Merge branch 'main' into more-ruff

.codiumai.toml

@@ -0,0 +1,40 @@
+#.codiumai.toml
+[tests]
+
+## Testing framework to use - this can affect the content of the generated tests
+## as well as the test run command.
+## Possible values are:
+##  Python: Pytest, Unittest
+framework = "Pytest"
+
+## A hint to the test generator about whether to use mocks or not. Possible values are true or false.
+# use_mocks = false
+
+## How many tests should be generated by default. Fewer tests is faster.
+## Does not apply at the moment to extend-suite tests.
+num_desired_tests = 20
+
+## A multiline string, delimited with triple-quotes (""") serving as an extra instruction
+## that the AI model will take into consideration.
+## This will appear as "General instructions" in the
+## configuration section in the tests panel.
+# plan_instructions = """
+# Each line should have a comment explaining it.
+# Each comment should start with the comment number (1., 2. etc.)
+# """
+
+## A multiline string, delimited with triple-quotes (""") serving as an example test that represents
+## what you would like the generated tests to look like in terms of style, setup, etc.
+# example_test = """
+# describe("something", () => {
+#   it("says 'bar'", () => {
+#     // given
+#
+#     // when
+#     const res = something.say();
+#
+#     // Then
+#     expect(res).to.equal("bar");
+#   });
+# });
+# """

.gitignore

@@ -11,3 +11,9 @@ eggs/
 /test.py
 /.vscode/settings.json
 /.coverage
+/whoosh-reloaded.code-workspace
+/.vscode/launch.json
+*.coverage.DESKTOP-*
+/coverage.xml
+/lcov.info
+/.codiumai.local.toml

.pre-commit-config.yaml

@@ -2,7 +2,6 @@ repos:
   - repo: https://github.com/pre-commit/pre-commit-hooks
     rev: v4.5.0
     hooks:
-      - id: check-added-large-files
       - id: check-ast
       - id: check-builtin-literals
       - id: check-merge-conflict

benchmark/dictionary.py

@@ -1,5 +1,5 @@
 import gzip
-import os.path
+import os
 
 from whoosh import analysis, fields
 from whoosh.support.bench import Bench, Spec

benchmark/marc21.py

@@ -4,7 +4,6 @@
 import re
 
 from whoosh import analysis, fields, index, qparser, query, scoring
-from whoosh.compat import range
 from whoosh.util import now
 
 log = logging.getLogger(__name__)

scripts/make_checkpoint.py

@@ -10,7 +10,7 @@
 from datetime import datetime
 
 from whoosh import fields, index
-from whoosh.compat import range, u
+from whoosh.compat import u
 
 if len(sys.argv) < 2:
     print("USAGE: make_checkpoint.py <dir>")

setup.cfg

@@ -22,3 +22,9 @@ addopts = -rs --tb=short
 norecursedirs = .hg .tox _build tmp* env* benchmark stress
 minversion = 3.0
 python_files = test_*.py
+
+[tool.coverage.run]
+source = ["src/whoosh"]
+
+[tool.pytest.ini_options]
+addopts = "--cov --cov-report=lcov:lcov.info --cov-report=term"

src/whoosh/analysis/intraword.py

@@ -29,7 +29,7 @@
 from collections import deque
 
 from whoosh.analysis.filters import Filter
-from whoosh.compat import range, text_type, u
+from whoosh.compat import text_type, u
 
 
 class CompoundWordFilter(Filter):

src/whoosh/analysis/ngrams.py

@@ -28,7 +28,7 @@
 from whoosh.analysis.acore import Token
 from whoosh.analysis.filters import Filter, LowercaseFilter
 from whoosh.analysis.tokenizers import RegexTokenizer, Tokenizer
-from whoosh.compat import range, text_type
+from whoosh.compat import text_type
 
 # Tokenizer
 

src/whoosh/automata/fsa.py

@@ -3,7 +3,7 @@
 import sys
 from bisect import bisect_left
 
-from whoosh.compat import iteritems, next, range, text_type, unichr
+from whoosh.compat import iteritems, next, text_type, unichr
 
 unull = unichr(0)
 
@@ -122,7 +122,7 @@ def dump(self, stream=sys.stdout):
             xs = self.transitions[src]
             for label in xs:
                 dests = xs[label]
-                end = "||" if self.is_final(dests) else ""
+                _ = "||" if self.is_final(dests) else ""
 
     def start(self):
         return frozenset(self._expand({self.initial}))
@@ -230,7 +230,7 @@ def dump(self, stream=sys.stdout):
             xs = self.transitions[src]
             for label in sorted(xs):
                 dest = xs[label]
-                end = "||" if self.is_final(dest) else ""
+                _ = "||" if self.is_final(dest) else ""
 
     def start(self):
         return self.initial
@@ -446,7 +446,7 @@ def u_to_utf8(dfa, base=0):
             if label is EPSILON:
                 continue
             elif label is ANY:
-                raise Exception
+                raise ValueError
             else:
                 assert isinstance(label, text_type)
                 label8 = label.encode("utf8")
@@ -652,9 +652,9 @@ def strings_dfa(strings):
 
     for string in strings:
         if string <= last:
-            raise Exception("Strings must be in order")
+            raise ValueError("Strings must be in order")
         if not string:
-            raise Exception("Can't add empty string")
+            raise ValueError("Can't add empty string")
 
         # Find the common prefix with the previous string
         i = 0

src/whoosh/automata/fst.py

@@ -307,7 +307,7 @@ def write(dbfile, v):
     def read(self, dbfile):
         typecode = u(dbfile.read(1))
         length = dbfile.read_int()
-        return dbfile.read_array(self.typecode, length)
+        return dbfile.read_array(typecode, length)
 
     def skip(self, dbfile):
         length = dbfile.read_int()

src/whoosh/automata/lev.py

@@ -1,5 +1,4 @@
 from whoosh.automata.fsa import ANY, EPSILON, NFA
-from whoosh.compat import range
 
 
 def levenshtein_automaton(term, k, prefix=0):

src/whoosh/classify.py

@@ -34,7 +34,7 @@
 from collections import defaultdict
 from math import log
 
-from whoosh.compat import iteritems, range
+from whoosh.compat import iteritems
 
 # Expansion models
 

src/whoosh/codec/base.py

@@ -33,7 +33,7 @@
 
 from whoosh import columns
 from whoosh.automata import lev
-from whoosh.compat import abstractmethod, izip, range, unichr
+from whoosh.compat import abstractmethod, izip, unichr
 from whoosh.filedb.compound import CompoundStorage
 from whoosh.system import emptybytes
 from whoosh.util import random_name

src/whoosh/codec/memory.py

@@ -30,7 +30,6 @@
 from threading import Lock
 
 from whoosh.codec import base
-from whoosh.compat import range
 from whoosh.matching import ListMatcher
 from whoosh.reading import SegmentReader, TermInfo, TermNotFound
 from whoosh.writing import SegmentWriter

src/whoosh/collectors.py

@@ -83,7 +83,7 @@ def collect(self, sub_docnum):
 from heapq import heapify, heappush, heapreplace
 
 from whoosh import sorting
-from whoosh.compat import abstractmethod, iteritems, itervalues, range
+from whoosh.compat import abstractmethod, iteritems, itervalues
 from whoosh.searching import Results, TimeLimit
 from whoosh.util import now
 

src/whoosh/columns.py

@@ -57,7 +57,7 @@
 except ImportError:
     zlib = None
 
-from whoosh.compat import BytesIO, array_tobytes, b, bytes_type, dumps, loads, range
+from whoosh.compat import BytesIO, array_tobytes, b, bytes_type, dumps, loads
 from whoosh.filedb.structfile import StructFile
 from whoosh.idsets import BitSet, OnDiskBitSet
 from whoosh.system import emptybytes

src/whoosh/filedb/filetables.py

@@ -36,7 +36,7 @@
 from binascii import crc32
 from hashlib import md5  # type: ignore @UnresolvedImport
 
-from whoosh.compat import b, bytes_type, range
+from whoosh.compat import b, bytes_type
 from whoosh.system import _INT_SIZE, emptybytes
 from whoosh.util.numlists import GrowableArray
 

src/whoosh/idsets.py

@@ -6,7 +6,7 @@
 from array import array
 from bisect import bisect_left, bisect_right
 
-from whoosh.compat import izip, izip_longest, next, range
+from whoosh.compat import izip, izip_longest, next
 from whoosh.util.numeric import bytes_for_bits
 
 # Number of '1' bits in each byte (0-255)

src/whoosh/lang/morph_en.py

@@ -8,7 +8,7 @@ class of Sun's `Minion search engine <https://minion.dev.java.net/>`_.
 
 import re
 
-from whoosh.compat import iteritems, range
+from whoosh.compat import iteritems
 
 # Rule exceptions
 

src/whoosh/matching/combo.py

@@ -28,7 +28,6 @@
 
 from array import array
 
-from whoosh.compat import range
 from whoosh.matching import mcore
 
 

src/whoosh/multiproc.py

@@ -29,7 +29,7 @@
 from multiprocessing import Process, Queue, cpu_count
 
 from whoosh.codec import base
-from whoosh.compat import pickle, queue, range
+from whoosh.compat import pickle, queue
 from whoosh.externalsort import imerge
 from whoosh.util import random_name
 from whoosh.writing import SegmentWriter

src/whoosh/qparser/plugins.py

@@ -28,7 +28,7 @@
 import copy
 
 from whoosh import query
-from whoosh.compat import iteritems, range, u
+from whoosh.compat import iteritems, u
 from whoosh.qparser import syntax
 from whoosh.qparser.common import attach
 from whoosh.qparser.taggers import FnTagger, RegexTagger

src/whoosh/query/nested.py

@@ -26,7 +26,6 @@
 # policies, either expressed or implied, of Matt Chaput.
 
 from whoosh import matching
-from whoosh.compat import range
 from whoosh.query import qcore
 from whoosh.query.wrappers import WrappingQuery
 

src/whoosh/searching.py

@@ -34,7 +34,7 @@
 from math import ceil
 
 from whoosh import classify, highlight, query, scoring
-from whoosh.compat import iteritems, iterkeys, itervalues, range
+from whoosh.compat import iteritems, iterkeys, itervalues
 from whoosh.idsets import BitSet, DocIdSet
 from whoosh.reading import TermNotFound
 

src/whoosh/sorting.py

@@ -28,7 +28,7 @@
 from array import array
 from collections import defaultdict
 
-from whoosh.compat import iteritems, izip, range, string_type
+from whoosh.compat import iteritems, izip, string_type
 
 # Faceting objects
 

src/whoosh/spelling.py

@@ -33,7 +33,7 @@
 from heapq import heappush, heapreplace
 
 from whoosh import highlight
-from whoosh.compat import iteritems, range
+from whoosh.compat import iteritems
 
 # Corrector objects
 

src/whoosh/support/base85.py

@@ -9,8 +9,6 @@
 
 import struct
 
-from whoosh.compat import range
-
 # Instead of using the character set from the ascii85 algorithm, I put the
 # characters in order so that the encoded text sorts properly (my life would be
 # a lot easier if they had just done that from the start)

src/whoosh/support/levenshtein.py

@@ -2,8 +2,6 @@
 Contains functions implementing edit distance algorithms.
 """
 
-from whoosh.compat import range
-
 
 def levenshtein(seq1, seq2, limit=None):
     """Returns the Levenshtein edit distance between two strings."""

src/whoosh/util/__init__.py

@@ -32,8 +32,6 @@
 from bisect import insort
 from functools import wraps
 
-from whoosh.compat import range
-
 # These must be valid separate characters in CASE-INSENSTIVE filenames
 IDCHARS = "0123456789abcdefghijklmnopqrstuvwxyz"
 

src/whoosh/util/numlists.py

@@ -1,6 +1,5 @@
 from array import array
 
-from whoosh.compat import range
 from whoosh.system import (
     emptybytes,
     pack_byte,

src/whoosh/util/varints.py

@@ -27,7 +27,7 @@
 
 from array import array
 
-from whoosh.compat import array_tobytes, range
+from whoosh.compat import array_tobytes
 
 # Varint cache
 

stress/test_bigindex.py

@@ -1,7 +1,7 @@
 import random
 
 from whoosh import fields
-from whoosh.compat import range, text_type, u
+from whoosh.compat import text_type, u
 from whoosh.util import now
 from whoosh.util.testing import TempIndex
 

stress/test_bigsort.py

@@ -4,7 +4,7 @@
 from datetime import datetime
 
 from whoosh import fields, index, query
-from whoosh.compat import range, text_type
+from whoosh.compat import text_type
 from whoosh.util import now
 
 

stress/test_bigtable.py

@@ -1,7 +1,7 @@
 from random import randint, shuffle
 
 from nose.tools import assert_equal  # type: ignore @UnresolvedImport
-from whoosh.compat import iteritems, range
+from whoosh.compat import iteritems
 from whoosh.filedb.filetables import HashReader, HashWriter
 from whoosh.util.testing import TempStorage