scripts/media-shows.py

@@ -278,9 +278,14 @@ def tmdb(kind, query):
         CACHE[ck] = None
         return None
     top = found[0]
+    # The two search endpoints date their rows differently: movies carry
+    # `release_date`, tv carries `first_air_date`. Reading only one of them leaves
+    # every film answer year-less, and a year-less answer can never be refused by
+    # the year guard below.
+    when = str(top.get("year") or "") or \
+        str(top.get("release_date") or top.get("first_air_date") or "")[:4]
     CACHE[ck] = {"name": (top.get("title") or top.get("name") or "").strip(),
-                 "year": str(top.get("year") or "") or (top.get("first_air_date") or "")[:4],
-                 "id": top.get("id")}
+                 "year": when, "id": top.get("id")}
     return CACHE[ck]
 
 
@@ -787,8 +792,13 @@ for r, name, kind in extras:
 for r in films:
     parsed, year = title_of(r["base"])
     got = tmdb("movie", parsed)
-    words = eng.norm(got["name"]).split() if got else []
-    if not got or not eng.mentions(parsed.split(), words) \
+    # The provider's title must be a run of words the FILE itself states. The query
+    # is only what title_of could salvage from the name, and a short one ("russia")
+    # lets the top hit be a different work entirely: a 1963 Bond film is not a 1991
+    # documentary episode, and Special Edition I is not Special Edition III.
+    said = eng.norm(os.path.splitext(r["base"])[0]).split()
+    named = eng.norm(got["name"]).split() if got else []
+    if not got or not eng.mentions(named, said) \
             or (year != "?" and got["year"] and got["year"] != year):
         park(r, "long file with no episode evidence, and no movie provider names it")
         continue

tests/media_shows.bats

@@ -360,6 +360,38 @@ json.dump({"movie:some documentary":
     [[ "$output" == "$PARK/"* ]]
 }
 
+@test "a movie answer the file does not itself name stays in the review pile" {
+    # TMDb's top hit for a truncated query is a NEAR miss, not an answer: "mobile
+    # suit gundam 00" comes back as Special Edition I while the file is Special
+    # Edition III, and a one-word query "russia" comes back as a 1963 Bond film. A
+    # file leaves the TV library only when it states the title the provider names.
+    printf '8000\t%s\t7200\thevc\t1920x1080\t23.976\t4000000\tyuv420p10le\taac:eng\t0\t0\tmatroska,webm\n' \
+        "$LIB/Longform/Some Documentary Special (2015).mkv" > "$PROBED"
+    python3 -c 'import json, sys
+json.dump({"movie:some documentary":
+           {"name": "Some Documentary Special Part Two", "year": "2015", "id": 55}},
+          open(sys.argv[1], "w"))' "$CACHE"
+    plan
+    run dst "$LIB/Longform/Some Documentary Special (2015).mkv"
+    [[ "$output" == "$PARK/"* ]]
+    run awk -F '\t' -v m="$MOVIES/" '$1 == "move" && index($3, m) == 1 {print $3}' "$OUT"
+    [ -z "$output" ]
+}
+
+@test "a movie answer from another year is not that film" {
+    # The year the file states outranks a provider's eagerness: the 2015 special is
+    # not the 1999 one, however alike their names are.
+    printf '8000\t%s\t7200\thevc\t1920x1080\t23.976\t4000000\tyuv420p10le\taac:eng\t0\t0\tmatroska,webm\n' \
+        "$LIB/Longform/Some Documentary Special (2015).mkv" > "$PROBED"
+    python3 -c 'import json, sys
+json.dump({"movie:some documentary":
+           {"name": "Some Documentary Special", "year": "1999", "id": 55}},
+          open(sys.argv[1], "w"))' "$CACHE"
+    plan
+    run dst "$LIB/Longform/Some Documentary Special (2015).mkv"
+    [[ "$output" == "$PARK/"* ]]
+}
+
 @test "the plan creates every folder before the move that needs it" {
     plan
     python3 - "$OUT" "$LIB" "$MOVIES" "$PARK" <<'PY'