Dealing with string issues (issue #79).

components/classifier/wrapper.py

@@ -11,6 +11,7 @@
 from library.main import LIBRARY
 from utilities import logger, mallet
 from components.classifier import vectors
+from io import open
 
 TTK_ROOT = os.environ['TTK_ROOT']
 

components/common_modules/chunks.py

@@ -29,6 +29,7 @@
 from components.evita.settings import EVITA_NOM_WNPRIMSENSE_ONLY
 
 from utilities import logger
+from io import open
 
 
 # Get the Bayesian event recognizer

components/evita/wordnet.py

@@ -8,6 +8,7 @@
 from library import forms
 import utilities.binsearch as binsearch
 import utilities.logger as logger
+from io import open
 
 
 # Open dbm's with information about nominal events. If that does not work, open

components/evita/wrapper.py

@@ -8,6 +8,7 @@
 from library.tarsqi_constants import EVITA
 from library.main import LIBRARY
 from components.evita.main import Evita
+from io import open
 
 
 # Set this to True if you want to do a simplistic evaluation of how many of the

components/merging/sputlink/graph.py

@@ -19,6 +19,7 @@
 from .mappings import abbreviate_convex_relation
 from utilities import logger
 from library.main import LIBRARY
+from io import open
 
 DEBUG = True
 DEBUG = False

components/merging/sputlink/main.py

@@ -8,6 +8,7 @@
 from .utils import CompositionTable
 from .utils import html_graph_prefix
 from library.main import LIBRARY
+from io import open
 
 DEBUG = False
 DEBUG = True

components/merging/sputlink/rules/generateRules.py

@@ -14,6 +14,7 @@
      Node, EventNode, TimexNode, Point, Link, PLink 
 
 from closure import Axiom, Closure
+from io import open
 
 settings = {}
 settings['debug'] = 0

components/merging/sputlink/utils.py

@@ -1,5 +1,7 @@
 
 
+from __future__ import absolute_import
+from io import open
 def intersect_relations(rels1, rels2):
     """Returns the intersection of two relation sets. Returns None if both
     of the two sets are None."""

components/simpletime/main.py

@@ -1,5 +1,6 @@
 from __future__ import absolute_import
 import os, sys
+from io import open
 
 
 def elements_file():

deprecated/demo/display.py

@@ -27,6 +27,7 @@
 import os
 from docmodel.xml_parser import Parser, create_dct_element
 from library.tarsqi_constants import BLINKER, SLINKET, S2T, CLASSIFIER
+from io import open
 
 TTK_ROOT = os.environ['TTK_ROOT']
 

deprecated/get_lexes.py

@@ -19,6 +19,7 @@
 import sys, os
 
 from xml.dom.minidom import parse
+from io import open
 
 
 def getText(nodelist):

deprecated/get_tags.py

@@ -12,6 +12,7 @@
 import os, glob
 
 from xml.dom import minidom
+from io import open
 
 
 INDIR = "data/out/Timebank"

deprecated/gui.py

@@ -20,6 +20,7 @@
 from docmodel.xml_parser import Parser
 from library.tarsqi_constants import PREPROCESSOR, GUTIME, EVITA, SLINKET, S2T
 from library.tarsqi_constants import CLASSIFIER, BLINKER, CLASSIFIER, LINK_MERGER
+from io import open
 
 TTK_ROOT = os.environ['TTK_ROOT']
 

deprecated/sputlink/rule_creation/generateRules.py

@@ -13,6 +13,7 @@
      Node, EventNode, TimexNode, Point, Link, PLink 
 
 from closure import Axiom, Closure
+from io import open
 
 settings = {}
 settings['debug'] = 0

deprecated/xml_parser.py

@@ -18,6 +18,7 @@
 from types import UnicodeType, IntType, StringType, NoneType
 import xml.parsers.expat
 from xml.sax.saxutils import escape, quoteattr
+from io import open
 
 
 # variable used for assigning unique IDs to XmlDocElements

docmodel/document.py

@@ -12,6 +12,7 @@
 
 from library.main import LIBRARY
 from utilities import logger
+from io import open
 
 
 TIMEX = LIBRARY.timeml.TIMEX

docmodel/main.py

@@ -21,6 +21,7 @@
 from docmodel.docstructure_parser import DocumentStructureParser
 
 from utilities import logger
+from io import open
 
 
 PARSERS = {'ttk': (SourceParserTTK, MetadataParserTTK),

docmodel/source_parser.py

@@ -43,6 +43,7 @@
 
 from docmodel.document import SourceDoc, ProcessingStep
 from utilities.lif import Container, LIF
+from io import open
 
 
 class SourceParser(object):
@@ -214,7 +215,11 @@ def parse_file(self, filename, tarsqidoc):
         text and tags in SourceDoc."""
         self.sourcedoc = SourceDoc(filename)
         # TODO: should this be codecs.open() for non-ascii?
-        self.parser.ParseFile(open(filename))
+        # self.parser.ParseFile(open(filename))
+        # NOTE: actually, the above line needed to replaced with the following
+        # while preparing to port code to Python3.
+        content = open(filename).read()
+        self.parser.Parse(content)
         self.sourcedoc.finish()
         tarsqidoc.sourcedoc = self.sourcedoc