History

Add Elisp documentation for 26.3 release

- Add elisp.rb, clean_html.rb and entries.rb

MasterEnoc committed 6 years ago

Commit d470f301 parent 4eb4bfe3 files · +171 −0Browse files

Unified · Split

3 files
  1. lib/docs/filters/elisp/clean_html.rb +56 −0
  2. lib/docs/filters/elisp/entries.rb +50 −0
  3. lib/docs/scrapers/elisp.rb +65 −0
lib/docs/filters/elisp/clean_html.rb+56−0
@@ -0,0 +1,56 @@
1+module Docs
2+ class Elisp
3+ class CleanHtmlFilter < Filter
4+ def call
5+
6+ if current_url == root_url
7+ # remove copyright header
8+ css('table ~ p').remove
9+
10+ # remove "Detailed Node Listing" header
11+ css('h3').remove
12+
13+ # remove "Detailed Node Listing" table
14+ css('table')[1].remove
15+
16+ # remove copyright
17+ css('blockquote').remove
18+
19+ # remove index page in the index table
20+ css('tbody tr:last-child').remove
21+ end
22+
23+ # remove navigation bar
24+ css('.node').remove
25+
26+ # Remove content in headers
27+ css('h2', 'h3', 'h4', 'h5', 'h6').each do |node|
28+
29+ # remove numbers at the beginning of all headers
30+ node.content = node.content.slice(/[[:alpha:]]...*/)
31+
32+ # remove 'Appendix' word
33+ node.content = node.content.sub(/Appendix.{2}/, '') if node.content.include?('Appendix')
34+
35+ # remove 'E.' notation for appendixes
36+ if node.content.match?(/[[:upper:]]\./)
37+ # remove 'E.'
38+ node.content = node.content.sub(/[[:upper:]]\./, '')
39+ # remove all dots (.)
40+ node.content = node.content.gsub(/\./, '')
41+ # remove all numbers
42+ node.content = node.content.gsub(/[[:digit:]]/, '')
43+ end
44+
45+ end
46+
47+ # add id to each defun section that contains a functions, macro, etc.
48+ css('.defun').each do |node|
49+ node['id']= node.first_element_child.content
50+ end
51+
52+ doc
53+ end
54+ end
55+ end
56+end
lib/docs/filters/elisp/entries.rb+50−0
@@ -0,0 +1,50 @@
1+module Docs
2+ class Elisp
3+ class EntriesFilter < Docs::EntriesFilter
4+ def get_name
5+ # remove numbers at the beginnig
6+ name = at_css('h2', 'h3', 'h4', 'h5', 'h6').content.slice(/[[:alpha:]]...*/)
7+
8+ # remove 'Appendix' word
9+ name = name.sub(/Appendix.{2}/, '') if name.include?('Appendix')
10+
11+ # remove 'E.' notation for appendixes
12+ if name.match?(/[[:upper:]]\./)
13+ # remove 'E.'
14+ name = name.sub(/[[:upper:]]\./, '')
15+ # remove all dots (.)
16+ name = name.gsub(/\./, '')
17+ # remove all numbers
18+ name = name.gsub(/[[:digit:]]/, '')
19+ end
20+
21+ name
22+ end
23+
24+ def get_type
25+ 'Manual'
26+ end
27+
28+ def additional_entries
29+ entries = []
30+
31+ css('.defun').each do |node|
32+ entry_type = 'Builtin Functions' if node.content.include?('Function')
33+ entry_type = 'Builtin Macros' if node.content.include?('Macro')
34+ entry_type = 'Builtin Variables' if node.content.include?('Variable')
35+ entry_type = 'Builtin User Options' if node.content.include?('User Option')
36+ entry_type = 'Builtin Special Forms' if node.content.include?('Special Form')
37+ entry_type = 'Builtin Commands' if node.content.include?('Command')
38+ entry_type = 'Builtin Constants' if node.content.include?('Constant')
39+
40+ entry_name = node.first_element_child.content
41+ entry_path = slug + '#' + entry_name
42+ entries << [entry_name, entry_path.downcase, entry_type]
43+ end
44+
45+ entries
46+ end
47+
48+ end
49+ end
50+end
lib/docs/scrapers/elisp.rb+65−0
@@ -0,0 +1,65 @@
1+module Docs
2+ class Elisp < UrlScraper
3+ self.type = 'elisp'
4+ self.release = '26.3'
5+ self.base_url= 'https://www.gnu.org/software/emacs/manual/html_node/elisp/'
6+ self.root_path = 'index.html'
7+ self.links = {
8+ home:'https://www.gnu.org/software/emacs/manual/elisp',
9+ code: 'https://git.savannah.gnu.org/cgit/emacs.git'
10+ }
11+
12+ html_filters.push 'elisp/entries', 'elisp/clean_html'
13+
14+ # some file that were not skipped by skip patterns
15+ options[:skip] = [
16+ 'Coding-Conventions.html',
17+ 'Key-Binding-Conventions.html',
18+ 'Library-Headers.html'
19+ ]
20+
21+ # some non essential sections
22+ options[:skip_patterns] = [
23+ /Introduction.html/,
24+ /Antinews.html/,
25+ /GNU-Free-Documentation-License.html/,
26+ /GPL.html/,
27+ /Tips.html/,
28+ /Definition-of-/
29+ ]
30+
31+ # fix duplicates
32+ options[:fix_urls]= -> (url) do
33+ url.sub!('Window-Group.html', 'Basic-Windows.html')
34+ url.sub!('Local-defvar-example.html', 'Using-Lexical-Binding.html')
35+ url.sub!('Defining-Lisp-variables-in-C.html', 'Writing-Emacs-Primitives.html')
36+ url.sub!('describe_002dsymbols-example.html', 'Accessing-Documentation.html')
37+ url.sub!('The-interactive_002donly-property.html', 'Defining-Commands.html')
38+ url.sub!('Text-help_002decho.html', 'Special-Properties.html')
39+ url.sub!('Help-display.html', 'Special-Properties.html')
40+ url.sub!('autoload-cookie.html', 'Autoload.html')
41+ url.sub!('external_002ddebugging_002doutput.html', 'Output-Streams.html')
42+ url.sub!('modifier-bits.html', 'Other-Char-Bits.html')
43+ url.sub!('message_002dbox.html', 'Displaying-Messages.html')
44+ url.sub!('abbreviate_002dfile_002dname.html', 'Directory-Names.html')
45+ url.sub!('Inhibit-point-motion-hooks.html', 'Special-Properties.html')
46+ url.sub!('Coding-systems-for-a-subprocess.html', 'Process-Information.html')
47+ url.sub!('Process-Filter-Example.html', 'Filter-Functions.html')
48+ url.sub!('Docstring-hyperlinks.html', 'Documentation-Tips.html')
49+ url.sub!('seq_002dlet.html', 'Sequence-Functions.html')
50+ url.sub!('should_005fquit.html', 'Module-Misc.html')
51+ url.sub!('Display-Face-Attribute-Testing.html', 'Display-Feature-Testing.html')
52+ url.sub!('module-initialization-function.html', 'Module-Initialization.html')
53+ url.sub!('pcase_002dsymbol_002dcaveats.html', 'pcase-Macro.html')
54+ url.sub!('intern.html', 'Module-Misc.html')
55+ url.sub!('pcase_002dexample_002d1.html', 'pcase-Macro.html')
56+ url
57+ end
58+
59+ options[:attribution]= <<-HTML
60+ Copyright &copy; 1990-1996, 1998-2019 Free Software Foundation, Inc. <br>
61+ Licensed under the GNU GPL license.
62+ HTML
63+
64+ end
65+end