src/Pure/General/xml.ML
author wenzelm
Fri, 18 Dec 2009 12:28:50 +0100
changeset 34119 ae92efb48784
parent 31469 40f815edbde4
child 38228 ada3ab6b9085
permissions -rw-r--r--
markup bad YXML as malformed; removed unused XML.document; removed unused markup;
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
24584
01e83ffa6c54 fixed title
haftmann
parents: 24264
diff changeset
     1
(*  Title:      Pure/General/xml.ML
24264
d6935e7dac8b moved Tools/xml.ML to General/xml.ML (again);
wenzelm
parents:
diff changeset
     2
    Author:     David Aspinall, Stefan Berghofer and Markus Wenzel
d6935e7dac8b moved Tools/xml.ML to General/xml.ML (again);
wenzelm
parents:
diff changeset
     3
d6935e7dac8b moved Tools/xml.ML to General/xml.ML (again);
wenzelm
parents:
diff changeset
     4
Basic support for XML.
d6935e7dac8b moved Tools/xml.ML to General/xml.ML (again);
wenzelm
parents:
diff changeset
     5
*)
d6935e7dac8b moved Tools/xml.ML to General/xml.ML (again);
wenzelm
parents:
diff changeset
     6
d6935e7dac8b moved Tools/xml.ML to General/xml.ML (again);
wenzelm
parents:
diff changeset
     7
signature XML =
d6935e7dac8b moved Tools/xml.ML to General/xml.ML (again);
wenzelm
parents:
diff changeset
     8
sig
28017
4919bd124a58 type Properties.T;
wenzelm
parents: 27884
diff changeset
     9
  type attributes = Properties.T
24264
d6935e7dac8b moved Tools/xml.ML to General/xml.ML (again);
wenzelm
parents:
diff changeset
    10
  datatype tree =
d6935e7dac8b moved Tools/xml.ML to General/xml.ML (again);
wenzelm
parents:
diff changeset
    11
      Elem of string * attributes * tree list
d6935e7dac8b moved Tools/xml.ML to General/xml.ML (again);
wenzelm
parents:
diff changeset
    12
    | Text of string
26546
ba4cdf92c7c4 further cleanup of XML signature;
wenzelm
parents: 26539
diff changeset
    13
  val add_content: tree -> Buffer.T -> Buffer.T
ba4cdf92c7c4 further cleanup of XML signature;
wenzelm
parents: 26539
diff changeset
    14
  val header: string
ba4cdf92c7c4 further cleanup of XML signature;
wenzelm
parents: 26539
diff changeset
    15
  val text: string -> string
ba4cdf92c7c4 further cleanup of XML signature;
wenzelm
parents: 26539
diff changeset
    16
  val element: string -> attributes -> string list -> string
ba4cdf92c7c4 further cleanup of XML signature;
wenzelm
parents: 26539
diff changeset
    17
  val output_markup: Markup.T -> output * output
26539
a0754be538ab added output_markup (from Tools/isabelle_process.ML);
wenzelm
parents: 26525
diff changeset
    18
  val string_of: tree -> string
26546
ba4cdf92c7c4 further cleanup of XML signature;
wenzelm
parents: 26539
diff changeset
    19
  val output: tree -> TextIO.outstream -> unit
26984
d0e098e206f3 added parse_document (optional unchecked header material);
wenzelm
parents: 26554
diff changeset
    20
  val parse_comments: string list -> unit * string list
24264
d6935e7dac8b moved Tools/xml.ML to General/xml.ML (again);
wenzelm
parents:
diff changeset
    21
  val parse_string : string -> string option
26546
ba4cdf92c7c4 further cleanup of XML signature;
wenzelm
parents: 26539
diff changeset
    22
  val parse_element: string list -> tree * string list
26984
d0e098e206f3 added parse_document (optional unchecked header material);
wenzelm
parents: 26554
diff changeset
    23
  val parse_document: string list -> tree * string list
26539
a0754be538ab added output_markup (from Tools/isabelle_process.ML);
wenzelm
parents: 26525
diff changeset
    24
  val parse: string -> tree
24264
d6935e7dac8b moved Tools/xml.ML to General/xml.ML (again);
wenzelm
parents:
diff changeset
    25
end;
d6935e7dac8b moved Tools/xml.ML to General/xml.ML (again);
wenzelm
parents:
diff changeset
    26
d6935e7dac8b moved Tools/xml.ML to General/xml.ML (again);
wenzelm
parents:
diff changeset
    27
structure XML: XML =
d6935e7dac8b moved Tools/xml.ML to General/xml.ML (again);
wenzelm
parents:
diff changeset
    28
struct
d6935e7dac8b moved Tools/xml.ML to General/xml.ML (again);
wenzelm
parents:
diff changeset
    29
26546
ba4cdf92c7c4 further cleanup of XML signature;
wenzelm
parents: 26539
diff changeset
    30
(** XML trees **)
ba4cdf92c7c4 further cleanup of XML signature;
wenzelm
parents: 26539
diff changeset
    31
28017
4919bd124a58 type Properties.T;
wenzelm
parents: 27884
diff changeset
    32
type attributes = Properties.T;
26546
ba4cdf92c7c4 further cleanup of XML signature;
wenzelm
parents: 26539
diff changeset
    33
ba4cdf92c7c4 further cleanup of XML signature;
wenzelm
parents: 26539
diff changeset
    34
datatype tree =
ba4cdf92c7c4 further cleanup of XML signature;
wenzelm
parents: 26539
diff changeset
    35
    Elem of string * attributes * tree list
28033
f03b5856f286 removed obsolete XML.Output workaround;
wenzelm
parents: 28017
diff changeset
    36
  | Text of string;
26546
ba4cdf92c7c4 further cleanup of XML signature;
wenzelm
parents: 26539
diff changeset
    37
ba4cdf92c7c4 further cleanup of XML signature;
wenzelm
parents: 26539
diff changeset
    38
fun add_content (Elem (_, _, ts)) = fold add_content ts
28033
f03b5856f286 removed obsolete XML.Output workaround;
wenzelm
parents: 28017
diff changeset
    39
  | add_content (Text s) = Buffer.add s;
26546
ba4cdf92c7c4 further cleanup of XML signature;
wenzelm
parents: 26539
diff changeset
    40
ba4cdf92c7c4 further cleanup of XML signature;
wenzelm
parents: 26539
diff changeset
    41
24264
d6935e7dac8b moved Tools/xml.ML to General/xml.ML (again);
wenzelm
parents:
diff changeset
    42
26525
14a56f013469 added detect;
wenzelm
parents: 25838
diff changeset
    43
(** string representation **)
14a56f013469 added detect;
wenzelm
parents: 25838
diff changeset
    44
24264
d6935e7dac8b moved Tools/xml.ML to General/xml.ML (again);
wenzelm
parents:
diff changeset
    45
val header = "<?xml version=\"1.0\"?>\n";
d6935e7dac8b moved Tools/xml.ML to General/xml.ML (again);
wenzelm
parents:
diff changeset
    46
d6935e7dac8b moved Tools/xml.ML to General/xml.ML (again);
wenzelm
parents:
diff changeset
    47
26546
ba4cdf92c7c4 further cleanup of XML signature;
wenzelm
parents: 26539
diff changeset
    48
(* escaped text *)
24264
d6935e7dac8b moved Tools/xml.ML to General/xml.ML (again);
wenzelm
parents:
diff changeset
    49
d6935e7dac8b moved Tools/xml.ML to General/xml.ML (again);
wenzelm
parents:
diff changeset
    50
fun decode "&lt;" = "<"
d6935e7dac8b moved Tools/xml.ML to General/xml.ML (again);
wenzelm
parents:
diff changeset
    51
  | decode "&gt;" = ">"
d6935e7dac8b moved Tools/xml.ML to General/xml.ML (again);
wenzelm
parents:
diff changeset
    52
  | decode "&amp;" = "&"
d6935e7dac8b moved Tools/xml.ML to General/xml.ML (again);
wenzelm
parents:
diff changeset
    53
  | decode "&apos;" = "'"
d6935e7dac8b moved Tools/xml.ML to General/xml.ML (again);
wenzelm
parents:
diff changeset
    54
  | decode "&quot;" = "\""
d6935e7dac8b moved Tools/xml.ML to General/xml.ML (again);
wenzelm
parents:
diff changeset
    55
  | decode c = c;
d6935e7dac8b moved Tools/xml.ML to General/xml.ML (again);
wenzelm
parents:
diff changeset
    56
d6935e7dac8b moved Tools/xml.ML to General/xml.ML (again);
wenzelm
parents:
diff changeset
    57
fun encode "<" = "&lt;"
d6935e7dac8b moved Tools/xml.ML to General/xml.ML (again);
wenzelm
parents:
diff changeset
    58
  | encode ">" = "&gt;"
d6935e7dac8b moved Tools/xml.ML to General/xml.ML (again);
wenzelm
parents:
diff changeset
    59
  | encode "&" = "&amp;"
d6935e7dac8b moved Tools/xml.ML to General/xml.ML (again);
wenzelm
parents:
diff changeset
    60
  | encode "'" = "&apos;"
d6935e7dac8b moved Tools/xml.ML to General/xml.ML (again);
wenzelm
parents:
diff changeset
    61
  | encode "\"" = "&quot;"
d6935e7dac8b moved Tools/xml.ML to General/xml.ML (again);
wenzelm
parents:
diff changeset
    62
  | encode c = c;
d6935e7dac8b moved Tools/xml.ML to General/xml.ML (again);
wenzelm
parents:
diff changeset
    63
25838
00b2a1b2c4e9 removed unused text_charref, cdata;
wenzelm
parents: 24584
diff changeset
    64
val text = translate_string encode;
24264
d6935e7dac8b moved Tools/xml.ML to General/xml.ML (again);
wenzelm
parents:
diff changeset
    65
d6935e7dac8b moved Tools/xml.ML to General/xml.ML (again);
wenzelm
parents:
diff changeset
    66
d6935e7dac8b moved Tools/xml.ML to General/xml.ML (again);
wenzelm
parents:
diff changeset
    67
(* elements *)
d6935e7dac8b moved Tools/xml.ML to General/xml.ML (again);
wenzelm
parents:
diff changeset
    68
26539
a0754be538ab added output_markup (from Tools/isabelle_process.ML);
wenzelm
parents: 26525
diff changeset
    69
fun elem name atts =
26551
da1cd11d8a25 renamed parse_comment_whspc to parse_comments;
wenzelm
parents: 26546
diff changeset
    70
  space_implode " " (name :: map (fn (a, x) => a ^ "=\"" ^ text x ^ "\"") atts);
24264
d6935e7dac8b moved Tools/xml.ML to General/xml.ML (again);
wenzelm
parents:
diff changeset
    71
26525
14a56f013469 added detect;
wenzelm
parents: 25838
diff changeset
    72
fun element name atts body =
26539
a0754be538ab added output_markup (from Tools/isabelle_process.ML);
wenzelm
parents: 26525
diff changeset
    73
  let val b = implode body in
a0754be538ab added output_markup (from Tools/isabelle_process.ML);
wenzelm
parents: 26525
diff changeset
    74
    if b = "" then enclose "<" "/>" (elem name atts)
a0754be538ab added output_markup (from Tools/isabelle_process.ML);
wenzelm
parents: 26525
diff changeset
    75
    else enclose "<" ">" (elem name atts) ^ b ^ enclose "</" ">" name
24264
d6935e7dac8b moved Tools/xml.ML to General/xml.ML (again);
wenzelm
parents:
diff changeset
    76
  end;
d6935e7dac8b moved Tools/xml.ML to General/xml.ML (again);
wenzelm
parents:
diff changeset
    77
27884
10c927e4abf5 output_markup: check Markup.is_none;
wenzelm
parents: 26984
diff changeset
    78
fun output_markup (markup as (name, atts)) =
29325
a205acc94356 Markup.no_output;
wenzelm
parents: 28033
diff changeset
    79
  if Markup.is_none markup then Markup.no_output
27884
10c927e4abf5 output_markup: check Markup.is_none;
wenzelm
parents: 26984
diff changeset
    80
  else (enclose "<" ">" (elem name atts), enclose "</" ">" name);
26539
a0754be538ab added output_markup (from Tools/isabelle_process.ML);
wenzelm
parents: 26525
diff changeset
    81
24264
d6935e7dac8b moved Tools/xml.ML to General/xml.ML (again);
wenzelm
parents:
diff changeset
    82
26546
ba4cdf92c7c4 further cleanup of XML signature;
wenzelm
parents: 26539
diff changeset
    83
(* output *)
24264
d6935e7dac8b moved Tools/xml.ML to General/xml.ML (again);
wenzelm
parents:
diff changeset
    84
26546
ba4cdf92c7c4 further cleanup of XML signature;
wenzelm
parents: 26539
diff changeset
    85
fun buffer_of tree =
24264
d6935e7dac8b moved Tools/xml.ML to General/xml.ML (again);
wenzelm
parents:
diff changeset
    86
  let
26546
ba4cdf92c7c4 further cleanup of XML signature;
wenzelm
parents: 26539
diff changeset
    87
    fun traverse (Elem (name, atts, [])) =
26539
a0754be538ab added output_markup (from Tools/isabelle_process.ML);
wenzelm
parents: 26525
diff changeset
    88
          Buffer.add "<" #> Buffer.add (elem name atts) #> Buffer.add "/>"
26546
ba4cdf92c7c4 further cleanup of XML signature;
wenzelm
parents: 26539
diff changeset
    89
      | traverse (Elem (name, atts, ts)) =
26539
a0754be538ab added output_markup (from Tools/isabelle_process.ML);
wenzelm
parents: 26525
diff changeset
    90
          Buffer.add "<" #> Buffer.add (elem name atts) #> Buffer.add ">" #>
26546
ba4cdf92c7c4 further cleanup of XML signature;
wenzelm
parents: 26539
diff changeset
    91
          fold traverse ts #>
26525
14a56f013469 added detect;
wenzelm
parents: 25838
diff changeset
    92
          Buffer.add "</" #> Buffer.add name #> Buffer.add ">"
28033
f03b5856f286 removed obsolete XML.Output workaround;
wenzelm
parents: 28017
diff changeset
    93
      | traverse (Text s) = Buffer.add (text s);
26546
ba4cdf92c7c4 further cleanup of XML signature;
wenzelm
parents: 26539
diff changeset
    94
  in Buffer.empty |> traverse tree end;
24264
d6935e7dac8b moved Tools/xml.ML to General/xml.ML (again);
wenzelm
parents:
diff changeset
    95
26546
ba4cdf92c7c4 further cleanup of XML signature;
wenzelm
parents: 26539
diff changeset
    96
val string_of = Buffer.content o buffer_of;
ba4cdf92c7c4 further cleanup of XML signature;
wenzelm
parents: 26539
diff changeset
    97
val output = Buffer.output o buffer_of;
25838
00b2a1b2c4e9 removed unused text_charref, cdata;
wenzelm
parents: 24584
diff changeset
    98
24264
d6935e7dac8b moved Tools/xml.ML to General/xml.ML (again);
wenzelm
parents:
diff changeset
    99
d6935e7dac8b moved Tools/xml.ML to General/xml.ML (again);
wenzelm
parents:
diff changeset
   100
26546
ba4cdf92c7c4 further cleanup of XML signature;
wenzelm
parents: 26539
diff changeset
   101
(** XML parsing (slow) **)
ba4cdf92c7c4 further cleanup of XML signature;
wenzelm
parents: 26539
diff changeset
   102
ba4cdf92c7c4 further cleanup of XML signature;
wenzelm
parents: 26539
diff changeset
   103
local
24264
d6935e7dac8b moved Tools/xml.ML to General/xml.ML (again);
wenzelm
parents:
diff changeset
   104
d6935e7dac8b moved Tools/xml.ML to General/xml.ML (again);
wenzelm
parents:
diff changeset
   105
fun err s (xs, _) =
d6935e7dac8b moved Tools/xml.ML to General/xml.ML (again);
wenzelm
parents:
diff changeset
   106
  "XML parsing error: " ^ s ^ "\nfound: " ^ quote (Symbol.beginning 100 xs);
d6935e7dac8b moved Tools/xml.ML to General/xml.ML (again);
wenzelm
parents:
diff changeset
   107
26984
d0e098e206f3 added parse_document (optional unchecked header material);
wenzelm
parents: 26554
diff changeset
   108
fun ignored _ = [];
d0e098e206f3 added parse_document (optional unchecked header material);
wenzelm
parents: 26554
diff changeset
   109
26551
da1cd11d8a25 renamed parse_comment_whspc to parse_comments;
wenzelm
parents: 26546
diff changeset
   110
val blanks = Scan.many Symbol.is_blank;
da1cd11d8a25 renamed parse_comment_whspc to parse_comments;
wenzelm
parents: 26546
diff changeset
   111
val special = $$ "&" ^^ Symbol.scan_id ^^ $$ ";" >> decode;
da1cd11d8a25 renamed parse_comment_whspc to parse_comments;
wenzelm
parents: 26546
diff changeset
   112
val regular = Scan.one Symbol.is_regular;
da1cd11d8a25 renamed parse_comment_whspc to parse_comments;
wenzelm
parents: 26546
diff changeset
   113
fun regular_except x = Scan.one (fn c => Symbol.is_regular c andalso c <> x);
24264
d6935e7dac8b moved Tools/xml.ML to General/xml.ML (again);
wenzelm
parents:
diff changeset
   114
26551
da1cd11d8a25 renamed parse_comment_whspc to parse_comments;
wenzelm
parents: 26546
diff changeset
   115
val parse_chars = Scan.repeat1 (special || regular_except "<") >> implode;
24264
d6935e7dac8b moved Tools/xml.ML to General/xml.ML (again);
wenzelm
parents:
diff changeset
   116
26551
da1cd11d8a25 renamed parse_comment_whspc to parse_comments;
wenzelm
parents: 26546
diff changeset
   117
val parse_cdata =
da1cd11d8a25 renamed parse_comment_whspc to parse_comments;
wenzelm
parents: 26546
diff changeset
   118
  Scan.this_string "<![CDATA[" |--
da1cd11d8a25 renamed parse_comment_whspc to parse_comments;
wenzelm
parents: 26546
diff changeset
   119
  (Scan.repeat (Scan.unless (Scan.this_string "]]>") regular) >> implode) --|
da1cd11d8a25 renamed parse_comment_whspc to parse_comments;
wenzelm
parents: 26546
diff changeset
   120
  Scan.this_string "]]>";
24264
d6935e7dac8b moved Tools/xml.ML to General/xml.ML (again);
wenzelm
parents:
diff changeset
   121
d6935e7dac8b moved Tools/xml.ML to General/xml.ML (again);
wenzelm
parents:
diff changeset
   122
val parse_att =
26551
da1cd11d8a25 renamed parse_comment_whspc to parse_comments;
wenzelm
parents: 26546
diff changeset
   123
  (Symbol.scan_id --| (blanks -- $$ "=" -- blanks)) --
da1cd11d8a25 renamed parse_comment_whspc to parse_comments;
wenzelm
parents: 26546
diff changeset
   124
  (($$ "\"" || $$ "'") :|-- (fn s =>
da1cd11d8a25 renamed parse_comment_whspc to parse_comments;
wenzelm
parents: 26546
diff changeset
   125
    (Scan.repeat (special || regular_except s) >> implode) --| $$ s));
24264
d6935e7dac8b moved Tools/xml.ML to General/xml.ML (again);
wenzelm
parents:
diff changeset
   126
26551
da1cd11d8a25 renamed parse_comment_whspc to parse_comments;
wenzelm
parents: 26546
diff changeset
   127
val parse_comment =
da1cd11d8a25 renamed parse_comment_whspc to parse_comments;
wenzelm
parents: 26546
diff changeset
   128
  Scan.this_string "<!--" --
da1cd11d8a25 renamed parse_comment_whspc to parse_comments;
wenzelm
parents: 26546
diff changeset
   129
  Scan.repeat (Scan.unless (Scan.this_string "-->") regular) --
26984
d0e098e206f3 added parse_document (optional unchecked header material);
wenzelm
parents: 26554
diff changeset
   130
  Scan.this_string "-->" >> ignored;
24264
d6935e7dac8b moved Tools/xml.ML to General/xml.ML (again);
wenzelm
parents:
diff changeset
   131
26551
da1cd11d8a25 renamed parse_comment_whspc to parse_comments;
wenzelm
parents: 26546
diff changeset
   132
val parse_processing_instruction =
da1cd11d8a25 renamed parse_comment_whspc to parse_comments;
wenzelm
parents: 26546
diff changeset
   133
  Scan.this_string "<?" --
da1cd11d8a25 renamed parse_comment_whspc to parse_comments;
wenzelm
parents: 26546
diff changeset
   134
  Scan.repeat (Scan.unless (Scan.this_string "?>") regular) --
26984
d0e098e206f3 added parse_document (optional unchecked header material);
wenzelm
parents: 26554
diff changeset
   135
  Scan.this_string "?>" >> ignored;
d0e098e206f3 added parse_document (optional unchecked header material);
wenzelm
parents: 26554
diff changeset
   136
d0e098e206f3 added parse_document (optional unchecked header material);
wenzelm
parents: 26554
diff changeset
   137
val parse_doctype =
d0e098e206f3 added parse_document (optional unchecked header material);
wenzelm
parents: 26554
diff changeset
   138
  Scan.this_string "<!DOCTYPE" --
d0e098e206f3 added parse_document (optional unchecked header material);
wenzelm
parents: 26554
diff changeset
   139
  Scan.repeat (Scan.unless ($$ ">") regular) --
d0e098e206f3 added parse_document (optional unchecked header material);
wenzelm
parents: 26554
diff changeset
   140
  $$ ">" >> ignored;
d0e098e206f3 added parse_document (optional unchecked header material);
wenzelm
parents: 26554
diff changeset
   141
d0e098e206f3 added parse_document (optional unchecked header material);
wenzelm
parents: 26554
diff changeset
   142
val parse_misc =
d0e098e206f3 added parse_document (optional unchecked header material);
wenzelm
parents: 26554
diff changeset
   143
  Scan.one Symbol.is_blank >> ignored ||
d0e098e206f3 added parse_document (optional unchecked header material);
wenzelm
parents: 26554
diff changeset
   144
  parse_processing_instruction ||
d0e098e206f3 added parse_document (optional unchecked header material);
wenzelm
parents: 26554
diff changeset
   145
  parse_comment;
26551
da1cd11d8a25 renamed parse_comment_whspc to parse_comments;
wenzelm
parents: 26546
diff changeset
   146
da1cd11d8a25 renamed parse_comment_whspc to parse_comments;
wenzelm
parents: 26546
diff changeset
   147
val parse_optional_text =
da1cd11d8a25 renamed parse_comment_whspc to parse_comments;
wenzelm
parents: 26546
diff changeset
   148
  Scan.optional (parse_chars >> (single o Text)) [];
24264
d6935e7dac8b moved Tools/xml.ML to General/xml.ML (again);
wenzelm
parents:
diff changeset
   149
26546
ba4cdf92c7c4 further cleanup of XML signature;
wenzelm
parents: 26539
diff changeset
   150
in
ba4cdf92c7c4 further cleanup of XML signature;
wenzelm
parents: 26539
diff changeset
   151
26984
d0e098e206f3 added parse_document (optional unchecked header material);
wenzelm
parents: 26554
diff changeset
   152
val parse_comments =
d0e098e206f3 added parse_document (optional unchecked header material);
wenzelm
parents: 26554
diff changeset
   153
  blanks -- Scan.repeat (parse_comment -- blanks >> K ()) >> K ();
d0e098e206f3 added parse_document (optional unchecked header material);
wenzelm
parents: 26554
diff changeset
   154
26546
ba4cdf92c7c4 further cleanup of XML signature;
wenzelm
parents: 26539
diff changeset
   155
val parse_string = Scan.read Symbol.stopper parse_chars o explode;
ba4cdf92c7c4 further cleanup of XML signature;
wenzelm
parents: 26539
diff changeset
   156
24264
d6935e7dac8b moved Tools/xml.ML to General/xml.ML (again);
wenzelm
parents:
diff changeset
   157
fun parse_content xs =
26551
da1cd11d8a25 renamed parse_comment_whspc to parse_comments;
wenzelm
parents: 26546
diff changeset
   158
  (parse_optional_text @@@
da1cd11d8a25 renamed parse_comment_whspc to parse_comments;
wenzelm
parents: 26546
diff changeset
   159
    (Scan.repeat
da1cd11d8a25 renamed parse_comment_whspc to parse_comments;
wenzelm
parents: 26546
diff changeset
   160
      ((parse_element >> single ||
da1cd11d8a25 renamed parse_comment_whspc to parse_comments;
wenzelm
parents: 26546
diff changeset
   161
        parse_cdata >> (single o Text) ||
26984
d0e098e206f3 added parse_document (optional unchecked header material);
wenzelm
parents: 26554
diff changeset
   162
        parse_processing_instruction ||
d0e098e206f3 added parse_document (optional unchecked header material);
wenzelm
parents: 26554
diff changeset
   163
        parse_comment)
26551
da1cd11d8a25 renamed parse_comment_whspc to parse_comments;
wenzelm
parents: 26546
diff changeset
   164
      @@@ parse_optional_text) >> flat)) xs
24264
d6935e7dac8b moved Tools/xml.ML to General/xml.ML (again);
wenzelm
parents:
diff changeset
   165
26546
ba4cdf92c7c4 further cleanup of XML signature;
wenzelm
parents: 26539
diff changeset
   166
and parse_element xs =
24264
d6935e7dac8b moved Tools/xml.ML to General/xml.ML (again);
wenzelm
parents:
diff changeset
   167
  ($$ "<" |-- Symbol.scan_id --
26551
da1cd11d8a25 renamed parse_comment_whspc to parse_comments;
wenzelm
parents: 26546
diff changeset
   168
    Scan.repeat (blanks |-- parse_att) --| blanks :-- (fn (s, _) =>
24264
d6935e7dac8b moved Tools/xml.ML to General/xml.ML (again);
wenzelm
parents:
diff changeset
   169
      !! (err "Expected > or />")
26984
d0e098e206f3 added parse_document (optional unchecked header material);
wenzelm
parents: 26554
diff changeset
   170
        (Scan.this_string "/>" >> ignored
24264
d6935e7dac8b moved Tools/xml.ML to General/xml.ML (again);
wenzelm
parents:
diff changeset
   171
         || $$ ">" |-- parse_content --|
d6935e7dac8b moved Tools/xml.ML to General/xml.ML (again);
wenzelm
parents:
diff changeset
   172
            !! (err ("Expected </" ^ s ^ ">"))
26551
da1cd11d8a25 renamed parse_comment_whspc to parse_comments;
wenzelm
parents: 26546
diff changeset
   173
              (Scan.this_string ("</" ^ s) --| blanks --| $$ ">"))) >>
24264
d6935e7dac8b moved Tools/xml.ML to General/xml.ML (again);
wenzelm
parents:
diff changeset
   174
    (fn ((s, atts), ts) => Elem (s, atts, ts))) xs;
d6935e7dac8b moved Tools/xml.ML to General/xml.ML (again);
wenzelm
parents:
diff changeset
   175
26984
d0e098e206f3 added parse_document (optional unchecked header material);
wenzelm
parents: 26554
diff changeset
   176
val parse_document =
d0e098e206f3 added parse_document (optional unchecked header material);
wenzelm
parents: 26554
diff changeset
   177
  (Scan.repeat parse_misc -- Scan.option parse_doctype -- Scan.repeat parse_misc)
d0e098e206f3 added parse_document (optional unchecked header material);
wenzelm
parents: 26554
diff changeset
   178
  |-- parse_element;
24264
d6935e7dac8b moved Tools/xml.ML to General/xml.ML (again);
wenzelm
parents:
diff changeset
   179
26539
a0754be538ab added output_markup (from Tools/isabelle_process.ML);
wenzelm
parents: 26525
diff changeset
   180
fun parse s =
24264
d6935e7dac8b moved Tools/xml.ML to General/xml.ML (again);
wenzelm
parents:
diff changeset
   181
  (case Scan.finite Symbol.stopper (Scan.error (!! (err "Malformed element")
26984
d0e098e206f3 added parse_document (optional unchecked header material);
wenzelm
parents: 26554
diff changeset
   182
      (blanks |-- parse_document --| blanks))) (explode s) of
24264
d6935e7dac8b moved Tools/xml.ML to General/xml.ML (again);
wenzelm
parents:
diff changeset
   183
    (x, []) => x
d6935e7dac8b moved Tools/xml.ML to General/xml.ML (again);
wenzelm
parents:
diff changeset
   184
  | (_, ys) => error ("XML parsing error: Unprocessed input\n" ^ Symbol.beginning 100 ys));
d6935e7dac8b moved Tools/xml.ML to General/xml.ML (again);
wenzelm
parents:
diff changeset
   185
d6935e7dac8b moved Tools/xml.ML to General/xml.ML (again);
wenzelm
parents:
diff changeset
   186
end;
26546
ba4cdf92c7c4 further cleanup of XML signature;
wenzelm
parents: 26539
diff changeset
   187
ba4cdf92c7c4 further cleanup of XML signature;
wenzelm
parents: 26539
diff changeset
   188
end;