def process_file(gold_dir, fname):
infile = os.path.join(gold_dir, fname)
source_parser = create_source_parser(options)
tarsqidoc = source_parser.parse_file(infile)
(ee_vectors, et_vectors) = collect_tarsqidoc_vectors(tarsqidoc)
tlinks = collect_tlinks(tarsqidoc)
add_reltype_to_vectors(tlinks, ee_vectors, et_vectors)
write_vectors(ee_vectors, et_vectors)
def load(infile):
options = tarsqi.Options([('--source', 'timebank')])
source_parser = create_source_parser(options)
metadata_parser = create_metadata_parser(options)
docstructure_parser = create_docstructure_parser()
tarsqidoc = source_parser.parse_file(infile)
metadata_parser.parse(tarsqidoc)
docstructure_parser.parse(tarsqidoc)
tarsqidoc.add_options(options)
for tagname in TIMEML_TAGS:
tarsqidoc.tags.import_tags(tarsqidoc.source.tags, tagname)
tarsqidoc.source.tags.remove_tags(tagname)
return tarsqidoc
def load(infile):
options = tarsqi.Options([('--source', 'timebank')])
source_parser = create_source_parser(options)
metadata_parser = create_metadata_parser(options)
docstructure_parser = create_docstructure_parser()
tarsqidoc = source_parser.parse_file(infile)
metadata_parser.parse(tarsqidoc)
docstructure_parser.parse(tarsqidoc)
tarsqidoc.add_options(options)
for tagname in TIMEML_TAGS:
tarsqidoc.tags.import_tags(tarsqidoc.source.tags, tagname)
tarsqidoc.source.tags.remove_tags(tagname)
return tarsqidoc
def __init__(self, opts, infile, outfile):
"""Initialize Tarsqi object conform the data source identifier and the
processing options. Does not set the instance variables related to the
document model and the meta data. The opts argument has a list of
commanid line options and the infile and outfile arguments are typically
absolute paths, but they can be None when we are processing strings."""
# Make sure we're in the right directory. If the toolkit crashed on a
# previous file we may be in a different directory.
os.chdir(TTK_ROOT)
self.input = infile
self.output = outfile
self.basename = _basename(infile) if infile else None
self.options = Options(opts)
if self.options.loglevel:
logger.set_level(self.options.loglevel)
self.DIR_TMP_DATA = os.path.join(TTK_ROOT, 'data', 'tmp')
self.components = COMPONENTS
self.source_parser = create_source_parser(self.options)
self.metadata_parser = create_metadata_parser(self.options)
self.docstructure_parser = create_docstructure_parser()
self.pipeline = self._create_pipeline()
def __init__(self, opts, infile, outfile):
"""Initialize Tarsqi object conform the data source identifier and the
processing options. Does not set the instance variables related to the
document model and the meta data. The opts argument has a list of
commanid line options and the infile and outfile arguments are typically
absolute paths, but they can be None when we are processing strings."""
# Make sure we're in the right directory. If the toolkit crashed on a
# previous file we may be in a different directory.
os.chdir(TTK_ROOT)
self.input = infile
self.output = outfile
self.basename = _basename(infile) if infile else None
self.options = Options(opts)
if self.options.loglevel:
logger.set_level(self.options.loglevel)
self.DIR_TMP_DATA = os.path.join(TTK_ROOT, 'data', 'tmp')
self.components = COMPONENTS
self.source_parser = create_source_parser(self.options)
self.metadata_parser = create_metadata_parser(self.options)
self.docstructure_parser = create_docstructure_parser()
self.pipeline = self._create_pipeline()
def _initialize_parsers(self):
self.source_parser = create_source_parser(self.options)
self.metadata_parser = create_metadata_parser(self.options)
self.docstructure_parser = create_docstructure_parser()
def _initialize_parsers(self):
self.source_parser = create_source_parser(self.options)
self.metadata_parser = create_metadata_parser(self.options)
self.docstructure_parser = create_docstructure_parser()