X-Git-Url: https://git.lyx.org/gitweb/?a=blobdiff_plain;f=lib%2Flyx2lyx%2Flyx_1_6.py;h=071280836b670f61213117e800e25e9764eedaaa;hb=648ddd25eca045f34569405aca15c5d638bbb723;hp=d11ed229745174eda299ce0a65d5223da01c8a83;hpb=5ef8c7bc54d8157c9afe8ec8565ae0f5e09a44d0;p=lyx.git diff --git a/lib/lyx2lyx/lyx_1_6.py b/lib/lyx2lyx/lyx_1_6.py index d11ed22974..071280836b 100644 --- a/lib/lyx2lyx/lyx_1_6.py +++ b/lib/lyx2lyx/lyx_1_6.py @@ -14,7 +14,7 @@ # # 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 """ Convert files to the file format generated by lyx 1.6""" @@ -22,11 +22,28 @@ import re import unicodedata import sys, os -from parser_tools import find_token, find_end_of, find_tokens, get_value, get_value_string +from parser_tools import find_token, find_end_of, find_tokens, get_value +from unicode_symbols import read_unicodesymbols #################################################################### # Private helper functions + +def get_value_string(lines, token, start, end = 0, trim = False, default = ""): + """ get_value_string(lines, token, start[[, end], trim, default]) -> string + + Return tokens after token as string, in lines, where + token is the first element. When trim is used, the first and last character + of the string is trimmed.""" + + val = get_value(lines, token, start, end, "") + if not val: + return default + if trim: + return val[1:-1] + return val + + def find_end_of_inset(lines, i): " Find end of inset, where lines[i] is included." return find_end_of(lines, i, "\\begin_inset", "\\end_inset") @@ -35,7 +52,7 @@ def find_end_of_inset(lines, i): # DO NOT do this: # document.body[i] = wrap_insert_ert(...) # wrap_into_ert may returns a multiline string, which should NOT appear -# in document.body. Insetad, do something like this: +# in document.body. Instead, do something like this: # subst = wrap_inset_ert(...) # subst = subst.split('\n') # document.body[i:i+1] = subst @@ -78,7 +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] @@ -129,8 +146,18 @@ def set_option(document, m, option, value): return l -def read_unicodesymbols(): +# FIXME: Remove this function if the version imported from unicode_symbols works. +# This function was the predecessor from that function, that in the meanwhile got +# new fixes. +def read_unicodesymbols2(): " Read the unicodesymbols list of unicode characters and corresponding commands." + + # 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 + pathname = os.path.abspath(os.path.dirname(sys.argv[0])) fp = open(os.path.join(pathname.strip('lyx2lyx'), 'unicodesymbols')) spec_chars = [] @@ -209,7 +236,7 @@ def extract_argument(line): return (line[:pos + 1], line[pos + 1:]) -def latex2ert(line): +def latex2ert(line, isindex): '''Converts LaTeX commands into ERT. line may well be a multi-line string when it is returned.''' if not line: @@ -246,6 +273,9 @@ def latex2ert(line): # put all remaining braces in ERT line = wrap_into_ert(line, '}', '}') line = wrap_into_ert(line, '{', '{') + if isindex: + # active character that is not available in all font encodings + line = wrap_into_ert(line, '|', '|') retval += line return retval @@ -257,10 +287,12 @@ unicode_reps = read_unicodesymbols() #end up inside ERT. That routine could be modified so that it returned #a list of lines, and we could then skip ERT bits and only deal with #the other bits. -def latex2lyx(data): +def latex2lyx(data, isindex): '''Takes a string, possibly multi-line, and returns the result of converting LaTeX constructs into LyX constructs. Returns a list of - lines, suitable for insertion into document.body.''' + lines, suitable for insertion into document.body. + The bool isindex specifies whether we are in an index macro (which + has some specific active characters that need to be ERTed).''' if not data: return [""] @@ -309,14 +341,14 @@ def latex2lyx(data): g = m.group(3) if s: # this is non-math! - s = latex2ert(s) + s = latex2ert(s, isindex) subst = s.split('\n') retval += subst retval.append("\\begin_inset Formula " + f) retval.append("\\end_inset") m = mathre.match(g) # Handle whatever is left, which is just text - g = latex2ert(g) + g = latex2ert(g, isindex) subst = g.split('\n') retval += subst return retval @@ -402,7 +434,7 @@ def lyx2latex(document, lines): continue inert = ert_end >= curline content += lyxline2latex(document, lines[curline], inert) - + return content @@ -417,6 +449,7 @@ def convert_ltcaption(document): j = find_end_of_inset(document.body, i + 1) if j == -1: document.warning("Malformed LyX document: Could not find end of tabular.") + i += 1 continue nrows = int(document.body[i+1].split('"')[3]) @@ -467,6 +500,7 @@ def revert_ltcaption(document): j = find_end_of_inset(document.body, i + 1) if j == -1: document.warning("Malformed LyX document: Could not find end of tabular.") + i += 1 continue m = i + 1 @@ -507,6 +541,7 @@ def convert_tablines(document): j = find_end_of_inset(document.body, i + 1) if j == -1: document.warning("Malformed LyX document: Could not find end of tabular.") + i += 1 continue m = i + 1 @@ -566,9 +601,10 @@ def revert_tablines(document): i = find_token(document.body, "\\begin_inset Tabular", i) if i == -1: return - j = find_end_of_inset(document.body, i + 1) + j = find_end_of_inset(document.body, i) if j == -1: document.warning("Malformed LyX document: Could not find end of tabular.") + i += 1 continue m = i + 1 @@ -645,6 +681,7 @@ def fix_wrong_tables(document): j = find_end_of_inset(document.body, i + 1) if j == -1: document.warning("Malformed LyX document: Could not find end of tabular.") + i += 1 continue m = i + 1 @@ -767,7 +804,7 @@ def convert_flex(document): document.body[i] = document.body[i].replace('\\begin_inset CharStyle', '\\begin_inset Flex') def revert_flex(document): - "Convert Flex to CharStyle" + "Revert Flex to CharStyle" i = 0 while True: i = find_token(document.body, "\\begin_inset Flex", i) @@ -939,7 +976,7 @@ 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 @@ -947,6 +984,8 @@ def remove_inzip_options(document): if j == -1: # should not happen document.warning("Malformed LyX document: Could not find end of graphics inset.") + i += 1 + continue # If there's a inzip param, just remove that k = find_token(document.body, "\tinzipName", i + 1, j) if k != -1: @@ -965,7 +1004,7 @@ 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 @@ -1004,7 +1043,7 @@ 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 @@ -1074,7 +1113,7 @@ 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: @@ -1096,7 +1135,7 @@ def convert_latexcommand_index(document): linelist = [""] else: fullcontent = m.group(1) - linelist = latex2lyx(fullcontent) + linelist = latex2lyx(fullcontent, True) #document.warning(fullcontent) linelist = ["\\begin_inset Index", "status collapsed", "\\begin_layout Standard", ""] + \ @@ -1106,7 +1145,7 @@ 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) @@ -1227,7 +1266,7 @@ 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 @@ -1235,6 +1274,8 @@ def revert_inset_info(document): if j == -1: # should not happen document.warning("Malformed LyX document: Could not find end of Info inset.") + i += 1 + continue type = 'unknown' arg = '' for k in range(i, j+1): @@ -1321,13 +1362,13 @@ def convert_url(document): j = find_token(document.body, "target", i) if j == -1: document.warning("Malformed LyX document: Can't find target for url inset") - i = j + i += 1 continue target = document.body[j][8:-1] k = find_token(document.body, "\\end_inset", j) if k == -1: document.warning("Malformed LyX document: Can't find end of url inset") - i = k + i = j continue newstuff = ["\\begin_inset Flex URL", "status collapsed", "", @@ -1337,7 +1378,7 @@ def convert_url(document): "\\end_layout", ""] document.body[i:k] = newstuff - i = k + i = i + len(newstuff) def convert_ams_classes(document): tc = document.textclass @@ -1570,7 +1611,7 @@ def convert_macro_global(document): "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://bugzilla.lyx.org/show_bug.cgi?id=5371 + # http://www.lyx.org/trac/ticket/5371 # We're looking for something like this: # \begin_inset ERT # status collapsed @@ -1706,7 +1747,7 @@ 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 @@ -1735,7 +1776,7 @@ 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) @@ -1754,7 +1795,7 @@ def revert_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) @@ -1783,7 +1824,7 @@ 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: @@ -1792,19 +1833,24 @@ def revert_framed_notes(document): if j == -1: # should not happen document.warning("Malformed LyX document: Could not find end of Box inset.") + i += 1 + continue k = find_token(document.body, "status", i + 1, j) if k == -1: document.warning("Malformed LyX document: Missing `status' tag in Box inset.") - return + i = j + continue status = document.body[k] l = find_default_layout(document, i + 1, j) if l == -1: document.warning("Malformed LyX document: Missing `\\begin_layout' in Box inset.") - return + i = j + continue m = find_token(document.body, "\\end_layout", i + 1, j) if m == -1: document.warning("Malformed LyX document: Missing `\\end_layout' in Box inset.") - return + i = j + continue ibox = find_token(document.body, "has_inner_box 1", i + 1, k) pbox = find_token(document.body, "use_parbox 1", i + 1, k) if ibox == -1 and pbox == -1: @@ -1867,7 +1913,8 @@ def revert_nobreakdash(document): j = find_token(document.header, "\\use_amsmath", 0) if j == -1: document.warning("Malformed LyX document: Missing '\\use_amsmath'.") - return + i += 1 + continue document.header[j] = "\\use_amsmath 2" else: i = i + 1 @@ -1895,7 +1942,7 @@ 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 @@ -2013,7 +2060,7 @@ 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: @@ -2041,7 +2088,8 @@ def revert_rotfloat(document): l = find_default_layout(document, i + 1, j) if l == -1: document.warning("Malformed LyX document: Missing `\\begin_layout' in Float inset.") - return + i = j + continue subst = ['\\begin_layout Standard', '\\begin_inset ERT', 'status collapsed', '', @@ -2075,7 +2123,7 @@ 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: @@ -2103,7 +2151,8 @@ def revert_widesideways(document): l = find_default_layout(document, i + 1, j) if l == -1: document.warning("Malformed LyX document: Missing `\\begin_layout' in Float inset.") - return + i = j + continue subst = ['\\begin_layout Standard', '\\begin_inset ERT', 'status collapsed', '', '\\begin_layout Standard', '', '', '\\backslash', @@ -2126,7 +2175,7 @@ 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 @@ -2151,7 +2200,7 @@ 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: @@ -2176,7 +2225,7 @@ def convert_subfig(document): addedLines -= 1 subst = ['\\begin_inset Float figure', 'wide false', 'sideways false', 'status open', '', '\\begin_layout Plain Layout', '\\begin_inset Caption', - '', '\\begin_layout Plain Layout'] + latex2lyx(caption) + \ + '', '\\begin_layout Plain Layout'] + latex2lyx(caption, False) + \ [ '\\end_layout', '', '\\end_inset', '', '\\end_layout', '', '\\begin_layout Plain Layout'] document.body[i : i] = subst @@ -2191,7 +2240,7 @@ 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: @@ -2262,7 +2311,7 @@ def revert_subfig(document): if opt != -1: optend = find_end_of_inset(document.body, opt) if optend == -1: - document.warning("Malformed lyx document: Missing '\\end_inset' (OptArg).") + document.warning("Malformed LyX document: Missing '\\end_inset' (OptArg).") return optc = find_default_layout(document, opt, optend) if optc == -1: @@ -2372,6 +2421,7 @@ def revert_spaceinset(document): j = find_end_of_inset(document.body, i) if j == -1: document.warning("Malformed LyX document: Could not find end of space inset.") + i += 1 continue document.body[i] = document.body[i].replace('\\begin_inset Space', '\\InsetSpace') del document.body[j] @@ -2474,6 +2524,7 @@ def revert_protected_hfill(document): j = find_end_of_inset(document.body, i) if j == -1: document.warning("Malformed LyX document: Could not find end of space inset.") + i += 1 continue del document.body[j] subst = document.body[i].replace('\\begin_inset Space \\hspace*{\\fill}', \ @@ -2495,6 +2546,7 @@ def revert_leftarrowfill(document): j = find_end_of_inset(document.body, i) if j == -1: document.warning("Malformed LyX document: Could not find end of space inset.") + i += 1 continue del document.body[j] subst = document.body[i].replace('\\begin_inset Space \\leftarrowfill{}', \ @@ -2516,6 +2568,7 @@ def revert_rightarrowfill(document): j = find_end_of_inset(document.body, i) if j == -1: document.warning("Malformed LyX document: Could not find end of space inset.") + i += 1 continue del document.body[j] subst = document.body[i].replace('\\begin_inset Space \\rightarrowfill{}', \ @@ -2537,6 +2590,7 @@ def revert_upbracefill(document): j = find_end_of_inset(document.body, i) if j == -1: document.warning("Malformed LyX document: Could not find end of space inset.") + i += 1 continue del document.body[j] subst = document.body[i].replace('\\begin_inset Space \\upbracefill{}', \ @@ -2558,6 +2612,7 @@ def revert_downbracefill(document): j = find_end_of_inset(document.body, i) if j == -1: document.warning("Malformed LyX document: Could not find end of space inset.") + i += 1 continue del document.body[j] subst = document.body[i].replace('\\begin_inset Space \\downbracefill{}', \ @@ -2625,6 +2680,7 @@ def revert_pagebreaks(document): j = find_end_of_inset(document.body, i) if j == -1: document.warning("Malformed LyX document: Could not find end of Newpage inset.") + i += 1 continue del document.body[j] document.body[i] = document.body[i].replace('\\begin_inset Newpage newpage', '\\newpage') @@ -2661,6 +2717,7 @@ def revert_linebreaks(document): j = find_end_of_inset(document.body, i) if j == -1: document.warning("Malformed LyX document: Could not find end of Newline inset.") + i += 1 continue del document.body[j] document.body[i] = document.body[i].replace('\\begin_inset Newline newline', '\\newline') @@ -2687,7 +2744,7 @@ 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 @@ -2789,7 +2846,7 @@ 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 @@ -2819,7 +2876,7 @@ 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 @@ -2833,7 +2890,7 @@ def update_apa_styles(document): 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 + # routine is needed to fix http://www.lyx.org/trac/ticket/4868 i = 0 j = 0 i = find_token(document.header, "\\papersize executivepaper", 0)