Initial commit: Dick Show Index pipeline with install script and docs

2026-08-24 15:47:21 +02:00
commit 6234c6bf55
25 changed files with 10459 additions and 0 deletions
@@ -0,0 +1,131 @@
+"""Hashtag lexicon: maps aliases -> canonical tag.
+
+Seeded from the research dossier (people, feuds, events, recurring bits).
+Extend freely; matching is case-insensitive whole-word on each transcript
+segment, then aggregated per episode and per segment in the FTS index.
+"""
+import re
+
+PEOPLE = {
+    "maddox": ["maddox", "george ochotsk", "ouzounian"],
+    "asterios": ["asterios", "asterios kokkinos", "kokkinos"],
+    "vito": ["vito", "vito gesualdi", "gesualdi"],
+    "sean": ["sean", "seanie"],  # Sean the audio engineer
+    "eric_july": ["eric july", "rippaverse", "rippa", "isom", "yaira",
+                  "alphacore", "horseman", "backwordz"],
+    "ethan_van_sciver": ["van sciver", "van schiver", "evs", "cyberfrog",
+                         "comicsgate", "trashcast"],
+    "razorfist": ["razorfist", "razor fist"],
+    "yellowflash": ["yellowflash", "yellow flash"],
+    "clippa": ["clippa", "young clippa", "riley"],
+    "kevin_landau": ["kevin landau", "landau"],
+    "nick_rekieta": ["rekieta", "rekieta law", "rackets",
+                     # whisper phonetic variants observed in transcripts
+                     "raketa", "riketa", "rikita", "rakiti", "rakeda",
+                     "rikata", "rikade"],
+    "ethan_ralph": ["ralph", "the ralph retort", "killstream", "ralphretort"],
+    "null": ["joshua moon", "kiwi farms", "kiwifarms"],
+    "mumkey_jones": ["mumkey", "mumkey jones"],
+    "josh_denny": ["denny", "josh denny"],
+    "frank_hassle": ["hassle", "frank hassle"],
+    "destiny": ["destiny", "steven bonnell"],
+    "justin_whang": ["whang", "justin whang", "whang!"],
+    "digibro": ["digibro"],
+    "wauterboi": ["waut3rboi", "wauterboi"],
+    "andy_lee": ["andy lee", "callofthedeep"],
+    "cliff_campbell": ["cliff campbell"],
+    "john_morgan": ["john morgan"],
+    "mumkey": [],
+    "greg_boser": ["boser", "greg boser"],
+    "loren_baker": ["loren baker"],
+    "tuomas": ["tuomas", "holmburg", "collector crypt"],
+    "john_mcafee": ["mcafee"],
+    "bunty_king": ["bunty"],
+    "jf_gariepy": ["jf garpey", "gariepy", "jfg"],
+    "sargon": ["sargon"],
+    "boogie2988": ["boogie", "boogie2988"],
+    "kraut": ["kraut"],
+    "andy_warski": ["warski"],
+    "tony_heller": [],
+    "stefan_molyneux": ["molyneux"],
+    "lauren_southern": ["lauren southern", "southern"],
+    "gavin_mcinnes": ["gavin mcinnes", "mcinnes"],
+    "milo": ["milo yiannopoulos", "milo"],
+    "cuck_shack_cast": [],
+}
+
+EVENTS = {
+    "lolsuit": ["lolsuit", "lol suit", "lawsuit", "complaint", "deposition",
+                "judge ramos", "greenberger", "subpoena", "dismissed with prejudice"],
+    "isom_lawsuit": ["international school of ministry", "trademark lawsuit",
+                     "night letter", "cease and desist"],
+    "patreon_drama": ["patreon"],
+    "deplatforming": ["deplatform", "mastercard", "match list", "visa",
+                      "stripe", "paypal", "banking", "backed.by", "backedby"],
+    "seanies": ["seanie", "seanies", "seany award"],
+    "rage_calendar": ["rage calendar", "advent calendar"],
+    "hot_goss": ["hot goss"],
+    "rape_list": ["rape list"],
+    "drunk_sober_high": ["drunk sober high"],
+    "dick_tips": ["dick tip", "dick tips"],
+    "voicemail": ["voicemail", "voice mail"],
+    "rage": ["are you a rage", "the rage"],
+    "isom_review": ["isom #1", "isom review", "grave digger", "tombstone"],
+    "charity_accusations": ["charity"],
+    "new_project2": ["new project 2", "np2"],
+    "web3": ["web3", "nft", "solana", "crypto", "token", "blockchain",
+             "wallet", "mint"],
+    "maddox_book_prank": ["fuck whales", "fuck whales"],
+    "best_debate": ["best debate in the universe"],
+    "biggest_problem": ["biggest problem in the universe", "tbpitu"],
+}
+
+TOPICS = {
+    "politics": ["trump", "biden", "obama", "election", "senate", "congress",
+                 "democrat", "republican", "libertarian"],
+    "gun_policy": ["second amendment", "nra", "gun control"],
+    "covid": ["covid", "pandemic", "mask", "vaccine", "lockdown", "fauci"],
+    "ukraine_war": ["ukraine", "zelensky", "putin", "russia"],
+    "israel": ["israel", "gaza", "hamas", "idf", "antisemitism"],
+    "ai_tech": ["artificial intelligence", " chatgpt", " openai", " ai ",
+                "machine learning"],
+    "gaming": ["video game", "playstation", "nintendo", "xbox", "steam"],
+    "movies_tv": ["movie", "netflix", "disney", "marvel", "star wars"],
+    "sports": ["nfl", "nba", "ufc", "boxing", "wnba"],
+    "relationships": ["girlfriend", "wife", "divorce", "dating", "marriage"],
+}
+
+
+def build_lexicon() -> list[tuple[str, str, "re.Pattern"]]:
+    """Returns [(category, canonical_tag, compiled_regex)]."""
+    import re
+    out = []
+    for category, table in (("person", PEOPLE), ("event", EVENTS),
+                            ("topic", TOPICS)):
+        for tag, aliases in table.items():
+            parts = []
+            for alias in aliases:
+                a = alias.strip()
+                if not a:
+                    continue
+                esc = re.escape(a)
+                if a[:1].isalnum():
+                    esc = r"\b" + esc
+                if a[-1:].isalnum():
+                    esc = esc + r"\b"
+                parts.append(esc)
+            if not parts:
+                continue
+            rx = re.compile("|".join(parts), re.IGNORECASE)
+            out.append((category, tag, rx))
+    return out
+
+
+def tags_for_text(text: str, lexicon=None) -> list[str]:
+    if lexicon is None:
+        lexicon = build_lexicon()
+    found = []
+    for _cat, tag, rx in lexicon:
+        if rx.search(text):
+            found.append(tag)
+    return found