Drop Python 2 (4/n): SearchQuery.query is a str instead of bytes

searx/answerers/__init__.py

@@ -32,10 +32,10 @@ def ask(query):
     results = []
     query_parts = list(filter(None, query.query.split()))
 
-    if query_parts[0].decode() not in answerers_by_keywords:
+    if query_parts[0] not in answerers_by_keywords:
         return results
 
-    for answerer in answerers_by_keywords[query_parts[0].decode()]:
+    for answerer in answerers_by_keywords[query_parts[0]]:
         result = answerer(query)
         if result:
             results.append(result)

searx/answerers/random/answerer.py

@@ -39,11 +39,11 @@ def random_uuid():
     return str(uuid.uuid4())
 
 
-random_types = {b'string': random_string,
-                b'int': random_int,
-                b'float': random_float,
-                b'sha256': random_sha256,
-                b'uuid': random_uuid}
+random_types = {'string': random_string,
+                'int': random_int,
+                'float': random_float,
+                'sha256': random_sha256,
+                'uuid': random_uuid}
 
 
 # required answerer function
@@ -64,4 +64,4 @@ def answer(query):
 def self_info():
     return {'name': gettext('Random value generator'),
             'description': gettext('Generate different random values'),
-            'examples': ['random {}'.format(x.decode()) for x in random_types]}
+            'examples': ['random {}'.format(x) for x in random_types]}

searx/answerers/statistics/answerer.py

@@ -27,15 +27,15 @@ def answer(query):
     func = parts[0]
     answer = None
 
-    if func == b'min':
+    if func == 'min':
         answer = min(args)
-    elif func == b'max':
+    elif func == 'max':
         answer = max(args)
-    elif func == b'avg':
+    elif func == 'avg':
         answer = sum(args) / len(args)
-    elif func == b'sum':
+    elif func == 'sum':
         answer = sum(args)
-    elif func == b'prod':
+    elif func == 'prod':
         answer = reduce(mul, args, 1)
 
     if answer is None:

searx/engines/archlinux.py

@@ -105,7 +105,7 @@ def request(query, params):
     # if our language is hosted on the main site, we need to add its name
     # to the query in order to narrow the results to that language
     if language in main_langs:
-        query += b' (' + main_langs[language] + b')'
+        query += ' (' + main_langs[language] + ')'
 
     # prepare the request parameters
     query = urlencode({'search': query})

searx/engines/arxiv.py

@@ -30,7 +30,7 @@ def request(query, params):
     # basic search
     offset = (params['pageno'] - 1) * number_of_results
 
-    string_args = dict(query=query.decode(),
+    string_args = dict(query=query,
                        offset=offset,
                        number_of_results=number_of_results)
 

searx/engines/base.py

@@ -55,7 +55,7 @@ shorcut_dict = {
 def request(query, params):
     # replace shortcuts with API advanced search keywords
     for key in shorcut_dict.keys():
-        query = re.sub(key, shorcut_dict[key], str(query))
+        query = re.sub(key, shorcut_dict[key], query)
 
     # basic search
     offset = (params['pageno'] - 1) * number_of_results

searx/engines/bing.py

@@ -47,7 +47,7 @@ def request(query, params):
     else:
         lang = match_language(params['language'], supported_languages, language_aliases)
 
-    query = 'language:{} {}'.format(lang.split('-')[0].upper(), query.decode()).encode()
+    query = 'language:{} {}'.format(lang.split('-')[0].upper(), query)
 
     search_path = search_string.format(
         query=urlencode({'q': query}),

searx/engines/currency_convert.py

@@ -11,13 +11,13 @@ categories = []
 url = 'https://duckduckgo.com/js/spice/currency/1/{0}/{1}'
 weight = 100
 
-parser_re = re.compile(b'.*?(\\d+(?:\\.\\d+)?) ([^.0-9]+) (?:in|to) ([^.0-9]+)', re.I)
+parser_re = re.compile('.*?(\\d+(?:\\.\\d+)?) ([^.0-9]+) (?:in|to) ([^.0-9]+)', re.I)
 
 db = 1
 
 
 def normalize_name(name):
-    name = name.decode().lower().replace('-', ' ').rstrip('s')
+    name = name.lower().replace('-', ' ').rstrip('s')
     name = re.sub(' +', ' ', name)
     return unicodedata.normalize('NFKD', name).lower()
 

searx/engines/dictzone.py

@@ -18,7 +18,7 @@ categories = ['general']
 url = 'https://dictzone.com/{from_lang}-{to_lang}-dictionary/{query}'
 weight = 100
 
-parser_re = re.compile(b'.*?([a-z]+)-([a-z]+) ([^ ]+)$', re.I)
+parser_re = re.compile('.*?([a-z]+)-([a-z]+) ([^ ]+)$', re.I)
 results_xpath = './/table[@id="r"]/tr'
 
 
@@ -37,7 +37,7 @@ def request(query, params):
 
     params['url'] = url.format(from_lang=from_lang[2],
                                to_lang=to_lang[2],
-                               query=query.decode())
+                               query=query)
 
     return params
 

searx/engines/gentoo.py

@@ -90,7 +90,7 @@ def request(query, params):
     # if our language is hosted on the main site, we need to add its name
     # to the query in order to narrow the results to that language
     if language in main_langs:
-        query += b' (' + (main_langs[language]).encode() + b')'
+        query += ' (' + main_langs[language] + ')'
 
     # prepare the request parameters
     query = urlencode({'search': query})

searx/engines/openstreetmap.py

@@ -30,8 +30,8 @@ route_re = re.compile('(?:from )?(.+) to (.+)')
 # do search-request
 def request(query, params):
 
-    params['url'] = base_url + search_string.format(query=query.decode())
-    params['route'] = route_re.match(query.decode())
+    params['url'] = base_url + search_string.format(query=query)
+    params['route'] = route_re.match(query)
 
     return params
 

searx/engines/scanr_structures.py

@@ -29,7 +29,7 @@ def request(query, params):
     params['url'] = search_url
     params['method'] = 'POST'
     params['headers']['Content-type'] = "application/json"
-    params['data'] = dumps({"query": query.decode(),
+    params['data'] = dumps({"query": query,
                             "searchField": "ALL",
                             "sortDirection": "ASC",
                             "sortOrder": "RELEVANCY",

searx/engines/translated.py

@@ -16,7 +16,7 @@ url = 'https://api.mymemory.translated.net/get?q={query}&langpair={from_lang}|{t
 web_url = 'https://mymemory.translated.net/en/{from_lang}/{to_lang}/{query}'
 weight = 100
 
-parser_re = re.compile(b'.*?([a-z]+)-([a-z]+) (.{2,})$', re.I)
+parser_re = re.compile('.*?([a-z]+)-([a-z]+) (.{2,})$', re.I)
 api_key = ''
 
 
@@ -39,9 +39,9 @@ def request(query, params):
         key_form = ''
     params['url'] = url.format(from_lang=from_lang[1],
                                to_lang=to_lang[1],
-                               query=query.decode(),
+                               query=query,
                                key=key_form)
-    params['query'] = query.decode()
+    params['query'] = query
     params['from_lang'] = from_lang
     params['to_lang'] = to_lang
 

searx/external_bang.py

@@ -23,7 +23,7 @@ def get_bang_url(search_query):
     """
 
     if search_query.external_bang:
-        query = search_query.query.decode(errors='ignore')
+        query = search_query.query
         bang = _get_bang(search_query.external_bang)
 
         if bang and query:

searx/plugins/self_info.py

@@ -22,7 +22,7 @@ default_on = True
 
 
 # Self User Agent regex
-p = re.compile(b'.*user[ -]agent.*', re.IGNORECASE)
+p = re.compile('.*user[ -]agent.*', re.IGNORECASE)
 
 
 # attach callback to the post search hook
@@ -31,7 +31,7 @@ p = re.compile(b'.*user[ -]agent.*', re.IGNORECASE)
 def post_search(request, search):
     if search.search_query.pageno > 1:
         return True
-    if search.search_query.query == b'ip':
+    if search.search_query.query == 'ip':
         x_forwarded_for = request.headers.getlist("X-Forwarded-For")
         if x_forwarded_for:
             ip = x_forwarded_for[0]

searx/query.py

@@ -32,6 +32,7 @@ class RawTextQuery:
     """parse raw text query (the value from the html input)"""
 
     def __init__(self, query, disabled_engines):
+        assert isinstance(query, str)
         self.query = query
         self.disabled_engines = []
 
@@ -51,7 +52,7 @@ class RawTextQuery:
         self.query_parts = []
 
         # split query, including whitespaces
-        raw_query_parts = re.split(r'(\s+)' if isinstance(self.query, str) else b'(\s+)', self.query)
+        raw_query_parts = re.split(r'(\s+)', self.query)
 
         parse_next = True
 
@@ -183,7 +184,7 @@ class SearchQuery:
 
     def __init__(self, query, engines, categories, lang, safesearch, pageno, time_range,
                  timeout_limit=None, preferences=None, external_bang=None):
-        self.query = query.encode()
+        self.query = query
         self.engines = engines
         self.categories = categories
         self.lang = lang
@@ -195,4 +196,4 @@ class SearchQuery:
         self.external_bang = external_bang
 
     def __str__(self):
-        return str(self.query) + ";" + str(self.engines)
+        return self.query + ";" + str(self.engines)

searx/utils.py

@@ -59,7 +59,6 @@ def highlight_content(content, query):
     if content.find('<') != -1:
         return content
 
-    query = query.decode()
     if content.lower().find(query.lower()) > -1:
         query_regex = '({0})'.format(re.escape(query))
         content = re.sub(query_regex, '<span class="highlight">\\1</span>',

searx/webapp.py

@@ -623,7 +623,7 @@ def index():
                     result['publishedDate'] = format_date(result['publishedDate'])
 
     if output_format == 'json':
-        return Response(json.dumps({'query': search_query.query.decode(),
+        return Response(json.dumps({'query': search_query.query,
                                     'number_of_results': number_of_results,
                                     'results': results,
                                     'answers': list(result_container.answers),
@@ -652,7 +652,7 @@ def index():
             csv.writerow([row.get(key, '') for key in keys])
         csv.stream.seek(0)
         response = Response(csv.stream.read(), mimetype='application/csv')
-        cont_disp = 'attachment;Filename=searx_-_{0}.csv'.format(search_query.query.decode())
+        cont_disp = 'attachment;Filename=searx_-_{0}.csv'.format(search_query.query)
         response.headers.add('Content-Disposition', cont_disp)
         return response
 
@@ -736,7 +736,7 @@ def autocompleter():
     disabled_engines = request.preferences.engines.get_disabled()
 
     # parse query
-    raw_text_query = RawTextQuery(request.form.get('q', b''), disabled_engines)
+    raw_text_query = RawTextQuery(str(request.form.get('q', b'')), disabled_engines)
     raw_text_query.parse_query()
 
     # check if search query is set

tests/unit/test_plugins.py

@@ -48,11 +48,11 @@ class SelfIPTest(SearxTestCase):
         # IP test
         request = Mock(remote_addr='127.0.0.1')
         request.headers.getlist.return_value = []
-        search = get_search_mock(query=b'ip', pageno=1)
+        search = get_search_mock(query='ip', pageno=1)
         store.call(store.plugins, 'post_search', request, search)
         self.assertTrue('127.0.0.1' in search.result_container.answers["ip"]["answer"])
 
-        search = get_search_mock(query=b'ip', pageno=2)
+        search = get_search_mock(query='ip', pageno=2)
         store.call(store.plugins, 'post_search', request, search)
         self.assertFalse('ip' in search.result_container.answers)
 
@@ -60,26 +60,26 @@ class SelfIPTest(SearxTestCase):
         request = Mock(user_agent='Mock')
         request.headers.getlist.return_value = []
 
-        search = get_search_mock(query=b'user-agent', pageno=1)
+        search = get_search_mock(query='user-agent', pageno=1)
         store.call(store.plugins, 'post_search', request, search)
         self.assertTrue('Mock' in search.result_container.answers["user-agent"]["answer"])
 
-        search = get_search_mock(query=b'user-agent', pageno=2)
+        search = get_search_mock(query='user-agent', pageno=2)
         store.call(store.plugins, 'post_search', request, search)
         self.assertFalse('user-agent' in search.result_container.answers)
 
-        search = get_search_mock(query=b'user-agent', pageno=1)
+        search = get_search_mock(query='user-agent', pageno=1)
         store.call(store.plugins, 'post_search', request, search)
         self.assertTrue('Mock' in search.result_container.answers["user-agent"]["answer"])
 
-        search = get_search_mock(query=b'user-agent', pageno=2)
+        search = get_search_mock(query='user-agent', pageno=2)
         store.call(store.plugins, 'post_search', request, search)
         self.assertFalse('user-agent' in search.result_container.answers)
 
-        search = get_search_mock(query=b'What is my User-Agent?', pageno=1)
+        search = get_search_mock(query='What is my User-Agent?', pageno=1)
         store.call(store.plugins, 'post_search', request, search)
         self.assertTrue('Mock' in search.result_container.answers["user-agent"]["answer"])
 
-        search = get_search_mock(query=b'What is my User-Agent?', pageno=2)
+        search = get_search_mock(query='What is my User-Agent?', pageno=2)
         store.call(store.plugins, 'post_search', request, search)
         self.assertFalse('user-agent' in search.result_container.answers)

tests/unit/test_utils.py

@@ -30,9 +30,9 @@ class TestUtils(SearxTestCase):
             self.assertEqual(utils.highlight_content(content, None), content)
 
         content = 'a'
-        query = b'test'
+        query = 'test'
         self.assertEqual(utils.highlight_content(content, query), content)
-        query = b'a test'
+        query = 'a test'
         self.assertEqual(utils.highlight_content(content, query), content)
 
     def test_html_to_text(self):