Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Deprecate sphinx.util.stemmer in favour of snowballstemmer
PorterStemmer, BaseStemmer, PyStemmer, StandardStemmer, and get_stemmer are deprecated sphinx.util.stemmer.porter is removed
- Loading branch information
Showing
5 changed files
with
60 additions
and
436 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -1,37 +1,67 @@ | ||
"""Word stemming utilities for Sphinx.""" | ||
import warnings | ||
|
||
from sphinx.util.stemmer.porter import PorterStemmer | ||
import snowballstemmer | ||
|
||
try: | ||
from Stemmer import Stemmer as _PyStemmer | ||
PYSTEMMER = True | ||
except ImportError: | ||
PYSTEMMER = False | ||
from sphinx.deprecation import RemovedInSphinx70Warning | ||
|
||
_ENGLISH_STEMMER_TYPE = type(snowballstemmer.stemmer('english')) | ||
|
||
|
||
class PorterStemmer(_ENGLISH_STEMMER_TYPE): | ||
def __init__(self): | ||
warnings.warn(f"{self.__class__.__name__} is deprecated, use " | ||
"snowballstemmer.stemmer('english') instead.", | ||
RemovedInSphinx70Warning, stacklevel=2) | ||
super().__init__() | ||
|
||
def stem(self, p: str, i: int, j: int) -> str: | ||
warnings.warn(f"{self.__class__.__name__}.stem() is deprecated, use " | ||
"snowballstemmer.stemmer('english').stemWord() instead.", | ||
RemovedInSphinx70Warning, stacklevel=2) | ||
return self.stemWord(p) | ||
|
||
|
||
class BaseStemmer: | ||
def __init__(self): | ||
warnings.warn(f"{self.__class__.__name__} is deprecated.", | ||
RemovedInSphinx70Warning, stacklevel=2) | ||
super().__init__() | ||
|
||
def stem(self, word: str) -> str: | ||
raise NotImplementedError() | ||
raise NotImplementedError | ||
|
||
|
||
class PyStemmer(BaseStemmer): | ||
def __init__(self) -> None: | ||
self.stemmer = _PyStemmer('porter') | ||
class PyStemmer(BaseStemmer, _ENGLISH_STEMMER_TYPE): | ||
def __init__(self): | ||
warnings.warn(f"{self.__class__.__name__} is deprecated, use " | ||
"snowballstemmer.stemmer('english') instead.", | ||
RemovedInSphinx70Warning, stacklevel=2) | ||
super().__init__() | ||
|
||
def stem(self, word: str) -> str: | ||
return self.stemmer.stemWord(word) | ||
warnings.warn(f"{self.__class__.__name__}.stem() is deprecated, use " | ||
"snowballstemmer.stemmer('english').stemWord() instead.", | ||
RemovedInSphinx70Warning, stacklevel=2) | ||
return self.stemWord(word) | ||
|
||
|
||
class StandardStemmer(BaseStemmer, PorterStemmer): | ||
def __init__(self): | ||
warnings.warn(f"{self.__class__.__name__} is deprecated, use " | ||
"snowballstemmer.stemmer('english') instead.", | ||
RemovedInSphinx70Warning, stacklevel=2) | ||
super().__init__() | ||
|
||
class StandardStemmer(PorterStemmer, BaseStemmer): | ||
"""All those porter stemmer implementations look hideous; | ||
make at least the stem method nicer. | ||
""" | ||
def stem(self, word: str) -> str: # type: ignore | ||
return super().stem(word, 0, len(word) - 1) | ||
def stem(self, word: str) -> str: | ||
warnings.warn(f"{self.__class__.__name__}.stem() is deprecated, use " | ||
"snowballstemmer.stemmer('english').stemWord() instead.", | ||
RemovedInSphinx70Warning, stacklevel=2) | ||
return self.stemWord(word) | ||
|
||
|
||
def get_stemmer() -> BaseStemmer: | ||
if PYSTEMMER: | ||
return PyStemmer() | ||
else: | ||
return StandardStemmer() | ||
warnings.warn("get_stemmer() is deprecated, use " | ||
"snowballstemmer.stemmer('english') instead.", | ||
RemovedInSphinx70Warning, stacklevel=2) | ||
return PyStemmer() |
Oops, something went wrong.