about summary refs log tree commit diff stats
path: root/016dilated_reagent.cc
blob: 1354ba458b2a4dab6be637bbc324f11f9c053694 (plain) (blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
pre { line-height: 125%; }
td.linenos .normal { color: inherit; background-color: transparent; padding-left: 5px; padding-right: 5px; }
span.linenos { color: inherit; background-color: transparent; padding-left: 5px; padding-right: 5px; }
td.linenos .special { color: #000000; background-color: #ffffc0; padding-left: 5px; padding-right: 5px; }
span.linenos.special { color: #000000; background-color: #ffffc0; padding-left: 5px; padding-right: 5px; }
.highlight .hll { background-color: #ffffcc }
.highlight .c { color: #888888 } /* Comment */
.highlight .err { color: #a61717; background-color: #e3d2d2 } /* Error */
.highlight .k { color: #008800; font-weight: bold } /* Keyword */
.highlight .ch { color: #888888 } /* Comment.Hashbang */
.highlight .cm { color: #888888 } /* Comment.Multiline */
.highlight .cp { color: #cc0000; font-weight: bold } /* Comment.Preproc */
.highlight .cpf { color: #888888 } /* Comment.PreprocFile */
.highlight .c1 { color: #888888 } /* Comment.Single */
.highlight .cs { color: #cc0000; font-weight: bold; background-color: #fff0f0 } /* Comment.Special */
.highlight .gd { color: #000000; background-color: #ffdddd } /* Generic.Deleted */
.highlight .ge { font-style: italic } /* Generic.Emph */
.highlight .ges { font-weight: bold; font-style: italic } /* Generic.EmphStrong */
.highlight .gr { color: #aa0000 } /* Generic.Error */
.highlight .gh { color: #333333 } /* Generic.Heading */
.highlight .gi { color: #000000; background-color: #ddffdd } /* Generic.Inserted */
.highlight .go { color: #888888 } /* Generic.Output */
.highlight .gp { color: #555555 } /* Generic.Prompt */
.highlight .gs { font-weight: bold } /* Generic.Strong */
.highlight .gu { color: #666666 } /* Generic.Subheading */
.highlight .gt { color: #aa0000 } /* Generic.Traceback */
.highlight .kc { color: #008800; font-weight: bold } /* Keyword.Constant */
.highlight .kd { color: #008800; font-weight: bold } /* Keyword.Declaration */
.highlight .kn { color: #008800; font-weight: bold } /* Keyword.Namespace */
.highlight .kp { color: #008800 } /* Keyword.Pseudo */
.highlight .kr { color: #008800; font-weight: bold } /* Keyword.Reserved */
.highlight .kt { color: #888888; font-weight: bold } /* Keyword.Type */
.highlight .m { color: #0000DD; font-weight: bold } /* Literal.Number */
.highlight .s { color: #dd2200; background-color: #fff0f0 } /* Literal.String */
.highlight .na { color: #336699 } /* Name.Attribute */
.highlight .nb { color: #003388 } /* Name.Builtin */
.highlight .nc { color: #bb0066; font-weight: bold } /* Name.Class */
.highlight .no { color: #003366; font-weight: bold } /* Name.Constant */
.highlight .nd { color: #555555 } /* Name.Decorator */
.highlight .ne { color: #bb0066; font-weight: bold } /* Name.Exception */
.highlight .nf { color: #0066bb; font-weight: bold } /* Name.Function */
.highlight .nl { color: #336699; font-style: italic } /* Name.Label */
.highlight .nn { color: #bb0066; font-weight: bold } /* Name.Namespace */
.highlight .py { color: #336699; font-weight: bold } /* Name.Property */
.highlight .nt { color: #bb0066; font-weight: bold } /* Name.Tag */
.highlight .nv { color: #336699 } /* Name.Variable */
.highlight .ow { color: #008800 } /* Operator.Word */
.highlight .w { color: #bbbbbb } /* Text.Whitespace */
.highlight .mb { color: #0000DD; font-weight: bold } /* Literal.Number.Bin */
.highlight .mf { color: #0000DD; font-weight: bold } /* Literal.Number.Float */
.highlight .mh { color: #0000DD; font-weight: bold } /* Literal.Number.Hex */
.highlight .mi { color: #0000DD; font-weight: bold } /* Literal.Number.Integer */
.highlight .mo { color: #0000DD; font-weight: bold } /* Literal.Number.Oct */
.highlight .sa { color: #dd2200; background-color: #fff0f0 } /* Literal.String.Affix */
.highlight .sb { color: #dd2200; background-color: #fff0f0 } /* Literal.String.Backtick */
.highlight .sc { color: #dd2200; background-color: #fff0f0 } /* Literal.String.Char */
.highlight .dl { color: #dd2200; background-color: #fff0f0 } /* Literal.String.Delimiter */
.highlight .sd { color: #dd2200; background-color: #fff0f0 } /* Literal.String.Doc */
.highlight .s2 { color: #dd2200; background-color: #fff0f0 } /* Literal.String.Double */
.highlight .se { color: #0044dd; background-color: #fff0f0 } /* Literal.String.Escape */
.highlight .sh { color: #dd2200; background-color: #fff0f0 } /* Literal.String.Heredoc */
.highlight .si { color: #3333bb; background-color: #fff0f0 } /* Literal.String.Inter
//: An alternative syntax for reagents that permits whitespace in properties,
//: grouped by brackets. We'll use this ability in the next layer, when we
//: generalize types from lists to trees of properties.

void test_dilated_reagent() {
  load(
      "def main [\n"
      "  {1: number, foo: bar} <- copy 34\n"
      "]\n"
  );
  CHECK_TRACE_CONTENTS(
      "parse:   product: {1: \"number\", \"foo\": \"bar\"}\n"
  );
}

void test_load_trailing_space_after_curly_bracket() {
  load(
      "def main [\n"
      "  # line below has a space at the end\n"
      "  { \n"
      "]\n"
      "# successfully parsed\n"
  );
}

void test_dilated_reagent_with_comment() {
  load(
      "def main [\n"
      "  {1: number, foo: bar} <- copy 34  # test comment\n"
      "]\n"
  );
  CHECK_TRACE_CONTENTS(
      "parse:   product: {1: \"number\", \"foo\": \"bar\"}\n"
  );
  CHECK_TRACE_COUNT("error", 0);
}

void test_dilated_reagent_with_comment_immediately_following() {
  load(
      "def main [\n"
      "  1:number <- copy {34: literal}  # test comment\n"
      "]\n"
  );
  CHECK_TRACE_COUNT("error", 0);
}

//: First augment next_word to group balanced brackets together.

:(before "End next_word Special-cases")
if (in.peek() == '(')
  return slurp_balanced_bracket(in);
// treat curlies mostly like parens, but don't mess up labels
if (start_of_dilated_reagent(in))
  return slurp_balanced_bracket(in);

:(code)
// A curly is considered a label if it's the last thing on a line. Dilated
// reagents should remain all on one line.
bool start_of_dilated_reagent(istream& in) {
  if (in.peek() != '{') return false;
  int pos = in.tellg();
  in.get();  // slurp '{'
  skip_whitespace_but_not_newline(in);
  char next = in.peek();
  in.seekg(pos);
  return next != '\n';
}

// Assume the first letter is an open bracket, and read everything until the
// matching close bracket.
// We balance {} () and [].
string slurp_balanced_bracket(istream& in) {
  ostringstream result;
  char c;
  list<char> open_brackets;
  while (in >> c) {
    if (c == '(') open_brackets.push_back(c);
    if (c == ')') {
      if (open_brackets.empty() || open_brackets.back() != '(') {
        raise << "unbalanced ')'\n" << end();
        continue;
      }
      assert(open_brackets.back() == '(');
      open_brackets.pop_back();
    }
    if (c == '[') open_brackets.push_back(c);
    if (c == ']') {
      if (open_brackets.empty() || open_brackets.back() != '[') {
        raise << "unbalanced ']'\n" << end();
        continue;
      }
      open_brackets.pop_back();
    }
    if (c == '{') open_brackets.push_back(c);
    if (c == '}') {
      if (open_brackets.empty() || open_brackets.back() != '{') {
        raise << "unbalanced '}'\n" << end();
        continue;
      }
      open_brackets.pop_back();
    }
    result << c;
    if (open_brackets.empty()) break;
  }
  skip_whitespace_and_comments_but_not_newline(in);
  return result.str();
}

:(after "Parsing reagent(string s)")
if (starts_with(s, "{")) {
  assert(properties.empty());
  istringstream in(s);
  in >> std::noskipws;
  in.get();  // skip '{'
  name = slurp_key(in);
  if (name.empty()) {
    raise << "invalid reagent '" << s << "' without a name\n" << end();
    return;
  }
  if (name == "}") {
    raise << "invalid empty reagent '" << s << "'\n" << end();
    return;
  }
  {
    string s = next_word(in);
    if (s.empty()) {
      assert(!has_data(in));
      raise << "incomplete dilated reagent at end of file (0)\n" << end();
      return;
    }
    string_tree* type_names = new string_tree(s);
    // End Parsing Dilated Reagent Type Property(type_names)
    type = new_type_tree(type_names);
    delete type_names;
  }
  while (has_data(in)) {
    string key = slurp_key(in);
    if (key.empty()) continue;
    if (key == "}") continue;
    string s = next_word(in);
    if (s.empty()) {
      assert(!has_data(in));
      raise << "incomplete dilated reagent at end of file (1)\n" << end();
      return;
    }
    string_tree* value = new string_tree(s);
    // End Parsing Dilated Reagent Property(value)
    properties.push_back(pair<string, string_tree*>(key, value));
  }
  return;
}

:(code)
string slurp_key(istream& in) {
  string result = next_word(in);
  if (result.empty()) {
    assert(!has_data(in));
    raise << "incomplete dilated reagent at end of file (2)\n" << end();
    return result;
  }
  while (!result.empty() && *result.rbegin() == ':')
    strip_last(result);
  while (isspace(in.peek()) || in.peek() == ':')
    in.get();
  return result;
}