src/Pure/General/xml.ML
author wenzelm
Mon, 20 Sep 2010 15:08:51 +0200
changeset 39555 ccb223a4d49c
parent 38474 e498dc2eb576
child 40131 7cbebd636e79
permissions -rw-r--r--
added XML.content_of convenience -- cover XML.body, which is the general situation;
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
38228
ada3ab6b9085 simplified type XML.tree: embed Markup.T directly, avoid slightly odd triple;
wenzelm
parents: 31469
diff changeset
     4
Simple XML tree values.
24264
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 =
38228
ada3ab6b9085 simplified type XML.tree: embed Markup.T directly, avoid slightly odd triple;
wenzelm
parents: 31469
diff changeset
    11
      Elem of Markup.T * tree list
24264
d6935e7dac8b moved Tools/xml.ML to General/xml.ML (again);
wenzelm
parents:
diff changeset
    12
    | Text of string
38266
492d377ecfe2 type XML.body as basic data representation language;
wenzelm
parents: 38228
diff changeset
    13
  type body = tree list
26546
ba4cdf92c7c4 further cleanup of XML signature;
wenzelm
parents: 26539
diff changeset
    14
  val add_content: tree -> Buffer.T -> Buffer.T
39555
ccb223a4d49c added XML.content_of convenience -- cover XML.body, which is the general situation;
wenzelm
parents: 38474
diff changeset
    15
  val content_of: body -> string
26546
ba4cdf92c7c4 further cleanup of XML signature;
wenzelm
parents: 26539
diff changeset
    16
  val header: string
ba4cdf92c7c4 further cleanup of XML signature;
wenzelm
parents: 26539
diff changeset
    17
  val text: string -> string
ba4cdf92c7c4 further cleanup of XML signature;
wenzelm
parents: 26539
diff changeset
    18
  val element: string -> attributes -> string list -> string
ba4cdf92c7c4 further cleanup of XML signature;
wenzelm
parents: 26539
diff changeset
    19
  val output_markup: Markup.T -> output * output
26539
a0754be538ab added output_markup (from Tools/isabelle_process.ML);
wenzelm
parents: 26525
diff changeset
    20
  val string_of: tree -> string
26546
ba4cdf92c7c4 further cleanup of XML signature;
wenzelm
parents: 26539
diff changeset
    21
  val output: tree -> TextIO.outstream -> unit
26984
d0e098e206f3 added parse_document (optional unchecked header material);
wenzelm
parents: 26554
diff changeset
    22
  val parse_comments: string list -> unit * string list
24264
d6935e7dac8b moved Tools/xml.ML to General/xml.ML (again);
wenzelm
parents:
diff changeset
    23
  val parse_string : string -> string option
26546
ba4cdf92c7c4 further cleanup of XML signature;
wenzelm
parents: 26539
diff changeset
    24
  val parse_element: string list -> tree * string list
26984
d0e098e206f3 added parse_document (optional unchecked header material);
wenzelm
parents: 26554
diff changeset
    25
  val parse_document: string list -> tree * string list
26539
a0754be538ab added output_markup (from Tools/isabelle_process.ML);
wenzelm
parents: 26525
diff changeset
    26
  val parse: string -> tree
24264
d6935e7dac8b moved Tools/xml.ML to General/xml.ML (again);
wenzelm
parents:
diff changeset
    27
end;
d6935e7dac8b moved Tools/xml.ML to General/xml.ML (again);
wenzelm
parents:
diff changeset
    28
d6935e7dac8b moved Tools/xml.ML to General/xml.ML (again);
wenzelm
parents:
diff changeset
    29
structure XML: XML =
d6935e7dac8b moved Tools/xml.ML to General/xml.ML (again);
wenzelm
parents:
diff changeset
    30
struct
d6935e7dac8b moved Tools/xml.ML to General/xml.ML (again);
wenzelm
parents:
diff changeset
    31
26546
ba4cdf92c7c4 further cleanup of XML signature;
wenzelm
parents: 26539
diff changeset
    32
(** XML trees **)
ba4cdf92c7c4 further cleanup of XML signature;
wenzelm
parents: 26539
diff changeset
    33
28017
4919bd124a58 type Properties.T;
wenzelm
parents: 27884
diff changeset
    34
type attributes = Properties.T;
26546
ba4cdf92c7c4 further cleanup of XML signature;
wenzelm
parents: 26539
diff changeset
    35
ba4cdf92c7c4 further cleanup of XML signature;
wenzelm
parents: 26539
diff changeset
    36
datatype tree =
38228
ada3ab6b9085 simplified type XML.tree: embed Markup.T directly, avoid slightly odd triple;
wenzelm
parents: 31469
diff changeset
    37
    Elem of Markup.T * tree list
28033
f03b5856f286 removed obsolete XML.Output workaround;
wenzelm
parents: 28017
diff changeset
    38
  | Text of string;
26546
ba4cdf92c7c4 further cleanup of XML signature;
wenzelm
parents: 26539
diff changeset
    39
38266
492d377ecfe2 type XML.body as basic data representation language;
wenzelm
parents: 38228
diff changeset
    40
type body = tree list;
492d377ecfe2 type XML.body as basic data representation language;
wenzelm
parents: 38228
diff changeset
    41
38228
ada3ab6b9085 simplified type XML.tree: embed Markup.T directly, avoid slightly odd triple;
wenzelm
parents: 31469
diff changeset
    42
fun add_content (Elem (_, ts)) = fold add_content ts
28033
f03b5856f286 removed obsolete XML.Output workaround;
wenzelm
parents: 28017
diff changeset
    43
  | add_content (Text s) = Buffer.add s;
26546
ba4cdf92c7c4 further cleanup of XML signature;
wenzelm
parents: 26539
diff changeset
    44
39555
ccb223a4d49c added XML.content_of convenience -- cover XML.body, which is the general situation;
wenzelm
parents: 38474
diff changeset
    45
fun content_of body = Buffer.empty |> fold add_content body |> Buffer.content;
ccb223a4d49c added XML.content_of convenience -- cover XML.body, which is the general situation;
wenzelm
parents: 38474
diff changeset
    46
26546
ba4cdf92c7c4 further cleanup of XML signature;
wenzelm
parents: 26539
diff changeset
    47
24264
d6935e7dac8b moved Tools/xml.ML to General/xml.ML (again);
wenzelm
parents:
diff changeset
    48
26525
14a56f013469 added detect;
wenzelm
parents: 25838
diff changeset
    49
(** string representation **)
14a56f013469 added detect;
wenzelm
parents: 25838
diff changeset
    50
24264
d6935e7dac8b moved Tools/xml.ML to General/xml.ML (again);
wenzelm
parents:
diff changeset
    51
val header = "<?xml version=\"1.0\"?>\n";
d6935e7dac8b moved Tools/xml.ML to General/xml.ML (again);
wenzelm
parents:
diff changeset
    52
d6935e7dac8b moved Tools/xml.ML to General/xml.ML (again);
wenzelm
parents:
diff changeset
    53
26546
ba4cdf92c7c4 further cleanup of XML signature;
wenzelm
parents: 26539
diff changeset
    54
(* escaped text *)
24264
d6935e7dac8b moved Tools/xml.ML to General/xml.ML (again);
wenzelm
parents:
diff changeset
    55
d6935e7dac8b moved Tools/xml.ML to General/xml.ML (again);
wenzelm
parents:
diff changeset
    56
fun decode "&lt;" = "<"
d6935e7dac8b moved Tools/xml.ML to General/xml.ML (again);
wenzelm
parents:
diff changeset
    57
  | decode "&gt;" = ">"
d6935e7dac8b moved Tools/xml.ML to General/xml.ML (again);
wenzelm
parents:
diff changeset
    58
  | decode "&amp;" = "&"
d6935e7dac8b moved Tools/xml.ML to General/xml.ML (again);
wenzelm
parents:
diff changeset
    59
  | decode "&apos;" = "'"
d6935e7dac8b moved Tools/xml.ML to General/xml.ML (again);
wenzelm
parents:
diff changeset
    60
  | decode "&quot;" = "\""
d6935e7dac8b moved Tools/xml.ML to General/xml.ML (again);
wenzelm
parents:
diff changeset
    61
  | decode c = c;
d6935e7dac8b moved Tools/xml.ML to General/xml.ML (again);
wenzelm
parents:
diff changeset
    62
d6935e7dac8b moved Tools/xml.ML to General/xml.ML (again);
wenzelm
parents:
diff changeset
    63
fun encode "<" = "&lt;"
d6935e7dac8b moved Tools/xml.ML to General/xml.ML (again);
wenzelm
parents:
diff changeset
    64
  | encode ">" = "&gt;"
d6935e7dac8b moved Tools/xml.ML to General/xml.ML (again);
wenzelm
parents:
diff changeset
    65
  | encode "&" = "&amp;"
d6935e7dac8b moved Tools/xml.ML to General/xml.ML (again);
wenzelm
parents:
diff changeset
    66
  | encode "'" = "&apos;"
d6935e7dac8b moved Tools/xml.ML to General/xml.ML (again);
wenzelm
parents:
diff changeset
    67
  | encode "\"" = "&quot;"
d6935e7dac8b moved Tools/xml.ML to General/xml.ML (again);
wenzelm
parents:
diff changeset
    68
  | encode c = c;
d6935e7dac8b moved Tools/xml.ML to General/xml.ML (again);
wenzelm
parents:
diff changeset
    69
25838
00b2a1b2c4e9 removed unused text_charref, cdata;
wenzelm
parents: 24584
diff changeset
    70
val text = translate_string encode;
24264
d6935e7dac8b moved Tools/xml.ML to General/xml.ML (again);
wenzelm
parents:
diff changeset
    71
d6935e7dac8b moved Tools/xml.ML to General/xml.ML (again);
wenzelm
parents:
diff changeset
    72
d6935e7dac8b moved Tools/xml.ML to General/xml.ML (again);
wenzelm
parents:
diff changeset
    73
(* elements *)
d6935e7dac8b moved Tools/xml.ML to General/xml.ML (again);
wenzelm
parents:
diff changeset
    74
26539
a0754be538ab added output_markup (from Tools/isabelle_process.ML);
wenzelm
parents: 26525
diff changeset
    75
fun elem name atts =
26551
da1cd11d8a25 renamed parse_comment_whspc to parse_comments;
wenzelm
parents: 26546
diff changeset
    76
  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
    77
26525
14a56f013469 added detect;
wenzelm
parents: 25838
diff changeset
    78
fun element name atts body =
26539
a0754be538ab added output_markup (from Tools/isabelle_process.ML);
wenzelm
parents: 26525
diff changeset
    79
  let val b = implode body in
a0754be538ab added output_markup (from Tools/isabelle_process.ML);
wenzelm
parents: 26525
diff changeset
    80
    if b = "" then enclose "<" "/>" (elem name atts)
a0754be538ab added output_markup (from Tools/isabelle_process.ML);
wenzelm
parents: 26525
diff changeset
    81
    else enclose "<" ">" (elem name atts) ^ b ^ enclose "</" ">" name
24264
d6935e7dac8b moved Tools/xml.ML to General/xml.ML (again);
wenzelm
parents:
diff changeset
    82
  end;
d6935e7dac8b moved Tools/xml.ML to General/xml.ML (again);
wenzelm
parents:
diff changeset
    83
27884
10c927e4abf5 output_markup: check Markup.is_none;
wenzelm
parents: 26984
diff changeset
    84
fun output_markup (markup as (name, atts)) =
38474
e498dc2eb576 uniform Markup.empty/Markup.Empty in ML and Scala;
wenzelm
parents: 38266
diff changeset
    85
  if Markup.is_empty markup then Markup.no_output
27884
10c927e4abf5 output_markup: check Markup.is_none;
wenzelm
parents: 26984
diff changeset
    86
  else (enclose "<" ">" (elem name atts), enclose "</" ">" name);
26539
a0754be538ab added output_markup (from Tools/isabelle_process.ML);
wenzelm
parents: 26525
diff changeset
    87
24264
d6935e7dac8b moved Tools/xml.ML to General/xml.ML (again);
wenzelm
parents:
diff changeset
    88
26546
ba4cdf92c7c4 further cleanup of XML signature;
wenzelm
parents: 26539
diff changeset
    89
(* output *)
24264
d6935e7dac8b moved Tools/xml.ML to General/xml.ML (again);
wenzelm
parents:
diff changeset
    90
26546
ba4cdf92c7c4 further cleanup of XML signature;
wenzelm
parents: 26539
diff changeset
    91
fun buffer_of tree =
24264
d6935e7dac8b moved Tools/xml.ML to General/xml.ML (again);
wenzelm
parents:
diff changeset
    92
  let
38228
ada3ab6b9085 simplified type XML.tree: embed Markup.T directly, avoid slightly odd triple;
wenzelm
parents: 31469
diff changeset
    93
    fun traverse (Elem ((name, atts), [])) =
26539
a0754be538ab added output_markup (from Tools/isabelle_process.ML);
wenzelm
parents: 26525
diff changeset
    94
          Buffer.add "<" #> Buffer.add (elem name atts) #> Buffer.add "/>"
38228
ada3ab6b9085 simplified type XML.tree: embed Markup.T directly, avoid slightly odd triple;
wenzelm
parents: 31469
diff changeset
    95
      | traverse (Elem ((name, atts), ts)) =
26539
a0754be538ab added output_markup (from Tools/isabelle_process.ML);
wenzelm
parents: 26525
diff changeset
    96
          Buffer.add "<" #> Buffer.add (elem name atts) #> Buffer.add ">" #>
26546
ba4cdf92c7c4 further cleanup of XML signature;
wenzelm
parents: 26539
diff changeset
    97
          fold traverse ts #>
26525
14a56f013469 added detect;
wenzelm
parents: 25838
diff changeset
    98
          Buffer.add "</" #> Buffer.add name #> Buffer.add ">"
28033
f03b5856f286 removed obsolete XML.Output workaround;
wenzelm
parents: 28017
diff changeset
    99
      | traverse (Text s) = Buffer.add (text s);
26546
ba4cdf92c7c4 further cleanup of XML signature;
wenzelm
parents: 26539
diff changeset
   100
  in Buffer.empty |> traverse tree end;
24264
d6935e7dac8b moved Tools/xml.ML to General/xml.ML (again);
wenzelm
parents:
diff changeset
   101
26546
ba4cdf92c7c4 further cleanup of XML signature;
wenzelm
parents: 26539
diff changeset
   102
val string_of = Buffer.content o buffer_of;
ba4cdf92c7c4 further cleanup of XML signature;
wenzelm
parents: 26539
diff changeset
   103
val output = Buffer.output o buffer_of;
25838
00b2a1b2c4e9 removed unused text_charref, cdata;
wenzelm
parents: 24584
diff changeset
   104
24264
d6935e7dac8b moved Tools/xml.ML to General/xml.ML (again);
wenzelm
parents:
diff changeset
   105
d6935e7dac8b moved Tools/xml.ML to General/xml.ML (again);
wenzelm
parents:
diff changeset
   106
26546
ba4cdf92c7c4 further cleanup of XML signature;
wenzelm
parents: 26539
diff changeset
   107
(** XML parsing (slow) **)
ba4cdf92c7c4 further cleanup of XML signature;
wenzelm
parents: 26539
diff changeset
   108
ba4cdf92c7c4 further cleanup of XML signature;
wenzelm
parents: 26539
diff changeset
   109
local
24264
d6935e7dac8b moved Tools/xml.ML to General/xml.ML (again);
wenzelm
parents:
diff changeset
   110
d6935e7dac8b moved Tools/xml.ML to General/xml.ML (again);
wenzelm
parents:
diff changeset
   111
fun err s (xs, _) =
d6935e7dac8b moved Tools/xml.ML to General/xml.ML (again);
wenzelm
parents:
diff changeset
   112
  "XML parsing error: " ^ s ^ "\nfound: " ^ quote (Symbol.beginning 100 xs);
d6935e7dac8b moved Tools/xml.ML to General/xml.ML (again);
wenzelm
parents:
diff changeset
   113
26984
d0e098e206f3 added parse_document (optional unchecked header material);
wenzelm
parents: 26554
diff changeset
   114
fun ignored _ = [];
d0e098e206f3 added parse_document (optional unchecked header material);
wenzelm
parents: 26554
diff changeset
   115
26551
da1cd11d8a25 renamed parse_comment_whspc to parse_comments;
wenzelm
parents: 26546
diff changeset
   116
val blanks = Scan.many Symbol.is_blank;
da1cd11d8a25 renamed parse_comment_whspc to parse_comments;
wenzelm
parents: 26546
diff changeset
   117
val special = $$ "&" ^^ Symbol.scan_id ^^ $$ ";" >> decode;
da1cd11d8a25 renamed parse_comment_whspc to parse_comments;
wenzelm
parents: 26546
diff changeset
   118
val regular = Scan.one Symbol.is_regular;
da1cd11d8a25 renamed parse_comment_whspc to parse_comments;
wenzelm
parents: 26546
diff changeset
   119
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
   120
26551
da1cd11d8a25 renamed parse_comment_whspc to parse_comments;
wenzelm
parents: 26546
diff changeset
   121
val parse_chars = Scan.repeat1 (special || regular_except "<") >> implode;
24264
d6935e7dac8b moved Tools/xml.ML to General/xml.ML (again);
wenzelm
parents:
diff changeset
   122
26551
da1cd11d8a25 renamed parse_comment_whspc to parse_comments;
wenzelm
parents: 26546
diff changeset
   123
val parse_cdata =
da1cd11d8a25 renamed parse_comment_whspc to parse_comments;
wenzelm
parents: 26546
diff changeset
   124
  Scan.this_string "<![CDATA[" |--
da1cd11d8a25 renamed parse_comment_whspc to parse_comments;
wenzelm
parents: 26546
diff changeset
   125
  (Scan.repeat (Scan.unless (Scan.this_string "]]>") regular) >> implode) --|
da1cd11d8a25 renamed parse_comment_whspc to parse_comments;
wenzelm
parents: 26546
diff changeset
   126
  Scan.this_string "]]>";
24264
d6935e7dac8b moved Tools/xml.ML to General/xml.ML (again);
wenzelm
parents:
diff changeset
   127
d6935e7dac8b moved Tools/xml.ML to General/xml.ML (again);
wenzelm
parents:
diff changeset
   128
val parse_att =
26551
da1cd11d8a25 renamed parse_comment_whspc to parse_comments;
wenzelm
parents: 26546
diff changeset
   129
  (Symbol.scan_id --| (blanks -- $$ "=" -- blanks)) --
da1cd11d8a25 renamed parse_comment_whspc to parse_comments;
wenzelm
parents: 26546
diff changeset
   130
  (($$ "\"" || $$ "'") :|-- (fn s =>
da1cd11d8a25 renamed parse_comment_whspc to parse_comments;
wenzelm
parents: 26546
diff changeset
   131
    (Scan.repeat (special || regular_except s) >> implode) --| $$ s));
24264
d6935e7dac8b moved Tools/xml.ML to General/xml.ML (again);
wenzelm
parents:
diff changeset
   132
26551
da1cd11d8a25 renamed parse_comment_whspc to parse_comments;
wenzelm
parents: 26546
diff changeset
   133
val parse_comment =
da1cd11d8a25 renamed parse_comment_whspc to parse_comments;
wenzelm
parents: 26546
diff changeset
   134
  Scan.this_string "<!--" --
da1cd11d8a25 renamed parse_comment_whspc to parse_comments;
wenzelm
parents: 26546
diff changeset
   135
  Scan.repeat (Scan.unless (Scan.this_string "-->") regular) --
26984
d0e098e206f3 added parse_document (optional unchecked header material);
wenzelm
parents: 26554
diff changeset
   136
  Scan.this_string "-->" >> ignored;
24264
d6935e7dac8b moved Tools/xml.ML to General/xml.ML (again);
wenzelm
parents:
diff changeset
   137
26551
da1cd11d8a25 renamed parse_comment_whspc to parse_comments;
wenzelm
parents: 26546
diff changeset
   138
val parse_processing_instruction =
da1cd11d8a25 renamed parse_comment_whspc to parse_comments;
wenzelm
parents: 26546
diff changeset
   139
  Scan.this_string "<?" --
da1cd11d8a25 renamed parse_comment_whspc to parse_comments;
wenzelm
parents: 26546
diff changeset
   140
  Scan.repeat (Scan.unless (Scan.this_string "?>") regular) --
26984
d0e098e206f3 added parse_document (optional unchecked header material);
wenzelm
parents: 26554
diff changeset
   141
  Scan.this_string "?>" >> ignored;
d0e098e206f3 added parse_document (optional unchecked header material);
wenzelm
parents: 26554
diff changeset
   142
d0e098e206f3 added parse_document (optional unchecked header material);
wenzelm
parents: 26554
diff changeset
   143
val parse_doctype =
d0e098e206f3 added parse_document (optional unchecked header material);
wenzelm
parents: 26554
diff changeset
   144
  Scan.this_string "<!DOCTYPE" --
d0e098e206f3 added parse_document (optional unchecked header material);
wenzelm
parents: 26554
diff changeset
   145
  Scan.repeat (Scan.unless ($$ ">") regular) --
d0e098e206f3 added parse_document (optional unchecked header material);
wenzelm
parents: 26554
diff changeset
   146
  $$ ">" >> ignored;
d0e098e206f3 added parse_document (optional unchecked header material);
wenzelm
parents: 26554
diff changeset
   147
d0e098e206f3 added parse_document (optional unchecked header material);
wenzelm
parents: 26554
diff changeset
   148
val parse_misc =
d0e098e206f3 added parse_document (optional unchecked header material);
wenzelm
parents: 26554
diff changeset
   149
  Scan.one Symbol.is_blank >> ignored ||
d0e098e206f3 added parse_document (optional unchecked header material);
wenzelm
parents: 26554
diff changeset
   150
  parse_processing_instruction ||
d0e098e206f3 added parse_document (optional unchecked header material);
wenzelm
parents: 26554
diff changeset
   151
  parse_comment;
26551
da1cd11d8a25 renamed parse_comment_whspc to parse_comments;
wenzelm
parents: 26546
diff changeset
   152
da1cd11d8a25 renamed parse_comment_whspc to parse_comments;
wenzelm
parents: 26546
diff changeset
   153
val parse_optional_text =
da1cd11d8a25 renamed parse_comment_whspc to parse_comments;
wenzelm
parents: 26546
diff changeset
   154
  Scan.optional (parse_chars >> (single o Text)) [];
24264
d6935e7dac8b moved Tools/xml.ML to General/xml.ML (again);
wenzelm
parents:
diff changeset
   155
26546
ba4cdf92c7c4 further cleanup of XML signature;
wenzelm
parents: 26539
diff changeset
   156
in
ba4cdf92c7c4 further cleanup of XML signature;
wenzelm
parents: 26539
diff changeset
   157
26984
d0e098e206f3 added parse_document (optional unchecked header material);
wenzelm
parents: 26554
diff changeset
   158
val parse_comments =
d0e098e206f3 added parse_document (optional unchecked header material);
wenzelm
parents: 26554
diff changeset
   159
  blanks -- Scan.repeat (parse_comment -- blanks >> K ()) >> K ();
d0e098e206f3 added parse_document (optional unchecked header material);
wenzelm
parents: 26554
diff changeset
   160
26546
ba4cdf92c7c4 further cleanup of XML signature;
wenzelm
parents: 26539
diff changeset
   161
val parse_string = Scan.read Symbol.stopper parse_chars o explode;
ba4cdf92c7c4 further cleanup of XML signature;
wenzelm
parents: 26539
diff changeset
   162
24264
d6935e7dac8b moved Tools/xml.ML to General/xml.ML (again);
wenzelm
parents:
diff changeset
   163
fun parse_content xs =
26551
da1cd11d8a25 renamed parse_comment_whspc to parse_comments;
wenzelm
parents: 26546
diff changeset
   164
  (parse_optional_text @@@
da1cd11d8a25 renamed parse_comment_whspc to parse_comments;
wenzelm
parents: 26546
diff changeset
   165
    (Scan.repeat
da1cd11d8a25 renamed parse_comment_whspc to parse_comments;
wenzelm
parents: 26546
diff changeset
   166
      ((parse_element >> single ||
da1cd11d8a25 renamed parse_comment_whspc to parse_comments;
wenzelm
parents: 26546
diff changeset
   167
        parse_cdata >> (single o Text) ||
26984
d0e098e206f3 added parse_document (optional unchecked header material);
wenzelm
parents: 26554
diff changeset
   168
        parse_processing_instruction ||
d0e098e206f3 added parse_document (optional unchecked header material);
wenzelm
parents: 26554
diff changeset
   169
        parse_comment)
26551
da1cd11d8a25 renamed parse_comment_whspc to parse_comments;
wenzelm
parents: 26546
diff changeset
   170
      @@@ parse_optional_text) >> flat)) xs
24264
d6935e7dac8b moved Tools/xml.ML to General/xml.ML (again);
wenzelm
parents:
diff changeset
   171
26546
ba4cdf92c7c4 further cleanup of XML signature;
wenzelm
parents: 26539
diff changeset
   172
and parse_element xs =
24264
d6935e7dac8b moved Tools/xml.ML to General/xml.ML (again);
wenzelm
parents:
diff changeset
   173
  ($$ "<" |-- Symbol.scan_id --
26551
da1cd11d8a25 renamed parse_comment_whspc to parse_comments;
wenzelm
parents: 26546
diff changeset
   174
    Scan.repeat (blanks |-- parse_att) --| blanks :-- (fn (s, _) =>
24264
d6935e7dac8b moved Tools/xml.ML to General/xml.ML (again);
wenzelm
parents:
diff changeset
   175
      !! (err "Expected > or />")
26984
d0e098e206f3 added parse_document (optional unchecked header material);
wenzelm
parents: 26554
diff changeset
   176
        (Scan.this_string "/>" >> ignored
24264
d6935e7dac8b moved Tools/xml.ML to General/xml.ML (again);
wenzelm
parents:
diff changeset
   177
         || $$ ">" |-- parse_content --|
d6935e7dac8b moved Tools/xml.ML to General/xml.ML (again);
wenzelm
parents:
diff changeset
   178
            !! (err ("Expected </" ^ s ^ ">"))
38228
ada3ab6b9085 simplified type XML.tree: embed Markup.T directly, avoid slightly odd triple;
wenzelm
parents: 31469
diff changeset
   179
              (Scan.this_string ("</" ^ s) --| blanks --| $$ ">"))) >> Elem) xs;
24264
d6935e7dac8b moved Tools/xml.ML to General/xml.ML (again);
wenzelm
parents:
diff changeset
   180
26984
d0e098e206f3 added parse_document (optional unchecked header material);
wenzelm
parents: 26554
diff changeset
   181
val parse_document =
d0e098e206f3 added parse_document (optional unchecked header material);
wenzelm
parents: 26554
diff changeset
   182
  (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
   183
  |-- parse_element;
24264
d6935e7dac8b moved Tools/xml.ML to General/xml.ML (again);
wenzelm
parents:
diff changeset
   184
26539
a0754be538ab added output_markup (from Tools/isabelle_process.ML);
wenzelm
parents: 26525
diff changeset
   185
fun parse s =
24264
d6935e7dac8b moved Tools/xml.ML to General/xml.ML (again);
wenzelm
parents:
diff changeset
   186
  (case Scan.finite Symbol.stopper (Scan.error (!! (err "Malformed element")
26984
d0e098e206f3 added parse_document (optional unchecked header material);
wenzelm
parents: 26554
diff changeset
   187
      (blanks |-- parse_document --| blanks))) (explode s) of
24264
d6935e7dac8b moved Tools/xml.ML to General/xml.ML (again);
wenzelm
parents:
diff changeset
   188
    (x, []) => x
d6935e7dac8b moved Tools/xml.ML to General/xml.ML (again);
wenzelm
parents:
diff changeset
   189
  | (_, 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
   190
d6935e7dac8b moved Tools/xml.ML to General/xml.ML (again);
wenzelm
parents:
diff changeset
   191
end;
26546
ba4cdf92c7c4 further cleanup of XML signature;
wenzelm
parents: 26539
diff changeset
   192
ba4cdf92c7c4 further cleanup of XML signature;
wenzelm
parents: 26539
diff changeset
   193
end;