openlp-core team mailing list archive

[Simon Hanna <simon@xxxxxxxxxxx>]

Simon Hanna has proposed merging lp:~thelinuxguy/openlp/fix-newline-bug into lp:openlp.

Requested reviews:
  Tim Bentley (trb143)
  Phill (phill-ridout)
Related bugs:
  Bug #1727517 in OpenLP: "Unicode control chars causes song importer to crash"
  https://bugs.launchpad.net/openlp/+bug/1727517

For more details, see:
https://code.launchpad.net/~thelinuxguy/openlp/fix-newline-bug/+merge/343306

Fix the fix for 1727517
-- 
Your team OpenLP Core is subscribed to branch lp:openlp.

=== modified file 'openlp/core/common/__init__.py'
--- openlp/core/common/__init__.py	2018-02-24 16:10:02 +0000
+++ openlp/core/common/__init__.py	2018-04-16 11:33:07 +0000
@@ -44,7 +44,7 @@
 
 FIRST_CAMEL_REGEX = re.compile('(.)([A-Z][a-z]+)')
 SECOND_CAMEL_REGEX = re.compile('([a-z0-9])([A-Z])')
-CONTROL_CHARS = re.compile(r'[\x00-\x1F\x7F-\x9F]')
+CONTROL_CHARS = re.compile(r'[\x00-\08\x0B\x0C\x0E-\x1F\x7F-\x9F]')
 INVALID_FILE_CHARS = re.compile(r'[\\/:\*\?"<>\|\+\[\]%]')
 IMAGES_FILTER = None
 REPLACMENT_CHARS_MAP = str.maketrans({'\u2018': '\'', '\u2019': '\'', '\u201c': '"', '\u201d': '"', '\u2026': '...',
@@ -471,15 +471,15 @@
         log.exception('Error detecting file encoding')
 
 
-def normalize_str(irreg_str):
+def normalize_str(string):
     """
     Normalize the supplied string. Remove unicode control chars and tidy up white space.
 
-    :param str irreg_str: The string to normalize.
+    :param str string: The string to normalize.
     :return: The normalized string
     :rtype: str
     """
-    irreg_str = irreg_str.translate(REPLACMENT_CHARS_MAP)
-    irreg_str = CONTROL_CHARS.sub('', irreg_str)
-    irreg_str = NEW_LINE_REGEX.sub('\n', irreg_str)
-    return WHITESPACE_REGEX.sub(' ', irreg_str)
+    string = string.translate(REPLACMENT_CHARS_MAP)
+    string = CONTROL_CHARS.sub('', string)
+    string = NEW_LINE_REGEX.sub('\n', string)
+    return WHITESPACE_REGEX.sub(' ', string)

=== modified file 'tests/functional/openlp_core/common/test_common.py'
--- tests/functional/openlp_core/common/test_common.py	2017-12-29 09:15:48 +0000
+++ tests/functional/openlp_core/common/test_common.py	2018-04-16 11:33:07 +0000
@@ -25,8 +25,8 @@
 from unittest import TestCase
 from unittest.mock import MagicMock, call, patch
 
-from openlp.core.common import clean_button_text, de_hump, extension_loader, is_macosx, is_linux, is_win, \
-    path_to_module, trace_error_handler
+from openlp.core.common import clean_button_text, de_hump, extension_loader, is_macosx, is_linux, \
+    is_win, normalize_str, path_to_module, trace_error_handler
 from openlp.core.common.path import Path
 
 
@@ -211,6 +211,30 @@
             assert is_win() is False, 'is_win() should return False'
             assert is_macosx() is False, 'is_macosx() should return False'
 
+    def test_normalize_str_leaves_newlines(self):
+        # GIVEN: a string containing newlines
+        string = 'something\nelse'
+        # WHEN: normalize is called
+        normalized_string = normalize_str(string)
+        # THEN: string is unchanged
+        assert normalized_string == string
+
+    def test_normalize_str_removes_null_byte(self):
+        # GIVEN: a string containing newlines
+        string = 'somet\x00hing'
+        # WHEN: normalize is called
+        normalized_string = normalize_str(string)
+        # THEN: string is unchanged
+        assert normalized_string == 'something'
+
+    def test_normalize_str_replaces_crlf_with_lf(self):
+        # GIVEN: a string containing crlf
+        string = 'something\r\nelse'
+        # WHEN: normalize is called
+        normalized_string = normalize_str(string)
+        # THEN: crlf is replaced with lf
+        assert normalized_string == 'something\nelse'
+
     def test_clean_button_text(self):
         """
         Test the clean_button_text() function.