Re: Encoding customization variable names

[Patrice Dumas]

On Mon, May 30, 2022 at 08:04:34PM +0100, Gavin Smith wrote:
> On Mon, May 30, 2022 at 06:43:32PM +0100, Gavin Smith wrote:
> > On Mon, May 30, 2022 at 11:48:22AM +0200, Patrice Dumas wrote:
> 
> > > Some tests need this either to have expected error messages, or
> > > more fundamentaly for input file names decoding.  I can propose
> > > something similar with 'Need recoded file names' with a dummy set
> > > on the test command line.
> > 
> > Could some of this be fixed with customization variables added to the
> > tests?
> 
> > 
> > I'm going to try to see if some of the other tests can be made to pass
> > the same way.
> 
> Here are the changes currently needed for the test suite to pass:

This looks good to me.  I could do the same for the remaining tests in
many_input_files too.

> 
> diff --git a/tp/tests/formatting/list-of-tests 
> b/tp/tests/formatting/list-of-tests
> index 8965ca597c..0938dd90b8 100644
> --- a/tp/tests/formatting/list-of-tests
> +++ b/tp/tests/formatting/list-of-tests
> @@ -12,23 +12,23 @@ documentlanguage_cmdline documentlanguage.texi 
> --document-language=fr
>  
>  # already tested in t/*.t, but here want to have a result with
>  # accented characters in error messages
> -cpp_lines ../../t/input_files/cpp_lines.texi
> +cpp_lines ../../t/input_files/cpp_lines.texi -c MESSAGE_ENCODING=UTF-8
>  
>  # some command-line arguments when incorrect cause texi2any to die.
>  # easily tested by calling directly ./texi2any.pl and checking visually:
>  # ./texi2any.pl --footnote-style=bâd
>  # ./texi2any.pl --paragraph-indent=ïndent
>  # check non ascii command line arguments and css files
> -non_ascii_command_line osé_utf8.texi --html --split=Mekanïk 
> --document-language=Destruktïw -c 'Kommandöh vâl' -D TÛT -D 'vùr ké' -U ôndef 
> -c 'FORMAT_MENU mînù' --macro-expand=@OUT_DIR@osé-texinfo.texi 
> --internal-links=@OUT_DIR@intérnal.txt --css-include çss.css --css-include 
> cêss.css --css-ref=rëf --css-ref=öref
> +non_ascii_command_line osé_utf8.texi -c COMMAND_LINE_ENCODING=UTF-8 -c 
> MESSAGE_ENCODING=UTF-8 -c LOCALE_OUTPUT_FILE_NAME_ENCODING=UTF-8 --html 
> --split=Mekanïk --document-language=Destruktïw -c 'Kommandöh vâl' -D TÛT -D 
> 'vùr ké' -U ôndef -c 'FORMAT_MENU mînù' 
> --macro-expand=@OUT_DIR@osé-texinfo.texi 
> --internal-links=@OUT_DIR@intérnal.txt --css-include çss.css --css-include 
> cêss.css --css-ref=rëf --css-ref=öref
>  
>  # test for the copying of image with non ascii characters for epub
> -non_ascii_test_epub osé_utf8.texi --init epub3.pm -c 'EPUB_CREATE_CONTAINER 
> 0'
> +non_ascii_test_epub osé_utf8.texi -c COMMAND_LINE_ENCODING=UTF-8 -c 
> MESSAGE_ENCODING=UTF-8 -c LOCALE_OUTPUT_FILE_NAME_ENCODING=UTF-8 --init 
> epub3.pm -c 'EPUB_CREATE_CONTAINER 0' -c 'COMMAND_LINE_ENCODING UTF-8'
>  
>  # check that the output is right when based on @setfilename
> -non_ascii_test_rawtext osé_utf8.texi -c TEXINFO_OUTPUT_FORMAT=rawtext
> +non_ascii_test_rawtext osé_utf8.texi -c COMMAND_LINE_ENCODING=UTF-8 -c 
> MESSAGE_ENCODING=UTF-8 -c LOCALE_OUTPUT_FILE_NAME_ENCODING=UTF-8 -c 
> LOCALE_INPUT_FILE_NAME_ENCODING=UTF-8 -c TEXINFO_OUTPUT_FORMAT=rawtext -c 
> 'COMMAND_LINE_ENCODING UTF-8'
>  
>  # check that the output is right when based on input file name
> -non_ascii_no_setfilename_test_rawtext osé_utf8_no_setfilename.texi -c 
> TEXINFO_OUTPUT_FORMAT=rawtext
> +non_ascii_no_setfilename_test_rawtext osé_utf8_no_setfilename.texi -c 
> COMMAND_LINE_ENCODING=UTF-8 -c MESSAGE_ENCODING=UTF-8 -c 
> LOCALE_OUTPUT_FILE_NAME_ENCODING=UTF-8 -c 
> LOCALE_INPUT_FILE_NAME_ENCODING=UTF-8 -c TEXINFO_OUTPUT_FORMAT=rawtext
>  
>  # test of non utf8 encoded file name in non utf8 document
>  # "Need recoded file names" string is used in test driving script
> @@ -40,5 +40,5 @@ manual_include_accented_file_name_latin1_explicit_encoding 
> manual_include_accent
>  
>  # fails to find the latin1 encoded include file as the locale encoding
>  # of the test suite is utf8
> -manual_include_accented_file_name_latin1_use_locale_encoding 
> manual_include_accented_file_name_latin1.texi --info -c 
> DOC_ENCODING_FOR_INPUT_FILE_NAME=0 -D 'needrecodedfilenames Need recoded file 
> names'
> +manual_include_accented_file_name_latin1_use_locale_encoding 
> manual_include_accented_file_name_latin1.texi --info -c 
> DOC_ENCODING_FOR_INPUT_FILE_NAME=0 -D 'needrecodedfilenames Need recoded file 
> names' -c MESSAGE_ENCODING=UTF-8 -c LOCALE_INPUT_FILE_NAME_ENCODING=UTF-8
>  
> diff --git a/tp/tests/run_parser_all.sh b/tp/tests/run_parser_all.sh
> index 3054ba010f..e29a89ee1f 100755
> --- a/tp/tests/run_parser_all.sh
> +++ b/tp/tests/run_parser_all.sh
> @@ -126,8 +126,8 @@ post_process_output ()
>    fi
>  }
>  
> -LC_ALL=en_US.UTF-8; export LC_ALL
> -LANGUAGE=en_US.UTF-8; export LANGUAGE
> +LC_ALL=C; export LC_ALL
> +LANGUAGE=en; export LANGUAGE
>  
>  prepended_command=
>  #prepended_command=time
>