Merge pull request #80 from coreofscience/fix-missing-fields-raise

Do not take into account articles with missing fields

.zenodo.json

@@ -2,7 +2,7 @@
     "description": "Translates isi web of knowledge files into python objects.",
     "license": "MIT",
     "title": "coreofscience/python-wostools",
-    "version": "v2.0.6",
+    "version": "v2.0.7",
     "upload_type": "software",
     "publication_date": "2018-08-13",
     "creators": [
@@ -25,7 +25,7 @@
     "related_identifiers": [
         {
             "scheme": "url",
-            "identifier": "https://github.com/coreofscience/python-wostools/tree/v2.0.6",
+            "identifier": "https://github.com/coreofscience/python-wostools/tree/v2.0.7",
             "relation": "isSupplementTo"
         },
         {

HISTORY.md

@@ -1,6 +1,10 @@
 # History
 
-## 2.0.5 (2020-08-21)
+## 2.0.7 (2020-08-23)
+
+- Remove from the collection those documents whose label is unknow or conflictive.
+
+## 2.0.6 (2020-08-21)
 
 - Accomodate for unknown fields in ISI WOS files.
 

setup.py

@@ -42,7 +42,7 @@
     test_suite="tests",
     tests_require=test_requirements,
     url="https://github.com/coreofscience/python-wostools",
-    version="2.0.6",
+    version="2.0.7",
     zip_safe=False,
     long_description_content_type="text/markdown",
 )

tests/test_article.py

@@ -6,7 +6,7 @@
 from pytest_bdd import given, parsers, scenarios, then, when
 
 from wostools.article import Article
-from wostools.exceptions import InvalidIsiLine, InvalidReference
+from wostools.exceptions import InvalidIsiLine, InvalidReference, MissingLabelFields
 
 from wostools._testutils import Context
 
@@ -286,7 +286,7 @@ def no_error_computing_label(label_context: Context[str]):
 @then("There's an error computing the label")
 def error_computing_label(label_context: Context[str]):
     with label_context.assert_error() as error:
-        assert isinstance(error, ValueError)
+        assert isinstance(error, MissingLabelFields)
 
 
 @then(parsers.parse("the article matches the {field:w} of the other"))

wostools/__init__.py

@@ -2,7 +2,7 @@
 
 __author__ = """Core of Science"""
 __email__ = "[email protected]"
-__version__ = "2.0.6"
+__version__ = "2.0.7"
 
 from wostools.article import Article
 from wostools.lazy import LazyCollection

wostools/cached.py

@@ -4,11 +4,12 @@
 
 import itertools
 import logging
+from contextlib import suppress
 from typing import Dict, Iterable, Iterator, Tuple
 
 from wostools.article import Article
 from wostools.base import BaseCollection
-from wostools.exceptions import InvalidReference
+from wostools.exceptions import InvalidReference, MissingLabelFields
 
 logger = logging.getLogger(__name__)
 
@@ -40,14 +41,15 @@ def _preheat(self):
         if key == self._cache_key:
             return
         for article in self._articles():
-            self._add_article(article)
-            for reference in article.references:
-                try:
-                    self._add_article(Article.from_isi_citation(reference))
-                except InvalidReference:
-                    logger.info(
-                        f"Ignoring malformed reference '{reference}' from '{article.label}'"
-                    )
+            with suppress(MissingLabelFields):
+                self._add_article(article)
+                for reference in article.references:
+                    try:
+                        self._add_article(Article.from_isi_citation(reference))
+                    except InvalidReference:
+                        logger.info(
+                            f"Ignoring malformed reference '{reference}' from '{article.label}'"
+                        )
         self._cache_key = key
 
     def __iter__(self) -> Iterator[Article]:

wostools/lazy.py

@@ -4,11 +4,12 @@
 
 import itertools
 import logging
+from contextlib import suppress
 from typing import Iterable, Tuple
 
 from wostools.article import Article
 from wostools.base import BaseCollection
-from wostools.exceptions import InvalidReference
+from wostools.exceptions import InvalidReference, MissingLabelFields
 
 logger = logging.getLogger(__name__)
 
@@ -37,8 +38,9 @@ def _article_texts(self):
                     yield article_text
 
     def _articles(self) -> Iterable[Article]:
-        for article_text in self._article_texts:
-            yield Article.from_isi_text(article_text)
+        with suppress(MissingLabelFields):
+            for article_text in self._article_texts:
+                yield Article.from_isi_text(article_text)
 
     @property
     def authors(self) -> Iterable[str]: