auto_paragraph 1.0.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/lib/auto_paragraph.rb +335 -0
- metadata +46 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: 1ec07b8849e86618e4f7408753f47d7465daaa01
|
4
|
+
data.tar.gz: db510925c1a4a89d4a36a7348c10ee1edc2a01a6
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: 376ee810f0b881b127f6c245d30abec8ca83a6083b42b5af411bfc1b00e34db86b2bc9dca7a03828490ac3b7be3e8d99670ef32a25fea4863e86e27abf342e6b
|
7
|
+
data.tar.gz: ad41dbf903a765dbfc037b5692207c62d2a47f86866da0ef2a584dcbd05b49c5df08bb8f3659508acd6fc1de28bebb9206217d4cadb25d9425c8e4efccfc0e35
|
@@ -0,0 +1,335 @@
|
|
1
|
+
class AutoParagraph
|
2
|
+
# Same as Wordpress' wpautop
|
3
|
+
# From https://github.com/WordPress/WordPress/blob/4.3-branch/wp-includes/formatting.php
|
4
|
+
|
5
|
+
BLOCK_LEVEL_TAGS = '(?:table|thead|tfoot|caption|col|colgroup|tbody|tr|td|th|div|dl|dd|dt|ul|ol|li|pre|form|map|area|blockquote|address|math|style|p|h[1-6]|hr|fieldset|legend|section|article|aside|hgroup|header|footer|nav|figure|figcaption|details|menu|summary)'
|
6
|
+
|
7
|
+
def initialize(insert_line_breaks: true)
|
8
|
+
@pre_tags = {}
|
9
|
+
@insert_line_breaks = insert_line_breaks
|
10
|
+
end
|
11
|
+
|
12
|
+
def execute(input)
|
13
|
+
return '' if input.strip.empty?
|
14
|
+
|
15
|
+
@input = input.to_s
|
16
|
+
|
17
|
+
setup_input_string
|
18
|
+
|
19
|
+
add_placeholders
|
20
|
+
add_p_tags
|
21
|
+
remove_extraneous_p_tags
|
22
|
+
insert_and_cleanup_br_tags
|
23
|
+
|
24
|
+
replace_more_with_clear_both
|
25
|
+
|
26
|
+
restore_placeholders
|
27
|
+
|
28
|
+
@input
|
29
|
+
end
|
30
|
+
|
31
|
+
private
|
32
|
+
|
33
|
+
|
34
|
+
# For testing
|
35
|
+
def input_hook
|
36
|
+
@input
|
37
|
+
end
|
38
|
+
|
39
|
+
def input_hook=(input)
|
40
|
+
@input = input
|
41
|
+
end
|
42
|
+
|
43
|
+
def add_placeholders
|
44
|
+
pad_newline
|
45
|
+
replace_pre_with_placeholders
|
46
|
+
end
|
47
|
+
|
48
|
+
|
49
|
+
def setup_input_string
|
50
|
+
multiple_brs_into_two_line_breaks
|
51
|
+
add_single_line_break_above_block_level_opening_tags
|
52
|
+
add_double_break_below_block_level_closing_tags
|
53
|
+
standardize_newline_to_backslash_n
|
54
|
+
replace_newlines_in_elements_with_placeholders
|
55
|
+
collapse_line_breaks_around_option_elements
|
56
|
+
collapse_line_breaks_inside_object_before_param_or_embed
|
57
|
+
collapse_line_breaks_inside_audio_video_around_source_track
|
58
|
+
remove_more_than_two_contiguous_line_breaks
|
59
|
+
end
|
60
|
+
|
61
|
+
def add_p_tags
|
62
|
+
add_p_tags_at_doule_linebreaks
|
63
|
+
end
|
64
|
+
|
65
|
+
def remove_extraneous_p_tags
|
66
|
+
remove_p_with_only_whitespace
|
67
|
+
add_closing_p_inside_div_address_form
|
68
|
+
unwrap_opening_closing_element_from_p
|
69
|
+
unwrap_li_from_p
|
70
|
+
unwrap_blockquote_from_p
|
71
|
+
remove_preceeding_p_from_block_element_tag
|
72
|
+
remove_following_p_from_block_element_tag
|
73
|
+
end
|
74
|
+
|
75
|
+
def insert_and_cleanup_br_tags
|
76
|
+
insert_line_breaks
|
77
|
+
remove_br_after_opening_closing_block_tag
|
78
|
+
remove_br_before_some_block_tags
|
79
|
+
end
|
80
|
+
|
81
|
+
def restore_placeholders
|
82
|
+
restore_pre_with_placeholders
|
83
|
+
restore_newlines_in_elements_with_placeholders
|
84
|
+
end
|
85
|
+
|
86
|
+
def pad_newline
|
87
|
+
@input += "\n"
|
88
|
+
end
|
89
|
+
|
90
|
+
def replace_pre_with_placeholders
|
91
|
+
# Pre tags shouldn't be touched by autop.
|
92
|
+
# Replace pre tags with placeholders and bring them back after autop.
|
93
|
+
if @input.match("<pre")
|
94
|
+
@pre_tags = {}
|
95
|
+
|
96
|
+
input_parts = @input.split '</pre>'
|
97
|
+
last_input_part = input_parts.pop
|
98
|
+
|
99
|
+
input = ''
|
100
|
+
input_parts.each_with_index do |input_part,i|
|
101
|
+
|
102
|
+
start_position = input_part.index('<pre')
|
103
|
+
|
104
|
+
# Malformed html?
|
105
|
+
if !start_position
|
106
|
+
input += input_part
|
107
|
+
next
|
108
|
+
end
|
109
|
+
|
110
|
+
placeholder_name = "<pre wp-pre-tag-#{i}></pre>";
|
111
|
+
@pre_tags[placeholder_name] = input_part[start_position..-1]+'</pre>'
|
112
|
+
|
113
|
+
input += input_part[0..start_position-1] + placeholder_name
|
114
|
+
end
|
115
|
+
@input = input + last_input_part
|
116
|
+
end
|
117
|
+
@input
|
118
|
+
end
|
119
|
+
|
120
|
+
|
121
|
+
def multiple_brs_into_two_line_breaks
|
122
|
+
@input.gsub! %r{<br\s*/?>\s*<br\s*/?>}, "\n\n"
|
123
|
+
end
|
124
|
+
|
125
|
+
|
126
|
+
def add_single_line_break_above_block_level_opening_tags
|
127
|
+
@input.gsub! %r{(<#{BLOCK_LEVEL_TAGS}[^>]*>)}, "\n\\1"
|
128
|
+
end
|
129
|
+
|
130
|
+
def add_double_break_below_block_level_closing_tags
|
131
|
+
# input = preg_replace('!(</' . $allblocks . '>)!', "$1\n\n", input);
|
132
|
+
@input.gsub! %r{(</#{BLOCK_LEVEL_TAGS}>)}, "\\1\n\n"
|
133
|
+
end
|
134
|
+
|
135
|
+
def standardize_newline_to_backslash_n
|
136
|
+
["\r\n","\r"].each do |from|
|
137
|
+
@input.gsub! from, "\n"
|
138
|
+
end
|
139
|
+
end
|
140
|
+
|
141
|
+
def replace_newlines_in_elements_with_placeholders
|
142
|
+
@input = replace_in_html_tags(@input, { "\n" => " <!-- wpnl --> " })
|
143
|
+
end
|
144
|
+
|
145
|
+
def collapse_line_breaks_around_option_elements
|
146
|
+
if @input.match("<option")
|
147
|
+
@input.gsub!(/\s*<option/, '<option');
|
148
|
+
@input.gsub!(/<\/option>\s*/, '</option>');
|
149
|
+
end
|
150
|
+
end
|
151
|
+
|
152
|
+
def collapse_line_breaks_inside_object_before_param_or_embed
|
153
|
+
# Collapse line breaks inside <object> elements, before <param> and <embed> elements
|
154
|
+
if @input.match("</object>")
|
155
|
+
@input.gsub!(/(<object[^>]*>)\s*/, "\\1")
|
156
|
+
@input.gsub!(/\s*<\/object>/, '</object>')
|
157
|
+
@input.gsub!(/\s*(<\/?(?:param|embed)[^>]*>)\s*/, "\\1")
|
158
|
+
end
|
159
|
+
end
|
160
|
+
|
161
|
+
def collapse_line_breaks_inside_audio_video_around_source_track
|
162
|
+
# Collapse line breaks inside <audio> and <video> elements,
|
163
|
+
# before and after <source> and <track> elements.
|
164
|
+
if @input.match("<source") || @input.match("<track")
|
165
|
+
@input.gsub!(%r{([<\[](?:audio|video)[^>\]]*[>\]])\s*}, "\\1")
|
166
|
+
@input.gsub!(%r{\s*([<\[]/(?:audio|video)[>\]])}, "\\1")
|
167
|
+
@input.gsub!(%r{\s*(<(?:source|track)[^>]*>)\s*}, "\\1")
|
168
|
+
end
|
169
|
+
end
|
170
|
+
|
171
|
+
|
172
|
+
def remove_more_than_two_contiguous_line_breaks
|
173
|
+
@input.gsub!(/\n\n+/, "\n\n")
|
174
|
+
end
|
175
|
+
|
176
|
+
def add_p_tags_at_doule_linebreaks
|
177
|
+
# Split up the contents into an array of strings, separated by double line breaks.
|
178
|
+
@input = @input.split(/\n\s*\n/).map do |para|
|
179
|
+
'<p>'+para.sub(/^\n+/,'').sub(/\n+$/,'')+"</p>\n"
|
180
|
+
end.join("")
|
181
|
+
end
|
182
|
+
|
183
|
+
def remove_p_with_only_whitespace
|
184
|
+
# Under certain strange conditions it could create a P of entirely whitespace.
|
185
|
+
@input.gsub!(%r{<p>\s*</p>}, '')
|
186
|
+
end
|
187
|
+
|
188
|
+
def add_closing_p_inside_div_address_form
|
189
|
+
#Add a closing <p> inside <div>, <address>, or <form> tag if missing.
|
190
|
+
@input.gsub!(%r{<p>([^<]+)</(div|address|form)>}, "<p>\\1</p></\\2>")
|
191
|
+
end
|
192
|
+
|
193
|
+
def unwrap_opening_closing_element_from_p
|
194
|
+
# If an opening or closing block element tag is wrapped in a <p>, unwrap it.
|
195
|
+
@input.gsub!(%r{<p>\s*(</?#{BLOCK_LEVEL_TAGS}[^>]*>)\s*</p>}, "\\1")
|
196
|
+
end
|
197
|
+
|
198
|
+
def unwrap_li_from_p
|
199
|
+
# In some cases <li> may get wrapped in <p>, fix them.
|
200
|
+
@input.gsub!(%r{<p>(<li.+?)</p>}, "\\1")
|
201
|
+
end
|
202
|
+
|
203
|
+
|
204
|
+
def unwrap_blockquote_from_p
|
205
|
+
# If a <blockquote> is wrapped with a <p>, move it inside the <blockquote>.
|
206
|
+
@input.gsub!(%r{<p><blockquote([^>]*)>}i, "<blockquote\\1><p>")
|
207
|
+
@input.gsub!("</blockquote></p>", "</p></blockquote>")
|
208
|
+
end
|
209
|
+
|
210
|
+
def remove_preceeding_p_from_block_element_tag
|
211
|
+
# If an opening or closing block element tag is preceded by an opening <p> tag, remove it.
|
212
|
+
@input.gsub!(%r{<p>\s*(</?#{BLOCK_LEVEL_TAGS}[^>]*>)}, "\\1")
|
213
|
+
end
|
214
|
+
|
215
|
+
def remove_following_p_from_block_element_tag
|
216
|
+
# If an opening or closing block element tag is followed by a closing <p> tag, remove it.
|
217
|
+
@input.gsub!(%r{(</?#{BLOCK_LEVEL_TAGS}[^>]*>)\s*</p>}, "\\1")
|
218
|
+
end
|
219
|
+
|
220
|
+
def insert_line_breaks
|
221
|
+
# Optionally insert line breaks.
|
222
|
+
if @insert_line_breaks
|
223
|
+
# Replace newlines that shouldn't be touched with a placeholder.
|
224
|
+
@input.gsub!(%r{<(script|style).*?</\1>}m) do |match|
|
225
|
+
match.gsub("\n", "<WPPreserveNewline />")
|
226
|
+
end
|
227
|
+
|
228
|
+
# Normalize <br>
|
229
|
+
@input.gsub!(Regexp.union('<br>', '<br/>'), '<br />')
|
230
|
+
|
231
|
+
# Replace any new line characters that aren't preceded by a <br /> with a <br />.
|
232
|
+
@input.gsub!(%r{(?<!<br />)\s*\n}, "<br />\n")
|
233
|
+
|
234
|
+
# Replace newline placeholders with newlines.
|
235
|
+
@input.gsub!('<WPPreserveNewline />', "\n")
|
236
|
+
end
|
237
|
+
end
|
238
|
+
|
239
|
+
def remove_br_after_opening_closing_block_tag
|
240
|
+
# If a <br /> tag is after an opening or closing block tag, remove it.
|
241
|
+
@input.gsub!(%r{(</?#{BLOCK_LEVEL_TAGS}[^>]*>)\s*<br />}, "\\1")
|
242
|
+
end
|
243
|
+
|
244
|
+
def remove_br_before_some_block_tags
|
245
|
+
# If a <br /> tag is before a subset of opening or closing block tags, remove it.
|
246
|
+
@input.gsub!(%r{<br />(\s*</?(?:p|li|div|dl|dd|dt|th|pre|td|ul|ol)[^>]*>)}, "\\1")
|
247
|
+
@input.gsub!(%r{\n</p>$}, "</p>")
|
248
|
+
end
|
249
|
+
|
250
|
+
def replace_more_with_clear_both
|
251
|
+
@input.gsub! %r{<!--more(.*?)?-->}, '<div class="clear-both"></div>'
|
252
|
+
end
|
253
|
+
|
254
|
+
def restore_pre_with_placeholders
|
255
|
+
# Replace placeholder <pre> tags with their original content.
|
256
|
+
@pre_tags.each do |key, val|
|
257
|
+
@input.gsub!(key, val)
|
258
|
+
end
|
259
|
+
end
|
260
|
+
|
261
|
+
def restore_newlines_in_elements_with_placeholders
|
262
|
+
# Restore newlines in all elements.
|
263
|
+
@input.gsub!(Regexp.union(' <!-- wpnl --> ', '<!-- wpnl -->'), "\n")
|
264
|
+
end
|
265
|
+
|
266
|
+
|
267
|
+
def split_html_elements_regex
|
268
|
+
|
269
|
+
comments =
|
270
|
+
'!' + # Start of comment, after the <.
|
271
|
+
'(?:' + # Unroll the loop: Consume everything until --> is found.
|
272
|
+
'-(?!->)' + # Dash not followed by end of comment.
|
273
|
+
'[^\-]*+' + # Consume non-dashes.
|
274
|
+
')*+' + # Loop possessively.
|
275
|
+
'(?:-->)?' # End of comment. If not found, match all input.
|
276
|
+
|
277
|
+
cdata =
|
278
|
+
'!\[CDATA\[' + # Start of comment, after the <.
|
279
|
+
'[^\]]*+' + # Consume non-].
|
280
|
+
'(?:' + # Unroll the loop: Consume everything until ]]> is found.
|
281
|
+
'\](?!\]>)' + # One ] not followed by end of comment.
|
282
|
+
'[^\]]*+' + # Consume non-].
|
283
|
+
')*+' + # Loop possessively.
|
284
|
+
'(?:\]\]>)?' # End of comment. If not found, match all input.
|
285
|
+
|
286
|
+
regex =
|
287
|
+
'([^<]*)' + # Find from the start of the string
|
288
|
+
'(' + # Capture the tag
|
289
|
+
'<' + # Find start of element.
|
290
|
+
'(?:' + # (non-matching group)
|
291
|
+
'(?=!--)' + # Is this a comment?
|
292
|
+
comments + # Find end of comment
|
293
|
+
')' +
|
294
|
+
'|' + # OR
|
295
|
+
'(?:' + # (non-matching group)
|
296
|
+
'(?=!\[CDATA\[)' + # Is this a comment?
|
297
|
+
cdata + # Find end of comment
|
298
|
+
')' +
|
299
|
+
'|' + # OR
|
300
|
+
'(?:' + # (non-matching group)
|
301
|
+
'[^>]*' + # Find end of element.
|
302
|
+
')' + #
|
303
|
+
'>?' + # If not found, match all input.
|
304
|
+
')'
|
305
|
+
|
306
|
+
Regexp.new(regex, Regexp::MULTILINE)
|
307
|
+
end
|
308
|
+
|
309
|
+
def split_html_elements(text)
|
310
|
+
text.split(split_html_elements_regex)
|
311
|
+
end
|
312
|
+
|
313
|
+
def every_tag_only(source)
|
314
|
+
# Returns every third element starting at 3: ["","data","<tag>","","more data","</closetag>"] => ["<tag>","</closetag>"]
|
315
|
+
source.drop(2).each_slice(3).map(&:first)
|
316
|
+
end
|
317
|
+
|
318
|
+
def replace_in_html_tags(haystack, replace_pairs)
|
319
|
+
# find all elements
|
320
|
+
tags_split = split_html_elements(haystack)
|
321
|
+
changed = false
|
322
|
+
|
323
|
+
# Loop through every third element (html tags only)
|
324
|
+
keys = Regexp.new(replace_pairs.keys.join("|"))
|
325
|
+
every_tag_only(tags_split).each do |tag|
|
326
|
+
# Changes existing string, so replaces inside tags_split array
|
327
|
+
changed = true if tag.gsub!(keys, replace_pairs)
|
328
|
+
end
|
329
|
+
|
330
|
+
haystack = tags_split.join("") if changed
|
331
|
+
|
332
|
+
haystack
|
333
|
+
end
|
334
|
+
|
335
|
+
end
|
metadata
ADDED
@@ -0,0 +1,46 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: auto_paragraph
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 1.0.0
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- David Peterson
|
8
|
+
autorequire:
|
9
|
+
bindir: bin
|
10
|
+
cert_chain: []
|
11
|
+
date: 2016-01-11 00:00:00.000000000 Z
|
12
|
+
dependencies: []
|
13
|
+
description: Same as Wordpress' wpautop() function
|
14
|
+
email: dp@vivitec.com.au
|
15
|
+
executables: []
|
16
|
+
extensions: []
|
17
|
+
extra_rdoc_files: []
|
18
|
+
files:
|
19
|
+
- lib/auto_paragraph.rb
|
20
|
+
homepage: https://github.com/dippysan/auto_paragraph
|
21
|
+
licenses:
|
22
|
+
- MIT
|
23
|
+
metadata: {}
|
24
|
+
post_install_message:
|
25
|
+
rdoc_options: []
|
26
|
+
require_paths:
|
27
|
+
- lib
|
28
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
29
|
+
requirements:
|
30
|
+
- - ">="
|
31
|
+
- !ruby/object:Gem::Version
|
32
|
+
version: '0'
|
33
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
34
|
+
requirements:
|
35
|
+
- - ">="
|
36
|
+
- !ruby/object:Gem::Version
|
37
|
+
version: '0'
|
38
|
+
requirements: []
|
39
|
+
rubyforge_project:
|
40
|
+
rubygems_version: 2.2.2
|
41
|
+
signing_key:
|
42
|
+
specification_version: 4
|
43
|
+
summary: 'Formats Wordpress post content in Ruby: Replaces double line breaks with
|
44
|
+
paragraph elements'
|
45
|
+
test_files: []
|
46
|
+
has_rdoc:
|