asposewordsjavaforruby 0.0.4 → 0.0.5
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 +7 -0
- data/Gempackage +2 -2
- data/LICENSE +20 -20
- data/README.md +28 -2
- data/Rakefile +2 -2
- data/asposewordsjavaforruby.gemspec +27 -27
- data/config/aspose.yml +5 -5
- data/data/LoadTxt.txt +14 -14
- data/lib/asposewordsjavaforruby.rb +71 -71
- data/lib/asposewordsjavaforruby/addwatermark.rb +84 -84
- data/lib/asposewordsjavaforruby/appenddoc.rb +24 -24
- data/lib/asposewordsjavaforruby/appenddocument.rb +229 -229
- data/lib/asposewordsjavaforruby/applylicense.rb +16 -16
- data/lib/asposewordsjavaforruby/asposewordsjava.rb +23 -23
- data/lib/asposewordsjavaforruby/autofittables.rb +123 -123
- data/lib/asposewordsjavaforruby/bookmarks.rb +132 -132
- data/lib/asposewordsjavaforruby/checkformat.rb +70 -70
- data/lib/asposewordsjavaforruby/compressimages.rb +53 -53
- data/lib/asposewordsjavaforruby/doc2pdf.rb +15 -15
- data/lib/asposewordsjavaforruby/doctohtml.rb +26 -26
- data/lib/asposewordsjavaforruby/extractcontent.rb +395 -395
- data/lib/asposewordsjavaforruby/findandreplace.rb +29 -29
- data/lib/asposewordsjavaforruby/helloworld.rb +26 -26
- data/lib/asposewordsjavaforruby/imagetopdf.rb +71 -71
- data/lib/asposewordsjavaforruby/insertnestedfields.rb +39 -39
- data/lib/asposewordsjavaforruby/loadandsavetodisk.rb +20 -20
- data/lib/asposewordsjavaforruby/loadandsavetostream.rb +32 -32
- data/lib/asposewordsjavaforruby/loadtxt.rb +14 -14
- data/lib/asposewordsjavaforruby/mergefield.rb +45 -45
- data/lib/asposewordsjavaforruby/nodes.rb +29 -29
- data/lib/asposewordsjavaforruby/processcomments.rb +72 -72
- data/lib/asposewordsjavaforruby/removebreaks.rb +65 -65
- data/lib/asposewordsjavaforruby/removefield.rb +23 -23
- data/lib/asposewordsjavaforruby/saveasmultipagetiff.rb +26 -26
- data/lib/asposewordsjavaforruby/simplemailmerge.rb +23 -23
- data/lib/asposewordsjavaforruby/styles.rb +77 -77
- data/lib/asposewordsjavaforruby/updatefields.rb +62 -62
- data/lib/asposewordsjavaforruby/version.rb +3 -3
- metadata +18 -28
|
@@ -1,70 +1,70 @@
|
|
|
1
|
-
require 'fileutils'
|
|
2
|
-
module Asposewordsjavaforruby
|
|
3
|
-
module CheckFormat
|
|
4
|
-
def initialize()
|
|
5
|
-
# The path to the documents directory.
|
|
6
|
-
data_dir = File.dirname(File.dirname(File.dirname(__FILE__))) + '/data/'
|
|
7
|
-
|
|
8
|
-
@supported_dir = data_dir + 'OutSupported/'
|
|
9
|
-
file = Rjb::import("java.io.File").new(data_dir + 'joiningandappending/')
|
|
10
|
-
|
|
11
|
-
check_fromat(file)
|
|
12
|
-
end
|
|
13
|
-
|
|
14
|
-
def check_fromat(file)
|
|
15
|
-
files_list = file.listFiles()
|
|
16
|
-
load_format = Rjb::import('com.aspose.words.LoadFormat')
|
|
17
|
-
|
|
18
|
-
files_list.each do |file|
|
|
19
|
-
if(file.isDirectory()) then
|
|
20
|
-
next
|
|
21
|
-
end
|
|
22
|
-
|
|
23
|
-
name_only = file.getName()
|
|
24
|
-
puts name_only
|
|
25
|
-
file_name = file.getPath()
|
|
26
|
-
puts file_name
|
|
27
|
-
|
|
28
|
-
info_obj = Rjb::import('com.aspose.words.FileFormatUtil')
|
|
29
|
-
info = info_obj.detectFileFormat(file_name)
|
|
30
|
-
case info.getLoadFormat()
|
|
31
|
-
when load_format.DOC
|
|
32
|
-
puts "Microsoft Word 97-2003 document."
|
|
33
|
-
when load_format.DOT
|
|
34
|
-
puts "Microsoft Word 97-2003 template."
|
|
35
|
-
when load_format.DOCX
|
|
36
|
-
puts "Office Open XML WordprocessingML Macro-Free Document."
|
|
37
|
-
when load_format.DOCM
|
|
38
|
-
puts "Office Open XML WordprocessingML Macro-Enabled Document."
|
|
39
|
-
when load_format.DOTX
|
|
40
|
-
puts "Office Open XML WordprocessingML Macro-Free Template."
|
|
41
|
-
when load_format.DOTM
|
|
42
|
-
puts "Office Open XML WordprocessingML Macro-Enabled Template."
|
|
43
|
-
when load_format.FLAT_OPC
|
|
44
|
-
puts "Flat OPC document."
|
|
45
|
-
when load_format.RTF
|
|
46
|
-
puts "RTF format."
|
|
47
|
-
when load_format.WORD_ML
|
|
48
|
-
puts "Microsoft Word 2003 WordprocessingML format."
|
|
49
|
-
when load_format.HTML
|
|
50
|
-
puts "HTML format."
|
|
51
|
-
when load_format.MHTML
|
|
52
|
-
puts "MHTML (Web archive) format."
|
|
53
|
-
when load_format.ODT
|
|
54
|
-
puts "OpenDocument Text."
|
|
55
|
-
when load_format.OTT
|
|
56
|
-
puts "OpenDocument Text Template."
|
|
57
|
-
when load_format.DOC_PRE_WORD_97
|
|
58
|
-
puts "MS Word 6 or Word 95 format."
|
|
59
|
-
else load_format.UNKNOWN
|
|
60
|
-
puts "Unknown format."
|
|
61
|
-
end
|
|
62
|
-
|
|
63
|
-
dest_file_obj = Rjb::import("java.io.File").new(@supported_dir + name_only)
|
|
64
|
-
dest_File = dest_file_obj.getPath()
|
|
65
|
-
FileUtils.cp(file_name, dest_File)
|
|
66
|
-
end
|
|
67
|
-
end
|
|
68
|
-
|
|
69
|
-
end
|
|
70
|
-
end
|
|
1
|
+
require 'fileutils'
|
|
2
|
+
module Asposewordsjavaforruby
|
|
3
|
+
module CheckFormat
|
|
4
|
+
def initialize()
|
|
5
|
+
# The path to the documents directory.
|
|
6
|
+
data_dir = File.dirname(File.dirname(File.dirname(__FILE__))) + '/data/'
|
|
7
|
+
|
|
8
|
+
@supported_dir = data_dir + 'OutSupported/'
|
|
9
|
+
file = Rjb::import("java.io.File").new(data_dir + 'joiningandappending/')
|
|
10
|
+
|
|
11
|
+
check_fromat(file)
|
|
12
|
+
end
|
|
13
|
+
|
|
14
|
+
def check_fromat(file)
|
|
15
|
+
files_list = file.listFiles()
|
|
16
|
+
load_format = Rjb::import('com.aspose.words.LoadFormat')
|
|
17
|
+
|
|
18
|
+
files_list.each do |file|
|
|
19
|
+
if(file.isDirectory()) then
|
|
20
|
+
next
|
|
21
|
+
end
|
|
22
|
+
|
|
23
|
+
name_only = file.getName()
|
|
24
|
+
puts name_only
|
|
25
|
+
file_name = file.getPath()
|
|
26
|
+
puts file_name
|
|
27
|
+
|
|
28
|
+
info_obj = Rjb::import('com.aspose.words.FileFormatUtil')
|
|
29
|
+
info = info_obj.detectFileFormat(file_name)
|
|
30
|
+
case info.getLoadFormat()
|
|
31
|
+
when load_format.DOC
|
|
32
|
+
puts "Microsoft Word 97-2003 document."
|
|
33
|
+
when load_format.DOT
|
|
34
|
+
puts "Microsoft Word 97-2003 template."
|
|
35
|
+
when load_format.DOCX
|
|
36
|
+
puts "Office Open XML WordprocessingML Macro-Free Document."
|
|
37
|
+
when load_format.DOCM
|
|
38
|
+
puts "Office Open XML WordprocessingML Macro-Enabled Document."
|
|
39
|
+
when load_format.DOTX
|
|
40
|
+
puts "Office Open XML WordprocessingML Macro-Free Template."
|
|
41
|
+
when load_format.DOTM
|
|
42
|
+
puts "Office Open XML WordprocessingML Macro-Enabled Template."
|
|
43
|
+
when load_format.FLAT_OPC
|
|
44
|
+
puts "Flat OPC document."
|
|
45
|
+
when load_format.RTF
|
|
46
|
+
puts "RTF format."
|
|
47
|
+
when load_format.WORD_ML
|
|
48
|
+
puts "Microsoft Word 2003 WordprocessingML format."
|
|
49
|
+
when load_format.HTML
|
|
50
|
+
puts "HTML format."
|
|
51
|
+
when load_format.MHTML
|
|
52
|
+
puts "MHTML (Web archive) format."
|
|
53
|
+
when load_format.ODT
|
|
54
|
+
puts "OpenDocument Text."
|
|
55
|
+
when load_format.OTT
|
|
56
|
+
puts "OpenDocument Text Template."
|
|
57
|
+
when load_format.DOC_PRE_WORD_97
|
|
58
|
+
puts "MS Word 6 or Word 95 format."
|
|
59
|
+
else load_format.UNKNOWN
|
|
60
|
+
puts "Unknown format."
|
|
61
|
+
end
|
|
62
|
+
|
|
63
|
+
dest_file_obj = Rjb::import("java.io.File").new(@supported_dir + name_only)
|
|
64
|
+
dest_File = dest_file_obj.getPath()
|
|
65
|
+
FileUtils.cp(file_name, dest_File)
|
|
66
|
+
end
|
|
67
|
+
end
|
|
68
|
+
|
|
69
|
+
end
|
|
70
|
+
end
|
|
@@ -1,53 +1,53 @@
|
|
|
1
|
-
module Asposewordsjavaforruby
|
|
2
|
-
module CompressImages
|
|
3
|
-
def initialize()
|
|
4
|
-
# The path to the documents directory.
|
|
5
|
-
@data_dir = File.dirname(File.dirname(File.dirname(__FILE__))) + '/data/'
|
|
6
|
-
srcFileName = @data_dir + "TestCompressImages.docx"
|
|
7
|
-
|
|
8
|
-
doc = Rjb::import('com.aspose.words.Document').new(@data_dir + "TestCompressImages.docx")
|
|
9
|
-
|
|
10
|
-
# Demonstrate autofitting a table to the window.
|
|
11
|
-
compress_images(doc, srcFileName)
|
|
12
|
-
end
|
|
13
|
-
|
|
14
|
-
def compress_images(doc, srcFileName)
|
|
15
|
-
messageFormat = Rjb::import("java.text.MessageFormat")
|
|
16
|
-
file_size = get_file_size(srcFileName)
|
|
17
|
-
|
|
18
|
-
# 220ppi Print - said to be excellent on most printers and screens.
|
|
19
|
-
# 150ppi Screen - said to be good for web pages and projectors.
|
|
20
|
-
# 96ppi Email - said to be good for minimal document size and sharing.
|
|
21
|
-
desiredPpi = 150
|
|
22
|
-
# In Java this seems to be a good compression / quality setting.
|
|
23
|
-
jpegQuality = 90
|
|
24
|
-
|
|
25
|
-
# Resample images to desired ppi and save.
|
|
26
|
-
resampler = Rjb::import("com.aspose.words.Resampler").new
|
|
27
|
-
count = resampler.resample(doc, desiredPpi, jpegQuality)
|
|
28
|
-
puts MessageFormat.format("Resampled {0} images.", count)
|
|
29
|
-
if (count != 1) then
|
|
30
|
-
puts "We expected to have only 1 image resampled in this test document!"
|
|
31
|
-
end
|
|
32
|
-
dstFileName = @data_dir + "TestCompressImages Out.docx"
|
|
33
|
-
doc.save(dstFileName)
|
|
34
|
-
puts messageFormat.format("Saving {0}. Size {1}.", dstFileName, get_file_size(dstFileName))
|
|
35
|
-
|
|
36
|
-
# Verify that the first image was compressed by checking the new Ppi.
|
|
37
|
-
dst_doc = Rjb::import("com.aspose.words.Document").new(dstFileName)
|
|
38
|
-
nodeType = Rjb::import("com.aspose.words.NodeType")
|
|
39
|
-
shape = dst_doc.getChild(nodeType.DRAWING_ML, 0, true)
|
|
40
|
-
convertUtil = Rjb::import("com.aspose.words.ConvertUtil")
|
|
41
|
-
imagePpi = shape.getImageData().getImageSize().getWidthPixels() / convertUtil.pointToInch(shape.getSize().getX())
|
|
42
|
-
if (imagePpi < 150) then
|
|
43
|
-
puts "Image was not resampled successfully."
|
|
44
|
-
end
|
|
45
|
-
end
|
|
46
|
-
|
|
47
|
-
def get_file_size(file_name)
|
|
48
|
-
file = Rjb::import("java.io.File").new(file_name)
|
|
49
|
-
return file.length()
|
|
50
|
-
end
|
|
51
|
-
|
|
52
|
-
end
|
|
53
|
-
end
|
|
1
|
+
module Asposewordsjavaforruby
|
|
2
|
+
module CompressImages
|
|
3
|
+
def initialize()
|
|
4
|
+
# The path to the documents directory.
|
|
5
|
+
@data_dir = File.dirname(File.dirname(File.dirname(__FILE__))) + '/data/'
|
|
6
|
+
srcFileName = @data_dir + "TestCompressImages.docx"
|
|
7
|
+
|
|
8
|
+
doc = Rjb::import('com.aspose.words.Document').new(@data_dir + "TestCompressImages.docx")
|
|
9
|
+
|
|
10
|
+
# Demonstrate autofitting a table to the window.
|
|
11
|
+
compress_images(doc, srcFileName)
|
|
12
|
+
end
|
|
13
|
+
|
|
14
|
+
def compress_images(doc, srcFileName)
|
|
15
|
+
messageFormat = Rjb::import("java.text.MessageFormat")
|
|
16
|
+
file_size = get_file_size(srcFileName)
|
|
17
|
+
|
|
18
|
+
# 220ppi Print - said to be excellent on most printers and screens.
|
|
19
|
+
# 150ppi Screen - said to be good for web pages and projectors.
|
|
20
|
+
# 96ppi Email - said to be good for minimal document size and sharing.
|
|
21
|
+
desiredPpi = 150
|
|
22
|
+
# In Java this seems to be a good compression / quality setting.
|
|
23
|
+
jpegQuality = 90
|
|
24
|
+
|
|
25
|
+
# Resample images to desired ppi and save.
|
|
26
|
+
resampler = Rjb::import("com.aspose.words.Resampler").new
|
|
27
|
+
count = resampler.resample(doc, desiredPpi, jpegQuality)
|
|
28
|
+
puts MessageFormat.format("Resampled {0} images.", count)
|
|
29
|
+
if (count != 1) then
|
|
30
|
+
puts "We expected to have only 1 image resampled in this test document!"
|
|
31
|
+
end
|
|
32
|
+
dstFileName = @data_dir + "TestCompressImages Out.docx"
|
|
33
|
+
doc.save(dstFileName)
|
|
34
|
+
puts messageFormat.format("Saving {0}. Size {1}.", dstFileName, get_file_size(dstFileName))
|
|
35
|
+
|
|
36
|
+
# Verify that the first image was compressed by checking the new Ppi.
|
|
37
|
+
dst_doc = Rjb::import("com.aspose.words.Document").new(dstFileName)
|
|
38
|
+
nodeType = Rjb::import("com.aspose.words.NodeType")
|
|
39
|
+
shape = dst_doc.getChild(nodeType.DRAWING_ML, 0, true)
|
|
40
|
+
convertUtil = Rjb::import("com.aspose.words.ConvertUtil")
|
|
41
|
+
imagePpi = shape.getImageData().getImageSize().getWidthPixels() / convertUtil.pointToInch(shape.getSize().getX())
|
|
42
|
+
if (imagePpi < 150) then
|
|
43
|
+
puts "Image was not resampled successfully."
|
|
44
|
+
end
|
|
45
|
+
end
|
|
46
|
+
|
|
47
|
+
def get_file_size(file_name)
|
|
48
|
+
file = Rjb::import("java.io.File").new(file_name)
|
|
49
|
+
return file.length()
|
|
50
|
+
end
|
|
51
|
+
|
|
52
|
+
end
|
|
53
|
+
end
|
|
@@ -1,15 +1,15 @@
|
|
|
1
|
-
module Asposewordsjavaforruby
|
|
2
|
-
module Doc2Pdf
|
|
3
|
-
|
|
4
|
-
def doc_to_pdf()
|
|
5
|
-
data_dir = File.dirname(File.dirname(File.dirname(__FILE__))) + '/data/'
|
|
6
|
-
|
|
7
|
-
# Open document.
|
|
8
|
-
document = Rjb::import('com.aspose.words.Document').new(data_dir + "Template.doc")
|
|
9
|
-
|
|
10
|
-
# Save the document in PDF format.
|
|
11
|
-
document.save(data_dir + "Doc2PdfSave Out.pdf")
|
|
12
|
-
end
|
|
13
|
-
|
|
14
|
-
end
|
|
15
|
-
end
|
|
1
|
+
module Asposewordsjavaforruby
|
|
2
|
+
module Doc2Pdf
|
|
3
|
+
|
|
4
|
+
def doc_to_pdf()
|
|
5
|
+
data_dir = File.dirname(File.dirname(File.dirname(__FILE__))) + '/data/'
|
|
6
|
+
|
|
7
|
+
# Open document.
|
|
8
|
+
document = Rjb::import('com.aspose.words.Document').new(data_dir + "Template.doc")
|
|
9
|
+
|
|
10
|
+
# Save the document in PDF format.
|
|
11
|
+
document.save(data_dir + "Doc2PdfSave Out.pdf")
|
|
12
|
+
end
|
|
13
|
+
|
|
14
|
+
end
|
|
15
|
+
end
|
|
@@ -1,26 +1,26 @@
|
|
|
1
|
-
module Asposewordsjavaforruby
|
|
2
|
-
module DocToHTML
|
|
3
|
-
def initialize()
|
|
4
|
-
# The path to the documents directory.
|
|
5
|
-
data_dir = File.dirname(File.dirname(File.dirname(__FILE__))) + '/data/'
|
|
6
|
-
|
|
7
|
-
# Open the document.
|
|
8
|
-
doc = Rjb::import('com.aspose.words.Document').new(data_dir + "TestFile.doc")
|
|
9
|
-
|
|
10
|
-
#HtmlSaveOptions options = new HtmlSaveOptions();
|
|
11
|
-
options = Rjb::import('com.aspose.words.HtmlSaveOptions').new
|
|
12
|
-
|
|
13
|
-
# HtmlSaveOptions.ExportRoundtripInformation property specifies
|
|
14
|
-
# whether to write the roundtrip information when saving to HTML, MHTML or EPUB.
|
|
15
|
-
# Default value is true for HTML and false for MHTML and EPUB.
|
|
16
|
-
options.setExportRoundtripInformation(true)
|
|
17
|
-
doc.save(data_dir + "ExportRoundtripInformation Out.html", options)
|
|
18
|
-
|
|
19
|
-
doc = Rjb::import('com.aspose.words.Document').new(data_dir + "ExportRoundtripInformation Out.html")
|
|
20
|
-
|
|
21
|
-
# Save the document Docx file format
|
|
22
|
-
save_format = Rjb::import('com.aspose.words.SaveFormat')
|
|
23
|
-
doc.save(data_dir + "Out.docx", save_format.DOCX)
|
|
24
|
-
end
|
|
25
|
-
end
|
|
26
|
-
end
|
|
1
|
+
module Asposewordsjavaforruby
|
|
2
|
+
module DocToHTML
|
|
3
|
+
def initialize()
|
|
4
|
+
# The path to the documents directory.
|
|
5
|
+
data_dir = File.dirname(File.dirname(File.dirname(__FILE__))) + '/data/'
|
|
6
|
+
|
|
7
|
+
# Open the document.
|
|
8
|
+
doc = Rjb::import('com.aspose.words.Document').new(data_dir + "TestFile.doc")
|
|
9
|
+
|
|
10
|
+
#HtmlSaveOptions options = new HtmlSaveOptions();
|
|
11
|
+
options = Rjb::import('com.aspose.words.HtmlSaveOptions').new
|
|
12
|
+
|
|
13
|
+
# HtmlSaveOptions.ExportRoundtripInformation property specifies
|
|
14
|
+
# whether to write the roundtrip information when saving to HTML, MHTML or EPUB.
|
|
15
|
+
# Default value is true for HTML and false for MHTML and EPUB.
|
|
16
|
+
options.setExportRoundtripInformation(true)
|
|
17
|
+
doc.save(data_dir + "ExportRoundtripInformation Out.html", options)
|
|
18
|
+
|
|
19
|
+
doc = Rjb::import('com.aspose.words.Document').new(data_dir + "ExportRoundtripInformation Out.html")
|
|
20
|
+
|
|
21
|
+
# Save the document Docx file format
|
|
22
|
+
save_format = Rjb::import('com.aspose.words.SaveFormat')
|
|
23
|
+
doc.save(data_dir + "Out.docx", save_format.DOCX)
|
|
24
|
+
end
|
|
25
|
+
end
|
|
26
|
+
end
|
|
@@ -1,395 +1,395 @@
|
|
|
1
|
-
module Asposewordsjavaforruby
|
|
2
|
-
module ExtractContent
|
|
3
|
-
def initialize()
|
|
4
|
-
# The path to the documents directory.
|
|
5
|
-
@data_dir = File.dirname(File.dirname(File.dirname(__FILE__))) + '/data/document/'
|
|
6
|
-
|
|
7
|
-
# Open the document.
|
|
8
|
-
doc = Rjb::import('com.aspose.words.Document').new(@data_dir + "TestFile.doc")
|
|
9
|
-
|
|
10
|
-
extract_content_between_paragraphs(doc)
|
|
11
|
-
extract_content_between_block_level_nodes(doc)
|
|
12
|
-
extract_content_between_paragraph_styles(doc)
|
|
13
|
-
extract_content_between_runs(doc)
|
|
14
|
-
extract_content_using_field(doc)
|
|
15
|
-
extract_content_between_bookmark(doc)
|
|
16
|
-
extract_content_between_comment_range(doc)
|
|
17
|
-
end
|
|
18
|
-
|
|
19
|
-
def extract_content_between_paragraphs(doc)
|
|
20
|
-
# Gather the nodes. The GetChild method uses 0-based index
|
|
21
|
-
node_type = Rjb::import("com.aspose.words.NodeType")
|
|
22
|
-
start_para = doc.getFirstSection().getChild(node_type.PARAGRAPH, 6, true)
|
|
23
|
-
end_para = doc.getFirstSection().getChild(node_type.PARAGRAPH, 10, true)
|
|
24
|
-
|
|
25
|
-
# Extract the content between these nodes in the document. Include these markers in the extraction.
|
|
26
|
-
extracted_nodes = extract_contents(start_para, end_para, true)
|
|
27
|
-
|
|
28
|
-
# Insert the content into a new separate document and save it to disk.
|
|
29
|
-
dst_doc = generate_document(doc, extracted_nodes)
|
|
30
|
-
dst_doc.save(@data_dir + "TestFile.Paragraphs Out.doc")
|
|
31
|
-
end
|
|
32
|
-
|
|
33
|
-
def extract_content_between_block_level_nodes(doc)
|
|
34
|
-
# Gather the nodes. The GetChild method uses 0-based index
|
|
35
|
-
node_type = Rjb::import("com.aspose.words.NodeType")
|
|
36
|
-
start_para = doc.getLastSection().getChild(node_type.PARAGRAPH, 2, true)
|
|
37
|
-
end_table = doc.getLastSection().getChild(node_type.TABLE, 0, true)
|
|
38
|
-
|
|
39
|
-
# Extract the content between these nodes in the document. Include these markers in the extraction.
|
|
40
|
-
extracted_nodes = extract_contents(start_para, end_table, true)
|
|
41
|
-
|
|
42
|
-
# Lets reverse the array to make inserting the content back into the document easier.
|
|
43
|
-
collections = Rjb::import("java.util.Collections")
|
|
44
|
-
collections.reverse(extracted_nodes)
|
|
45
|
-
|
|
46
|
-
while extracted_nodes.size() > 0 do
|
|
47
|
-
# Insert the last node from the reversed list
|
|
48
|
-
end_table.getParentNode().insertAfter(extracted_nodes.get(0), end_table)
|
|
49
|
-
# Remove this node from the list after insertion.
|
|
50
|
-
extracted_nodes.remove(0)
|
|
51
|
-
end
|
|
52
|
-
|
|
53
|
-
# Save the generated document to disk.
|
|
54
|
-
doc.save(@data_dir + "TestFile.DuplicatedContent Out.doc")
|
|
55
|
-
end
|
|
56
|
-
|
|
57
|
-
def extract_content_between_paragraph_styles(doc)
|
|
58
|
-
# Gather a list of the paragraphs using the respective heading styles.
|
|
59
|
-
paras_style_heading1 = paragraphs_by_style_name(doc, "Heading 1")
|
|
60
|
-
paras_style_heading3 = paragraphs_by_style_name(doc, "Heading 3")
|
|
61
|
-
|
|
62
|
-
# Use the first instance of the paragraphs with those styles.
|
|
63
|
-
start_para1 = paras_style_heading1.get(0)
|
|
64
|
-
end_para1 = paras_style_heading3.get(0)
|
|
65
|
-
|
|
66
|
-
# Extract the content between these nodes in the document. Don't include these markers in the extraction.
|
|
67
|
-
extracted_nodes = extract_contents(start_para1, end_para1, false)
|
|
68
|
-
|
|
69
|
-
# Insert the content into a new separate document and save it to disk.
|
|
70
|
-
dst_doc = generate_document(doc, extracted_nodes)
|
|
71
|
-
dst_doc.save(@data_dir + "TestFile.Styles Out.doc")
|
|
72
|
-
end
|
|
73
|
-
|
|
74
|
-
def extract_content_between_runs(doc)
|
|
75
|
-
# Retrieve a paragraph from the first section.
|
|
76
|
-
node_type = Rjb::import("com.aspose.words.NodeType")
|
|
77
|
-
para = doc.getChild(node_type.PARAGRAPH, 7, true)
|
|
78
|
-
|
|
79
|
-
# Use some runs for extraction.
|
|
80
|
-
start_run = para.getRuns().get(1)
|
|
81
|
-
end_run = para.getRuns().get(4)
|
|
82
|
-
|
|
83
|
-
# Extract the content between these nodes in the document. Include these markers in the extraction.
|
|
84
|
-
extracted_nodes = extract_contents(start_run, end_run, true)
|
|
85
|
-
|
|
86
|
-
# Get the node from the list. There should only be one paragraph returned in the list.
|
|
87
|
-
node = extracted_nodes.get(0)
|
|
88
|
-
|
|
89
|
-
# Print the text of this node to the console.
|
|
90
|
-
save_format = Rjb::import("com.aspose.words.SaveFormat")
|
|
91
|
-
puts node.toString(save_format.TEXT)
|
|
92
|
-
end
|
|
93
|
-
|
|
94
|
-
def extract_content_using_field(doc)
|
|
95
|
-
# Use a document builder to retrieve the field start of a merge field.
|
|
96
|
-
builder = Rjb::import("com.aspose.words.DocumentBuilder").new(doc)
|
|
97
|
-
|
|
98
|
-
# Pass the first boolean parameter to get the DocumentBuilder to move to the FieldStart of the field.
|
|
99
|
-
# We could also get FieldStarts of a field using GetChildNode method as in the other examples.
|
|
100
|
-
builder.moveToMergeField("Fullname", false, false)
|
|
101
|
-
|
|
102
|
-
#/ The builder cursor should be positioned at the start of the field.
|
|
103
|
-
node_type = Rjb::import("com.aspose.words.NodeType")
|
|
104
|
-
start_field = builder.getCurrentNode()
|
|
105
|
-
end_para = doc.getFirstSection().getChild(node_type.PARAGRAPH, 5, true)
|
|
106
|
-
|
|
107
|
-
# Extract the content between these nodes in the document. Don't include these markers in the extraction.
|
|
108
|
-
extracted_nodes = extract_contents(start_field, end_para, false)
|
|
109
|
-
|
|
110
|
-
# Insert the content into a new separate document and save it to disk.
|
|
111
|
-
dst_doc = generate_document(doc, extracted_nodes)
|
|
112
|
-
dst_doc.save(@data_dir + "TestFile.Fields Out.doc")
|
|
113
|
-
end
|
|
114
|
-
|
|
115
|
-
def extract_content_between_bookmark(doc)
|
|
116
|
-
# Retrieve the bookmark from the document.
|
|
117
|
-
bookmark = doc.getRange().getBookmarks().get("Bookmark1")
|
|
118
|
-
|
|
119
|
-
# We use the BookmarkStart and BookmarkEnd nodes as markers.
|
|
120
|
-
bookmark_start = bookmark.getBookmarkStart()
|
|
121
|
-
bookmark_end = bookmark.getBookmarkEnd()
|
|
122
|
-
|
|
123
|
-
# Firstly extract the content between these nodes including the bookmark.
|
|
124
|
-
extracted_nodes_inclusive = extract_contents(bookmark_start, bookmark_end, true)
|
|
125
|
-
dst_doc = generate_document(doc, extracted_nodes_inclusive)
|
|
126
|
-
dst_doc.save(@data_dir + "TestFile.BookmarkInclusive Out.doc")
|
|
127
|
-
|
|
128
|
-
# Secondly extract the content between these nodes this time without including the bookmark.
|
|
129
|
-
extracted_nodes_exclusive = extract_contents(bookmark_start, bookmark_end, false)
|
|
130
|
-
dst_doc = generate_document(doc, extracted_nodes_exclusive)
|
|
131
|
-
dst_doc.save(@data_dir + "TestFile.BookmarkExclusive Out.doc")
|
|
132
|
-
end
|
|
133
|
-
|
|
134
|
-
def extract_content_between_comment_range(doc)
|
|
135
|
-
# This is a quick way of getting both comment nodes.
|
|
136
|
-
# Your code should have a proper method of retrieving each corresponding start and end node.
|
|
137
|
-
node_type = Rjb::import("com.aspose.words.NodeType")
|
|
138
|
-
comment_start = doc.getChild(node_type.COMMENT_RANGE_START, 0, true)
|
|
139
|
-
comment_end = doc.getChild(node_type.COMMENT_RANGE_END, 0, true)
|
|
140
|
-
|
|
141
|
-
# Firstly extract the content between these nodes including the bookmark.
|
|
142
|
-
extracted_nodes_inclusive = extract_contents(comment_start, comment_end, true)
|
|
143
|
-
dst_doc = generate_document(doc, extracted_nodes_inclusive)
|
|
144
|
-
dst_doc.save(@data_dir + "TestFile.CommentInclusive Out.doc")
|
|
145
|
-
|
|
146
|
-
# Secondly extract the content between these nodes this time without including the bookmark.
|
|
147
|
-
extracted_nodes_exclusive = extract_contents(comment_start, comment_end, false)
|
|
148
|
-
dst_doc = generate_document(doc, extracted_nodes_exclusive)
|
|
149
|
-
dst_doc.save(@data_dir + "TestFile.CommentExclusive Out.doc")
|
|
150
|
-
end
|
|
151
|
-
|
|
152
|
-
=begin
|
|
153
|
-
This is a method which extracts blocks of content from a document between specified nodes.
|
|
154
|
-
|
|
155
|
-
Extracts a range of nodes from a document found between specified markers and returns a copy of those nodes. Content can be extracted
|
|
156
|
-
between inline nodes, block level nodes, and also special nodes such as Comment or Boomarks. Any combination of different marker types can used.
|
|
157
|
-
|
|
158
|
-
@param string startNode The node which defines where to start the extraction from the document. This node can be block or inline level of a body.
|
|
159
|
-
@param string endNode The node which defines where to stop the extraction from the document. This node can be block or inline level of body.
|
|
160
|
-
@param boolean isInclusive Should the marker nodes be included.
|
|
161
|
-
=end
|
|
162
|
-
def extract_contents(startNode, endNode, isInclusive)
|
|
163
|
-
# First check that the nodes passed to this method are valid for use.
|
|
164
|
-
verify_parameter_nodes(startNode, endNode)
|
|
165
|
-
|
|
166
|
-
# Create a list to store the extracted nodes.
|
|
167
|
-
nodes = Rjb::import("java.util.ArrayList").new
|
|
168
|
-
|
|
169
|
-
# Keep a record of the original nodes passed to this method so we can split marker nodes if needed.
|
|
170
|
-
originalStartNode = startNode
|
|
171
|
-
originalEndNode = endNode
|
|
172
|
-
|
|
173
|
-
# Extract content based on block level nodes (paragraphs and tables). Traverse through parent nodes to find them.
|
|
174
|
-
# We will split the content of first and last nodes depending if the marker nodes are inline
|
|
175
|
-
node_type = Rjb::import("com.aspose.words.NodeType")
|
|
176
|
-
|
|
177
|
-
while (startNode.getParentNode().getNodeType() != node_type.BODY) do
|
|
178
|
-
startNode = startNode.getParentNode()
|
|
179
|
-
end
|
|
180
|
-
|
|
181
|
-
while (endNode.getParentNode().getNodeType() != node_type.BODY) do
|
|
182
|
-
endNode = endNode.getParentNode()
|
|
183
|
-
end
|
|
184
|
-
|
|
185
|
-
isExtracting = true
|
|
186
|
-
isStartingNode = true
|
|
187
|
-
isEndingNode = ''
|
|
188
|
-
#The current node we are extracting from the document.
|
|
189
|
-
currNode = startNode
|
|
190
|
-
|
|
191
|
-
#Begin extracting content. Process all block level nodes and specifically split the first and last nodes when needed so paragraph formatting is retained.
|
|
192
|
-
# Method is little more complex than a regular extractor as we need to factor in extracting using inline nodes, fields, bookmarks etc as to make it really useful.
|
|
193
|
-
while (isExtracting) do
|
|
194
|
-
# Clone the current node and its children to obtain a copy.
|
|
195
|
-
cloneNode = currNode.deepClone(true)
|
|
196
|
-
isEndingNode = currNode.equals(endNode)
|
|
197
|
-
|
|
198
|
-
if (isStartingNode || isEndingNode) then
|
|
199
|
-
# We need to process each marker separately so pass it off to a separate method instead.
|
|
200
|
-
if (isStartingNode) then
|
|
201
|
-
process_marker(cloneNode, nodes, originalStartNode, isInclusive, isStartingNode, isEndingNode)
|
|
202
|
-
isStartingNode = false
|
|
203
|
-
end
|
|
204
|
-
# Conditional needs to be separate as the block level start and end markers maybe the same node.
|
|
205
|
-
if (isEndingNode) then
|
|
206
|
-
process_marker(cloneNode, nodes, originalEndNode, isInclusive, isStartingNode, isEndingNode)
|
|
207
|
-
isExtracting = false
|
|
208
|
-
end
|
|
209
|
-
else
|
|
210
|
-
# Node is not a start or end marker, simply add the copy to the list.
|
|
211
|
-
nodes.add(cloneNode)
|
|
212
|
-
end
|
|
213
|
-
|
|
214
|
-
# Move to the next node and extract it. If next node is null that means the rest of the content is found in a different section.
|
|
215
|
-
#if (currNode.getNextSibling() == null && isExtracting) then
|
|
216
|
-
if ((currNode.getNextSibling()).nil? && isExtracting) then
|
|
217
|
-
# Move to the next section.
|
|
218
|
-
nodeType = Rjb::import("com.aspose.words.NodeType")
|
|
219
|
-
nextSection = currNode.getAncestor(nodeType.SECTION).getNextSibling()
|
|
220
|
-
currNode = nextSection.getBody().getFirstChild()
|
|
221
|
-
else
|
|
222
|
-
# Move to the next node in the body.
|
|
223
|
-
currNode = currNode.getNextSibling()
|
|
224
|
-
end
|
|
225
|
-
end
|
|
226
|
-
# Return the nodes between the node markers.
|
|
227
|
-
nodes
|
|
228
|
-
end
|
|
229
|
-
|
|
230
|
-
=begin
|
|
231
|
-
Checks the input parameters are correct and can be used. Throws an exception if there is any problem.
|
|
232
|
-
=end
|
|
233
|
-
def verify_parameter_nodes(startNode, endNode)
|
|
234
|
-
# The order in which these checks are done is important.
|
|
235
|
-
raise 'Start node cannot be null' if startNode.nil?
|
|
236
|
-
raise 'End node cannot be null' if endNode.nil?
|
|
237
|
-
raise "Start node and end node must belong to the same document" if (startNode.getDocument() == endNode.getDocument())
|
|
238
|
-
|
|
239
|
-
nodeType = Rjb::import("com.aspose.words.NodeType")
|
|
240
|
-
#raise "Start node and end node must be a child or descendant of a body" if (startNode.getAncestor(nodeType.BODY) == '' || endNode.getAncestor(nodeType.BODY) == '')
|
|
241
|
-
raise "Start node and end node must be a child or descendant of a body" if (startNode.getAncestor(nodeType.BODY).nil? || endNode.getAncestor(nodeType.BODY).nil?)
|
|
242
|
-
|
|
243
|
-
# Check the end node is after the start node in the DOM tree
|
|
244
|
-
# First check if they are in different sections, then if they're not check their position in the body of the same section they are in.
|
|
245
|
-
startSection = startNode.getAncestor(nodeType.SECTION)
|
|
246
|
-
endSection = endNode.getAncestor(nodeType.SECTION)
|
|
247
|
-
startIndex = startSection.getParentNode().indexOf(startSection)
|
|
248
|
-
endIndex = endSection.getParentNode().indexOf(endSection)
|
|
249
|
-
|
|
250
|
-
if (startIndex == endIndex) then
|
|
251
|
-
raise "The end node must be after the start node in the body" if (startSection.getBody().indexOf(startNode) > endSection.getBody().indexOf(endNode))
|
|
252
|
-
elsif (startIndex > endIndex) then
|
|
253
|
-
raise "The section of end node must be after the section start node"
|
|
254
|
-
end
|
|
255
|
-
end
|
|
256
|
-
|
|
257
|
-
def generate_document(src_doc, nodes)
|
|
258
|
-
# Create a blank document.
|
|
259
|
-
dst_doc = Rjb::import("com.aspose.words.Document").new
|
|
260
|
-
|
|
261
|
-
# Remove the first paragraph from the empty document.
|
|
262
|
-
dst_doc.getFirstSection().getBody().removeAllChildren()
|
|
263
|
-
|
|
264
|
-
# Import each node from the list into the new document. Keep the original formatting of the node.
|
|
265
|
-
import_format_mode = Rjb::import("com.aspose.words.ImportFormatMode")
|
|
266
|
-
importer = Rjb::import("com.aspose.words.NodeImporter").new(src_doc, dst_doc, import_format_mode.KEEP_SOURCE_FORMATTING)
|
|
267
|
-
|
|
268
|
-
i = 0
|
|
269
|
-
while i < nodes.size
|
|
270
|
-
node = nodes.get(i)
|
|
271
|
-
import_node = importer.importNode(node, true)
|
|
272
|
-
dst_doc.getFirstSection().getBody().appendChild(import_node)
|
|
273
|
-
i +=1
|
|
274
|
-
end
|
|
275
|
-
|
|
276
|
-
# Return the generated document.
|
|
277
|
-
dst_doc
|
|
278
|
-
end
|
|
279
|
-
|
|
280
|
-
def process_marker(cloneNode, nodes, node, isInclusive, isStartMarker, isEndMarker)
|
|
281
|
-
# If we are dealing with a block level node just see if it should be included and add it to the list.
|
|
282
|
-
if (!is_inline(node)) then
|
|
283
|
-
# Don't add the node twice if the markers are the same node
|
|
284
|
-
if(!(isStartMarker && isEndMarker)) then
|
|
285
|
-
if (isInclusive) then
|
|
286
|
-
nodes.add(cloneNode)
|
|
287
|
-
end
|
|
288
|
-
end
|
|
289
|
-
return
|
|
290
|
-
end
|
|
291
|
-
|
|
292
|
-
# If a marker is a FieldStart node check if it's to be included or not.
|
|
293
|
-
# We assume for simplicity that the FieldStart and FieldEnd appear in the same paragraph.
|
|
294
|
-
nodeType = Rjb::import("com.aspose.words.NodeType")
|
|
295
|
-
if (node.getNodeType() == nodeType.FIELD_START) then
|
|
296
|
-
# If the marker is a start node and is not be included then skip to the end of the field.
|
|
297
|
-
# If the marker is an end node and it is to be included then move to the end field so the field will not be removed.
|
|
298
|
-
#if ((isStartMarker && !isInclusive) || (!isStartMarker && isInclusive)) then
|
|
299
|
-
if ((isStartMarker && isInclusive.nil?) || (!isStartMarker && isInclusive)) then
|
|
300
|
-
#while (node.getNextSibling() != null && node.getNodeType() != nodeType.FIELD_END) do
|
|
301
|
-
while (node.getNextSibling().nil? && (node.getNodeType() != nodeType.FIELD_END)) do
|
|
302
|
-
node = node.getNextSibling()
|
|
303
|
-
end
|
|
304
|
-
end
|
|
305
|
-
end
|
|
306
|
-
|
|
307
|
-
# If either marker is part of a comment then to include the comment itself we need to move the pointer forward to the Comment
|
|
308
|
-
# node found after the CommentRangeEnd node.
|
|
309
|
-
if (node.getNodeType() == nodeType.COMMENT_RANGE_END) then
|
|
310
|
-
while (node.getNextSibling().nil? && (node.getNodeType() != nodeType.COMMENT)) do
|
|
311
|
-
node = node.getNextSibling()
|
|
312
|
-
end
|
|
313
|
-
end
|
|
314
|
-
|
|
315
|
-
# Find the corresponding node in our cloned node by index and return it.
|
|
316
|
-
# If the start and end node are the same some child nodes might already have been removed. Subtract the
|
|
317
|
-
# difference to get the right index.
|
|
318
|
-
indexDiff = (node.getParentNode().getChildNodes().getCount() - cloneNode.getChildNodes().getCount())
|
|
319
|
-
|
|
320
|
-
# Child node count identical.
|
|
321
|
-
if (indexDiff == 0) then
|
|
322
|
-
node = cloneNode.getChildNodes().get(node.getParentNode().indexOf(node))
|
|
323
|
-
else
|
|
324
|
-
node = cloneNode.getChildNodes().get(node.getParentNode().indexOf(node) - indexDiff)
|
|
325
|
-
end
|
|
326
|
-
|
|
327
|
-
# Remove the nodes up to/from the marker.
|
|
328
|
-
isSkip = ''
|
|
329
|
-
isProcessing = true
|
|
330
|
-
isRemoving = isStartMarker
|
|
331
|
-
nextNode = cloneNode.getFirstChild()
|
|
332
|
-
#while (isProcessing && nextNode != null) do
|
|
333
|
-
unless (isProcessing && nextNode.nil?)
|
|
334
|
-
currentNode = nextNode
|
|
335
|
-
isSkip = false
|
|
336
|
-
if (currentNode == node) then
|
|
337
|
-
if (isStartMarker) then
|
|
338
|
-
isProcessing = false
|
|
339
|
-
if isInclusive then
|
|
340
|
-
isRemoving = false
|
|
341
|
-
end
|
|
342
|
-
else
|
|
343
|
-
isRemoving = true
|
|
344
|
-
if isInclusive then
|
|
345
|
-
isSkip = true
|
|
346
|
-
end
|
|
347
|
-
end
|
|
348
|
-
end
|
|
349
|
-
nextNode = nextNode.getNextSibling()
|
|
350
|
-
#if (isRemoving && !isSkip) then
|
|
351
|
-
if (isRemoving && isSkip==false) then
|
|
352
|
-
currentNode.remove()
|
|
353
|
-
end
|
|
354
|
-
end
|
|
355
|
-
|
|
356
|
-
# After processing the composite node may become empty. If it has don't include it.
|
|
357
|
-
if (!(isStartMarker && isEndMarker)) then
|
|
358
|
-
if cloneNode.hasChildNodes() then
|
|
359
|
-
nodes.add(cloneNode)
|
|
360
|
-
end
|
|
361
|
-
end
|
|
362
|
-
end
|
|
363
|
-
|
|
364
|
-
def is_inline(node)
|
|
365
|
-
# Test if the node is desendant of a Paragraph or Table node and also is not a paragraph or a table a paragraph inside a comment class which is decesant of a pararaph is possible.
|
|
366
|
-
node_type = Rjb::import("com.aspose.words.NodeType")
|
|
367
|
-
#return ((node.getAncestor(node_type.PARAGRAPH) != null) || (node.getAncestor(node_type.TABLE) != null) && !(node.getNodeType() == nodeType.PARAGRAPH) || (node.getNodeType() == nodeType.TABLE))
|
|
368
|
-
return ((node.getAncestor(node_type.PARAGRAPH).nil?) || (node.getAncestor(node_type.TABLE).nil?) && !(node.getNodeType() == node_type.PARAGRAPH) || (node.getNodeType() == node_type.TABLE))
|
|
369
|
-
end
|
|
370
|
-
|
|
371
|
-
def paragraphs_by_style_name(doc, style_name)
|
|
372
|
-
# Create an array to collect paragraphs of the specified style.
|
|
373
|
-
paragraphsWithStyle = Rjb::import("java.util.ArrayList").new
|
|
374
|
-
|
|
375
|
-
# Get all paragraphs from the document.
|
|
376
|
-
node_type = Rjb::import("com.aspose.words.NodeType")
|
|
377
|
-
paragraphs = doc.getChildNodes(node_type.PARAGRAPH, true)
|
|
378
|
-
paragraphs_count = paragraphs.getCount()
|
|
379
|
-
#paragraphs_count = java_values($paragraphs_count)
|
|
380
|
-
|
|
381
|
-
# Look through all paragraphs to find those with the specified style.
|
|
382
|
-
i = 0
|
|
383
|
-
while (i < paragraphs_count) do
|
|
384
|
-
paragraphs = doc.getChildNodes(node_type.PARAGRAPH, true)
|
|
385
|
-
paragraph = paragraphs.get(i)
|
|
386
|
-
if (paragraph.getParagraphFormat().getStyle().getName() == style_name) then
|
|
387
|
-
paragraphsWithStyle.add(paragraph)
|
|
388
|
-
end
|
|
389
|
-
i = i + 1
|
|
390
|
-
end
|
|
391
|
-
paragraphsWithStyle
|
|
392
|
-
end
|
|
393
|
-
|
|
394
|
-
end
|
|
395
|
-
end
|
|
1
|
+
module Asposewordsjavaforruby
|
|
2
|
+
module ExtractContent
|
|
3
|
+
def initialize()
|
|
4
|
+
# The path to the documents directory.
|
|
5
|
+
@data_dir = File.dirname(File.dirname(File.dirname(__FILE__))) + '/data/document/'
|
|
6
|
+
|
|
7
|
+
# Open the document.
|
|
8
|
+
doc = Rjb::import('com.aspose.words.Document').new(@data_dir + "TestFile.doc")
|
|
9
|
+
|
|
10
|
+
extract_content_between_paragraphs(doc)
|
|
11
|
+
extract_content_between_block_level_nodes(doc)
|
|
12
|
+
extract_content_between_paragraph_styles(doc)
|
|
13
|
+
extract_content_between_runs(doc)
|
|
14
|
+
extract_content_using_field(doc)
|
|
15
|
+
extract_content_between_bookmark(doc)
|
|
16
|
+
extract_content_between_comment_range(doc)
|
|
17
|
+
end
|
|
18
|
+
|
|
19
|
+
def extract_content_between_paragraphs(doc)
|
|
20
|
+
# Gather the nodes. The GetChild method uses 0-based index
|
|
21
|
+
node_type = Rjb::import("com.aspose.words.NodeType")
|
|
22
|
+
start_para = doc.getFirstSection().getChild(node_type.PARAGRAPH, 6, true)
|
|
23
|
+
end_para = doc.getFirstSection().getChild(node_type.PARAGRAPH, 10, true)
|
|
24
|
+
|
|
25
|
+
# Extract the content between these nodes in the document. Include these markers in the extraction.
|
|
26
|
+
extracted_nodes = extract_contents(start_para, end_para, true)
|
|
27
|
+
|
|
28
|
+
# Insert the content into a new separate document and save it to disk.
|
|
29
|
+
dst_doc = generate_document(doc, extracted_nodes)
|
|
30
|
+
dst_doc.save(@data_dir + "TestFile.Paragraphs Out.doc")
|
|
31
|
+
end
|
|
32
|
+
|
|
33
|
+
def extract_content_between_block_level_nodes(doc)
|
|
34
|
+
# Gather the nodes. The GetChild method uses 0-based index
|
|
35
|
+
node_type = Rjb::import("com.aspose.words.NodeType")
|
|
36
|
+
start_para = doc.getLastSection().getChild(node_type.PARAGRAPH, 2, true)
|
|
37
|
+
end_table = doc.getLastSection().getChild(node_type.TABLE, 0, true)
|
|
38
|
+
|
|
39
|
+
# Extract the content between these nodes in the document. Include these markers in the extraction.
|
|
40
|
+
extracted_nodes = extract_contents(start_para, end_table, true)
|
|
41
|
+
|
|
42
|
+
# Lets reverse the array to make inserting the content back into the document easier.
|
|
43
|
+
collections = Rjb::import("java.util.Collections")
|
|
44
|
+
collections.reverse(extracted_nodes)
|
|
45
|
+
|
|
46
|
+
while extracted_nodes.size() > 0 do
|
|
47
|
+
# Insert the last node from the reversed list
|
|
48
|
+
end_table.getParentNode().insertAfter(extracted_nodes.get(0), end_table)
|
|
49
|
+
# Remove this node from the list after insertion.
|
|
50
|
+
extracted_nodes.remove(0)
|
|
51
|
+
end
|
|
52
|
+
|
|
53
|
+
# Save the generated document to disk.
|
|
54
|
+
doc.save(@data_dir + "TestFile.DuplicatedContent Out.doc")
|
|
55
|
+
end
|
|
56
|
+
|
|
57
|
+
def extract_content_between_paragraph_styles(doc)
|
|
58
|
+
# Gather a list of the paragraphs using the respective heading styles.
|
|
59
|
+
paras_style_heading1 = paragraphs_by_style_name(doc, "Heading 1")
|
|
60
|
+
paras_style_heading3 = paragraphs_by_style_name(doc, "Heading 3")
|
|
61
|
+
|
|
62
|
+
# Use the first instance of the paragraphs with those styles.
|
|
63
|
+
start_para1 = paras_style_heading1.get(0)
|
|
64
|
+
end_para1 = paras_style_heading3.get(0)
|
|
65
|
+
|
|
66
|
+
# Extract the content between these nodes in the document. Don't include these markers in the extraction.
|
|
67
|
+
extracted_nodes = extract_contents(start_para1, end_para1, false)
|
|
68
|
+
|
|
69
|
+
# Insert the content into a new separate document and save it to disk.
|
|
70
|
+
dst_doc = generate_document(doc, extracted_nodes)
|
|
71
|
+
dst_doc.save(@data_dir + "TestFile.Styles Out.doc")
|
|
72
|
+
end
|
|
73
|
+
|
|
74
|
+
def extract_content_between_runs(doc)
|
|
75
|
+
# Retrieve a paragraph from the first section.
|
|
76
|
+
node_type = Rjb::import("com.aspose.words.NodeType")
|
|
77
|
+
para = doc.getChild(node_type.PARAGRAPH, 7, true)
|
|
78
|
+
|
|
79
|
+
# Use some runs for extraction.
|
|
80
|
+
start_run = para.getRuns().get(1)
|
|
81
|
+
end_run = para.getRuns().get(4)
|
|
82
|
+
|
|
83
|
+
# Extract the content between these nodes in the document. Include these markers in the extraction.
|
|
84
|
+
extracted_nodes = extract_contents(start_run, end_run, true)
|
|
85
|
+
|
|
86
|
+
# Get the node from the list. There should only be one paragraph returned in the list.
|
|
87
|
+
node = extracted_nodes.get(0)
|
|
88
|
+
|
|
89
|
+
# Print the text of this node to the console.
|
|
90
|
+
save_format = Rjb::import("com.aspose.words.SaveFormat")
|
|
91
|
+
puts node.toString(save_format.TEXT)
|
|
92
|
+
end
|
|
93
|
+
|
|
94
|
+
def extract_content_using_field(doc)
|
|
95
|
+
# Use a document builder to retrieve the field start of a merge field.
|
|
96
|
+
builder = Rjb::import("com.aspose.words.DocumentBuilder").new(doc)
|
|
97
|
+
|
|
98
|
+
# Pass the first boolean parameter to get the DocumentBuilder to move to the FieldStart of the field.
|
|
99
|
+
# We could also get FieldStarts of a field using GetChildNode method as in the other examples.
|
|
100
|
+
builder.moveToMergeField("Fullname", false, false)
|
|
101
|
+
|
|
102
|
+
#/ The builder cursor should be positioned at the start of the field.
|
|
103
|
+
node_type = Rjb::import("com.aspose.words.NodeType")
|
|
104
|
+
start_field = builder.getCurrentNode()
|
|
105
|
+
end_para = doc.getFirstSection().getChild(node_type.PARAGRAPH, 5, true)
|
|
106
|
+
|
|
107
|
+
# Extract the content between these nodes in the document. Don't include these markers in the extraction.
|
|
108
|
+
extracted_nodes = extract_contents(start_field, end_para, false)
|
|
109
|
+
|
|
110
|
+
# Insert the content into a new separate document and save it to disk.
|
|
111
|
+
dst_doc = generate_document(doc, extracted_nodes)
|
|
112
|
+
dst_doc.save(@data_dir + "TestFile.Fields Out.doc")
|
|
113
|
+
end
|
|
114
|
+
|
|
115
|
+
def extract_content_between_bookmark(doc)
|
|
116
|
+
# Retrieve the bookmark from the document.
|
|
117
|
+
bookmark = doc.getRange().getBookmarks().get("Bookmark1")
|
|
118
|
+
|
|
119
|
+
# We use the BookmarkStart and BookmarkEnd nodes as markers.
|
|
120
|
+
bookmark_start = bookmark.getBookmarkStart()
|
|
121
|
+
bookmark_end = bookmark.getBookmarkEnd()
|
|
122
|
+
|
|
123
|
+
# Firstly extract the content between these nodes including the bookmark.
|
|
124
|
+
extracted_nodes_inclusive = extract_contents(bookmark_start, bookmark_end, true)
|
|
125
|
+
dst_doc = generate_document(doc, extracted_nodes_inclusive)
|
|
126
|
+
dst_doc.save(@data_dir + "TestFile.BookmarkInclusive Out.doc")
|
|
127
|
+
|
|
128
|
+
# Secondly extract the content between these nodes this time without including the bookmark.
|
|
129
|
+
extracted_nodes_exclusive = extract_contents(bookmark_start, bookmark_end, false)
|
|
130
|
+
dst_doc = generate_document(doc, extracted_nodes_exclusive)
|
|
131
|
+
dst_doc.save(@data_dir + "TestFile.BookmarkExclusive Out.doc")
|
|
132
|
+
end
|
|
133
|
+
|
|
134
|
+
def extract_content_between_comment_range(doc)
|
|
135
|
+
# This is a quick way of getting both comment nodes.
|
|
136
|
+
# Your code should have a proper method of retrieving each corresponding start and end node.
|
|
137
|
+
node_type = Rjb::import("com.aspose.words.NodeType")
|
|
138
|
+
comment_start = doc.getChild(node_type.COMMENT_RANGE_START, 0, true)
|
|
139
|
+
comment_end = doc.getChild(node_type.COMMENT_RANGE_END, 0, true)
|
|
140
|
+
|
|
141
|
+
# Firstly extract the content between these nodes including the bookmark.
|
|
142
|
+
extracted_nodes_inclusive = extract_contents(comment_start, comment_end, true)
|
|
143
|
+
dst_doc = generate_document(doc, extracted_nodes_inclusive)
|
|
144
|
+
dst_doc.save(@data_dir + "TestFile.CommentInclusive Out.doc")
|
|
145
|
+
|
|
146
|
+
# Secondly extract the content between these nodes this time without including the bookmark.
|
|
147
|
+
extracted_nodes_exclusive = extract_contents(comment_start, comment_end, false)
|
|
148
|
+
dst_doc = generate_document(doc, extracted_nodes_exclusive)
|
|
149
|
+
dst_doc.save(@data_dir + "TestFile.CommentExclusive Out.doc")
|
|
150
|
+
end
|
|
151
|
+
|
|
152
|
+
=begin
|
|
153
|
+
This is a method which extracts blocks of content from a document between specified nodes.
|
|
154
|
+
|
|
155
|
+
Extracts a range of nodes from a document found between specified markers and returns a copy of those nodes. Content can be extracted
|
|
156
|
+
between inline nodes, block level nodes, and also special nodes such as Comment or Boomarks. Any combination of different marker types can used.
|
|
157
|
+
|
|
158
|
+
@param string startNode The node which defines where to start the extraction from the document. This node can be block or inline level of a body.
|
|
159
|
+
@param string endNode The node which defines where to stop the extraction from the document. This node can be block or inline level of body.
|
|
160
|
+
@param boolean isInclusive Should the marker nodes be included.
|
|
161
|
+
=end
|
|
162
|
+
def extract_contents(startNode, endNode, isInclusive)
|
|
163
|
+
# First check that the nodes passed to this method are valid for use.
|
|
164
|
+
verify_parameter_nodes(startNode, endNode)
|
|
165
|
+
|
|
166
|
+
# Create a list to store the extracted nodes.
|
|
167
|
+
nodes = Rjb::import("java.util.ArrayList").new
|
|
168
|
+
|
|
169
|
+
# Keep a record of the original nodes passed to this method so we can split marker nodes if needed.
|
|
170
|
+
originalStartNode = startNode
|
|
171
|
+
originalEndNode = endNode
|
|
172
|
+
|
|
173
|
+
# Extract content based on block level nodes (paragraphs and tables). Traverse through parent nodes to find them.
|
|
174
|
+
# We will split the content of first and last nodes depending if the marker nodes are inline
|
|
175
|
+
node_type = Rjb::import("com.aspose.words.NodeType")
|
|
176
|
+
|
|
177
|
+
while (startNode.getParentNode().getNodeType() != node_type.BODY) do
|
|
178
|
+
startNode = startNode.getParentNode()
|
|
179
|
+
end
|
|
180
|
+
|
|
181
|
+
while (endNode.getParentNode().getNodeType() != node_type.BODY) do
|
|
182
|
+
endNode = endNode.getParentNode()
|
|
183
|
+
end
|
|
184
|
+
|
|
185
|
+
isExtracting = true
|
|
186
|
+
isStartingNode = true
|
|
187
|
+
isEndingNode = ''
|
|
188
|
+
#The current node we are extracting from the document.
|
|
189
|
+
currNode = startNode
|
|
190
|
+
|
|
191
|
+
#Begin extracting content. Process all block level nodes and specifically split the first and last nodes when needed so paragraph formatting is retained.
|
|
192
|
+
# Method is little more complex than a regular extractor as we need to factor in extracting using inline nodes, fields, bookmarks etc as to make it really useful.
|
|
193
|
+
while (isExtracting) do
|
|
194
|
+
# Clone the current node and its children to obtain a copy.
|
|
195
|
+
cloneNode = currNode.deepClone(true)
|
|
196
|
+
isEndingNode = currNode.equals(endNode)
|
|
197
|
+
|
|
198
|
+
if (isStartingNode || isEndingNode) then
|
|
199
|
+
# We need to process each marker separately so pass it off to a separate method instead.
|
|
200
|
+
if (isStartingNode) then
|
|
201
|
+
process_marker(cloneNode, nodes, originalStartNode, isInclusive, isStartingNode, isEndingNode)
|
|
202
|
+
isStartingNode = false
|
|
203
|
+
end
|
|
204
|
+
# Conditional needs to be separate as the block level start and end markers maybe the same node.
|
|
205
|
+
if (isEndingNode) then
|
|
206
|
+
process_marker(cloneNode, nodes, originalEndNode, isInclusive, isStartingNode, isEndingNode)
|
|
207
|
+
isExtracting = false
|
|
208
|
+
end
|
|
209
|
+
else
|
|
210
|
+
# Node is not a start or end marker, simply add the copy to the list.
|
|
211
|
+
nodes.add(cloneNode)
|
|
212
|
+
end
|
|
213
|
+
|
|
214
|
+
# Move to the next node and extract it. If next node is null that means the rest of the content is found in a different section.
|
|
215
|
+
#if (currNode.getNextSibling() == null && isExtracting) then
|
|
216
|
+
if ((currNode.getNextSibling()).nil? && isExtracting) then
|
|
217
|
+
# Move to the next section.
|
|
218
|
+
nodeType = Rjb::import("com.aspose.words.NodeType")
|
|
219
|
+
nextSection = currNode.getAncestor(nodeType.SECTION).getNextSibling()
|
|
220
|
+
currNode = nextSection.getBody().getFirstChild()
|
|
221
|
+
else
|
|
222
|
+
# Move to the next node in the body.
|
|
223
|
+
currNode = currNode.getNextSibling()
|
|
224
|
+
end
|
|
225
|
+
end
|
|
226
|
+
# Return the nodes between the node markers.
|
|
227
|
+
nodes
|
|
228
|
+
end
|
|
229
|
+
|
|
230
|
+
=begin
|
|
231
|
+
Checks the input parameters are correct and can be used. Throws an exception if there is any problem.
|
|
232
|
+
=end
|
|
233
|
+
def verify_parameter_nodes(startNode, endNode)
|
|
234
|
+
# The order in which these checks are done is important.
|
|
235
|
+
raise 'Start node cannot be null' if startNode.nil?
|
|
236
|
+
raise 'End node cannot be null' if endNode.nil?
|
|
237
|
+
raise "Start node and end node must belong to the same document" if (startNode.getDocument() == endNode.getDocument())
|
|
238
|
+
|
|
239
|
+
nodeType = Rjb::import("com.aspose.words.NodeType")
|
|
240
|
+
#raise "Start node and end node must be a child or descendant of a body" if (startNode.getAncestor(nodeType.BODY) == '' || endNode.getAncestor(nodeType.BODY) == '')
|
|
241
|
+
raise "Start node and end node must be a child or descendant of a body" if (startNode.getAncestor(nodeType.BODY).nil? || endNode.getAncestor(nodeType.BODY).nil?)
|
|
242
|
+
|
|
243
|
+
# Check the end node is after the start node in the DOM tree
|
|
244
|
+
# First check if they are in different sections, then if they're not check their position in the body of the same section they are in.
|
|
245
|
+
startSection = startNode.getAncestor(nodeType.SECTION)
|
|
246
|
+
endSection = endNode.getAncestor(nodeType.SECTION)
|
|
247
|
+
startIndex = startSection.getParentNode().indexOf(startSection)
|
|
248
|
+
endIndex = endSection.getParentNode().indexOf(endSection)
|
|
249
|
+
|
|
250
|
+
if (startIndex == endIndex) then
|
|
251
|
+
raise "The end node must be after the start node in the body" if (startSection.getBody().indexOf(startNode) > endSection.getBody().indexOf(endNode))
|
|
252
|
+
elsif (startIndex > endIndex) then
|
|
253
|
+
raise "The section of end node must be after the section start node"
|
|
254
|
+
end
|
|
255
|
+
end
|
|
256
|
+
|
|
257
|
+
def generate_document(src_doc, nodes)
|
|
258
|
+
# Create a blank document.
|
|
259
|
+
dst_doc = Rjb::import("com.aspose.words.Document").new
|
|
260
|
+
|
|
261
|
+
# Remove the first paragraph from the empty document.
|
|
262
|
+
dst_doc.getFirstSection().getBody().removeAllChildren()
|
|
263
|
+
|
|
264
|
+
# Import each node from the list into the new document. Keep the original formatting of the node.
|
|
265
|
+
import_format_mode = Rjb::import("com.aspose.words.ImportFormatMode")
|
|
266
|
+
importer = Rjb::import("com.aspose.words.NodeImporter").new(src_doc, dst_doc, import_format_mode.KEEP_SOURCE_FORMATTING)
|
|
267
|
+
|
|
268
|
+
i = 0
|
|
269
|
+
while i < nodes.size
|
|
270
|
+
node = nodes.get(i)
|
|
271
|
+
import_node = importer.importNode(node, true)
|
|
272
|
+
dst_doc.getFirstSection().getBody().appendChild(import_node)
|
|
273
|
+
i +=1
|
|
274
|
+
end
|
|
275
|
+
|
|
276
|
+
# Return the generated document.
|
|
277
|
+
dst_doc
|
|
278
|
+
end
|
|
279
|
+
|
|
280
|
+
def process_marker(cloneNode, nodes, node, isInclusive, isStartMarker, isEndMarker)
|
|
281
|
+
# If we are dealing with a block level node just see if it should be included and add it to the list.
|
|
282
|
+
if (!is_inline(node)) then
|
|
283
|
+
# Don't add the node twice if the markers are the same node
|
|
284
|
+
if(!(isStartMarker && isEndMarker)) then
|
|
285
|
+
if (isInclusive) then
|
|
286
|
+
nodes.add(cloneNode)
|
|
287
|
+
end
|
|
288
|
+
end
|
|
289
|
+
return
|
|
290
|
+
end
|
|
291
|
+
|
|
292
|
+
# If a marker is a FieldStart node check if it's to be included or not.
|
|
293
|
+
# We assume for simplicity that the FieldStart and FieldEnd appear in the same paragraph.
|
|
294
|
+
nodeType = Rjb::import("com.aspose.words.NodeType")
|
|
295
|
+
if (node.getNodeType() == nodeType.FIELD_START) then
|
|
296
|
+
# If the marker is a start node and is not be included then skip to the end of the field.
|
|
297
|
+
# If the marker is an end node and it is to be included then move to the end field so the field will not be removed.
|
|
298
|
+
#if ((isStartMarker && !isInclusive) || (!isStartMarker && isInclusive)) then
|
|
299
|
+
if ((isStartMarker && isInclusive.nil?) || (!isStartMarker && isInclusive)) then
|
|
300
|
+
#while (node.getNextSibling() != null && node.getNodeType() != nodeType.FIELD_END) do
|
|
301
|
+
while (node.getNextSibling().nil? && (node.getNodeType() != nodeType.FIELD_END)) do
|
|
302
|
+
node = node.getNextSibling()
|
|
303
|
+
end
|
|
304
|
+
end
|
|
305
|
+
end
|
|
306
|
+
|
|
307
|
+
# If either marker is part of a comment then to include the comment itself we need to move the pointer forward to the Comment
|
|
308
|
+
# node found after the CommentRangeEnd node.
|
|
309
|
+
if (node.getNodeType() == nodeType.COMMENT_RANGE_END) then
|
|
310
|
+
while (node.getNextSibling().nil? && (node.getNodeType() != nodeType.COMMENT)) do
|
|
311
|
+
node = node.getNextSibling()
|
|
312
|
+
end
|
|
313
|
+
end
|
|
314
|
+
|
|
315
|
+
# Find the corresponding node in our cloned node by index and return it.
|
|
316
|
+
# If the start and end node are the same some child nodes might already have been removed. Subtract the
|
|
317
|
+
# difference to get the right index.
|
|
318
|
+
indexDiff = (node.getParentNode().getChildNodes().getCount() - cloneNode.getChildNodes().getCount())
|
|
319
|
+
|
|
320
|
+
# Child node count identical.
|
|
321
|
+
if (indexDiff == 0) then
|
|
322
|
+
node = cloneNode.getChildNodes().get(node.getParentNode().indexOf(node))
|
|
323
|
+
else
|
|
324
|
+
node = cloneNode.getChildNodes().get(node.getParentNode().indexOf(node) - indexDiff)
|
|
325
|
+
end
|
|
326
|
+
|
|
327
|
+
# Remove the nodes up to/from the marker.
|
|
328
|
+
isSkip = ''
|
|
329
|
+
isProcessing = true
|
|
330
|
+
isRemoving = isStartMarker
|
|
331
|
+
nextNode = cloneNode.getFirstChild()
|
|
332
|
+
#while (isProcessing && nextNode != null) do
|
|
333
|
+
unless (isProcessing && nextNode.nil?)
|
|
334
|
+
currentNode = nextNode
|
|
335
|
+
isSkip = false
|
|
336
|
+
if (currentNode == node) then
|
|
337
|
+
if (isStartMarker) then
|
|
338
|
+
isProcessing = false
|
|
339
|
+
if isInclusive then
|
|
340
|
+
isRemoving = false
|
|
341
|
+
end
|
|
342
|
+
else
|
|
343
|
+
isRemoving = true
|
|
344
|
+
if isInclusive then
|
|
345
|
+
isSkip = true
|
|
346
|
+
end
|
|
347
|
+
end
|
|
348
|
+
end
|
|
349
|
+
nextNode = nextNode.getNextSibling()
|
|
350
|
+
#if (isRemoving && !isSkip) then
|
|
351
|
+
if (isRemoving && isSkip==false) then
|
|
352
|
+
currentNode.remove()
|
|
353
|
+
end
|
|
354
|
+
end
|
|
355
|
+
|
|
356
|
+
# After processing the composite node may become empty. If it has don't include it.
|
|
357
|
+
if (!(isStartMarker && isEndMarker)) then
|
|
358
|
+
if cloneNode.hasChildNodes() then
|
|
359
|
+
nodes.add(cloneNode)
|
|
360
|
+
end
|
|
361
|
+
end
|
|
362
|
+
end
|
|
363
|
+
|
|
364
|
+
def is_inline(node)
|
|
365
|
+
# Test if the node is desendant of a Paragraph or Table node and also is not a paragraph or a table a paragraph inside a comment class which is decesant of a pararaph is possible.
|
|
366
|
+
node_type = Rjb::import("com.aspose.words.NodeType")
|
|
367
|
+
#return ((node.getAncestor(node_type.PARAGRAPH) != null) || (node.getAncestor(node_type.TABLE) != null) && !(node.getNodeType() == nodeType.PARAGRAPH) || (node.getNodeType() == nodeType.TABLE))
|
|
368
|
+
return ((node.getAncestor(node_type.PARAGRAPH).nil?) || (node.getAncestor(node_type.TABLE).nil?) && !(node.getNodeType() == node_type.PARAGRAPH) || (node.getNodeType() == node_type.TABLE))
|
|
369
|
+
end
|
|
370
|
+
|
|
371
|
+
def paragraphs_by_style_name(doc, style_name)
|
|
372
|
+
# Create an array to collect paragraphs of the specified style.
|
|
373
|
+
paragraphsWithStyle = Rjb::import("java.util.ArrayList").new
|
|
374
|
+
|
|
375
|
+
# Get all paragraphs from the document.
|
|
376
|
+
node_type = Rjb::import("com.aspose.words.NodeType")
|
|
377
|
+
paragraphs = doc.getChildNodes(node_type.PARAGRAPH, true)
|
|
378
|
+
paragraphs_count = paragraphs.getCount()
|
|
379
|
+
#paragraphs_count = java_values($paragraphs_count)
|
|
380
|
+
|
|
381
|
+
# Look through all paragraphs to find those with the specified style.
|
|
382
|
+
i = 0
|
|
383
|
+
while (i < paragraphs_count) do
|
|
384
|
+
paragraphs = doc.getChildNodes(node_type.PARAGRAPH, true)
|
|
385
|
+
paragraph = paragraphs.get(i)
|
|
386
|
+
if (paragraph.getParagraphFormat().getStyle().getName() == style_name) then
|
|
387
|
+
paragraphsWithStyle.add(paragraph)
|
|
388
|
+
end
|
|
389
|
+
i = i + 1
|
|
390
|
+
end
|
|
391
|
+
paragraphsWithStyle
|
|
392
|
+
end
|
|
393
|
+
|
|
394
|
+
end
|
|
395
|
+
end
|