Practical example 2 WIP

1 files changed, 107 insertions, 0 deletions

diff --git a/spec/practical_spec.cr b/spec/practical_spec.cr
index 9dc8ed5..f992a15 100644
--- a/spec/practical_spec.cr
+++ b/spec/practical_spec.cr
@@ -37,3 +37,110 @@ describe "Text surrounded by whitespace" do
   end
 end
 
+enum BFOpType
+  BFAdd
+  BFShift
+  BFByteIn
+  BFByteOut
+  BFLoopStart
+  BFLoopEnd
+end
+
+alias BFOp = {
+  type: BFOpType,
+  amount: Int32,
+}
+
+describe "brainfuck parser" do
+  # From https://esolangs.org/wiki/Brainfuck#Examples
+  hello_world_str = "1 +++++ +++               Set Cell #0 to 8
+ 2 [
+ 3     >++++               Add 4 to Cell #1; this will always set Cell #1 to 4
+ 4     [                   as the cell will be cleared by the loop
+ 5         >++             Add 4*2 to Cell #2
+ 6         >+++            Add 4*3 to Cell #3
+ 7         >+++            Add 4*3 to Cell #4
+ 8         >+              Add 4 to Cell #5
+ 9         <<<<-           Decrement the loop counter in Cell #1
+10     ]                   Loop till Cell #1 is zero
+11     >+                  Add 1 to Cell #2
+12     >+                  Add 1 to Cell #3
+13     >-                  Subtract 1 from Cell #4
+14     >>+                 Add 1 to Cell #6
+15     [<]                 Move back to the first zero cell you find; this will
+16                         be Cell #1 which was cleared by the previous loop
+17     <-                  Decrement the loop Counter in Cell #0
+18 ]                       Loop till Cell #0 is zero
+19 
+20 The result of this is:
+21 Cell No :   0   1   2   3   4   5   6
+22 Contents:   0   0  72 104  88  32   8
+23 Pointer :   ^
+24 
+25 >>.                     Cell #2 has value 72 which is 'H'
+26 >---.                   Subtract 3 from Cell #3 to get 101 which is 'e'
+27 +++++ ++..+++.          Likewise for 'llo' from Cell #3
+28 >>.                     Cell #5 is 32 for the space
+29 <-.                     Subtract 1 from Cell #4 for 87 to give a 'W'
+30 <.                      Cell #3 was set to 'o' from the end of 'Hello'
+31 +++.----- -.----- ---.  Cell #3 for 'rl' and 'd'
+32 >>+.                    Add 1 to Cell #5 gives us an exclamation point
+33 >++.                    And finally a newline from Cell #6"
+
+  bf_chars = Set{'+', '-', '.', ',', '<', '>', '[', ']'}
+  other = Parser(Char, Char).satisfy { |c| !bf_chars.includes?(c) }
+  bf_char = Parser(Char, Char).satisfy { |c| bf_chars.includes?(c) }
+
+  char_body = bf_char.some.sep_by(other.some).map(&.flatten)
+  just_bf_chars = other.many >> char_body << other.many
+
+  loop_start = Parser(Char, Char).token('[').map do |_|
+    {type: BFOpType::BFLoopStart, amount: 0}
+  end
+
+  loop_end = Parser(Char, Char).token(']').map do |_|
+    {type: BFOpType::BFLoopEnd, amount: 0}
+  end
+
+  read_block = Parser(Char, Char).token(',').some.map do |cs|
+    {type: BFOpType::BFByteIn, amount: cs.size}
+  end
+
+  write_block = Parser(Char, Char).token('.').some.map do |cs|
+    {type: BFOpType::BFByteOut, amount: cs.size}
+  end
+
+  shift_block = (Parser.token('<') | Parser.token('>')).some.map do |cs|
+    left_count = cs.count { |c| c == '<' }
+    right_count = cs.size - left_count
+    {type: BFOpType::BFShift, amount: right_count - left_count}
+  end
+
+  add_block = (Parser.token('+') | Parser.token('-')).some.map do |cs|
+    minus_count = cs.count { |c| c == '-' }
+    plus_count = cs.size - minus_count
+    {type: BFOpType::BFAdd, amount: plus_count - minus_count}
+  end
+
+  bf_token = Parser.first_of([
+    loop_start,
+    loop_end,
+    read_block,
+    write_block,
+    shift_block,
+    add_block,
+  ])
+
+  tokenizer = Parser(Char, Array(BFOp)).new("BF tokenizer") do |tokens|
+    result = just_bf_chars.parse(tokens)
+    puts result
+    chars = Tokens.new(result.value)
+    bf_token.some.parse(chars)
+  end
+
+  tokens = Tokens.from_string(hello_world_str)
+  result = tokenizer.parse(tokens)
+  puts result
+  # TODO: find a good way to verify this result
+end
+