-
Notifications
You must be signed in to change notification settings - Fork 3
/
configure.ac
225 lines (189 loc) · 9.85 KB
/
configure.ac
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
## Process this file with autoconf to produce configure script
## Copyright (C) 2017 Samediggi/Divvun/UiT
## 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 3 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, see <http://www.gnu.org/licenses/>.
# The following things need to be at top of all configure.ac files:
# AC_INIT sets up project metadata:
# first field the name of the "software"
# second field is version identifier
# third is email address for bug reports
# fourth is name of packages made by make dist, excluding .tar.gz
# fifth is the project web address
AC_INIT([Giella kal], [0.2.0], [feedback@divvun.no], [giella-kal],
[http://divvun.no])
# AC_REVISION is used to get SVN revision into bug reports
AC_REVISION([$Revision$])
# These configuration dirs hide some extra cruft
AC_CONFIG_AUX_DIR([build-aux])
AC_CONFIG_MACRO_DIR([m4])
# AM_INIT_AUTOMAKE sets up make conventions
AM_INIT_AUTOMAKE(
1.11.6 tar-pax -Wall -Werror
foreign -Wno-portability
)
m4_ifdef([AM_SILENT_RULES], [AM_SILENT_RULES([yes])])
########## LANGUAGE SPECIFIC SETTINGS ##########
# GLANG is the language code used to identify this project; it is the
# ISO 639-3 three-letter code for the language.
# It is also the second part of the repo name lang-XXX.
# GTLANG is deprecated, defined for backwards compatibility.
AC_SUBST([GLANG], [kal])
AC_SUBST([GTLANG], $GLANG)
# GLANG2 is the shortest unambiguous language code for this project; it
# should be the ISO 639-1 two-letter code if available, otherwise usually the
# same as above:
# GTLANG2 is deprecated, defined for backwards compatibility.
AC_SUBST([GLANG2], [kl])
AC_SUBST([GTLANG2], $GLANG2)
# GLANGUAGE is the full language name as given by the ISO 639-3 file.
# GTLANGUAGE is deprecated, defined for backwards compatibility.
AC_SUBST([GLANGUAGE], ["Kalaallisut"])
AC_SUBST([GTLANGUAGE], $GLANGUAGE)
### Speller release version (usually different from the package version,
### typically spellers are released more often than the language package):
### Translate the *_NAT placeholder contents into
### the native language of this repo.
### The AC variables SPELLER_NAME_xxx and SPELLER_DESC_xxx are used in:
### - manifest.toml.in
### - tools/spellcheckers/index.*.xml.in
AC_SUBST([SPELLERVERSION], [1.0.1])
AC_SUBST([SPELLER_NAME_ENG], ["$GLANGUAGE spellchecker"])
AC_SUBST([SPELLER_NAME_NATIVE], ["Autonym spellchecker"])
AC_SUBST([SPELLER_DESC_ENG], ["A spellchecker for $GLANGUAGE, made by members of the language community, and by the Divvun and Giellatekno groups at UiT The Arctic University of Norway"])
AC_SUBST([SPELLER_DESC_NATIVE], ["TRANSLATE: A spellchecker for $GLANGUAGE, made by members of the language community, and by the Divvun and Giellatekno groups at UiT The Arctic University of Norway"])
### Grammar checker release version (usually different from the package version,
### typically grammar checkers are released more often than the language
### package, and also different from the speller release version):
AC_SUBST([GRAMCHECKVERSION], [0.1.0])
# Alternate writing system(s) should be listed here using the ISO 15924 code.
# Multiple alternate WS's should be space separated. For a list of such codes
# see http://en.wikipedia.org/wiki/ISO_15924 and
# http://www.unicode.org/iso15924/codelists.html
# It is assumed that conversion from the default WS to the alternate WS(s)
# can be done programmatically with a regex or xfscript. If not, resources
# for multiple WS's must be developed and maintained as separate languages.
AC_SUBST([DEFAULT_WS], ["Latn"])
AC_SUBST([ALT_WSS], [""])
AM_CONDITIONAL([HAVE_ALT_WSS], [test "x$ALT_WSS" != "x"])
# Specify the ISO 3166-1 alpha-2 codes for countries as pr BCP-47. A list of
# codes can be found at http://en.wikipedia.org/wiki/ISO_3166-1.
# Only specify country codes if there is a real difference between and real need
# for country-specific normative tools. E.g. in SMJ, people write æ or ä
# depending on whether they are in Norway or Sweden, and restricting a speller
# to only the relevant variant will improve the overall quality of the speller.
AC_SUBST([AREAS], [""])
AM_CONDITIONAL([HAVE_AREAS], [test "x$AREAS" != "x"])
# Names for default and alternate orthographies. The names must follow the BCP
# 47 rules for private use subtags, which requires that the names must be at
# most eight - 8 - characters long, and only contain ascii letters and digits.
# If only one orthography is used, leave both variables empty. If there are
# alternate orthographies, also the default must have a name.
# It is assumed that conversion from the default orthography to the alternate
# orthographies can be done programmatically with a regex or xfscript.
AC_SUBST([DEFAULT_ORTH], [""])
AC_SUBST([ALT_ORTHS], [""])
AM_CONDITIONAL([HAVE_ALT_ORTHS], [test "x$ALT_ORTHS" != "x" \
-a "x$DEFAULT_ORTH" != "x"])
# Specify whether spellers for alternative orthographies should be built, the
# default is to build them. Change the value below from 'true' to 'false' if
# such spellers are NOT wanted.
AM_CONDITIONAL([WANT_ALT_ORTH_PROOFTOOLS], [ true ])
# Case handling: the default is to assume an orthography with case distinctions:
# upper vs lower case. That is not always true, or the case handling is such
# that the default system doesn't cut it. In those cases, change the value
# below from 'true' to 'false':
AM_CONDITIONAL([DEFAULT_CASE_HANDLING], [ true ])
# Specify the tags for all dialects in this variable, leave it empty if you do
# NOT support dialectal variant fst's. Use upper case, separate with space.
# Dialects are presently only used in Oahpa fst's, and only support dialectal
# variation within the -norm- fst's.
AC_SUBST([DIALECTS], [""])
AM_CONDITIONAL([HAVE_DIALECTS], [test "x$DIALECTS" != "x"])
########## LANGUAGE SPECIFIC BUILD SETTINGS ##########
# NO_PHONOLOGY = yes
# ... makes the bulid process skip compilation of anything in the fst/
# dir. This is mainly useful when building from external sources such that the
# lexical fst built in the fst/ dir is actually the full analyser.
# The variable can also be set if a language is such that everything is
# encoded in lexc, and thus does not need any phonology processing.
# Default: empty, meaning that phonologies will be compiled.
AC_SUBST([NO_PHONOLOGY], [""])
AM_CONDITIONAL([SKIP_PHONOLOGY], [test "x$NO_PHONOLOGY" != "x"])
# LEXICON_IN_PHONOLOGY
# Set this to 'yes' IFF a) your phonology is formulated using rewrite rules,
# AND b) your phonology file contains a reference to the lexical transducer in
# the following form:
#
# load stack fst/lexicon.&FST&
#
# where &FST& will be automatically replaced with the relevant fst suffix (xfst,
# hfst, foma). When done like that, the phonology rules will be composed with
# the lexicon directly, which should lead to much faster compilaton of xfst
# rewrite rules.
AC_SUBST([LEXREF_IN_XFSCRIPT], [""])
AM_CONDITIONAL([LEXREF_IN_PHONOLOGY], [test "x$LEXREF_IN_XFSCRIPT" != "x"])
# Variables for language specific settings
# TODO: maybe some could be env.vars AC_ARG_VAR so power users know what
# they want to compile theirs stuff with
AC_SUBST([DEFAULT_FOMA], [no])
AC_SUBST([DEFAULT_HFST], [yes])
AC_SUBST([DEFAULT_XFST], [no])
AC_SUBST([DEFAULT_HYPERMIN], [yes])
AC_SUBST([DEFAULT_REVERCI], [yes])
AC_SUBST([DEFAULT_HFST_BACKEND], [foma])
AC_SUBST([DEFAULT_SPELLER_MINIMISATION], [no])
AC_SUBST([DEFAULT_ANALYSERS], [yes])
AC_SUBST([DEFAULT_GENERATORS], [yes])
AC_SUBST([DEFAULT_CUSTOM_FSTS], [yes])
# Tests and sets up giella-core directories and scripts
gt_PROG_SCRIPTS_PATHS
# kal uses m4 to process
AC_PATH_PROGS([M4], [m4 gm4])
# Tests and sets up XFST
gt_PROG_XFST
# Tests and sets up FOMA
gt_PROG_FOMA
# Tests and sets up HFST
gt_PROG_HFST
# Tests and sets up Voikko
gt_PROG_VFST
# Tests and sets up vislcg3
gt_PROG_VISLCG3
# Tests and sets up XML to lexc conversion
gt_PROG_SAXON
# Adds --enable/disable-morphology, -speller, -hyphenation, etc.
# This should be the last step so that all program variables are available
# to the enable checks
gt_ENABLE_TARGETS
# Add usage of optional shared data here.
# By default, all languages have shared symbols and punctuation.
# One language repo can even share / use data from another language repo!
# See lang-smj for an example.
# Add locally used shares below this line:
gt_USE_SHARED([common], [shared-mul], [giella-shared-mul])
AM_CONDITIONAL([HAVE_SHARED_COMMON], [test x$gt_SHARED_common != xfalse])
# Locally used shares above this line
# Call a function that lists all files that should be processed by autoconf:
gt_CONFIG_FILES
##########################################################
##### BEGIN: Add language-specific list of files to ######
########## be processed by autoconf below here: ##########
AC_CONFIG_FILES([tools/shellscripts/kal-analyse], [chmod +x tools/shellscripts/kal-analyse])
AC_CONFIG_FILES([tools/shellscripts/kal-tokenise], [chmod +x tools/shellscripts/kal-tokenise])
AC_CONFIG_FILES([tools/shellscripts/kal-generate], [chmod +x tools/shellscripts/kal-generate])
AC_CONFIG_FILES([tools/shellscripts/kal-hybrid-split], [chmod +x tools/shellscripts/kal-hybrid-split])
AC_CONFIG_FILES([tools/shellscripts/kal-lu-prefix], [chmod +x tools/shellscripts/kal-lu-prefix])
AC_CONFIG_FILES([tools/shellscripts/kal-spell-heur], [chmod +x tools/shellscripts/kal-spell-heur])
############ END: Language-specific scripts. #############
# This must be near the end of all configure.ac files:
AC_OUTPUT
# Prints the informative blurb at the end of ./configure command
gt_PRINT_FOOTER