datauris 1.0.0 → 1.1.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 8b17d925dd560274e1e3a4f21e5caa118762e74c1d5b1e4e07777c9456b64f0f
-  data.tar.gz: 34c7263eea9cd31e1bfede00bb4002d303dc59d7870d3bad620a88a7345d292a
+  metadata.gz: 7709f8cf824f237c4aed38259191ecb6fd4cf39d3b29664a93ea1ee16902f492
+  data.tar.gz: 8961a0856b232df9c7a5995db91e4f4ae08c072e7d4d655d51ae0be6b8226009
 SHA512:
-  metadata.gz: 509299375bebbc22eee68c3c3a704030df51c1d555a57ee5ff83435b1b5d6a0cf9de75c49d1551f277e89db01280bb7f15dc2f2ddd42cfa9bf3ef7279cef0ce4
-  data.tar.gz: b0aba84982c23968350395e3aedf91e11bf7f31a20566e1262f715f9638fdcf05b91aa2e575f4189ca0d58318f8702de0d587efbd7262d7a0c466a3b8e1e33e9
+  metadata.gz: 85584d023850013b98801c46775c5a43ea76d08eedef815457921684063081a0786517919190c1b9c0b2fbd2d9923773739c0f029338d78d44fcfe88513b9459
+  data.tar.gz: e4a6796902329a3efb962f3733012bbce8b9dd2baf2f315f92b033e41c627630a4ef5c0981368c84526623ed9226bd573e7f079cae6b03c0beb3f0382cdc98d8

data/CHANGELOG.md

@@ -1,4 +1,4 @@
-### 1.0.0
+### 1.1.0
 ### 0.0.1 / 2023-11-23
 
 * Everything is new. First release

data/README.md

@@ -1,6 +1,6 @@
 # Data URI Helpers
 
-datauris - helpers to parse (decode) and build (encode) data uris incl. (strict)base64-encoded/decoded images and more
+datauris - helpers to parse (decode) and build (encode) data uris incl. (strict) base64-encoded/decoded images and more
 
 * home  :: [github.com/s6ruby/rubidity](https://github.com/s6ruby/rubidity)
 * bugs  :: [github.com/s6ruby/rubidity/issues](https://github.com/s6ruby/rubidity/issues)
@@ -58,21 +58,21 @@ Let's try and parse the Wikipedia Data URI examples:
 uri = "data:text/vnd-example+xyz;foo=bar;base64,R0lGODdh"
 DataUri.valid?( uri )  
 #=> true
-mediatype, data = DataUri.parse( uri )    ## returns 1) mediatype (+parameters), 2) data
-#=> "text/vnd-example+xyz;foo=bar", "<blob>"
+data, mediatype = DataUri.parse( uri )    ## returns 1) data, 2) mediatype (+parameters)
+#=> "<blob>", "text/vnd-example+xyz;foo=bar"
 
 uri = "data:text/plain;charset=UTF-8;page=21,the%20data:1234,5678"
 DataUri.valid?( uri )  
 #=> true
-mediatype, data = DataUri.parse( uri )    ## returns 1) mediatype (+parameters), 2) data
-#=> "text/plain;charset=UTF-8;page=21", "the data:1234,5678"
+data, mediatype = DataUri.parse( uri )    ## returns 1) data, 2) mediatype (+parameters)
+#=> "the data:1234,5678", "text/plain;charset=UTF-8;page=21"
 
 
 uri = "data:image/jpeg;base64,/9j/4AAQSkZJRgABAgAAZABkAAD/"
 DataUri.valid?( uri )  
 #=> true
-mediatype, data = DataUri.parse( uri )    ## returns 1) mediatype (+parameters), 2) data
-#=> "image/jpeg", "<blob>"
+data, mediatype = DataUri.parse( uri )    ## returns 1) data, 2) mediatype (+parameters)
+#=> "<blob>", "image/jpeg"
 ```
 
 
@@ -87,7 +87,7 @@ uri = "data:,"
 
 DataUri.valid?( uri )  
 #=> true
-mediatype, data = DataUri.parse( uri )    ## returns 1) mediatype (+parameters), 2) data
+data, mediatype = DataUri.parse( uri )    ## returns 1) data, 2) mediatype (+parameters)
 #=> "", ""
 ```
 
@@ -98,8 +98,8 @@ uri = "data:image/jpeg;base64,/9j/4AAQSkZJRgABAgAAZABkAAD/7AARRHV..."
 
 DataUri.valid?( uri )  
 #=> true
-mediatype, data = DataUri.parse( uri )    ## returns 1) mediatype (+parameters), 2) data
-#=> "image/jpeg", "<blob>"
+data, mediatype = DataUri.parse( uri )    ## returns 1) data, 2) mediatype (+parameters)
+#=> "<blob>", "image/jpeg"
 
 ## let's save the jpeg image (blob)
 write_blob( "0.jpeg", data )
@@ -117,8 +117,8 @@ uri = "data:image/png;base64,/9j/4gxYSUNDX1BST0ZJTEUAAQEAAAxITGlubwIQAAB..."
 
 DataUri.valid?( uri )  
 #=> true
-mediatype, data = DataUri.parse( uri )    ## returns 1) mediatype (+parameters), 2) data
-#=> "image/png", "<blob>"
+data, mediatype = DataUri.parse( uri )    ## returns 1) data, 2) mediatype (+parameters)
+#=> "<blob>", "image/png"
 
 ## let's save the png image (blob)
 write_blob( "15.png", data )

data/lib/datauris/version.rb

@@ -1,7 +1,7 @@
 
 module DataUri
   MAJOR = 1 ## todo: namespace inside version or something - why? why not??
-  MINOR = 0
+  MINOR = 1
   PATCH = 0
   VERSION = [MAJOR,MINOR,PATCH].join('.')
 

data/lib/datauris.rb

@@ -8,17 +8,6 @@ require_relative 'datauris/version'     # let version go first
 
 
 module DataUri
-    REGEX_V0 = %r{
-      \Adata:
-      (?<mediatype>
-        (?<type> .+? / .+? )?
-        (?<parameters> (?: ; .+? = .+? )* )
-      )?
-      (?<base64extension>;base64)?
-      ,
-      (?<data>.*)\z
-    }x
-
     ## allow type only - why? why not?
     ## split subtype into [tree prefix] and subtype
     ##  check if type can include dash (-) - why? why not?
@@ -58,13 +47,15 @@ module DataUri
             (?<subtype> [\w.+-]+? )
         )?
         (?<parameters> (?: ; 
-                           [\w.+-]+? 
+                           [\w-]+? 
                               = 
                               .+? 
                         )* 
         )
       )?
-      (?<base64extension>;base64)?
+      (?:;
+         (?<extension>base64|utf8)
+       )?
       ,
       (?<data>.*)
       \z
@@ -73,41 +64,57 @@ module DataUri
 
     def self._parse( str ) REGEX.match( str ); end
 
-    def self.parse( str )
+    def self.parse( str, utf8: false )   ## allow force utf8 with utf8: true
         m = _parse( str ) 
   
         if m
           ## 1) return mediatype (mimetype PLUS optional parameters)
           ## 2) return data (base64 decoded or not)
   
+          ## todo/check:
+          ##   add force_encoding( 'UTF-8' ) to returned data (if not base64) - why? why not?
+
           mediatype = m[:mediatype]  
-          data      = if m[:base64extension]   ## assume base64 encoded
+          data      = if m[:extension] && m[:extension] == 'base64'  ## assume base64 encoded
                          Base64.strict_decode64(m[:data])
+                      elsif utf8 || (m[:extension] && m[:extension] == 'utf8')
+                         m[:data]    ## note: no decode; assume "plain" utf8 string  
                       else
                          ## e.g. %20 => space(20)
                          ##  etc.
                          ## todo/double check - use a different URI decoder - why? why not?
                          URI.decode_uri_component(m[:data])
                       end
-          [mediatype, data]
+
+          ## returns data first!!!
+          ##  and mediatype second (to follow the order in build)
+          ##   - also mediatype is optional -  arguable more intuitive - yes,no?
+          [data, mediatype]
         else
            raise ArgumentError, "invalid datauri - cannot match regex; sorry"
         end
     end
 
 
-    def self.valid?( str )
+    def self.valid?( str, utf8: false )
       m = _parse( str )
       if m 
-        if m[:base64extension]   ## assume base64
+        if m[:extension] && m[:extension] == 'base64'   ## assume base64
           begin
             Base64.strict_decode64(m[:data])
             true
           rescue ArgumentError
             false
           end
+        elsif utf8 || (m[:extension] && m[:extension] == 'utf8') 
+           true   ## pass through as is; assume always true (check valid utf8 encoding - why? why not?) 
         else
-          true
+          begin 
+            URI.decode_uri_component(m[:data])            
+            true
+          rescue ArgumentError   ## check if decode errors are argument errors??
+            false
+          end
         end
       else
         false
@@ -161,8 +168,10 @@ module DataUri
     end
 
 
-    ## base64 - force base64 encoding (instead of "automagic")
-    def self.build( data, type=nil, base64: nil )
+    ## base64 - force base64 encoding instead of "automagic" (base64: true)
+    ## utf8   - or force utf8 encoding  (utf8: true)
+    ## uri    - or force STOPPING uri encoding (uri: false)
+    def self.build( data, type=nil, base64: nil, utf8: nil, uri: nil )
         uri = "data:"
         uri += type      if type   ## note: allow optional / no type
         
@@ -187,12 +196,16 @@ module DataUri
 
         if base64    
             uri += ";base64," + Base64.strict_encode64( data )
+        elsif utf8 
+            uri += ";utf8," + data          
         else
             ## use encode_uri_component by default - why? why not?
             ##  space becomes %20
             ##  :     becomes %3A
             ##  ,     becomes %2C  and so on
-            uri += "," + encode_uri( data )
+            ##
+            ## note: use uri: false to turn of uri encode!!!
+            uri += "," +  (uri == false ? data : encode_uri( data ))
         end   
     end
       
@@ -201,8 +214,8 @@ module DataUri
     ## add alias convenience names - why? why not?
     class << self 
       alias_method :is_valid?,   :valid?
-      alias_method :decode,      :parse
-      alias_method :encode,      :build
+      alias_method :decode,      :parse    ### add decode - why? why not?
+      alias_method :encode,      :build    ### add encode - why? why not?
     end
 end  # module  DataUri
 

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: datauris
 version: !ruby/object:Gem::Version
-  version: 1.0.0
+  version: 1.1.0
 platform: ruby
 authors:
 - Gerald Bauer
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2023-11-24 00:00:00.000000000 Z
+date: 2023-11-27 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rdoc