[mod] normalize variable name for the max number of results per request (#6131)

[mod] normalize variable name for the max number of results per request

In the past, we have used different names for the variable that specifies the
maximum number of hits in the outgoing request.

- ``page_size``
- ``number_of_results``
- ``nb_per_page``

Since *page_size* is the most accurate term and is also used in the XPath
engines, all other engines are adjusted accordingly within this
patch .. documentation adjusted accordingly.

Signed-off-by: Markus Heiser <markus.heiser@darmarit.de>

docs/dev/engines/engine_overview.rst

@@ -107,7 +107,7 @@ module:
    ======================= =========== ===========================================
    base_url                string      base-url, can be overwritten to use same
                                        engine on other URL
-   number_of_results       int         maximum number of results per request
+   page_size               int         maximum number of results per request
    language                string      ISO code of language and country like en_US
    api_key                 string      api-key if required by engine
    ======================= =========== ===========================================

searx/engines/artic.py

@@ -21,7 +21,7 @@ about = {
 
 categories = ['images']
 paging = True
-nb_per_page = 20
+page_size = 20
 
 search_api = 'https://api.artic.edu/api/v1/artworks/search?'
 image_api = 'https://www.artic.edu/iiif/2/'
@@ -34,7 +34,7 @@ def request(query, params):
             'q': query,
             'page': params['pageno'],
             'fields': 'id,title,artist_display,medium_display,image_id,date_display,dimensions,artist_titles',
-            'limit': nb_per_page,
+            'limit': page_size,
         }
     )
     params['url'] = search_api + args

searx/engines/base.py

@@ -26,7 +26,7 @@ base_url = (
 
 # engine dependent config
 paging = True
-number_of_results = 10
+page_size = 10
 
 # shortcuts for advanced search
 shortcut_dict = {
@@ -57,12 +57,12 @@ def request(query, params):
         query = re.sub(key, val, query)
 
     # basic search
-    offset = (params['pageno'] - 1) * number_of_results
+    offset = (params['pageno'] - 1) * page_size
 
     string_args = {
         'query': urlencode({'query': query}),
         'offset': offset,
-        'hits': number_of_results,
+        'hits': page_size,
     }
 
     params['url'] = base_url.format(**string_args)

searx/engines/chefkoch.py

@@ -16,7 +16,7 @@ about = {
 paging = True
 categories = []
 
-number_of_results = 20
+page_size = 20
 skip_premium = True
 
 
@@ -25,7 +25,7 @@ thumbnail_format = "crop-240x300"
 
 
 def request(query, params):
-    args = {'query': query, 'limit': number_of_results, 'offset': (params['pageno'] - 1) * number_of_results}
+    args = {'query': query, 'limit': page_size, 'offset': (params['pageno'] - 1) * page_size}
     params['url'] = f"{base_url}/v2/search-gateway/recipes?{urlencode(args)}"
     return params
 

searx/engines/core.py

@@ -56,7 +56,7 @@ the API key in the engine :ref:`core engine config`."""
 
 categories = ["science", "scientific publications"]
 paging = True
-nb_per_page = 10
+page_size = 10
 base_url = "https://api.core.ac.uk/v3/search/works/"
 
 
@@ -77,8 +77,8 @@ def request(query: str, params: "OnlineParams") -> None:
     # API v3 uses different parameters
     search_params = {
         "q": query,
-        "offset": (params["pageno"] - 1) * nb_per_page,
+        "offset": (params["pageno"] - 1) * page_size,
-        "limit": nb_per_page,
+        "limit": page_size,
         "sort": "relevance",
     }
 

searx/engines/dailymotion.py

@@ -38,7 +38,7 @@ about = {
 # engine dependent config
 categories = ["videos"]
 paging = True
-number_of_results = 10
+page_size = 10
 
 time_range_support = True
 time_delta_dict = {
@@ -113,7 +113,7 @@ def request(query, params):
         "password_protected": "false",
         "private": "false",
         "sort": "relevance",
-        "limit": number_of_results,
+        "limit": page_size,
         "fields": ",".join(result_fields),
     }
 

searx/engines/doku.py

@@ -21,7 +21,6 @@ about = {
 # engine dependent config
 categories = ['general']  # 'images', 'music', 'videos', 'files'
 paging = False
-number_of_results = 5
 
 # search-url
 # Doku is OpenSearch compatible

searx/engines/flickr.py

@@ -20,7 +20,7 @@ about = {
 
 categories = ['images']
 
-nb_per_page = 15
+page_size = 15
 paging = True
 api_key = None
 
@@ -29,7 +29,7 @@ url = (
     'https://api.flickr.com/services/rest/?method=flickr.photos.search'
     + '&api_key={api_key}&{text}&sort=relevance'
     + '&extras=description%2C+owner_name%2C+url_o%2C+url_n%2C+url_z'
-    + '&per_page={nb_per_page}&format=json&nojsoncallback=1&page={page}'
+    + '&per_page={page_size}&format=json&nojsoncallback=1&page={page}'
 )
 photo_url = 'https://www.flickr.com/photos/{userid}/{photoid}'
 
@@ -42,7 +42,7 @@ def build_flickr_url(user_id, photo_id):
 
 def request(query, params):
     params['url'] = url.format(
-        text=urlencode({'text': query}), api_key=api_key, nb_per_page=nb_per_page, page=params['pageno']
+        text=urlencode({'text': query}), api_key=api_key, page_size=page_size, page=params['pageno']
     )
     return params
 

searx/engines/mediawiki.py

@@ -51,7 +51,7 @@ about = {
 # engine dependent config
 categories = ['general']
 paging = True
-number_of_results = 5
+page_size = 5
 
 search_type: str = 'nearmatch'
 """Which type of search to perform.  One of the following values: ``nearmatch``,
@@ -110,7 +110,7 @@ def request(query, params):
         params['language'] = params['language'].split('-')[0]
 
     api_url = f"{base_url.rstrip('/')}/{api_path}?".format(language=params['language'])
-    offset = (params['pageno'] - 1) * number_of_results
+    offset = (params['pageno'] - 1) * page_size
 
     args = {
         'action': 'query',
@@ -118,7 +118,7 @@ def request(query, params):
         'format': 'json',
         'srsearch': query,
         'sroffset': offset,
-        'srlimit': number_of_results,
+        'srlimit': page_size,
         'srwhat': search_type,
         'srprop': srprop,
         'srsort': srsort,

searx/engines/metacpan.py

@@ -14,7 +14,7 @@ about = {
 }
 
 # engine dependent config
-number_of_results = 20  # Don't put this over 5000
+page_size = 20  # Don't put this over 5000
 categories = ["it", "packages"]
 disabled = True
 shortcut = "cpan"
@@ -43,7 +43,7 @@ query_data_template = {
         {"date": {"order": "desc"}},
     ],
     '_source': ['documentation', "abstract"],
-    'size': number_of_results,
+    'size': page_size,
 }
 search_url = urlunparse(["https", "fastapi.metacpan.org", "/v1/file/_search", "", "", ""])
 
@@ -53,7 +53,7 @@ def request(query, params):
     params["method"] = "POST"
     query_data = query_data_template
     query_data["query"]["multi_match"]["query"] = query
-    query_data["from"] = (params["pageno"] - 1) * number_of_results
+    query_data["from"] = (params["pageno"] - 1) * page_size
     params["json"] = query_data
     return params
 

searx/engines/openverse.py

@@ -21,15 +21,15 @@ about = {
 categories = ['images']
 
 paging = True
-nb_per_page = 20
+page_size = 20
 
 base_url = 'https://api.openverse.org/v1/images/'
-search_string = '?page={page}&page_size={nb_per_page}&format=json&{query}'
+search_string = '?page={page}&page_size={page_size}&format=json&{query}'
 
 
 def request(query, params):
 
-    search_path = search_string.format(query=urlencode({'q': query}), nb_per_page=nb_per_page, page=params['pageno'])
+    search_path = search_string.format(query=urlencode({'q': query}), page_size=page_size, page=params['pageno'])
 
     params['url'] = base_url + search_path
 

searx/engines/photon.py

@@ -20,7 +20,7 @@ about = {
 # engine dependent config
 categories = ['map']
 paging = False
-number_of_results = 10
+page_size = 10
 
 # search-url
 base_url = 'https://photon.komoot.io/'
@@ -33,7 +33,7 @@ supported_languages = ['de', 'en', 'fr', 'it']
 
 # do search-request
 def request(query, params):
-    params['url'] = base_url + search_string.format(query=urlencode({'q': query}), limit=number_of_results)
+    params['url'] = base_url + search_string.format(query=urlencode({'q': query}), limit=page_size)
 
     if params['language'] != 'all':
         language = params['language'].split('_')[0]

searx/engines/pubmed.py

@@ -57,7 +57,7 @@ categories = ["science", "scientific publications"]
 eutils_api = "https://eutils.ncbi.nlm.nih.gov/entrez/eutils"
 
 # engine dependent config
-number_of_results = 10
+page_size = 10
 pubmed_url = "https://www.ncbi.nlm.nih.gov/pubmed/"
 
 
@@ -67,8 +67,8 @@ def request(query: str, params: "OnlineParams") -> None:
         {
             "db": "pubmed",
             "term": query,
-            "retstart": (params["pageno"] - 1) * number_of_results,
+            "retstart": (params["pageno"] - 1) * page_size,
-            "hits": number_of_results,
+            "hits": page_size,
         }
     )
     esearch_url = f"{eutils_api}/esearch.fcgi?{args}"

searx/engines/radio_browser.py

@@ -28,7 +28,7 @@ about = {
 paging = True
 categories = ["music", "radio"]
 
-number_of_results = 10
+page_size = 10
 
 station_filters = []  # ['countrycode', 'language']
 """A list of filters to be applied to the search of radio stations.  By default
@@ -100,8 +100,8 @@ def request(query, params):
     args = {
         "name": query,
         "order": "votes",
-        "offset": (params["pageno"] - 1) * number_of_results,
+        "offset": (params["pageno"] - 1) * page_size,
-        "limit": number_of_results,
+        "limit": page_size,
         "hidebroken": "true",
         "reverse": "true",
     }

searx/engines/springer.py

@@ -74,7 +74,7 @@ about = {
 categories = ["science", "scientific publications"]
 
 paging = True
-nb_per_page = 10
+page_size = 10
 """Number of results to return in the request, see `Pagination and Limits`_ for
 more details.
 
@@ -109,8 +109,8 @@ def request(query: str, params: "OnlineParams") -> None:
     args = {
         "api_key": api_key,
         "q": query,
-        "s": nb_per_page * (params["pageno"] - 1),
+        "s": page_size * (params["pageno"] - 1),
-        "p": nb_per_page,
+        "p": page_size,
     }
     params["url"] = f"{base_url}?{urlencode(args)}"
     # For example, the ``year:`` filter requires a *Premium Plan* subscription.

searx/engines/wikicommons.py

@@ -62,7 +62,7 @@ about = {
 
 categories: list[str] = []
 paging = True
-number_of_results = 10
+page_size = 10
 
 wc_api_url = "https://commons.wikimedia.org/w/api.php"
 wc_search_type: str = ""
@@ -107,8 +107,8 @@ def request(query: str, params: "OnlineParams") -> None:
         "generator": "search",
         "gsrnamespace": "6",  # https://www.mediawiki.org/wiki/Help:Namespaces#Renaming_namespaces
         "gsrprop": "snippet",
-        "gsrlimit": number_of_results,
+        "gsrlimit": page_size,
-        "gsroffset": number_of_results * (params["pageno"] - 1),
+        "gsroffset": page_size * (params["pageno"] - 1),
         "gsrsearch": f"filetype:{filetype} {query}",
         # imageinfo: https://commons.wikimedia.org/w/api.php?action=help&modules=query%2Bimageinfo
         "iiprop": "url|size|mime",

searx/engines/yacy.py

@@ -75,7 +75,7 @@ about = {
 # engine dependent config
 categories = ['general']
 paging = True
-number_of_results = 10
+page_size = 10
 http_digest_auth_user = ""
 """HTTP digest user for the local YACY instance"""
 http_digest_auth_pass = ""
@@ -125,11 +125,11 @@ def _base_url() -> str:
 
 def request(query, params):
 
-    offset = (params['pageno'] - 1) * number_of_results
+    offset = (params['pageno'] - 1) * page_size
     args = {
         'query': query,
         'startRecord': offset,
-        'maximumRecords': number_of_results,
+        'maximumRecords': page_size,
         'contentdom': search_type,
         'resource': search_mode,
     }

searx/settings.yml

@@ -1391,7 +1391,6 @@ engines:
     engine: metacpan
     shortcut: cpan
     disabled: true
-    number_of_results: 20
 
   # https://docs.searxng.org/dev/engines/offline/search-indexer-engines.html#module-searx.engines.meilisearch
   # - name: meilisearch