add two new verbosity options and show detected Language

release 0.8.0
Findus23 · Jul 19, 2019 · b94494b · b94494b
1 parent b1265f0
commit b94494b
Show file tree

Hide file tree

Showing 4 changed files with 120 additions and 69 deletions.
diff --git a/CHANGELOG.rst b/CHANGELOG.rst
@@ -1,9 +1,12 @@
 Changelog
 =========
 
-`0.7.2` (unreleased)
+`0.8.0` (2019-07-19)
 --------------------
 * don't use goo.gl in the help text
+* add new option `-r`/`--rules` to show details for matching rules
+* add new option `--rule-categories` to show categories of matching rules
+* print autodetected language
 
 
 `0.7.1` (2019-06-14)

diff --git a/pylanguagetool/__init__.py b/pylanguagetool/__init__.py
@@ -31,7 +31,10 @@ def init_config():
                    choices=["txt", "html", "md", "rst", "ipynb"],
                    help="if not plaintext")
     p.add_argument('input file', help='input file', nargs='?')
-
+    p.add_argument("-r", "--rules", env_var="RULES", action='store_true', default=False,
+                   help="show the matching rules")
+    p.add_argument("--rule-categories", env_var="RULE_CATEGORIES", action='store_true', default=False,
+                   help="show the the categories of the matching rules")
     p.add_argument('-l', '--lang', env_var='TEXTLANG', default="auto",
                    help="A language code like en or en-US, or auto to guess the language automatically (see preferredVariants below). For languages with variants (English, German, Portuguese) spell checking will only be activated when you specify the variant, e.g. en-GB instead of just en."
                    )
@@ -122,14 +125,28 @@ def get_input_text(config):
         sys.exit(2)
 
 
-def print_errors(matches, api_url, version, print_color=True):
+def print_errors(response, api_url, print_color=True, rules=False, rule_categories=False):
+    matches = response["matches"]
+    language = response["language"]
+    version = response["software"]["name"] + " " + response["software"]["version"]
+
     def colored(text, color):
         if print_color:
             init_colors()
             return color + text + Fore.RESET
         else:
             return text
 
+    print(colored(
+        "{} detected ({:.0f}% confidence)".format(language["detectedLanguage"]["name"],
+                                                  language["detectedLanguage"]["confidence"] * 100)
+        , Fore.LIGHTBLACK_EX))
+    if language["detectedLanguage"]["code"] != language["code"]:
+        print(colored(
+            "checking as {} text because of setting".format(language["name"])
+            , Fore.LIGHTBLACK_EX))
+    print()
+
     tick = colored(u"\u2713", Fore.LIGHTGREEN_EX) + " "
     cross = colored(u"\u2717", Fore.LIGHTRED_EX) + " "
 
@@ -165,6 +182,16 @@ def colored(text, color):
                     colored(replacement["value"], Fore.LIGHTGREEN_EX) +
                     colored(context[endpostion:], Fore.LIGHTBLACK_EX)
                 )
+        rule = error["rule"]
+        if rules:
+            print(
+                indention[:2] + colored(rule["id"] + ": ", Fore.LIGHTBLACK_EX) + rule["description"]
+            )
+        if rule_categories:
+            category = rule["category"]
+            print(
+                indention[:2] + colored(category["id"] + ": ", Fore.LIGHTBLACK_EX) + category["name"]
+            )
         print()
     print(colored("Text checked by {url} ({version})".format(url=api_url, version=version), Fore.LIGHTBLACK_EX))
 
@@ -195,10 +222,11 @@ def main():
         found = False
         for line in check_text.splitlines():
             response = api.check(line, **config)
-            print_errors(response["matches"],
+            print_errors(response,
                          config["api_url"],
-                         response["software"]["name"] + " " + response["software"]["version"],
-                         not config["no_color"]
+                         not config["no_color"],
+                         config["rules"],
+                         config["rule_categories"]
                          )
             if len(response["matches"]) > 0:
                 found = True
@@ -207,10 +235,11 @@ def main():
 
     else:
         response = api.check(check_text, **config)
-        print_errors(response["matches"],
+        print_errors(response,
                      config["api_url"],
-                     response["software"]["name"] + " " + response["software"]["version"],
-                     not config["no_color"]
+                     not config["no_color"],
+                     config["rules"],
+                     config["rule_categories"]
                      )
 
         if len(response["matches"]) > 0:

diff --git a/setup.py b/setup.py
@@ -12,7 +12,7 @@
 
 setup(
     name='pyLanguagetool',
-    version='0.7.1',
+    version='0.8.0',
     packages=find_packages(),
     url='https://pylanguagetool.lw1.at/',
     license='MIT',

diff --git a/tests/test_cli.py b/tests/test_cli.py
@@ -4,85 +4,104 @@
 
 def test_cli(capsys):
     response = {
-        'software': {
-            'buildDate': '2016-12-28 15:25',
-            'apiVersion': '1',
-            'version': '3.6',
-            'status': '',
-            'name': 'LanguageTool'
+        "software": {
+            "name": "LanguageTool",
+            "version": "4.6",
+            "buildDate": "2019-06-26 07:28",
+            "apiVersion": 1,
+            "premium": False,
+            "premiumHint": "You might be missing errors only the Premium version can find. Contact us at support<at>languagetoolplus.com.",
+            "status": "",
         },
-        'matches': [
+        "warnings": {"incompleteResults": False},
+        "language": {
+            "name": "German (Austria)",
+            "code": "de-AT",
+            "detectedLanguage": {
+                "name": "German (Austria)",
+                "code": "de-AT",
+                "confidence": 0.99999136,
+            },
+        },
+        "matches": [
             {
-                'length': 3,
-                'shortMessage': '',
-                'context': {
-                    'length': 3,
-                    'text': 'das ist ein est',
-                    'offset': 0
+                "message": "Dieser Satz fängt nicht mit einem großgeschriebenen Wort an",
+                "shortMessage": "",
+                "replacements": [{"value": "Das"}],
+                "offset": 0,
+                "length": 3,
+                "context": {"text": "das ist ein est", "offset": 0, "length": 3},
+                "sentence": "das ist ein est",
+                "type": {"typeName": "Other"},
+                "rule": {
+                    "id": "UPPERCASE_SENTENCE_START",
+                    "description": "Großschreibung am Satzanfang",
+                    "issueType": "typographical",
+                    "category": {"id": "CASING", "name": "Groß-/Kleinschreibung"},
                 },
-                'replacements':
-                    [{'value': 'Das'}],
-                'rule': {
-                    'category': {
-                        'name': 'Groß-/Kleinschreibung',
-                        'id': 'CASING'
-                    },
-                    'issueType': 'typographical',
-                    'description': 'Großschreibung am Satzanfang',
-                    'id': 'UPPERCASE_SENTENCE_START'
+                "ignoreForIncompleteSentence": True,
+                "contextForSureMatch": -1,
+            },
+            {
+                "message": "Möglicher Rechtschreibfehler gefunden",
+                "shortMessage": "Rechtschreibfehler",
+                "replacements": [
+                    {"value": "ist"},
+                    {"value": "es"},
+                    {"value": "erst"},
+                    {"value": "fest"},
+                    {"value": "West"},
+                    {"value": "Ost"},
+                    {"value": "Rest"},
+                    {"value": "Nest"},
+                    {"value": "Pest"},
+                    {"value": "lest"},
+                    {"value": "Ast"},
+                    {"value": "Fest"},
+                    {"value": "Gst"},
+                    {"value": "Test"},
+                    {"value": "best"},
+                    {"value": "esst"},
+                    {"value": "et"},
+                    {"value": "äst"},
+                    {"value": "des"},
+                    {"value": "mit"},
+                ],
+                "offset": 12,
+                "length": 3,
+                "context": {"text": "das ist ein est", "offset": 12, "length": 3},
+                "sentence": "das ist ein est",
+                "type": {"typeName": "UnknownWord"},
+                "rule": {
+                    "id": "AUSTRIAN_GERMAN_SPELLER_RULE",
+                    "description": "Möglicher Rechtschreibfehler",
+                    "issueType": "misspelling",
+                    "category": {"id": "TYPOS", "name": "Mögliche Tippfehler"},
                 },
-                'message': 'Dieser Satz fängt nicht mit einem großgeschriebenen Wort an',
-                'offset': 0
+                "ignoreForIncompleteSentence": False,
+                "contextForSureMatch": 0,
             },
-            {'length': 3,
-             'shortMessage': 'Rechtschreibfehler',
-             'context':
-                 {'length': 3,
-                  'text': 'das ist ein est',
-                  'offset': 12
-                  },
-             'replacements':
-                 [
-                     {'value': 'esst'}, {'value': 'ist'}, {'value': 'es'}, {'value': 'erst'}, {'value': 'fest'},
-                     {'value': 'Rest'}, {'value': 'Test'}, {'value': 'Fest'}, {'value': 'West'}, {'value': 'Nest'},
-                     {'value': 'Ost'}, {'value': 'Ast'}, {'value': 'Gst'}, {'value': 'Pest'}, {'value': 'et'},
-                     {'value': 'lest'}, {'value': 'äst'}, {'value': 'des'}, {'value': 'mit'}, {'value': 'ein'}
-                 ],
-             'rule': {
-                 'category': {
-                     'name': 'Mögliche Tippfehler',
-                     'id': 'TYPOS'
-                 },
-                 'issueType': 'misspelling',
-                 'description': 'Möglicher Rechtschreibfehler',
-                 'id': 'GERMAN_SPELLER_RULE'
-             },
-             'message': 'Möglicher Rechtschreibfehler gefunden',
-             'offset': 12
-             }
         ],
-        'language': {
-            'code': 'de-AT',
-            'name': 'German (Austria)'
-        }
     }
 
-    should_output = u"""Dieser Satz fängt nicht mit einem großgeschriebenen Wort an
+    should_output = u"""German (Austria) detected (100% confidence)
+
+Dieser Satz fängt nicht mit einem großgeschriebenen Wort an
   ✗ das ist ein est
     ^^^
   ✓ Das ist ein est
 
 Möglicher Rechtschreibfehler gefunden
   ✗ das ist ein est
                 ^^^
-  ✓ das ist ein esst
   ✓ das ist ein ist
   ✓ das ist ein es
   ✓ das ist ein erst
   ✓ das ist ein fest
+  ✓ das ist ein West
 
-Text checked by https://example.com/v2/ (Test 1.0)
+Text checked by https://example.com/v2/ (LanguageTool 4.6)
 """
-    pylanguagetool.print_errors(response["matches"], "https://example.com/v2/", "Test 1.0", False)
+    pylanguagetool.print_errors(response, "https://example.com/v2/", False)
     out, err = capsys.readouterr()
     assert out == should_output