# This file is part of lyx2lyx
# -*- coding: utf-8 -*-
# Copyright (C) 2002-2011 Dekel Tsur <dekel@lyx.org>,
-# José Matos <jamatos@lyx.org>, Richard Heck <rgheck@comcast.net>
+# José Matos <jamatos@lyx.org>, Richard Kimberly Heck <rikiheck@lyx.org>
#
# This program is free software; you can redistribute it and/or
# modify it under the terms of the GNU General Public License
find_tokens_backwards(lines, tokens, start):
As before, but look backwards.
+find_substring(lines, sub[, start[, end]]) -> int
+ As find_token, but sub may be anywhere in the line.
+
find_re(lines, rexp, start[, end]):
As find_token, but rexp is a regular expression object,
so it has to be passed as e.g.: re.compile(r'...').
is stripped.) The final argument, default, defaults to "",
and is what is returned if we do not find anything. So you
can use that to set a default.
+ If delete is True, then delete the line if found.
get_quoted_value(lines, token[, start[, end[, default[, delete]]]]):
Similar to get_value, but it will strip quotes off the
get_bool_value(lines, token[, start[, end[, default, delete]]]]):
Like get_value, but returns a boolean.
-del_token(lines, token, start[, end]):
+set_bool_value(lines, token, value[, start[, end]]):
+ Find `token` in `lines[start:end]` and set to boolean value bool(`value`).
+ Return old value. Raise ValueError if token is not in lines.
+
+del_token(lines, token[, start[, end]]):
Like find_token, but deletes the line if it finds one.
Returns True if a line got deleted, otherwise False.
+ Use get_* with the optional argument "delete=True", if you want to
+ get and delete a token.
+
find_beginning_of(lines, i, start_token, end_token):
Here, start_token and end_token are meant to be a matching
pair, like "\\begin_layout" and "\\end_layout". We look for
find_end_of_sequence(lines, i):
Find the end of the sequence of layouts of the same kind.
Considers nesting. If the last paragraph in sequence is nested,
- the position of the last \end_deeper is returned, else
- the position of the last \end_layout.
+ the position of the last \\end_deeper is returned, else
+ the position of the last \\end_layout.
is_in_inset(lines, i, inset, default=(-1,-1)):
Check if line i is in an inset of the given type.
get_containing_inset(lines, i):
Finds out what kind of inset line i is within. Returns a
- list containing what follows \begin_inset on the line
+ list containing what follows \\begin_inset on the line
on which the inset begins, plus the starting and ending line.
Returns False on any kind of error or if it isn't in an inset.
So get_containing_inset(document.body, i) might return:
whitespace are ignored, but there must be whitespace following
token itself.
+ Use find_substring(lines, sub) to find a substring anywhere in `lines`.
+
Return -1 on failure."""
if end == 0 or end > len(lines):
the first element, in lines[start, end].
Return -1 on failure."""
+
if end == 0 or end > len(lines):
end = len(lines)
return find_tokens(lines, tokens, start, end, True)
-def find_re(lines, rexp, start=0, end=0):
- """ find_re(lines, rexp, start[, end]) -> int
+def find_substring(lines, sub, start=0, end=0):
+ """ find_substring(lines, sub[, start[, end]]) -> int
- Return the lowest line where rexp, a regular expression, is found
- in lines[start, end].
+ Return the lowest line number `i` in [start, end] where
+ `sub` is a substring of line[i].
Return -1 on failure."""
+ if end == 0 or end > len(lines):
+ end = len(lines)
+ for i in range(start, end):
+ if sub in lines[i]:
+ return i
+ return -1
+
+
+def find_re(lines, rexp, start=0, end=0):
+ """ find_re(lines, rexp[, start[, end]]) -> int
+
+ Return the lowest line number `i` in [start, end] where the regular
+ expression object `rexp` matches at the beginning of line[i].
+ Return -1 on failure.
+
+ Start your pattern with the wildcard ".*" to find a match anywhere in a
+ line. Use find_substring() to find a substring anywhere in the lines.
+ """
if end == 0 or end > len(lines):
end = len(lines)
for i in range(start, end):
return val.strip('"')
+bool_values = {"true": True, "1": True,
+ "false": False, "0": False}
+
def get_bool_value(lines, token, start=0, end=0, default=None, delete=False):
""" get_bool_value(lines, token, start[[, end], default]) -> string
Find the next line that looks like:
- token bool_value
+ `token` <bool_value>
- Returns True if bool_value is 1 or true and
- False if bool_value is 0 or false
+ Return True if <bool_value> is 1 or "true", False if <bool_value>
+ is 0 or "false", else `default`.
"""
-
val = get_quoted_value(lines, token, start, end, default, delete)
+ return bool_values.get(val, default)
- if val == "1" or val == "true":
- return True
- if val == "0" or val == "false":
- return False
- return default
+
+def set_bool_value(lines, token, value, start=0, end=0):
+ """Find `token` in `lines` and set to bool(`value`).
+
+ Return previous value. Raise `ValueError` if `token` is not in lines.
+
+ Cf. find_token(), get_bool_value().
+ """
+ i = find_token(lines, token, start, end)
+ if i == -1:
+ raise ValueError
+ oldvalue = get_bool_value(lines, token, i, i+1)
+ if oldvalue is value:
+ return oldvalue
+ # set to new value
+ if get_quoted_value(lines, token, i, i+1) in ('0', '1'):
+ lines[i] = "%s %d" % (token, value)
+ else:
+ lines[i] = "%s %s" % (token, str(value).lower())
+
+ return oldvalue
def get_option_value(line, option):
- rx = option + '\s*=\s*"([^"]+)"'
+ rx = option + r'\s*=\s*"([^"]+)"'
rx = re.compile(rx)
m = rx.search(line)
if not m:
def set_option_value(line, option, value):
- rx = '(' + option + '\s*=\s*")[^"]+"'
+ rx = '(' + option + r'\s*=\s*")[^"]+"'
rx = re.compile(rx)
m = rx.search(line)
if not m:
return line
- return re.sub(rx, '\g<1>' + value + '"', line)
+ return re.sub(rx, r'\g<1>' + value + '"', line)
def del_token(lines, token, start=0, end=0):
def get_containing_inset(lines, i):
'''
Finds out what kind of inset line i is within. Returns a
- list containing (i) what follows \begin_inset on the line
+ list containing (i) what follows \\begin_inset on the line
on which the inset begins, plus the starting and ending line.
Returns False on any kind of error or if it isn't in an inset.
'''
def get_containing_layout(lines, i):
'''
- Finds out what kind of layout line i is within. Returns a
- list containing what follows \begin_layout on the line
- on which the layout begins, plus the starting and ending line
- and the start of the paragraph (after all params). I.e, returns:
+ Find out what kind of layout line `i` is within.
+ Return a tuple
(layoutname, layoutstart, layoutend, startofcontent)
- Returns False on any kind of error.
+ containing
+ * layout style/name,
+ * start line number,
+ * end line number, and
+ * number of first paragraph line (after all params).
+ Return `False` on any kind of error.
'''
j = i
while True:
if endlay < i:
return False
- lay = get_value(lines, "\\begin_layout", stlay)
- if lay == "":
- # shouldn't happen
- return False
+ layoutname = get_value(lines, "\\begin_layout", stlay)
+ if layoutname == "": # layout style missing
+ # TODO: What shall we do in this case?
+ pass
+ # layoutname == "Standard" # use same fallback as the LyX parser:
+ # raise ValueError("Missing layout name on line %d"%stlay) # diagnosis
+ # return False # generic error response
par_params = ["\\noindent", "\\indent", "\\indent-toggle", "\\leftindent",
"\\start_of_appendix", "\\paragraph_spacing", "\\align",
"\\labelwidthstring"]
stpar += 1
if lines[stpar].split(' ', 1)[0] not in par_params:
break
- return (lay, stlay, endlay, stpar)
+ return (layoutname, stlay, endlay, stpar)
def count_pars_in_inset(lines, i):
pars = 0
for j in range(ins[1], ins[2]):
m = re.match(r'\\begin_layout (.*)', lines[j])
- if m and get_containing_inset(lines, j)[0] == ins[0]:
+ if m and get_containing_inset(lines, j)[1] == ins[1]:
pars += 1
return pars