w3m-autopagerize 1.0.2 → 1.0.3
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- data/lib/w3m-autopagerize-server.rb +10 -17
- data/readme.org +0 -3
- metadata +2 -2
@@ -1,8 +1,8 @@
|
|
1
1
|
# -*- coding: utf-8 -*-
|
2
2
|
# (executable-interpret "ruby19 /m/home/rubikitch/w3m/cgi-bin/w3m-autopagerize/test-w3m-autopagerize.rb --no-use-color ")
|
3
|
-
# (executable-interpret "rm -f /log/w3m-autopagerize.log; w3m-autopagerize-server
|
3
|
+
# (executable-interpret "rm -f /log/w3m-autopagerize.log; ../bin/w3m-autopagerize-server -r")
|
4
4
|
$start_time = Time.now
|
5
|
-
|
5
|
+
Encoding.default_external = "ASCII-8BIT" if RUBY_VERSION >= "1.9"
|
6
6
|
require 'kconv'
|
7
7
|
require 'uri'
|
8
8
|
require 'rubygems'
|
@@ -194,7 +194,6 @@ $content_cache = Hash.new do |h,url|
|
|
194
194
|
header, source = get_header_and_content(url)
|
195
195
|
$logger.debug "cache miss: source is html? = #{source =~ /<body/i and true}"
|
196
196
|
charset = normalize_charset(header[/charset=(.+)$/,1] || Kconv.guess(source))
|
197
|
-
source.force_encoding("ASCII-8BIT")
|
198
197
|
h[url] = [source, charset]
|
199
198
|
end
|
200
199
|
|
@@ -213,9 +212,9 @@ end
|
|
213
212
|
###########################################################################
|
214
213
|
def get_header_and_content(url)
|
215
214
|
output = `w3m #$W3M_EXTRA_OPTIONS -dump_both -o accept_encoding='gzip' "#{url}"`
|
216
|
-
header, source = output.
|
215
|
+
header, source = output.split(/\n\n/, 2)
|
217
216
|
open(TMPFILE,"wb"){|f| f.write source}
|
218
|
-
source = File.zread(TMPFILE)
|
217
|
+
source = File.zread(TMPFILE)
|
219
218
|
[header, source]
|
220
219
|
ensure
|
221
220
|
File.unlink TMPFILE if File.exist? TMPFILE
|
@@ -225,7 +224,7 @@ def get_content(url)
|
|
225
224
|
if url =~ /^https?:/
|
226
225
|
get_header_and_content(url)[1]
|
227
226
|
else # local file
|
228
|
-
File.zread(File.expand_path(url))
|
227
|
+
File.zread(File.expand_path(url))
|
229
228
|
end
|
230
229
|
end
|
231
230
|
|
@@ -240,13 +239,6 @@ def reinit
|
|
240
239
|
$SITEINFO = []
|
241
240
|
end
|
242
241
|
|
243
|
-
# unless "".respond_to? :force_encoding # for ruby 1.8
|
244
|
-
# class String
|
245
|
-
# def force_encoding(args); self end
|
246
|
-
# def encoding; Kconv.guess(self) end
|
247
|
-
# end
|
248
|
-
# end
|
249
|
-
|
250
242
|
###########################################################################
|
251
243
|
# Entry Points #
|
252
244
|
###########################################################################
|
@@ -289,12 +281,13 @@ class Server
|
|
289
281
|
else
|
290
282
|
errmsg = ""
|
291
283
|
end
|
284
|
+
html_piece
|
292
285
|
# BUG: Nokogiri emits superfluous .
|
293
286
|
html_piece.gsub! / /, '' # hack
|
294
287
|
# BUG: w3m cannot handle <script />, so replace it with <script></script>
|
295
288
|
html_piece.gsub! %r!(<script.+?)/>!, '\1></script>' # hack
|
296
289
|
%w[location title prev_url sitedata.pageElement sitedata.nextLink errmsg html_piece].each do |e|
|
297
|
-
|
290
|
+
$logger.debug "#{__method__}: #{e}.encoding = #{eval("#{e}.encoding rescue nil")}"
|
298
291
|
end
|
299
292
|
html = %{<html>
|
300
293
|
<head><base href="#{location}" />#{title}
|
@@ -334,14 +327,14 @@ class Server
|
|
334
327
|
$logger.debug "#{method}: W3M_SOURCEFILE = #{srcfile}" if srcfile
|
335
328
|
$client = client
|
336
329
|
|
337
|
-
src = File.zread(srcfile)
|
330
|
+
src = File.zread(srcfile) if srcfile
|
338
331
|
if url =~ /^file:.*\/cgi-bin\// # from Local CGI
|
339
|
-
url = src
|
332
|
+
url = src[%r!<base href=['"](.+?)['"]!, 1] # '"
|
340
333
|
$logger.info "#{method}: base url=#{url}"
|
341
334
|
else # from W3M_SOURCEFILE
|
342
335
|
$logger.debug "#{method}: set $content_cache[#{url.inspect}] from W3M_SOURCEFILE"
|
343
336
|
$logger.debug "#{method}: source is html? = #{src =~ /<body/i and true}"
|
344
|
-
$content_cache[url] = [src
|
337
|
+
$content_cache[url] = [src, normalize_charset(charset)] if src
|
345
338
|
end
|
346
339
|
[ src, url ]
|
347
340
|
end
|
data/readme.org
CHANGED
@@ -1,14 +1,11 @@
|
|
1
1
|
#+TITLE: AutoPagerize for w3m
|
2
2
|
#+AUTHOR: rubikitch
|
3
3
|
#+EMAIL: rubikitch@ruby-lang.org
|
4
|
-
#+DATE: 2009-01-30
|
5
4
|
#+LANGUAGE: en
|
6
5
|
#+OPTIONS: H:3 num:t toc:t \n:nil @:t ::t |:t ^:t -:t f:t *:t TeX:t LaTeX:nil skip:nil d:nil todo:t pri:nil tags:not-in-toc
|
7
6
|
#+INFOJS_OPT: view:nil toc:nil ltoc:t mouse:underline buttons:0 path:http://orgmode.org/org-info.js
|
8
7
|
#+EXPORT_SELECT_TAGS: export
|
9
8
|
#+EXPORT_EXCLUDE_TAGS: noexport
|
10
|
-
#+LINK_UP:
|
11
|
-
#+LINK_HOME:
|
12
9
|
AutoPagerize for w3m http://rubikitchrb.rubyforge.org/
|
13
10
|
|
14
11
|
Copyright (c) 2009 rubikitch <rubikitch@ruby-lang.org> http://www.rubyist.net/~rubikitch/
|
metadata
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: w3m-autopagerize
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 1.0.
|
4
|
+
version: 1.0.3
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- rubikitch
|
@@ -23,7 +23,7 @@ dependencies:
|
|
23
23
|
version: "0"
|
24
24
|
version:
|
25
25
|
- !ruby/object:Gem::Dependency
|
26
|
-
name:
|
26
|
+
name: json
|
27
27
|
type: :runtime
|
28
28
|
version_requirement:
|
29
29
|
version_requirements: !ruby/object:Gem::Requirement
|