src/Pure/General/symbol.ML
author wenzelm
Thu, 09 Feb 2017 15:40:34 +0100
changeset 65009 eda9366bbfac
parent 64275 ac2abc987cf9
child 66020 a31760eee09d
permissions -rw-r--r--
remote database access via ssh port forwarding;
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
6118
caa439435666 fixed titles;
wenzelm
parents: 6116
diff changeset
     1
(*  Title:      Pure/General/symbol.ML
63936
b87784e19a77 discontinued raw symbols;
wenzelm
parents: 62877
diff changeset
     2
    Author:     Makarius
6116
8ba2f25610f7 files scan.ML, source.ML, symbol.ML, pretty.ML moved to Pure/General;
wenzelm
parents:
diff changeset
     3
21897
d0c67d715deb fixed typo in comment
paulson
parents: 21858
diff changeset
     4
Generalized characters with infinitely many named symbols.
6116
8ba2f25610f7 files scan.ML, source.ML, symbol.ML, pretty.ML moved to Pure/General;
wenzelm
parents:
diff changeset
     5
*)
8ba2f25610f7 files scan.ML, source.ML, symbol.ML, pretty.ML moved to Pure/General;
wenzelm
parents:
diff changeset
     6
8ba2f25610f7 files scan.ML, source.ML, symbol.ML, pretty.ML moved to Pure/General;
wenzelm
parents:
diff changeset
     7
signature SYMBOL =
8ba2f25610f7 files scan.ML, source.ML, symbol.ML, pretty.ML moved to Pure/General;
wenzelm
parents:
diff changeset
     8
sig
40509
0bc83ae22789 tuned signatures;
wenzelm
parents: 40131
diff changeset
     9
  type symbol = string
63936
b87784e19a77 discontinued raw symbols;
wenzelm
parents: 62877
diff changeset
    10
  val explode: string -> symbol list
61865
6dcc9e4f1aa6 tuned signature;
wenzelm
parents: 61707
diff changeset
    11
  val spaces: int -> string
26524
63953bec4c98 added some ASCII control symbols;
wenzelm
parents: 25644
diff changeset
    12
  val STX: symbol
63953bec4c98 added some ASCII control symbols;
wenzelm
parents: 25644
diff changeset
    13
  val DEL: symbol
62210
e068ea693678 tuned signature (according to Scala version);
wenzelm
parents: 61865
diff changeset
    14
  val open_: symbol
e068ea693678 tuned signature (according to Scala version);
wenzelm
parents: 61865
diff changeset
    15
  val close: symbol
6116
8ba2f25610f7 files scan.ML, source.ML, symbol.ML, pretty.ML moved to Pure/General;
wenzelm
parents:
diff changeset
    16
  val space: symbol
62804
7b9c5416f30e tuned signature;
wenzelm
parents: 62529
diff changeset
    17
  val is_space: symbol -> bool
61579
634cd44bb1d3 symbolic syntax "\<comment> text";
wenzelm
parents: 61475
diff changeset
    18
  val comment: symbol
14678
662b181cae05 clarification of ascii vs. symbolic entities;
wenzelm
parents: 14632
diff changeset
    19
  val is_char: symbol -> bool
37533
d775bd70f571 explicit treatment of UTF8 character sequences as Isabelle symbols;
wenzelm
parents: 34095
diff changeset
    20
  val is_utf8: symbol -> bool
14678
662b181cae05 clarification of ascii vs. symbolic entities;
wenzelm
parents: 14632
diff changeset
    21
  val is_symbolic: symbol -> bool
55033
8e8243975860 support for nested text cartouches;
wenzelm
parents: 54734
diff changeset
    22
  val is_symbolic_char: symbol -> bool
14678
662b181cae05 clarification of ascii vs. symbolic entities;
wenzelm
parents: 14632
diff changeset
    23
  val is_printable: symbol -> bool
61470
c42960228a81 clarified Symbol.is_control;
wenzelm
parents: 61435
diff changeset
    24
  val is_control: symbol -> bool
6116
8ba2f25610f7 files scan.ML, source.ML, symbol.ML, pretty.ML moved to Pure/General;
wenzelm
parents:
diff changeset
    25
  val eof: symbol
8ba2f25610f7 files scan.ML, source.ML, symbol.ML, pretty.ML moved to Pure/General;
wenzelm
parents:
diff changeset
    26
  val is_eof: symbol -> bool
27766
1ae745357856 export not_eof;
wenzelm
parents: 27745
diff changeset
    27
  val not_eof: symbol -> bool
27732
8dbf5761a24a abstract type Scan.stopper;
wenzelm
parents: 26632
diff changeset
    28
  val stopper: symbol Scan.stopper
40523
1050315f6ee2 simplified/robustified treatment of malformed symbols, which are now fully internalized (total Symbol.explode etc.);
wenzelm
parents: 40509
diff changeset
    29
  val is_malformed: symbol -> bool
1050315f6ee2 simplified/robustified treatment of malformed symbols, which are now fully internalized (total Symbol.explode etc.);
wenzelm
parents: 40509
diff changeset
    30
  val malformed_msg: symbol -> string
6116
8ba2f25610f7 files scan.ML, source.ML, symbol.ML, pretty.ML moved to Pure/General;
wenzelm
parents:
diff changeset
    31
  val is_ascii: symbol -> bool
14678
662b181cae05 clarification of ascii vs. symbolic entities;
wenzelm
parents: 14632
diff changeset
    32
  val is_ascii_letter: symbol -> bool
662b181cae05 clarification of ascii vs. symbolic entities;
wenzelm
parents: 14632
diff changeset
    33
  val is_ascii_digit: symbol -> bool
24580
916259859344 replaced Symbol.is_hex_letter to Symbol.is_ascii_hex;
wenzelm
parents: 23784
diff changeset
    34
  val is_ascii_hex: symbol -> bool
14678
662b181cae05 clarification of ascii vs. symbolic entities;
wenzelm
parents: 14632
diff changeset
    35
  val is_ascii_quasi: symbol -> bool
662b181cae05 clarification of ascii vs. symbolic entities;
wenzelm
parents: 14632
diff changeset
    36
  val is_ascii_blank: symbol -> bool
34095
c2f176a38448 robust representation of low ASCII control characters within XML/YXML text;
wenzelm
parents: 33955
diff changeset
    37
  val is_ascii_control: symbol -> bool
50236
476a3350589c clarified Symbol.scan_ascii_id;
wenzelm
parents: 50235
diff changeset
    38
  val is_ascii_letdig: symbol -> bool
20200
c6fb50dbbc30 added is/to_ascii_lower/upper;
wenzelm
parents: 20192
diff changeset
    39
  val is_ascii_lower: symbol -> bool
c6fb50dbbc30 added is/to_ascii_lower/upper;
wenzelm
parents: 20192
diff changeset
    40
  val is_ascii_upper: symbol -> bool
c6fb50dbbc30 added is/to_ascii_lower/upper;
wenzelm
parents: 20192
diff changeset
    41
  val to_ascii_lower: symbol -> symbol
c6fb50dbbc30 added is/to_ascii_lower/upper;
wenzelm
parents: 20192
diff changeset
    42
  val to_ascii_upper: symbol -> symbol
50238
98d35a7368bd more uniform Symbol.is_ascii_identifier in ML/Scala;
wenzelm
parents: 50237
diff changeset
    43
  val is_ascii_identifier: string -> bool
50236
476a3350589c clarified Symbol.scan_ascii_id;
wenzelm
parents: 50235
diff changeset
    44
  val scan_ascii_id: string list -> string * string list
40523
1050315f6ee2 simplified/robustified treatment of malformed symbols, which are now fully internalized (total Symbol.explode etc.);
wenzelm
parents: 40509
diff changeset
    45
  datatype sym =
63936
b87784e19a77 discontinued raw symbols;
wenzelm
parents: 62877
diff changeset
    46
    Char of string | UTF8 of string | Sym of string | Control of string | Malformed of string | EOF
14873
7efc14398e82 added datatype sym, val decode: symbol -> sym;
wenzelm
parents: 14834
diff changeset
    47
  val decode: symbol -> sym
14678
662b181cae05 clarification of ascii vs. symbolic entities;
wenzelm
parents: 14632
diff changeset
    48
  datatype kind = Letter | Digit | Quasi | Blank | Other
662b181cae05 clarification of ascii vs. symbolic entities;
wenzelm
parents: 14632
diff changeset
    49
  val kind: symbol -> kind
6116
8ba2f25610f7 files scan.ML, source.ML, symbol.ML, pretty.ML moved to Pure/General;
wenzelm
parents:
diff changeset
    50
  val is_letter: symbol -> bool
8ba2f25610f7 files scan.ML, source.ML, symbol.ML, pretty.ML moved to Pure/General;
wenzelm
parents:
diff changeset
    51
  val is_digit: symbol -> bool
12904
c208d71702d1 added is_quasi;
wenzelm
parents: 12116
diff changeset
    52
  val is_quasi: symbol -> bool
14678
662b181cae05 clarification of ascii vs. symbolic entities;
wenzelm
parents: 14632
diff changeset
    53
  val is_blank: symbol -> bool
47850
c638127b4653 avoid interference of markup for literal tokens, which may contain slightly odd \<^bsub> \<^esub> counted as pseudo-markup (especially relevant for HTML output, e.g. of thm power3_eq_cube);
wenzelm
parents: 43947
diff changeset
    54
  val is_block_ctrl: symbol -> bool
6116
8ba2f25610f7 files scan.ML, source.ML, symbol.ML, pretty.ML moved to Pure/General;
wenzelm
parents:
diff changeset
    55
  val is_quasi_letter: symbol -> bool
8ba2f25610f7 files scan.ML, source.ML, symbol.ML, pretty.ML moved to Pure/General;
wenzelm
parents:
diff changeset
    56
  val is_letdig: symbol -> bool
14728
wenzelm
parents: 14678
diff changeset
    57
  val beginning: int -> symbol list -> string
50237
wenzelm
parents: 50236
diff changeset
    58
  val esc: symbol -> string
wenzelm
parents: 50236
diff changeset
    59
  val escape: string -> string
wenzelm
parents: 50236
diff changeset
    60
  val scanner: string -> (string list -> 'a * string list) -> symbol list -> 'a
50162
e06eabc421e7 some support for breakable text and paragraphs;
wenzelm
parents: 48774
diff changeset
    61
  val split_words: symbol list -> string list
e06eabc421e7 some support for breakable text and paragraphs;
wenzelm
parents: 48774
diff changeset
    62
  val explode_words: string -> string list
61435
636bb75e7683 tuned signature (cf. XML.trim_blanks);
wenzelm
parents: 58864
diff changeset
    63
  val trim_blanks: string -> string
14678
662b181cae05 clarification of ascii vs. symbolic entities;
wenzelm
parents: 14632
diff changeset
    64
  val bump_init: string -> string
12904
c208d71702d1 added is_quasi;
wenzelm
parents: 12116
diff changeset
    65
  val bump_string: string -> string
14678
662b181cae05 clarification of ascii vs. symbolic entities;
wenzelm
parents: 14632
diff changeset
    66
  val length: symbol list -> int
6692
05c56f41e661 avoid string constants;
wenzelm
parents: 6640
diff changeset
    67
  val xsymbolsN: string
40131
7cbebd636e79 explicitly qualify type Output.output, which is a slightly odd internal feature;
wenzelm
parents: 37728
diff changeset
    68
  val output: string -> Output.output * int
6116
8ba2f25610f7 files scan.ML, source.ML, symbol.ML, pretty.ML moved to Pure/General;
wenzelm
parents:
diff changeset
    69
end;
8ba2f25610f7 files scan.ML, source.ML, symbol.ML, pretty.ML moved to Pure/General;
wenzelm
parents:
diff changeset
    70
8ba2f25610f7 files scan.ML, source.ML, symbol.ML, pretty.ML moved to Pure/General;
wenzelm
parents:
diff changeset
    71
structure Symbol: SYMBOL =
8ba2f25610f7 files scan.ML, source.ML, symbol.ML, pretty.ML moved to Pure/General;
wenzelm
parents:
diff changeset
    72
struct
8ba2f25610f7 files scan.ML, source.ML, symbol.ML, pretty.ML moved to Pure/General;
wenzelm
parents:
diff changeset
    73
14678
662b181cae05 clarification of ascii vs. symbolic entities;
wenzelm
parents: 14632
diff changeset
    74
(** type symbol **)
6272
52d99d68d3be added output_width;
wenzelm
parents: 6225
diff changeset
    75
14678
662b181cae05 clarification of ascii vs. symbolic entities;
wenzelm
parents: 14632
diff changeset
    76
(*Symbols, which are considered the smallest entities of any Isabelle
6272
52d99d68d3be added output_width;
wenzelm
parents: 6225
diff changeset
    77
  string, may be of the following form:
14678
662b181cae05 clarification of ascii vs. symbolic entities;
wenzelm
parents: 14632
diff changeset
    78
63936
b87784e19a77 discontinued raw symbols;
wenzelm
parents: 62877
diff changeset
    79
    (1) ASCII: a
b87784e19a77 discontinued raw symbols;
wenzelm
parents: 62877
diff changeset
    80
    (2) UTF-8: ä
17823
4735c07399c8 raw symbols: allow non-ASCII chars (e.g. UTF-8);
wenzelm
parents: 17756
diff changeset
    81
    (2) regular symbols: \<ident>
14834
e47744683560 improved support for raw symbols;
wenzelm
parents: 14728
diff changeset
    82
    (3) control symbols: \<^ident>
6272
52d99d68d3be added output_width;
wenzelm
parents: 6225
diff changeset
    83
14678
662b181cae05 clarification of ascii vs. symbolic entities;
wenzelm
parents: 14632
diff changeset
    84
  Output is subject to the print_mode variable (default: verbatim),
662b181cae05 clarification of ascii vs. symbolic entities;
wenzelm
parents: 14632
diff changeset
    85
  actual interpretation in display is up to front-end tools.
6272
52d99d68d3be added output_width;
wenzelm
parents: 6225
diff changeset
    86
*)
52d99d68d3be added output_width;
wenzelm
parents: 6225
diff changeset
    87
52d99d68d3be added output_width;
wenzelm
parents: 6225
diff changeset
    88
type symbol = string;
52d99d68d3be added output_width;
wenzelm
parents: 6225
diff changeset
    89
26524
63953bec4c98 added some ASCII control symbols;
wenzelm
parents: 25644
diff changeset
    90
val STX = chr 2;
63953bec4c98 added some ASCII control symbols;
wenzelm
parents: 25644
diff changeset
    91
val DEL = chr 127;
63953bec4c98 added some ASCII control symbols;
wenzelm
parents: 25644
diff changeset
    92
62529
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
    93
val open_ = "\<open>";
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
    94
val close = "\<close>";
62210
e068ea693678 tuned signature (according to Scala version);
wenzelm
parents: 61865
diff changeset
    95
26524
63953bec4c98 added some ASCII control symbols;
wenzelm
parents: 25644
diff changeset
    96
val space = chr 32;
62804
7b9c5416f30e tuned signature;
wenzelm
parents: 62529
diff changeset
    97
fun is_space s = s = space;
17063
502105583951 tuned Symbol.spaces;
wenzelm
parents: 16138
diff changeset
    98
61865
6dcc9e4f1aa6 tuned signature;
wenzelm
parents: 61707
diff changeset
    99
local
6dcc9e4f1aa6 tuned signature;
wenzelm
parents: 61707
diff changeset
   100
  val small_spaces = Vector.tabulate (65, fn i => replicate_string i space);
6dcc9e4f1aa6 tuned signature;
wenzelm
parents: 61707
diff changeset
   101
in
6dcc9e4f1aa6 tuned signature;
wenzelm
parents: 61707
diff changeset
   102
  fun spaces n =
6dcc9e4f1aa6 tuned signature;
wenzelm
parents: 61707
diff changeset
   103
    if n < 64 then Vector.sub (small_spaces, n)
6dcc9e4f1aa6 tuned signature;
wenzelm
parents: 61707
diff changeset
   104
    else
6dcc9e4f1aa6 tuned signature;
wenzelm
parents: 61707
diff changeset
   105
      replicate_string (n div 64) (Vector.sub (small_spaces, 64)) ^
6dcc9e4f1aa6 tuned signature;
wenzelm
parents: 61707
diff changeset
   106
        Vector.sub (small_spaces, n mod 64);
6dcc9e4f1aa6 tuned signature;
wenzelm
parents: 61707
diff changeset
   107
end;
6dcc9e4f1aa6 tuned signature;
wenzelm
parents: 61707
diff changeset
   108
62529
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   109
val comment = "\<comment>";
61579
634cd44bb1d3 symbolic syntax "\<comment> text";
wenzelm
parents: 61475
diff changeset
   110
14678
662b181cae05 clarification of ascii vs. symbolic entities;
wenzelm
parents: 14632
diff changeset
   111
fun is_char s = size s = 1;
662b181cae05 clarification of ascii vs. symbolic entities;
wenzelm
parents: 14632
diff changeset
   112
37533
d775bd70f571 explicit treatment of UTF8 character sequences as Isabelle symbols;
wenzelm
parents: 34095
diff changeset
   113
fun is_utf8 s = size s > 0 andalso forall_string (fn c => ord c >= 128) s;
d775bd70f571 explicit treatment of UTF8 character sequences as Isabelle symbols;
wenzelm
parents: 34095
diff changeset
   114
55033
8e8243975860 support for nested text cartouches;
wenzelm
parents: 54734
diff changeset
   115
fun raw_symbolic s =
62877
741560a5283b avoid malformed Isabelle symbols during bootstrap;
wenzelm
parents: 62804
diff changeset
   116
  String.isPrefix "\092<" s andalso String.isSuffix ">" s andalso not (String.isPrefix "\092<^" s);
55033
8e8243975860 support for nested text cartouches;
wenzelm
parents: 54734
diff changeset
   117
14678
662b181cae05 clarification of ascii vs. symbolic entities;
wenzelm
parents: 14632
diff changeset
   118
fun is_symbolic s =
62210
e068ea693678 tuned signature (according to Scala version);
wenzelm
parents: 61865
diff changeset
   119
  s <> open_ andalso s <> close andalso raw_symbolic s;
55033
8e8243975860 support for nested text cartouches;
wenzelm
parents: 54734
diff changeset
   120
8e8243975860 support for nested text cartouches;
wenzelm
parents: 54734
diff changeset
   121
val is_symbolic_char = member (op =) (raw_explode "!#$%&*+-/<=>?@^_|~");
14678
662b181cae05 clarification of ascii vs. symbolic entities;
wenzelm
parents: 14632
diff changeset
   122
662b181cae05 clarification of ascii vs. symbolic entities;
wenzelm
parents: 14632
diff changeset
   123
fun is_printable s =
64275
ac2abc987cf9 accomodate Poly/ML repository version, which treats singleton strings as boxed;
wenzelm
parents: 63936
diff changeset
   124
  if is_char s then 32 <= ord s andalso ord s <= Char.ord #"~"
55033
8e8243975860 support for nested text cartouches;
wenzelm
parents: 54734
diff changeset
   125
  else is_utf8 s orelse raw_symbolic s;
26632
90c0b075c0d3 added is_utf8_trailer;
wenzelm
parents: 26538
diff changeset
   126
61470
c42960228a81 clarified Symbol.is_control;
wenzelm
parents: 61435
diff changeset
   127
fun is_control s =
62877
741560a5283b avoid malformed Isabelle symbols during bootstrap;
wenzelm
parents: 62804
diff changeset
   128
  String.isPrefix "\092<^" s andalso String.isSuffix ">" s;
61470
c42960228a81 clarified Symbol.is_control;
wenzelm
parents: 61435
diff changeset
   129
6272
52d99d68d3be added output_width;
wenzelm
parents: 6225
diff changeset
   130
14678
662b181cae05 clarification of ascii vs. symbolic entities;
wenzelm
parents: 14632
diff changeset
   131
(* input source control *)
6272
52d99d68d3be added output_width;
wenzelm
parents: 6225
diff changeset
   132
14678
662b181cae05 clarification of ascii vs. symbolic entities;
wenzelm
parents: 14632
diff changeset
   133
val eof = "";
6272
52d99d68d3be added output_width;
wenzelm
parents: 6225
diff changeset
   134
fun is_eof s = s = eof;
52d99d68d3be added output_width;
wenzelm
parents: 6225
diff changeset
   135
fun not_eof s = s <> eof;
27732
8dbf5761a24a abstract type Scan.stopper;
wenzelm
parents: 26632
diff changeset
   136
val stopper = Scan.stopper (K eof) is_eof;
6272
52d99d68d3be added output_width;
wenzelm
parents: 6225
diff changeset
   137
48774
c4bd5bb3ae69 further clarification of malformed symbols;
wenzelm
parents: 48773
diff changeset
   138
fun is_malformed s =
62877
741560a5283b avoid malformed Isabelle symbols during bootstrap;
wenzelm
parents: 62804
diff changeset
   139
  String.isPrefix "\092<" s andalso not (String.isSuffix ">" s)
741560a5283b avoid malformed Isabelle symbols during bootstrap;
wenzelm
parents: 62804
diff changeset
   140
  orelse s = "\092<>" orelse s = "\092<^>";
48774
c4bd5bb3ae69 further clarification of malformed symbols;
wenzelm
parents: 48773
diff changeset
   141
40523
1050315f6ee2 simplified/robustified treatment of malformed symbols, which are now fully internalized (total Symbol.explode etc.);
wenzelm
parents: 40509
diff changeset
   142
fun malformed_msg s = "Malformed symbolic character: " ^ quote s;
14678
662b181cae05 clarification of ascii vs. symbolic entities;
wenzelm
parents: 14632
diff changeset
   143
662b181cae05 clarification of ascii vs. symbolic entities;
wenzelm
parents: 14632
diff changeset
   144
43418
c69e9fbb81a8 recovered markup for non-alphabetic keywords;
wenzelm
parents: 40627
diff changeset
   145
(* ASCII symbols *)
14678
662b181cae05 clarification of ascii vs. symbolic entities;
wenzelm
parents: 14632
diff changeset
   146
662b181cae05 clarification of ascii vs. symbolic entities;
wenzelm
parents: 14632
diff changeset
   147
fun is_ascii s = is_char s andalso ord s < 128;
662b181cae05 clarification of ascii vs. symbolic entities;
wenzelm
parents: 14632
diff changeset
   148
662b181cae05 clarification of ascii vs. symbolic entities;
wenzelm
parents: 14632
diff changeset
   149
fun is_ascii_letter s =
662b181cae05 clarification of ascii vs. symbolic entities;
wenzelm
parents: 14632
diff changeset
   150
  is_char s andalso
64275
ac2abc987cf9 accomodate Poly/ML repository version, which treats singleton strings as boxed;
wenzelm
parents: 63936
diff changeset
   151
   (Char.ord #"A" <= ord s andalso ord s <= Char.ord #"Z" orelse
ac2abc987cf9 accomodate Poly/ML repository version, which treats singleton strings as boxed;
wenzelm
parents: 63936
diff changeset
   152
    Char.ord #"a" <= ord s andalso ord s <= Char.ord #"z");
14678
662b181cae05 clarification of ascii vs. symbolic entities;
wenzelm
parents: 14632
diff changeset
   153
662b181cae05 clarification of ascii vs. symbolic entities;
wenzelm
parents: 14632
diff changeset
   154
fun is_ascii_digit s =
64275
ac2abc987cf9 accomodate Poly/ML repository version, which treats singleton strings as boxed;
wenzelm
parents: 63936
diff changeset
   155
  is_char s andalso Char.ord #"0" <= ord s andalso ord s <= Char.ord #"9";
14678
662b181cae05 clarification of ascii vs. symbolic entities;
wenzelm
parents: 14632
diff changeset
   156
24580
916259859344 replaced Symbol.is_hex_letter to Symbol.is_ascii_hex;
wenzelm
parents: 23784
diff changeset
   157
fun is_ascii_hex s =
916259859344 replaced Symbol.is_hex_letter to Symbol.is_ascii_hex;
wenzelm
parents: 23784
diff changeset
   158
  is_char s andalso
64275
ac2abc987cf9 accomodate Poly/ML repository version, which treats singleton strings as boxed;
wenzelm
parents: 63936
diff changeset
   159
   (Char.ord #"0" <= ord s andalso ord s <= Char.ord #"9" orelse
ac2abc987cf9 accomodate Poly/ML repository version, which treats singleton strings as boxed;
wenzelm
parents: 63936
diff changeset
   160
    Char.ord #"A" <= ord s andalso ord s <= Char.ord #"F" orelse
ac2abc987cf9 accomodate Poly/ML repository version, which treats singleton strings as boxed;
wenzelm
parents: 63936
diff changeset
   161
    Char.ord #"a" <= ord s andalso ord s <= Char.ord #"f");
24580
916259859344 replaced Symbol.is_hex_letter to Symbol.is_ascii_hex;
wenzelm
parents: 23784
diff changeset
   162
14678
662b181cae05 clarification of ascii vs. symbolic entities;
wenzelm
parents: 14632
diff changeset
   163
fun is_ascii_quasi "_" = true
662b181cae05 clarification of ascii vs. symbolic entities;
wenzelm
parents: 14632
diff changeset
   164
  | is_ascii_quasi "'" = true
662b181cae05 clarification of ascii vs. symbolic entities;
wenzelm
parents: 14632
diff changeset
   165
  | is_ascii_quasi _ = false;
662b181cae05 clarification of ascii vs. symbolic entities;
wenzelm
parents: 14632
diff changeset
   166
662b181cae05 clarification of ascii vs. symbolic entities;
wenzelm
parents: 14632
diff changeset
   167
val is_ascii_blank =
43845
d89353d17f54 added File.fold_pages for streaming of large files;
wenzelm
parents: 43777
diff changeset
   168
  fn " " => true | "\t" => true | "\n" => true | "\^K" => true | "\f" => true | "\^M" => true
14678
662b181cae05 clarification of ascii vs. symbolic entities;
wenzelm
parents: 14632
diff changeset
   169
    | _ => false;
662b181cae05 clarification of ascii vs. symbolic entities;
wenzelm
parents: 14632
diff changeset
   170
34095
c2f176a38448 robust representation of low ASCII control characters within XML/YXML text;
wenzelm
parents: 33955
diff changeset
   171
fun is_ascii_control s = is_char s andalso ord s < 32 andalso not (is_ascii_blank s);
c2f176a38448 robust representation of low ASCII control characters within XML/YXML text;
wenzelm
parents: 33955
diff changeset
   172
50236
476a3350589c clarified Symbol.scan_ascii_id;
wenzelm
parents: 50235
diff changeset
   173
fun is_ascii_letdig s = is_ascii_letter s orelse is_ascii_digit s orelse is_ascii_quasi s;
476a3350589c clarified Symbol.scan_ascii_id;
wenzelm
parents: 50235
diff changeset
   174
64275
ac2abc987cf9 accomodate Poly/ML repository version, which treats singleton strings as boxed;
wenzelm
parents: 63936
diff changeset
   175
fun is_ascii_lower s = is_char s andalso (Char.ord #"a" <= ord s andalso ord s <= Char.ord #"z");
ac2abc987cf9 accomodate Poly/ML repository version, which treats singleton strings as boxed;
wenzelm
parents: 63936
diff changeset
   176
fun is_ascii_upper s = is_char s andalso (Char.ord #"A" <= ord s andalso ord s <= Char.ord #"Z");
20200
c6fb50dbbc30 added is/to_ascii_lower/upper;
wenzelm
parents: 20192
diff changeset
   177
64275
ac2abc987cf9 accomodate Poly/ML repository version, which treats singleton strings as boxed;
wenzelm
parents: 63936
diff changeset
   178
fun to_ascii_lower s = if is_ascii_upper s then chr (ord s + Char.ord #"a" - Char.ord #"A") else s;
ac2abc987cf9 accomodate Poly/ML repository version, which treats singleton strings as boxed;
wenzelm
parents: 63936
diff changeset
   179
fun to_ascii_upper s = if is_ascii_lower s then chr (ord s + Char.ord #"A" - Char.ord #"a") else s;
20200
c6fb50dbbc30 added is/to_ascii_lower/upper;
wenzelm
parents: 20192
diff changeset
   180
50238
98d35a7368bd more uniform Symbol.is_ascii_identifier in ML/Scala;
wenzelm
parents: 50237
diff changeset
   181
fun is_ascii_identifier s =
98d35a7368bd more uniform Symbol.is_ascii_identifier in ML/Scala;
wenzelm
parents: 50237
diff changeset
   182
  size s > 0 andalso is_ascii_letter (String.substring (s, 0, 1)) andalso
98d35a7368bd more uniform Symbol.is_ascii_identifier in ML/Scala;
wenzelm
parents: 50237
diff changeset
   183
  forall_string is_ascii_letdig s;
98d35a7368bd more uniform Symbol.is_ascii_identifier in ML/Scala;
wenzelm
parents: 50237
diff changeset
   184
50236
476a3350589c clarified Symbol.scan_ascii_id;
wenzelm
parents: 50235
diff changeset
   185
val scan_ascii_id = Scan.one is_ascii_letter ^^ (Scan.many is_ascii_letdig >> implode);
476a3350589c clarified Symbol.scan_ascii_id;
wenzelm
parents: 50235
diff changeset
   186
14678
662b181cae05 clarification of ascii vs. symbolic entities;
wenzelm
parents: 14632
diff changeset
   187
14956
70ec4b8aef8d prevent looping of error messages involving malformed symbols;
wenzelm
parents: 14908
diff changeset
   188
(* diagnostics *)
70ec4b8aef8d prevent looping of error messages involving malformed symbols;
wenzelm
parents: 14908
diff changeset
   189
70ec4b8aef8d prevent looping of error messages involving malformed symbols;
wenzelm
parents: 14908
diff changeset
   190
fun beginning n cs =
70ec4b8aef8d prevent looping of error messages involving malformed symbols;
wenzelm
parents: 14908
diff changeset
   191
  let
33955
fff6f11b1f09 curried take/drop
haftmann
parents: 33548
diff changeset
   192
    val drop_blanks = #1 o take_suffix is_ascii_blank;
14956
70ec4b8aef8d prevent looping of error messages involving malformed symbols;
wenzelm
parents: 14908
diff changeset
   193
    val all_cs = drop_blanks cs;
70ec4b8aef8d prevent looping of error messages involving malformed symbols;
wenzelm
parents: 14908
diff changeset
   194
    val dots = if length all_cs > n then " ..." else "";
70ec4b8aef8d prevent looping of error messages involving malformed symbols;
wenzelm
parents: 14908
diff changeset
   195
  in
33955
fff6f11b1f09 curried take/drop
haftmann
parents: 33548
diff changeset
   196
    (drop_blanks (take n all_cs)
14956
70ec4b8aef8d prevent looping of error messages involving malformed symbols;
wenzelm
parents: 14908
diff changeset
   197
      |> map (fn c => if is_ascii_blank c then space else c)
70ec4b8aef8d prevent looping of error messages involving malformed symbols;
wenzelm
parents: 14908
diff changeset
   198
      |> implode) ^ dots
70ec4b8aef8d prevent looping of error messages involving malformed symbols;
wenzelm
parents: 14908
diff changeset
   199
  end;
70ec4b8aef8d prevent looping of error messages involving malformed symbols;
wenzelm
parents: 14908
diff changeset
   200
70ec4b8aef8d prevent looping of error messages involving malformed symbols;
wenzelm
parents: 14908
diff changeset
   201
14873
7efc14398e82 added datatype sym, val decode: symbol -> sym;
wenzelm
parents: 14834
diff changeset
   202
(* symbol variants *)
7efc14398e82 added datatype sym, val decode: symbol -> sym;
wenzelm
parents: 14834
diff changeset
   203
37533
d775bd70f571 explicit treatment of UTF8 character sequences as Isabelle symbols;
wenzelm
parents: 34095
diff changeset
   204
datatype sym =
63936
b87784e19a77 discontinued raw symbols;
wenzelm
parents: 62877
diff changeset
   205
  Char of string | UTF8 of string | Sym of string | Control of string | Malformed of string | EOF;
14873
7efc14398e82 added datatype sym, val decode: symbol -> sym;
wenzelm
parents: 14834
diff changeset
   206
7efc14398e82 added datatype sym, val decode: symbol -> sym;
wenzelm
parents: 14834
diff changeset
   207
fun decode s =
43485
33a24212a72d more tolerant Symbol.decode;
wenzelm
parents: 43418
diff changeset
   208
  if s = "" then EOF
33a24212a72d more tolerant Symbol.decode;
wenzelm
parents: 43418
diff changeset
   209
  else if is_char s then Char s
37533
d775bd70f571 explicit treatment of UTF8 character sequences as Isabelle symbols;
wenzelm
parents: 34095
diff changeset
   210
  else if is_utf8 s then UTF8 s
40523
1050315f6ee2 simplified/robustified treatment of malformed symbols, which are now fully internalized (total Symbol.explode etc.);
wenzelm
parents: 40509
diff changeset
   211
  else if is_malformed s then Malformed s
61475
5b58a17c440a tuned signature;
wenzelm
parents: 61470
diff changeset
   212
  else if is_control s then Control (String.substring (s, 3, size s - 4))
40523
1050315f6ee2 simplified/robustified treatment of malformed symbols, which are now fully internalized (total Symbol.explode etc.);
wenzelm
parents: 40509
diff changeset
   213
  else Sym (String.substring (s, 2, size s - 3));
14873
7efc14398e82 added datatype sym, val decode: symbol -> sym;
wenzelm
parents: 14834
diff changeset
   214
7efc14398e82 added datatype sym, val decode: symbol -> sym;
wenzelm
parents: 14834
diff changeset
   215
14678
662b181cae05 clarification of ascii vs. symbolic entities;
wenzelm
parents: 14632
diff changeset
   216
(* standard symbol kinds *)
662b181cae05 clarification of ascii vs. symbolic entities;
wenzelm
parents: 14632
diff changeset
   217
14171
0cab06e3bbd0 Extended the notion of letter and digit, such that now one may use greek,
skalberg
parents: 13730
diff changeset
   218
local
50235
wenzelm
parents: 50233
diff changeset
   219
  val letter_symbols =
wenzelm
parents: 50233
diff changeset
   220
    Symtab.make_set [
62529
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   221
      "\<A>",
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   222
      "\<B>",
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   223
      "\<C>",
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   224
      "\<D>",
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   225
      "\<E>",
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   226
      "\<F>",
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   227
      "\<G>",
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   228
      "\<H>",
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   229
      "\<I>",
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   230
      "\<J>",
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   231
      "\<K>",
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   232
      "\<L>",
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   233
      "\<M>",
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   234
      "\<N>",
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   235
      "\<O>",
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   236
      "\<P>",
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   237
      "\<Q>",
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   238
      "\<R>",
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   239
      "\<S>",
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   240
      "\<T>",
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   241
      "\<U>",
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   242
      "\<V>",
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   243
      "\<W>",
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   244
      "\<X>",
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   245
      "\<Y>",
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   246
      "\<Z>",
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   247
      "\<a>",
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   248
      "\<b>",
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   249
      "\<c>",
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   250
      "\<d>",
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   251
      "\<e>",
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   252
      "\<f>",
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   253
      "\<g>",
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   254
      "\<h>",
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   255
      "\<i>",
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   256
      "\<j>",
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   257
      "\<k>",
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   258
      "\<l>",
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   259
      "\<m>",
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   260
      "\<n>",
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   261
      "\<o>",
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   262
      "\<p>",
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   263
      "\<q>",
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   264
      "\<r>",
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   265
      "\<s>",
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   266
      "\<t>",
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   267
      "\<u>",
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   268
      "\<v>",
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   269
      "\<w>",
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   270
      "\<x>",
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   271
      "\<y>",
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   272
      "\<z>",
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   273
      "\<AA>",
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   274
      "\<BB>",
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   275
      "\<CC>",
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   276
      "\<DD>",
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   277
      "\<EE>",
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   278
      "\<FF>",
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   279
      "\<GG>",
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   280
      "\<HH>",
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   281
      "\<II>",
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   282
      "\<JJ>",
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   283
      "\<KK>",
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   284
      "\<LL>",
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   285
      "\<MM>",
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   286
      "\<NN>",
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   287
      "\<OO>",
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   288
      "\<PP>",
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   289
      "\<QQ>",
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   290
      "\<RR>",
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   291
      "\<SS>",
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   292
      "\<TT>",
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   293
      "\<UU>",
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   294
      "\<VV>",
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   295
      "\<WW>",
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   296
      "\<XX>",
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   297
      "\<YY>",
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   298
      "\<ZZ>",
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   299
      "\<aa>",
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   300
      "\<bb>",
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   301
      "\<cc>",
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   302
      "\<dd>",
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   303
      "\<ee>",
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   304
      "\<ff>",
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   305
      "\<gg>",
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   306
      "\<hh>",
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   307
      "\<ii>",
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   308
      "\<jj>",
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   309
      "\<kk>",
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   310
      "\<ll>",
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   311
      "\<mm>",
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   312
      "\<nn>",
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   313
      "\<oo>",
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   314
      "\<pp>",
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   315
      "\<qq>",
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   316
      "\<rr>",
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   317
      "\<ss>",
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   318
      "\<tt>",
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   319
      "\<uu>",
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   320
      "\<vv>",
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   321
      "\<ww>",
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   322
      "\<xx>",
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   323
      "\<yy>",
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   324
      "\<zz>",
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   325
      "\<alpha>",
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   326
      "\<beta>",
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   327
      "\<gamma>",
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   328
      "\<delta>",
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   329
      "\<epsilon>",
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   330
      "\<zeta>",
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   331
      "\<eta>",
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   332
      "\<theta>",
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   333
      "\<iota>",
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   334
      "\<kappa>",
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   335
      (*"\<lambda>", sic!*)
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   336
      "\<mu>",
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   337
      "\<nu>",
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   338
      "\<xi>",
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   339
      "\<pi>",
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   340
      "\<rho>",
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   341
      "\<sigma>",
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   342
      "\<tau>",
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   343
      "\<upsilon>",
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   344
      "\<phi>",
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   345
      "\<chi>",
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   346
      "\<psi>",
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   347
      "\<omega>",
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   348
      "\<Gamma>",
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   349
      "\<Delta>",
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   350
      "\<Theta>",
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   351
      "\<Lambda>",
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   352
      "\<Xi>",
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   353
      "\<Pi>",
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   354
      "\<Sigma>",
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   355
      "\<Upsilon>",
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   356
      "\<Phi>",
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   357
      "\<Psi>",
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   358
      "\<Omega>"
50235
wenzelm
parents: 50233
diff changeset
   359
    ];
14171
0cab06e3bbd0 Extended the notion of letter and digit, such that now one may use greek,
skalberg
parents: 13730
diff changeset
   360
in
50242
56b9c792a98b support for sub-structured identifier syntax (inactive);
wenzelm
parents: 50239
diff changeset
   361
56b9c792a98b support for sub-structured identifier syntax (inactive);
wenzelm
parents: 50239
diff changeset
   362
val is_letter_symbol = Symtab.defined letter_symbols;
56b9c792a98b support for sub-structured identifier syntax (inactive);
wenzelm
parents: 50239
diff changeset
   363
14678
662b181cae05 clarification of ascii vs. symbolic entities;
wenzelm
parents: 14632
diff changeset
   364
end;
14173
a3690aeb79d4 Removed the extended digits again.
skalberg
parents: 14171
diff changeset
   365
50242
56b9c792a98b support for sub-structured identifier syntax (inactive);
wenzelm
parents: 50239
diff changeset
   366
datatype kind = Letter | Digit | Quasi | Blank | Other;
56b9c792a98b support for sub-structured identifier syntax (inactive);
wenzelm
parents: 50239
diff changeset
   367
56b9c792a98b support for sub-structured identifier syntax (inactive);
wenzelm
parents: 50239
diff changeset
   368
fun kind s =
56b9c792a98b support for sub-structured identifier syntax (inactive);
wenzelm
parents: 50239
diff changeset
   369
  if is_ascii_letter s then Letter
56b9c792a98b support for sub-structured identifier syntax (inactive);
wenzelm
parents: 50239
diff changeset
   370
  else if is_ascii_digit s then Digit
56b9c792a98b support for sub-structured identifier syntax (inactive);
wenzelm
parents: 50239
diff changeset
   371
  else if is_ascii_quasi s then Quasi
56b9c792a98b support for sub-structured identifier syntax (inactive);
wenzelm
parents: 50239
diff changeset
   372
  else if is_ascii_blank s then Blank
56b9c792a98b support for sub-structured identifier syntax (inactive);
wenzelm
parents: 50239
diff changeset
   373
  else if is_char s then Other
56b9c792a98b support for sub-structured identifier syntax (inactive);
wenzelm
parents: 50239
diff changeset
   374
  else if is_letter_symbol s then Letter
56b9c792a98b support for sub-structured identifier syntax (inactive);
wenzelm
parents: 50239
diff changeset
   375
  else Other;
56b9c792a98b support for sub-structured identifier syntax (inactive);
wenzelm
parents: 50239
diff changeset
   376
14678
662b181cae05 clarification of ascii vs. symbolic entities;
wenzelm
parents: 14632
diff changeset
   377
fun is_letter s = kind s = Letter;
662b181cae05 clarification of ascii vs. symbolic entities;
wenzelm
parents: 14632
diff changeset
   378
fun is_digit s = kind s = Digit;
662b181cae05 clarification of ascii vs. symbolic entities;
wenzelm
parents: 14632
diff changeset
   379
fun is_quasi s = kind s = Quasi;
662b181cae05 clarification of ascii vs. symbolic entities;
wenzelm
parents: 14632
diff changeset
   380
fun is_blank s = kind s = Blank;
6272
52d99d68d3be added output_width;
wenzelm
parents: 6225
diff changeset
   381
62529
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   382
val is_block_ctrl = member (op =) ["\<^bsub>", "\<^esub>", "\<^bsup>", "\<^esup>"];
47850
c638127b4653 avoid interference of markup for literal tokens, which may contain slightly odd \<^bsub> \<^esub> counted as pseudo-markup (especially relevant for HTML output, e.g. of thm power3_eq_cube);
wenzelm
parents: 43947
diff changeset
   383
14678
662b181cae05 clarification of ascii vs. symbolic entities;
wenzelm
parents: 14632
diff changeset
   384
fun is_quasi_letter s = let val k = kind s in k = Letter orelse k = Quasi end;
662b181cae05 clarification of ascii vs. symbolic entities;
wenzelm
parents: 14632
diff changeset
   385
fun is_letdig s = let val k = kind s in k = Letter orelse k = Digit orelse k = Quasi end;
11010
2c6559297be3 added strip_blanks;
wenzelm
parents: 10953
diff changeset
   386
6272
52d99d68d3be added output_width;
wenzelm
parents: 6225
diff changeset
   387
50237
wenzelm
parents: 50236
diff changeset
   388
(* escape *)
wenzelm
parents: 50236
diff changeset
   389
wenzelm
parents: 50236
diff changeset
   390
val esc = fn s =>
wenzelm
parents: 50236
diff changeset
   391
  if is_char s then s
wenzelm
parents: 50236
diff changeset
   392
  else if is_utf8 s then translate_string (fn c => "\\" ^ string_of_int (ord c)) s
wenzelm
parents: 50236
diff changeset
   393
  else "\\" ^ s;
wenzelm
parents: 50236
diff changeset
   394
63936
b87784e19a77 discontinued raw symbols;
wenzelm
parents: 62877
diff changeset
   395
val escape = implode o map esc o Symbol.explode;
50237
wenzelm
parents: 50236
diff changeset
   396
wenzelm
parents: 50236
diff changeset
   397
wenzelm
parents: 50236
diff changeset
   398
wenzelm
parents: 50236
diff changeset
   399
(** scanning through symbols **)
wenzelm
parents: 50236
diff changeset
   400
wenzelm
parents: 50236
diff changeset
   401
(* scanner *)
wenzelm
parents: 50236
diff changeset
   402
wenzelm
parents: 50236
diff changeset
   403
fun scanner msg scan syms =
wenzelm
parents: 50236
diff changeset
   404
  let
wenzelm
parents: 50236
diff changeset
   405
    fun message (ss, NONE) = (fn () => msg ^ ": " ^ quote (beginning 10 ss))
wenzelm
parents: 50236
diff changeset
   406
      | message (ss, SOME msg') = (fn () => msg ^ ", " ^ msg' () ^ ": " ^ quote (beginning 10 ss));
wenzelm
parents: 50236
diff changeset
   407
    val finite_scan = Scan.error (Scan.finite stopper (!! message scan));
wenzelm
parents: 50236
diff changeset
   408
  in
wenzelm
parents: 50236
diff changeset
   409
    (case finite_scan syms of
wenzelm
parents: 50236
diff changeset
   410
      (result, []) => result
wenzelm
parents: 50236
diff changeset
   411
    | (_, rest) => error (message (rest, NONE) ()))
wenzelm
parents: 50236
diff changeset
   412
  end;
wenzelm
parents: 50236
diff changeset
   413
wenzelm
parents: 50236
diff changeset
   414
50162
e06eabc421e7 some support for breakable text and paragraphs;
wenzelm
parents: 48774
diff changeset
   415
(* space-separated words *)
e06eabc421e7 some support for breakable text and paragraphs;
wenzelm
parents: 48774
diff changeset
   416
e06eabc421e7 some support for breakable text and paragraphs;
wenzelm
parents: 48774
diff changeset
   417
val scan_word =
e06eabc421e7 some support for breakable text and paragraphs;
wenzelm
parents: 48774
diff changeset
   418
  Scan.many1 is_ascii_blank >> K NONE ||
e06eabc421e7 some support for breakable text and paragraphs;
wenzelm
parents: 48774
diff changeset
   419
  Scan.many1 (fn s => not (is_ascii_blank s) andalso not_eof s) >> (SOME o implode);
e06eabc421e7 some support for breakable text and paragraphs;
wenzelm
parents: 48774
diff changeset
   420
e06eabc421e7 some support for breakable text and paragraphs;
wenzelm
parents: 48774
diff changeset
   421
val split_words = scanner "Bad text" (Scan.repeat scan_word >> map_filter I);
e06eabc421e7 some support for breakable text and paragraphs;
wenzelm
parents: 48774
diff changeset
   422
63936
b87784e19a77 discontinued raw symbols;
wenzelm
parents: 62877
diff changeset
   423
val explode_words = split_words o Symbol.explode;
50162
e06eabc421e7 some support for breakable text and paragraphs;
wenzelm
parents: 48774
diff changeset
   424
e06eabc421e7 some support for breakable text and paragraphs;
wenzelm
parents: 48774
diff changeset
   425
14678
662b181cae05 clarification of ascii vs. symbolic entities;
wenzelm
parents: 14632
diff changeset
   426
(* blanks *)
662b181cae05 clarification of ascii vs. symbolic entities;
wenzelm
parents: 14632
diff changeset
   427
63936
b87784e19a77 discontinued raw symbols;
wenzelm
parents: 62877
diff changeset
   428
val trim_blanks = Symbol.explode #> trim is_blank #> implode;
14678
662b181cae05 clarification of ascii vs. symbolic entities;
wenzelm
parents: 14632
diff changeset
   429
662b181cae05 clarification of ascii vs. symbolic entities;
wenzelm
parents: 14632
diff changeset
   430
662b181cae05 clarification of ascii vs. symbolic entities;
wenzelm
parents: 14632
diff changeset
   431
(* bump string -- treat as base 26 or base 1 numbers *)
662b181cae05 clarification of ascii vs. symbolic entities;
wenzelm
parents: 14632
diff changeset
   432
62529
8b7bdfc09f3b clarified treatment of fragments of Isabelle symbols during bootstrap;
wenzelm
parents: 62210
diff changeset
   433
fun symbolic_end (_ :: "\<^sub>" :: _) = true
53198
06b096cf89ca ignore trailing primes, e.g. rename \<alpha>' to \<alpha>'' instead of \<alpha>'a;
wenzelm
parents: 53016
diff changeset
   434
  | symbolic_end ("'" :: ss) = symbolic_end ss
55033
8e8243975860 support for nested text cartouches;
wenzelm
parents: 54734
diff changeset
   435
  | symbolic_end (s :: _) = raw_symbolic s
14908
wenzelm
parents: 14873
diff changeset
   436
  | symbolic_end [] = false;
14678
662b181cae05 clarification of ascii vs. symbolic entities;
wenzelm
parents: 14632
diff changeset
   437
662b181cae05 clarification of ascii vs. symbolic entities;
wenzelm
parents: 14632
diff changeset
   438
fun bump_init str =
63936
b87784e19a77 discontinued raw symbols;
wenzelm
parents: 62877
diff changeset
   439
  if symbolic_end (rev (Symbol.explode str)) then str ^ "'"
14678
662b181cae05 clarification of ascii vs. symbolic entities;
wenzelm
parents: 14632
diff changeset
   440
  else str ^ "a";
12904
c208d71702d1 added is_quasi;
wenzelm
parents: 12116
diff changeset
   441
c208d71702d1 added is_quasi;
wenzelm
parents: 12116
diff changeset
   442
fun bump_string str =
c208d71702d1 added is_quasi;
wenzelm
parents: 12116
diff changeset
   443
  let
c208d71702d1 added is_quasi;
wenzelm
parents: 12116
diff changeset
   444
    fun bump [] = ["a"]
c208d71702d1 added is_quasi;
wenzelm
parents: 12116
diff changeset
   445
      | bump ("z" :: ss) = "a" :: bump ss
c208d71702d1 added is_quasi;
wenzelm
parents: 12116
diff changeset
   446
      | bump (s :: ss) =
64275
ac2abc987cf9 accomodate Poly/ML repository version, which treats singleton strings as boxed;
wenzelm
parents: 63936
diff changeset
   447
          if is_char s andalso Char.ord #"a" <= ord s andalso ord s < Char.ord #"z"
12904
c208d71702d1 added is_quasi;
wenzelm
parents: 12116
diff changeset
   448
          then chr (ord s + 1) :: ss
c208d71702d1 added is_quasi;
wenzelm
parents: 12116
diff changeset
   449
          else "a" :: s :: ss;
14678
662b181cae05 clarification of ascii vs. symbolic entities;
wenzelm
parents: 14632
diff changeset
   450
63936
b87784e19a77 discontinued raw symbols;
wenzelm
parents: 62877
diff changeset
   451
    val (ss, qs) = apfst rev (take_suffix is_quasi (Symbol.explode str));
14908
wenzelm
parents: 14873
diff changeset
   452
    val ss' = if symbolic_end ss then "'" :: ss else bump ss;
14678
662b181cae05 clarification of ascii vs. symbolic entities;
wenzelm
parents: 14632
diff changeset
   453
  in implode (rev ss' @ qs) end;
662b181cae05 clarification of ascii vs. symbolic entities;
wenzelm
parents: 14632
diff changeset
   454
12904
c208d71702d1 added is_quasi;
wenzelm
parents: 12116
diff changeset
   455
6272
52d99d68d3be added output_width;
wenzelm
parents: 6225
diff changeset
   456
29324
e07fc65e296b added output;
wenzelm
parents: 27903
diff changeset
   457
(** symbol output **)
14977
77d88064991a added escape, export encode_raw, default mode now trivial, tuned;
wenzelm
parents: 14961
diff changeset
   458
29324
e07fc65e296b added output;
wenzelm
parents: 27903
diff changeset
   459
(* length *)
6272
52d99d68d3be added output_width;
wenzelm
parents: 6225
diff changeset
   460
14678
662b181cae05 clarification of ascii vs. symbolic entities;
wenzelm
parents: 14632
diff changeset
   461
fun sym_len s =
24593
1547ea587f5a added some int constraints (ML_Parse.fix_ints not active here);
wenzelm
parents: 24580
diff changeset
   462
  if not (is_printable s) then (0: int)
62877
741560a5283b avoid malformed Isabelle symbols during bootstrap;
wenzelm
parents: 62804
diff changeset
   463
  else if String.isPrefix "\092<long" s then 2
741560a5283b avoid malformed Isabelle symbols during bootstrap;
wenzelm
parents: 62804
diff changeset
   464
  else if String.isPrefix "\092<Long" s then 2
14678
662b181cae05 clarification of ascii vs. symbolic entities;
wenzelm
parents: 14632
diff changeset
   465
  else 1;
662b181cae05 clarification of ascii vs. symbolic entities;
wenzelm
parents: 14632
diff changeset
   466
19473
wenzelm
parents: 19305
diff changeset
   467
fun sym_length ss = fold (fn s => fn n => sym_len s + n) ss 0;
14678
662b181cae05 clarification of ascii vs. symbolic entities;
wenzelm
parents: 14632
diff changeset
   468
29324
e07fc65e296b added output;
wenzelm
parents: 27903
diff changeset
   469
e07fc65e296b added output;
wenzelm
parents: 27903
diff changeset
   470
(* print mode *)
e07fc65e296b added output;
wenzelm
parents: 27903
diff changeset
   471
e07fc65e296b added output;
wenzelm
parents: 27903
diff changeset
   472
val xsymbolsN = "xsymbols";
e07fc65e296b added output;
wenzelm
parents: 27903
diff changeset
   473
63936
b87784e19a77 discontinued raw symbols;
wenzelm
parents: 62877
diff changeset
   474
fun output s = (s, sym_length (Symbol.explode s));
29324
e07fc65e296b added output;
wenzelm
parents: 27903
diff changeset
   475
e07fc65e296b added output;
wenzelm
parents: 27903
diff changeset
   476
6116
8ba2f25610f7 files scan.ML, source.ML, symbol.ML, pretty.ML moved to Pure/General;
wenzelm
parents:
diff changeset
   477
(*final declarations of this structure!*)
63936
b87784e19a77 discontinued raw symbols;
wenzelm
parents: 62877
diff changeset
   478
val explode = Symbol.explode;
6272
52d99d68d3be added output_width;
wenzelm
parents: 6225
diff changeset
   479
val length = sym_length;
6116
8ba2f25610f7 files scan.ML, source.ML, symbol.ML, pretty.ML moved to Pure/General;
wenzelm
parents:
diff changeset
   480
8ba2f25610f7 files scan.ML, source.ML, symbol.ML, pretty.ML moved to Pure/General;
wenzelm
parents:
diff changeset
   481
end;