regexador 0.4.5 → 0.4.6

data/test/programs.yaml

@@ -0,0 +1,201 @@
+---
+- !ruby/object:Program
+  description: Simple use of two vars
+  program: |
+       var1 = "abc"
+       var2 = "def"
+       match var1 var2 end
+  regex: !ruby/regexp /abcdef/
+  good:
+  - abcdefghi
+  - xyzabcdef
+  bad:
+  - ''
+  - abcxyzdef
+- !ruby/object:Program
+  description: Multiline match with two vars
+  program: "   var1 = \"abc\"\n   var2 = \"def\"\n        \n   # Test a blank line
+    and comment as well.\n \n   match   # multiline match with comment\n     var1\n
+    \    var2\n   end\n"
+  regex: !ruby/regexp /abcdef/
+  good:
+  - abcdefghi
+  - xyzabcdef
+  bad:
+  - ''
+  - abcxyzdef
+- !ruby/object:Program
+  description: IPv4 address
+  program: |
+       dot = "."
+       num = "25" D5 | `2 D4 D | maybe D1 1,2*D
+       match BOS num dot num dot num dot num EOS end
+  regex: !ruby/regexp /^(25[0-5]|2[0-4]\d|([01])?(\d){1,2})\.(25[0-5]|2[0-4]\d|([01])?(\d){1,2})\.(25[0-5]|2[0-4]\d|([01])?(\d){1,2})\.(25[0-5]|2[0-4]\d|([01])?(\d){1,2})$/
+  good:
+  - "127.0.0.1"
+  - "255.254.93.22"
+  - "255.254.93.22"
+  bad:
+  - ''
+  - "7.8.9"
+  - "3.4.5.6.7"
+  - "1.2.3.256"
+- !ruby/object:Program
+  description: Identifying credit cards
+  program: |
+       # Warning: This one likely has errors!
+        
+       visa     = `4 12*D maybe 3*D
+       mc       = `5 D5 14*D
+       discover = `6 ("011" | `5 2*D) 12*D
+       amex     = `3 '47' 13*D
+       diners   = `3 (`0 D5 | '68' D) 11*D
+       jcb      = ("2131"|"1800"|"35" 3*D) 11*D
+       
+       match visa | mc | discover | amex | diners | jcb end
+  regex: !ruby/regexp /(4(\d){12}((\d){3})?|5[0-5](\d){14}|6(011|5(\d){2})(\d){12}|3[47](\d){13}|3(0[0-5]|[68]\d)(\d){11}|(2131|1800|35(\d){3})(\d){11})/
+
+
+  good: []
+  bad: []
+- !ruby/object:Program
+  description: Matching US phone num (with captures)
+  program: |
+       match
+         @area_code = 3 * D
+         `-
+         @prefix = 3*D
+         `-
+         @last4 = 4*D
+       end
+# regex: !ruby/regexp /(?<area_code>\d{3}){0}(?<prefix>\d{3}){0}(?<last4>\d{4}){0}\g<area_code>-\g<prefix>-\g<last4>/
+  regex: !ruby/regexp /(?<area_code>(\d){3})\-(?<prefix>(\d){3})\-(?<last4>(\d){4})/
+  good:
+  - '601-555-2345'
+  - 'call me at 888-425-9000'
+  bad:
+  - '888-HAL-9000'
+  - '800.237.1234'
+- !ruby/object:Program
+  description: KNOWNFAIL Matching a clock time, 12/24 hrs
+  program: |
+       hr12 = (maybe `0) `1-`9 | `1 D2
+       hr24 = (maybe `0) D | `1 D | `2 D3
+       sep  = `: | `.
+       min  = D5 D9
+       sec  = D5 D9
+       ampm = (maybe SPACE) ("am" | "pm")
+       time12 = hr12 sep min maybe (sep sec) maybe ampm
+       time24 = hr24 sep min maybe (sep sec)
+       match BOS (time12 | time24) EOS end
+  regex: !ruby/regexp /^(((0)?[1-9]|1[0-2])(:|\.)[0-5]\d((:|\.)[0-5]\d)?(( )?(am|pm))?|((0)?\d|1\d|2[0-3])(:|\.)[0-5]\d((:|\.)[0-5]\d)?)$/
+  good:
+  - '12:34'
+  - '1:23'
+  - '5:14pm'
+  - '19:43'
+  - '1:23:45'
+  - '1:23:45 pm'
+  - '7:43 pm'
+  - '8:32:45'
+  - '8.34'
+  - '8.34 pm'
+  - '8.34.45'
+  bad:
+  - ''
+  - abc
+  - '24:30'
+  - '25:30'
+  - '19:43 pm'
+  - '5:14  pm'
+- !ruby/object:Program
+  description: Using nocase
+  program: 'match BOS "abc" nocase "def" "ghi" EOS end'
+  regex: !ruby/regexp /^abc((?i)def)ghi$/
+  good:
+  - "abcdefghi"
+  - "abcDEFghi"
+  - "abcdEfghi"
+  bad:
+  - ""
+  - "x"
+  - "xabcdefghi"
+  - "abcdefghix"
+  - "aBcdefghi"
+  - "abcdefGhi"
+  - "abCdefghI"
+  - "abCdEfghI"
+# - !ruby/object:Program
+#   description: Simple use of two vars
+#   program: |
+#   regex: !ruby/regexp //
+#   good:
+#   bad:
+- !ruby/object:Program
+  description: Var used in simple repetition
+  program: |
+       n = 3
+       match BOS n * `x EOS end
+  regex: !ruby/regexp /^(x){3}$/
+  good:
+  - "xxx"
+  bad:
+  - ""
+  - "x"
+  - "xx x"
+  - "xxxx"
+- !ruby/object:Program
+  description: Var used in complex repetition
+  program: |
+       m = 4
+       n = 6
+       match BOS m,n * `x EOS end
+  regex: !ruby/regexp /^(x){4,6}$/
+  good:
+  - "xxxx"
+  - "xxxxx"
+  - "xxxxxx"
+  bad:
+  - ""
+  - "x"
+  - "xx x"
+  - "xxx"
+  - "xxxxxxx"
+- !ruby/object:Program
+  description: Using Unicode codepoint again
+  program: |
+       euro = &20ac
+       price = (euro | "$") SPACE many D maybe ("." 2*D)
+       match BOS price EOS end
+  regex: !ruby/regexp /^(€|\$) (\d)+(\.(\d){2})?$/
+  good:
+  - "€ 237"
+  - "$ 237"
+  - "€ 23.45"
+  - "€ 0.25"
+  bad:
+  - ""
+  - "x"
+  - "€"
+  - "€ "
+  - "€  237"
+  - "$  237"
+  - "€ 23.456"
+- !ruby/object:Program
+  description: Using within (1)
+  program: |
+       match within `/ end
+  regex: !ruby/regexp /(\/.*?\/)/
+  good:
+  - "There is a /slash-delimited string/ here."
+  bad:
+  - "No such string here."
+- !ruby/object:Program
+  description: Using escaping (1)
+  program: |
+       match escaping `/ end
+  regex: !ruby/regexp /\/|[^\/]*?\//
+  good:
+  - "This is /slash-delimited but \\/with embedded slashes \\/ also /."
+  bad:
+  - "No such string here."

data/test/test.rb

@@ -8,32 +8,163 @@ require "minitest/autorun"
 class TestRegexador < Minitest::Test
 
   def test_001_special_chars
-    @parser = Regexador::Parser.new 
-    assert @parser.cSQUOTE.parse("'")
-    assert @parser.cHASH.parse('#')
-    assert @parser.cNEWLINE.parse("\n")
-    assert @parser.cEQUAL.parse('=')
+    parser = Regexador::Parser.new 
+    assert parser.cSQUOTE.parse("'")
+    assert parser.cHASH.parse('#')
+    assert parser.cNEWLINE.parse("\n")
+    assert parser.cEQUAL.parse('=')
   end
 
   def test_002_intl_chars
-    @parser = Regexador::Parser.new 
-    assert @parser.char.parse_with_debug("`æ")
-    assert @parser.char.parse("`ß")
-    assert @parser.char.parse("`ç")
-    assert @parser.char.parse("`ö")
-    assert @parser.char.parse("`ñ")
+    parser = Regexador::Parser.new 
+    assert parser.char.parse_with_debug("`æ")
+    assert parser.char.parse("`ß")
+    assert parser.char.parse("`ç")
+    assert parser.char.parse("`ö")
+    assert parser.char.parse("`ñ")
   end
 
   def test_003_codepoints
-    @parser = Regexador::Parser.new 
-    assert @parser.codepoint.parse_with_debug("&1234")
-    assert @parser.codepoint.parse('&beef')
+    parser = Regexador::Parser.new 
+    assert parser.codepoint.parse_with_debug("&1234")
+    assert parser.codepoint.parse('&beef')
   end
 
   def test_004_predef_tokens
-    @parser = Regexador::Parser.new 
+    parser = Regexador::Parser.new 
     %w(BOS EOS START END).each do |token|
-      assert @parser.pattern.parse_with_debug(token)
+      assert parser.pattern.parse_with_debug(token)
     end
   end
+
+  def test_005_assignment
+    parser = Regexador::Parser.new 
+    assert parser.assignment.parse("a = 5")
+    assert parser.assignment.parse("a= 5")
+    assert parser.assignment.parse("a =5")
+    assert parser.assignment.parse("a=5")
+    assert parser.assignment.parse("myvar = 'xyz'")
+    assert parser.assignment.parse('var2 = "hello"')
+    assert parser.assignment.parse('this_var = `x-`z')
+    assert parser.assignment.parse('pat = maybe many `x-`z')
+  end
+
+  def test_006_keyword_as_var
+    parser = Regexador::Parser.new 
+    assert_raises { parser.assignment.parse("end = 'hello'") }
+    parser = Regexador::Parser.new 
+    assert parser.assignment.parse_with_debug("endx = 'hello'")
+    assert parser.assignment.parse_with_debug("end5 = 'hello'")
+    assert parser.assignment.parse_with_debug("end_ = 'hello'")
+    assert parser.assignment.parse_with_debug("anyx = 'hello'")
+  end
+
+  def test_007_def_section
+    parser = Regexador::Parser.new 
+    defs1 = <<-EOS
+      a = 5
+      str = "hello"
+    EOS
+    assert parser.definitions.parse(defs1), "assertion 1"
+    defs2 = <<-EOF
+      a = 5
+      pat = maybe many `a-`c
+      # empty line follows:
+
+      str = "hello"
+      # another comment...
+    EOF
+    assert parser.definitions.parse(defs2), "assertion 2"
+  end
+
+  def test_008_capture_var
+    parser = Regexador::Parser.new 
+    str1 = "@myvar"
+    assert parser.capture_var.parse(str1)
+  end
+
+  def test_009_captured_pattern
+    parser = Regexador::Parser.new 
+    prog = "@myvar = maybe 'abc'"
+    assert parser.capture.parse(prog)
+    assert parser.parse("match #{prog} end")
+  end
+
+  def test_010_back_ref
+    parser = Regexador::Parser.new 
+    prog = '@myvar'
+    parser.capture.parse(prog)
+    assert parser.parse("match #{prog} end")
+  end
+
+  def test_011_one_line_match_clause
+    parser = Regexador::Parser.new 
+    mc1 = "match `a~`x end"
+    assert parser.match_clause.parse(mc1)
+  end
+
+  def test_012_multiline_match_clause
+    parser = Regexador::Parser.new 
+    mc2 = <<-EOF
+      match 
+        `< "tag" WB 
+        any ~`>
+        # blah blah blah
+        "</" "tag" `> 
+      end
+    EOF
+    assert parser.multiline_clause.parse(mc2)
+  end
+
+  def test_013_oneline_program
+    parser = Regexador::Parser.new 
+    prog = "match `a-`f end"
+    assert parser.parse_with_debug(prog)
+  end
+
+  def test_014_multiline_program
+    parser = Regexador::Parser.new 
+    prog1 = <<-EOF
+      dot = "."
+      num = "25" D5 | `2 D4 D | maybe D1 1,2*D
+      match WB num dot num dot num dot num WB end
+    EOF
+    assert parser.program.parse(prog1)
+
+    prog2 = <<-EOF
+      # Warning: This one likely has errors!
+  
+      visa     = `4 12*D maybe 3*D
+      mc       = `5 D5 14*D
+      amex     = `3 '47' 13*D
+      diners   = `3 (`0 D5 | '68' D) 11*D
+      discover = `6 ("011" | `5 2*D) 12*D
+      jcb      = ("2131"|"1800"|"35" 3*D) 11*D
+  
+      match visa | mc | amex | diners | discover | jcb end
+    EOF
+    assert parser.program.parse(prog2)
+  end
+
+  def test_015_neg_lookbehind
+    parser = Regexador::Parser.new 
+    prog = ' match without "USD" find 3*D end'
+
+    assert parser.program.parse(prog)
+    rx = Regexador.new(prog)
+    assert rx.regexp == /(?<!USD)(\d){3}/
+  end
+
+  def test_010_neg_lookahead
+  end
+
+  def test_010_
+  end
+
+  def test_010_
+  end
+
+  def test_010_
+  end
+
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: regexador
 version: !ruby/object:Gem::Version
-  version: 0.4.5
+  version: 0.4.6
 platform: ruby
 authors:
 - Hal Fulton
@@ -9,7 +9,7 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2019-11-30 00:00:00.000000000 Z
+date: 2019-12-29 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: parslet
@@ -56,11 +56,11 @@ dependencies:
 description: "This is implemented as an \"external DSL\" in Ruby; that is (like SQL
   for example), \na \"program\" in a Ruby string is passed into some kind of parser/interpreter
   method.\nIn this case, it is possible to use the result \"as is\" or to convert
-  to an ordinary \nRuby regular expression.\n\nThough this mini-language was conceived
-  and implemented \"for Ruby, using Ruby,\" \nin principle there is no reason it might
-  not also be implemented in other languages\nsuch as Python or Perl.\n\nDevelopment
-  on this project began in mid-July 2013. As such, it is still an immature\nproject.
-  Syntax and semantics may change. Feel free to offer comments or suggestions.\n"
+  to an ordinary \nRuby regular expression.\n\nThis project was originally implemented
+  \"for Ruby, using Ruby.\" Tentative efforts\nare being made for ports to Elixir
+  and Python.\n\nDevelopment on this project resumed in 2019 after being untouched
+  since 2015. As such, \nit is not 100% mature. Syntax and semantics may change. Feel
+  free to offer comments \nor suggestions.\n"
 email:
 - rubyhacker@gmail.com
 executables: []
@@ -74,13 +74,23 @@ files:
 - lib/regexador.rb
 - lib/regexador_parser.rb
 - lib/regexador_xform.rb
+- spec/GENERATED_spec.rb
+- spec/captures.yaml
+- spec/old_mkcode.rb
+- spec/oneliners.yaml
 - spec/parsing_spec.rb
+- spec/programs.yaml
 - spec/programs_spec.rb
+- spec/regexador_spec.rb
 - spec/testing.rb
+- test/captures.yaml
+- test/mkcode.rb
+- test/oneliners.yaml
+- test/programs.yaml
 - test/test.rb
 homepage: http://github.com/hal9000/regexador
 licenses:
-- The Ruby License
+- Ruby
 metadata: {}
 post_install_message: 
 rdoc_options: []
@@ -97,13 +107,22 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubyforge_project: 
-rubygems_version: 2.2.2
+rubygems_version: 3.0.4
 signing_key: 
 specification_version: 4
 summary: A mini-language to make regular expressions more readable.
 test_files:
+- test/captures.yaml
+- test/mkcode.rb
+- test/oneliners.yaml
+- test/programs.yaml
 - test/test.rb
-- spec/testing.rb
+- spec/GENERATED_spec.rb
+- spec/captures.yaml
+- spec/old_mkcode.rb
+- spec/oneliners.yaml
 - spec/parsing_spec.rb
+- spec/programs.yaml
 - spec/programs_spec.rb
+- spec/regexador_spec.rb
+- spec/testing.rb