RubyGems - treat - Versions diffs - 1.2.0 → 2.0.0rc1 - Mend

treat 1.2.0 → 2.0.0rc1

Files changed (217) hide show

data/LICENSE +2 -2
data/README.md +12 -21
data/lib/treat/autoload.rb +44 -0
data/lib/treat/config/config.rb +38 -0
data/lib/treat/config/configurable.rb +51 -0
data/lib/treat/config/data/config.rb +50 -0
data/lib/treat/config/data/core.rb +52 -0
data/lib/treat/config/data/databases.rb +10 -0
data/lib/treat/config/data/entities.rb +15 -0
data/lib/treat/config/data/languages/agnostic.rb +31 -0
data/lib/treat/config/{languages → data/languages}/arabic.rb +0 -0
data/lib/treat/config/{languages → data/languages}/chinese.rb +0 -0
data/lib/treat/config/{languages → data/languages}/dutch.rb +1 -1
data/lib/treat/config/data/languages/english.rb +95 -0
data/lib/treat/config/data/languages/french.rb +148 -0
data/lib/treat/config/data/languages/german.rb +135 -0
data/lib/treat/config/{languages → data/languages}/greek.rb +1 -1
data/lib/treat/config/data/languages/italian.rb +162 -0
data/lib/treat/config/data/languages/polish.rb +11 -0
data/lib/treat/config/{languages → data/languages}/portuguese.rb +1 -1
data/lib/treat/config/{languages → data/languages}/russian.rb +1 -1
data/lib/treat/config/data/languages/spanish.rb +291 -0
data/lib/treat/config/data/languages/swedish.rb +289 -0
data/lib/treat/config/data/libraries.rb +12 -0
data/lib/treat/config/data/linguistics.rb +44 -0
data/lib/treat/config/data/tags.rb +328 -0
data/lib/treat/config/{workers → data/workers}/extractors.rb +2 -10
data/lib/treat/config/{workers → data/workers}/formatters.rb +0 -0
data/lib/treat/config/{workers → data/workers}/inflectors.rb +0 -0
data/lib/treat/config/{workers → data/workers}/learners.rb +0 -0
data/lib/treat/config/{workers → data/workers}/lexicalizers.rb +4 -3
data/lib/treat/config/{workers → data/workers}/processors.rb +3 -3
data/lib/treat/config/{workers → data/workers}/retrievers.rb +0 -0
data/lib/treat/config/importable.rb +31 -0
data/lib/treat/config/paths.rb +23 -0
data/lib/treat/config/tags.rb +37 -0
data/lib/treat/core/dsl.rb +55 -0
data/lib/treat/{installer.rb → core/installer.rb} +10 -12
data/lib/treat/core/server.rb +40 -0
data/lib/treat/entities/entities.rb +101 -0
data/lib/treat/entities/{abilities/doable.rb → entity/applicable.rb} +5 -3
data/lib/treat/entities/{abilities → entity}/buildable.rb +118 -63
data/lib/treat/entities/{abilities → entity}/checkable.rb +2 -2
data/lib/treat/entities/{abilities → entity}/comparable.rb +6 -6
data/lib/treat/entities/{abilities → entity}/countable.rb +2 -1
data/lib/treat/entities/entity/debuggable.rb +86 -0
data/lib/treat/entities/{abilities → entity}/delegatable.rb +16 -26
data/lib/treat/entities/{abilities → entity}/exportable.rb +2 -2
data/lib/treat/entities/{abilities → entity}/iterable.rb +4 -16
data/lib/treat/entities/{abilities → entity}/magical.rb +22 -17
data/lib/treat/entities/entity/registrable.rb +36 -0
data/lib/treat/entities/{abilities → entity}/stringable.rb +18 -15
data/lib/treat/entities/entity.rb +86 -77
data/lib/treat/exception.rb +3 -0
data/lib/treat/helpers/hash.rb +29 -0
data/lib/treat/helpers/help.rb +35 -0
data/lib/treat/helpers/object.rb +55 -0
data/lib/treat/helpers/string.rb +124 -0
data/lib/treat/{core → learning}/data_set.rb +11 -11
data/lib/treat/{core → learning}/export.rb +3 -3
data/lib/treat/{core → learning}/problem.rb +26 -16
data/lib/treat/{core → learning}/question.rb +5 -9
data/lib/treat/loaders/linguistics.rb +8 -9
data/lib/treat/loaders/stanford.rb +5 -11
data/lib/treat/modules.rb +33 -0
data/lib/treat/proxies/array.rb +27 -0
data/lib/treat/proxies/language.rb +47 -0
data/lib/treat/proxies/number.rb +18 -0
data/lib/treat/proxies/proxy.rb +25 -0
data/lib/treat/proxies/string.rb +18 -0
data/lib/treat/version.rb +10 -1
data/lib/treat/{workers.rb → workers/categorizable.rb} +18 -19
data/lib/treat/workers/extractors/keywords/tf_idf.rb +11 -11
data/lib/treat/workers/extractors/language/what_language.rb +8 -6
data/lib/treat/workers/extractors/name_tag/stanford.rb +10 -4
data/lib/treat/workers/extractors/similarity/levenshtein.rb +36 -0
data/lib/treat/workers/extractors/similarity/tf_idf.rb +27 -0
data/lib/treat/workers/extractors/tf_idf/native.rb +4 -4
data/lib/treat/workers/extractors/time/chronic.rb +2 -4
data/lib/treat/workers/extractors/time/nickel.rb +19 -20
data/lib/treat/workers/extractors/time/ruby.rb +2 -1
data/lib/treat/workers/extractors/topic_words/lda.rb +12 -12
data/lib/treat/workers/extractors/topics/reuters.rb +9 -13
data/lib/treat/workers/formatters/readers/autoselect.rb +1 -1
data/lib/treat/workers/formatters/readers/image.rb +19 -9
data/lib/treat/workers/formatters/readers/odt.rb +2 -1
data/lib/treat/workers/formatters/readers/pdf.rb +20 -3
data/lib/treat/workers/formatters/readers/xml.rb +0 -1
data/lib/treat/workers/formatters/serializers/mongo.rb +10 -20
data/lib/treat/workers/formatters/serializers/xml.rb +17 -26
data/lib/treat/workers/formatters/serializers/yaml.rb +5 -4
data/lib/treat/workers/formatters/unserializers/mongo.rb +4 -4
data/lib/treat/workers/formatters/unserializers/xml.rb +3 -4
data/lib/treat/workers/formatters/unserializers/yaml.rb +3 -4
data/lib/treat/workers/formatters/visualizers/dot.rb +1 -0
data/lib/treat/workers/formatters/visualizers/standoff.rb +2 -3
data/lib/treat/workers/formatters/visualizers/tree.rb +2 -3
data/lib/treat/workers/{group.rb → groupable.rb} +9 -9
data/lib/treat/workers/inflectors/cardinalizers/linguistics.rb +1 -3
data/lib/treat/workers/inflectors/conjugators/linguistics.rb +5 -7
data/lib/treat/workers/inflectors/declensors/english.rb +13 -20
data/lib/treat/workers/inflectors/declensors/linguistics.rb +29 -28
data/lib/treat/workers/inflectors/ordinalizers/linguistics.rb +0 -2
data/lib/treat/workers/inflectors/stemmers/porter.rb +8 -10
data/lib/treat/workers/inflectors/stemmers/porter_c.rb +7 -7
data/lib/treat/workers/inflectors/stemmers/uea.rb +3 -8
data/lib/treat/workers/learners/classifiers/id3.rb +17 -14
data/lib/treat/workers/learners/classifiers/linear.rb +15 -27
data/lib/treat/workers/learners/classifiers/mlp.rb +32 -19
data/lib/treat/workers/learners/classifiers/svm.rb +28 -21
data/lib/treat/workers/lexicalizers/categorizers/from_tag.rb +19 -3
data/lib/treat/workers/lexicalizers/sensers/wordnet.rb +15 -7
data/lib/treat/workers/lexicalizers/taggers/brill/patch.rb +4 -1
data/lib/treat/workers/lexicalizers/taggers/brill.rb +8 -19
data/lib/treat/workers/lexicalizers/taggers/lingua.rb +4 -15
data/lib/treat/workers/lexicalizers/taggers/stanford.rb +22 -13
data/lib/treat/workers/processors/chunkers/autoselect.rb +2 -3
data/lib/treat/workers/processors/chunkers/html.rb +1 -6
data/lib/treat/workers/processors/parsers/enju.rb +2 -4
data/lib/treat/workers/processors/parsers/stanford.rb +13 -7
data/lib/treat/workers/processors/segmenters/punkt.rb +25 -11
data/lib/treat/workers/processors/segmenters/scalpel.rb +20 -0
data/lib/treat/workers/processors/segmenters/srx.rb +42 -0
data/lib/treat/workers/processors/segmenters/stanford.rb +5 -5
data/lib/treat/workers/processors/segmenters/tactful.rb +21 -11
data/lib/treat/workers/processors/tokenizers/ptb.rb +40 -30
data/lib/treat/workers/processors/tokenizers/punkt.rb +14 -19
data/lib/treat/workers/processors/tokenizers/stanford.rb +38 -22
data/lib/treat/workers/retrievers/indexers/ferret.rb +6 -3
data/lib/treat/workers/retrievers/searchers/ferret.rb +2 -2
data/lib/treat/workers/workers.rb +6 -0
data/lib/treat.rb +18 -32
data/models/MANIFEST +1 -0
data/spec/core/data_set.rb +174 -0
data/spec/core/export.rb +52 -0
data/spec/core/problem.rb +144 -0
data/spec/core/question.rb +52 -0
data/spec/{collection.rb → entities/collection.rb} +20 -35
data/spec/{document.rb → entities/document.rb} +3 -54
data/spec/{entity.rb → entities/entity.rb} +10 -9
data/spec/entities/phrase.rb +33 -0
data/spec/{token.rb → entities/token.rb} +0 -57
data/spec/entities/word.rb +3 -0
data/spec/{zone.rb → entities/zone.rb} +0 -26
data/spec/helper.rb +116 -32
data/spec/sandbox.rb +258 -25
data/spec/treat.rb +26 -34
data/spec/workers/agnostic.rb +137 -0
data/spec/workers/english.rb +194 -0
data/spec/workers/examples/english/economist/hungarys_troubles.txt +46 -0
data/spec/workers/examples/english/economist/saving_the_euro.odt +0 -0
data/spec/{samples → workers/examples/english}/mathematicians/archimedes.abw +0 -0
data/spec/{samples → workers/examples/english}/mathematicians/euler.html +0 -0
data/spec/{samples → workers/examples/english}/mathematicians/gauss.pdf +0 -0
data/spec/{samples → workers/examples/english}/mathematicians/leibniz.txt +0 -0
data/spec/{samples → workers/examples/english}/mathematicians/newton.doc +0 -0
data/spec/workers/examples/english/phrase.xml +5 -0
data/spec/workers/examples/english/test.txt +1 -0
data/spec/workers/language.rb +280 -0
data/spec/workers.rb +28 -0
metadata +122 -105
data/lib/treat/config/core/acronyms.rb +0 -5
data/lib/treat/config/core/encodings.rb +0 -8
data/lib/treat/config/core/entities.rb +0 -2
data/lib/treat/config/core/language.rb +0 -3
data/lib/treat/config/core/paths.rb +0 -8
data/lib/treat/config/core/syntax.rb +0 -1
data/lib/treat/config/core/verbosity.rb +0 -1
data/lib/treat/config/databases/default.rb +0 -1
data/lib/treat/config/databases/mongo.rb +0 -1
data/lib/treat/config/languages/agnostic.rb +0 -34
data/lib/treat/config/languages/english.rb +0 -60
data/lib/treat/config/languages/french.rb +0 -18
data/lib/treat/config/languages/german.rb +0 -18
data/lib/treat/config/languages/italian.rb +0 -12
data/lib/treat/config/languages/polish.rb +0 -12
data/lib/treat/config/languages/spanish.rb +0 -12
data/lib/treat/config/languages/swedish.rb +0 -12
data/lib/treat/config/libraries/punkt.rb +0 -1
data/lib/treat/config/libraries/reuters.rb +0 -1
data/lib/treat/config/libraries/stanford.rb +0 -1
data/lib/treat/config/linguistics/categories.rb +0 -4
data/lib/treat/config/linguistics/punctuation.rb +0 -33
data/lib/treat/config/tags/aligned.rb +0 -221
data/lib/treat/config/tags/enju.rb +0 -71
data/lib/treat/config/tags/paris7.rb +0 -17
data/lib/treat/config/tags/ptb.rb +0 -15
data/lib/treat/config/workers/list.rb +0 -1
data/lib/treat/config.rb +0 -135
data/lib/treat/core.rb +0 -5
data/lib/treat/entities/abilities/copyable.rb +0 -47
data/lib/treat/entities/abilities/debuggable.rb +0 -83
data/lib/treat/entities/abilities/registrable.rb +0 -46
data/lib/treat/entities/collection.rb +0 -40
data/lib/treat/entities/document.rb +0 -10
data/lib/treat/entities/group.rb +0 -18
data/lib/treat/entities/section.rb +0 -13
data/lib/treat/entities/token.rb +0 -47
data/lib/treat/entities/zone.rb +0 -12
data/lib/treat/entities.rb +0 -6
data/lib/treat/helpers/didyoumean.rb +0 -57
data/lib/treat/helpers/escaping.rb +0 -15
data/lib/treat/helpers/formatting.rb +0 -41
data/lib/treat/helpers/objtohash.rb +0 -8
data/lib/treat/helpers/platform.rb +0 -15
data/lib/treat/helpers/reflection.rb +0 -17
data/lib/treat/helpers/temporary.rb +0 -27
data/lib/treat/helpers/verbosity.rb +0 -19
data/lib/treat/helpers.rb +0 -5
data/lib/treat/loaders.rb +0 -10
data/lib/treat/proxies.rb +0 -106
data/lib/treat/workers/formatters/unserializers/autoselect.rb +0 -17
data/lib/treat/workers/inflectors/declensors/active_support.rb +0 -31
data/lib/treat/workers/processors/tokenizers/tactful.rb +0 -68
data/spec/core.rb +0 -441
data/spec/phrase.rb +0 -112
data/spec/word.rb +0 -111

data/lib/treat/config/data/languages/swedish.rb ADDED Viewed

@@ -0,0 +1,289 @@
+{
+  dependencies: [
+    'punkt-segmenter',
+    'tactful_tokenizer'
+  ],
+  workers: {
+    processors: {
+      segmenters: [:punkt],
+      tokenizers: []
+    }
+  },
+  stop_words:
+    [
+      "atminstone",
+      "an",
+      "anda",
+      "aven",
+      "aldrig",
+      "alla",
+      "alls",
+      "allt",
+      "alltid",
+      "allting",
+      "alltsa",
+      "andra",
+      "annan",
+      "annars",
+      "antingen",
+      "att",
+      "bakom",
+      "bland",
+      "blev",
+      "bli",
+      "bliva",
+      "blivit",
+      "bort",
+      "bortom",
+      "bredvid",
+      "dar",
+      "darav",
+      "darefter",
+      "darfor",
+      "dari",
+      "darigenom",
+      "darvid",
+      "dedar",
+      "definitivt",
+      "del",
+      "den",
+      "dendar",
+      "denhar",
+      "denna",
+      "deras",
+      "dessa",
+      "dessutom",
+      "desto",
+      "det",
+      "detta",
+      "dylik",
+      "efterat",
+      "efter",
+      "eftersom",
+      "eller",
+      "emellertid",
+      "enbart",
+      "endast",
+      "enligt",
+      "ens",
+      "ensam",
+      "envar",
+      "eran",
+      "etc",
+      "ett",
+      "exakt",
+      "fatt",
+      "fastan",
+      "fick",
+      "fler",
+      "flera",
+      "foljande",
+      "foljde",
+      "foljer",
+      "for",
+      "fore",
+      "forhoppningsvis",
+      "formodligen",
+      "forr",
+      "forra",
+      "forutom",
+      "forvisso",
+      "fran",
+      "framfor",
+      "fullstandigt",
+      "gang",
+      "gar",
+      "gatt",
+      "ganska",
+      "gav",
+      "genom",
+      "genomgaende",
+      "ger",
+      "gick",
+      "gjorde",
+      "gjort",
+      "gor",
+      "hade",
+      "har",
+      "harav",
+      "har",
+      "hej",
+      "hela",
+      "helst",
+      "helt",
+      "hitta",
+      "hon",
+      "honom",
+      "hur",
+      "huruvida",
+      "huvudsakligen",
+      "ibland",
+      "icke",
+      "ickedestomindre",
+      "igen",
+      "ihop",
+      "inat",
+      "ingen",
+      "ingenstans",
+      "inget",
+      "innan",
+      "innehalla",
+      "inre",
+      "inte",
+      "inuti",
+      "istaellet",
+      "kanske",
+      "klart",
+      "knappast",
+      "knappt",
+      "kom",
+      "komma",
+      "kommer",
+      "kraver",
+      "kunde",
+      "kunna",
+      "lata",
+      "later",
+      "lagga",
+      "langre",
+      "laet",
+      "lagd",
+      "leta",
+      "letar",
+      "manga",
+      "maste",
+      "med",
+      "medan",
+      "medans",
+      "mellan",
+      "mest",
+      "min",
+      "mindre",
+      "minst",
+      "mittemellan",
+      "motsvarande",
+      "mycket",
+      "nagon",
+      "nagongang",
+      "nagonsin",
+      "nagonstans",
+      "nagonting",
+      "nagorlunda",
+      "nagot",
+      "namligen",
+      "nar",
+      "nara",
+      "nasta",
+      "nastan",
+      "nedat",
+      "nedanfor",
+      "nerat",
+      "ner",
+      "nog",
+      "normalt",
+      "nummer",
+      "nuvarande",
+      "nytt",
+      "oavsett",
+      "och",
+      "ocksa",
+      "oppna",
+      "over",
+      "overallt",
+      "ofta",
+      "okej",
+      "olika",
+      "ovanfor",
+      "ratt",
+      "redan",
+      "relativt",
+      "respektive",
+      "rimlig",
+      "rimligen",
+      "rimligt",
+      "salunda",
+      "savida",
+      "saga",
+      "sager",
+      "sakert",
+      "sand",
+      "sarskilt",
+      "satt",
+      "sak",
+      "samma",
+      "samtliga",
+      "sedd",
+      "senare",
+      "senaste",
+      "ser",
+      "sig",
+      "sista",
+      "sjaelv",
+      "ska",
+      "skall",
+      "skickad",
+      "skriva",
+      "skulle",
+      "snabb",
+      "snarare",
+      "snart",
+      "som",
+      "somliga",
+      "speciellt",
+      "stalla",
+      "stallet",
+      "starta",
+      "strax",
+      "stundom",
+      "tackar",
+      "tanka",
+      "taga",
+      "tagen",
+      "tala",
+      "tanke",
+      "tidigare",
+      "tills",
+      "tog",
+      "totalt",
+      "trolig",
+      "troligen",
+      "tvaers",
+      "tvars",
+      "tycka",
+      "tyckte",
+      "tyvarr",
+      "understundom",
+      "upp",
+      "uppenbarligen",
+      "uppenbart",
+      "utan",
+      "utanfor",
+      "uteslutande",
+      "utom",
+      "var",
+      "varan",
+      "vad",
+      "val",
+      "varde",
+      "vanlig",
+      "vanligen",
+      "var",
+      "vare",
+      "varenda",
+      "varfor",
+      "varifran",
+      "varit",
+      "varje",
+      "varken",
+      "vars",
+      "vart",
+      "vem",
+      "verkligen",
+      "vidare",
+      "vilken",
+      "vill",
+      "visar",
+      "visst",
+      "visste"
+    ]
+}

data/lib/treat/config/data/libraries.rb ADDED Viewed

@@ -0,0 +1,12 @@
+{
+  punkt: {
+    model_path: nil
+  },
+  reuters: {
+    model_path: nil
+  },
+  stanford: {
+    jar_path: nil,
+    model_path: nil
+  }
+}

data/lib/treat/config/data/linguistics.rb ADDED Viewed

@@ -0,0 +1,44 @@
+{
+  categories:
+    ['adjective', 'adverb', 'noun',
+    'verb', 'interjection', 'clitic',
+    'coverb', 'conjunction', 'determiner',
+    'particle', 'preposition', 'pronoun',
+    'number', 'symbol', 'punctuation',
+    'complementizer'],
+  punctuation: {
+    punct_to_category: {
+    '.' => 'period',
+    ',' => 'comma',
+    ';' => 'semicolon',
+    ':' => 'colon',
+    '?' => 'interrogation',
+    '!' => 'exclamation',
+    '"' => 'double_quote',
+    "'" => 'single_quote',
+    '$' => 'dollar',
+    '%' => 'percent',
+    '#' => 'hash',
+    '*' => 'asterisk',
+    '&' => 'ampersand',
+    '+' => 'plus',
+    '-' => 'dash',
+    '/' => 'slash',
+    '\\' => 'backslash',
+    '^' => 'caret',
+    '_' => 'underscore',
+    '`' => 'tick',
+    '|' => 'pipe',
+    '~' => 'tilde',
+    '@' => 'at',
+    '[' => 'bracket',
+    ']' => 'bracket',
+    '{' => 'brace',
+    '}' => 'brace',
+    '(' => 'parenthesis',
+    ')' => 'parenthesis',
+    '<' => 'tag',
+    '>' => 'tag'
+  }}
+}