epstein-files 1.1.2__py3-none-any.whl → 1.1.5__py3-none-any.whl

epstein_files/__init__.py

@@ -16,13 +16,14 @@ from rich.text import Text
 from epstein_files.epstein_files import EpsteinFiles, document_cls
 from epstein_files.documents.document import INFO_PADDING, Document
 from epstein_files.documents.email import Email
-from epstein_files.util.constant.output_files import ALL_EMAILS_PATH, CHRONOLOGICAL_EMAILS_PATH, TEXT_MSGS_HTML_PATH, make_clean
+from epstein_files.util.constant.output_files import make_clean
 from epstein_files.util.env import args
 from epstein_files.util.file_helper import coerce_file_path, extract_file_id
 from epstein_files.util.logging import exit_with_error, logger
 from epstein_files.util.output import (print_emails_section, print_json_files, print_json_stats,
-     print_other_files_section, print_text_messages_section, write_complete_emails_timeline, write_json_metadata, write_urls)
-from epstein_files.util.rich import build_highlighter, console, print_color_key, print_title_page_header, print_title_page_tables, print_subtitle_panel, write_html
+     print_other_files_section, print_text_messages_section, print_email_timeline, print_json_metadata, write_urls)
+from epstein_files.util.rich import (build_highlighter, console, print_color_key, print_title_page_header,
+     print_title_page_tables, print_subtitle_panel, write_html)
 from epstein_files.util.timer import Timer
 from epstein_files.util.word_count import write_word_counts_html
 
@@ -37,13 +38,13 @@ def generate_html() -> None:
     epstein_files = EpsteinFiles.get_files(timer)
 
     if args.json_metadata:
-        write_json_metadata(epstein_files)
+        print_json_metadata(epstein_files)
         exit()
     elif args.json_files:
         print_json_files(epstein_files)
         exit()
 
-    print_title_page_header(epstein_files)
+    print_title_page_header()
 
     if args.email_timeline:
         print_color_key()
@@ -62,7 +63,7 @@ def generate_html() -> None:
         emails_that_were_printed = print_emails_section(epstein_files)
         timer.print_at_checkpoint(f"Printed {len(emails_that_were_printed):,} emails")
     elif args.email_timeline:
-        write_complete_emails_timeline(epstein_files)
+        print_email_timeline(epstein_files)
         timer.print_at_checkpoint(f"Printed chronological emails table")
 
     if args.output_other:
@@ -74,15 +75,7 @@ def generate_html() -> None:
         print_other_files_section(files, epstein_files)
         timer.print_at_checkpoint(f"Printed {len(files)} other files (skipped {len(epstein_files.other_files) - len(files)})")
 
-    # Save output
-    if args.all_emails:
-        output_path = ALL_EMAILS_PATH
-    elif args.email_timeline:
-        output_path = CHRONOLOGICAL_EMAILS_PATH
-    else:
-        output_path = TEXT_MSGS_HTML_PATH
-
-    write_html(output_path)
+    write_html(args.build)
     logger.warning(f"Total time: {timer.seconds_since_start_str()}")
 
     # JSON stats (mostly used for building pytest checks)
@@ -103,8 +96,7 @@ def epstein_search():
     for search_term in args.positional_args:
         temp_highlighter = build_highlighter(search_term)
         search_results = epstein_files.docs_matching(search_term, args.names)
-        console.line(2)
-        print_subtitle_panel(f"Found {len(search_results)} documents matching '{search_term}'", padding=(0, 0, 0, 3))
+        print_subtitle_panel(f"Found {len(search_results)} documents matching '{search_term}'")
 
         for search_result in search_results:
             console.line()
@@ -122,11 +114,16 @@ def epstein_search():
 def epstein_show():
     """Show the color highlighted file. If --raw arg is passed, show the raw text of the file as well."""
     _assert_positional_args()
-    ids = [extract_file_id(arg) for arg in args.positional_args]
-    raw_docs = [Document(coerce_file_path(id)) for id in ids]
-    docs = [document_cls(doc)(doc.file_path) for doc in raw_docs]
+    raw_docs: list[Document] = []
     console.line()
 
+    try:
+        ids = [extract_file_id(arg) for arg in args.positional_args]
+        raw_docs = [Document(coerce_file_path(id)) for id in ids]
+        docs = Document.sort_by_timestamp([document_cls(doc)(doc.file_path) for doc in raw_docs])
+    except Exception as e:
+        exit_with_error(str(e))
+
     for doc in docs:
         console.print('\n', doc, '\n')
 

epstein_files/documents/communication.py

@@ -9,7 +9,7 @@ from epstein_files.documents.document import CLOSE_PROPERTIES_CHAR, Document
 from epstein_files.util.constant.names import UNKNOWN
 from epstein_files.util.constants import FALLBACK_TIMESTAMP
 from epstein_files.util.doc_cfg import CommunicationCfg
-from epstein_files.util.highlighted_group import get_style_for_name
+from epstein_files.util.highlighted_group import get_style_for_name, styled_name
 from epstein_files.util.rich import key_value_txt
 
 TIMESTAMP_SECONDS_REGEX = re.compile(r":\d{2}$")
@@ -25,10 +25,10 @@ class Communication(Document):
         return self.author or UNKNOWN
 
     def author_style(self) -> str:
-        return get_style_for_name(self.author_or_unknown())
+        return get_style_for_name(self.author)
 
     def author_txt(self) -> Text:
-        return Text(self.author_or_unknown(), style=self.author_style())
+        return styled_name(self.author)
 
     def external_links_txt(self, _style: str = '', include_alt_links: bool = True) -> Text:
         """Overrides super() method to apply self.author_style."""

epstein_files/documents/document.py

@@ -88,6 +88,9 @@ class Document:
     strip_whitespace: ClassVar[bool] = True  # Overridden in JsonFile
 
     def __post_init__(self):
+        if not self.file_path.exists():
+            raise FileNotFoundError(f"File '{self.file_path.name}' does not exist!")
+
         self.filename = self.file_path.name
         self.file_id = extract_file_id(self.filename)
         # config and url_slug could have been pre-set in Email

epstein_files/documents/email.py

@@ -24,7 +24,7 @@ from epstein_files.util.data import (TIMEZONE_INFO, collapse_newlines, escape_si
      flatten, listify, remove_timezone, uniquify)
 from epstein_files.util.doc_cfg import EmailCfg, Metadata
 from epstein_files.util.file_helper import extract_file_id, file_stem_for_id
-from epstein_files.util.highlighted_group import get_style_for_name
+from epstein_files.util.highlighted_group import JUNK_EMAILERS, get_style_for_name
 from epstein_files.util.logging import logger
 from epstein_files.util.rich import *
 
@@ -71,6 +71,7 @@ OCR_REPAIRS: dict[str | re.Pattern, str] = {
     # Signatures
     'BlackBerry by AT &T': 'BlackBerry by AT&T',
     'BlackBerry from T- Mobile': 'BlackBerry from T-Mobile',
+    'Envoy& de mon iPhone': 'Envoyé de mon iPhone',
     "from my 'Phone": 'from my iPhone',
     'from Samsung Mob.le': 'from Samsung Mobile',
     'gJeremyRubin': '@JeremyRubin',
@@ -126,13 +127,12 @@ EMAIL_SIGNATURE_REGEXES = {
     UNKNOWN: re.compile(r"(This message is directed to and is for the use of the above-noted addressee only.*\nhereon\.)", re.DOTALL),
 }
 
-# Invalid for links to EpsteinWeb
-JUNK_EMAILERS = [
-    'asmallworld@travel.asmallworld.net',
-    "digest-noreply@quora.com",
-    'editorialstaff@flipboard.com',
-    'How To Academy',
-    'Jokeland',
+EMAIL_TABLE_COLS = [
+    {'name': 'Sent At', 'justify': 'left', 'style': TIMESTAMP_DIM},
+    {'name': 'From', 'justify': 'left', 'max_width': 20},
+    {'name': 'To', 'justify': 'left', 'max_width': 22},
+    {'name': 'Length', 'justify': 'right', 'style': 'wheat4'},
+    {'name': 'Subject', 'justify': 'left', 'min_width': 35, 'style': 'honeydew2'},
 ]
 
 MAILING_LISTS = [
@@ -150,11 +150,13 @@ TRUNCATE_ALL_EMAILS_FROM = JUNK_EMAILERS + MAILING_LISTS + [
 
 TRUNCATION_LENGTHS = {
     '023627': 16_800,  # Micheal Wolff article with brock pierce
-    '030245': 7_500,   # Epstein rationalizes his behavior in an open letter to the world
-    '030781': 1_700,   # Bannon email about crypto coin issues
-    '032906': 750,     # David Blaine email
+    '030245': None,    # Epstein rationalizes his behavior in an open letter to the world
+    '030781': None,    # Bannon email about crypto coin issues
+    '032906': None,    # David Blaine email
     '026036': 6000,    # Gino Yu blockchain mention
-    '023208': 350_000, # Long discussion about leon black's finances
+    '023208': None,    # Long discussion about leon black's finances
+    '029609': None,    # Joi Ito
+    '025233': None,    # Reputation.com discussion
 }
 
 # These are long forwarded articles so we force a trim to 1,333 chars if these strings exist
@@ -296,14 +298,6 @@ USELESS_EMAILERS = FLIGHT_IN_2012_PEOPLE + IRAN_DEAL_RECIPIENTS + KRASSNER_RECIP
     'p.peachev@independent.co.uk',
 ]
 
-# Emails sent by epstein to himself that are just notes
-SELF_EMAILS_FILE_IDS = [
-    '026677',
-    '029752',   # TODO: jokeland...
-    '030238',
-    # '033274',  # TODO: Epstein's note to self doesn't get printed if we don't set the recipients to [None]
-]
-
 METADATA_FIELDS = [
     'is_junk_mail',
     'recipients',
@@ -320,6 +314,7 @@ LINE_REPAIR_MERGES = {
     '022695': 4,
     '023067': 3,
     '025790': 2,
+    '026345': 3,
     '026609': 4,
     '026924': [2, 4],
     '028931': [3, 6],
@@ -346,6 +341,7 @@ LINE_REPAIR_MERGES = {
     '032405': 4,
     '033097': 2,
     '033144': [2, 4],
+    '033217': 3,
     '033228': [3, 5],
     '033357': [2, 4],
     '033486': [7, 9],
@@ -391,25 +387,21 @@ class Email(Communication):
 
         super().__post_init__()
 
-        try:
-            if self.config and self.config.recipients:
-                self.recipients = self.config.recipients
-            else:
-                for recipient in self.header.recipients():
-                    self.recipients.extend(self._extract_emailer_names(recipient))
-
-                if self.author in MAILING_LISTS and (len(self.recipients) == 0 or self.recipients == [self.author]):
-                    self.recipients = [JEFFREY_EPSTEIN]   # Assume mailing list emails are to Epstein
-        except Exception as e:
-            console.print_exception()
-            console.line(2)
-            logger.fatal(f"Failed on {self.file_id}")
-            console.line(2)
-            raise e
-
-        # Remove self CCs
-        recipients = [r for r in self.recipients if r != self.author or self.file_id in SELF_EMAILS_FILE_IDS]
-        self.recipients = list(set(recipients))
+        if self.config and self.config.recipients:
+            self.recipients = self.config.recipients
+        else:
+            for recipient in self.header.recipients():
+                self.recipients.extend(self._extract_emailer_names(recipient))
+
+            # Assume mailing list emails are to Epstein
+            if self.author in MAILING_LISTS and (self.is_note_to_self() or not self.recipients):
+                self.recipients = [JEFFREY_EPSTEIN]
+
+        # Remove self CCs but preserve self emails
+        if not self.is_note_to_self():
+            self.recipients = [r for r in self.recipients if r != self.author]
+
+        self.recipients = sorted(list(set(self.recipients)), key=lambda r: r or UNKNOWN)
         self.text = self._prettify_text()
         self.actual_text = self._actual_text()
         self.sent_from_device = self._sent_from_device()
@@ -419,8 +411,13 @@ class Email(Communication):
 
     def info_txt(self) -> Text:
         email_type = 'fwded article' if self.is_fwded_article() else 'email'
-        txt = Text(f"OCR text of {email_type} from ", style='grey46').append(self.author_txt()).append(' to ')
-        return txt.append(self.recipients_txt()).append(highlighter(f" probably sent at {self.timestamp}"))
+        txt = Text(f"OCR text of {email_type} from ", style='grey46').append(self.author_txt())
+
+        if self.config and self.config.is_attribution_uncertain:
+            txt.append(f" {QUESTION_MARKS}", style=self.author_style())
+
+        txt.append(' to ').append(self.recipients_txt())
+        return txt.append(highlighter(f" probably sent at {self.timestamp}"))
 
     def is_fwded_article(self) -> bool:
         return bool(self.config and self.config.is_fwded_article)
@@ -428,6 +425,9 @@ class Email(Communication):
     def is_junk_mail(self) -> bool:
         return self.author in JUNK_EMAILERS or self.author in MAILING_LISTS
 
+    def is_note_to_self(self) -> bool:
+        return self.recipients == [self.author]
+
     def metadata(self) -> Metadata:
         local_metadata = asdict(self)
         local_metadata['is_junk_mail'] = self.is_junk_mail()
@@ -447,7 +447,10 @@ class Email(Communication):
         ], join=', ')
 
     def subject(self) -> str:
-        return self.header.subject or ''
+        if self.config and self.config.subject:
+            return self.config.subject
+        else:
+            return self.header.subject or ''
 
     def summary(self) -> Text:
         """One line summary mostly for logging."""
@@ -498,11 +501,8 @@ class Email(Communication):
 
     def _border_style(self) -> str:
         """Color emails from epstein to others with the color for the first recipient."""
-        if self.author == JEFFREY_EPSTEIN:
-            if len(self.recipients) == 0 or self.recipients == [None]:
-                style = self.author_style()
-            else:
-                style = get_style_for_name(self.recipients[0])
+        if self.author == JEFFREY_EPSTEIN and len(self.recipients) > 0:
+            style = get_style_for_name(self.recipients[0])
         else:
             style = self.author_style()
 
@@ -772,7 +772,7 @@ class Email(Communication):
         if args.whole_file:
             num_chars = len(self.text)
         elif self.file_id in TRUNCATION_LENGTHS:
-            num_chars = TRUNCATION_LENGTHS[self.file_id]
+            num_chars = TRUNCATION_LENGTHS[self.file_id] or self.file_size()
         elif self.author in TRUNCATE_ALL_EMAILS_FROM or includes_truncate_term:
             num_chars = int(MAX_CHARS_TO_PRINT / 3)
         elif quote_cutoff and quote_cutoff < MAX_CHARS_TO_PRINT:
@@ -839,26 +839,37 @@ class Email(Communication):
             self.log_top_lines(self.header.num_header_rows + 4, f'Original header:')
 
     @staticmethod
-    def build_emails_table(emails: list['Email'], _author: str | None, include_title: bool = False) -> Table:
-        """Turn a set of Emails to/from a given _author into a Table."""
-        author = _author or UNKNOWN
-
-        table = Table(
-            title=f"Emails to/from {author} starting {emails[0].timestamp.date()}" if include_title else None,
-            border_style=get_style_for_name(author, allow_bold=False),
-            header_style="bold"
+    def build_emails_table(emails: list['Email'], author: str | None = '', title: str = '', show_length: bool = False) -> Table:
+        """Turn a set of Emails into a Table."""
+        if title and author:
+            raise ValueError(f"Can't provide both 'author' and 'title' args")
+        elif author == '' and title == '':
+            raise ValueError(f"Must provide either 'author' or 'title' arg")
+
+        author_style = get_style_for_name(author, allow_bold=False)
+        link_style = author_style if author else ARCHIVE_LINK_COLOR
+
+        table = build_table(
+            title or None,
+            cols=[col for col in EMAIL_TABLE_COLS if show_length or col['name'] not in ['Length']],
+            border_style=DEFAULT_TABLE_KWARGS['border_style'] if title else author_style,
+            header_style="bold",
+            highlight=True,
         )
 
-        table.add_column('From', justify='left')
-        table.add_column('Timestamp', justify='center')
-        table.add_column('Subject', justify='left', style='honeydew2', min_width=70)
-
         for email in emails:
-            table.add_row(
+            fields = [
+                email.epstein_media_link(link_txt=email.timestamp_without_seconds(), style=link_style),
                 email.author_txt(),
-                email.epstein_media_link(link_txt=email.timestamp_without_seconds()),
-                highlighter(email.subject())
-            )
+                email.recipients_txt(max_full_names=1),
+                f"{email.length()}",
+                email.subject(),
+            ]
+
+            if not show_length:
+                del fields[3]
+
+            table.add_row(*fields)
 
         return table
 

epstein_files/documents/imessage/text_message.py

@@ -11,19 +11,16 @@ from epstein_files.util.highlighted_group import get_style_for_name
 from epstein_files.util.logging import logger
 from epstein_files.util.rich import TEXT_LINK, highlighter
 
+EPSTEIN_TEXTERS = ['e:', 'e:jeeitunes@gmail.com']
 MSG_DATE_FORMAT = r"%m/%d/%y %I:%M:%S %p"
 PHONE_NUMBER_REGEX = re.compile(r'^[\d+]+.*')
+UNCERTAIN_SUFFIX = ' (?)'
 
 DISPLAY_LAST_NAME_ONLY = [
     JEFFREY_EPSTEIN,
     STEVE_BANNON,
 ]
 
-TEXTER_MAPPING = {
-    'e:': JEFFREY_EPSTEIN,
-    'e:jeeitunes@gmail.com': JEFFREY_EPSTEIN,
-}
-
 
 @dataclass(kw_only=True)
 class TextMessage:
@@ -35,7 +32,7 @@ class TextMessage:
     timestamp_str: str
 
     def __post_init__(self):
-        self.author = TEXTER_MAPPING.get(self.author or UNKNOWN, self.author)
+        self.author = JEFFREY_EPSTEIN if self.author in EPSTEIN_TEXTERS else self.author
 
         if not self.author:
             self.author_str = UNKNOWN
@@ -45,7 +42,7 @@ class TextMessage:
             self.author_str = self.author_str or self.author
 
         if not self.is_id_confirmed and self.author is not None and self.author != JEFFREY_EPSTEIN:
-            self.author_str += ' (?)'
+            self.author_str += UNCERTAIN_SUFFIX
 
         if self.is_link():
             self.text = self.text.replace('\n', '').replace(' ', '_')
@@ -59,12 +56,11 @@ class TextMessage:
         return datetime.strptime(self.timestamp_str, MSG_DATE_FORMAT)
 
     def timestamp_txt(self) -> Text:
-        timestamp_str = self.timestamp_str
-
         try:
             timestamp_str = iso_timestamp(self.parse_timestamp())
         except Exception as e:
             logger.warning(f"Failed to parse timestamp for {self}")
+            timestamp_str = self.timestamp_str
 
         return Text(f"[{timestamp_str}]", style=TIMESTAMP_DIM)
 

epstein_files/documents/messenger_log.py

@@ -14,7 +14,7 @@ from epstein_files.util.constant.names import JEFFREY_EPSTEIN, UNKNOWN
 from epstein_files.util.constant.strings import AUTHOR, TIMESTAMP_STYLE
 from epstein_files.util.data import days_between, days_between_str, iso_timestamp, sort_dict
 from epstein_files.util.doc_cfg import Metadata, TextCfg
-from epstein_files.util.highlighted_group import get_style_for_name
+from epstein_files.util.highlighted_group import get_style_for_name, styled_name
 from epstein_files.util.logging import logger
 from epstein_files.util.rich import LAST_TIMESTAMP_STYLE, build_table, highlighter
 
@@ -160,7 +160,7 @@ class MessengerLog(Communication):
             last_at = logs[-1].first_message_at(name)
 
             counts_table.add_row(
-                Text(name or UNKNOWN, get_style_for_name(name)),
+                styled_name(name),
                 str(len(logs)),
                 f"{count:,}",
                 iso_timestamp(first_at),

epstein_files/epstein_files.py

@@ -30,7 +30,6 @@ from epstein_files.util.rich import (NA_TXT, add_cols_to_table, build_table, con
 from epstein_files.util.search_result import SearchResult
 from epstein_files.util.timer import Timer
 
-EXCLUDED_EMAILERS = USELESS_EMAILERS + [JEFFREY_EPSTEIN]
 DEVICE_SIGNATURE_SUBTITLE = f"Email [italic]Sent from \\[DEVICE][/italic] Signature Breakdown"
 DEVICE_SIGNATURE = 'Device Signature'
 DEVICE_SIGNATURE_PADDING = (1, 0)
@@ -116,9 +115,9 @@ class EpsteinFiles:
         return self.imessage_logs + self.emails + self.other_files
 
     def all_emailers(self, include_useless: bool = False) -> list[str | None]:
-        """Returns all emailers except Epstein and EXCLUDED_EMAILERS, sorted from least frequent to most."""
+        """Returns all emailers USELESS_EMAILERS, sorted from least frequent to most."""
         names = [a for a in self.email_author_counts.keys()] + [r for r in self.email_recipient_counts.keys()]
-        names = names if include_useless else [e for e in names if e not in EXCLUDED_EMAILERS]
+        names = names if include_useless else [e for e in names if e not in USELESS_EMAILERS]
         return sorted(list(set(names)), key=lambda e: self.email_author_counts[e] + self.email_recipient_counts[e])
 
     def docs_matching(
@@ -167,7 +166,10 @@ class EpsteinFiles:
 
     def emails_for(self, author: str | None) -> list[Email]:
         """Returns emails to or from a given 'author' sorted chronologically."""
-        emails = self.emails_by(author) + self.emails_to(author)
+        if author == JEFFREY_EPSTEIN:
+            emails = [e for e in self.emails_by(JEFFREY_EPSTEIN) if e.is_note_to_self()]
+        else:
+            emails = self.emails_by(author) + self.emails_to(author)
 
         if len(emails) == 0:
             raise RuntimeError(f"No emails found for '{author}'")
@@ -182,7 +184,7 @@ class EpsteinFiles:
 
         return Document.sort_by_timestamp(emails)
 
-    def get_documents_by_id(self, file_ids: str | list[str]) -> list[Document]:
+    def for_ids(self, file_ids: str | list[str]) -> list[Document]:
         file_ids = listify(file_ids)
         docs = [doc for doc in self.all_documents() if doc.file_id in file_ids]
 
@@ -218,8 +220,8 @@ class EpsteinFiles:
         return [doc for doc in self.other_files if not isinstance(doc, JsonFile)]
 
     def print_files_summary(self) -> None:
-        table = build_table('Summary of Document Types')
-        add_cols_to_table(table, ['File Type', 'Files', 'Author Known', 'Author Unknown', 'Duplicates'])
+        table = build_table('File Overview')
+        add_cols_to_table(table, ['File Type', 'Count', 'Author Known', 'Author Unknown', 'Duplicates'])
         table.columns[1].justify = 'right'
 
         def add_row(label: str, docs: list):
@@ -247,13 +249,14 @@ class EpsteinFiles:
         unique_emails = [email for email in emails if not email.is_duplicate()]
         start_date = emails[0].timestamp.date()
         author = _author or UNKNOWN
+        title = f"Found {len(unique_emails)} emails"
 
-        print_author_panel(
-            f"Found {len(unique_emails)} emails to/from {author} starting {start_date} covering {num_days:,} days",
-            get_style_for_name(author),
-            get_info_for_name(author)
-        )
+        if author == JEFFREY_EPSTEIN:
+            title += f" sent by {JEFFREY_EPSTEIN} to himself"
+        else:
+            title += f" to/from {author} starting {start_date} covering {num_days:,} days"
 
+        print_author_panel(title, get_info_for_name(author), get_style_for_name(author))
         self.print_emails_table_for(_author)
         last_printed_email_was_duplicate = False
 
@@ -272,11 +275,10 @@ class EpsteinFiles:
 
     def print_emails_table_for(self, author: str | None) -> None:
         emails = [email for email in self.emails_for(author) if not email.is_duplicate()]  # Remove dupes
-        print_centered(Email.build_emails_table(emails, author))
-        console.line()
+        print_centered(Padding(Email.build_emails_table(emails, author), (0, 5, 1, 5)))
 
     def print_email_device_info(self) -> None:
-        print_subtitle_panel(DEVICE_SIGNATURE_SUBTITLE, padding=(2, 0, 0, 0), centered=True)
+        print_subtitle_panel(DEVICE_SIGNATURE_SUBTITLE)
         console.print(_build_signature_table(self.email_device_signatures_to_authors, (DEVICE_SIGNATURE, AUTHOR), ', '))
         console.print(_build_signature_table(self.email_authors_to_device_signatures, (AUTHOR, DEVICE_SIGNATURE)))
 

epstein_files/util/constant/names.py

@@ -178,6 +178,7 @@ HENRY_HOLT = 'Henry Holt'  # Actually a company?
 IVANKA = 'Ivanka'
 JAMES_PATTERSON = 'James Patterson'
 JARED_KUSHNER = 'Jared Kushner'
+JEFFREY_WERNICK = 'Jeffrey Wernick'
 JULIE_K_BROWN = 'Julie K. Brown'
 KARIM_SADJADPOUR = 'KARIM SADJADPOUR'.title()
 MICHAEL_J_BOCCIO = 'Michael J. Boccio'
@@ -207,53 +208,53 @@ TRUMP_ORG = 'Trump Organization'
 UBS = 'UBS'
 
 # First and last names that should be made part of a highlighting regex for emailers
-NAMES_TO_NOT_HIGHLIGHT: list[str] = [name.lower() for name in [
-    'Al', 'Alan', 'Alfredo', 'Allen', 'Alex', 'Alexander', 'Amanda', 'Andres', 'Andrew',
-    'Bard', 'Barry', 'Bill', 'Black', 'Boris', 'Brad', 'Bruce',
-    'Carolyn', 'Chris', 'Christina',
-    'Dan', 'Daniel', 'Danny', 'Darren', 'Dave', 'David',
-    'Ed', 'Edward', 'Edwards', 'Epstein', 'Eric', 'Erika', 'Etienne',
-    'Faith', 'Fred', 'Friendly', 'Frost', 'Fuller',
-    'George',
-    'Heather', 'Henry', 'Hill', 'Hoffman',
-    'Ian',
-    'Jack', 'James', 'Jay', 'Jean', 'Jeff', 'Jeffrey', 'Jennifer', 'Jeremy', 'jessica', 'Joel', 'John', 'Jon', 'Jonathan', 'Joseph', 'Jr',
-    'Kahn', 'Katherine', 'Kelly', 'Ken', 'Kevin',
-    'Larry', 'Leon', 'Lesley', 'Linda', 'Link', 'Lisa',
-    'Mann', 'Marc', 'Marie', 'Mark', 'Martin', 'Melanie', 'Michael', 'Mike', 'Miller', 'Mitchell', 'Miles', 'Morris', 'Moskowitz',
-    'Nancy', 'Neal', 'New',
-    'Paul', 'Paula', 'Pen', 'Peter', 'Philip', 'Prince',
-    'Randall', 'Reid', 'Richard', 'Robert', 'Rodriguez', 'Roger', 'Rosenberg', 'Ross', 'Roth', 'Rubin',
-    'Scott', 'Sean', 'Stanley', 'Stern', 'Stephen', 'Steve', 'Steven', 'Stone', 'Susan',
-    'The', 'Thomas', 'Tim', 'Tom', 'Tyler',
-    'Victor',
-    'Wade',
-    "Y",
-]]
+NAMES_TO_NOT_HIGHLIGHT = """
+    al alan alfredo allen alex alexander amanda andres andrew
+    bard barrett barry bill black boris brad bruce
+    carolyn chris christina
+    dan daniel danny darren dave david donald
+    ed edward edwards enterprise enterprises entourage epstein eric erika etienne
+    faith fred friendly frost fuller
+    gerald george gold
+    harry hay heather henry hill hoffman
+    ian
+    jack james jay jean jeff jeffrey jennifer jeremy jessica joel john jon jonathan joseph jr
+    kahn karl kate katherine kelly ken kevin
+    larry laurie lawrence leon lesley linda link lisa
+    mann marc marie mark martin melanie michael mike miller mitchell miles morris moskowitz
+    nancy neal new nicole
+    owen
+    paul paula pen peter philip prince
+    randall reid richard robert rodriguez roger rosenberg ross roth roy rubin
+    scott sean skip stanley stern stephen steve steven stone susan
+    the thomas tim tom tony tyler
+    victor
+    wade waters
+    y
+""".strip().split()
 
 # Names to color white in the word counts
 OTHER_NAMES = NAMES_TO_NOT_HIGHLIGHT + """
     aaron albert alberto alec alexandra alice anderson andre ann anna anne ariana arthur
     baldwin barack barrett ben benjamin berger bert binant bob bonner boyden bradley brady branson bright bruno bryant burton
     chapman charles charlie christopher clint cohen colin collins conway
-    danny davis dean debra deborah dennis diana diane diaz dickinson dixon dominique don dylan
-    edmond elizabeth emily enterprises entwistle erik evelyn
-    ferguson flachsbart francis franco frank frost
-    gardner gary geoff geoffrey gerald gilbert gloria gold goldberg gonzalez gould graham greene guarino gwyneth
-    hancock harold harrison harry hay helen hill hirsch hofstadter horowitz hussein
-    ian isaac isaacson
-    james jamie jane janet jason jeffrey jen jim joe johnson jones josh julie justin
-    karl kate kathy kelly kim kruger kyle
-    laurie lawrence leo leonard lenny leslie lieberman louis lynch lynn
+    davis dean debra deborah dennis diana diane diaz dickinson dixon dominique don dylan
+    edmond elizabeth emily entwistle erik evelyn
+    ferguson flachsbart francis franco frank
+    gardner gary geoff geoffrey gilbert gloria goldberg gonzalez gould graham greene guarino gwyneth
+    hancock harold harrison helen hirsch hofstadter horowitz hussein
+    isaac isaacson
+    jamie jane janet jason jeffrey jen jim joe johnson jones josh julie justin
+    kathy kim kruger kyle
+    lawrence leo leonard lenny leslie lieberman louis lynch lynn
     marcus marianne matt matthew melissa michele michelle moore moscowitz
-    nancy nicole nussbaum
-    owen
-    paulson peter philippe
+    nancy nussbaum
+    paulson philippe
     rafael ray richard richardson rob robert robin ron rubin rudolph ryan
-    sara sarah sean seligman serge sergey silverman sloman smith snowden sorkin steele stevie stewart
-    ted theresa thompson tiffany timothy tony
+    sara sarah seligman serge sergey silverman sloman smith snowden sorkin steele stevie stewart
+    ted theresa thompson tiffany timothy
     valeria
-    walter warren waters weinstein weiss william
+    walter warren weinstein weiss william
     zach zack
 """.strip().split()
 

epstein_files/util/constant/strings.py

@@ -50,6 +50,7 @@ TEXT_MESSAGE = 'text message'
 SiteType = Literal['email', 'text message']
 
 # Styles
+DEFAULT_NAME_STYLE = 'gray46'
 TIMESTAMP_STYLE = 'turquoise4'
 TIMESTAMP_DIM = f"turquoise4 dim"