epstein-files 1.1.3__py3-none-any.whl → 1.2.0__py3-none-any.whl

epstein_files/util/constants.py

@@ -19,12 +19,13 @@ HEADER_ABBREVIATIONS = {
     'bgC3': 'Bill Gates Ventures (renamed in 2018)',
     "Brock": 'Brock Pierce (crypto bro with a very sordid past)',
     "DB": "Deutsche Bank (maybe??)",
+    "GRAT": "Grantor Retained Annuity Trust (tax shelter)",
     'HBJ': "Sheikh Hamad bin Jassim (former Qatari prime minister)",
     'Jabor': '"an influential man in Qatar"',
     'Jared': "Jared Kushner",
     'Jagland': 'Thorbjørn Jagland (former Norwegian prime minister)',
     'JEGE': "Epstein's airplane holding company",
-    'Jeffrey Wernick': 'right wing crypto bro, former COO of Parler',
+    JEFFREY_WERNICK: 'right wing crypto bro, former COO of Parler',
     'Joi': f"Joi Ito ({MIT_MEDIA_LAB}, MIT Digital Currency Initiative)",
     "Hoffenberg": f"{STEVEN_HOFFENBERG} (Epstein's ponzi scheme partner)",
     'KSA': "Kingdom of Saudi Arabia",
@@ -62,6 +63,7 @@ EMAILER_ID_REGEXES: dict[str, re.Pattern] = {
     BARBRO_C_EHNBOM: re.compile(r'behnbom@aol.com|(Barbro\s.*)?Ehnbom', re.IGNORECASE),
     BARRY_J_COHEN: re.compile(r'barry\s*((j.?|james)\s*)?cohen?', re.IGNORECASE),
     BENNET_MOSKOWITZ: re.compile(r'Moskowitz.*Bennet|Bennet.*Moskowitz', re.IGNORECASE),
+    BOB_CROWE: re.compile(r"[BR]ob Crowe", re.IGNORECASE),
     BORIS_NIKOLIC: re.compile(r'(boris )?nikolic?', re.IGNORECASE),
     BRAD_EDWARDS:  re.compile(r'Brad(ley)?(\s*J(.?|ames))?\s*Edwards', re.IGNORECASE),
     BRAD_KARP: re.compile(r'Brad (S.? )?Karp|Karp, Brad', re.IGNORECASE),
@@ -83,13 +85,14 @@ EMAILER_ID_REGEXES: dict[str, re.Pattern] = {
     JACKIE_PERCZEK:  re.compile(r'jackie percze[kl]?', re.IGNORECASE),
     JABOR_Y: re.compile(r'[ji]abor\s*y?', re.IGNORECASE),
     JAMES_HILL: re.compile(r"hill, james e.|james.e.hill@abc.com", re.IGNORECASE),
+    JANUSZ_BANASIAK: re.compile(r"Janu[is]z Banasiak", re.IGNORECASE),
     JEAN_LUC_BRUNEL: re.compile(r'Jean[- ]Luc Brunel?', re.IGNORECASE),
     JEFF_FULLER: re.compile(r"jeff@mc2mm.com|Jeff Fuller", re.IGNORECASE),
     JEFFREY_EPSTEIN: re.compile(r'[djl]\s?ee[vy]acation[©@]?g?(mail.com)?|Epstine|\bJEE?\b|Jeffrey E((sp|ps)tein?)?( VI Foundation)?|jeeproject@yahoo.com|J Jep|Jeffery Edwards|(?<!(Mark L.|ard Jay) )Epstein', re.IGNORECASE),
     JESSICA_CADWELL: re.compile(r'Jessica Cadwell?', re.IGNORECASE),
     JOHNNY_EL_HACHEM: re.compile(r'el hachem johnny|johnny el hachem', re.IGNORECASE),
     JOI_ITO: re.compile(r'ji@media.mit.?edu|(joichi|joi)( Ito)?', re.IGNORECASE),
-    JONATHAN_FARKAS: re.compile(r'Jonathan Farka(s|il)', re.IGNORECASE),
+    JONATHAN_FARKAS: re.compile(r'Jonathan Fark(a|u)(s|il)', re.IGNORECASE),
     KATHRYN_RUEMMLER: re.compile(r'Kathr?yn? Ruemmler?', re.IGNORECASE),
     KEN_STARR: re.compile(r'starr, ken|Ken(neth\s*(W.\s*)?)?\s+starr?|starr', re.IGNORECASE),
     LANDON_THOMAS: re.compile(r'lando[nr] thomas( jr)?|thomas jr.?, lando[nr]', re.IGNORECASE),
@@ -157,6 +160,7 @@ EMAILERS = [
     BILL_GATES,
     BILL_SIEGEL,
     BRAD_WECHSLER,
+    CHRISTINA_GALBRAITH,
     DANIEL_SABBA,
     'Danny Goldberg',
     DAVID_SCHOEN,
@@ -302,15 +306,53 @@ TEXTS_CONFIG = CONFIRMED_TEXTS_CONFIG + UNCONFIRMED_TEXTS_CONFIG
 ################################################ EMAILS ################################################
 ########################################################################################################
 
-MICHAEL_WOLFF_EPSTEIN_ARTICLE_DRAFT = f"draft of an unpublished article about Epstein by {MICHAEL_WOLFF} written ca. 2014/2015"
-
 # Some emails have a lot of uninteresting CCs
-IRAN_DEAL_RECIPIENTS = ['Allen West', 'Rafael Bardaji', 'Philip Kafka', 'Herb Goodman', 'Grant Seeger', 'Lisa Albert', 'Janet Kafka', 'James Ramsey', 'ACT for America', 'John Zouzelka', 'Joel Dunn', 'Nate McClain', 'Bennet Greenwald', 'Taal Safdie', 'Uri Fouzailov', 'Neil Anderson', 'Nate White', 'Rita Hortenstine', 'Henry Hortenstine', 'Gary Gross', 'Forrest Miller', 'Bennett Schmidt', 'Val Sherman', 'Marcie Brown', 'Michael Horowitz', 'Marshall Funk']
-FLIGHT_IN_2012_PEOPLE = ['Francis Derby', 'Januiz Banasiak', 'Louella Rabuyo', 'Richard Barnnet']
+FLIGHT_IN_2012_PEOPLE: list[Name] = ['Francis Derby', JANUSZ_BANASIAK, 'Louella Rabuyo', 'Richard Barnnet']
+IRAN_DEAL_RECIPIENTS: list[Name] = ['Allen West', 'Rafael Bardaji', 'Philip Kafka', 'Herb Goodman', 'Grant Seeger', 'Lisa Albert', 'Janet Kafka', 'James Ramsey', 'ACT for America', 'John Zouzelka', 'Joel Dunn', 'Nate McClain', 'Bennet Greenwald', 'Taal Safdie', 'Uri Fouzailov', 'Neil Anderson', 'Nate White', 'Rita Hortenstine', 'Henry Hortenstine', 'Gary Gross', 'Forrest Miller', 'Bennett Schmidt', 'Val Sherman', 'Marcie Brown', 'Michael Horowitz', 'Marshall Funk']
+MICHAEL_WOLFF_EPSTEIN_ARTICLE_DRAFT = f"draft of an unpublished article about Epstein by {MICHAEL_WOLFF} written ca. 2014/2015"
 
 EMAILS_CONFIG = [
+    # 026294 and 026296 might also be Ittihadieh based on timing
     EmailCfg(id='032436', author=ALIREZA_ITTIHADIEH, attribution_reason='Signature'),
+    # 032542 026078 026080 026083 026086 026090 might also be Anas based on discussion of Dubai and Kuwait
     EmailCfg(id='032543', author=ANAS_ALRASHEED, attribution_reason='Later reply 033000 has quote'),
+    EmailCfg(id='026167', author=ANAS_ALRASHEED, attribution_reason='name visible in 033022 reply'),
+    EmailCfg(id='032571', author=ANAS_ALRASHEED, attribution_reason='name visible in 033022 reply'),
+    EmailCfg(id='032573', author=ANAS_ALRASHEED, attribution_reason='name visible in 033022 reply'),
+    EmailCfg(id='032575', author=ANAS_ALRASHEED, attribution_reason='name visible in 033022 reply'),
+    EmailCfg(id='032577', author=ANAS_ALRASHEED, attribution_reason='name visible in 033022 reply'),
+    EmailCfg(id='032579', author=ANAS_ALRASHEED, attribution_reason='name visible in 033022 reply'),
+    EmailCfg(id='032582', author=ANAS_ALRASHEED, attribution_reason='name visible in 033022 reply'),
+    EmailCfg(id='032585', author=ANAS_ALRASHEED, attribution_reason='name visible in 033022 reply'),
+    EmailCfg(id='032588', author=ANAS_ALRASHEED, attribution_reason='name visible in 033022 reply'),
+    EmailCfg(id='032591', author=ANAS_ALRASHEED, attribution_reason='name visible in 033022 reply'),
+    EmailCfg(id='032595', author=ANAS_ALRASHEED, attribution_reason='name visible in 033022 reply'),
+    EmailCfg(id='032599', author=ANAS_ALRASHEED, attribution_reason='name visible in 033022 reply'),
+    EmailCfg(id='032611', author=ANAS_ALRASHEED, attribution_reason='name visible in 033022 reply'),
+    EmailCfg(id='023661', author=ANAS_ALRASHEED, attribution_reason='name visible in 033022 reply'),
+    EmailCfg(id='032616', author=ANAS_ALRASHEED, attribution_reason='name visible in 033022 reply'),
+    EmailCfg(id='032622', author=ANAS_ALRASHEED, attribution_reason='name visible in 033022 reply'),
+    EmailCfg(id='032628', author=ANAS_ALRASHEED, attribution_reason='name visible in 026180 reply'),
+    EmailCfg(id='032629', author=ANAS_ALRASHEED, attribution_reason='name visible in 026180 reply'),
+    EmailCfg(id='032631', author=ANAS_ALRASHEED, attribution_reason='name visible in 026180 reply'),
+    EmailCfg(id='026168', author=ANAS_ALRASHEED, attribution_reason='name visible in 026180 reply'),
+    EmailCfg(id='026170', author=ANAS_ALRASHEED, attribution_reason='name visible in 026180 reply'),
+    EmailCfg(id='026173', author=ANAS_ALRASHEED, attribution_reason='name visible in 026180 reply'),
+    EmailCfg(id='026176', author=ANAS_ALRASHEED, attribution_reason='name visible in 026180 reply'),
+    EmailCfg(id='026180', author=ANAS_ALRASHEED, attribution_reason='name visible in 026180 reply'),
+    EmailCfg(id='026184', author=ANAS_ALRASHEED, attribution_reason='name visible in 026180 reply'),
+    EmailCfg(id='026188', author=ANAS_ALRASHEED, attribution_reason='name visible in 026180 reply'),
+    EmailCfg(id='026193', author=ANAS_ALRASHEED, attribution_reason='name visible in 026180 reply'),
+    EmailCfg(id='026198', author=ANAS_ALRASHEED, attribution_reason='name visible in 026180 reply'),
+    EmailCfg(id='026210', author=ANAS_ALRASHEED, attribution_reason='name visible in 026180 reply'),
+    EmailCfg(id='026204', author=ANAS_ALRASHEED, attribution_reason='name visible in 026180 reply'),
+    EmailCfg(id='032660', author=ANAS_ALRASHEED, attribution_reason='name visible in 029113 reply'),
+    EmailCfg(id='032663', author=ANAS_ALRASHEED, attribution_reason='name visible in 029113 reply'),
+    EmailCfg(id='032667', author=ANAS_ALRASHEED, attribution_reason='name visible in 029113 reply'),
+    EmailCfg(id='032672', author=ANAS_ALRASHEED, attribution_reason='name visible in 029113 reply'),
+    EmailCfg(id='032676', author=ANAS_ALRASHEED, attribution_reason='name visible in 029113 reply'),
+    EmailCfg(id='026237', author=ANAS_ALRASHEED, attribution_reason='name visible in 029113 reply'),
+    EmailCfg(id='032682', author=ANAS_ALRASHEED, attribution_reason='name visible in 029113 reply'),
     EmailCfg(id='026064', author=ARIANE_DE_ROTHSCHILD, attribution_reason='signature'),
     EmailCfg(id='026069', author=ARIANE_DE_ROTHSCHILD, attribution_reason='signature'),
     EmailCfg(id='030741', author=ARIANE_DE_ROTHSCHILD, attribution_reason='signature'),
@@ -351,6 +393,7 @@ EMAILS_CONFIG = [
         actual_text='',
         author=DARREN_INDYKE,
         description=f"heavily redacted email, quoted replies are from {STEVEN_HOFFENBERG} about James Patterson's book",
+        recipients=['Charles Michael'],
         timestamp=parse('2016-08-17 11:26:00'),
         attribution_reason='Quoted replies are in 019109',
     ),
@@ -369,11 +412,11 @@ EMAILS_CONFIG = [
         dupe_type='redacted'
     ),
     EmailCfg(id='026547', author=GERALD_BARTON, recipients=[JEFFREY_EPSTEIN]),  # Bad OCR # TODO: email header is really jacked up
-    EmailCfg(id='029969', author=GWENDOLYN_BECK, attribution_reason='Signature'),
-    EmailCfg(id='029968', author=GWENDOLYN_BECK, attribution_reason='Signature', duplicate_ids=['031120']),
+    EmailCfg(id='029969', author=GWENDOLYN_BECK, attribution_reason='signature "Longevity & Successful Aging"'),
+    EmailCfg(id='029968', author=GWENDOLYN_BECK, attribution_reason='signature "beckresearchlabs.com"', duplicate_ids=['031120']),
     EmailCfg(id='029970', author=GWENDOLYN_BECK, attribution_reason='signed "Longevity & Successful Agin"'),
-    EmailCfg(id='029960', author=GWENDOLYN_BECK, attribution_reason='Reply'),
-    EmailCfg(id='029959', author=GWENDOLYN_BECK, attribution_reason='"Longevity & Aging"'),
+    EmailCfg(id='029960', author=GWENDOLYN_BECK, attribution_reason='signature "Beck Center for Longevity & Aging"'),
+    EmailCfg(id='029959', author=GWENDOLYN_BECK, attribution_reason='signature "Beck Center for Longevity & Aging"'),
     EmailCfg(id='033360', author=HENRY_HOLT, attribution_reason='in signature'),  # Henry Holt is a company not a person
     EmailCfg(id='033384', author=JACK_GOLDBERGER, attribution_reason='Might be Paul Prosperi?', is_attribution_uncertain=True),
     EmailCfg(id='026024', author=JEAN_HUGUEN, attribution_reason='Signature'),
@@ -434,7 +477,7 @@ EMAILS_CONFIG = [
     EmailCfg(
         id='029977',
         author=LAWRANCE_VISOSKI,
-        recipients=cast(list[str | None], [JEFFREY_EPSTEIN, DARREN_INDYKE, LESLEY_GROFF, RICHARD_KAHN] + FLIGHT_IN_2012_PEOPLE),
+        recipients=[JEFFREY_EPSTEIN, DARREN_INDYKE, LESLEY_GROFF, RICHARD_KAHN] + FLIGHT_IN_2012_PEOPLE,
         attribution_reason=LARRY_REASON,
         duplicate_ids=['031129'],
     ),
@@ -444,11 +487,19 @@ EMAILS_CONFIG = [
     EmailCfg(id='017581', author='Lisa Randall', attribution_reason='reply header'),
     EmailCfg(id='026609', author='Mark Green', attribution_reason='Actually a fwd, Mark Green is in signature'),
     EmailCfg(id='030472', author=MARTIN_WEINBERG, attribution_reason='Maybe. in reply', is_attribution_uncertain=True),
+    EmailCfg(id='032563', author=MASHA_DROKOVA, attribution_reason='replied to in 033014'),
+    EmailCfg(id='032564', author=MASHA_DROKOVA, attribution_reason='follow up to 032563 about huffpo article with link'),
+    EmailCfg(id='031544', author=MASHA_DROKOVA, attribution_reason='follow up to 032563 about huffpo article with link'),
+    EmailCfg(id='032605', author=MASHA_DROKOVA, attribution_reason="re: PR interview, 031544 says she'll be in NY at that time"),
+    EmailCfg(id='032606', author=MASHA_DROKOVA, attribution_reason="re: PR interview, 031544 says she'll be in NY at that time"),
+    EmailCfg(id='032607', author=MASHA_DROKOVA, attribution_reason="re: PR interview, 031544 says she'll be in NY at that time"),
+    EmailCfg(id='032609', author=MASHA_DROKOVA, attribution_reason="re: PR interview, 031544 says she'll be in NY at that time"),
+    EmailCfg(id='032604', author=MASHA_DROKOVA, attribution_reason="timing, subject (interviews/articles), and sequential ID", is_attribution_uncertain=True),
+    EmailCfg(id='032581', author=MASHA_DROKOVA, attribution_reason="timing, subject (interviews/articles), and sequential ID", is_attribution_uncertain=True),
     EmailCfg(id='030235', author=MELANIE_WALKER, attribution_reason='In fwd'),
     EmailCfg(id='032343', author=MELANIE_WALKER, attribution_reason='Name seen in later reply 032346'),
     EmailCfg(id='032212', author=MIROSLAV_LAJCAK, attribution_reason='signature'),
-    EmailCfg(id='022193', author=NADIA_MARCINKO, attribution_reason='reply'),
-    EmailCfg(id='021814', author=NADIA_MARCINKO, attribution_reason='reply'),
+    EmailCfg(id='021814', author=NADIA_MARCINKO, attribution_reason='reply'), #, actual_text="I'm a pilot...I prefer sex slave to copilot ;)"),
     EmailCfg(id='021808', author=NADIA_MARCINKO, attribution_reason='reply'),
     EmailCfg(id='022190', author=NADIA_MARCINKO, attribution_reason='reply'),
     EmailCfg(id='021818', author=NADIA_MARCINKO, attribution_reason='reply'),
@@ -490,11 +541,12 @@ EMAILS_CONFIG = [
         author=SEAN_BANNON,
         attribution_reason="From protonmail, Bannon wrote 'just sent from my protonmail' in 027067",
     ),
-    EmailCfg(id='029003', author=SOON_YI_PREVIN, attribution_reason="\"Sent from Soon-Yi's iPhone\""),
-    EmailCfg(id='029005', author=SOON_YI_PREVIN, attribution_reason="\"Sent from Soon-Yi's iPhone\""),
-    EmailCfg(id='029007', author=SOON_YI_PREVIN, attribution_reason="\"Sent from Soon-Yi's iPhone\""),
-    EmailCfg(id='029010', author=SOON_YI_PREVIN, attribution_reason="\"Sent from Soon-Yi's iPhone\""),
-    EmailCfg(id='032296', author=SOON_YI_PREVIN, attribution_reason="\"Sent from Soon-Yi's iPhone\""),
+    EmailCfg(id='029003', author=SOON_YI_PREVIN, attribution_reason='"Sent from Soon-Yi\'s iPhone"'),
+    EmailCfg(id='029005', author=SOON_YI_PREVIN, attribution_reason='"Sent from Soon-Yi\'s iPhone"'),
+    EmailCfg(id='029007', author=SOON_YI_PREVIN, attribution_reason='"Sent from Soon-Yi\'s iPhone"'),
+    EmailCfg(id='029010', author=SOON_YI_PREVIN, attribution_reason='"Sent from Soon-Yi\'s iPhone"'),
+    EmailCfg(id='032296', author=SOON_YI_PREVIN, attribution_reason='"Sent from Soon-Yi\'s iPhone"'),
+    EmailCfg(id='033292', author=SOON_YI_PREVIN, attribution_reason='mentions "Woody\'s movie"', is_attribution_uncertain=True),
     EmailCfg(
         id='019109',
         author=STEVEN_HOFFENBERG,
@@ -507,13 +559,15 @@ EMAILS_CONFIG = [
         attribution_reason='ends with "Respectfully, terry"',
         author=TERRY_KAFKA,
         fwded_text_after='From: Mike Cohen',
-        recipients=cast(list[str | None], [JEFFREY_EPSTEIN, MARK_EPSTEIN, MICHAEL_BUCHHOLTZ] + IRAN_DEAL_RECIPIENTS),
+        recipients=[JEFFREY_EPSTEIN, MARK_EPSTEIN, MICHAEL_BUCHHOLTZ] + IRAN_DEAL_RECIPIENTS,
+        subject='Fw: The Iran Nuclear Deal',
         duplicate_ids=['028482'],
     ),
     EmailCfg(id='029992', author=TERRY_KAFKA, attribution_reason='Quoted reply'),
     EmailCfg(id='029985', author=TERRY_KAFKA, attribution_reason='Quoted reply in 029992'),
     EmailCfg(id='020666', author=TERRY_KAFKA, attribution_reason="Ends with 'Terry'"),
     EmailCfg(id='026014', author=ZUBAIR_KHAN, recipients=[JEFFREY_EPSTEIN], timestamp=parse('2016-11-04 17:46:00')),
+    EmailCfg(id='033021', recipients=[ANAS_ALRASHEED], attribution_reason='visible in 033022'),
     EmailCfg(id='027063', recipients=[ANTHONY_BARRETT]),
     EmailCfg(id='030764', recipients=[ARIANE_DE_ROTHSCHILD], attribution_reason='Reply'),
     EmailCfg(id='026431', recipients=[ARIANE_DE_ROTHSCHILD], attribution_reason='Reply'),
@@ -538,6 +592,7 @@ EMAILS_CONFIG = [
     EmailCfg(id='032780', recipients=[JEFFREY_EPSTEIN]),  # Bad OCR (nofix)
     EmailCfg(id='029324', recipients=[JEFFREY_EPSTEIN, "Jojo Fontanilla", "Lyn Fontanilla"]),  # Bad OCR (nofix)
     EmailCfg(id='013482', recipients=[JEFFREY_EPSTEIN], is_fwded_article=True),  # other recipients redacted. "The view from the US: Stem cell therapy steps up a gear with firs"
+    EmailCfg(id='029558', recipients=[JEFFREY_EPSTEIN, KATHERINE_KEATING], attribution_reason='BCC', fwded_text_after='Creativity is central'),
     EmailCfg(id='033456', recipients=["Joel"], attribution_reason='Reply'),
     EmailCfg(id='033458', recipients=["Joel"], attribution_reason='Reply'),
     EmailCfg(id='033460', recipients=["Joel"], attribution_reason='Reply'),
@@ -566,10 +621,14 @@ EMAILS_CONFIG = [
     EmailCfg(id='033466', recipients=[LAWRANCE_VISOSKI], attribution_reason='Reply signature'),
     EmailCfg(id='022250', recipients=[LESLEY_GROFF], attribution_reason='Reply'),
     EmailCfg(id='030242', recipients=[MARIANA_IDZKOWSKA], duplicate_ids=['032048'], dupe_type='redacted'),
+    EmailCfg(id='033027', recipients=[MASHA_DROKOVA], attribution_reason="re: PR interview, 031544 says she'll be in NY at that time"),
+    EmailCfg(id='033025', recipients=[MASHA_DROKOVA], attribution_reason="timing, subject (interviews/articles), and sequential ID", is_attribution_uncertain=True),
     EmailCfg(id='030368', recipients=[MELANIE_SPINELLA], attribution_reason='Actually a self fwd from jeffrey to jeffrey'),
     EmailCfg(id='030369', recipients=[MELANIE_SPINELLA], attribution_reason='Actually a self fwd from jeffrey to jeffrey'),
     EmailCfg(id='030371', recipients=[MELANIE_SPINELLA], attribution_reason='Actually a self fwd from jeffrey to jeffrey'),
     EmailCfg(id='022258', recipients=[NADIA_MARCINKO], attribution_reason='Reply header'),
+    EmailCfg(id='022193', recipients=[NADIA_MARCINKO], attribution_reason='reply'),
+    EmailCfg(id='030572', recipients=[PAULA], attribution_reason='quoted in 030482', is_attribution_uncertain=True),
     EmailCfg(id='030506', recipients=[PAULA], attribution_reason=PAULA_REASON, is_attribution_uncertain=True),
     EmailCfg(id='030507', recipients=[PAULA], attribution_reason=PAULA_REASON, is_attribution_uncertain=True),
     EmailCfg(id='030508', recipients=[PAULA], attribution_reason=PAULA_REASON, is_attribution_uncertain=True),
@@ -585,8 +644,9 @@ EMAILS_CONFIG = [
     EmailCfg(id='032358', actual_text=REDACTED),  # Completely redacted
     EmailCfg(id='033050', actual_text='schwartman'),
     EmailCfg(id='022219', description="discussion of attempts to clean up Epstein's Google search results"),
-    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='028524', is_fwded_article=True, description='Zach Braff op-ed on Woody Allen in NYT'),
+    EmailCfg(id='031333', is_fwded_article=True, description='Fort Knox conspiracy theory, 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='Fort Knox conspiracy theory, 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='023627', is_fwded_article=True, description=MICHAEL_WOLFF_EPSTEIN_ARTICLE_DRAFT),
     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
@@ -640,7 +700,6 @@ EMAILS_CONFIG = [
     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'
@@ -655,6 +714,7 @@ EMAILS_CONFIG = [
     EmailCfg(id='030373', timestamp=parse('2018-10-03 01:49:27')),
 
     # Configure duplicates
+    EmailCfg(id='026631', duplicate_ids=['026632'], dupe_type='quoted'),
     EmailCfg(id='028768', duplicate_ids=['026563'], dupe_type='redacted'),
     EmailCfg(id='027056', duplicate_ids=['028762'], dupe_type='redacted'),
     EmailCfg(id='032248', duplicate_ids=['032246'], dupe_type='redacted'),
@@ -667,6 +727,7 @@ EMAILS_CONFIG = [
     EmailCfg(id='029841', duplicate_ids=['012711'], dupe_type='redacted'),
     EmailCfg(id='030414', duplicate_ids=['030578'], dupe_type='redacted'),
     EmailCfg(id='031135', duplicate_ids=['030634'], dupe_type='redacted'),
+    EmailCfg(id='030620', duplicate_ids=['023067']),
     EmailCfg(id='029835', duplicate_ids=['028968']),
     EmailCfg(id='033512', duplicate_ids=['033361']),
     EmailCfg(id='030299', duplicate_ids=['021794']),
@@ -768,7 +829,6 @@ EMAILS_CONFIG = [
     # 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'),
@@ -1323,8 +1383,6 @@ OTHER_FILES_LETTERS = [
         description=f"letter about algorithmic trading",
         date='2016-06-24',  # date is based on Brexit reference but he could be backtesting,
     ),
-    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='026134', description=f'letter to someone named George about investment opportunities in the Ukraine banking sector'),
 ]
 
@@ -1475,13 +1533,27 @@ OTHER_FILES_ACADEMIA = [
 
 # resumes and application letters
 OTHER_FILES_RESUMES = [
+    DocCfg(
+        id='029304',
+        attached_to_email_id='029299',
+        author=DONALD_TRUMP,
+        description=f"recommendation letter for recently departed {TRUMP_ORG} lawyer {MICHAEL_J_BOCCIO}",
+    ),
     DocCfg(id='022367', author='Jack J Grynberg', description=RESUME_OF, date='2014-07-01'),
     DocCfg(
         id='029302',
+        attached_to_email_id='029299',
         author=MICHAEL_J_BOCCIO,
         description=f"{RESUME_OF} (former lawyer at the {TRUMP_ORG})",
         date='2011-08-07',
     ),
+    DocCfg(
+        id='029301',
+        attached_to_email_id='029299',
+        author=MICHAEL_J_BOCCIO,
+        description=f"letter from former lawyer at the {TRUMP_ORG}",
+        date='2011-08-07',
+    ),
     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,
@@ -1622,4 +1694,40 @@ REPLY_LINE_ON_NUMERIC_DATE_PATTERN = fr"On \d+/\d+/\d+[, ].*{REPLY_LINE_ENDING_P
 REPLY_LINE_ON_DATE_PATTERN = fr"^On (\d+ )?((Mon|Tues?|Wed(nes)?|Thu(rs)?|Fri|Sat(ur)?|Sun)(day)?|(Jan|Feb|Mar|Apr|May|Jun|Jul|Aug|Sep|Oct|Nov|Dec)\w*)[, ].*{REPLY_LINE_ENDING_PATTERN}"
 REPLY_LINE_PATTERN = rf"({REPLY_LINE_IN_A_MSG_PATTERN}|{REPLY_LINE_ON_NUMERIC_DATE_PATTERN}|{REPLY_LINE_ON_DATE_PATTERN}|{FORWARDED_LINE_PATTERN})"
 REPLY_REGEX = re.compile(REPLY_LINE_PATTERN, re.IGNORECASE | re.MULTILINE)
-SENT_FROM_REGEX = re.compile(r'^(?:(Please forgive|Sorry for all the) typos.{1,4})?(Sent (from|via).*(and string|AT&T|Droid|iPad|Phone|Mail|BlackBerry(.*(smartphone|device|Handheld|AT&T|T- ?Mobile))?)\.?)', re.M | re.I)
+SENT_FROM_REGEX = re.compile(r'^(?:(Please forgive|Sorry for all the) typos.{1,4})?((Envoyé de mon|Sent (from|via)).*(and string|AT&T|Droid|iPad|Phone|Mail|BlackBerry(.*(smartphone|device|Handheld|AT&T|T- ?Mobile))?)\.?)', re.M | re.I)
+
+
+# No point in ever displaying these; their emails show up elsewhere because they're mostly CC recipients
+UNINTERESTING_EMAILERS = FLIGHT_IN_2012_PEOPLE + IRAN_DEAL_RECIPIENTS + [
+    'Alan Dlugash',                          # CCed with Richard Kahn
+    'Alan Rogers',                           # Random CC
+    'Andrew Friendly',                       # Presumably some relation of Kelly Friendly
+    'BS Stern',                              # A random fwd of email we have
+    'Cheryl Kleen',                          # Single email from Anne Boyles, displayed under Anne Boyles
+    'Connie Zaguirre',                       # Random CC
+    'Dan Fleuette',                          # CC from sean bannon
+    'Danny Goldberg',                        # Random Paul Krassner emails
+    GERALD_LEFCOURT,                         # Single CC
+    GORDON_GETTY,                            # Random CC
+    JEFF_FULLER,                             # Random Jean Luc Brunel CC
+    'Jojo Fontanilla',                       # Random CC
+    'Joseph Vinciguerra',                    # Random CC
+    'Larry Cohen',                           # Random Bill Gates CC
+    'Lyn Fontanilla',                        # Random CC
+    'Mark Albert',                           # Random CC
+    'Matthew Schafer',                       # Random CC
+    MICHAEL_BUCHHOLTZ,                       # Terry Kafka CC
+    'Nancy Dahl',                            # covered by Lawrence Krauss (her husband)
+    'Michael Simmons',                       # Random CC
+    'Nancy Portland',                        # Lawrence Krauss CC
+    'Oliver Goodenough',                     # Robert Trivers CC
+    'Peter Aldhous',                         # Lawrence Krauss CC
+    'Players2',                              # Hoffenberg CC
+    'Sam Harris',                            # Lawrence Krauss CC
+    SAMUEL_LEFF,                             # Random CC
+    'Sean T Lehane',                         # Random CC
+    'Stephen Rubin',                         # Random CC
+    'Tim Kane',                              # Random CC
+    'Travis Pangburn',                       # Random CC
+    'Vahe Stepanian',                        # Random CC
+]

epstein_files/util/data.py

@@ -8,6 +8,7 @@ from dateutil import tz
 from typing import TypeVar
 
 from epstein_files.util.constant import names
+from epstein_files.util.constant.strings import QUESTION_MARKS
 from epstein_files.util.env import args
 from epstein_files.util.logging import logger
 
@@ -37,18 +38,6 @@ def dict_sets_to_lists(d: dict[str, set]) -> dict[str, list]:
     return {k: sorted(list(v)) for k, v in d.items()}
 
 
-def extract_last_name(name: str) -> str:
-    if ' ' not in name:
-        return name
-
-    names = name.split()
-
-    if names[-1].startswith('Jr') and len(names[-1]) <= 3:
-        return ' '.join(names[-2:])
-    else:
-        return names[-1]
-
-
 def flatten(_list: list[list[T]]) -> list[T]:
     return list(itertools.chain.from_iterable(_list))
 

epstein_files/util/doc_cfg.py

@@ -62,7 +62,7 @@ class DocCfg:
 
     Attributes:
         id (str): ID of file
-        author (str | None): Author of the document (if any)
+        author (Name): Author of the document (if any)
         category (str | None): Type of file
         date (str | None): If passed will be immediated parsed into the 'timestamp' field
         dupe_type (DuplicateType | None): The type of duplicate this file is or its 'duplicate_ids' are
@@ -74,7 +74,7 @@ class DocCfg:
     """
     id: str
     attached_to_email_id: str | None = None
-    author: str | None = None
+    author: Name = None
     category: str | None = None
     date: str | None = None
     description: str | None = None
@@ -94,26 +94,40 @@ class DocCfg:
 
     def complete_description(self) -> str | None:
         """String that summarizes what is known about this document."""
+        description = ''
+
         if self.category and not self.description and not self.author:
-            return self.category
+            if self.category == JUNK:
+                return None
+            else:
+                description = self.category
         elif self.category == REPUTATION:
-            return f"{REPUTATION_MGMT}: {self.description}"
+            author_str = f"{self.author} " if self.author else ''
+            description = f"{REPUTATION_MGMT}: {author_str}{self.description}"
         elif self.category == SKYPE_LOG:
             msg = f"{self.category} of conversation with {self.author}" if self.author else self.category
-            return f"{msg} {self.description}" if self.description else msg
+            description = f"{msg} {self.description}" if self.description else msg
         elif self.author and self.description:
             if self.category in [ACADEMIA, BOOK]:
                 title = self.description if '"' in self.description else f'"{self.description}"'
-                return f"{title} by {self.author}"
+                description = f"{title} by {self.author}"
             elif self.category == FINANCE and self.author in FINANCIAL_REPORTS_AUTHORS:
-                return f'{self.author} report: "{self.description}"'
+                description = f'{self.author} report: "{self.description}"'
             elif self.category == LEGAL and 'v.' in self.author:
-                return f"{self.author}: {self.description}"
-        elif self.category and self.author is None and self.description is None:
-            return self.category
+                description = f"{self.author}: {self.description}"
+
+        if not description:
+            pieces = without_falsey([self.author, self.description])
+
+            if pieces:
+                description = ' '.join(pieces)
+            else:
+                return None
+
+        if self.attached_to_email_id:
+            description += f" attached to email {self.attached_to_email_id}"
 
-        pieces = without_falsey([self.author, self.description])
-        return ' '.join(pieces) if pieces else None
+        return description
 
     def duplicate_cfgs(self) -> Generator['DocCfg', None, None]:
         """Create synthetic DocCfg objects that set the 'duplicate_of_id' field to point back to this object."""
@@ -205,12 +219,14 @@ class EmailCfg(CommunicationCfg):
         actual_text (str | None): In dire cases of broken OCR we just configure the body of the email as a string.
         fwded_text_after (str | None): If set, any text after this is a fwd of an article or similar
         is_fwded_article (bool): True if this is a newspaper article someone fwded. Used to exclude articles from word counting.
-        recipients (list[str | None]): Who received the email
+        recipients (list[Name]): Who received the email
+        subject (str): Subject line
     """
     actual_text: str | None = None
     fwded_text_after: str | None = None
     is_fwded_article: bool = False
-    recipients: list[str | None] = field(default_factory=list)
+    recipients: list[Name] = field(default_factory=list)
+    subject: str | None = None
 
     # This is necessary because for some dumb reason @dataclass(repr=False) doesn't cut it
     def __repr__(self) -> str:

epstein_files/util/env.py

@@ -8,7 +8,7 @@ from rich_argparse_plus import RichHelpFormatterPlus
 from epstein_files.util.constant.output_files import ALL_EMAILS_PATH, CHRONOLOGICAL_EMAILS_PATH, TEXT_MSGS_HTML_PATH
 from epstein_files.util.logging import env_log_level, exit_with_error, logger
 
-DEFAULT_WIDTH = 145
+DEFAULT_WIDTH = 155
 DEFAULT_FILE = 'default_file'
 EPSTEIN_GENERATE = 'epstein_generate'
 HTML_SCRIPTS = [EPSTEIN_GENERATE, 'epstein_word_count']
@@ -38,6 +38,7 @@ output.add_argument('--all-emails', '-ae', action='store_true', help='all the em
 output.add_argument('--all-other-files', '-ao', action='store_true', help='all the non-email, non-text msg files instead of just the interesting ones')
 parser.add_argument('--build', '-b', nargs="?", default=None, const=DEFAULT_FILE, help='write output to HTML file')
 output.add_argument('--email-timeline', action='store_true', help='print a table of all emails in chronological order')
+output.add_argument('--emailers-info-png', action='store_true', help='write a .png of the emeailers info table')
 output.add_argument('--json-files', action='store_true', help='pretty print all the raw JSON data files in the collection and exit')
 output.add_argument('--json-metadata', action='store_true', help='dump JSON metadata for all files and exit')
 output.add_argument('--output-emails', '-oe', action='store_true', help='generate emails section')
@@ -66,6 +67,7 @@ debug.add_argument('--suppress-logs', '-sl', action='store_true', help='set debu
 args = parser.parse_args()
 is_html_script = parser.prog in HTML_SCRIPTS
 
+args.build = args.build or args.emailers_info_png
 args.debug = args.deep_debug or args.debug or is_env_var_set('DEBUG')
 args.names = [None if n == 'None' else n for n in (args.names or [])]
 args.output_emails = args.output_emails or args.all_emails

epstein_files/util/file_helper.py

@@ -33,10 +33,13 @@ def coerce_file_stem(filename_or_id: int | str) -> str:
 
 
 def extract_file_id(filename_or_id: int | str | Path) -> str:
+    if isinstance(filename_or_id, str):
+        filename_or_id = filename_or_id.removesuffix(',')
+
     if isinstance(filename_or_id, int) or (isinstance(filename_or_id, str) and len(filename_or_id) <= 6):
         return id_str(filename_or_id)
 
-    file_match = FILE_ID_REGEX.match(str(filename_or_id))
+    file_match = FILE_ID_REGEX.match(str(filename_or_id).upper())
 
     if not file_match:
         raise RuntimeError(f"Failed to extract file ID from {filename_or_id}")