PHJ-OCR-Evaluation-and-Correction
In [1]:
%load_ext autoreload
In [2]:
%autoreload 2
In [3]:
from text2topics import reports
from text2topics import utilities
from text2topics import clean
import re
import os
from os import listdir
from os.path import isfile, join
import collections
In [4]:
%matplotlib inline
In [5]:
wordlist_dir = "/Users/jeriwieringa/Dissertation/drafts/data/word-lists"
wordlists = ["2016-12-07-SDA-last-names.txt",
"2016-12-07-SDA-place-names.txt",
"2016-12-08-SDA-Vocabulary.txt",
"2017-01-03-place-names.txt",
"2017-02-14-Base-Word-List-SCOWL&KJV.txt",
"2017-02-14-Roman-Numerals.txt",
"2017-03-01-Additional-Approved-Words.txt"
]
In [6]:
spelling_dictionary = GoH.utilities.create_spelling_dictionary(wordlists, wordlist_dir)
In [7]:
title = "PHJ"
In [8]:
base_dir = "/Users/jeriwieringa/Dissertation/text/text/2017-01-31-corpus-with-utf8-split-into-titles-cleaning/{}/".format(title)
Baseline¶
In [9]:
cycle = 'baseline'
In [10]:
stats = GoH.reports.overview_report(join(base_dir, cycle), spelling_dictionary, title)
Directory: /Users/jeriwieringa/Dissertation/text/text/2017-01-31-corpus-with-utf8-split-into-titles-cleaning/PHJ/baseline Average verified rate: 0.9485069283287639 Average of error rates: 0.06036458564763386 Total token count: 2897885
In [11]:
errors_summary = GoH.reports.get_errors_summary( stats )
GoH.reports.top_errors( errors_summary, 200 )
Out[11]:
[('-', 3311),
('m', 2671),
('d', 2283),
('¥', 2135),
("'", 1992),
('ñ', 1991),
('tion', 1419),
('con-', 1357),
('in-', 1275),
('e', 1273),
('re-', 1243),
('r', 1143),
('w', 1134),
('co', 1092),
('t', 1026),
('n', 969),
(')', 878),
('be-', 795),
('ex-', 740),
('g', 726),
('f', 721),
('de-', 691),
('com-', 656),
('ment', 649),
('dis-', 642),
('lb', 585),
('pro-', 507),
('x', 490),
('im-', 452),
('per-', 408),
('un-', 407),
('(', 404),
('tions', 379),
('pre-', 347),
('ful', 334),
('sub-', 329),
('ad-', 328),
('ñthe', 326),
('en-', 307),
('ments', 272),
('al-', 257),
('th', 255),
('*', 250),
('ap-', 249),
('ac-', 248),
('/', 238),
('oo', 229),
('ñselected', 228),
('ñsel', 227),
('ous', 225),
('mo', 225),
('pp', 223),
('sup-', 209),
('%', 207),
('to-', 201)]
Review Special Character Use¶
In [12]:
GoH.reports.tokens_with_special_characters(errors_summary)
Out[12]:
[('¥', 2135),
('ñ', 1991),
(')', 878),
('(', 404),
('ñthe', 326),
('*', 250),
('/', 238),
('ñselected', 228),
('ñsel', 227),
('%', 207),
('_', 180),
('+', 172),
('ñthis', 168),
('¡', 158),
('ñthese', 155),
(']', 154),
('•', 146),
('ña', 143),
("(misses')", 139),
("(ladies')", 124),
('ã', 123),
('\\', 111),
('¥¥', 102),
('=', 92),
('ñall', 92),
('ñby', 89),
('ñdr', 85),
('ñmrs', 82),
("(children's)", 81),
('societyñmrs', 80),
('societyñl', 78),
('(to', 74),
('ñone', 66),
('ô', 65),
('ñcomposed', 65),
('(the', 63),
('ñtake', 62),
('ñand', 55),
('ñmedical', 54),
('ñmr', 51),
('(and', 51),
('ñto', 51),
('(in', 48),
('ñex', 48),
('ñit', 47),
('ñin', 45),
('ñwe', 45),
('ñgood', 43),
('ñtwo', 41),
('ñan', 40),
('`', 39),
('ñnew', 39),
('ñboston', 39),
('(especially', 38),
('bandage)', 37),
('large)', 37),
('(monthly', 37),
('societyña', 37),
('(elastic)', 37),
('(which', 36),
('(continued', 36),
('(extra', 36),
('%x', 35),
('ñchristian', 35),
('ñmade', 35),
('ñfor', 35),
('bookñ', 34),
('(not', 34),
('(dyspeptic)', 34),
('ñslightly', 33),
('(or', 33),
('ñshortened', 33),
('ñthat', 33),
('societyñj', 33),
('(bosom)', 33),
('(poetry)', 32),
('ñj', 32),
('monthlyñdevoted', 32),
('ñmost', 31),
('societyñhattie', 31),
('o¡', 30),
('(size', 30),
('(i)', 30),
('societyñs', 30),
('[', 30),
('vermontñlizzie', 29),
('preventiveñsimple', 28),
('ñt', 28),
('societyñleroy', 28),
('zealandñinternational', 28),
('australiañecho', 28),
('corset)', 27),
('ñno', 27),
('virginiañamy', 27),
('ñmiss', 26),
('ñespecially', 26),
('[from', 26),
('societyñm', 25),
('}', 25),
('(diabetes)', 25),
('(i', 24),
('ñamerican', 24),
('islandñbernard', 24),
('(concluded', 24),
('ñed', 23),
('(as', 23),
('\\\\', 23),
('japanña', 23),
('ñst', 23),
('ñsame', 23),
('recipesñpost-paid', 23),
('¥¥¥', 22),
("dies')", 22),
('(la-', 22),
('africañinternational', 22),
('ñnot', 21),
('[the', 21),
('¥¥¥¥', 21),
('i)', 20),
('fasteningñwith', 20),
('ets)', 20),
('islandsñinternational', 20),
('ñamong', 20),
('ñe', 20),
('virginiañmrs', 20),
('(wheat)', 20),
('societyñc', 20),
('ñtroubles', 20),
('<', 19),
('(r)', 19),
('ñelder', 19),
('carolinañn', 18),
('ñwhat', 18),
('ñn', 18),
('ñbecause', 18),
('(of', 18),
('ñour', 18),
('ñdietetic', 18),
('ñif', 18),
('[supt', 17),
('ñjohn', 17),
('ñhow', 17),
('callñyour', 17),
('(a', 17),
('ñcook', 17),
('societyñjohn', 17),
('ñrev', 16),
("ñhall's", 16),
('englandñn', 16),
('ñpare', 16),
('ñis', 16),
('pennell=suydam', 16),
('ñhealth', 16),
('ñscientific', 16),
('water)', 16),
('ñfig', 16),
('ñpacific', 16),
('(if', 16),
('ñchicago', 16),
("ñladies'", 16),
('mechanicalñmassage', 15),
('ñfrom', 15),
('{no', 15),
('ñs', 15),
('societyñturner', 15),
('ñella', 15),
('ñdio', 15),
("(child'n's)", 15),
('ñherald', 15),
('movementsñmanual', 15),
('switzerlandñimprimerie', 15),
('ñboil', 15),
('dore)', 15),
('ñwhen', 14),
("¥'", 14),
('ñphiladelphia', 14),
('{', 14),
('louisianaña', 14),
('ñthree', 14),
('ñm', 14),
('ñjournal', 14),
('[superintendent', 14),
('ñbeat', 13),
('ñsoak', 13),
('(for', 13),
('ñwash', 13),
('(egypt)', 13),
('ñprepare', 13),
('resortñsteamers', 13),
('(b)', 13),
('societyñf', 13),
('menña', 13),
('ñhousekeeper', 13),
('(a)', 13),
('ñmary', 13),
('land)', 13),
('-¥', 12),
('(illustrated)', 12),
('(holy', 12),
('flordiañcharles', 12),
('switzerlandñ', 12),
('+r', 12),
('breathingñas', 12),
('ãã', 12),
('ñyes', 12),
('temperanceñembracing', 12),
('ñmanual', 12),
('societyñcharles', 12),
('it)', 12),
('(this', 12),
('ñsilicate', 12),
('(island', 12),
('societyñlock', 11),
('ñplease', 11),
('••', 11),
('t¥', 11),
('(mich', 11),
('floridañcharles', 11),
('germanyñl', 11),
("'¥", 11),
('columbiañu', 11),
('(from', 11),
('ñlondon', 11),
('pacificñn', 11),
('(some', 11),
('stateñj', 11),
('deming=', 11),
('ñi', 11),
('\ufeff', 11),
('to¥', 11),
('(c)', 11),
('temperance)', 11),
('ñantiseptic', 11),
('\\fully', 10),
('(t)', 10),
('ñprof', 10),
('ñpopular', 10),
('street)', 10),
('(n', 10),
('(no', 10),
('ñexchange', 10),
('#', 10),
('ñput', 10),
('(england)', 10),
('societyñclara', 10),
('—', 10),
('[physician', 10),
('¥-', 10),
('c)', 10),
('(literature', 10),
('/x', 10),
('¥the', 10),
('evilñsolitary', 10),
('ñbritish', 10),
('(incorporated)', 10),
('ñafter', 10),
('ñsanitary', 9),
('(one', 9),
('societyñeliza', 9),
('(fig', 9),
('ñf', 9),
('englandñthe', 9),
('(an', 9),
('ñc', 9),
('ñthere', 9),
('ó', 9),
('cineñpersonal', 9),
('ñof', 9),
("ñharper's", 9),
('pages)', 9),
('ñbut', 9),
('[director', 9),
('ñsubscribers', 9),
('(new', 9),
('ñsome', 9),
('ñkeep', 9),
('ñsacramento', 9),
('~~', 9),
('ñgerman', 9),
('dietñfruits', 9),
('ñfood', 9),
('crackersñthese', 9),
('`¥', 9),
('tennesseeñj', 9),
('(by', 9),
('caf\x8e', 9),
('echoñ', 9),
('ñdetroit', 9),
('itñ', 9),
('norwayñsundhedsbladet', 8),
('„', 8),
('¥a', 8),
('(that', 8),
('societyñw', 8),
('\\\\\\', 8),
('youñthat', 8),
('i¥', 8),
('**', 8),
('georgiañcharles', 8),
('ñh', 8),
('columbiañmr', 8),
('ñfirst', 8),
('(with', 8),
('senti\\el', 8),
('\\ve', 8),
('best)', 8),
('a¥', 8),
('(gen', 8),
('islandñe', 8),
('ñhe', 8),
('(dia-', 8),
('ñd', 8),
('ñen', 8),
('kentuckyñelsie', 8),
('betes)', 8),
('ñfarm', 8),
('(so', 8),
('ñprofessor', 8),
('canadañmrs', 8),
('ñl', 8),
('formsñreproductionñsexual', 8),
('englandñinternational', 8),
('ñmix', 8),
('ñmake', 8),
('(see', 8),
('£', 8),
('soeietyñs', 8),
('ñare', 8),
('(except', 8),
('societyñamelia', 8),
('¥¥¥¥¥', 8),
('societyñt', 8),
('ñthey', 8),
('ñshe', 7),
('them)', 7),
('ñmay', 7),
('ñsuch', 7),
('ñstew', 7),
('(though', 7),
('___', 7),
('teeth)', 7),
('yñeñsñbut', 7),
('ñhome', 7),
('ñr', 7),
('(signed)', 7),
('ñhall', 7),
('boysña', 7),
('ñwith', 7),
('(who', 7),
('ñsir', 7),
('lifeñthe', 7),
('societyñbox', 7),
('(h', 7),
('themñ', 7),
('ô¥', 7),
('ñabridged', 7),
('ñbread', 7),
('mothersñdiseases', 7),
('norwayñ', 7),
('ñmassage', 7),
('girlsña', 7),
('ñuse', 7),
('kentuckyñelder', 7),
('(including', 7),
('york)', 7),
('floridañlysle', 7),
('ñpeel', 7),
('-)', 6),
('lungsñprinciples', 6),
('¥and', 6),
('(such', 6),
('ñsigns', 6),
('ò', 6),
('addressñpacific', 6),
('carolinañelder', 6),
("ñpeople's", 6),
("(childrens')", 6),
('ñwhile', 6),
('(we', 6),
('(applause', 6),
('ñsix', 6),
('ñwhich', 6),
('xl%', 6),
('itña', 6),
('ñinternational', 6),
('ñrub', 6),
('societyñno', 6),
('womenña', 6),
('^', 6),
('ñselect', 6),
('the¥', 6),
('great)', 6),
('`the', 6),
('ñman', 6),
('forñ', 6),
('columbiañinternational', 6),
('ñhousehold', 6),
('ñunion', 6),
('¢', 6),
('ñjudge', 6),
('ñwhere', 6),
('womenñone', 6),
('ñmany', 6),
('stripe)', 6),
('ñnational', 6),
('ñwoman', 6),
('ñcan', 6),
('__', 6),
('ñheat', 6),
('englandñwm', 6),
('ñanon', 6),
('ñsunday', 6),
('sightñlittle', 6),
('oo¡', 6),
('[of', 6),
('miles)', 6),
('¤', 6),
('(lev', 6),
('(but', 6),
('ñforñ', 6),
('ñalcohol', 6),
('pacificñjohn', 6),
('gansñdescription', 6),
('all)', 6),
('viceña', 6),
('{service', 5),
('ñas', 5),
('ñsan', 5),
('ñwho', 5),
('protein)', 5),
('\\\\n', 5),
('alabamañc', 5),
('manhoodñdangers', 5),
('hygieneñunchastityñthe', 5),
('ñsex', 5),
('ñdress', 5),
('number_', 5),
('ñfive', 5),
('_health', 5),
('(formerly', 5),
('scotiañelder', 5),
('\\\\v', 5),
('(it', 5),
('(d)', 5),
("'`", 5),
('ñgolden', 5),
('c¥', 5),
('ñgirl', 5),
('ñlaws', 5),
('>', 5),
('¥-¥', 5),
('diseaseñ', 5),
('r¥', 5),
('years)', 5),
('post=paid', 5),
('montanañwalter', 5),
('stomachsñpoints', 5),
('manña', 5),
('parlor_', 5),
('ñjames', 5),
('ñnever', 5),
('marylandñelder', 5),
('journal)', 5),
('ñclara', 5),
('ñyou', 5),
('co¥', 5),
('ñgeorge', 5),
('{coolest', 5),
('(do', 5),
('ñatlanta', 5),
('ñmargaret', 5),
('man)', 5),
('ñcalifornia', 5),
('*the', 5),
('patientñ', 5),
('ailmentsñas', 5),
('ñtomatoes', 5),
('ñeat', 5),
('ñcongregationalist', 5),
('ñinto', 5),
('p¥', 5),
('ñcincinnati', 5),
('~', 5),
('¥/', 5),
('ñhave', 5),
('ñscience', 5),
('\\t', 5),
('(she', 5),
(')(', 5),
('(cal', 5),
('(she)', 5),
('motherñ', 5),
('/a', 5),
('ñ¤ñ', 5),
('\\v', 5),
('arizonañcol', 5),
('`i', 5),
('englandñpacific', 5),
('africañcharles', 5),
('ñvegetarian', 5),
('ñp', 5),
('(e)', 5),
('in¥', 5),
('(he', 5),
('ñelizabeth', 5),
('germsñof', 5),
('(nearly', 5),
('mississippiñc', 5),
('societyñfremont', 4),
('useñdiphtheria', 4),
('healthñ', 4),
('\\\\\\\\\\', 4),
('(when', 4),
('ñprov', 4),
('or¥', 4),
('ñpresent', 4),
('stateñn', 4),
('ñcause', 4),
('ñcut', 4),
('¥¥¥¥¥¥¥¥¥¥¥¥¥¥¥¥¥¥¥¥¥¥¥', 4),
('mississippiñelder', 4),
('guianañgeorge', 4),
('days)', 4),
("ñdon't", 4),
('better)', 4),
('¥for', 4),
('poisoningñtobacco-using', 4),
('ñillustrated', 4),
('himñ', 4),
('¥i', 4),
('ñwell', 4),
('ö', 4),
('ñthen', 4),
('l¥', 4),
('[this', 4),
('absorptionñ', 4),
('it¥', 4),
('ñannals', 4),
('answeredñalcoholic', 4),
('ñgod', 4),
('societyñh', 4),
('ñgrate', 4),
('t)', 4),
('goodñbut', 4),
('ñher', 4),
('/-', 4),
('ñold', 4),
('(about', 4),
('ñunder', 4),
('teacherñ', 4),
('woman)', 4),
('ñon', 4),
('answerñ', 4),
('a*', 4),
('ñemetic', 4),
('viceñetc', 4),
('ñjuvenile', 4),
('sabbathñschool', 4),
('coffeeñten', 4),
('i\\', 4),
('ñcrushed', 4),
('(front', 4),
('ñalcoholism', 4),
('wifeñ', 4),
('ñtemperance', 4),
('a/', 4),
("'/", 4),
('soldñnot', 4),
('tahitiñthe', 4),
('great]', 4),
('ñadvance', 4),
('age)', 4),
('(there', 4),
('ñcanadian', 4),
('ñevery', 4),
('ñphillips', 4),
('ñw', 4),
('-(no', 4),
('body)', 4),
('winter_', 4),
('notñ', 4),
('day)', 4),
('`if', 4),
('temperanceñalcohol', 4),
('offñand', 4),
('-ã', 4),
('be)', 4),
('(turner', 4),
('fairñ', 4),
('pacificñj', 4),
('t_', 4),
('andñ', 4),
('kindnessñoh', 4),
('childrenñwill', 4),
('ñphrenological', 4),
('montanañd', 4),
('againñ', 4),
('=-', 4),
('thatñ', 4),
('ñmilton', 4),
('wifeñif', 4),
('alabamañd', 4),
('want==', 4),
('too¡', 4),
('(x', 4),
('*a', 4),
('barbarismñevil', 4),
('ñbible', 4),
('ñdoes', 4),
('myñ', 4),
('ñhelen', 4),
('ñpeople', 4),
('(according', 4),
('ñedward', 4),
('of¥', 4),
(')-', 4),
('-¥-', 4),
('englandñs', 4),
('ñcertainly', 4),
('was)', 4),
('intemperanceñeffects', 4),
('\\n', 4),
('lifeñ', 4),
('noticeñspecial', 4),
('¥o', 4),
('tractsocietyñc', 4),
('(after', 4),
('ñrural', 4),
('-_', 4),
('is¥', 4),
('++++++++++++++++++++++++++++++', 4),
('/heart', 4),
('ñem-', 4),
('ñah', 4),
('poison)', 4),
('patentsñ', 4),
('illustratedñjust', 4),
('ú', 4),
('wellñcayenne', 3),
('ñthose', 3),
('tableña', 3),
('familyña', 3),
('ñcanon', 3),
('societyñmiss', 3),
('ñpresbyterian', 3),
('childrenñhygiene', 3),
('(k)', 3),
('zealandñiternational', 3),
('good)', 3),
('pacificñcharles', 3),
('cultureñ', 3),
('experiencesñvoiced', 3),
('valuesñyou', 3),
('(san', 3),
('above)', 3),
('***', 3),
('(all', 3),
('(enough', 3),
('pounds)', 3),
('ñcells', 3),
('gñ', 3),
('st)-', 3),
('ñb', 3),
('/t', 3),
('ñnothing', 3),
('ñbefore', 3),
('brown=fox', 3),
('ñplace', 3),
('ñpure', 3),
('societyñspringville', 3),
('nessñtea', 3),
('¥ñ', 3),
('appl/cat/on', 3),
('etry)', 3),
('canadañs', 3),
('itñcongressional', 3),
('waterfallsñpictures', 3),
('ñlook', 3),
('ñpeaches', 3),
('so)', 3),
('moreñ', 3),
('`thou', 3),
('louisianañelder', 3),
('(f)', 3),
('¥ô', 3),
('partñ', 3),
('examinedñinventory', 3),
('summer_', 3),
('@', 3),
('aloneñand', 3),
('v¥', 3),
('blossomñalcoholism', 3),
('ñpotatoes', 3),
('*extracts', 3),
('//', 3),
('ageña', 3),
('(detroit', 3),
('ñespeciall', 3),
('masterpieceñhow', 3),
('ñlight', 3),
('ñfather', 3),
('ñlowell', 3),
('a)', 3),
('oatsñgetting', 3),
('this¥', 3),
('ñtimes', 3),
('blindnessñscience', 3),
('(eng', 3),
('ñlancet', 3),
('(provided', 3),
('(h)', 3),
('se\\ti\\el', 3),
('societyñmelissa', 3),
('ñscald', 3),
('healthñhow', 3),
('rightsñthe', 3),
('healthñcare', 3),
('ñone-half', 3),
('grandeurñpeculiar', 3),
('ñjoseph', 3),
('thisña', 3),
('space]', 3),
('centsñprobably', 3),
('allñto', 3),
('societyñmts', 3),
('girlsñ', 3),
('mississippiñoscar', 3),
('ofñ', 3),
('pacificñc', 3),
('ñmuch', 3),
('surroundingsñthe', 3),
('pñ', 3),
('/i', 3),
('+t', 3),
('û', 3),
('divineñhow', 3),
('ñfigs', 3),
('(p', 3),
('ñse/', 3),
('_nteresting', 3),
('(sometimes', 3),
('ñmeasure', 3),
('child-cultureñ', 3),
('sinceñpioneer', 3),
('developmentña', 3),
('gasoline)', 3),
('mexicoñjohn', 3),
('australiañinternational', 3),
('condition)', 3),
('intemperanceñ', 3),
('dietñthe', 3),
('significationñthe', 3),
('influencesñlaw', 3),
('houseña', 3),
('state)', 3),
('histories)', 3),
('nuisanceñthe', 3),
('marredñmodesty', 3),
('¥ã', 3),
('sweetñ', 3),
('buchananñyes', 3),
('(yes', 3),
('ñwill', 3),
('discoveredñthe', 3),
('tastersñtea', 3),
('roomña', 3),
('case)', 3),
('ñjust', 3),
('ôii', 3),
('fever)', 3),
('-*', 3),
('himself)', 3),
('handñ', 3),
('congenersña', 3),
('examinedña', 3),
('o¥', 3),
('ñshould', 3),
('marriedñthe', 3),
('voiceñ', 3),
('ñlaura', 3),
('ñjoaquin', 3),
('¥by', 3),
('ñlittle', 3),
('monthñ', 3),
('(gas', 3),
('wombñ', 3),
('tr)', 3),
('idahoñelder', 3),
('ñnellie', 3),
('beforeñ', 3),
('wayñ', 3),
('(page', 3),
('year)', 3),
("cellarñwhat's", 3),
('ñkate', 3),
('inñ', 3),
('e¥', 3),
('(on', 3),
('us)', 3),
('switzerlandñelder', 3),
('food)', 3),
('(dress', 3),
('ñat', 3),
('back)', 3),
('ôvt', 3),
('formationñaltitude', 3),
('*parlor', 3),
('con_', 3),
('%*', 3),
('people)', 3),
('subjectñone', 3),
('molars)', 3),
('(these', 3),
('flour_', 3),
('ñbuds', 3),
('itñthat', 3),
('barbarismñtobacco', 3),
('(subject', 3),
('stomachñgin', 3),
('lovelinessñthe', 3),
('coffeeñpork', 3),
('pubertyña', 3),
('(sold', 3),
('ñsunday-school', 3),
('+++', 3),
('worldñman', 3),
('comfortñmakes', 3),
('liversña', 3),
('featuresñtheo-', 3),
('ñfrank', 3),
('ñhenry', 3),
('(through', 3),
('in_', 3),
('ñsee', 3),
('ñsturdy', 3),
('(he)', 3),
('dried)', 3),
('(looking', 3),
('ñposition', 3),
('ñsouthern', 3),
('societyñnew', 3),
('_a', 3),
('itñit', 3),
('ñmince', 3),
('ñtheir', 3),
('pen)', 3),
('vitalityñchildren', 3),
('t=', 3),
('¥e', 3),
('tipplingñtobacco', 3),
('airñhow', 3),
('(chap', 3),
('ñlawyer', 3),
('favorñits', 3),
('doctrineña', 3),
('coã', 3),
('xviiñdorsal', 3),
('()', 3),
('ñcor', 3),
('medicationñ', 3),
('adñ', 3),
('motherñimportant', 3),
('i%', 3),
("'ã", 3),
('poisoningña', 3),
('oneña', 3),
('vainñthe', 3),
('(j)', 3),
('ñeben', 3),
('iñi', 3),
('beñ', 3),
('rememberñthere', 3),
('mannersñsowing', 3),
('societyñwest', 3),
('\\vhy', 3),
("(don't", 3),
('ñdip', 3),
('instance)', 3),
('ñsurely', 3),
('houseñthe', 3),
('(common', 3),
('ñrecipes', 3),
('sugar)', 3),
('physicianñ', 3),
('declineñeconomy', 3),
('(plus', 3),
('foodsñthe', 3),
('ñbabyhood', 3),
('r)', 3),
('ñmail', 3),
('inhabitantsñthe', 3),
('[san', 3),
('(let', 3),
('ñnearly', 3),
('ñofñ', 3),
('lit¥', 3),
('bodyñthe', 3),
('sinsñerrors', 3),
('societyñn', 3),
('ñbreak', 3),
('myselfñas', 3),
('frie\\d', 3),
('(luke', 3),
('thoughtñ', 3),
('deo)', 3),
('g)', 3),
('ñshake', 3),
('profit)', 3),
('[or', 3),
('ñoil', 3),
('♦', 3),
('carolinañ', 3),
('i¡', 3),
("'ñ", 3),
('w_', 3),
('(silk', 3),
('suggestionsñante-natal', 3),
('com_', 3),
('ñwhy', 3),
('ñspread', 3),
('ñmilk', 3),
("`'", 3),
(')i', 3),
('sinñ', 3),
('deserveñreverently', 3),
('(babyhood)', 3),
('tuberculosisñits', 3),
('girlñ', 3),
('(unless', 3),
('poisonñtobacco', 3),
('sayñand', 3),
('ñ¥', 3),
('childñthe', 3),
('retreat)', 3),
('ñduring', 3),
('stillñ', 3),
('periodñimportant', 3),
('ex_', 3),
('•••', 3),
('(without', 3),
('ñemily', 3),
('ti)', 3),
('for_', 3),
('womenñsexual', 3),
('ciselyñyet', 3),
('topersñtea', 3),
('(white', 3),
('_-', 3),
('usingñthe', 3),
('ñ/', 3),
('ñenglish', 3),
('(-', 3),
('))', 3),
('zealandñedward', 3),
('summerñmap', 3),
('ñhouse-', 3),
('ñindeed', 3),
('nobodyñonly', 3),
('whileñ', 3),
("fasteningñcan't", 3),
('diseaseñtobacco-using', 3),
('bestñfor', 3),
('(illustrated', 3),
('ã\\', 3),
('smithñ', 2),
('tractsocietyñl', 2),
('countryñthe', 2),
('ñeliza', 2),
('sugars)', 2),
('(soft', 2),
('(they)', 2),
('entr\x8ee', 2),
('motherña', 2),
("ñwoman's", 2),
('bodyñfor', 2),
('brideñ', 2),
('ñjour-', 2),
('\\tg', 2),
('‘', 2),
('ñmaryland', 2),
('g¥', 2),
('result)', 2),
('¥s', 2),
('answerñthe', 2),
('____', 2),
('bread)', 2),
('worldlinessñwho', 2),
('dressingñin', 2),
('<<', 2),
('druggist)', 2),
(')s', 2),
('lit=', 2),
('(where', 2),
('affectionñare', 2),
('\\taining', 2),
('ñsteam', 2),
('(registration', 2),
('ñharriet', 2),
('millsñ', 2),
('norwayñsundhedsbiadet', 2),
...]
Correction 1 -- Normalize Special Characters¶
In [13]:
# %load shared_elements/normalize_characters.py
prev = "baseline"
cycle = "correction1"
directories = GoH.utilities.define_directories(prev, cycle, base_dir)
if not os.path.exists(directories['cycle']):
os.makedirs(directories['cycle'])
corpus = (f for f in listdir(directories['prev']) if not f.startswith('.') and isfile(join(directories['prev'], f)))
for filename in corpus:
content = GoH.utilities.readfile(directories['prev'], filename)
# Substitute for all other dashes
content = re.sub(r"—-—–‑", r"-", content)
# Substitute formatted apostrophe
content = re.sub(r"\’\’\‘\'\‛\´", r"'", content)
# Replace all special characters with a space (as these tend to occur at the end of lines)
content = re.sub(r"[^a-zA-Z0-9\s,.!?$:;\-&\'\"]", r" ", content)
with open(join(directories['cycle'], filename), mode="w") as o:
o.write(content)
o.close()
In [14]:
# %load shared_elements/summary.py
summary = GoH.reports.overview_report(directories['cycle'], spelling_dictionary, title)
Directory: /Users/jeriwieringa/Dissertation/text/text/2017-01-31-corpus-with-utf8-split-into-titles-cleaning/PHJ/correction1 Average verified rate: 0.9563835150945872 Average of error rates: 0.05139457898244834 Total token count: 2895740
In [15]:
# %load shared_elements/top_errors.py
errors_summary = GoH.reports.get_errors_summary( summary )
GoH.reports.top_errors( errors_summary, 10 )[:50]
Out[15]:
[('-', 3495),
('m', 2732),
('d', 2320),
("'", 2130),
('tion', 1424),
('e', 1371),
('con-', 1360),
('in-', 1275),
('re-', 1243),
('r', 1238),
('w', 1166),
('t', 1148),
('n', 1104),
('co', 1103),
('be-', 798),
('f', 775),
('g', 754),
('ex-', 744),
('de-', 692),
('com-', 658),
('ment', 652),
('dis-', 642),
('x', 639),
('lb', 585),
('pro-', 509),
('im-', 452),
('per-', 412),
('un-', 408),
('tions', 380),
('pre-', 347),
('ful', 334),
('ad-', 330),
('sub-', 329),
('en-', 308),
('ments', 272),
('th', 260),
('sel', 259),
('al-', 257),
('ap-', 250),
('ac-', 248),
('oo', 235),
('pp', 228),
('mo', 227),
('ous', 225),
('k', 210),
('sup-', 209),
('z', 206),
('to-', 201),
('u', 196),
('treat-', 196)]
Correction 2 -- Correct Line Endings¶
In [16]:
# %load shared_elements/correct_line_endings.py
prev = cycle
cycle = "correction2"
directories = GoH.utilities.define_directories(prev, cycle, base_dir)
if not os.path.exists(directories['cycle']):
os.makedirs(directories['cycle'])
corpus = (f for f in listdir(directories['prev']) if not f.startswith('.') and isfile(join(directories['prev'], f)))
for filename in corpus:
content = GoH.utilities.readfile(directories['prev'], filename)
content = re.sub(r"(\w+)(\-\s{1,})([a-z]+)", r"\1\3", content)
with open(join(directories['cycle'], filename), mode="w") as o:
o.write(content)
o.close()
In [17]:
# %load shared_elements/summary.py
summary = GoH.reports.overview_report(directories['cycle'], spelling_dictionary, title)
Directory: /Users/jeriwieringa/Dissertation/text/text/2017-01-31-corpus-with-utf8-split-into-titles-cleaning/PHJ/correction2 Average verified rate: 0.9782014724508072 Average of error rates: 0.030641413019329045 Total token count: 2851844
In [18]:
# %load shared_elements/top_errors.py
errors_summary = GoH.reports.get_errors_summary( summary )
GoH.reports.top_errors( errors_summary, 10 )[:50]
Out[18]:
[('-', 3480),
('m', 2730),
('d', 2320),
("'", 2130),
('e', 1370),
('r', 1235),
('w', 1166),
('t', 1146),
('n', 1104),
('co', 1101),
('f', 775),
('g', 753),
('x', 639),
('lb', 585),
('th', 260),
('sel', 251),
('oo', 235),
('pp', 228),
('mo', 227),
('k', 210),
('z', 206),
('u', 196),
("an'", 192),
('--', 189),
('-page', 133),
('q', 132),
('ournal', 103),
('society-', 100),
('al', 100),
("'tis", 87),
('te', 86),
('pa', 83),
('ex', 82),
('ro', 82),
('oz', 81),
("'the", 80),
('ga', 77),
('munn', 73),
('va', 73),
('io', 72),
('ti', 70),
("''", 66),
('tion', 63),
("infants'", 61),
('---', 60),
('id', 59),
('zo', 55),
('viperance', 54),
('si', 48),
('urnal', 48)]
Correction 3 -- Remove extra dashes¶
In [19]:
# %load shared_elements/remove_extra_dashes.py
prev = cycle
cycle = "correction3"
directories = GoH.utilities.define_directories(prev, cycle, base_dir)
if not os.path.exists(directories['cycle']):
os.makedirs(directories['cycle'])
corpus = (f for f in listdir(directories['prev']) if not f.startswith('.') and isfile(join(directories['prev'], f)))
for filename in corpus:
content = GoH.utilities.readfile(directories['prev'], filename)
text = re.sub(r"[0-9,!?$:;&]", " ", content)
tokens = GoH.utilities.tokenize_text(text)
replacements = []
for token in tokens:
if token[0] is "-":
replacements.append((token, token[1:]))
elif token[-1] is "-":
replacements.append((token, token[:-1]))
else:
pass
if len(replacements) > 0:
print("{}: {}".format(filename, replacements))
for replacement in replacements:
content = GoH.clean.replace_pair(replacement, content)
else:
pass
with open(join(directories['cycle'], filename), mode="w") as o:
o.write(content)
o.close()
PHJ18850601-V01-01-page1.txt: [('-MONTHLY', 'MONTHLY'), ('-', ''), ('TEMPER-', 'TEMPER')]
PHJ18850601-V01-01-page10.txt: [('Temperqee-', 'Temperqee')]
PHJ18850601-V01-01-page12.txt: [('-suppression', 'suppression')]
PHJ18850601-V01-01-page13.txt: [('-', ''), ('"--', '"-')]
PHJ18850601-V01-01-page15.txt: [('Tar-', 'Tar')]
PHJ18850601-V01-01-page16.txt: [('dis-', 'dis')]
PHJ18850601-V01-01-page17.txt: [('-ed', 'ed'), ('Lam-', 'Lam')]
PHJ18850601-V01-01-page19.txt: [('--', '-')]
PHJ18850601-V01-01-page2.txt: [('-wage', 'wage')]
PHJ18850601-V01-01-page21.txt: [('symp-', 'symp')]
PHJ18850601-V01-01-page23.txt: [('-a-', 'a-'), ('-s...se', 's...se'), ('-.', '.'), ('-...-', '...-'), ('----a', '---a'), ('-', ''), ('--', '-'), ('---', '--'), ('-', ''), ('-', ''), ('OTHER-', 'OTHER'), ('-', ''), ('-', '')]
PHJ18850601-V01-01-page24.txt: [('.-', '.'), ('-', ''), ('----', '---'), ('CAL.--', 'CAL.-')]
PHJ18850601-V01-01-page3.txt: [('care-', 'care')]
PHJ18850601-V01-01-page7.txt: [('-', '')]
PHJ18850601-V01-01-page9.txt: [('ap-', 'ap')]
PHJ18850801-V01-02-page11.txt: [('tre-', 'tre')]
PHJ18850801-V01-02-page23.txt: [('Library-', 'Library'), ('-', ''), ('-', '')]
PHJ18850801-V01-02-page24.txt: [('--', '-'), ('CAL.cp----', 'CAL.cp---'), ('-', ''), ('-......', '......'), ('-', ''), ('-IFIWWW', 'IFIWWW')]
PHJ18850801-V01-02-page7.txt: [('con-', 'con')]
PHJ18850801-V01-02-page8.txt: [('-', '')]
PHJ18851001-V01-03-page13.txt: [('--', '-')]
PHJ18851001-V01-03-page18.txt: [('-a-month', 'a-month')]
PHJ18851001-V01-03-page2.txt: [('-all', 'all'), ('table--', 'table-')]
PHJ18851001-V01-03-page23.txt: [('G-', 'G'), ('--', '-'), ('-', ''), ('-', '')]
PHJ18851001-V01-03-page24.txt: [('-', ''), ('-For', 'For'), ('iitslitrlifVit-', 'iitslitrlifVit'), ('Fig-', 'Fig')]
PHJ18851001-V01-03-page3.txt: [('per-', 'per'), ('dif-', 'dif')]
PHJ18851001-V01-03-page6.txt: [('sub-', 'sub'), ('Ameri-', 'Ameri')]
PHJ18851201-V01-04-page1.txt: [('-', ''), ('-n-.-', 'n-.-'), ('strength-', 'strength'), ('-e', 'e')]
PHJ18851201-V01-04-page10.txt: [('false-', 'false')]
PHJ18851201-V01-04-page11.txt: [('discov-', 'discov')]
PHJ18851201-V01-04-page13.txt: [('-', '')]
PHJ18851201-V01-04-page14.txt: [('-', '')]
PHJ18851201-V01-04-page21.txt: [('JOUR-', 'JOUR'), ('JOUR-', 'JOUR'), ('-', '')]
PHJ18851201-V01-04-page23.txt: [('ATONENII-', 'ATONENII'), ('---o', '--o')]
PHJ18851201-V01-04-page24.txt: [('ale.gboetve-', 'ale.gboetve'), ('--', '-'), ('-', ''), ('co-', 'co'), ('t-', 't'), ('-', '')]
PHJ18851201-V01-04-page6.txt: [('obser-', 'obser')]
PHJ18851201-V01-04-page8.txt: [('-', '')]
PHJ18860201-V01-05-page1.txt: [('pERh\'"--', 'pERh\'"-')]
PHJ18860201-V01-05-page11.txt: [('Inter-', 'Inter')]
PHJ18860201-V01-05-page16.txt: [('mem-', 'mem')]
PHJ18860201-V01-05-page17.txt: [('oh-', 'oh')]
PHJ18860201-V01-05-page18.txt: [('Examina-', 'Examina')]
PHJ18860201-V01-05-page21.txt: [('cer-', 'cer'), ('State-', 'State')]
PHJ18860201-V01-05-page23.txt: [('PRESERVA-', 'PRESERVA'), ('P-', 'P'), ('-', ''), ('con-', 'con')]
PHJ18860201-V01-05-page24.txt: [('.V.e..SIT-', '.V.e..SIT'), ('W-', 'W'), ('VALLZT-', 'VALLZT'), ('it-', 'it'), ('-', ''), ('-', ''), ('F-', 'F'), ('-..', '..')]
PHJ18860201-V01-05-page8.txt: [('mem-', 'mem')]
PHJ18860201-V01-05-page9.txt: [('--', '-')]
PHJ18860401-V01-06-page13.txt: [('an-', 'an')]
PHJ18860401-V01-06-page14.txt: [('North-', 'North')]
PHJ18860401-V01-06-page16.txt: [('DIS-', 'DIS')]
PHJ18860401-V01-06-page20.txt: [('-page', 'page'), ('-page', 'page')]
PHJ18860401-V01-06-page21.txt: [('JOUR-', 'JOUR')]
PHJ18860401-V01-06-page22.txt: [('PREVEN-', 'PREVEN')]
PHJ18860401-V01-06-page23.txt: [('-mo.', 'mo.'), ('-PAGE', 'PAGE'), ('SAB-', 'SAB'), ('SEC-', 'SEC'), ('s-', 's')]
PHJ18860401-V01-06-page24.txt: [('-', ''), ('-L', 'L'), ('tern-', 'tern'), ('-erg', 'erg'), ('Vit-', 'Vit'), ('-irliif', 'irliif'), ('-', '')]
PHJ18860401-V01-06-page4.txt: [('knowl-', 'knowl')]
PHJ18860401-V01-06-page9.txt: [('-', '')]
PHJ18860601-V02-01-page12.txt: [('-', ''), ('-sons', 'sons')]
PHJ18860601-V02-01-page15.txt: [('sev-', 'sev')]
PHJ18860601-V02-01-page16.txt: [('-', '')]
PHJ18860601-V02-01-page19.txt: [('Mad-', 'Mad')]
PHJ18860601-V02-01-page20.txt: [('-ton', 'ton'), ('fla-', 'fla'), ('-', ''), ('-', ''), ('-', '')]
PHJ18860601-V02-01-page22.txt: [('Society-', 'Society'), ('Society-', 'Society'), ('Society-', 'Society'), ('Society-', 'Society'), ('Society-', 'Society'), ('Society-', 'Society'), ('Society-', 'Society'), ('Society-', 'Society')]
PHJ18860601-V02-01-page23.txt: [('-', ''), ('-', '')]
PHJ18860601-V02-01-page24.txt: [('V-', 'V'), ('F-', 'F'), ('-i-WWWW', 'i-WWWW'), ('VALLEY-', 'VALLEY'), ('-', ''), ('-', '')]
PHJ18860601-V02-01-page3.txt: [('derange-', 'derange'), ('well-', 'well')]
PHJ18860601-V02-01-page6.txt: [('move-', 'move')]
PHJ18860601-V02-01-page7.txt: [('BEDS.-', 'BEDS.')]
PHJ18860601-V02-01-page9.txt: [('ob-', 'ob'), ('in-', 'in')]
PHJ18860801-V02-02-page1.txt: [('-', ''), ('-', '')]
PHJ18860801-V02-02-page13.txt: [('con-', 'con'), ('-', '')]
PHJ18860801-V02-02-page15.txt: [('prod-', 'prod')]
PHJ18860801-V02-02-page20.txt: [('SUPPLY.---', 'SUPPLY.--')]
PHJ18860801-V02-02-page21.txt: [('dareddown-', 'dareddown')]
PHJ18860801-V02-02-page24.txt: [('-', '')]
PHJ18860801-V02-02-page25.txt: [('-t', 't')]
PHJ18860801-V02-02-page26.txt: [('Society-', 'Society'), ('Society-', 'Society'), ('Society-', 'Society'), ('Society-', 'Society'), ('Society-', 'Society'), ('Society-', 'Society'), ('Society-', 'Society'), ('Society-', 'Society'), ('-', ''), ('-', ''), ('-', ''), ('-SENTINEL', 'SENTINEL')]
PHJ18860801-V02-02-page28.txt: [('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('.-', '.'), ('SUP-', 'SUP'), ('-', ''), ('-', ''), ('-', '')]
PHJ18860801-V02-02-page29.txt: [('"-', '"'), ('---', '--'), ('-', ''), ('-vvoax', 'vvoax')]
PHJ18860801-V02-02-page31.txt: [('STOM-', 'STOM'), ('-', ''), ('-', ''), ('de-', 'de')]
PHJ18860801-V02-02-page32.txt: [('------', '-----'), ('L-', 'L'), ('-', ''), ('-..', '..'), ('CAL.a.-', 'CAL.a.'), ('WW-', 'WW'), ('-f', 'f'), ('VW-', 'VW'), ('C-', 'C')]
PHJ18860801-V02-02-page7.txt: [('success-', 'success')]
PHJ18860801-V02-02-page9.txt: [('mus-', 'mus')]
PHJ18861001-V02-03-page1.txt: [('-', ''), ('-k', 'k'), ('.-', '.'), ('....-', '....'), ('-..', '..'), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('--', '-'), ('-', ''), ('-', ''), ('-', ''), ('r--', 'r-'), ('-', ''), ('-', ''), ('N-', 'N'), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', '')]
PHJ18861001-V02-03-page11.txt: [('cov-', 'cov')]
PHJ18861001-V02-03-page15.txt: [('-at', 'at')]
PHJ18861001-V02-03-page18.txt: [('-', ''), ('ex-', 'ex')]
PHJ18861001-V02-03-page19.txt: [('nder-cloth--', 'nder-cloth-')]
PHJ18861001-V02-03-page2.txt: [('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', '')]
PHJ18861001-V02-03-page26.txt: [('Society-', 'Society'), ('Society-', 'Society'), ('Society-', 'Society'), ('Society-', 'Society'), ('Society-', 'Society'), ('Society-', 'Society'), ('Society-', 'Society'), ('Society-', 'Society'), ('-', ''), ('-', ''), ('-', ''), ('-page', 'page'), ('-page', 'page')]
PHJ18861001-V02-03-page27.txt: [('t--', 't-'), ('-', ''), ('-tQ', 'tQ')]
PHJ18861001-V02-03-page28.txt: [('.-', '.'), ('-', ''), ('---', '--')]
PHJ18861001-V02-03-page29.txt: [('-MO.', 'MO.'), ('-PAGE', 'PAGE'), ('SAB-', 'SAB'), ('SEC-', 'SEC'), ('-', ''), ('-', '')]
PHJ18861001-V02-03-page3.txt: [('cli-', 'cli')]
PHJ18861001-V02-03-page30.txt: [('SII-', 'SII'), ('-jil', 'jil'), ('-', ''), ('PRESERVA-', 'PRESERVA'), ('SCRIP-', 'SCRIP'), ('na-', 'na'), ('-', ''), ('con-', 'con')]
PHJ18861001-V02-03-page32.txt: [('-', ''), ('IA-', 'IA'), ('VALLEY-', 'VALLEY'), ('--', '-'), ('-', ''), ('lat-', 'lat'), ('lit-', 'lit')]
PHJ18861201-V02-04-page1.txt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iii-', 'Iiii'), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('I\'A\'."."-', 'I\'A\'."."'), ('----"zz', '---"zz'), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('v-', 'v'), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ("'-", "'"), ('--', '-'), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('.--', '.-'), ('-', ''), ('-', ''), ('-.', '.'), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', '')]
PHJ18861201-V02-04-page15.txt: [('Jour-', 'Jour'), ('--one', '-one')]
PHJ18861201-V02-04-page16.txt: [('--', '-')]
PHJ18861201-V02-04-page2.txt: [('-', ''), ('---', '--')]
PHJ18861201-V02-04-page20.txt: [('-', '')]
PHJ18861201-V02-04-page26.txt: [('Society-', 'Society'), ('Society-', 'Society'), ('Society-', 'Society'), ('Society-', 'Society'), ('Society-', 'Society'), ('Society-', 'Society'), ('-', ''), ('Society-', 'Society')]
PHJ18861201-V02-04-page27.txt: [('Es--', 'Es-'), ('PRESERVA-', 'PRESERVA'), ('SCRIP-', 'SCRIP'), ('con-', 'con'), ('-', '')]
PHJ18861201-V02-04-page29.txt: [('-ame', 'ame')]
PHJ18861201-V02-04-page3.txt: [('-', ''), ('-', ''), ('-', '')]
PHJ18861201-V02-04-page30.txt: [('IN-', 'IN')]
PHJ18861201-V02-04-page31.txt: [('-', '')]
PHJ18861201-V02-04-page32.txt: [('-V', 'V'), ('-.', '.'), ('-', ''), ('-', ''), ('in-', 'in')]
PHJ18870201-V02-05-page1.txt: [('-t-', 't-'), ('-..', '..'), ('-', ''), ('--', '-'), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('Patient-', 'Patient'), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', '')]
PHJ18870201-V02-05-page13.txt: [('con-', 'con')]
PHJ18870201-V02-05-page17.txt: [('something."-', 'something."')]
PHJ18870201-V02-05-page19.txt: [('-fr', 'fr'), ('-', ''), ('-', ''), ('beef--', 'beef-'), ('-', ''), ('-', ''), ('-', ''), ('-', '')]
PHJ18870201-V02-05-page2.txt: [('-', ''), ('-', ''), ('-', '')]
PHJ18870201-V02-05-page20.txt: [('---', '--')]
PHJ18870201-V02-05-page21.txt: [('-from', 'from')]
PHJ18870201-V02-05-page22.txt: [('-Upon', 'Upon'), ('be-', 'be')]
PHJ18870201-V02-05-page23.txt: [('-', ''), ('-', '')]
PHJ18870201-V02-05-page24.txt: [('-', ''), ('-', ''), ('-', ''), ('-', '')]
PHJ18870201-V02-05-page26.txt: [('Society-', 'Society'), ('Society-', 'Society'), ('Society-', 'Society'), ('Society-', 'Society'), ('Society-', 'Society'), ('Society-', 'Society'), ('Society-', 'Society'), ('Society-', 'Society'), ('Society-', 'Society'), ('-FJR-', 'FJR-')]
PHJ18870201-V02-05-page29.txt: [('IN-', 'IN'), ('-', ''), ('-', ''), ('-C', 'C'), ('I-', 'I'), ('-htio', 'htio'), ('-', '')]
PHJ18870201-V02-05-page30.txt: [('-', ''), ('-', ''), ('-', '')]
PHJ18870201-V02-05-page32.txt: [('-.VlP', '.VlP'), ('t-', 't')]
PHJ18870201-V02-05-page6.txt: [('-clueing', 'clueing'), ('nar-', 'nar'), ('-cotics', 'cotics'), ('per-', 'per')]
PHJ18870401-V02-06-page1.txt: [('-', ''), ('-rl', 'rl'), ('-', ''), ('-', ''), ('-DER', 'DER'), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('N-', 'N'), ('a.-', 'a.')]
PHJ18870401-V02-06-page10.txt: [('-would', 'would'), ('noth-', 'noth')]
PHJ18870401-V02-06-page11.txt: [('--', '-')]
PHJ18870401-V02-06-page14.txt: [('Insane-', 'Insane')]
PHJ18870401-V02-06-page16.txt: [('an-', 'an')]
PHJ18870401-V02-06-page19.txt: [('-', ''), ('Sat-', 'Sat')]
PHJ18870401-V02-06-page23.txt: [('-every', 'every')]
PHJ18870401-V02-06-page24.txt: [('Peerless-', 'Peerless'), ('.-', '.'), ('-', ''), ('FOUNTAIN-', 'FOUNTAIN'), ('-', '')]
PHJ18870401-V02-06-page26.txt: [('Society-', 'Society'), ('Society-', 'Society'), ('Society-', 'Society'), ('Society-', 'Society'), ('Society-', 'Society'), ('y-', 'y'), ('Society-', 'Society'), ('Society-', 'Society'), ('-N.', 'N.'), ('Society-', 'Society'), ('cor-', 'cor'), ('-', ''), ('Kg-', 'Kg'), ('cor-', 'cor')]
PHJ18870401-V02-06-page27.txt: [('-and', 'and')]
PHJ18870401-V02-06-page28.txt: [('Satan-', 'Satan'), ('-', ''), ('-', '')]
PHJ18870401-V02-06-page29.txt: [('-', '')]
PHJ18870401-V02-06-page30.txt: [('-.', '.'), ('.--', '.-'), ('-', ''), ('....i.-', '....i.'), ('-', '')]
PHJ18870401-V02-06-page31.txt: [('-', ''), ('Prescrip-', 'Prescrip'), ('be-', 'be'), ('sell-', 'sell'), ('IN-', 'IN'), ('-', ''), ('-', '')]
PHJ18870401-V02-06-page32.txt: [('-', ''), ('-l', 'l'), ('iitrgiWW.Nfit\'VIVWVit"-', 'iitrgiWW.Nfit\'VIVWVit"'), ('-----', '----'), ('---', '--')]
PHJ18870401-V02-06-page7.txt: [('-', '')]
PHJ18870601-V02-07-page1.txt: [('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('Circula-', 'Circula'), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('--', '-'), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', '')]
PHJ18870601-V02-07-page11.txt: [('-', '')]
PHJ18870601-V02-07-page12.txt: [('re-', 're')]
PHJ18870601-V02-07-page15.txt: [('Declar-', 'Declar')]
PHJ18870601-V02-07-page19.txt: [('-', '')]
PHJ18870601-V02-07-page2.txt: [('-', ''), ('-', '')]
PHJ18870601-V02-07-page20.txt: [('Mc-', 'Mc')]
PHJ18870601-V02-07-page21.txt: [('-sand', 'sand')]
PHJ18870601-V02-07-page22.txt: [('differ-', 'differ')]
PHJ18870601-V02-07-page25.txt: [('-stomachs', 'stomachs'), ('-cracker', 'cracker'), ('-combines', 'combines'), ('But-', 'But')]
PHJ18870601-V02-07-page26.txt: [('PRES-', 'PRES')]
PHJ18870601-V02-07-page27.txt: [('-Georgetown', 'Georgetown'), ('Society-', 'Society'), ('Society-', 'Society'), ('Society--', 'Society-'), ('Society-', 'Society'), ('-Ofifce', 'Ofifce'), ('y-', 'y'), ('Society-', 'Society'), ('Society-', 'Society'), ('-Upper', 'Upper'), ('Society-', 'Society'), ('Society-', 'Society'), ('GEN-', 'GEN'), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', '')]
PHJ18870601-V02-07-page28.txt: [('-', ''), ('-', ''), ('-', ''), ('P-', 'P'), ('-', ''), ('-', ''), ('-', '')]
PHJ18870601-V02-07-page29.txt: [('Sup-', 'Sup'), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', '')]
PHJ18870601-V02-07-page31.txt: [('-Was', 'Was')]
PHJ18870601-V02-07-page32.txt: [('Ail-', 'Ail'), ('regularly-gradu-', 'regularly-gradu'), ('-', ''), ('-', '')]
PHJ18870601-V02-07-page6.txt: [('-', '')]
PHJ18870801-V02-08-page1.txt: [('-Tr"', 'Tr"'), ('-..alii', '..alii'), ('"-I.LI-', '"-I.LI'), ('--', '-'), ('---', '--'), ('-.-', '.-'), ('--', '-'), ('"--', '"-'), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('A-', 'A'), ('-', ''), ('-.', '.'), ('---.', '--.'), ('-.', '.'), ('-', ''), ('---', '--'), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('G---', 'G--'), ('rr-', 'rr'), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('t--', 't-'), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('o-ys-----', 'o-ys----'), ('-', ''), ("--'", "-'"), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('c-', 'c'), ('-', ''), ('---.', '--.'), ('"-', '"'), ('--', '-'), ('-.', '.'), ('...-', '...'), ('.-', '.'), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-.', '.'), ('--.L', '-.L'), ('-', ''), ('-', ''), ('-', ''), ('-a', 'a'), ('-', ''), ('--', '-'), ('-', ''), ('-', ''), ('--', '-'), ('..--', '..-'), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('.-', '.'), ('-', ''), ('-', ''), ('--', '-'), ('----', '---'), ('-', '')]
PHJ18870801-V02-08-page10.txt: [('-the', 'the')]
PHJ18870801-V02-08-page12.txt: [('-wife', 'wife')]
PHJ18870801-V02-08-page17.txt: [('-maintains', 'maintains')]
PHJ18870801-V02-08-page18.txt: [('re-', 're')]
PHJ18870801-V02-08-page2.txt: [('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', '')]
PHJ18870801-V02-08-page25.txt: [('-', '')]
PHJ18870801-V02-08-page26.txt: [('-"', '"'), ('S.-', 'S.'), ('-"', '"')]
PHJ18870801-V02-08-page27.txt: [('Society-', 'Society'), ('Her-', 'Her'), ('Society-', 'Society'), ('Society-', 'Society'), ('Society-', 'Society'), ('Society-', 'Society'), ('Society-', 'Society'), ('Society-', 'Society'), ('-all', 'all'), ('-a', 'a'), ('cor-', 'cor'), ('-', ''), ('Society-', 'Society'), ('Society-', 'Society'), ('Society-', 'Society'), ('Society-', 'Society')]
PHJ18870801-V02-08-page28.txt: [('-', ''), ('-', ''), ('-Address', 'Address'), ('-', ''), ('-', ''), ('-', ''), ('-', '')]
PHJ18870801-V02-08-page29.txt: [('Prescrlp-', 'Prescrlp'), ('sell-', 'sell'), ('IN-', 'IN'), ('-', ''), ('-', ''), ('-', '')]
PHJ18870801-V02-08-page30.txt: [('...y-', '...y')]
PHJ18870801-V02-08-page31.txt: [('---', '--'), ('-', ''), ('-', ''), ('-FTIIE', 'FTIIE'), ('--a', '-a'), ('-G', 'G'), ('-HRILLIra', 'HRILLIra')]
PHJ18870801-V02-08-page32.txt: [('-', ''), ('-', ''), ('IA-', 'IA'), ('IAlit-', 'IAlit'), ('DIELALTE-', 'DIELALTE')]
PHJ18870801-V02-08-page6.txt: [('-', '')]
PHJ18871001-V02-09-page1.txt: [('......................................................--', '......................................................-'), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('po-', 'po'), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', '')]
PHJ18871001-V02-09-page17.txt: [('honor-', 'honor')]
PHJ18871001-V02-09-page2.txt: [('-', '')]
PHJ18871001-V02-09-page21.txt: [('-', ''), ('-', '')]
PHJ18871001-V02-09-page22.txt: [('ijousel-', 'ijousel')]
PHJ18871001-V02-09-page24.txt: [('--', '-'), ('-', ''), ('-', ''), ('e-', 'e'), ('-', ''), ('-.', '.'), ('Electro-', 'Electro'), ('UT-', 'UT')]
PHJ18871001-V02-09-page25.txt: [('-', ''), ('-', '')]
PHJ18871001-V02-09-page26.txt: [('Society-', 'Society'), ('Society-', 'Society'), ('Society-', 'Society'), ('Society-', 'Society'), ('Society-', 'Society'), ('Society-', 'Society'), ('Record-', 'Record')]
PHJ18871001-V02-09-page27.txt: [('-Was', 'Was')]
PHJ18871001-V02-09-page28.txt: [('-.', '.')]
PHJ18871001-V02-09-page29.txt: [('-WITH', 'WITH'), ('-', '')]
PHJ18871001-V02-09-page3.txt: [('-', '')]
PHJ18871001-V02-09-page31.txt: [('-TbB', 'TbB'), ('-', ''), ('-', ''), ('-', ''), ('P-', 'P')]
PHJ18871001-V02-09-page32.txt: [('-t', 't')]
PHJ18871001-V02-09-page33.txt: [('-olum', 'olum')]
PHJ18871001-V02-09-page36.txt: [('PAGE-', 'PAGE'), ('-', '')]
PHJ18871001-V02-09-page5.txt: [('apolo-', 'apolo')]
PHJ18871001-V02-09-page6.txt: [('-', '')]
PHJ18871001-V02-09-page7.txt: [('-', '')]
PHJ18871001-V02-09-page8.txt: [('window--', 'window-')]
PHJ18880101-V03-01-page1.txt: [('-', ''), ('-PAGE', 'PAGE')]
PHJ18880101-V03-01-page10.txt: [('away-', 'away')]
PHJ18880101-V03-01-page13.txt: [('be-', 'be')]
PHJ18880101-V03-01-page16.txt: [('seasick-', 'seasick')]
PHJ18880101-V03-01-page17.txt: [('go-', 'go')]
PHJ18880101-V03-01-page19.txt: [('con-', 'con')]
PHJ18880101-V03-01-page2.txt: [('saccha-', 'saccha')]
PHJ18880101-V03-01-page20.txt: [('-', '')]
PHJ18880101-V03-01-page26.txt: [('Tobacco-', 'Tobacco'), ('-', '')]
PHJ18880101-V03-01-page28.txt: [('Electro-', 'Electro'), ('----', '---')]
PHJ18880101-V03-01-page29.txt: [('-', '')]
PHJ18880101-V03-01-page30.txt: [("Bird's-", "Bird's")]
PHJ18880101-V03-01-page31.txt: [('Chromo-', 'Chromo'), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-------', '------'), ('-Style', 'Style')]
PHJ18880101-V03-01-page32.txt: [('-', '')]
PHJ18880101-V03-01-page5.txt: [('mur-', 'mur'), ('-xcellence', 'xcellence')]
PHJ18880101-V03-01-page6.txt: [('break-', 'break')]
PHJ18880101-V03-01-page7.txt: [('thou-', 'thou')]
PHJ18880201-V03-02-page1.txt: [('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-PAGE', 'PAGE')]
PHJ18880201-V03-02-page11.txt: [('iron-', 'iron')]
PHJ18880201-V03-02-page13.txt: [('two-', 'two')]
PHJ18880201-V03-02-page14.txt: [('-', ''), ('-', '')]
PHJ18880201-V03-02-page18.txt: [('-', '')]
PHJ18880201-V03-02-page23.txt: [('-', ''), ('-', '')]
PHJ18880201-V03-02-page24.txt: [('AD-', 'AD'), ('-page', 'page')]
PHJ18880201-V03-02-page26.txt: [('Tobacco-', 'Tobacco'), ('-', '')]
PHJ18880201-V03-02-page27.txt: [('-ERFUL', 'ERFUL'), ('-sdho', 'sdho'), ('-Volume', 'Volume')]
PHJ18880201-V03-02-page28.txt: [('Electro-', 'Electro')]
PHJ18880201-V03-02-page3.txt: [('abomi-', 'abomi')]
PHJ18880201-V03-02-page30.txt: [('-b-ums.', 'b-ums.'), ('-This', 'This'), ('-SEND', 'SEND')]
PHJ18880201-V03-02-page31.txt: [('Chromo-', 'Chromo'), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-------', '------')]
PHJ18880201-V03-02-page4.txt: [('-', '')]
PHJ18880201-V03-02-page5.txt: [('emul-', 'emul')]
PHJ18880201-V03-02-page8.txt: [('-correct', 'correct')]
PHJ18880201-V03-02-page9.txt: [('sensibil-', 'sensibil'), ('con-', 'con'), ('be-', 'be')]
PHJ18880301-V03-03-page1.txt: [('-', ''), ('-', '')]
PHJ18880301-V03-03-page10.txt: [('blood-', 'blood')]
PHJ18880301-V03-03-page11.txt: [('consid-', 'consid'), ('fount-', 'fount')]
PHJ18880301-V03-03-page18.txt: [('--', '-')]
PHJ18880301-V03-03-page2.txt: [('en-', 'en'), ('sys-', 'sys')]
PHJ18880301-V03-03-page20.txt: [('Ex-', 'Ex')]
PHJ18880301-V03-03-page24.txt: [('TEM-', 'TEM'), ('Record-', 'Record')]
PHJ18880301-V03-03-page25.txt: [('-it', 'it'), ('Electro-', 'Electro'), ('.-', '.'), ('-', ''), ('-', ''), ('---', '--'), ('r---', 'r--'), ('-', ''), ('-', ''), ('-', '')]
PHJ18880301-V03-03-page26.txt: [('per-', 'per'), ('--', '-'), ('DE-', 'DE'), ('-page', 'page')]
PHJ18880301-V03-03-page27.txt: [('LAUN-', 'LAUN'), ('-', ''), ('-', ''), ('--wl-.food', '-wl-.food'), ('miss.n-fw-', 'miss.n-fw'), ('-page', 'page'), ('-az', 'az')]
PHJ18880301-V03-03-page28.txt: [('-', ''), ('-', '')]
PHJ18880301-V03-03-page3.txt: [('monu-', 'monu')]
PHJ18880301-V03-03-page30.txt: [('--', '-'), ("i'li-", "i'li"), ('---G', '--G'), ("Bird's-", "Bird's")]
PHJ18880301-V03-03-page31.txt: [('I-', 'I'), ('Chromo-', 'Chromo'), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-------', '------'), ('--', '-'), ('-', '')]
PHJ18880301-V03-03-page4.txt: [('-', '')]
PHJ18880301-V03-03-page5.txt: [('ex-', 'ex')]
PHJ18880301-V03-03-page7.txt: [('most.-', 'most.')]
PHJ18880301-V03-03-page9.txt: [('-', '')]
PHJ18880401-V03-04-page1.txt: [('-P', 'P'), ('Mes-', 'Mes')]
PHJ18880401-V03-04-page11.txt: [('af-', 'af'), ('de-', 'de')]
PHJ18880401-V03-04-page16.txt: [('-is', 'is')]
PHJ18880401-V03-04-page17.txt: [('--', '-')]
PHJ18880401-V03-04-page2.txt: [('nat-', 'nat')]
PHJ18880401-V03-04-page20.txt: [('im-', 'im')]
PHJ18880401-V03-04-page23.txt: [('-field', 'field')]
PHJ18880401-V03-04-page25.txt: [('ar-', 'ar'), ('-', ''), ('I-', 'I'), ('JOUR-', 'JOUR')]
PHJ18880401-V03-04-page26.txt: [('-', ''), ('-', ''), ('Healthr--', 'Healthr-'), ('DE-', 'DE'), ('-PAGE', 'PAGE'), ('-Arithmetic', 'Arithmetic')]
PHJ18880401-V03-04-page27.txt: [('LAUN-', 'LAUN'), ("miss.'-", "miss.'"), ("-'-", "'-"), ('-page', 'page'), ('Electro-', 'Electro'), ('-page', 'page'), ('-', ''), ('-', ''), ('-r....', 'r....'), ('-', ''), ('.-.-', '.-.'), ('.-', '.'), ('-', ''), ('--', '-'), ('-..', '..'), ('-', ''), ('C-', 'C'), ("--'", "-'"), ('-', ''), ('r--', 'r-'), ('-', ''), ('-', ''), ('-r', 'r'), ('-', ''), ("-'", "'"), ('--', '-'), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-.', '.'), ('-', ''), ('-', ''), ('-', ''), ('-', '')]
PHJ18880401-V03-04-page28.txt: [('-', '')]
PHJ18880401-V03-04-page31.txt: [('Chromo-', 'Chromo'), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-------', '------'), ('-ELTTS', 'ELTTS')]
PHJ18880401-V03-04-page32.txt: [('-', ''), ('-r', 'r')]
PHJ18880401-V03-04-page8.txt: [('---', '--')]
PHJ18880501-V03-05-page1.txt: [('-', ''), ('-PAGE', 'PAGE')]
PHJ18880501-V03-05-page12.txt: [('ju-', 'ju')]
PHJ18880501-V03-05-page13.txt: [('-a', 'a')]
PHJ18880501-V03-05-page15.txt: [('con-', 'con')]
PHJ18880501-V03-05-page18.txt: [('re-', 're')]
PHJ18880501-V03-05-page22.txt: [('Some-', 'Some')]
PHJ18880501-V03-05-page23.txt: [('in-', 'in')]
PHJ18880501-V03-05-page24.txt: [('-page', 'page')]
PHJ18880501-V03-05-page25.txt: [('LAUN-', 'LAUN'), ('--wttlood', '-wttlood')]
PHJ18880501-V03-05-page26.txt: [('Indianapoli-', 'Indianapoli'), ('-', ''), ('per-', 'per'), ('-twining', 'twining'), ('HY-', 'HY'), ('DE-', 'DE'), ('NX-', 'NX')]
PHJ18880501-V03-05-page27.txt: [('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('FIRST-', 'FIRST'), ('-THE', 'THE'), ('to-', 'to'), ('APPLI-', 'APPLI'), ('-page', 'page'), ('-', ''), ('-', ''), ('-', ''), ('zz--', 'zz-'), ('-', ''), ('-', ''), ("-'z", "'z"), ('-', ''), ('r--', 'r-'), ('.--', '.-'), ('-', ''), ('c-', 'c'), (".'-", ".'"), ('.".--', '.".-'), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('S-', 'S')]
PHJ18880501-V03-05-page28.txt: [('-PAGE', 'PAGE'), ('-Arithmetic', 'Arithmetic'), ('Electro-', 'Electro'), ('PI-', 'PI'), ('-', '')]
PHJ18880501-V03-05-page3.txt: [('con-', 'con')]
PHJ18880501-V03-05-page31.txt: [('Chromo-', 'Chromo'), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-------', '------')]
PHJ18880501-V03-05-page32.txt: [("'-", "'")]
PHJ18880501-V03-05-page9.txt: [('chil-', 'chil')]
PHJ18880601-V03-06-page1.txt: [('-', '')]
PHJ18880601-V03-06-page11.txt: [('-.', '.'), ('-', '')]
PHJ18880601-V03-06-page12.txt: [('PEO-', 'PEO')]
PHJ18880601-V03-06-page17.txt: [('Thirst-Maker-', 'Thirst-Maker')]
PHJ18880601-V03-06-page19.txt: [('WINE.-', 'WINE.'), ('-ro.', 'ro.'), ('INSTITU-', 'INSTITU')]
PHJ18880601-V03-06-page20.txt: [('-', ''), ('Pota-', 'Pota')]
PHJ18880601-V03-06-page23.txt: [('--that', '-that')]
PHJ18880601-V03-06-page25.txt: [('LAUN-', 'LAUN'), ('--s', '-s'), ('-', ''), ('-page', 'page'), ('PA-', 'PA')]
PHJ18880601-V03-06-page27.txt: [('-', ''), ('-', ''), ('----', '---'), ('---', '--'), ('FIRST-', 'FIRST'), ('-page', 'page'), ('BEST-', 'BEST'), ('APPLI-', 'APPLI'), ('-rte', 'rte')]
PHJ18880601-V03-06-page28.txt: [('Electro-', 'Electro'), ('-PAGE', 'PAGE')]
PHJ18880601-V03-06-page30.txt: [('-ums.', 'ums.')]
PHJ18880601-V03-06-page31.txt: [('Chromo-', 'Chromo'), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-------', '------')]
PHJ18880601-V03-06-page32.txt: [('-', ''), ('CALI-', 'CALI')]
PHJ18880601-V03-06-page4.txt: [('-', ''), ('-', ''), ('-', '')]
PHJ18880601-V03-06-page6.txt: [('-administer', 'administer'), ('-of', 'of')]
PHJ18880601-V03-06-page8.txt: [('-chest', 'chest')]
PHJ18880701-V03-07-page1.txt: [('-', ''), ('-', ''), ('-P', 'P'), ('di"-', 'di"')]
PHJ18880701-V03-07-page13.txt: [('con-', 'con')]
PHJ18880701-V03-07-page15.txt: [('Di-', 'Di')]
PHJ18880701-V03-07-page21.txt: [('A-', 'A')]
PHJ18880701-V03-07-page26.txt: [('Society-', 'Society'), ('-F.', 'F.'), ('Tennessee-', 'Tennessee'), ("-'", "'"), ('per-', 'per'), ('-', ''), ('j-', 'j'), ("-'", "'"), ('HY-', 'HY')]
PHJ18880701-V03-07-page27.txt: [('-', ''), ('-', ''), ('FIRST-', 'FIRST'), ('x-', 'x'), ('-page', 'page'), ('-', ''), ('r--', 'r-'), ('"-', '"'), ('.-', '.'), ('-', ''), ('---THE', '--THE'), ('to-', 'to'), ('APPLI-', 'APPLI'), ('-', ''), ('-', ''), ('ior-', 'ior'), ('i--', 'i-')]
PHJ18880701-V03-07-page28.txt: [('com-', 'com'), ('Electro-', 'Electro'), ('-PAGE', 'PAGE')]
PHJ18880701-V03-07-page29.txt: [('-', '')]
PHJ18880701-V03-07-page30.txt: [('-PAGE', 'PAGE'), ('-', ''), ('-page', 'page')]
PHJ18880801-V03-08-page1.txt: [('-PAGE', 'PAGE')]
PHJ18880801-V03-08-page15.txt: [('-no', 'no')]
PHJ18880801-V03-08-page21.txt: [('-', ''), ('-the', 'the'), ('de-', 'de')]
PHJ18880801-V03-08-page24.txt: [("'-", "'")]
PHJ18880801-V03-08-page26.txt: [('-Row', 'Row'), ('Society-', 'Society'), ('-F.', 'F.'), ('-Elder', 'Elder'), ('Tennessee-', 'Tennessee'), ('DE-', 'DE'), ('-f', 'f')]
PHJ18880801-V03-08-page27.txt: [('es-', 'es'), ('Electro-', 'Electro'), ('-PAGE', 'PAGE'), ('-', '')]
PHJ18880801-V03-08-page29.txt: [('-FOR-', 'FOR-')]
PHJ18880801-V03-08-page30.txt: [('-page', 'page'), ('-', ''), ('-', ''), ('S--', 'S-'), ('FIRST-', 'FIRST'), ('-', ''), ('--THE', '-THE'), ('-Especially', 'Especially'), ('to-', 'to'), ('-', ''), ('APPLI-', 'APPLI')]
PHJ18880801-V03-08-page31.txt: [('-PAGE', 'PAGE'), ('Tobacco-', 'Tobacco'), ('-', ''), ('-page', 'page'), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-page', 'page'), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', '')]
PHJ18880801-V03-08-page32.txt: [('Vitalske-', 'Vitalske'), ('-', '')]
PHJ18880801-V03-08-page6.txt: [('HKALTI-', 'HKALTI')]
PHJ18880801-V03-08-page7.txt: [('-', '')]
PHJ18880901-V03-09-page1.txt: [('-', ''), ('-PAGE', 'PAGE'), ('-', '')]
PHJ18880901-V03-09-page14.txt: [('DRUNK-', 'DRUNK')]
PHJ18880901-V03-09-page16.txt: [('to-', 'to'), ('to-', 'to')]
PHJ18880901-V03-09-page17.txt: [('---', '--')]
PHJ18880901-V03-09-page18.txt: [('---', '--')]
PHJ18880901-V03-09-page24.txt: [('OMNIBUS-', 'OMNIBUS')]
PHJ18880901-V03-09-page26.txt: [('an-', 'an'), ('ex-', 'ex'), ('-page', 'page'), ('--We', '-We')]
PHJ18880901-V03-09-page27.txt: [('Society-', 'Society'), ('-F.', 'F.'), ('EqUAREMX-', 'EqUAREMX')]
PHJ18880901-V03-09-page3.txt: [('Infirmi-', 'Infirmi')]
PHJ18880901-V03-09-page30.txt: [('Electro-', 'Electro'), ('-PAGE', 'PAGE')]
PHJ18880901-V03-09-page31.txt: [('-PAGE', 'PAGE'), ('jour-', 'jour'), ('-', ''), ('PRES-', 'PRES'), ('-page', 'page'), ('-rt', 'rt'), ('-page', 'page')]
PHJ18880901-V03-09-page8.txt: [('SENTIMENT-', 'SENTIMENT')]
PHJ18880901-V03-09-page9.txt: [('-', '')]
PHJ18881001-V03-10-page1.txt: [('-', ''), ('-PAGE', 'PAGE'), ('ner-', 'ner')]
PHJ18881001-V03-10-page12.txt: [('be-', 'be')]
PHJ18881001-V03-10-page14.txt: [('TempeFar-', 'TempeFar')]
PHJ18881001-V03-10-page18.txt: [('contin-', 'contin')]
PHJ18881001-V03-10-page19.txt: [('can-', 'can')]
PHJ18881001-V03-10-page22.txt: [('-', ''), ('affection-', 'affection')]
PHJ18881001-V03-10-page24.txt: [('-', ''), ('-', ''), ('-', ''), ('-', '')]
PHJ18881001-V03-10-page27.txt: [('Society-', 'Society'), ('-F.', 'F.'), ('-----"', '----"'), ('.j-', '.j'), ('-', '')]
PHJ18881001-V03-10-page28.txt: [('Electro-', 'Electro'), ('-PAGE', 'PAGE'), ('-', ''), ('.egi-', '.egi')]
PHJ18881001-V03-10-page3.txt: [('OVER-', 'OVER'), ('doubt-', 'doubt')]
PHJ18881001-V03-10-page30.txt: [('-', ''), ('Chromo-', 'Chromo'), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-------', '------')]
PHJ18881001-V03-10-page32.txt: [('-', ''), ('But-', 'But')]
PHJ18881001-V03-10-page6.txt: [('pro-', 'pro')]
PHJ18881001-V03-10-page9.txt: [('-', '')]
PHJ18881101-V03-11-page1.txt: [('-', ''), ('-Dor', 'Dor'), ('expe-', 'expe'), ('-', ''), ('-', ''), ('-', ''), ('-', '')]
PHJ18881101-V03-11-page13.txt: [('-', ''), ('-', '')]
PHJ18881101-V03-11-page18.txt: [('to-', 'to')]
PHJ18881101-V03-11-page19.txt: [('pros-', 'pros')]
PHJ18881101-V03-11-page20.txt: [('TEM-', 'TEM')]
PHJ18881101-V03-11-page24.txt: [('tyran-', 'tyran')]
PHJ18881101-V03-11-page26.txt: [('brush-', 'brush')]
PHJ18881101-V03-11-page27.txt: [('-Ctr', 'Ctr'), ('COPlEII-', 'COPlEII'), ('-Y.', 'Y.')]
PHJ18881101-V03-11-page28.txt: [('Society-', 'Society'), ('-F.', 'F.'), ('-f-', 'f-'), ('-', ''), ('DE-', 'DE')]
PHJ18881101-V03-11-page29.txt: [('-PAGE', 'PAGE'), ('-', ''), ('PRES-', 'PRES'), ('-page', 'page'), ('in-', 'in'), ('-a', 'a'), ('-"', '"'), ('"Y-', '"Y'), ('-', ''), ('-page', 'page'), ('-', '')]
PHJ18881101-V03-11-page3.txt: [('syste-', 'syste'), ('Re-', 'Re')]
PHJ18881101-V03-11-page31.txt: [('-FOR-', 'FOR-'), ('-', ''), ('-EN.q', 'EN.q')]
PHJ18881101-V03-11-page5.txt: [('-', '')]
PHJ18881101-V03-11-page7.txt: [('excep-', 'excep')]
PHJ18881201-V03-12-page1.txt: [('-', ''), ('-PAGE', 'PAGE'), ('ex-', 'ex')]
PHJ18881201-V03-12-page17.txt: [('Ex-', 'Ex')]
PHJ18881201-V03-12-page19.txt: [('ex-', 'ex')]
PHJ18881201-V03-12-page21.txt: [('re-', 're'), ('-', ''), ('treat-', 'treat')]
PHJ18881201-V03-12-page27.txt: [('-page', 'page'), ('Society-', 'Society'), ('-F.', 'F.'), ('Tennessee-', 'Tennessee')]
PHJ18881201-V03-12-page28.txt: [('-', ''), ('-', '')]
PHJ18881201-V03-12-page29.txt: [('L-', 'L'), ('-', ''), ('-FOR-', 'FOR-'), ('Cal-', 'Cal')]
PHJ18881201-V03-12-page30.txt: [('HY-', 'HY'), ('DE-', 'DE'), ('-', ''), ('NX.-', 'NX.'), ('LI-', 'LI')]
PHJ18881201-V03-12-page31.txt: [('PRES-', 'PRES'), ('-page', 'page'), ('Electro-', 'Electro'), ('-PAGE', 'PAGE'), ('-', '')]
PHJ18881201-V03-12-page32.txt: [('OR-', 'OR')]
PHJ18881201-V03-12-page33.txt: [('Hip-', 'Hip')]
PHJ18881201-V03-12-page7.txt: [('re-', 're')]
PHJ18881201-V03-12-page9.txt: [('them-', 'them'), ('be-', 'be')]
PHJ18890101-V04-01-page1.txt: [('-PAGE', 'PAGE'), ('-', ''), ('-', '')]
PHJ18890101-V04-01-page17.txt: [('-', '')]
PHJ18890101-V04-01-page21.txt: [('HYPERTRO-', 'HYPERTRO')]
PHJ18890101-V04-01-page23.txt: [('ordina-', 'ordina')]
PHJ18890101-V04-01-page26.txt: [('-V', 'V')]
PHJ18890101-V04-01-page27.txt: [('-page', 'page'), ('-page.', 'page.'), ('-page', 'page'), ('things--', 'things-'), ('Society-', 'Society'), ('-F.', 'F.'), ('Indian-', 'Indian')]
PHJ18890101-V04-01-page28.txt: [('-', ''), ('-', ''), ('-', '')]
PHJ18890101-V04-01-page29.txt: [('But-', 'But')]
PHJ18890101-V04-01-page3.txt: [('ani-', 'ani')]
PHJ18890101-V04-01-page30.txt: [('-PAGE', 'PAGE')]
PHJ18890101-V04-01-page31.txt: [('-TEMPERANCE', 'TEMPERANCE'), ('-s-', 's-'), ('-page', 'page'), ('-', ''), ('-', '')]
PHJ18890101-V04-01-page32.txt: [('L-', 'L')]
PHJ18890101-V04-01-page9.txt: [('edu-', 'edu')]
PHJ18890201-V04-02-page1.txt: [('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-IMGE', 'IMGE'), ('-', '')]
PHJ18890201-V04-02-page11.txt: [('differ-', 'differ'), ('atten-', 'atten')]
PHJ18890201-V04-02-page14.txt: [('Consul-', 'Consul')]
PHJ18890201-V04-02-page16.txt: [('INTEMPER-', 'INTEMPER')]
PHJ18890201-V04-02-page17.txt: [('medi-', 'medi')]
PHJ18890201-V04-02-page18.txt: [('pri-', 'pri')]
PHJ18890201-V04-02-page2.txt: [('membr-', 'membr'), ('-e', 'e'), ('rec-', 'rec')]
PHJ18890201-V04-02-page24.txt: [('-', ''), ('Muffins.-', 'Muffins.')]
PHJ18890201-V04-02-page26.txt: [('Society-', 'Society'), ('-F.', 'F.'), ('Tennessee-', 'Tennessee')]
PHJ18890201-V04-02-page27.txt: [('-page', 'page'), ('-page', 'page'), ('-page', 'page'), ('-page', 'page'), ('-page', 'page')]
PHJ18890201-V04-02-page28.txt: [('-', '')]
PHJ18890201-V04-02-page29.txt: [('-', ''), ('-', ''), ('-', ''), ('-s-', 's-'), ('-page', 'page')]
PHJ18890201-V04-02-page3.txt: [('desti-', 'desti')]
PHJ18890201-V04-02-page30.txt: [('.-', '.'), ('--.', '-.'), ('-PAGE', 'PAGE')]
PHJ18890201-V04-02-page31.txt: [('War-', 'War'), ('-', ''), ('-', ''), ('-', '')]
PHJ18890201-V04-02-page5.txt: [('-', '')]
PHJ18890301-V04-03-page1.txt: [('-', ''), ('-PAGE', 'PAGE')]
PHJ18890301-V04-03-page14.txt: [('dream.-', 'dream.')]
PHJ18890301-V04-03-page15.txt: [('consump-', 'consump')]
PHJ18890301-V04-03-page18.txt: [('sui-', 'sui')]
PHJ18890301-V04-03-page19.txt: [('be-', 'be'), ('-', ''), ('A-', 'A')]
PHJ18890301-V04-03-page22.txt: [('cream-', 'cream'), ('Vegetarian-', 'Vegetarian')]
PHJ18890301-V04-03-page23.txt: [('-ttrwrItsrovv"-', 'ttrwrItsrovv"-')]
PHJ18890301-V04-03-page25.txt: [('GAR-', 'GAR')]
PHJ18890301-V04-03-page26.txt: [("t'-", "t'")]
PHJ18890301-V04-03-page27.txt: [('-', ''), ('-', '')]
PHJ18890301-V04-03-page28.txt: [('-', ''), ('But-', 'But')]
PHJ18890301-V04-03-page29.txt: [('-', ''), ('-page', 'page')]
PHJ18890301-V04-03-page3.txt: [('WES-', 'WES')]
PHJ18890301-V04-03-page30.txt: [('-', '')]
PHJ18890301-V04-03-page32.txt: [('-----I', '----I'), ('circu-', 'circu'), ('-PAGE', 'PAGE')]
PHJ18890301-V04-03-page7.txt: [('-', ''), ('-', '')]
PHJ18890301-V04-03-page9.txt: [('Chris-', 'Chris'), ('yield-', 'yield')]
PHJ18890401-V04-04-page1.txt: [('-', ''), ('at-', 'at'), ('-P', 'P')]
PHJ18890401-V04-04-page13.txt: [('-', '')]
PHJ18890401-V04-04-page15.txt: [('naughti-', 'naughti')]
PHJ18890401-V04-04-page17.txt: [('gusta-', 'gusta'), ('sen-', 'sen')]
PHJ18890401-V04-04-page19.txt: [('impa-', 'impa'), ('re-', 're'), ('ex-', 'ex')]
PHJ18890401-V04-04-page2.txt: [('-plainly', 'plainly')]
PHJ18890401-V04-04-page24.txt: [('possi-', 'possi')]
PHJ18890401-V04-04-page27.txt: [('Society-', 'Society'), ('-Lillie', 'Lillie'), ('-"-', '"-'), ('-', ''), ('..----', '..---'), ('War-', 'War')]
PHJ18890401-V04-04-page28.txt: [('SANC-', 'SANC'), ("'-", "'"), ('-', ''), ('---', '--'), ('p-', 'p'), ('.-', '.'), ('I--', 'I-'), ('-', ''), ('.--', '.-'), ('-', ''), ('-', ''), ('-', ''), ('r-T-', 'r-T'), ('...-', '...'), ("-'-'c'zic.-", "'-'c'zic.-"), ('-', ''), ('I.--', 'I.-'), ('-', ''), ('-', ''), ('-', ''), ('--', '-'), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('...-', '...'), ('.-', '.'), ('I-', 'I'), ('-..', '..'), ('-', ''), ('--', '-'), ('--', '-'), ('--', '-'), ('-', ''), ("'-", "'"), ('..-', '..'), ('.--', '.-')]
PHJ18890401-V04-04-page30.txt: [('-', ''), ('-page', 'page')]
PHJ18890401-V04-04-page31.txt: [('But-', 'But')]
PHJ18890401-V04-04-page32.txt: [('-PAGE', 'PAGE'), ('-', ''), ('NEW-', 'NEW')]
PHJ18890401-V04-04-page6.txt: [('actinomy-', 'actinomy')]
PHJ18890501-V04-05-page1.txt: [('-', ''), ('-PAGE', 'PAGE')]
PHJ18890501-V04-05-page11.txt: [('men-', 'men')]
PHJ18890501-V04-05-page14.txt: [('sun-', 'sun'), ('Har-', 'Har')]
PHJ18890501-V04-05-page15.txt: [('im-', 'im'), ('correspond-', 'correspond')]
PHJ18890501-V04-05-page16.txt: [('car-', 'car')]
PHJ18890501-V04-05-page17.txt: [('compre-', 'compre')]
PHJ18890501-V04-05-page23.txt: [('cocaine-', 'cocaine')]
PHJ18890501-V04-05-page24.txt: [('pat-', 'pat'), ('-eierVit', 'eierVit')]
PHJ18890501-V04-05-page25.txt: [('-Ertred', 'Ertred'), ('-', ''), ('-', '')]
PHJ18890501-V04-05-page27.txt: [('Society-', 'Society'), ('-Lillie', 'Lillie'), ('Society-', 'Society'), ('Tennessee-', 'Tennessee'), ('use-', 'use')]
PHJ18890501-V04-05-page29.txt: [('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('Nat-', 'Nat'), ('-', ''), ('-', ''), ('--Massage', '-Massage'), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', '')]
PHJ18890501-V04-05-page30.txt: [('-', ''), ('-page', 'page')]
PHJ18890501-V04-05-page31.txt: [('--', '-'), ('-FOR-', 'FOR-')]
PHJ18890601-V04-06-page1.txt: [('-PAGE', 'PAGE')]
PHJ18890601-V04-06-page11.txt: [('hav-', 'hav'), ('Trib-', 'Trib')]
PHJ18890601-V04-06-page12.txt: [('--Stier', '-Stier')]
PHJ18890601-V04-06-page15.txt: [('-', ''), ('-', '')]
PHJ18890601-V04-06-page17.txt: [('an-', 'an')]
PHJ18890601-V04-06-page19.txt: [('carboni-', 'carboni'), ('can-', 'can')]
PHJ18890601-V04-06-page2.txt: [('appropri-', 'appropri')]
PHJ18890601-V04-06-page25.txt: [('-', ''), ("Children's-", "Children's")]
PHJ18890601-V04-06-page26.txt: [('III..-', 'III..')]
PHJ18890601-V04-06-page27.txt: [('Society-', 'Society'), ('-Lillie', 'Lillie'), ('Tennessee-', 'Tennessee'), ("'-", "'")]
PHJ18890601-V04-06-page29.txt: [('-', ''), ('-', ''), ('-', ''), ('-', ''), ('War-', 'War'), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('--', '-'), ('-', ''), ('---', '--'), ('-', ''), ('-', ''), ('-', ''), ('----', '---'), ('-', ''), ('-', ''), ('-', ''), ('-a', 'a'), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', '')]
PHJ18890601-V04-06-page30.txt: [('-', ''), ('-', ''), ('-page', 'page')]
PHJ18890601-V04-06-page5.txt: [('skel-', 'skel')]
PHJ18890601-V04-06-page8.txt: [('indul-', 'indul')]
PHJ18890701-V04-07-page1.txt: [('-PAGE', 'PAGE'), ('-', '')]
PHJ18890701-V04-07-page10.txt: [('-', ''), ('Consti-', 'Consti')]
PHJ18890701-V04-07-page12.txt: [('re-', 're')]
PHJ18890701-V04-07-page17.txt: [('can-', 'can'), ('--', '-'), ('mani-', 'mani')]
PHJ18890701-V04-07-page2.txt: [('one-', 'one')]
PHJ18890701-V04-07-page22.txt: [('once.-', 'once.')]
PHJ18890701-V04-07-page27.txt: [('Society-', 'Society'), ('-Lillie', 'Lillie'), ('Tennessee-', 'Tennessee')]
PHJ18890701-V04-07-page28.txt: [('-', ''), ('-.."', '.."'), ('World-', 'World'), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('La-', 'La'), ('---', '--'), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', '')]
PHJ18890701-V04-07-page30.txt: [('exam-', 'exam'), ('-PAGE', 'PAGE'), ('-THE', 'THE')]
PHJ18890701-V04-07-page8.txt: [('IDOL-', 'IDOL')]
PHJ18890701-V04-07-page9.txt: [('com-', 'com'), ('tyran-', 'tyran')]
PHJ18890801-V04-08-page1.txt: [('condi-', 'condi'), ('-', ''), ('-PAGE', 'PAGE')]
PHJ18890801-V04-08-page10.txt: [('-ginie', 'ginie')]
PHJ18890801-V04-08-page11.txt: [('granu-', 'granu')]
PHJ18890801-V04-08-page15.txt: [('swal-', 'swal')]
PHJ18890801-V04-08-page21.txt: [('WEATHER.-', 'WEATHER.')]
PHJ18890801-V04-08-page24.txt: [('-', '')]
PHJ18890801-V04-08-page26.txt: [('pi-', 'pi'), ('-', '')]
PHJ18890801-V04-08-page27.txt: [('Society-', 'Society'), ('-Lillie', 'Lillie'), ('Tennessee-', 'Tennessee')]
PHJ18890801-V04-08-page28.txt: [('World.-', 'World.'), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', '')]
PHJ18890801-V04-08-page30.txt: [('--', '-'), ('-', ''), ('-', '')]
PHJ18890801-V04-08-page31.txt: [('-page', 'page')]
PHJ18890801-V04-08-page32.txt: [('TEN-', 'TEN')]
PHJ18890801-V04-08-page5.txt: [('in-', 'in')]
PHJ18890801-V04-08-page7.txt: [('Hy-', 'Hy')]
PHJ18890901-V04-09-page1.txt: [('-', ''), ('-', ''), ('-PAGE', 'PAGE'), ('o-', 'o')]
PHJ18890901-V04-09-page14.txt: [('corn-', 'corn'), ('-', '')]
PHJ18890901-V04-09-page15.txt: [('per-', 'per'), ('---why', '--why')]
PHJ18890901-V04-09-page18.txt: [('conver-', 'conver')]
PHJ18890901-V04-09-page19.txt: [('es-', 'es')]
PHJ18890901-V04-09-page2.txt: [('Ca-', 'Ca'), ('Albu-', 'Albu'), ('ap-', 'ap')]
PHJ18890901-V04-09-page21.txt: [('-should', 'should')]
PHJ18890901-V04-09-page23.txt: [('ordi-', 'ordi')]
PHJ18890901-V04-09-page24.txt: [('al-', 'al')]
PHJ18890901-V04-09-page25.txt: [('Ashby-', 'Ashby'), ("Children's-", "Children's")]
PHJ18890901-V04-09-page26.txt: [('HEL-', 'HEL')]
PHJ18890901-V04-09-page27.txt: [('-PAGE', 'PAGE'), ('-', ''), ('-', ''), ('-Lillie', 'Lillie'), ('Tennessee-', 'Tennessee')]
PHJ18890901-V04-09-page29.txt: [('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('Nat-', 'Nat'), ('La-', 'La'), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', '')]
PHJ18890901-V04-09-page30.txt: [('-', ''), ('-', ''), ('-', '')]
PHJ18890901-V04-09-page31.txt: [('-', '')]
PHJ18890901-V04-09-page4.txt: [('-', ''), ('air."--', 'air."-')]
PHJ18890901-V04-09-page5.txt: [('ex-', 'ex')]
PHJ18890901-V04-09-page6.txt: [('wife.--', 'wife.-')]
PHJ18890901-V04-09-page8.txt: [('dy-', 'dy')]
PHJ18891001-V04-10-page1.txt: [('-', ''), ('-PAGE', 'PAGE'), ('stom-', 'stom')]
PHJ18891001-V04-10-page11.txt: [('-', '')]
PHJ18891001-V04-10-page12.txt: [('stupify-', 'stupify')]
PHJ18891001-V04-10-page15.txt: [('com-', 'com')]
PHJ18891001-V04-10-page16.txt: [('island-', 'island')]
PHJ18891001-V04-10-page17.txt: [('peo-', 'peo'), ('sick-', 'sick')]
PHJ18891001-V04-10-page20.txt: [('fel-', 'fel')]
PHJ18891001-V04-10-page21.txt: [('ques-', 'ques')]
PHJ18891001-V04-10-page26.txt: [('-page', 'page')]
PHJ18891001-V04-10-page27.txt: [('-PAGE', 'PAGE'), ('-everal', 'everal'), ('-THE', 'THE'), ('Society-', 'Society'), ('-Lillie', 'Lillie'), ('-', ''), ('-', '')]
PHJ18891001-V04-10-page28.txt: [('.-', '.')]
PHJ18891001-V04-10-page29.txt: [('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('quarts----', 'quarts---'), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('La-', 'La'), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('--', '-'), ('-', '')]
PHJ18891001-V04-10-page30.txt: [('COMBINING-', 'COMBINING')]
PHJ18891001-V04-10-page31.txt: [('-', ''), ('-page', 'page')]
PHJ18891001-V04-10-page32.txt: [('--', '-'), ('-', ''), ('--z.', '-z.'), ('IR-', 'IR'), ('-', ''), ('--', '-')]
PHJ18891001-V04-10-page6.txt: [('--', '-')]
PHJ18891101-V04-11-page1.txt: [('-.P', '.P'), ('antifi-', 'antifi')]
PHJ18891101-V04-11-page13.txt: [('gen-', 'gen')]
PHJ18891101-V04-11-page14.txt: [('physi-', 'physi'), ('stimula-', 'stimula')]
PHJ18891101-V04-11-page15.txt: [('Inter-', 'Inter')]
PHJ18891101-V04-11-page17.txt: [('ab-', 'ab')]
PHJ18891101-V04-11-page21.txt: [('--', '-'), ('pro-', 'pro')]
PHJ18891101-V04-11-page24.txt: [('-hygiene', 'hygiene')]
PHJ18891101-V04-11-page25.txt: [("Children's-", "Children's")]
PHJ18891101-V04-11-page26.txt: [('TEM-', 'TEM')]
PHJ18891101-V04-11-page27.txt: [('-Lillie', 'Lillie'), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', '')]
PHJ18891101-V04-11-page29.txt: [('World.-', 'World.'), ('--', '-'), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('publi-', 'publi'), ('-', '')]
PHJ18891101-V04-11-page30.txt: [('-', ''), ('-', ''), ('-', ''), ('-', '')]
PHJ18891101-V04-11-page31.txt: [('-', ''), ('-page', 'page')]
PHJ18891101-V04-11-page32.txt: [('es-', 'es'), ('GA-', 'GA')]
PHJ18891101-V04-11-page6.txt: [('ear-', 'ear')]
PHJ18891101-V04-11-page7.txt: [('Ro-', 'Ro')]
PHJ18891101-V04-11-page8.txt: [('acknowl-', 'acknowl'), ('tempta-', 'tempta')]
PHJ18891101-V04-11-page9.txt: [('im-', 'im'), ('over-', 'over')]
PHJ18891201-V04-12-page1.txt: [('-', ''), ('-P', 'P')]
PHJ18891201-V04-12-page12.txt: [('mas-', 'mas')]
PHJ18891201-V04-12-page13.txt: [('-', '')]
PHJ18891201-V04-12-page14.txt: [('-', '')]
PHJ18891201-V04-12-page17.txt: [('-EDITOR', 'EDITOR')]
PHJ18891201-V04-12-page19.txt: [('Stiff-', 'Stiff')]
PHJ18891201-V04-12-page21.txt: [('meet-', 'meet'), ('immedi-', 'immedi'), ('familiar-', 'familiar'), ('cer-', 'cer'), ('be-', 'be')]
PHJ18891201-V04-12-page29.txt: [('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', '')]
PHJ18891201-V04-12-page30.txt: [('--', '-')]
PHJ18891201-V04-12-page31.txt: [('-', ''), ('-page', 'page')]
PHJ18891201-V04-12-page32.txt: [('Li-', 'Li'), ('-', '')]
PHJ18891201-V04-12-page33.txt: [('died-', 'died'), ('-', ''), ('-', ''), ('-', ''), ('absti-', 'absti'), ('-', ''), ('-', '')]
PHJ18891201-V04-12-page34.txt: [('-orming', 'orming'), ('-', ''), ('chil-', 'chil'), ('-', '')]
PHJ18891201-V04-12-page7.txt: [('-', ''), ('-', '')]
PHJ18900101-V05-01-page1.txt: [('-', ''), ('ad-', 'ad'), ('-dressed', 'dressed'), ('-', '')]
PHJ18900101-V05-01-page11.txt: [('ex-', 'ex'), ('par-', 'par')]
PHJ18900101-V05-01-page12.txt: [('de-', 'de')]
PHJ18900101-V05-01-page13.txt: [('com-', 'com')]
PHJ18900101-V05-01-page15.txt: [('police-', 'police'), ('occa-', 'occa')]
PHJ18900101-V05-01-page17.txt: [('awak-', 'awak')]
PHJ18900101-V05-01-page19.txt: [('-which', 'which')]
PHJ18900101-V05-01-page24.txt: [('compres-', 'compres')]
PHJ18900101-V05-01-page25.txt: [('-', '')]
PHJ18900101-V05-01-page27.txt: [('Society-', 'Society'), ('-Lillie', 'Lillie')]
PHJ18900101-V05-01-page28.txt: [('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('La-', 'La'), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', '')]
PHJ18900101-V05-01-page29.txt: [('-FOR', 'FOR'), ('-page', 'page')]
PHJ18900101-V05-01-page30.txt: [('-', '')]
PHJ18900101-V05-01-page31.txt: [('es-', 'es')]
PHJ18900101-V05-01-page32.txt: [('-', ''), ('-Orders', 'Orders')]
PHJ18900101-V05-01-page6.txt: [('feet-', 'feet'), ('-"and', '"and')]
PHJ18900101-V05-01-page9.txt: [('temp-', 'temp'), ('pat-', 'pat')]
PHJ18900201-V05-02-page1.txt: [('-', ''), ('-', ''), ('-PAGE', 'PAGE')]
PHJ18900201-V05-02-page10.txt: [('to-', 'to')]
PHJ18900201-V05-02-page14.txt: [('neighbor-', 'neighbor')]
PHJ18900201-V05-02-page15.txt: [('-', ''), ('under-', 'under')]
PHJ18900201-V05-02-page16.txt: [('at-', 'at'), ('-', ''), ('di-', 'di')]
PHJ18900201-V05-02-page17.txt: [('ex-', 'ex'), ('un-', 'un')]
PHJ18900201-V05-02-page2.txt: [('ab-', 'ab')]
PHJ18900201-V05-02-page27.txt: [('Society-', 'Society'), ('-Lillie', 'Lillie'), ('Tennessee-', 'Tennessee')]
PHJ18900201-V05-02-page28.txt: [('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-Ire', 'Ire'), ('Md.-', 'Md.'), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', '')]
PHJ18900201-V05-02-page29.txt: [('secur-', 'secur'), ('-page', 'page')]
PHJ18900201-V05-02-page3.txt: [('...-', '...'), ('-', ''), ('..-', '..'), ('-.VT', '.VT')]
PHJ18900201-V05-02-page30.txt: [('-', ''), ('-PAGE', 'PAGE'), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', '')]
PHJ18900201-V05-02-page31.txt: [('-', '')]
PHJ18900201-V05-02-page4.txt: [('-', '')]
PHJ18900201-V05-02-page5.txt: [('in-', 'in'), ('investi-', 'investi'), ('aw-', 'aw'), ('vil-', 'vil')]
PHJ18900201-V05-02-page7.txt: [('-', ''), ('-', ''), ('-', ''), ('re-', 're')]
PHJ18900301-V05-03-page1.txt: [('-PAGE', 'PAGE'), ('-', ''), ('-', '')]
PHJ18900301-V05-03-page13.txt: [('-caliber', 'caliber')]
PHJ18900301-V05-03-page15.txt: [('-', '')]
PHJ18900301-V05-03-page16.txt: [('ache-', 'ache'), ('--', '-')]
PHJ18900301-V05-03-page18.txt: [('abomi-', 'abomi')]
PHJ18900301-V05-03-page21.txt: [('-', '')]
PHJ18900301-V05-03-page22.txt: [('When-', 'When')]
PHJ18900301-V05-03-page23.txt: [('con-', 'con'), ('be-', 'be')]
PHJ18900301-V05-03-page24.txt: [('measure-', 'measure')]
PHJ18900301-V05-03-page26.txt: [('"Non-', '"Non')]
PHJ18900301-V05-03-page27.txt: [('---', '--')]
PHJ18900301-V05-03-page28.txt: [('stock-', 'stock')]
PHJ18900301-V05-03-page29.txt: [('-', '')]
PHJ18900301-V05-03-page30.txt: [('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-I', 'I'), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('quarts-', 'quarts'), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('quarts----', 'quarts---'), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', '')]
PHJ18900301-V05-03-page32.txt: [('-', ''), ('RESTTeI-', 'RESTTeI'), ('Garri-', 'Garri')]
PHJ18900401-V05-04-page1.txt: [('-', ''), ('-', '')]
PHJ18900401-V05-04-page11.txt: [('-', '')]
PHJ18900401-V05-04-page13.txt: [('de-', 'de')]
PHJ18900401-V05-04-page14.txt: [('Con-', 'Con')]
PHJ18900401-V05-04-page17.txt: [('nour-', 'nour'), ('mat-', 'mat')]
PHJ18900401-V05-04-page21.txt: [('Look-', 'Look'), ('to-', 'to'), ('--', '-')]
PHJ18900401-V05-04-page22.txt: [('re-', 're')]
PHJ18900401-V05-04-page24.txt: [('"abstain-', '"abstain')]
PHJ18900401-V05-04-page26.txt: [('Re-', 'Re')]
PHJ18900401-V05-04-page27.txt: [('-Deseret', 'Deseret')]
PHJ18900401-V05-04-page28.txt: [('-', '')]
PHJ18900401-V05-04-page29.txt: [('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', '')]
PHJ18900401-V05-04-page30.txt: [('-', '')]
PHJ18900401-V05-04-page31.txt: [('-Ts.', 'Ts.'), ('es-', 'es')]
PHJ18900401-V05-04-page32.txt: [('I.-', 'I.'), ('r-', 'r'), ('ilst.-', 'ilst.')]
PHJ18900401-V05-04-page6.txt: [('car-', 'car')]
PHJ18900401-V05-04-page7.txt: [('recogni-', 'recogni'), ('in-', 'in'), ('nu-', 'nu'), ('rela-', 'rela')]
PHJ18900401-V05-04-page8.txt: [('com-', 'com')]
PHJ18900401-V05-04-page9.txt: [('appe-', 'appe')]
PHJ18900501-V05-05-page1.txt: [('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-PAGE', 'PAGE'), ('con-', 'con')]
PHJ18900501-V05-05-page11.txt: [('un-', 'un'), ('in-', 'in'), ('re-', 're')]
PHJ18900501-V05-05-page12.txt: [('-', ''), ('--', '-'), ('con-', 'con')]
PHJ18900501-V05-05-page14.txt: [('-', ''), ('-', '')]
PHJ18900501-V05-05-page15.txt: [('-', '')]
PHJ18900501-V05-05-page18.txt: [('ac-', 'ac')]
PHJ18900501-V05-05-page19.txt: [('con-', 'con')]
PHJ18900501-V05-05-page20.txt: [('H.-', 'H.')]
PHJ18900501-V05-05-page21.txt: [('impor-', 'impor')]
PHJ18900501-V05-05-page22.txt: [('let-', 'let')]
PHJ18900501-V05-05-page23.txt: [('decom-', 'decom'), ('cot-', 'cot')]
PHJ18900501-V05-05-page26.txt: [('Mc-', 'Mc'), ('JOUR-', 'JOUR')]
PHJ18900501-V05-05-page27.txt: [('Society-', 'Society'), ('Society-', 'Society'), ('-J.', 'J.')]
PHJ18900501-V05-05-page28.txt: [('-', ''), ('-', '')]
PHJ18900501-V05-05-page29.txt: [('-', '')]
PHJ18900501-V05-05-page30.txt: [('tele-', 'tele')]
PHJ18900501-V05-05-page31.txt: [('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', '')]
PHJ18900501-V05-05-page32.txt: [('-', '')]
PHJ18900501-V05-05-page8.txt: [('be-', 'be')]
PHJ18900601-V05-06-page1.txt: [('-PAGE', 'PAGE')]
PHJ18900601-V05-06-page12.txt: [('-thought', 'thought')]
PHJ18900601-V05-06-page13.txt: [('run-', 'run')]
PHJ18900601-V05-06-page15.txt: [('in-', 'in')]
PHJ18900601-V05-06-page18.txt: [('MURRAIN.-', 'MURRAIN.')]
PHJ18900601-V05-06-page2.txt: [('-', '')]
PHJ18900601-V05-06-page23.txt: [('am-', 'am')]
PHJ18900601-V05-06-page24.txt: [('produc-', 'produc')]
PHJ18900601-V05-06-page25.txt: [('--."', '-."')]
PHJ18900601-V05-06-page26.txt: [('-', '')]
PHJ18900601-V05-06-page27.txt: [('Society-', 'Society'), ('Society-', 'Society'), ('-J.', 'J.'), ('Lincoln-', 'Lincoln'), ('Lancet-', 'Lancet')]
PHJ18900601-V05-06-page29.txt: [('-', '')]
PHJ18900601-V05-06-page3.txt: [('grad-', 'grad')]
PHJ18900601-V05-06-page30.txt: [('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', '')]
PHJ18900601-V05-06-page31.txt: [('-e', 'e'), ('-', '')]
PHJ18900601-V05-06-page32.txt: [('-', ''), ('-idesiring', 'idesiring'), ('tele-', 'tele')]
PHJ18900601-V05-06-page5.txt: [('re-', 're')]
PHJ18900601-V05-06-page6.txt: [('sys-', 'sys')]
PHJ18900701-V05-07-page1.txt: [('-', ''), ('-', '')]
PHJ18900701-V05-07-page13.txt: [('Tem-', 'Tem')]
PHJ18900701-V05-07-page19.txt: [('ousel-', 'ousel')]
PHJ18900701-V05-07-page22.txt: [('com-', 'com'), ('de-', 'de'), ('hun-', 'hun'), ('ex-', 'ex')]
PHJ18900701-V05-07-page25.txt: [('CLOTHING.-', 'CLOTHING.')]
PHJ18900701-V05-07-page26.txt: [('SUR-', 'SUR'), ('-', '')]
PHJ18900701-V05-07-page27.txt: [('Society-', 'Society'), ('Society-', 'Society'), ('-J.', 'J.'), ('Lincoln-', 'Lincoln')]
PHJ18900701-V05-07-page29.txt: [('-', '')]
PHJ18900701-V05-07-page3.txt: [('major-', 'major')]
PHJ18900701-V05-07-page30.txt: [('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('La-', 'La'), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', '')]
PHJ18900701-V05-07-page31.txt: [('.twani-', '.twani'), ('-', ''), ('-', ''), ('.-', '.'), ('-', '')]
PHJ18900701-V05-07-page32.txt: [('apply-', 'apply')]
PHJ18900701-V05-07-page4.txt: [('deodor-', 'deodor')]
PHJ18900701-V05-07-page5.txt: [('SELF-', 'SELF')]
PHJ18900701-V05-07-page6.txt: [('INDEPEND-', 'INDEPEND'), ('con-', 'con'), ('reduc-', 'reduc')]
PHJ18900801-V05-08-page1.txt: [('-', '')]
PHJ18900801-V05-08-page12.txt: [('-', '')]
PHJ18900801-V05-08-page15.txt: [('side-', 'side')]
PHJ18900801-V05-08-page18.txt: [('pre-', 'pre'), ('immedi-', 'immedi')]
PHJ18900801-V05-08-page2.txt: [('-', ''), ('quanti-', 'quanti'), ('-', '')]
PHJ18900801-V05-08-page20.txt: [('-', '')]
PHJ18900801-V05-08-page23.txt: [('ex-', 'ex'), ('hap-', 'hap'), ('treat-', 'treat'), ('at-', 'at')]
PHJ18900801-V05-08-page26.txt: [('PROHIBI-', 'PROHIBI'), ('SUR-', 'SUR')]
PHJ18900801-V05-08-page27.txt: [('civiliza-', 'civiliza'), ('-page', 'page')]
PHJ18900801-V05-08-page28.txt: [('corn-', 'corn'), ('im-', 'im')]
PHJ18900801-V05-08-page29.txt: [('-', ''), ('-', ''), ('La-', 'La'), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('Cata-', 'Cata'), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', '')]
PHJ18900801-V05-08-page30.txt: [('-i', 'i'), ('-Unparalleled', 'Unparalleled'), ('-', '')]
PHJ18900801-V05-08-page31.txt: [('Corres-', 'Corres')]
PHJ18900801-V05-08-page32.txt: [('--', '-'), ('-', ''), ('-', '')]
PHJ18900801-V05-08-page7.txt: [('self-', 'self')]
PHJ18900901-V05-09-page1.txt: [('-F', 'F')]
PHJ18900901-V05-09-page13.txt: [('--', '-'), ('-', '')]
PHJ18900901-V05-09-page14.txt: [('Fif-', 'Fif')]
PHJ18900901-V05-09-page15.txt: [('impair-', 'impair')]
PHJ18900901-V05-09-page16.txt: [('condition--', 'condition-')]
PHJ18900901-V05-09-page17.txt: [('con-', 'con')]
PHJ18900901-V05-09-page21.txt: [('min-', 'min')]
PHJ18900901-V05-09-page22.txt: [('one-', 'one')]
PHJ18900901-V05-09-page23.txt: [('in-', 'in')]
PHJ18900901-V05-09-page26.txt: [('Record-', 'Record')]
PHJ18900901-V05-09-page27.txt: [('-food', 'food'), ('-page', 'page'), ('dice-', 'dice'), ('Society-', 'Society'), ('Society-', 'Society'), ('-J.', 'J.'), ('Lincoln-', 'Lincoln'), ('-T.', 'T.'), ('Switzerland-', 'Switzerland'), ('Tennessee-', 'Tennessee')]
PHJ18900901-V05-09-page28.txt: [('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('------', '-----'), ('Warrant-', 'Warrant'), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', '')]
PHJ18900901-V05-09-page29.txt: [('com-', 'com')]
PHJ18900901-V05-09-page31.txt: [('WORLD.-', 'WORLD.'), ('-make', 'make')]
PHJ18900901-V05-09-page32.txt: [('E-', 'E'), ('E-', 'E'), ('-DOORS', 'DOORS'), ('pock-', 'pock'), ('---', '--')]
PHJ18900901-V05-09-page9.txt: [('quota-', 'quota'), ('com-', 'com'), ('uncom-', 'uncom'), ('mov-', 'mov')]
PHJ18901001-V05-10-page1.txt: [('-', ''), ('pa-', 'pa'), ('conta-', 'conta')]
PHJ18901001-V05-10-page15.txt: [('seer-', 'seer')]
PHJ18901001-V05-10-page16.txt: [('LIQ-', 'LIQ'), ('temper-', 'temper')]
PHJ18901001-V05-10-page17.txt: [('fanatic.--', 'fanatic.-')]
PHJ18901001-V05-10-page18.txt: [('-', '')]
PHJ18901001-V05-10-page2.txt: [('-', '')]
PHJ18901001-V05-10-page22.txt: [('"bil-', '"bil')]
PHJ18901001-V05-10-page26.txt: [('CON-', 'CON')]
PHJ18901001-V05-10-page27.txt: [('-page', 'page'), ('-page', 'page'), ('-page', 'page'), ('Society-', 'Society'), ('Society-', 'Society'), ('-J.', 'J.')]
PHJ18901001-V05-10-page28.txt: [('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('---', '--'), ('--', '-'), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('------', '-----'), ('La-', 'La'), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', '')]
PHJ18901001-V05-10-page31.txt: [('tele-', 'tele'), ("'--", "'-")]
PHJ18901001-V05-10-page32.txt: [('SATURDAY.-', 'SATURDAY.')]
PHJ18901101-V05-11-page1.txt: [('-', ''), ('ex-', 'ex')]
PHJ18901101-V05-11-page12.txt: [('par-', 'par'), ('gen-', 'gen')]
PHJ18901101-V05-11-page13.txt: [('lounge-', 'lounge')]
PHJ18901101-V05-11-page14.txt: [('respect-', 'respect')]
PHJ18901101-V05-11-page19.txt: [('IN-', 'IN')]
PHJ18901101-V05-11-page2.txt: [("-'", "'")]
PHJ18901101-V05-11-page20.txt: [('vege-', 'vege')]
PHJ18901101-V05-11-page26.txt: [('ASSOCIA-', 'ASSOCIA'), ('-', ''), ('-WHEREAS', 'WHEREAS')]
PHJ18901101-V05-11-page27.txt: [('Society-', 'Society'), ('Sub-', 'Sub')]
PHJ18901101-V05-11-page28.txt: [('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('La-', 'La'), ('lltho-', 'lltho'), ('i.ata-', 'i.ata'), ('-', ''), ('quarts-', 'quarts'), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', '')]
PHJ18901101-V05-11-page3.txt: [('-at', 'at')]
PHJ18901101-V05-11-page31.txt: [('Tel-', 'Tel'), ('In-', 'In'), ('tele-', 'tele'), ('-', '')]
PHJ18901101-V05-11-page32.txt: [('E-', 'E'), ('-', ''), ('-', ''), ('E-', 'E'), ('-', '')]
PHJ18901101-V05-11-page6.txt: [('-', ''), ('-', '')]
PHJ18901101-V05-11-page9.txt: [('Gilles-de-la-', 'Gilles-de-la')]
PHJ18901201-V05-12-page1.txt: [('-.Pzi', '.Pzi'), ('Jour-', 'Jour'), ('al-', 'al')]
PHJ18901201-V05-12-page11.txt: [('inter-', 'inter')]
PHJ18901201-V05-12-page12.txt: [('abste-', 'abste')]
PHJ18901201-V05-12-page14.txt: [('DRUNK-', 'DRUNK'), ('-', '')]
PHJ18901201-V05-12-page17.txt: [('-', ''), ('dainty-', 'dainty')]
PHJ18901201-V05-12-page2.txt: [('dan-', 'dan')]
PHJ18901201-V05-12-page22.txt: [('Dis-', 'Dis')]
PHJ18901201-V05-12-page26.txt: [('-', ''), ('PA-', 'PA'), ('-page', 'page'), ('sage-', 'sage')]
PHJ18901201-V05-12-page27.txt: [('-page', 'page')]
PHJ18901201-V05-12-page28.txt: [('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('"-', '"'), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('For-', 'For'), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', '')]
PHJ18901201-V05-12-page3.txt: [('-', ''), ('--those', '-those')]
PHJ18901201-V05-12-page30.txt: [('ara---', 'ara--'), ('Tr."-', 'Tr."'), ("-'", "'"), ('Typo-', 'Typo'), ('corres--', 'corres-'), ('--', '-'), ("Itl'-", "Itl'")]
PHJ18901201-V05-12-page31.txt: [('tele-', 'tele')]
PHJ18901201-V05-12-page33.txt: [('-a', 'a'), ('-', '')]
PHJ18901201-V05-12-page34.txt: [('-', '')]
PHJ18901201-V05-12-page4.txt: [('con-', 'con'), ('through-', 'through')]
PHJ18910101-V06-01-page1.txt: [('-', ''), ('-P', 'P'), ('EAT-', 'EAT')]
PHJ18910101-V06-01-page15.txt: [('go-', 'go'), ('re-', 're')]
PHJ18910101-V06-01-page19.txt: [('re-', 're')]
PHJ18910101-V06-01-page2.txt: [('nutrition-', 'nutrition'), ('in-', 'in'), ('sow-', 'sow')]
PHJ18910101-V06-01-page23.txt: [('de-', 'de'), ('ab-', 'ab'), ('some-', 'some'), ('con-', 'con'), ('spar-', 'spar')]
PHJ18910101-V06-01-page24.txt: [('-with', 'with')]
PHJ18910101-V06-01-page25.txt: [('INDIA.-', 'INDIA.'), ('-', '')]
PHJ18910101-V06-01-page26.txt: [('-', ''), ('JOUR-', 'JOUR')]
PHJ18910101-V06-01-page27.txt: [('-page', 'page')]
PHJ18910101-V06-01-page28.txt: [('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('--', '-'), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('La-', 'La'), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('treat-', 'treat')]
PHJ18910101-V06-01-page3.txt: [('-when', 'when')]
PHJ18910101-V06-01-page32.txt: [('-', ''), ("'-", "'"), ('--....', '-....'), ('.--', '.-'), (".'-", ".'"), ('--"', '-"'), ('-ir', 'ir'), ('-', ''), ('-', ''), ('Type-', 'Type'), ('Inter-', 'Inter'), ('corres-', 'corres'), ('--', '-'), ('-gia.', 'gia.'), ('-tftl', 'tftl'), ('-e', 'e'), ('-', ''), ('--', '-')]
PHJ18910101-V06-01-page5.txt: [('--', '-'), ('-', ''), ('peo-', 'peo'), ('health-', 'health')]
PHJ18910101-V06-01-page8.txt: [('OPPOR-', 'OPPOR')]
PHJ18910101-V06-01-page9.txt: [('hpsys-', 'hpsys')]
PHJ18910201-V06-02-page1.txt: [('-PAGE', 'PAGE')]
PHJ18910201-V06-02-page12.txt: [('-on', 'on')]
PHJ18910201-V06-02-page18.txt: [('re-', 're'), ('Courier-', 'Courier'), ('SHIR-', 'SHIR')]
PHJ18910201-V06-02-page27.txt: [('Health-', 'Health'), ('-t', 't'), ('ad-', 'ad')]
PHJ18910201-V06-02-page28.txt: [('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', '')]
PHJ18910201-V06-02-page29.txt: [('-', ''), ('stock-', 'stock')]
PHJ18910201-V06-02-page31.txt: [('-', '')]
PHJ18910201-V06-02-page32.txt: [('-Tn', 'Tn'), ('-r', 'r'), ('Type-', 'Type'), ('Inter-', 'Inter'), ('corres-', 'corres'), ('--', '-'), ('..--', '..-')]
PHJ18910201-V06-02-page8.txt: [('COR-', 'COR'), ('con-', 'con')]
PHJ18910201-V06-02-page9.txt: [('pre-', 'pre')]
PHJ18910301-V06-03-page1.txt: [('-', ''), ('EAT-', 'EAT')]
PHJ18910301-V06-03-page13.txt: [('al-', 'al'), ('-of', 'of')]
PHJ18910301-V06-03-page14.txt: [('fel-', 'fel')]
PHJ18910301-V06-03-page17.txt: [('sweet-', 'sweet')]
PHJ18910301-V06-03-page19.txt: [('fami-', 'fami')]
PHJ18910301-V06-03-page2.txt: [('-lot', 'lot'), ('use-', 'use')]
PHJ18910301-V06-03-page23.txt: [('learn-', 'learn'), ('use-', 'use')]
PHJ18910301-V06-03-page24.txt: [('--', '-'), ('pro-', 'pro')]
PHJ18910301-V06-03-page28.txt: [('-looking."', 'looking."'), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', '')]
PHJ18910301-V06-03-page30.txt: [('PEI-IPSO-', 'PEI-IPSO')]
PHJ18910301-V06-03-page31.txt: [('Birth-', 'Birth')]
PHJ18910301-V06-03-page32.txt: [('-Arica', 'Arica'), ('Type-', 'Type'), ('corres-', 'corres'), ('--', '-')]
PHJ18910401-V06-04-page1.txt: [('-PAGE', 'PAGE'), ('re-', 're')]
PHJ18910401-V06-04-page10.txt: [('some-', 'some')]
PHJ18910401-V06-04-page11.txt: [('IN-', 'IN')]
PHJ18910401-V06-04-page12.txt: [('-', ''), ('-', '')]
PHJ18910401-V06-04-page13.txt: [('-', '')]
PHJ18910401-V06-04-page14.txt: [('-', '')]
PHJ18910401-V06-04-page17.txt: [('un-', 'un')]
PHJ18910401-V06-04-page24.txt: [('prosper-', 'prosper')]
PHJ18910401-V06-04-page25.txt: [('atmos-', 'atmos')]
PHJ18910401-V06-04-page29.txt: [('-', '')]
PHJ18910401-V06-04-page3.txt: [('lux-', 'lux')]
PHJ18910401-V06-04-page30.txt: [('--', '-'), ('pock-', 'pock')]
PHJ18910401-V06-04-page31.txt: [('-ow', 'ow'), ('-Ts.', 'Ts.'), ('MO-', 'MO')]
PHJ18910401-V06-04-page32.txt: [('corres-', 'corres'), ('--', '-')]
PHJ18910401-V06-04-page4.txt: [('alco-', 'alco')]
PHJ18910501-V06-05-page1.txt: [('-PAGE', 'PAGE')]
PHJ18910501-V06-05-page10.txt: [('-IXALTH', 'IXALTH')]
PHJ18910501-V06-05-page11.txt: [('recom-', 'recom')]
PHJ18910501-V06-05-page12.txt: [('-', ''), ('IN-', 'IN')]
PHJ18910501-V06-05-page14.txt: [('farm-', 'farm')]
PHJ18910501-V06-05-page15.txt: [('constitu-', 'constitu'), ('man-', 'man'), ('im-', 'im')]
PHJ18910501-V06-05-page16.txt: [('-', '')]
PHJ18910501-V06-05-page17.txt: [('-', ''), ('-', '')]
PHJ18910501-V06-05-page2.txt: [('dimin-', 'dimin')]
PHJ18910501-V06-05-page20.txt: [('-', '')]
PHJ18910501-V06-05-page25.txt: [('Al-', 'Al')]
PHJ18910501-V06-05-page27.txt: [('-From', 'From'), ('-ook', 'ook'), ('-development', 'development'), ('-', '')]
PHJ18910501-V06-05-page28.txt: [('absorb-', 'absorb')]
PHJ18910501-V06-05-page29.txt: [('-FOR-', 'FOR-')]
PHJ18910501-V06-05-page31.txt: [('-', ''), ('.--', '.-')]
PHJ18910501-V06-05-page32.txt: [('-', ''), ('-', ''), ('corres-', 'corres'), ('--', '-')]
PHJ18910501-V06-05-page5.txt: [('de-', 'de')]
PHJ18910501-V06-05-page9.txt: [('DYS-', 'DYS')]
PHJ18910601-V06-06-page1.txt: [('-', ''), ('-', ''), ('-PAGE', 'PAGE')]
PHJ18910601-V06-06-page10.txt: [('sup-', 'sup'), ('mal-', 'mal')]
PHJ18910601-V06-06-page11.txt: [('use-', 'use')]
PHJ18910601-V06-06-page13.txt: [('CI-', 'CI'), ('I-', 'I'), ('nine-', 'nine')]
PHJ18910601-V06-06-page15.txt: [('TO-', 'TO'), ('re-', 're')]
PHJ18910601-V06-06-page17.txt: [('-', '')]
PHJ18910601-V06-06-page19.txt: [('recom-', 'recom'), ('mis-', 'mis')]
PHJ18910601-V06-06-page23.txt: [('-sensible', 'sensible')]
PHJ18910601-V06-06-page27.txt: [('mu-', 'mu')]
PHJ18910601-V06-06-page28.txt: [('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', '')]
PHJ18910601-V06-06-page31.txt: [('------', '-----'), ('-.', '.'), ('adver-', 'adver'), ('---', '--'), ('--', '-'), ('Oce-', 'Oce'), ('..---', '..--'), ('-..', '..'), ('..--', '..-'), ('-', ''), ('----', '---'), ('-', ''), ('-', ''), ('-', '')]
PHJ18910601-V06-06-page32.txt: [('j-', 'j'), ('-', ''), ('-', ''), ('.--', '.-'), ('Type-', 'Type'), ('corres-', 'corres'), ('--', '-')]
PHJ18910601-V06-06-page4.txt: [('-', '')]
PHJ18910701-V06-07-page1.txt: [('-', ''), ('-', ''), ('-', ''), ('-PAGE', 'PAGE')]
PHJ18910701-V06-07-page12.txt: [('-those', 'those')]
PHJ18910701-V06-07-page13.txt: [('INTOX-', 'INTOX')]
PHJ18910701-V06-07-page16.txt: [('--man', '-man')]
PHJ18910701-V06-07-page19.txt: [('--picture', '-picture')]
PHJ18910701-V06-07-page24.txt: [('r.-', 'r.')]
PHJ18910701-V06-07-page25.txt: [('-the', 'the')]
PHJ18910701-V06-07-page26.txt: [('un-', 'un'), ('-', ''), ('JOUR-', 'JOUR'), ('-', '')]
PHJ18910701-V06-07-page28.txt: [('announce-', 'announce'), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ("Children's-", "Children's")]
PHJ18910701-V06-07-page29.txt: [("'Mimic-", "'Mimic")]
PHJ18910701-V06-07-page31.txt: [('-', '')]
PHJ18910701-V06-07-page32.txt: [('--', '-'), ('corres-', 'corres'), ('--', '-')]
PHJ18910701-V06-07-page4.txt: [('advanta-', 'advanta')]
PHJ18910801-V06-08-page1.txt: [('-', ''), ('-', ''), ('-PAGE', 'PAGE')]
PHJ18910801-V06-08-page10.txt: [('-IVIrsr', 'IVIrsr')]
PHJ18910801-V06-08-page11.txt: [('per-', 'per'), ('ar-', 'ar'), ('med-', 'med')]
PHJ18910801-V06-08-page16.txt: [('free.--', 'free.-')]
PHJ18910801-V06-08-page19.txt: [('hys-', 'hys')]
PHJ18910801-V06-08-page20.txt: [('HKALTI-', 'HKALTI')]
PHJ18910801-V06-08-page21.txt: [('-', ''), ('hu-', 'hu')]
PHJ18910801-V06-08-page22.txt: [('Answers.-', 'Answers.')]
PHJ18910801-V06-08-page23.txt: [('COMMAND-', 'COMMAND'), ('cheap-', 'cheap')]
PHJ18910801-V06-08-page24.txt: [('fa-', 'fa')]
PHJ18910801-V06-08-page27.txt: [('A-', 'A'), ('ND-', 'ND'), ('-', '')]
PHJ18910801-V06-08-page28.txt: [('-', ''), ('-', ''), ('announce-', 'announce'), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('price-', 'price'), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', '')]
PHJ18910801-V06-08-page29.txt: [('corn-', 'corn')]
PHJ18910801-V06-08-page31.txt: [('Par-', 'Par')]
PHJ18910801-V06-08-page32.txt: [('ci--', 'ci-'), ('-', ''), ('-.', '.'), ('-', ''), ('..---', '..--'), ('-"', '"'), ('--', '-'), ('Type-', 'Type'), ('corres-', 'corres'), ('--', '-')]
PHJ18910801-V06-08-page5.txt: [('be-', 'be')]
PHJ18910901-V06-09-page1.txt: [('-', ''), ('-', ''), ('-PAGE', 'PAGE')]
PHJ18910901-V06-09-page13.txt: [('be-', 'be')]
PHJ18910901-V06-09-page15.txt: [('dis-', 'dis')]
PHJ18910901-V06-09-page19.txt: [('-chance', 'chance')]
PHJ18910901-V06-09-page22.txt: [('incom-', 'incom'), ('de-', 'de')]
PHJ18910901-V06-09-page25.txt: [('after-', 'after'), ('susceptibil-', 'susceptibil')]
PHJ18910901-V06-09-page27.txt: [('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', '')]
PHJ18910901-V06-09-page28.txt: [('announce-', 'announce'), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ("Children's-", "Children's")]
PHJ18910901-V06-09-page30.txt: [('circa-', 'circa'), ('World.-', 'World.'), ('-', '')]
PHJ18910901-V06-09-page31.txt: [('w-', 'w'), ('Paz-', 'Paz'), ('MO-', 'MO')]
PHJ18910901-V06-09-page32.txt: [('chil-', 'chil'), ('-', ''), ('-', '')]
PHJ18910901-V06-09-page5.txt: [('--Josephine', '-Josephine')]
PHJ18910901-V06-09-page8.txt: [('pre-', 'pre'), ('anx-', 'anx')]
PHJ18911001-V06-10-page1.txt: [('-', ''), ('-P', 'P'), ('ipe-', 'ipe'), ('impro-', 'impro')]
PHJ18911001-V06-10-page10.txt: [('-', '')]
PHJ18911001-V06-10-page12.txt: [('AL-', 'AL'), ('--Selected.', '-Selected.')]
PHJ18911001-V06-10-page16.txt: [('-lady', 'lady')]
PHJ18911001-V06-10-page17.txt: [('in-', 'in')]
PHJ18911001-V06-10-page20.txt: [('con-', 'con')]
PHJ18911001-V06-10-page21.txt: [('in-', 'in')]
PHJ18911001-V06-10-page22.txt: [('CHOCO-', 'CHOCO'), ('molds-', 'molds')]
PHJ18911001-V06-10-page3.txt: [('-thought', 'thought')]
PHJ18911001-V06-10-page30.txt: [('Chromo-', 'Chromo'), ('-', ''), ('-', ''), ('-', ''), ('-vsrA', 'vsrA')]
PHJ18911001-V06-10-page31.txt: [('-', ''), ('-iotograph', 'iotograph'), ("Bird's-", "Bird's")]
PHJ18911001-V06-10-page32.txt: [('cata-', 'cata'), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', '')]
PHJ18911001-V06-10-page5.txt: [('-', '')]
PHJ18911001-V06-10-page7.txt: [('-', '')]
PHJ18911101-V06-11-page1.txt: [('-', ''), ('-', ''), ('-PAGE', 'PAGE')]
PHJ18911101-V06-11-page10.txt: [('God-', 'God'), ('-funnel', 'funnel')]
PHJ18911101-V06-11-page12.txt: [('-', '')]
PHJ18911101-V06-11-page17.txt: [('but-', 'but'), ('tuber-', 'tuber')]
PHJ18911101-V06-11-page2.txt: [('se-', 'se')]
PHJ18911101-V06-11-page20.txt: [('-', '')]
PHJ18911101-V06-11-page21.txt: [('Brit-', 'Brit')]
PHJ18911101-V06-11-page23.txt: [('ad-', 'ad')]
PHJ18911101-V06-11-page25.txt: [('DRESS-', 'DRESS')]
PHJ18911101-V06-11-page26.txt: [('-pound', 'pound')]
PHJ18911101-V06-11-page28.txt: [('cata-', 'cata'), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', '')]
PHJ18911101-V06-11-page29.txt: [('-', '')]
PHJ18911101-V06-11-page30.txt: [('-', ''), ('-', '')]
PHJ18911101-V06-11-page31.txt: [('--A', '-A'), ('-', ''), ('com-', 'com'), ('-the', 'the'), ('-', ''), ('graphi-', 'graphi'), ('-', ''), ('-', ''), ('in-', 'in'), ('done.-', 'done.'), ('his-', 'his'), ('---....-............z', '--....-............z'), ('book.-', 'book.'), ('-The', 'The')]
PHJ18911101-V06-11-page32.txt: [('-', ''), ('-', ''), ('-', ''), ('-', '')]
PHJ18911101-V06-11-page4.txt: [('man--', 'man-')]
PHJ18911101-V06-11-page5.txt: [('inter-', 'inter')]
PHJ18911101-V06-11-page9.txt: [('appe-', 'appe')]
PHJ18911201-V06-12-page1.txt: [('-PAGE', 'PAGE')]
PHJ18911201-V06-12-page10.txt: [('in-', 'in')]
PHJ18911201-V06-12-page11.txt: [('TO-', 'TO')]
PHJ18911201-V06-12-page22.txt: [('Chem-', 'Chem')]
PHJ18911201-V06-12-page28.txt: [('catalogue-', 'catalogue'), ('cata-', 'cata'), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', '')]
PHJ18911201-V06-12-page30.txt: [('G-', 'G')]
PHJ18911201-V06-12-page31.txt: [('disease--', 'disease-'), ('G-G-', 'G-G'), ('-', ''), ('IN-', 'IN')]
PHJ18911201-V06-12-page32.txt: [('-', ''), ('-', '')]
PHJ18911201-V06-12-page33.txt: [('-', ''), ('-', '')]
PHJ18911201-V06-12-page34.txt: [('-', ''), ('-', ''), ('-', '')]
PHJ18911201-V06-12-page6.txt: [('whole-', 'whole')]
PHJ18920101-V07-01-page1.txt: [('-', ''), ('-PAGE', 'PAGE')]
PHJ18920101-V07-01-page10.txt: [('ex-', 'ex')]
PHJ18920101-V07-01-page12.txt: [('--Selected.', '-Selected.')]
PHJ18920101-V07-01-page20.txt: [('EF-', 'EF')]
PHJ18920101-V07-01-page25.txt: [('self-adorn-', 'self-adorn')]
PHJ18920101-V07-01-page27.txt: [('Ir-', 'Ir')]
PHJ18920101-V07-01-page28.txt: [('-page', 'page'), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('ADVERTIS-', 'ADVERTIS'), ('-', ''), ('-', ''), ('-', '')]
PHJ18920101-V07-01-page29.txt: [('r-', 'r'), ('-fho', 'fho'), ('-', '')]
PHJ18920101-V07-01-page30.txt: [('-', '')]
PHJ18920101-V07-01-page31.txt: [('Ingrow-', 'Ingrow'), ('G-', 'G'), ('-', ''), ('-z', 'z'), ('sell-', 'sell'), ('IN-', 'IN'), ('--', '-')]
PHJ18920101-V07-01-page6.txt: [('DIS-', 'DIS')]
PHJ18920101-V07-01-page7.txt: [('-', '')]
PHJ18920101-V07-01-page9.txt: [('gentle-', 'gentle')]
PHJ18920201-V07-02-page1.txt: [('-', ''), ('-PAGE', 'PAGE')]
PHJ18920201-V07-02-page12.txt: [('-', '')]
PHJ18920201-V07-02-page15.txt: [('-', ''), ('-', '')]
PHJ18920201-V07-02-page2.txt: [('con-', 'con')]
PHJ18920201-V07-02-page20.txt: [('in-', 'in')]
PHJ18920201-V07-02-page22.txt: [('-', ''), ('-', ''), ('--', '-'), ('-', '')]
PHJ18920201-V07-02-page25.txt: [('investi-', 'investi')]
PHJ18920201-V07-02-page26.txt: [('diagram.--', 'diagram.-')]
PHJ18920201-V07-02-page27.txt: [('prog-', 'prog'), ('Secretary-', 'Secretary')]
PHJ18920201-V07-02-page28.txt: [('ADVERTIS-', 'ADVERTIS'), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', '')]
PHJ18920201-V07-02-page30.txt: [('-ant', 'ant'), ('work."-', 'work."'), ('-', ''), ('-Bible', 'Bible'), ('-Ax', 'Ax')]
PHJ18920201-V07-02-page31.txt: [('-', ''), ('-', ''), ('-OF', 'OF')]
PHJ18920201-V07-02-page6.txt: [('suf-', 'suf'), ('stom-', 'stom')]
PHJ18920201-V07-02-page9.txt: [('re-', 're')]
PHJ18920301-V07-03-page1.txt: [('-', ''), ('-PAGE', 'PAGE')]
PHJ18920301-V07-03-page10.txt: [('-r', 'r')]
PHJ18920301-V07-03-page13.txt: [('-mss', 'mss')]
PHJ18920301-V07-03-page17.txt: [('-', '')]
PHJ18920301-V07-03-page19.txt: [('--upon', '-upon')]
PHJ18920301-V07-03-page20.txt: [('tray-', 'tray')]
PHJ18920301-V07-03-page25.txt: [('--', '-')]
PHJ18920301-V07-03-page27.txt: [('NEWS-', 'NEWS'), ('illus-', 'illus')]
PHJ18920301-V07-03-page28.txt: [('-page', 'page'), ('ADVERTIS-', 'ADVERTIS'), ('-PUBLISHERS', 'PUBLISHERS'), ('the-', 'the'), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', '')]
PHJ18920301-V07-03-page30.txt: [('--rice', '-rice')]
PHJ18920301-V07-03-page31.txt: [('-FOR-', 'FOR-')]
PHJ18920301-V07-03-page32.txt: [('brevi-', 'brevi'), ('Washing-', 'Washing')]
PHJ18920301-V07-03-page4.txt: [('-', '')]
PHJ18920301-V07-03-page9.txt: [('-the', 'the')]
PHJ18920401-V07-04-page1.txt: [('-PAGE', 'PAGE'), ('Dr-', 'Dr')]
PHJ18920401-V07-04-page10.txt: [('-U', 'U')]
PHJ18920401-V07-04-page11.txt: [('con-', 'con'), ('-', '')]
PHJ18920401-V07-04-page12.txt: [('hope-', 'hope')]
PHJ18920401-V07-04-page13.txt: [('---', '--'), ('-', ''), ('harm-', 'harm')]
PHJ18920401-V07-04-page2.txt: [('Ian-', 'Ian')]
PHJ18920401-V07-04-page20.txt: [("-'-'", "'-'")]
PHJ18920401-V07-04-page21.txt: [('-', '')]
PHJ18920401-V07-04-page26.txt: [('-', '')]
PHJ18920401-V07-04-page28.txt: [('COR-', 'COR'), ('digestion-', 'digestion')]
PHJ18920401-V07-04-page29.txt: [('-etreatb.', 'etreatb.')]
PHJ18920401-V07-04-page3.txt: [('re-', 're')]
PHJ18920401-V07-04-page30.txt: [('de-', 'de')]
PHJ18920401-V07-04-page32.txt: [('ADVERTIS-', 'ADVERTIS'), ('-page', 'page'), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', '')]
PHJ18920401-V07-04-page5.txt: [('employment--', 'employment-'), ('-', '')]
PHJ18920401-V07-04-page6.txt: [('BY-', 'BY')]
PHJ18920401-V07-04-page7.txt: [('-vrr', 'vrr')]
PHJ18920401-V07-04-page9.txt: [('-', '')]
PHJ18920501-V07-05-page1.txt: [('-PAGE', 'PAGE')]
PHJ18920501-V07-05-page11.txt: [('-', '')]
PHJ18920501-V07-05-page15.txt: [('-', '')]
PHJ18920501-V07-05-page16.txt: [('-', '')]
PHJ18920501-V07-05-page19.txt: [('-', '')]
PHJ18920501-V07-05-page20.txt: [('infant-', 'infant')]
PHJ18920501-V07-05-page21.txt: [('-', '')]
PHJ18920501-V07-05-page22.txt: [('--', '-'), ('-', ''), ('I-', 'I')]
PHJ18920501-V07-05-page24.txt: [('COR-', 'COR'), ('con-', 'con')]
PHJ18920501-V07-05-page25.txt: [('cos-', 'cos')]
PHJ18920501-V07-05-page27.txt: [('-page', 'page'), ('-', '')]
PHJ18920501-V07-05-page28.txt: [('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('La-', 'La'), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', '')]
PHJ18920501-V07-05-page31.txt: [('-', ''), ('-', '')]
PHJ18920501-V07-05-page32.txt: [('-page', 'page'), ('-', ''), ('-', ''), ('ADVERTIS-', 'ADVERTIS'), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', '')]
PHJ18920501-V07-05-page8.txt: [('abstinence.--', 'abstinence.-')]
PHJ18920601-V07-06-page1.txt: [('-PAGE', 'PAGE')]
PHJ18920601-V07-06-page10.txt: [('medi-', 'medi')]
PHJ18920601-V07-06-page11.txt: [('-have', 'have'), ('Anglo-', 'Anglo'), ('-', '')]
PHJ18920601-V07-06-page12.txt: [('-', '')]
PHJ18920601-V07-06-page14.txt: [('wide-', 'wide')]
PHJ18920601-V07-06-page19.txt: [('ham-', 'ham'), ('atten-', 'atten')]
PHJ18920601-V07-06-page2.txt: [('-and', 'and')]
PHJ18920601-V07-06-page21.txt: [('-.aF', '.aF'), ('-', '')]
PHJ18920601-V07-06-page27.txt: [('ST-', 'ST')]
PHJ18920601-V07-06-page28.txt: [('-rice', 'rice')]
PHJ18920601-V07-06-page3.txt: [('mus-', 'mus')]
PHJ18920601-V07-06-page30.txt: [('World-', 'World')]
PHJ18920601-V07-06-page32.txt: [('ADVERTIS-', 'ADVERTIS'), ('-page', 'page'), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', '')]
PHJ18920601-V07-06-page6.txt: [('EXTER-', 'EXTER')]
PHJ18920601-V07-06-page7.txt: [('WAGER-', 'WAGER')]
PHJ18920701-V07-07-page1.txt: [('-PAGE', 'PAGE')]
PHJ18920701-V07-07-page10.txt: [('reme-', 'reme')]
PHJ18920701-V07-07-page16.txt: [('.-', '.')]
PHJ18920701-V07-07-page19.txt: [('CHIL-', 'CHIL')]
PHJ18920701-V07-07-page25.txt: [('-', '')]
PHJ18920701-V07-07-page26.txt: [('COR-', 'COR')]
PHJ18920701-V07-07-page27.txt: [('--Philadelphia', '-Philadelphia'), ('Moorish-', 'Moorish'), ('-', ''), ('.-', '.'), ('-', '')]
PHJ18920701-V07-07-page28.txt: [('Hygeio-', 'Hygeio'), ('-', ''), ('-', '')]
PHJ18920701-V07-07-page29.txt: [('---', '--'), ('-', ''), ('--..', '-..')]
PHJ18920701-V07-07-page30.txt: [('-page', 'page')]
PHJ18920701-V07-07-page32.txt: [('-', ''), ('-', ''), ('THRILL-', 'THRILL')]
PHJ18920701-V07-07-page4.txt: [('-frequent', 'frequent')]
PHJ18920701-V07-07-page6.txt: [('--', '-')]
PHJ18920801-V07-08-page1.txt: [('-PAGE', 'PAGE'), ('promis-', 'promis')]
PHJ18920801-V07-08-page10.txt: [('--IC', '-IC'), ('VENTILA-', 'VENTILA')]
PHJ18920801-V07-08-page12.txt: [('-Ak', 'Ak')]
PHJ18920801-V07-08-page15.txt: [('ARITH-', 'ARITH'), ('--Sel.', '-Sel.')]
PHJ18920801-V07-08-page18.txt: [('-"No', '"No')]
PHJ18920801-V07-08-page19.txt: [("-'", "'"), ('-', ''), ('-', ''), ('-"', '"'), ('.-', '.')]
PHJ18920801-V07-08-page2.txt: [('en-', 'en')]
PHJ18920801-V07-08-page20.txt: [('-"', '"')]
PHJ18920801-V07-08-page23.txt: [('-V', 'V')]
PHJ18920801-V07-08-page24.txt: [('be-', 'be')]
PHJ18920801-V07-08-page25.txt: [('foam-', 'foam')]
PHJ18920801-V07-08-page27.txt: [('-', '')]
PHJ18920801-V07-08-page28.txt: [('mis-', 'mis')]
PHJ18920801-V07-08-page29.txt: [('--Mr.', '-Mr.'), ('--We', '-We'), ('House-', 'House')]
PHJ18920801-V07-08-page30.txt: [('--The', '-The'), ('-', ''), ('pul--', 'pul-')]
PHJ18920801-V07-08-page32.txt: [('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', '')]
PHJ18920801-V07-08-page4.txt: [('fa-', 'fa')]
PHJ18920901-V07-09-page1.txt: [('-PAGE', 'PAGE')]
PHJ18920901-V07-09-page13.txt: [('-', ''), ('-', ''), ('-', '')]
PHJ18920901-V07-09-page14.txt: [('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', '')]
PHJ18920901-V07-09-page15.txt: [('-', '')]
PHJ18920901-V07-09-page21.txt: [('--', '-'), ('-', ''), ('-', '')]
PHJ18920901-V07-09-page23.txt: [('-', ''), ('-', '')]
PHJ18920901-V07-09-page28.txt: [('-', ''), ('-', ''), ('-', ''), ('Cali-', 'Cali')]
PHJ18920901-V07-09-page29.txt: [('r-', 'r'), ('-', ''), ('--Mr.', '-Mr.'), ('--A', '-A'), ('--Our', '-Our')]
PHJ18920901-V07-09-page30.txt: [('Net-', 'Net'), ('---', '--'), ('lipPH"-', 'lipPH"'), ('-', ''), ('-', ''), ('Cal-', 'Cal'), ('-', '')]
PHJ18920901-V07-09-page31.txt: [('-lam', 'lam')]
PHJ18920901-V07-09-page32.txt: [('Hygeio-', 'Hygeio'), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', '')]
PHJ18920901-V07-09-page4.txt: [('at-', 'at')]
PHJ18920901-V07-09-page8.txt: [('-', '')]
PHJ18921001-V07-10-page1.txt: [('-PriGE', 'PriGE')]
PHJ18921001-V07-10-page10.txt: [('-the', 'the')]
PHJ18921001-V07-10-page11.txt: [('-', ''), ('-For', 'For'), ('de-', 'de')]
PHJ18921001-V07-10-page13.txt: [('SURF-', 'SURF')]
PHJ18921001-V07-10-page14.txt: [('--more', '-more')]
PHJ18921001-V07-10-page15.txt: [('grow-', 'grow')]
PHJ18921001-V07-10-page17.txt: [('-', ''), ('-', ''), ('in-', 'in')]
PHJ18921001-V07-10-page19.txt: [('COM-', 'COM')]
PHJ18921001-V07-10-page20.txt: [('pecul-', 'pecul')]
PHJ18921001-V07-10-page21.txt: [('-', ''), ('-', '')]
PHJ18921001-V07-10-page22.txt: [('-', ''), ('-', ''), ('-', ''), ('---', '--'), ('-', '')]
PHJ18921001-V07-10-page23.txt: [('-.', '.'), ('--', '-'), ('t-', 't'), ('pro-', 'pro')]
PHJ18921001-V07-10-page24.txt: [('In-', 'In'), ('com-', 'com'), ('vegeta-', 'vegeta')]
PHJ18921001-V07-10-page27.txt: [('-', ''), ('-', ''), ('-', '')]
PHJ18921001-V07-10-page28.txt: [('Os-', 'Os'), ('-rest', 'rest')]
PHJ18921001-V07-10-page29.txt: [('-page', 'page'), ('-', ''), ('-Nonessentials', 'Nonessentials')]
PHJ18921001-V07-10-page3.txt: [('-that', 'that')]
PHJ18921001-V07-10-page30.txt: [('-', ''), ('-ir', 'ir'), ('-Liol', 'Liol'), ('-', ''), ('E-', 'E'), ('-', '')]
PHJ18921001-V07-10-page32.txt: [("-ars'", "ars'"), ('Hygeio-', 'Hygeio'), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', '')]
PHJ18921001-V07-10-page4.txt: [("-'ACIFIC", "'ACIFIC")]
PHJ18921001-V07-10-page7.txt: [('MED-', 'MED')]
PHJ18921001-V07-10-page9.txt: [('-', ''), ('-in', 'in')]
PHJ18921101-V07-11-page1.txt: [('-PAGE', 'PAGE'), ('or-', 'or')]
PHJ18921101-V07-11-page11.txt: [('Abc--', 'Abc-'), ('-', '')]
PHJ18921101-V07-11-page15.txt: [('bless-', 'bless')]
PHJ18921101-V07-11-page20.txt: [('-OURNAL.', 'OURNAL.')]
PHJ18921101-V07-11-page21.txt: [('-', '')]
PHJ18921101-V07-11-page25.txt: [('descrip-', 'descrip')]
PHJ18921101-V07-11-page28.txt: [('do-', 'do')]
PHJ18921101-V07-11-page29.txt: [('-', ''), ('Non-', 'Non')]
PHJ18921101-V07-11-page3.txt: [('-"The', '"The')]
PHJ18921101-V07-11-page30.txt: [('-', ''), ('-', ''), ('w-', 'w'), ('-t-.arr.OLIVElSTOIC.', 't-.arr.OLIVElSTOIC.')]
PHJ18921101-V07-11-page31.txt: [('I-', 'I'), ('-', '')]
PHJ18921101-V07-11-page32.txt: [('-page', 'page'), ('-', ''), ('.-', '.'), ('-', ''), ('-', '')]
PHJ18921101-V07-11-page6.txt: [('-e-', 'e-'), ('-', ''), ('-', '')]
PHJ18921101-V07-11-page7.txt: [('even--', 'even-')]
PHJ18921201-V07-12-page1.txt: [('-PAGE', 'PAGE'), ('--', '-')]
PHJ18921201-V07-12-page10.txt: [('CEN-', 'CEN')]
PHJ18921201-V07-12-page11.txt: [('ene-', 'ene')]
PHJ18921201-V07-12-page18.txt: [('---', '--')]
PHJ18921201-V07-12-page21.txt: [('-', ''), ('o-', 'o')]
PHJ18921201-V07-12-page22.txt: [('-', '')]
PHJ18921201-V07-12-page26.txt: [('perni-', 'perni')]
PHJ18921201-V07-12-page29.txt: [('.".-', '.".'), ('-', '')]
PHJ18921201-V07-12-page30.txt: [('-C', 'C'), ('-', ''), ('-.', '.'), ('-', ''), ('-', ''), ('-', '')]
PHJ18921201-V07-12-page32.txt: [('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('there-', 'there')]
PHJ18921201-V07-12-page33.txt: [('-', ''), ('-', ''), ('-', ''), ('-', '')]
PHJ18921201-V07-12-page34.txt: [('com-', 'com'), ('doc-', 'doc'), ('-', '')]
PHJ18921201-V07-12-page7.txt: [('-the', 'the')]
PHJ18921201-V07-12-page8.txt: [('-', '')]
PHJ18960101-V11-01-page12.txt: [('disa-', 'disa')]
PHJ18960101-V11-01-page17.txt: [('NERV-', 'NERV')]
PHJ18960101-V11-01-page19.txt: [('JOUR-', 'JOUR')]
PHJ18960101-V11-01-page2.txt: [('-', ''), ('con-', 'con')]
PHJ18960101-V11-01-page22.txt: [('table-', 'table')]
PHJ18960101-V11-01-page26.txt: [('-', '')]
PHJ18960101-V11-01-page27.txt: [('-to', 'to')]
PHJ18960101-V11-01-page29.txt: [('-"-.--.-', '"-.--.-')]
PHJ18960101-V11-01-page32.txt: [('Price--', 'Price-'), ('-', '')]
PHJ18960101-V11-01-page7.txt: [('re-', 're')]
PHJ18960101-V11-01-page8.txt: [('mus-', 'mus')]
PHJ18960101-V11-01-page9.txt: [('-', '')]
PHJ18960201-V11-02-page12.txt: [('promis-', 'promis')]
PHJ18960201-V11-02-page18.txt: [('-', ''), ('-', ''), ('-', '')]
PHJ18960201-V11-02-page19.txt: [('health-', 'health')]
PHJ18960201-V11-02-page22.txt: [('ASSO-', 'ASSO')]
PHJ18960201-V11-02-page26.txt: [('fleet-', 'fleet'), ('sing-', 'sing')]
PHJ18960201-V11-02-page28.txt: [('-', '')]
PHJ18960201-V11-02-page29.txt: [('-', ''), ('-ARETREAT', 'ARETREAT'), ('---', '--'), ('-', '')]
PHJ18960201-V11-02-page31.txt: [('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('I-', 'I'), ('-', ''), ('-', ''), ('-', ''), ('-', '')]
PHJ18960201-V11-02-page32.txt: [('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('--', '-'), ('-', '')]
PHJ18960201-V11-02-page4.txt: [('-', ''), ('atmos-', 'atmos')]
PHJ18960201-V11-02-page5.txt: [('Hebri-', 'Hebri')]
PHJ18960301-V11-03-page13.txt: [('in-', 'in'), ('un-', 'un')]
PHJ18960301-V11-03-page16.txt: [('assistance-', 'assistance')]
PHJ18960301-V11-03-page19.txt: [('con-', 'con'), ('nec-', 'nec')]
PHJ18960301-V11-03-page21.txt: [('step-', 'step')]
PHJ18960301-V11-03-page31.txt: [('CIR-', 'CIR'), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('---', '--'), ('-', ''), ('-', ''), ('-', '')]
PHJ18960301-V11-03-page32.txt: [('-', ''), ('--', '-')]
PHJ18960301-V11-03-page7.txt: [('Re-', 'Re')]
PHJ18960301-V11-03-page8.txt: [('-caliber', 'caliber')]
PHJ18960401-V11-04-page2.txt: [('-', ''), ('de-', 'de')]
PHJ18960401-V11-04-page21.txt: [('-with', 'with')]
PHJ18960401-V11-04-page28.txt: [('demo-', 'demo')]
PHJ18960401-V11-04-page29.txt: [('-', ''), ('-RETREAT', 'RETREAT')]
PHJ18960401-V11-04-page3.txt: [('-attain', 'attain')]
PHJ18960401-V11-04-page30.txt: [('--.....', '-.....')]
PHJ18960401-V11-04-page31.txt: [('-', ''), ('-', ''), ('CIA-', 'CIA'), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', '')]
PHJ18960401-V11-04-page32.txt: [('-', ''), ('-', ''), ('----', '---')]
PHJ18960501-V11-05-page17.txt: [('tend-', 'tend')]
PHJ18960501-V11-05-page19.txt: [('ex-', 'ex')]
PHJ18960501-V11-05-page21.txt: [('deve.-', 'deve.'), ('heaven-', 'heaven'), ('-', '')]
PHJ18960501-V11-05-page23.txt: [('mo-', 'mo')]
PHJ18960501-V11-05-page28.txt: [('-', '')]
PHJ18960501-V11-05-page31.txt: [('CIR-', 'CIR'), ('-', ''), ('-', ''), ('-', ''), ("'-", "'"), ('-', ''), ('-', ''), ('-', ''), ('-', '')]
PHJ18960501-V11-05-page32.txt: [('-', '')]
PHJ18960501-V11-05-page6.txt: [('-cold', 'cold'), ('multi-', 'multi')]
PHJ18960601-V11-06-page19.txt: [('-devote', 'devote')]
PHJ18960601-V11-06-page23.txt: [('some-', 'some')]
PHJ18960601-V11-06-page25.txt: [('VENTILATION.-', 'VENTILATION.')]
PHJ18960601-V11-06-page28.txt: [('Record-', 'Record')]
PHJ18960601-V11-06-page29.txt: [('-', ''), ('-', '')]
PHJ18960601-V11-06-page31.txt: [('CIR-', 'CIR'), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', '')]
PHJ18960601-V11-06-page32.txt: [('use-', 'use'), ('-', ''), ('--', '-'), ('-', ''), ('-', ''), ('.-', '.'), ('-', ''), ('-.-.-', '.-.-'), ('-', ''), ('-', ''), ('-.', '.'), ('-', ''), ('-', ''), ('-tioi', 'tioi'), ('i-', 'i'), ('-', '')]
PHJ18960601-V11-06-page6.txt: [('DISSEM-', 'DISSEM')]
PHJ18960601-V11-06-page8.txt: [('SICK-', 'SICK')]
PHJ18960701-V11-07-page14.txt: [('judg-', 'judg')]
PHJ18960701-V11-07-page16.txt: [('spe-', 'spe')]
PHJ18960701-V11-07-page19.txt: [('po-', 'po'), ('Chris-', 'Chris'), ('pro-', 'pro')]
PHJ18960701-V11-07-page2.txt: [('occu-', 'occu')]
PHJ18960701-V11-07-page23.txt: [('STU-', 'STU')]
PHJ18960701-V11-07-page25.txt: [('-', ''), ('Peameal--', 'Peameal-'), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', '')]
PHJ18960701-V11-07-page27.txt: [('-', '')]
PHJ18960701-V11-07-page29.txt: [('-', '')]
PHJ18960701-V11-07-page3.txt: [('prob-', 'prob'), ('develop-', 'develop')]
PHJ18960701-V11-07-page31.txt: [('CIR-', 'CIR'), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', '')]
PHJ18960701-V11-07-page32.txt: [('-', ''), ('-...-', '...-'), ('..-.........-', '..-.........'), ('-', ''), ('---Z-', '--Z-'), ('-', ''), ('----', '---'), ('--', '-'), ('-', ''), ('--', '-'), ('-', '')]
PHJ18960701-V11-07-page7.txt: [('-', '')]
PHJ18960801-V11-08-page13.txt: [('-longer', 'longer'), ('de-', 'de')]
PHJ18960801-V11-08-page19.txt: [('med-', 'med')]
PHJ18960801-V11-08-page23.txt: [('WOR-', 'WOR')]
PHJ18960801-V11-08-page31.txt: [('CIR-', 'CIR'), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('DRUGGISTSqk-', 'DRUGGISTSqk'), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', '')]
PHJ18960801-V11-08-page8.txt: [('ONES-', 'ONES')]
PHJ18960901-V11-09-page14.txt: [('im-', 'im')]
PHJ18960901-V11-09-page2.txt: [('-colored', 'colored')]
PHJ18960901-V11-09-page20.txt: [('prac-', 'prac')]
PHJ18960901-V11-09-page27.txt: [('-was', 'was')]
PHJ18960901-V11-09-page29.txt: [('-Mrs.', 'Mrs.')]
PHJ18960901-V11-09-page30.txt: [('R-', 'R'), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', '')]
PHJ18961001-V11-10-page1.txt: [('fermenta-', 'fermenta'), ('con-', 'con')]
PHJ18961001-V11-10-page10.txt: [('LOCOMO-', 'LOCOMO')]
PHJ18961001-V11-10-page14.txt: [('lower--', 'lower-'), ('--touch', '-touch')]
PHJ18961001-V11-10-page16.txt: [('ONES-', 'ONES')]
PHJ18961001-V11-10-page18.txt: [('CHIL-', 'CHIL')]
PHJ18961001-V11-10-page27.txt: [('con-', 'con'), ('Omni-', 'Omni')]
PHJ18961001-V11-10-page30.txt: [('--', '-'), ('NOTES-', 'NOTES'), ('ex-', 'ex')]
PHJ18961001-V11-10-page31.txt: [('YEAR.-', 'YEAR.'), ('Senii-', 'Senii')]
PHJ18961001-V11-10-page32.txt: [('-', ''), ('--', '-'), ('-', ''), ("---'", "--'")]
PHJ18961101-V11-11-page10.txt: [('CAPI-', 'CAPI')]
PHJ18961101-V11-11-page11.txt: [('it-', 'it')]
PHJ18961101-V11-11-page13.txt: [('im-', 'im')]
PHJ18961101-V11-11-page16.txt: [('Congrega-', 'Congrega')]
PHJ18961101-V11-11-page24.txt: [('-sufficient', 'sufficient')]
PHJ18961101-V11-11-page25.txt: [('-', ''), ('-', ''), ('-', '')]
PHJ18961101-V11-11-page30.txt: [('NOTES-', 'NOTES')]
PHJ18961101-V11-11-page31.txt: [('--The', '-The'), ('Mis-', 'Mis')]
PHJ18961101-V11-11-page32.txt: [('-', ''), ('-', ''), ('i-i-', 'i-i'), ('i-', 'i'), ('...--', '...-'), ('-', ''), ('-', ''), ('-', ''), ('-..-', '..-'), ('-', ''), ('-', ''), ('Ittgiiiiiic-', 'Ittgiiiiiic'), ('-', ''), ('-', ''), ('-', '')]
PHJ18961101-V11-11-page7.txt: [('con-', 'con')]
PHJ18961201-V11-12-page16.txt: [('sympa-', 'sympa')]
PHJ18961201-V11-12-page19.txt: [('corn-', 'corn')]
PHJ18961201-V11-12-page22.txt: [('--', '-')]
PHJ18961201-V11-12-page25.txt: [('---', '--')]
PHJ18961201-V11-12-page33.txt: [('rheuma-', 'rheuma')]
PHJ18961201-V11-12-page5.txt: [('degrad-', 'degrad')]
PHJ18961201-V11-12-page8.txt: [('RAIL-', 'RAIL')]
PHJ18990101-V14-01-page1.txt: [('JouR-', 'JouR')]
PHJ18990201-V14-02-page1.txt: [('ac-', 'ac')]
PHJ18990201-V14-02-page10.txt: [('SPIRIT-', 'SPIRIT')]
PHJ18990201-V14-02-page12.txt: [('prop-', 'prop')]
PHJ18990201-V14-02-page4.txt: [('condi-', 'condi')]
PHJ18990201-V14-02-page6.txt: [('-lot.', 'lot.')]
PHJ18990301-V14-03-page1.txt: [('im-', 'im')]
PHJ18990301-V14-03-page11.txt: [('-', '')]
PHJ18990301-V14-03-page19.txt: [('ASSOCIA-', 'ASSOCIA'), ('PA-', 'PA'), ('JoUR-', 'JoUR')]
PHJ18990301-V14-03-page4.txt: [('con-', 'con')]
PHJ18990301-V14-03-page7.txt: [('con-', 'con')]
PHJ18990301-V14-03-page8.txt: [('PHYSI-', 'PHYSI')]
PHJ18990401-V14-04-page1.txt: [('-', '')]
PHJ18990401-V14-04-page11.txt: [('-', ''), ('IN-', 'IN')]
PHJ18990401-V14-04-page12.txt: [('-has', 'has')]
PHJ18990401-V14-04-page13.txt: [('appre-', 'appre')]
PHJ18990401-V14-04-page14.txt: [('-', '')]
PHJ18990401-V14-04-page15.txt: [('consider-', 'consider'), ('fur-', 'fur')]
PHJ18990401-V14-04-page7.txt: [('re-', 're')]
PHJ18990501-V14-05-page12.txt: [('burst-', 'burst')]
PHJ18990501-V14-05-page16.txt: [('gone."--', 'gone."-')]
PHJ18990501-V14-05-page3.txt: [('unload-', 'unload')]
PHJ18990601-V14-06-page11.txt: [('ac-', 'ac')]
PHJ18990601-V14-06-page13.txt: [('-', '')]
PHJ18990601-V14-06-page15.txt: [('noth-', 'noth'), ('recep-', 'recep'), ('opportu-', 'opportu')]
PHJ18990601-V14-06-page19.txt: [('Indian-', 'Indian')]
PHJ18990601-V14-06-page20.txt: [('-', '')]
PHJ18990601-V14-06-page24.txt: [('God-', 'God')]
PHJ18990701-V14-07-page10.txt: [('con-', 'con'), ('-could', 'could')]
PHJ18990701-V14-07-page14.txt: [('an-', 'an')]
PHJ18990701-V14-07-page15.txt: [('HOT-', 'HOT')]
PHJ18990701-V14-07-page19.txt: [('DRESS-', 'DRESS')]
PHJ18990701-V14-07-page3.txt: [('con-', 'con')]
PHJ18990801-V14-08-page10.txt: [('-order', 'order')]
PHJ18990801-V14-08-page12.txt: [('Atwater.-', 'Atwater.')]
PHJ18990801-V14-08-page15.txt: [('impor-', 'impor')]
PHJ18990801-V14-08-page2.txt: [('hence-', 'hence')]
PHJ18990801-V14-08-page4.txt: [('func-', 'func')]
PHJ18990801-V14-08-page9.txt: [('-', '')]
PHJ18990901-V14-09-page10.txt: [('de-', 'de')]
PHJ18990901-V14-09-page18.txt: [('-something', 'something')]
PHJ18990901-V14-09-page2.txt: [('dis-', 'dis')]
PHJ18990901-V14-09-page24.txt: [('-that', 'that')]
PHJ18990901-V14-09-page30.txt: [('-"', '"')]
PHJ18990901-V14-09-page5.txt: [('thou-', 'thou')]
PHJ18991001-V14-10-page13.txt: [('-of', 'of')]
PHJ18991001-V14-10-page15.txt: [('--Ella', '-Ella')]
PHJ18991001-V14-10-page17.txt: [('--', '-')]
PHJ18991001-V14-10-page3.txt: [('G-', 'G'), ('parent-', 'parent')]
PHJ18991001-V14-10-page9.txt: [('-', '')]
PHJ18991101-V14-11-page15.txt: [('GASTRO-INTESTI-', 'GASTRO-INTESTI')]
PHJ18991101-V14-11-page3.txt: [('corn-', 'corn')]
PHJ18991101-V14-11-page7.txt: [('pre-', 'pre')]
PHJ18991101-V14-11-page9.txt: [('DISINFECT-', 'DISINFECT')]
PHJ18991201-V14-12-page12.txt: [('Hundred-', 'Hundred')]
PHJ18991201-V14-12-page15.txt: [('ad-', 'ad')]
PHJ18991201-V14-12-page18.txt: [('-', '')]
PHJ18991201-V14-12-page5.txt: [('--We', '-We')]
PHJ18991201-V14-12-page7.txt: [('en-', 'en')]
PHJ19010201-V16-02-page12.txt: [('HEALTI-', 'HEALTI'), ('CHRIS-', 'CHRIS')]
PHJ19010201-V16-02-page17.txt: [('tissue-', 'tissue')]
PHJ19010201-V16-02-page20.txt: [('I-IEALTI-', 'I-IEALTI')]
PHJ19010201-V16-02-page21.txt: [('SANI-', 'SANI')]
PHJ19010201-V16-02-page22.txt: [('-Health', 'Health')]
PHJ19010201-V16-02-page23.txt: [('Hebrew-', 'Hebrew')]
PHJ19010201-V16-02-page25.txt: [('under-', 'under')]
PHJ19010201-V16-02-page27.txt: [('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', '')]
PHJ19010201-V16-02-page28.txt: [('-', ''), ('-', ''), ('-', ''), ('-', '')]
PHJ19010201-V16-02-page29.txt: [('-ow', 'ow')]
PHJ19010201-V16-02-page3.txt: [('k---', 'k--'), ('.-', '.'), ('-', ''), ('Ff.-', 'Ff.'), ('rt.C.P-', 'rt.C.P'), ('-', ''), ('-.', '.'), ('-', ''), ('-', ''), ('-', ''), ('-i', 'i'), ('-', ''), ("-'", "'"), ('.-', '.'), ('--', '-'), ('-', ''), ("-'", "'"), ('-', ''), ('-"', '"'), ('-', ''), ('-lir', 'lir')]
PHJ19010201-V16-02-page30.txt: [('..----', '..---')]
PHJ19010201-V16-02-page32.txt: [('-str', 'str'), ('-Mir', 'Mir'), ('-stir', 'stir'), ('-stir', 'stir'), ('-stir', 'stir'), ('-stir', 'stir'), ('-stir', 'stir')]
PHJ19010201-V16-02-page33.txt: [('t-', 't'), ('t-', 't'), ('t-', 't'), ('tt-', 'tt'), ('t-', 't'), ('-', ''), ('t-', 't'), ('t-', 't'), ('-', ''), ('-', ''), ('-r', 'r'), ('-', ''), ('-', '')]
PHJ19010201-V16-02-page34.txt: [('-', ''), ('-', '')]
PHJ19010201-V16-02-page4.txt: [('SNAP-', 'SNAP')]
PHJ19010201-V16-02-page5.txt: [('night-', 'night')]
PHJ19010201-V16-02-page6.txt: [('pre-', 'pre')]
PHJ19010201-V16-02-page8.txt: [('-SUPERSTITIONS', 'SUPERSTITIONS')]
PHJ19010201-V16-02-page9.txt: [('pre-', 'pre')]
PHJ19010301-V16-03-page12.txt: [('exten-', 'exten'), ('-character."', 'character."')]
PHJ19010301-V16-03-page19.txt: [('-', '')]
PHJ19010301-V16-03-page2.txt: [('-', '')]
PHJ19010301-V16-03-page20.txt: [('dan-', 'dan')]
PHJ19010301-V16-03-page21.txt: [('-SEVEN', 'SEVEN')]
PHJ19010301-V16-03-page25.txt: [('-toprove', 'toprove')]
PHJ19010301-V16-03-page26.txt: [('ft-', 'ft'), ('-', ''), ('-', ''), ('-et', 'et'), ('-s-', 's-'), ("-V..'", "V..'"), ('-', ''), ('-i-.', 'i-.'), ('-e', 'e'), ('-', ''), ('-', ''), ('-s-ir', 's-ir'), ('-i.', 'i.'), ('-s--.e', 's--.e'), ('-V', 'V'), ("'--s-", "'--s")]
PHJ19010301-V16-03-page27.txt: [('-', ''), ('A-', 'A')]
PHJ19010301-V16-03-page28.txt: [('-', ''), ('-', ''), ('-', '')]
PHJ19010301-V16-03-page29.txt: [('-', ''), ('-', ''), ('-', ''), ('-', '')]
PHJ19010301-V16-03-page3.txt: [('-', ''), ('-', ''), ('-', ''), ('-', '')]
PHJ19010301-V16-03-page30.txt: [('it-', 'it')]
PHJ19010301-V16-03-page32.txt: [('-s', 's'), ('-Pi-', 'Pi-'), ('-', '')]
PHJ19010301-V16-03-page33.txt: [('-', ''), ('-', ''), ('-', '')]
PHJ19010301-V16-03-page34.txt: [('PARLOR-', 'PARLOR')]
PHJ19010301-V16-03-page35.txt: [('-', '')]
PHJ19010301-V16-03-page5.txt: [('-VOL.', 'VOL.'), ('medi-', 'medi')]
PHJ19010301-V16-03-page7.txt: [('ter-', 'ter')]
PHJ19010301-V16-03-page8.txt: [('-of', 'of')]
PHJ19010401-V16-04-page1.txt: [('-', ''), ('-t', 't')]
PHJ19010401-V16-04-page14.txt: [('accumula-', 'accumula')]
PHJ19010401-V16-04-page15.txt: [('per-', 'per')]
PHJ19010401-V16-04-page2.txt: [('-', ''), ('-', '')]
PHJ19010401-V16-04-page24.txt: [('thick-', 'thick')]
PHJ19010401-V16-04-page26.txt: [('-', ''), ('--d', '-d')]
PHJ19010401-V16-04-page28.txt: [('days.-', 'days.'), ('-', ''), ('-', ''), ('--', '-'), ("-'", "'"), ('-', ''), ('----', '---'), ('-', ''), ('----', '---'), ('--', '-')]
PHJ19010401-V16-04-page29.txt: [('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', '')]
PHJ19010401-V16-04-page3.txt: [('-', '')]
PHJ19010401-V16-04-page30.txt: [('-', ''), ('-', '')]
PHJ19010401-V16-04-page31.txt: [('Correspond-', 'Correspond'), ('-MAIN', 'MAIN')]
PHJ19010401-V16-04-page32.txt: [('-Mr', 'Mr'), ('Code-', 'Code')]
PHJ19010401-V16-04-page33.txt: [('--', '-')]
PHJ19010401-V16-04-page34.txt: [('Electric-', 'Electric')]
PHJ19010401-V16-04-page9.txt: [('base-', 'base')]
PHJ19010501-V16-05-page14.txt: [('how-', 'how')]
PHJ19010501-V16-05-page17.txt: [('climato-', 'climato'), ('hydro-', 'hydro')]
PHJ19010501-V16-05-page19.txt: [('transmi-', 'transmi')]
PHJ19010501-V16-05-page2.txt: [('-', ''), ('-The', 'The')]
PHJ19010501-V16-05-page21.txt: [('-', ''), ('EALTI-', 'EALTI')]
PHJ19010501-V16-05-page24.txt: [('SCI-', 'SCI')]
PHJ19010501-V16-05-page27.txt: [('--', '-')]
PHJ19010501-V16-05-page29.txt: [('triu.K-', 'triu.K'), ('-trio.', 'trio.')]
PHJ19010501-V16-05-page30.txt: [('-', ''), ('----.', '---.'), ('M-', 'M')]
PHJ19010501-V16-05-page31.txt: [('-g', 'g'), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', '')]
PHJ19010501-V16-05-page32.txt: [('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-r-', 'r-'), ('-', ''), ('i-', 'i'), ('-', ''), ('r-', 'r'), ('-', '')]
PHJ19010501-V16-05-page34.txt: [('-', '')]
PHJ19010501-V16-05-page35.txt: [('---', '--'), ("'-", "'"), ('.-', '.'), ('-', ''), ('.--', '.-'), ('-', ''), ('-', ''), ('-.', '.'), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-Ye', 'Ye'), ('-', ''), ('-tt-', 'tt-'), ('i-', 'i'), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-t-', 't-'), ('-', '')]
PHJ19010501-V16-05-page36.txt: [('-', ''), ('-', ''), ('-s', 's')]
PHJ19010501-V16-05-page37.txt: [('-', '')]
PHJ19010501-V16-05-page5.txt: [('THO-FORMO-', 'THO-FORMO')]
PHJ19010601-V16-06-page1.txt: [('-w', 'w')]
PHJ19010601-V16-06-page13.txt: [('-', ''), ('battle-', 'battle')]
PHJ19010601-V16-06-page17.txt: [('Well-', 'Well'), ('-cooked', 'cooked'), ('-eliminated', 'eliminated'), ('-increased', 'increased')]
PHJ19010601-V16-06-page18.txt: [('con--', 'con-')]
PHJ19010601-V16-06-page2.txt: [('-', ''), ('Pala-', 'Pala')]
PHJ19010601-V16-06-page3.txt: [('-', ''), ('-', ''), ('-', '')]
PHJ19010601-V16-06-page32.txt: [('-AK', 'AK')]
PHJ19010601-V16-06-page33.txt: [('Pow-', 'Pow'), ('rose-', 'rose')]
PHJ19010601-V16-06-page34.txt: [('thor-', 'thor')]
PHJ19010601-V16-06-page36.txt: [('as-', 'as')]
PHJ19010601-V16-06-page38.txt: [('dis-', 'dis')]
PHJ19010601-V16-06-page40.txt: [('-', '')]
PHJ19010601-V16-06-page44.txt: [('-ipes', 'ipes')]
PHJ19010601-V16-06-page46.txt: [('..-', '..'), ('E--', 'E-'), ('--', '-'), ('L-', 'L'), ('-.r', '.r'), ('-', ''), ('-', ''), ('-', ''), ('-page', 'page'), ('TEN-', 'TEN')]
PHJ19010601-V16-06-page47.txt: [('-', ''), ('-"fir', '"fir'), ('-', '')]
PHJ19010601-V16-06-page48.txt: [('Correspond-', 'Correspond')]
PHJ19010601-V16-06-page49.txt: [('-------', '------'), ('-', ''), ('-s"', 's"'), ('THO-FORMO-', 'THO-FORMO')]
PHJ19010601-V16-06-page50.txt: [('Tr-Q.-', 'Tr-Q.'), ('--', '-'), ('-zi', 'zi'), ('-', ''), ('--', '-'), ('-', '')]
PHJ19010601-V16-06-page51.txt: [('-', ''), ('-', '')]
PHJ19010601-V16-06-page53.txt: [("-'", "'")]
PHJ19010601-V16-06-page7.txt: [('--they', '-they')]
PHJ19010701-V16-07-page1.txt: [('-', ''), ('-', '')]
PHJ19010701-V16-07-page11.txt: [('I-', 'I')]
PHJ19010701-V16-07-page12.txt: [('---', '--')]
PHJ19010701-V16-07-page13.txt: [('-', '')]
PHJ19010701-V16-07-page15.txt: [('-', ''), ('-', ''), ('-', '')]
PHJ19010701-V16-07-page17.txt: [('-the', 'the')]
PHJ19010701-V16-07-page2.txt: [('-', ''), ('-Two', 'Two')]
PHJ19010701-V16-07-page24.txt: [('SCI-', 'SCI')]
PHJ19010701-V16-07-page25.txt: [('Do-', 'Do'), ('Men-', 'Men')]
PHJ19010701-V16-07-page26.txt: [('-', ''), ('-', ''), ('-', ''), ('-', '')]
PHJ19010701-V16-07-page27.txt: [('-', ''), ('-', ''), ('-', ''), ('-', ''), ('E-', 'E'), ("'-", "'"), ('-', ''), ("-Man's", "Man's"), ('-Preparation', 'Preparation'), ('-', ''), ('--', '-'), ('-', ''), ('-', ''), ('-page', 'page'), ('TEM-', 'TEM')]
PHJ19010701-V16-07-page28.txt: [('-', ''), ('-', ''), ('-', '')]
PHJ19010701-V16-07-page29.txt: [('"--', '"-'), ('t.-', 't.'), ('-"-""-', '"-""-'), ('-', ''), ('-', ''), ('-', ''), ('--', '-'), ('-', ''), ('THO-FORMO-', 'THO-FORMO')]
PHJ19010701-V16-07-page3.txt: [('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-.s-ie', '.s-ie'), ('.-', '.'), ('-frir', 'frir')]
PHJ19010701-V16-07-page30.txt: [('------', '-----'), ('-', ''), ('-', ''), ('-', ''), ('--.', '-.'), ('-', '')]
PHJ19010701-V16-07-page31.txt: [('-', ''), ('EL-', 'EL'), ('-', '')]
PHJ19010701-V16-07-page32.txt: [('-', ''), ('-', '')]
PHJ19010701-V16-07-page33.txt: [('-ryvvyyl-', 'ryvvyyl-'), ('-', ''), ('-', '')]
PHJ19010701-V16-07-page34.txt: [('-', '')]
PHJ19010701-V16-07-page35.txt: [('-STREET', 'STREET')]
PHJ19010801-V16-08-page1.txt: [('-', '')]
PHJ19010801-V16-08-page14.txt: [('-Tir', 'Tir'), ('-beautiful', 'beautiful')]
PHJ19010801-V16-08-page2.txt: [('-', ''), ('-', '')]
PHJ19010801-V16-08-page27.txt: [("-IERS'", "IERS'"), ('-with', 'with')]
PHJ19010801-V16-08-page28.txt: [('BRUSI-', 'BRUSI')]
PHJ19010801-V16-08-page29.txt: [('-', ''), ('irrr-', 'irrr'), ('--', '-'), ('--', '-'), ('-', ''), ("-'", "'"), ('-', ''), ('MENTHO-FORMO-', 'MENTHO-FORMO')]
PHJ19010801-V16-08-page3.txt: [('-', ''), ('-', ''), ('-', ''), ('-s-', 's-')]
PHJ19010801-V16-08-page30.txt: [('-', '')]
PHJ19010801-V16-08-page31.txt: [('-', ''), ('-', '')]
PHJ19010801-V16-08-page32.txt: [('-', ''), ('-', '')]
PHJ19010801-V16-08-page33.txt: [('--iri', '-iri'), ('i-', 'i')]
PHJ19010801-V16-08-page4.txt: [('-', ''), ('-', ''), ('--', '-'), ('-', ''), ('--v--', '-v--'), ('-page', 'page'), ('TEM-', 'TEM')]
PHJ19010801-V16-08-page7.txt: [('tend-', 'tend'), ('pro-', 'pro'), ('per-', 'per')]
PHJ19010901-V16-09-page17.txt: [('EALTI-', 'EALTI')]
PHJ19010901-V16-09-page2.txt: [('-', '')]
PHJ19010901-V16-09-page20.txt: [('-', ''), ('EALTI-', 'EALTI')]
PHJ19010901-V16-09-page29.txt: [('-stir', 'stir')]
PHJ19010901-V16-09-page3.txt: [('t"..-', 't"..'), ('-', ''), ('t-', 't'), ('--A', '-A'), ('--', '-'), ('.-', '.'), ('-', ''), ('-', ''), ('..-', '..'), ('-', ''), ('-', ''), ('-i-', 'i-'), ('---', '--'), ('-s-', 's-'), ('.-', '.'), ('-s-.', 's-.'), ('-.-.', '.-.')]
PHJ19010901-V16-09-page30.txt: [('-----', '----'), ('-...', '...'), ('-', ''), ('-', ''), ('-vAi', 'vAi'), ('...-', '...'), ('-', ''), ('ilEALTI-', 'ilEALTI'), ('-', ''), ('-eeeeee-eeeest', 'eeeeee-eeeest')]
PHJ19010901-V16-09-page32.txt: [('-', ''), ('-', '')]
PHJ19010901-V16-09-page33.txt: [('-', ''), ('-', ''), ('-', '')]
PHJ19010901-V16-09-page34.txt: [('-', ''), ('-', ''), ('-', '')]
PHJ19010901-V16-09-page6.txt: [('con-', 'con')]
PHJ19010901-V16-09-page8.txt: [('persever-', 'persever')]
PHJ19011001-V16-10-page1.txt: [('-', ''), ('-', '')]
PHJ19011001-V16-10-page11.txt: [('Fielding-', 'Fielding')]
PHJ19011001-V16-10-page2.txt: [('-', '')]
PHJ19011001-V16-10-page21.txt: [('IlEALTI-', 'IlEALTI')]
PHJ19011001-V16-10-page23.txt: [('I-IEALTI-', 'I-IEALTI')]
PHJ19011001-V16-10-page25.txt: [('-', ''), ('EALTI-', 'EALTI')]
PHJ19011001-V16-10-page26.txt: [('HEALTI-', 'HEALTI')]
PHJ19011001-V16-10-page28.txt: [('-', '')]
PHJ19011001-V16-10-page3.txt: [('-', ''), ('--', '-'), ('-', ''), ('tss-', 'tss'), ('-i-', 'i-'), ('--', '-'), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-.', '.'), ('-P.', 'P.'), ('-', ''), ('-', ''), ('-s-', 's-')]
PHJ19011001-V16-10-page30.txt: [('--', '-'), ('-', ''), ('--------', '-------'), ('-', ''), ('--', '-'), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', '')]
PHJ19011001-V16-10-page31.txt: [('-', ''), ('-', '')]
PHJ19011001-V16-10-page32.txt: [('HEALTI-', 'HEALTI'), ('-', ''), ('-', '')]
PHJ19011001-V16-10-page34.txt: [('-', ''), ('-', '')]
PHJ19011001-V16-10-page35.txt: [('-', ''), ('-frfr', 'frfr')]
PHJ19011101-V16-11-page14.txt: [('HEALTI-', 'HEALTI')]
PHJ19011101-V16-11-page29.txt: [('-', '')]
PHJ19011101-V16-11-page3.txt: [('HEL-', 'HEL'), ('SAD-', 'SAD')]
PHJ19011101-V16-11-page30.txt: [('-', ''), ('----', '---'), ('-', ''), ('---', '--'), ('--', '-'), ('---', '--'), ('-', ''), ('-', ''), ('-', '')]
PHJ19011101-V16-11-page33.txt: [('-', ''), ('-frfr', 'frfr'), ('-', '')]
PHJ19011101-V16-11-page34.txt: [('-', ''), ('-', '')]
PHJ19011101-V16-11-page35.txt: [('-lir', 'lir'), ('-', ''), ('-', ''), ('-', ''), ('.i-', '.i')]
PHJ19011101-V16-11-page36.txt: [('-', ''), ('-', '')]
PHJ19011101-V16-11-page37.txt: [('-if', 'if')]
PHJ19011101-V16-11-page7.txt: [('TUBERCU-', 'TUBERCU')]
PHJ19011201-V16-12-page1.txt: [('MON-', 'MON')]
PHJ19011201-V16-12-page17.txt: [('ef-', 'ef')]
PHJ19011201-V16-12-page2.txt: [('-', ''), ('-.', '.'), ('-', ''), ('.-', '.'), ('----', '---'), ('-..-', '..-'), ('t-', 't'), ('-', ''), ('Li--', 'Li-'), ('-', ''), ('-', ''), ("-'", "'"), ('"--', '"-'), ('---.', '--.'), ('-...', '...')]
PHJ19011201-V16-12-page25.txt: [('irregu-', 'irregu'), ('weak-', 'weak')]
PHJ19011201-V16-12-page3.txt: [('-', '')]
PHJ19011201-V16-12-page31.txt: [('-only', 'only')]
PHJ19011201-V16-12-page33.txt: [('-large', 'large')]
PHJ19011201-V16-12-page34.txt: [('ap-', 'ap')]
PHJ19011201-V16-12-page39.txt: [('-', ''), ('---', '--'), ('---', '--'), ('P-', 'P'), ('..-', '..'), ('---', '--')]
PHJ19011201-V16-12-page4.txt: [('-', ''), ('-W', 'W'), ('.-', '.'), ('-', ''), ('--.', '-.'), ("-r.'.'.", "r.'.'."), ('--', '-'), ('---', '--'), ('-', ''), ('--', '-'), ('---', '--'), ('-', ''), ('-', ''), ('-"N', '"N'), ('.....-', '.....')]
PHJ19011201-V16-12-page40.txt: [('-', '')]
PHJ19011201-V16-12-page44.txt: [('vtouOwttitiOK-', 'vtouOwttitiOK')]
PHJ19011201-V16-12-page45.txt: [('-', ''), ('-', ''), ('-STREET', 'STREET')]
PHJ19020101-V17-01-page13.txt: [('-oluer.', 'oluer.')]
PHJ19020101-V17-01-page16.txt: [('--tartaric', '-tartaric')]
PHJ19020101-V17-01-page17.txt: [('essen-', 'essen')]
PHJ19020101-V17-01-page19.txt: [('concludes--', 'concludes-')]
PHJ19020101-V17-01-page28.txt: [('ELECTRIC-', 'ELECTRIC'), ('applica-', 'applica')]
PHJ19020101-V17-01-page29.txt: [('ELECTRIC-', 'ELECTRIC')]
PHJ19020101-V17-01-page3.txt: [('-', ''), ('-', '')]
PHJ19020101-V17-01-page36.txt: [('t-', 't'), ('t-', 't'), ('i-', 'i'), ('-', ''), ('t-', 't'), ('-', ''), ('t-', 't'), ('t-', 't'), ('i-', 'i'), ('t-', 't'), ('.-', '.'), ('-', ''), ('t-', 't'), ('t-', 't'), ('-', ''), ('t-', 't')]
PHJ19020101-V17-01-page37.txt: [('-', ''), ('-tou.witriu', 'tou.witriu'), ('if-', 'if'), ('-tou', 'tou')]
PHJ19020201-V17-02-page16.txt: [('destruc-', 'destruc')]
PHJ19020201-V17-02-page2.txt: [('-', '')]
PHJ19020201-V17-02-page20.txt: [('mar-', 'mar')]
PHJ19020201-V17-02-page30.txt: [('-----lee.', '----lee.'), ('-', ''), ('-ffr', 'ffr'), ('Vice-', 'Vice')]
PHJ19020201-V17-02-page31.txt: [('-i', 'i'), ('dif-', 'dif'), ('---', '--')]
PHJ19020201-V17-02-page32.txt: [('--', '-'), ('-', ''), ('-', ''), ('-', ''), ('-.', '.'), ('-t', 't')]
PHJ19020201-V17-02-page34.txt: [('BABY-', 'BABY')]
PHJ19020201-V17-02-page35.txt: [('-', '')]
PHJ19020201-V17-02-page9.txt: [('aggra-', 'aggra')]
PHJ19020301-V17-03-page2.txt: [('can-', 'can'), ('Z-', 'Z'), ('SIXTY-', 'SIXTY')]
PHJ19020301-V17-03-page21.txt: [('indus-', 'indus')]
PHJ19020301-V17-03-page22.txt: [('eter-', 'eter')]
PHJ19020301-V17-03-page27.txt: [('preven-', 'preven')]
PHJ19020301-V17-03-page3.txt: [('NUTTY-', 'NUTTY')]
PHJ19020301-V17-03-page33.txt: [('-', '')]
PHJ19020301-V17-03-page34.txt: [('-v', 'v')]
PHJ19020301-V17-03-page37.txt: [('-', '')]
PHJ19020301-V17-03-page5.txt: [('-', '')]
PHJ19020401-V17-04-page13.txt: [('constipa-', 'constipa')]
PHJ19020401-V17-04-page22.txt: [("advantages.'.-", "advantages.'."), ('pres-', 'pres')]
PHJ19020401-V17-04-page29.txt: [('book-', 'book')]
PHJ19020401-V17-04-page3.txt: [('NUTTY-', 'NUTTY')]
PHJ19020401-V17-04-page31.txt: [('.--------', '.-------'), ('--.--', '-.--'), ('---.--', '--.--'), ('..--', '..-')]
PHJ19020401-V17-04-page32.txt: [('-------', '------'), ('-', ''), ('-', ''), ("'-'-'-", "'-'-'"), ('A.-', 'A.'), ('-', '')]
PHJ19020401-V17-04-page5.txt: [('-', '')]
PHJ19020501-V17-05-page14.txt: [('re-', 're')]
PHJ19020501-V17-05-page15.txt: [('how-', 'how')]
PHJ19020501-V17-05-page18.txt: [('sub-', 'sub'), ('un-', 'un'), ('solu-', 'solu'), ('useful-', 'useful')]
PHJ19020501-V17-05-page21.txt: [('-a', 'a')]
PHJ19020501-V17-05-page23.txt: [('-', '')]
PHJ19020501-V17-05-page27.txt: [('supply-', 'supply')]
PHJ19020501-V17-05-page28.txt: [('PA-', 'PA')]
PHJ19020501-V17-05-page3.txt: [('NUTTY-', 'NUTTY')]
PHJ19020501-V17-05-page9.txt: [('-', '')]
PHJ19020601-V17-06-page10.txt: [('--since', '-since')]
PHJ19020601-V17-06-page12.txt: [('-', '')]
PHJ19020601-V17-06-page13.txt: [('SAN-', 'SAN')]
PHJ19020601-V17-06-page14.txt: [('"--', '"-')]
PHJ19020601-V17-06-page16.txt: [('unevan-', 'unevan')]
PHJ19020601-V17-06-page2.txt: [('SUBSCRIP-', 'SUBSCRIP')]
PHJ19020601-V17-06-page24.txt: [('irri-', 'irri')]
PHJ19020601-V17-06-page26.txt: [('posi-', 'posi')]
PHJ19020601-V17-06-page3.txt: [('NUTTY-', 'NUTTY')]
PHJ19020601-V17-06-page32.txt: [('Govern-', 'Govern')]
PHJ19020601-V17-06-page7.txt: [('-eaten', 'eaten')]
PHJ19020701-V17-07-page10.txt: [('con-', 'con')]
PHJ19020701-V17-07-page11.txt: [('--', '-')]
PHJ19020701-V17-07-page12.txt: [('pro-', 'pro'), ('fif-', 'fif')]
PHJ19020701-V17-07-page14.txt: [('com-', 'com')]
PHJ19020701-V17-07-page2.txt: [('SUBSCRIP-', 'SUBSCRIP')]
PHJ19020701-V17-07-page23.txt: [('min-', 'min')]
PHJ19020701-V17-07-page24.txt: [('re-', 're')]
PHJ19020701-V17-07-page25.txt: [('-cream', 'cream')]
PHJ19020701-V17-07-page3.txt: [('NUTTY-', 'NUTTY')]
PHJ19020701-V17-07-page30.txt: [('-', ''), ('-', '')]
PHJ19020701-V17-07-page35.txt: [('r-', 'r')]
PHJ19020701-V17-07-page5.txt: [('temper-', 'temper')]
PHJ19020801-V17-08-page13.txt: [('-', ''), ('-', '')]
PHJ19020801-V17-08-page15.txt: [('al-', 'al')]
PHJ19020801-V17-08-page2.txt: [('-', '')]
PHJ19020801-V17-08-page25.txt: [('-', '')]
PHJ19020801-V17-08-page28.txt: [('JOUR-', 'JOUR')]
PHJ19020801-V17-08-page29.txt: [('Train-', 'Train')]
PHJ19020801-V17-08-page3.txt: [('NUTTY-', 'NUTTY')]
PHJ19020801-V17-08-page30.txt: [('---', '--'), ('-', ''), ('--......', '-......'), ('-.', '.'), ('-', ''), ('----', '---'), ('-', ''), ('---', '--')]
PHJ19020801-V17-08-page31.txt: [('-', '')]
PHJ19020801-V17-08-page5.txt: [('com-', 'com')]
PHJ19020801-V17-08-page7.txt: [('re-', 're')]
PHJ19020801-V17-08-page8.txt: [('re-', 're')]
PHJ19020901-V17-09-page1.txt: [('-', ''), ("'-", "'"), ('-', '')]
PHJ19020901-V17-09-page10.txt: [('dif-', 'dif')]
PHJ19020901-V17-09-page11.txt: [('--In', '-In'), ('--Certainly', '-Certainly'), ('deterio-', 'deterio')]
PHJ19020901-V17-09-page13.txt: [('cya-', 'cya')]
PHJ19020901-V17-09-page15.txt: [('yes-', 'yes')]
PHJ19020901-V17-09-page18.txt: [('consumption.--', 'consumption.-')]
PHJ19020901-V17-09-page2.txt: [('-.onto', '.onto')]
PHJ19020901-V17-09-page22.txt: [('--Dietetic', '-Dietetic')]
PHJ19020901-V17-09-page3.txt: [('NUTTY-', 'NUTTY')]
PHJ19020901-V17-09-page34.txt: [('--', '-'), ('-', '')]
PHJ19020901-V17-09-page4.txt: [('-', ''), ('-', '')]
PHJ19020901-V17-09-page7.txt: [('-and', 'and'), ('QUANTI-', 'QUANTI')]
PHJ19021001-V17-10-page11.txt: [('pro-', 'pro')]
PHJ19021001-V17-10-page15.txt: [('---the', '--the'), ('heal-', 'heal')]
PHJ19021001-V17-10-page18.txt: [('in--', 'in-')]
PHJ19021001-V17-10-page2.txt: [('-', '')]
PHJ19021001-V17-10-page21.txt: [('-herself', 'herself')]
PHJ19021001-V17-10-page22.txt: [('to-', 'to')]
PHJ19021001-V17-10-page28.txt: [('-will', 'will'), ('-page', 'page')]
PHJ19021001-V17-10-page3.txt: [('NUTTY-', 'NUTTY')]
PHJ19021001-V17-10-page34.txt: [('-', '')]
PHJ19021101-V17-11-page1.txt: [('-S', 'S')]
PHJ19021101-V17-11-page10.txt: [('influ-', 'influ'), ('-', ''), ('phys-', 'phys')]
PHJ19021101-V17-11-page11.txt: [('-', '')]
PHJ19021101-V17-11-page12.txt: [('irritability--', 'irritability-'), ('-', '')]
PHJ19021101-V17-11-page13.txt: [('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', '')]
PHJ19021101-V17-11-page19.txt: [('-physical', 'physical')]
PHJ19021101-V17-11-page2.txt: [('-', '')]
PHJ19021101-V17-11-page22.txt: [('-', ''), ("and'Bata-", "and'Bata")]
PHJ19021101-V17-11-page25.txt: [('con-', 'con')]
PHJ19021101-V17-11-page29.txt: [('Train-', 'Train')]
PHJ19021101-V17-11-page3.txt: [('NUTTY-', 'NUTTY')]
PHJ19021101-V17-11-page34.txt: [('NI-', 'NI'), ('-', ''), ('-', '')]
PHJ19021101-V17-11-page36.txt: [('like-', 'like')]
PHJ19021101-V17-11-page6.txt: [('dis-', 'dis'), ('vig-', 'vig')]
PHJ19021101-V17-11-page7.txt: [('hay-', 'hay'), ('unhy-', 'unhy')]
PHJ19021201-V17-12-page20.txt: [('perish-', 'perish')]
PHJ19021201-V17-12-page3.txt: [('NUTTY-', 'NUTTY')]
PHJ19021201-V17-12-page31.txt: [('-cent', 'cent')]
PHJ19021201-V17-12-page32.txt: [('-ice-President', 'ice-President')]
PHJ19021201-V17-12-page34.txt: [('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', '')]
PHJ19021201-V17-12-page5.txt: [('tem-', 'tem'), ('be-', 'be')]
PHJ19030101-V18-01-page11.txt: [("-day's", "day's")]
PHJ19030101-V18-01-page13.txt: [('---', '--')]
PHJ19030101-V18-01-page15.txt: [('-', '')]
PHJ19030101-V18-01-page2.txt: [('Temper-', 'Temper')]
PHJ19030101-V18-01-page22.txt: [('-', ''), ('-', '')]
PHJ19030101-V18-01-page27.txt: [('DISINFECT-', 'DISINFECT'), ('OR-', 'OR')]
PHJ19030101-V18-01-page29.txt: [('con-', 'con')]
PHJ19030101-V18-01-page3.txt: [('NUTTY-', 'NUTTY')]
PHJ19030101-V18-01-page30.txt: [('-', '')]
PHJ19030101-V18-01-page31.txt: [('Train-', 'Train')]
PHJ19030101-V18-01-page34.txt: [('-', ''), ('-', ''), ('-', '')]
PHJ19030101-V18-01-page35.txt: [('.-', '.'), ('f-', 'f'), ('-.', '.'), ('L-', 'L'), ('..-', '..'), ('.-', '.'), ('.-', '.')]
PHJ19030101-V18-01-page5.txt: [('strengthen-', 'strengthen')]
PHJ19030101-V18-01-page7.txt: [('in-', 'in')]
PHJ19030201-V18-02-page16.txt: [('Ga-', 'Ga')]
PHJ19030201-V18-02-page22.txt: [('be-', 'be')]
PHJ19030201-V18-02-page25.txt: [('JouR-', 'JouR')]
PHJ19030201-V18-02-page3.txt: [('NUTTY-', 'NUTTY')]
PHJ19030201-V18-02-page34.txt: [('-', ''), ('-', ''), ('-', '')]
PHJ19030201-V18-02-page35.txt: [('-', ''), ('-', '')]
PHJ19030201-V18-02-page36.txt: [('-', '')]
PHJ19030201-V18-02-page9.txt: [('neural-', 'neural')]
PHJ19030301-V18-03-page11.txt: [('walk-', 'walk'), ('impor-', 'impor')]
PHJ19030301-V18-03-page12.txt: [('dis-', 'dis')]
PHJ19030301-V18-03-page18.txt: [("-Woman's", "Woman's")]
PHJ19030301-V18-03-page25.txt: [('per-', 'per')]
PHJ19030301-V18-03-page3.txt: [('NUTTY-', 'NUTTY')]
PHJ19030301-V18-03-page31.txt: [('-', '')]
PHJ19030301-V18-03-page34.txt: [('-', ''), ('-', ''), ('-', '')]
PHJ19030301-V18-03-page5.txt: [('prevent-', 'prevent')]
PHJ19030301-V18-03-page7.txt: [('-another', 'another')]
PHJ19030301-V18-03-page9.txt: [('peo-', 'peo')]
PHJ19030401-V18-04-page13.txt: [('Emer-', 'Emer')]
PHJ19030401-V18-04-page16.txt: [('--allowing', '-allowing')]
PHJ19030401-V18-04-page2.txt: [('-', '')]
PHJ19030401-V18-04-page23.txt: [('theo-', 'theo'), ('ques-', 'ques')]
PHJ19030401-V18-04-page26.txt: [('-He', 'He')]
PHJ19030401-V18-04-page28.txt: [('STAM-', 'STAM')]
PHJ19030401-V18-04-page29.txt: [('-', ''), ('-page', 'page'), ('-page', 'page')]
PHJ19030401-V18-04-page3.txt: [('NUTTY-', 'NUTTY')]
PHJ19030401-V18-04-page30.txt: [('---------', '--------'), ('-', ''), ('Ar--', 'Ar-'), ('-', ''), ('-', ''), ('.-', '.'), ('-', ''), ('-', '')]
PHJ19030401-V18-04-page34.txt: [('-', ''), ('-', ''), ('-', '')]
PHJ19030401-V18-04-page35.txt: [('tingtatnitfr-', 'tingtatnitfr'), ('T-', 'T'), ('-', '')]
PHJ19030401-V18-04-page36.txt: [('-', ''), ('--..', '-..')]
PHJ19030401-V18-04-page5.txt: [('-', ''), ('-it', 'it')]
PHJ19030401-V18-04-page8.txt: [('in-', 'in')]
PHJ19030501-V18-05-page19.txt: [('EDU-', 'EDU')]
PHJ19030501-V18-05-page2.txt: [('NENNP--now-', 'NENNP--now')]
PHJ19030501-V18-05-page20.txt: [('quarrel-', 'quarrel')]
PHJ19030501-V18-05-page24.txt: [('JOUR-', 'JOUR')]
PHJ19030501-V18-05-page3.txt: [('NUTTY-', 'NUTTY')]
PHJ19030501-V18-05-page30.txt: [('-.bur', '.bur'), ('w-', 'w'), ('-', ''), ('-', ''), ('....-', '....'), ('alb-', 'alb'), ('c---', 'c--'), ('-', ''), ('-.', '.'), ('-----', '----'), ('-', ''), ('-', ''), ('--', '-'), ('-', ''), ('------', '-----')]
PHJ19030501-V18-05-page34.txt: [('D-', 'D'), ('-lb.', 'lb.'), ('-', ''), ('-', ''), ('-', '')]
PHJ19030501-V18-05-page35.txt: [('SCIENTIFIC-', 'SCIENTIFIC'), ('-', ''), ('-', '')]
PHJ19030601-V18-06-page11.txt: [('wake-', 'wake'), ('activ-', 'activ'), ('at-', 'at')]
PHJ19030601-V18-06-page16.txt: [('disappoint-', 'disappoint')]
PHJ19030601-V18-06-page18.txt: [('--Bice', '-Bice')]
PHJ19030601-V18-06-page19.txt: [('tab-', 'tab'), ('lit-', 'lit')]
PHJ19030601-V18-06-page2.txt: [('r--', 'r-'), ('-cent', 'cent')]
PHJ19030601-V18-06-page22.txt: [('con-', 'con')]
PHJ19030601-V18-06-page27.txt: [('Biscuit.--', 'Biscuit.-')]
PHJ19030601-V18-06-page3.txt: [('NUTTY-', 'NUTTY')]
PHJ19030601-V18-06-page30.txt: [('s-', 's'), ('-', ''), ('-', ''), ("-I'", "I'"), ('R.-', 'R.'), ('V"-', 'V"'), ('-', ''), ("'-------", "'------"), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-be', 'be'), ('-', ''), ('.-', '.'), ('-f', 'f'), ("-'", "'"), ('-', ''), ('--', '-'), ('-', ''), ('-', '')]
PHJ19030601-V18-06-page34.txt: [('-', ''), ('-', ''), ('-', ''), ('-lb.', 'lb.')]
PHJ19030601-V18-06-page35.txt: [('SCIENTIFIC-', 'SCIENTIFIC')]
PHJ19030601-V18-06-page6.txt: [('les-', 'les')]
PHJ19030701-V18-07-page15.txt: [('-', ''), ('prescrip-', 'prescrip'), ('-', '')]
PHJ19030701-V18-07-page21.txt: [('-please', 'please')]
PHJ19030701-V18-07-page22.txt: [('be-', 'be')]
PHJ19030701-V18-07-page28.txt: [('JOUR-', 'JOUR'), ('-', '')]
PHJ19030701-V18-07-page3.txt: [('NUTTY-', 'NUTTY')]
PHJ19030701-V18-07-page31.txt: [('-SIGNS', 'SIGNS'), ('-PAGE', 'PAGE')]
PHJ19030701-V18-07-page34.txt: [('-lb.', 'lb.'), ('-', ''), ('-', ''), ('-', ''), ('-', '')]
PHJ19030701-V18-07-page35.txt: [('care-', 'care'), ("'tci-", "'tci"), ('-', '')]
PHJ19030701-V18-07-page36.txt: [('prepara-', 'prepara'), ('-p', 'p'), ('c-', 'c')]
PHJ19030801-V18-08-page12.txt: [('-', ''), ('-', ''), ('-', ''), ('arrange-', 'arrange')]
PHJ19030801-V18-08-page13.txt: [('-', ''), ('-', ''), ('-', '')]
PHJ19030801-V18-08-page14.txt: [('pre-', 'pre')]
PHJ19030801-V18-08-page18.txt: [('for-', 'for')]
PHJ19030801-V18-08-page31.txt: [('-PAGE', 'PAGE')]
PHJ19030801-V18-08-page34.txt: [('-', ''), ('-', ''), ('-', '')]
PHJ19030901-V18-09-page1.txt: [('Culture-', 'Culture'), ('Rahy-', 'Rahy')]
PHJ19030901-V18-09-page12.txt: [('-', '')]
PHJ19030901-V18-09-page16.txt: [('bear-', 'bear')]
PHJ19030901-V18-09-page21.txt: [('-page', 'page')]
PHJ19030901-V18-09-page25.txt: [('com-', 'com')]
PHJ19030901-V18-09-page27.txt: [('--', '-'), ('-', '')]
PHJ19030901-V18-09-page29.txt: [('ot-', 'ot'), ('---si-', '--si-'), ('-..', '..'), ('ti-', 'ti'), ('-', ''), ('-', ''), ('JIA-', 'JIA'), ('-', ''), ('-.', '.')]
PHJ19030901-V18-09-page30.txt: [('Man-', 'Man')]
PHJ19030901-V18-09-page31.txt: [('-', '')]
PHJ19030901-V18-09-page32.txt: [('-....', '....'), ('--', '-'), ('-', ''), ('-', ''), ("--i'-", "-i'-"), ('-----', '----'), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('--ri---m---', '-ri---m---'), ('-', ''), ('-', ''), ('--', '-'), ('-', ''), ('-', ''), ('--', '-'), ('-', ''), ('-', ''), ('--...', '-...'), ("..aill'-", "..aill'"), ('-', ''), ("'-", "'"), ('-----', '----'), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-...Lii', '...Lii'), ('A-', 'A'), ('-a', 'a'), ('-.', '.')]
PHJ19030901-V18-09-page34.txt: [('-', ''), ('-', ''), ('-', '')]
PHJ19030901-V18-09-page35.txt: [('care-', 'care'), ('rA-', 'rA'), ('-', '')]
PHJ19030901-V18-09-page4.txt: [('-', ''), ('X---', 'X--'), ('-', ''), ('-', ''), ('------------', '-----------'), ("'---", "'--"), ('I-', 'I'), ('I-', 'I')]
PHJ19031001-V18-10-page10.txt: [('-', ''), ('im-', 'im')]
PHJ19031001-V18-10-page11.txt: [('pto-', 'pto')]
PHJ19031001-V18-10-page16.txt: [('phi-', 'phi')]
PHJ19031001-V18-10-page2.txt: [('-', ''), ('-', ''), ('-', '')]
PHJ19031001-V18-10-page20.txt: [('de-', 'de')]
PHJ19031001-V18-10-page23.txt: [('offen-', 'offen'), ('poi-', 'poi'), ('jour-', 'jour'), ('poi-', 'poi')]
PHJ19031001-V18-10-page24.txt: [('-numerous', 'numerous')]
PHJ19031001-V18-10-page25.txt: [('-', '')]
PHJ19031001-V18-10-page29.txt: [('-', '')]
PHJ19031001-V18-10-page31.txt: [('martyr-fashion--', 'martyr-fashion-')]
PHJ19031001-V18-10-page37.txt: [('I-', 'I')]
PHJ19031001-V18-10-page5.txt: [('-', ''), ('add-', 'add')]
PHJ19031001-V18-10-page6.txt: [('-', '')]
PHJ19031001-V18-10-page7.txt: [('-', ''), ('anti-', 'anti'), ('-', ''), ('de-', 'de'), ('-', '')]
PHJ19031001-V18-10-page8.txt: [('fornica-', 'fornica')]
PHJ19031001-V18-10-page9.txt: [('grind-', 'grind'), ('-', ''), ('Short-', 'Short'), ('vegetarian-', 'vegetarian')]
PHJ19031101-V18-11-page11.txt: [('em-', 'em')]
PHJ19031101-V18-11-page12.txt: [('hyper-', 'hyper')]
PHJ19031101-V18-11-page15.txt: [('for--', 'for-')]
PHJ19031101-V18-11-page29.txt: [('mother--', 'mother-')]
PHJ19031101-V18-11-page3.txt: [('-', ''), ('-', ''), ('-', ''), ('-..', '..'), ('-', ''), ('-', ''), ('-..', '..'), ('-', ''), ('-', ''), ('-', ''), ('.-', '.'), ('-', ''), ('V-', 'V'), ('-', '')]
PHJ19031101-V18-11-page30.txt: [('be.-', 'be.')]
PHJ19031101-V18-11-page36.txt: [('S-', 'S'), ('-', '')]
PHJ19031101-V18-11-page7.txt: [('objec-', 'objec')]
PHJ19031201-V18-12-page17.txt: [('-', '')]
PHJ19031201-V18-12-page20.txt: [('beck-', 'beck')]
PHJ19031201-V18-12-page24.txt: [('bun-', 'bun')]
PHJ19031201-V18-12-page25.txt: [('Wood-', 'Wood')]
PHJ19031201-V18-12-page3.txt: [('-..', '..'), ('..---', '..--'), ('-', ''), ("'..-", "'.."), ('.-', '.'), ('-', ''), ('Represent-', 'Represent'), ('ag-', 'ag'), ('-t', 't'), ('.-', '.'), ('-dfill', 'dfill'), ('-f', 'f'), ('--', '-'), ('-', ''), ('---', '--'), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', '')]
PHJ19031201-V18-12-page32.txt: [('-e', 'e'), ('.--', '.-'), ('-', ''), ('------', '-----'), ('-', ''), ('....--', '....-'), ('..---."--', '..---."-'), ('-', ''), ('-', ''), ('.....-', '.....'), ('.---', '.--'), ('---', '--'), ('r-', 'r'), ('-', ''), ('-', ''), ('---r-', '--r-'), ('-', ''), ('-', ''), ('----ii', '---ii'), ('-', ''), ('-.', '.'), ('-', ''), ('-', ''), ('--', '-'), ('-ilili', 'ilili'), ('-', ''), ('f-', 'f'), ('.-', '.'), ('--', '-')]
PHJ19031201-V18-12-page34.txt: [('-', ''), ('-', '')]
PHJ19031201-V18-12-page6.txt: [('dis-', 'dis')]
PHJ19040101-V19-01-page28.txt: [('be-', 'be')]
PHJ19040101-V19-01-page29.txt: [('----it', '---it')]
PHJ19040101-V19-01-page32.txt: [('Cook-', 'Cook')]
PHJ19040101-V19-01-page34.txt: [('-', ''), ('-', '')]
PHJ19040101-V19-01-page4.txt: [('-ADDER', 'ADDER')]
PHJ19040101-V19-01-page7.txt: [('water-ab-', 'water-ab')]
PHJ19040101-V19-01-page8.txt: [('-ick', 'ick')]
PHJ19040201-V19-02-page11.txt: [('-There', 'There')]
PHJ19040201-V19-02-page2.txt: [('-tou', 'tou'), ('"-', '"')]
PHJ19040201-V19-02-page23.txt: [('ex-', 'ex')]
PHJ19040201-V19-02-page29.txt: [('.---', '.--')]
PHJ19040201-V19-02-page30.txt: [('-', '')]
PHJ19040201-V19-02-page31.txt: [('-I', 'I'), ('-', ''), ('--', '-'), ('--i', '-i'), ('-f-', 'f-'), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('..-', '..'), ('oti-', 'oti'), ('-', ''), ('-', ''), ('-', '')]
PHJ19040201-V19-02-page32.txt: [('Cook-', 'Cook')]
PHJ19040201-V19-02-page34.txt: [('-ctriu', 'ctriu'), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', '')]
PHJ19040201-V19-02-page35.txt: [('-', ''), ('N-', 'N'), ('t--', 't-'), ('k----', 'k---')]
PHJ19040301-V19-03-page2.txt: [('--', '-'), ('-atin', 'atin'), ('-', ''), ('-', '')]
PHJ19040301-V19-03-page27.txt: [('-', ''), ('-', ''), ('N-', 'N')]
PHJ19040301-V19-03-page29.txt: [('-', ''), ('-', ''), ('-..."', '..."'), ('..-', '..'), ('-', ''), ('--ma', '-ma'), ('-', ''), ('-', ''), ('-...', '...'), ('----', '---'), ('ii-', 'ii'), ('--', '-'), ('-', ''), ('-', ''), ('-', ''), ('-.', '.'), ("-'", "'"), ('it-', 'it'), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ("'--", "'-")]
PHJ19040301-V19-03-page31.txt: [('---', '--'), ('..-', '..'), ('-', '')]
PHJ19040301-V19-03-page33.txt: [('r-', 'r')]
PHJ19040301-V19-03-page34.txt: [('-clouwtyiu', 'clouwtyiu'), ('-', ''), ('-t-', 't-'), ('-', ''), ('-', ''), ('-', '')]
PHJ19040401-V19-04-page15.txt: [('irregu-', 'irregu')]
PHJ19040401-V19-04-page17.txt: [('ob-', 'ob')]
PHJ19040401-V19-04-page19.txt: [('or-', 'or')]
PHJ19040401-V19-04-page29.txt: [('Text-', 'Text')]
PHJ19040401-V19-04-page30.txt: [('--', '-')]
PHJ19040401-V19-04-page34.txt: [('-', ''), ('-', ''), ('-', ''), ('-', '')]
PHJ19040401-V19-04-page35.txt: [('-', '')]
PHJ19040401-V19-04-page36.txt: [('-.', '.'), ('-', ''), ("-'", "'"), ('-', ''), ('....-', '....'), ('-', ''), ('-A-', 'A-')]
PHJ19040401-V19-04-page6.txt: [('-', ''), ('.-', '.')]
PHJ19040501-V19-05-page11.txt: [('JOUR-', 'JOUR')]
PHJ19040501-V19-05-page12.txt: [('pub-', 'pub')]
PHJ19040501-V19-05-page13.txt: [('def-', 'def')]
PHJ19040501-V19-05-page16.txt: [('hope-', 'hope')]
PHJ19040501-V19-05-page2.txt: [("-'L", "'L")]
PHJ19040501-V19-05-page29.txt: [('Pub-', 'Pub')]
PHJ19040501-V19-05-page33.txt: [('-', '')]
PHJ19040501-V19-05-page34.txt: [('-clfou', 'clfou'), ('-iti', 'iti'), ('-', ''), ('-', ''), ('-', ''), ('-', ''), ('-', '')]
PHJ19040501-V19-05-page5.txt: [('be-', 'be')]
PHJ19040501-V19-05-page8.txt: [('Him-', 'Him')]
PHJ19040501-V19-05-page9.txt: [('des-', 'des')]
PHJ19040601-V19-06-page1.txt: [('--', '-')]
PHJ19040601-V19-06-page10.txt: [('elimina-', 'elimina')]
PHJ19040601-V19-06-page18.txt: [('doubt-', 'doubt')]
PHJ19040601-V19-06-page19.txt: [('JouR-', 'JouR')]
PHJ19040601-V19-06-page23.txt: [('--', '-')]
PHJ19040601-V19-06-page3.txt: [('phy-', 'phy')]
PHJ19040601-V19-06-page5.txt: [('-', '')]
PHJ19040601-V19-06-page7.txt: [('in-', 'in')]
PHJ19040601-V19-06-page9.txt: [('Pawlow-', 'Pawlow')]
In [20]:
# %load shared_elements/summary.py
summary = GoH.reports.overview_report(directories['cycle'], spelling_dictionary, title)
Directory: /Users/jeriwieringa/Dissertation/text/text/2017-01-31-corpus-with-utf8-split-into-titles-cleaning/PHJ/correction3 Average verified rate: 0.9803429572874915 Average of error rates: 0.027733170406576316 Total token count: 2850734
In [21]:
# %load shared_elements/top_errors.py
errors_summary = GoH.reports.get_errors_summary( summary )
GoH.reports.top_errors( errors_summary, 10 )[:50]
Out[21]:
[('m', 2734),
('d', 2327),
("'", 2191),
('e', 1391),
('r', 1266),
('t', 1202),
('w', 1175),
('n', 1117),
('co', 1105),
('f', 794),
('g', 766),
('x', 647),
('lb', 588),
('th', 260),
('sel', 251),
('oo', 236),
('mo', 233),
('pp', 228),
('k', 216),
('z', 214),
('u', 199),
("an'", 192),
('q', 133),
('ex', 111),
('al', 107),
('ournal', 105),
('pa', 88),
("'tis", 87),
('te', 86),
('ro', 85),
('oz', 81),
('ga', 81),
("'the", 80),
('va', 73),
('munn', 73),
('ti', 73),
('io', 72),
("''", 68),
('-', 65),
('tion', 63),
("infants'", 61),
('id', 59),
('re', 58),
('zo', 55),
('viperance', 54),
('yo', 48),
('si', 48),
('urnal', 48),
("'em", 48),
('fahr', 46)]
Correction 4 -- Remove extra quotation marks¶
In [22]:
# %load shared_elements/replace_extra_quotation_marks.py
prev = cycle
cycle = "correction4"
directories = GoH.utilities.define_directories(prev, cycle, base_dir)
if not os.path.exists(directories['cycle']):
os.makedirs(directories['cycle'])
corpus = (f for f in listdir(directories['prev']) if not f.startswith('.') and isfile(join(directories['prev'], f)))
for filename in corpus:
content = GoH.utilities.readfile(directories['prev'], filename)
text = re.sub(r"[0-9,!?$:;&]", " ", content)
tokens = GoH.utilities.tokenize_text(text)
corrections = []
for token in tokens:
token_list = list(token)
last_char = token_list[-1]
if last_char is "'":
if len(token) > 1:
if token_list[-2] is 's' or 'S':
pass
else:
corrections.append((token, re.sub(r"'", r"", token)))
else:
pass
elif token[0] is "'":
corrections.append((token, re.sub(r"'", r"", token)))
else:
pass
if len(corrections) > 0:
print('{}: {}'.format(filename, corrections))
for correction in corrections:
content = GoH.clean.replace_pair(correction, content)
else:
pass
with open(join(directories['cycle'], filename), mode="w") as o:
o.write(content)
o.close()
PHJ18850601-V01-01-page12.txt: [("'Blessed", 'Blessed')]
PHJ18850601-V01-01-page16.txt: [("'graham", 'graham')]
PHJ18850601-V01-01-page17.txt: [("'should", 'should')]
PHJ18850601-V01-01-page24.txt: [("'natural", 'natural'), ("'A", 'A'), ("'VP", 'VP')]
PHJ18850601-V01-01-page7.txt: [("'Tis", 'Tis'), ("'Twill", 'Twill'), ("'Tis", 'Tis')]
PHJ18850601-V01-01-page8.txt: [("'Now", 'Now')]
PHJ18850801-V01-02-page16.txt: [("'But", 'But')]
PHJ18850801-V01-02-page5.txt: [("'of", 'of')]
PHJ18850801-V01-02-page7.txt: [("'not", 'not')]
PHJ18851001-V01-03-page11.txt: [("'fortunately", 'fortunately')]
PHJ18851001-V01-03-page12.txt: [("'Taper", 'Taper'), ("'taper", 'taper'), ("'a", 'a')]
PHJ18851001-V01-03-page13.txt: [("'Sometimes", 'Sometimes'), ("'A", 'A')]
PHJ18851001-V01-03-page18.txt: [("'What", 'What')]
PHJ18851001-V01-03-page19.txt: [("'healthy", 'healthy')]
PHJ18851001-V01-03-page20.txt: [("'heroine", 'heroine')]
PHJ18851001-V01-03-page21.txt: [("'sure", 'sure')]
PHJ18851001-V01-03-page22.txt: [("'Our", 'Our')]
PHJ18851001-V01-03-page24.txt: [("'ii", 'ii')]
PHJ18851201-V01-04-page10.txt: [("'It", 'It'), ("'The", 'The'), ("'He", 'He')]
PHJ18851201-V01-04-page14.txt: [("'the", 'the'), ("'The", 'The'), ("'Spect", 'Spect')]
PHJ18851201-V01-04-page15.txt: [("'to", 'to'), ("'Indeed", 'Indeed'), ("'but", 'but'), ("'came", 'came')]
PHJ18851201-V01-04-page18.txt: [("'e", 'e')]
PHJ18851201-V01-04-page22.txt: [("'s", 's')]
PHJ18851201-V01-04-page4.txt: [("'doubt", 'doubt'), ("'and", 'and')]
PHJ18860201-V01-05-page12.txt: [("'ruddy", 'ruddy')]
PHJ18860201-V01-05-page19.txt: [("'Can't", 'Cant'), ("'Why", 'Why')]
PHJ18860201-V01-05-page23.txt: [("'I", 'I')]
PHJ18860201-V01-05-page3.txt: [("'of", 'of')]
PHJ18860401-V01-06-page1.txt: [("'spring.", 'spring.')]
PHJ18860401-V01-06-page12.txt: [("'Indifference", 'Indifference'), ("'is", 'is')]
PHJ18860401-V01-06-page13.txt: [("'Shall", 'Shall'), ("'Yes", 'Yes'), ("'No", 'No')]
PHJ18860401-V01-06-page24.txt: [("'For", 'For')]
PHJ18860401-V01-06-page4.txt: [("'first", 'first')]
PHJ18860401-V01-06-page7.txt: [("'morning", 'morning')]
PHJ18860401-V01-06-page9.txt: [("'will", 'will')]
PHJ18860601-V02-01-page10.txt: [("'pears", 'pears'), ("'tis", 'tis'), ("'fore", 'fore'), ("'em.", 'em.'), ("'em", 'em'), ("'em", 'em')]
PHJ18860601-V02-01-page11.txt: [("'em", 'em'), ("'em.", 'em.')]
PHJ18860601-V02-01-page12.txt: [("'and", 'and'), ("'users", 'users')]
PHJ18860601-V02-01-page13.txt: [("'respiratory", 'respiratory'), ("'regulator", 'regulator')]
PHJ18860601-V02-01-page15.txt: [("'er", 'er'), ("'stonishing", 'stonishing'), ("'er", 'er')]
PHJ18860601-V02-01-page16.txt: [("'The", 'The')]
PHJ18860601-V02-01-page23.txt: [("'How", 'How')]
PHJ18860601-V02-01-page5.txt: [("'midst", 'midst')]
PHJ18860601-V02-01-page9.txt: [("'The", 'The')]
PHJ18860801-V02-02-page1.txt: [("''Ir", 'Ir')]
PHJ18860801-V02-02-page17.txt: [("'spect", 'spect')]
PHJ18860801-V02-02-page18.txt: [("'oo", 'oo')]
PHJ18860801-V02-02-page22.txt: [("'Tish", 'Tish')]
PHJ18860801-V02-02-page26.txt: [("'ffia", 'ffia')]
PHJ18860801-V02-02-page28.txt: [("'Ibrown", 'Ibrown')]
PHJ18860801-V02-02-page6.txt: [("'They", 'They'), ("'But", 'But')]
PHJ18861001-V02-03-page1.txt: [("'.", '.'), ("'..", '..')]
PHJ18861001-V02-03-page13.txt: [("'The", 'The')]
PHJ18861001-V02-03-page14.txt: [("'There", 'There'), ("'em.", 'em.'), ("'em", 'em'), ("'em", 'em'), ("'em", 'em')]
PHJ18861001-V02-03-page16.txt: [("'s", 's')]
PHJ18861001-V02-03-page17.txt: [("'tobacco", 'tobacco')]
PHJ18861001-V02-03-page26.txt: [("'Rip", 'Rip'), ("'created", 'created'), ("'very", 'very')]
PHJ18861001-V02-03-page27.txt: [("'Tress", 'Tress')]
PHJ18861001-V02-03-page28.txt: [('\'m"aenrnel', 'm"aenrnel'), ("'TEMPERANCE", 'TEMPERANCE'), ("'TEMPERANCE", 'TEMPERANCE')]
PHJ18861001-V02-03-page29.txt: [("'What", 'What')]
PHJ18861001-V02-03-page5.txt: [("'A", 'A')]
PHJ18861201-V02-04-page1.txt: [("'NNN.", 'NNN.'), ("'...", '...'), ("'i", 'i')]
PHJ18861201-V02-04-page13.txt: [("'corsets", 'corsets')]
PHJ18861201-V02-04-page14.txt: [("'twas", 'twas'), ("'tis", 'tis')]
PHJ18861201-V02-04-page22.txt: [("'very", 'very')]
PHJ18861201-V02-04-page26.txt: [("'x.", 'x.')]
PHJ18861201-V02-04-page29.txt: [("'In", 'In'), ("'In", 'In')]
PHJ18861201-V02-04-page30.txt: [("'rum", 'rum')]
PHJ18861201-V02-04-page7.txt: [("'or", 'or')]
PHJ18870201-V02-05-page1.txt: [("'.s.", '.s.'), ("''XXN.V..", 'XXN.V..')]
PHJ18870201-V02-05-page10.txt: [("'of", 'of')]
PHJ18870201-V02-05-page18.txt: [("'great", 'great')]
PHJ18870201-V02-05-page2.txt: [("'to", 'to')]
PHJ18870201-V02-05-page25.txt: [("'clothing", 'clothing'), ("'the", 'the')]
PHJ18870201-V02-05-page29.txt: [('\'e"', 'e"')]
PHJ18870201-V02-05-page9.txt: [("'that", 'that'), ("'Taint", 'Taint')]
PHJ18870401-V02-06-page16.txt: [("'em.", 'em.'), ("'em.", 'em.'), ("'em", 'em'), ("'em", 'em'), ("'em", 'em'), ("'em", 'em'), ("'did", 'did')]
PHJ18870401-V02-06-page18.txt: [("'etc.", 'etc.')]
PHJ18870401-V02-06-page22.txt: [("'Tis", 'Tis'), ("'Tis", 'Tis'), ("'tis", 'tis'), ("'ots", 'ots')]
PHJ18870401-V02-06-page26.txt: [("'Society", 'Society')]
PHJ18870401-V02-06-page27.txt: [("'Territory", 'Territory')]
PHJ18870401-V02-06-page28.txt: [("'The", 'The')]
PHJ18870401-V02-06-page29.txt: [("'The", 'The')]
PHJ18870401-V02-06-page31.txt: [("'arks", 'arks')]
PHJ18870401-V02-06-page4.txt: [("'In", 'In')]
PHJ18870401-V02-06-page5.txt: [("'T", 'T')]
PHJ18870401-V02-06-page8.txt: [("'God", 'God'), ("'drinking", 'drinking')]
PHJ18870401-V02-06-page9.txt: [("'If", 'If'), ("'unseasonable", 'unseasonable')]
PHJ18870601-V02-07-page1.txt: [("'N", 'N')]
PHJ18870601-V02-07-page16.txt: [("'taint", 'taint'), ("'cause", 'cause'), ("'Vice", 'Vice')]
PHJ18870601-V02-07-page17.txt: [("'Twas", 'Twas')]
PHJ18870601-V02-07-page20.txt: [("'hard-pan", 'hard-pan')]
PHJ18870601-V02-07-page24.txt: [("'II", 'II'), ("'aint", 'aint')]
PHJ18870601-V02-07-page25.txt: [("'These", 'These'), ("'intended", 'intended')]
PHJ18870601-V02-07-page26.txt: [("'gainst", 'gainst')]
PHJ18870601-V02-07-page27.txt: [("'Walla", 'Walla')]
PHJ18870601-V02-07-page29.txt: [("'These", 'These'), ("'Breakfast", 'Breakfast')]
PHJ18870601-V02-07-page3.txt: [("'healthy", 'healthy')]
PHJ18870801-V02-08-page1.txt: [("'.", '.'), ("'.", '.'), ("'.", '.'), ("'.", '.')]
PHJ18870801-V02-08-page12.txt: [("'things", 'things')]
PHJ18870801-V02-08-page18.txt: [("'Twas", 'Twas'), ("'em", 'em')]
PHJ18870801-V02-08-page2.txt: [("'New", 'New')]
PHJ18870801-V02-08-page21.txt: [("'interesting", 'interesting')]
PHJ18870801-V02-08-page23.txt: [('\'"MY', '"MY')]
PHJ18870801-V02-08-page24.txt: [("'bout", 'bout')]
PHJ18870801-V02-08-page26.txt: [("'poor", 'poor')]
PHJ18870801-V02-08-page29.txt: [("''....", '....')]
PHJ18870801-V02-08-page32.txt: [("'For", 'For'), ("'oat", 'oat')]
PHJ18870801-V02-08-page6.txt: [("'day", 'day')]
PHJ18870801-V02-08-page8.txt: [("'Crystal", 'Crystal')]
PHJ18870801-V02-08-page9.txt: [("'work", 'work')]
PHJ18871001-V02-09-page1.txt: [("'.", '.'), ("'s.", 's.')]
PHJ18871001-V02-09-page12.txt: [("'round", 'round'), ("'nough", 'nough'), ("'pears", 'pears')]
PHJ18871001-V02-09-page13.txt: [("'spose", 'spose')]
PHJ18871001-V02-09-page15.txt: [("'or", 'or')]
PHJ18871001-V02-09-page23.txt: [("'of", 'of'), ("'directly", 'directly')]
PHJ18871001-V02-09-page25.txt: [("'No.", 'No.')]
PHJ18871001-V02-09-page32.txt: [("'Muscular", 'Muscular')]
PHJ18871001-V02-09-page34.txt: [("'Two", 'Two')]
PHJ18871001-V02-09-page5.txt: [("'And", 'And')]
PHJ18871001-V02-09-page8.txt: [("'to", 'to')]
PHJ18880101-V03-01-page12.txt: [("'Mid", 'Mid')]
PHJ18880101-V03-01-page13.txt: [("'ong.", 'ong.'), ("'following", 'following')]
PHJ18880101-V03-01-page14.txt: [("'evil", 'evil')]
PHJ18880101-V03-01-page16.txt: [("'that", 'that'), ("'Faith", 'Faith')]
PHJ18880101-V03-01-page22.txt: [("'gin", 'gin'), ("'midst", 'midst')]
PHJ18880101-V03-01-page26.txt: [("'N", 'N')]
PHJ18880101-V03-01-page28.txt: [("'I", 'I')]
PHJ18880101-V03-01-page4.txt: [("'Have", 'Have'), ('\'flesh.\'"', 'flesh."')]
PHJ18880101-V03-01-page6.txt: [("'dines", 'dines')]
PHJ18880201-V03-02-page11.txt: [("'tisn't", 'tisnt'), ("'tain't", 'taint')]
PHJ18880201-V03-02-page14.txt: [("'It", 'It'), ("'iquors", 'iquors')]
PHJ18880201-V03-02-page17.txt: [("'em", 'em'), ("'em.", 'em.')]
PHJ18880201-V03-02-page2.txt: [("'give", 'give'), ("'As", 'As')]
PHJ18880201-V03-02-page22.txt: [("'Twere", 'Twere')]
PHJ18880201-V03-02-page5.txt: [("'Bile", 'Bile')]
PHJ18880301-V03-03-page12.txt: [("'also", 'also')]
PHJ18880301-V03-03-page18.txt: [("'I", 'I')]
PHJ18880301-V03-03-page25.txt: [("'jnI", 'jnI')]
PHJ18880301-V03-03-page27.txt: [("'L", 'L')]
PHJ18880301-V03-03-page30.txt: [("''.", '.'), ("'i", 'i'), ("'.", '.'), ("'.", '.')]
PHJ18880301-V03-03-page7.txt: [("'.", '.')]
PHJ18880401-V03-04-page11.txt: [("'But", 'But'), ("'Because", 'Because'), ("'Fannie", 'Fannie'), ("'so", 'so'), ("'Twas", 'Twas')]
PHJ18880401-V03-04-page12.txt: [("'Thy", 'Thy')]
PHJ18880401-V03-04-page15.txt: [("'a", 'a')]
PHJ18880401-V03-04-page16.txt: [("'em", 'em')]
PHJ18880401-V03-04-page17.txt: [("'.", '.')]
PHJ18880401-V03-04-page2.txt: [("'be", 'be')]
PHJ18880401-V03-04-page22.txt: [("'Alice", 'Alice')]
PHJ18880401-V03-04-page23.txt: [("'cept", 'cept')]
PHJ18880401-V03-04-page27.txt: [("'.", '.'), ("'T", 'T')]
PHJ18880401-V03-04-page28.txt: [("'Co", 'Co')]
PHJ18880401-V03-04-page32.txt: [("'who", 'who'), ("'who", 'who')]
PHJ18880401-V03-04-page5.txt: [("'behind", 'behind')]
PHJ18880401-V03-04-page6.txt: [("'em.", 'em.'), ("'em.", 'em.')]
PHJ18880401-V03-04-page8.txt: [("'the", 'the')]
PHJ18880401-V03-04-page9.txt: [("'I", 'I'), ("'perfectly", 'perfectly')]
PHJ18880501-V03-05-page13.txt: [("'Why", 'Why'), ("'the", 'the'), ("'Water", 'Water')]
PHJ18880501-V03-05-page14.txt: [("'tis", 'tis')]
PHJ18880501-V03-05-page18.txt: [("'Twas", 'Twas')]
PHJ18880501-V03-05-page21.txt: [("'Those", 'Those')]
PHJ18880501-V03-05-page25.txt: [("'ate", 'ate')]
PHJ18880501-V03-05-page26.txt: [("'qllltlioutr", 'qllltlioutr')]
PHJ18880501-V03-05-page27.txt: [("'z", 'z'), ('\'""', '""')]
PHJ18880501-V03-05-page29.txt: [("'Co", 'Co')]
PHJ18880501-V03-05-page7.txt: [("'an", 'an')]
PHJ18880501-V03-05-page8.txt: [("'so", 'so'), ("'And", 'And')]
PHJ18880501-V03-05-page9.txt: [("'That", 'That')]
PHJ18880601-V03-06-page13.txt: [("'Ripeness", 'Ripeness')]
PHJ18880601-V03-06-page16.txt: [("'to", 'to')]
PHJ18880601-V03-06-page17.txt: [("'gainst", 'gainst'), ("'bout", 'bout')]
PHJ18880601-V03-06-page19.txt: [("'and", 'and')]
PHJ18880601-V03-06-page20.txt: [("'make", 'make')]
PHJ18880601-V03-06-page25.txt: [("'co", 'co')]
PHJ18880601-V03-06-page27.txt: [("'MONEY", 'MONEY'), ("'SM", 'SM')]
PHJ18880601-V03-06-page28.txt: [("'the", 'the')]
PHJ18880601-V03-06-page30.txt: [("'d", 'd')]
PHJ18880601-V03-06-page8.txt: [("'to", 'to')]
PHJ18880701-V03-07-page10.txt: [("'the", 'the')]
PHJ18880701-V03-07-page13.txt: [("'T.", 'T.')]
PHJ18880701-V03-07-page15.txt: [("'Additional", 'Additional')]
PHJ18880701-V03-07-page21.txt: [("'bleeged", 'bleeged'), ("'bleeged", 'bleeged')]
PHJ18880701-V03-07-page27.txt: [("'fc", 'fc')]
PHJ18880701-V03-07-page30.txt: [("'Each", 'Each')]
PHJ18880701-V03-07-page4.txt: [("'that", 'that')]
PHJ18880801-V03-08-page12.txt: [("'J", 'J')]
PHJ18880801-V03-08-page14.txt: [("'tis", 'tis')]
PHJ18880801-V03-08-page18.txt: [("'notwithstanding", 'notwithstanding')]
PHJ18880801-V03-08-page19.txt: [("'twas", 'twas'), ("'twas", 'twas'), ("'twasn't", 'twasnt')]
PHJ18880801-V03-08-page26.txt: [("'f", 'f')]
PHJ18880801-V03-08-page27.txt: [("'I", 'I'), ("'P", 'P')]
PHJ18880801-V03-08-page29.txt: [("'Co", 'Co')]
PHJ18880801-V03-08-page31.txt: [("'gaper", 'gaper')]
PHJ18880801-V03-08-page32.txt: [("'uncap", 'uncap'), ("'cry", 'cry')]
PHJ18880801-V03-08-page8.txt: [("'down", 'down')]
PHJ18880901-V03-09-page12.txt: [("'a", 'a')]
PHJ18880901-V03-09-page14.txt: [("'twas", 'twas')]
PHJ18880901-V03-09-page15.txt: [("'demands", 'demands')]
PHJ18880901-V03-09-page16.txt: [("'the", 'the')]
PHJ18880901-V03-09-page17.txt: [("'public", 'public'), ("'decomposition", 'decomposition')]
PHJ18880901-V03-09-page20.txt: [("'We", 'We')]
PHJ18880901-V03-09-page22.txt: [("'neath", 'neath')]
PHJ18880901-V03-09-page29.txt: [("'Liberal", 'Liberal')]
PHJ18880901-V03-09-page31.txt: [("'Slill", 'Slill')]
PHJ18880901-V03-09-page32.txt: [("'Workmanship", 'Workmanship'), ("'Y", 'Y')]
PHJ18881001-V03-10-page12.txt: [("'on", 'on')]
PHJ18881001-V03-10-page13.txt: [("'What", 'What'), ("'Ah", 'Ah'), ("'they", 'they'), ("'Not", 'Not'), ("'Mean", 'Mean'), ("'that", 'that'), ("'Mr.", 'Mr.'), ("'ere", 'ere'), ("'and", 'and'), ("'em", 'em'), ("'em", 'em')]
PHJ18881001-V03-10-page14.txt: [("'my", 'my'), ("'Tis", 'Tis'), ("'Twill", 'Twill')]
PHJ18881001-V03-10-page15.txt: [("'all", 'all')]
PHJ18881001-V03-10-page18.txt: [("'Though", 'Though'), ("'neath", 'neath'), ("'tis", 'tis')]
PHJ18881001-V03-10-page20.txt: [("'After", 'After'), ("'Suddenly", 'Suddenly')]
PHJ18881001-V03-10-page21.txt: [("'rest", 'rest')]
PHJ18881001-V03-10-page23.txt: [("'em", 'em')]
PHJ18881001-V03-10-page24.txt: [("'and", 'and')]
PHJ18881001-V03-10-page26.txt: [("'em", 'em'), ("'em", 'em')]
PHJ18881001-V03-10-page29.txt: [("'Co", 'Co')]
PHJ18881001-V03-10-page31.txt: [("'Sides", 'Sides')]
PHJ18881101-V03-11-page1.txt: [("'Duty", 'Duty'), ("'bad", 'bad'), ("'misfortune", 'misfortune')]
PHJ18881101-V03-11-page14.txt: [("'Tis", 'Tis')]
PHJ18881101-V03-11-page18.txt: [("'Tis", 'Tis'), ("'must", 'must')]
PHJ18881101-V03-11-page19.txt: [("'soul", 'soul')]
PHJ18881101-V03-11-page20.txt: [("'Whether", 'Whether')]
PHJ18881101-V03-11-page24.txt: [("'ow", 'ow'), ("'ooman", 'ooman')]
PHJ18881101-V03-11-page25.txt: [("'bout", 'bout'), ("'Gusty", 'Gusty'), ("'vised", 'vised'), ("'spinted", 'spinted'), ("'splain", 'splain')]
PHJ18881101-V03-11-page27.txt: [("'iii", 'iii')]
PHJ18881101-V03-11-page29.txt: [("'S", 'S')]
PHJ18881101-V03-11-page3.txt: [("'burn", 'burn')]
PHJ18881101-V03-11-page31.txt: [("'ts", 'ts'), ("'Co", 'Co')]
PHJ18881101-V03-11-page7.txt: [("'on", 'on')]
PHJ18881201-V03-12-page11.txt: [("'I", 'I'), ("'The", 'The')]
PHJ18881201-V03-12-page13.txt: [("'the", 'the')]
PHJ18881201-V03-12-page17.txt: [("'cos", 'cos')]
PHJ18881201-V03-12-page22.txt: [("'mid", 'mid')]
PHJ18881201-V03-12-page27.txt: [("'ciety", 'ciety')]
PHJ18881201-V03-12-page28.txt: [("'zr", 'zr')]
PHJ18881201-V03-12-page3.txt: [("'Hannah's", 'Hannahs')]
PHJ18881201-V03-12-page6.txt: [("'While", 'While'), ("'The", 'The'), ("'physiological", 'physiological'), ("'The", 'The')]
PHJ18881201-V03-12-page8.txt: [("'when", 'when')]
PHJ18890101-V04-01-page1.txt: [("'Worry", 'Worry')]
PHJ18890101-V04-01-page12.txt: [("'their", 'their')]
PHJ18890101-V04-01-page13.txt: [("'em", 'em')]
PHJ18890101-V04-01-page14.txt: [("'bacco", 'bacco'), ("'bacco", 'bacco')]
PHJ18890101-V04-01-page16.txt: [("'a", 'a')]
PHJ18890101-V04-01-page17.txt: [("'We", 'We')]
PHJ18890101-V04-01-page2.txt: [("'never", 'never')]
PHJ18890101-V04-01-page22.txt: [("'Tis", 'Tis'), ("'Tis", 'Tis'), ("'Tis", 'Tis'), ("'Tis", 'Tis')]
PHJ18890101-V04-01-page24.txt: [("'.I", '.I')]
PHJ18890101-V04-01-page26.txt: [("'looked", 'looked')]
PHJ18890101-V04-01-page29.txt: [("'No.", 'No.')]
PHJ18890101-V04-01-page31.txt: [("'I", 'I')]
PHJ18890201-V04-02-page11.txt: [("'ontaminate", 'ontaminate'), ("'From", 'From')]
PHJ18890201-V04-02-page14.txt: [("'spirituous", 'spirituous')]
PHJ18890201-V04-02-page16.txt: [("'THE", 'THE')]
PHJ18890201-V04-02-page17.txt: [("'the", 'the')]
PHJ18890201-V04-02-page18.txt: [("'tis", 'tis')]
PHJ18890201-V04-02-page21.txt: [("'that", 'that')]
PHJ18890201-V04-02-page24.txt: [("'I", 'I')]
PHJ18890201-V04-02-page28.txt: [("'mole..", 'mole..')]
PHJ18890201-V04-02-page31.txt: [("'SW", 'SW')]
PHJ18890201-V04-02-page32.txt: [("'a", 'a'), ("'Abiding", 'Abiding')]
PHJ18890201-V04-02-page4.txt: [("'to", 'to'), ("'.", '.')]
PHJ18890201-V04-02-page8.txt: [("'and", 'and'), ("'article.", 'article.')]
PHJ18890201-V04-02-page9.txt: [("'artist", 'artist')]
PHJ18890301-V04-03-page12.txt: [("'a", 'a')]
PHJ18890301-V04-03-page13.txt: [("'Who", 'Who')]
PHJ18890301-V04-03-page14.txt: [("'very", 'very'), ("'the", 'the')]
PHJ18890301-V04-03-page19.txt: [("'Some", 'Some'), ("'My", 'My')]
PHJ18890301-V04-03-page2.txt: [("'nooralgy", 'nooralgy')]
PHJ18890301-V04-03-page20.txt: [("'twas", 'twas'), ("'twould", 'twould')]
PHJ18890301-V04-03-page24.txt: [("'twas", 'twas'), ("'twas", 'twas')]
PHJ18890301-V04-03-page28.txt: [("'C", 'C')]
PHJ18890301-V04-03-page3.txt: [("'from", 'from')]
PHJ18890301-V04-03-page32.txt: [("'I", 'I')]
PHJ18890301-V04-03-page8.txt: [("'that", 'that')]
PHJ18890401-V04-04-page17.txt: [("'organs", 'organs')]
PHJ18890401-V04-04-page18.txt: [("'through", 'through')]
PHJ18890401-V04-04-page24.txt: [("'Twas", 'Twas'), ("'then", 'then')]
PHJ18890401-V04-04-page25.txt: [("'The", 'The')]
PHJ18890401-V04-04-page27.txt: [("'ro", 'ro'), ("'he", 'he')]
PHJ18890401-V04-04-page28.txt: [("'C", 'C'), ("'c'zic.", 'czic.'), ("'WVA.", 'WVA.'), ("'.", '.'), ("'a", 'a'), ("'c", 'c'), ("''Va.d", 'Va.d')]
PHJ18890401-V04-04-page3.txt: [("'My", 'My'), ("'go", 'go')]
PHJ18890401-V04-04-page31.txt: [("'shortened.", 'shortened.')]
PHJ18890401-V04-04-page32.txt: [("'Thermo", 'Thermo')]
PHJ18890401-V04-04-page5.txt: [("'Send", 'Send'), ("'enough", 'enough')]
PHJ18890401-V04-04-page6.txt: [("'plaster", 'plaster'), ("'something", 'something'), ("'something", 'something'), ("'Something", 'Something'), ("'big-jaw", 'big-jaw')]
PHJ18890401-V04-04-page7.txt: [("'big-jaw", 'big-jaw')]
PHJ18890401-V04-04-page8.txt: [("'of", 'of')]
PHJ18890501-V04-05-page1.txt: [("'Eat", 'Eat')]
PHJ18890501-V04-05-page10.txt: [("'gargling", 'gargling')]
PHJ18890501-V04-05-page15.txt: [("'Yes", 'Yes'), ("'the", 'the')]
PHJ18890501-V04-05-page21.txt: [("'airy", 'airy')]
PHJ18890501-V04-05-page24.txt: [("'Tis", 'Tis'), ("'ail", 'ail')]
PHJ18890501-V04-05-page25.txt: [("'Misses", 'Misses'), ("'y", 'y')]
PHJ18890501-V04-05-page3.txt: [("'as", 'as')]
PHJ18890501-V04-05-page31.txt: [("'Co", 'Co'), ("'dress", 'dress')]
PHJ18890501-V04-05-page8.txt: [("'taint", 'taint'), ("'twas", 'twas'), ("'tis", 'tis'), ("'till", 'till')]
PHJ18890601-V04-06-page12.txt: [("'Tis", 'Tis')]
PHJ18890601-V04-06-page16.txt: [("'Tis", 'Tis')]
PHJ18890601-V04-06-page19.txt: [("'man", 'man')]
PHJ18890601-V04-06-page24.txt: [("'r", 'r')]
PHJ18890601-V04-06-page27.txt: [("'and", 'and')]
PHJ18890601-V04-06-page29.txt: [('\'"', '"'), ("'.", '.')]
PHJ18890601-V04-06-page32.txt: [("'TOY", 'TOY')]
PHJ18890601-V04-06-page5.txt: [("'There", 'There')]
PHJ18890701-V04-07-page10.txt: [("'or", 'or')]
PHJ18890701-V04-07-page12.txt: [("'twas", 'twas'), ("'tis", 'tis')]
PHJ18890701-V04-07-page17.txt: [("'mature", 'mature')]
PHJ18890701-V04-07-page18.txt: [("'em", 'em')]
PHJ18890701-V04-07-page22.txt: [("'every", 'every')]
PHJ18890701-V04-07-page27.txt: [("'A", 'A')]
PHJ18890701-V04-07-page28.txt: [("'II", 'II'), ("'MEDICAL", 'MEDICAL')]
PHJ18890701-V04-07-page7.txt: [("'excursus", 'excursus')]
PHJ18890801-V04-08-page13.txt: [("'ballots", 'ballots'), ("'e", 'e'), ("'em", 'em')]
PHJ18890801-V04-08-page14.txt: [("'em", 'em'), ("'E", 'E')]
PHJ18890801-V04-08-page16.txt: [("'Twill", 'Twill')]
PHJ18890801-V04-08-page2.txt: [("'conditions", 'conditions')]
PHJ18890801-V04-08-page21.txt: [("'most", 'most'), ("'most", 'most'), ("'most", 'most'), ("'most", 'most')]
PHJ18890801-V04-08-page24.txt: [("'Tis", 'Tis')]
PHJ18890801-V04-08-page28.txt: [("'tars", 'tars')]
PHJ18890901-V04-09-page12.txt: [('\'"', '"')]
PHJ18890901-V04-09-page16.txt: [("'tis", 'tis')]
PHJ18890901-V04-09-page20.txt: [("'Tis", 'Tis')]
PHJ18890901-V04-09-page24.txt: [("'Tts", 'Tts')]
PHJ18890901-V04-09-page25.txt: [("'say", 'say')]
PHJ18890901-V04-09-page27.txt: [("'those", 'those')]
PHJ18890901-V04-09-page31.txt: [("'Co", 'Co')]
PHJ18891001-V04-10-page16.txt: [("'most", 'most')]
PHJ18891001-V04-10-page2.txt: [("'ere", 'ere')]
PHJ18891001-V04-10-page21.txt: [("'Twill", 'Twill'), ("'the", 'the')]
PHJ18891001-V04-10-page22.txt: [("'You", 'You')]
PHJ18891001-V04-10-page24.txt: [("'twas", 'twas')]
PHJ18891001-V04-10-page29.txt: [("'WS", 'WS'), ("'rs.", 'rs.')]
PHJ18891001-V04-10-page32.txt: [("'I", 'I'), ("'dress", 'dress')]
PHJ18891001-V04-10-page8.txt: [("'twas", 'twas')]
PHJ18891101-V04-11-page11.txt: [("'Take", 'Take')]
PHJ18891101-V04-11-page12.txt: [("'To", 'To')]
PHJ18891101-V04-11-page23.txt: [("'simple", 'simple')]
PHJ18891101-V04-11-page24.txt: [("'taking", 'taking')]
PHJ18891101-V04-11-page26.txt: [("'Temperance", 'Temperance')]
PHJ18891101-V04-11-page3.txt: [("'But", 'But')]
PHJ18891201-V04-12-page1.txt: [("'live", 'live')]
PHJ18891201-V04-12-page31.txt: [("'While", 'While')]
PHJ18891201-V04-12-page32.txt: [("'I", 'I')]
PHJ18891201-V04-12-page33.txt: [("'or", 'or')]
PHJ18891201-V04-12-page34.txt: [("'ea.", 'ea.'), ("'s", 's')]
PHJ18900101-V05-01-page1.txt: [("'visitation", 'visitation'), ("'judgment", 'judgment')]
PHJ18900101-V05-01-page10.txt: [("'Pears", 'Pears'), ("'ill", 'ill'), ("'pear", 'pear'), ("'pears", 'pears'), ("'pears", 'pears')]
PHJ18900101-V05-01-page11.txt: [("'bout", 'bout')]
PHJ18900101-V05-01-page12.txt: [("'hale", 'hale')]
PHJ18900101-V05-01-page16.txt: [("'neath", 'neath'), ("'neath", 'neath')]
PHJ18900101-V05-01-page24.txt: [("'dure", 'dure')]
PHJ18900101-V05-01-page26.txt: [("'which", 'which')]
PHJ18900101-V05-01-page28.txt: [("'or", 'or')]
PHJ18900101-V05-01-page3.txt: [("'the", 'the')]
PHJ18900201-V05-02-page10.txt: [("'cause", 'cause')]
PHJ18900201-V05-02-page11.txt: [("'Pears", 'Pears'), ("'cept", 'cept'), ("'pears", 'pears'), ("'fo", 'fo'), ("'that's", 'thats'), ("'tis", 'tis')]
PHJ18900201-V05-02-page12.txt: [("'evil", 'evil')]
PHJ18900201-V05-02-page15.txt: [("'THE", 'THE')]
PHJ18900201-V05-02-page20.txt: [("'Tis", 'Tis')]
PHJ18900201-V05-02-page21.txt: [("'toil", 'toil')]
PHJ18900201-V05-02-page23.txt: [("'Cats", 'Cats')]
PHJ18900201-V05-02-page25.txt: [("'was", 'was'), ("'that", 'that')]
PHJ18900201-V05-02-page29.txt: [("'Co", 'Co')]
PHJ18900201-V05-02-page31.txt: [("'I", 'I'), ("'spring", 'spring')]
PHJ18900201-V05-02-page32.txt: [("'Orders", 'Orders')]
PHJ18900301-V05-03-page12.txt: [("'twas", 'twas'), ("'neath", 'neath'), ("'Twas", 'Twas')]
PHJ18900301-V05-03-page13.txt: [("'We", 'We'), ("'What", 'What'), ("'Master", 'Master')]
PHJ18900301-V05-03-page14.txt: [("''pointing", 'pointing'), ("'Ye're", 'Yere'), ("'What", 'What'), ("'Were", 'Were'), ("'It", 'It'), ("'I", 'I'), ("'and", 'and'), ("'Well", 'Well'), ("'that", 'that')]
PHJ18900301-V05-03-page15.txt: [("'Your", 'Your'), ("'many", 'many'), ("'you", 'you')]
PHJ18900301-V05-03-page16.txt: [("'avert", 'avert'), ("'dispensation", 'dispensation'), ("'part", 'part')]
PHJ18900301-V05-03-page17.txt: [("'respecter", 'respecter')]
PHJ18900301-V05-03-page20.txt: [("'twould", 'twould')]
PHJ18900301-V05-03-page21.txt: [("'tis", 'tis'), ("'There", 'There')]
PHJ18900301-V05-03-page25.txt: [("'er", 'er'), ("'er", 'er'), ("'f", 'f')]
PHJ18900301-V05-03-page26.txt: [("'physicians", 'physicians')]
PHJ18900301-V05-03-page28.txt: [("'.", '.')]
PHJ18900301-V05-03-page29.txt: [("'the", 'the')]
PHJ18900301-V05-03-page8.txt: [("'TB", 'TB')]
PHJ18900401-V05-04-page1.txt: [("'A", 'A')]
PHJ18900401-V05-04-page12.txt: [("'Tis", 'Tis')]
PHJ18900401-V05-04-page16.txt: [("'tis", 'tis'), ("'little", 'little')]
PHJ18900401-V05-04-page17.txt: [("'anecdotes.", 'anecdotes.'), ("'You", 'You'), ("'You", 'You'), ("'manna", 'manna'), ("'There", 'There')]
PHJ18900401-V05-04-page21.txt: [("'For", 'For'), ("'And", 'And'), ("'they're", 'theyre')]
PHJ18900401-V05-04-page24.txt: [("'Tis", 'Tis')]
PHJ18900401-V05-04-page26.txt: [("'more", 'more')]
PHJ18900401-V05-04-page29.txt: [("'.", '.')]
PHJ18900401-V05-04-page31.txt: [("'flexible", 'flexible')]
PHJ18900401-V05-04-page4.txt: [("'room", 'room')]
PHJ18900401-V05-04-page5.txt: [("'rhe", 'rhe')]
PHJ18900501-V05-05-page12.txt: [("'tis", 'tis'), ("'Tis", 'Tis'), ("'increase", 'increase')]
PHJ18900501-V05-05-page13.txt: [("'remarkable", 'remarkable'), ("'honest", 'honest')]
PHJ18900501-V05-05-page18.txt: [("'rings", 'rings')]
PHJ18900501-V05-05-page21.txt: [("'a", 'a'), ("'A", 'A')]
PHJ18900501-V05-05-page24.txt: [("'fore", 'fore')]
PHJ18900501-V05-05-page29.txt: [("'ice", 'ice')]
PHJ18900501-V05-05-page30.txt: [("'Warranted", 'Warranted')]
PHJ18900501-V05-05-page31.txt: [("'.", '.')]
PHJ18900501-V05-05-page7.txt: [("'But", 'But')]
PHJ18900601-V05-06-page1.txt: [("'fever.", 'fever.')]
PHJ18900601-V05-06-page14.txt: [("'tired", 'tired')]
PHJ18900601-V05-06-page15.txt: [("'education", 'education')]
PHJ18900601-V05-06-page20.txt: [("'which", 'which')]
PHJ18900601-V05-06-page21.txt: [("'railroads", 'railroads')]
PHJ18900601-V05-06-page23.txt: [("'feel", 'feel')]
PHJ18900601-V05-06-page31.txt: [("'c", 'c')]
PHJ18900701-V05-07-page11.txt: [("'excessive", 'excessive'), ("'The", 'The')]
PHJ18900701-V05-07-page12.txt: [("'Dead", 'Dead')]
PHJ18900701-V05-07-page15.txt: [("'mid", 'mid'), ("'Tis", 'Tis'), ("'neath", 'neath'), ("'mid", 'mid')]
PHJ18900701-V05-07-page18.txt: [("'What's", 'Whats'), ("'Man", 'Man')]
PHJ18900701-V05-07-page19.txt: [("'What", 'What'), ("'Onions", 'Onions'), ("'that's", 'thats'), ("'By", 'By')]
PHJ18900701-V05-07-page24.txt: [("'twere", 'twere')]
PHJ18900701-V05-07-page29.txt: [("'You", 'You')]
PHJ18900701-V05-07-page31.txt: [("'cl", 'cl')]
PHJ18900701-V05-07-page6.txt: [("'that", 'that'), ("'That", 'That')]
PHJ18900801-V05-08-page10.txt: [("'Sweet", 'Sweet')]
PHJ18900801-V05-08-page12.txt: [("'extensively", 'extensively')]
PHJ18900801-V05-08-page14.txt: [("'the", 'the')]
PHJ18900801-V05-08-page15.txt: [("'scenes", 'scenes'), ("'tis", 'tis'), ("'tween", 'tween')]
PHJ18900801-V05-08-page24.txt: [("'tis", 'tis'), ("'Gainst", 'Gainst')]
PHJ18900801-V05-08-page25.txt: [("'Co", 'Co')]
PHJ18900801-V05-08-page28.txt: [("'I", 'I')]
PHJ18900801-V05-08-page4.txt: [("'not", 'not')]
PHJ18900801-V05-08-page7.txt: [("'first", 'first')]
PHJ18900801-V05-08-page8.txt: [("'John", 'John')]
PHJ18900801-V05-08-page9.txt: [("'Elizabeth", 'Elizabeth')]
PHJ18900901-V05-09-page11.txt: [("'tis", 'tis'), ("'fraid", 'fraid'), ("'em", 'em'), ("'em", 'em')]
PHJ18900901-V05-09-page15.txt: [("'Neath", 'Neath')]
PHJ18900901-V05-09-page18.txt: [("'evenings", 'evenings')]
PHJ18900901-V05-09-page21.txt: [("'whatever", 'whatever'), ("'an", 'an')]
PHJ18900901-V05-09-page27.txt: [("'the", 'the')]
PHJ18900901-V05-09-page28.txt: [("'promoting", 'promoting'), ('\'"', '"'), ("'r", 'r'), ("'Gold", 'Gold')]
PHJ18900901-V05-09-page9.txt: [("'Coughs", 'Coughs')]
PHJ18901001-V05-10-page10.txt: [("'tis", 'tis')]
PHJ18901001-V05-10-page11.txt: [("'Each", 'Each')]
PHJ18901001-V05-10-page14.txt: [("'The", 'The'), ("'said", 'said')]
PHJ18901001-V05-10-page18.txt: [("'both", 'both')]
PHJ18901001-V05-10-page19.txt: [("'Tis", 'Tis'), ("'Tis", 'Tis'), ("'tis", 'tis'), ("'tis", 'tis')]
PHJ18901001-V05-10-page25.txt: [("'vision", 'vision')]
PHJ18901001-V05-10-page28.txt: [("'t", 't')]
PHJ18901001-V05-10-page3.txt: [("'The", 'The')]
PHJ18901001-V05-10-page31.txt: [("'EWE", 'EWE'), ("'-", '-'), ("'i", 'i')]
PHJ18901001-V05-10-page7.txt: [("'Mid", 'Mid')]
PHJ18901101-V05-11-page11.txt: [("'tis", 'tis'), ("'tis", 'tis')]
PHJ18901101-V05-11-page15.txt: [("'Tis", 'Tis')]
PHJ18901101-V05-11-page26.txt: [("'willing", 'willing')]
PHJ18901101-V05-11-page28.txt: [("'S", 'S')]
PHJ18901101-V05-11-page29.txt: [("'inducements", 'inducements')]
PHJ18901101-V05-11-page31.txt: [("'this", 'this'), ("'FALSE", 'FALSE')]
PHJ18901101-V05-11-page6.txt: [("'But", 'But')]
PHJ18901101-V05-11-page7.txt: [("'all", 'all')]
PHJ18901201-V05-12-page1.txt: [("'There", 'There')]
PHJ18901201-V05-12-page13.txt: [("'TOBACCO", 'TOBACCO')]
PHJ18901201-V05-12-page14.txt: [("'Saul", 'Saul')]
PHJ18901201-V05-12-page15.txt: [("'twould", 'twould'), ("'good", 'good'), ("'Twas", 'Twas')]
PHJ18901201-V05-12-page16.txt: [("'tis", 'tis')]
PHJ18901201-V05-12-page20.txt: [("'No", 'No')]
PHJ18901201-V05-12-page24.txt: [("'round", 'round')]
PHJ18901201-V05-12-page25.txt: [("'Co", 'Co')]
PHJ18901201-V05-12-page26.txt: [("'of", 'of')]
PHJ18901201-V05-12-page28.txt: [("'earn", 'earn')]
PHJ18901201-V05-12-page30.txt: [("'ilinTirliTiFillairirtigillitiffITIFFESTITFIR", 'ilinTirliTiFillairirtigillitiffITIFFESTITFIR'), ("'-il", '-il')]
PHJ18901201-V05-12-page31.txt: [('\'"', '"')]
PHJ18901201-V05-12-page34.txt: [("'Temperance", 'Temperance'), ("'Tea", 'Tea'), ("'Talk", 'Talk'), ("'Three", 'Three'), ("'Pest", 'Pest'), ("'Tight", 'Tight'), ("'Tight", 'Tight')]
PHJ18901201-V05-12-page4.txt: [("'was", 'was')]
PHJ18901201-V05-12-page7.txt: [("'I'here", 'Ihere')]
PHJ18910101-V06-01-page10.txt: [("'Twas", 'Twas')]
PHJ18910101-V06-01-page13.txt: [("'Twill", 'Twill'), ("'poorly", 'poorly')]
PHJ18910101-V06-01-page14.txt: [("'thout", 'thout')]
PHJ18910101-V06-01-page16.txt: [("'.", '.'), ("'women", 'women'), ("'Come", 'Come')]
PHJ18910101-V06-01-page17.txt: [("'mother", 'mother')]
PHJ18910101-V06-01-page2.txt: [("'more", 'more')]
PHJ18910101-V06-01-page22.txt: [("'whether", 'whether')]
PHJ18910101-V06-01-page24.txt: [("'em", 'em'), ("'Tis", 'Tis'), ("'redeeming", 'redeeming')]
PHJ18910101-V06-01-page26.txt: [("'used", 'used')]
PHJ18910101-V06-01-page31.txt: [("'As", 'As'), ("'The", 'The')]
PHJ18910101-V06-01-page32.txt: [("'.", '.'), ("'T", 'T'), ("'AirlfliTlirn", 'AirlfliTlirn'), ('\'"...', '"...')]
PHJ18910101-V06-01-page7.txt: [("'Tis", 'Tis')]
PHJ18910201-V06-02-page1.txt: [("'easily", 'easily')]
PHJ18910201-V06-02-page14.txt: [("'boy", 'boy')]
PHJ18910201-V06-02-page15.txt: [("'Into", 'Into')]
PHJ18910201-V06-02-page16.txt: [("'The", 'The')]
PHJ18910201-V06-02-page18.txt: [("'Lord", 'Lord')]
PHJ18910201-V06-02-page21.txt: [("'The", 'The')]
PHJ18910201-V06-02-page29.txt: [("'I", 'I')]
PHJ18910201-V06-02-page31.txt: [("'SEA'arAtV", 'SEAarAtV')]
PHJ18910201-V06-02-page32.txt: [("'ifTriirittialiiMI", 'ifTriirittialiiMI')]
PHJ18910201-V06-02-page8.txt: [("'off", 'off')]
PHJ18910201-V06-02-page9.txt: [("'not", 'not')]
PHJ18910301-V06-03-page13.txt: [("'in", 'in')]
PHJ18910301-V06-03-page15.txt: [("'If", 'If')]
PHJ18910301-V06-03-page16.txt: [("'Now", 'Now'), ("'t", 't')]
PHJ18910301-V06-03-page17.txt: [("'Tis", 'Tis'), ("'This", 'This')]
PHJ18910301-V06-03-page26.txt: [("'sentiment", 'sentiment')]
PHJ18910301-V06-03-page29.txt: [("'functual", 'functual'), ("'I", 'I')]
PHJ18910301-V06-03-page31.txt: [("'hese", 'hese')]
PHJ18910301-V06-03-page6.txt: [("'the", 'the')]
PHJ18910301-V06-03-page7.txt: [("'Tts", 'Tts')]
PHJ18910401-V06-04-page21.txt: [("'Twas", 'Twas')]
PHJ18910401-V06-04-page8.txt: [("'Twould", 'Twould')]
PHJ18910501-V06-05-page14.txt: [("'Produces", 'Produces')]
PHJ18910501-V06-05-page15.txt: [("'of", 'of')]
PHJ18910501-V06-05-page18.txt: [("'Forget", 'Forget'), ("'floating", 'floating'), ("'healing", 'healing')]
PHJ18910501-V06-05-page25.txt: [('\'stays."', 'stays."')]
PHJ18910501-V06-05-page27.txt: [("'pink", 'pink')]
PHJ18910501-V06-05-page29.txt: [("'dress", 'dress')]
PHJ18910501-V06-05-page30.txt: [("'Waists", 'Waists')]
PHJ18910601-V06-06-page18.txt: [("'Hoosier", 'Hoosier'), ("'Ancient", 'Ancient'), ("'Ancient", 'Ancient')]
PHJ18910601-V06-06-page22.txt: [("'tis", 'tis')]
PHJ18910601-V06-06-page24.txt: [("'that", 'that')]
PHJ18910601-V06-06-page25.txt: [("'Neath", 'Neath')]
PHJ18910601-V06-06-page26.txt: [("'I", 'I')]
PHJ18910701-V06-07-page13.txt: [("'Rs", 'Rs')]
PHJ18910701-V06-07-page14.txt: [("'the", 'the')]
PHJ18910701-V06-07-page24.txt: [("'Twas", 'Twas')]
PHJ18910701-V06-07-page29.txt: [("'Mimic", 'Mimic')]
PHJ18910701-V06-07-page30.txt: [("'.olumes.", '.olumes.')]
PHJ18910701-V06-07-page31.txt: [("'Wen", 'Wen')]
PHJ18910701-V06-07-page6.txt: [("'is", 'is'), ("'In", 'In')]
PHJ18910701-V06-07-page8.txt: [("'Tis", 'Tis')]
PHJ18910801-V06-08-page11.txt: [("'perfectly", 'perfectly')]
PHJ18910801-V06-08-page12.txt: [("'devoted", 'devoted')]
PHJ18910801-V06-08-page14.txt: [("'Tis", 'Tis'), ("'tis", 'tis'), ("'tis", 'tis')]
PHJ18910801-V06-08-page15.txt: [("'dead-lift", 'dead-lift')]
PHJ18910801-V06-08-page17.txt: [("'What", 'What'), ("'If", 'If')]
PHJ18910801-V06-08-page18.txt: [("'Ye", 'Ye'), ("'And", 'And'), ("'the", 'the'), ("'proceed", 'proceed'), ("'suffered", 'suffered')]
PHJ18910801-V06-08-page19.txt: [("'regenerated.", 'regenerated.')]
PHJ18910801-V06-08-page27.txt: [("'Cases", 'Cases')]
PHJ18910801-V06-08-page31.txt: [("'V", 'V'), ("'riven", 'riven')]
PHJ18910801-V06-08-page9.txt: [("'twixt", 'twixt')]
PHJ18910901-V06-09-page11.txt: [("'plays", 'plays')]
PHJ18910901-V06-09-page12.txt: [("'Twas", 'Twas'), ("'kills", 'kills')]
PHJ18910901-V06-09-page13.txt: [("'slop", 'slop')]
PHJ18910901-V06-09-page15.txt: [("'Tis", 'Tis'), ("'mid", 'mid'), ("'I", 'I')]
PHJ18910901-V06-09-page16.txt: [("'Ye", 'Ye'), ("'Where", 'Where')]
PHJ18910901-V06-09-page17.txt: [("'a", 'a')]
PHJ18910901-V06-09-page26.txt: [("'Write", 'Write')]
PHJ18910901-V06-09-page30.txt: [("'MEDICAL", 'MEDICAL')]
PHJ18911001-V06-10-page1.txt: [("'Health", 'Health')]
PHJ18911001-V06-10-page11.txt: [("'finding", 'finding')]
PHJ18911001-V06-10-page12.txt: [("'the", 'the'), ("'proceed", 'proceed')]
PHJ18911001-V06-10-page14.txt: [("'pocket.", 'pocket.')]
PHJ18911001-V06-10-page16.txt: [("'I", 'I'), ("'the", 'the')]
PHJ18911001-V06-10-page17.txt: [("'Blessed", 'Blessed'), ("'all", 'all'), ("'Inasmuch", 'Inasmuch'), ("'Thou", 'Thou')]
PHJ18911001-V06-10-page18.txt: [("'the", 'the')]
PHJ18911001-V06-10-page2.txt: [("'description", 'description')]
PHJ18911001-V06-10-page20.txt: [("'it", 'it')]
PHJ18911001-V06-10-page25.txt: [("'tis", 'tis')]
PHJ18911001-V06-10-page26.txt: [("'No", 'No'), ("'North", 'North')]
PHJ18911001-V06-10-page3.txt: [("'induced", 'induced'), ("'observer.", 'observer.'), ("'creating", 'creating')]
PHJ18911001-V06-10-page30.txt: [("'Style", 'Style')]
PHJ18911001-V06-10-page31.txt: [("'Extension", 'Extension'), ("'Sides", 'Sides'), ("'of", 'of')]
PHJ18911001-V06-10-page4.txt: [("'a", 'a')]
PHJ18911001-V06-10-page5.txt: [("'Others", 'Others')]
PHJ18911001-V06-10-page6.txt: [("'twill", 'twill')]
PHJ18911001-V06-10-page7.txt: [("'education", 'education'), ("'saturated", 'saturated')]
PHJ18911001-V06-10-page8.txt: [("'sturb", 'sturb'), ("'cause", 'cause'), ("'portant", 'portant'), ("'Flo", 'Flo'), ("'cause", 'cause')]
PHJ18911101-V06-11-page12.txt: [("'Let", 'Let'), ("'Thou", 'Thou')]
PHJ18911101-V06-11-page15.txt: [("'abdomen", 'abdomen')]
PHJ18911101-V06-11-page16.txt: [("'Neath", 'Neath'), ("'Mid", 'Mid')]
PHJ18911101-V06-11-page19.txt: [("'of", 'of')]
PHJ18911101-V06-11-page2.txt: [("'come", 'come')]
PHJ18911101-V06-11-page25.txt: [("'of", 'of')]
PHJ18911101-V06-11-page27.txt: [("'.", '.')]
PHJ18911101-V06-11-page3.txt: [("'The", 'The')]
PHJ18911101-V06-11-page31.txt: [("'When", 'When')]
PHJ18911201-V06-12-page13.txt: [("'Not", 'Not')]
PHJ18911201-V06-12-page21.txt: [("'overstimulation", 'overstimulation')]
PHJ18911201-V06-12-page22.txt: [("'.way", '.way')]
PHJ18911201-V06-12-page24.txt: [("'Tis", 'Tis'), ("'tis", 'tis')]
PHJ18911201-V06-12-page26.txt: [("'make", 'make')]
PHJ18911201-V06-12-page28.txt: [("'or", 'or')]
PHJ18911201-V06-12-page31.txt: [("'MALAY", 'MALAY')]
PHJ18911201-V06-12-page32.txt: [("'and", 'and')]
PHJ18911201-V06-12-page33.txt: [("'Tobacco", 'Tobacco')]
PHJ18911201-V06-12-page34.txt: [("'rom", 'rom'), ("'reaching", 'reaching')]
PHJ18911201-V06-12-page7.txt: [("'The", 'The')]
PHJ18911201-V06-12-page9.txt: [("'midst", 'midst'), ("'of", 'of')]
PHJ18920101-V07-01-page12.txt: [("'take", 'take')]
PHJ18920101-V07-01-page13.txt: [("'come", 'come')]
PHJ18920101-V07-01-page17.txt: [("'Twere", 'Twere')]
PHJ18920101-V07-01-page18.txt: [("'Tis", 'Tis')]
PHJ18920101-V07-01-page24.txt: [("'of", 'of')]
PHJ18920101-V07-01-page25.txt: [("'Tis", 'Tis')]
PHJ18920101-V07-01-page27.txt: [("'Thomas", 'Thomas')]
PHJ18920101-V07-01-page29.txt: [("'Volume", 'Volume')]
PHJ18920101-V07-01-page30.txt: [("'LAND", 'LAND')]
PHJ18920201-V07-02-page12.txt: [("'mong", 'mong'), ("'mong", 'mong')]
PHJ18920201-V07-02-page14.txt: [("'You", 'You')]
PHJ18920201-V07-02-page15.txt: [("'Steenth", 'Steenth')]
PHJ18920201-V07-02-page16.txt: [("'Ye", 'Ye'), ("'he", 'he'), ("'Now", 'Now'), ("'in", 'in')]
PHJ18920201-V07-02-page17.txt: [("'The", 'The')]
PHJ18920201-V07-02-page19.txt: [("'Love", 'Love')]
PHJ18920201-V07-02-page22.txt: [('\'"', '"'), ("'twas", 'twas'), ("'twould", 'twould')]
PHJ18920201-V07-02-page25.txt: [("'we", 'we')]
PHJ18920201-V07-02-page27.txt: [("'Publishers", 'Publishers')]
PHJ18920201-V07-02-page29.txt: [("'teat", 'teat'), ("'Old", 'Old')]
PHJ18920201-V07-02-page30.txt: [("'a.", 'a.'), ("'h", 'h')]
PHJ18920201-V07-02-page31.txt: [("'Al", 'Al')]
PHJ18920301-V07-03-page12.txt: [("'All", 'All')]
PHJ18920301-V07-03-page15.txt: [("'way", 'way'), ("'way", 'way')]
PHJ18920301-V07-03-page16.txt: [("'taken", 'taken')]
PHJ18920301-V07-03-page17.txt: [("'at", 'at')]
PHJ18920301-V07-03-page18.txt: [("'Tis", 'Tis')]
PHJ18920301-V07-03-page21.txt: [("'twixt", 'twixt'), ("'twixt", 'twixt')]
PHJ18920301-V07-03-page26.txt: [("'My", 'My')]
PHJ18920301-V07-03-page28.txt: [("'volumes", 'volumes')]
PHJ18920301-V07-03-page32.txt: [("'o", 'o'), ("'As", 'As')]
PHJ18920301-V07-03-page4.txt: [("'to", 'to')]
PHJ18920401-V07-04-page11.txt: [("'sun", 'sun')]
PHJ18920401-V07-04-page12.txt: [("'.They", '.They')]
PHJ18920401-V07-04-page13.txt: [("'.", '.')]
PHJ18920401-V07-04-page14.txt: [("'Nature", 'Nature')]
PHJ18920401-V07-04-page15.txt: [("'this", 'this'), ("'Spring", 'Spring')]
PHJ18920401-V07-04-page17.txt: [("'How", 'How')]
PHJ18920401-V07-04-page20.txt: [("'Whether", 'Whether'), ("'THE", 'THE'), ("'the", 'the'), ("'a", 'a'), ("'little", 'little')]
PHJ18920401-V07-04-page22.txt: [("'Now", 'Now'), ("'I", 'I'), ("'Yes", 'Yes')]
PHJ18920401-V07-04-page23.txt: [("'come", 'come')]
PHJ18920401-V07-04-page24.txt: [("'T", 'T')]
PHJ18920401-V07-04-page32.txt: [("'Jewspaper", 'Jewspaper')]
PHJ18920401-V07-04-page5.txt: [("'do", 'do'), ("'r", 'r')]
PHJ18920401-V07-04-page9.txt: [("'A", 'A')]
PHJ18920501-V07-05-page10.txt: [("'it", 'it')]
PHJ18920501-V07-05-page21.txt: [("'enough", 'enough')]
PHJ18920501-V07-05-page24.txt: [("'Co", 'Co')]
PHJ18920601-V07-06-page11.txt: [("'This", 'This')]
PHJ18920601-V07-06-page14.txt: [("'dark", 'dark')]
PHJ18920601-V07-06-page25.txt: [("'never", 'never'), ("'turn", 'turn'), ("'Loose", 'Loose'), ("'mean", 'mean'), ("'The", 'The'), ("'drop", 'drop')]
PHJ18920601-V07-06-page26.txt: [("'polished", 'polished')]
PHJ18920601-V07-06-page28.txt: [("'powes", 'powes')]
PHJ18920601-V07-06-page30.txt: [("'Ind", 'Ind')]
PHJ18920701-V07-07-page1.txt: [("'Pacific", 'Pacific')]
PHJ18920701-V07-07-page11.txt: [("'He", 'He'), ("'The", 'The')]
PHJ18920701-V07-07-page15.txt: [("'pitied", 'pitied')]
PHJ18920701-V07-07-page17.txt: [("'teetotal", 'teetotal')]
PHJ18920701-V07-07-page18.txt: [("'There", 'There')]
PHJ18920701-V07-07-page23.txt: [("'neath", 'neath'), ("'Tis", 'Tis'), ("'tis", 'tis')]
PHJ18920701-V07-07-page27.txt: [("'anyone", 'anyone'), ("'Compound", 'Compound'), ("'Ohio", 'Ohio')]
PHJ18920701-V07-07-page28.txt: [("'Will", 'Will')]
PHJ18920701-V07-07-page29.txt: [("'they", 'they')]
PHJ18920701-V07-07-page31.txt: [("'flour", 'flour')]
PHJ18920701-V07-07-page32.txt: [("'Marvelous", 'Marvelous')]
PHJ18920701-V07-07-page4.txt: [("'.ccurately", '.ccurately')]
PHJ18920701-V07-07-page6.txt: [("'population", 'population')]
PHJ18920801-V07-08-page14.txt: [("'Joe", 'Joe'), ("'Tennessee", 'Tennessee')]
PHJ18920801-V07-08-page17.txt: [("'clay", 'clay'), ("'dumb", 'dumb'), ("'have", 'have'), ("'And", 'And'), ("'Let", 'Let')]
PHJ18920801-V07-08-page18.txt: [('\'Excelsior.\'"', 'Excelsior."'), ("'What", 'What'), ("'em", 'em')]
PHJ18920801-V07-08-page2.txt: [("'Vault", 'Vault'), ("'danger", 'danger')]
PHJ18920801-V07-08-page24.txt: [("'properly-prepared", 'properly-prepared'), ("'Vhen", 'Vhen')]
PHJ18920801-V07-08-page25.txt: [("'any", 'any')]
PHJ18920801-V07-08-page26.txt: [("'mean", 'mean')]
PHJ18920801-V07-08-page27.txt: [("'consumptive", 'consumptive')]
PHJ18920801-V07-08-page3.txt: [("'Wren", 'Wren'), ("'and", 'and')]
PHJ18920801-V07-08-page4.txt: [("'sugar", 'sugar'), ("'sugar", 'sugar')]
PHJ18920801-V07-08-page7.txt: [("'That", 'That')]
PHJ18920801-V07-08-page8.txt: [("'man", 'man'), ("'ten", 'ten'), ("'scrofula", 'scrofula')]
PHJ18920901-V07-09-page15.txt: [("'It", 'It'), ("'The", 'The'), ("'thoughts", 'thoughts'), ("'Her", 'Her')]
PHJ18920901-V07-09-page16.txt: [("'What", 'What'), ("'It", 'It')]
PHJ18920901-V07-09-page17.txt: [("'Your", 'Your')]
PHJ18920901-V07-09-page18.txt: [("'the", 'the')]
PHJ18920901-V07-09-page6.txt: [("'rise", 'rise')]
PHJ18920901-V07-09-page9.txt: [("'Hasty", 'Hasty')]
PHJ18921001-V07-10-page1.txt: [("'Vacific", 'Vacific')]
PHJ18921001-V07-10-page10.txt: [("'Nessel", 'Nessel')]
PHJ18921001-V07-10-page13.txt: [("'Tis", 'Tis'), ("'Tis", 'Tis')]
PHJ18921001-V07-10-page15.txt: [("'I", 'I')]
PHJ18921001-V07-10-page18.txt: [("'twere", 'twere'), ("'Mong", 'Mong')]
PHJ18921001-V07-10-page2.txt: [("'the", 'the'), ("'of", 'of')]
PHJ18921001-V07-10-page20.txt: [("'that", 'that')]
PHJ18921001-V07-10-page21.txt: [("'It", 'It'), ("'more.", 'more.')]
PHJ18921001-V07-10-page24.txt: [("'other", 'other')]
PHJ18921001-V07-10-page26.txt: [("'DRESSING.", 'DRESSING.')]
PHJ18921001-V07-10-page27.txt: [("'.common", '.common')]
PHJ18921001-V07-10-page28.txt: [("'-Mrs.", '-Mrs.'), ("'hillside", 'hillside'), ("'I.'a.", 'I.a.')]
PHJ18921001-V07-10-page30.txt: [("'Water", 'Water')]
PHJ18921001-V07-10-page32.txt: [("'HASHERS", 'HASHERS')]
PHJ18921001-V07-10-page4.txt: [("'ACIFIC", 'ACIFIC')]
PHJ18921001-V07-10-page9.txt: [("'veins", 'veins')]
PHJ18921101-V07-11-page13.txt: [("'an", 'an')]
PHJ18921101-V07-11-page22.txt: [("'e", 'e')]
PHJ18921101-V07-11-page29.txt: [("'The", 'The'), ("'The", 'The')]
PHJ18921101-V07-11-page3.txt: [("'Elements", 'Elements')]
PHJ18921101-V07-11-page30.txt: [("'Great", 'Great')]
PHJ18921201-V07-12-page10.txt: [("'food", 'food'), ("'three", 'three'), ("'Some", 'Some')]
PHJ18921201-V07-12-page11.txt: [("'In", 'In')]
PHJ18921201-V07-12-page18.txt: [("'CONDUCTED", 'CONDUCTED')]
PHJ18921201-V07-12-page21.txt: [('\'\'Obedience"', 'Obedience"')]
PHJ18921201-V07-12-page26.txt: [("'TWERE", 'TWERE')]
PHJ18921201-V07-12-page29.txt: [('\'"', '"')]
PHJ18921201-V07-12-page30.txt: [("'Great", 'Great')]
PHJ18921201-V07-12-page33.txt: [("'tirade", 'tirade')]
PHJ18921201-V07-12-page5.txt: [("'were", 'were')]
PHJ18921201-V07-12-page7.txt: [("'in", 'in')]
PHJ18921201-V07-12-page8.txt: [("'herself", 'herself')]
PHJ18960101-V11-01-page12.txt: [("'house-band", 'house-band'), ("'Behold", 'Behold')]
PHJ18960101-V11-01-page16.txt: [("'order", 'order'), ("'The", 'The')]
PHJ18960101-V11-01-page17.txt: [("'cooperation", 'cooperation'), ("'The", 'The')]
PHJ18960101-V11-01-page26.txt: [("''Y", 'Y')]
PHJ18960101-V11-01-page28.txt: [("'O", 'O')]
PHJ18960101-V11-01-page5.txt: [("'The", 'The')]
PHJ18960201-V11-02-page10.txt: [("'neath", 'neath')]
PHJ18960201-V11-02-page11.txt: [("'comprehend", 'comprehend'), ("'The", 'The'), ("'fallen", 'fallen'), ("'fallen", 'fallen'), ("'fallen", 'fallen'), ("'the", 'the')]
PHJ18960201-V11-02-page12.txt: [("'vital", 'vital'), ("'magnificent", 'magnificent'), ("'nervous", 'nervous'), ("'reasoning", 'reasoning')]
PHJ18960201-V11-02-page18.txt: [("'neath", 'neath')]
PHJ18960201-V11-02-page2.txt: [("'rubber", 'rubber')]
PHJ18960201-V11-02-page21.txt: [("'Tis", 'Tis')]
PHJ18960201-V11-02-page22.txt: [("'he", 'he')]
PHJ18960201-V11-02-page26.txt: [("'twill", 'twill')]
PHJ18960201-V11-02-page28.txt: [("'em", 'em')]
PHJ18960201-V11-02-page29.txt: [("'favorably", 'favorably')]
PHJ18960201-V11-02-page31.txt: [("'to", 'to'), ("'Many", 'Many'), ("'York", 'York')]
PHJ18960201-V11-02-page5.txt: [("'kerchief", 'kerchief')]
PHJ18960201-V11-02-page6.txt: [("'they", 'they')]
PHJ18960301-V11-03-page11.txt: [("'twas", 'twas'), ("'Twas", 'Twas')]
PHJ18960301-V11-03-page13.txt: [("'Why", 'Why'), ('\'"', '"')]
PHJ18960301-V11-03-page14.txt: [("'a", 'a')]
PHJ18960301-V11-03-page2.txt: [("'permit", 'permit')]
PHJ18960301-V11-03-page24.txt: [("'em", 'em')]
PHJ18960301-V11-03-page25.txt: [("'long", 'long'), ("'em", 'em')]
PHJ18960301-V11-03-page29.txt: [("'has", 'has')]
PHJ18960301-V11-03-page30.txt: [("'use", 'use')]
PHJ18960301-V11-03-page31.txt: [("'Many", 'Many'), ("'not", 'not')]
PHJ18960401-V11-04-page10.txt: [("'tis", 'tis'), ("'Twill", 'Twill'), ("'tis", 'tis')]
PHJ18960401-V11-04-page12.txt: [("'LEAST", 'LEAST')]
PHJ18960401-V11-04-page14.txt: [("'Godfrey's", 'Godfreys')]
PHJ18960401-V11-04-page17.txt: [("'Bout", 'Bout'), ("'r", 'r'), ("'im", 'im'), ("'R", 'R'), ("'er", 'er'), ("'er", 'er'), ("'er", 'er'), ("'in", 'in'), ("'im", 'im')]
PHJ18960401-V11-04-page19.txt: [("''SLEEP", 'SLEEP')]
PHJ18960401-V11-04-page24.txt: [("'Look", 'Look')]
PHJ18960401-V11-04-page25.txt: [("'In", 'In'), ("'In", 'In'), ("'In", 'In')]
PHJ18960401-V11-04-page29.txt: [("'the", 'the')]
PHJ18960401-V11-04-page31.txt: [("'but", 'but'), ("'York", 'York'), ("'INSTRUMENT", 'INSTRUMENT')]
PHJ18960401-V11-04-page5.txt: [("'head", 'head')]
PHJ18960401-V11-04-page6.txt: [("'I", 'I')]
PHJ18960501-V11-05-page13.txt: [("'Rights", 'Rights'), ("'em", 'em'), ("'em.", 'em.'), ("'em", 'em')]
PHJ18960501-V11-05-page15.txt: [("'lust", 'lust'), ("'chapter", 'chapter')]
PHJ18960501-V11-05-page16.txt: [("'If", 'If'), ("'Not", 'Not'), ("'Love", 'Love'), ("'He", 'He'), ("'Whoso", 'Whoso'), ("'turned", 'turned'), ("'No", 'No'), ("'You", 'You'), ("'Mama", 'Mama'), ("'Mama", 'Mama'), ("'I've", 'Ive'), ("'love-force", 'love-force')]
PHJ18960501-V11-05-page17.txt: [("'what", 'what')]
PHJ18960501-V11-05-page20.txt: [("'to", 'to')]
PHJ18960501-V11-05-page23.txt: [("'.", '.')]
PHJ18960501-V11-05-page25.txt: [("'leaves", 'leaves')]
PHJ18960501-V11-05-page27.txt: [("'use", 'use')]
PHJ18960501-V11-05-page28.txt: [("'I", 'I'), ("'Well", 'Well'), ("'didn't", 'didnt'), ("'Yes", 'Yes'), ("'but", 'but'), ("'You", 'You'), ("'And", 'And')]
PHJ18960501-V11-05-page31.txt: [("'Z", 'Z'), ("'Operating", 'Operating')]
PHJ18960501-V11-05-page6.txt: [("'THE", 'THE')]
PHJ18960601-V11-06-page10.txt: [("'The", 'The')]
PHJ18960601-V11-06-page11.txt: [("'round", 'round')]
PHJ18960601-V11-06-page22.txt: [("'neath", 'neath')]
PHJ18960601-V11-06-page31.txt: [("'Many", 'Many')]
PHJ18960601-V11-06-page32.txt: [("'...", '...'), ("'d", 'd'), ("'.", '.'), ('\'"', '"')]
PHJ18960601-V11-06-page9.txt: [('\'sympathy"', 'sympathy"')]
PHJ18960701-V11-07-page12.txt: [("'brain", 'brain')]
PHJ18960701-V11-07-page16.txt: [("'Value", 'Value'), ("'a", 'a')]
PHJ18960701-V11-07-page20.txt: [("'an", 'an'), ("'cross", 'cross')]
PHJ18960701-V11-07-page22.txt: [("'stop", 'stop')]
PHJ18960701-V11-07-page31.txt: [("'Many", 'Many')]
PHJ18960701-V11-07-page32.txt: [("'ill", 'ill'), ('\'\'"..', '"..'), ('\'a."', 'a."')]
PHJ18960701-V11-07-page7.txt: [("'.", '.')]
PHJ18960801-V11-08-page13.txt: [("'The", 'The')]
PHJ18960801-V11-08-page19.txt: [("'dreamt", 'dreamt')]
PHJ18960801-V11-08-page22.txt: [("'.", '.')]
PHJ18960801-V11-08-page23.txt: [("'em", 'em'), ("'twas", 'twas'), ("'em.", 'em.'), ("'twas", 'twas'), ("'If", 'If')]
PHJ18960801-V11-08-page24.txt: [("'A.", 'A.')]
PHJ18960801-V11-08-page25.txt: [("'of", 'of')]
PHJ18960801-V11-08-page26.txt: [("'Sample", 'Sample')]
PHJ18960801-V11-08-page28.txt: [("'Tis", 'Tis'), ("'Twill", 'Twill')]
PHJ18960801-V11-08-page31.txt: [("'York", 'York')]
PHJ18960901-V11-09-page10.txt: [("'Twas", 'Twas')]
PHJ18960901-V11-09-page11.txt: [("'be", 'be')]
PHJ18960901-V11-09-page13.txt: [("'twould", 'twould'), ("'twould", 'twould')]
PHJ18960901-V11-09-page15.txt: [("'thought", 'thought')]
PHJ18960901-V11-09-page17.txt: [("'hard", 'hard')]
PHJ18960901-V11-09-page21.txt: [("'tis", 'tis')]
PHJ18960901-V11-09-page23.txt: [("'Come", 'Come'), ("'Be", 'Be'), ("'Sarah", 'Sarah'), ("'d", 'd'), ("'Hello", 'Hello'), ("'Come", 'Come'), ("'but", 'but'), ("'you'll", 'youll'), ("'Come", 'Come'), ("'let's", 'lets'), ("'never", 'never'), ("'Here", 'Here'), ("'I", 'I'), ("'Mama", 'Mama'), ("'Stop", 'Stop'), ("'All", 'All')]
PHJ18960901-V11-09-page24.txt: [("'.Johnny", '.Johnny')]
PHJ18960901-V11-09-page28.txt: [("'Tis", 'Tis')]
PHJ18960901-V11-09-page3.txt: [("'his", 'his')]
PHJ18960901-V11-09-page30.txt: [("'Many", 'Many'), ("'but", 'but'), ("'not", 'not'), ("'York", 'York')]
PHJ18960901-V11-09-page7.txt: [("'husband's", 'husbands')]
PHJ18960901-V11-09-page9.txt: [("'to", 'to')]
PHJ18961001-V11-10-page10.txt: [("'Tobacco", 'Tobacco')]
PHJ18961001-V11-10-page13.txt: [("'The", 'The')]
PHJ18961001-V11-10-page14.txt: [("'condition", 'condition')]
PHJ18961001-V11-10-page24.txt: [("'kerchief", 'kerchief')]
PHJ18961001-V11-10-page26.txt: [("'em", 'em')]
PHJ18961001-V11-10-page5.txt: [("'done", 'done')]
PHJ18961001-V11-10-page9.txt: [("'Tell", 'Tell'), ("'general", 'general'), ("'Who", 'Who'), ("'It", 'It'), ("'If", 'If'), ("'the", 'the')]
PHJ18961101-V11-11-page1.txt: [("'Nothing", 'Nothing')]
PHJ18961101-V11-11-page10.txt: [("'Non-Alcoholics", 'Non-Alcoholics')]
PHJ18961101-V11-11-page18.txt: [("'not", 'not'), ("'pretty", 'pretty'), ("'Ground", 'Ground'), ("'then", 'then'), ("'hundreds", 'hundreds'), ("'And", 'And')]
PHJ18961101-V11-11-page19.txt: [("'presently", 'presently')]
PHJ18961101-V11-11-page2.txt: [("'make", 'make')]
PHJ18961101-V11-11-page23.txt: [("'the", 'the')]
PHJ18961101-V11-11-page24.txt: [("'nervous", 'nervous'), ("'tis", 'tis')]
PHJ18961101-V11-11-page25.txt: [("'fectionate", 'fectionate')]
PHJ18961101-V11-11-page26.txt: [("'might", 'might')]
PHJ18961101-V11-11-page27.txt: [("'a", 'a')]
PHJ18961101-V11-11-page28.txt: [("'the", 'the')]
PHJ18961101-V11-11-page32.txt: [("'I", 'I'), ("'Ili", 'Ili'), ("'..", '..'), ("'ifiill", 'ifiill'), ('\'"ZingSliimiediullIVIgi', '"ZingSliimiediullIVIgi')]
PHJ18961101-V11-11-page7.txt: [("'Functional", 'Functional')]
PHJ18961101-V11-11-page8.txt: [("'the", 'the'), ("'There", 'There'), ("'The", 'The')]
PHJ18961101-V11-11-page9.txt: [("'It", 'It')]
PHJ18961201-V11-12-page10.txt: [("'Tis", 'Tis')]
PHJ18961201-V11-12-page15.txt: [("'face", 'face'), ("'something", 'something'), ("'endeavor", 'endeavor')]
PHJ18961201-V11-12-page17.txt: [("'can", 'can')]
PHJ18961201-V11-12-page22.txt: [("'And", 'And')]
PHJ18961201-V11-12-page23.txt: [("'The", 'The'), ("'Self-seeking", 'Self-seeking')]
PHJ18961201-V11-12-page24.txt: [("'OURNAL.", 'OURNAL.')]
PHJ18961201-V11-12-page25.txt: [("'Mr.", 'Mr.'), ("'these", 'these'), ("'but", 'but'), ("'but", 'but')]
PHJ18961201-V11-12-page30.txt: [("'pass", 'pass')]
PHJ18961201-V11-12-page33.txt: [("'levers", 'levers'), ("'s", 's')]
PHJ18961201-V11-12-page5.txt: [("'The", 'The')]
PHJ18990101-V14-01-page12.txt: [("'Tis", 'Tis'), ("'Tis", 'Tis')]
PHJ18990201-V14-02-page10.txt: [("'skulls", 'skulls')]
PHJ18990201-V14-02-page13.txt: [("'em", 'em')]
PHJ18990201-V14-02-page15.txt: [("'end", 'end'), ("'count", 'count')]
PHJ18990201-V14-02-page7.txt: [("'the", 'the')]
PHJ18990301-V14-03-page11.txt: [("'number", 'number')]
PHJ18990301-V14-03-page8.txt: [("'seems", 'seems')]
PHJ18990401-V14-04-page16.txt: [("'should", 'should'), ("'I", 'I'), ("'Give", 'Give'), ('\'"Getout', '"Getout'), ("'You", 'You')]
PHJ18990401-V14-04-page19.txt: [("'the", 'the'), ("'count", 'count')]
PHJ18990501-V14-05-page10.txt: [("'Yes", 'Yes'), ("'you", 'you')]
PHJ18990501-V14-05-page13.txt: [("'if", 'if')]
PHJ18990501-V14-05-page14.txt: [("'no", 'no')]
PHJ18990501-V14-05-page9.txt: [("'something", 'something')]
PHJ18990601-V14-06-page11.txt: [("'stomach", 'stomach')]
PHJ18990601-V14-06-page14.txt: [("'cause", 'cause')]
PHJ18990601-V14-06-page16.txt: [("'Oh", 'Oh'), ("'You", 'You')]
PHJ18990701-V14-07-page7.txt: [("'Twas", 'Twas')]
PHJ18990801-V14-08-page12.txt: [("'used", 'used')]
PHJ18990901-V14-09-page19.txt: [("'plain", 'plain')]
PHJ18990901-V14-09-page9.txt: [("'These", 'These')]
PHJ18991001-V14-10-page11.txt: [("'between", 'between')]
PHJ18991001-V14-10-page3.txt: [("'GILW", 'GILW')]
PHJ18991001-V14-10-page4.txt: [("'but", 'but')]
PHJ18991101-V14-11-page9.txt: [("'Tis", 'Tis'), ("'Tis", 'Tis')]
PHJ19010201-V16-02-page25.txt: [("'can", 'can')]
PHJ19010201-V16-02-page26.txt: [("'his", 'his')]
PHJ19010201-V16-02-page27.txt: [("'at", 'at')]
PHJ19010201-V16-02-page32.txt: [("'Mr", 'Mr'), ("'glittering", 'glittering')]
PHJ19010201-V16-02-page4.txt: [("'i", 'i')]
PHJ19010301-V16-03-page23.txt: [("'are", 'are')]
PHJ19010301-V16-03-page28.txt: [("'his", 'his')]
PHJ19010301-V16-03-page32.txt: [("'sir", 'sir'), ("'r", 'r'), ("'sir", 'sir'), ("'glittering", 'glittering')]
PHJ19010301-V16-03-page33.txt: [("'III", 'III'), ("'VE", 'VE')]
PHJ19010301-V16-03-page34.txt: [("'sty", 'sty')]
PHJ19010401-V16-04-page20.txt: [("'made", 'made')]
PHJ19010401-V16-04-page21.txt: [("'Mr", 'Mr')]
PHJ19010401-V16-04-page31.txt: [("'in", 'in')]
PHJ19010401-V16-04-page33.txt: [("'I", 'I')]
PHJ19010401-V16-04-page35.txt: [("'Or", 'Or')]
PHJ19010501-V16-05-page19.txt: [("'PK", 'PK'), ("'SFr", 'SFr'), ("'AK", 'AK')]
PHJ19010501-V16-05-page33.txt: [("'atteivi", 'atteivi'), ("'San", 'San')]
PHJ19010501-V16-05-page35.txt: [("'t", 't')]
PHJ19010501-V16-05-page36.txt: [("'ElLER", 'ElLER')]
PHJ19010501-V16-05-page37.txt: [("'I", 'I'), ("'I", 'I')]
PHJ19010601-V16-06-page33.txt: [("'should", 'should')]
PHJ19010601-V16-06-page46.txt: [("'.S", '.S'), ("'N", 'N')]
PHJ19010601-V16-06-page49.txt: [("'.", '.'), ("'I", 'I'), ("'r", 'r')]
PHJ19010601-V16-06-page52.txt: [("'str", 'str')]
PHJ19010701-V16-07-page1.txt: [("'DEPARTMENT", 'DEPARTMENT'), ("'l", 'l')]
PHJ19010701-V16-07-page14.txt: [("'Tis", 'Tis')]
PHJ19010701-V16-07-page27.txt: [("'stte", 'stte')]
PHJ19010701-V16-07-page29.txt: [("'rep", 'rep')]
PHJ19010701-V16-07-page32.txt: [("'.", '.')]
PHJ19010701-V16-07-page35.txt: [("'lir", 'lir')]
PHJ19010701-V16-07-page9.txt: [("'dead", 'dead')]
PHJ19010801-V16-08-page20.txt: [("'cause", 'cause')]
PHJ19010801-V16-08-page29.txt: [("'be", 'be')]
PHJ19010801-V16-08-page32.txt: [("'.", '.')]
PHJ19010801-V16-08-page36.txt: [("'St.", 'St.')]
PHJ19010801-V16-08-page4.txt: [("'P.", 'P.')]
PHJ19010901-V16-09-page19.txt: [("'Tis", 'Tis')]
PHJ19010901-V16-09-page3.txt: [("'prevents", 'prevents')]
PHJ19011001-V16-10-page13.txt: [("'to", 'to')]
PHJ19011001-V16-10-page18.txt: [("'He", 'He')]
PHJ19011001-V16-10-page29.txt: [("'sir", 'sir')]
PHJ19011001-V16-10-page30.txt: [("'V", 'V')]
PHJ19011001-V16-10-page34.txt: [("'.", '.')]
PHJ19011001-V16-10-page5.txt: [("''the", 'the')]
PHJ19011001-V16-10-page8.txt: [("'daily", 'daily')]
PHJ19011101-V16-11-page30.txt: [('\'LIT"', 'LIT"'), ("'answered", 'answered')]
PHJ19011101-V16-11-page33.txt: [("'Street", 'Street')]
PHJ19011101-V16-11-page34.txt: [("'sir", 'sir')]
PHJ19011101-V16-11-page9.txt: [("'a", 'a')]
PHJ19011201-V16-12-page16.txt: [("'The", 'The')]
PHJ19011201-V16-12-page19.txt: [("'can", 'can')]
PHJ19011201-V16-12-page2.txt: [("'C.", 'C.')]
PHJ19011201-V16-12-page4.txt: [('\'..\'"\'.."', '..".."'), ("'.", '.')]
PHJ19020101-V17-01-page18.txt: [("'O", 'O')]
PHJ19020101-V17-01-page34.txt: [("'PORT", 'PORT')]
PHJ19020101-V17-01-page35.txt: [("'irraurif", 'irraurif')]
PHJ19020101-V17-01-page36.txt: [("'I", 'I'), ("'TiTTVT", 'TiTTVT')]
PHJ19020101-V17-01-page38.txt: [("'stir", 'stir')]
PHJ19020201-V17-02-page19.txt: [("'railroad", 'railroad')]
PHJ19020201-V17-02-page20.txt: [("'no", 'no')]
PHJ19020201-V17-02-page30.txt: [("'.", '.'), ("'TT", 'TT')]
PHJ19020201-V17-02-page31.txt: [('\'\'"', '"')]
PHJ19020201-V17-02-page33.txt: [("'.", '.')]
PHJ19020301-V17-03-page37.txt: [("'.", '.')]
PHJ19020401-V17-04-page22.txt: [("'mong", 'mong'), ("'tis", 'tis')]
PHJ19020401-V17-04-page23.txt: [("'mind", 'mind'), ("'result", 'result')]
PHJ19020401-V17-04-page24.txt: [("'Go", 'Go'), ("'Aurora", 'Aurora'), ("'Consuelo", 'Consuelo')]
PHJ19020401-V17-04-page29.txt: [("'''ket", 'ket')]
PHJ19020501-V17-05-page11.txt: [("'with", 'with')]
PHJ19020501-V17-05-page20.txt: [("'in", 'in')]
PHJ19020501-V17-05-page25.txt: [("'a", 'a')]
PHJ19020501-V17-05-page26.txt: [("'infections", 'infections')]
PHJ19020501-V17-05-page7.txt: [("'O", 'O')]
PHJ19020601-V17-06-page22.txt: [("'Oh", 'Oh')]
PHJ19020601-V17-06-page28.txt: [("'or", 'or')]
PHJ19020701-V17-07-page11.txt: [("'the", 'the')]
PHJ19020701-V17-07-page8.txt: [("'the", 'the')]
PHJ19020801-V17-08-page30.txt: [("'fri", 'fri')]
PHJ19020901-V17-09-page18.txt: [("'Les", 'Les')]
PHJ19021001-V17-10-page16.txt: [('\'em."', 'em."')]
PHJ19021001-V17-10-page24.txt: [("'risky", 'risky'), ("'matter", 'matter')]
PHJ19021001-V17-10-page26.txt: [("'should", 'should')]
PHJ19021001-V17-10-page29.txt: [("'Regularly", 'Regularly')]
PHJ19021001-V17-10-page32.txt: [("'Iarlagers", 'Iarlagers')]
PHJ19021001-V17-10-page33.txt: [("'laths", 'laths')]
PHJ19021001-V17-10-page36.txt: [("'By", 'By')]
PHJ19021101-V17-11-page18.txt: [("'Tis", 'Tis')]
PHJ19021101-V17-11-page20.txt: [('\'em."', 'em."')]
PHJ19021101-V17-11-page22.txt: [("'The", 'The'), ("'Some", 'Some')]
PHJ19021101-V17-11-page29.txt: [("'rig", 'rig')]
PHJ19021101-V17-11-page6.txt: [("'ease", 'ease')]
PHJ19021201-V17-12-page13.txt: [("'time", 'time')]
PHJ19021201-V17-12-page22.txt: [("'health", 'health')]
PHJ19021201-V17-12-page30.txt: [("'Regularly", 'Regularly')]
PHJ19021201-V17-12-page4.txt: [("'D", 'D')]
PHJ19021201-V17-12-page6.txt: [("'We", 'We')]
PHJ19030101-V18-01-page21.txt: [("'bout", 'bout')]
PHJ19030101-V18-01-page31.txt: [("'rig", 'rig')]
PHJ19030101-V18-01-page32.txt: [('\'"', '"'), ("'PORTER", 'PORTER')]
PHJ19030101-V18-01-page36.txt: [("'true", 'true')]
PHJ19030201-V18-02-page2.txt: [("'true", 'true')]
PHJ19030201-V18-02-page21.txt: [("'Tts", 'Tts')]
PHJ19030201-V18-02-page22.txt: [("'of", 'of')]
PHJ19030201-V18-02-page23.txt: [("'curve", 'curve')]
PHJ19030201-V18-02-page35.txt: [("'cf", 'cf')]
PHJ19030201-V18-02-page6.txt: [("'sufficient", 'sufficient')]
PHJ19030201-V18-02-page8.txt: [("'and", 'and')]
PHJ19030301-V18-03-page23.txt: [("'sfr", 'sfr')]
PHJ19030301-V18-03-page24.txt: [("'Nor", 'Nor')]
PHJ19030301-V18-03-page33.txt: [("'D.", 'D.')]
PHJ19030301-V18-03-page4.txt: [("'Ivo", 'Ivo')]
PHJ19030401-V18-04-page17.txt: [("'SW", 'SW')]
PHJ19030401-V18-04-page21.txt: [("'PK", 'PK')]
PHJ19030401-V18-04-page30.txt: [("'Uncle", 'Uncle')]
PHJ19030401-V18-04-page36.txt: [("'NIL", 'NIL')]
PHJ19030501-V18-05-page10.txt: [("'sfir", 'sfir')]
PHJ19030501-V18-05-page12.txt: [("'give", 'give')]
PHJ19030501-V18-05-page14.txt: [("'except", 'except'), ("'sleep", 'sleep')]
PHJ19030501-V18-05-page17.txt: [("'stir", 'stir')]
PHJ19030501-V18-05-page30.txt: [("'..", '..'), ("''S", 'S'), ("'o", 'o'), ("''Uncle", 'Uncle'), ("'rf", 'rf')]
PHJ19030501-V18-05-page4.txt: [("'PliOCE", 'PliOCE')]
PHJ19030501-V18-05-page7.txt: [("'and", 'and')]
PHJ19030601-V18-06-page11.txt: [("'I'bis", 'Ibis')]
PHJ19030601-V18-06-page12.txt: [("'The", 'The')]
PHJ19030601-V18-06-page2.txt: [("'Physical", 'Physical')]
PHJ19030601-V18-06-page27.txt: [("'PK", 'PK')]
PHJ19030601-V18-06-page30.txt: [("'r", 'r')]
PHJ19030701-V18-07-page2.txt: [("'AO", 'AO')]
PHJ19030701-V18-07-page31.txt: [('\'\'immoral."', 'immoral."')]
PHJ19030701-V18-07-page35.txt: [("'IA", 'IA'), ("'AV", 'AV'), ("'tci", 'tci')]
PHJ19030701-V18-07-page36.txt: [("'.", '.'), ("'ILIMPItAtL", 'ILIMPItAtL')]
PHJ19030801-V18-08-page18.txt: [("'twas", 'twas')]
PHJ19030901-V18-09-page1.txt: [("'Next", 'Next')]
PHJ19030901-V18-09-page16.txt: [("'tis", 'tis')]
PHJ19030901-V18-09-page24.txt: [("'Par", 'Par')]
PHJ19030901-V18-09-page34.txt: [("'Coolest", 'Coolest')]
PHJ19030901-V18-09-page35.txt: [("'r", 'r')]
PHJ19030901-V18-09-page8.txt: [("'word", 'word')]
PHJ19031001-V18-10-page25.txt: [("'tis", 'tis')]
PHJ19031001-V18-10-page30.txt: [("'em", 'em'), ("'em", 'em'), ("'No", 'No')]
PHJ19031001-V18-10-page7.txt: [("'lusted", 'lusted')]
PHJ19031101-V18-11-page13.txt: [("'Mr", 'Mr')]
PHJ19031101-V18-11-page15.txt: [("'sir", 'sir'), ("'PK", 'PK')]
PHJ19031101-V18-11-page21.txt: [("'phone.", 'phone.')]
PHJ19031101-V18-11-page27.txt: [("'SW", 'SW')]
PHJ19031101-V18-11-page3.txt: [("'.", '.'), ("'j", 'j'), ("'..", '..'), ("'..", '..')]
PHJ19031101-V18-11-page32.txt: [("''The", 'The')]
PHJ19031101-V18-11-page6.txt: [("'H", 'H')]
PHJ19031201-V18-12-page28.txt: [("'SW", 'SW')]
PHJ19031201-V18-12-page3.txt: [("'.", '.'), ("'..", '..'), ("'.Ji.", '.Ji.')]
PHJ19031201-V18-12-page35.txt: [("'A", 'A'), ("'A", 'A')]
PHJ19031201-V18-12-page4.txt: [("'Dubbing", 'Dubbing'), ("'Puts", 'Puts')]
PHJ19040101-V19-01-page25.txt: [("'mong", 'mong'), ("'Tis", 'Tis')]
PHJ19040101-V19-01-page28.txt: [("'neath", 'neath')]
PHJ19040101-V19-01-page3.txt: [("'will", 'will')]
PHJ19040201-V19-02-page12.txt: [("'who", 'who')]
PHJ19040201-V19-02-page13.txt: [("'for", 'for')]
PHJ19040201-V19-02-page16.txt: [("'Tis", 'Tis')]
PHJ19040201-V19-02-page17.txt: [("'till", 'till')]
PHJ19040201-V19-02-page2.txt: [("'creative", 'creative')]
PHJ19040201-V19-02-page27.txt: [("'t", 't')]
PHJ19040201-V19-02-page29.txt: [("'Bible.", 'Bible.')]
PHJ19040201-V19-02-page35.txt: [("'crol", 'crol')]
PHJ19040301-V19-03-page15.txt: [("'Twas", 'Twas')]
PHJ19040301-V19-03-page19.txt: [("'found", 'found')]
PHJ19040301-V19-03-page2.txt: [("'creative", 'creative')]
PHJ19040301-V19-03-page24.txt: [("'ranks", 'ranks')]
PHJ19040301-V19-03-page27.txt: [("'if", 'if'), ("'A", 'A')]
PHJ19040301-V19-03-page34.txt: [("'clounk", 'clounk')]
PHJ19040301-V19-03-page9.txt: [("'not", 'not')]
PHJ19040401-V19-04-page12.txt: [("'a", 'a')]
PHJ19040401-V19-04-page23.txt: [("'ow", 'ow'), ("'urt", 'urt')]
PHJ19040401-V19-04-page24.txt: [("'ere's", 'eres'), ("'and", 'and')]
PHJ19040401-V19-04-page26.txt: [("'lowed", 'lowed')]
PHJ19040401-V19-04-page28.txt: [("'MC", 'MC')]
PHJ19040401-V19-04-page3.txt: [("'of", 'of')]
PHJ19040401-V19-04-page34.txt: [("'ClktNi", 'ClktNi')]
PHJ19040401-V19-04-page35.txt: [("'r", 'r')]
PHJ19040401-V19-04-page5.txt: [("'bad", 'bad')]
PHJ19040501-V19-05-page2.txt: [("'L", 'L')]
PHJ19040501-V19-05-page6.txt: [("'PK", 'PK')]
In [23]:
# %load shared_elements/summary.py
summary = GoH.reports.overview_report(directories['cycle'], spelling_dictionary, title)
Directory: /Users/jeriwieringa/Dissertation/text/text/2017-01-31-corpus-with-utf8-split-into-titles-cleaning/PHJ/correction4 Average verified rate: 0.9808491067757629 Average of error rates: 0.02707709397911575 Total token count: 2850572
In [24]:
# %load shared_elements/top_errors.py
errors_summary = GoH.reports.get_errors_summary( summary )
GoH.reports.top_errors( errors_summary, 10 )[:50]
Out[24]:
[('m', 2736),
('d', 2336),
("'", 1997),
('e', 1399),
('r', 1279),
('t', 1213),
('w', 1176),
('n', 1124),
('co', 1118),
('f', 796),
('g', 766),
('x', 649),
('lb', 588),
('th', 260),
('sel', 251),
('oo', 237),
('mo', 233),
('pp', 228),
('z', 217),
('k', 216),
('u', 199),
("an'", 192),
('q', 133),
('ex', 111),
('al', 109),
('ournal', 106),
('pa', 88),
('te', 86),
('ro', 86),
('oz', 81),
('ga', 81),
('va', 74),
('munn', 73),
('ti', 73),
('io', 72),
('-', 66),
('tion', 63),
("infants'", 61),
('id', 59),
('re', 58),
('zo', 55),
('em', 55),
('viperance', 54),
("''", 49),
('si', 48),
('urnal', 48),
('yo', 48),
('fahr', 46),
('cc', 45),
("hours'", 44)]
Correction 5 -- Rejoin Burst Words¶
In [25]:
# %load shared_elements/rejoin_burst_words.py
prev = cycle
cycle = "correction5"
directories = GoH.utilities.define_directories(prev, cycle, base_dir)
if not os.path.exists(directories['cycle']):
os.makedirs(directories['cycle'])
corpus = (f for f in listdir(directories['prev']) if not f.startswith('.') and isfile(join(directories['prev'], f)))
for filename in corpus:
content = GoH.utilities.readfile(directories['prev'], filename)
pattern = re.compile("(\s(\w{1,2}\s){5,})")
replacements = []
GoH.clean.check_splits(pattern, spelling_dictionary, content, replacements)
if len(replacements) > 0:
print('{}: {}'.format(filename, replacements))
for replacement in replacements:
content = GoH.clean.replace_pair(replacement, content)
else:
pass
with open(join(directories['cycle'], filename), mode="w") as o:
o.write(content)
o.close()
PHJ18850601-V01-01-page2.txt: [('It', 'It')]
PHJ18861001-V02-03-page1.txt: [('So', 'So')]
PHJ18870401-V02-06-page1.txt: [('Iv', 'Iv')]
PHJ18870601-V02-07-page13.txt: [('At', 'At')]
PHJ18890401-V04-04-page28.txt: [('Of', 'Of')]
PHJ18890501-V04-05-page14.txt: [(' w o nd e r ', 'wonder')]
PHJ18890501-V04-05-page29.txt: [('If', 'If'), ('Of', 'Of')]
PHJ18891001-V04-10-page29.txt: [('It', 'It')]
PHJ18891201-V04-12-page34.txt: [('To', 'To')]
PHJ18900301-V05-03-page30.txt: [('So', 'So')]
PHJ18900501-V05-05-page31.txt: [('In', 'In')]
PHJ18900801-V05-08-page29.txt: [('So', 'So')]
PHJ18901001-V05-10-page31.txt: [('St', 'St')]
PHJ18901201-V05-12-page28.txt: [('It', 'It')]
PHJ18901201-V05-12-page29.txt: [('Go', 'Go')]
PHJ18910101-V06-01-page28.txt: [('Do', 'Do')]
PHJ18920401-V07-04-page30.txt: [('No', 'No')]
PHJ18920501-V07-05-page28.txt: [('Is', 'Is')]
PHJ19020201-V17-02-page2.txt: [('It', 'It')]
PHJ19020301-V17-03-page24.txt: [('He', 'He')]
PHJ19020601-V17-06-page35.txt: [('Is', 'Is')]
PHJ19020801-V17-08-page31.txt: [('Be', 'Be'), ('Do', 'Do')]
PHJ19020801-V17-08-page7.txt: [('If', 'If')]
PHJ19030101-V18-01-page35.txt: [('El', 'El')]
PHJ19030401-V18-04-page2.txt: [('Vs', 'Vs'), ('Vs', 'Vs')]
PHJ19031201-V18-12-page35.txt: [('Ai', 'Ai')]
PHJ19040301-V19-03-page29.txt: [('If', 'If')]
In [26]:
# %load shared_elements/summary.py
summary = GoH.reports.overview_report(directories['cycle'], spelling_dictionary, title)
Directory: /Users/jeriwieringa/Dissertation/text/text/2017-01-31-corpus-with-utf8-split-into-titles-cleaning/PHJ/correction5 Average verified rate: 0.9808463809521136 Average of error rates: 0.027078649189069097 Total token count: 2850584
In [27]:
# %load shared_elements/top_errors.py
errors_summary = GoH.reports.get_errors_summary( summary )
GoH.reports.top_errors( errors_summary, 10 )[:50]
Out[27]:
[('m', 2736),
('d', 2336),
("'", 1997),
('e', 1398),
('r', 1278),
('t', 1213),
('w', 1175),
('n', 1124),
('co', 1118),
('f', 796),
('g', 766),
('x', 649),
('lb', 588),
('th', 260),
('sel', 251),
('oo', 237),
('mo', 233),
('pp', 228),
('z', 217),
('k', 216),
('u', 199),
("an'", 192),
('q', 133),
('ex', 111),
('al', 109),
('ournal', 106),
('pa', 88),
('te', 86),
('ro', 86),
('oz', 81),
('ga', 81),
('va', 74),
('munn', 73),
('ti', 73),
('io', 72),
('-', 66),
('tion', 63),
("infants'", 61),
('id', 59),
('re', 58),
('zo', 55),
('em', 55),
('viperance', 54),
("''", 49),
('si', 48),
('urnal', 48),
('yo', 48),
('fahr', 46),
('cc', 45),
("hours'", 44)]
Correction 6 -- Rejoin Split Words¶
In [28]:
# %load shared_elements/rejoin_split_words.py
prev = cycle
cycle = "correction6"
directories = GoH.utilities.define_directories(prev, cycle, base_dir)
if not os.path.exists(directories['cycle']):
os.makedirs(directories['cycle'])
corpus = (f for f in listdir(directories['prev']) if not f.startswith('.') and isfile(join(directories['prev'], f)))
for filename in corpus:
content = GoH.utilities.readfile(directories['prev'], filename)
text = re.sub(r"[0-9,!?$:;&]", " ", content)
tokens = GoH.utilities.tokenize_text(text)
errors = GoH.reports.identify_errors(tokens, spelling_dictionary)
replacements = GoH.clean.check_if_stem(errors, spelling_dictionary, tokens, get_prior=False)
if len(replacements) > 0:
print('{}: {}'.format(filename, replacements))
for replacement in replacements:
content = GoH.clean.replace_split_words(replacement, content)
else:
pass
with open(join(directories['cycle'], filename), mode="w") as o:
o.write(content)
o.close()
PHJ18850601-V01-01-page23.txt: [('re', 's')]
PHJ18850601-V01-01-page3.txt: [('th', 'ese'), ('co', 'exist')]
PHJ18850801-V01-02-page22.txt: [('pp', 'r')]
PHJ18850801-V01-02-page23.txt: [('ri', 'le')]
PHJ18851001-V01-03-page22.txt: [('PP', 'r')]
PHJ18851201-V01-04-page16.txt: [('devel', 'oped')]
PHJ18851201-V01-04-page18.txt: [('wiv', 'e')]
PHJ18851201-V01-04-page5.txt: [('FO', 'UL')]
PHJ18851201-V01-04-page6.txt: [('accommo', 'dating')]
PHJ18851201-V01-04-page8.txt: [('phy', 'sician')]
PHJ18860201-V01-05-page23.txt: [('PRESERVA', 'TION')]
PHJ18860201-V01-05-page3.txt: [('dif', 'ficult')]
PHJ18860401-V01-06-page22.txt: [('PREVEN', 'TION')]
PHJ18860601-V02-01-page19.txt: [('striv', 'ing')]
PHJ18860601-V02-01-page21.txt: [('shoul', 'ders'), ('ri', 'ce')]
PHJ18860601-V02-01-page22.txt: [('TEMPERANC', 'E')]
PHJ18860601-V02-01-page3.txt: [('alime', 'ntation')]
PHJ18860801-V02-02-page1.txt: [('ti', 'e')]
PHJ18860801-V02-02-page24.txt: [('fo', 'r')]
PHJ18860801-V02-02-page26.txt: [('BI', 'MONTHLY')]
PHJ18860801-V02-02-page31.txt: [('STOM', 'ACHS')]
PHJ18860801-V02-02-page4.txt: [('ea', 't')]
PHJ18860801-V02-02-page8.txt: [('condi', 'ments')]
PHJ18861001-V02-03-page11.txt: [('mechan', 'ism')]
PHJ18861001-V02-03-page13.txt: [('Plym', 'outh')]
PHJ18861001-V02-03-page2.txt: [('Genito', 'Urinary')]
PHJ18861001-V02-03-page20.txt: [('AMENORRH', 'EA')]
PHJ18861001-V02-03-page21.txt: [('recog', 'nized'), ('ac', 'companies')]
PHJ18861001-V02-03-page24.txt: [('ti', 'ti')]
PHJ18861001-V02-03-page26.txt: [('bi', 'monthly')]
PHJ18861001-V02-03-page27.txt: [('Bi', 'Monthly')]
PHJ18861001-V02-03-page30.txt: [('PRESERVA', 'TION')]
PHJ18861001-V02-03-page7.txt: [('supernum', 'erary')]
PHJ18861001-V02-03-page8.txt: [('th', 'e'), ('kno', 'wledge')]
PHJ18861201-V02-04-page1.txt: [('Dau', 'ghters'), ('ti', 'e')]
PHJ18861201-V02-04-page17.txt: [('CU', 'RE')]
PHJ18861201-V02-04-page24.txt: [('co', 'o')]
PHJ18861201-V02-04-page27.txt: [('PRESERVA', 'TION')]
PHJ18861201-V02-04-page28.txt: [('Yo', 'Semite'), ('HUTC', 'HINGS')]
PHJ18861201-V02-04-page29.txt: [('Yo', 'Semite')]
PHJ18861201-V02-04-page3.txt: [('BI', 'MONTHLY')]
PHJ18861201-V02-04-page32.txt: [('M.', '')]
PHJ18870201-V02-05-page1.txt: [('ti', 'e')]
PHJ18870201-V02-05-page16.txt: [('frustrat', 'ing')]
PHJ18870201-V02-05-page19.txt: [('ro', 'per')]
PHJ18870201-V02-05-page2.txt: [('Genito', 'Urinary')]
PHJ18870201-V02-05-page21.txt: [('diffi', 'culty')]
PHJ18870201-V02-05-page30.txt: [('Yo', 'Semite')]
PHJ18870201-V02-05-page32.txt: [('TE', 'E'), ('li', 't')]
PHJ18870201-V02-05-page6.txt: [('nar', 'cotics')]
PHJ18870201-V02-05-page8.txt: [('ne', 'ighbors')]
PHJ18870401-V02-06-page1.txt: [('al', 'e'), ('Mal', 'aria')]
PHJ18870401-V02-06-page13.txt: [('neces', 'saries')]
PHJ18870401-V02-06-page26.txt: [('Societ', 'y'), ('PRE', 'S'), ('Norwa', 'y')]
PHJ18870401-V02-06-page29.txt: [('soci', 'ety'), ('Bi', 'Monthly')]
PHJ18870401-V02-06-page30.txt: [('Yo', 'Semite')]
PHJ18870401-V02-06-page32.txt: [('li', 'V')]
PHJ18870601-V02-07-page15.txt: [('Declar', 'ing')]
PHJ18870601-V02-07-page2.txt: [('Genito', 'Urinary')]
PHJ18870601-V02-07-page20.txt: [('Mc', 'Dowell')]
PHJ18870601-V02-07-page25.txt: [('WA', 'FERS')]
PHJ18870601-V02-07-page27.txt: [('Societ', 'y'), ('Ow', 'n')]
PHJ18870601-V02-07-page31.txt: [('Yo', 'Semite')]
PHJ18870801-V02-08-page1.txt: [('ti', 'e')]
PHJ18870801-V02-08-page2.txt: [('Genito', 'Urinary')]
PHJ18870801-V02-08-page21.txt: [('diseas', 'e')]
PHJ18870801-V02-08-page25.txt: [('WHEA', 'TENA')]
PHJ18870801-V02-08-page31.txt: [('Yo', 'Semite')]
PHJ18871001-V02-09-page1.txt: [('po', 'etry')]
PHJ18871001-V02-09-page14.txt: [('fathe', 'r')]
PHJ18871001-V02-09-page18.txt: [('devel', 'oped')]
PHJ18871001-V02-09-page2.txt: [('Genito', 'Urinary')]
PHJ18871001-V02-09-page23.txt: [('HEA', 'T')]
PHJ18871001-V02-09-page24.txt: [('ID', 'S'), ('Thermo', 'Electric')]
PHJ18871001-V02-09-page25.txt: [('WHEA', 'TENA'), ('WA', 'FERS')]
PHJ18871001-V02-09-page26.txt: [('Yo', 'Semite')]
PHJ18871001-V02-09-page27.txt: [('SC', 'R'), ('Yo', 'Semite')]
PHJ18871001-V02-09-page32.txt: [('AL', 'G')]
PHJ18871001-V02-09-page8.txt: [('gener', 'ation')]
PHJ18880101-V03-01-page21.txt: [('holi', 'days')]
PHJ18880101-V03-01-page22.txt: [('dic', 'tionary')]
PHJ18880101-V03-01-page27.txt: [('Yo', 'Semite')]
PHJ18880101-V03-01-page5.txt: [('mur', 'murings')]
PHJ18880101-V03-01-page7.txt: [('olfac', 'tory')]
PHJ18880201-V03-02-page14.txt: [('re', 'instate')]
PHJ18880201-V03-02-page26.txt: [('DELT', 'A')]
PHJ18880201-V03-02-page27.txt: [('Yo', 'Semite')]
PHJ18880201-V03-02-page28.txt: [('CA', 'N')]
PHJ18880201-V03-02-page5.txt: [('Defi', 'ciency')]
PHJ18880201-V03-02-page7.txt: [('Deo', 'N')]
PHJ18880201-V03-02-page8.txt: [('respon', 'sible')]
PHJ18880301-V03-03-page24.txt: [('TEM', 'PERANCE')]
PHJ18880301-V03-03-page25.txt: [('gi', 'A')]
PHJ18880301-V03-03-page27.txt: [('econom', 'ical'), ('LAUN', 'DRY')]
PHJ18880401-V03-04-page19.txt: [('communicat', 'ing')]
PHJ18880401-V03-04-page27.txt: [('ro', 'c'), ('econom', 'ical'), ('LAUN', 'DRY'), ('Thermo', 'Electric'), ('SA', 'FETY')]
PHJ18880401-V03-04-page31.txt: [('BI', 'S')]
PHJ18880401-V03-04-page32.txt: [('Yo', 'Semite')]
PHJ18880501-V03-05-page2.txt: [('beco', 'me')]
PHJ18880501-V03-05-page23.txt: [('vid', 'a')]
PHJ18880501-V03-05-page25.txt: [('econom', 'ical'), ('LAUN', 'DRY'), ('Fr', 'is')]
PHJ18880501-V03-05-page26.txt: [('HY', 'GIENE'), ('CA', 'N')]
PHJ18880501-V03-05-page27.txt: [('APPLI', 'ANCES'), ('SI', 'g')]
PHJ18880501-V03-05-page28.txt: [('Thermo', 'Electric')]
PHJ18880601-V03-06-page12.txt: [('PEO', 'PLE')]
PHJ18880601-V03-06-page15.txt: [('endur', 'ance')]
PHJ18880601-V03-06-page19.txt: [('INSTITU', 'TION')]
PHJ18880601-V03-06-page25.txt: [('LAUN', 'DRY'), ('co', 'per'), ('PA', 'CIFIC')]
PHJ18880601-V03-06-page27.txt: [('APPLI', 'ANCES')]
PHJ18880601-V03-06-page3.txt: [('ap', 'petite')]
PHJ18880601-V03-06-page31.txt: [('pag', 'es')]
PHJ18880701-V03-07-page1.txt: [('prerequi', 'site'), ('Si', 'P'), ('cerebro', 'spinal')]
PHJ18880701-V03-07-page22.txt: [('wh', 'ich')]
PHJ18880701-V03-07-page26.txt: [('HY', 'GIENE')]
PHJ18880701-V03-07-page27.txt: [('APPLI', 'ANCES'), ('co', 't')]
PHJ18880701-V03-07-page6.txt: [('experim', 'ents'), ('co', 'mplete')]
PHJ18880801-V03-08-page24.txt: [('pre', 'ssing')]
PHJ18880801-V03-08-page25.txt: [('ap', 'ply')]
PHJ18880801-V03-08-page27.txt: [('Thermo', 'Electric'), ('es', 'sentially')]
PHJ18880801-V03-08-page28.txt: [('Phy', 'sician')]
PHJ18880801-V03-08-page30.txt: [('APPLI', 'ANCES')]
PHJ18880801-V03-08-page32.txt: [('OAKLAN', 'D'), ('mo', 't')]
PHJ18880801-V03-08-page6.txt: [('carbo', 'hydrates')]
PHJ18880801-V03-08-page7.txt: [('carbo', 'hydrates')]
PHJ18880901-V03-09-page19.txt: [('ri', 'to')]
PHJ18880901-V03-09-page28.txt: [('WANTE', 'D')]
PHJ18880901-V03-09-page32.txt: [('Yo', 'Semite'), ('SUBSCR', 'IPTION')]
PHJ18881001-V03-10-page12.txt: [('legis', 'late')]
PHJ18881001-V03-10-page20.txt: [('ro', 'm')]
PHJ18881001-V03-10-page27.txt: [('MO', 'per')]
PHJ18881001-V03-10-page28.txt: [('Thermo', 'Electric')]
PHJ18881001-V03-10-page6.txt: [('foreig', 'n')]
PHJ18881101-V03-11-page11.txt: [('pa', 'tiently')]
PHJ18881101-V03-11-page19.txt: [('th', 'at'), ('Stimu', 'lating')]
PHJ18881101-V03-11-page20.txt: [('TEM', 'PERANCE')]
PHJ18881101-V03-11-page21.txt: [('ex', 'ample')]
PHJ18881101-V03-11-page25.txt: [('Id', 'a')]
PHJ18881101-V03-11-page29.txt: [('CA', 'N'), ('co', 'co')]
PHJ18881101-V03-11-page32.txt: [('al', 'a')]
PHJ18881101-V03-11-page5.txt: [('re', 'absorption')]
PHJ18881101-V03-11-page9.txt: [('lazi', 'ness')]
PHJ18881201-V03-12-page30.txt: [('HY', 'GIENE')]
PHJ18881201-V03-12-page31.txt: [('Thermo', 'Electric')]
PHJ18881201-V03-12-page34.txt: [('PAG', 'E')]
PHJ18881201-V03-12-page9.txt: [('dren', 'the')]
PHJ18890101-V04-01-page12.txt: [('conclu', 'sion')]
PHJ18890101-V04-01-page21.txt: [('HYPERTRO', 'PHY')]
PHJ18890101-V04-01-page24.txt: [('charac', 'ter')]
PHJ18890101-V04-01-page29.txt: [('ove', 'n'), ('WHEA', 'TENA'), ('WA', 'FERS')]
PHJ18890101-V04-01-page32.txt: [('STEE', 'L')]
PHJ18890201-V04-02-page15.txt: [('atte', 'mpt')]
PHJ18890201-V04-02-page16.txt: [('INTEMPER', 'ANCE')]
PHJ18890201-V04-02-page20.txt: [('ment', 'or')]
PHJ18890201-V04-02-page28.txt: [('WA', 'FERS')]
PHJ18890301-V04-03-page2.txt: [('ex', 'hausting')]
PHJ18890301-V04-03-page21.txt: [('squan', 'ders')]
PHJ18890301-V04-03-page28.txt: [('bu', 't'), ('WA', 'FERS')]
PHJ18890301-V04-03-page3.txt: [('WES', 'LEY')]
PHJ18890301-V04-03-page32.txt: [('MA', 'i')]
PHJ18890401-V04-04-page1.txt: [('nurs', 'ing')]
PHJ18890401-V04-04-page14.txt: [('ca', 'rousal')]
PHJ18890401-V04-04-page22.txt: [("Woman'", 's')]
PHJ18890401-V04-04-page27.txt: [('ro', 'at')]
PHJ18890401-V04-04-page28.txt: [('SANC', 'TIFICATION'), ('ti', 'c')]
PHJ18890401-V04-04-page3.txt: [('ex', 'perience')]
PHJ18890401-V04-04-page31.txt: [('WA', 'FERS')]
PHJ18890401-V04-04-page32.txt: [('Thermo', 'Electric')]
PHJ18890501-V04-05-page14.txt: [('exten', 'sively')]
PHJ18890501-V04-05-page25.txt: [('follo', 'ws')]
PHJ18890501-V04-05-page27.txt: [('insti', 'tution')]
PHJ18890501-V04-05-page29.txt: [('Thermo', 'Electric')]
PHJ18890501-V04-05-page31.txt: [('substan', 'tial')]
PHJ18890601-V04-06-page13.txt: [('smok', 'ing')]
PHJ18890601-V04-06-page25.txt: [('substan', 'tial')]
PHJ18890601-V04-06-page27.txt: [('Lan', 'caster')]
PHJ18890601-V04-06-page28.txt: [('Cr', 'ackers')]
PHJ18890601-V04-06-page29.txt: [('Thermo', 'Electric'), ('ti', 'a')]
PHJ18890601-V04-06-page32.txt: [('ro', 'C')]
PHJ18890701-V04-07-page27.txt: [('Lan', 'caster')]
PHJ18890701-V04-07-page28.txt: [('Thermo', 'Electric')]
PHJ18890801-V04-08-page10.txt: [('re', 'marks')]
PHJ18890801-V04-08-page14.txt: [('PA', 'SO')]
PHJ18890801-V04-08-page15.txt: [('swal', 'low')]
PHJ18890801-V04-08-page20.txt: [('ab', 'out')]
PHJ18890801-V04-08-page21.txt: [('ca', 'n')]
PHJ18890801-V04-08-page28.txt: [('Thermo', 'Electric')]
PHJ18890801-V04-08-page29.txt: [('Cr', 'ackers')]
PHJ18890801-V04-08-page7.txt: [("Harper'", 's')]
PHJ18890901-V04-09-page12.txt: [('re', 'frain')]
PHJ18890901-V04-09-page21.txt: [('reme', 'died')]
PHJ18890901-V04-09-page23.txt: [('subordi', 'nate')]
PHJ18890901-V04-09-page24.txt: [('al', 'I')]
PHJ18890901-V04-09-page29.txt: [('Thermo', 'Electric')]
PHJ18891001-V04-10-page11.txt: [('profes', 'sion'), ("Harper'", 's')]
PHJ18891001-V04-10-page29.txt: [('Thermo', 'Electric'), ('Da', 'isy')]
PHJ18891101-V04-11-page26.txt: [('TEM', 'PERANCE')]
PHJ18891101-V04-11-page29.txt: [('Thermo', 'Electric')]
PHJ18891101-V04-11-page30.txt: [("SALISBURY'", 'S')]
PHJ18891101-V04-11-page7.txt: [('Ro', 'Me')]
PHJ18891101-V04-11-page8.txt: [('inclina', 'tions')]
PHJ18891201-V04-12-page14.txt: [('chil', 'dren')]
PHJ18891201-V04-12-page15.txt: [('recom', 'mended')]
PHJ18891201-V04-12-page18.txt: [('kal', 'is')]
PHJ18891201-V04-12-page28.txt: [('lb', 's')]
PHJ18891201-V04-12-page29.txt: [('Thermo', 'Electric')]
PHJ18891201-V04-12-page33.txt: [('absti', 'nence')]
PHJ18891201-V04-12-page34.txt: [('chil', 'dren')]
PHJ18891201-V04-12-page8.txt: [('al', 'd')]
PHJ18900101-V05-01-page25.txt: [('re', 'adapting')]
PHJ18900101-V05-01-page27.txt: [('Jou', 'RNAL')]
PHJ18900101-V05-01-page28.txt: [('Thermo', 'Electric')]
PHJ18900101-V05-01-page7.txt: [('VEGETA', 'RIANISM')]
PHJ18900201-V05-02-page17.txt: [('se', 'a')]
PHJ18900201-V05-02-page24.txt: [('th', 'e')]
PHJ18900201-V05-02-page25.txt: [('demi', 'monde')]
PHJ18900201-V05-02-page27.txt: [('Lincol', 'n')]
PHJ18900201-V05-02-page28.txt: [('Suppo', 'rter'), ('Thermo', 'Electric')]
PHJ18900301-V05-03-page23.txt: [('ful', 'as')]
PHJ18900301-V05-03-page26.txt: [('mo', 't')]
PHJ18900301-V05-03-page32.txt: [('Sto', 'a')]
PHJ18900401-V05-04-page26.txt: [('respons', 'e')]
PHJ18900401-V05-04-page27.txt: [('pa', 'say')]
PHJ18900401-V05-04-page31.txt: [('cl', 'osed'), ('es', 'sentially')]
PHJ18900401-V05-04-page32.txt: [('CO', 'R'), ('pr', 'ef')]
PHJ18900401-V05-04-page9.txt: [('appe', 'tites')]
PHJ18900501-V05-05-page21.txt: [('impor', 'tant')]
PHJ18900501-V05-05-page26.txt: [('Mc', 'Clure')]
PHJ18900501-V05-05-page8.txt: [('al', 'way')]
PHJ18900601-V05-06-page12.txt: [('tink', 'ling')]
PHJ18900601-V05-06-page21.txt: [('inno', 'vations'), ('nu', 'n')]
PHJ18900601-V05-06-page24.txt: [('increasin', 'g')]
PHJ18900601-V05-06-page27.txt: [('Lan', 'caster')]
PHJ18900601-V05-06-page30.txt: [('ONL', 'Y')]
PHJ18900601-V05-06-page32.txt: [('HALLET', 'T')]
PHJ18900601-V05-06-page5.txt: [('re', 'garded')]
PHJ18900701-V05-07-page12.txt: [("Youth'", 's')]
PHJ18900701-V05-07-page25.txt: [('al', 'ways')]
PHJ18900701-V05-07-page30.txt: [('lithog', 'raph')]
PHJ18900701-V05-07-page31.txt: [('ta', 't')]
PHJ18900701-V05-07-page32.txt: [('buil', 'ding')]
PHJ18900701-V05-07-page6.txt: [('INDEPEND', 'ENCE')]
PHJ18900801-V05-08-page23.txt: [('fl', 'at')]
PHJ18900801-V05-08-page26.txt: [('PROHIBI', 'TION')]
PHJ18900801-V05-08-page28.txt: [('COMBINA', 'TION')]
PHJ18900801-V05-08-page29.txt: [('Cata', 'logue')]
PHJ18900801-V05-08-page31.txt: [('buil', 'ding')]
PHJ18900801-V05-08-page32.txt: [('Vo', 'e')]
PHJ18900801-V05-08-page4.txt: [('un', 'heeded')]
PHJ18900901-V05-09-page26.txt: [('forti', 'eth')]
PHJ18900901-V05-09-page31.txt: [('Thi', 's')]
PHJ18901001-V05-10-page12.txt: [('ap', 'plied')]
PHJ18901001-V05-10-page17.txt: [('ro', 'per')]
PHJ18901001-V05-10-page31.txt: [('CO', 'P'), ('buil', 'ding')]
PHJ18901001-V05-10-page7.txt: [('al', 'e')]
PHJ18901101-V05-11-page26.txt: [('ASSOCIA', 'TION')]
PHJ18901101-V05-11-page6.txt: [('CI', 'NE')]
PHJ18901201-V05-12-page14.txt: [("Youth'", 's')]
PHJ18901201-V05-12-page23.txt: [('tem', 'ple')]
PHJ18901201-V05-12-page26.txt: [('PA', 'CIFIC')]
PHJ18901201-V05-12-page28.txt: [('CO', 'P'), ('ca', 'se'), ('ti', 'The')]
PHJ18901201-V05-12-page31.txt: [('IE', 'R')]
PHJ18910101-V06-01-page11.txt: [("Hall'", 's')]
PHJ18910101-V06-01-page27.txt: [('exi', 'ts')]
PHJ18910101-V06-01-page29.txt: [('cl', 'osed')]
PHJ18910101-V06-01-page30.txt: [('Assy', 'rian')]
PHJ18910101-V06-01-page32.txt: [('corres', 'pondence')]
PHJ18910101-V06-01-page8.txt: [('OPPOR', 'TUNITIES')]
PHJ18910201-V06-02-page12.txt: [('al', 'ways')]
PHJ18910201-V06-02-page18.txt: [('SHIR', 'KING')]
PHJ18910201-V06-02-page29.txt: [('se', 'c')]
PHJ18910201-V06-02-page30.txt: [('M.', ''), ('Assy', 'rian')]
PHJ18910301-V06-03-page32.txt: [('corres', 'pondence')]
PHJ18910401-V06-04-page17.txt: [('un', 'til')]
PHJ18910401-V06-04-page28.txt: [('TA', 'PE-WORM')]
PHJ18910401-V06-04-page31.txt: [('wor', 'ld')]
PHJ18910401-V06-04-page32.txt: [('corres', 'pondence')]
PHJ18910501-V06-05-page11.txt: [('recom', 'mend'), ('ob', 'taining')]
PHJ18910501-V06-05-page27.txt: [('sani', 'tas')]
PHJ18910501-V06-05-page30.txt: [('HEA', 'LTHFUL')]
PHJ18910501-V06-05-page32.txt: [('corres', 'pondence')]
PHJ18910501-V06-05-page9.txt: [('DYS', 'PEPSIA')]
PHJ18910601-V06-06-page11.txt: [('oc', 'currence')]
PHJ18910601-V06-06-page19.txt: [('jeal', 'ousy')]
PHJ18910601-V06-06-page20.txt: [('Balti', 'more')]
PHJ18910601-V06-06-page24.txt: [('sus', 'picion')]
PHJ18910601-V06-06-page28.txt: [('phy', 'sicians'), ('inconven', 'iently')]
PHJ18910601-V06-06-page32.txt: [('corres', 'pondence')]
PHJ18910701-V06-07-page13.txt: [('INTOX', 'ICATING')]
PHJ18910701-V06-07-page17.txt: [('Espe', 'cially')]
PHJ18910701-V06-07-page19.txt: [('substan', 'tials')]
PHJ18910701-V06-07-page27.txt: [('Cr', 'ackers')]
PHJ18910701-V06-07-page28.txt: [('inconven', 'iently')]
PHJ18910701-V06-07-page29.txt: [('cl', 'osed')]
PHJ18910701-V06-07-page3.txt: [('capacit', 'y')]
PHJ18910701-V06-07-page32.txt: [('corres', 'pondence')]
PHJ18910801-V06-08-page1.txt: [('MONTHL', 'Y')]
PHJ18910801-V06-08-page28.txt: [('shoul', 'ders'), ('phy', 'sicians'), ('inconven', 'iently')]
PHJ18910801-V06-08-page32.txt: [('corres', 'pondence')]
PHJ18910901-V06-09-page11.txt: [('progeni', 'tors')]
PHJ18910901-V06-09-page30.txt: [('Ne', 'w'), ('Thermo', 'Electric')]
PHJ18910901-V06-09-page31.txt: [('Tu', 'm')]
PHJ18910901-V06-09-page32.txt: [('Clo', 'th'), ('th', 'e')]
PHJ18911001-V06-10-page12.txt: [('AL', 'COHOL')]
PHJ18911001-V06-10-page22.txt: [('CHOCO', 'LATE')]
PHJ18911001-V06-10-page23.txt: [('itt', 'a')]
PHJ18911001-V06-10-page27.txt: [('mo', 't')]
PHJ18911001-V06-10-page28.txt: [('th', 'e')]
PHJ18911001-V06-10-page3.txt: [('dyna', 'mite')]
PHJ18911001-V06-10-page32.txt: [('BEA', 'TTY'), ('GA', 's')]
PHJ18911001-V06-10-page5.txt: [('bac', 'teria')]
PHJ18911101-V06-11-page19.txt: [('prec', 'incts')]
PHJ18911101-V06-11-page22.txt: [('entr', 'e')]
PHJ18911101-V06-11-page27.txt: [('elec', 'tric')]
PHJ18911101-V06-11-page28.txt: [('Beatt', 'y')]
PHJ18911101-V06-11-page29.txt: [('ib', 'o')]
PHJ18911101-V06-11-page30.txt: [('Thermo', 'Electric')]
PHJ18911101-V06-11-page31.txt: [('ase', 'r')]
PHJ18911101-V06-11-page32.txt: [('FRIE', 'D')]
PHJ18911101-V06-11-page5.txt: [('pater', 'familias')]
PHJ18911201-V06-12-page1.txt: [('exer', 'cise')]
PHJ18911201-V06-12-page30.txt: [('PLA', 'TES')]
PHJ18911201-V06-12-page31.txt: [('wor', 'k')]
PHJ18911201-V06-12-page32.txt: [('FRIE', 'D')]
PHJ18920101-V07-01-page1.txt: [('co', 'operation')]
PHJ18920101-V07-01-page20.txt: [('EF', 'FECT')]
PHJ18920101-V07-01-page28.txt: [('ADVERTIS', 'ING')]
PHJ18920101-V07-01-page29.txt: [('OA', 'R'), ('Yo', 'Semite'), ('pu', 'BLISHING')]
PHJ18920101-V07-01-page31.txt: [('Ingrow', 'Ing'), ('generat', 'ion')]
PHJ18920201-V07-02-page25.txt: [('investi', 'gate')]
PHJ18920201-V07-02-page27.txt: [('pa', 'd')]
PHJ18920201-V07-02-page28.txt: [('ADVERTIS', 'ING')]
PHJ18920201-V07-02-page29.txt: [('YO', 'SEMITE'), ('Yo', 'Semite')]
PHJ18920201-V07-02-page3.txt: [('cul', 'ture')]
PHJ18920201-V07-02-page30.txt: [('FRIE', 'D')]
PHJ18920201-V07-02-page5.txt: [('py', 'emia')]
PHJ18920201-V07-02-page6.txt: [('stom', 'A')]
PHJ18920201-V07-02-page9.txt: [('re', 'leased')]
PHJ18920301-V07-03-page10.txt: [('EM', 'P')]
PHJ18920301-V07-03-page18.txt: [('enjoyabl', 'e')]
PHJ18920301-V07-03-page19.txt: [('ti', 't')]
PHJ18920301-V07-03-page25.txt: [('th', 'e')]
PHJ18920301-V07-03-page28.txt: [('te', 'a'), ('ADVERTIS', 'ING')]
PHJ18920301-V07-03-page31.txt: [('po', 'o')]
PHJ18920301-V07-03-page6.txt: [('additi', 'on')]
PHJ18920401-V07-04-page2.txt: [('treatmen', 't')]
PHJ18920401-V07-04-page22.txt: [('remem', 'bered')]
PHJ18920401-V07-04-page3.txt: [('pre', 'vention'), ('re', 'lief')]
PHJ18920401-V07-04-page31.txt: [('pa', 'd')]
PHJ18920401-V07-04-page32.txt: [('tI', 'S'), ('Fitz', 'Gerald'), ('ADVERTIS', 'ING')]
PHJ18920401-V07-04-page5.txt: [('indi', 'cates')]
PHJ18920501-V07-05-page22.txt: [('re', 'T'), ('LI', 'I'), ('ri', 'a')]
PHJ18920501-V07-05-page28.txt: [('NA', 'PA')]
PHJ18920501-V07-05-page32.txt: [('Fitz', 'Gerald'), ('ADVERTIS', 'ING')]
PHJ18920601-V07-06-page11.txt: [('Fitz', 'Hugh')]
PHJ18920601-V07-06-page25.txt: [('Un', 'doubtedly')]
PHJ18920601-V07-06-page26.txt: [('esti', 'mated')]
PHJ18920601-V07-06-page31.txt: [('Yr', 'S')]
PHJ18920601-V07-06-page32.txt: [('Fitz', 'Gerald'), ('ADVERTIS', 'ING')]
PHJ18920601-V07-06-page5.txt: [('RI', 'AL')]
PHJ18920601-V07-06-page6.txt: [('EXTER', 'NALLY')]
PHJ18920701-V07-07-page13.txt: [('phy', 'sicians')]
PHJ18920701-V07-07-page14.txt: [('ab', 'e'), ('profes', 'sion')]
PHJ18920701-V07-07-page19.txt: [('CHIL', 'DREN')]
PHJ18920701-V07-07-page22.txt: [('th', 'at')]
PHJ18920701-V07-07-page28.txt: [('sar', 'Is'), ('CO', 'on')]
PHJ18920701-V07-07-page30.txt: [('Fitz', 'Gerald'), ('AZIe', 'I')]
PHJ18920701-V07-07-page32.txt: [('Yo', 'Semite')]
PHJ18920801-V07-08-page1.txt: [('M.', '')]
PHJ18920801-V07-08-page10.txt: [('VENTILA', 'TION')]
PHJ18920801-V07-08-page30.txt: [('CO', 'on')]
PHJ18920801-V07-08-page32.txt: [('Fitz', 'Gerald'), ('WA', 'S')]
PHJ18920801-V07-08-page4.txt: [('expen', 'diture')]
PHJ18920801-V07-08-page7.txt: [('suc', 'ceeded')]
PHJ18920901-V07-09-page1.txt: [('MONTHL', 'Y')]
PHJ18920901-V07-09-page28.txt: [('Pre', 'Adamite')]
PHJ18920901-V07-09-page4.txt: [('ex', 'ercise')]
PHJ18921001-V07-10-page1.txt: [('MONTHL', 'Y')]
PHJ18921001-V07-10-page23.txt: [('nitroge', 'nous')]
PHJ18921001-V07-10-page28.txt: [('CO', 'on'), ('pa', 'd')]
PHJ18921001-V07-10-page32.txt: [('HYGIE', 'NIC')]
PHJ18921001-V07-10-page8.txt: [('uncon', 'scious')]
PHJ18921101-V07-11-page19.txt: [("MOTHER'", 'S')]
PHJ18921101-V07-11-page25.txt: [('descrip', 'tions')]
PHJ18921101-V07-11-page31.txt: [('pre', 'eminent')]
PHJ18921101-V07-11-page32.txt: [('Gasolin', 'e'), ('Fitz', 'Gerald')]
PHJ18921101-V07-11-page5.txt: [('ca', 'tarrh')]
PHJ18921101-V07-11-page6.txt: [('bi', 'concave')]
PHJ18921201-V07-12-page11.txt: [('ene', 'mies')]
PHJ18921201-V07-12-page15.txt: [('th', 'a')]
PHJ18921201-V07-12-page2.txt: [('thermo', 'electricity')]
PHJ18921201-V07-12-page28.txt: [('Re', 'treat')]
PHJ18921201-V07-12-page29.txt: [('PRE', 'PAID')]
PHJ18921201-V07-12-page32.txt: [('Fitz', 'Gerald')]
PHJ18921201-V07-12-page5.txt: [('oth', 'erwise'), ('es', 'pecially')]
PHJ18960101-V11-01-page17.txt: [('NERV', 'OUS')]
PHJ18960101-V11-01-page7.txt: [("Harper'", 's')]
PHJ18960201-V11-02-page22.txt: [('ASSO', 'CIATIONS')]
PHJ18960201-V11-02-page27.txt: [('ig', 'norant')]
PHJ18960201-V11-02-page29.txt: [('th', 'a')]
PHJ18960201-V11-02-page31.txt: [('CALIFORNI', 'A')]
PHJ18960201-V11-02-page5.txt: [('Hebri', 'des')]
PHJ18960301-V11-03-page20.txt: [('QUERI', 'ES')]
PHJ18960501-V11-05-page11.txt: [('IL', 'A')]
PHJ18960501-V11-05-page7.txt: [('physiol', 'ogy')]
PHJ18960601-V11-06-page31.txt: [('OA', 'KLAND')]
PHJ18960601-V11-06-page32.txt: [('asth', 'ma')]
PHJ18960601-V11-06-page6.txt: [('DISSEM', 'INATION')]
PHJ18960801-V11-08-page23.txt: [('WOR', 'RYING')]
PHJ18960801-V11-08-page26.txt: [('atten', 'tion')]
PHJ18960801-V11-08-page32.txt: [('ri', 'D')]
PHJ18960801-V11-08-page5.txt: [('ro', 'of')]
PHJ18960901-V11-09-page16.txt: [('ce', 'rtain')]
PHJ18960901-V11-09-page17.txt: [('MO', "THER'S")]
PHJ18960901-V11-09-page32.txt: [('CO', 'St')]
PHJ18961001-V11-10-page10.txt: [('LOCOMO', 'TION')]
PHJ18961001-V11-10-page18.txt: [('CHIL', 'DREN')]
PHJ18961001-V11-10-page26.txt: [('ma', 'I')]
PHJ18961001-V11-10-page30.txt: [('ex', 'It')]
PHJ18961001-V11-10-page32.txt: [('CO', 'St')]
PHJ18961101-V11-11-page10.txt: [('CAPI', 'TAL')]
PHJ18961101-V11-11-page17.txt: [('witho', 'ut'), ('ut', 'a')]
PHJ18961201-V11-12-page14.txt: [("Trumbull'", 's')]
PHJ18961201-V11-12-page31.txt: [('SNY', 'DER')]
PHJ18961201-V11-12-page32.txt: [('asth', 'ma')]
PHJ18961201-V11-12-page5.txt: [('degrad', 'ing')]
PHJ18990301-V14-03-page19.txt: [('ASSOCIA', 'TION'), ('PA', 'CIFIC')]
PHJ18990301-V14-03-page8.txt: [('PHYSI', "CIAN'S")]
PHJ18990501-V14-05-page16.txt: [("Youth'", 's')]
PHJ18990601-V14-06-page11.txt: [('Sa', 'lts')]
PHJ18990601-V14-06-page17.txt: [('Ric', 'E')]
PHJ18990701-V14-07-page10.txt: [('em', 'bodied')]
PHJ18990701-V14-07-page13.txt: [('wh', 'at')]
PHJ18990901-V14-09-page30.txt: [('Ch', 'ina')]
PHJ18991001-V14-10-page17.txt: [('un', 'usually')]
PHJ18991101-V14-11-page19.txt: [('sug', 'gestion')]
PHJ19010201-V16-02-page1.txt: [('PA', 'CIFIC')]
PHJ19010201-V16-02-page21.txt: [('SANI', 'TARIUM')]
PHJ19010201-V16-02-page29.txt: [('CALIFOR', 'NIA')]
PHJ19010201-V16-02-page34.txt: [('ele', 'vated')]
PHJ19010301-V16-03-page23.txt: [('M.', '')]
PHJ19010301-V16-03-page27.txt: [('ou', 'd')]
PHJ19010301-V16-03-page31.txt: [('TELE', 'PHONE'), ('Al', 'e')]
PHJ19010301-V16-03-page33.txt: [('RE', 'A')]
PHJ19010401-V16-04-page11.txt: [('Br', 'O')]
PHJ19010401-V16-04-page3.txt: [('M.', '')]
PHJ19010501-V16-05-page2.txt: [('Th', 'y')]
PHJ19010601-V16-06-page40.txt: [('MIS', 'SIONARY')]
PHJ19010701-V16-07-page12.txt: [('Br', 'O')]
PHJ19010701-V16-07-page13.txt: [('Boi', 'led'), ('Al', 'A')]
PHJ19010701-V16-07-page27.txt: [('TEM', 'PERATURES'), ('OP', 'TIME')]
PHJ19010701-V16-07-page3.txt: [('SANITA', 'RIUM')]
PHJ19010701-V16-07-page35.txt: [('EU', 'REkA')]
PHJ19010801-V16-08-page1.txt: [('PA', 'CIFIC')]
PHJ19010801-V16-08-page19.txt: [('AL', 'MOND')]
PHJ19010801-V16-08-page2.txt: [('fr', 'A')]
PHJ19010801-V16-08-page29.txt: [('ADVERTISEM', 'ENTS')]
PHJ19010801-V16-08-page30.txt: [('DIA', 'NA'), ('NA', 'P')]
PHJ19010801-V16-08-page33.txt: [('SPECIA', 'LTY')]
PHJ19010801-V16-08-page4.txt: [('TEM', 'PERATURES')]
PHJ19010901-V16-09-page1.txt: [('PA', 'CIFIC')]
PHJ19010901-V16-09-page25.txt: [('impossi', 'ble')]
PHJ19010901-V16-09-page27.txt: [('PARLI', 'N')]
PHJ19010901-V16-09-page29.txt: [('SE', 'ALS')]
PHJ19010901-V16-09-page30.txt: [('CA', 'lk')]
PHJ19010901-V16-09-page35.txt: [('EU', 'REKA')]
PHJ19011001-V16-10-page1.txt: [('PA', 'CIFIC'), ('ta', 'rt')]
PHJ19011001-V16-10-page12.txt: [('hydrothera', 'peutic')]
PHJ19011001-V16-10-page3.txt: [('FA', 'in')]
PHJ19011001-V16-10-page30.txt: [('il', 'l')]
PHJ19011101-V16-11-page30.txt: [('dif', 'fers')]
PHJ19011101-V16-11-page5.txt: [('THOM', 'AS')]
PHJ19011101-V16-11-page7.txt: [('TUBERCU', 'LOSIS'), ('arterio', 'sclerosis')]
PHJ19011201-V16-12-page2.txt: [('Li', 'S')]
PHJ19011201-V16-12-page39.txt: [('KE', 'A')]
PHJ19011201-V16-12-page44.txt: [('Sanitariu', 'm')]
PHJ19020101-V17-01-page35.txt: [('KE', 'A')]
PHJ19020101-V17-01-page36.txt: [('Langle', 'y')]
PHJ19020101-V17-01-page38.txt: [('STENCI', 'LS')]
PHJ19020201-V17-02-page1.txt: [('Br', 'O')]
PHJ19020201-V17-02-page9.txt: [('indul', 'gence')]
PHJ19020301-V17-03-page27.txt: [('preven', 'tive')]
PHJ19020301-V17-03-page36.txt: [('STENCI', 'LS')]
PHJ19020401-V17-04-page15.txt: [('pota', 'toes')]
PHJ19020401-V17-04-page32.txt: [('KE', 'A')]
PHJ19020401-V17-04-page5.txt: [('Vo', 'L')]
PHJ19020501-V17-05-page1.txt: [('Br', 'A')]
PHJ19020501-V17-05-page13.txt: [('TREA', 'TMENTS')]
PHJ19020501-V17-05-page2.txt: [('TH', 'o')]
PHJ19020501-V17-05-page21.txt: [('Housek', 'eeping')]
PHJ19020501-V17-05-page28.txt: [('PA', 'CIFIC')]
PHJ19020601-V17-06-page2.txt: [('SUBSCRIP', 'TIONS')]
PHJ19020701-V17-07-page11.txt: [('ro', 'o')]
PHJ19020701-V17-07-page2.txt: [('SUBSCRIP', 'TIONS')]
PHJ19020801-V17-08-page2.txt: [('li', 'E')]
PHJ19020801-V17-08-page25.txt: [('un', 'dertaking')]
PHJ19020801-V17-08-page7.txt: [('re', 'turned')]
PHJ19020901-V17-09-page15.txt: [('conse', 'quent')]
PHJ19020901-V17-09-page34.txt: [('SANI', 'TARIUM')]
PHJ19020901-V17-09-page7.txt: [('QUANTI', 'TIES')]
PHJ19021001-V17-10-page34.txt: [('SANI', 'TARIUM')]
PHJ19021101-V17-11-page27.txt: [('KNO', 'W')]
PHJ19021101-V17-11-page29.txt: [('sonom', 'a')]
PHJ19021101-V17-11-page34.txt: [('HARRIM', 'AN')]
PHJ19021201-V17-12-page36.txt: [('se', 'P')]
PHJ19030101-V18-01-page15.txt: [('artis', 'tic')]
PHJ19030101-V18-01-page28.txt: [('graduall', 'y')]
PHJ19030101-V18-01-page30.txt: [('fo', 'B')]
PHJ19030101-V18-01-page34.txt: [('M.', '')]
PHJ19030401-V18-04-page23.txt: [('theo', 'ries')]
PHJ19030401-V18-04-page28.txt: [('STAM', 'MERING')]
PHJ19030401-V18-04-page35.txt: [('cr', 'U'), ('Zi', 'Or')]
PHJ19030501-V18-05-page19.txt: [('EDU', 'CATE')]
PHJ19030501-V18-05-page29.txt: [('STENCI', 'LS')]
PHJ19030501-V18-05-page30.txt: [('fr', 'A')]
PHJ19030601-V18-06-page17.txt: [('Tid', 'Bits')]
PHJ19030601-V18-06-page2.txt: [('Trainin', 'g')]
PHJ19030601-V18-06-page30.txt: [("I'", 's')]
PHJ19030601-V18-06-page31.txt: [('JOURNA', 'LS')]
PHJ19030701-V18-07-page35.txt: [('NI', 't')]
PHJ19030801-V18-08-page12.txt: [('re', 'examined')]
PHJ19030901-V18-09-page10.txt: [('infan', 'tum')]
PHJ19030901-V18-09-page35.txt: [('li', 'st')]
PHJ19030901-V18-09-page4.txt: [('LI', 'I')]
PHJ19031001-V18-10-page11.txt: [('re', 'a')]
PHJ19031001-V18-10-page17.txt: [('Socr', 'ates')]
PHJ19031001-V18-10-page34.txt: [('particula', 'rs')]
PHJ19031101-V18-11-page11.txt: [('Itt', 'A')]
PHJ19031101-V18-11-page29.txt: [('Ent', 'irely')]
PHJ19031101-V18-11-page3.txt: [('fi', 'N'), ('gi', 'g')]
PHJ19031101-V18-11-page9.txt: [('gladi', 'ators')]
PHJ19031201-V18-12-page35.txt: [('PA', 'li'), ('ti', 'A')]
PHJ19040101-V19-01-page27.txt: [("V'", 'S')]
PHJ19040101-V19-01-page33.txt: [('LIMITE', 'D')]
PHJ19040201-V19-02-page28.txt: [('Ba', 'ttle')]
PHJ19040301-V19-03-page34.txt: [('EUREK', 'A'), ('Vegetar', 'ian')]
PHJ19040401-V19-04-page12.txt: [('inj', 'uriousness')]
PHJ19040401-V19-04-page5.txt: [('hav', 'e')]
PHJ19040501-V19-05-page19.txt: [("WOMAN'", 'S')]
PHJ19040501-V19-05-page30.txt: [('entr', 'e')]
PHJ19040601-V19-06-page13.txt: [('FOMENTA', 'TIONS')]
In [29]:
# %load shared_elements/summary.py
summary = GoH.reports.overview_report(directories['cycle'], spelling_dictionary, title)
Directory: /Users/jeriwieringa/Dissertation/text/text/2017-01-31-corpus-with-utf8-split-into-titles-cleaning/PHJ/correction6 Average verified rate: 0.9811191527390404 Average of error rates: 0.026716285269940018 Total token count: 2850031
In [30]:
# %load shared_elements/top_errors.py
errors_summary = GoH.reports.get_errors_summary( summary )
GoH.reports.top_errors( errors_summary, 10 )[:50]
Out[30]:
[('m', 2734),
('d', 2327),
("'", 1997),
('e', 1381),
('r', 1270),
('t', 1207),
('w', 1173),
('n', 1120),
('co', 1109),
('f', 796),
('g', 761),
('x', 649),
('lb', 583),
('th', 251),
('sel', 251),
('oo', 237),
('mo', 230),
('pp', 226),
('z', 217),
('k', 215),
('u', 199),
("an'", 192),
('q', 133),
('ex', 106),
('ournal', 106),
('al', 98),
('te', 85),
('oz', 81),
('ro', 80),
('ga', 80),
('pa', 74),
('va', 74),
('munn', 73),
('io', 72),
('ti', 67),
('-', 66),
("infants'", 61),
('id', 58),
('zo', 55),
('viperance', 54),
('em', 53),
('tion', 51),
("''", 49),
('re', 48),
('urnal', 48),
('si', 47),
('fahr', 46),
('cc', 45),
("hours'", 44),
('cloe', 43)]
Correction 7 -- Rejoin Split Words II¶
In [31]:
# %load shared_elements/rejoin_split_words.py
prev = cycle
cycle = "correction7"
directories = GoH.utilities.define_directories(prev, cycle, base_dir)
if not os.path.exists(directories['cycle']):
os.makedirs(directories['cycle'])
corpus = (f for f in listdir(directories['prev']) if not f.startswith('.') and isfile(join(directories['prev'], f)))
for filename in corpus:
content = GoH.utilities.readfile(directories['prev'], filename)
text = re.sub(r"[0-9,!?$:;&]", " ", content)
tokens = GoH.utilities.tokenize_text(text)
errors = GoH.reports.identify_errors(tokens, spelling_dictionary)
replacements = GoH.clean.check_if_stem(errors, spelling_dictionary, tokens, get_prior=True)
if len(replacements) > 0:
print('{}: {}'.format(filename, replacements))
for replacement in replacements:
content = GoH.clean.replace_split_words(replacement, content)
else:
pass
with open(join(directories['cycle'], filename), mode="w") as o:
o.write(content)
o.close()
PHJ18850601-V01-01-page1.txt: [('in', 'toxicating'), ('TEMPER', 'ANCE')]
PHJ18850601-V01-01-page16.txt: [('PHYSIC', 'AL'), ('state', 'ment')]
PHJ18850601-V01-01-page21.txt: [('o', 'pp')]
PHJ18850601-V01-01-page24.txt: [('A', 'ZAL'), ('A', 'li')]
PHJ18850801-V01-02-page1.txt: [('F', 'lt')]
PHJ18850801-V01-02-page22.txt: [('o', 'pp')]
PHJ18850801-V01-02-page4.txt: [('f', 'und')]
PHJ18850801-V01-02-page8.txt: [('Q', 'uick'), ('U', 'se'), ('J', 'ust'), ('R', 'emember'), ('K', 'eep'), ('T', 'ake'), ('N', 'ow'), ('P', 'eople'), ('Z', 'eal'), ('C', 'hildren'), ('G', 'arments'), ('M', 'uch'), ('H', 'omes'), ('S', 'ee'), ('X', 'erxes'), ('F', 'reshen'), ('V', 'ery')]
PHJ18851001-V01-03-page13.txt: [('A', 'ccount')]
PHJ18851001-V01-03-page22.txt: [('num', 'ber'), ('o', 'pp')]
PHJ18851001-V01-03-page23.txt: [('K', 'Ra')]
PHJ18851001-V01-03-page5.txt: [('r', 'oo')]
PHJ18851201-V01-04-page21.txt: [('JOUR', 'NAL')]
PHJ18851201-V01-04-page22.txt: [('o', 'pp')]
PHJ18860201-V01-05-page14.txt: [('physic', 'al')]
PHJ18860401-V01-06-page21.txt: [('JOUR', 'NAL')]
PHJ18860401-V01-06-page22.txt: [('con', 'sisted')]
PHJ18860401-V01-06-page23.txt: [('SAB', 'BATH-SCHOOL'), ('SEC', 'ULAR')]
PHJ18860601-V02-01-page1.txt: [('J', 'UN')]
PHJ18860601-V02-01-page21.txt: [('M', "isses'")]
PHJ18860601-V02-01-page22.txt: [('P', 'RACTICAL')]
PHJ18860801-V02-02-page13.txt: [('con', 'nection')]
PHJ18860801-V02-02-page26.txt: [('con', 'tains')]
PHJ18860801-V02-02-page28.txt: [('P', 'ase')]
PHJ18860801-V02-02-page4.txt: [('to', 'ea')]
PHJ18861001-V02-03-page10.txt: [('intro', 'duced')]
PHJ18861001-V02-03-page11.txt: [('inter', 'nal')]
PHJ18861001-V02-03-page16.txt: [('main', 'tenance')]
PHJ18861001-V02-03-page28.txt: [('c', 'astro')]
PHJ18861001-V02-03-page29.txt: [('SEC', 'ULAR')]
PHJ18861001-V02-03-page30.txt: [('SCRIP', 'TURES')]
PHJ18861001-V02-03-page32.txt: [('B', 'AL')]
PHJ18861201-V02-04-page19.txt: [('dis', 'pensary'), ('as', 'sume')]
PHJ18861201-V02-04-page27.txt: [('H', 'Es'), ('SCRIP', 'TURES'), ('M', 'ARVEL')]
PHJ18861201-V02-04-page28.txt: [('r', 'OW')]
PHJ18861201-V02-04-page30.txt: [('G', 'eneral'), ('IN', 'TRINSIC'), ('C', 'ONTENT'), ('ad', 'mitted')]
PHJ18870201-V02-05-page25.txt: [('on', 'ce')]
PHJ18870201-V02-05-page29.txt: [('IN', 'TRINSIC'), ('M', 'icroscopists')]
PHJ18870201-V02-05-page30.txt: [('T', 'OW')]
PHJ18870201-V02-05-page32.txt: [('I', 'Va')]
PHJ18870201-V02-05-page4.txt: [('mus', 'cular')]
PHJ18870401-V02-06-page13.txt: [('con', 'ception')]
PHJ18870401-V02-06-page31.txt: [('C', 'ome'), ('IN', 'TRINSIC'), ('A', 'uthor')]
PHJ18870401-V02-06-page32.txt: [('p', 'atients')]
PHJ18870601-V02-07-page13.txt: [('pop', 'ulation'), ('de', 'Lorme')]
PHJ18870601-V02-07-page26.txt: [('PRES', 'ERVATION'), ('j', 'ournal')]
PHJ18870601-V02-07-page27.txt: [('GEN', 'ERAL')]
PHJ18870801-V02-08-page25.txt: [('gas', 'es')]
PHJ18870801-V02-08-page28.txt: [('la', 'th')]
PHJ18870801-V02-08-page29.txt: [('IN', 'TRINSIC'), ('A', 'uthor'), ('ad', 'mitted')]
PHJ18871001-V02-09-page1.txt: [('po', 'etry')]
PHJ18871001-V02-09-page29.txt: [('L', 'ithographic')]
PHJ18871001-V02-09-page30.txt: [('K', 'Ra')]
PHJ18880101-V03-01-page16.txt: [('be', 'ma')]
PHJ18880101-V03-01-page18.txt: [('mem', 'branous')]
PHJ18880101-V03-01-page21.txt: [('Lin', 'coln')]
PHJ18880101-V03-01-page29.txt: [('med', 'ical')]
PHJ18880101-V03-01-page5.txt: [('mur', 'murings')]
PHJ18880201-V03-02-page24.txt: [('AD', 'VOCATE')]
PHJ18880201-V03-02-page28.txt: [('a', 'nd')]
PHJ18880301-V03-03-page13.txt: [('com', 'plexion')]
PHJ18880301-V03-03-page21.txt: [('rem', 'edy')]
PHJ18880301-V03-03-page27.txt: [('a', 'wl')]
PHJ18880401-V03-04-page10.txt: [('phys', 'ical')]
PHJ18880401-V03-04-page25.txt: [('JOUR', 'NAL')]
PHJ18880401-V03-04-page26.txt: [('PUBL', 'IC')]
PHJ18880401-V03-04-page27.txt: [('e', 'ND')]
PHJ18880401-V03-04-page28.txt: [('med', 'ical')]
PHJ18880501-V03-05-page27.txt: [('z', 'zz')]
PHJ18880601-V03-06-page26.txt: [('P', 'RY')]
PHJ18880701-V03-07-page14.txt: [('imper', 'fectly')]
PHJ18880701-V03-07-page27.txt: [('o', 'ch')]
PHJ18880801-V03-08-page26.txt: [('M', 'ACH')]
PHJ18880801-V03-08-page27.txt: [('es', 'sentially')]
PHJ18880901-V03-09-page3.txt: [('pleas', 'ure')]
PHJ18880901-V03-09-page31.txt: [('PRES', 'ERVATION')]
PHJ18880901-V03-09-page8.txt: [('amuse', 'ments')]
PHJ18881001-V03-10-page12.txt: [('in', 'fectious')]
PHJ18881001-V03-10-page22.txt: [('A', 'RE')]
PHJ18881101-V03-11-page13.txt: [('wine', 'bibbers')]
PHJ18881101-V03-11-page16.txt: [('prom', 'ptings')]
PHJ18881101-V03-11-page17.txt: [('in', 'fluence')]
PHJ18881101-V03-11-page22.txt: [('so', 'Iree')]
PHJ18881101-V03-11-page25.txt: [('he', 'sed')]
PHJ18881101-V03-11-page29.txt: [('PRES', 'ERVATION')]
PHJ18881101-V03-11-page3.txt: [('The', 'Re')]
PHJ18881201-V03-12-page21.txt: [('the', 're')]
PHJ18881201-V03-12-page31.txt: [('PRES', 'ERVATION')]
PHJ18890101-V04-01-page12.txt: [('A', 'IL')]
PHJ18890101-V04-01-page29.txt: [('C', 'AL'), ('r', 'oo')]
PHJ18890101-V04-01-page31.txt: [('P', 'RY')]
PHJ18890101-V04-01-page5.txt: [('essen', 'tial')]
PHJ18890201-V04-02-page23.txt: [('a', 'plomb')]
PHJ18890201-V04-02-page28.txt: [('W', 'AIST'), ('M', "isses'")]
PHJ18890201-V04-02-page30.txt: [('I', 'LL')]
PHJ18890301-V04-03-page2.txt: [('nourish', 'ment')]
PHJ18890301-V04-03-page4.txt: [('main', 'taining')]
PHJ18890401-V04-04-page10.txt: [('h', 'aring')]
PHJ18890401-V04-04-page14.txt: [('sin', 'gle')]
PHJ18890401-V04-04-page19.txt: [('d', 'ismally')]
PHJ18890401-V04-04-page29.txt: [('A', 'id')]
PHJ18890401-V04-04-page32.txt: [('we', 'ekly')]
PHJ18890401-V04-04-page5.txt: [('of', 'fering')]
PHJ18890501-V04-05-page11.txt: [('men', 'tioned')]
PHJ18890501-V04-05-page14.txt: [('wonder', 'ful')]
PHJ18890501-V04-05-page20.txt: [('at', 'tained')]
PHJ18890501-V04-05-page5.txt: [('or', 'dinary')]
PHJ18890601-V04-06-page6.txt: [('r', 'oo')]
PHJ18890701-V04-07-page10.txt: [('to', 'ro')]
PHJ18890701-V04-07-page12.txt: [('a', 're')]
PHJ18890701-V04-07-page17.txt: [('bod', 'ies')]
PHJ18890701-V04-07-page27.txt: [('A', 'ugusta')]
PHJ18890701-V04-07-page28.txt: [('a', 'sp'), ('p', 'ay')]
PHJ18890701-V04-07-page30.txt: [('me', 'ekly')]
PHJ18890701-V04-07-page8.txt: [('IDOL', 'ATRY')]
PHJ18890801-V04-08-page27.txt: [('st', 'ine')]
PHJ18890901-V04-09-page26.txt: [('HEL', 'ENA')]
PHJ18890901-V04-09-page27.txt: [('we', 'ekly')]
PHJ18891001-V04-10-page26.txt: [('Ad', 'ventists')]
PHJ18891001-V04-10-page27.txt: [('we', 'ekly')]
PHJ18891001-V04-10-page29.txt: [('Da', 'isy'), ('Supp', 'orter'), ('sin', 'gle')]
PHJ18891001-V04-10-page31.txt: [('r', 'oo')]
PHJ18891101-V04-11-page1.txt: [('P', 'ACIFIC')]
PHJ18891201-V04-12-page29.txt: [('well', 'es')]
PHJ18891201-V04-12-page32.txt: [('Heal', 'dsburg')]
PHJ18891201-V04-12-page33.txt: [('absti', 'nence')]
PHJ18891201-V04-12-page34.txt: [('To', 'ssing'), ('To', 'bacco'), ('To', 'tal'), ('chil', 'dren'), ('To', 'nics'), ('To', 'othache'), ('To', 'ilet')]
PHJ18900101-V05-01-page28.txt: [('a', 'sp'), ('La', "dies'"), ('W', 'aist')]
PHJ18900101-V05-01-page9.txt: [('temp', 'tations')]
PHJ18900201-V05-02-page14.txt: [('accomplish', 'ment'), ('con', 'trol')]
PHJ18900201-V05-02-page28.txt: [('Suppo', 'rter'), ('Child', "ren's")]
PHJ18900201-V05-02-page31.txt: [('med', 'ical')]
PHJ18900301-V05-03-page27.txt: [('in', 'cludes')]
PHJ18900301-V05-03-page30.txt: [('r', 'oo'), ('So', 'cial')]
PHJ18900301-V05-03-page8.txt: [('temp', 'tations')]
PHJ18900401-V05-04-page10.txt: [('care', 'ful')]
PHJ18900401-V05-04-page29.txt: [('r', 'oo')]
PHJ18900401-V05-04-page31.txt: [('es', 'sentially')]
PHJ18900401-V05-04-page32.txt: [('DU', 'NN')]
PHJ18900401-V05-04-page9.txt: [('appe', 'tites')]
PHJ18900501-V05-05-page11.txt: [('pro', 'fessional')]
PHJ18900501-V05-05-page15.txt: [('exam', 'inations')]
PHJ18900501-V05-05-page21.txt: [('impor', 'tant')]
PHJ18900501-V05-05-page26.txt: [('JOUR', 'NAL')]
PHJ18900501-V05-05-page32.txt: [('r', 'oo')]
PHJ18900601-V05-06-page27.txt: [('Christian', 'ia')]
PHJ18900601-V05-06-page29.txt: [('G', 'REAT')]
PHJ18900601-V05-06-page30.txt: [('o', 'ro')]
PHJ18900601-V05-06-page5.txt: [('re', 'garded')]
PHJ18900701-V05-07-page28.txt: [('P', 'AL')]
PHJ18900801-V05-08-page28.txt: [('ODE', 'LL')]
PHJ18900801-V05-08-page29.txt: [('Cata', 'logue'), ('l', 'id'), ('So', 'cial')]
PHJ18900801-V05-08-page4.txt: [('pun', 'ish')]
PHJ18900901-V05-09-page27.txt: [('N', 'ineteenth')]
PHJ18900901-V05-09-page28.txt: [('r', 'oo')]
PHJ18900901-V05-09-page31.txt: [('A', 'ddress')]
PHJ18901001-V05-10-page16.txt: [('LIQ', 'UOR')]
PHJ18901001-V05-10-page26.txt: [('CON', 'FLICT')]
PHJ18901001-V05-10-page27.txt: [('In', 'spiration')]
PHJ18901001-V05-10-page28.txt: [('D', 'aisy')]
PHJ18901101-V05-11-page28.txt: [('quart', 'IC'), ('C', 'lasp'), ('r', 'oo'), ('Supp', 'orter')]
PHJ18901101-V05-11-page31.txt: [('A', 'merican')]
PHJ18901201-V05-12-page14.txt: [('in', 'dulgences')]
PHJ18901201-V05-12-page25.txt: [('cir', 'culation')]
PHJ18901201-V05-12-page28.txt: [('r', 'oo')]
PHJ18901201-V05-12-page30.txt: [('LEA', 'THERETTE')]
PHJ18910101-V06-01-page13.txt: [('per', 'se')]
PHJ18910101-V06-01-page15.txt: [('and', 're')]
PHJ18910101-V06-01-page19.txt: [('to', 're')]
PHJ18910101-V06-01-page27.txt: [('exi', 'ts')]
PHJ18910101-V06-01-page28.txt: [('Do', 'mestic')]
PHJ18910101-V06-01-page30.txt: [('Assy', 'rian')]
PHJ18910101-V06-01-page32.txt: [('LEA', 'THERETTE'), ('corres', 'pondence')]
PHJ18910201-V06-02-page19.txt: [('b', 'ead')]
PHJ18910201-V06-02-page28.txt: [('t', 'oo')]
PHJ18910301-V06-03-page11.txt: [('to', 'ro')]
PHJ18910301-V06-03-page14.txt: [('sin', 'gularly')]
PHJ18910301-V06-03-page32.txt: [('LEA', 'THERETTE'), ('corres', 'pondence')]
PHJ18910401-V06-04-page1.txt: [('the', 're')]
PHJ18910401-V06-04-page32.txt: [('corres', 'pondence')]
PHJ18910501-V06-05-page2.txt: [('r', 'oo')]
PHJ18910501-V06-05-page3.txt: [('to', 'ro')]
PHJ18910501-V06-05-page31.txt: [('W', 'YLIE')]
PHJ18910501-V06-05-page32.txt: [('corres', 'pondence')]
PHJ18910601-V06-06-page10.txt: [('fever', 'ous'), ('r', 'oo')]
PHJ18910601-V06-06-page18.txt: [('per', 'se')]
PHJ18910601-V06-06-page19.txt: [('be', 'mis')]
PHJ18910601-V06-06-page25.txt: [('m', 'oistened')]
PHJ18910601-V06-06-page29.txt: [('med', 'ical')]
PHJ18910601-V06-06-page32.txt: [('corres', 'pondence')]
PHJ18910701-V06-07-page26.txt: [('JOUR', 'NAL')]
PHJ18910701-V06-07-page31.txt: [('I', 'LL')]
PHJ18910701-V06-07-page32.txt: [('LEA', 'THERETTE'), ('corres', 'pondence')]
PHJ18910801-V06-08-page27.txt: [('A', 'ND')]
PHJ18910801-V06-08-page32.txt: [('g', 'Lt'), ('T', 'ip'), ('corres', 'pondence')]
PHJ18910901-V06-09-page24.txt: [('lit', 'tle')]
PHJ18910901-V06-09-page28.txt: [('r', 'oo')]
PHJ18910901-V06-09-page29.txt: [('med', 'ical')]
PHJ18910901-V06-09-page32.txt: [('VI', 'NCENT')]
PHJ18911001-V06-10-page26.txt: [('No', 'rth')]
PHJ18911001-V06-10-page5.txt: [('bac', 'teria')]
PHJ18911001-V06-10-page6.txt: [('phys', 'ical')]
PHJ18911101-V06-11-page19.txt: [('prec', 'incts')]
PHJ18911201-V06-12-page14.txt: [('pres', 'ent')]
PHJ18911201-V06-12-page18.txt: [('treas', 'ure')]
PHJ18911201-V06-12-page22.txt: [('Chem', 'istry')]
PHJ18911201-V06-12-page28.txt: [('W', 'ASHINGTON')]
PHJ18911201-V06-12-page31.txt: [('o', 'ne'), ('IN', 'TRINSIC')]
PHJ18911201-V06-12-page33.txt: [('An', 'Ita')]
PHJ18911201-V06-12-page34.txt: [('z', 'oo')]
PHJ18920101-V07-01-page29.txt: [('THE', 'reat')]
PHJ18920101-V07-01-page31.txt: [('ad', 'mitted'), ('IN', 'TRINSIC')]
PHJ18920201-V07-02-page18.txt: [('sis', 'ters')]
PHJ18920201-V07-02-page21.txt: [('sec', 'ond')]
PHJ18920201-V07-02-page27.txt: [('prog', 'ress')]
PHJ18920201-V07-02-page5.txt: [('py', 'emia')]
PHJ18920201-V07-02-page7.txt: [('s', 'ubject')]
PHJ18920301-V07-03-page10.txt: [('r', 'epeated')]
PHJ18920301-V07-03-page18.txt: [('enjoy', 'ment')]
PHJ18920301-V07-03-page26.txt: [('I', 'Lk')]
PHJ18920301-V07-03-page31.txt: [('c', 'losed')]
PHJ18920401-V07-04-page12.txt: [('hope', 'ful')]
PHJ18920401-V07-04-page16.txt: [('per', 'fect')]
PHJ18920401-V07-04-page23.txt: [('char', 'acter')]
PHJ18920401-V07-04-page3.txt: [('the', 're')]
PHJ18920401-V07-04-page5.txt: [('in', 'flammation')]
PHJ18920501-V07-05-page20.txt: [('gen', 'erally')]
PHJ18920501-V07-05-page25.txt: [('cos', 'tumes')]
PHJ18920501-V07-05-page28.txt: [('T', 'HESE')]
PHJ18920501-V07-05-page31.txt: [('L', 'ithographic')]
PHJ18920601-V07-06-page21.txt: [('r', 'ie')]
PHJ18920801-V07-08-page31.txt: [('H', 'EALTH'), ('I', 'NA')]
PHJ18920801-V07-08-page4.txt: [('expen', 'diture')]
PHJ18920901-V07-09-page10.txt: [('de', 'preciated')]
PHJ18920901-V07-09-page29.txt: [('and', 're')]
PHJ18920901-V07-09-page31.txt: [('H', 'EAL'), ('U', 'nderwear')]
PHJ18921001-V07-10-page30.txt: [('w', 'ith')]
PHJ18921001-V07-10-page31.txt: [('G', 'ev')]
PHJ18921001-V07-10-page7.txt: [('MED', 'ICAL')]
PHJ18921101-V07-11-page16.txt: [('T', 'ue')]
PHJ18921101-V07-11-page25.txt: [('descrip', 'tions')]
PHJ18921101-V07-11-page28.txt: [('s', 'ith')]
PHJ18921101-V07-11-page31.txt: [('H', 'EALTHFUL')]
PHJ18921201-V07-12-page11.txt: [('ene', 'mies')]
PHJ18921201-V07-12-page15.txt: [('THE', 'BA')]
PHJ18921201-V07-12-page31.txt: [('H', 'EALTHFUL'), ('excursion', 'ists')]
PHJ18921201-V07-12-page32.txt: [('t', 'reatment')]
PHJ18921201-V07-12-page34.txt: [('sum', 'ption')]
PHJ18921201-V07-12-page4.txt: [('sup', 'posedly')]
PHJ18921201-V07-12-page5.txt: [('es', 'pecially')]
PHJ18960101-V11-01-page19.txt: [('JOUR', 'NAL')]
PHJ18960101-V11-01-page29.txt: [('A', 'VE')]
PHJ18960101-V11-01-page32.txt: [('Pro', 'fessions')]
PHJ18960101-V11-01-page7.txt: [('a', 're')]
PHJ18960201-V11-02-page19.txt: [('com', 'fortable'), ('health', 'ful')]
PHJ18960301-V11-03-page24.txt: [('U', 'RN')]
PHJ18960601-V11-06-page29.txt: [('Y', 'ork')]
PHJ18960601-V11-06-page31.txt: [('CIR', 'CUIT')]
PHJ18960701-V11-07-page10.txt: [('par', 'ticularly')]
PHJ18960701-V11-07-page25.txt: [('sub', 'sistence')]
PHJ18960701-V11-07-page3.txt: [('develop', 'ment')]
PHJ18960701-V11-07-page31.txt: [('LA', 'ND')]
PHJ18960701-V11-07-page7.txt: [('con', 'tagious')]
PHJ18960801-V11-08-page19.txt: [('med', 'ical')]
PHJ18960801-V11-08-page3.txt: [('com', 'pany')]
PHJ18960801-V11-08-page32.txt: [('o', 'ng')]
PHJ18960801-V11-08-page5.txt: [('or', 'zo')]
PHJ18960901-V11-09-page4.txt: [('in', 'duced')]
PHJ18960901-V11-09-page5.txt: [('a', 'nd')]
PHJ18961001-V11-10-page2.txt: [('the', 're')]
PHJ18961001-V11-10-page27.txt: [('con', 'stant')]
PHJ18961001-V11-10-page30.txt: [('c', 'hile')]
PHJ18961101-V11-11-page32.txt: [('I', 'll')]
PHJ18961201-V11-12-page12.txt: [('p', 'istil')]
PHJ18961201-V11-12-page28.txt: [('P', 'olish')]
PHJ18990101-V14-01-page1.txt: [('JouR', 'NAL')]
PHJ18990101-V14-01-page14.txt: [('req', 'uest')]
PHJ18990101-V14-01-page15.txt: [('A', 'NEM')]
PHJ18990201-V14-02-page12.txt: [('prop', 'erties')]
PHJ18990201-V14-02-page9.txt: [('consist', 'ently')]
PHJ18990301-V14-03-page19.txt: [('JoUR', 'NAL')]
PHJ18990301-V14-03-page5.txt: [('con', 'trast')]
PHJ18990601-V14-06-page13.txt: [('Whip', 'poorwill')]
PHJ18991001-V14-10-page2.txt: [('alco', 'holic')]
PHJ18991101-V14-11-page19.txt: [('sug', 'gestion')]
PHJ18991101-V14-11-page2.txt: [('R', 'ussia')]
PHJ19010201-V16-02-page12.txt: [('CHRIS', 'TIAN')]
PHJ19010201-V16-02-page2.txt: [('I', 'wo')]
PHJ19010201-V16-02-page21.txt: [('A', 'LT'), ('H', 'OW')]
PHJ19010301-V16-03-page27.txt: [('d', 'Ie')]
PHJ19010301-V16-03-page30.txt: [('p', 'acific')]
PHJ19010401-V16-04-page1.txt: [('w', 'itt')]
PHJ19010401-V16-04-page33.txt: [('A', 'NE'), ('C', 'ItE')]
PHJ19010401-V16-04-page34.txt: [('chron', 'ic')]
PHJ19010501-V16-05-page36.txt: [('a', 'll')]
PHJ19010601-V16-06-page45.txt: [('I', 'NG')]
PHJ19010601-V16-06-page49.txt: [('a', 'nd')]
PHJ19010701-V16-07-page23.txt: [('W', 'ashington')]
PHJ19010701-V16-07-page9.txt: [('so', 'weth')]
PHJ19010801-V16-08-page20.txt: [('D', 'RESS')]
PHJ19010801-V16-08-page28.txt: [('en', 'gine')]
PHJ19010801-V16-08-page33.txt: [('C', 'ap'), ('p', 'acific')]
PHJ19010801-V16-08-page4.txt: [('E', 'ff')]
PHJ19010901-V16-09-page30.txt: [('r', 'EP')]
PHJ19010901-V16-09-page31.txt: [('C', 'tn')]
PHJ19011001-V16-10-page26.txt: [('LE', 'GENDRE')]
PHJ19011101-V16-11-page2.txt: [('Deli', 'cious'), ('lit', 'tle')]
PHJ19011101-V16-11-page3.txt: [('SAD', 'LER')]
PHJ19011101-V16-11-page30.txt: [('t', 'il')]
PHJ19011201-V16-12-page16.txt: [('JO', 'URNAL')]
PHJ19011201-V16-12-page2.txt: [('lit', 'tle')]
PHJ19011201-V16-12-page3.txt: [('C', 'apitol')]
PHJ19011201-V16-12-page39.txt: [('R', 'IGHTED')]
PHJ19020201-V17-02-page2.txt: [('con', 'venient')]
PHJ19020301-V17-03-page27.txt: [('preven', 'tive')]
PHJ19020301-V17-03-page35.txt: [('C', 'ItE'), ('R', 'IGHTED')]
PHJ19020301-V17-03-page36.txt: [('P', 'acific')]
PHJ19020401-V17-04-page34.txt: [('O', 'ffer')]
PHJ19020601-V17-06-page13.txt: [('SAN', 'ITARIUM')]
PHJ19020601-V17-06-page32.txt: [('ST', 'ENCILS'), ('BRAN', 'DS')]
PHJ19020601-V17-06-page37.txt: [('cor', 'onation')]
PHJ19020801-V17-08-page28.txt: [('JOUR', 'NAL')]
PHJ19020801-V17-08-page30.txt: [('Y', 'ork')]
PHJ19020901-V17-09-page31.txt: [('BRAN', 'DS')]
PHJ19021001-V17-10-page31.txt: [('M', 'adison')]
PHJ19021001-V17-10-page34.txt: [('BRA', 'NCH')]
PHJ19021101-V17-11-page12.txt: [('H', 'ygienic')]
PHJ19021101-V17-11-page29.txt: [('M', 'ariposa')]
PHJ19021101-V17-11-page31.txt: [('HEAL', 'TH'), ('P', 'ACIFIC')]
PHJ19021101-V17-11-page36.txt: [('R', 'UN')]
PHJ19021201-V17-12-page30.txt: [('M', 'ariposa')]
PHJ19030101-V18-01-page2.txt: [('r', 'oo')]
PHJ19030101-V18-01-page27.txt: [('OR', 'THOPEDIC')]
PHJ19030101-V18-01-page30.txt: [('A', 'uthority')]
PHJ19030101-V18-01-page34.txt: [('Health', 'ful')]
PHJ19030101-V18-01-page35.txt: [('I', 'ri')]
PHJ19030101-V18-01-page4.txt: [('H', 'ip')]
PHJ19030201-V18-02-page25.txt: [('JouR', 'NAL')]
PHJ19030501-V18-05-page24.txt: [('JOUR', 'NAL')]
PHJ19030501-V18-05-page34.txt: [('a', 'id')]
PHJ19030501-V18-05-page35.txt: [('A', 'Ny')]
PHJ19030701-V18-07-page20.txt: [('a', 'zo')]
PHJ19030701-V18-07-page24.txt: [('char', 'acter')]
PHJ19030701-V18-07-page28.txt: [('JOUR', 'NAL')]
PHJ19030801-V18-08-page33.txt: [('IN', 'CL')]
PHJ19031101-V18-11-page32.txt: [('C', 'hicago')]
PHJ19031201-V18-12-page35.txt: [('IN', 'ti')]
PHJ19040101-V19-01-page1.txt: [('AT', 'TA')]
PHJ19040201-V19-02-page28.txt: [('W', 'hile')]
PHJ19040201-V19-02-page8.txt: [('j', 'uices')]
PHJ19040301-V19-03-page31.txt: [('BOO', 'KS'), ('A', 'nal')]
PHJ19040401-V19-04-page28.txt: [('HA', 'IG')]
PHJ19040501-V19-05-page33.txt: [('East', 'ern')]
PHJ19040501-V19-05-page34.txt: [('pam', 'phlet')]
PHJ19040601-V19-06-page27.txt: [('I', 'Lk')]
In [32]:
# %load shared_elements/summary.py
summary = GoH.reports.overview_report(directories['cycle'], spelling_dictionary, title)
Directory: /Users/jeriwieringa/Dissertation/text/text/2017-01-31-corpus-with-utf8-split-into-titles-cleaning/PHJ/correction7 Average verified rate: 0.9812578035460998 Average of error rates: 0.02651921795156632 Total token count: 2849666
In [33]:
# %load shared_elements/top_errors.py
errors_summary = GoH.reports.get_errors_summary( summary )
GoH.reports.top_errors( errors_summary, 10 )[:50]
Out[33]:
[('m', 2724),
('d', 2324),
("'", 1997),
('e', 1380),
('r', 1248),
('t', 1203),
('w', 1166),
('n', 1118),
('co', 1109),
('f', 795),
('g', 759),
('x', 648),
('lb', 583),
('sel', 251),
('th', 250),
('mo', 230),
('oo', 222),
('pp', 218),
('z', 215),
('k', 214),
('u', 196),
("an'", 192),
('q', 132),
('ex', 106),
('ournal', 105),
('al', 94),
('te', 85),
('oz', 81),
('ga', 80),
('ro', 77),
('pa', 74),
('va', 74),
('munn', 73),
('io', 72),
('-', 66),
('ti', 66),
("infants'", 61),
('id', 55),
('viperance', 54),
('zo', 53),
('em', 53),
('tion', 51),
("''", 49),
('si', 47),
('urnal', 47),
('fahr', 46),
('cc', 45),
("hours'", 44),
('cloe', 43),
('tt', 42)]
Review Remaining Errors¶
In [34]:
GoH.reports.docs_with_high_error_rate(summary)
Out[34]:
[('PHJ19030301-V18-03-page4.txt', 1.0),
('PHJ19030201-V18-02-page4.txt', 1.0),
('PHJ19030501-V18-05-page4.txt', 0.744),
('PHJ19030401-V18-04-page35.txt', 0.719),
('PHJ19040201-V19-02-page4.txt', 0.667),
('PHJ19030901-V18-09-page4.txt', 0.632),
('PHJ19021201-V17-12-page4.txt', 0.6),
('PHJ19030101-V18-01-page35.txt', 0.556),
('PHJ18870801-V02-08-page1.txt', 0.468),
('PHJ19011201-V16-12-page4.txt', 0.429),
('PHJ19011201-V16-12-page3.txt', 0.388),
('PHJ18870201-V02-05-page1.txt', 0.376),
('PHJ19010201-V16-02-page33.txt', 0.375),
('PHJ18870401-V02-06-page1.txt', 0.355),
('PHJ18860801-V02-02-page1.txt', 0.354),
('PHJ18861201-V02-04-page1.txt', 0.35),
('PHJ19010701-V16-07-page13.txt', 0.311),
('PHJ18871001-V02-09-page1.txt', 0.309),
('PHJ18870601-V02-07-page1.txt', 0.308),
('PHJ18861001-V02-03-page1.txt', 0.297),
('PHJ19031201-V18-12-page35.txt', 0.274),
('PHJ19011001-V16-10-page33.txt', 0.267),
('PHJ19021101-V17-11-page36.txt', 0.264),
('PHJ19011201-V16-12-page2.txt', 0.259),
('PHJ19031201-V18-12-page4.txt', 0.257),
('PHJ19010501-V16-05-page35.txt', 0.248),
('PHJ19010301-V16-03-page33.txt', 0.246),
('PHJ19030901-V18-09-page35.txt', 0.243),
('PHJ19030201-V18-02-page35.txt', 0.243),
('PHJ18880501-V03-05-page32.txt', 0.241),
('PHJ19030301-V18-03-page33.txt', 0.24),
('PHJ19020801-V17-08-page36.txt', 0.234),
('PHJ19010701-V16-07-page31.txt', 0.232),
('PHJ19010801-V16-08-page30.txt', 0.229),
('PHJ19040201-V19-02-page35.txt', 0.229),
('PHJ19040301-V19-03-page29.txt', 0.227),
('PHJ19011001-V16-10-page31.txt', 0.225),
('PHJ19010901-V16-09-page33.txt', 0.225),
('PHJ19030301-V18-03-page35.txt', 0.223),
('PHJ19020901-V17-09-page1.txt', 0.222),
('PHJ19010801-V16-08-page33.txt', 0.222),
('PHJ19030601-V18-06-page30.txt', 0.219),
('PHJ19010401-V16-04-page30.txt', 0.215),
('PHJ19010201-V16-02-page30.txt', 0.215),
('PHJ19010501-V16-05-page32.txt', 0.214),
('PHJ19020901-V17-09-page4.txt', 0.211),
('PHJ19010701-V16-07-page33.txt', 0.21),
('PHJ19020501-V17-05-page1.txt', 0.21),
('PHJ19020401-V17-04-page1.txt', 0.208),
('PHJ19031201-V18-12-page32.txt', 0.207),
('PHJ19030701-V18-07-page35.txt', 0.205),
('PHJ18880201-V03-02-page27.txt', 0.205),
('PHJ19020301-V17-03-page1.txt', 0.203),
('PHJ19010901-V16-09-page31.txt', 0.203),
('PHJ19011101-V16-11-page35.txt', 0.203)]
In [35]:
# %load shared_elements/high_error_rates.py
doc_keys = [x[0] for x in GoH.reports.docs_with_high_error_rate(summary) if x[1] > 0.4]
GoH.utilities.open_original_docs(doc_keys, directories['cycle'])
Opened files: PHJ19030301-V18-03-page4.txt PHJ19030201-V18-02-page4.txt PHJ19030501-V18-05-page4.txt PHJ19030401-V18-04-page35.txt PHJ19040201-V19-02-page4.txt PHJ19030901-V18-09-page4.txt PHJ19021201-V17-12-page4.txt PHJ19030101-V18-01-page35.txt PHJ18870801-V02-08-page1.txt PHJ19011201-V16-12-page4.txt
Mostly image pages.
In [36]:
GoH.reports.long_errors(errors_summary, min_length=15)
Out[36]:
(['sanitaryshnitary', "english'temperance", 'restaurant-stand', 'wefurnishpatternsforhigh', 'acccoommodations', 'good-for-nothing', 'iiiiietaiiawrialauumnamumaymmo', 'queen-of-the-queens', 'gradual-reduction-process', 'itchialrractaerned', 'three-sixteenths', 'artificially-fed', 'three-hundredths', 'gilmniiiimmiumffinum', 'whisky-drunkards', 'perfectly-constructed', 'gently-stimulating', 'divinely-appointed', "paid'advertisements", 'mnuamanenummonami', 'non-crystallizable', 'mminiminnecatalogue', 'supersensitiveness', 'originallyjnvestigated', 'household-helpers', 'aermotorwindmills', "thesd'habitliabits", 'rosy-complexioned', 'sanitariumsanitarium', 'health-promoting', 'deudnsidtnaigntges', 'public-spiritedness', 'advertielderitiderb', 'unconditionaltly', 'pleasure-seekers', 'not-afraid-of-the-rain', 'accomplishmentwhichhascomevery', 'self-preservation', 'heaven-appointed', 'over-consumption', 'avoiddanarousbarbi', 'prayer-answering', 'souland-body-destroying', 'maid-of-all-work', 'never-seen-flirting', 'imperfectlycleansed', 'ewditchaunneoxctoepietiron', 'sulphur-bleaching', 'partially-filled', 'whitewhitekorackers', 'localititecalities', 'moisture-absorbing', 'intercommunicability', 'voitesooprieffsioretooneadrress', 'arigrirralenrillitmonown', 'absent-mindedness', 'ingsliimiediullivigi', 'non-contagiousness', 'sanitaritnnitarium', 'alcohol-poisoned', 'rapidly-increasing', 'become-estranged', "subject--mother's", 'muscle-producing', 'helenasanitarium', 'commonly-received', 'twenty-hundredths', 'nerve-strengthening', 'contented-looking', 'wholesale-liquor-dealer', 'pacificpresspublishinghouse', 'foundation-stone', 'mitimiiiiiiiiiiimmitutimmiticium', 'spanish-american', 'time-and-strength-exhausting', 'barbarsympathize', 'several-months-old', 'badly-ventilated', 'lucas-championniere', 'better-befitting', 'properly-fitting', 'xjkivivwplyofurt', 'picture-of-health', 'regularly-graduated', 'maiden-in-her-teens', 'perfectsaanction', 'ilintirlitifillairirtigillitiffitiffestitfir', 'feather-stitched', 'delicatelybalanced', 'little-suspected', 'physician-in-chief', 'poisonoussubstances', 'firtuanfiireilitiid', 'commander-in-chief', 'whilecross-examining', 'quickly-repeated', 'different-colored', 'castro-intestinal', 'unremunerativeloans', 'stronglyflavored', 'needsintelligence', 'criminalcarelessness--getting', 'at-home-in-her-place', 'givenfromcatholi', 'lungs-and-stomach', 'ernecewaotnigdirlywanossphet', 'easily-assimilated', 'self-examination', 'heavenly-wrought', 'anti-stimulating', 'gymnasiyinnasium', 'taste-preference', "sunday-morning's", 'newhomesewingmachinerorange', 'long-believed-in', 'nerve-destroying', 'gradually-developed', 'over-accumulation', 'tetextbaoicinary', 'mprohibitioncampaignexchange', 'xotimutimootxxximaklasimmitarmalemmunot', 'wear-her-own-hair', 'oftencircumstances', 'umninmalimenuilig', 'theruralhealtehtrerat', 'freshly-slaughtered', 'peculiarly-arranged', 'cleverly-executed', 'properly-performed', 'chemicallytreated', 'duringthechristian', 'soul-and-body-destroying', 'eecliceizliecouizieificinciimic', 'sewage-contaminated', 'fellow-prisoners', 'supercarbonization', 'mrprohibitioncampaignexchange', 'kloxfpaperkifriu', 'aplebaredsohlaubtitonstriasiaglhl', 'eiscehviniisbtos', 'life-ioliifeciistig', 'whole-wheat-flour', 'starch-digesting', 'rvfirrtprmflftitiiifirt', 'self-destructive', "consolation'that", 'mampormitylifighlimirummx', 'alpequckaabuckles', 'considerieguttieeenig', 'skirt-supporting', 'abstidegeneration', 'vegetable-colored', 'cream-bespattered', 'iihwalithlipainful', 'goodhealthrestaurant', 'free-from-a-stare', 'fifteen-hundredths', 'christirailitniifi', 'stenographlicaly', 'properly-regulated', 'half-unconscious', 'closely-corseted', 'fifteen-hundredth', 'comfortablycircumstanced', 'ficilirifirrefrfittifiefewitivi', 'raspberry-banana', 'future-most-fair', 'finely-pulverized', 'morodlaitiestaco', 'itithnffiffiefinfficiently', 'thrashing-machine', 'great-grandchildren', 'neiromesewingmachinea', 'motor-depressant', 'iontrontriustrororsummi', 'highly-stimulating', 'cifahrilrilfstry', 'health-and-life-destroying', 'frequently-repeated', 're-establishment', 'self-control--not', 'higgledy-piggledly', "'non-compensation'", 'suffiexperiments', 'boa-constrictors', 'greatgrandmothers', 'character-shaping', 'painkillezejkillers', 'becomeintelligent', 'tastefully-decorated', 'dramshop-keepers', 'dyspepsia-producing', 'conscience-stricken', 'photo-engravings', 'wanglannantinampanagamatt', 'charactershaping', 'pressure-induced', 'trichina-infested', 'carefully-watched', 'pacificpresspublishingrouseoaldgildcal', 'literadestruction', 'volcanic-scarred', 'whochangedthesabbath', 'vegetable-eating', 'altogether-too-common', "formingasidetableforsim'sposition", 'husband--personal', 'siltooftugllezre', "little'understood", 'is-reladiefitched', 'auto-intoxication', 'bread-and-butter', 'satisfacantiseptic', 'delicately-formed', 'twenty-threeinch', 'instruction-book', 'pleasantdisinfectant', 'improperlywashed', 'ever-accelerating', 'informationladdress', 'dateand-barley-eating', 'nefftittiattivid', 'ilimunaiwilmiumumiumilmm', 'quickly-shifting', 'fever-engendering', 'rhrmeusmoaftidsm', 'well-disciplined', 'lttlitlyamtkilletaitaillitialaailkill', 'birds-of-paradise', 'penny-in-the-slot', 'clothtscgtiliehlbf', 'non-professional', 'auto-suggestions', 'goldengolilawnbrown', 'scientifically-conducted', 'africa-international', 'medico-chirurgical', 'gradual-reduction', 'iikrtgninpcelruagrev', 'barbaphysiologists', 'iftriirittialiimi', 'fellow-travelers', 'poison-destroying', 'carefully-regulated', 'ouriarcilitiesare', 'self-gratification', 'uummairruilumounammor', 'free-from-the-blues', 'poorly-ventilated', 'counter-arguments', 'theonlysewingmachine', 'partially-cooked', 'familypresenting', 'powerpowirinanduinactive', 'heat-and-force-producing', 'go-as-you-please', 'photo-lithography', 'alkaloid-containing', "'mama-don'tlove-her-little-angel-baby-no-more-'tall", 'great-grandfather', 'hypochondriachal', 'recomaeznaiedufnded', 'andlurntshesheal', 'prekrioeetcribed', 'alai-extraordinary', 'reformationsburg', 'mountain-climbers', 'non-intoxicating', 'sought-everywhere', 'regularlyprescribed', 'sltlortrshrirteried', 'tiktio-stringent', 'thepitoirtrolblattt', 'commandment-keeping', 'rapidly-advancing', 'titmemommiffitriliii', 'cliinoindhwialtceh', 'evcetrsyahroeuwsheosledt', 'easily-digestible', 'appetizinerreatniogtheningbreakfast', 'selfcomplaisance', 'litiadziaidpeizially', 'fellow-passengers', 'long-to-beremembered', 'thoroughly-cooked', 'newhomesewingmachineaortinge', 'lawrillifiliaminiwi', 'forraravageikraitarnviccimuli', 'selfaggrandizement', 'naelstnoonwhenarlithr', 'thoroughly-educated', 'mitantviactuvinl', 'total-abstinence', 'mmtvmszkommommeszmmtimmotmectoot', 'alcoholic-poisoned', 'quickly-workedoff', 'over-development', 'all-falling-to-pieces', 'nmagamangearateannitm', 'nerve-prostration', 'carefullyarranged', 'mommirmeneeruton', 'innocent-hearted', 'chemically-changed', 'ingeniously-devised', 'melxximarantemennzeuta', 'substittatbstitutdisper', 'suffereduffrocal', 'auto-intoxications', 'xvimiiminimmilklakm', 'pertectsatizicroy', 'arterio-sclerosis', 'eltellimiticlarnonxiimpewommirm', 'kardobenedictenkraut', 'sweet-dispositioned', 'minding-my-own-business', 'wholftnthialeavitheat', 'pleasure-seeking', 'carefullycontrolled', 'kreislaufstbrungen', 'cabbage-soup-andrye-bread-eating', 'disease-carrying', 'wasatworkonafarmfor', 'elaborately-decorated', 'oatmtkitilieallbiscuit', 'rprohibitioncampaignexchange', 'uraragarararrarrarrantatti', 'mechano-therapeutics', 'inter-dependence', 'practically-balanced', 'platindatittneal', 'iimunmiumfdialemumammumaniumu', 'extensively-used', 'antdehmeamerrlmattete', 'kitchenspoonfuls', 'would-be-hygienist', 'contaiaonitiiituidthing', 'poorly-constructed', 'faraerelimmammenixamievn', 'waste-not-an-hour', 'good-for-nothings', 'supernormally-imparted', 'non-grape-producing', 'narrow-mindedness', 'ivremilawritaxtomitsmeati', 'tender-heartedness', 'self-development', 'prescription-book', 'coarsely-prepared', 'elaborately-wrought', 'novtigigtgeowawavanwinumagtgtgtagtel', 'velkistrciffirst', "woman'sjournalof", 'progress-evoking', 'diseaseproducing', 'tobacco-saturated', 'develiiptreieszensoteadndfotrheitsa', 'tubular-contracted', 'tobacco-consumers', 'miummiiniimimmormilleirimmunipm', 'no-neck-to-her-dress', 'pfrfectsamiction', 'honestly-courting', 'antedineveranyshow', 'constantly-growing', 'respectably-dressed', 'self-satisfaction', 'ithemnpromisingly', 'consumptionbreeding', 'carefully-selected', 'physio-mechanism', 'sharply-indicated', 'reccommendations', 'asitlitlattialdr', 'cbtherideletenious', 'fashionable-dressed', 'nagnatematmantgatsmage', 'artificially-induced', 'thought-producing', 'secretary-general', 'red-lips-so-delicious', 'mosquito-breeding', 'self-eliminative', 'self-destruction', 'icooxynizzionearea', 'frightfully-coated', 'magneto-conservative', 'transmissibility', 'non-tobacco-using', 'ofiatioifuettiquette', 'sulphur-bleached', 'fashionably-attired', 'ttitttttttttittitt', 'pleasant-mannered', 'naudeekliitfokliiitokittiti', 'self-administration', 'mommevetmormaarvottnkwakomeinkatit', 'suddenly-occurring', 'registrar-general', 'early-contracted', 'finely-developed', 'physiinstruments', "housek'eapigkceper", 'soul-development', 'electro-chemical', 'trichina-spiralis', 'one-hundred-foot', 'one-five-hundredth', 'chemically-prepared', 'freshly-prepared', 'sensitively-organized', 'frequently-changed', 'much-to-be-pitied', 'self-sympathizer', 'dolewhooping-cough', 'helenasanitariumrs', 'pivectsatiention', 'immediatelyremoved', 'iiiififiiiiiiiiii', 'rapidly-multiplying', 'slaughter-houses', 'companion--assistance', 'one-three-hundredth', 'ameraccomplished', 'trviavommxtrvargurgsat', 'prettytypewriter', 'quiteindigestible', 'thoroughlywarmed', 'prematpzernature', 'diseasecleanliness', 'constantlyincreasing', 'inspector-general', 'stimulo-sedative', 'divinely-ordained', 'pivectsatistiction', 'bacon-shakespeare', 'suiilliirhuthbert', 'breast-nourished', 'butthebodywithoutasoulisonlya', 'instructions-with', 'unself-consciousness', 'irregularly-shaped', 'set-em-up-all-round', 'strength-imparting', 'dujardin-beaumetx', 'curawarararanzatararom', 'physibroken-down', 'newhomesewingmachineco', 'anti-constipation', 'unamaniummumumusa', 'ctluiwaeffemmeinettneffeixorg', 'self-disciplined', 'over-sentimental', 'three-thousandth', 'nnonoranningrinnuncarannonciationcimannoroarancinempzinntn', "it'swuffmoretome", 'shortesladrtedexit', 'divinelyappointed', 'rereconstruction', 'near-sightedness', "temperate'thaliits", 'srzanlleeonfditorfedthuecet', 'nutrition-drawing', 'drictithietitstfrd', 'wealth-producers', 'self-registering', 'swiftlydeparting', 'fairly-developed', 'ctimiopripliardeaey', 'shippedererywhere', 'pageillustratthns', 'pertectsatanction', 'esteemeriftiseed', 'tausendguldenkraut', 'homesewingmachineaorangemass', 'innocent-looking', "school-children's", 'long-established', 'pleuro-pneumonia', 'counteractedcrbyted', 'thirst-creatingpower', 'wevonelitlitrakliailiamem', 'rirtroriffirirvi', 'ritresctesvaerreypir', 'aamenontmenalwanunionawaimmatatatem', 'tifitoilioffileigioulders', 'childreehiltiffitig', 'sundltedablaclei', 'willebcuyathefsordirolllratoicrp', 'carelessness--getting', 'delicately-furnished', 'poorly-nourished', 'pfreectsatisfiction', 'newhomesewingmachine', 'ourfacilitiesare', 'pageillustrations', 'equally-important', 'delleatelelicate', 'health-restoring', 'arrowroot-starch', 'well-intentioned', "remedial'measures", 'well-advertising', 'poison-producing', "superintendents'", 'three-months-old', 'eighteenth-century', 'brotherly-kindness', 'dujardin-beaumetz', 'fignuassigumffinquirsi', 'nineteen-twentieths', 'wonderfully-taking', 'short-sightedness', 'wiffinwowhiiiiiwiffeffitivil', 'steadily-increasing', 'intellivibrations', 'fiteltkeinieftneinng', 'precedingpreparations', 'before-described', 'imperfectlymasticated', 'generous-hearted', 'otettettentuovel', 'oteefcleittuttve', 'permanently-established', 'imperfectly-cooked', 'hunger-headaches', 'glosso-pharyngeal', 'theircrispnessitmayberestoredbyplacingtheminahotovenfor', 'bitreieszensoteadndfotrheitsagsuernecewaotrilidirlywanossphety', 'fellow-countryman', 'weakielleliklmeisink', 'immegeographical', 'passion-stimulating', 'oxygenaijealtigul', 'health-destroyer', 'raabritioonfoffotealthful', 'continually-multiplying', 'well-proportioned', 'one-twenty-fifth', 'skilfully-worded', 'largely-experienced', 'hislitthitherother', 'erhbat-embarrassment', 'ciliimmuciziolic', 'householddictionary', 'cruelly-ignorant', 'artificially-colored', 'holonaqanitariutre', 'micro-photographs', 'needle-and-thread', 'noarffillptdally', 'maktbtlignietthet', 'requiremultiplies', 'maize-and-macaroni-eating', 'healthdestroying', 'semi-occasionally', 'comfortable-feeling', 'brownsugarinwhichahalfteaspoonpulverized', 'tissuepaper-like', 'non-self-consciousness', 'corresfiondenz-blatt', 'artificially-heated', 'at-ten-in-her-bed', 'insponsibilities', 'austro-hungarian', 'shorteshortenekutor', 'tempercelebrated', 'acquire-strength', 'turn-up-the-nose', 'self-reliant-looking', 'four-thousandths', 'dangerouslycontaminated', 'gastro-intestinal', 'illy-constructed', 'skillfully-contrived', 'nvenoutiottnnamonivemmaigaramitmm', 'theaqties-question', 'linlsistimisisted', 'cunningly-perverted', 'poorly-developed', 'smoothly-polished', 'carefully-tested', 'church-membership', 'berrenger-ferroud', 'pondeneestrictly', 'intinixtivillytively', 'partiallyreleased', 'recently-discovered', 'constipation-its', 'ricememeicecomememizimicimmiiiiiiimoccemidemei', 'experienexperience', 'semi-unconsciousness', 'greatgrandmother', 'perfettly-dressed', 'widely-differing', 'generally-accepted', 'strength-testing', 'needle-andthread', 'distillery-slops', 'cruelly-accurate', 'disease-bringing', 'agairksqlfbcpthe', 'poison-eliminating', 'forsimplicityitbeatatheworld', 'twenty-five-inch', 'sanfranciscoagents', 'nineteenth-century', 'opportuthemselves', 'stomaciitontstoki', 'thoroughlyorganized', 'molonnolommudoonnutot', "''''''''''''''''", 'descriptivearticles', 'cotemporaneously', 'sttflkikokiftnwtiolen', 'unconscientiously', 'splendid-looking', 'flower-bouquet-like', 'broad-shouldered', 'consumptive-looking', 'intendedtaitlkdsithei', 'counter-irritant', 'comsuperstitions', 'temperately-worded', 'catarrh--laceration', 'highly-developed', 'suitedtomanyuses', 'eighty-and-eight', 'properly-conducted', 'delicately-reared', 'howtodresshealthfully', 'non-commissioned', 'eight-hundredpound', 'semi-intoxication', 'yellow-fever-like', 'closely-arranged', 'ceionametiamanammutanda', 'contra-indicated', 'dabclitsittliblished', 'pertectsatisfiction', 'earnestly-written', 'police-headquarters', 'noncommunicability', 'poverty-stricken', 'ultra-fashionable', 'carlyledescribed', 'noncrystallizable', 'straight-jackets', 'norway-sundhedabladat', 'self-renunciation', 'iforinciratnoral', 'gris-amber-steamed', 'handsomely-bound', 'super-excitation', 'gorgeously-dressed', 'newspaper-covered', 'slaughtering-places', 'selfsatisfaction', 'fifteen-year-old', "mothers'meetings", 'htenanitariantsm', 'akfastmereekfast', 'carefully-prepared', 'strangely-poised', 'spiritualeffectsofintemperance', 'oliver-twistlike', 'boiledwheat-and-fruit-eating', 'properly-prepared', 'nicely-cushioned', 'health-andlife-destroying', 'whitepublishingco', 'motherrecognized', 'generalattention', 'wine-drinking-for-dyspepsia', 'hlenfulltarianism', 'life-restricting', 'wasthrownintoanunfrequented', 'iiicigslirplelasure', 'great-great-great-great-grandchildren', 'compensatoryluxury--the', 'bfilvilarliftightklalthiglitilaritiontintarablanklm', 'fiddle-sticksrsaid', 'sonntnncvccocnnnosc', 'slightly-rounded', 'mionviimillimarkliblogemtialk', 'slaughtering-place', 'witagitiniftititiat', 'thread-and-needle', 'world-conquering', 'wellproportioned', 'health-bestowing', 'character-making', 'scientifically-demonstrated', 'thoroughly-applied', 'rapidly-developing', 'sanguiniolymphatic', 'self-maintenance', 'star-like-shaped', 'self-distrusting', 'additiohtuddition', 'properly-directed', 'skillfully-prepared', 'aerillaissithsbugh', 'wanteweverycounty', 'frifreelirdindird', 'malaria-poisoned', 'yellowish-colored', 'ilimmusiinunaimmumwmeneu', 'widely-advertised', 'aamognmuenitainftwomatualenamman', 'well-authenticated', 'scientificamerican', 'rapidlydeveloping', "constitunature's", 'lactid-acid-containing', 'everaccelerating', 'highly-organized', 'mentho-formoline', 'ifinfifttlicfiffeitivef', 'onthsallshallbecomeyourown', 'commonly-recognized', 'thltisecthsinerispness', 'nnntvvionniccnnnwkwx', 'whiskybesprinkled', 'abnakawwahyeiirounsinsfdsetiori', 'irregular-shaped', 'sineottlievatell', 'fellow-passenger', 'slfiesiiiwisecibade', 'liberallyfurnished', 'glosso-pharvngeal', 'dead-horse-flesh-fattened', 'house-furnishing', 'vapor-inhalation', 'rapidly-spreading', 'princess-of-peace', 'magazinecontains', 'etheonlysewingmachine', 'health-destroying', 'pfriectsatanction', 'question-scavengers', 'electro-therapeutics', 'twenty-four-page', 'electro-therapeutic', 'self-preservashun', 'imimmosummworanicvnimmaixiimicil', 'wine-drinkingfor-dyspepsia', 'strength-producing', 'chititleethildren', 'dyspepsia-breeding', 'iint-strattitstick', 'noixoffeacitexcmicam', "pivects'ataniction", 'cheap-jewel-flash', 'street-sweepings', 'winnegar-simpson', 'super-oxygenates', 'zealand-international', 'cadaverous-looking', 'counter-indicated', 'well-illustrated', 'underciftimmtfrilileg', 'self-purification', 'newly-discovered', 'anti-gkettiagottruipation', 'beautifully-rounded', 'consumpabstainers', 'defectively-lighted', 'thought-pictures', 'favorably-conducted', 'apparently-relieved', 'properlyregulated'], 15)
Correction 8 -- Remove long tokens¶
In [37]:
# %load shared_elements/remove-tokens-with-long-strings-of-characters.py
prev = "correction7"
cycle = "correction8"
directories = GoH.utilities.define_directories(prev, cycle, base_dir)
if not os.path.exists(directories['cycle']):
os.makedirs(directories['cycle'])
corpus = (f for f in listdir(directories['prev']) if not f.startswith('.') and isfile(join(directories['prev'], f)))
for filename in corpus:
content = GoH.utilities.readfile(directories['prev'], filename)
text = re.sub(r"[0-9,!?$:;&]", " ", content)
tokens = GoH.utilities.tokenize_text(text)
replacements = []
replacements.append(GoH.clean.check_for_repeating_characters(tokens, "i|I"))
replacements.append(GoH.clean.check_for_repeating_characters(tokens, "m|M"))
replacements.append(GoH.clean.check_for_repeating_characters(tokens, "n|N"))
replacements.append(GoH.clean.check_for_repeating_characters(tokens, "f|F"))
replacements.append(GoH.clean.check_for_repeating_characters(tokens, "t|T"))
replacements.append(GoH.clean.check_for_repeating_characters(tokens, "l|L"))
replacements = [item for sublist in replacements for item in sublist]
if len(replacements) > 0:
print('{}: {}'.format(filename, replacements))
for replacement in replacements:
content = GoH.clean.replace_pair(replacement, content)
else:
pass
with open(join(directories['cycle'], filename), mode="w") as o:
o.write(content)
o.close()
PHJ18851201-V01-04-page24.txt: [('IIIIfIfIIIIIIIIII', ' ')]
PHJ18860801-V02-02-page1.txt: [('soNntNncvccocNnNosc.m.tv.c.tnNxcvccw', ' '), ('NNNtvvioNnIccNnNwkwx', ' ')]
PHJ18870601-V02-07-page1.txt: [('N.NNILNNILNNN.', ' ')]
PHJ18881101-V03-11-page27.txt: [('nnonoranniNgrinnuncarannonciationcimannoroarancinempzinntn', ' ')]
PHJ18890501-V04-05-page24.txt: [('Itithnffiffiefinfficiently', ' ')]
PHJ18900801-V05-08-page32.txt: [('WIFFINWOWHIIIIIWIFFEFFITIVIL', ' ')]
PHJ18920701-V07-07-page23.txt: [('mitimiiiiiiiiiiimmitutimmiticium', ' ')]
PHJ18921101-V07-11-page22.txt: [('Millillitilill', ' ')]
PHJ19010301-V16-03-page30.txt: [('ttitttttttttittitt', ' ')]
PHJ19010401-V16-04-page30.txt: [('IMIMMOSUMMWORANICVNIMMAIXIIMICil', ' ')]
PHJ19010501-V16-05-page35.txt: [('iiiiIIIIIIIII', ' ')]
PHJ19010901-V16-09-page33.txt: [('MIUMMIINIIMIMMORMIlleiriMMUNIPM', ' '), ('LttlitlYAMtkilletaitaillitialaailkill.failk', ' ')]
PHJ19030901-V18-09-page2.txt: [('mmtvmszKommommeszmmtimmotmectoot', ' ')]
In [38]:
# %load shared_elements/summary.py
summary = GoH.reports.overview_report(directories['cycle'], spelling_dictionary, title)
Directory: /Users/jeriwieringa/Dissertation/text/text/2017-01-31-corpus-with-utf8-split-into-titles-cleaning/PHJ/correction8 Average verified rate: 0.9812646838465844 Average of error rates: 0.026498778049322377 Total token count: 2849645
In [39]:
# %load shared_elements/top_errors.py
errors_summary = GoH.reports.get_errors_summary( summary )
GoH.reports.top_errors( errors_summary, 10 )[:50]
Out[39]:
[('m', 2723),
('d', 2324),
("'", 1997),
('e', 1380),
('r', 1248),
('t', 1203),
('w', 1166),
('n', 1117),
('co', 1109),
('f', 795),
('g', 759),
('x', 648),
('lb', 583),
('sel', 251),
('th', 250),
('mo', 230),
('oo', 222),
('pp', 218),
('z', 215),
('k', 214),
('u', 196),
("an'", 192),
('q', 132),
('ex', 106),
('ournal', 105),
('al', 94),
('te', 85),
('oz', 81),
('ga', 80),
('ro', 77),
('pa', 74),
('va', 74),
('munn', 73),
('io', 72),
('-', 66),
('ti', 66),
("infants'", 61),
('id', 55),
('viperance', 54),
('zo', 53),
('em', 53),
('tion', 51),
("''", 49),
('si', 47),
('urnal', 47),
('fahr', 46),
('cc', 45),
("hours'", 44),
('cloe', 43),
('tt', 42)]
Correction 9 -- Separate Squashed Words¶
In [41]:
# %load shared_elements/separate_squashed_words.py
import pandas as pd
from math import log
prev = "correction8"
cycle = "correction9"
directories = GoH.utilities.define_directories(prev, cycle, base_dir)
if not os.path.exists(directories['cycle']):
os.makedirs(directories['cycle'])
corpus = (f for f in listdir(directories['prev']) if not f.startswith('.') and isfile(join(directories['prev'], f)))
verified_tokens = []
for filename in corpus:
content = GoH.utilities.readfile(directories['prev'], filename)
clean.get_approved_tokens(content, spelling_dictionary, verified_tokens)
tokens_with_freq = dict(collections.Counter(verified_tokens))
words = pd.DataFrame(list(tokens_with_freq.items()), columns=['token','freq'])
words_sorted = words.sort_values('freq', ascending=False)
words_sorted_short = words_sorted[words_sorted.freq > 2]
sorted_list_of_words = list(words_sorted_short['token'])
wordcost = dict((k, log((i+1)*log(len(sorted_list_of_words)))) for i,k in enumerate(sorted_list_of_words))
maxword = max(len(x) for x in sorted_list_of_words)
corpus = (f for f in listdir(directories['prev']) if not f.startswith('.') and isfile(join(directories['prev'], f)))
for filename in corpus:
content = GoH.utilities.readfile(directories['prev'], filename)
text = GoH.utilities.strip_punct(content)
tokens = GoH.utilities.tokenize_text(text)
replacements = []
for token in tokens:
if not token.lower() in spelling_dictionary:
if len(token) > 17:
if re.search(r"[\-\-\'\"]", token):
pass
else:
split_string = clean.infer_spaces(token, wordcost, maxword)
list_split_string = split_string.split()
if clean.verify_split_string(list_split_string, spelling_dictionary):
replacements.append((token, split_string))
else:
pass
else:
pass
else:
pass
if len(replacements) > 0:
print("{}: {}".format(filename, replacements))
for replacement in replacements:
content = GoH.clean.replace_pair(replacement, content)
else:
pass
with open(join(directories['cycle'], filename), mode="w") as o:
o.write(content)
o.close()
PHJ18860801-V02-02-page21.txt: [('painkillezejkillers', 'p a ink i l le z e j k i l l e r s')]
PHJ18860801-V02-02-page25.txt: [('localititecalities', 'local it it e c a l i t i e s')]
PHJ18860801-V02-02-page4.txt: [('immediatelyremoved', 'immediately removed')]
PHJ18870401-V02-06-page24.txt: [('brownsugarinwhichahalfteaspoonpulverized', 'brown sugar in which a half teaspoon pulverized')]
PHJ18870401-V02-06-page28.txt: [('DURINGTHECHRISTIAN', 'DURING THE CHRISTIAN')]
PHJ18870801-V02-08-page29.txt: [('PACIFICPRESSPUBLISHINGROUSEOaldgildCal', 'PACIFIC PRESS PUBLISHING R O U S E O a l d g i l d C a l')]
PHJ18870801-V02-08-page30.txt: [('householddictionary', 'household dictionary')]
PHJ18871001-V02-09-page25.txt: [('precedingpreparations', 'preceding preparations')]
PHJ18880301-V03-03-page26.txt: [('informationladdress', 'information lad dress')]
PHJ18881101-V03-11-page27.txt: [('EECLICEIZLIECOUIZIEIFICINCIIMIC', 'E E C L I C E I Z L I E C O U I Z I E I F I C I N C I I M I C')]
PHJ18890201-V04-02-page28.txt: [('theircrispnessitmayberestoredbyplacingtheminahotovenfor', 'their crispness it may be restored by placing them in a hot oven for'), ('precedingpreparations', 'preceding preparations')]
PHJ18890301-V04-03-page32.txt: [('NEWHOMESEWINGMACHINE', 'NEW HOME SEWING MACHINE')]
PHJ18890401-V04-04-page31.txt: [('theircrispnessitmayberestoredbyplacingtheminahotovenfor', 'their crispness it may be restored by placing them in a hot oven for')]
PHJ18890501-V04-05-page21.txt: [('intinixtivillytively', 'in tin ix t i v i l l y t i v e l y'), ('hislItthitherother', 'his l It thither other')]
PHJ18890501-V04-05-page24.txt: [('Iiicigslirplelasure', 'I ii c i g s l i r p l e l a s u r e'), ('clothtscgtiliehlbf', 'cloth t s c g t i l i e h l b f'), ('slfiesiiiWiSecibade', 's l fie s iii W i S e c i b a d e')]
PHJ18890501-V04-05-page25.txt: [('ChristirailitNiifi', 'Christ i rail it N i i f i'), ('dAbclitsittliblished', 'd A b c l i t s i t t l i b l i s h e d'), ('goldengolilawnbrown', 'golden go l i lawn brown')]
PHJ18890501-V04-05-page28.txt: [('advertielderitiderb', 'adv er tie l der it i der b'), ('OatmtkitilieallBiscuit', 'Oat m t k i t i l i e a l l B i s c u i t'), ('contaiaonitiiituidthing', 'c ont ai a on it ii it u i d t h i n g'), ('aerillaissIthsbugh', 'a er ill a is s It h s bug h'), ('cbtherideletenious', 'c b the ride let en i o us'), ('litiadziaidpeizially', 'lit i ad z i a i d p e i z i a l l y'), ('substittatbstitutdisper', 'sub st it tat b st it u t d i s p e r'), ('iihwalithlipainful', 'ii h w a l i t h l i p a i n f u l'), ('drictithietitstfrd', 'dr i c tit hi et it st f r d')]
PHJ18890601-V04-06-page27.txt: [('onthsallshallbecomeyourown', 'ont h s all shall become your own')]
PHJ18891001-V04-10-page29.txt: [('Wasatworkonafarmfor', 'Was at work on a farm for')]
PHJ18891101-V04-11-page3.txt: [('sanguiniolymphatic', 'sang u i n i o l y m p h a t i c')]
PHJ18891201-V04-12-page34.txt: [('Spiritualeffectsofintemperance', 'Spiritual effects of intemperance')]
PHJ18900201-V05-02-page3.txt: [('Dangerouslycontaminated', 'Dangerous l y contaminated')]
PHJ18900301-V05-03-page23.txt: [('oftencircumstances', 'often circumstances')]
PHJ18900301-V05-03-page30.txt: [('CliinoindhWialtceh', 'C l ii no in d h W i a l t c e h')]
PHJ18900301-V05-03-page32.txt: [('SCIENTIFICAMERICAN', 'SCIENTIFIC AMERICAN')]
PHJ18900401-V05-04-page15.txt: [('thoroughlyorganized', 'thoroughly organized')]
PHJ18900701-V05-07-page28.txt: [('willEbcuyatheFsORDiroLlLRATOICRP', 'will E b c u y a t h e F s O R D i r o L l L R A T O I C R P')]
PHJ18900801-V05-08-page28.txt: [('HowtoDressHealthfully', 'How to Dress Healthfully')]
PHJ18900801-V05-08-page31.txt: [('SCIENTIFICAMERICAN', 'SCIENTIFIC AMERICAN')]
PHJ18900901-V05-09-page29.txt: [('thepitOirtroLBLATTT', 'the pit O ir t r o L B L A T T T')]
PHJ18900901-V05-09-page31.txt: [('SCIENTIFICAMERICAN', 'SCIENTIFIC AMERICAN')]
PHJ18901001-V05-10-page31.txt: [('ANTEDineveranYshow', 'ANT ED in ever an Y show'), ('WHOCHANGEDTHESABBATH', 'WHO CHANGED THE SABBATH')]
PHJ18901201-V05-12-page11.txt: [('barbaphysiologists', 'bar b a physiologists')]
PHJ18901201-V05-12-page31.txt: [('THEONLYSEWINGMACHINE', 'THE ONLY SEWING MACHINE'), ('NEWHOMESEWINGMACHINECo', 'NEW HOME SEWING MACHINE C o'), ('Wefurnishpatternsforhigh', 'We furnish patterns for high')]
PHJ18910101-V06-01-page31.txt: [('THEONLYSEWINGMACHINE', 'THE ONLY SEWING MACHINE'), ('PIVECTSATISTICTION', 'P IV E C T S A T I S T I C T I O N')]
PHJ18910301-V06-03-page31.txt: [('NEWHOMESEWINGMACHINEaORTINGE', 'NEW HOME SEWING MACHINE a OR TIN G E'), ('ctiMioprIpliardeaey', 'c t i M i o p r I p l i a r d e a e y')]
PHJ18910401-V06-04-page31.txt: [('THEONLYSEWINGMACHINE', 'THE ONLY SEWING MACHINE')]
PHJ18910501-V06-05-page31.txt: [('HOMESEWINGMACHINEaORANGEMASS', 'HOME SEWING MACHINE a ORANGE MASS')]
PHJ18910601-V06-06-page2.txt: [('imperfectlycleansed', 'imperfectly cleansed')]
PHJ18910601-V06-06-page32.txt: [('laWrillifiliaMiniWi', 'la W r i l l i f i l i a M i n i W i')]
PHJ18910801-V06-08-page8.txt: [('constantlyincreasing', 'constantly increasing')]
PHJ18910901-V06-09-page11.txt: [('comfortablycircumstanced', 'comfortably circumstanced')]
PHJ18911001-V06-10-page27.txt: [('consumptionbreeding', 'consumption breeding')]
PHJ18911001-V06-10-page4.txt: [('supercarbonization', 'sup er carbon i z a t i o n')]
PHJ18911101-V06-11-page31.txt: [('descriptivearticles', 'descriptive articles')]
PHJ18911201-V06-12-page31.txt: [('PACIFICPRESSPUBLISHINGHOUSE', 'PACIFIC PRESS PUBLISHING HOUSE')]
PHJ18920901-V07-09-page25.txt: [('butthebodywithoutasoulisonlya', 'but the body without a soul is only a')]
PHJ18920901-V07-09-page32.txt: [('ForSimplicityitBeatatheWorld', 'For Simplicity it Beat a the World')]
PHJ18921101-V07-11-page30.txt: [('avoIddanarousbarbi', 'a v o I d d a n a r o u s b a r b i')]
PHJ18960501-V11-05-page6.txt: [('supersensitiveness', 'sup er sensitiveness')]
PHJ18961101-V11-11-page32.txt: [('ingSliimiediullIVIgi', 'ing S l i im i ed i u l l I V I g i')]
PHJ18990401-V14-04-page16.txt: [('accomplishmentwhichhascomevery', 'accomplishment which has come very')]
PHJ18990701-V14-07-page18.txt: [('supersensitiveness', 'sup er sensitiveness')]
PHJ18990901-V14-09-page29.txt: [('poisonoussubstances', 'poisonous substances')]
PHJ19010201-V16-02-page33.txt: [('bfilVilarliftightklalthiglitilaritiontintarAblanklM', 'b f i l V i l a r l i f t i g h t k l a l t h i g l i t i l a r i t i o n t i n t a r A b l a n k l M')]
PHJ19010501-V16-05-page4.txt: [('liberallyfurnished', 'liberally furnished')]
PHJ19010701-V16-07-page29.txt: [('SanFranciscoAgents', 'San Francisco Agents')]
PHJ19010701-V16-07-page33.txt: [('MIONVIIMIlliMaRkliblOgeMtialk', 'M I O N V I I M I l l i M a R k l i b l O g e M t i a l k'), ('aamenontmenalwanunionawaimmatatatem', 'a a men ont men a l wan union a w a i m m a t a t a t e m')]
PHJ19010801-V16-08-page29.txt: [('pleasantdisinfectant', 'pleasant disinfectant')]
PHJ19010801-V16-08-page33.txt: [('WEVONElitlitrAkliailIAMEM', 'WE V ONE lit lit r A k l i a i l I A M E M')]
PHJ19011201-V16-12-page35.txt: [('carefullycontrolled', 'carefully controlled')]
PHJ19011201-V16-12-page43.txt: [('GOODHEALTHRESTAURANT', 'GOOD HEALTH RESTAURANT')]
PHJ19020401-V17-04-page7.txt: [('delicatelybalanced', 'delicately balanced')]
PHJ19020501-V17-05-page18.txt: [('diseasecleanliness', 'disease cleanliness')]
PHJ19020501-V17-05-page19.txt: [('satisfacantiseptic', 'sat is f a c a n t i s e p t i c')]
PHJ19020801-V17-08-page2.txt: [('curawarararanzaTararom', 'cur a war ar a ran z a T a r a r o m')]
PHJ19030801-V18-08-page17.txt: [('noncommunicability', 'non communicability'), ('intercommunicability', 'inter communicability')]
PHJ19030801-V18-08-page35.txt: [('Noixoffeacitexcmicam', 'No ix of fe a cite x c m i c a m')]
PHJ19031001-V18-10-page36.txt: [('Witagitiniftititiat', 'Wit a git in if tit it i at')]
PHJ19031101-V18-11-page36.txt: [('SanitariumSanitarium', 'Sanitarium Sanitarium')]
PHJ19031201-V18-12-page36.txt: [('HelenaSanitariumRS', 'Helena Sanitarium R S')]
PHJ19040101-V19-01-page24.txt: [('regularlyprescribed', 'regularly prescribed')]
PHJ19040601-V19-06-page14.txt: [('aplebaredsohlaubtitonstriasiaglhl', 'a p le bar ed so h l au b tit on str i as i a g l h l')]
PHJ19040601-V19-06-page9.txt: [('imperfectlymasticated', 'imperfectly masticated')]
In [42]:
# %load shared_elements/summary.py
summary = GoH.reports.overview_report(directories['cycle'], spelling_dictionary, title)
Directory: /Users/jeriwieringa/Dissertation/text/text/2017-01-31-corpus-with-utf8-split-into-titles-cleaning/PHJ/correction9 Average verified rate: 0.9812348137373975 Average of error rates: 0.026514996667407243 Total token count: 2850438
In [43]:
# %load shared_elements/top_errors.py
errors_summary = GoH.reports.get_errors_summary( summary )
GoH.reports.top_errors( errors_summary, 10 )[:50]
Out[43]:
[('m', 2741),
('d', 2338),
("'", 1997),
('e', 1411),
('r', 1272),
('t', 1245),
('w', 1172),
('n', 1131),
('co', 1109),
('f', 805),
('g', 769),
('x', 649),
('lb', 583),
('sel', 251),
('th', 250),
('mo', 230),
('z', 222),
('oo', 222),
('k', 221),
('pp', 218),
('u', 207),
("an'", 192),
('q', 132),
('ex', 106),
('ournal', 105),
('al', 94),
('te', 85),
('oz', 81),
('ga', 80),
('ro', 77),
('pa', 74),
('va', 74),
('munn', 73),
('io', 72),
('-', 66),
('ti', 66),
("infants'", 61),
('id', 55),
('viperance', 54),
('zo', 53),
('em', 53),
('tion', 51),
("''", 49),
('si', 47),
('urnal', 47),
('fahr', 46),
('cc', 45),
("hours'", 44),
('cloe', 43),
('tt', 42)]
In [ ]: