DOI extractor

chemdataextractor/doc/text.py

@@ -26,6 +26,7 @@
 from ..parse.mp import MpParser
 from ..parse.tg import TgParser
 from ..parse.nmr import NmrParser
+from ..parse.doi import DoiParser
 from ..parse.uvvis import UvvisParser
 from ..nlp.lexicon import ChemLexicon
 from ..nlp.cem import CemTagger, IGNORE_PREFIX, IGNORE_SUFFIX, SPECIALS, SPLITS
@@ -266,7 +267,8 @@ def _repr_html_(self):
 
 class Paragraph(Text):
 
-    parsers = [CompoundParser(), ChemicalLabelParser(), NmrParser(), IrParser(), UvvisParser(), MpParser(), TgParser(), ContextParser()]
+    parsers = [CompoundParser(), ChemicalLabelParser(), NmrParser(), IrParser(), UvvisParser(), MpParser(), TgParser(),
+               ContextParser(), DoiParser()]
 
     def _repr_html_(self):
         return '<p class="cde-paragraph">' + self.text + '</p>'
@@ -510,6 +512,7 @@ def records(self):
         tagged_tokens = [(CONTROL_RE.sub('', token), tag) for token, tag in self.tagged_tokens]
         for parser in self.parsers:
             for record in parser.parse(tagged_tokens):
+                # print(record)
                 p = record.serialize()
                 if not p:  # TODO: Potential performance issues?
                     continue

chemdataextractor/model.py

@@ -22,12 +22,10 @@
 
 from .utils import python_2_unicode_compatible
 
-
 log = logging.getLogger(__name__)
 
 
 class BaseType(six.with_metaclass(ABCMeta)):
-
     # This is assigned by ModelMeta to match the attribute on the Model
     name = None
 
@@ -90,7 +88,6 @@ def process(self, value):
 
 
 class ModelType(BaseType):
-
     def __init__(self, model, **kwargs):
         self.model_class = model
         self.model_name = self.model_class.__name__
@@ -102,7 +99,6 @@ def serialize(self, value, primitive=False):
 
 
 class ListType(BaseType):
-
     def __init__(self, field, default=None, **kwargs):
         super(ListType, self).__init__(**kwargs)
         self.field = field
@@ -394,6 +390,7 @@ class GlassTransition(BaseModel):
     concentration = StringType(contextual=True)
     concentration_units = StringType(contextual=True)
 
+
 class QuantumYield(BaseModel):
     """A quantum yield measurement."""
     value = StringType()
@@ -439,6 +436,7 @@ class Compound(BaseModel):
     names = ListType(StringType())
     labels = ListType(StringType())
     roles = ListType(StringType())
+    doi = ListType(StringType())
     nmr_spectra = ListType(ModelType(NmrSpectrum))
     ir_spectra = ListType(ModelType(IrSpectrum))
     uvvis_spectra = ListType(ModelType(UvvisSpectrum))
@@ -502,8 +500,8 @@ def is_unidentified(self):
     def is_id_only(self):
         """Return True if identifier information only."""
         for key, value in self.items():
-            if key not in {'names', 'labels', 'roles'} and value:
+            if key not in {'names', 'labels', 'roles', 'doi'} and value:
                 return False
-        if self.names or self.labels:
+        if self.names or self.labels or self.doi:
             return True
         return False

chemdataextractor/parse/doi.py

@@ -0,0 +1,30 @@
+from __future__ import absolute_import
+from __future__ import division
+from __future__ import print_function
+from __future__ import unicode_literals
+
+from .base import BaseParser
+from .elements import W, R, Optional
+from ..model import StringType, Compound
+from .actions import merge
+
+
+doi = ((R('[Dd][Oo][Ii]') + Optional(W(':'))).hide() +
+       R('10[.][0-9]{4,}(?:[.][0-9]+)*') +
+       W('/') +
+       R('(?:(?!["&\'<>])\S)+')).add_action(merge)('doi')
+
+
+class DoiParser(BaseParser):
+    """"""
+    root = doi
+
+    def __init__(self):
+        pass
+
+    def interpret(self, result, start, end):
+        c = Compound(
+            doi=result.xpath('./text()')
+        )
+
+        yield c

tests/test_parse_doi.py

@@ -0,0 +1,49 @@
+# -*- coding: utf-8 -*-
+"""
+test_parse_doi
+~~~~~~~~~~~~~~
+
+Test DOI parser.
+
+"""
+
+from __future__ import absolute_import
+from __future__ import division
+from __future__ import print_function
+from __future__ import unicode_literals
+import logging
+import unittest
+
+from lxml import etree
+
+from chemdataextractor.doc.text import Sentence
+from chemdataextractor.parse.doi import doi
+
+logging.basicConfig(level=logging.DEBUG)
+log = logging.getLogger(__name__)
+
+
+class TestParseDOI(unittest.TestCase):
+    maxDiff = None
+
+    def do_parse(self, input, expected):
+        s = Sentence(input)
+        log.debug(s)
+        log.debug(s.tagged_tokens)
+        result = next(doi.scan(s.tagged_tokens))[0]
+        log.debug(etree.tostring(result, pretty_print=True, encoding='unicode'))
+        self.assertEqual(expected, etree.tostring(result, encoding='unicode'))
+
+    def test_doi1(self):
+        tests = [
+            'DOI:10.1021/jo101758t',
+            'doi:10.3390/molecules201219848\n hello world',
+            'Molecules 2015, 20(12), 22272-22285; doi:10.3390/molecules201219846'
+        ]
+        values = [
+            '<doi>10.1021/jo101758t</doi>',
+            '<doi>10.3390/molecules201219848</doi>',
+            '<doi>10.3390/molecules201219846</doi>'
+        ]
+        for test, expected in zip(tests, values):
+            self.do_parse(test, expected)

tests/test_parse_nmr.py

@@ -33,7 +33,7 @@ def do_parse(self, input, expected):
         log.debug(s.tagged_tokens)
         result = next(nmr.scan(s.tagged_tokens))[0]
         log.debug(etree.tostring(result, pretty_print=True, encoding='unicode'))
-        self.assertEqual(expected, etree.tostring(result, encoding='unicode'))
+        self.assertEqual(etree.tostring(result, encoding='unicode'), expected)
 
     def test_nmr1(self):
         s = '1H NMR (300 MHz, CDCl3), 1.00 (t, J = 7.3 Hz, 3H), 1.50 (m, 2H), 1.77 (m, 2H), 2.42 (s, 3H), ' \