1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
|
From 2a04eb936ccb60af4dfdd523c68b99e0d43e373f Mon Sep 17 00:00:00 2001
From: Jamison Lahman <jamison@lahman.dev>
Date: Sat, 29 Jul 2023 16:33:16 -0700
Subject: [PATCH] [chore] fix "SyntaxError: invalid escape sequence"
---
src/whoosh/analysis/filters.py | 4 ++--
src/whoosh/analysis/intraword.py | 6 +++---
src/whoosh/lang/paicehusk.py | 2 +-
src/whoosh/lang/porter2.py | 2 +-
tests/test_analysis.py | 2 +-
5 files changed, 8 insertions(+), 8 deletions(-)
diff --git a/src/whoosh/analysis/filters.py b/src/whoosh/analysis/filters.py
index 3b6f5b47..5cea1480 100644
--- a/src/whoosh/analysis/filters.py
+++ b/src/whoosh/analysis/filters.py
@@ -53,7 +53,7 @@
\\S+? # URL body
(?=\\s|[.]\\s|$|[.]$) # Stop at space/end, or a dot followed by space/end
) | ( # or...
- \w+([:.]?\w+)* # word characters, with opt. internal colons/dots
+ \\w+([:.]?\\w+)* # word characters, with opt. internal colons/dots
)
""", verbose=True)
@@ -145,7 +145,7 @@ def __call__(self, tokens):
class TeeFilter(Filter):
- """Interleaves the results of two or more filters (or filter chains).
+ r"""Interleaves the results of two or more filters (or filter chains).
NOTE: because it needs to create copies of each token for each sub-filter,
this filter is quite slow.
diff --git a/src/whoosh/analysis/intraword.py b/src/whoosh/analysis/intraword.py
index 601423e1..9c1b8831 100644
--- a/src/whoosh/analysis/intraword.py
+++ b/src/whoosh/analysis/intraword.py
@@ -34,7 +34,7 @@
class CompoundWordFilter(Filter):
- """Given a set of words (or any object with a ``__contains__`` method),
+ r"""Given a set of words (or any object with a ``__contains__`` method),
break any tokens in the stream that are composites of words in the word set
into their individual parts.
@@ -272,7 +272,7 @@ class IntraWordFilter(Filter):
>>> iwf_i = IntraWordFilter(mergewords=True, mergenums=True)
>>> iwf_q = IntraWordFilter(mergewords=False, mergenums=False)
>>> iwf = MultiFilter(index=iwf_i, query=iwf_q)
- >>> analyzer = RegexTokenizer(r"\S+") | iwf | LowercaseFilter()
+ >>> analyzer = RegexTokenizer(r"\\S+") | iwf | LowercaseFilter()
(See :class:`MultiFilter`.)
"""
@@ -282,7 +282,7 @@ class IntraWordFilter(Filter):
__inittypes__ = dict(delims=text_type, splitwords=bool, splitnums=bool,
mergewords=bool, mergenums=bool)
- def __init__(self, delims=u("-_'\"()!@#$%^&*[]{}<>\|;:,./?`~=+"),
+ def __init__(self, delims=u("-_'\"()!@#$%^&*[]{}<>\\|;:,./?`~=+"),
splitwords=True, splitnums=True,
mergewords=False, mergenums=False):
"""
diff --git a/src/whoosh/lang/paicehusk.py b/src/whoosh/lang/paicehusk.py
index 481c3e40..6aee9066 100644
--- a/src/whoosh/lang/paicehusk.py
+++ b/src/whoosh/lang/paicehusk.py
@@ -30,7 +30,7 @@ class PaiceHuskStemmer(object):
(?P<cont>[.>])
""", re.UNICODE | re.VERBOSE)
- stem_expr = re.compile("^\w+", re.UNICODE)
+ stem_expr = re.compile(r"^\w+", re.UNICODE)
def __init__(self, ruletable):
"""
diff --git a/src/whoosh/lang/porter2.py b/src/whoosh/lang/porter2.py
index 4c740473..4d669752 100644
--- a/src/whoosh/lang/porter2.py
+++ b/src/whoosh/lang/porter2.py
@@ -64,7 +64,7 @@ def remove_initial_apostrophe(word):
def capitalize_consonant_ys(word):
if word.startswith('y'):
word = 'Y' + word[1:]
- return ccy_exp.sub('\g<1>Y', word)
+ return ccy_exp.sub(r'\g<1>Y', word)
def step_0(word):
diff --git a/tests/test_analysis.py b/tests/test_analysis.py
index c46a70db..425415f4 100644
--- a/tests/test_analysis.py
+++ b/tests/test_analysis.py
@@ -520,7 +520,7 @@ def test_stop_lang():
def test_issue358():
- t = analysis.RegexTokenizer("\w+")
+ t = analysis.RegexTokenizer(r"\w+")
with pytest.raises(analysis.CompositionError):
_ = t | analysis.StandardAnalyzer()
|
