Commit 0039aa3f authored by Jérome Perrin's avatar Jérome Perrin

fixup! web_renderjs_ui: use lxml to extract data-i18n messages

a928abd2 (web_renderjs_ui: use lxml to extract data-i18n messages, 2020-12-14)
was an old version of the patch that was pushed accidentally. This applies
the missing bits.
parent 1137838d
......@@ -12,22 +12,20 @@ Base_translateString = context.Base_translateString
# <!-- data-i18n="The message" -->
translatable_message_set = set([])
# Web pages can be in web page module ...
web_page_reference_list = context.Base_getTranslationSourceFileList(only_html=1)
not_found_in_web_page_reference_set = set([])
for web_page_reference in web_page_reference_list:
# Web pages can be in web page module ...
web_page = context.getDocumentValue(web_page_reference)
if web_page is None:
not_found_in_web_page_reference_set.add(web_page_reference)
if web_page is not None:
web_page_text_content = web_page.getTextContent()
else:
for message in portal.ERP5Site_extractTranslationMessageListFromHTML(web_page.getTextContent()):
translatable_message_set.add(message)
# ... or in skin folders
for web_page_reference in not_found_in_web_page_reference_set:
if not '/' in web_page_reference:
# ... or in skin folders
web_page = context.restrictedTraverse(web_page_reference, None)
if web_page is not None and hasattr(web_page, 'manage_FTPget'):
for message in portal.ERP5Site_extractTranslationMessageListFromHTML(web_page.manage_FTPget()):
web_page_text_content = web_page.manage_FTPget()
if web_page_text_content:
for message in portal.ERP5Site_extractTranslationMessageListFromHTML(web_page_text_content):
translatable_message_set.add(message)
tmp = {}
......@@ -36,7 +34,12 @@ for language in context.getAvailableLanguageSet():
for word in translatable_message_set:
tmp[language][word] = unicode(Base_translateString(word, lang = language), 'utf-8')
return u"""/**
# We pass unicode to this json.dump(ensure_ascii=False), so that it produce
# UTF-8 string and not escaped characters. At the end we return an UTF-8
# encoded string and not an unicode instance, because text_content property
# is usually UTF-8 encoded str (not unicode).
return (u"""/**
* This translation data is generated automatically and updated with upgrader in post-upgarde.
* Do not edit manually, but use "Update Translation Data" action on web site to update from
* Localizer and from data-i18n tags on web pages.
......@@ -55,4 +58,4 @@ return u"""/**
sort_keys=True,
indent=2,
ensure_ascii=False,
separators=(',', ': ')).splitlines()))
separators=(',', ': ')).splitlines()))).encode('utf-8')
......@@ -200,7 +200,7 @@ class TestRenderUpdateTranslationData(RenderJSUpgradeTestCase):
self.web_script_translation_data_js.publish()
self.web_page_translation_gadget = self.portal.web_page_module.newContent(
portal_type='Web Page',
reference='{}.html'.format(self.id()),
reference='{}_translation.html'.format(self.id()),
content_type='text/html',
text_content=textwrap.dedent('''
<!DOCTYPE html>
......@@ -313,7 +313,7 @@ class TestRenderUpdateTranslationData(RenderJSUpgradeTestCase):
self.assertIn('"Message with [square brackets]":', translation_data_text_content)
self.assertIn('"Message in <a href=\'link\'>HTML</a>":', translation_data_text_content)
self.assertIn('"Message in script attributes":', translation_data_text_content)
self.assertIn(u'"メッサージュ":', translation_data_text_content)
self.assertIn('"メッサージュ":', translation_data_text_content)
def test_WebSite_getTranslationDataTextContent_extract_from_page_template(self):
self.portal.portal_skins.custom.manage_addProduct['PageTemplates'].manage_addPageTemplate(
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment