text-format-revised 1.1.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/Gemfile +5 -0
- data/Gemfile.lock +22 -0
- data/LICENSE +61 -0
- data/README.md +16 -0
- data/Rakefile +13 -0
- data/ToDo +8 -0
- data/lib/text/format.rb +1043 -0
- data/lib/text/format/alpha.rb +61 -0
- data/lib/text/format/number.rb +34 -0
- data/lib/text/format/roman.rb +105 -0
- data/pre-setup.rb +46 -0
- data/setup.rb +1366 -0
- data/test/testall.rb +20 -0
- data/test/text_format_test.rb +475 -0
- metadata +111 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: dd5b39a8ae855ade9797b43e324ff8d9611ad92e
|
4
|
+
data.tar.gz: 7b12bc913f0f63eb53829b1ab448157072a1bf2a
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: 4e0bf57d87869ffaaeb9aca078645c270d10ddf8b7d5f3a0c13074163413795d1e2e71e677cb9f316ed2f54faa4ff9cc11152956091ff26c64c0b38c129bea21
|
7
|
+
data.tar.gz: 3f759682b6b61862077fe71c9636f2de07cdda8a1d2db49306ffb3c76f4eb70a1e1a69ca5ca829d93aad93412874de4f7f7e49e6914d8b8ec98c7254b0f81f31
|
data/Gemfile
ADDED
data/Gemfile.lock
ADDED
@@ -0,0 +1,22 @@
|
|
1
|
+
PATH
|
2
|
+
remote: .
|
3
|
+
specs:
|
4
|
+
text-format (1.1.0)
|
5
|
+
text-hyphen (~> 1.2.0)
|
6
|
+
|
7
|
+
GEM
|
8
|
+
remote: https://rubygems.org/
|
9
|
+
specs:
|
10
|
+
ansi (1.4.3)
|
11
|
+
rake (10.0.4)
|
12
|
+
text-hyphen (1.2)
|
13
|
+
turn (0.9.6)
|
14
|
+
ansi
|
15
|
+
|
16
|
+
PLATFORMS
|
17
|
+
ruby
|
18
|
+
|
19
|
+
DEPENDENCIES
|
20
|
+
rake
|
21
|
+
text-format!
|
22
|
+
turn
|
data/LICENSE
ADDED
@@ -0,0 +1,61 @@
|
|
1
|
+
Copyright (c) 2013 Austin Ziegler, Chris Ledet
|
2
|
+
|
3
|
+
Text::Format is copyrighted free software owned by Austin Ziegler.
|
4
|
+
The Owner of this software permits you to redistribute and/or modify
|
5
|
+
the software under either the terms of
|
6
|
+
the GPL version 2 (see the file GPL), or the conditions below ("Ruby License"):
|
7
|
+
|
8
|
+
1. You may make and give away verbatim copies of the source form of this
|
9
|
+
software without restriction, provided that you retain ALL of the
|
10
|
+
original copyright notices and associated disclaimers.
|
11
|
+
|
12
|
+
2. You may modify your copy of the software in any way, provided that
|
13
|
+
you do at least ONE of the following:
|
14
|
+
|
15
|
+
a) place your modifications in the Public Domain or otherwise
|
16
|
+
make them Freely Available, such as by posting said
|
17
|
+
modifications to Usenet or an equivalent medium, or by allowing
|
18
|
+
the author to include your modifications in the software.
|
19
|
+
|
20
|
+
b) use the modified software only within your corporation or
|
21
|
+
organization.
|
22
|
+
|
23
|
+
c) give non-standard binaries non-standard names, with
|
24
|
+
instructions on where to get the original software distribution.
|
25
|
+
|
26
|
+
d) make other distribution arrangements with the Owner.
|
27
|
+
|
28
|
+
3. You may distribute the software in object code or binary form,
|
29
|
+
provided that you do at least ONE of the following:
|
30
|
+
|
31
|
+
a) distribute the binaries and library files of the software,
|
32
|
+
together with instructions (in a manual page or equivalent)
|
33
|
+
on where to get the original distribution.
|
34
|
+
|
35
|
+
b) accompany the distribution with the machine-readable source of
|
36
|
+
the software.
|
37
|
+
|
38
|
+
c) give non-standard binaries non-standard names, with
|
39
|
+
instructions on where to get the original software distribution.
|
40
|
+
|
41
|
+
d) make other distribution arrangements with the Owner.
|
42
|
+
|
43
|
+
4. You may modify and include parts of the software into any other
|
44
|
+
software (possibly commercial), provided you comply with the terms in
|
45
|
+
Sections 1, 2, and 3 above. But some files in the distribution
|
46
|
+
are not written by the Owner, so they may be made available to you
|
47
|
+
under different terms.
|
48
|
+
|
49
|
+
For the list of those files and their copying conditions, see the
|
50
|
+
file LEGAL.
|
51
|
+
|
52
|
+
5. The scripts and library files supplied as input to or produced as
|
53
|
+
output from the software do not automatically fall under the
|
54
|
+
copyright of the software, but belong to whoever generated them,
|
55
|
+
and may be sold commercially, and may be aggregated with this
|
56
|
+
software.
|
57
|
+
|
58
|
+
6. THIS SOFTWARE IS PROVIDED "AS IS" AND WITHOUT ANY EXPRESS OR
|
59
|
+
IMPLIED WARRANTIES, INCLUDING, WITHOUT LIMITATION, THE IMPLIED
|
60
|
+
WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
|
61
|
+
PURPOSE.
|
data/README.md
ADDED
@@ -0,0 +1,16 @@
|
|
1
|
+
## Text::Format fork
|
2
|
+
|
3
|
+
### Ruby 1.9 Update
|
4
|
+
|
5
|
+
Updated this gem so it works with Ruby 2.0.0. Do not use this gem if you're using for Ruby versions <1.9.2.
|
6
|
+
|
7
|
+
###
|
8
|
+
|
9
|
+
### About
|
10
|
+
|
11
|
+
Text::Format is provides the ability to nicely format fixed-width text with knowledge of the writeable space (number of columns), margins, and indentation settings. Text::Format can work with either TeX::Hyphen or Text::Hyphen to hyphenate words when formatting.
|
12
|
+
|
13
|
+
### License
|
14
|
+
|
15
|
+
Text::Format is originally based on the Perl library of the same name by Gábor Egressy.
|
16
|
+
Licenced under [Ruby's licence](http://www.ruby-lang.org/en/about/license.txt). It is also available under the [Perl Artistic licence](http://dev.perl.org/licenses/artistic.html).
|
data/Rakefile
ADDED
@@ -0,0 +1,13 @@
|
|
1
|
+
#! /usr/bin/env rake
|
2
|
+
$LOAD_PATH.unshift('lib')
|
3
|
+
|
4
|
+
require 'bundler'
|
5
|
+
Bundler::GemHelper.install_tasks
|
6
|
+
|
7
|
+
require 'rake/testtask'
|
8
|
+
Rake::TestTask.new(:test) do |t|
|
9
|
+
t.libs << 'test'
|
10
|
+
t.pattern = 'test/**/*_test.rb'
|
11
|
+
end
|
12
|
+
|
13
|
+
task :default => :test
|
data/ToDo
ADDED
@@ -0,0 +1,8 @@
|
|
1
|
+
Text::Format To Do
|
2
|
+
==================
|
3
|
+
* Margin markers: the ability to place markers in the margin when
|
4
|
+
formatting.
|
5
|
+
* Line numbering: the ability to number lines in the margin when
|
6
|
+
formatting, including numering lines by step (every fifth line, etc.).
|
7
|
+
* Email attribution quoting reformatting.
|
8
|
+
* Proportional width support for GUI formatting.
|
data/lib/text/format.rb
ADDED
@@ -0,0 +1,1043 @@
|
|
1
|
+
# :title: Text::Format
|
2
|
+
# :main: Text::Format
|
3
|
+
#--
|
4
|
+
# Text::Format for Ruby
|
5
|
+
# Version 1.0.0
|
6
|
+
#
|
7
|
+
# Copyright (c) 2002 - 2005 Austin Ziegler
|
8
|
+
#
|
9
|
+
# $Id: format.rb,v 1.5 2005/04/20 01:43:55 austin Exp $
|
10
|
+
#++
|
11
|
+
unless defined?(Text)
|
12
|
+
module Text; end
|
13
|
+
end
|
14
|
+
|
15
|
+
# = Introduction
|
16
|
+
#
|
17
|
+
# Text::Format provides the ability to nicely format fixed-width text with
|
18
|
+
# knowledge of the writeable space (number of columns), margins, and
|
19
|
+
# indentation settings.
|
20
|
+
#
|
21
|
+
# Copyright:: Copyright (c) 2002 - 2005 by Austin Ziegler
|
22
|
+
# Version:: 1.0.0
|
23
|
+
# Based On:: Perl
|
24
|
+
# Text::Format[http://search.cpan.org/author/GABOR/Text-Format0.52/lib/Text/Format.pm],
|
25
|
+
# Copyright (c) 1998 G�bor Egressy
|
26
|
+
# Licence:: Ruby's, Perl Artistic, or GPL version 2 (or later)
|
27
|
+
#
|
28
|
+
class Text::Format
|
29
|
+
VERSION = '1.0.0'
|
30
|
+
|
31
|
+
SPACES_RE = %r{\s+}mo.freeze
|
32
|
+
NEWLINE_RE = %r{\n}o.freeze
|
33
|
+
TAB = "\t".freeze
|
34
|
+
NEWLINE = "\n".freeze
|
35
|
+
|
36
|
+
# Global common English abbreviations. More can be added with
|
37
|
+
# #abbreviations.
|
38
|
+
ABBREV = %w(Mr Mrs Ms Jr Sr Dr)
|
39
|
+
|
40
|
+
# Formats text flush to the left margin with a visual and physical
|
41
|
+
# ragged right margin.
|
42
|
+
#
|
43
|
+
# >A paragraph that is<
|
44
|
+
# >left aligned.<
|
45
|
+
LEFT_ALIGN = :left
|
46
|
+
# Formats text flush to the right margin with a visual ragged left
|
47
|
+
# margin. The actual left margin is padded with spaces from the
|
48
|
+
# beginning of the line to the start of the text such that the right
|
49
|
+
# margin will be flush.
|
50
|
+
#
|
51
|
+
# >A paragraph that is<
|
52
|
+
# > right aligned.<
|
53
|
+
RIGHT_ALIGN = :right
|
54
|
+
# Formats text flush to the left margin with a visual ragged right
|
55
|
+
# margin. The line is padded with spaces from the end of the text to the
|
56
|
+
# right margin.
|
57
|
+
#
|
58
|
+
# >A paragraph that is<
|
59
|
+
# >right filled. <
|
60
|
+
RIGHT_FILL = :fill
|
61
|
+
# Formats the text flush to both the left and right margins. The last
|
62
|
+
# line will not be justified if it consists of a single word (it will be
|
63
|
+
# treated as +RIGHT_FILL+ in this case). Spacing between words is
|
64
|
+
# increased to ensure that the textg is flush with both margins.
|
65
|
+
#
|
66
|
+
# |A paragraph that|
|
67
|
+
# |is justified.|
|
68
|
+
#
|
69
|
+
# |A paragraph that is|
|
70
|
+
# |justified. |
|
71
|
+
JUSTIFY = :justify
|
72
|
+
|
73
|
+
# When #hard_margins is enabled, a word that extends over the right
|
74
|
+
# margin will be split at the number of characters needed. This is
|
75
|
+
# similar to how characters wrap on a terminal. This is the default
|
76
|
+
# split mechanism when #hard_margins is enabled.
|
77
|
+
#
|
78
|
+
# repre
|
79
|
+
# senta
|
80
|
+
# ion
|
81
|
+
SPLIT_FIXED = 1
|
82
|
+
# When #hard_margins is enabled, a word that extends over the right
|
83
|
+
# margin will be split at one less than the number of characters needed
|
84
|
+
# with a C-style continuation character (\). If the word cannot be split
|
85
|
+
# using the rules of SPLIT_CONTINUATION, and the word will not fit
|
86
|
+
# wholly into the next line, then SPLIT_FIXED will be used.
|
87
|
+
#
|
88
|
+
# repr\
|
89
|
+
# esen\
|
90
|
+
# tati\
|
91
|
+
# on
|
92
|
+
SPLIT_CONTINUATION = 2
|
93
|
+
# When #hard_margins is enabled, a word that extends over the right
|
94
|
+
# margin will be split according to the hyphenator specified by the
|
95
|
+
# #hyphenator object; if there is no hyphenation library supplied, then
|
96
|
+
# the hyphenator of Text::Format itself is used, which is the same as
|
97
|
+
# SPLIT_CONTINUATION. See #hyphenator for more information about
|
98
|
+
# hyphenation libraries. The example below is valid with either
|
99
|
+
# TeX::Hyphen or Text::Hyphen. If the word cannot be split using the
|
100
|
+
# hyphenator's rules, and the word will not fit wholly into the next
|
101
|
+
# line, then SPLIT_FIXED will be used.
|
102
|
+
#
|
103
|
+
# rep-
|
104
|
+
# re-
|
105
|
+
# sen-
|
106
|
+
# ta-
|
107
|
+
# tion
|
108
|
+
#
|
109
|
+
SPLIT_HYPHENATION = 4
|
110
|
+
# When #hard_margins is enabled, a word that extends over the right
|
111
|
+
# margin will be split at one less than the number of characters needed
|
112
|
+
# with a C-style continuation character (\). If the word cannot be split
|
113
|
+
# using the rules of SPLIT_CONTINUATION, then SPLIT_FIXED will be used.
|
114
|
+
SPLIT_CONTINUATION_FIXED = SPLIT_CONTINUATION | SPLIT_FIXED
|
115
|
+
# When #hard_margins is enabled, a word that extends over the right
|
116
|
+
# margin will be split according to the hyphenator specified by the
|
117
|
+
# #hyphenator object; if there is no hyphenation library supplied, then
|
118
|
+
# the hyphenator of Text::Format itself is used, which is the same as
|
119
|
+
# SPLIT_CONTINUATION. See #hyphenator for more information about
|
120
|
+
# hyphenation libraries. The example below is valid with either
|
121
|
+
# TeX::Hyphen or Text::Hyphen. If the word cannot be split using the
|
122
|
+
# hyphenator's rules, then SPLIT_FIXED will be used.
|
123
|
+
SPLIT_HYPHENATION_FIXED = SPLIT_HYPHENATION | SPLIT_FIXED
|
124
|
+
# Attempts to split words according to the rules of the supplied
|
125
|
+
# hyphenator (e.g., SPLIT_HYPHENATION); if the word cannot be split
|
126
|
+
# using these rules, then the rules of SPLIT_CONTINUATION will be
|
127
|
+
# followed. In all cases, if the word cannot be split using either
|
128
|
+
# SPLIT_HYPHENATION or SPLIT_CONTINUATION, and the word will not fit
|
129
|
+
# wholly into the next line, then SPLIT_FIXED will be used.
|
130
|
+
SPLIT_HYPHENATION_CONTINUATION = SPLIT_HYPHENATION | SPLIT_CONTINUATION
|
131
|
+
# Attempts to split words according to the rules of the supplied
|
132
|
+
# hyphenator (e.g., SPLIT_HYPHENATION); if the word cannot be split
|
133
|
+
# using these rules, then the rules of SPLIT_CONTINUATION will be
|
134
|
+
# followed. In all cases, if the word cannot be split using either
|
135
|
+
# SPLIT_HYPHENATION or SPLIT_CONTINUATION, then SPLIT_FIXED will be
|
136
|
+
# used.
|
137
|
+
SPLIT_ALL = SPLIT_HYPHENATION | SPLIT_CONTINUATION | SPLIT_FIXED
|
138
|
+
|
139
|
+
# Words forcibly split by Text::Format will be stored as split words.
|
140
|
+
# This class represents a word forcibly split.
|
141
|
+
class SplitWord
|
142
|
+
# The word that was split.
|
143
|
+
attr_reader :word
|
144
|
+
# The first part of the word that was split.
|
145
|
+
attr_reader :first
|
146
|
+
# The remainder of the word that was split.
|
147
|
+
attr_reader :rest
|
148
|
+
|
149
|
+
def initialize(word, first, rest)
|
150
|
+
@word = word
|
151
|
+
@first = first
|
152
|
+
@rest = rest
|
153
|
+
end
|
154
|
+
end
|
155
|
+
|
156
|
+
# Indicates punctuation characters that terminates a sentence, as some
|
157
|
+
# English typesetting rules indicate that sentences should be followed
|
158
|
+
# by two spaces. This is an archaic rule, but is supported with
|
159
|
+
# #extra_space. This is the default set of terminal punctuation
|
160
|
+
# characters. Additional terminal punctuation may be added to the
|
161
|
+
# formatting object through #terminal_punctuation.
|
162
|
+
TERMINAL_PUNCTUATION = %q(.?!)
|
163
|
+
# Indicates quote characters that may follow terminal punctuation under
|
164
|
+
# the current formatting rules. This satisfies the English formatting
|
165
|
+
# rule that indicates that sentences terminated inside of quotes should
|
166
|
+
# have the punctuation inside of the quoted text, not outside of the
|
167
|
+
# terminal quote. Additional terminal quotes may be added to the
|
168
|
+
# formatting object through #terminal_quotes. See TERMINAL_PUNCTUATION
|
169
|
+
# for more information.
|
170
|
+
TERMINAL_QUOTES = %q('")
|
171
|
+
|
172
|
+
# This method returns the regular expression used to detect the end of a
|
173
|
+
# sentence under the current definition of TERMINAL_PUNCTUATION,
|
174
|
+
# #terminal_punctuation, TERMINAL_QUOTES, and #terminal_quotes.
|
175
|
+
def __sentence_end_re
|
176
|
+
%r{[#{TERMINAL_PUNCTUATION}#{self.terminal_punctuation}][#{TERMINAL_QUOTES}#{self.terminal_quotes}]?$}
|
177
|
+
end
|
178
|
+
private :__sentence_end_re
|
179
|
+
|
180
|
+
# Returns a regular expression for a set of characters (at least one
|
181
|
+
# non-whitespace followed by at least one space) of the specified size
|
182
|
+
# followed by one or more of any character.
|
183
|
+
RE_BREAK_SIZE = lambda { |size| %r[((?:\S+\s+){#{size}})(.+)] }
|
184
|
+
|
185
|
+
# Compares the formatting rules, excepting #hyphenator, of two
|
186
|
+
# Text::Format objects. Generated results (e.g., #split_words) are not
|
187
|
+
# compared.
|
188
|
+
def ==(o)
|
189
|
+
(@text == o.text) and
|
190
|
+
(@columns == o.columns) and
|
191
|
+
(@left_margin == o.left_margin) and
|
192
|
+
(@right_margin == o.right_margin) and
|
193
|
+
(@hard_margins == o.hard_margins) and
|
194
|
+
(@split_rules == o.split_rules) and
|
195
|
+
(@first_indent == o.first_indent) and
|
196
|
+
(@body_indent == o.body_indent) and
|
197
|
+
(@tag_text == o.tag_text) and
|
198
|
+
(@tabstop == o.tabstop) and
|
199
|
+
(@format_style == o.format_style) and
|
200
|
+
(@extra_space == o.extra_space) and
|
201
|
+
(@tag_paragraph == o.tag_paragraph) and
|
202
|
+
(@nobreak == o.nobreak) and
|
203
|
+
(@terminal_punctuation == o.terminal_punctuation) and
|
204
|
+
(@terminal_quotes == o.terminal_quotes) and
|
205
|
+
(@abbreviations == o.abbreviations) and
|
206
|
+
(@nobreak_regex == o.nobreak_regex)
|
207
|
+
end
|
208
|
+
|
209
|
+
# The default text to be manipulated. Note that value is optional, but
|
210
|
+
# if the formatting functions are called without values, this text is
|
211
|
+
# what will be formatted.
|
212
|
+
#
|
213
|
+
# *Default*:: <tt>[]</tt>
|
214
|
+
# <b>Used in</b>:: All methods
|
215
|
+
attr_accessor :text
|
216
|
+
|
217
|
+
# The total width of the format area. The margins, indentation, and text
|
218
|
+
# are formatted into this space. Any value provided is silently
|
219
|
+
# converted to a positive integer.
|
220
|
+
#
|
221
|
+
# COLUMNS
|
222
|
+
# <-------------------------------------------------------------->
|
223
|
+
# <-----------><------><---------------------------><------------>
|
224
|
+
# left margin indent text is formatted into here right margin
|
225
|
+
#
|
226
|
+
# *Default*:: <tt>72</tt>
|
227
|
+
# <b>Used in</b>:: #format, #paragraphs, #center
|
228
|
+
attr_accessor :columns
|
229
|
+
def columns=(col) #:nodoc:
|
230
|
+
@columns = col.to_i.abs
|
231
|
+
end
|
232
|
+
|
233
|
+
# The number of spaces used for the left margin. The value provided is
|
234
|
+
# silently converted to a positive integer value.
|
235
|
+
#
|
236
|
+
# columns
|
237
|
+
# <-------------------------------------------------------------->
|
238
|
+
# <-----------><------><---------------------------><------------>
|
239
|
+
# LEFT MARGIN indent text is formatted into here right margin
|
240
|
+
#
|
241
|
+
# *Default*:: <tt>0</tt>
|
242
|
+
# <b>Used in</b>:: #format, #paragraphs, #center
|
243
|
+
attr_accessor :left_margin
|
244
|
+
def left_margin=(left) #:nodoc:
|
245
|
+
@left_margin = left.to_i.abs
|
246
|
+
end
|
247
|
+
|
248
|
+
# The number of spaces used for the right margin. The value provided is
|
249
|
+
# silently converted to a positive integer value.
|
250
|
+
#
|
251
|
+
# columns
|
252
|
+
# <-------------------------------------------------------------->
|
253
|
+
# <-----------><------><---------------------------><------------>
|
254
|
+
# left margin indent text is formatted into here RIGHT MARGIN
|
255
|
+
#
|
256
|
+
# *Default*:: <tt>0</tt>
|
257
|
+
# <b>Used in</b>:: #format, #paragraphs, #center
|
258
|
+
attr_accessor :right_margin
|
259
|
+
def right_margin=(right) #:nodoc:
|
260
|
+
@right_margin = right.to_i.abs
|
261
|
+
end
|
262
|
+
|
263
|
+
# The number of spaces to indent the first line of a paragraph. The
|
264
|
+
# value provided is silently converted to a positive integer value.
|
265
|
+
#
|
266
|
+
# columns
|
267
|
+
# <-------------------------------------------------------------->
|
268
|
+
# <-----------><------><---------------------------><------------>
|
269
|
+
# left margin INDENT text is formatted into here right margin
|
270
|
+
#
|
271
|
+
# *Default*:: <tt>4</tt>
|
272
|
+
# <b>Used in</b>:: #format, #paragraphs
|
273
|
+
attr_accessor :first_indent
|
274
|
+
def first_indent=(first) #:nodoc:
|
275
|
+
@first_indent = first.to_i.abs
|
276
|
+
end
|
277
|
+
|
278
|
+
# The number of spaces to indent all lines after the first line of a
|
279
|
+
# paragraph. The value provided is silently converted to a positive
|
280
|
+
# integer value.
|
281
|
+
#
|
282
|
+
# columns
|
283
|
+
# <-------------------------------------------------------------->
|
284
|
+
# <-----------><------><---------------------------><------------>
|
285
|
+
# left margin INDENT text is formatted into here right margin
|
286
|
+
#
|
287
|
+
# *Default*:: <tt>0</tt>
|
288
|
+
# <b>Used in</b>:: #format, #paragraphs
|
289
|
+
attr_accessor :body_indent
|
290
|
+
def body_indent=(body) #:nodoc:
|
291
|
+
@body_indent = body.to_i.abs
|
292
|
+
end
|
293
|
+
|
294
|
+
# Normally, words larger than the format area will be placed on a line
|
295
|
+
# by themselves. Setting this value to +true+ will force words larger
|
296
|
+
# than the format area to be split into one or more "words" each at most
|
297
|
+
# the size of the format area. The first line and the original word will
|
298
|
+
# be placed into #split_words. Note that this will cause the output to
|
299
|
+
# look *similar* to a #format_style of JUSTIFY. (Lines will be filled as
|
300
|
+
# much as possible.)
|
301
|
+
#
|
302
|
+
# *Default*:: +false+
|
303
|
+
# <b>Used in</b>:: #format, #paragraphs
|
304
|
+
attr_accessor :hard_margins
|
305
|
+
|
306
|
+
# An array of words split during formatting if #hard_margins is set to
|
307
|
+
# +true+.
|
308
|
+
# #split_words << Text::Format::SplitWord.new(word, first, rest)
|
309
|
+
attr_reader :split_words
|
310
|
+
|
311
|
+
# The object responsible for hyphenating. It must respond to
|
312
|
+
# #hyphenate_to(word, size) or #hyphenate_to(word, size, formatter) and
|
313
|
+
# return an array of the word split into two parts (e.g., <tt>[part1,
|
314
|
+
# part2]</tt>; if there is a hyphenation mark to be applied,
|
315
|
+
# responsibility belongs to the hyphenator object. The size is the
|
316
|
+
# MAXIMUM size permitted, including any hyphenation marks.
|
317
|
+
#
|
318
|
+
# If the #hyphenate_to method has an arity of 3, the current formatter
|
319
|
+
# (+self+) will be provided to the method. This allows the hyphenator to
|
320
|
+
# make decisions about the hyphenation based on the formatting rules.
|
321
|
+
#
|
322
|
+
# #hyphenate_to should return <tt>[nil, word]</tt> if the word cannot be
|
323
|
+
# hyphenated.
|
324
|
+
#
|
325
|
+
# *Default*:: +self+ (SPLIT_CONTINUATION)
|
326
|
+
# <b>Used in</b>:: #format, #paragraphs
|
327
|
+
attr_accessor :hyphenator
|
328
|
+
def hyphenator=(h) #:nodoc:
|
329
|
+
h ||= self
|
330
|
+
|
331
|
+
raise ArgumentError, "#{h.inspect} is not a valid hyphenator." unless h.respond_to?(:hyphenate_to)
|
332
|
+
arity = h.method(:hyphenate_to).arity
|
333
|
+
raise ArgumentError, "#{h.inspect} must have exactly two or three arguments." unless arity.between?(2, 3)
|
334
|
+
|
335
|
+
@hyphenator = h
|
336
|
+
@hyphenator_arity = arity
|
337
|
+
end
|
338
|
+
|
339
|
+
# Specifies the split mode; used only when #hard_margins is set to
|
340
|
+
# +true+. Allowable values are:
|
341
|
+
#
|
342
|
+
# * +SPLIT_FIXED+
|
343
|
+
# * +SPLIT_CONTINUATION+
|
344
|
+
# * +SPLIT_HYPHENATION+
|
345
|
+
# * +SPLIT_CONTINUATION_FIXED+
|
346
|
+
# * +SPLIT_HYPHENATION_FIXED+
|
347
|
+
# * +SPLIT_HYPHENATION_CONTINUATION+
|
348
|
+
# * +SPLIT_ALL+
|
349
|
+
#
|
350
|
+
# *Default*:: <tt>Text::Format::SPLIT_FIXED</tt>
|
351
|
+
# <b>Used in</b>:: #format, #paragraphs
|
352
|
+
attr_accessor :split_rules
|
353
|
+
def split_rules=(s) #:nodoc:
|
354
|
+
raise ArgumentError, "Invalid value provided for #split_rules." if ((s < SPLIT_FIXED) or (s > SPLIT_ALL))
|
355
|
+
@split_rules = s
|
356
|
+
end
|
357
|
+
|
358
|
+
# Indicates whether sentence terminators should be followed by a single
|
359
|
+
# space (+false+), or two spaces (+true+). See #abbreviations for more
|
360
|
+
# information.
|
361
|
+
#
|
362
|
+
# *Default*:: +false+
|
363
|
+
# <b>Used in</b>:: #format, #paragraphs
|
364
|
+
attr_accessor :extra_space
|
365
|
+
|
366
|
+
# Defines the current abbreviations as an array. This is only used if
|
367
|
+
# extra_space is turned on.
|
368
|
+
#
|
369
|
+
# If one is abbreviating "President" as "Pres." (abbreviations =
|
370
|
+
# ["Pres"]), then the results of formatting will be as illustrated in
|
371
|
+
# the table below:
|
372
|
+
#
|
373
|
+
# abbreviations
|
374
|
+
# extra_space | #include?("Pres") | not #include?("Pres")
|
375
|
+
# ------------+-------------------+----------------------
|
376
|
+
# true | Pres. Lincoln | Pres. Lincoln
|
377
|
+
# false | Pres. Lincoln | Pres. Lincoln
|
378
|
+
# ------------+-------------------+----------------------
|
379
|
+
# extra_space | #include?("Mrs") | not #include?("Mrs")
|
380
|
+
# true | Mrs. Lincoln | Mrs. Lincoln
|
381
|
+
# false | Mrs. Lincoln | Mrs. Lincoln
|
382
|
+
#
|
383
|
+
# Note that abbreviations should not have the terminal period as part of
|
384
|
+
# their definitions.
|
385
|
+
#
|
386
|
+
# This automatic abbreviation handling *will* cause some issues with
|
387
|
+
# uncommon sentence structures. The two sentences below will not be
|
388
|
+
# formatted correctly:
|
389
|
+
#
|
390
|
+
# You're in trouble now, Mr.
|
391
|
+
# Just wait until your father gets home.
|
392
|
+
#
|
393
|
+
# Under no circumstances (because Mr is a predefined abbreviation) will
|
394
|
+
# this ever be separated by two spaces.
|
395
|
+
#
|
396
|
+
# *Default*:: <tt>[]</tt>
|
397
|
+
# <b>Used in</b>:: #format, #paragraphs
|
398
|
+
attr_accessor :abbreviations
|
399
|
+
|
400
|
+
# Specifies additional punctuation characters that terminate a sentence,
|
401
|
+
# as some English typesetting rules indicate that sentences should be
|
402
|
+
# followed by two spaces. This is an archaic rule, but is supported with
|
403
|
+
# #extra_space. This is added to the default set of terminal punctuation
|
404
|
+
# defined in TERMINAL_PUNCTUATION.
|
405
|
+
#
|
406
|
+
# *Default*:: <tt>""</tt>
|
407
|
+
# <b>Used in</b>:: #format, #paragraphs
|
408
|
+
attr_accessor :terminal_punctuation
|
409
|
+
# Specifies additional quote characters that may follow
|
410
|
+
# terminal punctuation under the current formatting rules. This
|
411
|
+
# satisfies the English formatting rule that indicates that sentences
|
412
|
+
# terminated inside of quotes should have the punctuation inside of the
|
413
|
+
# quoted text, not outside of the terminal quote. This is added to the
|
414
|
+
# default set of terminal quotes defined in TERMINAL_QUOTES.
|
415
|
+
#
|
416
|
+
# *Default*:: <tt>""</tt>
|
417
|
+
# <b>Used in</b>:: #format, #paragraphs
|
418
|
+
attr_accessor :terminal_quotes
|
419
|
+
|
420
|
+
# Indicates whether the formatting of paragraphs should be done with
|
421
|
+
# tagged paragraphs. Useful only with #tag_text.
|
422
|
+
#
|
423
|
+
# *Default*:: +false+
|
424
|
+
# <b>Used in</b>:: #format, #paragraphs
|
425
|
+
attr_accessor :tag_paragraph
|
426
|
+
|
427
|
+
# The text to be placed before each paragraph when #tag_paragraph is
|
428
|
+
# +true+. When #format is called, only the first element (#tag_text[0])
|
429
|
+
# is used. When #paragraphs is called, then each successive element
|
430
|
+
# (#tag_text[n]) will be used once, with corresponding paragraphs. If
|
431
|
+
# the tag elements are exhausted before the text is exhausted, then the
|
432
|
+
# remaining paragraphs will not be tagged. Regardless of indentation
|
433
|
+
# settings, a blank line will be inserted between all paragraphs when
|
434
|
+
# #tag_paragraph is +true+.
|
435
|
+
#
|
436
|
+
# The Text::Format package provides three number generators,
|
437
|
+
# Text::Format::Alpha, Text::Format::Number, and Text::Format::Roman to
|
438
|
+
# assist with the numbering of paragraphs.
|
439
|
+
#
|
440
|
+
# *Default*:: <tt>[]</tt>
|
441
|
+
# <b>Used in</b>:: #format, #paragraphs
|
442
|
+
attr_accessor :tag_text
|
443
|
+
|
444
|
+
# Indicates whether or not the non-breaking space feature should be
|
445
|
+
# used.
|
446
|
+
#
|
447
|
+
# *Default*:: +false+
|
448
|
+
# <b>Used in</b>:: #format, #paragraphs
|
449
|
+
attr_accessor :nobreak
|
450
|
+
|
451
|
+
# A hash which holds the regular expressions on which spaces should not
|
452
|
+
# be broken. The hash is set up such that the key is the first word and
|
453
|
+
# the value is the second word.
|
454
|
+
#
|
455
|
+
# For example, if +nobreak_regex+ contains the following hash:
|
456
|
+
#
|
457
|
+
# { %r{Mrs?\.?} => %r{\S+}, %r{\S+} => %r{(?:[SJ])r\.?} }
|
458
|
+
#
|
459
|
+
# Then "Mr. Jones", "Mrs Jones", and "Jones Jr." would not be broken. If
|
460
|
+
# this simple matching algorithm indicates that there should not be a
|
461
|
+
# break at the current end of line, then a backtrack is done until there
|
462
|
+
# are two words on which line breaking is permitted. If two such words
|
463
|
+
# are not found, then the end of the line will be broken *regardless*.
|
464
|
+
# If there is a single word on the current line, then no backtrack is
|
465
|
+
# done and the word is stuck on the end.
|
466
|
+
#
|
467
|
+
# *Default*:: <tt>{}</tt>
|
468
|
+
# <b>Used in</b>:: #format, #paragraphs
|
469
|
+
attr_accessor :nobreak_regex
|
470
|
+
|
471
|
+
# Indicates the number of spaces that a single tab represents. Any value
|
472
|
+
# provided is silently converted to a positive integer.
|
473
|
+
#
|
474
|
+
# *Default*:: <tt>8</tt>
|
475
|
+
# <b>Used in</b>:: #expand, #unexpand,
|
476
|
+
# #paragraphs
|
477
|
+
attr_accessor :tabstop
|
478
|
+
def tabstop=(tabs) #:nodoc:
|
479
|
+
@tabstop = tabs.to_i.abs
|
480
|
+
end
|
481
|
+
|
482
|
+
# Specifies the format style. Allowable values are:
|
483
|
+
# *+LEFT_ALIGN+
|
484
|
+
# *+RIGHT_ALIGN+
|
485
|
+
# *+RIGHT_FILL+
|
486
|
+
# *+JUSTIFY+
|
487
|
+
#
|
488
|
+
# *Default*:: <tt>Text::Format::LEFT_ALIGN</tt>
|
489
|
+
# <b>Used in</b>:: #format, #paragraphs
|
490
|
+
attr_accessor :format_style
|
491
|
+
def format_style=(fs) #:nodoc:
|
492
|
+
raise ArgumentError, "Invalid value provided for format_style." unless [LEFT_ALIGN, RIGHT_ALIGN, RIGHT_FILL, JUSTIFY].include?(fs)
|
493
|
+
@format_style = fs
|
494
|
+
end
|
495
|
+
|
496
|
+
# Indicates that the format style is left alignment.
|
497
|
+
#
|
498
|
+
# *Default*:: +true+
|
499
|
+
# <b>Used in</b>:: #format, #paragraphs
|
500
|
+
def left_align?
|
501
|
+
@format_style == LEFT_ALIGN
|
502
|
+
end
|
503
|
+
|
504
|
+
# Indicates that the format style is right alignment.
|
505
|
+
#
|
506
|
+
# *Default*:: +false+
|
507
|
+
# <b>Used in</b>:: #format, #paragraphs
|
508
|
+
def right_align?
|
509
|
+
@format_style == RIGHT_ALIGN
|
510
|
+
end
|
511
|
+
|
512
|
+
# Indicates that the format style is right fill.
|
513
|
+
#
|
514
|
+
# *Default*:: +false+
|
515
|
+
# <b>Used in</b>:: #format, #paragraphs
|
516
|
+
def right_fill?
|
517
|
+
@format_style == RIGHT_FILL
|
518
|
+
end
|
519
|
+
|
520
|
+
# Indicates that the format style is full justification.
|
521
|
+
#
|
522
|
+
# *Default*:: +false+
|
523
|
+
# <b>Used in</b>:: #format, #paragraphs
|
524
|
+
def justify?
|
525
|
+
@format_style == JUSTIFY
|
526
|
+
end
|
527
|
+
|
528
|
+
# The formatting object itself can be used as a #hyphenator, where the
|
529
|
+
# default implementation of #hyphenate_to implements the conditions
|
530
|
+
# necessary to properly produce SPLIT_CONTINUATION.
|
531
|
+
def hyphenate_to(word, size)
|
532
|
+
if (size - 2) < 0
|
533
|
+
[nil, word]
|
534
|
+
else
|
535
|
+
[word[0 .. (size - 2)] + "\\", word[(size - 1) .. -1]]
|
536
|
+
end
|
537
|
+
end
|
538
|
+
|
539
|
+
# Splits the provided word so that it is in two parts, <tt>word[0 ..
|
540
|
+
# (size - 1)]</tt> and <tt>word[size .. -1]</tt>.
|
541
|
+
def split_word_to(word, size)
|
542
|
+
[word[0 .. (size - 1)], word[size .. -1]]
|
543
|
+
end
|
544
|
+
|
545
|
+
# Formats text into a nice paragraph format. The text is separated into
|
546
|
+
# words and then reassembled a word at a time using the settings of this
|
547
|
+
# Format object.
|
548
|
+
#
|
549
|
+
# If +text+ is +nil+, then the value of #text will be worked on.
|
550
|
+
def format_one_paragraph(text = nil)
|
551
|
+
text ||= @text
|
552
|
+
text = text[0] if text.kind_of?(Array)
|
553
|
+
|
554
|
+
# Convert the provided paragraph to a list of words.
|
555
|
+
words = text.split(SPACES_RE).reverse.reject { |ww| ww.nil? or ww.empty? }
|
556
|
+
|
557
|
+
text = []
|
558
|
+
|
559
|
+
# Find the maximum line width and the initial indent string.
|
560
|
+
# TODO 20050114 - allow the left and right margins to be specified as
|
561
|
+
# strings. If they are strings, then we need to use the sizes of the
|
562
|
+
# strings. Also: allow the indent string to be set manually and
|
563
|
+
# indicate whether the indent string will have a following space.
|
564
|
+
max_line_width = @columns - @first_indent - @left_margin - @right_margin
|
565
|
+
indent_str = ' ' * @first_indent
|
566
|
+
|
567
|
+
first_line = true
|
568
|
+
|
569
|
+
if words.empty?
|
570
|
+
line = []
|
571
|
+
line_size = 0
|
572
|
+
extra_space = false
|
573
|
+
else
|
574
|
+
line = [ words.pop ]
|
575
|
+
line_size = line[-1].size
|
576
|
+
extra_space = __add_extra_space?(line[-1])
|
577
|
+
end
|
578
|
+
|
579
|
+
while next_word = words.pop
|
580
|
+
next_word.strip! unless next_word.nil?
|
581
|
+
new_line_size = (next_word.size + line_size) + 1
|
582
|
+
|
583
|
+
if extra_space
|
584
|
+
if (line[-1] !~ __sentence_end_re)
|
585
|
+
extra_space = false
|
586
|
+
end
|
587
|
+
end
|
588
|
+
|
589
|
+
# Increase the width of the new line if there's a sentence
|
590
|
+
# terminator and we are applying extra_space.
|
591
|
+
new_line_size += 1 if extra_space
|
592
|
+
|
593
|
+
# Will the word fit onto the current line? If so, simply append it
|
594
|
+
# to the end of the line.
|
595
|
+
|
596
|
+
if new_line_size <= max_line_width
|
597
|
+
if line.empty?
|
598
|
+
line << next_word
|
599
|
+
else
|
600
|
+
if extra_space
|
601
|
+
line << " #{next_word}"
|
602
|
+
else
|
603
|
+
line << " #{next_word}"
|
604
|
+
end
|
605
|
+
end
|
606
|
+
else
|
607
|
+
# Forcibly wrap the line if nonbreaking spaces are turned on and
|
608
|
+
# there is a condition where words must be wrapped. If we have
|
609
|
+
# returned more than one word, readjust the word list.
|
610
|
+
line, next_word = __wrap_line(line, next_word) if @nobreak
|
611
|
+
if next_word.kind_of?(Array)
|
612
|
+
if next_word.size > 1
|
613
|
+
words.push(*(next_word.reverse))
|
614
|
+
next_word = words.pop
|
615
|
+
else
|
616
|
+
next_word = next_word[0]
|
617
|
+
end
|
618
|
+
next_word.strip! unless next_word.nil?
|
619
|
+
end
|
620
|
+
|
621
|
+
# Check to see if the line needs to be hyphenated. If a word has a
|
622
|
+
# hyphen in it (e.g., "fixed-width"), then we can ALWAYS wrap at
|
623
|
+
# that hyphenation, even if #hard_margins is not turned on. More
|
624
|
+
# elaborate forms of hyphenation will only be performed if
|
625
|
+
# #hard_margins is turned on. If we have returned more than one
|
626
|
+
# word, readjust the word list.
|
627
|
+
line, new_line_size, next_word = __hyphenate(line, line_size, next_word, max_line_width)
|
628
|
+
if next_word.kind_of?(Array)
|
629
|
+
if next_word.size > 1
|
630
|
+
words.push(*(next_word.reverse))
|
631
|
+
next_word = words.pop
|
632
|
+
else
|
633
|
+
next_word = next_word[0]
|
634
|
+
end
|
635
|
+
next_word.strip! unless next_word.nil?
|
636
|
+
end
|
637
|
+
|
638
|
+
text << __make_line(line, indent_str, max_line_width, next_word.nil?) unless line.nil?
|
639
|
+
|
640
|
+
if first_line
|
641
|
+
first_line = false
|
642
|
+
max_line_width = @columns - @body_indent - @left_margin - @right_margin
|
643
|
+
indent_str = ' ' * @body_indent
|
644
|
+
end
|
645
|
+
|
646
|
+
if next_word.nil?
|
647
|
+
line = []
|
648
|
+
new_line_size = 0
|
649
|
+
else
|
650
|
+
line = [ next_word ]
|
651
|
+
new_line_size = next_word.size
|
652
|
+
end
|
653
|
+
end
|
654
|
+
|
655
|
+
line_size = new_line_size
|
656
|
+
extra_space = __add_extra_space?(next_word) unless next_word.nil?
|
657
|
+
end
|
658
|
+
|
659
|
+
loop do
|
660
|
+
break if line.nil? or line.empty?
|
661
|
+
line, line_size, ww = __hyphenate(line, line_size, ww, max_line_width)#if @hard_margins
|
662
|
+
text << __make_line(line, indent_str, max_line_width, ww.nil?)
|
663
|
+
line = ww
|
664
|
+
ww = nil
|
665
|
+
end
|
666
|
+
|
667
|
+
if (@tag_paragraph and (not text.empty?))
|
668
|
+
if @tag_cur.nil? or @tag_cur.empty?
|
669
|
+
@tag_cur = @tag_text[0]
|
670
|
+
end
|
671
|
+
|
672
|
+
fchar = /(\S)/o.match(text[0])[1]
|
673
|
+
white = text[0].index(fchar)
|
674
|
+
|
675
|
+
unless @tag_cur.nil?
|
676
|
+
if ((white - @left_margin - 1) > @tag_cur.size) then
|
677
|
+
white = @tag_cur.size + @left_margin
|
678
|
+
text[0].gsub!(/^ {#{white}}/, "#{' ' * @left_margin}#{@tag_cur}")
|
679
|
+
else
|
680
|
+
text.unshift("#{' ' * @left_margin}#{@tag_cur}\n")
|
681
|
+
end
|
682
|
+
end
|
683
|
+
end
|
684
|
+
|
685
|
+
text.join('')
|
686
|
+
end
|
687
|
+
alias format format_one_paragraph
|
688
|
+
|
689
|
+
# Considers each element of text (provided or internal) as a paragraph.
|
690
|
+
# If #first_indent is the same as #body_indent, then paragraphs will be
|
691
|
+
# separated by a single empty line in the result; otherwise, the
|
692
|
+
# paragraphs will follow immediately after each other. Uses #format to
|
693
|
+
# do the heavy lifting.
|
694
|
+
#
|
695
|
+
# If +to_wrap+ responds to #split, then it will be split into an array
|
696
|
+
# of elements by calling #split with the value of +split_on+. The
|
697
|
+
# default value of split_on is $/, or the default record separator,
|
698
|
+
# repeated twice (e.g., /\n\n/).
|
699
|
+
def paragraphs(to_wrap = nil, split_on = /(#{$/}){2}/o)
|
700
|
+
to_wrap = @text if to_wrap.nil?
|
701
|
+
if to_wrap.respond_to?(:split)
|
702
|
+
to_wrap = to_wrap.split(split_on)
|
703
|
+
else
|
704
|
+
to_wrap = [to_wrap].flatten
|
705
|
+
end
|
706
|
+
|
707
|
+
if ((@first_indent == @body_indent) or @tag_paragraph) then
|
708
|
+
p_end = NEWLINE
|
709
|
+
else
|
710
|
+
p_end = ''
|
711
|
+
end
|
712
|
+
|
713
|
+
cnt = 0
|
714
|
+
ret = []
|
715
|
+
to_wrap.each do |tw|
|
716
|
+
@tag_cur = @tag_text[cnt] if @tag_paragraph
|
717
|
+
@tag_cur = '' if @tag_cur.nil?
|
718
|
+
line = format(tw)
|
719
|
+
ret << "#{line}#{p_end}" if (not line.nil?) and (line.size > 0)
|
720
|
+
cnt += 1
|
721
|
+
end
|
722
|
+
|
723
|
+
ret[-1].chomp! unless ret.empty?
|
724
|
+
ret.join('')
|
725
|
+
end
|
726
|
+
|
727
|
+
# Centers the text, preserving empty lines and tabs.
|
728
|
+
def center(to_center = nil)
|
729
|
+
to_center = @text if to_center.nil?
|
730
|
+
to_center = [to_center].flatten
|
731
|
+
|
732
|
+
tabs = 0
|
733
|
+
width = @columns - @left_margin - @right_margin
|
734
|
+
centered = []
|
735
|
+
to_center.each do |tc|
|
736
|
+
s = tc.strip
|
737
|
+
tabs = s.count(TAB)
|
738
|
+
tabs = 0 if tabs.nil?
|
739
|
+
ct = ((width - s.size - (tabs * @tabstop) + tabs) / 2)
|
740
|
+
ct = (width - @left_margin - @right_margin) - ct
|
741
|
+
centered << "#{s.rjust(ct)}\n"
|
742
|
+
end
|
743
|
+
centered.join('')
|
744
|
+
end
|
745
|
+
|
746
|
+
# Replaces all tab characters in the text with #tabstop spaces.
|
747
|
+
def expand(to_expand = nil)
|
748
|
+
to_expand = @text if to_expand.nil?
|
749
|
+
|
750
|
+
tmp = ' ' * @tabstop
|
751
|
+
changer = lambda do |text|
|
752
|
+
res = text.split(NEWLINE_RE)
|
753
|
+
res.collect! { |ln| ln.gsub!(/\t/o, tmp) }
|
754
|
+
res.join(NEWLINE)
|
755
|
+
end
|
756
|
+
|
757
|
+
if to_expand.kind_of?(Array)
|
758
|
+
to_expand.collect { |te| changer[te] }
|
759
|
+
else
|
760
|
+
changer[to_expand]
|
761
|
+
end
|
762
|
+
end
|
763
|
+
|
764
|
+
# Replaces all occurrences of #tabstop consecutive spaces with a tab
|
765
|
+
# character.
|
766
|
+
def unexpand(to_unexpand = nil)
|
767
|
+
to_unexpand = @text if to_unexpand.nil?
|
768
|
+
|
769
|
+
tmp = / {#{@tabstop}}/
|
770
|
+
changer = lambda do |text|
|
771
|
+
res = text.split(NEWLINE_RE)
|
772
|
+
res.collect! { |ln| ln.gsub!(tmp, TAB) }
|
773
|
+
res.join(NEWLINE)
|
774
|
+
end
|
775
|
+
|
776
|
+
if to_unexpand.kind_of?(Array)
|
777
|
+
to_unexpand.collect { |tu| changer[tu] }
|
778
|
+
else
|
779
|
+
changer[to_unexpand]
|
780
|
+
end
|
781
|
+
end
|
782
|
+
|
783
|
+
# Return +true+ if the word may have an extra space added after it. This
|
784
|
+
# will only be the case if #extra_space is +true+ and the word is not an
|
785
|
+
# abbreviation.
|
786
|
+
def __add_extra_space?(word)
|
787
|
+
return false unless @extra_space
|
788
|
+
word = word.gsub(/\.$/o, '') unless word.nil?
|
789
|
+
return false if ABBREV.include?(word)
|
790
|
+
return false if @abbreviations.include?(word)
|
791
|
+
true
|
792
|
+
end
|
793
|
+
private :__add_extra_space?
|
794
|
+
|
795
|
+
def __make_line(line, indent, width, last = false) #:nodoc:
|
796
|
+
line_size = line.inject(0) { |ls, el| ls + el.size }
|
797
|
+
lmargin = " " * @left_margin
|
798
|
+
fill = " " * (width - line_size) if right_fill? and (line_size <= width)
|
799
|
+
|
800
|
+
unless last
|
801
|
+
if justify? and (line.size > 1)
|
802
|
+
spaces = width - line_size
|
803
|
+
word_spaces = spaces / (line.size / 2)
|
804
|
+
spaces = spaces % (line.size / 2) if word_spaces > 0
|
805
|
+
line.reverse.each do |word|
|
806
|
+
next if (word =~ /^\S/o)
|
807
|
+
|
808
|
+
word.sub!(/^/o, " " * word_spaces)
|
809
|
+
|
810
|
+
next unless (spaces > 0)
|
811
|
+
|
812
|
+
word.sub!(/^/o, " ")
|
813
|
+
spaces -= 1
|
814
|
+
end
|
815
|
+
end
|
816
|
+
end
|
817
|
+
|
818
|
+
line = "#{lmargin}#{indent}#{line.join('')}#{fill}\n" unless line.empty?
|
819
|
+
|
820
|
+
if right_align? and (not line.nil?)
|
821
|
+
line.sub(/^/o, " " * (@columns - @right_margin - (line.size - 1)))
|
822
|
+
else
|
823
|
+
line
|
824
|
+
end
|
825
|
+
end
|
826
|
+
# private :__make_line
|
827
|
+
|
828
|
+
def __hyphenate(line, line_size, next_word, width) #:nodoc:
|
829
|
+
return [ line, line_size, next_word ] if line.nil? or line.empty?
|
830
|
+
rline = line.dup
|
831
|
+
rsize = line_size
|
832
|
+
|
833
|
+
rnext = []
|
834
|
+
rnext << next_word.dup unless next_word.nil?
|
835
|
+
|
836
|
+
loop do
|
837
|
+
break if rnext.nil? or rline.nil?
|
838
|
+
|
839
|
+
if rsize == width
|
840
|
+
break
|
841
|
+
elsif rsize > width
|
842
|
+
word = rline.pop
|
843
|
+
size = width - rsize + word.size
|
844
|
+
|
845
|
+
if (size < 1)
|
846
|
+
rnext.unshift word
|
847
|
+
next
|
848
|
+
end
|
849
|
+
|
850
|
+
first = rest = nil
|
851
|
+
|
852
|
+
# TODO: Add the check to see if the word contains a hyphen to
|
853
|
+
# split on automatically.
|
854
|
+
# Does the word already have a hyphen in it? If so, try to use
|
855
|
+
# that to split the word.
|
856
|
+
# if word.index('-') < size
|
857
|
+
# first = word[0 ... word.index("-")]
|
858
|
+
# rest = word[word.index("-") .. -1]
|
859
|
+
# end
|
860
|
+
|
861
|
+
if @hard_margins
|
862
|
+
if first.nil? and (@split_rules & SPLIT_HYPHENATION) == SPLIT_HYPHENATION
|
863
|
+
if @hyphenator_arity == 2
|
864
|
+
first, rest = @hyphenator.hyphenate_to(word, size)
|
865
|
+
else
|
866
|
+
first, rest = @hyphenator.hyphenate_to(word, size, self)
|
867
|
+
end
|
868
|
+
end
|
869
|
+
|
870
|
+
if first.nil? and (@split_rules & SPLIT_CONTINUATION) == SPLIT_CONTINUATION
|
871
|
+
first, rest = self.hyphenate_to(word, size)
|
872
|
+
end
|
873
|
+
|
874
|
+
if first.nil?
|
875
|
+
if (@split_rules & SPLIT_FIXED) == SPLIT_FIXED
|
876
|
+
first, rest = split_word_to(word, size)
|
877
|
+
elsif (not rest.nil? and (rest.size > size))
|
878
|
+
first, rest = split_word_to(word, size)
|
879
|
+
end
|
880
|
+
end
|
881
|
+
else
|
882
|
+
first = word if first.nil?
|
883
|
+
end
|
884
|
+
|
885
|
+
if first.nil?
|
886
|
+
rest = word
|
887
|
+
else
|
888
|
+
rsize = rsize - word.size + first.size
|
889
|
+
if rline.empty?
|
890
|
+
rline << first
|
891
|
+
else
|
892
|
+
rsize += 1
|
893
|
+
rline << " #{first}"
|
894
|
+
end
|
895
|
+
@split_words << SplitWord.new(word, first, rest)
|
896
|
+
end
|
897
|
+
rnext.unshift rest unless rest.nil?
|
898
|
+
break
|
899
|
+
else
|
900
|
+
break if rnext.empty?
|
901
|
+
word = rnext.shift.dup
|
902
|
+
size = width - rsize - 1
|
903
|
+
|
904
|
+
if (size <= 0)
|
905
|
+
rnext.unshift word
|
906
|
+
break
|
907
|
+
end
|
908
|
+
|
909
|
+
first = rest = nil
|
910
|
+
|
911
|
+
# TODO: Add the check to see if the word contains a hyphen to
|
912
|
+
# split on automatically.
|
913
|
+
# Does the word already have a hyphen in it? If so, try to use
|
914
|
+
# that to split the word.
|
915
|
+
# if word.index('-') < size
|
916
|
+
# first = word[0 ... word.index("-")]
|
917
|
+
# rest = word[word.index("-") .. -1]
|
918
|
+
# end
|
919
|
+
|
920
|
+
if @hard_margins
|
921
|
+
if (@split_rules & SPLIT_HYPHENATION) == SPLIT_HYPHENATION
|
922
|
+
if @hyphenator_arity == 2
|
923
|
+
first, rest = @hyphenator.hyphenate_to(word, size)
|
924
|
+
else
|
925
|
+
first, rest = @hyphenator.hyphenate_to(word, size, self)
|
926
|
+
end
|
927
|
+
end
|
928
|
+
|
929
|
+
if first.nil? and (@split_rules & SPLIT_CONTINUATION) == SPLIT_CONTINUATION
|
930
|
+
first, rest = self.hyphenate_to(word, size)
|
931
|
+
end
|
932
|
+
|
933
|
+
if first.nil?
|
934
|
+
if (@split_rules & SPLIT_FIXED) == SPLIT_FIXED
|
935
|
+
first, rest = split_word_to(word, size)
|
936
|
+
elsif (not rest.nil? and (rest.size > width))
|
937
|
+
first, rest = split_word_to(word, size)
|
938
|
+
end
|
939
|
+
end
|
940
|
+
else
|
941
|
+
first = word if first.nil?
|
942
|
+
end
|
943
|
+
|
944
|
+
# The word was successfully split. Does it fit?
|
945
|
+
unless first.nil?
|
946
|
+
if (rsize + first.size) < width
|
947
|
+
@split_words << SplitWord.new(word, first, rest)
|
948
|
+
|
949
|
+
rsize += first.size + 1
|
950
|
+
rline << " #{first}"
|
951
|
+
else
|
952
|
+
rest = word
|
953
|
+
end
|
954
|
+
else
|
955
|
+
rest = word unless rest.nil?
|
956
|
+
end
|
957
|
+
|
958
|
+
rnext.unshift rest
|
959
|
+
break
|
960
|
+
end
|
961
|
+
end
|
962
|
+
[ rline, rsize, rnext ]
|
963
|
+
end
|
964
|
+
private :__hyphenate
|
965
|
+
|
966
|
+
# The line must be broken. Typically, this is done by moving the last
|
967
|
+
# word on the current line to the next line. However, it may be possible
|
968
|
+
# that certain combinations of words may not be broken (see
|
969
|
+
# #nobreak_regex for more information). Therefore, it may be necessary
|
970
|
+
# to move multiple words from the current line to the next line. This
|
971
|
+
# function does this.
|
972
|
+
def __wrap_line(line, next_word)
|
973
|
+
no_break = false
|
974
|
+
|
975
|
+
word_index = line.size - 1
|
976
|
+
|
977
|
+
@nobreak_regex.each_pair do |first, second|
|
978
|
+
if line[word_index] =~ first and next_word =~ second
|
979
|
+
no_break = true
|
980
|
+
end
|
981
|
+
end
|
982
|
+
|
983
|
+
# If the last word and the next word aren't to be broken, and the line
|
984
|
+
# has more than one word in it, then we need to go back by words to
|
985
|
+
# ensure that we break as allowed.
|
986
|
+
if no_break and word_index.nonzero?
|
987
|
+
word_index -= 1
|
988
|
+
|
989
|
+
while word_index.nonzero?
|
990
|
+
no_break = false
|
991
|
+
@nobreak_regex.each_pair { |first, second|
|
992
|
+
if line[word_index] =~ first and line[word_index + 1] =~ second
|
993
|
+
no_break = true
|
994
|
+
end
|
995
|
+
}
|
996
|
+
|
997
|
+
break unless no_break
|
998
|
+
word_index -= 1
|
999
|
+
end
|
1000
|
+
|
1001
|
+
if word_index.nonzero?
|
1002
|
+
words = line.slice!(word_index .. -1)
|
1003
|
+
words << next_word
|
1004
|
+
end
|
1005
|
+
end
|
1006
|
+
|
1007
|
+
[line, words]
|
1008
|
+
end
|
1009
|
+
private :__wrap_line
|
1010
|
+
|
1011
|
+
# Create a Text::Format object. Accepts an optional hash of construction
|
1012
|
+
# options (this will be changed to named paramters in Ruby 2.0). After
|
1013
|
+
# the initial object is constructed (with either the provided or default
|
1014
|
+
# values), the object will be yielded (as +self+) to an optional block
|
1015
|
+
# for further construction and operation.
|
1016
|
+
def initialize(options = {}) #:yields self:
|
1017
|
+
@text = options[:text] || []
|
1018
|
+
@columns = options[:columns] || 72
|
1019
|
+
@tabstop = options[:tabstop] || 8
|
1020
|
+
@first_indent = options[:first_indent] || 4
|
1021
|
+
@body_indent = options[:body_indent] || 0
|
1022
|
+
@format_style = options[:format_style] || LEFT_ALIGN
|
1023
|
+
@left_margin = options[:left_margin] || 0
|
1024
|
+
@right_margin = options[:right_margin] || 0
|
1025
|
+
@extra_space = options[:extra_space] || false
|
1026
|
+
@tag_paragraph = options[:tag_paragraph] || false
|
1027
|
+
@tag_text = options[:tag_text] || []
|
1028
|
+
@abbreviations = options[:abbreviations] || []
|
1029
|
+
@terminal_punctuation = options[:terminal_punctuation] || ""
|
1030
|
+
@terminal_quotes = options[:terminal_quotes] || ""
|
1031
|
+
@nobreak = options[:nobreak] || false
|
1032
|
+
@nobreak_regex = options[:nobreak_regex] || {}
|
1033
|
+
@hard_margins = options[:hard_margins] || false
|
1034
|
+
@split_rules = options[:split_rules] || SPLIT_FIXED
|
1035
|
+
@hyphenator = options[:hyphenator] || self
|
1036
|
+
|
1037
|
+
@hyphenator_arity = @hyphenator.method(:hyphenate_to).arity
|
1038
|
+
@tag_cur = ""
|
1039
|
+
@split_words = []
|
1040
|
+
|
1041
|
+
yield self if block_given?
|
1042
|
+
end
|
1043
|
+
end
|