Pytest failure

.circleci/config.yml

@@ -0,0 +1,54 @@
+version: 2
+executorType: docker
+jobs:
+  test:
+    docker:
+      - image: python:3.6.4-stretch
+      - image: elasticsearch:7.1.0
+        environment:
+          - cluster.name: elasticsearch
+          - xpack.security.enabled: false
+          - transport.host: localhost
+          - network.host: 127.0.0.1
+          - http.port: 9200
+          - discovery.type: single-node
+    working_directory: ~/code
+    steps:
+      - checkout
+      - run:
+          name: Install Dependencies
+          command: pip install -e .[test]
+      - run:
+          name: Test
+          command: pytest
+  deploy:
+    docker:
+      - image: docker:18.06.1-git
+    working_directory: ~/code
+    steps:
+      - checkout
+      - setup_remote_docker:
+          docker_layer_caching: true
+      - run:
+          name: Install cli tools
+          command: |
+            apk --update add py-pip curl
+            pip install --upgrade pip
+      - run:
+          name: Build and push pip package
+          command: |
+            source circle/build_pip_package.sh
+workflows:
+  version: 2
+  test_deploy:
+    jobs:
+      - test:
+          context: 360platform
+      - deploy:
+          context: 360platform
+          filters:
+            branches:
+              only:
+                - master
+          requires:
+            - test

.gitignore

@@ -8,6 +8,8 @@ __pycache__/
 # Distribution / packaging
 .Python
 env/
+.idea
+.venv
 build/
 develop-eggs/
 dist/
@@ -22,6 +24,7 @@ var/
 *.egg-info/
 .installed.cfg
 *.egg
+*.tar.gz
 
 # PyInstaller
 #  Usually these files are written by a python script from a template
@@ -57,4 +60,4 @@ docs/_build/
 target/
 image_match/web/static/tmp/
 
-*.jpg
+*.jpg

MANIFEST.in

@@ -0,0 +1 @@
+include build.info

build.info

@@ -0,0 +1 @@
+__version__ = '2.0.1'

circle/build_pip_package.sh

@@ -0,0 +1,32 @@
+#!/usr/bin/env bash
+
+set -e
+
+MAJOR=2
+MINOR=0
+PATCH=0
+
+rm -f image-match-*.tar.gz
+pip download --no-deps --extra-index-url https://pypi.fury.io/UmFoYTJTNACus1W8zjP8/360core/ image-match
+
+for DOWNLOADED_FILE in image-match-${MAJOR}.${MINOR}.*.gz; do
+  if [[ -e ${DOWNLOADED_FILE} ]]; then
+      DOWNLOADED_FILE=${DOWNLOADED_FILE/image-match-${MAJOR}.${MINOR}./}
+      DOWNLOADED_FILE=${DOWNLOADED_FILE/.tar.gz/}
+      PATCH=$((DOWNLOADED_FILE+1))
+  fi
+  break
+done
+
+echo "__version__ = '$MAJOR.$MINOR.$PATCH'" > build.info
+PYTHONPATH=. python setup.py sdist
+PACKAGENAME=dist/image-match-${MAJOR}.${MINOR}.${PATCH}.tar.gz
+
+exec 3>&1
+STATUS=$(curl -w "%{http_code}" -o /dev/null -s -F package=@${PACKAGENAME} https://UmFoYTJTNACus1W8zjP8@push.fury.io/360core/)
+
+if [ ${STATUS} != 200 ]
+then
+    echo curl response status: ${STATUS}
+    exit ${STATUS}
+fi

image_match/__init__.py

@@ -1,2 +1 @@
 __author__ = 'ryan'
-__version__ = '1.1.2'

image_match/elasticsearch_driver.py

@@ -10,14 +10,13 @@ class SignatureES(SignatureDatabaseBase):
 
     """
 
-    def __init__(self, es, index='images', doc_type='image', timeout='10s', size=100,
+    def __init__(self, es, index='images', timeout='10s', size=100,
                  *args, **kwargs):
         """Extra setup for Elasticsearch
 
         Args:
             es (elasticsearch): an instance of the elasticsearch python driver
             index (Optional[string]): a name for the Elasticsearch index (default 'images')
-            doc_type (Optional[string]): a name for the document time (default 'image')
             timeout (Optional[int]): how long to wait on an Elasticsearch query, in seconds (default 10)
             size (Optional[int]): maximum number of Elasticsearch results (default 100)
             *args (Optional): Variable length argument list to pass to base constructor
@@ -40,7 +39,6 @@ def __init__(self, es, index='images', doc_type='image', timeout='10s', size=100
         """
         self.es = es
         self.index = index
-        self.doc_type = doc_type
         self.timeout = timeout
         self.size = size
 
@@ -64,11 +62,12 @@ def search_single_record(self, rec, pre_filter=None):
         if pre_filter is not None:
             body['query']['bool']['filter'] = pre_filter
 
-        res = self.es.search(index=self.index,
-                              doc_type=self.doc_type,
-                              body=body,
-                              size=self.size,
-                              timeout=self.timeout)['hits']['hits']
+        res = self.es.search(
+            index=self.index,
+            body=body,
+            size=self.size,
+            timeout=self.timeout
+        )['hits']['hits']
 
         sigs = np.array([x['_source']['signature'] for x in res])
 
@@ -91,7 +90,9 @@ def search_single_record(self, rec, pre_filter=None):
 
     def insert_single_record(self, rec, refresh_after=False):
         rec['timestamp'] = datetime.now()
-        self.es.index(index=self.index, doc_type=self.doc_type, body=rec, refresh=refresh_after)
+        self.es.index(
+            index=self.index, body=rec, refresh=refresh_after
+        )
 
     def delete_duplicates(self, path):
         """Delete all but one entries in elasticsearch whose `path` value is equivalent to that of path.
@@ -108,4 +109,4 @@ def delete_duplicates(self, path):
                           if item['_source']['path'] == path]
         if len(matching_paths) > 0:
             for id_tag in matching_paths[1:]:
-                self.es.delete(index=self.index, doc_type=self.doc_type, id=id_tag)
+                self.es.delete(index=self.index, id=id_tag)

image_match/goldberg.py

@@ -236,14 +236,14 @@ def preprocess_image(image_or_path, bytestream=False, handle_mpo=False):
             return rgb2gray(np.asarray(img, dtype=np.uint8))
         elif type(image_or_path) in string_types or \
              type(image_or_path) is text_type:
-            return imread(image_or_path, as_grey=True)
+            return imread(image_or_path, as_gray=True)
         elif type(image_or_path) is bytes:
             try:
                 img = Image.open(image_or_path)
                 arr = np.array(img.convert('RGB'))
             except IOError:
                 # try again due to PIL weirdness
-                return imread(image_or_path, as_grey=True)
+                return imread(image_or_path, as_gray=True)
             if handle_mpo:
                 # take the first images from the MPO
                 if arr.shape == (2,) and isinstance(arr[1].tolist(), MpoImageFile):

image_match/signature_database_base.py

@@ -404,7 +404,7 @@ def get_words(array, k, N):
             words[i] = array[pos:pos+k]
         else:
             temp = array[pos:].copy()
-            temp.resize(k)
+            temp.resize(k, refcheck=False)
             words[i] = temp
 
     return words

setup.py

@@ -1,5 +1,5 @@
 """
-image_match is a simple package for finding approximate image matches from a
+image-match is a simple package for finding approximate image matches from a
 corpus. It is similar, for instance, to pHash <http://www.phash.org/>, but
 includes a database backend that easily scales to billions of images and
 supports sustained high rates of image insertion: up to 10,000 images/s on our
@@ -56,9 +56,9 @@ def find_version(*file_paths):
 
 
 setup(
-    name='image_match',
-    version=find_version('image_match', '__init__.py'),
-    description='image_match is a simple package for finding approximate '\
+    name='image-match',
+    version=find_version('', 'build.info'),
+    description='image-match is a simple package for finding approximate '\
                 'image matches from a corpus.',
     long_description=__doc__,
     url='https://github.com/ascribe/image-match/',
@@ -89,7 +89,7 @@ def find_version(*file_paths):
     ],
     install_requires=[
         'scikit-image>=0.14',
-        'elasticsearch>=5.0.0,<6.0.0',
+        'elasticsearch>=7.0.0,<8.0.0',
         'six>=1.11.0',
     ],
     tests_require=tests_require,

tests/test_elasticsearch_driver.py

@@ -17,10 +17,8 @@
 urlretrieve(test_img_url2, 'test2.jpg')
 
 INDEX_NAME = 'test_environment_{}'.format(hashlib.md5(os.urandom(128)).hexdigest()[:12])
-DOC_TYPE = 'image'
 MAPPINGS = {
   "mappings": {
-    DOC_TYPE: {
       "dynamic": True,
       "properties": {
         "metadata": {
@@ -31,7 +29,6 @@
             }
         }
       }
-    }
   }
 }
 
@@ -74,7 +71,8 @@ def es():
 
 @pytest.fixture
 def ses(es, index_name):
-    return SignatureES(es=es, index=index_name, doc_type=DOC_TYPE)
+    return SignatureES(es=es, index=index_name)
+
 
 def test_elasticsearch_running(es):
     i = 0

tests/test_elasticsearch_driver_metadata_as_nested.py

@@ -17,10 +17,8 @@
 urlretrieve(test_img_url2, 'test2.jpg')
 
 INDEX_NAME = 'test_environment_{}'.format(hashlib.md5(os.urandom(128)).hexdigest()[:12])
-DOC_TYPE = 'image'
 MAPPINGS = {
   "mappings": {
-    DOC_TYPE: {
       "dynamic": True,
       "properties": {
         "metadata": {
@@ -32,7 +30,6 @@
             }
         }
       }
-    }
   }
 }
 
@@ -75,7 +72,7 @@ def es():
 
 @pytest.fixture
 def ses(es, index_name):
-    return SignatureES(es=es, index=index_name, doc_type=DOC_TYPE)
+    return SignatureES(es=es, index=index_name)
 
 def test_elasticsearch_running(es):
     i = 0
@@ -134,4 +131,4 @@ def _nested_filter(tenant_id, project_id):
                 }
              }
         }
-    }
+    }

tests/test_goldberg.py

@@ -74,4 +74,4 @@ def test_difference():
     sig1 = gis.generate_signature('test.jpg')
     sig2 = gis.generate_signature(test_diff_img_url)
     dist = gis.normalized_distance(sig1, sig2)
-    assert dist == 0.42263283502672722
+    assert dist == 0.424549547059671