Fix so can build iso-8859-2 Polish dicts using make (won't work on

BYOD yet): add encoding to emacs mode line and fix the letters,
including hard-coding them as decimal numbers until I can figure out
how to get perl (in xloc.pm) to emit iso-8859-2 instead of utf8.
This commit is contained in:
ehouse 2009-03-14 19:27:29 +00:00
parent 121b8253cf
commit f0ccaa92bc
2 changed files with 54 additions and 44 deletions

View file

@ -1,5 +1,6 @@
# -*-mode: Makefile -*-
# Copyright 2002 by Eric House (xwords@eehouse.org). All rights reserved.
# -*- coding: iso-8859-2; mode: Makefile; -*-
# Copyright 2002 - 2009 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
@ -17,16 +18,24 @@
XWLANG=Polish
LANGCODE=pl_PL
ENC = ISO-8859-2
TARGET_TYPE ?= FRANK
# DICT2DAWGARGS = -lang $(LANGCODE)
# DICT2DAWGARGS = -debug
TARGET_TYPE ?= WINCE
include ../Makefile.2to8
include ../Makefile.langcommon
$(XWLANG)Main.dict.gz: slowa.txt.gz
zcat $< | tr -d '\r' | tr [a-z±æê³ñ󶼿] [A-Z¡ÆÊ£ÑÓ¦¬¯] | \
grep '^[A-PR-UWYZ¡ÆÊ£ÑÓ¦¬¯]*$$' | gzip >$@
SOURCEDICT ?= $(XWDICTPATH)/Polish/iso-8859-2/slowa.txt.gz
$(XWLANG)Main.dict.gz: $(SOURCEDICT)
zcat $< | tr -d '\r' \
| LANG=$(LANGCODE):$(ENC) tr [a帳c熛e璒ghijkl軛n隳鏕rs鈣uwyz撚] [A、C鑪E甪GHIJKLΚN埆紞RS吋UWYZ炫] \
| LANG=$(LANGCODE):$(ENC) grep '^[A、C鑪E甪GHIJKLΚN埆紞RS吋UWYZ炫]*$$' \
| gzip > $@
# Everything but creating of the Main.dict file is inherited from the
# "parent" Makefile.langcommon in the parent directory.

View file

@ -1,5 +1,6 @@
# -*- mode: conf; -*-
# Copyright 2002 by Eric House (xwords@eehouse.org). All rights reserved.
# -*- coding: iso-8859-2; mode: conf; -*-
# Copyright 2002-2009 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
@ -22,8 +23,8 @@ CHARSET:iso-8859-2
# deal with DOS files
LANGFILTER_PRECLIP: tr -d '\r' |
LANGFILTER_POSTCLIP: | tr [a-z±æê³ñ󶼿] [A-Z¡ÆÊ£ÑÓ¦¬¯]
LANGFILTER_POSTCLIP: | grep '^[A-PR-UWYZ¡ÆÊ£ÑÓ¦¬¯]*$'
LANGFILTER_POSTCLIP: | tr [a-z] [A-Z]
LANGFILTER_POSTCLIP: | grep '^[A-Z]*$'
LANGFILTER_POSTCLIP: | tr '\n' '\000'
NEEDSSORT:true
@ -39,7 +40,7 @@ LANGINFO: href="mailto:xwords@eehouse.org">me</a> know so that I can get
LANGINFO: this working.</p>
LANGINFO: <p>Note that the blank is the last tile here, while with all
LANGINFO: other languages it's the first.</p>
LANGINFO: other languages it&apos;s the first.</p>
LANGINFO: <p>Also, please note that we currently require the files you
LANGINFO: upload to use the iso-8859-2 character encoding.</p>
@ -48,40 +49,40 @@ LANGINFO: upload to use the iso-8859-2 character encoding.</p>
# Polish==8. Low byte is padding
XLOC_HEADER:0x8800
<BEGIN_TILES>
9 1 'A'
1 5 '¡'
2 3 'B'
3 2 'C'
1 6 'Æ'
3 2 'D'
7 1 'E'
1 5 'Ê'
1 5 'F'
2 3 'G'
2 3 'H'
8 1 'I'
2 3 'J'
3 2 'K'
3 2 'L'
2 3 '£'
3 2 'M'
5 1 'N'
1 7 'Ñ'
6 1 'O'
1 5 'Ó'
3 2 'P'
4 1 'R'
4 1 'S'
1 5 '¦'
3 2 'T'
2 3 'U'
4 1 'W'
4 2 'Y'
5 1 'Z'
1 9 '¬'
1 5 '¯'
9 1 'A'
1 5 161 # '¡'
2 3 'B'
3 2 'C'
1 6 198 # 'Æ'
3 2 'D'
7 1 'E'
1 5 202 # 'Ê'
1 5 'F'
2 3 'G'
2 3 'H'
8 1 'I'
2 3 'J'
3 3 'K'
3 2 'L'
2 3 163 # '£'
3 2 'M'
5 1 'N'
1 7 209 # 'Ñ'
6 1 'O'
1 5 211 # 'Ó'
3 2 'P'
4 1 'R'
4 1 'S'
1 5 166 # '¦'
3 2 'T'
2 3 'U'
4 1 'W'
4 2 'Y'
5 1 'Z'
1 9 172 # '¬'
1 5 175 # '¯'
# the blank *must* be last here!!!
2 0 {"_"}
<END_TILES>