Use textpre.py instead of textpre.awk.

Makefile

@@ -1,6 +1,3 @@
-#gawk sort order
-export LC_CTYPE=C
-
 .SUFFIXES: .asm .tx .o .gbc
 
 TEXTFILES =	
@@ -11,7 +8,7 @@ pokecrystal.o: pokecrystal.asm main.tx constants.asm ${TEXTFILES}
 	rgbasm -o pokecrystal.o pokecrystal.asm
 	
 .asm.tx:
-	awk -f textpre.awk < $< > $@
+	python textpre.py < $< > $@
 
 pokecrystal.gbc: pokecrystal.o
 	rgblink -o $@ $<

main.asm

@@ -19,7 +19,7 @@ INCBIN "baserom.gbc",$20000,$4000
 SECTION "bank9",DATA,BANK[$9]
 INCBIN "baserom.gbc",$24000,$4000
 SECTION "bankA",DATA,BANK[$A]
-INCBIN "baserom.gbc",$28000,$$2A5e9 - $28000
+INCBIN "baserom.gbc",$28000,$2A5e9 - $28000
 
 	db $03,$02 ; Sprout Tower 2F
 	db $05,$05,$05 ; encounter rates: morn/day/nite

textpre.awk

@@ -1,302 +0,0 @@
-BEGIN {
-FS = "\""
-
-char["ガ"] = "$05"
-char["ギ"] = "$06"
-char["グ"] = "$07"
-char["ゲ"] = "$08"
-char["ゴ"] = "$09"
-char["ザ"] = "$0A"
-char["ジ"] = "$0B"
-char["ズ"] = "$0C"
-char["ゼ"] = "$0D"
-char["ゾ"] = "$0E"
-char["ダ"] = "$0F"
-char["ヂ"] = "$10"
-char["ヅ"] = "$11"
-char["デ"] = "$12"
-char["ド"] = "$13"
-char["バ"] = "$19"
-char["ビ"] = "$1A"
-char["ブ"] = "$1B"
-char["ボ"] = "$1C"
-char["が"] = "$26"
-char["ぎ"] = "$27"
-char["ぐ"] = "$28"
-char["げ"] = "$29"
-char["ご"] = "$2A"
-char["ざ"] = "$2B"
-char["じ"] = "$2C"
-char["ず"] = "$2D"
-char["ぜ"] = "$2E"
-char["ぞ"] = "$2F"
-char["だ"] = "$30"
-char["ぢ"] = "$31"
-char["づ"] = "$32"
-char["で"] = "$33"
-char["ど"] = "$34"
-char["ば"] = "$3A"
-char["び"] = "$3B"
-char["ぶ"] = "$3C"
-char["べ"] = "$3D"
-char["ぼ"] = "$3E"
-char["パ"] = "$40"
-char["ピ"] = "$41"
-char["プ"] = "$42"
-char["ポ"] = "$43"
-char["ぱ"] = "$44"
-char["ぴ"] = "$45"
-char["ぷ"] = "$46"
-char["ぺ"] = "$47"
-char["ぽ"] = "$48"
-char["ア"] = "$80"
-char["イ"] = "$81"
-char["ウ"] = "$82"
-char["エ"] = "$83"
-char["ォ"] = "$84"
-char["カ"] = "$85"
-char["キ"] = "$86"
-char["ク"] = "$87"
-char["ケ"] = "$88"
-char["コ"] = "$89"
-char["サ"] = "$8A"
-char["シ"] = "$8B"
-char["ス"] = "$8C"
-char["セ"] = "$8D"
-char["ソ"] = "$8E"
-char["タ"] = "$8F"
-char["チ"] = "$90"
-char["ツ"] = "$91"
-char["テ"] = "$92"
-char["ト"] = "$93"
-char["ナ"] = "$94"
-char["ニ"] = "$95"
-char["ヌ"] = "$96"
-char["ネ"] = "$97"
-char["ノ"] = "$98"
-char["ハ"] = "$99"
-char["ヒ"] = "$9A"
-char["フ"] = "$9B"
-char["ホ"] = "$9C"
-char["マ"] = "$9D"
-char["ミ"] = "$9E"
-char["ム"] = "$9F"
-char["メ"] = "$A0"
-char["モ"] = "$A1"
-char["ヤ"] = "$A2"
-char["ユ"] = "$A3"
-char["ヨ"] = "$A4"
-char["ラ"] = "$A5"
-char["ル"] = "$A6"
-char["レ"] = "$A7"
-char["ロ"] = "$A8"
-char["ワ"] = "$A9"
-char["ヲ"] = "$AA"
-char["ン"] = "$AB"
-char["ッ"] = "$AC"
-char["ャ"] = "$AD"
-char["ュ"] = "$AE"
-char["ョ"] = "$AF"
-char["ィ"] = "$B0"
-char["あ"] = "$B1"
-char["い"] = "$B2"
-char["う"] = "$B3"
-char["え"] = "$B4"
-char["お"] = "$B5"
-char["か"] = "$B6"
-char["き"] = "$B7"
-char["く"] = "$B8"
-char["け"] = "$B9"
-char["こ"] = "$BA"
-char["さ"] = "$BB"
-char["し"] = "$BC"
-char["す"] = "$BD"
-char["せ"] = "$BE"
-char["そ"] = "$BF"
-char["た"] = "$C0"
-char["ち"] = "$C1"
-char["つ"] = "$C2"
-char["て"] = "$C3"
-char["と"] = "$C4"
-char["な"] = "$C5"
-char["に"] = "$C6"
-char["ぬ"] = "$C7"
-char["ね"] = "$C8"
-char["の"] = "$C9"
-char["は"] = "$CA"
-char["ひ"] = "$CB"
-char["ふ"] = "$CC"
-char["へ"] = "$CD"
-char["ほ"] = "$CE"
-char["ま"] = "$CF"
-char["み"] = "$D0"
-char["む"] = "$D1"
-char["め"] = "$D2"
-char["も"] = "$D3"
-char["や"] = "$D4"
-char["ゆ"] = "$D5"
-char["よ"] = "$D6"
-char["ら"] = "$D7"
-char["り"] = "$D8"
-char["る"] = "$D9"
-char["れ"] = "$DA"
-char["ろ"] = "$DB"
-char["わ"] = "$DC"
-char["を"] = "$DD"
-char["ん"] = "$DE"
-char["っ"] = "$DF"
-char["ゃ"] = "$E0"
-char["ゅ"] = "$E1"
-char["ょ"] = "$E2"
-char["ー"] = "$E3"
-
-
-char["@"] = "$50"
-char["#"] = "$54"
-char["…"] = "$75"
-
-# textbox borders
-char["┌"] = "$79"
-char["─"] = "$7A"
-char["┐"] = "$7B"
-char["│"] = "$7C"
-char["└"] = "$7D"
-char["┘"] = "$7E"
-
-char["№"] = "$74"
-
-char[" "] = "$7F"
-char["A"] = "$80"
-char["B"] = "$81"
-char["C"] = "$82"
-char["D"] = "$83"
-char["E"] = "$84"
-char["F"] = "$85"
-char["G"] = "$86"
-char["H"] = "$87"
-char["I"] = "$88"
-char["J"] = "$89"
-char["K"] = "$8A"
-char["L"] = "$8B"
-char["M"] = "$8C"
-char["N"] = "$8D"
-char["O"] = "$8E"
-char["P"] = "$8F"
-char["Q"] = "$90"
-char["R"] = "$91"
-char["S"] = "$92"
-char["T"] = "$93"
-char["U"] = "$94"
-char["V"] = "$95"
-char["W"] = "$96"
-char["X"] = "$97"
-char["Y"] = "$98"
-char["Z"] = "$99"
-char["("] = "$9A"
-char[")"] = "$9B"
-char[":"] = "$9C"
-char[";"] = "$9D"
-char["["] = "$9E"
-char["]"] = "$9F"
-char["a"] = "$A0"
-char["b"] = "$A1"
-char["c"] = "$A2"
-char["d"] = "$A3"
-char["e"] = "$A4"
-char["f"] = "$A5"
-char["g"] = "$A6"
-char["h"] = "$A7"
-char["i"] = "$A8"
-char["j"] = "$A9"
-char["k"] = "$AA"
-char["l"] = "$AB"
-char["m"] = "$AC"
-char["n"] = "$AD"
-char["o"] = "$AE"
-char["p"] = "$AF"
-char["q"] = "$B0"
-char["r"] = "$B1"
-char["s"] = "$B2"
-char["t"] = "$B3"
-char["u"] = "$B4"
-char["v"] = "$B5"
-char["w"] = "$B6"
-char["x"] = "$B7"
-char["y"] = "$B8"
-char["z"] = "$B9"
-char["é"] = "$BA"
-char["'t"] = "$BE"
-char["'s"] = "$D4"
-char["'"] = "$E0"
-char["-"] = "$E3"
-char["?"] = "$E6"
-char["!"] = "$E7"
-char["."] = "$E8"
-char["&"] = "$E9"
-char["♂"] = "$EF"
-char["/"] = "$F3"
-char[","] = "$F4"
-char["♀"] = "$F5"
-char["0"] = "$F6"
-char["1"] = "$F7"
-char["2"] = "$F8"
-char["3"] = "$F9"
-char["4"] = "$FA"
-char["5"] = "$FB"
-char["6"] = "$FC"
-char["7"] = "$FD"
-char["8"] = "$FE"
-char["9"] = "$FF"
-}
-
-# skip lines that actually do use ASCII in quotes
-tolower($1) ~ /section/ ||
-tolower($1) ~ /include/ || 
-tolower($1) ~ /incbin/
-
-!(tolower($1) ~ /section/ || tolower($1) ~ /include/ || tolower($1) ~ /incbin/) {
-i = 1
-ORS = ""
-
-while (i <= NF) {
-if (i % 2 == 1)
-	print $(i)
-else {
-	f = $(i)
-	while (f != "") {
-		c = substr(f,1,1)
-		f = substr(f,2,length(f) - 1)
-		if (c > "𐀀") { # U+10000
-			c = c substr(f,1,3)
-			f = substr(f,4,length(f) - 3)
-		} else if (c > "ࠀ") { # U+0800
-			c = c substr(f,1,2)
-			f = substr(f,3,length(f) - 2)
-		} else if (c > "€") { # U+0080
-			c = c substr(f,1,1)
-			f = substr(f,2,length(f) - 1)
-		}
-
-		if (c == "'") {
-			if (substr(f,1,1) == "m" ||
-			    substr(f,1,1) == "r" ||
-			    substr(f,1,1) == "t" ||
-			    substr(f,1,1) == "s" ||
-			    substr(f,1,1) == "v" ||
-			    substr(f,1,1) == "l") {
-				c = c substr(f,1,1)
-				f = substr(f,2,length(f) - 1)
-			}
-		}
-
-		print char[c]
-		if (length(f))
-			print ","
-	}
-}
-
-i = i + 1
-}
-print "\n"
-ORS = "\n"
-}

textpre.py

@@ -0,0 +1,341 @@
+#!/usr/bin/python
+# -*- coding: utf-8 -*-
+
+import sys
+
+chars = {}
+chars["ガ"] = "$05"
+chars["ギ"] = "$06"
+chars["グ"] = "$07"
+chars["ゲ"] = "$08"
+chars["ゴ"] = "$09"
+chars["ザ"] = "$0A"
+chars["ジ"] = "$0B"
+chars["ズ"] = "$0C"
+chars["ゼ"] = "$0D"
+chars["ゾ"] = "$0E"
+chars["ダ"] = "$0F"
+chars["ヂ"] = "$10"
+chars["ヅ"] = "$11"
+chars["デ"] = "$12"
+chars["ド"] = "$13"
+chars["バ"] = "$19"
+chars["ビ"] = "$1A"
+chars["ブ"] = "$1B"
+chars["ボ"] = "$1C"
+chars["が"] = "$26"
+chars["ぎ"] = "$27"
+chars["ぐ"] = "$28"
+chars["げ"] = "$29"
+chars["ご"] = "$2A"
+chars["ざ"] = "$2B"
+chars["じ"] = "$2C"
+chars["ず"] = "$2D"
+chars["ぜ"] = "$2E"
+chars["ぞ"] = "$2F"
+chars["だ"] = "$30"
+chars["ぢ"] = "$31"
+chars["づ"] = "$32"
+chars["で"] = "$33"
+chars["ど"] = "$34"
+chars["ば"] = "$3A"
+chars["び"] = "$3B"
+chars["ぶ"] = "$3C"
+chars["べ"] = "$3D"
+chars["ぼ"] = "$3E"
+chars["パ"] = "$40"
+chars["ピ"] = "$41"
+chars["プ"] = "$42"
+chars["ポ"] = "$43"
+chars["ぱ"] = "$44"
+chars["ぴ"] = "$45"
+chars["ぷ"] = "$46"
+chars["ぺ"] = "$47"
+chars["ぽ"] = "$48"
+chars["ア"] = "$80"
+chars["イ"] = "$81"
+chars["ウ"] = "$82"
+chars["エ"] = "$83"
+chars["ォ"] = "$84"
+chars["カ"] = "$85"
+chars["キ"] = "$86"
+chars["ク"] = "$87"
+chars["ケ"] = "$88"
+chars["コ"] = "$89"
+chars["サ"] = "$8A"
+chars["シ"] = "$8B"
+chars["ス"] = "$8C"
+chars["セ"] = "$8D"
+chars["ソ"] = "$8E"
+chars["タ"] = "$8F"
+chars["チ"] = "$90"
+chars["ツ"] = "$91"
+chars["テ"] = "$92"
+chars["ト"] = "$93"
+chars["ナ"] = "$94"
+chars["ニ"] = "$95"
+chars["ヌ"] = "$96"
+chars["ネ"] = "$97"
+chars["ノ"] = "$98"
+chars["ハ"] = "$99"
+chars["ヒ"] = "$9A"
+chars["フ"] = "$9B"
+chars["ホ"] = "$9C"
+chars["マ"] = "$9D"
+chars["ミ"] = "$9E"
+chars["ム"] = "$9F"
+chars["メ"] = "$A0"
+chars["モ"] = "$A1"
+chars["ヤ"] = "$A2"
+chars["ユ"] = "$A3"
+chars["ヨ"] = "$A4"
+chars["ラ"] = "$A5"
+chars["ル"] = "$A6"
+chars["レ"] = "$A7"
+chars["ロ"] = "$A8"
+chars["ワ"] = "$A9"
+chars["ヲ"] = "$AA"
+chars["ン"] = "$AB"
+chars["ッ"] = "$AC"
+chars["ャ"] = "$AD"
+chars["ュ"] = "$AE"
+chars["ョ"] = "$AF"
+chars["ィ"] = "$B0"
+chars["あ"] = "$B1"
+chars["い"] = "$B2"
+chars["う"] = "$B3"
+chars["え"] = "$B4"
+chars["お"] = "$B5"
+chars["か"] = "$B6"
+chars["き"] = "$B7"
+chars["く"] = "$B8"
+chars["け"] = "$B9"
+chars["こ"] = "$BA"
+chars["さ"] = "$BB"
+chars["し"] = "$BC"
+chars["す"] = "$BD"
+chars["せ"] = "$BE"
+chars["そ"] = "$BF"
+chars["た"] = "$C0"
+chars["ち"] = "$C1"
+chars["つ"] = "$C2"
+chars["て"] = "$C3"
+chars["と"] = "$C4"
+chars["な"] = "$C5"
+chars["に"] = "$C6"
+chars["ぬ"] = "$C7"
+chars["ね"] = "$C8"
+chars["の"] = "$C9"
+chars["は"] = "$CA"
+chars["ひ"] = "$CB"
+chars["ふ"] = "$CC"
+chars["へ"] = "$CD"
+chars["ほ"] = "$CE"
+chars["ま"] = "$CF"
+chars["み"] = "$D0"
+chars["む"] = "$D1"
+chars["め"] = "$D2"
+chars["も"] = "$D3"
+chars["や"] = "$D4"
+chars["ゆ"] = "$D5"
+chars["よ"] = "$D6"
+chars["ら"] = "$D7"
+chars["り"] = "$D8"
+chars["る"] = "$D9"
+chars["れ"] = "$DA"
+chars["ろ"] = "$DB"
+chars["わ"] = "$DC"
+chars["を"] = "$DD"
+chars["ん"] = "$DE"
+chars["っ"] = "$DF"
+chars["ゃ"] = "$E0"
+chars["ゅ"] = "$E1"
+chars["ょ"] = "$E2"
+chars["ー"] = "$E3"
+
+
+chars["@"] = "$50"
+chars["#"] = "$54"
+chars["…"] = "$75"
+
+# textbox borders
+chars["┌"] = "$79"
+chars["─"] = "$7A"
+chars["┐"] = "$7B"
+chars["│"] = "$7C"
+chars["└"] = "$7D"
+chars["┘"] = "$7E"
+
+chars["№"] = "$74"
+
+chars[" "] = "$7F"
+chars["A"] = "$80"
+chars["B"] = "$81"
+chars["C"] = "$82"
+chars["D"] = "$83"
+chars["E"] = "$84"
+chars["F"] = "$85"
+chars["G"] = "$86"
+chars["H"] = "$87"
+chars["I"] = "$88"
+chars["J"] = "$89"
+chars["K"] = "$8A"
+chars["L"] = "$8B"
+chars["M"] = "$8C"
+chars["N"] = "$8D"
+chars["O"] = "$8E"
+chars["P"] = "$8F"
+chars["Q"] = "$90"
+chars["R"] = "$91"
+chars["S"] = "$92"
+chars["T"] = "$93"
+chars["U"] = "$94"
+chars["V"] = "$95"
+chars["W"] = "$96"
+chars["X"] = "$97"
+chars["Y"] = "$98"
+chars["Z"] = "$99"
+chars["("] = "$9A"
+chars[")"] = "$9B"
+chars[":"] = "$9C"
+chars[";"] = "$9D"
+chars["["] = "$9E"
+chars["]"] = "$9F"
+chars["a"] = "$A0"
+chars["b"] = "$A1"
+chars["c"] = "$A2"
+chars["d"] = "$A3"
+chars["e"] = "$A4"
+chars["f"] = "$A5"
+chars["g"] = "$A6"
+chars["h"] = "$A7"
+chars["i"] = "$A8"
+chars["j"] = "$A9"
+chars["k"] = "$AA"
+chars["l"] = "$AB"
+chars["m"] = "$AC"
+chars["n"] = "$AD"
+chars["o"] = "$AE"
+chars["p"] = "$AF"
+chars["q"] = "$B0"
+chars["r"] = "$B1"
+chars["s"] = "$B2"
+chars["t"] = "$B3"
+chars["u"] = "$B4"
+chars["v"] = "$B5"
+chars["w"] = "$B6"
+chars["x"] = "$B7"
+chars["y"] = "$B8"
+chars["z"] = "$B9"
+chars["Ä"] = "$C0"
+chars["Ö"] = "$C1"
+chars["Ü"] = "$C2"
+chars["ä"] = "$C3"
+chars["ö"] = "$C4"
+chars["ü"] = "$C5"
+chars["'d"] = "$D0"
+chars["'l"] = "$D1"
+chars["'m"] = "$D2"
+chars["'r"] = "$D3"
+chars["'s"] = "$D4"
+chars["'t"] = "$D5"
+chars["'v"] = "$D6"
+chars["'"] = "$E0"
+chars["-"] = "$E3"
+chars["?"] = "$E6"
+chars["!"] = "$E7"
+chars["."] = "$E8"
+chars["&"] = "$E9"
+chars["é"] = "$EA"
+chars["→"] = "$EB"
+chars["♂"] = "$EF"
+chars["¥"] = "$F0"
+chars["×"] = "$F1"
+chars["/"] = "$F3"
+chars[","] = "$F4"
+chars["♀"] = "$F5"
+chars["0"] = "$F6"
+chars["1"] = "$F7"
+chars["2"] = "$F8"
+chars["3"] = "$F9"
+chars["4"] = "$FA"
+chars["5"] = "$FB"
+chars["6"] = "$FC"
+chars["7"] = "$FD"
+chars["8"] = "$FE"
+chars["9"] = "$FF"
+
+for l in sys.stdin:
+
+    # strip comments
+    line = l.partition(";")
+    i = 0
+    asm = ""
+    while i < len(line) and l[0] != ";":
+        asm = asm + line[i]
+        i = i + 1
+
+    # skip asm with no quotes
+    if "\"" not in asm:
+        sys.stdout.write(l)
+        continue
+
+    # split by quotes
+    asms = asm.split("\"")
+
+    # skip asm that actually does use ASCII in quotes
+    lowasm = asms[0].lower()
+    if "section" in lowasm \
+    or "include" in lowasm \
+    or "incbin" in lowasm:
+        sys.stdout.write(l)
+        continue
+
+    even = False
+    i = 0
+    for token in asms:
+        i = i + 1
+        if even:
+            # token is a string to convert to byte values
+
+            while len(token):
+                # read a single UTF-8 codepoint
+                char = token[0]
+                if ord(char) >= 0xFC:
+                    char = char + token[1:6]
+                    token = token[6:]
+                elif ord(char) >= 0xF8:
+                    char = char + token[1:5]
+                    token = token[5:]
+                elif ord(char) >= 0xF0:
+                    char = char + token[1:4]
+                    token = token[4:]
+                elif ord(char) >= 0xE0:
+                    char = char + token[1:3]
+                    token = token[3:]
+                elif ord(char) >= 0xC0:
+                    char = char + token[1:2]
+                    token = token[2:]
+                else:
+                    token = token[1:]
+
+                    # certain apostrophe-letter pairs are only a single byte
+                    if char == "'" and \
+                        (token[0] == "d" or \
+                         token[0] == "l" or \
+                         token[0] == "m" or \
+                         token[0] == "r" or \
+                         token[0] == "s" or \
+                         token[0] == "t" or \
+                         token[0] == "v"):
+                        char = char + token[0]
+                        token = token[1:]
+
+                sys.stdout.write(chars[char])
+
+                if len(token):
+                    sys.stdout.write(", ")
+
+        else:
+            sys.stdout.write(token)
+        even = not even