global: rename from crawler to hepcrawl record

Signed-off-by: David Caro <[email protected]>

hepcrawl/pipelines.py

@@ -24,7 +24,7 @@
 
 from inspire_schemas.utils import validate
 
-from hepcrawl.crawler2hep import item_to_hep
+from hepcrawl.tohep import item_to_hep
 from hepcrawl.settings import FILES_STORE
 from hepcrawl.utils import RecordFile
 

hepcrawl/testlib/fixtures.py

@@ -17,7 +17,12 @@
 from scrapy.selector import Selector
 
 
-def fake_response_from_file(file_name, test_suite='unit', url='http://www.example.com', response_type=TextResponse):
+def fake_response_from_file(
+    file_name,
+    test_suite='unit',
+    url='http://www.example.com',
+    response_type=TextResponse,
+):
     """Create a Scrapy fake HTTP response from a HTML file
 
     Args:
@@ -26,11 +31,12 @@ def fake_response_from_file(file_name, test_suite='unit', url='http://www.exampl
         test_suite(str): The test suite that the response file comes from,
             e.g. ``unit``, ``functional``.
         url(str): The URL of the response.
-        response_type: The type of the scrapy Response to be returned,
+        response_type(class): The type of the scrapy Response to be returned,
             depending on the Request (Response, TextResponse, etc).
 
     Returns:
-        ``response_type``: A scrapy HTTP response which can be used for unit testing.
+        ``response_type``: A scrapy HTTP response which can be used for unit
+            testing.
     """
     request = Request(url=url)
 
@@ -55,15 +61,18 @@ def fake_response_from_file(file_name, test_suite='unit', url='http://www.exampl
     return response
 
 
-def fake_response_from_string(text, url='http://www.example.com', response_type=TextResponse):
-    """Fake Scrapy response from a string."""
+def fake_response_from_string(
+    text,
+    url='http://www.example.com',
+    response_type=TextResponse,
+):
     request = Request(url=url)
     response = response_type(
         url=url,
         request=request,
         body=text,
-        **{'encoding': 'utf-8'}
-        )
+        encoding='utf-8',
+    )
 
     return response
 
@@ -83,7 +92,8 @@ def get_node(spider, tag, response=None, text=None, rtype="xml"):
 def get_test_suite_path(*path_chunks, **kwargs):
     """
     Args:
-        *path_chunks: Optional extra path element (strings) to suffix the responses directory with.
+        *path_chunks: Optional extra path element (strings) to suffix the
+            responses directory with.
         **kwargs: The test type folder name, default is the ``unit`` test suite,
             e.g. ``test_suite='unit'``, ``test_suite='functional'``.
 

hepcrawl/utils.py

@@ -373,7 +373,7 @@ class RecordFile(object):
         name(str): Optional, name of the file, if not passed, will use the name
             in the ``path``.
 
-    Rises:
+    Raises:
         PathDoesNotExist:
     """
     def __init__(self, path, name=None):

tests/unit/test_crawler2hep.py → tests/unit/test_tohep.py

@@ -12,14 +12,14 @@
 import pytest
 import yaml
 
-from hepcrawl.crawler2hep import hepcrawl_to_hep
+from hepcrawl.tohep import hepcrawl_to_hep
 from hepcrawl.testlib.fixtures import get_test_suite_path
 
 
 def load_file(file_name):
     path = get_test_suite_path(
         'responses',
-        'crawler2hep',
+        'tohep',
         file_name,
     )
     with open(path) as input_data:
@@ -29,13 +29,13 @@ def load_file(file_name):
 
 
 @pytest.fixture('module')
-def expected_generic_crawler_record():
-    return load_file('out_generic_crawler_record.yaml')
+def expected_generic_hepcrawl_record():
+    return load_file('out_generic_hepcrawl_record.yaml')
 
 
 @pytest.fixture('module')
-def input_generic_crawler_record():
-    return load_file('in_generic_crawler_record.yaml')
+def input_generic_hepcrawl_record():
+    return load_file('in_generic_hepcrawl_record.yaml')
 
 
 @pytest.fixture('module')
@@ -48,12 +48,12 @@ def input_no_document_type_record():
     return load_file('in_no_document_type.yaml')
 
 
-def test_generic_crawler_record(
-        input_generic_crawler_record,
-        expected_generic_crawler_record
+def test_generic_hepcrawl_record(
+        input_generic_hepcrawl_record,
+        expected_generic_hepcrawl_record
 ):
-    produced_record = hepcrawl_to_hep(input_generic_crawler_record)
-    assert produced_record == expected_generic_crawler_record
+    produced_record = hepcrawl_to_hep(input_generic_hepcrawl_record)
+    assert produced_record == expected_generic_hepcrawl_record
 
 
 def test_no_document_type(