IntenseWebs/sphinx
3
0
Fork 0
mirror of https://github.com/sphinx-doc/sphinx.git synced 2025-02-25 18:55:22 -06:00
Code Issues Packages Projects Releases Wiki Activity

Simplify Sphinx's Stemmer (#10467)

Browse Source
This commit is contained in:
Adam Turner
2022-06-16 19:47:09 +01:00
committed by GitHub
parent 956cddb7d4
commit 881f66c557
7 changed files with 61 additions and 434 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
AUTHORS
View File

@@ -96,5 +96,3 @@ authors and projects:
* sphinx.util.jsdump uses the basestring encoding from simplejson,
written by Bob Ippolito, released under the MIT license
* sphinx.util.stemmer was written by Vivake Gupta, placed in the
Public Domain

3
CHANGES
View File

@@ -10,6 +10,9 @@ Incompatible changes
Deprecated
----------
* #10467: Deprecated ``sphinx.util.stemmer`` in favour of ``snowballstemmer``.
Patch by Adam Turner.
Features added
--------------

5
doc/extdev/deprecated.rst
View File

@@ -22,6 +22,11 @@ The following is a list of deprecated interfaces.
- (will be) Removed
- Alternatives
* - ``sphinx.util.stemmer``
- 5.1
- 7.0
- ``snowballstemmer``
* - ``sphinx.util.jsdump``
- 5.0
- 7.0

7
sphinx/search/en.py
View File

@@ -2,8 +2,9 @@
from typing import Dict
import snowballstemmer
from sphinx.search import SearchLanguage
from sphinx.util.stemmer import get_stemmer
english_stopwords = set("""
a and are as at
@@ -211,7 +212,7 @@ class SearchEnglish(SearchLanguage):
stopwords = english_stopwords
def init(self, options: Dict) -> None:
self.stemmer = get_stemmer()
self.stemmer = snowballstemmer.stemmer('porter')
def stem(self, word: str) -> str:
return self.stemmer.stem(word.lower())
return self.stemmer.stemWord(word.lower())

9
sphinx/search/zh.py
View File

@@ -4,8 +4,9 @@ import os
import re
from typing import Dict, List
import snowballstemmer
from sphinx.search import SearchLanguage
from sphinx.util.stemmer import get_stemmer
try:
import jieba
@@ -230,7 +231,7 @@ class SearchChinese(SearchLanguage):
if dict_path and os.path.isfile(dict_path):
jieba.load_userdict(dict_path)
self.stemmer = get_stemmer()
self.stemmer = snowballstemmer.stemmer('english')
def split(self, input: str) -> List[str]:
chinese: List[str] = []
@@ -252,8 +253,8 @@ class SearchChinese(SearchLanguage):
should_not_be_stemmed = (
word in self.latin_terms and
len(word) >= 3 and
len(self.stemmer.stem(word.lower())) < 3
len(self.stemmer.stemWord(word.lower())) < 3
)
if should_not_be_stemmed:
return word.lower()
return self.stemmer.stem(word.lower())
return self.stemmer.stemWord(word.lower())

61
sphinx/util/stemmer/__init__.py
View File

@@ -1,37 +1,62 @@
"""Word stemming utilities for Sphinx."""
from sphinx.util.stemmer.porter import PorterStemmer
import warnings
try:
from Stemmer import Stemmer as _PyStemmer
PYSTEMMER = True
except ImportError:
PYSTEMMER = False
import snowballstemmer
from sphinx.deprecation import RemovedInSphinx70Warning
class PorterStemmer:
def __init__(self):
warnings.warn(f"{self.__class__.__name__} is deprecated, use "
"snowballstemmer.stemmer('porter') instead.",
RemovedInSphinx70Warning, stacklevel=2)
self.stemmer = snowballstemmer.stemmer('porter')
def stem(self, p: str, i: int, j: int) -> str:
warnings.warn(f"{self.__class__.__name__}.stem() is deprecated, use "
"snowballstemmer.stemmer('porter').stemWord() instead.",
RemovedInSphinx70Warning, stacklevel=2)
return self.stemmer.stemWord(p)
class BaseStemmer:
def __init__(self):
warnings.warn(f"{self.__class__.__name__} is deprecated, use "
"snowballstemmer.stemmer('porter') instead.",
RemovedInSphinx70Warning, stacklevel=3)
def stem(self, word: str) -> str:
raise NotImplementedError()
raise NotImplementedError
class PyStemmer(BaseStemmer):
def __init__(self) -> None:
self.stemmer = _PyStemmer('porter')
def __init__(self): # NoQA
super().__init__()
self.stemmer = snowballstemmer.stemmer('porter')
def stem(self, word: str) -> str:
warnings.warn(f"{self.__class__.__name__}.stem() is deprecated, use "
"snowballstemmer.stemmer('porter').stemWord() instead.",
RemovedInSphinx70Warning, stacklevel=2)
return self.stemmer.stemWord(word)
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)
class StandardStemmer(BaseStemmer):
def __init__(self): # NoQA
super().__init__()
self.stemmer = snowballstemmer.stemmer('porter')
def stem(self, word: str) -> str:
warnings.warn(f"{self.__class__.__name__}.stem() is deprecated, use "
"snowballstemmer.stemmer('porter').stemWord() instead.",
RemovedInSphinx70Warning, stacklevel=2)
return self.stemmer.stemWord(word)
def get_stemmer() -> BaseStemmer:
if PYSTEMMER:
warnings.warn("get_stemmer() is deprecated, use "
"snowballstemmer.stemmer('porter') instead.",
RemovedInSphinx70Warning, stacklevel=2)
return PyStemmer()
else:
return StandardStemmer()

406
sphinx/util/stemmer/porter.py
View File

@@ -1,406 +0,0 @@
"""Porter Stemming Algorithm
This is the Porter stemming algorithm, ported to Python from the
version coded up in ANSI C by the author. It may be be regarded
as canonical, in that it follows the algorithm presented in
Porter, 1980, An algorithm for suffix stripping, Program, Vol. 14,
no. 3, pp 130-137,
only differing from it at the points made --DEPARTURE-- below.
See also https://tartarus.org/martin/PorterStemmer/
The algorithm as described in the paper could be exactly replicated
by adjusting the points of DEPARTURE, but this is barely necessary,
because (a) the points of DEPARTURE are definitely improvements, and
(b) no encoding of the Porter stemmer I have seen is anything like
as exact as this version, even with the points of DEPARTURE!
Release 1: January 2001
:author: Vivake Gupta <v@nano.com>.
:license: Public Domain ("can be used free of charge for any purpose").
"""
class PorterStemmer:
def __init__(self) -> None:
"""The main part of the stemming algorithm starts here.
b is a buffer holding a word to be stemmed. The letters are in b[k0],
b[k0+1] ... ending at b[k]. In fact k0 = 0 in this demo program. k is
readjusted downwards as the stemming progresses. Zero termination is
not in fact used in the algorithm.
Note that only lower case sequences are stemmed. Forcing to lower case
should be done before stem(...) is called.
"""
self.b = "" # buffer for word to be stemmed
self.k = 0
self.k0 = 0
self.j = 0 # j is a general offset into the string
def cons(self, i: int) -> int:
"""cons(i) is TRUE <=> b[i] is a consonant."""
if self.b[i] == 'a' or self.b[i] == 'e' or self.b[i] == 'i' \
or self.b[i] == 'o' or self.b[i] == 'u':
return 0
if self.b[i] == 'y':
if i == self.k0:
return 1
else:
return (not self.cons(i - 1))
return 1
def m(self) -> int:
"""m() measures the number of consonant sequences between k0 and j.
if c is a consonant sequence and v a vowel sequence, and <..>
indicates arbitrary presence,
<c><v> gives 0
<c>vc<v> gives 1
<c>vcvc<v> gives 2
<c>vcvcvc<v> gives 3
....
"""
n = 0
i = self.k0
while 1:
if i > self.j:
return n
if not self.cons(i):
break
i = i + 1
i = i + 1
while 1:
while 1:
if i > self.j:
return n
if self.cons(i):
break
i = i + 1
i = i + 1
n = n + 1
while 1:
if i > self.j:
return n
if not self.cons(i):
break
i = i + 1
i = i + 1
def vowelinstem(self) -> int:
"""vowelinstem() is TRUE <=> k0,...j contains a vowel"""
for i in range(self.k0, self.j + 1):
if not self.cons(i):
return 1
return 0
def doublec(self, j: int) -> int:
"""doublec(j) is TRUE <=> j,(j-1) contain a double consonant."""
if j < (self.k0 + 1):
return 0
if (self.b[j] != self.b[j - 1]):
return 0
return self.cons(j)
def cvc(self, i: int) -> int:
"""cvc(i) is TRUE <=> i-2,i-1,i has the form
consonant - vowel - consonant
and also if the second c is not w,x or y. this is used when trying to
restore an e at the end of a short e.g.
cav(e), lov(e), hop(e), crim(e), but
snow, box, tray.
"""
if i < (self.k0 + 2) or not self.cons(i) or self.cons(i - 1) \
or not self.cons(i - 2):
return 0
ch = self.b[i]
if ch in ('w', 'x', 'y'):
return 0
return 1
def ends(self, s: str) -> int:
"""ends(s) is TRUE <=> k0,...k ends with the string s."""
length = len(s)
if s[length - 1] != self.b[self.k]: # tiny speed-up
return 0
if length > (self.k - self.k0 + 1):
return 0
if self.b[self.k - length + 1:self.k + 1] != s:
return 0
self.j = self.k - length
return 1
def setto(self, s: str) -> None:
"""setto(s) sets (j+1),...k to the characters in the string s,
readjusting k."""
length = len(s)
self.b = self.b[:self.j + 1] + s + self.b[self.j + length + 1:]
self.k = self.j + length
def r(self, s: str) -> None:
"""r(s) is used further down."""
if self.m() > 0:
self.setto(s)
def step1ab(self) -> None:
"""step1ab() gets rid of plurals and -ed or -ing. e.g.
caresses -> caress
ponies -> poni
ties -> ti
caress -> caress
cats -> cat
feed -> feed
agreed -> agree
disabled -> disable
matting -> mat
mating -> mate
meeting -> meet
milling -> mill
messing -> mess
meetings -> meet
"""
if self.b[self.k] == 's':
if self.ends("sses"):
self.k = self.k - 2
elif self.ends("ies"):
self.setto("i")
elif self.b[self.k - 1] != 's':
self.k = self.k - 1
if self.ends("eed"):
if self.m() > 0:
self.k = self.k - 1
elif (self.ends("ed") or self.ends("ing")) and self.vowelinstem():
self.k = self.j
if self.ends("at"):
self.setto("ate")
elif self.ends("bl"):
self.setto("ble")
elif self.ends("iz"):
self.setto("ize")
elif self.doublec(self.k):
self.k = self.k - 1
ch = self.b[self.k]
if ch in ('l', 's', 'z'):
self.k = self.k + 1
elif (self.m() == 1 and self.cvc(self.k)):
self.setto("e")
def step1c(self) -> None:
"""step1c() turns terminal y to i when there is another vowel in
the stem."""
if (self.ends("y") and self.vowelinstem()):
self.b = self.b[:self.k] + 'i' + self.b[self.k + 1:]
def step2(self) -> None:
"""step2() maps double suffices to single ones.
so -ization ( = -ize plus -ation) maps to -ize etc. note that the
string before the suffix must give m() > 0.
"""
if self.b[self.k - 1] == 'a':
if self.ends("ational"):
self.r("ate")
elif self.ends("tional"):
self.r("tion")
elif self.b[self.k - 1] == 'c':
if self.ends("enci"):
self.r("ence")
elif self.ends("anci"):
self.r("ance")
elif self.b[self.k - 1] == 'e':
if self.ends("izer"):
self.r("ize")
elif self.b[self.k - 1] == 'l':
if self.ends("bli"):
self.r("ble") # --DEPARTURE--
# To match the published algorithm, replace this phrase with
# if self.ends("abli"): self.r("able")
elif self.ends("alli"):
self.r("al")
elif self.ends("entli"):
self.r("ent")
elif self.ends("eli"):
self.r("e")
elif self.ends("ousli"):
self.r("ous")
elif self.b[self.k - 1] == 'o':
if self.ends("ization"):
self.r("ize")
elif self.ends("ation"):
self.r("ate")
elif self.ends("ator"):
self.r("ate")
elif self.b[self.k - 1] == 's':
if self.ends("alism"):
self.r("al")
elif self.ends("iveness"):
self.r("ive")
elif self.ends("fulness"):
self.r("ful")
elif self.ends("ousness"):
self.r("ous")
elif self.b[self.k - 1] == 't':
if self.ends("aliti"):
self.r("al")
elif self.ends("iviti"):
self.r("ive")
elif self.ends("biliti"):
self.r("ble")
elif self.b[self.k - 1] == 'g': # --DEPARTURE--
if self.ends("logi"):
self.r("log")
# To match the published algorithm, delete this phrase
def step3(self) -> None:
"""step3() dels with -ic-, -full, -ness etc. similar strategy
to step2."""
if self.b[self.k] == 'e':
if self.ends("icate"):
self.r("ic")
elif self.ends("ative"):
self.r("")
elif self.ends("alize"):
self.r("al")
elif self.b[self.k] == 'i':
if self.ends("iciti"):
self.r("ic")
elif self.b[self.k] == 'l':
if self.ends("ical"):
self.r("ic")
elif self.ends("ful"):
self.r("")
elif self.b[self.k] == 's':
if self.ends("ness"):
self.r("")
def step4(self) -> None:
"""step4() takes off -ant, -ence etc., in context <c>vcvc<v>."""
if self.b[self.k - 1] == 'a':
if self.ends("al"):
pass
else:
return
elif self.b[self.k - 1] == 'c':
if self.ends("ance"):
pass
elif self.ends("ence"):
pass
else:
return
elif self.b[self.k - 1] == 'e':
if self.ends("er"):
pass
else:
return
elif self.b[self.k - 1] == 'i':
if self.ends("ic"):
pass
else:
return
elif self.b[self.k - 1] == 'l':
if self.ends("able"):
pass
elif self.ends("ible"):
pass
else:
return
elif self.b[self.k - 1] == 'n':
if self.ends("ant"):
pass
elif self.ends("ement"):
pass
elif self.ends("ment"):
pass
elif self.ends("ent"):
pass
else:
return
elif self.b[self.k - 1] == 'o':
if self.ends("ion") and (self.b[self.j] == 's' or
self.b[self.j] == 't'):
pass
elif self.ends("ou"):
pass
# takes care of -ous
else:
return
elif self.b[self.k - 1] == 's':
if self.ends("ism"):
pass
else:
return
elif self.b[self.k - 1] == 't':
if self.ends("ate"):
pass
elif self.ends("iti"):
pass
else:
return
elif self.b[self.k - 1] == 'u':
if self.ends("ous"):
pass
else:
return
elif self.b[self.k - 1] == 'v':
if self.ends("ive"):
pass
else:
return
elif self.b[self.k - 1] == 'z':
if self.ends("ize"):
pass
else:
return
else:
return
if self.m() > 1:
self.k = self.j
def step5(self) -> None:
"""step5() removes a final -e if m() > 1, and changes -ll to -l if
m() > 1.
"""
self.j = self.k
if self.b[self.k] == 'e':
a = self.m()
if a > 1 or (a == 1 and not self.cvc(self.k - 1)):
self.k = self.k - 1
if self.b[self.k] == 'l' and self.doublec(self.k) and self.m() > 1:
self.k = self.k - 1
def stem(self, p: str, i: int, j: int) -> str:
"""In stem(p,i,j), p is a char pointer, and the string to be stemmed
is from p[i] to p[j] inclusive. Typically i is zero and j is the
offset to the last character of a string, (p[j+1] == '\0'). The
stemmer adjusts the characters p[i] ... p[j] and returns the new
end-point of the string, k. Stemming never increases word length, so
i <= k <= j. To turn the stemmer into a module, declare 'stem' as
extern, and delete the remainder of this file.
"""
# copy the parameters into statics
self.b = p
self.k = j
self.k0 = i
if self.k <= self.k0 + 1:
return self.b # --DEPARTURE--
# With this line, strings of length 1 or 2 don't go through the
# stemming process, although no mention is made of this in the
# published algorithm. Remove the line to match the published
# algorithm.
self.step1ab()
self.step1c()
self.step2()
self.step3()
self.step4()
self.step5()
return self.b[self.k0:self.k + 1]