X-Git-Url: https://git.lyx.org/gitweb/?a=blobdiff_plain;f=lib%2Flyx2lyx%2Flyx_1_6.py;h=7a3710e47e46f1f3e9be95d77afc47a90ec424b7;hb=c52808ce1a804a875514713eb6f5dcd6f05dd6c8;hp=2d0964c3afeab7f80a4da853715b9c4feea507ea;hpb=14bcaa5f9d2489dc1e9bd72021064d0533f273bf;p=features.git

diff --git a/lib/lyx2lyx/lyx_1_6.py b/lib/lyx2lyx/lyx_1_6.py
index 2d0964c3af..7a3710e47e 100644
--- a/lib/lyx2lyx/lyx_1_6.py
+++ b/lib/lyx2lyx/lyx_1_6.py
@@ -23,6 +23,7 @@ import unicodedata
 import sys, os
 
 from parser_tools import find_token, find_end_of, find_tokens, get_value
+from unicode_symbols import unicode_reps
 
 ####################################################################
 # Private helper functions
@@ -94,7 +95,7 @@ def convert_len(len):
              "theight%":"\\backslash\ntextheight", "pheight%":"\\backslash\npageheight"}
 
     # Convert LyX units to LaTeX units
-    for unit in units.keys():
+    for unit in list(units.keys()):
         if len.find(unit) != -1:
             len = '%f' % (len2value(len) / 100)
             len = len.strip('0') + units[unit]
@@ -145,51 +146,13 @@ def set_option(document, m, option, value):
     return l
 
 
-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'))
-    spec_chars = []
-    # Two backslashes, 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)\}')
-    for line in fp.readlines():
-        if line[0] != '#' and line.strip() != "":
-            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)
-            try:
-                [ucs4,command,dead] = line.split(None,2)
-                if command[0:1] != "\\":
-                    continue
-                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 += "\\"
-                commandbl = command
-                command += m.group(1) + m.group(2)
-                commandbl += m.group(1) + ' ' + m.group(2)
-                spec_chars.append([command, unichr(eval(ucs4))])
-                spec_chars.append([commandbl, unichr(eval(ucs4))])
-    fp.close()
-    return spec_chars
-
-
 def extract_argument(line):
     'Extracts a LaTeX argument from the start of line. Returns (arg, rest).'
 
     if not line:
         return (None, "")
 
-    bracere = re.compile("(\s*)(.*)")
+    bracere = re.compile(r"(\s*)(.*)")
     n = bracere.match(line)
     whitespace = n.group(1)
     stuff = n.group(2)
@@ -269,8 +232,6 @@ def latex2ert(line, isindex):
     return retval
 
 
-unicode_reps = read_unicodesymbols()
-
 #Bug 5022....
 #Might should do latex2ert first, then deal with stuff that DOESN'T
 #end up inside ERT. That routine could be modified so that it returned
@@ -316,7 +277,7 @@ def latex2lyx(data, isindex):
     data = data.replace('\\\\', '\\')
 
     # Math:
-    mathre = re.compile('^(.*?)(\$.*?\$)(.*)')
+    mathre = re.compile(r'^(.*?)(\$.*?\$)(.*)')
     lines = data.split('\n')
     for line in lines:
         #document.warning("LINE: " + line)
@@ -423,7 +384,7 @@ def lyx2latex(document, lines):
             continue
         inert = ert_end >= curline
         content += lyxline2latex(document, lines[curline], inert)
-      
+
     return content
 
 
@@ -965,7 +926,7 @@ def revert_pdf_options(document):
 def remove_inzip_options(document):
     "Remove inzipName and embed options from the Graphics inset"
     i = 0
-    while 1:
+    while True:
         i = find_token(document.body, "\\begin_inset Graphics", i)
         if i == -1:
             return
@@ -985,7 +946,7 @@ def remove_inzip_options(document):
 
 
 def convert_inset_command(document):
-    """
+    r"""
         Convert:
             \begin_inset LatexCommand cmd
         to
@@ -993,7 +954,7 @@ def convert_inset_command(document):
             LatexCommand cmd
     """
     i = 0
-    while 1:
+    while True:
         i = find_token(document.body, "\\begin_inset LatexCommand", i)
         if i == -1:
             return
@@ -1022,7 +983,7 @@ def convert_inset_command(document):
 
 
 def revert_inset_command(document):
-    """
+    r"""
         Convert:
             \begin_inset CommandInset InsetType
             LatexCommand cmd
@@ -1032,7 +993,7 @@ def revert_inset_command(document):
         will not be able to recognize. Not sure what to do about that.
     """
     i = 0
-    while 1:
+    while True:
         i = find_token(document.body, "\\begin_inset CommandInset", i)
         if i == -1:
             return
@@ -1102,7 +1063,7 @@ def revert_wrapfig_options(document):
 
 
 def convert_latexcommand_index(document):
-    "Convert from LatexCommand form to collapsable form."
+    "Convert from LatexCommand form to collapsible form."
     i = 0
     r1 = re.compile('name "(.*)"')
     while True:
@@ -1134,7 +1095,7 @@ def convert_latexcommand_index(document):
 
 
 def revert_latexcommand_index(document):
-    "Revert from collapsable form to LatexCommand form."
+    "Revert from collapsible form to LatexCommand form."
     i = 0
     while True:
         i = find_token(document.body, "\\begin_inset Index", i)
@@ -1255,7 +1216,7 @@ def revert_japanese_encoding(document):
 def revert_inset_info(document):
     'Replace info inset with its content'
     i = 0
-    while 1:
+    while True:
         i = find_token(document.body, '\\begin_inset Info', i)
         if i == -1:
             return
@@ -1597,7 +1558,7 @@ def convert_usorbian(document):
 
 
 def convert_macro_global(document):
-    "Remove TeX code command \global when it is in front of a macro"
+    r"Remove TeX code command \global when it is in front of a macro"
     # math macros are nowadays already defined \global, so that an additional
     # \global would make the document uncompilable, see
     # http://www.lyx.org/trac/ticket/5371
@@ -1736,7 +1697,7 @@ def convert_serbocroatian(document):
 def convert_framed_notes(document):
     "Convert framed notes to boxes. "
     i = 0
-    while 1:
+    while True:
         i = find_tokens(document.body, ["\\begin_inset Note Framed", "\\begin_inset Note Shaded"], i)
         if i == -1:
             return
@@ -1765,7 +1726,7 @@ def convert_module_names(document):
     return
   newmodlist = []
   for mod in modlist:
-    if modulemap.has_key(mod):
+    if mod in modulemap:
       newmodlist.append(modulemap[mod])
     else:
       document.warning("Can't find module %s in the module map!" % mod)
@@ -1813,7 +1774,7 @@ def revert_colsep(document):
 def revert_framed_notes(document):
     "Revert framed boxes to notes. "
     i = 0
-    while 1:
+    while True:
         i = find_tokens(document.body, ["\\begin_inset Box Framed", "\\begin_inset Box Shaded"], i)
 
         if i == -1:
@@ -1931,7 +1892,7 @@ def revert_nocite_key(body, start, end):
 def revert_nocite(document):
     "Revert LatexCommand nocite to ERT"
     i = 0
-    while 1:
+    while True:
         i = find_token(document.body, "\\begin_inset CommandInset citation", i)
         if i == -1:
             return
@@ -2049,7 +2010,7 @@ def revert_serbianlatin(document):
 def revert_rotfloat(document):
     " Revert sideways custom floats. "
     i = 0
-    while 1:
+    while True:
         # whitespace intended (exclude \\begin_inset FloatList)
         i = find_token(document.body, "\\begin_inset Float ", i)
         if i == -1:
@@ -2112,7 +2073,7 @@ def revert_rotfloat(document):
 def revert_widesideways(document):
     " Revert wide sideways floats. "
     i = 0
-    while 1:
+    while True:
         # whitespace intended (exclude \\begin_inset FloatList)
         i = find_token(document.body, '\\begin_inset Float ', i)
         if i == -1:
@@ -2164,7 +2125,7 @@ def revert_widesideways(document):
 def revert_inset_embedding(document, type):
     ' Remove embed tag from certain type of insets'
     i = 0
-    while 1:
+    while True:
         i = find_token(document.body, "\\begin_inset %s" % type, i)
         if i == -1:
             return
@@ -2189,7 +2150,7 @@ def revert_external_embedding(document):
 def convert_subfig(document):
     " Convert subfigures to subfloats. "
     i = 0
-    while 1:
+    while True:
         addedLines = 0
         i = find_token(document.body, '\\begin_inset Graphics', i)
         if i == -1:
@@ -2229,7 +2190,7 @@ def convert_subfig(document):
 def revert_subfig(document):
     " Revert subfloats. "
     i = 0
-    while 1:
+    while True:
         # whitespace intended (exclude \\begin_inset FloatList)
         i = find_tokens(document.body, ['\\begin_inset Float ', '\\begin_inset Wrap'], i)
         if i == -1:
@@ -2378,7 +2339,7 @@ def revert_wrapplacement(document):
 
 
 def remove_extra_embedded_files(document):
-    " Remove \extra_embedded_files from buffer params "
+    r" Remove \extra_embedded_files from buffer params "
     i = find_token(document.header, '\\extra_embedded_files', 0)
     if i == -1:
         return
@@ -2733,7 +2694,7 @@ def convert_japanese_plain(document):
 def revert_pdfpages(document):
     ' Revert pdfpages external inset to ERT '
     i = 0
-    while 1:
+    while True:
         i = find_token(document.body, "\\begin_inset External", i)
         if i == -1:
             return
@@ -2835,7 +2796,7 @@ def revert_master(document):
 def revert_graphics_group(document):
     ' Revert group information from graphics insets '
     i = 0
-    while 1:
+    while True:
         i = find_token(document.body, "\\begin_inset Graphics", i)
         if i == -1:
             return
@@ -2865,7 +2826,7 @@ def update_apa_styles(document):
                     "Paragraph*":      "Paragraph",
                     "Subparagraph*":   "Subparagraph"}
     i = 0
-    while 1:
+    while True:
         i = find_token(document.body, "\\begin_layout", i)
         if i == -1:
             return