epstein-files 1.0.10__py3-none-any.whl → 1.0.12__py3-none-any.whl

epstein_files/util/rich.py

@@ -20,8 +20,9 @@ from epstein_files.util.constant.urls import *
 from epstein_files.util.constants import FALLBACK_TIMESTAMP, HEADER_ABBREVIATIONS
 from epstein_files.util.data import json_safe
 from epstein_files.util.env import args
+from epstein_files.util.file_helper import log_file_write
 from epstein_files.util.highlighted_group import ALL_HIGHLIGHTS, HIGHLIGHTED_NAMES, EpsteinHighlighter
-from epstein_files.util.logging import log_file_write, logger
+from epstein_files.util.logging import logger
 
 TITLE_WIDTH = 50
 NUM_COLOR_KEY_COLS = 4
@@ -30,6 +31,7 @@ QUESTION_MARK_TXT = Text(QUESTION_MARKS, style='dim')
 GREY_NUMBERS = [58, 39, 39, 35, 30, 27, 23, 23, 19, 19, 15, 15, 15]
 
 DEFAULT_NAME_STYLE = 'gray46'
+INFO_STYLE = 'white dim italic'
 KEY_STYLE='honeydew2 bold'
 SECTION_HEADER_STYLE = 'bold white on blue3'
 SOCIAL_MEDIA_LINK_STYLE = 'pale_turquoise4'
@@ -239,23 +241,26 @@ def print_numbered_list_of_emailers(_list: list[str | None], epstein_files = Non
 def print_other_site_link(is_header: bool = True) -> None:
     """Print a link to the emails site if we're building text messages site and vice versa."""
     site_type: SiteType = EMAIL if args.all_emails else TEXT_MESSAGE
+    link_style = OTHER_SITE_LINK_STYLE if is_header else 'light_slate_grey bold'
 
     if is_header:
         print_starred_header(f"This is the Epstein {site_type.title()}s site", num_spaces=4, num_stars=14)
 
     other_site_type: SiteType = TEXT_MESSAGE if site_type == EMAIL else EMAIL
-    other_site_msg = "another site for" + (' all of' if other_site_type == EMAIL else '')
+    other_site_msg = "another site with" + (' all of' if other_site_type == EMAIL else '')
     other_site_msg += f" Epstein's {other_site_type}s also generated by this code"
-    markup_msg = link_markup(SITE_URLS[other_site_type], other_site_msg, OTHER_SITE_LINK_STYLE)
+    markup_msg = link_markup(SITE_URLS[other_site_type], other_site_msg, link_style)
     print_centered(parenthesize(Text.from_markup(markup_msg)), style='bold')
 
-    if is_header:
-        word_count_link = link_text_obj(WORD_COUNT_URL, 'most frequently used words in the emails and texts', AUX_SITE_LINK_STYLE)
-        print_centered(parenthesize(word_count_link))
-        metadata_link = link_text_obj(JSON_METADATA_URL, 'author attribution explanations', AUX_SITE_LINK_STYLE)
-        print_centered(parenthesize(metadata_link))
-        json_link = link_text_obj(WORD_COUNT_URL, "epstein's json files", AUX_SITE_LINK_STYLE)
-        print_centered(parenthesize(json_link))
+    if not is_header:
+        return
+
+    word_count_link = link_text_obj(WORD_COUNT_URL, 'most frequently used words in the emails and texts', AUX_SITE_LINK_STYLE)
+    print_centered(parenthesize(word_count_link))
+    metadata_link = link_text_obj(JSON_METADATA_URL, 'author attribution explanations', AUX_SITE_LINK_STYLE)
+    print_centered(parenthesize(metadata_link))
+    json_link = link_text_obj(WORD_COUNT_URL, "epstein's json files", AUX_SITE_LINK_STYLE)
+    print_centered(parenthesize(json_link))
 
 
 def print_page_title(expand: bool = True, width: int | None = None) -> None:

epstein_files/util/word_count.py

@@ -9,18 +9,22 @@ from rich.padding import Padding
 from rich.text import Text
 
 from epstein_files.documents.emails.email_header import EmailHeader
-from epstein_files.util.constant.common_words import COMMON_WORDS, UNSINGULARIZABLE_WORDS
+from epstein_files.epstein_files import EpsteinFiles
+from epstein_files.util.constant.common_words import COMMON_WORDS_LIST, COMMON_WORDS, UNSINGULARIZABLE_WORDS
 from epstein_files.util.constant.names import OTHER_NAMES
+from epstein_files.util.constant.output_files import WORD_COUNT_HTML_PATH
 from epstein_files.util.data import ALL_NAMES, flatten, sort_dict
-from epstein_files.util.env import args
+from epstein_files.util.env import args, specified_names
 from epstein_files.util.logging import logger
-from epstein_files.util.rich import highlighter
-from epstein_files.util.search_result import SearchResult
+from epstein_files.util.rich import (console, highlighter, print_centered, print_color_key, print_page_title,
+     print_panel, print_starred_header, write_html)
+from epstein_files.util.search_result import MatchedLine, SearchResult
+from epstein_files.util.timer import Timer
 
 FIRST_AND_LAST_NAMES = flatten([n.split() for n in ALL_NAMES])
 FIRST_AND_LAST_NAMES = [n.lower() for n in FIRST_AND_LAST_NAMES] + OTHER_NAMES
 
-HTML_REGEX = re.compile(r"com/|cae-v2w=|content-(transfe|type)|font(/|-(family|size))|http|\.html?\??|margin-bottom|padding-left|quoted-printable|region=|text-decoration|ttps|www|\.(gif|jpe?g|png);?$")
+HTML_REGEX = re.compile(r"^http|#yiv|com/|cae-v2w=|content-(transfe|type)|font(/|-(family|size))|http|\.html?\??|margin-bottom|padding-left|quoted-printable|region=|text-decoration|ttps|www|\.(gif|jpe?g|png);?$")
 HYPHENATED_WORD_REGEX = re.compile(r"[a-z]+-[a-z]+", re.IGNORECASE)
 OK_SYMBOL_WORDS = ['mar-a-lago', 'p/e', 's&p', ':)', ':).', ';)', ':-)', ';-)']
 ONLY_SYMBOLS_REGEX = re.compile(r"^[^a-zA-Z0-9]+$")
@@ -187,6 +191,62 @@ class WordCount:
         yield f"Showing {len(word_txts):,} words appearing at least {MIN_COUNT_CUTOFF} times (out of {len(self.count):,} words)."
 
 
+def write_word_counts_html() -> None:
+    timer = Timer()
+    epstein_files = EpsteinFiles.get_files(timer)
+    email_subjects: set[str] = set()
+    word_count = WordCount()
+
+    # Remove dupes, junk mail, and fwded articles from emails
+    emails = [e for e in epstein_files.emails if not (e.is_duplicate() or e.is_junk_mail() or e.is_fwded_article())]
+
+    for email in emails:
+        if specified_names and email.author not in specified_names:
+            continue
+
+        logger.info(f"Counting words in {email}\n  [SUBJECT] {email.subject()}")
+        lines = email.actual_text.split('\n')
+
+        if email.subject() not in email_subjects and f'Re: {email.subject()}' not in email_subjects:
+            email_subjects.add(email.subject())
+            lines.append(email.subject())
+
+        for i, line in enumerate(lines):
+            if HTML_REGEX.search(line):
+                continue
+
+            for word in line.split():
+                word_count.tally_word(word, SearchResult(email, [MatchedLine(line, i)]))
+
+    # Add in iMessage conversation words
+    imessage_logs = epstein_files.imessage_logs_for(specified_names) if specified_names else epstein_files.imessage_logs
+
+    for imessage_log in imessage_logs:
+        logger.info(f"Counting words in {imessage_log}")
+
+        for i, msg in enumerate(imessage_log.messages):
+            if specified_names and msg.author not in specified_names:
+                continue
+            elif HTML_REGEX.search(line):
+                continue
+
+            for word in msg.text.split():
+                word_count.tally_word(word, SearchResult(imessage_log, [MatchedLine(msg.text, i)]))
+
+    print_page_title(expand=False)
+    print_starred_header(f"Most Common Words in {len(emails):,} Emails and {len(imessage_logs)} iMessage Logs")
+    print_centered(f"(excluding {len(COMMON_WORDS_LIST)} particularly common words at bottom)", style='dim')
+    console.line()
+    print_color_key()
+    console.line()
+    console.print(word_count)
+    console.line(2)
+    print_panel(f"{len(COMMON_WORDS_LIST):,} Excluded Words", centered=True)
+    console.print(', '.join(COMMON_WORDS_LIST), highlight=False)
+    write_html(WORD_COUNT_HTML_PATH)
+    timer.print_at_checkpoint(f"Finished counting words")
+
+
 def _word_style(word: str | None) -> str:
     word = word or ''
     return 'bright_white' if word in FIRST_AND_LAST_NAMES else 'grey53'

{epstein_files-1.0.10.dist-info → epstein_files-1.0.12.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: epstein-files
-Version: 1.0.10
+Version: 1.0.12
 Summary: Tools for working with the Jeffrey Epstein documents released in November 2025.
 Home-page: https://michelcrypt4d4mus.github.io/epstein_text_messages/
 License: GPL-3.0-or-later

epstein_files-1.0.12.dist-info/RECORD

@@ -0,0 +1,33 @@
+epstein_files/__init__.py,sha256=qVFB7sS6XSlZX-ByyDwdbGSn2h06aoX2Mx8WcgRb-To,4710
+epstein_files/documents/communication.py,sha256=XapJlNfcaww3TpSkZIBE5c1Skqv_pFEFlIVi06V7k3E,2046
+epstein_files/documents/document.py,sha256=2FxyqWKROi7w2SmaQ493oGKekNvYAHSuv2YsDhPNQBU,16987
+epstein_files/documents/email.py,sha256=y8QTq349LWlm2LLUJ8rGcdkDbaGYJCV99wJytPcEMew,40587
+epstein_files/documents/emails/email_header.py,sha256=wkPfSLbmzkAeQwvhf0bAeFDLPbQT-EeG0v8vNNLYktM,7502
+epstein_files/documents/imessage/text_message.py,sha256=4gFvTfulj_Su10lNQl6Hq_p9ArTrSmn5pfC22YRJXjI,2794
+epstein_files/documents/json_file.py,sha256=tIYTwA3FYkwVZSpXvFYyUoH9m2sGYCD1U0ttamH6r1o,1306
+epstein_files/documents/messenger_log.py,sha256=yT4WQyTE_W6yelug_YGpBMRJ0YxWNtX4rKoEj8n5TMA,6260
+epstein_files/documents/other_file.py,sha256=pnl_q1o7ur3eeqGPwsYL2qbM3Y8O9LX6j6LbWnoxAiE,9939
+epstein_files/epstein_files.py,sha256=SaD4DJJ5tRxY97Ei4BdOgLzHQ9wrBVGrP64CSqdmk-w,18691
+epstein_files/util/constant/common_words.py,sha256=aR0UjoWmxyR49XS-DtHECQ1CiA_bK8hNP6CQ1TS9yZA,3696
+epstein_files/util/constant/html.py,sha256=9U098TGzlghGg4WfxLYHyub5JGR17Dv7VP5i2MSu8Kk,1415
+epstein_files/util/constant/names.py,sha256=CLWXrln8J-Dth6C-YF7Wdy7UoA8dybKJyqOLETrBeek,10284
+epstein_files/util/constant/output_files.py,sha256=BkV4_gmdj46RfGy5SFYp6dgTty3FtlBth5YGmaGutls,1700
+epstein_files/util/constant/strings.py,sha256=02DwbhAe8qBRq5HOUFx5FafXJ1P2-RJf9TCVu2b7UDQ,1932
+epstein_files/util/constant/urls.py,sha256=0IdCVVvXib0i-4TZFkVHoS4zCbjOBZWcr6NkGxsmQWM,4981
+epstein_files/util/constants.py,sha256=BpPRivoDYFI0uLU35kKpOdrSI6Rr9cmcrRj9-kANVrs,111834
+epstein_files/util/data.py,sha256=X3AutdW-ascIlE2bz1BtN0Bywqpe4OwYzJ-diEpfogI,2992
+epstein_files/util/doc_cfg.py,sha256=_f03qtA7qVbViHwqMXC4O5nfNbh90zDSq6El9Ior6f0,8996
+epstein_files/util/env.py,sha256=HnYcfHSNkwVJ_T75Woy43_OpDyxD0KHPj3GxcVx86N4,5751
+epstein_files/util/file_helper.py,sha256=tacTe1GcAnckPFvjMgxRRSLnFgr2aVIYsgfDR_C9uXk,2780
+epstein_files/util/highlighted_group.py,sha256=xrDLB05YUYGsU6vDvhvENMvIyjEz-9eb9xN-RjfCQbQ,36531
+epstein_files/util/logging.py,sha256=fuREq06xUUI3DfCV2JE-8QM-sQKxpLDj0_AYFO6qR1M,1983
+epstein_files/util/output.py,sha256=XcflgSOlzUGj6FsFaK6j4Dljld8A0h_uVV7ERcI_EYw,8120
+epstein_files/util/rich.py,sha256=8-4IA5bwPBdDPqkPdymq3zVKB9hfy3nrT7fUrN_XevY,14744
+epstein_files/util/search_result.py,sha256=1fxe0KPBQXBk4dLfu6m0QXIzYfZCzvaSkWqvghJGzxY,567
+epstein_files/util/timer.py,sha256=8hxW4Y1JcTUfnBrHh7sL2pM9xu1sL4HFQM4CmmzTarU,837
+epstein_files/util/word_count.py,sha256=8qBTuq3d0Q-3fwiuECKWi2RfL-KUiZD8TciwvfL0D_o,9353
+epstein_files-1.0.12.dist-info/LICENSE,sha256=OXLcl0T2SZ8Pmy2_dmlvKuetivmyPd5m1q-Gyd-zaYY,35149
+epstein_files-1.0.12.dist-info/METADATA,sha256=imTDdrHjWC-bWuw58SAyjYyiziZsqHkO7ODQUntw6YQ,5480
+epstein_files-1.0.12.dist-info/WHEEL,sha256=d2fvjOD7sXsVzChCqf0Ty0JbHKBaLYwDbGQDwQTnJ50,88
+epstein_files-1.0.12.dist-info/entry_points.txt,sha256=5qYgwAXpxegeAicD_rzda_trDRnUC51F5UVDpcZ7j6Q,240
+epstein_files-1.0.12.dist-info/RECORD,,

epstein_files/count_words.py

@@ -1,72 +0,0 @@
-# Count word usage in emails and texts
-import re
-
-from epstein_files.epstein_files import EpsteinFiles
-from epstein_files.util.constant.common_words import COMMON_WORDS_LIST
-from epstein_files.util.constant.output_files import WORD_COUNT_HTML_PATH
-from epstein_files.util.env import args, specified_names
-from epstein_files.util.logging import logger
-from epstein_files.util.rich import (console, print_centered, print_color_key, print_page_title, print_panel,
-     print_starred_header, write_html)
-from epstein_files.util.search_result import MatchedLine, SearchResult
-from epstein_files.util.timer import Timer
-from epstein_files.util.word_count import WordCount
-
-HTML_REGEX = re.compile(r"^http|#yiv")
-
-
-def write_word_counts_html() -> None:
-    timer = Timer()
-    epstein_files = EpsteinFiles.get_files(timer)
-    email_subjects: set[str] = set()
-    word_count = WordCount()
-
-    # Remove dupes, junk mail, and fwded articles from emails
-    emails = [
-        e for e in epstein_files.emails
-        if not (e.is_duplicate or e.is_junk_mail() or (e.config and e.config.is_fwded_article)) \
-            and (len(specified_names) == 0 or e.author in specified_names)
-    ]
-
-    for email in emails:
-        logger.info(f"Counting words in {email}\n  [SUBJECT] {email.subject()}")
-        lines = email.actual_text.split('\n')
-
-        if email.subject() not in email_subjects and f'Re: {email.subject()}' not in email_subjects:
-            email_subjects.add(email.subject())
-            lines.append(email.subject())
-
-        for i, line in enumerate(lines):
-            if HTML_REGEX.search(line):
-                continue
-
-            for word in line.split():
-                word_count.tally_word(word, SearchResult(email, [MatchedLine(line, i)]))
-
-    # Add in iMessage conversation words
-    imessage_logs = epstein_files.imessage_logs_for(specified_names) if specified_names else epstein_files.imessage_logs
-
-    for imessage_log in imessage_logs:
-        logger.info(f"Counting words in {imessage_log}")
-
-        for msg in imessage_log.messages():
-            if len(specified_names) > 0 and msg.author not in specified_names:
-                continue
-            elif HTML_REGEX.search(line):
-                continue
-
-            for word in msg.text.split():
-                word_count.tally_word(word, SearchResult(imessage_log, [msg.text]))
-
-    print_page_title(expand=False)
-    print_starred_header(f"Most Common Words in {len(emails):,} Emails and {len(imessage_logs)} iMessage Logs")
-    print_centered(f"(excluding {len(COMMON_WORDS_LIST)} particularly common words at bottom)", style='dim')
-    console.line()
-    print_color_key()
-    console.line()
-    console.print(word_count)
-    console.line(2)
-    print_panel(f"{len(COMMON_WORDS_LIST):,} Excluded Words", centered=True)
-    console.print(', '.join(COMMON_WORDS_LIST), highlight=False)
-    write_html(WORD_COUNT_HTML_PATH)
-    timer.print_at_checkpoint(f"Finished counting words")

epstein_files-1.0.10.dist-info/RECORD

@@ -1,34 +0,0 @@
-epstein_files/__init__.py,sha256=SfLLu9X7rfHdmZcl8JGmiIxZ_E1RVsmCrh8sLO4jNPU,4859
-epstein_files/count_words.py,sha256=i1pYaQzX7b9S3pyV3RM_8asbQJ1PEk8wJgLOG6Mf0D8,2966
-epstein_files/documents/communication.py,sha256=SunZdjMhR9v6y8LlQ6jhIu8vYjSndaBK0Su1mKnhfj0,2060
-epstein_files/documents/document.py,sha256=BUaioSvOmfsR-ULa6hJy3WYg-hBDC-kqafUheMJ-jFY,16665
-epstein_files/documents/email.py,sha256=H34b2zt_TrPUgXHwZXybjmLE9-QNAtezs9NVSCPOSGM,38462
-epstein_files/documents/emails/email_header.py,sha256=wkPfSLbmzkAeQwvhf0bAeFDLPbQT-EeG0v8vNNLYktM,7502
-epstein_files/documents/imessage/text_message.py,sha256=wfWPQhwGG5Yzyhbr1NAQAY0bzRjjqVZmh8SPl48XmAM,3025
-epstein_files/documents/json_file.py,sha256=1Cx_3uM38Dwgrbs8fU55TUZKSrCsmd4QpHKWtfWdudw,1089
-epstein_files/documents/messenger_log.py,sha256=DHlQpbLbMITMpMtCYk2vcRc7-CTvYvOXql-9nDUc3tQ,5887
-epstein_files/documents/other_file.py,sha256=NdVlCYcyzHvOInReqF-zvHJI1hwtzMWW9ekDojHIb4U,9091
-epstein_files/epstein_files.py,sha256=EEx8Auwv8z0FkRrCi7wE8iuuRQd6K1rQDMc2vdbrsh4,18298
-epstein_files/util/constant/common_words.py,sha256=aR0UjoWmxyR49XS-DtHECQ1CiA_bK8hNP6CQ1TS9yZA,3696
-epstein_files/util/constant/html.py,sha256=9U098TGzlghGg4WfxLYHyub5JGR17Dv7VP5i2MSu8Kk,1415
-epstein_files/util/constant/names.py,sha256=uYhv9xa4NO5jCk9zrGpPKFkcVVaMY2qtBC7ZaKGK3J8,10135
-epstein_files/util/constant/output_files.py,sha256=BkV4_gmdj46RfGy5SFYp6dgTty3FtlBth5YGmaGutls,1700
-epstein_files/util/constant/strings.py,sha256=FDtksfH50PSxtSBw9XhmqxtrgRgGxdIvGiAR2bbPpu4,1899
-epstein_files/util/constant/urls.py,sha256=0IdCVVvXib0i-4TZFkVHoS4zCbjOBZWcr6NkGxsmQWM,4981
-epstein_files/util/constants.py,sha256=gp5HWHt5FHd916r4UpjcJKslO5L-Wno6kjA4F3ZA4YU,110884
-epstein_files/util/data.py,sha256=xwTqrbAi7ZDJM0iyFVOevnokP_oIQ2npkRjHzF1KGGY,2908
-epstein_files/util/doc_cfg.py,sha256=5Pb__bP00mKi9ACv33omZQA-TBzumc7D2Td_Mk4M5DY,9822
-epstein_files/util/env.py,sha256=PaPBi27-npU9egt9LHxr5qR65B2DPHwt7Xc9sx5VN-M,5225
-epstein_files/util/file_helper.py,sha256=v_bE10MHEcXti9DVJo4WqyOsG83Xrv05S3Vc70cYJkk,3082
-epstein_files/util/highlighted_group.py,sha256=dajLYuSbT69zMWf6XKUOZI6ZcgFy-Beq7Nsg9qlteck,35715
-epstein_files/util/logging.py,sha256=4hVl1Qw1qRMSVEYKXZxrvdQuSIMBgTPskzvNMNu8268,2185
-epstein_files/util/output.py,sha256=wLjFBGR5ffn4cLep12G3OmUR0H3WtEMXeVMOXtd-6ig,7909
-epstein_files/util/rich.py,sha256=rdHzn4XRB2erQSf2yYyPakRmd9ixqBUdS8-BVOUAXnE,14603
-epstein_files/util/search_result.py,sha256=1fxe0KPBQXBk4dLfu6m0QXIzYfZCzvaSkWqvghJGzxY,567
-epstein_files/util/timer.py,sha256=8hxW4Y1JcTUfnBrHh7sL2pM9xu1sL4HFQM4CmmzTarU,837
-epstein_files/util/word_count.py,sha256=eGzcsoAvMcutRUFOJnVuEp9_28H74to7T9jTdGUZnuI,6757
-epstein_files-1.0.10.dist-info/LICENSE,sha256=OXLcl0T2SZ8Pmy2_dmlvKuetivmyPd5m1q-Gyd-zaYY,35149
-epstein_files-1.0.10.dist-info/METADATA,sha256=zi10sSw5g5BZDRovIeWlpMYEgLbqFxSl7QII9jUuKdw,5480
-epstein_files-1.0.10.dist-info/WHEEL,sha256=d2fvjOD7sXsVzChCqf0Ty0JbHKBaLYwDbGQDwQTnJ50,88
-epstein_files-1.0.10.dist-info/entry_points.txt,sha256=5qYgwAXpxegeAicD_rzda_trDRnUC51F5UVDpcZ7j6Q,240
-epstein_files-1.0.10.dist-info/RECORD,,