pragmatic_segmenter 0.1.1 → 0.1.2
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/README.md +4 -0
- data/lib/pragmatic_segmenter/abbreviation.rb +1 -1
- data/lib/pragmatic_segmenter/abbreviation_replacer.rb +1 -1
- data/lib/pragmatic_segmenter/cleaner.rb +4 -1
- data/lib/pragmatic_segmenter/languages/spanish.rb +2 -2
- data/lib/pragmatic_segmenter/version.rb +1 -1
- data/spec/pragmatic_segmenter_spec.rb +5 -0
- metadata +2 -2
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA1:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 1cf05fd20f9672f1186e1c4f857f6045d2fcf4b8
|
4
|
+
data.tar.gz: f8c2685f66e2a177f18683bae290dfc892c8b67f
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: b45bc699fa3cb055c54a028f87c803889ac3889ba454534abf794c9fc5cce36983172898955723c0c4b05ec040320e0126fa36fdf565897ca358aa0d34b1db8f
|
7
|
+
data.tar.gz: 65384a1dd4e0b43a03925447e7dbf4ce7c8fe1f4c58ee86c3b660f1a33e3783a1cc9c73235ff600b4c32c140a15a54955eb55a117e83ddf4b0d4064a2616e533
|
data/README.md
CHANGED
@@ -750,6 +750,10 @@ To test the relative performance of different segmentation tools and libraries I
|
|
750
750
|
**Version 0.1.1**
|
751
751
|
* Fix handling of German dates
|
752
752
|
|
753
|
+
**Version 0.1.2**
|
754
|
+
* Fix missing abbreviations
|
755
|
+
* Add footnote rule to `cleaner.rb`
|
756
|
+
|
753
757
|
## Contributing
|
754
758
|
|
755
759
|
If you find a text that is incorrectly segmented using this gem, please submit an issue.
|
@@ -4,7 +4,7 @@ module PragmaticSegmenter
|
|
4
4
|
# Defines the abbreviations for each language (if available)
|
5
5
|
class Abbreviation
|
6
6
|
ABBREVIATIONS = ['adj', 'adm', 'adv', 'al', 'ala', 'alta', 'apr', 'arc', 'ariz', 'ark', 'art', 'assn', 'asst', 'attys', 'aug', 'ave', 'bart', 'bld', 'bldg', 'blvd', 'brig', 'bros', 'cal', 'calif', 'capt', 'cl', 'cmdr', 'co', 'col', 'colo', 'comdr', 'con', 'conn', 'corp', 'cpl', 'cres', 'ct', 'd.phil', 'dak', 'dec', 'del', 'dept', 'det', 'dist', 'dr', 'dr.phil', 'dr.philos', 'drs', 'e.g', 'ens', 'esp', 'esq', 'etc', 'exp', 'expy', 'ext', 'feb', 'fed', 'fla', 'ft', 'fwy', 'fy', 'ga', 'gen', 'gov', 'hon', 'hosp', 'hr', 'hway', 'hwy', 'i.e', 'ia', 'id', 'ida', 'ill', 'inc', 'ind', 'ing', 'insp', 'is', 'jan', 'jr', 'jul', 'jun', 'kan', 'kans', 'ken', 'ky', 'la', 'lt', 'ltd', 'maj', 'man', 'mar', 'mass', 'may', 'md', 'me', 'messrs', 'mex', 'mfg', 'mich', 'min', 'minn', 'miss', 'mlle', 'mm', 'mme', 'mo', 'mont', 'mr', 'mrs', 'ms', 'msgr', 'mssrs', 'mt', 'mtn', 'neb', 'nebr', 'nev', 'no', 'nos', 'nov', 'nr', 'oct', 'ok', 'okla', 'ont', 'op', 'ord', 'ore', 'p', 'pa', 'pd', 'pde', 'penn', 'penna', 'pfc', 'ph', 'ph.d', 'pl', 'plz', 'pp', 'prof', 'pvt', 'que', 'rd', 'ref', 'rep', 'reps', 'res', 'rev', 'rt', 'sask', 'sen', 'sens', 'sep', 'sept', 'sfc', 'sgt', 'sr', 'st', 'supt', 'surg', 'tce', 'tenn', 'tex', 'univ', 'usafa', 'u.s', 'ut', 'va', 'v', 'ver', 'vs', 'vt', 'wash', 'wis', 'wisc', 'wy', 'wyo', 'yuk']
|
7
|
-
PREPOSITIVE_ABBREVIATIONS = ['adm', 'attys', 'brig', 'capt', 'cmdr', 'col', 'cpl', 'det', 'dr', 'gen', 'gov', 'ing', 'lt', 'maj', 'mr', 'mrs', 'ms', 'mt', 'messrs', 'mssrs', 'prof', 'rep', 'reps', 'rev', 'sen', 'sens', 'sgt', 'st', 'supt', 'v', 'vs']
|
7
|
+
PREPOSITIVE_ABBREVIATIONS = ['adm', 'attys', 'brig', 'capt', 'cmdr', 'col', 'cpl', 'det', 'dr', 'gen', 'gov', 'ing', 'lt', 'maj', 'mr', 'mrs', 'ms', 'mt', 'messrs', 'mssrs', 'prof', 'ph', 'rep', 'reps', 'rev', 'sen', 'sens', 'sgt', 'st', 'supt', 'v', 'vs']
|
8
8
|
NUMBER_ABBREVIATIONS = ['art', 'ext', 'no', 'nos', 'p', 'pp']
|
9
9
|
|
10
10
|
def all
|
@@ -145,7 +145,7 @@ module PragmaticSegmenter
|
|
145
145
|
|
146
146
|
def replace_period_of_abbr(txt, abbr)
|
147
147
|
txt.gsub(/(?<=#{abbr.strip})\.(?=((\.|:|\?)|(\s([a-z]|I\s|I'm|I'll|\d))))/, '∯')
|
148
|
-
|
148
|
+
.gsub(/(?<=#{abbr.strip})\.(?=,)/, '∯')
|
149
149
|
end
|
150
150
|
|
151
151
|
def replace_possessive_abbreviations(txt)
|
@@ -61,6 +61,9 @@ module PragmaticSegmenter
|
|
61
61
|
# Rubular: http://rubular.com/r/IQ4TPfsbd8
|
62
62
|
ConsecutiveForwardSlashRule = Rule.new(/\/{3}/, '')
|
63
63
|
|
64
|
+
# Rubular: http://rubular.com/r/gEjxQ0HmSD
|
65
|
+
FootnoteRule = Rule.new(/\[\?\]/, '[&ᓷ&]')
|
66
|
+
|
64
67
|
# Rubular: http://rubular.com/r/6dt98uI76u
|
65
68
|
NoSpaceBetweenSentencesRule = Rule.new(NO_SPACE_BETWEEN_SENTENCES_REGEX, '. ')
|
66
69
|
|
@@ -105,7 +108,7 @@ module PragmaticSegmenter
|
|
105
108
|
replace_newlines(@clean_text)
|
106
109
|
replace_escaped_newlines(@clean_text)
|
107
110
|
@clean_text.apply(HtmlRules::All)
|
108
|
-
@clean_text.apply(InlineFormattingRule)
|
111
|
+
@clean_text.apply(InlineFormattingRule, FootnoteRule)
|
109
112
|
clean_quotations(@clean_text)
|
110
113
|
clean_table_of_contents(@clean_text)
|
111
114
|
check_for_no_space_in_between_sentences(@clean_text)
|
@@ -18,8 +18,8 @@ module PragmaticSegmenter
|
|
18
18
|
end
|
19
19
|
|
20
20
|
class Abbreviation < PragmaticSegmenter::Abbreviation
|
21
|
-
ABBREVIATIONS = ['a.c', 'a/c', 'abr', 'adj', 'admón', 'afmo', 'ago', 'almte', 'ap', 'apdo', 'arq', 'art', 'atte', 'av', 'avda', 'bco', 'bibl', 'bs. as', 'c', 'c.f', 'c.g', 'c/c', 'c/u', 'cap', 'cc.aa', 'cdad', 'cm', 'co', 'cra', 'cta', 'cv', 'd.e.p', 'da', 'dcha', 'dcho', 'dep', 'dic', 'dicc', 'dir', 'dn', 'doc', 'dom', 'dpto', 'dr', 'dra', 'dto', 'ee', 'ej', 'en', 'entlo', 'esq', 'etc', 'excmo', 'ext', 'f.c', 'fca', 'fdo', 'febr', 'ff. aa', 'ff.cc', 'fig', 'fil', 'fra', 'g.p', 'g/p', 'gob', 'gr', 'gral', 'grs', 'hnos', 'hs', 'igl', 'iltre', 'imp', 'impr', 'impto', 'incl', 'ing', 'inst', 'izdo', 'izq', 'izqdo', 'j.c', 'jue', 'jul', 'jun', 'kg', 'km', 'lcdo', 'ldo', 'let', 'lic', 'ltd', 'lun', 'mar', 'may', 'mg', 'min', 'mié', 'mm', 'máx', 'mín', 'mt', 'n. del t', 'n.b', 'no', 'nov', 'ntra. sra', 'núm', 'oct', 'p', 'p.a', 'p.d', 'p.ej', 'p.v.p', 'párrf', 'ppal', 'prev', 'prof', 'prov', 'ptas', 'pts', 'pza', 'pág', 'págs', 'párr', 'q.e.g.e', 'q.e.p.d', 'q.e.s.m', 'reg', 'rep', 'rr. hh', 'rte', 's', 's. a', 's.a.r', 's.e', 's.l', 's.r.c', 's.r.l', 's.s.s', 's/n', 'sdad', 'seg', 'sept', 'sig', 'sr', 'sra', 'sres', 'srta', 'sta', 'sto', 'sáb', 't.v.e', 'tamb', 'tel', 'tfno', 'ud', 'uu', 'uds', 'univ', 'v.b', 'v.e', 'vd', 'vds', 'vid', 'vie', 'vol', 'vs', 'vto', 'a', 'aero', 'ambi', 'an', 'anfi', 'ante', 'anti', 'archi', 'arci', 'auto', 'bi', 'bien', 'bis', 'co', 'com', 'con', 'contra', 'crio', 'cuadri', 'cuasi', 'cuatri', 'de', 'deci', 'des', 'di', 'dis', 'dr', 'ecto', 'en', 'endo', 'entre', 'epi', 'equi', 'ex', 'extra', 'geo', 'hemi', 'hetero', 'hiper', 'hipo', 'homo', 'i', 'im', 'in', 'infra', 'inter', 'intra', 'iso', 'lic', 'macro', 'mega', 'micro', 'mini', 'mono', 'multi', 'neo', 'omni', 'para', 'pen', 'pluri', 'poli', 'pos', 'post', 'pre', 'pro', 'pseudo', 're', 'retro', 'semi', 'seudo', 'sobre', 'sub', 'super', 'supra', 'trans', 'tras', 'tri', 'ulter', 'ultra', 'un', 'uni', 'vice', 'yuxta']
|
22
|
-
PREPOSITIVE_ABBREVIATIONS = ['a', 'aero', 'ambi', 'an', 'anfi', 'ante', 'anti', 'archi', 'arci', 'auto', 'bi', 'bien', 'bis', 'co', 'com', 'con', 'contra', 'crio', 'cuadri', 'cuasi', 'cuatri', 'de', 'deci', 'des', 'di', 'dis', 'dr', 'ecto', 'ee', 'en', 'endo', 'entre', 'epi', 'equi', 'ex', 'extra', 'geo', 'hemi', 'hetero', 'hiper', 'hipo', 'homo', 'i', 'im', 'in', 'infra', 'inter', 'intra', 'iso', 'lic', 'macro', 'mega', 'micro', 'mini', 'mono', 'mt', 'multi', 'neo', 'omni', 'para', 'pen', 'pluri', 'poli', 'pos', 'post', 'pre', 'pro', 'pseudo', 're', 'retro', 'semi', 'seudo', 'sobre', 'sub', 'super', 'supra', 'srta', 'trans', 'tras', 'tri', 'ulter', 'ultra', 'un', 'uni', 'vice', 'yuxta']
|
21
|
+
ABBREVIATIONS = ['a.c', 'a/c', 'abr', 'adj', 'admón', 'afmo', 'ago', 'almte', 'ap', 'apdo', 'arq', 'art', 'atte', 'av', 'avda', 'bco', 'bibl', 'bs. as', 'c', 'c.f', 'c.g', 'c/c', 'c/u', 'cap', 'cc.aa', 'cdad', 'cm', 'co', 'cra', 'cta', 'cv', 'd.e.p', 'da', 'dcha', 'dcho', 'dep', 'dic', 'dicc', 'dir', 'dn', 'doc', 'dom', 'dpto', 'dr', 'dra', 'dto', 'ee', 'ej', 'en', 'entlo', 'esq', 'etc', 'excmo', 'ext', 'f.c', 'fca', 'fdo', 'febr', 'ff. aa', 'ff.cc', 'fig', 'fil', 'fra', 'g.p', 'g/p', 'gob', 'gr', 'gral', 'grs', 'hnos', 'hs', 'igl', 'iltre', 'imp', 'impr', 'impto', 'incl', 'ing', 'inst', 'izdo', 'izq', 'izqdo', 'j.c', 'jue', 'jul', 'jun', 'kg', 'km', 'lcdo', 'ldo', 'let', 'lic', 'ltd', 'lun', 'mar', 'may', 'mg', 'min', 'mié', 'mm', 'máx', 'mín', 'mt', 'n. del t', 'n.b', 'no', 'nov', 'ntra. sra', 'núm', 'oct', 'p', 'p.a', 'p.d', 'p.ej', 'p.v.p', 'párrf', 'ppal', 'prev', 'prof', 'prov', 'ptas', 'pts', 'pza', 'pág', 'págs', 'párr', 'q.e.g.e', 'q.e.p.d', 'q.e.s.m', 'reg', 'rep', 'rr. hh', 'rte', 's', 's. a', 's.a.r', 's.e', 's.l', 's.r.c', 's.r.l', 's.s.s', 's/n', 'sdad', 'seg', 'sept', 'sig', 'sr', 'sra', 'sres', 'srta', 'sta', 'sto', 'sáb', 't.v.e', 'tamb', 'tel', 'tfno', 'ud', 'uu', 'uds', 'univ', 'v.b', 'v.e', 'vd', 'vds', 'vid', 'vie', 'vol', 'vs', 'vto', 'a', 'aero', 'ambi', 'an', 'anfi', 'ante', 'anti', 'archi', 'arci', 'auto', 'bi', 'bien', 'bis', 'co', 'com', 'con', 'contra', 'crio', 'cuadri', 'cuasi', 'cuatri', 'de', 'deci', 'des', 'di', 'dis', 'dr', 'ecto', 'en', 'endo', 'entre', 'epi', 'equi', 'ex', 'extra', 'geo', 'hemi', 'hetero', 'hiper', 'hipo', 'homo', 'i', 'im', 'in', 'infra', 'inter', 'intra', 'iso', 'lic', 'macro', 'mega', 'micro', 'mini', 'mono', 'multi', 'neo', 'omni', 'para', 'pen', 'ph', 'ph.d', 'pluri', 'poli', 'pos', 'post', 'pre', 'pro', 'pseudo', 're', 'retro', 'semi', 'seudo', 'sobre', 'sub', 'super', 'supra', 'trans', 'tras', 'tri', 'ulter', 'ultra', 'un', 'uni', 'vice', 'yuxta']
|
22
|
+
PREPOSITIVE_ABBREVIATIONS = ['a', 'aero', 'ambi', 'an', 'anfi', 'ante', 'anti', 'archi', 'arci', 'auto', 'bi', 'bien', 'bis', 'co', 'com', 'con', 'contra', 'crio', 'cuadri', 'cuasi', 'cuatri', 'de', 'deci', 'des', 'di', 'dis', 'dr', 'ecto', 'ee', 'en', 'endo', 'entre', 'epi', 'equi', 'ex', 'extra', 'geo', 'hemi', 'hetero', 'hiper', 'hipo', 'homo', 'i', 'im', 'in', 'infra', 'inter', 'intra', 'iso', 'lic', 'macro', 'mega', 'micro', 'mini', 'mono', 'mt', 'multi', 'neo', 'omni', 'para', 'pen', 'ph', 'pluri', 'poli', 'pos', 'post', 'pre', 'pro', 'prof', 'pseudo', 're', 'retro', 'semi', 'seudo', 'sobre', 'sub', 'super', 'supra', 'srta', 'trans', 'tras', 'tri', 'ulter', 'ultra', 'un', 'uni', 'vice', 'yuxta']
|
23
23
|
NUMBER_ABBREVIATIONS = ['cra', 'ext', 'no', 'nos', 'p', 'pp', 'tel']
|
24
24
|
|
25
25
|
def all
|
@@ -918,6 +918,11 @@ RSpec.describe PragmaticSegmenter::Segmenter do
|
|
918
918
|
ps = PragmaticSegmenter::Segmenter.new(text: "The GmbH & Co. KG is a limited partnership with, typically, the sole general partner being a limited liability company.")
|
919
919
|
expect(ps.segment).to eq(["The GmbH & Co. KG is a limited partnership with, typically, the sole general partner being a limited liability company."])
|
920
920
|
end
|
921
|
+
|
922
|
+
it "correctly segments text #090" do
|
923
|
+
ps = PragmaticSegmenter::Segmenter.new(text: "[?][footnoteRef:6] This is a footnote.")
|
924
|
+
expect(ps.segment).to eq(["[?][footnoteRef:6] This is a footnote."])
|
925
|
+
end
|
921
926
|
end
|
922
927
|
end
|
923
928
|
|
metadata
CHANGED
@@ -1,14 +1,14 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: pragmatic_segmenter
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.1.
|
4
|
+
version: 0.1.2
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Kevin S. Dias
|
8
8
|
autorequire:
|
9
9
|
bindir: bin
|
10
10
|
cert_chain: []
|
11
|
-
date: 2015-01-
|
11
|
+
date: 2015-01-13 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: bundler
|