qnd_html2page 0.2.1 → 0.2.2
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.
- checksums.yaml +4 -4
- checksums.yaml.gz.sig +0 -0
- data.tar.gz.sig +0 -0
- data/lib/qnd_html2page.rb +29 -9
- metadata +1 -1
- metadata.gz.sig +0 -0
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA256:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 51029b1be2ac9cb9e95d6567f99dc1c6fdda70c3a8d5904372f0ee07dcd2d78f
|
4
|
+
data.tar.gz: d9ff95df9754003699ce0a0bea93ebf308c7ff808bd5a8a6e450f016aba45c70
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 5496cc9c5f98b5d4dd0a68686983a42cac7f97c451b56acca42520dfc77aa0a5e5721851a9d4d0c970ad6c078f7e714ab14fa91f7e414e74dfb518bac8e6b559
|
7
|
+
data.tar.gz: 8330416d589c832e06df5147eb648617c92cd75809905803a10fffa5da1b4aca5ae81372c7c1cd7dae21d5b3d0bbd0a02f35312dbf1d6e614f2cf0051d09fec9
|
checksums.yaml.gz.sig
CHANGED
Binary file
|
data.tar.gz.sig
CHANGED
Binary file
|
data/lib/qnd_html2page.rb
CHANGED
@@ -39,9 +39,16 @@ class QndHtml2Page
|
|
39
39
|
|
40
40
|
private
|
41
41
|
|
42
|
-
def scan(
|
43
|
-
|
44
|
-
|
42
|
+
def scan(obj)
|
43
|
+
|
44
|
+
raw_html = obj.is_a?(Rexle) ? obj.xml : obj
|
45
|
+
|
46
|
+
# <br/> acts as a hard page break
|
47
|
+
html = raw_html.gsub(/<br\s*\/>/) do |x|
|
48
|
+
'<span class="qndhtml2pg">pagebreak' + x.object_id.to_s + '</span>'
|
49
|
+
end
|
50
|
+
|
51
|
+
# add the span tag after almost every element in the body
|
45
52
|
|
46
53
|
doc = Rexle.new(html)
|
47
54
|
body = doc.root.element('body')
|
@@ -68,11 +75,16 @@ class QndHtml2Page
|
|
68
75
|
|
69
76
|
browser = Ferrum::Browser.new
|
70
77
|
browser.goto('file://' + tmpfile.path + '.html')
|
71
|
-
span_list = browser.xpath('//span')
|
72
|
-
|
78
|
+
span_list = browser.xpath('//span[@class="qndhtml2pg"]')
|
79
|
+
|
80
|
+
maxheight = span_list.last.find_position.last
|
73
81
|
|
82
|
+
a = span_list.map do |x|
|
83
|
+
ypos = x.text[/^pagebreak/] ? maxheight : x.find_position.last
|
84
|
+
[x.text, ypos]
|
85
|
+
end
|
74
86
|
|
75
|
-
heights = ((
|
87
|
+
heights = ((maxheight) / @height).round.to_i.times\
|
76
88
|
.inject([@height]) {|r, x| r << (r.last + @height) }
|
77
89
|
|
78
90
|
puts ('heights: ' + heights.inspect).debug if @debug
|
@@ -84,7 +96,12 @@ class QndHtml2Page
|
|
84
96
|
puts ('x: ' + x.inspect).debug if @debug
|
85
97
|
puts ('height: ' + height.inspect).debug if @debug
|
86
98
|
|
87
|
-
|
99
|
+
if x.first[/^pagebreak/] then
|
100
|
+
r << [x]
|
101
|
+
else
|
102
|
+
x.last < height ? (r.last << x) : (height = heights.shift; r << [x])
|
103
|
+
end
|
104
|
+
|
88
105
|
r
|
89
106
|
|
90
107
|
end
|
@@ -106,9 +123,12 @@ class QndHtml2Page
|
|
106
123
|
pages = elements.slice_at(*stops).map do |e_list|
|
107
124
|
|
108
125
|
div = Rexle::Element.new 'div'
|
109
|
-
e_list.reject!
|
110
|
-
|
126
|
+
e_list.reject! do |e|
|
127
|
+
r = e.name == 'span' and e.attributes[:class] == 'qndhtml2pg'
|
128
|
+
r
|
129
|
+
end
|
111
130
|
next if e_list.empty?
|
131
|
+
|
112
132
|
e_list.each {|e| div.add e}
|
113
133
|
|
114
134
|
div
|
metadata
CHANGED
metadata.gz.sig
CHANGED
Binary file
|