epstein-files 1.1.5__py3-none-any.whl → 1.2.0__py3-none-any.whl

epstein_files/person.py

@@ -0,0 +1,350 @@
+from dataclasses import dataclass, field
+from datetime import datetime, date
+
+from rich.console import Group, RenderableType
+from rich.padding import Padding
+from rich.panel import Panel
+from rich.table import Table
+from rich.text import Text
+
+from epstein_files.documents.document import Document
+from epstein_files.documents.email import MAILING_LISTS, JUNK_EMAILERS, Email
+from epstein_files.documents.messenger_log import MessengerLog
+from epstein_files.documents.other_file import OtherFile
+from epstein_files.util.constant.strings import *
+from epstein_files.util.constant.urls import *
+from epstein_files.util.constants import *
+from epstein_files.util.data import days_between, flatten, without_falsey
+from epstein_files.util.env import args
+from epstein_files.util.highlighted_group import (QUESTION_MARKS_TXT, HighlightedNames,
+     get_highlight_group_for_name, get_style_for_name, styled_category, styled_name)
+from epstein_files.util.rich import GREY_NUMBERS, LAST_TIMESTAMP_STYLE, TABLE_TITLE_STYLE, build_table, console, join_texts, print_centered
+
+ALT_INFO_STYLE = 'medium_purple4'
+CC = 'cc:'
+MIN_AUTHOR_PANEL_WIDTH = 80
+EMAILER_INFO_TITLE = 'Email Conversations Will Appear'
+UNINTERESTING_CC_INFO = "CC: or BCC: recipient only"
+
+INVALID_FOR_EPSTEIN_WEB = JUNK_EMAILERS + MAILING_LISTS + [
+    'ACT for America',
+    'BS Stern',
+    UNKNOWN,
+]
+
+
+@dataclass(kw_only=True)
+class Person:
+    """Collection of data about someone texting or emailing Epstein."""
+    name: Name
+    emails: list[Email] = field(default_factory=list)
+    imessage_logs: list[MessengerLog] = field(default_factory=list)
+    other_files: list[OtherFile] = field(default_factory=list)
+    is_uninteresting_cc: bool = False
+
+    def __post_init__(self):
+        self.emails = Document.sort_by_timestamp(self.emails)
+        self.imessage_logs = Document.sort_by_timestamp(self.imessage_logs)
+
+    def category(self) -> str | None:
+        highlight_group = self.highlight_group()
+
+        if highlight_group and isinstance(highlight_group, HighlightedNames):
+            category = highlight_group.category or highlight_group.label
+
+            if category != self.name and category != 'paula':  # TODO: this sucks
+                return category
+
+    def category_txt(self) -> Text | None:
+        if self.name is None:
+            return None
+        elif self.category():
+            return styled_category(self.category())
+        elif self.is_a_mystery() or self.is_uninteresting_cc:
+            return QUESTION_MARKS_TXT
+
+    def email_conversation_length_in_days(self) -> int:
+        return days_between(self.emails[0].timestamp, self.emails[-1].timestamp)
+
+    def earliest_email_at(self) -> datetime:
+        return self.emails[0].timestamp
+
+    def earliest_email_date(self) -> date:
+        return self.earliest_email_at().date()
+
+    def last_email_at(self) -> datetime:
+        return self.emails[-1].timestamp
+
+    def last_email_date(self) -> date:
+        return self.last_email_at().date()
+
+    def emails_by(self) -> list[Email]:
+        return [e for e in self.emails if self.name == e.author]
+
+    def emails_to(self) -> list[Email]:
+        return [
+            e for e in self.emails
+            if self.name in e.recipients or (self.name is None and len(e.recipients) == 0)
+        ]
+
+    def external_link(self, site: ExternalSite = EPSTEINIFY) -> str:
+        return PERSON_LINK_BUILDERS[site](self.name_str())
+
+    def external_link_txt(self, site: ExternalSite = EPSTEINIFY, link_str: str | None = None) -> Text:
+        if self.name is None:
+            return Text('')
+
+        return link_text_obj(self.external_link(site), link_str or site, style=self.style())
+
+    def external_links_line(self) -> Text:
+        links = [self.external_link_txt(site) for site in PERSON_LINK_BUILDERS]
+        return Text('', justify='center', style='dim').append(join_texts(links, join=' / '))  #, encloser='()'))#, encloser='‹›'))
+
+    def highlight_group(self) -> HighlightedNames | None:
+        return get_highlight_group_for_name(self.name)
+
+    def info_panel(self) -> Padding:
+        """Print a panel with the name of an emailer and a few tidbits of information about them."""
+        style = 'white' if (not self.style() or self.style() == DEFAULT) else self.style()
+        panel_style = f"black on {style} bold"
+
+        if self.name == JEFFREY_EPSTEIN:
+            email_count = len(self._printable_emails())
+            title_suffix = f"sent by {JEFFREY_EPSTEIN} to himself"
+        else:
+            email_count = len(self.unique_emails())
+            num_days = self.email_conversation_length_in_days()
+            title_suffix = f"to/from {self.name_str()} starting {self.earliest_email_date()} covering {num_days:,} days"
+
+        title = f"Found {email_count} emails {title_suffix}"
+        width = max(MIN_AUTHOR_PANEL_WIDTH, len(title) + 4, len(self.info_with_category()) + 8)
+        panel = Panel(Text(title, justify='center'), width=width, style=panel_style)
+        elements: list[RenderableType] = [panel]
+
+        if self.info_with_category():
+            elements.append(Text(f"({self.info_with_category()})", justify='center', style=f"{style} italic"))
+
+        return Padding(Group(*elements), (2, 0, 1, 0))
+
+    def info_str(self) -> str | None:
+        highlight_group = self.highlight_group()
+
+        if highlight_group and isinstance(highlight_group, HighlightedNames) and self.name:
+            return highlight_group.info_for(self.name)
+        elif self.is_uninteresting_cc:
+            return UNINTERESTING_CC_INFO
+
+    def info_with_category(self) -> str:
+        return ', '.join(without_falsey([self.category(), self.info_str()]))
+
+    def info_txt(self) -> Text | None:
+        if self.name == JEFFREY_EPSTEIN:
+            return Text('(emails sent by Epstein to himself are here)', style=ALT_INFO_STYLE)
+        elif self.name is None:
+            return Text('(emails whose author or recipient could not be determined)', style=ALT_INFO_STYLE)
+        elif self.category() == JUNK:
+            return Text(f"({JUNK} mail)", style='tan dim')
+        elif self.is_a_mystery():
+            return Text(QUESTION_MARKS, style='magenta dim')
+        elif self.is_uninteresting_cc and self.info_str() == UNINTERESTING_CC_INFO:
+            return Text(f"({self.info_str()})", style='wheat4 dim')
+        elif self.info_str() is None:
+            if self.name in MAILING_LISTS:
+                return Text('(mailing list)', style=f"{self.style()} dim")
+            else:
+                return None
+        else:
+            return Text(self.info_str())
+
+    def is_a_mystery(self) -> bool:
+        """Return True if this is someone we theroetically could know more about."""
+        return self.is_unstyled() and not (self.is_email_address() or self.info_str() or self.is_uninteresting_cc)
+
+    def is_email_address(self) -> bool:
+        return '@' in (self.name or '')
+
+    def is_linkable(self) -> bool:
+        """Return True if it's likely that EpsteinWeb has a page for this name."""
+        if self.name is None or ' ' not in self.name:
+            return False
+        elif self.is_email_address() or '/' in self.name or QUESTION_MARKS in self.name:
+            return False
+        elif self.name in INVALID_FOR_EPSTEIN_WEB:
+            return False
+
+        return True
+
+    def is_unstyled(self) -> bool:
+        """True if there's no highlight group for this name."""
+        return self.style() == DEFAULT_NAME_STYLE
+
+    def name_str(self) -> str:
+        return self.name or UNKNOWN
+
+    def name_link(self) -> Text:
+        """Will only link if it's worth linking, otherwise just a Text object."""
+        if not self.is_linkable():
+            return self.name_txt()
+        else:
+            return Text.from_markup(link_markup(self.external_link(), self.name_str(), self.style()))
+
+    def name_txt(self) -> Text:
+        return styled_name(self.name)
+
+    def print_emails(self) -> list[Email]:
+        """Print complete emails to or from a particular 'author'. Returns the Emails that were printed."""
+        print_centered(self.info_panel())
+        self.print_emails_table()
+        last_printed_email_was_duplicate = False
+
+        if self.category() == JUNK:
+            logger.warning(f"Not printing junk emailer '{self.name}'")
+        else:
+            for email in self._printable_emails():
+                if email.is_duplicate():
+                    console.print(Padding(email.duplicate_file_txt().append('...'), (0, 0, 0, 4)))
+                    last_printed_email_was_duplicate = True
+                else:
+                    if last_printed_email_was_duplicate:
+                        console.line()
+
+                    console.print(email)
+                    last_printed_email_was_duplicate = False
+
+        return self._printable_emails()
+
+    def print_emails_table(self) -> None:
+        emails = [email for email in self._printable_emails() if not email.is_duplicate()]  # Remove dupes
+        print_centered(Padding(Email.build_emails_table(emails, self.name), (0, 5, 0, 5)))
+
+        if self.is_linkable():
+            print_centered(self.external_links_line())
+
+        console.line()
+
+    def sort_key(self) -> list[int | str]:
+        counts = [len(self.unique_emails())]
+        counts = [-1 * count for count in counts]
+
+        if args.sort_alphabetical:
+            return [self.name_str()] + counts
+        else:
+            return counts + [self.name_str()]
+
+    def style(self) -> str:
+        return get_style_for_name(self.name)
+
+    def unique_emails(self) -> list[Email]:
+        return [email for email in self.emails if not email.is_duplicate()]
+
+    def unique_emails_by(self) -> list[Email]:
+        return [email for email in self.emails_by() if not email.is_duplicate()]
+
+    def unique_emails_to(self) -> list[Email]:
+        return [email for email in self.emails_to() if not email.is_duplicate()]
+
+    def _printable_emails(self):
+        """For Epstein we only want to print emails he sent to himself."""
+        if self.name == JEFFREY_EPSTEIN:
+            return [e for e in self.emails if e.is_note_to_self()]
+        else:
+            return self.emails
+
+    def __str__(self):
+        return f"{self.name_str()}"
+
+    @staticmethod
+    def emailer_info_table(people: list['Person'], highlighted: list['Person'] | None = None) -> Table:
+        """Table of info about emailers."""
+        highlighted = highlighted or people
+        highlighted_names = [p.name for p in highlighted]
+        is_selection = len(people) != len(highlighted) or args.emailers_info_png
+
+        if is_selection:
+            title = Text(f"{EMAILER_INFO_TITLE} in This Order for the Highlighted Names (see ", style=TABLE_TITLE_STYLE)
+            title.append(THE_OTHER_PAGE_TXT).append(" for the rest)")
+        else:
+            title = f"{EMAILER_INFO_TITLE} in Chronological Order Based on Timestamp of First Email"
+
+        table = build_table(title)
+        table.add_column('Start')
+        table.add_column('Name', max_width=24, no_wrap=True)
+        table.add_column('Category', justify='left', style='dim italic')
+        table.add_column('Num', justify='right', style='white')
+        table.add_column('Sent', justify='right', style='wheat4')
+        table.add_column('Recv', justify='right', style='wheat4')
+        table.add_column('Days', justify='right', style=TIMESTAMP_DIM)
+        table.add_column('Info', style='white italic')
+        current_year = 1990
+        current_year_month = current_year * 12
+        grey_idx = 0
+
+        for person in people:
+            earliest_email_date = person.earliest_email_date()
+            year_months = (earliest_email_date.year * 12) + earliest_email_date.month
+
+            # Color year rollovers more brightly
+            if current_year != earliest_email_date.year:
+                grey_idx = 0
+            elif current_year_month != year_months:
+                grey_idx = ((current_year_month - 1) % 12) + 1
+
+            current_year_month = year_months
+            current_year = earliest_email_date.year
+
+            table.add_row(
+                Text(str(earliest_email_date), style=f"grey{GREY_NUMBERS[0 if is_selection else grey_idx]}"),
+                person.name_txt(),  # TODO: make link?
+                person.category_txt(),
+                f"{len(person._printable_emails())}",
+                f"{len(person.unique_emails_by())}",
+                f"{len(person.unique_emails_to())}",
+                f"{person.email_conversation_length_in_days()}",
+                person.info_txt() or '',
+                style='' if person.name in highlighted_names else 'dim',
+            )
+
+        return table
+
+    @staticmethod
+    def emailer_stats_table(people: list['Person']) -> Table:
+        email_authors = [p for p in people if p.emails_by() and p.name]
+        all_emails = Document.uniquify(flatten([p.unique_emails() for p in people]))
+        attributed_emails = [email for email in all_emails if email.author]
+        footer = f"(identified {len(email_authors)} authors of {len(attributed_emails):,}"
+        footer = f"{footer} out of {len(attributed_emails):,} emails)"
+
+        counts_table = build_table(
+            f"All {len(email_authors)} People Who Sent or Received an Email in the Files",
+            caption=footer,
+            cols=[
+                'Name',
+                {'name': 'Count', 'justify': 'right', 'style': 'bold bright_white'},
+                {'name': 'Sent', 'justify': 'right', 'style': 'gray74'},
+                {'name': 'Recv', 'justify': 'right', 'style': 'gray74'},
+                {'name': 'First', 'style': TIMESTAMP_STYLE},
+                {'name': 'Last', 'style': LAST_TIMESTAMP_STYLE},
+                {'name': 'Days', 'justify': 'right', 'style': 'dim'},
+                JMAIL,
+                EPSTEIN_MEDIA,
+                EPSTEIN_WEB,
+                'Twitter',
+            ]
+        )
+
+        for person in sorted(people, key=lambda person: person.sort_key()):
+            counts_table.add_row(
+                person.name_link(),
+                f"{len(person.unique_emails()):,}",
+                f"{len(person.unique_emails_by()):,}",
+                f"{len(person.unique_emails_to()):,}",
+                str(person.earliest_email_date()),
+                str(person.last_email_date()),
+                f"{person.email_conversation_length_in_days()}",
+                person.external_link_txt(JMAIL),
+                person.external_link_txt(EPSTEIN_MEDIA) if person.is_linkable() else '',
+                person.external_link_txt(EPSTEIN_WEB) if person.is_linkable() else '',
+                person.external_link_txt(TWITTER),
+            )
+
+        return counts_table

epstein_files/util/constant/names.py

@@ -1,6 +1,6 @@
 from epstein_files.util.constant.strings import QUESTION_MARKS, remove_question_marks
 
-UNKNOWN = '(unknown)'
+Name = str | None
 
 # Texting Names
 ANDRZEJ_DUDA = 'Andrzej Duda or entourage'
@@ -34,6 +34,7 @@ BARBRO_C_EHNBOM = 'Barbro C. Ehnbom'
 BARRY_J_COHEN = 'Barry J. Cohen'
 BENNET_MOSKOWITZ = 'Bennet Moskowitz'
 BILL_SIEGEL = 'Bill Siegel'
+BOB_CROWE = 'Bob Crowe'
 BRAD_EDWARDS = 'Brad Edwards'
 BRAD_KARP = 'Brad Karp'
 BRAD_WECHSLER = 'Brad Wechsler'
@@ -78,6 +79,7 @@ JACK_GOLDBERGER = 'Jack Goldberger'
 JACK_SCAROLA = 'Jack Scarola'
 JACKIE_PERCZEK = 'Jackie Perczek'
 JAMES_HILL = 'James Hill'
+JANUSZ_BANASIAK = 'Janusz Banasiak'
 JAY_LEFKOWITZ = 'Jay Lefkowitz'
 JEAN_HUGUEN = 'Jean Huguen'
 JEAN_LUC_BRUNEL = 'Jean Luc Brunel'
@@ -114,6 +116,7 @@ MARK_TRAMO = 'Mark Tramo'
 MARTIN_NOWAK = 'Martin Nowak'
 MARTIN_WEINBERG = "Martin Weinberg"
 MASHA_DROKOVA = 'Masha Drokova'
+MATTHEW_HILTZIK = 'Matthew Hiltzik'
 MELANIE_SPINELLA = 'Melanie Spinella'
 MERWIN_DELA_CRUZ = 'Merwin Dela Cruz'
 MICHAEL_BUCHHOLTZ = 'Michael Buchholtz'
@@ -170,6 +173,8 @@ VINCENZO_IOZZO = 'Vincenzo Iozzo'
 VINIT_SAHNI = 'Vinit Sahni'
 ZUBAIR_KHAN = 'Zubair Khan'
 
+UNKNOWN = '(unknown)'
+
 # No communications but name is in the files
 BILL_GATES = 'Bill Gates'
 DONALD_TRUMP = 'Donald Trump'
@@ -202,30 +207,30 @@ INSIGHTS_POD = f"InsightsPod"  # Zubair bots
 MIT_MEDIA_LAB = 'MIT Media Lab'
 NEXT_MANAGEMENT = 'Next Management LLC'
 JP_MORGAN = 'JP Morgan'
-OSBORNE_LLP = f"{IAN_OSBORNE} & Partners LLP"  # Ian Osborne's PR firm
-ROTHSTEIN_ROSENFELDT_ADLER = 'Rothstein Rosenfeldt Adler (Rothstein was a crook & partner of Roger Stone)'
+OSBORNE_LLP = f"{IAN_OSBORNE} & Partners"  # Ian Osborne's PR firm
+ROTHSTEIN_ROSENFELDT_ADLER = "Rothstein Rosenfeldt Adler (Rothstein was Roger Stone's partner)"  # and a crook
 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 = """
-    al alan alfredo allen alex alexander amanda andres andrew
-    bard barrett barry bill black boris brad bruce
+    al alain alan alfredo allen alex alexander amanda andres andrew
+    bard barrett barry bill black bob 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
+    faith forget fred friendly frost fuller
+    gerald george gold gordon
+    haddad harry hay heather henry hill hoffman
+    ian ivan
     jack james jay jean jeff jeffrey jennifer jeremy jessica joel john jon jonathan joseph jr
-    kahn karl kate katherine kelly ken kevin
+    kahn karl kate katherine kelly ken kevin krassner
     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
+    randall rangel 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
@@ -272,3 +277,22 @@ def constantize_name(name: str) -> str:
         return f"'{name}'"
     else:
         return variable_name
+
+
+def extract_first_name(name: str) -> str:
+    if ' ' not in name:
+        return name
+
+    return name.removesuffix(f" {extract_last_name(name)}")
+
+
+def extract_last_name(name: str) -> str:
+    if ' ' not in name:
+        return name
+
+    first_last_names = remove_question_marks(name).strip().split()
+
+    if first_last_names[-1].startswith('Jr') and len(first_last_names[-1]) <= 3:
+        return ' '.join(first_last_names[-2:])
+    else:
+        return first_last_names[-1]

epstein_files/util/constant/output_files.py

@@ -13,6 +13,7 @@ TEXT_MSGS_HTML_PATH = HTML_DIR.joinpath('index.html')
 WORD_COUNT_HTML_PATH = HTML_DIR.joinpath(f'communication_word_count_{EPSTEIN_FILES_NOV_2025}.html')
 # EPSTEIN_WORD_COUNT_HTML_PATH = HTML_DIR.joinpath('epstein_texts_and_emails_word_count.html')
 URLS_ENV = '.urls.env'
+EMAILERS_TABLE_PNG_PATH = HTML_DIR.joinpath('emailers_info_table.png')
 
 # Deployment URLS
 # NOTE: don't rename these variables without changing deploy.sh!

epstein_files/util/constant/strings.py

@@ -11,6 +11,7 @@ BUSINESS = 'business'
 CONFERENCE = 'conference'
 ENTERTAINER = 'entertainer'
 FINANCE = 'finance'
+FRIEND = 'friend'
 FLIGHT_LOG = 'flight log'
 JOURNALIST = 'journalist'
 JUNK = 'junk'
@@ -50,7 +51,7 @@ TEXT_MESSAGE = 'text message'
 SiteType = Literal['email', 'text message']
 
 # Styles
-DEFAULT_NAME_STYLE = 'gray46'
+DEFAULT_NAME_STYLE = 'grey23'
 TIMESTAMP_STYLE = 'turquoise4'
 TIMESTAMP_DIM = f"turquoise4 dim"
 
@@ -76,7 +77,7 @@ MESSENGER_LOG_CLASS = 'MessengerLog'
 OTHER_FILE_CLASS = 'OtherFile'
 
 
-remove_question_marks = lambda name: QUESTION_MARKS_REGEX.sub('', name)
+remove_question_marks = lambda name: QUESTION_MARKS_REGEX.sub('', name).strip()
 
 
 def indented(s: str, spaces: int = 4) -> str:

epstein_files/util/constant/urls.py

@@ -1,6 +1,6 @@
 import re
 import urllib.parse
-from typing import Literal
+from typing import Callable, Literal
 
 from inflection import parameterize
 from rich.text import Text
@@ -14,12 +14,13 @@ ARCHIVE_LINK_COLOR = 'slate_blue3'
 TEXT_LINK = 'text_link'
 
 # External site names
-ExternalSite = Literal['epstein.media', 'epsteinify', 'EpsteinWeb', 'RollCall']
+ExternalSite = Literal['epstein.media', 'epsteinify', 'EpsteinWeb', 'Jmail', 'RollCall', 'search X']
 EPSTEIN_MEDIA = 'epstein.media'
 EPSTEIN_WEB = 'EpsteinWeb'
 EPSTEINIFY = 'epsteinify'
 JMAIL = 'Jmail'
 ROLLCALL = 'RollCall'
+TWITTER = 'search X'
 
 GH_PROJECT_URL = 'https://github.com/michelcrypt4d4mus/epstein_text_messages'
 GH_MASTER_URL = f"{GH_PROJECT_URL}/blob/master"
@@ -71,6 +72,15 @@ search_jmail_url = lambda txt: f"{JMAIL_URL}/search?q={urllib.parse.quote(txt)}"
 search_twitter_url = lambda txt: f"https://x.com/search?q={urllib.parse.quote(txt)}&src=typed_query&f=live"
 
 
+PERSON_LINK_BUILDERS: dict[ExternalSite, Callable[[str], str]] = {
+    EPSTEIN_MEDIA: epstein_media_person_url,
+    EPSTEIN_WEB: epstein_web_person_url,
+    EPSTEINIFY: epsteinify_name_url,
+    JMAIL: search_jmail_url,
+    TWITTER: search_twitter_url,
+}
+
+
 def build_doc_url(base_url: str, filename_or_id: int | str, case: Literal['lower', 'title'] | None = None) -> str:
     file_stem = coerce_file_stem(filename_or_id)
     file_stem = file_stem.lower() if case == 'lower' or EPSTEIN_MEDIA in base_url else file_stem
@@ -111,3 +121,5 @@ def other_site_url() -> str:
 
 
 CRYPTADAMUS_TWITTER = link_markup('https://x.com/cryptadamist', '@cryptadamist')
+THE_OTHER_PAGE_MARKUP = link_markup(other_site_url(), 'the other page', style='light_slate_grey bold')
+THE_OTHER_PAGE_TXT = Text.from_markup(THE_OTHER_PAGE_MARKUP)