Add no text option

src/converter.py

 """Implementation of ccl2json usage."""
 import json
+import pathlib
 from xml.sax import handler, make_parser
 
 from ccl2json.parse import CCLhandler
 
 
-def ccl2json(path_in, path_out):
+def ccl2json(path_in, options, path_out):
     """Function converting xml ccl to json.
 
     :param path_in: path to xml ccl file
     :type path_in: str
+    :param options: task_options: Dictionary containing options of ccl2json
+    json_text: if json output should contain original text (default = True)
+    :type: options: dict
     :param path_out: path to output json file
     :type path_out: str
     """
@@ -18,12 +22,13 @@ def ccl2json(path_in, path_out):
     parser.setContentHandler(CCLhandler())
     parser.parse(path_in)
 
-    with open(path_out, 'w', encoding='utf-8') as fout:
-        dout = {
-            "filename": path_in.split('/')[-1].replace('.ccl', ''),
-            'text': parser.getContentHandler().get_text(),
+    with open(path_out, 'w', encoding='utf-8') as file_out:
+        data_out = {
+            "filename": pathlib.Path(path_in).stem,
             'tagset': 'nkjp',
             'tokens': [token.as_dict() for token
                        in parser.getContentHandler().get_tokens()]
         }
-        json.dump(dout, fout, ensure_ascii=False)
+        if 'json_text' not in options or options['json_text']:
+            data_out['text'] = parser.getContentHandler().get_text()
+        json.dump(data_out, file_out, ensure_ascii=False)

src/tagger.py

@@ -41,6 +41,8 @@ class TaggerWorker(nlp_ws.NLPWorker):
         :param task_options: Dictionary containing options of pos_tagger
         lang: language of text (default = 'pl')
         output: format of results (default = 'json', values: json, ccl, lemmas)
+        json_text: bool if json output should contain original
+        text (default = True)
         :type task_options: dict
 
         :param output_path: Path to directory where the
@@ -67,6 +69,6 @@ class TaggerWorker(nlp_ws.NLPWorker):
         elif tagger_output == "ccl" and output == "lemmas":
             lemmatizer.ccl_2_lemmas(l_result, output_path)
         elif tagger_output == "ccl" and output == "json":
-            converter.ccl2json(l_result, output_path)
+            converter.ccl2json(l_result, task_options, output_path)
         else:
             raise Exception("Unsupported format conversion")