epstein-files 1.4.1__py3-none-any.whl → 1.5.0__py3-none-any.whl

epstein_files/documents/emails/emailers.py

@@ -0,0 +1,223 @@
+"""
+Regexes and patterns for identifying people in email headers.
+"""
+import re
+from copy import deepcopy
+
+from epstein_files.util.constant.names import *
+from epstein_files.util.constant.strings import REDACTED
+from epstein_files.util.data import escape_single_quotes
+from epstein_files.util.logging import logger
+
+BAD_EMAILER_REGEX = re.compile(r'^(>|11111111)|agreed|ok|sexy|re:|fwd:|Multiple Senders|((sent|attachments|subject|importance).*|.*(january|201\d|hysterical|i have|image0|so that people|article 1.?|momminnemummin|These conspiracy theories|your state|undisclosed|www\.theguardian|talk in|it was a|what do|cc:|call (back|me)|afiaata|[IM]{4,}).*)$', re.IGNORECASE)
+BAD_NAME_CHARS_REGEX = re.compile(r"[\"'\[\]*><•=()]")
+TIME_REGEX = re.compile(r'^((\d{1,2}/\d{1,2}/\d{2,4}|Thursday|Monday|Tuesday|Wednesday|Friday|Saturday|Sunday)|\d{4} ).*')
+
+EMAILER_ID_PATTERNS: dict[str, str] = {
+    ALAN_DERSHOWITZ: r'(alan.{1,7})?dershowi(lz?|t?z)|AlanDersh',
+    ALIREZA_ITTIHADIEH: r'Alireza.[Il]ttihadieh',
+    ALISON_J_NATHAN: r"Alison(\s*J\.?)?\s*Nathan|Nathan NYSD Chambers?",
+    AMANDA_ENS: r'ens, amanda?|Amanda.Ens',
+    AMIR_TAAKI: r'Amir\s*Taaki|genjix',
+    ANAS_ALRASHEED: r'anas\s*al\s*rashee[cd]',
+    ANIL_AMBANI: r'Anil.Ambani',
+    ANN_MARIE_VILLAFANA: r'Villafana, Ann Marie|(A(\.|nn) Marie )?Villafa(c|n|ri)a',
+    ANTHONY_SCARAMUCCI: r"mooch|(Anthony ('The Mooch' )?)?Scaramucci",
+    ARIANE_DE_ROTHSCHILD: r'AdeR|((Ariane|Edmond) (de )?)?Rothsh?ch?ild|Ariane(?!\s+Dwyer)',
+    BARBRO_C_EHNBOM: r'behnbom@aol.com|(Barbro\s.*)?Ehnbom',
+    BARRY_J_COHEN: r'barry\s*((j.?|james)\s*)?cohen?',
+    BENNET_MOSKOWITZ: r'Moskowitz.*Bennet|Bennet.*Moskowitz',
+    BOB_CROWE: r"[BR]ob Crowe",
+    BORIS_NIKOLIC: r'(boris )?nikolic?',
+    BRAD_EDWARDS: r'Brad(ley)?(\s*J(.?|ames))?\s*Edwards',
+    BRAD_KARP: r'Brad (S.? )?Karp|Karp, Brad',
+    CHRISTIAN_EVERDELL: r"C(hristian\s*)?Everdell?",
+    CHRISTOPHER_DILORIO: r"Chris\s*Di[lI]o[nr](io)?",
+    DANGENE_AND_JENNIE_ENTERPRISE: r'Dangene and Jennie Enterprise?',
+    DANNY_FROST: r'Frost, Danny|frostd@dany.nyc.gov|Danny\s*Frost',
+    DARREN_INDYKE: r'darren$|Darren\s*(K\.?\s*)?[il]n[dq]_?yke?|dkiesq',
+    DAVID_FISZEL: r'David\s*Fis?zel',
+    DAVID_HAIG: fr'{DAVID_HAIG}|Haig, David',
+    DAVID_STERN: r'David Stern?',
+    DOUGLAS_WIGDOR: r'Doug(las)?\s*(H\.?)?\s*Wigdor',
+    EDUARDO_ROBLES: r'Ed(uardo)?\s*Robles',
+    EDWARD_JAY_EPSTEIN: r'(?<!Jeffrey )Edward (Jay )?Epstein',
+    EHUD_BARAK: r'(ehud|e?h)\s*barak|\behud',
+    FAITH_KATES: r'faith kates?',
+    GERALD_BARTON: r'Gerald.*Barton',
+    GERALD_LEFCOURT: r'Gerald\s*(B\.?\s*)?Lefcourt',
+    GHISLAINE_MAXWELL: r'g ?max(well)?|Ghislaine|Maxwell',
+    HEATHER_MANN: r'Heather Mann?',
+    INTELLIGENCE_SQUARED: r'intelligence\s*squared',
+    JACKIE_PERCZEK: r'jackie percze[kl]?',
+    JABOR_Y: r'[ji]abor\s*y?',
+    JAMES_HILL: r"hill, james e.|james.e.hill@abc.com",
+    JANUSZ_BANASIAK: r"Janu[is]z Banasiak",
+    JEAN_HUGUEN: r"Jean[\s.]Huguen",
+    JEAN_LUC_BRUNEL: r'Jean[- ]Luc Brunel?|JeanLuc',
+    JEFF_FULLER: r"jeff@mc2mm.com|Jeff Fuller",
+    JEFFREY_EPSTEIN: r'[djl]\s?ee[vy]acation[©@]?g?(mail.com)?|Epstine|\bJEE?\b|Jeff(rey)? (Edward )?E((sp|ps)tein?)?( VI Foundation)?|jeeproject@yahoo.com|J Jep|Jeffery Edwards|(?<!(Mark L.|ard Jay) )Epstein',
+    JESSICA_CADWELL: r'Jessica Cadwell?',
+    JOHNNY_EL_HACHEM: r'el hachem johnny|johnny el hachem',
+    JOI_ITO: r'ji@media.mit.?edu|(joichi|joi)( Ito)?',
+    JONATHAN_FARKAS: r'Jonathan Fark(a|u)(s|il)',
+    KARYNA_SHULIAK: r"Karyna\s*Shuliak?",
+    KATHRYN_RUEMMLER: r'Kathr?yn? Ruemmler?',
+    KEN_STARR: r'starr, ken|Ken(neth\s*(W.\s*)?)?\s+starr?|starr',
+    LANDON_THOMAS: r'lando[nr] thomas( jr)?|thomas jr.?, lando[nr]',
+    LARRY_SUMMERS: r'(La(wrence|rry).{1,5})?Summers?|^LH$|LHS|[Il]hsofficel?',
+    LAWRANCE_VISOSKI: r'La(rry|wrance) Visoski?|Lvjet',
+    LAWRENCE_KRAUSS: r'Lawrence Kraus[es]?|[jl]awkrauss|kruase',
+    LEON_BLACK: r'Leon\s*Black?|(?<!Marc )Leon(?! (Botstein|Jaworski|Wieseltier))',
+    LILLY_SANCHEZ: r'Lilly.*Sanchez',
+    LISA_NEW: r'E?Lisa New?\b',
+    MANUELA_MARTINEZ: fr'Manuela (- Mega Partners|Martinez)',
+    MARIANA_IDZKOWSKA: r'Mariana [Il]d[źi]kowska?',
+    MARK_EPSTEIN: r'Mark (L\. )?(Epstein|Lloyd)',
+    MARC_LEON: r'Marc[.\s]+(Kensington|Leon)|Kensington2',
+    MARTIN_NOWAK: r'(Martin.*?)?No[vw]ak|Nowak, Martin',
+    MARTIN_WEINBERG: r'martin.*?weinberg',
+    "Matthew Schafer": r"matthew\.?schafer?",
+    MELANIE_SPINELLA: r'M?elanie Spine[Il]{2}a',
+    MICHAEL_BUCHHOLTZ: r'Michael.*Buchholtz',
+    MICHAEL_MILLER: r'Micha(el)? Miller|Miller, Micha(el)?',
+    MICHAEL_SITRICK: r'(Mi(chael|ke).{0,5})?[CS]itrick',
+    MICHAEL_WOLFF: r'Michael\s*Wol(f[ef]e?|i)|Wolff',
+    MIROSLAV_LAJCAK: r"Miro(slav)?(\s+Laj[cč][aá]k)?",
+    MOHAMED_WAHEED_HASSAN: r'Mohamed Waheed(\s+Hassan)?',
+    NADIA_MARCINKO: r"Na[dď]i?a\s+Marcinko(v[aá])?",
+    NEAL_KASSELL: r'Neal\s*Kassell?',
+    NICHOLAS_RIBIS: r'Nic(holas|k)[\s._]Ribi?s?|Ribbis',
+    OLIVIER_COLOM: fr'Colom, Olivier|{OLIVIER_COLOM}',
+    PAUL_BARRETT: r'Paul Barre(d|tt)',
+    PAUL_KRASSNER: r'Pa\s?ul Krassner',
+    PAUL_MORRIS: r'morris, paul|Paul Morris',
+    PAULA: r'^Paula( Heil Fisher)?$',
+    PEGGY_SIEGAL: r'Peggy Siegal?',
+    PETER_ATTIA: r'Peter Attia?',
+    PETER_MANDELSON: r"((Lord|Peter) )?Mandelson",
+    'pink@mc2mm.com': r"^Pink$|pink@mc2mm\.com",
+    PRINCE_ANDREW: r'Prince Andrew|The Duke',
+    REID_WEINGARTEN: r'Weingarten, Rei[cdi]|Rei[cdi] Weingarten',
+    RICHARD_KAHN: r'rich(ard)? kahn?',
+    ROBERT_D_CRITTON_JR: r'Robert D.? Critton,? Jr.?',
+    ROBERT_LAWRENCE_KUHN: r'Robert\s*(Lawrence)?\s*Kuhn',
+    ROBERT_TRIVERS: r'tri[vy]ersr@gmail|Robert\s*Trivers?',
+    ROSS_GOW: fr"Ross(acuity)? Gow|(ross@)?acuity\s*reputation(\.com)?",
+    SAMUEL_LEFF: r"Sam(uel)?(/Walli)? Leff",
+    SCOTT_J_LINK: r'scott j. link?',
+    SEAN_BANNON: r'sean bannon?',
+    SHAHER_ABDULHAK_BESHER: r'\bShaher( Abdulhak Besher)?\b',
+    SOON_YI_PREVIN: r'Soon[- ]Yi Previn?',
+    STACEY_RICHMAN: r"srichmanlaw|Stacey\s*Richman",
+    STEPHEN_HANSON: r'ste(phen|ve) hanson?|Shanson900',
+    STEVE_BANNON: r'steve banno[nr]?',
+    STEVEN_SINOFSKY: r'Steven Sinofsky?',
+    SULTAN_BIN_SULAYEM: r'Sultan (Ahmed )?bin Sulaye?m?',
+    TERJE_ROD_LARSEN: r"Terje(( (R[øo]e?d[- ])?)?Lars[eo]n)?",
+    TERRY_KAFKA: r'Terry Kafka?',
+    THANU_BOONYAWATANA: r"Thanu (BOONYAWATANA|Cnx)",
+    THORBJORN_JAGLAND: r'(Thor.{3,8})?Jag[il]and?',
+    TONJA_HADDAD_COLEMAN: r"To(nj|rl)a Haddad Coleman|haddadfm@aol.com",
+    VINCENZO_IOZZO: r"Vincenzo [IL]ozzo",
+}
+
+# If found as substring consider them the author
+EMAILERS = [
+    'Anne Boyles',
+    AL_SECKEL,
+    'Ariane Dwyer',
+    AZIZA_ALAHMADI,
+    BILL_GATES,
+    BILL_SIEGEL,
+    'Bobbi C Sternheim',
+    BRAD_WECHSLER,
+    BROCK_PIERCE,
+    CHRISTINA_GALBRAITH,
+    DANIEL_SABBA,
+    'Danny Goldberg',
+    DAVID_SCHOEN,
+    DEBBIE_FEIN,
+    DEEPAK_CHOPRA,
+    GLENN_DUBIN,
+    GORDON_GETTY,
+    'Jeff Pagliuca',
+    'Kevin Bright',
+    'Jack Lang',
+    JACK_SCAROLA,
+    JAY_LEFKOWITZ,
+    JES_STALEY,
+    JOHN_PAGE,
+    'Jokeland',
+    JOSCHA_BACH,
+    'Kathleen Ruderman',
+    KENNETH_E_MAPP,
+    'Larry Cohen',
+    LESLEY_GROFF,
+    'lorraine@mc2mm.com',
+    LINDA_STONE,
+    'Lyn Fontanilla',
+    MARK_TRAMO,
+    MELANIE_WALKER,
+    MERWIN_DELA_CRUZ,
+    'Michael Simmons',   # Not the only "To:"
+    'middle.east.update@hotmail.com',
+    'Nancy Cain',
+    'Nancy Dahl',
+    'Nancy Portland',
+    'Nathan NYSD Chambers',
+    'Oliver Goodenough',
+    'Paula Speer',
+    'Peter Aldhous',
+    'Peter Green',
+    ROGER_SCHANK,
+    'Roy Black',
+    STEVEN_PFEIFFER,
+    'Steven Victor MD',
+    'Susan Edelman',
+    TOM_BARRACK,
+    'USANYS',
+    'Vahe Stepanian',
+    'Vladimir Yudashkin',
+]
+
+EMAILER_ID_REGEXES = {name: re.compile(pattern, re.IGNORECASE) for name, pattern in EMAILER_ID_PATTERNS.items()}
+EMAILER_REGEXES = deepcopy(EMAILER_ID_REGEXES)  # Keep a copy without the simple EMAILERS regexes
+
+# Add simple matching regexes for EMAILERS entries to EMAILER_REGEXES
+for emailer in EMAILERS:
+    if emailer in EMAILER_REGEXES:
+        raise RuntimeError(f"Can't overwrite emailer regex for '{emailer}'")
+
+    EMAILER_REGEXES[emailer] = re.compile(emailer + '?', re.IGNORECASE)  # Last char optional bc OCR sucks
+
+SUPPRESS_LOGS_FOR_AUTHORS = [
+    'Multiple Senders Multiple Senders',
+    'Undisclosed recipients:',
+    'undisclosed-recipients:',
+]
+
+
+def cleanup_str(_str: str) -> str:
+    return BAD_NAME_CHARS_REGEX.sub('', _str.replace(REDACTED, '')).strip().strip('_').strip()
+
+
+def extract_emailer_names(emailer_str: str) -> list[str]:
+    """Return a list of people's names found in `emailer_str` (email author or recipients field)."""
+    emailer_str = cleanup_str(emailer_str)
+
+    if len(emailer_str) == 0:
+        return []
+
+    names_found = [name for name, regex in EMAILER_REGEXES.items() if regex.search(emailer_str)]
+
+    if len(emailer_str) <= 2 or BAD_EMAILER_REGEX.match(emailer_str) or TIME_REGEX.match(emailer_str):
+        if len(names_found) == 0 and emailer_str not in SUPPRESS_LOGS_FOR_AUTHORS:
+            logger.warning(f"No emailer found in '{escape_single_quotes(emailer_str)}'")
+        else:
+            logger.info(f"Extracted {len(names_found)} names from semi-invalid '{emailer_str}': {names_found}...")
+
+        return names_found
+
+    names_found = names_found or [emailer_str]
+    return [reverse_first_and_last_names(name) for name in names_found]

epstein_files/documents/imessage/text_message.py

@@ -6,13 +6,12 @@ from rich.text import Text
 
 from epstein_files.util.constant.names import ANTHONY_SCARAMUCCI, JEFFREY_EPSTEIN, STEVE_BANNON, UNKNOWN, Name, extract_last_name
 from epstein_files.util.constant.strings import TIMESTAMP_DIM
-from epstein_files.util.data import iso_timestamp
+from epstein_files.util.data import AMERICAN_DATE_FORMAT, iso_timestamp
 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 = ' (?)'
 
@@ -54,7 +53,7 @@ class TextMessage:
         return self.text.startswith('http')
 
     def parse_timestamp(self) -> datetime:
-        return datetime.strptime(self.timestamp_str, MSG_DATE_FORMAT)
+        return datetime.strptime(self.timestamp_str, AMERICAN_DATE_FORMAT)
 
     def timestamp_txt(self) -> Text:
         try:

epstein_files/documents/json_file.py

@@ -28,6 +28,24 @@ class JsonFile(OtherFile):
     include_description_in_summary_panel: ClassVar[bool] = False
     strip_whitespace: ClassVar[bool] = False
 
+    @property
+    def category(self) -> str:
+        return JSON
+
+    @property
+    def is_interesting(self):
+        return False
+
+    @property
+    def info_txt(self) -> Text | None:
+        return Text(DESCRIPTION, style=INFO_STYLE)
+
+    @property
+    def metadata(self) -> Metadata:
+        metadata = super().metadata
+        metadata['description'] = DESCRIPTION
+        return metadata
+
     def __post_init__(self):
         super().__post_init__()
 
@@ -36,23 +54,9 @@ class JsonFile(OtherFile):
 
         self._set_computed_fields(text=self.json_str())
 
-    def category(self) -> str:
-        return JSON
-
-    def info_txt(self) -> Text | None:
-        return Text(DESCRIPTION, style=INFO_STYLE)
-
-    def is_interesting(self):
-        return False
-
     def json_data(self) -> object:
         with open(self.file_path, encoding='utf-8-sig') as f:
             return json.load(f)
 
-    def metadata(self) -> Metadata:
-        metadata = super().metadata()
-        metadata['description'] = DESCRIPTION
-        return metadata
-
     def json_str(self) -> str:
         return json.dumps(self.json_data(), indent=4)

epstein_files/documents/messenger_log.py

@@ -31,38 +31,30 @@ class MessengerLog(Communication):
     messages: list[TextMessage] = field(default_factory=list)
     phone_number: str | None = None
 
-    def __post_init__(self):
-        super().__post_init__()
-        self.messages = [self._build_message(match) for match in MSG_REGEX.finditer(self.text)]
-
-    def first_message_at(self, name: Name) -> datetime:
-        return self.messages_by(name)[0].parse_timestamp()
+    @property
+    def border_style(self) -> str:
+        return self.author_style
 
+    @property
     def info_txt(self) -> Text | None:
         num_days_str = days_between_str(self.timestamp, self.messages[-1].parse_timestamp())
         txt = Text(f"(Covers {num_days_str} starting ", style='dim')
-        txt.append(self.date_str(), style=TIMESTAMP_STYLE).append(' ')
+        txt.append(self.date_str, style=TIMESTAMP_STYLE).append(' ')
 
         if not self.author:
             txt.append('with unknown counterparty')
         else:
-            txt.append(GUESSED_MSG if self.is_attribution_uncertain() else CONFIRMED_MSG).append(' ')
-            txt.append(Text(self.author, style=self.author_style() + ' bold'))
+            txt.append(GUESSED_MSG if self.is_attribution_uncertain else CONFIRMED_MSG).append(' ')
+            txt.append(Text(self.author, style=self.author_style + ' bold'))
 
         if self.phone_number:
             txt.append(highlighter(f" using the phone number {self.phone_number}"))
 
         return txt.append(')')
 
-    def last_message_at(self, name: Name) -> datetime:
-        return self.messages_by(name)[-1].parse_timestamp()
-
-    def messages_by(self, name: Name) -> list[TextMessage]:
-        """Return all messages by 'name'."""
-        return [m for m in self.messages if m.author == name]
-
+    @property
     def metadata(self) -> Metadata:
-        metadata = super().metadata()
+        metadata = super().metadata
         metadata.update({'num_messages': len(self.messages)})
 
         if self.phone_number:
@@ -70,8 +62,19 @@ class MessengerLog(Communication):
 
         return metadata
 
-    def _border_style(self) -> str:
-        return self.author_style()
+    def __post_init__(self):
+        super().__post_init__()
+        self.messages = [self._build_message(match) for match in MSG_REGEX.finditer(self.text)]
+
+    def first_message_at(self, name: Name) -> datetime:
+        return self.messages_by(name)[0].parse_timestamp()
+
+    def last_message_at(self, name: Name) -> datetime:
+        return self.messages_by(name)[-1].parse_timestamp()
+
+    def messages_by(self, name: Name) -> list[TextMessage]:
+        """Return all messages by 'name'."""
+        return [m for m in self.messages if m.author == name]
 
     def _build_message(self, match: re.Match) -> TextMessage:
         """Turn a regex match into a TextMessage."""
@@ -86,7 +89,7 @@ class MessengerLog(Communication):
         return TextMessage(
             author=self.author if (is_phone_number or not author_str) else author_str,
             author_str=author_str if is_phone_number else '',  # Preserve phone numbers
-            is_id_confirmed=not self.is_attribution_uncertain(),
+            is_id_confirmed=not self.is_attribution_uncertain,
             text=match.group(4).strip(),
             timestamp_str=match.group(2).strip(),
         )
@@ -102,25 +105,6 @@ class MessengerLog(Communication):
 
         raise RuntimeError(f"{self}: No timestamp found!")
 
-    def _set_message_timestamps(self) -> None:
-        raise NotImplementedError(f"TextMessage.timestamp no longer exists")
-        last_message: TextMessage | None = None
-
-        for i, message in enumerate(self.messages):
-            try:
-                message.timestamp = message.parse_timestamp()
-            except Exception as e:
-                msg = f"Failed to parse timestamp for TextMessage {i + 1}, {message}: {e}"
-
-                if i == 0:
-                    message.timestamp = self.timestamp
-                    self.warn(f"{msg}\nit's the first message so using the MessengerLog timestamp property {self.timestamp}")
-                else:
-                    message.timestamp = last_message.timestamp + timedelta(milliseconds=1)
-                    self.warn(f"{msg}\nadding 1 millisecond to last timestamp {last_message.timestamp}")
-
-            last_message = message
-
     def __rich_console__(self, console: Console, options: ConsoleOptions) -> RenderResult:
         yield self.file_info_panel()
         yield Text('')

epstein_files/documents/other_file.py

@@ -30,7 +30,6 @@ MAX_DAYS_SPANNED_TO_BE_VALID = 10
 MAX_EXTRACTED_TIMESTAMPS = 100
 MIN_TIMESTAMP = datetime(2000, 1, 1)
 MID_TIMESTAMP = datetime(2007, 1, 1)
-MAX_TIMESTAMP = datetime(2022, 12, 31)
 PREVIEW_CHARS = int(580 * (1 if args.all_other_files else 1.5))
 LOG_INDENT = '\n         '
 TIMESTAMP_LOG_INDENT = f'{LOG_INDENT}    '
@@ -93,40 +92,28 @@ class OtherFile(Document):
     """
     was_timestamp_extracted: bool = False
     include_description_in_summary_panel: ClassVar[bool] = True  # Class var for logging output
+    max_timestamp: ClassVar[datetime] = datetime(2022, 12, 31) # Overloaded in DojFile
 
-    def __post_init__(self):
-        super().__post_init__()
-
-        if self.config is None and VI_DAILY_NEWS_REGEX.search(self.text):
-            self.log(f"Creating synthetic config for VI Daily News article...")
-            self.config = DocCfg(id=self.file_id, author=VI_DAILY_NEWS, category=ARTICLE, description='article')
+    @property
+    def config_description(self) -> str | None:
+        """Overloads superclass property."""
+        if self.config and self.config.description:
+            return self.config.complete_description
 
+    @property
     def category(self) -> str | None:
         return self.config and self.config.category
 
+    @property
     def category_txt(self) -> Text | None:
-        return styled_category(self.category())
-
-    def config_description(self) -> str | None:
-        """Overloads superclass method."""
-        if self.config is not None:
-            return self.config.complete_description()
-
-    def highlighted_preview_text(self) -> Text:
-        try:
-            return highlighter(escape(self.preview_text()))
-        except Exception as e:
-            logger.error(f"Failed to apply markup in string '{escape_single_quotes(self.preview_text())}'\n"
-                         f"Original string: '{escape_single_quotes(self.preview_text())}'\n"
-                         f"File: '{self.filename}'\n")
-
-            return Text(escape(self.preview_text()))
+        return styled_category(self.category)
 
+    @property
     def is_interesting(self) -> bool:
         """Overloaded. False for lame prefixes, duplicates, and other boring files."""
-        info_sentences = self.info()
+        info_sentences = self.info
 
-        if self.is_duplicate():
+        if self.is_duplicate:
             return False
         elif len(info_sentences) == 0:
             return True
@@ -135,9 +122,9 @@ class OtherFile(Document):
                 return self.config.is_interesting
             elif self.config.author in INTERESTING_AUTHORS:
                 return True
-            elif self.category() == FINANCE and self.author is not None:
+            elif self.category == FINANCE and self.author is not None:
                 return False
-            elif self.category() in UNINTERESTING_CATEGORIES:
+            elif self.category in UNINTERESTING_CATEGORIES:
                 return False
 
         for prefix in UNINTERESTING_PREFIXES:
@@ -146,15 +133,33 @@ class OtherFile(Document):
 
         return True
 
+    @property
     def metadata(self) -> Metadata:
-        metadata = super().metadata()
-        metadata['is_interesting'] = self.is_interesting()
+        metadata = super().metadata
+        metadata['is_interesting'] = self.is_interesting
 
         if self.was_timestamp_extracted:
             metadata['was_timestamp_extracted'] = self.was_timestamp_extracted
 
         return metadata
 
+    def __post_init__(self):
+        super().__post_init__()
+
+        if self.config is None and VI_DAILY_NEWS_REGEX.search(self.text):
+            self.log(f"Creating synthetic config for VI Daily News article...")
+            self.config = DocCfg(id=self.file_id, author=VI_DAILY_NEWS, category=ARTICLE, description='article')
+
+    def highlighted_preview_text(self) -> Text:
+        try:
+            return highlighter(escape(self.preview_text()))
+        except Exception as e:
+            logger.error(f"Failed to apply markup in string '{escape_single_quotes(self.preview_text())}'\n"
+                         f"Original string: '{escape_single_quotes(self.preview_text())}'\n"
+                         f"File: '{self.filename}'\n")
+
+            return Text(escape(self.preview_text()))
+
     def preview_text(self) -> str:
         return WHITESPACE_REGEX.sub(' ', self.text)[0:PREVIEW_CHARS]
 
@@ -164,9 +169,7 @@ class OtherFile(Document):
 
     def _extract_timestamp(self) -> datetime | None:
         """Return configured timestamp or value extracted by scanning text with datefinder."""
-        if self.config and self.config.timestamp():
-            return self.config.timestamp()
-        elif self.config and any([s in (self.config_description() or '') for s in SKIP_TIMESTAMP_EXTRACT]):
+        if self.config and any([s in (self.config_description or '') for s in SKIP_TIMESTAMP_EXTRACT]):
             return None
 
         timestamps: list[datetime] = []
@@ -175,10 +178,11 @@ class OtherFile(Document):
             warnings.filterwarnings("ignore", module="dateutil")
 
             try:
-                for timestamp in datefinder.find_dates(self.text, strict=True):
+                # TODO: datefinder.find_dates() cannot find 08/29/2019 style e.g. in EFTA00005783 :(
+                for timestamp in datefinder.find_dates(self.text, strict=False):
                     timestamp = remove_timezone(timestamp)
 
-                    if MIN_TIMESTAMP < timestamp < MAX_TIMESTAMP:
+                    if MIN_TIMESTAMP < timestamp < self.max_timestamp:
                         timestamps.append(timestamp)
 
                     if len(timestamps) >= MAX_EXTRACTED_TIMESTAMPS:
@@ -187,7 +191,7 @@ class OtherFile(Document):
                 self.warn(f"Error while iterating through datefinder.find_dates(): {e}")
 
         if len(timestamps) == 0:
-            if not (self.is_duplicate() or VAST_HOUSE in self.text):
+            if not (self.is_duplicate or VAST_HOUSE in self.text):
                 self.log_top_lines(15, msg=f"No timestamps found")
 
             return None
@@ -222,21 +226,21 @@ class OtherFile(Document):
 
         for file in files:
             link_and_info = [file.external_links_txt()]
-            date_str = file.date_str()
+            date_str = file.date_str
 
-            if file.is_duplicate():
-                preview_text = file.duplicate_file_txt()
+            if file.is_duplicate:
+                preview_text = file.duplicate_file_txt
                 row_style = ' dim'
             else:
-                link_and_info += file.info()
+                link_and_info += file.info
                 preview_text = file.highlighted_preview_text()
                 row_style = ''
 
             table.add_row(
                 Group(*link_and_info),
                 Text(date_str, style=TIMESTAMP_STYLE) if date_str else QUESTION_MARKS_TXT,
-                file.file_size_str(),
-                file.category_txt(),
+                file.file_size_str,
+                file.category_txt,
                 preview_text,
                 style=row_style
             )
@@ -246,12 +250,12 @@ class OtherFile(Document):
     @classmethod
     def summary_table(cls, files: Sequence['OtherFile'], title_pfx: str = '') -> Table:
         """Table showing file count by category."""
-        categories = uniquify([f.category() for f in files])
-        categories = sorted(categories, key=lambda c: -len([f for f in files if f.category() == c]))
+        categories = uniquify([f.category for f in files])
+        categories = sorted(categories, key=lambda c: -len([f for f in files if f.category == c]))
         table = cls.file_info_table(f'{title_pfx}Other Files Summary', 'Category')
 
         for category in categories:
-            category_files = [f for f in files if f.category() == category]
+            category_files = [f for f in files if f.category == category]
             table.add_row(styled_category(category), *cls.files_info_row(category_files))
 
         table.columns = table.columns[:-2] + [table.columns[-1]]  # Removee unknown author col