Version 3.1.0: voice lines linked across all languages from the game data

ackit/subtitles.py

@@ -19,7 +19,6 @@ import re
 import struct
 from collections import defaultdict, namedtuple
 
-from .upk import Package
 
 CLASS = "RDialogueEvent"
 SUBTITLE_CLASS, LOOKUP_CLASS = "RSubtitle", "RSubtitleLookup"   # scripted radio/encryption subtitles
@@ -29,7 +28,8 @@ T_STRUCT, T_STRING, T_OBJECT = 0x09, 0x0D, 0x10
 # one subtitle string inside a package: pos = absolute uncompressed offset of the FString length field,
 # size = bytes of the whole FString (length field included), enc 'a' (cp1252) or 'w' (UTF-16)
 Field = namedtuple("Field", "lang index text pos size enc")
-Dialogue = namedtuple("Dialogue", "speech export fields")   # speech: name of the referenced speech event
+# speech: name of the referenced speech event; speaker: the object's speaker field (RDialogueEvent only)
+Dialogue = namedtuple("Dialogue", "speech export fields speaker", defaults=("",))
 
 
 class SubtitleError(ValueError):
@@ -148,6 +148,15 @@ def parse_dialogue(b, base, names_idx):
     return fields
 
 
+def _speaker(b):
+    """The speaker FString of a dialogue object (property 0x0D at field offset 0x34), '' if none."""
+    m = re.search(rb"\x0d\x00\x34\x00", b)
+    try:
+        return read_fstring(b, m.start() + 4)[0] if m else ""
+    except (struct.error, UnicodeDecodeError, ValueError):
+        return ""
+
+
 def _speech_ref(b, exports, imports):
     """Name of the object referenced by the dialogue's first object property (its speech event)."""
     m = re.search(rb"\x10\x00\x2c\x00", b)
@@ -197,7 +206,14 @@ class Collector:
 # --- catalog files: SUB_<LANG>.csv (texts) + SUB_locations.csv.gz (every copy) ------------------
 LOCATIONS = "SUB_locations.csv.gz"
 TEXT_FIELDS = ["speech", "line", "text", "room", "enc", "sound"]
-SubLine = namedtuple("SubLine", "lang speech line text room enc sound")      # sound: linked WAD sound key
+class SubLine(namedtuple("SubLine", "lang speech line text room enc sound")):
+    """A subtitle string. sound: the voice recording(s) its speech event plays in that language (sound keys,
+    ';'-separated in the event's order: an event can play one of two versions of a line)."""
+    __slots__ = ()
+
+    @property
+    def sounds(self):
+        return tuple(self.sound.split(";")) if self.sound else ()
 SubLoc = namedtuple("SubLoc", "lang speech line file pos size enc")
 
 
@@ -312,5 +328,5 @@ def scan_package(pkg, data=None, start=None, tables=None):
                 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))
+            out.append(Dialogue(speech, e.name, fields, _speaker(b) if kind == CLASS else ""))
     return out