def parse_ingredients():
"""
This endpoint takes a url-encoded ingredient string and runs it through the
tagger. Requests should be in the form of:
http://example.com/parse?ingredient=some%20ingredient%20here
Multiple ingredients can be delimited with a newline character. (%0A url-encoded)
:return: JSON containing the tagged ingredient data
"""
ingredient_input = request.args.get("ingredient").split('\n')
input_ok, bad_resp = validate_input(ingredient_input)
json_result_fname = "%s.txt" % str(uuid.uuid4())
if not input_ok:
return bad_resp
_, tmp_file = tempfile.mkstemp()
with open(tmp_file, 'w') as input_file:
input_file.write(utils.export_data(ingredient_input))
input_file.flush()
input_file.close()
os.system("crf_test -v 1 -m %s %s > %s" % (modelFilename, tmp_file, json_result_fname))
os.remove(tmp_file)
json_output = json.dumps(utils.import_data(open(json_result_fname)), indent=4)
os.remove(json_result_fname)
resp = Response(u'%s' % json_output)
resp.headers['Content-Type'] = 'application/json; charset=utf-8'
return resp
def tag(ingredient_phrase):
with tempfile.NamedTemporaryFile(mode='w+',
encoding='utf-8') as input_file:
input_file.write(utils.export_data(ingredient_phrase))
input_file.flush()
processOutput = subprocess.check_output([
'crf_test', '--verbose=1', '--model', model_path, input_file.name
]).decode('utf-8')
return utils.import_data(processOutput.split('\n'))
def tag(ingredients_string):
_, tmpFile = tempfile.mkstemp()
with open(tmpFile, 'w') as outfile:
outfile.write(utils.export_data(ingredients_string.splitlines()))
modelFilename = "/ingredient-phrase-tagger/tmp/model_file"
result = subprocess.check_output("crf_test -v 1 -m %s %s" %
(modelFilename, tmpFile),
shell=True)
os.system("rm %s" % tmpFile)
return json.dumps(utils.import_data(result.splitlines()), indent=4)
def parse_ingredients(ingredients):
# take out any characters not suited for json
formatted_ingredients = [
i.replace(u'\xa0', ' ') \
.encode('ascii', 'ignore') \
.encode('utf-8') \
for i in ingredients ]
_, tmpFile = tempfile.mkstemp()
with open(tmpFile, 'w') as outfile:
outfile.write(utils.export_data(formatted_ingredients))
tmpFilePath = "tmp/model_file"
modelFilename = os.path.join(os.path.dirname(__file__), tmpFilePath)
command = ("crf_test -v 1 -m %s %s" % (modelFilename, tmpFile)).split(" ")
proc = subprocess.Popen(command, stdout=subprocess.PIPE)
output = proc.stdout.read()
parsed_ingredients = utils.import_data(output.split('\n'))
os.system("rm %s" % tmpFile)
return [i for i in parsed_ingredients if i.get('name')]
#!/usr/bin/env python
from __future__ import print_function
import sys
import json
from ingredient_phrase_tagger.training import utils
if len(sys.argv) < 2:
sys.stderr.write('Usage: make-data.py FILENAME')
sys.exit(1)
# the latin 1 bit here is naughty - we need to do unicode properly
print(
json.dumps(utils.import_data(open(sys.argv[1])),
indent=4,
encoding='latin1'))
def _convert_crf_output_to_json(crf_output):
return json.dumps(utils.import_data(crf_output), indent=2, sort_keys=True)
#!/usr/bin/env python
from __future__ import print_function
import sys
import json
from ingredient_phrase_tagger.training import utils
if len(sys.argv) < 2:
sys.stderr.write('Usage: make-data.py FILENAME')
sys.exit(1)
print(json.dumps(utils.import_data(open(sys.argv[1])), indent=4))
from __future__ import print_function
import sys
import os
import tempfile
import json
import subprocess
from ingredient_phrase_tagger.training import utils
_, tmpFile = tempfile.mkstemp()
with open(tmpFile, 'w') as outfile:
outfile.write(
utils.export_data(
['2 tablespoons cornstarch, dissolved in 2 tablespoons water']))
tmpFilePath = "tmp/model_file"
modelFilename = os.path.join(os.path.dirname(__file__), tmpFilePath)
command = ("crf_test -v 1 -m %s %s" % (modelFilename, tmpFile)).split(" ")
proc = subprocess.Popen(command, stdout=subprocess.PIPE)
output = proc.stdout.read()
print(json.dumps(utils.import_data(output.split('\n'))))
os.system("rm %s" % tmpFile)
import sys
import os
import tempfile
import StringIO
import json
import subprocess
from ingredient_phrase_tagger.training import utils
if len(sys.argv) < 2:
sys.stderr.write('Usage: parse-ingredients.py TEXT')
sys.exit(1)
text = sys.argv[1]
_, tmpFile = tempfile.mkstemp()
string_file = StringIO.StringIO(text)
text_file = open(tmpFile, "wt")
text_file.write(utils.export_data(string_file.readlines()))
text_file.close()
tmpFilePath = "../tmp/model_file"
modelFilename = os.path.join(os.path.dirname(__file__), tmpFilePath)
results = StringIO.StringIO(
subprocess.check_output(
["crf_test", "-v", "1", "-m", modelFilename, tmpFile]))
os.system("rm %s" % tmpFile)
results_json = (json.dumps(utils.import_data(results), indent=4))
print(results_json)
#!/usr/bin/env python
from __future__ import print_function
import sys
import json
from ingredient_phrase_tagger.training import utils
if len(sys.argv) < 2:
sys.stderr.write('Usage: make-data.py FILENAME')
sys.exit(1)
print(json.dumps(utils.import_data(open(sys.argv[1])), indent=4))
#!/usr/bin/env python
from __future__ import print_function
import sys
import os
import tempfile
import json
from ingredient_phrase_tagger.training import utils
if len(sys.argv) < 2:
sys.stderr.write('Usage: parse-ingredients-as-json.py FILENAME')
sys.exit(1)
FILENAME = str(sys.argv[1])
_, tmpFile = tempfile.mkstemp()
with open(FILENAME) as infile, open(tmpFile, 'w') as outfile:
outfile.write(utils.export_data(infile.readlines()))
tmpFilePath = "../tmp/model_file"
modelFilename = os.path.join(os.path.dirname(__file__), tmpFilePath)
parsed = os.popen("crf_test -v 1 -m %s %s" %
(modelFilename, tmpFile)).readlines()
os.system("rm %s" % tmpFile)
print(json.dumps(utils.import_data(parsed), indent=4))
#!/usr/bin/env python from __future__ import print_function import fileinput import json from ingredient_phrase_tagger.training import utils print(json.dumps(utils.import_data(fileinput.input()), indent=4)) fileinput.close()
