[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
branch master updated: * tp/ext/epub3.pm (epub_finish): use transliterat
|
From: |
Patrice Dumas |
|
Subject: |
branch master updated: * tp/ext/epub3.pm (epub_finish): use transliterate_protect_file_name on opf file name to replace spaces, and avoid non ascii characters. |
|
Date: |
Fri, 06 Sep 2024 19:01:05 -0400 |
This is an automated email from the git hooks/post-receive script.
pertusus pushed a commit to branch master
in repository texinfo.
The following commit(s) were added to refs/heads/master by this push:
new 0d43e61e67 * tp/ext/epub3.pm (epub_finish): use
transliterate_protect_file_name on opf file name to replace spaces, and avoid
non ascii characters.
0d43e61e67 is described below
commit 0d43e61e67f5170553f8583938d68138c6c74baa
Author: Patrice Dumas <pertusus@free.fr>
AuthorDate: Sat Sep 7 01:00:59 2024 +0200
* tp/ext/epub3.pm (epub_finish): use transliterate_protect_file_name
on opf file name to replace spaces, and avoid non ascii characters.
* tp/t/test_utils.pl (test): add $srcdir.'ext/' to init files search
path.
* tp/Makefile.tres, tp/t/html_tests.t
(setfilename_on_top_and_after_node_epub): add test of EPUB generation,
tesing EPUB generation with files with spaces in their names.
---
ChangeLog | 12 ++
tp/Makefile.tres | 2 +
tp/ext/epub3.pm | 8 +-
tp/t/html_tests.t | 13 +-
.../setfilename_on_top_and_after_node_epub.pl | 239 +++++++++++++++++++++
.../EPUB/very-badly-placed-setfilename.opf | 10 +-
.../EPUB/xhtml/nav_toc.xhtml | 16 ++
.../EPUB/xhtml/very badly placed setfilename.xhtml | 25 +++
.../META-INF/container.xml | 2 +-
.../mimetype | 1 +
tp/t/test_utils.pl | 3 +-
.../EPUB/ose_utf8.opf" | 0
.../META-INF/container.xml" | 2 +-
13 files changed, 321 insertions(+), 12 deletions(-)
diff --git a/ChangeLog b/ChangeLog
index 09cb38513c..2827bb31e7 100644
--- a/ChangeLog
+++ b/ChangeLog
@@ -1,3 +1,15 @@
+2024-09-06 Patrice Dumas <pertusus@free.fr>
+
+ * tp/ext/epub3.pm (epub_finish): use transliterate_protect_file_name
+ on opf file name to replace spaces, and avoid non ascii characters.
+
+ * tp/t/test_utils.pl (test): add $srcdir.'ext/' to init files search
+ path.
+
+ * tp/Makefile.tres, tp/t/html_tests.t
+ (setfilename_on_top_and_after_node_epub): add test of EPUB generation,
+ tesing EPUB generation with files with spaces in their names.
+
2024-09-06 Patrice Dumas <pertusus@free.fr>
Percent encode file name in internal href
diff --git a/tp/Makefile.tres b/tp/Makefile.tres
index d43aeaed0c..510283ab6a 100644
--- a/tp/Makefile.tres
+++ b/tp/Makefile.tres
@@ -737,6 +737,8 @@ test_files_generated_list =
$(test_tap_files_generated_list) \
t/results/html_tests/sectioning_check_menu_structure/res_html \
t/results/html_tests/set_unit_file_name_filepath.pl \
t/results/html_tests/set_unit_file_name_filepath/res_html \
+ t/results/html_tests/setfilename_on_top_and_after_node_epub.pl \
+ t/results/html_tests/setfilename_on_top_and_after_node_epub/res_html \
t/results/html_tests/shortcontents_no_top.pl \
t/results/html_tests/shorttitlepage.pl \
t/results/html_tests/simple_only_special_spaces_node.pl \
diff --git a/tp/ext/epub3.pm b/tp/ext/epub3.pm
index 89f7e37028..7ad4b66d49 100644
--- a/tp/ext/epub3.pm
+++ b/tp/ext/epub3.pm
@@ -98,6 +98,7 @@ use Encode qw(decode);
# also for __(
use Texinfo::Common;
+use Texinfo::Convert::NodeNameNormalization;
use Texinfo::Convert::Utils;
use Texinfo::Convert::Text;
@@ -628,7 +629,12 @@ sub epub_finish($$)
return 1;
}
my $document_name = $self->get_info('document_name');
- my $opf_filename = $document_name . '.opf';
+ # We do not only percent encode the file name, as in that case the
+ # checker tells that the file cannot be found, however we can set the
+ # opf file name to anything as long as we are consistent.
+ my $opf_filename
+ = Texinfo::Convert::NodeNameNormalization::transliterate_protect_file_name(
+ $document_name) . '.opf';
print $container_fh <<EOT;
<?xml version="1.0"?>
<container version="1.0"
xmlns="urn:oasis:names:tc:opendocument:xmlns:container">
diff --git a/tp/t/html_tests.t b/tp/t/html_tests.t
index 6b5068470e..78b7e98df8 100644
--- a/tp/t/html_tests.t
+++ b/tp/t/html_tests.t
@@ -1520,6 +1520,16 @@ undef, {'test_file' =>
'simple_only_special_spaces_node.texi',
'init_files' => ['no_navigation.pm']},
# needed to test for the bug
{'SPLIT' => 'node'}],
+# also in *sectioning.t. Here we are interested by testing spaces
+# in filenames.
+['setfilename_on_top_and_after_node_epub',
+'@node Top
+@top In top @setfilename very badly placed setfilename
+
+@setfilename a bit too late
+', {'init_files' => ['epub3.pm'],
+ 'test_input_file_name' => 'very badly placed setfilename.texi'},
+ {'EPUB_CREATE_CONTAINER_FILE' => 0}],
);
@@ -1531,7 +1541,8 @@ foreach my $test (@test_cases_text) {
}
foreach my $test (@file_tests) {
push @{$test->[2]->{'test_formats'}}, 'file_html';
- $test->[2]->{'test_input_file_name'} = $test->[0] . '.texi';
+ $test->[2]->{'test_input_file_name'} = $test->[0] . '.texi'
+ unless (exists($test->[2]->{'test_input_file_name'}));
$test->[2]->{'full_document'} = 1 unless
(exists($test->[2]->{'full_document'}));
}
foreach my $test (@test_cases_file_text) {
diff --git a/tp/t/results/html_tests/setfilename_on_top_and_after_node_epub.pl
b/tp/t/results/html_tests/setfilename_on_top_and_after_node_epub.pl
new file mode 100644
index 0000000000..f68e0f1766
--- /dev/null
+++ b/tp/t/results/html_tests/setfilename_on_top_and_after_node_epub.pl
@@ -0,0 +1,239 @@
+use vars qw(%result_texis %result_texts %result_trees %result_errors
+ %result_indices %result_sectioning %result_nodes %result_menus
+ %result_floats %result_converted %result_converted_errors
+ %result_elements %result_directions_text %result_indices_sort_strings);
+
+use utf8;
+
+$result_trees{'setfilename_on_top_and_after_node_epub'} = {
+ 'contents' => [
+ {
+ 'contents' => [
+ {
+ 'type' => 'preamble_before_content'
+ }
+ ],
+ 'type' => 'before_node_section'
+ },
+ {
+ 'args' => [
+ {
+ 'contents' => [
+ {
+ 'text' => 'Top'
+ }
+ ],
+ 'info' => {
+ 'spaces_after_argument' => {
+ 'text' => '
+'
+ }
+ },
+ 'type' => 'line_arg'
+ }
+ ],
+ 'cmdname' => 'node',
+ 'extra' => {
+ 'is_target' => 1,
+ 'normalized' => 'Top'
+ },
+ 'info' => {
+ 'spaces_before_argument' => {
+ 'text' => ' '
+ }
+ },
+ 'source_info' => {
+ 'line_nr' => 1
+ }
+ },
+ {
+ 'args' => [
+ {
+ 'contents' => [
+ {
+ 'text' => 'In top '
+ },
+ {
+ 'args' => [
+ {
+ 'contents' => [
+ {
+ 'text' => 'very badly placed setfilename'
+ }
+ ],
+ 'info' => {
+ 'spaces_after_argument' => {
+ 'text' => '
+'
+ }
+ },
+ 'type' => 'line_arg'
+ }
+ ],
+ 'cmdname' => 'setfilename',
+ 'extra' => {
+ 'text_arg' => 'very badly placed setfilename'
+ },
+ 'info' => {
+ 'spaces_before_argument' => {
+ 'text' => ' '
+ }
+ },
+ 'source_info' => {
+ 'line_nr' => 2
+ }
+ }
+ ],
+ 'type' => 'line_arg'
+ }
+ ],
+ 'cmdname' => 'top',
+ 'contents' => [
+ {
+ 'text' => '
+',
+ 'type' => 'empty_line'
+ },
+ {
+ 'args' => [
+ {
+ 'contents' => [
+ {
+ 'text' => 'a bit too late'
+ }
+ ],
+ 'info' => {
+ 'spaces_after_argument' => {
+ 'text' => '
+'
+ }
+ },
+ 'type' => 'line_arg'
+ }
+ ],
+ 'cmdname' => 'setfilename',
+ 'extra' => {
+ 'text_arg' => 'a bit too late'
+ },
+ 'info' => {
+ 'spaces_before_argument' => {
+ 'text' => ' '
+ }
+ },
+ 'source_info' => {
+ 'line_nr' => 4
+ }
+ }
+ ],
+ 'extra' => {},
+ 'info' => {
+ 'spaces_before_argument' => {
+ 'text' => ' '
+ }
+ },
+ 'source_info' => {
+ 'line_nr' => 2
+ }
+ }
+ ],
+ 'type' => 'document_root'
+};
+
+$result_texis{'setfilename_on_top_and_after_node_epub'} = '@node Top
+@top In top @setfilename very badly placed setfilename
+
+@setfilename a bit too late
+';
+
+
+$result_texts{'setfilename_on_top_and_after_node_epub'} = 'In top
+*******
+
+';
+
+$result_sectioning{'setfilename_on_top_and_after_node_epub'} = {
+ 'extra' => {
+ 'section_childs' => [
+ {
+ 'cmdname' => 'top',
+ 'extra' => {
+ 'associated_node' => {
+ 'cmdname' => 'node',
+ 'extra' => {
+ 'normalized' => 'Top'
+ }
+ },
+ 'section_level' => 0,
+ 'sectioning_root' => {}
+ }
+ }
+ ],
+ 'section_level' => -1
+ }
+};
+$result_sectioning{'setfilename_on_top_and_after_node_epub'}{'extra'}{'section_childs'}[0]{'extra'}{'sectioning_root'}
= $result_sectioning{'setfilename_on_top_and_after_node_epub'};
+
+$result_nodes{'setfilename_on_top_and_after_node_epub'} = [
+ {
+ 'cmdname' => 'node',
+ 'extra' => {
+ 'associated_section' => {
+ 'cmdname' => 'top',
+ 'extra' => {}
+ },
+ 'normalized' => 'Top'
+ }
+ }
+];
+
+$result_menus{'setfilename_on_top_and_after_node_epub'} = [
+ {
+ 'extra' => {
+ 'normalized' => 'Top'
+ }
+ }
+];
+
+$result_errors{'setfilename_on_top_and_after_node_epub'} = [
+ {
+ 'error_line' => 'warning: @setfilename should only appear at the beginning
of a line
+',
+ 'line_nr' => 2,
+ 'text' => '@setfilename should only appear at the beginning of a line',
+ 'type' => 'warning'
+ },
+ {
+ 'error_line' => 'warning: @setfilename should not appear on @top line
+',
+ 'line_nr' => 2,
+ 'text' => '@setfilename should not appear on @top line',
+ 'type' => 'warning'
+ },
+ {
+ 'error_line' => 'warning: @setfilename after the first element
+',
+ 'line_nr' => 2,
+ 'text' => '@setfilename after the first element',
+ 'type' => 'warning'
+ },
+ {
+ 'error_line' => 'warning: multiple @setfilename
+',
+ 'line_nr' => 4,
+ 'text' => 'multiple @setfilename',
+ 'type' => 'warning'
+ },
+ {
+ 'error_line' => 'warning: @setfilename after the first element
+',
+ 'line_nr' => 4,
+ 'text' => '@setfilename after the first element',
+ 'type' => 'warning'
+ }
+];
+
+
+$result_floats{'setfilename_on_top_and_after_node_epub'} = {};
+
+
+1;
diff --git
"a/tp/tests/encoded/res_parser/non_ascii_test_epub/os\303\251_utf8_epub_package/EPUB/os\303\251_utf8.opf"
b/tp/t/results/html_tests/setfilename_on_top_and_after_node_epub/res_html/very
badly placed setfilename_epub_package/EPUB/very-badly-placed-setfilename.opf
similarity index 55%
copy from
"tp/tests/encoded/res_parser/non_ascii_test_epub/os\303\251_utf8_epub_package/EPUB/os\303\251_utf8.opf"
copy to
tp/t/results/html_tests/setfilename_on_top_and_after_node_epub/res_html/very
badly placed setfilename_epub_package/EPUB/very-badly-placed-setfilename.opf
index d2c3042703..77c631af20 100644
---
"a/tp/tests/encoded/res_parser/non_ascii_test_epub/os\303\251_utf8_epub_package/EPUB/os\303\251_utf8.opf"
+++
b/tp/t/results/html_tests/setfilename_on_top_and_after_node_epub/res_html/very
badly placed setfilename_epub_package/EPUB/very-badly-placed-setfilename.opf
@@ -1,19 +1,15 @@
<?xml version="1.0" encoding="UTF-8"?>
<package xmlns="http://www.idpf.org/2007/opf"; version="3.0"
unique-identifier="texi-uid">
<metadata xmlns:dc="http://purl.org/dc/elements/1.1/";>
- <dc:identifier id="texi-uid">texinfo:osé_utf8</dc:identifier>
- <dc:title>Tôp</dc:title>
+ <dc:identifier id="texi-uid">texinfo:very badly placed
setfilename</dc:identifier>
+ <dc:title>In top </dc:title>
<dc:language>en</dc:language>
</metadata>
<manifest>
<item id="nav" properties="nav" media-type="application/xhtml+xml"
href="xhtml/nav_toc.xhtml"/>
- <item id="unit1" media-type="application/xhtml+xml"
href="xhtml/osé_utf8.xhtml"/>
- <item id="unit2" media-type="application/xhtml+xml"
href="xhtml/Chapteur.xhtml"/>
- <item id="image1" media-type="image/png" href="images/1-an_image.png"/>
- <item id="image2" media-type="image/png" href="images/2-an_image.png"/>
+ <item id="unit1" media-type="application/xhtml+xml" href="xhtml/very
badly placed setfilename.xhtml"/>
</manifest>
<spine>
<itemref idref="unit1"/>
- <itemref idref="unit2"/>
</spine>
</package>
diff --git
a/tp/t/results/html_tests/setfilename_on_top_and_after_node_epub/res_html/very
badly placed setfilename_epub_package/EPUB/xhtml/nav_toc.xhtml
b/tp/t/results/html_tests/setfilename_on_top_and_after_node_epub/res_html/very
badly placed setfilename_epub_package/EPUB/xhtml/nav_toc.xhtml
new file mode 100644
index 0000000000..6d4df7fa0a
--- /dev/null
+++
b/tp/t/results/html_tests/setfilename_on_top_and_after_node_epub/res_html/very
badly placed setfilename_epub_package/EPUB/xhtml/nav_toc.xhtml
@@ -0,0 +1,16 @@
+<?xml version="1.0" encoding="utf-8"?>
+<html xmlns="http://www.w3.org/1999/xhtml";
xmlns:epub="http://www.idpf.org/2007/ops";>
+<head>
+<meta charset="utf-8" />
+<title>In top - Table of contents</title>
+</head>
+<body>
+<nav epub:type="toc" id="nav">
+<h1>Table of contents</h1>
+
+<ol>
+ <li><a href="very%20badly%20placed%20setfilename.xhtml">In top </a></li>
+</ol>
+</nav>
+</body>
+</html>
diff --git
a/tp/t/results/html_tests/setfilename_on_top_and_after_node_epub/res_html/very
badly placed setfilename_epub_package/EPUB/xhtml/very badly placed
setfilename.xhtml
b/tp/t/results/html_tests/setfilename_on_top_and_after_node_epub/res_html/very
badly placed setfilename_epub_package/EPUB/xhtml/very badly placed
setfilename.xhtml
new file mode 100644
index 0000000000..62e0f7f2c0
--- /dev/null
+++
b/tp/t/results/html_tests/setfilename_on_top_and_after_node_epub/res_html/very
badly placed setfilename_epub_package/EPUB/xhtml/very badly placed
setfilename.xhtml
@@ -0,0 +1,25 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<!DOCTYPE html>
+<html xmlns="http://www.w3.org/1999/xhtml";>
+<!-- Created by texinfo, http://www.gnu.org/software/texinfo/ -->
+<head>
+<meta http-equiv="Content-Type" content="text/html; charset=utf-8"/>
+<title>In top </title>
+
+<meta name="description" content="In top "/>
+<meta name="keywords" content="In top "/>
+<meta name="resource-type" content="document"/>
+<meta name="distribution" content="global"/>
+<meta name="viewport" content="width=device-width,initial-scale=1"/>
+
+<link href="#Top" rel="start" title="In top "/>
+
+
+</head>
+
+<body lang="en">
+<a class="node" id="Top"></a><a class="top" id="In-top-"></a>
+
+
+</body>
+</html>
diff --git
"a/tp/tests/encoded/res_parser/non_ascii_test_epub/os\303\251_utf8_epub_package/META-INF/container.xml"
b/tp/t/results/html_tests/setfilename_on_top_and_after_node_epub/res_html/very
badly placed setfilename_epub_package/META-INF/container.xml
similarity index 75%
copy from
"tp/tests/encoded/res_parser/non_ascii_test_epub/os\303\251_utf8_epub_package/META-INF/container.xml"
copy to
tp/t/results/html_tests/setfilename_on_top_and_after_node_epub/res_html/very
badly placed setfilename_epub_package/META-INF/container.xml
index 6640a792e1..c46272314f 100644
---
"a/tp/tests/encoded/res_parser/non_ascii_test_epub/os\303\251_utf8_epub_package/META-INF/container.xml"
+++
b/tp/t/results/html_tests/setfilename_on_top_and_after_node_epub/res_html/very
badly placed setfilename_epub_package/META-INF/container.xml
@@ -1,7 +1,7 @@
<?xml version="1.0"?>
<container version="1.0"
xmlns="urn:oasis:names:tc:opendocument:xmlns:container">
<rootfiles>
- <rootfile full-path="EPUB/osé_utf8.opf"
+ <rootfile full-path="EPUB/very-badly-placed-setfilename.opf"
media-type="application/oebps-package+xml" />
</rootfiles>
</container>
diff --git
a/tp/t/results/html_tests/setfilename_on_top_and_after_node_epub/res_html/very
badly placed setfilename_epub_package/mimetype
b/tp/t/results/html_tests/setfilename_on_top_and_after_node_epub/res_html/very
badly placed setfilename_epub_package/mimetype
new file mode 100644
index 0000000000..57ef03f24a
--- /dev/null
+++
b/tp/t/results/html_tests/setfilename_on_top_and_after_node_epub/res_html/very
badly placed setfilename_epub_package/mimetype
@@ -0,0 +1 @@
+application/epub+zip
\ No newline at end of file
diff --git a/tp/t/test_utils.pl b/tp/t/test_utils.pl
index 39a67351f1..681f8b42f8 100644
--- a/tp/t/test_utils.pl
+++ b/tp/t/test_utils.pl
@@ -881,7 +881,8 @@ sub test($$)
my $init_files_options
= Texinfo::Config::GNUT_initialize_customization('',
$test_customization_defaults, {});
- my $init_file_directories = [$srcdir.'init/', $srcdir.'t/init/'];
+ my $init_file_directories = [$srcdir.'init/', $srcdir.'t/init/',
+ $srcdir.'ext/'];
# the init file names should be binary strings. Since they
# are not encoded here, ascii file names should be used or they
# should be encoded in test specification files.
diff --git
"a/tp/tests/encoded/res_parser/non_ascii_test_epub/os\303\251_utf8_epub_package/EPUB/os\303\251_utf8.opf"
"b/tp/tests/encoded/res_parser/non_ascii_test_epub/os\303\251_utf8_epub_package/EPUB/ose_utf8.opf"
similarity index 100%
rename from
"tp/tests/encoded/res_parser/non_ascii_test_epub/os\303\251_utf8_epub_package/EPUB/os\303\251_utf8.opf"
rename to
"tp/tests/encoded/res_parser/non_ascii_test_epub/os\303\251_utf8_epub_package/EPUB/ose_utf8.opf"
diff --git
"a/tp/tests/encoded/res_parser/non_ascii_test_epub/os\303\251_utf8_epub_package/META-INF/container.xml"
"b/tp/tests/encoded/res_parser/non_ascii_test_epub/os\303\251_utf8_epub_package/META-INF/container.xml"
index 6640a792e1..3fead36985 100644
---
"a/tp/tests/encoded/res_parser/non_ascii_test_epub/os\303\251_utf8_epub_package/META-INF/container.xml"
+++
"b/tp/tests/encoded/res_parser/non_ascii_test_epub/os\303\251_utf8_epub_package/META-INF/container.xml"
@@ -1,7 +1,7 @@
<?xml version="1.0"?>
<container version="1.0"
xmlns="urn:oasis:names:tc:opendocument:xmlns:container">
<rootfiles>
- <rootfile full-path="EPUB/osé_utf8.opf"
+ <rootfile full-path="EPUB/ose_utf8.opf"
media-type="application/oebps-package+xml" />
</rootfiles>
</container>
| [Prev in Thread] |
Current Thread |
[Next in Thread] |
- branch master updated: * tp/ext/epub3.pm (epub_finish): use transliterate_protect_file_name on opf file name to replace spaces, and avoid non ascii characters.,
Patrice Dumas <=