ENH: Added downoading a dictionary from a URL.

Author: dave3d

comment_spell_check/comment_spell_check.py

@@ -322,10 +322,7 @@ def build_dictionary_list(args):
     if not isinstance(args.dict, list):
         return dict_list
 
-    for d in args.dict:
-        dpath = Path(d)
-        if dpath.exists():
-            dict_list.append(dpath)
+    dict_list.extend(args.dict)
 
     return dict_list
 

comment_spell_check/utils/create_checker.py

@@ -5,6 +5,8 @@
 import logging
 import importlib.resources
 import spellchecker
+import requests
+import pathlib
 
 
 def create_checker(dict_list: list[str] = None) -> spellchecker.SpellChecker:
@@ -22,13 +24,26 @@ def create_checker(dict_list: list[str] = None) -> spellchecker.SpellChecker:
     english_dict = str(lib_path) + "/resources/en.json.gz"
     logger.info("Loading English dictionary from: %s", english_dict)
     checker.word_frequency.load_dictionary(english_dict)
+    logger.info("number of words: %s", checker.word_frequency.unique_words)
 
     # load the additional dictionaries
     if not isinstance(dict_list, list):
         return checker
     if len(dict_list) > 0:
         for d in dict_list:
             logger.info("Loading additional dictionary from: %s", d)
-            checker.word_frequency.load_text_file(d)
+            if isinstance(d, pathlib.PosixPath):
+                # assume it's a local file path
+                checker.word_frequency.load_text_file(d)
+            else:
+                # load dictionary from URL
+                if d.startswith("http://") or d.startswith("https://"):
+                    response = requests.get(d)
+                    response.raise_for_status()
+                    checker.word_frequency.load_text(response.text)
+                else:
+                    # assume it's a local file path
+                    checker.word_frequency.load_text_file(d)
+            logger.info("# of words: %s", checker.word_frequency.unique_words)
 
     return checker

comment_spell_check/utils/parseargs.py

@@ -60,7 +60,8 @@ def create_parser():
         dest="dict",
         help="File that contains words that will be ignored."
         " Argument can be passed multiple times."
-        " File must contain 1 word per line.",
+        " File must contain 1 word per line."
+        " Argument can also be a URL to a text file with words.",
     )
 
     parser.add_argument(

requirements.txt

@@ -1,3 +1,4 @@
 comment_parser
 pyspellchecker
 bibtexparser
+requests

tests/test_comment_spell_check.py

@@ -96,6 +96,24 @@ def test_bibtex(self):
         )
         self.assertEqual(runresult.returncode, 0, runresult.stdout)
 
+    def test_url(self):
+        """URL test"""
+        url = (
+            "https://raw.githubusercontent.com/SimpleITK/SimpleITK/"
+            "refs/heads/master/.github/workflows/additional_dictionary.txt"
+        )
+        runresult = subprocess.run(
+            [
+                "comment_spell_check",
+                "--dict",
+                url,
+                "../tests/urltest.py",
+            ],
+            cwd="comment_spell_check",
+            stdout=subprocess.PIPE,
+        )
+        self.assertEqual(runresult.returncode, 0, runresult.stdout)
+
 
 if __name__ == "__main__":
     unittest.main()

tests/urltest.py

@@ -0,0 +1,4 @@
+# visualstudio.  This word is in the SimpleITK dictionary but not the
+# local one.
+#
+print("Hi Mom!")