l = find_token(document.body, "\\begin_layout Plain Layout", start, end)
return l
-####################################################################
-
def get_option(document, m, option, default):
l = document.body[m].find(option)
val = default
document.body[m] = document.body[m][:-1] + ' ' + option + '="' + value + '">'
return l
+
+####################################################################
+
+def convert_ltcaption(document):
+ i = 0
+ while True:
+ i = find_token(document.body, "\\begin_inset Tabular", i)
+ if i == -1:
+ return
+ j = find_end_of_inset(document.body, i + 1)
+ if j == -1:
+ document.warning("Malformed LyX document: Could not find end of tabular.")
+ continue
+
+ nrows = int(document.body[i+1].split('"')[3])
+ ncols = int(document.body[i+1].split('"')[5])
+
+ m = i + 1
+ for k in range(nrows):
+ m = find_token(document.body, "<row", m)
+ r = m
+ caption = 'false'
+ for k in range(ncols):
+ m = find_token(document.body, "<cell", m)
+ if (k == 0):
+ mend = find_token(document.body, "</cell>", m + 1)
+ # first look for caption insets
+ mcap = find_token(document.body, "\\begin_inset Caption", m + 1, mend)
+ # then look for ERT captions
+ if mcap == -1:
+ mcap = find_token(document.body, "caption", m + 1, mend)
+ if mcap > -1:
+ mcap = find_token(document.body, "\\backslash", mcap - 1, mcap)
+ if mcap > -1:
+ caption = 'true'
+ if caption == 'true':
+ if (k == 0):
+ set_option(document, r, 'caption', 'true')
+ set_option(document, m, 'multicolumn', '1')
+ set_option(document, m, 'bottomline', 'false')
+ set_option(document, m, 'topline', 'false')
+ set_option(document, m, 'rightline', 'false')
+ set_option(document, m, 'leftline', 'false')
+ #j = find_end_of_inset(document.body, j + 1)
+ else:
+ set_option(document, m, 'multicolumn', '2')
+ m = m + 1
+ m = m + 1
+
+ i = j + 1
+
+def revert_ltcaption(document):
+ i = 0
+ while True:
+ i = find_token(document.body, "\\begin_inset Tabular", i)
+ if i == -1:
+ return
+ j = find_end_of_inset(document.body, i + 1)
+ if j == -1:
+ document.warning("Malformed LyX document: Could not find end of tabular.")
+ continue
+
+ m = i + 1
+ nrows = int(document.body[i+1].split('"')[3])
+ ncols = int(document.body[i+1].split('"')[5])
+
+ for k in range(nrows):
+ m = find_token(document.body, "<row", m)
+ caption = get_option(document, m, 'caption', 'false')
+ if caption == 'true':
+ remove_option(document, m, 'caption')
+ for k in range(ncols):
+ m = find_token(document.body, "<cell", m)
+ remove_option(document, m, 'multicolumn')
+ if k == 0:
+ m = find_token(document.body, "\\begin_inset Caption", m)
+ if m == -1:
+ return
+ m = find_end_of_inset(document.body, m + 1)
+ document.body[m] += wrap_into_ert("","","\\backslash\n\\backslash\n%")
+ m = m + 1
+ m = m + 1
+ i = j + 1
+
+
def convert_tablines(document):
i = 0
while True:
lines.append([top, bottom, left, right])
m = m + 1
+ # we will want to ignore longtable captions
+ m = i + 1
+ caption_info = []
+ for k in range(nrows):
+ m = find_token(document.body, "<row", m)
+ caption = get_option(document, m, 'caption', 'false')
+ caption_info.append([caption])
+ m = m + 1
+
m = i + 1
col_info = []
for k in range(ncols):
left = 'true'
for l in range(nrows):
left = lines[l*ncols + k][2]
- if left == 'false':
+ if left == 'false' and caption_info[l] == 'false':
break
set_option(document, m, 'leftline', left)
right = 'true'
for l in range(nrows):
right = lines[l*ncols + k][3]
- if right == 'false':
+ if right == 'false' and caption_info[l] == 'false':
break
set_option(document, m, 'rightline', right)
m = m + 1
top = lines[k*ncols + l][0]
if top == 'false':
break
+ if caption_info[k] == 'false':
+ top = 'false'
set_option(document, m, 'topline', top)
bottom = 'true'
for l in range(ncols):
bottom = lines[k*ncols + l][1]
if bottom == 'false':
break
+ if caption_info[k] == 'false':
+ bottom = 'false'
set_option(document, m, 'bottomline', bottom)
m = m + 1
document.body.insert(i + 4, "\\end_inset")
i += 2
# Generic, \\ -> \backslash:
- g = wrap_into_ert(g, r'\\', '\\backslash{}')
+ g = wrap_into_ert(g, r'\\', '\\backslash')
g = wrap_into_ert(g, '{', '{')
g = wrap_into_ert(g, '}', '}')
document.body.insert(i + 3, g)
document.body[i + 1] = "LatexCommand index"
# clean up multiline stuff
content = ""
+ ert_end = 0
for k in range(i + 3, j - 2):
line = document.body[k]
if line.startswith("\\begin_inset ERT"):
- line = line[16:]
+ ert_end = find_end_of_inset(document.body, k + 1)
+ line = line[16:]
if line.startswith("\\begin_inset Formula"):
line = line[20:]
if line.startswith("\\begin_layout Standard"):
line = line[22:]
- if line.startswith("\\begin_layout Plain"):
- line = line[22:]
+ if line.startswith("\\begin_layout Plain Layout"):
+ line = line[26:]
if line.startswith("\\end_layout"):
line = line[11:]
if line.startswith("\\end_inset"):
line = line[10:]
if line.startswith("status collapsed"):
line = line[16:]
- line = line.replace(u'ä', r'\\\"a').replace(u'ö', r'\\\"o').replace(u'ü', r'\\\"u')
+ if line.startswith("status open"):
+ line = line[11:]
+ # a lossless reversion is not possible
+ # try at least to handle some common insets and settings
+ # do not replace inside ERTs
+ if ert_end < k:
+ line = line.replace(u'ä', r'\\\"a').replace(u'ö', r'\\\"o').replace(u'ü', r'\\\"u')
+ line = line.replace(r'\\backslash', r'\\textbackslash{}')
+ line = line.replace(r'\\series bold', r'\\bfseries{}').replace(r'\\series default', r'\\mdseries{}')
+ line = line.replace(r'\\shape italic', r'\\itshape{}').replace(r'\\shape smallcaps', r'\\scshape{}')
+ line = line.replace(r'\\shape slanted', r'\\slshape{}').replace(r'\\shape default', r'\\upshape{}')
+ line = line.replace(r'\\emph on', r'\\em{}').replace(r'\\emph default', r'\\em{}')
+ line = line.replace(r'\\noun on', r'\\scshape{}').replace(r'\\noun default', r'\\upshape{}')
+ line = line.replace(r'\\bar under', r'\\underbar{').replace(r'\\bar default', r'}')
+ line = line.replace(r'\\family sans', r'\\sffamily{}').replace(r'\\family default', r'\\normalfont{}')
+ line = line.replace(r'\\family typewriter', r'\\ttfamily{}').replace(r'\\family roman', r'\\rmfamily{}')
+ line = line.replace(r'\\InsetSpace ', r'').replace(r'\\SpecialChar ', r'')
+ else:
+ line = line.replace(r'\\backslash', r'\\')
content = content + line;
document.body[i + 3] = "name " + '"' + content + '"'
for k in range(i + 4, j - 2):
" Revert sideways custom floats. "
i = 0
while 1:
- i = find_token(document.body, "\\begin_inset Float", i)
+ # whitespace intended (exclude \\begin_inset FloatList)
+ i = find_token(document.body, "\\begin_inset Float ", i)
if i == -1:
return
line = document.body[i]
r = re.compile(r'\\begin_inset Float (.*)$')
m = r.match(line)
+ if m == None:
+ document.warning("Unable to match line " + str(i) + " of body!")
+ i += 1
+ continue
floattype = m.group(1)
if floattype == "figure" or floattype == "table":
i = i + 1
" Revert wide sideways floats. "
i = 0
while 1:
- i = find_token(document.body, '\\begin_inset Float', i)
+ # whitespace intended (exclude \\begin_inset FloatList)
+ i = find_token(document.body, '\\begin_inset Float ', i)
if i == -1:
return
line = document.body[i]
r = re.compile(r'\\begin_inset Float (.*)$')
m = r.match(line)
+ if m == None:
+ document.warning("Unable to match line " + str(i) + " of body!")
+ i += 1
+ continue
floattype = m.group(1)
if floattype != "figure" and floattype != "table":
i = i + 1
" Revert subfloats. "
i = 0
while 1:
- i = find_token(document.body, '\\begin_inset Float', i)
+ # whitespace intended (exclude \\begin_inset FloatList)
+ i = find_token(document.body, '\\begin_inset Float ', i)
if i == -1:
return
while 1:
i = i + 1
continue
# look for embedded float (= subfloat)
- k = find_token(document.body, '\\begin_inset Float', i + 1, j)
+ # whitespace intended (exclude \\begin_inset FloatList)
+ k = find_token(document.body, '\\begin_inset Float ', i + 1, j)
if k == -1:
break
l = find_end_of_inset(document.body, k)
def convert_spaceinset(document):
- " Convert '\\InsetSpace foo' to '\\begin_inset Space foo\n\\end_inset' "
- for i in range(len(document.body)):
- if re.search(r'\InsetSpace', document.body[i]):
- document.body[i] = document.body[i].replace('\\InsetSpace', '\n\\begin_inset Space')
- document.body[i] = document.body[i] + "\n\\end_inset"
+ " Convert '\\InsetSpace foo' to '\\begin_inset Space foo\n\\end_inset' "
+ for i in range(len(document.body)):
+ m = re.match(r'(.*)\\InsetSpace (.*)', document.body[i])
+ if m:
+ before = m.group(1)
+ after = m.group(2)
+ subst = [before, "\\begin_inset Space " + after, "\\end_inset"]
+ document.body[i: i+1] = subst
def revert_spaceinset(document):
del document.header[i]
+def revert_graphics_group(document):
+ ' Revert group information from graphics insets '
+ i = 0
+ while 1:
+ i = find_token(document.body, "\\begin_inset Graphics", i)
+ if i == -1:
+ return
+ j = find_end_of_inset(document.body, i)
+ if j == -1:
+ document.warning("Malformed lyx document: Missing '\\end_inset'.")
+ i = i + 1
+ continue
+ k = find_token(document.body, " groupId", i, j)
+ if k == -1:
+ i = i + 1
+ continue
+ del document.body[k]
+ i = i + 1
+
+
+def update_apa_styles(document):
+ ' Replace obsolete styles '
+
+ if document.textclass != "apa":
+ return
+
+ obsoletedby = { "Acknowledgments": "Acknowledgements",
+ "Section*": "Section",
+ "Subsection*": "Subsection",
+ "Subsubsection*": "Subsubsection",
+ "Paragraph*": "Paragraph",
+ "Subparagraph*": "Subparagraph"}
+ i = 0
+ while 1:
+ i = find_token(document.body, "\\begin_layout", i)
+ if i == -1:
+ return
+
+ layout = document.body[i][14:]
+ if layout in obsoletedby:
+ document.body[i] = "\\begin_layout " + obsoletedby[layout]
+
+ i += 1
+
+
+def convert_paper_sizes(document):
+ ' exchange size options legalpaper and executivepaper to correct order '
+ # routine is needed to fix http://bugzilla.lyx.org/show_bug.cgi?id=4868
+ i = 0
+ j = 0
+ i = find_token(document.header, "\\papersize executivepaper", 0)
+ if i != -1:
+ document.header[i] = "\\papersize legalpaper"
+ return
+ j = find_token(document.header, "\\papersize legalpaper", 0)
+ if j != -1:
+ document.header[j] = "\\papersize executivepaper"
+
+
+def revert_paper_sizes(document):
+ ' exchange size options legalpaper and executivepaper to correct order '
+ i = 0
+ j = 0
+ i = find_token(document.header, "\\papersize executivepaper", 0)
+ if i != -1:
+ document.header[i] = "\\papersize legalpaper"
+ return
+ j = find_token(document.header, "\\papersize legalpaper", 0)
+ if j != -1:
+ document.header[j] = "\\papersize executivepaper"
+
+
+def convert_InsetSpace(document):
+ " Convert '\\begin_inset Space foo' to '\\begin_inset space foo'"
+ i = 0
+ while True:
+ i = find_token(document.body, "\\begin_inset Space", i)
+ if i == -1:
+ return
+ document.body[i] = document.body[i].replace('\\begin_inset Space', '\\begin_inset space')
+
+
+def revert_InsetSpace(document):
+ " Revert '\\begin_inset space foo' to '\\begin_inset Space foo'"
+ i = 0
+ while True:
+ i = find_token(document.body, "\\begin_inset space", i)
+ if i == -1:
+ return
+ document.body[i] = document.body[i].replace('\\begin_inset space', '\\begin_inset Space')
+
+
##
# Conversion hub
#
[327, []],
[328, [remove_embedding, remove_extra_embedded_files, remove_inzip_options]],
[329, []],
- [330, []],
+ [330, []],
+ [331, [convert_ltcaption]],
+ [332, []],
+ [333, [update_apa_styles]],
+ [334, [convert_paper_sizes]],
+ [335, [convert_InsetSpace]],
]
-revert = [[329, [revert_leftarrowfill, revert_rightarrowfill, revert_upbracefill, revert_downbracefill]],
- [328, [revert_master]],
+revert = [[334, [revert_InsetSpace]],
+ [333, [revert_paper_sizes]],
+ [332, []],
+ [331, [revert_graphics_group]],
+ [330, [revert_ltcaption]],
+ [329, [revert_leftarrowfill, revert_rightarrowfill, revert_upbracefill, revert_downbracefill]],
+ [328, [revert_master]],
[327, []],
[326, [revert_mexican]],
[325, [revert_pdfpages]],