New TOC CD-TEXT string decoding

This patch replaces the previous broken approach to TOC string decoding that used `.encode().decode('unicode_escape')` with proper parsing of the escape sequences cdrdao is known to generate. The new parser is also lenient with invalid escape sequences, that can occur due to improper escaping in cdrdao. See: cdrdao/cdrdao#32 Latin-1: This new parsing method should work for Latin-1 strings for both old and new versions of cdrdao, as long as those strings don't trigger the improper escaping issues in upstream cdrdao. This has been verified with the album Diorama from the Danish black metal band MØL. MS-JIS: This new parsing method should also work for MS-JIS strings as long as the .toc file was generated by cdrdao 1.2.5+ and the strings don't trigger improper escaping issues in upstream cdrdao. Unfortunately, I don't have any CD with CD-Text in MS-JIS, so I could not verify this. cdrdao versions before 1.2.5 will still cause whipper to produce mojibake (garbled characters) when reading MS-JIS CD-Text, as those versions do not encode strings in UTF-8. Other encodings: As far as I know, CD-Text only supports officially ASCII, Latin-1 and MS-JIS, but I wouldn't be surprised if there are unofficial encodings out there, given the strange strings I've seen in some bug reports. If you have a CD with garbled CD-Text, please submit a bug report indicating the performer, album name, language and attach the .toc file so that the produced strings can be compared to the expected text. Fixes whipper-team#169 Fixes whipper-team#183 Signed-off-by: Alicia Boya García <[email protected]>
ntrrgc · Aug 27, 2024 · ac16fbc · ac16fbc
1 parent a4b9742
commit ac16fbc
Show file tree

Hide file tree

Showing 6 changed files with 472 additions and 6 deletions.
diff --git a/whipper/image/toc.py b/whipper/image/toc.py
@@ -33,7 +33,61 @@
 logger = logging.getLogger(__name__)
 
 # shared
-_CDTEXT_CANDIDATE_RE = re.compile(r'(?P<key>\w+) "(?P<value>.+)"')
+_CDTEXT_CANDIDATE_RE = re.compile(r'''
+    (?P<key>\w+)   # CD-TEXT key.
+    \s+
+    "(?P<value>    # CD-TEXT value.
+        (?:
+            \\\\   # escaped backslash.
+        |   \\"    # escaped double-quote.
+        |   [^"]   # not a double-quote.
+        )+?        # the value must not be empty.
+    )"
+''', flags=re.VERBOSE)
+
+_STRING_SUBSTITUTIONS_RE = re.compile(r'''
+      \\(?P<octal>[0-8][0-8][0-8])
+    | \\"
+    | \\\\
+''', flags=re.VERBOSE)
+
+
+def _string_contents_repl(match: 're.Match[str]') -> str:
+    group_octal = match.group('octal')
+    if group_octal is not None:
+        code_point = int(group_octal, base=8)
+        return chr(code_point)
+
+    entire_match = match.group(0)
+    if entire_match == '\\"':
+        return '"'
+    elif entire_match == '\\\\':
+        return '\\'
+    else:
+        raise RuntimeError("unexpected match: ", entire_match)
+
+
+def parse_toc_string(str_within_quotes: str) -> str:
+    """
+    Given the a quoted string obtained from a TOC file using
+    _CDTEXT_CANDIDATE_RE, compute the unescaped string contained inside.
+
+    Backslash substitutions fail gracefully, which is important since cdrdao
+    string encoding has been found to be flawed as recently as cdrdao 1.2.5
+    (2023):
+    https://github.com/cdrdao/cdrdao/issues/32
+    https://github.com/whipper-team/whipper/issues/169
+
+    This function assumes cdrdao 1.2.5+ (2023) was used, which unless --no-utf8
+    is passed, provides UTF-8 strings. It also works with older versions as long
+    as the encoding was ASCII or Latin-1.
+
+    Note: CD-Text in MS-JIS produced by cdrdao <1.2.5 will produce mojibake
+    (garbled characters), just like the older code this function replaced.
+    """
+    return _STRING_SUBSTITUTIONS_RE.sub(_string_contents_repl,
+                                        str_within_quotes)
+
 
 # header
 _CATALOG_RE = re.compile(r'^CATALOG "(?P<catalog>\d+)"$')
@@ -208,11 +262,7 @@ def parse(self):
             m = _CDTEXT_CANDIDATE_RE.search(line)
             if m:
                 key = m.group('key')
-                value = m.group('value')
-                # usually, value is encoded with octal escapes and in latin-1
-                # FIXME: other encodings are possible, does cdrdao handle
-                # them ?
-                value = value.encode().decode('unicode_escape')
+                value = parse_toc_string(m.group('value'))
                 if key in table.CDTEXT_FIELDS:
                     # FIXME: consider ISRC separate for now, but this
                     # is a limitation of our parser approach

diff --git a/whipper/test/diorama.cue b/whipper/test/diorama.cue
@@ -0,0 +1,45 @@
+REM DISCID 700AC908
+REM COMMENT "whipper 0.10.1.dev27+ga4b9742.d20240827"
+PERFORMER "MØL"
+TITLE "Diorama"
+FILE "data.wav" WAVE
+  TRACK 01 AUDIO
+    PERFORMER "MØL"
+    TITLE "Fraktur"
+    ISRC DED832100085
+    INDEX 01 00:00:00
+  TRACK 02 AUDIO
+    PERFORMER "MØL"
+    TITLE "Photophobic"
+    ISRC DED832100086
+    INDEX 01 04:19:00
+  TRACK 03 AUDIO
+    PERFORMER "MØL"
+    TITLE "Serf"
+    ISRC DED832100087
+    INDEX 01 09:37:00
+  TRACK 04 AUDIO
+    PERFORMER "MØL"
+    TITLE "Vestige"
+    ISRC DED832100088
+    INDEX 01 14:59:12
+  TRACK 05 AUDIO
+    PERFORMER "MØL"
+    TITLE "Redacted"
+    ISRC DED832100089
+    INDEX 01 20:37:68
+  TRACK 06 AUDIO
+    PERFORMER "MØL"
+    TITLE "Itinerari"
+    ISRC DED832100090
+    INDEX 01 25:54:18
+  TRACK 07 AUDIO
+    PERFORMER "MØL"
+    TITLE "Tvesind"
+    ISRC DED832100091
+    INDEX 01 30:57:58
+  TRACK 08 AUDIO
+    PERFORMER "MØL"
+    TITLE "Diorama"
+    ISRC DED832100092
+    INDEX 01 38:46:57
diff --git a/whipper/test/diorama_noutf8.toc b/whipper/test/diorama_noutf8.toc
@@ -0,0 +1,134 @@
+CD_DA
+
+CD_TEXT {
+  LANGUAGE_MAP {
+    0: 9
+  }
+  LANGUAGE 0 {
+    TITLE "Diorama"
+    PERFORMER "M\330L"
+    SIZE_INFO { 0,  1,  8,  0,  7,  3,  0,  0,  0,  0,  0,  0,
+                0,  0,  0,  0,  0,  0,  0,  3, 12,  0,  0,  0,
+                0,  0,  0,  0,  9,  0,  0,  0,  0,  0,  0,  0}
+  }
+}
+
+// Track 1
+TRACK AUDIO
+NO COPY
+NO PRE_EMPHASIS
+TWO_CHANNEL_AUDIO
+ISRC "DED832100085"
+CD_TEXT {
+  LANGUAGE 0 {
+    TITLE "Fraktur"
+    PERFORMER "M\330L"
+  }
+}
+FILE "data.wav" 0 04:19:00
+
+
+// Track 2
+TRACK AUDIO
+NO COPY
+NO PRE_EMPHASIS
+TWO_CHANNEL_AUDIO
+ISRC "DED832100086"
+CD_TEXT {
+  LANGUAGE 0 {
+    TITLE "Photophobic"
+    PERFORMER "M\330L"
+  }
+}
+FILE "data.wav" 04:19:00 05:18:00
+
+
+// Track 3
+TRACK AUDIO
+NO COPY
+NO PRE_EMPHASIS
+TWO_CHANNEL_AUDIO
+ISRC "DED832100087"
+CD_TEXT {
+  LANGUAGE 0 {
+    TITLE "Serf"
+    PERFORMER "M\330L"
+  }
+}
+FILE "data.wav" 09:37:00 05:22:12
+
+
+// Track 4
+TRACK AUDIO
+NO COPY
+NO PRE_EMPHASIS
+TWO_CHANNEL_AUDIO
+ISRC "DED832100088"
+CD_TEXT {
+  LANGUAGE 0 {
+    TITLE "Vestige"
+    PERFORMER "M\330L"
+  }
+}
+FILE "data.wav" 14:59:12 05:38:56
+
+
+// Track 5
+TRACK AUDIO
+NO COPY
+NO PRE_EMPHASIS
+TWO_CHANNEL_AUDIO
+ISRC "DED832100089"
+CD_TEXT {
+  LANGUAGE 0 {
+    TITLE "Redacted"
+    PERFORMER "M\330L"
+  }
+}
+FILE "data.wav" 20:37:68 05:16:25
+
+
+// Track 6
+TRACK AUDIO
+NO COPY
+NO PRE_EMPHASIS
+TWO_CHANNEL_AUDIO
+ISRC "DED832100090"
+CD_TEXT {
+  LANGUAGE 0 {
+    TITLE "Itinerari"
+    PERFORMER "M\330L"
+  }
+}
+FILE "data.wav" 25:54:18 05:03:40
+
+
+// Track 7
+TRACK AUDIO
+NO COPY
+NO PRE_EMPHASIS
+TWO_CHANNEL_AUDIO
+ISRC "DED832100091"
+CD_TEXT {
+  LANGUAGE 0 {
+    TITLE "Tvesind"
+    PERFORMER "M\330L"
+  }
+}
+FILE "data.wav" 30:57:58 07:48:74
+
+
+// Track 10
+TRACK AUDIO
+NO COPY
+NO PRE_EMPHASIS
+TWO_CHANNEL_AUDIO
+ISRC "DED832100092"
+CD_TEXT {
+  LANGUAGE 0 {
+    TITLE "Diorama"
+    PERFORMER "M\330L"
+  }
+}
+FILE "data.wav" 38:46:57 07:14:36
+
diff --git a/whipper/test/diorama_utf8.toc b/whipper/test/diorama_utf8.toc
@@ -0,0 +1,134 @@
+CD_DA
+
+CD_TEXT {
+  LANGUAGE_MAP {
+    0: 9
+  }
+  LANGUAGE 0 {
+    TITLE "Diorama"
+    PERFORMER "MØL"
+    SIZE_INFO { 0,  1,  8,  0,  7,  3,  0,  0,  0,  0,  0,  0,
+                0,  0,  0,  0,  0,  0,  0,  3, 12,  0,  0,  0,
+                0,  0,  0,  0,  9,  0,  0,  0,  0,  0,  0,  0}
+  }
+}
+
+// Track 1
+TRACK AUDIO
+NO COPY
+NO PRE_EMPHASIS
+TWO_CHANNEL_AUDIO
+ISRC "DED832100085"
+CD_TEXT {
+  LANGUAGE 0 {
+    TITLE "Fraktur"
+    PERFORMER "MØL"
+  }
+}
+FILE "data.wav" 0 04:19:00
+
+
+// Track 2
+TRACK AUDIO
+NO COPY
+NO PRE_EMPHASIS
+TWO_CHANNEL_AUDIO
+ISRC "DED832100086"
+CD_TEXT {
+  LANGUAGE 0 {
+    TITLE "Photophobic"
+    PERFORMER "MØL"
+  }
+}
+FILE "data.wav" 04:19:00 05:18:00
+
+
+// Track 3
+TRACK AUDIO
+NO COPY
+NO PRE_EMPHASIS
+TWO_CHANNEL_AUDIO
+ISRC "DED832100087"
+CD_TEXT {
+  LANGUAGE 0 {
+    TITLE "Serf"
+    PERFORMER "MØL"
+  }
+}
+FILE "data.wav" 09:37:00 05:22:12
+
+
+// Track 4
+TRACK AUDIO
+NO COPY
+NO PRE_EMPHASIS
+TWO_CHANNEL_AUDIO
+ISRC "DED832100088"
+CD_TEXT {
+  LANGUAGE 0 {
+    TITLE "Vestige"
+    PERFORMER "MØL"
+  }
+}
+FILE "data.wav" 14:59:12 05:38:56
+
+
+// Track 5
+TRACK AUDIO
+NO COPY
+NO PRE_EMPHASIS
+TWO_CHANNEL_AUDIO
+ISRC "DED832100089"
+CD_TEXT {
+  LANGUAGE 0 {
+    TITLE "Redacted"
+    PERFORMER "MØL"
+  }
+}
+FILE "data.wav" 20:37:68 05:16:25
+
+
+// Track 6
+TRACK AUDIO
+NO COPY
+NO PRE_EMPHASIS
+TWO_CHANNEL_AUDIO
+ISRC "DED832100090"
+CD_TEXT {
+  LANGUAGE 0 {
+    TITLE "Itinerari"
+    PERFORMER "MØL"
+  }
+}
+FILE "data.wav" 25:54:18 05:03:40
+
+
+// Track 7
+TRACK AUDIO
+NO COPY
+NO PRE_EMPHASIS
+TWO_CHANNEL_AUDIO
+ISRC "DED832100091"
+CD_TEXT {
+  LANGUAGE 0 {
+    TITLE "Tvesind"
+    PERFORMER "MØL"
+  }
+}
+FILE "data.wav" 30:57:58 07:48:74
+
+
+// Track 8
+TRACK AUDIO
+NO COPY
+NO PRE_EMPHASIS
+TWO_CHANNEL_AUDIO
+ISRC "DED832100092"
+CD_TEXT {
+  LANGUAGE 0 {
+    TITLE "Diorama"
+    PERFORMER "MØL"
+  }
+}
+FILE "data.wav" 38:46:57 07:14:36
+