X-Git-Url: https://git.lyx.org/gitweb/?a=blobdiff_plain;f=lib%2Flyx2lyx%2Funicode_symbols.py;h=d9eeff96835d81b0e9fe0b46a8ed63e56360add0;hb=b35fb98335b1fff52ac0a266d45e48579427dbf8;hp=7f6d4bfb385f5f2b3525e36226c1fd32e41beac0;hpb=1246a70abd5e5eec6057daa3b35f7c626270cf4d;p=lyx.git

diff --git a/lib/lyx2lyx/unicode_symbols.py b/lib/lyx2lyx/unicode_symbols.py
index 7f6d4bfb38..d9eeff9683 100644
--- a/lib/lyx2lyx/unicode_symbols.py
+++ b/lib/lyx2lyx/unicode_symbols.py
@@ -14,41 +14,58 @@
 #
 # You should have received a copy of the GNU General Public License
 # along with this program; if not, write to the Free Software
-# Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA  02111-1307, USA.
+# Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301  USA
 
 " Import unicode_reps from this module for access to the unicode<->LaTeX mapping. "
 
 import sys, os, re
 
+# Provide support for both python 2 and 3
+PY2 = sys.version_info[0] == 2
+if not PY2:
+    unichr = chr
+# End of code to support for both python 2 and 3
+
 def read_unicodesymbols():
     " Read the unicodesymbols list of unicode characters and corresponding commands."
     pathname = os.path.abspath(os.path.dirname(sys.argv[0]))
-    fp = open(os.path.join(pathname.strip('lyx2lyx'), 'unicodesymbols'))
+    filename = os.path.join(pathname.strip('lyx2lyx'), 'unicodesymbols')
+
+    # For python 3+ we have to specify the encoding for those systems
+    # where the default is not UTF-8
+    fp = open(filename, encoding="utf8") if (not PY2) else open(filename)
+
     spec_chars = []
-    # Two backslashes, followed by some non-word character, and then a character
+    # A backslash, followed by some non-word character, and then a character
     # in brackets. The idea is to check for constructs like: \"{u}, which is how
     # they are written in the unicodesymbols file; but they can also be written
     # as: \"u or even \" u.
-    r = re.compile(r'\\\\(\W)\{(\w)\}')
+    # The two backslashes in the string literal are needed to specify a literal
+    # backslash in the regex. Without r prefix, these would be four backslashes.
+    r = re.compile(r'\\(\W)\{(\w)\}')
     for line in fp.readlines():
         if line[0] != '#' and line.strip() != "":
+            # Note: backslashes in the string literals with r prefix are not escaped,
+            #       so one backslash in the source file equals one backslash in memory.
+            #       Without r prefix backslahses are escaped, so two backslashes in the
+            #       source file equal one backslash in memory.
             line=line.replace(' "',' ') # remove all quotation marks with spaces before
             line=line.replace('" ',' ') # remove all quotation marks with spaces after
-            line=line.replace(r'\"','"') # replace \" by " (for characters with diaeresis)
+            line=line.replace(r'\"','"') # unescape "
+            line=line.replace(r'\\','\\') # unescape \
             try:
                 [ucs4,command,dead] = line.split(None,2)
                 if command[0:1] != "\\":
                     continue
+                if (line.find("notermination=text") < 0 and
+                    line.find("notermination=both") < 0 and command[-1] != "}"):
+                    command = command + "{}"
                 spec_chars.append([command, unichr(eval(ucs4))])
             except:
                 continue
             m = r.match(command)
             if m != None:
-                command = "\\\\"
-                # If the character is a double-quote, then we need to escape it, too,
-                # since it is done that way in the LyX file.
-                if m.group(1) == "\"":
-                    command += "\\"
+                command = "\\"
                 commandbl = command
                 command += m.group(1) + m.group(2)
                 commandbl += m.group(1) + ' ' + m.group(2)