X-Git-Url: https://git.lyx.org/gitweb/?a=blobdiff_plain;f=lib%2Flyx2lyx%2Fparser_tools.py;h=43ebcd091c3d90625e483bed50fd3a408014ab04;hb=0db238a371fe9b9455cea32d88c8c5d4216fc9d9;hp=95f60d22fc802b311732fefba46b0dbc5c618c65;hpb=296632a2c33ed1f363078f60981f195598cfa908;p=lyx.git diff --git a/lib/lyx2lyx/parser_tools.py b/lib/lyx2lyx/parser_tools.py index 95f60d22fc..43ebcd091c 100644 --- a/lib/lyx2lyx/parser_tools.py +++ b/lib/lyx2lyx/parser_tools.py @@ -1,6 +1,7 @@ # This file is part of lyx2lyx -# -*- coding: iso-8859-1 -*- -# Copyright (C) 2002-2004 Dekel Tsur , José Matos +# -*- coding: utf-8 -*- +# Copyright (C) 2002-2010 Dekel Tsur , +# José Matos , Richard Heck # # This program is free software; you can redistribute it and/or # modify it under the terms of the GNU General Public License @@ -16,341 +17,243 @@ # along with this program; if not, write to the Free Software # Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. -import string -import re +" This modules offer several free functions to help parse lines. " +# Utilities for one line def check_token(line, token): - if line[:len(token)] == token: - return 1 - return 0 + """ check_token(line, token) -> bool + + Return True if token is present in line and is the first element + else returns False.""" + + return line[:len(token)] == token + + +def is_nonempty_line(line): + """ is_nonempty_line(line) -> bool + + Return False if line is either empty or it has only whitespaces, + else return True.""" + return line != " "*len(line) + + +# Utilities for a list of lines +def find_token(lines, token, start, end = 0, exact = False): + """ find_token(lines, token, start[[, end], exact]) -> int + + Return the lowest line where token is found, and is the first + element, in lines[start, end]. + + Return -1 on failure.""" -# We need to check that the char after the token is space, but I think -# we can ignore this -def find_token(lines, token, start, end = 0): if end == 0: - end = len(lines) + end = len(lines) m = len(token) for i in xrange(start, end): - if lines[i][:m] == token: - return i + if exact: + x = lines[i].split() + y = token.split() + if len(x) < len(y): + continue + if x[:len(y)] == y: + return i + else: + if lines[i][:m] == token: + return i return -1 -def find_token2(lines, token, start, end = 0): - if end == 0: - end = len(lines) - for i in xrange(start, end): - x = string.split(lines[i]) - if len(x) > 0 and x[0] == token: - return i - return -1 -def find_tokens(lines, tokens, start, end = 0): +def find_token_exact(lines, token, start, end = 0): + return find_token(lines, token, start, end, True) + + +def find_tokens(lines, tokens, start, end = 0, exact = False): + """ find_tokens(lines, tokens, start[[, end], exact]) -> int + + Return the lowest line where one token in tokens is found, and is + the first element, in lines[start, end]. + + Return -1 on failure.""" if end == 0: - end = len(lines) + end = len(lines) + for i in xrange(start, end): - line = lines[i] - for token in tokens: - if line[:len(token)] == token: - return i + for token in tokens: + if exact: + x = lines[i].split() + y = token.split() + if len(x) < len(y): + continue + if x[:len(y)] == y: + return i + else: + if lines[i][:len(token)] == token: + return i return -1 + +def find_tokens_exact(lines, tokens, start, end = 0): + return find_tokens(lines, tokens, start, end, True) + + def find_re(lines, rexp, start, end = 0): + """ find_token_re(lines, rexp, start[, end]) -> int + + Return the lowest line where rexp, a regular expression, is found + in lines[start, end]. + + Return -1 on failure.""" + if end == 0: - end = len(lines) + end = len(lines) for i in xrange(start, end): - if rexp.match(lines[i]): - return i + if rexp.match(lines[i]): + return i return -1 + def find_token_backwards(lines, token, start): - m = len(token) - for i in xrange(start, -1, -1): - line = lines[i] - if line[:m] == token: - return i - return -1 + """ find_token_backwards(lines, token, start) -> int -def find_tokens_backwards(lines, tokens, start): + Return the highest line where token is found, and is the first + element, in lines[start, end]. + + Return -1 on failure.""" + m = len(token) for i in xrange(start, -1, -1): - line = lines[i] - for token in tokens: - if line[:len(token)] == token: - return i + line = lines[i] + if line[:m] == token: + return i return -1 -def get_value(lines, token, start, end = 0): - i = find_token2(lines, token, start, end) - if i == -1: - return "" - if len(string.split(lines[i])) > 1: - return string.split(lines[i])[1] - else: - return "" -def del_token(lines, token, i, j): - k = find_token2(lines, token, i, j) - if k == -1: - return j - else: - del lines[k] - return j-1 - -# Finds the paragraph that contains line i. -def get_paragraph(lines, i): - while i != -1: - i = find_tokens_backwards(lines, ["\\end_inset", "\\layout"], i) - if i == -1: return -1 - if check_token(lines[i], "\\layout"): - return i - i = find_beginning_of_inset(lines, i) - return -1 +def find_tokens_backwards(lines, tokens, start): + """ find_tokens_backwards(lines, token, start) -> int -# Finds the paragraph after the paragraph that contains line i. -def get_next_paragraph(lines, i): - while i != -1: - i = find_tokens(lines, ["\\begin_inset", "\\layout", "\\end_float", "\\the_end"], i) - if not check_token(lines[i], "\\begin_inset"): - return i - i = find_end_of_inset(lines, i) - return -1 + Return the highest line where token is found, and is the first + element, in lines[end, start]. -def find_end_of(lines, i, start_token, end_token): - count = 1 - n = len(lines) - while i < n: - i = find_tokens(lines, [end_token, start_token], i+1) - if check_token(lines[i], start_token): - count = count+1 - else: - count = count-1 - if count == 0: - return i + Return -1 on failure.""" + for i in xrange(start, -1, -1): + line = lines[i] + for token in tokens: + if line[:len(token)] == token: + return i return -1 -# Finds the matching \end_inset -def find_beginning_of(lines, i, start_token, end_token): - count = 1 - while i > 0: - i = find_tokens_backwards(lines, [start_token, end_token], i-1) - if check_token(lines[i], end_token): - count = count+1 - else: - count = count-1 - if count == 0: - return i - return -1 -# Finds the matching \end_inset -def find_end_of_inset(lines, i): - return find_end_of(lines, i, "\\begin_inset", "\\end_inset") +def get_value(lines, token, start, end = 0, default = ""): + """ get_value(lines, token, start[[, end], default]) -> list of strings -# Finds the matching \end_inset -def find_beginning_of_inset(lines, i): - return find_beginning_of(lines, i, "\\begin_inset", "\\end_inset") + Return tokens after token for the first line, in lines, where + token is the first element.""" -def find_end_of_tabular(lines, i): - return find_end_of(lines, i, " 1: + return lines[i].split()[1] + else: + return default -def get_tabular_lines(lines, i): - result = [] - i = i+1 - j = find_end_of_tabular(lines, i) - if j == -1: - return [] - while i <= j: - if check_token(lines[i], "\\begin_inset"): - i = find_end_of_inset(lines, i)+1 - else: - result.append(i) - i = i+1 - return result +def get_value_string(lines, token, start, end = 0, trim = False, default = ""): + """ get_value_string(lines, token, start[[, end], trim, default]) -> string -def is_nonempty_line(line): - return line != " "*len(line) + 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.""" -def find_nonempty_line(lines, start, end = 0): - if end == 0: - end = len(lines) - for i in xrange(start, end): - if is_nonempty_line(lines[i]): - return i - return -1 + i = find_token_exact(lines, token, start, end) + if i == -1: + return default + if len(lines[i].split()) > 1: + for k in range (0, len(lines[i])): + if lines[i][k] == ' ': + if trim ==False: + return lines[i][k+1:len(lines[i])] + else: + return lines[i][k+2:len(lines[i])-1] + else: + return default -## -# Tools for file reading -# -def read_file(header, body, opt): - """Reads a file into the header and body parts""" - preamble = 0 - - while 1: - line = opt.input.readline() - if not line: - opt.error("Invalid LyX file.") - - line = line[:-1] - if check_token(line, '\\begin_preamble'): - preamble = 1 - if check_token(line, '\\end_preamble'): - preamble = 0 - - if not preamble: - line = string.strip(line) - - if not line and not preamble: - break - - header.append(line) - - while 1: - line = opt.input.readline() - if not line: - break - body.append(line[:-1]) - -def write_file(header, body, opt): - for line in header: - opt.output.write(line+"\n") - opt.output.write("\n") - for line in body: - opt.output.write(line+"\n") - -## -# lyx version -# -original_version = re.compile(r"\#LyX (\S*)") -def read_version(header): - for line in header: - if line[0] != "#": - return None +def del_token(lines, token, start, end): + """ del_token(lines, token, start, end) -> int - result = original_version.match(line) - if result: - return result.group(1) - return None + Find the lower line in lines where token is the first element and + delete that line. -def set_version(lines, version): - lines[0] = "#LyX %s created this file. For more info see http://www.lyx.org/" % version - if lines[1][0] == '#': - del lines[1] + Returns the number of lines remaining.""" -## -# file format version -# -format_re = re.compile(r"(\d)[\.,]?(\d\d)") -fileformat = re.compile(r"\\lyxformat\s*(\S*)") -lst_ft = [210, 215, 216, 217, 218, 220, 221, 223, 224, 225, 226, 227, 228, 229, - 230, 231, 232] - -format_relation = [("0_10", [210], ["0.10.7","0.10"]), - ("0_12", [215], ["0.12","0.12.1","0.12"]), - ("1_0_0", [215], ["1.0.0","1.0"]), - ("1_0_1", [215], ["1.0.1","1.0.2","1.0.3","1.0.4", "1.1.2","1.1"]), - ("1_1_4", [215], ["1.1.4","1.1"]), - ("1_1_5", [216], ["1.1.5","1.1.5fix1","1.1.5fix2","1.1"]), - ("1_1_6", [217], ["1.1.6","1.1.6fix1","1.1.6fix2","1.1"]), - ("1_1_6fix3", [218], ["1.1.6fix3","1.1.6fix4","1.1"]), - ("1_2", [220], ["1.2.0","1.2.1","1.2.3","1.2.4","1.2"]), - ("1_3", [221], ["1.3.0","1.3.1","1.3.2","1.3.3","1.3.4","1.3"]), - ("1_4", [223,224,225,226,227,228,229,230,231,232], ["1.4.0cvs","1.4"])] - -def lyxformat(format, opt): - result = format_re.match(format) - if result: - format = int(result.group(1) + result.group(2)) + k = find_token_exact(lines, token, start, end) + if k == -1: + return end else: - opt.error(str(format) + ": " + "Invalid LyX file.") + del lines[k] + return end - 1 - if format in lst_ft: - return format - opt.error(str(format) + ": " + "Format no supported.") - return None +def find_beginning_of(lines, i, start_token, end_token): + count = 1 + while i > 0: + i = find_tokens_backwards(lines, [start_token, end_token], i-1) + if i == -1: + return -1 + if check_token(lines[i], end_token): + count = count+1 + else: + count = count-1 + if count == 0: + return i + return -1 -def read_format(header, opt): - for line in header: - result = fileformat.match(line) - if result: - return lyxformat(result.group(1), opt) - else: - opt.error("Invalid LyX File.") - return None -def set_format(lines, number): - if int(number) <= 217: - number = float(number)/100 - i = find_token(lines, "\\lyxformat", 0) - lines[i] = "\\lyxformat %s" % number +def find_end_of(lines, i, start_token, end_token): + count = 1 + n = len(lines) + while i < n: + i = find_tokens(lines, [end_token, start_token], i+1) + if i == -1: + return -1 + if check_token(lines[i], start_token): + count = count+1 + else: + count = count-1 + if count == 0: + return i + return -1 -def get_end_format(): - return format_relation[-1:][0][1][-1:][0] -def chain(opt, initial_version): - """ This is where all the decisions related with the convertion are taken""" +def find_nonempty_line(lines, start, end = 0): + if end == 0: + end = len(lines) + for i in xrange(start, end): + if is_nonempty_line(lines[i]): + return i + return -1 - format = opt.format - if opt.start: - if opt.start != format: - opt.warning("%s: %s %s" % ("Proposed file format and input file formats do not match:", opt.start, format)) - else: - opt.start = format - - if not opt.end: - opt.end = get_end_format() - - correct_version = 0 - - for rel in format_relation: - if initial_version in rel[2]: - if format in rel[1]: - initial_step = rel[0] - correct_version = 1 - break - - if not correct_version: - if format <= 215: - opt.warning("Version does not match file format, discarding it.") - for rel in format_relation: - if format in rel[1]: - initial_step = rel[0] - break - else: - # This should not happen, really. - opt.error("Format not supported.") - - # Find the final step - for rel in format_relation: - if opt.end in rel[1]: - final_step = rel[0] - break - else: - opt.error("Format not supported.") - - # Convertion mode, back or forth - steps = [] - if (initial_step, opt.start) < (final_step, opt.end): - mode = "convert" - first_step = 1 - for step in format_relation: - if initial_step <= step[0] <= final_step: - if first_step and len(step[1]) == 1: - first_step = 0 - continue - steps.append(step[0]) - else: - mode = "revert" - relation_format = format_relation - relation_format.reverse() - last_step = None - for step in relation_format: - if final_step <= step[0] <= initial_step: - steps.append(step[0]) - last_step = step +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") - if last_step[1][-1] == opt.end: - steps.pop() - return mode, steps +def find_end_of_layout(lines, i): + " Find end of layout, where lines[i] is included." + return find_end_of(lines, i, "\\begin_layout", "\\end_layout") + + +# checks if line i is in the inset e.g., "\\begin_inset CommandInset ref" +# if so, returns starting and ending lines +# otherwise, returns (-1, -1) +def get_containing_inset(lines, i, inset): + defval = (-1, -1) + stins = find_token_backwards(lines, inset, i) + if stins == -1: + return defval + endins = find_end_of_inset(lines, stins) + # note that this includes the notfound case. + if endins < i: + return defval + return (stins, endins)