1 # This file is part of lyx2lyx
2 # -*- coding: utf-8 -*-
3 # Copyright (C) 2002-2011 Dekel Tsur <dekel@lyx.org>,
4 # José Matos <jamatos@lyx.org>, Richard Heck <rgheck@comcast.net>
6 # This program is free software; you can redistribute it and/or
7 # modify it under the terms of the GNU General Public License
8 # as published by the Free Software Foundation; either version 2
9 # of the License, or (at your option) any later version.
11 # This program is distributed in the hope that it will be useful,
12 # but WITHOUT ANY WARRANTY; without even the implied warranty of
13 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
14 # GNU General Public License for more details.
16 # You should have received a copy of the GNU General Public License
17 # along with this program; if not, write to the Free Software
18 # Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
22 This modules offer several free functions to help parse lines.
23 More documentaton is below, but here is a quick guide to what
24 they do. Optional arguments are marked by brackets.
26 find_token(lines, token, start[, end[, ignorews]]):
27 Returns the first line i, start <= i < end, on which
28 token is found at the beginning. Returns -1 if not
30 If ignorews is (given and) True, then differences
31 in whitespace do not count, except that there must be no
32 extra whitespace following token itself.
34 find_token_exact(lines, token, start[, end]):
35 As find_token, but with ignorews True.
37 find_tokens(lines, tokens, start[, end[, ignorews]]):
38 Returns the first line i, start <= i < end, on which
39 oen of the tokens in tokens is found at the beginning.
40 Returns -1 if not found.
41 If ignorews is (given and) True, then differences
42 in whitespace do not count, except that there must be no
43 extra whitespace following token itself.
45 find_tokens_exact(lines, token, start[, end]):
46 As find_tokens, but with ignorews True.
48 find_token_backwards(lines, token, start):
49 find_tokens_backwards(lines, tokens, start):
50 As before, but look backwards.
52 find_re(lines, rexp, start[, end]):
53 As find_token, but rexp is a regular expression object,
54 so it has to be passed as e.g.: re.compile(r'...').
56 get_value(lines, token, start[, end[, default]):
57 Similar to find_token, but it returns what follows the
58 token on the found line. Example:
59 get_value(document.header, "\use_xetex", 0)
60 will find a line like:
62 and, in that case, return "true". (Note that whitespace
63 is stripped.) The final argument, default, defaults to "",
64 and is what is returned if we do not find anything. So you
65 can use that to set a default.
67 get_quoted_value(lines, token, start[, end[, default]):
68 Similar to get_value, but it will strip quotes off the
69 value, if they are present. So use this one for cases
70 where the value is normally quoted.
72 get_option_value(line, option):
73 This assumes we have a line with something like:
75 and returns value. Returns "" if not found.
77 del_token(lines, token, start[, end]):
78 Like find_token, but deletes the line if it finds one.
79 Returns True if a line got deleted, otherwise False.
81 find_beginning_of(lines, i, start_token, end_token):
82 Here, start_token and end_token are meant to be a matching
83 pair, like "\begin_layout" and "\end_layout". We look for
84 the start_token that pairs with the end_token that occurs
85 on or after line i. Returns -1 if not found.
86 So, in the layout case, this would find the \begin_layout
87 for the layout line i is in.
89 ec = find_token(document.body, "</cell", i)
90 bc = find_beginning_of(document.body, ec, \
92 Now, assuming no -1s, bc-ec wraps the cell for line i.
94 find_end_of(lines, i, start_token, end_token):
95 Like find_beginning_of, but looking for the matching
96 end_token. This might look like:
97 bc = find_token_(document.body, "<cell", i)
98 ec = find_end_of(document.body, bc, "<cell", "</cell")
99 Now, assuming no -1s, bc-ec wrap the next cell.
101 find_end_of_inset(lines, i):
102 Specialization of find_end_of for insets.
104 find_end_of_layout(lines, i):
105 Specialization of find_end_of for layouts.
107 find_end_of_sequence(lines, i):
108 Find the end of the sequence of layouts of the same kind.
111 is_in_inset(lines, i, inset):
112 Checks if line i is in an inset of the given type.
113 If so, returns starting and ending lines. Otherwise,
116 is_in_inset(document.body, i, "\\begin_inset Tabular")
117 returns False unless i is within a table. If it is, then
118 it returns the line on which the table begins and the one
119 on which it ends. Note that this pair will evaulate to
122 will do what you expect.
124 get_containing_inset(lines, i):
125 Finds out what kind of inset line i is within. Returns a
126 list containing what follows \begin_inset on the the line
127 on which the inset begins, plus the starting and ending line.
128 Returns False on any kind of error or if it isn't in an inset.
129 So get_containing_inset(document.body, i) might return:
130 ("CommandInset ref", 300, 306)
131 if i is within an InsetRef beginning on line 300 and ending
134 get_containing_layout(lines, i):
135 As get_containing_inset, but for layout. Additionally returns the
136 position of real paragraph start (after par params) as 4th value.
139 find_nonempty_line(lines, start[, end):
140 Finds the next non-empty line.
142 check_token(line, token):
143 Does line begin with token?
145 is_nonempty_line(line):
146 Does line contain something besides whitespace?
148 count_pars_in_inset(lines, i):
149 Counts the paragraphs inside an inset.
155 # Utilities for one line
156 def check_token(line, token):
157 """ check_token(line, token) -> bool
159 Return True if token is present in line and is the first element
160 else returns False."""
162 return line[:len(token)] == token
165 def is_nonempty_line(line):
166 """ is_nonempty_line(line) -> bool
168 Return False if line is either empty or it has only whitespaces,
170 return line != " "*len(line)
173 # Utilities for a list of lines
174 def find_token(lines, token, start, end = 0, ignorews = False):
175 """ find_token(lines, token, start[[, end], ignorews]) -> int
177 Return the lowest line where token is found, and is the first
178 element, in lines[start, end].
180 If ignorews is True (default is False), then differences in
181 whitespace are ignored, except that there must be no extra
182 whitespace following token itself.
184 Return -1 on failure."""
186 if end == 0 or end > len(lines):
189 for i in xrange(start, end):
198 if lines[i][:m] == token:
203 def find_token_exact(lines, token, start, end = 0):
204 return find_token(lines, token, start, end, True)
207 def find_tokens(lines, tokens, start, end = 0, ignorews = False):
208 """ find_tokens(lines, tokens, start[[, end], ignorews]) -> int
210 Return the lowest line where one token in tokens is found, and is
211 the first element, in lines[start, end].
213 Return -1 on failure."""
214 if end == 0 or end > len(lines):
217 for i in xrange(start, end):
227 if lines[i][:len(token)] == token:
232 def find_tokens_exact(lines, tokens, start, end = 0):
233 return find_tokens(lines, tokens, start, end, True)
236 def find_re(lines, rexp, start, end = 0):
237 """ find_token_re(lines, rexp, start[, end]) -> int
239 Return the lowest line where rexp, a regular expression, is found
240 in lines[start, end].
242 Return -1 on failure."""
244 if end == 0 or end > len(lines):
246 for i in xrange(start, end):
247 if rexp.match(lines[i]):
252 def find_token_backwards(lines, token, start):
253 """ find_token_backwards(lines, token, start) -> int
255 Return the highest line where token is found, and is the first
256 element, in lines[start, end].
258 Return -1 on failure."""
260 for i in xrange(start, -1, -1):
262 if line[:m] == token:
267 def find_tokens_backwards(lines, tokens, start):
268 """ find_tokens_backwards(lines, token, start) -> int
270 Return the highest line where token is found, and is the first
271 element, in lines[end, start].
273 Return -1 on failure."""
274 for i in xrange(start, -1, -1):
277 if line[:len(token)] == token:
282 def get_value(lines, token, start, end = 0, default = ""):
283 """ get_value(lines, token, start[[, end], default]) -> string
285 Find the next line that looks like:
286 token followed by other stuff
287 Returns "followed by other stuff" with leading and trailing
291 i = find_token_exact(lines, token, start, end)
294 l = lines[i].split(None, 1)
300 def get_quoted_value(lines, token, start, end = 0, default = ""):
301 """ get_quoted_value(lines, token, start[[, end], default]) -> string
303 Find the next line that looks like:
304 token "followed by other stuff"
305 Returns "followed by other stuff" with leading and trailing
306 whitespace and quotes removed. If there are no quotes, that is OK too.
307 So use get_value to preserve possible quotes, this one to remove them,
309 Note that we will NOT strip quotes from default!
311 val = get_value(lines, token, start, end, "")
314 return val.strip('"')
317 def get_option_value(line, option):
318 rx = option + '\s*=\s*"([^"]+)"'
326 def set_option_value(line, option, value):
327 rx = '(' + option + '\s*=\s*")[^"]+"'
332 return re.sub(rx, '\g<1>' + value + '"', line)
335 def del_token(lines, token, start, end = 0):
336 """ del_token(lines, token, start, end) -> int
338 Find the first line in lines where token is the first element
339 and delete that line. Returns True if we deleted a line, False
342 k = find_token_exact(lines, token, start, end)
349 def find_beginning_of(lines, i, start_token, end_token):
352 i = find_tokens_backwards(lines, [start_token, end_token], i-1)
355 if check_token(lines[i], end_token):
364 def find_end_of(lines, i, start_token, end_token):
368 i = find_tokens(lines, [end_token, start_token], i+1)
371 if check_token(lines[i], start_token):
380 def find_nonempty_line(lines, start, end = 0):
383 for i in xrange(start, end):
384 if is_nonempty_line(lines[i]):
389 def find_end_of_inset(lines, i):
390 " Find end of inset, where lines[i] is included."
391 return find_end_of(lines, i, "\\begin_inset", "\\end_inset")
394 def find_end_of_layout(lines, i):
395 " Find end of layout, where lines[i] is included."
396 return find_end_of(lines, i, "\\begin_layout", "\\end_layout")
399 def is_in_inset(lines, i, inset):
401 Checks if line i is in an inset of the given type.
402 If so, returns starting and ending lines.
403 Otherwise, returns False.
405 is_in_inset(document.body, i, "\\begin_inset Tabular")
406 returns False unless i is within a table. If it is, then
407 it returns the line on which the table begins and the one
408 on which it ends. Note that this pair will evaulate to
411 will do what you expect.
414 stins = find_token_backwards(lines, inset, i)
417 endins = find_end_of_inset(lines, stins)
418 # note that this includes the notfound case.
421 return (stins, endins)
424 def get_containing_inset(lines, i):
426 Finds out what kind of inset line i is within. Returns a
427 list containing (i) what follows \begin_inset on the the line
428 on which the inset begins, plus the starting and ending line.
429 Returns False on any kind of error or if it isn't in an inset.
433 stins = find_token_backwards(lines, "\\begin_inset", j)
436 endins = find_end_of_inset(lines, stins)
441 inset = get_value(lines, "\\begin_inset", stins)
445 return (inset, stins, endins)
448 def get_containing_layout(lines, i):
450 Finds out what kind of layout line i is within. Returns a
451 list containing (i) what follows \begin_layout on the the line
452 on which the layout begins, plus the starting and ending line
453 and the start of the apargraph (after all params).
454 Returns False on any kind of error.
458 stlay = find_token_backwards(lines, "\\begin_layout", j)
461 endlay = find_end_of_layout(lines, stlay)
466 lay = get_value(lines, "\\begin_layout", stlay)
470 par_params = ["\\noindent", "\\indent", "\\indent-toggle", "\\leftindent",
471 "\\start_of_appendix", "\\paragraph_spacing single",
472 "\\paragraph_spacing onehalf", "\\paragraph_spacing double",
473 "\\paragraph_spacing other", "\\align", "\\labelwidthstring"]
477 if lines[stpar] not in par_params:
479 return (lay, stlay, endlay, stpar)
482 def count_pars_in_inset(lines, i):
484 Counts the paragraphs within this inset
486 ins = get_containing_inset(lines, i)
490 for j in range(ins[1], ins[2]):
491 m = re.match(r'\\begin_layout (.*)', lines[j])
492 if m and get_containing_inset(lines, j)[0] == ins[0]:
498 def find_end_of_sequence(lines, i):
500 Returns the end of a sequence of identical layouts.
502 lay = get_containing_layout(lines, i)
509 m = re.match(r'\\begin_layout (.*)', lines[i])
510 if m and m.group(1) != layout:
512 elif lines[i] == "\\begin_deeper":
513 j = find_end_of(lines, i, "\\begin_deeper", "\\end_deeper")
517 if m and m.group(1) == layout:
518 endlay = find_end_of_layout(lines, i)
521 if i == len(lines) - 1: