Merge pull request #107 from spirosdelviniotis/hepcrawl_wsp_local_pac…

…kage_test

tests: adds WSP functional test for local package

docker-compose.test.yml

@@ -23,6 +23,7 @@ services:
       - ${DOCKER_DATA}/tmp/hepcrawl_venv:/hepcrawl_venv/
       - ${PWD}:/code/
       - ${PWD}/tests/functional/scrapyd_coverage_runner.conf:/etc/scrapyd/scrapyd.conf
+      - /tmp/WSP:/tmp/WSP  # the tmp folder that keeps the history of the crawled records
     links:
       - rabbitmq
       - celery

hepcrawl/spiders/wsp_spider.py

@@ -1,7 +1,7 @@
 # -*- coding: utf-8 -*-
 #
 # This file is part of hepcrawl.
-# Copyright (C) 2015, 2016 CERN.
+# Copyright (C) 2015, 2016, 2017 CERN.
 #
 # hepcrawl is a free software; you can redistribute it and/or modify it
 # under the terms of the Revised BSD License; see LICENSE file for
@@ -23,6 +23,7 @@
 from ..utils import (
     ftp_list_files,
     ftp_connection_info,
+    local_list_files,
     get_license,
     unzip_xml_files,
 )
@@ -88,19 +89,25 @@ def __init__(self, package_path=None, ftp_folder="WSP", ftp_host=None, ftp_netrc
     def start_requests(self):
         """List selected folder on remote FTP and yield new zip files."""
         if self.package_path:
-            yield Request(self.package_path, callback=self.handle_package_file)
+            new_files_paths = local_list_files(
+                self.package_path,
+                self.target_folder
+            )
+
+            for file_path in new_files_paths:
+                yield Request("file://{0}".format(file_path), callback=self.handle_package_file)
         else:
             ftp_host, ftp_params = ftp_connection_info(self.ftp_host, self.ftp_netrc)
 
-            dummy, new_files = ftp_list_files(
+            new_files_paths = ftp_list_files(
                 self.ftp_folder,
                 self.target_folder,
                 server=ftp_host,
                 user=ftp_params['ftp_user'],
                 password=ftp_params['ftp_password']
             )
 
-            for remote_file in new_files:
+            for remote_file in new_files_paths:
                 # Cast to byte-string for scrapy compatibility
                 remote_file = str(remote_file)
                 ftp_params["ftp_local_filename"] = os.path.join(
@@ -116,7 +123,7 @@ def start_requests(self):
 
     def handle_package_ftp(self, response):
         """Handle a zip package and yield every XML found."""
-        self.log("Visited %s" % response.url)
+        self.log("Visited url %s" % response.url)
         zip_filepath = response.body
         zip_target_folder, dummy = os.path.splitext(zip_filepath)
         xml_files = unzip_xml_files(zip_filepath, zip_target_folder)
@@ -128,6 +135,7 @@ def handle_package_ftp(self, response):
 
     def handle_package_file(self, response):
         """Handle a local zip package and yield every XML."""
+        self.log("Visited file %s" % response.url)
         zip_filepath = urlparse.urlsplit(response.url).path
         zip_target_folder, dummy = os.path.splitext(zip_filepath)
         xml_files = unzip_xml_files(zip_filepath, zip_target_folder)

hepcrawl/utils.py

@@ -1,7 +1,7 @@
 # -*- coding: utf-8 -*-
 #
 # This file is part of hepcrawl.
-# Copyright (C) 2015, 2016 CERN.
+# Copyright (C) 2015, 2016, 2017 CERN.
 #
 # hepcrawl is a free software; you can redistribute it and/or modify it
 # under the terms of the Revised BSD License; see LICENSE file for
@@ -66,16 +66,24 @@ def ftp_list_files(server_folder, target_folder, server, user, password, passive
         encrypt_data_channel=True)
 
     with ftputil.FTPHost(server, user, password, session_factory=session_factory) as host:
-        files = host.listdir(host.curdir + '/' + server_folder)
-        missing_files = []
-        all_files = []
-        for filename in files:
-            destination_file = os.path.join(target_folder, filename)
-            source_file = os.path.join(server_folder, filename)
-            if not os.path.exists(destination_file):
-                missing_files.append(source_file)
-            all_files.append(source_file)
-    return all_files, missing_files
+        file_names = host.listdir(os.path.join(host.curdir, '/', server_folder))
+        return list_missing_files(server_folder, target_folder, file_names)
+
+
+def local_list_files(local_folder, target_folder):
+    file_names = os.listdir(local_folder)
+    return list_missing_files(local_folder, target_folder, file_names)
+
+
+def list_missing_files(remote_folder, target_folder, file_names):
+    missing_files = []
+    for file_name in file_names:
+        destination_file = os.path.join(target_folder, file_name)
+        source_file = os.path.join(remote_folder, file_name)
+        if not os.path.exists(destination_file):
+            missing_files.append(source_file)
+
+    return missing_files
 
 
 def get_first(iterable, default=None):

tests/functional/WSP/test_wsp.py

@@ -1,7 +1,7 @@
 # -*- coding: utf-8 -*-
 #
 # This file is part of hepcrawl.
-# Copyright (C) 2015, 2016, 2017 CERN.
+# Copyright (C) 2017 CERN.
 #
 # hepcrawl is a free software; you can redistribute it and/or modify it
 # under the terms of the Revised BSD License; see LICENSE file for
@@ -14,6 +14,7 @@
 import pytest
 import json
 import os
+import shutil
 
 from scrapyd_api import ScrapydAPI
 from time import sleep
@@ -50,14 +51,14 @@ def expected_results():
     return expected_data
 
 
-@pytest.fixture(scope="module")
-def set_up_environment():
-    netrc_location = os.path.join(os.path.dirname(
-        os.path.realpath(__file__)),
-        'fixtures/ftp_server/.netrc'
+@pytest.fixture(scope="function")
+def set_up_ftp_environment():
+    netrc_location = os.path.join(
+        os.path.dirname(os.path.realpath(__file__)),
+        os.path.join('fixtures', 'ftp_server', '.netrc')
     )
 
-    return {
+    yield {
         'CRAWLER_HOST_URL': 'http://scrapyd:6800',
         'CRAWLER_PROJECT': 'hepcrawl',
         'CRAWLER_ARGUMENTS': {
@@ -66,9 +67,44 @@ def set_up_environment():
         }
     }
 
+    clean_dir()
+
+
+@pytest.fixture(scope="function")
+def set_up_local_environment():
+    package_location = os.path.join(
+        os.path.dirname(os.path.realpath(__file__)),
+        os.path.join('fixtures', 'ftp_server', 'WSP')
+    )
+
+    yield {
+        'CRAWLER_HOST_URL': 'http://scrapyd:6800',
+        'CRAWLER_PROJECT': 'hepcrawl',
+        'CRAWLER_ARGUMENTS': {
+            'package_path': package_location,
+        }
+    }
+
+    remove_generated_files(package_location)
+
+
+def remove_generated_files(package_location):
+    clean_dir()
+
+    _, dirs, files = next(os.walk(package_location))
+    for dir_name in dirs:
+        clean_dir(os.path.join(package_location, dir_name))
+    for file_name in files:
+        if not file_name.endswith('.zip'):
+            os.unlink(os.path.join(package_location, file_name))
+
+
+def clean_dir(path='/tmp/WSP/'):
+    shutil.rmtree(path, ignore_errors=True)
 
-def test_wsp_normal_set_of_records(set_up_environment, expected_results):
-    crawler = get_crawler_instance(set_up_environment.get('CRAWLER_HOST_URL'))
+
+def test_wsp_ftp(set_up_ftp_environment, expected_results):
+    crawler = get_crawler_instance(set_up_ftp_environment.get('CRAWLER_HOST_URL'))
 
     # The test must wait until the docker environment is up (takes about 10 seconds).
     sleep(10)
@@ -78,13 +114,33 @@ def test_wsp_normal_set_of_records(set_up_environment, expected_results):
         monitor_timeout=5,
         monitor_iter_limit=100,
         crawler_instance=crawler,
-        project=set_up_environment.get('CRAWLER_PROJECT'),
+        project=set_up_ftp_environment.get('CRAWLER_PROJECT'),
+        spider='WSP',
+        settings={},
+        **set_up_ftp_environment.get('CRAWLER_ARGUMENTS')
+    )
+
+    gotten_results = [override_generated_fields(result) for result in results]
+    expected_results = [override_generated_fields(expected) for expected in expected_results]
+
+    assert gotten_results == expected_results
+
+
+def test_wsp_local_package_path(set_up_local_environment, expected_results):
+    crawler = get_crawler_instance(set_up_local_environment.get('CRAWLER_HOST_URL'))
+
+    results = CeleryMonitor.do_crawl(
+        app=celery_app,
+        monitor_timeout=5,
+        monitor_iter_limit=100,
+        crawler_instance=crawler,
+        project=set_up_local_environment.get('CRAWLER_PROJECT'),
         spider='WSP',
         settings={},
-        **set_up_environment.get('CRAWLER_ARGUMENTS')
+        **set_up_local_environment.get('CRAWLER_ARGUMENTS')
     )
 
-    gottern_results = [override_generated_fields(result) for result in results]
+    gotten_results = [override_generated_fields(result) for result in results]
     expected_results = [override_generated_fields(expected) for expected in expected_results]
 
-    assert gottern_results == expected_results
+    assert gotten_results == expected_results