ebnf 1.1.1 → 2.1.0

data/UNLICENSE

@@ -21,4 +21,4 @@ OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
 ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
 OTHER DEALINGS IN THE SOFTWARE.
 
-For more information, please refer to <http://unlicense.org/>
+For more information, please refer to <https://unlicense.org/>

data/VERSION

@@ -1 +1 @@
-1.1.1
+2.1.0

data/bin/ebnf

@@ -15,6 +15,7 @@ options = {
   output_format: :sxp,
   prefix: "ttl",
   namespace: "http://www.w3.org/ns/formats/Turtle#",
+  level: 4
 }
 
 input, out = nil, STDOUT
@@ -23,14 +24,17 @@ OPT_ARGS = [
   ["--debug",           GetoptLong::NO_ARGUMENT,      "Turn on debugging output"],
   ["--bnf",             GetoptLong::NO_ARGUMENT,      "Transform EBNF to BNF"],
   ["--evaluate","-e",   GetoptLong::REQUIRED_ARGUMENT,"Evaluate argument as an EBNF document"],
+  ["--format", "-f",    GetoptLong::REQUIRED_ARGUMENT,"Specify output format one of abnf, abnfh, ebnf, html, isoebnf, isoebnfh, ttl, sxp, or rb"],
+  ["--input-format",    GetoptLong::REQUIRED_ARGUMENT,"Specify input format one of abnf, ebnf isoebnf, native, or sxp"],
   ["--ll1",             GetoptLong::REQUIRED_ARGUMENT,"Generate First/Follow rules, argument is start symbol"],
-  ["--format", "-f",    GetoptLong::REQUIRED_ARGUMENT,"Specify output format one of ebnf, html, ttl, sxp, or rb"],
-  ["--input-format",    GetoptLong::REQUIRED_ARGUMENT,"Specify input format one of ebnf or sxp"],
   ["--mod-name",        GetoptLong::REQUIRED_ARGUMENT,"Module name used when creating ruby tables"],
+  ["--namespace", "-n", GetoptLong::REQUIRED_ARGUMENT,"Namespace to use when generating Turtle"],
   ["--output", "-o",    GetoptLong::REQUIRED_ARGUMENT,"Output to the specified file path"],
+  ["--peg",             GetoptLong::NO_ARGUMENT,      "Transform EBNF to PEG"],
   ["--prefix", "-p",    GetoptLong::REQUIRED_ARGUMENT,"Prefix to use when generating Turtle"],
   ["--progress", "-v",  GetoptLong::NO_ARGUMENT,      "Detail on execution"],
-  ["--namespace", "-n", GetoptLong::REQUIRED_ARGUMENT,"Namespace to use when generating Turtle"],
+  ["--renumber",        GetoptLong::NO_ARGUMENT,      "Renumber parsed reules"],
+  ["--validate",        GetoptLong::NO_ARGUMENT,      "Validate grammar"],
   ["--help", "-?",      GetoptLong::NO_ARGUMENT,      "This message"]
 ]
 def usage
@@ -53,42 +57,57 @@ opts = GetoptLong.new(*OPT_ARGS.map {|o| o[0..-2]})
 
 opts.each do |opt, arg|
   case opt
-  when '--debug'        then options[:debug] = true
+  when '--debug'        then options[:level] = 0
   when '--bnf'          then options[:bnf] = true
   when '--evaluate'     then input = arg
-  when '--input-format' then options[:format] = arg.to_sym
-  when '--format'       then options[:output_format] = arg.to_sym
-  when '--ll1'          then (options[:ll1] ||= []) <<arg.to_sym
+  when '--input-format'
+    unless %w(abnf ebnf isoebnf native sxp).include?(arg)
+      STDERR.puts("unrecognized input format #{arg}")
+      usage
+    end
+    options[:format] = arg.to_sym
+  when '--format'
+    unless %w(abnf abnfh ebnf html isoebnf isoebnfh rb sxp).include?(arg)
+      STDERR.puts("unrecognized output format #{arg}")
+      usage
+    end
+    options[:output_format] = arg.to_sym
+  when '--ll1'          then (options[:ll1] ||= []) << arg.to_sym
   when '--mod-name'     then options[:mod_name] = arg
   when '--output'       then out = File.open(arg, "w")
+  when '--peg'          then options[:peg] = true
   when '--prefix'       then options[:prefix] = arg
+  when '--renumber'     then options[:renumber] = true
   when '--namespace'    then options[:namespace] = arg
-  when '--progress'     then options[:progress] = true
+  when '--progress'     then options[:level] = 1 unless options[:level] == 0
+  when '--validate'     then options[:validate] = true
   when '--help'         then usage
   end
 end
 
-if options[:output_format] == :rb && !options[:ll1]
-  STDERR.puts "outputing in .rb format requires -ll"
-  exit(1)
-end
-
 input = File.open(ARGV[0]) if ARGV[0]
 
-ebnf = EBNF.parse(input || STDIN, options)
+ebnf = EBNF.parse(input || STDIN, **options)
 ebnf.make_bnf if options[:bnf] || options[:ll1]
+ebnf.make_peg if options[:peg]
 if options[:ll1]
   ebnf.first_follow(*options[:ll1])
   ebnf.build_tables
-  
+end
+
+ebnf.renumber! if options[:renumber]
 
 res = case options[:output_format]
-when :ebnf    then ebnf.to_s
-when :html    then ebnf.to_html
-when :sxp     then ebnf.to_sxp
-when :ttl     then ebnf.to_ttl(options[:prefix], options[:namespace])
-when :rb      then ebnf.to_ruby(out, options.merge(grammarFile: ARGV[0]))
-else          ebnf.ast.inspect
+when :abnf      then ebnf.to_s(format: :abnf)
+when :abnfh     then ebnf.to_html(format: :abnf)
+when :ebnf      then ebnf.to_s
+when :html      then ebnf.to_html
+when :isoebnf   then ebnf.to_s(format: :isoebnf)
+when :isoebnfh  then ebnf.to_html(format: :isoebnf)
+when :sxp       then ebnf.to_sxp
+when :ttl       then ebnf.to_ttl(options[:prefix], options[:namespace])
+when :rb        then ebnf.to_ruby(out, grammarFile: ARGV[0], **options)
+else            ebnf.ast.inspect
 end
 
 out.puts res

data/etc/abnf-core.ebnf

@@ -0,0 +1,52 @@
+# Core terminals available in uses of ABNF
+ALPHA        ::=  [#x41-#x5A#x61-#x7A]   # A-Z | a-z
+
+BIT          ::=  '0' | '1'
+
+CHAR         ::=  [#x01-#x7F]
+                       # any 7-bit US-ASCII character,
+                       #  excluding NUL
+CR           ::=  #x0D
+                       # carriage return
+
+CRLF         ::=  CR? LF
+                       # Internet standard newline
+
+CTL          ::=  [#x00-#x1F] | #x7F
+                       # controls
+
+DIGIT        ::=  [#x30-#x39]
+                       # 0-9
+
+DQUOTE       ::=  #x22
+                       # " (Double Quote)
+
+HEXDIG       ::=  DIGIT | [A-F] # [0-9A-F]
+
+HTAB         ::=  #x09
+                       # horizontal tab
+
+LF           ::=  #x0A
+                       # linefeed
+
+LWSP         ::=  (WSP | CRLF WSP)*
+                       # Use of this linear-white-space rule
+                       #  permits lines containing only white
+                       #  space that are no longer legal in
+                       #  mail headers and have caused
+                       #  interoperability problems in other
+                       #  contexts.
+                       # Do not use when defining mail
+                       #  headers and use with caution in
+                       #  other contexts.
+
+OCTET        ::=  [#x00-#xFF]
+                       # 8 bits of data
+
+SP           ::=  #x20
+
+VCHAR        ::=  [#x21-#x7E]
+                       # visible (printing) characters
+
+WSP          ::=  SP | HTAB
+                       # white space

data/etc/abnf.abnf

@@ -0,0 +1,121 @@
+rulelist       =  1*( rule / (*c-wsp c-nl) )
+
+rule           =  rulename defined-as elements c-nl
+                      ; continues if next line starts
+                      ;  with white space
+
+rulename       =  ALPHA *(ALPHA / DIGIT / "-")
+
+defined-as     =  *c-wsp ("=" / "=/") *c-wsp
+                      ; basic rules definition and
+                      ;  incremental alternatives
+
+elements       =  alternation *c-wsp
+
+c-wsp          =  WSP / (c-nl WSP)
+
+c-nl           =  comment / CRLF
+                      ; comment or newline
+
+comment        =  ";" *(WSP / VCHAR) CRLF
+
+alternation    =  concatenation
+                  *(*c-wsp "/" *c-wsp concatenation)
+
+concatenation  =  repetition *(1*c-wsp repetition)
+
+repetition     =  [repeat] element
+
+repeat         =  (*DIGIT "*" *DIGIT) / 1*DIGIT
+
+element        =  rulename / group / option /
+                  char-val / num-val / prose-val
+
+group          =  "(" *c-wsp alternation *c-wsp ")"
+
+option         =  "[" *c-wsp alternation *c-wsp "]"
+
+char-val       =  case-insensitive-string /
+                  case-sensitive-string
+
+case-insensitive-string =
+                  [ "%i" ] quoted-string
+
+case-sensitive-string =
+                  "%s" quoted-string
+
+quoted-string  =  DQUOTE *(%x20-21 / %x23-7E) DQUOTE
+                       ; quoted string of SP and VCHAR
+                       ;  without DQUOTE
+
+num-val        =  "%" (bin-val / dec-val / hex-val)
+
+bin-val        =  "b" 1*BIT
+                  [ 1*("." 1*BIT) / ("-" 1*BIT) ]
+                       ; series of concatenated bit values
+                       ;  or single ONEOF range
+
+dec-val        =  "d" 1*DIGIT
+                  [ 1*("." 1*DIGIT) / ("-" 1*DIGIT) ]
+
+hex-val        =  "x" 1*HEXDIG
+                  [ 1*("." 1*HEXDIG) / ("-" 1*HEXDIG) ]
+
+prose-val      =  "<" *(%x20-3D / %x3F-7E) ">"
+                       ; bracketed string of SP and VCHAR
+                       ;  without angles
+                       ; prose description, to be used as
+                       ;  last resort
+
+ALPHA          =  %x41-5A / %x61-7A   ; A-Z / a-z
+
+BIT            =  "0" / "1"
+
+CHAR           =  %x01-7F
+                         ; any 7-bit US-ASCII character,
+                         ;  excluding NUL
+CR             =  %x0D
+                             ; carriage return
+
+CRLF           =  [CR] LF
+                       ; Internet standard newline
+                       ; Extended to allow only newline
+
+CTL            =  %x00-1F / %x7F
+                       ; controls
+
+DIGIT          =  %x30-39
+                       ; 0-9
+
+DQUOTE         =  %x22
+                       ; " (Double Quote)
+
+HEXDIG         =  DIGIT / "A" / "B" / "C" / "D" / "E" / "F"
+
+HTAB           =  %x09
+                       ; horizontal tab
+
+LF             =  %x0A
+                       ; linefeed
+
+LWSP           =  *(WSP / CRLF WSP)
+                       ; Use of this linear-white-space rule
+                       ;  permits lines containing only white
+                       ;  space that are no longer legal in
+                       ;  mail headers and have caused
+                       ;  interoperability problems in other
+                       ;  contexts.
+                       ; Do not use when defining mail
+                       ;  headers and use with caution in
+                       ;  other contexts.
+
+OCTET          =  %x00-FF
+                       ; 8 bits of data
+
+SP             =  %x20
+
+VCHAR          =  %x21-7E
+                       ; visible (printing) characters
+
+WSP            =  SP / HTAB
+                       ; white space

data/etc/abnf.ebnf

@@ -0,0 +1,124 @@
+rulelist     ::=  ( rule | (c_wsp* c_nl) )+
+
+rule         ::=  rulename defined_as elements c_nl
+                      # continues if next line starts
+                      #  with white space
+
+elements     ::=  alternation c_wsp*
+
+alternation  ::=  concatenation
+                  (c_wsp* "/" c_wsp* concatenation)*
+
+concatenation::=  repetition (c_wsp+ repetition)*
+
+repetition   ::=  repeat? element
+
+repeat       ::=  (DIGIT* "*" DIGIT*) | DIGIT+
+
+element      ::=  rulename | group | option |
+                  char_val | num_val | prose_val
+
+group        ::=  "(" c_wsp* alternation c_wsp* ")"
+
+option       ::=  "[" c_wsp* alternation c_wsp* "]"
+
+char_val     ::=  case_insensitive_string |
+                  case_sensitive_string
+
+case_insensitive_string ::=
+                  "%i"? quoted_string
+
+case_sensitive_string ::=
+                  "%s" quoted_string
+
+num_val      ::=  "%" (bin_val | dec_val | hex_val)
+
+@terminals
+
+# Terminals used in ABNF, itself
+rulename     ::=  ALPHA (ALPHA | DIGIT | "-")*
+
+defined_as   ::=  c_wsp* ("=" | "=/") c_wsp*
+                      # basic rules definition and
+                      #  incremental alternatives
+
+c_wsp        ::=  WSP | (c_nl WSP)
+
+c_nl         ::=  COMMENT | CRLF
+                      # comment or newline
+
+comment      ::=  ";" (WSP | VCHAR)* CRLF
+
+quoted_string::=  DQUOTE [#x20-#x21#x23-#x7E]* DQUOTE
+                       # quoted string of SP and VCHAR
+                       #  without DQUOTE
+
+bin_val      ::=  "b" BIT+
+                  (("." BIT+)+  | ("-" BIT+))?
+                       # series of concatenated bit values
+                       #  or single ONEOF range
+
+dec_val      ::=  "d" DIGIT+
+                  (("." DIGIT+)+ | ("-" DIGIT+))?
+
+hex_val      ::=  "x" HEXDIG+
+                  (("." HEXDIG+)+ | ("-" HEXDIG+))?
+
+prose_val    ::=  "<" [#x20-#x3D#x3F-#x7E]* ">"
+                       # bracketed string of SP and VCHAR
+                       #  without angles
+                       # prose description, to be used as
+                       #  last resort
+
+# Core terminals available in uses of ABNF
+ALPHA        ::=  [#x41-#x5A#x61-#x7A]   # A-Z | a-z
+
+BIT          ::=  '0' | '1'
+
+CHAR         ::=  [#x01-#x7F]
+                       # any 7-bit US-ASCII character,
+                       #  excluding NUL
+CR           ::=  #x0D
+                       # carriage return
+
+CRLF         ::=  CR? LF
+                       # Internet standard newline
+
+CTL          ::=  [#x00-#x1F] | #x7F
+                       # controls
+
+DIGIT        ::=  [#x30-#x39]
+                       # 0-9
+
+DQUOTE       ::=  #x22
+                       # " (Double Quote)
+
+HEXDIG       ::=  DIGIT | "A" | "B" | "C" | "D" | "E" | "F"
+
+HTAB         ::=  #x09
+                       # horizontal tab
+
+LF           ::=  #x0A
+                       # linefeed
+
+LWSP         ::=  (WSP | CRLF WSP)*
+                       # Use of this linear-white-space rule
+                       #  permits lines containing only white
+                       #  space that are no longer legal in
+                       #  mail headers and have caused
+                       #  interoperability problems in other
+                       #  contexts.
+                       # Do not use when defining mail
+                       #  headers and use with caution in
+                       #  other contexts.
+
+OCTET        ::=  [#x00-#xFF]
+                       # 8 bits of data
+
+SP           ::=  #x20
+
+VCHAR        ::=  [#x21-#x7E]
+                       # visible (printing) characters
+
+WSP          ::=  SP | HTAB
+                       # white space

data/etc/abnf.sxp

@@ -0,0 +1,45 @@
+    (
+     (rule rulelist (plus (alt rule (seq (star c_wsp) c_nl))))
+     (rule rule (seq rulename defined_as elements c_nl))
+     (rule elements (seq alternation (star c_wsp)))
+     (rule alternation
+      (seq concatenation (star (seq (star c_wsp) "/" (star c_wsp) concatenation))))
+     (rule concatenation (seq repetition (star (seq (plus c_wsp) repetition))))
+     (rule repetition (seq (opt repeat) element))
+     (rule repeat (alt (seq (star DIGIT) "*" (star DIGIT)) (plus DIGIT)))
+     (rule element (alt rulename group option char_val num_val prose_val))
+     (rule group (seq "(" (star c_wsp) alternation (star c_wsp) ")"))
+     (rule option (seq "[" (star c_wsp) alternation (star c_wsp) "]"))
+     (rule char_val (alt case_insensitive_string case_sensitive_string))
+     (rule case_insensitive_string (seq (opt "%i") quoted_string))
+     (rule case_sensitive_string (seq "%s" quoted_string))
+     (rule num_val (seq "%" (alt bin_val dec_val hex_val)))
+     (terminals _terminals (seq))
+     (terminal rulename (seq ALPHA (star (alt ALPHA DIGIT "-"))))
+     (terminal defined_as (seq (star c_wsp) (alt "=" "=/") (star c_wsp)))
+     (terminal c_wsp (alt WSP (seq c_nl WSP)))
+     (terminal c_nl (alt COMMENT CRLF))
+     (terminal comment (seq ";" (star (alt WSP VCHAR)) CRLF))
+     (terminal quoted_string (seq DQUOTE (star (range "#x20-#x21#x23-#x7E")) DQUOTE))
+     (terminal bin_val (seq "b" (plus BIT) (opt (alt (plus (seq "." (plus BIT))) (seq "-" (plus BIT))))))
+     (terminal dec_val
+      (seq "d" (plus DIGIT) (opt (alt (plus (seq "." (plus DIGIT))) (seq "-" (plus DIGIT))))))
+     (terminal hex_val
+      (seq "x" (plus HEXDIG) (opt (alt (plus (seq "." (plus HEXDIG))) (seq "-" (plus HEXDIG))))))
+     (terminal prose_val (seq "<" (star (range "#x20-#x3D#x3F-#x7E")) ">"))
+     (terminal ALPHA (range "#x41-#x5A#x61-#x7A"))
+     (terminal BIT (alt "0" "1"))
+     (terminal CHAR (range "#x01-#x7F"))
+     (terminal CR (hex "#x0D"))
+     (terminal CRLF (seq (opt CR) LF))
+     (terminal CTL (alt (range "#x00-#x1F") (hex "#x7F")))
+     (terminal DIGIT (range "#x30-#x39"))
+     (terminal DQUOTE (hex "#x22"))
+     (terminal HEXDIG (alt DIGIT "A" "B" "C" "D" "E" "F"))
+     (terminal HTAB (hex "#x09"))
+     (terminal LF (hex "#x0A"))
+     (terminal LWSP (star (alt WSP (seq CRLF WSP))))
+     (terminal OCTET (range "#x00-#xFF"))
+     (terminal SP (hex "#x20"))
+     (terminal VCHAR (range "#x21-#x7E"))
+     (terminal WSP (alt SP HTAB)))