src/Pure/General/mailman.scala
author wenzelm
Tue, 14 Dec 2021 10:19:48 +0100
changeset 74934 f5ad3214bef4
parent 74933 0f27dcd030b8
child 74935 dc62948c6080
permissions -rw-r--r--
clarified signature: more operations;
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
74921
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
    21
  sealed case class Message(
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
    22
    name: String,
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
    23
    date: Date,
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
    24
    title: String,
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
    25
    author_name: String,
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
    26
    author_address: String,
74934
f5ad3214bef4 clarified signature: more operations;
wenzelm
parents: 74933
diff changeset
    27
    body: String,
f5ad3214bef4 clarified signature: more operations;
wenzelm
parents: 74933
diff changeset
    28
    tags: List[String])
72558
38ebf696fd0c support for Mailman list servers;
wenzelm
parents:
diff changeset
    29
  {
74925
4bc306cb2832 more data integrity: name vs. address;
wenzelm
parents: 74924
diff changeset
    30
    override def toString: String = name
74921
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
    31
    def print: String =
74922
15404e37c127 more mailing list content;
wenzelm
parents: 74921
diff changeset
    32
      name + "\n" + date + "\n" + title + "\n" +
15404e37c127 more mailing list content;
wenzelm
parents: 74921
diff changeset
    33
      quote(author_name) + "\n" + "<" + author_address + ">\n"
74931
1753dade9a24 more data integrity: name vs. address;
wenzelm
parents: 74930
diff changeset
    34
1753dade9a24 more data integrity: name vs. address;
wenzelm
parents: 74930
diff changeset
    35
    def normal_address: String = Word.lowercase(author_address)
74921
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
    36
  }
74906
9702913db56c more Mailman content;
wenzelm
parents: 74905
diff changeset
    37
74933
0f27dcd030b8 clarified signature;
wenzelm
parents: 74932
diff changeset
    38
  object Messages
74925
4bc306cb2832 more data integrity: name vs. address;
wenzelm
parents: 74924
diff changeset
    39
  {
74933
0f27dcd030b8 clarified signature;
wenzelm
parents: 74932
diff changeset
    40
    def apply(msgs: List[Message]): Messages =
0f27dcd030b8 clarified signature;
wenzelm
parents: 74932
diff changeset
    41
      new Messages(msgs.sortBy(_.date)(Date.Ordering))
74934
f5ad3214bef4 clarified signature: more operations;
wenzelm
parents: 74933
diff changeset
    42
f5ad3214bef4 clarified signature: more operations;
wenzelm
parents: 74933
diff changeset
    43
    def find(dir: Path): Messages =
f5ad3214bef4 clarified signature: more operations;
wenzelm
parents: 74933
diff changeset
    44
    {
f5ad3214bef4 clarified signature: more operations;
wenzelm
parents: 74933
diff changeset
    45
      val msgs =
f5ad3214bef4 clarified signature: more operations;
wenzelm
parents: 74933
diff changeset
    46
        for {
f5ad3214bef4 clarified signature: more operations;
wenzelm
parents: 74933
diff changeset
    47
          archive <- List(Isabelle_Users, Isabelle_Dev)
f5ad3214bef4 clarified signature: more operations;
wenzelm
parents: 74933
diff changeset
    48
          msg <- archive.find_messages(dir + Path.basic(archive.list_name))
f5ad3214bef4 clarified signature: more operations;
wenzelm
parents: 74933
diff changeset
    49
        } yield msg
f5ad3214bef4 clarified signature: more operations;
wenzelm
parents: 74933
diff changeset
    50
      Messages(msgs)
f5ad3214bef4 clarified signature: more operations;
wenzelm
parents: 74933
diff changeset
    51
    }
74933
0f27dcd030b8 clarified signature;
wenzelm
parents: 74932
diff changeset
    52
  }
0f27dcd030b8 clarified signature;
wenzelm
parents: 74932
diff changeset
    53
0f27dcd030b8 clarified signature;
wenzelm
parents: 74932
diff changeset
    54
  class Messages private(val sorted: List[Message])
0f27dcd030b8 clarified signature;
wenzelm
parents: 74932
diff changeset
    55
  {
0f27dcd030b8 clarified signature;
wenzelm
parents: 74932
diff changeset
    56
    override def toString: String = "Messages(" + sorted.length + ")"
74925
4bc306cb2832 more data integrity: name vs. address;
wenzelm
parents: 74924
diff changeset
    57
74933
0f27dcd030b8 clarified signature;
wenzelm
parents: 74932
diff changeset
    58
    def check(): Unit =
0f27dcd030b8 clarified signature;
wenzelm
parents: 74932
diff changeset
    59
    {
0f27dcd030b8 clarified signature;
wenzelm
parents: 74932
diff changeset
    60
      val proper = sorted.filter(msg => msg.author_name.nonEmpty && msg.author_address.nonEmpty)
0f27dcd030b8 clarified signature;
wenzelm
parents: 74932
diff changeset
    61
      val address_name = Multi_Map.from(proper.map(msg => (msg.normal_address, msg.author_name)))
0f27dcd030b8 clarified signature;
wenzelm
parents: 74932
diff changeset
    62
      val name_address = Multi_Map.from(proper.map(msg => (msg.author_name, msg.normal_address)))
74925
4bc306cb2832 more data integrity: name vs. address;
wenzelm
parents: 74924
diff changeset
    63
74933
0f27dcd030b8 clarified signature;
wenzelm
parents: 74932
diff changeset
    64
      def print_dup(a: String, bs: List[String]): String =
0f27dcd030b8 clarified signature;
wenzelm
parents: 74932
diff changeset
    65
        "  * " + a + bs.mkString("\n      ", "\n      ", "")
74925
4bc306cb2832 more data integrity: name vs. address;
wenzelm
parents: 74924
diff changeset
    66
74933
0f27dcd030b8 clarified signature;
wenzelm
parents: 74932
diff changeset
    67
      def print_dups(title: String, m: Multi_Map[String, String]): Unit =
0f27dcd030b8 clarified signature;
wenzelm
parents: 74932
diff changeset
    68
      {
0f27dcd030b8 clarified signature;
wenzelm
parents: 74932
diff changeset
    69
        val dups = m.iterator_list.filter(p => p._2.length > 1).toList
0f27dcd030b8 clarified signature;
wenzelm
parents: 74932
diff changeset
    70
        if (dups.nonEmpty) {
0f27dcd030b8 clarified signature;
wenzelm
parents: 74932
diff changeset
    71
          Output.writeln(cat_lines(title :: dups.map(p => print_dup(p._1, p._2))))
0f27dcd030b8 clarified signature;
wenzelm
parents: 74932
diff changeset
    72
        }
74925
4bc306cb2832 more data integrity: name vs. address;
wenzelm
parents: 74924
diff changeset
    73
      }
74933
0f27dcd030b8 clarified signature;
wenzelm
parents: 74932
diff changeset
    74
0f27dcd030b8 clarified signature;
wenzelm
parents: 74932
diff changeset
    75
      print_dups("\nduplicate names:", address_name)
0f27dcd030b8 clarified signature;
wenzelm
parents: 74932
diff changeset
    76
      print_dups("\nduplicate addresses:", name_address)
74925
4bc306cb2832 more data integrity: name vs. address;
wenzelm
parents: 74924
diff changeset
    77
74933
0f27dcd030b8 clarified signature;
wenzelm
parents: 74932
diff changeset
    78
      def get_name(msg: Message): Option[String] =
0f27dcd030b8 clarified signature;
wenzelm
parents: 74932
diff changeset
    79
        proper_string(msg.author_name) orElse address_name.get(msg.author_address)
74925
4bc306cb2832 more data integrity: name vs. address;
wenzelm
parents: 74924
diff changeset
    80
74933
0f27dcd030b8 clarified signature;
wenzelm
parents: 74932
diff changeset
    81
      val missing_name =
0f27dcd030b8 clarified signature;
wenzelm
parents: 74932
diff changeset
    82
        sorted.flatMap(msg =>
0f27dcd030b8 clarified signature;
wenzelm
parents: 74932
diff changeset
    83
          if (get_name(msg).isEmpty) Some(proper_string(msg.author_address).getOrElse(msg.name))
0f27dcd030b8 clarified signature;
wenzelm
parents: 74932
diff changeset
    84
          else None).toSet.toList.sorted
74925
4bc306cb2832 more data integrity: name vs. address;
wenzelm
parents: 74924
diff changeset
    85
74933
0f27dcd030b8 clarified signature;
wenzelm
parents: 74932
diff changeset
    86
      val missing_address =
0f27dcd030b8 clarified signature;
wenzelm
parents: 74932
diff changeset
    87
        sorted.flatMap(msg =>
0f27dcd030b8 clarified signature;
wenzelm
parents: 74932
diff changeset
    88
          if (msg.author_address.isEmpty) Some(proper_string(msg.author_name).getOrElse(msg.name))
0f27dcd030b8 clarified signature;
wenzelm
parents: 74932
diff changeset
    89
          else None).toSet.toList.sorted
74925
4bc306cb2832 more data integrity: name vs. address;
wenzelm
parents: 74924
diff changeset
    90
74933
0f27dcd030b8 clarified signature;
wenzelm
parents: 74932
diff changeset
    91
      if (missing_name.nonEmpty) {
0f27dcd030b8 clarified signature;
wenzelm
parents: 74932
diff changeset
    92
        Output.writeln(("missing name:" :: missing_name).mkString("\n", "\n  ", ""))
0f27dcd030b8 clarified signature;
wenzelm
parents: 74932
diff changeset
    93
      }
74931
1753dade9a24 more data integrity: name vs. address;
wenzelm
parents: 74930
diff changeset
    94
74933
0f27dcd030b8 clarified signature;
wenzelm
parents: 74932
diff changeset
    95
      if (missing_address.nonEmpty) {
0f27dcd030b8 clarified signature;
wenzelm
parents: 74932
diff changeset
    96
        Output.writeln(("missing address:" :: missing_address).mkString("\n", "\n  ", ""))
0f27dcd030b8 clarified signature;
wenzelm
parents: 74932
diff changeset
    97
      }
74925
4bc306cb2832 more data integrity: name vs. address;
wenzelm
parents: 74924
diff changeset
    98
    }
4bc306cb2832 more data integrity: name vs. address;
wenzelm
parents: 74924
diff changeset
    99
  }
4bc306cb2832 more data integrity: name vs. address;
wenzelm
parents: 74924
diff changeset
   100
4bc306cb2832 more data integrity: name vs. address;
wenzelm
parents: 74924
diff changeset
   101
74921
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   102
  /* mailing list archives */
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   103
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   104
  abstract class Archive(
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   105
    url: URL,
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   106
    name: String = "",
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   107
    tag: String = "")
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   108
  {
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   109
    def message_regex: Regex
74923
e0070487b635 clarified name;
wenzelm
parents: 74922
diff changeset
   110
    def message_content(name: String, lines: List[String]): Message
74921
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   111
74924
af954161e1cd misc tuning and clarification;
wenzelm
parents: 74923
diff changeset
   112
    def message_match(lines: List[String], re: Regex): Option[Match] =
af954161e1cd misc tuning and clarification;
wenzelm
parents: 74923
diff changeset
   113
      lines.flatMap(re.findFirstMatchIn(_)).headOption
af954161e1cd misc tuning and clarification;
wenzelm
parents: 74923
diff changeset
   114
74931
1753dade9a24 more data integrity: name vs. address;
wenzelm
parents: 74930
diff changeset
   115
    def make_name(str: String): String =
1753dade9a24 more data integrity: name vs. address;
wenzelm
parents: 74930
diff changeset
   116
      str.replaceAll("""\s+""", " ").replaceAll(" at ", "@")
74924
af954161e1cd misc tuning and clarification;
wenzelm
parents: 74923
diff changeset
   117
af954161e1cd misc tuning and clarification;
wenzelm
parents: 74923
diff changeset
   118
    def make_body(lines: List[String]): String =
af954161e1cd misc tuning and clarification;
wenzelm
parents: 74923
diff changeset
   119
      cat_lines(Library.take_suffix[String](_.isEmpty, lines)._1)
af954161e1cd misc tuning and clarification;
wenzelm
parents: 74923
diff changeset
   120
74921
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   121
    private val main_url: URL =
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   122
      Url(Library.take_suffix[Char](_ == '/', Url.trim_index(url).toString.toList)._1.mkString + "/")
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   123
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   124
    private val main_html = Url.read(main_url)
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   125
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   126
    val list_name: String =
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   127
    {
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   128
      val title =
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   129
        """<title>The ([^</>]*) Archives</title>""".r.findFirstMatchIn(main_html).map(_.group(1))
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   130
      (proper_string(name) orElse title).getOrElse(error("Failed to determine mailing list name"))
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   131
    }
72558
38ebf696fd0c support for Mailman list servers;
wenzelm
parents:
diff changeset
   132
    override def toString: String = list_name
38ebf696fd0c support for Mailman list servers;
wenzelm
parents:
diff changeset
   133
74923
e0070487b635 clarified name;
wenzelm
parents: 74922
diff changeset
   134
    def full_name(href: String): String = list_name + "/" + href
e0070487b635 clarified name;
wenzelm
parents: 74922
diff changeset
   135
74921
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   136
    def list_tag: String = proper_string(tag).getOrElse(list_name)
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   137
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   138
    def read_text(href: String): String = Url.read(new URL(main_url, href))
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   139
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   140
    def hrefs_text: List[String] =
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   141
      """href="([^"]+\.txt(?:\.gz)?)"""".r.findAllMatchIn(main_html).map(_.group(1)).toList
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   142
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   143
    def hrefs_msg: List[String] =
74906
9702913db56c more Mailman content;
wenzelm
parents: 74905
diff changeset
   144
      (for {
74921
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   145
        href <- """href="([^"]+)/date.html"""".r.findAllMatchIn(main_html).map(_.group(1))
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   146
        html = read_text(href + "/date.html")
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   147
        msg <- message_regex.findAllMatchIn(html).map(_.group(1))
74906
9702913db56c more Mailman content;
wenzelm
parents: 74905
diff changeset
   148
      } yield href + "/" + msg).toList
9702913db56c more Mailman content;
wenzelm
parents: 74905
diff changeset
   149
9702913db56c more Mailman content;
wenzelm
parents: 74905
diff changeset
   150
    def get(target_dir: Path, href: String, progress: Progress = new Progress): Option[Path] =
72558
38ebf696fd0c support for Mailman list servers;
wenzelm
parents:
diff changeset
   151
    {
38ebf696fd0c support for Mailman list servers;
wenzelm
parents:
diff changeset
   152
      val dir = target_dir + Path.basic(list_name)
74906
9702913db56c more Mailman content;
wenzelm
parents: 74905
diff changeset
   153
      val path = dir + Path.explode(href)
74921
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   154
      val url = new URL(main_url, href)
74906
9702913db56c more Mailman content;
wenzelm
parents: 74905
diff changeset
   155
      val connection = url.openConnection
9702913db56c more Mailman content;
wenzelm
parents: 74905
diff changeset
   156
      try {
9702913db56c more Mailman content;
wenzelm
parents: 74905
diff changeset
   157
        val length = connection.getContentLengthLong
9702913db56c more Mailman content;
wenzelm
parents: 74905
diff changeset
   158
        val timestamp = connection.getLastModified
9702913db56c more Mailman content;
wenzelm
parents: 74905
diff changeset
   159
        val file = path.file
9702913db56c more Mailman content;
wenzelm
parents: 74905
diff changeset
   160
        if (file.isFile && file.length == length && file.lastModified == timestamp) None
9702913db56c more Mailman content;
wenzelm
parents: 74905
diff changeset
   161
        else {
9702913db56c more Mailman content;
wenzelm
parents: 74905
diff changeset
   162
          Isabelle_System.make_directory(path.dir)
9702913db56c more Mailman content;
wenzelm
parents: 74905
diff changeset
   163
          progress.echo("Getting " + url)
9702913db56c more Mailman content;
wenzelm
parents: 74905
diff changeset
   164
          val bytes =
9702913db56c more Mailman content;
wenzelm
parents: 74905
diff changeset
   165
            using(connection.getInputStream)(Bytes.read_stream(_, hint = length.toInt max 1024))
9702913db56c more Mailman content;
wenzelm
parents: 74905
diff changeset
   166
          Bytes.write(file, bytes)
9702913db56c more Mailman content;
wenzelm
parents: 74905
diff changeset
   167
          file.setLastModified(timestamp)
9702913db56c more Mailman content;
wenzelm
parents: 74905
diff changeset
   168
          Some(path)
9702913db56c more Mailman content;
wenzelm
parents: 74905
diff changeset
   169
        }
9702913db56c more Mailman content;
wenzelm
parents: 74905
diff changeset
   170
      }
9702913db56c more Mailman content;
wenzelm
parents: 74905
diff changeset
   171
      finally { connection.getInputStream.close() }
9702913db56c more Mailman content;
wenzelm
parents: 74905
diff changeset
   172
    }
72558
38ebf696fd0c support for Mailman list servers;
wenzelm
parents:
diff changeset
   173
74906
9702913db56c more Mailman content;
wenzelm
parents: 74905
diff changeset
   174
    def download_text(target_dir: Path, progress: Progress = new Progress): List[Path] =
9702913db56c more Mailman content;
wenzelm
parents: 74905
diff changeset
   175
      hrefs_text.flatMap(get(target_dir, _, progress = progress))
9702913db56c more Mailman content;
wenzelm
parents: 74905
diff changeset
   176
9702913db56c more Mailman content;
wenzelm
parents: 74905
diff changeset
   177
    def download_msg(target_dir: Path, progress: Progress = new Progress): List[Path] =
9702913db56c more Mailman content;
wenzelm
parents: 74905
diff changeset
   178
      hrefs_msg.flatMap(get(target_dir, _, progress = progress))
74907
af2323593473 more Mailman archives;
wenzelm
parents: 74906
diff changeset
   179
af2323593473 more Mailman archives;
wenzelm
parents: 74906
diff changeset
   180
    def download(target_dir: Path, progress: Progress = new Progress): List[Path] =
af2323593473 more Mailman archives;
wenzelm
parents: 74906
diff changeset
   181
      download_text(target_dir, progress = progress) :::
af2323593473 more Mailman archives;
wenzelm
parents: 74906
diff changeset
   182
      download_msg(target_dir, progress = progress)
74921
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   183
74924
af954161e1cd misc tuning and clarification;
wenzelm
parents: 74923
diff changeset
   184
    def make_title(str: String): String =
74921
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   185
    {
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   186
      val Trim1 = ("""\s*\Q[""" + list_tag + """]\E\s*(.*)""").r
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   187
      val Trim2 = """(?i:(?:re|fw|fwd)\s*:\s*)(.*)""".r
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   188
      val Trim3 = """\[\s*(.*?)\s*\]""".r
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   189
      @tailrec def trim(s: String): String =
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   190
        s match {
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   191
          case Trim1(s1) => trim(s1)
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   192
          case Trim2(s1) => trim(s1)
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   193
          case Trim3(s1) => trim(s1)
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   194
          case _ => s
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   195
        }
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   196
      trim(str)
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   197
    }
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   198
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   199
    def get_messages(): List[Message] =
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   200
      for (href <- hrefs_msg) yield message_content(href, split_lines(read_text(href)))
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   201
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   202
    def find_messages(dir: Path): List[Message] =
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   203
    {
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   204
      for {
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   205
        file <- File.find_files(dir.file, file => file.getName.endsWith(".html"))
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   206
        rel_path <- File.relative_path(dir, File.path(file))
74923
e0070487b635 clarified name;
wenzelm
parents: 74922
diff changeset
   207
      }
e0070487b635 clarified name;
wenzelm
parents: 74922
diff changeset
   208
      yield {
e0070487b635 clarified name;
wenzelm
parents: 74922
diff changeset
   209
        val name = full_name(rel_path.implode)
e0070487b635 clarified name;
wenzelm
parents: 74922
diff changeset
   210
        message_content(name, split_lines(File.read(file)))
e0070487b635 clarified name;
wenzelm
parents: 74922
diff changeset
   211
      }
74921
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   212
    }
72558
38ebf696fd0c support for Mailman list servers;
wenzelm
parents:
diff changeset
   213
  }
72559
274c9986e55b maintain Isabelle mailing list archives;
wenzelm
parents: 72558
diff changeset
   214
74932
wenzelm
parents: 74931
diff changeset
   215
  private class Message_Chunk(bg: String = "", en: String = "")
wenzelm
parents: 74931
diff changeset
   216
  {
wenzelm
parents: 74931
diff changeset
   217
    def unapply(lines: List[String]): Option[List[String]] =
wenzelm
parents: 74931
diff changeset
   218
    {
wenzelm
parents: 74931
diff changeset
   219
      val res1 =
wenzelm
parents: 74931
diff changeset
   220
        if (bg.isEmpty) Some(lines)
wenzelm
parents: 74931
diff changeset
   221
        else {
wenzelm
parents: 74931
diff changeset
   222
          lines.dropWhile(_ != bg) match {
wenzelm
parents: 74931
diff changeset
   223
            case Nil => None
wenzelm
parents: 74931
diff changeset
   224
            case _ :: rest => Some(rest)
wenzelm
parents: 74931
diff changeset
   225
          }
wenzelm
parents: 74931
diff changeset
   226
        }
wenzelm
parents: 74931
diff changeset
   227
      if (en.isEmpty) res1
wenzelm
parents: 74931
diff changeset
   228
      else {
wenzelm
parents: 74931
diff changeset
   229
        res1 match {
wenzelm
parents: 74931
diff changeset
   230
          case None => None
wenzelm
parents: 74931
diff changeset
   231
          case Some(lines1) =>
wenzelm
parents: 74931
diff changeset
   232
            val lines2 = lines1.takeWhile(_ != en)
wenzelm
parents: 74931
diff changeset
   233
            if (lines1.drop(lines2.length).isEmpty) None else Some(lines2)
wenzelm
parents: 74931
diff changeset
   234
        }
wenzelm
parents: 74931
diff changeset
   235
      }
wenzelm
parents: 74931
diff changeset
   236
    }
wenzelm
parents: 74931
diff changeset
   237
wenzelm
parents: 74931
diff changeset
   238
    def get(lines: List[String]): List[String] =
wenzelm
parents: 74931
diff changeset
   239
      unapply(lines) getOrElse
wenzelm
parents: 74931
diff changeset
   240
        error("Missing delimiters:" +
wenzelm
parents: 74931
diff changeset
   241
          (if (bg.nonEmpty) " " else "") + bg +
wenzelm
parents: 74931
diff changeset
   242
          (if (en.nonEmpty) " " else "") + en)
wenzelm
parents: 74931
diff changeset
   243
  }
wenzelm
parents: 74931
diff changeset
   244
72559
274c9986e55b maintain Isabelle mailing list archives;
wenzelm
parents: 72558
diff changeset
   245
74930
e9506503efea tuned comments;
wenzelm
parents: 74925
diff changeset
   246
  /* isabelle-users mailing list */
72559
274c9986e55b maintain Isabelle mailing list archives;
wenzelm
parents: 72558
diff changeset
   247
74921
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   248
  object Isabelle_Users extends Archive(
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   249
    Url("https://lists.cam.ac.uk/pipermail/cl-isabelle-users"),
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   250
    name = "isabelle-users", tag = "isabelle")
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   251
  {
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   252
    override def message_regex: Regex = """<li><a name="\d+" href="(msg\d+\.html)">""".r
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   253
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   254
    private object Head extends
74922
15404e37c127 more mailing list content;
wenzelm
parents: 74921
diff changeset
   255
      Message_Chunk(bg = "<!--X-Head-of-Message-->", en = "<!--X-Head-of-Message-End-->")
74921
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   256
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   257
    private object Body extends
74922
15404e37c127 more mailing list content;
wenzelm
parents: 74921
diff changeset
   258
      Message_Chunk(bg = "<!--X-Body-of-Message-->", en = "<!--X-Body-of-Message-End-->")
15404e37c127 more mailing list content;
wenzelm
parents: 74921
diff changeset
   259
15404e37c127 more mailing list content;
wenzelm
parents: 74921
diff changeset
   260
    private object Date_Format
15404e37c127 more mailing list content;
wenzelm
parents: 74921
diff changeset
   261
    {
15404e37c127 more mailing list content;
wenzelm
parents: 74921
diff changeset
   262
      private val Trim1 = """\w+,\s*(.*)""".r
15404e37c127 more mailing list content;
wenzelm
parents: 74921
diff changeset
   263
      private val Trim2 = """(.*?)\s*\(.*\)""".r
15404e37c127 more mailing list content;
wenzelm
parents: 74921
diff changeset
   264
      private val Format =
15404e37c127 more mailing list content;
wenzelm
parents: 74921
diff changeset
   265
        Date.Format(
15404e37c127 more mailing list content;
wenzelm
parents: 74921
diff changeset
   266
          "d MMM uuuu H:m:s Z",
15404e37c127 more mailing list content;
wenzelm
parents: 74921
diff changeset
   267
          "d MMM uuuu H:m:s z",
15404e37c127 more mailing list content;
wenzelm
parents: 74921
diff changeset
   268
          "d MMM yy H:m:s Z",
15404e37c127 more mailing list content;
wenzelm
parents: 74921
diff changeset
   269
          "d MMM yy H:m:s z")
15404e37c127 more mailing list content;
wenzelm
parents: 74921
diff changeset
   270
      def unapply(s: String): Option[Date] =
15404e37c127 more mailing list content;
wenzelm
parents: 74921
diff changeset
   271
      {
15404e37c127 more mailing list content;
wenzelm
parents: 74921
diff changeset
   272
        val s0 = s.replaceAll("""\s+""", " ")
15404e37c127 more mailing list content;
wenzelm
parents: 74921
diff changeset
   273
        val s1 =
15404e37c127 more mailing list content;
wenzelm
parents: 74921
diff changeset
   274
          s0 match {
15404e37c127 more mailing list content;
wenzelm
parents: 74921
diff changeset
   275
            case Trim1(s1) => s1
15404e37c127 more mailing list content;
wenzelm
parents: 74921
diff changeset
   276
            case _ => s0
15404e37c127 more mailing list content;
wenzelm
parents: 74921
diff changeset
   277
          }
15404e37c127 more mailing list content;
wenzelm
parents: 74921
diff changeset
   278
        val s2 =
15404e37c127 more mailing list content;
wenzelm
parents: 74921
diff changeset
   279
          s1 match {
15404e37c127 more mailing list content;
wenzelm
parents: 74921
diff changeset
   280
            case Trim2(s2) => s2
15404e37c127 more mailing list content;
wenzelm
parents: 74921
diff changeset
   281
            case _ => s1
15404e37c127 more mailing list content;
wenzelm
parents: 74921
diff changeset
   282
          }
15404e37c127 more mailing list content;
wenzelm
parents: 74921
diff changeset
   283
        Format.unapply(s2)
15404e37c127 more mailing list content;
wenzelm
parents: 74921
diff changeset
   284
      }
15404e37c127 more mailing list content;
wenzelm
parents: 74921
diff changeset
   285
    }
74921
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   286
74924
af954161e1cd misc tuning and clarification;
wenzelm
parents: 74923
diff changeset
   287
    override def make_name(str: String): String =
74921
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   288
    {
74931
1753dade9a24 more data integrity: name vs. address;
wenzelm
parents: 74930
diff changeset
   289
      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
   290
      if (s == "cl-isabelle-users@lists.cam.ac.uk") "" else s
4bc306cb2832 more data integrity: name vs. address;
wenzelm
parents: 74924
diff changeset
   291
    }
4bc306cb2832 more data integrity: name vs. address;
wenzelm
parents: 74924
diff changeset
   292
74924
af954161e1cd misc tuning and clarification;
wenzelm
parents: 74923
diff changeset
   293
    object Address
af954161e1cd misc tuning and clarification;
wenzelm
parents: 74923
diff changeset
   294
    {
af954161e1cd misc tuning and clarification;
wenzelm
parents: 74923
diff changeset
   295
      private def anchor(s: String): String = """<a href="[^"]*">""" + s + """</a>"""
af954161e1cd misc tuning and clarification;
wenzelm
parents: 74923
diff changeset
   296
      private def angl(s: String): String = """&lt;""" + s + """&gt;"""
af954161e1cd misc tuning and clarification;
wenzelm
parents: 74923
diff changeset
   297
      private def quot(s: String): String = """&quot;""" + s + """&quot;"""
af954161e1cd misc tuning and clarification;
wenzelm
parents: 74923
diff changeset
   298
      private def paren(s: String): String = """\(""" + s + """\)"""
af954161e1cd misc tuning and clarification;
wenzelm
parents: 74923
diff changeset
   299
      private val adr = """([^<>]*? at [^<>]*?)"""
af954161e1cd misc tuning and clarification;
wenzelm
parents: 74923
diff changeset
   300
      private val any = """([^<>]*?)"""
af954161e1cd misc tuning and clarification;
wenzelm
parents: 74923
diff changeset
   301
      private val spc = """\s*"""
af954161e1cd misc tuning and clarification;
wenzelm
parents: 74923
diff changeset
   302
af954161e1cd misc tuning and clarification;
wenzelm
parents: 74923
diff changeset
   303
      private val Name1 = quot(anchor(any)).r
af954161e1cd misc tuning and clarification;
wenzelm
parents: 74923
diff changeset
   304
      private val Name2 = quot(any).r
af954161e1cd misc tuning and clarification;
wenzelm
parents: 74923
diff changeset
   305
      private val Name_Adr1 = (quot(anchor(any)) + spc + angl(anchor(adr))).r
af954161e1cd misc tuning and clarification;
wenzelm
parents: 74923
diff changeset
   306
      private val Name_Adr2 = (quot(any) + spc + angl(anchor(adr))).r
af954161e1cd misc tuning and clarification;
wenzelm
parents: 74923
diff changeset
   307
      private val Name_Adr3 = (anchor(any) + spc + angl(anchor(adr))).r
af954161e1cd misc tuning and clarification;
wenzelm
parents: 74923
diff changeset
   308
      private val Name_Adr4 = (any + spc + angl(anchor(adr))).r
af954161e1cd misc tuning and clarification;
wenzelm
parents: 74923
diff changeset
   309
      private val Adr_Name1 = (angl(anchor(adr)) + spc + paren(any)).r
af954161e1cd misc tuning and clarification;
wenzelm
parents: 74923
diff changeset
   310
      private val Adr_Name2 = (anchor(adr) + spc + paren(any)).r
af954161e1cd misc tuning and clarification;
wenzelm
parents: 74923
diff changeset
   311
      private val Adr1 = angl(anchor(adr)).r
af954161e1cd misc tuning and clarification;
wenzelm
parents: 74923
diff changeset
   312
      private val Adr2 = anchor(adr).r
af954161e1cd misc tuning and clarification;
wenzelm
parents: 74923
diff changeset
   313
af954161e1cd misc tuning and clarification;
wenzelm
parents: 74923
diff changeset
   314
      def unapply(s: String): Option[(String, String)] =
af954161e1cd misc tuning and clarification;
wenzelm
parents: 74923
diff changeset
   315
        s match {
74931
1753dade9a24 more data integrity: name vs. address;
wenzelm
parents: 74930
diff changeset
   316
          case Name1(a) => Some((make_name(a), ""))
1753dade9a24 more data integrity: name vs. address;
wenzelm
parents: 74930
diff changeset
   317
          case Name2(a) => Some((make_name(a), ""))
1753dade9a24 more data integrity: name vs. address;
wenzelm
parents: 74930
diff changeset
   318
          case Name_Adr1(a, b) => Some((make_name(a), make_name(b)))
1753dade9a24 more data integrity: name vs. address;
wenzelm
parents: 74930
diff changeset
   319
          case Name_Adr2(a, b) => Some((make_name(a), make_name(b)))
1753dade9a24 more data integrity: name vs. address;
wenzelm
parents: 74930
diff changeset
   320
          case Name_Adr3(a, b) => Some((make_name(a), make_name(b)))
1753dade9a24 more data integrity: name vs. address;
wenzelm
parents: 74930
diff changeset
   321
          case Name_Adr4(a, b) => Some((make_name(a), make_name(b)))
1753dade9a24 more data integrity: name vs. address;
wenzelm
parents: 74930
diff changeset
   322
          case Adr_Name1(b, a) => Some((make_name(a), make_name(b)))
1753dade9a24 more data integrity: name vs. address;
wenzelm
parents: 74930
diff changeset
   323
          case Adr_Name2(b, a) => Some((make_name(a), make_name(b)))
1753dade9a24 more data integrity: name vs. address;
wenzelm
parents: 74930
diff changeset
   324
          case Adr1(a) => Some(("", make_name(a)))
1753dade9a24 more data integrity: name vs. address;
wenzelm
parents: 74930
diff changeset
   325
          case Adr2(a) => Some(("", make_name(a)))
74924
af954161e1cd misc tuning and clarification;
wenzelm
parents: 74923
diff changeset
   326
          case _ => None
af954161e1cd misc tuning and clarification;
wenzelm
parents: 74923
diff changeset
   327
        }
af954161e1cd misc tuning and clarification;
wenzelm
parents: 74923
diff changeset
   328
    }
af954161e1cd misc tuning and clarification;
wenzelm
parents: 74923
diff changeset
   329
74923
e0070487b635 clarified name;
wenzelm
parents: 74922
diff changeset
   330
    override def message_content(name: String, lines: List[String]): Message =
74921
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   331
    {
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   332
      def err(msg: String = ""): Nothing =
74923
e0070487b635 clarified name;
wenzelm
parents: 74922
diff changeset
   333
        error("Malformed message: " + name + (if (msg.isEmpty) "" else "\n" + msg))
74921
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   334
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   335
      val (head, body) =
74924
af954161e1cd misc tuning and clarification;
wenzelm
parents: 74923
diff changeset
   336
        try { (Head.get(lines), make_body(Body.get(lines))) }
74921
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   337
        catch { case ERROR(msg) => err(msg) }
72559
274c9986e55b maintain Isabelle mailing list archives;
wenzelm
parents: 72558
diff changeset
   338
74921
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   339
      val date =
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   340
        message_match(head, """<li><em>Date</em>:\s*(.*?)\s*</li>""".r)
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   341
          .map(m => HTML.input(m.group(1))) match
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   342
        {
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   343
          case Some(Date_Format(d)) => d
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   344
          case Some(s) => err("Malformed Date: " + quote(s))
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   345
          case None => err("Missing Date")
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   346
        }
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   347
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   348
      val title =
74924
af954161e1cd misc tuning and clarification;
wenzelm
parents: 74923
diff changeset
   349
        make_title(
af954161e1cd misc tuning and clarification;
wenzelm
parents: 74923
diff changeset
   350
          HTML.input(message_match(head, """<li><em>Subject</em>:\s*(.*)</li>""".r)
af954161e1cd misc tuning and clarification;
wenzelm
parents: 74923
diff changeset
   351
            .getOrElse(err("Missing Subject")).group(1)))
74921
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   352
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   353
      val (author_name, author_address) =
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   354
        message_match(head, """<li><em>From</em>:\s*(.*?)\s*</li>""".r) match {
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   355
          case None => err("Missing From")
74925
4bc306cb2832 more data integrity: name vs. address;
wenzelm
parents: 74924
diff changeset
   356
          case Some(m) =>
74931
1753dade9a24 more data integrity: name vs. address;
wenzelm
parents: 74930
diff changeset
   357
            val (a0, b0) = Address.unapply(m.group(1)) getOrElse err("Malformed From")
1753dade9a24 more data integrity: name vs. address;
wenzelm
parents: 74930
diff changeset
   358
            val a = HTML.input(a0)
1753dade9a24 more data integrity: name vs. address;
wenzelm
parents: 74930
diff changeset
   359
            val b = HTML.input(b0)
74925
4bc306cb2832 more data integrity: name vs. address;
wenzelm
parents: 74924
diff changeset
   360
            (if (a == b) "" else a, b)
74921
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   361
        }
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   362
74934
f5ad3214bef4 clarified signature: more operations;
wenzelm
parents: 74933
diff changeset
   363
      val tags = List(list_name)
f5ad3214bef4 clarified signature: more operations;
wenzelm
parents: 74933
diff changeset
   364
f5ad3214bef4 clarified signature: more operations;
wenzelm
parents: 74933
diff changeset
   365
      Message(name, date, title, author_name, author_address, body, tags)
74921
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   366
    }
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   367
  }
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   368
74930
e9506503efea tuned comments;
wenzelm
parents: 74925
diff changeset
   369
e9506503efea tuned comments;
wenzelm
parents: 74925
diff changeset
   370
  /* isabelle-dev mailing list */
e9506503efea tuned comments;
wenzelm
parents: 74925
diff changeset
   371
74921
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   372
  object Isabelle_Dev extends Archive(Url("https://mailmanbroy.in.tum.de/pipermail/isabelle-dev"))
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   373
  {
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   374
    override def message_regex: Regex = """<LI><A HREF="(\d+\.html)">""".r
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   375
74922
15404e37c127 more mailing list content;
wenzelm
parents: 74921
diff changeset
   376
    private object Head extends Message_Chunk(en = "<!--beginarticle-->")
15404e37c127 more mailing list content;
wenzelm
parents: 74921
diff changeset
   377
    private object Body extends Message_Chunk(bg = "<!--beginarticle-->", en = "<!--endarticle-->")
15404e37c127 more mailing list content;
wenzelm
parents: 74921
diff changeset
   378
15404e37c127 more mailing list content;
wenzelm
parents: 74921
diff changeset
   379
    private object Date_Format
15404e37c127 more mailing list content;
wenzelm
parents: 74921
diff changeset
   380
    {
15404e37c127 more mailing list content;
wenzelm
parents: 74921
diff changeset
   381
      val Format = Date.Format("E MMM d H:m:s z uuuu")
15404e37c127 more mailing list content;
wenzelm
parents: 74921
diff changeset
   382
      def unapply(s: String): Option[Date] = Format.unapply(s.replaceAll("""\s+""", " "))
15404e37c127 more mailing list content;
wenzelm
parents: 74921
diff changeset
   383
    }
15404e37c127 more mailing list content;
wenzelm
parents: 74921
diff changeset
   384
74931
1753dade9a24 more data integrity: name vs. address;
wenzelm
parents: 74930
diff changeset
   385
    override def make_name(str: String): String =
1753dade9a24 more data integrity: name vs. address;
wenzelm
parents: 74930
diff changeset
   386
    {
1753dade9a24 more data integrity: name vs. address;
wenzelm
parents: 74930
diff changeset
   387
      val s = Library.perhaps_unsuffix("via RT", super.make_name(str))
1753dade9a24 more data integrity: name vs. address;
wenzelm
parents: 74930
diff changeset
   388
      if (s == "sys-admin@cl.cam.ac.uk") "" else s
1753dade9a24 more data integrity: name vs. address;
wenzelm
parents: 74930
diff changeset
   389
    }
1753dade9a24 more data integrity: name vs. address;
wenzelm
parents: 74930
diff changeset
   390
74923
e0070487b635 clarified name;
wenzelm
parents: 74922
diff changeset
   391
    override def message_content(name: String, lines: List[String]): Message =
74922
15404e37c127 more mailing list content;
wenzelm
parents: 74921
diff changeset
   392
    {
15404e37c127 more mailing list content;
wenzelm
parents: 74921
diff changeset
   393
      def err(msg: String = ""): Nothing =
74923
e0070487b635 clarified name;
wenzelm
parents: 74922
diff changeset
   394
        error("Malformed message: " + name + (if (msg.isEmpty) "" else "\n" + msg))
74922
15404e37c127 more mailing list content;
wenzelm
parents: 74921
diff changeset
   395
15404e37c127 more mailing list content;
wenzelm
parents: 74921
diff changeset
   396
      val (head, body) =
74924
af954161e1cd misc tuning and clarification;
wenzelm
parents: 74923
diff changeset
   397
        try { (Head.get(lines), make_body(Body.get(lines))) }
74922
15404e37c127 more mailing list content;
wenzelm
parents: 74921
diff changeset
   398
        catch { case ERROR(msg) => err(msg) }
15404e37c127 more mailing list content;
wenzelm
parents: 74921
diff changeset
   399
15404e37c127 more mailing list content;
wenzelm
parents: 74921
diff changeset
   400
      val date =
15404e37c127 more mailing list content;
wenzelm
parents: 74921
diff changeset
   401
        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
   402
          case Some(Date_Format(d)) => d
15404e37c127 more mailing list content;
wenzelm
parents: 74921
diff changeset
   403
          case Some(s) => err("Malformed Date: " + quote(s))
15404e37c127 more mailing list content;
wenzelm
parents: 74921
diff changeset
   404
          case None => err("Missing Date")
15404e37c127 more mailing list content;
wenzelm
parents: 74921
diff changeset
   405
        }
15404e37c127 more mailing list content;
wenzelm
parents: 74921
diff changeset
   406
15404e37c127 more mailing list content;
wenzelm
parents: 74921
diff changeset
   407
      val (title, author_address) =
15404e37c127 more mailing list content;
wenzelm
parents: 74921
diff changeset
   408
      {
15404e37c127 more mailing list content;
wenzelm
parents: 74921
diff changeset
   409
        message_match(head, """TITLE="([^"]+)">(.*)""".r) match {
74931
1753dade9a24 more data integrity: name vs. address;
wenzelm
parents: 74930
diff changeset
   410
          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
   411
          case None => err("Missing TITLE")
15404e37c127 more mailing list content;
wenzelm
parents: 74921
diff changeset
   412
        }
15404e37c127 more mailing list content;
wenzelm
parents: 74921
diff changeset
   413
      }
15404e37c127 more mailing list content;
wenzelm
parents: 74921
diff changeset
   414
15404e37c127 more mailing list content;
wenzelm
parents: 74921
diff changeset
   415
      val author_name =
15404e37c127 more mailing list content;
wenzelm
parents: 74921
diff changeset
   416
        message_match(head, """\s*<B>(.*)</B>""".r) match {
15404e37c127 more mailing list content;
wenzelm
parents: 74921
diff changeset
   417
          case None => err("Missing author")
74931
1753dade9a24 more data integrity: name vs. address;
wenzelm
parents: 74930
diff changeset
   418
          case Some(m) =>
1753dade9a24 more data integrity: name vs. address;
wenzelm
parents: 74930
diff changeset
   419
            val a = make_name(HTML.input(m.group(1)))
1753dade9a24 more data integrity: name vs. address;
wenzelm
parents: 74930
diff changeset
   420
            if (a == author_address) "" else a
74922
15404e37c127 more mailing list content;
wenzelm
parents: 74921
diff changeset
   421
        }
15404e37c127 more mailing list content;
wenzelm
parents: 74921
diff changeset
   422
74934
f5ad3214bef4 clarified signature: more operations;
wenzelm
parents: 74933
diff changeset
   423
      val tags = List(list_name)
f5ad3214bef4 clarified signature: more operations;
wenzelm
parents: 74933
diff changeset
   424
f5ad3214bef4 clarified signature: more operations;
wenzelm
parents: 74933
diff changeset
   425
      Message(name, date, title, author_name, author_address, body, tags)
74922
15404e37c127 more mailing list content;
wenzelm
parents: 74921
diff changeset
   426
    }
74921
74655fd58f8e more mailing list content;
wenzelm
parents: 74907
diff changeset
   427
  }
72558
38ebf696fd0c support for Mailman list servers;
wenzelm
parents:
diff changeset
   428
}