Git-Mirrors/textfiles-politics
1
0
Fork 0
mirror of https://github.com/nhammer514/textfiles-politics.git synced 2024-12-25 07:19:31 -05:00
Code Issues Packages Projects Releases Wiki Activity
main
textfiles-politics/pythonCode/main.py

1677 lines
122 KiB
Python
Raw Permalink Normal View History

created main.py with code
2023-03-27 17:14:07 -04:00
import spacy
cleaning files
2023-04-30 18:35:36 -04:00
from spacy.pipeline import EntityRuler
created main.py with code
2023-03-27 17:14:07 -04:00
from collections import Counter
modifed main.py to test regex lib
2023-03-27 18:22:30 -04:00
import re as regex
created main.py with code
2023-03-27 17:14:07 -04:00
import os
improved main.py, can wrap all names in document now
2023-03-31 13:41:41 -04:00
from saxonche import PySaxonProcessor
main.py outputs new files and wraps elements around tokens
2023-03-29 14:22:05 -04:00
#### Loads all of the necessary variables and functions.
cleaning files
2023-04-30 18:35:36 -04:00
#nlp = spacy.cli.download("en_core_web_lg")
main.py outputs new files and wraps elements around tokens
2023-03-29 14:22:05 -04:00
nlp = spacy.load("en_core_web_lg")
cleaning files
2023-04-30 18:35:36 -04:00
#########################################################################################
# ebb: After reading the NLP output, we know spaCy is making some mistakes.
# So, here let's try adding an EntityRuler to customize spaCy's classification. We need
# to configure this BEFORE we send the tokens off to nlp() for processing.
##########################################################################################
# Create the EntityRuler and set it so the ner comes after, so OUR rules take precedence
# Sources:
# W. J. B. Mattingly: https://ner.pythonhumanities.com/02_01_spaCy_Entity_Ruler.html
# spaCy documentation on NER Entity Ruler: https://spacy.io/usage/rule-based-matching#entityruler
config = {"spans_key": None, "annotate_ents": True, "overwrite": True, "validate": True}
ruler = nlp.add_pipe("span_ruler", before="ner", config=config)
# 2023-04-07: ebb: NOTE: before="ner" setting seems to allow the spaCy NER rules to prevail over these patterns where
# there is a conflict.
# after="ner" means that the spaCy NER is TOTALLY OVERWRITTEN and invalidated by our patterns.
# Notes: Mattingly has this: ruler = nlp.add_pipe("entity_ruler", after="ner", config={"validate": True})
# But this only works when spaCy doesn't recognize a word / phrase as a named entity of any kind.
# If it recognizes a named entity but tags it wrong, we correct it with the span_ruler, not the entity_ruler
patterns = [
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "^-\w+?"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "^.$"}}]},
# ebb: Don't match on any single characters!
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "\^+"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "^\w\w$"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "^[a-z]+ [a-z]+$"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "^.*?__{2,}.*?$"}}]},
{"label": "NORP", "pattern": [{"TEXT": {"REGEX": "CHRISTIAN(ITY|DOM)?"}}]},
{"label": "NORP", "pattern": [{"TEXT": {"REGEX": "CHRISTIAN NETWORK"}}]},
{"label": "NORP", "pattern": [{"TEXT": {"REGEX": "Catholic(ism)?"}}]},
{"label": "NORP", "pattern": [{"TEXT": {"REGEX": "Zion(is[tm])?"}}]},
{"label": "NORP", "pattern": [{"TEXT": {"REGEX": "Juda(ism)?"}}]},
{"label": "NORP", "pattern": [{"TEXT": {"REGEX": "Jew(s|ish)?"}}]},
{"label": "GPE", "pattern": [{"TEXT": {"REGEX": "Vatican"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "(IBM|CIA|FBI)"}}]},
# ebb: Pick up IBM, FBI, etc
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "(Bush|Reagan|Kennedy|Nixon|Ford|Carter|Eisenhower) Administration"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "[A-Z]{2,}[A-Z][a-z]+"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "[a-z]{2,}[A-Z][a-z]+"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "^.*?[a-z][A-Z].*?$"}}]},
# ebb: Above line attempts to stop matching things like Oak IslandThe Method
{"label": "NULL", "pattern": [{"TEXT" : {"REGEX": "^[Mm\-]+$"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "\w+cia\w+"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "fed\w+"}}]},
# SOCIALISMBY RICHARD
# ebb: Above line attempts to stop matching things Mmm-mm or mm , etc.
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "TITIOUS CONCEPTS"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "TORTIOUS"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "THROUGHWAYS"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "TARGET"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "NULL"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Sympathisers"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Sympathy"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "UNTIL"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "UNCLE"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "VCI"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "VISUALIZATION"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "YOGA"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "ack Canfield"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "aurem concepisti"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Xref"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Wspomnienia"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Untrustworthy"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Twelve Apostles"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Tsar"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Treasurer"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Thunderer"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Thou raisest"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Thou cleansest"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Thou castest"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "This Leopold the Traitor"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Swore"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Swastika"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Superstrings"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Subj"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Subterrene"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Sts"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Strength"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Sol Deus Invictus"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Skis"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Sect"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Sen"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Senza Aristotele noi"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Salubrious Living"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Saint vouches"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Safehaven"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "SURPRISED"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "SURE"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "SUCCESSIVE"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "SUBSEQUENT"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "STUNTS"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "STREAMLINED"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "SPECULATION"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "SPECULA"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "SOVEREIGN"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "SHOCKED"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "SEPT"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "SAVIOR"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Roman Emperor"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Revelation"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Resurrection Bone"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Relearning"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Reason"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Read again Knocking the Key Weapon"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Rea"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "RESOLVE"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "RESALE"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "REBELS"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "RATIFICATION"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Qui"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Priest"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Price"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Popes"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Place"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Philosophizing"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Pharmacopaeia"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Pharaoh"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Pauline Privilege"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Paul the Persecutor"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Page"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Pagan Fathers"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "PWs"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "PROPAGANDA"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "PRIVILEGES"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "PRIOR RESTRAINT"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "PRINCE satropic"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "PRESERVATION"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "POPE"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Obersturmbannfuehrer"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Obersturmbannfuehrer Brandt"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Obersturmbannfuehrer Eichmann"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Obersturmbannfuehrer Liebehenschel"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Obersturmbannfuehrer Rauff"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Obersturmbannfuehrer Rodl"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Obersturmbannfuehrer Sievers"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Obersturmbannfuehrer Walter Rauff"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "OPIUM CULTIVATION"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Nutshell"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Numberless"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Num"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Northwest"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Northshore"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Northeast"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Ngo Dinh Diem"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Ngo Din Diem"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Nay"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "NAZI CARTEL"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "NATURE"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Msgr"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Mother Goose"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Ministerially"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Martial Law Threat"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Marquis Who"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Mapmakers"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Mao"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "MIllbourn"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "MEDLEY"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "MAR"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Lop"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "LYINGLY FOUNDED"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Law"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "LAW"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Keys"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "KOD"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Juifs"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Judo"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Joseph the Carpenter"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Jerome arraigns"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Jack Built"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "JUDAICA"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "JURIS"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "JOINT"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "JHVH"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "JESUS THE"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "JESUS DIED"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Izvestiya VUZ"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Iron Shins"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Iren"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Infotechnology"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Inerrancy"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Imprimatur"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Imposture"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Implore"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Immortale Dei"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Illuminatus Lanz"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Illiterates Illiterates"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "INTELLECTUALS"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "IMMOVABLE"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "IMMIGRANT AZIZ Rehman"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "ILLUNINATI USE MAFIAS"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Hun"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Hoo boy"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Holy Virginity"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Holy Vehm"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Hoc Signo"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "His Covenant"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Henry the Navigator"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Heathens don"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "auptsturmfuehrer Truehe"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Hauptscharfuehrer Ruebe"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Hamstring Yugo"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "HYPERSPACE"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "HUMANE"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "HEED"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "HEARINGS"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Guillotine"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Grupenfuehrer Globocnik"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Gruppenfuehrer Katzmann"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Groom"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Gregory the Great"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Grammarians"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Grammar"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Gospel"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Gort"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Goebbelesque"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Godhead"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Girkalinei Comm"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Geschichte der Staatstheorien"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Genus Shamanensis"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Genius"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Gene Pool"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Gemeter"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Gaude Virgo"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Gamel Abdul Nasser"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Gameplayers"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Galicie Ukrainienne"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Gal"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "GUNJAMMER"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "GUILTY"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "GREED"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "GRAMS"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "GOVERNORS"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "GENIUS"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "GAER"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Furness"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Free Inq"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Foxx"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Foo Fighters"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Fig"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Figs"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Feverfew"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Feathers"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Fathers"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "FUNC"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "FOUO"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "FILES KIT"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "FEVERFEW"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "FHK"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Exodus"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Eur"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Epistle clxvi"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Epistle"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Enfranchised"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Endothermic"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Encyc"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Encloged"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Emperor"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Emperor Vespasian"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Electromagnetically"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Ecclesiastici Publici"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Eccles"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Ebrietatis Enconium"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "EXTRAORDINAIRE"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "EXPATRIATION"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "EPISTLES"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "ENORMOUS"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "EMPLOY"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Dupes"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Dueling Spymasters"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Dual Amiga"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Driver"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Dritte Reich"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Drang nach Osten"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Dorman"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Don sez"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Divinatione Daemonorum"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Distinguished paedagogists"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Dies irae"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Die Geschichte von Joel Brand"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Dew"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Deut"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Desert Rat"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Deregulatory Creep"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Der Weg des Politischen Katholizismus"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Depository"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Debasement"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Death Ray"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Das Sogenannte Boese"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "CORRUPT"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "COMMISSIONED THE UNDERSIGNED"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "CLEARFIELD"}}]},
{"label": "WORK_OF_ART", "pattern": [{"TEXT": {"REGEX": "Pagan Sibylline Oracles"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "CIRCUMSTANTIAL"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "CDT"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "CANNOT"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "BATF"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "BEEN"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "BLACKMAIL"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "BOURGEOIS GENTILHOMME"}}]},
{"label": "GPE", "pattern": [{"TEXT": {"REGEX": "Bagdad"}}]},
{"label": "LAW", "pattern": [{"TEXT": {"REGEX": "Balfour Declaration"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Battle"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Biblical"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Bishop"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Blade Runner"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Blackmail"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Blessing"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Briefly"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Brigadefuehrer"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Brigadefuehrer Globocnik"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Brigadefuehrer Gluecks"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Brigadefuehrer Zenner"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Brigadefuhrer Richard Glucks"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Brigadefuehrer"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Brigadefuhrer"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "CREATORS"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Cap"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Capitula Angilrammi"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Case"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Charles Mentesana Filmed"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Chillingworth"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Christian Pope"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Chronicles xxviii"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Coddled Omar Abdel Rahman"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Chronicles xxxiv"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Clem"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Commrce"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Corinthians"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Cosi"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Crucifixion"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Czar"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "DECRETALS"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "DECAY"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "DEPLETION"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "DISASTROUS THAN PEARL"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "DISEASES"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "DOPE"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Damit Ich"}}]},
{"label": "WORK_OF_ART", "pattern": [{"TEXT": {"REGEX": "Pagan Oracles"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Deceits"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Deep Cover"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Demagnetize"}}]},
{"label": "WORK_OF_ART", "pattern": [{"TEXT": {"REGEX": "Mona Lisa"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Demigod"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Demjanjuk"}}]},
{"label": "NORP", "pattern": [{"TEXT": {"REGEX": "Democratic Centralism"}}]},
{"label": "WORK_OF_ART", "pattern": [{"TEXT": {"REGEX": "Mein Kampf"}}]},
{"label": "WORK_OF_ART", "pattern": [{"TEXT": {"REGEX": "Mary Magdalin Gospel"}}]},
{"label": "WORK_OF_ART", "pattern": [{"TEXT": {"REGEX": "Horst Wessel Song"}}]},
{"label": "WORK_OF_ART", "pattern": [{"TEXT": {"REGEX": "Fama Fraternitatis"}}]},
{"label": "NORP", "pattern": [{"TEXT": {"REGEX": "Physiocrats"}}]},
{"label": "NORP", "pattern": [{"TEXT": {"REGEX": "Pagan"}}]},
{"label": "NORP", "pattern": [{"TEXT": {"REGEX": "Meo"}}]},
{"label": "NORP", "pattern": [{"TEXT": {"REGEX": "PAGAN"}}]},
{"label": "NORP", "pattern": [{"TEXT": {"REGEX": "Obersturmfuehrer"}}]},
{"label": "NORP", "pattern": [{"TEXT": {"REGEX": "MARTYRS"}}]},
{"label": "NORP", "pattern": [{"TEXT": {"REGEX": "Jurisconsults"}}]},
{"label": "NORP", "pattern": [{"TEXT": {"REGEX": "Jewess"}}]},
{"label": "NORP", "pattern": [{"TEXT": {"REGEX": "Jeremiads"}}]},
{"label": "NORP", "pattern": [{"TEXT": {"REGEX": "Jehovah's Witnesses"}}]},
{"label": "NORP", "pattern": [{"TEXT": {"REGEX": "Jehovah's Witness"}}]},
{"label": "NORP", "pattern": [{"TEXT": {"REGEX": "Jehovahs Witness"}}]},
{"label": "NORP", "pattern": [{"TEXT": {"REGEX": "JURORS"}}]},
{"label": "NORP", "pattern": [{"TEXT": {"REGEX": "Heathens"}}]},
{"label": "NORP", "pattern": [{"TEXT": {"REGEX": "Gypsy"}}]},
{"label": "NORP", "pattern": [{"TEXT": {"REGEX": "Geronimo Chiricahua Apache"}}]},
{"label": "NORP", "pattern": [{"TEXT": {"REGEX": "Gauleiter"}}]},
{"label": "NORP", "pattern": [{"TEXT": {"REGEX": "Frankists"}}]},
{"label": "NORP", "pattern": [{"TEXT": {"REGEX": "Framers"}}]},
{"label": "NORP", "pattern": [{"TEXT": {"REGEX": "Framer"}}]},
{"label": "NORP", "pattern": [{"TEXT": {"REGEX": "Felloweraft"}}]},
{"label": "NORP", "pattern": [{"TEXT": {"REGEX": "Evangelist"}}]},
{"label": "NORP", "pattern": [{"TEXT": {"REGEX": "Egotists"}}]},
{"label": "NORP", "pattern": [{"TEXT": {"REGEX": "Duce"}}]},
{"label": "GPE", "pattern": [{"TEXT": {"REGEX": "Babylon(ia)?"}}]},
{"label": "NORP", "pattern": [{"TEXT": {"REGEX": "Diluvian Patriarchs"}}]},
{"label": "NORP", "pattern": [{"TEXT": {"REGEX": "Christiani ty"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "CAIB"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "the .+?"}}]},
{"label": "NORP", "pattern": [{"TEXT": {"REGEX": "Infidels"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Christiani"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "MAHAT"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Mahat"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Atta Boy"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Assailants"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Assassinated Robert"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Article"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Adrift"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "MAD"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "bacchanalian"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "behests"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Parallel"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": ""}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "the user"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "NETWORK"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Attemps"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Foundation"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Iena"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "attemps"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "pgh"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Christiani"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "MAHAT"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Mahat"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "MAD"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Parallel"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "the user"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "NETWORK"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Attemps"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Iena"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "attemps"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Advanced"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Believability"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Onesuch"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "the People"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "REPRINT"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "The Next Banking Crisis"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Incidently"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Martini Glass"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Customs"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "the Sheriff"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Greets"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "bey"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "conven"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Pro"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "THUS"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "TUNED CIRCUT"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "the supreme end"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Ebe"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Big Government"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "State"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "pseudoscientists"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "undam"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "News"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Times"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "PERIODICALS"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "SPEECHES"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "INCLUSION"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "MAJESTY"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "interpet"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "manifesta"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "aspetic"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "mish"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "petros"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "shevirat"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "sanguinis"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "resop"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "tryed"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "quandry"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "imbeds"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "germain"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "orleans"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "tgg"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Families"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "preparingits"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "germain"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "wintry"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "trogan"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Interested"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Time"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "ACTUALLY"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "ACCIDENTALLY"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "The Transmission"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "contra"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Mental Health"}}]},
{"label": "LAW", "pattern": [{"TEXT": {"REGEX": "Bill of Rights"}}]},
{"label": "LAW", "pattern": [{"TEXT": {"REGEX": "MCCARREN ACT"}}]},
{"label": "LAW", "pattern": [{"TEXT": {"REGEX": "Emergency Detention Act"}}]},
{"label": "LAW", "pattern": [{"TEXT": {"REGEX": "Geneva Convention"}}]},
{"label": "LAW", "pattern": [{"TEXT": {"REGEX": "Official Secrets Act"}}]},
{"label": "LAW", "pattern": [{"TEXT": {"REGEX": "Executive Order"}}]},
{"label": "LAW", "pattern": [{"TEXT": {"REGEX": "American Press freedom"}}]},
{"label": "LAW", "pattern": [{"TEXT": {"REGEX": "State Constitution"}}]},
{"label": "LAW", "pattern": [{"TEXT": {"REGEX": "Constitution"}}]},
{"label": "LAW", "pattern": [{"TEXT": {"REGEX": "Martial Law"}}]},
{"label": "LAW", "pattern": [{"TEXT": {"REGEX": "Martial Rule"}}]},
{"label": "LAW", "pattern": [{"TEXT": {"REGEX": "Unalienable Rights"}}]},
{"label": "LAW", "pattern": [{"TEXT": {"REGEX": "Alaska Mental Health Bill"}}]},
{"label": "LAW", "pattern": [{"TEXT": {"REGEX": "Multilateral Protection of War Victims/Prisoners of War"}}]},
{"label": "LAW", "pattern": [{"TEXT": {"REGEX": "Multilateral Protection of War Victims/Civilian Persons"}}]},
{"label": "LAW", "pattern": [{"TEXT": {"REGEX": "Public Health Service Draft Act"}}]},
{"label": "LAW", "pattern": [{"TEXT": {"REGEX": "Uniform Mental Health Act"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Executive Order #[0-9]+"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Median"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Next"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Daily"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "the General"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Diplomatic"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "televi"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "patsy"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "mike"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "MODIFY"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Nations"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "substanti"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "audi"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Justice"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Cancer"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Natural causes"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "PLATO"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "darksuckers"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Darksuckers"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "MAJESTY"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "SNOWBIRD"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "GARNET"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "AGL"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "DELTA"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "the King"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "EXCALIBUR"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "the secret control group"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "JASON"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Heart"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "sentatives"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Peter Gregory Original"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Billy Lovelady Depository"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "The World"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "John Holbrook Psychiatrist"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Paul Mandal Life"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Jackson Life Magazine"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Drug"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "thou mayest"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "thou eatest"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Unity movement"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Conn"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "intel"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "xxx xxxxx"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Xxxxxx Xxxxxxxx"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Xxxxxxx Xxxxxxx"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Wie hoch"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "WOULDN"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Waar"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "WCH"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "WCR"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "yeldeth ben"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "zwite Aufseher"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "wuz"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "beeb"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "duetschen Juden"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "bison"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "enim pejor"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "enshroud"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "entorce"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "epidemica"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "blasphemously"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "bull dudu"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "bowie asst"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "canonizes"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "clarinews"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "columno"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "complicitly"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "conspiracy buff"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "creo"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "decrepid"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Motor Collision"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "pro tem"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Electrotherapeutic"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "megs"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "JRD"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "The Wealth"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "state"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Trade"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Atomic"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Expo"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "looney"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "the Kingdom"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )??Office of Strategic Services"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Life Magazine"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Seattle Post Intellegencer"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "Industrias Cardoen"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "di"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "VENTURE"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "ALLEGED REAGAN"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Constitu"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "econonic aid"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Edgar Hoover"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "fed"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Apollo Astronauts"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "the Temple"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "CONNECTED WACKENHUT CORP"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "GREAT"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Lung"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "the Bill"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Said"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "CAPACITOR"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "SPARK"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "DAMPED"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "ANEW"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "THEREBY REDUCING EFFICIENCY"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "HOWEVER"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "TAPPED"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "ELECTRICALLY"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "ELECTRODE"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "TUNED CIRCUT"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "WAVELENGTH"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "HORIZONTALLY"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "THE OUDIN PRIMARY"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "AUTOTRANSFORMER"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "the Allied"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "the National"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Cheez Whiz"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "the Rich Discover Worthy"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Examiner"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "msen"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "ORG"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Physics A\. Mathematical"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "PALE"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Operation"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Order"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Command"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "jackboots"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "DARK"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "COLD"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Long Range"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "\S+@\S+\.\S+"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Human Behavior"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "SINCE LAWYERS OCCUPY"}}]},
{"label": "WORK_OF_ART", "pattern": [{"TEXT": {"REGEX": "Digha Nikaya"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "(Ludwig [Vv]an )?Beethoven"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Falangist"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Future of Freedom Foundation"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Congressional committee"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?The Federal Bureau of Prisons"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?American Red Cross"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Annals of Internal Medicine"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Houston Post"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "MKULTRA"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "KTOK"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Houston Chronicle"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Concentration Camp Program"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Operation Garden Plot"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?federal government"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?British intelligence"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?JASON SOCIETY"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Composite Service Organization"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Psychological Operations Organization"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Council on Foreign Relations"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Dept\. of Defense"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Mental Health Institution"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Dept\. of Transportation"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Dept\. of Justice"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?L\.E\.A\.F\."}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "Junio Valerio Black Prince Borghese"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Las Vegas Bullet"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?C\.I\.A\."}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?J\.C\. Penney"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?[Aa]-albionic Research"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Law Enforcement Assistance Force"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Young Americans for Freedom"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Military Police Unit"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Annals"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Inslaw"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "WACL"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "JDL"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "SJG"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "LEAA"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "Newe Anthropologie"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "NSTAC"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "NEWSBYTES"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "NDPC"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "National Democratic Policy Committee"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "National Security Telecommunications Advisory Committee"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "Tom Davis Research"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Civil Affairs Operations"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Civil Affairs Organization"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Big Brother"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Big brother"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?State Youthful Offenders Division"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?The California State Bar's Standing Committee on Professional Responsibility and Conduct"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?ILLUMINATI"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Crystic Institute"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Crystic institute"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?New World Order"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Roundtables"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Club of Rome"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Tri-lateral Commission"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Committee of 300"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Alaska Bar Association"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Rose Law Firm"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?University of Wisconsin"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?University of Southern California"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?ROTC"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Plunge"}}]},
{"label": "EVENT", "pattern": [{"TEXT": {"REGEX": "Fifth International Martin Luther King Tribunal"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Bayshore Inn"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Los Angeles Sheriff's Dept\."}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?U\.N\. Security Council"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?U\.N\."}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Daily Telegraph"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Alternative 3"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Library of Congress"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?International Congress on Mental health"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?National Academy of Sciences"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?U\. S . Secret Service"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Office of Thrift Supervision"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Comptroller of the Currency"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Urban Plunge"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Institute of Atmospheric Physics"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?State Department"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?National Libertarian Party"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Libertarian Party"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Bank of England"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Dept\. of State"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?United Grand Lodge"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Board of General Purposes"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?National Recon Organization"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?G\.S\.A\."}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?United States Military Establishment"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?State Dept\."}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Sapata Oil"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?California National Guard"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?H\.U\.D\."}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Royal Bank of Canada"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Bank of Montreal"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Rockefeller Bank"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?American Express"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Loeb Company"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?H\.E\.W\."}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?U\.S\. Senate"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Institute of Political Studies"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?law enforcement"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Housing & Urban Development"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Dept\. of Education"}}]},
{"label": "NORP", "pattern": [{"TEXT": {"REGEX": "Dropa"}}]},
{"label": "NORP", "pattern": [{"TEXT": {"REGEX": "Fria Ord"}}]},
{"label": "NORP", "pattern": [{"TEXT": {"REGEX": "Haitian"}}]},
{"label": "NORP", "pattern": [{"TEXT": {"REGEX": "Astronauts"}}]},
{"label": "NORP", "pattern": [{"TEXT": {"REGEX": "ISHVARA"}}]},
{"label": "NORP", "pattern": [{"TEXT": {"REGEX": "Wehrwirtschaftsfuehrer"}}]},
{"label": "NORP", "pattern": [{"TEXT": {"REGEX": "Viet Cong"}}]},
{"label": "NORP", "pattern": [{"TEXT": {"REGEX": "Egyptian"}}]},
{"label": "NORP", "pattern": [{"TEXT": {"REGEX": "Lybian"}}]},
{"label": "NORP", "pattern": [{"TEXT": {"REGEX": "Cuban"}}]},
{"label": "NORP", "pattern": [{"TEXT": {"REGEX": "Japanese"}}]},
{"label": "NORP", "pattern": [{"TEXT": {"REGEX": "Nicaraguan"}}]},
{"label": "NORP", "pattern": [{"TEXT": {"REGEX": "African"}}]},
{"label": "NORP", "pattern": [{"TEXT": {"REGEX": "Indian"}}]},
{"label": "NORP", "pattern": [{"TEXT": {"REGEX": "Icelandic"}}]},
{"label": "NORP", "pattern": [{"TEXT": {"REGEX": "Russian"}}]},
{"label": "NORP", "pattern": [{"TEXT": {"REGEX": "CANADIAN"}}]},
{"label": "NORP", "pattern": [{"TEXT": {"REGEX": "Clandestinism"}}]},
{"label": "NORP", "pattern": [{"TEXT": {"REGEX": "SCIENTOLOGISTS"}}]},
{"label": "NORP", "pattern": [{"TEXT": {"REGEX": "Trilateralists"}}]},
{"label": "NORP", "pattern": [{"TEXT": {"REGEX": "Homo Sapiens"}}]},
{"label": "NORP", "pattern": [{"TEXT": {"REGEX": "Spaniard"}}]},
{"label": "NORP", "pattern": [{"TEXT": {"REGEX": "Freemason"}}]},
{"label": "NORP", "pattern": [{"TEXT": {"REGEX": "Freemson"}}]},
{"label": "NORP", "pattern": [{"TEXT": {"REGEX": "Freemasonry"}}]},
{"label": "NORP", "pattern": [{"TEXT": {"REGEX": "Masonic"}}]},
{"label": "LOC", "pattern": [{"TEXT": {"REGEX": "Vietnam Moratorium"}}]},
{"label": "LOC", "pattern": [{"TEXT": {"REGEX": "Homestead Air Force Base"}}]},
{"label": "LOC", "pattern": [{"TEXT": {"REGEX": "Moon"}}]},
{"label": "LOC", "pattern": [{"TEXT": {"REGEX": "Swartz Creek"}}]},
{"label": "LOC", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Marshall Fields"}}]},
{"label": "LOC", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Gulf of Mexico"}}]},
{"label": "LOC", "pattern": [{"TEXT": {"REGEX": "DREAMLAND"}}]},
{"label": "LOC", "pattern": [{"TEXT": {"REGEX": "Pharselis"}}]},
{"label": "LOC", "pattern": [{"TEXT": {"REGEX": "Northlake"}}]},
{"label": "LOC", "pattern": [{"TEXT": {"REGEX": "Oak Cliff"}}]},
{"label": "LOC", "pattern": [{"TEXT": {"REGEX": "Paddington station"}}]},
{"label": "LOC", "pattern": [{"TEXT": {"REGEX": "David Munson Air Base"}}]},
{"label": "LOC", "pattern": [{"TEXT": {"REGEX": "Southeast Asia"}}]},
{"label": "LOC", "pattern": [{"TEXT": {"REGEX": "Eielson Air Force Base"}}]},
{"label": "LOC", "pattern": [{"TEXT": {"REGEX": "U\.S\. Army Reserves"}}]},
{"label": "LOC", "pattern": [{"TEXT": {"REGEX": "Bay of Pigs"}}]},
{"label": "LOC", "pattern": [{"TEXT": {"REGEX": "US Air Force L\. Fletcher Prouty"}}]},
{"label": "LOC", "pattern": [{"TEXT": {"REGEX": "Bohemian Grove"}}]},
{"label": "LOC", "pattern": [{"TEXT": {"REGEX": "Broadway"}}]},
{"label": "LOC", "pattern": [{"TEXT": {"REGEX": "Mockingbird Lane"}}]},
{"label": "LOC", "pattern": [{"TEXT": {"REGEX": "Mockingbird"}}]},
{"label": "LOC", "pattern": [{"TEXT": {"REGEX": "LAOS"}}]},
{"label": "LOC", "pattern": [{"TEXT": {"REGEX": "Hyannisport"}}]},
{"label": "LOC", "pattern": [{"TEXT": {"REGEX": "Lop Nor"}}]},
{"label": "LOC", "pattern": [{"TEXT": {"REGEX": "Gross Wannsee"}}]},
{"label": "LOC", "pattern": [{"TEXT": {"REGEX": "Groom Lake"}}]},
{"label": "NORP", "pattern": [{"TEXT": {"REGEX": "North [A-Z][a-z]+"}}]},
{"label": "NORP", "pattern": [{"TEXT": {"REGEX": "Monk"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Northern"}}]},
{"label": "GPE", "pattern": [{"TEXT": {"REGEX": "Allanwood"}}]},
{"label": "GPE", "pattern": [{"TEXT": {"REGEX": "Roswell"}}]},
{"label": "GPE", "pattern": [{"TEXT": {"REGEX": "Westminster"}}]},
{"label": "GPE", "pattern": [{"TEXT": {"REGEX": "Portland"}}]},
{"label": "GPE", "pattern": [{"TEXT": {"REGEX": "Richmond"}}]},
{"label": "GPE", "pattern": [{"TEXT": {"REGEX": "Sacramento"}}]},
{"label": "GPE", "pattern": [{"TEXT": {"REGEX": "St Louis"}}]},
{"label": "GPE", "pattern": [{"TEXT": {"REGEX": "New Haven"}}]},
{"label": "GPE", "pattern": [{"TEXT": {"REGEX": "Milwaukee"}}]},
{"label": "GPE", "pattern": [{"TEXT": {"REGEX": "Little Rock"}}]},
{"label": "GPE", "pattern": [{"TEXT": {"REGEX": "Los Angeles"}}]},
{"label": "GPE", "pattern": [{"TEXT": {"REGEX": "Briton"}}]},
{"label": "GPE", "pattern": [{"TEXT": {"REGEX": "El Paso"}}]},
{"label": "GPE", "pattern": [{"TEXT": {"REGEX": "Columbia"}}]},
{"label": "GPE", "pattern": [{"TEXT": {"REGEX": "FORT HUNT"}}]},
{"label": "GPE", "pattern": [{"TEXT": {"REGEX": "Butte"}}]},
{"label": "GPE", "pattern": [{"TEXT": {"REGEX": "State College"}}]},
{"label": "GPE", "pattern": [{"TEXT": {"REGEX": "Williamsport"}}]},
{"label": "GPE", "pattern": [{"TEXT": {"REGEX": "Landsdale"}}]},
{"label": "GPE", "pattern": [{"TEXT": {"REGEX": "Newtown Square"}}]},
{"label": "GPE", "pattern": [{"TEXT": {"REGEX": "Allentown"}}]},
{"label": "GPE", "pattern": [{"TEXT": {"REGEX": "New Castle"}}]},
{"label": "GPE", "pattern": [{"TEXT": {"REGEX": "Beckley"}}]},
{"label": "GPE", "pattern": [{"TEXT": {"REGEX": "Alton"}}]},
{"label": "GPE", "pattern": [{"TEXT": {"REGEX": "Stubenville"}}]},
{"label": "GPE", "pattern": [{"TEXT": {"REGEX": "Buffalo"}}]},
{"label": "GPE", "pattern": [{"TEXT": {"REGEX": "Belleville"}}]},
{"label": "GPE", "pattern": [{"TEXT": {"REGEX": "Bloomington"}}]},
{"label": "GPE", "pattern": [{"TEXT": {"REGEX": "Carbondale"}}]},
{"label": "GPE", "pattern": [{"TEXT": {"REGEX": "Champaign"}}]},
{"label": "GPE", "pattern": [{"TEXT": {"REGEX": "Constitantinoble"}}]},
{"label": "GPE", "pattern": [{"TEXT": {"REGEX": "Rock Island"}}]},
{"label": "GPE", "pattern": [{"TEXT": {"REGEX": "Birmingham"}}]},
{"label": "GPE", "pattern": [{"TEXT": {"REGEX": "IRAQ"}}]},
{"label": "GPE", "pattern": [{"TEXT": {"REGEX": "CANADA"}}]},
{"label": "GPE", "pattern": [{"TEXT": {"REGEX": "ENGLAND"}}]},
{"label": "GPE", "pattern": [{"TEXT": {"REGEX": "Danvers"}}]},
{"label": "GPE", "pattern": [{"TEXT": {"REGEX": "GERMANY"}}]},
{"label": "GPE", "pattern": [{"TEXT": {"REGEX": "Montreal"}}]},
{"label": "GPE", "pattern": [{"TEXT": {"REGEX": "Canada"}}]},
{"label": "GPE", "pattern": [{"TEXT": {"REGEX": "Baltimore"}}]},
{"label": "GPE", "pattern": [{"TEXT": {"REGEX": "Anchorage"}}]},
{"label": "GPE", "pattern": [{"TEXT": {"REGEX": "Albuquerque"}}]},
{"label": "GPE", "pattern": [{"TEXT": {"REGEX": "Albany"}}]},
{"label": "GPE", "pattern": [{"TEXT": {"REGEX": "CORAL GABLES"}}]},
{"label": "GPE", "pattern": [{"TEXT": {"REGEX": "Washington,? D\.?C\.?"}}]},
{"label": "GPE", "pattern": [{"TEXT": {"REGEX": "Avon Park"}}]},
{"label": "GPE", "pattern": [{"TEXT": {"REGEX": "Mill Point"}}]},
{"label": "GPE", "pattern": [{"TEXT": {"REGEX": "El Reno"}}]},
{"label": "GPE", "pattern": [{"TEXT": {"REGEX": "Zagreb"}}]},
{"label": "GPE", "pattern": [{"TEXT": {"REGEX": "ZAGREB"}}]},
{"label": "LOC", "pattern": [{"TEXT": {"REGEX": "Whiskey Flat"}}]},
{"label": "LOC", "pattern": [{"TEXT": {"REGEX": "site S-4"}}]},
{"label": "LOC", "pattern": [{"TEXT": {"REGEX": "LUNA"}}]},
{"label": "LOC", "pattern": [{"TEXT": {"REGEX": "AREA 51"}}]},
{"label": "LOC", "pattern": [{"TEXT": {"REGEX": "El Salvador air base"}}]},
{"label": "LOC", "pattern": [{"TEXT": {"REGEX": "Greenville County"}}]},
{"label": "LOC", "pattern": [{"TEXT": {"REGEX": "Toyland"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Sunday"}}]},
{"label": "LOC", "pattern": [{"TEXT": {"REGEX": "Sun"}}]},
{"label": "LOC", "pattern": [{"TEXT": {"REGEX": "North Pole"}}]},
{"label": "LOC", "pattern": [{"TEXT": {"REGEX": "Qua Vieaf"}}]},
{"label": "LOC", "pattern": [{"TEXT": {"REGEX": "North Viet [Nn]am"}}]},
{"label": "LOC", "pattern": [{"TEXT": {"REGEX": "Owl's Nest"}}]},
{"label": "LOC", "pattern": [{"TEXT": {"REGEX": "Dachau"}}]},
{"label": "LOC", "pattern": [{"TEXT": {"REGEX": "Hill Billies"}}]},
{"label": "LOC", "pattern": [{"TEXT": {"REGEX": "Cave Man's"}}]},
{"label": "LOC", "pattern": [{"TEXT": {"REGEX": "Cherry Brook Valley"}}]},
{"label": "LOC", "pattern": [{"TEXT": {"REGEX": "Postbridge"}}]},
{"label": "LOC", "pattern": [{"TEXT": {"REGEX": "McDill Air Force Base"}}]},
{"label": "LOC", "pattern": [{"TEXT": {"REGEX": "Egland Air Force Base"}}]},
{"label": "GPE", "pattern": [{"TEXT": {"REGEX": "Nazareth"}}]},
{"label": "GPE", "pattern": [{"TEXT": {"REGEX": "Latin America"}}]},
{"label": "GPE", "pattern": [{"TEXT": {"REGEX": "GREAT BRITAIN"}}]},
{"label": "GPE", "pattern": [{"TEXT": {"REGEX": "U\.S\.S\.R"}}]},
{"label": "GPE", "pattern": [{"TEXT": {"REGEX": "New York City"}}]},
{"label": "GPE", "pattern": [{"TEXT": {"REGEX": "Soviet Union"}}]},
{"label": "GPE", "pattern": [{"TEXT": {"REGEX": "Viet Nam"}}]},
{"label": "GPE", "pattern": [{"TEXT": {"REGEX": "U\.S\.A\."}}]},
{"label": "GPE", "pattern": [{"TEXT": {"REGEX": "U\.S\."}}]},
{"label": "GPE", "pattern": [{"TEXT": {"REGEX": "U\.S"}}]},
{"label": "GPE", "pattern": [{"TEXT": {"REGEX": "Saudi Arabia"}}]},
{"label": "GPE", "pattern": [{"TEXT": {"REGEX": "Washington, DC"}}]},
{"label": "GPE", "pattern": [{"TEXT": {"REGEX": "the Vatican"}}]},
{"label": "GPE", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?British Empire"}}]},
{"label": "GPE", "pattern": [{"TEXT": {"REGEX": "Pennsylvania"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Warren Commission"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Tesla Electric Company"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Hahn group"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?U\.S\. Department of Health and Human Services"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?American Council of Life Insurance"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Health Insurance Association of America\."}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?U\.S\. District Court"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?United States Pacific Fleet"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Pacific Fleet"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?National Guard"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Christic Institute"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Nugan-Hand"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Military-Industrial complex"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Condon Committee"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "COMMUNICATIONS CANADA"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?ABC"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?CBS"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Unity movement"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Covert Action"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?General Electric"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?US Army"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?US Navy"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?London Underground"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?US Justice Department"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Sur Coester"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Colorado Springs Gazette"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?SoftQuad Inc\."}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?United Nations World Health Organization"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?World Health Organization"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?L\.E\.A\.A\."}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Justice Dept\."}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "(THE )?HOUSE JUDICIARY COMMITTEE"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Contemporary Research, Inc\."}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?British Government"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?House Select Committee on Assassinations"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Office of Criminal Justice Planning"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Dept\. of Defense of the United States"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Dept\. of Commerce"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?MAJIC"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "Mother Jones"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?W\.A\. Harriman & Co\."}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Securities C\. Commission"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Rockefeller Syndicate"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Dallas Citizens Council"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Round Table groups"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Devon Unidentified Flying Objects centre"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?San Francisco Sidewalk Astronomers Association"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Dartmoor Livestock Protection Society"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Animal Defence Society"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?U\.S\. Agriculture Department"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Perpetual Hidden Government"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Office of the Deputy Chief of Staff of Personnel"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Harriman Fifteen Corp\."}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Israeli secret service"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Bell Helicopter"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Eurocheque"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?MasterCard"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?CitiCorp"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Marconi company"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Marconi"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?NRO"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Illinois Bell Telephone Company"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?UFO Magazine"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?University of Toronto"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Taymar, Inc\."}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Kerr McGree Nuclear Corporation"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Edward R\. Murrow Center"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?American Ship and Commerce Corp\."}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?American government"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Silverado Savings & Loan"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?American Association for the Advancement of Science"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?G\.H\. Walker & Co\."}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Office of Preparedness"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?National Aeronautics and Space Agency"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Martin Marietta company"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?John Birch Society"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?U\.S\. government"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Cleveland Field Office"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "The John F\. Kennedy Center for the Performing Arts Education Program"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?United States government"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?National Institute of Agrarian Reform"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?National Institute of Mental Health"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?INRA"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Massachusetts Institute of Technology"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?International UFO Bureau"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?National Investigations Committee on Aerial Phenomena"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Dept\. of the Army"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?U\.S\. Air Force"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?University of Arizona"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Criminal Justice System"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Sheriffs Dept\."}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "Standard & Poors"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Federal Reserve"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?L\.E\.A\.A\. Newsletter"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Texas School Book Depository"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Senate Select Committee on Intelligence"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Senate Intelligence Committee"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?House Committee on Assassinations"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?House Committee"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?House Select Committee"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?House of Saud"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "Wackenhut"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "KPFA"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "WACKENHUT CORP"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?International Agency for Research on Cancer"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?The London Times"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "WACKENHUT"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Federal Emergency Management Agency"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Special Forces Unit"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Defense Central Index"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Joint Chiefs of Staff"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Federal Information Center"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?American Counter-intelligence Corps"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "CIC"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?British Establishment\."}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "[A-Z][a-z]+ ([A-Z]\. [A-Z][a-z]+)?(, Jr\.)"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "[A-Z][a-z]+ ([A-Z]\. [A-Z][a-z]+)?( Jr\.)"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "[A-Z][a-z]+ (([A-Z]\. )?[A-Z][a-z]+([A-Z][a-z]+)?)? Jr\."}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "[[A-Z][a-z]+ [A-Z]\. ([A-Z][a-z])?[A-Z][a-z]+"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Nostradameus"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Harrison Edward Livingstone"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "J\. Herbert Sawyer"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "L\. Harmon Zeigler"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "C\. Everett Koop"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Edward L\. van Roden"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Kirschbaum"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Raphael Shumacker"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Martin Marietta"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "DAVID MELLOR"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "J\. W\. Willmott"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "O'Neill"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "O'Neil"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "O'Neal"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Orsenigo"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Neil Bush"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "SWAMI VIVEKANANDA"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Morris Ellowitz"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Harry Thon"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "David Ferrie"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Darrell W\. Garner"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "David Goldstein"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Mona B\. Saenz"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Abraham Zapruder"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Clayton Fowler"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "WILLIAM L\. LAW"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Reynolds"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Marriner S. Eccles"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "H\.S\.M\. Coxeter"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "A\.D\. Bowie"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Phillip Geraci"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "E\.R\. Walthers"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "George McGann"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Perry Russo"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "JOHN PHILIP NICHOLS"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "SALVADOR ALLENDE"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "D\. CASOLARO"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "AFFIDAVIT"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Koreshan"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Koresh"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Carl Oglesby"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Earline Roberts"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Lee Bowers, Jr\."}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Locust"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Starmaster"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Nuri Al-Said"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Pamela Courson"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Jimmy Hendrix"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Faisal II"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Milton Cooper"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Mostafa A Abdelkader"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Abdul Llah"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Marc J\. Seifer"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "R\. J\. Biggar"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Stanford White"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "John Paul I"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "John Paul II"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Ensign Ball"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "O\.H\. Cril"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Crill"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "KRLL"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "KRLLL"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "EBE"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Rockefeller III"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "John D\. Rockefeller III"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Dennis DeConcini"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Phil Gramm"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "BILL HAMILTON"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Gramm"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "DeConcini"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Michael Emerling"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Rockefeller"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Johnston"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Dodd"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Laurence Rockefeller"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "John D\. Rockefeller"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "John D\. Rockefeller IV"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "John D\. Rockefeller, Jr\."}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "William H\. Draper III"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Eduardo"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "EARL W\. BRIAN"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "RICONOSCIUTO"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Ramakrishna"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Don Ecker"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "John Galt"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "C\.D\. Jackson"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "G\.H\. Walker III"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Daniel Gooch"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Ramses II"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Alexander II"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Alexander V"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Alexander IV"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Alexander VI"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Breck Wall"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "CARROLL QUIGLEY"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Swami Vivekananda"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "DOOLITTLE"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "James I"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Oswald II"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Oswald I"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Umberto I"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Nikola Tesla"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Tesla"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "C\. Hamilton Ellis"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Alfred Ely Beach"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Ed Vyrdolak"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Beach"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Lord Milner"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Agapetus I"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Agapetus II"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "C\. Victor Raiser II"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "C\.V\. Raiser II"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Boniface VIII"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Boniface VII"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Boniface III"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Boniface II"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Boniface VI"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Gonda"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Ollie North"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Oliver North"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Mr\. North"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "E\. Howard Hunt"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "MLK"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "RFK"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "O\. W\. Judd"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "C\.J\. Duffner"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "J\.P\. Morgan"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Richard II"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "James McDonald"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "McDonald"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Saunders"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Richard III"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "George Terwilliger III"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "C\.E\. Koop"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Callistus I"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Francis von Hapsburg"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Malcom X"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Paramahansa Yogananda"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Victor IV"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Carles C\. Messick III"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "John D\. Rockefeller IV"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "MARCONI"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Marconi"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Bill English"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Bill Cooper"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Charles W\. Bailey II"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Charles I"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Charles McKee"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Charles X"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Charles V"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Jerome I"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Mark I"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "John XXIII"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Ferdinand I"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Hillary( Rodham)? Clinton"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "(President|Bill) Clinton"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Clinton"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "Bill and Hillary Clinton"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Vincent Foster, jr\."}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Nicholas I"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Nicholas II"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Nicholas V"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Vespasian"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "John Zajac"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Sylvester I"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Sylvester II"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Engenius IV"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Philip IV"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Stephen II"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Stephen VI"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Pious X"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Honorius II"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Sergius III"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Adrian I"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Adrian VI"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "William F\. Hamilton III"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "James Baker III"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "William Stamps Farish III"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Elizabeth II"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Anacletus II"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Edward II"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Edward III"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Edward V"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Matthew XVI"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Vyrdolak"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Thothmes III"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Harry Hurt III"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Napoleon III"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Clement VIII"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Clement I"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Clement VI"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Clement IV"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Pius X"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Pius II"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Pius IX"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Pius XI"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Pius XII"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Leo IX"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Leo X"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Leo III"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Leo XIII"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Amenhotep IV"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Charles W\. Bailey II"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Constantine"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Tut-ankh-amen"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Sixtus V"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Sixtus IV"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Benedict XIV"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Benedict VI"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Benedict IX"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Benedict XV"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "George I"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "George III"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Gregory VII"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Gregory I"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Gregory XVI"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Gregory IX"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Constantine II"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Albert I"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Albert V\. Bryan Jr"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Alfonso XII"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Alfonso XIII"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Gustavus III"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Gustav III"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Felix III"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Valentinian III"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Innocent III"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Innocent IV"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Frederick, II"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Frederick II"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Theodosius I"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Henry VIII"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Henry VI"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Henry IV"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Louis IX"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Louis XVI"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Joseph II"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Catherine II"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "James D Bryant II"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Paul III"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Paul II"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Julius II"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Paul VI"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "William II"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "William III"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Baldwin II"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Urban VIII"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Charles Goodhue, III"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Edwin Meese, III"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Thomas Downing"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Thomas E\. Davis"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "J\.A\. Milteer"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Charles Cabell"}}]},
{'label': 'PERSON', 'pattern': [{'TEXT': {'REGEX': 'James "Bo" Gritz'}}]},
{'label': 'PERSON', 'pattern': [{'TEXT': {'REGEX': 'Mike "Chucky" Peters'}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "James Earl Ray"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Earl Wheeler"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "William S\. Thompson"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "S\. Rilling"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Ralph Paul"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Scott Weekly"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Ford, L\.H"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "A\. Vilenkin"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Renate Viebahn"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Lustick, Ian S\."}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Friedman, Robert I\."}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Howard Sprague"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Mark Clark"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Owen"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Theodore Shackley"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "DeLesseps Morrison"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Betty McDonald"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Clines"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "L\. F\. Prouty"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "L\. Fletcher Prouty"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Knight, Amy W\."}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Martindale"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "R\. Knox"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Leon Oswald"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "H\. Ross Perot"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Stanly R\. Larsen"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "L\.E\. Allen Jr\."}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "A\. Lewis"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "D\. Fleming"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "J\. Edgar Hoover"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "V\. Pirie"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Nancy B\."}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "(Ronald )?Reagan"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "P\. Gibbs"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "W\. Citrine"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "E\. Moore"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Lyndon Johnson"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "John( F\.)? Kennedy"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Zia ul-Haque"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Ronald Payne"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "R\. Muldoon"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "F\. Orr"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Frank H\. Schwable"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "R\. F\. Doyle"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "David Munson"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Frances Clark"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "G\. Gordon Broadbent"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "J\. Segal"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "F\. Brangwyn"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Luc Montagnier"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "A\. Luchaire"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "L\. Segal"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "R\. William Davis"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "William C\. Sullivan"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "William W\. Quinn"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "William R\. Pabst"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Oliver Nichelson"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "James Worrell, Jr\."}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Hank Suydam"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "William Pabst"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "G\. Maeferren"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Dian-Lanz"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Buria"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "North"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Ortho III"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Swami Nikhilananda"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Santo Trafficante"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Felix Rodreguez"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Stanly F\. Yoles"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "G\. B\. Chisholm"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Baron Kurt von Schroeder"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "George Bush"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Roland Harriman"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "John Foster Dulles"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Sherman Skolnick"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Francis G\. Powers"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Kenneth O'Donnell"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "J\.M\. English"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "William Sullivan"}}]},
{'label': 'PERSON', 'pattern': [{'TEXT': {'REGEX': 'C\.L\. "Lummie" Lewis'}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Garland Slack"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Billy Lovelady"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "John Holbrook"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Marguerite Oswald"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Andrew Cetti"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Will H\. Griffin"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Peter Gregory"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Harry Grindell-Matthews"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Grindell-Matthews"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Rosenholtz"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Karen Silkwood"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "N\. McQuire"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "William Highland"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Harriman"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "William Saxby"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Ellis O\. Briggs"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Daniel Ludwig"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Robert C\. Klowers"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Tatum B\. Laird"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "William F\. Buckley, Jr\."}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "William Randolph Hearst, Jr\."}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Justin Dart"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Larry McDonald"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Mac MacPherson"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "MacPherson"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Callen"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Lievense"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "CASTRO"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Erik Jonsson"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Charles E\. Allen"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Laurence H\. Shoup"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "David Rieff"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "David Rockefeller"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Diamond"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Donald DeFreeze"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "McGovern"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "McCarthy"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "John DiNardo"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Gyeorgos C\. Hatonn"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "John Connally"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Lyndon LaRouche"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "LaRouche"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "W\.H\. Bowart"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Alan H\. Belmont"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Alan Belmont"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Joseph C\. Ayres"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Lehrman"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "John McCone"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Al Haig"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "J\. Latimer Clark"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "T\. W\. Rammell"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Elizabeth II"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Martha Honey"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Vince Bielski"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Anton Chaitkin"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Dean Burch"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Burch"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Gaius Caesar"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Gaius Chaerea"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "McCone"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Richard Nixon"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "David Wise"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Zapruder"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Mortimer J\. Adler"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Angela Davis"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Segals"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "COLIN WALLACE"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Thomas B\. Ross"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "JACOB G\. HORNBERGER"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Bowart"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Frank H\. Schwable"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Billy Goodman"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Leonard Pullin"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "R\. J\. Biggar"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "David R\. Hunter"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Hugh Everett, III"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Sigmund Diamond"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "J\. Pierpont Morgan"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Montagnier"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "W\. Schmunger"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Mary Pat Flaherty"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Vince Bielski"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Lee Harvey Oswald"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Schmunger"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Stranglove"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "James Calcutt"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Florentine Giovanni Boccaccio"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Prescott Bush"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Maxwell"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Daniel Schorr"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Allard K\. Lowenstein"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Daniel Patrick Moynihan"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?National Institute of Health"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Department of Justice"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Yakuza"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "YAKUZA"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Citizens' Committee to Clean Up the Courts"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Bank of Criminals and Conspirators International"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?U\.S\. Department of Justice"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?U\.S\. Justice Department"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?FBI Field Office"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Bureau of Investigation"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Dallas Citizens Council"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?University of Maryland,"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Carnegie Corporation"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Katzenbach Committee"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Democratic Congress"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?National Endowment for Democracy"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Congress for Cultural Freedom"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Cambridge University Press"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Association of National Security Alumni"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Avon Books"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?American Psychiatric Association"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Ministry of Defence"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Ramparts Press"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Grove Press"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?National Association of Scholars"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Council on Foreign Relations"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Symbionese Liberation Army"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Washington Post"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Internal Revenue Service"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Terminate With Extreme Prejudice"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Center for Strategic and International Studies"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?School of Foreign Service"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?The Anglo-American Establishment"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Centre of Eternity"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Life magazine"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Full Disclosure Newspaper"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "North American Newspaper Alliance"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Trilateral Commision"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Ruling Elite"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?US Congress"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Church Committee"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?National Academy of Sciences"}}]},
{"label": "ORG", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Ramparts"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Bab"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Century"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "The Problem"}}]},
{"label": "LOC", "pattern": [{"TEXT": {"REGEX": "Air Force One"}}]},
{"label": "LOC", "pattern": [{"TEXT": {"REGEX": "Kingdom of God"}}]},
{"label": "LOC", "pattern": [{"TEXT": {"REGEX": "Grassy Knoll"}}]},
{"label": "LOC", "pattern": [{"TEXT": {"REGEX": "Frankfurt airport"}}]},
{"label": "LOC", "pattern": [{"TEXT": {"REGEX": "Dealey Plaza"}}]},
{"label": "LOC", "pattern": [{"TEXT": {"REGEX": "Central Africa"}}]},
{"label": "LOC", "pattern": [{"TEXT": {"REGEX": "Fort Detrick"}}]},
{"label": "LOC", "pattern": [{"TEXT": {"REGEX": "Area-51"}}]},
{"label": "LOC", "pattern": [{"TEXT": {"REGEX": "Clifton suspension bridge"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "mandkind"}}]},
{"label": "NULL", "pattern": [{"TEXT": {"REGEX": "Motor"}}]},
{"label": "MISC", "pattern": [{"TEXT": {"REGEX": "AIDS virus"}}]},
{"label": "MISC", "pattern": [{"TEXT": {"REGEX": "AIDS"}}]},
{"label": "MISC", "pattern": [{"TEXT": {"REGEX": "AIDS-1"}}]},
{"label": "MISC", "pattern": [{"TEXT": {"REGEX": "AIDS VIRUS"}}]},
{"label": "MISC", "pattern": [{"TEXT": {"REGEX": "Human Adult Leukemia virus"}}]},
{"label": "MISC", "pattern": [{"TEXT": {"REGEX": "LAV"}}]},
{"label": "MISC", "pattern": [{"TEXT": {"REGEX": "Malaria"}}]},
{"label": "MISC", "pattern": [{"TEXT": {"REGEX": "ARC"}}]},
{"label": "MISC", "pattern": [{"TEXT": {"REGEX": "HTLV-1"}}]},
{"label": "MISC", "pattern": [{"TEXT": {"REGEX": "HTLV-III"}}]},
{"label": "MISC", "pattern": [{"TEXT": {"REGEX": "HTLV"}}]},
{"label": "MISC", "pattern": [{"TEXT": {"REGEX": "HIV"}}]},
{"label": "MISC", "pattern": [{"TEXT": {"REGEX": "HIV virus"}}]},
{"label": "MISC", "pattern": [{"TEXT": {"REGEX": "Sheep Visna Virus"}}]},
{"label": "MISC", "pattern": [{"TEXT": {"REGEX": "Pneumocystis carinii pneumonia"}}]},
{"label": "MISC", "pattern": [{"TEXT": {"REGEX": "Kaposi's sarcoma"}}]},
{"label": "MISC", "pattern": [{"TEXT": {"REGEX": "Smallpox"}}]},
{"label": "MISC", "pattern": [{"TEXT": {"REGEX": "Polio"}}]},
{"label": "MISC", "pattern": [{"TEXT": {"REGEX": "Gunshot"}}]},
{"label": "MISC", "pattern": [{"TEXT": {"REGEX": "LSD"}}]},
{"label": "MISC", "pattern": [{"TEXT": {"REGEX": "Poison"}}]},
{"label": "MISC", "pattern": [{"TEXT": {"REGEX": "MHz"}}]},
{"label": "MISC", "pattern": [{"TEXT": {"REGEX": "TNT"}}]},
{"label": "MISC", "pattern": [{"TEXT": {"REGEX": "Acquired Immuno-Deficiency Syndrome"}}]},
{"label": "MISC", "pattern": [{"TEXT": {"REGEX": "Equal Opportunity Employer"}}]},
{"label": "MISC", "pattern": [{"TEXT": {"REGEX": "Visna"}}]},
{"label": "MISC", "pattern": [{"TEXT": {"REGEX": "visna"}}]},
{"label": "MISC", "pattern": [{"TEXT": {"REGEX": "visna virus"}}]},
{"label": "EVENT", "pattern": [{"TEXT": {"REGEX": "Korean War"}}]},
{"label": "EVENT", "pattern": [{"TEXT": {"REGEX": "National Jury Rights Day"}}]},
{"label": "EVENT", "pattern": [{"TEXT": {"REGEX": "Miranda Case"}}]},
{"label": "EVENT", "pattern": [{"TEXT": {"REGEX": "World War II"}}]},
{"label": "EVENT", "pattern": [{"TEXT": {"REGEX": "Second World War"}}]},
{"label": "EVENT", "pattern": [{"TEXT": {"REGEX": "KRISTALLNACHT"}}]},
{"label": "EVENT", "pattern": [{"TEXT": {"REGEX": "First World War"}}]},
{"label": "EVENT", "pattern": [{"TEXT": {"REGEX": "World War I"}}]},
{"label": "EVENT", "pattern": [{"TEXT": {"REGEX": "Parliament of Religions"}}]},
{"label": "EVENT", "pattern": [{"TEXT": {"REGEX": "JFK assassination"}}]},
{"label": "EVENT", "pattern": [{"TEXT": {"REGEX": "Apollo 14 mission"}}]},
{"label": "EVENT", "pattern": [{"TEXT": {"REGEX": "Apollo 11"}}]},
{"label": "EVENT", "pattern": [{"TEXT": {"REGEX": "([Tt]he )?Andrew Cetti Affair"}}]},
{"label": "EVENT", "pattern": [{"TEXT": {"REGEX": "Railway Mania"}}]},
{"label": "EVENT", "pattern": [{"TEXT": {"REGEX": "EVENT"}}]},
{"label": "EVENT", "pattern": [{"TEXT": {"REGEX": "CHRISTIAN ERA"}}]},
{"label": "EVENT", "pattern": [{"TEXT": {"REGEX": "ante-Niccne"}}]},
{"label": "EVENT", "pattern": [{"TEXT": {"REGEX": "Vietnam War"}}]},
{"label": "EVENT", "pattern": [{"TEXT": {"REGEX": "Project Red-light"}}]},
{"label": "EVENT", "pattern": [{"TEXT": {"REGEX": "Moon mission"}}]},
{"label": "EVENT", "pattern": [{"TEXT": {"REGEX": "UFO"}}]},
{"label": "EVENT", "pattern": [{"TEXT": {"REGEX": "Apollo 11"}}]},
{"label": "EVENT", "pattern": [{"TEXT": {"REGEX": "Johnson's war on poverty"}}]},
{"label": "MISC", "pattern": [{"TEXT": {"REGEX": "AIDS"}}]},
{"label": "NORP", "pattern": [{"TEXT": {"REGEX": "Chinesse"}}]},
{"label": "NORP", "pattern": [{"TEXT": {"REGEX": "Vietnamese"}}]},
{"label": "EVENT", "pattern": [{"TEXT": {"REGEX": "Identified Alien Crafts"}}]},
{"label": "EVENT", "pattern": [{"TEXT": {"REGEX": "IAC"}}]},
{"label": "NORP", "pattern": [{"TEXT": {"REGEX": "multiculturalists"}}]},
{"label": "NORP", "pattern": [{"TEXT": {"REGEX": "Vietnamese"}}]},
{"label": "NORP", "pattern": [{"TEXT": {"REGEX": "Anglo-Saxon"}}]},
{"label": "NORP", "pattern": [{"TEXT": {"REGEX": "Patriots"}}]},
{"label": "NORP", "pattern": [{"TEXT": {"REGEX": "Patriot"}}]},
]
ruler.add_patterns(patterns)
created main.py with code
2023-03-27 17:14:07 -04:00
workingDir = os.getcwd()
cleaning files
2023-04-30 18:35:36 -04:00
CollPath = os.path.join(workingDir, '../pre-src-xml')
outputPath = os.path.join(workingDir, '../src-xml')
main.py outputs new files and wraps elements around tokens
2023-03-29 14:22:05 -04:00
# Everything in original conspiracy directory.
created main.py with code
2023-03-27 17:14:07 -04:00
insideDir = os.listdir(CollPath)
print(insideDir)
main.py outputs new files and wraps elements around tokens
2023-03-29 14:22:05 -04:00
# Copies files in case they do not exist
def copyTextFiles(file):
content = []
# Reads the contents of file, and saves each line of file into the content array.
with open(CollPath + "/" + file, 'r', encoding='utf8') as inFile:
for line in inFile:
content.append(line)
improved main.py, can wrap all names in document now
2023-03-31 13:41:41 -04:00
print(" ~~~~~~~~~~~~~~~~~~~~~~~~~~~ copying " + file + " ~~~~~~~~~~~~~~~~~~~~~~~~~~~ ")
main.py outputs new files and wraps elements around tokens
2023-03-29 14:22:05 -04:00
inFile.close()
# With the contents copied, a loop will go through the array and write it all in a new file in output folder.
with open(outputPath + "/" + file, 'w', encoding='utf8') as f:
for line in content:
f.write(str(line))
created main.py with code
2023-03-27 17:14:07 -04:00
main.py outputs new files and wraps elements around tokens
2023-03-29 14:22:05 -04:00
# Function runs through the tokens of given file. Entities are stored in array, then returned. Called by regexFile().
created main.py with code
2023-03-27 17:14:07 -04:00
def entitycollector(tokens):
added comments to main.py
2023-03-31 15:01:49 -04:00
# creates a new file that includes all of the found entities.
cleaning files
2023-04-30 18:35:36 -04:00
with open('conspPERSON.txt', 'w') as f:
improved main.py, can wrap all names in document now
2023-03-31 13:41:41 -04:00
entities = {}
added comments to main.py
2023-03-31 15:01:49 -04:00
# goes through each entity in the token list.
improved main.py, can wrap all names in document now
2023-03-31 13:41:41 -04:00
for ent in sorted(tokens.ents):
cleaning files
2023-04-30 18:35:36 -04:00
entityInfo = [ent.text, ent.label_]
improved main.py, can wrap all names in document now
2023-03-31 13:41:41 -04:00
stringify = str(entityInfo)
f.write(stringify)
f.write('\n')
entities[ent.text] = ent.label_
added comments to main.py
2023-03-31 15:01:49 -04:00
# return all entities with its label and text.
modifed main.py to test regex lib
2023-03-27 18:22:30 -04:00
return entities
created main.py with code
2023-03-27 17:14:07 -04:00
main.py outputs new files and wraps elements around tokens
2023-03-29 14:22:05 -04:00
# Function runs regex through given file.
def regexFile(file):
improved main.py, can wrap all names in document now
2023-03-31 13:41:41 -04:00
fileDir = os.path.join(outputPath, file)
with PySaxonProcessor(license=False) as proc:
added comments to main.py
2023-03-31 15:01:49 -04:00
# grabs the original xml file and stores it in a variable for later. this some xquery bs
improved main.py, can wrap all names in document now
2023-03-31 13:41:41 -04:00
xml = open(fileDir, encoding='utf-8').read()
xp = proc.new_xpath_processor()
node = proc.parse_xml(xml_text=xml)
xp.set_context(xdm_item=node)
added comments to main.py
2023-03-31 15:01:49 -04:00
# xquery goes through original text, and stores it all in a single string.
improved main.py, can wrap all names in document now
2023-03-31 13:41:41 -04:00
xpath = xp.evaluate('//p ! normalize-space() => string-join()')
cleaning files
2023-04-30 18:35:36 -04:00
string = str(xpath)
added comments to main.py
2023-03-31 15:01:49 -04:00
# regex goes through the text and deletes anything that is not a letter or space.
cleaning files
2023-04-30 18:35:36 -04:00
cleanedText = regex.sub(r'[^A-z ]+', ' ', string)
cleanedText = regex.sub(r'\n+', ' ', cleanedText)
added comments to main.py
2023-03-31 15:01:49 -04:00
# gets the tokens of the clean text.
main.py outputs new files and wraps elements around tokens
2023-03-29 14:22:05 -04:00
tokens = nlp(cleanedText)
added comments to main.py
2023-03-31 15:01:49 -04:00
improved main.py, can wrap all names in document now
2023-03-31 13:41:41 -04:00
wrappedText = xml
added comments to main.py
2023-03-31 15:01:49 -04:00
# grabs all the entities in file and stores it in a list/array.
cleaning files
2023-04-30 18:35:36 -04:00
dictEntities = entitycollector(tokens)
added comments to main.py
2023-03-31 15:01:49 -04:00
# if anything exists in the list, the following code will run.
cleaning files
2023-04-30 18:35:36 -04:00
if dictEntities:
added comments to main.py
2023-03-31 15:01:49 -04:00
# it will check through each entity in the list and see its entity type. it is looking for "PERSON" tokens
# in this instance, which includes of nouns and names.
cleaning files
2023-04-30 18:35:36 -04:00
for entity in dictEntities.keys():
if dictEntities[entity] == "PERSON" or dictEntities[entity] == "LOC" or dictEntities[entity] == "ORG" or dictEntities[entity] == "GPE" or dictEntities[entity] == "NORP" or dictEntities[entity] == "EVENT" or dictEntities[entity] == "WORK_OF_ART":
added comments to main.py
2023-03-31 15:01:49 -04:00
# key_template variable is the elements we wrap around found instances.
cleaning files
2023-04-30 18:35:36 -04:00
key_template = "<ent type='" + dictEntities[entity] + "'>" + entity + "</ent>"
added comments to main.py
2023-03-31 15:01:49 -04:00
# loops through wrappedText until all entities are wrapped.
improved main.py, can wrap all names in document now
2023-03-31 13:41:41 -04:00
wrappedText = wrappedText.replace(entity, key_template)
added comments to main.py
2023-03-31 15:01:49 -04:00
# Saves newly wrapped elements and then writes it into new file.
improved main.py, can wrap all names in document now
2023-03-31 13:41:41 -04:00
with open(fileDir, 'w', encoding='utf8') as f:
f.write(wrappedText)
print("WRAPPING " + entity)
cleaning files
2023-04-30 18:35:36 -04:00
checkTags(file)
# ebb: Added above line to send the tagged file to the checkTags() function for cleaning.
main.py outputs new files and wraps elements around tokens
2023-03-29 14:22:05 -04:00
cleaning files
2023-04-30 18:35:36 -04:00
# This part of the code is a WIP.
# ebb: I just activated it, and it works! (Nice job.) I altered it just a bit. May need more regexes to match.
added comments to main.py
2023-03-31 15:01:49 -04:00
## It tries to find weird or invalid elements/tags and fix them.
def checkTags(file):
content = []
fileDir = os.path.join(outputPath, file)
with open(fileDir, 'r', encoding='utf8') as inFile:
for line in inFile:
content.append(line)
# With the contents copied, a loop will go through the array and write it all in a new file in output folder.
with open(fileDir, 'w', encoding='utf8') as f:
for line in content:
cleaning files
2023-04-30 18:35:36 -04:00
# match = regex.search(r"(<ent type='.+?'>[^<>]*?)<ent[^>]+?>([^<>]+?)</ent>([^<>]*?</ent>)", line)
# if match:
# print("broken line found, fixing...")
# ebb: NOTE: IF this function only processes a line when there's a regex match, we'd have a serious problem:
# we'd not output the rest of the file--only the cleaned matches. So the output files would be mostly empty!
# Better to just string-clean every line using regex.sub(). Where there's no regex match, no substitution will happen.
origLine = line
# newLine = regex.sub(r"(<ent type='.+?'>[^<>]*?)<ent[^>]+?>([^<>]+?)</ent>([^<>]*?</ent>)", r"\1\2\3",line)
# <spe<ent type='ORG'>cia</ent>l>
newLine = regex.sub(r"(</?spe)<ent type='ORG'>(cia)</ent>(l>)", r"\1\2\3", origLine)
newLine = regex.sub(r"([^>])(New\s+?York\s+?Times)([^<])", r"\1<ent type='ORG'>\2</ent>\3", newLine)
newLine = regex.sub(r"([^>])(British)([^<])", r"\1<ent type='NORP'>\2</ent>\3", newLine)
newLine = regex.sub(r"([^>])(New\s+?York(\s+?City)?)([^<])", r"\1<ent type='GPE'>\2</ent>\4", newLine)
newLine = regex.sub(r"<ent type='[A-z]+?'>(Sundays?)</ent>", r"\1", newLine)
newLine = regex.sub(r"<ent type='PERSON'>(North)</ent>([a-z]*\s+[A-Z][a-z]+)*", r"<ent type='LOC'>\1\2</ent>", newLine)
newLine = regex.sub(r"(North\s+o?f?\s*([A-Z][a-z]+\s+)+)", r"<ent type='LOC'>\1</ent>", newLine)
# newLine = regex.sub(r"(<)<ent type='ORG'>(di)</ent>(v>)", r"\1\2\3", newLine)
newLine = regex.sub(r"(<ent type='[A-z]+?'>[^<]*?)<ent type='[A-z]+?'>([^<]+?)</ent>([^<]*?</ent>)", r"\1\2\3", newLine)
newLine = regex.sub(r"(<ent type='[A-z]+?'>[^<]*?)<ent type='[A-z]+?'>([^<]+?)</ent>([^<]*?</ent>)", r"\1\2\3", newLine)
newLine = regex.sub(r"(<ent type='[A-z]+?'>[^<]*?)<ent type='[A-z]+?'>([^<]+?)</ent>([^<]*?</ent>)", r"\1\2\3", newLine)
newLine = regex.sub(r"(<ent type='[A-z]+?'>[^<]*?)<ent type='[A-z]+?'>([^<]+?)</ent>([^<]*?</ent>)", r"\1\2\3", newLine)
newLine = regex.sub(r"(<ent type='[A-z]+?'>[^<]*?)<ent type='[A-z]+?'>([^<]+?)</ent>([^<]*?</ent>)", r"\1\2\3", newLine)
newLine = regex.sub(r"(<ent type='[A-z]+?'>[^<]*?)<ent type='[A-z]+?'>([^<]+?)</ent>([^<]*?</ent>)", r"\1\2\3", newLine)
# ebb: I'm repeating the above just in case of the weird event of triple or quadruple nested <ent> tags in <ent> tags.
# We saw it happen on the LOTR project and running it through multiple passes of the above line ultimately got rid of them all
# preserving only the outermost tags.
newLine = regex.sub(r"(<ent type=')<ent type='ORG'>(ORG)</ent>('>)", r"\1\2\3", newLine)
newLine = regex.sub(r"(<ent type='[A-Z]+'>)<ent type='[A-Z]+'>(\w+)</ent><ent type='[A-Z]+'>(\w+)</ent>(</ent>)", "\1\2 \3\4", newLine)
newLine = regex.sub(r"(<ent type='[A-Z]+?'>)(\w+)\s+?(<ent type='[A-Z+?]'>)(\w+)(</ent>)(\w+)(<ent type='[A-Z]+?'>)(\w+)(</ent>)(</ent>)", r"\1\2 \4 \6 \8\9", newLine)
# ebb: Problem line below: eliminates <ent type="PERSON">John Kennedy</ent>'s
# newLine = regex.sub(r"<ent type='\w+'>(\w+)</ent>('\w)", r"\1\2", newLine)
#
# <spe<ent type='ORG'>cia</ent>l>
# <<ent type='ORG'>di</ent>v>
if origLine != newLine:
added comments to main.py
2023-03-31 15:01:49 -04:00
print("broken line found, fixing...")
cleaning files
2023-04-30 18:35:36 -04:00
print(origLine + "\n INTO.")
added comments to main.py
2023-03-31 15:01:49 -04:00
print(newLine)
cleaning files
2023-04-30 18:35:36 -04:00
f.write(str(newLine))
print("File checking finished.")
added comments to main.py
2023-03-31 15:01:49 -04:00
main.py outputs new files and wraps elements around tokens
2023-03-29 14:22:05 -04:00
for file in insideDir:
copyTextFiles(file)
improved main.py, can wrap all names in document now
2023-03-31 13:41:41 -04:00
regexFile(file)
added comments to main.py
2023-03-31 15:01:49 -04:00
#checkTags(file)
cleaning files
2023-04-30 18:35:36 -04:00
# ebb: You don't really want to activate checkTags here,
# because it would run over the untagged input files.
Reference in New Issue Copy Permalink