wp2txt 0.9.1 → 0.9.4

checksums.yaml

@@ -1,7 +1,7 @@
 ---
-SHA1:
-  metadata.gz: 7354f2494c849046bdf54d6c5b798e25faeebdda
-  data.tar.gz: 9287f7cf4a18b4525a4e6a3ba2faf749b375f1eb
+SHA256:
+  metadata.gz: 50f291332872b0e3cd0b651662d7494ec9edd823fdb6ba6a928f501a37ea06c3
+  data.tar.gz: ec4891f6a30c7bc2f8f0a6fd3ec56618c9f706ea277207e7f955347417959f7e
 SHA512:
-  metadata.gz: e623c78f32aed94821a74353999462ce3cc32595a29afe2d439a2abce461a809f13f145039d0c30db5774290b06958963a1c70f5c4bbae3f7980416a11571bde
-  data.tar.gz: e85430ddae0dfca581533b7487ef365844594bcea43735f6f5f61589f689ed941dddb5472b303772966ca5236d42557e57a318023a15075fe3214f32e328d941
+  metadata.gz: afa3770c47bc25252993bfddf6da6e99a7bca87d4d899b3f8ce44d8a6298d29a19ce06fe9b64166316a31672a76d7d4530887e77d98212bc8f17a350c0e1598a
+  data.tar.gz: ef6f5b11b8a7d2ae5eeb640b0f2319bea9ee1209b0ab1dd78833f3cde41149fb8468871d90ba75b00c62876fccfa5c5f7cca6fc2420d4769c3c35a7bd9aa8786

data/README.md

@@ -1,32 +1,51 @@
 # WP2TXT
 
-Wikipedia dump file to text converter
+Wikipedia dump file to text converter that extracts both content and category data
 
-**IMPORTANT:** This is a project still work in progress and it could be slow, unstable, and even destructive! It should be used with caution.
-
-### About ###
+## About
 
 WP2TXT extracts plain text data from Wikipedia dump file (encoded in XML/compressed with Bzip2) stripping all the MediaWiki markups and other metadata. It is originally intended to be useful for researchers who look for an easy way to obtain open-source multi-lingual corpora, but may be handy for other purposes.
 
-**UPDATE:** Version 0.9.1 has added a new option `num-threads`, which improves the performance significantly . Note also that `--category` option is enabled by default, resulting with output format somewhat different from previous versions. Check out the new format using test data in `data/output_samples` folder before going on to convert a huge wikipedia dump.
+**UPDATE (July 2022)**: Version 0.9.3 has added a new option `category_only`. With this option enabled, wp2txt extracts article title and category info only. Please see output examples below.
 
-### Features ###
+## Features
 
-* Convert dump files of Wikipedia of various languages (I hope).
+* Convert dump files of Wikipedia of various languages
 * Create output files of specified size.
-* Allow users to specify text elements to be extracted/converted (page titles, section titles, lists, and tables).
+* Allow users to specify text elements to be extracted/converted (page titles, section titles, lists, and tables)
+* Extract category information of each article
+
+## Installation
 
-### Installation
-    
     $ gem install wp2txt
 
-### Usage
+## Usage
 
 Obtain a Wikipedia dump file (from [here](http://dumps.wikimedia.org/backup-index.html)) with a file name such as:
 
     xxwiki-yyyymmdd-pages-articles.xml.bz2
 
-where `xx` is language code such as "en (English)" or "ja (Japanese)", and  `yyyymmdd` is the date of creation (e.g. 20120601).
+where `xx` is language code such as "en (English)" or "ja (Japanese)", and  `yyyymmdd` is the date of creation (e.g. 20220720).
+
+### Example 1
+
+The following extracts text data, including list items and excluding tables.
+
+    $ wp2txt -i xxwiki-yyyymmdd-pages-articles.xml.bz2 -o /output_dir
+
+- [Output example (English)](https://raw.githubusercontent.com/yohasebe/wp2txt/master/data/output_samples/testdata_en.txt)
+- [Output example (Japanese)](https://raw.githubusercontent.com/yohasebe/wp2txt/master/data/output_samples/testdata_ja.txt)
+
+### Example 2
+
+The following will extract only article titles and the categories to which each article belongs:
+
+    $ wp2txt --category-only -i xxwiki-yyyymmdd-pages-articles.xml.bz2 -o /output_dir
+
+- [Output example (English)](https://raw.githubusercontent.com/yohasebe/wp2txt/master/data/output_samples/testdata_en_categories.txt)
+- [Output example (Japanese)](https://raw.githubusercontent.com/yohasebe/wp2txt/master/data/output_samples/testdata_ja_categories.txt)
+
+## Options
 
 Command line options are as follows:
 
@@ -40,44 +59,45 @@ Command line options are as follows:
           --list, --no-list, -l:   Show list items in output (default: true)
     --heading, --no-heading, -d:   Show section titles in output (default: true)
         --title, --no-title, -t:   Show page titles in output (default: true)
-                    --table, -a:   Show table source code in output
-                   --inline, -n:   leave inline template notations unmodified
-                --multiline, -m:   leave multiline template notations unmodified
-                      --ref, -r:   leave reference notations in the format
+                    --table, -a:   Show table source code in output (default: false)
+                   --inline, -n:   leave inline template notations unmodified (default: false)
+                --multiline, -m:   leave multiline template notations unmodified (default: false)
+                      --ref, -r:   leave reference notations in the format (default: false)
                                    [ref]...[/ref]
-                 --redirect, -e:   Show redirect destination
+                 --redirect, -e:   Show redirect destination (default: false)
       --marker, --no-marker, -k:   Show symbols prefixed to list items,
                                    definitions, etc. (Default: true)
-                 --category, -g:   Show article category information
+                 --category, -g:   Show article category information (default: true)
+            --category-only, -y:   Extract only article title and categories (default: false)
             --file-size, -f <i>:   Approximate size (in MB) of each output file
                                    (default: 10)
-          -u, --num-threads=<i>:   Number of threads to be spawned (capped to the number of CPU cores; 
+          -u, --num-threads=<i>:   Number of threads to be spawned (capped to the number of CPU cores;
                                    set 99 to spawn max num of threads) (default: 4)
                   --version, -v:   Print version and exit
                      --help, -h:   Show this message
 
-### Caveats ###
+## Caveats
 
 * Certain types of data such as mathematical equations and computer source code are not be properly converted.  Please remember this software is originally intended for correcting “sentences” for linguistic studies.
-* Extraction of normal text data could sometimes fail for various reasons (e.g. illegal matching of begin/end tags, language-specific conventions of formatting, etc). 
+* Extraction of normal text data could sometimes fail for various reasons (e.g. illegal matching of begin/end tags, language-specific conventions of formatting, etc).
 * Conversion process can take far more than you would expect. It could take several hours or more when dealing with a huge data set such as the English Wikipedia on a low-spec environments.
 * Because of nature of the task, WP2TXT needs much machine power and consumes a lot of memory/storage resources. The process thus could halt unexpectedly. It may even get stuck, in the worst case, without getting gracefully terminated. Please understand this and use the software __at your own risk__.
 
-### Useful Link ###
+### Useful Links
 
 * [Wikipedia Database backup dumps](http://dumps.wikimedia.org/backup-index.html)
-                
-### Author ###
+
+### Author
 
 * Yoichiro Hasebe (<yohasebe@gmail.com>)
 
-### References ###
+### References
 
 The author will appreciate your mentioning one of these in your research.
 
 * Yoichiro HASEBE. 2006. [Method for using Wikipedia as Japanese corpus.](http://ci.nii.ac.jp/naid/110006226727) _Doshisha Studies in Language and Culture_ 9(2), 373-403.
 * 長谷部陽一郎. 2006. [Wikipedia日本語版をコーパスとして用いた言語研究の手法](http://ci.nii.ac.jp/naid/110006226727). 『言語文化』9(2), 373-403.
 
-### License ###
+### License
 
 This software is distributed under the MIT License. Please see the LICENSE file.

data/bin/wp2txt

@@ -11,11 +11,11 @@ DOCDIR = File.join(File.dirname(__FILE__), '..', 'doc')
 require 'wp2txt'
 require 'wp2txt/utils'
 require 'wp2txt/version'
-require 'trollop'
+require 'optimist'
 
 include Wp2txt
 
-opts = Trollop::options do
+opts = Optimist::options do
 	version Wp2txt::VERSION
 	banner <<-EOS
 WP2TXT extracts plain text data from Wikipedia dump file (encoded in XML/compressed with Bzip2) stripping all the MediaWiki markups and other metadata.
@@ -37,11 +37,12 @@ EOS
   opt :redirect, "Show redirect destination", :default => false
   opt :marker, "Show symbols prefixed to list items, definitions, etc.", :default => true
   opt :category, "Show article category information", :default => true 
+  opt :category_only, "Extract only article title and categories", :default => false
   opt :file_size,   "Approximate size (in MB) of each output file", :default => 10
   opt :num_threads,   "Number of threads to be spawned (capped to the number of CPU cores; set 99 to spawn max num of threads)", :default => 4
 end
-Trollop::die :size, "must be larger than 0" unless opts[:file_size] >= 0
-Trollop::die :output_dir, "must exist" unless File.exist?(opts[:output_dir])
+Optimist::die :size, "must be larger than 0" unless opts[:file_size] >= 0
+Optimist::die :output_dir, "must exist" unless File.exist?(opts[:output_dir])
 
 input_file = ARGV[0]
 output_dir = opts[:output_dir]
@@ -63,72 +64,79 @@ wpconv = Wp2txt::Runner.new(parent, input_file, output_dir, tfile_size, num_thre
 
 wpconv.extract_text do |article|
   format_wiki!(article.title)
-  title = "[[#{article.title}]]\n"
 
-  if opts[:category] && !article.categories.empty?
+  if opts[:category_only]
+    title = "#{article.title}\t"
+    contents = article.categories.join(", ")
+    contents << "\n"
+  elsif opts[:category] && !article.categories.empty?
+    title = "\n[[#{article.title}]]\n\n"
     contents = "\nCATEGORIES: "
     contents << article.categories.join(", ")
     contents << "\n\n"
   else
+    title = "\n[[#{article.title}]]\n\n"
     contents = ""
   end
 
-  article.elements.each do |e|
-    case e.first
-    when :mw_heading
-      next if !config[:heading]
-      format_wiki!(e.last)
-      line = e.last
-      line << "+HEADING+" if $DEBUG_MODE
-    when :mw_paragraph
-      format_wiki!(e.last)
-      line = e.last + "\n"
-      line << "+PARAGRAPH+" if $DEBUG_MODE
-    when :mw_table, :mw_htable
-      next if !config[:table]
-      line = e.last
-      line << "+TABLE+" if $DEBUG_MODE
-    when :mw_pre
-      next if !config[:pre]
-      line = e.last
-      line << "+PRE+" if $DEBUG_MODE
-    when :mw_quote
-      line = e.last
-      line << "+QUOTE+" if $DEBUG_MODE
-    when :mw_unordered, :mw_ordered, :mw_definition
-      next if !config[:list]
-      line = e.last
-      line << "+LIST+" if $DEBUG_MODE
-    when :mw_ml_template
-      next if !config[:multiline]
-      line = e.last
-      line << "+MLTEMPLATE+" if $DEBUG_MODE
-    when :mw_redirect
-      next if !config[:redirect]
-      line = e.last
-      line << "+REDIRECT+" if $DEBUG_MODE
-      line << "\n\n"
-    when :mw_isolated_template
-      next if !config[:multiline]
-      line = e.last
-      line << "+ISOLATED_TEMPLATE+" if $DEBUG_MODE
-    when :mw_isolated_tag
-      next
-    else
-      if $DEBUG_MODE
-        # format_wiki!(e.last)
+  unless opts[:category_only]
+    article.elements.each do |e|
+      case e.first
+      when :mw_heading
+        next if !config[:heading]
+        format_wiki!(e.last)
         line = e.last
-        line << "+OTHER+"
-      else
+        line << "+HEADING+" if $DEBUG_MODE
+      when :mw_paragraph
+        format_wiki!(e.last)
+        line = e.last + "\n"
+        line << "+PARAGRAPH+" if $DEBUG_MODE
+      when :mw_table, :mw_htable
+        next if !config[:table]
+        line = e.last
+        line << "+TABLE+" if $DEBUG_MODE
+      when :mw_pre
+        next if !config[:pre]
+        line = e.last
+        line << "+PRE+" if $DEBUG_MODE
+      when :mw_quote
+        line = e.last
+        line << "+QUOTE+" if $DEBUG_MODE
+      when :mw_unordered, :mw_ordered, :mw_definition
+        next if !config[:list]
+        line = e.last
+        line << "+LIST+" if $DEBUG_MODE
+      when :mw_ml_template
+        next if !config[:multiline]
+        line = e.last
+        line << "+MLTEMPLATE+" if $DEBUG_MODE
+      when :mw_redirect
+        next if !config[:redirect]
+        line = e.last
+        line << "+REDIRECT+" if $DEBUG_MODE
+        line << "\n\n"
+      when :mw_isolated_template
+        next if !config[:multiline]
+        line = e.last
+        line << "+ISOLATED_TEMPLATE+" if $DEBUG_MODE
+      when :mw_isolated_tag
         next
+      else
+        if $DEBUG_MODE
+          # format_wiki!(e.last)
+          line = e.last
+          line << "+OTHER+"
+        else
+          next
+        end
       end
+      contents << line << "\n"
     end
-    contents << line << "\n"
   end
     
   if /\A[\s　]*\z/m =~ contents
     result = ""
   else
-    result = config[:title] ? "\n#{title}\n" << contents : contents
+    result = config[:title] ? title << contents : contents
   end
 end

data/data/output_samples/testdata_en.txt

@@ -28704,7 +28704,7 @@ File:Halkbank.jpg|Halkbank Tower (1993) designed by Doğan Tekeli and Sami Sisa
 
 * [http://www.esenbogaairport.com/ Esenboğa International Airport]
 
-[[Anaconda]]
+[[Arabic language]]
 
 CATEGORIES: Arabic language, Central Semitic languages, Fusional languages, Languages of Algeria, Languages of Bahrain, Languages of Chad, Languages of Comoros, Languages of Djibouti, Languages of Eritrea, Languages of Gibraltar, Languages of Iraq, Languages of Israel, Languages of Jordan, Languages of Kuwait, Languages of Lebanon, Languages of Libya, Languages of Mauritania, Languages of Morocco, Languages of Oman, Languages of Qatar, Languages of Saudi Arabia, Languages of Somalia, Languages of Somaliland, Languages of Sudan, Languages of Syria, Languages of the United Arab Emirates, Languages of Tunisia, Languages of Yemen, Languages of Trinidad and Tobago, Requests for audio pronunciation (Arabic), Stress-timed languages, Subject–verb–object languages, Languages of Palestine
 

data/data/output_samples/testdata_en_categories.txt

@@ -0,0 +1,207 @@
+Anarchism	Anarchism, Political culture, Political ideologies, Social theories, Anti-fascism, Anti-capitalism, Far-left politics
+Autism	Autism, Communication disorders, Mental and behavioural disorders, Neurological disorders, Neurological disorders in children, Pervasive developmental disorders, Psychiatric diagnosis
+Albedo	Climate forcing, Climatology, Electromagnetic radiation, Radiometry, Scattering, absorption and radiative transfer (optics), Radiation
+A	ISO basic Latin letters, Vowel letters
+Alabama	Alabama, States and territories established in 1819, States of the Confederate States of America, States of the United States, Southern United States
+Achilles	Characters in the Iliad, Demigods of Classical mythology, Kings of the Myrmidons, Greek mythological hero cult, People of the Trojan War, Thessalians in the Trojan War
+Abraham Lincoln	Abraham Lincoln, 1809 births, 1865 deaths, American people of English descent, Assassinated heads of state, Assassinated United States Presidents, Burials at Oak Ridge Cemetery, Deaths by firearm in Washington, D.C., Illinois lawyers, Illinois Republicans, Illinois Whigs, Lincoln family, Members of the Illinois House of Representatives, Members of the United States House of Representatives from Illinois, People from Coles County, Illinois, People from LaRue County, Kentucky, People from Macon County, Illinois, People from Spencer County, Indiana, People from Springfield, Illinois, People murdered in Washington, D.C., People of Illinois in the American Civil War, Political party founders, American postmasters, Presidents of the United States, Republican Party (United States) presidential nominees, Republican Party Presidents of the United States, Smallpox survivors, Union political leaders, United States presidential candidates, 1860, United States presidential candidates, 1864, Whig Party members of the United States House of Representatives, Hall of Fame for Great Americans inductees
+Aristotle	Aristotle, 384 BC births, 322 BC deaths, 4th-century BC philosophers, 4th-century BC writers, Academic philosophers, Acting theorists, Ancient Greek mathematicians, Ancient Greek philosophers, Ancient Greek physicists, Ancient Greeks in Macedon, Ancient Stagirites, Attic Greek writers, Cosmologists, Pro-slavery activists, Empiricists, Ancient Greek biologists, Ancient Greek logicians, History of logic, Humor researchers, Metaphysicians, Meteorologists, Metic philosophers in Classical Athens, Natural philosophers, Peripatetic philosophers, Philosophers and tutors of Alexander the Great, Philosophers of ancient Chalcidice, Philosophers of language, Philosophers of law, Philosophers of mind, Political philosophers, Rhetoric theorists, Trope theorists, Ancient literary critics, Virtue ethicists, Zoologists
+An American in Paris	Compositions by George Gershwin, Symphonic poems, Grammy Hall of Fame Award recipients, 1928 compositions, Music about Paris
+Academy Award for Best Production Design	Academy Awards, Best Art Direction Academy Award winners, Awards for best art direction
+Academy Awards	Academy Awards, American film awards, Awards established in 1929, 1929 establishments in the United States
+Actrius	1996 films, 1990s drama films, Spanish films, Catalan-language films, Films set in Barcelona, Barcelona in fiction, Films directed by Ventura Pons
+Animalia (book)	Children's picture books, Alphabet books, 1986 books, Picture books by Graeme Base, Puzzle books
+International Atomic Time	Time scales
+Altruism	Altruism, Defence mechanisms, Evolution by phenotype, Morality, Philanthropy, Social philosophy, Social psychology, Auguste Comte, Virtue
+Ayn Rand	1905 births, 1982 deaths, 20th-century American novelists, 20th-century philosophers, 20th-century women writers, American anti-communists, American anti-fascists, American atheists, American classical liberals, American essayists, American ethicists, American people of Russian-Jewish descent, American political theorists, American science fiction writers, American screenwriters, American women novelists, American women philosophers, American women screenwriters, American writers of Russian descent, Atheist philosophers, Ayn Rand, Burials at Kensico Cemetery, Cardiovascular disease deaths in New York, Critics of feminism, Critics of religions, Deaths from heart failure, Epistemologists, Imperial Russian atheists, Imperial Russian emigrants to the United States, Imperial Russian Jews, Jewish American dramatists and playwrights, Jewish American novelists, Jewish atheists, Jewish philosophers, Jewish women writers, Metaphysicians, Objectivists, Philosophers of mind, Political philosophers, Prometheus Award winners, Pseudonymous writers, Russian anti-communists, Russian anti-fascists, Russian dramatists and playwrights, Russian essayists, Russian novelists, Russian philosophers, Russian science fiction writers, Russian screenwriters, Russian women writers, Saint Petersburg State University alumni, Soviet emigrants to the United States, Women essayists, Women science fiction and fantasy writers, Writers from New York City, Writers from Saint Petersburg, American women dramatists and playwrights, 20th-century American dramatists and playwrights
+Alain Connes	1947 births, Living people, 20th-century mathematicians, Members of the United States National Academy of Sciences, 21st-century mathematicians, Collège de France faculty, French mathematicians, Fields Medalists, Mathematical analysts, Differential geometers, École Normale Supérieure alumni, Vanderbilt University faculty, Foreign Members of the Russian Academy of Sciences, Members of the French Academy of Sciences, Members of the Norwegian Academy of Science and Letters, Members of the Royal Danish Academy of Sciences and Letters, Clay Research Award recipients
+Allan Dwan	1885 births, 1981 deaths, American film directors, American film producers, American screenwriters, Western (genre) film directors, Canadian film directors, Canadian emigrants to the United States, Writers from Toronto, Short film directors, Disease-related deaths in California, Burials at San Fernando Mission Cemetery
+Algeria	Algeria, Countries in Africa, North African countries, List of Mediterranean countries, Maghrebi countries, Arabic-speaking countries and territories, Berber-speaking countries and territories, French-speaking countries and territories, G15 nations, Member states of OPEC, Member states of the African Union, Member states of the Arab League, Member states of the Organisation of Islamic Cooperation, Member states of the Union for the Mediterranean, Member states of the United Nations, Republics, Requests for audio pronunciation (Arabic), Requests for audio pronunciation (Berber), States and territories established in 1962, World Digital Library related
+List of Atlas Shrugged characters	Atlas Shrugged characters, Fictional socialites, Lists of literary characters
+Anthropology	Anthropology, Social sciences
+Agricultural science	Agronomy
+Alchemy	Alchemy, Hermeticism, Esotericism
+Astronomer	Astronomy, Astronomers, Science occupations
+ASCII	ASCII, Character sets, Latin-alphabet representations, Presentation layer protocols
+Animation	Animation
+Apollo	Apollo, Arts gods, Deities in the Iliad, Dragonslayers, Health gods, Knowledge gods, LGBT history in Greece, LGBT themes in mythology, Muses, Temples of Apollo, Mythological Greek archers, Mythological rapists, Oracular gods, Roman gods, Solar gods
+Andre Agassi	1970 births, American male tennis players, American people of Armenian descent, American people of Iranian-Assyrian descent, American philanthropists, Australian Open (tennis) champions, Doping cases in tennis, French Open champions, Grand Slam (tennis) champions in men's singles, International Tennis Hall of Fame inductees, Living people, Nevada Democrats, Assyrian sportspeople, Olympic gold medalists for the United States, Olympic medalists in tennis, Olympic tennis players of the United States, Sportspeople from the Las Vegas Valley, Tennis people from Nevada, Tennis players at the 1996 Summer Olympics, US Open (tennis) champions, Wimbledon champions, World No. 1 tennis players, Iranian Assyrian people, American autobiographers, Writers from Nevada, Medalists at the 1996 Summer Olympics, American sportspeople in doping cases, 20th-century American businesspeople, 21st-century American businesspeople, American investors, American real estate businesspeople
+Austroasiatic languages	Agglutinative languages, Austroasiatic languages
+Afroasiatic languages	Afro-Asiatic, Afro-Asiatic languages, Language families
+Andorra	Andorra, Constitutional monarchies, Countries in Europe, Diarchies, Landlocked countries, Liberal democracies, Member states of La Francophonie, Member states of the United Nations, Països Catalans, Prince-Bishoprics, Principalities, Pyrenees, Romance countries and territories, States and territories established in 1278
+Arithmetic mean	Means
+American Football Conference	National Football League, American Football League, Organizations established in 1970
+Animal Farm	1945 novels, Allegory, Animal Farm, Dystopian novels, English novels, Hugo Award for Best Novella winning works, Prometheus Award winning works, Literature featuring anthropomorphic characters, British novellas, Novels by George Orwell, Political literature, Roman à clef novels, Satirical novels, Novels about revolutionaries, Novels about totalitarianism, Novels about propaganda, British satirical novels, Animals in media, Secker & Warburg books
+Amphibian	Amphibians, Animal classes
+Alaska	Alaska, Arctic Ocean, Exclaves in the United States, Former Russian colonies, States and territories established in 1959, States of the United States, West Coast of the United States
+Agriculture	Agriculture
+Aldous Huxley	Aldous Huxley, 1894 births, 1963 deaths, 19th-century English people, People educated at Eton College, Alumni of Balliol College, Oxford, Burials in Surrey, Cancer deaths in California, Consciousness researchers and theorists, Deaths from laryngeal cancer, Duke University faculty, English agnostics, English essayists, English expatriates in the United States, English humanists, English novelists, English pacifists, English people of Cornish descent, English poets, English philosophers, English satirists, English science fiction writers, English short story writers, English travel writers, Huxley family, James Tait Black Memorial Prize recipients, Mystics, People associated with the Human Potential Movement, People from Godalming, People from Taos, New Mexico, Psychedelic drug advocates, Writers from Los Angeles, California, 20th-century British novelists
+Algae	Algae, Endosymbiotic events
+Analysis of variance	Analysis of variance, Design of experiments, Statistical tests, Parametric statistics
+Alkane	Alkanes, Hydrocarbons, Organic compounds, Functional groups
+Appellate procedure in the United States	United States appellate procedure, United States procedural law, Legal procedure
+Answer	Common law, Legal documents
+Appellate court	Courts by type, Appellate courts
+Arraignment	Legal terms, Prosecution, United States criminal procedure, Criminal law of the United Kingdom, Australian criminal law
+America the Beautiful	1895 songs, American patriotic songs, Pikes Peak
+Assistive technology	Assistive technology, Disability, Educational technology, Web accessibility
+Abacus	Abacus, Chinese mathematics, Egyptian mathematics, Greek mathematics, Indian mathematics, Japanese mathematics, Mathematical tools, Roman mathematics
+Acid	Acids, Acid–base chemistry
+Asphalt	Building materials, Road construction, Chemical mixtures, Amorphous solids, Asphalt, Petroleum, Petroleum products, IARC Group 2B carcinogens, Latin words and phrases, Pavements
+American National Standards Institute	Organizations established in 1918, 501(c)(3) nonprofit organizations, Standards organizations, ISO member bodies, ANSI standards, 1918 establishments in the United States, Technical specifications
+Apollo 11	Apollo program, Manned missions to the Moon, Missions to the Moon, Sample return missions, 1969 in the United States, Spacecraft launched in 1969, Articles containing video clips, Individual spacecraft in the collection of the Smithsonian Institution, Soft landings on the Moon, Spacecraft which reentered in 1969
+Apollo 8	Spacecraft launched in 1968, 1968 in the United States, Apollo program, Manned missions to the Moon, Spacecraft which reentered in 1968
+Astronaut	Astronauts, Science occupations
+A Modest Proposal	Essays by Jonathan Swift, Satirical works, Pamphlets, 1729 essays, Works published anonymously, British satire, 1729 in Great Britain, Cannibalism in fiction
+Alkali metal	Alkali metals, Groups in the periodic table, Periodic table
+Alphabet	Alphabets, Documents, Orthography
+Atomic number	Chemical properties, Nuclear physics, Atoms
+Anatomy	Anatomy
+Affirming the consequent	Propositional fallacies
+Andrei Tarkovsky	1932 births, 1986 deaths, People from Yuryevets District, Burials at Sainte-Geneviève-des-Bois Russian Cemetery, Russian people of Polish descent, Ukrainian people of Polish descent, Russian people of Ukrainian descent, Andrei Tarkovsky, BAFTA winners (people), Russian male actors, Russian Orthodox Christians, Soviet film directors, Russian film directors, Russian opera directors, Gerasimov Institute of Cinematography alumni, High Courses for Scriptwriters and Film Directors faculty, Deaths from lung cancer, Cancer deaths in France, Lenin Prize winners
+Ambiguity	Semantics, Critical thinking, Ambiguity
+Aardvark	Mammals of Africa, Myrmecophagous mammals, Living fossils, Megafauna of Africa, Animals described in 1766
+Aardwolf	Animals described in 1783, Carnivorans of Africa, Hyenas, Mammals of Africa, Fauna of Southern Africa, Fauna of East Africa, Myrmecophagous mammals
+Adobe	Building materials, Masonry, Adobe buildings and structures, Appropriate technology, Vernacular architecture, Requests for audio pronunciation (Spanish), Sustainable building, Buildings and structures by construction material
+Adventure	Adventure
+Asia	Asia, Continents
+Aruba	Aruba, Countries in the Caribbean, Dependent territories in North America, Dutch-speaking countries and territories, Former Dutch colonies, Island countries, Islands of the Netherlands Antilles, Kingdom of the Netherlands, Lesser Antilles, Netherlands Antilles articles correct after Dissolution, Special territories of the European Union, States and territories established in 1986
+Articles of Confederation	1781 in law, Defunct constitutions, Documents of the American Revolution, Ordinances of the Continental Congress, Federalism in the United States, History of the United States (1776–89), History of York County, Pennsylvania, Legal history of the United States, Pennsylvania in the American Revolution, Political charters, United States historical documents, York, Pennsylvania
+Atlantic Ocean	Atlantic Ocean, Oceans, History of the Atlantic Ocean, Landforms of the Atlantic Ocean
+Arthur Schopenhauer	Arthur Schopenhauer, 1788 births, 1860 deaths, 19th-century German writers, 19th-century philosophers, Antinatalists, Atheist philosophers, German atheists, German monarchists, German people of Dutch descent, German philosophers, Humboldt University of Berlin faculty, Idealists, Kantian philosophers, Metaphysicians, Monism, People from Gdańsk, University of Göttingen alumni, Philosophers of art, Burials at Frankfurt Main Cemetery
+Angola	Angola, Bantu countries and territories, Central African countries, Countries in Africa, Former Portuguese colonies, Least developed countries, Member states of OPEC, Member states of the African Union, Member states of the Community of Portuguese Language Countries, Member states of the United Nations, Portuguese-speaking countries and territories, Republics, States and territories established in 1975, World Digital Library related
+Demographics of Angola	Angolan society, Demographics by country
+Politics of Angola	Politics of Angola
+Economy of Angola	African Union member economies, Economy of Angola, OPEC, World Trade Organization member economies, Blood diamonds
+Transport in Angola	Transport in Angola
+Angolan Armed Forces	Military of Angola, Military history of Angola
+Foreign relations of Angola	Foreign relations of Angola
+Albert Sidney Johnston	1803 births, 1862 deaths, Confederate States military personnel killed in the American Civil War, Burials at Texas State Cemetery, Confederate States Army generals, People from Washington, Kentucky, People from Texas, People of California in the American Civil War, People of Texas in the American Civil War, American people of the Black Hawk War, Transylvania University alumni, United States Army generals, United States Military Academy alumni, People of the Texas Revolution, People of the Utah War
+Android (robot)	Androids, Science fiction themes, Android (robot), Osaka University research
+Alberta	Alberta, 1905 establishments in Canada, Provinces and territories of Canada, States and territories established in 1905, Canadian Prairies
+List of anthropologists	Lists of social scientists, Anthropologists
+Actinopterygii	Ray-finned fish, Animal classes
+Albert Einstein	1879 births, 1955 deaths, 20th-century American writers, 20th-century German writers, Albert Einstein, American agnostics, American engineers, American pacifists, American philosophers, American physicists, American science writers, American socialists, American Zionists, Charles University in Prague faculty, Cosmologists, Deaths from abdominal aortic aneurysm, Einstein family, ETH Zurich alumni, ETH Zurich faculty, Foreign Members of the Royal Society, German emigrants to Switzerland, German Jews who emigrated to the United States to escape Nazism, German Nobel laureates, German physicists, German socialists, Institute for Advanced Study faculty, Jewish agnostics, Jewish American scientists, Jewish engineers, Jewish philosophers, Jewish physicists, Leiden University faculty, Members of the American Philosophical Society, Nobel laureates in Physics, Pantheists, Patent examiners, People from Berlin, People from Bern, People from Munich, People from Princeton, New Jersey, People from Ulm, People from Zürich, People with acquired Austria-Hungary citizenship, People with acquired Swiss citizenship, Philosophers of science, Relativists, Stateless people, Swiss agnostics, Swiss emigrants to the United States, Swiss physicists, Swiss Jews, Theoretical physicists, Winners of the Max Planck Medal
+Afghanistan	Afghanistan, Central Asian countries, Education in Afghanistan, Iranian Plateau, Islamic republics, Islamic states, Landlocked countries, Least developed countries, Member states of the Organisation of Islamic Cooperation, Member states of the South Asian Association for Regional Cooperation, Member states of the United Nations, Pashto-speaking countries and territories, Persian-speaking countries and territories, Republics, South Asian countries, States and territories established in 1709, States and territories established in 1747, Territories under military occupation
+Albania	Albania, Albanian-speaking countries and territories, Balkans, Countries in Europe, List of Mediterranean countries, Member states of La Francophonie, Member states of NATO, Member states of the Organisation of Islamic Cooperation, Member states of the Union for the Mediterranean, Member states of the United Nations, Republics, States and territories established in 1912, World Digital Library related
+Allah	Allah, Islamic theology, God, Creator deities
+Algorithms (journal)	Computer science journals, Open access journals, Multidisciplinary Digital Publishing Institute academic journals, Quarterly journals, English-language journals, Publications established in 2008, Mathematics journals
+Azerbaijan	Azerbaijan, Caucasus, Western Asian countries, Countries in Europe, Near Eastern countries, Landlocked countries, Modern Turkic states, Republics, Requests for audio pronunciation (Azerbaijani), Russian-speaking countries and territories, States and territories established in 1991, Western Asia, Member states of the Organisation of Islamic Cooperation, Member states of the Commonwealth of Independent States, Member states of the United Nations, Azerbaijani-speaking countries and territories, Ethnic Azerbaijani people, Eastern Europe
+Amateur astronomy	Amateur astronomers, Amateur astronomy
+Aikido	Japanese martial arts, Aikido, Dō
+Art	Aesthetics, Arts, Visual arts
+Agnostida	Agnostida, Trilobites, Cambrian trilobites, Ordovician trilobites, Fossil taxa described in 1864
+Abortion	Abortion, Gender studies, Fertility, Human reproduction, Ethically disputed practices
+Abstract (law)	Legal research
+American Revolutionary War	American Revolutionary War, Global conflicts, Resistance to the British Empire, Wars of independence
+Ampere	SI base units, Units of electric current
+Algorithm	Algorithms, Articles with example pseudocode, Mathematical logic, Theoretical computer science
+Annual plant	Plants, Garden plants, Horticulture and gardening, Annual plants
+Anthophyta	Plants
+Mouthwash	Dentifrices, Oral hygiene, Drug delivery devices, Dosage forms
+Alexander the Great	Alexander the Great, 356 BC births, 323 BC deaths, 4th-century BC Greek people, 4th-century BC Macedonians, 4th-century BC rulers, Ancient Macedonian generals, Ancient Pellaeans, City founders, Deified people, Greek historical hero cult, Hellenistic individuals, Hellenistic ruler cult, Macedonian monarchs, Monarchs of Persia, Pharaohs of the Argead dynasty
+Alfred Korzybski	1879 births, 1950 deaths, People from Warsaw, People from Warsaw Governorate, Clan of Abdank, Polish emigrants to the United States, Polish engineers, Polish philosophers, Polish mathematicians, Linguists from Poland, Contemporary philosophers, General semantics
+Asteroids (video game)	1979 video games, Ed Logg games, Amiga games, Arcade games, Atari 2600 games, Cancelled Atari 5200 games, Atari 7800 games, IOS games, Atari 8-bit family games, Atari arcade games, Atari Lynx games, Game Boy Color games, Mac OS games, Mobile games, Windows games, PlayStation games, Nintendo 64 games, Xbox 360 Live Arcade games, Xbox 360 games, Multidirectional shooters, Vector arcade games, Multiplayer video games, Android games, Video games of the Museum of Modern Art, Asteroids in fiction
+Asparagales	Asparagales, Angiosperm orders
+Alismatales	Alismatales, Angiosperm orders
+Apiales	Apiales, Angiosperm orders
+Asterales	Asterales, Angiosperm orders
+Asteroid	Asteroids, Asteroid groups and families, Binary asteroids, Spaceflight
+Allocution	Criminal procedure, Evidence law
+Affidavit	Evidence law, Legal documents, Notary
+Aries (constellation)	Aries (constellation), Constellations, Constellations listed by Ptolemy, Northern constellations, Western astrology
+Aquarius (constellation)	Aquarius (constellation), Constellations, Western astrology, Equatorial constellations, Constellations listed by Ptolemy
+Anime	1917 introductions, Anime, Anime and manga terminology, Articles including recorded pronunciations, Japanese inventions
+Ankara	Ankara, Capitals in Asia, Capitals in Europe, Populated places in Ankara Province
+Arabic language	Arabic language, Central Semitic languages, Fusional languages, Languages of Algeria, Languages of Bahrain, Languages of Chad, Languages of Comoros, Languages of Djibouti, Languages of Eritrea, Languages of Gibraltar, Languages of Iraq, Languages of Israel, Languages of Jordan, Languages of Kuwait, Languages of Lebanon, Languages of Libya, Languages of Mauritania, Languages of Morocco, Languages of Oman, Languages of Qatar, Languages of Saudi Arabia, Languages of Somalia, Languages of Somaliland, Languages of Sudan, Languages of Syria, Languages of the United Arab Emirates, Languages of Tunisia, Languages of Yemen, Languages of Trinidad and Tobago, Requests for audio pronunciation (Arabic), Stress-timed languages, Subject–verb–object languages, Languages of Palestine
+Alfred Hitchcock	1899 births, 1980 deaths, 19th-century English people, Alfred Hitchcock, BAFTA fellows, Deaths from renal failure, English film directors, English film producers, English emigrants to the United States, English-language film directors, English people of Irish descent, English Roman Catholics, English television directors, American film directors, American film producers, American television directors, German-language film directors, Horror film directors, Knights Commander of the Order of the British Empire, People educated at St Ignatius' College, Enfield, Silent film directors, People from Leytonstone, Edgar Award winners, Cecil B. DeMille Award Golden Globe winners
+Anaconda	Snakes, Boinae by common name
+Altaic languages	Altaic languages, Agglutinative languages, Altai Mountains, Northeast Asia, Requests for audio pronunciation
+Austrian German	German dialects, Languages of Austria, National varieties of German, Upper German languages
+Axiom of choice	Axiom of choice
+Attila	Attila the Hun, 406 births, 453 deaths, Huns, 5th-century monarchs in Europe, Turkic rulers, Ancient Germanic rulers, Deaths from choking, History of Hungary
+Aegean Sea	Aegean Sea, Bodies of water of Greece, Bodies of water of Turkey, Seas of the Mediterranean, European seas
+A Clockwork Orange	A Clockwork Orange, 1962 novels, Mind control in fiction, Books written in fictional dialects, British novellas, British novels adapted into films, British philosophical novels, British science fiction novels, Dystopian novels, Fiction with unreliable narrators, Ludwig van Beethoven in popular culture, Metafictional works, Novels about music, Novels by Anthony Burgess, Novels set in England, Obscenity controversies, Prometheus Award winning works, Rape in fiction, Heinemann (publisher) books, English-language novels
+Amsterdam	Amsterdam, Capitals in Europe, Cities in the Netherlands, Olympic cycling venues, Populated places established in the 13th century, Populated places in North Holland, Port cities and towns in the Netherlands, Port cities and towns of the North Sea, 1928 Summer Olympic venues
+Museum of Work	Museums in Östergötland County, Norrköping, Industry museums in Sweden
+Audi	Audi, Baden-Württemberg, Companies based in Bavaria, Car manufacturers of Germany, Companies disestablished in 1939, Companies established in 1909, Companies established in 1965, German brands, Ingolstadt, Luxury motor vehicle manufacturers, Motor vehicle manufacturers of Germany, Saxony, Sports car manufacturers, Volkswagen Group
+Aircraft	Aircraft
+Alfred Nobel	1833 births, 1896 deaths, 19th-century Swedish people, Deaths from stroke, Swedish Christians, Members of the Royal Swedish Academy of Sciences, Nobel family, Nobel Prize, People from Stockholm, Swedish businesspeople, Swedish chemists, Swedish engineers, Swedish inventors, Swedish Lutherans, Burials in Sweden
+Alexander Graham Bell	1847 births, 1922 deaths, 19th-century Scottish people, Alexander Graham Bell, Alumni of the University of Edinburgh, Alumni of University College London, American agnostics, American businesspeople, American educationists, American eugenicists, American inventors, American people of Scottish descent, American physicists, American Unitarians, Aviation pioneers, Canadian agnostics, Canadian Aviation Hall of Fame inductees, Canadian emigrants to the United States, Canadian eugenicists, Canadian inventors, Canadian people of Scottish descent, Canadian physicists, Canadian Unitarians, Elliott Cresson Medal recipients, Fellows of the American Academy of Arts and Sciences, History of telecommunications, IEEE Edison Medal recipients, Language teachers, Members of the American Philosophical Society, Members of the United States National Academy of Sciences, National Aviation Hall of Fame inductees, National Geographic Society, Officiers of the Légion d'honneur, People educated at the Royal High School, Edinburgh, People from Baddeck, Nova Scotia, People from Boston, Massachusetts, People from Brantford, People from Edinburgh, People from Washington, D.C., Scottish agnostics, Scottish businesspeople, Scottish emigrants to Canada, Scottish eugenicists, Scottish inventors, Scottish Science Hall of Fame, Scottish Unitarians, Smithsonian Institution people, Hall of Fame for Great Americans inductees, George Washington University trustee
+Anatolia	Anatolia, Ancient Greek geography, Geography of Turkey, Peninsulas of Asia, Physiographic provinces, Western Asia, World Digital Library related
+Apple Inc.	1976 establishments in California, Apple Inc., Companies based in Cupertino, California, Companies established in 1976, Computer companies of the United States, Computer hardware companies, Display technology companies, Electronics companies of the United States, Home computer hardware companies, Mobile phone manufacturers, Multinational companies headquartered in the United States, Networking hardware companies, Portable audio player manufacturers, Publicly traded companies of the United States, Electronics companies, Retail companies of the United States, Software companies based in the San Francisco Bay Area, Steve Jobs, Warrants issued in Hong Kong Stock Exchange, Technology companies of the United States
+Aberdeenshire	Council areas of Scotland, Aberdeenshire
+Aztlan Underground	Native American rappers, American rappers of Mexican descent, Musical groups from Los Angeles, California, Rapcore groups, West Coast hip hop musicians
+American Civil War	American Civil War, Rebellions in the United States, Wars involving the United States, 1860s in the United States, Wars of independence
+Andy Warhol	Andy Warhol, 1928 births, 1987 deaths, 20th-century American writers, 20th-century artists, 20th-century painters, Album-cover and concert-poster artists, American cinematographers, American contemporary artists, American Eastern Catholics, American experimental filmmakers, American film directors, American film directors of Hungarian descent, American film producers, American painters, American portrait painters, American people of Hungarian descent, American people of Lemko descent, American people of Slovak descent, American people of Rusyn descent, American pop artists, American printmakers, American screenwriters, American shooting survivors, American socialites, Artists from New York, Artists from Pittsburgh, Pennsylvania, Burials in Pennsylvania, Carnegie Mellon University alumni, Censorship in the arts, Counterculture of the 1960s, Deaths from myocardial infarction, Deaths from surgical complications, Fashion illustrators, Film directors from Pennsylvania, Gay artists, Gay writers, LGBT artists from the United States, LGBT Roman Catholics, LGBT directors, LGBT people from New York, LGBT people from Pennsylvania, LGBT producers, LGBT writers from the United States, Photographers from New York, Pop artists, Postmodern artists, Ruthenian Catholics, Schenley High School alumni, The Velvet Underground, Warhola family, Writers from New York, Writers from Pittsburgh, Pennsylvania
+Alp Arslan	1029 births, 1072 deaths, Seljuk rulers, Monarchs of Persia, Byzantine–Seljuq Wars, Murdered monarchs
+American Film Institute	1967 establishments in the United States, American Film Institute, Organizations established in 1967
+Akira Kurosawa	1910 births, 1998 deaths, People from Tokyo, Akira Kurosawa, Fellows of the American Academy of Arts and Sciences, Recipients of the Order of Culture, Recipients of the Praemium Imperiale, Recipients of the Order of Friendship of Peoples, Silver Bear for Best Director recipients, Academy Honorary Award recipients, Légion d'honneur recipients, Fukuoka Asian Culture Prize winners, Ramon Magsaysay Award winners, David di Donatello winners, Best Director BAFTA Award winners, César Award winners, People's Honour Award winners, Cardiovascular disease deaths in Japan, Deaths from stroke, Japanese film producers, Japanese film directors, Japanese screenwriters, Samurai film directors, Yakuza film directors, Asian film producers
+Ancient Egypt	Ancient Egypt, African civilizations, Former empires of Africa, States of Ancient Africa
+Analog Brothers	American hip hop groups, Ice-T
+Motor neuron disease	Motor neurone disease, Systemic atrophies primarily affecting the central nervous system, Rare diseases
+Abjad	Abjad writing systems, Arabic orthography
+Abugida	Abugida writing systems, Requests for audio pronunciation (English)
+ABBA	ABBA, Atlantic Records artists, Eurodisco groups, Eurovision Song Contest entrants of 1974, Eurovision Song Contest winners, Melodifestivalen contestants, Melodifestivalen winners, Musical groups disestablished in 1982, Musical groups established in 1972, Musical groups from Stockholm, Musical quartets, RCA Records artists, Rock and Roll Hall of Fame inductees, Swedish dance music groups, Swedish Eurovision Song Contest entrants, Swedish musical groups, Swedish pop music groups, Schlager groups, 1972 establishments in Sweden, Europop groups, Swedish-language singers
+Allegiance	Allegiance, Nationalism, Authoritarianism
+Altenberg	Place name disambiguation pages
+MessagePad	Apple Newton, Products introduced in 1993, Apple personal digital assistants
+A. E. van Vogt	1912 births, 2000 deaths, 20th-century American novelists, American male novelists, American science fiction writers, American short story writers, Canadian male novelists, Canadian science fiction writers, Canadian short story writers, Canadian expatriate writers in the United States, Deaths from Alzheimer's disease, Prometheus Award winners, SFWA Grand Masters, Science Fiction Hall of Fame inductees, Writers from Manitoba
+Anna Kournikova	1981 births, Living people, Australian Open (tennis) champions, Olympic tennis players of Russia, Sportspeople from Miami-Dade County, Florida, Russian emigrants to the United States, Russian female models, Russian female tennis players, Russian socialites, Sportspeople from Moscow, Tennis players at the 1996 Summer Olympics, Grand Slam (tennis) champions in women's doubles, Participants in American reality television series
+Alfons Maria Jakob	People from Aschaffenburg, German neurologists, German neuroscientists, German Roman Catholics, 1884 births, 1931 deaths
+Agnosticism	Agnosticism, Epistemological theories, Secularism, Philosophical movements, Philosophy of religion, Skepticism
+Argon	Argon, Chemical elements, Industrial gases, Noble gases
+Arsenic	Metalloids, Pnictogens, Toxicology, Chemical elements, Endocrine disruptors, Arsenic, IARC Group 1 carcinogens, Biology and pharmacology of chemical elements, Trigonal minerals, Teratogens, Fetotoxicants, Suspected testicular toxicants
+Antimony	Antimonide minerals, Antimony compounds, Chemical elements, Metalloids, Pnictogens, Antimony, Nuclear materials, Trigonal minerals
+Actinium	Chemical elements, Actinides, Actinium
+Americium	Actinides, Americium, Carcinogens, Chemical elements, Synthetic elements
+Astatine	Astatine, Chemical elements, Halogens, Metalloids, Articles containing Greek-language text
+Atom	Atoms, Concepts in physics, Chemistry
+Arable land	Agricultural land
+Aluminium	Aluminium minerals, Aluminium, Rocket fuels, Electrical conductors, Pyrotechnic fuels, Airship technology, Chemical elements, Post-transition metals, Reducing agents
+Advanced Chemistry	German hip hop groups
+Anglican Communion	1867 establishments in England, Religious organizations established in 1867, Anglicanism, Chalcedonianism, International bodies of denominations
+Arne Kaijser	1950 births, Living people, Swedish scholars and academics, Royal Institute of Technology academics, Members of the Royal Swedish Academy of Engineering Sciences, Historians of science, Historians of technology, Linköping University alumni
+Archipelago	Archipelagoes, Coastal and oceanic landforms, Islands
+Author	Writing occupations, Literary criticism
+Andrey Markov	1856 births, 1922 deaths, 19th-century Russian mathematicians, 20th-century mathematicians, Russian atheists, Russian mathematicians, Former Eastern Orthodox Christians, Probability theorists, Saint Petersburg State University alumni, Full Members of the St Petersburg Academy of Sciences, Full Members of the Russian Academy of Sciences (1917–25), People from Ryazan, Russian statisticians
+Angst	Anxiety, Emotions, Existentialist concepts
+Anxiety	Anxiety, Emotions, Mental states in Csikszentmihalyi's flow model
+A. A. Milne	1882 births, 1956 deaths, People from Hampstead, People from Kilburn, London, 20th-century British children's literature, 20th-century British novelists, Alumni of Trinity College, Cambridge, British Army personnel of World War I, Royal Warwickshire Fusiliers officers, English children's writers, English novelists, Members of the Detection Club, People educated at Westminster School, London, English poets, Winnie-the-Pooh, Deaths from stroke, English people of Scottish descent, Writers from London
+Asociación Alumni	Rugby clubs established in 1951, Argentine rugby union teams
+Axiom	Mathematical axioms, Mathematical terminology, Formal systems, Concepts in logic
+Alpha	Greek letters, Vowel letters
+Alvin Toffler	American male writers, American non-fiction writers, American science fiction writers, American technology writers, American futurologists, Transhumanists, Jewish American writers, People from Ridgefield, Connecticut, Radical centrist writers, Writers from Connecticut, 1928 births, Living people
+The Amazing Spider-Man	1963 comic debuts, Comics by J. Michael Straczynski, Comics by John Byrne, Comics by Mark Waid, Comics by Stan Lee, Comics by Steve Ditko, Spider-Man titles
+AM	Two-letter disambiguation pages
+Antigua and Barbuda	Antigua and Barbuda, Countries in the Caribbean, Constitutional monarchies, English-speaking countries and territories, Former British colonies, Island countries, Liberal democracies, Member states of the Caribbean Community, Member states of the Commonwealth of Nations, Member states of the United Nations, States and territories established in 1981
+Azincourt	Communes of Pas-de-Calais
+Albert Speer	Albert Speer, 1905 births, 1981 deaths, People from the Grand Duchy of Baden, People from Mannheim, 20th-century German architects, German people convicted of crimes against humanity, German people of World War II, German prisoners and detainees, German writers, Nazi architects, Historians of Nazism, Nazi Germany ministers, Nazi leaders, Neoclassical architects, Officials of Nazi Germany, People convicted by the International Military Tribunal in Nuremberg, SS officers, Technical University of Berlin alumni, Technische Universität München alumni, Karlsruhe Institute of Technology alumni, Members of the Reichstag of Nazi Germany, Recipients of the Golden Party Badge, Recipients of the Knights Cross of the War Merit Cross, Recipients of the Honour Chevron for the Old Guard
+Allioideae	Allioideae, Plant subfamilies
+Asteraceae	Asteraceae, Asterales families, Flowers
+Apiaceae	Asterid families, Apiaceae
+Axon	Neurons, Neurophysiology, Neuroanatomy
+Aramaic alphabet	Aramaic alphabet, Scripts encoded in Unicode 5.2
+American shot	Cinematography
+Acute disseminated encephalomyelitis	Multiple sclerosis, Autoimmune diseases, Neurological disorders, Enterovirus-associated diseases, Measles
+Ataxia	Symptoms and signs: Nervous system, Cerebral palsy types, Stroke
+Abdul Alhazred	Characters in short stories, Fictional alchemists, Fictional Arab people, Fictional characters introduced in 1924, Fictional writers, Mortals in the Cthulhu Mythos
+Ada Lovelace	1815 births, 1852 deaths, 19th-century English mathematicians, 19th-century women writers, Ada programming language, British computer scientists, British countesses, Burials in Nottinghamshire, Byron family, Cancer deaths in England, Computer designers, Daughters of barons, Deaths from uterine cancer, English computer programmers, English computer scientists, English people of Scottish descent, English scientists, English women poets, Lord Byron, Programming language designers, Women computer scientists, Women in engineering, Women in technology, Women mathematicians, Women of the Victorian era
+August Derleth	1909 births, 1971 deaths, University of Wisconsin–Madison alumni, American Christians, American short story writers, American mystery writers, 20th-century American novelists, Cthulhu Mythos writers, Guggenheim Fellows, American horror writers, People from Sauk County, Wisconsin, Writers from Wisconsin, Deaths from myocardial infarction, Science fiction editors, Solar Pons, Anthologists
+Alps	Alps, Mountain ranges of Europe, Mountains of Europe, Geography of Central Europe, Geography of Western Europe, Physiographic provinces
+Albert Camus	1913 births, 1960 deaths, 20th-century French novelists, 20th-century French philosophers, Albert Camus, Anarchist communists, Anarcho-pacifists, Anarcho-syndicalists, Anti-fascists, Atheist philosophers, Existentialists, French agnostics, French anarchists, French anti–death penalty activists, French atheists, French Communist Party members, French dramatists and playwrights, French essayists, French expatriates in Algeria, French humanists, French journalists, French Nobel laureates, French pacifists, French people of Spanish descent, French Resistance members, Légion d'honneur refusals, Modernist writers, Nobel laureates in Literature, People from Dréan, Pieds-Noirs, Road accident deaths in France, University of Algiers alumni
+Agatha Christie	Agatha Christie, 1890 births, 1976 deaths, 20th-century English writers, Dames Commander of the Order of the British Empire, Edgar Award winners, English crime fiction writers, English dramatists and playwrights, English mystery writers, English short story writers, British detective writers, Members of the Detection Club, English women dramatists and playwrights, Female wartime nurses, People from Cholsey, People from Sunningdale, People from Torquay, British women in World War I, Fellows of the Royal Society of Literature, Anthony Award winners, Women mystery writers, Booker authors' division, Burials in Oxfordshire, Writers of historical mysteries, World War I nurses, British women short story writers, British dramatists and playwrights, 20th-century British novelists, 20th-century women writers, English women novelists
+The Plague	1947 novels, Novels by Albert Camus, Absurdist fiction, Novels set in Algeria, Plague (disease), Éditions Gallimard books
+Applied ethics	Applied ethics, Ethics
+Absolute value	Special functions
+Analog signal	Analog circuits, Electronic design, Television terminology, Video signal
+Arecales	Palms, Angiosperm orders
+Hercule Poirot	Hercule Poirot, Characters in British novels of the 20th century, Fictional Belgian people, Fictional characters introduced in 1920, Fictional criminologists, Fictional police officers, Fictional private investigators, Hercule Poirot characters, Series of books
+Miss Marple	Miss Marple, Novel series, Fictional amateur detectives, Fictional English people, Fictional characters introduced in 1926, Characters in British novels of the 20th century
+April	Months, April
+August	Months, August
+Aaron	Ancient Egyptian Jews, Torah people, Christian saints from the Old Testament, Moses, Kohanim, Aaron, Book of Exodus, Biblical figures in Islam
+April 6	Days of the year, April
+April 12	Days of the year, April
+April 15	Days of the year, April
+

data/data/output_samples/testdata_ja_categories.txt

@@ -0,0 +1,48 @@
+アンパサンド	記号
+エスペラント	エスペラント, 人工言語
+言語	言語, 言語学, 民族
+日本語	日本語, Japanese language, 国語
+地理学	地理学
+欧州連合	欧州連合
+国の一覧	一覧, 国
+漫画	漫画, 娯楽, Comics
+日本	日本, 島国, 君主国
+フランス	France, フランス, G8加盟国
+パリ	フランスの都市, ローマ都市, パリ, イル＝ド＝フランス
+ヨーロッパ	ヨーロッパ
+ジミー・カーター	アメリカ合衆国の大統領, ノーベル平和賞受賞者, ジョージア州知事, ジョージア州の人物, 1924年生
+生物	生物, 地球, 地球史
+センタイ類	植物学, コケ植物
+社会学	社会学
+古代エジプト	古代エジプト, 考古学
+エジプト	エジプト, イスラム教国
+著作権の保護期間	著作権法
+東京	Tokyo, 東京都, 東京23区の地域, 関東地方, 日本の都市
+台東区	特別区, 台東区
+地理	地理, 教科
+生物学	Biology, 生物学, 自然科学, 理学
+社会	社会
+こどもの文化	子供の遊び, 子供, 育児
+特撮	特撮, SF, テレビドラマ
+日常生活	生活, 文化, 人の行動
+情報工学	情報工学, 情報学, 計算科学
+形式言語	言語学, 形式言語, 構文解析 (プログラミング)
+文脈自由言語	形式言語, 構文解析 (プログラミング)
+正規言語	形式言語
+自然言語処理	言語学, 自然言語処理
+自然言語	言語の分類, 言語学
+プログラミング言語	プログラミング言語, コンピュータ言語
+人工知能	情報工学, 人工知能, 心の哲学, ユーザインターフェイス (コンピュータ), SF
+オーストリア	オーストリア, 内陸国
+GNU Free Documentation License	ライセンス, 知的財産権, フリーソフトウェア財団
+社会学者の一覧	社会学者, 学者の人名一覧
+オランダ	オランダ, 君主国
+ゴーダチーズ	チーズ, オランダの食文化
+バールーフ・デ・スピノザ	オランダ史の人物, オランダの哲学者, ユダヤ教改革派, 破門, 17世紀の学者
+文脈自由文法	形式言語
+フランス語	フランス語, フランスの言語, カナダの言語, スイスの言語, ベルギーの言語, レバノンの言語, モロッコの言語, コンゴ共和国の言語, コンゴ民主共和国の言語, チュニジアの言語, カメルーンの言語, マリ共和国の言語, セネガルの言語, トーゴの言語, ルワンダの言語, ブルンジの言語, ベナンの言語, コートジボワールの言語, インド・ヨーロッパ語族
+イタリア語	イタリア語, イタリアの言語, インド・ヨーロッパ語族
+スペイン語	スペイン語, スペインの言語, アルゼンチンの言語, メキシコの言語, ボリビアの言語, チリの言語, コロンビアの言語, パラグアイの言語, ウルグアイの言語, イタリック語派
+宗教学	宗教学, 人文科学, 宗教
+音楽	Music, 音楽
+

data/lib/wp2txt/version.rb

@@ -1,3 +1,3 @@
 module Wp2txt
-  VERSION = "0.9.1"
+  VERSION = "0.9.4"
 end

data/lib/wp2txt.rb

@@ -6,6 +6,7 @@ $: << File.join(File.dirname(__FILE__))
 require "nokogiri"
 require "parallel"
 
+require 'etc'
 require 'pp'
 require "wp2txt/article"
 require "wp2txt/utils"
@@ -100,7 +101,7 @@ module Wp2txt
       if /.bz2$/ =~ @input_file
         unless NO_BZ2
           file = Bzip2::Reader.new File.open(@input_file, "r:UTF-8")
-          @parent.msg("WP2TXT is spawming #{@num_threads} threads to process data \n", 0)         
+          @parent.msg("WP2TXT is spawning #{@num_threads} threads to process data \n", 0)         
           @parent.msg("Preparing ... This may take several minutes or more ", 0)         
           @infile_size = file_size(file)
           @parent.msg("... Done.", 1)
@@ -112,7 +113,7 @@ module Wp2txt
           else
             file = IO.popen("bzip2 -c -d #{@input_file}") 
           end
-          @parent.msg("WP2TXT is spawming #{@num_threads} threads to process data \n", 0)         
+          @parent.msg("WP2TXT is spawning #{@num_threads} threads to process data \n", 0)         
           @parent.msg("Preparing ... This may take several minutes or more ", 0)         
           @infile_size = file_size(file)
           @parent.msg("... Done.", 1)

data/wp2txt.gemspec

@@ -25,5 +25,5 @@ Gem::Specification.new do |s|
   s.add_dependency "nokogiri"
   s.add_dependency "parallel"
   s.add_dependency "htmlentities"
-  s.add_dependency "trollop"
+  s.add_dependency "optimist"
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: wp2txt
 version: !ruby/object:Gem::Version
-  version: 0.9.1
+  version: 0.9.4
 platform: ruby
 authors:
 - Yoichiro Hasebe
-autorequire: 
+autorequire:
 bindir: bin
 cert_chain: []
-date: 2018-01-10 00:00:00.000000000 Z
+date: 2022-07-29 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: nokogiri
@@ -53,7 +53,7 @@ dependencies:
       - !ruby/object:Gem::Version
         version: '0'
 - !ruby/object:Gem::Dependency
-  name: trollop
+  name: optimist
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
@@ -84,7 +84,9 @@ files:
 - bin/benchmark.rb
 - bin/wp2txt
 - data/output_samples/testdata_en.txt
+- data/output_samples/testdata_en_categories.txt
 - data/output_samples/testdata_ja.txt
+- data/output_samples/testdata_ja_categories.txt
 - data/testdata_en.bz2
 - data/testdata_ja.bz2
 - lib/wp2txt.rb
@@ -99,7 +101,7 @@ files:
 homepage: http://github.com/yohasebe/wp2txt
 licenses: []
 metadata: {}
-post_install_message: 
+post_install_message:
 rdoc_options: []
 require_paths:
 - lib
@@ -114,9 +116,8 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubyforge_project: wp2txt
-rubygems_version: 2.6.13
-signing_key: 
+rubygems_version: 3.3.7
+signing_key:
 specification_version: 4
 summary: Wikipedia dump to text converter
 test_files: