X-Git-Url: https://git.lyx.org/gitweb/?a=blobdiff_plain;f=lib%2Flyx2lyx%2Flyx_1_6.py;h=7a3710e47e46f1f3e9be95d77afc47a90ec424b7;hb=c52808ce1a804a875514713eb6f5dcd6f05dd6c8;hp=8a33eaace795b63508bd4aea6a506df195dc17d2;hpb=d7c31dfff3d647b6b16942f0f8c001966a470a4c;p=features.git diff --git a/lib/lyx2lyx/lyx_1_6.py b/lib/lyx2lyx/lyx_1_6.py index 8a33eaace7..7a3710e47e 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 unicode_reps #################################################################### # 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] @@ -129,51 +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) @@ -253,8 +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 @@ -300,7 +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) @@ -407,7 +384,7 @@ def lyx2latex(document, lines): continue inert = ert_end >= curline content += lyxline2latex(document, lines[curline], inert) - + return content @@ -422,6 +399,7 @@ 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]) @@ -513,6 +491,7 @@ 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 @@ -572,9 +551,10 @@ 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 @@ -651,6 +631,7 @@ 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 @@ -773,7 +754,7 @@ 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) @@ -945,7 +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 @@ -953,6 +934,8 @@ 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: @@ -963,7 +946,7 @@ def remove_inzip_options(document): def convert_inset_command(document): - """ + r""" Convert: \begin_inset LatexCommand cmd to @@ -971,7 +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 @@ -1000,7 +983,7 @@ def convert_inset_command(document): def revert_inset_command(document): - """ + r""" Convert: \begin_inset CommandInset InsetType LatexCommand cmd @@ -1010,7 +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 @@ -1080,7 +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: @@ -1112,7 +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) @@ -1233,7 +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 @@ -1241,6 +1224,8 @@ 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): @@ -1573,10 +1558,10 @@ 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://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 @@ -1712,7 +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 @@ -1741,7 +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) @@ -1760,7 +1745,7 @@ 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) @@ -1789,7 +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: @@ -1798,19 +1783,24 @@ 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: @@ -1873,7 +1863,8 @@ 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 @@ -1901,7 +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 @@ -2019,7 +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: @@ -2047,7 +2038,8 @@ 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', '', @@ -2081,7 +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: @@ -2109,7 +2101,8 @@ 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', @@ -2132,7 +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 @@ -2157,7 +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: @@ -2197,7 +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: @@ -2268,7 +2261,7 @@ 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: @@ -2346,7 +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 @@ -2378,6 +2371,7 @@ 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] @@ -2480,6 +2474,7 @@ 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}', \ @@ -2501,6 +2496,7 @@ 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{}', \ @@ -2522,6 +2518,7 @@ 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{}', \ @@ -2543,6 +2540,7 @@ 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{}', \ @@ -2564,6 +2562,7 @@ 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{}', \ @@ -2631,6 +2630,7 @@ 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') @@ -2667,6 +2667,7 @@ 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') @@ -2693,7 +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 @@ -2795,7 +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 @@ -2825,7 +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 @@ -2839,7 +2840,7 @@ 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)