xapian-fu 1.7.0 → 1.8.0

data/lib/xapian_fu/stopwords/zu.txt

@@ -0,0 +1,29 @@
+futhi
+kahle
+kakhulu
+kanye
+khona
+kodwa
+kungani
+kusho
+la
+lakhe
+lapho
+mina
+ngesikhathi
+nje
+phansi
+phezulu
+u
+ukuba
+ukuthi
+ukuze
+uma
+wahamba
+wakhe
+wami
+wase
+wathi
+yakhe
+zakhe
+zonke

data/lib/xapian_fu/version.rb

@@ -1,3 +1,3 @@
 module XapianFu #:nodoc:
-  VERSION = "1.7.0"
+  VERSION = "1.8.0"
 end

data/lib/xapian_fu/xapian_db.rb

@@ -58,6 +58,9 @@ module XapianFu #:nodoc:
   # :portuguese, :romanian, :russian, :spanish, :swedish,
   # :turkish</tt>.  Set it to <tt>false</tt> to specify none.
   #
+  # There are more stoppers available than stemmers. See
+  # <tt>lib/xapian_fu/stopwords/*.txt</tt> for a complete list.
+  #
   # The default for all is <tt>:english</tt>.
   #
   #   db = XapianDb.new(:language => :italian, :stopper => false)

data/spec/xapian_doc_spec.rb

@@ -203,7 +203,7 @@ describe XapianDoc do
     it "should allow setting the stopper on initialisation" do
       xdb = XapianDb.new(:stopper => :english)
       xdoc = xdb.documents.new("And they made a cake", :stopper => :french)
-      xdoc.stopper.call("ayantes").should == true
+      xdoc.stopper.call("apres").should == true
       xdoc.stopper.call("and").should == false
     end
 

metadata

@@ -1,15 +1,15 @@
 --- !ruby/object:Gem::Specification
 name: xapian-fu
 version: !ruby/object:Gem::Version
-  version: 1.7.0
+  version: 1.8.0
 platform: ruby
 authors:
 - John Leach
 - Damian Janowski
-autorequire: 
+autorequire:
 bindir: bin
 cert_chain: []
-date: 2020-03-23 00:00:00.000000000 Z
+date: 2025-10-19 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rspec
@@ -17,14 +17,14 @@ dependencies:
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '2.7'
+        version: 2.7.0
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '2.7'
+        version: 2.7.0
 - !ruby/object:Gem::Dependency
   name: rake
   requirement: !ruby/object:Gem::Requirement
@@ -90,20 +90,78 @@ files:
 - lib/xapian_fu/result_set.rb
 - lib/xapian_fu/stopper_factory.rb
 - lib/xapian_fu/stopwords/README
+- lib/xapian_fu/stopwords/af.txt
+- lib/xapian_fu/stopwords/ar.txt
+- lib/xapian_fu/stopwords/bg.txt
+- lib/xapian_fu/stopwords/bn.txt
+- lib/xapian_fu/stopwords/br.txt
+- lib/xapian_fu/stopwords/ca.txt
+- lib/xapian_fu/stopwords/cs.txt
+- lib/xapian_fu/stopwords/da.txt
 - lib/xapian_fu/stopwords/danish.txt
+- lib/xapian_fu/stopwords/de.txt
 - lib/xapian_fu/stopwords/dutch.txt
+- lib/xapian_fu/stopwords/el.txt
+- lib/xapian_fu/stopwords/en.txt
 - lib/xapian_fu/stopwords/english.txt
+- lib/xapian_fu/stopwords/eo.txt
+- lib/xapian_fu/stopwords/es.txt
+- lib/xapian_fu/stopwords/et.txt
+- lib/xapian_fu/stopwords/eu.txt
+- lib/xapian_fu/stopwords/fa.txt
+- lib/xapian_fu/stopwords/fi.txt
 - lib/xapian_fu/stopwords/finnish.txt
+- lib/xapian_fu/stopwords/fr.txt
 - lib/xapian_fu/stopwords/french.txt
+- lib/xapian_fu/stopwords/ga.txt
 - lib/xapian_fu/stopwords/german.txt
+- lib/xapian_fu/stopwords/gl.txt
+- lib/xapian_fu/stopwords/gu.txt
+- lib/xapian_fu/stopwords/ha.txt
+- lib/xapian_fu/stopwords/he.txt
+- lib/xapian_fu/stopwords/hi.txt
+- lib/xapian_fu/stopwords/hr.txt
+- lib/xapian_fu/stopwords/hu.txt
 - lib/xapian_fu/stopwords/hungarian.txt
+- lib/xapian_fu/stopwords/hy.txt
+- lib/xapian_fu/stopwords/id.txt
+- lib/xapian_fu/stopwords/it.txt
 - lib/xapian_fu/stopwords/italian.txt
+- lib/xapian_fu/stopwords/ja.txt
+- lib/xapian_fu/stopwords/ko.txt
+- lib/xapian_fu/stopwords/ku.txt
+- lib/xapian_fu/stopwords/la.txt
+- lib/xapian_fu/stopwords/lt.txt
+- lib/xapian_fu/stopwords/lv.txt
+- lib/xapian_fu/stopwords/mr.txt
+- lib/xapian_fu/stopwords/ms.txt
+- lib/xapian_fu/stopwords/nl.txt
+- lib/xapian_fu/stopwords/no.txt
 - lib/xapian_fu/stopwords/norwegian.txt
+- lib/xapian_fu/stopwords/pl.txt
 - lib/xapian_fu/stopwords/portuguese.txt
+- lib/xapian_fu/stopwords/pt.txt
+- lib/xapian_fu/stopwords/ro.txt
+- lib/xapian_fu/stopwords/ru.txt
 - lib/xapian_fu/stopwords/russian.txt
+- lib/xapian_fu/stopwords/sk.txt
+- lib/xapian_fu/stopwords/sl.txt
+- lib/xapian_fu/stopwords/so.txt
 - lib/xapian_fu/stopwords/spanish.txt
+- lib/xapian_fu/stopwords/st.txt
+- lib/xapian_fu/stopwords/sv.txt
+- lib/xapian_fu/stopwords/sw.txt
 - lib/xapian_fu/stopwords/swedish.txt
+- lib/xapian_fu/stopwords/th.txt
+- lib/xapian_fu/stopwords/tl.txt
+- lib/xapian_fu/stopwords/tr.txt
+- lib/xapian_fu/stopwords/uk.txt
 - lib/xapian_fu/stopwords/update.rb
+- lib/xapian_fu/stopwords/ur.txt
+- lib/xapian_fu/stopwords/vi.txt
+- lib/xapian_fu/stopwords/yo.txt
+- lib/xapian_fu/stopwords/zh.txt
+- lib/xapian_fu/stopwords/zu.txt
 - lib/xapian_fu/version.rb
 - lib/xapian_fu/xapian_db.rb
 - lib/xapian_fu/xapian_doc.rb
@@ -172,7 +230,7 @@ homepage: https://github.com/johnl/xapian-fu
 licenses:
 - MIT
 metadata: {}
-post_install_message: 
+post_install_message:
 rdoc_options:
 - "--title"
 - Xapian Fu
@@ -193,67 +251,67 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
 requirements:
 - libxapian-dev, or the xapian-ruby gem
-rubygems_version: 3.1.2
-signing_key: 
+rubygems_version: 3.3.26
+signing_key:
 specification_version: 4
 summary: A Ruby interface to the Xapian search engine
 test_files:
-- spec/xapian_db_spec.rb
-- spec/fixtures/film_data.rb
-- spec/fixtures/film_data/x86_64-linux-gnu~2.5.5/position.baseA
+- spec/build_db_for_value_testing.rb
+- spec/facets_spec.rb
 - spec/fixtures/film_data/x86_64-linux-gnu~2.5.5/flintlock
-- spec/fixtures/film_data/x86_64-linux-gnu~2.5.5/spelling.baseB
-- spec/fixtures/film_data/x86_64-linux-gnu~2.5.5/record.baseB
-- spec/fixtures/film_data/x86_64-linux-gnu~2.5.5/postlist.baseB
-- spec/fixtures/film_data/x86_64-linux-gnu~2.5.5/spelling.baseA
-- spec/fixtures/film_data/x86_64-linux-gnu~2.5.5/position.DB
-- spec/fixtures/film_data/x86_64-linux-gnu~2.5.5/postlist.baseA
 - spec/fixtures/film_data/x86_64-linux-gnu~2.5.5/iamchert
-- spec/fixtures/film_data/x86_64-linux-gnu~2.5.5/postlist.DB
+- spec/fixtures/film_data/x86_64-linux-gnu~2.5.5/position.DB
+- spec/fixtures/film_data/x86_64-linux-gnu~2.5.5/position.baseA
 - spec/fixtures/film_data/x86_64-linux-gnu~2.5.5/position.baseB
-- spec/fixtures/film_data/x86_64-linux-gnu~2.5.5/termlist.DB
-- spec/fixtures/film_data/x86_64-linux-gnu~2.5.5/termlist.baseB
-- spec/fixtures/film_data/x86_64-linux-gnu~2.5.5/spelling.DB
+- spec/fixtures/film_data/x86_64-linux-gnu~2.5.5/postlist.DB
+- spec/fixtures/film_data/x86_64-linux-gnu~2.5.5/postlist.baseA
+- spec/fixtures/film_data/x86_64-linux-gnu~2.5.5/postlist.baseB
 - spec/fixtures/film_data/x86_64-linux-gnu~2.5.5/record.DB
 - spec/fixtures/film_data/x86_64-linux-gnu~2.5.5/record.baseA
+- spec/fixtures/film_data/x86_64-linux-gnu~2.5.5/record.baseB
+- spec/fixtures/film_data/x86_64-linux-gnu~2.5.5/spelling.DB
+- spec/fixtures/film_data/x86_64-linux-gnu~2.5.5/spelling.baseA
+- spec/fixtures/film_data/x86_64-linux-gnu~2.5.5/spelling.baseB
+- spec/fixtures/film_data/x86_64-linux-gnu~2.5.5/termlist.DB
 - spec/fixtures/film_data/x86_64-linux-gnu~2.5.5/termlist.baseA
-- spec/fixtures/film_data/x86_64-linux~1.9.3/position.baseA
-- spec/fixtures/film_data/x86_64-linux~1.9.3/flintlock
-- spec/fixtures/film_data/x86_64-linux~1.9.3/spelling.baseB
-- spec/fixtures/film_data/x86_64-linux~1.9.3/record.baseB
-- spec/fixtures/film_data/x86_64-linux~1.9.3/postlist.baseB
-- spec/fixtures/film_data/x86_64-linux~1.9.3/spelling.baseA
-- spec/fixtures/film_data/x86_64-linux~1.9.3/position.DB
-- spec/fixtures/film_data/x86_64-linux~1.9.3/postlist.baseA
-- spec/fixtures/film_data/x86_64-linux~1.9.3/iamchert
-- spec/fixtures/film_data/x86_64-linux~1.9.3/postlist.DB
-- spec/fixtures/film_data/x86_64-linux~1.9.3/position.baseB
-- spec/fixtures/film_data/x86_64-linux~1.9.3/termlist.DB
-- spec/fixtures/film_data/x86_64-linux~1.9.3/termlist.baseB
-- spec/fixtures/film_data/x86_64-linux~1.9.3/spelling.DB
-- spec/fixtures/film_data/x86_64-linux~1.9.3/record.DB
-- spec/fixtures/film_data/x86_64-linux~1.9.3/record.baseA
-- spec/fixtures/film_data/x86_64-linux~1.9.3/termlist.baseA
-- spec/fixtures/film_data/x86_64-linux~1.8.7/position.baseA
+- spec/fixtures/film_data/x86_64-linux-gnu~2.5.5/termlist.baseB
 - spec/fixtures/film_data/x86_64-linux~1.8.7/flintlock
-- spec/fixtures/film_data/x86_64-linux~1.8.7/spelling.baseB
-- spec/fixtures/film_data/x86_64-linux~1.8.7/record.baseB
-- spec/fixtures/film_data/x86_64-linux~1.8.7/postlist.baseB
-- spec/fixtures/film_data/x86_64-linux~1.8.7/spelling.baseA
-- spec/fixtures/film_data/x86_64-linux~1.8.7/position.DB
-- spec/fixtures/film_data/x86_64-linux~1.8.7/postlist.baseA
 - spec/fixtures/film_data/x86_64-linux~1.8.7/iamchert
-- spec/fixtures/film_data/x86_64-linux~1.8.7/postlist.DB
+- spec/fixtures/film_data/x86_64-linux~1.8.7/position.DB
+- spec/fixtures/film_data/x86_64-linux~1.8.7/position.baseA
 - spec/fixtures/film_data/x86_64-linux~1.8.7/position.baseB
-- spec/fixtures/film_data/x86_64-linux~1.8.7/termlist.DB
-- spec/fixtures/film_data/x86_64-linux~1.8.7/termlist.baseB
-- spec/fixtures/film_data/x86_64-linux~1.8.7/spelling.DB
+- spec/fixtures/film_data/x86_64-linux~1.8.7/postlist.DB
+- spec/fixtures/film_data/x86_64-linux~1.8.7/postlist.baseA
+- spec/fixtures/film_data/x86_64-linux~1.8.7/postlist.baseB
 - spec/fixtures/film_data/x86_64-linux~1.8.7/record.DB
 - spec/fixtures/film_data/x86_64-linux~1.8.7/record.baseA
+- spec/fixtures/film_data/x86_64-linux~1.8.7/record.baseB
+- spec/fixtures/film_data/x86_64-linux~1.8.7/spelling.DB
+- spec/fixtures/film_data/x86_64-linux~1.8.7/spelling.baseA
+- spec/fixtures/film_data/x86_64-linux~1.8.7/spelling.baseB
+- spec/fixtures/film_data/x86_64-linux~1.8.7/termlist.DB
 - spec/fixtures/film_data/x86_64-linux~1.8.7/termlist.baseA
+- spec/fixtures/film_data/x86_64-linux~1.8.7/termlist.baseB
+- spec/fixtures/film_data/x86_64-linux~1.9.3/flintlock
+- spec/fixtures/film_data/x86_64-linux~1.9.3/iamchert
+- spec/fixtures/film_data/x86_64-linux~1.9.3/position.DB
+- spec/fixtures/film_data/x86_64-linux~1.9.3/position.baseA
+- spec/fixtures/film_data/x86_64-linux~1.9.3/position.baseB
+- spec/fixtures/film_data/x86_64-linux~1.9.3/postlist.DB
+- spec/fixtures/film_data/x86_64-linux~1.9.3/postlist.baseA
+- spec/fixtures/film_data/x86_64-linux~1.9.3/postlist.baseB
+- spec/fixtures/film_data/x86_64-linux~1.9.3/record.DB
+- spec/fixtures/film_data/x86_64-linux~1.9.3/record.baseA
+- spec/fixtures/film_data/x86_64-linux~1.9.3/record.baseB
+- spec/fixtures/film_data/x86_64-linux~1.9.3/spelling.DB
+- spec/fixtures/film_data/x86_64-linux~1.9.3/spelling.baseA
+- spec/fixtures/film_data/x86_64-linux~1.9.3/spelling.baseB
+- spec/fixtures/film_data/x86_64-linux~1.9.3/termlist.DB
+- spec/fixtures/film_data/x86_64-linux~1.9.3/termlist.baseA
+- spec/fixtures/film_data/x86_64-linux~1.9.3/termlist.baseB
+- spec/fixtures/film_data.rb
 - spec/query_parser_spec.rb
 - spec/stopper_factory_spec.rb
+- spec/xapian_db_spec.rb
 - spec/xapian_doc_spec.rb
 - spec/xapian_doc_value_accessor_spec.rb
-- spec/build_db_for_value_testing.rb
-- spec/facets_spec.rb

data/lib/xapian_fu/stopwords/danish.txt

@@ -1,102 +0,0 @@
-
- | A Danish stop word list. Comments begin with vertical bar. Each stop
- | word is at the start of a line.
-
- | This is a ranked list (commonest to rarest) of stopwords derived from
- | a large text sample.
-
-
-og           | and
-i            | in
-jeg          | I
-det          | that (dem. pronoun)/it (pers. pronoun)
-at           | that (in front of a sentence)/to (with infinitive)
-en           | a/an
-den          | it (pers. pronoun)/that (dem. pronoun)
-til          | to/at/for/until/against/by/of/into, more
-er           | present tense of "to be"
-som          | who, as
-på           | on/upon/in/on/at/to/after/of/with/for, on
-de           | they
-med          | with/by/in, along
-han          | he
-af           | of/by/from/off/for/in/with/on, off
-for          | at/for/to/from/by/of/ago, in front/before, because
-ikke         | not
-der          | who/which, there/those
-var          | past tense of "to be"
-mig          | me/myself
-sig          | oneself/himself/herself/itself/themselves
-men          | but
-et           | a/an/one, one (number), someone/somebody/one
-har          | present tense of "to have"
-om           | round/about/for/in/a, about/around/down, if
-vi           | we
-min          | my
-havde        | past tense of "to have"
-ham          | him
-hun          | she
-nu           | now
-over         | over/above/across/by/beyond/past/on/about, over/past
-da           | then, when/as/since
-fra          | from/off/since, off, since
-du           | you
-ud           | out
-sin          | his/her/its/one's
-dem          | them
-os           | us/ourselves
-op           | up
-man          | you/one
-hans         | his
-hvor         | where
-eller        | or
-hvad         | what
-skal         | must/shall etc.
-selv         | myself/youself/herself/ourselves etc., even
-her          | here
-alle         | all/everyone/everybody etc.
-vil          | will (verb)
-blev         | past tense of "to stay/to remain/to get/to become"
-kunne        | could
-ind          | in
-når          | when
-være         | present tense of "to be"
-dog          | however/yet/after all
-noget        | something
-ville        | would
-jo           | you know/you see (adv), yes
-deres        | their/theirs
-efter        | after/behind/according to/for/by/from, later/afterwards
-ned          | down
-skulle       | should
-denne        | this
-end          | than
-dette        | this
-mit          | my/mine
-også         | also
-under        | under/beneath/below/during, below/underneath
-have         | have
-dig          | you
-anden        | other
-hende        | her
-mine         | my
-alt          | everything
-meget        | much/very, plenty of
-sit          | his, her, its, one's
-sine         | his, her, its, one's
-vor          | our
-mod          | against
-disse        | these
-hvis         | if
-din          | your/yours
-nogle        | some
-hos          | by/at
-blive        | be/become
-mange        | many
-ad           | by/through
-bliver       | present tense of "to be/to become"
-hendes       | her/hers
-været        | be
-thi          | for (conj)
-jer          | you
-sådan        | such, like this/like that

data/lib/xapian_fu/stopwords/dutch.txt

@@ -1,113 +0,0 @@
-
-
- | A Dutch stop word list. Comments begin with vertical bar. Each stop
- | word is at the start of a line.
-
- | This is a ranked list (commonest to rarest) of stopwords derived from
- | a large sample of Dutch text.
-
- | Dutch stop words frequently exhibit homonym clashes. These are indicated
- | clearly below.
-
-de             |  the
-en             |  and
-van            |  of, from
-ik             |  I, the ego
-te             |  (1) chez, at etc, (2) to, (3) too
-dat            |  that, which
-die            |  that, those, who, which
-in             |  in, inside
-een            |  a, an, one
-hij            |  he
-het            |  the, it
-niet           |  not, nothing, naught
-zijn           |  (1) to be, being, (2) his, one's, its
-is             |  is
-was            |  (1) was, past tense of all persons sing. of 'zijn' (to be) (2) wax, (3) the washing, (4) rise of river
-op             |  on, upon, at, in, up, used up
-aan            |  on, upon, to (as dative)
-met            |  with, by
-als            |  like, such as, when
-voor           |  (1) before, in front of, (2) furrow
-had            |  had, past tense all persons sing. of 'hebben' (have)
-er             |  there
-maar           |  but, only
-om             |  round, about, for etc
-hem            |  him
-dan            |  then
-zou            |  should/would, past tense all persons sing. of 'zullen'
-of             |  or, whether, if
-wat            |  what, something, anything
-mijn           |  possessive and noun 'mine'
-men            |  people, 'one'
-dit            |  this
-zo             |  so, thus, in this way
-door           |  through by
-over           |  over, across
-ze             |  she, her, they, them
-zich           |  oneself
-bij            |  (1) a bee, (2) by, near, at
-ook            |  also, too
-tot            |  till, until
-je             |  you
-mij            |  me
-uit            |  out of, from
-der            |  Old Dutch form of 'van der' still found in surnames
-daar           |  (1) there, (2) because
-haar           |  (1) her, their, them, (2) hair
-naar           |  (1) unpleasant, unwell etc, (2) towards, (3) as
-heb            |  present first person sing. of 'to have'
-hoe            |  how, why
-heeft          |  present third person sing. of 'to have'
-hebben         |  'to have' and various parts thereof
-deze           |  this
-u              |  you
-want           |  (1) for, (2) mitten, (3) rigging
-nog            |  yet, still
-zal            |  'shall', first and third person sing. of verb 'zullen' (will)
-me             |  me
-zij            |  she, they
-nu             |  now
-ge             |  'thou', still used in Belgium and south Netherlands
-geen           |  none
-omdat          |  because
-iets           |  something, somewhat
-worden         |  to become, grow, get
-toch           |  yet, still
-al             |  all, every, each
-waren          |  (1) 'were' (2) to wander, (3) wares, (3)
-veel           |  much, many
-meer           |  (1) more, (2) lake
-doen           |  to do, to make
-toen           |  then, when
-moet           |  noun 'spot/mote' and present form of 'to must'
-ben            |  (1) am, (2) 'are' in interrogative second person singular of 'to be'
-zonder         |  without
-kan            |  noun 'can' and present form of 'to be able'
-hun            |  their, them
-dus            |  so, consequently
-alles          |  all, everything, anything
-onder          |  under, beneath
-ja             |  yes, of course
-eens           |  once, one day
-hier           |  here
-wie            |  who
-werd           |  imperfect third person sing. of 'become'
-altijd         |  always
-doch           |  yet, but etc
-wordt          |  present third person sing. of 'become'
-wezen          |  (1) to be, (2) 'been' as in 'been fishing', (3) orphans
-kunnen         |  to be able
-ons            |  us/our
-zelf           |  self
-tegen          |  against, towards, at
-na             |  after, near
-reeds          |  already
-wil            |  (1) present tense of 'want', (2) 'will', noun, (3) fender
-kon            |  could; past tense of 'to be able'
-niets          |  nothing
-uw             |  your
-iemand         |  somebody
-geweest        |  been; past participle of 'be'
-andere         |  other
-