epstein-files 1.2.5__py3-none-any.whl → 1.4.1__py3-none-any.whl

epstein_files/util/doc_cfg.py

@@ -1,3 +1,4 @@
+import json
 import re
 from copy import deepcopy
 from dataclasses import Field, asdict, dataclass, field, fields
@@ -9,20 +10,21 @@ from dateutil.parser import parse
 from epstein_files.util.constant.names import *
 from epstein_files.util.constant.strings import *
 from epstein_files.util.data import remove_zero_time, without_falsey
+from epstein_files.util.env import args
 
-DuplicateType = Literal['earlier', 'quoted', 'redacted', 'same']
+DuplicateType = Literal['bounced', 'earlier', 'quoted', 'redacted', 'same']
 Metadata = dict[str, bool | datetime | int | str | list[str | None] |dict[str, bool | str]]
 
 # Misc
-CONSTANTIZE_NAMES = False  # A flag set to True that causes repr() of these classes to return strings of usable code
 INDENT = '    '
 INDENT_NEWLINE = f'\n{INDENT}'
 INDENTED_JOIN = f',{INDENT_NEWLINE}'
-MAX_LINE_LENGTH = 150
+MAX_LINE_LENGTH = 135
 REPUTATION_MGMT = f'{REPUTATION} management'
 SAME = 'same'
 
 DUPE_TYPE_STRS: dict[DuplicateType, str] = {
+    'bounced': 'a bounced copy of',
     'earlier': 'an earlier draft of',
     'quoted': 'quoted in full in',
     'redacted': 'a redacted version of',
@@ -32,7 +34,10 @@ DUPE_TYPE_STRS: dict[DuplicateType, str] = {
 FIELD_SORT_KEY = {
     'id': 'a',
     'author': 'aa',
-    'attribution_reason': 'zz',
+    'comment': 'zz',
+    'duplicate_ids': 'dup',
+    'duplicate_of_id': 'dupe',
+    'recipients': 'aaa',
 }
 
 FINANCIAL_REPORTS_AUTHORS = [
@@ -49,7 +54,6 @@ FINANCIAL_REPORTS_AUTHORS = [
 # Fields like timestamp and author are better added from the Document object
 NON_METADATA_FIELDS = [
     'actual_text',
-    'date',
     'id',
     'is_synthetic',
 ]
@@ -64,18 +68,18 @@ class DocCfg:
         id (str): ID of file
         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
+        date (str | None): Parsed to a datetime by timestamp() if it exists
         dupe_type (DuplicateType | None): The type of duplicate this file is or its 'duplicate_ids' are
         duplicate_ids (list[str]): IDs of *other* documents that are dupes of this document
         duplicate_of_id (str | None): If this is a dupe the ID of the duplicated file. This file will be suppressed
         is_interesting (bool | None): Override other considerations and always consider this file interesting (or not)
-        timestamp (datetime | None): Time this email was sent, file was created, article published, etc.
         is_synthetic (bool): True if this config was generated by the duplicate_cfgs() method
     """
     id: str
     attached_to_email_id: str | None = None
     author: Name = None
     category: str | None = None
+    comment: str = ''
     date: str | None = None
     description: str | None = None
     dupe_type: DuplicateType | None = None
@@ -84,12 +88,8 @@ class DocCfg:
     is_attribution_uncertain: bool = False
     is_interesting: bool | None = None
     is_synthetic: bool = False
-    timestamp: datetime | None = None
 
     def __post_init__(self):
-        if self.date:
-            self.timestamp = parse(self.date)
-
         if self.duplicate_of_id or self.duplicate_ids:
             self.dupe_type = self.dupe_type or SAME
 
@@ -142,7 +142,16 @@ class DocCfg:
             yield dupe_cfg
 
     def metadata(self) -> Metadata:
-        return {k: v for k, v in asdict(self).items() if k not in NON_METADATA_FIELDS and v}
+        metadata = {k: v for k, v in asdict(self).items() if k not in NON_METADATA_FIELDS and v}
+
+        if self.is_interesting is False:
+            metadata['is_interesting'] = False
+
+        return metadata
+
+    def timestamp(self) -> datetime | None:
+        if self.date:
+            return parse(self.date)
 
     def _props_strs(self) -> list[str]:
         props = []
@@ -151,20 +160,16 @@ class DocCfg:
         for _field in sorted(fields(self), key=lambda f: FIELD_SORT_KEY.get(f.name, f.name)):
             value = getattr(self, _field.name)
 
-            if value is None or value is False or (isinstance(value, list) and len(value) == 0):
+            if _field.name in ['actual_text', 'is_fwded_article', 'is_interesting']:  # fields can be False or None or ''
+                if value is not None:
+                    add_prop(_field, str(value))
+            elif not value or _field.name == 'dupe_type' and value == 'same':
                 continue
             elif _field.name == AUTHOR:
-                add_prop(_field, constantize_name(str(value)) if CONSTANTIZE_NAMES else f"'{value}'")
-            elif _field.name == 'category' and value in [EMAIL, TEXT_MESSAGE]:
-                continue
-            elif _field.name == 'recipients' and value:
-                recipients_str = str([constantize_name(r) if (CONSTANTIZE_NAMES and r) else r for r in value])
-                add_prop(_field, recipients_str.replace("'", '') if CONSTANTIZE_NAMES else recipients_str)
-            elif _field.name == 'timestamp' and self.date is not None:
-                continue  # Don't print both timestamp and date
-            elif isinstance(value, datetime):
-                value_str = remove_zero_time(value)
-                add_prop(_field, f"parse('{value_str}')" if CONSTANTIZE_NAMES else f"'{value}'")
+                add_prop(_field, constantize_name(str(value)) if args.constantize else f"'{value}'")
+            elif _field.name == 'recipients':
+                recipients_str = str([constantize_name(r) if (args.constantize and r) else r for r in value])
+                add_prop(_field, recipients_str.replace("'", '') if args.constantize else recipients_str)
             elif isinstance(value, str):
                 if "'" in value:
                     value = '"' + value.replace('"', r'\"') + '"'
@@ -182,14 +187,14 @@ class DocCfg:
         type_str = f"{type(self).__name__}("
         single_line_repr = type_str + ', '.join(props) + f')'
 
-        if len(single_line_repr) < MAX_LINE_LENGTH:
+        if len(single_line_repr) < MAX_LINE_LENGTH or (self.comment and getattr(self, 'is_fwded_article')):
             repr_str = single_line_repr
         else:
             repr_str = f"{type_str}{INDENT_NEWLINE}" + INDENTED_JOIN.join(props)
             repr_str += ',' if props else ''
             repr_str += '\n)'
 
-        if CONSTANTIZE_NAMES:
+        if args.constantize:
             repr_str = INDENT + INDENT_NEWLINE.join(repr_str.split('\n'))
             return repr_str.replace(',,', ',').replace(',),', '),').replace(',),', '),')
         else:
@@ -224,9 +229,10 @@ class EmailCfg(CommunicationCfg):
     """
     actual_text: str | None = None
     fwded_text_after: str | None = None
-    is_fwded_article: bool = False
+    is_fwded_article: bool | None = None
     recipients: list[Name] = field(default_factory=list)
     subject: str | None = None
+    truncate_to: int | 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

@@ -49,13 +49,16 @@ output.add_argument('--suppress-output', action='store_true', help='no output to
 output.add_argument('--uninteresting', action='store_true', help='only output uninteresting other files')
 output.add_argument('--width', '-w', type=int, default=DEFAULT_WIDTH, help='screen width to use (in characters)')
 
-scripts = parser.add_argument_group('SCRIPTS', 'Options used by epstein_search, epstein_show, and epstein_diff.')
+scripts = parser.add_argument_group('SCRIPTS', 'Options used by epstein_grep, epstein_show, and epstein_diff.')
 scripts.add_argument('positional_args', nargs='*', help='strings to searchs for, file IDs to show or diff, etc.')
+scripts.add_argument('--email-body', action='store_true', help='epstein_grep but only for the body of the email')
+scripts.add_argument('--min-line-length', type=int, help='epstein_grep minimum length of a matched line')
 scripts.add_argument('--raw', '-r', action='store_true', help='show raw contents of file (used by epstein_show)')
 scripts.add_argument('--whole-file', '-wf', action='store_true', help='print whole files')
 
 debug = parser.add_argument_group('DEBUG')
 debug.add_argument('--colors-only', '-c', action='store_true', help='print header with color key table and links and exit')
+debug.add_argument('--constantize', action='store_true', help='constantize names when printing repr() of objects')
 debug.add_argument('--debug', '-d', action='store_true', help='set debug level to INFO')
 debug.add_argument('--deep-debug', '-dd', action='store_true', help='set debug level to DEBUG')
 debug.add_argument('--json-stats', '-j', action='store_true', help='print JSON formatted stats about the files')
@@ -78,7 +81,9 @@ args.width = args.width if is_html_script else None
 args.any_output_selected = any([is_output_arg(arg) and val for arg, val in vars(args).items()])
 
 if not (args.any_output_selected or args.email_timeline or args.emailers_info):
-    logger.warning(f"No output section chosen; outputting default selection of texts, selected emails, and other files...")
+    if is_html_script:
+        logger.warning(f"No output section chosen; outputting default selection of texts, selected emails, and other files...")
+
     args.output_emails = args.output_other = args.output_texts = True
 
 if is_html_script:
@@ -97,13 +102,15 @@ if is_html_script:
             args.build = CHRONOLOGICAL_EMAILS_PATH
         else:
             args.build = TEXT_MSGS_HTML_PATH
-elif parser.prog.startswith('epstein_') and not args.positional_args:
+elif parser.prog.startswith('epstein_') and not args.positional_args and not args.names:
     exit_with_error(f"{parser.prog} requires positional arguments but got none!")
 
 if args.names:
     logger.warning(f"Output restricted to {args.names}")
     args.output_other = False
 
+if args.truncate and args.whole_file:
+    exit_with_error(f"--whole-file and --truncate are incompatible")
 
 # Log level args
 if args.deep_debug:

epstein_files/util/file_helper.py

@@ -38,6 +38,8 @@ def extract_file_id(filename_or_id: int | str | Path) -> str:
 
     if isinstance(filename_or_id, int) or (isinstance(filename_or_id, str) and len(filename_or_id) <= 6):
         return id_str(filename_or_id)
+    elif isinstance(filename_or_id, str) and len(filename_or_id) == 8:
+        return f"{HOUSE_OVERSIGHT_PREFIX}{filename_or_id}"
 
     file_match = FILE_ID_REGEX.match(str(filename_or_id).upper())
 

epstein_files/util/highlighted_group.py

@@ -31,6 +31,8 @@ REGEX_STYLE_PREFIX = 'regex'
 SIMPLE_NAME_REGEX = re.compile(r"^[-\w, ]+$", re.IGNORECASE)
 TECH_BRO = 'tech bro'
 
+VICTIM_COLOR = 'orchid1'
+
 CATEGORY_STYLE_MAPPING = {
     ARTICLE: JOURNALIST,
     BOOK: JOURNALIST,
@@ -160,7 +162,7 @@ class HighlightedNames(HighlightedText):
 
         pattern = '|'.join(name_patterns)
 
-        if args.deep_debug:
+        if args.deep_debug and args.colors_only:
             debug_console.print(Text('').append(f"{name:25s}", style=self.style).append(f" '{pattern}'", style='dim'))
 
         return pattern
@@ -215,7 +217,7 @@ HIGHLIGHTED_NAMES = [
     ManualHighlight(
         label='email_subject',
         style='light_yellow3',
-        pattern=r"^(> )?(Classification|Flag|Subject): (?P<email_subject>.*)",
+        pattern=r"^(> )?(Classification|Flag|Subject|Sujet ?): (?P<email_subject>.*)",
     ),
     HighlightedNames(
         label=ACADEMIA,
@@ -245,12 +247,13 @@ HIGHLIGHTED_NAMES = [
             r"Bard\s+((Early )?College|High School|Schools)",
             r"Brotherton",
             r"Carl\s*Sagan",
-            r"Columbia",
+            r"Columbia(\s*(Business\s*School|University))?",
             r"Dan(iel|ny) Kahneman",
             r"(Francis\s*)?Crick",
             r"J(ames|im)\s*Watson",
             r"(Lord\s*)?Martin\s*Rees",
             r"Massachusetts\s*Institute\s*of\s*Technology",
+            r"Mayo\s*Clinic",
             r"Media\s*Lab",
             r"(Marvin\s*)?Minsky",
             r"MIT(\s*Media\s*Lab)?",
@@ -260,10 +263,11 @@ HIGHLIGHTED_NAMES = [
             r"Princeton(\s*University)?",
             r"Regeneron",
             r"(Richard\s*)?Dawkins",
+            r"Rockefeller\s*University",
             r"(Sandy\s*)?Pentland",  # Media Lab
             r"Sanofi",
             r"Stanford(\s*University)?(\s*Hospital)?",
-            r"(Stephen\s*)?Hawking",
+            r"(Ste(ph|v)en\s*)?Hawking",
             r"(Steven?\s*)?Pinker",
             r"Texas\s*A&M",
             r"Tulane",
@@ -319,6 +323,7 @@ HIGHLIGHTED_NAMES = [
         patterns=[
             r"(Art )?Spiegelman",
             r"Artspace",
+            r"Ayn\s*Rand",
             r"Bobby slayton",
             r"bono\s*mick",
             r"Errol(\s*Morris)?",
@@ -413,9 +418,10 @@ HIGHLIGHTED_NAMES = [
             'Philip Kafka': 'president of Prince Concepts (and son of Terry Kafka?)',
             ROBERT_LAWRENCE_KUHN: 'investment banker, China expert',
             TERRY_KAFKA: 'CEO of Impact Outdoor (highway billboards)',
-            TOM_PRITZKER: 'brother of J.B. Pritzker',
+            TOM_PRITZKER: 'chairman of The Pritzker Organization and Hyatt Hotels',
         },
         patterns=[
+            r"Arthur Klein",
             r"((Bill|David)\s*)?Koch(\s*(Bro(s|thers)|Industries))?",
             r"Gruterite",
             r"((John|Patricia)\s*)?Kluge",
@@ -423,6 +429,7 @@ HIGHLIGHTED_NAMES = [
             r"(Mi(chael|ke)\s*)?Ovitz",
             r"(Steve\s+)?Wynn",
             r"(Les(lie)?\s+)?Wexner",
+            r"Michael\s*Klein",
             r"New Leaf Ventures",
             r"Park Partners",
             r"SALSS",
@@ -500,6 +507,7 @@ HIGHLIGHTED_NAMES = [
             r"Dem(ocrat(ic)?)?",
             r"(Diana\s*)?DeGette",
             r"DNC",
+            r"(Ed(ward)?\s*)?Mezvinsky",
             r"Elena\s*Kagan",
             r"(Eliott?\s*)?Spitzer(, Eliot)?",
             r"Eric Holder",
@@ -550,7 +558,6 @@ HIGHLIGHTED_NAMES = [
             MERWIN_DELA_CRUZ: None,  # HOUSE_OVERSIGHT_032652 Groff says "Jojo and Merwin both requested off Nov. 25 and 26"
             NADIA_MARCINKO: "Epstein's pilot",
             'Sean J. Lancaster': 'airplane reseller',
-            ZUBAIR_KHAN: 'Tranchulas cybersecurity, InsightsPod founder, Islamabad / Dubai',
         },
         patterns=[
             r"Adriana\s*Ross",
@@ -566,7 +573,7 @@ HIGHLIGHTED_NAMES = [
             MARK_EPSTEIN: 'brother of Jeffrey',
         },
         patterns=[
-            r"JEGE(\s*Inc)",
+            r"JEGE(\s*Inc)?",
             r"LSJ",
         ],
     ),
@@ -640,6 +647,7 @@ HIGHLIGHTED_NAMES = [
             r"AfD",
             r"(Angela )?Merk(el|le)",
             r"Austria",
+            r"Belgi(an|um)",
             r"(Benjamin\s*)?Harnwell",
             r"Berlin",
             r"Borge",
@@ -649,6 +657,7 @@ HIGHLIGHTED_NAMES = [
             r"Brussels",
             r"Cannes",
             r"Cypr(iot|us)",
+            r"David\s*Cameron",
             r"Davos",
             r"ECB",
             r"England",
@@ -663,6 +672,8 @@ HIGHLIGHTED_NAMES = [
             r"Ital(ian|y)",
             r"Jacques",
             r"Kiev",
+            r"Latvian?",
+            r"Lithuanian?",
             r"Le\s*Pen",
             r"London",
             r"Macron",
@@ -672,11 +683,13 @@ HIGHLIGHTED_NAMES = [
             r"NATO",
             r"(Nicholas\s*)?Sarkozy",
             r"Nigel(\s*Farage)?",
+            r"(Northern\s*)?Ireland",
             r"Norw(ay|egian)",
             r"Oslo",
             r"Paris",
             r"Polish",
             r"pope",
+            r"Portugal",
             r"Scotland",
             r"(Sebastian )?Kurz",
             r"Stockholm",
@@ -685,6 +698,7 @@ HIGHLIGHTED_NAMES = [
             r"Swed(en|ish)(?![-\s]+American Life Scienc)",
             r"Swi(ss|tzerland)",
             r"(Tony\s)?Blair",
+            r"United\s*Kingdom",
             r"U\.K\.",
             r"Ukrain(e|ian)",
             r"Venice",
@@ -748,6 +762,7 @@ HIGHLIGHTED_NAMES = [
             r"(Janet\s*)?Yellen",
             r"(Jerome\s*)?Powell(?! M\. Cabot)",
             r"(Jimmy\s*)?Cayne",
+            r"Joon\s*Yun",
             r"JPMC?",
             r"j\.?p\.?\s*morgan(\.?com|\s*Chase)?",
             r"Madoff",
@@ -760,6 +775,7 @@ HIGHLIGHTED_NAMES = [
             r"(Peter L. )?Scher",
             r"(Ray\s*)?Dalio",
             r"(Richard\s*)?LeFrak",
+            r"Rockefeller(?! University)(\s*Foundation)?",
             r"(Ste(phen|ve)\s*)?Schwart?z?man",
             r"Serageldin",
             r"UBS",
@@ -823,6 +839,7 @@ HIGHLIGHTED_NAMES = [
             r"FTC",
             r"(General\s*)?P(a|e)traeus",
             r"Geoff\s*Ling",
+            r"Homeland\s*Security",
             r"IRS",
             r"(James\s*)?Comey",
             r"(Jennifer\s*Shasky\s*)?Calvery",
@@ -952,7 +969,7 @@ HIGHLIGHTED_NAMES = [
             'Alain Forget': 'author of "How To Get Out Of This World ALIVE"',
             'Alex Yablon': 'New York Magazine fact checker (?)',
             EDWARD_JAY_EPSTEIN: 'no relation, wrote books about spies',
-            HENRY_HOLT: f"{MICHAEL_WOLFF}'s book publisher",
+            HENRY_HOLT: f"{MICHAEL_WOLFF}'s book publisher (company not a person)",
             JAMES_HILL: 'ABC News',
             JENNIFER_JACQUET: 'Future Science magazine',
             JOHN_BROCKMAN: 'literary agent and author specializing in scientific literature',
@@ -972,14 +989,14 @@ HIGHLIGHTED_NAMES = [
             r'Associated\s*Press',
             r"Axios",
             r"BBC",
-            r"(Bob|Robert)\s*Costa",
+            r"(Bob|Robert)\s*(Costa|Woodward)",
             r"Breitbart",
             r"BuzzFeed(\s*News)?",
             r"C-?Span",
             r"CBS(\s*(4|Corp|News))?",
             r"Charlie\s*Rose",
             r"China\s*Daily",
-            r"CNBC",
+            r"(C|MS)?NBC(\s*News)?",
             r"CNN(politics?)?",
             r"Con[cs]hita", r"Sarnoff",
             r"Daily Business Review",
@@ -1000,6 +1017,7 @@ HIGHLIGHTED_NAMES = [
             r"Globe\s*and\s*Mail",
             r"Good\s*Morning\s*America",
             r"Graydon(\s*Carter)?",
+            r"Hollywood\s*Reporter",
             r"Huff(ington)?(\s*Po(st)?)?",
             r"Ingram, David",
             r"James\s*Hill",
@@ -1007,6 +1025,7 @@ HIGHLIGHTED_NAMES = [
             r"Jesse Kornbluth",
             r"John\s*Connolly",
             r"Jonathan\s*Karl",
+            r"Journal of Criminal Law and Criminology",
             r"Julie\s*(K.?\s*)?Brown", r'jbrown@miamiherald.com',
             r"(Katie\s*)?Couric",
             r"Keith\s*Larsen",
@@ -1025,7 +1044,6 @@ HIGHLIGHTED_NAMES = [
             r"PERVERSION\s*OF\s*JUSTICE",
             r"Politico",
             r"Pro\s*Publica",
-            r"Reuters",
             r"(Sean\s*)?Hannity",
             r"Sharon Churcher",  # Daily Mail
             r"Sulzberger",
@@ -1038,7 +1056,9 @@ HIGHLIGHTED_NAMES = [
             r"(The\s*)?New\s*Yorker",
             r"(The\s*)?Wall\s*Street\s*Journal",
             r"(The\s*)?Wa(shington\s*)?Po(st)?",
+            r"(Thomson\s*)?Reuters",
             r"(Uma\s*)?Sanghvi",
+            r"USA\s*Today",
             r"Vanity\s*Fair",
             r"Viceland",
             r"Vick[iy]\s*Ward",
@@ -1072,6 +1092,7 @@ HIGHLIGHTED_NAMES = [
             r"Chile",
             r"Colombian?",
             r"Cuban?",
+            r"el chapo",
             r"El\s*Salvador",
             r"((Enrique )?Pena )?Nieto",
             r"Lat(in)?\s*Am(erican?)?",
@@ -1113,12 +1134,16 @@ HIGHLIGHTED_NAMES = [
             r"Arizona(?! State University)",
             r"Aspen",
             r"Berkeley",
+            r"Boston",
             r"Brooklyn",
             r"California",
             r"Canada",
             r"Cape Cod",
+            r"Charlottesville",
+            r"Colorado",
             r"Connecticut",
             r"Florida",
+            r"Los Angeles",
             r"Loudoun\s*County?",
             r"Martha's\s*Vineyard",
             r"Miami(?!\s?Herald)",
@@ -1128,9 +1153,12 @@ HIGHLIGHTED_NAMES = [
             r"NY(C|\s*State)",
             r"Orange\s*County",
             r"Oregon",
+            r"Palo Alto",
+            r"Pennsylvania",
             r"Phoenix",
             r"Portland",
-            r"Santa\s*Fe",
+            r"San Francisco",
+            r"Sant[ae]\s*Fe",
             r"Telluride",
             r"Teterboro",
             r"Texas(?! A&M)",
@@ -1157,6 +1185,7 @@ HIGHLIGHTED_NAMES = [
             r"Afghanistan",
             r"Al[-\s]?Qa[ei]da",
             r"Ahmadinejad",
+            r"(Rakhat )?Aliyev",
             r"Arab",
             r"Aramco",
             r"Armenia",
@@ -1185,6 +1214,7 @@ HIGHLIGHTED_NAMES = [
             r"Hamas",
             r"Hezbollah",
             r"HBJ",
+            r"Hourani",
             r"Houthi",
             r"Imran\s+Khan",
             r"Iran(ian)?([-\s]Contra)?",
@@ -1207,10 +1237,11 @@ HIGHLIGHTED_NAMES = [
             r"MB(N|S|Z)",
             r"Mid(dle)?\s*East(ern)?",
             r"Mohammed\s+bin\s+Salman",
-            r"Morocco",
+            r"Morocc(an|o)",
             r"Mubarak",
             r"Muslim(\s*Brotherhood)?",
             r"Nayaf",
+            r"Nazarbayev",
             r"Pakistani?",
             r"Omar",
             r"(Osama\s*)?Bin\s*Laden",
@@ -1230,10 +1261,10 @@ HIGHLIGHTED_NAMES = [
             r"Syrian?",
             r"(Tarek\s*)?El\s*Sayed",
             r"Tehran",
+            r"Timur\s*Kulibayev",
             r"Tripoli",
             r"Tunisian?",
-            r"Turk(ey|ish)",
-            r"Turks(?! & Caicos)",
+            r"Turk(ey|ish)?(?!s & Caicos)",
             r"UAE",
             r"((Iraq|Iran|Kuwait|Qatar|Yemen)i?)",
         ],
@@ -1281,6 +1312,7 @@ HIGHLIGHTED_NAMES = [
         },
         patterns=[
             r"(Matt(hew)? )?Hiltzi[gk]",
+            r"Philip\s*Barden",
             r"PR\s*Newswire",
             REPUTATION_MGMT,
             r"Reputation.com",
@@ -1308,6 +1340,7 @@ HIGHLIGHTED_NAMES = [
             r"Broidy",
             r"(Chris\s)?Christie",
             r"(?<!Merwin Dela )Cruz",
+            r"Darrell\s*Issa",
             r"Devin\s*Nunes",
             r"(Don\s*)?McGa[hn]n",
             r"Erik Prince",
@@ -1333,7 +1366,7 @@ HIGHLIGHTED_NAMES = [
             r"(Michael\s)?Hayden",
             r"((General|Mike)\s*)?(Flynn|Pence)",
             r"(Mitt\s*)?Romney",
-            r"Mnuchin",
+            r"(Steven?\s*)?Mnuchin",
             r"(Newt\s*)Gingrich",
             r"Nikki",
             r"Haley",
@@ -1346,7 +1379,9 @@ HIGHLIGHTED_NAMES = [
             r"(Rex\s*)?Till?erson",
             r"(?<!Cynthia )(Richard\s*)?Nixon",
             r"RNC",
+            r"(Roy|Stephen)\s*Moore",
             r"Tea\s*Party",
+            r"Wilbur\s*Ross",
         ],
     ),
     HighlightedNames(
@@ -1396,7 +1431,6 @@ HIGHLIGHTED_NAMES = [
             r"Russian?",
             r"Sberbank",
             r"Soviet(\s*Union)?",
-            r"Timur\s*Kulibayev",
             r"USSR",
             r"Vlad(imir)?(?! Yudash)",
             r"(Vladimir\s*)?Putin",
@@ -1435,6 +1469,7 @@ HIGHLIGHTED_NAMES = [
             REID_HOFFMAN: 'PayPal mafia member, founder of LinkedIn',
             STEVEN_SINOFSKY: 'ex-Microsoft, loves bitcoin',
             VINCENZO_IOZZO: 'CEO of the identity-security company SlashID',
+            ZUBAIR_KHAN: 'Tranchulas cybersecurity, InsightsPod founder, Islamabad / Dubai',
         },
         patterns=[
             r"AG?I",
@@ -1443,6 +1478,7 @@ HIGHLIGHTED_NAMES = [
             r"Danny\s*Hillis",
             r"deep learning",
             r"Drew\s*Houston",
+            r"Eliezer\s*Yudkowsky",
             r"Eric\s*Schmidt",
             r"Greylock(\s*Partners)?",
             r"(?<!(ustin|Moshe)\s)Hoffmand?",
@@ -1462,6 +1498,7 @@ HIGHLIGHTED_NAMES = [
             r"Softbank",
             r"SpaceX",
             r"Tim\s*Ferriss?",
+            r"Vision\s*Fund",
             r"WikiLeak(ed|s)",
         ],
     ),
@@ -1518,6 +1555,7 @@ HIGHLIGHTED_NAMES = [
             r"(Kenneth E\. )?Mapp",
             r"PBI",
             r"Puerto\s*Ric(an|o)",
+            r"San\s*Juan",
             r"S(ain)?t.?\s*Thomas",
             r"USVI",
             r"(?<!stein |vis-a-)VI(?!s-a-)",
@@ -1527,9 +1565,9 @@ HIGHLIGHTED_NAMES = [
     ),
     HighlightedNames(
         label='victim',
-        style='orchid1',
+        style=VICTIM_COLOR,
         patterns=[
-            r"#metoo",
+            r"child\s*pornography",
             r"(David\s*)?Bo[il]es(,?\s*Schiller( & Flexner)?)?",
             r"(Gloria\s*)?Allred",
             r"(Jane|Tiffany)\s*Doe",
@@ -1595,6 +1633,11 @@ HIGHLIGHTED_NAMES = [
     HighlightedNames(emailers={SULTAN_BIN_SULAYEM: 'chairman of ports in Dubai, CEO of DP World'}, style='green1', category=MIDEAST),
 
     # HighlightedText not HighlightedNames bc of word boundary issue
+    HighlightedText(
+        label='metoo',
+        style=VICTIM_COLOR,
+        patterns=[r"#metoo"]
+    ),
     HighlightedText(
         label='phone_number',
         style='bright_green',
@@ -1615,7 +1658,7 @@ HIGHLIGHTED_TEXTS = [
     HighlightedText(
         label='header_field',
         style='plum4',
-        patterns=[r'^>? ?(Date|From|Sent|To|C[cC]|Importance|Reply[- ]?To|Subject|Bee|B[cC]{2}|Attachments|Flag|Classification|((A|De(stinataire)?|Envoye|Expe(cl|d)iteur|Objet|Q) ?)):'],
+        patterns=[r'^[>• ]{,4}(Date ?|From|Sent|To|C[cC]|Importance|Reply[- ]?To|Subject|Bee|B[cC]{2}|Attachments|Flag|Classification|((A|Debut du message transfer[&e]|De(stinataire)?|Envoye|Expe(cl|d)iteur|Objet|Q|Sujet) ?)):|^on behalf of'],
     ),
     HighlightedText(
         label='http_links',
@@ -1625,16 +1668,16 @@ HIGHLIGHTED_TEXTS = [
     HighlightedText(
         label='quoted_reply_line',
         style='dim',
-        patterns=[REPLY_REGEX.pattern],
+        patterns=[REPLY_REGEX.pattern, r"^(> )?wrote:$"],
     ),
     HighlightedText(
         label='redacted',
         style='grey58',
-        patterns=[fr"{REDACTED}|Privileged - Redacted"],
+        patterns=[fr"{REDACTED}|<?Privileged - Redacted>?"],
     ),
     HighlightedText(
         label='sent_from',
-        style='gray42 italic',
+        style='light_cyan3 italic dim',
         patterns=[SENT_FROM_REGEX.pattern],
     ),
     HighlightedText(