From 39ebe329758f47efe7696c77db838d8882430c92 Mon Sep 17 00:00:00 2001
From: Dietrich Epp <depp@zdome.net>
Date: Fri, 1 Apr 2022 12:17:43 -0400
Subject: [PATCH] Extract hexadecimal constants from enums

---
 scripts/encoding.csv | 77 ++++++++++++++++++++++++++++++++++++++++++++
 scripts/extract.py   | 10 +++---
 2 files changed, 82 insertions(+), 5 deletions(-)

diff --git a/scripts/encoding.csv b/scripts/encoding.csv
index b3a77a9..1727191 100644
--- a/scripts/encoding.csv
+++ b/scripts/encoding.csv
@@ -39,3 +39,80 @@ kTextEncodingMacRomanian,38
 kTextEncodingMacCeltic,39
 kTextEncodingMacGaelic,40
 kTextEncodingMacKeyboardGlyphs,41
+kTextEncodingMacRSymbol,8
+kTextEncodingMacUninterp,32
+kTextEncodingMacUkrainian,152
+kTextEncodingUnicodeDefault,256
+kTextEncodingUnicodeV1_1,257
+kTextEncodingISO10646_1993,257
+kTextEncodingUnicodeV2_0,259
+kTextEncodingUnicodeV2_1,259
+kTextEncodingUnicodeV3_0,260
+kTextEncodingUnicodeV3_1,261
+kTextEncodingUnicodeV3_2,262
+kTextEncodingISOLatin1,513
+kTextEncodingISOLatin2,514
+kTextEncodingISOLatin3,515
+kTextEncodingISOLatin4,516
+kTextEncodingISOLatinCyrillic,517
+kTextEncodingISOLatinArabic,518
+kTextEncodingISOLatinGreek,519
+kTextEncodingISOLatinHebrew,520
+kTextEncodingISOLatin5,521
+kTextEncodingDOSLatinUS,1024
+kTextEncodingDOSGreek,1029
+kTextEncodingDOSBalticRim,1030
+kTextEncodingDOSLatin1,1040
+kTextEncodingDOSGreek1,1041
+kTextEncodingDOSLatin2,1042
+kTextEncodingDOSCyrillic,1043
+kTextEncodingDOSTurkish,1044
+kTextEncodingDOSPortuguese,1045
+kTextEncodingDOSIcelandic,1046
+kTextEncodingDOSHebrew,1047
+kTextEncodingDOSCanadianFrench,1048
+kTextEncodingDOSArabic,1049
+kTextEncodingDOSJapanese,1056
+kTextEncodingDOSChineseSimplif,1057
+kTextEncodingDOSKorean,1058
+kTextEncodingDOSChineseTrad,1059
+kTextEncodingWindowsLatin1,1280
+kTextEncodingWindowsANSI,1280
+kTextEncodingWindowsLatin2,1281
+kTextEncodingWindowsCyrillic,1282
+kTextEncodingWindowsGreek,1283
+kTextEncodingWindowsLatin5,1284
+kTextEncodingWindowsHebrew,1285
+kTextEncodingWindowsArabic,1286
+kTextEncodingWindowsBalticRim,1287
+kTextEncodingWindowsVietnamese,1288
+kTextEncodingWindowsKoreanJohab,1296
+kTextEncodingUS_ASCII,1536
+kTextEncodingJIS_X0201_76,1568
+kTextEncodingJIS_X0208_83,1569
+kTextEncodingJIS_X0208_90,1570
+kTextEncodingJIS_X0212_90,1571
+kTextEncodingJIS_C6226_78,1572
+kTextEncodingGB_2312_80,1584
+kTextEncodingGBK_95,1585
+kTextEncodingKSC_5601_87,1600
+kTextEncodingKSC_5601_92_Johab,1601
+kTextEncodingCNS_11643_92_P1,1617
+kTextEncodingCNS_11643_92_P2,1618
+kTextEncodingCNS_11643_92_P3,1619
+kTextEncodingISO_2022_JP,2080
+kTextEncodingISO_2022_JP_2,2081
+kTextEncodingISO_2022_JP_1,2082
+kTextEncodingISO_2022_CN,2096
+kTextEncodingISO_2022_CN_EXT,2097
+kTextEncodingISO_2022_KR,2112
+kTextEncodingEUC_JP,2336
+kTextEncodingEUC_CN,2352
+kTextEncodingEUC_TW,2353
+kTextEncodingEUC_KR,2368
+kTextEncodingDefaultVariant,0
+kTextEncodingDefaultFormat,0
+kTextEncodingFullName,0
+kTextEncodingBaseName,1
+kTextEncodingVariantName,2
+kTextEncodingFormatName,3
diff --git a/scripts/extract.py b/scripts/extract.py
index 58f9633..efc1e0d 100644
--- a/scripts/extract.py
+++ b/scripts/extract.py
@@ -12,9 +12,11 @@ def list_enums(filename: str) -> Iterator[Item]:
     """List enum definitions in a file."""
     with open(filename, 'rb') as fp:
         data = fp.read()
-    for item in re.finditer(rb'^\s*(\w+)\s*=\s*(\d+)', data, re.MULTILINE):
+    for item in re.finditer(
+            rb'^\s*(\w+)\s*=\s*((?:0x)?\d+)u?l?\b',
+            data, re.MULTILINE | re.IGNORECASE):
         name, value = item.groups()
-        yield name.decode('ASCII'), int(value)
+        yield name.decode('ASCII'), int(value, 0)
 
 def index_of(data: List[Item], key: str) -> int:
     for i, (name, _) in enumerate(data):
@@ -49,9 +51,7 @@ def process_textcommon(filename: str) -> None:
     for name, value in list_enums(filename):
         if name.startswith('kTextEncoding'):
             encodings.append((name, value))
-    write_csv('encoding.csv',
-              slice(encodings, 'kTextEncodingMacRoman',
-                    'kTextEncodingMacKeyboardGlyphs'))
+    write_csv('encoding.csv', encodings)
 
 def process(filename: str) -> None:
     name = os.path.basename(filename).lower()