epstein-files 1.0.1__py3-none-any.whl → 1.0.3__py3-none-any.whl

epstein_files/util/constants.py

@@ -6,6 +6,7 @@ from dateutil.parser import parse
 from epstein_files.util.constant.names import *
 from epstein_files.util.constant.strings import *
 from epstein_files.util.doc_cfg import DocCfg, EmailCfg, TextCfg
+from epstein_files.util.logging import logger
 
 FALLBACK_TIMESTAMP = parse("1/1/2051 12:01:01 AM")
 
@@ -213,22 +214,22 @@ for emailer in EMAILERS:
 FBI = 'FBI'
 MEME = 'meme of'
 PRESS_RELEASE = 'press release'
-RESUME_OF = 'professional resumé of'
+RESUME_OF = 'professional resumé'
 SCREENSHOT = 'screenshot of'
 TRANSLATION = 'translation of'
 TWEET = 'tweet'
 TEXT_OF_US_LAW = 'text of U.S. law:'
 
 # Legal cases
-BRUNEL_V_EPSTEIN = f"{JEAN_LUC_BRUNEL} v. {JEFFREY_EPSTEIN}"
-EDWARDS_V_DERSHOWITZ = f"{BRAD_EDWARDS} & {PAUL_G_CASSELL} v. {ALAN_DERSHOWITZ}:"
-EPSTEIN_V_ROTHSTEIN_EDWARDS = f"Epstein v. Scott Rothstein, {BRAD_EDWARDS}, and L.M.:"
-GIUFFRE_V_DERSHOWITZ = f"{VIRGINIA_GIUFFRE} v. {ALAN_DERSHOWITZ}:"
-GIUFFRE_V_EPSTEIN = f"{VIRGINIA_GIUFFRE} v. {JEFFREY_EPSTEIN}:"
-GIUFFRE_V_MAXWELL = f"{VIRGINIA_GIUFFRE} v. {GHISLAINE_MAXWELL}:"
-JANE_DOE_V_EPSTEIN_TRUMP = f"Jane Doe v. Donald Trump and {JEFFREY_EPSTEIN}:"
-JANE_DOE_V_USA = 'Jane Doe #1 and Jane Doe #2 v. United States:'
-NEW_YORK_V_EPSTEIN = f"New York v. {JEFFREY_EPSTEIN}:"
+BRUNEL_V_EPSTEIN = f"{JEAN_LUC_BRUNEL} v. {JEFFREY_EPSTEIN} and Tyler McDonald d/b/a YI.org"
+EDWARDS_V_DERSHOWITZ = f"{BRAD_EDWARDS} & {PAUL_G_CASSELL} v. {ALAN_DERSHOWITZ}"
+EPSTEIN_V_ROTHSTEIN_EDWARDS = f"Epstein v. Scott Rothstein, {BRAD_EDWARDS}, and L.M."
+GIUFFRE_V_DERSHOWITZ = f"{VIRGINIA_GIUFFRE} v. {ALAN_DERSHOWITZ}"
+GIUFFRE_V_EPSTEIN = f"{VIRGINIA_GIUFFRE} v. {JEFFREY_EPSTEIN}"
+GIUFFRE_V_MAXWELL = f"{VIRGINIA_GIUFFRE} v. {GHISLAINE_MAXWELL}"
+JANE_DOE_V_EPSTEIN_TRUMP = f"Jane Doe v. Donald Trump and {JEFFREY_EPSTEIN}"
+JANE_DOE_V_USA = 'Jane Doe #1 and Jane Doe #2 v. United States'
+NEW_YORK_V_EPSTEIN = f"New York v. {JEFFREY_EPSTEIN}"
 
 # Descriptions of non-email, non-text message files
 ARTICLE_DRAFT = 'draft of an article about'
@@ -238,41 +239,41 @@ BROCKMAN_INC = 'Brockman, Inc.'
 CVRA = "Crime Victims' Rights Act [CVRA]"
 DAVID_BLAINE_VISA_LETTER = f"letter of recommendation for visa for a model"
 DAVID_SCHOEN_CVRA_LEXIS_SEARCH = f"Lexis Nexis search for case law around the {CVRA} by {DAVID_SCHOEN}"
-DERSH_GIUFFRE_TWEET = f"{TWEET} by {ALAN_DERSHOWITZ} about {VIRGINIA_GIUFFRE}"
+DERSH_GIUFFRE_TWEET = f"{TWEET} about {VIRGINIA_GIUFFRE}"
 DEUTSCHE_BANK_TAX_TOPICS = f'{DEUTSCHE_BANK} Wealth Management Tax Topics'
-DIANA_DEGETTES_CAMPAIGN = "Colorado legislator Diana DeGette's campaign"
+DIANA_DEGETTE_CAMPAIGN = "Colorado legislator Diana DeGette's campaign"
 EPSTEIN_FOUNDATION = 'Jeffrey Epstein VI Foundation'
 FBI_REPORT = f"{FBI} report on Epstein investigation (redacted)"
 FBI_SEIZED_PROPERTY = f"{FBI} seized property inventory (redacted)"
 FEMALE_HEALTH_COMPANY = 'Female Health Company (FHX)'
 FIRE_AND_FURY = f"Fire And Fury"
 HARVARD_POETRY = f'{HARVARD} poetry stuff from {LISA_NEW}'
-HBS_APPLICATION_NERIO = f"{HARVARD} Business School application letter from Nerio Alessandri (Founder and Chairman of Technogym S.p.A. Italy)"
+HBS_APPLICATION = f"{HARVARD} Business School application letter"
 JASTA = 'JASTA'
 JASTA_SAUDI_LAWSUIT = f"{JASTA} lawsuit against Saudi Arabia by 9/11 victims"
 JOHN_BOLTON_PRESS_CLIPPING = 'John Bolton press clipping'
 JP_MORGAN_EYE_ON_THE_MARKET = f"Eye On The Market"
+LAWRENCE_KRAUSS_ASU_ORIGINS = f"{LAWRENCE_KRAUSS}'s ASU Origins Project"
 KEN_STARR_LETTER = f"letter to judge overseeing Epstein's criminal prosecution, mentions Alex Acosta"
 MICHAEL_WOLFF_ARTICLE_HINT = f"draft of an unpublished article about Epstein by {MICHAEL_WOLFF} written ca. 2014/2015"
+NERIO_ALESSANDRI = 'Nerio Alessandri (Founder and Chairman of Technogym S.p.A. Italy)'
 NIGHT_FLIGHT_BOOK = f'"Night Flight" (draft)'
 NOBEL_CHARITABLE_TRUST = 'Nobel Charitable Trust'
 OBAMA_JOKE = 'joke about Obama'
-PALM_BEACH_CODE_ENFORCEMENT = f'{PALM_BEACH} code enforcement board minutes'
-PALM_BEACH_DAILY_ARTICLE = f'{PALM_BEACH} Daily News article about'
-PALM_BEACH_POST_ARTICLE = f'{PALM_BEACH} Post article about'
+PALM_BEACH_CODE_ENFORCEMENT = f'{PALM_BEACH} Code Enforcement'
 PALM_BEACH_TSV = f"TSV of {PALM_BEACH} property"
 PALM_BEACH_WATER_COMMITTEE = f'{PALM_BEACH} Water Committee'
 PATTERSON_BOOK_SCANS = f'pages of "Filthy Rich: The Shocking True Story of {JEFFREY_EPSTEIN}"'
 SHIMON_POST = 'The Shimon Post'
-SHIMON_POST_ARTICLE = f'{SHIMON_POST} selection of articles about the mideast'
+SHIMON_POST_ARTICLE = f'selection of articles about the mideast'
 SINGLE_PAGE = 'single page of'
+STRANGE_BEDFELLOWS = "'Strange Bedfellows' list of invitees f. Johnny Depp, Woody Allen, Obama, and more"
 SWEDISH_LIFE_SCIENCES_SUMMIT = f"{BARBRO_C_EHNBOM}'s Swedish American Life Science Summit"
 THE_REAL_DEAL_ARTICLE = 'article by Keith Larsen'
 TRUMP_DISCLOSURES = f"Donald Trump financial disclosures from U.S. Office of Government Ethics"
 UBS_CIO_REPORT = 'CIO Monthly Extended report'
 UN_GENERAL_ASSEMBLY = '67th U.N. General Assembly'
-VI_DAILY_NEWS_ARTICLE = f'{VIRGIN_ISLANDS} Daily News article'
-WOMEN_EMPOWERMENT = f"Women Empowerment (WE) conference run by {SVETLANA_POZHIDAEVA}"
+WOMEN_EMPOWERMENT = f"Women Empowerment (WE) conference"
 ZUBAIR_AND_ANYA = f"{ZUBAIR_KHAN} and Anya Rasulova"
 
 # Atribution reasons
@@ -297,7 +298,7 @@ CONFIRMED_TEXTS_CONFIG = [
     TextCfg(id='027650', author=JOI_ITO, attribution_reason=PARTICIPANTS_FIELD),
     TextCfg(id='027777', author=LARRY_SUMMERS, attribution_reason=PARTICIPANTS_FIELD),
     TextCfg(id='027515', author=MIROSLAV_LAJCAK, attribution_reason='https://x.com/ImDrinknWyn/status/1990210266114789713'),
-    TextCfg(id='027165', author=MELANIE_WALKER, attribution_reason='https://www.wired.com/story/jeffrey-epstein-claimed-intimate-knowledge-of-donald-trumps-views-in-texts-with-bill-gates-adviser/'),
+    TextCfg(id='027165', author=MELANIE_WALKER, attribution_reason='says "it\'s Melanie", also https://www.wired.com/story/jeffrey-epstein-claimed-intimate-knowledge-of-donald-trumps-views-in-texts-with-bill-gates-adviser/'),
     TextCfg(id='027248', author=MELANIE_WALKER, attribution_reason='says "we met through Trump" which is confirmed by Melanie in 032803'),
     TextCfg(id='025429', author=STACEY_PLASKETT, attribution_reason='widely reported'),
     TextCfg(id='027128', author=SOON_YI_PREVIN, attribution_reason='https://x.com/ImDrinknWyn/status/1990227281101434923'),
@@ -385,7 +386,12 @@ EMAILS_CONFIG = [
         author='Audrey/Aubrey Raimbault (???)',
         attribution_reason='based on "GMI" in signature, a company registered by "Aubrey Raimbault"',
     ),
-    EmailCfg(id='033316', author=AZIZA_ALAHMADI, attribution_reason='"Regards, Aziza" at bottom'),
+    EmailCfg(
+        id='033316',
+        author=AZIZA_ALAHMADI,
+        attribution_reason='"Regards, Aziza" at bottom',
+        fwded_text_after='Transcript: Phone call between President',
+    ),
     EmailCfg(id='033328', author=AZIZA_ALAHMADI, attribution_reason='"Regards, Aziza" at bottom'),
     EmailCfg(id='026659', author=BARBRO_C_EHNBOM, attribution_reason='Reply'),
     EmailCfg(id='031215', author=BARBRO_C_EHNBOM, duplicate_ids=['026745'], dupe_type='redacted'),  # the same except for 'your Anna!'. author must be specified because email address is redacted in 026745 so it needs the config
@@ -408,6 +414,7 @@ EMAILS_CONFIG = [
     ),
     EmailCfg(
         id='031278',
+        actual_text='',
         author=DARREN_INDYKE,
         description=f"heavily redacted email, quoted replies are from {STEVEN_HOFFENBERG} about James Patterson's book",
         timestamp=parse('2016-08-17 11:26:00'),
@@ -419,7 +426,7 @@ EMAILS_CONFIG = [
     EmailCfg(id='031560', author=DAVID_SCHOEN, attribution_reason='Signature'),
     EmailCfg(id='026287', author=DAVID_SCHOEN, attribution_reason='Signature'),
     EmailCfg(id='033419', author=DAVID_SCHOEN, attribution_reason='Signature'),
-    EmailCfg(id='031460', author=EDWARD_JAY_EPSTEIN, attribution_reason=f"quoted reply has edwardjayepstein.com"),
+    EmailCfg(id='031460', author=EDWARD_JAY_EPSTEIN, attribution_reason=f"quoted reply has edwardjayepstein.com", is_fwded_article=True),
     EmailCfg(
         id='030475',
         author=FAITH_KATES,
@@ -443,7 +450,13 @@ EMAILS_CONFIG = [
     EmailCfg(id='018726', author=JEFFREY_EPSTEIN, timestamp=parse('2018-06-08 08:36:00')),  # nofix
     EmailCfg(id='032283', author=JEFFREY_EPSTEIN, timestamp=parse('2016-09-14 08:04:00')),  # nofix
     EmailCfg(id='026943', author=JEFFREY_EPSTEIN, timestamp=parse('2019-05-22 05:47:00')),  # nofix
-    EmailCfg(id='023208', author=JEFFREY_EPSTEIN, recipients=[BRAD_WECHSLER, MELANIE_SPINELLA], duplicate_ids=['023291']),
+    EmailCfg(
+        id='023208',
+        author=JEFFREY_EPSTEIN,
+        fwded_text_after='Date: Tue, Oct 27',
+        recipients=[BRAD_WECHSLER, MELANIE_SPINELLA],
+        duplicate_ids=['023291'],
+    ),
     EmailCfg(
         id='032214',
         author=JEFFREY_EPSTEIN,
@@ -559,9 +572,10 @@ EMAILS_CONFIG = [
     ),
     EmailCfg(
         id='026620',
+        attribution_reason='ends with "Respectfully, terry"',
         author=TERRY_KAFKA,
+        fwded_text_after='From: Mike Cohen',
         recipients=[JEFFREY_EPSTEIN, MARK_EPSTEIN, MICHAEL_BUCHHOLTZ] + IRAN_NUCLEAR_DEAL_SPAM_EMAIL_RECIPIENTS,
-        attribution_reason='ends with "Respectfully, terry"',
         duplicate_ids=['028482'],
     ),
     EmailCfg(id='029992', author=TERRY_KAFKA, attribution_reason='Quoted reply'),
@@ -580,6 +594,8 @@ EMAILS_CONFIG = [
         attribution_reason=f'Reply in 030414 has {NEXT_MANAGEMENT} legal signature',
         duplicate_ids=['030581'],
     ),
+    EmailCfg(id='025329', recipients=['George Krassner', 'Nancy Cain', 'Tom', 'Marie Moneysmith', 'Steven Gaydos', 'Linda W. Grossman', 'Holly Krassner Dawson', 'Daniel Dawson', 'Danny Goldberg', 'Caryl Ratner', 'Kevin Bright', 'Michael Simmons', SAMUEL_LEFF, 'Bob Fass', 'Lynnie Tofte Fass', 'Barb Cowles', 'Lee Quarnstrom']),
+    EmailCfg(id='033568', recipients=['George Krassner', 'Daniel Dawson', 'Danny Goldberg', 'Tom', 'Kevin Bright', 'Walli Leff', 'Michael Simmons', 'Lee Quarnstrom', 'Lanny Swerdlow', 'Larry Sloman', 'W&K', 'Harry Shearer', 'Jay Levin']),
     EmailCfg(id='026426', recipients=[JEAN_HUGUEN], attribution_reason='Reply'),
     EmailCfg(id='022202', recipients=[JEAN_LUC_BRUNEL], attribution_reason='Follow up / reply', duplicate_ids=['029975']),
     EmailCfg(id='022187', recipients=[JEFFREY_EPSTEIN]),  # Bad OCR (nofix)
@@ -611,8 +627,6 @@ EMAILS_CONFIG = [
         attribution_reason='to "Kathy" about dems, sent from iPad',
         is_attribution_uncertain=True,  # It's actually Kathy R. as the recipient that's the uncertain part
     ),
-    EmailCfg(id='025329', recipients=['Nancy Cain', 'Tom', 'Marie Moneysmith', 'Steven Gaydos', 'George Krassner', 'Linda W. Grossman', 'Holly Krassner Dawson', 'Daniel Dawson', 'Danny Goldberg', 'Caryl Ratner', 'Kevin Bright', 'Michael Simmons', SAMUEL_LEFF, 'Bob Fass', 'Lynnie Tofte Fass', 'Barb Cowles', 'Lee Quarnstrom']),
-    EmailCfg(id='033568', recipients=['George Krassner', 'Daniel Dawson', 'Danny Goldberg', 'Tom', 'Kevin Bright', 'Walli Leff', 'Michael Simmons', 'Lee Quarnstrom', 'Lanny Swerdlow', 'Larry Sloman', 'W&K', 'Harry Shearer', 'Jay Levin']),
     EmailCfg(id='030522', recipients=[LANDON_THOMAS], attribution_reason='reply header', is_fwded_article=True),  # Vicky Ward article
     EmailCfg(id='031413', recipients=[LANDON_THOMAS], attribution_reason='reply header'),
     EmailCfg(id='033591', recipients=[LAWRANCE_VISOSKI], attribution_reason='Reply signature', duplicate_ids=['033591']),
@@ -637,15 +651,26 @@ EMAILS_CONFIG = [
     # Misc configs
     EmailCfg(id='033050', actual_text='schwartman'),
     EmailCfg(id='029344', actual_text='I thought of you when I read this article. Was this your idea? Alan'),
-    EmailCfg(id='023627', description=MICHAEL_WOLFF_ARTICLE_HINT, is_fwded_article=True),
+    EmailCfg(id='022219', description="discussion of attempts to clean up Epstein's Google search results"),
+    EmailCfg(id='023627', is_fwded_article=True, description=MICHAEL_WOLFF_ARTICLE_HINT),
+    EmailCfg(id='031333', is_fwded_article=True, description='looks like a Russian disinfo article'),  # Russia Says IMF Chief Jailed For Discovering All US Gold is Gone
+    EmailCfg(id='031335', is_fwded_article=True, description='looks like a Russian disinfo article'),  # DOMINQUE STRAUSS-KAHN ARRESTED, NOT BECAUSE HE RAPED A MAID, BUT BECAUSE HE HAD EVIDENCE US HAS NO GOLD IN FORT KNOX.
     EmailCfg(id='026298', is_fwded_article=True, duplicate_ids=['026499']),  # Written by someone else?
     EmailCfg(id='029692', is_fwded_article=True, duplicate_ids=['029779']),  # WaPo article
     EmailCfg(id='022344', is_fwded_article=True, duplicate_ids=['028529']),  # Bill Gates is most admired from Nikolic
     EmailCfg(id='018197', is_fwded_article=True, duplicate_ids=['028648']),  # Ray Takeyh article fwd
     EmailCfg(id='028728', is_fwded_article=True, duplicate_ids=['027102']),  # WSJ forward to Larry Summers
     EmailCfg(id='028781', is_fwded_article=True, duplicate_ids=['013460']),  # Atlantic on Jim Yong Kim, Obama's World Bank Pick
+    EmailCfg(id='025041', is_fwded_article=True, duplicate_ids=['028675']),  # Obama agenda
+    EmailCfg(id='031136', is_fwded_article=True, duplicate_ids=['028791']),  # 'Smart Money is Fleeing US Stocks'
+    EmailCfg(id='031779', is_fwded_article=True, duplicate_ids=['026938']),  # Sarah Silverman on AI
+    EmailCfg(id='029849', is_fwded_article=True, duplicate_ids=['033482']), # Fareed Zakaria: Trump sells America short),
+    EmailCfg(id='032023', is_fwded_article=True, duplicate_ids=['032012']), # American-Israeli Cooperative Enterprise Newsletter
+    EmailCfg(id='030868', is_fwded_article=True),  # 'He doesn't like this sh*t': Trump reportedly hates his job and his staff after 1 month
     EmailCfg(id='026755', is_fwded_article=True),  # HuffPo
+    EmailCfg(id='016218', is_fwded_article=True),  # AT&T confirms it paid Trump lawyer Cohen for insights on Trump
     EmailCfg(id='030528', is_fwded_article=True),  # Vicky Ward article
+    EmailCfg(id='030460', is_fwded_article=True),  # Vicky Ward article
     EmailCfg(id='028508', is_fwded_article=True),  # nanosatellites article
     EmailCfg(id='019845', is_fwded_article=True),  # Pro Publica article on Preet Bharara
     EmailCfg(id='029021', is_fwded_article=True),  # article about bannon sent by Alain Forget
@@ -655,6 +680,36 @@ EMAILS_CONFIG = [
     EmailCfg(id='031569', is_fwded_article=True),  # Article by Kathryn Alexeeff fwded to Peter Thiel
     EmailCfg(id='029689', is_fwded_article=True),  # Tunisia article to Larry Summers
     EmailCfg(id='014525', is_fwded_article=True),  # Really more of a mailing list from Paul Morris?
+    EmailCfg(id='024384', is_fwded_article=True),  # Interview with Bill Siegal re: Islam
+    EmailCfg(id='030200', is_fwded_article=True),  # Lawfare indicting a president
+    EmailCfg(id='029509', is_fwded_article=True),  # Deepak Chopra LSD, Quantum Healing
+    EmailCfg(id='026778', is_fwded_article=True),  # tax alert
+    EmailCfg(id='023001', is_fwded_article=True),  # Miami Herald article timeline of the sex abuse case
+    EmailCfg(id='013405', is_fwded_article=True),  # Articles about epstein case
+    EmailCfg(id='021740', is_fwded_article=True),  # Miami Herald article about Epstein prosecutor
+    EmailCfg(id='023126', is_fwded_article=True),  # Miami Herald on Alex Acosta
+    EmailCfg(id='029625', is_fwded_article=True),  # Conchita Sarnoff Daily Beast Articles - Epstein Sex Trafficking Investigation and Settlement
+    EmailCfg(id='013482', is_fwded_article=True),  # The view from the US: Stem cell therapy steps up a gear with firs
+    EmailCfg(id='029505', is_fwded_article=True),  # Foreign Policy Middle Eastern Monarchs Look at the Trump
+    EmailCfg(id='029859', is_fwded_article=True),  # Palm Beach Post: Epstein paid three women $5.5 million to end lawsuits
+    EmailCfg(id='031988', is_fwded_article=True),  # NYT review of Inside Job
+    EmailCfg(id='029901', is_fwded_article=True),  # THE EDGE question
+    EmailCfg(id='031399', is_fwded_article=True),  # Miami U.S. Attorney's Office recuses itself from Jeffrey Epstein case
+    EmailCfg(id='031705', is_fwded_article=True),  # Thomas Friedman why not in vegas?
+    EmailCfg(id='016801', is_fwded_article=True),  # Capital Market Outlook
+    EmailCfg(id='023564', is_fwded_article=True),  # BBG ;Leon Black's Tax-Overhaul Dilemma Could Alter Wall Street Model
+    EmailCfg(id='025231', is_fwded_article=True),  # Newsmax: Laffer, Laffer: Obama Must Use Reaganomics to Save Economy The only way President Barack Obama can solve
+    EmailCfg(id='031472', is_fwded_article=True),  # WSJ: Lawyers for Imam Wanted by Turkish authorities Fear for Their Client's Life
+    EmailCfg(id='012684', is_fwded_article=True),  # Trump in talks to buy socialite Kluge's Charlottesville vineyard
+    EmailCfg(id='028536', is_fwded_article=True),  # Palm Beach Post FBI Epstein files say he gave info. Does it explain sweetheart deal?
+    EmailCfg(id='028524', is_fwded_article=True),  # Zach Braff article on Woody Allen in NYT
+    EmailCfg(id='030326', is_fwded_article=True),  # NYP Congressional candidate compares Melania Trump to prostitute
+    EmailCfg(id='030519', is_fwded_article=True),  # Daily Mail on Prince Andrew
+    EmailCfg(id='030878', is_fwded_article=True),  # Steve Bannon almost appeared in Michael Moore's 'Fahrenheit 11/9'
+    EmailCfg(id='024300', is_fwded_article=True),  # Bookstore owner calls police after customer confronted Steve Bannon
+    EmailCfg(id='026924', is_fwded_article=True),  # The Onion
+    EmailCfg(id='033311', is_fwded_article=True),  # 2016 election polls
+    EmailCfg(id='026580', is_fwded_article=True),  # NPR: Antigua: Land Of Sun, Sand, And Super Cheap
     EmailCfg(id='032475', timestamp=parse('2017-02-15 13:31:25')),
     EmailCfg(id='030373', timestamp=parse('2018-10-03 01:49:27')),
 
@@ -679,10 +734,8 @@ EMAILS_CONFIG = [
     EmailCfg(id='031980', duplicate_ids=['019409']),
     EmailCfg(id='033486', duplicate_ids=['033156']),
     EmailCfg(id='025790', duplicate_ids=['031994']),
-    EmailCfg(id='025041', duplicate_ids=['028675']),
     EmailCfg(id='028497', duplicate_ids=['026228']),
     EmailCfg(id='033528', duplicate_ids=['033517']),
-    EmailCfg(id='032023', duplicate_ids=['032012']),
     EmailCfg(id='019412', duplicate_ids=['028621']),
     EmailCfg(id='027053', duplicate_ids=['028765']),
     EmailCfg(id='027049', duplicate_ids=['028773']),
@@ -699,13 +752,11 @@ EMAILS_CONFIG = [
     EmailCfg(id='031912', duplicate_ids=['032158']),
     EmailCfg(id='030587', duplicate_ids=['030514']),
     EmailCfg(id='029773', duplicate_ids=['012685']),
-    EmailCfg(id='029849', duplicate_ids=['033482']),
     EmailCfg(id='033297', duplicate_ids=['033586']),
     EmailCfg(id='031089', duplicate_ids=['018084']),
     EmailCfg(id='031088', duplicate_ids=['030885']),
     EmailCfg(id='030238', duplicate_ids=['031130']),
     EmailCfg(id='030859', duplicate_ids=['031067']),
-    EmailCfg(id='031136', duplicate_ids=['028791']),
     EmailCfg(id='030635', duplicate_ids=['031134']),
     EmailCfg(id='028494', duplicate_ids=['026234']),
     EmailCfg(id='030311', duplicate_ids=['021790']),
@@ -775,6 +826,35 @@ EMAILS_CONFIG = [
     EmailCfg(id='029752', duplicate_ids=['023550']),
     EmailCfg(id='030339', duplicate_ids=['030592']),
     EmailCfg(id='032250', duplicate_ids=['033589']),
+
+    # Emails that need a little help determining how to separate the actual text from fwded text
+    EmailCfg(id='013415', fwded_text_after='Darren K. Indyke'),
+    EmailCfg(id='024624', fwded_text_after='On Tue, May 14'),
+    EmailCfg(id='029558', fwded_text_after='Creativity is central'),
+    EmailCfg(id='025888', fwded_text_after='Jul 24, 2015'),
+    EmailCfg(id='016413', fwded_text_after='In a former warehouse'),
+    EmailCfg(id='025548', fwded_text_after='Edward Jay Epstein'),
+    EmailCfg(id='032806', fwded_text_after='• Sep 13, 2018'),
+    EmailCfg(id='024251', fwded_text_after='Debate Schedule'),
+    EmailCfg(id='028943', fwded_text_after='-Lisa'),
+    EmailCfg(id='029431', fwded_text_after='I am writing now'),
+    EmailCfg(id='020437', fwded_text_after='Will Cohen Cooperate'),
+    EmailCfg(id='026663', fwded_text_after='REGULATORY & COMPLIANCE ALERT'),
+    EmailCfg(id='028921', fwded_text_after='Salacious new chapter'),
+    EmailCfg(id='030324', fwded_text_after='For Federal Programs'),
+    EmailCfg(id='022766', fwded_text_after='--- On Wed, 4/22/15'),
+    EmailCfg(id='025606', fwded_text_after='> On May 6,'),
+    EmailCfg(id='022977', fwded_text_after='Top of Form'),
+    EmailCfg(id='033420', fwded_text_after='Slowing economy could increase pressure on'),
+    EmailCfg(id='019203', fwded_text_after='This end-of-the-year'),
+    EmailCfg(id='022207', fwded_text_after='Web Images Videos Maps'),
+    EmailCfg(id='033210', fwded_text_after='Trump appears with mobster-affiliated'),
+    EmailCfg(id='030989', fwded_text_after='New book paints sordid picture of Trump real estate'),
+    EmailCfg(id='029174', fwded_text_after='The US trade war against China'),
+    EmailCfg(id='030015', fwded_text_after='Bill Clinton reportedly'),
+    EmailCfg(id='026312', fwded_text_after='Steve Bannon trying to get on disgraced'),
+    EmailCfg(id='031742', fwded_text_after="Trump's former campaign manager Paul Manafort"),
+
 ]
 
 
@@ -814,12 +894,19 @@ OTHER_FILES_BOOKS = [
 ]
 
 OTHER_FILES_ARTICLES = [
+    DocCfg(id='030258', author=ALAN_DERSHOWITZ, description=f'{ARTICLE_DRAFT} Mueller probe, almost same as 030248'),
+    DocCfg(id='030248', author=ALAN_DERSHOWITZ, description=f'{ARTICLE_DRAFT} Mueller probe, almost same as 030258'),
+    DocCfg(id='029165', author=ALAN_DERSHOWITZ, description=f'{ARTICLE_DRAFT} Mueller probe, almost same as 030258'),
+    DocCfg(id='030013', author=f'Aviation International News', description=f'article', date='2012-07-01'),
     DocCfg(id='013275', author=BLOOMBERG, description=f"article on notable 2013 obituaries", date='2013-12-26'),
     DocCfg(id='026543', author=BLOOMBERG, description=f"BNA article about taxes"),
+    DocCfg(id='014865', author=f'Boston Globe', description=f"article about {ALAN_DERSHOWITZ}"),
+    DocCfg(id='033231', author=f'Business Standard', description=f"article about Trump's visit with India's Modi"),
     DocCfg(id='023572', author=CHINA_DAILY, description=f"article on China's Belt & Road Initiative"),
     DocCfg(id='023571', author=CHINA_DAILY, description=f"article on terrorism, Macau, trade initiatives", date='2016-09-18'),
     DocCfg(id='023570', author=CHINA_DAILY, description=f"article on Belt & Road in Central/South America, Xi philosophy", date='2017-05-14'),
     DocCfg(id='025115', author=CHINA_DAILY, description=f"article on China and the US working together", date='2017-05-14'),
+    DocCfg(id='012704', author='Daily Business Review', description=f"article about {JANE_DOE_V_USA} and {CVRA}", date='2011-04-21'),
     DocCfg(id='025292', author=DAILY_MAIL, description=f"article on Bill Clinton being named in a lawsuit"),
     DocCfg(id='019468', author=DAILY_MAIL, description=f"article on Epstein and Clinton"),
     DocCfg(id='022970', author=DAILY_MAIL, description=f"article on Epstein and Prince Andrew"),
@@ -827,10 +914,20 @@ OTHER_FILES_ARTICLES = [
     DocCfg(id='013437', author=DAILY_TELEGRAPH, description=f"article about Epstein's diary", date='2011-03-05'),
     DocCfg(id='023287', author=DAILY_TELEGRAPH, description=f"article about a play based on the Oslo Accords", date='2017-09-15'),
     DocCfg(id='019206', author=EDWARD_JAY_EPSTEIN, description=f"WSJ article about Edward Snowden", date='2016-12-30'),
+    DocCfg(id='023567', author=f'Financial Times', description=f"article about quantitative easing"),
+    DocCfg(id='026761', author=f'Forbes', description=f"article about {BARBRO_C_EHNBOM} 'Swedish American Group Focuses On Cancer'"),
+    DocCfg(id='031716', author=f'Fortune Magazine', description=f'article by {TOM_BARRACK}', date='2016-10-22'),
+    DocCfg(id='019444', author=f'Frontlines magazine', description=f"article 'Biologists Dig Deeper'", date='2008-01-01'),
+    DocCfg(id='023720', author=f'Future Science', description=f'article: "Is Shame Necessary?" by {JENNIFER_JACQUET}'),
+    DocCfg(id='021094', author=f'Globe and Mail', description=f"article about Gerd Heinrich"),
+    DocCfg(id='013268', author=f'JetGala', description=f"article about airplane interior designer {ERIC_ROTH}"),
     DocCfg(id='029539', author=LA_TIMES, description=f"Alan Trounson interview on California stem cell research and CIRM"),
     DocCfg(id='029865', author=LA_TIMES, description=f"front page article about {DEEPAK_CHOPRA} and young Iranians", date='2016-11-05'),
     DocCfg(id='026598', author=LA_TIMES, description=f"op-ed about why America needs a Ministry of Culture"),
     DocCfg(id='027024', author=LA_TIMES, description=f"Scientists Create Human Embryos to Make Stem Cells", date='2013-05-15'),
+    DocCfg(id='031776', author='Law360', description=f"article about Michael Avenatti by Andrew Strickler"),
+    DocCfg(id='023102', author=f'Litigation Daily', description=f"article about {REID_WEINGARTEN}", date='2015-09-04'),
+    DocCfg(id='029340', author=f'MarketWatch', description=f'article about estate taxes, particularly Epstein\'s favoured GRATs'),
     DocCfg(id='022707', author=MICHAEL_WOLFF, description=MICHAEL_WOLFF_ARTICLE_HINT),
     DocCfg(id='022727', author=MICHAEL_WOLFF, description=MICHAEL_WOLFF_ARTICLE_HINT),
     DocCfg(id='022746', author=MICHAEL_WOLFF, description=MICHAEL_WOLFF_ARTICLE_HINT),
@@ -839,6 +936,26 @@ OTHER_FILES_ARTICLES = [
     DocCfg(id='022894', author=MICHAEL_WOLFF, description=MICHAEL_WOLFF_ARTICLE_HINT),
     DocCfg(id='022952', author=MICHAEL_WOLFF, description=MICHAEL_WOLFF_ARTICLE_HINT),
     DocCfg(id='024229', author=MICHAEL_WOLFF, description=MICHAEL_WOLFF_ARTICLE_HINT),
+    DocCfg(id='031198', author='Morning News USA', description=f"article about identify of Jane Doe in {JANE_DOE_V_EPSTEIN_TRUMP}"),
+    DocCfg(id='031972', author=NYT, description=f"article about #MeToo allegations against {LAWRENCE_KRAUSS}", date='2018-03-07'),
+    DocCfg(id='032435', author=NYT, description=f'article about Chinese butlers'),
+    DocCfg(id='029452', author=NYT, description=f"article about {PETER_THIEL}"),
+    DocCfg(id='025328', author=NYT, description=f"article about radio host Bob Fass and Robert Durst"),
+    DocCfg(id='033479', author=NYT, description=f"article about Rex Tillerson", date='2010-03-14'),
+    DocCfg(id='028481', author=NYT, description=f'article about {STEVE_BANNON}', date='2018-03-09'),
+    DocCfg(id='033181', author=NYT, description=f"article about Trump's tax avoidance", date='2016-10-31'),
+    DocCfg(id='023097', author=NYT, description=f"column about The Aristocrats by Frank Rich 'The Greatest Dirty Joke Ever Told'"),
+    DocCfg(id='033365', author=NYT, description=f'column about trade war with China by Kevin Rudd'),
+    DocCfg(id='019439', author=NYT, description=f"column about the Clintons and money by Maureen Dowd", date='2013-08-17'),
+    DocCfg(id='029925', author=f'New Yorker', description=f"article about the placebo effect by Michael Specter"),
+    DocCfg(id='013435', author=PALM_BEACH_DAILY_NEWS, description=f"article about Epstein's address book", date='2011-03-11'),
+    DocCfg(id='013440', author=PALM_BEACH_DAILY_NEWS, description=f"article about Epstein's gag order", date='2011-07-13'),
+    DocCfg(id='029238', author=PALM_BEACH_DAILY_NEWS, description=f"article about Epstein's plea deal"),
+    DocCfg(id='021775', author=PALM_BEACH_POST, description="article about 'He Was 50. And They Were Girls'"),
+    DocCfg(id='022989', author=PALM_BEACH_POST, description="article about alleged rape of 13 year old by Trump"),
+    DocCfg(id='022987', author=PALM_BEACH_POST, description="article about just a headline on Trump and Epstein"),
+    DocCfg(id='015028', author=PALM_BEACH_POST, description="article about reopening Epstein's criminal case"),
+    DocCfg(id='022990', author=PALM_BEACH_POST, description="article about Trump and Epstein"),
     DocCfg(id='031753', author=PAUL_KRASSNER, description=f'essay for Playboy in the 1980s', date='1985-01-01'),
     DocCfg(id='023638', author=PAUL_KRASSNER, description=f'magazine interview'),
     DocCfg(id='024374', author=PAUL_KRASSNER, description=f"Remembering Cavalier Magazine"),
@@ -851,6 +968,7 @@ OTHER_FILES_ARTICLES = [
     DocCfg(id='013450', author=PEGGY_SIEGAL, description=f"Oscar Diary in Avenue Magazine", date='2011-02-27'),
     DocCfg(id='010715', author=PEGGY_SIEGAL, description=f"Oscar Diary April", date='2012-02-27'),
     DocCfg(id='019849', author=PEGGY_SIEGAL, description=f"Oscar Diary April", date='2017-02-27', duplicate_ids=['019864']),
+    DocCfg(id='026851', author='Politifact', description=f"lying politicians chart", date='2016-07-26'),
     DocCfg(id='033253', author=ROBERT_LAWRENCE_KUHN, description=f'{BBC} article about Rohingya in Myanmar'),
     DocCfg(id='026887', author=ROBERT_LAWRENCE_KUHN, description=f'{BBC} "New Tariffs - Trade War"'),
     DocCfg(id='026877', author=ROBERT_LAWRENCE_KUHN, description=f'{CNN} "New Tariffs - Trade War"'),
@@ -859,8 +977,41 @@ OTHER_FILES_ARTICLES = [
     DocCfg(id='029176', author=ROBERT_LAWRENCE_KUHN, description=f'{CNN} "U.S. China Tariffs - Trade War"'),
     DocCfg(id='032638', author=ROBERT_LAWRENCE_KUHN, description=f'{CNN} "Xi Jinping and the New Politburo Committee"'),
     DocCfg(id='023666', author=ROBERT_LAWRENCE_KUHN, description=f"sizzle reel / television appearances"),
+    DocCfg(id='016996', author=f'SciencExpress', description=f'article "Quantitative Analysis of Culture Using Millions of Digitized Books" by Jean-Baptiste Michel'),
     DocCfg(id='025104', author='SCMP', description=f"article about China and globalisation"),
-    DocCfg(id='033379', author=WAPO, description=f'How Washington Pivoted From Finger-Wagging to Appeasement (about Viktor Orban)', date='2018-05-25'),
+    DocCfg(id='030030', author=SHIMON_POST, description=SHIMON_POST_ARTICLE, date='2011-03-29'),
+    DocCfg(id='025610', author=SHIMON_POST, description=SHIMON_POST_ARTICLE, date='2011-04-03'),
+    DocCfg(id='023458', author=SHIMON_POST, description=SHIMON_POST_ARTICLE, date='2011-04-17'),
+    DocCfg(id='023487', author=SHIMON_POST, description=SHIMON_POST_ARTICLE, date='2011-04-18'),
+    DocCfg(id='030531', author=SHIMON_POST, description=SHIMON_POST_ARTICLE, date='2011-05-16'),
+    DocCfg(id='024958', author=SHIMON_POST, description=SHIMON_POST_ARTICLE, date='2011-05-08'),
+    DocCfg(id='030060', author=SHIMON_POST, description=SHIMON_POST_ARTICLE, date='2011-05-13'),
+    DocCfg(id='031834', author=SHIMON_POST, description=SHIMON_POST_ARTICLE, date='2011-05-16'),
+    DocCfg(id='023517', author=SHIMON_POST, description=SHIMON_POST_ARTICLE, date='2011-05-26'),
+    DocCfg(id='030268', author=SHIMON_POST, description=SHIMON_POST_ARTICLE, date='2011-05-29'),
+    DocCfg(id='029628', author=SHIMON_POST, description=SHIMON_POST_ARTICLE, date='2011-06-04'),
+    DocCfg(id='018085', author=SHIMON_POST, description=SHIMON_POST_ARTICLE, date='2011-06-07'),
+    DocCfg(id='030156', author=SHIMON_POST, description=SHIMON_POST_ARTICLE, date='2011-06-22'),
+    DocCfg(id='031876', author=SHIMON_POST, description=SHIMON_POST_ARTICLE, date='2011-06-14'),
+    DocCfg(id='032171', author=SHIMON_POST, description=SHIMON_POST_ARTICLE, date='2011-06-26'),
+    DocCfg(id='029932', author=SHIMON_POST, description=SHIMON_POST_ARTICLE, date='2011-07-03'),
+    DocCfg(id='031913', author=SHIMON_POST, description=SHIMON_POST_ARTICLE, date='2011-08-24'),
+    DocCfg(id='024592', author=SHIMON_POST, description=SHIMON_POST_ARTICLE, date='2011-08-25'),
+    DocCfg(id='024997', author=SHIMON_POST, description=SHIMON_POST_ARTICLE, date='2011-09-08'),
+    DocCfg(id='031941', author=SHIMON_POST, description=SHIMON_POST_ARTICLE, date='2011-11-17'),
+    DocCfg(id='030829', author=f'South Florida Sun Sentinel', description=f'article about {BRAD_EDWARDS} and {JEFFREY_EPSTEIN}'),
+    DocCfg(id='021092', author='Tatler', description=f'{SINGLE_PAGE} of article about {GHISLAINE_MAXWELL} shredding documents', date='2019-08-15'),
+    DocCfg(id='030333', author=f'The Independent', description=f'article about Prince Andrew, Epstein, and Epstein\'s butler who stole his address book'),
+    DocCfg(id='010754', author=f'U.S. News', description=f"article about Yitzhak Rabin"),
+    DocCfg(id='014498', author=VI_DAILY_NEWS, description='article', date='2016-12-13'),
+    DocCfg(id='031171', author=VI_DAILY_NEWS, description='article', date='2019-02-06'),
+    DocCfg(id='023048', author=VI_DAILY_NEWS, description='article', date='2019-02-27'),
+    DocCfg(id='023046', author=VI_DAILY_NEWS, description='article', date='2019-02-27'),
+    DocCfg(id='031170', author=VI_DAILY_NEWS, description='article', date='2019-03-06'),
+    DocCfg(id='016506', author=VI_DAILY_NEWS, description='article', date='2019-02-28'),
+    DocCfg(id='016507', author=VI_DAILY_NEWS, description=f"'Perversion of Justice' by {JULIE_K_BROWN}", date='2018-12-19'),
+    DocCfg(id='019212', author=WAPO, description=f'and Times Tribune articles about Bannon, Trump, and healthcare execs'),
+    DocCfg(id='033379', author=WAPO, description=f'"How Washington Pivoted From Finger-Wagging to Appeasement" (about Viktor Orban)', date='2018-05-25'),
     DocCfg(
         id='031396',
         author=WAPO,
@@ -868,235 +1019,185 @@ OTHER_FILES_ARTICLES = [
         date='2019-02-06',
         duplicate_ids=['031415'],
     ),
+
     DocCfg(
         id='030199',
         description=f'article about allegations Trump raped a 13 year old girl {JANE_DOE_V_EPSTEIN_TRUMP}',
         date='2017-11-16',
     ),
     DocCfg(id='031725', description=f"article about Gloria Allred and Trump allegations", date='2016-10-10'),
-    DocCfg(id='031198', description=f"article about identify of Jane Doe in {JANE_DOE_V_EPSTEIN_TRUMP}"),
-    DocCfg(id='012704', description=f"article about {JANE_DOE_V_USA} and {CVRA}", date='2011-04-21'),
     DocCfg(id='026648', description=f'article about {JASTA} lawsuit against Saudi Arabia by 9/11 victims (Russian propaganda?)', date='2017-05-13'),
-    DocCfg(id='031776', description=f"article about Michael Avenatti by Andrew Strickler"),
     DocCfg(id='032159', description=f"article about microfinance and cell phones in Zimbabwe, Strive Masiyiwa (Econet Wireless)"),
-    DocCfg(id='026584', description=f"article about tax implications of 'disregarded entities'", date='2009-07-01'),
-    DocCfg(id='030258', description=f'{ARTICLE_DRAFT} Mueller probe, almost same as 030248'),
-    DocCfg(id='030248', description=f'{ARTICLE_DRAFT} Mueller probe, almost same as 030258'),
-    DocCfg(id='029165', description=f'{ARTICLE_DRAFT} Mueller probe, almost same as 030258'),
     DocCfg(id='033468', description=f'{ARTICLE_DRAFT} Rod Rosenstein', date='2018-09-24'),
     DocCfg(id='030825', description=f'{ARTICLE_DRAFT} Syria'),
-    DocCfg(id='030013', description=f'Aviation International News article', date='2012-07-01'),
-    DocCfg(id='014865', description=f"Boston Globe article about {ALAN_DERSHOWITZ}"),
-    DocCfg(id='033231', description=f"Business Standard article about Trump's visit with India's Modi"),
-    DocCfg(id='023567', description=f"Financial Times article about quantitative easing"),
-    DocCfg(id='026761', description=f"Forbes article about {BARBRO_C_EHNBOM} 'Swedish American Group Focuses On Cancer'"),
-    DocCfg(id='031716', description=f'Fortune Magazine article by {TOM_BARRACK}', date='2016-10-22'),
     DocCfg(
         id='019233',
         description=f"Freedom House: 'Breaking Down Democracy: Goals, Strategies, and Methods of Modern Authoritarians'",
         date='2017-06-02',
     ),
-    DocCfg(id='019444', description=f"Frontlines magazine article 'Biologists Dig Deeper'", date='2008-01-01'),
-    DocCfg(id='023720', description=f'Future Science article: "Is Shame Necessary?" by {JENNIFER_JACQUET}'),
     DocCfg(id='027051', description=f"German language article about the 2013 Lifeball / AIDS Gala", date='2013-01-01'),
-    DocCfg(id='021094', description=f"Globe and Mail article about Gerd Heinrich"),
-    DocCfg(id='013268', description=f"JetGala article about airplane interior designer {ERIC_ROTH}"),
     DocCfg(id='033480', description=f"{JOHN_BOLTON_PRESS_CLIPPING}", date='2018-04-06', duplicate_ids=['033481']),
     DocCfg(id='013403', description=f"Lexis Nexis result from The Evening Standard about Bernie Madoff", date='2009-12-24'),
-    DocCfg(id='023102', description=f"Litigation Daily article about {REID_WEINGARTEN}", date='2015-09-04'),
-    DocCfg(id='029340', description=f'MarketWatch article about estate taxes, particularly Epstein\'s favoured GRATs'),
-    DocCfg(
-        id='029416',
-        description=f"National Enquirer / Radar Online v. FBI FOIA lawsuit court filing",
-        date='2017-05-25',
-        duplicate_ids=['029405']
-    ),
     DocCfg(id='015462', description=f'Nautilus Education magazine (?) issue'),
-    DocCfg(id='029925', description=f"New Yorker article about the placebo effect by Michael Specter"),
-    DocCfg(id='031972', description=f"{NYT_ARTICLE} #MeToo allegations against {LAWRENCE_KRAUSS}", date='2018-03-07'),
-    DocCfg(id='032435', description=f'{NYT_ARTICLE} Chinese butlers'),
-    DocCfg(id='029452', description=f"{NYT_ARTICLE} {PETER_THIEL}"),
-    DocCfg(id='025328', description=f"{NYT_ARTICLE} radio host Bob Fass and Robert Durst"),
-    DocCfg(id='033479', description=f"{NYT_ARTICLE} Rex Tillerson", date='2010-03-14'),
-    DocCfg(id='028481', description=f'{NYT_ARTICLE} {STEVE_BANNON}', date='2018-03-09'),
-    DocCfg(id='033181', description=f'{NYT_ARTICLE} Trump\'s tax avoidance', date='2016-10-31'),
-    DocCfg(id='023097', description=f"{NYT_COLUMN} The Aristocrats by Frank Rich 'The Greatest Dirty Joke Ever Told'"),
-    DocCfg(id='033365', description=f'{NYT_COLUMN} trade war with China by Kevin Rudd'),
-    DocCfg(id='019439', description=f"{NYT_COLUMN} the Clintons and money by Maureen Dowd", date='2013-08-17'),
     DocCfg(id='021093', description=f"page of unknown article about Epstein and Maxwell"),
-    DocCfg(id='013435', description=f"{PALM_BEACH_DAILY_ARTICLE} Epstein's address book", date='2011-03-11'),
-    DocCfg(id='013440', description=f"{PALM_BEACH_DAILY_ARTICLE} Epstein's gag order", date='2011-07-13'),
-    DocCfg(id='029238', description=f"{PALM_BEACH_DAILY_ARTICLE} Epstein's plea deal"),
-    DocCfg(id='021775', description=f"{PALM_BEACH_POST_ARTICLE} 'He Was 50. And They Were Girls'"),
-    DocCfg(id='022989', description=f"{PALM_BEACH_POST_ARTICLE} alleged rape of 13 year old by Trump"),
-    DocCfg(id='022987', description=f"{PALM_BEACH_POST_ARTICLE} just a headline on Trump and Epstein"),
-    DocCfg(id='015028', description=f"{PALM_BEACH_POST_ARTICLE} reopening Epstein's criminal case"),
-    DocCfg(id='022990', description=f"{PALM_BEACH_POST_ARTICLE} Trump and Epstein"),
-    DocCfg(id='016996', description=f'SciencExpress article "Quantitative Analysis of Culture Using Millions of Digitized Books" by Jean-Baptiste Michel'),
-    DocCfg(id='030030', description=SHIMON_POST_ARTICLE, date='2011-03-29'),
-    DocCfg(id='025610', description=SHIMON_POST_ARTICLE, date='2011-04-03'),
-    DocCfg(id='023458', description=SHIMON_POST_ARTICLE, date='2011-04-17'),
-    DocCfg(id='023487', description=SHIMON_POST_ARTICLE, date='2011-04-18'),
-    DocCfg(id='030531', description=SHIMON_POST_ARTICLE, date='2011-05-16'),
-    DocCfg(id='024958', description=SHIMON_POST_ARTICLE, date='2011-05-08'),
-    DocCfg(id='030060', description=SHIMON_POST_ARTICLE, date='2011-05-13'),
-    DocCfg(id='031834', description=SHIMON_POST_ARTICLE, date='2011-05-16'),
-    DocCfg(id='023517', description=SHIMON_POST_ARTICLE, date='2011-05-26'),
-    DocCfg(id='030268', description=SHIMON_POST_ARTICLE, date='2011-05-29'),
-    DocCfg(id='029628', description=SHIMON_POST_ARTICLE, date='2011-06-04'),
-    DocCfg(id='018085', description=SHIMON_POST_ARTICLE, date='2011-06-07'),
-    DocCfg(id='030156', description=SHIMON_POST_ARTICLE, date='2011-06-22'),
-    DocCfg(id='031876', description=SHIMON_POST_ARTICLE, date='2011-06-14'),
-    DocCfg(id='032171', description=SHIMON_POST_ARTICLE, date='2011-06-26'),
-    DocCfg(id='029932', description=SHIMON_POST_ARTICLE, date='2011-07-03'),
-    DocCfg(id='031913', description=SHIMON_POST_ARTICLE, date='2011-08-24'),
-    DocCfg(id='024592', description=SHIMON_POST_ARTICLE, date='2011-08-25'),
-    DocCfg(id='024997', description=SHIMON_POST_ARTICLE, date='2011-09-08'),
-    DocCfg(id='031941', description=SHIMON_POST_ARTICLE, date='2011-11-17'),
-    DocCfg(id='021092', description=f'{SINGLE_PAGE} Tatler article about {GHISLAINE_MAXWELL} shredding documents', date='2019-08-15'),
     DocCfg(id='031191', description=f"{SINGLE_PAGE} unknown article about Epstein and Trump's relationship in 1997"),
-    DocCfg(id='030829', description=f'South Florida Sun Sentinel article about {BRAD_EDWARDS} and {JEFFREY_EPSTEIN}'),
     DocCfg(id='026520', description=f'Spanish language article about {SULTAN_BIN_SULAYEM}', date='2013-09-27'),
-    DocCfg(id='030333', description=f'The Independent article about Prince Andrew, Epstein, and Epstein\'s butler who stole his address book'),
     DocCfg(
         id='031736',
         description=f"{TRANSLATION} Arabic article by Abdulnaser Salamah 'Trump; Prince of Believers (Caliph)!'",
         date='2017-05-13',
     ),
     DocCfg(id='025094', description=f'{TRANSLATION} Spanish article about Cuba', date='2015-11-08'),
-    DocCfg(id='010754', description=f"U.S. News article about Yitzhak Rabin"),
     DocCfg(id='031794', description=f"very short French magazine clipping"),
-    DocCfg(id='014498', description=VI_DAILY_NEWS_ARTICLE, date='2016-12-13'),
-    DocCfg(id='031171', description=VI_DAILY_NEWS_ARTICLE, date='2019-02-06'),
-    DocCfg(id='023048', description=VI_DAILY_NEWS_ARTICLE, date='2019-02-27'),
-    DocCfg(id='023046', description=VI_DAILY_NEWS_ARTICLE, date='2019-02-27'),
-    DocCfg(id='031170', description=VI_DAILY_NEWS_ARTICLE, date='2019-03-06'),
-    DocCfg(id='016506', description=VI_DAILY_NEWS_ARTICLE, date='2019-02-28'),
-    DocCfg(id='016507', description=f"{VI_DAILY_NEWS_ARTICLE} 'Perversion of Justice' by {JULIE_K_BROWN}", date='2018-12-19'),
-    DocCfg(id='019212', description=f'{WAPO} and Times Tribune articles about Bannon, Trump, and healthcare execs'),
 ]
 
 OTHER_FILES_LEGAL = [
+    DocCfg(id='011908', author=BRUNEL_V_EPSTEIN, description=f"court filing"),
     DocCfg(id='025353', author=KEN_STARR, description=KEN_STARR_LETTER, date='2008-05-19', duplicate_ids=['010723', '019224'], dupe_type='redacted'),
     DocCfg(id='025704', author=KEN_STARR, description=KEN_STARR_LETTER, date='2008-05-27', duplicate_ids=['010732', '019221'], dupe_type='redacted'),
     DocCfg(id='012130', author=KEN_STARR, description=KEN_STARR_LETTER, date='2008-06-19', duplicate_ids=['012135']),
-    DocCfg(id='011908', description=f"{BRUNEL_V_EPSTEIN} and Tyler McDonald d/b/a YI.org court filing"),
-    DocCfg(id='017603', description=DAVID_SCHOEN_CVRA_LEXIS_SEARCH, date='2019-02-28'),
-    DocCfg(id='017635', description=DAVID_SCHOEN_CVRA_LEXIS_SEARCH, date='2019-02-28'),
-    DocCfg(id='016509', description=DAVID_SCHOEN_CVRA_LEXIS_SEARCH, date='2019-02-28'),
-    DocCfg(id='017714', description=DAVID_SCHOEN_CVRA_LEXIS_SEARCH, date='2019-02-28'),
-    DocCfg(id='021824', description=f"{EDWARDS_V_DERSHOWITZ} deposition of {PAUL_G_CASSELL}"),
+    DocCfg(id='021824', author=EDWARDS_V_DERSHOWITZ, description=f"deposition of {PAUL_G_CASSELL}"),
     DocCfg(
         id='010757',
-        description=f"{EDWARDS_V_DERSHOWITZ} plaintiff response to Dershowitz Motion to Determine Confidentiality of Court Records",
+        author=EDWARDS_V_DERSHOWITZ,
+        description=f"plaintiff response to Dershowitz Motion to Determine Confidentiality of Court Records",
         date='2015-11-23',
     ),
     DocCfg(
         id='010887',
-        description=f"{EDWARDS_V_DERSHOWITZ} Dershowitz Motion for Clarification of Confidentiality Order",
+        author=EDWARDS_V_DERSHOWITZ,
+        description=f"Dershowitz Motion for Clarification of Confidentiality Order",
         date='2016-01-29',
     ),
     DocCfg(
         id='015590',
-        description=f"{EDWARDS_V_DERSHOWITZ} Dershowitz Redacted Motion to Modify Confidentiality Order",
+        author=EDWARDS_V_DERSHOWITZ,
+        description=f"Dershowitz Redacted Motion to Modify Confidentiality Order",
         date='2016-02-03',
     ),
     DocCfg(
         id='015650',
-        description=f"{EDWARDS_V_DERSHOWITZ} Giuffre Response to Dershowitz Motion for Clarification of Confidentiality Order",
+        author=EDWARDS_V_DERSHOWITZ,
+        description=f"Giuffre Response to Dershowitz Motion for Clarification of Confidentiality Order",
         date='2016-02-08',
     ),
-    DocCfg(id='010566', description=f"{EPSTEIN_V_ROTHSTEIN_EDWARDS} Statement of Undisputed Facts", date='2010-11-04'),
-    DocCfg(id='012707', description=f"{EPSTEIN_V_ROTHSTEIN_EDWARDS} Master Contact List - Privilege Log", date='2011-03-22'),
-    DocCfg(id='012103', description=f"{EPSTEIN_V_ROTHSTEIN_EDWARDS} Telephone Interview with {VIRGINIA_GIUFFRE}", date='2011-05-17'),
-    DocCfg(id='017488', description=f"{EPSTEIN_V_ROTHSTEIN_EDWARDS} Deposition of Scott Rothstein", date='2012-06-22'),
-    DocCfg(id='029315', description=f"{EPSTEIN_V_ROTHSTEIN_EDWARDS} Plaintiff Motion for Summary Judgment by {JACK_SCAROLA}", date='2013-09-13'),
-    DocCfg(id='013304', description=f"{EPSTEIN_V_ROTHSTEIN_EDWARDS} Plaintiff Response to Epstein's Motion for Summary Judgment", date='2014-04-17'),
+    DocCfg(id='010566', author=EPSTEIN_V_ROTHSTEIN_EDWARDS, description=f"Statement of Undisputed Facts", date='2010-11-04'),
+    DocCfg(id='012707', author=EPSTEIN_V_ROTHSTEIN_EDWARDS, description=f"Master Contact List - Privilege Log", date='2011-03-22'),
+    DocCfg(id='012103', author=EPSTEIN_V_ROTHSTEIN_EDWARDS, description=f"Telephone Interview with {VIRGINIA_GIUFFRE}", date='2011-05-17'),
+    DocCfg(id='017488', author=EPSTEIN_V_ROTHSTEIN_EDWARDS, description=f"Deposition of Scott Rothstein", date='2012-06-22'),
+    DocCfg(id='029315', author=EPSTEIN_V_ROTHSTEIN_EDWARDS, description=f"Plaintiff Motion for Summary Judgment by {JACK_SCAROLA}", date='2013-09-13'),
+    DocCfg(id='013304', author=EPSTEIN_V_ROTHSTEIN_EDWARDS, description=f"Plaintiff Response to Epstein's Motion for Summary Judgment", date='2014-04-17'),
     DocCfg(id='019352', description=FBI_REPORT,),
     DocCfg(id='021434', description=FBI_REPORT,),
     DocCfg(id='018872', description=FBI_SEIZED_PROPERTY,),
     DocCfg(id='021569', description=FBI_SEIZED_PROPERTY,),
-    DocCfg(id='017792', description=f"{GIUFFRE_V_DERSHOWITZ} article about {ALAN_DERSHOWITZ}'s appearance on Wolf Blitzer"),
-    DocCfg(id='017767', description=f"{GIUFFRE_V_DERSHOWITZ} article about {ALAN_DERSHOWITZ} working with {JEFFREY_EPSTEIN}"),
-    DocCfg(id='017796', description=f"{GIUFFRE_V_DERSHOWITZ} article about {ALAN_DERSHOWITZ}"),
-    DocCfg(id='017935', description=f"{GIUFFRE_V_DERSHOWITZ} defamation complaint", date='2019-04-16'),
-    DocCfg(id='017824', description=f"{GIUFFRE_V_DERSHOWITZ} {MIAMI_HERALD} article by {JULIE_K_BROWN}"),
+    DocCfg(id='017792', author=GIUFFRE_V_DERSHOWITZ, description=f"article about {ALAN_DERSHOWITZ}'s appearance on Wolf Blitzer"),
+    DocCfg(id='017767', author=GIUFFRE_V_DERSHOWITZ, description=f"article about {ALAN_DERSHOWITZ} working with {JEFFREY_EPSTEIN}"),
+    DocCfg(id='017796', author=GIUFFRE_V_DERSHOWITZ, description=f"article about {ALAN_DERSHOWITZ}"),
+    DocCfg(id='017935', author=GIUFFRE_V_DERSHOWITZ, description=f"defamation complaint", date='2019-04-16'),
+    DocCfg(id='017824', author=GIUFFRE_V_DERSHOWITZ, description=f"{MIAMI_HERALD} article by {JULIE_K_BROWN}"),
     DocCfg(
         id='017818',
-        description=f"{GIUFFRE_V_DERSHOWITZ} {MIAMI_HERALD} article about accusations against {ALAN_DERSHOWITZ} by {JULIE_K_BROWN}",
+        author=GIUFFRE_V_DERSHOWITZ,
+        description=f"{MIAMI_HERALD} article about accusations against {ALAN_DERSHOWITZ} by {JULIE_K_BROWN}",
         date='2018-12-27',
     ),
-    DocCfg(id='017800', description=f'{GIUFFRE_V_DERSHOWITZ} {MIAMI_HERALD} "Perversion of Justice" by {JULIE_K_BROWN}'),
-    DocCfg(id='022237', description=f"{GIUFFRE_V_DERSHOWITZ} partial court filing with fact checking questions?"),
-    DocCfg(id='016197', description=f"{GIUFFRE_V_DERSHOWITZ} response to Florida Bar complaint by {ALAN_DERSHOWITZ} about David Boies from {PAUL_G_CASSELL}"),
-    DocCfg(id='017771', description=f'{GIUFFRE_V_DERSHOWITZ} Vanity Fair article "The Talented Mr. Epstein" by Vicky Ward', date='2011-06-27'),
-    DocCfg(id='014118', description=f"{GIUFFRE_V_EPSTEIN} Declaration in Support of Motion to Compel Production of Documents", date='2016-10-21'),
-    DocCfg(id='014652', description=f"{GIUFFRE_V_MAXWELL} Complaint", date='2015-04-22'),
-    DocCfg(id='015529', description=f"{GIUFFRE_V_MAXWELL} Defamation Complaint", date='2015-09-21'),
-    DocCfg(id='014797', description=f"{GIUFFRE_V_MAXWELL} Declaration of Laura A. Menninger in Opposition to Plaintiff's Motion", date='2017-03-17'),
-    DocCfg(id='011304', description=f"{GIUFFRE_V_MAXWELL} Oral Argument Transcript", date='2017-03-17'),
+    DocCfg(id='017800', author=GIUFFRE_V_DERSHOWITZ, description=f'{MIAMI_HERALD} "Perversion of Justice" by {JULIE_K_BROWN}'),
+    DocCfg(id='022237', author=GIUFFRE_V_DERSHOWITZ, description=f"partial court filing with fact checking questions?"),
+    DocCfg(id='016197', author=GIUFFRE_V_DERSHOWITZ, description=f"response to Florida Bar complaint by {ALAN_DERSHOWITZ} about David Boies from {PAUL_G_CASSELL}"),
+    DocCfg(id='017771', author=GIUFFRE_V_DERSHOWITZ, description=f'Vanity Fair article "The Talented Mr. Epstein" by Vicky Ward', date='2011-06-27'),
+    DocCfg(id='014118', author=GIUFFRE_V_EPSTEIN, description=f"Declaration in Support of Motion to Compel Production of Documents", date='2016-10-21'),
+    DocCfg(id='014652', author=GIUFFRE_V_MAXWELL, description=f"Complaint", date='2015-04-22'),
+    DocCfg(id='015529', author=GIUFFRE_V_MAXWELL, description=f"Defamation Complaint", date='2015-09-21'),
+    DocCfg(id='014797', author=GIUFFRE_V_MAXWELL, description=f"Declaration of Laura A. Menninger in Opposition to Plaintiff's Motion", date='2017-03-17'),
+    DocCfg(id='011304', author=GIUFFRE_V_MAXWELL, description=f"Oral Argument Transcript", date='2017-03-17'),
     DocCfg(
         id='014788',
-        description=f"{GIUFFRE_V_MAXWELL} Maxwell Response to Plaintiff's Omnibus Motion in Limine",
+        author=GIUFFRE_V_MAXWELL,
+        description=f"Maxwell Response to Plaintiff's Omnibus Motion in Limine",
         date='2017-03-17',
         duplicate_ids=['011463'],
     ),
     DocCfg(
         id='019297',
-        description=f'{GIUFFRE_V_MAXWELL} letter from {ALAN_DERSHOWITZ} lawyer Andrew G. Celli',
+        author=GIUFFRE_V_MAXWELL,
+        description=f'letter from {ALAN_DERSHOWITZ} lawyer Andrew G. Celli',
         date='2018-02-07'
     ),
-    DocCfg(
-        id='025937',
-        description=f'{JANE_DOE_V_EPSTEIN_TRUMP} Affidavit of Tiffany Doe describing Jane Doe being raped by Epstein and Trump',
-        date='2016-06-20',
-    ),
-    DocCfg(id='025939', description=f'{JANE_DOE_V_EPSTEIN_TRUMP} Affidavit of Jane Doe describing being raped by Epstein', date='2016-06-20'),
-    DocCfg(id='013489', description=f'{JANE_DOE_V_EPSTEIN_TRUMP} Affidavit of {BRAD_EDWARDS}', date='2010-07-20'),
-    DocCfg(id='029398', description=f'{JANE_DOE_V_EPSTEIN_TRUMP} article in Law.com'),
-    DocCfg(id='026854', description=f"{JANE_DOE_V_EPSTEIN_TRUMP} Civil Docket"),
-    DocCfg(id='026384', description=f"{JANE_DOE_V_EPSTEIN_TRUMP} Complaint for rape and sexual abuse", date='2016-06-20'),
-    DocCfg(id='013463', description=f'{JANE_DOE_V_EPSTEIN_TRUMP} Deposition of Scott Rothstein', date='2010-03-23'),
-    DocCfg(id='029257', description=f'{JANE_DOE_V_EPSTEIN_TRUMP} allegations and identity of plaintiff Katie Johnson', date='2016-04-26'),
-    DocCfg(id='032321', description=f"{JANE_DOE_V_EPSTEIN_TRUMP} Notice of Initial Conference", date='2016-10-04'),
-    DocCfg(id='010735', description=f"{JANE_DOE_V_USA} Dershowitz Reply in Support of Motion for Limited Intervention", date='2015-02-02'),
-    DocCfg(id='014084', description=f"{JANE_DOE_V_USA} Jane Doe Response to Dershowitz's Motion for Limited Intervention", date='2015-03-24'),
-    DocCfg(id='023361', description=f"{JASTA_SAUDI_LAWSUIT} legal text and court documents", date='2012-01-20'),
-    DocCfg(id='017830', description=f"{JASTA_SAUDI_LAWSUIT} legal text and court documents"),
-    DocCfg(id='017904', description=f"{JASTA_SAUDI_LAWSUIT} Westlaw search results", date='2019-01-01'),
-    DocCfg(id='014037', description=f"Journal of Criminal Law and Criminology article on {CVRA}"),
-    DocCfg(id='020662', description=f"letter from {ALAN_DERSHOWITZ}'s British lawyers Mishcon de Reya to Daily Mail threatening libel suit"),
     DocCfg(
         id='010560',
-        description=f"letter from Gloria Allred to {SCOTT_J_LINK} alleging abuse of a girl from Kansas",
+        author='Gloria Allred',
+        description=f"letter to {SCOTT_J_LINK} alleging abuse of a girl from Kansas",
         date='2019-06-19',
     ),
+    DocCfg(
+        id='025937',
+        author=JANE_DOE_V_EPSTEIN_TRUMP,
+        description=f'Affidavit of Tiffany Doe describing Jane Doe being raped by Epstein and Trump',
+        date='2016-06-20',
+    ),
+    DocCfg(id='025939', author=JANE_DOE_V_EPSTEIN_TRUMP, description=f'Affidavit of Jane Doe describing being raped by Epstein', date='2016-06-20'),
+    DocCfg(id='013489', author=JANE_DOE_V_EPSTEIN_TRUMP, description=f'Affidavit of {BRAD_EDWARDS}', date='2010-07-20'),
+    DocCfg(id='029398', author=JANE_DOE_V_EPSTEIN_TRUMP, description=f'article in Law.com'),
+    DocCfg(id='026854', author=JANE_DOE_V_EPSTEIN_TRUMP, description=f"Civil Docket"),
+    DocCfg(id='026384', author=JANE_DOE_V_EPSTEIN_TRUMP, description=f"Complaint for rape and sexual abuse", date='2016-06-20'),
+    DocCfg(id='013463', author=JANE_DOE_V_EPSTEIN_TRUMP, description=f'Deposition of Scott Rothstein', date='2010-03-23'),
+    DocCfg(id='029257', author=JANE_DOE_V_EPSTEIN_TRUMP, description=f'allegations and identity of plaintiff Katie Johnson', date='2016-04-26'),
+    DocCfg(id='032321', author=JANE_DOE_V_EPSTEIN_TRUMP, description=f"Notice of Initial Conference", date='2016-10-04'),
+    DocCfg(id='010735', author=JANE_DOE_V_USA, description=f"Dershowitz Reply in Support of Motion for Limited Intervention", date='2015-02-02'),
+    DocCfg(id='014084', author=JANE_DOE_V_USA, description=f"Jane Doe Response to Dershowitz's Motion for Limited Intervention", date='2015-03-24'),
+    DocCfg(id='023361', author=JASTA_SAUDI_LAWSUIT, description=f"legal text and court documents", date='2012-01-20'),
+    DocCfg(id='017830', author=JASTA_SAUDI_LAWSUIT, description=f"legal text and court documents"),
+    DocCfg(id='017904', author=JASTA_SAUDI_LAWSUIT, description=f"Westlaw search results", date='2019-01-01'),
+    DocCfg(id='014037', author='Journal of Criminal Law and Criminology', description=f"article on {CVRA}"),
     DocCfg(
         id='031447',
-        description=f"letter from {MARTIN_WEINBERG} to Melanie Ann Pustay and Sean O'Neill re: an Epstein FOIA request"
+        author=MARTIN_WEINBERG,
+        description=f"letter from to Melanie Ann Pustay and Sean O'Neill re: an Epstein FOIA request"
     ),
     DocCfg(
         id='028965',
-        description=f"letter from {MARTIN_WEINBERG} to ABC / Good Morning America threatening libel lawsuit",
+        author=MARTIN_WEINBERG,
+        description=f"letter from to ABC / Good Morning America threatening libel lawsuit",
         duplicate_ids=['028928']
     ),
     DocCfg(
-        id='026793',
-        description=f"letter from {STEVEN_HOFFENBERG}'s lawyers at Mintz Fraade offering to take over Epstein's business and resolve his legal issues",
-        date='2018-03-23',
+        id='029416',
+        author="National Enquirer / Radar Online v. FBI",
+        description=f"FOIA lawsuit filing",
+        date='2017-05-25',
+        duplicate_ids=['029405']
     ),
     DocCfg(
         id='016420',
-        description=f"{NEW_YORK_V_EPSTEIN} New York Post Motion to Unseal Appellate Briefs",
+        author=NEW_YORK_V_EPSTEIN,
+        description=f"New York Post Motion to Unseal Appellate Briefs",
         date='2019-01-11',
     ),
-    DocCfg(id='028540', description=f"SCOTUS decision in Budha Ismail Jam et al. v. INTERNATIONAL FINANCE CORP"),
-    DocCfg(id='012197', description=f"SDFL Response to {JAY_LEFKOWITZ} on Epstein Plea Agreement Compliance"),
+    DocCfg(id='028540', author='SCOTUS', description=f"decision in Budha Ismail Jam et al. v. INTERNATIONAL FINANCE CORP"),
+    DocCfg(id='012197', author='SDFL', description=f"Response to {JAY_LEFKOWITZ} on Epstein Plea Agreement Compliance"),
+    DocCfg(id='020662', author='Mishcon de Reya', description=f"letter from {ALAN_DERSHOWITZ}'s British lawyers to Daily Mail threatening libel suit"),
+    DocCfg(
+        id='026793',
+        description=f"letter from {STEVEN_HOFFENBERG}'s lawyers at Mintz Fraade offering to take over Epstein's business and resolve his legal issues",
+        date='2018-03-23',
+    ),
     DocCfg(id='022277', description=f"{TEXT_OF_US_LAW} National Labour Relations Board (NLRB)"),
 ]
 
 OTHER_FILES_CONFERENCES = [
     DocCfg(id='014315', author=BOFA_MERRILL, description=f'2016 Future of Financials Conference'),
+    DocCfg(id='026825', author=DEUTSCHE_BANK, description=f"Asset & Wealth Management featured speaker bios"),  # Really "Deutsche Asset" which may not be Deutsche Bank?
+    DocCfg(id='023123', author=LAWRENCE_KRAUSS_ASU_ORIGINS, description=f"{STRANGE_BEDFELLOWS} (old draft)"),
+    DocCfg(id='023120', author=LAWRENCE_KRAUSS_ASU_ORIGINS, description=STRANGE_BEDFELLOWS, duplicate_ids=['023121'], dupe_type='earlier'),
+    DocCfg(id='031359', author=NOBEL_CHARITABLE_TRUST, description=f"Earth Environment Convention about ESG investing"),
+    DocCfg(id='031354', author=NOBEL_CHARITABLE_TRUST, description=f'"Thinking About the Environment and Technology" report 2011'),
+    DocCfg(id='019300', author=SVETLANA_POZHIDAEVA, description=f'{WOMEN_EMPOWERMENT} f. {KATHRYN_RUEMMLER}', date='2019-04-05'),
+    DocCfg(id='022267', author=SVETLANA_POZHIDAEVA, description=f'{WOMEN_EMPOWERMENT} founder essay about growing the seminar business'),
+    DocCfg(id='022407', author=SVETLANA_POZHIDAEVA, description=f'{WOMEN_EMPOWERMENT} seminar pitch deck'),
+    DocCfg(id='017524', author=SWEDISH_LIFE_SCIENCES_SUMMIT, description=f"2012 program"),
+    DocCfg(id='026747', author=SWEDISH_LIFE_SCIENCES_SUMMIT, description=f"2017 program", date='2017-08-23'),
+    DocCfg(id='014951', author='TED Talks', description=f"2017 program", date='2017-04-20'),
     DocCfg(id='024179', author=UN_GENERAL_ASSEMBLY, description=f'president and first lady schedule', date='2012-09-21'),
     DocCfg(
         id='024185',
@@ -1104,20 +1205,13 @@ OTHER_FILES_CONFERENCES = [
         description=f'schedule including "Presidents Private Dinner - Jeffrey Epstine (sic)"',
         date='2012-09-21',
     ),
-    DocCfg(id='014951', description=f"2017 TED Talks program", date='2017-04-20'),
-    DocCfg(id='026825', description=f"{DEUTSCHE_BANK} Asset & Wealth Management featured speaker bios"),  # Really "Deutsche Asset" which may not be Deutsche Bank?
+    DocCfg(id='017603', description=DAVID_SCHOEN_CVRA_LEXIS_SEARCH, date='2019-02-28'),
+    DocCfg(id='017635', description=DAVID_SCHOEN_CVRA_LEXIS_SEARCH, date='2019-02-28'),
+    DocCfg(id='016509', description=DAVID_SCHOEN_CVRA_LEXIS_SEARCH, date='2019-02-28'),
+    DocCfg(id='017714', description=DAVID_SCHOEN_CVRA_LEXIS_SEARCH, date='2019-02-28'),
     DocCfg(id='017526', description=f'Intellectual Jazz conference brochure f. {DAVID_BLAINE}'),
-    DocCfg(id='023120', description=f"{LAWRENCE_KRAUSS} 'Strange Bedfellows' list of invitees f. Johnny Depp, Woody Allen, Obama, and more (old draft)"),
-    DocCfg(id='023123', description=f"{LAWRENCE_KRAUSS} 'Strange Bedfellows' list of invitees f. Johnny Depp, Woody Allen, Obama, and more", duplicate_ids=['023121'], dupe_type='earlier'),
-    DocCfg(id='031359', description=f"{NOBEL_CHARITABLE_TRUST} Earth Environment Convention about ESG investing"),
-    DocCfg(id='031354', description=f'{NOBEL_CHARITABLE_TRUST} "Thinking About the Environment and Technology" report 2011'),
     DocCfg(id='029427', description=f"seems related to an IRL meeting about concerns China will attempt to absorb Mongolia"),
     DocCfg(id='025797', description=f'someone\'s notes from Aspen Strategy Group', date='2013-05-29'),
-    DocCfg(id='017524', description=f"{SWEDISH_LIFE_SCIENCES_SUMMIT} 2012 program"),
-    DocCfg(id='026747', description=f"{SWEDISH_LIFE_SCIENCES_SUMMIT} 2017 program", date='2017-08-23'),
-    DocCfg(id='019300', description=f'{WOMEN_EMPOWERMENT} f. {KATHRYN_RUEMMLER}', date='2019-04-05'),
-    DocCfg(id='022267', description=f'{WOMEN_EMPOWERMENT} founder essay about growing the seminar business'),
-    DocCfg(id='022407', description=f'{WOMEN_EMPOWERMENT} seminar pitch deck'),
     DocCfg(
         id='017060',
         description=f'World Economic Forum (WEF) Annual Meeting 2011 List of Participants',
@@ -1186,6 +1280,7 @@ OTHER_FILES_FINANCE = [
     DocCfg(id='024135', author=UBS, description=UBS_CIO_REPORT, date='2012-06-29'),
     DocCfg(id='025247', author=UBS, description=UBS_CIO_REPORT, date='2012-10-25'),
     DocCfg(id='024631', description=f"Ackrell Capital report: Cannabis Investment Report 2018"),
+    DocCfg(id='026584', description=f"article about tax implications of disregarded entities", date='2009-07-01'),
     DocCfg(id='024271', description=f"Blockchain Capital and Brock Pierce pitch deck", date='2015-10-01'),
     DocCfg(id='024817', description=f"Cowen's Collective View of CBD / Cannabis report"),
     DocCfg(id='012048', description=f"{PRESS_RELEASE} 'Rockefeller Partners with Gregory J. Fleming to Create Independent Financial Services Firm' and other articles"),
@@ -1198,6 +1293,7 @@ OTHER_FILES_FINANCE = [
 
 OTHER_FILES_LETTERS = [
     DocCfg(id='017789', author=ALAN_DERSHOWITZ, description=f'letter to {HARVARD} Crimson complaining he was defamed'),
+    DocCfg(id='026668', author="Boothbay Fund Management", description=f"2016-Q4 earnings report signed by Ari Glass"),
     DocCfg(
         id='019086',
         author=DAVID_BLAINE,
@@ -1216,7 +1312,6 @@ OTHER_FILES_LETTERS = [
         description=f"{DAVID_BLAINE_VISA_LETTER} (probably {SVETLANA_POZHIDAEVA}?)",
         date='2015-06-01',
     ),
-    DocCfg(id='031670', description=f"letter from General Mike Flynn's lawyers to senators Mark Warner & Richard Burr about subpoena"),
     DocCfg(
         id='026011',
         author='Gennady Mashtalyar',
@@ -1224,21 +1319,20 @@ OTHER_FILES_LETTERS = [
         date='2016-06-24',  # date is based on Brexit reference but he could be backtesting,
     ),
     DocCfg(id='026248', author='Don McGahn', description=f'letter from Trump lawyer to Devin Nunes (R-CA) about FISA courts and Trump'),
-    DocCfg(id='029301', author=MICHAEL_J_BOCCIO, description=f"letter from former lawyer at the Trump Organization", date='2011-08-07'),
+    DocCfg(id='029304', author=DONALD_TRUMP, description=f"recommendation letter for recently departed {TRUMP_ORG} lawyer {MICHAEL_J_BOCCIO}"),
+    DocCfg(id='029301', author=MICHAEL_J_BOCCIO, description=f"letter from former lawyer at the {TRUMP_ORG}", date='2011-08-07'),
     DocCfg(id='022405', author=NOAM_CHOMSKY, description=f"letter attesting to Epstein's good character"),
     DocCfg(id='026134', description=f'letter to someone named George about investment opportunities in the Ukraine banking sector'),
-    DocCfg(id='029304', description=f"Trump recommendation letter for recently departed Trump Organization lawyer {MICHAEL_J_BOCCIO}"),
-    DocCfg(id='026668', description=f"Boothbay Fund Management 2016-Q4 earnings report signed by Ari Glass"),
 ]
 
 OTHER_FILES_PROPERTY = [
     DocCfg(id='026759', author='Great Bay Condominium Owners Association', description=f'{PRESS_RELEASE} by about Hurricane Irma damage', date='2017-09-13'),
+    DocCfg(id='016602', author=PALM_BEACH_CODE_ENFORCEMENT, description='board minutes', date='2008-04-17'),
+    DocCfg(id='016554', author=PALM_BEACH_CODE_ENFORCEMENT, description='board minutes', date='2008-07-17', duplicate_ids=['016616', '016574']),
     DocCfg(id='027068', author=THE_REAL_DEAL, description=f"{THE_REAL_DEAL_ARTICLE} Palm House Hotel Bankruptcy and EB-5 Visa Fraud Allegations"),
     DocCfg(id='029520', author=THE_REAL_DEAL, description=f"{THE_REAL_DEAL_ARTICLE} 'Lost Paradise at the Palm House'", date='2019-06-17'),
+    DocCfg(id='016597', author='Trump Properties LLC', description=f'appeal of some decision about Mar-a-Lago by {PALM_BEACH} authorities'),
     DocCfg(id='018743', description=f"Las Vegas property listing"),
-    DocCfg(id='016597', description=f'letter from Trump Properties LLC appealing some decision about Mar-a-Lago by {PALM_BEACH} authorities'),
-    DocCfg(id='016602', description=PALM_BEACH_CODE_ENFORCEMENT, date='2008-04-17'),
-    DocCfg(id='016554', description=PALM_BEACH_CODE_ENFORCEMENT, date='2008-07-17', duplicate_ids=['016616', '016574']),
     DocCfg(id='016695', description=f"{PALM_BEACH} property info (?)"),
     DocCfg(id='016697', description=f"{PALM_BEACH} property tax info (?) that mentions Trump"),
     DocCfg(id='016599', description=f"{PALM_BEACH_TSV} consumption (water?)"),
@@ -1258,26 +1352,26 @@ OTHER_FILES_PROPERTY = [
 ]
 
 OTHER_FILES_REPUTATION = [
+    DocCfg(id='030426', author=OSBORNE_LLP, description=f"reputation repair proposal (cites Michael Milken)", date='2011-06-14'),
     DocCfg(id='026582', description=f"Epstein's internet search results at start of reputation repair campaign, maybe from {OSBORNE_LLP}"),
     DocCfg(id='030573', description=f"Epstein's unflattering Google search results, maybe screenshot by {AL_SECKEL} or {OSBORNE_LLP}"),
     DocCfg(id='030875', description=f"Epstein's Wikipedia page"),
     DocCfg(id='026583', description=f"Google search results for '{JEFFREY_EPSTEIN}' with analysis ({OSBORNE_LLP}?)"),
     DocCfg(id='029350', description=f"Microsoft Bing search results for Epstein with sex offender at top, maybe from {TYLER_SHEARS}?"),
-    DocCfg(id='030426', description=f"{OSBORNE_LLP} reputation repair proposal (cites Michael Milken)", date='2011-06-14'),
 ]
 
 # social media / InsightsPod
 OTHER_FILES_SOCIAL = [
+    DocCfg(id='023050', author=ALAN_DERSHOWITZ, description=DERSH_GIUFFRE_TWEET),
+    DocCfg(id='017787', author=ALAN_DERSHOWITZ, description=DERSH_GIUFFRE_TWEET),
+    DocCfg(id='033433', author=ALAN_DERSHOWITZ, description=f"{DERSH_GIUFFRE_TWEET} / David Boies", date='2019-03-02'),
+    DocCfg(id='033432', author=ALAN_DERSHOWITZ, description=f"{DERSH_GIUFFRE_TWEET} / David Boies", date='2019-05-02'),
     DocCfg(id='028815', author=ZUBAIR_AND_ANYA, description=f"{INSIGHTS_POD} business plan", date='2016-08-20'),
     DocCfg(id='011170', author=ZUBAIR_AND_ANYA, description=f'{INSIGHTS_POD} collected tweets about #Brexit', date='2016-06-23'),
     DocCfg(id='032324', author=ZUBAIR_AND_ANYA, description=f"{INSIGHTS_POD} election social media trend analysis", date='2016-11-05'),
     DocCfg(id='032281', author=ZUBAIR_AND_ANYA, description=f"{INSIGHTS_POD} forecasting election for Trump", date='2016-10-25'),
     DocCfg(id='028988', author=ZUBAIR_AND_ANYA, description=f"{INSIGHTS_POD} pitch deck", date='2016-08-20'),
     DocCfg(id='026627', author=ZUBAIR_AND_ANYA, description=f"{INSIGHTS_POD} report on the presidential debate"),
-    DocCfg(id='023050', description=f"{DERSH_GIUFFRE_TWEET}"),
-    DocCfg(id='017787', description=f"{DERSH_GIUFFRE_TWEET}"),
-    DocCfg(id='033433', description=f"{DERSH_GIUFFRE_TWEET} / David Boies", date='2019-03-02'),
-    DocCfg(id='033432', description=f"{DERSH_GIUFFRE_TWEET} / David Boies", date='2019-05-02'),
     DocCfg(id='022213', description=f"{SCREENSHOT} Facebook group called 'Shit Pilots Say' disparaging a 'global girl'"),
     DocCfg(id='030884', description=f"{TWEET} by Ed Krassenstein"),
     DocCfg(id='031546', description=f"{TWEET}s by Donald Trump about Russian collusion", date='2018-01-06'),
@@ -1285,8 +1379,10 @@ OTHER_FILES_SOCIAL = [
 ]
 
 OTHER_FILES_POLITICS = [
+    DocCfg(id='029918', author=DIANA_DEGETTE_CAMPAIGN, description=f"bio", date='2012-01-01'),
+    DocCfg(id='031184', author=DIANA_DEGETTE_CAMPAIGN, description=f"fundraiser invitation"),
     DocCfg(id='026827', author='Scowcroft Group', description=f'report on ISIS', date='2015-11-14'),
-    DocCfg(id='026851', author='Politifact', description=f"lying politicians chart", date='2016-07-26'),
+    DocCfg(id='024294', author=STACEY_PLASKETT, description=f"campaign flier", date='2016-10-01'),
     DocCfg(
         id='023133',
         author=f"{TERJE_ROD_LARSEN}, Nur Laiq, Fabrice Aidan",
@@ -1298,9 +1394,7 @@ OTHER_FILES_POLITICS = [
         author='US Office of Government Information Services',
         description=f"Building a Bridge Between FOIA Requesters & Agencies",
     ),
-    DocCfg(id='029918', description=f"{DIANA_DEGETTES_CAMPAIGN} bio", date='2012-01-01'),
-    DocCfg(id='031184', description=f"{DIANA_DEGETTES_CAMPAIGN} fundraiser invitation"),
-    DocCfg(id='024294', description=f"{STACEY_PLASKETT} campaign flier", date='2016-10-01'),
+    DocCfg(id='031670', description=f"letter from General Mike Flynn's lawyers to senators Mark Warner & Richard Burr about subpoena"),
     DocCfg(
         id='029357',
         description=f"text about Israel's challenges going into 2015, feels like it was extracted from a book",
@@ -1312,15 +1406,20 @@ OTHER_FILES_POLITICS = [
 ]
 
 OTHER_FILES_ACADEMIA = [
+    DocCfg(id='024256', author=JOI_ITO, description=f"Internet & Society: The Technologies and Politics of Control"),
+    DocCfg(id='027004', author=JOSCHA_BACH, description=f"The Computational Structure of Mental Representation", date='2013-02-26'),
     DocCfg(
         id='014697',
-        author=f"{LAWRENCE_KRAUSS}'s ASU Origins Project",
+        author=LAWRENCE_KRAUSS_ASU_ORIGINS,
         description=f'report: "Challenges of AI: Envisioning and Addressing Adverse Outcomes"',
         duplicate_ids=['011284']
     ),
-    DocCfg(id='024256', author=JOI_ITO, description=f"Internet & Society: The Technologies and Politics of Control"),
-    DocCfg(id='027004', author=JOSCHA_BACH, description=f"The Computational Structure of Mental Representation", date='2013-02-26'),
     DocCfg(id='015501', author=f"{MOSHE_HOFFMAN}, Erez Yoeli, and Carlos David Navarrete", description=f"Game Theory and Morality"),
+    DocCfg(
+        id='026521',
+        author=f"{MOSHE_HOFFMAN}, Erez Yoeli, and {MARTIN_NOWAK}",
+        description=f"Cooperating Without Looking: Game Theory Model of Trust and Reciprocal Cooperation"
+    ),
     DocCfg(id='025143', author=ROBERT_TRIVERS, description=f"Africa, Parasites, Intelligence", date='2018-06-25'),
     DocCfg(id='029155', author=ROBERT_TRIVERS, description=f'response sent to the Gruterites ({GORDON_GETTY} fans)', date='2018-03-19'),
     DocCfg(
@@ -1329,11 +1428,6 @@ OTHER_FILES_ACADEMIA = [
         description=f"'Does Trump Fit the Evolutionary Role of Narcissistic Sociopath?' (draft)",
         date='2018-12-07',
     ),
-    DocCfg(
-        id='026521',
-        author=f"{MARTIN_NOWAK}, Erez Yoeli, and {MOSHE_HOFFMAN}",
-        description=f"Cooperating Without Looking: Game Theory Model of Trust and Reciprocal Cooperation"
-    ),
     DocCfg(id='023416', description=HARVARD_POETRY),
     DocCfg(id='023435', description=HARVARD_POETRY),
     DocCfg(id='023450', description=HARVARD_POETRY),
@@ -1352,35 +1446,37 @@ OTHER_FILES_ACADEMIA = [
 OTHER_FILES_SPEECH = [
     DocCfg(id='027009', author=EHUD_BARAK, description=f"speech to AIPAC", date='2013-03-03'),
     DocCfg(id='026856', author='Kevin Rudd', description=f"speech 'Xi Jinping, China And The Global Order'", date='2018-06-26'),
-    DocCfg(id='026731', description=f"speech by Lord Martin Rees at first inaugural Carl Sagan Lecture at Cornell"),
+    DocCfg(id='026731', author='Lord Martin Rees', description=f"speech at first inaugural Cornell Carl Sagan Lecture"),
 ]
 
 # resumes and application letters
 OTHER_FILES_RESUMES = [
-    DocCfg(id='029102', description=HBS_APPLICATION_NERIO),
-    DocCfg(id='029104', description=HBS_APPLICATION_NERIO),
-    DocCfg(id='022367', description=f"{RESUME_OF} Jack J Grynberg", date='2014-07-01'),
+    DocCfg(id='022367', author='Jack J Grynberg', description=RESUME_OF, date='2014-07-01'),
     DocCfg(
         id='029302',
-        description=f"{RESUME_OF} {MICHAEL_J_BOCCIO}, former lawyer at the Trump Organization",
+        author=MICHAEL_J_BOCCIO,
+        description=f"{RESUME_OF} (former lawyer at the {TRUMP_ORG})",
         date='2011-08-07',
     ),
-    DocCfg(id='015671', description=f"{RESUME_OF} Robin Solomon", date='2015-06-02'),  # She left Mount Sinai at some point in 2015,
-    DocCfg(id='015672', description=f"{RESUME_OF} Robin Solomon", date='2015-06-02'),  # She left Mount Sinai at some point in 2015,
-    DocCfg(id='029623', description=f'short bio of Kathleen Harrington, Founding Partner, C/H Global Strategies'),
+    DocCfg(id='029102', author=NERIO_ALESSANDRI, description=HBS_APPLICATION),
+    DocCfg(id='029104', author=NERIO_ALESSANDRI, description=HBS_APPLICATION),
+    DocCfg(id='015671', author='Robin Solomon', description=RESUME_OF, date='2015-06-02'),  # She left Mount Sinai at some point in 2015,
+    DocCfg(id='015672', author='Robin Solomon', description=RESUME_OF, date='2015-06-02'),  # She left Mount Sinai at some point in 2015,
+    DocCfg(id='029623', description=f'bio of Kathleen Harrington, Founding Partner, C/H Global Strategies'),
 ]
 
 OTHER_FILES_ARTS = [
     DocCfg(id='018703', author=ANDRES_SERRANO, description=f"artist statement about Trump objects"),
     DocCfg(id='023438', author=BROCKMAN_INC, description=f"announcement of auction of 'Noise' by Daniel Kahneman, Olivier Sibony, and Cass Sunstein"),
-    DocCfg(id='030769', description=f"2017 Independent Filmmaker Project (IFP) Gotham Awards invitation"),
-    DocCfg(id='028281', description=f'art show flier for "The House Of The Nobleman" curated by Wolfe Von Lenkiewicz & Victoria Golembiovskaya'),
+    DocCfg(id='030769', author='Independent Filmmaker Project (IFP)', description=f"2017 Gotham Awards invitation"),
     DocCfg(
         id='025205',
-        description=f'Mercury Films partner profiles of Jennifer Baichwal, Nicholas de Pencier, Kermit Blackwood, Travis Rummel',
+        author='Mercury Films',
+        description=f'partner profiles of Jennifer Baichwal, Nicholas de Pencier, Kermit Blackwood, Travis Rummel',
         date='2010-02-01',
         duplicate_ids=['025210']
     ),
+    DocCfg(id='028281', description=f'art show flier for "The House Of The Nobleman" curated by Wolfe Von Lenkiewicz & Victoria Golembiovskaya'),
 ]
 
 OTHER_FILES_MISC = [
@@ -1392,32 +1488,32 @@ OTHER_FILES_MISC = [
         description=f'hot list Frankfurt Book Fair (includes article about Silk Road/Ross Ulbricht)',
         date='2016-10-23',
     ),
+    DocCfg(id='022494', author='DOJ', description=f'Foreign Corrupt Practices Act (FCPA) Resource Guide'),
     DocCfg(id='023096', author=EPSTEIN_FOUNDATION, description=f'blog post', date='2012-11-15'),
     DocCfg(id='029326', author=EPSTEIN_FOUNDATION, description=f'{PRESS_RELEASE}', date='2013-02-15'),
     DocCfg(id='026565', author=EPSTEIN_FOUNDATION, description=f'{PRESS_RELEASE}, maybe a draft of 029326', date='2013-02-15'),
+    DocCfg(id='027071', author=FEMALE_HEALTH_COMPANY, description=f"brochure requesting donations for female condoms in Uganda"),
+    DocCfg(id='027074', author=FEMALE_HEALTH_COMPANY, description=f"pitch deck (USAID was a customer)"),
+    DocCfg(id='032735', author=GORDON_GETTY, description=f"on Trump", date='2018-03-20'),  # Dated based on concurrent emails from Getty
+    DocCfg(id='025540', author=JEFFREY_EPSTEIN, description=f"rough draft of Epstein's side of the story?"),
+    DocCfg(id='018224', author=LAWRENCE_KRAUSS, description=f"Skype conversation log"),
     DocCfg(id='026634', author='Michael Carrier', description=f"comments about an Apollo linked hedge fund 'DE Fund VIII'"),
+    DocCfg(id='031425', author=SCOTT_J_LINK, description=f'completely redacted email from'),
     DocCfg(id='020447', author='Working Group on Chinese Influence Activities in the U.S.', description=f'Promoting Constructive Vigilance'),
     DocCfg(id='031743', description=f'a few pages describing the internet as a "New Nation State" (Network State?)'),
-    DocCfg(id='031425', description=f'completely redacted email from {SCOTT_J_LINK}'),
-    DocCfg(id='018224', description=f"conversation with {LAWRENCE_KRAUSS}?"),
     DocCfg(id='012718', description=f"{CVRA} congressional record", date='2011-06-17'),
-    DocCfg(id='025540', description=f"Epstein's rough draft of his side of the story?"),
     DocCfg(id='024117', description=f"FAQ about anti-money laundering (AML) and terrorist financing (CFT) law in the U.S."),
-    DocCfg(id='027071', description=f"{FEMALE_HEALTH_COMPANY} brochure requesting donations for female condoms in Uganda"),
-    DocCfg(id='027074', description=f"{FEMALE_HEALTH_COMPANY} pitch deck (USAID was a customer)"),
-    DocCfg(id='022494', description=f'Foreign Corrupt Practices Act (FCPA) DOJ Resource Guide'),
-    DocCfg(id='032735', description=f"{GORDON_GETTY} on Trump", date='2018-03-20'),  # Dated based on concurrent emails from Getty
     DocCfg(id='019448', description=f"Haitian business investment proposal called Jacmel"),
     DocCfg(id='023644', description=f"interview with Mohammed bin Salman", date='2016-04-25'),
     DocCfg(
         id='030142',
-        description=f"{JASTA} (Justice Against Sponsors of Terrorism Act) doc that's mostly empty, references suit against Saudi f. {KATHRYN_RUEMMLER} & {KEN_STARR}",
         date='2016-09-01',
+        description=f"{JASTA} (Justice Against Sponsors of Terrorism Act) doc that's mostly empty, references suit against Saudi f. {KATHRYN_RUEMMLER} & {KEN_STARR}",
     ),
     DocCfg(
         id='033338',
-        description=f"{PRESS_RELEASE} announcing Donald Trump & {NICHOLAS_RIBIS} ended their working relationship at Trump's casino",
         date='2000-06-07',
+        description=f"{PRESS_RELEASE} announcing Donald Trump & {NICHOLAS_RIBIS} ended their working relationship at Trump's casino",
     ),
     DocCfg(id='029328', description=f"Rafanelli Events promotional deck"),
     DocCfg(id='033434', description=f"{SCREENSHOT} iPhone chat labeled 'Edwards' at the top"),
@@ -1493,7 +1589,9 @@ SENT_FROM_REGEX = re.compile(r'^(?:(Please forgive|Sorry for all the) typos.{1,4
 
 
 # Error checking.
-assert len(OTHER_FILES_CONFIG) == 438
+if len(OTHER_FILES_CONFIG) != 438:
+    logger.warning(f"Only {len(OTHER_FILES_CONFIG)} configured other files!")
+
 encountered_file_ids = set()
 
 for cfg in ALL_CONFIGS: