Improved pt_PT spell file generation.

This commit is contained in:
Bram Moolenaar
2010-08-10 22:53:02 +02:00
parent d70b2a8355
commit 0ee8df9ce5
3 changed files with 75 additions and 67 deletions

View File

@ -14,15 +14,15 @@ FILES = pt_PT.aff pt_PT.dic
#
# Fetching the pt_PT files from the Natura project.
#
PT_DIR = http://natura.di.uminho.pt/download/sources/Dictionaries/myspell
PT_FNAME = myspell.pt-latest.zip
:attr {fetch = $PT_DIR/%file%} $PT_FNAME
PT_FNAME = oo3x-pt-PT.oxt
PT_DIR = http://extensions.services.openoffice.org/e-files/1196/5/$(PT_FNAME)
:attr {fetch = $PT_DIR} $PT_FNAME
#
# Fetching the pt_BR files from BrOffice.org (Brazilian OOo).
#
BR_FNAME = pt_BR-V.zip
BR_DIR = http://www.deso-se.com.br/downloads/broffice.org/$(BR_FNAME)
BR_FNAME = Vero_pt_BR_V207AOC.oxt
BR_DIR = http://www.broffice.org/files/$(BR_FNAME)
:attr {fetch = $BR_DIR} $BR_FNAME
all: $SPELLDIR/pt.latin1.spl $SPELLDIR/pt.utf-8.spl \
@ -50,11 +50,17 @@ pt_PT.aff pt_PT.dic: {buildcheck=}
:fetch $PT_FNAME
:sys $UNZIP $PT_FNAME
:delete $PT_FNAME
:move myspell.pt-*/pt_PT.dic .
:move myspell.pt-*/pt_PT.aff .
:move myspell.pt-*/README_pt_PT.txt .
:move myspell.pt-*/COPYING COPYING_pt_PT.txt
:deldir myspell.pt-*
:move dictionaries/pt_PT.dic .
:move dictionaries/pt_PT.aff .
:move dictionaries/README_pt_PT.txt .
:move dictionaries/COPYING COPYING_pt_PT.txt
:delete {r}{f} dictionaries
:delete {r}{f} META-INF
:delete {f} description.xml
:delete {f} dictionaries.xcu
:delete {f} LICENSES.txt
:sys $VIM pt_PT.dic -u NONE -e -c "%s/\t.*//" -c update -c q
:sys $VIM pt_PT.aff -u NONE -e -c "%s/\S\+=\S\+$$//" -c update -c q
@if not os.path.exists('pt_PT.orig.aff'):
:copy pt_PT.aff pt_PT.orig.aff
@if not os.path.exists('pt_PT.orig.dic'):
@ -67,13 +73,11 @@ pt_BR.aff pt_BR.dic: {buildcheck=}
:fetch $BR_FNAME
:sys $UNZIP $BR_FNAME
:delete $BR_FNAME
:sys $VIM README_pt_BR.TXT -u NONE -e -c "set ff=unix" -c update -c q
:sys $VIM README_pt_BR.TXT -u NONE -N -e -c "set ff=unix" -c update -c q
:move README_pt_BR.TXT README_pt_BR.txt
# Vim seems to ignore the dots from the word list.
# Removing words with dot to avoid misbehaviour.
:sys $VIM pt_BR.dic -u NONE -e -c "set ff=unix" -c "/\./d" -c update -c q
:sys $VIM pt_BR.aff -u NONE -e -c "set ff=unix" -c update -c q
:sys $VIM pt_BR.dic -u NONE -N -e -c "set ff=unix" -c update -c q
:sys $VIM pt_BR.aff -u NONE -N -e -c "set ff=unix" -c update -c q
@if not os.path.exists('pt_BR.orig.aff'):
:copy pt_BR.aff pt_BR.orig.aff
@if not os.path.exists('pt_BR.orig.dic'):
@ -92,6 +96,23 @@ diff:
:sys {force} diff -a -C 1 pt_BR.orig.aff pt_BR.aff >pt_BR.diff
:sys {force} diff -a -C 1 pt_BR.orig.dic pt_BR.dic >>pt_BR.diff
# Delete all downloaded and generated files.
clean: clean_pt_BR clean_pt_PT
clean_pt_BR:
:delete {f} pt_BR.aff
:delete {f} pt_BR.dic
:delete {f} pt_BR.orig.aff
:delete {f} pt_BR.orig.dic
:delete {f} README_pt_BR.txt
clean_pt_PT:
:delete {f} pt_PT.aff
:delete {f} pt_PT.dic
:delete {f} pt_PT.orig.aff
:delete {f} pt_PT.orig.dic
:delete {f} README_pt_PT.txt
:delete {f} COPYING_pt_PT.txt
# Check for updated OpenOffice spell files. When there are changes the
# ".new.aff" and ".new.dic" files are left behind for manual inspection.

View File

@ -1,5 +1,5 @@
*** pt_BR.orig.aff 2008-02-21 19:41:04.000000000 -0300
--- pt_BR.aff 2008-02-24 11:08:15.000000000 -0300
*** pt_BR.orig.aff 2010-05-15 13:03:45.000000000 +0200
--- pt_BR.aff 2010-05-15 13:03:45.000000000 +0200
***************
*** 1,3 ****
SET ISO8859-1

View File

@ -1,58 +1,45 @@
*** pt_PT.orig.aff 2008-02-21 19:40:49.000000000 -0300
--- pt_PT.aff 2008-02-24 11:14:39.000000000 -0300
*** pt_PT.orig.aff 2010-08-10 22:36:56.000000000 +0200
--- pt_PT.aff 2010-08-10 22:43:56.000000000 +0200
***************
*** 1,4 ****
SET ISO8859-1
- TRY aerisontcdmlupvgbfz<66>h<EFBFBD>qj<71>x<EFBFBD><78><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ACMPSBTELGRIFVDkHJON<4F>ywUKXZWQ<57>Y<EFBFBD><59><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>
*** 1,6 ****
SET UTF-8
! LANG pt_PT
! TRY aerisontcdmlupvgbfzáhçqjíxãóéêâúõACMPSBTELGRIFVDkHJONôywUKXZWQÁYÍÉàÓèÂÚ
! KEY qwertyuiop|asdfghjkl|zxcvbnm
! WORDCHARS -
--- 1,17 ----
SET ISO8859-1
+ NAME European Portuguese
+ VERSION 2008-07-05
+ HOME http://natura.di.uminho.pt/
+ AUTHOR Rui Vilela
+ EMAIL ruivilela AT di DOT uminho DOT pt
+ AUTHOR Jos<6F> Jo<4A>o de Almeira
+ EMAIL jj AT di DOT uminho DOT pt
+ AUTHOR Alberto Sim<69>es
+ EMAIL ambs AT di DOT uminho DOT pt
+ COPYRIGHT GPL, LGPL, MPL
+
+ FOL <20><><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>
+ LOW <20><><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>
+ UPP <20><><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>
--- 1,10 ----
SET UTF-8
! #LANG pt_PT
! #TRY aerisontcdmlupvgbfzáhçqjíxãóéêâúõACMPSBTELGRIFVDkHJONôywUKXZWQÁYÍÉàÓèÂÚ
! #KEY qwertyuiop|asdfghjkl|zxcvbnm
! #WORDCHARS -
!
! FOL ßàáâãäåæçèéêëìíîïðñòóôõöøùúûüýþÿ
! LOW ßàáâãäåæçèéêëìíîïðñòóôõöøùúûüýþÿ
! UPP ßÀÁÂÃÄÅÆÇÈÉÊËÌÍÎÏÐÑÒÓÔÕÖØÙÚÛÜÝÞÿ
***************
*** 1047,1048 ****
--- 1060,1063 ----
SFX J e <20>dromo e
+
+
REP 24
***************
*** 1073,1086 ****
*** 1300,1312 ****
! MAP 11
! MAP a<EFBFBD>
! MAP a<EFBFBD>
! MAP a<EFBFBD>
! MAP e<EFBFBD>
! MAP e<EFBFBD>
! MAP i<EFBFBD>
MAP c<EFBFBD>
! MAP o<EFBFBD>
! MAP o<EFBFBD>
! MAP o<EFBFBD>
! MAP u<EFBFBD>
!
--- 1088,1095 ----
! MAP aá
! MAP aã
! MAP aâ
! MAP eé
! MAP eê
! MAP ií
MAP cç
! MAP oó
! MAP oô
! MAP oõ
! MAP uú
--- 1304,1311 ----
! MAP 6
! MAP a<EFBFBD><EFBFBD><EFBFBD>A<EFBFBD><EFBFBD><EFBFBD>
! MAP e<EFBFBD><EFBFBD>E<EFBFBD><EFBFBD>
! MAP i<EFBFBD>I<EFBFBD>
MAP c<EFBFBD>
! MAP o<EFBFBD><EFBFBD><EFBFBD>O<EFBFBD><EFBFBD><EFBFBD>
! MAP u<EFBFBD><EFBFBD>U<EFBFBD><EFBFBD>
! MAP aáãâAÁÃÂ
! MAP eéêEÉÊ
! MAP iíIÍ
MAP cç
! MAP oóõôOÓÕÔ
! MAP uúüUÚÜ