anne/lyx_mirror
1
0
Fork 0
mirror of https://git.lyx.org/repos/lyx.git synced 2024-12-25 22:06:15 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

* lib/lyx2lyx/lyx_1_5.py:

Browse Source 
- implement wrapper around normalize that handles specific cases
	  that must not be normalized (rest of bug 3313).

git-svn-id: svn://svn.lyx.org/lyx/lyx-devel/trunk@23227 a592a061-630c-0410-9148-cb99ea01b6c8
This commit is contained in:
Jürgen Spitzmüller 2008-02-25 13:32:08 +00:00
parent 962fdc2923
commit ca6246e4da
1 changed files with 23 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

27
lib/lyx2lyx/lyx_1_5.py
View File

@ -1158,6 +1158,25 @@ def is_inset_line(document, i):
return last_tokens.find('\\') != -1 return last_tokens.find('\\') != -1
# A wrapper around normalize that handles special cases (cf. bug 3313)
def normalize(form, text):
# do not normalize OHM, ANGSTROM
keep_characters = [0x2126,0x212b]
result = ''
convert = ''
for i in text:
if ord(i) in keep_characters:
if len(convert) > 0:
result = result + unicodedata.normalize(form, convert)
convert = ''
result = result + i
else:
convert = convert + i
if len(convert) > 0:
result = result + unicodedata.normalize(form, convert)
return result
def revert_accent(document): def revert_accent(document):
inverse_accent_map = {} inverse_accent_map = {}
for k in accent_map: for k in accent_map:
@ -1190,9 +1209,9 @@ def revert_accent(document):
# because we never use u'xxx' for string literals, but 'xxx'. # because we never use u'xxx' for string literals, but 'xxx'.
# Therefore we may have to try two times to normalize the data. # Therefore we may have to try two times to normalize the data.
try: try:
document.body[i] = unicodedata.normalize("NFD", document.body[i]) document.body[i] = normalize("NFD", document.body[i])
except TypeError: except TypeError:
document.body[i] = unicodedata.normalize("NFD", unicode(document.body[i], 'utf-8')) document.body[i] = normalize("NFD", unicode(document.body[i], 'utf-8'))
# Replace accented characters with InsetLaTeXAccent # Replace accented characters with InsetLaTeXAccent
# Do not convert characters that can be represented in the chosen # Do not convert characters that can be represented in the chosen
@ -1247,7 +1266,7 @@ def revert_accent(document):
accented_char = inverse_accented_map[accented_char] accented_char = inverse_accented_map[accented_char]
accent = document.body[i][j] accent = document.body[i][j]
try: try:
dummy = unicodedata.normalize("NFC", accented_char + accent).encode(encoding_stack[-1]) dummy = normalize("NFC", accented_char + accent).encode(encoding_stack[-1])
except UnicodeEncodeError: except UnicodeEncodeError:
# Insert the rest of the line as new line # Insert the rest of the line as new line
if j < len(document.body[i]) - 1: if j < len(document.body[i]) - 1:
@ -1261,7 +1280,7 @@ def revert_accent(document):
# Normalize to "Normal form C" (NFC, pre-composed characters) again # Normalize to "Normal form C" (NFC, pre-composed characters) again
for i in range(len(document.body)): for i in range(len(document.body)):
document.body[i] = unicodedata.normalize("NFC", document.body[i]) document.body[i] = normalize("NFC", document.body[i])
def normalize_font_whitespace_259(document): def normalize_font_whitespace_259(document):