Fixes #1157 by renaming filelock to filelock_brat

server/src/annotation.py

@@ -3,7 +3,6 @@
 # vim:set ft=python ts=4 sw=4 sts=4 autoindent:
 
 from __future__ import with_statement
-
 '''
 Functionality related to the annotation file format.
 
@@ -25,7 +24,7 @@
 from re import compile as re_compile
 
 from common import ProtocolError
-from filelock import file_lock
+from filelock_brat import file_lock
 from message import Messager
 
 

server/src/backup.py

@@ -24,7 +24,7 @@
 from os import listdir, walk
 from subprocess import Popen, PIPE
 
-from filelock import file_lock, PID_WARN
+from filelock_brat import file_lock, PID_WARN
 
 from config import BACKUP_DIR, DATA_DIR
 

tools/anntoconll.py

@@ -11,7 +11,9 @@
 from collections import namedtuple
 from os import path
 from subprocess import Popen, PIPE
-from cStringIO import StringIO
+#from cStringIO import StringIO
+from StringIO import StringIO
+from codecs import open
 
 # assume script in brat tools/ directory, extend path to find sentencesplit.py
 sys.path.append(os.path.join(os.path.dirname(__file__), '../server/src'))
@@ -203,7 +205,7 @@ def process_files(files):
                 if fn == '-':
                     lines = process(sys.stdin)
                 else:
-                    with open(fn, 'rU') as f:
+                    with open(fn, 'rU', "utf8") as f:
                         lines = process(f)
 
                 # TODO: better error handling
@@ -214,7 +216,7 @@ def process_files(files):
                     sys.stdout.write(''.join(lines))
                 else:
                     ofn = path.splitext(fn)[0]+options.outsuffix
-                    with open(ofn, 'wt') as of:
+                    with open(ofn, 'wt', "utf8") as of:
                         of.write(''.join(lines))
 
             except:
@@ -278,7 +280,7 @@ def get_annotations(fn):
 
     annfn = path.splitext(fn)[0]+options.annsuffix
 
-    with open(annfn, 'rU') as f:
+    with open(annfn, 'rU', "utf8") as f:
         textbounds = parse_textbounds(f)
 
     textbounds = eliminate_overlaps(textbounds)

tools/conll02tostandoff.py

@@ -148,7 +148,7 @@ def process(fn):
             token, tag = m.groups()
 
             # parse tag
-            m = re.match(r'^([BIO])((?:-[A-Za-z_]+)?)$', tag)
+            m = re.match(r'^([BIO])((?:-[A-Za-z_\-]+)?)$', tag)
             assert m, "ERROR: failed to parse tag '%s' in %s" % (tag, fn)
             ttag, ttype = m.groups()
             if len(ttype) > 0 and ttype[0] == "-":