache2/modules/mod_headers.so
+LoadModule ident_module /usr/lib/apache2/modules/mod_ident.so
+LoadModule usertrack_module /usr/lib/apache2/modules/mod_usertrack.so
+LoadModule unique_id_module /usr/lib/apache2/modules/mod_unique_id.so
+LoadModule setenvif_module /usr/lib/apache2/modules/mod_setenvif.so
+LoadModule version_module /usr/lib/apache2/modules/mod_version.so
+LoadModule proxy_module /usr/lib/apache2/modules/mod_proxy.so
+LoadModule proxy_connect_module /usr/lib/apache2/modules/mod_proxy_connect.so
+LoadModule proxy_ftp_module /usr/lib/apache2/modules/mod_proxy_ftp.so
+LoadModule proxy_http_module /usr/lib/apache2/modules/mod_proxy_http.so
+LoadModule proxy_ajp_module /usr/lib/apache2/modules/mod_proxy_ajp.so
+LoadModule proxy_balancer_module /usr/lib/apache2/modules/mod_proxy_balancer.so
+LoadModule ssl_module /usr/lib/apache2/modules/mod_ssl.so
+LoadModule mime_module /usr/lib/apache2/modules/mod_mime.so
+LoadModule dav_module /usr/lib/apache2/modules/mod_dav.so
+LoadModule status_module /usr/lib/apache2/modules/mod_status.so
+LoadModule autoindex_module /usr/lib/apache2/modules/mod_autoindex.so
+LoadModule asis_module /usr/lib/apache2/modules/mod_asis.so
+LoadModule info_module /usr/lib/apache2/modules/mod_info.so
+LoadModule suexec_module /usr/lib/apache2/modules/mod_suexec.so
+LoadModule cgid_module /usr/lib/apache2/modules/mod_cgid.so
+LoadModule cgi_module /usr/lib/apache2/modules/mod_cgi.so
+LoadModule dav_fs_module /usr/lib/apache2/modules/mod_dav_fs.so
+LoadModule dav_lock_module /usr/lib/apache2/modules/mod_dav_lock.so
+LoadModule vhost_alias_module /usr/lib/apache2/modules/mod_vhost_alias.so
+LoadModule negotiation_module /usr/lib/apache2/modules/mod_negotiation.so
+LoadModule dir_module /usr/lib/apache2/modules/mod_dir.so
+LoadModule imagemap_module /usr/lib/apache2/modules/mod_imagemap.so
+LoadModule actions_module /usr/lib/apache2/modules/mod_actions.so
+LoadModule speling_module /usr/lib/apache2/modules/mod_speling.so
+LoadModule userdir_module /usr/lib/apache2/modules/mod_userdir.so
+LoadModule alias_module /usr/lib/apache2/modules/mod_alias.so
+LoadModule rewrite_module /usr/lib/apache2/modules/mod_rewrite.so
+
+<IfModule !mpm_netware_module>
+#
+# If you wish httpd to run as a different user or group, you must run
+# httpd as root initially and it will switch.
+#
+# User/Group: The name (or #number) of the user/group to run httpd as.
+# It is usually good practice to create a dedicated user and group for
+# running httpd, as with most system services.
+#
+User daemon
+Group daemon
+</IfModule>
+
+# 'Main' server configuration
+#
+# The directives in this section set up the values used by the 'main'
+# server, which responds to any requests that aren't handled by a
+# <VirtualHost> definition.  These values also provide defaults for
+# any <VirtualHost> containers you may define later in the file.
+#
+# All of these directives may appear inside <VirtualHost> containers,
+# in which case these default settings will be overridden for the
+# virtual host being defined.
+#
+
+#
+# ServerAdmin: Your address, where problems with the server should be
+# e-mailed.  This address appears on some server-generated pages, such
+# as error documents.  e.g. admin@your-domain.com
+#
+ServerAdmin you@example.com
+
+#
+# ServerName gives the name and port that the server uses to identify itself.
+# This can often be determined automatically, but we recommend you specify
+# it explicitly to prevent problems during startup.
+#
+# If your host doesn't have a registered DNS name, enter its IP address here.
+#
+#ServerName www.example.com:80
+
+#
+# DocumentRoot: The directory out of which you will serve your
+# documents. By default, all requests are taken from this directory, but
+# symbolic links and aliases may be used to point to other locations.
+#
+DocumentRoot "/usr/share/apache2/default-site/htdocs"
+
+#
+# Each directory to which Apache has access can be configured with respect
+# to which services and features are allowed and/or disabled in that
+# directory (and its subdirectories).
+#
+# First, we configure the "default" to be a very restrictive set of
+# features.
+#
+<Directory />
+    Options FollowSymLinks
+    AllowOverride None
+    Order deny,allow
+    Deny from all
+</Directory>
+
+#
+# Note that from this point forward you must specifically allow
+# particular features to be enabled - so if something's not working as
+# you might expect, make sure that you have specifically enabled it
+# below.
+#
+
+#
+# This should be changed to whatever you set DocumentRoot to.
+#
+<Directory "/usr/share/apache2/default-site/htdocs">
+    #
+    # Possible values for the Options directive are "None", "All",
+    # or any combination of:
+    #   Indexes Includes FollowSymLinks SymLinksifOwnerMatch ExecCGI MultiViews
+    #
+    # Note that "MultiViews" must be named *explicitly* --- "Options All"
+    # doesn't give it to you.
+    #
+    # The Options directive is both complicated and important.  Please see
+    # http://httpd.apache.org/docs/2.2/mod/core.html#options
+    # for more information.
+    #
+    Options Indexes FollowSymLinks
+
+    #
+    # AllowOverride controls what directives may be placed in .htaccess files.
+    # It can be "All", "None", or any combination of the keywords:
+    #   Options FileInfo AuthConfig Limit
+    #
+    AllowOverride None
+
+    #
+    # Controls who can get stuff from this server.
+    #
+    Order allow,deny
+    Allow from all
+
+</Directory>
+
+#
+# DirectoryIndex: sets the file that Apache will serve if a directory
+# is requested.
+#
+<IfModule dir_module>
+    DirectoryIndex index.html
+</IfModule>
+
+#
+# The following lines prevent .htaccess and .htpasswd files from being
+# viewed by Web clients.
+#
+<FilesMatch "^\.ht">
+    Order allow,deny
+    Deny from all
+    Satisfy All
+</FilesMatch>
+
+#
+# ErrorLog: The location of the error log file.
+# If you do not specify an ErrorLog directive within a <VirtualHost>
+# container, error messages relating to that virtual host will be
+# logged here.  If you *do* define an error logfile for a <VirtualHost>
+# container, that host's errors will be logged there and not here.
+#
+ErrorLog /var/log/apache2/error_log
+
+#
+# LogLevel: Control the number of messages logged to the error_log.
+# Possible values include: debug, info, notice, warn, error, crit,
+# alert, emerg.
+#
+LogLevel warn
+
+<IfModule log_config_module>
+    #
+    # The following directives define some format nicknames for use with
+    # a CustomLog directive (see below).
+    #
+    LogFormat "%h %l %u %t \"%r\" %>s %b \"%{Referer}i\" \"%{User-Agent}i\"" combined
+    LogFormat "%h %l %u %t \"%r\" %>s %b" common
+
+    <IfModule logio_module>
+      # You need to enable mod_logio.c to use %I and %O
+      LogFormat "%h %l %u %t \"%r\" %>s %b \"%{Referer}i\" \"%{User-Agent}i\" %I %O" combinedio
+    </IfModule>
+
+    #
+    # The location and format of the access logfile (Common Logfile Format).
+    # If you do not define any access logfiles within a <VirtualHost>
+    # container, they will be logged here.  Contrariwise, if you *do*
+    # define per-<VirtualHost> access logfiles, transactions will be
+    # logged therein and *not* in this file.
+    #
+    CustomLog /var/log/apache2/access_log common
+
+    #
+    # If you prefer a logfile with access, agent, and referer information
+    # (Combined Logfile Format) you can use the following directive.
+    #
+    #CustomLog /var/log/apache2/access_log combined
+</IfModule>
+
+<IfModule alias_module>
+    #
+    # Redirect: Allows you to tell clients about documents that used to
+    # exist in your server's namespace, but do not anymore. The client
+    # will make a new request for the document at its new location.
+    # Example:
+    # Redirect permanent /foo http://www.example.com/bar
+
+    #
+    # Alias: Maps web paths into filesystem paths and is used to
+    # access content that does not live under the DocumentRoot.
+    # Example:
+    # Alias /webpath /full/filesystem/path
+    #
+    # If you include a trailing / on /webpath then the server will
+    # require it to be present in the URL.  You will also likely
+    # need to provide a <Directory> section to allow access to
+    # the filesystem path.
+
+    #
+    # ScriptAlias: This controls which directories contain server scripts.
+    # ScriptAliases are essentially the same as Aliases, except that
+    # documents in the target directory are treated as applications and
+    # run by the server when requested rather than as documents sent to the
+    # client.  The same rules about trailing "/" apply to ScriptAlias
+    # directives as to Alias.
+    #
+    ScriptAlias /cgi-bin/ "/usr/lib/cgi-bin/"
+
+</IfModule>
+
+<IfModule cgid_module>
+    #
+    # ScriptSock: On threaded servers, designate the path to the UNIX
+    # socket used to communicate with the CGI daemon of mod_cgid.
+    #
+    #Scriptsock /var/run/apache2/cgisock
+</IfModule>
+
+#
+# "/usr/lib/cgi-bin" should be changed to whatever your ScriptAliased
+# CGI directory exists, if you have that configured.
+#
+<Directory "/usr/lib/cgi-bin">
+    AllowOverride None
+    Options None
+    Order allow,deny
+    Allow from all
+</Directory>
+
+#
+# DefaultType: the default MIME type the server will use for a document
+# if it cannot otherwise determine one, such as from filename extensions.
+# If your server contains mostly text or HTML documents, "text/plain" is
+# a good value.  If most of your content is binary, such as applications
+# or images, you may want to use "application/octet-stream" instead to
+# keep browsers from trying to display binary files as though they are
+# text.
+#
+DefaultType text/plain
+
+<IfModule mime_module>
+    #
+    # TypesConfig points to the file containing the list of mappings from
+    # filename extension to MIME-type.
+    #
+    TypesConfig /etc/apache2/mime.types
+
+    #
+    # AddType allows you to add to or override the MIME configuration
+    # file specified in TypesConfig for specific file types.
+    #
+    #AddType application/x-gzip .tgz
+    #
+    # AddEncoding allows you to have certain browsers uncompress
+    # information on the fly. Note: Not all browsers support this.
+    #
+    #AddEncoding x-compress .Z
+    #AddEncoding x-gzip .gz .tgz
+    #
+    # If the AddEncoding directives above are commented-out, then you
+    # probably should define those extensions to indicate media types:
+    #
+    AddType application/x-compress .Z
+    AddType application/x-gzip .gz .tgz
+
+    #
+    # AddHandler allows you to map certain file extensions to "handlers":
+    # actions unrelated to filetype. These can be either built into the server
+    # or added with the Action directive (see below)
+    #
+    # To use CGI scripts outside of ScriptAliased directories:
+    # (You will also need to add "ExecCGI" to the "Options" directive.)
+    #
+    #AddHandler cgi-script .cgi
+
+    # For type maps (negotiated resources):
+    #AddHandler type-map var
+
+    #
+    # Filters allow you to process content before it is sent to the client.
+    #
+    # To parse .shtml files for server-side includes (SSI):
+    # (You will also need to add "Includes" to the "Options" directive.)
+    #
+    #AddType text/html .shtml
+    #AddOutputFilter INCLUDES .shtml
+</IfModule>
+
+#
+# The mod_mime_magic module allows the server to use various hints from the
+# contents of the file itself to determine its type.  The MIMEMagicFile
+# directive tells the module where the hint definitions are located.
+#
+#MIMEMagicFile /etc/apache2/magic
+
+#
+# Customizable error responses come in three flavors:
+# 1) plain text 2) local redirects 3) external redirects
+#
+# Some examples:
+#ErrorDocument 500 "The server made a boo boo."
+#ErrorDocument 404 /missing.html
+#ErrorDocument 404 "/cgi-bin/missing_handler.pl"
+#ErrorDocument 402 http://www.example.com/subscription_info.html
+#
+
+#
+# EnableMMAP and EnableSendfile: On systems that support it,
+# memory-mapping or the sendfile syscall is used to deliver
+# files.  This usually improves server performance, but must
+# be turned off when serving from networked-mounted
+# filesystems or if support for these functions is otherwise
+# broken on your system.
+#
+#EnableMMAP off
+#EnableSendfile off
+
+# Supplemental configuration
+#
+# The configuration files in the /etc/apache2/extra/ directory can be
+# included to add extra features or to modify the default configuration of
+# the server, or you may simply copy their contents here and change as
+# necessary.
+
+# Server-pool management (MPM specific)
+#Include /etc/apache2/extra/httpd-mpm.conf
+
+# Multi-language error messages
+#Include /etc/apache2/extra/httpd-multilang-errordoc.conf
+
+# Fancy directory listings
+#Include /etc/apache2/extra/httpd-autoindex.conf
+
+# Language settings
+#Include /etc/apache2/extra/httpd-languages.conf
+
+# User home directories
+#Include /etc/apache2/extra/httpd-userdir.conf
+
+# Real-time info on requests and configuration
+#Include /etc/apache2/extra/httpd-info.conf
+
+# Virtual hosts
+#Include /etc/apache2/extra/httpd-vhosts.conf
+
+# Local access to the Apache HTTP Server Manual
+#Include /etc/apache2/extra/httpd-manual.conf
+
+# Distributed authoring and versioning (WebDAV)
+#Include /etc/apache2/extra/httpd-dav.conf
+
+# Various default settings
+#Include /etc/apache2/extra/httpd-default.conf
+
+# Secure (SSL/TLS) connections
+#Include /etc/apache2/extra/httpd-ssl.conf
+#
+# Note: The following must must be present to support
+#       starting without SSL on platforms with no /dev/random equivalent
+#       but a statically compiled-in mod_ssl.
+#
+<IfModule ssl_module>
+SSLRandomSeed startup builtin
+SSLRandomSeed connect builtin
+</IfModule>

samples/ApacheConf/filenames/httpd.conf

@@ -0,0 +1,500 @@
+#
+# This is the main Apache HTTP server configuration file.  It contains the
+# configuration directives that give the server its instructions.
+# See <URL:http://httpd.apache.org/docs/2.2> for detailed information.
+# In particular, see 
+# <URL:http://httpd.apache.org/docs/2.2/mod/directives.html>
+# for a discussion of each configuration directive.
+#
+# Do NOT simply read the instructions in here without understanding
+# what they do.  They're here only as hints or reminders.  If you are unsure
+# consult the online docs. You have been warned.  
+#
+# Configuration and logfile names: If the filenames you specify for many
+# of the server's control files begin with "/" (or "drive:/" for Win32), the
+# server will use that explicit path.  If the filenames do *not* begin
+# with "/", the value of ServerRoot is prepended -- so "log/foo_log"
+# with ServerRoot set to "/usr" will be interpreted by the
+# server as "/usr/log/foo_log".
+
+#
+# ServerRoot: The top of the directory tree under which the server's
+# configuration, error, and log files are kept.
+#
+# Do not add a slash at the end of the directory path.  If you point
+# ServerRoot at a non-local disk, be sure to point the LockFile directive
+# at a local disk.  If you wish to share the same ServerRoot for multiple
+# httpd daemons, you will need to change at least LockFile and PidFile.
+#
+ServerRoot "/usr"
+
+#
+# Listen: Allows you to bind Apache to specific IP addresses and/or
+# ports, instead of the default. See also the <VirtualHost>
+# directive.
+#
+# Change this to Listen on specific IP addresses as shown below to 
+# prevent Apache from glomming onto all bound IP addresses.
+#
+#Listen 12.34.56.78:80
+Listen 80
+
+#
+# Dynamic Shared Object (DSO) Support
+#
+# To be able to use the functionality of a module which was built as a DSO you
+# have to place corresponding `LoadModule' lines at this location so the
+# directives contained in it are actually available _before_ they are used.
+# Statically compiled modules (those listed by `httpd -l') do not need
+# to be loaded here.
+#
+# Example:
+# LoadModule foo_module modules/mod_foo.so
+#
+LoadModule authn_file_module libexec/apache2/mod_authn_file.so
+LoadModule authn_dbm_module libexec/apache2/mod_authn_dbm.so
+LoadModule authn_anon_module libexec/apache2/mod_authn_anon.so
+LoadModule authn_dbd_module libexec/apache2/mod_authn_dbd.so
+LoadModule authn_default_module libexec/apache2/mod_authn_default.so
+LoadModule authz_host_module libexec/apache2/mod_authz_host.so
+LoadModule authz_groupfile_module libexec/apache2/mod_authz_groupfile.so
+LoadModule authz_user_module libexec/apache2/mod_authz_user.so
+LoadModule authz_dbm_module libexec/apache2/mod_authz_dbm.so
+LoadModule authz_owner_module libexec/apache2/mod_authz_owner.so
+LoadModule authz_default_module libexec/apache2/mod_authz_default.so
+LoadModule auth_basic_module libexec/apache2/mod_auth_basic.so
+LoadModule auth_digest_module libexec/apache2/mod_auth_digest.so
+LoadModule cache_module libexec/apache2/mod_cache.so
+LoadModule disk_cache_module libexec/apache2/mod_disk_cache.so
+LoadModule mem_cache_module libexec/apache2/mod_mem_cache.so
+LoadModule dbd_module libexec/apache2/mod_dbd.so
+LoadModule dumpio_module libexec/apache2/mod_dumpio.so
+LoadModule reqtimeout_module libexec/apache2/mod_reqtimeout.so
+LoadModule ext_filter_module libexec/apache2/mod_ext_filter.so
+LoadModule include_module libexec/apache2/mod_include.so
+LoadModule filter_module libexec/apache2/mod_filter.so
+LoadModule substitute_module libexec/apache2/mod_substitute.so
+LoadModule deflate_module libexec/apache2/mod_deflate.so
+LoadModule log_config_module libexec/apache2/mod_log_config.so
+LoadModule log_forensic_module libexec/apache2/mod_log_forensic.so
+LoadModule logio_module libexec/apache2/mod_logio.so
+LoadModule env_module libexec/apache2/mod_env.so
+LoadModule mime_magic_module libexec/apache2/mod_mime_magic.so
+LoadModule cern_meta_module libexec/apache2/mod_cern_meta.so
+LoadModule expires_module libexec/apache2/mod_expires.so
+LoadModule headers_module libexec/apache2/mod_headers.so
+LoadModule ident_module libexec/apache2/mod_ident.so
+LoadModule usertrack_module libexec/apache2/mod_usertrack.so
+#LoadModule unique_id_module libexec/apache2/mod_unique_id.so
+LoadModule setenvif_module libexec/apache2/mod_setenvif.so
+LoadModule version_module libexec/apache2/mod_version.so
+LoadModule proxy_module libexec/apache2/mod_proxy.so
+LoadModule proxy_connect_module libexec/apache2/mod_proxy_connect.so
+LoadModule proxy_ftp_module libexec/apache2/mod_proxy_ftp.so
+LoadModule proxy_http_module libexec/apache2/mod_proxy_http.so
+LoadModule proxy_scgi_module libexec/apache2/mod_proxy_scgi.so
+LoadModule proxy_ajp_module libexec/apache2/mod_proxy_ajp.so
+LoadModule proxy_balancer_module libexec/apache2/mod_proxy_balancer.so
+LoadModule ssl_module libexec/apache2/mod_ssl.so
+LoadModule mime_module libexec/apache2/mod_mime.so
+LoadModule dav_module libexec/apache2/mod_dav.so
+LoadModule status_module libexec/apache2/mod_status.so
+LoadModule autoindex_module libexec/apache2/mod_autoindex.so
+LoadModule asis_module libexec/apache2/mod_asis.so
+LoadModule info_module libexec/apache2/mod_info.so
+LoadModule cgi_module libexec/apache2/mod_cgi.so
+LoadModule dav_fs_module libexec/apache2/mod_dav_fs.so
+LoadModule vhost_alias_module libexec/apache2/mod_vhost_alias.so
+LoadModule negotiation_module libexec/apache2/mod_negotiation.so
+LoadModule dir_module libexec/apache2/mod_dir.so
+LoadModule imagemap_module libexec/apache2/mod_imagemap.so
+LoadModule actions_module libexec/apache2/mod_actions.so
+LoadModule speling_module libexec/apache2/mod_speling.so
+LoadModule userdir_module libexec/apache2/mod_userdir.so
+LoadModule alias_module libexec/apache2/mod_alias.so
+LoadModule rewrite_module libexec/apache2/mod_rewrite.so
+#LoadModule perl_module libexec/apache2/mod_perl.so
+#LoadModule php5_module libexec/apache2/libphp5.so
+#LoadModule hfs_apple_module libexec/apache2/mod_hfs_apple.so
+
+<IfModule !mpm_netware_module>
+<IfModule !mpm_winnt_module>
+#
+# If you wish httpd to run as a different user or group, you must run
+# httpd as root initially and it will switch.  
+#
+# User/Group: The name (or #number) of the user/group to run httpd as.
+# It is usually good practice to create a dedicated user and group for
+# running httpd, as with most system services.
+#
+User _www
+Group _www
+
+</IfModule>
+</IfModule>
+
+# 'Main' server configuration
+#
+# The directives in this section set up the values used by the 'main'
+# server, which responds to any requests that aren't handled by a
+# <VirtualHost> definition.  These values also provide defaults for
+# any <VirtualHost> containers you may define later in the file.
+#
+# All of these directives may appear inside <VirtualHost> containers,
+# in which case these default settings will be overridden for the
+# virtual host being defined.
+#
+
+#
+# ServerAdmin: Your address, where problems with the server should be
+# e-mailed.  This address appears on some server-generated pages, such
+# as error documents.  e.g. admin@your-domain.com
+#
+ServerAdmin you@example.com
+
+#
+# ServerName gives the name and port that the server uses to identify itself.
+# This can often be determined automatically, but we recommend you specify
+# it explicitly to prevent problems during startup.
+#
+# If your host doesn't have a registered DNS name, enter its IP address here.
+#
+#ServerName www.example.com:80
+
+#
+# DocumentRoot: The directory out of which you will serve your
+# documents. By default, all requests are taken from this directory, but
+# symbolic links and aliases may be used to point to other locations.
+#
+DocumentRoot "/Library/WebServer/Documents"
+
+#
+# Each directory to which Apache has access can be configured with respect
+# to which services and features are allowed and/or disabled in that
+# directory (and its subdirectories). 
+#
+# First, we configure the "default" to be a very restrictive set of 
+# features.  
+#
+<Directory />
+    Options FollowSymLinks
+    AllowOverride None
+    Order deny,allow
+    Deny from all
+</Directory>
+
+#
+# Note that from this point forward you must specifically allow
+# particular features to be enabled - so if something's not working as
+# you might expect, make sure that you have specifically enabled it
+# below.
+#
+
+#
+# This should be changed to whatever you set DocumentRoot to.
+#
+<Directory "/Library/WebServer/Documents">
+    #
+    # Possible values for the Options directive are "None", "All",
+    # or any combination of:
+    #   Indexes Includes FollowSymLinks SymLinksifOwnerMatch ExecCGI MultiViews
+    #
+    # Note that "MultiViews" must be named *explicitly* --- "Options All"
+    # doesn't give it to you.
+    #
+    # The Options directive is both complicated and important.  Please see
+    # http://httpd.apache.org/docs/2.2/mod/core.html#options
+    # for more information.
+    #
+    Options Indexes FollowSymLinks MultiViews
+
+    #
+    # AllowOverride controls what directives may be placed in .htaccess files.
+    # It can be "All", "None", or any combination of the keywords:
+    #   Options FileInfo AuthConfig Limit
+    #
+    AllowOverride None
+
+    #
+    # Controls who can get stuff from this server.
+    #
+    Order allow,deny
+    Allow from all
+
+</Directory>
+
+#
+# DirectoryIndex: sets the file that Apache will serve if a directory
+# is requested.
+#
+<IfModule dir_module>
+    DirectoryIndex index.html
+</IfModule>
+
+#
+# The following lines prevent .htaccess and .htpasswd files from being 
+# viewed by Web clients. 
+#
+<FilesMatch "^\.([Hh][Tt]|[Dd][Ss]_[Ss])">
+    Order allow,deny
+    Deny from all
+    Satisfy All
+</FilesMatch>
+
+#
+# Apple specific filesystem protection.
+#
+<Files "rsrc">
+    Order allow,deny
+    Deny from all
+    Satisfy All
+</Files>
+<DirectoryMatch ".*\.\.namedfork">
+    Order allow,deny
+    Deny from all
+    Satisfy All
+</DirectoryMatch>
+
+#
+# ErrorLog: The location of the error log file.
+# If you do not specify an ErrorLog directive within a <VirtualHost>
+# container, error messages relating to that virtual host will be
+# logged here.  If you *do* define an error logfile for a <VirtualHost>
+# container, that host's errors will be logged there and not here.
+#
+ErrorLog "/private/var/log/apache2/error_log"
+
+#
+# LogLevel: Control the number of messages logged to the error_log.
+# Possible values include: debug, info, notice, warn, error, crit,
+# alert, emerg.
+#
+LogLevel warn
+
+<IfModule log_config_module>
+    #
+    # The following directives define some format nicknames for use with
+    # a CustomLog directive (see below).
+    #
+    LogFormat "%h %l %u %t \"%r\" %>s %b \"%{Referer}i\" \"%{User-Agent}i\"" combined
+    LogFormat "%h %l %u %t \"%r\" %>s %b" common
+
+    <IfModule logio_module>
+      # You need to enable mod_logio.c to use %I and %O
+      LogFormat "%h %l %u %t \"%r\" %>s %b \"%{Referer}i\" \"%{User-Agent}i\" %I %O" combinedio
+    </IfModule>
+
+    #
+    # The location and format of the access logfile (Common Logfile Format).
+    # If you do not define any access logfiles within a <VirtualHost>
+    # container, they will be logged here.  Contrariwise, if you *do*
+    # define per-<VirtualHost> access logfiles, transactions will be
+    # logged therein and *not* in this file.
+    #
+    CustomLog "/private/var/log/apache2/access_log" common
+
+    #
+    # If you prefer a logfile with access, agent, and referer information
+    # (Combined Logfile Format) you can use the following directive.
+    #
+    #CustomLog "/private/var/log/apache2/access_log" combined
+</IfModule>
+
+<IfModule alias_module>
+    #
+    # Redirect: Allows you to tell clients about documents that used to 
+    # exist in your server's namespace, but do not anymore. The client 
+    # will make a new request for the document at its new location.
+    # Example:
+    # Redirect permanent /foo http://www.example.com/bar
+
+    #
+    # Alias: Maps web paths into filesystem paths and is used to
+    # access content that does not live under the DocumentRoot.
+    # Example:
+    # Alias /webpath /full/filesystem/path
+    #
+    # If you include a trailing / on /webpath then the server will
+    # require it to be present in the URL.  You will also likely
+    # need to provide a <Directory> section to allow access to
+    # the filesystem path.
+
+    #
+    # ScriptAlias: This controls which directories contain server scripts. 
+    # ScriptAliases are essentially the same as Aliases, except that
+    # documents in the target directory are treated as applications and
+    # run by the server when requested rather than as documents sent to the
+    # client.  The same rules about trailing "/" apply to ScriptAlias
+    # directives as to Alias.
+    #
+    ScriptAliasMatch ^/cgi-bin/((?!(?i:webobjects)).*$) "/Library/WebServer/CGI-Executables/$1"
+
+</IfModule>
+
+<IfModule cgid_module>
+    #
+    # ScriptSock: On threaded servers, designate the path to the UNIX
+    # socket used to communicate with the CGI daemon of mod_cgid.
+    #
+    #Scriptsock /private/var/run/cgisock
+</IfModule>
+
+#
+# "/Library/WebServer/CGI-Executables" should be changed to whatever your ScriptAliased
+# CGI directory exists, if you have that configured.
+#
+<Directory "/Library/WebServer/CGI-Executables">
+    AllowOverride None
+    Options None
+    Order allow,deny
+    Allow from all
+</Directory>
+
+#
+# DefaultType: the default MIME type the server will use for a document
+# if it cannot otherwise determine one, such as from filename extensions.
+# If your server contains mostly text or HTML documents, "text/plain" is
+# a good value.  If most of your content is binary, such as applications
+# or images, you may want to use "application/octet-stream" instead to
+# keep browsers from trying to display binary files as though they are
+# text.
+#
+DefaultType text/plain
+
+<IfModule mime_module>
+    #
+    # TypesConfig points to the file containing the list of mappings from
+    # filename extension to MIME-type.
+    #
+    TypesConfig /private/etc/apache2/mime.types
+
+    #
+    # AddType allows you to add to or override the MIME configuration
+    # file specified in TypesConfig for specific file types.
+    #
+    #AddType application/x-gzip .tgz
+    #
+    # AddEncoding allows you to have certain browsers uncompress
+    # information on the fly. Note: Not all browsers support this.
+    #
+    #AddEncoding x-compress .Z
+    #AddEncoding x-gzip .gz .tgz
+    #
+    # If the AddEncoding directives above are commented-out, then you
+    # probably should define those extensions to indicate media types:
+    #
+    AddType application/x-compress .Z
+    AddType application/x-gzip .gz .tgz
+
+    #
+    # AddHandler allows you to map certain file extensions to "handlers":
+    # actions unrelated to filetype. These can be either built into the server
+    # or added with the Action directive (see below)
+    #
+    # To use CGI scripts outside of ScriptAliased directories:
+    # (You will also need to add "ExecCGI" to the "Options" directive.)
+    #
+    #AddHandler cgi-script .cgi
+
+    # For type maps (negotiated resources):
+    #AddHandler type-map var
+
+    #
+    # Filters allow you to process content before it is sent to the client.
+    #
+    # To parse .shtml files for server-side includes (SSI):
+    # (You will also need to add "Includes" to the "Options" directive.)
+    #
+    #AddType text/html .shtml
+    #AddOutputFilter INCLUDES .shtml
+</IfModule>
+
+#
+# The mod_mime_magic module allows the server to use various hints from the
+# contents of the file itself to determine its type.  The MIMEMagicFile
+# directive tells the module where the hint definitions are located.
+#
+#MIMEMagicFile /private/etc/apache2/magic
+
+#
+# Customizable error responses come in three flavors:
+# 1) plain text 2) local redirects 3) external redirects
+#
+# Some examples:
+#ErrorDocument 500 "The server made a boo boo."
+#ErrorDocument 404 /missing.html
+#ErrorDocument 404 "/cgi-bin/missing_handler.pl"
+#ErrorDocument 402 http://www.example.com/subscription_info.html
+#
+
+#
+# MaxRanges: Maximum number of Ranges in a request before
+# returning the entire resource, or one of the special
+# values 'default', 'none' or 'unlimited'.
+# Default setting is to accept 200 Ranges.
+#MaxRanges unlimited
+
+#
+# EnableMMAP and EnableSendfile: On systems that support it, 
+# memory-mapping or the sendfile syscall is used to deliver
+# files.  This usually improves server performance, but must
+# be turned off when serving from networked-mounted 
+# filesystems or if support for these functions is otherwise
+# broken on your system.
+#
+#EnableMMAP off
+#EnableSendfile off
+
+# 6894961
+TraceEnable off
+
+# Supplemental configuration
+#
+# The configuration files in the /private/etc/apache2/extra/ directory can be 
+# included to add extra features or to modify the default configuration of 
+# the server, or you may simply copy their contents here and change as 
+# necessary.
+
+# Server-pool management (MPM specific)
+Include /private/etc/apache2/extra/httpd-mpm.conf
+
+# Multi-language error messages
+#Include /private/etc/apache2/extra/httpd-multilang-errordoc.conf
+
+# Fancy directory listings
+Include /private/etc/apache2/extra/httpd-autoindex.conf
+
+# Language settings
+Include /private/etc/apache2/extra/httpd-languages.conf
+
+# User home directories
+Include /private/etc/apache2/extra/httpd-userdir.conf
+
+# Real-time info on requests and configuration
+#Include /private/etc/apache2/extra/httpd-info.conf
+
+# Virtual hosts
+#Include /private/etc/apache2/extra/httpd-vhosts.conf
+
+# Local access to the Apache HTTP Server Manual
+Include /private/etc/apache2/extra/httpd-manual.conf
+
+# Distributed authoring and versioning (WebDAV)
+#Include /private/etc/apache2/extra/httpd-dav.conf
+
+# Various default settings
+#Include /private/etc/apache2/extra/httpd-default.conf
+
+# Secure (SSL/TLS) connections
+#Include /private/etc/apache2/extra/httpd-ssl.conf
+#
+# Note: The following must must be present to support
+#       starting without SSL on platforms with no /dev/random equivalent
+#       but a statically compiled-in mod_ssl.
+#
+<IfModule ssl_module>
+SSLRandomSeed startup builtin
+SSLRandomSeed connect builtin
+</IfModule>
+
+Include /private/etc/apache2/other/*.conf

samples/C++/gdsdbreader.h

@@ -0,0 +1,69 @@
+#ifndef GDSDBREADER_H
+#define GDSDBREADER_H
+
+// This file contains core structures, classes and types for the entire gds app
+// WARNING: DO NOT MODIFY UNTIL IT'S STRICTLY NECESSARY
+
+#include <QDir>
+#include "diagramwidget/qgldiagramwidget.h"
+
+#define GDS_DIR "gdsdata"
+
+enum level {LEVEL_ONE, LEVEL_TWO, LEVEL_THREE};
+
+// The internal structure of the db to store information about each node (each level)
+// this will be serialized before being written to file
+class dbDataStructure
+{
+public:
+    QString label;
+    quint32 depth;
+    quint32 userIndex;
+    QByteArray data;    // This is COMPRESSED data, optimize ram and disk space, is decompressed
+                        // just when needed (to display the comments)
+
+    // The following ID is used to create second-third level files
+    quint64 uniqueID;
+    // All the next items linked to this one
+    QVector<dbDataStructure*> nextItems;
+    // Corresponding indices vector (used to store data)
+    QVector<quint32> nextItemsIndices;
+    // The father element (or NULL if it's root)
+    dbDataStructure* father;
+    // Corresponding indices vector (used to store data)
+    quint32 fatherIndex;
+    bool noFatherRoot; // Used to tell if this node is the root (so hasn't a father)
+
+    // These fields will be useful for levels 2 and 3
+    QString fileName; // Relative filename for the associated code file
+    QByteArray firstLineData; // Compressed first line data, this will be used with the line number to retrieve info
+    QVector<quint32> linesNumbers; // First and next lines (next are relative to the first) numbers
+
+    // -- Generic system data not to be stored on disk
+    void *glPointer; // GL pointer
+
+    // These operator overrides prevent the glPointer and other non-disk-necessary data serialization
+    friend QDataStream& operator<<(QDataStream& stream, const dbDataStructure& myclass)
+    // Notice: this function has to be "friend" because it cannot be a member function, member functions
+    // have an additional parameter "this" which isn't in the argument list of an operator overload. A friend
+    // function has full access to private data of the class without having the "this" argument
+    {
+        // Don't write glPointer and every pointer-dependent structure
+        return stream << myclass.label << myclass.depth << myclass.userIndex << qCompress(myclass.data)
+                         << myclass.uniqueID << myclass.nextItemsIndices << myclass.fatherIndex << myclass.noFatherRoot
+                            << myclass.fileName << qCompress(myclass.firstLineData) << myclass.linesNumbers;
+    }
+    friend QDataStream& operator>>(QDataStream& stream, dbDataStructure& myclass)
+    {
+        //Don't read it, either
+        stream >> myclass.label >> myclass.depth >> myclass.userIndex >> myclass.data
+                      >> myclass.uniqueID >> myclass.nextItemsIndices >> myclass.fatherIndex >> myclass.noFatherRoot
+                         >> myclass.fileName >> myclass.firstLineData >> myclass.linesNumbers;
+        myclass.data = qUncompress(myclass.data);
+        myclass.firstLineData = qUncompress(myclass.firstLineData);
+        return stream;
+    }
+
+};
+
+#endif // GDSDBREADER_H

samples/C/rf_io.h

@@ -0,0 +1,682 @@
+/**
+** Copyright (c) 2011-2012, Karapetsas Eleftherios
+** All rights reserved.
+**
+** Redistribution and use in source and binary forms, with or without modification, are permitted provided that the following conditions are met:
+**  1. Redistributions of source code must retain the above copyright notice, this list of conditions and the following disclaimer.
+**  2. Redistributions in binary form must reproduce the above copyright notice, this list of conditions and the following disclaimer in
+**     the documentation and/or other materials provided with the distribution.
+**  3. Neither the name of the Original Author of Refu nor the names of its contributors may be used to endorse or promote products derived from
+**
+**  THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES,
+**  INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+**  DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+**  SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
+**  SERVICES;LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY,
+**  WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+**  OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+**/
+
+
+#ifndef REFU_IO_H
+#define REFU_IO_H
+
+#include <rf_setup.h>
+#include <stdio.h>
+
+#ifdef __cplusplus
+extern "C"
+{// opening bracket for calling from C++
+#endif
+
+// New line feed
+#define RF_LF   0xA
+// Carriage Return
+#define RF_CR   0xD
+
+#ifdef REFU_WIN32_VERSION
+    #define i_PLUSB_WIN32   "b"
+#else
+    #define i_PLUSB_WIN32   ""
+#endif
+
+// This is the type that represents the file offset
+#ifdef _MSC_VER
+typedef __int64 foff_rft;
+#else
+#include <sys/types.h>
+typedef off64_t foff_rft;
+#endif
+///Fseek and Ftelll definitions
+#ifdef _MSC_VER
+    #define rfFseek(i_FILE_,i_OFFSET_,i_WHENCE_)    _fseeki64(i_FILE_,i_OFFSET_,i_WHENCE_)
+    #define rfFtell(i_FILE_)                        _ftelli64(i_FILE_)
+#else
+    #define rfFseek(i_FILE_,i_OFFSET_,i_WHENCE_)    fseeko64(i_FILE_,i_OFFSET_,i_WHENCE_)
+    #define rfFtell(i_FILE_)                        ftello64(i_FILE_)
+#endif
+
+/**
+** @defgroup RF_IOGRP I/O
+** @addtogroup RF_IOGRP
+** @{
+**/
+
+// @brief Reads a UTF-8 file descriptor until end of line or EOF is found and returns a UTF-8 byte buffer
+//
+// The file descriptor at @c f must have been opened in <b>binary</b> and not text mode. That means that if under
+// Windows make sure to call fopen with "wb", "rb" e.t.c. instead of the simple "w", "r" e.t.c. since the initial
+// default value under Windows is text mode. Alternatively you can set the initial value using _get_fmode() and
+// _set_fmode(). For more information take a look at the msdn pages here:
+// http://msdn.microsoft.com/en-us/library/ktss1a9b.aspx
+//
+// When the compile flag @c RF_NEWLINE_CRLF is defined (the default case at Windows) then this function
+// shall not be adding any CR character that is found in the file behind a newline character since this is
+// the Windows line ending scheme. Beware though that the returned  read bytes value shall still count the CR character inside.
+//
+// @param[in] f The file descriptor to read
+// @param[out] utf8 Give here a refence to an unitialized char* that will be allocated inside the function
+// and contain the utf8 byte buffer. Needs to be freed by the caller explicitly later
+// @param[out] byteLength Give an @c uint32_t here to receive the length of the @c utf8 buffer in bytes
+// @param[out] bufferSize Give an @c uint32_t here to receive the capacity of the @c utf8 buffer in bytes
+// @param[out] eof Pass a pointer to a char to receive a true or false value in case the end of file
+// with reading this line
+// @return Returns either a positive number for success that represents the number of bytes read from @c f and and error in case something goes wrong.
+// The possible errors to return are the same as rfFgets_UTF8()
+i_DECLIMEX_ int32_t rfFReadLine_UTF8(FILE* f,char** utf8,uint32_t* byteLength,uint32_t* bufferSize,char* eof);
+// @brief Reads a Big Endian UTF-16 file descriptor until end of line or EOF is found and returns a UTF-8 byte buffer
+//
+// The file descriptor at @c f must have been opened in <b>binary</b> and not text mode. That means that if under
+// Windows make sure to call fopen with "wb", "rb" e.t.c. instead of the simple "w", "r" e.t.c. since the initial
+// default value under Windows is text mode. Alternatively you can set the initial value using _get_fmode() and
+// _set_fmode(). For more information take a look at the msdn pages here:
+// http://msdn.microsoft.com/en-us/library/ktss1a9b.aspx
+//
+// When the compile flag @c RF_NEWLINE_CRLF is defined (the default case at Windows) then this function
+// shall not be adding any CR character that is found in the file behind a newline character since this is
+// the Windows line ending scheme. Beware though that the returned  read bytes value shall still count the CR character inside.
+//
+// @param[in] f The file descriptor to read
+// @param[out] utf8 Give here a refence to an unitialized char* that will be allocated inside the function
+// and contain the utf8 byte buffer. Needs to be freed by the caller explicitly later
+// @param[out] byteLength Give an @c uint32_t here to receive the length of the @c utf8 buffer in bytes
+// @param[out] eof Pass a pointer to a char to receive a true or false value in case the end of file
+// with reading this line
+// @return Returns either a positive number for success that represents the number of bytes read from @c f and and error in case something goes wrong.
+// + Any error that can be returned by @ref rfFgets_UTF16BE()
+// + @c RE_UTF16_INVALID_SEQUENCE: Failed to decode the UTF-16 byte stream of the file descriptor
+// + @c RE_UTF8_ENCODING: Failed to encode the UTF-16 of the file descriptor into UTF-8
+i_DECLIMEX_ int32_t rfFReadLine_UTF16BE(FILE* f,char** utf8,uint32_t* byteLength,char* eof);
+// @brief Reads a Little Endian UTF-16 file descriptor until end of line or EOF is found and returns a UTF-8 byte buffer
+//
+// The file descriptor at @c f must have been opened in <b>binary</b> and not text mode. That means that if under
+// Windows make sure to call fopen with "wb", "rb" e.t.c. instead of the simple "w", "r" e.t.c. since the initial
+// default value under Windows is text mode. Alternatively you can set the initial value using _get_fmode() and
+// _set_fmode(). For more information take a look at the msdn pages here:
+// http://msdn.microsoft.com/en-us/library/ktss1a9b.aspx
+//
+// When the compile flag @c RF_NEWLINE_CRLF is defined (the default case at Windows) then this function
+// shall not be adding any CR character that is found in the file behind a newline character since this is
+// the Windows line ending scheme. Beware though that the returned read bytes value shall still count the CR character inside.
+//
+// @param[in] f The file descriptor to read
+// @param[out] utf8 Give here a refence to an unitialized char* that will be allocated inside the function
+// and contain the utf8 byte buffer. Needs to be freed by the caller explicitly later
+// @param[out] byteLength Give an @c uint32_t here to receive the length of the @c utf8 buffer in bytes
+// @param[out] eof Pass a pointer to a char to receive a true or false value in case the end of file
+// with reading this line
+// @return Returns either a positive number for success that represents the number of bytes read from @c f and and error in case something goes wrong.
+// + Any error that can be returned by @ref rfFgets_UTF16LE()
+// + @c RE_UTF16_INVALID_SEQUENCE: Failed to decode the UTF-16 byte stream of the file descriptor
+// + @c RE_UTF8_ENCODING: Failed to encode the UTF-16 of the file descriptor into UTF-8
+i_DECLIMEX_ int32_t rfFReadLine_UTF16LE(FILE* f,char** utf8,uint32_t* byteLength,char* eof);
+
+// @brief Reads a Big Endian UTF-32 file descriptor until end of line or EOF is found and returns a UTF-8 byte buffer
+//
+// The file descriptor at @c f must have been opened in <b>binary</b> and not text mode. That means that if under
+// Windows make sure to call fopen with "wb", "rb" e.t.c. instead of the simple "w", "r" e.t.c. since the initial
+// default value under Windows is text mode. Alternatively you can set the initial value using _get_fmode() and
+// _set_fmode(). For more information take a look at the msdn pages here:
+// http://msdn.microsoft.com/en-us/library/ktss1a9b.aspx
+//
+// When the compile flag @c RF_NEWLINE_CRLF is defined (the default case at Windows) then this function
+// shall not be adding any CR character that is found in the file behind a newline character since this is
+// the Windows line ending scheme. Beware though that the returned read bytes value shall still count the CR character inside.
+//
+// @param[in] f The file descriptor to read
+// @param[out] utf8 Give here a refence to an unitialized char* that will be allocated inside the function
+// and contain the utf8 byte buffer. Needs to be freed by the caller explicitly later
+// @param[out] byteLength Give an @c uint32_t here to receive the length of the @c utf8 buffer in bytes
+// @param[out] eof Pass a pointer to a char to receive a true or false value in case the end of file
+// with reading this line
+// @return Returns either a positive number for success that represents the number of bytes read from @c f and and error in case something goes wrong.
+// + Any error that can be returned by @ref rfFgets_UTF32BE()
+// + @c RE_UTF8_ENCODING: Failed to encode the UTF-16 of the file descriptor into UTF-8
+i_DECLIMEX_ int32_t rfFReadLine_UTF32BE(FILE* f,char** utf8,uint32_t* byteLength,char* eof);
+// @brief Reads a Little Endian UTF-32 file descriptor until end of line or EOF is found and returns a UTF-8 byte buffer
+//
+// The file descriptor at @c f must have been opened in <b>binary</b> and not text mode. That means that if under
+// Windows make sure to call fopen with "wb", "rb" e.t.c. instead of the simple "w", "r" e.t.c. since the initial
+// default value under Windows is text mode. Alternatively you can set the initial value using _get_fmode() and
+// _set_fmode(). For more information take a look at the msdn pages here:
+// http://msdn.microsoft.com/en-us/library/ktss1a9b.aspx
+//
+// When the compile flag @c RF_NEWLINE_CRLF is defined (the default case at Windows) then this function
+// shall not be adding any CR character that is found in the file behind a newline character since this is
+// the Windows line ending scheme. Beware though that the returned read bytes value shall still count the CR character inside.
+//
+// @param[in] f The file descriptor to read
+// @param[out] utf8 Give here a refence to an unitialized char* that will be allocated inside the function
+// and contain the utf8 byte buffer. Needs to be freed by the caller explicitly later
+// @param[out] byteLength Give an @c uint32_t here to receive the length of the @c utf8 buffer in bytes
+// @param[out] eof Pass a pointer to a char to receive a true or false value in case the end of file
+// with reading this line
+// @return Returns either a positive number for success that represents the number of bytes read from @c f and and error in case something goes wrong.
+// + Any error that can be returned by @ref rfFgets_UTF32LE()
+// + @c RE_UTF8_ENCODING: Failed to encode the UTF-16 of the file descriptor into UTF-8
+i_DECLIMEX_ int32_t rfFReadLine_UTF32LE(FILE* f,char** utf8,uint32_t* byteLength,char* eof);
+
+// @brief Gets a number of bytes from a BIG endian UTF-32 file descriptor
+//
+// This is a function that's similar to c library fgets but it also returns the number of bytes read. Reads in from the file until @c num bytes
+// have been read or new line or EOF character has been encountered.
+//
+// The function will read until @c num characters are read and if @c num
+// would take us to the middle of a UTF32 character then the next character shall also be read
+// and the function will return the number of bytes read.
+// Since the function null terminates the buffer the given @c buff needs to be of at least
+// @c num+7 size to cater for the worst case.
+//
+// The final bytestream stored inside @c buff is in the endianess of the system.
+//
+// If right after the last character read comes the EOF, the function
+// shall detect so and assign @c true to @c eof.
+//
+// In Windows where file endings are in the form of 2 bytes CR-LF (Carriage return - NewLine) this function
+// shall just ignore the carriage returns and not return it inside the return buffer at @c buff.
+//
+// The file descriptor at @c f must have been opened in <b>binary</b> and not text mode. That means that if under
+// Windows make sure to call fopen with "wb", "rb" e.t.c. instead of the simple "w", "r" e.t.c. since the initial
+// default value under Windows is text mode. Alternatively you can set the initial value using _get_fmode() and
+// _set_fmode(). For more information take a look at the msdn pages here:
+// http://msdn.microsoft.com/en-us/library/ktss1a9b.aspx
+//
+// @param[in] buff A buffer to be filled with the contents of the file. Should be of size at least @c num+7
+// @param[in] num The maximum number of bytes to read from within the file NOT including the null terminating character(which in itelf is 4 bytes). Should be a multiple of 4
+// @param[in] f A valid FILE descriptor from which to read the bytes
+// @param[out] eof Pass a reference to a char to receive a true/false value for whether EOF has been reached.
+// @return Returns the actual number of bytes read or an error if there was a problem.
+// The possible errors are:
+// + @c RE_FILE_READ: If during reading the file there was an unknown read error
+// + @c RE_FILE_READ_BLOCK: If the read operation failed due to the file descriptor being occupied by another thread
+// + @c RE_FILE_MODE: If during reading the file the file descriptor's mode was not correctly set for reading
+// + @c RE_FILE_POS_OVERFLOW: If during reading, the current file position can't be represented by the system
+// + @c RE_INTERRUPT: If during reading, there was a system interrupt
+// + @c RE_FILE_IO: If there was a physical I/O error
+// + @c RE_FILE_NOSPACE: If reading failed due to insufficient storage space
+i_DECLIMEX_ int32_t rfFgets_UTF32BE(char* buff,uint32_t num,FILE* f,char* eof);
+// @brief Gets a number of bytes from a Little endian UTF-32 file descriptor
+//
+// This is a function that's similar to c library fgets but it also returns the number of bytes read. Reads in from the file until @c num bytes
+// have been read or new line or EOF character has been encountered.
+//
+// The function will read until @c num characters are read and if @c num
+// would take us to the middle of a UTF32 character then the next character shall also be read
+// and the function will return the number of bytes read.
+// Since the function null terminates the buffer the given @c buff needs to be of at least
+// @c num+7 size to cater for the worst case.
+//
+// The final bytestream stored inside @c buff is in the endianess of the system.
+//
+// If right after the last character read comes the EOF, the function
+// shall detect so and assign @c true to @c eof.
+//
+// In Windows where file endings are in the form of 2 bytes CR-LF (Carriage return - NewLine) this function
+// shall just ignore the carriage returns and not return it inside the return buffer at @c buff.
+//
+// The file descriptor at @c f must have been opened in <b>binary</b> and not text mode. That means that if under
+// Windows make sure to call fopen with "wb", "rb" e.t.c. instead of the simple "w", "r" e.t.c. since the initial
+// default value under Windows is text mode. Alternatively you can set the initial value using _get_fmode() and
+// _set_fmode(). For more information take a look at the msdn pages here:
+// http://msdn.microsoft.com/en-us/library/ktss1a9b.aspx
+//
+// @param[in] buff A buffer to be filled with the contents of the file. Should be of size at least @c num+7
+// @param[in] num The maximum number of bytes to read from within the file NOT including the null terminating character(which in itelf is 4 bytes). Should be a multiple of 4
+// @param[in] f A valid FILE descriptor from which to read the bytes
+// @param[out] eof Pass a reference to a char to receive a true/false value for whether EOF has been reached.
+// @return Returns the actual number of bytes read or an error if there was a problem.
+// The possible errors are:
+// + @c RE_FILE_READ: If during reading the file there was an unknown read error
+// + @c RE_FILE_READ_BLOCK: If the read operation failed due to the file descriptor being occupied by another thread
+// + @c RE_FILE_MODE: If during reading the file the file descriptor's mode was not correctly set for reading
+// + @c RE_FILE_POS_OVERFLOW: If during reading, the current file position can't be represented by the system
+// + @c RE_INTERRUPT: If during reading, there was a system interrupt
+// + @c RE_FILE_IO: If there was a physical I/O error
+// + @c RE_FILE_NOSPACE: If reading failed due to insufficient storage space
+i_DECLIMEX_ int32_t rfFgets_UTF32LE(char* buff,uint32_t num,FILE* f,char* eof);
+
+// @brief Gets a number of bytes from a BIG endian UTF-16 file descriptor
+//
+// This is a function that's similar to c library fgets but it also returns the number of bytes read. Reads in from the file until @c num bytes
+// have been read or new line or EOF character has been encountered.
+//
+// The function will read until @c num characters are read and if @c num
+// would take us to the middle of a UTF16 character then the next character shall also be read
+// and the function will return the number of bytes read.
+// Since the function null terminates the buffer the given @c buff needs to be of at least
+// @c num+5 size to cater for the worst case.
+//
+// The final bytestream stored inside @c buff is in the endianess of the system.
+//
+// If right after the last character read comes the EOF, the function
+// shall detect so and assign @c true to @c eof.
+//
+// In Windows where file endings are in the form of 2 bytes CR-LF (Carriage return - NewLine) this function
+// shall just ignore the carriage returns and not return it inside the return buffer at @c buff.
+//
+// The file descriptor at @c f must have been opened in <b>binary</b> and not text mode. That means that if under
+// Windows make sure to call fopen with "wb", "rb" e.t.c. instead of the simple "w", "r" e.t.c. since the initial
+// default value under Windows is text mode. Alternatively you can set the initial value using _get_fmode() and
+// _set_fmode(). For more information take a look at the msdn pages here:
+// http://msdn.microsoft.com/en-us/library/ktss1a9b.aspx
+//
+// @param[in] buff A buffer to be filled with the contents of the file. Should be of size at least @c num+5
+// @param[in] num The maximum number of bytes to read from within the file NOT including the null terminating character(which in itelf is 2 bytes). Should be a multiple of 2
+// @param[in] f A valid FILE descriptor from which to read the bytes
+// @param[out] eof Pass a reference to a char to receive a true/false value for whether EOF has been reached.
+// @return Returns the actual number of bytes read or an error if there was a problem.
+// The possible errors are:
+// + @c RE_FILE_READ: If during reading the file there was an unknown read error
+// + @c RE_FILE_READ_BLOCK: If the read operation failed due to the file descriptor being occupied by another thread
+// + @c RE_FILE_MODE: If during reading the file the file descriptor's mode was not correctly set for reading
+// + @c RE_FILE_POS_OVERFLOW: If during reading, the current file position can't be represented by the system
+// + @c RE_INTERRUPT: If during reading, there was a system interrupt
+// + @c RE_FILE_IO: If there was a physical I/O error
+// + @c RE_FILE_NOSPACE: If reading failed due to insufficient storage space
+i_DECLIMEX_ int32_t rfFgets_UTF16BE(char* buff,uint32_t num,FILE* f,char* eof);
+// @brief Gets a number of bytes from a Little endian UTF-16 file descriptor
+//
+// This is a function that's similar to c library fgets but it also returns the number of bytes read. Reads in from the file until @c num bytes
+// have been read or new line or EOF character has been encountered.
+//
+// The function will read until @c num characters are read and if @c num
+// would take us to the middle of a UTF16 character then the next character shall also be read
+// and the function will return the number of bytes read.
+// Since the function null terminates the buffer the given @c buff needs to be of at least
+// @c num+5 size to cater for the worst case.
+//
+// The final bytestream stored inside @c buff is in the endianess of the system.
+//
+// If right after the last character read comes the EOF, the function
+// shall detect so and assign @c true to @c eof.
+//
+// In Windows where file endings are in the form of 2 bytes CR-LF (Carriage return - NewLine) this function
+// shall just ignore the carriage returns and not return it inside the return buffer at @c buff.
+//
+// The file descriptor at @c f must have been opened in <b>binary</b> and not text mode. That means that if under
+// Windows make sure to call fopen with "wb", "rb" e.t.c. instead of the simple "w", "r" e.t.c. since the initial
+// default value under Windows is text mode. Alternatively you can set the initial value using _get_fmode() and
+// _set_fmode(). For more information take a look at the msdn pages here:
+// http://msdn.microsoft.com/en-us/library/ktss1a9b.aspx
+//
+// @param[in] buff A buffer to be filled with the contents of the file. Should be of size at least @c num+2
+// @param[in] num The maximum number of bytes to read from within the file NOT including the null terminating character(which in itelf is 2 bytes). Should be a multiple of 2
+// @param[in] f A valid FILE descriptor from which to read the bytes
+// @param[out] eof Pass a reference to a char to receive a true/false value for whether EOF has been reached.
+// @return Returns the actual number of bytes read or an error if there was a problem.
+// The possible errors are:
+// + @c RE_FILE_READ: If during reading the file there was an unknown read error
+// + @c RE_FILE_READ_BLOCK: If the read operation failed due to the file descriptor being occupied by another thread
+// + @c RE_FILE_MODE: If during reading the file the file descriptor's mode was not correctly set for reading
+// + @c RE_FILE_POS_OVERFLOW: If during reading, the current file position can't be represented by the system
+// + @c RE_INTERRUPT: If during reading, there was a system interrupt
+// + @c RE_FILE_IO: If there was a physical I/O error
+// + @c RE_FILE_NOSPACE: If reading failed due to insufficient storage space
+i_DECLIMEX_ int32_t rfFgets_UTF16LE(char* buff,uint32_t num,FILE* f,char* eof);
+// @brief Gets a number of bytes from a UTF-8 file descriptor
+//
+// This is a function that's similar to c library fgets but it also returns the number of bytes read. Reads in from the file until @c num characters
+// have been read or new line or EOF character has been encountered.
+//
+// The function  automatically adds a null termination character at the end of
+// @c buff but this character is not included in the returned actual number of bytes.
+//
+// The function will read until @c num characters are read and if @c num
+// would take us to the middle of a UTF8 character then the next character shall also be read
+// and the function will return the number of bytes read.
+// Since the function null terminates the buffer the given @c buff needs to be of at least
+// @c num+4 size to cater for the worst case.
+//
+// If right after the last character read comes the EOF, the function
+// shall detect so and assign @c true to @c eof.
+//
+// In Windows where file endings are in the form of 2 bytes CR-LF (Carriage return - NewLine) this function
+// shall just ignore the carriage returns and not return it inside the return buffer at @c buff.
+//
+// The file descriptor at @c f must have been opened in <b>binary</b> and not text mode. That means that if under
+// Windows make sure to call fopen with "wb", "rb" e.t.c. instead of the simple "w", "r" e.t.c. since the initial
+// default value under Windows is text mode. Alternatively you can set the initial value using _get_fmode() and
+// _set_fmode(). For more information take a look at the msdn pages here:
+// http://msdn.microsoft.com/en-us/library/ktss1a9b.aspx
+//
+// @param[in] buff A buffer to be filled with the contents of the file. Should of size at least @c num+4
+// @param[in] num The maximum number of bytes to read from within the file NOT including the null terminating character(which in itelf is 1 byte)
+// @param[in] f A valid FILE descriptor from which to read the bytes
+// @param[out] eof Pass a reference to a char to receive a true/false value for whether EOF has been reached.
+// @return Returns the actual number of bytes read or an error if there was a problem.
+// The possible errors are:
+// + @c RE_UTF8_INVALID_SEQUENCE_INVALID_BYTE: If an invalid UTF-8 byte has been found
+// + @c RE_UTF8_INVALID_SEQUENCE_CONBYTE: If during parsing the file we were expecting a continuation
+// byte and did not find it
+// + @c RE_UTF8_INVALID_SEQUENCE_END: If the null character is encountered in between bytes that should
+// have been continuation bytes
+// + @c RE_FILE_READ: If during reading the file there was an unknown read error
+// + @c RE_FILE_READ_BLOCK: If the read operation failed due to the file descriptor being occupied by another thread
+// + @c RE_FILE_MODE: If during reading the file the file descriptor's mode was not correctly set for reading
+// + @c RE_FILE_POS_OVERFLOW: If during reading, the current file position can't be represented by the system
+// + @c RE_INTERRUPT: If during reading, there was a system interrupt
+// + @c RE_FILE_IO: If there was a physical I/O error
+// + @c RE_FILE_NOSPACE: If reading failed due to insufficient storage space
+i_DECLIMEX_ int32_t rfFgets_UTF8(char* buff,uint32_t num,FILE* f,char* eof);
+
+// @brief  Gets a unicode character from a UTF-8 file descriptor
+//
+// This function attempts to assume a more modern fgetc() role for UTF-8 encoded files.
+// Reads bytes from the File descriptor @c f until a full UTF-8 unicode character has been read
+//
+// After this function the file pointer will have moved either by @c 1, @c 2, @c 3 or @c 4
+// bytes if the return value is positive. You can see how much by checking the return value.
+//
+// You shall need to provide an integer at @c c to contain either the decoded Unicode
+// codepoint or the UTF-8 endoced byte depending on the value of the @c cp argument.
+//
+// @param f A valid FILE descriptor from which to read the bytes
+// @param c Pass an int that will receive either the unicode code point value or
+// the UTF8 bytes depending on the value of the @c cp flag
+// @param cp A boolean flag. If @c true then the int passed at @c c will contain the unicode code point
+// of the read character, so the UTF-8 will be decoded.
+// If @c false the int passed at @c c will contain the value of the read bytes in UTF-8 without any decoding
+// @return Returns the number of bytes read (either @c 1, @c 2, @c 3 or @c 4) or an error if the function
+// fails for some reason. Possible error values are:
+// + @c RE_FILE_EOF: The end of file has been found while reading. If the end of file is encountered
+// in the middle of a UTF-8 encoded character where we would be expecting something different
+// and @c RE_UTF8_INVALID_SEQUENCE_END error is also logged
+// + @c RE_UTF8_INVALID_SEQUENCE_INVALID_BYTE: If an invalid UTF-8 byte has been found
+// + @c RE_UTF8_INVALID_SEQUENCE_CONBYTE: If during parsing the file we were expecting a continuation
+// byte and did not find it
+// + @c RE_UTF8_INVALID_SEQUENCE_END: If the null character is encountered in between bytes that should
+// have been continuation bytes
+// + @c RE_FILE_READ: If during reading the file there was an unknown read error
+// + @c RE_FILE_READ_BLOCK: If the read operation failed due to the file descriptor being occupied by another thread
+// + @c RE_FILE_MODE: If during reading the file the file descriptor's mode was not correctly set for reading
+// + @c RE_FILE_POS_OVERFLOW: If during reading, the current file position can't be represented by the system
+// + @c RE_INTERRUPT: If during reading, there was a system interrupt
+// + @c RE_FILE_IO: If there was a physical I/O error
+// + @c RE_FILE_NOSPACE: If reading failed due to insufficient storage space
+i_DECLIMEX_ int32_t rfFgetc_UTF8(FILE* f,uint32_t *c,char cp);
+// @brief  Gets a unicode character from a UTF-16 Big Endian file descriptor
+//
+// This function attempts to assume a more modern fgetc() role for UTF-16 encoded files.
+// Reads bytes from the File descriptor @c f until a full UTF-16 unicode character has been read
+//
+// After this function the file pointer will have moved either by @c 2 or @c 4
+// bytes if the return value is positive. You can see how much by checking the return value.
+//
+// You shall need to provide an integer at @c c to contain either the decoded Unicode
+// codepoint or the Bigendian encoded UTF-16 bytes depending on the value of @c the cp argument.
+//
+// @param f A valid FILE descriptor from which to read the bytes
+// @param c Pass an int that will receive either the unicode code point value or
+// the UTF16 bytes depending on the value of the @c cp flag
+// @param cp A boolean flag. If @c true then the int passed at @c c will contain the unicode code point
+// of the read character, so the UTF-16 will be decoded.
+// If @c false the int passed at @c c will contain the value of the read bytes in UTF-16 without any decoding
+// @return Returns the number of bytes read (either @c 2 or @c 4) or an error if the function
+// fails for some reason. Possible error values are:
+// + @c RE_UTF16_INVALID_SEQUENCE: Either the read word or its surrogate pair if 4 bytes were read held illegal values
+// + @c RE_UTF16_NO_SURRPAIR: According to the first read word a surrogate pair was expected but none was found
+// + @c RE_FILE_EOF: The end of file has been found while reading. If the end of file is encountered
+// while we expect a UTF-16 surrogate pair an appropriate error is logged
+// + @c RE_FILE_READ: If during reading the file there was an unknown read error
+// + @c RE_FILE_READ_BLOCK: If the read operation failed due to the file descriptor being occupied by another thread
+// + @c RE_FILE_MODE: If during reading the file the file descriptor's mode was not correctly set for reading
+// + @c RE_FILE_POS_OVERFLOW: If during reading, the current file position can't be represented by the system
+// + @c RE_INTERRUPT: If during reading, there was a system interrupt
+// + @c RE_FILE_IO: If there was a physical I/O error
+// + @c RE_FILE_NOSPACE: If reading failed due to insufficient storage space
+i_DECLIMEX_ int32_t rfFgetc_UTF16BE(FILE* f,uint32_t *c,char cp);
+// @brief  Gets a unicode character from a UTF-16 Little Endian file descriptor
+//
+// This function attempts to assume a more modern fgetc() role for UTF-16 encoded files.
+// Reads bytes from the File descriptor @c f until a full UTF-16 unicode character has been read
+//
+// After this function the file pointer will have moved either by @c 2 or @c 4
+// bytes if the return value is positive. You can see how much by checking the return value.
+//
+// You shall need to provide an integer at @c c to contain either the decoded Unicode
+// codepoint or the Bigendian encoded UTF-16 bytes depending on the value of @c the cp argument.
+//
+// @param f A valid FILE descriptor from which to read the bytes
+// @param c Pass an int that will receive either the unicode code point value or
+// the UTF16 bytes depending on the value of the @c cp flag
+// @param cp A boolean flag. If @c true then the int passed at @c c will contain the unicode code point
+// of the read character, so the UTF-16 will be decoded.
+// If @c false the int passed at @c c will contain the value of the read bytes in UTF-16 without any decoding
+// @return Returns the number of bytes read (either @c 2 or @c 4) or an error if the function
+// fails for some reason. Possible error values are:
+// + @c RE_UTF16_INVALID_SEQUENCE: Either the read word or its surrogate pair if 4 bytes were read held illegal values
+// + @c RE_UTF16_NO_SURRPAIR: According to the first read word a surrogate pair was expected but none was found
+// + @c RE_FILE_EOF: The end of file has been found while reading. If the end of file is encountered
+// while we expect a UTF-16 surrogate pair an appropriate error is logged
+// + @c RE_FILE_READ: If during reading the file there was an unknown read error
+// + @c RE_FILE_READ_BLOCK: If the read operation failed due to the file descriptor being occupied by another thread
+// + @c RE_FILE_MODE: If during reading the file the file descriptor's mode was not correctly set for reading
+// + @c RE_FILE_POS_OVERFLOW: If during reading, the current file position can't be represented by the system
+// + @c RE_INTERRUPT: If during reading, there was a system interrupt
+// + @c RE_FILE_IO: If there was a physical I/O error
+// + @c RE_FILE_NOSPACE: If reading failed due to insufficient storage space
+i_DECLIMEX_ int32_t rfFgetc_UTF16LE(FILE* f,uint32_t *c,char cp);
+// @brief  Gets a unicode character from a UTF-32 Little Endian file descriptor
+//
+// This function attempts to assume a more modern fgetc() role for UTF-32 encoded files.
+// Reads bytes from the File descriptor @c f until a full UTF-32 unicode character has been read
+//
+// After this function the file pointer will have moved by @c 4
+// bytes if the return value is positive.
+//
+// You shall need to provide an integer at @c to contain the UTF-32 codepoint.
+//
+// @param f A valid FILE descriptor from which to read the bytes
+// @param c Pass an int that will receive either the unicode code point value or
+// the UTF16 bytes depending on the value of the @c cp flag
+// If @c false the int passed at @c c will contain the value of the read bytes in UTF-16 without any decoding
+// @return Returns either @c RF_SUCCESS for succesfull readin or one of the following errors:
+// + @c RE_FILE_EOF: The end of file has been found while reading.
+// + @c RE_FILE_READ: If during reading the file there was an unknown read error
+// + @c RE_FILE_READ_BLOCK: If the read operation failed due to the file descriptor being occupied by another thread
+// + @c RE_FILE_MODE: If during reading the file the file descriptor's mode was not correctly set for reading
+// + @c RE_FILE_POS_OVERFLOW: If during reading, the current file position can't be represented by the system
+// + @c RE_INTERRUPT: If during reading, there was a system interrupt
+// + @c RE_FILE_IO: If there was a physical I/O error
+// + @c RE_FILE_NOSPACE: If reading failed due to insufficient storage space
+i_DECLIMEX_ int32_t rfFgetc_UTF32LE(FILE* f,uint32_t *c);
+// @brief  Gets a unicode character from a UTF-32 Big Endian file descriptor
+//
+// This function attempts to assume a more modern fgetc() role for UTF-32 encoded files.
+// Reads bytes from the File descriptor @c f until a full UTF-32 unicode character has been read
+//
+// After this function the file pointer will have moved by @c 4
+// bytes if the return value is positive.
+//
+// You shall need to provide an integer at @c to contain the UTF-32 codepoint.
+//
+// @param f A valid FILE descriptor from which to read the bytes
+// @param c Pass an int that will receive either the unicode code point value or
+// the UTF16 bytes depending on the value of the @c cp flag
+// If @c false the int passed at @c c will contain the value of the read bytes in UTF-16 without any decoding
+// @return Returns either @c RF_SUCCESS for succesfull readin or one of the following errors:
+// + @c RE_FILE_EOF: The end of file has been found while reading.
+// + @c RE_FILE_READ: If during reading the file there was an unknown read error
+// + @c RE_FILE_READ_BLOCK: If the read operation failed due to the file descriptor being occupied by another thread
+// + @c RE_FILE_MODE: If during reading the file the file descriptor's mode was not correctly set for reading
+// + @c RE_FILE_POS_OVERFLOW: If during reading, the current file position can't be represented by the system
+// + @c RE_INTERRUPT: If during reading, there was a system interrupt
+// + @c RE_FILE_IO: If there was a physical I/O error
+// + @c RE_FILE_NOSPACE: If reading failed due to insufficient storage space
+i_DECLIMEX_ int32_t rfFgetc_UTF32BE(FILE* f,uint32_t *c);
+
+// @brief Moves a unicode character backwards in a big endian UTF-32 file stream
+//
+// @param f The file stream
+// @param c Returns the character we moved back to as a unicode codepoint
+// @return Returns either @c RF_SUCCESS for success or one of the following errors:
+// + @c RE_FILE_POS_OVERFLOW: If during trying to read the current file's position it can't be represented by the system
+// + @c RE_FILE_BAD: If The file descriptor is corrupt/illegal
+// + @c RE_FILE_NOTFILE: If the file descriptor is not a file but something else. e.g. socket.
+// + @c RE_FILE_GETFILEPOS: If the file's position could not be retrieved for some unknown reason
+// + @c RE_FILE_WRITE_BLOCK: While attempting to move the file pointer, it was occupied by another thread, and the no block flag was set
+// + @c RE_INTERRUPT: Operating on the file failed due to a system interrupt
+// + @c RE_FILE_IO: There was a physical I/O error
+// + @c RE_FILE_NOSPACE: There was no space on the device holding the file
+// + @c RE_FILE_NOTFILE: The device we attempted to manipulate is non-existent
+// + @c RE_FILE_READ: If during reading the file there was an error
+// + @c RE_FILE_READ_BLOCK: If during reading the file the read operation failed due to the file being occupied by another thread
+// + @c RE_FILE_MODE: If during reading the file the underlying file descriptor's mode was not correctly set for reading
+i_DECLIMEX_ int32_t rfFback_UTF32BE(FILE* f,uint32_t *c);
+// @brief Moves a unicode character backwards in a little endian UTF-32 file stream
+//
+// The file descriptor at @c f must have been opened in <b>binary</b> and not text mode. That means that if under
+// Windows make sure to call fopen with "wb", "rb" e.t.c. instead of the simple "w", "r" e.t.c. since the initial
+// default value under Windows is text mode. Alternatively you can set the initial value using _get_fmode() and
+// _set_fmode(). For more information take a look at the msdn pages here:
+// http://msdn.microsoft.com/en-us/library/ktss1a9b.aspx
+//
+// @param f The file stream
+// @param c Returns the character we moved back to as a unicode codepoint
+// @return Returns either @c RF_SUCCESS for success or one of the following errors:
+// + @c RE_FILE_POS_OVERFLOW: If during trying to read the current file's position it can't be represented by the system
+// + @c RE_FILE_BAD: If The file descriptor is corrupt/illegal
+// + @c RE_FILE_NOTFILE: If the file descriptor is not a file but something else. e.g. socket.
+// + @c RE_FILE_GETFILEPOS: If the file's position could not be retrieved for some unknown reason
+// + @c RE_FILE_WRITE_BLOCK: While attempting to move the file pointer, it was occupied by another thread, and the no block flag was set
+// + @c RE_INTERRUPT: Operating on the file failed due to a system interrupt
+// + @c RE_FILE_IO: There was a physical I/O error
+// + @c RE_FILE_NOSPACE: There was no space on the device holding the file
+// + @c RE_FILE_NOTFILE: The device we attempted to manipulate is non-existent
+// + @c RE_FILE_READ: If during reading the file there was an error
+// + @c RE_FILE_READ_BLOCK: If during reading the file the read operation failed due to the file being occupied by another thread
+// + @c RE_FILE_MODE: If during reading the file the underlying file descriptor's mode was not correctly set for reading
+i_DECLIMEX_ int32_t rfFback_UTF32LE(FILE* f,uint32_t *c);
+// @brief Moves a unicode character backwards in a big endian UTF-16 file stream
+//
+// The file descriptor at @c f must have been opened in <b>binary</b> and not text mode. That means that if under
+// Windows make sure to call fopen with "wb", "rb" e.t.c. instead of the simple "w", "r" e.t.c. since the initial
+// default value under Windows is text mode. Alternatively you can set the initial value using _get_fmode() and
+// _set_fmode(). For more information take a look at the msdn pages here:
+// http://msdn.microsoft.com/en-us/library/ktss1a9b.aspx
+//
+// @param f The file stream
+// @param c Returns the character we moved back to as a unicode codepoint
+// @return Returns either the number of bytes moved backwards (either @c 4 or @c 2) for success or one of the following errors:
+// + @c RE_UTF16_INVALID_SEQUENCE: Either the read word or its surrogate pair if 4 bytes were read held illegal values
+// + @c RE_FILE_POS_OVERFLOW: If during trying to read the current file's position it can't be represented by the system
+// + @c RE_FILE_BAD: If The file descriptor is corrupt/illegal
+// + @c RE_FILE_NOTFILE: If the file descriptor is not a file but something else. e.g. socket.
+// + @c RE_FILE_GETFILEPOS: If the file's position could not be retrieved for some unknown reason
+// + @c RE_FILE_WRITE_BLOCK: While attempting to move the file pointer, it was occupied by another thread, and the no block flag was set
+// + @c RE_INTERRUPT: Operating on the file failed due to a system interrupt
+// + @c RE_FILE_IO: There was a physical I/O error
+// + @c RE_FILE_NOSPACE: There was no space on the device holding the file
+// + @c RE_FILE_NOTFILE: The device we attempted to manipulate is non-existent
+// + @c RE_FILE_READ: If during reading the file there was an error
+// + @c RE_FILE_READ_BLOCK: If during reading the file the read operation failed due to the file being occupied by another thread
+// + @c RE_FILE_MODE: If during reading the file the underlying file descriptor's mode was not correctly set for reading
+i_DECLIMEX_ int32_t rfFback_UTF16BE(FILE* f,uint32_t *c);
+// @brief Moves a unicode character backwards in a little endian UTF-16 file stream
+//
+// The file descriptor at @c f must have been opened in <b>binary</b> and not text mode. That means that if under
+// Windows make sure to call fopen with "wb", "rb" e.t.c. instead of the simple "w", "r" e.t.c. since the initial
+// default value under Windows is text mode. Alternatively you can set the initial value using _get_fmode() and
+// _set_fmode(). For more information take a look at the msdn pages here:
+// http://msdn.microsoft.com/en-us/library/ktss1a9b.aspx
+//
+// @param f The file stream
+// @param c Returns the character we moved back to as a unicode codepoint
+// @return Returns either the number of bytes moved backwards (either @c 4 or @c 2) for success or one of the following errors:
+// + @c RE_UTF16_INVALID_SEQUENCE: Either the read word or its surrogate pair if 4 bytes were read held illegal values
+// + @c RE_FILE_POS_OVERFLOW: If during trying to read the current file's position it can't be represented by the system
+// + @c RE_FILE_BAD: If The file descriptor is corrupt/illegal
+// + @c RE_FILE_NOTFILE: If the file descriptor is not a file but something else. e.g. socket.
+// + @c RE_FILE_GETFILEPOS: If the file's position could not be retrieved for some unknown reason
+// + @c RE_FILE_WRITE_BLOCK: While attempting to move the file pointer, it was occupied by another thread, and the no block flag was set
+// + @c RE_INTERRUPT: Operating on the file failed due to a system interrupt
+// + @c RE_FILE_IO: There was a physical I/O error
+// + @c RE_FILE_NOSPACE: There was no space on the device holding the file
+// + @c RE_FILE_NOTFILE: The device we attempted to manipulate is non-existent
+// + @c RE_FILE_READ: If during reading the file there was an error
+// + @c RE_FILE_READ_BLOCK: If during reading the file the read operation failed due to the file being occupied by another thread
+// + @c RE_FILE_MODE: If during reading the file the underlying file descriptor's mode was not correctly set for reading
+i_DECLIMEX_ int32_t rfFback_UTF16LE(FILE* f,uint32_t *c);
+// @brief Moves a unicode character backwards in a UTF-8 file stream
+//
+// The file descriptor at @c f must have been opened in <b>binary</b> and not text mode. That means that if under
+// Windows make sure to call fopen with "wb", "rb" e.t.c. instead of the simple "w", "r" e.t.c. since the initial
+// default value under Windows is text mode. Alternatively you can set the initial value using _get_fmode() and
+// _set_fmode(). For more information take a look at the msdn pages here:
+// http://msdn.microsoft.com/en-us/library/ktss1a9b.aspx
+//
+// @param f The file stream
+// @param c Returns the character we moved back to as a unicode codepoint
+// @return Returns either the number of bytes moved backwards for success (either @c 4, @c 3, @c 2 or @c 1) or one of the following errors:
+// + @c RE_UTF8_INVALID_SEQUENCE: If during moving bacwards in the file unexpected UTF-8 bytes were found
+// + @c RE_FILE_POS_OVERFLOW: If during trying to read the current file's position it can't be represented by the system
+// + @c RE_FILE_BAD: If The file descriptor is corrupt/illegal
+// + @c RE_FILE_NOTFILE: If the file descriptor is not a file but something else. e.g. socket.
+// + @c RE_FILE_GETFILEPOS: If the file's position could not be retrieved for some unknown reason
+// + @c RE_FILE_WRITE_BLOCK: While attempting to move the file pointer, it was occupied by another thread, and the no block flag was set
+// + @c RE_INTERRUPT: Operating on the file failed due to a system interrupt
+// + @c RE_FILE_IO: There was a physical I/O error
+// + @c RE_FILE_NOSPACE: There was no space on the device holding the file
+// + @c RE_FILE_NOTFILE: The device we attempted to manipulate is non-existent
+// + @c RE_FILE_READ: If during reading the file there was an error
+// + @c RE_FILE_READ_BLOCK: If during reading the file the read operation failed due to the file being occupied by another thread
+// + @c RE_FILE_MODE: If during reading the file the underlying file descriptor's mode was not correctly set for reading
+i_DECLIMEX_ int32_t rfFback_UTF8(FILE* f,uint32_t *c);
+
+// @brief Opens another process as a pipe
+//
+// This function is a cross-platform popen wrapper. In linux it uses popen and in Windows it uses
+// _popen.
+// @lmsFunction
+// @param command The string with the command to execute. Is basically the name of the program/process you want to spawn
+// with its full path and its parameters. @inhtype{String,StringX} @tmpSTR
+// @param mode The mode you want the pipe to work in. There are two possible values:
+// + @c "r" The calling process can read the spawned command's standard output via the returned stream.
+// + @c "w" The calling process can write to the spawned command's standard input via the returned stream.
+//
+// Anything else will result in an error
+// @return For success popen will return a FILE descriptor that can be used to either read or write from the pipe.
+// If there was an error @c 0 is returned and an error is logged.
+#ifdef RF_IAMHERE_FOR_DOXYGEN
+i_DECLIMEX_ FILE* rfPopen(void* command,const char* mode);
+#else
+i_DECLIMEX_ FILE* i_rfPopen(void* command,const char* mode);
+#define rfPopen(i_CMD_,i_MODE_) i_rfLMS_WRAP2(FILE*,i_rfPopen,i_CMD_,i_MODE_)
+#endif
+
+// @brief Closes a pipe
+//
+// This function is a cross-platform wrapper for pclose. It closes a file descriptor opened with @ref rfPopen() and
+// returns the exit code of the process that was running
+// @param stream The file descriptor of the pipe returned by @ref rfPopen() that we want to close
+// @return Returns the exit code of the process or -1 if there was an error
+i_DECLIMEX_ int rfPclose(FILE* stream);
+
+// @} End of I/O group
+
+#ifdef __cplusplus
+}///closing bracket for calling from C++
+#endif
+
+
+#endif//include guards end

samples/Coq/Heap.v

@@ -1,13 +1,3 @@
-(************************************************************************)
-(*  v      *   The Coq Proof Assistant  /  The Coq Development Team     *)
-(* <O___,, *   INRIA - CNRS - LIX - LRI - PPS - Copyright 1999-2010     *)
-(*   \VV/  **************************************************************)
-(*    //   *      This file is distributed under the terms of the       *)
-(*         *       GNU Lesser General Public License Version 2.1        *)
-(************************************************************************)
-
-(** This file is deprecated, for a tree on list, use [Mergesort.v]. *)
-
 (** A development of Treesort on Heap trees. It has an average
     complexity of O(n.log n) but of O(n²) in the worst case (e.g. if
     the list is already sorted) *)

samples/Coq/PermutSetoid.v

@@ -1,11 +1,3 @@
-(************************************************************************)
-(*  v      *   The Coq Proof Assistant  /  The Coq Development Team     *)
-(* <O___,, *   INRIA - CNRS - LIX - LRI - PPS - Copyright 1999-2010     *)
-(*   \VV/  **************************************************************)
-(*    //   *      This file is distributed under the terms of the       *)
-(*         *       GNU Lesser General Public License Version 2.1        *)
-(************************************************************************)
-
 Require Import Omega Relations Multiset SetoidList.
 
 (** This file is deprecated, use [Permutation.v] instead.

samples/Coq/Permutation.v

@@ -1,17 +1,5 @@
-(************************************************************************)
-(*  v      *   The Coq Proof Assistant  /  The Coq Development Team     *)
-(* <O___,, *   INRIA - CNRS - LIX - LRI - PPS - Copyright 1999-2010     *)
-(*   \VV/  **************************************************************)
-(*    //   *      This file is distributed under the terms of the       *)
-(*         *       GNU Lesser General Public License Version 2.1        *)
-(************************************************************************)
-
-(*********************************************************************)
-(** * List permutations as a composition of adjacent transpositions  *)
-(*********************************************************************)
-
 (* Adapted in May 2006 by Jean-Marc Notin from initial contents by
-   Laurent Théry (Huffmann contribution, October 2003) *)
+   Laurent Thery (Huffmann contribution, October 2003) *)
 
 Require Import List Setoid Compare_dec Morphisms.
 Import ListNotations. (* For notations [] and [a;b;c] *)

samples/Coq/Sorting.v

@@ -1,10 +1,2 @@
-(************************************************************************)
-(*  v      *   The Coq Proof Assistant  /  The Coq Development Team     *)
-(* <O___,, *   INRIA - CNRS - LIX - LRI - PPS - Copyright 1999-2010     *)
-(*   \VV/  **************************************************************)
-(*    //   *      This file is distributed under the terms of the       *)
-(*         *       GNU Lesser General Public License Version 2.1        *)
-(************************************************************************)
-
 Require Export Sorted.
 Require Export Mergesort.

samples/Ecl/sample.ecl

@@ -0,0 +1,42 @@
+/* 
+ * Multi-line comment
+ */
+#option ('slidingJoins', true);
+
+namesRecord :=
+            RECORD
+string20        surname;
+string10        forename;
+integer2        age;
+integer2        dadAge;
+integer2        mumAge;
+            END;
+
+namesRecord2 :=
+            record
+string10        extra;
+namesRecord;
+            end;
+
+namesTable := dataset('x',namesRecord,FLAT);
+namesTable2 := dataset('y',namesRecord2,FLAT);
+
+integer2 aveAgeL(namesRecord l) := (l.dadAge+l.mumAge)/2;
+integer2 aveAgeR(namesRecord2 r) := (r.dadAge+r.mumAge)/2;
+
+// Standard join on a function of left and right
+output(join(namesTable, namesTable2, aveAgeL(left) = aveAgeR(right)));
+
+//Several simple examples of sliding join syntax
+output(join(namesTable, namesTable2, left.age >= right.age - 10 and left.age <= right.age +10));
+output(join(namesTable, namesTable2, left.age between right.age - 10 and right.age +10));
+output(join(namesTable, namesTable2, left.age between right.age + 10 and right.age +30));
+output(join(namesTable, namesTable2, left.age between (right.age + 20) - 10 and (right.age +20) + 10));
+output(join(namesTable, namesTable2, aveAgeL(left) between aveAgeR(right)+10 and aveAgeR(right)+40));
+
+//Same, but on strings.  Also includes age to ensure sort is done by non-sliding before sliding.
+output(join(namesTable, namesTable2, left.surname between right.surname[1..10]+'AAAAAAAAAA' and right.surname[1..10]+'ZZZZZZZZZZ' and left.age=right.age));
+output(join(namesTable, namesTable2, left.surname between right.surname[1..10]+'AAAAAAAAAA' and right.surname[1..10]+'ZZZZZZZZZZ' and left.age=right.age,all));
+
+//This should not generate a self join
+output(join(namesTable, namesTable, left.age between right.age - 10 and right.age +10));

samples/Elm/Basic.elm

@@ -0,0 +1,127 @@
+
+import List (intercalate,intersperse)
+import Website.Skeleton
+import Website.ColorScheme
+
+addFolder folder lst =
+  let add (x,y) = (x, folder ++ y ++ ".elm") in
+  let f (n,xs) = (n, map add xs) in
+  map f lst
+
+elements = addFolder "Elements/"
+  [ ("Primitives",
+        [ ("Text"  , "HelloWorld")
+        , ("Images", "Image")
+        , ("Fitted Images", "FittedImage")
+        , ("Videos", "Video")
+        , ("Markdown", "Markdown")
+        ])
+  , ("Formatting",
+        [ ("Size"    , "Size")
+        , ("Opacity" , "Opacity")
+        , ("Text"    , "Text")
+        , ("Typeface", "Typeface")
+        ])
+  , ("Layout",
+        [ ("Simple Flow", "FlowDown1a")
+        , ("Flow Down"  , "FlowDown2")
+        , ("Layers"     , "Layers")
+        , ("Positioning", "Position")
+        , ("Spacers"    , "Spacer")
+        ])
+  , ("Collage", [ ("Lines"     , "Lines")
+                , ("Shapes"    , "Shapes")
+                , ("Sprites"   , "Sprite")
+                , ("Elements"  , "ToForm")
+                , ("Colors"    , "Color")
+                , ("Textures"  , "Texture")
+                , ("Transforms", "Transforms")
+                ])
+  ]
+
+
+functional = addFolder "Functional/"
+  [ ("Recursion",
+        [ ("Factorial"  , "Factorial")
+        , ("List Length", "Length")
+        , ("Zip"        , "Zip")
+        , ("Quick Sort" , "QuickSort")
+        ])
+  , ("Functions",
+        [ ("Anonymous Functions", "Anonymous")
+        , ("Application"        , "Application")
+        , ("Composition"        , "Composition")
+        , ("Infix Operators"    , "Infix")
+        ])
+  , ("Higher-Order",
+        [ ("Map"    , "Map")
+        , ("Fold"   , "Sum")
+        , ("Filter" , "Filter")
+        , ("ZipWith", "ZipWith")
+        ])
+  , ("Data Types",
+        [ ("Maybe", "Maybe")
+        , ("Boolean Expressions", "BooleanExpressions")
+        , ("Tree", "Tree")
+        ])
+  ]
+
+reactive = addFolder "Reactive/"
+  [ ("Mouse",  [ ("Position", "Position")
+               , ("Presses"    , "IsDown")
+               , ("Clicks"    , "CountClicks")
+               , ("Position+Image", "ResizeYogi")
+               , ("Position+Collage"    , "Transforms")
+               -- , ("Hover"     , "IsAbove")
+               ])
+  ,("Keyboard",[ ("Keys Down"  , "KeysDown")
+               , ("Key Presses", "CharPressed")
+               ])
+  , ("Window", [ ("Size", "ResizePaint")
+               , ("Centering", "Centering")
+               ])
+  , ("Time",   [ ("Before and After", "Between")
+               , ("Every"           , "Every")
+               , ("Clock"           , "Clock")
+               ])
+  , ("Input",  [ ("Text Fields", "TextField")
+               , ("Passwords"  , "Password")
+               , ("Check Boxes", "CheckBox")
+               , ("String Drop Down", "StringDropDown")
+               , ("Drop Down", "DropDown")
+               ])
+  , ("Random", [ ("Randomize", "Randomize") ])
+  , ("HTTP",   [ ("Zip Codes", "ZipCodes") ])
+  , ("Filters",[ ("Sample", "SampleOn")
+               , ("Keep If", "KeepIf")
+               , ("Drop Repeats", "DropRepeats")
+               ])
+  ]
+
+example (name, loc) = Text.link ("/edit/examples/" ++ loc) (toText name)
+toLinks (title, links) =
+  flow right [ width 130 (text $ toText "   " ++ italic (toText title))
+             , text (intercalate (bold . Text.color accent4 $ toText "  ·  ") $ map example links)
+             ]
+
+insertSpace lst = case lst of { x:xs -> x : spacer 1 5 : xs ; [] -> [] }
+
+subsection w (name,info) =
+  flow down . insertSpace . intersperse (spacer 1 1) . map (width w) $
+    (text . bold $ toText name) : map toLinks info
+
+words = [markdown|
+
+### Basic Examples
+
+Each example listed below focuses on a single function or concept.
+These examples demonstrate all of the basic building blocks of Elm.
+
+|]
+
+content w =
+  words : map (subsection w) [ ("Display",elements), ("React",reactive), ("Compute",functional) ]
+
+exampleSets w = flow down . map (width w) . intersperse (plainText " ") $ content w
+
+main = lift (skeleton exampleSets) Window.width

samples/Elm/QuickSort.elm

@@ -0,0 +1,32 @@
+
+main = asText (qsort [3,9,1,8,5,4,7])
+
+qsort lst =
+  case lst of
+    x:xs -> qsort (filter ((>=)x) xs) ++ [x] ++ qsort (filter ((<)x) xs)
+    [] -> []
+
+
+{---------------------
+
+QuickSort works as follows:
+ - Choose a pivot element which be placed in the "middle" of the sorted list.
+   In our case we are choosing the first element as the pivot.
+ - Gather all of the elements less than the pivot (the first filter).
+   We know that these must come before our pivot element in the sorted list.
+   Note: ((>=)x) === (\y -> (>=) x y) === (\y -> x >= y)
+ - Gather all of the elements greater than the pivot (the second filter).
+   We know that these must come after our pivot element in the sorted list.
+ - Run `qsort` on the lesser elements, producing a sorted list that contains
+   only elements less than the pivot. Put these before the pivot.
+ - Run `qsort` on the greater elements, producing a sorted list. Put these
+   after the pivot.
+
+Note that choosing a bad pivot can have bad effects. Take a sorted list with
+N elements. The pivot will always be the lowest member, meaning that it does
+not divide the list very evenly. The list of lessers has 0 elements
+and the list of greaters has N-1 elemens. This means qsort will be called
+N times, each call looking through the entire list. This means, in the worst
+case, QuickSort will make N^2 comparisons.
+
+----------------------}

samples/Elm/Tree.elm

@@ -0,0 +1,91 @@
+
+{-----------------------------------------------------------------
+
+Overview: A "Tree" represents a binary tree. A "Node" in a binary
+tree always has two children. A tree can also be "Empty". Below
+I have defined "Tree" and a number of useful functions.
+
+This example also includes some challenge problems :)
+
+-----------------------------------------------------------------}
+
+
+data Tree a = Node a (Tree a) (Tree a) | Empty
+
+empty = Empty
+singleton v = Node v Empty Empty
+
+insert x tree =
+  case tree of
+    Empty -> singleton x
+    Node y left right ->
+      if x == y then tree else
+      if x <  y then Node y (insert x left) right
+                else Node y left (insert x right)
+
+fromList xs = foldl insert empty xs
+
+depth tree =
+  case tree of
+    Node v left right -> 1 + max (depth left) (depth right)
+    Empty -> 0
+
+map f tree =
+  case tree of
+    Node v left right -> Node (f v) (map f left) (map f right)
+    Empty -> Empty
+
+t1 = fromList [1,2,3]
+t2 = fromList [2,1,3]
+
+main = flow down [ display "depth" depth t1
+                 , display "depth" depth t2
+                 , display "map ((+)1)" (map ((+)1)) t2
+                 ]
+
+display name f v =
+  text . monospace . toText $
+  concat [ show (f v), " &lArr; ", name, " ", show v ]
+
+{-----------------------------------------------------------------
+
+Exercises:
+
+(1) Sum all of the elements of a tree.
+
+       sum :: Tree Number -> Number
+
+(2) Flatten a tree into a list.
+
+       flatten :: Tree a -> [a]
+
+(3) Check to see if an element is in a given tree.
+
+       isElement :: a -> Tree a -> Bool 
+
+(4) Write a general fold function that acts on trees. The fold
+    function does not need to guarantee a particular order of
+    traversal.
+
+       fold :: (a -> b -> b) -> b -> Tree a -> b
+
+(5) Use "fold" to do exercises 1-3 in one line each. The best
+    readable versions I have come up have the following length
+    in characters including spaces and function name:
+      sum: 16
+      flatten: 21
+      isElement: 46
+    See if you can match or beat me! Don't forget about currying
+    and partial application!
+
+(6) Can "fold" be used to implement "map" or "depth"?
+
+(7) Try experimenting with different ways to traverse a
+    tree: pre-order, in-order, post-order, depth-first, etc.
+    More info at: http://en.wikipedia.org/wiki/Tree_traversal
+
+-----------------------------------------------------------------}
+
+
+
+

samples/Handlebars/basic.handlebars

@@ -0,0 +1,6 @@
+<div class="entry">
+  <h1>{{title}}</h1>
+  <div class="body">
+    {{body}}
+  </div>
+</div>

samples/Handlebars/each.hbs

@@ -0,0 +1,11 @@
+<div class="post">
+  <h1>By {{fullName author}}</h1>
+  <div class="body">{{body}}</div>
+
+  <h1>Comments</h1>
+
+  {{#each comments}}
+  <h2>By {{fullName author}}</h2>
+  <div class="body">{{body}}</div>
+  {{/each}}
+</div>

samples/Nginx/filenames/nginx.conf

@@ -0,0 +1,70 @@
+user       www www;
+worker_processes  5;
+error_log  logs/error.log;
+pid        logs/nginx.pid;
+worker_rlimit_nofile 8192;
+
+events {
+  worker_connections  4096;
+}
+
+http {
+  include    conf/mime.types;
+  include    /etc/nginx/proxy.conf;
+  include    /etc/nginx/fastcgi.conf;
+  index    index.html index.htm index.php;
+
+  default_type application/octet-stream;
+  log_format   main '$remote_addr - $remote_user [$time_local]  $status '
+    '"$request" $body_bytes_sent "$http_referer" '
+    '"$http_user_agent" "$http_x_forwarded_for"';
+  access_log   logs/access.log  main;
+  sendfile     on;
+  tcp_nopush   on;
+  server_names_hash_bucket_size 128; # this seems to be required for some vhosts
+
+  server { # php/fastcgi
+    listen       80;
+    server_name  domain1.com www.domain1.com;
+    access_log   logs/domain1.access.log  main;
+    root         html;
+
+    location ~ \.php$ {
+      fastcgi_pass   127.0.0.1:1025;
+    }
+  }
+
+  server { # simple reverse-proxy
+    listen       80;
+    server_name  domain2.com www.domain2.com;
+    access_log   logs/domain2.access.log  main;
+
+    # serve static files
+    location ~ ^/(images|javascript|js|css|flash|media|static)/  {
+      root    /var/www/virtual/big.server.com/htdocs;
+      expires 30d;
+    }
+
+    # pass requests for dynamic content to rails/turbogears/zope, et al
+    location / {
+      proxy_pass      http://127.0.0.1:8080;
+    }
+  }
+
+  upstream big_server_com {
+    server 127.0.0.3:8000 weight=5;
+    server 127.0.0.3:8001 weight=5;
+    server 192.168.0.1:8000;
+    server 192.168.0.1:8001;
+  }
+
+  server { # simple load balancing
+    listen          80;
+    server_name     big.server.com;
+    access_log      logs/big.server.access.log main;
+
+    location / {
+      proxy_pass      http://big_server_com;
+    }
+  }
+}

samples/PHP/php-script.script!

@@ -0,0 +1,4 @@
+#!/usr/bin/php
+<?php
+
+echo "PHP\n";

samples/PHP/php.script!

@@ -0,0 +1,4 @@
+#!/usr/bin/env php
+<?php
+
+echo "PHP\n";

samples/Shell/filenames/.bash_logout

@@ -0,0 +1 @@
+/usr/bin/clear

samples/Shell/filenames/.bash_profile

@@ -1 +1,36 @@
-export PATH="/usr/local/bin:/usr/bin:/bin"
+##
+# Environment...
+##
+# Set up some variables for 'screen'
+if [ -z "${SCREENDIR}" ];then echo -n
+        export SCREENDIR="${HOME}/.screen"
+                # Save my screen sockets within my $HOME dir
+fi
+## PATH
+export PATH=/usr/local/bin:/usr/local/sbin:/usr/xpg4/bin:/usr/sbin:/usr/bin:/usr/sfw/bin:/usr/ccs/bin:/usr/openwin/bin:/opt/mysql/current/bin
+export MANPATH=/usr/local/man:/usr/share/man
+
+## Random ENV...
+# Set $TERM to 'vt100' (a safe default) if, for some
+# reason, it is set to 'network' (which is not valid!)
+if [ ${TERM} == 'network' ];then echo -n
+        export TERM='vt100'
+                # not 'nsterm' because if its 'network' we're
+                # probly not in Terminal.app
+fi
+# Set $COLORTERM, all this does is trick *some* apps into
+# using color in the terminal, which should happen anyway.
+if [ -z "${COLORTERM}" ];then echo -n
+        export COLORTERM="${TERM}"
+fi
+# another color option, this one for BSD's ls
+if [ -z "${CLICOLOR}" ];then echo -n
+        export CLICOLOR='1' # can be set to anything, actually
+fi
+# If $DISPLAY is not already set, set it!
+if [ -z "${DISPLAY}" ];then echo -n
+        export DISPLAY=':0'
+fi
+##
+# Source the bash rc file
+[ -r "${HOME}/.bashrc" ] && . "${HOME}/.bashrc"

samples/Shell/filenames/.bashrc

@@ -1 +1,119 @@
-export PATH="/usr/local/bin:/usr/bin:/bin"
+##
+# Functions... *MUCH* better than aliases, and they do more too!
+# but they clutter the environment... (try typing just 'set' at the prompt)
+##
+# The reason that some of these are... odd... is because
+# I had to convert them early because bash can't do positional
+# arguments in aliases! functionName () { do something $@<-arguments ; }
+ function ls    { command ls -Fh "$@"; }
+        # 'command ls' to prevent loop; -A for .file, -F for dir/ link@,
+        # -h for 5k 3m 1g, -o for printing flags (uchg)...
+ function l     { ls -l "$@"; } # -l to list in long format...
+ function ll    { l "$@" | less -XF ; } # pipe into 'more'
+
+##
+# Tips and Ticks... from http://www.caliban.org/bash/index.shtml
+##
+# The $CDPATH variable is so that you can be in /path/to/something and 'cd'
+# to 'somethingElse' and end up in /not/the/same/path/to/somethingElse.
+# iWould use it if it didn't ALWAYS echo the directory it changes to!
+#CDPATH='.:~'
+#
+# HISTIGNORE="&:l:ls:ls *:l *:cd:cd *:[bf]g:exit:quit:q:sleep *"
+        # History ignores commands that include any l/ls/cd etc
+        # This kicks-ass! It drops repeats and other useless
+        # things from the command history!
+ HISTIGNORE="[bf]g:exit:quit:q:sleep *"
+        # I want to see l/ls/cd in my history
+ HISTCONTROL=ignoreboth
+        # ignores both commands that start with a space or a tab, and duplicates
+        # other options are as follows:
+        # `ignorespace' means to not enter lines which begin with a space or tab into the history list.
+        # `ignoredups' means to not enter lines which match the last entered line.
+        # `ignoreboth' combines the two options.
+
+ shopt -s cdspell extglob progcomp
+        # Spell check for 'cd', extended globbing, programmable completion
+
+##
+# Bash Completion... Cannibalised from bash_completion 20030929
+# Completion defaults... Yes, its long...
+# Basically this sets up many useful defaults for command completion, these
+#  should probly be built into bash. Use bash_completions itself if you want
+#  more functionality and don't mind the hacks it uses.
+ complete -f -X '!*.?(t)bz2' bunzip2 bzcat bzcmp bzdiff bzegrep bzfgrep bzgrep
+ complete -f -X '!*.@(zip|ZIP|jar|JAR|exe|EXE|pk3|war|wsz|ear|zargo|xpi)' unzip zipinfo
+ complete -f -X '*.Z' compress znew
+ complete -f -X '!*.@(Z|gz|tgz|Gz|dz)' gunzip zcmp zdiff zcat zegrep zfgrep zgrep zless zmore
+ complete -f -X '!*.Z' uncompress
+ complete -f -X '!*.@(gif|jp?(e)g|tif?(f)|pn[gm]|p[bgp]m|bmp|xpm|ico|xwd|tga|GIF|JP?(E)G|TIF?(F)|PN[GM]|P[BGP]M|BMP|XPM|ICO|XWD|TGA)' ee  display
+ complete -f -X '!*.@(gif|jp?(e)g|tif?(f)|png|p[bgp]m|bmp|x[bp]m|rle|rgb|pcx|fits|pm|GIF|JPG|JP?(E)G|TIF?(F)|PNG|P[BGP]M|BMP|X[BP]M|RLE|RGB|PCX|FITS|PM)' xv qiv
+ complete -f -X '!*.@(@(?(e)ps|?(E)PS|pdf|PDF)?(.gz|.GZ|.Z))' gv ggv
+ complete -f -X '!*.@(dvi|DVI)?(.@(gz|Z|bz2))' xdvi
+ complete -f -X '!*.@(dvi|DVI)' dvips dviselect dvitype
+ complete -f -X '!*.@(pdf|PDF)' acroread xpdf
+ complete -f -X '!*.texi*' makeinfo texi2html
+ complete -f -X '!*.@(?(la)tex|?(LA)TEX|texi|TEXI|dtx|DTX|ins|INS)' tex latex slitex jadetex pdfjadetex pdftex pdflatex texi2dvi
+ complete -f -X '!*.@(mp3|MP3|m3u)' mpg123 mpg321
+ complete -f -X '!*.@(mp?(e)g|MP?(E)G|wma|avi|AVI|asf|vob|bin|dat|vcd|ps|pes|fli|viv|rm|ram|yuv|mov|MOV|qt|QT|wmv|mp3|MP3|ogg|OGG|ogm|OGM|mp4|MP4|wav|WAV)' xine
+ complete -f -X '!*.@(avi|asf|wmv)' aviplay
+ complete -f -X '!*.@(rm|ram|smi?(l))' realplay
+ complete -f -X '!*.@(mp?(e)g|avi|mov|qt)' xanim
+ complete -f -X '!*.@(ogg|OGG|m3u)' ogg123
+ complete -f -X '!*.@(mp3|MP3|ogg|OGG|pls|m3u)' gqmpeg freeamp
+ complete -f -X '!*.@(mp[23]|MP[23]|ogg|OGG|wav|WAV|pls|m3u|xm|mod|s[3t]m|it|mtm|ult|flac)' xmms
+ complete -f -X '!*.fig' xfig
+ complete -f -X '!*.@(mid?(i))' timidity playmidi
+ complete -f -X '.*|*.@(o|so|so.!(conf)|a|tar?(.@(gz|bz2))|tgz|tbz2|rpm|zip|ZIP|gif|GIF|jp?(e)g|JP?(E)G|mp3|MP3|mp?(e)g|MPG|avi|AVI|asf|ASF|ogg|OGG|class|CLASS)' vi vim gvim rvim view rview rgvim rgview gview emacs
+ complete -f -X '!*.@(exe|EXE|com|COM|scr|SCR)' wine
+ complete -f -X '!*.@(zip|ZIP|z|Z|gz|GZ|tgz|TGZ)' bzme
+ complete -f -X '!*.@(?([xX]|[sS])[hH][tT][mM]?([lL]))' netscape mozilla lynx opera w3m galeon curl dillo elinks links
+#
+ complete -u su passwd groups # user commands see only users
+ complete -A stopped -P '%' bg # bg completes with stopped jobs
+ complete -j -P '%' fg jobs disown # other job commands
+ complete -v readonly unset export # readonly and unset complete with shell variables
+ complete -A setopt set # set completes with set options
+ complete -A shopt shopt # shopt completes with shopt options
+ complete -A helptopic help # helptopics
+ complete -a unalias # unalias completes with aliases
+ complete -A binding bind # bind completes with readline bindings (make this more intelligent)
+ complete -c command type which man #sudo # type, which, man complete on commands
+ complete -d pushd cd rmdir # Make directory commands see only directories
+ complete -W ' ' alias # no filenames for alias,
+
+##
+# Set the prompt
+##
+ PS1="[\h:\w] \[\033[1;34m\]\u\[\033[0m\]\\$ "
+        # My prompt line:       "[gaelicWizard:~/Documents] user$ " user is in blue
+        # Or:                   "[gaelicWizard:~/Documents] root# " root is in blue
+##
+# Aliases:
+##
+# Aliases frequently used...
+ alias ..='cd ..;l'
+ alias cd..='cd ..'
+ alias which='type' # 'which' in (t)csh is same(?) as 'type' in bash...
+ alias quit='exit'
+ alias q='quit' # and 'q' is even shorter! :-D
+ alias v='vim'
+ alias rehash='. ~/.bashrc;' # source ~/.bashrc after I edit it
+ alias pg='ps -afe|grep -v grep|grep'
+ alias make='gmake'
+ alias patch='gpatch'
+ alias sed='gsed'
+ alias awk='nawk'
+ alias diff='gdiff'
+ alias grep='ggrep'
+ alias find='gfind'
+ alias ps='/usr/ucb/ps'
+ alias whoami='/usr/ucb/whoami'
+ alias ping='ping -s'
+ alias man='GROFF_NO_SGR= TCAT="less -s" TROFF="groff -Tascii" man -t'
+
+
+# The rest are uncategorised and fairly random... :-)
+shopt -s histappend
+PROMPT_COMMAND='echo -ne "\033]0;${USER} on ${HOSTNAME} at ${PWD}\007" && history -a'
+export PATH=/usr/local/bin:/usr/local/sbin:/usr/xpg4/bin:/usr/sbin:/usr/bin:/usr/sfw/bin:/usr/ccs/bin:/usr/openwin/bin:/opt/mysql/current/bin

samples/Shell/filenames/.cshrc

@@ -0,0 +1,5 @@
+umask 022
+set path=(/opt/local/bin /opt/local/sbin /bin /usr/bin)
+if ( $?prompt ) then
+        set history=32
+endif

samples/Shell/filenames/.login

@@ -0,0 +1,2 @@
+stty -istrip
+# setenv TERM `tset -Q -`

samples/Shell/filenames/.zlogout

@@ -0,0 +1,3 @@
+# Store dirs stack
+# See ~/.dotfiles/oh-my-zsh/plugins/dirspersist.plugin.zsh
+dirpersiststore

samples/Shell/filenames/.zprofile

@@ -0,0 +1,28 @@
+##############################################################################
+#Import the shell-agnostic (Bash or Zsh) environment config
+##############################################################################
+source ~/.profile
+
+##############################################################################
+# History Configuration
+##############################################################################
+HISTSIZE=5000               #How many lines of history to keep in memory
+HISTFILE=~/.zsh_history     #Where to save history to disk
+SAVEHIST=5000               #Number of history entries to save to disk
+HISTDUP=erase               #Erase duplicates in the history file
+setopt    appendhistory     #Append history to the history file (no overwriting)
+setopt    sharehistory      #Share history across terminals
+setopt    incappendhistory  #Immediately append to the history file, not just when a term is killed
+
+##############################################################################
+# sjl/z-zsh setup
+##############################################################################
+#. ~/.dotfiles/z-zsh/z.sh
+#function precmd () {
+#  z --add "$(pwd -P)"
+#}
+
+##############################################################################
+# rupa/z setup
+##############################################################################
+. ~/.dotfiles/z-rupa/z.sh

samples/Shell/filenames/.zshenv

@@ -0,0 +1,2 @@
+fpath=($fpath $HOME/.zsh/func)
+typeset -U fpath

samples/Shell/filenames/bash_logout

@@ -0,0 +1 @@
+/usr/bin/clear

samples/Shell/filenames/bash_profile

@@ -0,0 +1,36 @@
+##
+# Environment...
+##
+# Set up some variables for 'screen'
+if [ -z "${SCREENDIR}" ];then echo -n
+        export SCREENDIR="${HOME}/.screen"
+                # Save my screen sockets within my $HOME dir
+fi
+## PATH
+export PATH=/usr/local/bin:/usr/local/sbin:/usr/xpg4/bin:/usr/sbin:/usr/bin:/usr/sfw/bin:/usr/ccs/bin:/usr/openwin/bin:/opt/mysql/current/bin
+export MANPATH=/usr/local/man:/usr/share/man
+
+## Random ENV...
+# Set $TERM to 'vt100' (a safe default) if, for some
+# reason, it is set to 'network' (which is not valid!)
+if [ ${TERM} == 'network' ];then echo -n
+        export TERM='vt100'
+                # not 'nsterm' because if its 'network' we're
+                # probly not in Terminal.app
+fi
+# Set $COLORTERM, all this does is trick *some* apps into
+# using color in the terminal, which should happen anyway.
+if [ -z "${COLORTERM}" ];then echo -n
+        export COLORTERM="${TERM}"
+fi
+# another color option, this one for BSD's ls
+if [ -z "${CLICOLOR}" ];then echo -n
+        export CLICOLOR='1' # can be set to anything, actually
+fi
+# If $DISPLAY is not already set, set it!
+if [ -z "${DISPLAY}" ];then echo -n
+        export DISPLAY=':0'
+fi
+##
+# Source the bash rc file
+[ -r "${HOME}/.bashrc" ] && . "${HOME}/.bashrc"

samples/Shell/filenames/bashrc

@@ -0,0 +1,119 @@
+##
+# Functions... *MUCH* better than aliases, and they do more too!
+# but they clutter the environment... (try typing just 'set' at the prompt)
+##
+# The reason that some of these are... odd... is because
+# I had to convert them early because bash can't do positional
+# arguments in aliases! functionName () { do something $@<-arguments ; }
+ function ls    { command ls -Fh "$@"; }
+        # 'command ls' to prevent loop; -A for .file, -F for dir/ link@,
+        # -h for 5k 3m 1g, -o for printing flags (uchg)...
+ function l     { ls -l "$@"; } # -l to list in long format...
+ function ll    { l "$@" | less -XF ; } # pipe into 'more'
+
+##
+# Tips and Ticks... from http://www.caliban.org/bash/index.shtml
+##
+# The $CDPATH variable is so that you can be in /path/to/something and 'cd'
+# to 'somethingElse' and end up in /not/the/same/path/to/somethingElse.
+# iWould use it if it didn't ALWAYS echo the directory it changes to!
+#CDPATH='.:~'
+#
+# HISTIGNORE="&:l:ls:ls *:l *:cd:cd *:[bf]g:exit:quit:q:sleep *"
+        # History ignores commands that include any l/ls/cd etc
+        # This kicks-ass! It drops repeats and other useless
+        # things from the command history!
+ HISTIGNORE="[bf]g:exit:quit:q:sleep *"
+        # I want to see l/ls/cd in my history
+ HISTCONTROL=ignoreboth
+        # ignores both commands that start with a space or a tab, and duplicates
+        # other options are as follows:
+        # `ignorespace' means to not enter lines which begin with a space or tab into the history list.
+        # `ignoredups' means to not enter lines which match the last entered line.
+        # `ignoreboth' combines the two options.
+
+ shopt -s cdspell extglob progcomp
+        # Spell check for 'cd', extended globbing, programmable completion
+
+##
+# Bash Completion... Cannibalised from bash_completion 20030929
+# Completion defaults... Yes, its long...
+# Basically this sets up many useful defaults for command completion, these
+#  should probly be built into bash. Use bash_completions itself if you want
+#  more functionality and don't mind the hacks it uses.
+ complete -f -X '!*.?(t)bz2' bunzip2 bzcat bzcmp bzdiff bzegrep bzfgrep bzgrep
+ complete -f -X '!*.@(zip|ZIP|jar|JAR|exe|EXE|pk3|war|wsz|ear|zargo|xpi)' unzip zipinfo
+ complete -f -X '*.Z' compress znew
+ complete -f -X '!*.@(Z|gz|tgz|Gz|dz)' gunzip zcmp zdiff zcat zegrep zfgrep zgrep zless zmore
+ complete -f -X '!*.Z' uncompress
+ complete -f -X '!*.@(gif|jp?(e)g|tif?(f)|pn[gm]|p[bgp]m|bmp|xpm|ico|xwd|tga|GIF|JP?(E)G|TIF?(F)|PN[GM]|P[BGP]M|BMP|XPM|ICO|XWD|TGA)' ee  display
+ complete -f -X '!*.@(gif|jp?(e)g|tif?(f)|png|p[bgp]m|bmp|x[bp]m|rle|rgb|pcx|fits|pm|GIF|JPG|JP?(E)G|TIF?(F)|PNG|P[BGP]M|BMP|X[BP]M|RLE|RGB|PCX|FITS|PM)' xv qiv
+ complete -f -X '!*.@(@(?(e)ps|?(E)PS|pdf|PDF)?(.gz|.GZ|.Z))' gv ggv
+ complete -f -X '!*.@(dvi|DVI)?(.@(gz|Z|bz2))' xdvi
+ complete -f -X '!*.@(dvi|DVI)' dvips dviselect dvitype
+ complete -f -X '!*.@(pdf|PDF)' acroread xpdf
+ complete -f -X '!*.texi*' makeinfo texi2html
+ complete -f -X '!*.@(?(la)tex|?(LA)TEX|texi|TEXI|dtx|DTX|ins|INS)' tex latex slitex jadetex pdfjadetex pdftex pdflatex texi2dvi
+ complete -f -X '!*.@(mp3|MP3|m3u)' mpg123 mpg321
+ complete -f -X '!*.@(mp?(e)g|MP?(E)G|wma|avi|AVI|asf|vob|bin|dat|vcd|ps|pes|fli|viv|rm|ram|yuv|mov|MOV|qt|QT|wmv|mp3|MP3|ogg|OGG|ogm|OGM|mp4|MP4|wav|WAV)' xine
+ complete -f -X '!*.@(avi|asf|wmv)' aviplay
+ complete -f -X '!*.@(rm|ram|smi?(l))' realplay
+ complete -f -X '!*.@(mp?(e)g|avi|mov|qt)' xanim
+ complete -f -X '!*.@(ogg|OGG|m3u)' ogg123
+ complete -f -X '!*.@(mp3|MP3|ogg|OGG|pls|m3u)' gqmpeg freeamp
+ complete -f -X '!*.@(mp[23]|MP[23]|ogg|OGG|wav|WAV|pls|m3u|xm|mod|s[3t]m|it|mtm|ult|flac)' xmms
+ complete -f -X '!*.fig' xfig
+ complete -f -X '!*.@(mid?(i))' timidity playmidi
+ complete -f -X '.*|*.@(o|so|so.!(conf)|a|tar?(.@(gz|bz2))|tgz|tbz2|rpm|zip|ZIP|gif|GIF|jp?(e)g|JP?(E)G|mp3|MP3|mp?(e)g|MPG|avi|AVI|asf|ASF|ogg|OGG|class|CLASS)' vi vim gvim rvim view rview rgvim rgview gview emacs
+ complete -f -X '!*.@(exe|EXE|com|COM|scr|SCR)' wine
+ complete -f -X '!*.@(zip|ZIP|z|Z|gz|GZ|tgz|TGZ)' bzme
+ complete -f -X '!*.@(?([xX]|[sS])[hH][tT][mM]?([lL]))' netscape mozilla lynx opera w3m galeon curl dillo elinks links
+#
+ complete -u su passwd groups # user commands see only users
+ complete -A stopped -P '%' bg # bg completes with stopped jobs
+ complete -j -P '%' fg jobs disown # other job commands
+ complete -v readonly unset export # readonly and unset complete with shell variables
+ complete -A setopt set # set completes with set options
+ complete -A shopt shopt # shopt completes with shopt options
+ complete -A helptopic help # helptopics
+ complete -a unalias # unalias completes with aliases
+ complete -A binding bind # bind completes with readline bindings (make this more intelligent)
+ complete -c command type which man #sudo # type, which, man complete on commands
+ complete -d pushd cd rmdir # Make directory commands see only directories
+ complete -W ' ' alias # no filenames for alias,
+
+##
+# Set the prompt
+##
+ PS1="[\h:\w] \[\033[1;34m\]\u\[\033[0m\]\\$ "
+        # My prompt line:       "[gaelicWizard:~/Documents] user$ " user is in blue
+        # Or:                   "[gaelicWizard:~/Documents] root# " root is in blue
+##
+# Aliases:
+##
+# Aliases frequently used...
+ alias ..='cd ..;l'
+ alias cd..='cd ..'
+ alias which='type' # 'which' in (t)csh is same(?) as 'type' in bash...
+ alias quit='exit'
+ alias q='quit' # and 'q' is even shorter! :-D
+ alias v='vim'
+ alias rehash='. ~/.bashrc;' # source ~/.bashrc after I edit it
+ alias pg='ps -afe|grep -v grep|grep'
+ alias make='gmake'
+ alias patch='gpatch'
+ alias sed='gsed'
+ alias awk='nawk'
+ alias diff='gdiff'
+ alias grep='ggrep'
+ alias find='gfind'
+ alias ps='/usr/ucb/ps'
+ alias whoami='/usr/ucb/whoami'
+ alias ping='ping -s'
+ alias man='GROFF_NO_SGR= TCAT="less -s" TROFF="groff -Tascii" man -t'
+
+
+# The rest are uncategorised and fairly random... :-)
+shopt -s histappend
+PROMPT_COMMAND='echo -ne "\033]0;${USER} on ${HOSTNAME} at ${PWD}\007" && history -a'
+export PATH=/usr/local/bin:/usr/local/sbin:/usr/xpg4/bin:/usr/sbin:/usr/bin:/usr/sfw/bin:/usr/ccs/bin:/usr/openwin/bin:/opt/mysql/current/bin

samples/Shell/filenames/cshrc

@@ -0,0 +1,5 @@
+umask 022
+set path=(/opt/local/bin /opt/local/sbin /bin /usr/bin)
+if ( $?prompt ) then
+        set history=32
+endif

samples/Shell/filenames/login

@@ -0,0 +1,2 @@
+stty -istrip
+# setenv TERM `tset -Q -`

samples/Shell/filenames/profile

@@ -0,0 +1 @@
+export PATH="/usr/local/bin:/usr/bin:/bin"

samples/Shell/filenames/zlogin

@@ -0,0 +1 @@
+export PATH="/usr/local/bin:/usr/bin:/bin"

samples/Shell/filenames/zlogout

@@ -0,0 +1,3 @@
+# Store dirs stack
+# See ~/.dotfiles/oh-my-zsh/plugins/dirspersist.plugin.zsh
+dirpersiststore

samples/Shell/filenames/zprofile

@@ -0,0 +1,28 @@
+##############################################################################
+#Import the shell-agnostic (Bash or Zsh) environment config
+##############################################################################
+source ~/.profile
+
+##############################################################################
+# History Configuration
+##############################################################################
+HISTSIZE=5000               #How many lines of history to keep in memory
+HISTFILE=~/.zsh_history     #Where to save history to disk
+SAVEHIST=5000               #Number of history entries to save to disk
+HISTDUP=erase               #Erase duplicates in the history file
+setopt    appendhistory     #Append history to the history file (no overwriting)
+setopt    sharehistory      #Share history across terminals
+setopt    incappendhistory  #Immediately append to the history file, not just when a term is killed
+
+##############################################################################
+# sjl/z-zsh setup
+##############################################################################
+#. ~/.dotfiles/z-zsh/z.sh
+#function precmd () {
+#  z --add "$(pwd -P)"
+#}
+
+##############################################################################
+# rupa/z setup
+##############################################################################
+. ~/.dotfiles/z-rupa/z.sh

samples/Shell/filenames/zshenv

@@ -0,0 +1,2 @@
+fpath=($fpath $HOME/.zsh/func)
+typeset -U fpath

samples/Shell/filenames/zshrc

@@ -0,0 +1 @@
+export PATH="/usr/local/bin:/usr/bin:/bin"

samples/Shell/invalid-shebang.sh

@@ -0,0 +1,3 @@
+#!/usr/bin/env 
+
+echo "wat"

samples/Shell/sbt.script!

@@ -0,0 +1,432 @@
+#!/usr/bin/env bash
+#
+# A more capable sbt runner, coincidentally also called sbt.
+# Author: Paul Phillips <paulp@typesafe.com>
+
+# todo - make this dynamic
+declare -r sbt_release_version=0.11.3
+declare -r sbt_snapshot_version=0.13.0-SNAPSHOT
+
+unset sbt_jar sbt_dir sbt_create sbt_snapshot sbt_launch_dir
+unset scala_version java_home sbt_explicit_version
+unset verbose debug quiet
+
+build_props_sbt () {
+  if [[ -f project/build.properties ]]; then
+    versionLine=$(grep ^sbt.version project/build.properties)
+    versionString=${versionLine##sbt.version=}
+    echo "$versionString"
+  fi
+}
+
+update_build_props_sbt () {
+  local ver="$1"
+  local old=$(build_props_sbt)
+
+  if [[ $ver == $old ]]; then
+    return
+  elif [[ -f project/build.properties ]]; then
+    perl -pi -e "s/^sbt\.version=.*\$/sbt.version=${ver}/" project/build.properties
+    grep -q '^sbt.version=' project/build.properties || echo "sbt.version=${ver}" >> project/build.properties
+
+    echo !!!
+    echo !!! Updated file project/build.properties setting sbt.version to: $ver
+    echo !!! Previous value was: $old
+    echo !!!
+  fi
+}
+
+sbt_version () {
+  if [[ -n $sbt_explicit_version ]]; then
+    echo $sbt_explicit_version
+  else
+    local v=$(build_props_sbt)
+    if [[ -n $v ]]; then
+      echo $v
+    else
+      echo $sbt_release_version
+    fi
+  fi
+}
+
+echoerr () {
+  echo 1>&2 "$@"
+}
+vlog () {
+  [[ $verbose || $debug ]] && echoerr "$@"
+}
+dlog () {
+  [[ $debug ]] && echoerr "$@"
+}
+
+# this seems to cover the bases on OSX, and someone will
+# have to tell me about the others.
+get_script_path () {
+  local path="$1"
+  [[ -L "$path" ]] || { echo "$path" ; return; }
+
+  local target=$(readlink "$path")
+  if [[ "${target:0:1}" == "/" ]]; then
+    echo "$target"
+  else
+    echo "$(dirname $path)/$target"
+  fi
+}
+
+# a ham-fisted attempt to move some memory settings in concert
+# so they need not be dicked around with individually.
+get_mem_opts () {
+  local mem=${1:-1536}
+  local perm=$(( $mem / 4 ))
+  (( $perm > 256 )) || perm=256
+  (( $perm < 1024 )) || perm=1024
+  local codecache=$(( $perm / 2 ))
+  
+  echo "-Xms${mem}m -Xmx${mem}m -XX:MaxPermSize=${perm}m -XX:ReservedCodeCacheSize=${codecache}m"
+}
+
+die() {
+  echo "Aborting: $@"
+  exit 1
+}
+
+make_url () {
+  groupid="$1"
+  category="$2"
+  version="$3"
+  
+  echo "http://typesafe.artifactoryonline.com/typesafe/ivy-$category/$groupid/sbt-launch/$version/sbt-launch.jar"
+}
+
+declare -r default_jvm_opts="-Dfile.encoding=UTF8"
+declare -r default_sbt_opts="-XX:+CMSClassUnloadingEnabled"
+declare -r default_sbt_mem=1536
+declare -r noshare_opts="-Dsbt.global.base=project/.sbtboot -Dsbt.boot.directory=project/.boot -Dsbt.ivy.home=project/.ivy"
+declare -r sbt_opts_file=".sbtopts"
+declare -r jvm_opts_file=".jvmopts"
+declare -r latest_28="2.8.2"
+declare -r latest_29="2.9.1"
+declare -r latest_210="2.10.0-SNAPSHOT"
+
+declare -r script_path=$(get_script_path "$BASH_SOURCE")
+declare -r script_dir="$(dirname $script_path)"
+declare -r script_name="$(basename $script_path)"
+
+# some non-read-onlies set with defaults
+declare java_cmd=java
+declare sbt_launch_dir="$script_dir/.lib"
+declare sbt_mem=$default_sbt_mem
+
+# pull -J and -D options to give to java.
+declare -a residual_args
+declare -a java_args
+declare -a scalac_args
+declare -a sbt_commands
+
+build_props_scala () {
+  if [[ -f project/build.properties ]]; then
+    versionLine=$(grep ^build.scala.versions project/build.properties)
+    versionString=${versionLine##build.scala.versions=}
+    echo ${versionString%% .*}
+  fi
+}
+
+execRunner () {
+  # print the arguments one to a line, quoting any containing spaces
+  [[ $verbose || $debug ]] && echo "# Executing command line:" && {
+    for arg; do
+      if printf "%s\n" "$arg" | grep -q ' '; then
+        printf "\"%s\"\n" "$arg"
+      else
+        printf "%s\n" "$arg"
+      fi
+    done
+    echo ""
+  }
+
+  exec "$@"
+}
+
+sbt_groupid () {
+  case $(sbt_version) in
+        0.7.*) echo org.scala-tools.sbt ;;
+       0.10.*) echo org.scala-tools.sbt ;;
+    0.11.[12]) echo org.scala-tools.sbt ;;
+            *) echo org.scala-sbt ;;
+  esac
+}
+
+sbt_artifactory_list () {
+  local version0=$(sbt_version)
+  local version=${version0%-SNAPSHOT}
+  local url="http://typesafe.artifactoryonline.com/typesafe/ivy-snapshots/$(sbt_groupid)/sbt-launch/"
+  dlog "Looking for snapshot list at: $url "
+  
+  curl -s --list-only "$url" | \
+    grep -F $version | \
+    perl -e 'print reverse <>' | \
+    perl -pe 's#^<a href="([^"/]+).*#$1#;'
+}
+
+make_release_url () {
+  make_url $(sbt_groupid) releases $(sbt_version)
+}
+
+# argument is e.g. 0.13.0-SNAPSHOT
+# finds the actual version (with the build id) at artifactory
+make_snapshot_url () {
+  for ver in $(sbt_artifactory_list); do
+    local url=$(make_url $(sbt_groupid) snapshots $ver)
+    dlog "Testing $url"
+    curl -s --head "$url" >/dev/null
+    dlog "curl returned: $?"
+    echo "$url"
+    return
+  done
+}
+
+jar_url () {
+  case $(sbt_version) in
+             0.7.*) echo "http://simple-build-tool.googlecode.com/files/sbt-launch-0.7.7.jar" ;;
+        *-SNAPSHOT) make_snapshot_url ;;
+                 *) make_release_url ;;
+  esac
+}
+
+jar_file () {
+  echo "$sbt_launch_dir/$1/sbt-launch.jar"
+}
+
+download_url () {
+  local url="$1"
+  local jar="$2"
+  
+  echo "Downloading sbt launcher $(sbt_version):"
+  echo "  From  $url"
+  echo "    To  $jar"
+
+  mkdir -p $(dirname "$jar") && {
+    if which curl >/dev/null; then
+      curl --fail --silent "$url" --output "$jar"
+    elif which wget >/dev/null; then
+      wget --quiet -O "$jar" "$url"
+    fi
+  } && [[ -f "$jar" ]]
+}
+
+acquire_sbt_jar () {
+  sbt_url="$(jar_url)"
+  sbt_jar="$(jar_file $(sbt_version))"
+
+  [[ -f "$sbt_jar" ]] || download_url "$sbt_url" "$sbt_jar"
+}
+
+usage () {
+  cat <<EOM
+Usage: $script_name [options]
+
+  -h | -help         print this message
+  -v | -verbose      this runner is chattier
+  -d | -debug        set sbt log level to Debug
+  -q | -quiet        set sbt log level to Error
+  -no-colors         disable ANSI color codes
+  -sbt-create        start sbt even if current directory contains no sbt project
+  -sbt-dir   <path>  path to global settings/plugins directory (default: ~/.sbt/<version>)
+  -sbt-boot  <path>  path to shared boot directory (default: ~/.sbt/boot in 0.11 series)
+  -ivy       <path>  path to local Ivy repository (default: ~/.ivy2)
+  -mem    <integer>  set memory options (default: $sbt_mem, which is
+                       $(get_mem_opts $sbt_mem) )
+  -no-share          use all local caches; no sharing
+  -offline           put sbt in offline mode
+  -jvm-debug <port>  Turn on JVM debugging, open at the given port.
+  -batch             Disable interactive mode
+
+  # sbt version (default: from project/build.properties if present, else latest release)
+  !!! The only way to accomplish this pre-0.12.0 if there is a build.properties file which
+  !!! contains an sbt.version property is to update the file on disk.  That's what this does.
+  -sbt-version  <version>   use the specified version of sbt 
+  -sbt-jar      <path>      use the specified jar as the sbt launcher
+  -sbt-snapshot             use a snapshot version of sbt
+  -sbt-launch-dir <path>    directory to hold sbt launchers (default: $sbt_launch_dir)
+
+  # scala version (default: as chosen by sbt)
+  -28                       use $latest_28
+  -29                       use $latest_29
+  -210                      use $latest_210
+  -scala-home <path>        use the scala build at the specified directory
+  -scala-version <version>  use the specified version of scala
+
+  # java version (default: java from PATH, currently $(java -version |& grep version))
+  -java-home <path>         alternate JAVA_HOME
+
+  # jvm options and output control
+  JAVA_OPTS     environment variable holding jvm args, if unset uses "$default_jvm_opts"
+  SBT_OPTS      environment variable holding jvm args, if unset uses "$default_sbt_opts"
+  .jvmopts      if file is in sbt root, it is prepended to the args given to the jvm
+  .sbtopts      if file is in sbt root, it is prepended to the args given to **sbt**
+  -Dkey=val     pass -Dkey=val directly to the jvm
+  -J-X          pass option -X directly to the jvm (-J is stripped)
+  -S-X          add -X to sbt's scalacOptions (-S is stripped)
+
+In the case of duplicated or conflicting options, the order above
+shows precedence: JAVA_OPTS lowest, command line options highest.
+EOM
+}
+
+addJava () {
+  dlog "[addJava] arg = '$1'"
+  java_args=( "${java_args[@]}" "$1" )
+}
+addSbt () {
+  dlog "[addSbt] arg = '$1'"
+  sbt_commands=( "${sbt_commands[@]}" "$1" )
+}
+addScalac () {
+  dlog "[addScalac] arg = '$1'"
+  scalac_args=( "${scalac_args[@]}" "$1" )
+}
+addResidual () {
+  dlog "[residual] arg = '$1'"
+  residual_args=( "${residual_args[@]}" "$1" )
+}
+addResolver () {
+  addSbt "set resolvers in ThisBuild += $1"
+}
+addDebugger () {
+  addJava "-Xdebug -Xrunjdwp:transport=dt_socket,server=y,suspend=n,address=$1"
+}
+get_jvm_opts () {
+  # echo "${JAVA_OPTS:-$default_jvm_opts}"
+  # echo "${SBT_OPTS:-$default_sbt_opts}"
+
+  [[ -f "$jvm_opts_file" ]] && cat "$jvm_opts_file"
+}
+
+process_args ()
+{
+  require_arg () {
+    local type="$1"
+    local opt="$2"
+    local arg="$3"
+    
+    if [[ -z "$arg" ]] || [[ "${arg:0:1}" == "-" ]]; then
+      die "$opt requires <$type> argument"
+    fi
+  }
+  while [[ $# -gt 0 ]]; do
+    case "$1" in
+       -h|-help) usage; exit 1 ;;
+    -v|-verbose) verbose=1 && shift ;;
+      -d|-debug) debug=1 && shift ;;
+      -q|-quiet) quiet=1 && shift ;;
+
+           -ivy) require_arg path "$1" "$2" && addJava "-Dsbt.ivy.home=$2" && shift 2 ;;
+           -mem) require_arg integer "$1" "$2" && sbt_mem="$2" && shift 2 ;;
+     -no-colors) addJava "-Dsbt.log.noformat=true" && shift ;;
+      -no-share) addJava "$noshare_opts" && shift ;;
+      -sbt-boot) require_arg path "$1" "$2" && addJava "-Dsbt.boot.directory=$2" && shift 2 ;;
+       -sbt-dir) require_arg path "$1" "$2" && sbt_dir="$2" && shift 2 ;;
+     -debug-inc) addJava "-Dxsbt.inc.debug=true" && shift ;;
+       -offline) addSbt "set offline := true" && shift ;;
+     -jvm-debug) require_arg port "$1" "$2" && addDebugger $2 && shift 2 ;;
+         -batch) exec </dev/null && shift ;;
+
+    -sbt-create) sbt_create=true && shift ;;
+  -sbt-snapshot) sbt_explicit_version=$sbt_snapshot_version && shift ;;
+       -sbt-jar) require_arg path "$1" "$2" && sbt_jar="$2" && shift 2 ;;
+   -sbt-version) require_arg version "$1" "$2" && sbt_explicit_version="$2" && shift 2 ;;
+-sbt-launch-dir) require_arg path "$1" "$2" && sbt_launch_dir="$2" && shift 2 ;;
+ -scala-version) require_arg version "$1" "$2" && addSbt "set scalaVersion := \"$2\"" && shift 2 ;;
+    -scala-home) require_arg path "$1" "$2" && addSbt "set scalaHome in ThisBuild := Some(file(\"$2\"))" && shift 2 ;;
+     -java-home) require_arg path "$1" "$2" && java_cmd="$2/bin/java" && shift 2 ;;
+
+            -D*) addJava "$1" && shift ;;
+            -J*) addJava "${1:2}" && shift ;;
+            -S*) addScalac "${1:2}" && shift ;;
+            -28) addSbt "++ $latest_28" && shift ;;
+            -29) addSbt "++ $latest_29" && shift ;;
+           -210) addSbt "++ $latest_210" && shift ;;
+
+              *) addResidual "$1" && shift ;;
+    esac
+  done
+  
+  [[ $debug ]] && {
+    case $(sbt_version) in
+     0.7.*) addSbt "debug" ;; 
+         *) addSbt "set logLevel in Global := Level.Debug" ;;
+    esac
+  }
+  [[ $quiet ]] && {
+    case $(sbt_version) in
+     0.7.*) ;; 
+         *) addSbt "set logLevel in Global := Level.Error" ;;
+    esac
+  }
+}
+
+# if .sbtopts exists, prepend its contents to $@ so it can be processed by this runner
+[[ -f "$sbt_opts_file" ]] && {
+  sbtargs=()
+  while IFS= read -r arg; do
+    sbtargs=( "${sbtargs[@]}" "$arg" )
+  done <"$sbt_opts_file"
+
+  set -- "${sbtargs[@]}" "$@"
+}
+
+# process the combined args, then reset "$@" to the residuals
+process_args "$@"
+set -- "${residual_args[@]}"
+argumentCount=$#
+
+# set scalacOptions if we were given any -S opts
+[[ ${#scalac_args[@]} -eq 0 ]] || addSbt "set scalacOptions in ThisBuild += \"${scalac_args[@]}\""
+
+# Update build.properties no disk to set explicit version - sbt gives us no choice
+[[ -n "$sbt_explicit_version" ]] && update_build_props_sbt "$sbt_explicit_version"
+echo "Detected sbt version $(sbt_version)"
+
+[[ -n "$scala_version" ]] && echo "Overriding scala version to $scala_version"
+
+# no args - alert them there's stuff in here
+(( $argumentCount > 0 )) || echo "Starting $script_name: invoke with -help for other options"
+
+# verify this is an sbt dir or -create was given
+[[ -f ./build.sbt || -d ./project || -n "$sbt_create" ]] || {
+  cat <<EOM
+$(pwd) doesn't appear to be an sbt project.
+If you want to start sbt anyway, run:
+  $0 -sbt-create
+
+EOM
+  exit 1
+}
+
+# pick up completion if present; todo
+[[ -f .sbt_completion.sh ]] && source .sbt_completion.sh
+
+# no jar? download it.
+[[ -f "$sbt_jar" ]] || acquire_sbt_jar || {
+  # still no jar? uh-oh.
+  echo "Download failed. Obtain the jar manually and place it at $sbt_jar"
+  exit 1
+}
+
+[[ -n "$sbt_dir" ]] || {
+  sbt_dir=~/.sbt/$(sbt_version)
+  addJava "-Dsbt.global.base=$sbt_dir"
+  echo "Using $sbt_dir as sbt dir, -sbt-dir to override."
+}
+
+# since sbt 0.7 doesn't understand iflast
+(( ${#residual_args[@]} == 0 )) && residual_args=( "shell" )
+
+# run sbt
+execRunner "$java_cmd" \
+  $(get_mem_opts $sbt_mem) \
+  $(get_jvm_opts) \
+  ${java_args[@]} \
+  -jar "$sbt_jar" \
+  "${sbt_commands[@]}" \
+  "${residual_args[@]}"

samples/Text/mac.txt

@@ -0,0 +1 @@
+line 1

test/test_blob.rb

@@ -2,6 +2,7 @@ require 'linguist/file_blob'
 require 'linguist/samples'
 
 require 'test/unit'
+require 'mocha'
 require 'mime/types'
 require 'pygments'
 
@@ -64,6 +65,14 @@ class TestBlob < Test::Unit::TestCase
     assert_equal ["module Foo", "end", ""], blob("Ruby/foo.rb").lines
   end
 
+  def test_mac_format
+    assert blob("Text/mac.txt").mac_format?
+  end
+
+  def test_lines_mac_format
+    assert_equal ["line 1", "line 2", ""], blob("Text/mac.txt").lines
+  end
+
   def test_size
     assert_equal 15, blob("Ruby/foo.rb").size
   end
@@ -261,6 +270,12 @@ class TestBlob < Test::Unit::TestCase
     assert !blob("Text/dump.sql").indexable?
     assert !blob("Binary/github.po").indexable?
     assert !blob("Binary/linguist.gem").indexable?
+
+    # large binary blobs should fail on size check first, not call
+    # into charlock_holmes and alloc big buffers for testing encoding
+    b = blob("Binary/octocat.ai")
+    b.expects(:binary?).never
+    assert !b.indexable?
   end
 
   def test_language
@@ -276,11 +291,10 @@ class TestBlob < Test::Unit::TestCase
   end
 
   def test_colorize
-    assert_equal <<-HTML, blob("Ruby/foo.rb").colorize
+    assert_equal <<-HTML.chomp, blob("Ruby/foo.rb").colorize
 <div class="highlight"><pre><span class="k">module</span> <span class="nn">Foo</span>
 <span class="k">end</span>
-</pre>
-</div>
+</pre></div>
     HTML
   end
 

test/test_language.rb

@@ -26,6 +26,7 @@ class TestLanguage < Test::Unit::TestCase
     assert_equal Lexer['HTML'], Language['HTML'].lexer
     assert_equal Lexer['HTML+Django/Jinja'], Language['HTML+Django'].lexer
     assert_equal Lexer['HTML+PHP'], Language['HTML+PHP'].lexer
+    assert_equal Lexer['HTTP'], Language['HTTP'].lexer
     assert_equal Lexer['JSON'], Language['JSON'].lexer
     assert_equal Lexer['Java'], Language['ChucK'].lexer
     assert_equal Lexer['Java'], Language['Java'].lexer
@@ -51,7 +52,7 @@ class TestLanguage < Test::Unit::TestCase
     assert_equal Lexer['Verilog'], Language['Verilog'].lexer
     assert_equal Lexer['XSLT'], Language['XSLT'].lexer
     assert_equal Lexer['aspx-vb'], Language['ASP'].lexer
-    assert_equal Lexer['haXe'], Language['HaXe'].lexer
+    assert_equal Lexer['haXe'], Language['Haxe'].lexer
     assert_equal Lexer['reStructuredText'], Language['reStructuredText'].lexer
   end
 
@@ -60,6 +61,7 @@ class TestLanguage < Test::Unit::TestCase
     assert_equal Language['ASP'], Language.find_by_alias('aspx')
     assert_equal Language['ASP'], Language.find_by_alias('aspx-vb')
     assert_equal Language['ActionScript'], Language.find_by_alias('as3')
+    assert_equal Language['ApacheConf'], Language.find_by_alias('apache')
     assert_equal Language['Assembly'], Language.find_by_alias('nasm')
     assert_equal Language['Batchfile'], Language.find_by_alias('bat')
     assert_equal Language['C#'], Language.find_by_alias('c#')
@@ -68,6 +70,7 @@ class TestLanguage < Test::Unit::TestCase
     assert_equal Language['C++'], Language.find_by_alias('c++')
     assert_equal Language['C++'], Language.find_by_alias('cpp')
     assert_equal Language['CoffeeScript'], Language.find_by_alias('coffee')
+    assert_equal Language['CoffeeScript'], Language.find_by_alias('coffee-script')
     assert_equal Language['ColdFusion'], Language.find_by_alias('cfm')
     assert_equal Language['Common Lisp'], Language.find_by_alias('common-lisp')
     assert_equal Language['Common Lisp'], Language.find_by_alias('lisp')
@@ -78,7 +81,9 @@ class TestLanguage < Test::Unit::TestCase
     assert_equal Language['Emacs Lisp'], Language.find_by_alias('emacs-lisp')
     assert_equal Language['Gettext Catalog'], Language.find_by_alias('pot')
     assert_equal Language['HTML'], Language.find_by_alias('html')
+    assert_equal Language['HTML'], Language.find_by_alias('xhtml')
     assert_equal Language['HTML+ERB'], Language.find_by_alias('html+erb')
+    assert_equal Language['HTML+ERB'], Language.find_by_alias('erb')
     assert_equal Language['IRC log'], Language.find_by_alias('irc')
     assert_equal Language['JSON'], Language.find_by_alias('json')
     assert_equal Language['Java Server Pages'], Language.find_by_alias('jsp')
@@ -87,6 +92,7 @@ class TestLanguage < Test::Unit::TestCase
     assert_equal Language['JavaScript'], Language.find_by_alias('js')
     assert_equal Language['Literate Haskell'], Language.find_by_alias('lhs')
     assert_equal Language['Literate Haskell'], Language.find_by_alias('literate-haskell')
+    assert_equal Language['Objective-C'], Language.find_by_alias('objc')
     assert_equal Language['OpenEdge ABL'], Language.find_by_alias('openedge')
     assert_equal Language['OpenEdge ABL'], Language.find_by_alias('progress')
     assert_equal Language['OpenEdge ABL'], Language.find_by_alias('abl')
@@ -106,6 +112,7 @@ class TestLanguage < Test::Unit::TestCase
     assert_equal Language['VimL'], Language.find_by_alias('vim')
     assert_equal Language['VimL'], Language.find_by_alias('viml')
     assert_equal Language['reStructuredText'], Language.find_by_alias('rst')
+    assert_equal Language['YAML'], Language.find_by_alias('yml')
   end
 
   def test_groups
@@ -224,10 +231,16 @@ class TestLanguage < Test::Unit::TestCase
     assert_equal [Language['Ruby']], Language.find_by_filename('foo/bar.rb')
     assert_equal [Language['Ruby']], Language.find_by_filename('Rakefile')
     assert_equal [Language['Ruby']], Language.find_by_filename('PKGBUILD.rb')
+    assert_equal Language['ApacheConf'], Language.find_by_filename('httpd.conf').first
+    assert_equal [Language['ApacheConf']], Language.find_by_filename('.htaccess')
+    assert_equal Language['Nginx'], Language.find_by_filename('nginx.conf').first
     assert_equal ['C', 'C++', 'Objective-C'], Language.find_by_filename('foo.h').map(&:name).sort
     assert_equal [], Language.find_by_filename('rb')
     assert_equal [], Language.find_by_filename('.rb')
     assert_equal [], Language.find_by_filename('.nkt')
+    assert_equal [Language['Shell']], Language.find_by_filename('.bashrc')
+    assert_equal [Language['Shell']], Language.find_by_filename('bash_profile')
+    assert_equal [Language['Shell']], Language.find_by_filename('.zshrc')
   end
 
   def test_find
@@ -286,6 +299,11 @@ class TestLanguage < Test::Unit::TestCase
     assert !Language.ace_modes.include?(Language['FORTRAN'])
   end
 
+  def test_wrap
+    assert_equal false, Language['C'].wrap
+    assert_equal true, Language['Markdown'].wrap
+  end
+
   def test_extensions
     assert Language['Perl'].extensions.include?('.pl')
     assert Language['Python'].extensions.include?('.py')
@@ -314,12 +332,11 @@ class TestLanguage < Test::Unit::TestCase
 
 
   def test_colorize
-    assert_equal <<-HTML, Language['Ruby'].colorize("def foo\n  'foo'\nend\n")
+    assert_equal <<-HTML.chomp, Language['Ruby'].colorize("def foo\n  'foo'\nend\n")
 <div class="highlight"><pre><span class="k">def</span> <span class="nf">foo</span>
   <span class="s1">&#39;foo&#39;</span>
 <span class="k">end</span>
-</pre>
-</div>
+</pre></div>
     HTML
   end
 end

test/test_samples.rb

@@ -1,4 +1,6 @@
 require 'linguist/samples'
+require 'tempfile'
+require 'yajl'
 
 require 'test/unit'
 
@@ -12,6 +14,19 @@ class TestSamples < Test::Unit::TestCase
     # Just warn, it shouldn't scare people off by breaking the build.
     if serialized['md5'] != latest['md5']
       warn "Samples database is out of date. Run `bundle exec rake samples`."
+
+      expected = Tempfile.new('expected.json')
+      expected.write Yajl::Encoder.encode(serialized, :pretty => true)
+      expected.close
+
+      actual = Tempfile.new('actual.json')
+      actual.write Yajl::Encoder.encode(latest, :pretty => true)
+      actual.close
+
+      warn `diff #{expected.path} #{actual.path}`
+
+      expected.unlink
+      actual.unlink
     end
   end
 

test/test_tokenizer.rb

@@ -94,6 +94,8 @@ class TestTokenizer < Test::Unit::TestCase
     assert_equal "SHEBANG#!ruby", tokenize(:"Ruby/ruby.script!")[0]
     assert_equal "SHEBANG#!ruby", tokenize(:"Ruby/ruby2.script!")[0]
     assert_equal "SHEBANG#!node", tokenize(:"JavaScript/js.script!")[0]
+    assert_equal "SHEBANG#!php", tokenize(:"PHP/php.script!")[0]
+    assert_equal "echo", tokenize(:"Shell/invalid-shebang.sh")[0]
   end
 
   def test_javascript_tokens