Fixed #5849 -- Strip whitespace from blocktrans

Add the trimmed option to the blocktrans tag to trim any newlines and
whitespace from its content.

This allows the developer to indent the blocktrans tag without adding
new lines and whitespace to the msgid in the PO file.

Thanks to mpessas for the initial patch and Dmitri Fedortchenko for the
report.

django/templatetags/i18n.py

@@ -97,14 +97,16 @@ class TranslateNode(Node):
 
 
 class BlockTranslateNode(Node):
+
     def __init__(self, extra_context, singular, plural=None, countervar=None,
-            counter=None, message_context=None):
+            counter=None, message_context=None, trimmed=False):
         self.extra_context = extra_context
         self.singular = singular
         self.plural = plural
         self.countervar = countervar
         self.counter = counter
         self.message_context = message_context
+        self.trimmed = trimmed
 
     def render_token_list(self, tokens):
         result = []
@@ -115,7 +117,10 @@ class BlockTranslateNode(Node):
             elif token.token_type == TOKEN_VAR:
                 result.append('%%(%s)s' % token.contents)
                 vars.append(token.contents)
-        return ''.join(result), vars
+        msg = ''.join(result)
+        if self.trimmed:
+            msg = translation.trim_whitespace(msg)
+        return msg, vars
 
     def render(self, context, nested=False):
         if self.message_context:
@@ -438,6 +443,8 @@ def do_block_translate(parser, token):
                     '"context" in %r tag expected '
                     'exactly one argument.') % bits[0]
                 six.reraise(TemplateSyntaxError, TemplateSyntaxError(msg), sys.exc_info()[2])
+        elif option == "trimmed":
+            value = True
         else:
             raise TemplateSyntaxError('Unknown argument for %r tag: %r.' %
                                       (bits[0], option))
@@ -453,6 +460,8 @@ def do_block_translate(parser, token):
         message_context = None
     extra_context = options.get('with', {})
 
+    trimmed = options.get("trimmed", False)
+
     singular = []
     plural = []
     while parser.tokens:
@@ -474,7 +483,7 @@ def do_block_translate(parser, token):
         raise TemplateSyntaxError("'blocktrans' doesn't allow other block tags (seen %r) inside it" % token.contents)
 
     return BlockTranslateNode(extra_context, singular, plural, countervar,
-            counter, message_context)
+                              counter, message_context, trimmed=trimmed)
 
 
 @register.tag

django/utils/translation/__init__.py

@@ -2,7 +2,7 @@
 Internationalization support.
 """
 from __future__ import unicode_literals
-
+import re
 from django.utils.encoding import force_text
 from django.utils.functional import lazy
 from django.utils import six
@@ -218,3 +218,9 @@ def get_language_info(lang_code):
             return LANG_INFO[generic_lang_code]
         except KeyError:
             raise KeyError("Unknown language code %s and %s." % (lang_code, generic_lang_code))
+
+trim_whitespace_re = re.compile('\s*\n\s*')
+
+
+def trim_whitespace(s):
+    return trim_whitespace_re.sub(' ', s.strip())

django/utils/translation/trans_real.py

@@ -19,7 +19,7 @@ from django.utils._os import upath
 from django.utils.safestring import mark_safe, SafeData
 from django.utils import six
 from django.utils.six import StringIO
-from django.utils.translation import TranslatorCommentWarning
+from django.utils.translation import TranslatorCommentWarning, trim_whitespace
 
 
 # Translations are cached in a dictionary for every language+app tuple.
@@ -530,6 +530,7 @@ def blankout(src, char):
     """
     return dot_re.sub(char, src)
 
+
 context_re = re.compile(r"""^\s+.*context\s+((?:"[^"]*?")|(?:'[^']*?'))\s*""")
 inline_re = re.compile(r"""^\s*trans\s+((?:"[^"]*?")|(?:'[^']*?'))(\s+.*context\s+((?:"[^"]*?")|(?:'[^']*?')))?\s*""")
 block_re = re.compile(r"""^\s*blocktrans(\s+.*context\s+((?:"[^"]*?")|(?:'[^']*?')))?(?:\s+|$)""")
@@ -553,6 +554,7 @@ def templatize(src, origin=None):
     message_context = None
     intrans = False
     inplural = False
+    trimmed = False
     singular = []
     plural = []
     incomment = False
@@ -582,20 +584,29 @@ def templatize(src, origin=None):
                 endbmatch = endblock_re.match(t.contents)
                 pluralmatch = plural_re.match(t.contents)
                 if endbmatch:
-                    if inplural:
+                    if trimmed:
-                        if message_context:
+                        singular = trim_whitespace(''.join(singular))
-                            out.write(' npgettext(%r, %r, %r,count) ' % (message_context, ''.join(singular), ''.join(plural)))
                     else:
-                            out.write(' ngettext(%r, %r, count) ' % (''.join(singular), ''.join(plural)))
+                        singular = ''.join(singular)
+
+                    if inplural:
+                        if trimmed:
+                            plural = trim_whitespace(''.join(plural))
+                        else:
+                            plural = ''.join(plural)
+                        if message_context:
+                            out.write(' npgettext(%r, %r, %r,count) ' % (message_context, singular, plural))
+                        else:
+                            out.write(' ngettext(%r, %r, count) ' % (singular, plural))
                         for part in singular:
                             out.write(blankout(part, 'S'))
                         for part in plural:
                             out.write(blankout(part, 'P'))
                     else:
                         if message_context:
-                            out.write(' pgettext(%r, %r) ' % (message_context, ''.join(singular)))
+                            out.write(' pgettext(%r, %r) ' % (message_context, singular))
                         else:
-                            out.write(' gettext(%r) ' % ''.join(singular))
+                            out.write(' gettext(%r) ' % singular)
                         for part in singular:
                             out.write(blankout(part, 'S'))
                     message_context = None
@@ -678,6 +689,7 @@ def templatize(src, origin=None):
                             message_context = message_context.strip("'")
                     intrans = True
                     inplural = False
+                    trimmed = 'trimmed' in t.split_contents()
                     singular = []
                     plural = []
                 elif cmatches:

docs/releases/1.7.txt

@@ -342,6 +342,15 @@ Internationalization
   still read from in 1.7. Sessions will be migrated to the new ``_language``
   key as they are written.
 
+* The :ttag:`blocktrans` now supports a ``trimmed`` option. This
+  option will remove newline characters from the beginning and the end of the
+  content of the ``{% blocktrans %}`` tag, replace any whitespace at the
+  beginning and end of a line and merge all lines into one using a space
+  character to separate them. This is quite useful for indenting the content of
+  a ``{% blocktrans %}`` tag without having the indentation characters end up
+  in the corresponding entry in the PO file, which makes the translation
+  process easier.
+
 Management Commands
 ^^^^^^^^^^^^^^^^^^^
 

docs/topics/i18n/translation.txt

@@ -674,6 +674,30 @@ markers<contextual-markers>` using the ``context`` keyword:
 
     {% blocktrans with name=user.username context "greeting" %}Hi {{ name }}{% endblocktrans %}
 
+Another feature ``{% blocktrans %}`` supports is the ``trimmed`` option. This
+option will remove newline characters from the beginning and the end of the
+content of the ``{% blocktrans %}`` tag, replace any whitespace at the beginning
+and end of a line and merge all lines into one using a space character to
+separate them. This is quite useful for indenting the content of a ``{%
+blocktrans %}`` tag without having the indentation characters end up in the
+corresponding entry in the PO file, which makes the translation process easier.
+
+For instance, the following ``{% blocktrans %}`` tag::
+
+    {% blocktrans trimmed %}
+      First sentence.
+      Second paragraph.
+    {% endblocktrans %}
+
+will result in the entry ``"First sentence. Second paragraph."`` in the PO file,
+compared to ``"\n  First sentence.\n  Second sentence.\n"``, if the ``trimmed``
+option had not been specified.
+
+.. versionchanged:: 1.7
+
+    The ``trimmed`` option was added.
+
+
 String literals passed to tags and filters
 ------------------------------------------
 

tests/i18n/commands/templates/test.html

@@ -82,3 +82,15 @@ continued here.{% endcomment %}
 {% trans "Translatable literal with context wrapped in double quotes" context "Context wrapped in double quotes" as var %}
 {% blocktrans context 'Special blocktrans context wrapped in single quotes' %}Translatable literal with context wrapped in single quotes{% endblocktrans %}
 {% blocktrans context "Special blocktrans context wrapped in double quotes" %}Translatable literal with context wrapped in double quotes{% endblocktrans %}
+
+
+{# BasicExtractorTests.test_blocktrans_trimmed #}
+{% blocktrans %}
+  Text with a few
+  line breaks.
+{% endblocktrans %}
+{% blocktrans trimmed %}
+  Again some text with a few
+  line breaks, this time
+  should be trimmed.
+{% endblocktrans %}

tests/i18n/test_extraction.py

@@ -121,6 +121,17 @@ class BasicExtractorTests(ExtractorTests):
             self.assertMsgId('I think that 100%% is more that 50%% of %(obj)s.', po_contents)
             self.assertMsgId("Blocktrans extraction shouldn't double escape this: %%, a=%(a)s", po_contents)
 
+    def test_blocktrans_trimmed(self):
+        os.chdir(self.test_dir)
+        management.call_command('makemessages', locale=LOCALE, verbosity=0)
+        self.assertTrue(os.path.exists(self.PO_FILE))
+        with open(self.PO_FILE, 'r') as fp:
+            po_contents = force_text(fp.read())
+            # should not be trimmed
+            self.assertNotMsgId('Text with a few line breaks.', po_contents)
+            # should be trimmed
+            self.assertMsgId("Again some text with a few line breaks, this time should be trimmed.", po_contents)
+
     def test_force_en_us_locale(self):
         """Value of locale-munging option used by the command is the right one"""
         from django.core.management.commands.makemessages import Command

tests/i18n/tests.py

@@ -245,6 +245,17 @@ class TranslationTests(TransRealMixin, TestCase):
             rendered = t.render(Context())
             self.assertEqual(rendered, 'Andere: Es gibt 5 Kommentare')
 
+            # Using trimmed
+            t = Template('{% load i18n %}{% blocktrans trimmed %}\n\nThere\n\t are 5  \n\n   comments\n{% endblocktrans %}')
+            rendered = t.render(Context())
+            self.assertEqual(rendered, 'There are 5 comments')
+            t = Template('{% load i18n %}{% blocktrans with num_comments=5 context "comment count" trimmed %}\n\nThere are  \t\n  \t {{ num_comments }} comments\n\n{% endblocktrans %}')
+            rendered = t.render(Context())
+            self.assertEqual(rendered, 'Es gibt 5 Kommentare')
+            t = Template('{% load i18n %}{% blocktrans context "other super search" count number=2 trimmed %}\n{{ number }} super \n result{% plural %}{{ number }} super results{% endblocktrans %}')
+            rendered = t.render(Context())
+            self.assertEqual(rendered, '2 andere Super-Ergebnisse')
+
             # Mis-uses
             self.assertRaises(TemplateSyntaxError, Template, '{% load i18n %}{% blocktrans context with month="May" %}{{ month }}{% endblocktrans %}')
             self.assertRaises(TemplateSyntaxError, Template, '{% load i18n %}{% blocktrans context %}{% endblocktrans %}')