autotools: support optionally building the extended Russian and Chinese dictionaries

.gitignore

@@ -62,6 +62,9 @@ Makefile
 dictsource/*_extra
 dictsource/dict_log
 dictsource/dict_phonemes
+dictsource/ru_listx
+dictsource/zh_listx
+dictsource/zhy_list
 
 phsource/compile_prog_log
 phsource/compile_report

Makefile.am

@@ -659,7 +659,13 @@ espeak-data/ro_dict: src/espeak phsource/phonemes.stamp dictsource/ro_list dicts
 ru: espeak-data/ru_dict
 dictsource/ru_extra:
 	touch dictsource/ru_extra
+dictsource/ru_listx:
+	ln -svf extra/ru_listx dictsource/
+if HAVE_RU_EXTENDED_DICTIONARY
+espeak-data/ru_dict: src/espeak phsource/phonemes.stamp dictsource/ru_list dictsource/ru_rules dictsource/ru_extra dictsource/ru_listx
+else
 espeak-data/ru_dict: src/espeak phsource/phonemes.stamp dictsource/ru_list dictsource/ru_rules dictsource/ru_extra
+endif
 	cd dictsource && ESPEAK_DATA_PATH=$(PWD) LD_LIBRARY_PATH=../src:${LD_LIBRARY_PATH} ../src/espeak --compile=ru && cd ..
 
 si: espeak-data/si_dict
@@ -731,11 +737,23 @@ espeak-data/vi_dict: src/espeak phsource/phonemes.stamp dictsource/vi_list dicts
 zh: espeak-data/zh_dict
 dictsource/zh_extra:
 	touch dictsource/zh_extra
+dictsource/zh_listx:
+	ln -svf extra/zh_listx dictsource/
+if HAVE_ZH_EXTENDED_DICTIONARY
+espeak-data/zh_dict: src/espeak phsource/phonemes.stamp dictsource/zh_list dictsource/zh_rules dictsource/zh_extra dictsource/zh_listx
+else
 espeak-data/zh_dict: src/espeak phsource/phonemes.stamp dictsource/zh_list dictsource/zh_rules dictsource/zh_extra
+endif
 	cd dictsource && ESPEAK_DATA_PATH=$(PWD) LD_LIBRARY_PATH=../src:${LD_LIBRARY_PATH} ../src/espeak --compile=zh && cd ..
 
 zhy: espeak-data/zhy_dict
 dictsource/zhy_extra:
 	touch dictsource/zhy_extra
+dictsource/zhy_list:
+	ln -svf extra/zhy_list dictsource/
+if HAVE_ZHY_EXTENDED_DICTIONARY
+espeak-data/zhy_dict: src/espeak phsource/phonemes.stamp dictsource/zhy_rules dictsource/zhy_extra dictsource/zhy_list
+else
 espeak-data/zhy_dict: src/espeak phsource/phonemes.stamp dictsource/zhy_rules dictsource/zhy_extra
+endif
 	cd dictsource && ESPEAK_DATA_PATH=$(PWD) LD_LIBRARY_PATH=../src:${LD_LIBRARY_PATH} ../src/espeak --compile=zhy && cd ..

README.md

@@ -33,14 +33,17 @@ This is a mirror of the eSpeak sources with the following improvements on the
 1.  An autotools-based build system that supports building the phoneme data and
     language dictionaries from source on POSIX systems.
 
-2.  Detection of the supported audio APIs via the `configure` script — no need to
+2.  Optional support for the extended Russian and Chinese dictionaries from
+    [http://espeak.sourceforge.net/data/](http://espeak.sourceforge.net/data/).
+
+3.  Detection of the supported audio APIs via the `configure` script — no need to
     modify the build files.
 
-3.  The NVDA voice variants are included in the `espeak-data/voices/!v` directory.
+4.  The NVDA voice variants are included in the `espeak-data/voices/!v` directory.
 
-4.  Add support for the Oromo language (`om`, contributed by [gude432](https://github.com/gude432)).
+5.  Add support for the Oromo language (`om`, contributed by [gude432](https://github.com/gude432)).
 
-5.  Support for wxWidgets 3.0.
+6.  Support for wxWidgets 3.0.
 
 ## Build Dependencies
 
@@ -239,6 +242,10 @@ fixes detailed in the sections below. In addition, it:
 
 2.  supports the Oromo language (`om`, contributed by [gude432](https://github.com/gude432)).
 
+3.  Optional support for the extended Russian (`ru`), Mandarin Chinese (`zh`)
+    and Cantonese Chinese (`zhy`) dictionaries from
+    [http://espeak.sourceforge.net/data/](http://espeak.sourceforge.net/data/).
+
 #### Build System
 
 The build system for eSpeak has been changed on the *master* branch to use

configure.ac

@@ -173,6 +173,44 @@ AM_CONDITIONAL(OPT_MBROLA, [test x"$have_mbrola" = xyes])
 AM_CONDITIONAL(OPT_SONIC,  [test x"$have_sonic"  = xyes])
 AM_CONDITIONAL(OPT_ASYNC,  [test x"$have_async"  = xyes])
 
+dnl ================================================================
+dnl Extended dictionary checks.
+dnl ================================================================
+
+AC_ARG_WITH([extdict-ru],
+    [AS_HELP_STRING([--with-extdict-ru], [use the extended Russian Dictionary file @<:@default=no@:>@])],
+    [])
+
+if test "$with_extdict_ru" = "yes" ; then
+	have_extdict_ru=yes
+else
+	have_extdict_ru=no
+fi
+
+AC_ARG_WITH([extdict-zh],
+    [AS_HELP_STRING([--with-extdict-zh], [use the extended Mandarin Chinese Dictionary file @<:@default=no@:>@])],
+    [])
+
+if test "$with_extdict_zh" = "yes" ; then
+	have_extdict_zh=yes
+else
+	have_extdict_zh=no
+fi
+
+AC_ARG_WITH([extdict-zhy],
+    [AS_HELP_STRING([--with-extdict-zhy], [use the extended Cantonese Chinese Dictionary file @<:@default=no@:>@])],
+    [])
+
+if test "$with_extdict_zhy" = "yes" ; then
+	have_extdict_zhy=yes
+else
+	have_extdict_zhy=no
+fi
+
+AM_CONDITIONAL(HAVE_RU_EXTENDED_DICTIONARY,  [test x"$have_extdict_ru"  = xyes])
+AM_CONDITIONAL(HAVE_ZH_EXTENDED_DICTIONARY,  [test x"$have_extdict_zh"  = xyes])
+AM_CONDITIONAL(HAVE_ZHY_EXTENDED_DICTIONARY, [test x"$have_extdict_zhy" = xyes])
+
 dnl ================================================================
 dnl wxWidgets checks.
 dnl ================================================================
@@ -215,4 +253,9 @@ AC_MSG_NOTICE([
         MBROLA:                        ${have_mbrola}
         Sonic:                         ${have_sonic}
         Async:                         ${have_async}
+
+        Extended Dictionaries:
+            Russian:                   ${have_extdict_ru}
+            Chinese (Mandarin):        ${have_extdict_zh}
+            Chinese (Cantonese):       ${have_extdict_zhy}
 ])

mkdictlist

@@ -19,6 +19,13 @@ special_voices = {
 	'zh-yue': 'zhy',
 }
 
+# Support for extended dictionaries.
+extended_dictionaries = {
+	'ru':  'ru_listx',
+	'zh':  'zh_listx',
+	'zhy': 'zhy_list',
+}
+
 exclude_voices = []
 
 def find_voices(path):
@@ -43,7 +50,7 @@ find_voices('espeak-data/voices')
 find_phoneme_data('phsource')
 
 for filename in os.listdir('dictsource'):
-	if filename.endswith('_rules') or filename.endswith('_list') or filename.endswith('_listx'):
+	if filename.endswith('_rules') or filename.endswith('_list') or filename in ['bg_listx', 'it_listx']:
 		dic, cat = filename.split('_')
 		if dic in voices:
 			if not dic in dictionaries.keys():
@@ -81,7 +88,16 @@ def write_dictionary_make_rules(f):
 		f.write('%s: espeak-data/%s_dict\n' % (name, name))
 		f.write('dictsource/%s_extra:\n' % name)
 		f.write('\ttouch dictsource/%s_extra\n' % name)
+		if name in extended_dictionaries.keys():
+			ext = extended_dictionaries[name]
+			f.write('dictsource/%s:\n' % ext)
+			f.write('\tln -svf extra/%s dictsource/\n' % ext)
+			f.write('if HAVE_%s_EXTENDED_DICTIONARY\n' % name.upper())
+			f.write('espeak-data/%s_dict: src/espeak phsource/phonemes.stamp %s dictsource/%s_extra dictsource/%s\n' % (name, ' '.join(sorted(files)), name, ext))
+			f.write('else\n')
 		f.write('espeak-data/%s_dict: src/espeak phsource/phonemes.stamp %s dictsource/%s_extra\n' % (name, ' '.join(sorted(files)), name))
+		if name in extended_dictionaries.keys():
+			f.write('endif\n')
 		f.write('\tcd dictsource && ESPEAK_DATA_PATH=$(PWD) LD_LIBRARY_PATH=../src:${LD_LIBRARY_PATH} ../src/espeak --compile=%s && cd ..\n' % name)
 
 try: