engtagger 0.4.2 → 0.4.3
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/.gitignore +0 -3
- data/CHANGELOG.md +16 -0
- data/Gemfile +1 -1
- data/README.md +1 -1
- data/Rakefile +10 -0
- data/lib/engtagger/version.rb +1 -1
- data/lib/engtagger.rb +3 -3
- metadata +4 -6
checksums.yaml
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
---
|
|
2
2
|
SHA256:
|
|
3
|
-
metadata.gz:
|
|
4
|
-
data.tar.gz:
|
|
3
|
+
metadata.gz: 688eb41815586b529212a5451966f0cb2a1f4027c8aeb1c949fb437f1c8e5b4a
|
|
4
|
+
data.tar.gz: 1c7eea0dccc4c52133506220861c3ccce512d84f75df10060419dce5d24dfb8f
|
|
5
5
|
SHA512:
|
|
6
|
-
metadata.gz:
|
|
7
|
-
data.tar.gz:
|
|
6
|
+
metadata.gz: 3e5d673b7dd49cbe468c915e247f7d7e6b13002dc1b67e4e98c4e2d9066165f6cc6e0426d1393ff2711a4fb9df1294e44e9dbfc4c89e2b685b32a49482cd68c6
|
|
7
|
+
data.tar.gz: 609562c6c5cc2ea37762ff27e16a8689d569389eb9bf31af413d702e421a78d47acc8bdf993a1acffdce19631c565ca3452f371936f005e395db7f930933695e
|
data/.gitignore
CHANGED
data/CHANGELOG.md
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
1
|
+
# Changelog
|
|
2
|
+
|
|
3
|
+
## 0.4.3
|
|
4
|
+
|
|
5
|
+
- Fix gem packaging that produced files with owner-only (0600) permissions,
|
|
6
|
+
making the gem unreadable after a `sudo gem install` (#20). File permissions
|
|
7
|
+
are now normalized before packaging.
|
|
8
|
+
- Restore lost debug output in `valid_text` (a remnant of the Perl port left
|
|
9
|
+
the message string in void context).
|
|
10
|
+
- Clarify that the VBG tag covers both gerunds and present participles, as in
|
|
11
|
+
the Penn Treebank tagset (#19).
|
|
12
|
+
- Minor RuboCop cleanups.
|
|
13
|
+
|
|
14
|
+
## 0.4.2 and earlier
|
|
15
|
+
|
|
16
|
+
See the [commit history](https://github.com/yohasebe/engtagger/commits/master).
|
data/Gemfile
CHANGED
data/README.md
CHANGED
|
@@ -104,7 +104,7 @@ The set of POS tags used here is a modified version of the Penn Treebank tagset.
|
|
|
104
104
|
UH Interjection oh, yes, mmm
|
|
105
105
|
VB Verb, infinitive take, live
|
|
106
106
|
VBD Verb, past tense took, lived
|
|
107
|
-
VBG Verb, gerund
|
|
107
|
+
VBG Verb, gerund or present participle taking, living
|
|
108
108
|
VBN Verb, past/passive participle taken, lived
|
|
109
109
|
VBP Verb, base present form take, live
|
|
110
110
|
VBZ Verb, present 3SG -s form takes, lives
|
data/Rakefile
CHANGED
|
@@ -8,3 +8,13 @@ Rake::TestTask.new do |t|
|
|
|
8
8
|
t.test_files = FileList["test/test*.rb"]
|
|
9
9
|
t.verbose = true
|
|
10
10
|
end
|
|
11
|
+
|
|
12
|
+
# Gem packaging preserves on-disk file modes; owner-only permissions here
|
|
13
|
+
# produce gems whose files are unreadable after a sudo install (issue #20).
|
|
14
|
+
task :normalize_permissions do
|
|
15
|
+
`git ls-files -z`.split("\x0").each do |f|
|
|
16
|
+
File.chmod(File.executable?(f) ? 0o755 : 0o644, f)
|
|
17
|
+
end
|
|
18
|
+
end
|
|
19
|
+
|
|
20
|
+
Rake::Task["build"].enhance([:normalize_permissions])
|
data/lib/engtagger/version.rb
CHANGED
data/lib/engtagger.rb
CHANGED
|
@@ -128,7 +128,7 @@ class EngTagger
|
|
|
128
128
|
"UH", "Interjection",
|
|
129
129
|
"VB", "Verb, infinitive",
|
|
130
130
|
"VBD", "Verb, past tense",
|
|
131
|
-
"VBG", "Verb, gerund",
|
|
131
|
+
"VBG", "Verb, gerund or present participle",
|
|
132
132
|
"VBN", "Verb, past/passive participle",
|
|
133
133
|
"VBP", "Verb, base present form",
|
|
134
134
|
"VBZ", "Verb, present 3SG -s form",
|
|
@@ -645,7 +645,7 @@ class EngTagger
|
|
|
645
645
|
def valid_text(text)
|
|
646
646
|
if !text
|
|
647
647
|
# there's nothing to parse
|
|
648
|
-
"method call on uninitialized variable" if @conf[:debug]
|
|
648
|
+
puts "method call on uninitialized variable" if @conf[:debug]
|
|
649
649
|
false
|
|
650
650
|
elsif /\A\s*\z/ =~ text
|
|
651
651
|
# text is an empty string, nothing to parse
|
|
@@ -839,7 +839,7 @@ class EngTagger
|
|
|
839
839
|
when /\w-\w/o # Hyphenated word
|
|
840
840
|
/-([^-]+)\z/ =~ word
|
|
841
841
|
h_suffix = $1
|
|
842
|
-
if h_suffix &&
|
|
842
|
+
if h_suffix && @@lexicon[h_suffix] && @@lexicon[h_suffix]["jj"]
|
|
843
843
|
# last part of this is defined as an adjective
|
|
844
844
|
"-hyp-adj-"
|
|
845
845
|
else
|
metadata
CHANGED
|
@@ -1,14 +1,13 @@
|
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
|
2
2
|
name: engtagger
|
|
3
3
|
version: !ruby/object:Gem::Version
|
|
4
|
-
version: 0.4.
|
|
4
|
+
version: 0.4.3
|
|
5
5
|
platform: ruby
|
|
6
6
|
authors:
|
|
7
7
|
- Yoichiro Hasebe
|
|
8
|
-
autorequire:
|
|
9
8
|
bindir: bin
|
|
10
9
|
cert_chain: []
|
|
11
|
-
date:
|
|
10
|
+
date: 1980-01-02 00:00:00.000000000 Z
|
|
12
11
|
dependencies:
|
|
13
12
|
- !ruby/object:Gem::Dependency
|
|
14
13
|
name: sin_lru_redux
|
|
@@ -37,6 +36,7 @@ files:
|
|
|
37
36
|
- ".rubocop.yml"
|
|
38
37
|
- ".solargraph.yml"
|
|
39
38
|
- ".yardopts"
|
|
39
|
+
- CHANGELOG.md
|
|
40
40
|
- Gemfile
|
|
41
41
|
- LICENSE
|
|
42
42
|
- README.md
|
|
@@ -54,7 +54,6 @@ homepage: http://github.com/yohasebe/engtagger
|
|
|
54
54
|
licenses:
|
|
55
55
|
- GPL
|
|
56
56
|
metadata: {}
|
|
57
|
-
post_install_message:
|
|
58
57
|
rdoc_options: []
|
|
59
58
|
require_paths:
|
|
60
59
|
- lib
|
|
@@ -69,8 +68,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
|
|
|
69
68
|
- !ruby/object:Gem::Version
|
|
70
69
|
version: '0'
|
|
71
70
|
requirements: []
|
|
72
|
-
rubygems_version: 3.
|
|
73
|
-
signing_key:
|
|
71
|
+
rubygems_version: 3.6.9
|
|
74
72
|
specification_version: 4
|
|
75
73
|
summary: A probability based, corpus-trained English POS tagger
|
|
76
74
|
test_files: []
|