src/Pure/Isar/outer_syntax.scala
author wenzelm
Wed, 05 Nov 2014 21:59:21 +0100
changeset 58907 0ee3563803c9
parent 58901 47809a811eba
child 58938 0c45680b7d9d
permissions -rw-r--r--
more uniform header_keywords in ML/Scala; tuned signature;
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
34166
446a33b874b3 renamed class Outer_Keyword to Outer_Syntax;
wenzelm
parents:
diff changeset
     1
/*  Title:      Pure/Isar/outer_syntax.scala
446a33b874b3 renamed class Outer_Keyword to Outer_Syntax;
wenzelm
parents:
diff changeset
     2
    Author:     Makarius
446a33b874b3 renamed class Outer_Keyword to Outer_Syntax;
wenzelm
parents:
diff changeset
     3
446a33b874b3 renamed class Outer_Keyword to Outer_Syntax;
wenzelm
parents:
diff changeset
     4
Isabelle/Isar outer syntax.
446a33b874b3 renamed class Outer_Keyword to Outer_Syntax;
wenzelm
parents:
diff changeset
     5
*/
446a33b874b3 renamed class Outer_Keyword to Outer_Syntax;
wenzelm
parents:
diff changeset
     6
446a33b874b3 renamed class Outer_Keyword to Outer_Syntax;
wenzelm
parents:
diff changeset
     7
package isabelle
446a33b874b3 renamed class Outer_Keyword to Outer_Syntax;
wenzelm
parents:
diff changeset
     8
446a33b874b3 renamed class Outer_Keyword to Outer_Syntax;
wenzelm
parents:
diff changeset
     9
446a33b874b3 renamed class Outer_Keyword to Outer_Syntax;
wenzelm
parents:
diff changeset
    10
import scala.util.parsing.input.{Reader, CharSequenceReader}
43411
0206466ee473 some support for partial scans with explicit context;
wenzelm
parents: 40533
diff changeset
    11
import scala.collection.mutable
58706
70a947611792 tuned signature and modules;
wenzelm
parents: 58703
diff changeset
    12
import scala.annotation.tailrec
34166
446a33b874b3 renamed class Outer_Keyword to Outer_Syntax;
wenzelm
parents:
diff changeset
    13
446a33b874b3 renamed class Outer_Keyword to Outer_Syntax;
wenzelm
parents:
diff changeset
    14
43774
6dfdb70496fe added Outer_Syntax.quote_string, which is conceptually a bit different from Token.unparse;
wenzelm
parents: 43695
diff changeset
    15
object Outer_Syntax
6dfdb70496fe added Outer_Syntax.quote_string, which is conceptually a bit different from Token.unparse;
wenzelm
parents: 43695
diff changeset
    16
{
58706
70a947611792 tuned signature and modules;
wenzelm
parents: 58703
diff changeset
    17
  /* syntax */
70a947611792 tuned signature and modules;
wenzelm
parents: 58703
diff changeset
    18
70a947611792 tuned signature and modules;
wenzelm
parents: 58703
diff changeset
    19
  val empty: Outer_Syntax = new Outer_Syntax()
70a947611792 tuned signature and modules;
wenzelm
parents: 58703
diff changeset
    20
70a947611792 tuned signature and modules;
wenzelm
parents: 58703
diff changeset
    21
  def init(): Outer_Syntax = new Outer_Syntax(completion = Completion.init())
70a947611792 tuned signature and modules;
wenzelm
parents: 58703
diff changeset
    22
70a947611792 tuned signature and modules;
wenzelm
parents: 58703
diff changeset
    23
70a947611792 tuned signature and modules;
wenzelm
parents: 58703
diff changeset
    24
  /* string literals */
70a947611792 tuned signature and modules;
wenzelm
parents: 58703
diff changeset
    25
43774
6dfdb70496fe added Outer_Syntax.quote_string, which is conceptually a bit different from Token.unparse;
wenzelm
parents: 43695
diff changeset
    26
  def quote_string(str: String): String =
6dfdb70496fe added Outer_Syntax.quote_string, which is conceptually a bit different from Token.unparse;
wenzelm
parents: 43695
diff changeset
    27
  {
6dfdb70496fe added Outer_Syntax.quote_string, which is conceptually a bit different from Token.unparse;
wenzelm
parents: 43695
diff changeset
    28
    val result = new StringBuilder(str.length + 10)
6dfdb70496fe added Outer_Syntax.quote_string, which is conceptually a bit different from Token.unparse;
wenzelm
parents: 43695
diff changeset
    29
    result += '"'
6dfdb70496fe added Outer_Syntax.quote_string, which is conceptually a bit different from Token.unparse;
wenzelm
parents: 43695
diff changeset
    30
    for (s <- Symbol.iterator(str)) {
6dfdb70496fe added Outer_Syntax.quote_string, which is conceptually a bit different from Token.unparse;
wenzelm
parents: 43695
diff changeset
    31
      if (s.length == 1) {
6dfdb70496fe added Outer_Syntax.quote_string, which is conceptually a bit different from Token.unparse;
wenzelm
parents: 43695
diff changeset
    32
        val c = s(0)
6dfdb70496fe added Outer_Syntax.quote_string, which is conceptually a bit different from Token.unparse;
wenzelm
parents: 43695
diff changeset
    33
        if (c < 32 && c != YXML.X && c != YXML.Y || c == '\\' || c == '"') {
6dfdb70496fe added Outer_Syntax.quote_string, which is conceptually a bit different from Token.unparse;
wenzelm
parents: 43695
diff changeset
    34
          result += '\\'
6dfdb70496fe added Outer_Syntax.quote_string, which is conceptually a bit different from Token.unparse;
wenzelm
parents: 43695
diff changeset
    35
          if (c < 10) result += '0'
6dfdb70496fe added Outer_Syntax.quote_string, which is conceptually a bit different from Token.unparse;
wenzelm
parents: 43695
diff changeset
    36
          if (c < 100) result += '0'
6dfdb70496fe added Outer_Syntax.quote_string, which is conceptually a bit different from Token.unparse;
wenzelm
parents: 43695
diff changeset
    37
          result ++= (c.asInstanceOf[Int].toString)
6dfdb70496fe added Outer_Syntax.quote_string, which is conceptually a bit different from Token.unparse;
wenzelm
parents: 43695
diff changeset
    38
        }
6dfdb70496fe added Outer_Syntax.quote_string, which is conceptually a bit different from Token.unparse;
wenzelm
parents: 43695
diff changeset
    39
        else result += c
6dfdb70496fe added Outer_Syntax.quote_string, which is conceptually a bit different from Token.unparse;
wenzelm
parents: 43695
diff changeset
    40
      }
6dfdb70496fe added Outer_Syntax.quote_string, which is conceptually a bit different from Token.unparse;
wenzelm
parents: 43695
diff changeset
    41
      else result ++= s
6dfdb70496fe added Outer_Syntax.quote_string, which is conceptually a bit different from Token.unparse;
wenzelm
parents: 43695
diff changeset
    42
    }
6dfdb70496fe added Outer_Syntax.quote_string, which is conceptually a bit different from Token.unparse;
wenzelm
parents: 43695
diff changeset
    43
    result += '"'
6dfdb70496fe added Outer_Syntax.quote_string, which is conceptually a bit different from Token.unparse;
wenzelm
parents: 43695
diff changeset
    44
    result.toString
6dfdb70496fe added Outer_Syntax.quote_string, which is conceptually a bit different from Token.unparse;
wenzelm
parents: 43695
diff changeset
    45
  }
46626
a02115865bcc streamlined abstract datatype;
wenzelm
parents: 46624
diff changeset
    46
58696
6b7445774ce3 more explicit Line_Nesting;
wenzelm
parents: 58695
diff changeset
    47
58697
5bc1d6c4a499 tuned signature;
wenzelm
parents: 58696
diff changeset
    48
  /* line-oriented structure */
58696
6b7445774ce3 more explicit Line_Nesting;
wenzelm
parents: 58695
diff changeset
    49
58697
5bc1d6c4a499 tuned signature;
wenzelm
parents: 58696
diff changeset
    50
  object Line_Structure
58696
6b7445774ce3 more explicit Line_Nesting;
wenzelm
parents: 58695
diff changeset
    51
  {
58700
4717d18cc619 clarified Line_Structure wrt. command span;
wenzelm
parents: 58697
diff changeset
    52
    val init = Line_Structure()
58696
6b7445774ce3 more explicit Line_Nesting;
wenzelm
parents: 58695
diff changeset
    53
  }
6b7445774ce3 more explicit Line_Nesting;
wenzelm
parents: 58695
diff changeset
    54
58700
4717d18cc619 clarified Line_Structure wrt. command span;
wenzelm
parents: 58697
diff changeset
    55
  sealed case class Line_Structure(
4717d18cc619 clarified Line_Structure wrt. command span;
wenzelm
parents: 58697
diff changeset
    56
    improper: Boolean = true,
4717d18cc619 clarified Line_Structure wrt. command span;
wenzelm
parents: 58697
diff changeset
    57
    command: Boolean = false,
4717d18cc619 clarified Line_Structure wrt. command span;
wenzelm
parents: 58697
diff changeset
    58
    depth: Int = 0,
4717d18cc619 clarified Line_Structure wrt. command span;
wenzelm
parents: 58697
diff changeset
    59
    span_depth: Int = 0,
4717d18cc619 clarified Line_Structure wrt. command span;
wenzelm
parents: 58697
diff changeset
    60
    after_span_depth: Int = 0)
58706
70a947611792 tuned signature and modules;
wenzelm
parents: 58703
diff changeset
    61
70a947611792 tuned signature and modules;
wenzelm
parents: 58703
diff changeset
    62
70a947611792 tuned signature and modules;
wenzelm
parents: 58703
diff changeset
    63
  /* overall document structure */
70a947611792 tuned signature and modules;
wenzelm
parents: 58703
diff changeset
    64
70a947611792 tuned signature and modules;
wenzelm
parents: 58703
diff changeset
    65
  sealed abstract class Document { def length: Int }
58747
c680f181b32e tuned rendering;
wenzelm
parents: 58743
diff changeset
    66
  case class Document_Block(name: String, text: String, body: List[Document]) extends Document
58706
70a947611792 tuned signature and modules;
wenzelm
parents: 58703
diff changeset
    67
  {
70a947611792 tuned signature and modules;
wenzelm
parents: 58703
diff changeset
    68
    val length: Int = (0 /: body)(_ + _.length)
70a947611792 tuned signature and modules;
wenzelm
parents: 58703
diff changeset
    69
  }
58747
c680f181b32e tuned rendering;
wenzelm
parents: 58743
diff changeset
    70
  case class Document_Atom(command: Command) extends Document
58706
70a947611792 tuned signature and modules;
wenzelm
parents: 58703
diff changeset
    71
  {
70a947611792 tuned signature and modules;
wenzelm
parents: 58703
diff changeset
    72
    def length: Int = command.length
70a947611792 tuned signature and modules;
wenzelm
parents: 58703
diff changeset
    73
  }
43774
6dfdb70496fe added Outer_Syntax.quote_string, which is conceptually a bit different from Token.unparse;
wenzelm
parents: 43695
diff changeset
    74
}
6dfdb70496fe added Outer_Syntax.quote_string, which is conceptually a bit different from Token.unparse;
wenzelm
parents: 43695
diff changeset
    75
46712
8650d9a95736 prefer final ADTs -- prevent ooddities;
wenzelm
parents: 46626
diff changeset
    76
final class Outer_Syntax private(
58900
1435cc20b022 explicit type Keyword.Keywords;
wenzelm
parents: 58899
diff changeset
    77
  val keywords: Keyword.Keywords = Keyword.Keywords.empty,
53280
c63a016805b9 explicit indication of outer syntax with no tokens;
wenzelm
parents: 52439
diff changeset
    78
  val completion: Completion = Completion.empty,
55749
75a48dc4383e tuned signature;
wenzelm
parents: 55666
diff changeset
    79
  val language_context: Completion.Language_Context = Completion.Language_Context.outer,
56393
22f533e6a049 more abstract Prover.Syntax, as proposed by Carst Tankink;
wenzelm
parents: 56314
diff changeset
    80
  val has_tokens: Boolean = true) extends Prover.Syntax
34166
446a33b874b3 renamed class Outer_Keyword to Outer_Syntax;
wenzelm
parents:
diff changeset
    81
{
58706
70a947611792 tuned signature and modules;
wenzelm
parents: 58703
diff changeset
    82
  /** syntax content **/
70a947611792 tuned signature and modules;
wenzelm
parents: 58703
diff changeset
    83
58900
1435cc20b022 explicit type Keyword.Keywords;
wenzelm
parents: 58899
diff changeset
    84
  override def toString: String = keywords.toString
56393
22f533e6a049 more abstract Prover.Syntax, as proposed by Carst Tankink;
wenzelm
parents: 56314
diff changeset
    85
58695
91839729224e tuned comments;
wenzelm
parents: 58694
diff changeset
    86
91839729224e tuned comments;
wenzelm
parents: 58694
diff changeset
    87
  /* add keywords */
91839729224e tuned comments;
wenzelm
parents: 58694
diff changeset
    88
58907
0ee3563803c9 more uniform header_keywords in ML/Scala;
wenzelm
parents: 58901
diff changeset
    89
  def + (name: String): Outer_Syntax = this + (name, None, None)
0ee3563803c9 more uniform header_keywords in ML/Scala;
wenzelm
parents: 58901
diff changeset
    90
  def + (name: String, kind: String): Outer_Syntax = this + (name, Some((kind, Nil)), None)
58901
47809a811eba clarified representation of type Keywords;
wenzelm
parents: 58900
diff changeset
    91
  def + (name: String, opt_kind: Option[(String, List[String])], replace: Option[String])
47809a811eba clarified representation of type Keywords;
wenzelm
parents: 58900
diff changeset
    92
    : Outer_Syntax =
53280
c63a016805b9 explicit indication of outer syntax with no tokens;
wenzelm
parents: 52439
diff changeset
    93
  {
58901
47809a811eba clarified representation of type Keywords;
wenzelm
parents: 58900
diff changeset
    94
    val keywords1 =
47809a811eba clarified representation of type Keywords;
wenzelm
parents: 58900
diff changeset
    95
      opt_kind match {
47809a811eba clarified representation of type Keywords;
wenzelm
parents: 58900
diff changeset
    96
        case None => keywords + name
47809a811eba clarified representation of type Keywords;
wenzelm
parents: 58900
diff changeset
    97
        case Some(kind) => keywords + (name, kind)
47809a811eba clarified representation of type Keywords;
wenzelm
parents: 58900
diff changeset
    98
      }
53280
c63a016805b9 explicit indication of outer syntax with no tokens;
wenzelm
parents: 52439
diff changeset
    99
    val completion1 =
58853
f8715e7c1be6 discontinued obsolete control command category;
wenzelm
parents: 58753
diff changeset
   100
      if (replace == Some("")) completion
53280
c63a016805b9 explicit indication of outer syntax with no tokens;
wenzelm
parents: 52439
diff changeset
   101
      else completion + (name, replace getOrElse name)
58900
1435cc20b022 explicit type Keyword.Keywords;
wenzelm
parents: 58899
diff changeset
   102
    new Outer_Syntax(keywords1, completion1, language_context, true)
53280
c63a016805b9 explicit indication of outer syntax with no tokens;
wenzelm
parents: 52439
diff changeset
   103
  }
48706
e2b512024eab tuned signature;
wenzelm
parents: 48671
diff changeset
   104
48873
18b17f15bc62 more direct cumulation of (sparse) keywords;
wenzelm
parents: 48872
diff changeset
   105
  def add_keywords(keywords: Thy_Header.Keywords): Outer_Syntax =
18b17f15bc62 more direct cumulation of (sparse) keywords;
wenzelm
parents: 48872
diff changeset
   106
    (this /: keywords) {
58901
47809a811eba clarified representation of type Keywords;
wenzelm
parents: 58900
diff changeset
   107
      case (syntax, (name, opt_spec, replace)) =>
47809a811eba clarified representation of type Keywords;
wenzelm
parents: 58900
diff changeset
   108
        val opt_kind = opt_spec.map(_._1)
50128
599c935aac82 alternative completion for outer syntax keywords;
wenzelm
parents: 48885
diff changeset
   109
        syntax +
58901
47809a811eba clarified representation of type Keywords;
wenzelm
parents: 58900
diff changeset
   110
          (Symbol.decode(name), opt_kind, replace) +
47809a811eba clarified representation of type Keywords;
wenzelm
parents: 58900
diff changeset
   111
          (Symbol.encode(name), opt_kind, replace)
46940
a40be2f10ca9 explicit Outer_Syntax.Decl;
wenzelm
parents: 46712
diff changeset
   112
    }
34166
446a33b874b3 renamed class Outer_Keyword to Outer_Syntax;
wenzelm
parents:
diff changeset
   113
58695
91839729224e tuned comments;
wenzelm
parents: 58694
diff changeset
   114
58900
1435cc20b022 explicit type Keyword.Keywords;
wenzelm
parents: 58899
diff changeset
   115
  /* load commands */
1435cc20b022 explicit type Keyword.Keywords;
wenzelm
parents: 58899
diff changeset
   116
1435cc20b022 explicit type Keyword.Keywords;
wenzelm
parents: 58899
diff changeset
   117
  def load_command(name: String): Option[List[String]] = keywords.load_command(name)
1435cc20b022 explicit type Keyword.Keywords;
wenzelm
parents: 58899
diff changeset
   118
  def load_commands_in(text: String): Boolean = keywords.load_commands_in(text)
1435cc20b022 explicit type Keyword.Keywords;
wenzelm
parents: 58899
diff changeset
   119
1435cc20b022 explicit type Keyword.Keywords;
wenzelm
parents: 58899
diff changeset
   120
58706
70a947611792 tuned signature and modules;
wenzelm
parents: 58703
diff changeset
   121
  /* language context */
34166
446a33b874b3 renamed class Outer_Keyword to Outer_Syntax;
wenzelm
parents:
diff changeset
   122
58706
70a947611792 tuned signature and modules;
wenzelm
parents: 58703
diff changeset
   123
  def set_language_context(context: Completion.Language_Context): Outer_Syntax =
58900
1435cc20b022 explicit type Keyword.Keywords;
wenzelm
parents: 58899
diff changeset
   124
    new Outer_Syntax(keywords, completion, context, has_tokens)
58706
70a947611792 tuned signature and modules;
wenzelm
parents: 58703
diff changeset
   125
70a947611792 tuned signature and modules;
wenzelm
parents: 58703
diff changeset
   126
  def no_tokens: Outer_Syntax =
46969
481b7d9ad6fe more abstract heading level;
wenzelm
parents: 46941
diff changeset
   127
  {
58900
1435cc20b022 explicit type Keyword.Keywords;
wenzelm
parents: 58899
diff changeset
   128
    require(keywords.is_empty)
58706
70a947611792 tuned signature and modules;
wenzelm
parents: 58703
diff changeset
   129
    new Outer_Syntax(
70a947611792 tuned signature and modules;
wenzelm
parents: 58703
diff changeset
   130
      completion = completion,
70a947611792 tuned signature and modules;
wenzelm
parents: 58703
diff changeset
   131
      language_context = language_context,
70a947611792 tuned signature and modules;
wenzelm
parents: 58703
diff changeset
   132
      has_tokens = false)
46969
481b7d9ad6fe more abstract heading level;
wenzelm
parents: 46941
diff changeset
   133
  }
40454
2516ea25a54b some support for nested source structure, based on section headings;
wenzelm
parents: 38471
diff changeset
   134
58706
70a947611792 tuned signature and modules;
wenzelm
parents: 58703
diff changeset
   135
40454
2516ea25a54b some support for nested source structure, based on section headings;
wenzelm
parents: 38471
diff changeset
   136
58706
70a947611792 tuned signature and modules;
wenzelm
parents: 58703
diff changeset
   137
  /** parsing **/
34166
446a33b874b3 renamed class Outer_Keyword to Outer_Syntax;
wenzelm
parents:
diff changeset
   138
58697
5bc1d6c4a499 tuned signature;
wenzelm
parents: 58696
diff changeset
   139
  /* line-oriented structure */
58696
6b7445774ce3 more explicit Line_Nesting;
wenzelm
parents: 58695
diff changeset
   140
58700
4717d18cc619 clarified Line_Structure wrt. command span;
wenzelm
parents: 58697
diff changeset
   141
  def line_structure(tokens: List[Token], struct: Outer_Syntax.Line_Structure)
4717d18cc619 clarified Line_Structure wrt. command span;
wenzelm
parents: 58697
diff changeset
   142
    : Outer_Syntax.Line_Structure =
58696
6b7445774ce3 more explicit Line_Nesting;
wenzelm
parents: 58695
diff changeset
   143
  {
58700
4717d18cc619 clarified Line_Structure wrt. command span;
wenzelm
parents: 58697
diff changeset
   144
    val improper1 = tokens.forall(_.is_improper)
4717d18cc619 clarified Line_Structure wrt. command span;
wenzelm
parents: 58697
diff changeset
   145
    val command1 = tokens.exists(_.is_command)
4717d18cc619 clarified Line_Structure wrt. command span;
wenzelm
parents: 58697
diff changeset
   146
58696
6b7445774ce3 more explicit Line_Nesting;
wenzelm
parents: 58695
diff changeset
   147
    val depth1 =
58901
47809a811eba clarified representation of type Keywords;
wenzelm
parents: 58900
diff changeset
   148
      if (tokens.exists(tok => keywords.is_command_kind(tok, Keyword.theory))) 0
58700
4717d18cc619 clarified Line_Structure wrt. command span;
wenzelm
parents: 58697
diff changeset
   149
      else if (command1) struct.after_span_depth
4717d18cc619 clarified Line_Structure wrt. command span;
wenzelm
parents: 58697
diff changeset
   150
      else struct.span_depth
4717d18cc619 clarified Line_Structure wrt. command span;
wenzelm
parents: 58697
diff changeset
   151
4717d18cc619 clarified Line_Structure wrt. command span;
wenzelm
parents: 58697
diff changeset
   152
    val (span_depth1, after_span_depth1) =
4717d18cc619 clarified Line_Structure wrt. command span;
wenzelm
parents: 58697
diff changeset
   153
      ((struct.span_depth, struct.after_span_depth) /: tokens) {
58703
883efcc7a50d more folds;
wenzelm
parents: 58700
diff changeset
   154
        case ((x, y), tok) =>
883efcc7a50d more folds;
wenzelm
parents: 58700
diff changeset
   155
          if (tok.is_command) {
58901
47809a811eba clarified representation of type Keywords;
wenzelm
parents: 58900
diff changeset
   156
            if (keywords.is_command_kind(tok, Keyword.theory_goal))
58900
1435cc20b022 explicit type Keyword.Keywords;
wenzelm
parents: 58899
diff changeset
   157
              (2, 1)
58901
47809a811eba clarified representation of type Keywords;
wenzelm
parents: 58900
diff changeset
   158
            else if (keywords.is_command_kind(tok, Keyword.theory))
58900
1435cc20b022 explicit type Keyword.Keywords;
wenzelm
parents: 58899
diff changeset
   159
              (1, 0)
58901
47809a811eba clarified representation of type Keywords;
wenzelm
parents: 58900
diff changeset
   160
            else if (keywords.is_command_kind(tok, Keyword.proof_goal) || tok.is_begin_block)
58900
1435cc20b022 explicit type Keyword.Keywords;
wenzelm
parents: 58899
diff changeset
   161
              (y + 2, y + 1)
58901
47809a811eba clarified representation of type Keywords;
wenzelm
parents: 58900
diff changeset
   162
            else if (keywords.is_command_kind(tok, Keyword.qed) || tok.is_end_block)
58900
1435cc20b022 explicit type Keyword.Keywords;
wenzelm
parents: 58899
diff changeset
   163
              (y + 1, y - 1)
58901
47809a811eba clarified representation of type Keywords;
wenzelm
parents: 58900
diff changeset
   164
            else if (keywords.is_command_kind(tok, Keyword.qed_global))
58900
1435cc20b022 explicit type Keyword.Keywords;
wenzelm
parents: 58899
diff changeset
   165
              (1, 0)
58703
883efcc7a50d more folds;
wenzelm
parents: 58700
diff changeset
   166
            else (x, y)
883efcc7a50d more folds;
wenzelm
parents: 58700
diff changeset
   167
          }
883efcc7a50d more folds;
wenzelm
parents: 58700
diff changeset
   168
          else (x, y)
58696
6b7445774ce3 more explicit Line_Nesting;
wenzelm
parents: 58695
diff changeset
   169
      }
58700
4717d18cc619 clarified Line_Structure wrt. command span;
wenzelm
parents: 58697
diff changeset
   170
4717d18cc619 clarified Line_Structure wrt. command span;
wenzelm
parents: 58697
diff changeset
   171
    Outer_Syntax.Line_Structure(improper1, command1, depth1, span_depth1, after_span_depth1)
58696
6b7445774ce3 more explicit Line_Nesting;
wenzelm
parents: 58695
diff changeset
   172
  }
6b7445774ce3 more explicit Line_Nesting;
wenzelm
parents: 58695
diff changeset
   173
6b7445774ce3 more explicit Line_Nesting;
wenzelm
parents: 58695
diff changeset
   174
53280
c63a016805b9 explicit indication of outer syntax with no tokens;
wenzelm
parents: 52439
diff changeset
   175
  /* token language */
c63a016805b9 explicit indication of outer syntax with no tokens;
wenzelm
parents: 52439
diff changeset
   176
57907
7fc36b4c7cce tuned signature;
wenzelm
parents: 57906
diff changeset
   177
  def scan(input: CharSequence): List[Token] =
52066
83b7b88770c9 discontinued odd workaround for scala-2.9.2, which is hopefully obsolete in scala-2.10.x;
wenzelm
parents: 50428
diff changeset
   178
  {
58503
wenzelm
parents: 57911
diff changeset
   179
    val in: Reader[Char] = new CharSequenceReader(input)
58900
1435cc20b022 explicit type Keyword.Keywords;
wenzelm
parents: 58899
diff changeset
   180
    Token.Parsers.parseAll(Token.Parsers.rep(Token.Parsers.token(keywords)), in) match {
55494
009b71c1ed23 tuned signature (in accordance to ML version);
wenzelm
parents: 55492
diff changeset
   181
      case Token.Parsers.Success(tokens, _) => tokens
57907
7fc36b4c7cce tuned signature;
wenzelm
parents: 57906
diff changeset
   182
      case _ => error("Unexpected failure of tokenizing input:\n" + input.toString)
34166
446a33b874b3 renamed class Outer_Keyword to Outer_Syntax;
wenzelm
parents:
diff changeset
   183
    }
52066
83b7b88770c9 discontinued odd workaround for scala-2.9.2, which is hopefully obsolete in scala-2.10.x;
wenzelm
parents: 50428
diff changeset
   184
  }
34166
446a33b874b3 renamed class Outer_Keyword to Outer_Syntax;
wenzelm
parents:
diff changeset
   185
58748
8f92f17d8781 support for structure matching;
wenzelm
parents: 58747
diff changeset
   186
  def scan_line(input: CharSequence, context: Scan.Line_Context): (List[Token], Scan.Line_Context) =
52066
83b7b88770c9 discontinued odd workaround for scala-2.9.2, which is hopefully obsolete in scala-2.10.x;
wenzelm
parents: 50428
diff changeset
   187
  {
83b7b88770c9 discontinued odd workaround for scala-2.9.2, which is hopefully obsolete in scala-2.10.x;
wenzelm
parents: 50428
diff changeset
   188
    var in: Reader[Char] = new CharSequenceReader(input)
83b7b88770c9 discontinued odd workaround for scala-2.9.2, which is hopefully obsolete in scala-2.10.x;
wenzelm
parents: 50428
diff changeset
   189
    val toks = new mutable.ListBuffer[Token]
83b7b88770c9 discontinued odd workaround for scala-2.9.2, which is hopefully obsolete in scala-2.10.x;
wenzelm
parents: 50428
diff changeset
   190
    var ctxt = context
83b7b88770c9 discontinued odd workaround for scala-2.9.2, which is hopefully obsolete in scala-2.10.x;
wenzelm
parents: 50428
diff changeset
   191
    while (!in.atEnd) {
58900
1435cc20b022 explicit type Keyword.Keywords;
wenzelm
parents: 58899
diff changeset
   192
      Token.Parsers.parse(Token.Parsers.token_line(keywords, ctxt), in) match {
55494
009b71c1ed23 tuned signature (in accordance to ML version);
wenzelm
parents: 55492
diff changeset
   193
        case Token.Parsers.Success((x, c), rest) => { toks += x; ctxt = c; in = rest }
009b71c1ed23 tuned signature (in accordance to ML version);
wenzelm
parents: 55492
diff changeset
   194
        case Token.Parsers.NoSuccess(_, rest) =>
52066
83b7b88770c9 discontinued odd workaround for scala-2.9.2, which is hopefully obsolete in scala-2.10.x;
wenzelm
parents: 50428
diff changeset
   195
          error("Unexpected failure of tokenizing input:\n" + rest.source.toString)
43411
0206466ee473 some support for partial scans with explicit context;
wenzelm
parents: 40533
diff changeset
   196
      }
0206466ee473 some support for partial scans with explicit context;
wenzelm
parents: 40533
diff changeset
   197
    }
58748
8f92f17d8781 support for structure matching;
wenzelm
parents: 58747
diff changeset
   198
    (toks.toList, ctxt)
52066
83b7b88770c9 discontinued odd workaround for scala-2.9.2, which is hopefully obsolete in scala-2.10.x;
wenzelm
parents: 50428
diff changeset
   199
  }
55616
25a7a998852a default completion context via outer syntax;
wenzelm
parents: 55510
diff changeset
   200
25a7a998852a default completion context via outer syntax;
wenzelm
parents: 55510
diff changeset
   201
58706
70a947611792 tuned signature and modules;
wenzelm
parents: 58703
diff changeset
   202
  /* command spans */
57905
c0c5652e796e separate module Command_Span: mostly syntactic representation;
wenzelm
parents: 57901
diff changeset
   203
c0c5652e796e separate module Command_Span: mostly syntactic representation;
wenzelm
parents: 57901
diff changeset
   204
  def parse_spans(toks: List[Token]): List[Command_Span.Span] =
c0c5652e796e separate module Command_Span: mostly syntactic representation;
wenzelm
parents: 57901
diff changeset
   205
  {
c0c5652e796e separate module Command_Span: mostly syntactic representation;
wenzelm
parents: 57901
diff changeset
   206
    val result = new mutable.ListBuffer[Command_Span.Span]
c0c5652e796e separate module Command_Span: mostly syntactic representation;
wenzelm
parents: 57901
diff changeset
   207
    val content = new mutable.ListBuffer[Token]
c0c5652e796e separate module Command_Span: mostly syntactic representation;
wenzelm
parents: 57901
diff changeset
   208
    val improper = new mutable.ListBuffer[Token]
c0c5652e796e separate module Command_Span: mostly syntactic representation;
wenzelm
parents: 57901
diff changeset
   209
c0c5652e796e separate module Command_Span: mostly syntactic representation;
wenzelm
parents: 57901
diff changeset
   210
    def ship(span: List[Token])
c0c5652e796e separate module Command_Span: mostly syntactic representation;
wenzelm
parents: 57901
diff changeset
   211
    {
c0c5652e796e separate module Command_Span: mostly syntactic representation;
wenzelm
parents: 57901
diff changeset
   212
      val kind =
57910
a50837b637dc maintain Command_Range position as in ML;
wenzelm
parents: 57907
diff changeset
   213
        if (!span.isEmpty && span.head.is_command && !span.exists(_.is_error)) {
a50837b637dc maintain Command_Range position as in ML;
wenzelm
parents: 57907
diff changeset
   214
          val name = span.head.source
57911
dcb758188aa6 clarified Position.Identified: do not require range from prover, default to command position;
wenzelm
parents: 57910
diff changeset
   215
          val pos = Position.Range(Text.Range(0, Symbol.iterator(name).length) + 1)
57910
a50837b637dc maintain Command_Range position as in ML;
wenzelm
parents: 57907
diff changeset
   216
          Command_Span.Command_Span(name, pos)
a50837b637dc maintain Command_Range position as in ML;
wenzelm
parents: 57907
diff changeset
   217
        }
57905
c0c5652e796e separate module Command_Span: mostly syntactic representation;
wenzelm
parents: 57901
diff changeset
   218
        else if (span.forall(_.is_improper)) Command_Span.Ignored_Span
c0c5652e796e separate module Command_Span: mostly syntactic representation;
wenzelm
parents: 57901
diff changeset
   219
        else Command_Span.Malformed_Span
c0c5652e796e separate module Command_Span: mostly syntactic representation;
wenzelm
parents: 57901
diff changeset
   220
      result += Command_Span.Span(kind, span)
c0c5652e796e separate module Command_Span: mostly syntactic representation;
wenzelm
parents: 57901
diff changeset
   221
    }
c0c5652e796e separate module Command_Span: mostly syntactic representation;
wenzelm
parents: 57901
diff changeset
   222
c0c5652e796e separate module Command_Span: mostly syntactic representation;
wenzelm
parents: 57901
diff changeset
   223
    def flush()
c0c5652e796e separate module Command_Span: mostly syntactic representation;
wenzelm
parents: 57901
diff changeset
   224
    {
c0c5652e796e separate module Command_Span: mostly syntactic representation;
wenzelm
parents: 57901
diff changeset
   225
      if (!content.isEmpty) { ship(content.toList); content.clear }
c0c5652e796e separate module Command_Span: mostly syntactic representation;
wenzelm
parents: 57901
diff changeset
   226
      if (!improper.isEmpty) { ship(improper.toList); improper.clear }
c0c5652e796e separate module Command_Span: mostly syntactic representation;
wenzelm
parents: 57901
diff changeset
   227
    }
c0c5652e796e separate module Command_Span: mostly syntactic representation;
wenzelm
parents: 57901
diff changeset
   228
c0c5652e796e separate module Command_Span: mostly syntactic representation;
wenzelm
parents: 57901
diff changeset
   229
    for (tok <- toks) {
c0c5652e796e separate module Command_Span: mostly syntactic representation;
wenzelm
parents: 57901
diff changeset
   230
      if (tok.is_command) { flush(); content += tok }
c0c5652e796e separate module Command_Span: mostly syntactic representation;
wenzelm
parents: 57901
diff changeset
   231
      else if (tok.is_improper) improper += tok
c0c5652e796e separate module Command_Span: mostly syntactic representation;
wenzelm
parents: 57901
diff changeset
   232
      else { content ++= improper; improper.clear; content += tok }
c0c5652e796e separate module Command_Span: mostly syntactic representation;
wenzelm
parents: 57901
diff changeset
   233
    }
c0c5652e796e separate module Command_Span: mostly syntactic representation;
wenzelm
parents: 57901
diff changeset
   234
    flush()
c0c5652e796e separate module Command_Span: mostly syntactic representation;
wenzelm
parents: 57901
diff changeset
   235
c0c5652e796e separate module Command_Span: mostly syntactic representation;
wenzelm
parents: 57901
diff changeset
   236
    result.toList
c0c5652e796e separate module Command_Span: mostly syntactic representation;
wenzelm
parents: 57901
diff changeset
   237
  }
c0c5652e796e separate module Command_Span: mostly syntactic representation;
wenzelm
parents: 57901
diff changeset
   238
57906
020df63dd0a9 tuned signature;
wenzelm
parents: 57905
diff changeset
   239
  def parse_spans(input: CharSequence): List[Command_Span.Span] =
020df63dd0a9 tuned signature;
wenzelm
parents: 57905
diff changeset
   240
    parse_spans(scan(input))
020df63dd0a9 tuned signature;
wenzelm
parents: 57905
diff changeset
   241
57905
c0c5652e796e separate module Command_Span: mostly syntactic representation;
wenzelm
parents: 57901
diff changeset
   242
58706
70a947611792 tuned signature and modules;
wenzelm
parents: 58703
diff changeset
   243
  /* overall document structure */
55616
25a7a998852a default completion context via outer syntax;
wenzelm
parents: 55510
diff changeset
   244
58706
70a947611792 tuned signature and modules;
wenzelm
parents: 58703
diff changeset
   245
  def heading_level(command: Command): Option[Int] =
70a947611792 tuned signature and modules;
wenzelm
parents: 58703
diff changeset
   246
  {
58868
c5e1cce7ace3 uniform heading commands work in any context, even in theory header;
wenzelm
parents: 58853
diff changeset
   247
    command.name match {
c5e1cce7ace3 uniform heading commands work in any context, even in theory header;
wenzelm
parents: 58853
diff changeset
   248
      case "chapter" => Some(0)
c5e1cce7ace3 uniform heading commands work in any context, even in theory header;
wenzelm
parents: 58853
diff changeset
   249
      case "section" | "header" => Some(1)
c5e1cce7ace3 uniform heading commands work in any context, even in theory header;
wenzelm
parents: 58853
diff changeset
   250
      case "subsection" => Some(2)
c5e1cce7ace3 uniform heading commands work in any context, even in theory header;
wenzelm
parents: 58853
diff changeset
   251
      case "subsubsection" => Some(3)
c5e1cce7ace3 uniform heading commands work in any context, even in theory header;
wenzelm
parents: 58853
diff changeset
   252
      case _ =>
58901
47809a811eba clarified representation of type Keywords;
wenzelm
parents: 58900
diff changeset
   253
        keywords.command_kind(command.name) match {
58868
c5e1cce7ace3 uniform heading commands work in any context, even in theory header;
wenzelm
parents: 58853
diff changeset
   254
          case Some(kind) if Keyword.theory(kind) => Some(4)
c5e1cce7ace3 uniform heading commands work in any context, even in theory header;
wenzelm
parents: 58853
diff changeset
   255
          case _ => None
c5e1cce7ace3 uniform heading commands work in any context, even in theory header;
wenzelm
parents: 58853
diff changeset
   256
        }
58706
70a947611792 tuned signature and modules;
wenzelm
parents: 58703
diff changeset
   257
    }
70a947611792 tuned signature and modules;
wenzelm
parents: 58703
diff changeset
   258
  }
70a947611792 tuned signature and modules;
wenzelm
parents: 58703
diff changeset
   259
58743
c07a59140fee clarified tree root;
wenzelm
parents: 58706
diff changeset
   260
  def parse_document(node_name: Document.Node.Name, text: CharSequence):
c07a59140fee clarified tree root;
wenzelm
parents: 58706
diff changeset
   261
    List[Outer_Syntax.Document] =
58706
70a947611792 tuned signature and modules;
wenzelm
parents: 58703
diff changeset
   262
  {
70a947611792 tuned signature and modules;
wenzelm
parents: 58703
diff changeset
   263
    /* stack operations */
70a947611792 tuned signature and modules;
wenzelm
parents: 58703
diff changeset
   264
70a947611792 tuned signature and modules;
wenzelm
parents: 58703
diff changeset
   265
    def buffer(): mutable.ListBuffer[Outer_Syntax.Document] =
70a947611792 tuned signature and modules;
wenzelm
parents: 58703
diff changeset
   266
      new mutable.ListBuffer[Outer_Syntax.Document]
70a947611792 tuned signature and modules;
wenzelm
parents: 58703
diff changeset
   267
58747
c680f181b32e tuned rendering;
wenzelm
parents: 58743
diff changeset
   268
    var stack: List[(Int, Command, mutable.ListBuffer[Outer_Syntax.Document])] =
c680f181b32e tuned rendering;
wenzelm
parents: 58743
diff changeset
   269
      List((0, Command.empty, buffer()))
55616
25a7a998852a default completion context via outer syntax;
wenzelm
parents: 55510
diff changeset
   270
58706
70a947611792 tuned signature and modules;
wenzelm
parents: 58703
diff changeset
   271
    @tailrec def close(level: Int => Boolean)
70a947611792 tuned signature and modules;
wenzelm
parents: 58703
diff changeset
   272
    {
70a947611792 tuned signature and modules;
wenzelm
parents: 58703
diff changeset
   273
      stack match {
58747
c680f181b32e tuned rendering;
wenzelm
parents: 58743
diff changeset
   274
        case (lev, command, body) :: (_, _, body2) :: rest if level(lev) =>
c680f181b32e tuned rendering;
wenzelm
parents: 58743
diff changeset
   275
          body2 += Outer_Syntax.Document_Block(command.name, command.source, body.toList)
58706
70a947611792 tuned signature and modules;
wenzelm
parents: 58703
diff changeset
   276
          stack = stack.tail
70a947611792 tuned signature and modules;
wenzelm
parents: 58703
diff changeset
   277
          close(level)
70a947611792 tuned signature and modules;
wenzelm
parents: 58703
diff changeset
   278
        case _ =>
70a947611792 tuned signature and modules;
wenzelm
parents: 58703
diff changeset
   279
      }
70a947611792 tuned signature and modules;
wenzelm
parents: 58703
diff changeset
   280
    }
70a947611792 tuned signature and modules;
wenzelm
parents: 58703
diff changeset
   281
58743
c07a59140fee clarified tree root;
wenzelm
parents: 58706
diff changeset
   282
    def result(): List[Outer_Syntax.Document] =
58706
70a947611792 tuned signature and modules;
wenzelm
parents: 58703
diff changeset
   283
    {
70a947611792 tuned signature and modules;
wenzelm
parents: 58703
diff changeset
   284
      close(_ => true)
58743
c07a59140fee clarified tree root;
wenzelm
parents: 58706
diff changeset
   285
      stack.head._3.toList
58706
70a947611792 tuned signature and modules;
wenzelm
parents: 58703
diff changeset
   286
    }
70a947611792 tuned signature and modules;
wenzelm
parents: 58703
diff changeset
   287
70a947611792 tuned signature and modules;
wenzelm
parents: 58703
diff changeset
   288
    def add(command: Command)
70a947611792 tuned signature and modules;
wenzelm
parents: 58703
diff changeset
   289
    {
70a947611792 tuned signature and modules;
wenzelm
parents: 58703
diff changeset
   290
      heading_level(command) match {
70a947611792 tuned signature and modules;
wenzelm
parents: 58703
diff changeset
   291
        case Some(i) =>
70a947611792 tuned signature and modules;
wenzelm
parents: 58703
diff changeset
   292
          close(_ > i)
58747
c680f181b32e tuned rendering;
wenzelm
parents: 58743
diff changeset
   293
          stack = (i + 1, command, buffer()) :: stack
58706
70a947611792 tuned signature and modules;
wenzelm
parents: 58703
diff changeset
   294
        case None =>
70a947611792 tuned signature and modules;
wenzelm
parents: 58703
diff changeset
   295
      }
70a947611792 tuned signature and modules;
wenzelm
parents: 58703
diff changeset
   296
      stack.head._3 += Outer_Syntax.Document_Atom(command)
70a947611792 tuned signature and modules;
wenzelm
parents: 58703
diff changeset
   297
    }
70a947611792 tuned signature and modules;
wenzelm
parents: 58703
diff changeset
   298
70a947611792 tuned signature and modules;
wenzelm
parents: 58703
diff changeset
   299
70a947611792 tuned signature and modules;
wenzelm
parents: 58703
diff changeset
   300
    /* result structure */
70a947611792 tuned signature and modules;
wenzelm
parents: 58703
diff changeset
   301
70a947611792 tuned signature and modules;
wenzelm
parents: 58703
diff changeset
   302
    val spans = parse_spans(text)
70a947611792 tuned signature and modules;
wenzelm
parents: 58703
diff changeset
   303
    spans.foreach(span => add(Command(Document_ID.none, node_name, Nil, span)))
70a947611792 tuned signature and modules;
wenzelm
parents: 58703
diff changeset
   304
    result()
55616
25a7a998852a default completion context via outer syntax;
wenzelm
parents: 55510
diff changeset
   305
  }
34166
446a33b874b3 renamed class Outer_Keyword to Outer_Syntax;
wenzelm
parents:
diff changeset
   306
}