pdftohtmlr 0.3.1 → 0.4
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/README.textile +1 -1
- data/lib/pdftohtmlr.rb +10 -15
- data/test/pdftohtmlr_test.rb +4 -4
- metadata +2 -2
data/README.textile
CHANGED
@@ -15,7 +15,7 @@ h1. install
|
|
15
15
|
<pre><code>gem install pdftohtmlr</code></pre>
|
16
16
|
|
17
17
|
h1. using
|
18
|
-
"gist examples":http://gist.github.com/254556
|
18
|
+
"gist examples":http://gist.github.com/254556
|
19
19
|
|
20
20
|
<pre><code lang="ruby">require 'pdftohtmlr'
|
21
21
|
require 'nokogiri'
|
data/lib/pdftohtmlr.rb
CHANGED
@@ -10,7 +10,6 @@
|
|
10
10
|
# License:: MIT
|
11
11
|
|
12
12
|
require 'rubygems'
|
13
|
-
require 'open3'
|
14
13
|
require 'nokogiri'
|
15
14
|
require 'uri'
|
16
15
|
require 'open-uri'
|
@@ -21,7 +20,7 @@ module PDFToHTMLR
|
|
21
20
|
# Simple local error abstraction
|
22
21
|
class PDFToHTMLRError < RuntimeError; end
|
23
22
|
|
24
|
-
VERSION = '0.
|
23
|
+
VERSION = '0.4'
|
25
24
|
|
26
25
|
# Provides facilities for converting PDFs to HTML from Ruby code.
|
27
26
|
class PdfFile
|
@@ -42,22 +41,19 @@ module PDFToHTMLR
|
|
42
41
|
errors = ""
|
43
42
|
output = ""
|
44
43
|
if @user_pwd
|
45
|
-
cmd = "pdftohtml -stdout -upw #{@user_pwd}
|
44
|
+
cmd = "pdftohtml -stdout -upw #{@user_pwd}" + ' "' + @path + '"'
|
46
45
|
elsif @owner_pwd
|
47
|
-
cmd = "pdftohtml -stdout -opw #{@owner_pwd}
|
46
|
+
cmd = "pdftohtml -stdout -opw #{@owner_pwd}" + ' "' + @path + '"'
|
48
47
|
else
|
49
|
-
cmd = "pdftohtml -stdout
|
48
|
+
cmd = "pdftohtml -stdout" + ' "' + @path + '"'
|
50
49
|
end
|
51
50
|
|
52
|
-
|
53
|
-
stdin.write cmd
|
54
|
-
stdin.close
|
55
|
-
output = stdout.read
|
56
|
-
errors = stderr.read
|
57
|
-
end
|
51
|
+
output = `#{cmd} 2>&1`
|
58
52
|
|
59
|
-
if (
|
60
|
-
raise PDFToHTMLRError,
|
53
|
+
if (output.include?("Error: May not be a PDF file"))
|
54
|
+
raise PDFToHTMLRError, "Error: May not be a PDF file (continuing anyway)"
|
55
|
+
elsif (output.include?("Error:"))
|
56
|
+
raise PDFToHTMLRError, output.split("\n").first.to_s.chomp
|
61
57
|
else
|
62
58
|
return output
|
63
59
|
end
|
@@ -67,7 +63,6 @@ module PDFToHTMLR
|
|
67
63
|
def convert_to_document()
|
68
64
|
Nokogiri::HTML.parse(convert())
|
69
65
|
end
|
70
|
-
|
71
66
|
end
|
72
67
|
|
73
68
|
# Handle a string-based local path as input, extends PdfFile
|
@@ -92,7 +87,7 @@ module PDFToHTMLR
|
|
92
87
|
raise PDFToHTMLRError, "invalid file url"
|
93
88
|
end
|
94
89
|
tempfile = Tempfile.new('pdftohtmlr')
|
95
|
-
File.open(tempfile.path, '
|
90
|
+
File.open(tempfile.path, 'wb') {|f| f.write(open(input_url).read) }
|
96
91
|
super(tempfile.path, target_path, user_pwd, owner_pwd)
|
97
92
|
rescue => bang
|
98
93
|
raise PDFToHTMLRError, bang.to_s
|
data/test/pdftohtmlr_test.rb
CHANGED
@@ -36,7 +36,7 @@ class PdfFileTest < Test::Unit::TestCase
|
|
36
36
|
def test_string_from_pdffile
|
37
37
|
file = PdfFilePath.new(TEST_PDF_PATH, ".", nil, nil)
|
38
38
|
assert_equal "String", file.convert().class.to_s
|
39
|
-
assert_equal `pdftohtml -stdout #{TEST_PDF_PATH}`, file.convert()
|
39
|
+
assert_equal `pdftohtml -stdout "#{TEST_PDF_PATH}"`, file.convert()
|
40
40
|
end
|
41
41
|
|
42
42
|
def test_invalid_pwd_pdffile
|
@@ -50,7 +50,7 @@ class PdfFileTest < Test::Unit::TestCase
|
|
50
50
|
def test_valid_pwd_pdffile
|
51
51
|
file = PdfFilePath.new(TEST_PWD_PDF_PATH, ".", "user", nil)
|
52
52
|
assert_equal "String", file.convert().class.to_s
|
53
|
-
assert_equal `pdftohtml -stdout -upw user #{TEST_PWD_PDF_PATH}`,
|
53
|
+
assert_equal `pdftohtml -stdout -upw user "#{TEST_PWD_PDF_PATH}"`,
|
54
54
|
file.convert()
|
55
55
|
end
|
56
56
|
|
@@ -59,7 +59,7 @@ class PdfFileTest < Test::Unit::TestCase
|
|
59
59
|
assert_equal "Nokogiri::HTML::Document",
|
60
60
|
file.convert_to_document().class.to_s
|
61
61
|
assert_equal Nokogiri::HTML.parse(
|
62
|
-
`pdftohtml -stdout #{TEST_PDF_PATH}`
|
62
|
+
`pdftohtml -stdout "#{TEST_PDF_PATH}"`
|
63
63
|
).css('body').first.to_s,
|
64
64
|
file.convert_to_document().css('body').first.to_s
|
65
65
|
end
|
@@ -90,7 +90,7 @@ class PdfFileTest < Test::Unit::TestCase
|
|
90
90
|
# http://github.com/kitplummer/pdftohtmlr/raw/master/test/test.pdf
|
91
91
|
file = PdfFileUrl.new(TEST_URL_PDF, ".", nil, nil)
|
92
92
|
assert_equal "String", file.convert().class.to_s
|
93
|
-
assert_equal `pdftohtml -stdout #{TEST_PDF_PATH}`, file.convert()
|
93
|
+
assert_equal `pdftohtml -stdout "#{TEST_PDF_PATH}"`, file.convert()
|
94
94
|
end
|
95
95
|
|
96
96
|
def test_args
|
metadata
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: pdftohtmlr
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.
|
4
|
+
version: "0.4"
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Kit Plummer
|
@@ -9,7 +9,7 @@ autorequire: pdftohtml
|
|
9
9
|
bindir: bin
|
10
10
|
cert_chain: []
|
11
11
|
|
12
|
-
date: 2009-12-
|
12
|
+
date: 2009-12-18 00:00:00 -07:00
|
13
13
|
default_executable:
|
14
14
|
dependencies: []
|
15
15
|
|