anne/lyx_mirror
1
0
Fork 0
mirror of https://git.lyx.org/repos/lyx.git synced 2024-12-23 05:25:26 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

Improve revert unicode (bug 3958) from Anders Ekberg

Browse Source 
git-svn-id: svn://svn.lyx.org/lyx/lyx-devel/trunk@19113 a592a061-630c-0410-9148-cb99ea01b6c8
This commit is contained in:
José Matox 2007-07-18 10:47:44 +00:00
parent 1007714d2e
commit 8397a051fa
1 changed files with 110 additions and 56 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

164
lib/lyx2lyx/lyx_1_5.py
View File

@ -1769,6 +1769,7 @@ def convert_ext_font_sizes(document):
else: else:
del document.header[i] del document.header[i]
def revert_separator_layout(document): def revert_separator_layout(document):
r'''Revert --Separator-- to a lyx note r'''Revert --Separator-- to a lyx note
From From
@ -1817,6 +1818,7 @@ something
r'\end_layout' r'\end_layout'
] ]
def convert_arabic (document): def convert_arabic (document):
if document.language == "arabic": if document.language == "arabic":
document.language = "arabic_arabtex" document.language = "arabic_arabtex"
@ -1831,6 +1833,7 @@ def convert_arabic (document):
document.body[i] = '\lang arabic_arabtex' document.body[i] = '\lang arabic_arabtex'
i = i + 1 i = i + 1
def revert_arabic (document): def revert_arabic (document):
if document.language == "arabic_arabtex": if document.language == "arabic_arabtex":
document.language = "arabic" document.language = "arabic"
@ -1845,13 +1848,11 @@ def revert_arabic (document):
document.body[i] = '\lang arabic' document.body[i] = '\lang arabic'
i = i + 1 i = i + 1
def revert_unicode(document):
'''Transform unicode symbols according to the unicode list. def read_unicodesymbols():
Preamble flags are not implemented. " Read the unicodesymbols list of unicode characters and corresponding commands."
Combination characters are currently ignored. pathname = os.path.abspath(os.path.dirname(sys.argv[0]))
Forced output is currently not enforced''' fp = open(os.path.join(pathname.strip('lyx2lyx'), 'unicodesymbols'))
pathname = os.path.dirname(sys.argv[0])
fp = open(pathname.strip('lyx2lyx') + 'unicodesymbols','r')
spec_chars = {} spec_chars = {}
for line in fp.readlines(): for line in fp.readlines():
if line[0] != '#': if line[0] != '#':
@ -1859,82 +1860,135 @@ Forced output is currently not enforced'''
line=line.replace('" ',' ') # remove all quotation marks with spaces after line=line.replace('" ',' ') # remove all quotation marks with spaces after
line=line.replace(r'\"','"') # replace \" by " (for characters with diaeresis) line=line.replace(r'\"','"') # replace \" by " (for characters with diaeresis)
try: try:
# flag1 and flag2 are preamble & flags # flag1 and flag2 are preamble and other flags
# currently NOT implemented
[ucs4,command,flag1,flag2] =line.split(None,3) [ucs4,command,flag1,flag2] =line.split(None,3)
spec_chars[unichr(eval(ucs4))] = [command, flag1, flag2] spec_chars[unichr(eval(ucs4))] = [command, flag1, flag2]
except: except:
pass pass
fp.close() fp.close()
return spec_chars
def revert_unicode(document):
'''Transform unicode characters that can not be written using the
document encoding to commands according to the unicodesymbols
file. Characters that can not be replaced by commands are replaced by
an replacement string. Flags other than 'combined' are currently not
implemented.'''
replacement_character = '???'
spec_chars = read_unicodesymbols()
# Define strings to start and end ERT and math insets # Define strings to start and end ERT and math insets
ert_intro='\n\n\\begin_inset ERT\nstatus collapsed\n\\begin_layout Standard\n\\backslash\n' ert_intro='\n\n\\begin_inset ERT\nstatus collapsed\n\\begin_layout Standard\n\\backslash\n'
ert_outro='\n\\end_layout\n\n\\end_inset\n\n' ert_outro='\n\\end_layout\n\n\\end_inset\n\n'
math_intro='\n\\begin_inset Formula $' math_intro='\n\\begin_inset Formula $'
math_outro='$\n\\end_inset\n' math_outro='$\n\\end_inset\n'
# Find unicode characters and replace them # Find unicode characters and replace them
in_ert = 0 # flag set to 1 if in ERT inset in_ert = False # flag set to 1 if in ERT inset
in_math = 0 # flag set to 1 if in math inset in_math = False # flag set to 1 if in math inset
temp_file = os.tmpfile()
insets = [] # list of active insets insets = [] # list of active insets
for i, current_line in enumerate(document.body): mod_body = u'' # to store the modified document body
if current_line.find('\\begin_inset') > -1:
# Go through the file to capture all combining characters
last_char = '' # to store the previous character
body_string = u'' # store the document temporarily as a string
for line in document.body:
body_string = body_string + line +'\n'
[body_string, apa] = body_string.rsplit('\n',1)
body = body_string.split('\n')
for line in body:
# Check for insets
if line.find('\\begin_inset') > -1:
# check which inset to start # check which inset to start
if current_line.find('\\begin_inset ERT') > -1: if line.find('\\begin_inset ERT') > -1:
in_ert = 1 in_ert = True
insets.append('ert') insets.append('ert')
elif current_line.find('\\begin_inset Formula') > -1: elif line.find('\\begin_inset Formula') > -1:
in_math = 1 in_math = True
insets.append('math') insets.append('math')
else: else:
insets.append('other') insets.append('other')
if current_line.find('\\end_inset') > -1: if line.find('\\end_inset') > -1:
# check which inset to end # check which inset to end
try: try:
cur_inset = insets.pop() cur_inset = insets.pop()
if cur_inset == 'ert': if cur_inset == 'ert':
in_ert = 0 in_ert = False
elif cur_inset == 'math': elif cur_inset == 'math':
in_math = 0 in_math = False
else: else:
pass # end of other inset pass # end of other inset
except: except:
pass # inset list was empty (for some reason) pass # inset list was empty (for some reason)
current_line=''; # clear to have as container for modified line
for j in range(len(document.body[i])): # Try to write the line
if spec_chars.has_key(document.body[i][j]): try:
flags = spec_chars[document.body[i][j]][1] + spec_chars[document.body[i][j]][2] # If all goes well the line is written here
if flags.find('combining') > -1: temp_file.write(line.encode(document.encoding) + '\n')
command = '' mod_body = mod_body + line + '\n'
else: last_char = line[-1]
command = spec_chars[document.body[i][j]][0]; # the command to replace unicode except:
if command[0:2] == '\\\\': # Error, some character(s) in the line need to be replaced
if command[2:12]=='ensuremath': for character in line:
if in_ert == 1: try:
# math in ERT # Try to write the character
command = command.replace('\\\\ensuremath{\\\\', '$\n\\backslash\n') temp_file.write(character.encode(document.encoding))
command = command.replace('}', '$\n') mod_body = mod_body + character
elif in_math == 0: last_char = character
# add a math inset with the replacement character except:
command = command.replace('\\\\ensuremath{\\', math_intro) # Try to replace with ERT/math inset
command = command.replace('}', math_outro) if spec_chars.has_key(character):
command = spec_chars[character][0]; # the command to replace unicode
flag1 = spec_chars[character][1]
flag2 = spec_chars[character][2]
if flag1.find('combining') > -1 or flag2.find('combining') > -1:
# We have a character that should be combined with the previous
command = command + '{' +last_char + '}'
# Remove the last character. Ignore if it is whitespace
if len(last_char.rstrip()) > 0:
# last_char was found and is not whitespace
[mod_body, apa] = mod_body.rsplit(last_char,1)
else: else:
# we are already in a math inset # The last character was replaced by a command. For now it is
command = command.replace('\\\\ensuremath{\\', '') # ignored. This could be handled better.
command = command.replace('}', '') pass
else: if command[0:2] == '\\\\':
if in_math == 1: if command[2:12]=='ensuremath':
# avoid putting an ERT in a math; instead put command as text if in_ert == True:
command = command.replace('\\\\', '\mathrm{') # math in ERT
command = command + '}' command = command.replace('\\\\ensuremath{\\\\', '$\n\\backslash\n')
elif in_ert == 0: command = command.replace('}', '$\n')
# add an ERT inset with the replacement character elif in_math == False:
command = command.replace('\\\\', ert_intro) # add a math inset with the replacement character
command = command + ert_outro command = command.replace('\\\\ensuremath{\\', math_intro)
command = command.replace('}', math_outro)
else:
# we are already in a math inset
command = command.replace('\\\\ensuremath{\\', '')
command = command.replace('}', '')
else: else:
command = command.replace('\\\\', '\n\\backslash\n') if in_math == True:
current_line = current_line + command # avoid putting an ERT in a math; instead put command as text
else: command = command.replace('\\\\', '\mathrm{')
current_line = current_line + document.body[i][j] command = command + '}'
document.body[i] = current_line elif in_ert == False:
# add an ERT inset with the replacement character
command = command.replace('\\\\', ert_intro)
command = command + ert_outro
else:
command = command.replace('\\\\', '\n\\backslash\n')
last_char = '' # indicate that the character should not be removed
mod_body = mod_body + command
else:
# Replace with replacement string
mod_body = mod_body + replacement_character
[mod_body, apa] = mod_body.rsplit('\n',1)
document.body = mod_body.split('\n')
temp_file.close()
## ##