rley 0.8.13 → 0.8.14
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- checksums.yaml +4 -4
- data/.rubocop.yml +10 -1
- data/CHANGELOG.md +3 -0
- data/examples/NLP/engtagger.rb +1 -1
- data/lib/rley/constants.rb +1 -1
- data/lib/rley/rgn/tokenizer.rb +7 -7
- metadata +2 -2
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA256:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: cf803f55dde48af888bfb7e0be524e66b8d2357aa85ae6292cf8c70d7a521273
|
4
|
+
data.tar.gz: f9cf09dffb9939c03b2c301c4669600d6d8f3bcefac20313fd54406456ed800a
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: fa9e22773d7679b615d9119be340aac8ad91890dab9e1fe79c240883cb8059bed11dc48be011649ba068db7c62de23d25f3637acd2c3112b92f057e8319bae9e
|
7
|
+
data.tar.gz: 892e9fdb184f4ab33de790fe998504b8ab9fbacdcd19f1ce389ca39cdddc4c28634742cef281036a67a4e8cdb1b7d301df15a6846386f279eb971def3d083820
|
data/.rubocop.yml
CHANGED
@@ -499,4 +499,13 @@ Style/StringChars:
|
|
499
499
|
Enabled: true
|
500
500
|
|
501
501
|
Style/StringConcatenation:
|
502
|
-
Enabled: true
|
502
|
+
Enabled: true
|
503
|
+
|
504
|
+
#RSpec/ContextWording:
|
505
|
+
# Enabled: false
|
506
|
+
#
|
507
|
+
#RSpec/ExampleLength:
|
508
|
+
# Max: 50
|
509
|
+
#
|
510
|
+
#RSpec/MultipleExpectations:
|
511
|
+
# Max: 15
|
data/CHANGELOG.md
CHANGED
data/examples/NLP/engtagger.rb
CHANGED
@@ -4,7 +4,7 @@ require 'rley'
|
|
4
4
|
require 'engtagger' # Load POS (Part-Of-Speech) tagger EngTagger
|
5
5
|
|
6
6
|
# REGEX to remove XML tags from Engtagger output
|
7
|
-
GET_TAG = /<(.+?)>(.*?)
|
7
|
+
GET_TAG = /<(.+?)>(.*?)<.+?>/
|
8
8
|
|
9
9
|
# Text tokenizer
|
10
10
|
# Taken directly from Engtagger, will ensure uniform indexing while parsing
|
data/lib/rley/constants.rb
CHANGED
data/lib/rley/rgn/tokenizer.rb
CHANGED
@@ -14,12 +14,12 @@ module Rley
|
|
14
14
|
# Delimiters: e.g. parentheses '(', ')'
|
15
15
|
# Separators: e.g. comma
|
16
16
|
class Tokenizer
|
17
|
-
PATT_KEY = /[a-zA-Z_][a-zA-Z_0-9]
|
18
|
-
PATT_INTEGER = /\d
|
19
|
-
PATT_NEWLINE = /(?:\r\n)|\r|\n
|
20
|
-
PATT_STRING_START = /"|'
|
21
|
-
PATT_SYMBOL = /[^?*+,:(){}\s]
|
22
|
-
PATT_WHITESPACE = /[ \t\f]
|
17
|
+
PATT_KEY = /[a-zA-Z_][a-zA-Z_0-9]*:/
|
18
|
+
PATT_INTEGER = /\d+/
|
19
|
+
PATT_NEWLINE = /(?:\r\n)|\r|\n/
|
20
|
+
PATT_STRING_START = /"|'/
|
21
|
+
PATT_SYMBOL = /[^?*+,:(){}\s]+/
|
22
|
+
PATT_WHITESPACE = /[ \t\f]+/
|
23
23
|
|
24
24
|
# @return [StringScanner] Low-level input scanner
|
25
25
|
attr_reader(:scanner)
|
@@ -41,7 +41,7 @@ module Rley
|
|
41
41
|
'?' => 'QUESTION_MARK',
|
42
42
|
'*' => 'STAR',
|
43
43
|
'..' => 'ELLIPSIS'
|
44
|
-
}
|
44
|
+
}
|
45
45
|
|
46
46
|
# Here are all the implemented Rley notation keywords
|
47
47
|
@@keywords = %w[
|
metadata
CHANGED
@@ -1,13 +1,13 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: rley
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.8.
|
4
|
+
version: 0.8.14
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Dimitri Geshef
|
8
8
|
bindir: bin
|
9
9
|
cert_chain: []
|
10
|
-
date: 2025-02-
|
10
|
+
date: 2025-02-26 00:00:00.000000000 Z
|
11
11
|
dependencies:
|
12
12
|
- !ruby/object:Gem::Dependency
|
13
13
|
name: prime
|