Handle excess whitespace in strings

Whitespace between words and tags doesn't matter to HTML. Indeed, the
text in a translatable element may be formatted any way over any number
of lines, so we normalize all consecutive whitespace to be just one space
character and strip whitespace from the beginning and end of the strings.

This is so that translators are not confronted with strange newlines and
whitespace on Transifex.

[endlessm/eos-sdk#3291]

1 files changed, 4 insertions, 1 deletions

diff --git a/tools/eos-html-extractor b/tools/eos-html-extractor
index f82afa1..ef8fc54 100755
--- a/tools/eos-html-extractor
+++ b/tools/eos-html-extractor
@@ -10,6 +10,9 @@ import sys
 from bs4 import BeautifulSoup
 from html.parser import HTMLParser
 
+def normalize_string(string):
+    return re.sub(r'\s+', ' ', string.strip())
+
 
 # Parser that adds line numbers to the HTML strings that need translating
 class TranslatableHTMLParser(HTMLParser):
@@ -38,7 +41,7 @@ class TranslatableHTMLParser(HTMLParser):
             if comment_line + comment_length == code_line:
                 optional_comment = ' '.join(comment_string.split())
 
-        self.all_translatable_data.append((data.strip(), code_line, optional_comment))
+        self.all_translatable_data.append((normalize_string(data), code_line, optional_comment))
 
     def handle_comment(self, comment):
         self._comments_with_line_numbers.append((comment, self.getpos()[0]))