process dgt

dgt/.gitignore

@@ -0,0 +1,3 @@
+DGT*
+ids.txt
+ids_sources.txt

dgt/process_dgt_ids.py

@@ -0,0 +1,24 @@
+#!/usr/bin/python3
+# -*- coding: utf-8 -*-
+
+import sys, re
+
+p = re.compile(r'^pl/([A-Z0-9]+).*\.xml\.gz$')
+
+ids_dictionary = {}
+next_free = 0
+
+with open('DGT.ids') as in_ids, open('ids.txt', 'w') as out_ids, open('ids_sources.txt','w') as out_ids_sources:
+    for line in in_ids:
+        fields = line.split('\t')
+        filename = fields[1]
+        m = p.match(filename)
+        if not m:
+            print('Wrong line: '+line.rstrip())
+        else:
+            doc_number = m.group(1)
+            if not doc_number in ids_dictionary:
+                ids_dictionary[doc_number] = next_free
+                out_ids_sources.write('%d\thttps://eur-lex.europa.eu/legal-content/PL/TXT/?uri=CELEX:%s\tBaza aktów prawnych Unii Europejskiej\n' % (next_free,doc_number))
+                next_free += 1
+            out_ids.write(str(ids_dictionary[doc_number])+'\n')