hans/Nominatim
1
0
Fork 1
mirror of https://github.com/osm-search/Nominatim.git synced 2026-02-26 11:08:13 +00:00
Code Issues Packages Projects Releases Wiki Activity

update to modern mkdocstrings python handler

Browse Source
This commit is contained in:
Sarah Hoffmann
2023-08-18 17:28:45 +02:00
parent d5b6042118
commit d3372e69ec
9 changed files with 75 additions and 71 deletions
Download Patch File Download Diff File Expand all files Collapse all files

20
nominatim/tokenizer/base.py
View File

@@ -53,8 +53,8 @@ class AbstractAnalyzer(ABC):
Returns:
The function returns the list of all tuples that could be
found for the given words. Each list entry is a tuple of
(original word, word token, word id).
found for the given words. Each list entry is a tuple of
(original word, word token, word id).
"""
@@ -118,7 +118,7 @@ class AbstractAnalyzer(ABC):
Returns:
A JSON-serialisable structure that will be handed into
the database via the `token_info` field.
the database via the `token_info` field.
"""
@@ -144,8 +144,6 @@ class AbstractTokenizer(ABC):
tables should be skipped. This option is only required for
migration purposes and can be safely ignored by custom
tokenizers.
TODO: can we move the init_db parameter somewhere else?
"""
@@ -197,8 +195,8 @@ class AbstractTokenizer(ABC):
Returns:
If an issue was found, return an error message with the
description of the issue as well as hints for the user on
how to resolve the issue. If everything is okay, return `None`.
description of the issue as well as hints for the user on
how to resolve the issue. If everything is okay, return `None`.
"""
@@ -236,8 +234,12 @@ class AbstractTokenizer(ABC):
@abstractmethod
def most_frequent_words(self, conn: Connection, num: int) -> List[str]:
""" Return a list of the `num` most frequent full words
in the database.
""" Return a list of the most frequent full words in the database.
Arguments:
conn: Open connection to the database which may be used to
retrive the words.
num: Maximum number of words to return.
"""

18
nominatim/tokenizer/sanitizers/config.py
View File

@@ -41,9 +41,9 @@ class SanitizerConfig(_BaseUserDict):
Returns:
If the parameter value is a simple string, it is returned as a
one-item list. If the parameter value does not exist, the given
default is returned. If the parameter value is a list, it is
checked to contain only strings before being returned.
one-item list. If the parameter value does not exist, the given
default is returned. If the parameter value is a list, it is
checked to contain only strings before being returned.
"""
values = self.data.get(param, None)
@@ -94,10 +94,10 @@ class SanitizerConfig(_BaseUserDict):
Returns:
A regular expression pattern which can be used to
split a string. The regular expression makes sure that the
resulting names are stripped and that repeated delimiters
are ignored. It may still create empty fields on occasion. The
code needs to filter those.
split a string. The regular expression makes sure that the
resulting names are stripped and that repeated delimiters
are ignored. It may still create empty fields on occasion. The
code needs to filter those.
"""
delimiter_set = set(self.data.get('delimiters', default))
if not delimiter_set:
@@ -133,8 +133,8 @@ class SanitizerConfig(_BaseUserDict):
Returns:
A filter function that takes a target string as the argument and
returns True if it fully matches any of the regular expressions
otherwise returns False.
returns True if it fully matches any of the regular expressions
otherwise returns False.
"""
filters = self.get_string_list(param) or default

24
nominatim/tokenizer/token_analysis/base.py
View File

@@ -28,8 +28,8 @@ class Analyzer(Protocol):
Returns:
ID string with a canonical form of the name. The string may
be empty, when the analyzer cannot analyze the name at all,
for example because the character set in use does not match.
be empty, when the analyzer cannot analyze the name at all,
for example because the character set in use does not match.
"""
def compute_variants(self, canonical_id: str) -> List[str]:
@@ -42,13 +42,13 @@ class Analyzer(Protocol):
Returns:
A list of possible spelling variants. All strings must have
been transformed with the global normalizer and
transliterator ICU rules. Otherwise they cannot be matched
against the input by the query frontend.
The list may be empty, when there are no useful
spelling variants. This may happen when an analyzer only
usually outputs additional variants to the canonical spelling
and there are no such variants.
been transformed with the global normalizer and
transliterator ICU rules. Otherwise they cannot be matched
against the input by the query frontend.
The list may be empty, when there are no useful
spelling variants. This may happen when an analyzer only
usually outputs additional variants to the canonical spelling
and there are no such variants.
"""
@@ -74,8 +74,8 @@ class AnalysisModule(Protocol):
Returns:
A data object with configuration data. This will be handed
as is into the `create()` function and may be
used freely by the analysis module as needed.
as is into the `create()` function and may be
used freely by the analysis module as needed.
"""
def create(self, normalizer: Any, transliterator: Any, config: Any) -> Analyzer:
@@ -92,5 +92,5 @@ class AnalysisModule(Protocol):
Returns:
A new analyzer instance. This must be an object that implements
the Analyzer protocol.
the Analyzer protocol.
"""