online api as default

opustools_pkg/README.md

@@ -479,7 +479,7 @@ arguments:
                       source language in a given corpus.
 -lc, --list_corpora   List available corpora. Use -s to find corpora for a given language and use
                       both -s and -t to find corpora for a given language pair.
--o, --online_api      Search resources from the online OPUS-API instead of the local database.
+--local_db            Search resources from the local database instead of the online OPUS-API.
 -dl DOWNLOAD_DIR, --download_dir DOWNLOAD_DIR
                       Set download directory (default=current directory)
 -q, --suppress_prompts

opustools_pkg/bin/opus_get

@@ -20,7 +20,7 @@ parser.add_argument('-ll', '--list_languages', help='List available languages. U
     action='store_true')
 parser.add_argument('-lc', '--list_corpora', help='List available corpora. Use -s to find corpora for a given language and use both -s and -t to find corpora for a given language pair.',
     action='store_true')
-parser.add_argument('-o', '--online_api', help='Search resources from the online OPUS-API instead of the local database.',
+parser.add_argument('--local_db', help='Search resources from the local database instead of the online OPUS-API.',
     action='store_true')
 parser.add_argument('-dl', '--download_dir',
     help='Set download directory (default=current directory)', default='.')

opustools_pkg/opustools/opus_get.py

@@ -12,7 +12,7 @@ class OpusGet:
     def __init__(self, source=None, target=None, directory=None,
             release='latest', preprocess='xml', list_resources=False,
             list_languages=False, list_corpora=False, download_dir='.',
-            online_api=False, suppress_prompts=False, database=None):
+            local_db=False, suppress_prompts=False, database=None):
         """Download files from OPUS.
 
         Keyword arguments:
@@ -24,7 +24,7 @@ def __init__(self, source=None, target=None, directory=None,
         list_resource -- List resources instead of downloading
         list_languages -- List available languages
         list_corpora -- List available corpora
-        online_api -- Search resource from the online OPUS-API instead of the local database.
+        local_db -- Search resources from the local database instead of the online OPUS-API.
         download_dir -- Directory where files will be downloaded (default .)
         suppress_prompts -- Download files without prompting "(y/n)"
         database -- Use custom sqlite db file
@@ -44,7 +44,7 @@ def __init__(self, source=None, target=None, directory=None,
 
         self.list_languages = list_languages
         self.list_corpora = list_corpora
-        self.online_api = online_api
+        self.local_db = local_db
 
         if source and target:
             self.fromto = [source, target]
@@ -118,11 +118,11 @@ def get_corpora_data(self):
         """Receive corpus data."""
         total_size = 0
 
-        if self.online_api:
+        if self.local_db:
+            corpora = self.dbo.get_corpora(self.parameters)
+        else:
             data = self.get_response(self.url)
             corpora = data['corpora']
-        else:
-            corpora = self.dbo.get_corpora(self.parameters)
 
         ret_corpora = []
         for c in corpora:
@@ -191,17 +191,17 @@ def get_files(self):
         """Output corpus file information/data."""
         try:
             if self.list_languages:
-                if self.online_api:
-                    languages = self.get_response(self.url+'languages=True')['languages']
-                else:
+                if self.local_db:
                     languages = self.dbo.run_languages_query(self.parameters)
+                else:
+                    languages = self.get_response(self.url+'languages=True')['languages']
                 print(', '.join([str(l) for l in languages]))
                 return
             elif self.list_corpora:
-                if self.online_api:
-                    corpus_list = self.get_response(self.url+'corpora=True')['corpora']
-                else:
+                if self.local_db:
                     corpus_list = self.dbo.run_corpora_query(self.parameters)
+                else:
+                    corpus_list = self.get_response(self.url+'corpora=True')['corpora']
                 print(', '.join([str(c) for c in corpus_list]))
                 return
             else:

opustools_pkg/setup.py

@@ -5,7 +5,7 @@
 
 setuptools.setup(
     name="opustools",
-    version="1.5.4",
+    version="1.5.5",
     author="Mikko Aulamo",
     author_email="[email protected]",
     description="Tools to read OPUS",

opustools_pkg/tests/test_opus_get.py

@@ -32,7 +32,7 @@ def test_format_size(self):
 
     def test_get_files_invalid_url(self):
         opg = OpusGet(directory='RF', source='en', target='sv',
-            list_resources=True, online_api=True)
+            list_resources=True)
         opg.url = 'http://slkdfjlks'
         old_stdout = sys.stdout
         printout = io.StringIO()
@@ -64,13 +64,13 @@ def test_dont_list_files_that_are_already_in_path(self, mocked_input):
         printout = io.StringIO()
         sys.stdout = printout
         OpusGet(directory='RF', source='en', target='sv', preprocess='xml',
-            download_dir=self.tempdir).get_files()
+            download_dir=self.tempdir, local_db=True).get_files()
         sys.stdout = old_stdout
         old_stdout = sys.stdout
         printout = io.StringIO()
         sys.stdout = printout
         OpusGet(directory='RF', source='en', target='sv', preprocess='xml',
-            download_dir=self.tempdir, list_resources=True).get_files()
+            download_dir=self.tempdir, list_resources=True, local_db=True).get_files()
         sys.stdout = old_stdout
         os.remove(os.path.join(self.tempdir, 'RF_latest_xml_en-sv.xml.gz'))
         os.remove(os.path.join(self.tempdir, 'RF_latest_xml_en.zip'))
@@ -108,7 +108,7 @@ def test_download_everything_from_a_corpus(self):
         printout = io.StringIO()
         sys.stdout = printout
         files = OpusGet(directory='RF', release='v1', preprocess='xml',
-            list_resources=True).get_files()
+            list_resources=True, local_db=True).get_files()
         sys.stdout = old_stdout
         self.assertEqual(len(printout.getvalue().split('\n')), 18)