add 21x21 info for German

xwords4/dawg/German/Makefile

@@ -1 +1 @@
-Makefile.sf
+Makefile.Deutsch2022

xwords4/dawg/German/Makefile.Deutsch2022

@@ -0,0 +1,45 @@
+# -*- mode: makefile; coding: utf-8; -*-
+# Copyright 2002 - 2023 by Eric House (xwords@eehouse.org).  All
+# rights reserved.
+#
+# This program is free software; you can redistribute it and/or
+# modify it under the terms of the GNU General Public License
+# as published by the Free Software Foundation; either version 2
+# of the License, or (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with this program; if not, write to the Free Software
+# Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA  02111-1307, USA.
+
+XWLANG = Deutsch2022
+LANGCODE = de_DE
+ENC = UTF-8
+DICTNOTE = "Contributed by a user"
+
+TARGET_TYPE ?= WINCE
+
+include ../Makefile.langcommon
+
+SOURCEDICT ?= $(XWDICTPATH)/German/Deutsch2022.txt
+
+$(XWLANG)Main.dict.gz: $(SOURCEDICT) Makefile
+	file -z $(SOURCEDICT) | grep -q 'UTF-8 text' || exit 1
+	cat $< \
+		| sed 's,.,\U\0,g' \
+		| sed -e 's/ß/SS/g' \
+		| grep '^[AÄBCDEFGHIJKLMNOÖPQRSTUÜVWXYZ]*$$' \
+		| gzip -c > $@
+
+# Everything but creating of the Main.dict file is inherited from the
+# "parent" Makefile.langcommon in the parent directory.
+
+clean: clean_common
+	rm -f $(XWLANG)Main.dict.gz *.bin $(XWLANG)*.pdb $(XWLANG)*.seb
+
+help:
+	@echo 'make [SOURCEDICT=HansGerman.dict.gz|deutsch.dict.gz]'

xwords4/dawg/German/info.txt

@@ -47,36 +47,38 @@ LANGINFO: contain letters not found on tiles.</p>
 # German==3.  Low byte is padding
 XLOC_HEADER:0x8300
 
+COUNT_SIZES: 15 21
+
 <BEGIN_TILES>
-{"_"}    0		2
-'A|a'    1		5
-'Ä|ä'    6		1
-'B|b'    3		2
-'C|c'    4		2
-'D|d'    1		4
-'E|e'    1		15
-'F|f'    4		2
-'G|g'    2		3
-'H|h'    2		4
-'I|i'    1		6
-'J|j'    6		1
-'K|k'    4		2
-'L|l'    2		3
-'M|m'    3		4
-'N|n'    1		9
-'O|o'    2		3
-'Ö|ö'    8		1
-'P|p'    4		1
-'Q|q'    10		1
-'R|r'    1		6
-'S|s'    1		7
-'T|t'    1		6
-'U|u'    1		6
-'Ü|ü'    6		1
-'V|v'    6		1
-'W|w'    3		1
-'X|x'    8		1
-'Y|y'    10		1
-'Z|z'    3		1
+{"_"}    0    2   4
+'A|a'    1    5  10
+'Ä|ä'    6    1   2
+'B|b'    3    2   4
+'C|c'    4    2   4
+'D|d'    1    4   8
+'E|e'    1   15  29
+'F|f'    4    2   4
+'G|g'    2    3   6
+'H|h'    2    4   8
+'I|i'    1    6   11
+'J|j'    6    1   2
+'K|k'    4    2   4
+'L|l'    2    3   6
+'M|m'    3    4   8
+'N|n'    1    9  17
+'O|o'    2    3   6
+'Ö|ö'    8    1   2
+'P|p'    4    1   2
+'Q|q'   10    1   2
+'R|r'    1    6  11
+'S|s'    1    7  14
+'T|t'    1    6  12
+'U|u'    1    6  12
+'Ü|ü'    6    1   2
+'V|v'    6    1   2
+'W|w'    3    1   2
+'X|x'    8    1   2
+'Y|y'   10    1   2
+'Z|z'    3    1   2
 <END_TILES>
 # should ignore all after the <END_TILES> above

xwords4/dawg/dictstats.py

@@ -54,13 +54,12 @@ def main():
         line = line.strip()
 
         length = len(line)
-        # if not length in wordSizeCounts: wordSizeCounts[length] = 0
         wordSizeCounts[length] += 1
         wordCount += 1
 
         for letter in line:
             ii = ord(letter)
-            assert ii > 32 or ii < 4 or ii == 0, 'letter {} out of range'.format(ii)
+            assert ii > 32 or ii < 4 or ii == 0, 'letter {} in word {} out of range'.format(ii, line)
             if not letter in letters: letters[letter] = Letter(letter)
             letters[letter].increment()
             letterCount += 1