cddl 0.11.5 → 0.12.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 652f1e63847fbed19fceeca1ed0b695b25b5f8aa6d312b2bd17f21c0ac7c6549
-  data.tar.gz: d55f4a0bff69a37b1c6101b11eb003eb93c00df24ede1dded8d7be9844b4afb1
+  metadata.gz: 4b6553d8156f74c2c630f22f6069c537e53b4f34a3d436df02ce73f99e648cb5
+  data.tar.gz: 175ddf07c82ef984d40c932eb80f8a8d7cdab54823777d8e9482239251756edc
 SHA512:
-  metadata.gz: 6622daf044d0f5a6d0ce4fe90ac57341526f7723aef0ce49e228edd2284711a44302ab0c3a1a28e3e156676db61afb4477a9b97b27269e1509034c41796ca8b9
-  data.tar.gz: 966fd633edc283925e0e4bbb5ca04cb40de60470044bbbd94e7df41fb05c185f59ff09ae4767d5dea2899491d3f82db50d3feb01a585fe03891d60f073e50557
+  metadata.gz: 357a054cb881ab89c00befe26adfcbf9999b8cbd19f400bdd31eccc39a0eb690e50f4552fc446dfa364086987e1187638983e3579e1a3e06084eb874e1311509
+  data.tar.gz: bf8e429cf02926f4c078e7911d73ccffb47ee3c96520f627e33673333061cd85b472e3795a122362fe615c7b73f8ac2ad6ac02290c5f9a0a9ba19ebe3b15fae6

data/bin/cddl

@@ -22,6 +22,13 @@ def usage
   exit EX_USAGE
 end
 
+def utfify(s)
+  s.force_encoding(Encoding::UTF_8).scrub { |c|
+      warn "*** replaced invalid UTF-8 byte sequence #{c.inspect} by U+FFFD REPLACEMENT CHARACTER"
+      0xFFFD.chr(Encoding::UTF_8)
+  }
+end
+
 def read_arg(arg, remember_fn = true)
   if arg == "-"
     $fn = "(stdin)" if remember_fn
@@ -34,7 +41,7 @@ def read_arg(arg, remember_fn = true)
 end
 
 def parser
-  @parser ||= CDDL::Parser.new(read_arg(ARGV[0], false))
+  @parser ||= CDDL::Parser.new(utfify(read_arg(ARGV[0], false)))
 end
 
 def my_pp(v)
@@ -99,7 +106,12 @@ begin
       instance = if $sequence
                    CBOR.decode("\x9f".b << instance.b << "\xff".b)
                  else
-                   CBOR.decode(instance.b) rescue JSON.load(instance)
+                   begin
+                     CBOR.decode(instance.b)
+                   rescue => e
+                     warn e.inspect if verbose
+                     JSON.load(utfify(instance))
+                   end
                  end
       instance = instance.cbor_clone if $annotate && ENV["EXPERIMENTAL_ANNOTATE"]
       warn "#{fn}:" if verbose
@@ -107,6 +119,7 @@ begin
       # my_pp ann
       instance.cbor_add_annotations_from(ann) rescue nil
       my_diag(instance) if $annotate
+      warn "ann: #{!!ann}" if verbose
       unless ann
         retcode = 1
       end

data/cddl.gemspec

@@ -1,6 +1,6 @@
 spec = Gem::Specification.new do |s|
   s.name = 'cddl'
-  s.version = '0.11.5'
+  s.version = '0.12.2'
   s.summary = "CDDL generator and validator."
   s.description = %{A parser, generator, and validator for CDDL}
   s.add_dependency('cbor-diag')

data/data/cddl.abnf

@@ -70,27 +70,39 @@ fraction = 1*DIGIT
 exponent = int
 
 text = %x22 *SCHAR %x22
-SCHAR = %x20-21 / %x23-7E / SESC
-SESC = "\" %x20-7E
+SCHAR = %x20-21 / %x23-5B / %x5D-7E / NONASCII / SESC
+
+SESC = "\" ( %x22 / "/" / "\" /                 ; \" \/ \\
+             %x62 / %x66 / %x6E / %x72 / %x74 / ; \b \f \n \r \t
+             (%x75 hexchar) )                   ; \uXXXX
+
+hexchar = "{" (1*"0" [ hexscalar ] / hexscalar) "}" /
+          non-surrogate / (high-surrogate "\" %x75 low-surrogate)
+non-surrogate = ((DIGIT / "A"/"B"/"C" / "E"/"F") HEXDIG HEXDIG HEXDIG) /
+                ("D" %x30-37 HEXDIG HEXDIG)
+high-surrogate = "D" ("8"/"9"/"A"/"B") HEXDIG HEXDIG
+low-surrogate = "D" ("C"/"D"/"E"/"F") HEXDIG HEXDIG
+hexscalar = "10" HEXDIG HEXDIG HEXDIG HEXDIG / HEXDIG1 HEXDIG HEXDIG HEXDIG HEXDIG
+          / non-surrogate / HEXDIG [HEXDIG [HEXDIG]]
 
 bytes = [bsqual] %x27 *BCHAR %x27
-BCHAR = %x20-26 / %x28-5B / %x5D-7E / SESC / CRLF
-bsqual = %x68 ; "h"
-       / %x62.36.34 ; "b64"
+BCHAR = %x20-26 / %x28-5B / %x5D-7E / NONASCII / SESC / "\'" / CRLF
+bsqual = "h" / "b64"
 
 id = EALPHA *(*("-" / ".") (EALPHA / DIGIT))
 ALPHA = %x41-5A / %x61-7A
-EALPHA = %x41-5A / %x61-7A / "@" / "_" / "$"
+EALPHA = ALPHA / "@" / "_" / "$"
 DIGIT = %x30-39
 DIGIT1 = %x31-39
 HEXDIG = DIGIT / "A" / "B" / "C" / "D" / "E" / "F"
+HEXDIG1 = DIGIT1 / "A" / "B" / "C" / "D" / "E" / "F"
 BINDIG = %x30-31
 
 S = *WS
 WS = SP / NL
 SP = %x20
 NL = COMMENT / CRLF
-COMMENT = ";" *(SP / VCHAR) CRLF
-VCHAR = %x21-7E
+COMMENT = ";" *PCHAR CRLF
+PCHAR = %x20-7E / NONASCII
+NONASCII = %xA0-D7FF / %xE000-10FFFD
 CRLF = %x0A / %x0D.0A
-

data/lib/cddl.rb

@@ -61,7 +61,7 @@ module CDDL
         if upto - presult < 100
           part2 = source_text[presult...upto]
         else
-          part2 = source_text[presult, 50] + "......." + source_text[upto-50, 50]
+          part2 = source_text[presult, 50] + "......." + (source_text[upto-50, 50] || "")
         end
         warn "*** Look for syntax problems around the #{
                "%%%".colorize(background: :light_yellow)} markers:\n#{
@@ -1473,6 +1473,18 @@ module CDDL
                      end
     end
 
+    STRING_ESCAPES = {
+      "\"" => "\"",
+      "/" => "/",
+      "\\" => "\\",
+      "'" => "'",
+      "b" => "\b",
+      "f" => "\f",
+      "n" => "\n",
+      "r" => "\r",
+      "t" => "\t",
+    }
+
     def value(n)
       # cheat:
       # warn n
@@ -1482,7 +1494,20 @@ module CDDL
         if parts[-1] != ""
           warn "*** Problem decoding byte string #{s.inspect}"
         end
-        bsval = parts[0...-1].join("'").gsub(/\\(.)/){$1}
+        bsval = parts[0...-1].join("'").gsub(/\\u([Dd][89AaBb][0-9a-zA-Z]{2})\\u([Dd][CcDdEeFf][0-9a-zA-Z]{2})|\\u([0-9a-zA-Z]{4})|\\u\{([0-9a-zA-Z]+)\}|\r?(\n)|\\([^u])/) {
+          if hex = $3 || $4
+            hex.to_i(16).chr(Encoding::UTF_8)
+          elsif lf = $5
+            lf
+          elsif escaped = $6
+            STRING_ESCAPES[$6] or (
+              fail "Invalid String Escape #{escaped.inspect} in #{s.inspect}"
+            )
+          else
+            ((($1.to_i(16) & 0x3ff) << 10) +
+             ($2.to_i(16) & 0x3ff) + 0x10000).chr(Encoding::UTF_8)
+          end
+        }
         [:bytes,
          case bsqual
          when ""
@@ -1496,7 +1521,17 @@ module CDDL
          end
         ]
       else
-        val = eval(n.to_s)
+        if s[-1] == '"'
+          s.gsub!(/\\u([Dd][89AaBb][0-9a-zA-Z]{2})\\u([Dd][CcDdEeFf][0-9a-zA-Z]{2})|\\([^u]|u[0-9a-zA-Z]{4})/) {
+            if $3
+              "\\#$3" # skip this, use eval parser
+            else
+              ((($1.to_i(16) & 0x3ff) << 10) +
+               ($2.to_i(16) & 0x3ff) + 0x10000).chr(Encoding::UTF_8)
+            end
+          }
+        end
+        val = eval(s)
         # warn val
         case val
          when Integer; [:int, val]

data/test-data/b64u-strict.cddl

@@ -5,6 +5,8 @@ a = text .b64u bytes
 ;;vp "AAAA"
 ;;vp "AAA-"
 ;;vp "AAA_"
+; fail with 0.11.5:
 ;;vp "AAA+"
 ;;vp "AAA/"
 ;;vp "AAA="
+;;vp "+kd8"

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: cddl
 version: !ruby/object:Gem::Version
-  version: 0.11.5
+  version: 0.12.2
 platform: ruby
 authors:
 - Carsten Bormann
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2024-04-15 00:00:00.000000000 Z
+date: 2024-06-02 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: cbor-diag
@@ -290,7 +290,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.5.4
+rubygems_version: 3.5.11
 signing_key:
 specification_version: 4
 summary: CDDL generator and validator.