Game line names across languages; RSubtitle; editor in three columns

ackit/subtitles.py

@@ -22,6 +22,8 @@ from collections import defaultdict, namedtuple
 from .upk import Package
 
 CLASS = "RDialogueEvent"
+SUBTITLE_CLASS, LOOKUP_CLASS = "RSubtitle", "RSubtitleLookup"   # scripted radio/encryption subtitles
+UNRESOLVED = "#lookup:%08X"     # speech of an RSubtitle until its lookup key is matched to a line name
 T_STRUCT, T_STRING, T_OBJECT = 0x09, 0x0D, 0x10
 
 # one subtitle string inside a package: pos = absolute uncompressed offset of the FString length field,
@@ -109,9 +111,14 @@ def _parse_lines(b, o, end, base, lang):
 
 
 def parse_dialogue(b, base, names_idx):
-    """Fields of one RDialogueEvent export (bytes `b` starting at uncompressed offset `base`)."""
-    ls, sub = names_idx
-    i = b.find(struct.pack("<II", ls, 0))
+    """Fields of one dialogue/subtitle export (bytes `b` starting at uncompressed offset `base`).
+    names_idx: (name indices of the per-language array: LocalizedSubtitles or ArraySubtitles, of Subtitles)."""
+    arrays, sub = names_idx
+    i = -1
+    for ls in arrays:
+        i = b.find(struct.pack("<II", ls, 0))
+        if i >= 4 and struct.unpack_from("<H", b, i - 4)[0] == T_STRUCT:
+            break
     if i < 4 or struct.unpack_from("<H", b, i - 4)[0] != T_STRUCT:
         return []
     size = struct.unpack_from("<i", b, i + 8)[0]
@@ -168,6 +175,24 @@ class Collector:
         except (SubtitleError, struct.error, ValueError, IndexError) as e:
             self.issues.append(("subtitles", "%s: %s" % (rel, e)))
 
+    PREFIXES = ("", "RADIO_SCAN_", "RADIO_", "TV_", "CH_ZERO_", "GCPD_", "CHAR_", "SEQUENCE_")
+
+    def resolve(self, line_names):
+        """Give RSubtitle objects their speech line name: the name whose lookup_key equals the object's key,
+        from `line_names` or built from the object's own name (Speech_ + prefix + name; exact hash match)."""
+        by_key = {lookup_key(n): n for n in line_names}
+        for sp in [s for s in self.dialogues if s.startswith("#lookup:")]:
+            key = int(sp.split(":")[1], 16)
+            name = by_key.get(key)
+            if not name:
+                exp = self.dialogues[sp][0][1].export
+                name = next(("Speech_" + p + exp for p in self.PREFIXES if lookup_key("Speech_" + p + exp) == key), None)
+            copies = self.dialogues.pop(sp)
+            if not name:
+                self.issues.append(("subtitles", "no speech line for subtitle %s" % copies[0][1].export))
+                name = copies[0][1].export
+            self.dialogues[name].extend((rel, d._replace(speech=name)) for rel, d in copies)
+
 
 # --- catalog files: SUB_<LANG>.csv (texts) + SUB_locations.csv.gz (every copy) ------------------
 LOCATIONS = "SUB_locations.csv.gz"
@@ -236,20 +261,56 @@ def read_locations(path, lang=None):
     return dict(out)
 
 
+def lookup_key(line_name):
+    """Key of a speech line in the RSubtitleLookup table: FNV-1 of its name without 'Speech_'."""
+    from .bnk import fnv1
+    return fnv1(line_name[7:] if line_name.lower().startswith("speech_") else line_name)
+
+
+def _lookup_table(b):
+    """RSubtitleLookup export data -> {export index: key}: array of {int key @0, object @4}."""
+    count = struct.unpack_from("<I", b, 24)[0]
+    out, o = {}, 28
+    for _ in range(count):
+        if b[o:o + 4] != b"\x02\x00\x00\x00" or b[o + 8:o + 12] != b"\x10\x00\x04\x00":
+            raise SubtitleError("unexpected subtitle lookup layout")
+        key, ref = struct.unpack_from("<Ii", b, o + 4)[0], struct.unpack_from("<i", b, o + 12)[0]
+        out[ref] = key
+        o += 18
+    return out
+
+
 def scan_package(pkg, data=None, start=None, tables=None):
-    """[Dialogue] of one package (empty if it has none)."""
+    """[Dialogue] of one package (empty if it has none): RDialogueEvent objects (speech = the referenced
+    speech event) and RSubtitle objects (speech = UNRESOLVED % lookup key, see Collector.resolve)."""
     if data is None:
         start, data = pkg.read_all()
     names, imports, exports = tables or pkg.tables(data, start)
-    cls = {-(i + 1) for i, (c, o, _) in enumerate(imports) if c == "Class" and o == CLASS}
-    if not cls or "LocalizedSubtitles" not in names or "Subtitles" not in names:
+    by_class = {}
+    for i, (c, o, _) in enumerate(imports):
+        if c == "Class" and o in (CLASS, SUBTITLE_CLASS, LOOKUP_CLASS):
+            by_class[-(i + 1)] = o
+    arrays = [names.index(a) for a in ("LocalizedSubtitles", "ArraySubtitles") if a in names]
+    if not by_class or not arrays or "Subtitles" not in names:
         return []
-    idx = (names.index("LocalizedSubtitles"), names.index("Subtitles"))
+    idx = (arrays, names.index("Subtitles"))
+    keys = {}
+    for e in exports:
+        if by_class.get(e.cls) == LOOKUP_CLASS and e.size > 0:
+            keys.update(_lookup_table(data[e.offset - start:e.offset - start + e.size]))
     out = []
     for e in exports:
-        if e.cls in cls and e.size > 0:
+        kind = by_class.get(e.cls)
+        if kind in (CLASS, SUBTITLE_CLASS) and e.size > 0:
             b = data[e.offset - start:e.offset - start + e.size]
             fields = parse_dialogue(b, e.offset, idx)
-            if fields:
-                out.append(Dialogue(_speech_ref(b, exports, imports), e.name, fields))
+            if not fields:
+                continue
+            if kind == CLASS:
+                speech = _speech_ref(b, exports, imports)
+            elif e.index in keys:
+                speech = UNRESOLVED % keys[e.index]
+            else:
+                speech = e.name                       # not in a lookup table: keep the object's name
+            out.append(Dialogue(speech, e.name, fields))
     return out