src/Pure/General/mailman.scala
author wenzelm
Tue, 14 Dec 2021 17:22:40 +0100
changeset 74935 dc62948c6080
parent 74934 f5ad3214bef4
child 74936 4c166d510b65
permissions -rw-r--r--
more data integrity: name vs. address;
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
72558
38ebf696fd0c support for Mailman list servers;
wenzelm
parents:
diff changeset
     1
/*  Title:      Pure/General/mailman.scala
38ebf696fd0c support for Mailman list servers;
wenzelm
parents:
diff changeset
     2
    Author:     Makarius
38ebf696fd0c support for Mailman list servers;
wenzelm
parents:
diff changeset
     3
38ebf696fd0c support for Mailman list servers;
wenzelm
parents:
diff changeset
     4
Support for Mailman list servers.
38ebf696fd0c support for Mailman list servers;
wenzelm
parents:
diff changeset
     5
*/
38ebf696fd0c support for Mailman list servers;
wenzelm
parents:
diff changeset
     6
38ebf696fd0c support for Mailman list servers;
wenzelm
parents:
diff changeset
     7
package isabelle
38ebf696fd0c support for Mailman list servers;
wenzelm
parents:
diff changeset
     8
38ebf696fd0c support for Mailman list servers;
wenzelm
parents:
diff changeset
     9
38ebf696fd0c support for Mailman list servers;
wenzelm
parents:
diff changeset
    10
import java.net.URL
38ebf696fd0c support for Mailman list servers;
wenzelm
parents:
diff changeset
    11
74921
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
    12
import scala.annotation.tailrec
74906
9702913db56c more Mailman content;
wenzelm
parents: 74905
diff changeset
    13
import scala.util.matching.Regex
74921
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
    14
import scala.util.matching.Regex.Match
74906
9702913db56c more Mailman content;
wenzelm
parents: 74905
diff changeset
    15
72558
38ebf696fd0c support for Mailman list servers;
wenzelm
parents:
diff changeset
    16
38ebf696fd0c support for Mailman list servers;
wenzelm
parents:
diff changeset
    17
object Mailman
38ebf696fd0c support for Mailman list servers;
wenzelm
parents:
diff changeset
    18
{
74921
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
    19
  /* mailing list messages */
72559
274c9986e55b maintain Isabelle mailing list archives;
wenzelm
parents: 72558
diff changeset
    20
74935
dc62948c6080 more data integrity: name vs. address;
wenzelm
parents: 74934
diff changeset
    21
  def is_address(s: String): Boolean =
dc62948c6080 more data integrity: name vs. address;
wenzelm
parents: 74934
diff changeset
    22
    s.contains('@') && s.contains('.') && !s.contains(' ')
dc62948c6080 more data integrity: name vs. address;
wenzelm
parents: 74934
diff changeset
    23
dc62948c6080 more data integrity: name vs. address;
wenzelm
parents: 74934
diff changeset
    24
  val standard_name: Map[String, String] =
dc62948c6080 more data integrity: name vs. address;
wenzelm
parents: 74934
diff changeset
    25
    Map(
dc62948c6080 more data integrity: name vs. address;
wenzelm
parents: 74934
diff changeset
    26
      "Blanchette, J.C." -> "Jasmin Christian Blanchette",
dc62948c6080 more data integrity: name vs. address;
wenzelm
parents: 74934
diff changeset
    27
      "Buday Gergely István" -> "Gergely Buday",
dc62948c6080 more data integrity: name vs. address;
wenzelm
parents: 74934
diff changeset
    28
      "Carsten Schuermann" -> "Carsten Schürman",
dc62948c6080 more data integrity: name vs. address;
wenzelm
parents: 74934
diff changeset
    29
      "Christoph Lueth" -> "Christoph Lüth",
dc62948c6080 more data integrity: name vs. address;
wenzelm
parents: 74934
diff changeset
    30
      "Claude Marche" -> "Claude Marché",
dc62948c6080 more data integrity: name vs. address;
wenzelm
parents: 74934
diff changeset
    31
      "Farquhar, Colin I" -> "Colin Farquhar",
dc62948c6080 more data integrity: name vs. address;
wenzelm
parents: 74934
diff changeset
    32
      "George K." -> "George Karabotsos",
dc62948c6080 more data integrity: name vs. address;
wenzelm
parents: 74934
diff changeset
    33
      "Filip MariÄ" -> "Filip Marić",
dc62948c6080 more data integrity: name vs. address;
wenzelm
parents: 74934
diff changeset
    34
      "Hitoshi Ohsaki (RTA publicity chair)" -> "Hitoshi Ohsaki",
dc62948c6080 more data integrity: name vs. address;
wenzelm
parents: 74934
diff changeset
    35
      "Farn" -> "Farn Wang",
dc62948c6080 more data integrity: name vs. address;
wenzelm
parents: 74934
diff changeset
    36
      "Fleury Mathias" -> "Mathias Fleury",
dc62948c6080 more data integrity: name vs. address;
wenzelm
parents: 74934
diff changeset
    37
      "Urban, Christian" -> "Christian Urban",
dc62948c6080 more data integrity: name vs. address;
wenzelm
parents: 74934
diff changeset
    38
      "Moscato, Mariano M. \\(LARC-D320\\)\\[NATIONAL INSTITUTE OF AEROSPACE\\]" -> "Moscato, Mariano M. (LARC-D320)",
dc62948c6080 more data integrity: name vs. address;
wenzelm
parents: 74934
diff changeset
    39
    ).withDefault(identity)
dc62948c6080 more data integrity: name vs. address;
wenzelm
parents: 74934
diff changeset
    40
74921
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
    41
  sealed case class Message(
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
    42
    name: String,
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
    43
    date: Date,
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
    44
    title: String,
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
    45
    author_name: String,
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
    46
    author_address: String,
74934
f5ad3214bef4 clarified signature: more operations;
wenzelm
parents: 74933
diff changeset
    47
    body: String,
f5ad3214bef4 clarified signature: more operations;
wenzelm
parents: 74933
diff changeset
    48
    tags: List[String])
72558
38ebf696fd0c support for Mailman list servers;
wenzelm
parents:
diff changeset
    49
  {
74935
dc62948c6080 more data integrity: name vs. address;
wenzelm
parents: 74934
diff changeset
    50
    if (author_name.nonEmpty && is_address(author_name)) {
dc62948c6080 more data integrity: name vs. address;
wenzelm
parents: 74934
diff changeset
    51
      Output.warning("Bad author name, looks like mail address: " +
dc62948c6080 more data integrity: name vs. address;
wenzelm
parents: 74934
diff changeset
    52
        quote(author_name) + " in " + quote(name))
dc62948c6080 more data integrity: name vs. address;
wenzelm
parents: 74934
diff changeset
    53
    }
dc62948c6080 more data integrity: name vs. address;
wenzelm
parents: 74934
diff changeset
    54
dc62948c6080 more data integrity: name vs. address;
wenzelm
parents: 74934
diff changeset
    55
    if (author_address.nonEmpty && !is_address(author_address)) {
dc62948c6080 more data integrity: name vs. address;
wenzelm
parents: 74934
diff changeset
    56
      error("Bad mail address: " + quote(author_address) + " in " + quote(name))
dc62948c6080 more data integrity: name vs. address;
wenzelm
parents: 74934
diff changeset
    57
    }
dc62948c6080 more data integrity: name vs. address;
wenzelm
parents: 74934
diff changeset
    58
74925
4bc306cb2832 more data integrity: name vs. address;
wenzelm
parents: 74924
diff changeset
    59
    override def toString: String = name
74935
dc62948c6080 more data integrity: name vs. address;
wenzelm
parents: 74934
diff changeset
    60
dc62948c6080 more data integrity: name vs. address;
wenzelm
parents: 74934
diff changeset
    61
    def nodes: List[String] =
dc62948c6080 more data integrity: name vs. address;
wenzelm
parents: 74934
diff changeset
    62
      proper_string(author_name).toList :::
dc62948c6080 more data integrity: name vs. address;
wenzelm
parents: 74934
diff changeset
    63
      proper_string(author_address).toList
dc62948c6080 more data integrity: name vs. address;
wenzelm
parents: 74934
diff changeset
    64
74921
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
    65
    def print: String =
74922
15404e37c127 more mailing list content;
wenzelm
parents: 74921
diff changeset
    66
      name + "\n" + date + "\n" + title + "\n" +
15404e37c127 more mailing list content;
wenzelm
parents: 74921
diff changeset
    67
      quote(author_name) + "\n" + "<" + author_address + ">\n"
74935
dc62948c6080 more data integrity: name vs. address;
wenzelm
parents: 74934
diff changeset
    68
   }
74906
9702913db56c more Mailman content;
wenzelm
parents: 74905
diff changeset
    69
74933
0f27dcd030b8 clarified signature;
wenzelm
parents: 74932
diff changeset
    70
  object Messages
74925
4bc306cb2832 more data integrity: name vs. address;
wenzelm
parents: 74924
diff changeset
    71
  {
74935
dc62948c6080 more data integrity: name vs. address;
wenzelm
parents: 74934
diff changeset
    72
    type Graph = isabelle.Graph[String, Message]
dc62948c6080 more data integrity: name vs. address;
wenzelm
parents: 74934
diff changeset
    73
74933
0f27dcd030b8 clarified signature;
wenzelm
parents: 74932
diff changeset
    74
    def apply(msgs: List[Message]): Messages =
74935
dc62948c6080 more data integrity: name vs. address;
wenzelm
parents: 74934
diff changeset
    75
    {
dc62948c6080 more data integrity: name vs. address;
wenzelm
parents: 74934
diff changeset
    76
      def update_node(g: Graph, node: String, msg: Message): Graph =
dc62948c6080 more data integrity: name vs. address;
wenzelm
parents: 74934
diff changeset
    77
        if (node.isEmpty ||
dc62948c6080 more data integrity: name vs. address;
wenzelm
parents: 74934
diff changeset
    78
            g.defined(node) && Date.Ordering.compare(g.get_node(node).date, msg.date) >= 0) g
dc62948c6080 more data integrity: name vs. address;
wenzelm
parents: 74934
diff changeset
    79
        else g.default_node(node, msg)
dc62948c6080 more data integrity: name vs. address;
wenzelm
parents: 74934
diff changeset
    80
dc62948c6080 more data integrity: name vs. address;
wenzelm
parents: 74934
diff changeset
    81
      new Messages(msgs.sortBy(_.date)(Date.Ordering),
dc62948c6080 more data integrity: name vs. address;
wenzelm
parents: 74934
diff changeset
    82
        msgs.foldLeft[Graph](Graph.string)(
dc62948c6080 more data integrity: name vs. address;
wenzelm
parents: 74934
diff changeset
    83
          { case (g, msg) =>
dc62948c6080 more data integrity: name vs. address;
wenzelm
parents: 74934
diff changeset
    84
              val a = msg.author_name
dc62948c6080 more data integrity: name vs. address;
wenzelm
parents: 74934
diff changeset
    85
              val b = msg.author_address
dc62948c6080 more data integrity: name vs. address;
wenzelm
parents: 74934
diff changeset
    86
              val g1 = update_node(update_node(g, a, msg), b, msg)
dc62948c6080 more data integrity: name vs. address;
wenzelm
parents: 74934
diff changeset
    87
              if (a.nonEmpty && b.nonEmpty) g1.add_edge(a, b).add_edge(b, a)
dc62948c6080 more data integrity: name vs. address;
wenzelm
parents: 74934
diff changeset
    88
              else g1
dc62948c6080 more data integrity: name vs. address;
wenzelm
parents: 74934
diff changeset
    89
          }))
dc62948c6080 more data integrity: name vs. address;
wenzelm
parents: 74934
diff changeset
    90
    }
74934
f5ad3214bef4 clarified signature: more operations;
wenzelm
parents: 74933
diff changeset
    91
f5ad3214bef4 clarified signature: more operations;
wenzelm
parents: 74933
diff changeset
    92
    def find(dir: Path): Messages =
f5ad3214bef4 clarified signature: more operations;
wenzelm
parents: 74933
diff changeset
    93
    {
f5ad3214bef4 clarified signature: more operations;
wenzelm
parents: 74933
diff changeset
    94
      val msgs =
f5ad3214bef4 clarified signature: more operations;
wenzelm
parents: 74933
diff changeset
    95
        for {
f5ad3214bef4 clarified signature: more operations;
wenzelm
parents: 74933
diff changeset
    96
          archive <- List(Isabelle_Users, Isabelle_Dev)
f5ad3214bef4 clarified signature: more operations;
wenzelm
parents: 74933
diff changeset
    97
          msg <- archive.find_messages(dir + Path.basic(archive.list_name))
f5ad3214bef4 clarified signature: more operations;
wenzelm
parents: 74933
diff changeset
    98
        } yield msg
f5ad3214bef4 clarified signature: more operations;
wenzelm
parents: 74933
diff changeset
    99
      Messages(msgs)
f5ad3214bef4 clarified signature: more operations;
wenzelm
parents: 74933
diff changeset
   100
    }
74935
dc62948c6080 more data integrity: name vs. address;
wenzelm
parents: 74934
diff changeset
   101
dc62948c6080 more data integrity: name vs. address;
wenzelm
parents: 74934
diff changeset
   102
    sealed case class Cluster(names: List[String], addresses: List[String])
dc62948c6080 more data integrity: name vs. address;
wenzelm
parents: 74934
diff changeset
   103
    {
dc62948c6080 more data integrity: name vs. address;
wenzelm
parents: 74934
diff changeset
   104
      val name: String =
dc62948c6080 more data integrity: name vs. address;
wenzelm
parents: 74934
diff changeset
   105
        names.headOption getOrElse {
dc62948c6080 more data integrity: name vs. address;
wenzelm
parents: 74934
diff changeset
   106
          addresses match {
dc62948c6080 more data integrity: name vs. address;
wenzelm
parents: 74934
diff changeset
   107
            case a :: _ => a.substring(0, a.indexOf('@')).replace('.', ' ')
dc62948c6080 more data integrity: name vs. address;
wenzelm
parents: 74934
diff changeset
   108
            case Nil => error("Empty cluster")
dc62948c6080 more data integrity: name vs. address;
wenzelm
parents: 74934
diff changeset
   109
          }
dc62948c6080 more data integrity: name vs. address;
wenzelm
parents: 74934
diff changeset
   110
        }
dc62948c6080 more data integrity: name vs. address;
wenzelm
parents: 74934
diff changeset
   111
dc62948c6080 more data integrity: name vs. address;
wenzelm
parents: 74934
diff changeset
   112
      def get_address: Option[String] = addresses.headOption
dc62948c6080 more data integrity: name vs. address;
wenzelm
parents: 74934
diff changeset
   113
dc62948c6080 more data integrity: name vs. address;
wenzelm
parents: 74934
diff changeset
   114
      def unique: Boolean = names.length == 1 && addresses.length == 1
dc62948c6080 more data integrity: name vs. address;
wenzelm
parents: 74934
diff changeset
   115
      def multi: Boolean = names.length > 1 || addresses.length > 1
dc62948c6080 more data integrity: name vs. address;
wenzelm
parents: 74934
diff changeset
   116
dc62948c6080 more data integrity: name vs. address;
wenzelm
parents: 74934
diff changeset
   117
      def print: String =
dc62948c6080 more data integrity: name vs. address;
wenzelm
parents: 74934
diff changeset
   118
      {
dc62948c6080 more data integrity: name vs. address;
wenzelm
parents: 74934
diff changeset
   119
        val entries = names ::: (if (addresses.isEmpty) Nil else List("")) ::: addresses
dc62948c6080 more data integrity: name vs. address;
wenzelm
parents: 74934
diff changeset
   120
        entries.mkString("\n  * ", "\n    ", "")
dc62948c6080 more data integrity: name vs. address;
wenzelm
parents: 74934
diff changeset
   121
      }
dc62948c6080 more data integrity: name vs. address;
wenzelm
parents: 74934
diff changeset
   122
    }
74933
0f27dcd030b8 clarified signature;
wenzelm
parents: 74932
diff changeset
   123
  }
0f27dcd030b8 clarified signature;
wenzelm
parents: 74932
diff changeset
   124
74935
dc62948c6080 more data integrity: name vs. address;
wenzelm
parents: 74934
diff changeset
   125
  class Messages private(val sorted: List[Message], val graph: Messages.Graph)
74933
0f27dcd030b8 clarified signature;
wenzelm
parents: 74932
diff changeset
   126
  {
74935
dc62948c6080 more data integrity: name vs. address;
wenzelm
parents: 74934
diff changeset
   127
    override def toString: String = "Messages(" + sorted.size + ")"
74925
4bc306cb2832 more data integrity: name vs. address;
wenzelm
parents: 74924
diff changeset
   128
74935
dc62948c6080 more data integrity: name vs. address;
wenzelm
parents: 74934
diff changeset
   129
    object Node_Ordering extends scala.math.Ordering[String]
74933
0f27dcd030b8 clarified signature;
wenzelm
parents: 74932
diff changeset
   130
    {
74935
dc62948c6080 more data integrity: name vs. address;
wenzelm
parents: 74934
diff changeset
   131
      override def compare(a: String, b: String): Int =
dc62948c6080 more data integrity: name vs. address;
wenzelm
parents: 74934
diff changeset
   132
        Date.Rev_Ordering.compare(graph.get_node(a).date, graph.get_node(b).date)
dc62948c6080 more data integrity: name vs. address;
wenzelm
parents: 74934
diff changeset
   133
    }
dc62948c6080 more data integrity: name vs. address;
wenzelm
parents: 74934
diff changeset
   134
dc62948c6080 more data integrity: name vs. address;
wenzelm
parents: 74934
diff changeset
   135
    def get_nodes(msg: Message): List[String] =
dc62948c6080 more data integrity: name vs. address;
wenzelm
parents: 74934
diff changeset
   136
      graph.all_succs(msg.nodes).sorted(Node_Ordering)
74925
4bc306cb2832 more data integrity: name vs. address;
wenzelm
parents: 74924
diff changeset
   137
74935
dc62948c6080 more data integrity: name vs. address;
wenzelm
parents: 74934
diff changeset
   138
    def get_cluster(msg: Message): Messages.Cluster =
dc62948c6080 more data integrity: name vs. address;
wenzelm
parents: 74934
diff changeset
   139
    {
dc62948c6080 more data integrity: name vs. address;
wenzelm
parents: 74934
diff changeset
   140
      val (addresses, names) = get_nodes(msg).partition(is_address)
dc62948c6080 more data integrity: name vs. address;
wenzelm
parents: 74934
diff changeset
   141
      Messages.Cluster(names, addresses)
dc62948c6080 more data integrity: name vs. address;
wenzelm
parents: 74934
diff changeset
   142
    }
dc62948c6080 more data integrity: name vs. address;
wenzelm
parents: 74934
diff changeset
   143
dc62948c6080 more data integrity: name vs. address;
wenzelm
parents: 74934
diff changeset
   144
    def get_name(msg: Message): String = get_cluster(msg).name
74925
4bc306cb2832 more data integrity: name vs. address;
wenzelm
parents: 74924
diff changeset
   145
74935
dc62948c6080 more data integrity: name vs. address;
wenzelm
parents: 74934
diff changeset
   146
    def get_address(msg: Message): String =
dc62948c6080 more data integrity: name vs. address;
wenzelm
parents: 74934
diff changeset
   147
      get_cluster(msg).get_address getOrElse error("No author address for " + quote(msg.name))
dc62948c6080 more data integrity: name vs. address;
wenzelm
parents: 74934
diff changeset
   148
dc62948c6080 more data integrity: name vs. address;
wenzelm
parents: 74934
diff changeset
   149
    def check(check_multi: Boolean = false): Unit =
dc62948c6080 more data integrity: name vs. address;
wenzelm
parents: 74934
diff changeset
   150
    {
dc62948c6080 more data integrity: name vs. address;
wenzelm
parents: 74934
diff changeset
   151
      val clusters = sorted.map(get_cluster).distinct.sortBy(_.name)
dc62948c6080 more data integrity: name vs. address;
wenzelm
parents: 74934
diff changeset
   152
dc62948c6080 more data integrity: name vs. address;
wenzelm
parents: 74934
diff changeset
   153
      val multi = if (check_multi) clusters.filter(_.multi) else Nil
dc62948c6080 more data integrity: name vs. address;
wenzelm
parents: 74934
diff changeset
   154
      if (multi.nonEmpty) {
dc62948c6080 more data integrity: name vs. address;
wenzelm
parents: 74934
diff changeset
   155
        Output.writeln(cat_lines("ambiguous:" :: multi.map(_.print)))
74925
4bc306cb2832 more data integrity: name vs. address;
wenzelm
parents: 74924
diff changeset
   156
      }
74933
0f27dcd030b8 clarified signature;
wenzelm
parents: 74932
diff changeset
   157
74935
dc62948c6080 more data integrity: name vs. address;
wenzelm
parents: 74934
diff changeset
   158
      val unknown = clusters.filter(cluster => cluster.get_address.isEmpty)
dc62948c6080 more data integrity: name vs. address;
wenzelm
parents: 74934
diff changeset
   159
      if (unknown.nonEmpty) {
dc62948c6080 more data integrity: name vs. address;
wenzelm
parents: 74934
diff changeset
   160
        Output.writeln(cat_lines("unknown mail:" :: unknown.map(_.print)))
74933
0f27dcd030b8 clarified signature;
wenzelm
parents: 74932
diff changeset
   161
      }
74925
4bc306cb2832 more data integrity: name vs. address;
wenzelm
parents: 74924
diff changeset
   162
    }
4bc306cb2832 more data integrity: name vs. address;
wenzelm
parents: 74924
diff changeset
   163
  }
4bc306cb2832 more data integrity: name vs. address;
wenzelm
parents: 74924
diff changeset
   164
4bc306cb2832 more data integrity: name vs. address;
wenzelm
parents: 74924
diff changeset
   165
74921
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   166
  /* mailing list archives */
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   167
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   168
  abstract class Archive(
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   169
    url: URL,
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   170
    name: String = "",
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   171
    tag: String = "")
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   172
  {
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   173
    def message_regex: Regex
74923
e0070487b635 clarified name;
wenzelm
parents: 74922
diff changeset
   174
    def message_content(name: String, lines: List[String]): Message
74921
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   175
74924
af954161e1cd misc tuning and clarification;
wenzelm
parents: 74923
diff changeset
   176
    def message_match(lines: List[String], re: Regex): Option[Match] =
af954161e1cd misc tuning and clarification;
wenzelm
parents: 74923
diff changeset
   177
      lines.flatMap(re.findFirstMatchIn(_)).headOption
af954161e1cd misc tuning and clarification;
wenzelm
parents: 74923
diff changeset
   178
74931
1753dade9a24 more data integrity: name vs. address;
wenzelm
parents: 74930
diff changeset
   179
    def make_name(str: String): String =
74935
dc62948c6080 more data integrity: name vs. address;
wenzelm
parents: 74934
diff changeset
   180
    {
dc62948c6080 more data integrity: name vs. address;
wenzelm
parents: 74934
diff changeset
   181
      val s = str.trim.replaceAll("""\s+""", " ").replaceAll(" at ", "@")
dc62948c6080 more data integrity: name vs. address;
wenzelm
parents: 74934
diff changeset
   182
      if (s.startsWith("=") && s.endsWith("=")) "" else s
dc62948c6080 more data integrity: name vs. address;
wenzelm
parents: 74934
diff changeset
   183
    }
74924
af954161e1cd misc tuning and clarification;
wenzelm
parents: 74923
diff changeset
   184
af954161e1cd misc tuning and clarification;
wenzelm
parents: 74923
diff changeset
   185
    def make_body(lines: List[String]): String =
af954161e1cd misc tuning and clarification;
wenzelm
parents: 74923
diff changeset
   186
      cat_lines(Library.take_suffix[String](_.isEmpty, lines)._1)
af954161e1cd misc tuning and clarification;
wenzelm
parents: 74923
diff changeset
   187
74921
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   188
    private val main_url: URL =
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   189
      Url(Library.take_suffix[Char](_ == '/', Url.trim_index(url).toString.toList)._1.mkString + "/")
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   190
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   191
    private val main_html = Url.read(main_url)
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   192
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   193
    val list_name: String =
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   194
    {
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   195
      val title =
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   196
        """<title>The ([^</>]*) Archives</title>""".r.findFirstMatchIn(main_html).map(_.group(1))
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   197
      (proper_string(name) orElse title).getOrElse(error("Failed to determine mailing list name"))
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   198
    }
72558
38ebf696fd0c support for Mailman list servers;
wenzelm
parents:
diff changeset
   199
    override def toString: String = list_name
38ebf696fd0c support for Mailman list servers;
wenzelm
parents:
diff changeset
   200
74923
e0070487b635 clarified name;
wenzelm
parents: 74922
diff changeset
   201
    def full_name(href: String): String = list_name + "/" + href
e0070487b635 clarified name;
wenzelm
parents: 74922
diff changeset
   202
74921
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   203
    def list_tag: String = proper_string(tag).getOrElse(list_name)
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   204
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   205
    def read_text(href: String): String = Url.read(new URL(main_url, href))
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   206
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   207
    def hrefs_text: List[String] =
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   208
      """href="([^"]+\.txt(?:\.gz)?)"""".r.findAllMatchIn(main_html).map(_.group(1)).toList
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   209
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   210
    def hrefs_msg: List[String] =
74906
9702913db56c more Mailman content;
wenzelm
parents: 74905
diff changeset
   211
      (for {
74921
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   212
        href <- """href="([^"]+)/date.html"""".r.findAllMatchIn(main_html).map(_.group(1))
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   213
        html = read_text(href + "/date.html")
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   214
        msg <- message_regex.findAllMatchIn(html).map(_.group(1))
74906
9702913db56c more Mailman content;
wenzelm
parents: 74905
diff changeset
   215
      } yield href + "/" + msg).toList
9702913db56c more Mailman content;
wenzelm
parents: 74905
diff changeset
   216
9702913db56c more Mailman content;
wenzelm
parents: 74905
diff changeset
   217
    def get(target_dir: Path, href: String, progress: Progress = new Progress): Option[Path] =
72558
38ebf696fd0c support for Mailman list servers;
wenzelm
parents:
diff changeset
   218
    {
38ebf696fd0c support for Mailman list servers;
wenzelm
parents:
diff changeset
   219
      val dir = target_dir + Path.basic(list_name)
74906
9702913db56c more Mailman content;
wenzelm
parents: 74905
diff changeset
   220
      val path = dir + Path.explode(href)
74921
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   221
      val url = new URL(main_url, href)
74906
9702913db56c more Mailman content;
wenzelm
parents: 74905
diff changeset
   222
      val connection = url.openConnection
9702913db56c more Mailman content;
wenzelm
parents: 74905
diff changeset
   223
      try {
9702913db56c more Mailman content;
wenzelm
parents: 74905
diff changeset
   224
        val length = connection.getContentLengthLong
9702913db56c more Mailman content;
wenzelm
parents: 74905
diff changeset
   225
        val timestamp = connection.getLastModified
9702913db56c more Mailman content;
wenzelm
parents: 74905
diff changeset
   226
        val file = path.file
9702913db56c more Mailman content;
wenzelm
parents: 74905
diff changeset
   227
        if (file.isFile && file.length == length && file.lastModified == timestamp) None
9702913db56c more Mailman content;
wenzelm
parents: 74905
diff changeset
   228
        else {
9702913db56c more Mailman content;
wenzelm
parents: 74905
diff changeset
   229
          Isabelle_System.make_directory(path.dir)
9702913db56c more Mailman content;
wenzelm
parents: 74905
diff changeset
   230
          progress.echo("Getting " + url)
9702913db56c more Mailman content;
wenzelm
parents: 74905
diff changeset
   231
          val bytes =
9702913db56c more Mailman content;
wenzelm
parents: 74905
diff changeset
   232
            using(connection.getInputStream)(Bytes.read_stream(_, hint = length.toInt max 1024))
9702913db56c more Mailman content;
wenzelm
parents: 74905
diff changeset
   233
          Bytes.write(file, bytes)
9702913db56c more Mailman content;
wenzelm
parents: 74905
diff changeset
   234
          file.setLastModified(timestamp)
9702913db56c more Mailman content;
wenzelm
parents: 74905
diff changeset
   235
          Some(path)
9702913db56c more Mailman content;
wenzelm
parents: 74905
diff changeset
   236
        }
9702913db56c more Mailman content;
wenzelm
parents: 74905
diff changeset
   237
      }
9702913db56c more Mailman content;
wenzelm
parents: 74905
diff changeset
   238
      finally { connection.getInputStream.close() }
9702913db56c more Mailman content;
wenzelm
parents: 74905
diff changeset
   239
    }
72558
38ebf696fd0c support for Mailman list servers;
wenzelm
parents:
diff changeset
   240
74906
9702913db56c more Mailman content;
wenzelm
parents: 74905
diff changeset
   241
    def download_text(target_dir: Path, progress: Progress = new Progress): List[Path] =
9702913db56c more Mailman content;
wenzelm
parents: 74905
diff changeset
   242
      hrefs_text.flatMap(get(target_dir, _, progress = progress))
9702913db56c more Mailman content;
wenzelm
parents: 74905
diff changeset
   243
9702913db56c more Mailman content;
wenzelm
parents: 74905
diff changeset
   244
    def download_msg(target_dir: Path, progress: Progress = new Progress): List[Path] =
9702913db56c more Mailman content;
wenzelm
parents: 74905
diff changeset
   245
      hrefs_msg.flatMap(get(target_dir, _, progress = progress))
74907
af2323593473 more Mailman archives;
wenzelm
parents: 74906
diff changeset
   246
af2323593473 more Mailman archives;
wenzelm
parents: 74906
diff changeset
   247
    def download(target_dir: Path, progress: Progress = new Progress): List[Path] =
af2323593473 more Mailman archives;
wenzelm
parents: 74906
diff changeset
   248
      download_text(target_dir, progress = progress) :::
af2323593473 more Mailman archives;
wenzelm
parents: 74906
diff changeset
   249
      download_msg(target_dir, progress = progress)
74921
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   250
74924
af954161e1cd misc tuning and clarification;
wenzelm
parents: 74923
diff changeset
   251
    def make_title(str: String): String =
74921
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   252
    {
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   253
      val Trim1 = ("""\s*\Q[""" + list_tag + """]\E\s*(.*)""").r
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   254
      val Trim2 = """(?i:(?:re|fw|fwd)\s*:\s*)(.*)""".r
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   255
      val Trim3 = """\[\s*(.*?)\s*\]""".r
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   256
      @tailrec def trim(s: String): String =
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   257
        s match {
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   258
          case Trim1(s1) => trim(s1)
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   259
          case Trim2(s1) => trim(s1)
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   260
          case Trim3(s1) => trim(s1)
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   261
          case _ => s
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   262
        }
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   263
      trim(str)
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   264
    }
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   265
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   266
    def get_messages(): List[Message] =
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   267
      for (href <- hrefs_msg) yield message_content(href, split_lines(read_text(href)))
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   268
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   269
    def find_messages(dir: Path): List[Message] =
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   270
    {
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   271
      for {
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   272
        file <- File.find_files(dir.file, file => file.getName.endsWith(".html"))
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   273
        rel_path <- File.relative_path(dir, File.path(file))
74923
e0070487b635 clarified name;
wenzelm
parents: 74922
diff changeset
   274
      }
e0070487b635 clarified name;
wenzelm
parents: 74922
diff changeset
   275
      yield {
e0070487b635 clarified name;
wenzelm
parents: 74922
diff changeset
   276
        val name = full_name(rel_path.implode)
e0070487b635 clarified name;
wenzelm
parents: 74922
diff changeset
   277
        message_content(name, split_lines(File.read(file)))
e0070487b635 clarified name;
wenzelm
parents: 74922
diff changeset
   278
      }
74921
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   279
    }
72558
38ebf696fd0c support for Mailman list servers;
wenzelm
parents:
diff changeset
   280
  }
72559
274c9986e55b maintain Isabelle mailing list archives;
wenzelm
parents: 72558
diff changeset
   281
74932
wenzelm
parents: 74931
diff changeset
   282
  private class Message_Chunk(bg: String = "", en: String = "")
wenzelm
parents: 74931
diff changeset
   283
  {
wenzelm
parents: 74931
diff changeset
   284
    def unapply(lines: List[String]): Option[List[String]] =
wenzelm
parents: 74931
diff changeset
   285
    {
wenzelm
parents: 74931
diff changeset
   286
      val res1 =
wenzelm
parents: 74931
diff changeset
   287
        if (bg.isEmpty) Some(lines)
wenzelm
parents: 74931
diff changeset
   288
        else {
wenzelm
parents: 74931
diff changeset
   289
          lines.dropWhile(_ != bg) match {
wenzelm
parents: 74931
diff changeset
   290
            case Nil => None
wenzelm
parents: 74931
diff changeset
   291
            case _ :: rest => Some(rest)
wenzelm
parents: 74931
diff changeset
   292
          }
wenzelm
parents: 74931
diff changeset
   293
        }
wenzelm
parents: 74931
diff changeset
   294
      if (en.isEmpty) res1
wenzelm
parents: 74931
diff changeset
   295
      else {
wenzelm
parents: 74931
diff changeset
   296
        res1 match {
wenzelm
parents: 74931
diff changeset
   297
          case None => None
wenzelm
parents: 74931
diff changeset
   298
          case Some(lines1) =>
wenzelm
parents: 74931
diff changeset
   299
            val lines2 = lines1.takeWhile(_ != en)
wenzelm
parents: 74931
diff changeset
   300
            if (lines1.drop(lines2.length).isEmpty) None else Some(lines2)
wenzelm
parents: 74931
diff changeset
   301
        }
wenzelm
parents: 74931
diff changeset
   302
      }
wenzelm
parents: 74931
diff changeset
   303
    }
wenzelm
parents: 74931
diff changeset
   304
wenzelm
parents: 74931
diff changeset
   305
    def get(lines: List[String]): List[String] =
wenzelm
parents: 74931
diff changeset
   306
      unapply(lines) getOrElse
wenzelm
parents: 74931
diff changeset
   307
        error("Missing delimiters:" +
wenzelm
parents: 74931
diff changeset
   308
          (if (bg.nonEmpty) " " else "") + bg +
wenzelm
parents: 74931
diff changeset
   309
          (if (en.nonEmpty) " " else "") + en)
wenzelm
parents: 74931
diff changeset
   310
  }
wenzelm
parents: 74931
diff changeset
   311
72559
274c9986e55b maintain Isabelle mailing list archives;
wenzelm
parents: 72558
diff changeset
   312
74930
e9506503efea tuned comments;
wenzelm
parents: 74925
diff changeset
   313
  /* isabelle-users mailing list */
72559
274c9986e55b maintain Isabelle mailing list archives;
wenzelm
parents: 72558
diff changeset
   314
74921
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   315
  object Isabelle_Users extends Archive(
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   316
    Url("https://lists.cam.ac.uk/pipermail/cl-isabelle-users"),
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   317
    name = "isabelle-users", tag = "isabelle")
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   318
  {
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   319
    override def message_regex: Regex = """<li><a name="\d+" href="(msg\d+\.html)">""".r
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   320
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   321
    private object Head extends
74922
15404e37c127 more mailing list content;
wenzelm
parents: 74921
diff changeset
   322
      Message_Chunk(bg = "<!--X-Head-of-Message-->", en = "<!--X-Head-of-Message-End-->")
74921
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   323
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   324
    private object Body extends
74922
15404e37c127 more mailing list content;
wenzelm
parents: 74921
diff changeset
   325
      Message_Chunk(bg = "<!--X-Body-of-Message-->", en = "<!--X-Body-of-Message-End-->")
15404e37c127 more mailing list content;
wenzelm
parents: 74921
diff changeset
   326
15404e37c127 more mailing list content;
wenzelm
parents: 74921
diff changeset
   327
    private object Date_Format
15404e37c127 more mailing list content;
wenzelm
parents: 74921
diff changeset
   328
    {
15404e37c127 more mailing list content;
wenzelm
parents: 74921
diff changeset
   329
      private val Trim1 = """\w+,\s*(.*)""".r
15404e37c127 more mailing list content;
wenzelm
parents: 74921
diff changeset
   330
      private val Trim2 = """(.*?)\s*\(.*\)""".r
15404e37c127 more mailing list content;
wenzelm
parents: 74921
diff changeset
   331
      private val Format =
15404e37c127 more mailing list content;
wenzelm
parents: 74921
diff changeset
   332
        Date.Format(
15404e37c127 more mailing list content;
wenzelm
parents: 74921
diff changeset
   333
          "d MMM uuuu H:m:s Z",
15404e37c127 more mailing list content;
wenzelm
parents: 74921
diff changeset
   334
          "d MMM uuuu H:m:s z",
15404e37c127 more mailing list content;
wenzelm
parents: 74921
diff changeset
   335
          "d MMM yy H:m:s Z",
15404e37c127 more mailing list content;
wenzelm
parents: 74921
diff changeset
   336
          "d MMM yy H:m:s z")
15404e37c127 more mailing list content;
wenzelm
parents: 74921
diff changeset
   337
      def unapply(s: String): Option[Date] =
15404e37c127 more mailing list content;
wenzelm
parents: 74921
diff changeset
   338
      {
15404e37c127 more mailing list content;
wenzelm
parents: 74921
diff changeset
   339
        val s0 = s.replaceAll("""\s+""", " ")
15404e37c127 more mailing list content;
wenzelm
parents: 74921
diff changeset
   340
        val s1 =
15404e37c127 more mailing list content;
wenzelm
parents: 74921
diff changeset
   341
          s0 match {
15404e37c127 more mailing list content;
wenzelm
parents: 74921
diff changeset
   342
            case Trim1(s1) => s1
15404e37c127 more mailing list content;
wenzelm
parents: 74921
diff changeset
   343
            case _ => s0
15404e37c127 more mailing list content;
wenzelm
parents: 74921
diff changeset
   344
          }
15404e37c127 more mailing list content;
wenzelm
parents: 74921
diff changeset
   345
        val s2 =
15404e37c127 more mailing list content;
wenzelm
parents: 74921
diff changeset
   346
          s1 match {
15404e37c127 more mailing list content;
wenzelm
parents: 74921
diff changeset
   347
            case Trim2(s2) => s2
15404e37c127 more mailing list content;
wenzelm
parents: 74921
diff changeset
   348
            case _ => s1
15404e37c127 more mailing list content;
wenzelm
parents: 74921
diff changeset
   349
          }
15404e37c127 more mailing list content;
wenzelm
parents: 74921
diff changeset
   350
        Format.unapply(s2)
15404e37c127 more mailing list content;
wenzelm
parents: 74921
diff changeset
   351
      }
15404e37c127 more mailing list content;
wenzelm
parents: 74921
diff changeset
   352
    }
74921
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   353
74924
af954161e1cd misc tuning and clarification;
wenzelm
parents: 74923
diff changeset
   354
    override def make_name(str: String): String =
74921
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   355
    {
74935
dc62948c6080 more data integrity: name vs. address;
wenzelm
parents: 74934
diff changeset
   356
      val s = Library.perhaps_unsuffix(" via Cl-isabelle-users", super.make_name(str))
74925
4bc306cb2832 more data integrity: name vs. address;
wenzelm
parents: 74924
diff changeset
   357
      if (s == "cl-isabelle-users@lists.cam.ac.uk") "" else s
4bc306cb2832 more data integrity: name vs. address;
wenzelm
parents: 74924
diff changeset
   358
    }
4bc306cb2832 more data integrity: name vs. address;
wenzelm
parents: 74924
diff changeset
   359
74924
af954161e1cd misc tuning and clarification;
wenzelm
parents: 74923
diff changeset
   360
    object Address
af954161e1cd misc tuning and clarification;
wenzelm
parents: 74923
diff changeset
   361
    {
af954161e1cd misc tuning and clarification;
wenzelm
parents: 74923
diff changeset
   362
      private def anchor(s: String): String = """<a href="[^"]*">""" + s + """</a>"""
af954161e1cd misc tuning and clarification;
wenzelm
parents: 74923
diff changeset
   363
      private def angl(s: String): String = """&lt;""" + s + """&gt;"""
af954161e1cd misc tuning and clarification;
wenzelm
parents: 74923
diff changeset
   364
      private def quot(s: String): String = """&quot;""" + s + """&quot;"""
af954161e1cd misc tuning and clarification;
wenzelm
parents: 74923
diff changeset
   365
      private def paren(s: String): String = """\(""" + s + """\)"""
af954161e1cd misc tuning and clarification;
wenzelm
parents: 74923
diff changeset
   366
      private val adr = """([^<>]*? at [^<>]*?)"""
af954161e1cd misc tuning and clarification;
wenzelm
parents: 74923
diff changeset
   367
      private val any = """([^<>]*?)"""
af954161e1cd misc tuning and clarification;
wenzelm
parents: 74923
diff changeset
   368
      private val spc = """\s*"""
af954161e1cd misc tuning and clarification;
wenzelm
parents: 74923
diff changeset
   369
af954161e1cd misc tuning and clarification;
wenzelm
parents: 74923
diff changeset
   370
      private val Name1 = quot(anchor(any)).r
af954161e1cd misc tuning and clarification;
wenzelm
parents: 74923
diff changeset
   371
      private val Name2 = quot(any).r
af954161e1cd misc tuning and clarification;
wenzelm
parents: 74923
diff changeset
   372
      private val Name_Adr1 = (quot(anchor(any)) + spc + angl(anchor(adr))).r
af954161e1cd misc tuning and clarification;
wenzelm
parents: 74923
diff changeset
   373
      private val Name_Adr2 = (quot(any) + spc + angl(anchor(adr))).r
af954161e1cd misc tuning and clarification;
wenzelm
parents: 74923
diff changeset
   374
      private val Name_Adr3 = (anchor(any) + spc + angl(anchor(adr))).r
af954161e1cd misc tuning and clarification;
wenzelm
parents: 74923
diff changeset
   375
      private val Name_Adr4 = (any + spc + angl(anchor(adr))).r
af954161e1cd misc tuning and clarification;
wenzelm
parents: 74923
diff changeset
   376
      private val Adr_Name1 = (angl(anchor(adr)) + spc + paren(any)).r
af954161e1cd misc tuning and clarification;
wenzelm
parents: 74923
diff changeset
   377
      private val Adr_Name2 = (anchor(adr) + spc + paren(any)).r
af954161e1cd misc tuning and clarification;
wenzelm
parents: 74923
diff changeset
   378
      private val Adr1 = angl(anchor(adr)).r
af954161e1cd misc tuning and clarification;
wenzelm
parents: 74923
diff changeset
   379
      private val Adr2 = anchor(adr).r
af954161e1cd misc tuning and clarification;
wenzelm
parents: 74923
diff changeset
   380
af954161e1cd misc tuning and clarification;
wenzelm
parents: 74923
diff changeset
   381
      def unapply(s: String): Option[(String, String)] =
af954161e1cd misc tuning and clarification;
wenzelm
parents: 74923
diff changeset
   382
        s match {
74931
1753dade9a24 more data integrity: name vs. address;
wenzelm
parents: 74930
diff changeset
   383
          case Name1(a) => Some((make_name(a), ""))
1753dade9a24 more data integrity: name vs. address;
wenzelm
parents: 74930
diff changeset
   384
          case Name2(a) => Some((make_name(a), ""))
1753dade9a24 more data integrity: name vs. address;
wenzelm
parents: 74930
diff changeset
   385
          case Name_Adr1(a, b) => Some((make_name(a), make_name(b)))
1753dade9a24 more data integrity: name vs. address;
wenzelm
parents: 74930
diff changeset
   386
          case Name_Adr2(a, b) => Some((make_name(a), make_name(b)))
1753dade9a24 more data integrity: name vs. address;
wenzelm
parents: 74930
diff changeset
   387
          case Name_Adr3(a, b) => Some((make_name(a), make_name(b)))
1753dade9a24 more data integrity: name vs. address;
wenzelm
parents: 74930
diff changeset
   388
          case Name_Adr4(a, b) => Some((make_name(a), make_name(b)))
1753dade9a24 more data integrity: name vs. address;
wenzelm
parents: 74930
diff changeset
   389
          case Adr_Name1(b, a) => Some((make_name(a), make_name(b)))
1753dade9a24 more data integrity: name vs. address;
wenzelm
parents: 74930
diff changeset
   390
          case Adr_Name2(b, a) => Some((make_name(a), make_name(b)))
1753dade9a24 more data integrity: name vs. address;
wenzelm
parents: 74930
diff changeset
   391
          case Adr1(a) => Some(("", make_name(a)))
1753dade9a24 more data integrity: name vs. address;
wenzelm
parents: 74930
diff changeset
   392
          case Adr2(a) => Some(("", make_name(a)))
74924
af954161e1cd misc tuning and clarification;
wenzelm
parents: 74923
diff changeset
   393
          case _ => None
af954161e1cd misc tuning and clarification;
wenzelm
parents: 74923
diff changeset
   394
        }
af954161e1cd misc tuning and clarification;
wenzelm
parents: 74923
diff changeset
   395
    }
af954161e1cd misc tuning and clarification;
wenzelm
parents: 74923
diff changeset
   396
74923
e0070487b635 clarified name;
wenzelm
parents: 74922
diff changeset
   397
    override def message_content(name: String, lines: List[String]): Message =
74921
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   398
    {
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   399
      def err(msg: String = ""): Nothing =
74923
e0070487b635 clarified name;
wenzelm
parents: 74922
diff changeset
   400
        error("Malformed message: " + name + (if (msg.isEmpty) "" else "\n" + msg))
74921
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   401
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   402
      val (head, body) =
74924
af954161e1cd misc tuning and clarification;
wenzelm
parents: 74923
diff changeset
   403
        try { (Head.get(lines), make_body(Body.get(lines))) }
74921
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   404
        catch { case ERROR(msg) => err(msg) }
72559
274c9986e55b maintain Isabelle mailing list archives;
wenzelm
parents: 72558
diff changeset
   405
74921
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   406
      val date =
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   407
        message_match(head, """<li><em>Date</em>:\s*(.*?)\s*</li>""".r)
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   408
          .map(m => HTML.input(m.group(1))) match
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   409
        {
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   410
          case Some(Date_Format(d)) => d
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   411
          case Some(s) => err("Malformed Date: " + quote(s))
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   412
          case None => err("Missing Date")
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   413
        }
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   414
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   415
      val title =
74924
af954161e1cd misc tuning and clarification;
wenzelm
parents: 74923
diff changeset
   416
        make_title(
af954161e1cd misc tuning and clarification;
wenzelm
parents: 74923
diff changeset
   417
          HTML.input(message_match(head, """<li><em>Subject</em>:\s*(.*)</li>""".r)
af954161e1cd misc tuning and clarification;
wenzelm
parents: 74923
diff changeset
   418
            .getOrElse(err("Missing Subject")).group(1)))
74921
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   419
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   420
      val (author_name, author_address) =
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   421
        message_match(head, """<li><em>From</em>:\s*(.*?)\s*</li>""".r) match {
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   422
          case None => err("Missing From")
74925
4bc306cb2832 more data integrity: name vs. address;
wenzelm
parents: 74924
diff changeset
   423
          case Some(m) =>
74931
1753dade9a24 more data integrity: name vs. address;
wenzelm
parents: 74930
diff changeset
   424
            val (a0, b0) = Address.unapply(m.group(1)) getOrElse err("Malformed From")
1753dade9a24 more data integrity: name vs. address;
wenzelm
parents: 74930
diff changeset
   425
            val a = HTML.input(a0)
1753dade9a24 more data integrity: name vs. address;
wenzelm
parents: 74930
diff changeset
   426
            val b = HTML.input(b0)
74925
4bc306cb2832 more data integrity: name vs. address;
wenzelm
parents: 74924
diff changeset
   427
            (if (a == b) "" else a, b)
74921
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   428
        }
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   429
74934
f5ad3214bef4 clarified signature: more operations;
wenzelm
parents: 74933
diff changeset
   430
      val tags = List(list_name)
f5ad3214bef4 clarified signature: more operations;
wenzelm
parents: 74933
diff changeset
   431
74935
dc62948c6080 more data integrity: name vs. address;
wenzelm
parents: 74934
diff changeset
   432
      Message(name, date, title, standard_name(author_name), author_address, body, tags)
74921
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   433
    }
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   434
  }
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   435
74930
e9506503efea tuned comments;
wenzelm
parents: 74925
diff changeset
   436
e9506503efea tuned comments;
wenzelm
parents: 74925
diff changeset
   437
  /* isabelle-dev mailing list */
e9506503efea tuned comments;
wenzelm
parents: 74925
diff changeset
   438
74921
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   439
  object Isabelle_Dev extends Archive(Url("https://mailmanbroy.in.tum.de/pipermail/isabelle-dev"))
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   440
  {
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   441
    override def message_regex: Regex = """<LI><A HREF="(\d+\.html)">""".r
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   442
74922
15404e37c127 more mailing list content;
wenzelm
parents: 74921
diff changeset
   443
    private object Head extends Message_Chunk(en = "<!--beginarticle-->")
15404e37c127 more mailing list content;
wenzelm
parents: 74921
diff changeset
   444
    private object Body extends Message_Chunk(bg = "<!--beginarticle-->", en = "<!--endarticle-->")
15404e37c127 more mailing list content;
wenzelm
parents: 74921
diff changeset
   445
15404e37c127 more mailing list content;
wenzelm
parents: 74921
diff changeset
   446
    private object Date_Format
15404e37c127 more mailing list content;
wenzelm
parents: 74921
diff changeset
   447
    {
15404e37c127 more mailing list content;
wenzelm
parents: 74921
diff changeset
   448
      val Format = Date.Format("E MMM d H:m:s z uuuu")
15404e37c127 more mailing list content;
wenzelm
parents: 74921
diff changeset
   449
      def unapply(s: String): Option[Date] = Format.unapply(s.replaceAll("""\s+""", " "))
15404e37c127 more mailing list content;
wenzelm
parents: 74921
diff changeset
   450
    }
15404e37c127 more mailing list content;
wenzelm
parents: 74921
diff changeset
   451
74931
1753dade9a24 more data integrity: name vs. address;
wenzelm
parents: 74930
diff changeset
   452
    override def make_name(str: String): String =
1753dade9a24 more data integrity: name vs. address;
wenzelm
parents: 74930
diff changeset
   453
    {
74935
dc62948c6080 more data integrity: name vs. address;
wenzelm
parents: 74934
diff changeset
   454
      val s = Library.perhaps_unsuffix(" via RT", super.make_name(str))
74931
1753dade9a24 more data integrity: name vs. address;
wenzelm
parents: 74930
diff changeset
   455
      if (s == "sys-admin@cl.cam.ac.uk") "" else s
1753dade9a24 more data integrity: name vs. address;
wenzelm
parents: 74930
diff changeset
   456
    }
1753dade9a24 more data integrity: name vs. address;
wenzelm
parents: 74930
diff changeset
   457
74923
e0070487b635 clarified name;
wenzelm
parents: 74922
diff changeset
   458
    override def message_content(name: String, lines: List[String]): Message =
74922
15404e37c127 more mailing list content;
wenzelm
parents: 74921
diff changeset
   459
    {
15404e37c127 more mailing list content;
wenzelm
parents: 74921
diff changeset
   460
      def err(msg: String = ""): Nothing =
74923
e0070487b635 clarified name;
wenzelm
parents: 74922
diff changeset
   461
        error("Malformed message: " + name + (if (msg.isEmpty) "" else "\n" + msg))
74922
15404e37c127 more mailing list content;
wenzelm
parents: 74921
diff changeset
   462
15404e37c127 more mailing list content;
wenzelm
parents: 74921
diff changeset
   463
      val (head, body) =
74924
af954161e1cd misc tuning and clarification;
wenzelm
parents: 74923
diff changeset
   464
        try { (Head.get(lines), make_body(Body.get(lines))) }
74922
15404e37c127 more mailing list content;
wenzelm
parents: 74921
diff changeset
   465
        catch { case ERROR(msg) => err(msg) }
15404e37c127 more mailing list content;
wenzelm
parents: 74921
diff changeset
   466
15404e37c127 more mailing list content;
wenzelm
parents: 74921
diff changeset
   467
      val date =
15404e37c127 more mailing list content;
wenzelm
parents: 74921
diff changeset
   468
        message_match(head, """\s*<I>(.*)</I>""".r).map(m => HTML.input(m.group(1))) match {
15404e37c127 more mailing list content;
wenzelm
parents: 74921
diff changeset
   469
          case Some(Date_Format(d)) => d
15404e37c127 more mailing list content;
wenzelm
parents: 74921
diff changeset
   470
          case Some(s) => err("Malformed Date: " + quote(s))
15404e37c127 more mailing list content;
wenzelm
parents: 74921
diff changeset
   471
          case None => err("Missing Date")
15404e37c127 more mailing list content;
wenzelm
parents: 74921
diff changeset
   472
        }
15404e37c127 more mailing list content;
wenzelm
parents: 74921
diff changeset
   473
15404e37c127 more mailing list content;
wenzelm
parents: 74921
diff changeset
   474
      val (title, author_address) =
15404e37c127 more mailing list content;
wenzelm
parents: 74921
diff changeset
   475
      {
15404e37c127 more mailing list content;
wenzelm
parents: 74921
diff changeset
   476
        message_match(head, """TITLE="([^"]+)">(.*)""".r) match {
74931
1753dade9a24 more data integrity: name vs. address;
wenzelm
parents: 74930
diff changeset
   477
          case Some(m) => (make_title(HTML.input(m.group(1))), make_name(HTML.input(m.group(2))))
74922
15404e37c127 more mailing list content;
wenzelm
parents: 74921
diff changeset
   478
          case None => err("Missing TITLE")
15404e37c127 more mailing list content;
wenzelm
parents: 74921
diff changeset
   479
        }
15404e37c127 more mailing list content;
wenzelm
parents: 74921
diff changeset
   480
      }
15404e37c127 more mailing list content;
wenzelm
parents: 74921
diff changeset
   481
15404e37c127 more mailing list content;
wenzelm
parents: 74921
diff changeset
   482
      val author_name =
15404e37c127 more mailing list content;
wenzelm
parents: 74921
diff changeset
   483
        message_match(head, """\s*<B>(.*)</B>""".r) match {
15404e37c127 more mailing list content;
wenzelm
parents: 74921
diff changeset
   484
          case None => err("Missing author")
74931
1753dade9a24 more data integrity: name vs. address;
wenzelm
parents: 74930
diff changeset
   485
          case Some(m) =>
1753dade9a24 more data integrity: name vs. address;
wenzelm
parents: 74930
diff changeset
   486
            val a = make_name(HTML.input(m.group(1)))
1753dade9a24 more data integrity: name vs. address;
wenzelm
parents: 74930
diff changeset
   487
            if (a == author_address) "" else a
74922
15404e37c127 more mailing list content;
wenzelm
parents: 74921
diff changeset
   488
        }
15404e37c127 more mailing list content;
wenzelm
parents: 74921
diff changeset
   489
74934
f5ad3214bef4 clarified signature: more operations;
wenzelm
parents: 74933
diff changeset
   490
      val tags = List(list_name)
f5ad3214bef4 clarified signature: more operations;
wenzelm
parents: 74933
diff changeset
   491
74935
dc62948c6080 more data integrity: name vs. address;
wenzelm
parents: 74934
diff changeset
   492
      Message(name, date, title, standard_name(author_name), author_address, body, tags)
74922
15404e37c127 more mailing list content;
wenzelm
parents: 74921
diff changeset
   493
    }
74921
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   494
  }
72558
38ebf696fd0c support for Mailman list servers;
wenzelm
parents:
diff changeset
   495
}