Deleted xmark dataset.

We don't use it. It is archived on Nextcloud in 'ted-join-leftovers'.

xmark/README.md

-# X-Mark
-
-NOT FINISHED.
\ No newline at end of file

xmark/download.sh

-#!/bin/bash
-
-# Download the XML file.
-wget -v http://www.ins.cwi.nl/projects/xmark/Assets/standard.gz
-
-# Download the DTD file.
-wget -v http://www.ins.cwi.nl/projects/xmark/Assets/auction.dtd
-
-# Extract the XML file.
-gzip -d standard.gz
\ No newline at end of file

xmark/sort_dataset.sh

-#!/bin/bash
-
-#      | sort by number of nodes (equivalent to number of "{")
-cat $1 | awk '{print gsub("{","{"), $0}' | sort -n  | cut -d' ' -f2- > "${1%.bracket}_sorted.bracket"

xmark/xmark_to_bracket.py

-from lxml import etree
-import lxml.sax
-from xml.sax.handler import ContentHandler
-
-# This class implements the sax-like events for converting XML elemnts into
-# bracket-notation nodes and labels.
-class XMarkContentHandler(ContentHandler):
-    def __init__(self):
-        self.bn = ""
-
-    # Open tag.
-    def startElementNS(self, name, qname, attributes):
-        uri, localname = name
-        self.bn += "{" + localname
-        d = dict(attributes)
-        # Sort the attributes by their keys.
-        for key, value in sorted(d.items(), key = lambda element : element[0][1]):
-            self.bn += "{" + key[1].translate(str.maketrans({"{":  r"\{",
-                                          "}":  r"\}",
-                                          "\\": r"\\"})) + "{" + value.translate(str.maketrans({"{":  r"\{",
-                                          "}":  r"\}",
-                                          "\\": r"\\"})) + "}}"
-
-    # Close tag.
-    def endElementNS(self, name, qname):
-        self.bn += "}"
-
-    # Tag content.
-    def characters(self, data):
-        self.bn += "{" + data.translate(str.maketrans({"{":  r"\{",
-                                          "}":  r"\}",
-                                          "\\": r"\\"})) + "}"
-
-print("--- Loading XMARK dataset.")
-
-xmark_parser = etree.XMLParser(load_dtd=True, remove_blank_text=True)
-xmark_data_tree = etree.parse('standard', xmark_parser)
-root = xmark_data_tree.getroot()
-
-# Output files.
-xmark_bracket = open('xmark.bracket', 'w')
-
-print("--- Processing each child of xmark's root.")
-
-tree_id = 0
-for child in root:
-    tree_id += 1
-    # Printing simple progress.
-    if tree_id % 1000 == 0:
-        print("- Tree %s" % (tree_id))
-    handler = XMarkContentHandler()
-    lxml.sax.saxify(child, handler)
-    xmark_bracket.write(handler.bn + "\n")
-
-print("--- Closing output files.")
-xmark_bracket.close()
-